commit b8ae30ee26d379db436b0b8c8c3ff1b52f69e5d1
author Linus Torvalds <torvalds@linux-foundation.org> Tue May 18 08:27:54 2010 -0700
committer Linus Torvalds <torvalds@linux-foundation.org> Tue May 18 08:27:54 2010 -0700
tree 506aa0b4bdbf90f61e7e9261c7db90aa1452dcce
parent 4d7b4ac22fbec1a03206c6cde353f2fd6942f828
parent 9c6f7e43b4e02c161b53e97ba913855246876c61

Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (49 commits)
  stop_machine: Move local variable closer to the usage site in cpu_stop_cpu_callback()
  sched, wait: Use wrapper functions
  sched: Remove a stale comment
  ondemand: Make the iowait-is-busy time a sysfs tunable
  ondemand: Solve a big performance issue by counting IOWAIT time as busy
  sched: Intoduce get_cpu_iowait_time_us()
  sched: Eliminate the ts->idle_lastupdate field
  sched: Fold updating of the last_update_time_info into update_ts_time_stats()
  sched: Update the idle statistics in get_cpu_idle_time_us()
  sched: Introduce a function to update the idle statistics
  sched: Add a comment to get_cpu_idle_time_us()
  cpu_stop: add dummy implementation for UP
  sched: Remove rq argument to the tracepoints
  rcu: need barrier() in UP synchronize_sched_expedited()
  sched: correctly place paranioa memory barriers in synchronize_sched_expedited()
  sched: kill paranoia check in synchronize_sched_expedited()
  sched: replace migration_thread with cpu_stop
  stop_machine: reimplement using cpu_stop
  cpu_stop: implement stop_cpu[s]()
  sched: Fix select_idle_sibling() logic in select_task_rq_fair()
  ...

Documentation/DocBook/libata.tmpl

diff --git a/Documentation/DocBook/libata.tmpl b/Documentation/DocBook/libata.tmpl
index ba99757..ff3e5be 100644
--- a/Documentation/DocBook/libata.tmpl
+++ b/Documentation/DocBook/libata.tmpl
@@ -107,10 +107,6 @@
 	issue of SET FEATURES - XFER MODE, and prior to operation.
 	</para>
 	<para>
-	Called by ata_device_add() after ata_dev_identify() determines
-	a device is present.
-	</para>
-	<para>
 	This entry may be specified as NULL in ata_port_operations.
 	</para>
 
@@ -154,8 +150,8 @@
 
 	<sect2><title>Taskfile read/write</title>
 	<programlisting>
-void (*tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
-void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
 	</programlisting>
 
 	<para>
@@ -164,36 +160,35 @@
 	hardware registers / DMA buffers, to obtain the current set of
 	taskfile register values.
 	Most drivers for taskfile-based hardware (PIO or MMIO) use
-	ata_tf_load() and ata_tf_read() for these hooks.
+	ata_sff_tf_load() and ata_sff_tf_read() for these hooks.
 	</para>
 
 	</sect2>
 
 	<sect2><title>PIO data read/write</title>
 	<programlisting>
-void (*data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
+void (*sff_data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
 	</programlisting>
 
 	<para>
 All bmdma-style drivers must implement this hook.  This is the low-level
 operation that actually copies the data bytes during a PIO data
 transfer.
-Typically the driver
-will choose one of ata_pio_data_xfer_noirq(), ata_pio_data_xfer(), or
-ata_mmio_data_xfer().
+Typically the driver will choose one of ata_sff_data_xfer_noirq(),
+ata_sff_data_xfer(), or ata_sff_data_xfer32().
 	</para>
 
 	</sect2>
 
 	<sect2><title>ATA command execute</title>
 	<programlisting>
-void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
 	</programlisting>
 
 	<para>
 	causes an ATA command, previously loaded with
 	->tf_load(), to be initiated in hardware.
-	Most drivers for taskfile-based hardware use ata_exec_command()
+	Most drivers for taskfile-based hardware use ata_sff_exec_command()
 	for this hook.
 	</para>
 
@@ -218,8 +213,8 @@
 
 	<sect2><title>Read specific ATA shadow registers</title>
 	<programlisting>
-u8   (*check_status)(struct ata_port *ap);
-u8   (*check_altstatus)(struct ata_port *ap);
+u8   (*sff_check_status)(struct ata_port *ap);
+u8   (*sff_check_altstatus)(struct ata_port *ap);
 	</programlisting>
 
 	<para>
@@ -227,20 +222,14 @@
 	hardware.  On some hardware, reading the Status register has
 	the side effect of clearing the interrupt condition.
 	Most drivers for taskfile-based hardware use
-	ata_check_status() for this hook.
-	</para>
-	<para>
-	Note that because this is called from ata_device_add(), at
-	least a dummy function that clears device interrupts must be
-	provided for all drivers, even if the controller doesn't
-	actually have a taskfile status register.
+	ata_sff_check_status() for this hook.
 	</para>
 
 	</sect2>
 
 	<sect2><title>Select ATA device on bus</title>
 	<programlisting>
-void (*dev_select)(struct ata_port *ap, unsigned int device);
+void (*sff_dev_select)(struct ata_port *ap, unsigned int device);
 	</programlisting>
 
 	<para>
@@ -251,9 +240,7 @@
 	</para>
 	<para>
 	Most drivers for taskfile-based hardware use
-	ata_std_dev_select() for this hook.  Controllers which do not
-	support second drives on a port (such as SATA contollers) will
-	use ata_noop_dev_select().
+	ata_sff_dev_select() for this hook.
 	</para>
 
 	</sect2>
@@ -441,13 +428,13 @@
 	to struct ata_host_set.
 	</para>
 	<para>
-	Most legacy IDE drivers use ata_interrupt() for the
+	Most legacy IDE drivers use ata_sff_interrupt() for the
 	irq_handler hook, which scans all ports in the host_set,
 	determines which queued command was active (if any), and calls
-	ata_host_intr(ap,qc).
+	ata_sff_host_intr(ap,qc).
 	</para>
 	<para>
-	Most legacy IDE drivers use ata_bmdma_irq_clear() for the
+	Most legacy IDE drivers use ata_sff_irq_clear() for the
 	irq_clear() hook, which simply clears the interrupt and error
 	flags in the DMA status register.
 	</para>
@@ -496,10 +483,6 @@
 	data from port at this time.
 	</para>
 	<para>
-	Many drivers use ata_port_stop() as this hook, which frees the
-	PRD table.
-	</para>
-	<para>
 	->host_stop() is called after all ->port_stop() calls
 have completed.  The hook must finalize hardware shutdown, release DMA
 and other resources, etc.

Documentation/RCU/stallwarn.txt

diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 1423d25..44c6dcc 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -3,35 +3,79 @@
 The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables
 RCU's CPU stall detector, which detects conditions that unduly delay
 RCU grace periods.  The stall detector's idea of what constitutes
-"unduly delayed" is controlled by a pair of C preprocessor macros:
+"unduly delayed" is controlled by a set of C preprocessor macros:
 
 RCU_SECONDS_TILL_STALL_CHECK
 
 	This macro defines the period of time that RCU will wait from
 	the beginning of a grace period until it issues an RCU CPU
-	stall warning.	It is normally ten seconds.
+	stall warning.	This time period is normally ten seconds.
 
 RCU_SECONDS_TILL_STALL_RECHECK
 
 	This macro defines the period of time that RCU will wait after
-	issuing a stall warning until it issues another stall warning.
-	It is normally set to thirty seconds.
+	issuing a stall warning until it issues another stall warning
+	for the same stall.  This time period is normally set to thirty
+	seconds.
 
 RCU_STALL_RAT_DELAY
 
-	The CPU stall detector tries to make the offending CPU rat on itself,
-	as this often gives better-quality stack traces.  However, if
-	the offending CPU does not detect its own stall in the number
-	of jiffies specified by RCU_STALL_RAT_DELAY, then other CPUs will
-	complain.  This is normally set to two jiffies.
+	The CPU stall detector tries to make the offending CPU print its
+	own warnings, as this often gives better-quality stack traces.
+	However, if the offending CPU does not detect its own stall in
+	the number of jiffies specified by RCU_STALL_RAT_DELAY, then
+	some other CPU will complain.  This delay is normally set to
+	two jiffies.
 
-The following problems can result in an RCU CPU stall warning:
+When a CPU detects that it is stalling, it will print a message similar
+to the following:
+
+INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies)
+
+This message indicates that CPU 5 detected that it was causing a stall,
+and that the stall was affecting RCU-sched.  This message will normally be
+followed by a stack dump of the offending CPU.  On TREE_RCU kernel builds,
+RCU and RCU-sched are implemented by the same underlying mechanism,
+while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented
+by rcu_preempt_state.
+
+On the other hand, if the offending CPU fails to print out a stall-warning
+message quickly enough, some other CPU will print a message similar to
+the following:
+
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 jiffies)
+
+This message indicates that CPU 2 detected that CPUs 3 and 5 were both
+causing stalls, and that the stall was affecting RCU-bh.  This message
+will normally be followed by stack dumps for each CPU.  Please note that
+TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs,
+and that the tasks will be indicated by PID, for example, "P3421".
+It is even possible for a rcu_preempt_state stall to be caused by both
+CPUs -and- tasks, in which case the offending CPUs and tasks will all
+be called out in the list.
+
+Finally, if the grace period ends just as the stall warning starts
+printing, there will be a spurious stall-warning message:
+
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies)
+
+This is rare, but does happen from time to time in real life.
+
+So your kernel printed an RCU CPU stall warning.  The next question is
+"What caused it?"  The following problems can result in RCU CPU stall
+warnings:
 
 o	A CPU looping in an RCU read-side critical section.
 	
-o	A CPU looping with interrupts disabled.
+o	A CPU looping with interrupts disabled.  This condition can
+	result in RCU-sched and RCU-bh stalls.
 
-o	A CPU looping with preemption disabled.
+o	A CPU looping with preemption disabled.  This condition can
+	result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
+	stalls.
+
+o	A CPU looping with bottom halves disabled.  This condition can
+	result in RCU-sched and RCU-bh stalls.
 
 o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
 	without invoking schedule().
@@ -39,20 +83,24 @@
 o	A bug in the RCU implementation.
 
 o	A hardware failure.  This is quite unlikely, but has occurred
-	at least once in a former life.  A CPU failed in a running system,
+	at least once in real life.  A CPU failed in a running system,
 	becoming unresponsive, but not causing an immediate crash.
 	This resulted in a series of RCU CPU stall warnings, eventually
 	leading the realization that the CPU had failed.
 
-The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning.
-SRCU does not do so directly, but its calls to synchronize_sched() will
-result in RCU-sched detecting any CPU stalls that might be occurring.
+The RCU, RCU-sched, and RCU-bh implementations have CPU stall
+warning.  SRCU does not have its own CPU stall warnings, but its
+calls to synchronize_sched() will result in RCU-sched detecting
+RCU-sched-related CPU stalls.  Please note that RCU only detects
+CPU stalls when there is a grace period in progress.  No grace period,
+no CPU stall warnings.
 
-To diagnose the cause of the stall, inspect the stack traces.  The offending
-function will usually be near the top of the stack.  If you have a series
-of stall warnings from a single extended stall, comparing the stack traces
-can often help determine where the stall is occurring, which will usually
-be in the function nearest the top of the stack that stays the same from
-trace to trace.
+To diagnose the cause of the stall, inspect the stack traces.
+The offending function will usually be near the top of the stack.
+If you have a series of stall warnings from a single extended stall,
+comparing the stack traces can often help determine where the stall
+is occurring, which will usually be in the function nearest the top of
+that portion of the stack which remains the same from trace to trace.
+If you can reliably trigger the stall, ftrace can be quite helpful.
 
 RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE.

Documentation/RCU/trace.txt

diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 8608fd8..efd8cc9 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -256,23 +256,23 @@
 The output of "cat rcu/rcu_pending" looks as follows:
 
 rcu_sched:
-  0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
-  1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
-  2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
-  3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
-  4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
-  5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
-  6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
-  7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+  0 np=255892 qsp=53936 rpq=85 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+  1 np=261224 qsp=54638 rpq=33 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+  2 np=237496 qsp=49664 rpq=23 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+  3 np=236249 qsp=48766 rpq=98 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+  4 np=221310 qsp=46850 rpq=7 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+  5 np=237332 qsp=48449 rpq=9 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+  6 np=219995 qsp=46718 rpq=12 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+  7 np=249893 qsp=49390 rpq=42 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
 rcu_bh:
-  0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
-  1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
-  2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
-  3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
-  4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
-  5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
-  6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
-  7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+  0 np=146741 qsp=1419 rpq=6 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+  1 np=155792 qsp=12597 rpq=3 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+  2 np=136629 qsp=18680 rpq=1 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+  3 np=137723 qsp=2843 rpq=0 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+  4 np=123110 qsp=12433 rpq=0 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+  5 np=137456 qsp=4210 rpq=1 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+  6 np=120834 qsp=9902 rpq=2 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+  7 np=144888 qsp=26336 rpq=0 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
 
 As always, this is once again split into "rcu_sched" and "rcu_bh"
 portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional
@@ -284,6 +284,9 @@
 o	"qsp" is the number of times that the RCU was waiting for a
 	quiescent state from this CPU.
 
+o	"rpq" is the number of times that the CPU had passed through
+	a quiescent state, but not yet reported it to RCU.
+
 o	"cbr" is the number of times that this CPU had RCU callbacks
 	that had passed through a grace period, and were thus ready
 	to be invoked.

Documentation/feature-removal-schedule.txt

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index ed511af..05df0b7 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -589,3 +589,26 @@
 	Generally invoked by accident today.
 	Seen as doing more harm than good.
 Who:	Len Brown <len.brown@intel.com>
+
+----------------------------
+
+What:	video4linux /dev/vtx teletext API support
+When:	2.6.35
+Files:	drivers/media/video/saa5246a.c drivers/media/video/saa5249.c
+	include/linux/videotext.h
+Why:	The vtx device nodes have been superseded by vbi device nodes
+	for many years. No applications exist that use the vtx support.
+	Of the two i2c drivers that actually support this API the saa5249
+	has been impossible to use for a year now and no known hardware
+	that supports this device exists. The saa5246a is theoretically
+	supported by the old mxb boards, but it never actually worked.
+
+	In summary: there is no hardware that can use this API and there
+	are no applications actually implementing this API.
+
+	The vtx support still reserves minors 192-223 and we would really
+	like to reuse those for upcoming new functionality. In the unlikely
+	event that new hardware appears that wants to use the functionality
+	provided by the vtx API, then that functionality should be build
+	around the sliced VBI API instead.
+Who:	Hans Verkuil <hverkuil@xs4all.nl>

Documentation/filesystems/proc.txt

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index a4f30fa..1e359b6 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -316,7 +316,7 @@
 08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0          [threadstack:001ff4b4]
+a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
 a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
@@ -352,7 +352,6 @@
  [stack]                  = the stack of the main process
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
- [threadstack:xxxxxxxx]   = the stack of the thread, xxxxxxxx is the stack size
 
  or if empty, the mapping is anonymous.
 

Documentation/i2c/writing-clients

diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients
index 3219ee0..5ebf5af 100644
--- a/Documentation/i2c/writing-clients
+++ b/Documentation/i2c/writing-clients
@@ -74,6 +74,11 @@
 	/* retrieve the value */
 	void *i2c_get_clientdata(const struct i2c_client *client);
 
+Note that starting with kernel 2.6.34, you don't have to set the `data' field
+to NULL in remove() or if probe() failed anymore. The i2c-core does this
+automatically on these occasions. Those are also the only times the core will
+touch this field.
+
 
 Accessing the client
 ====================

Documentation/input/elantech.txt

diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt
index a10c3b6..56941ae 100644
--- a/Documentation/input/elantech.txt
+++ b/Documentation/input/elantech.txt
@@ -333,14 +333,14 @@
 byte 1:
 
    bit   7   6   5   4   3   2   1   0
-        x15 x14 x13 x12 x11 x10 x9  x8
+         .   .   .   .   .  x10 x9  x8
 
 byte 2:
 
    bit   7   6   5   4   3   2   1   0
         x7  x6  x5  x4  x4  x2  x1  x0
 
-         x15..x0 = absolute x value (horizontal)
+         x10..x0 = absolute x value (horizontal)
 
 byte 3:
 
@@ -350,14 +350,14 @@
 byte 4:
 
    bit   7   6   5   4   3   2   1   0
-        y15 y14 y13 y12 y11 y10 y8  y8
+         .   .   .   .   .   .  y9  y8
 
 byte 5:
 
    bit   7   6   5   4   3   2   1   0
         y7  y6  y5  y4  y3  y2  y1  y0
 
-         y15..y0 = absolute y value (vertical)
+         y9..y0 = absolute y value (vertical)
 
 
 4.2.2 Two finger touch

Documentation/kernel-parameters.txt

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 839b21b..0c6c560 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -324,6 +324,8 @@
 				    they are unmapped. Otherwise they are
 				    flushed before they will be reused, which
 				    is a lot of faster
+			off	  - do not initialize any AMD IOMMU found in
+				    the system
 
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT

Documentation/kprobes.txt

diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 2f9115c..61c291c 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -165,8 +165,8 @@
 
 1.4 How Does Jump Optimization Work?
 
-If you configured your kernel with CONFIG_OPTPROBES=y (currently
-this option is supported on x86/x86-64, non-preemptive kernel) and
+If your kernel is built with CONFIG_OPTPROBES=y (currently this flag
+is automatically set 'y' on x86/x86-64, non-preemptive kernel) and
 the "debug.kprobes_optimization" kernel parameter is set to 1 (see
 sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
 instruction instead of a breakpoint instruction at each probepoint.
@@ -271,8 +271,6 @@
 using one of the following techniques:
 - Specify an empty function for the kprobe's post_handler or break_handler.
  or
-- Config CONFIG_OPTPROBES=n.
- or
 - Execute 'sysctl -w debug.kprobes_optimization=n'
 
 2. Architectures Supported
@@ -307,10 +305,6 @@
 so you can use "objdump -d -l vmlinux" to see the source-to-object
 code mapping.
 
-If you want to reduce probing overhead, set "Kprobes jump optimization
-support" (CONFIG_OPTPROBES) to "y". You can find this option under the
-"Kprobes" line.
-
 4. API Reference
 
 The Kprobes API includes a "register" function and an "unregister"

Documentation/spi/spidev_test.c

diff --git a/Documentation/spi/spidev_test.c b/Documentation/spi/spidev_test.c
index 10abd37..16feda9 100644
--- a/Documentation/spi/spidev_test.c
+++ b/Documentation/spi/spidev_test.c
@@ -58,7 +58,7 @@
 	};
 
 	ret = ioctl(fd, SPI_IOC_MESSAGE(1), &tr);
-	if (ret == 1)
+	if (ret < 1)
 		pabort("can't send spi message");
 
 	for (ret = 0; ret < ARRAY_SIZE(tx); ret++) {

Documentation/trace/kprobetrace.txt

diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index a9100b2..ec94748 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -40,7 +40,9 @@
   $stack	: Fetch stack address.
   $retval	: Fetch return value.(*)
   +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
-  NAME=FETCHARG: Set NAME as the argument name of FETCHARG.
+  NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
+  FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
+		  (u8/u16/u32/u64/s8/s16/s32/s64) are supported.
 
   (*) only for return probe.
   (**) this is useful for fetching a field of data structures.

MAINTAINERS

diff --git a/MAINTAINERS b/MAINTAINERS
index d5b0b1b..28332e1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4165,6 +4165,7 @@
 M:	Robert Richter <robert.richter@amd.com>
 L:	oprofile-list@lists.sf.net
 S:	Maintained
+F:	arch/*/include/asm/oprofile*.h
 F:	arch/*/oprofile/
 F:	drivers/oprofile/
 F:	include/linux/oprofile.h
@@ -4353,13 +4354,13 @@
 M:	Ingo Molnar <mingo@elte.hu>
 M:	Arnaldo Carvalho de Melo <acme@redhat.com>
 S:	Supported
-F:	kernel/perf_event.c
+F:	kernel/perf_event*.c
 F:	include/linux/perf_event.h
-F:	arch/*/kernel/perf_event.c
-F:	arch/*/kernel/*/perf_event.c
-F:	arch/*/kernel/*/*/perf_event.c
+F:	arch/*/kernel/perf_event*.c
+F:	arch/*/kernel/*/perf_event*.c
+F:	arch/*/kernel/*/*/perf_event*.c
 F:	arch/*/include/asm/perf_event.h
-F:	arch/*/lib/perf_event.c
+F:	arch/*/lib/perf_event*.c
 F:	arch/*/kernel/perf_callchain.c
 F:	tools/perf/
 
@@ -5492,7 +5493,7 @@
 F:	drivers/mmc/host/tmio_mmc.*
 
 TMPFS (SHMEM FILESYSTEM)
-M:	Hugh Dickins <hugh.dickins@tiscali.co.uk>
+M:	Hugh Dickins <hughd@google.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	include/linux/shmem_fs.h

Makefile

diff --git a/Makefile b/Makefile
index 5f05f8c..ebc8225 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 34
-EXTRAVERSION = -rc6
+EXTRAVERSION =
 NAME = Sheep on Meth
 
 # *DOCUMENTATION*

arch/Kconfig

diff --git a/arch/Kconfig b/arch/Kconfig
index e5eb133..acda512 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -42,15 +42,10 @@
 	  If in doubt, say "N".
 
 config OPTPROBES
-	bool "Kprobes jump optimization support (EXPERIMENTAL)"
-	default y
-	depends on KPROBES
+	def_bool y
+	depends on KPROBES && HAVE_OPTPROBES
 	depends on !PREEMPT
-	depends on HAVE_OPTPROBES
 	select KALLSYMS_ALL
-	help
-	  This option will allow kprobes to optimize breakpoint to
-	  a jump for reducing its overhead.
 
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool
@@ -142,6 +137,17 @@
 	bool
 	depends on PERF_EVENTS
 
+config HAVE_MIXED_BREAKPOINTS_REGS
+	bool
+	depends on HAVE_HW_BREAKPOINT
+	help
+	  Depending on the arch implementation of hardware breakpoints,
+	  some of them have separate registers for data and instruction
+	  breakpoints addresses, others have mixed registers to store
+	  them but define the access type in a control register.
+	  Select this option if your arch implements breakpoints under the
+	  latter fashion.
+
 config HAVE_USER_RETURN_NOTIFIER
 	bool
 

arch/alpha/include/asm/atomic.h

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 610dff4..e756d04 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -17,8 +17,8 @@
 #define ATOMIC_INIT(i)		( (atomic_t) { (i) } )
 #define ATOMIC64_INIT(i)	( (atomic64_t) { (i) } )
 
-#define atomic_read(v)		((v)->counter + 0)
-#define atomic64_read(v)	((v)->counter + 0)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
 
 #define atomic_set(v,i)		((v)->counter = (i))
 #define atomic64_set(v,i)	((v)->counter = (i))

arch/arm/boot/compressed/head.S

diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 6ab6b33..c5191b1 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -685,8 +685,8 @@
 		W(b)	__armv4_mmu_cache_off
 		W(b)	__armv4_mmu_cache_flush
 
-		.word	0x56056930
-		.word	0xff0ffff0		@ PXA935
+		.word	0x56056900
+		.word	0xffffff00		@ PXA9xx
 		W(b)	__armv4_mmu_cache_on
 		W(b)	__armv4_mmu_cache_off
 		W(b)	__armv4_mmu_cache_flush
@@ -697,12 +697,6 @@
 		W(b)	__armv4_mmu_cache_off
 		W(b)	__armv5tej_mmu_cache_flush
 
-		.word	0x56056930
-		.word	0xff0ffff0		@ PXA935
-		W(b)	__armv4_mmu_cache_on
-		W(b)	__armv4_mmu_cache_off
-		W(b)	__armv4_mmu_cache_flush
-
 		.word	0x56050000		@ Feroceon
 		.word	0xff0f0000
 		W(b)	__armv4_mmu_cache_on

arch/arm/configs/imote2_defconfig

diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig
index 95d2bec..21f2bff 100644
--- a/arch/arm/configs/imote2_defconfig
+++ b/arch/arm/configs/imote2_defconfig
@@ -1,13 +1,14 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.33-rc8
-# Sat Feb 13 21:48:53 2010
+# Linux kernel version: 2.6.34-rc2
+# Thu Apr  8 14:49:08 2010
 #
 CONFIG_ARM=y
 CONFIG_SYS_SUPPORTS_APM_EMULATION=y
 CONFIG_GENERIC_GPIO=y
 CONFIG_GENERIC_TIME=y
 CONFIG_GENERIC_CLOCKEVENTS=y
+CONFIG_HAVE_PROC_CPU=y
 CONFIG_GENERIC_HARDIRQS=y
 CONFIG_STACKTRACE_SUPPORT=y
 CONFIG_HAVE_LATENCYTOP_SUPPORT=y
@@ -19,6 +20,7 @@
 CONFIG_ARCH_HAS_CPUFREQ=y
 CONFIG_GENERIC_HWEIGHT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_NEED_DMA_MAP_STATE=y
 CONFIG_ARCH_MTD_XIP=y
 CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
 CONFIG_VECTORS_BASE=0xffff0000
@@ -60,11 +62,6 @@
 # CONFIG_TREE_RCU_TRACE is not set
 # CONFIG_IKCONFIG is not set
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_GROUP_SCHED=y
-CONFIG_FAIR_GROUP_SCHED=y
-# CONFIG_RT_GROUP_SCHED is not set
-CONFIG_USER_SCHED=y
-# CONFIG_CGROUP_SCHED is not set
 # CONFIG_CGROUPS is not set
 CONFIG_SYSFS_DEPRECATED=y
 CONFIG_SYSFS_DEPRECATED_V2=y
@@ -97,10 +94,14 @@
 CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
 CONFIG_AIO=y
+CONFIG_HAVE_PERF_EVENTS=y
+CONFIG_PERF_USE_VMALLOC=y
 
 #
 # Kernel Performance Events And Counters
 #
+# CONFIG_PERF_EVENTS is not set
+# CONFIG_PERF_COUNTERS is not set
 CONFIG_VM_EVENT_COUNTERS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_SLAB=y
@@ -184,6 +185,7 @@
 # CONFIG_ARCH_REALVIEW is not set
 # CONFIG_ARCH_VERSATILE is not set
 # CONFIG_ARCH_AT91 is not set
+# CONFIG_ARCH_BCMRING is not set
 # CONFIG_ARCH_CLPS711X is not set
 # CONFIG_ARCH_GEMINI is not set
 # CONFIG_ARCH_EBSA110 is not set
@@ -193,7 +195,6 @@
 # CONFIG_ARCH_STMP3XXX is not set
 # CONFIG_ARCH_NETX is not set
 # CONFIG_ARCH_H720X is not set
-# CONFIG_ARCH_NOMADIK is not set
 # CONFIG_ARCH_IOP13XX is not set
 # CONFIG_ARCH_IOP32X is not set
 # CONFIG_ARCH_IOP33X is not set
@@ -210,21 +211,26 @@
 # CONFIG_ARCH_KS8695 is not set
 # CONFIG_ARCH_NS9XXX is not set
 # CONFIG_ARCH_W90X900 is not set
+# CONFIG_ARCH_NUC93X is not set
 # CONFIG_ARCH_PNX4008 is not set
 CONFIG_ARCH_PXA=y
 # CONFIG_ARCH_MSM is not set
+# CONFIG_ARCH_SHMOBILE is not set
 # CONFIG_ARCH_RPC is not set
 # CONFIG_ARCH_SA1100 is not set
 # CONFIG_ARCH_S3C2410 is not set
 # CONFIG_ARCH_S3C64XX is not set
+# CONFIG_ARCH_S5P6440 is not set
+# CONFIG_ARCH_S5P6442 is not set
 # CONFIG_ARCH_S5PC1XX is not set
+# CONFIG_ARCH_S5PV210 is not set
 # CONFIG_ARCH_SHARK is not set
 # CONFIG_ARCH_LH7A40X is not set
 # CONFIG_ARCH_U300 is not set
+# CONFIG_ARCH_U8500 is not set
+# CONFIG_ARCH_NOMADIK is not set
 # CONFIG_ARCH_DAVINCI is not set
 # CONFIG_ARCH_OMAP is not set
-# CONFIG_ARCH_BCMRING is not set
-# CONFIG_ARCH_U8500 is not set
 
 #
 # Intel PXA2xx/PXA3xx Implementations
@@ -253,6 +259,7 @@
 # CONFIG_MACH_EM_X270 is not set
 # CONFIG_MACH_EXEDA is not set
 # CONFIG_MACH_CM_X300 is not set
+# CONFIG_MACH_CAPC7117 is not set
 # CONFIG_ARCH_GUMSTIX is not set
 CONFIG_MACH_INTELMOTE2=y
 # CONFIG_MACH_STARGATE2 is not set
@@ -275,7 +282,11 @@
 # CONFIG_PXA_EZX is not set
 # CONFIG_MACH_MP900C is not set
 # CONFIG_ARCH_PXA_PALM is not set
+# CONFIG_MACH_RAUMFELD_RC is not set
+# CONFIG_MACH_RAUMFELD_CONNECTOR is not set
+# CONFIG_MACH_RAUMFELD_SPEAKER is not set
 # CONFIG_PXA_SHARPSL is not set
+# CONFIG_MACH_ICONTROL is not set
 # CONFIG_ARCH_PXA_ESERIES is not set
 CONFIG_PXA27x=y
 CONFIG_PXA_SSP=y
@@ -302,6 +313,7 @@
 CONFIG_ARM_L1_CACHE_SHIFT=5
 CONFIG_IWMMXT=y
 CONFIG_XSCALE_PMU=y
+CONFIG_CPU_HAS_PMU=y
 CONFIG_COMMON_CLKDEV=y
 
 #
@@ -352,7 +364,7 @@
 #
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_CMDLINE="console=tty1 root=/dev/mmcblk0p2 rootfstype=ext2 rootdelay=3 ip=192.168.0.202:192.168.0.200:192.168.0.200:255.255.255.0 debug"
+CONFIG_CMDLINE="root=/dev/mtdblock2 rootfstype=jffs2 console=ttyS2,115200 mem=32M"
 # CONFIG_XIP_KERNEL is not set
 CONFIG_KEXEC=y
 CONFIG_ATAGS_PROC=y
@@ -360,24 +372,8 @@
 #
 # CPU Power Management
 #
-CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_TABLE=y
-CONFIG_CPU_FREQ_DEBUG=y
-CONFIG_CPU_FREQ_STAT=y
-# CONFIG_CPU_FREQ_STAT_DETAILS is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
-# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
-# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
-# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
-# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
-CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
-CONFIG_CPU_FREQ_GOV_POWERSAVE=m
-CONFIG_CPU_FREQ_GOV_USERSPACE=m
-CONFIG_CPU_FREQ_GOV_ONDEMAND=m
-CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
-CONFIG_CPU_IDLE=y
-CONFIG_CPU_IDLE_GOV_LADDER=y
-CONFIG_CPU_IDLE_GOV_MENU=y
+# CONFIG_CPU_FREQ is not set
+# CONFIG_CPU_IDLE is not set
 
 #
 # Floating point emulation
@@ -409,6 +405,7 @@
 CONFIG_SUSPEND_FREEZER=y
 CONFIG_APM_EMULATION=y
 CONFIG_PM_RUNTIME=y
+CONFIG_PM_OPS=y
 CONFIG_ARCH_SUSPEND_POSSIBLE=y
 CONFIG_NET=y
 
@@ -416,7 +413,6 @@
 # Networking options
 #
 CONFIG_PACKET=y
-CONFIG_PACKET_MMAP=y
 CONFIG_UNIX=y
 CONFIG_XFRM=y
 # CONFIG_XFRM_USER is not set
@@ -506,6 +502,7 @@
 CONFIG_NETFILTER_XTABLES=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
 # CONFIG_NETFILTER_XT_TARGET_CONNMARK is not set
+# CONFIG_NETFILTER_XT_TARGET_CT is not set
 # CONFIG_NETFILTER_XT_TARGET_DSCP is not set
 CONFIG_NETFILTER_XT_TARGET_HL=m
 CONFIG_NETFILTER_XT_TARGET_LED=m
@@ -622,6 +619,7 @@
 # CONFIG_ATM is not set
 CONFIG_STP=m
 CONFIG_BRIDGE=m
+# CONFIG_BRIDGE_IGMP_SNOOPING is not set
 # CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
@@ -646,32 +644,7 @@
 # CONFIG_HAMRADIO is not set
 # CONFIG_CAN is not set
 # CONFIG_IRDA is not set
-CONFIG_BT=y
-CONFIG_BT_L2CAP=y
-CONFIG_BT_SCO=y
-CONFIG_BT_RFCOMM=y
-CONFIG_BT_RFCOMM_TTY=y
-CONFIG_BT_BNEP=y
-CONFIG_BT_BNEP_MC_FILTER=y
-CONFIG_BT_BNEP_PROTO_FILTER=y
-CONFIG_BT_HIDP=y
-
-#
-# Bluetooth device drivers
-#
-CONFIG_BT_HCIBTUSB=m
-CONFIG_BT_HCIBTSDIO=m
-CONFIG_BT_HCIUART=y
-CONFIG_BT_HCIUART_H4=y
-# CONFIG_BT_HCIUART_BCSP is not set
-# CONFIG_BT_HCIUART_LL is not set
-CONFIG_BT_HCIBCM203X=m
-CONFIG_BT_HCIBPA10X=m
-CONFIG_BT_HCIBFUSB=m
-CONFIG_BT_HCIVHCI=m
-CONFIG_BT_MRVL=m
-CONFIG_BT_MRVL_SDIO=m
-# CONFIG_BT_ATH3K is not set
+# CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
 CONFIG_FIB_RULES=y
 # CONFIG_WIRELESS is not set
@@ -687,7 +660,8 @@
 # Generic Driver Options
 #
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_DEVTMPFS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
 CONFIG_FW_LOADER=m
@@ -703,9 +677,9 @@
 # CONFIG_MTD_CONCAT is not set
 CONFIG_MTD_PARTITIONS=y
 # CONFIG_MTD_REDBOOT_PARTS is not set
-# CONFIG_MTD_CMDLINE_PARTS is not set
-# CONFIG_MTD_AFS_PARTS is not set
-# CONFIG_MTD_AR7_PARTS is not set
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_AFS_PARTS=y
+CONFIG_MTD_AR7_PARTS=y
 
 #
 # User Modules And Translation Layers
@@ -812,6 +786,7 @@
 #
 # SCSI device support
 #
+CONFIG_SCSI_MOD=y
 # CONFIG_RAID_ATTRS is not set
 # CONFIG_SCSI is not set
 # CONFIG_SCSI_DMA is not set
@@ -965,6 +940,7 @@
 CONFIG_SERIAL_PXA_CONSOLE=y
 CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y
+# CONFIG_SERIAL_TIMBERDALE is not set
 CONFIG_UNIX98_PTYS=y
 # CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
 CONFIG_LEGACY_PTYS=y
@@ -993,6 +969,7 @@
 CONFIG_I2C_PXA=y
 # CONFIG_I2C_PXA_SLAVE is not set
 # CONFIG_I2C_SIMTEC is not set
+# CONFIG_I2C_XILINX is not set
 
 #
 # External I2C/SMBus adapter drivers
@@ -1006,15 +983,9 @@
 #
 # CONFIG_I2C_PCA_PLATFORM is not set
 # CONFIG_I2C_STUB is not set
-
-#
-# Miscellaneous I2C Chip support
-#
-# CONFIG_SENSORS_TSL2550 is not set
 # CONFIG_I2C_DEBUG_CORE is not set
 # CONFIG_I2C_DEBUG_ALGO is not set
 # CONFIG_I2C_DEBUG_BUS is not set
-# CONFIG_I2C_DEBUG_CHIP is not set
 CONFIG_SPI=y
 # CONFIG_SPI_DEBUG is not set
 CONFIG_SPI_MASTER=y
@@ -1046,10 +1017,12 @@
 #
 # Memory mapped GPIO expanders:
 #
+# CONFIG_GPIO_IT8761E is not set
 
 #
 # I2C GPIO expanders:
 #
+# CONFIG_GPIO_MAX7300 is not set
 # CONFIG_GPIO_MAX732X is not set
 # CONFIG_GPIO_PCA953X is not set
 # CONFIG_GPIO_PCF857X is not set
@@ -1093,10 +1066,12 @@
 # Multifunction device drivers
 #
 # CONFIG_MFD_CORE is not set
+# CONFIG_MFD_88PM860X is not set
 # CONFIG_MFD_SM501 is not set
 # CONFIG_MFD_ASIC3 is not set
 # CONFIG_HTC_EGPIO is not set
 # CONFIG_HTC_PASIC3 is not set
+# CONFIG_HTC_I2CPLD is not set
 # CONFIG_TPS65010 is not set
 # CONFIG_TWL4030_CORE is not set
 # CONFIG_MFD_TMIO is not set
@@ -1105,22 +1080,25 @@
 # CONFIG_MFD_TC6393XB is not set
 CONFIG_PMIC_DA903X=y
 # CONFIG_PMIC_ADP5520 is not set
+# CONFIG_MFD_MAX8925 is not set
 # CONFIG_MFD_WM8400 is not set
 # CONFIG_MFD_WM831X is not set
 # CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_WM8994 is not set
 # CONFIG_MFD_PCF50633 is not set
 # CONFIG_MFD_MC13783 is not set
 # CONFIG_AB3100_CORE is not set
 # CONFIG_EZX_PCAP is not set
-# CONFIG_MFD_88PM8607 is not set
 # CONFIG_AB4500_CORE is not set
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_DEBUG=y
+# CONFIG_REGULATOR_DUMMY is not set
 # CONFIG_REGULATOR_FIXED_VOLTAGE is not set
 CONFIG_REGULATOR_VIRTUAL_CONSUMER=y
 CONFIG_REGULATOR_USERSPACE_CONSUMER=y
 # CONFIG_REGULATOR_BQ24022 is not set
 # CONFIG_REGULATOR_MAX1586 is not set
+# CONFIG_REGULATOR_MAX8649 is not set
 # CONFIG_REGULATOR_MAX8660 is not set
 CONFIG_REGULATOR_DA903X=y
 # CONFIG_REGULATOR_LP3971 is not set
@@ -1218,6 +1196,7 @@
 # CONFIG_VIDEO_SAA7191 is not set
 # CONFIG_VIDEO_TVP514X is not set
 # CONFIG_VIDEO_TVP5150 is not set
+# CONFIG_VIDEO_TVP7002 is not set
 # CONFIG_VIDEO_VPX3220 is not set
 
 #
@@ -1264,15 +1243,7 @@
 CONFIG_VIDEO_PXA27x=y
 # CONFIG_VIDEO_SH_MOBILE_CEU is not set
 # CONFIG_V4L_USB_DRIVERS is not set
-CONFIG_RADIO_ADAPTERS=y
-# CONFIG_I2C_SI4713 is not set
-# CONFIG_RADIO_SI4713 is not set
-# CONFIG_USB_DSBR is not set
-# CONFIG_RADIO_SI470X is not set
-# CONFIG_USB_MR800 is not set
-CONFIG_RADIO_TEA5764=y
-CONFIG_RADIO_TEA5764_XTAL=y
-# CONFIG_RADIO_TEF6862 is not set
+# CONFIG_RADIO_ADAPTERS is not set
 # CONFIG_DAB is not set
 
 #
@@ -1398,8 +1369,6 @@
 #
 # Special HID drivers
 #
-CONFIG_HID_APPLE=m
-# CONFIG_HID_WACOM is not set
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
@@ -1477,7 +1446,6 @@
 # CONFIG_USB_RIO500 is not set
 # CONFIG_USB_LEGOTOWER is not set
 # CONFIG_USB_LCD is not set
-# CONFIG_USB_BERRY_CHARGE is not set
 # CONFIG_USB_LED is not set
 # CONFIG_USB_CYPRESS_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
@@ -1489,7 +1457,6 @@
 # CONFIG_USB_IOWARRIOR is not set
 # CONFIG_USB_TEST is not set
 # CONFIG_USB_ISIGHTFW is not set
-# CONFIG_USB_VST is not set
 CONFIG_USB_GADGET=y
 # CONFIG_USB_GADGET_DEBUG is not set
 # CONFIG_USB_GADGET_DEBUG_FILES is not set
@@ -1529,6 +1496,7 @@
 # CONFIG_USB_MIDI_GADGET is not set
 # CONFIG_USB_G_PRINTER is not set
 # CONFIG_USB_CDC_COMPOSITE is not set
+# CONFIG_USB_G_NOKIA is not set
 # CONFIG_USB_G_MULTI is not set
 
 #
@@ -1555,8 +1523,6 @@
 #
 CONFIG_MMC_PXA=y
 # CONFIG_MMC_SDHCI is not set
-# CONFIG_MMC_AT91 is not set
-# CONFIG_MMC_ATMELMCI is not set
 CONFIG_MMC_SPI=y
 # CONFIG_MEMSTICK is not set
 CONFIG_NEW_LEDS=y
@@ -1574,11 +1540,11 @@
 # CONFIG_LEDS_REGULATOR is not set
 # CONFIG_LEDS_BD2802 is not set
 # CONFIG_LEDS_LT3593 is not set
+CONFIG_LEDS_TRIGGERS=y
 
 #
 # LED Triggers
 #
-CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_BACKLIGHT=y
@@ -1656,7 +1622,7 @@
 # on-CPU RTC drivers
 #
 # CONFIG_RTC_DRV_SA1100 is not set
-# CONFIG_RTC_DRV_PXA is not set
+CONFIG_RTC_DRV_PXA=y
 # CONFIG_DMADEVICES is not set
 # CONFIG_AUXDISPLAY is not set
 # CONFIG_UIO is not set
@@ -1681,19 +1647,10 @@
 CONFIG_JBD=m
 # CONFIG_JBD_DEBUG is not set
 CONFIG_FS_MBCACHE=m
-CONFIG_REISERFS_FS=m
-# CONFIG_REISERFS_CHECK is not set
-# CONFIG_REISERFS_PROC_INFO is not set
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
+# CONFIG_REISERFS_FS is not set
 # CONFIG_JFS_FS is not set
 CONFIG_FS_POSIX_ACL=y
-CONFIG_XFS_FS=m
-# CONFIG_XFS_QUOTA is not set
-# CONFIG_XFS_POSIX_ACL is not set
-# CONFIG_XFS_RT is not set
-# CONFIG_XFS_DEBUG is not set
+# CONFIG_XFS_FS is not set
 # CONFIG_OCFS2_FS is not set
 # CONFIG_BTRFS_FS is not set
 # CONFIG_NILFS2_FS is not set
@@ -1716,9 +1673,7 @@
 #
 # CD-ROM/DVD Filesystems
 #
-CONFIG_ISO9660_FS=m
-CONFIG_JOLIET=y
-CONFIG_ZISOFS=y
+# CONFIG_ISO9660_FS is not set
 # CONFIG_UDF_FS is not set
 
 #
@@ -1750,12 +1705,14 @@
 # CONFIG_BEFS_FS is not set
 # CONFIG_BFS_FS is not set
 # CONFIG_EFS_FS is not set
-CONFIG_JFFS2_FS=m
+CONFIG_JFFS2_FS=y
 CONFIG_JFFS2_FS_DEBUG=0
 CONFIG_JFFS2_FS_WRITEBUFFER=y
-# CONFIG_JFFS2_FS_WBUF_VERIFY is not set
-# CONFIG_JFFS2_SUMMARY is not set
-# CONFIG_JFFS2_FS_XATTR is not set
+CONFIG_JFFS2_FS_WBUF_VERIFY=y
+CONFIG_JFFS2_SUMMARY=y
+CONFIG_JFFS2_FS_XATTR=y
+CONFIG_JFFS2_FS_POSIX_ACL=y
+CONFIG_JFFS2_FS_SECURITY=y
 CONFIG_JFFS2_COMPRESSION_OPTIONS=y
 CONFIG_JFFS2_ZLIB=y
 CONFIG_JFFS2_LZO=y
@@ -1765,6 +1722,7 @@
 CONFIG_JFFS2_CMODE_PRIORITY=y
 # CONFIG_JFFS2_CMODE_SIZE is not set
 # CONFIG_JFFS2_CMODE_FAVOURLZO is not set
+# CONFIG_LOGFS is not set
 CONFIG_CRAMFS=m
 CONFIG_SQUASHFS=m
 # CONFIG_SQUASHFS_EMBEDDED is not set
@@ -1802,6 +1760,7 @@
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 CONFIG_SMB_FS=m
 # CONFIG_SMB_NLS_DEFAULT is not set
+# CONFIG_CEPH_FS is not set
 CONFIG_CIFS=m
 CONFIG_CIFS_STATS=y
 # CONFIG_CIFS_STATS2 is not set
@@ -1895,6 +1854,7 @@
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=y
+# CONFIG_PROVE_RCU is not set
 CONFIG_LOCKDEP=y
 # CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_LOCKDEP is not set
@@ -1918,6 +1878,7 @@
 # CONFIG_BACKTRACE_SELF_TEST is not set
 # CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
 # CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
+# CONFIG_LKDTM is not set
 # CONFIG_FAULT_INJECTION is not set
 # CONFIG_LATENCYTOP is not set
 # CONFIG_SYSCTL_SYSCALL_CHECK is not set
@@ -2061,9 +2022,9 @@
 CONFIG_CRC7=y
 CONFIG_LIBCRC32C=m
 CONFIG_ZLIB_INFLATE=y
-CONFIG_ZLIB_DEFLATE=m
-CONFIG_LZO_COMPRESS=m
-CONFIG_LZO_DECOMPRESS=m
+CONFIG_ZLIB_DEFLATE=y
+CONFIG_LZO_COMPRESS=y
+CONFIG_LZO_DECOMPRESS=y
 CONFIG_DECOMPRESS_GZIP=y
 CONFIG_DECOMPRESS_BZIP2=y
 CONFIG_DECOMPRESS_LZMA=y
@@ -2075,3 +2036,4 @@
 CONFIG_HAS_IOPORT=y
 CONFIG_HAS_DMA=y
 CONFIG_NLATTR=y
+CONFIG_GENERIC_ATOMIC64=y

arch/arm/include/asm/atomic.h

diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index e8ddec2..a0162fa 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -24,7 +24,7 @@
  * strex/ldrex monitor on some implementations. The reason we can use it for
  * atomic_set() is the clrex or dummy strex done on every exception return.
  */
-#define atomic_read(v)	((v)->counter)
+#define atomic_read(v)	(*(volatile int *)&(v)->counter)
 #define atomic_set(v,i)	(((v)->counter) = (i))
 
 #if __LINUX_ARM_ARCH__ >= 6

arch/arm/include/asm/cacheflush.h

diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 0d08d41..4656a24 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -371,6 +371,10 @@
 #ifdef CONFIG_ARM_ERRATA_411920
 	extern void v6_icache_inval_all(void);
 	v6_icache_inval_all();
+#elif defined(CONFIG_SMP) && __LINUX_ARM_ARCH__ >= 7
+	asm("mcr	p15, 0, %0, c7, c1, 0	@ invalidate I-cache inner shareable\n"
+	    :
+	    : "r" (0));
 #else
 	asm("mcr	p15, 0, %0, c7, c5, 0	@ invalidate I-cache\n"
 	    :

arch/arm/include/asm/elf.h

diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index bff0564..51662fe 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -9,6 +9,8 @@
 #include <asm/ptrace.h>
 #include <asm/user.h>
 
+struct task_struct;
+
 typedef unsigned long elf_greg_t;
 typedef unsigned long elf_freg_t[3];
 

arch/arm/include/asm/smp_twd.h

diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h
index 7be0978..634f357 100644
--- a/arch/arm/include/asm/smp_twd.h
+++ b/arch/arm/include/asm/smp_twd.h
@@ -1,6 +1,23 @@
 #ifndef __ASMARM_SMP_TWD_H
 #define __ASMARM_SMP_TWD_H
 
+#define TWD_TIMER_LOAD			0x00
+#define TWD_TIMER_COUNTER		0x04
+#define TWD_TIMER_CONTROL		0x08
+#define TWD_TIMER_INTSTAT		0x0C
+
+#define TWD_WDOG_LOAD			0x20
+#define TWD_WDOG_COUNTER		0x24
+#define TWD_WDOG_CONTROL		0x28
+#define TWD_WDOG_INTSTAT		0x2C
+#define TWD_WDOG_RESETSTAT		0x30
+#define TWD_WDOG_DISABLE		0x34
+
+#define TWD_TIMER_CONTROL_ENABLE	(1 << 0)
+#define TWD_TIMER_CONTROL_ONESHOT	(0 << 1)
+#define TWD_TIMER_CONTROL_PERIODIC	(1 << 1)
+#define TWD_TIMER_CONTROL_IT_ENABLE	(1 << 2)
+
 struct clock_event_device;
 
 extern void __iomem *twd_base;

arch/arm/include/asm/tlbflush.h

diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index e085e2c..bd863d8 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -46,6 +46,9 @@
 #define TLB_V7_UIS_FULL (1 << 20)
 #define TLB_V7_UIS_ASID (1 << 21)
 
+/* Inner Shareable BTB operation (ARMv7 MP extensions) */
+#define TLB_V7_IS_BTB	(1 << 22)
+
 #define TLB_L2CLEAN_FR	(1 << 29)		/* Feroceon */
 #define TLB_DCLEAN	(1 << 30)
 #define TLB_WB		(1 << 31)
@@ -183,7 +186,7 @@
 #endif
 
 #ifdef CONFIG_SMP
-#define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BTB | \
+#define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_V7_IS_BTB | \
 			 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | TLB_V7_UIS_ASID)
 #else
 #define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BTB | \
@@ -339,6 +342,12 @@
 		dsb();
 		isb();
 	}
+	if (tlb_flag(TLB_V7_IS_BTB)) {
+		/* flush the branch target cache */
+		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc");
+		dsb();
+		isb();
+	}
 }
 
 static inline void local_flush_tlb_mm(struct mm_struct *mm)
@@ -376,6 +385,12 @@
 		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc");
 		dsb();
 	}
+	if (tlb_flag(TLB_V7_IS_BTB)) {
+		/* flush the branch target cache */
+		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc");
+		dsb();
+		isb();
+	}
 }
 
 static inline void
@@ -416,6 +431,12 @@
 		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc");
 		dsb();
 	}
+	if (tlb_flag(TLB_V7_IS_BTB)) {
+		/* flush the branch target cache */
+		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc");
+		dsb();
+		isb();
+	}
 }
 
 static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
@@ -454,6 +475,12 @@
 		dsb();
 		isb();
 	}
+	if (tlb_flag(TLB_V7_IS_BTB)) {
+		/* flush the branch target cache */
+		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc");
+		dsb();
+		isb();
+	}
 }
 
 /*

arch/arm/kernel/entry-armv.S

diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index e6a0fb0..7ee48e7 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -676,10 +676,10 @@
  *  lr  = unrecognised FP instruction return address
  */
 
-	.data
+	.pushsection .data
 ENTRY(fp_enter)
 	.word	no_fp
-	.text
+	.popsection
 
 ENTRY(no_fp)
 	mov	pc, lr

arch/arm/kernel/smp.c

diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 577543f..a01194e 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -86,6 +86,12 @@
 			return PTR_ERR(idle);
 		}
 		ci->idle = idle;
+	} else {
+		/*
+		 * Since this idle thread is being re-used, call
+		 * init_idle() to reinitialize the thread structure.
+		 */
+		init_idle(idle, cpu);
 	}
 
 	/*

arch/arm/kernel/smp_twd.c

diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index ea02a7b..7c5f0c0 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -21,23 +21,6 @@
 #include <asm/smp_twd.h>
 #include <asm/hardware/gic.h>
 
-#define TWD_TIMER_LOAD 			0x00
-#define TWD_TIMER_COUNTER		0x04
-#define TWD_TIMER_CONTROL		0x08
-#define TWD_TIMER_INTSTAT		0x0C
-
-#define TWD_WDOG_LOAD			0x20
-#define TWD_WDOG_COUNTER		0x24
-#define TWD_WDOG_CONTROL		0x28
-#define TWD_WDOG_INTSTAT		0x2C
-#define TWD_WDOG_RESETSTAT		0x30
-#define TWD_WDOG_DISABLE		0x34
-
-#define TWD_TIMER_CONTROL_ENABLE	(1 << 0)
-#define TWD_TIMER_CONTROL_ONESHOT	(0 << 1)
-#define TWD_TIMER_CONTROL_PERIODIC	(1 << 1)
-#define TWD_TIMER_CONTROL_IT_ENABLE	(1 << 2)
-
 /* set up by the platform code */
 void __iomem *twd_base;
 

arch/arm/lib/clear_user.S

diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index 5e3f996..14a0d98 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -45,6 +45,7 @@
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
 ENDPROC(__clear_user)
+ENDPROC(__clear_user_std)
 
 		.pushsection .fixup,"ax"
 		.align	0

arch/arm/lib/copy_to_user.S

diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 027b69b..d066df6 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -93,6 +93,7 @@
 #include "copy_template.S"
 
 ENDPROC(__copy_to_user)
+ENDPROC(__copy_to_user_std)
 
 	.pushsection .fixup,"ax"
 	.align 0

arch/arm/mach-davinci/da830.c

diff --git a/arch/arm/mach-davinci/da830.c b/arch/arm/mach-davinci/da830.c
index 122e61a..e8cb982 100644
--- a/arch/arm/mach-davinci/da830.c
+++ b/arch/arm/mach-davinci/da830.c
@@ -410,7 +410,7 @@
 	CLK("davinci-mcasp.0",	NULL,		&mcasp0_clk),
 	CLK("davinci-mcasp.1",	NULL,		&mcasp1_clk),
 	CLK("davinci-mcasp.2",	NULL,		&mcasp2_clk),
-	CLK("musb_hdrc",	NULL,		&usb20_clk),
+	CLK(NULL,		"usb20",	&usb20_clk),
 	CLK(NULL,		"aemif",	&aemif_clk),
 	CLK(NULL,		"aintc",	&aintc_clk),
 	CLK(NULL,		"secu_mgr",	&secu_mgr_clk),

arch/arm/mach-mx5/clock-mx51.c

diff --git a/arch/arm/mach-mx5/clock-mx51.c b/arch/arm/mach-mx5/clock-mx51.c
index 8f85f73..1ee6ce4 100644
--- a/arch/arm/mach-mx5/clock-mx51.c
+++ b/arch/arm/mach-mx5/clock-mx51.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 
 #include <asm/clkdev.h>
+#include <asm/div64.h>
 
 #include <mach/hardware.h>
 #include <mach/common.h>

arch/arm/mach-pxa/include/mach/colibri.h

diff --git a/arch/arm/mach-pxa/include/mach/colibri.h b/arch/arm/mach-pxa/include/mach/colibri.h
index 811743c..5f2ba8d 100644
--- a/arch/arm/mach-pxa/include/mach/colibri.h
+++ b/arch/arm/mach-pxa/include/mach/colibri.h
@@ -2,6 +2,7 @@
 #define _COLIBRI_H_
 
 #include <net/ax88796.h>
+#include <mach/mfp.h>
 
 /*
  * common settings for all modules

arch/arm/mach-pxa/include/mach/hardware.h

diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h
index 7515757..3d8d8cb 100644
--- a/arch/arm/mach-pxa/include/mach/hardware.h
+++ b/arch/arm/mach-pxa/include/mach/hardware.h
@@ -202,7 +202,7 @@
 #define __cpu_is_pxa950(id)                             \
 	({                                              \
 		unsigned int _id = (id) >> 4 & 0xfff;	\
-		id == 0x697;				\
+		_id == 0x697;				\
 	 })
 #else
 #define __cpu_is_pxa950(id)	(0)

arch/arm/mach-pxa/include/mach/regs-u2d.h

diff --git a/arch/arm/mach-pxa/include/mach/regs-u2d.h b/arch/arm/mach-pxa/include/mach/regs-u2d.h
index 44b0b20..c15c0c5 100644
--- a/arch/arm/mach-pxa/include/mach/regs-u2d.h
+++ b/arch/arm/mach-pxa/include/mach/regs-u2d.h
@@ -166,7 +166,8 @@
 #define U2DMACSR_BUSERRTYPE	(7 << 10)	/* PX Bus Error Type */
 #define U2DMACSR_EORINTR	(1 << 9)	/* End Of Receive */
 #define U2DMACSR_REQPEND	(1 << 8)	/* Request Pending */
-#define U2DMACSR_RASINTR	(1 << 4)	/* Request After Channel Stopped (read / write 1 clear) */#define U2DMACSR_STOPINTR	(1 << 3)	/* Stop Interrupt (read only) */
+#define U2DMACSR_RASINTR	(1 << 4)	/* Request After Channel Stopped (read / write 1 clear) */
+#define U2DMACSR_STOPINTR	(1 << 3)	/* Stop Interrupt (read only) */
 #define U2DMACSR_ENDINTR	(1 << 2)	/* End Interrupt (read / write 1 clear) */
 #define U2DMACSR_STARTINTR	(1 << 1)	/* Start Interrupt (read / write 1 clear) */
 #define U2DMACSR_BUSERRINTR	(1 << 0)	/* Bus Error Interrupt (read / write 1 clear) */

arch/arm/mach-pxa/raumfeld.c

diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c
index 44bb675..d12667b 100644
--- a/arch/arm/mach-pxa/raumfeld.c
+++ b/arch/arm/mach-pxa/raumfeld.c
@@ -983,7 +983,7 @@
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(gpio_keys_button); i++)
-			if (!strcmp(gpio_keys_button[i].desc, "on/off button"))
+			if (!strcmp(gpio_keys_button[i].desc, "on_off button"))
 				gpio_keys_button[i].active_low = 1;
 	}
 
@@ -1009,8 +1009,7 @@
 		gpio_direction_output(GPIO_W2W_PDN, 0);
 
 	/* this can be used to switch off the device */
-	ret = gpio_request(GPIO_SHUTDOWN_SUPPLY,
-				"supply shutdown");
+	ret = gpio_request(GPIO_SHUTDOWN_SUPPLY, "supply shutdown");
 	if (ret < 0)
 		pr_warning("Unable to request GPIO_SHUTDOWN_SUPPLY\n");
 	else

arch/arm/mach-pxa/spitz.c

diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index 19b5109..01bdd75 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -363,7 +363,7 @@
 		.type	= EV_PWR,
 		.code	= KEY_SUSPEND,
 		.gpio	= SPITZ_GPIO_ON_KEY,
-		.desc	= "On/Off",
+		.desc	= "On Off",
 		.wakeup	= 1,
 	},
 	/* Two buttons detecting the lid state */

arch/arm/mach-pxa/viper.c

diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index 9e0c5c3..e90114a 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -34,6 +34,7 @@
 #include <linux/pm.h>
 #include <linux/sched.h>
 #include <linux/gpio.h>
+#include <linux/jiffies.h>
 #include <linux/i2c-gpio.h>
 #include <linux/serial_8250.h>
 #include <linux/smc91x.h>
@@ -454,7 +455,7 @@
 	.sda_pin = VIPER_RTC_I2C_SDA_GPIO,
 	.scl_pin = VIPER_RTC_I2C_SCL_GPIO,
 	.udelay  = 10,
-	.timeout = 100,
+	.timeout = HZ,
 };
 
 static struct platform_device i2c_bus_device = {
@@ -779,7 +780,7 @@
 		.sda_pin = VIPER_TPM_I2C_SDA_GPIO,
 		.scl_pin = VIPER_TPM_I2C_SCL_GPIO,
 		.udelay  = 10,
-		.timeout = 100,
+		.timeout = HZ,
 	};
 	char *errstr;
 

arch/arm/mach-sa1100/Kconfig

diff --git a/arch/arm/mach-sa1100/Kconfig b/arch/arm/mach-sa1100/Kconfig
index b17d52f..fd4c52b 100644
--- a/arch/arm/mach-sa1100/Kconfig
+++ b/arch/arm/mach-sa1100/Kconfig
@@ -57,7 +57,7 @@
 config SA1100_H3100
 	bool "Compaq iPAQ H3100"
 	select HTC_EGPIO
-	select CPU_FREQ_SA1100
+	select CPU_FREQ_SA1110
 	help
 	  Say Y here if you intend to run this kernel on the Compaq iPAQ
 	  H3100 handheld computer.  Information about this machine and the
@@ -68,7 +68,7 @@
 config SA1100_H3600
 	bool "Compaq iPAQ H3600/H3700"
 	select HTC_EGPIO
-	select CPU_FREQ_SA1100
+	select CPU_FREQ_SA1110
 	help
 	  Say Y here if you intend to run this kernel on the Compaq iPAQ
 	  H3600 handheld computer.  Information about this machine and the

arch/arm/mach-sa1100/cpu-sa1110.c

diff --git a/arch/arm/mach-sa1100/cpu-sa1110.c b/arch/arm/mach-sa1100/cpu-sa1110.c
index 63b32b6..7252874 100644
--- a/arch/arm/mach-sa1100/cpu-sa1110.c
+++ b/arch/arm/mach-sa1100/cpu-sa1110.c
@@ -363,6 +363,9 @@
 	struct sdram_params *sdram;
 	const char *name = sdram_name;
 
+	if (!cpu_is_sa1110())
+		return -ENODEV;
+
 	if (!name[0]) {
 		if (machine_is_assabet())
 			name = "TC59SM716-CL3";

arch/arm/mm/cache-v6.S

diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 9d89c67..e46ecd8 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -211,6 +211,9 @@
 	mcrne	p15, 0, r1, c7, c15, 1		@ clean & invalidate unified line
 #endif
 1:
+#ifdef CONFIG_SMP
+	str	r0, [r0]			@ write for ownership
+#endif
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D line
 #else
@@ -231,6 +234,9 @@
 v6_dma_clean_range:
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
+#ifdef CONFIG_SMP
+	ldr	r2, [r0]			@ read for ownership
+#endif
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D line
 #else
@@ -251,6 +257,10 @@
 ENTRY(v6_dma_flush_range)
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
+#ifdef CONFIG_SMP
+	ldr	r2, [r0]			@ read for ownership
+	str	r2, [r0]			@ write for ownership
+#endif
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D line
 #else
@@ -273,7 +283,9 @@
 	add	r1, r1, r0
 	teq	r2, #DMA_FROM_DEVICE
 	beq	v6_dma_inv_range
-	b	v6_dma_clean_range
+	teq	r2, #DMA_TO_DEVICE
+	beq	v6_dma_clean_range
+	b	v6_dma_flush_range
 ENDPROC(v6_dma_map_area)
 
 /*
@@ -283,9 +295,6 @@
  *	- dir	- DMA direction
  */
 ENTRY(v6_dma_unmap_area)
-	add	r1, r1, r0
-	teq	r2, #DMA_TO_DEVICE
-	bne	v6_dma_inv_range
 	mov	pc, lr
 ENDPROC(v6_dma_unmap_area)
 

arch/arm/mm/cache-v7.S

diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index bcd64f2..06a90dc 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -167,7 +167,11 @@
 	cmp	r0, r1
 	blo	1b
 	mov	r0, #0
+#ifdef CONFIG_SMP
+	mcr	p15, 0, r0, c7, c1, 6		@ invalidate BTB Inner Shareable
+#else
 	mcr	p15, 0, r0, c7, c5, 6		@ invalidate BTB
+#endif
 	dsb
 	isb
 	mov	pc, lr

arch/arm/mm/init.c

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 83db12a..0ed29bf 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -86,9 +86,6 @@
 	printk("Mem-info:\n");
 	show_free_areas();
 	for_each_online_node(node) {
-		pg_data_t *n = NODE_DATA(node);
-		struct page *map = pgdat_page_nr(n, 0) - n->node_start_pfn;
-
 		for_each_nodebank (i,mi,node) {
 			struct membank *bank = &mi->bank[i];
 			unsigned int pfn1, pfn2;
@@ -97,8 +94,8 @@
 			pfn1 = bank_pfn_start(bank);
 			pfn2 = bank_pfn_end(bank);
 
-			page = map + pfn1;
-			end  = map + pfn2;
+			page = pfn_to_page(pfn1);
+			end  = pfn_to_page(pfn2 - 1) + 1;
 
 			do {
 				total++;
@@ -603,9 +600,6 @@
 	reserved_pages = free_pages = 0;
 
 	for_each_online_node(node) {
-		pg_data_t *n = NODE_DATA(node);
-		struct page *map = pgdat_page_nr(n, 0) - n->node_start_pfn;
-
 		for_each_nodebank(i, &meminfo, node) {
 			struct membank *bank = &meminfo.bank[i];
 			unsigned int pfn1, pfn2;
@@ -614,8 +608,8 @@
 			pfn1 = bank_pfn_start(bank);
 			pfn2 = bank_pfn_end(bank);
 
-			page = map + pfn1;
-			end  = map + pfn2;
+			page = pfn_to_page(pfn1);
+			end  = pfn_to_page(pfn2 - 1) + 1;
 
 			do {
 				if (PageReserved(page))

arch/arm/mm/nommu.c

diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 9bfeb6b..33b3273 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -65,6 +65,15 @@
 }
 EXPORT_SYMBOL(flush_dcache_page);
 
+void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
+		       unsigned long uaddr, void *dst, const void *src,
+		       unsigned long len)
+{
+	memcpy(dst, src, len);
+	if (vma->vm_flags & VM_EXEC)
+		__cpuc_coherent_user_range(uaddr, uaddr + len);
+}
+
 void __iomem *__arm_ioremap_pfn(unsigned long pfn, unsigned long offset,
 				size_t size, unsigned int mtype)
 {
@@ -87,8 +96,8 @@
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
-void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
-			    unsigned int mtype, void *caller)
+void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+				   unsigned int mtype, void *caller)
 {
 	return __arm_ioremap(phys_addr, size, mtype);
 }

arch/arm/mm/tlb-v7.S

diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index 0cb1848..f3f288a 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -50,7 +50,11 @@
 	cmp	r0, r1
 	blo	1b
 	mov	ip, #0
+#ifdef CONFIG_SMP
+	mcr	p15, 0, ip, c7, c1, 6		@ flush BTAC/BTB Inner Shareable
+#else
 	mcr	p15, 0, ip, c7, c5, 6		@ flush BTAC/BTB
+#endif
 	dsb
 	mov	pc, lr
 ENDPROC(v7wbi_flush_user_tlb_range)
@@ -79,7 +83,11 @@
 	cmp	r0, r1
 	blo	1b
 	mov	r2, #0
+#ifdef CONFIG_SMP
+	mcr	p15, 0, r2, c7, c1, 6		@ flush BTAC/BTB Inner Shareable
+#else
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
+#endif
 	dsb
 	isb
 	mov	pc, lr

arch/arm/plat-mxc/include/mach/dma-mx1-mx2.h

diff --git a/arch/arm/plat-mxc/include/mach/dma-mx1-mx2.h b/arch/arm/plat-mxc/include/mach/dma-mx1-mx2.h
index 07be8ad..7c4870b 100644
--- a/arch/arm/plat-mxc/include/mach/dma-mx1-mx2.h
+++ b/arch/arm/plat-mxc/include/mach/dma-mx1-mx2.h
@@ -31,7 +31,13 @@
 #define DMA_MODE_WRITE		1
 #define DMA_MODE_MASK		1
 
-#define DMA_BASE IO_ADDRESS(DMA_BASE_ADDR)
+#define MX1_DMA_REG(offset)	MX1_IO_ADDRESS(MX1_DMA_BASE_ADDR + (offset))
+
+/* DMA Interrupt Mask Register */
+#define MX1_DMA_DIMR		MX1_DMA_REG(0x08)
+
+/* Channel Control Register */
+#define MX1_DMA_CCR(x)		MX1_DMA_REG(0x8c + ((x) << 6))
 
 #define IMX_DMA_MEMSIZE_32	(0 << 4)
 #define IMX_DMA_MEMSIZE_8	(1 << 4)

arch/arm/plat-omap/include/plat/usb.h

diff --git a/arch/arm/plat-omap/include/plat/usb.h b/arch/arm/plat-omap/include/plat/usb.h
index 568578d..876ca8d 100644
--- a/arch/arm/plat-omap/include/plat/usb.h
+++ b/arch/arm/plat-omap/include/plat/usb.h
@@ -46,7 +46,7 @@
 struct omap_musb_board_data {
 	u8	interface_type;
 	u8	mode;
-	u8	power;
+	u16	power;
 };
 
 enum musb_interface    {MUSB_INTERFACE_ULPI, MUSB_INTERFACE_UTMI};

arch/arm/plat-pxa/dma.c

diff --git a/arch/arm/plat-pxa/dma.c b/arch/arm/plat-pxa/dma.c
index 742350e..2d3c19d 100644
--- a/arch/arm/plat-pxa/dma.c
+++ b/arch/arm/plat-pxa/dma.c
@@ -245,7 +245,7 @@
 
 	dbgfs_chan = kmalloc(sizeof(*dbgfs_state) * num_dma_channels,
 			     GFP_KERNEL);
-	if (!dbgfs_state)
+	if (!dbgfs_chan)
 		goto err_alloc;
 
 	chandir = debugfs_create_dir("channels", dbgfs_root);

arch/arm/tools/mach-types

diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types
index 1536f17..8f10d24 100644
--- a/arch/arm/tools/mach-types
+++ b/arch/arm/tools/mach-types
@@ -12,7 +12,7 @@
 #
 #   http://www.arm.linux.org.uk/developer/machines/?action=new
 #
-# Last update: Sat Mar 20 15:35:41 2010
+# Last update: Sat May 1 10:36:42 2010
 #
 # machine_is_xxx	CONFIG_xxxx		MACH_TYPE_xxx		number
 #
@@ -2749,3 +2749,58 @@
 h6053			MACH_H6053		H6053			2762
 smint01			MACH_SMINT01		SMINT01			2763
 prtlvt2			MACH_PRTLVT2		PRTLVT2			2764
+ap420			MACH_AP420		AP420			2765
+htcshift		MACH_HTCSHIFT		HTCSHIFT		2766
+davinci_dm365_fc	MACH_DAVINCI_DM365_FC	DAVINCI_DM365_FC	2767
+msm8x55_surf		MACH_MSM8X55_SURF	MSM8X55_SURF		2768
+msm8x55_ffa		MACH_MSM8X55_FFA	MSM8X55_FFA		2769
+esl_vamana		MACH_ESL_VAMANA		ESL_VAMANA		2770
+sbc35			MACH_SBC35		SBC35			2771
+mpx6446			MACH_MPX6446		MPX6446			2772
+oreo_controller		MACH_OREO_CONTROLLER	OREO_CONTROLLER		2773
+kopin_models		MACH_KOPIN_MODELS	KOPIN_MODELS		2774
+ttc_vision2		MACH_TTC_VISION2	TTC_VISION2		2775
+cns3420vb		MACH_CNS3420VB		CNS3420VB		2776
+lpc2			MACH_LPC2		LPC2			2777
+olympus			MACH_OLYMPUS		OLYMPUS			2778
+vortex			MACH_VORTEX		VORTEX			2779
+s5pc200			MACH_S5PC200		S5PC200			2780
+ecucore_9263		MACH_ECUCORE_9263	ECUCORE_9263		2781
+smdkc200		MACH_SMDKC200		SMDKC200		2782
+emsiso_sx27		MACH_EMSISO_SX27	EMSISO_SX27		2783
+apx_som9g45_ek		MACH_APX_SOM9G45_EK	APX_SOM9G45_EK		2784
+songshan		MACH_SONGSHAN		SONGSHAN		2785
+tianshan		MACH_TIANSHAN		TIANSHAN		2786
+vpx500			MACH_VPX500		VPX500			2787
+am3517sam		MACH_AM3517SAM		AM3517SAM		2788
+skat91_sim508		MACH_SKAT91_SIM508	SKAT91_SIM508		2789
+skat91_s3e		MACH_SKAT91_S3E		SKAT91_S3E		2790
+omap4_panda		MACH_OMAP4_PANDA	OMAP4_PANDA		2791
+df7220			MACH_DF7220		DF7220			2792
+nemini			MACH_NEMINI		NEMINI			2793
+t8200			MACH_T8200		T8200			2794
+apf51			MACH_APF51		APF51			2795
+dr_rc_unit		MACH_DR_RC_UNIT		DR_RC_UNIT		2796
+bordeaux		MACH_BORDEAUX		BORDEAUX		2797
+catania_b		MACH_CATANIA_B		CATANIA_B		2798
+mx51_ocean		MACH_MX51_OCEAN		MX51_OCEAN		2799
+ti8168evm		MACH_TI8168EVM		TI8168EVM		2800
+neocoreomap		MACH_NEOCOREOMAP	NEOCOREOMAP		2801
+withings_wbp		MACH_WITHINGS_WBP	WITHINGS_WBP		2802
+dbps			MACH_DBPS		DBPS			2803
+sbc9261			MACH_SBC9261		SBC9261			2804
+pcbfp0001		MACH_PCBFP0001		PCBFP0001		2805
+speedy			MACH_SPEEDY		SPEEDY			2806
+chrysaor		MACH_CHRYSAOR		CHRYSAOR		2807
+tango			MACH_TANGO		TANGO			2808
+synology_dsx11		MACH_SYNOLOGY_DSX11	SYNOLOGY_DSX11		2809
+hanlin_v3ext		MACH_HANLIN_V3EXT	HANLIN_V3EXT		2810
+hanlin_v5		MACH_HANLIN_V5		HANLIN_V5		2811
+hanlin_v3plus		MACH_HANLIN_V3PLUS	HANLIN_V3PLUS		2812
+iriver_story		MACH_IRIVER_STORY	IRIVER_STORY		2813
+irex_iliad		MACH_IREX_ILIAD		IREX_ILIAD		2814
+irex_dr1000		MACH_IREX_DR1000	IREX_DR1000		2815
+teton_bga		MACH_TETON_BGA		TETON_BGA		2816
+snapper9g45		MACH_SNAPPER9G45	SNAPPER9G45		2817
+tam3517			MACH_TAM3517		TAM3517			2818
+pdc100			MACH_PDC100		PDC100			2819

arch/avr32/include/asm/atomic.h

diff --git a/arch/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h
index b131c27..bbce6a1 100644
--- a/arch/avr32/include/asm/atomic.h
+++ b/arch/avr32/include/asm/atomic.h
@@ -19,7 +19,7 @@
 
 #define ATOMIC_INIT(i)  { (i) }
 
-#define atomic_read(v)		((v)->counter)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = i)
 
 /*

arch/cris/include/asm/atomic.h

diff --git a/arch/cris/include/asm/atomic.h b/arch/cris/include/asm/atomic.h
index a6aca81..88dc9b9 100644
--- a/arch/cris/include/asm/atomic.h
+++ b/arch/cris/include/asm/atomic.h
@@ -15,7 +15,7 @@
 
 #define ATOMIC_INIT(i)  { (i) }
 
-#define atomic_read(v) ((v)->counter)
+#define atomic_read(v) (*(volatile int *)&(v)->counter)
 #define atomic_set(v,i) (((v)->counter) = (i))
 
 /* These should be written in asm but we do it in C for now. */

arch/frv/include/asm/atomic.h

diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index 00a57af..fae32c7 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -36,7 +36,7 @@
 #define smp_mb__after_atomic_inc()	barrier()
 
 #define ATOMIC_INIT(i)		{ (i) }
-#define atomic_read(v)		((v)->counter)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = (i))
 
 #ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS

arch/h8300/include/asm/atomic.h

diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 33c8c0f..e936804 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -10,7 +10,7 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)		((v)->counter)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = i)
 
 #include <asm/system.h>

arch/ia64/include/asm/atomic.h

diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 88405cb..4e19484 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -21,8 +21,8 @@
 #define ATOMIC_INIT(i)		((atomic_t) { (i) })
 #define ATOMIC64_INIT(i)	((atomic64_t) { (i) })
 
-#define atomic_read(v)		((v)->counter)
-#define atomic64_read(v)	((v)->counter)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
 
 #define atomic_set(v,i)		(((v)->counter) = (i))
 #define atomic64_set(v,i)	(((v)->counter) = (i))

arch/m32r/include/asm/atomic.h

diff --git a/arch/m32r/include/asm/atomic.h b/arch/m32r/include/asm/atomic.h
index 63f0cf0..d44a51e 100644
--- a/arch/m32r/include/asm/atomic.h
+++ b/arch/m32r/include/asm/atomic.h
@@ -26,7 +26,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)	((v)->counter)
+#define atomic_read(v)	(*(volatile int *)&(v)->counter)
 
 /**
  * atomic_set - set atomic variable

arch/m68k/amiga/Makefile

diff --git a/arch/m68k/amiga/Makefile b/arch/m68k/amiga/Makefile
index 6a0d765..11dd30b 100644
--- a/arch/m68k/amiga/Makefile
+++ b/arch/m68k/amiga/Makefile
@@ -2,6 +2,6 @@
 # Makefile for Linux arch/m68k/amiga source directory
 #
 
-obj-y		:= config.o amiints.o cia.o chipram.o amisound.o
+obj-y		:= config.o amiints.o cia.o chipram.o amisound.o platform.o
 
 obj-$(CONFIG_AMIGA_PCMCIA)	+= pcmcia.o

arch/m68k/amiga/platform.c

diff --git a/arch/m68k/amiga/platform.c b/arch/m68k/amiga/platform.c
new file mode 100644
index 0000000..38f18bf
--- /dev/null
+++ b/arch/m68k/amiga/platform.c
@@ -0,0 +1,83 @@
+/*
+ *  Copyright (C) 2007-2009 Geert Uytterhoeven
+ *
+ * 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/init.h>
+#include <linux/platform_device.h>
+#include <linux/zorro.h>
+
+#include <asm/amigahw.h>
+
+
+#ifdef CONFIG_ZORRO
+
+static const struct resource zorro_resources[] __initconst = {
+	/* Zorro II regions (on Zorro II/III) */
+	{
+		.name	= "Zorro II exp",
+		.start	= 0x00e80000,
+		.end	= 0x00efffff,
+		.flags	= IORESOURCE_MEM,
+	}, {
+		.name	= "Zorro II mem",
+		.start	= 0x00200000,
+		.end	= 0x009fffff,
+		.flags	= IORESOURCE_MEM,
+	},
+	/* Zorro III regions (on Zorro III only) */
+	{
+		.name	= "Zorro III exp",
+		.start	= 0xff000000,
+		.end	= 0xffffffff,
+		.flags	= IORESOURCE_MEM,
+	}, {
+		.name	= "Zorro III cfg",
+		.start	= 0x40000000,
+		.end	= 0x7fffffff,
+		.flags	= IORESOURCE_MEM,
+	}
+};
+
+
+static int __init amiga_init_bus(void)
+{
+	if (!MACH_IS_AMIGA || !AMIGAHW_PRESENT(ZORRO))
+		return -ENODEV;
+
+	platform_device_register_simple("amiga-zorro", -1, zorro_resources,
+					AMIGAHW_PRESENT(ZORRO3) ? 4 : 2);
+	return 0;
+}
+
+subsys_initcall(amiga_init_bus);
+
+#endif /* CONFIG_ZORRO */
+
+
+static int __init amiga_init_devices(void)
+{
+	if (!MACH_IS_AMIGA)
+		return -ENODEV;
+
+	/* video hardware */
+	if (AMIGAHW_PRESENT(AMI_VIDEO))
+		platform_device_register_simple("amiga-video", -1, NULL, 0);
+
+
+	/* sound hardware */
+	if (AMIGAHW_PRESENT(AMI_AUDIO))
+		platform_device_register_simple("amiga-audio", -1, NULL, 0);
+
+
+	/* storage interfaces */
+	if (AMIGAHW_PRESENT(AMI_FLOPPY))
+		platform_device_register_simple("amiga-floppy", -1, NULL, 0);
+
+	return 0;
+}
+
+device_initcall(amiga_init_devices);

arch/m68k/bvme6000/rtc.c

diff --git a/arch/m68k/bvme6000/rtc.c b/arch/m68k/bvme6000/rtc.c
index b46ea17..cb8617b 100644
--- a/arch/m68k/bvme6000/rtc.c
+++ b/arch/m68k/bvme6000/rtc.c
@@ -9,7 +9,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/miscdevice.h>
-#include <linux/smp_lock.h>
 #include <linux/ioport.h>
 #include <linux/capability.h>
 #include <linux/fcntl.h>
@@ -35,10 +34,9 @@
 static unsigned char days_in_mo[] =
 {0, 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31};
 
-static char rtc_status;
+static atomic_t rtc_status = ATOMIC_INIT(1);
 
-static int rtc_ioctl(struct inode *inode, struct file *file, unsigned int cmd,
-		     unsigned long arg)
+static long rtc_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE;
 	unsigned char msr;
@@ -132,29 +130,20 @@
 }
 
 /*
- *	We enforce only one user at a time here with the open/close.
- *	Also clear the previous interrupt data on an open, and clean
- *	up things on a close.
+ * We enforce only one user at a time here with the open/close.
  */
-
 static int rtc_open(struct inode *inode, struct file *file)
 {
-	lock_kernel();
-	if(rtc_status) {
-		unlock_kernel();
+	if (!atomic_dec_and_test(&rtc_status)) {
+		atomic_inc(&rtc_status);
 		return -EBUSY;
 	}
-
-	rtc_status = 1;
-	unlock_kernel();
 	return 0;
 }
 
 static int rtc_release(struct inode *inode, struct file *file)
 {
-	lock_kernel();
-	rtc_status = 0;
-	unlock_kernel();
+	atomic_inc(&rtc_status);
 	return 0;
 }
 
@@ -163,9 +152,9 @@
  */
 
 static const struct file_operations rtc_fops = {
-	.ioctl =	rtc_ioctl,
-	.open =		rtc_open,
-	.release =	rtc_release,
+	.unlocked_ioctl	= rtc_ioctl,
+	.open		= rtc_open,
+	.release	= rtc_release,
 };
 
 static struct miscdevice rtc_dev = {

arch/m68k/hp300/time.h

diff --git a/arch/m68k/hp300/time.h b/arch/m68k/hp300/time.h
index f5b3d09..7b98242 100644
--- a/arch/m68k/hp300/time.h
+++ b/arch/m68k/hp300/time.h
@@ -1,4 +1,2 @@
 extern void hp300_sched_init(irq_handler_t vector);
-extern unsigned long hp300_gettimeoffset (void);
-
-
+extern unsigned long hp300_gettimeoffset(void);

arch/m68k/include/asm/atomic_mm.h

diff --git a/arch/m68k/include/asm/atomic_mm.h b/arch/m68k/include/asm/atomic_mm.h
index d9d2ed6..6a223b3 100644
--- a/arch/m68k/include/asm/atomic_mm.h
+++ b/arch/m68k/include/asm/atomic_mm.h
@@ -15,7 +15,7 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)		((v)->counter)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = i)
 
 static inline void atomic_add(int i, atomic_t *v)

arch/m68k/include/asm/atomic_no.h

diff --git a/arch/m68k/include/asm/atomic_no.h b/arch/m68k/include/asm/atomic_no.h
index 5674cb9..289310c 100644
--- a/arch/m68k/include/asm/atomic_no.h
+++ b/arch/m68k/include/asm/atomic_no.h
@@ -15,7 +15,7 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)		((v)->counter)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = i)
 
 static __inline__ void atomic_add(int i, atomic_t *v)

arch/m68k/include/asm/bitops_mm.h

diff --git a/arch/m68k/include/asm/bitops_mm.h b/arch/m68k/include/asm/bitops_mm.h
index 9bde784..b4ecdaa 100644
--- a/arch/m68k/include/asm/bitops_mm.h
+++ b/arch/m68k/include/asm/bitops_mm.h
@@ -365,6 +365,10 @@
 #define ext2_set_bit_atomic(lock, nr, addr)	test_and_set_bit((nr) ^ 24, (unsigned long *)(addr))
 #define ext2_clear_bit(nr, addr)		__test_and_clear_bit((nr) ^ 24, (unsigned long *)(addr))
 #define ext2_clear_bit_atomic(lock, nr, addr)	test_and_clear_bit((nr) ^ 24, (unsigned long *)(addr))
+#define ext2_find_next_zero_bit(addr, size, offset) \
+	generic_find_next_zero_le_bit((unsigned long *)addr, size, offset)
+#define ext2_find_next_bit(addr, size, offset) \
+	generic_find_next_le_bit((unsigned long *)addr, size, offset)
 
 static inline int ext2_test_bit(int nr, const void *vaddr)
 {
@@ -394,10 +398,9 @@
 	return (p - addr) * 32 + res;
 }
 
-static inline int ext2_find_next_zero_bit(const void *vaddr, unsigned size,
-					  unsigned offset)
+static inline unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
+		unsigned long size, unsigned long offset)
 {
-	const unsigned long *addr = vaddr;
 	const unsigned long *p = addr + (offset >> 5);
 	int bit = offset & 31UL, res;
 
@@ -437,10 +440,9 @@
 	return (p - addr) * 32 + res;
 }
 
-static inline int ext2_find_next_bit(const void *vaddr, unsigned size,
-				     unsigned offset)
+static inline unsigned long generic_find_next_le_bit(const unsigned long *addr,
+		unsigned long size, unsigned long offset)
 {
-	const unsigned long *addr = vaddr;
 	const unsigned long *p = addr + (offset >> 5);
 	int bit = offset & 31UL, res;
 

arch/m68k/include/asm/param.h

diff --git a/arch/m68k/include/asm/param.h b/arch/m68k/include/asm/param.h
index 85c41b7..36265cc 100644
--- a/arch/m68k/include/asm/param.h
+++ b/arch/m68k/include/asm/param.h
@@ -1,26 +1,12 @@
 #ifndef _M68K_PARAM_H
 #define _M68K_PARAM_H
 
-#ifdef __KERNEL__
-# define HZ		CONFIG_HZ	/* Internal kernel timer frequency */
-# define USER_HZ	100		/* .. some user interfaces are in "ticks" */
-# define CLOCKS_PER_SEC	(USER_HZ)	/* like times() */
-#endif
-
-#ifndef HZ
-#define HZ 100
-#endif
-
 #ifdef __uClinux__
 #define EXEC_PAGESIZE	4096
 #else
 #define EXEC_PAGESIZE	8192
 #endif
 
-#ifndef NOGROUP
-#define NOGROUP		(-1)
-#endif
-
-#define MAXHOSTNAMELEN	64	/* max length of hostname */
+#include <asm-generic/param.h>
 
 #endif /* _M68K_PARAM_H */

arch/m68k/kernel/traps.c

diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index aacd6d1..ada4f4c 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -455,7 +455,7 @@
 
 		if (do_page_fault(&fp->ptregs, addr, errorcode)) {
 #ifdef DEBUG
-		        printk("do_page_fault() !=0 \n");
+			printk("do_page_fault() !=0\n");
 #endif
 			if (user_mode(&fp->ptregs)){
 				/* delay writebacks after signal delivery */

arch/m68k/mac/config.c

diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 0356da9..1c16b1b 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -148,7 +148,7 @@
 void __init config_mac(void)
 {
 	if (!MACH_IS_MAC)
-		printk(KERN_ERR "ERROR: no Mac, but config_mac() called!! \n");
+		printk(KERN_ERR "ERROR: no Mac, but config_mac() called!!\n");
 
 	mach_sched_init = mac_sched_init;
 	mach_init_IRQ = mac_init_IRQ;
@@ -867,7 +867,7 @@
 	 */
 	iop_preinit();
 
-	printk(KERN_INFO "Detected Macintosh model: %d \n", model);
+	printk(KERN_INFO "Detected Macintosh model: %d\n", model);
 
 	/*
 	 * Report booter data:
@@ -878,12 +878,12 @@
 		mac_bi_data.videoaddr, mac_bi_data.videorow,
 		mac_bi_data.videodepth, mac_bi_data.dimensions & 0xFFFF,
 		mac_bi_data.dimensions >> 16);
-	printk(KERN_DEBUG " Videological 0x%lx phys. 0x%lx, SCC at 0x%lx \n",
+	printk(KERN_DEBUG " Videological 0x%lx phys. 0x%lx, SCC at 0x%lx\n",
 		mac_bi_data.videological, mac_orig_videoaddr,
 		mac_bi_data.sccbase);
-	printk(KERN_DEBUG " Boottime: 0x%lx GMTBias: 0x%lx \n",
+	printk(KERN_DEBUG " Boottime: 0x%lx GMTBias: 0x%lx\n",
 		mac_bi_data.boottime, mac_bi_data.gmtbias);
-	printk(KERN_DEBUG " Machine ID: %ld CPUid: 0x%lx memory size: 0x%lx \n",
+	printk(KERN_DEBUG " Machine ID: %ld CPUid: 0x%lx memory size: 0x%lx\n",
 		mac_bi_data.id, mac_bi_data.cpuid, mac_bi_data.memsize);
 
 	iop_init();

arch/m68k/mm/fault.c

diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index d0e35cf..a96394a 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -154,7 +154,6 @@
 	 * the fault.
 	 */
 
- survive:
 	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
 #ifdef DEBUG
 	printk("handle_mm_fault returns %d\n",fault);
@@ -180,15 +179,10 @@
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (is_global_init(current)) {
-		yield();
-		down_read(&mm->mmap_sem);
-		goto survive;
-	}
-
-	printk("VM: killing process %s\n", current->comm);
-	if (user_mode(regs))
-		do_group_exit(SIGKILL);
+	if (!user_mode(regs))
+		goto no_context;
+	pagefault_out_of_memory();
+	return 0;
 
 no_context:
 	current->thread.signo = SIGBUS;

arch/m68k/mvme16x/rtc.c

diff --git a/arch/m68k/mvme16x/rtc.c b/arch/m68k/mvme16x/rtc.c
index 8da9c25..11ac6f6 100644
--- a/arch/m68k/mvme16x/rtc.c
+++ b/arch/m68k/mvme16x/rtc.c
@@ -9,7 +9,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/miscdevice.h>
-#include <linux/smp_lock.h>
 #include <linux/ioport.h>
 #include <linux/capability.h>
 #include <linux/fcntl.h>
@@ -36,8 +35,7 @@
 
 static atomic_t rtc_ready = ATOMIC_INIT(1);
 
-static int rtc_ioctl(struct inode *inode, struct file *file, unsigned int cmd,
-		     unsigned long arg)
+static long rtc_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	volatile MK48T08ptr_t rtc = (MK48T08ptr_t)MVME_RTC_BASE;
 	unsigned long flags;
@@ -120,22 +118,15 @@
 }
 
 /*
- *	We enforce only one user at a time here with the open/close.
- *	Also clear the previous interrupt data on an open, and clean
- *	up things on a close.
+ * We enforce only one user at a time here with the open/close.
  */
-
 static int rtc_open(struct inode *inode, struct file *file)
 {
-	lock_kernel();
 	if( !atomic_dec_and_test(&rtc_ready) )
 	{
 		atomic_inc( &rtc_ready );
-		unlock_kernel();
 		return -EBUSY;
 	}
-	unlock_kernel();
-
 	return 0;
 }
 
@@ -150,9 +141,9 @@
  */
 
 static const struct file_operations rtc_fops = {
-	.ioctl =	rtc_ioctl,
-	.open =		rtc_open,
-	.release =	rtc_release,
+	.unlocked_ioctl	= rtc_ioctl,
+	.open		= rtc_open,
+	.release	= rtc_release,
 };
 
 static struct miscdevice rtc_dev=

arch/m68k/q40/config.c

diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 31ab3f0..ad10fec 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -126,7 +126,7 @@
 {
         halted = 1;
         printk("\n\n*******************************************\n"
-		"Called q40_reset : press the RESET button!! \n"
+		"Called q40_reset : press the RESET button!!\n"
 		"*******************************************\n");
 	Q40_LED_ON();
 	while (1)

arch/microblaze/configs/mmu_defconfig

diff --git a/arch/microblaze/configs/mmu_defconfig b/arch/microblaze/configs/mmu_defconfig
index 6fced1f..3c91cf6 100644
--- a/arch/microblaze/configs/mmu_defconfig
+++ b/arch/microblaze/configs/mmu_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.33-rc6
-# Wed Feb  3 10:02:59 2010
+# Linux kernel version: 2.6.34-rc6
+# Thu May  6 11:22:14 2010
 #
 CONFIG_MICROBLAZE=y
 # CONFIG_SWAP is not set
@@ -22,8 +22,6 @@
 CONFIG_STACKTRACE_SUPPORT=y
 CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_HAVE_LATENCYTOP_SUPPORT=y
-# CONFIG_PCI is not set
-CONFIG_NO_DMA=y
 CONFIG_DTC=y
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 CONFIG_CONSTRUCTORS=y
@@ -56,7 +54,6 @@
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=17
-# CONFIG_GROUP_SCHED is not set
 # CONFIG_CGROUPS is not set
 CONFIG_SYSFS_DEPRECATED=y
 CONFIG_SYSFS_DEPRECATED_V2=y
@@ -106,6 +103,8 @@
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
 CONFIG_HAVE_OPROFILE=y
+CONFIG_HAVE_DMA_ATTRS=y
+CONFIG_HAVE_DMA_API_DEBUG=y
 
 #
 # GCOV-based kernel profiling
@@ -245,13 +244,20 @@
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_HAVE_AOUT is not set
 # CONFIG_BINFMT_MISC is not set
+
+#
+# Bus Options
+#
+# CONFIG_PCI is not set
+# CONFIG_PCI_DOMAINS is not set
+# CONFIG_PCI_SYSCALL is not set
+# CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_NET=y
 
 #
 # Networking options
 #
 CONFIG_PACKET=y
-# CONFIG_PACKET_MMAP is not set
 CONFIG_UNIX=y
 CONFIG_XFRM=y
 # CONFIG_XFRM_USER is not set
@@ -341,7 +347,9 @@
 # CONFIG_SYS_HYPERVISOR is not set
 # CONFIG_CONNECTOR is not set
 # CONFIG_MTD is not set
+CONFIG_OF_FLATTREE=y
 CONFIG_OF_DEVICE=y
+CONFIG_OF_MDIO=y
 # CONFIG_PARPORT is not set
 CONFIG_BLK_DEV=y
 # CONFIG_BLK_DEV_COW_COMMON is not set
@@ -370,6 +378,7 @@
 #
 # SCSI device support
 #
+CONFIG_SCSI_MOD=y
 # CONFIG_RAID_ATTRS is not set
 # CONFIG_SCSI is not set
 # CONFIG_SCSI_DMA is not set
@@ -383,9 +392,30 @@
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
 # CONFIG_VETH is not set
-# CONFIG_PHYLIB is not set
+CONFIG_PHYLIB=y
+
+#
+# MII PHY device drivers
+#
+# CONFIG_MARVELL_PHY is not set
+# CONFIG_DAVICOM_PHY is not set
+# CONFIG_QSEMI_PHY is not set
+# CONFIG_LXT_PHY is not set
+# CONFIG_CICADA_PHY is not set
+# CONFIG_VITESSE_PHY is not set
+# CONFIG_SMSC_PHY is not set
+# CONFIG_BROADCOM_PHY is not set
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_NATIONAL_PHY is not set
+# CONFIG_STE10XP is not set
+# CONFIG_LSI_ET1011C_PHY is not set
+# CONFIG_MICREL_PHY is not set
+# CONFIG_FIXED_PHY is not set
+# CONFIG_MDIO_BITBANG is not set
 CONFIG_NET_ETHERNET=y
 # CONFIG_MII is not set
+# CONFIG_ETHOC is not set
 # CONFIG_DNET is not set
 # CONFIG_IBM_NEW_EMAC_ZMII is not set
 # CONFIG_IBM_NEW_EMAC_RGMII is not set
@@ -394,6 +424,7 @@
 # CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
 # CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
 # CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
+# CONFIG_B44 is not set
 # CONFIG_KS8842 is not set
 # CONFIG_KS8851_MLL is not set
 CONFIG_XILINX_EMACLITE=y
@@ -444,6 +475,7 @@
 CONFIG_SERIAL_UARTLITE_CONSOLE=y
 CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y
+# CONFIG_SERIAL_TIMBERDALE is not set
 # CONFIG_SERIAL_GRLIB_GAISLER_APBUART is not set
 CONFIG_UNIX98_PTYS=y
 # CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
@@ -471,6 +503,12 @@
 # CONFIG_HWMON is not set
 # CONFIG_THERMAL is not set
 # CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
 
 #
 # Multifunction device drivers
@@ -502,6 +540,7 @@
 # CONFIG_NEW_LEDS is not set
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_RTC_CLASS is not set
+# CONFIG_DMADEVICES is not set
 # CONFIG_AUXDISPLAY is not set
 # CONFIG_UIO is not set
 
@@ -572,6 +611,7 @@
 # CONFIG_BEFS_FS is not set
 # CONFIG_BFS_FS is not set
 # CONFIG_EFS_FS is not set
+# CONFIG_LOGFS is not set
 # CONFIG_CRAMFS is not set
 # CONFIG_SQUASHFS is not set
 # CONFIG_VXFS_FS is not set
@@ -595,6 +635,7 @@
 # CONFIG_RPCSEC_GSS_KRB5 is not set
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
+# CONFIG_CEPH_FS is not set
 CONFIG_CIFS=y
 CONFIG_CIFS_STATS=y
 CONFIG_CIFS_STATS2=y
@@ -696,6 +737,7 @@
 # CONFIG_DEBUG_OBJECTS is not set
 CONFIG_DEBUG_SLAB=y
 # CONFIG_DEBUG_SLAB_LEAK is not set
+# CONFIG_DEBUG_KMEMLEAK is not set
 CONFIG_DEBUG_SPINLOCK=y
 # CONFIG_DEBUG_MUTEXES is not set
 # CONFIG_DEBUG_LOCK_ALLOC is not set
@@ -741,6 +783,7 @@
 # CONFIG_KMEMTRACE is not set
 # CONFIG_WORKQUEUE_TRACER is not set
 # CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_EARLY_PRINTK=y
 # CONFIG_HEART_BEAT is not set
@@ -862,5 +905,6 @@
 CONFIG_DECOMPRESS_GZIP=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
 CONFIG_HAVE_LMB=y
 CONFIG_NLATTR=y

arch/microblaze/configs/nommu_defconfig

diff --git a/arch/microblaze/configs/nommu_defconfig b/arch/microblaze/configs/nommu_defconfig
index ce2da53..dd3a494 100644
--- a/arch/microblaze/configs/nommu_defconfig
+++ b/arch/microblaze/configs/nommu_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.33-rc6
-# Wed Feb  3 10:03:21 2010
+# Linux kernel version: 2.6.34-rc6
+# Thu May  6 11:25:12 2010
 #
 CONFIG_MICROBLAZE=y
 # CONFIG_SWAP is not set
@@ -22,8 +22,6 @@
 CONFIG_STACKTRACE_SUPPORT=y
 CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_HAVE_LATENCYTOP_SUPPORT=y
-# CONFIG_PCI is not set
-CONFIG_NO_DMA=y
 CONFIG_DTC=y
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 CONFIG_CONSTRUCTORS=y
@@ -58,7 +56,6 @@
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=17
-# CONFIG_GROUP_SCHED is not set
 # CONFIG_CGROUPS is not set
 CONFIG_SYSFS_DEPRECATED=y
 CONFIG_SYSFS_DEPRECATED_V2=y
@@ -96,6 +93,8 @@
 # CONFIG_MMAP_ALLOW_UNINITIALIZED is not set
 # CONFIG_PROFILING is not set
 CONFIG_HAVE_OPROFILE=y
+CONFIG_HAVE_DMA_ATTRS=y
+CONFIG_HAVE_DMA_API_DEBUG=y
 
 #
 # GCOV-based kernel profiling
@@ -209,11 +208,14 @@
 #
 # Advanced setup
 #
+# CONFIG_ADVANCED_OPTIONS is not set
 
 #
 # Default settings for advanced configuration options are used
 #
+CONFIG_LOWMEM_SIZE=0x30000000
 CONFIG_KERNEL_START=0x90000000
+CONFIG_TASK_SIZE=0x80000000
 CONFIG_SELECT_MEMORY_MODEL=y
 CONFIG_FLATMEM_MANUAL=y
 # CONFIG_DISCONTIGMEM_MANUAL is not set
@@ -235,13 +237,20 @@
 # CONFIG_BINFMT_SHARED_FLAT is not set
 # CONFIG_HAVE_AOUT is not set
 # CONFIG_BINFMT_MISC is not set
+
+#
+# Bus Options
+#
+# CONFIG_PCI is not set
+# CONFIG_PCI_DOMAINS is not set
+# CONFIG_PCI_SYSCALL is not set
+# CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_NET=y
 
 #
 # Networking options
 #
 CONFIG_PACKET=y
-# CONFIG_PACKET_MMAP is not set
 CONFIG_UNIX=y
 CONFIG_XFRM=y
 # CONFIG_XFRM_USER is not set
@@ -413,6 +422,7 @@
 # UBI - Unsorted block images
 #
 # CONFIG_MTD_UBI is not set
+CONFIG_OF_FLATTREE=y
 CONFIG_OF_DEVICE=y
 # CONFIG_PARPORT is not set
 CONFIG_BLK_DEV=y
@@ -442,6 +452,7 @@
 #
 # SCSI device support
 #
+CONFIG_SCSI_MOD=y
 # CONFIG_RAID_ATTRS is not set
 # CONFIG_SCSI is not set
 # CONFIG_SCSI_DMA is not set
@@ -458,6 +469,7 @@
 # CONFIG_PHYLIB is not set
 CONFIG_NET_ETHERNET=y
 # CONFIG_MII is not set
+# CONFIG_ETHOC is not set
 # CONFIG_DNET is not set
 # CONFIG_IBM_NEW_EMAC_ZMII is not set
 # CONFIG_IBM_NEW_EMAC_RGMII is not set
@@ -466,6 +478,7 @@
 # CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
 # CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
 # CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
+# CONFIG_B44 is not set
 # CONFIG_KS8842 is not set
 # CONFIG_KS8851_MLL is not set
 # CONFIG_XILINX_EMACLITE is not set
@@ -516,6 +529,7 @@
 CONFIG_SERIAL_UARTLITE_CONSOLE=y
 CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y
+# CONFIG_SERIAL_TIMBERDALE is not set
 # CONFIG_SERIAL_GRLIB_GAISLER_APBUART is not set
 CONFIG_UNIX98_PTYS=y
 # CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
@@ -544,6 +558,12 @@
 # CONFIG_HWMON is not set
 # CONFIG_THERMAL is not set
 # CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
 
 #
 # Multifunction device drivers
@@ -593,6 +613,7 @@
 # CONFIG_NEW_LEDS is not set
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_RTC_CLASS is not set
+# CONFIG_DMADEVICES is not set
 # CONFIG_AUXDISPLAY is not set
 # CONFIG_UIO is not set
 
@@ -661,6 +682,7 @@
 # CONFIG_BFS_FS is not set
 # CONFIG_EFS_FS is not set
 # CONFIG_JFFS2_FS is not set
+# CONFIG_LOGFS is not set
 CONFIG_CRAMFS=y
 # CONFIG_SQUASHFS is not set
 # CONFIG_VXFS_FS is not set
@@ -689,6 +711,7 @@
 # CONFIG_RPCSEC_GSS_KRB5 is not set
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
+# CONFIG_CEPH_FS is not set
 # CONFIG_CIFS is not set
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
@@ -733,6 +756,7 @@
 # CONFIG_DEBUG_OBJECTS_WORK is not set
 CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1
 # CONFIG_DEBUG_SLAB is not set
+# CONFIG_DEBUG_KMEMLEAK is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
 # CONFIG_RT_MUTEX_TESTER is not set
 # CONFIG_DEBUG_SPINLOCK is not set
@@ -758,6 +782,7 @@
 # CONFIG_BACKTRACE_SELF_TEST is not set
 # CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
 # CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
+# CONFIG_LKDTM is not set
 # CONFIG_FAULT_INJECTION is not set
 # CONFIG_LATENCYTOP is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
@@ -782,6 +807,7 @@
 # CONFIG_WORKQUEUE_TRACER is not set
 # CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_EARLY_PRINTK=y
 # CONFIG_HEART_BEAT is not set
@@ -901,5 +927,6 @@
 CONFIG_ZLIB_INFLATE=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
 CONFIG_HAVE_LMB=y
 CONFIG_NLATTR=y

arch/microblaze/include/asm/cache.h

diff --git a/arch/microblaze/include/asm/cache.h b/arch/microblaze/include/asm/cache.h
index e522108..4efe96a 100644
--- a/arch/microblaze/include/asm/cache.h
+++ b/arch/microblaze/include/asm/cache.h
@@ -15,7 +15,7 @@
 
 #include <asm/registers.h>
 
-#define L1_CACHE_SHIFT	2
+#define L1_CACHE_SHIFT 5
 /* word-granular cache in microblaze */
 #define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
 

arch/microblaze/include/asm/dma.h

diff --git a/arch/microblaze/include/asm/dma.h b/arch/microblaze/include/asm/dma.h
index 08c073b..0d73d0c 100644
--- a/arch/microblaze/include/asm/dma.h
+++ b/arch/microblaze/include/asm/dma.h
@@ -18,4 +18,10 @@
 #define MAX_DMA_ADDRESS (CONFIG_KERNEL_START + memory_size - 1)
 #endif
 
+#ifdef CONFIG_PCI
+extern int isa_dma_bridge_buggy;
+#else
+#define isa_dma_bridge_buggy     (0)
+#endif
+
 #endif /* _ASM_MICROBLAZE_DMA_H */

arch/microblaze/include/asm/exceptions.h

diff --git a/arch/microblaze/include/asm/exceptions.h b/arch/microblaze/include/asm/exceptions.h
index 90731df..4c7b5d0 100644
--- a/arch/microblaze/include/asm/exceptions.h
+++ b/arch/microblaze/include/asm/exceptions.h
@@ -64,12 +64,6 @@
 void die(const char *str, struct pt_regs *fp, long err);
 void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr);
 
-#ifdef CONFIG_MMU
-void __bug(const char *file, int line, void *data);
-int bad_trap(int trap_num, struct pt_regs *regs);
-int debug_trap(struct pt_regs *regs);
-#endif /* CONFIG_MMU */
-
 #if defined(CONFIG_KGDB)
 void (*debugger)(struct pt_regs *regs);
 int (*debugger_bpt)(struct pt_regs *regs);

arch/microblaze/include/asm/io.h

diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index e45a6ee..00b5398 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -139,8 +139,6 @@
 
 #ifdef CONFIG_MMU
 
-#define mm_ptov(addr)		((void *)__phys_to_virt(addr))
-#define mm_vtop(addr)		((unsigned long)__virt_to_phys(addr))
 #define phys_to_virt(addr)	((void *)__phys_to_virt(addr))
 #define virt_to_phys(addr)	((unsigned long)__virt_to_phys(addr))
 #define virt_to_bus(addr)	((unsigned long)__virt_to_phys(addr))

arch/microblaze/include/asm/page.h

diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h
index 2dd1d04..de493f8 100644
--- a/arch/microblaze/include/asm/page.h
+++ b/arch/microblaze/include/asm/page.h
@@ -31,6 +31,9 @@
 
 #ifndef __ASSEMBLY__
 
+/* MS be sure that SLAB allocates aligned objects */
+#define ARCH_KMALLOC_MINALIGN	L1_CACHE_BYTES
+
 #define PAGE_UP(addr)	(((addr)+((PAGE_SIZE)-1))&(~((PAGE_SIZE)-1)))
 #define PAGE_DOWN(addr)	((addr)&(~((PAGE_SIZE)-1)))
 
@@ -70,14 +73,7 @@
 
 #endif /* CONFIG_MMU */
 
-#  ifndef CONFIG_MMU
-#  define copy_page(to, from)			memcpy((to), (from), PAGE_SIZE)
-#  define get_user_page(vaddr)			__get_free_page(GFP_KERNEL)
-#  define free_user_page(page, addr)		free_page(addr)
-#  else /* CONFIG_MMU */
-extern void copy_page(void *to, void *from);
-#  endif /* CONFIG_MMU */
-
+# define copy_page(to, from)			memcpy((to), (from), PAGE_SIZE)
 # define clear_page(pgaddr)			memset((pgaddr), 0, PAGE_SIZE)
 
 # define clear_user_page(pgaddr, vaddr, page)	memset((pgaddr), 0, PAGE_SIZE)

arch/microblaze/include/asm/pci.h

diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h
index bdd65aa..5a388ee 100644
--- a/arch/microblaze/include/asm/pci.h
+++ b/arch/microblaze/include/asm/pci.h
@@ -94,14 +94,6 @@
 
 #define HAVE_PCI_LEGACY	1
 
-/* pci_unmap_{page,single} is a nop so... */
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
-#define pci_unmap_addr(PTR, ADDR_NAME)		(0)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)	do { } while (0)
-#define pci_unmap_len(PTR, LEN_NAME)		(0)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)	do { } while (0)
-
 /* The PCI address space does equal the physical memory
  * address space (no IOMMU).  The IDE and SCSI device layers use
  * this boolean for bounce buffer decisions.

arch/microblaze/include/asm/pgalloc.h

diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h
index f44b0d6..c614a89 100644
--- a/arch/microblaze/include/asm/pgalloc.h
+++ b/arch/microblaze/include/asm/pgalloc.h
@@ -108,21 +108,7 @@
 #define pmd_alloc_one_fast(mm, address)	({ BUG(); ((pmd_t *)1); })
 #define pmd_alloc_one(mm, address)	({ BUG(); ((pmd_t *)2); })
 
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
-		unsigned long address)
-{
-	pte_t *pte;
-	extern void *early_get_page(void);
-	if (mem_init_done) {
-		pte = (pte_t *)__get_free_page(GFP_KERNEL |
-					__GFP_REPEAT | __GFP_ZERO);
-	} else {
-		pte = (pte_t *)early_get_page();
-		if (pte)
-			clear_page(pte);
-	}
-	return pte;
-}
+extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
 
 static inline struct page *pte_alloc_one(struct mm_struct *mm,
 		unsigned long address)

arch/microblaze/include/asm/pgtable.h

diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h
index dd2bb60..ca2d928 100644
--- a/arch/microblaze/include/asm/pgtable.h
+++ b/arch/microblaze/include/asm/pgtable.h
@@ -512,15 +512,6 @@
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 /*
- * When flushing the tlb entry for a page, we also need to flush the hash
- * table entry.  flush_hash_page is assembler (for speed) in hashtable.S.
- */
-extern int flush_hash_page(unsigned context, unsigned long va, pte_t *ptep);
-
-/* Add an HPTE to the hash table */
-extern void add_hash_page(unsigned context, unsigned long va, pte_t *ptep);
-
-/*
  * Encode and decode a swap entry.
  * Note that the bits we use in a PTE for representing a swap entry
  * must not include the _PAGE_PRESENT bit, or the _PAGE_HASHPTE bit
@@ -533,15 +524,7 @@
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) >> 2 })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val << 2 })
 
-
-/* CONFIG_APUS */
-/* For virtual address to physical address conversion */
-extern void cache_clear(__u32 addr, int length);
-extern void cache_push(__u32 addr, int length);
-extern int mm_end_of_chunk(unsigned long addr, int len);
 extern unsigned long iopa(unsigned long addr);
-/* extern unsigned long mm_ptov(unsigned long addr) \
-	__attribute__ ((const)); TBD */
 
 /* Values for nocacheflag and cmode */
 /* These are not used by the APUS kernel_map, but prevents
@@ -552,18 +535,6 @@
 #define	IOMAP_NOCACHE_NONSER	2
 #define	IOMAP_NO_COPYBACK	3
 
-/*
- * Map some physical address range into the kernel address space.
- */
-extern unsigned long kernel_map(unsigned long paddr, unsigned long size,
-				int nocacheflag, unsigned long *memavailp);
-
-/*
- * Set cache mode of (kernel space) address range.
- */
-extern void kernel_set_cachemode(unsigned long address, unsigned long size,
-				unsigned int cmode);
-
 /* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
 #define kern_addr_valid(addr)	(1)
 
@@ -577,10 +548,6 @@
 void do_page_fault(struct pt_regs *regs, unsigned long address,
 		   unsigned long error_code);
 
-void __init io_block_mapping(unsigned long virt, phys_addr_t phys,
-			     unsigned int size, int flags);
-
-void __init adjust_total_lowmem(void);
 void mapin_ram(void);
 int map_page(unsigned long va, phys_addr_t pa, int flags);
 
@@ -601,7 +568,7 @@
 extern unsigned long ioremap_bot, ioremap_base;
 
 void *consistent_alloc(int gfp, size_t size, dma_addr_t *dma_handle);
-void consistent_free(void *vaddr);
+void consistent_free(size_t size, void *vaddr);
 void consistent_sync(void *vaddr, size_t size, int direction);
 void consistent_sync_page(struct page *page, unsigned long offset,
 	size_t size, int direction);

arch/microblaze/include/asm/uaccess.h

diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 446bec2..26460d1 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -182,6 +182,39 @@
  * Returns zero on success, or -EFAULT on error.
  * On error, the variable @x is set to zero.
  */
+#define get_user(x, ptr)						\
+	__get_user_check((x), (ptr), sizeof(*(ptr)))
+
+#define __get_user_check(x, ptr, size)					\
+({									\
+	unsigned long __gu_val = 0;					\
+	const typeof(*(ptr)) __user *__gu_addr = (ptr);			\
+	int __gu_err = 0;						\
+									\
+	if (access_ok(VERIFY_READ, __gu_addr, size)) {			\
+		switch (size) {						\
+		case 1:							\
+			__get_user_asm("lbu", __gu_addr, __gu_val,	\
+				       __gu_err);			\
+			break;						\
+		case 2:							\
+			__get_user_asm("lhu", __gu_addr, __gu_val,	\
+				       __gu_err);			\
+			break;						\
+		case 4:							\
+			__get_user_asm("lw", __gu_addr, __gu_val,	\
+				       __gu_err);			\
+			break;						\
+		default:						\
+			__gu_err = __user_bad();			\
+			break;						\
+		}							\
+	} else {							\
+		__gu_err = -EFAULT;					\
+	}								\
+	x = (typeof(*(ptr)))__gu_val;					\
+	__gu_err;							\
+})
 
 #define __get_user(x, ptr)						\
 ({									\
@@ -206,12 +239,6 @@
 })
 
 
-#define get_user(x, ptr)						\
-({									\
-	access_ok(VERIFY_READ, (ptr), sizeof(*(ptr)))			\
-		? __get_user((x), (ptr)) : -EFAULT;			\
-})
-
 #define __put_user_asm(insn, __gu_ptr, __gu_val, __gu_err)	\
 ({								\
 	__asm__ __volatile__ (					\
@@ -266,6 +293,42 @@
  *
  * Returns zero on success, or -EFAULT on error.
  */
+#define put_user(x, ptr)						\
+	__put_user_check((x), (ptr), sizeof(*(ptr)))
+
+#define __put_user_check(x, ptr, size)					\
+({									\
+	typeof(*(ptr)) __pu_val;					\
+	typeof(*(ptr)) __user *__pu_addr = (ptr);			\
+	int __pu_err = 0;						\
+									\
+	__pu_val = (x);							\
+	if (access_ok(VERIFY_WRITE, __pu_addr, size)) {			\
+		switch (size) {						\
+		case 1:							\
+			__put_user_asm("sb", __pu_addr, __pu_val,	\
+				       __pu_err);			\
+			break;						\
+		case 2:							\
+			__put_user_asm("sh", __pu_addr, __pu_val,	\
+				       __pu_err);			\
+			break;						\
+		case 4:							\
+			__put_user_asm("sw", __pu_addr, __pu_val,	\
+				       __pu_err);			\
+			break;						\
+		case 8:							\
+			__put_user_asm_8(__pu_addr, __pu_val, __pu_err);\
+			break;						\
+		default:						\
+			__pu_err = __user_bad();			\
+			break;						\
+		}							\
+	} else {							\
+		__pu_err = -EFAULT;					\
+	}								\
+	__pu_err;							\
+})
 
 #define __put_user(x, ptr)						\
 ({									\
@@ -290,18 +353,6 @@
 	__gu_err;							\
 })
 
-#ifndef CONFIG_MMU
-
-#define put_user(x, ptr)	__put_user((x), (ptr))
-
-#else /* CONFIG_MMU */
-
-#define put_user(x, ptr)						\
-({									\
-	access_ok(VERIFY_WRITE, (ptr), sizeof(*(ptr)))			\
-		? __put_user((x), (ptr)) : -EFAULT;			\
-})
-#endif /* CONFIG_MMU */
 
 /* copy_to_from_user */
 #define __copy_from_user(to, from, n)	\

arch/microblaze/kernel/asm-offsets.c

diff --git a/arch/microblaze/kernel/asm-offsets.c b/arch/microblaze/kernel/asm-offsets.c
index 0071260..c1b459c 100644
--- a/arch/microblaze/kernel/asm-offsets.c
+++ b/arch/microblaze/kernel/asm-offsets.c
@@ -16,6 +16,7 @@
 #include <linux/hardirq.h>
 #include <linux/thread_info.h>
 #include <linux/kbuild.h>
+#include <asm/cpuinfo.h>
 
 int main(int argc, char *argv[])
 {

arch/microblaze/kernel/cpu/cache.c

diff --git a/arch/microblaze/kernel/cpu/cache.c b/arch/microblaze/kernel/cpu/cache.c
index f04d8a8..109876e 100644
--- a/arch/microblaze/kernel/cpu/cache.c
+++ b/arch/microblaze/kernel/cpu/cache.c
@@ -96,13 +96,16 @@
 }
 
 
-/* Helper macro for computing the limits of cache range loops */
+/* Helper macro for computing the limits of cache range loops
+ *
+ * End address can be unaligned which is OK for C implementation.
+ * ASM implementation align it in ASM macros
+ */
 #define CACHE_LOOP_LIMITS(start, end, cache_line_length, cache_size)	\
 do {									\
 	int align = ~(cache_line_length - 1);				\
 	end = min(start + cache_size, end);				\
 	start &= align;							\
-	end = ((end & align) + cache_line_length);			\
 } while (0);
 
 /*
@@ -111,9 +114,9 @@
  */
 #define CACHE_ALL_LOOP(cache_size, line_length, op)			\
 do {									\
-	unsigned int len = cache_size;					\
+	unsigned int len = cache_size - line_length;			\
 	int step = -line_length;					\
-	BUG_ON(step >= 0);						\
+	WARN_ON(step >= 0);						\
 									\
 	__asm__ __volatile__ (" 1:      " #op " %0, r0;			\
 					bgtid   %0, 1b;			\
@@ -122,26 +125,22 @@
 					: "memory");			\
 } while (0);
 
-
-#define CACHE_ALL_LOOP2(cache_size, line_length, op)			\
-do {									\
-	unsigned int len = cache_size;					\
-	int step = -line_length;					\
-	BUG_ON(step >= 0);						\
-									\
-	__asm__ __volatile__ (" 1:	" #op "	r0, %0;			\
-					bgtid	%0, 1b;			\
-					addk	%0, %0, %1;		\
-					" : : "r" (len), "r" (step)	\
-					: "memory");			\
-} while (0);
-
-/* for wdc.flush/clear */
+/* Used for wdc.flush/clear which can use rB for offset which is not possible
+ * to use for simple wdc or wic.
+ *
+ * start address is cache aligned
+ * end address is not aligned, if end is aligned then I have to substract
+ * cacheline length because I can't flush/invalidate the next cacheline.
+ * If is not, I align it because I will flush/invalidate whole line.
+ */
 #define CACHE_RANGE_LOOP_2(start, end, line_length, op)			\
 do {									\
 	int step = -line_length;					\
-	int count = end - start;					\
-	BUG_ON(count <= 0);						\
+	int align = ~(line_length - 1);					\
+	int count;							\
+	end = ((end & align) == end) ? end - line_length : end & align;	\
+	count = end - start;						\
+	WARN_ON(count < 0);						\
 									\
 	__asm__ __volatile__ (" 1:	" #op "	%0, %1;			\
 					bgtid	%1, 1b;			\
@@ -154,7 +153,9 @@
 #define CACHE_RANGE_LOOP_1(start, end, line_length, op)			\
 do {									\
 	int volatile temp;						\
-	BUG_ON(end - start <= 0);					\
+	int align = ~(line_length - 1);					\
+	end = ((end & align) == end) ? end - line_length : end & align;	\
+	WARN_ON(end - start < 0);					\
 									\
 	__asm__ __volatile__ (" 1:	" #op "	%1, r0;			\
 					cmpu	%0, %1, %2;		\
@@ -360,8 +361,12 @@
 #endif
 }
 
-/* FIXME this is weird - should be only wdc but not work
- * MS: I am getting bus errors and other weird things */
+/* FIXME It is blindly invalidation as is expected
+ * but can't be called on noMMU in microblaze_cache_init below
+ *
+ * MS: noMMU kernel won't boot if simple wdc is used
+ * The reason should be that there are discared data which kernel needs
+ */
 static void __invalidate_dcache_all_wb(void)
 {
 #ifndef ASM_LOOP
@@ -369,12 +374,12 @@
 #endif
 	pr_debug("%s\n", __func__);
 #ifdef ASM_LOOP
-	CACHE_ALL_LOOP2(cpuinfo.dcache_size, cpuinfo.dcache_line_length,
-					wdc.clear)
+	CACHE_ALL_LOOP(cpuinfo.dcache_size, cpuinfo.dcache_line_length,
+					wdc)
 #else
 	for (i = 0; i < cpuinfo.dcache_size;
 		 i += cpuinfo.dcache_line_length)
-			__asm__ __volatile__ ("wdc.clear	%0, r0;" \
+			__asm__ __volatile__ ("wdc	%0, r0;" \
 					: : "r" (i));
 #endif
 }
@@ -393,7 +398,7 @@
 #ifdef ASM_LOOP
 	CACHE_RANGE_LOOP_2(start, end, cpuinfo.dcache_line_length, wdc.clear);
 #else
-	for (i = start; i < end; i += cpuinfo.icache_line_length)
+	for (i = start; i < end; i += cpuinfo.dcache_line_length)
 		__asm__ __volatile__ ("wdc.clear	%0, r0;"	\
 				: : "r" (i));
 #endif
@@ -413,7 +418,7 @@
 #ifdef ASM_LOOP
 	CACHE_RANGE_LOOP_1(start, end, cpuinfo.dcache_line_length, wdc);
 #else
-	for (i = start; i < end; i += cpuinfo.icache_line_length)
+	for (i = start; i < end; i += cpuinfo.dcache_line_length)
 		__asm__ __volatile__ ("wdc	%0, r0;"	\
 				: : "r" (i));
 #endif
@@ -437,7 +442,7 @@
 #ifdef ASM_LOOP
 	CACHE_RANGE_LOOP_1(start, end, cpuinfo.dcache_line_length, wdc);
 #else
-	for (i = start; i < end; i += cpuinfo.icache_line_length)
+	for (i = start; i < end; i += cpuinfo.dcache_line_length)
 		__asm__ __volatile__ ("wdc	%0, r0;"	\
 				: : "r" (i));
 #endif
@@ -465,7 +470,7 @@
 #ifdef ASM_LOOP
 	CACHE_RANGE_LOOP_1(start, end, cpuinfo.dcache_line_length, wdc);
 #else
-	for (i = start; i < end; i += cpuinfo.icache_line_length)
+	for (i = start; i < end; i += cpuinfo.dcache_line_length)
 		__asm__ __volatile__ ("wdc	%0, r0;"	\
 				: : "r" (i));
 #endif
@@ -504,7 +509,7 @@
 #ifdef ASM_LOOP
 	CACHE_RANGE_LOOP_2(start, end, cpuinfo.dcache_line_length, wdc.flush);
 #else
-	for (i = start; i < end; i += cpuinfo.icache_line_length)
+	for (i = start; i < end; i += cpuinfo.dcache_line_length)
 		__asm__ __volatile__ ("wdc.flush	%0, r0;"	\
 				: : "r" (i));
 #endif
@@ -650,7 +655,11 @@
 			}
 		}
 	}
-	invalidate_dcache();
+/* FIXME Invalidation is done in U-BOOT
+ * WT cache: Data is already written to main memory
+ * WB cache: Discard data on noMMU which caused that kernel doesn't boot
+ */
+	/* invalidate_dcache(); */
 	enable_dcache();
 
 	invalidate_icache();

arch/microblaze/kernel/cpu/mb.c

diff --git a/arch/microblaze/kernel/cpu/mb.c b/arch/microblaze/kernel/cpu/mb.c
index 0c912b2..4216eb1 100644
--- a/arch/microblaze/kernel/cpu/mb.c
+++ b/arch/microblaze/kernel/cpu/mb.c
@@ -98,15 +98,17 @@
 
 	if (cpuinfo.use_icache)
 		count += seq_printf(m,
-				"Icache:\t\t%ukB\n",
-				cpuinfo.icache_size >> 10);
+				"Icache:\t\t%ukB\tline length:\t%dB\n",
+				cpuinfo.icache_size >> 10,
+				cpuinfo.icache_line_length);
 	else
 		count += seq_printf(m, "Icache:\t\tno\n");
 
 	if (cpuinfo.use_dcache) {
 		count += seq_printf(m,
-				"Dcache:\t\t%ukB\n",
-				cpuinfo.dcache_size >> 10);
+				"Dcache:\t\t%ukB\tline length:\t%dB\n",
+				cpuinfo.dcache_size >> 10,
+				cpuinfo.dcache_line_length);
 		if (cpuinfo.dcache_wb)
 			count += seq_printf(m, "\t\twrite-back\n");
 		else

arch/microblaze/kernel/dma.c

diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index ce72dd4..9dcd90b 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -74,7 +74,7 @@
 			      void *vaddr, dma_addr_t dma_handle)
 {
 #ifdef NOT_COHERENT_CACHE
-	consistent_free(vaddr);
+	consistent_free(size, vaddr);
 #else
 	free_pages((unsigned long)vaddr, get_order(size));
 #endif

arch/microblaze/kernel/entry-nommu.S

diff --git a/arch/microblaze/kernel/entry-nommu.S b/arch/microblaze/kernel/entry-nommu.S
index 391d619..8cc18cd 100644
--- a/arch/microblaze/kernel/entry-nommu.S
+++ b/arch/microblaze/kernel/entry-nommu.S
@@ -476,6 +476,8 @@
 	nop
 
 work_pending:
+	enable_irq
+
 	andi	r11, r19, _TIF_NEED_RESCHED
 	beqi	r11, 1f
 	bralid	r15, schedule

arch/microblaze/kernel/exceptions.c

diff --git a/arch/microblaze/kernel/exceptions.c b/arch/microblaze/kernel/exceptions.c
index d9f70f8..02cbdfe 100644
--- a/arch/microblaze/kernel/exceptions.c
+++ b/arch/microblaze/kernel/exceptions.c
@@ -121,7 +121,7 @@
 		}
 		printk(KERN_WARNING "Divide by zero exception " \
 							"in kernel mode.\n");
-		die("Divide by exception", regs, SIGBUS);
+		die("Divide by zero exception", regs, SIGBUS);
 		break;
 	case MICROBLAZE_FPU_EXCEPTION:
 		pr_debug(KERN_WARNING "FPU exception\n");

arch/microblaze/kernel/head.S

diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S
index da6a5f5..1bf7398 100644
--- a/arch/microblaze/kernel/head.S
+++ b/arch/microblaze/kernel/head.S
@@ -28,6 +28,7 @@
  * for more details.
  */
 
+#include <linux/init.h>
 #include <linux/linkage.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
@@ -49,7 +50,7 @@
 
 #endif /* CONFIG_MMU */
 
-	.text
+	__HEAD
 ENTRY(_start)
 #if CONFIG_KERNEL_BASE_ADDR == 0
 	brai	TOPHYS(real_start)

arch/microblaze/kernel/irq.c

diff --git a/arch/microblaze/kernel/irq.c b/arch/microblaze/kernel/irq.c
index 6f39e2c..8f120ac 100644
--- a/arch/microblaze/kernel/irq.c
+++ b/arch/microblaze/kernel/irq.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/ftrace.h>
 #include <linux/kernel.h>
 #include <linux/hardirq.h>
 #include <linux/interrupt.h>
@@ -32,7 +33,7 @@
 
 static u32 concurrent_irq;
 
-void do_IRQ(struct pt_regs *regs)
+void __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	unsigned int irq;
 	struct pt_regs *old_regs = set_irq_regs(regs);

arch/microblaze/kernel/microblaze_ksyms.c

diff --git a/arch/microblaze/kernel/microblaze_ksyms.c b/arch/microblaze/kernel/microblaze_ksyms.c
index bc4dcb7..ff85f77 100644
--- a/arch/microblaze/kernel/microblaze_ksyms.c
+++ b/arch/microblaze/kernel/microblaze_ksyms.c
@@ -52,3 +52,14 @@
 extern void _mcount(void);
 EXPORT_SYMBOL(_mcount);
 #endif
+
+/*
+ * Assembly functions that may be used (directly or indirectly) by modules
+ */
+EXPORT_SYMBOL(__copy_tofrom_user);
+EXPORT_SYMBOL(__strncpy_user);
+
+#ifdef CONFIG_OPT_LIB_ASM
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(memmove);
+#endif

arch/microblaze/kernel/misc.S

diff --git a/arch/microblaze/kernel/misc.S b/arch/microblaze/kernel/misc.S
index 7cf8649..0fb5fc6 100644
--- a/arch/microblaze/kernel/misc.S
+++ b/arch/microblaze/kernel/misc.S
@@ -93,39 +93,3 @@
 	nop
 
 	.size  early_console_reg_tlb_alloc, . - early_console_reg_tlb_alloc
-
-/*
- * Copy a whole page (4096 bytes).
- */
-#define COPY_16_BYTES		\
-	lwi	r7, r6, 0;	\
-	lwi	r8, r6, 4;	\
-	lwi	r9, r6, 8;	\
-	lwi	r10, r6, 12;	\
-	swi	r7, r5, 0;	\
-	swi	r8, r5, 4;	\
-	swi	r9, r5, 8;	\
-	swi	r10, r5, 12
-
-
-/* FIXME DCACHE_LINE_BYTES (CONFIG_XILINX_MICROBLAZE0_DCACHE_LINE_LEN * 4)*/
-#define DCACHE_LINE_BYTES (4 * 4)
-
-.globl copy_page;
-.type  copy_page, @function
-.align 4;
-copy_page:
-	ori	r11, r0, (PAGE_SIZE/DCACHE_LINE_BYTES) - 1
-_copy_page_loop:
-	COPY_16_BYTES
-#if DCACHE_LINE_BYTES >= 32
-	COPY_16_BYTES
-#endif
-	addik	r6, r6, DCACHE_LINE_BYTES
-	addik	r5, r5, DCACHE_LINE_BYTES
-	bneid	r11, _copy_page_loop
-	addik	r11, r11, -1
-	rtsd	r15, 8
-	nop
-
-	.size  copy_page, . - copy_page

arch/microblaze/kernel/module.c

diff --git a/arch/microblaze/kernel/module.c b/arch/microblaze/kernel/module.c
index cbecf11..0e73f66 100644
--- a/arch/microblaze/kernel/module.c
+++ b/arch/microblaze/kernel/module.c
@@ -16,6 +16,7 @@
 #include <linux/string.h>
 
 #include <asm/pgtable.h>
+#include <asm/cacheflush.h>
 
 void *module_alloc(unsigned long size)
 {
@@ -151,6 +152,7 @@
 int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
 		struct module *module)
 {
+	flush_dcache();
 	return 0;
 }
 

arch/microblaze/kernel/traps.c

diff --git a/arch/microblaze/kernel/traps.c b/arch/microblaze/kernel/traps.c
index 5e4570e..75e4920 100644
--- a/arch/microblaze/kernel/traps.c
+++ b/arch/microblaze/kernel/traps.c
@@ -95,37 +95,3 @@
 	show_stack(NULL, NULL);
 }
 EXPORT_SYMBOL(dump_stack);
-
-#ifdef CONFIG_MMU
-void __bug(const char *file, int line, void *data)
-{
-	if (data)
-		printk(KERN_CRIT "kernel BUG at %s:%d (data = %p)!\n",
-			file, line, data);
-	else
-		printk(KERN_CRIT "kernel BUG at %s:%d!\n", file, line);
-
-	machine_halt();
-}
-
-int bad_trap(int trap_num, struct pt_regs *regs)
-{
-	printk(KERN_CRIT
-		"unimplemented trap %d called at 0x%08lx, pid %d!\n",
-		trap_num, regs->pc, current->pid);
-	return -ENOSYS;
-}
-
-int debug_trap(struct pt_regs *regs)
-{
-	int i;
-	printk(KERN_CRIT "debug trap\n");
-	for (i = 0; i < 32; i++) {
-		/* printk("r%i:%08X\t",i,regs->gpr[i]); */
-		if ((i % 4) == 3)
-			printk(KERN_CRIT "\n");
-	}
-	printk(KERN_CRIT "pc:%08lX\tmsr:%08lX\n", regs->pc, regs->msr);
-	return -ENOSYS;
-}
-#endif

arch/microblaze/kernel/vmlinux.lds.S

diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S
index 5ef619a..db72d71 100644
--- a/arch/microblaze/kernel/vmlinux.lds.S
+++ b/arch/microblaze/kernel/vmlinux.lds.S
@@ -24,7 +24,8 @@
 	.text : AT(ADDR(.text) - LOAD_OFFSET) {
 		_text = . ;
 		_stext = . ;
-		*(.text .text.*)
+		HEAD_TEXT
+		TEXT_TEXT
 		*(.fixup)
 		EXIT_TEXT
 		EXIT_CALL

arch/microblaze/mm/consistent.c

diff --git a/arch/microblaze/mm/consistent.c b/arch/microblaze/mm/consistent.c
index f956e24..5a59dad 100644
--- a/arch/microblaze/mm/consistent.c
+++ b/arch/microblaze/mm/consistent.c
@@ -42,11 +42,12 @@
 #include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cpuinfo.h>
+#include <asm/tlbflush.h>
 
 #ifndef CONFIG_MMU
-
 /* I have to use dcache values because I can't relate on ram size */
-#define UNCACHED_SHADOW_MASK (cpuinfo.dcache_high - cpuinfo.dcache_base + 1)
+# define UNCACHED_SHADOW_MASK (cpuinfo.dcache_high - cpuinfo.dcache_base + 1)
+#endif
 
 /*
  * Consistent memory allocators. Used for DMA devices that want to
@@ -60,71 +61,16 @@
  */
 void *consistent_alloc(int gfp, size_t size, dma_addr_t *dma_handle)
 {
-	struct page *page, *end, *free;
-	unsigned long order;
-	void *ret, *virt;
+	unsigned long order, vaddr;
+	void *ret;
+	unsigned int i, err = 0;
+	struct page *page, *end;
 
-	if (in_interrupt())
-		BUG();
-
-	size = PAGE_ALIGN(size);
-	order = get_order(size);
-
-	page = alloc_pages(gfp, order);
-	if (!page)
-		goto no_page;
-
-	/* We could do with a page_to_phys and page_to_bus here. */
-	virt = page_address(page);
-	ret = ioremap(virt_to_phys(virt), size);
-	if (!ret)
-		goto no_remap;
-
-	/*
-	 * Here's the magic!  Note if the uncached shadow is not implemented,
-	 * it's up to the calling code to also test that condition and make
-	 * other arranegments, such as manually flushing the cache and so on.
-	 */
-#ifdef CONFIG_XILINX_UNCACHED_SHADOW
-	ret = (void *)((unsigned) ret | UNCACHED_SHADOW_MASK);
-#endif
-	/* dma_handle is same as physical (shadowed) address */
-	*dma_handle = (dma_addr_t)ret;
-
-	/*
-	 * free wasted pages.  We skip the first page since we know
-	 * that it will have count = 1 and won't require freeing.
-	 * We also mark the pages in use as reserved so that
-	 * remap_page_range works.
-	 */
-	page = virt_to_page(virt);
-	free = page + (size >> PAGE_SHIFT);
-	end  = page + (1 << order);
-
-	for (; page < end; page++) {
-		init_page_count(page);
-		if (page >= free)
-			__free_page(page);
-		else
-			SetPageReserved(page);
-	}
-
-	return ret;
-no_remap:
-	__free_pages(page, order);
-no_page:
-	return NULL;
-}
-
-#else
-
-void *consistent_alloc(int gfp, size_t size, dma_addr_t *dma_handle)
-{
-	int order, err, i;
-	unsigned long page, va, flags;
+#ifdef CONFIG_MMU
 	phys_addr_t pa;
 	struct vm_struct *area;
-	void	 *ret;
+	unsigned long va;
+#endif
 
 	if (in_interrupt())
 		BUG();
@@ -133,71 +79,133 @@
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
 
-	page = __get_free_pages(gfp, order);
-	if (!page) {
-		BUG();
+	vaddr = __get_free_pages(gfp, order);
+	if (!vaddr)
 		return NULL;
-	}
 
 	/*
 	 * we need to ensure that there are no cachelines in use,
 	 * or worse dirty in this area.
 	 */
-	flush_dcache_range(virt_to_phys(page), virt_to_phys(page) + size);
+	flush_dcache_range(virt_to_phys((void *)vaddr),
+					virt_to_phys((void *)vaddr) + size);
 
+#ifndef CONFIG_MMU
+	ret = (void *)vaddr;
+	/*
+	 * Here's the magic!  Note if the uncached shadow is not implemented,
+	 * it's up to the calling code to also test that condition and make
+	 * other arranegments, such as manually flushing the cache and so on.
+	 */
+# ifdef CONFIG_XILINX_UNCACHED_SHADOW
+	ret = (void *)((unsigned) ret | UNCACHED_SHADOW_MASK);
+# endif
+	if ((unsigned int)ret > cpuinfo.dcache_base &&
+				(unsigned int)ret < cpuinfo.dcache_high)
+		printk(KERN_WARNING
+			"ERROR: Your cache coherent area is CACHED!!!\n");
+
+	/* dma_handle is same as physical (shadowed) address */
+	*dma_handle = (dma_addr_t)ret;
+#else
 	/* Allocate some common virtual space to map the new pages. */
 	area = get_vm_area(size, VM_ALLOC);
-	if (area == NULL) {
-		free_pages(page, order);
+	if (!area) {
+		free_pages(vaddr, order);
 		return NULL;
 	}
 	va = (unsigned long) area->addr;
 	ret = (void *)va;
 
 	/* This gives us the real physical address of the first page. */
-	*dma_handle = pa = virt_to_bus((void *)page);
-
-	/* MS: This is the whole magic - use cache inhibit pages */
-	flags = _PAGE_KERNEL | _PAGE_NO_CACHE;
+	*dma_handle = pa = virt_to_bus((void *)vaddr);
+#endif
 
 	/*
-	 * Set refcount=1 on all pages in an order>0
-	 * allocation so that vfree() will actually
-	 * free all pages that were allocated.
+	 * free wasted pages.  We skip the first page since we know
+	 * that it will have count = 1 and won't require freeing.
+	 * We also mark the pages in use as reserved so that
+	 * remap_page_range works.
 	 */
-	if (order > 0) {
-		struct page *rpage = virt_to_page(page);
-		for (i = 1; i < (1 << order); i++)
-			init_page_count(rpage+i);
+	page = virt_to_page(vaddr);
+	end = page + (1 << order);
+
+	split_page(page, order);
+
+	for (i = 0; i < size && err == 0; i += PAGE_SIZE) {
+#ifdef CONFIG_MMU
+		/* MS: This is the whole magic - use cache inhibit pages */
+		err = map_page(va + i, pa + i, _PAGE_KERNEL | _PAGE_NO_CACHE);
+#endif
+
+		SetPageReserved(page);
+		page++;
 	}
 
-	err = 0;
-	for (i = 0; i < size && err == 0; i += PAGE_SIZE)
-		err = map_page(va+i, pa+i, flags);
+	/* Free the otherwise unused pages. */
+	while (page < end) {
+		__free_page(page);
+		page++;
+	}
 
 	if (err) {
-		vfree((void *)va);
+		free_pages(vaddr, order);
 		return NULL;
 	}
 
 	return ret;
 }
-#endif /* CONFIG_MMU */
 EXPORT_SYMBOL(consistent_alloc);
 
 /*
  * free page(s) as defined by the above mapping.
  */
-void consistent_free(void *vaddr)
+void consistent_free(size_t size, void *vaddr)
 {
+	struct page *page;
+
 	if (in_interrupt())
 		BUG();
 
+	size = PAGE_ALIGN(size);
+
+#ifndef CONFIG_MMU
 	/* Clear SHADOW_MASK bit in address, and free as per usual */
-#ifdef CONFIG_XILINX_UNCACHED_SHADOW
+# ifdef CONFIG_XILINX_UNCACHED_SHADOW
 	vaddr = (void *)((unsigned)vaddr & ~UNCACHED_SHADOW_MASK);
+# endif
+	page = virt_to_page(vaddr);
+
+	do {
+		ClearPageReserved(page);
+		__free_page(page);
+		page++;
+	} while (size -= PAGE_SIZE);
+#else
+	do {
+		pte_t *ptep;
+		unsigned long pfn;
+
+		ptep = pte_offset_kernel(pmd_offset(pgd_offset_k(
+						(unsigned int)vaddr),
+					(unsigned int)vaddr),
+				(unsigned int)vaddr);
+		if (!pte_none(*ptep) && pte_present(*ptep)) {
+			pfn = pte_pfn(*ptep);
+			pte_clear(&init_mm, (unsigned int)vaddr, ptep);
+			if (pfn_valid(pfn)) {
+				page = pfn_to_page(pfn);
+
+				ClearPageReserved(page);
+				__free_page(page);
+			}
+		}
+		vaddr += PAGE_SIZE;
+	} while (size -= PAGE_SIZE);
+
+	/* flush tlb */
+	flush_tlb_all();
 #endif
-	vfree(vaddr);
 }
 EXPORT_SYMBOL(consistent_free);
 
@@ -221,7 +229,7 @@
 	case PCI_DMA_NONE:
 		BUG();
 	case PCI_DMA_FROMDEVICE:	/* invalidate only */
-		flush_dcache_range(start, end);
+		invalidate_dcache_range(start, end);
 		break;
 	case PCI_DMA_TODEVICE:		/* writeback only */
 		flush_dcache_range(start, end);

arch/microblaze/mm/fault.c

diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 7af87f4..bab9229 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -273,16 +273,11 @@
  * us unable to handle the page fault gracefully.
  */
 out_of_memory:
-	if (current->pid == 1) {
-		yield();
-		down_read(&mm->mmap_sem);
-		goto survive;
-	}
 	up_read(&mm->mmap_sem);
-	printk(KERN_WARNING "VM: killing process %s\n", current->comm);
-	if (user_mode(regs))
-		do_exit(SIGKILL);
-	bad_page_fault(regs, address, SIGKILL);
+	if (!user_mode(regs))
+		bad_page_fault(regs, address, SIGKILL);
+	else
+		pagefault_out_of_memory();
 	return;
 
 do_sigbus:

arch/microblaze/mm/init.c

diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index f42c2dd..cca3579 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -47,6 +47,7 @@
 EXPORT_SYMBOL(memory_start);
 unsigned long memory_end; /* due to mm/nommu.c */
 unsigned long memory_size;
+EXPORT_SYMBOL(memory_size);
 
 /*
  * paging_init() sets up the page tables - in fact we've already done this.

arch/microblaze/mm/pgtable.c

diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index d31312c..59bf233 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -42,6 +42,7 @@
 
 unsigned long ioremap_base;
 unsigned long ioremap_bot;
+EXPORT_SYMBOL(ioremap_bot);
 
 /* The maximum lowmem defaults to 768Mb, but this can be configured to
  * another value.
@@ -161,24 +162,6 @@
 	return err;
 }
 
-void __init adjust_total_lowmem(void)
-{
-/* TBD */
-#if 0
-	unsigned long max_low_mem = MAX_LOW_MEM;
-
-	if (total_lowmem > max_low_mem) {
-		total_lowmem = max_low_mem;
-#ifndef CONFIG_HIGHMEM
-		printk(KERN_INFO "Warning, memory limited to %ld Mb, use "
-				"CONFIG_HIGHMEM to reach %ld Mb\n",
-				max_low_mem >> 20, total_memory >> 20);
-		total_memory = total_lowmem;
-#endif /* CONFIG_HIGHMEM */
-	}
-#endif
-}
-
 /*
  * Map in all of physical memory starting at CONFIG_KERNEL_START.
  */
@@ -206,24 +189,6 @@
 /* is x a power of 2? */
 #define is_power_of_2(x)	((x) != 0 && (((x) & ((x) - 1)) == 0))
 
-/*
- * Set up a mapping for a block of I/O.
- * virt, phys, size must all be page-aligned.
- * This should only be called before ioremap is called.
- */
-void __init io_block_mapping(unsigned long virt, phys_addr_t phys,
-			     unsigned int size, int flags)
-{
-	int i;
-
-	if (virt > CONFIG_KERNEL_START && virt < ioremap_bot)
-		ioremap_bot = ioremap_base = virt;
-
-	/* Put it in the page tables. */
-	for (i = 0; i < size; i += PAGE_SIZE)
-		map_page(virt + i, phys + i, flags);
-}
-
 /* Scan the real Linux page tables and return a PTE pointer for
  * a virtual address in a context.
  * Returns true (1) if PTE was found, zero otherwise.  The pointer to
@@ -274,3 +239,18 @@
 
 	return pa;
 }
+
+__init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+		unsigned long address)
+{
+	pte_t *pte;
+	if (mem_init_done) {
+		pte = (pte_t *)__get_free_page(GFP_KERNEL |
+					__GFP_REPEAT | __GFP_ZERO);
+	} else {
+		pte = (pte_t *)early_get_page();
+		if (pte)
+			clear_page(pte);
+	}
+	return pte;
+}

arch/microblaze/pci/pci-common.c

diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 740bb32..9cb782b 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -1025,7 +1025,7 @@
 
 	struct pci_dev *dev = bus->self;
 
-	for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) {
+	pci_bus_for_each_resource(bus, res, i) {
 		res = bus->resource[i];
 		if (!res)
 			continue;
@@ -1131,21 +1131,20 @@
  * but we want to try to avoid allocating at 0x2900-0x2bff
  * which might have be mirrored at 0x0100-0x03ff..
  */
-void pcibios_align_resource(void *data, struct resource *res,
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 				resource_size_t size, resource_size_t align)
 {
 	struct pci_dev *dev = data;
+	resource_size_t start = res->start;
 
 	if (res->flags & IORESOURCE_IO) {
-		resource_size_t start = res->start;
-
 		if (skip_isa_ioresource_align(dev))
-			return;
-		if (start & 0x300) {
+			return start;
+		if (start & 0x300)
 			start = (start + 0x3ff) & ~0x3ff;
-			res->start = start;
-		}
 	}
+
+	return start;
 }
 EXPORT_SYMBOL(pcibios_align_resource);
 
@@ -1228,7 +1227,7 @@
 	pr_debug("PCI: Allocating bus resources for %04x:%02x...\n",
 		 pci_domain_nr(bus), bus->number);
 
-	for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) {
+	pci_bus_for_each_resource(bus, res, i) {
 		res = bus->resource[i];
 		if (!res || !res->flags
 		    || res->start > res->end || res->parent)
@@ -1508,7 +1507,7 @@
 	pci_bus_add_devices(bus);
 
 	/* Fixup EEH */
-	eeh_add_device_tree_late(bus);
+	/* eeh_add_device_tree_late(bus); */
 }
 EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
 

arch/mips/Kconfig

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 29e8692..7e6fd1c 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -49,7 +49,7 @@
 	  family: TNETD7100, 7200 and 7300.
 
 config BCM47XX
-	bool "BCM47XX based boards"
+	bool "Broadcom BCM47XX based boards"
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
@@ -509,6 +509,7 @@
 	bool "Sibyte BCM91250A-SWARM"
 	select BOOT_ELF32
 	select DMA_COHERENT
+	select HAVE_PATA_PLATFORM
 	select NR_CPUS_DEFAULT_2
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
@@ -523,6 +524,7 @@
 	depends on EXPERIMENTAL
 	select BOOT_ELF32
 	select DMA_COHERENT
+	select HAVE_PATA_PLATFORM
 	select NR_CPUS_DEFAULT_2
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
@@ -1305,6 +1307,33 @@
 
 endchoice
 
+if CPU_LOONGSON2F
+config CPU_NOP_WORKAROUNDS
+	bool
+
+config CPU_JUMP_WORKAROUNDS
+	bool
+
+config CPU_LOONGSON2F_WORKAROUNDS
+	bool "Loongson 2F Workarounds"
+	default y
+	select CPU_NOP_WORKAROUNDS
+	select CPU_JUMP_WORKAROUNDS
+	help
+	  Loongson 2F01 / 2F02 processors have the NOP & JUMP issues which
+	  require workarounds.  Without workarounds the system may hang
+	  unexpectedly.  For more information please refer to the gas
+	  -mfix-loongson2f-nop and -mfix-loongson2f-jump options.
+
+	  Loongson 2F03 and later have fixed these issues and no workarounds
+	  are needed.  The workarounds have no significant side effect on them
+	  but may decrease the performance of the system so this option should
+	  be disabled unless the kernel is intended to be run on 2F01 or 2F02
+	  systems.
+
+	  If unsure, please say Y.
+endif # CPU_LOONGSON2F
+
 config SYS_SUPPORTS_ZBOOT
 	bool
 	select HAVE_KERNEL_GZIP

arch/mips/Makefile

diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 2f2eac2..0b9c01a 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -136,6 +136,19 @@
 	$(call cc-option,-march=loongson2e,-march=r4600)
 cflags-$(CONFIG_CPU_LOONGSON2F) += \
 	$(call cc-option,-march=loongson2f,-march=r4600)
+# enable the workarounds for loongson2f
+ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS
+  ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-nop,),)
+    $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-nop)
+  else
+    cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-nop
+  endif
+  ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-jump,),)
+    $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-jump)
+  else
+    cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-jump
+  endif
+endif
 
 cflags-$(CONFIG_CPU_MIPS32_R1)	+= $(call cc-option,-march=mips32,-mips32 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
 			-Wa,-mips32 -Wa,--trap

arch/mips/alchemy/devboards/db1200/setup.c

diff --git a/arch/mips/alchemy/devboards/db1200/setup.c b/arch/mips/alchemy/devboards/db1200/setup.c
index be7e92e..8876195 100644
--- a/arch/mips/alchemy/devboards/db1200/setup.c
+++ b/arch/mips/alchemy/devboards/db1200/setup.c
@@ -66,12 +66,16 @@
 	set_irq_type(AU1200_GPIO7_INT, IRQF_TRIGGER_LOW);
 	bcsr_init_irq(DB1200_INT_BEGIN, DB1200_INT_END, AU1200_GPIO7_INT);
 
-	/* do not autoenable these: CPLD has broken edge int handling,
-	 * and the CD handler setup requires manual enabling to work
-	 * around that.
+	/* insert/eject pairs: one of both is always screaming.  To avoid
+	 * issues they must not be automatically enabled when initially
+	 * requested.
 	 */
 	irq_to_desc(DB1200_SD0_INSERT_INT)->status |= IRQ_NOAUTOEN;
 	irq_to_desc(DB1200_SD0_EJECT_INT)->status |= IRQ_NOAUTOEN;
+	irq_to_desc(DB1200_PC0_INSERT_INT)->status |= IRQ_NOAUTOEN;
+	irq_to_desc(DB1200_PC0_EJECT_INT)->status |= IRQ_NOAUTOEN;
+	irq_to_desc(DB1200_PC1_INSERT_INT)->status |= IRQ_NOAUTOEN;
+	irq_to_desc(DB1200_PC1_EJECT_INT)->status |= IRQ_NOAUTOEN;
 
 	return 0;
 }

arch/mips/configs/bcm63xx_defconfig

diff --git a/arch/mips/configs/bcm63xx_defconfig b/arch/mips/configs/bcm63xx_defconfig
index 7fee027..6389ca0 100644
--- a/arch/mips/configs/bcm63xx_defconfig
+++ b/arch/mips/configs/bcm63xx_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.30-rc6
-# Sun May 31 20:17:18 2009
+# Linux kernel version: 2.6.34-rc2
+# Tue Mar 23 10:36:32 2010
 #
 CONFIG_MIPS=y
 
@@ -9,13 +9,14 @@
 # Machine selection
 #
 # CONFIG_MACH_ALCHEMY is not set
+# CONFIG_AR7 is not set
 # CONFIG_BCM47XX is not set
 CONFIG_BCM63XX=y
 # CONFIG_MIPS_COBALT is not set
 # CONFIG_MACH_DECSTATION is not set
 # CONFIG_MACH_JAZZ is not set
 # CONFIG_LASAT is not set
-# CONFIG_LEMOTE_FULONG is not set
+# CONFIG_MACH_LOONGSON is not set
 # CONFIG_MIPS_MALTA is not set
 # CONFIG_MIPS_SIM is not set
 # CONFIG_NEC_MARKEINS is not set
@@ -26,6 +27,7 @@
 # CONFIG_PNX8550_STB810 is not set
 # CONFIG_PMC_MSP is not set
 # CONFIG_PMC_YOSEMITE is not set
+# CONFIG_POWERTV is not set
 # CONFIG_SGI_IP22 is not set
 # CONFIG_SGI_IP27 is not set
 # CONFIG_SGI_IP28 is not set
@@ -45,13 +47,17 @@
 # CONFIG_WR_PPMC is not set
 # CONFIG_CAVIUM_OCTEON_SIMULATOR is not set
 # CONFIG_CAVIUM_OCTEON_REFERENCE_BOARD is not set
+# CONFIG_ALCHEMY_GPIO_INDIRECT is not set
 
 #
 # CPU support
 #
+CONFIG_BCM63XX_CPU_6338=y
+CONFIG_BCM63XX_CPU_6345=y
 CONFIG_BCM63XX_CPU_6348=y
 CONFIG_BCM63XX_CPU_6358=y
 CONFIG_BOARD_BCM963XX=y
+CONFIG_LOONGSON_UART_BASE=y
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
@@ -69,10 +75,8 @@
 CONFIG_CSRC_R4K_LIB=y
 CONFIG_CSRC_R4K=y
 CONFIG_DMA_NONCOHERENT=y
-CONFIG_DMA_NEED_PCI_MAP_STATE=y
-CONFIG_EARLY_PRINTK=y
+CONFIG_NEED_DMA_MAP_STATE=y
 CONFIG_SYS_HAS_EARLY_PRINTK=y
-# CONFIG_HOTPLUG_CPU is not set
 # CONFIG_NO_IOPORT is not set
 CONFIG_GENERIC_GPIO=y
 CONFIG_CPU_BIG_ENDIAN=y
@@ -85,7 +89,8 @@
 #
 # CPU selection
 #
-# CONFIG_CPU_LOONGSON2 is not set
+# CONFIG_CPU_LOONGSON2E is not set
+# CONFIG_CPU_LOONGSON2F is not set
 CONFIG_CPU_MIPS32_R1=y
 # CONFIG_CPU_MIPS32_R2 is not set
 # CONFIG_CPU_MIPS64_R1 is not set
@@ -128,7 +133,7 @@
 CONFIG_MIPS_MT_DISABLED=y
 # CONFIG_MIPS_MT_SMP is not set
 # CONFIG_MIPS_MT_SMTC is not set
-CONFIG_CPU_HAS_LLSC=y
+# CONFIG_ARCH_PHYS_ADDR_T_64BIT is not set
 CONFIG_CPU_HAS_SYNC=y
 CONFIG_GENERIC_HARDIRQS=y
 CONFIG_GENERIC_IRQ_PROBE=y
@@ -146,9 +151,8 @@
 # CONFIG_PHYS_ADDR_T_64BIT is not set
 CONFIG_ZONE_DMA_FLAG=0
 CONFIG_VIRT_TO_BUS=y
-CONFIG_UNEVICTABLE_LRU=y
-CONFIG_HAVE_MLOCK=y
-CONFIG_HAVE_MLOCKED_PAGE_BIT=y
+# CONFIG_KSM is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
 CONFIG_TICK_ONESHOT=y
 CONFIG_NO_HZ=y
 # CONFIG_HIGH_RES_TIMERS is not set
@@ -170,6 +174,7 @@
 CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_STACKTRACE_SUPPORT=y
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+CONFIG_CONSTRUCTORS=y
 
 #
 # General setup
@@ -189,15 +194,12 @@
 #
 # RCU Subsystem
 #
-CONFIG_CLASSIC_RCU=y
 # CONFIG_TREE_RCU is not set
-# CONFIG_PREEMPT_RCU is not set
+# CONFIG_TREE_PREEMPT_RCU is not set
+CONFIG_TINY_RCU=y
 # CONFIG_TREE_RCU_TRACE is not set
-# CONFIG_PREEMPT_RCU_TRACE is not set
 # CONFIG_IKCONFIG is not set
 CONFIG_LOG_BUF_SHIFT=17
-# CONFIG_GROUP_SCHED is not set
-# CONFIG_CGROUPS is not set
 CONFIG_SYSFS_DEPRECATED=y
 CONFIG_SYSFS_DEPRECATED_V2=y
 # CONFIG_RELAY is not set
@@ -205,11 +207,11 @@
 # CONFIG_BLK_DEV_INITRD is not set
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
 CONFIG_EMBEDDED=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
-# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -223,6 +225,10 @@
 # CONFIG_EVENTFD is not set
 # CONFIG_SHMEM is not set
 # CONFIG_AIO is not set
+
+#
+# Kernel Performance Events And Counters
+#
 # CONFIG_VM_EVENT_COUNTERS is not set
 CONFIG_PCI_QUIRKS=y
 # CONFIG_SLUB_DEBUG is not set
@@ -231,14 +237,17 @@
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
-# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
+
+#
+# GCOV-based kernel profiling
+#
 # CONFIG_SLOW_WORK is not set
-# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_BASE_SMALL=0
 # CONFIG_MODULES is not set
 CONFIG_BLOCK=y
-# CONFIG_LBD is not set
+CONFIG_LBDAF=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -246,14 +255,41 @@
 # IO Schedulers
 #
 CONFIG_IOSCHED_NOOP=y
-# CONFIG_IOSCHED_AS is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-# CONFIG_DEFAULT_AS is not set
 # CONFIG_DEFAULT_DEADLINE is not set
 # CONFIG_DEFAULT_CFQ is not set
 CONFIG_DEFAULT_NOOP=y
 CONFIG_DEFAULT_IOSCHED="noop"
+# CONFIG_INLINE_SPIN_TRYLOCK is not set
+# CONFIG_INLINE_SPIN_TRYLOCK_BH is not set
+# CONFIG_INLINE_SPIN_LOCK is not set
+# CONFIG_INLINE_SPIN_LOCK_BH is not set
+# CONFIG_INLINE_SPIN_LOCK_IRQ is not set
+# CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set
+CONFIG_INLINE_SPIN_UNLOCK=y
+# CONFIG_INLINE_SPIN_UNLOCK_BH is not set
+CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
+# CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set
+# CONFIG_INLINE_READ_TRYLOCK is not set
+# CONFIG_INLINE_READ_LOCK is not set
+# CONFIG_INLINE_READ_LOCK_BH is not set
+# CONFIG_INLINE_READ_LOCK_IRQ is not set
+# CONFIG_INLINE_READ_LOCK_IRQSAVE is not set
+CONFIG_INLINE_READ_UNLOCK=y
+# CONFIG_INLINE_READ_UNLOCK_BH is not set
+CONFIG_INLINE_READ_UNLOCK_IRQ=y
+# CONFIG_INLINE_READ_UNLOCK_IRQRESTORE is not set
+# CONFIG_INLINE_WRITE_TRYLOCK is not set
+# CONFIG_INLINE_WRITE_LOCK is not set
+# CONFIG_INLINE_WRITE_LOCK_BH is not set
+# CONFIG_INLINE_WRITE_LOCK_IRQ is not set
+# CONFIG_INLINE_WRITE_LOCK_IRQSAVE is not set
+CONFIG_INLINE_WRITE_UNLOCK=y
+# CONFIG_INLINE_WRITE_UNLOCK_BH is not set
+CONFIG_INLINE_WRITE_UNLOCK_IRQ=y
+# CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE is not set
+# CONFIG_MUTEX_SPIN_ON_OWNER is not set
 # CONFIG_FREEZER is not set
 
 #
@@ -263,15 +299,12 @@
 CONFIG_PCI=y
 CONFIG_PCI_DOMAINS=y
 # CONFIG_ARCH_SUPPORTS_MSI is not set
-# CONFIG_PCI_LEGACY is not set
 # CONFIG_PCI_STUB is not set
 # CONFIG_PCI_IOV is not set
 CONFIG_MMU=y
 CONFIG_PCCARD=y
-# CONFIG_PCMCIA_DEBUG is not set
 CONFIG_PCMCIA=y
 CONFIG_PCMCIA_LOAD_CIS=y
-CONFIG_PCMCIA_IOCTL=y
 CONFIG_CARDBUS=y
 
 #
@@ -295,6 +328,7 @@
 #
 # Power management options
 #
+CONFIG_ARCH_HIBERNATION_POSSIBLE=y
 CONFIG_ARCH_SUSPEND_POSSIBLE=y
 # CONFIG_PM is not set
 CONFIG_NET=y
@@ -333,6 +367,7 @@
 # CONFIG_NETFILTER is not set
 # CONFIG_IP_DCCP is not set
 # CONFIG_IP_SCTP is not set
+# CONFIG_RDS is not set
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
@@ -347,6 +382,7 @@
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
 # CONFIG_PHONET is not set
+# CONFIG_IEEE802154 is not set
 # CONFIG_NET_SCHED is not set
 # CONFIG_DCB is not set
 
@@ -359,7 +395,27 @@
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
-# CONFIG_WIRELESS is not set
+CONFIG_WIRELESS=y
+CONFIG_WEXT_CORE=y
+CONFIG_WEXT_PROC=y
+CONFIG_CFG80211=y
+CONFIG_NL80211_TESTMODE=y
+# CONFIG_CFG80211_DEVELOPER_WARNINGS is not set
+# CONFIG_CFG80211_REG_DEBUG is not set
+CONFIG_CFG80211_DEFAULT_PS=y
+# CONFIG_CFG80211_INTERNAL_REGDB is not set
+CONFIG_CFG80211_WEXT=y
+CONFIG_WIRELESS_EXT_SYSFS=y
+# CONFIG_LIB80211 is not set
+CONFIG_MAC80211=y
+# CONFIG_MAC80211_RC_PID is not set
+CONFIG_MAC80211_RC_MINSTREL=y
+# CONFIG_MAC80211_RC_DEFAULT_PID is not set
+CONFIG_MAC80211_RC_DEFAULT_MINSTREL=y
+CONFIG_MAC80211_RC_DEFAULT="minstrel"
+# CONFIG_MAC80211_MESH is not set
+CONFIG_MAC80211_LEDS=y
+# CONFIG_MAC80211_DEBUG_MENU is not set
 # CONFIG_WIMAX is not set
 # CONFIG_RFKILL is not set
 # CONFIG_NET_9P is not set
@@ -471,6 +527,7 @@
 #
 # SCSI device support
 #
+CONFIG_SCSI_MOD=y
 # CONFIG_RAID_ATTRS is not set
 # CONFIG_SCSI is not set
 # CONFIG_SCSI_DMA is not set
@@ -484,13 +541,16 @@
 #
 
 #
-# Enable only one of the two stacks, unless you know what you are doing
+# You can enable one or both FireWire driver stacks.
+#
+
+#
+# The newer stack is recommended.
 #
 # CONFIG_FIREWIRE is not set
 # CONFIG_IEEE1394 is not set
 # CONFIG_I2O is not set
 CONFIG_NETDEVICES=y
-CONFIG_COMPAT_NET_DEV_OPS=y
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
 # CONFIG_MACVLAN is not set
@@ -529,6 +589,7 @@
 # CONFIG_SMC91X is not set
 # CONFIG_DM9000 is not set
 # CONFIG_ETHOC is not set
+# CONFIG_SMSC911X is not set
 # CONFIG_DNET is not set
 # CONFIG_NET_TULIP is not set
 # CONFIG_HP100 is not set
@@ -541,17 +602,48 @@
 # CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
 # CONFIG_NET_PCI is not set
 # CONFIG_B44 is not set
+# CONFIG_KS8842 is not set
+# CONFIG_KS8851_MLL is not set
 # CONFIG_ATL2 is not set
 CONFIG_BCM63XX_ENET=y
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
 # CONFIG_TR is not set
-
-#
-# Wireless LAN
-#
-# CONFIG_WLAN_PRE80211 is not set
-# CONFIG_WLAN_80211 is not set
+CONFIG_WLAN=y
+# CONFIG_PCMCIA_RAYCS is not set
+# CONFIG_LIBERTAS_THINFIRM is not set
+# CONFIG_ATMEL is not set
+# CONFIG_AT76C50X_USB is not set
+# CONFIG_AIRO_CS is not set
+# CONFIG_PCMCIA_WL3501 is not set
+# CONFIG_PRISM54 is not set
+# CONFIG_USB_ZD1201 is not set
+# CONFIG_USB_NET_RNDIS_WLAN is not set
+# CONFIG_RTL8180 is not set
+# CONFIG_RTL8187 is not set
+# CONFIG_ADM8211 is not set
+# CONFIG_MAC80211_HWSIM is not set
+# CONFIG_MWL8K is not set
+# CONFIG_ATH_COMMON is not set
+CONFIG_B43=y
+CONFIG_B43_PCI_AUTOSELECT=y
+CONFIG_B43_PCICORE_AUTOSELECT=y
+# CONFIG_B43_PCMCIA is not set
+CONFIG_B43_PIO=y
+# CONFIG_B43_PHY_LP is not set
+CONFIG_B43_LEDS=y
+# CONFIG_B43_DEBUG is not set
+# CONFIG_B43LEGACY is not set
+# CONFIG_HOSTAP is not set
+# CONFIG_IPW2100 is not set
+# CONFIG_IPW2200 is not set
+# CONFIG_IWLWIFI is not set
+# CONFIG_LIBERTAS is not set
+# CONFIG_HERMES is not set
+# CONFIG_P54_COMMON is not set
+# CONFIG_RT2X00 is not set
+# CONFIG_WL12XX is not set
+# CONFIG_ZD1211RW is not set
 
 #
 # Enable WiMAX (Networking options) to see the WiMAX drivers
@@ -574,6 +666,7 @@
 # CONFIG_NETCONSOLE is not set
 # CONFIG_NETPOLL is not set
 # CONFIG_NET_POLL_CONTROLLER is not set
+# CONFIG_VMXNET3 is not set
 # CONFIG_ISDN is not set
 # CONFIG_PHONE is not set
 
@@ -607,6 +700,7 @@
 CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y
 # CONFIG_SERIAL_JSM is not set
+# CONFIG_SERIAL_TIMBERDALE is not set
 CONFIG_SERIAL_BCM63XX=y
 CONFIG_SERIAL_BCM63XX_CONSOLE=y
 # CONFIG_UNIX98_PTYS is not set
@@ -629,6 +723,11 @@
 CONFIG_DEVPORT=y
 # CONFIG_I2C is not set
 # CONFIG_SPI is not set
+
+#
+# PPS support
+#
+# CONFIG_PPS is not set
 CONFIG_ARCH_REQUIRE_GPIOLIB=y
 CONFIG_GPIOLIB=y
 # CONFIG_GPIO_SYSFS is not set
@@ -636,6 +735,8 @@
 #
 # Memory mapped GPIO expanders:
 #
+# CONFIG_GPIO_IT8761E is not set
+# CONFIG_GPIO_SCH is not set
 
 #
 # I2C GPIO expanders:
@@ -644,16 +745,21 @@
 #
 # PCI GPIO expanders:
 #
+# CONFIG_GPIO_CS5535 is not set
 # CONFIG_GPIO_BT8XX is not set
+# CONFIG_GPIO_LANGWELL is not set
 
 #
 # SPI GPIO expanders:
 #
+
+#
+# AC97 GPIO expanders:
+#
 # CONFIG_W1 is not set
 # CONFIG_POWER_SUPPLY is not set
 # CONFIG_HWMON is not set
 # CONFIG_THERMAL is not set
-# CONFIG_THERMAL_HWMON is not set
 # CONFIG_WATCHDOG is not set
 CONFIG_SSB_POSSIBLE=y
 
@@ -662,15 +768,16 @@
 #
 CONFIG_SSB=y
 CONFIG_SSB_SPROM=y
+CONFIG_SSB_BLOCKIO=y
 CONFIG_SSB_PCIHOST_POSSIBLE=y
 CONFIG_SSB_PCIHOST=y
-# CONFIG_SSB_B43_PCI_BRIDGE is not set
+CONFIG_SSB_B43_PCI_BRIDGE=y
 CONFIG_SSB_PCMCIAHOST_POSSIBLE=y
 # CONFIG_SSB_PCMCIAHOST is not set
 # CONFIG_SSB_SILENT is not set
 # CONFIG_SSB_DEBUG is not set
 CONFIG_SSB_DRIVER_PCICORE_POSSIBLE=y
-# CONFIG_SSB_DRIVER_PCICORE is not set
+CONFIG_SSB_DRIVER_PCICORE=y
 # CONFIG_SSB_DRIVER_MIPS is not set
 
 #
@@ -680,27 +787,15 @@
 # CONFIG_MFD_SM501 is not set
 # CONFIG_HTC_PASIC3 is not set
 # CONFIG_MFD_TMIO is not set
+# CONFIG_MFD_TIMBERDALE is not set
+# CONFIG_LPC_SCH is not set
 # CONFIG_REGULATOR is not set
-
-#
-# Multimedia devices
-#
-
-#
-# Multimedia core support
-#
-# CONFIG_VIDEO_DEV is not set
-# CONFIG_DVB_CORE is not set
-# CONFIG_VIDEO_MEDIA is not set
-
-#
-# Multimedia drivers
-#
-# CONFIG_DAB is not set
+# CONFIG_MEDIA_SUPPORT is not set
 
 #
 # Graphics support
 #
+# CONFIG_VGA_ARB is not set
 # CONFIG_DRM is not set
 # CONFIG_VGASTATE is not set
 # CONFIG_VIDEO_OUTPUT_CONTROL is not set
@@ -710,11 +805,7 @@
 #
 # Display device support
 #
-CONFIG_DISPLAY_SUPPORT=y
-
-#
-# Display hardware drivers
-#
+# CONFIG_DISPLAY_SUPPORT is not set
 # CONFIG_SOUND is not set
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
@@ -741,13 +832,14 @@
 # USB Host Controller Drivers
 #
 # CONFIG_USB_C67X00_HCD is not set
+# CONFIG_USB_XHCI_HCD is not set
 CONFIG_USB_EHCI_HCD=y
 # CONFIG_USB_EHCI_ROOT_HUB_TT is not set
 # CONFIG_USB_EHCI_TT_NEWSCHED is not set
-CONFIG_USB_EHCI_BIG_ENDIAN_MMIO=y
 # CONFIG_USB_OXU210HP_HCD is not set
 # CONFIG_USB_ISP116X_HCD is not set
 # CONFIG_USB_ISP1760_HCD is not set
+# CONFIG_USB_ISP1362_HCD is not set
 CONFIG_USB_OHCI_HCD=y
 # CONFIG_USB_OHCI_HCD_SSB is not set
 CONFIG_USB_OHCI_BIG_ENDIAN_DESC=y
@@ -796,7 +888,6 @@
 # CONFIG_USB_RIO500 is not set
 # CONFIG_USB_LEGOTOWER is not set
 # CONFIG_USB_LCD is not set
-# CONFIG_USB_BERRY_CHARGE is not set
 # CONFIG_USB_LED is not set
 # CONFIG_USB_CYPRESS_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
@@ -807,8 +898,8 @@
 # CONFIG_USB_LD is not set
 # CONFIG_USB_TRANCEVIBRATOR is not set
 # CONFIG_USB_IOWARRIOR is not set
+# CONFIG_USB_TEST is not set
 # CONFIG_USB_ISIGHTFW is not set
-# CONFIG_USB_VST is not set
 # CONFIG_USB_GADGET is not set
 
 #
@@ -819,7 +910,29 @@
 # CONFIG_UWB is not set
 # CONFIG_MMC is not set
 # CONFIG_MEMSTICK is not set
-# CONFIG_NEW_LEDS is not set
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+
+#
+# LED drivers
+#
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_GPIO_PLATFORM=y
+# CONFIG_LEDS_LT3593 is not set
+CONFIG_LEDS_TRIGGERS=y
+
+#
+# LED Triggers
+#
+CONFIG_LEDS_TRIGGER_TIMER=y
+# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
+# CONFIG_LEDS_TRIGGER_BACKLIGHT is not set
+CONFIG_LEDS_TRIGGER_GPIO=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
+
+#
+# iptables trigger is under Netfilter config (LED target)
+#
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
 CONFIG_RTC_LIB=y
@@ -827,6 +940,10 @@
 # CONFIG_DMADEVICES is not set
 # CONFIG_AUXDISPLAY is not set
 # CONFIG_UIO is not set
+
+#
+# TI VLYNQ
+#
 # CONFIG_STAGING is not set
 
 #
@@ -838,12 +955,16 @@
 # CONFIG_REISERFS_FS is not set
 # CONFIG_JFS_FS is not set
 # CONFIG_FS_POSIX_ACL is not set
-# CONFIG_FILE_LOCKING is not set
 # CONFIG_XFS_FS is not set
+# CONFIG_GFS2_FS is not set
 # CONFIG_OCFS2_FS is not set
 # CONFIG_BTRFS_FS is not set
+# CONFIG_NILFS2_FS is not set
+# CONFIG_FILE_LOCKING is not set
+CONFIG_FSNOTIFY=y
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY is not set
+CONFIG_INOTIFY_USER=y
 # CONFIG_QUOTA is not set
 # CONFIG_AUTOFS_FS is not set
 # CONFIG_AUTOFS4_FS is not set
@@ -875,8 +996,6 @@
 CONFIG_PROC_SYSCTL=y
 CONFIG_PROC_PAGE_MONITOR=y
 CONFIG_SYSFS=y
-CONFIG_TMPFS=y
-# CONFIG_TMPFS_POSIX_ACL is not set
 # CONFIG_HUGETLB_PAGE is not set
 # CONFIG_CONFIGFS_FS is not set
 CONFIG_MISC_FILESYSTEMS=y
@@ -888,6 +1007,7 @@
 # CONFIG_BFS_FS is not set
 # CONFIG_EFS_FS is not set
 # CONFIG_JFFS2_FS is not set
+# CONFIG_LOGFS is not set
 # CONFIG_CRAMFS is not set
 # CONFIG_SQUASHFS is not set
 # CONFIG_VXFS_FS is not set
@@ -898,7 +1018,6 @@
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
-# CONFIG_NILFS2_FS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 
 #
@@ -906,7 +1025,46 @@
 #
 # CONFIG_PARTITION_ADVANCED is not set
 CONFIG_MSDOS_PARTITION=y
-# CONFIG_NLS is not set
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="iso8859-1"
+# CONFIG_NLS_CODEPAGE_437 is not set
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+# CONFIG_NLS_CODEPAGE_850 is not set
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+# CONFIG_NLS_CODEPAGE_932 is not set
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
+# CONFIG_NLS_ASCII is not set
+# CONFIG_NLS_ISO8859_1 is not set
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_UTF8 is not set
 # CONFIG_DLM is not set
 
 #
@@ -918,29 +1076,23 @@
 CONFIG_ENABLE_MUST_CHECK=y
 CONFIG_FRAME_WARN=1024
 CONFIG_MAGIC_SYSRQ=y
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_UNUSED_SYMBOLS is not set
 # CONFIG_DEBUG_FS is not set
 # CONFIG_HEADERS_CHECK is not set
 # CONFIG_DEBUG_KERNEL is not set
 # CONFIG_DEBUG_MEMORY_INIT is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_HAVE_FUNCTION_TRACER=y
+CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
+CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_TRACING_SUPPORT=y
-
-#
-# Tracers
-#
-# CONFIG_IRQSOFF_TRACER is not set
-# CONFIG_SCHED_TRACER is not set
-# CONFIG_CONTEXT_SWITCH_TRACER is not set
-# CONFIG_EVENT_TRACER is not set
-# CONFIG_BOOT_TRACER is not set
-# CONFIG_TRACE_BRANCH_PROFILING is not set
-# CONFIG_KMEMTRACE is not set
-# CONFIG_WORKQUEUE_TRACER is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_FTRACE is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
+CONFIG_EARLY_PRINTK=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="console=ttyS0,115200"
 # CONFIG_CMDLINE_OVERRIDE is not set
@@ -951,8 +1103,108 @@
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
 # CONFIG_SECURITYFS is not set
-# CONFIG_SECURITY_FILE_CAPABILITIES is not set
-# CONFIG_CRYPTO is not set
+# CONFIG_DEFAULT_SECURITY_SELINUX is not set
+# CONFIG_DEFAULT_SECURITY_SMACK is not set
+# CONFIG_DEFAULT_SECURITY_TOMOYO is not set
+CONFIG_DEFAULT_SECURITY_DAC=y
+CONFIG_DEFAULT_SECURITY=""
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+# CONFIG_CRYPTO_FIPS is not set
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_ALGAPI2=y
+CONFIG_CRYPTO_AEAD2=y
+CONFIG_CRYPTO_BLKCIPHER=y
+CONFIG_CRYPTO_BLKCIPHER2=y
+CONFIG_CRYPTO_HASH2=y
+CONFIG_CRYPTO_RNG=y
+CONFIG_CRYPTO_RNG2=y
+CONFIG_CRYPTO_PCOMP=y
+CONFIG_CRYPTO_MANAGER=y
+CONFIG_CRYPTO_MANAGER2=y
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+CONFIG_CRYPTO_WORKQUEUE=y
+# CONFIG_CRYPTO_CRYPTD is not set
+# CONFIG_CRYPTO_AUTHENC is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+# CONFIG_CRYPTO_CBC is not set
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+CONFIG_CRYPTO_ECB=y
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+# CONFIG_CRYPTO_HMAC is not set
+# CONFIG_CRYPTO_XCBC is not set
+# CONFIG_CRYPTO_VMAC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_GHASH is not set
+# CONFIG_CRYPTO_MD4 is not set
+# CONFIG_CRYPTO_MD5 is not set
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
+# CONFIG_CRYPTO_SHA1 is not set
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+CONFIG_CRYPTO_AES=y
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_ARC4=y
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+# CONFIG_CRYPTO_DES is not set
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+
+#
+# Compression
+#
+# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_ZLIB is not set
+# CONFIG_CRYPTO_LZO is not set
+
+#
+# Random Number Generation
+#
+CONFIG_CRYPTO_ANSI_CPRNG=y
+# CONFIG_CRYPTO_HW is not set
 # CONFIG_BINARY_PRINTF is not set
 
 #

arch/mips/include/asm/atomic.h

diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 519197e..59dc0c7 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -29,7 +29,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)		((v)->counter)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
 
 /*
  * atomic_set - set atomic variable
@@ -410,7 +410,7 @@
  * @v: pointer of type atomic64_t
  *
  */
-#define atomic64_read(v)	((v)->counter)
+#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
 
 /*
  * atomic64_set - set atomic variable

arch/mips/include/asm/cmpxchg.h

diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index ed9aaaaf..2d28017 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -16,7 +16,7 @@
 ({									\
 	__typeof(*(m)) __ret;						\
 									\
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {				\
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {			\
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\

arch/mips/include/asm/i8253.h

diff --git a/arch/mips/include/asm/i8253.h b/arch/mips/include/asm/i8253.h
index 032ca73..48bb823 100644
--- a/arch/mips/include/asm/i8253.h
+++ b/arch/mips/include/asm/i8253.h
@@ -12,7 +12,7 @@
 #define PIT_CH0			0x40
 #define PIT_CH2			0x42
 
-extern spinlock_t i8253_lock;
+extern raw_spinlock_t i8253_lock;
 
 extern void setup_pit_timer(void);
 

arch/mips/include/asm/mach-loongson/loongson.h

diff --git a/arch/mips/include/asm/mach-loongson/loongson.h b/arch/mips/include/asm/mach-loongson/loongson.h
index 1cf7b14..fcdbe3a 100644
--- a/arch/mips/include/asm/mach-loongson/loongson.h
+++ b/arch/mips/include/asm/mach-loongson/loongson.h
@@ -307,7 +307,7 @@
  */
 #define LOONGSON_ADDRWIN_CFG(s, d, w, src, dst, size) do {\
 	s##_WIN##w##_BASE = (src); \
-	s##_WIN##w##_MMAP = (src) | ADDRWIN_MAP_DST_##d; \
+	s##_WIN##w##_MMAP = (dst) | ADDRWIN_MAP_DST_##d; \
 	s##_WIN##w##_MASK = ~(size-1); \
 } while (0)
 

arch/mips/include/asm/mipsregs.h

diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 49382d5..c6e3c93 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -135,6 +135,12 @@
 #define FPU_CSR_COND7   0x80000000      /* $fcc7 */
 
 /*
+ * Bits 18 - 20 of the FPU Status Register will be read as 0,
+ * and should be written as zero.
+ */
+#define FPU_CSR_RSVD	0x001c0000
+
+/*
  * X the exception cause indicator
  * E the exception enable
  * S the sticky/flag bit
@@ -161,7 +167,8 @@
 #define FPU_CSR_UDF_S   0x00000008
 #define FPU_CSR_INE_S   0x00000004
 
-/* rounding mode */
+/* Bits 0 and 1 of FPU Status Register specify the rounding mode */
+#define FPU_CSR_RM	0x00000003
 #define FPU_CSR_RN      0x0     /* nearest */
 #define FPU_CSR_RZ      0x1     /* towards zero */
 #define FPU_CSR_RU      0x2     /* towards +Infinity */

arch/mips/include/asm/pgtable-64.h

diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 26dc69d..1be4b0f 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -120,9 +120,14 @@
 #endif
 #define FIRST_USER_ADDRESS	0UL
 
-#define VMALLOC_START		MAP_BASE
+/*
+ * TLB refill handlers also map the vmalloc area into xuseg.  Avoid
+ * the first couple of pages so NULL pointer dereferences will still
+ * reliably trap.
+ */
+#define VMALLOC_START		(MAP_BASE + (2 * PAGE_SIZE))
 #define VMALLOC_END	\
-	(VMALLOC_START + \
+	(MAP_BASE + \
 	 min(PTRS_PER_PGD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, \
 	     (1UL << cpu_vmbits)) - (1UL << 32))
 

arch/mips/include/asm/ptrace.h

diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index ce47118..cdc6a46 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -142,9 +142,9 @@
 
 extern asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit);
 
-extern NORET_TYPE void die(const char *, const struct pt_regs *) ATTRIB_NORET;
+extern NORET_TYPE void die(const char *, struct pt_regs *) ATTRIB_NORET;
 
-static inline void die_if_kernel(const char *str, const struct pt_regs *regs)
+static inline void die_if_kernel(const char *str, struct pt_regs *regs)
 {
 	if (unlikely(!user_mode(regs)))
 		die(str, regs);

arch/mips/include/asm/stackframe.h

diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index c841912..58730c5 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -121,7 +121,7 @@
 		.endm
 #else
 		.macro	get_saved_sp	/* Uniprocessor variation */
-#ifdef CONFIG_CPU_LOONGSON2F
+#ifdef CONFIG_CPU_JUMP_WORKAROUNDS
 		/*
 		 * Clear BTB (branch target buffer), forbid RAS (return address
 		 * stack) to workaround the Out-of-order Issue in Loongson2F

arch/mips/include/asm/uasm.h

diff --git a/arch/mips/include/asm/uasm.h b/arch/mips/include/asm/uasm.h
index 11a8b52..697e40c 100644
--- a/arch/mips/include/asm/uasm.h
+++ b/arch/mips/include/asm/uasm.h
@@ -167,6 +167,24 @@
 #define uasm_i_ssnop(buf) uasm_i_sll(buf, 0, 0, 1)
 #define uasm_i_ehb(buf) uasm_i_sll(buf, 0, 0, 3)
 
+static inline void uasm_i_dsrl_safe(u32 **p, unsigned int a1,
+				    unsigned int a2, unsigned int a3)
+{
+	if (a3 < 32)
+		uasm_i_dsrl(p, a1, a2, a3);
+	else
+		uasm_i_dsrl32(p, a1, a2, a3 - 32);
+}
+
+static inline void uasm_i_dsll_safe(u32 **p, unsigned int a1,
+				    unsigned int a2, unsigned int a3)
+{
+	if (a3 < 32)
+		uasm_i_dsll(p, a1, a2, a3);
+	else
+		uasm_i_dsll32(p, a1, a2, a3 - 32);
+}
+
 /* Handle relocations. */
 struct uasm_reloc {
 	u32 *addr;

arch/mips/jazz/setup.c

diff --git a/arch/mips/jazz/setup.c b/arch/mips/jazz/setup.c
index 7043f6b..0d0f054 100644
--- a/arch/mips/jazz/setup.c
+++ b/arch/mips/jazz/setup.c
@@ -76,15 +76,9 @@
 
 #ifdef CONFIG_VT
 	screen_info = (struct screen_info) {
-		0, 0,		/* orig-x, orig-y */
-		0,		/* unused */
-		0,		/* orig_video_page */
-		0,		/* orig_video_mode */
-		160,		/* orig_video_cols */
-		0, 0, 0,	/* unused, ega_bx, unused */
-		64,		/* orig_video_lines */
-		0,		/* orig_video_isVGA */
-		16		/* orig_video_points */
+		.orig_video_cols	= 160,
+		.orig_video_lines	= 64,
+		.orig_video_points	= 16,
 	};
 #endif
 

arch/mips/kernel/i8253.c

diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c
index ed5c441..9479406 100644
--- a/arch/mips/kernel/i8253.c
+++ b/arch/mips/kernel/i8253.c
@@ -15,7 +15,7 @@
 #include <asm/io.h>
 #include <asm/time.h>
 
-DEFINE_SPINLOCK(i8253_lock);
+DEFINE_RAW_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
 /*
@@ -26,7 +26,7 @@
 static void init_pit_timer(enum clock_event_mode mode,
 			   struct clock_event_device *evt)
 {
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 
 	switch(mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
@@ -55,7 +55,7 @@
 		/* Nothing to do here */
 		break;
 	}
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 }
 
 /*
@@ -65,10 +65,10 @@
  */
 static int pit_next_event(unsigned long delta, struct clock_event_device *evt)
 {
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 	outb_p(delta & 0xff , PIT_CH0);	/* LSB */
 	outb(delta >> 8 , PIT_CH0);	/* MSB */
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 
 	return 0;
 }
@@ -137,7 +137,7 @@
 	static int old_count;
 	static u32 old_jifs;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 	/*
 	 * Although our caller may have the read side of xtime_lock,
 	 * this is now a seqlock, and we are cheating in this routine
@@ -183,7 +183,7 @@
 	old_count = count;
 	old_jifs = jifs;
 
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 
 	count = (LATCH - 1) - count;
 

arch/mips/kernel/scall64-n32.S

diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 44337ba..a5297e2 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -385,7 +385,7 @@
 	PTR	sys_fchmodat
 	PTR	sys_faccessat
 	PTR	compat_sys_pselect6
-	PTR	sys_ppoll			/* 6265 */
+	PTR	compat_sys_ppoll		/* 6265 */
 	PTR	sys_unshare
 	PTR	sys_splice
 	PTR	sys_sync_file_range

arch/mips/kernel/traps.c

diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 1a4dd65..d612c6d 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -352,9 +352,10 @@
 
 static DEFINE_SPINLOCK(die_lock);
 
-void __noreturn die(const char * str, const struct pt_regs * regs)
+void __noreturn die(const char * str, struct pt_regs * regs)
 {
 	static int die_counter;
+	int sig = SIGSEGV;
 #ifdef CONFIG_MIPS_MT_SMTC
 	unsigned long dvpret = dvpe();
 #endif /* CONFIG_MIPS_MT_SMTC */
@@ -365,6 +366,10 @@
 #ifdef CONFIG_MIPS_MT_SMTC
 	mips_mt_regdump(dvpret);
 #endif /* CONFIG_MIPS_MT_SMTC */
+
+	if (notify_die(DIE_OOPS, str, regs, 0, current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
+		sig = 0;
+
 	printk("%s[#%d]:\n", str, ++die_counter);
 	show_registers(regs);
 	add_taint(TAINT_DIE);
@@ -379,7 +384,7 @@
 		panic("Fatal exception");
 	}
 
-	do_exit(SIGSEGV);
+	do_exit(sig);
 }
 
 extern struct exception_table_entry __start___dbe_table[];
@@ -1557,12 +1562,7 @@
 void __cpuinit set_uncached_handler(unsigned long offset, void *addr,
 	unsigned long size)
 {
-#ifdef CONFIG_32BIT
-	unsigned long uncached_ebase = KSEG1ADDR(ebase);
-#endif
-#ifdef CONFIG_64BIT
-	unsigned long uncached_ebase = TO_UNCAC(ebase);
-#endif
+	unsigned long uncached_ebase = CKSEG1ADDR(ebase);
 
 	if (!addr)
 		panic(panic_null_cerr);

arch/mips/loongson/common/machtype.c

diff --git a/arch/mips/loongson/common/machtype.c b/arch/mips/loongson/common/machtype.c
index 853f184..81fbe6b 100644
--- a/arch/mips/loongson/common/machtype.c
+++ b/arch/mips/loongson/common/machtype.c
@@ -24,7 +24,7 @@
 	[MACH_LEMOTE_FL2F]              "lemote-fuloong-2f-box",
 	[MACH_LEMOTE_ML2F7]             "lemote-mengloong-2f-7inches",
 	[MACH_LEMOTE_YL2F89]            "lemote-yeeloong-2f-8.9inches",
-	[MACH_DEXXON_GDIUM2F10]         "dexxon-gidum-2f-10inches",
+	[MACH_DEXXON_GDIUM2F10]         "dexxon-gdium-2f",
 	[MACH_LEMOTE_NAS]		"lemote-nas-2f",
 	[MACH_LEMOTE_LL2F]              "lemote-lynloong-2f",
 	[MACH_LOONGSON_END]             NULL,

arch/mips/loongson/common/mem.c

diff --git a/arch/mips/loongson/common/mem.c b/arch/mips/loongson/common/mem.c
index ec2f796..30eba60 100644
--- a/arch/mips/loongson/common/mem.c
+++ b/arch/mips/loongson/common/mem.c
@@ -75,7 +75,7 @@
 	unsigned long end = offset + size;
 
 	if (__uncached_access(file, offset)) {
-		if (((uca_start && offset) >= uca_start) &&
+		if (uca_start && (offset >= uca_start) &&
 		    (end <= uca_end))
 			return __pgprot((pgprot_val(vma_prot) &
 					 ~_CACHE_MASK) |
@@ -96,7 +96,7 @@
 		return 0;
 
 	for_each_pci_dev(dev) {
-		if ((dev->class >> 8) == PCI_CLASS_DISPLAY_VGA) {
+		if ((dev->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
 			for (idx = 0; idx < PCI_NUM_RESOURCES; idx++) {
 				r = &dev->resource[idx];
 				if (!r->start && r->end)

arch/mips/loongson/common/reset.c

diff --git a/arch/mips/loongson/common/reset.c b/arch/mips/loongson/common/reset.c
index 4bd9c18..9e10d62 100644
--- a/arch/mips/loongson/common/reset.c
+++ b/arch/mips/loongson/common/reset.c
@@ -16,13 +16,31 @@
 
 #include <loongson.h>
 
+static inline void loongson_reboot(void)
+{
+#ifndef CONFIG_CPU_JUMP_WORKAROUNDS
+	((void (*)(void))ioremap_nocache(LOONGSON_BOOT_BASE, 4)) ();
+#else
+	void (*func)(void);
+
+	func = (void *)ioremap_nocache(LOONGSON_BOOT_BASE, 4);
+
+	__asm__ __volatile__(
+	"       .set    noat                                            \n"
+	"       jr      %[func]                                         \n"
+	"       .set    at                                              \n"
+	: /* No outputs */
+	: [func] "r" (func));
+#endif
+}
+
 static void loongson_restart(char *command)
 {
 	/* do preparation for reboot */
 	mach_prepare_reboot();
 
 	/* reboot via jumping to boot base address */
-	((void (*)(void))ioremap_nocache(LOONGSON_BOOT_BASE, 4)) ();
+	loongson_reboot();
 }
 
 static void loongson_poweroff(void)

arch/mips/loongson/common/setup.c

diff --git a/arch/mips/loongson/common/setup.c b/arch/mips/loongson/common/setup.c
index 4cd2aa9..27d826b 100644
--- a/arch/mips/loongson/common/setup.c
+++ b/arch/mips/loongson/common/setup.c
@@ -41,15 +41,12 @@
 	conswitchp = &vga_con;
 
 	screen_info = (struct screen_info) {
-		0, 25,		/* orig-x, orig-y */
-		    0,		/* unused */
-		    0,		/* orig-video-page */
-		    0,		/* orig-video-mode */
-		    80,		/* orig-video-cols */
-		    0, 0, 0,	/* ega_ax, ega_bx, ega_cx */
-		    25,		/* orig-video-lines */
-		    VIDEO_TYPE_VGAC,	/* orig-video-isVGA */
-		    16		/* orig-video-points */
+		.orig_x			= 0,
+		.orig_y			= 25,
+		.orig_video_cols	= 80,
+		.orig_video_lines	= 25,
+		.orig_video_isVGA	= VIDEO_TYPE_VGAC,
+		.orig_video_points	= 16,
 	};
 #elif defined(CONFIG_DUMMY_CONSOLE)
 	conswitchp = &dummy_con;

arch/mips/loongson/lemote-2f/irq.c

diff --git a/arch/mips/loongson/lemote-2f/irq.c b/arch/mips/loongson/lemote-2f/irq.c
index 882dfcd4..1d8b4d2 100644
--- a/arch/mips/loongson/lemote-2f/irq.c
+++ b/arch/mips/loongson/lemote-2f/irq.c
@@ -79,7 +79,7 @@
 	if (pending & CAUSEF_IP7)
 		do_IRQ(LOONGSON_TIMER_IRQ);
 	else if (pending & CAUSEF_IP6) {	/* North Bridge, Perf counter */
-#ifdef CONFIG_OPROFILE
+#if defined(CONFIG_OPROFILE) || defined(CONFIG_OPROFILE_MODULE)
 		do_IRQ(LOONGSON2_PERFCNT_IRQ);
 #endif
 		bonito_irqdispatch();

arch/mips/math-emu/cp1emu.c

diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 8f2f8e9..f2338d1 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -78,6 +78,9 @@
 #define FPCREG_RID	0	/* $0  = revision id */
 #define FPCREG_CSR	31	/* $31 = csr */
 
+/* Determine rounding mode from the RM bits of the FCSR */
+#define modeindex(v) ((v) & FPU_CSR_RM)
+
 /* Convert Mips rounding mode (0..3) to IEEE library modes. */
 static const unsigned char ieee_rm[4] = {
 	[FPU_CSR_RN] = IEEE754_RN,
@@ -384,10 +387,14 @@
 					(void *) (xcp->cp0_epc),
 					MIPSInst_RT(ir), value);
 #endif
-				value &= (FPU_CSR_FLUSH | FPU_CSR_ALL_E | FPU_CSR_ALL_S | 0x03);
-				ctx->fcr31 &= ~(FPU_CSR_FLUSH | FPU_CSR_ALL_E | FPU_CSR_ALL_S | 0x03);
-				/* convert to ieee library modes */
-				ctx->fcr31 |= (value & ~0x3) | ieee_rm[value & 0x3];
+
+				/*
+				 * Don't write reserved bits,
+				 * and convert to ieee library modes
+				 */
+				ctx->fcr31 = (value &
+						~(FPU_CSR_RSVD | FPU_CSR_RM)) |
+						ieee_rm[modeindex(value)];
 			}
 			if ((ctx->fcr31 >> 5) & ctx->fcr31 & FPU_CSR_ALL_E) {
 				return SIGFPE;

arch/mips/mm/tlbex.c

diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index d1f68aa..86f004d 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -31,6 +31,16 @@
 #include <asm/war.h>
 #include <asm/uasm.h>
 
+/*
+ * TLB load/store/modify handlers.
+ *
+ * Only the fastpath gets synthesized at runtime, the slowpath for
+ * do_page_fault remains normal asm.
+ */
+extern void tlb_do_page_fault_0(void);
+extern void tlb_do_page_fault_1(void);
+
+
 static inline int r45k_bvahwbug(void)
 {
 	/* XXX: We should probe for the presence of this bug, but we don't. */
@@ -83,6 +93,7 @@
 	label_nopage_tlbm,
 	label_smp_pgtable_change,
 	label_r3000_write_probe_fail,
+	label_large_segbits_fault,
 #ifdef CONFIG_HUGETLB_PAGE
 	label_tlb_huge_update,
 #endif
@@ -101,6 +112,7 @@
 UASM_L_LA(_nopage_tlbm)
 UASM_L_LA(_smp_pgtable_change)
 UASM_L_LA(_r3000_write_probe_fail)
+UASM_L_LA(_large_segbits_fault)
 #ifdef CONFIG_HUGETLB_PAGE
 UASM_L_LA(_tlb_huge_update)
 #endif
@@ -157,6 +169,10 @@
 static struct uasm_label labels[128] __cpuinitdata;
 static struct uasm_reloc relocs[128] __cpuinitdata;
 
+#ifdef CONFIG_64BIT
+static int check_for_high_segbits __cpuinitdata;
+#endif
+
 #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
 /*
  * CONFIG_MIPS_PGD_C0_CONTEXT implies 64 bit and lack of pgd_current,
@@ -408,7 +424,7 @@
 		UASM_i_ROTR(p, reg, reg, ilog2(_PAGE_GLOBAL) - ilog2(_PAGE_NO_EXEC));
 	} else {
 #ifdef CONFIG_64BIT_PHYS_ADDR
-		uasm_i_dsrl(p, reg, reg, ilog2(_PAGE_GLOBAL));
+		uasm_i_dsrl_safe(p, reg, reg, ilog2(_PAGE_GLOBAL));
 #else
 		UASM_i_SRL(p, reg, reg, ilog2(_PAGE_GLOBAL));
 #endif
@@ -532,7 +548,24 @@
 	 * The vmalloc handling is not in the hotpath.
 	 */
 	uasm_i_dmfc0(p, tmp, C0_BADVADDR);
-	uasm_il_bltz(p, r, tmp, label_vmalloc);
+
+	if (check_for_high_segbits) {
+		/*
+		 * The kernel currently implicitely assumes that the
+		 * MIPS SEGBITS parameter for the processor is
+		 * (PGDIR_SHIFT+PGDIR_BITS) or less, and will never
+		 * allocate virtual addresses outside the maximum
+		 * range for SEGBITS = (PGDIR_SHIFT+PGDIR_BITS). But
+		 * that doesn't prevent user code from accessing the
+		 * higher xuseg addresses.  Here, we make sure that
+		 * everything but the lower xuseg addresses goes down
+		 * the module_alloc/vmalloc path.
+		 */
+		uasm_i_dsrl_safe(p, ptr, tmp, PGDIR_SHIFT + PGD_ORDER + PAGE_SHIFT - 3);
+		uasm_il_bnez(p, r, ptr, label_vmalloc);
+	} else {
+		uasm_il_bltz(p, r, tmp, label_vmalloc);
+	}
 	/* No uasm_i_nop needed here, since the next insn doesn't touch TMP. */
 
 #ifdef CONFIG_MIPS_PGD_C0_CONTEXT
@@ -549,14 +582,14 @@
 	 * SMTC uses TCBind value as "CPU" index
 	 */
 	uasm_i_mfc0(p, ptr, C0_TCBIND);
-	uasm_i_dsrl(p, ptr, ptr, 19);
+	uasm_i_dsrl_safe(p, ptr, ptr, 19);
 # else
 	/*
 	 * 64 bit SMP running in XKPHYS has smp_processor_id() << 3
 	 * stored in CONTEXT.
 	 */
 	uasm_i_dmfc0(p, ptr, C0_CONTEXT);
-	uasm_i_dsrl(p, ptr, ptr, 23);
+	uasm_i_dsrl_safe(p, ptr, ptr, 23);
 # endif
 	UASM_i_LA_mostly(p, tmp, pgdc);
 	uasm_i_daddu(p, ptr, ptr, tmp);
@@ -569,44 +602,78 @@
 
 	uasm_l_vmalloc_done(l, *p);
 
-	if (PGDIR_SHIFT - 3 < 32)		/* get pgd offset in bytes */
-		uasm_i_dsrl(p, tmp, tmp, PGDIR_SHIFT-3);
-	else
-		uasm_i_dsrl32(p, tmp, tmp, PGDIR_SHIFT - 3 - 32);
+	/* get pgd offset in bytes */
+	uasm_i_dsrl_safe(p, tmp, tmp, PGDIR_SHIFT - 3);
 
 	uasm_i_andi(p, tmp, tmp, (PTRS_PER_PGD - 1)<<3);
 	uasm_i_daddu(p, ptr, ptr, tmp); /* add in pgd offset */
 #ifndef __PAGETABLE_PMD_FOLDED
 	uasm_i_dmfc0(p, tmp, C0_BADVADDR); /* get faulting address */
 	uasm_i_ld(p, ptr, 0, ptr); /* get pmd pointer */
-	uasm_i_dsrl(p, tmp, tmp, PMD_SHIFT-3); /* get pmd offset in bytes */
+	uasm_i_dsrl_safe(p, tmp, tmp, PMD_SHIFT-3); /* get pmd offset in bytes */
 	uasm_i_andi(p, tmp, tmp, (PTRS_PER_PMD - 1)<<3);
 	uasm_i_daddu(p, ptr, ptr, tmp); /* add in pmd offset */
 #endif
 }
 
+enum vmalloc64_mode {not_refill, refill};
 /*
  * BVADDR is the faulting address, PTR is scratch.
  * PTR will hold the pgd for vmalloc.
  */
 static void __cpuinit
 build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
-			unsigned int bvaddr, unsigned int ptr)
+			unsigned int bvaddr, unsigned int ptr,
+			enum vmalloc64_mode mode)
 {
 	long swpd = (long)swapper_pg_dir;
+	int single_insn_swpd;
+	int did_vmalloc_branch = 0;
+
+	single_insn_swpd = uasm_in_compat_space_p(swpd) && !uasm_rel_lo(swpd);
 
 	uasm_l_vmalloc(l, *p);
 
-	if (uasm_in_compat_space_p(swpd) && !uasm_rel_lo(swpd)) {
-		uasm_il_b(p, r, label_vmalloc_done);
-		uasm_i_lui(p, ptr, uasm_rel_hi(swpd));
-	} else {
-		UASM_i_LA_mostly(p, ptr, swpd);
-		uasm_il_b(p, r, label_vmalloc_done);
-		if (uasm_in_compat_space_p(swpd))
-			uasm_i_addiu(p, ptr, ptr, uasm_rel_lo(swpd));
-		else
-			uasm_i_daddiu(p, ptr, ptr, uasm_rel_lo(swpd));
+	if (mode == refill && check_for_high_segbits) {
+		if (single_insn_swpd) {
+			uasm_il_bltz(p, r, bvaddr, label_vmalloc_done);
+			uasm_i_lui(p, ptr, uasm_rel_hi(swpd));
+			did_vmalloc_branch = 1;
+			/* fall through */
+		} else {
+			uasm_il_bgez(p, r, bvaddr, label_large_segbits_fault);
+		}
+	}
+	if (!did_vmalloc_branch) {
+		if (uasm_in_compat_space_p(swpd) && !uasm_rel_lo(swpd)) {
+			uasm_il_b(p, r, label_vmalloc_done);
+			uasm_i_lui(p, ptr, uasm_rel_hi(swpd));
+		} else {
+			UASM_i_LA_mostly(p, ptr, swpd);
+			uasm_il_b(p, r, label_vmalloc_done);
+			if (uasm_in_compat_space_p(swpd))
+				uasm_i_addiu(p, ptr, ptr, uasm_rel_lo(swpd));
+			else
+				uasm_i_daddiu(p, ptr, ptr, uasm_rel_lo(swpd));
+		}
+	}
+	if (mode == refill && check_for_high_segbits) {
+		uasm_l_large_segbits_fault(l, *p);
+		/*
+		 * We get here if we are an xsseg address, or if we are
+		 * an xuseg address above (PGDIR_SHIFT+PGDIR_BITS) boundary.
+		 *
+		 * Ignoring xsseg (assume disabled so would generate
+		 * (address errors?), the only remaining possibility
+		 * is the upper xuseg addresses.  On processors with
+		 * TLB_SEGBITS <= PGDIR_SHIFT+PGDIR_BITS, these
+		 * addresses would have taken an address error. We try
+		 * to mimic that here by taking a load/istream page
+		 * fault.
+		 */
+		UASM_i_LA(p, ptr, (unsigned long)tlb_do_page_fault_0);
+		uasm_i_jr(p, ptr);
+		uasm_i_nop(p);
 	}
 }
 
@@ -720,9 +787,9 @@
 			UASM_i_MTC0(p, tmp, C0_ENTRYLO0); /* load it */
 			UASM_i_ROTR(p, ptep, ptep, ilog2(_PAGE_GLOBAL) - ilog2(_PAGE_NO_EXEC));
 		} else {
-			uasm_i_dsrl(p, tmp, tmp, ilog2(_PAGE_GLOBAL)); /* convert to entrylo0 */
+			uasm_i_dsrl_safe(p, tmp, tmp, ilog2(_PAGE_GLOBAL)); /* convert to entrylo0 */
 			UASM_i_MTC0(p, tmp, C0_ENTRYLO0); /* load it */
-			uasm_i_dsrl(p, ptep, ptep, ilog2(_PAGE_GLOBAL)); /* convert to entrylo1 */
+			uasm_i_dsrl_safe(p, ptep, ptep, ilog2(_PAGE_GLOBAL)); /* convert to entrylo1 */
 		}
 		UASM_i_MTC0(p, ptep, C0_ENTRYLO1); /* load it */
 	} else {
@@ -793,9 +860,9 @@
 		uasm_i_dmfc0(&p, K0, C0_BADVADDR);
 		uasm_i_dmfc0(&p, K1, C0_ENTRYHI);
 		uasm_i_xor(&p, K0, K0, K1);
-		uasm_i_dsrl32(&p, K1, K0, 62 - 32);
-		uasm_i_dsrl(&p, K0, K0, 12 + 1);
-		uasm_i_dsll32(&p, K0, K0, 64 + 12 + 1 - segbits - 32);
+		uasm_i_dsrl_safe(&p, K1, K0, 62);
+		uasm_i_dsrl_safe(&p, K0, K0, 12 + 1);
+		uasm_i_dsll_safe(&p, K0, K0, 64 + 12 + 1 - segbits);
 		uasm_i_or(&p, K0, K0, K1);
 		uasm_il_bnez(&p, &r, K0, label_leave);
 		/* No need for uasm_i_nop */
@@ -825,7 +892,7 @@
 #endif
 
 #ifdef CONFIG_64BIT
-	build_get_pgd_vmalloc64(&p, &l, &r, K0, K1);
+	build_get_pgd_vmalloc64(&p, &l, &r, K0, K1, refill);
 #endif
 
 	/*
@@ -935,15 +1002,6 @@
 }
 
 /*
- * TLB load/store/modify handlers.
- *
- * Only the fastpath gets synthesized at runtime, the slowpath for
- * do_page_fault remains normal asm.
- */
-extern void tlb_do_page_fault_0(void);
-extern void tlb_do_page_fault_1(void);
-
-/*
  * 128 instructions for the fastpath handler is generous and should
  * never be exceeded.
  */
@@ -1302,7 +1360,7 @@
 	uasm_i_eret(p); /* return from trap */
 
 #ifdef CONFIG_64BIT
-	build_get_pgd_vmalloc64(p, l, r, tmp, ptr);
+	build_get_pgd_vmalloc64(p, l, r, tmp, ptr, not_refill);
 #endif
 }
 
@@ -1322,9 +1380,9 @@
 		uasm_i_dmfc0(&p, K0, C0_BADVADDR);
 		uasm_i_dmfc0(&p, K1, C0_ENTRYHI);
 		uasm_i_xor(&p, K0, K0, K1);
-		uasm_i_dsrl32(&p, K1, K0, 62 - 32);
-		uasm_i_dsrl(&p, K0, K0, 12 + 1);
-		uasm_i_dsll32(&p, K0, K0, 64 + 12 + 1 - segbits - 32);
+		uasm_i_dsrl_safe(&p, K1, K0, 62);
+		uasm_i_dsrl_safe(&p, K0, K0, 12 + 1);
+		uasm_i_dsll_safe(&p, K0, K0, 64 + 12 + 1 - segbits);
 		uasm_i_or(&p, K0, K0, K1);
 		uasm_il_bnez(&p, &r, K0, label_leave);
 		/* No need for uasm_i_nop */
@@ -1526,6 +1584,10 @@
 	 */
 	static int run_once = 0;
 
+#ifdef CONFIG_64BIT
+	check_for_high_segbits = current_cpu_data.vmbits > (PGDIR_SHIFT + PGD_ORDER + PAGE_SHIFT - 3);
+#endif
+
 	switch (current_cpu_type()) {
 	case CPU_R2000:
 	case CPU_R3000:

arch/mips/nxp/pnx8550/common/reset.c

diff --git a/arch/mips/nxp/pnx8550/common/reset.c b/arch/mips/nxp/pnx8550/common/reset.c
index 76bc3ec..fadd8744 100644
--- a/arch/mips/nxp/pnx8550/common/reset.c
+++ b/arch/mips/nxp/pnx8550/common/reset.c
@@ -20,6 +20,8 @@
  * Reset the PNX8550 board.
  *
  */
+#include <linux/kernel.h>
+
 #include <asm/reboot.h>
 #include <glb.h>
 

arch/mips/oprofile/op_model_loongson2.c

diff --git a/arch/mips/oprofile/op_model_loongson2.c b/arch/mips/oprofile/op_model_loongson2.c
index 29e2326..fa3bf66 100644
--- a/arch/mips/oprofile/op_model_loongson2.c
+++ b/arch/mips/oprofile/op_model_loongson2.c
@@ -122,7 +122,7 @@
 	 */
 
 	/* Check whether the irq belongs to me */
-	enabled = read_c0_perfcnt() & LOONGSON2_PERFCNT_INT_EN;
+	enabled = read_c0_perfctrl() & LOONGSON2_PERFCNT_INT_EN;
 	if (!enabled)
 		return IRQ_NONE;
 	enabled = reg.cnt1_enabled | reg.cnt2_enabled;

arch/mips/pci/pci-sb1250.c

diff --git a/arch/mips/pci/pci-sb1250.c b/arch/mips/pci/pci-sb1250.c
index ada24e6..1711e8e 100644
--- a/arch/mips/pci/pci-sb1250.c
+++ b/arch/mips/pci/pci-sb1250.c
@@ -37,6 +37,7 @@
 #include <linux/mm.h>
 #include <linux/console.h>
 #include <linux/tty.h>
+#include <linux/vt.h>
 
 #include <asm/io.h>
 
@@ -254,7 +255,7 @@
 	 * XXX ehs: Should this happen in PCI Device mode?
 	 */
 	io_map_base = ioremap(A_PHYS_LDTPCI_IO_MATCH_BYTES, 1024 * 1024);
-	sb1250_controller.io_map_base = io_map_base;
+	sb1250_controller.io_map_base = (unsigned long)io_map_base;
 	set_io_port_base((unsigned long)io_map_base);
 
 #ifdef CONFIG_SIBYTE_HAS_LDT

arch/mips/sgi-ip22/ip22-berr.c

diff --git a/arch/mips/sgi-ip22/ip22-berr.c b/arch/mips/sgi-ip22/ip22-berr.c
index de6a0cc..911d399 100644
--- a/arch/mips/sgi-ip22/ip22-berr.c
+++ b/arch/mips/sgi-ip22/ip22-berr.c
@@ -89,7 +89,7 @@
 void ip22_be_interrupt(int irq)
 {
 	const int field = 2 * sizeof(unsigned long);
-	const struct pt_regs *regs = get_irq_regs();
+	struct pt_regs *regs = get_irq_regs();
 
 	save_and_clear_buserr();
 	print_buserr();

arch/mips/sgi-ip22/ip28-berr.c

diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c
index 30e12e2..88c684e 100644
--- a/arch/mips/sgi-ip22/ip28-berr.c
+++ b/arch/mips/sgi-ip22/ip28-berr.c
@@ -453,7 +453,7 @@
 
 void ip22_be_interrupt(int irq)
 {
-	const struct pt_regs *regs = get_irq_regs();
+	struct pt_regs *regs = get_irq_regs();
 
 	count_be_interrupt++;
 

arch/mips/sibyte/swarm/setup.c

diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c
index 5277aac..c308989 100644
--- a/arch/mips/sibyte/swarm/setup.c
+++ b/arch/mips/sibyte/swarm/setup.c
@@ -145,15 +145,14 @@
 
 #ifdef CONFIG_VT
 	screen_info = (struct screen_info) {
-		0, 0,           /* orig-x, orig-y */
-		0,              /* unused */
-		52,             /* orig_video_page */
-		3,              /* orig_video_mode */
-		80,             /* orig_video_cols */
-		4626, 3, 9,     /* unused, ega_bx, unused */
-		25,             /* orig_video_lines */
-		0x22,           /* orig_video_isVGA */
-		16              /* orig_video_points */
+		.orig_video_page	= 52,
+		.orig_video_mode	= 3,
+		.orig_video_cols	= 80,
+		.flags			= 12,
+		.orig_video_ega_bx	= 3,
+		.orig_video_lines	= 25,
+		.orig_video_isVGA	= 0x22,
+		.orig_video_points	= 16,
        };
        /* XXXKW for CFE, get lines/cols from environment */
 #endif

arch/mn10300/include/asm/atomic.h

diff --git a/arch/mn10300/include/asm/atomic.h b/arch/mn10300/include/asm/atomic.h
index 5bf5be9..e41222d 100644
--- a/arch/mn10300/include/asm/atomic.h
+++ b/arch/mn10300/include/asm/atomic.h
@@ -31,7 +31,7 @@
  * Atomically reads the value of @v.  Note that the guaranteed
  * useful range of an atomic_t is only 24 bits.
  */
-#define atomic_read(v)	((v)->counter)
+#define atomic_read(v)	(*(volatile int *)&(v)->counter)
 
 /**
  * atomic_set - set atomic variable

arch/parisc/include/asm/atomic.h

diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 716634d..f819559 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -189,7 +189,7 @@
 
 static __inline__ int atomic_read(const atomic_t *v)
 {
-	return v->counter;
+	return (*(volatile int *)&(v)->counter);
 }
 
 /* exported interface */
@@ -286,7 +286,7 @@
 static __inline__ s64
 atomic64_read(const atomic64_t *v)
 {
-	return v->counter;
+	return (*(volatile long *)&(v)->counter);
 }
 
 #define atomic64_add(i,v)	((void)(__atomic64_add_return( ((s64)(i)),(v))))

arch/powerpc/include/asm/hw_irq.h

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 9f4c9d4f..bd100fc 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -130,43 +130,5 @@
  */
 struct irq_chip;
 
-#ifdef CONFIG_PERF_EVENTS
-
-#ifdef CONFIG_PPC64
-static inline unsigned long test_perf_event_pending(void)
-{
-	unsigned long x;
-
-	asm volatile("lbz %0,%1(13)"
-		: "=r" (x)
-		: "i" (offsetof(struct paca_struct, perf_event_pending)));
-	return x;
-}
-
-static inline void set_perf_event_pending(void)
-{
-	asm volatile("stb %0,%1(13)" : :
-		"r" (1),
-		"i" (offsetof(struct paca_struct, perf_event_pending)));
-}
-
-static inline void clear_perf_event_pending(void)
-{
-	asm volatile("stb %0,%1(13)" : :
-		"r" (0),
-		"i" (offsetof(struct paca_struct, perf_event_pending)));
-}
-#endif /* CONFIG_PPC64 */
-
-#else  /* CONFIG_PERF_EVENTS */
-
-static inline unsigned long test_perf_event_pending(void)
-{
-	return 0;
-}
-
-static inline void clear_perf_event_pending(void) {}
-#endif /* CONFIG_PERF_EVENTS */
-
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_HW_IRQ_H */

arch/powerpc/kernel/asm-offsets.c

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 957ceb7..c09138d 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -133,7 +133,6 @@
 	DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
-	DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_event_pending));
 	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,

arch/powerpc/kernel/dma-swiotlb.c

diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 59c9285..4ff4da2c 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -1,7 +1,8 @@
 /*
  * Contains routines needed to support swiotlb for ppc.
  *
- * Copyright (C) 2009 Becky Bruce, Freescale Semiconductor
+ * Copyright (C) 2009-2010 Freescale Semiconductor, Inc.
+ * Author: Becky Bruce
  *
  * 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
@@ -70,7 +71,7 @@
 	sd->max_direct_dma_addr = 0;
 
 	/* May need to bounce if the device can't address all of DRAM */
-	if (dma_get_mask(dev) < lmb_end_of_DRAM())
+	if ((dma_get_mask(dev) + 1) < lmb_end_of_DRAM())
 		set_dma_ops(dev, &swiotlb_dma_ops);
 
 	return NOTIFY_DONE;

arch/powerpc/kernel/entry_64.S

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 07109d8..42e9d90 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -556,15 +556,6 @@
 2:
 	TRACE_AND_RESTORE_IRQ(r5);
 
-#ifdef CONFIG_PERF_EVENTS
-	/* check paca->perf_event_pending if we're enabling ints */
-	lbz	r3,PACAPERFPEND(r13)
-	and.	r3,r3,r5
-	beq	27f
-	bl	.perf_event_do_pending
-27:
-#endif /* CONFIG_PERF_EVENTS */
-
 	/* extract EE bit and use it to restore paca->hard_enabled */
 	ld	r3,_MSR(r1)
 	rldicl	r4,r3,49,63		/* r0 = (r3 >> 15) & 1 */

arch/powerpc/kernel/irq.c

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 64f6f20..066bd31 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -53,7 +53,6 @@
 #include <linux/bootmem.h>
 #include <linux/pci.h>
 #include <linux/debugfs.h>
-#include <linux/perf_event.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -145,11 +144,6 @@
 	}
 #endif /* CONFIG_PPC_STD_MMU_64 */
 
-	if (test_perf_event_pending()) {
-		clear_perf_event_pending();
-		perf_event_do_pending();
-	}
-
 	/*
 	 * if (get_paca()->hard_enabled) return;
 	 * But again we need to take care that gcc gets hard_enabled directly

arch/powerpc/kernel/perf_event.c

diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 08460a2..43b83c3 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -35,6 +35,9 @@
 	u64 alternatives[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
 	unsigned long amasks[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
 	unsigned long avalues[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
+
+	unsigned int group_flag;
+	int n_txn_start;
 };
 DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
 
@@ -718,66 +721,6 @@
 	return n;
 }
 
-static void event_sched_in(struct perf_event *event)
-{
-	event->state = PERF_EVENT_STATE_ACTIVE;
-	event->oncpu = smp_processor_id();
-	event->tstamp_running += event->ctx->time - event->tstamp_stopped;
-	if (is_software_event(event))
-		event->pmu->enable(event);
-}
-
-/*
- * Called to enable a whole group of events.
- * Returns 1 if the group was enabled, or -EAGAIN if it could not be.
- * Assumes the caller has disabled interrupts and has
- * frozen the PMU with hw_perf_save_disable.
- */
-int hw_perf_group_sched_in(struct perf_event *group_leader,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx)
-{
-	struct cpu_hw_events *cpuhw;
-	long i, n, n0;
-	struct perf_event *sub;
-
-	if (!ppmu)
-		return 0;
-	cpuhw = &__get_cpu_var(cpu_hw_events);
-	n0 = cpuhw->n_events;
-	n = collect_events(group_leader, ppmu->n_counter - n0,
-			   &cpuhw->event[n0], &cpuhw->events[n0],
-			   &cpuhw->flags[n0]);
-	if (n < 0)
-		return -EAGAIN;
-	if (check_excludes(cpuhw->event, cpuhw->flags, n0, n))
-		return -EAGAIN;
-	i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n + n0);
-	if (i < 0)
-		return -EAGAIN;
-	cpuhw->n_events = n0 + n;
-	cpuhw->n_added += n;
-
-	/*
-	 * OK, this group can go on; update event states etc.,
-	 * and enable any software events
-	 */
-	for (i = n0; i < n0 + n; ++i)
-		cpuhw->event[i]->hw.config = cpuhw->events[i];
-	cpuctx->active_oncpu += n;
-	n = 1;
-	event_sched_in(group_leader);
-	list_for_each_entry(sub, &group_leader->sibling_list, group_entry) {
-		if (sub->state != PERF_EVENT_STATE_OFF) {
-			event_sched_in(sub);
-			++n;
-		}
-	}
-	ctx->nr_active += n;
-
-	return 1;
-}
-
 /*
  * Add a event to the PMU.
  * If all events are not already frozen, then we disable and
@@ -805,12 +748,22 @@
 	cpuhw->event[n0] = event;
 	cpuhw->events[n0] = event->hw.config;
 	cpuhw->flags[n0] = event->hw.event_base;
+
+	/*
+	 * If group events scheduling transaction was started,
+	 * skip the schedulability test here, it will be peformed
+	 * at commit time(->commit_txn) as a whole
+	 */
+	if (cpuhw->group_flag & PERF_EVENT_TXN_STARTED)
+		goto nocheck;
+
 	if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1))
 		goto out;
 	if (power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n0 + 1))
 		goto out;
-
 	event->hw.config = cpuhw->events[n0];
+
+nocheck:
 	++cpuhw->n_events;
 	++cpuhw->n_added;
 
@@ -896,11 +849,65 @@
 	local_irq_restore(flags);
 }
 
+/*
+ * Start group events scheduling transaction
+ * Set the flag to make pmu::enable() not perform the
+ * schedulability test, it will be performed at commit time
+ */
+void power_pmu_start_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	cpuhw->group_flag |= PERF_EVENT_TXN_STARTED;
+	cpuhw->n_txn_start = cpuhw->n_events;
+}
+
+/*
+ * Stop group events scheduling transaction
+ * Clear the flag and pmu::enable() will perform the
+ * schedulability test.
+ */
+void power_pmu_cancel_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED;
+}
+
+/*
+ * Commit group events scheduling transaction
+ * Perform the group schedulability test as a whole
+ * Return 0 if success
+ */
+int power_pmu_commit_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw;
+	long i, n;
+
+	if (!ppmu)
+		return -EAGAIN;
+	cpuhw = &__get_cpu_var(cpu_hw_events);
+	n = cpuhw->n_events;
+	if (check_excludes(cpuhw->event, cpuhw->flags, 0, n))
+		return -EAGAIN;
+	i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n);
+	if (i < 0)
+		return -EAGAIN;
+
+	for (i = cpuhw->n_txn_start; i < n; ++i)
+		cpuhw->event[i]->hw.config = cpuhw->events[i];
+
+	return 0;
+}
+
 struct pmu power_pmu = {
 	.enable		= power_pmu_enable,
 	.disable	= power_pmu_disable,
 	.read		= power_pmu_read,
 	.unthrottle	= power_pmu_unthrottle,
+	.start_txn	= power_pmu_start_txn,
+	.cancel_txn	= power_pmu_cancel_txn,
+	.commit_txn	= power_pmu_commit_txn,
 };
 
 /*

arch/powerpc/kernel/time.c

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 1b16b9a..0441bbd 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -532,25 +532,60 @@
 }
 #endif /* CONFIG_PPC_ISERIES */
 
-#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_PPC32)
-DEFINE_PER_CPU(u8, perf_event_pending);
+#ifdef CONFIG_PERF_EVENTS
 
-void set_perf_event_pending(void)
+/*
+ * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
+ */
+#ifdef CONFIG_PPC64
+static inline unsigned long test_perf_event_pending(void)
 {
-	get_cpu_var(perf_event_pending) = 1;
-	set_dec(1);
-	put_cpu_var(perf_event_pending);
+	unsigned long x;
+
+	asm volatile("lbz %0,%1(13)"
+		: "=r" (x)
+		: "i" (offsetof(struct paca_struct, perf_event_pending)));
+	return x;
 }
 
+static inline void set_perf_event_pending_flag(void)
+{
+	asm volatile("stb %0,%1(13)" : :
+		"r" (1),
+		"i" (offsetof(struct paca_struct, perf_event_pending)));
+}
+
+static inline void clear_perf_event_pending(void)
+{
+	asm volatile("stb %0,%1(13)" : :
+		"r" (0),
+		"i" (offsetof(struct paca_struct, perf_event_pending)));
+}
+
+#else /* 32-bit */
+
+DEFINE_PER_CPU(u8, perf_event_pending);
+
+#define set_perf_event_pending_flag()	__get_cpu_var(perf_event_pending) = 1
 #define test_perf_event_pending()	__get_cpu_var(perf_event_pending)
 #define clear_perf_event_pending()	__get_cpu_var(perf_event_pending) = 0
 
-#else  /* CONFIG_PERF_EVENTS && CONFIG_PPC32 */
+#endif /* 32 vs 64 bit */
+
+void set_perf_event_pending(void)
+{
+	preempt_disable();
+	set_perf_event_pending_flag();
+	set_dec(1);
+	preempt_enable();
+}
+
+#else  /* CONFIG_PERF_EVENTS */
 
 #define test_perf_event_pending()	0
 #define clear_perf_event_pending()
 
-#endif /* CONFIG_PERF_EVENTS && CONFIG_PPC32 */
+#endif /* CONFIG_PERF_EVENTS */
 
 /*
  * For iSeries shared processors, we have to let the hypervisor
@@ -582,10 +617,6 @@
 	set_dec(DECREMENTER_MAX);
 
 #ifdef CONFIG_PPC32
-	if (test_perf_event_pending()) {
-		clear_perf_event_pending();
-		perf_event_do_pending();
-	}
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
 		do_IRQ(regs);
 #endif
@@ -604,6 +635,11 @@
 
 	calculate_steal_time();
 
+	if (test_perf_event_pending()) {
+		clear_perf_event_pending();
+		perf_event_do_pending();
+	}
+
 #ifdef CONFIG_PPC_ISERIES
 	if (firmware_has_feature(FW_FEATURE_ISERIES))
 		get_lppaca()->int_dword.fields.decr_int = 0;

arch/powerpc/kvm/44x_tlb.c

diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 2570fcc..8123125 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -440,7 +440,7 @@
 	unsigned int gtlb_index;
 
 	gtlb_index = kvmppc_get_gpr(vcpu, ra);
-	if (gtlb_index > KVM44x_GUEST_TLB_SIZE) {
+	if (gtlb_index >= KVM44x_GUEST_TLB_SIZE) {
 		printk("%s: index %d\n", __func__, gtlb_index);
 		kvmppc_dump_vcpu(vcpu);
 		return EMULATE_FAIL;

arch/s390/kernel/head31.S

diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S
index 1bbcc49..b8f8dc1 100644
--- a/arch/s390/kernel/head31.S
+++ b/arch/s390/kernel/head31.S
@@ -82,7 +82,7 @@
 _ehead:
 
 #ifdef CONFIG_SHARED_KERNEL
-	.org	0x100000
+	.org	0x100000 - 0x11000	# head.o ends at 0x11000
 #endif
 
 #

arch/s390/kernel/head64.S

diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 1f70970..cdef687 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -80,7 +80,7 @@
 _ehead:
 
 #ifdef CONFIG_SHARED_KERNEL
-	.org	0x100000
+	.org	0x100000 - 0x11000	# head.o ends at 0x11000
 #endif
 
 #

arch/s390/kernel/ptrace.c

diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 33fdc5a..9f654da 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -640,7 +640,7 @@
 
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 {
-	long ret;
+	long ret = 0;
 
 	/* Do the secure computing check first. */
 	secure_computing(regs->gprs[2]);
@@ -649,7 +649,6 @@
 	 * The sysc_tracesys code in entry.S stored the system
 	 * call number to gprs[2].
 	 */
-	ret = regs->gprs[2];
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
 	    (tracehook_report_syscall_entry(regs) ||
 	     regs->gprs[2] >= NR_syscalls)) {
@@ -671,7 +670,7 @@
 				    regs->gprs[2], regs->orig_gpr2,
 				    regs->gprs[3], regs->gprs[4],
 				    regs->gprs[5]);
-	return ret;
+	return ret ?: regs->gprs[2];
 }
 
 asmlinkage void do_syscall_trace_exit(struct pt_regs *regs)

arch/sh/Kconfig

diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 8d90564..e6d8ab5 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -44,6 +44,7 @@
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_ARCH_KGDB
 	select HAVE_HW_BREAKPOINT
+	select HAVE_MIXED_BREAKPOINTS_REGS
 	select PERF_EVENTS if HAVE_HW_BREAKPOINT
 	select ARCH_HIBERNATION_POSSIBLE if MMU
 

arch/sh/configs/rts7751r2d1_defconfig

diff --git a/arch/sh/configs/rts7751r2d1_defconfig b/arch/sh/configs/rts7751r2d1_defconfig
index fba1f62..dba024d 100644
--- a/arch/sh/configs/rts7751r2d1_defconfig
+++ b/arch/sh/configs/rts7751r2d1_defconfig
@@ -877,7 +877,7 @@
 #
 # CONFIG_SERIAL_MAX3100 is not set
 CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=1
+CONFIG_SERIAL_SH_SCI_NR_UARTS=2
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
 CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y

arch/sh/configs/rts7751r2dplus_defconfig

diff --git a/arch/sh/configs/rts7751r2dplus_defconfig b/arch/sh/configs/rts7751r2dplus_defconfig
index a8d538f..6d511d0 100644
--- a/arch/sh/configs/rts7751r2dplus_defconfig
+++ b/arch/sh/configs/rts7751r2dplus_defconfig
@@ -963,7 +963,7 @@
 #
 # CONFIG_SERIAL_MAX3100 is not set
 CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=1
+CONFIG_SERIAL_SH_SCI_NR_UARTS=2
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
 CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y

arch/sh/drivers/pci/pci-sh7751.c

diff --git a/arch/sh/drivers/pci/pci-sh7751.c b/arch/sh/drivers/pci/pci-sh7751.c
index 17811e5..f98141b 100644
--- a/arch/sh/drivers/pci/pci-sh7751.c
+++ b/arch/sh/drivers/pci/pci-sh7751.c
@@ -17,6 +17,7 @@
 #include <linux/io.h>
 #include "pci-sh4.h"
 #include <asm/addrspace.h>
+#include <asm/sizes.h>
 
 static int __init __area_sdram_check(struct pci_channel *chan,
 				     unsigned int area)
@@ -47,8 +48,8 @@
 static struct resource sh7751_pci_resources[] = {
 	{
 		.name	= "SH7751_IO",
-		.start	= SH7751_PCI_IO_BASE,
-		.end	= SH7751_PCI_IO_BASE + SH7751_PCI_IO_SIZE - 1,
+		.start	= 0x1000,
+		.end	= SZ_4M - 1,
 		.flags	= IORESOURCE_IO
 	}, {
 		.name	= "SH7751_mem",

arch/sh/include/asm/atomic.h

diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index 275a448..c798312 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -13,7 +13,7 @@
 
 #define ATOMIC_INIT(i)	( (atomic_t) { (i) } )
 
-#define atomic_read(v)		((v)->counter)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic_set(v,i)		((v)->counter = (i))
 
 #if defined(CONFIG_GUSA_RB)

arch/sh/include/asm/hw_breakpoint.h

diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h
index 965dd78..e14cad9 100644
--- a/arch/sh/include/asm/hw_breakpoint.h
+++ b/arch/sh/include/asm/hw_breakpoint.h
@@ -46,10 +46,14 @@
 /* Maximum number of UBC channels */
 #define HBP_NUM		2
 
+static inline int hw_breakpoint_slots(int type)
+{
+	return HBP_NUM;
+}
+
 /* arch/sh/kernel/hw_breakpoint.c */
-extern int arch_check_va_in_userspace(unsigned long va, u16 hbp_len);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp,
-					 struct task_struct *tsk);
+extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 

arch/sh/include/cpu-sh4/cpu/dma-register.h

diff --git a/arch/sh/include/cpu-sh4/cpu/dma-register.h b/arch/sh/include/cpu-sh4/cpu/dma-register.h
index 55f9fec..de23595 100644
--- a/arch/sh/include/cpu-sh4/cpu/dma-register.h
+++ b/arch/sh/include/cpu-sh4/cpu/dma-register.h
@@ -76,7 +76,7 @@
 }
 
 #define TS_INDEX2VAL(i)	((((i) & 3) << CHCR_TS_LOW_SHIFT) | \
-			 ((((i) >> 2) & 3) << CHCR_TS_HIGH_SHIFT))
+			 (((i) & 0xc) << CHCR_TS_HIGH_SHIFT))
 
 #else /* CONFIG_CPU_SH4A */
 

arch/sh/kernel/hw_breakpoint.c

diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index 675eea7..1f2cf62 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -120,25 +120,16 @@
 }
 
 /*
- * Check for virtual address in user space.
- */
-int arch_check_va_in_userspace(unsigned long va, u16 hbp_len)
-{
-	unsigned int len;
-
-	len = get_hbp_len(hbp_len);
-
-	return (va <= TASK_SIZE - len);
-}
-
-/*
  * Check for virtual address in kernel space.
  */
-static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len)
+int arch_check_bp_in_kernelspace(struct perf_event *bp)
 {
 	unsigned int len;
+	unsigned long va;
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	len = get_hbp_len(hbp_len);
+	va = info->address;
+	len = get_hbp_len(info->len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -226,8 +217,7 @@
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp,
-				  struct task_struct *tsk)
+int arch_validate_hwbkpt_settings(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
@@ -270,15 +260,6 @@
 	if (info->address & align)
 		return -EINVAL;
 
-	/* Check that the virtual address is in the proper range */
-	if (tsk) {
-		if (!arch_check_va_in_userspace(info->address, info->len))
-			return -EFAULT;
-	} else {
-		if (!arch_check_va_in_kernelspace(info->address, info->len))
-			return -EFAULT;
-	}
-
 	return 0;
 }
 
@@ -363,8 +344,7 @@
 		perf_bp_event(bp, args->regs);
 
 		/* Deliver the signal to userspace */
-		if (arch_check_va_in_userspace(bp->attr.bp_addr,
-					       bp->attr.bp_len)) {
+		if (!arch_check_bp_in_kernelspace(bp)) {
 			siginfo_t info;
 
 			info.si_signo = args->signr;

arch/sh/kernel/ptrace_32.c

diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index 7759a9a..d4104ce 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -85,7 +85,7 @@
 
 	bp = thread->ptrace_bps[0];
 	if (!bp) {
-		hw_breakpoint_init(&attr);
+		ptrace_breakpoint_init(&attr);
 
 		attr.bp_addr = addr;
 		attr.bp_len = HW_BREAKPOINT_LEN_2;

arch/sparc/include/asm/atomic_32.h

diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index f0d343c..7ae128b 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -25,7 +25,7 @@
 extern int atomic_add_unless(atomic_t *, int, int);
 extern void atomic_set(atomic_t *, int);
 
-#define atomic_read(v)          ((v)->counter)
+#define atomic_read(v)          (*(volatile int *)&(v)->counter)
 
 #define atomic_add(i, v)	((void)__atomic_add_return( (int)(i), (v)))
 #define atomic_sub(i, v)	((void)__atomic_add_return(-(int)(i), (v)))

arch/sparc/include/asm/atomic_64.h

diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index f2e4800..2050ca0 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -13,8 +13,8 @@
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
-#define atomic_read(v)		((v)->counter)
-#define atomic64_read(v)	((v)->counter)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
 
 #define atomic_set(v, i)	(((v)->counter) = i)
 #define atomic64_set(v, i)	(((v)->counter) = i)

arch/x86/Kconfig

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9458685..01177dc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -53,11 +53,15 @@
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
 	select HAVE_HW_BREAKPOINT
+	select HAVE_MIXED_BREAKPOINTS_REGS
 	select PERF_EVENTS
 	select ANON_INODES
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER
 
+config INSTRUCTION_DECODER
+	def_bool (KPROBES || PERF_EVENTS)
+
 config OUTPUT_FORMAT
 	string
 	default "elf32-i386" if X86_32

arch/x86/Kconfig.cpu

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index a198293..918fbb1 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -502,23 +502,3 @@
 	  CPU might render the kernel unbootable.
 
 	  If unsure, say N.
-
-config X86_DS
-	def_bool X86_PTRACE_BTS
-	depends on X86_DEBUGCTLMSR
-	select HAVE_HW_BRANCH_TRACER
-
-config X86_PTRACE_BTS
-	bool "Branch Trace Store"
-	default y
-	depends on X86_DEBUGCTLMSR
-	depends on BROKEN
-	---help---
-	  This adds a ptrace interface to the hardware's branch trace store.
-
-	  Debuggers may use it to collect an execution trace of the debugged
-	  application in order to answer the question 'how did I get here?'.
-	  Debuggers may trace user mode as well as kernel mode.
-
-	  Say Y unless there is no application development on this machine
-	  and you want to save a small amount of code size.

arch/x86/Kconfig.debug

diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index bc01e3e..bd58c8a 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -174,15 +174,6 @@
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.
 
-config X86_DS_SELFTEST
-    bool "DS selftest"
-    default y
-    depends on DEBUG_KERNEL
-    depends on X86_DS
-	---help---
-	  Perform Debug Store selftests at boot time.
-	  If in doubt, say "N".
-
 config HAVE_MMIOTRACE_SUPPORT
 	def_bool y
 

arch/x86/include/asm/amd_iommu_types.h

diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 86a0ff0..7014e88 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -174,6 +174,40 @@
 				(~((1ULL << (12 + ((lvl) * 9))) - 1)))
 #define PM_ALIGNED(lvl, addr)	((PM_MAP_MASK(lvl) & (addr)) == (addr))
 
+/*
+ * Returns the page table level to use for a given page size
+ * Pagesize is expected to be a power-of-two
+ */
+#define PAGE_SIZE_LEVEL(pagesize) \
+		((__ffs(pagesize) - 12) / 9)
+/*
+ * Returns the number of ptes to use for a given page size
+ * Pagesize is expected to be a power-of-two
+ */
+#define PAGE_SIZE_PTE_COUNT(pagesize) \
+		(1ULL << ((__ffs(pagesize) - 12) % 9))
+
+/*
+ * Aligns a given io-virtual address to a given page size
+ * Pagesize is expected to be a power-of-two
+ */
+#define PAGE_SIZE_ALIGN(address, pagesize) \
+		((address) & ~((pagesize) - 1))
+/*
+ * Creates an IOMMU PTE for an address an a given pagesize
+ * The PTE has no permission bits set
+ * Pagesize is expected to be a power-of-two larger than 4096
+ */
+#define PAGE_SIZE_PTE(address, pagesize)		\
+		(((address) | ((pagesize) - 1)) &	\
+		 (~(pagesize >> 1)) & PM_ADDR_MASK)
+
+/*
+ * Takes a PTE value with mode=0x07 and returns the page size it maps
+ */
+#define PTE_PAGE_SIZE(pte) \
+	(1ULL << (1 + ffz(((pte) | 0xfffULL))))
+
 #define IOMMU_PTE_P  (1ULL << 0)
 #define IOMMU_PTE_TV (1ULL << 1)
 #define IOMMU_PTE_U  (1ULL << 59)

arch/x86/include/asm/apic.h

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index b4ac2cd..1fa03e0 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -373,6 +373,7 @@
 extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
 #endif
 
+#ifdef CONFIG_X86_LOCAL_APIC
 static inline u32 apic_read(u32 reg)
 {
 	return apic->read(reg);
@@ -403,10 +404,19 @@
 	return apic->safe_wait_icr_idle();
 }
 
+#else /* CONFIG_X86_LOCAL_APIC */
+
+static inline u32 apic_read(u32 reg) { return 0; }
+static inline void apic_write(u32 reg, u32 val) { }
+static inline u64 apic_icr_read(void) { return 0; }
+static inline void apic_icr_write(u32 low, u32 high) { }
+static inline void apic_wait_icr_idle(void) { }
+static inline u32 safe_apic_wait_icr_idle(void) { return 0; }
+
+#endif /* CONFIG_X86_LOCAL_APIC */
 
 static inline void ack_APIC_irq(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
 	/*
 	 * ack_APIC_irq() actually gets compiled as a single instruction
 	 * ... yummie.
@@ -414,7 +424,6 @@
 
 	/* Docs say use 0 for future compatibility */
 	apic_write(APIC_EOI, 0);
-#endif
 }
 
 static inline unsigned default_get_apic_id(unsigned long x)

arch/x86/include/asm/atomic.h

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 8f8217b..37b39d2 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -22,7 +22,7 @@
  */
 static inline int atomic_read(const atomic_t *v)
 {
-	return v->counter;
+	return (*(volatile int *)&(v)->counter);
 }
 
 /**

arch/x86/include/asm/atomic64_64.h

diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 51c5b40..b014e23 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -18,7 +18,7 @@
  */
 static inline long atomic64_read(const atomic64_t *v)
 {
-	return v->counter;
+	return (*(volatile long *)&(v)->counter);
 }
 
 /**

arch/x86/include/asm/ds.h

diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
deleted file mode 100644
index 70dac19..0000000
--- a/arch/x86/include/asm/ds.h
+++ /dev/null
@@ -1,302 +0,0 @@
-/*
- * Debug Store (DS) support
- *
- * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for branch trace store (BTS) and
- * precise-event based sampling (PEBS).
- *
- * It manages:
- * - DS and BTS hardware configuration
- * - buffer overflow handling (to be done)
- * - buffer access
- *
- * It does not do:
- * - security checking (is the caller allowed to trace the task)
- * - buffer allocation (memory accounting)
- *
- *
- * Copyright (C) 2007-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
- */
-
-#ifndef _ASM_X86_DS_H
-#define _ASM_X86_DS_H
-
-
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/err.h>
-
-
-#ifdef CONFIG_X86_DS
-
-struct task_struct;
-struct ds_context;
-struct ds_tracer;
-struct bts_tracer;
-struct pebs_tracer;
-
-typedef void (*bts_ovfl_callback_t)(struct bts_tracer *);
-typedef void (*pebs_ovfl_callback_t)(struct pebs_tracer *);
-
-
-/*
- * A list of features plus corresponding macros to talk about them in
- * the ds_request function's flags parameter.
- *
- * We use the enum to index an array of corresponding control bits;
- * we use the macro to index a flags bit-vector.
- */
-enum ds_feature {
-	dsf_bts = 0,
-	dsf_bts_kernel,
-#define BTS_KERNEL (1 << dsf_bts_kernel)
-	/* trace kernel-mode branches */
-
-	dsf_bts_user,
-#define BTS_USER (1 << dsf_bts_user)
-	/* trace user-mode branches */
-
-	dsf_bts_overflow,
-	dsf_bts_max,
-	dsf_pebs = dsf_bts_max,
-
-	dsf_pebs_max,
-	dsf_ctl_max = dsf_pebs_max,
-	dsf_bts_timestamps = dsf_ctl_max,
-#define BTS_TIMESTAMPS (1 << dsf_bts_timestamps)
-	/* add timestamps into BTS trace */
-
-#define BTS_USER_FLAGS (BTS_KERNEL | BTS_USER | BTS_TIMESTAMPS)
-};
-
-
-/*
- * Request BTS or PEBS
- *
- * Due to alignement constraints, the actual buffer may be slightly
- * smaller than the requested or provided buffer.
- *
- * Returns a pointer to a tracer structure on success, or
- * ERR_PTR(errcode) on failure.
- *
- * The interrupt threshold is independent from the overflow callback
- * to allow users to use their own overflow interrupt handling mechanism.
- *
- * The function might sleep.
- *
- * task: the task to request recording for
- * cpu:  the cpu to request recording for
- * base: the base pointer for the (non-pageable) buffer;
- * size: the size of the provided buffer in bytes
- * ovfl: pointer to a function to be called on buffer overflow;
- *       NULL if cyclic buffer requested
- * th: the interrupt threshold in records from the end of the buffer;
- *     -1 if no interrupt threshold is requested.
- * flags: a bit-mask of the above flags
- */
-extern struct bts_tracer *ds_request_bts_task(struct task_struct *task,
-					      void *base, size_t size,
-					      bts_ovfl_callback_t ovfl,
-					      size_t th, unsigned int flags);
-extern struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
-					     bts_ovfl_callback_t ovfl,
-					     size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
-						void *base, size_t size,
-						pebs_ovfl_callback_t ovfl,
-						size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs_cpu(int cpu,
-					       void *base, size_t size,
-					       pebs_ovfl_callback_t ovfl,
-					       size_t th, unsigned int flags);
-
-/*
- * Release BTS or PEBS resources
- * Suspend and resume BTS or PEBS tracing
- *
- * Must be called with irq's enabled.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern void ds_release_bts(struct bts_tracer *tracer);
-extern void ds_suspend_bts(struct bts_tracer *tracer);
-extern void ds_resume_bts(struct bts_tracer *tracer);
-extern void ds_release_pebs(struct pebs_tracer *tracer);
-extern void ds_suspend_pebs(struct pebs_tracer *tracer);
-extern void ds_resume_pebs(struct pebs_tracer *tracer);
-
-/*
- * Release BTS or PEBS resources
- * Suspend and resume BTS or PEBS tracing
- *
- * Cpu tracers must call this on the traced cpu.
- * Task tracers must call ds_release_~_noirq() for themselves.
- *
- * May be called with irq's disabled.
- *
- * Returns 0 if successful;
- * -EPERM if the cpu tracer does not trace the current cpu.
- * -EPERM if the task tracer does not trace itself.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern int ds_release_bts_noirq(struct bts_tracer *tracer);
-extern int ds_suspend_bts_noirq(struct bts_tracer *tracer);
-extern int ds_resume_bts_noirq(struct bts_tracer *tracer);
-extern int ds_release_pebs_noirq(struct pebs_tracer *tracer);
-extern int ds_suspend_pebs_noirq(struct pebs_tracer *tracer);
-extern int ds_resume_pebs_noirq(struct pebs_tracer *tracer);
-
-
-/*
- * The raw DS buffer state as it is used for BTS and PEBS recording.
- *
- * This is the low-level, arch-dependent interface for working
- * directly on the raw trace data.
- */
-struct ds_trace {
-	/* the number of bts/pebs records */
-	size_t n;
-	/* the size of a bts/pebs record in bytes */
-	size_t size;
-	/* pointers into the raw buffer:
-	   - to the first entry */
-	void *begin;
-	/* - one beyond the last entry */
-	void *end;
-	/* - one beyond the newest entry */
-	void *top;
-	/* - the interrupt threshold */
-	void *ith;
-	/* flags given on ds_request() */
-	unsigned int flags;
-};
-
-/*
- * An arch-independent view on branch trace data.
- */
-enum bts_qualifier {
-	bts_invalid,
-#define BTS_INVALID bts_invalid
-
-	bts_branch,
-#define BTS_BRANCH bts_branch
-
-	bts_task_arrives,
-#define BTS_TASK_ARRIVES bts_task_arrives
-
-	bts_task_departs,
-#define BTS_TASK_DEPARTS bts_task_departs
-
-	bts_qual_bit_size = 4,
-	bts_qual_max = (1 << bts_qual_bit_size),
-};
-
-struct bts_struct {
-	__u64 qualifier;
-	union {
-		/* BTS_BRANCH */
-		struct {
-			__u64 from;
-			__u64 to;
-		} lbr;
-		/* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */
-		struct {
-			__u64 clock;
-			pid_t pid;
-		} event;
-	} variant;
-};
-
-
-/*
- * The BTS state.
- *
- * This gives access to the raw DS state and adds functions to provide
- * an arch-independent view of the BTS data.
- */
-struct bts_trace {
-	struct ds_trace ds;
-
-	int (*read)(struct bts_tracer *tracer, const void *at,
-		    struct bts_struct *out);
-	int (*write)(struct bts_tracer *tracer, const struct bts_struct *in);
-};
-
-
-/*
- * The PEBS state.
- *
- * This gives access to the raw DS state and the PEBS-specific counter
- * reset value.
- */
-struct pebs_trace {
-	struct ds_trace ds;
-
-	/* the number of valid counters in the below array */
-	unsigned int counters;
-
-#define MAX_PEBS_COUNTERS 4
-	/* the counter reset value */
-	unsigned long long counter_reset[MAX_PEBS_COUNTERS];
-};
-
-
-/*
- * Read the BTS or PEBS trace.
- *
- * Returns a view on the trace collected for the parameter tracer.
- *
- * The view remains valid as long as the traced task is not running or
- * the tracer is suspended.
- * Writes into the trace buffer are not reflected.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern const struct bts_trace *ds_read_bts(struct bts_tracer *tracer);
-extern const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer);
-
-
-/*
- * Reset the write pointer of the BTS/PEBS buffer.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern int ds_reset_bts(struct bts_tracer *tracer);
-extern int ds_reset_pebs(struct pebs_tracer *tracer);
-
-/*
- * Set the PEBS counter reset value.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_pebs()
- * counter: the index of the counter
- * value: the new counter reset value
- */
-extern int ds_set_pebs_reset(struct pebs_tracer *tracer,
-			     unsigned int counter, u64 value);
-
-/*
- * Initialization
- */
-struct cpuinfo_x86;
-extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
-
-/*
- * Context switch work
- */
-extern void ds_switch_to(struct task_struct *prev, struct task_struct *next);
-
-#else /* CONFIG_X86_DS */
-
-struct cpuinfo_x86;
-static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
-static inline void ds_switch_to(struct task_struct *prev,
-				struct task_struct *next) {}
-
-#endif /* CONFIG_X86_DS */
-#endif /* _ASM_X86_DS_H */

arch/x86/include/asm/hw_breakpoint.h

diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index 2a1bd8f..9422553 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -41,12 +41,16 @@
 /* Total number of available HW breakpoint registers */
 #define HBP_NUM 4
 
+static inline int hw_breakpoint_slots(int type)
+{
+	return HBP_NUM;
+}
+
 struct perf_event;
 struct pmu;
 
-extern int arch_check_va_in_userspace(unsigned long va, u8 hbp_len);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp,
-					 struct task_struct *tsk);
+extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 

arch/x86/include/asm/i8253.h

diff --git a/arch/x86/include/asm/i8253.h b/arch/x86/include/asm/i8253.h
index 1edbf89..fc1f579 100644
--- a/arch/x86/include/asm/i8253.h
+++ b/arch/x86/include/asm/i8253.h
@@ -6,7 +6,7 @@
 #define PIT_CH0			0x40
 #define PIT_CH2			0x42
 
-extern spinlock_t i8253_lock;
+extern raw_spinlock_t i8253_lock;
 
 extern struct clock_event_device *global_clock_event;
 

arch/x86/include/asm/insn.h

diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 96c2e0a..88c765e 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -68,6 +68,8 @@
 	const insn_byte_t *next_byte;
 };
 
+#define MAX_INSN_SIZE	16
+
 #define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
 #define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
 #define X86_MODRM_RM(modrm) ((modrm) & 0x07)

arch/x86/include/asm/io.h

diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index a1dcfa3..30a3e97 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -347,6 +347,7 @@
 extern void __iomem *early_memremap(resource_size_t phys_addr,
 				    unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
+extern void fixup_early_ioremap(void);
 
 #define IO_SPACE_LIMIT 0xffff
 

arch/x86/include/asm/k8.h

diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/k8.h
index f70e600..af00bd1 100644
--- a/arch/x86/include/asm/k8.h
+++ b/arch/x86/include/asm/k8.h
@@ -16,11 +16,16 @@
 extern int k8_scan_nodes(void);
 
 #ifdef CONFIG_K8_NB
+extern int num_k8_northbridges;
+
 static inline struct pci_dev *node_to_k8_nb_misc(int node)
 {
 	return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL;
 }
+
 #else
+#define num_k8_northbridges 0
+
 static inline struct pci_dev *node_to_k8_nb_misc(int node)
 {
 	return NULL;

arch/x86/include/asm/kprobes.h

diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 4ffa345..5478825 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -24,6 +24,7 @@
 #include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
+#include <asm/insn.h>
 
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
 
@@ -36,7 +37,6 @@
 #define RELATIVEJUMP_SIZE 5
 #define RELATIVECALL_OPCODE 0xe8
 #define RELATIVE_ADDR_SIZE 4
-#define MAX_INSN_SIZE 16
 #define MAX_STACK_SIZE 64
 #define MIN_STACK_SIZE(ADDR)					       \
 	(((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \

arch/x86/include/asm/msr-index.h

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4604e6a..bc473ac 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -71,11 +71,14 @@
 #define MSR_IA32_LASTINTTOIP		0x000001de
 
 /* DEBUGCTLMSR bits (others vary by model): */
-#define _DEBUGCTLMSR_LBR	0 /* last branch recording */
-#define _DEBUGCTLMSR_BTF	1 /* single-step on branches */
-
-#define DEBUGCTLMSR_LBR		(1UL << _DEBUGCTLMSR_LBR)
-#define DEBUGCTLMSR_BTF		(1UL << _DEBUGCTLMSR_BTF)
+#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
+#define DEBUGCTLMSR_TR			(1UL <<  6)
+#define DEBUGCTLMSR_BTS			(1UL <<  7)
+#define DEBUGCTLMSR_BTINT		(1UL <<  8)
+#define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
+#define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
+#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
 
 #define MSR_IA32_MC0_CTL		0x00000400
 #define MSR_IA32_MC0_STATUS		0x00000401
@@ -359,6 +362,8 @@
 #define MSR_P4_U2L_ESCR0		0x000003b0
 #define MSR_P4_U2L_ESCR1		0x000003b1
 
+#define MSR_P4_PEBS_MATRIX_VERT		0x000003f2
+
 /* Intel Core-based CPU performance counters */
 #define MSR_CORE_PERF_FIXED_CTR0	0x00000309
 #define MSR_CORE_PERF_FIXED_CTR1	0x0000030a

arch/x86/include/asm/perf_event.h

diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index db6109a..254883d 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -5,7 +5,7 @@
  * Performance event hw details:
  */
 
-#define X86_PMC_MAX_GENERIC					8
+#define X86_PMC_MAX_GENERIC				       32
 #define X86_PMC_MAX_FIXED					3
 
 #define X86_PMC_IDX_GENERIC				        0
@@ -18,39 +18,31 @@
 #define MSR_ARCH_PERFMON_EVENTSEL0			     0x186
 #define MSR_ARCH_PERFMON_EVENTSEL1			     0x187
 
-#define ARCH_PERFMON_EVENTSEL_ENABLE			  (1 << 22)
-#define ARCH_PERFMON_EVENTSEL_ANY			  (1 << 21)
-#define ARCH_PERFMON_EVENTSEL_INT			  (1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS			  (1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR			  (1 << 16)
+#define ARCH_PERFMON_EVENTSEL_EVENT			0x000000FFULL
+#define ARCH_PERFMON_EVENTSEL_UMASK			0x0000FF00ULL
+#define ARCH_PERFMON_EVENTSEL_USR			(1ULL << 16)
+#define ARCH_PERFMON_EVENTSEL_OS			(1ULL << 17)
+#define ARCH_PERFMON_EVENTSEL_EDGE			(1ULL << 18)
+#define ARCH_PERFMON_EVENTSEL_INT			(1ULL << 20)
+#define ARCH_PERFMON_EVENTSEL_ANY			(1ULL << 21)
+#define ARCH_PERFMON_EVENTSEL_ENABLE			(1ULL << 22)
+#define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
+#define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
 
-/*
- * Includes eventsel and unit mask as well:
- */
+#define AMD64_EVENTSEL_EVENT	\
+	(ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
+#define INTEL_ARCH_EVENT_MASK	\
+	(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
 
-
-#define INTEL_ARCH_EVTSEL_MASK		0x000000FFULL
-#define INTEL_ARCH_UNIT_MASK		0x0000FF00ULL
-#define INTEL_ARCH_EDGE_MASK		0x00040000ULL
-#define INTEL_ARCH_INV_MASK		0x00800000ULL
-#define INTEL_ARCH_CNT_MASK		0xFF000000ULL
-#define INTEL_ARCH_EVENT_MASK	(INTEL_ARCH_UNIT_MASK|INTEL_ARCH_EVTSEL_MASK)
-
-/*
- * filter mask to validate fixed counter events.
- * the following filters disqualify for fixed counters:
- *  - inv
- *  - edge
- *  - cnt-mask
- *  The other filters are supported by fixed counters.
- *  The any-thread option is supported starting with v3.
- */
-#define INTEL_ARCH_FIXED_MASK \
-	(INTEL_ARCH_CNT_MASK| \
-	 INTEL_ARCH_INV_MASK| \
-	 INTEL_ARCH_EDGE_MASK|\
-	 INTEL_ARCH_UNIT_MASK|\
-	 INTEL_ARCH_EVENT_MASK)
+#define X86_RAW_EVENT_MASK		\
+	(ARCH_PERFMON_EVENTSEL_EVENT |	\
+	 ARCH_PERFMON_EVENTSEL_UMASK |	\
+	 ARCH_PERFMON_EVENTSEL_EDGE  |	\
+	 ARCH_PERFMON_EVENTSEL_INV   |	\
+	 ARCH_PERFMON_EVENTSEL_CMASK)
+#define AMD64_RAW_EVENT_MASK		\
+	(X86_RAW_EVENT_MASK          |  \
+	 AMD64_EVENTSEL_EVENT)
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		      0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
@@ -67,7 +59,7 @@
 union cpuid10_eax {
 	struct {
 		unsigned int version_id:8;
-		unsigned int num_events:8;
+		unsigned int num_counters:8;
 		unsigned int bit_width:8;
 		unsigned int mask_length:8;
 	} split;
@@ -76,7 +68,7 @@
 
 union cpuid10_edx {
 	struct {
-		unsigned int num_events_fixed:4;
+		unsigned int num_counters_fixed:4;
 		unsigned int reserved:28;
 	} split;
 	unsigned int full;
@@ -136,6 +128,18 @@
 
 #define PERF_EVENT_INDEX_OFFSET			0
 
+/*
+ * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups.
+ * This flag is otherwise unused and ABI specified to be 0, so nobody should
+ * care what we do with it.
+ */
+#define PERF_EFLAGS_EXACT	(1UL << 3)
+
+struct pt_regs;
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs)	perf_misc_flags(regs)
+
 #else
 static inline void init_hw_perf_events(void)		{ }
 static inline void perf_events_lapic_init(void)	{ }

arch/x86/include/asm/perf_event_p4.h

diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
new file mode 100644
index 0000000..b05400a
--- /dev/null
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -0,0 +1,794 @@
+/*
+ * Netburst Perfomance Events (P4, old Xeon)
+ */
+
+#ifndef PERF_EVENT_P4_H
+#define PERF_EVENT_P4_H
+
+#include <linux/cpu.h>
+#include <linux/bitops.h>
+
+/*
+ * NetBurst has perfomance MSRs shared between
+ * threads if HT is turned on, ie for both logical
+ * processors (mem: in turn in Atom with HT support
+ * perf-MSRs are not shared and every thread has its
+ * own perf-MSRs set)
+ */
+#define ARCH_P4_TOTAL_ESCR	(46)
+#define ARCH_P4_RESERVED_ESCR	(2) /* IQ_ESCR(0,1) not always present */
+#define ARCH_P4_MAX_ESCR	(ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR)
+#define ARCH_P4_MAX_CCCR	(18)
+#define ARCH_P4_MAX_COUNTER	(ARCH_P4_MAX_CCCR / 2)
+
+#define P4_ESCR_EVENT_MASK	0x7e000000U
+#define P4_ESCR_EVENT_SHIFT	25
+#define P4_ESCR_EVENTMASK_MASK	0x01fffe00U
+#define P4_ESCR_EVENTMASK_SHIFT	9
+#define P4_ESCR_TAG_MASK	0x000001e0U
+#define P4_ESCR_TAG_SHIFT	5
+#define P4_ESCR_TAG_ENABLE	0x00000010U
+#define P4_ESCR_T0_OS		0x00000008U
+#define P4_ESCR_T0_USR		0x00000004U
+#define P4_ESCR_T1_OS		0x00000002U
+#define P4_ESCR_T1_USR		0x00000001U
+
+#define P4_ESCR_EVENT(v)	((v) << P4_ESCR_EVENT_SHIFT)
+#define P4_ESCR_EMASK(v)	((v) << P4_ESCR_EVENTMASK_SHIFT)
+#define P4_ESCR_TAG(v)		((v) << P4_ESCR_TAG_SHIFT)
+
+/* Non HT mask */
+#define P4_ESCR_MASK			\
+	(P4_ESCR_EVENT_MASK	|	\
+	P4_ESCR_EVENTMASK_MASK	|	\
+	P4_ESCR_TAG_MASK	|	\
+	P4_ESCR_TAG_ENABLE	|	\
+	P4_ESCR_T0_OS		|	\
+	P4_ESCR_T0_USR)
+
+/* HT mask */
+#define P4_ESCR_MASK_HT			\
+	(P4_ESCR_MASK |	P4_ESCR_T1_OS | P4_ESCR_T1_USR)
+
+#define P4_CCCR_OVF			0x80000000U
+#define P4_CCCR_CASCADE			0x40000000U
+#define P4_CCCR_OVF_PMI_T0		0x04000000U
+#define P4_CCCR_OVF_PMI_T1		0x08000000U
+#define P4_CCCR_FORCE_OVF		0x02000000U
+#define P4_CCCR_EDGE			0x01000000U
+#define P4_CCCR_THRESHOLD_MASK		0x00f00000U
+#define P4_CCCR_THRESHOLD_SHIFT		20
+#define P4_CCCR_COMPLEMENT		0x00080000U
+#define P4_CCCR_COMPARE			0x00040000U
+#define P4_CCCR_ESCR_SELECT_MASK	0x0000e000U
+#define P4_CCCR_ESCR_SELECT_SHIFT	13
+#define P4_CCCR_ENABLE			0x00001000U
+#define P4_CCCR_THREAD_SINGLE		0x00010000U
+#define P4_CCCR_THREAD_BOTH		0x00020000U
+#define P4_CCCR_THREAD_ANY		0x00030000U
+#define P4_CCCR_RESERVED		0x00000fffU
+
+#define P4_CCCR_THRESHOLD(v)		((v) << P4_CCCR_THRESHOLD_SHIFT)
+#define P4_CCCR_ESEL(v)			((v) << P4_CCCR_ESCR_SELECT_SHIFT)
+
+/* Custom bits in reerved CCCR area */
+#define P4_CCCR_CACHE_OPS_MASK		0x0000003fU
+
+
+/* Non HT mask */
+#define P4_CCCR_MASK				\
+	(P4_CCCR_OVF			|	\
+	P4_CCCR_CASCADE			|	\
+	P4_CCCR_OVF_PMI_T0		|	\
+	P4_CCCR_FORCE_OVF		|	\
+	P4_CCCR_EDGE			|	\
+	P4_CCCR_THRESHOLD_MASK		|	\
+	P4_CCCR_COMPLEMENT		|	\
+	P4_CCCR_COMPARE			|	\
+	P4_CCCR_ESCR_SELECT_MASK	|	\
+	P4_CCCR_ENABLE)
+
+/* HT mask */
+#define P4_CCCR_MASK_HT	(P4_CCCR_MASK | P4_CCCR_THREAD_ANY)
+
+#define P4_GEN_ESCR_EMASK(class, name, bit)	\
+	class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
+#define P4_ESCR_EMASK_BIT(class, name)		class##__##name
+
+/*
+ * config field is 64bit width and consists of
+ * HT << 63 | ESCR << 32 | CCCR
+ * where HT is HyperThreading bit (since ESCR
+ * has it reserved we may use it for own purpose)
+ *
+ * note that this is NOT the addresses of respective
+ * ESCR and CCCR but rather an only packed value should
+ * be unpacked and written to a proper addresses
+ *
+ * the base idea is to pack as much info as
+ * possible
+ */
+#define p4_config_pack_escr(v)		(((u64)(v)) << 32)
+#define p4_config_pack_cccr(v)		(((u64)(v)) & 0xffffffffULL)
+#define p4_config_unpack_escr(v)	(((u64)(v)) >> 32)
+#define p4_config_unpack_cccr(v)	(((u64)(v)) & 0xffffffffULL)
+
+#define p4_config_unpack_emask(v)			\
+	({						\
+		u32 t = p4_config_unpack_escr((v));	\
+		t = t &  P4_ESCR_EVENTMASK_MASK;	\
+		t = t >> P4_ESCR_EVENTMASK_SHIFT;	\
+		t;					\
+	})
+
+#define p4_config_unpack_event(v)			\
+	({						\
+		u32 t = p4_config_unpack_escr((v));	\
+		t = t &  P4_ESCR_EVENT_MASK;		\
+		t = t >> P4_ESCR_EVENT_SHIFT;		\
+		t;					\
+	})
+
+#define p4_config_unpack_cache_event(v)	(((u64)(v)) & P4_CCCR_CACHE_OPS_MASK)
+
+#define P4_CONFIG_HT_SHIFT		63
+#define P4_CONFIG_HT			(1ULL << P4_CONFIG_HT_SHIFT)
+
+static inline bool p4_is_event_cascaded(u64 config)
+{
+	u32 cccr = p4_config_unpack_cccr(config);
+	return !!(cccr & P4_CCCR_CASCADE);
+}
+
+static inline int p4_ht_config_thread(u64 config)
+{
+	return !!(config & P4_CONFIG_HT);
+}
+
+static inline u64 p4_set_ht_bit(u64 config)
+{
+	return config | P4_CONFIG_HT;
+}
+
+static inline u64 p4_clear_ht_bit(u64 config)
+{
+	return config & ~P4_CONFIG_HT;
+}
+
+static inline int p4_ht_active(void)
+{
+#ifdef CONFIG_SMP
+	return smp_num_siblings > 1;
+#endif
+	return 0;
+}
+
+static inline int p4_ht_thread(int cpu)
+{
+#ifdef CONFIG_SMP
+	if (smp_num_siblings == 2)
+		return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+#endif
+	return 0;
+}
+
+static inline int p4_should_swap_ts(u64 config, int cpu)
+{
+	return p4_ht_config_thread(config) ^ p4_ht_thread(cpu);
+}
+
+static inline u32 p4_default_cccr_conf(int cpu)
+{
+	/*
+	 * Note that P4_CCCR_THREAD_ANY is "required" on
+	 * non-HT machines (on HT machines we count TS events
+	 * regardless the state of second logical processor
+	 */
+	u32 cccr = P4_CCCR_THREAD_ANY;
+
+	if (!p4_ht_thread(cpu))
+		cccr |= P4_CCCR_OVF_PMI_T0;
+	else
+		cccr |= P4_CCCR_OVF_PMI_T1;
+
+	return cccr;
+}
+
+static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr)
+{
+	u32 escr = 0;
+
+	if (!p4_ht_thread(cpu)) {
+		if (!exclude_os)
+			escr |= P4_ESCR_T0_OS;
+		if (!exclude_usr)
+			escr |= P4_ESCR_T0_USR;
+	} else {
+		if (!exclude_os)
+			escr |= P4_ESCR_T1_OS;
+		if (!exclude_usr)
+			escr |= P4_ESCR_T1_USR;
+	}
+
+	return escr;
+}
+
+enum P4_EVENTS {
+	P4_EVENT_TC_DELIVER_MODE,
+	P4_EVENT_BPU_FETCH_REQUEST,
+	P4_EVENT_ITLB_REFERENCE,
+	P4_EVENT_MEMORY_CANCEL,
+	P4_EVENT_MEMORY_COMPLETE,
+	P4_EVENT_LOAD_PORT_REPLAY,
+	P4_EVENT_STORE_PORT_REPLAY,
+	P4_EVENT_MOB_LOAD_REPLAY,
+	P4_EVENT_PAGE_WALK_TYPE,
+	P4_EVENT_BSQ_CACHE_REFERENCE,
+	P4_EVENT_IOQ_ALLOCATION,
+	P4_EVENT_IOQ_ACTIVE_ENTRIES,
+	P4_EVENT_FSB_DATA_ACTIVITY,
+	P4_EVENT_BSQ_ALLOCATION,
+	P4_EVENT_BSQ_ACTIVE_ENTRIES,
+	P4_EVENT_SSE_INPUT_ASSIST,
+	P4_EVENT_PACKED_SP_UOP,
+	P4_EVENT_PACKED_DP_UOP,
+	P4_EVENT_SCALAR_SP_UOP,
+	P4_EVENT_SCALAR_DP_UOP,
+	P4_EVENT_64BIT_MMX_UOP,
+	P4_EVENT_128BIT_MMX_UOP,
+	P4_EVENT_X87_FP_UOP,
+	P4_EVENT_TC_MISC,
+	P4_EVENT_GLOBAL_POWER_EVENTS,
+	P4_EVENT_TC_MS_XFER,
+	P4_EVENT_UOP_QUEUE_WRITES,
+	P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE,
+	P4_EVENT_RETIRED_BRANCH_TYPE,
+	P4_EVENT_RESOURCE_STALL,
+	P4_EVENT_WC_BUFFER,
+	P4_EVENT_B2B_CYCLES,
+	P4_EVENT_BNR,
+	P4_EVENT_SNOOP,
+	P4_EVENT_RESPONSE,
+	P4_EVENT_FRONT_END_EVENT,
+	P4_EVENT_EXECUTION_EVENT,
+	P4_EVENT_REPLAY_EVENT,
+	P4_EVENT_INSTR_RETIRED,
+	P4_EVENT_UOPS_RETIRED,
+	P4_EVENT_UOP_TYPE,
+	P4_EVENT_BRANCH_RETIRED,
+	P4_EVENT_MISPRED_BRANCH_RETIRED,
+	P4_EVENT_X87_ASSIST,
+	P4_EVENT_MACHINE_CLEAR,
+	P4_EVENT_INSTR_COMPLETED,
+};
+
+#define P4_OPCODE(event)		event##_OPCODE
+#define P4_OPCODE_ESEL(opcode)		((opcode & 0x00ff) >> 0)
+#define P4_OPCODE_EVNT(opcode)		((opcode & 0xff00) >> 8)
+#define P4_OPCODE_PACK(event, sel)	(((event) << 8) | sel)
+
+/*
+ * Comments below the event represent ESCR restriction
+ * for this event and counter index per ESCR
+ *
+ * MSR_P4_IQ_ESCR0 and MSR_P4_IQ_ESCR1 are available only on early
+ * processor builds (family 0FH, models 01H-02H). These MSRs
+ * are not available on later versions, so that we don't use
+ * them completely
+ *
+ * Also note that CCCR1 do not have P4_CCCR_ENABLE bit properly
+ * working so that we should not use this CCCR and respective
+ * counter as result
+ */
+enum P4_EVENT_OPCODES {
+	P4_OPCODE(P4_EVENT_TC_DELIVER_MODE)		= P4_OPCODE_PACK(0x01, 0x01),
+	/*
+	 * MSR_P4_TC_ESCR0:	4, 5
+	 * MSR_P4_TC_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST)		= P4_OPCODE_PACK(0x03, 0x00),
+	/*
+	 * MSR_P4_BPU_ESCR0:	0, 1
+	 * MSR_P4_BPU_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_ITLB_REFERENCE)		= P4_OPCODE_PACK(0x18, 0x03),
+	/*
+	 * MSR_P4_ITLB_ESCR0:	0, 1
+	 * MSR_P4_ITLB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_MEMORY_CANCEL)		= P4_OPCODE_PACK(0x02, 0x05),
+	/*
+	 * MSR_P4_DAC_ESCR0:	8, 9
+	 * MSR_P4_DAC_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_MEMORY_COMPLETE)		= P4_OPCODE_PACK(0x08, 0x02),
+	/*
+	 * MSR_P4_SAAT_ESCR0:	8, 9
+	 * MSR_P4_SAAT_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY)		= P4_OPCODE_PACK(0x04, 0x02),
+	/*
+	 * MSR_P4_SAAT_ESCR0:	8, 9
+	 * MSR_P4_SAAT_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY)		= P4_OPCODE_PACK(0x05, 0x02),
+	/*
+	 * MSR_P4_SAAT_ESCR0:	8, 9
+	 * MSR_P4_SAAT_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY)		= P4_OPCODE_PACK(0x03, 0x02),
+	/*
+	 * MSR_P4_MOB_ESCR0:	0, 1
+	 * MSR_P4_MOB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE)		= P4_OPCODE_PACK(0x01, 0x04),
+	/*
+	 * MSR_P4_PMH_ESCR0:	0, 1
+	 * MSR_P4_PMH_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE)		= P4_OPCODE_PACK(0x0c, 0x07),
+	/*
+	 * MSR_P4_BSU_ESCR0:	0, 1
+	 * MSR_P4_BSU_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_IOQ_ALLOCATION)		= P4_OPCODE_PACK(0x03, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES)		= P4_OPCODE_PACK(0x1a, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY)		= P4_OPCODE_PACK(0x17, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_BSQ_ALLOCATION)		= P4_OPCODE_PACK(0x05, 0x07),
+	/*
+	 * MSR_P4_BSU_ESCR0:	0, 1
+	 */
+
+	P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES)		= P4_OPCODE_PACK(0x06, 0x07),
+	/*
+	 * NOTE: no ESCR name in docs, it's guessed
+	 * MSR_P4_BSU_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST)		= P4_OPCODE_PACK(0x34, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_PACKED_SP_UOP)		= P4_OPCODE_PACK(0x08, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_PACKED_DP_UOP)		= P4_OPCODE_PACK(0x0c, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_SCALAR_SP_UOP)		= P4_OPCODE_PACK(0x0a, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_SCALAR_DP_UOP)		= P4_OPCODE_PACK(0x0e, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_64BIT_MMX_UOP)		= P4_OPCODE_PACK(0x02, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_128BIT_MMX_UOP)		= P4_OPCODE_PACK(0x1a, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_X87_FP_UOP)			= P4_OPCODE_PACK(0x04, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_TC_MISC)			= P4_OPCODE_PACK(0x06, 0x01),
+	/*
+	 * MSR_P4_TC_ESCR0:	4, 5
+	 * MSR_P4_TC_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS)		= P4_OPCODE_PACK(0x13, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_TC_MS_XFER)			= P4_OPCODE_PACK(0x05, 0x00),
+	/*
+	 * MSR_P4_MS_ESCR0:	4, 5
+	 * MSR_P4_MS_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES)		= P4_OPCODE_PACK(0x09, 0x00),
+	/*
+	 * MSR_P4_MS_ESCR0:	4, 5
+	 * MSR_P4_MS_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE)	= P4_OPCODE_PACK(0x05, 0x02),
+	/*
+	 * MSR_P4_TBPU_ESCR0:	4, 5
+	 * MSR_P4_TBPU_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE)		= P4_OPCODE_PACK(0x04, 0x02),
+	/*
+	 * MSR_P4_TBPU_ESCR0:	4, 5
+	 * MSR_P4_TBPU_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_RESOURCE_STALL)		= P4_OPCODE_PACK(0x01, 0x01),
+	/*
+	 * MSR_P4_ALF_ESCR0:	12, 13, 16
+	 * MSR_P4_ALF_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_WC_BUFFER)			= P4_OPCODE_PACK(0x05, 0x05),
+	/*
+	 * MSR_P4_DAC_ESCR0:	8, 9
+	 * MSR_P4_DAC_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_B2B_CYCLES)			= P4_OPCODE_PACK(0x16, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_BNR)				= P4_OPCODE_PACK(0x08, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_SNOOP)			= P4_OPCODE_PACK(0x06, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_RESPONSE)			= P4_OPCODE_PACK(0x04, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_FRONT_END_EVENT)		= P4_OPCODE_PACK(0x08, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_EXECUTION_EVENT)		= P4_OPCODE_PACK(0x0c, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_REPLAY_EVENT)		= P4_OPCODE_PACK(0x09, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_INSTR_RETIRED)		= P4_OPCODE_PACK(0x02, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_UOPS_RETIRED)		= P4_OPCODE_PACK(0x01, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_UOP_TYPE)			= P4_OPCODE_PACK(0x02, 0x02),
+	/*
+	 * MSR_P4_RAT_ESCR0:	12, 13, 16
+	 * MSR_P4_RAT_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_BRANCH_RETIRED)		= P4_OPCODE_PACK(0x06, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED)	= P4_OPCODE_PACK(0x03, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_X87_ASSIST)			= P4_OPCODE_PACK(0x03, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_MACHINE_CLEAR)		= P4_OPCODE_PACK(0x02, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_INSTR_COMPLETED)		= P4_OPCODE_PACK(0x07, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+};
+
+/*
+ * a caller should use P4_ESCR_EMASK_NAME helper to
+ * pick the EventMask needed, for example
+ *
+ *	P4_ESCR_EMASK_NAME(P4_EVENT_TC_DELIVER_MODE, DD)
+ */
+enum P4_ESCR_EMASKS {
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DB, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DI, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BD, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BB, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BI, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, ID, 6),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BPU_FETCH_REQUEST, TCMISS, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, MISS, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT_UK, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, 64K_CONF, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, LSC, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, SSC, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STA, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STD, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, DTMISS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, ITMISS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS, 10),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, DEFAULT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_READ, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_UC, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WC, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WT, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WP, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WB, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OWN, 13),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OTHER, 14),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, PREFETCH, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN, 13),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER, 14),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1, 12),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2, 13),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1, 12),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2, 13),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SSE_INPUT_ASSIST, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_SP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_DP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_SP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_DP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_64BIT_MMX_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_128BIT_MMX_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_FP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_MISC, FLUSH, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_MS_XFER, CISC, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CALL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RESOURCE_STALL, SBFULL, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_EVICTS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS2, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS3, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS0, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS1, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS2, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS3, 7),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSTAG, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSNTAG, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSTAG, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGLOADS, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGSTORES, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNP, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNM, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTP, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTM, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSU, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSO, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAO, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAU, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, PREA, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, CLEAR, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, MOCLEAR, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, SMCLEAR, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1),
+};
+
+/* P4 PEBS: stale for a while */
+#define P4_PEBS_METRIC_MASK	0x00001fffU
+#define P4_PEBS_UOB_TAG		0x01000000U
+#define P4_PEBS_ENABLE		0x02000000U
+
+/* Replay metrics for MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT */
+#define P4_PEBS__1stl_cache_load_miss_retired	0x3000001
+#define P4_PEBS__2ndl_cache_load_miss_retired	0x3000002
+#define P4_PEBS__dtlb_load_miss_retired		0x3000004
+#define P4_PEBS__dtlb_store_miss_retired	0x3000004
+#define P4_PEBS__dtlb_all_miss_retired		0x3000004
+#define P4_PEBS__tagged_mispred_branch		0x3018000
+#define P4_PEBS__mob_load_replay_retired	0x3000200
+#define P4_PEBS__split_load_retired		0x3000400
+#define P4_PEBS__split_store_retired		0x3000400
+
+#define P4_VERT__1stl_cache_load_miss_retired	0x0000001
+#define P4_VERT__2ndl_cache_load_miss_retired	0x0000001
+#define P4_VERT__dtlb_load_miss_retired		0x0000001
+#define P4_VERT__dtlb_store_miss_retired	0x0000002
+#define P4_VERT__dtlb_all_miss_retired		0x0000003
+#define P4_VERT__tagged_mispred_branch		0x0000010
+#define P4_VERT__mob_load_replay_retired	0x0000001
+#define P4_VERT__split_load_retired		0x0000001
+#define P4_VERT__split_store_retired		0x0000002
+
+enum P4_CACHE_EVENTS {
+	P4_CACHE__NONE,
+
+	P4_CACHE__1stl_cache_load_miss_retired,
+	P4_CACHE__2ndl_cache_load_miss_retired,
+	P4_CACHE__dtlb_load_miss_retired,
+	P4_CACHE__dtlb_store_miss_retired,
+	P4_CACHE__itlb_reference_hit,
+	P4_CACHE__itlb_reference_miss,
+
+	P4_CACHE__MAX
+};
+
+#endif /* PERF_EVENT_P4_H */

arch/x86/include/asm/processor.h

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index b753ea5..32428b4 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -21,7 +21,6 @@
 #include <asm/msr.h>
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
-#include <asm/ds.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -29,6 +28,7 @@
 #include <linux/threads.h>
 #include <linux/math64.h>
 #include <linux/init.h>
+#include <linux/err.h>
 
 #define HBP_NUM 4
 /*
@@ -473,10 +473,6 @@
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
-/* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
-	unsigned long	debugctlmsr;
-	/* Debug Store context; see asm/ds.h */
-	struct ds_context	*ds_ctx;
 };
 
 static inline unsigned long native_get_debugreg(int regno)
@@ -803,7 +799,7 @@
 
 static inline unsigned long get_debugctlmsr(void)
 {
-    unsigned long debugctlmsr = 0;
+	unsigned long debugctlmsr = 0;
 
 #ifndef CONFIG_X86_DEBUGCTLMSR
 	if (boot_cpu_data.x86 < 6)
@@ -811,21 +807,6 @@
 #endif
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 
-    return debugctlmsr;
-}
-
-static inline unsigned long get_debugctlmsr_on_cpu(int cpu)
-{
-	u64 debugctlmsr = 0;
-	u32 val1, val2;
-
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return 0;
-#endif
-	rdmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, &val1, &val2);
-	debugctlmsr = val1 | ((u64)val2 << 32);
-
 	return debugctlmsr;
 }
 
@@ -838,18 +819,6 @@
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 }
 
-static inline void update_debugctlmsr_on_cpu(int cpu,
-					     unsigned long debugctlmsr)
-{
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return;
-#endif
-	wrmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR,
-		     (u32)((u64)debugctlmsr),
-		     (u32)((u64)debugctlmsr >> 32));
-}
-
 /*
  * from system description table in BIOS. Mostly for MCA use, but
  * others may find it useful:

arch/x86/include/asm/ptrace-abi.h

diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h
index 8672303..52b098a 100644
--- a/arch/x86/include/asm/ptrace-abi.h
+++ b/arch/x86/include/asm/ptrace-abi.h
@@ -82,61 +82,6 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
-
-/* configuration/status structure used in PTRACE_BTS_CONFIG and
-   PTRACE_BTS_STATUS commands.
-*/
-struct ptrace_bts_config {
-	/* requested or actual size of BTS buffer in bytes */
-	__u32 size;
-	/* bitmask of below flags */
-	__u32 flags;
-	/* buffer overflow signal */
-	__u32 signal;
-	/* actual size of bts_struct in bytes */
-	__u32 bts_size;
-};
-#endif /* __ASSEMBLY__ */
-
-#define PTRACE_BTS_O_TRACE	0x1 /* branch trace */
-#define PTRACE_BTS_O_SCHED	0x2 /* scheduling events w/ jiffies */
-#define PTRACE_BTS_O_SIGNAL     0x4 /* send SIG<signal> on buffer overflow
-				       instead of wrapping around */
-#define PTRACE_BTS_O_ALLOC	0x8 /* (re)allocate buffer */
-
-#define PTRACE_BTS_CONFIG	40
-/* Configure branch trace recording.
-   ADDR points to a struct ptrace_bts_config.
-   DATA gives the size of that buffer.
-   A new buffer is allocated, if requested in the flags.
-   An overflow signal may only be requested for new buffers.
-   Returns the number of bytes read.
-*/
-#define PTRACE_BTS_STATUS	41
-/* Return the current configuration in a struct ptrace_bts_config
-   pointed to by ADDR; DATA gives the size of that buffer.
-   Returns the number of bytes written.
-*/
-#define PTRACE_BTS_SIZE		42
-/* Return the number of available BTS records for draining.
-   DATA and ADDR are ignored.
-*/
-#define PTRACE_BTS_GET		43
-/* Get a single BTS record.
-   DATA defines the index into the BTS array, where 0 is the newest
-   entry, and higher indices refer to older entries.
-   ADDR is pointing to struct bts_struct (see asm/ds.h).
-*/
-#define PTRACE_BTS_CLEAR	44
-/* Clear the BTS buffer.
-   DATA and ADDR are ignored.
-*/
-#define PTRACE_BTS_DRAIN	45
-/* Read all available BTS records and clear the buffer.
-   ADDR points to an array of struct bts_struct.
-   DATA gives the size of that buffer.
-   BTS records are read from oldest to newest.
-   Returns number of BTS records drained.
-*/
+#endif
 
 #endif /* _ASM_X86_PTRACE_ABI_H */

arch/x86/include/asm/ptrace.h

diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 69a686a..78cd1ea 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -289,12 +289,6 @@
 extern int do_set_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info, int can_allocate);
 
-#ifdef CONFIG_X86_PTRACE_BTS
-extern void ptrace_bts_untrace(struct task_struct *tsk);
-
-#define arch_ptrace_untrace(tsk)	ptrace_bts_untrace(tsk)
-#endif /* CONFIG_X86_PTRACE_BTS */
-
 #endif /* __KERNEL__ */
 
 #endif /* !__ASSEMBLY__ */

arch/x86/include/asm/thread_info.h

diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e0d2890..d017ed55 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -92,8 +92,7 @@
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
 #define TIF_FREEZE		23	/* is freezing for suspend */
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
+#define TIF_BLOCKSTEP		25	/* set when we want DEBUGCTLMSR_BTF */
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
 #define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
 
@@ -115,8 +114,7 @@
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
 #define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_BLOCKSTEP		(1 << TIF_BLOCKSTEP)
 #define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 
@@ -147,7 +145,7 @@
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
-	(_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC)
+	(_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP)
 
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)

arch/x86/kernel/Makefile

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 4c58352..e77b220 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -47,8 +47,6 @@
 obj-y				+= process.o
 obj-y				+= i387.o xsave.o
 obj-y				+= ptrace.o
-obj-$(CONFIG_X86_DS)		+= ds.o
-obj-$(CONFIG_X86_DS_SELFTEST)		+= ds_selftest.o
 obj-$(CONFIG_X86_32)		+= tls.o
 obj-$(CONFIG_IA32_EMULATION)	+= tls.o
 obj-y				+= step.o

arch/x86/kernel/amd_iommu.c

diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index f854d89b..fa5a1474 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -731,18 +731,22 @@
 
 static u64 *alloc_pte(struct protection_domain *domain,
 		      unsigned long address,
-		      int end_lvl,
+		      unsigned long page_size,
 		      u64 **pte_page,
 		      gfp_t gfp)
 {
+	int level, end_lvl;
 	u64 *pte, *page;
-	int level;
+
+	BUG_ON(!is_power_of_2(page_size));
 
 	while (address > PM_LEVEL_SIZE(domain->mode))
 		increase_address_space(domain, gfp);
 
-	level =  domain->mode - 1;
-	pte   = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
+	level   = domain->mode - 1;
+	pte     = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
+	address = PAGE_SIZE_ALIGN(address, page_size);
+	end_lvl = PAGE_SIZE_LEVEL(page_size);
 
 	while (level > end_lvl) {
 		if (!IOMMU_PTE_PRESENT(*pte)) {
@@ -752,6 +756,10 @@
 			*pte = PM_LEVEL_PDE(level, virt_to_phys(page));
 		}
 
+		/* No level skipping support yet */
+		if (PM_PTE_LEVEL(*pte) != level)
+			return NULL;
+
 		level -= 1;
 
 		pte = IOMMU_PTE_PAGE(*pte);
@@ -769,28 +777,47 @@
  * This function checks if there is a PTE for a given dma address. If
  * there is one, it returns the pointer to it.
  */
-static u64 *fetch_pte(struct protection_domain *domain,
-		      unsigned long address, int map_size)
+static u64 *fetch_pte(struct protection_domain *domain, unsigned long address)
 {
 	int level;
 	u64 *pte;
 
-	level =  domain->mode - 1;
-	pte   = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
+	if (address > PM_LEVEL_SIZE(domain->mode))
+		return NULL;
 
-	while (level > map_size) {
+	level   =  domain->mode - 1;
+	pte     = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
+
+	while (level > 0) {
+
+		/* Not Present */
 		if (!IOMMU_PTE_PRESENT(*pte))
 			return NULL;
 
+		/* Large PTE */
+		if (PM_PTE_LEVEL(*pte) == 0x07) {
+			unsigned long pte_mask, __pte;
+
+			/*
+			 * If we have a series of large PTEs, make
+			 * sure to return a pointer to the first one.
+			 */
+			pte_mask = PTE_PAGE_SIZE(*pte);
+			pte_mask = ~((PAGE_SIZE_PTE_COUNT(pte_mask) << 3) - 1);
+			__pte    = ((unsigned long)pte) & pte_mask;
+
+			return (u64 *)__pte;
+		}
+
+		/* No level skipping support yet */
+		if (PM_PTE_LEVEL(*pte) != level)
+			return NULL;
+
 		level -= 1;
 
+		/* Walk to the next level */
 		pte = IOMMU_PTE_PAGE(*pte);
 		pte = &pte[PM_LEVEL_INDEX(level, address)];
-
-		if ((PM_PTE_LEVEL(*pte) == 0) && level != map_size) {
-			pte = NULL;
-			break;
-		}
 	}
 
 	return pte;
@@ -807,44 +834,84 @@
 			  unsigned long bus_addr,
 			  unsigned long phys_addr,
 			  int prot,
-			  int map_size)
+			  unsigned long page_size)
 {
 	u64 __pte, *pte;
-
-	bus_addr  = PAGE_ALIGN(bus_addr);
-	phys_addr = PAGE_ALIGN(phys_addr);
-
-	BUG_ON(!PM_ALIGNED(map_size, bus_addr));
-	BUG_ON(!PM_ALIGNED(map_size, phys_addr));
+	int i, count;
 
 	if (!(prot & IOMMU_PROT_MASK))
 		return -EINVAL;
 
-	pte = alloc_pte(dom, bus_addr, map_size, NULL, GFP_KERNEL);
+	bus_addr  = PAGE_ALIGN(bus_addr);
+	phys_addr = PAGE_ALIGN(phys_addr);
+	count     = PAGE_SIZE_PTE_COUNT(page_size);
+	pte       = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL);
 
-	if (IOMMU_PTE_PRESENT(*pte))
-		return -EBUSY;
+	for (i = 0; i < count; ++i)
+		if (IOMMU_PTE_PRESENT(pte[i]))
+			return -EBUSY;
 
-	__pte = phys_addr | IOMMU_PTE_P;
+	if (page_size > PAGE_SIZE) {
+		__pte = PAGE_SIZE_PTE(phys_addr, page_size);
+		__pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_P | IOMMU_PTE_FC;
+	} else
+		__pte = phys_addr | IOMMU_PTE_P | IOMMU_PTE_FC;
+
 	if (prot & IOMMU_PROT_IR)
 		__pte |= IOMMU_PTE_IR;
 	if (prot & IOMMU_PROT_IW)
 		__pte |= IOMMU_PTE_IW;
 
-	*pte = __pte;
+	for (i = 0; i < count; ++i)
+		pte[i] = __pte;
 
 	update_domain(dom);
 
 	return 0;
 }
 
-static void iommu_unmap_page(struct protection_domain *dom,
-			     unsigned long bus_addr, int map_size)
+static unsigned long iommu_unmap_page(struct protection_domain *dom,
+				      unsigned long bus_addr,
+				      unsigned long page_size)
 {
-	u64 *pte = fetch_pte(dom, bus_addr, map_size);
+	unsigned long long unmap_size, unmapped;
+	u64 *pte;
 
-	if (pte)
-		*pte = 0;
+	BUG_ON(!is_power_of_2(page_size));
+
+	unmapped = 0;
+
+	while (unmapped < page_size) {
+
+		pte = fetch_pte(dom, bus_addr);
+
+		if (!pte) {
+			/*
+			 * No PTE for this address
+			 * move forward in 4kb steps
+			 */
+			unmap_size = PAGE_SIZE;
+		} else if (PM_PTE_LEVEL(*pte) == 0) {
+			/* 4kb PTE found for this address */
+			unmap_size = PAGE_SIZE;
+			*pte       = 0ULL;
+		} else {
+			int count, i;
+
+			/* Large PTE found which maps this address */
+			unmap_size = PTE_PAGE_SIZE(*pte);
+			count      = PAGE_SIZE_PTE_COUNT(unmap_size);
+			for (i = 0; i < count; i++)
+				pte[i] = 0ULL;
+		}
+
+		bus_addr  = (bus_addr & ~(unmap_size - 1)) + unmap_size;
+		unmapped += unmap_size;
+	}
+
+	BUG_ON(!is_power_of_2(unmapped));
+
+	return unmapped;
 }
 
 /*
@@ -878,7 +945,7 @@
 	for (addr = e->address_start; addr < e->address_end;
 	     addr += PAGE_SIZE) {
 		ret = iommu_map_page(&dma_dom->domain, addr, addr, e->prot,
-				     PM_MAP_4k);
+				     PAGE_SIZE);
 		if (ret)
 			return ret;
 		/*
@@ -1006,7 +1073,7 @@
 		u64 *pte, *pte_page;
 
 		for (i = 0; i < num_ptes; ++i) {
-			pte = alloc_pte(&dma_dom->domain, address, PM_MAP_4k,
+			pte = alloc_pte(&dma_dom->domain, address, PAGE_SIZE,
 					&pte_page, gfp);
 			if (!pte)
 				goto out_free;
@@ -1042,7 +1109,7 @@
 	for (i = dma_dom->aperture[index]->offset;
 	     i < dma_dom->aperture_size;
 	     i += PAGE_SIZE) {
-		u64 *pte = fetch_pte(&dma_dom->domain, i, PM_MAP_4k);
+		u64 *pte = fetch_pte(&dma_dom->domain, i);
 		if (!pte || !IOMMU_PTE_PRESENT(*pte))
 			continue;
 
@@ -1712,7 +1779,7 @@
 
 	pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
 	if (!pte) {
-		pte = alloc_pte(&dom->domain, address, PM_MAP_4k, &pte_page,
+		pte = alloc_pte(&dom->domain, address, PAGE_SIZE, &pte_page,
 				GFP_ATOMIC);
 		aperture->pte_pages[APERTURE_PAGE_INDEX(address)] = pte_page;
 	} else
@@ -2439,12 +2506,11 @@
 	return ret;
 }
 
-static int amd_iommu_map_range(struct iommu_domain *dom,
-			       unsigned long iova, phys_addr_t paddr,
-			       size_t size, int iommu_prot)
+static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
+			 phys_addr_t paddr, int gfp_order, int iommu_prot)
 {
+	unsigned long page_size = 0x1000UL << gfp_order;
 	struct protection_domain *domain = dom->priv;
-	unsigned long i,  npages = iommu_num_pages(paddr, size, PAGE_SIZE);
 	int prot = 0;
 	int ret;
 
@@ -2453,61 +2519,50 @@
 	if (iommu_prot & IOMMU_WRITE)
 		prot |= IOMMU_PROT_IW;
 
-	iova  &= PAGE_MASK;
-	paddr &= PAGE_MASK;
-
 	mutex_lock(&domain->api_lock);
-
-	for (i = 0; i < npages; ++i) {
-		ret = iommu_map_page(domain, iova, paddr, prot, PM_MAP_4k);
-		if (ret)
-			return ret;
-
-		iova  += PAGE_SIZE;
-		paddr += PAGE_SIZE;
-	}
-
+	ret = iommu_map_page(domain, iova, paddr, prot, page_size);
 	mutex_unlock(&domain->api_lock);
 
-	return 0;
+	return ret;
 }
 
-static void amd_iommu_unmap_range(struct iommu_domain *dom,
-				  unsigned long iova, size_t size)
+static int amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
+			   int gfp_order)
 {
-
 	struct protection_domain *domain = dom->priv;
-	unsigned long i,  npages = iommu_num_pages(iova, size, PAGE_SIZE);
+	unsigned long page_size, unmap_size;
 
-	iova  &= PAGE_MASK;
+	page_size  = 0x1000UL << gfp_order;
 
 	mutex_lock(&domain->api_lock);
-
-	for (i = 0; i < npages; ++i) {
-		iommu_unmap_page(domain, iova, PM_MAP_4k);
-		iova  += PAGE_SIZE;
-	}
+	unmap_size = iommu_unmap_page(domain, iova, page_size);
+	mutex_unlock(&domain->api_lock);
 
 	iommu_flush_tlb_pde(domain);
 
-	mutex_unlock(&domain->api_lock);
+	return get_order(unmap_size);
 }
 
 static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
 					  unsigned long iova)
 {
 	struct protection_domain *domain = dom->priv;
-	unsigned long offset = iova & ~PAGE_MASK;
+	unsigned long offset_mask;
 	phys_addr_t paddr;
-	u64 *pte;
+	u64 *pte, __pte;
 
-	pte = fetch_pte(domain, iova, PM_MAP_4k);
+	pte = fetch_pte(domain, iova);
 
 	if (!pte || !IOMMU_PTE_PRESENT(*pte))
 		return 0;
 
-	paddr  = *pte & IOMMU_PAGE_MASK;
-	paddr |= offset;
+	if (PM_PTE_LEVEL(*pte) == 0)
+		offset_mask = PAGE_SIZE - 1;
+	else
+		offset_mask = PTE_PAGE_SIZE(*pte) - 1;
+
+	__pte = *pte & PM_ADDR_MASK;
+	paddr = (__pte & ~offset_mask) | (iova & offset_mask);
 
 	return paddr;
 }
@@ -2523,8 +2578,8 @@
 	.domain_destroy = amd_iommu_domain_destroy,
 	.attach_dev = amd_iommu_attach_device,
 	.detach_dev = amd_iommu_detach_device,
-	.map = amd_iommu_map_range,
-	.unmap = amd_iommu_unmap_range,
+	.map = amd_iommu_map,
+	.unmap = amd_iommu_unmap,
 	.iova_to_phys = amd_iommu_iova_to_phys,
 	.domain_has_cap = amd_iommu_domain_has_cap,
 };

arch/x86/kernel/amd_iommu_init.c

diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 6360abf..3bacb4d 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -120,6 +120,7 @@
 bool amd_iommu_dump;
 
 static int __initdata amd_iommu_detected;
+static bool __initdata amd_iommu_disabled;
 
 u16 amd_iommu_last_bdf;			/* largest PCI device id we have
 					   to handle */
@@ -1372,6 +1373,9 @@
 	if (no_iommu || (iommu_detected && !gart_iommu_aperture))
 		return;
 
+	if (amd_iommu_disabled)
+		return;
+
 	if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) {
 		iommu_detected = 1;
 		amd_iommu_detected = 1;
@@ -1401,6 +1405,8 @@
 	for (; *str; ++str) {
 		if (strncmp(str, "fullflush", 9) == 0)
 			amd_iommu_unmap_flush = true;
+		if (strncmp(str, "off", 3) == 0)
+			amd_iommu_disabled = true;
 	}
 
 	return 1;

arch/x86/kernel/apic/io_apic.c

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 127b871..eb2789c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2545,6 +2545,9 @@
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg = desc->chip_data;
 
+	if (!cfg)
+		return;
+
 	__irq_complete_move(&desc, cfg->vector);
 }
 #else

arch/x86/kernel/apm_32.c

diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 031aa88..c4f9182 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1224,7 +1224,7 @@
 #ifdef INIT_TIMER_AFTER_SUSPEND
 	unsigned long flags;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 	/* set the clock to HZ */
 	outb_pit(0x34, PIT_MODE);		/* binary, mode 2, LSB/MSB, ch 0 */
 	udelay(10);
@@ -1232,7 +1232,7 @@
 	udelay(10);
 	outb_pit(LATCH >> 8, PIT_CH0);	/* MSB */
 	udelay(10);
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 #endif
 }
 

arch/x86/kernel/cpu/cpufreq/powernow-k8.c

diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index d360b56..b6215b9 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -929,7 +929,8 @@
 		powernow_table[i].index = index;
 
 		/* Frequency may be rounded for these */
-		if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) {
+		if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
+				 || boot_cpu_data.x86 == 0x11) {
 			powernow_table[i].frequency =
 				freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
 		} else

arch/x86/kernel/cpu/intel.c

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 1366c7c..f5e5390 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -12,7 +12,6 @@
 #include <asm/processor.h>
 #include <asm/pgtable.h>
 #include <asm/msr.h>
-#include <asm/ds.h>
 #include <asm/bugs.h>
 #include <asm/cpu.h>
 
@@ -388,7 +387,6 @@
 			set_cpu_cap(c, X86_FEATURE_BTS);
 		if (!(l1 & (1<<12)))
 			set_cpu_cap(c, X86_FEATURE_PEBS);
-		ds_init_intel(c);
 	}
 
 	if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)

arch/x86/kernel/cpu/intel_cacheinfo.c

diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index b3eeb66..95962a9 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -340,6 +340,10 @@
 	     (boot_cpu_data.x86_mask  < 0x1)))
 		return;
 
+	/* not in virtualized environments */
+	if (num_k8_northbridges == 0)
+		return;
+
 	this_leaf->can_disable = true;
 	this_leaf->l3_indices  = amd_calc_l3_indices();
 }

arch/x86/kernel/cpu/perf_event.c

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index db5bdc8..fd4db0d 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -31,46 +31,51 @@
 #include <asm/nmi.h>
 #include <asm/compat.h>
 
-static u64 perf_event_mask __read_mostly;
-
-/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS	4
-
-/* The size of a BTS record in bytes: */
-#define BTS_RECORD_SIZE		24
-
-/* The size of a per-cpu BTS buffer in bytes: */
-#define BTS_BUFFER_SIZE		(BTS_RECORD_SIZE * 2048)
-
-/* The BTS overflow threshold in bytes from the end of the buffer: */
-#define BTS_OVFL_TH		(BTS_RECORD_SIZE * 128)
-
+#if 0
+#undef wrmsrl
+#define wrmsrl(msr, val) 					\
+do {								\
+	trace_printk("wrmsrl(%lx, %lx)\n", (unsigned long)(msr),\
+			(unsigned long)(val));			\
+	native_write_msr((msr), (u32)((u64)(val)), 		\
+			(u32)((u64)(val) >> 32));		\
+} while (0)
+#endif
 
 /*
- * Bits in the debugctlmsr controlling branch tracing.
+ * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
  */
-#define X86_DEBUGCTL_TR			(1 << 6)
-#define X86_DEBUGCTL_BTS		(1 << 7)
-#define X86_DEBUGCTL_BTINT		(1 << 8)
-#define X86_DEBUGCTL_BTS_OFF_OS		(1 << 9)
-#define X86_DEBUGCTL_BTS_OFF_USR	(1 << 10)
+static unsigned long
+copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long offset, addr = (unsigned long)from;
+	int type = in_nmi() ? KM_NMI : KM_IRQ0;
+	unsigned long size, len = 0;
+	struct page *page;
+	void *map;
+	int ret;
 
-/*
- * A debug store configuration.
- *
- * We only support architectures that use 64bit fields.
- */
-struct debug_store {
-	u64	bts_buffer_base;
-	u64	bts_index;
-	u64	bts_absolute_maximum;
-	u64	bts_interrupt_threshold;
-	u64	pebs_buffer_base;
-	u64	pebs_index;
-	u64	pebs_absolute_maximum;
-	u64	pebs_interrupt_threshold;
-	u64	pebs_event_reset[MAX_PEBS_EVENTS];
-};
+	do {
+		ret = __get_user_pages_fast(addr, 1, 0, &page);
+		if (!ret)
+			break;
+
+		offset = addr & (PAGE_SIZE - 1);
+		size = min(PAGE_SIZE - offset, n - len);
+
+		map = kmap_atomic(page, type);
+		memcpy(to, map+offset, size);
+		kunmap_atomic(map, type);
+		put_page(page);
+
+		len  += size;
+		to   += size;
+		addr += size;
+
+	} while (len < n);
+
+	return len;
+}
 
 struct event_constraint {
 	union {
@@ -89,18 +94,41 @@
 	struct event_constraint event_constraints[X86_PMC_IDX_MAX];
 };
 
+#define MAX_LBR_ENTRIES		16
+
 struct cpu_hw_events {
+	/*
+	 * Generic x86 PMC bits
+	 */
 	struct perf_event	*events[X86_PMC_IDX_MAX]; /* in counter order */
 	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
-	unsigned long		interrupts;
 	int			enabled;
-	struct debug_store	*ds;
 
 	int			n_events;
 	int			n_added;
 	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 */
+
+	unsigned int		group_flag;
+
+	/*
+	 * Intel DebugStore bits
+	 */
+	struct debug_store	*ds;
+	u64			pebs_enabled;
+
+	/*
+	 * Intel LBR bits
+	 */
+	int				lbr_users;
+	void				*lbr_context;
+	struct perf_branch_stack	lbr_stack;
+	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
+
+	/*
+	 * AMD specific bits
+	 */
 	struct amd_nb		*amd_nb;
 };
 
@@ -114,44 +142,75 @@
 #define EVENT_CONSTRAINT(c, n, m)	\
 	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n))
 
+/*
+ * Constraint on the Event code.
+ */
 #define INTEL_EVENT_CONSTRAINT(c, n)	\
-	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK)
+	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
 
+/*
+ * Constraint on the Event code + UMask + fixed-mask
+ *
+ * filter mask to validate fixed counter events.
+ * the following filters disqualify for fixed counters:
+ *  - inv
+ *  - edge
+ *  - cnt-mask
+ *  The other filters are supported by fixed counters.
+ *  The any-thread option is supported starting with v3.
+ */
 #define FIXED_EVENT_CONSTRAINT(c, n)	\
-	EVENT_CONSTRAINT(c, (1ULL << (32+n)), INTEL_ARCH_FIXED_MASK)
+	EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK)
+
+/*
+ * Constraint on the Event code + UMask
+ */
+#define PEBS_EVENT_CONSTRAINT(c, n)	\
+	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
 #define EVENT_CONSTRAINT_END		\
 	EVENT_CONSTRAINT(0, 0, 0)
 
 #define for_each_event_constraint(e, c)	\
-	for ((e) = (c); (e)->cmask; (e)++)
+	for ((e) = (c); (e)->weight; (e)++)
+
+union perf_capabilities {
+	struct {
+		u64	lbr_format    : 6;
+		u64	pebs_trap     : 1;
+		u64	pebs_arch_reg : 1;
+		u64	pebs_format   : 4;
+		u64	smm_freeze    : 1;
+	};
+	u64	capabilities;
+};
 
 /*
  * struct x86_pmu - generic x86 pmu
  */
 struct x86_pmu {
+	/*
+	 * Generic x86 PMC bits
+	 */
 	const char	*name;
 	int		version;
 	int		(*handle_irq)(struct pt_regs *);
 	void		(*disable_all)(void);
-	void		(*enable_all)(void);
+	void		(*enable_all)(int added);
 	void		(*enable)(struct perf_event *);
 	void		(*disable)(struct perf_event *);
+	int		(*hw_config)(struct perf_event *event);
+	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
 	unsigned	perfctr;
 	u64		(*event_map)(int);
-	u64		(*raw_event)(u64);
 	int		max_events;
-	int		num_events;
-	int		num_events_fixed;
-	int		event_bits;
-	u64		event_mask;
+	int		num_counters;
+	int		num_counters_fixed;
+	int		cntval_bits;
+	u64		cntval_mask;
 	int		apic;
 	u64		max_period;
-	u64		intel_ctrl;
-	void		(*enable_bts)(u64 config);
-	void		(*disable_bts)(void);
-
 	struct event_constraint *
 			(*get_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
@@ -159,11 +218,32 @@
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
+	void		(*quirks)(void);
 
 	int		(*cpu_prepare)(int cpu);
 	void		(*cpu_starting)(int cpu);
 	void		(*cpu_dying)(int cpu);
 	void		(*cpu_dead)(int cpu);
+
+	/*
+	 * Intel Arch Perfmon v2+
+	 */
+	u64			intel_ctrl;
+	union perf_capabilities intel_cap;
+
+	/*
+	 * Intel DebugStore bits
+	 */
+	int		bts, pebs;
+	int		pebs_record_size;
+	void		(*drain_pebs)(struct pt_regs *regs);
+	struct event_constraint *pebs_constraints;
+
+	/*
+	 * Intel LBR
+	 */
+	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
+	int		lbr_nr;			   /* hardware stack size */
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
@@ -198,7 +278,7 @@
 x86_perf_event_update(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	int shift = 64 - x86_pmu.event_bits;
+	int shift = 64 - x86_pmu.cntval_bits;
 	u64 prev_raw_count, new_raw_count;
 	int idx = hwc->idx;
 	s64 delta;
@@ -241,33 +321,32 @@
 static atomic_t active_events;
 static DEFINE_MUTEX(pmc_reserve_mutex);
 
+#ifdef CONFIG_X86_LOCAL_APIC
+
 static bool reserve_pmc_hardware(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
 	int i;
 
 	if (nmi_watchdog == NMI_LOCAL_APIC)
 		disable_lapic_nmi_watchdog();
 
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
 			goto perfctr_fail;
 	}
 
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		if (!reserve_evntsel_nmi(x86_pmu.eventsel + i))
 			goto eventsel_fail;
 	}
-#endif
 
 	return true;
 
-#ifdef CONFIG_X86_LOCAL_APIC
 eventsel_fail:
 	for (i--; i >= 0; i--)
 		release_evntsel_nmi(x86_pmu.eventsel + i);
 
-	i = x86_pmu.num_events;
+	i = x86_pmu.num_counters;
 
 perfctr_fail:
 	for (i--; i >= 0; i--)
@@ -277,128 +356,36 @@
 		enable_lapic_nmi_watchdog();
 
 	return false;
-#endif
 }
 
 static void release_pmc_hardware(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
 	int i;
 
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		release_perfctr_nmi(x86_pmu.perfctr + i);
 		release_evntsel_nmi(x86_pmu.eventsel + i);
 	}
 
 	if (nmi_watchdog == NMI_LOCAL_APIC)
 		enable_lapic_nmi_watchdog();
+}
+
+#else
+
+static bool reserve_pmc_hardware(void) { return true; }
+static void release_pmc_hardware(void) {}
+
 #endif
-}
 
-static inline bool bts_available(void)
-{
-	return x86_pmu.enable_bts != NULL;
-}
-
-static void init_debug_store_on_cpu(int cpu)
-{
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
-	if (!ds)
-		return;
-
-	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA,
-		     (u32)((u64)(unsigned long)ds),
-		     (u32)((u64)(unsigned long)ds >> 32));
-}
-
-static void fini_debug_store_on_cpu(int cpu)
-{
-	if (!per_cpu(cpu_hw_events, cpu).ds)
-		return;
-
-	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
-}
-
-static void release_bts_hardware(void)
-{
-	int cpu;
-
-	if (!bts_available())
-		return;
-
-	get_online_cpus();
-
-	for_each_online_cpu(cpu)
-		fini_debug_store_on_cpu(cpu);
-
-	for_each_possible_cpu(cpu) {
-		struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
-		if (!ds)
-			continue;
-
-		per_cpu(cpu_hw_events, cpu).ds = NULL;
-
-		kfree((void *)(unsigned long)ds->bts_buffer_base);
-		kfree(ds);
-	}
-
-	put_online_cpus();
-}
-
-static int reserve_bts_hardware(void)
-{
-	int cpu, err = 0;
-
-	if (!bts_available())
-		return 0;
-
-	get_online_cpus();
-
-	for_each_possible_cpu(cpu) {
-		struct debug_store *ds;
-		void *buffer;
-
-		err = -ENOMEM;
-		buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
-		if (unlikely(!buffer))
-			break;
-
-		ds = kzalloc(sizeof(*ds), GFP_KERNEL);
-		if (unlikely(!ds)) {
-			kfree(buffer);
-			break;
-		}
-
-		ds->bts_buffer_base = (u64)(unsigned long)buffer;
-		ds->bts_index = ds->bts_buffer_base;
-		ds->bts_absolute_maximum =
-			ds->bts_buffer_base + BTS_BUFFER_SIZE;
-		ds->bts_interrupt_threshold =
-			ds->bts_absolute_maximum - BTS_OVFL_TH;
-
-		per_cpu(cpu_hw_events, cpu).ds = ds;
-		err = 0;
-	}
-
-	if (err)
-		release_bts_hardware();
-	else {
-		for_each_online_cpu(cpu)
-			init_debug_store_on_cpu(cpu);
-	}
-
-	put_online_cpus();
-
-	return err;
-}
+static int reserve_ds_buffers(void);
+static void release_ds_buffers(void);
 
 static void hw_perf_event_destroy(struct perf_event *event)
 {
 	if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) {
 		release_pmc_hardware();
-		release_bts_hardware();
+		release_ds_buffers();
 		mutex_unlock(&pmc_reserve_mutex);
 	}
 }
@@ -441,54 +428,11 @@
 	return 0;
 }
 
-/*
- * Setup the hardware configuration for a given attr_type
- */
-static int __hw_perf_event_init(struct perf_event *event)
+static int x86_setup_perfctr(struct perf_event *event)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct hw_perf_event *hwc = &event->hw;
 	u64 config;
-	int err;
-
-	if (!x86_pmu_initialized())
-		return -ENODEV;
-
-	err = 0;
-	if (!atomic_inc_not_zero(&active_events)) {
-		mutex_lock(&pmc_reserve_mutex);
-		if (atomic_read(&active_events) == 0) {
-			if (!reserve_pmc_hardware())
-				err = -EBUSY;
-			else
-				err = reserve_bts_hardware();
-		}
-		if (!err)
-			atomic_inc(&active_events);
-		mutex_unlock(&pmc_reserve_mutex);
-	}
-	if (err)
-		return err;
-
-	event->destroy = hw_perf_event_destroy;
-
-	/*
-	 * Generate PMC IRQs:
-	 * (keep 'enabled' bit clear for now)
-	 */
-	hwc->config = ARCH_PERFMON_EVENTSEL_INT;
-
-	hwc->idx = -1;
-	hwc->last_cpu = -1;
-	hwc->last_tag = ~0ULL;
-
-	/*
-	 * Count user and OS events unless requested not to.
-	 */
-	if (!attr->exclude_user)
-		hwc->config |= ARCH_PERFMON_EVENTSEL_USR;
-	if (!attr->exclude_kernel)
-		hwc->config |= ARCH_PERFMON_EVENTSEL_OS;
 
 	if (!hwc->sample_period) {
 		hwc->sample_period = x86_pmu.max_period;
@@ -505,16 +449,8 @@
 			return -EOPNOTSUPP;
 	}
 
-	/*
-	 * Raw hw_event type provide the config in the hw_event structure
-	 */
-	if (attr->type == PERF_TYPE_RAW) {
-		hwc->config |= x86_pmu.raw_event(attr->config);
-		if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) &&
-		    perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
+	if (attr->type == PERF_TYPE_RAW)
 		return 0;
-	}
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
 		return set_ext_hw_attr(hwc, attr);
@@ -539,11 +475,11 @@
 	if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
 	    (hwc->sample_period == 1)) {
 		/* BTS is not supported by this architecture. */
-		if (!bts_available())
+		if (!x86_pmu.bts)
 			return -EOPNOTSUPP;
 
 		/* BTS is currently only allowed for user-mode. */
-		if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+		if (!attr->exclude_kernel)
 			return -EOPNOTSUPP;
 	}
 
@@ -552,12 +488,87 @@
 	return 0;
 }
 
+static int x86_pmu_hw_config(struct perf_event *event)
+{
+	if (event->attr.precise_ip) {
+		int precise = 0;
+
+		/* Support for constant skid */
+		if (x86_pmu.pebs)
+			precise++;
+
+		/* Support for IP fixup */
+		if (x86_pmu.lbr_nr)
+			precise++;
+
+		if (event->attr.precise_ip > precise)
+			return -EOPNOTSUPP;
+	}
+
+	/*
+	 * Generate PMC IRQs:
+	 * (keep 'enabled' bit clear for now)
+	 */
+	event->hw.config = ARCH_PERFMON_EVENTSEL_INT;
+
+	/*
+	 * Count user and OS events unless requested not to
+	 */
+	if (!event->attr.exclude_user)
+		event->hw.config |= ARCH_PERFMON_EVENTSEL_USR;
+	if (!event->attr.exclude_kernel)
+		event->hw.config |= ARCH_PERFMON_EVENTSEL_OS;
+
+	if (event->attr.type == PERF_TYPE_RAW)
+		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
+
+	return x86_setup_perfctr(event);
+}
+
+/*
+ * Setup the hardware configuration for a given attr_type
+ */
+static int __hw_perf_event_init(struct perf_event *event)
+{
+	int err;
+
+	if (!x86_pmu_initialized())
+		return -ENODEV;
+
+	err = 0;
+	if (!atomic_inc_not_zero(&active_events)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&active_events) == 0) {
+			if (!reserve_pmc_hardware())
+				err = -EBUSY;
+			else {
+				err = reserve_ds_buffers();
+				if (err)
+					release_pmc_hardware();
+			}
+		}
+		if (!err)
+			atomic_inc(&active_events);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+	if (err)
+		return err;
+
+	event->destroy = hw_perf_event_destroy;
+
+	event->hw.idx = -1;
+	event->hw.last_cpu = -1;
+	event->hw.last_tag = ~0ULL;
+
+	return x86_pmu.hw_config(event);
+}
+
 static void x86_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		u64 val;
 
 		if (!test_bit(idx, cpuc->active_mask))
@@ -587,12 +598,12 @@
 	x86_pmu.disable_all();
 }
 
-static void x86_pmu_enable_all(void)
+static void x86_pmu_enable_all(int added)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		struct perf_event *event = cpuc->events[idx];
 		u64 val;
 
@@ -667,14 +678,14 @@
 	 * assign events to counters starting with most
 	 * constrained events.
 	 */
-	wmax = x86_pmu.num_events;
+	wmax = x86_pmu.num_counters;
 
 	/*
 	 * when fixed event counters are present,
 	 * wmax is incremented by 1 to account
 	 * for one more choice
 	 */
-	if (x86_pmu.num_events_fixed)
+	if (x86_pmu.num_counters_fixed)
 		wmax++;
 
 	for (w = 1, num = n; num && w <= wmax; w++) {
@@ -724,7 +735,7 @@
 	struct perf_event *event;
 	int n, max_count;
 
-	max_count = x86_pmu.num_events + x86_pmu.num_events_fixed;
+	max_count = x86_pmu.num_counters + x86_pmu.num_counters_fixed;
 
 	/* current number of events already accepted */
 	n = cpuc->n_events;
@@ -795,7 +806,7 @@
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
-	int i;
+	int i, added = cpuc->n_added;
 
 	if (!x86_pmu_initialized())
 		return;
@@ -847,19 +858,20 @@
 	cpuc->enabled = 1;
 	barrier();
 
-	x86_pmu.enable_all();
+	x86_pmu.enable_all(added);
 }
 
-static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc)
+static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
+					  u64 enable_mask)
 {
-	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
-			      hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE);
+	wrmsrl(hwc->config_base + hwc->idx, hwc->config | enable_mask);
 }
 
 static inline void x86_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	(void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config);
+
+	wrmsrl(hwc->config_base + hwc->idx, hwc->config);
 }
 
 static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -874,7 +886,7 @@
 	struct hw_perf_event *hwc = &event->hw;
 	s64 left = atomic64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
-	int err, ret = 0, idx = hwc->idx;
+	int ret = 0, idx = hwc->idx;
 
 	if (idx == X86_PMC_IDX_FIXED_BTS)
 		return 0;
@@ -912,8 +924,8 @@
 	 */
 	atomic64_set(&hwc->prev_count, (u64)-left);
 
-	err = checking_wrmsrl(hwc->event_base + idx,
-			     (u64)(-left) & x86_pmu.event_mask);
+	wrmsrl(hwc->event_base + idx,
+			(u64)(-left) & x86_pmu.cntval_mask);
 
 	perf_event_update_userpage(event);
 
@@ -924,7 +936,8 @@
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	if (cpuc->enabled)
-		__x86_pmu_enable_event(&event->hw);
+		__x86_pmu_enable_event(&event->hw,
+				       ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
 /*
@@ -950,7 +963,15 @@
 	if (n < 0)
 		return n;
 
-	ret = x86_schedule_events(cpuc, n, assign);
+	/*
+	 * If group events scheduling transaction was started,
+	 * skip the schedulability test here, it will be peformed
+	 * at commit time(->commit_txn) as a whole
+	 */
+	if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+		goto out;
+
+	ret = x86_pmu.schedule_events(cpuc, n, assign);
 	if (ret)
 		return ret;
 	/*
@@ -959,6 +980,7 @@
 	 */
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
+out:
 	cpuc->n_events = n;
 	cpuc->n_added += n - n0;
 
@@ -991,11 +1013,12 @@
 void perf_event_print_debug(void)
 {
 	u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
+	u64 pebs;
 	struct cpu_hw_events *cpuc;
 	unsigned long flags;
 	int cpu, idx;
 
-	if (!x86_pmu.num_events)
+	if (!x86_pmu.num_counters)
 		return;
 
 	local_irq_save(flags);
@@ -1008,16 +1031,18 @@
 		rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
 		rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow);
 		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed);
+		rdmsrl(MSR_IA32_PEBS_ENABLE, pebs);
 
 		pr_info("\n");
 		pr_info("CPU#%d: ctrl:       %016llx\n", cpu, ctrl);
 		pr_info("CPU#%d: status:     %016llx\n", cpu, status);
 		pr_info("CPU#%d: overflow:   %016llx\n", cpu, overflow);
 		pr_info("CPU#%d: fixed:      %016llx\n", cpu, fixed);
+		pr_info("CPU#%d: pebs:       %016llx\n", cpu, pebs);
 	}
-	pr_info("CPU#%d: active:       %016llx\n", cpu, *(u64 *)cpuc->active_mask);
+	pr_info("CPU#%d: active:     %016llx\n", cpu, *(u64 *)cpuc->active_mask);
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
 		rdmsrl(x86_pmu.perfctr  + idx, pmc_count);
 
@@ -1030,7 +1055,7 @@
 		pr_info("CPU#%d:   gen-PMC%d left:  %016llx\n",
 			cpu, idx, prev_left);
 	}
-	for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
 		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
 
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
@@ -1095,7 +1120,7 @@
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -1103,7 +1128,7 @@
 		hwc = &event->hw;
 
 		val = x86_perf_event_update(event);
-		if (val & (1ULL << (x86_pmu.event_bits - 1)))
+		if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
 			continue;
 
 		/*
@@ -1146,7 +1171,6 @@
 
 void perf_events_lapic_init(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
 	if (!x86_pmu.apic || !x86_pmu_initialized())
 		return;
 
@@ -1154,7 +1178,6 @@
 	 * Always use NMI for PMU
 	 */
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
-#endif
 }
 
 static int __kprobes
@@ -1178,9 +1201,7 @@
 
 	regs = args->regs;
 
-#ifdef CONFIG_X86_LOCAL_APIC
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
-#endif
 	/*
 	 * Can't rely on the handled return value to say it was our NMI, two
 	 * events could trigger 'simultaneously' raising two back-to-back NMIs.
@@ -1217,118 +1238,11 @@
 	return &unconstrained;
 }
 
-static int x86_event_sched_in(struct perf_event *event,
-			  struct perf_cpu_context *cpuctx)
-{
-	int ret = 0;
-
-	event->state = PERF_EVENT_STATE_ACTIVE;
-	event->oncpu = smp_processor_id();
-	event->tstamp_running += event->ctx->time - event->tstamp_stopped;
-
-	if (!is_x86_event(event))
-		ret = event->pmu->enable(event);
-
-	if (!ret && !is_software_event(event))
-		cpuctx->active_oncpu++;
-
-	if (!ret && event->attr.exclusive)
-		cpuctx->exclusive = 1;
-
-	return ret;
-}
-
-static void x86_event_sched_out(struct perf_event *event,
-			    struct perf_cpu_context *cpuctx)
-{
-	event->state = PERF_EVENT_STATE_INACTIVE;
-	event->oncpu = -1;
-
-	if (!is_x86_event(event))
-		event->pmu->disable(event);
-
-	event->tstamp_running -= event->ctx->time - event->tstamp_stopped;
-
-	if (!is_software_event(event))
-		cpuctx->active_oncpu--;
-
-	if (event->attr.exclusive || !cpuctx->active_oncpu)
-		cpuctx->exclusive = 0;
-}
-
-/*
- * Called to enable a whole group of events.
- * Returns 1 if the group was enabled, or -EAGAIN if it could not be.
- * Assumes the caller has disabled interrupts and has
- * frozen the PMU with hw_perf_save_disable.
- *
- * called with PMU disabled. If successful and return value 1,
- * then guaranteed to call perf_enable() and hw_perf_enable()
- */
-int hw_perf_group_sched_in(struct perf_event *leader,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct perf_event *sub;
-	int assign[X86_PMC_IDX_MAX];
-	int n0, n1, ret;
-
-	/* n0 = total number of events */
-	n0 = collect_events(cpuc, leader, true);
-	if (n0 < 0)
-		return n0;
-
-	ret = x86_schedule_events(cpuc, n0, assign);
-	if (ret)
-		return ret;
-
-	ret = x86_event_sched_in(leader, cpuctx);
-	if (ret)
-		return ret;
-
-	n1 = 1;
-	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
-		if (sub->state > PERF_EVENT_STATE_OFF) {
-			ret = x86_event_sched_in(sub, cpuctx);
-			if (ret)
-				goto undo;
-			++n1;
-		}
-	}
-	/*
-	 * copy new assignment, now we know it is possible
-	 * will be used by hw_perf_enable()
-	 */
-	memcpy(cpuc->assign, assign, n0*sizeof(int));
-
-	cpuc->n_events  = n0;
-	cpuc->n_added  += n1;
-	ctx->nr_active += n1;
-
-	/*
-	 * 1 means successful and events are active
-	 * This is not quite true because we defer
-	 * actual activation until hw_perf_enable() but
-	 * this way we* ensure caller won't try to enable
-	 * individual events
-	 */
-	return 1;
-undo:
-	x86_event_sched_out(leader, cpuctx);
-	n0  = 1;
-	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
-		if (sub->state == PERF_EVENT_STATE_ACTIVE) {
-			x86_event_sched_out(sub, cpuctx);
-			if (++n0 == n1)
-				break;
-		}
-	}
-	return ret;
-}
-
 #include "perf_event_amd.c"
 #include "perf_event_p6.c"
+#include "perf_event_p4.c"
+#include "perf_event_intel_lbr.c"
+#include "perf_event_intel_ds.c"
 #include "perf_event_intel.c"
 
 static int __cpuinit
@@ -1402,48 +1316,50 @@
 
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
-	if (x86_pmu.num_events > X86_PMC_MAX_GENERIC) {
+	if (x86_pmu.quirks)
+		x86_pmu.quirks();
+
+	if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
 		WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
-		     x86_pmu.num_events, X86_PMC_MAX_GENERIC);
-		x86_pmu.num_events = X86_PMC_MAX_GENERIC;
+		     x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
+		x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
 	}
-	perf_event_mask = (1 << x86_pmu.num_events) - 1;
-	perf_max_events = x86_pmu.num_events;
+	x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+	perf_max_events = x86_pmu.num_counters;
 
-	if (x86_pmu.num_events_fixed > X86_PMC_MAX_FIXED) {
+	if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
 		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
-		     x86_pmu.num_events_fixed, X86_PMC_MAX_FIXED);
-		x86_pmu.num_events_fixed = X86_PMC_MAX_FIXED;
+		     x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
+		x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
 	}
 
-	perf_event_mask |=
-		((1LL << x86_pmu.num_events_fixed)-1) << X86_PMC_IDX_FIXED;
-	x86_pmu.intel_ctrl = perf_event_mask;
+	x86_pmu.intel_ctrl |=
+		((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
 
 	perf_events_lapic_init();
 	register_die_notifier(&perf_event_nmi_notifier);
 
 	unconstrained = (struct event_constraint)
-		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1,
-				   0, x86_pmu.num_events);
+		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
+				   0, x86_pmu.num_counters);
 
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if (c->cmask != INTEL_ARCH_FIXED_MASK)
+			if (c->cmask != X86_RAW_EVENT_MASK)
 				continue;
 
-			c->idxmsk64 |= (1ULL << x86_pmu.num_events) - 1;
-			c->weight += x86_pmu.num_events;
+			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+			c->weight += x86_pmu.num_counters;
 		}
 	}
 
 	pr_info("... version:                %d\n",     x86_pmu.version);
-	pr_info("... bit width:              %d\n",     x86_pmu.event_bits);
-	pr_info("... generic registers:      %d\n",     x86_pmu.num_events);
-	pr_info("... value mask:             %016Lx\n", x86_pmu.event_mask);
+	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
+	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
+	pr_info("... value mask:             %016Lx\n", x86_pmu.cntval_mask);
 	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
-	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_events_fixed);
-	pr_info("... event mask:             %016Lx\n", perf_event_mask);
+	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
+	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
 	perf_cpu_notifier(x86_pmu_notifier);
 }
@@ -1453,6 +1369,59 @@
 	x86_perf_event_update(event);
 }
 
+/*
+ * Start group events scheduling transaction
+ * Set the flag to make pmu::enable() not perform the
+ * schedulability test, it will be performed at commit time
+ */
+static void x86_pmu_start_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	cpuc->group_flag |= PERF_EVENT_TXN_STARTED;
+}
+
+/*
+ * Stop group events scheduling transaction
+ * Clear the flag and pmu::enable() will perform the
+ * schedulability test.
+ */
+static void x86_pmu_cancel_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED;
+}
+
+/*
+ * Commit group events scheduling transaction
+ * Perform the group schedulability test as a whole
+ * Return 0 if success
+ */
+static int x86_pmu_commit_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int assign[X86_PMC_IDX_MAX];
+	int n, ret;
+
+	n = cpuc->n_events;
+
+	if (!x86_pmu_initialized())
+		return -EAGAIN;
+
+	ret = x86_pmu.schedule_events(cpuc, n, assign);
+	if (ret)
+		return ret;
+
+	/*
+	 * copy new assignment, now we know it is possible
+	 * will be used by hw_perf_enable()
+	 */
+	memcpy(cpuc->assign, assign, n*sizeof(int));
+
+	return 0;
+}
+
 static const struct pmu pmu = {
 	.enable		= x86_pmu_enable,
 	.disable	= x86_pmu_disable,
@@ -1460,9 +1429,38 @@
 	.stop		= x86_pmu_stop,
 	.read		= x86_pmu_read,
 	.unthrottle	= x86_pmu_unthrottle,
+	.start_txn	= x86_pmu_start_txn,
+	.cancel_txn	= x86_pmu_cancel_txn,
+	.commit_txn	= x86_pmu_commit_txn,
 };
 
 /*
+ * validate that we can schedule this event
+ */
+static int validate_event(struct perf_event *event)
+{
+	struct cpu_hw_events *fake_cpuc;
+	struct event_constraint *c;
+	int ret = 0;
+
+	fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO);
+	if (!fake_cpuc)
+		return -ENOMEM;
+
+	c = x86_pmu.get_event_constraints(fake_cpuc, event);
+
+	if (!c || !c->weight)
+		ret = -ENOSPC;
+
+	if (x86_pmu.put_event_constraints)
+		x86_pmu.put_event_constraints(fake_cpuc, event);
+
+	kfree(fake_cpuc);
+
+	return ret;
+}
+
+/*
  * validate a single event group
  *
  * validation include:
@@ -1502,7 +1500,7 @@
 
 	fake_cpuc->n_events = n;
 
-	ret = x86_schedule_events(fake_cpuc, n, NULL);
+	ret = x86_pmu.schedule_events(fake_cpuc, n, NULL);
 
 out_free:
 	kfree(fake_cpuc);
@@ -1527,6 +1525,8 @@
 
 		if (event->group_leader != event)
 			err = validate_group(event);
+		else
+			err = validate_event(event);
 
 		event->pmu = tmp;
 	}
@@ -1574,8 +1574,7 @@
 {
 	struct perf_callchain_entry *entry = data;
 
-	if (reliable)
-		callchain_store(entry, addr);
+	callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops backtrace_ops = {
@@ -1597,41 +1596,6 @@
 	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
 }
 
-/*
- * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
- */
-static unsigned long
-copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
-{
-	unsigned long offset, addr = (unsigned long)from;
-	int type = in_nmi() ? KM_NMI : KM_IRQ0;
-	unsigned long size, len = 0;
-	struct page *page;
-	void *map;
-	int ret;
-
-	do {
-		ret = __get_user_pages_fast(addr, 1, 0, &page);
-		if (!ret)
-			break;
-
-		offset = addr & (PAGE_SIZE - 1);
-		size = min(PAGE_SIZE - offset, n - len);
-
-		map = kmap_atomic(page, type);
-		memcpy(to, map+offset, size);
-		kunmap_atomic(map, type);
-		put_page(page);
-
-		len  += size;
-		to   += size;
-		addr += size;
-
-	} while (len < n);
-
-	return len;
-}
-
 #ifdef CONFIG_COMPAT
 static inline int
 perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
@@ -1727,6 +1691,11 @@
 {
 	struct perf_callchain_entry *entry;
 
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* TODO: We don't support guest os callchain now */
+		return NULL;
+	}
+
 	if (in_nmi())
 		entry = &__get_cpu_var(pmc_nmi_entry);
 	else
@@ -1750,3 +1719,37 @@
 	regs->cs = __KERNEL_CS;
 	local_save_flags(regs->flags);
 }
+
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+	unsigned long ip;
+
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+		ip = perf_guest_cbs->get_guest_ip();
+	else
+		ip = instruction_pointer(regs);
+
+	return ip;
+}
+
+unsigned long perf_misc_flags(struct pt_regs *regs)
+{
+	int misc = 0;
+
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		if (perf_guest_cbs->is_user_mode())
+			misc |= PERF_RECORD_MISC_GUEST_USER;
+		else
+			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
+	} else {
+		if (user_mode(regs))
+			misc |= PERF_RECORD_MISC_USER;
+		else
+			misc |= PERF_RECORD_MISC_KERNEL;
+	}
+
+	if (regs->flags & PERF_EFLAGS_EXACT)
+		misc |= PERF_RECORD_MISC_EXACT_IP;
+
+	return misc;
+}

arch/x86/kernel/cpu/perf_event_amd.c

diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index db6f7d4..611df11 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -2,7 +2,7 @@
 
 static DEFINE_RAW_SPINLOCK(amd_nb_lock);
 
-static __initconst u64 amd_hw_cache_event_ids
+static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -111,22 +111,19 @@
 	return amd_perfmon_event_map[hw_event];
 }
 
-static u64 amd_pmu_raw_event(u64 hw_event)
+static int amd_pmu_hw_config(struct perf_event *event)
 {
-#define K7_EVNTSEL_EVENT_MASK	0xF000000FFULL
-#define K7_EVNTSEL_UNIT_MASK	0x00000FF00ULL
-#define K7_EVNTSEL_EDGE_MASK	0x000040000ULL
-#define K7_EVNTSEL_INV_MASK	0x000800000ULL
-#define K7_EVNTSEL_REG_MASK	0x0FF000000ULL
+	int ret = x86_pmu_hw_config(event);
 
-#define K7_EVNTSEL_MASK			\
-	(K7_EVNTSEL_EVENT_MASK |	\
-	 K7_EVNTSEL_UNIT_MASK  |	\
-	 K7_EVNTSEL_EDGE_MASK  |	\
-	 K7_EVNTSEL_INV_MASK   |	\
-	 K7_EVNTSEL_REG_MASK)
+	if (ret)
+		return ret;
 
-	return hw_event & K7_EVNTSEL_MASK;
+	if (event->attr.type != PERF_TYPE_RAW)
+		return 0;
+
+	event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK;
+
+	return 0;
 }
 
 /*
@@ -165,7 +162,7 @@
 	 * be removed on one CPU at a time AND PMU is disabled
 	 * when we come here
 	 */
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		if (nb->owners[i] == event) {
 			cmpxchg(nb->owners+i, event, NULL);
 			break;
@@ -215,7 +212,7 @@
 	struct hw_perf_event *hwc = &event->hw;
 	struct amd_nb *nb = cpuc->amd_nb;
 	struct perf_event *old = NULL;
-	int max = x86_pmu.num_events;
+	int max = x86_pmu.num_counters;
 	int i, j, k = -1;
 
 	/*
@@ -293,7 +290,7 @@
 	/*
 	 * initialize all possible NB constraints
 	 */
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		__set_bit(i, nb->event_constraints[i].idxmsk);
 		nb->event_constraints[i].weight = 1;
 	}
@@ -371,21 +368,22 @@
 	raw_spin_unlock(&amd_nb_lock);
 }
 
-static __initconst struct x86_pmu amd_pmu = {
+static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
 	.handle_irq		= x86_pmu_handle_irq,
 	.disable_all		= x86_pmu_disable_all,
 	.enable_all		= x86_pmu_enable_all,
 	.enable			= x86_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
+	.hw_config		= amd_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_K7_EVNTSEL0,
 	.perfctr		= MSR_K7_PERFCTR0,
 	.event_map		= amd_pmu_event_map,
-	.raw_event		= amd_pmu_raw_event,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_events		= 4,
-	.event_bits		= 48,
-	.event_mask		= (1ULL << 48) - 1,
+	.num_counters		= 4,
+	.cntval_bits		= 48,
+	.cntval_mask		= (1ULL << 48) - 1,
 	.apic			= 1,
 	/* use highest bit to detect overflow */
 	.max_period		= (1ULL << 47) - 1,

arch/x86/kernel/cpu/perf_event_intel.c

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 9c794ac..fdbc652 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -88,7 +88,7 @@
 	return intel_perfmon_event_map[hw_event];
 }
 
-static __initconst u64 westmere_hw_cache_event_ids
+static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -179,7 +179,7 @@
  },
 };
 
-static __initconst u64 nehalem_hw_cache_event_ids
+static __initconst const u64 nehalem_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -270,7 +270,7 @@
  },
 };
 
-static __initconst u64 core2_hw_cache_event_ids
+static __initconst const u64 core2_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -361,7 +361,7 @@
  },
 };
 
-static __initconst u64 atom_hw_cache_event_ids
+static __initconst const u64 atom_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -452,60 +452,6 @@
  },
 };
 
-static u64 intel_pmu_raw_event(u64 hw_event)
-{
-#define CORE_EVNTSEL_EVENT_MASK		0x000000FFULL
-#define CORE_EVNTSEL_UNIT_MASK		0x0000FF00ULL
-#define CORE_EVNTSEL_EDGE_MASK		0x00040000ULL
-#define CORE_EVNTSEL_INV_MASK		0x00800000ULL
-#define CORE_EVNTSEL_REG_MASK		0xFF000000ULL
-
-#define CORE_EVNTSEL_MASK		\
-	(INTEL_ARCH_EVTSEL_MASK |	\
-	 INTEL_ARCH_UNIT_MASK   |	\
-	 INTEL_ARCH_EDGE_MASK   |	\
-	 INTEL_ARCH_INV_MASK    |	\
-	 INTEL_ARCH_CNT_MASK)
-
-	return hw_event & CORE_EVNTSEL_MASK;
-}
-
-static void intel_pmu_enable_bts(u64 config)
-{
-	unsigned long debugctlmsr;
-
-	debugctlmsr = get_debugctlmsr();
-
-	debugctlmsr |= X86_DEBUGCTL_TR;
-	debugctlmsr |= X86_DEBUGCTL_BTS;
-	debugctlmsr |= X86_DEBUGCTL_BTINT;
-
-	if (!(config & ARCH_PERFMON_EVENTSEL_OS))
-		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS;
-
-	if (!(config & ARCH_PERFMON_EVENTSEL_USR))
-		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR;
-
-	update_debugctlmsr(debugctlmsr);
-}
-
-static void intel_pmu_disable_bts(void)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	unsigned long debugctlmsr;
-
-	if (!cpuc->ds)
-		return;
-
-	debugctlmsr = get_debugctlmsr();
-
-	debugctlmsr &=
-		~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT |
-		  X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR);
-
-	update_debugctlmsr(debugctlmsr);
-}
-
 static void intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -514,12 +460,17 @@
 
 	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
 		intel_pmu_disable_bts();
+
+	intel_pmu_pebs_disable_all();
+	intel_pmu_lbr_disable_all();
 }
 
-static void intel_pmu_enable_all(void)
+static void intel_pmu_enable_all(int added)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	intel_pmu_pebs_enable_all();
+	intel_pmu_lbr_enable_all();
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
 
 	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
@@ -533,6 +484,42 @@
 	}
 }
 
+/*
+ * Workaround for:
+ *   Intel Errata AAK100 (model 26)
+ *   Intel Errata AAP53  (model 30)
+ *   Intel Errata BD53   (model 44)
+ *
+ * These chips need to be 'reset' when adding counters by programming
+ * the magic three (non counting) events 0x4300D2, 0x4300B1 and 0x4300B5
+ * either in sequence on the same PMC or on different PMCs.
+ */
+static void intel_pmu_nhm_enable_all(int added)
+{
+	if (added) {
+		struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+		int i;
+
+		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 0, 0x4300D2);
+		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x4300B1);
+		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x4300B5);
+
+		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x3);
+		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
+
+		for (i = 0; i < 3; i++) {
+			struct perf_event *event = cpuc->events[i];
+
+			if (!event)
+				continue;
+
+			__x86_pmu_enable_event(&event->hw,
+					       ARCH_PERFMON_EVENTSEL_ENABLE);
+		}
+	}
+	intel_pmu_enable_all(added);
+}
+
 static inline u64 intel_pmu_get_status(void)
 {
 	u64 status;
@@ -547,8 +534,7 @@
 	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
 }
 
-static inline void
-intel_pmu_disable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 {
 	int idx = hwc->idx - X86_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
@@ -557,71 +543,10 @@
 
 	rdmsrl(hwc->config_base, ctrl_val);
 	ctrl_val &= ~mask;
-	(void)checking_wrmsrl(hwc->config_base, ctrl_val);
+	wrmsrl(hwc->config_base, ctrl_val);
 }
 
-static void intel_pmu_drain_bts_buffer(void)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct debug_store *ds = cpuc->ds;
-	struct bts_record {
-		u64	from;
-		u64	to;
-		u64	flags;
-	};
-	struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
-	struct bts_record *at, *top;
-	struct perf_output_handle handle;
-	struct perf_event_header header;
-	struct perf_sample_data data;
-	struct pt_regs regs;
-
-	if (!event)
-		return;
-
-	if (!ds)
-		return;
-
-	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
-	top = (struct bts_record *)(unsigned long)ds->bts_index;
-
-	if (top <= at)
-		return;
-
-	ds->bts_index = ds->bts_buffer_base;
-
-	perf_sample_data_init(&data, 0);
-
-	data.period	= event->hw.last_period;
-	regs.ip		= 0;
-
-	/*
-	 * Prepare a generic sample, i.e. fill in the invariant fields.
-	 * We will overwrite the from and to address before we output
-	 * the sample.
-	 */
-	perf_prepare_sample(&header, &data, event, &regs);
-
-	if (perf_output_begin(&handle, event,
-			      header.size * (top - at), 1, 1))
-		return;
-
-	for (; at < top; at++) {
-		data.ip		= at->from;
-		data.addr	= at->to;
-
-		perf_output_sample(&handle, &header, &data, event);
-	}
-
-	perf_output_end(&handle);
-
-	/* There's new data available. */
-	event->hw.interrupts++;
-	event->pending_kill = POLL_IN;
-}
-
-static inline void
-intel_pmu_disable_event(struct perf_event *event)
+static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -637,14 +562,15 @@
 	}
 
 	x86_pmu_disable_event(event);
+
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
 }
 
-static inline void
-intel_pmu_enable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 {
 	int idx = hwc->idx - X86_PMC_IDX_FIXED;
 	u64 ctrl_val, bits, mask;
-	int err;
 
 	/*
 	 * Enable IRQ generation (0x8),
@@ -669,7 +595,7 @@
 	rdmsrl(hwc->config_base, ctrl_val);
 	ctrl_val &= ~mask;
 	ctrl_val |= bits;
-	err = checking_wrmsrl(hwc->config_base, ctrl_val);
+	wrmsrl(hwc->config_base, ctrl_val);
 }
 
 static void intel_pmu_enable_event(struct perf_event *event)
@@ -689,7 +615,10 @@
 		return;
 	}
 
-	__x86_pmu_enable_event(hwc);
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_enable(event);
+
+	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
 /*
@@ -708,20 +637,20 @@
 	unsigned long flags;
 	int idx;
 
-	if (!x86_pmu.num_events)
+	if (!x86_pmu.num_counters)
 		return;
 
 	local_irq_save(flags);
 
 	printk("clearing PMU state on CPU#%d\n", smp_processor_id());
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
 		checking_wrmsrl(x86_pmu.perfctr  + idx, 0ull);
 	}
-	for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
 		checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
-	}
+
 	if (ds)
 		ds->bts_index = ds->bts_buffer_base;
 
@@ -747,7 +676,7 @@
 	intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
 	if (!status) {
-		intel_pmu_enable_all();
+		intel_pmu_enable_all(0);
 		return 0;
 	}
 
@@ -762,6 +691,15 @@
 
 	inc_irq_stat(apic_perf_irqs);
 	ack = status;
+
+	intel_pmu_lbr_read();
+
+	/*
+	 * PEBS overflow sets bit 62 in the global status register
+	 */
+	if (__test_and_clear_bit(62, (unsigned long *)&status))
+		x86_pmu.drain_pebs(regs);
+
 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];
 
@@ -787,26 +725,22 @@
 		goto again;
 
 done:
-	intel_pmu_enable_all();
+	intel_pmu_enable_all(0);
 	return 1;
 }
 
-static struct event_constraint bts_constraint =
-	EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
-
 static struct event_constraint *
-intel_special_constraints(struct perf_event *event)
+intel_bts_constraints(struct perf_event *event)
 {
-	unsigned int hw_event;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int hw_event, bts_event;
 
-	hw_event = event->hw.config & INTEL_ARCH_EVENT_MASK;
+	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
+	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
-	if (unlikely((hw_event ==
-		      x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) &&
-		     (event->hw.sample_period == 1))) {
-
+	if (unlikely(hw_event == bts_event && hwc->sample_period == 1))
 		return &bts_constraint;
-	}
+
 	return NULL;
 }
 
@@ -815,24 +749,53 @@
 {
 	struct event_constraint *c;
 
-	c = intel_special_constraints(event);
+	c = intel_bts_constraints(event);
+	if (c)
+		return c;
+
+	c = intel_pebs_constraints(event);
 	if (c)
 		return c;
 
 	return x86_get_event_constraints(cpuc, event);
 }
 
-static __initconst struct x86_pmu core_pmu = {
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	if (event->attr.type != PERF_TYPE_RAW)
+		return 0;
+
+	if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY))
+		return 0;
+
+	if (x86_pmu.version < 3)
+		return -EINVAL;
+
+	if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	event->hw.config |= ARCH_PERFMON_EVENTSEL_ANY;
+
+	return 0;
+}
+
+static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
 	.disable_all		= x86_pmu_disable_all,
 	.enable_all		= x86_pmu_enable_all,
 	.enable			= x86_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
 	.event_map		= intel_pmu_event_map,
-	.raw_event		= intel_pmu_raw_event,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
 	/*
@@ -845,17 +808,32 @@
 	.event_constraints	= intel_core_event_constraints,
 };
 
-static __initconst struct x86_pmu intel_pmu = {
+static void intel_pmu_cpu_starting(int cpu)
+{
+	init_debug_store_on_cpu(cpu);
+	/*
+	 * Deal with CPUs that don't clear their LBRs on power-up.
+	 */
+	intel_pmu_lbr_reset();
+}
+
+static void intel_pmu_cpu_dying(int cpu)
+{
+	fini_debug_store_on_cpu(cpu);
+}
+
+static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
 	.disable_all		= intel_pmu_disable_all,
 	.enable_all		= intel_pmu_enable_all,
 	.enable			= intel_pmu_enable_event,
 	.disable		= intel_pmu_disable_event,
+	.hw_config		= intel_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
 	.event_map		= intel_pmu_event_map,
-	.raw_event		= intel_pmu_raw_event,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
 	/*
@@ -864,14 +842,38 @@
 	 * the generic event period:
 	 */
 	.max_period		= (1ULL << 31) - 1,
-	.enable_bts		= intel_pmu_enable_bts,
-	.disable_bts		= intel_pmu_disable_bts,
 	.get_event_constraints	= intel_get_event_constraints,
 
-	.cpu_starting		= init_debug_store_on_cpu,
-	.cpu_dying		= fini_debug_store_on_cpu,
+	.cpu_starting		= intel_pmu_cpu_starting,
+	.cpu_dying		= intel_pmu_cpu_dying,
 };
 
+static void intel_clovertown_quirks(void)
+{
+	/*
+	 * PEBS is unreliable due to:
+	 *
+	 *   AJ67  - PEBS may experience CPL leaks
+	 *   AJ68  - PEBS PMI may be delayed by one event
+	 *   AJ69  - GLOBAL_STATUS[62] will only be set when DEBUGCTL[12]
+	 *   AJ106 - FREEZE_LBRS_ON_PMI doesn't work in combination with PEBS
+	 *
+	 * AJ67 could be worked around by restricting the OS/USR flags.
+	 * AJ69 could be worked around by setting PMU_FREEZE_ON_PMI.
+	 *
+	 * AJ106 could possibly be worked around by not allowing LBR
+	 *       usage from PEBS, including the fixup.
+	 * AJ68  could possibly be worked around by always programming
+	 * 	 a pebs_event_reset[0] value and coping with the lost events.
+	 *
+	 * But taken together it might just make sense to not enable PEBS on
+	 * these chips.
+	 */
+	printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
+	x86_pmu.pebs = 0;
+	x86_pmu.pebs_constraints = NULL;
+}
+
 static __init int intel_pmu_init(void)
 {
 	union cpuid10_edx edx;
@@ -881,12 +883,13 @@
 	int version;
 
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
-		/* check for P6 processor family */
-	   if (boot_cpu_data.x86 == 6) {
-		return p6_pmu_init();
-	   } else {
+		switch (boot_cpu_data.x86) {
+		case 0x6:
+			return p6_pmu_init();
+		case 0xf:
+			return p4_pmu_init();
+		}
 		return -ENODEV;
-	   }
 	}
 
 	/*
@@ -904,16 +907,28 @@
 		x86_pmu = intel_pmu;
 
 	x86_pmu.version			= version;
-	x86_pmu.num_events		= eax.split.num_events;
-	x86_pmu.event_bits		= eax.split.bit_width;
-	x86_pmu.event_mask		= (1ULL << eax.split.bit_width) - 1;
+	x86_pmu.num_counters		= eax.split.num_counters;
+	x86_pmu.cntval_bits		= eax.split.bit_width;
+	x86_pmu.cntval_mask		= (1ULL << eax.split.bit_width) - 1;
 
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
 	 * assume at least 3 events:
 	 */
 	if (version > 1)
-		x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3);
+		x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
+
+	/*
+	 * v2 and above have a perf capabilities MSR
+	 */
+	if (version > 1) {
+		u64 capabilities;
+
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
+		x86_pmu.intel_cap.capabilities = capabilities;
+	}
+
+	intel_ds_init();
 
 	/*
 	 * Install the hw-cache-events table:
@@ -924,12 +939,15 @@
 		break;
 
 	case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+		x86_pmu.quirks = intel_clovertown_quirks;
 	case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
 	case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
 	case 29: /* six-core 45 nm xeon "Dunnington" */
 		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
+		intel_pmu_lbr_init_core();
+
 		x86_pmu.event_constraints = intel_core2_event_constraints;
 		pr_cont("Core2 events, ");
 		break;
@@ -940,13 +958,19 @@
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
+		intel_pmu_lbr_init_nhm();
+
 		x86_pmu.event_constraints = intel_nehalem_event_constraints;
-		pr_cont("Nehalem/Corei7 events, ");
+		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
+		pr_cont("Nehalem events, ");
 		break;
+
 	case 28: /* Atom */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
+		intel_pmu_lbr_init_atom();
+
 		x86_pmu.event_constraints = intel_gen_event_constraints;
 		pr_cont("Atom events, ");
 		break;
@@ -956,7 +980,10 @@
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
+		intel_pmu_lbr_init_nhm();
+
 		x86_pmu.event_constraints = intel_westmere_event_constraints;
+		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		pr_cont("Westmere events, ");
 		break;
 

arch/x86/kernel/cpu/perf_event_intel_ds.c

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
new file mode 100644
index 0000000..18018d1
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -0,0 +1,641 @@
+#ifdef CONFIG_CPU_SUP_INTEL
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS		4
+
+/* The size of a BTS record in bytes: */
+#define BTS_RECORD_SIZE		24
+
+#define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE	PAGE_SIZE
+
+/*
+ * pebs_record_32 for p4 and core not supported
+
+struct pebs_record_32 {
+	u32 flags, ip;
+	u32 ax, bc, cx, dx;
+	u32 si, di, bp, sp;
+};
+
+ */
+
+struct pebs_record_core {
+	u64 flags, ip;
+	u64 ax, bx, cx, dx;
+	u64 si, di, bp, sp;
+	u64 r8,  r9,  r10, r11;
+	u64 r12, r13, r14, r15;
+};
+
+struct pebs_record_nhm {
+	u64 flags, ip;
+	u64 ax, bx, cx, dx;
+	u64 si, di, bp, sp;
+	u64 r8,  r9,  r10, r11;
+	u64 r12, r13, r14, r15;
+	u64 status, dla, dse, lat;
+};
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+	u64	bts_buffer_base;
+	u64	bts_index;
+	u64	bts_absolute_maximum;
+	u64	bts_interrupt_threshold;
+	u64	pebs_buffer_base;
+	u64	pebs_index;
+	u64	pebs_absolute_maximum;
+	u64	pebs_interrupt_threshold;
+	u64	pebs_event_reset[MAX_PEBS_EVENTS];
+};
+
+static void init_debug_store_on_cpu(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+	if (!ds)
+		return;
+
+	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA,
+		     (u32)((u64)(unsigned long)ds),
+		     (u32)((u64)(unsigned long)ds >> 32));
+}
+
+static void fini_debug_store_on_cpu(int cpu)
+{
+	if (!per_cpu(cpu_hw_events, cpu).ds)
+		return;
+
+	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
+}
+
+static void release_ds_buffers(void)
+{
+	int cpu;
+
+	if (!x86_pmu.bts && !x86_pmu.pebs)
+		return;
+
+	get_online_cpus();
+
+	for_each_online_cpu(cpu)
+		fini_debug_store_on_cpu(cpu);
+
+	for_each_possible_cpu(cpu) {
+		struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+		if (!ds)
+			continue;
+
+		per_cpu(cpu_hw_events, cpu).ds = NULL;
+
+		kfree((void *)(unsigned long)ds->pebs_buffer_base);
+		kfree((void *)(unsigned long)ds->bts_buffer_base);
+		kfree(ds);
+	}
+
+	put_online_cpus();
+}
+
+static int reserve_ds_buffers(void)
+{
+	int cpu, err = 0;
+
+	if (!x86_pmu.bts && !x86_pmu.pebs)
+		return 0;
+
+	get_online_cpus();
+
+	for_each_possible_cpu(cpu) {
+		struct debug_store *ds;
+		void *buffer;
+		int max, thresh;
+
+		err = -ENOMEM;
+		ds = kzalloc(sizeof(*ds), GFP_KERNEL);
+		if (unlikely(!ds))
+			break;
+		per_cpu(cpu_hw_events, cpu).ds = ds;
+
+		if (x86_pmu.bts) {
+			buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
+			if (unlikely(!buffer))
+				break;
+
+			max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+			thresh = max / 16;
+
+			ds->bts_buffer_base = (u64)(unsigned long)buffer;
+			ds->bts_index = ds->bts_buffer_base;
+			ds->bts_absolute_maximum = ds->bts_buffer_base +
+				max * BTS_RECORD_SIZE;
+			ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+				thresh * BTS_RECORD_SIZE;
+		}
+
+		if (x86_pmu.pebs) {
+			buffer = kzalloc(PEBS_BUFFER_SIZE, GFP_KERNEL);
+			if (unlikely(!buffer))
+				break;
+
+			max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+
+			ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+			ds->pebs_index = ds->pebs_buffer_base;
+			ds->pebs_absolute_maximum = ds->pebs_buffer_base +
+				max * x86_pmu.pebs_record_size;
+			/*
+			 * Always use single record PEBS
+			 */
+			ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
+				x86_pmu.pebs_record_size;
+		}
+
+		err = 0;
+	}
+
+	if (err)
+		release_ds_buffers();
+	else {
+		for_each_online_cpu(cpu)
+			init_debug_store_on_cpu(cpu);
+	}
+
+	put_online_cpus();
+
+	return err;
+}
+
+/*
+ * BTS
+ */
+
+static struct event_constraint bts_constraint =
+	EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
+
+static void intel_pmu_enable_bts(u64 config)
+{
+	unsigned long debugctlmsr;
+
+	debugctlmsr = get_debugctlmsr();
+
+	debugctlmsr |= DEBUGCTLMSR_TR;
+	debugctlmsr |= DEBUGCTLMSR_BTS;
+	debugctlmsr |= DEBUGCTLMSR_BTINT;
+
+	if (!(config & ARCH_PERFMON_EVENTSEL_OS))
+		debugctlmsr |= DEBUGCTLMSR_BTS_OFF_OS;
+
+	if (!(config & ARCH_PERFMON_EVENTSEL_USR))
+		debugctlmsr |= DEBUGCTLMSR_BTS_OFF_USR;
+
+	update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_disable_bts(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	unsigned long debugctlmsr;
+
+	if (!cpuc->ds)
+		return;
+
+	debugctlmsr = get_debugctlmsr();
+
+	debugctlmsr &=
+		~(DEBUGCTLMSR_TR | DEBUGCTLMSR_BTS | DEBUGCTLMSR_BTINT |
+		  DEBUGCTLMSR_BTS_OFF_OS | DEBUGCTLMSR_BTS_OFF_USR);
+
+	update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_drain_bts_buffer(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct bts_record {
+		u64	from;
+		u64	to;
+		u64	flags;
+	};
+	struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
+	struct bts_record *at, *top;
+	struct perf_output_handle handle;
+	struct perf_event_header header;
+	struct perf_sample_data data;
+	struct pt_regs regs;
+
+	if (!event)
+		return;
+
+	if (!ds)
+		return;
+
+	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
+	top = (struct bts_record *)(unsigned long)ds->bts_index;
+
+	if (top <= at)
+		return;
+
+	ds->bts_index = ds->bts_buffer_base;
+
+	perf_sample_data_init(&data, 0);
+	data.period = event->hw.last_period;
+	regs.ip     = 0;
+
+	/*
+	 * Prepare a generic sample, i.e. fill in the invariant fields.
+	 * We will overwrite the from and to address before we output
+	 * the sample.
+	 */
+	perf_prepare_sample(&header, &data, event, &regs);
+
+	if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1))
+		return;
+
+	for (; at < top; at++) {
+		data.ip		= at->from;
+		data.addr	= at->to;
+
+		perf_output_sample(&handle, &header, &data, event);
+	}
+
+	perf_output_end(&handle);
+
+	/* There's new data available. */
+	event->hw.interrupts++;
+	event->pending_kill = POLL_IN;
+}
+
+/*
+ * PEBS
+ */
+
+static struct event_constraint intel_core_pebs_events[] = {
+	PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */
+	PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
+	PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
+	PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
+	PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */
+	PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
+	PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */
+	PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
+	PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_nehalem_pebs_events[] = {
+	PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */
+	PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */
+	PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */
+	PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */
+	PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */
+	PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
+	PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */
+	PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
+	PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint *
+intel_pebs_constraints(struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	if (!event->attr.precise_ip)
+		return NULL;
+
+	if (x86_pmu.pebs_constraints) {
+		for_each_event_constraint(c, x86_pmu.pebs_constraints) {
+			if ((event->hw.config & c->cmask) == c->code)
+				return c;
+		}
+	}
+
+	return &emptyconstraint;
+}
+
+static void intel_pmu_pebs_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
+
+	cpuc->pebs_enabled |= 1ULL << hwc->idx;
+	WARN_ON_ONCE(cpuc->enabled);
+
+	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
+		intel_pmu_lbr_enable(event);
+}
+
+static void intel_pmu_pebs_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
+	if (cpuc->enabled)
+		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+
+	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
+
+	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
+		intel_pmu_lbr_disable(event);
+}
+
+static void intel_pmu_pebs_enable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->pebs_enabled)
+		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+}
+
+static void intel_pmu_pebs_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->pebs_enabled)
+		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+}
+
+#include <asm/insn.h>
+
+static inline bool kernel_ip(unsigned long ip)
+{
+#ifdef CONFIG_X86_32
+	return ip > PAGE_OFFSET;
+#else
+	return (long)ip < 0;
+#endif
+}
+
+static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	unsigned long from = cpuc->lbr_entries[0].from;
+	unsigned long old_to, to = cpuc->lbr_entries[0].to;
+	unsigned long ip = regs->ip;
+
+	/*
+	 * We don't need to fixup if the PEBS assist is fault like
+	 */
+	if (!x86_pmu.intel_cap.pebs_trap)
+		return 1;
+
+	/*
+	 * No LBR entry, no basic block, no rewinding
+	 */
+	if (!cpuc->lbr_stack.nr || !from || !to)
+		return 0;
+
+	/*
+	 * Basic blocks should never cross user/kernel boundaries
+	 */
+	if (kernel_ip(ip) != kernel_ip(to))
+		return 0;
+
+	/*
+	 * unsigned math, either ip is before the start (impossible) or
+	 * the basic block is larger than 1 page (sanity)
+	 */
+	if ((ip - to) > PAGE_SIZE)
+		return 0;
+
+	/*
+	 * We sampled a branch insn, rewind using the LBR stack
+	 */
+	if (ip == to) {
+		regs->ip = from;
+		return 1;
+	}
+
+	do {
+		struct insn insn;
+		u8 buf[MAX_INSN_SIZE];
+		void *kaddr;
+
+		old_to = to;
+		if (!kernel_ip(ip)) {
+			int bytes, size = MAX_INSN_SIZE;
+
+			bytes = copy_from_user_nmi(buf, (void __user *)to, size);
+			if (bytes != size)
+				return 0;
+
+			kaddr = buf;
+		} else
+			kaddr = (void *)to;
+
+		kernel_insn_init(&insn, kaddr);
+		insn_get_length(&insn);
+		to += insn.length;
+	} while (to < ip);
+
+	if (to == ip) {
+		regs->ip = old_to;
+		return 1;
+	}
+
+	/*
+	 * Even though we decoded the basic block, the instruction stream
+	 * never matched the given IP, either the TO or the IP got corrupted.
+	 */
+	return 0;
+}
+
+static int intel_pmu_save_and_restart(struct perf_event *event);
+
+static void __intel_pmu_pebs_event(struct perf_event *event,
+				   struct pt_regs *iregs, void *__pebs)
+{
+	/*
+	 * We cast to pebs_record_core since that is a subset of
+	 * both formats and we don't use the other fields in this
+	 * routine.
+	 */
+	struct pebs_record_core *pebs = __pebs;
+	struct perf_sample_data data;
+	struct pt_regs regs;
+
+	if (!intel_pmu_save_and_restart(event))
+		return;
+
+	perf_sample_data_init(&data, 0);
+	data.period = event->hw.last_period;
+
+	/*
+	 * We use the interrupt regs as a base because the PEBS record
+	 * does not contain a full regs set, specifically it seems to
+	 * lack segment descriptors, which get used by things like
+	 * user_mode().
+	 *
+	 * In the simple case fix up only the IP and BP,SP regs, for
+	 * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
+	 * A possible PERF_SAMPLE_REGS will have to transfer all regs.
+	 */
+	regs = *iregs;
+	regs.ip = pebs->ip;
+	regs.bp = pebs->bp;
+	regs.sp = pebs->sp;
+
+	if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
+		regs.flags |= PERF_EFLAGS_EXACT;
+	else
+		regs.flags &= ~PERF_EFLAGS_EXACT;
+
+	if (perf_event_overflow(event, 1, &data, &regs))
+		x86_pmu_stop(event);
+}
+
+static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct perf_event *event = cpuc->events[0]; /* PMC0 only */
+	struct pebs_record_core *at, *top;
+	int n;
+
+	if (!ds || !x86_pmu.pebs)
+		return;
+
+	at  = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base;
+	top = (struct pebs_record_core *)(unsigned long)ds->pebs_index;
+
+	/*
+	 * Whatever else happens, drain the thing
+	 */
+	ds->pebs_index = ds->pebs_buffer_base;
+
+	if (!test_bit(0, cpuc->active_mask))
+		return;
+
+	WARN_ON_ONCE(!event);
+
+	if (!event->attr.precise_ip)
+		return;
+
+	n = top - at;
+	if (n <= 0)
+		return;
+
+	/*
+	 * Should not happen, we program the threshold at 1 and do not
+	 * set a reset value.
+	 */
+	WARN_ON_ONCE(n > 1);
+	at += n - 1;
+
+	__intel_pmu_pebs_event(event, iregs, at);
+}
+
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct pebs_record_nhm *at, *top;
+	struct perf_event *event = NULL;
+	u64 status = 0;
+	int bit, n;
+
+	if (!ds || !x86_pmu.pebs)
+		return;
+
+	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+	top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
+
+	ds->pebs_index = ds->pebs_buffer_base;
+
+	n = top - at;
+	if (n <= 0)
+		return;
+
+	/*
+	 * Should not happen, we program the threshold at 1 and do not
+	 * set a reset value.
+	 */
+	WARN_ON_ONCE(n > MAX_PEBS_EVENTS);
+
+	for ( ; at < top; at++) {
+		for_each_set_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) {
+			event = cpuc->events[bit];
+			if (!test_bit(bit, cpuc->active_mask))
+				continue;
+
+			WARN_ON_ONCE(!event);
+
+			if (!event->attr.precise_ip)
+				continue;
+
+			if (__test_and_set_bit(bit, (unsigned long *)&status))
+				continue;
+
+			break;
+		}
+
+		if (!event || bit >= MAX_PEBS_EVENTS)
+			continue;
+
+		__intel_pmu_pebs_event(event, iregs, at);
+	}
+}
+
+/*
+ * BTS, PEBS probe and setup
+ */
+
+static void intel_ds_init(void)
+{
+	/*
+	 * No support for 32bit formats
+	 */
+	if (!boot_cpu_has(X86_FEATURE_DTES64))
+		return;
+
+	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
+	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+	if (x86_pmu.pebs) {
+		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
+		int format = x86_pmu.intel_cap.pebs_format;
+
+		switch (format) {
+		case 0:
+			printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
+			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
+			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
+			x86_pmu.pebs_constraints = intel_core_pebs_events;
+			break;
+
+		case 1:
+			printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
+			x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
+			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
+			x86_pmu.pebs_constraints = intel_nehalem_pebs_events;
+			break;
+
+		default:
+			printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
+			x86_pmu.pebs = 0;
+			break;
+		}
+	}
+}
+
+#else /* CONFIG_CPU_SUP_INTEL */
+
+static int reserve_ds_buffers(void)
+{
+	return 0;
+}
+
+static void release_ds_buffers(void)
+{
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */

arch/x86/kernel/cpu/perf_event_intel_lbr.c

diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
new file mode 100644
index 0000000..d202c1b
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -0,0 +1,218 @@
+#ifdef CONFIG_CPU_SUP_INTEL
+
+enum {
+	LBR_FORMAT_32		= 0x00,
+	LBR_FORMAT_LIP		= 0x01,
+	LBR_FORMAT_EIP		= 0x02,
+	LBR_FORMAT_EIP_FLAGS	= 0x03,
+};
+
+/*
+ * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
+ * otherwise it becomes near impossible to get a reliable stack.
+ */
+
+static void __intel_pmu_lbr_enable(void)
+{
+	u64 debugctl;
+
+	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+}
+
+static void __intel_pmu_lbr_disable(void)
+{
+	u64 debugctl;
+
+	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+}
+
+static void intel_pmu_lbr_reset_32(void)
+{
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++)
+		wrmsrl(x86_pmu.lbr_from + i, 0);
+}
+
+static void intel_pmu_lbr_reset_64(void)
+{
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		wrmsrl(x86_pmu.lbr_from + i, 0);
+		wrmsrl(x86_pmu.lbr_to   + i, 0);
+	}
+}
+
+static void intel_pmu_lbr_reset(void)
+{
+	if (!x86_pmu.lbr_nr)
+		return;
+
+	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
+		intel_pmu_lbr_reset_32();
+	else
+		intel_pmu_lbr_reset_64();
+}
+
+static void intel_pmu_lbr_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!x86_pmu.lbr_nr)
+		return;
+
+	WARN_ON_ONCE(cpuc->enabled);
+
+	/*
+	 * Reset the LBR stack if we changed task context to
+	 * avoid data leaks.
+	 */
+
+	if (event->ctx->task && cpuc->lbr_context != event->ctx) {
+		intel_pmu_lbr_reset();
+		cpuc->lbr_context = event->ctx;
+	}
+
+	cpuc->lbr_users++;
+}
+
+static void intel_pmu_lbr_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!x86_pmu.lbr_nr)
+		return;
+
+	cpuc->lbr_users--;
+	WARN_ON_ONCE(cpuc->lbr_users < 0);
+
+	if (cpuc->enabled && !cpuc->lbr_users)
+		__intel_pmu_lbr_disable();
+}
+
+static void intel_pmu_lbr_enable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->lbr_users)
+		__intel_pmu_lbr_enable();
+}
+
+static void intel_pmu_lbr_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->lbr_users)
+		__intel_pmu_lbr_disable();
+}
+
+static inline u64 intel_pmu_lbr_tos(void)
+{
+	u64 tos;
+
+	rdmsrl(x86_pmu.lbr_tos, tos);
+
+	return tos;
+}
+
+static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
+{
+	unsigned long mask = x86_pmu.lbr_nr - 1;
+	u64 tos = intel_pmu_lbr_tos();
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		unsigned long lbr_idx = (tos - i) & mask;
+		union {
+			struct {
+				u32 from;
+				u32 to;
+			};
+			u64     lbr;
+		} msr_lastbranch;
+
+		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
+
+		cpuc->lbr_entries[i].from  = msr_lastbranch.from;
+		cpuc->lbr_entries[i].to    = msr_lastbranch.to;
+		cpuc->lbr_entries[i].flags = 0;
+	}
+	cpuc->lbr_stack.nr = i;
+}
+
+#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
+
+/*
+ * Due to lack of segmentation in Linux the effective address (offset)
+ * is the same as the linear address, allowing us to merge the LIP and EIP
+ * LBR formats.
+ */
+static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
+{
+	unsigned long mask = x86_pmu.lbr_nr - 1;
+	int lbr_format = x86_pmu.intel_cap.lbr_format;
+	u64 tos = intel_pmu_lbr_tos();
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		unsigned long lbr_idx = (tos - i) & mask;
+		u64 from, to, flags = 0;
+
+		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
+		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
+
+		if (lbr_format == LBR_FORMAT_EIP_FLAGS) {
+			flags = !!(from & LBR_FROM_FLAG_MISPRED);
+			from = (u64)((((s64)from) << 1) >> 1);
+		}
+
+		cpuc->lbr_entries[i].from  = from;
+		cpuc->lbr_entries[i].to    = to;
+		cpuc->lbr_entries[i].flags = flags;
+	}
+	cpuc->lbr_stack.nr = i;
+}
+
+static void intel_pmu_lbr_read(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!cpuc->lbr_users)
+		return;
+
+	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
+		intel_pmu_lbr_read_32(cpuc);
+	else
+		intel_pmu_lbr_read_64(cpuc);
+}
+
+static void intel_pmu_lbr_init_core(void)
+{
+	x86_pmu.lbr_nr     = 4;
+	x86_pmu.lbr_tos    = 0x01c9;
+	x86_pmu.lbr_from   = 0x40;
+	x86_pmu.lbr_to     = 0x60;
+}
+
+static void intel_pmu_lbr_init_nhm(void)
+{
+	x86_pmu.lbr_nr     = 16;
+	x86_pmu.lbr_tos    = 0x01c9;
+	x86_pmu.lbr_from   = 0x680;
+	x86_pmu.lbr_to     = 0x6c0;
+}
+
+static void intel_pmu_lbr_init_atom(void)
+{
+	x86_pmu.lbr_nr	   = 8;
+	x86_pmu.lbr_tos    = 0x01c9;
+	x86_pmu.lbr_from   = 0x40;
+	x86_pmu.lbr_to     = 0x60;
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */

arch/x86/kernel/cpu/perf_event_p4.c

diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
new file mode 100644
index 0000000..424fc8d
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -0,0 +1,857 @@
+/*
+ * Netburst Perfomance Events (P4, old Xeon)
+ *
+ *  Copyright (C) 2010 Parallels, Inc., Cyrill Gorcunov <gorcunov@openvz.org>
+ *  Copyright (C) 2010 Intel Corporation, Lin Ming <ming.m.lin@intel.com>
+ *
+ *  For licencing details see kernel-base/COPYING
+ */
+
+#ifdef CONFIG_CPU_SUP_INTEL
+
+#include <asm/perf_event_p4.h>
+
+#define P4_CNTR_LIMIT 3
+/*
+ * array indices: 0,1 - HT threads, used with HT enabled cpu
+ */
+struct p4_event_bind {
+	unsigned int opcode;			/* Event code and ESCR selector */
+	unsigned int escr_msr[2];		/* ESCR MSR for this event */
+	char cntr[2][P4_CNTR_LIMIT];		/* counter index (offset), -1 on abscence */
+};
+
+struct p4_cache_event_bind {
+	unsigned int metric_pebs;
+	unsigned int metric_vert;
+};
+
+#define P4_GEN_CACHE_EVENT_BIND(name)		\
+	[P4_CACHE__##name] = {			\
+		.metric_pebs = P4_PEBS__##name,	\
+		.metric_vert = P4_VERT__##name,	\
+	}
+
+static struct p4_cache_event_bind p4_cache_event_bind_map[] = {
+	P4_GEN_CACHE_EVENT_BIND(1stl_cache_load_miss_retired),
+	P4_GEN_CACHE_EVENT_BIND(2ndl_cache_load_miss_retired),
+	P4_GEN_CACHE_EVENT_BIND(dtlb_load_miss_retired),
+	P4_GEN_CACHE_EVENT_BIND(dtlb_store_miss_retired),
+};
+
+/*
+ * Note that we don't use CCCR1 here, there is an
+ * exception for P4_BSQ_ALLOCATION but we just have
+ * no workaround
+ *
+ * consider this binding as resources which particular
+ * event may borrow, it doesn't contain EventMask,
+ * Tags and friends -- they are left to a caller
+ */
+static struct p4_event_bind p4_event_bind_map[] = {
+	[P4_EVENT_TC_DELIVER_MODE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_TC_DELIVER_MODE),
+		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_BPU_FETCH_REQUEST] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST),
+		.escr_msr	= { MSR_P4_BPU_ESCR0, MSR_P4_BPU_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_ITLB_REFERENCE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_ITLB_REFERENCE),
+		.escr_msr	= { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_MEMORY_CANCEL] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_CANCEL),
+		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_MEMORY_COMPLETE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_COMPLETE),
+		.escr_msr	= { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_LOAD_PORT_REPLAY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY),
+		.escr_msr	= { MSR_P4_SAAT_ESCR0, MSR_P4_SAAT_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_STORE_PORT_REPLAY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY),
+		.escr_msr	= { MSR_P4_SAAT_ESCR0 ,  MSR_P4_SAAT_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_MOB_LOAD_REPLAY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY),
+		.escr_msr	= { MSR_P4_MOB_ESCR0, MSR_P4_MOB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_PAGE_WALK_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE),
+		.escr_msr	= { MSR_P4_PMH_ESCR0, MSR_P4_PMH_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_BSQ_CACHE_REFERENCE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE),
+		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_IOQ_ALLOCATION] = {
+		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ALLOCATION),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_IOQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
+		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES),
+		.escr_msr	= { MSR_P4_FSB_ESCR1,  MSR_P4_FSB_ESCR1 },
+		.cntr		= { {2, -1, -1}, {3, -1, -1} },
+	},
+	[P4_EVENT_FSB_DATA_ACTIVITY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_BSQ_ALLOCATION] = {		/* shared ESCR, broken CCCR1 */
+		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ALLOCATION),
+		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR0 },
+		.cntr		= { {0, -1, -1}, {1, -1, -1} },
+	},
+	[P4_EVENT_BSQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
+		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES),
+		.escr_msr	= { MSR_P4_BSU_ESCR1 , MSR_P4_BSU_ESCR1 },
+		.cntr		= { {2, -1, -1}, {3, -1, -1} },
+	},
+	[P4_EVENT_SSE_INPUT_ASSIST] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_PACKED_SP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_PACKED_SP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_PACKED_DP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_PACKED_DP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_SCALAR_SP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_SP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_SCALAR_DP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_DP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_64BIT_MMX_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_64BIT_MMX_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_128BIT_MMX_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_128BIT_MMX_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_X87_FP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_X87_FP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_TC_MISC] = {
+		.opcode		= P4_OPCODE(P4_EVENT_TC_MISC),
+		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_GLOBAL_POWER_EVENTS] = {
+		.opcode		= P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_TC_MS_XFER] = {
+		.opcode		= P4_OPCODE(P4_EVENT_TC_MS_XFER),
+		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_UOP_QUEUE_WRITES] = {
+		.opcode		= P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES),
+		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE),
+		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR0 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_RETIRED_BRANCH_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE),
+		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_RESOURCE_STALL] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RESOURCE_STALL),
+		.escr_msr	= { MSR_P4_ALF_ESCR0, MSR_P4_ALF_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_WC_BUFFER] = {
+		.opcode		= P4_OPCODE(P4_EVENT_WC_BUFFER),
+		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_B2B_CYCLES] = {
+		.opcode		= P4_OPCODE(P4_EVENT_B2B_CYCLES),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_BNR] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BNR),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_SNOOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SNOOP),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_RESPONSE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RESPONSE),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_FRONT_END_EVENT] = {
+		.opcode		= P4_OPCODE(P4_EVENT_FRONT_END_EVENT),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_EXECUTION_EVENT] = {
+		.opcode		= P4_OPCODE(P4_EVENT_EXECUTION_EVENT),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_REPLAY_EVENT] = {
+		.opcode		= P4_OPCODE(P4_EVENT_REPLAY_EVENT),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_INSTR_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_INSTR_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_UOPS_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_UOPS_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_UOP_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_UOP_TYPE),
+		.escr_msr	= { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_BRANCH_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BRANCH_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_MISPRED_BRANCH_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_X87_ASSIST] = {
+		.opcode		= P4_OPCODE(P4_EVENT_X87_ASSIST),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_MACHINE_CLEAR] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MACHINE_CLEAR),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_INSTR_COMPLETED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_INSTR_COMPLETED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+};
+
+#define P4_GEN_CACHE_EVENT(event, bit, cache_event)			  \
+	p4_config_pack_escr(P4_ESCR_EVENT(event)			| \
+			    P4_ESCR_EMASK_BIT(event, bit))		| \
+	p4_config_pack_cccr(cache_event					| \
+			    P4_CCCR_ESEL(P4_OPCODE_ESEL(P4_OPCODE(event))))
+
+static __initconst const u64 p4_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__1stl_cache_load_miss_retired),
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__2ndl_cache_load_miss_retired),
+	},
+},
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__dtlb_load_miss_retired),
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__dtlb_store_miss_retired),
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, HIT,
+						P4_CACHE__itlb_reference_hit),
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, MISS,
+						P4_CACHE__itlb_reference_miss),
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static u64 p4_general_events[PERF_COUNT_HW_MAX] = {
+  /* non-halted CPU clocks */
+  [PERF_COUNT_HW_CPU_CYCLES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_GLOBAL_POWER_EVENTS)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING)),
+
+  /*
+   * retired instructions
+   * in a sake of simplicity we don't use the FSB tagging
+   */
+  [PERF_COUNT_HW_INSTRUCTIONS] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_INSTR_RETIRED)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSNTAG)),
+
+  /* cache hits */
+  [PERF_COUNT_HW_CACHE_REFERENCES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_BSQ_CACHE_REFERENCE)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM)),
+
+  /* cache misses */
+  [PERF_COUNT_HW_CACHE_MISSES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_BSQ_CACHE_REFERENCE)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS)),
+
+  /* branch instructions retired */
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_RETIRED_BRANCH_TYPE)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CALL)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT)),
+
+  /* mispredicted branches retired */
+  [PERF_COUNT_HW_BRANCH_MISSES]	=
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_MISPRED_BRANCH_RETIRED)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS)),
+
+  /* bus ready clocks (cpu is driving #DRDY_DRV\#DRDY_OWN):  */
+  [PERF_COUNT_HW_BUS_CYCLES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_FSB_DATA_ACTIVITY)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN))	|
+	p4_config_pack_cccr(P4_CCCR_EDGE | P4_CCCR_COMPARE),
+};
+
+static struct p4_event_bind *p4_config_get_bind(u64 config)
+{
+	unsigned int evnt = p4_config_unpack_event(config);
+	struct p4_event_bind *bind = NULL;
+
+	if (evnt < ARRAY_SIZE(p4_event_bind_map))
+		bind = &p4_event_bind_map[evnt];
+
+	return bind;
+}
+
+static u64 p4_pmu_event_map(int hw_event)
+{
+	struct p4_event_bind *bind;
+	unsigned int esel;
+	u64 config;
+
+	config = p4_general_events[hw_event];
+	bind = p4_config_get_bind(config);
+	esel = P4_OPCODE_ESEL(bind->opcode);
+	config |= p4_config_pack_cccr(P4_CCCR_ESEL(esel));
+
+	return config;
+}
+
+static int p4_hw_config(struct perf_event *event)
+{
+	int cpu = get_cpu();
+	int rc = 0;
+	unsigned int evnt;
+	u32 escr, cccr;
+
+	/*
+	 * the reason we use cpu that early is that: if we get scheduled
+	 * first time on the same cpu -- we will not need swap thread
+	 * specific flags in config (and will save some cpu cycles)
+	 */
+
+	cccr = p4_default_cccr_conf(cpu);
+	escr = p4_default_escr_conf(cpu, event->attr.exclude_kernel,
+					 event->attr.exclude_user);
+	event->hw.config = p4_config_pack_escr(escr) |
+			   p4_config_pack_cccr(cccr);
+
+	if (p4_ht_active() && p4_ht_thread(cpu))
+		event->hw.config = p4_set_ht_bit(event->hw.config);
+
+	if (event->attr.type == PERF_TYPE_RAW) {
+
+		/* user data may have out-of-bound event index */
+		evnt = p4_config_unpack_event(event->attr.config);
+		if (evnt >= ARRAY_SIZE(p4_event_bind_map)) {
+			rc = -EINVAL;
+			goto out;
+		}
+
+		/*
+		 * We don't control raw events so it's up to the caller
+		 * to pass sane values (and we don't count the thread number
+		 * on HT machine but allow HT-compatible specifics to be
+		 * passed on)
+		 *
+		 * XXX: HT wide things should check perf_paranoid_cpu() &&
+		 *      CAP_SYS_ADMIN
+		 */
+		event->hw.config |= event->attr.config &
+			(p4_config_pack_escr(P4_ESCR_MASK_HT) |
+			 p4_config_pack_cccr(P4_CCCR_MASK_HT));
+	}
+
+	rc = x86_setup_perfctr(event);
+out:
+	put_cpu();
+	return rc;
+}
+
+static inline void p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
+{
+	unsigned long dummy;
+
+	rdmsrl(hwc->config_base + hwc->idx, dummy);
+	if (dummy & P4_CCCR_OVF) {
+		(void)checking_wrmsrl(hwc->config_base + hwc->idx,
+			((u64)dummy) & ~P4_CCCR_OVF);
+	}
+}
+
+static inline void p4_pmu_disable_event(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * If event gets disabled while counter is in overflowed
+	 * state we need to clear P4_CCCR_OVF, otherwise interrupt get
+	 * asserted again and again
+	 */
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
+		(u64)(p4_config_unpack_cccr(hwc->config)) &
+			~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
+}
+
+static void p4_pmu_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx;
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		struct perf_event *event = cpuc->events[idx];
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+		p4_pmu_disable_event(event);
+	}
+}
+
+static void p4_pmu_enable_event(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int thread = p4_ht_config_thread(hwc->config);
+	u64 escr_conf = p4_config_unpack_escr(p4_clear_ht_bit(hwc->config));
+	unsigned int idx = p4_config_unpack_event(hwc->config);
+	unsigned int idx_cache = p4_config_unpack_cache_event(hwc->config);
+	struct p4_event_bind *bind;
+	struct p4_cache_event_bind *bind_cache;
+	u64 escr_addr, cccr;
+
+	bind = &p4_event_bind_map[idx];
+	escr_addr = (u64)bind->escr_msr[thread];
+
+	/*
+	 * - we dont support cascaded counters yet
+	 * - and counter 1 is broken (erratum)
+	 */
+	WARN_ON_ONCE(p4_is_event_cascaded(hwc->config));
+	WARN_ON_ONCE(hwc->idx == 1);
+
+	/* we need a real Event value */
+	escr_conf &= ~P4_ESCR_EVENT_MASK;
+	escr_conf |= P4_ESCR_EVENT(P4_OPCODE_EVNT(bind->opcode));
+
+	cccr = p4_config_unpack_cccr(hwc->config);
+
+	/*
+	 * it could be Cache event so that we need to
+	 * set metrics into additional MSRs
+	 */
+	BUILD_BUG_ON(P4_CACHE__MAX > P4_CCCR_CACHE_OPS_MASK);
+	if (idx_cache > P4_CACHE__NONE &&
+		idx_cache < ARRAY_SIZE(p4_cache_event_bind_map)) {
+		bind_cache = &p4_cache_event_bind_map[idx_cache];
+		(void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind_cache->metric_pebs);
+		(void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind_cache->metric_vert);
+	}
+
+	(void)checking_wrmsrl(escr_addr, escr_conf);
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
+				(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
+}
+
+static void p4_pmu_enable_all(int added)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx;
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		struct perf_event *event = cpuc->events[idx];
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+		p4_pmu_enable_event(event);
+	}
+}
+
+static int p4_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	struct perf_event *event;
+	struct hw_perf_event *hwc;
+	int idx, handled = 0;
+	u64 val;
+
+	data.addr = 0;
+	data.raw = NULL;
+
+	cpuc = &__get_cpu_var(cpu_hw_events);
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		event = cpuc->events[idx];
+		hwc = &event->hw;
+
+		WARN_ON_ONCE(hwc->idx != idx);
+
+		/*
+		 * FIXME: Redundant call, actually not needed
+		 * but just to check if we're screwed
+		 */
+		p4_pmu_clear_cccr_ovf(hwc);
+
+		val = x86_perf_event_update(event);
+		if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
+			continue;
+
+		/*
+		 * event overflow
+		 */
+		handled		= 1;
+		data.period	= event->hw.last_period;
+
+		if (!x86_perf_event_set_period(event))
+			continue;
+		if (perf_event_overflow(event, 1, &data, regs))
+			p4_pmu_disable_event(event);
+	}
+
+	if (handled) {
+		/* p4 quirk: unmask it again */
+		apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);
+		inc_irq_stat(apic_perf_irqs);
+	}
+
+	return handled;
+}
+
+/*
+ * swap thread specific fields according to a thread
+ * we are going to run on
+ */
+static void p4_pmu_swap_config_ts(struct hw_perf_event *hwc, int cpu)
+{
+	u32 escr, cccr;
+
+	/*
+	 * we either lucky and continue on same cpu or no HT support
+	 */
+	if (!p4_should_swap_ts(hwc->config, cpu))
+		return;
+
+	/*
+	 * the event is migrated from an another logical
+	 * cpu, so we need to swap thread specific flags
+	 */
+
+	escr = p4_config_unpack_escr(hwc->config);
+	cccr = p4_config_unpack_cccr(hwc->config);
+
+	if (p4_ht_thread(cpu)) {
+		cccr &= ~P4_CCCR_OVF_PMI_T0;
+		cccr |= P4_CCCR_OVF_PMI_T1;
+		if (escr & P4_ESCR_T0_OS) {
+			escr &= ~P4_ESCR_T0_OS;
+			escr |= P4_ESCR_T1_OS;
+		}
+		if (escr & P4_ESCR_T0_USR) {
+			escr &= ~P4_ESCR_T0_USR;
+			escr |= P4_ESCR_T1_USR;
+		}
+		hwc->config  = p4_config_pack_escr(escr);
+		hwc->config |= p4_config_pack_cccr(cccr);
+		hwc->config |= P4_CONFIG_HT;
+	} else {
+		cccr &= ~P4_CCCR_OVF_PMI_T1;
+		cccr |= P4_CCCR_OVF_PMI_T0;
+		if (escr & P4_ESCR_T1_OS) {
+			escr &= ~P4_ESCR_T1_OS;
+			escr |= P4_ESCR_T0_OS;
+		}
+		if (escr & P4_ESCR_T1_USR) {
+			escr &= ~P4_ESCR_T1_USR;
+			escr |= P4_ESCR_T0_USR;
+		}
+		hwc->config  = p4_config_pack_escr(escr);
+		hwc->config |= p4_config_pack_cccr(cccr);
+		hwc->config &= ~P4_CONFIG_HT;
+	}
+}
+
+/*
+ * ESCR address hashing is tricky, ESCRs are not sequential
+ * in memory but all starts from MSR_P4_BSU_ESCR0 (0x03e0) and
+ * the metric between any ESCRs is laid in range [0xa0,0xe1]
+ *
+ * so we make ~70% filled hashtable
+ */
+
+#define P4_ESCR_MSR_BASE		0x000003a0
+#define P4_ESCR_MSR_MAX			0x000003e1
+#define P4_ESCR_MSR_TABLE_SIZE		(P4_ESCR_MSR_MAX - P4_ESCR_MSR_BASE + 1)
+#define P4_ESCR_MSR_IDX(msr)		(msr - P4_ESCR_MSR_BASE)
+#define P4_ESCR_MSR_TABLE_ENTRY(msr)	[P4_ESCR_MSR_IDX(msr)] = msr
+
+static const unsigned int p4_escr_table[P4_ESCR_MSR_TABLE_SIZE] = {
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_ALF_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_ALF_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_BPU_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_BPU_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_BSU_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_BSU_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR2),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR3),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR4),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR5),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_DAC_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_DAC_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FIRM_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FIRM_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FLAME_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FLAME_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FSB_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FSB_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IQ_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IQ_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IS_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IS_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_ITLB_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_ITLB_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IX_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IX_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_MOB_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_MOB_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_MS_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_MS_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_PMH_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_PMH_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_RAT_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_RAT_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_SAAT_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_SAAT_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_SSU_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_SSU_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_TBPU_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_TBPU_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_TC_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_TC_ESCR1),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_U2L_ESCR0),
+	P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_U2L_ESCR1),
+};
+
+static int p4_get_escr_idx(unsigned int addr)
+{
+	unsigned int idx = P4_ESCR_MSR_IDX(addr);
+
+	if (unlikely(idx >= P4_ESCR_MSR_TABLE_SIZE ||
+			!p4_escr_table[idx])) {
+		WARN_ONCE(1, "P4 PMU: Wrong address passed: %x\n", addr);
+		return -1;
+	}
+
+	return idx;
+}
+
+static int p4_next_cntr(int thread, unsigned long *used_mask,
+			struct p4_event_bind *bind)
+{
+	int i, j;
+
+	for (i = 0; i < P4_CNTR_LIMIT; i++) {
+		j = bind->cntr[thread][i];
+		if (j != -1 && !test_bit(j, used_mask))
+			return j;
+	}
+
+	return -1;
+}
+
+static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
+{
+	unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	unsigned long escr_mask[BITS_TO_LONGS(P4_ESCR_MSR_TABLE_SIZE)];
+	int cpu = raw_smp_processor_id();
+	struct hw_perf_event *hwc;
+	struct p4_event_bind *bind;
+	unsigned int i, thread, num;
+	int cntr_idx, escr_idx;
+
+	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
+	bitmap_zero(escr_mask, P4_ESCR_MSR_TABLE_SIZE);
+
+	for (i = 0, num = n; i < n; i++, num--) {
+
+		hwc = &cpuc->event_list[i]->hw;
+		thread = p4_ht_thread(cpu);
+		bind = p4_config_get_bind(hwc->config);
+		escr_idx = p4_get_escr_idx(bind->escr_msr[thread]);
+		if (unlikely(escr_idx == -1))
+			goto done;
+
+		if (hwc->idx != -1 && !p4_should_swap_ts(hwc->config, cpu)) {
+			cntr_idx = hwc->idx;
+			if (assign)
+				assign[i] = hwc->idx;
+			goto reserve;
+		}
+
+		cntr_idx = p4_next_cntr(thread, used_mask, bind);
+		if (cntr_idx == -1 || test_bit(escr_idx, escr_mask))
+			goto done;
+
+		p4_pmu_swap_config_ts(hwc, cpu);
+		if (assign)
+			assign[i] = cntr_idx;
+reserve:
+		set_bit(cntr_idx, used_mask);
+		set_bit(escr_idx, escr_mask);
+	}
+
+done:
+	return num ? -ENOSPC : 0;
+}
+
+static __initconst const struct x86_pmu p4_pmu = {
+	.name			= "Netburst P4/Xeon",
+	.handle_irq		= p4_pmu_handle_irq,
+	.disable_all		= p4_pmu_disable_all,
+	.enable_all		= p4_pmu_enable_all,
+	.enable			= p4_pmu_enable_event,
+	.disable		= p4_pmu_disable_event,
+	.eventsel		= MSR_P4_BPU_CCCR0,
+	.perfctr		= MSR_P4_BPU_PERFCTR0,
+	.event_map		= p4_pmu_event_map,
+	.max_events		= ARRAY_SIZE(p4_general_events),
+	.get_event_constraints	= x86_get_event_constraints,
+	/*
+	 * IF HT disabled we may need to use all
+	 * ARCH_P4_MAX_CCCR counters simulaneously
+	 * though leave it restricted at moment assuming
+	 * HT is on
+	 */
+	.num_counters		= ARCH_P4_MAX_CCCR,
+	.apic			= 1,
+	.cntval_bits		= 40,
+	.cntval_mask		= (1ULL << 40) - 1,
+	.max_period		= (1ULL << 39) - 1,
+	.hw_config		= p4_hw_config,
+	.schedule_events	= p4_pmu_schedule_events,
+};
+
+static __init int p4_pmu_init(void)
+{
+	unsigned int low, high;
+
+	/* If we get stripped -- indexig fails */
+	BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC);
+
+	rdmsr(MSR_IA32_MISC_ENABLE, low, high);
+	if (!(low & (1 << 7))) {
+		pr_cont("unsupported Netburst CPU model %d ",
+			boot_cpu_data.x86_model);
+		return -ENODEV;
+	}
+
+	memcpy(hw_cache_event_ids, p4_hw_cache_event_ids,
+		sizeof(hw_cache_event_ids));
+
+	pr_cont("Netburst events, ");
+
+	x86_pmu = p4_pmu;
+
+	return 0;
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */

arch/x86/kernel/cpu/perf_event_p6.c

diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index a330485..34ba07b 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -27,24 +27,6 @@
  */
 #define P6_NOP_EVENT			0x0000002EULL
 
-static u64 p6_pmu_raw_event(u64 hw_event)
-{
-#define P6_EVNTSEL_EVENT_MASK		0x000000FFULL
-#define P6_EVNTSEL_UNIT_MASK		0x0000FF00ULL
-#define P6_EVNTSEL_EDGE_MASK		0x00040000ULL
-#define P6_EVNTSEL_INV_MASK		0x00800000ULL
-#define P6_EVNTSEL_REG_MASK		0xFF000000ULL
-
-#define P6_EVNTSEL_MASK			\
-	(P6_EVNTSEL_EVENT_MASK |	\
-	 P6_EVNTSEL_UNIT_MASK  |	\
-	 P6_EVNTSEL_EDGE_MASK  |	\
-	 P6_EVNTSEL_INV_MASK   |	\
-	 P6_EVNTSEL_REG_MASK)
-
-	return hw_event & P6_EVNTSEL_MASK;
-}
-
 static struct event_constraint p6_event_constraints[] =
 {
 	INTEL_EVENT_CONSTRAINT(0xc1, 0x1),	/* FLOPS */
@@ -66,7 +48,7 @@
 	wrmsrl(MSR_P6_EVNTSEL0, val);
 }
 
-static void p6_pmu_enable_all(void)
+static void p6_pmu_enable_all(int added)
 {
 	unsigned long val;
 
@@ -102,22 +84,23 @@
 	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
 }
 
-static __initconst struct x86_pmu p6_pmu = {
+static __initconst const struct x86_pmu p6_pmu = {
 	.name			= "p6",
 	.handle_irq		= x86_pmu_handle_irq,
 	.disable_all		= p6_pmu_disable_all,
 	.enable_all		= p6_pmu_enable_all,
 	.enable			= p6_pmu_enable_event,
 	.disable		= p6_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_P6_EVNTSEL0,
 	.perfctr		= MSR_P6_PERFCTR0,
 	.event_map		= p6_pmu_event_map,
-	.raw_event		= p6_pmu_raw_event,
 	.max_events		= ARRAY_SIZE(p6_perfmon_event_map),
 	.apic			= 1,
 	.max_period		= (1ULL << 31) - 1,
 	.version		= 0,
-	.num_events		= 2,
+	.num_counters		= 2,
 	/*
 	 * Events have 40 bits implemented. However they are designed such
 	 * that bits [32-39] are sign extensions of bit 31. As such the
@@ -125,8 +108,8 @@
 	 *
 	 * See IA-32 Intel Architecture Software developer manual Vol 3B
 	 */
-	.event_bits		= 32,
-	.event_mask		= (1ULL << 32) - 1,
+	.cntval_bits		= 32,
+	.cntval_mask		= (1ULL << 32) - 1,
 	.get_event_constraints	= x86_get_event_constraints,
 	.event_constraints	= p6_event_constraints,
 };

arch/x86/kernel/ds.c

diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
deleted file mode 100644
index 1c47390..0000000
--- a/arch/x86/kernel/ds.c
+++ /dev/null
@@ -1,1437 +0,0 @@
-/*
- * Debug Store support
- *
- * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for branch trace store (BTS) and
- * precise-event based sampling (PEBS).
- *
- * It manages:
- * - DS and BTS hardware configuration
- * - buffer overflow handling (to be done)
- * - buffer access
- *
- * It does not do:
- * - security checking (is the caller allowed to trace the task)
- * - buffer allocation (memory accounting)
- *
- *
- * Copyright (C) 2007-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
- */
-
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/mm.h>
-#include <linux/trace_clock.h>
-
-#include <asm/ds.h>
-
-#include "ds_selftest.h"
-
-/*
- * The configuration for a particular DS hardware implementation:
- */
-struct ds_configuration {
-	/* The name of the configuration: */
-	const char		*name;
-
-	/* The size of pointer-typed fields in DS, BTS, and PEBS: */
-	unsigned char		sizeof_ptr_field;
-
-	/* The size of a BTS/PEBS record in bytes: */
-	unsigned char		sizeof_rec[2];
-
-	/* The number of pebs counter reset values in the DS structure. */
-	unsigned char		nr_counter_reset;
-
-	/* Control bit-masks indexed by enum ds_feature: */
-	unsigned long		ctl[dsf_ctl_max];
-};
-static struct ds_configuration ds_cfg __read_mostly;
-
-
-/* Maximal size of a DS configuration: */
-#define MAX_SIZEOF_DS		0x80
-
-/* Maximal size of a BTS record: */
-#define MAX_SIZEOF_BTS		(3 * 8)
-
-/* BTS and PEBS buffer alignment: */
-#define DS_ALIGNMENT		(1 << 3)
-
-/* Number of buffer pointers in DS: */
-#define NUM_DS_PTR_FIELDS	8
-
-/* Size of a pebs reset value in DS: */
-#define PEBS_RESET_FIELD_SIZE	8
-
-/* Mask of control bits in the DS MSR register: */
-#define BTS_CONTROL				  \
-	( ds_cfg.ctl[dsf_bts]			| \
-	  ds_cfg.ctl[dsf_bts_kernel]		| \
-	  ds_cfg.ctl[dsf_bts_user]		| \
-	  ds_cfg.ctl[dsf_bts_overflow] )
-
-/*
- * A BTS or PEBS tracer.
- *
- * This holds the configuration of the tracer and serves as a handle
- * to identify tracers.
- */
-struct ds_tracer {
-	/* The DS context (partially) owned by this tracer. */
-	struct ds_context	*context;
-	/* The buffer provided on ds_request() and its size in bytes. */
-	void			*buffer;
-	size_t			size;
-};
-
-struct bts_tracer {
-	/* The common DS part: */
-	struct ds_tracer	ds;
-
-	/* The trace including the DS configuration: */
-	struct bts_trace	trace;
-
-	/* Buffer overflow notification function: */
-	bts_ovfl_callback_t	ovfl;
-
-	/* Active flags affecting trace collection. */
-	unsigned int		flags;
-};
-
-struct pebs_tracer {
-	/* The common DS part: */
-	struct ds_tracer	ds;
-
-	/* The trace including the DS configuration: */
-	struct pebs_trace	trace;
-
-	/* Buffer overflow notification function: */
-	pebs_ovfl_callback_t	ovfl;
-};
-
-/*
- * Debug Store (DS) save area configuration (see Intel64 and IA32
- * Architectures Software Developer's Manual, section 18.5)
- *
- * The DS configuration consists of the following fields; different
- * architetures vary in the size of those fields.
- *
- * - double-word aligned base linear address of the BTS buffer
- * - write pointer into the BTS buffer
- * - end linear address of the BTS buffer (one byte beyond the end of
- *   the buffer)
- * - interrupt pointer into BTS buffer
- *   (interrupt occurs when write pointer passes interrupt pointer)
- * - double-word aligned base linear address of the PEBS buffer
- * - write pointer into the PEBS buffer
- * - end linear address of the PEBS buffer (one byte beyond the end of
- *   the buffer)
- * - interrupt pointer into PEBS buffer
- *   (interrupt occurs when write pointer passes interrupt pointer)
- * - value to which counter is reset following counter overflow
- *
- * Later architectures use 64bit pointers throughout, whereas earlier
- * architectures use 32bit pointers in 32bit mode.
- *
- *
- * We compute the base address for the first 8 fields based on:
- * - the field size stored in the DS configuration
- * - the relative field position
- * - an offset giving the start of the respective region
- *
- * This offset is further used to index various arrays holding
- * information for BTS and PEBS at the respective index.
- *
- * On later 32bit processors, we only access the lower 32bit of the
- * 64bit pointer fields. The upper halves will be zeroed out.
- */
-
-enum ds_field {
-	ds_buffer_base = 0,
-	ds_index,
-	ds_absolute_maximum,
-	ds_interrupt_threshold,
-};
-
-enum ds_qualifier {
-	ds_bts = 0,
-	ds_pebs
-};
-
-static inline unsigned long
-ds_get(const unsigned char *base, enum ds_qualifier qual, enum ds_field field)
-{
-	base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual)));
-	return *(unsigned long *)base;
-}
-
-static inline void
-ds_set(unsigned char *base, enum ds_qualifier qual, enum ds_field field,
-       unsigned long value)
-{
-	base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual)));
-	(*(unsigned long *)base) = value;
-}
-
-
-/*
- * Locking is done only for allocating BTS or PEBS resources.
- */
-static DEFINE_SPINLOCK(ds_lock);
-
-/*
- * We either support (system-wide) per-cpu or per-thread allocation.
- * We distinguish the two based on the task_struct pointer, where a
- * NULL pointer indicates per-cpu allocation for the current cpu.
- *
- * Allocations are use-counted. As soon as resources are allocated,
- * further allocations must be of the same type (per-cpu or
- * per-thread). We model this by counting allocations (i.e. the number
- * of tracers of a certain type) for one type negatively:
- *   =0  no tracers
- *   >0  number of per-thread tracers
- *   <0  number of per-cpu tracers
- *
- * Tracers essentially gives the number of ds contexts for a certain
- * type of allocation.
- */
-static atomic_t tracers = ATOMIC_INIT(0);
-
-static inline int get_tracer(struct task_struct *task)
-{
-	int error;
-
-	spin_lock_irq(&ds_lock);
-
-	if (task) {
-		error = -EPERM;
-		if (atomic_read(&tracers) < 0)
-			goto out;
-		atomic_inc(&tracers);
-	} else {
-		error = -EPERM;
-		if (atomic_read(&tracers) > 0)
-			goto out;
-		atomic_dec(&tracers);
-	}
-
-	error = 0;
-out:
-	spin_unlock_irq(&ds_lock);
-	return error;
-}
-
-static inline void put_tracer(struct task_struct *task)
-{
-	if (task)
-		atomic_dec(&tracers);
-	else
-		atomic_inc(&tracers);
-}
-
-/*
- * The DS context is either attached to a thread or to a cpu:
- * - in the former case, the thread_struct contains a pointer to the
- *   attached context.
- * - in the latter case, we use a static array of per-cpu context
- *   pointers.
- *
- * Contexts are use-counted. They are allocated on first access and
- * deallocated when the last user puts the context.
- */
-struct ds_context {
-	/* The DS configuration; goes into MSR_IA32_DS_AREA: */
-	unsigned char		ds[MAX_SIZEOF_DS];
-
-	/* The owner of the BTS and PEBS configuration, respectively: */
-	struct bts_tracer	*bts_master;
-	struct pebs_tracer	*pebs_master;
-
-	/* Use count: */
-	unsigned long		count;
-
-	/* Pointer to the context pointer field: */
-	struct ds_context	**this;
-
-	/* The traced task; NULL for cpu tracing: */
-	struct task_struct	*task;
-
-	/* The traced cpu; only valid if task is NULL: */
-	int			cpu;
-};
-
-static DEFINE_PER_CPU(struct ds_context *, cpu_ds_context);
-
-
-static struct ds_context *ds_get_context(struct task_struct *task, int cpu)
-{
-	struct ds_context **p_context =
-		(task ? &task->thread.ds_ctx : &per_cpu(cpu_ds_context, cpu));
-	struct ds_context *context = NULL;
-	struct ds_context *new_context = NULL;
-
-	/* Chances are small that we already have a context. */
-	new_context = kzalloc(sizeof(*new_context), GFP_KERNEL);
-	if (!new_context)
-		return NULL;
-
-	spin_lock_irq(&ds_lock);
-
-	context = *p_context;
-	if (likely(!context)) {
-		context = new_context;
-
-		context->this = p_context;
-		context->task = task;
-		context->cpu = cpu;
-		context->count = 0;
-
-		*p_context = context;
-	}
-
-	context->count++;
-
-	spin_unlock_irq(&ds_lock);
-
-	if (context != new_context)
-		kfree(new_context);
-
-	return context;
-}
-
-static void ds_put_context(struct ds_context *context)
-{
-	struct task_struct *task;
-	unsigned long irq;
-
-	if (!context)
-		return;
-
-	spin_lock_irqsave(&ds_lock, irq);
-
-	if (--context->count) {
-		spin_unlock_irqrestore(&ds_lock, irq);
-		return;
-	}
-
-	*(context->this) = NULL;
-
-	task = context->task;
-
-	if (task)
-		clear_tsk_thread_flag(task, TIF_DS_AREA_MSR);
-
-	/*
-	 * We leave the (now dangling) pointer to the DS configuration in
-	 * the DS_AREA msr. This is as good or as bad as replacing it with
-	 * NULL - the hardware would crash if we enabled tracing.
-	 *
-	 * This saves us some problems with having to write an msr on a
-	 * different cpu while preventing others from doing the same for the
-	 * next context for that same cpu.
-	 */
-
-	spin_unlock_irqrestore(&ds_lock, irq);
-
-	/* The context might still be in use for context switching. */
-	if (task && (task != current))
-		wait_task_context_switch(task);
-
-	kfree(context);
-}
-
-static void ds_install_ds_area(struct ds_context *context)
-{
-	unsigned long ds;
-
-	ds = (unsigned long)context->ds;
-
-	/*
-	 * There is a race between the bts master and the pebs master.
-	 *
-	 * The thread/cpu access is synchronized via get/put_cpu() for
-	 * task tracing and via wrmsr_on_cpu for cpu tracing.
-	 *
-	 * If bts and pebs are collected for the same task or same cpu,
-	 * the same confiuration is written twice.
-	 */
-	if (context->task) {
-		get_cpu();
-		if (context->task == current)
-			wrmsrl(MSR_IA32_DS_AREA, ds);
-		set_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
-		put_cpu();
-	} else
-		wrmsr_on_cpu(context->cpu, MSR_IA32_DS_AREA,
-			     (u32)((u64)ds), (u32)((u64)ds >> 32));
-}
-
-/*
- * Call the tracer's callback on a buffer overflow.
- *
- * context: the ds context
- * qual: the buffer type
- */
-static void ds_overflow(struct ds_context *context, enum ds_qualifier qual)
-{
-	switch (qual) {
-	case ds_bts:
-		if (context->bts_master &&
-		    context->bts_master->ovfl)
-			context->bts_master->ovfl(context->bts_master);
-		break;
-	case ds_pebs:
-		if (context->pebs_master &&
-		    context->pebs_master->ovfl)
-			context->pebs_master->ovfl(context->pebs_master);
-		break;
-	}
-}
-
-
-/*
- * Write raw data into the BTS or PEBS buffer.
- *
- * The remainder of any partially written record is zeroed out.
- *
- * context: the DS context
- * qual:    the buffer type
- * record:  the data to write
- * size:    the size of the data
- */
-static int ds_write(struct ds_context *context, enum ds_qualifier qual,
-		    const void *record, size_t size)
-{
-	int bytes_written = 0;
-
-	if (!record)
-		return -EINVAL;
-
-	while (size) {
-		unsigned long base, index, end, write_end, int_th;
-		unsigned long write_size, adj_write_size;
-
-		/*
-		 * Write as much as possible without producing an
-		 * overflow interrupt.
-		 *
-		 * Interrupt_threshold must either be
-		 * - bigger than absolute_maximum or
-		 * - point to a record between buffer_base and absolute_maximum
-		 *
-		 * Index points to a valid record.
-		 */
-		base   = ds_get(context->ds, qual, ds_buffer_base);
-		index  = ds_get(context->ds, qual, ds_index);
-		end    = ds_get(context->ds, qual, ds_absolute_maximum);
-		int_th = ds_get(context->ds, qual, ds_interrupt_threshold);
-
-		write_end = min(end, int_th);
-
-		/*
-		 * If we are already beyond the interrupt threshold,
-		 * we fill the entire buffer.
-		 */
-		if (write_end <= index)
-			write_end = end;
-
-		if (write_end <= index)
-			break;
-
-		write_size = min((unsigned long) size, write_end - index);
-		memcpy((void *)index, record, write_size);
-
-		record = (const char *)record + write_size;
-		size -= write_size;
-		bytes_written += write_size;
-
-		adj_write_size = write_size / ds_cfg.sizeof_rec[qual];
-		adj_write_size *= ds_cfg.sizeof_rec[qual];
-
-		/* Zero out trailing bytes. */
-		memset((char *)index + write_size, 0,
-		       adj_write_size - write_size);
-		index += adj_write_size;
-
-		if (index >= end)
-			index = base;
-		ds_set(context->ds, qual, ds_index, index);
-
-		if (index >= int_th)
-			ds_overflow(context, qual);
-	}
-
-	return bytes_written;
-}
-
-
-/*
- * Branch Trace Store (BTS) uses the following format. Different
- * architectures vary in the size of those fields.
- * - source linear address
- * - destination linear address
- * - flags
- *
- * Later architectures use 64bit pointers throughout, whereas earlier
- * architectures use 32bit pointers in 32bit mode.
- *
- * We compute the base address for the fields based on:
- * - the field size stored in the DS configuration
- * - the relative field position
- *
- * In order to store additional information in the BTS buffer, we use
- * a special source address to indicate that the record requires
- * special interpretation.
- *
- * Netburst indicated via a bit in the flags field whether the branch
- * was predicted; this is ignored.
- *
- * We use two levels of abstraction:
- * - the raw data level defined here
- * - an arch-independent level defined in ds.h
- */
-
-enum bts_field {
-	bts_from,
-	bts_to,
-	bts_flags,
-
-	bts_qual		= bts_from,
-	bts_clock		= bts_to,
-	bts_pid			= bts_flags,
-
-	bts_qual_mask		= (bts_qual_max - 1),
-	bts_escape		= ((unsigned long)-1 & ~bts_qual_mask)
-};
-
-static inline unsigned long bts_get(const char *base, unsigned long field)
-{
-	base += (ds_cfg.sizeof_ptr_field * field);
-	return *(unsigned long *)base;
-}
-
-static inline void bts_set(char *base, unsigned long field, unsigned long val)
-{
-	base += (ds_cfg.sizeof_ptr_field * field);
-	(*(unsigned long *)base) = val;
-}
-
-
-/*
- * The raw BTS data is architecture dependent.
- *
- * For higher-level users, we give an arch-independent view.
- * - ds.h defines struct bts_struct
- * - bts_read translates one raw bts record into a bts_struct
- * - bts_write translates one bts_struct into the raw format and
- *   writes it into the top of the parameter tracer's buffer.
- *
- * return: bytes read/written on success; -Eerrno, otherwise
- */
-static int
-bts_read(struct bts_tracer *tracer, const void *at, struct bts_struct *out)
-{
-	if (!tracer)
-		return -EINVAL;
-
-	if (at < tracer->trace.ds.begin)
-		return -EINVAL;
-
-	if (tracer->trace.ds.end < (at + tracer->trace.ds.size))
-		return -EINVAL;
-
-	memset(out, 0, sizeof(*out));
-	if ((bts_get(at, bts_qual) & ~bts_qual_mask) == bts_escape) {
-		out->qualifier = (bts_get(at, bts_qual) & bts_qual_mask);
-		out->variant.event.clock = bts_get(at, bts_clock);
-		out->variant.event.pid = bts_get(at, bts_pid);
-	} else {
-		out->qualifier = bts_branch;
-		out->variant.lbr.from = bts_get(at, bts_from);
-		out->variant.lbr.to   = bts_get(at, bts_to);
-
-		if (!out->variant.lbr.from && !out->variant.lbr.to)
-			out->qualifier = bts_invalid;
-	}
-
-	return ds_cfg.sizeof_rec[ds_bts];
-}
-
-static int bts_write(struct bts_tracer *tracer, const struct bts_struct *in)
-{
-	unsigned char raw[MAX_SIZEOF_BTS];
-
-	if (!tracer)
-		return -EINVAL;
-
-	if (MAX_SIZEOF_BTS < ds_cfg.sizeof_rec[ds_bts])
-		return -EOVERFLOW;
-
-	switch (in->qualifier) {
-	case bts_invalid:
-		bts_set(raw, bts_from, 0);
-		bts_set(raw, bts_to, 0);
-		bts_set(raw, bts_flags, 0);
-		break;
-	case bts_branch:
-		bts_set(raw, bts_from, in->variant.lbr.from);
-		bts_set(raw, bts_to,   in->variant.lbr.to);
-		bts_set(raw, bts_flags, 0);
-		break;
-	case bts_task_arrives:
-	case bts_task_departs:
-		bts_set(raw, bts_qual, (bts_escape | in->qualifier));
-		bts_set(raw, bts_clock, in->variant.event.clock);
-		bts_set(raw, bts_pid, in->variant.event.pid);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return ds_write(tracer->ds.context, ds_bts, raw,
-			ds_cfg.sizeof_rec[ds_bts]);
-}
-
-
-static void ds_write_config(struct ds_context *context,
-			    struct ds_trace *cfg, enum ds_qualifier qual)
-{
-	unsigned char *ds = context->ds;
-
-	ds_set(ds, qual, ds_buffer_base, (unsigned long)cfg->begin);
-	ds_set(ds, qual, ds_index, (unsigned long)cfg->top);
-	ds_set(ds, qual, ds_absolute_maximum, (unsigned long)cfg->end);
-	ds_set(ds, qual, ds_interrupt_threshold, (unsigned long)cfg->ith);
-}
-
-static void ds_read_config(struct ds_context *context,
-			   struct ds_trace *cfg, enum ds_qualifier qual)
-{
-	unsigned char *ds = context->ds;
-
-	cfg->begin = (void *)ds_get(ds, qual, ds_buffer_base);
-	cfg->top = (void *)ds_get(ds, qual, ds_index);
-	cfg->end = (void *)ds_get(ds, qual, ds_absolute_maximum);
-	cfg->ith = (void *)ds_get(ds, qual, ds_interrupt_threshold);
-}
-
-static void ds_init_ds_trace(struct ds_trace *trace, enum ds_qualifier qual,
-			     void *base, size_t size, size_t ith,
-			     unsigned int flags) {
-	unsigned long buffer, adj;
-
-	/*
-	 * Adjust the buffer address and size to meet alignment
-	 * constraints:
-	 * - buffer is double-word aligned
-	 * - size is multiple of record size
-	 *
-	 * We checked the size at the very beginning; we have enough
-	 * space to do the adjustment.
-	 */
-	buffer = (unsigned long)base;
-
-	adj = ALIGN(buffer, DS_ALIGNMENT) - buffer;
-	buffer += adj;
-	size   -= adj;
-
-	trace->n = size / ds_cfg.sizeof_rec[qual];
-	trace->size = ds_cfg.sizeof_rec[qual];
-
-	size = (trace->n * trace->size);
-
-	trace->begin = (void *)buffer;
-	trace->top = trace->begin;
-	trace->end = (void *)(buffer + size);
-	/*
-	 * The value for 'no threshold' is -1, which will set the
-	 * threshold outside of the buffer, just like we want it.
-	 */
-	ith *= ds_cfg.sizeof_rec[qual];
-	trace->ith = (void *)(buffer + size - ith);
-
-	trace->flags = flags;
-}
-
-
-static int ds_request(struct ds_tracer *tracer, struct ds_trace *trace,
-		      enum ds_qualifier qual, struct task_struct *task,
-		      int cpu, void *base, size_t size, size_t th)
-{
-	struct ds_context *context;
-	int error;
-	size_t req_size;
-
-	error = -EOPNOTSUPP;
-	if (!ds_cfg.sizeof_rec[qual])
-		goto out;
-
-	error = -EINVAL;
-	if (!base)
-		goto out;
-
-	req_size = ds_cfg.sizeof_rec[qual];
-	/* We might need space for alignment adjustments. */
-	if (!IS_ALIGNED((unsigned long)base, DS_ALIGNMENT))
-		req_size += DS_ALIGNMENT;
-
-	error = -EINVAL;
-	if (size < req_size)
-		goto out;
-
-	if (th != (size_t)-1) {
-		th *= ds_cfg.sizeof_rec[qual];
-
-		error = -EINVAL;
-		if (size <= th)
-			goto out;
-	}
-
-	tracer->buffer = base;
-	tracer->size = size;
-
-	error = -ENOMEM;
-	context = ds_get_context(task, cpu);
-	if (!context)
-		goto out;
-	tracer->context = context;
-
-	/*
-	 * Defer any tracer-specific initialization work for the context until
-	 * context ownership has been clarified.
-	 */
-
-	error = 0;
- out:
-	return error;
-}
-
-static struct bts_tracer *ds_request_bts(struct task_struct *task, int cpu,
-					 void *base, size_t size,
-					 bts_ovfl_callback_t ovfl, size_t th,
-					 unsigned int flags)
-{
-	struct bts_tracer *tracer;
-	int error;
-
-	/* Buffer overflow notification is not yet implemented. */
-	error = -EOPNOTSUPP;
-	if (ovfl)
-		goto out;
-
-	error = get_tracer(task);
-	if (error < 0)
-		goto out;
-
-	error = -ENOMEM;
-	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
-	if (!tracer)
-		goto out_put_tracer;
-	tracer->ovfl = ovfl;
-
-	/* Do some more error checking and acquire a tracing context. */
-	error = ds_request(&tracer->ds, &tracer->trace.ds,
-			   ds_bts, task, cpu, base, size, th);
-	if (error < 0)
-		goto out_tracer;
-
-	/* Claim the bts part of the tracing context we acquired above. */
-	spin_lock_irq(&ds_lock);
-
-	error = -EPERM;
-	if (tracer->ds.context->bts_master)
-		goto out_unlock;
-	tracer->ds.context->bts_master = tracer;
-
-	spin_unlock_irq(&ds_lock);
-
-	/*
-	 * Now that we own the bts part of the context, let's complete the
-	 * initialization for that part.
-	 */
-	ds_init_ds_trace(&tracer->trace.ds, ds_bts, base, size, th, flags);
-	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
-	ds_install_ds_area(tracer->ds.context);
-
-	tracer->trace.read  = bts_read;
-	tracer->trace.write = bts_write;
-
-	/* Start tracing. */
-	ds_resume_bts(tracer);
-
-	return tracer;
-
- out_unlock:
-	spin_unlock_irq(&ds_lock);
-	ds_put_context(tracer->ds.context);
- out_tracer:
-	kfree(tracer);
- out_put_tracer:
-	put_tracer(task);
- out:
-	return ERR_PTR(error);
-}
-
-struct bts_tracer *ds_request_bts_task(struct task_struct *task,
-				       void *base, size_t size,
-				       bts_ovfl_callback_t ovfl,
-				       size_t th, unsigned int flags)
-{
-	return ds_request_bts(task, 0, base, size, ovfl, th, flags);
-}
-
-struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
-				      bts_ovfl_callback_t ovfl,
-				      size_t th, unsigned int flags)
-{
-	return ds_request_bts(NULL, cpu, base, size, ovfl, th, flags);
-}
-
-static struct pebs_tracer *ds_request_pebs(struct task_struct *task, int cpu,
-					   void *base, size_t size,
-					   pebs_ovfl_callback_t ovfl, size_t th,
-					   unsigned int flags)
-{
-	struct pebs_tracer *tracer;
-	int error;
-
-	/* Buffer overflow notification is not yet implemented. */
-	error = -EOPNOTSUPP;
-	if (ovfl)
-		goto out;
-
-	error = get_tracer(task);
-	if (error < 0)
-		goto out;
-
-	error = -ENOMEM;
-	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
-	if (!tracer)
-		goto out_put_tracer;
-	tracer->ovfl = ovfl;
-
-	/* Do some more error checking and acquire a tracing context. */
-	error = ds_request(&tracer->ds, &tracer->trace.ds,
-			   ds_pebs, task, cpu, base, size, th);
-	if (error < 0)
-		goto out_tracer;
-
-	/* Claim the pebs part of the tracing context we acquired above. */
-	spin_lock_irq(&ds_lock);
-
-	error = -EPERM;
-	if (tracer->ds.context->pebs_master)
-		goto out_unlock;
-	tracer->ds.context->pebs_master = tracer;
-
-	spin_unlock_irq(&ds_lock);
-
-	/*
-	 * Now that we own the pebs part of the context, let's complete the
-	 * initialization for that part.
-	 */
-	ds_init_ds_trace(&tracer->trace.ds, ds_pebs, base, size, th, flags);
-	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
-	ds_install_ds_area(tracer->ds.context);
-
-	/* Start tracing. */
-	ds_resume_pebs(tracer);
-
-	return tracer;
-
- out_unlock:
-	spin_unlock_irq(&ds_lock);
-	ds_put_context(tracer->ds.context);
- out_tracer:
-	kfree(tracer);
- out_put_tracer:
-	put_tracer(task);
- out:
-	return ERR_PTR(error);
-}
-
-struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
-					 void *base, size_t size,
-					 pebs_ovfl_callback_t ovfl,
-					 size_t th, unsigned int flags)
-{
-	return ds_request_pebs(task, 0, base, size, ovfl, th, flags);
-}
-
-struct pebs_tracer *ds_request_pebs_cpu(int cpu, void *base, size_t size,
-					pebs_ovfl_callback_t ovfl,
-					size_t th, unsigned int flags)
-{
-	return ds_request_pebs(NULL, cpu, base, size, ovfl, th, flags);
-}
-
-static void ds_free_bts(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-
-	task = tracer->ds.context->task;
-
-	WARN_ON_ONCE(tracer->ds.context->bts_master != tracer);
-	tracer->ds.context->bts_master = NULL;
-
-	/* Make sure tracing stopped and the tracer is not in use. */
-	if (task && (task != current))
-		wait_task_context_switch(task);
-
-	ds_put_context(tracer->ds.context);
-	put_tracer(task);
-
-	kfree(tracer);
-}
-
-void ds_release_bts(struct bts_tracer *tracer)
-{
-	might_sleep();
-
-	if (!tracer)
-		return;
-
-	ds_suspend_bts(tracer);
-	ds_free_bts(tracer);
-}
-
-int ds_release_bts_noirq(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long irq;
-	int error;
-
-	if (!tracer)
-		return 0;
-
-	task = tracer->ds.context->task;
-
-	local_irq_save(irq);
-
-	error = -EPERM;
-	if (!task &&
-	    (tracer->ds.context->cpu != smp_processor_id()))
-		goto out;
-
-	error = -EPERM;
-	if (task && (task != current))
-		goto out;
-
-	ds_suspend_bts_noirq(tracer);
-	ds_free_bts(tracer);
-
-	error = 0;
- out:
-	local_irq_restore(irq);
-	return error;
-}
-
-static void update_task_debugctlmsr(struct task_struct *task,
-				    unsigned long debugctlmsr)
-{
-	task->thread.debugctlmsr = debugctlmsr;
-
-	get_cpu();
-	if (task == current)
-		update_debugctlmsr(debugctlmsr);
-	put_cpu();
-}
-
-void ds_suspend_bts(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long debugctlmsr;
-	int cpu;
-
-	if (!tracer)
-		return;
-
-	tracer->flags = 0;
-
-	task = tracer->ds.context->task;
-	cpu  = tracer->ds.context->cpu;
-
-	WARN_ON(!task && irqs_disabled());
-
-	debugctlmsr = (task ?
-		       task->thread.debugctlmsr :
-		       get_debugctlmsr_on_cpu(cpu));
-	debugctlmsr &= ~BTS_CONTROL;
-
-	if (task)
-		update_task_debugctlmsr(task, debugctlmsr);
-	else
-		update_debugctlmsr_on_cpu(cpu, debugctlmsr);
-}
-
-int ds_suspend_bts_noirq(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long debugctlmsr, irq;
-	int cpu, error = 0;
-
-	if (!tracer)
-		return 0;
-
-	tracer->flags = 0;
-
-	task = tracer->ds.context->task;
-	cpu  = tracer->ds.context->cpu;
-
-	local_irq_save(irq);
-
-	error = -EPERM;
-	if (!task && (cpu != smp_processor_id()))
-		goto out;
-
-	debugctlmsr = (task ?
-		       task->thread.debugctlmsr :
-		       get_debugctlmsr());
-	debugctlmsr &= ~BTS_CONTROL;
-
-	if (task)
-		update_task_debugctlmsr(task, debugctlmsr);
-	else
-		update_debugctlmsr(debugctlmsr);
-
-	error = 0;
- out:
-	local_irq_restore(irq);
-	return error;
-}
-
-static unsigned long ds_bts_control(struct bts_tracer *tracer)
-{
-	unsigned long control;
-
-	control = ds_cfg.ctl[dsf_bts];
-	if (!(tracer->trace.ds.flags & BTS_KERNEL))
-		control |= ds_cfg.ctl[dsf_bts_kernel];
-	if (!(tracer->trace.ds.flags & BTS_USER))
-		control |= ds_cfg.ctl[dsf_bts_user];
-
-	return control;
-}
-
-void ds_resume_bts(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long debugctlmsr;
-	int cpu;
-
-	if (!tracer)
-		return;
-
-	tracer->flags = tracer->trace.ds.flags;
-
-	task = tracer->ds.context->task;
-	cpu  = tracer->ds.context->cpu;
-
-	WARN_ON(!task && irqs_disabled());
-
-	debugctlmsr = (task ?
-		       task->thread.debugctlmsr :
-		       get_debugctlmsr_on_cpu(cpu));
-	debugctlmsr |= ds_bts_control(tracer);
-
-	if (task)
-		update_task_debugctlmsr(task, debugctlmsr);
-	else
-		update_debugctlmsr_on_cpu(cpu, debugctlmsr);
-}
-
-int ds_resume_bts_noirq(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long debugctlmsr, irq;
-	int cpu, error = 0;
-
-	if (!tracer)
-		return 0;
-
-	tracer->flags = tracer->trace.ds.flags;
-
-	task = tracer->ds.context->task;
-	cpu  = tracer->ds.context->cpu;
-
-	local_irq_save(irq);
-
-	error = -EPERM;
-	if (!task && (cpu != smp_processor_id()))
-		goto out;
-
-	debugctlmsr = (task ?
-		       task->thread.debugctlmsr :
-		       get_debugctlmsr());
-	debugctlmsr |= ds_bts_control(tracer);
-
-	if (task)
-		update_task_debugctlmsr(task, debugctlmsr);
-	else
-		update_debugctlmsr(debugctlmsr);
-
-	error = 0;
- out:
-	local_irq_restore(irq);
-	return error;
-}
-
-static void ds_free_pebs(struct pebs_tracer *tracer)
-{
-	struct task_struct *task;
-
-	task = tracer->ds.context->task;
-
-	WARN_ON_ONCE(tracer->ds.context->pebs_master != tracer);
-	tracer->ds.context->pebs_master = NULL;
-
-	ds_put_context(tracer->ds.context);
-	put_tracer(task);
-
-	kfree(tracer);
-}
-
-void ds_release_pebs(struct pebs_tracer *tracer)
-{
-	might_sleep();
-
-	if (!tracer)
-		return;
-
-	ds_suspend_pebs(tracer);
-	ds_free_pebs(tracer);
-}
-
-int ds_release_pebs_noirq(struct pebs_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long irq;
-	int error;
-
-	if (!tracer)
-		return 0;
-
-	task = tracer->ds.context->task;
-
-	local_irq_save(irq);
-
-	error = -EPERM;
-	if (!task &&
-	    (tracer->ds.context->cpu != smp_processor_id()))
-		goto out;
-
-	error = -EPERM;
-	if (task && (task != current))
-		goto out;
-
-	ds_suspend_pebs_noirq(tracer);
-	ds_free_pebs(tracer);
-
-	error = 0;
- out:
-	local_irq_restore(irq);
-	return error;
-}
-
-void ds_suspend_pebs(struct pebs_tracer *tracer)
-{
-
-}
-
-int ds_suspend_pebs_noirq(struct pebs_tracer *tracer)
-{
-	return 0;
-}
-
-void ds_resume_pebs(struct pebs_tracer *tracer)
-{
-
-}
-
-int ds_resume_pebs_noirq(struct pebs_tracer *tracer)
-{
-	return 0;
-}
-
-const struct bts_trace *ds_read_bts(struct bts_tracer *tracer)
-{
-	if (!tracer)
-		return NULL;
-
-	ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
-	return &tracer->trace;
-}
-
-const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer)
-{
-	if (!tracer)
-		return NULL;
-
-	ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
-
-	tracer->trace.counters = ds_cfg.nr_counter_reset;
-	memcpy(tracer->trace.counter_reset,
-	       tracer->ds.context->ds +
-	       (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field),
-	       ds_cfg.nr_counter_reset * PEBS_RESET_FIELD_SIZE);
-
-	return &tracer->trace;
-}
-
-int ds_reset_bts(struct bts_tracer *tracer)
-{
-	if (!tracer)
-		return -EINVAL;
-
-	tracer->trace.ds.top = tracer->trace.ds.begin;
-
-	ds_set(tracer->ds.context->ds, ds_bts, ds_index,
-	       (unsigned long)tracer->trace.ds.top);
-
-	return 0;
-}
-
-int ds_reset_pebs(struct pebs_tracer *tracer)
-{
-	if (!tracer)
-		return -EINVAL;
-
-	tracer->trace.ds.top = tracer->trace.ds.begin;
-
-	ds_set(tracer->ds.context->ds, ds_pebs, ds_index,
-	       (unsigned long)tracer->trace.ds.top);
-
-	return 0;
-}
-
-int ds_set_pebs_reset(struct pebs_tracer *tracer,
-		      unsigned int counter, u64 value)
-{
-	if (!tracer)
-		return -EINVAL;
-
-	if (ds_cfg.nr_counter_reset < counter)
-		return -EINVAL;
-
-	*(u64 *)(tracer->ds.context->ds +
-		 (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field) +
-		 (counter * PEBS_RESET_FIELD_SIZE)) = value;
-
-	return 0;
-}
-
-static const struct ds_configuration ds_cfg_netburst = {
-	.name = "Netburst",
-	.ctl[dsf_bts]		= (1 << 2) | (1 << 3),
-	.ctl[dsf_bts_kernel]	= (1 << 5),
-	.ctl[dsf_bts_user]	= (1 << 6),
-	.nr_counter_reset	= 1,
-};
-static const struct ds_configuration ds_cfg_pentium_m = {
-	.name = "Pentium M",
-	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
-	.nr_counter_reset	= 1,
-};
-static const struct ds_configuration ds_cfg_core2_atom = {
-	.name = "Core 2/Atom",
-	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
-	.ctl[dsf_bts_kernel]	= (1 << 9),
-	.ctl[dsf_bts_user]	= (1 << 10),
-	.nr_counter_reset	= 1,
-};
-static const struct ds_configuration ds_cfg_core_i7 = {
-	.name = "Core i7",
-	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
-	.ctl[dsf_bts_kernel]	= (1 << 9),
-	.ctl[dsf_bts_user]	= (1 << 10),
-	.nr_counter_reset	= 4,
-};
-
-static void
-ds_configure(const struct ds_configuration *cfg,
-	     struct cpuinfo_x86 *cpu)
-{
-	unsigned long nr_pebs_fields = 0;
-
-	printk(KERN_INFO "[ds] using %s configuration\n", cfg->name);
-
-#ifdef __i386__
-	nr_pebs_fields = 10;
-#else
-	nr_pebs_fields = 18;
-#endif
-
-	/*
-	 * Starting with version 2, architectural performance
-	 * monitoring supports a format specifier.
-	 */
-	if ((cpuid_eax(0xa) & 0xff) > 1) {
-		unsigned long perf_capabilities, format;
-
-		rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_capabilities);
-
-		format = (perf_capabilities >> 8) & 0xf;
-
-		switch (format) {
-		case 0:
-			nr_pebs_fields = 18;
-			break;
-		case 1:
-			nr_pebs_fields = 22;
-			break;
-		default:
-			printk(KERN_INFO
-			       "[ds] unknown PEBS format: %lu\n", format);
-			nr_pebs_fields = 0;
-			break;
-		}
-	}
-
-	memset(&ds_cfg, 0, sizeof(ds_cfg));
-	ds_cfg = *cfg;
-
-	ds_cfg.sizeof_ptr_field =
-		(cpu_has(cpu, X86_FEATURE_DTES64) ? 8 : 4);
-
-	ds_cfg.sizeof_rec[ds_bts]  = ds_cfg.sizeof_ptr_field * 3;
-	ds_cfg.sizeof_rec[ds_pebs] = ds_cfg.sizeof_ptr_field * nr_pebs_fields;
-
-	if (!cpu_has(cpu, X86_FEATURE_BTS)) {
-		ds_cfg.sizeof_rec[ds_bts] = 0;
-		printk(KERN_INFO "[ds] bts not available\n");
-	}
-	if (!cpu_has(cpu, X86_FEATURE_PEBS)) {
-		ds_cfg.sizeof_rec[ds_pebs] = 0;
-		printk(KERN_INFO "[ds] pebs not available\n");
-	}
-
-	printk(KERN_INFO "[ds] sizes: address: %u bit, ",
-	       8 * ds_cfg.sizeof_ptr_field);
-	printk("bts/pebs record: %u/%u bytes\n",
-	       ds_cfg.sizeof_rec[ds_bts], ds_cfg.sizeof_rec[ds_pebs]);
-
-	WARN_ON_ONCE(MAX_PEBS_COUNTERS < ds_cfg.nr_counter_reset);
-}
-
-void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
-{
-	/* Only configure the first cpu. Others are identical. */
-	if (ds_cfg.name)
-		return;
-
-	switch (c->x86) {
-	case 0x6:
-		switch (c->x86_model) {
-		case 0x9:
-		case 0xd: /* Pentium M */
-			ds_configure(&ds_cfg_pentium_m, c);
-			break;
-		case 0xf:
-		case 0x17: /* Core2 */
-		case 0x1c: /* Atom */
-			ds_configure(&ds_cfg_core2_atom, c);
-			break;
-		case 0x1a: /* Core i7 */
-			ds_configure(&ds_cfg_core_i7, c);
-			break;
-		default:
-			/* Sorry, don't know about them. */
-			break;
-		}
-		break;
-	case 0xf:
-		switch (c->x86_model) {
-		case 0x0:
-		case 0x1:
-		case 0x2: /* Netburst */
-			ds_configure(&ds_cfg_netburst, c);
-			break;
-		default:
-			/* Sorry, don't know about them. */
-			break;
-		}
-		break;
-	default:
-		/* Sorry, don't know about them. */
-		break;
-	}
-}
-
-static inline void ds_take_timestamp(struct ds_context *context,
-				     enum bts_qualifier qualifier,
-				     struct task_struct *task)
-{
-	struct bts_tracer *tracer = context->bts_master;
-	struct bts_struct ts;
-
-	/* Prevent compilers from reading the tracer pointer twice. */
-	barrier();
-
-	if (!tracer || !(tracer->flags & BTS_TIMESTAMPS))
-		return;
-
-	memset(&ts, 0, sizeof(ts));
-	ts.qualifier		= qualifier;
-	ts.variant.event.clock	= trace_clock_global();
-	ts.variant.event.pid	= task->pid;
-
-	bts_write(tracer, &ts);
-}
-
-/*
- * Change the DS configuration from tracing prev to tracing next.
- */
-void ds_switch_to(struct task_struct *prev, struct task_struct *next)
-{
-	struct ds_context *prev_ctx	= prev->thread.ds_ctx;
-	struct ds_context *next_ctx	= next->thread.ds_ctx;
-	unsigned long debugctlmsr	= next->thread.debugctlmsr;
-
-	/* Make sure all data is read before we start. */
-	barrier();
-
-	if (prev_ctx) {
-		update_debugctlmsr(0);
-
-		ds_take_timestamp(prev_ctx, bts_task_departs, prev);
-	}
-
-	if (next_ctx) {
-		ds_take_timestamp(next_ctx, bts_task_arrives, next);
-
-		wrmsrl(MSR_IA32_DS_AREA, (unsigned long)next_ctx->ds);
-	}
-
-	update_debugctlmsr(debugctlmsr);
-}
-
-static __init int ds_selftest(void)
-{
-	if (ds_cfg.sizeof_rec[ds_bts]) {
-		int error;
-
-		error = ds_selftest_bts();
-		if (error) {
-			WARN(1, "[ds] selftest failed. disabling bts.\n");
-			ds_cfg.sizeof_rec[ds_bts] = 0;
-		}
-	}
-
-	if (ds_cfg.sizeof_rec[ds_pebs]) {
-		int error;
-
-		error = ds_selftest_pebs();
-		if (error) {
-			WARN(1, "[ds] selftest failed. disabling pebs.\n");
-			ds_cfg.sizeof_rec[ds_pebs] = 0;
-		}
-	}
-
-	return 0;
-}
-device_initcall(ds_selftest);

arch/x86/kernel/ds_selftest.c

diff --git a/arch/x86/kernel/ds_selftest.c b/arch/x86/kernel/ds_selftest.c
deleted file mode 100644
index 6bc7c19..0000000
--- a/arch/x86/kernel/ds_selftest.c
+++ /dev/null
@@ -1,408 +0,0 @@
-/*
- * Debug Store support - selftest
- *
- *
- * Copyright (C) 2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2009
- */
-
-#include "ds_selftest.h"
-
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/smp.h>
-#include <linux/cpu.h>
-
-#include <asm/ds.h>
-
-
-#define BUFFER_SIZE		521	/* Intentionally chose an odd size. */
-#define SMALL_BUFFER_SIZE	24	/* A single bts entry. */
-
-struct ds_selftest_bts_conf {
-	struct bts_tracer *tracer;
-	int error;
-	int (*suspend)(struct bts_tracer *);
-	int (*resume)(struct bts_tracer *);
-};
-
-static int ds_selftest_bts_consistency(const struct bts_trace *trace)
-{
-	int error = 0;
-
-	if (!trace) {
-		printk(KERN_CONT "failed to access trace...");
-		/* Bail out. Other tests are pointless. */
-		return -1;
-	}
-
-	if (!trace->read) {
-		printk(KERN_CONT "bts read not available...");
-		error = -1;
-	}
-
-	/* Do some sanity checks on the trace configuration. */
-	if (!trace->ds.n) {
-		printk(KERN_CONT "empty bts buffer...");
-		error = -1;
-	}
-	if (!trace->ds.size) {
-		printk(KERN_CONT "bad bts trace setup...");
-		error = -1;
-	}
-	if (trace->ds.end !=
-	    (char *)trace->ds.begin + (trace->ds.n * trace->ds.size)) {
-		printk(KERN_CONT "bad bts buffer setup...");
-		error = -1;
-	}
-	/*
-	 * We allow top in [begin; end], since its not clear when the
-	 * overflow adjustment happens: after the increment or before the
-	 * write.
-	 */
-	if ((trace->ds.top < trace->ds.begin) ||
-	    (trace->ds.end < trace->ds.top)) {
-		printk(KERN_CONT "bts top out of bounds...");
-		error = -1;
-	}
-
-	return error;
-}
-
-static int ds_selftest_bts_read(struct bts_tracer *tracer,
-				const struct bts_trace *trace,
-				const void *from, const void *to)
-{
-	const unsigned char *at;
-
-	/*
-	 * Check a few things which do not belong to this test.
-	 * They should be covered by other tests.
-	 */
-	if (!trace)
-		return -1;
-
-	if (!trace->read)
-		return -1;
-
-	if (to < from)
-		return -1;
-
-	if (from < trace->ds.begin)
-		return -1;
-
-	if (trace->ds.end < to)
-		return -1;
-
-	if (!trace->ds.size)
-		return -1;
-
-	/* Now to the test itself. */
-	for (at = from; (void *)at < to; at += trace->ds.size) {
-		struct bts_struct bts;
-		unsigned long index;
-		int error;
-
-		if (((void *)at - trace->ds.begin) % trace->ds.size) {
-			printk(KERN_CONT
-			       "read from non-integer index...");
-			return -1;
-		}
-		index = ((void *)at - trace->ds.begin) / trace->ds.size;
-
-		memset(&bts, 0, sizeof(bts));
-		error = trace->read(tracer, at, &bts);
-		if (error < 0) {
-			printk(KERN_CONT
-			       "error reading bts trace at [%lu] (0x%p)...",
-			       index, at);
-			return error;
-		}
-
-		switch (bts.qualifier) {
-		case BTS_BRANCH:
-			break;
-		default:
-			printk(KERN_CONT
-			       "unexpected bts entry %llu at [%lu] (0x%p)...",
-			       bts.qualifier, index, at);
-			return -1;
-		}
-	}
-
-	return 0;
-}
-
-static void ds_selftest_bts_cpu(void *arg)
-{
-	struct ds_selftest_bts_conf *conf = arg;
-	const struct bts_trace *trace;
-	void *top;
-
-	if (IS_ERR(conf->tracer)) {
-		conf->error = PTR_ERR(conf->tracer);
-		conf->tracer = NULL;
-
-		printk(KERN_CONT
-		       "initialization failed (err: %d)...", conf->error);
-		return;
-	}
-
-	/* We should meanwhile have enough trace. */
-	conf->error = conf->suspend(conf->tracer);
-	if (conf->error < 0)
-		return;
-
-	/* Let's see if we can access the trace. */
-	trace = ds_read_bts(conf->tracer);
-
-	conf->error = ds_selftest_bts_consistency(trace);
-	if (conf->error < 0)
-		return;
-
-	/* If everything went well, we should have a few trace entries. */
-	if (trace->ds.top == trace->ds.begin) {
-		/*
-		 * It is possible but highly unlikely that we got a
-		 * buffer overflow and end up at exactly the same
-		 * position we started from.
-		 * Let's issue a warning, but continue.
-		 */
-		printk(KERN_CONT "no trace/overflow...");
-	}
-
-	/* Let's try to read the trace we collected. */
-	conf->error =
-		ds_selftest_bts_read(conf->tracer, trace,
-				     trace->ds.begin, trace->ds.top);
-	if (conf->error < 0)
-		return;
-
-	/*
-	 * Let's read the trace again.
-	 * Since we suspended tracing, we should get the same result.
-	 */
-	top = trace->ds.top;
-
-	trace = ds_read_bts(conf->tracer);
-	conf->error = ds_selftest_bts_consistency(trace);
-	if (conf->error < 0)
-		return;
-
-	if (top != trace->ds.top) {
-		printk(KERN_CONT "suspend not working...");
-		conf->error = -1;
-		return;
-	}
-
-	/* Let's collect some more trace - see if resume is working. */
-	conf->error = conf->resume(conf->tracer);
-	if (conf->error < 0)
-		return;
-
-	conf->error = conf->suspend(conf->tracer);
-	if (conf->error < 0)
-		return;
-
-	trace = ds_read_bts(conf->tracer);
-
-	conf->error = ds_selftest_bts_consistency(trace);
-	if (conf->error < 0)
-		return;
-
-	if (trace->ds.top == top) {
-		/*
-		 * It is possible but highly unlikely that we got a
-		 * buffer overflow and end up at exactly the same
-		 * position we started from.
-		 * Let's issue a warning and check the full trace.
-		 */
-		printk(KERN_CONT
-		       "no resume progress/overflow...");
-
-		conf->error =
-			ds_selftest_bts_read(conf->tracer, trace,
-					     trace->ds.begin, trace->ds.end);
-	} else if (trace->ds.top < top) {
-		/*
-		 * We had a buffer overflow - the entire buffer should
-		 * contain trace records.
-		 */
-		conf->error =
-			ds_selftest_bts_read(conf->tracer, trace,
-					     trace->ds.begin, trace->ds.end);
-	} else {
-		/*
-		 * It is quite likely that the buffer did not overflow.
-		 * Let's just check the delta trace.
-		 */
-		conf->error =
-			ds_selftest_bts_read(conf->tracer, trace, top,
-					     trace->ds.top);
-	}
-	if (conf->error < 0)
-		return;
-
-	conf->error = 0;
-}
-
-static int ds_suspend_bts_wrap(struct bts_tracer *tracer)
-{
-	ds_suspend_bts(tracer);
-	return 0;
-}
-
-static int ds_resume_bts_wrap(struct bts_tracer *tracer)
-{
-	ds_resume_bts(tracer);
-	return 0;
-}
-
-static void ds_release_bts_noirq_wrap(void *tracer)
-{
-	(void)ds_release_bts_noirq(tracer);
-}
-
-static int ds_selftest_bts_bad_release_noirq(int cpu,
-					     struct bts_tracer *tracer)
-{
-	int error = -EPERM;
-
-	/* Try to release the tracer on the wrong cpu. */
-	get_cpu();
-	if (cpu != smp_processor_id()) {
-		error = ds_release_bts_noirq(tracer);
-		if (error != -EPERM)
-			printk(KERN_CONT "release on wrong cpu...");
-	}
-	put_cpu();
-
-	return error ? 0 : -1;
-}
-
-static int ds_selftest_bts_bad_request_cpu(int cpu, void *buffer)
-{
-	struct bts_tracer *tracer;
-	int error;
-
-	/* Try to request cpu tracing while task tracing is active. */
-	tracer = ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, NULL,
-				    (size_t)-1, BTS_KERNEL);
-	error = PTR_ERR(tracer);
-	if (!IS_ERR(tracer)) {
-		ds_release_bts(tracer);
-		error = 0;
-	}
-
-	if (error != -EPERM)
-		printk(KERN_CONT "cpu/task tracing overlap...");
-
-	return error ? 0 : -1;
-}
-
-static int ds_selftest_bts_bad_request_task(void *buffer)
-{
-	struct bts_tracer *tracer;
-	int error;
-
-	/* Try to request cpu tracing while task tracing is active. */
-	tracer = ds_request_bts_task(current, buffer, BUFFER_SIZE, NULL,
-				    (size_t)-1, BTS_KERNEL);
-	error = PTR_ERR(tracer);
-	if (!IS_ERR(tracer)) {
-		error = 0;
-		ds_release_bts(tracer);
-	}
-
-	if (error != -EPERM)
-		printk(KERN_CONT "task/cpu tracing overlap...");
-
-	return error ? 0 : -1;
-}
-
-int ds_selftest_bts(void)
-{
-	struct ds_selftest_bts_conf conf;
-	unsigned char buffer[BUFFER_SIZE], *small_buffer;
-	unsigned long irq;
-	int cpu;
-
-	printk(KERN_INFO "[ds] bts selftest...");
-	conf.error = 0;
-
-	small_buffer = (unsigned char *)ALIGN((unsigned long)buffer, 8) + 8;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		conf.suspend = ds_suspend_bts_wrap;
-		conf.resume = ds_resume_bts_wrap;
-		conf.tracer =
-			ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE,
-					   NULL, (size_t)-1, BTS_KERNEL);
-		ds_selftest_bts_cpu(&conf);
-		if (conf.error >= 0)
-			conf.error = ds_selftest_bts_bad_request_task(buffer);
-		ds_release_bts(conf.tracer);
-		if (conf.error < 0)
-			goto out;
-
-		conf.suspend = ds_suspend_bts_noirq;
-		conf.resume = ds_resume_bts_noirq;
-		conf.tracer =
-			ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE,
-					   NULL, (size_t)-1, BTS_KERNEL);
-		smp_call_function_single(cpu, ds_selftest_bts_cpu, &conf, 1);
-		if (conf.error >= 0) {
-			conf.error =
-				ds_selftest_bts_bad_release_noirq(cpu,
-								  conf.tracer);
-			/* We must not release the tracer twice. */
-			if (conf.error < 0)
-				conf.tracer = NULL;
-		}
-		if (conf.error >= 0)
-			conf.error = ds_selftest_bts_bad_request_task(buffer);
-		smp_call_function_single(cpu, ds_release_bts_noirq_wrap,
-					 conf.tracer, 1);
-		if (conf.error < 0)
-			goto out;
-	}
-
-	conf.suspend = ds_suspend_bts_wrap;
-	conf.resume = ds_resume_bts_wrap;
-	conf.tracer =
-		ds_request_bts_task(current, buffer, BUFFER_SIZE,
-				    NULL, (size_t)-1, BTS_KERNEL);
-	ds_selftest_bts_cpu(&conf);
-	if (conf.error >= 0)
-		conf.error = ds_selftest_bts_bad_request_cpu(0, buffer);
-	ds_release_bts(conf.tracer);
-	if (conf.error < 0)
-		goto out;
-
-	conf.suspend = ds_suspend_bts_noirq;
-	conf.resume = ds_resume_bts_noirq;
-	conf.tracer =
-		ds_request_bts_task(current, small_buffer, SMALL_BUFFER_SIZE,
-				   NULL, (size_t)-1, BTS_KERNEL);
-	local_irq_save(irq);
-	ds_selftest_bts_cpu(&conf);
-	if (conf.error >= 0)
-		conf.error = ds_selftest_bts_bad_request_cpu(0, buffer);
-	ds_release_bts_noirq(conf.tracer);
-	local_irq_restore(irq);
-	if (conf.error < 0)
-		goto out;
-
-	conf.error = 0;
- out:
-	put_online_cpus();
-	printk(KERN_CONT "%s.\n", (conf.error ? "failed" : "passed"));
-
-	return conf.error;
-}
-
-int ds_selftest_pebs(void)
-{
-	return 0;
-}

arch/x86/kernel/ds_selftest.h

diff --git a/arch/x86/kernel/ds_selftest.h b/arch/x86/kernel/ds_selftest.h
deleted file mode 100644
index 2ba8745..0000000
--- a/arch/x86/kernel/ds_selftest.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Debug Store support - selftest
- *
- *
- * Copyright (C) 2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2009
- */
-
-#ifdef CONFIG_X86_DS_SELFTEST
-extern int ds_selftest_bts(void);
-extern int ds_selftest_pebs(void);
-#else
-static inline int ds_selftest_bts(void) { return 0; }
-static inline int ds_selftest_pebs(void) { return 0; }
-#endif

arch/x86/kernel/dumpstack.c

diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 6d81755..c89a386 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -224,11 +224,6 @@
 	int cpu;
 	unsigned long flags;
 
-	/* notify the hw-branch tracer so it may disable tracing and
-	   add the last trace to the trace buffer -
-	   the earlier this happens, the more useful the trace. */
-	trace_hw_branch_oops();
-
 	oops_enter();
 
 	/* racy, but better than risking deadlock. */

arch/x86/kernel/hw_breakpoint.c

diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index d6cc065..a8f1b80 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -189,25 +189,16 @@
 }
 
 /*
- * Check for virtual address in user space.
- */
-int arch_check_va_in_userspace(unsigned long va, u8 hbp_len)
-{
-	unsigned int len;
-
-	len = get_hbp_len(hbp_len);
-
-	return (va <= TASK_SIZE - len);
-}
-
-/*
  * Check for virtual address in kernel space.
  */
-static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len)
+int arch_check_bp_in_kernelspace(struct perf_event *bp)
 {
 	unsigned int len;
+	unsigned long va;
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	len = get_hbp_len(hbp_len);
+	va = info->address;
+	len = get_hbp_len(info->len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -300,8 +291,7 @@
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp,
-				  struct task_struct *tsk)
+int arch_validate_hwbkpt_settings(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
@@ -314,16 +304,6 @@
 
 	ret = -EINVAL;
 
-	if (info->type == X86_BREAKPOINT_EXECUTE)
-		/*
-		 * Ptrace-refactoring code
-		 * For now, we'll allow instruction breakpoint only for user-space
-		 * addresses
-		 */
-		if ((!arch_check_va_in_userspace(info->address, info->len)) &&
-			info->len != X86_BREAKPOINT_EXECUTE)
-			return ret;
-
 	switch (info->len) {
 	case X86_BREAKPOINT_LEN_1:
 		align = 0;
@@ -350,15 +330,6 @@
 	if (info->address & align)
 		return -EINVAL;
 
-	/* Check that the virtual address is in the proper range */
-	if (tsk) {
-		if (!arch_check_va_in_userspace(info->address, info->len))
-			return -EFAULT;
-	} else {
-		if (!arch_check_va_in_kernelspace(info->address, info->len))
-			return -EFAULT;
-	}
-
 	return 0;
 }
 

arch/x86/kernel/i8253.c

diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 23c1679..2dfd315 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -16,7 +16,7 @@
 #include <asm/hpet.h>
 #include <asm/smp.h>
 
-DEFINE_SPINLOCK(i8253_lock);
+DEFINE_RAW_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
 /*
@@ -33,7 +33,7 @@
 static void init_pit_timer(enum clock_event_mode mode,
 			   struct clock_event_device *evt)
 {
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
@@ -62,7 +62,7 @@
 		/* Nothing to do here */
 		break;
 	}
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 }
 
 /*
@@ -72,10 +72,10 @@
  */
 static int pit_next_event(unsigned long delta, struct clock_event_device *evt)
 {
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 	outb_pit(delta & 0xff , PIT_CH0);	/* LSB */
 	outb_pit(delta >> 8 , PIT_CH0);		/* MSB */
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 
 	return 0;
 }
@@ -130,7 +130,7 @@
 	int count;
 	u32 jifs;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 	/*
 	 * Although our caller may have the read side of xtime_lock,
 	 * this is now a seqlock, and we are cheating in this routine
@@ -176,7 +176,7 @@
 	old_count = count;
 	old_jifs = jifs;
 
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 
 	count = (LATCH - 1) - count;
 

arch/x86/kernel/kprobes.c

diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index b43bbae..345a4b1 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -422,14 +422,22 @@
 
 static void __kprobes clear_btf(void)
 {
-	if (test_thread_flag(TIF_DEBUGCTLMSR))
-		update_debugctlmsr(0);
+	if (test_thread_flag(TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+	}
 }
 
 static void __kprobes restore_btf(void)
 {
-	if (test_thread_flag(TIF_DEBUGCTLMSR))
-		update_debugctlmsr(current->thread.debugctlmsr);
+	if (test_thread_flag(TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl |= DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+	}
 }
 
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
@@ -534,20 +542,6 @@
 	struct kprobe_ctlblk *kcb;
 
 	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
-	if (*addr != BREAKPOINT_INSTRUCTION) {
-		/*
-		 * The breakpoint instruction was removed right
-		 * after we hit it.  Another cpu has removed
-		 * either a probepoint or a debugger breakpoint
-		 * at this address.  In either case, no further
-		 * handling of this interrupt is appropriate.
-		 * Back up over the (now missing) int3 and run
-		 * the original instruction.
-		 */
-		regs->ip = (unsigned long)addr;
-		return 1;
-	}
-
 	/*
 	 * We don't want to be preempted for the entire
 	 * duration of kprobe processing. We conditionally
@@ -579,6 +573,19 @@
 				setup_singlestep(p, regs, kcb, 0);
 			return 1;
 		}
+	} else if (*addr != BREAKPOINT_INSTRUCTION) {
+		/*
+		 * The breakpoint instruction was removed right
+		 * after we hit it.  Another cpu has removed
+		 * either a probepoint or a debugger breakpoint
+		 * at this address.  In either case, no further
+		 * handling of this interrupt is appropriate.
+		 * Back up over the (now missing) int3 and run
+		 * the original instruction.
+		 */
+		regs->ip = (unsigned long)addr;
+		preempt_enable_no_resched();
+		return 1;
 	} else if (kprobe_running()) {
 		p = __get_cpu_var(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {

arch/x86/kernel/process.c

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 28ad9f4..cc68775 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -20,7 +20,6 @@
 #include <asm/idle.h>
 #include <asm/uaccess.h>
 #include <asm/i387.h>
-#include <asm/ds.h>
 #include <asm/debugreg.h>
 
 unsigned long idle_halt;
@@ -50,8 +49,6 @@
 		kmem_cache_free(task_xstate_cachep, tsk->thread.xstate);
 		tsk->thread.xstate = NULL;
 	}
-
-	WARN(tsk->thread.ds_ctx, "leaking DS context\n");
 }
 
 void free_thread_info(struct thread_info *ti)
@@ -198,11 +195,16 @@
 	prev = &prev_p->thread;
 	next = &next_p->thread;
 
-	if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) ||
-	    test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR))
-		ds_switch_to(prev_p, next_p);
-	else if (next->debugctlmsr != prev->debugctlmsr)
-		update_debugctlmsr(next->debugctlmsr);
+	if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^
+	    test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP))
+			debugctl |= DEBUGCTLMSR_BTF;
+
+		update_debugctlmsr(debugctl);
+	}
 
 	if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
 	    test_tsk_thread_flag(next_p, TIF_NOTSC)) {
@@ -546,11 +548,13 @@
 		 * check OSVW bit for CPUs that are not affected
 		 * by erratum #400
 		 */
-		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val);
-		if (val >= 2) {
-			rdmsrl(MSR_AMD64_OSVW_STATUS, val);
-			if (!(val & BIT(1)))
-				goto no_c1e_idle;
+		if (cpu_has(c, X86_FEATURE_OSVW)) {
+			rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val);
+			if (val >= 2) {
+				rdmsrl(MSR_AMD64_OSVW_STATUS, val);
+				if (!(val & BIT(1)))
+					goto no_c1e_idle;
+			}
 		}
 		return 1;
 	}

arch/x86/kernel/process_32.c

diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index f6c6266..75090c5 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -55,7 +55,6 @@
 #include <asm/cpu.h>
 #include <asm/idle.h>
 #include <asm/syscalls.h>
-#include <asm/ds.h>
 #include <asm/debugreg.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
@@ -238,13 +237,6 @@
 		kfree(p->thread.io_bitmap_ptr);
 		p->thread.io_bitmap_max = 0;
 	}
-
-	clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
-	p->thread.ds_ctx = NULL;
-
-	clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
-	p->thread.debugctlmsr = 0;
-
 	return err;
 }
 

arch/x86/kernel/process_64.c

diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 17cb329..50cc84a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -49,7 +49,6 @@
 #include <asm/ia32.h>
 #include <asm/idle.h>
 #include <asm/syscalls.h>
-#include <asm/ds.h>
 #include <asm/debugreg.h>
 
 asmlinkage extern void ret_from_fork(void);
@@ -313,13 +312,6 @@
 		if (err)
 			goto out;
 	}
-
-	clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
-	p->thread.ds_ctx = NULL;
-
-	clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
-	p->thread.debugctlmsr = 0;
-
 	err = 0;
 out:
 	if (err && p->thread.io_bitmap_ptr) {

arch/x86/kernel/ptrace.c

diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 2e9b550..70c4872 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -2,9 +2,6 @@
 /*
  * Pentium III FXSR, SSE support
  *	Gareth Hughes <gareth@valinux.com>, May 2000
- *
- * BTS tracing
- *	Markus Metzger <markus.t.metzger@intel.com>, Dec 2007
  */
 
 #include <linux/kernel.h>
@@ -22,7 +19,6 @@
 #include <linux/audit.h>
 #include <linux/seccomp.h>
 #include <linux/signal.h>
-#include <linux/workqueue.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
 
@@ -36,7 +32,6 @@
 #include <asm/desc.h>
 #include <asm/prctl.h>
 #include <asm/proto.h>
-#include <asm/ds.h>
 #include <asm/hw_breakpoint.h>
 
 #include "tls.h"
@@ -693,7 +688,7 @@
 	struct perf_event_attr attr;
 
 	if (!t->ptrace_bps[nr]) {
-		hw_breakpoint_init(&attr);
+		ptrace_breakpoint_init(&attr);
 		/*
 		 * Put stub len and type to register (reserve) an inactive but
 		 * correct bp
@@ -789,342 +784,6 @@
 				   0, IO_BITMAP_BYTES);
 }
 
-#ifdef CONFIG_X86_PTRACE_BTS
-/*
- * A branch trace store context.
- *
- * Contexts may only be installed by ptrace_bts_config() and only for
- * ptraced tasks.
- *
- * Contexts are destroyed when the tracee is detached from the tracer.
- * The actual destruction work requires interrupts enabled, so the
- * work is deferred and will be scheduled during __ptrace_unlink().
- *
- * Contexts hold an additional task_struct reference on the traced
- * task, as well as a reference on the tracer's mm.
- *
- * Ptrace already holds a task_struct for the duration of ptrace operations,
- * but since destruction is deferred, it may be executed after both
- * tracer and tracee exited.
- */
-struct bts_context {
-	/* The branch trace handle. */
-	struct bts_tracer	*tracer;
-
-	/* The buffer used to store the branch trace and its size. */
-	void			*buffer;
-	unsigned int		size;
-
-	/* The mm that paid for the above buffer. */
-	struct mm_struct	*mm;
-
-	/* The task this context belongs to. */
-	struct task_struct	*task;
-
-	/* The signal to send on a bts buffer overflow. */
-	unsigned int		bts_ovfl_signal;
-
-	/* The work struct to destroy a context. */
-	struct work_struct	work;
-};
-
-static int alloc_bts_buffer(struct bts_context *context, unsigned int size)
-{
-	void *buffer = NULL;
-	int err = -ENOMEM;
-
-	err = account_locked_memory(current->mm, current->signal->rlim, size);
-	if (err < 0)
-		return err;
-
-	buffer = kzalloc(size, GFP_KERNEL);
-	if (!buffer)
-		goto out_refund;
-
-	context->buffer = buffer;
-	context->size = size;
-	context->mm = get_task_mm(current);
-
-	return 0;
-
- out_refund:
-	refund_locked_memory(current->mm, size);
-	return err;
-}
-
-static inline void free_bts_buffer(struct bts_context *context)
-{
-	if (!context->buffer)
-		return;
-
-	kfree(context->buffer);
-	context->buffer = NULL;
-
-	refund_locked_memory(context->mm, context->size);
-	context->size = 0;
-
-	mmput(context->mm);
-	context->mm = NULL;
-}
-
-static void free_bts_context_work(struct work_struct *w)
-{
-	struct bts_context *context;
-
-	context = container_of(w, struct bts_context, work);
-
-	ds_release_bts(context->tracer);
-	put_task_struct(context->task);
-	free_bts_buffer(context);
-	kfree(context);
-}
-
-static inline void free_bts_context(struct bts_context *context)
-{
-	INIT_WORK(&context->work, free_bts_context_work);
-	schedule_work(&context->work);
-}
-
-static inline struct bts_context *alloc_bts_context(struct task_struct *task)
-{
-	struct bts_context *context = kzalloc(sizeof(*context), GFP_KERNEL);
-	if (context) {
-		context->task = task;
-		task->bts = context;
-
-		get_task_struct(task);
-	}
-
-	return context;
-}
-
-static int ptrace_bts_read_record(struct task_struct *child, size_t index,
-				  struct bts_struct __user *out)
-{
-	struct bts_context *context;
-	const struct bts_trace *trace;
-	struct bts_struct bts;
-	const unsigned char *at;
-	int error;
-
-	context = child->bts;
-	if (!context)
-		return -ESRCH;
-
-	trace = ds_read_bts(context->tracer);
-	if (!trace)
-		return -ESRCH;
-
-	at = trace->ds.top - ((index + 1) * trace->ds.size);
-	if ((void *)at < trace->ds.begin)
-		at += (trace->ds.n * trace->ds.size);
-
-	if (!trace->read)
-		return -EOPNOTSUPP;
-
-	error = trace->read(context->tracer, at, &bts);
-	if (error < 0)
-		return error;
-
-	if (copy_to_user(out, &bts, sizeof(bts)))
-		return -EFAULT;
-
-	return sizeof(bts);
-}
-
-static int ptrace_bts_drain(struct task_struct *child,
-			    long size,
-			    struct bts_struct __user *out)
-{
-	struct bts_context *context;
-	const struct bts_trace *trace;
-	const unsigned char *at;
-	int error, drained = 0;
-
-	context = child->bts;
-	if (!context)
-		return -ESRCH;
-
-	trace = ds_read_bts(context->tracer);
-	if (!trace)
-		return -ESRCH;
-
-	if (!trace->read)
-		return -EOPNOTSUPP;
-
-	if (size < (trace->ds.top - trace->ds.begin))
-		return -EIO;
-
-	for (at = trace->ds.begin; (void *)at < trace->ds.top;
-	     out++, drained++, at += trace->ds.size) {
-		struct bts_struct bts;
-
-		error = trace->read(context->tracer, at, &bts);
-		if (error < 0)
-			return error;
-
-		if (copy_to_user(out, &bts, sizeof(bts)))
-			return -EFAULT;
-	}
-
-	memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
-
-	error = ds_reset_bts(context->tracer);
-	if (error < 0)
-		return error;
-
-	return drained;
-}
-
-static int ptrace_bts_config(struct task_struct *child,
-			     long cfg_size,
-			     const struct ptrace_bts_config __user *ucfg)
-{
-	struct bts_context *context;
-	struct ptrace_bts_config cfg;
-	unsigned int flags = 0;
-
-	if (cfg_size < sizeof(cfg))
-		return -EIO;
-
-	if (copy_from_user(&cfg, ucfg, sizeof(cfg)))
-		return -EFAULT;
-
-	context = child->bts;
-	if (!context)
-		context = alloc_bts_context(child);
-	if (!context)
-		return -ENOMEM;
-
-	if (cfg.flags & PTRACE_BTS_O_SIGNAL) {
-		if (!cfg.signal)
-			return -EINVAL;
-
-		return -EOPNOTSUPP;
-		context->bts_ovfl_signal = cfg.signal;
-	}
-
-	ds_release_bts(context->tracer);
-	context->tracer = NULL;
-
-	if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) {
-		int err;
-
-		free_bts_buffer(context);
-		if (!cfg.size)
-			return 0;
-
-		err = alloc_bts_buffer(context, cfg.size);
-		if (err < 0)
-			return err;
-	}
-
-	if (cfg.flags & PTRACE_BTS_O_TRACE)
-		flags |= BTS_USER;
-
-	if (cfg.flags & PTRACE_BTS_O_SCHED)
-		flags |= BTS_TIMESTAMPS;
-
-	context->tracer =
-		ds_request_bts_task(child, context->buffer, context->size,
-				    NULL, (size_t)-1, flags);
-	if (unlikely(IS_ERR(context->tracer))) {
-		int error = PTR_ERR(context->tracer);
-
-		free_bts_buffer(context);
-		context->tracer = NULL;
-		return error;
-	}
-
-	return sizeof(cfg);
-}
-
-static int ptrace_bts_status(struct task_struct *child,
-			     long cfg_size,
-			     struct ptrace_bts_config __user *ucfg)
-{
-	struct bts_context *context;
-	const struct bts_trace *trace;
-	struct ptrace_bts_config cfg;
-
-	context = child->bts;
-	if (!context)
-		return -ESRCH;
-
-	if (cfg_size < sizeof(cfg))
-		return -EIO;
-
-	trace = ds_read_bts(context->tracer);
-	if (!trace)
-		return -ESRCH;
-
-	memset(&cfg, 0, sizeof(cfg));
-	cfg.size	= trace->ds.end - trace->ds.begin;
-	cfg.signal	= context->bts_ovfl_signal;
-	cfg.bts_size	= sizeof(struct bts_struct);
-
-	if (cfg.signal)
-		cfg.flags |= PTRACE_BTS_O_SIGNAL;
-
-	if (trace->ds.flags & BTS_USER)
-		cfg.flags |= PTRACE_BTS_O_TRACE;
-
-	if (trace->ds.flags & BTS_TIMESTAMPS)
-		cfg.flags |= PTRACE_BTS_O_SCHED;
-
-	if (copy_to_user(ucfg, &cfg, sizeof(cfg)))
-		return -EFAULT;
-
-	return sizeof(cfg);
-}
-
-static int ptrace_bts_clear(struct task_struct *child)
-{
-	struct bts_context *context;
-	const struct bts_trace *trace;
-
-	context = child->bts;
-	if (!context)
-		return -ESRCH;
-
-	trace = ds_read_bts(context->tracer);
-	if (!trace)
-		return -ESRCH;
-
-	memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
-
-	return ds_reset_bts(context->tracer);
-}
-
-static int ptrace_bts_size(struct task_struct *child)
-{
-	struct bts_context *context;
-	const struct bts_trace *trace;
-
-	context = child->bts;
-	if (!context)
-		return -ESRCH;
-
-	trace = ds_read_bts(context->tracer);
-	if (!trace)
-		return -ESRCH;
-
-	return (trace->ds.top - trace->ds.begin) / trace->ds.size;
-}
-
-/*
- * Called from __ptrace_unlink() after the child has been moved back
- * to its original parent.
- */
-void ptrace_bts_untrace(struct task_struct *child)
-{
-	if (unlikely(child->bts)) {
-		free_bts_context(child->bts);
-		child->bts = NULL;
-	}
-}
-#endif /* CONFIG_X86_PTRACE_BTS */
-
 /*
  * Called by kernel/ptrace.c when detaching..
  *
@@ -1252,39 +911,6 @@
 		break;
 #endif
 
-	/*
-	 * These bits need more cooking - not enabled yet:
-	 */
-#ifdef CONFIG_X86_PTRACE_BTS
-	case PTRACE_BTS_CONFIG:
-		ret = ptrace_bts_config
-			(child, data, (struct ptrace_bts_config __user *)addr);
-		break;
-
-	case PTRACE_BTS_STATUS:
-		ret = ptrace_bts_status
-			(child, data, (struct ptrace_bts_config __user *)addr);
-		break;
-
-	case PTRACE_BTS_SIZE:
-		ret = ptrace_bts_size(child);
-		break;
-
-	case PTRACE_BTS_GET:
-		ret = ptrace_bts_read_record
-			(child, data, (struct bts_struct __user *) addr);
-		break;
-
-	case PTRACE_BTS_CLEAR:
-		ret = ptrace_bts_clear(child);
-		break;
-
-	case PTRACE_BTS_DRAIN:
-		ret = ptrace_bts_drain
-			(child, data, (struct bts_struct __user *) addr);
-		break;
-#endif /* CONFIG_X86_PTRACE_BTS */
-
 	default:
 		ret = ptrace_request(child, request, addr, data);
 		break;
@@ -1544,14 +1170,6 @@
 
 	case PTRACE_GET_THREAD_AREA:
 	case PTRACE_SET_THREAD_AREA:
-#ifdef CONFIG_X86_PTRACE_BTS
-	case PTRACE_BTS_CONFIG:
-	case PTRACE_BTS_STATUS:
-	case PTRACE_BTS_SIZE:
-	case PTRACE_BTS_GET:
-	case PTRACE_BTS_CLEAR:
-	case PTRACE_BTS_DRAIN:
-#endif /* CONFIG_X86_PTRACE_BTS */
 		return arch_ptrace(child, request, addr, data);
 
 	default:

arch/x86/kernel/step.c

diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 3149032..58de45e 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -158,22 +158,6 @@
 }
 
 /*
- * Install this value in MSR_IA32_DEBUGCTLMSR whenever child is running.
- */
-static void write_debugctlmsr(struct task_struct *child, unsigned long val)
-{
-	if (child->thread.debugctlmsr == val)
-		return;
-
-	child->thread.debugctlmsr = val;
-
-	if (child != current)
-		return;
-
-	update_debugctlmsr(val);
-}
-
-/*
  * Enable single or block step.
  */
 static void enable_step(struct task_struct *child, bool block)
@@ -186,15 +170,17 @@
 	 * that uses user-mode single stepping itself.
 	 */
 	if (enable_single_step(child) && block) {
-		set_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
-		write_debugctlmsr(child,
-				  child->thread.debugctlmsr | DEBUGCTLMSR_BTF);
-	} else {
-		write_debugctlmsr(child,
-				  child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF);
+		unsigned long debugctl = get_debugctlmsr();
 
-		if (!child->thread.debugctlmsr)
-			clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
+		debugctl |= DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+		set_tsk_thread_flag(child, TIF_BLOCKSTEP);
+	} else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+		clear_tsk_thread_flag(child, TIF_BLOCKSTEP);
 	}
 }
 
@@ -213,11 +199,13 @@
 	/*
 	 * Make sure block stepping (BTF) is disabled.
 	 */
-	write_debugctlmsr(child,
-			  child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF);
+	if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
 
-	if (!child->thread.debugctlmsr)
-		clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+		clear_tsk_thread_flag(child, TIF_BLOCKSTEP);
+	}
 
 	/* Always clear TIF_SINGLESTEP... */
 	clear_tsk_thread_flag(child, TIF_SINGLESTEP);

arch/x86/kernel/traps.c

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 1168e44..36f1bd9 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -543,11 +543,11 @@
 
 	/* DR6 may or may not be cleared by the CPU */
 	set_debugreg(0, 6);
+
 	/*
 	 * The processor cleared BTF, so don't mark that we need it set.
 	 */
-	clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR);
-	tsk->thread.debugctlmsr = 0;
+	clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP);
 
 	/* Store the virtualized DR6 value */
 	tsk->thread.debugreg6 = dr6;

arch/x86/kvm/svm.c

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 2ba5820..737361f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2067,7 +2067,7 @@
 static int iret_interception(struct vcpu_svm *svm)
 {
 	++svm->vcpu.stat.nmi_window_exits;
-	svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+	svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_IRET);
 	svm->vcpu.arch.hflags |= HF_IRET_MASK;
 	return 1;
 }
@@ -2479,7 +2479,7 @@
 
 	svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI;
 	vcpu->arch.hflags |= HF_NMI_MASK;
-	svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+	svm->vmcb->control.intercept |= (1ULL << INTERCEPT_IRET);
 	++vcpu->stat.nmi_injections;
 }
 
@@ -2539,10 +2539,10 @@
 
 	if (masked) {
 		svm->vcpu.arch.hflags |= HF_NMI_MASK;
-		svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+		svm->vmcb->control.intercept |= (1ULL << INTERCEPT_IRET);
 	} else {
 		svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
-		svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+		svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_IRET);
 	}
 }
 

arch/x86/kvm/vmx.c

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bc933cf..edca080 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2703,8 +2703,7 @@
 		return 0;
 
 	return	!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
-			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS |
-				GUEST_INTR_STATE_NMI));
+			(GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_NMI));
 }
 
 static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
@@ -3660,8 +3659,11 @@
 
 	/* We need to handle NMIs before interrupts are enabled */
 	if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
-	    (exit_intr_info & INTR_INFO_VALID_MASK))
+	    (exit_intr_info & INTR_INFO_VALID_MASK)) {
+		kvm_before_handle_nmi(&vmx->vcpu);
 		asm("int $2");
+		kvm_after_handle_nmi(&vmx->vcpu);
+	}
 
 	idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
 

arch/x86/kvm/x86.c

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3c4ca98..dd9bc8f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -40,6 +40,7 @@
 #include <linux/user-return-notifier.h>
 #include <linux/srcu.h>
 #include <linux/slab.h>
+#include <linux/perf_event.h>
 #include <trace/events/kvm.h>
 #undef TRACE_INCLUDE_FILE
 #define CREATE_TRACE_POINTS
@@ -1712,6 +1713,7 @@
 	if (copy_from_user(cpuid_entries, entries,
 			   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
 		goto out_free;
+	vcpu_load(vcpu);
 	for (i = 0; i < cpuid->nent; i++) {
 		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
 		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
@@ -1729,6 +1731,7 @@
 	r = 0;
 	kvm_apic_set_version(vcpu);
 	kvm_x86_ops->cpuid_update(vcpu);
+	vcpu_put(vcpu);
 
 out_free:
 	vfree(cpuid_entries);
@@ -1749,9 +1752,11 @@
 	if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
 			   cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
 		goto out;
+	vcpu_load(vcpu);
 	vcpu->arch.cpuid_nent = cpuid->nent;
 	kvm_apic_set_version(vcpu);
 	kvm_x86_ops->cpuid_update(vcpu);
+	vcpu_put(vcpu);
 	return 0;
 
 out:
@@ -3743,6 +3748,51 @@
 	}
 }
 
+static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
+
+static int kvm_is_in_guest(void)
+{
+	return percpu_read(current_vcpu) != NULL;
+}
+
+static int kvm_is_user_mode(void)
+{
+	int user_mode = 3;
+
+	if (percpu_read(current_vcpu))
+		user_mode = kvm_x86_ops->get_cpl(percpu_read(current_vcpu));
+
+	return user_mode != 0;
+}
+
+static unsigned long kvm_get_guest_ip(void)
+{
+	unsigned long ip = 0;
+
+	if (percpu_read(current_vcpu))
+		ip = kvm_rip_read(percpu_read(current_vcpu));
+
+	return ip;
+}
+
+static struct perf_guest_info_callbacks kvm_guest_cbs = {
+	.is_in_guest		= kvm_is_in_guest,
+	.is_user_mode		= kvm_is_user_mode,
+	.get_guest_ip		= kvm_get_guest_ip,
+};
+
+void kvm_before_handle_nmi(struct kvm_vcpu *vcpu)
+{
+	percpu_write(current_vcpu, vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_before_handle_nmi);
+
+void kvm_after_handle_nmi(struct kvm_vcpu *vcpu)
+{
+	percpu_write(current_vcpu, NULL);
+}
+EXPORT_SYMBOL_GPL(kvm_after_handle_nmi);
+
 int kvm_arch_init(void *opaque)
 {
 	int r;
@@ -3779,6 +3829,8 @@
 
 	kvm_timer_init();
 
+	perf_register_guest_info_callbacks(&kvm_guest_cbs);
+
 	return 0;
 
 out:
@@ -3787,6 +3839,8 @@
 
 void kvm_arch_exit(void)
 {
+	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
+
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
 		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
 					    CPUFREQ_TRANSITION_NOTIFIER);

arch/x86/kvm/x86.h

diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 2d10163..b7a4047 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -65,4 +65,7 @@
 	return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
 }
 
+void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
+void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
+
 #endif

arch/x86/lib/Makefile

diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 419386c..cbaf8f2 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -20,7 +20,7 @@
 lib-y += thunk_$(BITS).o
 lib-y += usercopy_$(BITS).o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
-lib-$(CONFIG_KPROBES) += insn.o inat.o
+lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
 
 obj-y += msr.o msr-reg.o msr-reg-export.o
 

arch/x86/lib/rwsem_64.S

diff --git a/arch/x86/lib/rwsem_64.S b/arch/x86/lib/rwsem_64.S
index 15acecf..41fcf00 100644
--- a/arch/x86/lib/rwsem_64.S
+++ b/arch/x86/lib/rwsem_64.S
@@ -60,7 +60,7 @@
 	ENDPROC(call_rwsem_down_write_failed)
 
 ENTRY(call_rwsem_wake)
-	decw %dx    /* do nothing if still outstanding active readers */
+	decl %edx	/* do nothing if still outstanding active readers */
 	jnz 1f
 	save_common_regs
 	movq %rax,%rdi

arch/x86/mm/ioremap.c

diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 5eb1ba7..12e4d2d 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -448,6 +448,20 @@
 static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
 static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
 
+void __init fixup_early_ioremap(void)
+{
+	int i;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (prev_map[i]) {
+			WARN_ON(1);
+			break;
+		}
+	}
+
+	early_ioremap_init();
+}
+
 static int __init check_early_ioremap_leak(void)
 {
 	int count = 0;

arch/x86/mm/pgtable_32.c

diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 1a8faf0..7928540 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -18,6 +18,7 @@
 #include <asm/e820.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
+#include <asm/io.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
@@ -128,6 +129,7 @@
 
 	address = memparse(arg, &arg);
 	reserve_top_address(address);
+	fixup_early_ioremap();
 	return 0;
 }
 early_param("reservetop", parse_reservetop);

arch/x86/mm/srat_64.c

diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 28c6876..38512d0 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -461,7 +461,8 @@
 		 * node, it must now point to the fake node ID.
 		 */
 		for (j = 0; j < MAX_LOCAL_APIC; j++)
-			if (apicid_to_node[j] == nid)
+			if (apicid_to_node[j] == nid &&
+			    fake_apicid_to_node[j] == NUMA_NO_NODE)
 				fake_apicid_to_node[j] = i;
 	}
 	for (i = 0; i < num_nodes; i++)

arch/x86/oprofile/nmi_int.c

diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 2c505ee..b28d2f1 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -31,8 +31,9 @@
 static DEFINE_PER_CPU(struct op_msrs, cpu_msrs);
 static DEFINE_PER_CPU(unsigned long, saved_lvtpc);
 
-/* 0 == registered but off, 1 == registered and on */
-static int nmi_enabled = 0;
+/* must be protected with get_online_cpus()/put_online_cpus(): */
+static int nmi_enabled;
+static int ctr_running;
 
 struct op_counter_config counter_config[OP_MAX_COUNTER];
 
@@ -61,12 +62,16 @@
 {
 	struct die_args *args = (struct die_args *)data;
 	int ret = NOTIFY_DONE;
-	int cpu = smp_processor_id();
 
 	switch (val) {
 	case DIE_NMI:
 	case DIE_NMI_IPI:
-		model->check_ctrs(args->regs, &per_cpu(cpu_msrs, cpu));
+		if (ctr_running)
+			model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs));
+		else if (!nmi_enabled)
+			break;
+		else
+			model->stop(&__get_cpu_var(cpu_msrs));
 		ret = NOTIFY_STOP;
 		break;
 	default:
@@ -95,24 +100,36 @@
 static void nmi_cpu_start(void *dummy)
 {
 	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
-	model->start(msrs);
+	if (!msrs->controls)
+		WARN_ON_ONCE(1);
+	else
+		model->start(msrs);
 }
 
 static int nmi_start(void)
 {
+	get_online_cpus();
 	on_each_cpu(nmi_cpu_start, NULL, 1);
+	ctr_running = 1;
+	put_online_cpus();
 	return 0;
 }
 
 static void nmi_cpu_stop(void *dummy)
 {
 	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
-	model->stop(msrs);
+	if (!msrs->controls)
+		WARN_ON_ONCE(1);
+	else
+		model->stop(msrs);
 }
 
 static void nmi_stop(void)
 {
+	get_online_cpus();
 	on_each_cpu(nmi_cpu_stop, NULL, 1);
+	ctr_running = 0;
+	put_online_cpus();
 }
 
 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
@@ -252,7 +269,10 @@
 	if (nmi_multiplex_on() < 0)
 		return -EINVAL;		/* not necessary */
 
-	on_each_cpu(nmi_cpu_switch, NULL, 1);
+	get_online_cpus();
+	if (ctr_running)
+		on_each_cpu(nmi_cpu_switch, NULL, 1);
+	put_online_cpus();
 
 	return 0;
 }
@@ -295,6 +315,7 @@
 		kfree(per_cpu(cpu_msrs, i).controls);
 		per_cpu(cpu_msrs, i).controls = NULL;
 	}
+	nmi_shutdown_mux();
 }
 
 static int allocate_msrs(void)
@@ -307,14 +328,21 @@
 		per_cpu(cpu_msrs, i).counters = kzalloc(counters_size,
 							GFP_KERNEL);
 		if (!per_cpu(cpu_msrs, i).counters)
-			return 0;
+			goto fail;
 		per_cpu(cpu_msrs, i).controls = kzalloc(controls_size,
 							GFP_KERNEL);
 		if (!per_cpu(cpu_msrs, i).controls)
-			return 0;
+			goto fail;
 	}
 
+	if (!nmi_setup_mux())
+		goto fail;
+
 	return 1;
+
+fail:
+	free_msrs();
+	return 0;
 }
 
 static void nmi_cpu_setup(void *dummy)
@@ -336,49 +364,6 @@
 	.priority = 2
 };
 
-static int nmi_setup(void)
-{
-	int err = 0;
-	int cpu;
-
-	if (!allocate_msrs())
-		err = -ENOMEM;
-	else if (!nmi_setup_mux())
-		err = -ENOMEM;
-	else
-		err = register_die_notifier(&profile_exceptions_nb);
-
-	if (err) {
-		free_msrs();
-		nmi_shutdown_mux();
-		return err;
-	}
-
-	/* We need to serialize save and setup for HT because the subset
-	 * of msrs are distinct for save and setup operations
-	 */
-
-	/* Assume saved/restored counters are the same on all CPUs */
-	model->fill_in_addresses(&per_cpu(cpu_msrs, 0));
-	for_each_possible_cpu(cpu) {
-		if (!cpu)
-			continue;
-
-		memcpy(per_cpu(cpu_msrs, cpu).counters,
-		       per_cpu(cpu_msrs, 0).counters,
-		       sizeof(struct op_msr) * model->num_counters);
-
-		memcpy(per_cpu(cpu_msrs, cpu).controls,
-		       per_cpu(cpu_msrs, 0).controls,
-		       sizeof(struct op_msr) * model->num_controls);
-
-		mux_clone(cpu);
-	}
-	on_each_cpu(nmi_cpu_setup, NULL, 1);
-	nmi_enabled = 1;
-	return 0;
-}
-
 static void nmi_cpu_restore_registers(struct op_msrs *msrs)
 {
 	struct op_msr *counters = msrs->counters;
@@ -412,20 +397,24 @@
 	apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu));
 	apic_write(APIC_LVTERR, v);
 	nmi_cpu_restore_registers(msrs);
+	if (model->cpu_down)
+		model->cpu_down();
 }
 
-static void nmi_shutdown(void)
+static void nmi_cpu_up(void *dummy)
 {
-	struct op_msrs *msrs;
+	if (nmi_enabled)
+		nmi_cpu_setup(dummy);
+	if (ctr_running)
+		nmi_cpu_start(dummy);
+}
 
-	nmi_enabled = 0;
-	on_each_cpu(nmi_cpu_shutdown, NULL, 1);
-	unregister_die_notifier(&profile_exceptions_nb);
-	nmi_shutdown_mux();
-	msrs = &get_cpu_var(cpu_msrs);
-	model->shutdown(msrs);
-	free_msrs();
-	put_cpu_var(cpu_msrs);
+static void nmi_cpu_down(void *dummy)
+{
+	if (ctr_running)
+		nmi_cpu_stop(dummy);
+	if (nmi_enabled)
+		nmi_cpu_shutdown(dummy);
 }
 
 static int nmi_create_files(struct super_block *sb, struct dentry *root)
@@ -457,7 +446,6 @@
 	return 0;
 }
 
-#ifdef CONFIG_SMP
 static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action,
 				 void *data)
 {
@@ -465,10 +453,10 @@
 	switch (action) {
 	case CPU_DOWN_FAILED:
 	case CPU_ONLINE:
-		smp_call_function_single(cpu, nmi_cpu_start, NULL, 0);
+		smp_call_function_single(cpu, nmi_cpu_up, NULL, 0);
 		break;
 	case CPU_DOWN_PREPARE:
-		smp_call_function_single(cpu, nmi_cpu_stop, NULL, 1);
+		smp_call_function_single(cpu, nmi_cpu_down, NULL, 1);
 		break;
 	}
 	return NOTIFY_DONE;
@@ -477,7 +465,75 @@
 static struct notifier_block oprofile_cpu_nb = {
 	.notifier_call = oprofile_cpu_notifier
 };
-#endif
+
+static int nmi_setup(void)
+{
+	int err = 0;
+	int cpu;
+
+	if (!allocate_msrs())
+		return -ENOMEM;
+
+	/* We need to serialize save and setup for HT because the subset
+	 * of msrs are distinct for save and setup operations
+	 */
+
+	/* Assume saved/restored counters are the same on all CPUs */
+	err = model->fill_in_addresses(&per_cpu(cpu_msrs, 0));
+	if (err)
+		goto fail;
+
+	for_each_possible_cpu(cpu) {
+		if (!cpu)
+			continue;
+
+		memcpy(per_cpu(cpu_msrs, cpu).counters,
+		       per_cpu(cpu_msrs, 0).counters,
+		       sizeof(struct op_msr) * model->num_counters);
+
+		memcpy(per_cpu(cpu_msrs, cpu).controls,
+		       per_cpu(cpu_msrs, 0).controls,
+		       sizeof(struct op_msr) * model->num_controls);
+
+		mux_clone(cpu);
+	}
+
+	nmi_enabled = 0;
+	ctr_running = 0;
+	barrier();
+	err = register_die_notifier(&profile_exceptions_nb);
+	if (err)
+		goto fail;
+
+	get_online_cpus();
+	register_cpu_notifier(&oprofile_cpu_nb);
+	on_each_cpu(nmi_cpu_setup, NULL, 1);
+	nmi_enabled = 1;
+	put_online_cpus();
+
+	return 0;
+fail:
+	free_msrs();
+	return err;
+}
+
+static void nmi_shutdown(void)
+{
+	struct op_msrs *msrs;
+
+	get_online_cpus();
+	unregister_cpu_notifier(&oprofile_cpu_nb);
+	on_each_cpu(nmi_cpu_shutdown, NULL, 1);
+	nmi_enabled = 0;
+	ctr_running = 0;
+	put_online_cpus();
+	barrier();
+	unregister_die_notifier(&profile_exceptions_nb);
+	msrs = &get_cpu_var(cpu_msrs);
+	model->shutdown(msrs);
+	free_msrs();
+	put_cpu_var(cpu_msrs);
+}
 
 #ifdef CONFIG_PM
 
@@ -687,9 +743,6 @@
 		return -ENODEV;
 	}
 
-#ifdef CONFIG_SMP
-	register_cpu_notifier(&oprofile_cpu_nb);
-#endif
 	/* default values, can be overwritten by model */
 	ops->create_files	= nmi_create_files;
 	ops->setup		= nmi_setup;
@@ -716,12 +769,6 @@
 
 void op_nmi_exit(void)
 {
-	if (using_nmi) {
+	if (using_nmi)
 		exit_sysfs();
-#ifdef CONFIG_SMP
-		unregister_cpu_notifier(&oprofile_cpu_nb);
-#endif
-	}
-	if (model->exit)
-		model->exit();
 }

arch/x86/oprofile/op_model_amd.c

diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 090cbbe..b67a6b5 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -30,13 +30,10 @@
 #include "op_counter.h"
 
 #define NUM_COUNTERS 4
-#define NUM_CONTROLS 4
 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
 #define NUM_VIRT_COUNTERS 32
-#define NUM_VIRT_CONTROLS 32
 #else
 #define NUM_VIRT_COUNTERS NUM_COUNTERS
-#define NUM_VIRT_CONTROLS NUM_CONTROLS
 #endif
 
 #define OP_EVENT_MASK			0x0FFF
@@ -105,102 +102,6 @@
 	return ibs_caps;
 }
 
-#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
-
-static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
-			       struct op_msrs const * const msrs)
-{
-	u64 val;
-	int i;
-
-	/* enable active counters */
-	for (i = 0; i < NUM_COUNTERS; ++i) {
-		int virt = op_x86_phys_to_virt(i);
-		if (!reset_value[virt])
-			continue;
-		rdmsrl(msrs->controls[i].addr, val);
-		val &= model->reserved;
-		val |= op_x86_get_ctrl(model, &counter_config[virt]);
-		wrmsrl(msrs->controls[i].addr, val);
-	}
-}
-
-#endif
-
-/* functions for op_amd_spec */
-
-static void op_amd_fill_in_addresses(struct op_msrs * const msrs)
-{
-	int i;
-
-	for (i = 0; i < NUM_COUNTERS; i++) {
-		if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
-			msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
-	}
-
-	for (i = 0; i < NUM_CONTROLS; i++) {
-		if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i))
-			msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
-	}
-}
-
-static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
-			      struct op_msrs const * const msrs)
-{
-	u64 val;
-	int i;
-
-	/* setup reset_value */
-	for (i = 0; i < NUM_VIRT_COUNTERS; ++i) {
-		if (counter_config[i].enabled
-		    && msrs->counters[op_x86_virt_to_phys(i)].addr)
-			reset_value[i] = counter_config[i].count;
-		else
-			reset_value[i] = 0;
-	}
-
-	/* clear all counters */
-	for (i = 0; i < NUM_CONTROLS; ++i) {
-		if (unlikely(!msrs->controls[i].addr)) {
-			if (counter_config[i].enabled && !smp_processor_id())
-				/*
-				 * counter is reserved, this is on all
-				 * cpus, so report only for cpu #0
-				 */
-				op_x86_warn_reserved(i);
-			continue;
-		}
-		rdmsrl(msrs->controls[i].addr, val);
-		if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
-			op_x86_warn_in_use(i);
-		val &= model->reserved;
-		wrmsrl(msrs->controls[i].addr, val);
-	}
-
-	/* avoid a false detection of ctr overflows in NMI handler */
-	for (i = 0; i < NUM_COUNTERS; ++i) {
-		if (unlikely(!msrs->counters[i].addr))
-			continue;
-		wrmsrl(msrs->counters[i].addr, -1LL);
-	}
-
-	/* enable active counters */
-	for (i = 0; i < NUM_COUNTERS; ++i) {
-		int virt = op_x86_phys_to_virt(i);
-		if (!reset_value[virt])
-			continue;
-
-		/* setup counter registers */
-		wrmsrl(msrs->counters[i].addr, -(u64)reset_value[virt]);
-
-		/* setup control registers */
-		rdmsrl(msrs->controls[i].addr, val);
-		val &= model->reserved;
-		val |= op_x86_get_ctrl(model, &counter_config[virt]);
-		wrmsrl(msrs->controls[i].addr, val);
-	}
-}
-
 /*
  * 16-bit Linear Feedback Shift Register (LFSR)
  *
@@ -365,6 +266,125 @@
 		wrmsrl(MSR_AMD64_IBSOPCTL, 0);
 }
 
+#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+
+static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
+			       struct op_msrs const * const msrs)
+{
+	u64 val;
+	int i;
+
+	/* enable active counters */
+	for (i = 0; i < NUM_COUNTERS; ++i) {
+		int virt = op_x86_phys_to_virt(i);
+		if (!reset_value[virt])
+			continue;
+		rdmsrl(msrs->controls[i].addr, val);
+		val &= model->reserved;
+		val |= op_x86_get_ctrl(model, &counter_config[virt]);
+		wrmsrl(msrs->controls[i].addr, val);
+	}
+}
+
+#endif
+
+/* functions for op_amd_spec */
+
+static void op_amd_shutdown(struct op_msrs const * const msrs)
+{
+	int i;
+
+	for (i = 0; i < NUM_COUNTERS; ++i) {
+		if (!msrs->counters[i].addr)
+			continue;
+		release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+		release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+	}
+}
+
+static int op_amd_fill_in_addresses(struct op_msrs * const msrs)
+{
+	int i;
+
+	for (i = 0; i < NUM_COUNTERS; i++) {
+		if (!reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
+			goto fail;
+		if (!reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) {
+			release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+			goto fail;
+		}
+		/* both registers must be reserved */
+		msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
+		msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
+		continue;
+	fail:
+		if (!counter_config[i].enabled)
+			continue;
+		op_x86_warn_reserved(i);
+		op_amd_shutdown(msrs);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
+			      struct op_msrs const * const msrs)
+{
+	u64 val;
+	int i;
+
+	/* setup reset_value */
+	for (i = 0; i < NUM_VIRT_COUNTERS; ++i) {
+		if (counter_config[i].enabled
+		    && msrs->counters[op_x86_virt_to_phys(i)].addr)
+			reset_value[i] = counter_config[i].count;
+		else
+			reset_value[i] = 0;
+	}
+
+	/* clear all counters */
+	for (i = 0; i < NUM_COUNTERS; ++i) {
+		if (!msrs->controls[i].addr)
+			continue;
+		rdmsrl(msrs->controls[i].addr, val);
+		if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
+			op_x86_warn_in_use(i);
+		val &= model->reserved;
+		wrmsrl(msrs->controls[i].addr, val);
+		/*
+		 * avoid a false detection of ctr overflows in NMI
+		 * handler
+		 */
+		wrmsrl(msrs->counters[i].addr, -1LL);
+	}
+
+	/* enable active counters */
+	for (i = 0; i < NUM_COUNTERS; ++i) {
+		int virt = op_x86_phys_to_virt(i);
+		if (!reset_value[virt])
+			continue;
+
+		/* setup counter registers */
+		wrmsrl(msrs->counters[i].addr, -(u64)reset_value[virt]);
+
+		/* setup control registers */
+		rdmsrl(msrs->controls[i].addr, val);
+		val &= model->reserved;
+		val |= op_x86_get_ctrl(model, &counter_config[virt]);
+		wrmsrl(msrs->controls[i].addr, val);
+	}
+
+	if (ibs_caps)
+		setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0);
+}
+
+static void op_amd_cpu_shutdown(void)
+{
+	if (ibs_caps)
+		setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
+}
+
 static int op_amd_check_ctrs(struct pt_regs * const regs,
 			     struct op_msrs const * const msrs)
 {
@@ -425,42 +445,16 @@
 	op_amd_stop_ibs();
 }
 
-static void op_amd_shutdown(struct op_msrs const * const msrs)
-{
-	int i;
-
-	for (i = 0; i < NUM_COUNTERS; ++i) {
-		if (msrs->counters[i].addr)
-			release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-	}
-	for (i = 0; i < NUM_CONTROLS; ++i) {
-		if (msrs->controls[i].addr)
-			release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-	}
-}
-
-static u8 ibs_eilvt_off;
-
-static inline void apic_init_ibs_nmi_per_cpu(void *arg)
-{
-	ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0);
-}
-
-static inline void apic_clear_ibs_nmi_per_cpu(void *arg)
-{
-	setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
-}
-
-static int init_ibs_nmi(void)
+static int __init_ibs_nmi(void)
 {
 #define IBSCTL_LVTOFFSETVAL		(1 << 8)
 #define IBSCTL				0x1cc
 	struct pci_dev *cpu_cfg;
 	int nodes;
 	u32 value = 0;
+	u8 ibs_eilvt_off;
 
-	/* per CPU setup */
-	on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1);
+	ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
 
 	nodes = 0;
 	cpu_cfg = NULL;
@@ -490,22 +484,15 @@
 	return 0;
 }
 
-/* uninitialize the APIC for the IBS interrupts if needed */
-static void clear_ibs_nmi(void)
-{
-	if (ibs_caps)
-		on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1);
-}
-
 /* initialize the APIC for the IBS interrupts if available */
-static void ibs_init(void)
+static void init_ibs(void)
 {
 	ibs_caps = get_ibs_caps();
 
 	if (!ibs_caps)
 		return;
 
-	if (init_ibs_nmi()) {
+	if (__init_ibs_nmi()) {
 		ibs_caps = 0;
 		return;
 	}
@@ -514,14 +501,6 @@
 	       (unsigned)ibs_caps);
 }
 
-static void ibs_exit(void)
-{
-	if (!ibs_caps)
-		return;
-
-	clear_ibs_nmi();
-}
-
 static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
 
 static int setup_ibs_files(struct super_block *sb, struct dentry *root)
@@ -570,27 +549,22 @@
 
 static int op_amd_init(struct oprofile_operations *ops)
 {
-	ibs_init();
+	init_ibs();
 	create_arch_files = ops->create_files;
 	ops->create_files = setup_ibs_files;
 	return 0;
 }
 
-static void op_amd_exit(void)
-{
-	ibs_exit();
-}
-
 struct op_x86_model_spec op_amd_spec = {
 	.num_counters		= NUM_COUNTERS,
-	.num_controls		= NUM_CONTROLS,
+	.num_controls		= NUM_COUNTERS,
 	.num_virt_counters	= NUM_VIRT_COUNTERS,
 	.reserved		= MSR_AMD_EVENTSEL_RESERVED,
 	.event_mask		= OP_EVENT_MASK,
 	.init			= op_amd_init,
-	.exit			= op_amd_exit,
 	.fill_in_addresses	= &op_amd_fill_in_addresses,
 	.setup_ctrs		= &op_amd_setup_ctrs,
+	.cpu_down		= &op_amd_cpu_shutdown,
 	.check_ctrs		= &op_amd_check_ctrs,
 	.start			= &op_amd_start,
 	.stop			= &op_amd_stop,

arch/x86/oprofile/op_model_p4.c

diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index e6a160a..182558d 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -385,8 +385,26 @@
 
 static unsigned long reset_value[NUM_COUNTERS_NON_HT];
 
+static void p4_shutdown(struct op_msrs const * const msrs)
+{
+	int i;
 
-static void p4_fill_in_addresses(struct op_msrs * const msrs)
+	for (i = 0; i < num_counters; ++i) {
+		if (msrs->counters[i].addr)
+			release_perfctr_nmi(msrs->counters[i].addr);
+	}
+	/*
+	 * some of the control registers are specially reserved in
+	 * conjunction with the counter registers (hence the starting offset).
+	 * This saves a few bits.
+	 */
+	for (i = num_counters; i < num_controls; ++i) {
+		if (msrs->controls[i].addr)
+			release_evntsel_nmi(msrs->controls[i].addr);
+	}
+}
+
+static int p4_fill_in_addresses(struct op_msrs * const msrs)
 {
 	unsigned int i;
 	unsigned int addr, cccraddr, stag;
@@ -468,6 +486,18 @@
 			msrs->controls[i++].addr = MSR_P4_CRU_ESCR5;
 		}
 	}
+
+	for (i = 0; i < num_counters; ++i) {
+		if (!counter_config[i].enabled)
+			continue;
+		if (msrs->controls[i].addr)
+			continue;
+		op_x86_warn_reserved(i);
+		p4_shutdown(msrs);
+		return -EBUSY;
+	}
+
+	return 0;
 }
 
 
@@ -668,26 +698,6 @@
 	}
 }
 
-static void p4_shutdown(struct op_msrs const * const msrs)
-{
-	int i;
-
-	for (i = 0; i < num_counters; ++i) {
-		if (msrs->counters[i].addr)
-			release_perfctr_nmi(msrs->counters[i].addr);
-	}
-	/*
-	 * some of the control registers are specially reserved in
-	 * conjunction with the counter registers (hence the starting offset).
-	 * This saves a few bits.
-	 */
-	for (i = num_counters; i < num_controls; ++i) {
-		if (msrs->controls[i].addr)
-			release_evntsel_nmi(msrs->controls[i].addr);
-	}
-}
-
-
 #ifdef CONFIG_SMP
 struct op_x86_model_spec op_p4_ht2_spec = {
 	.num_counters		= NUM_COUNTERS_HT2,

arch/x86/oprofile/op_model_ppro.c

diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 2bf90fa..d769cda 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -30,19 +30,46 @@
 
 static u64 *reset_value;
 
-static void ppro_fill_in_addresses(struct op_msrs * const msrs)
+static void ppro_shutdown(struct op_msrs const * const msrs)
+{
+	int i;
+
+	for (i = 0; i < num_counters; ++i) {
+		if (!msrs->counters[i].addr)
+			continue;
+		release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
+		release_evntsel_nmi(MSR_P6_EVNTSEL0 + i);
+	}
+	if (reset_value) {
+		kfree(reset_value);
+		reset_value = NULL;
+	}
+}
+
+static int ppro_fill_in_addresses(struct op_msrs * const msrs)
 {
 	int i;
 
 	for (i = 0; i < num_counters; i++) {
-		if (reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i))
-			msrs->counters[i].addr = MSR_P6_PERFCTR0 + i;
+		if (!reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i))
+			goto fail;
+		if (!reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i)) {
+			release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
+			goto fail;
+		}
+		/* both registers must be reserved */
+		msrs->counters[i].addr = MSR_P6_PERFCTR0 + i;
+		msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
+		continue;
+	fail:
+		if (!counter_config[i].enabled)
+			continue;
+		op_x86_warn_reserved(i);
+		ppro_shutdown(msrs);
+		return -EBUSY;
 	}
 
-	for (i = 0; i < num_counters; i++) {
-		if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i))
-			msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
-	}
+	return 0;
 }
 
 
@@ -78,26 +105,17 @@
 
 	/* clear all counters */
 	for (i = 0; i < num_counters; ++i) {
-		if (unlikely(!msrs->controls[i].addr)) {
-			if (counter_config[i].enabled && !smp_processor_id())
-				/*
-				 * counter is reserved, this is on all
-				 * cpus, so report only for cpu #0
-				 */
-				op_x86_warn_reserved(i);
+		if (!msrs->controls[i].addr)
 			continue;
-		}
 		rdmsrl(msrs->controls[i].addr, val);
 		if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
 			op_x86_warn_in_use(i);
 		val &= model->reserved;
 		wrmsrl(msrs->controls[i].addr, val);
-	}
-
-	/* avoid a false detection of ctr overflows in NMI handler */
-	for (i = 0; i < num_counters; ++i) {
-		if (unlikely(!msrs->counters[i].addr))
-			continue;
+		/*
+		 * avoid a false detection of ctr overflows in NMI *
+		 * handler
+		 */
 		wrmsrl(msrs->counters[i].addr, -1LL);
 	}
 
@@ -189,25 +207,6 @@
 	}
 }
 
-static void ppro_shutdown(struct op_msrs const * const msrs)
-{
-	int i;
-
-	for (i = 0; i < num_counters; ++i) {
-		if (msrs->counters[i].addr)
-			release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
-	}
-	for (i = 0; i < num_counters; ++i) {
-		if (msrs->controls[i].addr)
-			release_evntsel_nmi(MSR_P6_EVNTSEL0 + i);
-	}
-	if (reset_value) {
-		kfree(reset_value);
-		reset_value = NULL;
-	}
-}
-
-
 struct op_x86_model_spec op_ppro_spec = {
 	.num_counters		= 2,
 	.num_controls		= 2,
@@ -239,11 +238,11 @@
 	if (eax.split.version_id == 0 && current_cpu_data.x86 == 6 &&
 		current_cpu_data.x86_model == 15) {
 		eax.split.version_id = 2;
-		eax.split.num_events = 2;
+		eax.split.num_counters = 2;
 		eax.split.bit_width = 40;
 	}
 
-	num_counters = eax.split.num_events;
+	num_counters = eax.split.num_counters;
 
 	op_arch_perfmon_spec.num_counters = num_counters;
 	op_arch_perfmon_spec.num_controls = num_counters;

arch/x86/oprofile/op_x86_model.h

diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h
index ff82a75..89017fa 100644
--- a/arch/x86/oprofile/op_x86_model.h
+++ b/arch/x86/oprofile/op_x86_model.h
@@ -40,10 +40,10 @@
 	u64		reserved;
 	u16		event_mask;
 	int		(*init)(struct oprofile_operations *ops);
-	void		(*exit)(void);
-	void		(*fill_in_addresses)(struct op_msrs * const msrs);
+	int		(*fill_in_addresses)(struct op_msrs * const msrs);
 	void		(*setup_ctrs)(struct op_x86_model_spec const *model,
 				      struct op_msrs const * const msrs);
+	void		(*cpu_down)(void);
 	int		(*check_ctrs)(struct pt_regs * const regs,
 				      struct op_msrs const * const msrs);
 	void		(*start)(struct op_msrs const * const msrs);

arch/x86/pci/mrst.c

diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c
index 8bf2fcb..1cdc02c 100644
--- a/arch/x86/pci/mrst.c
+++ b/arch/x86/pci/mrst.c
@@ -247,6 +247,10 @@
 	u32 size;
 	int i;
 
+	/* Must have extended configuration space */
+	if (dev->cfg_size < PCIE_CAP_OFFSET + 4)
+		return;
+
 	/* Fixup the BAR sizes for fixed BAR devices and make them unmoveable */
 	offset = fixed_bar_cap(dev->bus, dev->devfn);
 	if (!offset || PCI_DEVFN(2, 0) == dev->devfn ||

arch/xtensa/include/asm/atomic.h

diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index 22d6dde..a96a061 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -46,7 +46,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)		((v)->counter)
+#define atomic_read(v)		(*(volatile int *)&(v)->counter)
 
 /**
  * atomic_set - set atomic variable

block/blk-cgroup.c

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5fe03de..2cc682b 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -286,16 +286,16 @@
 static struct cgroup_subsys_state *
 blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 {
-	struct blkio_cgroup *blkcg, *parent_blkcg;
+	struct blkio_cgroup *blkcg;
+	struct cgroup *parent = cgroup->parent;
 
-	if (!cgroup->parent) {
+	if (!parent) {
 		blkcg = &blkio_root_cgroup;
 		goto done;
 	}
 
 	/* Currently we do not support hierarchy deeper than two level (0,1) */
-	parent_blkcg = cgroup_to_blkio_cgroup(cgroup->parent);
-	if (css_depth(&parent_blkcg->css) > 0)
+	if (parent != cgroup->top_cgroup)
 		return ERR_PTR(-EINVAL);
 
 	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);

block/cfq-iosched.c

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 838834b..5f127cf 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3694,8 +3694,10 @@
 	 * to make sure that cfq_put_cfqg() does not try to kfree root group
 	 */
 	atomic_set(&cfqg->ref, 1);
+	rcu_read_lock();
 	blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd,
 					0);
+	rcu_read_unlock();
 #endif
 	/*
 	 * Not strictly needed (since RB_ROOT just clears the node and we

crypto/async_tx/async_raid6_recov.c

diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
index 943f2ab..ce038d8 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -324,6 +324,7 @@
 async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 			struct page **blocks, struct async_submit_ctl *submit)
 {
+	void *scribble = submit->scribble;
 	int non_zero_srcs, i;
 
 	BUG_ON(faila == failb);
@@ -332,11 +333,13 @@
 
 	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
 
-	/* we need to preserve the contents of 'blocks' for the async
-	 * case, so punt to synchronous if a scribble buffer is not available
+	/* if a dma resource is not available or a scribble buffer is not
+	 * available punt to the synchronous path.  In the 'dma not
+	 * available' case be sure to use the scribble buffer to
+	 * preserve the content of 'blocks' as the caller intended.
 	 */
-	if (!submit->scribble) {
-		void **ptrs = (void **) blocks;
+	if (!async_dma_find_channel(DMA_PQ) || !scribble) {
+		void **ptrs = scribble ? scribble : (void **) blocks;
 
 		async_tx_quiesce(&submit->depend_tx);
 		for (i = 0; i < disks; i++)
@@ -406,11 +409,13 @@
 
 	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
 
-	/* we need to preserve the contents of 'blocks' for the async
-	 * case, so punt to synchronous if a scribble buffer is not available
+	/* if a dma resource is not available or a scribble buffer is not
+	 * available punt to the synchronous path.  In the 'dma not
+	 * available' case be sure to use the scribble buffer to
+	 * preserve the content of 'blocks' as the caller intended.
 	 */
-	if (!scribble) {
-		void **ptrs = (void **) blocks;
+	if (!async_dma_find_channel(DMA_PQ) || !scribble) {
+		void **ptrs = scribble ? scribble : (void **) blocks;
 
 		async_tx_quiesce(&submit->depend_tx);
 		for (i = 0; i < disks; i++)

drivers/Makefile

diff --git a/drivers/Makefile b/drivers/Makefile
index 34f1e10..f42a030 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -17,6 +17,7 @@
 obj-$(CONFIG_PNP)		+= pnp/
 obj-$(CONFIG_ARM_AMBA)		+= amba/
 
+obj-$(CONFIG_VIRTIO)		+= virtio/
 obj-$(CONFIG_XEN)		+= xen/
 
 # regulators early, since some subsystems rely on them to initialize
@@ -108,7 +109,6 @@
 obj-$(CONFIG_OF)		+= of/
 obj-$(CONFIG_SSB)		+= ssb/
 obj-$(CONFIG_VHOST_NET)		+= vhost/
-obj-$(CONFIG_VIRTIO)		+= virtio/
 obj-$(CONFIG_VLYNQ)		+= vlynq/
 obj-$(CONFIG_STAGING)		+= staging/
 obj-y				+= platform/

drivers/acpi/acpi_pad.c

diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 19dacfd..6212213 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -31,7 +31,7 @@
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
 
-#define ACPI_PROCESSOR_AGGREGATOR_CLASS	"processor_aggregator"
+#define ACPI_PROCESSOR_AGGREGATOR_CLASS	"acpi_pad"
 #define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator"
 #define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80
 static DEFINE_MUTEX(isolated_cpus_lock);

drivers/acpi/bus.c

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 37132dc..743576b 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -527,7 +527,7 @@
 	if (!event_is_open)
 		return 0;
 
-	event = kmalloc(sizeof(struct acpi_bus_event), GFP_ATOMIC);
+	event = kzalloc(sizeof(struct acpi_bus_event), GFP_ATOMIC);
 	if (!event)
 		return -ENOMEM;
 

drivers/acpi/hest.c

diff --git a/drivers/acpi/hest.c b/drivers/acpi/hest.c
index 4bb18c9..1c527a1 100644
--- a/drivers/acpi/hest.c
+++ b/drivers/acpi/hest.c
@@ -123,6 +123,10 @@
 {
 	acpi_status status = AE_NOT_FOUND;
 	struct acpi_table_header *hest = NULL;
+
+	if (acpi_disabled)
+		return 0;
+
 	status = acpi_get_table(ACPI_SIG_HEST, 1, &hest);
 
 	if (ACPI_SUCCESS(status)) {

drivers/acpi/power_meter.c

diff --git a/drivers/acpi/power_meter.c b/drivers/acpi/power_meter.c
index e8c32a4..66f6729 100644
--- a/drivers/acpi/power_meter.c
+++ b/drivers/acpi/power_meter.c
@@ -35,7 +35,7 @@
 #define ACPI_POWER_METER_NAME		"power_meter"
 ACPI_MODULE_NAME(ACPI_POWER_METER_NAME);
 #define ACPI_POWER_METER_DEVICE_NAME	"Power Meter"
-#define ACPI_POWER_METER_CLASS		"power_meter_resource"
+#define ACPI_POWER_METER_CLASS		"pwr_meter_resource"
 
 #define NUM_SENSORS			17
 

drivers/acpi/sbshc.c

diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index 36704b8..f8be23b 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -18,7 +18,7 @@
 
 #define PREFIX "ACPI: "
 
-#define ACPI_SMB_HC_CLASS	"smbus_host_controller"
+#define ACPI_SMB_HC_CLASS	"smbus_host_ctl"
 #define ACPI_SMB_HC_DEVICE_NAME	"ACPI SMBus HC"
 
 struct acpi_smb_hc {

drivers/acpi/sleep.c

diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index f74834a..baa76bb 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -450,6 +450,38 @@
 		},
 	},
 	{
+	.callback = init_set_sci_en_on_resume,
+	.ident = "Lenovo ThinkPad T410",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T410"),
+		},
+	},
+	{
+	.callback = init_set_sci_en_on_resume,
+	.ident = "Lenovo ThinkPad T510",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T510"),
+		},
+	},
+	{
+	.callback = init_set_sci_en_on_resume,
+	.ident = "Lenovo ThinkPad W510",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W510"),
+		},
+	},
+	{
+	.callback = init_set_sci_en_on_resume,
+	.ident = "Lenovo ThinkPad X201[s]",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201"),
+		},
+	},
+	{
 	.callback = init_old_suspend_ordering,
 	.ident = "Panasonic CF51-2L",
 	.matches = {
@@ -458,6 +490,30 @@
 		DMI_MATCH(DMI_BOARD_NAME, "CF51-2L"),
 		},
 	},
+	{
+	.callback = init_set_sci_en_on_resume,
+	.ident = "Dell Studio 1558",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1558"),
+		},
+	},
+	{
+	.callback = init_set_sci_en_on_resume,
+	.ident = "Dell Studio 1557",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1557"),
+		},
+	},
+	{
+	.callback = init_set_sci_en_on_resume,
+	.ident = "Dell Studio 1555",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1555"),
+		},
+	},
 	{},
 };
 #endif /* CONFIG_SUSPEND */

drivers/ata/pata_pcmcia.c

diff --git a/drivers/ata/pata_pcmcia.c b/drivers/ata/pata_pcmcia.c
index 4164dd2..d94b8f0 100644
--- a/drivers/ata/pata_pcmcia.c
+++ b/drivers/ata/pata_pcmcia.c
@@ -424,7 +424,7 @@
 	PCMCIA_DEVICE_PROD_ID12("Hyperstone", "Model1", 0x3d5b9ef5, 0xca6ab420),
 	PCMCIA_DEVICE_PROD_ID12("IBM", "microdrive", 0xb569a6e5, 0xa6d76178),
 	PCMCIA_DEVICE_PROD_ID12("IBM", "IBM17JSSFP20", 0xb569a6e5, 0xf2508753),
-	PCMCIA_DEVICE_PROD_ID12("KINGSTON", "CF CARD 1GB", 0x2e6d1829, 0x3e520e17),
+	PCMCIA_DEVICE_PROD_ID12("KINGSTON", "CF CARD 1GB", 0x2e6d1829, 0x55d5bffb),
 	PCMCIA_DEVICE_PROD_ID12("KINGSTON", "CF CARD 4GB", 0x2e6d1829, 0x531e7d10),
 	PCMCIA_DEVICE_PROD_ID12("KINGSTON", "CF8GB", 0x2e6d1829, 0xacbe682e),
 	PCMCIA_DEVICE_PROD_ID12("IO DATA", "CBIDE2      ", 0x547e66dc, 0x8671043b),
@@ -446,7 +446,7 @@
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS1GCF80", 0x709b1bf1, 0x2a54d4b1),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS2GCF120", 0x709b1bf1, 0x969aa4f2),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS4GCF120", 0x709b1bf1, 0xf54a91c8),
-	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS4GCF133", 0x709b1bf1, 0x9351e59d),
+	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS4GCF133", 0x709b1bf1, 0x7558f133),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS8GCF133", 0x709b1bf1, 0xb2f89b47),
 	PCMCIA_DEVICE_PROD_ID12("WIT", "IDE16", 0x244e5994, 0x3e232852),
 	PCMCIA_DEVICE_PROD_ID12("WEIDA", "TWTTI", 0xcc7cf69c, 0x212bb918),

drivers/base/iommu.c

diff --git a/drivers/base/iommu.c b/drivers/base/iommu.c
index 8ad4ffe..6e6b6a1 100644
--- a/drivers/base/iommu.c
+++ b/drivers/base/iommu.c
@@ -80,20 +80,6 @@
 }
 EXPORT_SYMBOL_GPL(iommu_detach_device);
 
-int iommu_map_range(struct iommu_domain *domain, unsigned long iova,
-		    phys_addr_t paddr, size_t size, int prot)
-{
-	return iommu_ops->map(domain, iova, paddr, size, prot);
-}
-EXPORT_SYMBOL_GPL(iommu_map_range);
-
-void iommu_unmap_range(struct iommu_domain *domain, unsigned long iova,
-		      size_t size)
-{
-	iommu_ops->unmap(domain, iova, size);
-}
-EXPORT_SYMBOL_GPL(iommu_unmap_range);
-
 phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
 			       unsigned long iova)
 {
@@ -107,3 +93,32 @@
 	return iommu_ops->domain_has_cap(domain, cap);
 }
 EXPORT_SYMBOL_GPL(iommu_domain_has_cap);
+
+int iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, int gfp_order, int prot)
+{
+	unsigned long invalid_mask;
+	size_t size;
+
+	size         = 0x1000UL << gfp_order;
+	invalid_mask = size - 1;
+
+	BUG_ON((iova | paddr) & invalid_mask);
+
+	return iommu_ops->map(domain, iova, paddr, gfp_order, prot);
+}
+EXPORT_SYMBOL_GPL(iommu_map);
+
+int iommu_unmap(struct iommu_domain *domain, unsigned long iova, int gfp_order)
+{
+	unsigned long invalid_mask;
+	size_t size;
+
+	size         = 0x1000UL << gfp_order;
+	invalid_mask = size - 1;
+
+	BUG_ON(iova & invalid_mask);
+
+	return iommu_ops->unmap(domain, iova, gfp_order);
+}
+EXPORT_SYMBOL_GPL(iommu_unmap);

drivers/base/platform.c

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 4b4b565..c5fbe19 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -187,7 +187,7 @@
  * released.
  */
 int platform_device_add_resources(struct platform_device *pdev,
-				  struct resource *res, unsigned int num)
+				  const struct resource *res, unsigned int num)
 {
 	struct resource *r;
 
@@ -367,7 +367,7 @@
  */
 struct platform_device *platform_device_register_simple(const char *name,
 							int id,
-							struct resource *res,
+							const struct resource *res,
 							unsigned int num)
 {
 	struct platform_device *pdev;

drivers/block/amiflop.c

diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 0182a22..832798a 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -66,6 +66,7 @@
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
 #include <linux/interrupt.h>
+#include <linux/platform_device.h>
 
 #include <asm/setup.h>
 #include <asm/uaccess.h>
@@ -1696,34 +1697,18 @@
 	return get_disk(unit[drive].gendisk);
 }
 
-static int __init amiga_floppy_init(void)
+static int __init amiga_floppy_probe(struct platform_device *pdev)
 {
 	int i, ret;
 
-	if (!MACH_IS_AMIGA)
-		return -ENODEV;
-
-	if (!AMIGAHW_PRESENT(AMI_FLOPPY))
-		return -ENODEV;
-
 	if (register_blkdev(FLOPPY_MAJOR,"fd"))
 		return -EBUSY;
 
-	/*
-	 *  We request DSKPTR, DSKLEN and DSKDATA only, because the other
-	 *  floppy registers are too spreaded over the custom register space
-	 */
-	ret = -EBUSY;
-	if (!request_mem_region(CUSTOM_PHYSADDR+0x20, 8, "amiflop [Paula]")) {
-		printk("fd: cannot get floppy registers\n");
-		goto out_blkdev;
-	}
-
 	ret = -ENOMEM;
 	if ((raw_buf = (char *)amiga_chip_alloc (RAW_BUF_SIZE, "Floppy")) ==
 	    NULL) {
 		printk("fd: cannot get chip mem buffer\n");
-		goto out_memregion;
+		goto out_blkdev;
 	}
 
 	ret = -EBUSY;
@@ -1792,18 +1777,13 @@
 	free_irq(IRQ_AMIGA_DSKBLK, NULL);
 out_irq:
 	amiga_chip_free(raw_buf);
-out_memregion:
-	release_mem_region(CUSTOM_PHYSADDR+0x20, 8);
 out_blkdev:
 	unregister_blkdev(FLOPPY_MAJOR,"fd");
 	return ret;
 }
 
-module_init(amiga_floppy_init);
-#ifdef MODULE
-
 #if 0 /* not safe to unload */
-void cleanup_module(void)
+static int __exit amiga_floppy_remove(struct platform_device *pdev)
 {
 	int i;
 
@@ -1820,12 +1800,25 @@
 	custom.dmacon = DMAF_DISK; /* disable DMA */
 	amiga_chip_free(raw_buf);
 	blk_cleanup_queue(floppy_queue);
-	release_mem_region(CUSTOM_PHYSADDR+0x20, 8);
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 }
 #endif
 
-#else
+static struct platform_driver amiga_floppy_driver = {
+	.driver   = {
+		.name	= "amiga-floppy",
+		.owner	= THIS_MODULE,
+	},
+};
+
+static int __init amiga_floppy_init(void)
+{
+	return platform_driver_probe(&amiga_floppy_driver, amiga_floppy_probe);
+}
+
+module_init(amiga_floppy_init);
+
+#ifndef MODULE
 static int __init amiga_floppy_setup (char *str)
 {
 	int n;
@@ -1840,3 +1833,5 @@
 
 __setup("floppy=", amiga_floppy_setup);
 #endif
+
+MODULE_ALIAS("platform:amiga-floppy");

drivers/block/drbd/drbd_worker.c

diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 44bf6d1..d48a1df 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -235,7 +235,7 @@
 	if (unlikely(error)) {
 		what = (bio_data_dir(bio) == WRITE)
 			? write_completed_with_error
-			: (bio_rw(bio) == READA)
+			: (bio_rw(bio) == READ)
 			  ? read_completed_with_error
 			  : read_ahead_completed_with_error;
 	} else

drivers/block/hd.c

diff --git a/drivers/block/hd.c b/drivers/block/hd.c
index 034e6df..81c78b3 100644
--- a/drivers/block/hd.c
+++ b/drivers/block/hd.c
@@ -164,12 +164,12 @@
 	unsigned long t, flags;
 	int i;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 	t = jiffies * 11932;
 	outb_p(0, 0x43);
 	i = inb_p(0x40);
 	i |= inb(0x40) << 8;
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 	return(t - i);
 }
 #endif

drivers/char/isicom.c

diff --git a/drivers/char/isicom.c b/drivers/char/isicom.c
index 0fa2e4a..c1ab303 100644
--- a/drivers/char/isicom.c
+++ b/drivers/char/isicom.c
@@ -879,8 +879,8 @@
 	if (tport == NULL)
 		return -ENODEV;
 	port = container_of(tport, struct isi_port, port);
-	card = &isi_card[BOARD(tty->index)];
 
+	tty->driver_data = port;
 	return tty_port_open(tport, tty, filp);
 }
 
@@ -936,7 +936,12 @@
 static void isicom_close(struct tty_struct *tty, struct file *filp)
 {
 	struct isi_port *ip = tty->driver_data;
-	struct tty_port *port = &ip->port;
+	struct tty_port *port;
+
+	if (ip == NULL)
+		return;
+
+	port = &ip->port;
 	if (isicom_paranoia_check(ip, tty->name, "isicom_close"))
 		return;
 	tty_port_close(port, tty, filp);

drivers/char/istallion.c

diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c
index 4cd6c52..4e395c9 100644
--- a/drivers/char/istallion.c
+++ b/drivers/char/istallion.c
@@ -827,6 +827,8 @@
 		return -ENODEV;
 	if (portp->devnr < 1)
 		return -ENODEV;
+
+	tty->driver_data = portp;
 	return tty_port_open(&portp->port, tty, filp);
 }
 

drivers/char/mxser.c

diff --git a/drivers/char/mxser.c b/drivers/char/mxser.c
index 4702305..d2692d4 100644
--- a/drivers/char/mxser.c
+++ b/drivers/char/mxser.c
@@ -1011,6 +1011,7 @@
 	if (!info->ioaddr)
 		return -ENODEV;
 
+	tty->driver_data = info;
 	return tty_port_open(&info->port, tty, filp);
 }
 
@@ -1074,7 +1075,7 @@
 	struct mxser_port *info = tty->driver_data;
 	struct tty_port *port = &info->port;
 
-	if (tty->index == MXSER_PORTS)
+	if (tty->index == MXSER_PORTS || info == NULL)
 		return;
 	if (tty_port_close_start(port, tty, filp) == 0)
 		return;

drivers/char/riscom8.c

diff --git a/drivers/char/riscom8.c b/drivers/char/riscom8.c
index 0a8d1e5..b02332a 100644
--- a/drivers/char/riscom8.c
+++ b/drivers/char/riscom8.c
@@ -909,6 +909,7 @@
 	if (error)
 		return error;
 
+	tty->driver_data = port;
 	return tty_port_open(&port->port, tty, filp);
 }
 

drivers/char/serial167.c

diff --git a/drivers/char/serial167.c b/drivers/char/serial167.c
index 8dfd247..78a62eb 100644
--- a/drivers/char/serial167.c
+++ b/drivers/char/serial167.c
@@ -627,7 +627,6 @@
 	char data;
 	int char_count;
 	int save_cnt;
-	int len;
 
 	/* determine the channel and change to that context */
 	channel = (u_short) (base_addr[CyLICR] >> 2);
@@ -1528,7 +1527,6 @@
 cy_ioctl(struct tty_struct *tty, struct file *file,
 	 unsigned int cmd, unsigned long arg)
 {
-	unsigned long val;
 	struct cyclades_port *info = tty->driver_data;
 	int ret_val = 0;
 	void __user *argp = (void __user *)arg;

drivers/char/stallion.c

diff --git a/drivers/char/stallion.c b/drivers/char/stallion.c
index 0e511d6..6049fd7 100644
--- a/drivers/char/stallion.c
+++ b/drivers/char/stallion.c
@@ -724,7 +724,6 @@
 {
 	struct stlport	*portp;
 	struct stlbrd	*brdp;
-	struct tty_port *port;
 	unsigned int	minordev, brdnr, panelnr;
 	int		portnr;
 
@@ -754,7 +753,8 @@
 	portp = brdp->panels[panelnr]->ports[portnr];
 	if (portp == NULL)
 		return -ENODEV;
-	port = &portp->port;
+
+	tty->driver_data = portp;
 	return tty_port_open(&portp->port, tty, filp);
 
 }
@@ -841,7 +841,8 @@
 	pr_debug("stl_close(tty=%p,filp=%p)\n", tty, filp);
 
 	portp = tty->driver_data;
-	BUG_ON(portp == NULL);
+	if(portp == NULL)
+		return;
 	tty_port_close(&portp->port, tty, filp);
 }
 

drivers/char/tty_io.c

diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c
index 6da962c..d71f0fc 100644
--- a/drivers/char/tty_io.c
+++ b/drivers/char/tty_io.c
@@ -1875,6 +1875,7 @@
 		 */
 		if (filp->f_op == &hung_up_tty_fops)
 			filp->f_op = &tty_fops;
+		unlock_kernel();
 		goto retry_open;
 	}
 	unlock_kernel();

drivers/cpuidle/governors/menu.c

diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 1aea715..f8e57c6 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -100,7 +100,6 @@
 	int             needs_update;
 
 	unsigned int	expected_us;
-	unsigned int	measured_us;
 	u64		predicted_us;
 	unsigned int	exit_us;
 	unsigned int	bucket;
@@ -187,14 +186,14 @@
 	int i;
 	int multiplier;
 
-	data->last_state_idx = 0;
-	data->exit_us = 0;
-
 	if (data->needs_update) {
 		menu_update(dev);
 		data->needs_update = 0;
 	}
 
+	data->last_state_idx = 0;
+	data->exit_us = 0;
+
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0))
 		return 0;
@@ -294,7 +293,7 @@
 	new_factor = data->correction_factor[data->bucket]
 			* (DECAY - 1) / DECAY;
 
-	if (data->expected_us > 0 && data->measured_us < MAX_INTERESTING)
+	if (data->expected_us > 0 && measured_us < MAX_INTERESTING)
 		new_factor += RESOLUTION * measured_us / data->expected_us;
 	else
 		/*

drivers/dma/shdma.c

diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c
index 7cc31b3..6f25a20 100644
--- a/drivers/dma/shdma.c
+++ b/drivers/dma/shdma.c
@@ -290,6 +290,7 @@
 	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
 	struct sh_desc *desc;
 	struct sh_dmae_slave *param = chan->private;
+	int ret;
 
 	pm_runtime_get_sync(sh_chan->dev);
 
@@ -301,11 +302,15 @@
 		struct sh_dmae_slave_config *cfg;
 
 		cfg = sh_dmae_find_slave(sh_chan, param->slave_id);
-		if (!cfg)
-			return -EINVAL;
+		if (!cfg) {
+			ret = -EINVAL;
+			goto efindslave;
+		}
 
-		if (test_and_set_bit(param->slave_id, sh_dmae_slave_used))
-			return -EBUSY;
+		if (test_and_set_bit(param->slave_id, sh_dmae_slave_used)) {
+			ret = -EBUSY;
+			goto etestused;
+		}
 
 		param->config = cfg;
 
@@ -334,10 +339,20 @@
 	}
 	spin_unlock_bh(&sh_chan->desc_lock);
 
-	if (!sh_chan->descs_allocated)
-		pm_runtime_put(sh_chan->dev);
+	if (!sh_chan->descs_allocated) {
+		ret = -ENOMEM;
+		goto edescalloc;
+	}
 
 	return sh_chan->descs_allocated;
+
+edescalloc:
+	if (param)
+		clear_bit(param->slave_id, sh_dmae_slave_used);
+etestused:
+efindslave:
+	pm_runtime_put(sh_chan->dev);
+	return ret;
 }
 
 /*

drivers/dma/txx9dmac.c

diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index 3ebc610..75fcf1a 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -1359,3 +1359,5 @@
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("TXx9 DMA Controller driver");
 MODULE_AUTHOR("Atsushi Nemoto <anemo@mba.ocn.ne.jp>");
+MODULE_ALIAS("platform:txx9dmac");
+MODULE_ALIAS("platform:txx9dmac-chan");

drivers/edac/edac_mce_amd.c

diff --git a/drivers/edac/edac_mce_amd.c b/drivers/edac/edac_mce_amd.c
index f5b6d9f..97e64bc 100644
--- a/drivers/edac/edac_mce_amd.c
+++ b/drivers/edac/edac_mce_amd.c
@@ -294,7 +294,6 @@
 void amd_decode_nb_mce(int node_id, struct err_regs *regs, int handle_errors)
 {
 	u32 ec  = ERROR_CODE(regs->nbsl);
-	u32 xec = EXT_ERROR_CODE(regs->nbsl);
 
 	if (!handle_errors)
 		return;
@@ -324,7 +323,7 @@
 		pr_cont("\n");
 	}
 
-	pr_emerg("%s.\n", EXT_ERR_MSG(xec));
+	pr_emerg("%s.\n", EXT_ERR_MSG(regs->nbsl));
 
 	if (BUS_ERROR(ec) && nb_bus_decoder)
 		nb_bus_decoder(node_id, regs);
@@ -374,7 +373,7 @@
 		 ((m->status & MCI_STATUS_PCC) ? "yes" : "no"));
 
 	/* do the two bits[14:13] together */
-	ecc = m->status & (3ULL << 45);
+	ecc = (m->status >> 45) & 0x3;
 	if (ecc)
 		pr_cont(", %sECC Error", ((ecc == 2) ? "C" : "U"));
 

drivers/gpio/gpiolib.c

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 76be229..eb0c3fe 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -416,7 +416,8 @@
 	return 0;
 
 free_sd:
-	sysfs_put(pdesc->value_sd);
+	if (pdesc)
+		sysfs_put(pdesc->value_sd);
 free_id:
 	idr_remove(&pdesc_idr, id);
 	desc->flags &= GPIO_FLAGS_MASK;

drivers/gpio/it8761e_gpio.c

diff --git a/drivers/gpio/it8761e_gpio.c b/drivers/gpio/it8761e_gpio.c
index 753219c..41a9388 100644
--- a/drivers/gpio/it8761e_gpio.c
+++ b/drivers/gpio/it8761e_gpio.c
@@ -80,8 +80,8 @@
 	u16 reg;
 	u8 bit;
 
-	bit = gpio_num % 7;
-	reg = (gpio_num >= 7) ? gpio_ba + 1 : gpio_ba;
+	bit = gpio_num % 8;
+	reg = (gpio_num >= 8) ? gpio_ba + 1 : gpio_ba;
 
 	return !!(inb(reg) & (1 << bit));
 }
@@ -91,8 +91,8 @@
 	u8 curr_dirs;
 	u8 io_reg, bit;
 
-	bit = gpio_num % 7;
-	io_reg = (gpio_num >= 7) ? GPIO2X_IO : GPIO1X_IO;
+	bit = gpio_num % 8;
+	io_reg = (gpio_num >= 8) ? GPIO2X_IO : GPIO1X_IO;
 
 	spin_lock(&sio_lock);
 
@@ -116,8 +116,8 @@
 	u8 curr_vals, bit;
 	u16 reg;
 
-	bit = gpio_num % 7;
-	reg = (gpio_num >= 7) ? gpio_ba + 1 : gpio_ba;
+	bit = gpio_num % 8;
+	reg = (gpio_num >= 8) ? gpio_ba + 1 : gpio_ba;
 
 	spin_lock(&sio_lock);
 
@@ -135,8 +135,8 @@
 {
 	u8 curr_dirs, io_reg, bit;
 
-	bit = gpio_num % 7;
-	io_reg = (gpio_num >= 7) ? GPIO2X_IO : GPIO1X_IO;
+	bit = gpio_num % 8;
+	io_reg = (gpio_num >= 8) ? GPIO2X_IO : GPIO1X_IO;
 
 	it8761e_gpio_set(gc, gpio_num, val);
 
@@ -200,7 +200,7 @@
 		return -EBUSY;
 
 	it8761e_gpio_chip.base = -1;
-	it8761e_gpio_chip.ngpio = 14;
+	it8761e_gpio_chip.ngpio = 16;
 
 	err = gpiochip_add(&it8761e_gpio_chip);
 	if (err < 0)

drivers/gpu/drm/drm_memory.c

diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c
index e4865f9..7732268 100644
--- a/drivers/gpu/drm/drm_memory.c
+++ b/drivers/gpu/drm/drm_memory.c
@@ -77,7 +77,7 @@
 		    && (agpmem->bound + (agpmem->pages << PAGE_SHIFT)) >=
 		    (offset + size))
 			break;
-	if (!agpmem)
+	if (&agpmem->head == &dev->agp->memory)
 		return NULL;
 
 	/*

drivers/gpu/drm/drm_sysfs.c

diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index 1a1825b..25bbd30 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -354,7 +354,10 @@
 int drm_sysfs_connector_add(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	int ret = 0, i, j;
+	int attr_cnt = 0;
+	int opt_cnt = 0;
+	int i;
+	int ret = 0;
 
 	/* We shouldn't get called more than once for the same connector */
 	BUG_ON(device_is_registered(&connector->kdev));
@@ -377,8 +380,8 @@
 
 	/* Standard attributes */
 
-	for (i = 0; i < ARRAY_SIZE(connector_attrs); i++) {
-		ret = device_create_file(&connector->kdev, &connector_attrs[i]);
+	for (attr_cnt = 0; attr_cnt < ARRAY_SIZE(connector_attrs); attr_cnt++) {
+		ret = device_create_file(&connector->kdev, &connector_attrs[attr_cnt]);
 		if (ret)
 			goto err_out_files;
 	}
@@ -394,8 +397,8 @@
 		case DRM_MODE_CONNECTOR_SVIDEO:
 		case DRM_MODE_CONNECTOR_Component:
 		case DRM_MODE_CONNECTOR_TV:
-			for (i = 0; i < ARRAY_SIZE(connector_attrs_opt1); i++) {
-				ret = device_create_file(&connector->kdev, &connector_attrs_opt1[i]);
+			for (opt_cnt = 0; opt_cnt < ARRAY_SIZE(connector_attrs_opt1); opt_cnt++) {
+				ret = device_create_file(&connector->kdev, &connector_attrs_opt1[opt_cnt]);
 				if (ret)
 					goto err_out_files;
 			}
@@ -414,10 +417,10 @@
 	return 0;
 
 err_out_files:
-	if (i > 0)
-		for (j = 0; j < i; j++)
-			device_remove_file(&connector->kdev,
-					   &connector_attrs[i]);
+	for (i = 0; i < opt_cnt; i++)
+		device_remove_file(&connector->kdev, &connector_attrs_opt1[i]);
+	for (i = 0; i < attr_cnt; i++)
+		device_remove_file(&connector->kdev, &connector_attrs[i]);
 	device_unregister(&connector->kdev);
 
 out:

drivers/gpu/drm/i915/i915_irq.c

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 2b8b969..df6a9cd 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -456,11 +456,15 @@
 
 	for (page = 0; page < page_count; page++) {
 		void *s, *d = kmalloc(PAGE_SIZE, GFP_ATOMIC);
+		unsigned long flags;
+
 		if (d == NULL)
 			goto unwind;
-		s = kmap_atomic(src_priv->pages[page], KM_USER0);
+		local_irq_save(flags);
+		s = kmap_atomic(src_priv->pages[page], KM_IRQ0);
 		memcpy(d, s, PAGE_SIZE);
-		kunmap_atomic(s, KM_USER0);
+		kunmap_atomic(s, KM_IRQ0);
+		local_irq_restore(flags);
 		dst->pages[page] = d;
 	}
 	dst->page_count = page_count;

drivers/gpu/drm/radeon/atombios.h

diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h
index 6732b5d..27e2c71 100644
--- a/drivers/gpu/drm/radeon/atombios.h
+++ b/drivers/gpu/drm/radeon/atombios.h
@@ -2912,7 +2912,7 @@
   UCHAR                    ucTV_BootUpDefaultStandard; 
   UCHAR                    ucExt_TV_ASIC_ID;
   UCHAR                    ucExt_TV_ASIC_SlaveAddr;
-  ATOM_DTD_FORMAT          aModeTimings[MAX_SUPPORTED_TV_TIMING];
+  ATOM_DTD_FORMAT          aModeTimings[MAX_SUPPORTED_TV_TIMING_V1_2];
 }ATOM_ANALOG_TV_INFO_V1_2;
 
 typedef struct _ATOM_DPCD_INFO

drivers/gpu/drm/radeon/r100.c

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index d7388fd..cf60c0b 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2975,7 +2975,7 @@
 
 	for (i = 0; i < track->num_cb; i++) {
 		if (track->cb[i].robj == NULL) {
-			if (!(track->fastfill || track->color_channel_mask ||
+			if (!(track->zb_cb_clear || track->color_channel_mask ||
 			      track->blend_read_enable)) {
 				continue;
 			}

drivers/gpu/drm/radeon/r100_track.h

diff --git a/drivers/gpu/drm/radeon/r100_track.h b/drivers/gpu/drm/radeon/r100_track.h
index fadfe68..f47cdca 100644
--- a/drivers/gpu/drm/radeon/r100_track.h
+++ b/drivers/gpu/drm/radeon/r100_track.h
@@ -75,7 +75,7 @@
 	struct r100_cs_track_texture	textures[R300_TRACK_MAX_TEXTURE];
 	bool				z_enabled;
 	bool                            separate_cube;
-	bool				fastfill;
+	bool				zb_cb_clear;
 	bool				blend_read_enable;
 };
 

drivers/gpu/drm/radeon/r300.c

diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index eaf1f6b..a5ff807 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -1044,7 +1044,7 @@
 		break;
 	case 0x4d1c:
 		/* ZB_BW_CNTL */
-		track->fastfill = !!(idx_value & (1 << 2));
+		track->zb_cb_clear = !!(idx_value & (1 << 5));
 		break;
 	case 0x4e04:
 		/* RB3D_BLENDCNTL */

drivers/gpu/drm/radeon/radeon_agp.c

diff --git a/drivers/gpu/drm/radeon/radeon_agp.c b/drivers/gpu/drm/radeon/radeon_agp.c
index c445779..28e473f 100644
--- a/drivers/gpu/drm/radeon/radeon_agp.c
+++ b/drivers/gpu/drm/radeon/radeon_agp.c
@@ -134,12 +134,10 @@
 	int ret;
 
 	/* Acquire AGP. */
-	if (!rdev->ddev->agp->acquired) {
-		ret = drm_agp_acquire(rdev->ddev);
-		if (ret) {
-			DRM_ERROR("Unable to acquire AGP: %d\n", ret);
-			return ret;
-		}
+	ret = drm_agp_acquire(rdev->ddev);
+	if (ret) {
+		DRM_ERROR("Unable to acquire AGP: %d\n", ret);
+		return ret;
 	}
 
 	ret = drm_agp_info(rdev->ddev, &info);

drivers/gpu/drm/radeon/radeon_atombios.c

diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 5673665..9916d825 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1264,7 +1264,7 @@
 	switch (crev) {
 	case 1:
 		tv_info = (ATOM_ANALOG_TV_INFO *)(mode_info->atom_context->bios + data_offset);
-		if (index > MAX_SUPPORTED_TV_TIMING)
+		if (index >= MAX_SUPPORTED_TV_TIMING)
 			return false;
 
 		mode->crtc_htotal = le16_to_cpu(tv_info->aModeTimings[index].usCRTC_H_Total);
@@ -1302,7 +1302,7 @@
 		break;
 	case 2:
 		tv_info_v1_2 = (ATOM_ANALOG_TV_INFO_V1_2 *)(mode_info->atom_context->bios + data_offset);
-		if (index > MAX_SUPPORTED_TV_TIMING_V1_2)
+		if (index >= MAX_SUPPORTED_TV_TIMING_V1_2)
 			return false;
 
 		dtd_timings = &tv_info_v1_2->aModeTimings[index];

drivers/gpu/drm/radeon/radeon_connectors.c

diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 1331351..4559a53 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1316,6 +1316,8 @@
 			radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "DVI");
 			if (!radeon_connector->ddc_bus)
 				goto failed;
+		}
+		if (connector_type == DRM_MODE_CONNECTOR_DVII) {
 			radeon_connector->dac_load_detect = true;
 			drm_connector_attach_property(&radeon_connector->base,
 						      rdev->mode_info.load_detect_property,

drivers/gpu/drm/radeon/radeon_drv.c

diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 4b05563..b3749d4 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -216,6 +216,7 @@
 		 .mmap = drm_mmap,
 		 .poll = drm_poll,
 		 .fasync = drm_fasync,
+		 .read = drm_read,
 #ifdef CONFIG_COMPAT
 		 .compat_ioctl = radeon_compat_ioctl,
 #endif
@@ -304,6 +305,7 @@
 		 .mmap = radeon_mmap,
 		 .poll = drm_poll,
 		 .fasync = drm_fasync,
+		 .read = drm_read,
 #ifdef CONFIG_COMPAT
 		 .compat_ioctl = radeon_kms_compat_ioctl,
 #endif

drivers/gpu/drm/radeon/radeon_encoders.c

diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index fed7b808..c5ddaf5 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -254,6 +254,53 @@
 	return dig_connector;
 }
 
+void radeon_panel_mode_fixup(struct drm_encoder *encoder,
+			     struct drm_display_mode *adjusted_mode)
+{
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct drm_display_mode *native_mode = &radeon_encoder->native_mode;
+	unsigned hblank = native_mode->htotal - native_mode->hdisplay;
+	unsigned vblank = native_mode->vtotal - native_mode->vdisplay;
+	unsigned hover = native_mode->hsync_start - native_mode->hdisplay;
+	unsigned vover = native_mode->vsync_start - native_mode->vdisplay;
+	unsigned hsync_width = native_mode->hsync_end - native_mode->hsync_start;
+	unsigned vsync_width = native_mode->vsync_end - native_mode->vsync_start;
+
+	adjusted_mode->clock = native_mode->clock;
+	adjusted_mode->flags = native_mode->flags;
+
+	if (ASIC_IS_AVIVO(rdev)) {
+		adjusted_mode->hdisplay = native_mode->hdisplay;
+		adjusted_mode->vdisplay = native_mode->vdisplay;
+	}
+
+	adjusted_mode->htotal = native_mode->hdisplay + hblank;
+	adjusted_mode->hsync_start = native_mode->hdisplay + hover;
+	adjusted_mode->hsync_end = adjusted_mode->hsync_start + hsync_width;
+
+	adjusted_mode->vtotal = native_mode->vdisplay + vblank;
+	adjusted_mode->vsync_start = native_mode->vdisplay + vover;
+	adjusted_mode->vsync_end = adjusted_mode->vsync_start + vsync_width;
+
+	drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V);
+
+	if (ASIC_IS_AVIVO(rdev)) {
+		adjusted_mode->crtc_hdisplay = native_mode->hdisplay;
+		adjusted_mode->crtc_vdisplay = native_mode->vdisplay;
+	}
+
+	adjusted_mode->crtc_htotal = adjusted_mode->crtc_hdisplay + hblank;
+	adjusted_mode->crtc_hsync_start = adjusted_mode->crtc_hdisplay + hover;
+	adjusted_mode->crtc_hsync_end = adjusted_mode->crtc_hsync_start + hsync_width;
+
+	adjusted_mode->crtc_vtotal = adjusted_mode->crtc_vdisplay + vblank;
+	adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + vover;
+	adjusted_mode->crtc_vsync_end = adjusted_mode->crtc_vsync_start + vsync_width;
+
+}
+
 static bool radeon_atom_mode_fixup(struct drm_encoder *encoder,
 				   struct drm_display_mode *mode,
 				   struct drm_display_mode *adjusted_mode)
@@ -275,18 +322,8 @@
 		adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2;
 
 	/* get the native mode for LVDS */
-	if (radeon_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) {
-		struct drm_display_mode *native_mode = &radeon_encoder->native_mode;
-		int mode_id = adjusted_mode->base.id;
-		*adjusted_mode = *native_mode;
-		if (!ASIC_IS_AVIVO(rdev)) {
-			adjusted_mode->hdisplay = mode->hdisplay;
-			adjusted_mode->vdisplay = mode->vdisplay;
-			adjusted_mode->crtc_hdisplay = mode->hdisplay;
-			adjusted_mode->crtc_vdisplay = mode->vdisplay;
-		}
-		adjusted_mode->base.id = mode_id;
-	}
+	if (radeon_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT))
+		radeon_panel_mode_fixup(encoder, adjusted_mode);
 
 	/* get the native mode for TV */
 	if (radeon_encoder->active_device & (ATOM_DEVICE_TV_SUPPORT)) {

drivers/gpu/drm/radeon/radeon_legacy_encoders.c

diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
index 2441cca..0274abe 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
@@ -228,16 +228,8 @@
 	drm_mode_set_crtcinfo(adjusted_mode, 0);
 
 	/* get the native mode for LVDS */
-	if (radeon_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) {
-		struct drm_display_mode *native_mode = &radeon_encoder->native_mode;
-		int mode_id = adjusted_mode->base.id;
-		*adjusted_mode = *native_mode;
-		adjusted_mode->hdisplay = mode->hdisplay;
-		adjusted_mode->vdisplay = mode->vdisplay;
-		adjusted_mode->crtc_hdisplay = mode->hdisplay;
-		adjusted_mode->crtc_vdisplay = mode->vdisplay;
-		adjusted_mode->base.id = mode_id;
-	}
+	if (radeon_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT))
+		radeon_panel_mode_fixup(encoder, adjusted_mode);
 
 	return true;
 }

drivers/gpu/drm/radeon/radeon_mode.h

diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 0b8e327..5413fcd 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -558,6 +558,8 @@
 bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
 					struct drm_display_mode *mode,
 					struct drm_display_mode *adjusted_mode);
+void radeon_panel_mode_fixup(struct drm_encoder *encoder,
+			     struct drm_display_mode *adjusted_mode);
 void atom_rv515_force_tv_scaler(struct radeon_device *rdev, struct radeon_crtc *radeon_crtc);
 
 /* legacy tv */

drivers/gpu/drm/radeon/radeon_state.c

diff --git a/drivers/gpu/drm/radeon/radeon_state.c b/drivers/gpu/drm/radeon/radeon_state.c
index 40ab6d9..cc5316d 100644
--- a/drivers/gpu/drm/radeon/radeon_state.c
+++ b/drivers/gpu/drm/radeon/radeon_state.c
@@ -424,7 +424,7 @@
 		if ((*cmd & RADEON_GMC_SRC_PITCH_OFFSET_CNTL) &&
 		    (*cmd & RADEON_GMC_DST_PITCH_OFFSET_CNTL)) {
 			u32 *cmd3 = drm_buffer_pointer_to_dword(cmdbuf->buffer, 3);
-			offset = *cmd << 10;
+			offset = *cmd3 << 10;
 			if (radeon_check_and_fixup_offset
 			    (dev_priv, file_priv, &offset)) {
 				DRM_ERROR("Invalid second packet offset\n");
@@ -2895,9 +2895,12 @@
 			return rv;
 		rv = drm_buffer_copy_from_user(cmdbuf->buffer, buffer,
 						cmdbuf->bufsz);
-		if (rv)
+		if (rv) {
+			drm_buffer_free(cmdbuf->buffer);
 			return rv;
-	}
+		}
+	} else
+		goto done;
 
 	orig_nbox = cmdbuf->nbox;
 
@@ -2905,8 +2908,7 @@
 		int temp;
 		temp = r300_do_cp_cmdbuf(dev, file_priv, cmdbuf);
 
-		if (cmdbuf->bufsz != 0)
-			drm_buffer_free(cmdbuf->buffer);
+		drm_buffer_free(cmdbuf->buffer);
 
 		return temp;
 	}
@@ -3012,16 +3014,15 @@
 		}
 	}
 
-	if (cmdbuf->bufsz != 0)
-		drm_buffer_free(cmdbuf->buffer);
+	drm_buffer_free(cmdbuf->buffer);
 
+      done:
 	DRM_DEBUG("DONE\n");
 	COMMIT_RING();
 	return 0;
 
       err:
-	if (cmdbuf->bufsz != 0)
-		drm_buffer_free(cmdbuf->buffer);
+	drm_buffer_free(cmdbuf->buffer);
 	return -EINVAL;
 }
 

drivers/gpu/drm/ttm/ttm_bo.c

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index dd47b2a..0e3754a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1716,40 +1716,12 @@
 }
 EXPORT_SYMBOL(ttm_bo_wait);
 
-void ttm_bo_unblock_reservation(struct ttm_buffer_object *bo)
-{
-	atomic_set(&bo->reserved, 0);
-	wake_up_all(&bo->event_queue);
-}
-
-int ttm_bo_block_reservation(struct ttm_buffer_object *bo, bool interruptible,
-			     bool no_wait)
-{
-	int ret;
-
-	while (unlikely(atomic_cmpxchg(&bo->reserved, 0, 1) != 0)) {
-		if (no_wait)
-			return -EBUSY;
-		else if (interruptible) {
-			ret = wait_event_interruptible
-			    (bo->event_queue, atomic_read(&bo->reserved) == 0);
-			if (unlikely(ret != 0))
-				return ret;
-		} else {
-			wait_event(bo->event_queue,
-				   atomic_read(&bo->reserved) == 0);
-		}
-	}
-	return 0;
-}
-
 int ttm_bo_synccpu_write_grab(struct ttm_buffer_object *bo, bool no_wait)
 {
 	int ret = 0;
 
 	/*
-	 * Using ttm_bo_reserve instead of ttm_bo_block_reservation
-	 * makes sure the lru lists are updated.
+	 * Using ttm_bo_reserve makes sure the lru lists are updated.
 	 */
 
 	ret = ttm_bo_reserve(bo, true, no_wait, false, 0);

drivers/gpu/drm/ttm/ttm_lock.c

diff --git a/drivers/gpu/drm/ttm/ttm_lock.c b/drivers/gpu/drm/ttm/ttm_lock.c
index 3d172ef..de41e55 100644
--- a/drivers/gpu/drm/ttm/ttm_lock.c
+++ b/drivers/gpu/drm/ttm/ttm_lock.c
@@ -204,7 +204,6 @@
 	lock->flags &= ~TTM_VT_LOCK;
 	wake_up_all(&lock->queue);
 	spin_unlock(&lock->lock);
-	printk(KERN_INFO TTM_PFX "vt unlock.\n");
 
 	return ret;
 }
@@ -265,10 +264,8 @@
 				   ttm_lock_type, &ttm_vt_lock_remove, NULL);
 	if (ret)
 		(void)__ttm_vt_unlock(lock);
-	else {
+	else
 		lock->vt_holder = tfile;
-		printk(KERN_INFO TTM_PFX "vt lock.\n");
-	}
 
 	return ret;
 }

drivers/gpu/drm/via/via_video.c

diff --git a/drivers/gpu/drm/via/via_video.c b/drivers/gpu/drm/via/via_video.c
index 6ec04ac..6efac81 100644
--- a/drivers/gpu/drm/via/via_video.c
+++ b/drivers/gpu/drm/via/via_video.c
@@ -75,7 +75,7 @@
 
 	DRM_DEBUG("\n");
 
-	if (fx->lock > VIA_NR_XVMC_LOCKS)
+	if (fx->lock >= VIA_NR_XVMC_LOCKS)
 		return -EFAULT;
 
 	lock = (volatile int *)XVMCLOCKPTR(sAPriv, fx->lock);

drivers/gpu/vga/vga_switcheroo.c

diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index d6d1149..c8768f3 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -276,8 +276,10 @@
 
 	mutex_lock(&vgasr_mutex);
 
-	if (!vgasr_priv.active)
-		return -EINVAL;
+	if (!vgasr_priv.active) {
+		cnt = -EINVAL;
+		goto out;
+	}
 
 	/* pwr off the device not in use */
 	if (strncmp(usercmd, "OFF", 3) == 0) {

drivers/hid/hid-cherry.c

diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c
index 7e597d7..24663a8 100644
--- a/drivers/hid/hid-cherry.c
+++ b/drivers/hid/hid-cherry.c
@@ -59,6 +59,7 @@
 
 static const struct hid_device_id ch_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_CYMOTION) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, ch_devices);

drivers/hid/hid-core.c

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 2e2aa75..143e788 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1043,13 +1043,8 @@
 
 	if ((hid->claimed & HID_CLAIMED_HIDDEV) && hid->hiddev_report_event)
 		hid->hiddev_report_event(hid, report);
-	if (hid->claimed & HID_CLAIMED_HIDRAW) {
-		/* numbered reports need to be passed with the report num */
-		if (report_enum->numbered)
-			hidraw_report_event(hid, data - 1, size + 1);
-		else
-			hidraw_report_event(hid, data, size);
-	}
+	if (hid->claimed & HID_CLAIMED_HIDRAW)
+		hidraw_report_event(hid, data, size);
 
 	for (a = 0; a < report->maxfield; a++)
 		hid_input_field(hid, report->field[a], cdata, interrupt);
@@ -1296,6 +1291,7 @@
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_BELKIN, USB_DEVICE_ID_FLIP_KVM) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_CYMOTION) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_TACTICAL_PAD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_1) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_2) },

drivers/hid/hid-ids.h

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 797e064..09d2764 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -131,6 +131,7 @@
 
 #define USB_VENDOR_ID_CHERRY		0x046a
 #define USB_DEVICE_ID_CHERRY_CYMOTION	0x0023
+#define USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR	0x0027
 
 #define USB_VENDOR_ID_CHIC		0x05fe
 #define USB_DEVICE_ID_CHIC_GAMEPAD	0x0014

drivers/hid/hid-ntrig.c

diff --git a/drivers/hid/hid-ntrig.c b/drivers/hid/hid-ntrig.c
index 9b24fc5..4777bbf 100644
--- a/drivers/hid/hid-ntrig.c
+++ b/drivers/hid/hid-ntrig.c
@@ -1,8 +1,8 @@
 /*
  *  HID driver for N-Trig touchscreens
  *
- *  Copyright (c) 2008 Rafi Rubin
- *  Copyright (c) 2009 Stephane Chatty
+ *  Copyright (c) 2008-2010 Rafi Rubin
+ *  Copyright (c) 2009-2010 Stephane Chatty
  *
  */
 
@@ -15,6 +15,8 @@
 
 #include <linux/device.h>
 #include <linux/hid.h>
+#include <linux/usb.h>
+#include "usbhid/usbhid.h"
 #include <linux/module.h>
 #include <linux/slab.h>
 
@@ -22,17 +24,16 @@
 
 #define NTRIG_DUPLICATE_USAGES	0x001
 
-#define nt_map_key_clear(c)	hid_map_usage_clear(hi, usage, bit, max, \
-					EV_KEY, (c))
-
 struct ntrig_data {
 	/* Incoming raw values for a single contact */
 	__u16 x, y, w, h;
 	__u16 id;
-	__u8 confidence;
+
+	bool tipswitch;
+	bool confidence;
+	bool first_contact_touch;
 
 	bool reading_mt;
-	__u8 first_contact_confidence;
 
 	__u8 mt_footer[4];
 	__u8 mt_foot_count;
@@ -139,9 +140,10 @@
 		case 0xff000001:
 			/* Tag indicating the start of a multitouch group */
 			nd->reading_mt = 1;
-			nd->first_contact_confidence = 0;
+			nd->first_contact_touch = 0;
 			break;
 		case HID_DG_TIPSWITCH:
+			nd->tipswitch = value;
 			/* Prevent emission of touch until validated */
 			return 1;
 		case HID_DG_CONFIDENCE:
@@ -169,8 +171,14 @@
 			 * to emit a normal (X, Y) position
 			 */
 			if (!nd->reading_mt) {
+				/*
+				 * TipSwitch indicates the presence of a
+				 * finger in single touch mode.
+				 */
+				input_report_key(input, BTN_TOUCH,
+						 nd->tipswitch);
 				input_report_key(input, BTN_TOOL_DOUBLETAP,
-						 (nd->confidence != 0));
+						 nd->tipswitch);
 				input_event(input, EV_ABS, ABS_X, nd->x);
 				input_event(input, EV_ABS, ABS_Y, nd->y);
 			}
@@ -209,7 +217,13 @@
 
 			/* emit a normal (X, Y) for the first point only */
 			if (nd->id == 0) {
-				nd->first_contact_confidence = nd->confidence;
+				/*
+				 * TipSwitch is superfluous in multitouch
+				 * mode.  The footer events tell us
+				 * if there is a finger on the screen or
+				 * not.
+				 */
+				nd->first_contact_touch = nd->confidence;
 				input_event(input, EV_ABS, ABS_X, nd->x);
 				input_event(input, EV_ABS, ABS_Y, nd->y);
 			}
@@ -239,30 +253,11 @@
 
 			nd->reading_mt = 0;
 
-			if (nd->first_contact_confidence) {
-				switch (value) {
-				case 0:	/* for single touch devices */
-				case 1:
-					input_report_key(input,
-							BTN_TOOL_DOUBLETAP, 1);
-					break;
-				case 2:
-					input_report_key(input,
-							BTN_TOOL_TRIPLETAP, 1);
-					break;
-				case 3:
-				default:
-					input_report_key(input,
-							BTN_TOOL_QUADTAP, 1);
-				}
+			if (nd->first_contact_touch) {
+				input_report_key(input, BTN_TOOL_DOUBLETAP, 1);
 				input_report_key(input, BTN_TOUCH, 1);
 			} else {
-				input_report_key(input,
-						BTN_TOOL_DOUBLETAP, 0);
-				input_report_key(input,
-						BTN_TOOL_TRIPLETAP, 0);
-				input_report_key(input,
-						BTN_TOOL_QUADTAP, 0);
+				input_report_key(input, BTN_TOOL_DOUBLETAP, 0);
 				input_report_key(input, BTN_TOUCH, 0);
 			}
 			break;
@@ -286,6 +281,7 @@
 	struct ntrig_data *nd;
 	struct hid_input *hidinput;
 	struct input_dev *input;
+	struct hid_report *report;
 
 	if (id->driver_data)
 		hdev->quirks |= HID_QUIRK_MULTI_INPUT;
@@ -327,13 +323,7 @@
 			__clear_bit(BTN_TOOL_PEN, input->keybit);
 			__clear_bit(BTN_TOOL_FINGER, input->keybit);
 			__clear_bit(BTN_0, input->keybit);
-			/*
-			 * A little something special to enable
-			 * two and three finger taps.
-			 */
 			__set_bit(BTN_TOOL_DOUBLETAP, input->keybit);
-			__set_bit(BTN_TOOL_TRIPLETAP, input->keybit);
-			__set_bit(BTN_TOOL_QUADTAP, input->keybit);
 			/*
 			 * The physical touchscreen (single touch)
 			 * input has a value for physical, whereas
@@ -349,6 +339,12 @@
 		}
 	}
 
+	/* This is needed for devices with more recent firmware versions */
+	report = hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0x0a];
+	if (report)
+		usbhid_submit_report(hdev, report, USB_DIR_OUT);
+
+
 	return 0;
 err_free:
 	kfree(nd);

drivers/hid/hid-sony.c

diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 7502a4b..402d557 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -76,7 +76,7 @@
 
 static int sony_set_operational_bt(struct hid_device *hdev)
 {
-	unsigned char buf[] = { 0x53, 0xf4,  0x42, 0x03, 0x00, 0x00 };
+	unsigned char buf[] = { 0xf4,  0x42, 0x03, 0x00, 0x00 };
 	return hdev->hid_output_raw_report(hdev, buf, sizeof(buf), HID_FEATURE_REPORT);
 }
 

drivers/hid/hid-wacom.c

diff --git a/drivers/hid/hid-wacom.c b/drivers/hid/hid-wacom.c
index f7700cf..f947d83 100644
--- a/drivers/hid/hid-wacom.c
+++ b/drivers/hid/hid-wacom.c
@@ -277,7 +277,6 @@
 	ret = hid_register_driver(&wacom_driver);
 	if (ret)
 		printk(KERN_ERR "can't register wacom driver\n");
-	printk(KERN_ERR "wacom driver registered\n");
 	return ret;
 }
 

drivers/hid/usbhid/hid-core.c

diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 56d06cd..7b85b69 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -999,13 +999,6 @@
 		}
 	}
 
-	init_waitqueue_head(&usbhid->wait);
-	INIT_WORK(&usbhid->reset_work, hid_reset);
-	INIT_WORK(&usbhid->restart_work, __usbhid_restart_queues);
-	setup_timer(&usbhid->io_retry, hid_retry_timeout, (unsigned long) hid);
-
-	spin_lock_init(&usbhid->lock);
-
 	usbhid->urbctrl = usb_alloc_urb(0, GFP_KERNEL);
 	if (!usbhid->urbctrl) {
 		ret = -ENOMEM;
@@ -1179,6 +1172,12 @@
 	usbhid->intf = intf;
 	usbhid->ifnum = interface->desc.bInterfaceNumber;
 
+	init_waitqueue_head(&usbhid->wait);
+	INIT_WORK(&usbhid->reset_work, hid_reset);
+	INIT_WORK(&usbhid->restart_work, __usbhid_restart_queues);
+	setup_timer(&usbhid->io_retry, hid_retry_timeout, (unsigned long) hid);
+	spin_lock_init(&usbhid->lock);
+
 	ret = hid_add_device(hid);
 	if (ret) {
 		if (ret != -ENODEV)

drivers/hwmon/applesmc.c

diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index 0f28d91..f085c18 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -195,6 +195,9 @@
 /* Indicates whether this computer has light sensors and keyboard backlight. */
 static unsigned int applesmc_light;
 
+/* The number of fans handled by the driver */
+static unsigned int fans_handled;
+
 /* Indicates which temperature sensors set to use. */
 static unsigned int applesmc_temperature_set;
 
@@ -1492,39 +1495,24 @@
 
 	/* create fan files */
 	count = applesmc_get_fan_count();
-	if (count < 0) {
+	if (count < 0)
 		printk(KERN_ERR "applesmc: Cannot get the number of fans.\n");
-	} else {
+	else
 		printk(KERN_INFO "applesmc: %d fans found.\n", count);
 
-		switch (count) {
-		default:
-			printk(KERN_WARNING "applesmc: More than 4 fans found,"
-					" but at most 4 fans are supported"
-						" by the driver.\n");
-		case 4:
-			ret = sysfs_create_group(&pdev->dev.kobj,
-						 &fan_attribute_groups[3]);
-			if (ret)
-				goto out_key_enumeration;
-		case 3:
-			ret = sysfs_create_group(&pdev->dev.kobj,
-						 &fan_attribute_groups[2]);
-			if (ret)
-				goto out_key_enumeration;
-		case 2:
-			ret = sysfs_create_group(&pdev->dev.kobj,
-						 &fan_attribute_groups[1]);
-			if (ret)
-				goto out_key_enumeration;
-		case 1:
-			ret = sysfs_create_group(&pdev->dev.kobj,
-						 &fan_attribute_groups[0]);
-			if (ret)
-				goto out_fan_1;
-		case 0:
-			;
-		}
+	if (count > 4) {
+		count = 4;
+		printk(KERN_WARNING "applesmc: More than 4 fans found,"
+		       " but at most 4 fans are supported"
+		       " by the driver.\n");
+	}
+
+	while (fans_handled < count) {
+		ret = sysfs_create_group(&pdev->dev.kobj,
+					 &fan_attribute_groups[fans_handled]);
+		if (ret)
+			goto out_fans;
+		fans_handled++;
 	}
 
 	for (i = 0;
@@ -1593,10 +1581,10 @@
 		applesmc_release_accelerometer();
 out_temperature:
 	sysfs_remove_group(&pdev->dev.kobj, &temperature_attributes_group);
-	sysfs_remove_group(&pdev->dev.kobj, &fan_attribute_groups[0]);
-out_fan_1:
-	sysfs_remove_group(&pdev->dev.kobj, &fan_attribute_groups[1]);
-out_key_enumeration:
+out_fans:
+	while (fans_handled)
+		sysfs_remove_group(&pdev->dev.kobj,
+				   &fan_attribute_groups[--fans_handled]);
 	sysfs_remove_group(&pdev->dev.kobj, &key_enumeration_group);
 out_name:
 	sysfs_remove_file(&pdev->dev.kobj, &dev_attr_name.attr);
@@ -1622,8 +1610,9 @@
 	if (applesmc_accelerometer)
 		applesmc_release_accelerometer();
 	sysfs_remove_group(&pdev->dev.kobj, &temperature_attributes_group);
-	sysfs_remove_group(&pdev->dev.kobj, &fan_attribute_groups[0]);
-	sysfs_remove_group(&pdev->dev.kobj, &fan_attribute_groups[1]);
+	while (fans_handled)
+		sysfs_remove_group(&pdev->dev.kobj,
+				   &fan_attribute_groups[--fans_handled]);
 	sysfs_remove_group(&pdev->dev.kobj, &key_enumeration_group);
 	sysfs_remove_file(&pdev->dev.kobj, &dev_attr_name.attr);
 	platform_device_unregister(pdev);

drivers/hwmon/asc7621.c

diff --git a/drivers/hwmon/asc7621.c b/drivers/hwmon/asc7621.c
index 7f94810..0f388ad 100644
--- a/drivers/hwmon/asc7621.c
+++ b/drivers/hwmon/asc7621.c
@@ -268,8 +268,11 @@
 	if (strict_strtol(buf, 10, &reqval))
 		return -EINVAL;
 
+	/* If a minimum RPM of zero is requested, then we set the register to
+	   0xffff. This value allows the fan to be stopped completely without
+	   generating an alarm. */
 	reqval =
-	    (SENSORS_LIMIT((reqval) <= 0 ? 0 : 5400000 / (reqval), 0, 65534));
+	    (reqval <= 0 ? 0xffff : SENSORS_LIMIT(5400000 / reqval, 0, 0xfffe));
 
 	mutex_lock(&data->update_lock);
 	data->reg[param->msb[0]] = (reqval >> 8) & 0xff;
@@ -285,8 +288,9 @@
  * Voltages are scaled in the device so that the nominal voltage
  * is 3/4ths of the 0-255 range (i.e. 192).
  * If all voltages are 'normal' then all voltage registers will
- * read 0xC0.  This doesn't help us if we don't have a point of refernce.
- * The data sheet however provides us with the full scale value for each
+ * read 0xC0.
+ *
+ * The data sheet provides us with the 3/4 scale value for each voltage
  * which is stored in in_scaling.  The sda->index parameter value provides
  * the index into in_scaling.
  *
@@ -295,7 +299,7 @@
  */
 
 static int asc7621_in_scaling[] = {
-	3320, 3000, 4380, 6640, 16000
+	2500, 2250, 3300, 5000, 12000
 };
 
 static ssize_t show_in10(struct device *dev, struct device_attribute *attr,
@@ -306,19 +310,12 @@
 	u8 nr = sda->index;
 
 	mutex_lock(&data->update_lock);
-	regval = (data->reg[param->msb[0]] * asc7621_in_scaling[nr]) / 256;
-
-	/* The LSB value is a 2-bit scaling of the MSB's LSbit value.
-	 * I.E.  If the maximim voltage for this input is 6640 millivolts then
-	 * a MSB register value of 0 = 0mv and 255 = 6640mv.
-	 * A 1 step change therefore represents 25.9mv (6640 / 256).
-	 * The extra 2-bits therefore represent increments of 6.48mv.
-	 */
-	regval += ((asc7621_in_scaling[nr] / 256) / 4) *
-	    (data->reg[param->lsb[0]] >> 6);
-
+	regval = (data->reg[param->msb[0]] << 8) | (data->reg[param->lsb[0]]);
 	mutex_unlock(&data->update_lock);
 
+	/* The LSB value is a 2-bit scaling of the MSB's LSbit value. */
+	regval = (regval >> 6) * asc7621_in_scaling[nr] / (0xc0 << 2);
+
 	return sprintf(buf, "%u\n", regval);
 }
 
@@ -331,7 +328,7 @@
 
 	return sprintf(buf, "%u\n",
 		       ((data->reg[param->msb[0]] *
-			 asc7621_in_scaling[nr]) / 256));
+			 asc7621_in_scaling[nr]) / 0xc0));
 }
 
 static ssize_t store_in8(struct device *dev, struct device_attribute *attr,
@@ -344,9 +341,11 @@
 	if (strict_strtol(buf, 10, &reqval))
 		return -EINVAL;
 
-	reqval = SENSORS_LIMIT(reqval, 0, asc7621_in_scaling[nr]);
+	reqval = SENSORS_LIMIT(reqval, 0, 0xffff);
 
-	reqval = (reqval * 255 + 128) / asc7621_in_scaling[nr];
+	reqval = reqval * 0xc0 / asc7621_in_scaling[nr];
+
+	reqval = SENSORS_LIMIT(reqval, 0, 0xff);
 
 	mutex_lock(&data->update_lock);
 	data->reg[param->msb[0]] = reqval;
@@ -846,11 +845,11 @@
 	PWRITE(in3_max, 3, PRI_LOW, 0x4b, 0, 0, 0, in8),
 	PWRITE(in4_max, 4, PRI_LOW, 0x4d, 0, 0, 0, in8),
 
-	PREAD(in0_alarm, 0, PRI_LOW, 0x41, 0, 0x01, 0, bitmask),
-	PREAD(in1_alarm, 1, PRI_LOW, 0x41, 0, 0x01, 1, bitmask),
-	PREAD(in2_alarm, 2, PRI_LOW, 0x41, 0, 0x01, 2, bitmask),
-	PREAD(in3_alarm, 3, PRI_LOW, 0x41, 0, 0x01, 3, bitmask),
-	PREAD(in4_alarm, 4, PRI_LOW, 0x42, 0, 0x01, 0, bitmask),
+	PREAD(in0_alarm, 0, PRI_HIGH, 0x41, 0, 0x01, 0, bitmask),
+	PREAD(in1_alarm, 1, PRI_HIGH, 0x41, 0, 0x01, 1, bitmask),
+	PREAD(in2_alarm, 2, PRI_HIGH, 0x41, 0, 0x01, 2, bitmask),
+	PREAD(in3_alarm, 3, PRI_HIGH, 0x41, 0, 0x01, 3, bitmask),
+	PREAD(in4_alarm, 4, PRI_HIGH, 0x42, 0, 0x01, 0, bitmask),
 
 	PREAD(fan1_input, 0, PRI_HIGH, 0x29, 0x28, 0, 0, fan16),
 	PREAD(fan2_input, 1, PRI_HIGH, 0x2b, 0x2a, 0, 0, fan16),
@@ -862,10 +861,10 @@
 	PWRITE(fan3_min, 2, PRI_LOW, 0x59, 0x58, 0, 0, fan16),
 	PWRITE(fan4_min, 3, PRI_LOW, 0x5b, 0x5a, 0, 0, fan16),
 
-	PREAD(fan1_alarm, 0, PRI_LOW, 0x42, 0, 0x01, 0, bitmask),
-	PREAD(fan2_alarm, 1, PRI_LOW, 0x42, 0, 0x01, 1, bitmask),
-	PREAD(fan3_alarm, 2, PRI_LOW, 0x42, 0, 0x01, 2, bitmask),
-	PREAD(fan4_alarm, 3, PRI_LOW, 0x42, 0, 0x01, 3, bitmask),
+	PREAD(fan1_alarm, 0, PRI_HIGH, 0x42, 0, 0x01, 2, bitmask),
+	PREAD(fan2_alarm, 1, PRI_HIGH, 0x42, 0, 0x01, 3, bitmask),
+	PREAD(fan3_alarm, 2, PRI_HIGH, 0x42, 0, 0x01, 4, bitmask),
+	PREAD(fan4_alarm, 3, PRI_HIGH, 0x42, 0, 0x01, 5, bitmask),
 
 	PREAD(temp1_input, 0, PRI_HIGH, 0x25, 0x10, 0, 0, temp10),
 	PREAD(temp2_input, 1, PRI_HIGH, 0x26, 0x15, 0, 0, temp10),
@@ -886,10 +885,10 @@
 	PWRITE(temp3_max, 2, PRI_LOW, 0x53, 0, 0, 0, temp8),
 	PWRITE(temp4_max, 3, PRI_LOW, 0x35, 0, 0, 0, temp8),
 
-	PREAD(temp1_alarm, 0, PRI_LOW, 0x41, 0, 0x01, 4, bitmask),
-	PREAD(temp2_alarm, 1, PRI_LOW, 0x41, 0, 0x01, 5, bitmask),
-	PREAD(temp3_alarm, 2, PRI_LOW, 0x41, 0, 0x01, 6, bitmask),
-	PREAD(temp4_alarm, 3, PRI_LOW, 0x43, 0, 0x01, 0, bitmask),
+	PREAD(temp1_alarm, 0, PRI_HIGH, 0x41, 0, 0x01, 4, bitmask),
+	PREAD(temp2_alarm, 1, PRI_HIGH, 0x41, 0, 0x01, 5, bitmask),
+	PREAD(temp3_alarm, 2, PRI_HIGH, 0x41, 0, 0x01, 6, bitmask),
+	PREAD(temp4_alarm, 3, PRI_HIGH, 0x43, 0, 0x01, 0, bitmask),
 
 	PWRITE(temp1_source, 0, PRI_LOW, 0x02, 0, 0x07, 4, bitmask),
 	PWRITE(temp2_source, 1, PRI_LOW, 0x02, 0, 0x07, 0, bitmask),
@@ -898,7 +897,7 @@
 
 	PWRITE(temp1_smoothing_enable, 0, PRI_LOW, 0x62, 0, 0x01, 3, bitmask),
 	PWRITE(temp2_smoothing_enable, 1, PRI_LOW, 0x63, 0, 0x01, 7, bitmask),
-	PWRITE(temp3_smoothing_enable, 2, PRI_LOW, 0x64, 0, 0x01, 3, bitmask),
+	PWRITE(temp3_smoothing_enable, 2, PRI_LOW, 0x63, 0, 0x01, 3, bitmask),
 	PWRITE(temp4_smoothing_enable, 3, PRI_LOW, 0x3c, 0, 0x01, 3, bitmask),
 
 	PWRITE(temp1_smoothing_time, 0, PRI_LOW, 0x62, 0, 0x07, 0, temp_st),

drivers/hwmon/hp_accel.c

diff --git a/drivers/hwmon/hp_accel.c b/drivers/hwmon/hp_accel.c
index c8ab505..7580f55 100644
--- a/drivers/hwmon/hp_accel.c
+++ b/drivers/hwmon/hp_accel.c
@@ -328,8 +328,8 @@
 	lis3lv02d_joystick_disable();
 	lis3lv02d_poweroff(&lis3_dev);
 
-	flush_work(&hpled_led.work);
 	led_classdev_unregister(&hpled_led.led_classdev);
+	flush_work(&hpled_led.work);
 
 	return lis3lv02d_remove_fs(&lis3_dev);
 }

drivers/i2c/busses/i2c-octeon.c

diff --git a/drivers/i2c/busses/i2c-octeon.c b/drivers/i2c/busses/i2c-octeon.c
index a2481f4..0e9f85d 100644
--- a/drivers/i2c/busses/i2c-octeon.c
+++ b/drivers/i2c/busses/i2c-octeon.c
@@ -447,7 +447,7 @@
 /**
  * octeon_i2c_setclock - Calculate and set clock divisors.
  */
-static int __init octeon_i2c_setclock(struct octeon_i2c *i2c)
+static int __devinit octeon_i2c_setclock(struct octeon_i2c *i2c)
 {
 	int tclk, thp_base, inc, thp_idx, mdiv_idx, ndiv_idx, foscl, diff;
 	int thp = 0x18, mdiv = 2, ndiv = 0, delta_hz = 1000000;
@@ -490,7 +490,7 @@
 	return 0;
 }
 
-static int __init octeon_i2c_initlowlevel(struct octeon_i2c *i2c)
+static int __devinit octeon_i2c_initlowlevel(struct octeon_i2c *i2c)
 {
 	u8 status;
 	int tries;

drivers/i2c/i2c-core.c

diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 3202a86..c2258a5 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -40,12 +40,11 @@
 #include "i2c-core.h"
 
 
-/* core_lock protects i2c_adapter_idr, userspace_devices, and guarantees
+/* core_lock protects i2c_adapter_idr, and guarantees
    that device detection, deletion of detected devices, and attach_adapter
    and detach_adapter calls are serialized */
 static DEFINE_MUTEX(core_lock);
 static DEFINE_IDR(i2c_adapter_idr);
-static LIST_HEAD(userspace_devices);
 
 static struct device_type i2c_client_type;
 static int i2c_check_addr(struct i2c_adapter *adapter, int addr);
@@ -117,8 +116,10 @@
 	dev_dbg(dev, "probe\n");
 
 	status = driver->probe(client, i2c_match_id(driver->id_table, client));
-	if (status)
+	if (status) {
 		client->driver = NULL;
+		i2c_set_clientdata(client, NULL);
+	}
 	return status;
 }
 
@@ -139,8 +140,10 @@
 		dev->driver = NULL;
 		status = 0;
 	}
-	if (status == 0)
+	if (status == 0) {
 		client->driver = NULL;
+		i2c_set_clientdata(client, NULL);
+	}
 	return status;
 }
 
@@ -538,9 +541,9 @@
 		return -EEXIST;
 
 	/* Keep track of the added device */
-	mutex_lock(&core_lock);
-	list_add_tail(&client->detected, &userspace_devices);
-	mutex_unlock(&core_lock);
+	i2c_lock_adapter(adap);
+	list_add_tail(&client->detected, &adap->userspace_clients);
+	i2c_unlock_adapter(adap);
 	dev_info(dev, "%s: Instantiated device %s at 0x%02hx\n", "new_device",
 		 info.type, info.addr);
 
@@ -579,9 +582,10 @@
 
 	/* Make sure the device was added through sysfs */
 	res = -ENOENT;
-	mutex_lock(&core_lock);
-	list_for_each_entry_safe(client, next, &userspace_devices, detected) {
-		if (client->addr == addr && client->adapter == adap) {
+	i2c_lock_adapter(adap);
+	list_for_each_entry_safe(client, next, &adap->userspace_clients,
+				 detected) {
+		if (client->addr == addr) {
 			dev_info(dev, "%s: Deleting device %s at 0x%02hx\n",
 				 "delete_device", client->name, client->addr);
 
@@ -591,7 +595,7 @@
 			break;
 		}
 	}
-	mutex_unlock(&core_lock);
+	i2c_unlock_adapter(adap);
 
 	if (res < 0)
 		dev_err(dev, "%s: Can't find device in list\n",
@@ -673,6 +677,7 @@
 	}
 
 	rt_mutex_init(&adap->bus_lock);
+	INIT_LIST_HEAD(&adap->userspace_clients);
 
 	/* Set default timeout to 1 second if not already set */
 	if (adap->timeout == 0)
@@ -875,14 +880,15 @@
 		return res;
 
 	/* Remove devices instantiated from sysfs */
-	list_for_each_entry_safe(client, next, &userspace_devices, detected) {
-		if (client->adapter == adap) {
-			dev_dbg(&adap->dev, "Removing %s at 0x%x\n",
-				client->name, client->addr);
-			list_del(&client->detected);
-			i2c_unregister_device(client);
-		}
+	i2c_lock_adapter(adap);
+	list_for_each_entry_safe(client, next, &adap->userspace_clients,
+				 detected) {
+		dev_dbg(&adap->dev, "Removing %s at 0x%x\n", client->name,
+			client->addr);
+		list_del(&client->detected);
+		i2c_unregister_device(client);
 	}
+	i2c_unlock_adapter(adap);
 
 	/* Detach any active clients. This can't fail, thus we do not
 	   checking the returned value. */
@@ -1260,12 +1266,23 @@
 		return 0;
 
 	/* Make sure there is something at this address */
-	if (i2c_smbus_xfer(adapter, addr, 0, 0, 0, I2C_SMBUS_QUICK, NULL) < 0)
-		return 0;
+	if (addr == 0x73 && (adapter->class & I2C_CLASS_HWMON)) {
+		/* Special probe for FSC hwmon chips */
+		union i2c_smbus_data dummy;
 
-	/* Prevent 24RF08 corruption */
-	if ((addr & ~0x0f) == 0x50)
-		i2c_smbus_xfer(adapter, addr, 0, 0, 0, I2C_SMBUS_QUICK, NULL);
+		if (i2c_smbus_xfer(adapter, addr, 0, I2C_SMBUS_READ, 0,
+				   I2C_SMBUS_BYTE_DATA, &dummy) < 0)
+			return 0;
+	} else {
+		if (i2c_smbus_xfer(adapter, addr, 0, I2C_SMBUS_WRITE, 0,
+				   I2C_SMBUS_QUICK, NULL) < 0)
+			return 0;
+
+		/* Prevent 24RF08 corruption */
+		if ((addr & ~0x0f) == 0x50)
+			i2c_smbus_xfer(adapter, addr, 0, I2C_SMBUS_WRITE, 0,
+				       I2C_SMBUS_QUICK, NULL);
+	}
 
 	/* Finally call the custom detection function */
 	memset(&info, 0, sizeof(struct i2c_board_info));

drivers/ide/ide-cs.c

diff --git a/drivers/ide/ide-cs.c b/drivers/ide/ide-cs.c
index defce28..b854508 100644
--- a/drivers/ide/ide-cs.c
+++ b/drivers/ide/ide-cs.c
@@ -409,7 +409,7 @@
 	PCMCIA_DEVICE_PROD_ID12("Hyperstone", "Model1", 0x3d5b9ef5, 0xca6ab420),
 	PCMCIA_DEVICE_PROD_ID12("IBM", "microdrive", 0xb569a6e5, 0xa6d76178),
 	PCMCIA_DEVICE_PROD_ID12("IBM", "IBM17JSSFP20", 0xb569a6e5, 0xf2508753),
-	PCMCIA_DEVICE_PROD_ID12("KINGSTON", "CF CARD 1GB", 0x2e6d1829, 0x3e520e17),
+	PCMCIA_DEVICE_PROD_ID12("KINGSTON", "CF CARD 1GB", 0x2e6d1829, 0x55d5bffb),
 	PCMCIA_DEVICE_PROD_ID12("KINGSTON", "CF CARD 4GB", 0x2e6d1829, 0x531e7d10),
 	PCMCIA_DEVICE_PROD_ID12("KINGSTON", "CF8GB", 0x2e6d1829, 0xacbe682e),
 	PCMCIA_DEVICE_PROD_ID12("IO DATA", "CBIDE2      ", 0x547e66dc, 0x8671043b),
@@ -431,7 +431,7 @@
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS1GCF80", 0x709b1bf1, 0x2a54d4b1),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS2GCF120", 0x709b1bf1, 0x969aa4f2),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS4GCF120", 0x709b1bf1, 0xf54a91c8),
-	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS4GCF133", 0x709b1bf1, 0x9351e59d),
+	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS4GCF133", 0x709b1bf1, 0x7558f133),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS8GCF133", 0x709b1bf1, 0xb2f89b47),
 	PCMCIA_DEVICE_PROD_ID12("WIT", "IDE16", 0x244e5994, 0x3e232852),
 	PCMCIA_DEVICE_PROD_ID12("WEIDA", "TWTTI", 0xcc7cf69c, 0x212bb918),

drivers/input/gameport/gameport.c

diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index 7e18bcf..46239e4 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -59,11 +59,11 @@
 	unsigned long flags;
 	unsigned int count;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 	outb_p(0x00, 0x43);
 	count = inb_p(0x40);
 	count |= inb_p(0x40) << 8;
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 
 	return count;
 }

drivers/input/joydev.c

diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c
index c52bec4..423e0e6 100644
--- a/drivers/input/joydev.c
+++ b/drivers/input/joydev.c
@@ -929,6 +929,24 @@
 		.evbit = { BIT_MASK(EV_ABS) },
 		.absbit = { BIT_MASK(ABS_THROTTLE) },
 	},
+	{
+		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
+				INPUT_DEVICE_ID_MATCH_KEYBIT,
+		.evbit = { BIT_MASK(EV_KEY) },
+		.keybit = {[BIT_WORD(BTN_JOYSTICK)] = BIT_MASK(BTN_JOYSTICK) },
+	},
+	{
+		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
+				INPUT_DEVICE_ID_MATCH_KEYBIT,
+		.evbit = { BIT_MASK(EV_KEY) },
+		.keybit = { [BIT_WORD(BTN_GAMEPAD)] = BIT_MASK(BTN_GAMEPAD) },
+	},
+	{
+		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
+				INPUT_DEVICE_ID_MATCH_KEYBIT,
+		.evbit = { BIT_MASK(EV_KEY) },
+		.keybit = { [BIT_WORD(BTN_TRIGGER_HAPPY)] = BIT_MASK(BTN_TRIGGER_HAPPY) },
+	},
 	{ }	/* Terminating entry */
 };
 

drivers/input/joystick/analog.c

diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c
index 1c0b529..4afe0a3 100644
--- a/drivers/input/joystick/analog.c
+++ b/drivers/input/joystick/analog.c
@@ -146,11 +146,11 @@
         unsigned long flags;
         unsigned int count;
 
-        spin_lock_irqsave(&i8253_lock, flags);
+        raw_spin_lock_irqsave(&i8253_lock, flags);
         outb_p(0x00, 0x43);
         count = inb_p(0x40);
         count |= inb_p(0x40) << 8;
-        spin_unlock_irqrestore(&i8253_lock, flags);
+        raw_spin_unlock_irqrestore(&i8253_lock, flags);
 
         return count;
 }

drivers/input/joystick/iforce/iforce-main.c

diff --git a/drivers/input/joystick/iforce/iforce-main.c b/drivers/input/joystick/iforce/iforce-main.c
index b1edd77..405febd 100644
--- a/drivers/input/joystick/iforce/iforce-main.c
+++ b/drivers/input/joystick/iforce/iforce-main.c
@@ -54,6 +54,9 @@
 static signed short abs_joystick[] =
 { ABS_X, ABS_Y, ABS_THROTTLE, ABS_HAT0X, ABS_HAT0Y, -1 };
 
+static signed short abs_joystick_rudder[] =
+{ ABS_X, ABS_Y, ABS_THROTTLE, ABS_RUDDER, ABS_HAT0X, ABS_HAT0Y, -1 };
+
 static signed short abs_avb_pegasus[] =
 { ABS_X, ABS_Y, ABS_THROTTLE, ABS_RUDDER, ABS_HAT0X, ABS_HAT0Y,
   ABS_HAT1X, ABS_HAT1Y, -1 };
@@ -76,8 +79,9 @@
 	{ 0x061c, 0xc0a4, "ACT LABS Force RS",                          btn_wheel, abs_wheel, ff_iforce }, //?
 	{ 0x061c, 0xc084, "ACT LABS Force RS",				btn_wheel, abs_wheel, ff_iforce },
 	{ 0x06f8, 0x0001, "Guillemot Race Leader Force Feedback",	btn_wheel, abs_wheel, ff_iforce }, //?
+	{ 0x06f8, 0x0001, "Guillemot Jet Leader Force Feedback",	btn_joystick, abs_joystick_rudder, ff_iforce },
 	{ 0x06f8, 0x0004, "Guillemot Force Feedback Racing Wheel",	btn_wheel, abs_wheel, ff_iforce }, //?
-	{ 0x06f8, 0x0004, "Gullemot Jet Leader 3D",			btn_joystick, abs_joystick, ff_iforce }, //?
+	{ 0x06f8, 0xa302, "Guillemot Jet Leader 3D",			btn_joystick, abs_joystick, ff_iforce }, //?
 	{ 0x06d6, 0x29bc, "Trust Force Feedback Race Master",		btn_wheel, abs_wheel, ff_iforce },
 	{ 0x0000, 0x0000, "Unknown I-Force Device [%04x:%04x]",		btn_joystick, abs_joystick, ff_iforce }
 };

drivers/input/joystick/iforce/iforce-usb.c

diff --git a/drivers/input/joystick/iforce/iforce-usb.c b/drivers/input/joystick/iforce/iforce-usb.c
index b41303d..6c96631 100644
--- a/drivers/input/joystick/iforce/iforce-usb.c
+++ b/drivers/input/joystick/iforce/iforce-usb.c
@@ -212,6 +212,7 @@
 	{ USB_DEVICE(0x061c, 0xc0a4) },         /* ACT LABS Force RS */
 	{ USB_DEVICE(0x061c, 0xc084) },         /* ACT LABS Force RS */
 	{ USB_DEVICE(0x06f8, 0x0001) },		/* Guillemot Race Leader Force Feedback */
+	{ USB_DEVICE(0x06f8, 0x0003) },		/* Guillemot Jet Leader Force Feedback */
 	{ USB_DEVICE(0x06f8, 0x0004) },		/* Guillemot Force Feedback Racing Wheel */
 	{ USB_DEVICE(0x06f8, 0xa302) },		/* Guillemot Jet Leader 3D */
 	{ }					/* Terminating entry */

drivers/input/misc/ati_remote.c

diff --git a/drivers/input/misc/ati_remote.c b/drivers/input/misc/ati_remote.c
index 614b65d..e8bbc61 100644
--- a/drivers/input/misc/ati_remote.c
+++ b/drivers/input/misc/ati_remote.c
@@ -98,10 +98,12 @@
  * Module and Version Information, Module Parameters
  */
 
-#define ATI_REMOTE_VENDOR_ID	0x0bc7
-#define ATI_REMOTE_PRODUCT_ID	0x004
-#define LOLA_REMOTE_PRODUCT_ID	0x002
-#define MEDION_REMOTE_PRODUCT_ID 0x006
+#define ATI_REMOTE_VENDOR_ID		0x0bc7
+#define LOLA_REMOTE_PRODUCT_ID		0x0002
+#define LOLA2_REMOTE_PRODUCT_ID		0x0003
+#define ATI_REMOTE_PRODUCT_ID		0x0004
+#define NVIDIA_REMOTE_PRODUCT_ID	0x0005
+#define MEDION_REMOTE_PRODUCT_ID	0x0006
 
 #define DRIVER_VERSION	        "2.2.1"
 #define DRIVER_AUTHOR           "Torrey Hoffman <thoffman@arnor.net>"
@@ -142,8 +144,10 @@
 #define err(format, arg...) printk(KERN_ERR format , ## arg)
 
 static struct usb_device_id ati_remote_table[] = {
-	{ USB_DEVICE(ATI_REMOTE_VENDOR_ID, ATI_REMOTE_PRODUCT_ID) },
 	{ USB_DEVICE(ATI_REMOTE_VENDOR_ID, LOLA_REMOTE_PRODUCT_ID) },
+	{ USB_DEVICE(ATI_REMOTE_VENDOR_ID, LOLA2_REMOTE_PRODUCT_ID) },
+	{ USB_DEVICE(ATI_REMOTE_VENDOR_ID, ATI_REMOTE_PRODUCT_ID) },
+	{ USB_DEVICE(ATI_REMOTE_VENDOR_ID, NVIDIA_REMOTE_PRODUCT_ID) },
 	{ USB_DEVICE(ATI_REMOTE_VENDOR_ID, MEDION_REMOTE_PRODUCT_ID) },
 	{}	/* Terminating entry */
 };

drivers/input/misc/pcspkr.c

diff --git a/drivers/input/misc/pcspkr.c b/drivers/input/misc/pcspkr.c
index ea4e1fd..f080dd3 100644
--- a/drivers/input/misc/pcspkr.c
+++ b/drivers/input/misc/pcspkr.c
@@ -30,7 +30,7 @@
 #include <asm/i8253.h>
 #else
 #include <asm/8253pit.h>
-static DEFINE_SPINLOCK(i8253_lock);
+static DEFINE_RAW_SPINLOCK(i8253_lock);
 #endif
 
 static int pcspkr_event(struct input_dev *dev, unsigned int type, unsigned int code, int value)
@@ -50,7 +50,7 @@
 	if (value > 20 && value < 32767)
 		count = PIT_TICK_RATE / value;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 
 	if (count) {
 		/* set command for counter 2, 2 byte write */
@@ -65,7 +65,7 @@
 		outb(inb_p(0x61) & 0xFC, 0x61);
 	}
 
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 
 	return 0;
 }

drivers/input/mouse/alps.c

diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 0d22cb9..99d5876 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -64,7 +64,6 @@
 	{ { 0x62, 0x02, 0x14 }, 0xcf, 0xcf,
 		ALPS_PASS | ALPS_DUALPOINT | ALPS_PS2_INTERLEAVED },
 	{ { 0x73, 0x02, 0x50 }, 0xcf, 0xcf, ALPS_FOUR_BUTTONS },	  /* Dell Vostro 1400 */
-	{ { 0x73, 0x02, 0x64 }, 0xf8, 0xf8, 0 },			  /* HP Pavilion dm3 */
 	{ { 0x52, 0x01, 0x14 }, 0xff, 0xff,
 		ALPS_PASS | ALPS_DUALPOINT | ALPS_PS2_INTERLEAVED },	  /* Toshiba Tecra A11-11L */
 };

drivers/input/mouse/elantech.c

diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index a138b5d..112b4ee 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -25,6 +25,10 @@
 			printk(KERN_DEBUG format, ##arg);	\
 	} while (0)
 
+static bool force_elantech;
+module_param_named(force_elantech, force_elantech, bool, 0644);
+MODULE_PARM_DESC(force_elantech, "Force the Elantech PS/2 protocol extension to be used, 1 = enabled, 0 = disabled (default).");
+
 /*
  * Send a Synaptics style sliced query command
  */
@@ -181,14 +185,18 @@
 	int fingers;
 	static int old_fingers;
 
-	if (etd->fw_version_maj == 0x01) {
-		/* byte 0:  D   U  p1  p2   1  p3   R   L
-		   byte 1:  f   0  th  tw  x9  x8  y9  y8 */
+	if (etd->fw_version < 0x020000) {
+		/*
+		 * byte 0:  D   U  p1  p2   1  p3   R   L
+		 * byte 1:  f   0  th  tw  x9  x8  y9  y8
+		 */
 		fingers = ((packet[1] & 0x80) >> 7) +
 				((packet[1] & 0x30) >> 4);
 	} else {
-		/* byte 0: n1  n0  p2  p1   1  p3   R   L
-		   byte 1:  0   0   0   0  x9  x8  y9  y8 */
+		/*
+		 * byte 0: n1  n0  p2  p1   1  p3   R   L
+		 * byte 1:  0   0   0   0  x9  x8  y9  y8
+		 */
 		fingers = (packet[0] & 0xc0) >> 6;
 	}
 
@@ -202,13 +210,15 @@
 
 	input_report_key(dev, BTN_TOUCH, fingers != 0);
 
-	/* byte 2: x7  x6  x5  x4  x3  x2  x1  x0
-	   byte 3: y7  y6  y5  y4  y3  y2  y1  y0 */
+	/*
+	 * byte 2: x7  x6  x5  x4  x3  x2  x1  x0
+	 * byte 3: y7  y6  y5  y4  y3  y2  y1  y0
+	 */
 	if (fingers) {
 		input_report_abs(dev, ABS_X,
 			((packet[1] & 0x0c) << 6) | packet[2]);
-		input_report_abs(dev, ABS_Y, ETP_YMAX_V1 -
-			(((packet[1] & 0x03) << 8) | packet[3]));
+		input_report_abs(dev, ABS_Y,
+			ETP_YMAX_V1 - (((packet[1] & 0x03) << 8) | packet[3]));
 	}
 
 	input_report_key(dev, BTN_TOOL_FINGER, fingers == 1);
@@ -217,7 +227,7 @@
 	input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
 	input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
 
-	if ((etd->fw_version_maj == 0x01) &&
+	if (etd->fw_version < 0x020000 &&
 	    (etd->capabilities & ETP_CAP_HAS_ROCKER)) {
 		/* rocker up */
 		input_report_key(dev, BTN_FORWARD, packet[0] & 0x40);
@@ -247,34 +257,47 @@
 
 	switch (fingers) {
 	case 1:
-		/* byte 1: x15 x14 x13 x12 x11 x10 x9  x8
-		   byte 2: x7  x6  x5  x4  x4  x2  x1  x0 */
-		input_report_abs(dev, ABS_X, (packet[1] << 8) | packet[2]);
-		/* byte 4: y15 y14 y13 y12 y11 y10 y8  y8
-		   byte 5: y7  y6  y5  y4  y3  y2  y1  y0 */
-		input_report_abs(dev, ABS_Y, ETP_YMAX_V2 -
-			((packet[4] << 8) | packet[5]));
+		/*
+		 * byte 1:  .   .   .   .   .  x10 x9  x8
+		 * byte 2: x7  x6  x5  x4  x4  x2  x1  x0
+		 */
+		input_report_abs(dev, ABS_X,
+			((packet[1] & 0x07) << 8) | packet[2]);
+		/*
+		 * byte 4:  .   .   .   .   .   .  y9  y8
+		 * byte 5: y7  y6  y5  y4  y3  y2  y1  y0
+		 */
+		input_report_abs(dev, ABS_Y,
+			ETP_YMAX_V2 - (((packet[4] & 0x03) << 8) | packet[5]));
 		break;
 
 	case 2:
-		/* The coordinate of each finger is reported separately with
-		   a lower resolution for two finger touches */
-		/* byte 0:  .   .  ay8 ax8  .   .   .   .
-		   byte 1: ax7 ax6 ax5 ax4 ax3 ax2 ax1 ax0 */
+		/*
+		 * The coordinate of each finger is reported separately
+		 * with a lower resolution for two finger touches:
+		 * byte 0:  .   .  ay8 ax8  .   .   .   .
+		 * byte 1: ax7 ax6 ax5 ax4 ax3 ax2 ax1 ax0
+		 */
 		x1 = ((packet[0] & 0x10) << 4) | packet[1];
 		/* byte 2: ay7 ay6 ay5 ay4 ay3 ay2 ay1 ay0 */
 		y1 = ETP_2FT_YMAX - (((packet[0] & 0x20) << 3) | packet[2]);
-		/* byte 3:  .   .  by8 bx8  .   .   .   .
-		   byte 4: bx7 bx6 bx5 bx4 bx3 bx2 bx1 bx0 */
+		/*
+		 * byte 3:  .   .  by8 bx8  .   .   .   .
+		 * byte 4: bx7 bx6 bx5 bx4 bx3 bx2 bx1 bx0
+		 */
 		x2 = ((packet[3] & 0x10) << 4) | packet[4];
 		/* byte 5: by7 by8 by5 by4 by3 by2 by1 by0 */
 		y2 = ETP_2FT_YMAX - (((packet[3] & 0x20) << 3) | packet[5]);
-		/* For compatibility with the X Synaptics driver scale up one
-		   coordinate and report as ordinary mouse movent */
+		/*
+		 * For compatibility with the X Synaptics driver scale up
+		 * one coordinate and report as ordinary mouse movent
+		 */
 		input_report_abs(dev, ABS_X, x1 << 2);
 		input_report_abs(dev, ABS_Y, y1 << 2);
-		/* For compatibility with the proprietary X Elantech driver
-		   report both coordinates as hat coordinates */
+		/*
+		 * For compatibility with the proprietary X Elantech driver
+		 * report both coordinates as hat coordinates
+		 */
 		input_report_abs(dev, ABS_HAT0X, x1);
 		input_report_abs(dev, ABS_HAT0Y, y1);
 		input_report_abs(dev, ABS_HAT1X, x2);
@@ -298,7 +321,7 @@
 	unsigned char p1, p2, p3;
 
 	/* Parity bits are placed differently */
-	if (etd->fw_version_maj == 0x01) {
+	if (etd->fw_version < 0x020000) {
 		/* byte 0:  D   U  p1  p2   1  p3   R   L */
 		p1 = (packet[0] & 0x20) >> 5;
 		p2 = (packet[0] & 0x10) >> 4;
@@ -434,7 +457,7 @@
 	switch (etd->hw_version) {
 	case 1:
 		/* Rocker button */
-		if ((etd->fw_version_maj == 0x01) &&
+		if (etd->fw_version < 0x020000 &&
 		    (etd->capabilities & ETP_CAP_HAS_ROCKER)) {
 			__set_bit(BTN_FORWARD, dev->keybit);
 			__set_bit(BTN_BACK, dev->keybit);
@@ -596,8 +619,12 @@
 		 param[0], param[1], param[2]);
 
 	if (param[0] == 0 || param[1] != 0) {
-		pr_debug("elantech.c: Probably not a real Elantech touchpad. Aborting.\n");
-		return -1;
+		if (!force_elantech) {
+			pr_debug("elantech.c: Probably not a real Elantech touchpad. Aborting.\n");
+			return -1;
+		}
+
+		pr_debug("elantech.c: Probably not a real Elantech touchpad. Enabling anyway due to force_elantech.\n");
 	}
 
 	if (set_properties) {
@@ -659,14 +686,14 @@
 		pr_err("elantech.c: failed to query firmware version.\n");
 		goto init_fail;
 	}
-	etd->fw_version_maj = param[0];
-	etd->fw_version_min = param[2];
+
+	etd->fw_version = (param[0] << 16) | (param[1] << 8) | param[2];
 
 	/*
 	 * Assume every version greater than this is new EeePC style
 	 * hardware with 6 byte packets
 	 */
-	if (etd->fw_version_maj >= 0x02 && etd->fw_version_min >= 0x30) {
+	if (etd->fw_version >= 0x020030) {
 		etd->hw_version = 2;
 		/* For now show extra debug information */
 		etd->debug = 1;
@@ -676,8 +703,9 @@
 		etd->hw_version = 1;
 		etd->paritycheck = 1;
 	}
-	pr_info("elantech.c: assuming hardware version %d, firmware version %d.%d\n",
-		etd->hw_version, etd->fw_version_maj, etd->fw_version_min);
+
+	pr_info("elantech.c: assuming hardware version %d, firmware version %d.%d.%d\n",
+		etd->hw_version, param[0], param[1], param[2]);
 
 	if (synaptics_send_cmd(psmouse, ETP_CAPABILITIES_QUERY, param)) {
 		pr_err("elantech.c: failed to query capabilities.\n");
@@ -692,8 +720,8 @@
 	 * a touch action starts causing the mouse cursor or scrolled page
 	 * to jump. Enable a workaround.
 	 */
-	if (etd->fw_version_maj == 0x02 && etd->fw_version_min == 0x22) {
-		pr_info("elantech.c: firmware version 2.34 detected, "
+	if (etd->fw_version == 0x020022) {
+		pr_info("elantech.c: firmware version 2.0.34 detected, "
 			"enabling jumpy cursor workaround\n");
 		etd->jumpy_cursor = 1;
 	}

drivers/input/mouse/elantech.h

diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h
index feac5f7..ac57bde 100644
--- a/drivers/input/mouse/elantech.h
+++ b/drivers/input/mouse/elantech.h
@@ -100,11 +100,10 @@
 	unsigned char reg_26;
 	unsigned char debug;
 	unsigned char capabilities;
-	unsigned char fw_version_maj;
-	unsigned char fw_version_min;
-	unsigned char hw_version;
 	unsigned char paritycheck;
 	unsigned char jumpy_cursor;
+	unsigned char hw_version;
+	unsigned int  fw_version;
 	unsigned char parity[256];
 };
 

drivers/input/mouse/psmouse-base.c

diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c
index d8c0c8d..a3c9731 100644
--- a/drivers/input/mouse/psmouse-base.c
+++ b/drivers/input/mouse/psmouse-base.c
@@ -110,6 +110,7 @@
 struct psmouse_protocol {
 	enum psmouse_type type;
 	bool maxproto;
+	bool ignore_parity; /* Protocol should ignore parity errors from KBC */
 	const char *name;
 	const char *alias;
 	int (*detect)(struct psmouse *, bool);
@@ -288,7 +289,9 @@
 	if (psmouse->state == PSMOUSE_IGNORE)
 		goto out;
 
-	if (flags & (SERIO_PARITY|SERIO_TIMEOUT)) {
+	if (unlikely((flags & SERIO_TIMEOUT) ||
+		     ((flags & SERIO_PARITY) && !psmouse->ignore_parity))) {
+
 		if (psmouse->state == PSMOUSE_ACTIVATED)
 			printk(KERN_WARNING "psmouse.c: bad data from KBC -%s%s\n",
 				flags & SERIO_TIMEOUT ? " timeout" : "",
@@ -759,6 +762,7 @@
 		.name		= "PS/2",
 		.alias		= "bare",
 		.maxproto	= true,
+		.ignore_parity	= true,
 		.detect		= ps2bare_detect,
 	},
 #ifdef CONFIG_MOUSE_PS2_LOGIPS2PP
@@ -786,6 +790,7 @@
 		.name		= "ImPS/2",
 		.alias		= "imps",
 		.maxproto	= true,
+		.ignore_parity	= true,
 		.detect		= intellimouse_detect,
 	},
 	{
@@ -793,6 +798,7 @@
 		.name		= "ImExPS/2",
 		.alias		= "exps",
 		.maxproto	= true,
+		.ignore_parity	= true,
 		.detect		= im_explorer_detect,
 	},
 #ifdef CONFIG_MOUSE_PS2_SYNAPTICS
@@ -1222,6 +1228,7 @@
 static int psmouse_switch_protocol(struct psmouse *psmouse,
 				   const struct psmouse_protocol *proto)
 {
+	const struct psmouse_protocol *selected_proto;
 	struct input_dev *input_dev = psmouse->dev;
 
 	input_dev->dev.parent = &psmouse->ps2dev.serio->dev;
@@ -1245,9 +1252,14 @@
 			return -1;
 
 		psmouse->type = proto->type;
-	} else
+		selected_proto = proto;
+	} else {
 		psmouse->type = psmouse_extensions(psmouse,
 						   psmouse_max_proto, true);
+		selected_proto = psmouse_protocol_by_type(psmouse->type);
+	}
+
+	psmouse->ignore_parity = selected_proto->ignore_parity;
 
 	/*
 	 * If mouse's packet size is 3 there is no point in polling the
@@ -1267,7 +1279,7 @@
 		psmouse->resync_time = 0;
 
 	snprintf(psmouse->devname, sizeof(psmouse->devname), "%s %s %s",
-		 psmouse_protocol_by_type(psmouse->type)->name, psmouse->vendor, psmouse->name);
+		 selected_proto->name, psmouse->vendor, psmouse->name);
 
 	input_dev->name = psmouse->devname;
 	input_dev->phys = psmouse->phys;
@@ -1382,6 +1394,7 @@
 	struct psmouse *psmouse = serio_get_drvdata(serio);
 	struct psmouse *parent = NULL;
 	struct serio_driver *drv = serio->drv;
+	unsigned char type;
 	int rc = -1;
 
 	if (!drv || !psmouse) {
@@ -1401,10 +1414,15 @@
 	if (psmouse->reconnect) {
 		if (psmouse->reconnect(psmouse))
 			goto out;
-	} else if (psmouse_probe(psmouse) < 0 ||
-		   psmouse->type != psmouse_extensions(psmouse,
-						psmouse_max_proto, false)) {
-		goto out;
+	} else {
+		psmouse_reset(psmouse);
+
+		if (psmouse_probe(psmouse) < 0)
+			goto out;
+
+		type = psmouse_extensions(psmouse, psmouse_max_proto, false);
+		if (psmouse->type != type)
+			goto out;
 	}
 
 	/* ok, the device type (and capabilities) match the old one,

drivers/input/mouse/psmouse.h

diff --git a/drivers/input/mouse/psmouse.h b/drivers/input/mouse/psmouse.h
index e053bdd..593e910 100644
--- a/drivers/input/mouse/psmouse.h
+++ b/drivers/input/mouse/psmouse.h
@@ -47,6 +47,7 @@
 	unsigned char pktcnt;
 	unsigned char pktsize;
 	unsigned char type;
+	bool ignore_parity;
 	bool acks_disable_command;
 	unsigned int model;
 	unsigned long last;

drivers/input/mouse/synaptics.c

diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 026df60..ebd7a99 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -137,7 +137,8 @@
 	if (synaptics_send_cmd(psmouse, SYN_QUE_CAPABILITIES, cap))
 		return -1;
 	priv->capabilities = (cap[0] << 16) | (cap[1] << 8) | cap[2];
-	priv->ext_cap = 0;
+	priv->ext_cap = priv->ext_cap_0c = 0;
+
 	if (!SYN_CAP_VALID(priv->capabilities))
 		return -1;
 
@@ -150,7 +151,7 @@
 	if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 1) {
 		if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_CAPAB, cap)) {
 			printk(KERN_ERR "Synaptics claims to have extended capabilities,"
-			       " but I'm not able to read them.");
+			       " but I'm not able to read them.\n");
 		} else {
 			priv->ext_cap = (cap[0] << 16) | (cap[1] << 8) | cap[2];
 
@@ -162,6 +163,16 @@
 				priv->ext_cap &= 0xff0fff;
 		}
 	}
+
+	if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 4) {
+		if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_CAPAB_0C, cap)) {
+			printk(KERN_ERR "Synaptics claims to have extended capability 0x0c,"
+			       " but I'm not able to read it.\n");
+		} else {
+			priv->ext_cap_0c = (cap[0] << 16) | (cap[1] << 8) | cap[2];
+		}
+	}
+
 	return 0;
 }
 
@@ -348,7 +359,15 @@
 		hw->left  = (buf[0] & 0x01) ? 1 : 0;
 		hw->right = (buf[0] & 0x02) ? 1 : 0;
 
-		if (SYN_CAP_MIDDLE_BUTTON(priv->capabilities)) {
+		if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
+			/*
+			 * Clickpad's button is transmitted as middle button,
+			 * however, since it is primary button, we will report
+			 * it as BTN_LEFT.
+			 */
+			hw->left = ((buf[0] ^ buf[3]) & 0x01) ? 1 : 0;
+
+		} else if (SYN_CAP_MIDDLE_BUTTON(priv->capabilities)) {
 			hw->middle = ((buf[0] ^ buf[3]) & 0x01) ? 1 : 0;
 			if (hw->w == 2)
 				hw->scroll = (signed char)(buf[1]);
@@ -593,6 +612,12 @@
 
 	dev->absres[ABS_X] = priv->x_res;
 	dev->absres[ABS_Y] = priv->y_res;
+
+	if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
+		/* Clickpads report only left button */
+		__clear_bit(BTN_RIGHT, dev->keybit);
+		__clear_bit(BTN_MIDDLE, dev->keybit);
+	}
 }
 
 static void synaptics_disconnect(struct psmouse *psmouse)
@@ -697,10 +722,10 @@
 
 	priv->pkt_type = SYN_MODEL_NEWABS(priv->model_id) ? SYN_NEWABS : SYN_OLDABS;
 
-	printk(KERN_INFO "Synaptics Touchpad, model: %ld, fw: %ld.%ld, id: %#lx, caps: %#lx/%#lx\n",
+	printk(KERN_INFO "Synaptics Touchpad, model: %ld, fw: %ld.%ld, id: %#lx, caps: %#lx/%#lx/%#lx\n",
 		SYN_ID_MODEL(priv->identity),
 		SYN_ID_MAJOR(priv->identity), SYN_ID_MINOR(priv->identity),
-		priv->model_id, priv->capabilities, priv->ext_cap);
+		priv->model_id, priv->capabilities, priv->ext_cap, priv->ext_cap_0c);
 
 	set_input_params(psmouse->dev, priv);
 

drivers/input/mouse/synaptics.h

diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h
index f0f40a3..ae37c5d 100644
--- a/drivers/input/mouse/synaptics.h
+++ b/drivers/input/mouse/synaptics.h
@@ -18,6 +18,7 @@
 #define SYN_QUE_SERIAL_NUMBER_SUFFIX	0x07
 #define SYN_QUE_RESOLUTION		0x08
 #define SYN_QUE_EXT_CAPAB		0x09
+#define SYN_QUE_EXT_CAPAB_0C		0x0c
 
 /* synatics modes */
 #define SYN_BIT_ABSOLUTE_MODE		(1 << 7)
@@ -48,6 +49,8 @@
 #define SYN_CAP_VALID(c)		((((c) & 0x00ff00) >> 8) == 0x47)
 #define SYN_EXT_CAP_REQUESTS(c)		(((c) & 0x700000) >> 20)
 #define SYN_CAP_MULTI_BUTTON_NO(ec)	(((ec) & 0x00f000) >> 12)
+#define SYN_CAP_PRODUCT_ID(ec)		(((ec) & 0xff0000) >> 16)
+#define SYN_CAP_CLICKPAD(ex0c)		((ex0c) & 0x100100)
 
 /* synaptics modes query bits */
 #define SYN_MODE_ABSOLUTE(m)		((m) & (1 << 7))
@@ -96,6 +99,7 @@
 	unsigned long int model_id;		/* Model-ID */
 	unsigned long int capabilities;		/* Capabilities */
 	unsigned long int ext_cap;		/* Extended Capabilities */
+	unsigned long int ext_cap_0c;		/* Ext Caps from 0x0c query */
 	unsigned long int identity;		/* Identification */
 	int x_res;				/* X resolution in units/mm */
 	int y_res;				/* Y resolution in units/mm */

drivers/input/touchscreen/ad7877.c

diff --git a/drivers/input/touchscreen/ad7877.c b/drivers/input/touchscreen/ad7877.c
index e019d53..0d2d7e5 100644
--- a/drivers/input/touchscreen/ad7877.c
+++ b/drivers/input/touchscreen/ad7877.c
@@ -156,9 +156,14 @@
 	u16			reset;
 	u16			ref_on;
 	u16			command;
-	u16			sample;
 	struct spi_message	msg;
 	struct spi_transfer	xfer[6];
+
+	/*
+	 * DMA (thus cache coherency maintenance) requires the
+	 * transfer buffers to live in their own cache lines.
+	 */
+	u16 sample ____cacheline_aligned;
 };
 
 struct ad7877 {
@@ -182,8 +187,6 @@
 	u8			averaging;
 	u8			pen_down_acc_interval;
 
-	u16			conversion_data[AD7877_NR_SENSE];
-
 	struct spi_transfer	xfer[AD7877_NR_SENSE + 2];
 	struct spi_message	msg;
 
@@ -195,6 +198,12 @@
 	spinlock_t		lock;
 	struct timer_list	timer;		/* P: lock */
 	unsigned		pending:1;	/* P: lock */
+
+	/*
+	 * DMA (thus cache coherency maintenance) requires the
+	 * transfer buffers to live in their own cache lines.
+	 */
+	u16 conversion_data[AD7877_NR_SENSE] ____cacheline_aligned;
 };
 
 static int gpio3;

drivers/input/touchscreen/eeti_ts.c

diff --git a/drivers/input/touchscreen/eeti_ts.c b/drivers/input/touchscreen/eeti_ts.c
index 204b8a1..75f8b73 100644
--- a/drivers/input/touchscreen/eeti_ts.c
+++ b/drivers/input/touchscreen/eeti_ts.c
@@ -124,14 +124,25 @@
 	return IRQ_HANDLED;
 }
 
-static int eeti_ts_open(struct input_dev *dev)
+static void eeti_ts_start(struct eeti_ts_priv *priv)
 {
-	struct eeti_ts_priv *priv = input_get_drvdata(dev);
-
 	enable_irq(priv->irq);
 
 	/* Read the events once to arm the IRQ */
 	eeti_ts_read(&priv->work);
+}
+
+static void eeti_ts_stop(struct eeti_ts_priv *priv)
+{
+	disable_irq(priv->irq);
+	cancel_work_sync(&priv->work);
+}
+
+static int eeti_ts_open(struct input_dev *dev)
+{
+	struct eeti_ts_priv *priv = input_get_drvdata(dev);
+
+	eeti_ts_start(priv);
 
 	return 0;
 }
@@ -140,8 +151,7 @@
 {
 	struct eeti_ts_priv *priv = input_get_drvdata(dev);
 
-	disable_irq(priv->irq);
-	cancel_work_sync(&priv->work);
+	eeti_ts_stop(priv);
 }
 
 static int __devinit eeti_ts_probe(struct i2c_client *client,
@@ -153,10 +163,12 @@
 	unsigned int irq_flags;
 	int err = -ENOMEM;
 
-	/* In contrast to what's described in the datasheet, there seems
+	/*
+	 * In contrast to what's described in the datasheet, there seems
 	 * to be no way of probing the presence of that device using I2C
 	 * commands. So we need to blindly believe it is there, and wait
-	 * for interrupts to occur. */
+	 * for interrupts to occur.
+	 */
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
@@ -212,9 +224,11 @@
 		goto err2;
 	}
 
-	/* Disable the irq for now. It will be enabled once the input device
-	 * is opened. */
-	disable_irq(priv->irq);
+	/*
+	 * Disable the device for now. It will be enabled once the
+	 * input device is opened.
+	 */
+	eeti_ts_stop(priv);
 
 	device_init_wakeup(&client->dev, 0);
 	return 0;
@@ -235,6 +249,12 @@
 	struct eeti_ts_priv *priv = i2c_get_clientdata(client);
 
 	free_irq(priv->irq, priv);
+	/*
+	 * eeti_ts_stop() leaves IRQ disabled. We need to re-enable it
+	 * so that device still works if we reload the driver.
+	 */
+	enable_irq(priv->irq);
+
 	input_unregister_device(priv->input);
 	i2c_set_clientdata(client, NULL);
 	kfree(priv);
@@ -246,6 +266,14 @@
 static int eeti_ts_suspend(struct i2c_client *client, pm_message_t mesg)
 {
 	struct eeti_ts_priv *priv = i2c_get_clientdata(client);
+	struct input_dev *input_dev = priv->input;
+
+	mutex_lock(&input_dev->mutex);
+
+	if (input_dev->users)
+		eeti_ts_stop(priv);
+
+	mutex_unlock(&input_dev->mutex);
 
 	if (device_may_wakeup(&client->dev))
 		enable_irq_wake(priv->irq);
@@ -256,10 +284,18 @@
 static int eeti_ts_resume(struct i2c_client *client)
 {
 	struct eeti_ts_priv *priv = i2c_get_clientdata(client);
+	struct input_dev *input_dev = priv->input;
 
 	if (device_may_wakeup(&client->dev))
 		disable_irq_wake(priv->irq);
 
+	mutex_lock(&input_dev->mutex);
+
+	if (input_dev->users)
+		eeti_ts_start(priv);
+
+	mutex_unlock(&input_dev->mutex);
+
 	return 0;
 }
 #else

drivers/md/md.c

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9712b2e..cefd63d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2109,12 +2109,18 @@
 		if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */
 			/* .. if the array isn't clean, an 'even' event must also go
 			 * to spares. */
-			if ((mddev->events&1)==0)
+			if ((mddev->events&1)==0) {
 				nospares = 0;
+				sync_req = 2; /* force a second update to get the
+					       * even/odd in sync */
+			}
 		} else {
 			/* otherwise an 'odd' event must go to spares */
-			if ((mddev->events&1))
+			if ((mddev->events&1)) {
 				nospares = 0;
+				sync_req = 2; /* force a second update to get the
+					       * even/odd in sync */
+			}
 		}
 	}
 

drivers/md/raid5.c

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 58ea0ec..15348c3 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1527,7 +1527,7 @@
 
 		clear_bit(R5_UPTODATE, &sh->dev[i].flags);
 		atomic_inc(&rdev->read_errors);
-		if (conf->mddev->degraded)
+		if (conf->mddev->degraded >= conf->max_degraded)
 			printk_rl(KERN_WARNING
 				  "raid5:%s: read error not correctable "
 				  "(sector %llu on %s).\n",

drivers/media/common/saa7146_fops.c

diff --git a/drivers/media/common/saa7146_fops.c b/drivers/media/common/saa7146_fops.c
index fd8e1f4..7364b96 100644
--- a/drivers/media/common/saa7146_fops.c
+++ b/drivers/media/common/saa7146_fops.c
@@ -423,15 +423,14 @@
 	}
 }
 
-int saa7146_vv_devinit(struct saa7146_dev *dev)
-{
-	return v4l2_device_register(&dev->pci->dev, &dev->v4l2_dev);
-}
-EXPORT_SYMBOL_GPL(saa7146_vv_devinit);
-
 int saa7146_vv_init(struct saa7146_dev* dev, struct saa7146_ext_vv *ext_vv)
 {
 	struct saa7146_vv *vv;
+	int err;
+
+	err = v4l2_device_register(&dev->pci->dev, &dev->v4l2_dev);
+	if (err)
+		return err;
 
 	vv = kzalloc(sizeof(struct saa7146_vv), GFP_KERNEL);
 	if (vv == NULL) {

drivers/media/common/saa7146_video.c

diff --git a/drivers/media/common/saa7146_video.c b/drivers/media/common/saa7146_video.c
index 5ed7526..b8b2c55 100644
--- a/drivers/media/common/saa7146_video.c
+++ b/drivers/media/common/saa7146_video.c
@@ -558,9 +558,11 @@
 	/* ok, accept it */
 	vv->ov_fb = *fb;
 	vv->ov_fmt = fmt;
-	if (0 == vv->ov_fb.fmt.bytesperline)
-		vv->ov_fb.fmt.bytesperline =
-			vv->ov_fb.fmt.width * fmt->depth / 8;
+
+	if (vv->ov_fb.fmt.bytesperline < vv->ov_fb.fmt.width) {
+		vv->ov_fb.fmt.bytesperline = vv->ov_fb.fmt.width * fmt->depth / 8;
+		DEB_D(("setting bytesperline to %d\n", vv->ov_fb.fmt.bytesperline));
+	}
 
 	mutex_unlock(&dev->lock);
 	return 0;

drivers/media/dvb/frontends/stv090x.c

diff --git a/drivers/media/dvb/frontends/stv090x.c b/drivers/media/dvb/frontends/stv090x.c
index a3c07fe..9697280 100644
--- a/drivers/media/dvb/frontends/stv090x.c
+++ b/drivers/media/dvb/frontends/stv090x.c
@@ -4470,6 +4470,10 @@
 	if (stv090x_write_reg(state, STV090x_TSTRES0, 0x00) < 0)
 		goto err;
 
+	/* workaround for stuck DiSEqC output */
+	if (config->diseqc_envelope_mode)
+		stv090x_send_diseqc_burst(fe, SEC_MINI_A);
+
 	return 0;
 err:
 	dprintk(FE_ERROR, 1, "I/O error");

drivers/media/dvb/ttpci/budget.c

diff --git a/drivers/media/dvb/ttpci/budget.c b/drivers/media/dvb/ttpci/budget.c
index 9fdf26c..1500210 100644
--- a/drivers/media/dvb/ttpci/budget.c
+++ b/drivers/media/dvb/ttpci/budget.c
@@ -643,9 +643,6 @@
 					&budget->i2c_adap,
 					&tt1600_isl6423_config);
 
-			} else {
-				dvb_frontend_detach(budget->dvb_frontend);
-				budget->dvb_frontend = NULL;
 			}
 		}
 		break;

drivers/media/video/Kconfig

diff --git a/drivers/media/video/Kconfig b/drivers/media/video/Kconfig
index f8fc865..9644cf7 100644
--- a/drivers/media/video/Kconfig
+++ b/drivers/media/video/Kconfig
@@ -361,7 +361,7 @@
 
 config VIDEO_SAA7191
 	tristate "Philips SAA7191 video decoder"
-	depends on VIDEO_V4L1 && I2C
+	depends on VIDEO_V4L2 && I2C
 	---help---
 	  Support for the Philips SAA7191 video decoder.
 
@@ -756,7 +756,7 @@
 
 config VIDEO_MXB
 	tristate "Siemens-Nixdorf 'Multimedia eXtension Board'"
-	depends on PCI && VIDEO_V4L1 && I2C
+	depends on PCI && VIDEO_V4L2 && I2C
 	select VIDEO_SAA7146_VV
 	select VIDEO_TUNER
 	select VIDEO_SAA711X if VIDEO_HELPER_CHIPS_AUTO

drivers/media/video/Makefile

diff --git a/drivers/media/video/Makefile b/drivers/media/video/Makefile
index b88b617..c51c386 100644
--- a/drivers/media/video/Makefile
+++ b/drivers/media/video/Makefile
@@ -160,8 +160,6 @@
 obj-$(CONFIG_VIDEO_PXA27x)		+= pxa_camera.o
 obj-$(CONFIG_VIDEO_SH_MOBILE_CEU)	+= sh_mobile_ceu_camera.o
 
-obj-$(CONFIG_ARCH_DAVINCI)		+= davinci/
-
 obj-$(CONFIG_VIDEO_AU0828) += au0828/
 
 obj-$(CONFIG_USB_VIDEO_CLASS)	+= uvc/

drivers/media/video/davinci/vpfe_capture.c

diff --git a/drivers/media/video/davinci/vpfe_capture.c b/drivers/media/video/davinci/vpfe_capture.c
index 7cf042f..398dbe7 100644
--- a/drivers/media/video/davinci/vpfe_capture.c
+++ b/drivers/media/video/davinci/vpfe_capture.c
@@ -223,7 +223,6 @@
 	BUG_ON(!dev->hw_ops.get_frame_format);
 	BUG_ON(!dev->hw_ops.get_pixel_format);
 	BUG_ON(!dev->hw_ops.set_pixel_format);
-	BUG_ON(!dev->hw_ops.set_params);
 	BUG_ON(!dev->hw_ops.set_image_window);
 	BUG_ON(!dev->hw_ops.get_image_window);
 	BUG_ON(!dev->hw_ops.get_line_length);
@@ -1689,11 +1688,12 @@
 	struct vpfe_device *vpfe_dev = video_drvdata(file);
 	int ret = 0;
 
-	v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_param_handler\n");
+	v4l2_dbg(2, debug, &vpfe_dev->v4l2_dev, "vpfe_param_handler\n");
 
 	if (vpfe_dev->started) {
 		/* only allowed if streaming is not started */
-		v4l2_err(&vpfe_dev->v4l2_dev, "device already started\n");
+		v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
+			"device already started\n");
 		return -EBUSY;
 	}
 
@@ -1705,16 +1705,23 @@
 	case VPFE_CMD_S_CCDC_RAW_PARAMS:
 		v4l2_warn(&vpfe_dev->v4l2_dev,
 			  "VPFE_CMD_S_CCDC_RAW_PARAMS: experimental ioctl\n");
-		ret = ccdc_dev->hw_ops.set_params(param);
-		if (ret) {
-			v4l2_err(&vpfe_dev->v4l2_dev,
-				"Error in setting parameters in CCDC\n");
-			goto unlock_out;
-		}
-		if (vpfe_get_ccdc_image_format(vpfe_dev, &vpfe_dev->fmt) < 0) {
-			v4l2_err(&vpfe_dev->v4l2_dev,
-				"Invalid image format at CCDC\n");
-			goto unlock_out;
+		if (ccdc_dev->hw_ops.set_params) {
+			ret = ccdc_dev->hw_ops.set_params(param);
+			if (ret) {
+				v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
+					"Error setting parameters in CCDC\n");
+				goto unlock_out;
+			}
+			if (vpfe_get_ccdc_image_format(vpfe_dev,
+						       &vpfe_dev->fmt) < 0) {
+				v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
+					"Invalid image format at CCDC\n");
+				goto unlock_out;
+			}
+		} else {
+			ret = -EINVAL;
+			v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
+				"VPFE_CMD_S_CCDC_RAW_PARAMS not supported\n");
 		}
 		break;
 	default:
@@ -1830,7 +1837,7 @@
 	if (NULL == ccdc_cfg) {
 		v4l2_err(pdev->dev.driver,
 			 "Memory allocation failed for ccdc_cfg\n");
-		goto probe_free_dev_mem;
+		goto probe_free_lock;
 	}
 
 	strncpy(ccdc_cfg->name, vpfe_cfg->ccdc, 32);
@@ -1982,8 +1989,9 @@
 probe_out_release_irq:
 	free_irq(vpfe_dev->ccdc_irq0, vpfe_dev);
 probe_free_ccdc_cfg_mem:
-	mutex_unlock(&ccdc_lock);
 	kfree(ccdc_cfg);
+probe_free_lock:
+	mutex_unlock(&ccdc_lock);
 probe_free_dev_mem:
 	kfree(vpfe_dev);
 	return ret;

drivers/media/video/gspca/sn9c20x.c

diff --git a/drivers/media/video/gspca/sn9c20x.c b/drivers/media/video/gspca/sn9c20x.c
index 38a6e15..3dee3e5 100644
--- a/drivers/media/video/gspca/sn9c20x.c
+++ b/drivers/media/video/gspca/sn9c20x.c
@@ -1427,7 +1427,7 @@
 	struct gspca_dev *gspca_dev = (struct gspca_dev *)data;
 	struct sd *sd = (struct sd *) gspca_dev;
 
-	DECLARE_WAIT_QUEUE_HEAD(wait);
+	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wait);
 	set_freezable();
 	for (;;) {
 		if (kthread_should_stop())

drivers/media/video/gspca/spca508.c

diff --git a/drivers/media/video/gspca/spca508.c b/drivers/media/video/gspca/spca508.c
index 15b2eef..edf0fe1 100644
--- a/drivers/media/video/gspca/spca508.c
+++ b/drivers/media/video/gspca/spca508.c
@@ -1513,7 +1513,6 @@
 static const __devinitdata struct usb_device_id device_table[] = {
 	{USB_DEVICE(0x0130, 0x0130), .driver_info = HamaUSBSightcam},
 	{USB_DEVICE(0x041e, 0x4018), .driver_info = CreativeVista},
-	{USB_DEVICE(0x0461, 0x0815), .driver_info = MicroInnovationIC200},
 	{USB_DEVICE(0x0733, 0x0110), .driver_info = ViewQuestVQ110},
 	{USB_DEVICE(0x0af9, 0x0010), .driver_info = HamaUSBSightcam},
 	{USB_DEVICE(0x0af9, 0x0011), .driver_info = HamaUSBSightcam2},

drivers/media/video/gspca/spca561.c

diff --git a/drivers/media/video/gspca/spca561.c b/drivers/media/video/gspca/spca561.c
index dc7f2b0..b9c80e2 100644
--- a/drivers/media/video/gspca/spca561.c
+++ b/drivers/media/video/gspca/spca561.c
@@ -1053,6 +1053,7 @@
 	{USB_DEVICE(0x041e, 0x401a), .driver_info = Rev072A},
 	{USB_DEVICE(0x041e, 0x403b), .driver_info = Rev012A},
 	{USB_DEVICE(0x0458, 0x7004), .driver_info = Rev072A},
+	{USB_DEVICE(0x0461, 0x0815), .driver_info = Rev072A},
 	{USB_DEVICE(0x046d, 0x0928), .driver_info = Rev012A},
 	{USB_DEVICE(0x046d, 0x0929), .driver_info = Rev012A},
 	{USB_DEVICE(0x046d, 0x092a), .driver_info = Rev012A},

drivers/media/video/gspca/stv06xx/stv06xx.c

diff --git a/drivers/media/video/gspca/stv06xx/stv06xx.c b/drivers/media/video/gspca/stv06xx/stv06xx.c
index af73da3..14f179a 100644
--- a/drivers/media/video/gspca/stv06xx/stv06xx.c
+++ b/drivers/media/video/gspca/stv06xx/stv06xx.c
@@ -524,8 +524,6 @@
 	{USB_DEVICE(0x046D, 0x08F5), .driver_info = BRIDGE_ST6422 },
 	/* QuickCam Messenger (new) */
 	{USB_DEVICE(0x046D, 0x08F6), .driver_info = BRIDGE_ST6422 },
-	/* QuickCam Messenger (new) */
-	{USB_DEVICE(0x046D, 0x08DA), .driver_info = BRIDGE_ST6422 },
 	{}
 };
 MODULE_DEVICE_TABLE(usb, device_table);

drivers/media/video/hexium_gemini.c

diff --git a/drivers/media/video/hexium_gemini.c b/drivers/media/video/hexium_gemini.c
index e620a3a..ad2c232 100644
--- a/drivers/media/video/hexium_gemini.c
+++ b/drivers/media/video/hexium_gemini.c
@@ -356,9 +356,6 @@
 
 	DEB_EE((".\n"));
 
-	ret = saa7146_vv_devinit(dev);
-	if (ret)
-		return ret;
 	hexium = kzalloc(sizeof(struct hexium), GFP_KERNEL);
 	if (NULL == hexium) {
 		printk("hexium_gemini: not enough kernel memory in hexium_attach().\n");

drivers/media/video/hexium_orion.c

diff --git a/drivers/media/video/hexium_orion.c b/drivers/media/video/hexium_orion.c
index fe596a1..938a1f8 100644
--- a/drivers/media/video/hexium_orion.c
+++ b/drivers/media/video/hexium_orion.c
@@ -216,10 +216,6 @@
 		return -EFAULT;
 	}
 
-	err = saa7146_vv_devinit(dev);
-	if (err)
-		return err;
-
 	hexium = kzalloc(sizeof(struct hexium), GFP_KERNEL);
 	if (NULL == hexium) {
 		printk("hexium_orion: hexium_probe: not enough kernel memory.\n");

drivers/media/video/mx1_camera.c

diff --git a/drivers/media/video/mx1_camera.c b/drivers/media/video/mx1_camera.c
index 3c8ebfc..34a6601 100644
--- a/drivers/media/video/mx1_camera.c
+++ b/drivers/media/video/mx1_camera.c
@@ -49,8 +49,6 @@
 /*
  * CSI registers
  */
-#define DMA_CCR(x)	(0x8c + ((x) << 6))	/* Control Registers */
-#define DMA_DIMR	0x08			/* Interrupt mask Register */
 #define CSICR1		0x00			/* CSI Control Register 1 */
 #define CSISR		0x08			/* CSI Status Register */
 #define CSIRXR		0x10			/* CSI RxFIFO Register */
@@ -784,7 +782,7 @@
 			       pcdev);
 
 	imx_dma_config_channel(pcdev->dma_chan, IMX_DMA_TYPE_FIFO,
-			       IMX_DMA_MEMSIZE_32, DMA_REQ_CSI_R, 0);
+			       IMX_DMA_MEMSIZE_32, MX1_DMA_REQ_CSI_R, 0);
 	/* burst length : 16 words = 64 bytes */
 	imx_dma_config_burstlen(pcdev->dma_chan, 0);
 
@@ -798,8 +796,8 @@
 	set_fiq_handler(&mx1_camera_sof_fiq_start, &mx1_camera_sof_fiq_end -
 						   &mx1_camera_sof_fiq_start);
 
-	regs.ARM_r8 = DMA_BASE + DMA_DIMR;
-	regs.ARM_r9 = DMA_BASE + DMA_CCR(pcdev->dma_chan);
+	regs.ARM_r8 = (long)MX1_DMA_DIMR;
+	regs.ARM_r9 = (long)MX1_DMA_CCR(pcdev->dma_chan);
 	regs.ARM_r10 = (long)pcdev->base + CSICR1;
 	regs.ARM_fp = (long)pcdev->base + CSISR;
 	regs.ARM_sp = 1 << pcdev->dma_chan;

drivers/media/video/mxb.c

diff --git a/drivers/media/video/mxb.c b/drivers/media/video/mxb.c
index 9f01f14..ef0c817 100644
--- a/drivers/media/video/mxb.c
+++ b/drivers/media/video/mxb.c
@@ -169,11 +169,7 @@
 static int mxb_probe(struct saa7146_dev *dev)
 {
 	struct mxb *mxb = NULL;
-	int err;
 
-	err = saa7146_vv_devinit(dev);
-	if (err)
-		return err;
 	mxb = kzalloc(sizeof(struct mxb), GFP_KERNEL);
 	if (mxb == NULL) {
 		DEB_D(("not enough kernel memory.\n"));
@@ -699,14 +695,17 @@
 /* this function only gets called when the probing was successful */
 static int mxb_attach(struct saa7146_dev *dev, struct saa7146_pci_extension_data *info)
 {
-	struct mxb *mxb = (struct mxb *)dev->ext_priv;
+	struct mxb *mxb;
 
 	DEB_EE(("dev:%p\n", dev));
 
-	/* checking for i2c-devices can be omitted here, because we
-	   already did this in "mxb_vl42_probe" */
-
 	saa7146_vv_init(dev, &vv_data);
+	if (mxb_probe(dev)) {
+		saa7146_vv_release(dev);
+		return -1;
+	}
+	mxb = (struct mxb *)dev->ext_priv;
+
 	vv_data.ops.vidioc_queryctrl = vidioc_queryctrl;
 	vv_data.ops.vidioc_g_ctrl = vidioc_g_ctrl;
 	vv_data.ops.vidioc_s_ctrl = vidioc_s_ctrl;
@@ -726,6 +725,7 @@
 	vv_data.ops.vidioc_default = vidioc_default;
 	if (saa7146_register_device(&mxb->video_dev, dev, "mxb", VFL_TYPE_GRABBER)) {
 		ERR(("cannot register capture v4l2 device. skipping.\n"));
+		saa7146_vv_release(dev);
 		return -1;
 	}
 
@@ -846,7 +846,6 @@
 	.pci_tbl	= &pci_tbl[0],
 	.module		= THIS_MODULE,
 
-	.probe		= mxb_probe,
 	.attach		= mxb_attach,
 	.detach		= mxb_detach,
 

drivers/media/video/omap24xxcam.c

diff --git a/drivers/media/video/omap24xxcam.c b/drivers/media/video/omap24xxcam.c
index b189fe6..ce76d95 100644
--- a/drivers/media/video/omap24xxcam.c
+++ b/drivers/media/video/omap24xxcam.c
@@ -1405,7 +1405,7 @@
 	}
 
 	size = 0;
-	for (i = first; i <= last; i++) {
+	for (i = first; i <= last && i < VIDEO_MAX_FRAME; i++) {
 		struct videobuf_dmabuf *dma = videobuf_to_dma(vbq->bufs[i]);
 
 		for (j = 0; j < dma->sglen; j++) {

drivers/media/video/pxa_camera.c

diff --git a/drivers/media/video/pxa_camera.c b/drivers/media/video/pxa_camera.c
index 5ecc30d..04bf5c1 100644
--- a/drivers/media/video/pxa_camera.c
+++ b/drivers/media/video/pxa_camera.c
@@ -609,12 +609,9 @@
  */
 static void pxa_camera_start_capture(struct pxa_camera_dev *pcdev)
 {
-	unsigned long cicr0, cifr;
+	unsigned long cicr0;
 
 	dev_dbg(pcdev->soc_host.v4l2_dev.dev, "%s\n", __func__);
-	/* Reset the FIFOs */
-	cifr = __raw_readl(pcdev->base + CIFR) | CIFR_RESET_F;
-	__raw_writel(cifr, pcdev->base + CIFR);
 	/* Enable End-Of-Frame Interrupt */
 	cicr0 = __raw_readl(pcdev->base + CICR0) | CICR0_ENB;
 	cicr0 &= ~CICR0_EOFM;
@@ -935,7 +932,7 @@
 static irqreturn_t pxa_camera_irq(int irq, void *data)
 {
 	struct pxa_camera_dev *pcdev = data;
-	unsigned long status, cicr0;
+	unsigned long status, cifr, cicr0;
 	struct pxa_buffer *buf;
 	struct videobuf_buffer *vb;
 
@@ -949,6 +946,10 @@
 	__raw_writel(status, pcdev->base + CISR);
 
 	if (status & CISR_EOF) {
+		/* Reset the FIFOs */
+		cifr = __raw_readl(pcdev->base + CIFR) | CIFR_RESET_F;
+		__raw_writel(cifr, pcdev->base + CIFR);
+
 		pcdev->active = list_first_entry(&pcdev->capture,
 					   struct pxa_buffer, vb.queue);
 		vb = &pcdev->active->vb;

drivers/media/video/sh_mobile_ceu_camera.c

diff --git a/drivers/media/video/sh_mobile_ceu_camera.c b/drivers/media/video/sh_mobile_ceu_camera.c
index 6e16b39..1ad980f 100644
--- a/drivers/media/video/sh_mobile_ceu_camera.c
+++ b/drivers/media/video/sh_mobile_ceu_camera.c
@@ -1633,7 +1633,7 @@
 	height = pix->height;
 
 	pix->bytesperline = soc_mbus_bytes_per_line(width, xlate->host_fmt);
-	if (pix->bytesperline < 0)
+	if ((int)pix->bytesperline < 0)
 		return pix->bytesperline;
 	pix->sizeimage = height * pix->bytesperline;
 

drivers/mfd/wm831x-core.c

diff --git a/drivers/mfd/wm831x-core.c b/drivers/mfd/wm831x-core.c
index a3d5728..f2ab025 100644
--- a/drivers/mfd/wm831x-core.c
+++ b/drivers/mfd/wm831x-core.c
@@ -349,6 +349,9 @@
 		goto disable;
 	}
 
+	/* If an interrupt arrived late clean up after it */
+	try_wait_for_completion(&wm831x->auxadc_done);
+
 	/* Ignore the result to allow us to soldier on without IRQ hookup */
 	wait_for_completion_timeout(&wm831x->auxadc_done, msecs_to_jiffies(5));
 

drivers/mfd/wm8350-core.c

diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c
index e400a3b..b580748 100644
--- a/drivers/mfd/wm8350-core.c
+++ b/drivers/mfd/wm8350-core.c
@@ -363,6 +363,10 @@
 	reg |= 1 << channel | WM8350_AUXADC_POLL;
 	wm8350_reg_write(wm8350, WM8350_DIGITISER_CONTROL_1, reg);
 
+	/* If a late IRQ left the completion signalled then consume
+	 * the completion. */
+	try_wait_for_completion(&wm8350->auxadc_done);
+
 	/* We ignore the result of the completion and just check for a
 	 * conversion result, allowing us to soldier on if the IRQ
 	 * infrastructure is not set up for the chip. */

drivers/mmc/host/at91_mci.c

diff --git a/drivers/mmc/host/at91_mci.c b/drivers/mmc/host/at91_mci.c
index a6dd7da..336d9f5 100644
--- a/drivers/mmc/host/at91_mci.c
+++ b/drivers/mmc/host/at91_mci.c
@@ -314,8 +314,8 @@
 			dmabuf = (unsigned *)tmpv;
 		}
 
+		flush_kernel_dcache_page(sg_page(sg));
 		kunmap_atomic(sgbuffer, KM_BIO_SRC_IRQ);
-		dmac_flush_range((void *)sgbuffer, ((void *)sgbuffer) + amount);
 		data->bytes_xfered += amount;
 		if (size == 0)
 			break;

drivers/mmc/host/atmel-mci.c

diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 88be37d..fb279f4 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -266,7 +266,7 @@
 				"CMD%u(0x%x) flg %x rsp %x %x %x %x err %d\n",
 				cmd->opcode, cmd->arg, cmd->flags,
 				cmd->resp[0], cmd->resp[1], cmd->resp[2],
-				cmd->resp[2], cmd->error);
+				cmd->resp[3], cmd->error);
 		if (data)
 			seq_printf(s, "DATA %u / %u * %u flg %x err %d\n",
 				data->bytes_xfered, data->blocks,
@@ -276,7 +276,7 @@
 				"CMD%u(0x%x) flg %x rsp %x %x %x %x err %d\n",
 				stop->opcode, stop->arg, stop->flags,
 				stop->resp[0], stop->resp[1], stop->resp[2],
-				stop->resp[2], stop->error);
+				stop->resp[3], stop->error);
 	}
 
 	spin_unlock_bh(&slot->host->lock);
@@ -569,9 +569,10 @@
 {
 	struct mmc_data			*data = host->data;
 
-	dma_unmap_sg(&host->pdev->dev, data->sg, data->sg_len,
-		     ((data->flags & MMC_DATA_WRITE)
-		      ? DMA_TO_DEVICE : DMA_FROM_DEVICE));
+	if (data)
+		dma_unmap_sg(&host->pdev->dev, data->sg, data->sg_len,
+			     ((data->flags & MMC_DATA_WRITE)
+			      ? DMA_TO_DEVICE : DMA_FROM_DEVICE));
 }
 
 static void atmci_stop_dma(struct atmel_mci *host)
@@ -1099,8 +1100,8 @@
 			"command error: status=0x%08x\n", status);
 
 		if (cmd->data) {
-			host->data = NULL;
 			atmci_stop_dma(host);
+			host->data = NULL;
 			mci_writel(host, IDR, MCI_NOTBUSY
 					| MCI_TXRDY | MCI_RXRDY
 					| ATMCI_DATA_ERROR_FLAGS);
@@ -1293,6 +1294,7 @@
 			} else {
 				data->bytes_xfered = data->blocks * data->blksz;
 				data->error = 0;
+				mci_writel(host, IDR, ATMCI_DATA_ERROR_FLAGS);
 			}
 
 			if (!data->stop) {
@@ -1751,13 +1753,13 @@
 	ret = -ENODEV;
 	if (pdata->slot[0].bus_width) {
 		ret = atmci_init_slot(host, &pdata->slot[0],
-				MCI_SDCSEL_SLOT_A, 0);
+				0, MCI_SDCSEL_SLOT_A);
 		if (!ret)
 			nr_slots++;
 	}
 	if (pdata->slot[1].bus_width) {
 		ret = atmci_init_slot(host, &pdata->slot[1],
-				MCI_SDCSEL_SLOT_B, 1);
+				1, MCI_SDCSEL_SLOT_B);
 		if (!ret)
 			nr_slots++;
 	}

drivers/mtd/internal.h

diff --git a/drivers/mtd/internal.h b/drivers/mtd/internal.h
deleted file mode 100644
index e69de29..0000000
--- a/drivers/mtd/internal.h
+++ /dev/null

drivers/mtd/mtdbdi.c

diff --git a/drivers/mtd/mtdbdi.c b/drivers/mtd/mtdbdi.c
deleted file mode 100644
index e69de29..0000000
--- a/drivers/mtd/mtdbdi.c
+++ /dev/null

drivers/net/a2065.c

diff --git a/drivers/net/a2065.c b/drivers/net/a2065.c
index ed5e974..a8f0512 100644
--- a/drivers/net/a2065.c
+++ b/drivers/net/a2065.c
@@ -674,6 +674,7 @@
 	{ ZORRO_PROD_AMERISTAR_A2065 },
 	{ 0 }
 };
+MODULE_DEVICE_TABLE(zorro, a2065_zorro_tbl);
 
 static struct zorro_driver a2065_driver = {
 	.name		= "a2065",

drivers/net/ariadne.c

diff --git a/drivers/net/ariadne.c b/drivers/net/ariadne.c
index fa1a235..4b30a46 100644
--- a/drivers/net/ariadne.c
+++ b/drivers/net/ariadne.c
@@ -145,6 +145,7 @@
     { ZORRO_PROD_VILLAGE_TRONIC_ARIADNE },
     { 0 }
 };
+MODULE_DEVICE_TABLE(zorro, ariadne_zorro_tbl);
 
 static struct zorro_driver ariadne_driver = {
     .name	= "ariadne",

drivers/net/arm/ep93xx_eth.c

diff --git a/drivers/net/arm/ep93xx_eth.c b/drivers/net/arm/ep93xx_eth.c
index 6995169..cd17d09 100644
--- a/drivers/net/arm/ep93xx_eth.c
+++ b/drivers/net/arm/ep93xx_eth.c
@@ -311,11 +311,6 @@
 		processed++;
 	}
 
-	if (processed) {
-		wrw(ep, REG_RXDENQ, processed);
-		wrw(ep, REG_RXSTSENQ, processed);
-	}
-
 	return processed;
 }
 
@@ -350,6 +345,11 @@
 			goto poll_some_more;
 	}
 
+	if (rx) {
+		wrw(ep, REG_RXDENQ, rx);
+		wrw(ep, REG_RXSTSENQ, rx);
+	}
+
 	return rx;
 }
 

drivers/net/e1000e/netdev.c

diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index fb8fc7d..dbf8178 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -4633,6 +4633,9 @@
 	reg16 &= ~state;
 	pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16);
 
+	if (!pdev->bus->self)
+		return;
+
 	pos = pci_pcie_cap(pdev->bus->self);
 	pci_read_config_word(pdev->bus->self, pos + PCI_EXP_LNKCTL, &reg16);
 	reg16 &= ~state;

drivers/net/fec.c

diff --git a/drivers/net/fec.c b/drivers/net/fec.c
index 9f98c1c..9b4e8f7 100644
--- a/drivers/net/fec.c
+++ b/drivers/net/fec.c
@@ -1653,7 +1653,7 @@
 		(dev->dev_addr[1] << 16) | (dev->dev_addr[0] << 24),
 		fep->hwp + FEC_ADDR_LOW);
 	writel((dev->dev_addr[5] << 16) | (dev->dev_addr[4] << 24),
-		fep + FEC_ADDR_HIGH);
+		fep->hwp + FEC_ADDR_HIGH);
 	return 0;
 }
 

drivers/net/gianfar.c

diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c
index 4e97ca1..5d3763f 100644
--- a/drivers/net/gianfar.c
+++ b/drivers/net/gianfar.c
@@ -1649,6 +1649,7 @@
 			sizeof(struct rxbd8) * priv->total_rx_ring_size,
 			priv->tx_queue[0]->tx_bd_base,
 			priv->tx_queue[0]->tx_bd_dma_base);
+	skb_queue_purge(&priv->rx_recycle);
 }
 
 void gfar_start(struct net_device *dev)
@@ -2088,7 +2089,6 @@
 
 	disable_napi(priv);
 
-	skb_queue_purge(&priv->rx_recycle);
 	cancel_work_sync(&priv->reset_task);
 	stop_gfar(dev);
 

drivers/net/hydra.c

diff --git a/drivers/net/hydra.c b/drivers/net/hydra.c
index 24724b4..07d8e5b 100644
--- a/drivers/net/hydra.c
+++ b/drivers/net/hydra.c
@@ -71,6 +71,7 @@
     { ZORRO_PROD_HYDRA_SYSTEMS_AMIGANET },
     { 0 }
 };
+MODULE_DEVICE_TABLE(zorro, hydra_zorro_tbl);
 
 static struct zorro_driver hydra_driver = {
     .name	= "hydra",

drivers/net/phy/Kconfig

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index fc5938b..a527e37 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -88,6 +88,11 @@
 	---help---
 	  Supports the LSI ET1011C PHY.
 
+config MICREL_PHY
+	tristate "Driver for Micrel PHYs"
+	---help---
+	  Supports the KSZ9021, VSC8201, KS8001 PHYs.
+
 config FIXED_PHY
 	bool "Driver for MDIO Bus/PHY emulation with fixed speed/link PHYs"
 	depends on PHYLIB=y

drivers/net/phy/Makefile

diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 1342585..13bebab 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -20,4 +20,5 @@
 obj-$(CONFIG_MDIO_GPIO)		+= mdio-gpio.o
 obj-$(CONFIG_NATIONAL_PHY)	+= national.o
 obj-$(CONFIG_STE10XP)		+= ste10Xp.o
+obj-$(CONFIG_MICREL_PHY)	+= micrel.o
 obj-$(CONFIG_MDIO_OCTEON)	+= mdio-octeon.o

drivers/net/phy/mdio-octeon.c

diff --git a/drivers/net/phy/mdio-octeon.c b/drivers/net/phy/mdio-octeon.c
index a872aea..f443d43 100644
--- a/drivers/net/phy/mdio-octeon.c
+++ b/drivers/net/phy/mdio-octeon.c
@@ -88,6 +88,7 @@
 static int __init octeon_mdiobus_probe(struct platform_device *pdev)
 {
 	struct octeon_mdiobus *bus;
+	union cvmx_smix_en smi_en;
 	int i;
 	int err = -ENOENT;
 
@@ -103,6 +104,10 @@
 	if (!bus->mii_bus)
 		goto err;
 
+	smi_en.u64 = 0;
+	smi_en.s.en = 1;
+	cvmx_write_csr(CVMX_SMIX_EN(bus->unit), smi_en.u64);
+
 	/*
 	 * Standard Octeon evaluation boards don't support phy
 	 * interrupts, we need to poll.
@@ -133,17 +138,22 @@
 
 err:
 	devm_kfree(&pdev->dev, bus);
+	smi_en.u64 = 0;
+	cvmx_write_csr(CVMX_SMIX_EN(bus->unit), smi_en.u64);
 	return err;
 }
 
 static int __exit octeon_mdiobus_remove(struct platform_device *pdev)
 {
 	struct octeon_mdiobus *bus;
+	union cvmx_smix_en smi_en;
 
 	bus = dev_get_drvdata(&pdev->dev);
 
 	mdiobus_unregister(bus->mii_bus);
 	mdiobus_free(bus->mii_bus);
+	smi_en.u64 = 0;
+	cvmx_write_csr(CVMX_SMIX_EN(bus->unit), smi_en.u64);
 	return 0;
 }
 

drivers/net/phy/micrel.c

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
new file mode 100644
index 0000000..e67691d
--- /dev/null
+++ b/drivers/net/phy/micrel.c
@@ -0,0 +1,105 @@
+/*
+ * drivers/net/phy/micrel.c
+ *
+ * Driver for Micrel PHYs
+ *
+ * Author: David J. Choi
+ *
+ * Copyright (c) 2010 Micrel, Inc.
+ *
+ * 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.
+ *
+ * Support : ksz9021 , vsc8201, ks8001
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+
+#define	PHY_ID_KSZ9021			0x00221611
+#define	PHY_ID_VSC8201			0x000FC413
+#define	PHY_ID_KS8001			0x0022161A
+
+
+static int kszphy_config_init(struct phy_device *phydev)
+{
+	return 0;
+}
+
+
+static struct phy_driver ks8001_driver = {
+	.phy_id		= PHY_ID_KS8001,
+	.name		= "Micrel KS8001",
+	.phy_id_mask	= 0x00fffff0,
+	.features	= PHY_BASIC_FEATURES,
+	.flags		= PHY_POLL,
+	.config_init	= kszphy_config_init,
+	.config_aneg	= genphy_config_aneg,
+	.read_status	= genphy_read_status,
+	.driver		= { .owner = THIS_MODULE,},
+};
+
+static struct phy_driver vsc8201_driver = {
+	.phy_id		= PHY_ID_VSC8201,
+	.name		= "Micrel VSC8201",
+	.phy_id_mask	= 0x00fffff0,
+	.features	= PHY_BASIC_FEATURES,
+	.flags		= PHY_POLL,
+	.config_init	= kszphy_config_init,
+	.config_aneg	= genphy_config_aneg,
+	.read_status	= genphy_read_status,
+	.driver		= { .owner = THIS_MODULE,},
+};
+
+static struct phy_driver ksz9021_driver = {
+	.phy_id		= PHY_ID_KSZ9021,
+	.phy_id_mask	= 0x000fff10,
+	.name		= "Micrel KSZ9021 Gigabit PHY",
+	.features	= PHY_GBIT_FEATURES | SUPPORTED_Pause,
+	.flags		= PHY_POLL,
+	.config_init	= kszphy_config_init,
+	.config_aneg	= genphy_config_aneg,
+	.read_status	= genphy_read_status,
+	.driver		= { .owner = THIS_MODULE, },
+};
+
+static int __init ksphy_init(void)
+{
+	int ret;
+
+	ret = phy_driver_register(&ks8001_driver);
+	if (ret)
+		goto err1;
+	ret = phy_driver_register(&vsc8201_driver);
+	if (ret)
+		goto err2;
+
+	ret = phy_driver_register(&ksz9021_driver);
+	if (ret)
+		goto err3;
+	return 0;
+
+err3:
+	phy_driver_unregister(&vsc8201_driver);
+err2:
+	phy_driver_unregister(&ks8001_driver);
+err1:
+	return ret;
+}
+
+static void __exit ksphy_exit(void)
+{
+	phy_driver_unregister(&ks8001_driver);
+	phy_driver_unregister(&vsc8201_driver);
+	phy_driver_unregister(&ksz9021_driver);
+}
+
+module_init(ksphy_init);
+module_exit(ksphy_exit);
+
+MODULE_DESCRIPTION("Micrel PHY driver");
+MODULE_AUTHOR("David J. Choi");
+MODULE_LICENSE("GPL");

drivers/net/ppp_generic.c

diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c
index 6e281bc..8518a2e 100644
--- a/drivers/net/ppp_generic.c
+++ b/drivers/net/ppp_generic.c
@@ -405,6 +405,7 @@
 	DECLARE_WAITQUEUE(wait, current);
 	ssize_t ret;
 	struct sk_buff *skb = NULL;
+	struct iovec iov;
 
 	ret = count;
 
@@ -448,7 +449,9 @@
 	if (skb->len > count)
 		goto outf;
 	ret = -EFAULT;
-	if (copy_to_user(buf, skb->data, skb->len))
+	iov.iov_base = buf;
+	iov.iov_len = count;
+	if (skb_copy_datagram_iovec(skb, 0, &iov, skb->len))
 		goto outf;
 	ret = skb->len;
 
@@ -1567,13 +1570,22 @@
 	struct channel *pch = chan->ppp;
 	int proto;
 
-	if (!pch || skb->len == 0) {
+	if (!pch) {
 		kfree_skb(skb);
 		return;
 	}
 
-	proto = PPP_PROTO(skb);
 	read_lock_bh(&pch->upl);
+	if (!pskb_may_pull(skb, 2)) {
+		kfree_skb(skb);
+		if (pch->ppp) {
+			++pch->ppp->dev->stats.rx_length_errors;
+			ppp_receive_error(pch->ppp);
+		}
+		goto done;
+	}
+
+	proto = PPP_PROTO(skb);
 	if (!pch->ppp || proto >= 0xc000 || proto == PPP_CCPFRAG) {
 		/* put it on the channel queue */
 		skb_queue_tail(&pch->file.rq, skb);
@@ -1585,6 +1597,8 @@
 	} else {
 		ppp_do_recv(pch->ppp, skb, pch);
 	}
+
+done:
 	read_unlock_bh(&pch->upl);
 }
 
@@ -1617,7 +1631,8 @@
 static void
 ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
 {
-	if (pskb_may_pull(skb, 2)) {
+	/* note: a 0-length skb is used as an error indication */
+	if (skb->len > 0) {
 #ifdef CONFIG_PPP_MULTILINK
 		/* XXX do channel-level decompression here */
 		if (PPP_PROTO(skb) == PPP_MP)
@@ -1625,15 +1640,10 @@
 		else
 #endif /* CONFIG_PPP_MULTILINK */
 			ppp_receive_nonmp_frame(ppp, skb);
-		return;
+	} else {
+		kfree_skb(skb);
+		ppp_receive_error(ppp);
 	}
-
-	if (skb->len > 0)
-		/* note: a 0-length skb is used as an error indication */
-		++ppp->dev->stats.rx_length_errors;
-
-	kfree_skb(skb);
-	ppp_receive_error(ppp);
 }
 
 static void

drivers/net/r8169.c

diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 4748c21..dd8106f 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -1042,14 +1042,14 @@
 }
 
 static int rtl8169_rx_vlan_skb(struct rtl8169_private *tp, struct RxDesc *desc,
-			       struct sk_buff *skb)
+			       struct sk_buff *skb, int polling)
 {
 	u32 opts2 = le32_to_cpu(desc->opts2);
 	struct vlan_group *vlgrp = tp->vlgrp;
 	int ret;
 
 	if (vlgrp && (opts2 & RxVlanTag)) {
-		vlan_hwaccel_receive_skb(skb, vlgrp, swab16(opts2 & 0xffff));
+		__vlan_hwaccel_rx(skb, vlgrp, swab16(opts2 & 0xffff), polling);
 		ret = 0;
 	} else
 		ret = -1;
@@ -1066,7 +1066,7 @@
 }
 
 static int rtl8169_rx_vlan_skb(struct rtl8169_private *tp, struct RxDesc *desc,
-			       struct sk_buff *skb)
+			       struct sk_buff *skb, int polling)
 {
 	return -1;
 }
@@ -4445,12 +4445,20 @@
 	return done;
 }
 
+/*
+ * Warning : rtl8169_rx_interrupt() might be called :
+ * 1) from NAPI (softirq) context
+ *	(polling = 1 : we should call netif_receive_skb())
+ * 2) from process context (rtl8169_reset_task())
+ *	(polling = 0 : we must call netif_rx() instead)
+ */
 static int rtl8169_rx_interrupt(struct net_device *dev,
 				struct rtl8169_private *tp,
 				void __iomem *ioaddr, u32 budget)
 {
 	unsigned int cur_rx, rx_left;
 	unsigned int delta, count;
+	int polling = (budget != ~(u32)0) ? 1 : 0;
 
 	cur_rx = tp->cur_rx;
 	rx_left = NUM_RX_DESC + tp->dirty_rx - cur_rx;
@@ -4512,8 +4520,12 @@
 			skb_put(skb, pkt_size);
 			skb->protocol = eth_type_trans(skb, dev);
 
-			if (rtl8169_rx_vlan_skb(tp, desc, skb) < 0)
-				netif_receive_skb(skb);
+			if (rtl8169_rx_vlan_skb(tp, desc, skb, polling) < 0) {
+				if (likely(polling))
+					netif_receive_skb(skb);
+				else
+					netif_rx(skb);
+			}
 
 			dev->stats.rx_bytes += pkt_size;
 			dev->stats.rx_packets++;

drivers/net/sb1250-mac.c

diff --git a/drivers/net/sb1250-mac.c b/drivers/net/sb1250-mac.c
index 9944e5d..04efc0c 100644
--- a/drivers/net/sb1250-mac.c
+++ b/drivers/net/sb1250-mac.c
@@ -2353,17 +2353,36 @@
 
 	sc->mii_bus = mdiobus_alloc();
 	if (sc->mii_bus == NULL) {
-		sbmac_uninitctx(sc);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto uninit_ctx;
 	}
 
+	sc->mii_bus->name = sbmac_mdio_string;
+	snprintf(sc->mii_bus->id, MII_BUS_ID_SIZE, "%x", idx);
+	sc->mii_bus->priv = sc;
+	sc->mii_bus->read = sbmac_mii_read;
+	sc->mii_bus->write = sbmac_mii_write;
+	sc->mii_bus->irq = sc->phy_irq;
+	for (i = 0; i < PHY_MAX_ADDR; ++i)
+		sc->mii_bus->irq[i] = SBMAC_PHY_INT;
+
+	sc->mii_bus->parent = &pldev->dev;
+	/*
+	 * Probe PHY address
+	 */
+	err = mdiobus_register(sc->mii_bus);
+	if (err) {
+		printk(KERN_ERR "%s: unable to register MDIO bus\n",
+		       dev->name);
+		goto free_mdio;
+	}
+	dev_set_drvdata(&pldev->dev, sc->mii_bus);
+
 	err = register_netdev(dev);
 	if (err) {
 		printk(KERN_ERR "%s.%d: unable to register netdev\n",
 		       sbmac_string, idx);
-		mdiobus_free(sc->mii_bus);
-		sbmac_uninitctx(sc);
-		return err;
+		goto unreg_mdio;
 	}
 
 	pr_info("%s.%d: registered as %s\n", sbmac_string, idx, dev->name);
@@ -2379,19 +2398,15 @@
 	pr_info("%s: SiByte Ethernet at 0x%08Lx, address: %pM\n",
 	       dev->name, base, eaddr);
 
-	sc->mii_bus->name = sbmac_mdio_string;
-	snprintf(sc->mii_bus->id, MII_BUS_ID_SIZE, "%x", idx);
-	sc->mii_bus->priv = sc;
-	sc->mii_bus->read = sbmac_mii_read;
-	sc->mii_bus->write = sbmac_mii_write;
-	sc->mii_bus->irq = sc->phy_irq;
-	for (i = 0; i < PHY_MAX_ADDR; ++i)
-		sc->mii_bus->irq[i] = SBMAC_PHY_INT;
-
-	sc->mii_bus->parent = &pldev->dev;
-	dev_set_drvdata(&pldev->dev, sc->mii_bus);
-
 	return 0;
+unreg_mdio:
+	mdiobus_unregister(sc->mii_bus);
+	dev_set_drvdata(&pldev->dev, NULL);
+free_mdio:
+	mdiobus_free(sc->mii_bus);
+uninit_ctx:
+	sbmac_uninitctx(sc);
+	return err;
 }
 
 
@@ -2417,16 +2432,6 @@
 		goto out_err;
 	}
 
-	/*
-	 * Probe PHY address
-	 */
-	err = mdiobus_register(sc->mii_bus);
-	if (err) {
-		printk(KERN_ERR "%s: unable to register MDIO bus\n",
-		       dev->name);
-		goto out_unirq;
-	}
-
 	sc->sbm_speed = sbmac_speed_none;
 	sc->sbm_duplex = sbmac_duplex_none;
 	sc->sbm_fc = sbmac_fc_none;
@@ -2457,11 +2462,7 @@
 	return 0;
 
 out_unregister:
-	mdiobus_unregister(sc->mii_bus);
-
-out_unirq:
 	free_irq(dev->irq, dev);
-
 out_err:
 	return err;
 }
@@ -2650,9 +2651,6 @@
 
 	phy_disconnect(sc->phy_dev);
 	sc->phy_dev = NULL;
-
-	mdiobus_unregister(sc->mii_bus);
-
 	free_irq(dev->irq, dev);
 
 	sbdma_emptyring(&(sc->sbm_txdma));
@@ -2760,6 +2758,7 @@
 
 	unregister_netdev(dev);
 	sbmac_uninitctx(sc);
+	mdiobus_unregister(sc->mii_bus);
 	mdiobus_free(sc->mii_bus);
 	iounmap(sc->sbm_base);
 	free_netdev(dev);

drivers/net/usb/Kconfig

diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 5d58abc..d7b7018 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -400,7 +400,6 @@
 config USB_SIERRA_NET
 	tristate "USB-to-WWAN Driver for Sierra Wireless modems"
 	depends on USB_USBNET
-	default y
 	help
 	  Choose this option if you have a Sierra Wireless USB-to-WWAN device.
 

drivers/net/usb/dm9601.c

diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 04b2810..5dfed92 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -240,7 +240,7 @@
 		goto out;
 
 	dm_write_reg(dev, DM_SHARED_ADDR, phy ? (reg | 0x40) : reg);
-	dm_write_reg(dev, DM_SHARED_CTRL, phy ? 0x1c : 0x14);
+	dm_write_reg(dev, DM_SHARED_CTRL, phy ? 0x1a : 0x12);
 
 	for (i = 0; i < DM_TIMEOUT; i++) {
 		u8 tmp;

drivers/net/usb/sierra_net.c

diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index a44f9e0..f1942d6 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -789,6 +789,9 @@
 	/* prepare sync message from template */
 	memcpy(priv->sync_msg, sync_tmplate, sizeof(priv->sync_msg));
 
+	/* initiate the sync sequence */
+	sierra_net_dosync(dev);
+
 	return 0;
 }
 

drivers/net/veth.c

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index f9f0730..5ec542d 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -187,7 +187,6 @@
 	return NETDEV_TX_OK;
 
 rx_drop:
-	kfree_skb(skb);
 	rcv_stats->rx_dropped++;
 	return NETDEV_TX_OK;
 }

drivers/net/wireless/ath/ar9170/usb.c

diff --git a/drivers/net/wireless/ath/ar9170/usb.c b/drivers/net/wireless/ath/ar9170/usb.c
index 99a6da4..e1c2fca 100644
--- a/drivers/net/wireless/ath/ar9170/usb.c
+++ b/drivers/net/wireless/ath/ar9170/usb.c
@@ -727,12 +727,16 @@
 {
 	struct device *parent = aru->udev->dev.parent;
 
+	complete(&aru->firmware_loading_complete);
+
 	/* unbind anything failed */
 	if (parent)
 		down(&parent->sem);
 	device_release_driver(&aru->udev->dev);
 	if (parent)
 		up(&parent->sem);
+
+	usb_put_dev(aru->udev);
 }
 
 static void ar9170_usb_firmware_finish(const struct firmware *fw, void *context)
@@ -761,6 +765,8 @@
 	if (err)
 		goto err_unrx;
 
+	complete(&aru->firmware_loading_complete);
+	usb_put_dev(aru->udev);
 	return;
 
  err_unrx:
@@ -858,6 +864,7 @@
 	init_usb_anchor(&aru->tx_pending);
 	init_usb_anchor(&aru->tx_submitted);
 	init_completion(&aru->cmd_wait);
+	init_completion(&aru->firmware_loading_complete);
 	spin_lock_init(&aru->tx_urb_lock);
 
 	aru->tx_pending_urbs = 0;
@@ -877,6 +884,7 @@
 	if (err)
 		goto err_freehw;
 
+	usb_get_dev(aru->udev);
 	return request_firmware_nowait(THIS_MODULE, 1, "ar9170.fw",
 				       &aru->udev->dev, GFP_KERNEL, aru,
 				       ar9170_usb_firmware_step2);
@@ -896,6 +904,9 @@
 		return;
 
 	aru->common.state = AR9170_IDLE;
+
+	wait_for_completion(&aru->firmware_loading_complete);
+
 	ar9170_unregister(&aru->common);
 	ar9170_usb_cancel_urbs(aru);
 

drivers/net/wireless/ath/ar9170/usb.h

diff --git a/drivers/net/wireless/ath/ar9170/usb.h b/drivers/net/wireless/ath/ar9170/usb.h
index a2ce3b1..919b060 100644
--- a/drivers/net/wireless/ath/ar9170/usb.h
+++ b/drivers/net/wireless/ath/ar9170/usb.h
@@ -71,6 +71,7 @@
 	unsigned int tx_pending_urbs;
 
 	struct completion cmd_wait;
+	struct completion firmware_loading_complete;
 	int readlen;
 	u8 *readbuf;
 

drivers/net/wireless/iwlwifi/iwl-commands.h

diff --git a/drivers/net/wireless/iwlwifi/iwl-commands.h b/drivers/net/wireless/iwlwifi/iwl-commands.h
index 6383d9f..f4e59ae 100644
--- a/drivers/net/wireless/iwlwifi/iwl-commands.h
+++ b/drivers/net/wireless/iwlwifi/iwl-commands.h
@@ -2621,7 +2621,9 @@
 #define PROBE_OPTION_MAX_3945		4
 #define PROBE_OPTION_MAX		20
 #define TX_CMD_LIFE_TIME_INFINITE	cpu_to_le32(0xFFFFFFFF)
-#define IWL_GOOD_CRC_TH			cpu_to_le16(1)
+#define IWL_GOOD_CRC_TH_DISABLED	0
+#define IWL_GOOD_CRC_TH_DEFAULT		cpu_to_le16(1)
+#define IWL_GOOD_CRC_TH_NEVER		cpu_to_le16(0xffff)
 #define IWL_MAX_SCAN_SIZE 1024
 #define IWL_MAX_CMD_SIZE 4096
 #define IWL_MAX_PROBE_REQUEST		200

drivers/net/wireless/iwlwifi/iwl-scan.c

diff --git a/drivers/net/wireless/iwlwifi/iwl-scan.c b/drivers/net/wireless/iwlwifi/iwl-scan.c
index 12e455a..741e65e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-scan.c
+++ b/drivers/net/wireless/iwlwifi/iwl-scan.c
@@ -813,16 +813,29 @@
 			rate = IWL_RATE_1M_PLCP;
 			rate_flags = RATE_MCS_CCK_MSK;
 		}
-		scan->good_CRC_th = 0;
+		scan->good_CRC_th = IWL_GOOD_CRC_TH_DISABLED;
 	} else if (priv->scan_bands & BIT(IEEE80211_BAND_5GHZ)) {
 		band = IEEE80211_BAND_5GHZ;
 		rate = IWL_RATE_6M_PLCP;
 		/*
-		 * If active scaning is requested but a certain channel
-		 * is marked passive, we can do active scanning if we
-		 * detect transmissions.
+		 * If active scanning is requested but a certain channel is
+		 * marked passive, we can do active scanning if we detect
+		 * transmissions.
+		 *
+		 * There is an issue with some firmware versions that triggers
+		 * a sysassert on a "good CRC threshold" of zero (== disabled),
+		 * on a radar channel even though this means that we should NOT
+		 * send probes.
+		 *
+		 * The "good CRC threshold" is the number of frames that we
+		 * need to receive during our dwell time on a channel before
+		 * sending out probes -- setting this to a huge value will
+		 * mean we never reach it, but at the same time work around
+		 * the aforementioned issue. Thus use IWL_GOOD_CRC_TH_NEVER
+		 * here instead of IWL_GOOD_CRC_TH_DISABLED.
 		 */
-		scan->good_CRC_th = is_active ? IWL_GOOD_CRC_TH : 0;
+		scan->good_CRC_th = is_active ? IWL_GOOD_CRC_TH_DEFAULT :
+						IWL_GOOD_CRC_TH_NEVER;
 
 		/* Force use of chains B and C (0x6) for scan Rx for 4965
 		 * Avoid A (0x1) because of its off-channel reception on A-band.

drivers/net/wireless/iwlwifi/iwl3945-base.c

diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c
index b55e4f3..b74a56c 100644
--- a/drivers/net/wireless/iwlwifi/iwl3945-base.c
+++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c
@@ -2967,7 +2967,8 @@
 		 * is marked passive, we can do active scanning if we
 		 * detect transmissions.
 		 */
-		scan->good_CRC_th = is_active ? IWL_GOOD_CRC_TH : 0;
+		scan->good_CRC_th = is_active ? IWL_GOOD_CRC_TH_DEFAULT :
+						IWL_GOOD_CRC_TH_DISABLED;
 		band = IEEE80211_BAND_5GHZ;
 	} else {
 		IWL_WARN(priv, "Invalid scan band count\n");

drivers/net/wireless/p54/p54pci.c

diff --git a/drivers/net/wireless/p54/p54pci.c b/drivers/net/wireless/p54/p54pci.c
index 269fda3..c24067f 100644
--- a/drivers/net/wireless/p54/p54pci.c
+++ b/drivers/net/wireless/p54/p54pci.c
@@ -246,7 +246,7 @@
 	u32 idx, i;
 
 	i = (*index) % ring_limit;
-	(*index) = idx = le32_to_cpu(ring_control->device_idx[1]);
+	(*index) = idx = le32_to_cpu(ring_control->device_idx[ring_index]);
 	idx %= ring_limit;
 
 	while (i != idx) {

drivers/net/zorro8390.c

diff --git a/drivers/net/zorro8390.c b/drivers/net/zorro8390.c
index 81c753a..9548cbb 100644
--- a/drivers/net/zorro8390.c
+++ b/drivers/net/zorro8390.c
@@ -102,6 +102,7 @@
     { ZORRO_PROD_INDIVIDUAL_COMPUTERS_X_SURF, },
     { 0 }
 };
+MODULE_DEVICE_TABLE(zorro, zorro8390_zorro_tbl);
 
 static struct zorro_driver zorro8390_driver = {
     .name	= "zorro8390",

drivers/of/of_mdio.c

diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 18ecae4..b474833 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -69,7 +69,7 @@
 		}
 
 		phy = get_phy_device(mdio, be32_to_cpup(addr));
-		if (!phy) {
+		if (!phy || IS_ERR(phy)) {
 			dev_err(&mdio->dev, "error probing PHY at address %i\n",
 				*addr);
 			continue;

drivers/oprofile/cpu_buffer.c

diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 166b67e..219f79e 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -30,23 +30,7 @@
 
 #define OP_BUFFER_FLAGS	0
 
-/*
- * Read and write access is using spin locking. Thus, writing to the
- * buffer by NMI handler (x86) could occur also during critical
- * sections when reading the buffer. To avoid this, there are 2
- * buffers for independent read and write access. Read access is in
- * process context only, write access only in the NMI handler. If the
- * read buffer runs empty, both buffers are swapped atomically. There
- * is potentially a small window during swapping where the buffers are
- * disabled and samples could be lost.
- *
- * Using 2 buffers is a little bit overhead, but the solution is clear
- * and does not require changes in the ring buffer implementation. It
- * can be changed to a single buffer solution when the ring buffer
- * access is implemented as non-locking atomic code.
- */
-static struct ring_buffer *op_ring_buffer_read;
-static struct ring_buffer *op_ring_buffer_write;
+static struct ring_buffer *op_ring_buffer;
 DEFINE_PER_CPU(struct oprofile_cpu_buffer, op_cpu_buffer);
 
 static void wq_sync_buffer(struct work_struct *work);
@@ -68,12 +52,9 @@
 
 void free_cpu_buffers(void)
 {
-	if (op_ring_buffer_read)
-		ring_buffer_free(op_ring_buffer_read);
-	op_ring_buffer_read = NULL;
-	if (op_ring_buffer_write)
-		ring_buffer_free(op_ring_buffer_write);
-	op_ring_buffer_write = NULL;
+	if (op_ring_buffer)
+		ring_buffer_free(op_ring_buffer);
+	op_ring_buffer = NULL;
 }
 
 #define RB_EVENT_HDR_SIZE 4
@@ -86,11 +67,8 @@
 	unsigned long byte_size = buffer_size * (sizeof(struct op_sample) +
 						 RB_EVENT_HDR_SIZE);
 
-	op_ring_buffer_read = ring_buffer_alloc(byte_size, OP_BUFFER_FLAGS);
-	if (!op_ring_buffer_read)
-		goto fail;
-	op_ring_buffer_write = ring_buffer_alloc(byte_size, OP_BUFFER_FLAGS);
-	if (!op_ring_buffer_write)
+	op_ring_buffer = ring_buffer_alloc(byte_size, OP_BUFFER_FLAGS);
+	if (!op_ring_buffer)
 		goto fail;
 
 	for_each_possible_cpu(i) {
@@ -162,16 +140,11 @@
 *op_cpu_buffer_write_reserve(struct op_entry *entry, unsigned long size)
 {
 	entry->event = ring_buffer_lock_reserve
-		(op_ring_buffer_write, sizeof(struct op_sample) +
+		(op_ring_buffer, sizeof(struct op_sample) +
 		 size * sizeof(entry->sample->data[0]));
-	if (entry->event)
-		entry->sample = ring_buffer_event_data(entry->event);
-	else
-		entry->sample = NULL;
-
-	if (!entry->sample)
+	if (!entry->event)
 		return NULL;
-
+	entry->sample = ring_buffer_event_data(entry->event);
 	entry->size = size;
 	entry->data = entry->sample->data;
 
@@ -180,25 +153,16 @@
 
 int op_cpu_buffer_write_commit(struct op_entry *entry)
 {
-	return ring_buffer_unlock_commit(op_ring_buffer_write, entry->event);
+	return ring_buffer_unlock_commit(op_ring_buffer, entry->event);
 }
 
 struct op_sample *op_cpu_buffer_read_entry(struct op_entry *entry, int cpu)
 {
 	struct ring_buffer_event *e;
-	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL);
-	if (e)
-		goto event;
-	if (ring_buffer_swap_cpu(op_ring_buffer_read,
-				 op_ring_buffer_write,
-				 cpu))
+	e = ring_buffer_consume(op_ring_buffer, cpu, NULL, NULL);
+	if (!e)
 		return NULL;
-	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL);
-	if (e)
-		goto event;
-	return NULL;
 
-event:
 	entry->event = e;
 	entry->sample = ring_buffer_event_data(e);
 	entry->size = (ring_buffer_event_length(e) - sizeof(struct op_sample))
@@ -209,8 +173,7 @@
 
 unsigned long op_cpu_buffer_entries(int cpu)
 {
-	return ring_buffer_entries_cpu(op_ring_buffer_read, cpu)
-		+ ring_buffer_entries_cpu(op_ring_buffer_write, cpu);
+	return ring_buffer_entries_cpu(op_ring_buffer, cpu);
 }
 
 static int
@@ -356,8 +319,16 @@
 
 void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
 {
-	int is_kernel = !user_mode(regs);
-	unsigned long pc = profile_pc(regs);
+	int is_kernel;
+	unsigned long pc;
+
+	if (likely(regs)) {
+		is_kernel = !user_mode(regs);
+		pc = profile_pc(regs);
+	} else {
+		is_kernel = 0;    /* This value will not be used */
+		pc = ESCAPE_CODE; /* as this causes an early return. */
+	}
 
 	__oprofile_add_ext_sample(pc, regs, event, is_kernel);
 }

drivers/oprofile/oprof.c

diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index dc8a042..b336cd9 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -253,22 +253,26 @@
 	int err;
 
 	err = oprofile_arch_init(&oprofile_ops);
-
 	if (err < 0 || timer) {
 		printk(KERN_INFO "oprofile: using timer interrupt.\n");
-		oprofile_timer_init(&oprofile_ops);
+		err = oprofile_timer_init(&oprofile_ops);
+		if (err)
+			goto out_arch;
 	}
-
 	err = oprofilefs_register();
 	if (err)
-		oprofile_arch_exit();
+		goto out_arch;
+	return 0;
 
+out_arch:
+	oprofile_arch_exit();
 	return err;
 }
 
 
 static void __exit oprofile_exit(void)
 {
+	oprofile_timer_exit();
 	oprofilefs_unregister();
 	oprofile_arch_exit();
 }

drivers/oprofile/oprof.h

diff --git a/drivers/oprofile/oprof.h b/drivers/oprofile/oprof.h
index cb92f5c..47e12cb 100644
--- a/drivers/oprofile/oprof.h
+++ b/drivers/oprofile/oprof.h
@@ -34,7 +34,8 @@
 struct dentry;
 
 void oprofile_create_files(struct super_block *sb, struct dentry *root);
-void oprofile_timer_init(struct oprofile_operations *ops);
+int oprofile_timer_init(struct oprofile_operations *ops);
+void oprofile_timer_exit(void);
 
 int oprofile_set_backtrace(unsigned long depth);
 int oprofile_set_timeout(unsigned long time);

drivers/oprofile/timer_int.c

diff --git a/drivers/oprofile/timer_int.c b/drivers/oprofile/timer_int.c
index 333f915..dc0ae4d 100644
--- a/drivers/oprofile/timer_int.c
+++ b/drivers/oprofile/timer_int.c
@@ -13,34 +13,94 @@
 #include <linux/oprofile.h>
 #include <linux/profile.h>
 #include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/hrtimer.h>
+#include <asm/irq_regs.h>
 #include <asm/ptrace.h>
 
 #include "oprof.h"
 
-static int timer_notify(struct pt_regs *regs)
+static DEFINE_PER_CPU(struct hrtimer, oprofile_hrtimer);
+
+static enum hrtimer_restart oprofile_hrtimer_notify(struct hrtimer *hrtimer)
 {
-	oprofile_add_sample(regs, 0);
+	oprofile_add_sample(get_irq_regs(), 0);
+	hrtimer_forward_now(hrtimer, ns_to_ktime(TICK_NSEC));
+	return HRTIMER_RESTART;
+}
+
+static void __oprofile_hrtimer_start(void *unused)
+{
+	struct hrtimer *hrtimer = &__get_cpu_var(oprofile_hrtimer);
+
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer->function = oprofile_hrtimer_notify;
+
+	hrtimer_start(hrtimer, ns_to_ktime(TICK_NSEC),
+		      HRTIMER_MODE_REL_PINNED);
+}
+
+static int oprofile_hrtimer_start(void)
+{
+	on_each_cpu(__oprofile_hrtimer_start, NULL, 1);
 	return 0;
 }
 
-static int timer_start(void)
+static void __oprofile_hrtimer_stop(int cpu)
 {
-	return register_timer_hook(timer_notify);
+	struct hrtimer *hrtimer = &per_cpu(oprofile_hrtimer, cpu);
+
+	hrtimer_cancel(hrtimer);
 }
 
-
-static void timer_stop(void)
+static void oprofile_hrtimer_stop(void)
 {
-	unregister_timer_hook(timer_notify);
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		__oprofile_hrtimer_stop(cpu);
 }
 
-
-void __init oprofile_timer_init(struct oprofile_operations *ops)
+static int __cpuinit oprofile_cpu_notify(struct notifier_block *self,
+					 unsigned long action, void *hcpu)
 {
+	long cpu = (long) hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		smp_call_function_single(cpu, __oprofile_hrtimer_start,
+					 NULL, 1);
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		__oprofile_hrtimer_stop(cpu);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __refdata oprofile_cpu_notifier = {
+	.notifier_call = oprofile_cpu_notify,
+};
+
+int __init oprofile_timer_init(struct oprofile_operations *ops)
+{
+	int rc;
+
+	rc = register_hotcpu_notifier(&oprofile_cpu_notifier);
+	if (rc)
+		return rc;
 	ops->create_files = NULL;
 	ops->setup = NULL;
 	ops->shutdown = NULL;
-	ops->start = timer_start;
-	ops->stop = timer_stop;
+	ops->start = oprofile_hrtimer_start;
+	ops->stop = oprofile_hrtimer_stop;
 	ops->cpu_type = "timer";
+	return 0;
+}
+
+void __exit oprofile_timer_exit(void)
+{
+	unregister_hotcpu_notifier(&oprofile_cpu_notifier);
 }

drivers/pci/intel-iommu.c

diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 4173125..371dc56 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -3626,14 +3626,15 @@
 	domain_remove_one_dev_info(dmar_domain, pdev);
 }
 
-static int intel_iommu_map_range(struct iommu_domain *domain,
-				 unsigned long iova, phys_addr_t hpa,
-				 size_t size, int iommu_prot)
+static int intel_iommu_map(struct iommu_domain *domain,
+			   unsigned long iova, phys_addr_t hpa,
+			   int gfp_order, int iommu_prot)
 {
 	struct dmar_domain *dmar_domain = domain->priv;
 	u64 max_addr;
 	int addr_width;
 	int prot = 0;
+	size_t size;
 	int ret;
 
 	if (iommu_prot & IOMMU_READ)
@@ -3643,6 +3644,7 @@
 	if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping)
 		prot |= DMA_PTE_SNP;
 
+	size     = PAGE_SIZE << gfp_order;
 	max_addr = iova + size;
 	if (dmar_domain->max_addr < max_addr) {
 		int min_agaw;
@@ -3669,19 +3671,19 @@
 	return ret;
 }
 
-static void intel_iommu_unmap_range(struct iommu_domain *domain,
-				    unsigned long iova, size_t size)
+static int intel_iommu_unmap(struct iommu_domain *domain,
+			     unsigned long iova, int gfp_order)
 {
 	struct dmar_domain *dmar_domain = domain->priv;
-
-	if (!size)
-		return;
+	size_t size = PAGE_SIZE << gfp_order;
 
 	dma_pte_clear_range(dmar_domain, iova >> VTD_PAGE_SHIFT,
 			    (iova + size - 1) >> VTD_PAGE_SHIFT);
 
 	if (dmar_domain->max_addr == iova + size)
 		dmar_domain->max_addr = iova;
+
+	return gfp_order;
 }
 
 static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
@@ -3714,8 +3716,8 @@
 	.domain_destroy = intel_iommu_domain_destroy,
 	.attach_dev	= intel_iommu_attach_device,
 	.detach_dev	= intel_iommu_detach_device,
-	.map		= intel_iommu_map_range,
-	.unmap		= intel_iommu_unmap_range,
+	.map		= intel_iommu_map,
+	.unmap		= intel_iommu_unmap,
 	.iova_to_phys	= intel_iommu_iova_to_phys,
 	.domain_has_cap = intel_iommu_domain_has_cap,
 };

drivers/pci/setup-bus.c

diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 4fe36d2..19b1113 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -838,65 +838,11 @@
 	}
 }
 
-static int __init pci_bus_get_depth(struct pci_bus *bus)
-{
-	int depth = 0;
-	struct pci_dev *dev;
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		int ret;
-		struct pci_bus *b = dev->subordinate;
-		if (!b)
-			continue;
-
-		ret = pci_bus_get_depth(b);
-		if (ret + 1 > depth)
-			depth = ret + 1;
-	}
-
-	return depth;
-}
-static int __init pci_get_max_depth(void)
-{
-	int depth = 0;
-	struct pci_bus *bus;
-
-	list_for_each_entry(bus, &pci_root_buses, node) {
-		int ret;
-
-		ret = pci_bus_get_depth(bus);
-		if (ret > depth)
-			depth = ret;
-	}
-
-	return depth;
-}
-
-/*
- * first try will not touch pci bridge res
- * second  and later try will clear small leaf bridge res
- * will stop till to the max  deepth if can not find good one
- */
 void __init
 pci_assign_unassigned_resources(void)
 {
 	struct pci_bus *bus;
-	int tried_times = 0;
-	enum release_type rel_type = leaf_only;
-	struct resource_list_x head, *list;
-	unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM |
-				  IORESOURCE_PREFETCH;
-	unsigned long failed_type;
-	int max_depth = pci_get_max_depth();
-	int pci_try_num;
 
-	head.next = NULL;
-
-	pci_try_num = max_depth + 1;
-	printk(KERN_DEBUG "PCI: max bus depth: %d pci_try_num: %d\n",
-		 max_depth, pci_try_num);
-
-again:
 	/* Depth first, calculate sizes and alignments of all
 	   subordinate buses. */
 	list_for_each_entry(bus, &pci_root_buses, node) {
@@ -904,65 +850,9 @@
 	}
 	/* Depth last, allocate resources and update the hardware. */
 	list_for_each_entry(bus, &pci_root_buses, node) {
-		__pci_bus_assign_resources(bus, &head);
-	}
-	tried_times++;
-
-	/* any device complain? */
-	if (!head.next)
-		goto enable_and_dump;
-	failed_type = 0;
-	for (list = head.next; list;) {
-		failed_type |= list->flags;
-		list = list->next;
-	}
-	/*
-	 * io port are tight, don't try extra
-	 * or if reach the limit, don't want to try more
-	 */
-	failed_type &= type_mask;
-	if ((failed_type == IORESOURCE_IO) || (tried_times >= pci_try_num)) {
-		free_failed_list(&head);
-		goto enable_and_dump;
-	}
-
-	printk(KERN_DEBUG "PCI: No. %d try to assign unassigned res\n",
-			 tried_times + 1);
-
-	/* third times and later will not check if it is leaf */
-	if ((tried_times + 1) > 2)
-		rel_type = whole_subtree;
-
-	/*
-	 * Try to release leaf bridge's resources that doesn't fit resource of
-	 * child device under that bridge
-	 */
-	for (list = head.next; list;) {
-		bus = list->dev->bus;
-		pci_bus_release_bridge_resources(bus, list->flags & type_mask,
-						  rel_type);
-		list = list->next;
-	}
-	/* restore size and flags */
-	for (list = head.next; list;) {
-		struct resource *res = list->res;
-
-		res->start = list->start;
-		res->end = list->end;
-		res->flags = list->flags;
-		if (list->dev->subordinate)
-			res->flags = 0;
-
-		list = list->next;
-	}
-	free_failed_list(&head);
-
-	goto again;
-
-enable_and_dump:
-	/* Depth last, update the hardware. */
-	list_for_each_entry(bus, &pci_root_buses, node)
+		pci_bus_assign_resources(bus);
 		pci_enable_bridges(bus);
+	}
 
 	/* dump the resource on buses */
 	list_for_each_entry(bus, &pci_root_buses, node) {

drivers/pcmcia/cs.c

diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c
index 75ed866..c338375 100644
--- a/drivers/pcmcia/cs.c
+++ b/drivers/pcmcia/cs.c
@@ -671,20 +671,22 @@
 				socket_remove(skt);
 			if (sysfs_events & PCMCIA_UEVENT_INSERT)
 				socket_insert(skt);
-			if ((sysfs_events & PCMCIA_UEVENT_RESUME) &&
-				!(skt->state & SOCKET_CARDBUS)) {
-				ret = socket_resume(skt);
-				if (!ret && skt->callback)
-					skt->callback->resume(skt);
-			}
 			if ((sysfs_events & PCMCIA_UEVENT_SUSPEND) &&
 				!(skt->state & SOCKET_CARDBUS)) {
 				if (skt->callback)
 					ret = skt->callback->suspend(skt);
 				else
 					ret = 0;
-				if (!ret)
+				if (!ret) {
 					socket_suspend(skt);
+					msleep(100);
+				}
+			}
+			if ((sysfs_events & PCMCIA_UEVENT_RESUME) &&
+				!(skt->state & SOCKET_CARDBUS)) {
+				ret = socket_resume(skt);
+				if (!ret && skt->callback)
+					skt->callback->resume(skt);
 			}
 			if ((sysfs_events & PCMCIA_UEVENT_REQUERY) &&
 				!(skt->state & SOCKET_CARDBUS)) {

drivers/pcmcia/db1xxx_ss.c

diff --git a/drivers/pcmcia/db1xxx_ss.c b/drivers/pcmcia/db1xxx_ss.c
index 2d48196..0f4cc3f 100644
--- a/drivers/pcmcia/db1xxx_ss.c
+++ b/drivers/pcmcia/db1xxx_ss.c
@@ -146,7 +146,6 @@
 static int db1x_pcmcia_setup_irqs(struct db1x_pcmcia_sock *sock)
 {
 	int ret;
-	unsigned long flags;
 
 	if (sock->stschg_irq != -1) {
 		ret = request_irq(sock->stschg_irq, db1000_pcmcia_stschgirq,
@@ -162,30 +161,23 @@
 	 * active one disabled.
 	 */
 	if (sock->board_type == BOARD_TYPE_DB1200) {
-		local_irq_save(flags);
-
 		ret = request_irq(sock->insert_irq, db1200_pcmcia_cdirq,
 				  IRQF_DISABLED, "pcmcia_insert", sock);
-		if (ret) {
-			local_irq_restore(flags);
+		if (ret)
 			goto out1;
-		}
 
 		ret = request_irq(sock->eject_irq, db1200_pcmcia_cdirq,
 				  IRQF_DISABLED, "pcmcia_eject", sock);
 		if (ret) {
 			free_irq(sock->insert_irq, sock);
-			local_irq_restore(flags);
 			goto out1;
 		}
 
-		/* disable the currently active one */
+		/* enable the currently silent one */
 		if (db1200_card_inserted(sock))
-			disable_irq_nosync(sock->insert_irq);
+			enable_irq(sock->eject_irq);
 		else
-			disable_irq_nosync(sock->eject_irq);
-
-		local_irq_restore(flags);
+			enable_irq(sock->insert_irq);
 	} else {
 		/* all other (older) Db1x00 boards use a GPIO to show
 		 * card detection status:  use both-edge triggers.

drivers/pcmcia/ds.c

diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c
index 508f94a..041eee4 100644
--- a/drivers/pcmcia/ds.c
+++ b/drivers/pcmcia/ds.c
@@ -1283,6 +1283,7 @@
 			destroy_cis_cache(skt);
 			kfree(skt->fake_cis);
 			skt->fake_cis = NULL;
+			s->functions = 0;
 			mutex_unlock(&s->ops_mutex);
 			/* now, add the new card */
 			ds_event(skt, CS_EVENT_CARD_INSERTION,

drivers/pcmcia/pcmcia_ioctl.c

diff --git a/drivers/pcmcia/pcmcia_ioctl.c b/drivers/pcmcia/pcmcia_ioctl.c
index 104e73d..7631faa 100644
--- a/drivers/pcmcia/pcmcia_ioctl.c
+++ b/drivers/pcmcia/pcmcia_ioctl.c
@@ -711,7 +711,7 @@
 	    warning_printed = 1;
     }
 
-    if (s->pcmcia_state.present)
+    if (atomic_read(&s->present))
 	queue_event(user, CS_EVENT_CARD_INSERTION);
 out:
     unlock_kernel();
@@ -770,9 +770,6 @@
 	return -EIO;
 
     s = user->socket;
-    if (s->pcmcia_state.dead)
-	return -EIO;
-
     ret = wait_event_interruptible(s->queue, !queue_empty(user));
     if (ret == 0)
 	ret = put_user(get_queued_event(user), (int __user *)buf) ? -EFAULT : 4;
@@ -838,8 +835,6 @@
 	return -EIO;
 
     s = user->socket;
-    if (s->pcmcia_state.dead)
-	return -EIO;
 
     size = (cmd & IOCSIZE_MASK) >> IOCSIZE_SHIFT;
     if (size > sizeof(ds_ioctl_arg_t))

drivers/pnp/pnpacpi/rsparser.c

diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 35bb44a..100e4d9 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -274,26 +274,6 @@
 	pnp_add_bus_resource(dev, start, end);
 }
 
-static u64 addr_space_length(struct pnp_dev *dev, u64 min, u64 max, u64 len)
-{
-	u64 max_len;
-
-	max_len = max - min + 1;
-	if (len <= max_len)
-		return len;
-
-	/*
-	 * Per 6.4.3.5, _LEN cannot exceed _MAX - _MIN + 1, but some BIOSes
-	 * don't do this correctly, e.g.,
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=15480
-	 */
-	dev_info(&dev->dev,
-	         "resource length %#llx doesn't fit in %#llx-%#llx, trimming\n",
-		 (unsigned long long) len, (unsigned long long) min,
-		 (unsigned long long) max);
-	return max_len;
-}
-
 static void pnpacpi_parse_allocated_address_space(struct pnp_dev *dev,
 						  struct acpi_resource *res)
 {
@@ -309,7 +289,8 @@
 		return;
 	}
 
-	len = addr_space_length(dev, p->minimum, p->maximum, p->address_length);
+	/* Windows apparently computes length rather than using _LEN */
+	len = p->maximum - p->minimum + 1;
 	window = (p->producer_consumer == ACPI_PRODUCER) ? 1 : 0;
 
 	if (p->resource_type == ACPI_MEMORY_RANGE)
@@ -330,7 +311,8 @@
 	int window;
 	u64 len;
 
-	len = addr_space_length(dev, p->minimum, p->maximum, p->address_length);
+	/* Windows apparently computes length rather than using _LEN */
+	len = p->maximum - p->minimum + 1;
 	window = (p->producer_consumer == ACPI_PRODUCER) ? 1 : 0;
 
 	if (p->resource_type == ACPI_MEMORY_RANGE)

drivers/pnp/resource.c

diff --git a/drivers/pnp/resource.c b/drivers/pnp/resource.c
index 2e54e6a..e3446ab 100644
--- a/drivers/pnp/resource.c
+++ b/drivers/pnp/resource.c
@@ -211,6 +211,8 @@
 			if (tres->flags & IORESOURCE_IO) {
 				if (cannot_compare(tres->flags))
 					continue;
+				if (tres->flags & IORESOURCE_WINDOW)
+					continue;
 				tport = &tres->start;
 				tend = &tres->end;
 				if (ranged_conflict(port, end, tport, tend))
@@ -271,6 +273,8 @@
 			if (tres->flags & IORESOURCE_MEM) {
 				if (cannot_compare(tres->flags))
 					continue;
+				if (tres->flags & IORESOURCE_WINDOW)
+					continue;
 				taddr = &tres->start;
 				tend = &tres->end;
 				if (ranged_conflict(addr, end, taddr, tend))

drivers/s390/block/dasd.c

diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index acf222f..fa2339c 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -37,6 +37,9 @@
  */
 #define DASD_CHANQ_MAX_SIZE 4
 
+#define DASD_SLEEPON_START_TAG	(void *) 1
+#define DASD_SLEEPON_END_TAG	(void *) 2
+
 /*
  * SECTION: exported variables of dasd.c
  */
@@ -1472,7 +1475,10 @@
  */
 static void dasd_wakeup_cb(struct dasd_ccw_req *cqr, void *data)
 {
-	wake_up((wait_queue_head_t *) data);
+	spin_lock_irq(get_ccwdev_lock(cqr->startdev->cdev));
+	cqr->callback_data = DASD_SLEEPON_END_TAG;
+	spin_unlock_irq(get_ccwdev_lock(cqr->startdev->cdev));
+	wake_up(&generic_waitq);
 }
 
 static inline int _wait_for_wakeup(struct dasd_ccw_req *cqr)
@@ -1482,10 +1488,7 @@
 
 	device = cqr->startdev;
 	spin_lock_irq(get_ccwdev_lock(device->cdev));
-	rc = ((cqr->status == DASD_CQR_DONE ||
-	       cqr->status == DASD_CQR_NEED_ERP ||
-	       cqr->status == DASD_CQR_TERMINATED) &&
-	      list_empty(&cqr->devlist));
+	rc = (cqr->callback_data == DASD_SLEEPON_END_TAG);
 	spin_unlock_irq(get_ccwdev_lock(device->cdev));
 	return rc;
 }
@@ -1573,7 +1576,7 @@
 			wait_event(generic_waitq, !(device->stopped));
 
 		cqr->callback = dasd_wakeup_cb;
-		cqr->callback_data = (void *) &generic_waitq;
+		cqr->callback_data = DASD_SLEEPON_START_TAG;
 		dasd_add_request_tail(cqr);
 		if (interruptible) {
 			rc = wait_event_interruptible(
@@ -1652,7 +1655,7 @@
 	}
 
 	cqr->callback = dasd_wakeup_cb;
-	cqr->callback_data = (void *) &generic_waitq;
+	cqr->callback_data = DASD_SLEEPON_START_TAG;
 	cqr->status = DASD_CQR_QUEUED;
 	list_add(&cqr->devlist, &device->ccw_queue);
 

drivers/scsi/advansys.c

diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index 9201afe..7f87979 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -4724,6 +4724,10 @@
 	BUG_ON((unsigned long)asc_dvc->overrun_buf & 7);
 	asc_dvc->overrun_dma = dma_map_single(board->dev, asc_dvc->overrun_buf,
 					ASC_OVERRUN_BSIZE, DMA_FROM_DEVICE);
+	if (dma_mapping_error(board->dev, asc_dvc->overrun_dma)) {
+		warn_code = -ENOMEM;
+		goto err_dma_map;
+	}
 	phy_addr = cpu_to_le32(asc_dvc->overrun_dma);
 	AscMemDWordCopyPtrToLram(iop_base, ASCV_OVERRUN_PADDR_D,
 				 (uchar *)&phy_addr, 1);
@@ -4739,14 +4743,23 @@
 	AscSetPCAddr(iop_base, ASC_MCODE_START_ADDR);
 	if (AscGetPCAddr(iop_base) != ASC_MCODE_START_ADDR) {
 		asc_dvc->err_code |= ASC_IERR_SET_PC_ADDR;
-		return warn_code;
+		warn_code = UW_ERR;
+		goto err_mcode_start;
 	}
 	if (AscStartChip(iop_base) != 1) {
 		asc_dvc->err_code |= ASC_IERR_START_STOP_CHIP;
-		return warn_code;
+		warn_code = UW_ERR;
+		goto err_mcode_start;
 	}
 
 	return warn_code;
+
+err_mcode_start:
+	dma_unmap_single(board->dev, asc_dvc->overrun_dma,
+			 ASC_OVERRUN_BSIZE, DMA_FROM_DEVICE);
+err_dma_map:
+	asc_dvc->overrun_dma = 0;
+	return warn_code;
 }
 
 static ushort AscInitAsc1000Driver(ASC_DVC_VAR *asc_dvc)
@@ -4802,6 +4815,8 @@
 	}
 	release_firmware(fw);
 	warn_code |= AscInitMicroCodeVar(asc_dvc);
+	if (!asc_dvc->overrun_dma)
+		return warn_code;
 	asc_dvc->init_state |= ASC_INIT_STATE_END_LOAD_MC;
 	AscEnableInterrupt(iop_base);
 	return warn_code;
@@ -7978,9 +7993,10 @@
 		status = AscInitAsc1000Driver(asc_dvc);
 
 		/* Refer to ASC_IERR_* definitions for meaning of 'err_code'. */
-		if (asc_dvc->err_code) {
+		if (asc_dvc->err_code || !asc_dvc->overrun_dma) {
 			scmd_printk(KERN_INFO, scp, "SCSI bus reset error: "
-				    "0x%x\n", asc_dvc->err_code);
+				    "0x%x, status: 0x%x\n", asc_dvc->err_code,
+				    status);
 			ret = FAILED;
 		} else if (status) {
 			scmd_printk(KERN_INFO, scp, "SCSI bus reset warning: "
@@ -12311,7 +12327,7 @@
 		asc_dvc_varp->overrun_buf = kzalloc(ASC_OVERRUN_BSIZE, GFP_KERNEL);
 		if (!asc_dvc_varp->overrun_buf) {
 			ret = -ENOMEM;
-			goto err_free_wide_mem;
+			goto err_free_irq;
 		}
 		warn_code = AscInitAsc1000Driver(asc_dvc_varp);
 
@@ -12320,30 +12336,36 @@
 					"warn 0x%x, error 0x%x\n",
 					asc_dvc_varp->init_state, warn_code,
 					asc_dvc_varp->err_code);
-			if (asc_dvc_varp->err_code) {
+			if (!asc_dvc_varp->overrun_dma) {
 				ret = -ENODEV;
-				kfree(asc_dvc_varp->overrun_buf);
+				goto err_free_mem;
 			}
 		}
 	} else {
-		if (advansys_wide_init_chip(shost))
+		if (advansys_wide_init_chip(shost)) {
 			ret = -ENODEV;
+			goto err_free_mem;
+		}
 	}
 
-	if (ret)
-		goto err_free_wide_mem;
-
 	ASC_DBG_PRT_SCSI_HOST(2, shost);
 
 	ret = scsi_add_host(shost, boardp->dev);
 	if (ret)
-		goto err_free_wide_mem;
+		goto err_free_mem;
 
 	scsi_scan_host(shost);
 	return 0;
 
- err_free_wide_mem:
-	advansys_wide_free_mem(boardp);
+ err_free_mem:
+	if (ASC_NARROW_BOARD(boardp)) {
+		if (asc_dvc_varp->overrun_dma)
+			dma_unmap_single(boardp->dev, asc_dvc_varp->overrun_dma,
+					 ASC_OVERRUN_BSIZE, DMA_FROM_DEVICE);
+		kfree(asc_dvc_varp->overrun_buf);
+	} else
+		advansys_wide_free_mem(boardp);
+ err_free_irq:
 	free_irq(boardp->irq, shost);
  err_free_dma:
 #ifdef CONFIG_ISA

drivers/scsi/libiscsi.c

diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 6d5ae44..633e090 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -471,12 +471,12 @@
 
 	WARN_ON(hdrlength >= 256);
 	hdr->hlength = hdrlength & 0xFF;
+	hdr->cmdsn = task->cmdsn = cpu_to_be32(session->cmdsn);
 
 	if (session->tt->init_task && session->tt->init_task(task))
 		return -EIO;
 
 	task->state = ISCSI_TASK_RUNNING;
-	hdr->cmdsn = task->cmdsn = cpu_to_be32(session->cmdsn);
 	session->cmdsn++;
 
 	conn->scsicmd_pdus_cnt++;

drivers/scsi/libsas/sas_ata.c

diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index b00efd1..88f7446 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -395,11 +395,15 @@
 void sas_ata_task_abort(struct sas_task *task)
 {
 	struct ata_queued_cmd *qc = task->uldd_task;
+	struct request_queue *q = qc->scsicmd->device->request_queue;
 	struct completion *waiting;
+	unsigned long flags;
 
 	/* Bounce SCSI-initiated commands to the SCSI EH */
 	if (qc->scsicmd) {
+		spin_lock_irqsave(q->queue_lock, flags);
 		blk_abort_request(qc->scsicmd->request);
+		spin_unlock_irqrestore(q->queue_lock, flags);
 		scsi_schedule_eh(qc->scsicmd->device->host);
 		return;
 	}

drivers/scsi/libsas/sas_scsi_host.c

diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 2660e1b..8228350 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -1030,6 +1030,8 @@
 void sas_task_abort(struct sas_task *task)
 {
 	struct scsi_cmnd *sc = task->uldd_task;
+	struct request_queue *q = sc->device->request_queue;
+	unsigned long flags;
 
 	/* Escape for libsas internal commands */
 	if (!sc) {
@@ -1044,7 +1046,9 @@
 		return;
 	}
 
+	spin_lock_irqsave(q->queue_lock, flags);
 	blk_abort_request(sc->request);
+	spin_unlock_irqrestore(q->queue_lock, flags);
 	scsi_schedule_eh(sc->device->host);
 }
 

drivers/scsi/scsi_debug.c

diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 3e10c30..3a5bfd1 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -957,7 +957,8 @@
 static sector_t get_sdebug_capacity(void)
 {
 	if (scsi_debug_virtual_gb > 0)
-		return 2048 * 1024 * (sector_t)scsi_debug_virtual_gb;
+		return (sector_t)scsi_debug_virtual_gb *
+			(1073741824 / scsi_debug_sector_size);
 	else
 		return sdebug_store_sectors;
 }

drivers/scsi/scsi_error.c

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index d45c69c..7ad53fa 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -302,7 +302,20 @@
 		if (scmd->device->allow_restart &&
 		    (sshdr.asc == 0x04) && (sshdr.ascq == 0x02))
 			return FAILED;
-		return SUCCESS;
+
+		if (blk_barrier_rq(scmd->request))
+			/*
+			 * barrier requests should always retry on UA
+			 * otherwise block will get a spurious error
+			 */
+			return NEEDS_RETRY;
+		else
+			/*
+			 * for normal (non barrier) commands, pass the
+			 * UA upwards for a determination in the
+			 * completion functions
+			 */
+			return SUCCESS;
 
 		/* these three are not supported */
 	case COPY_ABORTED:

drivers/scsi/sd.c

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 8b827f3..de6c603 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1040,6 +1040,7 @@
 {
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->timeout = SD_TIMEOUT;
+	rq->retries = SD_MAX_RETRIES;
 	rq->cmd[0] = SYNCHRONIZE_CACHE;
 	rq->cmd_len = 10;
 }

drivers/scsi/zorro7xx.c

diff --git a/drivers/scsi/zorro7xx.c b/drivers/scsi/zorro7xx.c
index 105449c..e17764d 100644
--- a/drivers/scsi/zorro7xx.c
+++ b/drivers/scsi/zorro7xx.c
@@ -69,6 +69,7 @@
 	},
 	{ 0 }
 };
+MODULE_DEVICE_TABLE(zorro, zorro7xx_zorro_tbl);
 
 static int __devinit zorro7xx_init_one(struct zorro_dev *z,
 				       const struct zorro_device_id *ent)

drivers/serial/8250_pnp.c

diff --git a/drivers/serial/8250_pnp.c b/drivers/serial/8250_pnp.c
index 24485cc..4822cb5 100644
--- a/drivers/serial/8250_pnp.c
+++ b/drivers/serial/8250_pnp.c
@@ -348,6 +348,8 @@
 	{	"FUJ02E6",		0	},
 	/* Fujitsu Wacom 2FGT Tablet PC device */
 	{	"FUJ02E7",		0	},
+	/* Fujitsu Wacom 1FGT Tablet PC device */
+	{	"FUJ02E9",		0	},
 	/*
 	 * LG C1 EXPRESS DUAL (C1-PB11A3) touch screen (actually a FUJ02E6 in
 	 * disguise)

drivers/serial/imx.c

diff --git a/drivers/serial/imx.c b/drivers/serial/imx.c
index 4315b23..eacb588 100644
--- a/drivers/serial/imx.c
+++ b/drivers/serial/imx.c
@@ -120,7 +120,8 @@
 #define  MX2_UCR3_RXDMUXSEL	 (1<<2)  /* RXD Muxed Input Select, on mx2/mx3 */
 #define  UCR3_INVT  	 (1<<1)  /* Inverted Infrared transmission */
 #define  UCR3_BPEN  	 (1<<0)  /* Preset registers enable */
-#define  UCR4_CTSTL_32   (32<<10) /* CTS trigger level (32 chars) */
+#define  UCR4_CTSTL_SHF  10      /* CTS trigger level shift */
+#define  UCR4_CTSTL_MASK 0x3F    /* CTS trigger is 6 bits wide */
 #define  UCR4_INVR  	 (1<<9)  /* Inverted infrared reception */
 #define  UCR4_ENIRI 	 (1<<8)  /* Serial infrared interrupt enable */
 #define  UCR4_WKEN  	 (1<<7)  /* Wake interrupt enable */
@@ -591,6 +592,9 @@
 	return 0;
 }
 
+/* half the RX buffer size */
+#define CTSTL 16
+
 static int imx_startup(struct uart_port *port)
 {
 	struct imx_port *sport = (struct imx_port *)port;
@@ -607,6 +611,10 @@
 	if (USE_IRDA(sport))
 		temp |= UCR4_IRSC;
 
+	/* set the trigger level for CTS */
+	temp &= ~(UCR4_CTSTL_MASK<<  UCR4_CTSTL_SHF);
+	temp |= CTSTL<<  UCR4_CTSTL_SHF;
+
 	writel(temp & ~UCR4_DREN, sport->port.membase + UCR4);
 
 	if (USE_IRDA(sport)) {

drivers/serial/mpc52xx_uart.c

diff --git a/drivers/serial/mpc52xx_uart.c b/drivers/serial/mpc52xx_uart.c
index 3119fdd..02469c3 100644
--- a/drivers/serial/mpc52xx_uart.c
+++ b/drivers/serial/mpc52xx_uart.c
@@ -29,39 +29,6 @@
  * kind, whether express or implied.
  */
 
-/* Platform device Usage :
- *
- * Since PSCs can have multiple function, the correct driver for each one
- * is selected by calling mpc52xx_match_psc_function(...). The function
- * handled by this driver is "uart".
- *
- * The driver init all necessary registers to place the PSC in uart mode without
- * DCD. However, the pin multiplexing aren't changed and should be set either
- * by the bootloader or in the platform init code.
- *
- * The idx field must be equal to the PSC index (e.g. 0 for PSC1, 1 for PSC2,
- * and so on). So the PSC1 is mapped to /dev/ttyPSC0, PSC2 to /dev/ttyPSC1 and
- * so on. But be warned, it's an ABSOLUTE REQUIREMENT ! This is needed mainly
- * fpr the console code : without this 1:1 mapping, at early boot time, when we
- * are parsing the kernel args console=ttyPSC?, we wouldn't know which PSC it
- * will be mapped to.
- */
-
-/* OF Platform device Usage :
- *
- * This driver is only used for PSCs configured in uart mode.  The device
- * tree will have a node for each PSC with "mpc52xx-psc-uart" in the compatible
- * list.
- *
- * By default, PSC devices are enumerated in the order they are found.  However
- * a particular PSC number can be forces by adding 'device_no = <port#>'
- * to the device node.
- *
- * The driver init all necessary registers to place the PSC in uart mode without
- * DCD. However, the pin multiplexing aren't changed and should be set either
- * by the bootloader or in the platform init code.
- */
-
 #undef DEBUG
 
 #include <linux/device.h>
@@ -1500,7 +1467,7 @@
 	/*
 	 * Map the PSC FIFO Controller and init if on MPC512x.
 	 */
-	if (psc_ops->fifoc_init) {
+	if (psc_ops && psc_ops->fifoc_init) {
 		ret = psc_ops->fifoc_init();
 		if (ret)
 			return ret;

drivers/serial/pmac_zilog.c

diff --git a/drivers/serial/pmac_zilog.c b/drivers/serial/pmac_zilog.c
index 4eaa043..700e108 100644
--- a/drivers/serial/pmac_zilog.c
+++ b/drivers/serial/pmac_zilog.c
@@ -752,8 +752,10 @@
 		uap->curregs[R5] = new_reg;
 
 		/* NOTE: Not subject to 'transmitter active' rule. */
-		if (ZS_IS_ASLEEP(uap))
+		if (ZS_IS_ASLEEP(uap)) {
+			spin_unlock_irqrestore(&port->lock, flags);
 			return;
+		}
 		write_zsreg(uap, R5, uap->curregs[R5]);
 	}
 

drivers/spi/omap2_mcspi.c

diff --git a/drivers/spi/omap2_mcspi.c b/drivers/spi/omap2_mcspi.c
index d8356af..e0de0d0 100644
--- a/drivers/spi/omap2_mcspi.c
+++ b/drivers/spi/omap2_mcspi.c
@@ -204,6 +204,7 @@
 
 	cs->chconf0 = val;
 	mcspi_write_cs_reg(spi, OMAP2_MCSPI_CHCONF0, val);
+	mcspi_read_cs_reg(spi, OMAP2_MCSPI_CHCONF0);
 }
 
 static void omap2_mcspi_set_dma_req(const struct spi_device *spi,
@@ -532,7 +533,7 @@
 					goto out;
 				}
 #ifdef VERBOSE
-				dev_dbg(&spi->dev, "write-%d %04x\n",
+				dev_dbg(&spi->dev, "write-%d %08x\n",
 						word_len, *tx);
 #endif
 				__raw_writel(*tx++, tx_reg);
@@ -550,7 +551,7 @@
 					mcspi_write_chconf0(spi, l);
 				*rx++ = __raw_readl(rx_reg);
 #ifdef VERBOSE
-				dev_dbg(&spi->dev, "read-%d %04x\n",
+				dev_dbg(&spi->dev, "read-%d %08x\n",
 						word_len, *(rx - 1));
 #endif
 			}

drivers/spi/spi.c

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 9ffb0fd..b3a1f92 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -41,7 +41,7 @@
 		spi->master->cleanup(spi);
 
 	spi_master_put(spi->master);
-	kfree(dev);
+	kfree(spi);
 }
 
 static ssize_t
@@ -257,6 +257,7 @@
 {
 	static DEFINE_MUTEX(spi_add_lock);
 	struct device *dev = spi->master->dev.parent;
+	struct device *d;
 	int status;
 
 	/* Chipselects are numbered 0..max; validate. */
@@ -278,10 +279,11 @@
 	 */
 	mutex_lock(&spi_add_lock);
 
-	if (bus_find_device_by_name(&spi_bus_type, NULL, dev_name(&spi->dev))
-			!= NULL) {
+	d = bus_find_device_by_name(&spi_bus_type, NULL, dev_name(&spi->dev));
+	if (d != NULL) {
 		dev_err(dev, "chipselect %d already in use\n",
 				spi->chip_select);
+		put_device(d);
 		status = -EBUSY;
 		goto done;
 	}

drivers/staging/dt3155/dt3155_drv.c

diff --git a/drivers/staging/dt3155/dt3155_drv.c b/drivers/staging/dt3155/dt3155_drv.c
index e2c44ec..7ac2c6d 100644
--- a/drivers/staging/dt3155/dt3155_drv.c
+++ b/drivers/staging/dt3155/dt3155_drv.c
@@ -464,9 +464,9 @@
   /* 50/60 Hz should be set before this point but let's make sure it is */
   /* right anyway */
 
-  ReadI2C(dt3155_lbase[ minor ], CONFIG, &i2c_csr2.reg);
+  ReadI2C(dt3155_lbase[ minor ], CSR2, &i2c_csr2.reg);
   i2c_csr2.fld.HZ50 = FORMAT50HZ;
-  WriteI2C(dt3155_lbase[ minor ], CONFIG, i2c_config.reg);
+  WriteI2C(dt3155_lbase[ minor ], CSR2, i2c_csr2.reg);
 
   /* enable busmaster chip, clear flags */
 

drivers/staging/hv/Hv.c

diff --git a/drivers/staging/hv/Hv.c b/drivers/staging/hv/Hv.c
index 5d53889..3a1112d 100644
--- a/drivers/staging/hv/Hv.c
+++ b/drivers/staging/hv/Hv.c
@@ -306,9 +306,9 @@
 	DPRINT_ENTER(VMBUS);
 
 	if (gHvContext.SignalEventBuffer) {
+		kfree(gHvContext.SignalEventBuffer);
 		gHvContext.SignalEventBuffer = NULL;
 		gHvContext.SignalEventParam = NULL;
-		kfree(gHvContext.SignalEventBuffer);
 	}
 
 	if (gHvContext.HypercallPage) {

drivers/staging/hv/RndisFilter.c

diff --git a/drivers/staging/hv/RndisFilter.c b/drivers/staging/hv/RndisFilter.c
index cd2930d..6704f64 100644
--- a/drivers/staging/hv/RndisFilter.c
+++ b/drivers/staging/hv/RndisFilter.c
@@ -751,6 +751,7 @@
 
 	ret = RndisFilterSetPacketFilter(Device,
 					 NDIS_PACKET_TYPE_BROADCAST |
+					 NDIS_PACKET_TYPE_ALL_MULTICAST |
 					 NDIS_PACKET_TYPE_DIRECTED);
 	if (ret == 0)
 		Device->State = RNDIS_DEV_DATAINITIALIZED;

drivers/staging/hv/netvsc_drv.c

diff --git a/drivers/staging/hv/netvsc_drv.c b/drivers/staging/hv/netvsc_drv.c
index 2ccb6b9..ab27d9a 100644
--- a/drivers/staging/hv/netvsc_drv.c
+++ b/drivers/staging/hv/netvsc_drv.c
@@ -403,8 +403,7 @@
 	if (!net_drv_obj->Base.OnDeviceAdd)
 		return -1;
 
-	net = alloc_netdev(sizeof(struct net_device_context), "seth%d",
-			   ether_setup);
+	net = alloc_etherdev(sizeof(struct net_device_context));
 	if (!net)
 		return -1;
 

drivers/staging/iio/accel/lis3l02dq_core.c

diff --git a/drivers/staging/iio/accel/lis3l02dq_core.c b/drivers/staging/iio/accel/lis3l02dq_core.c
index ea76902..82e4358 100644
--- a/drivers/staging/iio/accel/lis3l02dq_core.c
+++ b/drivers/staging/iio/accel/lis3l02dq_core.c
@@ -618,7 +618,7 @@
 static void lis3l02dq_thresh_handler_bh_no_check(struct work_struct *work_s)
 {
 	struct iio_work_cont *wc
-		= container_of(work_s, struct iio_work_cont, ws_nocheck);
+		= container_of(work_s, struct iio_work_cont, ws);
 	struct lis3l02dq_state *st = wc->st;
 	u8 t;
 

drivers/staging/iio/accel/lis3l02dq_ring.c

diff --git a/drivers/staging/iio/accel/lis3l02dq_ring.c b/drivers/staging/iio/accel/lis3l02dq_ring.c
index 9371243..a4d97ea 100644
--- a/drivers/staging/iio/accel/lis3l02dq_ring.c
+++ b/drivers/staging/iio/accel/lis3l02dq_ring.c
@@ -493,6 +493,9 @@
 	struct lis3l02dq_state *state = indio_dev->dev_data;
 
 	state->trig = iio_allocate_trigger();
+	if (!state->trig)
+		return -ENOMEM;
+
 	state->trig->name = kmalloc(IIO_TRIGGER_NAME_LENGTH, GFP_KERNEL);
 	if (!state->trig->name) {
 		ret = -ENOMEM;

drivers/staging/iio/adc/max1363_core.c

diff --git a/drivers/staging/iio/adc/max1363_core.c b/drivers/staging/iio/adc/max1363_core.c
index 790d1cc..773f1d1 100644
--- a/drivers/staging/iio/adc/max1363_core.c
+++ b/drivers/staging/iio/adc/max1363_core.c
@@ -557,6 +557,7 @@
 	if (!IS_ERR(st->reg))
 		regulator_put(st->reg);
 error_free_st:
+	i2c_set_clientdata(client, NULL);
 	kfree(st);
 
 error_ret:
@@ -574,6 +575,7 @@
 		regulator_disable(st->reg);
 		regulator_put(st->reg);
 	}
+	i2c_set_clientdata(client, NULL);
 	kfree(st);
 
 	return 0;

drivers/staging/iio/industrialio-core.c

diff --git a/drivers/staging/iio/industrialio-core.c b/drivers/staging/iio/industrialio-core.c
index 37f58f6..1d77082 100644
--- a/drivers/staging/iio/industrialio-core.c
+++ b/drivers/staging/iio/industrialio-core.c
@@ -537,6 +537,7 @@
 	sysfs_remove_group(&dev_info->dev.kobj, dev_info->attrs);
 }
 
+/* Return a negative errno on failure */
 int iio_get_new_idr_val(struct idr *this_idr)
 {
 	int ret;
@@ -660,7 +661,7 @@
 	for (i = 0; i < dev_info->num_interrupt_lines; i++) {
 		dev_info->event_interfaces[i].owner = dev_info->driver_module;
 		ret = iio_get_new_idr_val(&iio_event_idr);
-		if (ret)
+		if (ret < 0)
 			goto error_free_setup_ev_ints;
 		else
 			dev_info->event_interfaces[i].id = ret;

drivers/staging/iio/light/tsl2563.c

diff --git a/drivers/staging/iio/light/tsl2563.c b/drivers/staging/iio/light/tsl2563.c
index 1ba4aa3..8770a00 100644
--- a/drivers/staging/iio/light/tsl2563.c
+++ b/drivers/staging/iio/light/tsl2563.c
@@ -682,6 +682,7 @@
 fail2:
 	iio_device_unregister(chip->indio_dev);
 fail1:
+	i2c_set_clientdata(client, NULL);
 	kfree(chip);
 	return err;
 }
@@ -692,6 +693,7 @@
 
 	iio_device_unregister(chip->indio_dev);
 
+	i2c_set_clientdata(client, NULL);
 	kfree(chip);
 	return 0;
 }

drivers/staging/iio/ring_sw.c

diff --git a/drivers/staging/iio/ring_sw.c b/drivers/staging/iio/ring_sw.c
index b104c3d..cf22c09 100644
--- a/drivers/staging/iio/ring_sw.c
+++ b/drivers/staging/iio/ring_sw.c
@@ -293,7 +293,7 @@
 		return -EAGAIN;
 	memcpy(data, last_written_p_copy, ring->buf.bpd);
 
-	if (unlikely(ring->last_written_p >= last_written_p_copy))
+	if (unlikely(ring->last_written_p != last_written_p_copy))
 		goto again;
 
 	iio_unmark_sw_rb_in_use(&ring->buf);

drivers/staging/octeon/cvmx-helper-board.c

diff --git a/drivers/staging/octeon/cvmx-helper-board.c b/drivers/staging/octeon/cvmx-helper-board.c
index 3085e38..00a555b 100644
--- a/drivers/staging/octeon/cvmx-helper-board.c
+++ b/drivers/staging/octeon/cvmx-helper-board.c
@@ -153,6 +153,14 @@
 		 * through switch.
 		 */
 		return -1;
+
+	case CVMX_BOARD_TYPE_CUST_WSX16:
+		if (ipd_port >= 0 && ipd_port <= 3)
+			return ipd_port;
+		else if (ipd_port >= 16 && ipd_port <= 19)
+			return ipd_port - 16 + 4;
+		else
+			return -1;
 	}
 
 	/* Some unknown board. Somebody forgot to update this function... */

drivers/staging/rt2860/usb_main_dev.c

diff --git a/drivers/staging/rt2860/usb_main_dev.c b/drivers/staging/rt2860/usb_main_dev.c
index 1873a79..740db0c 100644
--- a/drivers/staging/rt2860/usb_main_dev.c
+++ b/drivers/staging/rt2860/usb_main_dev.c
@@ -63,6 +63,7 @@
 	{USB_DEVICE(0x07D1, 0x3C11)},	/* D-Link */
 	{USB_DEVICE(0x14B2, 0x3C07)},	/* AL */
 	{USB_DEVICE(0x050D, 0x8053)},	/* Belkin */
+	{USB_DEVICE(0x050D, 0x825B)},	/* Belkin */
 	{USB_DEVICE(0x14B2, 0x3C23)},	/* Airlink */
 	{USB_DEVICE(0x14B2, 0x3C27)},	/* Airlink */
 	{USB_DEVICE(0x07AA, 0x002F)},	/* Corega */

drivers/staging/rtl8192su/r8192U_core.c

diff --git a/drivers/staging/rtl8192su/r8192U_core.c b/drivers/staging/rtl8192su/r8192U_core.c
index e16256f..04d9b85 100644
--- a/drivers/staging/rtl8192su/r8192U_core.c
+++ b/drivers/staging/rtl8192su/r8192U_core.c
@@ -113,14 +113,17 @@
 
 static const struct usb_device_id rtl8192_usb_id_tbl[] = {
 	/* Realtek */
+	{USB_DEVICE(0x0bda, 0x8171)},
 	{USB_DEVICE(0x0bda, 0x8192)},
 	{USB_DEVICE(0x0bda, 0x8709)},
 	/* Corega */
 	{USB_DEVICE(0x07aa, 0x0043)},
 	/* Belkin */
 	{USB_DEVICE(0x050d, 0x805E)},
+	{USB_DEVICE(0x050d, 0x815F)}, /* Belkin F5D8053 v6 */
 	/* Sitecom */
 	{USB_DEVICE(0x0df6, 0x0031)},
+	{USB_DEVICE(0x0df6, 0x004b)},	/* WL-349 */
 	/* EnGenius */
 	{USB_DEVICE(0x1740, 0x9201)},
 	/* Dlink */

drivers/staging/usbip/usbip_event.c

diff --git a/drivers/staging/usbip/usbip_event.c b/drivers/staging/usbip/usbip_event.c
index 6da1021..a2566f1 100644
--- a/drivers/staging/usbip/usbip_event.c
+++ b/drivers/staging/usbip/usbip_event.c
@@ -117,6 +117,9 @@
 {
 	struct usbip_task *eh = &ud->eh;
 
+	if (eh->thread == current)
+		return; /* do not wait for myself */
+
 	wait_for_completion(&eh->thread_done);
 	usbip_dbg_eh("usbip_eh has finished\n");
 }

drivers/staging/vme/bridges/vme_tsi148.c

diff --git a/drivers/staging/vme/bridges/vme_tsi148.c b/drivers/staging/vme/bridges/vme_tsi148.c
index 68f2442..783051f 100644
--- a/drivers/staging/vme/bridges/vme_tsi148.c
+++ b/drivers/staging/vme/bridges/vme_tsi148.c
@@ -2455,9 +2455,10 @@
 	dev_info(&pdev->dev, "VME Write and flush and error check is %s\n",
 		err_chk ? "enabled" : "disabled");
 
-	if (tsi148_crcsr_init(tsi148_bridge, pdev))
+	if (tsi148_crcsr_init(tsi148_bridge, pdev)) {
 		dev_err(&pdev->dev, "CR/CSR configuration failed.\n");
 		goto err_crcsr;
+	}
 
 	retval = vme_register_bridge(tsi148_bridge);
 	if (retval != 0) {

drivers/usb/class/cdc-acm.c

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index be6331e..5e1a253 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1542,6 +1542,9 @@
 	{ USB_DEVICE(0x1bbb, 0x0003), /* Alcatel OT-I650 */
 	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
 	},
+	{ USB_DEVICE(0x1576, 0x03b1), /* Maretron USB100 */
+	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
+	},
 
 	/* Nokia S60 phones expose two ACM channels. The first is
 	 * a modem and is picked up by the standard AT-command

drivers/usb/core/Kconfig

diff --git a/drivers/usb/core/Kconfig b/drivers/usb/core/Kconfig
index 97a819c..7e594449 100644
--- a/drivers/usb/core/Kconfig
+++ b/drivers/usb/core/Kconfig
@@ -109,7 +109,7 @@
 config USB_OTG
 	bool
 	depends on USB && EXPERIMENTAL
-	select USB_SUSPEND
+	depends on USB_SUSPEND
 	default n
 
 

drivers/usb/core/generic.c

diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c
index bdf87a8..2c95153 100644
--- a/drivers/usb/core/generic.c
+++ b/drivers/usb/core/generic.c
@@ -120,7 +120,7 @@
 		 * than a vendor-specific driver. */
 		else if (udev->descriptor.bDeviceClass !=
 						USB_CLASS_VENDOR_SPEC &&
-				(!desc || desc->bInterfaceClass !=
+				(desc && desc->bInterfaceClass !=
 						USB_CLASS_VENDOR_SPEC)) {
 			best = c;
 			break;

drivers/usb/core/inode.c

diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c
index 97b40ce..111a01a 100644
--- a/drivers/usb/core/inode.c
+++ b/drivers/usb/core/inode.c
@@ -380,6 +380,7 @@
 	mutex_lock(&inode->i_mutex);
 	dentry_unhash(dentry);
 	if (usbfs_empty(dentry)) {
+		dont_mount(dentry);
 		drop_nlink(dentry->d_inode);
 		drop_nlink(dentry->d_inode);
 		dput(dentry);
@@ -515,13 +516,13 @@
 	*dentry = NULL;
 	mutex_lock(&parent->d_inode->i_mutex);
 	*dentry = lookup_one_len(name, parent, strlen(name));
-	if (!IS_ERR(dentry)) {
+	if (!IS_ERR(*dentry)) {
 		if ((mode & S_IFMT) == S_IFDIR)
 			error = usbfs_mkdir (parent->d_inode, *dentry, mode);
 		else 
 			error = usbfs_create (parent->d_inode, *dentry, mode);
 	} else
-		error = PTR_ERR(dentry);
+		error = PTR_ERR(*dentry);
 	mutex_unlock(&parent->d_inode->i_mutex);
 
 	return error;

drivers/usb/core/usb.c

diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index 1297e9b..0561430 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -718,7 +718,7 @@
 EXPORT_SYMBOL_GPL(__usb_get_extra_descriptor);
 
 /**
- * usb_buffer_alloc - allocate dma-consistent buffer for URB_NO_xxx_DMA_MAP
+ * usb_alloc_coherent - allocate dma-consistent buffer for URB_NO_xxx_DMA_MAP
  * @dev: device the buffer will be used with
  * @size: requested buffer size
  * @mem_flags: affect whether allocation may block
@@ -737,30 +737,30 @@
  * architectures where CPU caches are not DMA-coherent.  On systems without
  * bus-snooping caches, these buffers are uncached.
  *
- * When the buffer is no longer used, free it with usb_buffer_free().
+ * When the buffer is no longer used, free it with usb_free_coherent().
  */
-void *usb_buffer_alloc(struct usb_device *dev, size_t size, gfp_t mem_flags,
-		       dma_addr_t *dma)
+void *usb_alloc_coherent(struct usb_device *dev, size_t size, gfp_t mem_flags,
+			 dma_addr_t *dma)
 {
 	if (!dev || !dev->bus)
 		return NULL;
 	return hcd_buffer_alloc(dev->bus, size, mem_flags, dma);
 }
-EXPORT_SYMBOL_GPL(usb_buffer_alloc);
+EXPORT_SYMBOL_GPL(usb_alloc_coherent);
 
 /**
- * usb_buffer_free - free memory allocated with usb_buffer_alloc()
+ * usb_free_coherent - free memory allocated with usb_alloc_coherent()
  * @dev: device the buffer was used with
  * @size: requested buffer size
  * @addr: CPU address of buffer
  * @dma: DMA address of buffer
  *
  * This reclaims an I/O buffer, letting it be reused.  The memory must have
- * been allocated using usb_buffer_alloc(), and the parameters must match
+ * been allocated using usb_alloc_coherent(), and the parameters must match
  * those provided in that allocation request.
  */
-void usb_buffer_free(struct usb_device *dev, size_t size, void *addr,
-		     dma_addr_t dma)
+void usb_free_coherent(struct usb_device *dev, size_t size, void *addr,
+		       dma_addr_t dma)
 {
 	if (!dev || !dev->bus)
 		return;
@@ -768,7 +768,7 @@
 		return;
 	hcd_buffer_free(dev->bus, size, addr, dma);
 }
-EXPORT_SYMBOL_GPL(usb_buffer_free);
+EXPORT_SYMBOL_GPL(usb_free_coherent);
 
 /**
  * usb_buffer_map - create DMA mapping(s) for an urb

drivers/usb/gadget/s3c-hsotg.c

diff --git a/drivers/usb/gadget/s3c-hsotg.c b/drivers/usb/gadget/s3c-hsotg.c
index 124a8cc..1f73b48 100644
--- a/drivers/usb/gadget/s3c-hsotg.c
+++ b/drivers/usb/gadget/s3c-hsotg.c
@@ -2145,6 +2145,7 @@
 	u32 epctrl;
 	u32 mps;
 	int dir_in;
+	int ret = 0;
 
 	dev_dbg(hsotg->dev,
 		"%s: ep %s: a 0x%02x, attr 0x%02x, mps 0x%04x, intr %d\n",
@@ -2196,7 +2197,8 @@
 	switch (desc->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) {
 	case USB_ENDPOINT_XFER_ISOC:
 		dev_err(hsotg->dev, "no current ISOC support\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 
 	case USB_ENDPOINT_XFER_BULK:
 		epctrl |= S3C_DxEPCTL_EPType_Bulk;
@@ -2235,8 +2237,9 @@
 	/* enable the endpoint interrupt */
 	s3c_hsotg_ctrl_epint(hsotg, index, dir_in, 1);
 
+out:
 	spin_unlock_irqrestore(&hs_ep->lock, flags);
-	return 0;
+	return ret;
 }
 
 static int s3c_hsotg_ep_disable(struct usb_ep *ep)

drivers/usb/host/ohci-at91.c

diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 68b83ab..944291e 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -331,6 +331,8 @@
 	 */
 	if (at91_suspend_entering_slow_clock()) {
 		ohci_usb_reset (ohci);
+		/* flush the writes */
+		(void) ohci_readl (ohci, &ohci->regs->control);
 		at91_stop_clock();
 	}
 

drivers/usb/host/ohci-hub.c

diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c
index 32bbce9..65cac8c 100644
--- a/drivers/usb/host/ohci-hub.c
+++ b/drivers/usb/host/ohci-hub.c
@@ -697,7 +697,7 @@
 	u16		wLength
 ) {
 	struct ohci_hcd	*ohci = hcd_to_ohci (hcd);
-	int		ports = hcd_to_bus (hcd)->root_hub->maxchild;
+	int		ports = ohci->num_ports;
 	u32		temp;
 	int		retval = 0;
 

drivers/usb/host/oxu210hp-hcd.c

diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c
index 50f57f4..e62b30b 100644
--- a/drivers/usb/host/oxu210hp-hcd.c
+++ b/drivers/usb/host/oxu210hp-hcd.c
@@ -660,13 +660,13 @@
 		if (qh->dummy == NULL) {
 			oxu_dbg(oxu, "no dummy td\n");
 			oxu->qh_used[i] = 0;
-
-			return NULL;
+			qh = NULL;
+			goto unlock;
 		}
 
 		oxu->qh_used[i] = 1;
 	}
-
+unlock:
 	spin_unlock(&oxu->mem_lock);
 
 	return qh;

drivers/usb/host/sl811-hcd.c

diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c
index e11cc3a..3b867a8 100644
--- a/drivers/usb/host/sl811-hcd.c
+++ b/drivers/usb/host/sl811-hcd.c
@@ -720,10 +720,10 @@
 		/* port status seems weird until after reset, so
 		 * force the reset and make khubd clean up later.
 		 */
-		if (sl811->stat_insrmv & 1)
-			sl811->port1 |= 1 << USB_PORT_FEAT_CONNECTION;
-		else
+		if (irqstat & SL11H_INTMASK_RD)
 			sl811->port1 &= ~(1 << USB_PORT_FEAT_CONNECTION);
+		else
+			sl811->port1 |= 1 << USB_PORT_FEAT_CONNECTION;
 
 		sl811->port1 |= 1 << USB_PORT_FEAT_C_CONNECTION;
 

drivers/usb/host/xhci-mem.c

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index c09539b..d64f572 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -582,6 +582,19 @@
 	return EP_INTERVAL(interval);
 }
 
+/* The "Mult" field in the endpoint context is only set for SuperSpeed devices.
+ * High speed endpoint descriptors can define "the number of additional
+ * transaction opportunities per microframe", but that goes in the Max Burst
+ * endpoint context field.
+ */
+static inline u32 xhci_get_endpoint_mult(struct usb_device *udev,
+		struct usb_host_endpoint *ep)
+{
+	if (udev->speed != USB_SPEED_SUPER || !ep->ss_ep_comp)
+		return 0;
+	return ep->ss_ep_comp->desc.bmAttributes;
+}
+
 static inline u32 xhci_get_endpoint_type(struct usb_device *udev,
 		struct usb_host_endpoint *ep)
 {
@@ -612,6 +625,36 @@
 	return type;
 }
 
+/* Return the maximum endpoint service interval time (ESIT) payload.
+ * Basically, this is the maxpacket size, multiplied by the burst size
+ * and mult size.
+ */
+static inline u32 xhci_get_max_esit_payload(struct xhci_hcd *xhci,
+		struct usb_device *udev,
+		struct usb_host_endpoint *ep)
+{
+	int max_burst;
+	int max_packet;
+
+	/* Only applies for interrupt or isochronous endpoints */
+	if (usb_endpoint_xfer_control(&ep->desc) ||
+			usb_endpoint_xfer_bulk(&ep->desc))
+		return 0;
+
+	if (udev->speed == USB_SPEED_SUPER) {
+		if (ep->ss_ep_comp)
+			return ep->ss_ep_comp->desc.wBytesPerInterval;
+		xhci_warn(xhci, "WARN no SS endpoint companion descriptor.\n");
+		/* Assume no bursts, no multiple opportunities to send. */
+		return ep->desc.wMaxPacketSize;
+	}
+
+	max_packet = ep->desc.wMaxPacketSize & 0x3ff;
+	max_burst = (ep->desc.wMaxPacketSize & 0x1800) >> 11;
+	/* A 0 in max burst means 1 transfer per ESIT */
+	return max_packet * (max_burst + 1);
+}
+
 int xhci_endpoint_init(struct xhci_hcd *xhci,
 		struct xhci_virt_device *virt_dev,
 		struct usb_device *udev,
@@ -623,6 +666,7 @@
 	struct xhci_ring *ep_ring;
 	unsigned int max_packet;
 	unsigned int max_burst;
+	u32 max_esit_payload;
 
 	ep_index = xhci_get_endpoint_index(&ep->desc);
 	ep_ctx = xhci_get_ep_ctx(xhci, virt_dev->in_ctx, ep_index);
@@ -644,6 +688,7 @@
 	ep_ctx->deq = ep_ring->first_seg->dma | ep_ring->cycle_state;
 
 	ep_ctx->ep_info = xhci_get_endpoint_interval(udev, ep);
+	ep_ctx->ep_info |= EP_MULT(xhci_get_endpoint_mult(udev, ep));
 
 	/* FIXME dig Mult and streams info out of ep companion desc */
 
@@ -689,6 +734,26 @@
 	default:
 		BUG();
 	}
+	max_esit_payload = xhci_get_max_esit_payload(xhci, udev, ep);
+	ep_ctx->tx_info = MAX_ESIT_PAYLOAD_FOR_EP(max_esit_payload);
+
+	/*
+	 * XXX no idea how to calculate the average TRB buffer length for bulk
+	 * endpoints, as the driver gives us no clue how big each scatter gather
+	 * list entry (or buffer) is going to be.
+	 *
+	 * For isochronous and interrupt endpoints, we set it to the max
+	 * available, until we have new API in the USB core to allow drivers to
+	 * declare how much bandwidth they actually need.
+	 *
+	 * Normally, it would be calculated by taking the total of the buffer
+	 * lengths in the TD and then dividing by the number of TRBs in a TD,
+	 * including link TRBs, No-op TRBs, and Event data TRBs.  Since we don't
+	 * use Event Data TRBs, and we don't chain in a link TRB on short
+	 * transfers, we're basically dividing by 1.
+	 */
+	ep_ctx->tx_info |= AVG_TRB_LENGTH_FOR_EP(max_esit_payload);
+
 	/* FIXME Debug endpoint context */
 	return 0;
 }

drivers/usb/host/xhci.h

diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index e5eb09b..ea389e9 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -609,6 +609,10 @@
 #define MAX_PACKET_MASK		(0xffff << 16)
 #define MAX_PACKET_DECODED(p)	(((p) >> 16) & 0xffff)
 
+/* tx_info bitmasks */
+#define AVG_TRB_LENGTH_FOR_EP(p)	((p) & 0xffff)
+#define MAX_ESIT_PAYLOAD_FOR_EP(p)	(((p) & 0xffff) << 16)
+
 
 /**
  * struct xhci_input_control_context

drivers/usb/musb/Kconfig

diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig
index b4c783c..07fe490 100644
--- a/drivers/usb/musb/Kconfig
+++ b/drivers/usb/musb/Kconfig
@@ -42,7 +42,7 @@
 	default y if (BF52x && !BF522 && !BF523)
 
 comment "DaVinci 35x and 644x USB support"
-	depends on USB_MUSB_HDRC && ARCH_DAVINCI
+	depends on USB_MUSB_HDRC && ARCH_DAVINCI_DMx
 
 comment "OMAP 243x high speed USB support"
 	depends on USB_MUSB_HDRC && ARCH_OMAP2430

drivers/usb/musb/Makefile

diff --git a/drivers/usb/musb/Makefile b/drivers/usb/musb/Makefile
index 85710cc..3a485da 100644
--- a/drivers/usb/musb/Makefile
+++ b/drivers/usb/musb/Makefile
@@ -6,7 +6,7 @@
 
 obj-$(CONFIG_USB_MUSB_HDRC)	+= musb_hdrc.o
 
-ifeq ($(CONFIG_ARCH_DAVINCI),y)
+ifeq ($(CONFIG_ARCH_DAVINCI_DMx),y)
 	musb_hdrc-objs	+= davinci.o
 endif
 

drivers/usb/musb/blackfin.c

diff --git a/drivers/usb/musb/blackfin.c b/drivers/usb/musb/blackfin.c
index 719a22d..ec8d324 100644
--- a/drivers/usb/musb/blackfin.c
+++ b/drivers/usb/musb/blackfin.c
@@ -172,13 +172,7 @@
 
 	spin_unlock_irqrestore(&musb->lock, flags);
 
-	/* REVISIT we sometimes get spurious IRQs on g_ep0
-	 * not clear why... fall in BF54x too.
-	 */
-	if (retval != IRQ_HANDLED)
-		DBG(5, "spurious?\n");
-
-	return IRQ_HANDLED;
+	return retval;
 }
 
 static void musb_conn_timer_handler(unsigned long _musb)

drivers/usb/musb/davinci.c

diff --git a/drivers/usb/musb/davinci.c b/drivers/usb/musb/davinci.c
index 29bce5c..ce2e16f 100644
--- a/drivers/usb/musb/davinci.c
+++ b/drivers/usb/musb/davinci.c
@@ -444,6 +444,8 @@
 	return 0;
 
 fail:
+	clk_disable(musb->clock);
+
 	usb_nop_xceiv_unregister();
 	return -ENODEV;
 }

drivers/usb/musb/musb_core.c

diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 0e8b8ab..705cc4a 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -965,10 +965,8 @@
 	spin_lock_irqsave(&musb->lock, flags);
 	musb_platform_disable(musb);
 	musb_generic_disable(musb);
-	if (musb->clock) {
+	if (musb->clock)
 		clk_put(musb->clock);
-		musb->clock = NULL;
-	}
 	spin_unlock_irqrestore(&musb->lock, flags);
 
 	/* FIXME power down */
@@ -1853,15 +1851,6 @@
 	put_device(musb->xceiv->dev);
 #endif
 
-	musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
-	musb_platform_exit(musb);
-	musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
-
-	if (musb->clock) {
-		clk_disable(musb->clock);
-		clk_put(musb->clock);
-	}
-
 #ifdef CONFIG_USB_MUSB_HDRC_HCD
 	usb_put_hcd(musb_to_hcd(musb));
 #else
@@ -1889,8 +1878,10 @@
 	 */
 	if (!plat) {
 		dev_dbg(dev, "no platform_data?\n");
-		return -ENODEV;
+		status = -ENODEV;
+		goto fail0;
 	}
+
 	switch (plat->mode) {
 	case MUSB_HOST:
 #ifdef CONFIG_USB_MUSB_HDRC_HCD
@@ -1912,13 +1903,16 @@
 #endif
 	default:
 		dev_err(dev, "incompatible Kconfig role setting\n");
-		return -EINVAL;
+		status = -EINVAL;
+		goto fail0;
 	}
 
 	/* allocate */
 	musb = allocate_instance(dev, plat->config, ctrl);
-	if (!musb)
-		return -ENOMEM;
+	if (!musb) {
+		status = -ENOMEM;
+		goto fail0;
+	}
 
 	spin_lock_init(&musb->lock);
 	musb->board_mode = plat->mode;
@@ -1936,7 +1930,7 @@
 		if (IS_ERR(musb->clock)) {
 			status = PTR_ERR(musb->clock);
 			musb->clock = NULL;
-			goto fail;
+			goto fail1;
 		}
 	}
 
@@ -1955,12 +1949,12 @@
 	 */
 	musb->isr = generic_interrupt;
 	status = musb_platform_init(musb);
-
 	if (status < 0)
-		goto fail;
+		goto fail2;
+
 	if (!musb->isr) {
 		status = -ENODEV;
-		goto fail2;
+		goto fail3;
 	}
 
 #ifndef CONFIG_MUSB_PIO_ONLY
@@ -1986,7 +1980,7 @@
 			? MUSB_CONTROLLER_MHDRC
 			: MUSB_CONTROLLER_HDRC, musb);
 	if (status < 0)
-		goto fail2;
+		goto fail3;
 
 #ifdef CONFIG_USB_MUSB_OTG
 	setup_timer(&musb->otg_timer, musb_otg_timer_func, (unsigned long) musb);
@@ -1999,7 +1993,7 @@
 	if (request_irq(nIrq, musb->isr, 0, dev_name(dev), musb)) {
 		dev_err(dev, "request_irq %d failed!\n", nIrq);
 		status = -ENODEV;
-		goto fail2;
+		goto fail3;
 	}
 	musb->nIrq = nIrq;
 /* FIXME this handles wakeup irqs wrong */
@@ -2039,8 +2033,6 @@
 		musb->xceiv->state = OTG_STATE_A_IDLE;
 
 		status = usb_add_hcd(musb_to_hcd(musb), -1, 0);
-		if (status)
-			goto fail;
 
 		DBG(1, "%s mode, status %d, devctl %02x %c\n",
 			"HOST", status,
@@ -2055,8 +2047,6 @@
 		musb->xceiv->state = OTG_STATE_B_IDLE;
 
 		status = musb_gadget_setup(musb);
-		if (status)
-			goto fail;
 
 		DBG(1, "%s mode, status %d, dev%02x\n",
 			is_otg_enabled(musb) ? "OTG" : "PERIPHERAL",
@@ -2064,12 +2054,14 @@
 			musb_readb(musb->mregs, MUSB_DEVCTL));
 
 	}
+	if (status < 0)
+		goto fail3;
 
 #ifdef CONFIG_SYSFS
 	status = sysfs_create_group(&musb->controller->kobj, &musb_attr_group);
-#endif
 	if (status)
-		goto fail2;
+		goto fail4;
+#endif
 
 	dev_info(dev, "USB %s mode controller at %p using %s, IRQ %d\n",
 			({char *s;
@@ -2085,17 +2077,29 @@
 
 	return 0;
 
-fail2:
+fail4:
+	if (!is_otg_enabled(musb) && is_host_enabled(musb))
+		usb_remove_hcd(musb_to_hcd(musb));
+	else
+		musb_gadget_cleanup(musb);
+
+fail3:
+	if (musb->irq_wake)
+		device_init_wakeup(dev, 0);
 	musb_platform_exit(musb);
-fail:
+
+fail2:
+	if (musb->clock)
+		clk_put(musb->clock);
+
+fail1:
 	dev_err(musb->controller,
 		"musb_init_controller failed with status %d\n", status);
 
-	if (musb->clock)
-		clk_put(musb->clock);
-	device_init_wakeup(dev, 0);
 	musb_free(musb);
 
+fail0:
+
 	return status;
 
 }
@@ -2132,7 +2136,6 @@
 	/* clobbered by use_dma=n */
 	orig_dma_mask = dev->dma_mask;
 #endif
-
 	status = musb_init_controller(dev, irq, base);
 	if (status < 0)
 		iounmap(base);
@@ -2155,6 +2158,10 @@
 	if (musb->board_mode == MUSB_HOST)
 		usb_remove_hcd(musb_to_hcd(musb));
 #endif
+	musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
+	musb_platform_exit(musb);
+	musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
+
 	musb_free(musb);
 	iounmap(ctrl_base);
 	device_init_wakeup(&pdev->dev, 0);
@@ -2176,6 +2183,7 @@
 	if (is_host_enabled(musb)) {
 		musb_context.frame = musb_readw(musb_base, MUSB_FRAME);
 		musb_context.testmode = musb_readb(musb_base, MUSB_TESTMODE);
+		musb_context.busctl = musb_read_ulpi_buscontrol(musb->mregs);
 	}
 	musb_context.power = musb_readb(musb_base, MUSB_POWER);
 	musb_context.intrtxe = musb_readw(musb_base, MUSB_INTRTXE);
@@ -2247,6 +2255,7 @@
 	if (is_host_enabled(musb)) {
 		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);
 	musb_writew(musb_base, MUSB_INTRTXE, musb_context.intrtxe);

drivers/usb/musb/musb_core.h

diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index cd9f4a9..ac17b00 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -478,7 +478,7 @@
 	u16 frame;
 	u8 index, testmode;
 
-	u8 devctl, misc;
+	u8 devctl, busctl, misc;
 
 	struct musb_csr_regs index_regs[MUSB_C_NUM_EPS];
 };

drivers/usb/musb/musb_host.c

diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index dec896e..877d20b 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -2042,6 +2042,7 @@
 		 * odd, rare, error prone, but legal.
 		 */
 		kfree(qh);
+		qh = NULL;
 		ret = 0;
 	} else
 		ret = musb_schedule(musb, qh,

drivers/usb/musb/omap2430.c

diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 490cdf1..8259263 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -331,8 +331,5 @@
 
 	musb_platform_suspend(musb);
 
-	clk_put(musb->clock);
-	musb->clock = NULL;
-
 	return 0;
 }

drivers/usb/musb/tusb6010.c

diff --git a/drivers/usb/musb/tusb6010.c b/drivers/usb/musb/tusb6010.c
index ab776a8..60d3938 100644
--- a/drivers/usb/musb/tusb6010.c
+++ b/drivers/usb/musb/tusb6010.c
@@ -29,6 +29,19 @@
 #define TUSB_REV_MAJOR(reg_val)		((reg_val >> 4) & 0xf)
 #define TUSB_REV_MINOR(reg_val)		(reg_val & 0xf)
 
+#ifdef CONFIG_PM
+/* REVISIT: These should be only needed if somebody implements off idle */
+void musb_platform_save_context(struct musb *musb,
+			struct musb_context_registers *musb_context)
+{
+}
+
+void musb_platform_restore_context(struct musb *musb,
+			struct musb_context_registers *musb_context)
+{
+}
+#endif
+
 /*
  * Checks the revision. We need to use the DMA register as 3.0 does not
  * have correct versions for TUSB_PRCM_REV or TUSB_INT_CTRL_REV.

drivers/usb/musb/tusb6010_omap.c

diff --git a/drivers/usb/musb/tusb6010_omap.c b/drivers/usb/musb/tusb6010_omap.c
index 5afa070..c061a88 100644
--- a/drivers/usb/musb/tusb6010_omap.c
+++ b/drivers/usb/musb/tusb6010_omap.c
@@ -39,7 +39,7 @@
 
 	struct tusb_omap_dma	*tusb_dma;
 
-	void __iomem		*dma_addr;
+	dma_addr_t		dma_addr;
 
 	u32			len;
 	u16			packet_sz;
@@ -126,6 +126,7 @@
 	struct tusb_omap_dma_ch	*chdat = to_chdat(channel);
 	struct tusb_omap_dma	*tusb_dma = chdat->tusb_dma;
 	struct musb		*musb = chdat->musb;
+	struct device		*dev = musb->controller;
 	struct musb_hw_ep	*hw_ep = chdat->hw_ep;
 	void __iomem		*ep_conf = hw_ep->conf;
 	void __iomem		*mbase = musb->mregs;
@@ -173,13 +174,15 @@
 		DBG(3, "Using PIO for remaining %lu bytes\n", pio);
 		buf = phys_to_virt((u32)chdat->dma_addr) + chdat->transfer_len;
 		if (chdat->tx) {
-			dma_cache_maint(phys_to_virt((u32)chdat->dma_addr),
-					chdat->transfer_len, DMA_TO_DEVICE);
+			dma_unmap_single(dev, chdat->dma_addr,
+						chdat->transfer_len,
+						DMA_TO_DEVICE);
 			musb_write_fifo(hw_ep, pio, buf);
 		} else {
+			dma_unmap_single(dev, chdat->dma_addr,
+						chdat->transfer_len,
+						DMA_FROM_DEVICE);
 			musb_read_fifo(hw_ep, pio, buf);
-			dma_cache_maint(phys_to_virt((u32)chdat->dma_addr),
-					chdat->transfer_len, DMA_FROM_DEVICE);
 		}
 		channel->actual_len += pio;
 	}
@@ -224,6 +227,7 @@
 	struct tusb_omap_dma_ch		*chdat = to_chdat(channel);
 	struct tusb_omap_dma		*tusb_dma = chdat->tusb_dma;
 	struct musb			*musb = chdat->musb;
+	struct device			*dev = musb->controller;
 	struct musb_hw_ep		*hw_ep = chdat->hw_ep;
 	void __iomem			*mbase = musb->mregs;
 	void __iomem			*ep_conf = hw_ep->conf;
@@ -299,14 +303,16 @@
 	chdat->packet_sz = packet_sz;
 	chdat->len = len;
 	channel->actual_len = 0;
-	chdat->dma_addr = (void __iomem *)dma_addr;
+	chdat->dma_addr = dma_addr;
 	channel->status = MUSB_DMA_STATUS_BUSY;
 
 	/* Since we're recycling dma areas, we need to clean or invalidate */
 	if (chdat->tx)
-		dma_cache_maint(phys_to_virt(dma_addr), len, DMA_TO_DEVICE);
+		dma_map_single(dev, phys_to_virt(dma_addr), len,
+				DMA_TO_DEVICE);
 	else
-		dma_cache_maint(phys_to_virt(dma_addr), len, DMA_FROM_DEVICE);
+		dma_map_single(dev, phys_to_virt(dma_addr), len,
+				DMA_FROM_DEVICE);
 
 	/* Use 16-bit transfer if dma_addr is not 32-bit aligned */
 	if ((dma_addr & 0x3) == 0) {

drivers/usb/serial/option.c

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index ca9d866..84d0eda 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -305,6 +305,11 @@
 #define ZTE_PRODUCT_CDMA_TECH			0xfffe
 #define ZTE_PRODUCT_AC8710			0xfff1
 #define ZTE_PRODUCT_AC2726			0xfff5
+#define ZTE_PRODUCT_AC8710T			0xffff
+
+/* ZTE PRODUCTS -- alternate vendor ID */
+#define ZTE_VENDOR_ID2				0x1d6b
+#define ZTE_PRODUCT_MF_330			0x0002
 
 #define BENQ_VENDOR_ID				0x04a5
 #define BENQ_PRODUCT_H10			0x4068
@@ -373,6 +378,8 @@
 #define HAIER_VENDOR_ID				0x201e
 #define HAIER_PRODUCT_CE100			0x2009
 
+#define CINTERION_VENDOR_ID			0x0681
+
 /* some devices interfaces need special handling due to a number of reasons */
 enum option_blacklist_reason {
 		OPTION_BLACKLIST_NONE = 0,
@@ -679,6 +686,8 @@
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_CDMA_TECH, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE(ZTE_VENDOR_ID2, ZTE_PRODUCT_MF_330) },
 	{ USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) },
 	{ USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) },
 	{ USB_DEVICE(ALINK_VENDOR_ID, DLINK_PRODUCT_DWM_652_U5) }, /* Yes, ALINK_VENDOR_ID */
@@ -716,6 +725,7 @@
 	{ USB_DEVICE(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_1011)},
 	{ USB_DEVICE(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_1012)},
 
+	{ USB_DEVICE(CINTERION_VENDOR_ID, 0x0047) },
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);

drivers/usb/serial/pl2303.c

diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index c97a0bb..c28b160 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -59,6 +59,7 @@
 	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_ALDIGA) },
 	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MMX) },
 	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_GPRS) },
+	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_HCR331) },
 	{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) },
 	{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) },
 	{ USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) },

drivers/usb/serial/pl2303.h

diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index a352d5f3..23c09b3 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -20,6 +20,7 @@
 #define PL2303_PRODUCT_ID_ALDIGA	0x0611
 #define PL2303_PRODUCT_ID_MMX		0x0612
 #define PL2303_PRODUCT_ID_GPRS		0x0609
+#define PL2303_PRODUCT_ID_HCR331	0x331a
 
 #define ATEN_VENDOR_ID		0x0557
 #define ATEN_VENDOR_ID2		0x0547

drivers/usb/serial/ti_usb_3410_5052.c

diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index 880e990..e1bfda3 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -1735,7 +1735,7 @@
 		return -ENOENT;
 	}
 	if (fw_p->size > TI_FIRMWARE_BUF_SIZE) {
-		dev_err(&dev->dev, "%s - firmware too large %d \n", __func__, fw_p->size);
+		dev_err(&dev->dev, "%s - firmware too large %zu\n", __func__, fw_p->size);
 		return -ENOENT;
 	}
 

drivers/vhost/vhost.c

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index e69d238..49fa953 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1035,7 +1035,12 @@
 /* This actually signals the guest, using eventfd. */
 void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
-	__u16 flags = 0;
+	__u16 flags;
+	/* Flush out used index updates. This is paired
+	 * with the barrier that the Guest executes when enabling
+	 * interrupts. */
+	smp_mb();
+
 	if (get_user(flags, &vq->avail->flags)) {
 		vq_err(vq, "Failed to get flags");
 		return;

drivers/video/amifb.c

diff --git a/drivers/video/amifb.c b/drivers/video/amifb.c
index dca48df..e5d6b56 100644
--- a/drivers/video/amifb.c
+++ b/drivers/video/amifb.c
@@ -50,8 +50,9 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
-
+#include <linux/platform_device.h>
 #include <linux/uaccess.h>
+
 #include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/amigahw.h>
@@ -1135,7 +1136,7 @@
 	 * Interface to the low level console driver
 	 */
 
-static void amifb_deinit(void);
+static void amifb_deinit(struct platform_device *pdev);
 
 	/*
 	 * Internal routines
@@ -2246,7 +2247,7 @@
 	 * Initialisation
 	 */
 
-static int __init amifb_init(void)
+static int __init amifb_probe(struct platform_device *pdev)
 {
 	int tag, i, err = 0;
 	u_long chipptr;
@@ -2261,16 +2262,6 @@
 	}
 	amifb_setup(option);
 #endif
-	if (!MACH_IS_AMIGA || !AMIGAHW_PRESENT(AMI_VIDEO))
-		return -ENODEV;
-
-	/*
-	 * We request all registers starting from bplpt[0]
-	 */
-	if (!request_mem_region(CUSTOM_PHYSADDR+0xe0, 0x120,
-				"amifb [Denise/Lisa]"))
-		return -EBUSY;
-
 	custom.dmacon = DMAF_ALL | DMAF_MASTER;
 
 	switch (amiga_chipset) {
@@ -2377,6 +2368,7 @@
 	fb_info.fbops = &amifb_ops;
 	fb_info.par = &currentpar;
 	fb_info.flags = FBINFO_DEFAULT;
+	fb_info.device = &pdev->dev;
 
 	if (!fb_find_mode(&fb_info.var, &fb_info, mode_option, ami_modedb,
 			  NUM_TOTAL_MODES, &ami_modedb[defmode], 4)) {
@@ -2451,18 +2443,18 @@
 	return 0;
 
 amifb_error:
-	amifb_deinit();
+	amifb_deinit(pdev);
 	return err;
 }
 
-static void amifb_deinit(void)
+static void amifb_deinit(struct platform_device *pdev)
 {
 	if (fb_info.cmap.len)
 		fb_dealloc_cmap(&fb_info.cmap);
+	fb_dealloc_cmap(&fb_info.cmap);
 	chipfree();
 	if (videomemory)
 		iounmap((void*)videomemory);
-	release_mem_region(CUSTOM_PHYSADDR+0xe0, 0x120);
 	custom.dmacon = DMAF_ALL | DMAF_MASTER;
 }
 
@@ -3794,14 +3786,35 @@
 	}
 }
 
-static void __exit amifb_exit(void)
+static int __exit amifb_remove(struct platform_device *pdev)
 {
 	unregister_framebuffer(&fb_info);
-	amifb_deinit();
+	amifb_deinit(pdev);
 	amifb_video_off();
+	return 0;
+}
+
+static struct platform_driver amifb_driver = {
+	.remove = __exit_p(amifb_remove),
+	.driver   = {
+		.name	= "amiga-video",
+		.owner	= THIS_MODULE,
+	},
+};
+
+static int __init amifb_init(void)
+{
+	return platform_driver_probe(&amifb_driver, amifb_probe);
 }
 
 module_init(amifb_init);
+
+static void __exit amifb_exit(void)
+{
+	platform_driver_unregister(&amifb_driver);
+}
+
 module_exit(amifb_exit);
 
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:amiga-video");

drivers/video/bfin-t350mcqb-fb.c

diff --git a/drivers/video/bfin-t350mcqb-fb.c b/drivers/video/bfin-t350mcqb-fb.c
index 44e49c2..c2ec3dcd 100644
--- a/drivers/video/bfin-t350mcqb-fb.c
+++ b/drivers/video/bfin-t350mcqb-fb.c
@@ -488,9 +488,9 @@
 	fbinfo->fbops = &bfin_t350mcqb_fb_ops;
 	fbinfo->flags = FBINFO_FLAG_DEFAULT;
 
-	info->fb_buffer =
-	    dma_alloc_coherent(NULL, fbinfo->fix.smem_len, &info->dma_handle,
-			       GFP_KERNEL);
+	info->fb_buffer = dma_alloc_coherent(NULL, fbinfo->fix.smem_len +
+				ACTIVE_VIDEO_MEM_OFFSET,
+				&info->dma_handle, GFP_KERNEL);
 
 	if (NULL == info->fb_buffer) {
 		printk(KERN_ERR DRIVER_NAME
@@ -568,8 +568,8 @@
 out6:
 	fb_dealloc_cmap(&fbinfo->cmap);
 out4:
-	dma_free_coherent(NULL, fbinfo->fix.smem_len, info->fb_buffer,
-			  info->dma_handle);
+	dma_free_coherent(NULL, fbinfo->fix.smem_len + ACTIVE_VIDEO_MEM_OFFSET,
+			 info->fb_buffer, info->dma_handle);
 out3:
 	framebuffer_release(fbinfo);
 out2:
@@ -592,8 +592,9 @@
 	free_irq(info->irq, info);
 
 	if (info->fb_buffer != NULL)
-		dma_free_coherent(NULL, fbinfo->fix.smem_len, info->fb_buffer,
-				  info->dma_handle);
+		dma_free_coherent(NULL, fbinfo->fix.smem_len +
+			ACTIVE_VIDEO_MEM_OFFSET, info->fb_buffer,
+			info->dma_handle);
 
 	fb_dealloc_cmap(&fbinfo->cmap);
 

drivers/video/cirrusfb.c

diff --git a/drivers/video/cirrusfb.c b/drivers/video/cirrusfb.c
index 8d8dfda..6df7c54 100644
--- a/drivers/video/cirrusfb.c
+++ b/drivers/video/cirrusfb.c
@@ -299,6 +299,7 @@
 	},
 	{ 0 }
 };
+MODULE_DEVICE_TABLE(zorro, cirrusfb_zorro_table);
 
 static const struct {
 	zorro_id id2;

drivers/video/fm2fb.c

diff --git a/drivers/video/fm2fb.c b/drivers/video/fm2fb.c
index 6c91c61..1b0feb8 100644
--- a/drivers/video/fm2fb.c
+++ b/drivers/video/fm2fb.c
@@ -219,6 +219,7 @@
 	{ ZORRO_PROD_HELFRICH_RAINBOW_II },
 	{ 0 }
 };
+MODULE_DEVICE_TABLE(zorro, fm2fb_devices);
 
 static struct zorro_driver fm2fb_driver = {
 	.name		= "fm2fb",

drivers/video/sh_mobile_lcdcfb.c

diff --git a/drivers/video/sh_mobile_lcdcfb.c b/drivers/video/sh_mobile_lcdcfb.c
index e14bd07..e8c7699 100644
--- a/drivers/video/sh_mobile_lcdcfb.c
+++ b/drivers/video/sh_mobile_lcdcfb.c
@@ -695,6 +695,7 @@
 	 * 1) Enable Runtime PM
 	 * 2) Force Runtime PM Resume since hardware is accessed from probe()
 	 */
+	priv->dev = &pdev->dev;
 	pm_runtime_enable(priv->dev);
 	pm_runtime_resume(priv->dev);
 	return 0;
@@ -957,25 +958,24 @@
 
 	if (!pdev->dev.platform_data) {
 		dev_err(&pdev->dev, "no platform data defined\n");
-		error = -EINVAL;
-		goto err0;
+		return -EINVAL;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	i = platform_get_irq(pdev, 0);
 	if (!res || i < 0) {
 		dev_err(&pdev->dev, "cannot get platform resources\n");
-		error = -ENOENT;
-		goto err0;
+		return -ENOENT;
 	}
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
 		dev_err(&pdev->dev, "cannot allocate device data\n");
-		error = -ENOMEM;
-		goto err0;
+		return -ENOMEM;
 	}
 
+	platform_set_drvdata(pdev, priv);
+
 	error = request_irq(i, sh_mobile_lcdc_irq, IRQF_DISABLED,
 			    dev_name(&pdev->dev), priv);
 	if (error) {
@@ -984,8 +984,6 @@
 	}
 
 	priv->irq = i;
-	priv->dev = &pdev->dev;
-	platform_set_drvdata(pdev, priv);
 	pdata = pdev->dev.platform_data;
 
 	j = 0;
@@ -1099,9 +1097,9 @@
 		info = ch->info;
 
 		if (info->fbdefio) {
-			priv->ch->sglist = vmalloc(sizeof(struct scatterlist) *
+			ch->sglist = vmalloc(sizeof(struct scatterlist) *
 					info->fix.smem_len >> PAGE_SHIFT);
-			if (!priv->ch->sglist) {
+			if (!ch->sglist) {
 				dev_err(&pdev->dev, "cannot allocate sglist\n");
 				goto err1;
 			}
@@ -1126,9 +1124,9 @@
 	}
 
 	return 0;
- err1:
+err1:
 	sh_mobile_lcdc_remove(pdev);
- err0:
+
 	return error;
 }
 
@@ -1139,7 +1137,7 @@
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(priv->ch); i++)
-		if (priv->ch[i].info->dev)
+		if (priv->ch[i].info && priv->ch[i].info->dev)
 			unregister_framebuffer(priv->ch[i].info);
 
 	sh_mobile_lcdc_stop(priv);
@@ -1162,7 +1160,8 @@
 	if (priv->dot_clk)
 		clk_put(priv->dot_clk);
 
-	pm_runtime_disable(priv->dev);
+	if (priv->dev)
+		pm_runtime_disable(priv->dev);
 
 	if (priv->base)
 		iounmap(priv->base);

drivers/watchdog/Kconfig

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 0bf5020..b87ba23 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -175,7 +175,7 @@
 
 config MPCORE_WATCHDOG
 	tristate "MPcore watchdog"
-	depends on ARM_MPCORE_PLATFORM && LOCAL_TIMERS
+	depends on HAVE_ARM_TWD
 	help
 	  Watchdog timer embedded into the MPcore system.
 

drivers/watchdog/ep93xx_wdt.c

diff --git a/drivers/watchdog/ep93xx_wdt.c b/drivers/watchdog/ep93xx_wdt.c
index 88ed54e..59359c9 100644
--- a/drivers/watchdog/ep93xx_wdt.c
+++ b/drivers/watchdog/ep93xx_wdt.c
@@ -244,7 +244,7 @@
 module_param(timeout, int, 0);
 MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. (1<=timeout<=3600, default="
-				__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
+				__MODULE_STRING(WDT_TIMEOUT) ")");
 
 MODULE_AUTHOR("Ray Lehtiniemi <rayl@mail.com>,"
 		"Alessandro Zummo <a.zummo@towertech.it>");

drivers/watchdog/mpcore_wdt.c

diff --git a/drivers/watchdog/mpcore_wdt.c b/drivers/watchdog/mpcore_wdt.c
index 016c6a7..b8ec7ac 100644
--- a/drivers/watchdog/mpcore_wdt.c
+++ b/drivers/watchdog/mpcore_wdt.c
@@ -31,8 +31,9 @@
 #include <linux/platform_device.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 
-#include <asm/hardware/arm_twd.h>
+#include <asm/smp_twd.h>
 
 struct mpcore_wdt {
 	unsigned long	timer_alive;
@@ -44,7 +45,7 @@
 };
 
 static struct platform_device *mpcore_wdt_dev;
-extern unsigned int mpcore_timer_rate;
+static DEFINE_SPINLOCK(wdt_lock);
 
 #define TIMER_MARGIN	60
 static int mpcore_margin = TIMER_MARGIN;
@@ -94,13 +95,15 @@
  */
 static void mpcore_wdt_keepalive(struct mpcore_wdt *wdt)
 {
-	unsigned int count;
+	unsigned long count;
 
+	spin_lock(&wdt_lock);
 	/* Assume prescale is set to 256 */
-	count = (mpcore_timer_rate / 256) * mpcore_margin;
+	count =  __raw_readl(wdt->base + TWD_WDOG_COUNTER);
+	count = (0xFFFFFFFFU - count) * (HZ / 5);
+	count = (count / 256) * mpcore_margin;
 
 	/* Reload the counter */
-	spin_lock(&wdt_lock);
 	writel(count + wdt->perturb, wdt->base + TWD_WDOG_LOAD);
 	wdt->perturb = wdt->perturb ? 0 : 1;
 	spin_unlock(&wdt_lock);
@@ -119,7 +122,6 @@
 {
 	dev_printk(KERN_INFO, wdt->dev, "enabling watchdog.\n");
 
-	spin_lock(&wdt_lock);
 	/* This loads the count register but does NOT start the count yet */
 	mpcore_wdt_keepalive(wdt);
 
@@ -130,7 +132,6 @@
 		/* Enable watchdog - prescale=256, watchdog mode=1, enable=1 */
 		writel(0x0000FF09, wdt->base + TWD_WDOG_CONTROL);
 	}
-	spin_unlock(&wdt_lock);
 }
 
 static int mpcore_wdt_set_heartbeat(int t)
@@ -360,7 +361,7 @@
 	mpcore_wdt_miscdev.parent = &dev->dev;
 	ret = misc_register(&mpcore_wdt_miscdev);
 	if (ret) {
-		dev_printk(KERN_ERR, _dev,
+		dev_printk(KERN_ERR, wdt->dev,
 			"cannot register miscdev on minor=%d (err=%d)\n",
 							WATCHDOG_MINOR, ret);
 		goto err_misc;
@@ -369,13 +370,13 @@
 	ret = request_irq(wdt->irq, mpcore_wdt_fire, IRQF_DISABLED,
 							"mpcore_wdt", wdt);
 	if (ret) {
-		dev_printk(KERN_ERR, _dev,
+		dev_printk(KERN_ERR, wdt->dev,
 			"cannot register IRQ%d for watchdog\n", wdt->irq);
 		goto err_irq;
 	}
 
 	mpcore_wdt_stop(wdt);
-	platform_set_drvdata(&dev->dev, wdt);
+	platform_set_drvdata(dev, wdt);
 	mpcore_wdt_dev = dev;
 
 	return 0;

drivers/zorro/proc.c

diff --git a/drivers/zorro/proc.c b/drivers/zorro/proc.c
index d47c47f..3c7046d 100644
--- a/drivers/zorro/proc.c
+++ b/drivers/zorro/proc.c
@@ -97,7 +97,7 @@
 
 static int zorro_seq_show(struct seq_file *m, void *v)
 {
-	u_int slot = *(loff_t *)v;
+	unsigned int slot = *(loff_t *)v;
 	struct zorro_dev *z = &zorro_autocon[slot];
 
 	seq_printf(m, "%02x\t%08x\t%08lx\t%08lx\t%02x\n", slot, z->id,
@@ -129,7 +129,7 @@
 
 static struct proc_dir_entry *proc_bus_zorro_dir;
 
-static int __init zorro_proc_attach_device(u_int slot)
+static int __init zorro_proc_attach_device(unsigned int slot)
 {
 	struct proc_dir_entry *entry;
 	char name[4];
@@ -146,7 +146,7 @@
 
 static int __init zorro_proc_init(void)
 {
-	u_int slot;
+	unsigned int slot;
 
 	if (MACH_IS_AMIGA && AMIGAHW_PRESENT(ZORRO)) {
 		proc_bus_zorro_dir = proc_mkdir("bus/zorro", NULL);

drivers/zorro/zorro-driver.c

diff --git a/drivers/zorro/zorro-driver.c b/drivers/zorro/zorro-driver.c
index 53180a3..7ee2b6e 100644
--- a/drivers/zorro/zorro-driver.c
+++ b/drivers/zorro/zorro-driver.c
@@ -137,10 +137,34 @@
 	return 0;
 }
 
+static int zorro_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+#ifdef CONFIG_HOTPLUG
+	struct zorro_dev *z;
+
+	if (!dev)
+		return -ENODEV;
+
+	z = to_zorro_dev(dev);
+	if (!z)
+		return -ENODEV;
+
+	if (add_uevent_var(env, "ZORRO_ID=%08X", z->id) ||
+	    add_uevent_var(env, "ZORRO_SLOT_NAME=%s", dev_name(dev)) ||
+	    add_uevent_var(env, "ZORRO_SLOT_ADDR=%04X", z->slotaddr) ||
+	    add_uevent_var(env, "MODALIAS=" ZORRO_DEVICE_MODALIAS_FMT, z->id))
+		return -ENOMEM;
+
+	return 0;
+#else /* !CONFIG_HOTPLUG */
+	return -ENODEV;
+#endif /* !CONFIG_HOTPLUG */
+}
 
 struct bus_type zorro_bus_type = {
 	.name	= "zorro",
 	.match	= zorro_bus_match,
+	.uevent	= zorro_uevent,
 	.probe	= zorro_device_probe,
 	.remove	= zorro_device_remove,
 };

drivers/zorro/zorro-sysfs.c

diff --git a/drivers/zorro/zorro-sysfs.c b/drivers/zorro/zorro-sysfs.c
index 1d2a772e..eb924e0 100644
--- a/drivers/zorro/zorro-sysfs.c
+++ b/drivers/zorro/zorro-sysfs.c
@@ -77,6 +77,16 @@
 	.read = zorro_read_config,
 };
 
+static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct zorro_dev *z = to_zorro_dev(dev);
+
+	return sprintf(buf, ZORRO_DEVICE_MODALIAS_FMT "\n", z->id);
+}
+
+static DEVICE_ATTR(modalias, S_IRUGO, modalias_show, NULL);
+
 int zorro_create_sysfs_dev_files(struct zorro_dev *z)
 {
 	struct device *dev = &z->dev;
@@ -89,6 +99,7 @@
 	    (error = device_create_file(dev, &dev_attr_slotaddr)) ||
 	    (error = device_create_file(dev, &dev_attr_slotsize)) ||
 	    (error = device_create_file(dev, &dev_attr_resource)) ||
+	    (error = device_create_file(dev, &dev_attr_modalias)) ||
 	    (error = sysfs_create_bin_file(&dev->kobj, &zorro_config_attr)))
 		return error;
 

drivers/zorro/zorro.c

diff --git a/drivers/zorro/zorro.c b/drivers/zorro/zorro.c
index d45fb34..6455f3a 100644
--- a/drivers/zorro/zorro.c
+++ b/drivers/zorro/zorro.c
@@ -15,6 +15,8 @@
 #include <linux/zorro.h>
 #include <linux/bitops.h>
 #include <linux/string.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
 
 #include <asm/setup.h>
 #include <asm/amigahw.h>
@@ -26,24 +28,17 @@
      *  Zorro Expansion Devices
      */
 
-u_int zorro_num_autocon = 0;
+unsigned int zorro_num_autocon;
 struct zorro_dev zorro_autocon[ZORRO_NUM_AUTO];
 
 
     /*
-     *  Single Zorro bus
+     *  Zorro bus
      */
 
-struct zorro_bus zorro_bus = {\
-    .resources = {
-	/* Zorro II regions (on Zorro II/III) */
-	{ .name = "Zorro II exp", .start = 0x00e80000, .end = 0x00efffff },
-	{ .name = "Zorro II mem", .start = 0x00200000, .end = 0x009fffff },
-	/* Zorro III regions (on Zorro III only) */
-	{ .name = "Zorro III exp", .start = 0xff000000, .end = 0xffffffff },
-	{ .name = "Zorro III cfg", .start = 0x40000000, .end = 0x7fffffff }
-    },
-    .name = "Zorro bus"
+struct zorro_bus {
+	struct list_head devices;	/* list of devices on this bus */
+	struct device dev;
 };
 
 
@@ -53,18 +48,19 @@
 
 struct zorro_dev *zorro_find_device(zorro_id id, struct zorro_dev *from)
 {
-    struct zorro_dev *z;
+	struct zorro_dev *z;
 
-    if (!MACH_IS_AMIGA || !AMIGAHW_PRESENT(ZORRO))
+	if (!zorro_num_autocon)
+		return NULL;
+
+	for (z = from ? from+1 : &zorro_autocon[0];
+	     z < zorro_autocon+zorro_num_autocon;
+	     z++)
+		if (id == ZORRO_WILDCARD || id == z->id)
+			return z;
 	return NULL;
-
-    for (z = from ? from+1 : &zorro_autocon[0];
-	 z < zorro_autocon+zorro_num_autocon;
-	 z++)
-	if (id == ZORRO_WILDCARD || id == z->id)
-	    return z;
-    return NULL;
 }
+EXPORT_SYMBOL(zorro_find_device);
 
 
     /*
@@ -83,121 +79,138 @@
      */
 
 DECLARE_BITMAP(zorro_unused_z2ram, 128);
+EXPORT_SYMBOL(zorro_unused_z2ram);
 
 
 static void __init mark_region(unsigned long start, unsigned long end,
 			       int flag)
 {
-    if (flag)
-	start += Z2RAM_CHUNKMASK;
-    else
-	end += Z2RAM_CHUNKMASK;
-    start &= ~Z2RAM_CHUNKMASK;
-    end &= ~Z2RAM_CHUNKMASK;
-
-    if (end <= Z2RAM_START || start >= Z2RAM_END)
-	return;
-    start = start < Z2RAM_START ? 0x00000000 : start-Z2RAM_START;
-    end = end > Z2RAM_END ? Z2RAM_SIZE : end-Z2RAM_START;
-    while (start < end) {
-	u32 chunk = start>>Z2RAM_CHUNKSHIFT;
 	if (flag)
-	    set_bit(chunk, zorro_unused_z2ram);
+		start += Z2RAM_CHUNKMASK;
 	else
-	    clear_bit(chunk, zorro_unused_z2ram);
-	start += Z2RAM_CHUNKSIZE;
-    }
-}
+		end += Z2RAM_CHUNKMASK;
+	start &= ~Z2RAM_CHUNKMASK;
+	end &= ~Z2RAM_CHUNKMASK;
 
-
-static struct resource __init *zorro_find_parent_resource(struct zorro_dev *z)
-{
-    int i;
-
-    for (i = 0; i < zorro_bus.num_resources; i++)
-	if (zorro_resource_start(z) >= zorro_bus.resources[i].start &&
-	    zorro_resource_end(z) <= zorro_bus.resources[i].end)
-		return &zorro_bus.resources[i];
-    return &iomem_resource;
-}
-
-
-    /*
-     *  Initialization
-     */
-
-static int __init zorro_init(void)
-{
-    struct zorro_dev *z;
-    unsigned int i;
-    int error;
-
-    if (!MACH_IS_AMIGA || !AMIGAHW_PRESENT(ZORRO))
-	return 0;
-
-    pr_info("Zorro: Probing AutoConfig expansion devices: %d device%s\n",
-	   zorro_num_autocon, zorro_num_autocon == 1 ? "" : "s");
-
-    /* Initialize the Zorro bus */
-    INIT_LIST_HEAD(&zorro_bus.devices);
-    dev_set_name(&zorro_bus.dev, "zorro");
-    error = device_register(&zorro_bus.dev);
-    if (error) {
-	pr_err("Zorro: Error registering zorro_bus\n");
-	return error;
-    }
-
-    /* Request the resources */
-    zorro_bus.num_resources = AMIGAHW_PRESENT(ZORRO3) ? 4 : 2;
-    for (i = 0; i < zorro_bus.num_resources; i++)
-	request_resource(&iomem_resource, &zorro_bus.resources[i]);
-
-    /* Register all devices */
-    for (i = 0; i < zorro_num_autocon; i++) {
-	z = &zorro_autocon[i];
-	z->id = (z->rom.er_Manufacturer<<16) | (z->rom.er_Product<<8);
-	if (z->id == ZORRO_PROD_GVP_EPC_BASE) {
-	    /* GVP quirk */
-	    unsigned long magic = zorro_resource_start(z)+0x8000;
-	    z->id |= *(u16 *)ZTWO_VADDR(magic) & GVP_PRODMASK;
+	if (end <= Z2RAM_START || start >= Z2RAM_END)
+		return;
+	start = start < Z2RAM_START ? 0x00000000 : start-Z2RAM_START;
+	end = end > Z2RAM_END ? Z2RAM_SIZE : end-Z2RAM_START;
+	while (start < end) {
+		u32 chunk = start>>Z2RAM_CHUNKSHIFT;
+		if (flag)
+			set_bit(chunk, zorro_unused_z2ram);
+		else
+			clear_bit(chunk, zorro_unused_z2ram);
+		start += Z2RAM_CHUNKSIZE;
 	}
-	sprintf(z->name, "Zorro device %08x", z->id);
-	zorro_name_device(z);
-	z->resource.name = z->name;
-	if (request_resource(zorro_find_parent_resource(z), &z->resource))
-	    pr_err("Zorro: Address space collision on device %s %pR\n",
-		   z->name, &z->resource);
-	dev_set_name(&z->dev, "%02x", i);
-	z->dev.parent = &zorro_bus.dev;
-	z->dev.bus = &zorro_bus_type;
-	error = device_register(&z->dev);
+}
+
+
+static struct resource __init *zorro_find_parent_resource(
+	struct platform_device *bridge, struct zorro_dev *z)
+{
+	int i;
+
+	for (i = 0; i < bridge->num_resources; i++) {
+		struct resource *r = &bridge->resource[i];
+		if (zorro_resource_start(z) >= r->start &&
+		    zorro_resource_end(z) <= r->end)
+			return r;
+	}
+	return &iomem_resource;
+}
+
+
+
+static int __init amiga_zorro_probe(struct platform_device *pdev)
+{
+	struct zorro_bus *bus;
+	struct zorro_dev *z;
+	struct resource *r;
+	unsigned int i;
+	int error;
+
+	/* Initialize the Zorro bus */
+	bus = kzalloc(sizeof(*bus), GFP_KERNEL);
+	if (!bus)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&bus->devices);
+	bus->dev.parent = &pdev->dev;
+	dev_set_name(&bus->dev, "zorro");
+	error = device_register(&bus->dev);
 	if (error) {
-	    pr_err("Zorro: Error registering device %s\n", z->name);
-	    continue;
+		pr_err("Zorro: Error registering zorro_bus\n");
+		kfree(bus);
+		return error;
 	}
-	error = zorro_create_sysfs_dev_files(z);
-	if (error)
-	    dev_err(&z->dev, "Error creating sysfs files\n");
-    }
+	platform_set_drvdata(pdev, bus);
 
-    /* Mark all available Zorro II memory */
-    zorro_for_each_dev(z) {
-	if (z->rom.er_Type & ERTF_MEMLIST)
-	    mark_region(zorro_resource_start(z), zorro_resource_end(z)+1, 1);
-    }
+	/* Register all devices */
+	pr_info("Zorro: Probing AutoConfig expansion devices: %u device%s\n",
+		 zorro_num_autocon, zorro_num_autocon == 1 ? "" : "s");
 
-    /* Unmark all used Zorro II memory */
-    for (i = 0; i < m68k_num_memory; i++)
-	if (m68k_memory[i].addr < 16*1024*1024)
-	    mark_region(m68k_memory[i].addr,
-			m68k_memory[i].addr+m68k_memory[i].size, 0);
+	for (i = 0; i < zorro_num_autocon; i++) {
+		z = &zorro_autocon[i];
+		z->id = (z->rom.er_Manufacturer<<16) | (z->rom.er_Product<<8);
+		if (z->id == ZORRO_PROD_GVP_EPC_BASE) {
+			/* GVP quirk */
+			unsigned long magic = zorro_resource_start(z)+0x8000;
+			z->id |= *(u16 *)ZTWO_VADDR(magic) & GVP_PRODMASK;
+		}
+		sprintf(z->name, "Zorro device %08x", z->id);
+		zorro_name_device(z);
+		z->resource.name = z->name;
+		r = zorro_find_parent_resource(pdev, z);
+		error = request_resource(r, &z->resource);
+		if (error)
+			dev_err(&bus->dev,
+				"Address space collision on device %s %pR\n",
+				z->name, &z->resource);
+		dev_set_name(&z->dev, "%02x", i);
+		z->dev.parent = &bus->dev;
+		z->dev.bus = &zorro_bus_type;
+		error = device_register(&z->dev);
+		if (error) {
+			dev_err(&bus->dev, "Error registering device %s\n",
+				z->name);
+			continue;
+		}
+		error = zorro_create_sysfs_dev_files(z);
+		if (error)
+			dev_err(&z->dev, "Error creating sysfs files\n");
+	}
 
-    return 0;
+	/* Mark all available Zorro II memory */
+	zorro_for_each_dev(z) {
+		if (z->rom.er_Type & ERTF_MEMLIST)
+			mark_region(zorro_resource_start(z),
+				    zorro_resource_end(z)+1, 1);
+	}
+
+	/* Unmark all used Zorro II memory */
+	for (i = 0; i < m68k_num_memory; i++)
+		if (m68k_memory[i].addr < 16*1024*1024)
+			mark_region(m68k_memory[i].addr,
+				    m68k_memory[i].addr+m68k_memory[i].size,
+				    0);
+
+	return 0;
 }
 
-subsys_initcall(zorro_init);
+static struct platform_driver amiga_zorro_driver = {
+	.driver   = {
+		.name	= "amiga-zorro",
+		.owner	= THIS_MODULE,
+	},
+};
 
-EXPORT_SYMBOL(zorro_find_device);
-EXPORT_SYMBOL(zorro_unused_z2ram);
+static int __init amiga_zorro_init(void)
+{
+	return platform_driver_probe(&amiga_zorro_driver, amiga_zorro_probe);
+}
+
+module_init(amiga_zorro_init);
 
 MODULE_LICENSE("GPL");

fs/autofs4/root.c

diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 109a6c6..e8e5e63 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -177,8 +177,7 @@
 		}
 	/* Trigger mount for path component or follow link */
 	} else if (ino->flags & AUTOFS_INF_PENDING ||
-			autofs4_need_mount(flags) ||
-			current->link_count) {
+			autofs4_need_mount(flags)) {
 		DPRINTK("waiting for mount name=%.*s",
 			dentry->d_name.len, dentry->d_name.name);
 
@@ -262,7 +261,7 @@
 		spin_unlock(&dcache_lock);
 		spin_unlock(&sbi->fs_lock);
 
-		status = try_to_fill_dentry(dentry, 0);
+		status = try_to_fill_dentry(dentry, nd->flags);
 		if (status)
 			goto out_error;
 

fs/btrfs/ioctl.c

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index e84ef60..97a9783 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1481,12 +1481,17 @@
 		ret = -EBADF;
 		goto out_drop_write;
 	}
+
 	src = src_file->f_dentry->d_inode;
 
 	ret = -EINVAL;
 	if (src == inode)
 		goto out_fput;
 
+	/* the src must be open for reading */
+	if (!(src_file->f_mode & FMODE_READ))
+		goto out_fput;
+
 	ret = -EISDIR;
 	if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
 		goto out_fput;

fs/cachefiles/internal.h

diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index f7c255f..a8cd821 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -34,6 +34,7 @@
 	loff_t				i_size;		/* object size */
 	unsigned long			flags;
 #define CACHEFILES_OBJECT_ACTIVE	0		/* T if marked active */
+#define CACHEFILES_OBJECT_BURIED	1		/* T if preemptively buried */
 	atomic_t			usage;		/* object usage count */
 	uint8_t				type;		/* object type */
 	uint8_t				new;		/* T if object new */

fs/cachefiles/namei.c

diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index d5db84a..f4a7840 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -93,6 +93,59 @@
 }
 
 /*
+ * mark the owner of a dentry, if there is one, to indicate that that dentry
+ * has been preemptively deleted
+ * - the caller must hold the i_mutex on the dentry's parent as required to
+ *   call vfs_unlink(), vfs_rmdir() or vfs_rename()
+ */
+static void cachefiles_mark_object_buried(struct cachefiles_cache *cache,
+					  struct dentry *dentry)
+{
+	struct cachefiles_object *object;
+	struct rb_node *p;
+
+	_enter(",'%*.*s'",
+	       dentry->d_name.len, dentry->d_name.len, dentry->d_name.name);
+
+	write_lock(&cache->active_lock);
+
+	p = cache->active_nodes.rb_node;
+	while (p) {
+		object = rb_entry(p, struct cachefiles_object, active_node);
+		if (object->dentry > dentry)
+			p = p->rb_left;
+		else if (object->dentry < dentry)
+			p = p->rb_right;
+		else
+			goto found_dentry;
+	}
+
+	write_unlock(&cache->active_lock);
+	_leave(" [no owner]");
+	return;
+
+	/* found the dentry for  */
+found_dentry:
+	kdebug("preemptive burial: OBJ%x [%s] %p",
+	       object->fscache.debug_id,
+	       fscache_object_states[object->fscache.state],
+	       dentry);
+
+	if (object->fscache.state < FSCACHE_OBJECT_DYING) {
+		printk(KERN_ERR "\n");
+		printk(KERN_ERR "CacheFiles: Error:"
+		       " Can't preemptively bury live object\n");
+		cachefiles_printk_object(object, NULL);
+	} else if (test_and_set_bit(CACHEFILES_OBJECT_BURIED, &object->flags)) {
+		printk(KERN_ERR "CacheFiles: Error:"
+		       " Object already preemptively buried\n");
+	}
+
+	write_unlock(&cache->active_lock);
+	_leave(" [owner marked]");
+}
+
+/*
  * record the fact that an object is now active
  */
 static int cachefiles_mark_object_active(struct cachefiles_cache *cache,
@@ -219,7 +272,8 @@
  */
 static int cachefiles_bury_object(struct cachefiles_cache *cache,
 				  struct dentry *dir,
-				  struct dentry *rep)
+				  struct dentry *rep,
+				  bool preemptive)
 {
 	struct dentry *grave, *trap;
 	char nbuffer[8 + 8 + 1];
@@ -229,11 +283,16 @@
 	       dir->d_name.len, dir->d_name.len, dir->d_name.name,
 	       rep->d_name.len, rep->d_name.len, rep->d_name.name);
 
+	_debug("remove %p from %p", rep, dir);
+
 	/* non-directories can just be unlinked */
 	if (!S_ISDIR(rep->d_inode->i_mode)) {
 		_debug("unlink stale object");
 		ret = vfs_unlink(dir->d_inode, rep);
 
+		if (preemptive)
+			cachefiles_mark_object_buried(cache, rep);
+
 		mutex_unlock(&dir->d_inode->i_mutex);
 
 		if (ret == -EIO)
@@ -325,6 +384,9 @@
 	if (ret != 0 && ret != -ENOMEM)
 		cachefiles_io_error(cache, "Rename failed with error %d", ret);
 
+	if (preemptive)
+		cachefiles_mark_object_buried(cache, rep);
+
 	unlock_rename(cache->graveyard, dir);
 	dput(grave);
 	_leave(" = 0");
@@ -340,7 +402,7 @@
 	struct dentry *dir;
 	int ret;
 
-	_enter(",{%p}", object->dentry);
+	_enter(",OBJ%x{%p}", object->fscache.debug_id, object->dentry);
 
 	ASSERT(object->dentry);
 	ASSERT(object->dentry->d_inode);
@@ -350,15 +412,25 @@
 
 	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
 
-	/* we need to check that our parent is _still_ our parent - it may have
-	 * been renamed */
-	if (dir == object->dentry->d_parent) {
-		ret = cachefiles_bury_object(cache, dir, object->dentry);
-	} else {
-		/* it got moved, presumably by cachefilesd culling it, so it's
-		 * no longer in the key path and we can ignore it */
+	if (test_bit(CACHEFILES_OBJECT_BURIED, &object->flags)) {
+		/* object allocation for the same key preemptively deleted this
+		 * object's file so that it could create its own file */
+		_debug("object preemptively buried");
 		mutex_unlock(&dir->d_inode->i_mutex);
 		ret = 0;
+	} else {
+		/* we need to check that our parent is _still_ our parent - it
+		 * may have been renamed */
+		if (dir == object->dentry->d_parent) {
+			ret = cachefiles_bury_object(cache, dir,
+						     object->dentry, false);
+		} else {
+			/* it got moved, presumably by cachefilesd culling it,
+			 * so it's no longer in the key path and we can ignore
+			 * it */
+			mutex_unlock(&dir->d_inode->i_mutex);
+			ret = 0;
+		}
 	}
 
 	dput(dir);
@@ -381,7 +453,9 @@
 	const char *name;
 	int ret, nlen;
 
-	_enter("{%p},,%s,", parent->dentry, key);
+	_enter("OBJ%x{%p},OBJ%x,%s,",
+	       parent->fscache.debug_id, parent->dentry,
+	       object->fscache.debug_id, key);
 
 	cache = container_of(parent->fscache.cache,
 			     struct cachefiles_cache, cache);
@@ -509,7 +583,7 @@
 			 * mutex) */
 			object->dentry = NULL;
 
-			ret = cachefiles_bury_object(cache, dir, next);
+			ret = cachefiles_bury_object(cache, dir, next, true);
 			dput(next);
 			next = NULL;
 
@@ -828,7 +902,7 @@
 	/*  actually remove the victim (drops the dir mutex) */
 	_debug("bury");
 
-	ret = cachefiles_bury_object(cache, dir, victim);
+	ret = cachefiles_bury_object(cache, dir, victim, false);
 	if (ret < 0)
 		goto error;
 

fs/cachefiles/security.c

diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c
index b5808cd..039b501 100644
--- a/fs/cachefiles/security.c
+++ b/fs/cachefiles/security.c
@@ -77,6 +77,8 @@
 /*
  * check the security details of the on-disk cache
  * - must be called with security override in force
+ * - must return with a security override in force - even in the case of an
+ *   error
  */
 int cachefiles_determine_cache_security(struct cachefiles_cache *cache,
 					struct dentry *root,
@@ -99,6 +101,8 @@
 	 * which create files */
 	ret = set_create_files_as(new, root->d_inode);
 	if (ret < 0) {
+		abort_creds(new);
+		cachefiles_begin_secure(cache, _saved_cred);
 		_leave(" = %d [cfa]", ret);
 		return ret;
 	}

fs/ceph/addr.c

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 4125937..a9005d8 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -504,12 +504,11 @@
 	int i;
 	struct ceph_snap_context *snapc = req->r_snapc;
 	struct address_space *mapping = inode->i_mapping;
-	struct writeback_control *wbc = req->r_wbc;
 	__s32 rc = -EIO;
 	u64 bytes = 0;
 	struct ceph_client *client = ceph_inode_to_client(inode);
 	long writeback_stat;
-	unsigned issued = __ceph_caps_issued(ci, NULL);
+	unsigned issued = ceph_caps_issued(ci);
 
 	/* parse reply */
 	replyhead = msg->front.iov_base;
@@ -546,10 +545,6 @@
 			clear_bdi_congested(&client->backing_dev_info,
 					    BLK_RW_ASYNC);
 
-		if (i >= wrote) {
-			dout("inode %p skipping page %p\n", inode, page);
-			wbc->pages_skipped++;
-		}
 		ceph_put_snap_context((void *)page->private);
 		page->private = 0;
 		ClearPagePrivate(page);
@@ -799,7 +794,6 @@
 				alloc_page_vec(client, req);
 				req->r_callback = writepages_finish;
 				req->r_inode = inode;
-				req->r_wbc = wbc;
 			}
 
 			/* note position of first page in pvec */

fs/ceph/auth.c

diff --git a/fs/ceph/auth.c b/fs/ceph/auth.c
index f6394b9..818afe7 100644
--- a/fs/ceph/auth.c
+++ b/fs/ceph/auth.c
@@ -3,6 +3,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/slab.h>
 
 #include "types.h"
 #include "auth_none.h"

fs/ceph/auth_none.h

diff --git a/fs/ceph/auth_none.h b/fs/ceph/auth_none.h
index 56c0553..8164df1 100644
--- a/fs/ceph/auth_none.h
+++ b/fs/ceph/auth_none.h
@@ -1,6 +1,8 @@
 #ifndef _FS_CEPH_AUTH_NONE_H
 #define _FS_CEPH_AUTH_NONE_H
 
+#include <linux/slab.h>
+
 #include "auth.h"
 
 /*

fs/ceph/auth_x.c

diff --git a/fs/ceph/auth_x.c b/fs/ceph/auth_x.c
index d9001a4..fee5a08d 100644
--- a/fs/ceph/auth_x.c
+++ b/fs/ceph/auth_x.c
@@ -12,8 +12,6 @@
 #include "auth.h"
 #include "decode.h"
 
-struct kmem_cache *ceph_x_ticketbuf_cachep;
-
 #define TEMP_TICKET_BUF_LEN	256
 
 static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed);
@@ -131,13 +129,12 @@
 	char *ticket_buf;
 	u8 struct_v;
 
-	dbuf = kmem_cache_alloc(ceph_x_ticketbuf_cachep, GFP_NOFS | GFP_ATOMIC);
+	dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
 	if (!dbuf)
 		return -ENOMEM;
 
 	ret = -ENOMEM;
-	ticket_buf = kmem_cache_alloc(ceph_x_ticketbuf_cachep,
-				      GFP_NOFS | GFP_ATOMIC);
+	ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
 	if (!ticket_buf)
 		goto out_dbuf;
 
@@ -251,9 +248,9 @@
 
 	ret = 0;
 out:
-	kmem_cache_free(ceph_x_ticketbuf_cachep, ticket_buf);
+	kfree(ticket_buf);
 out_dbuf:
-	kmem_cache_free(ceph_x_ticketbuf_cachep, dbuf);
+	kfree(dbuf);
 	return ret;
 
 bad:
@@ -605,8 +602,6 @@
 		remove_ticket_handler(ac, th);
 	}
 
-	kmem_cache_destroy(ceph_x_ticketbuf_cachep);
-
 	kfree(ac->private);
 	ac->private = NULL;
 }
@@ -641,26 +636,20 @@
 	int ret;
 
 	dout("ceph_x_init %p\n", ac);
+	ret = -ENOMEM;
 	xi = kzalloc(sizeof(*xi), GFP_NOFS);
 	if (!xi)
-		return -ENOMEM;
+		goto out;
 
-	ret = -ENOMEM;
-	ceph_x_ticketbuf_cachep = kmem_cache_create("ceph_x_ticketbuf",
-				      TEMP_TICKET_BUF_LEN, 8,
-				      (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD),
-				      NULL);
-	if (!ceph_x_ticketbuf_cachep)
-		goto done_nomem;
 	ret = -EINVAL;
 	if (!ac->secret) {
 		pr_err("no secret set (for auth_x protocol)\n");
-		goto done_nomem;
+		goto out_nomem;
 	}
 
 	ret = ceph_crypto_key_unarmor(&xi->secret, ac->secret);
 	if (ret)
-		goto done_nomem;
+		goto out_nomem;
 
 	xi->starting = true;
 	xi->ticket_handlers = RB_ROOT;
@@ -670,10 +659,9 @@
 	ac->ops = &ceph_x_ops;
 	return 0;
 
-done_nomem:
+out_nomem:
 	kfree(xi);
-	if (ceph_x_ticketbuf_cachep)
-		kmem_cache_destroy(ceph_x_ticketbuf_cachep);
+out:
 	return ret;
 }
 

fs/ceph/caps.c

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index aa2239f..d940053 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -858,6 +858,8 @@
 }
 
 /*
+ * Remove a cap.  Take steps to deal with a racing iterate_session_caps.
+ *
  * caller should hold i_lock.
  * caller will not hold session s_mutex if called from destroy_inode.
  */
@@ -866,15 +868,10 @@
 	struct ceph_mds_session *session = cap->session;
 	struct ceph_inode_info *ci = cap->ci;
 	struct ceph_mds_client *mdsc = &ceph_client(ci->vfs_inode.i_sb)->mdsc;
+	int removed = 0;
 
 	dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
 
-	/* remove from inode list */
-	rb_erase(&cap->ci_node, &ci->i_caps);
-	cap->ci = NULL;
-	if (ci->i_auth_cap == cap)
-		ci->i_auth_cap = NULL;
-
 	/* remove from session list */
 	spin_lock(&session->s_cap_lock);
 	if (session->s_cap_iterator == cap) {
@@ -885,10 +882,18 @@
 		list_del_init(&cap->session_caps);
 		session->s_nr_caps--;
 		cap->session = NULL;
+		removed = 1;
 	}
+	/* protect backpointer with s_cap_lock: see iterate_session_caps */
+	cap->ci = NULL;
 	spin_unlock(&session->s_cap_lock);
 
-	if (cap->session == NULL)
+	/* remove from inode list */
+	rb_erase(&cap->ci_node, &ci->i_caps);
+	if (ci->i_auth_cap == cap)
+		ci->i_auth_cap = NULL;
+
+	if (removed)
 		ceph_put_cap(cap);
 
 	if (!__ceph_is_any_caps(ci) && ci->i_snap_realm) {
@@ -1861,8 +1866,8 @@
 		} else {
 			pr_err("%p auth cap %p not mds%d ???\n", inode,
 			       cap, session->s_mds);
-			spin_unlock(&inode->i_lock);
 		}
+		spin_unlock(&inode->i_lock);
 	}
 }
 

fs/ceph/dir.c

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index ea8ee2e..650d2db 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -880,7 +880,16 @@
 		 * do_request, above).  If there is no trace, we need
 		 * to do it here.
 		 */
+
+		/* d_move screws up d_subdirs order */
+		ceph_i_clear(new_dir, CEPH_I_COMPLETE);
+
 		d_move(old_dentry, new_dentry);
+
+		/* ensure target dentry is invalidated, despite
+		   rehashing bug in vfs_rename_dir */
+		new_dentry->d_time = jiffies;
+		ceph_dentry(new_dentry)->lease_shared_gen = 0;
 	}
 	ceph_mdsc_put_request(req);
 	return err;

fs/ceph/file.c

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 4add3d5..ed6f197 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -665,7 +665,8 @@
 		 * throw out any page cache pages in this range. this
 		 * may block.
 		 */
-		truncate_inode_pages_range(inode->i_mapping, pos, pos+len);
+		truncate_inode_pages_range(inode->i_mapping, pos, 
+					   (pos+len) | (PAGE_CACHE_SIZE-1));
 	} else {
 		pages = alloc_page_vector(num_pages);
 		if (IS_ERR(pages)) {

fs/ceph/inode.c

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 26f883c..85b4d2f 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -733,6 +733,10 @@
 				__ceph_get_fmode(ci, cap_fmode);
 			spin_unlock(&inode->i_lock);
 		}
+	} else if (cap_fmode >= 0) {
+		pr_warning("mds issued no caps on %llx.%llx\n",
+			   ceph_vinop(inode));
+		__ceph_get_fmode(ci, cap_fmode);
 	}
 
 	/* update delegation info? */
@@ -997,6 +1001,10 @@
 			     dn, dn->d_name.len, dn->d_name.name);
 			dout("fill_trace doing d_move %p -> %p\n",
 			     req->r_old_dentry, dn);
+
+			/* d_move screws up d_subdirs order */
+			ceph_i_clear(dir, CEPH_I_COMPLETE);
+
 			d_move(req->r_old_dentry, dn);
 			dout(" src %p '%.*s' dst %p '%.*s'\n",
 			     req->r_old_dentry,

fs/ceph/mds_client.c

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 60a9a4a..24561a5 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -736,9 +736,10 @@
 }
 
 /*
- * Helper to safely iterate over all caps associated with a session.
+ * Helper to safely iterate over all caps associated with a session, with
+ * special care taken to handle a racing __ceph_remove_cap().
  *
- * caller must hold session s_mutex
+ * Caller must hold session s_mutex.
  */
 static int iterate_session_caps(struct ceph_mds_session *session,
 				 int (*cb)(struct inode *, struct ceph_cap *,
@@ -2136,7 +2137,7 @@
 	struct ceph_mds_session *session = NULL;
 	struct ceph_msg *reply;
 	struct rb_node *p;
-	int err;
+	int err = -ENOMEM;
 	struct ceph_pagelist *pagelist;
 
 	pr_info("reconnect to recovering mds%d\n", mds);
@@ -2185,7 +2186,7 @@
 		goto fail;
 	err = iterate_session_caps(session, encode_caps_cb, pagelist);
 	if (err < 0)
-		goto out;
+		goto fail;
 
 	/*
 	 * snaprealms.  we provide mds with the ino, seq (version), and
@@ -2213,28 +2214,31 @@
 	reply->nr_pages = calc_pages_for(0, pagelist->length);
 	ceph_con_send(&session->s_con, reply);
 
-	if (session) {
-		session->s_state = CEPH_MDS_SESSION_OPEN;
-		__wake_requests(mdsc, &session->s_waiting);
-	}
+	session->s_state = CEPH_MDS_SESSION_OPEN;
+	mutex_unlock(&session->s_mutex);
 
-out:
+	mutex_lock(&mdsc->mutex);
+	__wake_requests(mdsc, &session->s_waiting);
+	mutex_unlock(&mdsc->mutex);
+
+	ceph_put_mds_session(session);
+
 	up_read(&mdsc->snap_rwsem);
-	if (session) {
-		mutex_unlock(&session->s_mutex);
-		ceph_put_mds_session(session);
-	}
 	mutex_lock(&mdsc->mutex);
 	return;
 
 fail:
 	ceph_msg_put(reply);
+	up_read(&mdsc->snap_rwsem);
+	mutex_unlock(&session->s_mutex);
+	ceph_put_mds_session(session);
 fail_nomsg:
 	ceph_pagelist_release(pagelist);
 	kfree(pagelist);
 fail_nopagelist:
-	pr_err("ENOMEM preparing reconnect for mds%d\n", mds);
-	goto out;
+	pr_err("error %d preparing reconnect for mds%d\n", err, mds);
+	mutex_lock(&mdsc->mutex);
+	return;
 }
 
 

fs/ceph/messenger.c

diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c
index cdaaa13..cd4fadb 100644
--- a/fs/ceph/messenger.c
+++ b/fs/ceph/messenger.c
@@ -492,7 +492,14 @@
 		list_move_tail(&m->list_head, &con->out_sent);
 	}
 
-	m->hdr.seq = cpu_to_le64(++con->out_seq);
+	/*
+	 * only assign outgoing seq # if we haven't sent this message
+	 * yet.  if it is requeued, resend with it's original seq.
+	 */
+	if (m->needs_out_seq) {
+		m->hdr.seq = cpu_to_le64(++con->out_seq);
+		m->needs_out_seq = false;
+	}
 
 	dout("prepare_write_message %p seq %lld type %d len %d+%d+%d %d pgs\n",
 	     m, con->out_seq, le16_to_cpu(m->hdr.type),
@@ -1334,6 +1341,7 @@
 	unsigned front_len, middle_len, data_len, data_off;
 	int datacrc = con->msgr->nocrc;
 	int skip;
+	u64 seq;
 
 	dout("read_partial_message con %p msg %p\n", con, m);
 
@@ -1368,6 +1376,25 @@
 		return -EIO;
 	data_off = le16_to_cpu(con->in_hdr.data_off);
 
+	/* verify seq# */
+	seq = le64_to_cpu(con->in_hdr.seq);
+	if ((s64)seq - (s64)con->in_seq < 1) {
+		pr_info("skipping %s%lld %s seq %lld, expected %lld\n",
+			ENTITY_NAME(con->peer_name),
+			pr_addr(&con->peer_addr.in_addr),
+			seq, con->in_seq + 1);
+		con->in_base_pos = -front_len - middle_len - data_len -
+			sizeof(m->footer);
+		con->in_tag = CEPH_MSGR_TAG_READY;
+		con->in_seq++;
+		return 0;
+	} else if ((s64)seq - (s64)con->in_seq > 1) {
+		pr_err("read_partial_message bad seq %lld expected %lld\n",
+		       seq, con->in_seq + 1);
+		con->error_msg = "bad message sequence # for incoming message";
+		return -EBADMSG;
+	}
+
 	/* allocate message? */
 	if (!con->in_msg) {
 		dout("got hdr type %d front %d data %d\n", con->in_hdr.type,
@@ -1379,6 +1406,7 @@
 			con->in_base_pos = -front_len - middle_len - data_len -
 				sizeof(m->footer);
 			con->in_tag = CEPH_MSGR_TAG_READY;
+			con->in_seq++;
 			return 0;
 		}
 		if (IS_ERR(con->in_msg)) {
@@ -1965,6 +1993,8 @@
 
 	BUG_ON(msg->front.iov_len != le32_to_cpu(msg->hdr.front_len));
 
+	msg->needs_out_seq = true;
+
 	/* queue */
 	mutex_lock(&con->mutex);
 	BUG_ON(!list_empty(&msg->list_head));
@@ -2030,6 +2060,7 @@
 		ceph_msg_put(con->in_msg);
 		con->in_msg = NULL;
 		con->in_tag = CEPH_MSGR_TAG_READY;
+		con->in_seq++;
 	} else {
 		dout("con_revoke_pages %p msg %p pages %p no-op\n",
 		     con, con->in_msg, msg);
@@ -2063,15 +2094,19 @@
 	kref_init(&m->kref);
 	INIT_LIST_HEAD(&m->list_head);
 
+	m->hdr.tid = 0;
 	m->hdr.type = cpu_to_le16(type);
+	m->hdr.priority = cpu_to_le16(CEPH_MSG_PRIO_DEFAULT);
+	m->hdr.version = 0;
 	m->hdr.front_len = cpu_to_le32(front_len);
 	m->hdr.middle_len = 0;
 	m->hdr.data_len = cpu_to_le32(page_len);
 	m->hdr.data_off = cpu_to_le16(page_off);
-	m->hdr.priority = cpu_to_le16(CEPH_MSG_PRIO_DEFAULT);
+	m->hdr.reserved = 0;
 	m->footer.front_crc = 0;
 	m->footer.middle_crc = 0;
 	m->footer.data_crc = 0;
+	m->footer.flags = 0;
 	m->front_max = front_len;
 	m->front_is_vmalloc = false;
 	m->more_to_follow = false;

fs/ceph/messenger.h

diff --git a/fs/ceph/messenger.h b/fs/ceph/messenger.h
index a343dae..a5caf91 100644
--- a/fs/ceph/messenger.h
+++ b/fs/ceph/messenger.h
@@ -86,6 +86,7 @@
 	struct kref kref;
 	bool front_is_vmalloc;
 	bool more_to_follow;
+	bool needs_out_seq;
 	int front_max;
 
 	struct ceph_msgpool *pool;

fs/ceph/osd_client.c

diff --git a/fs/ceph/osd_client.c b/fs/ceph/osd_client.c
index c7b4ded..3514f71 100644
--- a/fs/ceph/osd_client.c
+++ b/fs/ceph/osd_client.c
@@ -565,7 +565,8 @@
 {
 	struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
 	struct ceph_pg pgid;
-	int o = -1;
+	int acting[CEPH_PG_MAX_SIZE];
+	int o = -1, num = 0;
 	int err;
 
 	dout("map_osds %p tid %lld\n", req, req->r_tid);
@@ -576,10 +577,16 @@
 	pgid = reqhead->layout.ol_pgid;
 	req->r_pgid = pgid;
 
-	o = ceph_calc_pg_primary(osdc->osdmap, pgid);
+	err = ceph_calc_pg_acting(osdc->osdmap, pgid, acting);
+	if (err > 0) {
+		o = acting[0];
+		num = err;
+	}
 
 	if ((req->r_osd && req->r_osd->o_osd == o &&
-	     req->r_sent >= req->r_osd->o_incarnation) ||
+	     req->r_sent >= req->r_osd->o_incarnation &&
+	     req->r_num_pg_osds == num &&
+	     memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) ||
 	    (req->r_osd == NULL && o == -1))
 		return 0;  /* no change */
 
@@ -587,6 +594,10 @@
 	     req->r_tid, le32_to_cpu(pgid.pool), le16_to_cpu(pgid.ps), o,
 	     req->r_osd ? req->r_osd->o_osd : -1);
 
+	/* record full pg acting set */
+	memcpy(req->r_pg_osds, acting, sizeof(acting[0]) * num);
+	req->r_num_pg_osds = num;
+
 	if (req->r_osd) {
 		__cancel_request(req);
 		list_del_init(&req->r_osd_item);
@@ -612,7 +623,7 @@
 		__remove_osd_from_lru(req->r_osd);
 		list_add(&req->r_osd_item, &req->r_osd->o_requests);
 	}
-	err = 1;   /* osd changed */
+	err = 1;   /* osd or pg changed */
 
 out:
 	return err;
@@ -779,16 +790,18 @@
 	struct ceph_osd_request *req;
 	u64 tid;
 	int numops, object_len, flags;
+	s32 result;
 
 	tid = le64_to_cpu(msg->hdr.tid);
 	if (msg->front.iov_len < sizeof(*rhead))
 		goto bad;
 	numops = le32_to_cpu(rhead->num_ops);
 	object_len = le32_to_cpu(rhead->object_len);
+	result = le32_to_cpu(rhead->result);
 	if (msg->front.iov_len != sizeof(*rhead) + object_len +
 	    numops * sizeof(struct ceph_osd_op))
 		goto bad;
-	dout("handle_reply %p tid %llu\n", msg, tid);
+	dout("handle_reply %p tid %llu result %d\n", msg, tid, (int)result);
 
 	/* lookup */
 	mutex_lock(&osdc->request_mutex);
@@ -834,7 +847,8 @@
 	dout("handle_reply tid %llu flags %d\n", tid, flags);
 
 	/* either this is a read, or we got the safe response */
-	if ((flags & CEPH_OSD_FLAG_ONDISK) ||
+	if (result < 0 ||
+	    (flags & CEPH_OSD_FLAG_ONDISK) ||
 	    ((flags & CEPH_OSD_FLAG_WRITE) == 0))
 		__unregister_request(osdc, req);
 

fs/ceph/osd_client.h

diff --git a/fs/ceph/osd_client.h b/fs/ceph/osd_client.h
index b075991..ce77698 100644
--- a/fs/ceph/osd_client.h
+++ b/fs/ceph/osd_client.h
@@ -48,6 +48,8 @@
 	struct list_head r_osd_item;
 	struct ceph_osd *r_osd;
 	struct ceph_pg   r_pgid;
+	int              r_pg_osds[CEPH_PG_MAX_SIZE];
+	int              r_num_pg_osds;
 
 	struct ceph_connection *r_con_filling_msg;
 
@@ -66,7 +68,6 @@
 	struct list_head  r_unsafe_item;
 
 	struct inode *r_inode;         	      /* for use by callbacks */
-	struct writeback_control *r_wbc;      /* ditto */
 
 	char              r_oid[40];          /* object name */
 	int               r_oid_len;

fs/ceph/osdmap.c

diff --git a/fs/ceph/osdmap.c b/fs/ceph/osdmap.c
index 2e2c15e..cfdd8f4 100644
--- a/fs/ceph/osdmap.c
+++ b/fs/ceph/osdmap.c
@@ -1041,12 +1041,33 @@
 }
 
 /*
+ * Return acting set for given pgid.
+ */
+int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
+			int *acting)
+{
+	int rawosds[CEPH_PG_MAX_SIZE], *osds;
+	int i, o, num = CEPH_PG_MAX_SIZE;
+
+	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
+	if (!osds)
+		return -1;
+
+	/* primary is first up osd */
+	o = 0;
+	for (i = 0; i < num; i++)
+		if (ceph_osd_is_up(osdmap, osds[i]))
+			acting[o++] = osds[i];
+	return o;
+}
+
+/*
  * Return primary osd for given pgid, or -1 if none.
  */
 int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
 {
-	int rawosds[10], *osds;
-	int i, num = ARRAY_SIZE(rawosds);
+	int rawosds[CEPH_PG_MAX_SIZE], *osds;
+	int i, num = CEPH_PG_MAX_SIZE;
 
 	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
 	if (!osds)
@@ -1054,9 +1075,7 @@
 
 	/* primary is first up osd */
 	for (i = 0; i < num; i++)
-		if (ceph_osd_is_up(osdmap, osds[i])) {
+		if (ceph_osd_is_up(osdmap, osds[i]))
 			return osds[i];
-			break;
-		}
 	return -1;
 }

fs/ceph/osdmap.h

diff --git a/fs/ceph/osdmap.h b/fs/ceph/osdmap.h
index 8bc9f1e..970b547 100644
--- a/fs/ceph/osdmap.h
+++ b/fs/ceph/osdmap.h
@@ -120,6 +120,8 @@
 				   const char *oid,
 				   struct ceph_file_layout *fl,
 				   struct ceph_osdmap *osdmap);
+extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
+			       int *acting);
 extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
 				struct ceph_pg pgid);
 

fs/ceph/rados.h

diff --git a/fs/ceph/rados.h b/fs/ceph/rados.h
index a1fc1d0..fd56451 100644
--- a/fs/ceph/rados.h
+++ b/fs/ceph/rados.h
@@ -58,6 +58,7 @@
 #define CEPH_PG_LAYOUT_LINEAR 2
 #define CEPH_PG_LAYOUT_HYBRID 3
 
+#define CEPH_PG_MAX_SIZE      16  /* max # osds in a single pg */
 
 /*
  * placement group.

fs/ceph/snap.c

diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 2b88126..d5114db 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -869,16 +869,20 @@
 				continue;
 			ci = ceph_inode(inode);
 			spin_lock(&inode->i_lock);
-			if (!ci->i_snap_realm)
-				goto split_skip_inode;
-			ceph_put_snap_realm(mdsc, ci->i_snap_realm);
-			spin_lock(&realm->inodes_with_caps_lock);
-			list_add(&ci->i_snap_realm_item,
-				 &realm->inodes_with_caps);
-			ci->i_snap_realm = realm;
-			spin_unlock(&realm->inodes_with_caps_lock);
-			ceph_get_snap_realm(mdsc, realm);
-split_skip_inode:
+			if (list_empty(&ci->i_snap_realm_item)) {
+				struct ceph_snap_realm *oldrealm =
+					ci->i_snap_realm;
+
+				dout(" moving %p to split realm %llx %p\n",
+				     inode, realm->ino, realm);
+				spin_lock(&realm->inodes_with_caps_lock);
+				list_add(&ci->i_snap_realm_item,
+					 &realm->inodes_with_caps);
+				ci->i_snap_realm = realm;
+				spin_unlock(&realm->inodes_with_caps_lock);
+				ceph_get_snap_realm(mdsc, realm);
+				ceph_put_snap_realm(mdsc, oldrealm);
+			}
 			spin_unlock(&inode->i_lock);
 			iput(inode);
 		}

fs/ceph/super.c

diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 75d02ea..110857b 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -47,10 +47,20 @@
  */
 static void ceph_put_super(struct super_block *s)
 {
-	struct ceph_client *cl = ceph_client(s);
+	struct ceph_client *client = ceph_sb_to_client(s);
 
 	dout("put_super\n");
-	ceph_mdsc_close_sessions(&cl->mdsc);
+	ceph_mdsc_close_sessions(&client->mdsc);
+
+	/*
+	 * ensure we release the bdi before put_anon_super releases
+	 * the device name.
+	 */
+	if (s->s_bdi == &client->backing_dev_info) {
+		bdi_unregister(&client->backing_dev_info);
+		s->s_bdi = NULL;
+	}
+
 	return;
 }
 
@@ -636,6 +646,8 @@
 	destroy_workqueue(client->pg_inv_wq);
 	destroy_workqueue(client->trunc_wq);
 
+	bdi_destroy(&client->backing_dev_info);
+
 	if (client->msgr)
 		ceph_messenger_destroy(client->msgr);
 	mempool_destroy(client->wb_pagevec_pool);
@@ -876,14 +888,14 @@
 {
 	int err;
 
-	sb->s_bdi = &client->backing_dev_info;
-
 	/* set ra_pages based on rsize mount option? */
 	if (client->mount_args->rsize >= PAGE_CACHE_SIZE)
 		client->backing_dev_info.ra_pages =
 			(client->mount_args->rsize + PAGE_CACHE_SIZE - 1)
 			>> PAGE_SHIFT;
 	err = bdi_register_dev(&client->backing_dev_info, sb->s_dev);
+	if (!err)
+		sb->s_bdi = &client->backing_dev_info;
 	return err;
 }
 
@@ -957,9 +969,6 @@
 	dout("kill_sb %p\n", s);
 	ceph_mdsc_pre_umount(&client->mdsc);
 	kill_anon_super(s);    /* will call put_super after sb is r/o */
-	if (s->s_bdi == &client->backing_dev_info)
-		bdi_unregister(&client->backing_dev_info);
-	bdi_destroy(&client->backing_dev_info);
 	ceph_destroy_client(client);
 }
 
@@ -996,9 +1005,10 @@
 	if (ret)
 		goto out_icache;
 
-	pr_info("loaded %d.%d.%d (mon/mds/osd proto %d/%d/%d)\n",
-		CEPH_VERSION_MAJOR, CEPH_VERSION_MINOR, CEPH_VERSION_PATCH,
-		CEPH_MONC_PROTOCOL, CEPH_MDSC_PROTOCOL, CEPH_OSDC_PROTOCOL);
+	pr_info("loaded (mon/mds/osd proto %d/%d/%d, osdmap %d/%d %d/%d)\n",
+		CEPH_MONC_PROTOCOL, CEPH_MDSC_PROTOCOL, CEPH_OSDC_PROTOCOL,
+		CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT,
+		CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT);
 	return 0;
 
 out_icache:

fs/ceph/super.h

diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index e30dfbb..13513b8 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -10,6 +10,7 @@
 #include <linux/fs.h>
 #include <linux/mempool.h>
 #include <linux/pagemap.h>
+#include <linux/slab.h>
 #include <linux/wait.h>
 #include <linux/writeback.h>
 #include <linux/slab.h>

fs/cifs/asn1.c

diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c
index a20bea5..cfd1ce3 100644
--- a/fs/cifs/asn1.c
+++ b/fs/cifs/asn1.c
@@ -492,17 +492,13 @@
 
 int
 decode_negTokenInit(unsigned char *security_blob, int length,
-		    enum securityEnum *secType)
+		    struct TCP_Server_Info *server)
 {
 	struct asn1_ctx ctx;
 	unsigned char *end;
 	unsigned char *sequence_end;
 	unsigned long *oid = NULL;
 	unsigned int cls, con, tag, oidlen, rc;
-	bool use_ntlmssp = false;
-	bool use_kerberos = false;
-	bool use_kerberosu2u = false;
-	bool use_mskerberos = false;
 
 	/* cifs_dump_mem(" Received SecBlob ", security_blob, length); */
 
@@ -510,11 +506,11 @@
 
 	/* GSSAPI header */
 	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, ("Error decoding negTokenInit header"));
+		cFYI(1, "Error decoding negTokenInit header");
 		return 0;
 	} else if ((cls != ASN1_APL) || (con != ASN1_CON)
 		   || (tag != ASN1_EOC)) {
-		cFYI(1, ("cls = %d con = %d tag = %d", cls, con, tag));
+		cFYI(1, "cls = %d con = %d tag = %d", cls, con, tag);
 		return 0;
 	}
 
@@ -535,56 +531,52 @@
 
 	/* SPNEGO OID not present or garbled -- bail out */
 	if (!rc) {
-		cFYI(1, ("Error decoding negTokenInit header"));
+		cFYI(1, "Error decoding negTokenInit header");
 		return 0;
 	}
 
 	/* SPNEGO */
 	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, ("Error decoding negTokenInit"));
+		cFYI(1, "Error decoding negTokenInit");
 		return 0;
 	} else if ((cls != ASN1_CTX) || (con != ASN1_CON)
 		   || (tag != ASN1_EOC)) {
-		cFYI(1,
-		     ("cls = %d con = %d tag = %d end = %p (%d) exit 0",
-		      cls, con, tag, end, *end));
+		cFYI(1, "cls = %d con = %d tag = %d end = %p (%d) exit 0",
+		     cls, con, tag, end, *end);
 		return 0;
 	}
 
 	/* negTokenInit */
 	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, ("Error decoding negTokenInit"));
+		cFYI(1, "Error decoding negTokenInit");
 		return 0;
 	} else if ((cls != ASN1_UNI) || (con != ASN1_CON)
 		   || (tag != ASN1_SEQ)) {
-		cFYI(1,
-		     ("cls = %d con = %d tag = %d end = %p (%d) exit 1",
-		      cls, con, tag, end, *end));
+		cFYI(1, "cls = %d con = %d tag = %d end = %p (%d) exit 1",
+		     cls, con, tag, end, *end);
 		return 0;
 	}
 
 	/* sequence */
 	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, ("Error decoding 2nd part of negTokenInit"));
+		cFYI(1, "Error decoding 2nd part of negTokenInit");
 		return 0;
 	} else if ((cls != ASN1_CTX) || (con != ASN1_CON)
 		   || (tag != ASN1_EOC)) {
-		cFYI(1,
-		     ("cls = %d con = %d tag = %d end = %p (%d) exit 0",
-		      cls, con, tag, end, *end));
+		cFYI(1, "cls = %d con = %d tag = %d end = %p (%d) exit 0",
+		     cls, con, tag, end, *end);
 		return 0;
 	}
 
 	/* sequence of */
 	if (asn1_header_decode
 	    (&ctx, &sequence_end, &cls, &con, &tag) == 0) {
-		cFYI(1, ("Error decoding 2nd part of negTokenInit"));
+		cFYI(1, "Error decoding 2nd part of negTokenInit");
 		return 0;
 	} else if ((cls != ASN1_UNI) || (con != ASN1_CON)
 		   || (tag != ASN1_SEQ)) {
-		cFYI(1,
-		     ("cls = %d con = %d tag = %d end = %p (%d) exit 1",
-		      cls, con, tag, end, *end));
+		cFYI(1, "cls = %d con = %d tag = %d end = %p (%d) exit 1",
+		     cls, con, tag, end, *end);
 		return 0;
 	}
 
@@ -592,37 +584,33 @@
 	while (!asn1_eoc_decode(&ctx, sequence_end)) {
 		rc = asn1_header_decode(&ctx, &end, &cls, &con, &tag);
 		if (!rc) {
-			cFYI(1,
-			     ("Error decoding negTokenInit hdr exit2"));
+			cFYI(1, "Error decoding negTokenInit hdr exit2");
 			return 0;
 		}
 		if ((tag == ASN1_OJI) && (con == ASN1_PRI)) {
 			if (asn1_oid_decode(&ctx, end, &oid, &oidlen)) {
 
-				cFYI(1, ("OID len = %d oid = 0x%lx 0x%lx "
-					 "0x%lx 0x%lx", oidlen, *oid,
-					 *(oid + 1), *(oid + 2), *(oid + 3)));
+				cFYI(1, "OID len = %d oid = 0x%lx 0x%lx "
+					"0x%lx 0x%lx", oidlen, *oid,
+					*(oid + 1), *(oid + 2), *(oid + 3));
 
 				if (compare_oid(oid, oidlen, MSKRB5_OID,
-						MSKRB5_OID_LEN) &&
-						!use_mskerberos)
-					use_mskerberos = true;
+						MSKRB5_OID_LEN))
+					server->sec_mskerberos = true;
 				else if (compare_oid(oid, oidlen, KRB5U2U_OID,
-						     KRB5U2U_OID_LEN) &&
-						     !use_kerberosu2u)
-					use_kerberosu2u = true;
+						     KRB5U2U_OID_LEN))
+					server->sec_kerberosu2u = true;
 				else if (compare_oid(oid, oidlen, KRB5_OID,
-						     KRB5_OID_LEN) &&
-						     !use_kerberos)
-					use_kerberos = true;
+						     KRB5_OID_LEN))
+					server->sec_kerberos = true;
 				else if (compare_oid(oid, oidlen, NTLMSSP_OID,
 						     NTLMSSP_OID_LEN))
-					use_ntlmssp = true;
+					server->sec_ntlmssp = true;
 
 				kfree(oid);
 			}
 		} else {
-			cFYI(1, ("Should be an oid what is going on?"));
+			cFYI(1, "Should be an oid what is going on?");
 		}
 	}
 
@@ -632,54 +620,47 @@
 		   no mechListMic (e.g. NTLMSSP instead of KRB5) */
 		if (ctx.error == ASN1_ERR_DEC_EMPTY)
 			goto decode_negtoken_exit;
-		cFYI(1, ("Error decoding last part negTokenInit exit3"));
+		cFYI(1, "Error decoding last part negTokenInit exit3");
 		return 0;
 	} else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
 		/* tag = 3 indicating mechListMIC */
-		cFYI(1, ("Exit 4 cls = %d con = %d tag = %d end = %p (%d)",
-			 cls, con, tag, end, *end));
+		cFYI(1, "Exit 4 cls = %d con = %d tag = %d end = %p (%d)",
+			cls, con, tag, end, *end);
 		return 0;
 	}
 
 	/* sequence */
 	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, ("Error decoding last part negTokenInit exit5"));
+		cFYI(1, "Error decoding last part negTokenInit exit5");
 		return 0;
 	} else if ((cls != ASN1_UNI) || (con != ASN1_CON)
 		   || (tag != ASN1_SEQ)) {
-		cFYI(1, ("cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end));
+		cFYI(1, "cls = %d con = %d tag = %d end = %p (%d)",
+			cls, con, tag, end, *end);
 	}
 
 	/* sequence of */
 	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, ("Error decoding last part negTokenInit exit 7"));
+		cFYI(1, "Error decoding last part negTokenInit exit 7");
 		return 0;
 	} else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
-		cFYI(1, ("Exit 8 cls = %d con = %d tag = %d end = %p (%d)",
-			 cls, con, tag, end, *end));
+		cFYI(1, "Exit 8 cls = %d con = %d tag = %d end = %p (%d)",
+			cls, con, tag, end, *end);
 		return 0;
 	}
 
 	/* general string */
 	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, ("Error decoding last part negTokenInit exit9"));
+		cFYI(1, "Error decoding last part negTokenInit exit9");
 		return 0;
 	} else if ((cls != ASN1_UNI) || (con != ASN1_PRI)
 		   || (tag != ASN1_GENSTR)) {
-		cFYI(1, ("Exit10 cls = %d con = %d tag = %d end = %p (%d)",
-			 cls, con, tag, end, *end));
+		cFYI(1, "Exit10 cls = %d con = %d tag = %d end = %p (%d)",
+			cls, con, tag, end, *end);
 		return 0;
 	}
-	cFYI(1, ("Need to call asn1_octets_decode() function for %s",
-		 ctx.pointer));	/* is this UTF-8 or ASCII? */
+	cFYI(1, "Need to call asn1_octets_decode() function for %s",
+		ctx.pointer);	/* is this UTF-8 or ASCII? */
 decode_negtoken_exit:
-	if (use_kerberos)
-		*secType = Kerberos;
-	else if (use_mskerberos)
-		*secType = MSKerberos;
-	else if (use_ntlmssp)
-		*secType = RawNTLMSSP;
-
 	return 1;
 }

fs/cifs/cifs_debug.c

diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 42cec2a..4fce6e6 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -60,10 +60,10 @@
 #ifdef CONFIG_CIFS_DEBUG2
 void cifs_dump_detail(struct smb_hdr *smb)
 {
-	cERROR(1, ("Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d",
+	cERROR(1, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d",
 		  smb->Command, smb->Status.CifsError,
-		  smb->Flags, smb->Flags2, smb->Mid, smb->Pid));
-	cERROR(1, ("smb buf %p len %d", smb, smbCalcSize_LE(smb)));
+		  smb->Flags, smb->Flags2, smb->Mid, smb->Pid);
+	cERROR(1, "smb buf %p len %d", smb, smbCalcSize_LE(smb));
 }
 
 
@@ -75,25 +75,25 @@
 	if (server == NULL)
 		return;
 
-	cERROR(1, ("Dump pending requests:"));
+	cERROR(1, "Dump pending requests:");
 	spin_lock(&GlobalMid_Lock);
 	list_for_each(tmp, &server->pending_mid_q) {
 		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-		cERROR(1, ("State: %d Cmd: %d Pid: %d Tsk: %p Mid %d",
+		cERROR(1, "State: %d Cmd: %d Pid: %d Tsk: %p Mid %d",
 			mid_entry->midState,
 			(int)mid_entry->command,
 			mid_entry->pid,
 			mid_entry->tsk,
-			mid_entry->mid));
+			mid_entry->mid);
 #ifdef CONFIG_CIFS_STATS2
-		cERROR(1, ("IsLarge: %d buf: %p time rcv: %ld now: %ld",
+		cERROR(1, "IsLarge: %d buf: %p time rcv: %ld now: %ld",
 			mid_entry->largeBuf,
 			mid_entry->resp_buf,
 			mid_entry->when_received,
-			jiffies));
+			jiffies);
 #endif /* STATS2 */
-		cERROR(1, ("IsMult: %d IsEnd: %d", mid_entry->multiRsp,
-			  mid_entry->multiEnd));
+		cERROR(1, "IsMult: %d IsEnd: %d", mid_entry->multiRsp,
+			  mid_entry->multiEnd);
 		if (mid_entry->resp_buf) {
 			cifs_dump_detail(mid_entry->resp_buf);
 			cifs_dump_mem("existing buf: ",
@@ -716,7 +716,7 @@
 
 static int cifs_security_flags_proc_show(struct seq_file *m, void *v)
 {
-	seq_printf(m, "0x%x\n", extended_security);
+	seq_printf(m, "0x%x\n", global_secflags);
 	return 0;
 }
 
@@ -744,13 +744,13 @@
 		/* single char or single char followed by null */
 		c = flags_string[0];
 		if (c == '0' || c == 'n' || c == 'N') {
-			extended_security = CIFSSEC_DEF; /* default */
+			global_secflags = CIFSSEC_DEF; /* default */
 			return count;
 		} else if (c == '1' || c == 'y' || c == 'Y') {
-			extended_security = CIFSSEC_MAX;
+			global_secflags = CIFSSEC_MAX;
 			return count;
 		} else if (!isdigit(c)) {
-			cERROR(1, ("invalid flag %c", c));
+			cERROR(1, "invalid flag %c", c);
 			return -EINVAL;
 		}
 	}
@@ -758,26 +758,26 @@
 
 	flags = simple_strtoul(flags_string, NULL, 0);
 
-	cFYI(1, ("sec flags 0x%x", flags));
+	cFYI(1, "sec flags 0x%x", flags);
 
 	if (flags <= 0)  {
-		cERROR(1, ("invalid security flags %s", flags_string));
+		cERROR(1, "invalid security flags %s", flags_string);
 		return -EINVAL;
 	}
 
 	if (flags & ~CIFSSEC_MASK) {
-		cERROR(1, ("attempt to set unsupported security flags 0x%x",
-			flags & ~CIFSSEC_MASK));
+		cERROR(1, "attempt to set unsupported security flags 0x%x",
+			flags & ~CIFSSEC_MASK);
 		return -EINVAL;
 	}
 	/* flags look ok - update the global security flags for cifs module */
-	extended_security = flags;
-	if (extended_security & CIFSSEC_MUST_SIGN) {
+	global_secflags = flags;
+	if (global_secflags & CIFSSEC_MUST_SIGN) {
 		/* requiring signing implies signing is allowed */
-		extended_security |= CIFSSEC_MAY_SIGN;
-		cFYI(1, ("packet signing now required"));
-	} else if ((extended_security & CIFSSEC_MAY_SIGN) == 0) {
-		cFYI(1, ("packet signing disabled"));
+		global_secflags |= CIFSSEC_MAY_SIGN;
+		cFYI(1, "packet signing now required");
+	} else if ((global_secflags & CIFSSEC_MAY_SIGN) == 0) {
+		cFYI(1, "packet signing disabled");
 	}
 	/* BB should we turn on MAY flags for other MUST options? */
 	return count;

fs/cifs/cifs_debug.h

diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h
index 5eb3b83..aa31689 100644
--- a/fs/cifs/cifs_debug.h
+++ b/fs/cifs/cifs_debug.h
@@ -43,34 +43,54 @@
  */
 #ifdef CIFS_DEBUG
 
-
 /* information message: e.g., configuration, major event */
 extern int cifsFYI;
-#define cifsfyi(format,arg...) if (cifsFYI & CIFS_INFO) printk(KERN_DEBUG " " __FILE__ ": " format "\n" "" , ## arg)
+#define cifsfyi(fmt, arg...)						\
+do {									\
+	if (cifsFYI & CIFS_INFO)					\
+		printk(KERN_DEBUG "%s: " fmt "\n", __FILE__, ##arg);	\
+} while (0)
 
-#define cFYI(button,prspec) if (button) cifsfyi prspec
+#define cFYI(set, fmt, arg...)			\
+do {						\
+	if (set)				\
+		cifsfyi(fmt, ##arg);		\
+} while (0)
 
-#define cifswarn(format, arg...) printk(KERN_WARNING ": " format "\n" , ## arg)
+#define cifswarn(fmt, arg...)			\
+	printk(KERN_WARNING fmt "\n", ##arg)
 
 /* debug event message: */
 extern int cifsERROR;
 
-#define cEVENT(format,arg...) if (cifsERROR) printk(KERN_EVENT __FILE__ ": " format "\n" , ## arg)
+#define cEVENT(fmt, arg...)						\
+do {									\
+	if (cifsERROR)							\
+		printk(KERN_EVENT "%s: " fmt "\n", __FILE__, ##arg);	\
+} while (0)
 
 /* error event message: e.g., i/o error */
-#define cifserror(format,arg...) if (cifsERROR) printk(KERN_ERR " CIFS VFS: " format "\n" "" , ## arg)
+#define cifserror(fmt, arg...)					\
+do {								\
+	if (cifsERROR)						\
+		printk(KERN_ERR "CIFS VFS: " fmt "\n", ##arg);	\
+} while (0)
 
-#define cERROR(button, prspec) if (button) cifserror prspec
+#define cERROR(set, fmt, arg...)		\
+do {						\
+	if (set)				\
+		cifserror(fmt, ##arg);		\
+} while (0)
 
 /*
  *	debug OFF
  *	---------
  */
 #else		/* _CIFS_DEBUG */
-#define cERROR(button, prspec)
-#define cEVENT(format, arg...)
-#define cFYI(button, prspec)
-#define cifserror(format, arg...)
+#define cERROR(set, fmt, arg...)
+#define cEVENT(fmt, arg...)
+#define cFYI(set, fmt, arg...)
+#define cifserror(fmt, arg...)
 #endif		/* _CIFS_DEBUG */
 
 #endif				/* _H_CIFS_DEBUG */

fs/cifs/cifs_dfs_ref.c

diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 78e4d2a..ac19a6f 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -85,8 +85,8 @@
 	/* find server name end */
 	pSep = memchr(UNC+2, '\\', len-2);
 	if (!pSep) {
-		cERROR(1, ("%s: no server name end in node name: %s",
-			__func__, node_name));
+		cERROR(1, "%s: no server name end in node name: %s",
+			__func__, node_name);
 		kfree(UNC);
 		return ERR_PTR(-EINVAL);
 	}
@@ -142,8 +142,8 @@
 
 	rc = dns_resolve_server_name_to_ip(*devname, &srvIP);
 	if (rc != 0) {
-		cERROR(1, ("%s: Failed to resolve server part of %s to IP: %d",
-			  __func__, *devname, rc));
+		cERROR(1, "%s: Failed to resolve server part of %s to IP: %d",
+			  __func__, *devname, rc);
 		goto compose_mount_options_err;
 	}
 	/* md_len = strlen(...) + 12 for 'sep+prefixpath='
@@ -217,8 +217,8 @@
 		strcat(mountdata, fullpath + ref->path_consumed);
 	}
 
-	/*cFYI(1,("%s: parent mountdata: %s", __func__,sb_mountdata));*/
-	/*cFYI(1, ("%s: submount mountdata: %s", __func__, mountdata ));*/
+	/*cFYI(1, "%s: parent mountdata: %s", __func__,sb_mountdata);*/
+	/*cFYI(1, "%s: submount mountdata: %s", __func__, mountdata );*/
 
 compose_mount_options_out:
 	kfree(srvIP);
@@ -294,11 +294,11 @@
 
 static void dump_referral(const struct dfs_info3_param *ref)
 {
-	cFYI(1, ("DFS: ref path: %s", ref->path_name));
-	cFYI(1, ("DFS: node path: %s", ref->node_name));
-	cFYI(1, ("DFS: fl: %hd, srv_type: %hd", ref->flags, ref->server_type));
-	cFYI(1, ("DFS: ref_flags: %hd, path_consumed: %hd", ref->ref_flag,
-				ref->path_consumed));
+	cFYI(1, "DFS: ref path: %s", ref->path_name);
+	cFYI(1, "DFS: node path: %s", ref->node_name);
+	cFYI(1, "DFS: fl: %hd, srv_type: %hd", ref->flags, ref->server_type);
+	cFYI(1, "DFS: ref_flags: %hd, path_consumed: %hd", ref->ref_flag,
+				ref->path_consumed);
 }
 
 
@@ -314,7 +314,7 @@
 	int rc = 0;
 	struct vfsmount *mnt = ERR_PTR(-ENOENT);
 
-	cFYI(1, ("in %s", __func__));
+	cFYI(1, "in %s", __func__);
 	BUG_ON(IS_ROOT(dentry));
 
 	xid = GetXid();
@@ -352,15 +352,15 @@
 		/* connect to a node */
 		len = strlen(referrals[i].node_name);
 		if (len < 2) {
-			cERROR(1, ("%s: Net Address path too short: %s",
-					__func__, referrals[i].node_name));
+			cERROR(1, "%s: Net Address path too short: %s",
+					__func__, referrals[i].node_name);
 			rc = -EINVAL;
 			goto out_err;
 		}
 		mnt = cifs_dfs_do_refmount(nd->path.mnt,
 				nd->path.dentry, referrals + i);
-		cFYI(1, ("%s: cifs_dfs_do_refmount:%s , mnt:%p", __func__,
-					referrals[i].node_name, mnt));
+		cFYI(1, "%s: cifs_dfs_do_refmount:%s , mnt:%p", __func__,
+					referrals[i].node_name, mnt);
 
 		/* complete mount procedure if we accured submount */
 		if (!IS_ERR(mnt))
@@ -378,7 +378,7 @@
 	FreeXid(xid);
 	free_dfs_info_array(referrals, num_referrals);
 	kfree(full_path);
-	cFYI(1, ("leaving %s" , __func__));
+	cFYI(1, "leaving %s" , __func__);
 	return ERR_PTR(rc);
 out_err:
 	path_put(&nd->path);

fs/cifs/cifs_spnego.c

diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 310d12f..379bd7d 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -133,9 +133,9 @@
 	dp = description + strlen(description);
 
 	/* for now, only sec=krb5 and sec=mskrb5 are valid */
-	if (server->secType == Kerberos)
+	if (server->sec_kerberos)
 		sprintf(dp, ";sec=krb5");
-	else if (server->secType == MSKerberos)
+	else if (server->sec_mskerberos)
 		sprintf(dp, ";sec=mskrb5");
 	else
 		goto out;
@@ -149,7 +149,7 @@
 	dp = description + strlen(description);
 	sprintf(dp, ";pid=0x%x", current->pid);
 
-	cFYI(1, ("key description = %s", description));
+	cFYI(1, "key description = %s", description);
 	spnego_key = request_key(&cifs_spnego_key_type, description, "");
 
 #ifdef CONFIG_CIFS_DEBUG2

fs/cifs/cifs_unicode.c

diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index d07676b..430f510 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -200,9 +200,8 @@
 		/* works for 2.4.0 kernel or later */
 		charlen = codepage->char2uni(from, len, &wchar_to[i]);
 		if (charlen < 1) {
-			cERROR(1,
-			       ("strtoUCS: char2uni of %d returned %d",
-				(int)*from, charlen));
+			cERROR(1, "strtoUCS: char2uni of %d returned %d",
+				(int)*from, charlen);
 			/* A question mark */
 			to[i] = cpu_to_le16(0x003f);
 			charlen = 1;

fs/cifs/cifsacl.c

diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 9b716d0..85d7cf7 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -87,11 +87,11 @@
 				continue; /* all sub_auth values do not match */
 		}
 
-		cFYI(1, ("matching sid: %s\n", wksidarr[i].sidname));
+		cFYI(1, "matching sid: %s\n", wksidarr[i].sidname);
 		return 0; /* sids compare/match */
 	}
 
-	cFYI(1, ("No matching sid"));
+	cFYI(1, "No matching sid");
 	return -1;
 }
 
@@ -208,14 +208,14 @@
 			*pbits_to_set &= ~S_IXUGO;
 		return;
 	} else if (type != ACCESS_ALLOWED) {
-		cERROR(1, ("unknown access control type %d", type));
+		cERROR(1, "unknown access control type %d", type);
 		return;
 	}
 	/* else ACCESS_ALLOWED type */
 
 	if (flags & GENERIC_ALL) {
 		*pmode |= (S_IRWXUGO & (*pbits_to_set));
-		cFYI(DBG2, ("all perms"));
+		cFYI(DBG2, "all perms");
 		return;
 	}
 	if ((flags & GENERIC_WRITE) ||
@@ -228,7 +228,7 @@
 			((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS))
 		*pmode |= (S_IXUGO & (*pbits_to_set));
 
-	cFYI(DBG2, ("access flags 0x%x mode now 0x%x", flags, *pmode));
+	cFYI(DBG2, "access flags 0x%x mode now 0x%x", flags, *pmode);
 	return;
 }
 
@@ -257,7 +257,7 @@
 	if (mode & S_IXUGO)
 		*pace_flags |= SET_FILE_EXEC_RIGHTS;
 
-	cFYI(DBG2, ("mode: 0x%x, access flags now 0x%x", mode, *pace_flags));
+	cFYI(DBG2, "mode: 0x%x, access flags now 0x%x", mode, *pace_flags);
 	return;
 }
 
@@ -297,24 +297,24 @@
 	/* validate that we do not go past end of acl */
 
 	if (le16_to_cpu(pace->size) < 16) {
-		cERROR(1, ("ACE too small, %d", le16_to_cpu(pace->size)));
+		cERROR(1, "ACE too small %d", le16_to_cpu(pace->size));
 		return;
 	}
 
 	if (end_of_acl < (char *)pace + le16_to_cpu(pace->size)) {
-		cERROR(1, ("ACL too small to parse ACE"));
+		cERROR(1, "ACL too small to parse ACE");
 		return;
 	}
 
 	num_subauth = pace->sid.num_subauth;
 	if (num_subauth) {
 		int i;
-		cFYI(1, ("ACE revision %d num_auth %d type %d flags %d size %d",
+		cFYI(1, "ACE revision %d num_auth %d type %d flags %d size %d",
 			pace->sid.revision, pace->sid.num_subauth, pace->type,
-			pace->flags, le16_to_cpu(pace->size)));
+			pace->flags, le16_to_cpu(pace->size));
 		for (i = 0; i < num_subauth; ++i) {
-			cFYI(1, ("ACE sub_auth[%d]: 0x%x", i,
-				le32_to_cpu(pace->sid.sub_auth[i])));
+			cFYI(1, "ACE sub_auth[%d]: 0x%x", i,
+				le32_to_cpu(pace->sid.sub_auth[i]));
 		}
 
 		/* BB add length check to make sure that we do not have huge
@@ -347,13 +347,13 @@
 
 	/* validate that we do not go past end of acl */
 	if (end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) {
-		cERROR(1, ("ACL too small to parse DACL"));
+		cERROR(1, "ACL too small to parse DACL");
 		return;
 	}
 
-	cFYI(DBG2, ("DACL revision %d size %d num aces %d",
+	cFYI(DBG2, "DACL revision %d size %d num aces %d",
 		le16_to_cpu(pdacl->revision), le16_to_cpu(pdacl->size),
-		le32_to_cpu(pdacl->num_aces)));
+		le32_to_cpu(pdacl->num_aces));
 
 	/* reset rwx permissions for user/group/other.
 	   Also, if num_aces is 0 i.e. DACL has no ACEs,
@@ -437,25 +437,25 @@
 	/* validate that we do not go past end of ACL - sid must be at least 8
 	   bytes long (assuming no sub-auths - e.g. the null SID */
 	if (end_of_acl < (char *)psid + 8) {
-		cERROR(1, ("ACL too small to parse SID %p", psid));
+		cERROR(1, "ACL too small to parse SID %p", psid);
 		return -EINVAL;
 	}
 
 	if (psid->num_subauth) {
 #ifdef CONFIG_CIFS_DEBUG2
 		int i;
-		cFYI(1, ("SID revision %d num_auth %d",
-			psid->revision, psid->num_subauth));
+		cFYI(1, "SID revision %d num_auth %d",
+			psid->revision, psid->num_subauth);
 
 		for (i = 0; i < psid->num_subauth; i++) {
-			cFYI(1, ("SID sub_auth[%d]: 0x%x ", i,
-				le32_to_cpu(psid->sub_auth[i])));
+			cFYI(1, "SID sub_auth[%d]: 0x%x ", i,
+				le32_to_cpu(psid->sub_auth[i]));
 		}
 
 		/* BB add length check to make sure that we do not have huge
 			num auths and therefore go off the end */
-		cFYI(1, ("RID 0x%x",
-			le32_to_cpu(psid->sub_auth[psid->num_subauth-1])));
+		cFYI(1, "RID 0x%x",
+			le32_to_cpu(psid->sub_auth[psid->num_subauth-1]));
 #endif
 	}
 
@@ -482,11 +482,11 @@
 				le32_to_cpu(pntsd->gsidoffset));
 	dacloffset = le32_to_cpu(pntsd->dacloffset);
 	dacl_ptr = (struct cifs_acl *)((char *)pntsd + dacloffset);
-	cFYI(DBG2, ("revision %d type 0x%x ooffset 0x%x goffset 0x%x "
+	cFYI(DBG2, "revision %d type 0x%x ooffset 0x%x goffset 0x%x "
 		 "sacloffset 0x%x dacloffset 0x%x",
 		 pntsd->revision, pntsd->type, le32_to_cpu(pntsd->osidoffset),
 		 le32_to_cpu(pntsd->gsidoffset),
-		 le32_to_cpu(pntsd->sacloffset), dacloffset));
+		 le32_to_cpu(pntsd->sacloffset), dacloffset);
 /*	cifs_dump_mem("owner_sid: ", owner_sid_ptr, 64); */
 	rc = parse_sid(owner_sid_ptr, end_of_acl);
 	if (rc)
@@ -500,7 +500,7 @@
 		parse_dacl(dacl_ptr, end_of_acl, owner_sid_ptr,
 			   group_sid_ptr, fattr);
 	else
-		cFYI(1, ("no ACL")); /* BB grant all or default perms? */
+		cFYI(1, "no ACL"); /* BB grant all or default perms? */
 
 /*	cifscred->uid = owner_sid_ptr->rid;
 	cifscred->gid = group_sid_ptr->rid;
@@ -563,7 +563,7 @@
 	FreeXid(xid);
 
 
-	cFYI(1, ("GetCIFSACL rc = %d ACL len %d", rc, *pacllen));
+	cFYI(1, "GetCIFSACL rc = %d ACL len %d", rc, *pacllen);
 	return pntsd;
 }
 
@@ -581,12 +581,12 @@
 			 &fid, &oplock, NULL, cifs_sb->local_nls,
 			 cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
 	if (rc) {
-		cERROR(1, ("Unable to open file to get ACL"));
+		cERROR(1, "Unable to open file to get ACL");
 		goto out;
 	}
 
 	rc = CIFSSMBGetCIFSACL(xid, cifs_sb->tcon, fid, &pntsd, pacllen);
-	cFYI(1, ("GetCIFSACL rc = %d ACL len %d", rc, *pacllen));
+	cFYI(1, "GetCIFSACL rc = %d ACL len %d", rc, *pacllen);
 
 	CIFSSMBClose(xid, cifs_sb->tcon, fid);
  out:
@@ -621,7 +621,7 @@
 	rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen);
 	FreeXid(xid);
 
-	cFYI(DBG2, ("SetCIFSACL rc = %d", rc));
+	cFYI(DBG2, "SetCIFSACL rc = %d", rc);
 	return rc;
 }
 
@@ -638,12 +638,12 @@
 			 &fid, &oplock, NULL, cifs_sb->local_nls,
 			 cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
 	if (rc) {
-		cERROR(1, ("Unable to open file to set ACL"));
+		cERROR(1, "Unable to open file to set ACL");
 		goto out;
 	}
 
 	rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen);
-	cFYI(DBG2, ("SetCIFSACL rc = %d", rc));
+	cFYI(DBG2, "SetCIFSACL rc = %d", rc);
 
 	CIFSSMBClose(xid, cifs_sb->tcon, fid);
  out:
@@ -659,7 +659,7 @@
 	struct cifsFileInfo *open_file;
 	int rc;
 
-	cFYI(DBG2, ("set ACL for %s from mode 0x%x", path, inode->i_mode));
+	cFYI(DBG2, "set ACL for %s from mode 0x%x", path, inode->i_mode);
 
 	open_file = find_readable_file(CIFS_I(inode));
 	if (!open_file)
@@ -679,7 +679,7 @@
 	u32 acllen = 0;
 	int rc = 0;
 
-	cFYI(DBG2, ("converting ACL to mode for %s", path));
+	cFYI(DBG2, "converting ACL to mode for %s", path);
 
 	if (pfid)
 		pntsd = get_cifs_acl_by_fid(cifs_sb, *pfid, &acllen);
@@ -690,7 +690,7 @@
 	if (pntsd)
 		rc = parse_sec_desc(pntsd, acllen, fattr);
 	if (rc)
-		cFYI(1, ("parse sec desc failed rc = %d", rc));
+		cFYI(1, "parse sec desc failed rc = %d", rc);
 
 	kfree(pntsd);
 	return;
@@ -704,7 +704,7 @@
 	struct cifs_ntsd *pntsd = NULL; /* acl obtained from server */
 	struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
 
-	cFYI(DBG2, ("set ACL from mode for %s", path));
+	cFYI(DBG2, "set ACL from mode for %s", path);
 
 	/* Get the security descriptor */
 	pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen);
@@ -721,19 +721,19 @@
 					DEFSECDESCLEN : secdesclen;
 		pnntsd = kmalloc(secdesclen, GFP_KERNEL);
 		if (!pnntsd) {
-			cERROR(1, ("Unable to allocate security descriptor"));
+			cERROR(1, "Unable to allocate security descriptor");
 			kfree(pntsd);
 			return -ENOMEM;
 		}
 
 		rc = build_sec_desc(pntsd, pnntsd, inode, nmode);
 
-		cFYI(DBG2, ("build_sec_desc rc: %d", rc));
+		cFYI(DBG2, "build_sec_desc rc: %d", rc);
 
 		if (!rc) {
 			/* Set the security descriptor */
 			rc = set_cifs_acl(pnntsd, secdesclen, inode, path);
-			cFYI(DBG2, ("set_cifs_acl rc: %d", rc));
+			cFYI(DBG2, "set_cifs_acl rc: %d", rc);
 		}
 
 		kfree(pnntsd);

fs/cifs/cifsencrypt.c

diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index fbe9864..847628d 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -103,7 +103,7 @@
 		if (iov[i].iov_len == 0)
 			continue;
 		if (iov[i].iov_base == NULL) {
-			cERROR(1, ("null iovec entry"));
+			cERROR(1, "null iovec entry");
 			return -EIO;
 		}
 		/* The first entry includes a length field (which does not get
@@ -181,8 +181,8 @@
 
 	/* Do not need to verify session setups with signature "BSRSPYL "  */
 	if (memcmp(cifs_pdu->Signature.SecuritySignature, "BSRSPYL ", 8) == 0)
-		cFYI(1, ("dummy signature received for smb command 0x%x",
-			cifs_pdu->Command));
+		cFYI(1, "dummy signature received for smb command 0x%x",
+			cifs_pdu->Command);
 
 	/* save off the origiginal signature so we can modify the smb and check
 		its signature against what the server sent */
@@ -291,7 +291,7 @@
 	if (password)
 		strncpy(password_with_pad, password, CIFS_ENCPWD_SIZE);
 
-	if (!encrypt && extended_security & CIFSSEC_MAY_PLNTXT) {
+	if (!encrypt && global_secflags & CIFSSEC_MAY_PLNTXT) {
 		memset(lnm_session_key, 0, CIFS_SESS_KEY_SIZE);
 		memcpy(lnm_session_key, password_with_pad,
 			CIFS_ENCPWD_SIZE);
@@ -398,7 +398,7 @@
 	/* calculate buf->ntlmv2_hash */
 	rc = calc_ntlmv2_hash(ses, nls_cp);
 	if (rc)
-		cERROR(1, ("could not get v2 hash rc %d", rc));
+		cERROR(1, "could not get v2 hash rc %d", rc);
 	CalcNTLMv2_response(ses, resp_buf);
 
 	/* now calculate the MAC key for NTLMv2 */

fs/cifs/cifsfs.c

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index ad235d6..78c02eb 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -49,10 +49,6 @@
 #include "cifs_spnego.h"
 #define CIFS_MAGIC_NUMBER 0xFF534D42	/* the first four bytes of SMB PDUs */
 
-#ifdef CONFIG_CIFS_QUOTA
-static const struct quotactl_ops cifs_quotactl_ops;
-#endif /* QUOTA */
-
 int cifsFYI = 0;
 int cifsERROR = 1;
 int traceSMB = 0;
@@ -61,7 +57,7 @@
 unsigned int linuxExtEnabled = 1;
 unsigned int lookupCacheEnabled = 1;
 unsigned int multiuser_mount = 0;
-unsigned int extended_security = CIFSSEC_DEF;
+unsigned int global_secflags = CIFSSEC_DEF;
 /* unsigned int ntlmv2_support = 0; */
 unsigned int sign_CIFS_PDUs = 1;
 static const struct super_operations cifs_super_ops;
@@ -86,8 +82,6 @@
 extern mempool_t *cifs_req_poolp;
 extern mempool_t *cifs_mid_poolp;
 
-extern struct kmem_cache *cifs_oplock_cachep;
-
 static int
 cifs_read_super(struct super_block *sb, void *data,
 		const char *devname, int silent)
@@ -135,8 +129,7 @@
 
 	if (rc) {
 		if (!silent)
-			cERROR(1,
-			       ("cifs_mount failed w/return code = %d", rc));
+			cERROR(1, "cifs_mount failed w/return code = %d", rc);
 		goto out_mount_failed;
 	}
 
@@ -146,9 +139,6 @@
 /*	if (cifs_sb->tcon->ses->server->maxBuf > MAX_CIFS_HDR_SIZE + 512)
 	    sb->s_blocksize =
 		cifs_sb->tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE; */
-#ifdef CONFIG_CIFS_QUOTA
-	sb->s_qcop = &cifs_quotactl_ops;
-#endif
 	sb->s_blocksize = CIFS_MAX_MSGSIZE;
 	sb->s_blocksize_bits = 14;	/* default 2**14 = CIFS_MAX_MSGSIZE */
 	inode = cifs_root_iget(sb, ROOT_I);
@@ -168,7 +158,7 @@
 
 #ifdef CONFIG_CIFS_EXPERIMENTAL
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
-		cFYI(1, ("export ops supported"));
+		cFYI(1, "export ops supported");
 		sb->s_export_op = &cifs_export_ops;
 	}
 #endif /* EXPERIMENTAL */
@@ -176,7 +166,7 @@
 	return 0;
 
 out_no_root:
-	cERROR(1, ("cifs_read_super: get root inode failed"));
+	cERROR(1, "cifs_read_super: get root inode failed");
 	if (inode)
 		iput(inode);
 
@@ -203,10 +193,10 @@
 	int rc = 0;
 	struct cifs_sb_info *cifs_sb;
 
-	cFYI(1, ("In cifs_put_super"));
+	cFYI(1, "In cifs_put_super");
 	cifs_sb = CIFS_SB(sb);
 	if (cifs_sb == NULL) {
-		cFYI(1, ("Empty cifs superblock info passed to unmount"));
+		cFYI(1, "Empty cifs superblock info passed to unmount");
 		return;
 	}
 
@@ -214,7 +204,7 @@
 
 	rc = cifs_umount(sb, cifs_sb);
 	if (rc)
-		cERROR(1, ("cifs_umount failed with return code %d", rc));
+		cERROR(1, "cifs_umount failed with return code %d", rc);
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	if (cifs_sb->mountdata) {
 		kfree(cifs_sb->mountdata);
@@ -300,7 +290,6 @@
 static struct kmem_cache *cifs_inode_cachep;
 static struct kmem_cache *cifs_req_cachep;
 static struct kmem_cache *cifs_mid_cachep;
-struct kmem_cache *cifs_oplock_cachep;
 static struct kmem_cache *cifs_sm_req_cachep;
 mempool_t *cifs_sm_req_poolp;
 mempool_t *cifs_req_poolp;
@@ -432,106 +421,6 @@
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_QUOTA
-int cifs_xquota_set(struct super_block *sb, int quota_type, qid_t qid,
-		struct fs_disk_quota *pdquota)
-{
-	int xid;
-	int rc = 0;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-	struct cifsTconInfo *pTcon;
-
-	if (cifs_sb)
-		pTcon = cifs_sb->tcon;
-	else
-		return -EIO;
-
-
-	xid = GetXid();
-	if (pTcon) {
-		cFYI(1, ("set type: 0x%x id: %d", quota_type, qid));
-	} else
-		rc = -EIO;
-
-	FreeXid(xid);
-	return rc;
-}
-
-int cifs_xquota_get(struct super_block *sb, int quota_type, qid_t qid,
-		    struct fs_disk_quota *pdquota)
-{
-	int xid;
-	int rc = 0;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-	struct cifsTconInfo *pTcon;
-
-	if (cifs_sb)
-		pTcon = cifs_sb->tcon;
-	else
-		return -EIO;
-
-	xid = GetXid();
-	if (pTcon) {
-		cFYI(1, ("set type: 0x%x id: %d", quota_type, qid));
-	} else
-		rc = -EIO;
-
-	FreeXid(xid);
-	return rc;
-}
-
-int cifs_xstate_set(struct super_block *sb, unsigned int flags, int operation)
-{
-	int xid;
-	int rc = 0;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-	struct cifsTconInfo *pTcon;
-
-	if (cifs_sb)
-		pTcon = cifs_sb->tcon;
-	else
-		return -EIO;
-
-	xid = GetXid();
-	if (pTcon) {
-		cFYI(1, ("flags: 0x%x operation: 0x%x", flags, operation));
-	} else
-		rc = -EIO;
-
-	FreeXid(xid);
-	return rc;
-}
-
-int cifs_xstate_get(struct super_block *sb, struct fs_quota_stat *qstats)
-{
-	int xid;
-	int rc = 0;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-	struct cifsTconInfo *pTcon;
-
-	if (cifs_sb)
-		pTcon = cifs_sb->tcon;
-	else
-		return -EIO;
-
-	xid = GetXid();
-	if (pTcon) {
-		cFYI(1, ("pqstats %p", qstats));
-	} else
-		rc = -EIO;
-
-	FreeXid(xid);
-	return rc;
-}
-
-static const struct quotactl_ops cifs_quotactl_ops = {
-	.set_xquota	= cifs_xquota_set,
-	.get_xquota	= cifs_xquota_get,
-	.set_xstate	= cifs_xstate_set,
-	.get_xstate	= cifs_xstate_get,
-};
-#endif
-
 static void cifs_umount_begin(struct super_block *sb)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
@@ -558,7 +447,7 @@
 	/* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */
 	/* cancel_notify_requests(tcon); */
 	if (tcon->ses && tcon->ses->server) {
-		cFYI(1, ("wake up tasks now - umount begin not complete"));
+		cFYI(1, "wake up tasks now - umount begin not complete");
 		wake_up_all(&tcon->ses->server->request_q);
 		wake_up_all(&tcon->ses->server->response_q);
 		msleep(1); /* yield */
@@ -609,7 +498,7 @@
 	int rc;
 	struct super_block *sb = sget(fs_type, NULL, set_anon_super, NULL);
 
-	cFYI(1, ("Devname: %s flags: %d ", dev_name, flags));
+	cFYI(1, "Devname: %s flags: %d ", dev_name, flags);
 
 	if (IS_ERR(sb))
 		return PTR_ERR(sb);
@@ -656,7 +545,6 @@
 	return generic_file_llseek_unlocked(file, offset, origin);
 }
 
-#ifdef CONFIG_CIFS_EXPERIMENTAL
 static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
 {
 	/* note that this is called by vfs setlease with the BKL held
@@ -685,7 +573,6 @@
 	else
 		return -EAGAIN;
 }
-#endif
 
 struct file_system_type cifs_fs_type = {
 	.owner = THIS_MODULE,
@@ -762,10 +649,7 @@
 #ifdef CONFIG_CIFS_POSIX
 	.unlocked_ioctl	= cifs_ioctl,
 #endif /* CONFIG_CIFS_POSIX */
-
-#ifdef CONFIG_CIFS_EXPERIMENTAL
 	.setlease = cifs_setlease,
-#endif /* CONFIG_CIFS_EXPERIMENTAL */
 };
 
 const struct file_operations cifs_file_direct_ops = {
@@ -784,9 +668,7 @@
 	.unlocked_ioctl  = cifs_ioctl,
 #endif /* CONFIG_CIFS_POSIX */
 	.llseek = cifs_llseek,
-#ifdef CONFIG_CIFS_EXPERIMENTAL
 	.setlease = cifs_setlease,
-#endif /* CONFIG_CIFS_EXPERIMENTAL */
 };
 const struct file_operations cifs_file_nobrl_ops = {
 	.read = do_sync_read,
@@ -803,10 +685,7 @@
 #ifdef CONFIG_CIFS_POSIX
 	.unlocked_ioctl	= cifs_ioctl,
 #endif /* CONFIG_CIFS_POSIX */
-
-#ifdef CONFIG_CIFS_EXPERIMENTAL
 	.setlease = cifs_setlease,
-#endif /* CONFIG_CIFS_EXPERIMENTAL */
 };
 
 const struct file_operations cifs_file_direct_nobrl_ops = {
@@ -824,9 +703,7 @@
 	.unlocked_ioctl  = cifs_ioctl,
 #endif /* CONFIG_CIFS_POSIX */
 	.llseek = cifs_llseek,
-#ifdef CONFIG_CIFS_EXPERIMENTAL
 	.setlease = cifs_setlease,
-#endif /* CONFIG_CIFS_EXPERIMENTAL */
 };
 
 const struct file_operations cifs_dir_ops = {
@@ -878,7 +755,7 @@
 	} else {
 		CIFSMaxBufSize &= 0x1FE00; /* Round size to even 512 byte mult*/
 	}
-/*	cERROR(1,("CIFSMaxBufSize %d 0x%x",CIFSMaxBufSize,CIFSMaxBufSize)); */
+/*	cERROR(1, "CIFSMaxBufSize %d 0x%x",CIFSMaxBufSize,CIFSMaxBufSize); */
 	cifs_req_cachep = kmem_cache_create("cifs_request",
 					    CIFSMaxBufSize +
 					    MAX_CIFS_HDR_SIZE, 0,
@@ -890,7 +767,7 @@
 		cifs_min_rcv = 1;
 	else if (cifs_min_rcv > 64) {
 		cifs_min_rcv = 64;
-		cERROR(1, ("cifs_min_rcv set to maximum (64)"));
+		cERROR(1, "cifs_min_rcv set to maximum (64)");
 	}
 
 	cifs_req_poolp = mempool_create_slab_pool(cifs_min_rcv,
@@ -921,7 +798,7 @@
 		cifs_min_small = 2;
 	else if (cifs_min_small > 256) {
 		cifs_min_small = 256;
-		cFYI(1, ("cifs_min_small set to maximum (256)"));
+		cFYI(1, "cifs_min_small set to maximum (256)");
 	}
 
 	cifs_sm_req_poolp = mempool_create_slab_pool(cifs_min_small,
@@ -962,15 +839,6 @@
 		return -ENOMEM;
 	}
 
-	cifs_oplock_cachep = kmem_cache_create("cifs_oplock_structs",
-					sizeof(struct oplock_q_entry), 0,
-					SLAB_HWCACHE_ALIGN, NULL);
-	if (cifs_oplock_cachep == NULL) {
-		mempool_destroy(cifs_mid_poolp);
-		kmem_cache_destroy(cifs_mid_cachep);
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
@@ -979,7 +847,6 @@
 {
 	mempool_destroy(cifs_mid_poolp);
 	kmem_cache_destroy(cifs_mid_cachep);
-	kmem_cache_destroy(cifs_oplock_cachep);
 }
 
 static int __init
@@ -1019,10 +886,10 @@
 
 	if (cifs_max_pending < 2) {
 		cifs_max_pending = 2;
-		cFYI(1, ("cifs_max_pending set to min of 2"));
+		cFYI(1, "cifs_max_pending set to min of 2");
 	} else if (cifs_max_pending > 256) {
 		cifs_max_pending = 256;
-		cFYI(1, ("cifs_max_pending set to max of 256"));
+		cFYI(1, "cifs_max_pending set to max of 256");
 	}
 
 	rc = cifs_init_inodecache();
@@ -1080,7 +947,7 @@
 static void __exit
 exit_cifs(void)
 {
-	cFYI(DBG2, ("exit_cifs"));
+	cFYI(DBG2, "exit_cifs");
 	cifs_proc_clean();
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	cifs_dfs_release_automount_timer();

fs/cifs/cifsfs.h

diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 7aa57ec..0242ff9 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -114,5 +114,5 @@
 extern const struct export_operations cifs_export_ops;
 #endif /* EXPERIMENTAL */
 
-#define CIFS_VERSION   "1.62"
+#define CIFS_VERSION   "1.64"
 #endif				/* _CIFSFS_H */

fs/cifs/cifsglob.h

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index ecf0ffb..a88479c 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -87,7 +87,6 @@
 	RawNTLMSSP,		/* NTLMSSP without SPNEGO, NTLMv2 hash */
 /*	NTLMSSP, */ /* can use rawNTLMSSP instead of NTLMSSP via SPNEGO */
 	Kerberos,		/* Kerberos via SPNEGO */
-	MSKerberos,		/* MS Kerberos via SPNEGO */
 };
 
 enum protocolEnum {
@@ -185,6 +184,12 @@
 	struct mac_key mac_signing_key;
 	char ntlmv2_hash[16];
 	unsigned long lstrp; /* when we got last response from this server */
+	u16 dialect; /* dialect index that server chose */
+	/* extended security flavors that server supports */
+	bool	sec_kerberos;		/* supports plain Kerberos */
+	bool	sec_mskerberos;		/* supports legacy MS Kerberos */
+	bool	sec_kerberosu2u;	/* supports U2U Kerberos */
+	bool	sec_ntlmssp;		/* supports NTLMSSP */
 };
 
 /*
@@ -502,6 +507,7 @@
 #define CIFS_FATTR_DFS_REFERRAL		0x1
 #define CIFS_FATTR_DELETE_PENDING	0x2
 #define CIFS_FATTR_NEED_REVAL		0x4
+#define CIFS_FATTR_INO_COLLISION	0x8
 
 struct cifs_fattr {
 	u32		cf_flags;
@@ -717,7 +723,7 @@
 GLOBAL_EXTERN unsigned int oplockEnabled;
 GLOBAL_EXTERN unsigned int experimEnabled;
 GLOBAL_EXTERN unsigned int lookupCacheEnabled;
-GLOBAL_EXTERN unsigned int extended_security;	/* if on, session setup sent
+GLOBAL_EXTERN unsigned int global_secflags;	/* if on, session setup sent
 				with more secure ntlmssp2 challenge/resp */
 GLOBAL_EXTERN unsigned int sign_CIFS_PDUs;  /* enable smb packet signing */
 GLOBAL_EXTERN unsigned int linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/

fs/cifs/cifsproto.h

diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 39e47f4..fb1657e 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -39,8 +39,20 @@
 			unsigned int /* length */);
 extern unsigned int _GetXid(void);
 extern void _FreeXid(unsigned int);
-#define GetXid() (int)_GetXid(); cFYI(1,("CIFS VFS: in %s as Xid: %d with uid: %d",__func__, xid,current_fsuid()));
-#define FreeXid(curr_xid) {_FreeXid(curr_xid); cFYI(1,("CIFS VFS: leaving %s (xid = %d) rc = %d",__func__,curr_xid,(int)rc));}
+#define GetXid()						\
+({								\
+	int __xid = (int)_GetXid();				\
+	cFYI(1, "CIFS VFS: in %s as Xid: %d with uid: %d",	\
+	     __func__, __xid, current_fsuid());			\
+	__xid;							\
+})
+
+#define FreeXid(curr_xid)					\
+do {								\
+	_FreeXid(curr_xid);					\
+	cFYI(1, "CIFS VFS: leaving %s (xid = %d) rc = %d",	\
+	     __func__, curr_xid, (int)rc);			\
+} while (0)
 extern char *build_path_from_dentry(struct dentry *);
 extern char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb);
 extern char *build_wildcard_path_from_dentry(struct dentry *direntry);
@@ -73,7 +85,7 @@
 extern unsigned int smbCalcSize(struct smb_hdr *ptr);
 extern unsigned int smbCalcSize_LE(struct smb_hdr *ptr);
 extern int decode_negTokenInit(unsigned char *security_blob, int length,
-			enum securityEnum *secType);
+			struct TCP_Server_Info *server);
 extern int cifs_convert_address(char *src, void *dst);
 extern int map_smb_to_linux_error(struct smb_hdr *smb, int logErr);
 extern void header_assemble(struct smb_hdr *, char /* command */ ,
@@ -83,7 +95,6 @@
 				struct cifsSesInfo *ses,
 				void **request_buf);
 extern int CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses,
-			     const int stage,
 			     const struct nls_table *nls_cp);
 extern __u16 GetNextMid(struct TCP_Server_Info *server);
 extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
@@ -95,8 +106,11 @@
 				__u16 fileHandle, struct file *file,
 				struct vfsmount *mnt, unsigned int oflags);
 extern int cifs_posix_open(char *full_path, struct inode **pinode,
-			   struct vfsmount *mnt, int mode, int oflags,
-			   __u32 *poplock, __u16 *pnetfid, int xid);
+				struct vfsmount *mnt,
+				struct super_block *sb,
+				int mode, int oflags,
+				__u32 *poplock, __u16 *pnetfid, int xid);
+void cifs_fill_uniqueid(struct super_block *sb, struct cifs_fattr *fattr);
 extern void cifs_unix_basic_to_fattr(struct cifs_fattr *fattr,
 				     FILE_UNIX_BASIC_INFO *info,
 				     struct cifs_sb_info *cifs_sb);
@@ -125,7 +139,9 @@
 void cifs_proc_init(void);
 void cifs_proc_clean(void);
 
-extern int cifs_setup_session(unsigned int xid, struct cifsSesInfo *pSesInfo,
+extern int cifs_negotiate_protocol(unsigned int xid,
+				  struct cifsSesInfo *ses);
+extern int cifs_setup_session(unsigned int xid, struct cifsSesInfo *ses,
 			struct nls_table *nls_info);
 extern int CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses);
 

fs/cifs/cifssmb.c

diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 5d3f29f..c65c341 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1,7 +1,7 @@
 /*
  *   fs/cifs/cifssmb.c
  *
- *   Copyright (C) International Business Machines  Corp., 2002,2009
+ *   Copyright (C) International Business Machines  Corp., 2002,2010
  *   Author(s): Steve French (sfrench@us.ibm.com)
  *
  *   Contains the routines for constructing the SMB PDUs themselves
@@ -130,8 +130,8 @@
 		if (smb_command != SMB_COM_WRITE_ANDX &&
 		    smb_command != SMB_COM_OPEN_ANDX &&
 		    smb_command != SMB_COM_TREE_DISCONNECT) {
-			cFYI(1, ("can not send cmd %d while umounting",
-				smb_command));
+			cFYI(1, "can not send cmd %d while umounting",
+				smb_command);
 			return -ENODEV;
 		}
 	}
@@ -157,7 +157,7 @@
 		 * back on-line
 		 */
 		if (!tcon->retry || ses->status == CifsExiting) {
-			cFYI(1, ("gave up waiting on reconnect in smb_init"));
+			cFYI(1, "gave up waiting on reconnect in smb_init");
 			return -EHOSTDOWN;
 		}
 	}
@@ -172,7 +172,8 @@
 	 * reconnect the same SMB session
 	 */
 	mutex_lock(&ses->session_mutex);
-	if (ses->need_reconnect)
+	rc = cifs_negotiate_protocol(0, ses);
+	if (rc == 0 && ses->need_reconnect)
 		rc = cifs_setup_session(0, ses, nls_codepage);
 
 	/* do we need to reconnect tcon? */
@@ -184,7 +185,7 @@
 	mark_open_files_invalid(tcon);
 	rc = CIFSTCon(0, ses, tcon->treeName, tcon, nls_codepage);
 	mutex_unlock(&ses->session_mutex);
-	cFYI(1, ("reconnect tcon rc = %d", rc));
+	cFYI(1, "reconnect tcon rc = %d", rc);
 
 	if (rc)
 		goto out;
@@ -355,7 +356,6 @@
 	struct TCP_Server_Info *server;
 	u16 count;
 	unsigned int secFlags;
-	u16 dialect;
 
 	if (ses->server)
 		server = ses->server;
@@ -372,9 +372,9 @@
 	if (ses->overrideSecFlg & (~(CIFSSEC_MUST_SIGN | CIFSSEC_MUST_SEAL)))
 		secFlags = ses->overrideSecFlg;  /* BB FIXME fix sign flags? */
 	else /* if override flags set only sign/seal OR them with global auth */
-		secFlags = extended_security | ses->overrideSecFlg;
+		secFlags = global_secflags | ses->overrideSecFlg;
 
-	cFYI(1, ("secFlags 0x%x", secFlags));
+	cFYI(1, "secFlags 0x%x", secFlags);
 
 	pSMB->hdr.Mid = GetNextMid(server);
 	pSMB->hdr.Flags2 |= (SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS);
@@ -382,14 +382,14 @@
 	if ((secFlags & CIFSSEC_MUST_KRB5) == CIFSSEC_MUST_KRB5)
 		pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC;
 	else if ((secFlags & CIFSSEC_AUTH_MASK) == CIFSSEC_MAY_KRB5) {
-		cFYI(1, ("Kerberos only mechanism, enable extended security"));
+		cFYI(1, "Kerberos only mechanism, enable extended security");
 		pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC;
 	}
 #ifdef CONFIG_CIFS_EXPERIMENTAL
 	else if ((secFlags & CIFSSEC_MUST_NTLMSSP) == CIFSSEC_MUST_NTLMSSP)
 		pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC;
 	else if ((secFlags & CIFSSEC_AUTH_MASK) == CIFSSEC_MAY_NTLMSSP) {
-		cFYI(1, ("NTLMSSP only mechanism, enable extended security"));
+		cFYI(1, "NTLMSSP only mechanism, enable extended security");
 		pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC;
 	}
 #endif
@@ -408,10 +408,10 @@
 	if (rc != 0)
 		goto neg_err_exit;
 
-	dialect = le16_to_cpu(pSMBr->DialectIndex);
-	cFYI(1, ("Dialect: %d", dialect));
+	server->dialect = le16_to_cpu(pSMBr->DialectIndex);
+	cFYI(1, "Dialect: %d", server->dialect);
 	/* Check wct = 1 error case */
-	if ((pSMBr->hdr.WordCount < 13) || (dialect == BAD_PROT)) {
+	if ((pSMBr->hdr.WordCount < 13) || (server->dialect == BAD_PROT)) {
 		/* core returns wct = 1, but we do not ask for core - otherwise
 		small wct just comes when dialect index is -1 indicating we
 		could not negotiate a common dialect */
@@ -419,8 +419,8 @@
 		goto neg_err_exit;
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
 	} else if ((pSMBr->hdr.WordCount == 13)
-			&& ((dialect == LANMAN_PROT)
-				|| (dialect == LANMAN2_PROT))) {
+			&& ((server->dialect == LANMAN_PROT)
+				|| (server->dialect == LANMAN2_PROT))) {
 		__s16 tmp;
 		struct lanman_neg_rsp *rsp = (struct lanman_neg_rsp *)pSMBr;
 
@@ -428,8 +428,8 @@
 			(secFlags & CIFSSEC_MAY_PLNTXT))
 			server->secType = LANMAN;
 		else {
-			cERROR(1, ("mount failed weak security disabled"
-				   " in /proc/fs/cifs/SecurityFlags"));
+			cERROR(1, "mount failed weak security disabled"
+				   " in /proc/fs/cifs/SecurityFlags");
 			rc = -EOPNOTSUPP;
 			goto neg_err_exit;
 		}
@@ -462,9 +462,9 @@
 			utc = CURRENT_TIME;
 			ts = cnvrtDosUnixTm(rsp->SrvTime.Date,
 					    rsp->SrvTime.Time, 0);
-			cFYI(1, ("SrvTime %d sec since 1970 (utc: %d) diff: %d",
+			cFYI(1, "SrvTime %d sec since 1970 (utc: %d) diff: %d",
 				(int)ts.tv_sec, (int)utc.tv_sec,
-				(int)(utc.tv_sec - ts.tv_sec)));
+				(int)(utc.tv_sec - ts.tv_sec));
 			val = (int)(utc.tv_sec - ts.tv_sec);
 			seconds = abs(val);
 			result = (seconds / MIN_TZ_ADJ) * MIN_TZ_ADJ;
@@ -478,7 +478,7 @@
 			server->timeAdj = (int)tmp;
 			server->timeAdj *= 60; /* also in seconds */
 		}
-		cFYI(1, ("server->timeAdj: %d seconds", server->timeAdj));
+		cFYI(1, "server->timeAdj: %d seconds", server->timeAdj);
 
 
 		/* BB get server time for time conversions and add
@@ -493,14 +493,14 @@
 			goto neg_err_exit;
 		}
 
-		cFYI(1, ("LANMAN negotiated"));
+		cFYI(1, "LANMAN negotiated");
 		/* we will not end up setting signing flags - as no signing
 		was in LANMAN and server did not return the flags on */
 		goto signing_check;
 #else /* weak security disabled */
 	} else if (pSMBr->hdr.WordCount == 13) {
-		cERROR(1, ("mount failed, cifs module not built "
-			  "with CIFS_WEAK_PW_HASH support"));
+		cERROR(1, "mount failed, cifs module not built "
+			  "with CIFS_WEAK_PW_HASH support");
 		rc = -EOPNOTSUPP;
 #endif /* WEAK_PW_HASH */
 		goto neg_err_exit;
@@ -512,14 +512,14 @@
 	/* else wct == 17 NTLM */
 	server->secMode = pSMBr->SecurityMode;
 	if ((server->secMode & SECMODE_USER) == 0)
-		cFYI(1, ("share mode security"));
+		cFYI(1, "share mode security");
 
 	if ((server->secMode & SECMODE_PW_ENCRYPT) == 0)
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
 		if ((secFlags & CIFSSEC_MAY_PLNTXT) == 0)
 #endif /* CIFS_WEAK_PW_HASH */
-			cERROR(1, ("Server requests plain text password"
-				  " but client support disabled"));
+			cERROR(1, "Server requests plain text password"
+				  " but client support disabled");
 
 	if ((secFlags & CIFSSEC_MUST_NTLMV2) == CIFSSEC_MUST_NTLMV2)
 		server->secType = NTLMv2;
@@ -539,7 +539,7 @@
 #endif */
 	else {
 		rc = -EOPNOTSUPP;
-		cERROR(1, ("Invalid security type"));
+		cERROR(1, "Invalid security type");
 		goto neg_err_exit;
 	}
 	/* else ... any others ...? */
@@ -551,7 +551,7 @@
 	server->maxBuf = min(le32_to_cpu(pSMBr->MaxBufferSize),
 			(__u32) CIFSMaxBufSize + MAX_CIFS_HDR_SIZE);
 	server->max_rw = le32_to_cpu(pSMBr->MaxRawSize);
-	cFYI(DBG2, ("Max buf = %d", ses->server->maxBuf));
+	cFYI(DBG2, "Max buf = %d", ses->server->maxBuf);
 	GETU32(ses->server->sessid) = le32_to_cpu(pSMBr->SessionKey);
 	server->capabilities = le32_to_cpu(pSMBr->Capabilities);
 	server->timeAdj = (int)(__s16)le16_to_cpu(pSMBr->ServerTimeZone);
@@ -582,7 +582,7 @@
 			if (memcmp(server->server_GUID,
 				   pSMBr->u.extended_response.
 				   GUID, 16) != 0) {
-				cFYI(1, ("server UID changed"));
+				cFYI(1, "server UID changed");
 				memcpy(server->server_GUID,
 					pSMBr->u.extended_response.GUID,
 					16);
@@ -597,13 +597,19 @@
 			server->secType = RawNTLMSSP;
 		} else {
 			rc = decode_negTokenInit(pSMBr->u.extended_response.
-						 SecurityBlob,
-						 count - 16,
-						 &server->secType);
+						 SecurityBlob, count - 16,
+						 server);
 			if (rc == 1)
 				rc = 0;
 			else
 				rc = -EINVAL;
+
+			if (server->sec_kerberos || server->sec_mskerberos)
+				server->secType = Kerberos;
+			else if (server->sec_ntlmssp)
+				server->secType = RawNTLMSSP;
+			else
+				rc = -EOPNOTSUPP;
 		}
 	} else
 		server->capabilities &= ~CAP_EXTENDED_SECURITY;
@@ -614,22 +620,21 @@
 	if ((secFlags & CIFSSEC_MAY_SIGN) == 0) {
 		/* MUST_SIGN already includes the MAY_SIGN FLAG
 		   so if this is zero it means that signing is disabled */
-		cFYI(1, ("Signing disabled"));
+		cFYI(1, "Signing disabled");
 		if (server->secMode & SECMODE_SIGN_REQUIRED) {
-			cERROR(1, ("Server requires "
+			cERROR(1, "Server requires "
 				   "packet signing to be enabled in "
-				   "/proc/fs/cifs/SecurityFlags."));
+				   "/proc/fs/cifs/SecurityFlags.");
 			rc = -EOPNOTSUPP;
 		}
 		server->secMode &=
 			~(SECMODE_SIGN_ENABLED | SECMODE_SIGN_REQUIRED);
 	} else if ((secFlags & CIFSSEC_MUST_SIGN) == CIFSSEC_MUST_SIGN) {
 		/* signing required */
-		cFYI(1, ("Must sign - secFlags 0x%x", secFlags));
+		cFYI(1, "Must sign - secFlags 0x%x", secFlags);
 		if ((server->secMode &
 			(SECMODE_SIGN_ENABLED | SECMODE_SIGN_REQUIRED)) == 0) {
-			cERROR(1,
-				("signing required but server lacks support"));
+			cERROR(1, "signing required but server lacks support");
 			rc = -EOPNOTSUPP;
 		} else
 			server->secMode |= SECMODE_SIGN_REQUIRED;
@@ -643,7 +648,7 @@
 neg_err_exit:
 	cifs_buf_release(pSMB);
 
-	cFYI(1, ("negprot rc %d", rc));
+	cFYI(1, "negprot rc %d", rc);
 	return rc;
 }
 
@@ -653,7 +658,7 @@
 	struct smb_hdr *smb_buffer;
 	int rc = 0;
 
-	cFYI(1, ("In tree disconnect"));
+	cFYI(1, "In tree disconnect");
 
 	/* BB: do we need to check this? These should never be NULL. */
 	if ((tcon->ses == NULL) || (tcon->ses->server == NULL))
@@ -675,7 +680,7 @@
 
 	rc = SendReceiveNoRsp(xid, tcon->ses, smb_buffer, 0);
 	if (rc)
-		cFYI(1, ("Tree disconnect failed %d", rc));
+		cFYI(1, "Tree disconnect failed %d", rc);
 
 	/* No need to return error on this operation if tid invalidated and
 	   closed on server already e.g. due to tcp session crashing */
@@ -691,7 +696,7 @@
 	LOGOFF_ANDX_REQ *pSMB;
 	int rc = 0;
 
-	cFYI(1, ("In SMBLogoff for session disconnect"));
+	cFYI(1, "In SMBLogoff for session disconnect");
 
 	/*
 	 * BB: do we need to check validity of ses and server? They should
@@ -744,7 +749,7 @@
 	int bytes_returned = 0;
 	__u16 params, param_offset, offset, byte_count;
 
-	cFYI(1, ("In POSIX delete"));
+	cFYI(1, "In POSIX delete");
 PsxDelete:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -796,7 +801,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc)
-		cFYI(1, ("Posix delete returned %d", rc));
+		cFYI(1, "Posix delete returned %d", rc);
 	cifs_buf_release(pSMB);
 
 	cifs_stats_inc(&tcon->num_deletes);
@@ -843,7 +848,7 @@
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&tcon->num_deletes);
 	if (rc)
-		cFYI(1, ("Error in RMFile = %d", rc));
+		cFYI(1, "Error in RMFile = %d", rc);
 
 	cifs_buf_release(pSMB);
 	if (rc == -EAGAIN)
@@ -862,7 +867,7 @@
 	int bytes_returned;
 	int name_len;
 
-	cFYI(1, ("In CIFSSMBRmDir"));
+	cFYI(1, "In CIFSSMBRmDir");
 RmDirRetry:
 	rc = smb_init(SMB_COM_DELETE_DIRECTORY, 0, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -887,7 +892,7 @@
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&tcon->num_rmdirs);
 	if (rc)
-		cFYI(1, ("Error in RMDir = %d", rc));
+		cFYI(1, "Error in RMDir = %d", rc);
 
 	cifs_buf_release(pSMB);
 	if (rc == -EAGAIN)
@@ -905,7 +910,7 @@
 	int bytes_returned;
 	int name_len;
 
-	cFYI(1, ("In CIFSSMBMkDir"));
+	cFYI(1, "In CIFSSMBMkDir");
 MkDirRetry:
 	rc = smb_init(SMB_COM_CREATE_DIRECTORY, 0, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -930,7 +935,7 @@
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&tcon->num_mkdirs);
 	if (rc)
-		cFYI(1, ("Error in Mkdir = %d", rc));
+		cFYI(1, "Error in Mkdir = %d", rc);
 
 	cifs_buf_release(pSMB);
 	if (rc == -EAGAIN)
@@ -953,7 +958,7 @@
 	OPEN_PSX_REQ *pdata;
 	OPEN_PSX_RSP *psx_rsp;
 
-	cFYI(1, ("In POSIX Create"));
+	cFYI(1, "In POSIX Create");
 PsxCreat:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -1007,11 +1012,11 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Posix create returned %d", rc));
+		cFYI(1, "Posix create returned %d", rc);
 		goto psx_create_err;
 	}
 
-	cFYI(1, ("copying inode info"));
+	cFYI(1, "copying inode info");
 	rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
 	if (rc || (pSMBr->ByteCount < sizeof(OPEN_PSX_RSP))) {
@@ -1033,11 +1038,11 @@
 	/* check to make sure response data is there */
 	if (psx_rsp->ReturnedLevel != cpu_to_le16(SMB_QUERY_FILE_UNIX_BASIC)) {
 		pRetData->Type = cpu_to_le32(-1); /* unknown */
-		cFYI(DBG2, ("unknown type"));
+		cFYI(DBG2, "unknown type");
 	} else {
 		if (pSMBr->ByteCount < sizeof(OPEN_PSX_RSP)
 					+ sizeof(FILE_UNIX_BASIC_INFO)) {
-			cERROR(1, ("Open response data too small"));
+			cERROR(1, "Open response data too small");
 			pRetData->Type = cpu_to_le32(-1);
 			goto psx_create_err;
 		}
@@ -1084,7 +1089,7 @@
 			ofun = SMBOPEN_OCREATE | SMBOPEN_OTRUNC;
 			break;
 		default:
-			cFYI(1, ("unknown disposition %d", disposition));
+			cFYI(1, "unknown disposition %d", disposition);
 			ofun =  SMBOPEN_OAPPEND; /* regular open */
 	}
 	return ofun;
@@ -1175,7 +1180,7 @@
 			(struct smb_hdr *)pSMBr, &bytes_returned, CIFS_LONG_OP);
 	cifs_stats_inc(&tcon->num_opens);
 	if (rc) {
-		cFYI(1, ("Error in Open = %d", rc));
+		cFYI(1, "Error in Open = %d", rc);
 	} else {
 	/* BB verify if wct == 15 */
 
@@ -1288,7 +1293,7 @@
 			(struct smb_hdr *)pSMBr, &bytes_returned, CIFS_LONG_OP);
 	cifs_stats_inc(&tcon->num_opens);
 	if (rc) {
-		cFYI(1, ("Error in Open = %d", rc));
+		cFYI(1, "Error in Open = %d", rc);
 	} else {
 		*pOplock = pSMBr->OplockLevel; /* 1 byte no need to le_to_cpu */
 		*netfid = pSMBr->Fid;	/* cifs fid stays in le */
@@ -1326,7 +1331,7 @@
 	int resp_buf_type = 0;
 	struct kvec iov[1];
 
-	cFYI(1, ("Reading %d bytes on fid %d", count, netfid));
+	cFYI(1, "Reading %d bytes on fid %d", count, netfid);
 	if (tcon->ses->capabilities & CAP_LARGE_FILES)
 		wct = 12;
 	else {
@@ -1371,7 +1376,7 @@
 	cifs_stats_inc(&tcon->num_reads);
 	pSMBr = (READ_RSP *)iov[0].iov_base;
 	if (rc) {
-		cERROR(1, ("Send error in read = %d", rc));
+		cERROR(1, "Send error in read = %d", rc);
 	} else {
 		int data_length = le16_to_cpu(pSMBr->DataLengthHigh);
 		data_length = data_length << 16;
@@ -1381,15 +1386,15 @@
 		/*check that DataLength would not go beyond end of SMB */
 		if ((data_length > CIFSMaxBufSize)
 				|| (data_length > count)) {
-			cFYI(1, ("bad length %d for count %d",
-				 data_length, count));
+			cFYI(1, "bad length %d for count %d",
+				 data_length, count);
 			rc = -EIO;
 			*nbytes = 0;
 		} else {
 			pReadData = (char *) (&pSMBr->hdr.Protocol) +
 					le16_to_cpu(pSMBr->DataOffset);
 /*			if (rc = copy_to_user(buf, pReadData, data_length)) {
-				cERROR(1,("Faulting on read rc = %d",rc));
+				cERROR(1, "Faulting on read rc = %d",rc);
 				rc = -EFAULT;
 			}*/ /* can not use copy_to_user when using page cache*/
 			if (*buf)
@@ -1433,7 +1438,7 @@
 
 	*nbytes = 0;
 
-	/* cFYI(1, ("write at %lld %d bytes", offset, count));*/
+	/* cFYI(1, "write at %lld %d bytes", offset, count);*/
 	if (tcon->ses == NULL)
 		return -ECONNABORTED;
 
@@ -1514,7 +1519,7 @@
 			 (struct smb_hdr *) pSMBr, &bytes_returned, long_op);
 	cifs_stats_inc(&tcon->num_writes);
 	if (rc) {
-		cFYI(1, ("Send error in write = %d", rc));
+		cFYI(1, "Send error in write = %d", rc);
 	} else {
 		*nbytes = le16_to_cpu(pSMBr->CountHigh);
 		*nbytes = (*nbytes) << 16;
@@ -1551,7 +1556,7 @@
 
 	*nbytes = 0;
 
-	cFYI(1, ("write2 at %lld %d bytes", (long long)offset, count));
+	cFYI(1, "write2 at %lld %d bytes", (long long)offset, count);
 
 	if (tcon->ses->capabilities & CAP_LARGE_FILES) {
 		wct = 14;
@@ -1606,7 +1611,7 @@
 			  long_op);
 	cifs_stats_inc(&tcon->num_writes);
 	if (rc) {
-		cFYI(1, ("Send error Write2 = %d", rc));
+		cFYI(1, "Send error Write2 = %d", rc);
 	} else if (resp_buf_type == 0) {
 		/* presumably this can not happen, but best to be safe */
 		rc = -EIO;
@@ -1651,7 +1656,7 @@
 	int timeout = 0;
 	__u16 count;
 
-	cFYI(1, ("CIFSSMBLock timeout %d numLock %d", (int)waitFlag, numLock));
+	cFYI(1, "CIFSSMBLock timeout %d numLock %d", (int)waitFlag, numLock);
 	rc = small_smb_init(SMB_COM_LOCKING_ANDX, 8, tcon, (void **) &pSMB);
 
 	if (rc)
@@ -1699,7 +1704,7 @@
 	}
 	cifs_stats_inc(&tcon->num_locks);
 	if (rc)
-		cFYI(1, ("Send error in Lock = %d", rc));
+		cFYI(1, "Send error in Lock = %d", rc);
 
 	/* Note: On -EAGAIN error only caller can retry on handle based calls
 	since file handle passed in no longer valid */
@@ -1722,7 +1727,7 @@
 	__u16 params, param_offset, offset, byte_count, count;
 	struct kvec iov[1];
 
-	cFYI(1, ("Posix Lock"));
+	cFYI(1, "Posix Lock");
 
 	if (pLockData == NULL)
 		return -EINVAL;
@@ -1792,7 +1797,7 @@
 	}
 
 	if (rc) {
-		cFYI(1, ("Send error in Posix Lock = %d", rc));
+		cFYI(1, "Send error in Posix Lock = %d", rc);
 	} else if (get_flag) {
 		/* lock structure can be returned on get */
 		__u16 data_offset;
@@ -1849,7 +1854,7 @@
 {
 	int rc = 0;
 	CLOSE_REQ *pSMB = NULL;
-	cFYI(1, ("In CIFSSMBClose"));
+	cFYI(1, "In CIFSSMBClose");
 
 /* do not retry on dead session on close */
 	rc = small_smb_init(SMB_COM_CLOSE, 3, tcon, (void **) &pSMB);
@@ -1866,7 +1871,7 @@
 	if (rc) {
 		if (rc != -EINTR) {
 			/* EINTR is expected when user ctl-c to kill app */
-			cERROR(1, ("Send error in Close = %d", rc));
+			cERROR(1, "Send error in Close = %d", rc);
 		}
 	}
 
@@ -1882,7 +1887,7 @@
 {
 	int rc = 0;
 	FLUSH_REQ *pSMB = NULL;
-	cFYI(1, ("In CIFSSMBFlush"));
+	cFYI(1, "In CIFSSMBFlush");
 
 	rc = small_smb_init(SMB_COM_FLUSH, 1, tcon, (void **) &pSMB);
 	if (rc)
@@ -1893,7 +1898,7 @@
 	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
 	cifs_stats_inc(&tcon->num_flushes);
 	if (rc)
-		cERROR(1, ("Send error in Flush = %d", rc));
+		cERROR(1, "Send error in Flush = %d", rc);
 
 	return rc;
 }
@@ -1910,7 +1915,7 @@
 	int name_len, name_len2;
 	__u16 count;
 
-	cFYI(1, ("In CIFSSMBRename"));
+	cFYI(1, "In CIFSSMBRename");
 renameRetry:
 	rc = smb_init(SMB_COM_RENAME, 1, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -1956,7 +1961,7 @@
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&tcon->num_renames);
 	if (rc)
-		cFYI(1, ("Send error in rename = %d", rc));
+		cFYI(1, "Send error in rename = %d", rc);
 
 	cifs_buf_release(pSMB);
 
@@ -1980,7 +1985,7 @@
 	int len_of_str;
 	__u16 params, param_offset, offset, count, byte_count;
 
-	cFYI(1, ("Rename to File by handle"));
+	cFYI(1, "Rename to File by handle");
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, pTcon, (void **) &pSMB,
 			(void **) &pSMBr);
 	if (rc)
@@ -2035,7 +2040,7 @@
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&pTcon->num_t2renames);
 	if (rc)
-		cFYI(1, ("Send error in Rename (by file handle) = %d", rc));
+		cFYI(1, "Send error in Rename (by file handle) = %d", rc);
 
 	cifs_buf_release(pSMB);
 
@@ -2057,7 +2062,7 @@
 	int name_len, name_len2;
 	__u16 count;
 
-	cFYI(1, ("In CIFSSMBCopy"));
+	cFYI(1, "In CIFSSMBCopy");
 copyRetry:
 	rc = smb_init(SMB_COM_COPY, 1, tcon, (void **) &pSMB,
 			(void **) &pSMBr);
@@ -2102,8 +2107,8 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 		(struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in copy = %d with %d files copied",
-			rc, le16_to_cpu(pSMBr->CopyCount)));
+		cFYI(1, "Send error in copy = %d with %d files copied",
+			rc, le16_to_cpu(pSMBr->CopyCount));
 	}
 	cifs_buf_release(pSMB);
 
@@ -2127,7 +2132,7 @@
 	int bytes_returned = 0;
 	__u16 params, param_offset, offset, byte_count;
 
-	cFYI(1, ("In Symlink Unix style"));
+	cFYI(1, "In Symlink Unix style");
 createSymLinkRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -2192,7 +2197,7 @@
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&tcon->num_symlinks);
 	if (rc)
-		cFYI(1, ("Send error in SetPathInfo create symlink = %d", rc));
+		cFYI(1, "Send error in SetPathInfo create symlink = %d", rc);
 
 	cifs_buf_release(pSMB);
 
@@ -2216,7 +2221,7 @@
 	int bytes_returned = 0;
 	__u16 params, param_offset, offset, byte_count;
 
-	cFYI(1, ("In Create Hard link Unix style"));
+	cFYI(1, "In Create Hard link Unix style");
 createHardLinkRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -2278,7 +2283,7 @@
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&tcon->num_hardlinks);
 	if (rc)
-		cFYI(1, ("Send error in SetPathInfo (hard link) = %d", rc));
+		cFYI(1, "Send error in SetPathInfo (hard link) = %d", rc);
 
 	cifs_buf_release(pSMB);
 	if (rc == -EAGAIN)
@@ -2299,7 +2304,7 @@
 	int name_len, name_len2;
 	__u16 count;
 
-	cFYI(1, ("In CIFSCreateHardLink"));
+	cFYI(1, "In CIFSCreateHardLink");
 winCreateHardLinkRetry:
 
 	rc = smb_init(SMB_COM_NT_RENAME, 4, tcon, (void **) &pSMB,
@@ -2350,7 +2355,7 @@
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&tcon->num_hardlinks);
 	if (rc)
-		cFYI(1, ("Send error in hard link (NT rename) = %d", rc));
+		cFYI(1, "Send error in hard link (NT rename) = %d", rc);
 
 	cifs_buf_release(pSMB);
 	if (rc == -EAGAIN)
@@ -2373,7 +2378,7 @@
 	__u16 params, byte_count;
 	char *data_start;
 
-	cFYI(1, ("In QPathSymLinkInfo (Unix) for path %s", searchName));
+	cFYI(1, "In QPathSymLinkInfo (Unix) for path %s", searchName);
 
 querySymLinkRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
@@ -2420,7 +2425,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QuerySymLinkInfo = %d", rc));
+		cFYI(1, "Send error in QuerySymLinkInfo = %d", rc);
 	} else {
 		/* decode response */
 
@@ -2521,21 +2526,21 @@
 
 	/* should we also check that parm and data areas do not overlap? */
 	if (*ppparm > end_of_smb) {
-		cFYI(1, ("parms start after end of smb"));
+		cFYI(1, "parms start after end of smb");
 		return -EINVAL;
 	} else if (parm_count + *ppparm > end_of_smb) {
-		cFYI(1, ("parm end after end of smb"));
+		cFYI(1, "parm end after end of smb");
 		return -EINVAL;
 	} else if (*ppdata > end_of_smb) {
-		cFYI(1, ("data starts after end of smb"));
+		cFYI(1, "data starts after end of smb");
 		return -EINVAL;
 	} else if (data_count + *ppdata > end_of_smb) {
-		cFYI(1, ("data %p + count %d (%p) ends after end of smb %p start %p",
+		cFYI(1, "data %p + count %d (%p) past smb end %p start %p",
 			*ppdata, data_count, (data_count + *ppdata),
-			end_of_smb, pSMBr));
+			end_of_smb, pSMBr);
 		return -EINVAL;
 	} else if (parm_count + data_count > pSMBr->ByteCount) {
-		cFYI(1, ("parm count and data count larger than SMB"));
+		cFYI(1, "parm count and data count larger than SMB");
 		return -EINVAL;
 	}
 	*pdatalen = data_count;
@@ -2554,7 +2559,7 @@
 	struct smb_com_transaction_ioctl_req *pSMB;
 	struct smb_com_transaction_ioctl_rsp *pSMBr;
 
-	cFYI(1, ("In Windows reparse style QueryLink for path %s", searchName));
+	cFYI(1, "In Windows reparse style QueryLink for path %s", searchName);
 	rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
 	if (rc)
@@ -2583,7 +2588,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QueryReparseLinkInfo = %d", rc));
+		cFYI(1, "Send error in QueryReparseLinkInfo = %d", rc);
 	} else {		/* decode response */
 		__u32 data_offset = le32_to_cpu(pSMBr->DataOffset);
 		__u32 data_count = le32_to_cpu(pSMBr->DataCount);
@@ -2607,7 +2612,7 @@
 			if ((reparse_buf->LinkNamesBuf +
 				reparse_buf->TargetNameOffset +
 				reparse_buf->TargetNameLen) > end_of_smb) {
-				cFYI(1, ("reparse buf beyond SMB"));
+				cFYI(1, "reparse buf beyond SMB");
 				rc = -EIO;
 				goto qreparse_out;
 			}
@@ -2628,12 +2633,12 @@
 			}
 		} else {
 			rc = -EIO;
-			cFYI(1, ("Invalid return data count on "
-				 "get reparse info ioctl"));
+			cFYI(1, "Invalid return data count on "
+				 "get reparse info ioctl");
 		}
 		symlinkinfo[buflen] = 0; /* just in case so the caller
 					does not go off the end of the buffer */
-		cFYI(1, ("readlink result - %s", symlinkinfo));
+		cFYI(1, "readlink result - %s", symlinkinfo);
 	}
 
 qreparse_out:
@@ -2656,7 +2661,7 @@
 	ace->e_perm = cpu_to_le16(cifs_ace->cifs_e_perm);
 	ace->e_tag  = cpu_to_le16(cifs_ace->cifs_e_tag);
 	ace->e_id   = cpu_to_le32(le64_to_cpu(cifs_ace->cifs_uid));
-	/* cFYI(1,("perm %d tag %d id %d",ace->e_perm,ace->e_tag,ace->e_id)); */
+	/* cFYI(1, "perm %d tag %d id %d",ace->e_perm,ace->e_tag,ace->e_id); */
 
 	return;
 }
@@ -2682,8 +2687,8 @@
 		size += sizeof(struct cifs_posix_ace) * count;
 		/* check if we would go beyond end of SMB */
 		if (size_of_data_area < size) {
-			cFYI(1, ("bad CIFS POSIX ACL size %d vs. %d",
-				size_of_data_area, size));
+			cFYI(1, "bad CIFS POSIX ACL size %d vs. %d",
+				size_of_data_area, size);
 			return -EINVAL;
 		}
 	} else if (acl_type & ACL_TYPE_DEFAULT) {
@@ -2730,7 +2735,7 @@
 		cifs_ace->cifs_uid = cpu_to_le64(-1);
 	} else
 		cifs_ace->cifs_uid = cpu_to_le64(le32_to_cpu(local_ace->e_id));
-	/*cFYI(1,("perm %d tag %d id %d",ace->e_perm,ace->e_tag,ace->e_id));*/
+	/*cFYI(1, "perm %d tag %d id %d",ace->e_perm,ace->e_tag,ace->e_id);*/
 	return rc;
 }
 
@@ -2748,12 +2753,12 @@
 		return 0;
 
 	count = posix_acl_xattr_count((size_t)buflen);
-	cFYI(1, ("setting acl with %d entries from buf of length %d and "
+	cFYI(1, "setting acl with %d entries from buf of length %d and "
 		"version of %d",
-		count, buflen, le32_to_cpu(local_acl->a_version)));
+		count, buflen, le32_to_cpu(local_acl->a_version));
 	if (le32_to_cpu(local_acl->a_version) != 2) {
-		cFYI(1, ("unknown POSIX ACL version %d",
-		     le32_to_cpu(local_acl->a_version)));
+		cFYI(1, "unknown POSIX ACL version %d",
+		     le32_to_cpu(local_acl->a_version));
 		return 0;
 	}
 	cifs_acl->version = cpu_to_le16(1);
@@ -2762,7 +2767,7 @@
 	else if (acl_type == ACL_TYPE_DEFAULT)
 		cifs_acl->default_entry_count = cpu_to_le16(count);
 	else {
-		cFYI(1, ("unknown ACL type %d", acl_type));
+		cFYI(1, "unknown ACL type %d", acl_type);
 		return 0;
 	}
 	for (i = 0; i < count; i++) {
@@ -2795,7 +2800,7 @@
 	int name_len;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In GetPosixACL (Unix) for path %s", searchName));
+	cFYI(1, "In GetPosixACL (Unix) for path %s", searchName);
 
 queryAclRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
@@ -2847,7 +2852,7 @@
 		(struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&tcon->num_acl_get);
 	if (rc) {
-		cFYI(1, ("Send error in Query POSIX ACL = %d", rc));
+		cFYI(1, "Send error in Query POSIX ACL = %d", rc);
 	} else {
 		/* decode response */
 
@@ -2884,7 +2889,7 @@
 	int bytes_returned = 0;
 	__u16 params, byte_count, data_count, param_offset, offset;
 
-	cFYI(1, ("In SetPosixACL (Unix) for path %s", fileName));
+	cFYI(1, "In SetPosixACL (Unix) for path %s", fileName);
 setAclRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -2939,7 +2944,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc)
-		cFYI(1, ("Set POSIX ACL returned %d", rc));
+		cFYI(1, "Set POSIX ACL returned %d", rc);
 
 setACLerrorExit:
 	cifs_buf_release(pSMB);
@@ -2959,7 +2964,7 @@
 	int bytes_returned;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In GetExtAttr"));
+	cFYI(1, "In GetExtAttr");
 	if (tcon == NULL)
 		return -ENODEV;
 
@@ -2998,7 +3003,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("error %d in GetExtAttr", rc));
+		cFYI(1, "error %d in GetExtAttr", rc);
 	} else {
 		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
@@ -3013,7 +3018,7 @@
 			struct file_chattr_info *pfinfo;
 			/* BB Do we need a cast or hash here ? */
 			if (count != 16) {
-				cFYI(1, ("Illegal size ret in GetExtAttr"));
+				cFYI(1, "Illegal size ret in GetExtAttr");
 				rc = -EIO;
 				goto GetExtAttrOut;
 			}
@@ -3043,7 +3048,7 @@
 	QUERY_SEC_DESC_REQ *pSMB;
 	struct kvec iov[1];
 
-	cFYI(1, ("GetCifsACL"));
+	cFYI(1, "GetCifsACL");
 
 	*pbuflen = 0;
 	*acl_inf = NULL;
@@ -3068,7 +3073,7 @@
 			 CIFS_STD_OP);
 	cifs_stats_inc(&tcon->num_acl_get);
 	if (rc) {
-		cFYI(1, ("Send error in QuerySecDesc = %d", rc));
+		cFYI(1, "Send error in QuerySecDesc = %d", rc);
 	} else {                /* decode response */
 		__le32 *parm;
 		__u32 parm_len;
@@ -3083,7 +3088,7 @@
 			goto qsec_out;
 		pSMBr = (struct smb_com_ntransact_rsp *)iov[0].iov_base;
 
-		cFYI(1, ("smb %p parm %p data %p", pSMBr, parm, *acl_inf));
+		cFYI(1, "smb %p parm %p data %p", pSMBr, parm, *acl_inf);
 
 		if (le32_to_cpu(pSMBr->ParameterCount) != 4) {
 			rc = -EIO;      /* bad smb */
@@ -3095,8 +3100,8 @@
 
 		acl_len = le32_to_cpu(*parm);
 		if (acl_len != *pbuflen) {
-			cERROR(1, ("acl length %d does not match %d",
-				   acl_len, *pbuflen));
+			cERROR(1, "acl length %d does not match %d",
+				   acl_len, *pbuflen);
 			if (*pbuflen > acl_len)
 				*pbuflen = acl_len;
 		}
@@ -3105,7 +3110,7 @@
 		   header followed by the smallest SID */
 		if ((*pbuflen < sizeof(struct cifs_ntsd) + 8) ||
 		    (*pbuflen >= 64 * 1024)) {
-			cERROR(1, ("bad acl length %d", *pbuflen));
+			cERROR(1, "bad acl length %d", *pbuflen);
 			rc = -EINVAL;
 			*pbuflen = 0;
 		} else {
@@ -3179,9 +3184,9 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 		(struct smb_hdr *) pSMBr, &bytes_returned, 0);
 
-	cFYI(1, ("SetCIFSACL bytes_returned: %d, rc: %d", bytes_returned, rc));
+	cFYI(1, "SetCIFSACL bytes_returned: %d, rc: %d", bytes_returned, rc);
 	if (rc)
-		cFYI(1, ("Set CIFS ACL returned %d", rc));
+		cFYI(1, "Set CIFS ACL returned %d", rc);
 	cifs_buf_release(pSMB);
 
 	if (rc == -EAGAIN)
@@ -3205,7 +3210,7 @@
 	int bytes_returned;
 	int name_len;
 
-	cFYI(1, ("In SMBQPath path %s", searchName));
+	cFYI(1, "In SMBQPath path %s", searchName);
 QInfRetry:
 	rc = smb_init(SMB_COM_QUERY_INFORMATION, 0, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -3231,7 +3236,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QueryInfo = %d", rc));
+		cFYI(1, "Send error in QueryInfo = %d", rc);
 	} else if (pFinfo) {
 		struct timespec ts;
 		__u32 time = le32_to_cpu(pSMBr->last_write_time);
@@ -3305,7 +3310,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QPathInfo = %d", rc));
+		cFYI(1, "Send error in QPathInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -3343,7 +3348,7 @@
 	int name_len;
 	__u16 params, byte_count;
 
-/* cFYI(1, ("In QPathInfo path %s", searchName)); */
+/* cFYI(1, "In QPathInfo path %s", searchName); */
 QPathInfoRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -3393,7 +3398,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QPathInfo = %d", rc));
+		cFYI(1, "Send error in QPathInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -3473,14 +3478,14 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QPathInfo = %d", rc));
+		cFYI(1, "Send error in QPathInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
 		if (rc || (pSMBr->ByteCount < sizeof(FILE_UNIX_BASIC_INFO))) {
-			cERROR(1, ("Malformed FILE_UNIX_BASIC_INFO response.\n"
+			cERROR(1, "Malformed FILE_UNIX_BASIC_INFO response.\n"
 				   "Unix Extensions can be disabled on mount "
-				   "by specifying the nosfu mount option."));
+				   "by specifying the nosfu mount option.");
 			rc = -EIO;	/* bad smb */
 		} else {
 			__u16 data_offset = le16_to_cpu(pSMBr->t2.DataOffset);
@@ -3512,7 +3517,7 @@
 	int name_len;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In QPathInfo (Unix) the path %s", searchName));
+	cFYI(1, "In QPathInfo (Unix) the path %s", searchName);
 UnixQPathInfoRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -3559,14 +3564,14 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QPathInfo = %d", rc));
+		cFYI(1, "Send error in QPathInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
 		if (rc || (pSMBr->ByteCount < sizeof(FILE_UNIX_BASIC_INFO))) {
-			cERROR(1, ("Malformed FILE_UNIX_BASIC_INFO response.\n"
+			cERROR(1, "Malformed FILE_UNIX_BASIC_INFO response.\n"
 				   "Unix Extensions can be disabled on mount "
-				   "by specifying the nosfu mount option."));
+				   "by specifying the nosfu mount option.");
 			rc = -EIO;	/* bad smb */
 		} else {
 			__u16 data_offset = le16_to_cpu(pSMBr->t2.DataOffset);
@@ -3600,7 +3605,7 @@
 	int name_len;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In FindFirst for %s", searchName));
+	cFYI(1, "In FindFirst for %s", searchName);
 
 findFirstRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
@@ -3677,7 +3682,7 @@
 	if (rc) {/* BB add logic to retry regular search if Unix search
 			rejected unexpectedly by server */
 		/* BB Add code to handle unsupported level rc */
-		cFYI(1, ("Error in FindFirst = %d", rc));
+		cFYI(1, "Error in FindFirst = %d", rc);
 
 		cifs_buf_release(pSMB);
 
@@ -3716,7 +3721,7 @@
 			lnoff = le16_to_cpu(parms->LastNameOffset);
 			if (tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE <
 			      lnoff) {
-				cERROR(1, ("ignoring corrupt resume name"));
+				cERROR(1, "ignoring corrupt resume name");
 				psrch_inf->last_entry = NULL;
 				return rc;
 			}
@@ -3744,7 +3749,7 @@
 	int bytes_returned, name_len;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In FindNext"));
+	cFYI(1, "In FindNext");
 
 	if (psrch_inf->endOfSearch)
 		return -ENOENT;
@@ -3808,7 +3813,7 @@
 			cifs_buf_release(pSMB);
 			rc = 0; /* search probably was closed at end of search*/
 		} else
-			cFYI(1, ("FindNext returned = %d", rc));
+			cFYI(1, "FindNext returned = %d", rc);
 	} else {                /* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -3844,15 +3849,15 @@
 			lnoff = le16_to_cpu(parms->LastNameOffset);
 			if (tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE <
 			      lnoff) {
-				cERROR(1, ("ignoring corrupt resume name"));
+				cERROR(1, "ignoring corrupt resume name");
 				psrch_inf->last_entry = NULL;
 				return rc;
 			} else
 				psrch_inf->last_entry =
 					psrch_inf->srch_entries_start + lnoff;
 
-/*  cFYI(1,("fnxt2 entries in buf %d index_of_last %d",
-	    psrch_inf->entries_in_buffer, psrch_inf->index_of_last_entry)); */
+/*  cFYI(1, "fnxt2 entries in buf %d index_of_last %d",
+	    psrch_inf->entries_in_buffer, psrch_inf->index_of_last_entry); */
 
 			/* BB fixme add unlock here */
 		}
@@ -3877,7 +3882,7 @@
 	int rc = 0;
 	FINDCLOSE_REQ *pSMB = NULL;
 
-	cFYI(1, ("In CIFSSMBFindClose"));
+	cFYI(1, "In CIFSSMBFindClose");
 	rc = small_smb_init(SMB_COM_FIND_CLOSE2, 1, tcon, (void **)&pSMB);
 
 	/* no sense returning error if session restarted
@@ -3891,7 +3896,7 @@
 	pSMB->ByteCount = 0;
 	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
 	if (rc)
-		cERROR(1, ("Send error in FindClose = %d", rc));
+		cERROR(1, "Send error in FindClose = %d", rc);
 
 	cifs_stats_inc(&tcon->num_fclose);
 
@@ -3914,7 +3919,7 @@
 	int name_len, bytes_returned;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In GetSrvInodeNum for %s", searchName));
+	cFYI(1, "In GetSrvInodeNum for %s", searchName);
 	if (tcon == NULL)
 		return -ENODEV;
 
@@ -3964,7 +3969,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 		(struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("error %d in QueryInternalInfo", rc));
+		cFYI(1, "error %d in QueryInternalInfo", rc);
 	} else {
 		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
@@ -3979,7 +3984,7 @@
 			struct file_internal_info *pfinfo;
 			/* BB Do we need a cast or hash here ? */
 			if (count < 8) {
-				cFYI(1, ("Illegal size ret in QryIntrnlInf"));
+				cFYI(1, "Illegal size ret in QryIntrnlInf");
 				rc = -EIO;
 				goto GetInodeNumOut;
 			}
@@ -4020,16 +4025,16 @@
 	*num_of_nodes = le16_to_cpu(pSMBr->NumberOfReferrals);
 
 	if (*num_of_nodes < 1) {
-		cERROR(1, ("num_referrals: must be at least > 0,"
-			"but we get num_referrals = %d\n", *num_of_nodes));
+		cERROR(1, "num_referrals: must be at least > 0,"
+			"but we get num_referrals = %d\n", *num_of_nodes);
 		rc = -EINVAL;
 		goto parse_DFS_referrals_exit;
 	}
 
 	ref = (struct dfs_referral_level_3 *) &(pSMBr->referrals);
 	if (ref->VersionNumber != cpu_to_le16(3)) {
-		cERROR(1, ("Referrals of V%d version are not supported,"
-			"should be V3", le16_to_cpu(ref->VersionNumber)));
+		cERROR(1, "Referrals of V%d version are not supported,"
+			"should be V3", le16_to_cpu(ref->VersionNumber));
 		rc = -EINVAL;
 		goto parse_DFS_referrals_exit;
 	}
@@ -4038,14 +4043,14 @@
 	data_end = (char *)(&(pSMBr->PathConsumed)) +
 				le16_to_cpu(pSMBr->t2.DataCount);
 
-	cFYI(1, ("num_referrals: %d dfs flags: 0x%x ... \n",
+	cFYI(1, "num_referrals: %d dfs flags: 0x%x ...\n",
 			*num_of_nodes,
-			le32_to_cpu(pSMBr->DFSFlags)));
+			le32_to_cpu(pSMBr->DFSFlags));
 
 	*target_nodes = kzalloc(sizeof(struct dfs_info3_param) *
 			*num_of_nodes, GFP_KERNEL);
 	if (*target_nodes == NULL) {
-		cERROR(1, ("Failed to allocate buffer for target_nodes\n"));
+		cERROR(1, "Failed to allocate buffer for target_nodes\n");
 		rc = -ENOMEM;
 		goto parse_DFS_referrals_exit;
 	}
@@ -4121,7 +4126,7 @@
 	*num_of_nodes = 0;
 	*target_nodes = NULL;
 
-	cFYI(1, ("In GetDFSRefer the path %s", searchName));
+	cFYI(1, "In GetDFSRefer the path %s", searchName);
 	if (ses == NULL)
 		return -ENODEV;
 getDFSRetry:
@@ -4188,7 +4193,7 @@
 	rc = SendReceive(xid, ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in GetDFSRefer = %d", rc));
+		cFYI(1, "Send error in GetDFSRefer = %d", rc);
 		goto GetDFSRefExit;
 	}
 	rc = validate_t2((struct smb_t2_rsp *)pSMBr);
@@ -4199,9 +4204,9 @@
 		goto GetDFSRefExit;
 	}
 
-	cFYI(1, ("Decoding GetDFSRefer response BCC: %d  Offset %d",
+	cFYI(1, "Decoding GetDFSRefer response BCC: %d  Offset %d",
 				pSMBr->ByteCount,
-				le16_to_cpu(pSMBr->t2.DataOffset)));
+				le16_to_cpu(pSMBr->t2.DataOffset));
 
 	/* parse returned result into more usable form */
 	rc = parse_DFS_referrals(pSMBr, num_of_nodes,
@@ -4229,7 +4234,7 @@
 	int bytes_returned = 0;
 	__u16 params, byte_count;
 
-	cFYI(1, ("OldQFSInfo"));
+	cFYI(1, "OldQFSInfo");
 oldQFSInfoRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		(void **) &pSMBr);
@@ -4262,7 +4267,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 		(struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QFSInfo = %d", rc));
+		cFYI(1, "Send error in QFSInfo = %d", rc);
 	} else {                /* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -4270,8 +4275,8 @@
 			rc = -EIO;      /* bad smb */
 		else {
 			__u16 data_offset = le16_to_cpu(pSMBr->t2.DataOffset);
-			cFYI(1, ("qfsinf resp BCC: %d  Offset %d",
-				 pSMBr->ByteCount, data_offset));
+			cFYI(1, "qfsinf resp BCC: %d  Offset %d",
+				 pSMBr->ByteCount, data_offset);
 
 			response_data = (FILE_SYSTEM_ALLOC_INFO *)
 				(((char *) &pSMBr->hdr.Protocol) + data_offset);
@@ -4283,11 +4288,10 @@
 			       le32_to_cpu(response_data->TotalAllocationUnits);
 			FSData->f_bfree = FSData->f_bavail =
 				le32_to_cpu(response_data->FreeAllocationUnits);
-			cFYI(1,
-			     ("Blocks: %lld  Free: %lld Block size %ld",
-			      (unsigned long long)FSData->f_blocks,
-			      (unsigned long long)FSData->f_bfree,
-			      FSData->f_bsize));
+			cFYI(1, "Blocks: %lld  Free: %lld Block size %ld",
+			     (unsigned long long)FSData->f_blocks,
+			     (unsigned long long)FSData->f_bfree,
+			     FSData->f_bsize);
 		}
 	}
 	cifs_buf_release(pSMB);
@@ -4309,7 +4313,7 @@
 	int bytes_returned = 0;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In QFSInfo"));
+	cFYI(1, "In QFSInfo");
 QFSInfoRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -4342,7 +4346,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QFSInfo = %d", rc));
+		cFYI(1, "Send error in QFSInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -4363,11 +4367,10 @@
 			    le64_to_cpu(response_data->TotalAllocationUnits);
 			FSData->f_bfree = FSData->f_bavail =
 			    le64_to_cpu(response_data->FreeAllocationUnits);
-			cFYI(1,
-			     ("Blocks: %lld  Free: %lld Block size %ld",
-			      (unsigned long long)FSData->f_blocks,
-			      (unsigned long long)FSData->f_bfree,
-			      FSData->f_bsize));
+			cFYI(1, "Blocks: %lld  Free: %lld Block size %ld",
+			     (unsigned long long)FSData->f_blocks,
+			     (unsigned long long)FSData->f_bfree,
+			     FSData->f_bsize);
 		}
 	}
 	cifs_buf_release(pSMB);
@@ -4389,7 +4392,7 @@
 	int bytes_returned = 0;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In QFSAttributeInfo"));
+	cFYI(1, "In QFSAttributeInfo");
 QFSAttributeRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -4423,7 +4426,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cERROR(1, ("Send error in QFSAttributeInfo = %d", rc));
+		cERROR(1, "Send error in QFSAttributeInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -4459,7 +4462,7 @@
 	int bytes_returned = 0;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In QFSDeviceInfo"));
+	cFYI(1, "In QFSDeviceInfo");
 QFSDeviceRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -4494,7 +4497,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QFSDeviceInfo = %d", rc));
+		cFYI(1, "Send error in QFSDeviceInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -4529,7 +4532,7 @@
 	int bytes_returned = 0;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In QFSUnixInfo"));
+	cFYI(1, "In QFSUnixInfo");
 QFSUnixRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -4563,7 +4566,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cERROR(1, ("Send error in QFSUnixInfo = %d", rc));
+		cERROR(1, "Send error in QFSUnixInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -4598,7 +4601,7 @@
 	int bytes_returned = 0;
 	__u16 params, param_offset, offset, byte_count;
 
-	cFYI(1, ("In SETFSUnixInfo"));
+	cFYI(1, "In SETFSUnixInfo");
 SETFSUnixRetry:
 	/* BB switch to small buf init to save memory */
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
@@ -4646,7 +4649,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cERROR(1, ("Send error in SETFSUnixInfo = %d", rc));
+		cERROR(1, "Send error in SETFSUnixInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 		if (rc)
@@ -4674,7 +4677,7 @@
 	int bytes_returned = 0;
 	__u16 params, byte_count;
 
-	cFYI(1, ("In QFSPosixInfo"));
+	cFYI(1, "In QFSPosixInfo");
 QFSPosixRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -4708,7 +4711,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QFSUnixInfo = %d", rc));
+		cFYI(1, "Send error in QFSUnixInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -4768,7 +4771,7 @@
 	int bytes_returned = 0;
 	__u16 params, byte_count, data_count, param_offset, offset;
 
-	cFYI(1, ("In SetEOF"));
+	cFYI(1, "In SetEOF");
 SetEOFRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -4834,7 +4837,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc)
-		cFYI(1, ("SetPathInfo (file size) returned %d", rc));
+		cFYI(1, "SetPathInfo (file size) returned %d", rc);
 
 	cifs_buf_release(pSMB);
 
@@ -4854,8 +4857,8 @@
 	int rc = 0;
 	__u16 params, param_offset, offset, byte_count, count;
 
-	cFYI(1, ("SetFileSize (via SetFileInfo) %lld",
-			(long long)size));
+	cFYI(1, "SetFileSize (via SetFileInfo) %lld",
+			(long long)size);
 	rc = small_smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB);
 
 	if (rc)
@@ -4914,9 +4917,7 @@
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
 	if (rc) {
-		cFYI(1,
-		     ("Send error in SetFileInfo (SetFileSize) = %d",
-		      rc));
+		cFYI(1, "Send error in SetFileInfo (SetFileSize) = %d", rc);
 	}
 
 	/* Note: On -EAGAIN error only caller can retry on handle based calls
@@ -4940,7 +4941,7 @@
 	int rc = 0;
 	__u16 params, param_offset, offset, byte_count, count;
 
-	cFYI(1, ("Set Times (via SetFileInfo)"));
+	cFYI(1, "Set Times (via SetFileInfo)");
 	rc = small_smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB);
 
 	if (rc)
@@ -4985,7 +4986,7 @@
 	memcpy(data_offset, data, sizeof(FILE_BASIC_INFO));
 	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
 	if (rc)
-		cFYI(1, ("Send error in Set Time (SetFileInfo) = %d", rc));
+		cFYI(1, "Send error in Set Time (SetFileInfo) = %d", rc);
 
 	/* Note: On -EAGAIN error only caller can retry on handle based calls
 		since file handle passed in no longer valid */
@@ -5002,7 +5003,7 @@
 	int rc = 0;
 	__u16 params, param_offset, offset, byte_count, count;
 
-	cFYI(1, ("Set File Disposition (via SetFileInfo)"));
+	cFYI(1, "Set File Disposition (via SetFileInfo)");
 	rc = small_smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB);
 
 	if (rc)
@@ -5044,7 +5045,7 @@
 	*data_offset = delete_file ? 1 : 0;
 	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
 	if (rc)
-		cFYI(1, ("Send error in SetFileDisposition = %d", rc));
+		cFYI(1, "Send error in SetFileDisposition = %d", rc);
 
 	return rc;
 }
@@ -5062,7 +5063,7 @@
 	char *data_offset;
 	__u16 params, param_offset, offset, byte_count, count;
 
-	cFYI(1, ("In SetTimes"));
+	cFYI(1, "In SetTimes");
 
 SetTimesRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
@@ -5118,7 +5119,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc)
-		cFYI(1, ("SetPathInfo (times) returned %d", rc));
+		cFYI(1, "SetPathInfo (times) returned %d", rc);
 
 	cifs_buf_release(pSMB);
 
@@ -5143,7 +5144,7 @@
 	int bytes_returned;
 	int name_len;
 
-	cFYI(1, ("In SetAttrLegacy"));
+	cFYI(1, "In SetAttrLegacy");
 
 SetAttrLgcyRetry:
 	rc = smb_init(SMB_COM_SETATTR, 8, tcon, (void **) &pSMB,
@@ -5169,7 +5170,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc)
-		cFYI(1, ("Error in LegacySetAttr = %d", rc));
+		cFYI(1, "Error in LegacySetAttr = %d", rc);
 
 	cifs_buf_release(pSMB);
 
@@ -5231,7 +5232,7 @@
 	int rc = 0;
 	u16 params, param_offset, offset, byte_count, count;
 
-	cFYI(1, ("Set Unix Info (via SetFileInfo)"));
+	cFYI(1, "Set Unix Info (via SetFileInfo)");
 	rc = small_smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB);
 
 	if (rc)
@@ -5276,7 +5277,7 @@
 
 	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
 	if (rc)
-		cFYI(1, ("Send error in Set Time (SetFileInfo) = %d", rc));
+		cFYI(1, "Send error in Set Time (SetFileInfo) = %d", rc);
 
 	/* Note: On -EAGAIN error only caller can retry on handle based calls
 		since file handle passed in no longer valid */
@@ -5297,7 +5298,7 @@
 	FILE_UNIX_BASIC_INFO *data_offset;
 	__u16 params, param_offset, offset, count, byte_count;
 
-	cFYI(1, ("In SetUID/GID/Mode"));
+	cFYI(1, "In SetUID/GID/Mode");
 setPermsRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -5353,7 +5354,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc)
-		cFYI(1, ("SetPathInfo (perms) returned %d", rc));
+		cFYI(1, "SetPathInfo (perms) returned %d", rc);
 
 	cifs_buf_release(pSMB);
 	if (rc == -EAGAIN)
@@ -5372,7 +5373,7 @@
 	struct dir_notify_req *dnotify_req;
 	int bytes_returned;
 
-	cFYI(1, ("In CIFSSMBNotify for file handle %d", (int)netfid));
+	cFYI(1, "In CIFSSMBNotify for file handle %d", (int)netfid);
 	rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
 	if (rc)
@@ -5406,7 +5407,7 @@
 			 (struct smb_hdr *)pSMBr, &bytes_returned,
 			 CIFS_ASYNC_OP);
 	if (rc) {
-		cFYI(1, ("Error in Notify = %d", rc));
+		cFYI(1, "Error in Notify = %d", rc);
 	} else {
 		/* Add file to outstanding requests */
 		/* BB change to kmem cache alloc */
@@ -5462,7 +5463,7 @@
 	char *end_of_smb;
 	__u16 params, byte_count, data_offset;
 
-	cFYI(1, ("In Query All EAs path %s", searchName));
+	cFYI(1, "In Query All EAs path %s", searchName);
 QAllEAsRetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -5509,7 +5510,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cFYI(1, ("Send error in QueryAllEAs = %d", rc));
+		cFYI(1, "Send error in QueryAllEAs = %d", rc);
 		goto QAllEAsOut;
 	}
 
@@ -5537,16 +5538,16 @@
 				(((char *) &pSMBr->hdr.Protocol) + data_offset);
 
 	list_len = le32_to_cpu(ea_response_data->list_len);
-	cFYI(1, ("ea length %d", list_len));
+	cFYI(1, "ea length %d", list_len);
 	if (list_len <= 8) {
-		cFYI(1, ("empty EA list returned from server"));
+		cFYI(1, "empty EA list returned from server");
 		goto QAllEAsOut;
 	}
 
 	/* make sure list_len doesn't go past end of SMB */
 	end_of_smb = (char *)pByteArea(&pSMBr->hdr) + BCC(&pSMBr->hdr);
 	if ((char *)ea_response_data + list_len > end_of_smb) {
-		cFYI(1, ("EA list appears to go beyond SMB"));
+		cFYI(1, "EA list appears to go beyond SMB");
 		rc = -EIO;
 		goto QAllEAsOut;
 	}
@@ -5563,7 +5564,7 @@
 		temp_ptr += 4;
 		/* make sure we can read name_len and value_len */
 		if (list_len < 0) {
-			cFYI(1, ("EA entry goes beyond length of list"));
+			cFYI(1, "EA entry goes beyond length of list");
 			rc = -EIO;
 			goto QAllEAsOut;
 		}
@@ -5572,7 +5573,7 @@
 		value_len = le16_to_cpu(temp_fea->value_len);
 		list_len -= name_len + 1 + value_len;
 		if (list_len < 0) {
-			cFYI(1, ("EA entry goes beyond length of list"));
+			cFYI(1, "EA entry goes beyond length of list");
 			rc = -EIO;
 			goto QAllEAsOut;
 		}
@@ -5639,7 +5640,7 @@
 	int bytes_returned = 0;
 	__u16 params, param_offset, byte_count, offset, count;
 
-	cFYI(1, ("In SetEA"));
+	cFYI(1, "In SetEA");
 SetEARetry:
 	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
 		      (void **) &pSMBr);
@@ -5721,7 +5722,7 @@
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc)
-		cFYI(1, ("SetPathInfo (EA) returned %d", rc));
+		cFYI(1, "SetPathInfo (EA) returned %d", rc);
 
 	cifs_buf_release(pSMB);
 

fs/cifs/connect.c

diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index d9566bf..2208f06 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -102,6 +102,7 @@
 	bool sockopt_tcp_nodelay:1;
 	unsigned short int port;
 	char *prepath;
+	struct nls_table *local_nls;
 };
 
 static int ipv4_connect(struct TCP_Server_Info *server);
@@ -135,7 +136,7 @@
 	spin_unlock(&GlobalMid_Lock);
 	server->maxBuf = 0;
 
-	cFYI(1, ("Reconnecting tcp session"));
+	cFYI(1, "Reconnecting tcp session");
 
 	/* before reconnecting the tcp session, mark the smb session (uid)
 		and the tid bad so they are not used until reconnected */
@@ -153,12 +154,12 @@
 	/* do not want to be sending data on a socket we are freeing */
 	mutex_lock(&server->srv_mutex);
 	if (server->ssocket) {
-		cFYI(1, ("State: 0x%x Flags: 0x%lx", server->ssocket->state,
-			server->ssocket->flags));
+		cFYI(1, "State: 0x%x Flags: 0x%lx", server->ssocket->state,
+			server->ssocket->flags);
 		kernel_sock_shutdown(server->ssocket, SHUT_WR);
-		cFYI(1, ("Post shutdown state: 0x%x Flags: 0x%lx",
+		cFYI(1, "Post shutdown state: 0x%x Flags: 0x%lx",
 			server->ssocket->state,
-			server->ssocket->flags));
+			server->ssocket->flags);
 		sock_release(server->ssocket);
 		server->ssocket = NULL;
 	}
@@ -187,7 +188,7 @@
 		else
 			rc = ipv4_connect(server);
 		if (rc) {
-			cFYI(1, ("reconnect error %d", rc));
+			cFYI(1, "reconnect error %d", rc);
 			msleep(3000);
 		} else {
 			atomic_inc(&tcpSesReconnectCount);
@@ -223,7 +224,7 @@
 	/* check for plausible wct, bcc and t2 data and parm sizes */
 	/* check for parm and data offset going beyond end of smb */
 	if (pSMB->WordCount != 10) { /* coalesce_t2 depends on this */
-		cFYI(1, ("invalid transact2 word count"));
+		cFYI(1, "invalid transact2 word count");
 		return -EINVAL;
 	}
 
@@ -237,15 +238,15 @@
 	if (remaining == 0)
 		return 0;
 	else if (remaining < 0) {
-		cFYI(1, ("total data %d smaller than data in frame %d",
-			total_data_size, data_in_this_rsp));
+		cFYI(1, "total data %d smaller than data in frame %d",
+			total_data_size, data_in_this_rsp);
 		return -EINVAL;
 	} else {
-		cFYI(1, ("missing %d bytes from transact2, check next response",
-			remaining));
+		cFYI(1, "missing %d bytes from transact2, check next response",
+			remaining);
 		if (total_data_size > maxBufSize) {
-			cERROR(1, ("TotalDataSize %d is over maximum buffer %d",
-				total_data_size, maxBufSize));
+			cERROR(1, "TotalDataSize %d is over maximum buffer %d",
+				total_data_size, maxBufSize);
 			return -EINVAL;
 		}
 		return remaining;
@@ -267,7 +268,7 @@
 	total_data_size = le16_to_cpu(pSMBt->t2_rsp.TotalDataCount);
 
 	if (total_data_size != le16_to_cpu(pSMB2->t2_rsp.TotalDataCount)) {
-		cFYI(1, ("total data size of primary and secondary t2 differ"));
+		cFYI(1, "total data size of primary and secondary t2 differ");
 	}
 
 	total_in_buf = le16_to_cpu(pSMBt->t2_rsp.DataCount);
@@ -282,7 +283,7 @@
 
 	total_in_buf2 = le16_to_cpu(pSMB2->t2_rsp.DataCount);
 	if (remaining < total_in_buf2) {
-		cFYI(1, ("transact2 2nd response contains too much data"));
+		cFYI(1, "transact2 2nd response contains too much data");
 	}
 
 	/* find end of first SMB data area */
@@ -311,7 +312,7 @@
 	pTargetSMB->smb_buf_length = byte_count;
 
 	if (remaining == total_in_buf2) {
-		cFYI(1, ("found the last secondary response"));
+		cFYI(1, "found the last secondary response");
 		return 0; /* we are done */
 	} else /* more responses to go */
 		return 1;
@@ -339,7 +340,7 @@
 	int reconnect;
 
 	current->flags |= PF_MEMALLOC;
-	cFYI(1, ("Demultiplex PID: %d", task_pid_nr(current)));
+	cFYI(1, "Demultiplex PID: %d", task_pid_nr(current));
 
 	length = atomic_inc_return(&tcpSesAllocCount);
 	if (length > 1)
@@ -353,7 +354,7 @@
 		if (bigbuf == NULL) {
 			bigbuf = cifs_buf_get();
 			if (!bigbuf) {
-				cERROR(1, ("No memory for large SMB response"));
+				cERROR(1, "No memory for large SMB response");
 				msleep(3000);
 				/* retry will check if exiting */
 				continue;
@@ -366,7 +367,7 @@
 		if (smallbuf == NULL) {
 			smallbuf = cifs_small_buf_get();
 			if (!smallbuf) {
-				cERROR(1, ("No memory for SMB response"));
+				cERROR(1, "No memory for SMB response");
 				msleep(1000);
 				/* retry will check if exiting */
 				continue;
@@ -391,9 +392,9 @@
 		if (server->tcpStatus == CifsExiting) {
 			break;
 		} else if (server->tcpStatus == CifsNeedReconnect) {
-			cFYI(1, ("Reconnect after server stopped responding"));
+			cFYI(1, "Reconnect after server stopped responding");
 			cifs_reconnect(server);
-			cFYI(1, ("call to reconnect done"));
+			cFYI(1, "call to reconnect done");
 			csocket = server->ssocket;
 			continue;
 		} else if ((length == -ERESTARTSYS) || (length == -EAGAIN)) {
@@ -411,7 +412,7 @@
 				continue;
 		} else if (length <= 0) {
 			if (server->tcpStatus == CifsNew) {
-				cFYI(1, ("tcp session abend after SMBnegprot"));
+				cFYI(1, "tcp session abend after SMBnegprot");
 				/* some servers kill the TCP session rather than
 				   returning an SMB negprot error, in which
 				   case reconnecting here is not going to help,
@@ -419,18 +420,18 @@
 				break;
 			}
 			if (!try_to_freeze() && (length == -EINTR)) {
-				cFYI(1, ("cifsd thread killed"));
+				cFYI(1, "cifsd thread killed");
 				break;
 			}
-			cFYI(1, ("Reconnect after unexpected peek error %d",
-				length));
+			cFYI(1, "Reconnect after unexpected peek error %d",
+				length);
 			cifs_reconnect(server);
 			csocket = server->ssocket;
 			wake_up(&server->response_q);
 			continue;
 		} else if (length < pdu_length) {
-			cFYI(1, ("requested %d bytes but only got %d bytes",
-				  pdu_length, length));
+			cFYI(1, "requested %d bytes but only got %d bytes",
+				  pdu_length, length);
 			pdu_length -= length;
 			msleep(1);
 			goto incomplete_rcv;
@@ -450,18 +451,18 @@
 		pdu_length = be32_to_cpu((__force __be32)smb_buffer->smb_buf_length);
 		smb_buffer->smb_buf_length = pdu_length;
 
-		cFYI(1, ("rfc1002 length 0x%x", pdu_length+4));
+		cFYI(1, "rfc1002 length 0x%x", pdu_length+4);
 
 		if (temp == (char) RFC1002_SESSION_KEEP_ALIVE) {
 			continue;
 		} else if (temp == (char)RFC1002_POSITIVE_SESSION_RESPONSE) {
-			cFYI(1, ("Good RFC 1002 session rsp"));
+			cFYI(1, "Good RFC 1002 session rsp");
 			continue;
 		} else if (temp == (char)RFC1002_NEGATIVE_SESSION_RESPONSE) {
 			/* we get this from Windows 98 instead of
 			   an error on SMB negprot response */
-			cFYI(1, ("Negative RFC1002 Session Response Error 0x%x)",
-				pdu_length));
+			cFYI(1, "Negative RFC1002 Session Response Error 0x%x)",
+				pdu_length);
 			if (server->tcpStatus == CifsNew) {
 				/* if nack on negprot (rather than
 				ret of smb negprot error) reconnecting
@@ -484,7 +485,7 @@
 				continue;
 			}
 		} else if (temp != (char) 0) {
-			cERROR(1, ("Unknown RFC 1002 frame"));
+			cERROR(1, "Unknown RFC 1002 frame");
 			cifs_dump_mem(" Received Data: ", (char *)smb_buffer,
 				      length);
 			cifs_reconnect(server);
@@ -495,8 +496,8 @@
 		/* else we have an SMB response */
 		if ((pdu_length > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) ||
 			    (pdu_length < sizeof(struct smb_hdr) - 1 - 4)) {
-			cERROR(1, ("Invalid size SMB length %d pdu_length %d",
-					length, pdu_length+4));
+			cERROR(1, "Invalid size SMB length %d pdu_length %d",
+					length, pdu_length+4);
 			cifs_reconnect(server);
 			csocket = server->ssocket;
 			wake_up(&server->response_q);
@@ -539,8 +540,8 @@
 				length = 0;
 				continue;
 			} else if (length <= 0) {
-				cERROR(1, ("Received no data, expecting %d",
-					      pdu_length - total_read));
+				cERROR(1, "Received no data, expecting %d",
+					      pdu_length - total_read);
 				cifs_reconnect(server);
 				csocket = server->ssocket;
 				reconnect = 1;
@@ -588,7 +589,7 @@
 						}
 					} else {
 						if (!isLargeBuf) {
-							cERROR(1,("1st trans2 resp needs bigbuf"));
+							cERROR(1, "1st trans2 resp needs bigbuf");
 					/* BB maybe we can fix this up,  switch
 					   to already allocated large buffer? */
 						} else {
@@ -630,8 +631,8 @@
 			wake_up_process(task_to_wake);
 		} else if (!is_valid_oplock_break(smb_buffer, server) &&
 			   !isMultiRsp) {
-			cERROR(1, ("No task to wake, unknown frame received! "
-				   "NumMids %d", midCount.counter));
+			cERROR(1, "No task to wake, unknown frame received! "
+				   "NumMids %d", midCount.counter);
 			cifs_dump_mem("Received Data is: ", (char *)smb_buffer,
 				      sizeof(struct smb_hdr));
 #ifdef CONFIG_CIFS_DEBUG2
@@ -708,8 +709,8 @@
 		list_for_each(tmp, &server->pending_mid_q) {
 		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
 			if (mid_entry->midState == MID_REQUEST_SUBMITTED) {
-				cFYI(1, ("Clearing Mid 0x%x - waking up ",
-					 mid_entry->mid));
+				cFYI(1, "Clearing Mid 0x%x - waking up ",
+					 mid_entry->mid);
 				task_to_wake = mid_entry->tsk;
 				if (task_to_wake)
 					wake_up_process(task_to_wake);
@@ -728,7 +729,7 @@
 		to wait at least 45 seconds before giving up
 		on a request getting a response and going ahead
 		and killing cifsd */
-		cFYI(1, ("Wait for exit from demultiplex thread"));
+		cFYI(1, "Wait for exit from demultiplex thread");
 		msleep(46000);
 		/* if threads still have not exited they are probably never
 		coming home not much else we can do but free the memory */
@@ -849,7 +850,7 @@
 			separator[0] = options[4];
 			options += 5;
 		} else {
-			cFYI(1, ("Null separator not allowed"));
+			cFYI(1, "Null separator not allowed");
 		}
 	}
 
@@ -974,7 +975,7 @@
 			}
 		} else if (strnicmp(data, "sec", 3) == 0) {
 			if (!value || !*value) {
-				cERROR(1, ("no security value specified"));
+				cERROR(1, "no security value specified");
 				continue;
 			} else if (strnicmp(value, "krb5i", 5) == 0) {
 				vol->secFlg |= CIFSSEC_MAY_KRB5 |
@@ -982,7 +983,7 @@
 			} else if (strnicmp(value, "krb5p", 5) == 0) {
 				/* vol->secFlg |= CIFSSEC_MUST_SEAL |
 					CIFSSEC_MAY_KRB5; */
-				cERROR(1, ("Krb5 cifs privacy not supported"));
+				cERROR(1, "Krb5 cifs privacy not supported");
 				return 1;
 			} else if (strnicmp(value, "krb5", 4) == 0) {
 				vol->secFlg |= CIFSSEC_MAY_KRB5;
@@ -1014,7 +1015,7 @@
 			} else if (strnicmp(value, "none", 4) == 0) {
 				vol->nullauth = 1;
 			} else {
-				cERROR(1, ("bad security option: %s", value));
+				cERROR(1, "bad security option: %s", value);
 				return 1;
 			}
 		} else if ((strnicmp(data, "unc", 3) == 0)
@@ -1053,7 +1054,7 @@
 			a domain name and need special handling? */
 			if (strnlen(value, 256) < 256) {
 				vol->domainname = value;
-				cFYI(1, ("Domain name set"));
+				cFYI(1, "Domain name set");
 			} else {
 				printk(KERN_WARNING "CIFS: domain name too "
 						    "long\n");
@@ -1076,7 +1077,7 @@
 					strcpy(vol->prepath+1, value);
 				} else
 					strcpy(vol->prepath, value);
-				cFYI(1, ("prefix path %s", vol->prepath));
+				cFYI(1, "prefix path %s", vol->prepath);
 			} else {
 				printk(KERN_WARNING "CIFS: prefix too long\n");
 				return 1;
@@ -1092,7 +1093,7 @@
 					vol->iocharset = value;
 				/* if iocharset not set then load_nls_default
 				   is used by caller */
-				cFYI(1, ("iocharset set to %s", value));
+				cFYI(1, "iocharset set to %s", value);
 			} else {
 				printk(KERN_WARNING "CIFS: iocharset name "
 						    "too long.\n");
@@ -1144,14 +1145,14 @@
 			}
 		} else if (strnicmp(data, "sockopt", 5) == 0) {
 			if (!value || !*value) {
-				cERROR(1, ("no socket option specified"));
+				cERROR(1, "no socket option specified");
 				continue;
 			} else if (strnicmp(value, "TCP_NODELAY", 11) == 0) {
 				vol->sockopt_tcp_nodelay = 1;
 			}
 		} else if (strnicmp(data, "netbiosname", 4) == 0) {
 			if (!value || !*value || (*value == ' ')) {
-				cFYI(1, ("invalid (empty) netbiosname"));
+				cFYI(1, "invalid (empty) netbiosname");
 			} else {
 				memset(vol->source_rfc1001_name, 0x20, 15);
 				for (i = 0; i < 15; i++) {
@@ -1175,7 +1176,7 @@
 		} else if (strnicmp(data, "servern", 7) == 0) {
 			/* servernetbiosname specified override *SMBSERVER */
 			if (!value || !*value || (*value == ' ')) {
-				cFYI(1, ("empty server netbiosname specified"));
+				cFYI(1, "empty server netbiosname specified");
 			} else {
 				/* last byte, type, is 0x20 for servr type */
 				memset(vol->target_rfc1001_name, 0x20, 16);
@@ -1434,7 +1435,7 @@
 
 		++server->srv_count;
 		write_unlock(&cifs_tcp_ses_lock);
-		cFYI(1, ("Existing tcp session with server found"));
+		cFYI(1, "Existing tcp session with server found");
 		return server;
 	}
 	write_unlock(&cifs_tcp_ses_lock);
@@ -1475,7 +1476,7 @@
 
 	memset(&addr, 0, sizeof(struct sockaddr_storage));
 
-	cFYI(1, ("UNC: %s ip: %s", volume_info->UNC, volume_info->UNCip));
+	cFYI(1, "UNC: %s ip: %s", volume_info->UNC, volume_info->UNCip);
 
 	if (volume_info->UNCip && volume_info->UNC) {
 		rc = cifs_convert_address(volume_info->UNCip, &addr);
@@ -1487,13 +1488,12 @@
 	} else if (volume_info->UNCip) {
 		/* BB using ip addr as tcp_ses name to connect to the
 		   DFS root below */
-		cERROR(1, ("Connecting to DFS root not implemented yet"));
+		cERROR(1, "Connecting to DFS root not implemented yet");
 		rc = -EINVAL;
 		goto out_err;
 	} else /* which tcp_sess DFS root would we conect to */ {
-		cERROR(1,
-		       ("CIFS mount error: No UNC path (e.g. -o "
-			"unc=//192.168.1.100/public) specified"));
+		cERROR(1, "CIFS mount error: No UNC path (e.g. -o "
+			"unc=//192.168.1.100/public) specified");
 		rc = -EINVAL;
 		goto out_err;
 	}
@@ -1540,7 +1540,7 @@
 	++tcp_ses->srv_count;
 
 	if (addr.ss_family == AF_INET6) {
-		cFYI(1, ("attempting ipv6 connect"));
+		cFYI(1, "attempting ipv6 connect");
 		/* BB should we allow ipv6 on port 139? */
 		/* other OS never observed in Wild doing 139 with v6 */
 		sin_server6->sin6_port = htons(volume_info->port);
@@ -1554,7 +1554,7 @@
 		rc = ipv4_connect(tcp_ses);
 	}
 	if (rc < 0) {
-		cERROR(1, ("Error connecting to socket. Aborting operation"));
+		cERROR(1, "Error connecting to socket. Aborting operation");
 		goto out_err;
 	}
 
@@ -1567,7 +1567,7 @@
 				  tcp_ses, "cifsd");
 	if (IS_ERR(tcp_ses->tsk)) {
 		rc = PTR_ERR(tcp_ses->tsk);
-		cERROR(1, ("error %d create cifsd thread", rc));
+		cERROR(1, "error %d create cifsd thread", rc);
 		module_put(THIS_MODULE);
 		goto out_err;
 	}
@@ -1616,6 +1616,7 @@
 	int xid;
 	struct TCP_Server_Info *server = ses->server;
 
+	cFYI(1, "%s: ses_count=%d\n", __func__, ses->ses_count);
 	write_lock(&cifs_tcp_ses_lock);
 	if (--ses->ses_count > 0) {
 		write_unlock(&cifs_tcp_ses_lock);
@@ -1634,6 +1635,102 @@
 	cifs_put_tcp_session(server);
 }
 
+static struct cifsSesInfo *
+cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
+{
+	int rc = -ENOMEM, xid;
+	struct cifsSesInfo *ses;
+
+	xid = GetXid();
+
+	ses = cifs_find_smb_ses(server, volume_info->username);
+	if (ses) {
+		cFYI(1, "Existing smb sess found (status=%d)", ses->status);
+
+		/* existing SMB ses has a server reference already */
+		cifs_put_tcp_session(server);
+
+		mutex_lock(&ses->session_mutex);
+		rc = cifs_negotiate_protocol(xid, ses);
+		if (rc) {
+			mutex_unlock(&ses->session_mutex);
+			/* problem -- put our ses reference */
+			cifs_put_smb_ses(ses);
+			FreeXid(xid);
+			return ERR_PTR(rc);
+		}
+		if (ses->need_reconnect) {
+			cFYI(1, "Session needs reconnect");
+			rc = cifs_setup_session(xid, ses,
+						volume_info->local_nls);
+			if (rc) {
+				mutex_unlock(&ses->session_mutex);
+				/* problem -- put our reference */
+				cifs_put_smb_ses(ses);
+				FreeXid(xid);
+				return ERR_PTR(rc);
+			}
+		}
+		mutex_unlock(&ses->session_mutex);
+		FreeXid(xid);
+		return ses;
+	}
+
+	cFYI(1, "Existing smb sess not found");
+	ses = sesInfoAlloc();
+	if (ses == NULL)
+		goto get_ses_fail;
+
+	/* new SMB session uses our server ref */
+	ses->server = server;
+	if (server->addr.sockAddr6.sin6_family == AF_INET6)
+		sprintf(ses->serverName, "%pI6",
+			&server->addr.sockAddr6.sin6_addr);
+	else
+		sprintf(ses->serverName, "%pI4",
+			&server->addr.sockAddr.sin_addr.s_addr);
+
+	if (volume_info->username)
+		strncpy(ses->userName, volume_info->username,
+			MAX_USERNAME_SIZE);
+
+	/* volume_info->password freed at unmount */
+	if (volume_info->password) {
+		ses->password = kstrdup(volume_info->password, GFP_KERNEL);
+		if (!ses->password)
+			goto get_ses_fail;
+	}
+	if (volume_info->domainname) {
+		int len = strlen(volume_info->domainname);
+		ses->domainName = kmalloc(len + 1, GFP_KERNEL);
+		if (ses->domainName)
+			strcpy(ses->domainName, volume_info->domainname);
+	}
+	ses->linux_uid = volume_info->linux_uid;
+	ses->overrideSecFlg = volume_info->secFlg;
+
+	mutex_lock(&ses->session_mutex);
+	rc = cifs_negotiate_protocol(xid, ses);
+	if (!rc)
+		rc = cifs_setup_session(xid, ses, volume_info->local_nls);
+	mutex_unlock(&ses->session_mutex);
+	if (rc)
+		goto get_ses_fail;
+
+	/* success, put it on the list */
+	write_lock(&cifs_tcp_ses_lock);
+	list_add(&ses->smb_ses_list, &server->smb_ses_list);
+	write_unlock(&cifs_tcp_ses_lock);
+
+	FreeXid(xid);
+	return ses;
+
+get_ses_fail:
+	sesInfoFree(ses);
+	FreeXid(xid);
+	return ERR_PTR(rc);
+}
+
 static struct cifsTconInfo *
 cifs_find_tcon(struct cifsSesInfo *ses, const char *unc)
 {
@@ -1662,6 +1759,7 @@
 	int xid;
 	struct cifsSesInfo *ses = tcon->ses;
 
+	cFYI(1, "%s: tc_count=%d\n", __func__, tcon->tc_count);
 	write_lock(&cifs_tcp_ses_lock);
 	if (--tcon->tc_count > 0) {
 		write_unlock(&cifs_tcp_ses_lock);
@@ -1679,6 +1777,80 @@
 	cifs_put_smb_ses(ses);
 }
 
+static struct cifsTconInfo *
+cifs_get_tcon(struct cifsSesInfo *ses, struct smb_vol *volume_info)
+{
+	int rc, xid;
+	struct cifsTconInfo *tcon;
+
+	tcon = cifs_find_tcon(ses, volume_info->UNC);
+	if (tcon) {
+		cFYI(1, "Found match on UNC path");
+		/* existing tcon already has a reference */
+		cifs_put_smb_ses(ses);
+		if (tcon->seal != volume_info->seal)
+			cERROR(1, "transport encryption setting "
+				   "conflicts with existing tid");
+		return tcon;
+	}
+
+	tcon = tconInfoAlloc();
+	if (tcon == NULL) {
+		rc = -ENOMEM;
+		goto out_fail;
+	}
+
+	tcon->ses = ses;
+	if (volume_info->password) {
+		tcon->password = kstrdup(volume_info->password, GFP_KERNEL);
+		if (!tcon->password) {
+			rc = -ENOMEM;
+			goto out_fail;
+		}
+	}
+
+	if (strchr(volume_info->UNC + 3, '\\') == NULL
+	    && strchr(volume_info->UNC + 3, '/') == NULL) {
+		cERROR(1, "Missing share name");
+		rc = -ENODEV;
+		goto out_fail;
+	}
+
+	/* BB Do we need to wrap session_mutex around
+	 * this TCon call and Unix SetFS as
+	 * we do on SessSetup and reconnect? */
+	xid = GetXid();
+	rc = CIFSTCon(xid, ses, volume_info->UNC, tcon, volume_info->local_nls);
+	FreeXid(xid);
+	cFYI(1, "CIFS Tcon rc = %d", rc);
+	if (rc)
+		goto out_fail;
+
+	if (volume_info->nodfs) {
+		tcon->Flags &= ~SMB_SHARE_IS_IN_DFS;
+		cFYI(1, "DFS disabled (%d)", tcon->Flags);
+	}
+	tcon->seal = volume_info->seal;
+	/* we can have only one retry value for a connection
+	   to a share so for resources mounted more than once
+	   to the same server share the last value passed in
+	   for the retry flag is used */
+	tcon->retry = volume_info->retry;
+	tcon->nocase = volume_info->nocase;
+	tcon->local_lease = volume_info->local_lease;
+
+	write_lock(&cifs_tcp_ses_lock);
+	list_add(&tcon->tcon_list, &ses->tcon_list);
+	write_unlock(&cifs_tcp_ses_lock);
+
+	return tcon;
+
+out_fail:
+	tconInfoFree(tcon);
+	return ERR_PTR(rc);
+}
+
+
 int
 get_dfs_path(int xid, struct cifsSesInfo *pSesInfo, const char *old_path,
 	     const struct nls_table *nls_codepage, unsigned int *pnum_referrals,
@@ -1703,8 +1875,7 @@
 		strcpy(temp_unc + 2, pSesInfo->serverName);
 		strcpy(temp_unc + 2 + strlen(pSesInfo->serverName), "\\IPC$");
 		rc = CIFSTCon(xid, pSesInfo, temp_unc, NULL, nls_codepage);
-		cFYI(1,
-		     ("CIFS Tcon rc = %d ipc_tid = %d", rc, pSesInfo->ipc_tid));
+		cFYI(1, "CIFS Tcon rc = %d ipc_tid = %d", rc, pSesInfo->ipc_tid);
 		kfree(temp_unc);
 	}
 	if (rc == 0)
@@ -1777,12 +1948,12 @@
 		rc = sock_create_kern(PF_INET, SOCK_STREAM,
 				      IPPROTO_TCP, &socket);
 		if (rc < 0) {
-			cERROR(1, ("Error %d creating socket", rc));
+			cERROR(1, "Error %d creating socket", rc);
 			return rc;
 		}
 
 		/* BB other socket options to set KEEPALIVE, NODELAY? */
-		cFYI(1, ("Socket created"));
+		cFYI(1, "Socket created");
 		server->ssocket = socket;
 		socket->sk->sk_allocation = GFP_NOFS;
 		cifs_reclassify_socket4(socket);
@@ -1827,7 +1998,7 @@
 	if (!connected) {
 		if (orig_port)
 			server->addr.sockAddr.sin_port = orig_port;
-		cFYI(1, ("Error %d connecting to server via ipv4", rc));
+		cFYI(1, "Error %d connecting to server via ipv4", rc);
 		sock_release(socket);
 		server->ssocket = NULL;
 		return rc;
@@ -1855,12 +2026,12 @@
 		rc = kernel_setsockopt(socket, SOL_TCP, TCP_NODELAY,
 				(char *)&val, sizeof(val));
 		if (rc)
-			cFYI(1, ("set TCP_NODELAY socket option error %d", rc));
+			cFYI(1, "set TCP_NODELAY socket option error %d", rc);
 	}
 
-	 cFYI(1, ("sndbuf %d rcvbuf %d rcvtimeo 0x%lx",
+	 cFYI(1, "sndbuf %d rcvbuf %d rcvtimeo 0x%lx",
 		 socket->sk->sk_sndbuf,
-		 socket->sk->sk_rcvbuf, socket->sk->sk_rcvtimeo));
+		 socket->sk->sk_rcvbuf, socket->sk->sk_rcvtimeo);
 
 	/* send RFC1001 sessinit */
 	if (server->addr.sockAddr.sin_port == htons(RFC1001_PORT)) {
@@ -1938,13 +2109,13 @@
 		rc = sock_create_kern(PF_INET6, SOCK_STREAM,
 				      IPPROTO_TCP, &socket);
 		if (rc < 0) {
-			cERROR(1, ("Error %d creating ipv6 socket", rc));
+			cERROR(1, "Error %d creating ipv6 socket", rc);
 			socket = NULL;
 			return rc;
 		}
 
 		/* BB other socket options to set KEEPALIVE, NODELAY? */
-		cFYI(1, ("ipv6 Socket created"));
+		cFYI(1, "ipv6 Socket created");
 		server->ssocket = socket;
 		socket->sk->sk_allocation = GFP_NOFS;
 		cifs_reclassify_socket6(socket);
@@ -1988,7 +2159,7 @@
 	if (!connected) {
 		if (orig_port)
 			server->addr.sockAddr6.sin6_port = orig_port;
-		cFYI(1, ("Error %d connecting to server via ipv6", rc));
+		cFYI(1, "Error %d connecting to server via ipv6", rc);
 		sock_release(socket);
 		server->ssocket = NULL;
 		return rc;
@@ -2007,7 +2178,7 @@
 		rc = kernel_setsockopt(socket, SOL_TCP, TCP_NODELAY,
 				(char *)&val, sizeof(val));
 		if (rc)
-			cFYI(1, ("set TCP_NODELAY socket option error %d", rc));
+			cFYI(1, "set TCP_NODELAY socket option error %d", rc);
 	}
 
 	server->ssocket = socket;
@@ -2032,13 +2203,13 @@
 	if (vol_info && vol_info->no_linux_ext) {
 		tcon->fsUnixInfo.Capability = 0;
 		tcon->unix_ext = 0; /* Unix Extensions disabled */
-		cFYI(1, ("Linux protocol extensions disabled"));
+		cFYI(1, "Linux protocol extensions disabled");
 		return;
 	} else if (vol_info)
 		tcon->unix_ext = 1; /* Unix Extensions supported */
 
 	if (tcon->unix_ext == 0) {
-		cFYI(1, ("Unix extensions disabled so not set on reconnect"));
+		cFYI(1, "Unix extensions disabled so not set on reconnect");
 		return;
 	}
 
@@ -2054,12 +2225,11 @@
 				cap &= ~CIFS_UNIX_POSIX_ACL_CAP;
 			if ((saved_cap & CIFS_UNIX_POSIX_PATHNAMES_CAP) == 0) {
 				if (cap & CIFS_UNIX_POSIX_PATHNAMES_CAP)
-					cERROR(1, ("POSIXPATH support change"));
+					cERROR(1, "POSIXPATH support change");
 				cap &= ~CIFS_UNIX_POSIX_PATHNAMES_CAP;
 			} else if ((cap & CIFS_UNIX_POSIX_PATHNAMES_CAP) == 0) {
-				cERROR(1, ("possible reconnect error"));
-				cERROR(1,
-					("server disabled POSIX path support"));
+				cERROR(1, "possible reconnect error");
+				cERROR(1, "server disabled POSIX path support");
 			}
 		}
 
@@ -2067,7 +2237,7 @@
 		if (vol_info && vol_info->no_psx_acl)
 			cap &= ~CIFS_UNIX_POSIX_ACL_CAP;
 		else if (CIFS_UNIX_POSIX_ACL_CAP & cap) {
-			cFYI(1, ("negotiated posix acl support"));
+			cFYI(1, "negotiated posix acl support");
 			if (sb)
 				sb->s_flags |= MS_POSIXACL;
 		}
@@ -2075,7 +2245,7 @@
 		if (vol_info && vol_info->posix_paths == 0)
 			cap &= ~CIFS_UNIX_POSIX_PATHNAMES_CAP;
 		else if (cap & CIFS_UNIX_POSIX_PATHNAMES_CAP) {
-			cFYI(1, ("negotiate posix pathnames"));
+			cFYI(1, "negotiate posix pathnames");
 			if (sb)
 				CIFS_SB(sb)->mnt_cifs_flags |=
 					CIFS_MOUNT_POSIX_PATHS;
@@ -2090,39 +2260,38 @@
 		if (sb && (CIFS_SB(sb)->rsize > 127 * 1024)) {
 			if ((cap & CIFS_UNIX_LARGE_READ_CAP) == 0) {
 				CIFS_SB(sb)->rsize = 127 * 1024;
-				cFYI(DBG2,
-					("larger reads not supported by srv"));
+				cFYI(DBG2, "larger reads not supported by srv");
 			}
 		}
 
 
-		cFYI(1, ("Negotiate caps 0x%x", (int)cap));
+		cFYI(1, "Negotiate caps 0x%x", (int)cap);
 #ifdef CONFIG_CIFS_DEBUG2
 		if (cap & CIFS_UNIX_FCNTL_CAP)
-			cFYI(1, ("FCNTL cap"));
+			cFYI(1, "FCNTL cap");
 		if (cap & CIFS_UNIX_EXTATTR_CAP)
-			cFYI(1, ("EXTATTR cap"));
+			cFYI(1, "EXTATTR cap");
 		if (cap & CIFS_UNIX_POSIX_PATHNAMES_CAP)
-			cFYI(1, ("POSIX path cap"));
+			cFYI(1, "POSIX path cap");
 		if (cap & CIFS_UNIX_XATTR_CAP)
-			cFYI(1, ("XATTR cap"));
+			cFYI(1, "XATTR cap");
 		if (cap & CIFS_UNIX_POSIX_ACL_CAP)
-			cFYI(1, ("POSIX ACL cap"));
+			cFYI(1, "POSIX ACL cap");
 		if (cap & CIFS_UNIX_LARGE_READ_CAP)
-			cFYI(1, ("very large read cap"));
+			cFYI(1, "very large read cap");
 		if (cap & CIFS_UNIX_LARGE_WRITE_CAP)
-			cFYI(1, ("very large write cap"));
+			cFYI(1, "very large write cap");
 #endif /* CIFS_DEBUG2 */
 		if (CIFSSMBSetFSUnixInfo(xid, tcon, cap)) {
 			if (vol_info == NULL) {
-				cFYI(1, ("resetting capabilities failed"));
+				cFYI(1, "resetting capabilities failed");
 			} else
-				cERROR(1, ("Negotiating Unix capabilities "
+				cERROR(1, "Negotiating Unix capabilities "
 					   "with the server failed.  Consider "
 					   "mounting with the Unix Extensions\n"
 					   "disabled, if problems are found, "
 					   "by specifying the nounix mount "
-					   "option."));
+					   "option.");
 
 		}
 	}
@@ -2152,8 +2321,8 @@
 			  struct cifs_sb_info *cifs_sb)
 {
 	if (pvolume_info->rsize > CIFSMaxBufSize) {
-		cERROR(1, ("rsize %d too large, using MaxBufSize",
-			pvolume_info->rsize));
+		cERROR(1, "rsize %d too large, using MaxBufSize",
+			pvolume_info->rsize);
 		cifs_sb->rsize = CIFSMaxBufSize;
 	} else if ((pvolume_info->rsize) &&
 			(pvolume_info->rsize <= CIFSMaxBufSize))
@@ -2162,8 +2331,8 @@
 		cifs_sb->rsize = CIFSMaxBufSize;
 
 	if (pvolume_info->wsize > PAGEVEC_SIZE * PAGE_CACHE_SIZE) {
-		cERROR(1, ("wsize %d too large, using 4096 instead",
-			  pvolume_info->wsize));
+		cERROR(1, "wsize %d too large, using 4096 instead",
+			  pvolume_info->wsize);
 		cifs_sb->wsize = 4096;
 	} else if (pvolume_info->wsize)
 		cifs_sb->wsize = pvolume_info->wsize;
@@ -2181,7 +2350,7 @@
 	if (cifs_sb->rsize < 2048) {
 		cifs_sb->rsize = 2048;
 		/* Windows ME may prefer this */
-		cFYI(1, ("readsize set to minimum: 2048"));
+		cFYI(1, "readsize set to minimum: 2048");
 	}
 	/* calculate prepath */
 	cifs_sb->prepath = pvolume_info->prepath;
@@ -2199,8 +2368,8 @@
 	cifs_sb->mnt_gid = pvolume_info->linux_gid;
 	cifs_sb->mnt_file_mode = pvolume_info->file_mode;
 	cifs_sb->mnt_dir_mode = pvolume_info->dir_mode;
-	cFYI(1, ("file mode: 0x%x  dir mode: 0x%x",
-		cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode));
+	cFYI(1, "file mode: 0x%x  dir mode: 0x%x",
+		cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode);
 
 	if (pvolume_info->noperm)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM;
@@ -2229,13 +2398,13 @@
 	if (pvolume_info->dynperm)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DYNPERM;
 	if (pvolume_info->direct_io) {
-		cFYI(1, ("mounting share using direct i/o"));
+		cFYI(1, "mounting share using direct i/o");
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO;
 	}
 
 	if ((pvolume_info->cifs_acl) && (pvolume_info->dynperm))
-		cERROR(1, ("mount option dynperm ignored if cifsacl "
-			   "mount option supported"));
+		cERROR(1, "mount option dynperm ignored if cifsacl "
+			   "mount option supported");
 }
 
 static int
@@ -2262,7 +2431,7 @@
 {
 	struct smb_vol *volume_info;
 
-	if (!pvolume_info && !*pvolume_info)
+	if (!pvolume_info || !*pvolume_info)
 		return;
 
 	volume_info = *pvolume_info;
@@ -2344,11 +2513,11 @@
 	}
 
 	if (volume_info->nullauth) {
-		cFYI(1, ("null user"));
+		cFYI(1, "null user");
 		volume_info->username = "";
 	} else if (volume_info->username) {
 		/* BB fixme parse for domain name here */
-		cFYI(1, ("Username: %s", volume_info->username));
+		cFYI(1, "Username: %s", volume_info->username);
 	} else {
 		cifserror("No username specified");
 	/* In userspace mount helper we can get user name from alternate
@@ -2357,20 +2526,20 @@
 		goto out;
 	}
 
-
 	/* this is needed for ASCII cp to Unicode converts */
 	if (volume_info->iocharset == NULL) {
-		cifs_sb->local_nls = load_nls_default();
-	/* load_nls_default can not return null */
+		/* load_nls_default cannot return null */
+		volume_info->local_nls = load_nls_default();
 	} else {
-		cifs_sb->local_nls = load_nls(volume_info->iocharset);
-		if (cifs_sb->local_nls == NULL) {
-			cERROR(1, ("CIFS mount error: iocharset %s not found",
-				 volume_info->iocharset));
+		volume_info->local_nls = load_nls(volume_info->iocharset);
+		if (volume_info->local_nls == NULL) {
+			cERROR(1, "CIFS mount error: iocharset %s not found",
+				 volume_info->iocharset);
 			rc = -ELIBACC;
 			goto out;
 		}
 	}
+	cifs_sb->local_nls = volume_info->local_nls;
 
 	/* get a reference to a tcp session */
 	srvTcp = cifs_get_tcp_session(volume_info);
@@ -2379,148 +2548,30 @@
 		goto out;
 	}
 
-	pSesInfo = cifs_find_smb_ses(srvTcp, volume_info->username);
-	if (pSesInfo) {
-		cFYI(1, ("Existing smb sess found (status=%d)",
-			pSesInfo->status));
-		/*
-		 * The existing SMB session already has a reference to srvTcp,
-		 * so we can put back the extra one we got before
-		 */
-		cifs_put_tcp_session(srvTcp);
-
-		mutex_lock(&pSesInfo->session_mutex);
-		if (pSesInfo->need_reconnect) {
-			cFYI(1, ("Session needs reconnect"));
-			rc = cifs_setup_session(xid, pSesInfo,
-						cifs_sb->local_nls);
-		}
-		mutex_unlock(&pSesInfo->session_mutex);
-	} else if (!rc) {
-		cFYI(1, ("Existing smb sess not found"));
-		pSesInfo = sesInfoAlloc();
-		if (pSesInfo == NULL) {
-			rc = -ENOMEM;
-			goto mount_fail_check;
-		}
-
-		/* new SMB session uses our srvTcp ref */
-		pSesInfo->server = srvTcp;
-		if (srvTcp->addr.sockAddr6.sin6_family == AF_INET6)
-			sprintf(pSesInfo->serverName, "%pI6",
-				&srvTcp->addr.sockAddr6.sin6_addr);
-		else
-			sprintf(pSesInfo->serverName, "%pI4",
-				&srvTcp->addr.sockAddr.sin_addr.s_addr);
-
-		write_lock(&cifs_tcp_ses_lock);
-		list_add(&pSesInfo->smb_ses_list, &srvTcp->smb_ses_list);
-		write_unlock(&cifs_tcp_ses_lock);
-
-		/* volume_info->password freed at unmount */
-		if (volume_info->password) {
-			pSesInfo->password = kstrdup(volume_info->password,
-						     GFP_KERNEL);
-			if (!pSesInfo->password) {
-				rc = -ENOMEM;
-				goto mount_fail_check;
-			}
-		}
-		if (volume_info->username)
-			strncpy(pSesInfo->userName, volume_info->username,
-				MAX_USERNAME_SIZE);
-		if (volume_info->domainname) {
-			int len = strlen(volume_info->domainname);
-			pSesInfo->domainName = kmalloc(len + 1, GFP_KERNEL);
-			if (pSesInfo->domainName)
-				strcpy(pSesInfo->domainName,
-					volume_info->domainname);
-		}
-		pSesInfo->linux_uid = volume_info->linux_uid;
-		pSesInfo->overrideSecFlg = volume_info->secFlg;
-		mutex_lock(&pSesInfo->session_mutex);
-
-		/* BB FIXME need to pass vol->secFlgs BB */
-		rc = cifs_setup_session(xid, pSesInfo,
-					cifs_sb->local_nls);
-		mutex_unlock(&pSesInfo->session_mutex);
+	/* get a reference to a SMB session */
+	pSesInfo = cifs_get_smb_ses(srvTcp, volume_info);
+	if (IS_ERR(pSesInfo)) {
+		rc = PTR_ERR(pSesInfo);
+		pSesInfo = NULL;
+		goto mount_fail_check;
 	}
 
-	/* search for existing tcon to this server share */
-	if (!rc) {
-		setup_cifs_sb(volume_info, cifs_sb);
-
-		tcon = cifs_find_tcon(pSesInfo, volume_info->UNC);
-		if (tcon) {
-			cFYI(1, ("Found match on UNC path"));
-			/* existing tcon already has a reference */
-			cifs_put_smb_ses(pSesInfo);
-			if (tcon->seal != volume_info->seal)
-				cERROR(1, ("transport encryption setting "
-					   "conflicts with existing tid"));
-		} else {
-			tcon = tconInfoAlloc();
-			if (tcon == NULL) {
-				rc = -ENOMEM;
-				goto mount_fail_check;
-			}
-
-			tcon->ses = pSesInfo;
-			if (volume_info->password) {
-				tcon->password = kstrdup(volume_info->password,
-							 GFP_KERNEL);
-				if (!tcon->password) {
-					rc = -ENOMEM;
-					goto mount_fail_check;
-				}
-			}
-
-			if ((strchr(volume_info->UNC + 3, '\\') == NULL)
-			    && (strchr(volume_info->UNC + 3, '/') == NULL)) {
-				cERROR(1, ("Missing share name"));
-				rc = -ENODEV;
-				goto mount_fail_check;
-			} else {
-				/* BB Do we need to wrap sesSem around
-				 * this TCon call and Unix SetFS as
-				 * we do on SessSetup and reconnect? */
-				rc = CIFSTCon(xid, pSesInfo, volume_info->UNC,
-					      tcon, cifs_sb->local_nls);
-				cFYI(1, ("CIFS Tcon rc = %d", rc));
-				if (volume_info->nodfs) {
-					tcon->Flags &= ~SMB_SHARE_IS_IN_DFS;
-					cFYI(1, ("DFS disabled (%d)",
-						tcon->Flags));
-				}
-			}
-			if (rc)
-				goto remote_path_check;
-			tcon->seal = volume_info->seal;
-			write_lock(&cifs_tcp_ses_lock);
-			list_add(&tcon->tcon_list, &pSesInfo->tcon_list);
-			write_unlock(&cifs_tcp_ses_lock);
-		}
-
-		/* we can have only one retry value for a connection
-		   to a share so for resources mounted more than once
-		   to the same server share the last value passed in
-		   for the retry flag is used */
-		tcon->retry = volume_info->retry;
-		tcon->nocase = volume_info->nocase;
-		tcon->local_lease = volume_info->local_lease;
-	}
-	if (pSesInfo) {
-		if (pSesInfo->capabilities & CAP_LARGE_FILES)
-			sb->s_maxbytes = MAX_LFS_FILESIZE;
-		else
-			sb->s_maxbytes = MAX_NON_LFS;
-	}
+	setup_cifs_sb(volume_info, cifs_sb);
+	if (pSesInfo->capabilities & CAP_LARGE_FILES)
+		sb->s_maxbytes = MAX_LFS_FILESIZE;
+	else
+		sb->s_maxbytes = MAX_NON_LFS;
 
 	/* BB FIXME fix time_gran to be larger for LANMAN sessions */
 	sb->s_time_gran = 100;
 
-	if (rc)
+	/* search for existing tcon to this server share */
+	tcon = cifs_get_tcon(pSesInfo, volume_info);
+	if (IS_ERR(tcon)) {
+		rc = PTR_ERR(tcon);
+		tcon = NULL;
 		goto remote_path_check;
+	}
 
 	cifs_sb->tcon = tcon;
 
@@ -2544,7 +2595,7 @@
 
 	if ((tcon->unix_ext == 0) && (cifs_sb->rsize > (1024 * 127))) {
 		cifs_sb->rsize = 1024 * 127;
-		cFYI(DBG2, ("no very large read support, rsize now 127K"));
+		cFYI(DBG2, "no very large read support, rsize now 127K");
 	}
 	if (!(tcon->ses->capabilities & CAP_LARGE_WRITE_X))
 		cifs_sb->wsize = min(cifs_sb->wsize,
@@ -2593,7 +2644,7 @@
 			goto mount_fail_check;
 		}
 
-		cFYI(1, ("Getting referral for: %s", full_path));
+		cFYI(1, "Getting referral for: %s", full_path);
 		rc = get_dfs_path(xid, pSesInfo , full_path + 1,
 			cifs_sb->local_nls, &num_referrals, &referrals,
 			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
@@ -2707,7 +2758,7 @@
 		   by Samba (not sure whether other servers allow
 		   NTLMv2 password here) */
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
-		if ((extended_security & CIFSSEC_MAY_LANMAN) &&
+		if ((global_secflags & CIFSSEC_MAY_LANMAN) &&
 		    (ses->server->secType == LANMAN))
 			calc_lanman_hash(tcon->password, ses->server->cryptKey,
 					 ses->server->secMode &
@@ -2778,13 +2829,13 @@
 		if (length == 3) {
 			if ((bcc_ptr[0] == 'I') && (bcc_ptr[1] == 'P') &&
 			    (bcc_ptr[2] == 'C')) {
-				cFYI(1, ("IPC connection"));
+				cFYI(1, "IPC connection");
 				tcon->ipc = 1;
 			}
 		} else if (length == 2) {
 			if ((bcc_ptr[0] == 'A') && (bcc_ptr[1] == ':')) {
 				/* the most common case */
-				cFYI(1, ("disk share connection"));
+				cFYI(1, "disk share connection");
 			}
 		}
 		bcc_ptr += length + 1;
@@ -2797,7 +2848,7 @@
 						      bytes_left, is_unicode,
 						      nls_codepage);
 
-		cFYI(1, ("nativeFileSystem=%s", tcon->nativeFileSystem));
+		cFYI(1, "nativeFileSystem=%s", tcon->nativeFileSystem);
 
 		if ((smb_buffer_response->WordCount == 3) ||
 			 (smb_buffer_response->WordCount == 7))
@@ -2805,7 +2856,7 @@
 			tcon->Flags = le16_to_cpu(pSMBr->OptionalSupport);
 		else
 			tcon->Flags = 0;
-		cFYI(1, ("Tcon flags: 0x%x ", tcon->Flags));
+		cFYI(1, "Tcon flags: 0x%x ", tcon->Flags);
 	} else if ((rc == 0) && tcon == NULL) {
 		/* all we need to save for IPC$ connection */
 		ses->ipc_tid = smb_buffer_response->Tid;
@@ -2833,57 +2884,61 @@
 	return rc;
 }
 
-int cifs_setup_session(unsigned int xid, struct cifsSesInfo *pSesInfo,
-					   struct nls_table *nls_info)
+int cifs_negotiate_protocol(unsigned int xid, struct cifsSesInfo *ses)
 {
 	int rc = 0;
-	int first_time = 0;
-	struct TCP_Server_Info *server = pSesInfo->server;
+	struct TCP_Server_Info *server = ses->server;
 
-	/* what if server changes its buffer size after dropping the session? */
-	if (server->maxBuf == 0) /* no need to send on reconnect */ {
-		rc = CIFSSMBNegotiate(xid, pSesInfo);
-		if (rc == -EAGAIN) {
-			/* retry only once on 1st time connection */
-			rc = CIFSSMBNegotiate(xid, pSesInfo);
-			if (rc == -EAGAIN)
-				rc = -EHOSTDOWN;
-		}
-		if (rc == 0) {
-			spin_lock(&GlobalMid_Lock);
-			if (server->tcpStatus != CifsExiting)
-				server->tcpStatus = CifsGood;
-			else
-				rc = -EHOSTDOWN;
-			spin_unlock(&GlobalMid_Lock);
+	/* only send once per connect */
+	if (server->maxBuf != 0)
+		return 0;
 
-		}
-		first_time = 1;
+	rc = CIFSSMBNegotiate(xid, ses);
+	if (rc == -EAGAIN) {
+		/* retry only once on 1st time connection */
+		rc = CIFSSMBNegotiate(xid, ses);
+		if (rc == -EAGAIN)
+			rc = -EHOSTDOWN;
+	}
+	if (rc == 0) {
+		spin_lock(&GlobalMid_Lock);
+		if (server->tcpStatus != CifsExiting)
+			server->tcpStatus = CifsGood;
+		else
+			rc = -EHOSTDOWN;
+		spin_unlock(&GlobalMid_Lock);
+
 	}
 
-	if (rc)
-		goto ss_err_exit;
+	return rc;
+}
 
-	pSesInfo->flags = 0;
-	pSesInfo->capabilities = server->capabilities;
+
+int cifs_setup_session(unsigned int xid, struct cifsSesInfo *ses,
+			struct nls_table *nls_info)
+{
+	int rc = 0;
+	struct TCP_Server_Info *server = ses->server;
+
+	ses->flags = 0;
+	ses->capabilities = server->capabilities;
 	if (linuxExtEnabled == 0)
-		pSesInfo->capabilities &= (~CAP_UNIX);
+		ses->capabilities &= (~CAP_UNIX);
 
-	cFYI(1, ("Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d",
-		 server->secMode, server->capabilities, server->timeAdj));
+	cFYI(1, "Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d",
+		 server->secMode, server->capabilities, server->timeAdj);
 
-	rc = CIFS_SessSetup(xid, pSesInfo, first_time, nls_info);
+	rc = CIFS_SessSetup(xid, ses, nls_info);
 	if (rc) {
-		cERROR(1, ("Send error in SessSetup = %d", rc));
+		cERROR(1, "Send error in SessSetup = %d", rc);
 	} else {
-		cFYI(1, ("CIFS Session Established successfully"));
+		cFYI(1, "CIFS Session Established successfully");
 		spin_lock(&GlobalMid_Lock);
-		pSesInfo->status = CifsGood;
-		pSesInfo->need_reconnect = false;
+		ses->status = CifsGood;
+		ses->need_reconnect = false;
 		spin_unlock(&GlobalMid_Lock);
 	}
 
-ss_err_exit:
 	return rc;
 }
 

fs/cifs/dir.c

diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index e9f7ecc..391816b 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -73,7 +73,7 @@
 		namelen += (1 + temp->d_name.len);
 		temp = temp->d_parent;
 		if (temp == NULL) {
-			cERROR(1, ("corrupt dentry"));
+			cERROR(1, "corrupt dentry");
 			return NULL;
 		}
 	}
@@ -90,19 +90,18 @@
 			full_path[namelen] = dirsep;
 			strncpy(full_path + namelen + 1, temp->d_name.name,
 				temp->d_name.len);
-			cFYI(0, ("name: %s", full_path + namelen));
+			cFYI(0, "name: %s", full_path + namelen);
 		}
 		temp = temp->d_parent;
 		if (temp == NULL) {
-			cERROR(1, ("corrupt dentry"));
+			cERROR(1, "corrupt dentry");
 			kfree(full_path);
 			return NULL;
 		}
 	}
 	if (namelen != pplen + dfsplen) {
-		cERROR(1,
-		       ("did not end path lookup where expected namelen is %d",
-			namelen));
+		cERROR(1, "did not end path lookup where expected namelen is %d",
+			namelen);
 		/* presumably this is only possible if racing with a rename
 		of one of the parent directories  (we can not lock the dentries
 		above us to prevent this, but retrying should be harmless) */
@@ -130,6 +129,12 @@
 	return full_path;
 }
 
+/*
+ * When called with struct file pointer set to NULL, there is no way we could
+ * update file->private_data, but getting it stuck on openFileList provides a
+ * way to access it from cifs_fill_filedata and thereby set file->private_data
+ * from cifs_open.
+ */
 struct cifsFileInfo *
 cifs_new_fileinfo(struct inode *newinode, __u16 fileHandle,
 		  struct file *file, struct vfsmount *mnt, unsigned int oflags)
@@ -173,7 +178,7 @@
 		if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) {
 			pCifsInode->clientCanCacheAll = true;
 			pCifsInode->clientCanCacheRead = true;
-			cFYI(1, ("Exclusive Oplock inode %p", newinode));
+			cFYI(1, "Exclusive Oplock inode %p", newinode);
 		} else if ((oplock & 0xF) == OPLOCK_READ)
 				pCifsInode->clientCanCacheRead = true;
 	}
@@ -183,16 +188,17 @@
 }
 
 int cifs_posix_open(char *full_path, struct inode **pinode,
-		    struct vfsmount *mnt, int mode, int oflags,
-		    __u32 *poplock, __u16 *pnetfid, int xid)
+			struct vfsmount *mnt, struct super_block *sb,
+			int mode, int oflags,
+			__u32 *poplock, __u16 *pnetfid, int xid)
 {
 	int rc;
 	FILE_UNIX_BASIC_INFO *presp_data;
 	__u32 posix_flags = 0;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(mnt->mnt_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifs_fattr fattr;
 
-	cFYI(1, ("posix open %s", full_path));
+	cFYI(1, "posix open %s", full_path);
 
 	presp_data = kzalloc(sizeof(FILE_UNIX_BASIC_INFO), GFP_KERNEL);
 	if (presp_data == NULL)
@@ -242,7 +248,8 @@
 
 	/* get new inode and set it up */
 	if (*pinode == NULL) {
-		*pinode = cifs_iget(mnt->mnt_sb, &fattr);
+		cifs_fill_uniqueid(sb, &fattr);
+		*pinode = cifs_iget(sb, &fattr);
 		if (!*pinode) {
 			rc = -ENOMEM;
 			goto posix_open_ret;
@@ -251,7 +258,18 @@
 		cifs_fattr_to_inode(*pinode, &fattr);
 	}
 
-	cifs_new_fileinfo(*pinode, *pnetfid, NULL, mnt, oflags);
+	/*
+	 * cifs_fill_filedata() takes care of setting cifsFileInfo pointer to
+	 * file->private_data.
+	 */
+	if (mnt) {
+		struct cifsFileInfo *pfile_info;
+
+		pfile_info = cifs_new_fileinfo(*pinode, *pnetfid, NULL, mnt,
+					       oflags);
+		if (pfile_info == NULL)
+			rc = -ENOMEM;
+	}
 
 posix_open_ret:
 	kfree(presp_data);
@@ -315,13 +333,14 @@
 	if (nd && (nd->flags & LOOKUP_OPEN))
 		oflags = nd->intent.open.flags;
 	else
-		oflags = FMODE_READ;
+		oflags = FMODE_READ | SMB_O_CREAT;
 
 	if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) &&
 	    (CIFS_UNIX_POSIX_PATH_OPS_CAP &
 			le64_to_cpu(tcon->fsUnixInfo.Capability))) {
-		rc = cifs_posix_open(full_path, &newinode, nd->path.mnt,
-				     mode, oflags, &oplock, &fileHandle, xid);
+		rc = cifs_posix_open(full_path, &newinode,
+			nd ? nd->path.mnt : NULL,
+			inode->i_sb, mode, oflags, &oplock, &fileHandle, xid);
 		/* EIO could indicate that (posix open) operation is not
 		   supported, despite what server claimed in capability
 		   negotation.  EREMOTE indicates DFS junction, which is not
@@ -358,7 +377,7 @@
 		else if ((oflags & O_CREAT) == O_CREAT)
 			disposition = FILE_OPEN_IF;
 		else
-			cFYI(1, ("Create flag not set in create function"));
+			cFYI(1, "Create flag not set in create function");
 	}
 
 	/* BB add processing to set equivalent of mode - e.g. via CreateX with
@@ -394,7 +413,7 @@
 			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
 	}
 	if (rc) {
-		cFYI(1, ("cifs_create returned 0x%x", rc));
+		cFYI(1, "cifs_create returned 0x%x", rc);
 		goto cifs_create_out;
 	}
 
@@ -457,15 +476,22 @@
 	if (rc == 0)
 		setup_cifs_dentry(tcon, direntry, newinode);
 	else
-		cFYI(1, ("Create worked, get_inode_info failed rc = %d", rc));
+		cFYI(1, "Create worked, get_inode_info failed rc = %d", rc);
 
 	/* nfsd case - nfs srv does not set nd */
 	if ((nd == NULL) || (!(nd->flags & LOOKUP_OPEN))) {
 		/* mknod case - do not leave file open */
 		CIFSSMBClose(xid, tcon, fileHandle);
 	} else if (!(posix_create) && (newinode)) {
-			cifs_new_fileinfo(newinode, fileHandle, NULL,
-						nd->path.mnt, oflags);
+		struct cifsFileInfo *pfile_info;
+		/*
+		 * cifs_fill_filedata() takes care of setting cifsFileInfo
+		 * pointer to file->private_data.
+		 */
+		pfile_info = cifs_new_fileinfo(newinode, fileHandle, NULL,
+					       nd->path.mnt, oflags);
+		if (pfile_info == NULL)
+			rc = -ENOMEM;
 	}
 cifs_create_out:
 	kfree(buf);
@@ -531,7 +557,7 @@
 			u16 fileHandle;
 			FILE_ALL_INFO *buf;
 
-			cFYI(1, ("sfu compat create special file"));
+			cFYI(1, "sfu compat create special file");
 
 			buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
 			if (buf == NULL) {
@@ -616,8 +642,8 @@
 
 	xid = GetXid();
 
-	cFYI(1, ("parent inode = 0x%p name is: %s and dentry = 0x%p",
-	      parent_dir_inode, direntry->d_name.name, direntry));
+	cFYI(1, "parent inode = 0x%p name is: %s and dentry = 0x%p",
+	      parent_dir_inode, direntry->d_name.name, direntry);
 
 	/* check whether path exists */
 
@@ -632,7 +658,7 @@
 		int i;
 		for (i = 0; i < direntry->d_name.len; i++)
 			if (direntry->d_name.name[i] == '\\') {
-				cFYI(1, ("Invalid file name"));
+				cFYI(1, "Invalid file name");
 				FreeXid(xid);
 				return ERR_PTR(-EINVAL);
 			}
@@ -657,11 +683,11 @@
 	}
 
 	if (direntry->d_inode != NULL) {
-		cFYI(1, ("non-NULL inode in lookup"));
+		cFYI(1, "non-NULL inode in lookup");
 	} else {
-		cFYI(1, ("NULL inode in lookup"));
+		cFYI(1, "NULL inode in lookup");
 	}
-	cFYI(1, ("Full path: %s inode = 0x%p", full_path, direntry->d_inode));
+	cFYI(1, "Full path: %s inode = 0x%p", full_path, direntry->d_inode);
 
 	/* Posix open is only called (at lookup time) for file create now.
 	 * For opens (rather than creates), because we do not know if it
@@ -678,6 +704,7 @@
 		     (nd->flags & LOOKUP_OPEN) && !pTcon->broken_posix_open &&
 		     (nd->intent.open.flags & O_CREAT)) {
 			rc = cifs_posix_open(full_path, &newInode, nd->path.mnt,
+					parent_dir_inode->i_sb,
 					nd->intent.open.create_mode,
 					nd->intent.open.flags, &oplock,
 					&fileHandle, xid);
@@ -723,7 +750,7 @@
 	/*	if it was once a directory (but how can we tell?) we could do
 		shrink_dcache_parent(direntry); */
 	} else if (rc != -EACCES) {
-		cERROR(1, ("Unexpected lookup error %d", rc));
+		cERROR(1, "Unexpected lookup error %d", rc);
 		/* We special case check for Access Denied - since that
 		is a common return code */
 	}
@@ -742,8 +769,8 @@
 		if (cifs_revalidate_dentry(direntry))
 			return 0;
 	} else {
-		cFYI(1, ("neg dentry 0x%p name = %s",
-			 direntry, direntry->d_name.name));
+		cFYI(1, "neg dentry 0x%p name = %s",
+			 direntry, direntry->d_name.name);
 		if (time_after(jiffies, direntry->d_time + HZ) ||
 			!lookupCacheEnabled) {
 			d_drop(direntry);
@@ -758,7 +785,7 @@
 {
 	int rc = 0;
 
-	cFYI(1, ("In cifs d_delete, name = %s", direntry->d_name.name));
+	cFYI(1, "In cifs d_delete, name = %s", direntry->d_name.name);
 
 	return rc;
 }     */

fs/cifs/dns_resolve.c

diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c
index 6f8a0e3..4db2c5e 100644
--- a/fs/cifs/dns_resolve.c
+++ b/fs/cifs/dns_resolve.c
@@ -106,14 +106,14 @@
 	/* search for server name delimiter */
 	len = strlen(unc);
 	if (len < 3) {
-		cFYI(1, ("%s: unc is too short: %s", __func__, unc));
+		cFYI(1, "%s: unc is too short: %s", __func__, unc);
 		return -EINVAL;
 	}
 	len -= 2;
 	name = memchr(unc+2, '\\', len);
 	if (!name) {
-		cFYI(1, ("%s: probably server name is whole unc: %s",
-					__func__, unc));
+		cFYI(1, "%s: probably server name is whole unc: %s",
+					__func__, unc);
 	} else {
 		len = (name - unc) - 2/* leading // */;
 	}
@@ -127,8 +127,8 @@
 	name[len] = 0;
 
 	if (is_ip(name)) {
-		cFYI(1, ("%s: it is IP, skipping dns upcall: %s",
-					__func__, name));
+		cFYI(1, "%s: it is IP, skipping dns upcall: %s",
+					__func__, name);
 		data = name;
 		goto skip_upcall;
 	}
@@ -138,7 +138,7 @@
 		len = rkey->type_data.x[0];
 		data = rkey->payload.data;
 	} else {
-		cERROR(1, ("%s: unable to resolve: %s", __func__, name));
+		cERROR(1, "%s: unable to resolve: %s", __func__, name);
 		goto out;
 	}
 
@@ -148,10 +148,10 @@
 		if (*ip_addr) {
 			memcpy(*ip_addr, data, len + 1);
 			if (!IS_ERR(rkey))
-				cFYI(1, ("%s: resolved: %s to %s", __func__,
+				cFYI(1, "%s: resolved: %s to %s", __func__,
 							name,
 							*ip_addr
-					));
+					);
 			rc = 0;
 		} else {
 			rc = -ENOMEM;

fs/cifs/export.c

diff --git a/fs/cifs/export.c b/fs/cifs/export.c
index 6177f7c..993f820 100644
--- a/fs/cifs/export.c
+++ b/fs/cifs/export.c
@@ -49,7 +49,7 @@
 static struct dentry *cifs_get_parent(struct dentry *dentry)
 {
 	/* BB need to add code here eventually to enable export via NFSD */
-	cFYI(1, ("get parent for %p", dentry));
+	cFYI(1, "get parent for %p", dentry);
 	return ERR_PTR(-EACCES);
 }
 

fs/cifs/file.c

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 9b11a8f..a83541e 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3,7 +3,7 @@
  *
  *   vfs operations that deal with files
  *
- *   Copyright (C) International Business Machines  Corp., 2002,2007
+ *   Copyright (C) International Business Machines  Corp., 2002,2010
  *   Author(s): Steve French (sfrench@us.ibm.com)
  *              Jeremy Allison (jra@samba.org)
  *
@@ -108,8 +108,7 @@
 /* all arguments to this function must be checked for validity in caller */
 static inline int
 cifs_posix_open_inode_helper(struct inode *inode, struct file *file,
-			     struct cifsInodeInfo *pCifsInode,
-			     struct cifsFileInfo *pCifsFile, __u32 oplock,
+			     struct cifsInodeInfo *pCifsInode, __u32 oplock,
 			     u16 netfid)
 {
 
@@ -136,15 +135,15 @@
 	if (timespec_equal(&file->f_path.dentry->d_inode->i_mtime, &temp) &&
 			   (file->f_path.dentry->d_inode->i_size ==
 			    (loff_t)le64_to_cpu(buf->EndOfFile))) {
-		cFYI(1, ("inode unchanged on server"));
+		cFYI(1, "inode unchanged on server");
 	} else {
 		if (file->f_path.dentry->d_inode->i_mapping) {
 			rc = filemap_write_and_wait(file->f_path.dentry->d_inode->i_mapping);
 			if (rc != 0)
 				CIFS_I(file->f_path.dentry->d_inode)->write_behind_rc = rc;
 		}
-		cFYI(1, ("invalidating remote inode since open detected it "
-			 "changed"));
+		cFYI(1, "invalidating remote inode since open detected it "
+			 "changed");
 		invalidate_remote_inode(file->f_path.dentry->d_inode);
 	} */
 
@@ -152,8 +151,8 @@
 	if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) {
 		pCifsInode->clientCanCacheAll = true;
 		pCifsInode->clientCanCacheRead = true;
-		cFYI(1, ("Exclusive Oplock granted on inode %p",
-			 file->f_path.dentry->d_inode));
+		cFYI(1, "Exclusive Oplock granted on inode %p",
+			 file->f_path.dentry->d_inode);
 	} else if ((oplock & 0xF) == OPLOCK_READ)
 		pCifsInode->clientCanCacheRead = true;
 
@@ -190,8 +189,8 @@
 	if (file->private_data != NULL) {
 		return pCifsFile;
 	} else if ((file->f_flags & O_CREAT) && (file->f_flags & O_EXCL))
-			cERROR(1, ("could not find file instance for "
-				   "new file %p", file));
+			cERROR(1, "could not find file instance for "
+				   "new file %p", file);
 	return NULL;
 }
 
@@ -217,7 +216,7 @@
 	if (timespec_equal(&file->f_path.dentry->d_inode->i_mtime, &temp) &&
 			   (file->f_path.dentry->d_inode->i_size ==
 			    (loff_t)le64_to_cpu(buf->EndOfFile))) {
-		cFYI(1, ("inode unchanged on server"));
+		cFYI(1, "inode unchanged on server");
 	} else {
 		if (file->f_path.dentry->d_inode->i_mapping) {
 			/* BB no need to lock inode until after invalidate
@@ -226,8 +225,8 @@
 			if (rc != 0)
 				CIFS_I(file->f_path.dentry->d_inode)->write_behind_rc = rc;
 		}
-		cFYI(1, ("invalidating remote inode since open detected it "
-			 "changed"));
+		cFYI(1, "invalidating remote inode since open detected it "
+			 "changed");
 		invalidate_remote_inode(file->f_path.dentry->d_inode);
 	}
 
@@ -242,8 +241,8 @@
 	if ((*oplock & 0xF) == OPLOCK_EXCLUSIVE) {
 		pCifsInode->clientCanCacheAll = true;
 		pCifsInode->clientCanCacheRead = true;
-		cFYI(1, ("Exclusive Oplock granted on inode %p",
-			 file->f_path.dentry->d_inode));
+		cFYI(1, "Exclusive Oplock granted on inode %p",
+			 file->f_path.dentry->d_inode);
 	} else if ((*oplock & 0xF) == OPLOCK_READ)
 		pCifsInode->clientCanCacheRead = true;
 
@@ -285,8 +284,8 @@
 		return rc;
 	}
 
-	cFYI(1, ("inode = 0x%p file flags are 0x%x for %s",
-		 inode, file->f_flags, full_path));
+	cFYI(1, "inode = 0x%p file flags are 0x%x for %s",
+		 inode, file->f_flags, full_path);
 
 	if (oplockEnabled)
 		oplock = REQ_OPLOCK;
@@ -298,27 +297,29 @@
 	    (CIFS_UNIX_POSIX_PATH_OPS_CAP &
 			le64_to_cpu(tcon->fsUnixInfo.Capability))) {
 		int oflags = (int) cifs_posix_convert_flags(file->f_flags);
+		oflags |= SMB_O_CREAT;
 		/* can not refresh inode info since size could be stale */
 		rc = cifs_posix_open(full_path, &inode, file->f_path.mnt,
-				     cifs_sb->mnt_file_mode /* ignored */,
-				     oflags, &oplock, &netfid, xid);
+				inode->i_sb,
+				cifs_sb->mnt_file_mode /* ignored */,
+				oflags, &oplock, &netfid, xid);
 		if (rc == 0) {
-			cFYI(1, ("posix open succeeded"));
+			cFYI(1, "posix open succeeded");
 			/* no need for special case handling of setting mode
 			   on read only files needed here */
 
 			pCifsFile = cifs_fill_filedata(file);
 			cifs_posix_open_inode_helper(inode, file, pCifsInode,
-						     pCifsFile, oplock, netfid);
+						     oplock, netfid);
 			goto out;
 		} else if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
 			if (tcon->ses->serverNOS)
-				cERROR(1, ("server %s of type %s returned"
+				cERROR(1, "server %s of type %s returned"
 					   " unexpected error on SMB posix open"
 					   ", disabling posix open support."
 					   " Check if server update available.",
 					   tcon->ses->serverName,
-					   tcon->ses->serverNOS));
+					   tcon->ses->serverNOS);
 			tcon->broken_posix_open = true;
 		} else if ((rc != -EIO) && (rc != -EREMOTE) &&
 			 (rc != -EOPNOTSUPP)) /* path not found or net err */
@@ -386,7 +387,7 @@
 				& CIFS_MOUNT_MAP_SPECIAL_CHR);
 	}
 	if (rc) {
-		cFYI(1, ("cifs_open returned 0x%x", rc));
+		cFYI(1, "cifs_open returned 0x%x", rc);
 		goto out;
 	}
 
@@ -469,7 +470,7 @@
 	}
 
 	if (file->f_path.dentry == NULL) {
-		cERROR(1, ("no valid name if dentry freed"));
+		cERROR(1, "no valid name if dentry freed");
 		dump_stack();
 		rc = -EBADF;
 		goto reopen_error_exit;
@@ -477,7 +478,7 @@
 
 	inode = file->f_path.dentry->d_inode;
 	if (inode == NULL) {
-		cERROR(1, ("inode not valid"));
+		cERROR(1, "inode not valid");
 		dump_stack();
 		rc = -EBADF;
 		goto reopen_error_exit;
@@ -499,8 +500,8 @@
 		return rc;
 	}
 
-	cFYI(1, ("inode = 0x%p file flags 0x%x for %s",
-		 inode, file->f_flags, full_path));
+	cFYI(1, "inode = 0x%p file flags 0x%x for %s",
+		 inode, file->f_flags, full_path);
 
 	if (oplockEnabled)
 		oplock = REQ_OPLOCK;
@@ -513,10 +514,11 @@
 		int oflags = (int) cifs_posix_convert_flags(file->f_flags);
 		/* can not refresh inode info since size could be stale */
 		rc = cifs_posix_open(full_path, NULL, file->f_path.mnt,
-				     cifs_sb->mnt_file_mode /* ignored */,
-				     oflags, &oplock, &netfid, xid);
+				inode->i_sb,
+				cifs_sb->mnt_file_mode /* ignored */,
+				oflags, &oplock, &netfid, xid);
 		if (rc == 0) {
-			cFYI(1, ("posix reopen succeeded"));
+			cFYI(1, "posix reopen succeeded");
 			goto reopen_success;
 		}
 		/* fallthrough to retry open the old way on errors, especially
@@ -537,8 +539,8 @@
 				CIFS_MOUNT_MAP_SPECIAL_CHR);
 	if (rc) {
 		mutex_unlock(&pCifsFile->fh_mutex);
-		cFYI(1, ("cifs_open returned 0x%x", rc));
-		cFYI(1, ("oplock: %d", oplock));
+		cFYI(1, "cifs_open returned 0x%x", rc);
+		cFYI(1, "oplock: %d", oplock);
 	} else {
 reopen_success:
 		pCifsFile->netfid = netfid;
@@ -570,8 +572,8 @@
 			if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) {
 				pCifsInode->clientCanCacheAll = true;
 				pCifsInode->clientCanCacheRead = true;
-				cFYI(1, ("Exclusive Oplock granted on inode %p",
-					 file->f_path.dentry->d_inode));
+				cFYI(1, "Exclusive Oplock granted on inode %p",
+					 file->f_path.dentry->d_inode);
 			} else if ((oplock & 0xF) == OPLOCK_READ) {
 				pCifsInode->clientCanCacheRead = true;
 				pCifsInode->clientCanCacheAll = false;
@@ -619,8 +621,7 @@
 					the struct would be in each open file,
 					but this should give enough time to
 					clear the socket */
-					cFYI(DBG2,
-						("close delay, write pending"));
+					cFYI(DBG2, "close delay, write pending");
 					msleep(timeout);
 					timeout *= 4;
 				}
@@ -653,7 +654,7 @@
 
 	read_lock(&GlobalSMBSeslock);
 	if (list_empty(&(CIFS_I(inode)->openFileList))) {
-		cFYI(1, ("closing last open instance for inode %p", inode));
+		cFYI(1, "closing last open instance for inode %p", inode);
 		/* if the file is not open we do not know if we can cache info
 		   on this inode, much less write behind and read ahead */
 		CIFS_I(inode)->clientCanCacheRead = false;
@@ -674,7 +675,7 @@
 	    (struct cifsFileInfo *)file->private_data;
 	char *ptmp;
 
-	cFYI(1, ("Closedir inode = 0x%p", inode));
+	cFYI(1, "Closedir inode = 0x%p", inode);
 
 	xid = GetXid();
 
@@ -685,22 +686,22 @@
 
 		pTcon = cifs_sb->tcon;
 
-		cFYI(1, ("Freeing private data in close dir"));
+		cFYI(1, "Freeing private data in close dir");
 		write_lock(&GlobalSMBSeslock);
 		if (!pCFileStruct->srch_inf.endOfSearch &&
 		    !pCFileStruct->invalidHandle) {
 			pCFileStruct->invalidHandle = true;
 			write_unlock(&GlobalSMBSeslock);
 			rc = CIFSFindClose(xid, pTcon, pCFileStruct->netfid);
-			cFYI(1, ("Closing uncompleted readdir with rc %d",
-				 rc));
+			cFYI(1, "Closing uncompleted readdir with rc %d",
+				 rc);
 			/* not much we can do if it fails anyway, ignore rc */
 			rc = 0;
 		} else
 			write_unlock(&GlobalSMBSeslock);
 		ptmp = pCFileStruct->srch_inf.ntwrk_buf_start;
 		if (ptmp) {
-			cFYI(1, ("closedir free smb buf in srch struct"));
+			cFYI(1, "closedir free smb buf in srch struct");
 			pCFileStruct->srch_inf.ntwrk_buf_start = NULL;
 			if (pCFileStruct->srch_inf.smallBuf)
 				cifs_small_buf_release(ptmp);
@@ -748,49 +749,49 @@
 	rc = -EACCES;
 	xid = GetXid();
 
-	cFYI(1, ("Lock parm: 0x%x flockflags: "
+	cFYI(1, "Lock parm: 0x%x flockflags: "
 		 "0x%x flocktype: 0x%x start: %lld end: %lld",
 		cmd, pfLock->fl_flags, pfLock->fl_type, pfLock->fl_start,
-		pfLock->fl_end));
+		pfLock->fl_end);
 
 	if (pfLock->fl_flags & FL_POSIX)
-		cFYI(1, ("Posix"));
+		cFYI(1, "Posix");
 	if (pfLock->fl_flags & FL_FLOCK)
-		cFYI(1, ("Flock"));
+		cFYI(1, "Flock");
 	if (pfLock->fl_flags & FL_SLEEP) {
-		cFYI(1, ("Blocking lock"));
+		cFYI(1, "Blocking lock");
 		wait_flag = true;
 	}
 	if (pfLock->fl_flags & FL_ACCESS)
-		cFYI(1, ("Process suspended by mandatory locking - "
-			 "not implemented yet"));
+		cFYI(1, "Process suspended by mandatory locking - "
+			 "not implemented yet");
 	if (pfLock->fl_flags & FL_LEASE)
-		cFYI(1, ("Lease on file - not implemented yet"));
+		cFYI(1, "Lease on file - not implemented yet");
 	if (pfLock->fl_flags &
 	    (~(FL_POSIX | FL_FLOCK | FL_SLEEP | FL_ACCESS | FL_LEASE)))
-		cFYI(1, ("Unknown lock flags 0x%x", pfLock->fl_flags));
+		cFYI(1, "Unknown lock flags 0x%x", pfLock->fl_flags);
 
 	if (pfLock->fl_type == F_WRLCK) {
-		cFYI(1, ("F_WRLCK "));
+		cFYI(1, "F_WRLCK ");
 		numLock = 1;
 	} else if (pfLock->fl_type == F_UNLCK) {
-		cFYI(1, ("F_UNLCK"));
+		cFYI(1, "F_UNLCK");
 		numUnlock = 1;
 		/* Check if unlock includes more than
 		one lock range */
 	} else if (pfLock->fl_type == F_RDLCK) {
-		cFYI(1, ("F_RDLCK"));
+		cFYI(1, "F_RDLCK");
 		lockType |= LOCKING_ANDX_SHARED_LOCK;
 		numLock = 1;
 	} else if (pfLock->fl_type == F_EXLCK) {
-		cFYI(1, ("F_EXLCK"));
+		cFYI(1, "F_EXLCK");
 		numLock = 1;
 	} else if (pfLock->fl_type == F_SHLCK) {
-		cFYI(1, ("F_SHLCK"));
+		cFYI(1, "F_SHLCK");
 		lockType |= LOCKING_ANDX_SHARED_LOCK;
 		numLock = 1;
 	} else
-		cFYI(1, ("Unknown type of lock"));
+		cFYI(1, "Unknown type of lock");
 
 	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
 	tcon = cifs_sb->tcon;
@@ -833,8 +834,8 @@
 					 0 /* wait flag */ );
 			pfLock->fl_type = F_UNLCK;
 			if (rc != 0)
-				cERROR(1, ("Error unlocking previously locked "
-					   "range %d during test of lock", rc));
+				cERROR(1, "Error unlocking previously locked "
+					   "range %d during test of lock", rc);
 			rc = 0;
 
 		} else {
@@ -856,9 +857,9 @@
 						0 /* wait flag */);
 					pfLock->fl_type = F_RDLCK;
 					if (rc != 0)
-						cERROR(1, ("Error unlocking "
+						cERROR(1, "Error unlocking "
 						"previously locked range %d "
-						"during test of lock", rc));
+						"during test of lock", rc);
 					rc = 0;
 				} else {
 					pfLock->fl_type = F_WRLCK;
@@ -923,9 +924,10 @@
 							1, 0, li->type, false);
 					if (stored_rc)
 						rc = stored_rc;
-
-					list_del(&li->llist);
-					kfree(li);
+					else {
+						list_del(&li->llist);
+						kfree(li);
+					}
 				}
 			}
 			mutex_unlock(&fid->lock_mutex);
@@ -988,9 +990,8 @@
 
 	pTcon = cifs_sb->tcon;
 
-	/* cFYI(1,
-	   (" write %d bytes to offset %lld of %s", write_size,
-	   *poffset, file->f_path.dentry->d_name.name)); */
+	/* cFYI(1, " write %d bytes to offset %lld of %s", write_size,
+	   *poffset, file->f_path.dentry->d_name.name); */
 
 	if (file->private_data == NULL)
 		return -EBADF;
@@ -1091,8 +1092,8 @@
 
 	pTcon = cifs_sb->tcon;
 
-	cFYI(1, ("write %zd bytes to offset %lld of %s", write_size,
-	   *poffset, file->f_path.dentry->d_name.name));
+	cFYI(1, "write %zd bytes to offset %lld of %s", write_size,
+	   *poffset, file->f_path.dentry->d_name.name);
 
 	if (file->private_data == NULL)
 		return -EBADF;
@@ -1233,7 +1234,7 @@
 	it being zero) during stress testcases so we need to check for it */
 
 	if (cifs_inode == NULL) {
-		cERROR(1, ("Null inode passed to cifs_writeable_file"));
+		cERROR(1, "Null inode passed to cifs_writeable_file");
 		dump_stack();
 		return NULL;
 	}
@@ -1277,7 +1278,7 @@
 			again. Note that it would be bad
 			to hold up writepages here (rather than
 			in caller) with continuous retries */
-			cFYI(1, ("wp failed on reopen file"));
+			cFYI(1, "wp failed on reopen file");
 			read_lock(&GlobalSMBSeslock);
 			/* can not use this handle, no write
 			   pending on this one after all */
@@ -1353,7 +1354,7 @@
 		else if (bytes_written < 0)
 			rc = bytes_written;
 	} else {
-		cFYI(1, ("No writeable filehandles for inode"));
+		cFYI(1, "No writeable filehandles for inode");
 		rc = -EIO;
 	}
 
@@ -1525,7 +1526,7 @@
 			 */
 			open_file = find_writable_file(CIFS_I(mapping->host));
 			if (!open_file) {
-				cERROR(1, ("No writable handles for inode"));
+				cERROR(1, "No writable handles for inode");
 				rc = -EBADF;
 			} else {
 				long_op = cifs_write_timeout(cifsi, offset);
@@ -1538,8 +1539,8 @@
 				cifs_update_eof(cifsi, offset, bytes_written);
 
 				if (rc || bytes_written < bytes_to_write) {
-					cERROR(1, ("Write2 ret %d, wrote %d",
-						  rc, bytes_written));
+					cERROR(1, "Write2 ret %d, wrote %d",
+						  rc, bytes_written);
 					/* BB what if continued retry is
 					   requested via mount flags? */
 					if (rc == -ENOSPC)
@@ -1600,7 +1601,7 @@
 /* BB add check for wbc flags */
 	page_cache_get(page);
 	if (!PageUptodate(page))
-		cFYI(1, ("ppw - page not up to date"));
+		cFYI(1, "ppw - page not up to date");
 
 	/*
 	 * Set the "writeback" flag, and clear "dirty" in the radix tree.
@@ -1629,8 +1630,8 @@
 	int rc;
 	struct inode *inode = mapping->host;
 
-	cFYI(1, ("write_end for page %p from pos %lld with %d bytes",
-		 page, pos, copied));
+	cFYI(1, "write_end for page %p from pos %lld with %d bytes",
+		 page, pos, copied);
 
 	if (PageChecked(page)) {
 		if (copied == len)
@@ -1686,8 +1687,8 @@
 
 	xid = GetXid();
 
-	cFYI(1, ("Sync file - name: %s datasync: 0x%x",
-		dentry->d_name.name, datasync));
+	cFYI(1, "Sync file - name: %s datasync: 0x%x",
+		dentry->d_name.name, datasync);
 
 	rc = filemap_write_and_wait(inode->i_mapping);
 	if (rc == 0) {
@@ -1711,7 +1712,7 @@
 	unsigned int rpages = 0;
 	int rc = 0;
 
-	cFYI(1, ("sync page %p",page));
+	cFYI(1, "sync page %p", page);
 	mapping = page->mapping;
 	if (!mapping)
 		return 0;
@@ -1722,7 +1723,7 @@
 /*	fill in rpages then
 	result = cifs_pagein_inode(inode, index, rpages); */ /* BB finish */
 
-/*	cFYI(1, ("rpages is %d for sync page of Index %ld", rpages, index));
+/*	cFYI(1, "rpages is %d for sync page of Index %ld", rpages, index);
 
 #if 0
 	if (rc < 0)
@@ -1756,7 +1757,7 @@
 		CIFS_I(inode)->write_behind_rc = 0;
 	}
 
-	cFYI(1, ("Flush inode %p file %p rc %d", inode, file, rc));
+	cFYI(1, "Flush inode %p file %p rc %d", inode, file, rc);
 
 	return rc;
 }
@@ -1788,7 +1789,7 @@
 	open_file = (struct cifsFileInfo *)file->private_data;
 
 	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
-		cFYI(1, ("attempting read on write only file instance"));
+		cFYI(1, "attempting read on write only file instance");
 
 	for (total_read = 0, current_offset = read_data;
 	     read_size > total_read;
@@ -1869,7 +1870,7 @@
 	open_file = (struct cifsFileInfo *)file->private_data;
 
 	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
-		cFYI(1, ("attempting read on write only file instance"));
+		cFYI(1, "attempting read on write only file instance");
 
 	for (total_read = 0, current_offset = read_data;
 	     read_size > total_read;
@@ -1920,7 +1921,7 @@
 	xid = GetXid();
 	rc = cifs_revalidate_file(file);
 	if (rc) {
-		cFYI(1, ("Validation prior to mmap failed, error=%d", rc));
+		cFYI(1, "Validation prior to mmap failed, error=%d", rc);
 		FreeXid(xid);
 		return rc;
 	}
@@ -1931,8 +1932,7 @@
 
 
 static void cifs_copy_cache_pages(struct address_space *mapping,
-	struct list_head *pages, int bytes_read, char *data,
-	struct pagevec *plru_pvec)
+	struct list_head *pages, int bytes_read, char *data)
 {
 	struct page *page;
 	char *target;
@@ -1944,10 +1944,10 @@
 		page = list_entry(pages->prev, struct page, lru);
 		list_del(&page->lru);
 
-		if (add_to_page_cache(page, mapping, page->index,
+		if (add_to_page_cache_lru(page, mapping, page->index,
 				      GFP_KERNEL)) {
 			page_cache_release(page);
-			cFYI(1, ("Add page cache failed"));
+			cFYI(1, "Add page cache failed");
 			data += PAGE_CACHE_SIZE;
 			bytes_read -= PAGE_CACHE_SIZE;
 			continue;
@@ -1970,8 +1970,6 @@
 		flush_dcache_page(page);
 		SetPageUptodate(page);
 		unlock_page(page);
-		if (!pagevec_add(plru_pvec, page))
-			__pagevec_lru_add_file(plru_pvec);
 		data += PAGE_CACHE_SIZE;
 	}
 	return;
@@ -1990,7 +1988,6 @@
 	unsigned int read_size, i;
 	char *smb_read_data = NULL;
 	struct smb_com_read_rsp *pSMBr;
-	struct pagevec lru_pvec;
 	struct cifsFileInfo *open_file;
 	int buf_type = CIFS_NO_BUFFER;
 
@@ -2004,8 +2001,7 @@
 	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
 	pTcon = cifs_sb->tcon;
 
-	pagevec_init(&lru_pvec, 0);
-	cFYI(DBG2, ("rpages: num pages %d", num_pages));
+	cFYI(DBG2, "rpages: num pages %d", num_pages);
 	for (i = 0; i < num_pages; ) {
 		unsigned contig_pages;
 		struct page *tmp_page;
@@ -2038,8 +2034,8 @@
 		/* Read size needs to be in multiples of one page */
 		read_size = min_t(const unsigned int, read_size,
 				  cifs_sb->rsize & PAGE_CACHE_MASK);
-		cFYI(DBG2, ("rpages: read size 0x%x  contiguous pages %d",
-				read_size, contig_pages));
+		cFYI(DBG2, "rpages: read size 0x%x  contiguous pages %d",
+				read_size, contig_pages);
 		rc = -EAGAIN;
 		while (rc == -EAGAIN) {
 			if ((open_file->invalidHandle) &&
@@ -2066,14 +2062,14 @@
 			}
 		}
 		if ((rc < 0) || (smb_read_data == NULL)) {
-			cFYI(1, ("Read error in readpages: %d", rc));
+			cFYI(1, "Read error in readpages: %d", rc);
 			break;
 		} else if (bytes_read > 0) {
 			task_io_account_read(bytes_read);
 			pSMBr = (struct smb_com_read_rsp *)smb_read_data;
 			cifs_copy_cache_pages(mapping, page_list, bytes_read,
 				smb_read_data + 4 /* RFC1001 hdr */ +
-				le16_to_cpu(pSMBr->DataOffset), &lru_pvec);
+				le16_to_cpu(pSMBr->DataOffset));
 
 			i +=  bytes_read >> PAGE_CACHE_SHIFT;
 			cifs_stats_bytes_read(pTcon, bytes_read);
@@ -2089,9 +2085,9 @@
 				/* break; */
 			}
 		} else {
-			cFYI(1, ("No bytes read (%d) at offset %lld . "
-				 "Cleaning remaining pages from readahead list",
-				 bytes_read, offset));
+			cFYI(1, "No bytes read (%d) at offset %lld . "
+				"Cleaning remaining pages from readahead list",
+				bytes_read, offset);
 			/* BB turn off caching and do new lookup on
 			   file size at server? */
 			break;
@@ -2106,8 +2102,6 @@
 		bytes_read = 0;
 	}
 
-	pagevec_lru_add_file(&lru_pvec);
-
 /* need to free smb_read_data buf before exit */
 	if (smb_read_data) {
 		if (buf_type == CIFS_SMALL_BUFFER)
@@ -2136,7 +2130,7 @@
 	if (rc < 0)
 		goto io_error;
 	else
-		cFYI(1, ("Bytes read %d", rc));
+		cFYI(1, "Bytes read %d", rc);
 
 	file->f_path.dentry->d_inode->i_atime =
 		current_fs_time(file->f_path.dentry->d_inode->i_sb);
@@ -2168,8 +2162,8 @@
 		return rc;
 	}
 
-	cFYI(1, ("readpage %p at offset %d 0x%x\n",
-		 page, (int)offset, (int)offset));
+	cFYI(1, "readpage %p at offset %d 0x%x\n",
+		 page, (int)offset, (int)offset);
 
 	rc = cifs_readpage_worker(file, page, &offset);
 
@@ -2239,7 +2233,7 @@
 	struct page *page;
 	int rc = 0;
 
-	cFYI(1, ("write_begin from %lld len %d", (long long)pos, len));
+	cFYI(1, "write_begin from %lld len %d", (long long)pos, len);
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page) {
@@ -2311,12 +2305,10 @@
 	int rc, waitrc = 0;
 
 	if (inode && S_ISREG(inode->i_mode)) {
-#ifdef CONFIG_CIFS_EXPERIMENTAL
-		if (cinode->clientCanCacheAll == 0)
+		if (cinode->clientCanCacheRead)
 			break_lease(inode, O_RDONLY);
-		else if (cinode->clientCanCacheRead == 0)
+		else
 			break_lease(inode, O_WRONLY);
-#endif
 		rc = filemap_fdatawrite(inode->i_mapping);
 		if (cinode->clientCanCacheRead == 0) {
 			waitrc = filemap_fdatawait(inode->i_mapping);
@@ -2326,7 +2318,7 @@
 			rc = waitrc;
 		if (rc)
 			cinode->write_behind_rc = rc;
-		cFYI(1, ("Oplock flush inode %p rc %d", inode, rc));
+		cFYI(1, "Oplock flush inode %p rc %d", inode, rc);
 	}
 
 	/*
@@ -2338,7 +2330,7 @@
 	if (!cfile->closePend && !cfile->oplock_break_cancelled) {
 		rc = CIFSSMBLock(0, cifs_sb->tcon, cfile->netfid, 0, 0, 0, 0,
 				 LOCKING_ANDX_OPLOCK_RELEASE, false);
-		cFYI(1, ("Oplock release rc = %d", rc));
+		cFYI(1, "Oplock release rc = %d", rc);
 	}
 }
 

fs/cifs/inode.c

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 35ec117..62b324f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1,7 +1,7 @@
 /*
  *   fs/cifs/inode.c
  *
- *   Copyright (C) International Business Machines  Corp., 2002,2008
+ *   Copyright (C) International Business Machines  Corp., 2002,2010
  *   Author(s): Steve French (sfrench@us.ibm.com)
  *
  *   This library is free software; you can redistribute it and/or modify
@@ -86,30 +86,30 @@
 {
 	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
 
-	cFYI(1, ("%s: revalidating inode %llu", __func__, cifs_i->uniqueid));
+	cFYI(1, "%s: revalidating inode %llu", __func__, cifs_i->uniqueid);
 
 	if (inode->i_state & I_NEW) {
-		cFYI(1, ("%s: inode %llu is new", __func__, cifs_i->uniqueid));
+		cFYI(1, "%s: inode %llu is new", __func__, cifs_i->uniqueid);
 		return;
 	}
 
 	/* don't bother with revalidation if we have an oplock */
 	if (cifs_i->clientCanCacheRead) {
-		cFYI(1, ("%s: inode %llu is oplocked", __func__,
-			 cifs_i->uniqueid));
+		cFYI(1, "%s: inode %llu is oplocked", __func__,
+			 cifs_i->uniqueid);
 		return;
 	}
 
 	 /* revalidate if mtime or size have changed */
 	if (timespec_equal(&inode->i_mtime, &fattr->cf_mtime) &&
 	    cifs_i->server_eof == fattr->cf_eof) {
-		cFYI(1, ("%s: inode %llu is unchanged", __func__,
-			 cifs_i->uniqueid));
+		cFYI(1, "%s: inode %llu is unchanged", __func__,
+			 cifs_i->uniqueid);
 		return;
 	}
 
-	cFYI(1, ("%s: invalidating inode %llu mapping", __func__,
-		 cifs_i->uniqueid));
+	cFYI(1, "%s: invalidating inode %llu mapping", __func__,
+		 cifs_i->uniqueid);
 	cifs_i->invalid_mapping = true;
 }
 
@@ -137,15 +137,14 @@
 		inode->i_mode = fattr->cf_mode;
 
 	cifs_i->cifsAttrs = fattr->cf_cifsattrs;
-	cifs_i->uniqueid = fattr->cf_uniqueid;
 
 	if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)
 		cifs_i->time = 0;
 	else
 		cifs_i->time = jiffies;
 
-	cFYI(1, ("inode 0x%p old_time=%ld new_time=%ld", inode,
-		 oldtime, cifs_i->time));
+	cFYI(1, "inode 0x%p old_time=%ld new_time=%ld", inode,
+		 oldtime, cifs_i->time);
 
 	cifs_i->delete_pending = fattr->cf_flags & CIFS_FATTR_DELETE_PENDING;
 
@@ -170,6 +169,17 @@
 	cifs_set_ops(inode, fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL);
 }
 
+void
+cifs_fill_uniqueid(struct super_block *sb, struct cifs_fattr *fattr)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
+		return;
+
+	fattr->cf_uniqueid = iunique(sb, ROOT_I);
+}
+
 /* Fill a cifs_fattr struct with info from FILE_UNIX_BASIC_INFO. */
 void
 cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info,
@@ -227,7 +237,7 @@
 		/* safest to call it a file if we do not know */
 		fattr->cf_mode |= S_IFREG;
 		fattr->cf_dtype = DT_REG;
-		cFYI(1, ("unknown type %d", le32_to_cpu(info->Type)));
+		cFYI(1, "unknown type %d", le32_to_cpu(info->Type));
 		break;
 	}
 
@@ -256,7 +266,7 @@
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 
-	cFYI(1, ("creating fake fattr for DFS referral"));
+	cFYI(1, "creating fake fattr for DFS referral");
 
 	memset(fattr, 0, sizeof(*fattr));
 	fattr->cf_mode = S_IFDIR | S_IXUGO | S_IRWXU;
@@ -305,7 +315,7 @@
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 
 	tcon = cifs_sb->tcon;
-	cFYI(1, ("Getting info on %s", full_path));
+	cFYI(1, "Getting info on %s", full_path);
 
 	/* could have done a find first instead but this returns more info */
 	rc = CIFSSMBUnixQPathInfo(xid, tcon, full_path, &find_data,
@@ -323,6 +333,7 @@
 
 	if (*pinode == NULL) {
 		/* get new inode */
+		cifs_fill_uniqueid(sb, &fattr);
 		*pinode = cifs_iget(sb, &fattr);
 		if (!*pinode)
 			rc = -ENOMEM;
@@ -373,7 +384,7 @@
 				 &bytes_read, &pbuf, &buf_type);
 		if ((rc == 0) && (bytes_read >= 8)) {
 			if (memcmp("IntxBLK", pbuf, 8) == 0) {
-				cFYI(1, ("Block device"));
+				cFYI(1, "Block device");
 				fattr->cf_mode |= S_IFBLK;
 				fattr->cf_dtype = DT_BLK;
 				if (bytes_read == 24) {
@@ -385,7 +396,7 @@
 					fattr->cf_rdev = MKDEV(mjr, mnr);
 				}
 			} else if (memcmp("IntxCHR", pbuf, 8) == 0) {
-				cFYI(1, ("Char device"));
+				cFYI(1, "Char device");
 				fattr->cf_mode |= S_IFCHR;
 				fattr->cf_dtype = DT_CHR;
 				if (bytes_read == 24) {
@@ -397,7 +408,7 @@
 					fattr->cf_rdev = MKDEV(mjr, mnr);
 				}
 			} else if (memcmp("IntxLNK", pbuf, 7) == 0) {
-				cFYI(1, ("Symlink"));
+				cFYI(1, "Symlink");
 				fattr->cf_mode |= S_IFLNK;
 				fattr->cf_dtype = DT_LNK;
 			} else {
@@ -439,10 +450,10 @@
 	else if (rc > 3) {
 		mode = le32_to_cpu(*((__le32 *)ea_value));
 		fattr->cf_mode &= ~SFBITS_MASK;
-		cFYI(1, ("special bits 0%o org mode 0%o", mode,
-			 fattr->cf_mode));
+		cFYI(1, "special bits 0%o org mode 0%o", mode,
+			 fattr->cf_mode);
 		fattr->cf_mode = (mode & SFBITS_MASK) | fattr->cf_mode;
-		cFYI(1, ("special mode bits 0%o", mode));
+		cFYI(1, "special mode bits 0%o", mode);
 	}
 
 	return 0;
@@ -548,11 +559,11 @@
 	struct cifs_fattr fattr;
 
 	pTcon = cifs_sb->tcon;
-	cFYI(1, ("Getting info on %s", full_path));
+	cFYI(1, "Getting info on %s", full_path);
 
 	if ((pfindData == NULL) && (*pinode != NULL)) {
 		if (CIFS_I(*pinode)->clientCanCacheRead) {
-			cFYI(1, ("No need to revalidate cached inode sizes"));
+			cFYI(1, "No need to revalidate cached inode sizes");
 			return rc;
 		}
 	}
@@ -618,7 +629,7 @@
 					cifs_sb->mnt_cifs_flags &
 						CIFS_MOUNT_MAP_SPECIAL_CHR);
 			if (rc1 || !fattr.cf_uniqueid) {
-				cFYI(1, ("GetSrvInodeNum rc %d", rc1));
+				cFYI(1, "GetSrvInodeNum rc %d", rc1);
 				fattr.cf_uniqueid = iunique(sb, ROOT_I);
 				cifs_autodisable_serverino(cifs_sb);
 			}
@@ -634,13 +645,13 @@
 	    cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
 		tmprc = cifs_sfu_type(&fattr, full_path, cifs_sb, xid);
 		if (tmprc)
-			cFYI(1, ("cifs_sfu_type failed: %d", tmprc));
+			cFYI(1, "cifs_sfu_type failed: %d", tmprc);
 	}
 
 #ifdef CONFIG_CIFS_EXPERIMENTAL
 	/* fill in 0777 bits from ACL */
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
-		cFYI(1, ("Getting mode bits from ACL"));
+		cFYI(1, "Getting mode bits from ACL");
 		cifs_acl_to_fattr(cifs_sb, &fattr, *pinode, full_path, pfid);
 	}
 #endif
@@ -715,6 +726,16 @@
 	if (CIFS_I(inode)->uniqueid != fattr->cf_uniqueid)
 		return 0;
 
+	/*
+	 * uh oh -- it's a directory. We can't use it since hardlinked dirs are
+	 * verboten. Disable serverino and return it as if it were found, the
+	 * caller can discard it, generate a uniqueid and retry the find
+	 */
+	if (S_ISDIR(inode->i_mode) && !list_empty(&inode->i_dentry)) {
+		fattr->cf_flags |= CIFS_FATTR_INO_COLLISION;
+		cifs_autodisable_serverino(CIFS_SB(inode->i_sb));
+	}
+
 	return 1;
 }
 
@@ -734,15 +755,22 @@
 	unsigned long hash;
 	struct inode *inode;
 
-	cFYI(1, ("looking for uniqueid=%llu", fattr->cf_uniqueid));
+retry_iget5_locked:
+	cFYI(1, "looking for uniqueid=%llu", fattr->cf_uniqueid);
 
 	/* hash down to 32-bits on 32-bit arch */
 	hash = cifs_uniqueid_to_ino_t(fattr->cf_uniqueid);
 
 	inode = iget5_locked(sb, hash, cifs_find_inode, cifs_init_inode, fattr);
-
-	/* we have fattrs in hand, update the inode */
 	if (inode) {
+		/* was there a problematic inode number collision? */
+		if (fattr->cf_flags & CIFS_FATTR_INO_COLLISION) {
+			iput(inode);
+			fattr->cf_uniqueid = iunique(sb, ROOT_I);
+			fattr->cf_flags &= ~CIFS_FATTR_INO_COLLISION;
+			goto retry_iget5_locked;
+		}
+
 		cifs_fattr_to_inode(inode, fattr);
 		if (sb->s_flags & MS_NOATIME)
 			inode->i_flags |= S_NOATIME | S_NOCMTIME;
@@ -780,7 +808,7 @@
 		return ERR_PTR(-ENOMEM);
 
 	if (rc && cifs_sb->tcon->ipc) {
-		cFYI(1, ("ipc connection - fake read inode"));
+		cFYI(1, "ipc connection - fake read inode");
 		inode->i_mode |= S_IFDIR;
 		inode->i_nlink = 2;
 		inode->i_op = &cifs_ipc_inode_ops;
@@ -842,7 +870,7 @@
 	 * server times.
 	 */
 	if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
-		cFYI(1, ("CIFS - CTIME changed"));
+		cFYI(1, "CIFS - CTIME changed");
 		info_buf.ChangeTime =
 		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
 	} else
@@ -877,8 +905,8 @@
 			goto out;
 	}
 
-	cFYI(1, ("calling SetFileInfo since SetPathInfo for "
-		 "times not supported by this server"));
+	cFYI(1, "calling SetFileInfo since SetPathInfo for "
+		 "times not supported by this server");
 	rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN,
 			 SYNCHRONIZE | FILE_WRITE_ATTRIBUTES,
 			 CREATE_NOT_DIR, &netfid, &oplock,
@@ -1036,7 +1064,7 @@
 	struct iattr *attrs = NULL;
 	__u32 dosattr = 0, origattr = 0;
 
-	cFYI(1, ("cifs_unlink, dir=0x%p, dentry=0x%p", dir, dentry));
+	cFYI(1, "cifs_unlink, dir=0x%p, dentry=0x%p", dir, dentry);
 
 	xid = GetXid();
 
@@ -1055,7 +1083,7 @@
 		rc = CIFSPOSIXDelFile(xid, tcon, full_path,
 			SMB_POSIX_UNLINK_FILE_TARGET, cifs_sb->local_nls,
 			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
-		cFYI(1, ("posix del rc %d", rc));
+		cFYI(1, "posix del rc %d", rc);
 		if ((rc == 0) || (rc == -ENOENT))
 			goto psx_del_no_retry;
 	}
@@ -1129,7 +1157,7 @@
 	struct inode *newinode = NULL;
 	struct cifs_fattr fattr;
 
-	cFYI(1, ("In cifs_mkdir, mode = 0x%x inode = 0x%p", mode, inode));
+	cFYI(1, "In cifs_mkdir, mode = 0x%x inode = 0x%p", mode, inode);
 
 	xid = GetXid();
 
@@ -1164,7 +1192,7 @@
 			kfree(pInfo);
 			goto mkdir_retry_old;
 		} else if (rc) {
-			cFYI(1, ("posix mkdir returned 0x%x", rc));
+			cFYI(1, "posix mkdir returned 0x%x", rc);
 			d_drop(direntry);
 		} else {
 			if (pInfo->Type == cpu_to_le32(-1)) {
@@ -1181,6 +1209,7 @@
 				direntry->d_op = &cifs_dentry_ops;
 
 			cifs_unix_basic_to_fattr(&fattr, pInfo, cifs_sb);
+			cifs_fill_uniqueid(inode->i_sb, &fattr);
 			newinode = cifs_iget(inode->i_sb, &fattr);
 			if (!newinode) {
 				kfree(pInfo);
@@ -1190,12 +1219,12 @@
 			d_instantiate(direntry, newinode);
 
 #ifdef CONFIG_CIFS_DEBUG2
-			cFYI(1, ("instantiated dentry %p %s to inode %p",
-				direntry, direntry->d_name.name, newinode));
+			cFYI(1, "instantiated dentry %p %s to inode %p",
+				direntry, direntry->d_name.name, newinode);
 
 			if (newinode->i_nlink != 2)
-				cFYI(1, ("unexpected number of links %d",
-					newinode->i_nlink));
+				cFYI(1, "unexpected number of links %d",
+					newinode->i_nlink);
 #endif
 		}
 		kfree(pInfo);
@@ -1206,7 +1235,7 @@
 	rc = CIFSSMBMkDir(xid, pTcon, full_path, cifs_sb->local_nls,
 			  cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
 	if (rc) {
-		cFYI(1, ("cifs_mkdir returned 0x%x", rc));
+		cFYI(1, "cifs_mkdir returned 0x%x", rc);
 		d_drop(direntry);
 	} else {
 mkdir_get_info:
@@ -1309,7 +1338,7 @@
 	char *full_path = NULL;
 	struct cifsInodeInfo *cifsInode;
 
-	cFYI(1, ("cifs_rmdir, inode = 0x%p", inode));
+	cFYI(1, "cifs_rmdir, inode = 0x%p", inode);
 
 	xid = GetXid();
 
@@ -1511,6 +1540,11 @@
 	if (time_after_eq(jiffies, cifs_i->time + HZ))
 		return true;
 
+	/* hardlinked files w/ noserverino get "special" treatment */
+	if (!(CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
+	    S_ISREG(inode->i_mode) && inode->i_nlink != 1)
+		return true;
+
 	return false;
 }
 
@@ -1577,9 +1611,9 @@
 		goto check_inval;
 	}
 
-	cFYI(1, ("Revalidate: %s inode 0x%p count %d dentry: 0x%p d_time %ld "
+	cFYI(1, "Revalidate: %s inode 0x%p count %d dentry: 0x%p d_time %ld "
 		 "jiffies %ld", full_path, inode, inode->i_count.counter,
-		 dentry, dentry->d_time, jiffies));
+		 dentry, dentry->d_time, jiffies);
 
 	if (CIFS_SB(sb)->tcon->unix_ext)
 		rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid);
@@ -1673,12 +1707,12 @@
 		rc = CIFSSMBSetFileSize(xid, pTcon, attrs->ia_size, nfid,
 					npid, false);
 		cifsFileInfo_put(open_file);
-		cFYI(1, ("SetFSize for attrs rc = %d", rc));
+		cFYI(1, "SetFSize for attrs rc = %d", rc);
 		if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
 			unsigned int bytes_written;
 			rc = CIFSSMBWrite(xid, pTcon, nfid, 0, attrs->ia_size,
 					  &bytes_written, NULL, NULL, 1);
-			cFYI(1, ("Wrt seteof rc %d", rc));
+			cFYI(1, "Wrt seteof rc %d", rc);
 		}
 	} else
 		rc = -EINVAL;
@@ -1692,7 +1726,7 @@
 				   false, cifs_sb->local_nls,
 				   cifs_sb->mnt_cifs_flags &
 					CIFS_MOUNT_MAP_SPECIAL_CHR);
-		cFYI(1, ("SetEOF by path (setattrs) rc = %d", rc));
+		cFYI(1, "SetEOF by path (setattrs) rc = %d", rc);
 		if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
 			__u16 netfid;
 			int oplock = 0;
@@ -1709,7 +1743,7 @@
 						  attrs->ia_size,
 						  &bytes_written, NULL,
 						  NULL, 1);
-				cFYI(1, ("wrt seteof rc %d", rc));
+				cFYI(1, "wrt seteof rc %d", rc);
 				CIFSSMBClose(xid, pTcon, netfid);
 			}
 		}
@@ -1737,8 +1771,8 @@
 	struct cifs_unix_set_info_args *args = NULL;
 	struct cifsFileInfo *open_file;
 
-	cFYI(1, ("setattr_unix on file %s attrs->ia_valid=0x%x",
-		 direntry->d_name.name, attrs->ia_valid));
+	cFYI(1, "setattr_unix on file %s attrs->ia_valid=0x%x",
+		 direntry->d_name.name, attrs->ia_valid);
 
 	xid = GetXid();
 
@@ -1868,8 +1902,8 @@
 
 	xid = GetXid();
 
-	cFYI(1, ("setattr on file %s attrs->iavalid 0x%x",
-		 direntry->d_name.name, attrs->ia_valid));
+	cFYI(1, "setattr on file %s attrs->iavalid 0x%x",
+		 direntry->d_name.name, attrs->ia_valid);
 
 	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) == 0) {
 		/* check if we have permission to change attrs */
@@ -1926,7 +1960,7 @@
 		attrs->ia_valid &= ~ATTR_MODE;
 
 	if (attrs->ia_valid & ATTR_MODE) {
-		cFYI(1, ("Mode changed to 0%o", attrs->ia_mode));
+		cFYI(1, "Mode changed to 0%o", attrs->ia_mode);
 		mode = attrs->ia_mode;
 	}
 
@@ -2012,7 +2046,7 @@
 #if 0
 void cifs_delete_inode(struct inode *inode)
 {
-	cFYI(1, ("In cifs_delete_inode, inode = 0x%p", inode));
+	cFYI(1, "In cifs_delete_inode, inode = 0x%p", inode);
 	/* may have to add back in if and when safe distributed caching of
 	   directories added e.g. via FindNotify */
 }

fs/cifs/ioctl.c

diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index f946506..505926f 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -47,7 +47,7 @@
 
 	xid = GetXid();
 
-	cFYI(1, ("ioctl file %p  cmd %u  arg %lu", filep, command, arg));
+	cFYI(1, "ioctl file %p  cmd %u  arg %lu", filep, command, arg);
 
 	cifs_sb = CIFS_SB(inode->i_sb);
 
@@ -64,12 +64,12 @@
 
 	switch (command) {
 		case CIFS_IOC_CHECKUMOUNT:
-			cFYI(1, ("User unmount attempted"));
+			cFYI(1, "User unmount attempted");
 			if (cifs_sb->mnt_uid == current_uid())
 				rc = 0;
 			else {
 				rc = -EACCES;
-				cFYI(1, ("uids do not match"));
+				cFYI(1, "uids do not match");
 			}
 			break;
 #ifdef CONFIG_CIFS_POSIX
@@ -97,11 +97,11 @@
 				/* rc= CIFSGetExtAttr(xid,tcon,pSMBFile->netfid,
 					extAttrBits, &ExtAttrMask);*/
 			}
-			cFYI(1, ("set flags not implemented yet"));
+			cFYI(1, "set flags not implemented yet");
 			break;
 #endif /* CONFIG_CIFS_POSIX */
 		default:
-			cFYI(1, ("unsupported ioctl"));
+			cFYI(1, "unsupported ioctl");
 			break;
 	}
 

fs/cifs/link.c

diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index c1a9d42..473ca80 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -139,7 +139,7 @@
 	if (!full_path)
 		goto out;
 
-	cFYI(1, ("Full path: %s inode = 0x%p", full_path, inode));
+	cFYI(1, "Full path: %s inode = 0x%p", full_path, inode);
 
 	rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, &target_path,
 				     cifs_sb->local_nls);
@@ -178,8 +178,8 @@
 		return rc;
 	}
 
-	cFYI(1, ("Full path: %s", full_path));
-	cFYI(1, ("symname is %s", symname));
+	cFYI(1, "Full path: %s", full_path);
+	cFYI(1, "symname is %s", symname);
 
 	/* BB what if DFS and this volume is on different share? BB */
 	if (pTcon->unix_ext)
@@ -198,8 +198,8 @@
 						 inode->i_sb, xid, NULL);
 
 		if (rc != 0) {
-			cFYI(1, ("Create symlink ok, getinodeinfo fail rc = %d",
-			      rc));
+			cFYI(1, "Create symlink ok, getinodeinfo fail rc = %d",
+			      rc);
 		} else {
 			if (pTcon->nocase)
 				direntry->d_op = &cifs_ci_dentry_ops;

fs/cifs/misc.c

diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index d147499..1394aa3 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -51,7 +51,7 @@
 	if (GlobalTotalActiveXid > GlobalMaxActiveXid)
 		GlobalMaxActiveXid = GlobalTotalActiveXid;
 	if (GlobalTotalActiveXid > 65000)
-		cFYI(1, ("warning: more than 65000 requests active"));
+		cFYI(1, "warning: more than 65000 requests active");
 	xid = GlobalCurrentXid++;
 	spin_unlock(&GlobalMid_Lock);
 	return xid;
@@ -88,7 +88,7 @@
 sesInfoFree(struct cifsSesInfo *buf_to_free)
 {
 	if (buf_to_free == NULL) {
-		cFYI(1, ("Null buffer passed to sesInfoFree"));
+		cFYI(1, "Null buffer passed to sesInfoFree");
 		return;
 	}
 
@@ -126,7 +126,7 @@
 tconInfoFree(struct cifsTconInfo *buf_to_free)
 {
 	if (buf_to_free == NULL) {
-		cFYI(1, ("Null buffer passed to tconInfoFree"));
+		cFYI(1, "Null buffer passed to tconInfoFree");
 		return;
 	}
 	atomic_dec(&tconInfoAllocCount);
@@ -166,7 +166,7 @@
 cifs_buf_release(void *buf_to_free)
 {
 	if (buf_to_free == NULL) {
-		/* cFYI(1, ("Null buffer passed to cifs_buf_release"));*/
+		/* cFYI(1, "Null buffer passed to cifs_buf_release");*/
 		return;
 	}
 	mempool_free(buf_to_free, cifs_req_poolp);
@@ -202,7 +202,7 @@
 {
 
 	if (buf_to_free == NULL) {
-		cFYI(1, ("Null buffer passed to cifs_small_buf_release"));
+		cFYI(1, "Null buffer passed to cifs_small_buf_release");
 		return;
 	}
 	mempool_free(buf_to_free, cifs_sm_req_poolp);
@@ -345,19 +345,19 @@
 		/*      with userid/password pairs found on the smb session   */
 		/*	for other target tcp/ip addresses 		BB    */
 				if (current_fsuid() != treeCon->ses->linux_uid) {
-					cFYI(1, ("Multiuser mode and UID "
-						 "did not match tcon uid"));
+					cFYI(1, "Multiuser mode and UID "
+						 "did not match tcon uid");
 					read_lock(&cifs_tcp_ses_lock);
 					list_for_each(temp_item, &treeCon->ses->server->smb_ses_list) {
 						ses = list_entry(temp_item, struct cifsSesInfo, smb_ses_list);
 						if (ses->linux_uid == current_fsuid()) {
 							if (ses->server == treeCon->ses->server) {
-								cFYI(1, ("found matching uid substitute right smb_uid"));
+								cFYI(1, "found matching uid substitute right smb_uid");
 								buffer->Uid = ses->Suid;
 								break;
 							} else {
 				/* BB eventually call cifs_setup_session here */
-								cFYI(1, ("local UID found but no smb sess with this server exists"));
+								cFYI(1, "local UID found but no smb sess with this server exists");
 							}
 						}
 					}
@@ -394,17 +394,16 @@
 			if (smb->Command == SMB_COM_LOCKING_ANDX)
 				return 0;
 			else
-				cERROR(1, ("Received Request not response"));
+				cERROR(1, "Received Request not response");
 		}
 	} else { /* bad signature or mid */
 		if (*(__le32 *) smb->Protocol != cpu_to_le32(0x424d53ff))
-			cERROR(1,
-			       ("Bad protocol string signature header %x",
-				*(unsigned int *) smb->Protocol));
+			cERROR(1, "Bad protocol string signature header %x",
+				*(unsigned int *) smb->Protocol);
 		if (mid != smb->Mid)
-			cERROR(1, ("Mids do not match"));
+			cERROR(1, "Mids do not match");
 	}
-	cERROR(1, ("bad smb detected. The Mid=%d", smb->Mid));
+	cERROR(1, "bad smb detected. The Mid=%d", smb->Mid);
 	return 1;
 }
 
@@ -413,7 +412,7 @@
 {
 	__u32 len = smb->smb_buf_length;
 	__u32 clc_len;  /* calculated length */
-	cFYI(0, ("checkSMB Length: 0x%x, smb_buf_length: 0x%x", length, len));
+	cFYI(0, "checkSMB Length: 0x%x, smb_buf_length: 0x%x", length, len);
 
 	if (length < 2 + sizeof(struct smb_hdr)) {
 		if ((length >= sizeof(struct smb_hdr) - 1)
@@ -437,15 +436,15 @@
 				tmp[sizeof(struct smb_hdr)+1] = 0;
 				return 0;
 			}
-			cERROR(1, ("rcvd invalid byte count (bcc)"));
+			cERROR(1, "rcvd invalid byte count (bcc)");
 		} else {
-			cERROR(1, ("Length less than smb header size"));
+			cERROR(1, "Length less than smb header size");
 		}
 		return 1;
 	}
 	if (len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
-		cERROR(1, ("smb length greater than MaxBufSize, mid=%d",
-				   smb->Mid));
+		cERROR(1, "smb length greater than MaxBufSize, mid=%d",
+				   smb->Mid);
 		return 1;
 	}
 
@@ -454,8 +453,8 @@
 	clc_len = smbCalcSize_LE(smb);
 
 	if (4 + len != length) {
-		cERROR(1, ("Length read does not match RFC1001 length %d",
-			   len));
+		cERROR(1, "Length read does not match RFC1001 length %d",
+			   len);
 		return 1;
 	}
 
@@ -466,8 +465,8 @@
 			if (((4 + len) & 0xFFFF) == (clc_len & 0xFFFF))
 				return 0; /* bcc wrapped */
 		}
-		cFYI(1, ("Calculated size %d vs length %d mismatch for mid %d",
-				clc_len, 4 + len, smb->Mid));
+		cFYI(1, "Calculated size %d vs length %d mismatch for mid %d",
+				clc_len, 4 + len, smb->Mid);
 		/* Windows XP can return a few bytes too much, presumably
 		an illegal pad, at the end of byte range lock responses
 		so we allow for that three byte pad, as long as actual
@@ -482,8 +481,8 @@
 		if ((4+len > clc_len) && (len <= clc_len + 512))
 			return 0;
 		else {
-			cERROR(1, ("RFC1001 size %d bigger than SMB for Mid=%d",
-					len, smb->Mid));
+			cERROR(1, "RFC1001 size %d bigger than SMB for Mid=%d",
+					len, smb->Mid);
 			return 1;
 		}
 	}
@@ -501,7 +500,7 @@
 	struct cifsFileInfo *netfile;
 	int rc;
 
-	cFYI(1, ("Checking for oplock break or dnotify response"));
+	cFYI(1, "Checking for oplock break or dnotify response");
 	if ((pSMB->hdr.Command == SMB_COM_NT_TRANSACT) &&
 	   (pSMB->hdr.Flags & SMBFLG_RESPONSE)) {
 		struct smb_com_transaction_change_notify_rsp *pSMBr =
@@ -513,15 +512,15 @@
 
 			pnotify = (struct file_notify_information *)
 				((char *)&pSMBr->hdr.Protocol + data_offset);
-			cFYI(1, ("dnotify on %s Action: 0x%x",
-				 pnotify->FileName, pnotify->Action));
+			cFYI(1, "dnotify on %s Action: 0x%x",
+				 pnotify->FileName, pnotify->Action);
 			/*   cifs_dump_mem("Rcvd notify Data: ",buf,
 				sizeof(struct smb_hdr)+60); */
 			return true;
 		}
 		if (pSMBr->hdr.Status.CifsError) {
-			cFYI(1, ("notify err 0x%d",
-				pSMBr->hdr.Status.CifsError));
+			cFYI(1, "notify err 0x%d",
+				pSMBr->hdr.Status.CifsError);
 			return true;
 		}
 		return false;
@@ -535,7 +534,7 @@
 		   large dirty files cached on the client */
 		if ((NT_STATUS_INVALID_HANDLE) ==
 		   le32_to_cpu(pSMB->hdr.Status.CifsError)) {
-			cFYI(1, ("invalid handle on oplock break"));
+			cFYI(1, "invalid handle on oplock break");
 			return true;
 		} else if (ERRbadfid ==
 		   le16_to_cpu(pSMB->hdr.Status.DosError.Error)) {
@@ -547,8 +546,8 @@
 	if (pSMB->hdr.WordCount != 8)
 		return false;
 
-	cFYI(1, ("oplock type 0x%d level 0x%d",
-		 pSMB->LockType, pSMB->OplockLevel));
+	cFYI(1, "oplock type 0x%d level 0x%d",
+		 pSMB->LockType, pSMB->OplockLevel);
 	if (!(pSMB->LockType & LOCKING_ANDX_OPLOCK_RELEASE))
 		return false;
 
@@ -579,15 +578,15 @@
 					return true;
 				}
 
-				cFYI(1, ("file id match, oplock break"));
+				cFYI(1, "file id match, oplock break");
 				pCifsInode = CIFS_I(netfile->pInode);
 				pCifsInode->clientCanCacheAll = false;
 				if (pSMB->OplockLevel == 0)
 					pCifsInode->clientCanCacheRead = false;
 				rc = slow_work_enqueue(&netfile->oplock_break);
 				if (rc) {
-					cERROR(1, ("failed to enqueue oplock "
-						   "break: %d\n", rc));
+					cERROR(1, "failed to enqueue oplock "
+						   "break: %d\n", rc);
 				} else {
 					netfile->oplock_break_cancelled = false;
 				}
@@ -597,12 +596,12 @@
 			}
 			read_unlock(&GlobalSMBSeslock);
 			read_unlock(&cifs_tcp_ses_lock);
-			cFYI(1, ("No matching file for oplock break"));
+			cFYI(1, "No matching file for oplock break");
 			return true;
 		}
 	}
 	read_unlock(&cifs_tcp_ses_lock);
-	cFYI(1, ("Can not process oplock break for non-existent connection"));
+	cFYI(1, "Can not process oplock break for non-existent connection");
 	return true;
 }
 
@@ -721,11 +720,11 @@
 {
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
 		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM;
-		cERROR(1, ("Autodisabling the use of server inode numbers on "
+		cERROR(1, "Autodisabling the use of server inode numbers on "
 			   "%s. This server doesn't seem to support them "
 			   "properly. Hardlinks will not be recognized on this "
 			   "mount. Consider mounting with the \"noserverino\" "
 			   "option to silence this message.",
-			   cifs_sb->tcon->treeName));
+			   cifs_sb->tcon->treeName);
 	}
 }

fs/cifs/netmisc.c

diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index bd6d689..d35d528 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -149,7 +149,7 @@
 	else if (address_family == AF_INET6)
 		ret = in6_pton(cp, -1 /* len */, dst , '\\', NULL);
 
-	cFYI(DBG2, ("address conversion returned %d for %s", ret, cp));
+	cFYI(DBG2, "address conversion returned %d for %s", ret, cp);
 	if (ret > 0)
 		ret = 1;
 	return ret;
@@ -870,8 +870,8 @@
 	}
 	/* else ERRHRD class errors or junk  - return EIO */
 
-	cFYI(1, ("Mapping smb error code %d to POSIX err %d",
-		 smberrcode, rc));
+	cFYI(1, "Mapping smb error code %d to POSIX err %d",
+		 smberrcode, rc);
 
 	/* generic corrective action e.g. reconnect SMB session on
 	 * ERRbaduid could be added */
@@ -940,20 +940,20 @@
 	SMB_TIME *st = (SMB_TIME *)&time;
 	SMB_DATE *sd = (SMB_DATE *)&date;
 
-	cFYI(1, ("date %d time %d", date, time));
+	cFYI(1, "date %d time %d", date, time);
 
 	sec = 2 * st->TwoSeconds;
 	min = st->Minutes;
 	if ((sec > 59) || (min > 59))
-		cERROR(1, ("illegal time min %d sec %d", min, sec));
+		cERROR(1, "illegal time min %d sec %d", min, sec);
 	sec += (min * 60);
 	sec += 60 * 60 * st->Hours;
 	if (st->Hours > 24)
-		cERROR(1, ("illegal hours %d", st->Hours));
+		cERROR(1, "illegal hours %d", st->Hours);
 	days = sd->Day;
 	month = sd->Month;
 	if ((days > 31) || (month > 12)) {
-		cERROR(1, ("illegal date, month %d day: %d", month, days));
+		cERROR(1, "illegal date, month %d day: %d", month, days);
 		if (month > 12)
 			month = 12;
 	}
@@ -979,7 +979,7 @@
 
 	ts.tv_sec = sec + offset;
 
-	/* cFYI(1,("sec after cnvrt dos to unix time %d",sec)); */
+	/* cFYI(1, "sec after cnvrt dos to unix time %d",sec); */
 
 	ts.tv_nsec = 0;
 	return ts;

fs/cifs/readdir.c

diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 18e0bc1..daf1753 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -47,15 +47,15 @@
 	if (file) {
 		cf = file->private_data;
 		if (cf == NULL) {
-			cFYI(1, ("empty cifs private file data"));
+			cFYI(1, "empty cifs private file data");
 			return;
 		}
 		if (cf->invalidHandle)
-			cFYI(1, ("invalid handle"));
+			cFYI(1, "invalid handle");
 		if (cf->srch_inf.endOfSearch)
-			cFYI(1, ("end of search"));
+			cFYI(1, "end of search");
 		if (cf->srch_inf.emptyDir)
-			cFYI(1, ("empty dir"));
+			cFYI(1, "empty dir");
 	}
 }
 #else
@@ -76,7 +76,7 @@
 	struct inode *inode;
 	struct super_block *sb = parent->d_inode->i_sb;
 
-	cFYI(1, ("For %s", name->name));
+	cFYI(1, "For %s", name->name);
 
 	if (parent->d_op && parent->d_op->d_hash)
 		parent->d_op->d_hash(parent, name);
@@ -214,7 +214,7 @@
 				fid,
 				cifs_sb->local_nls);
 		if (CIFSSMBClose(xid, ptcon, fid)) {
-			cFYI(1, ("Error closing temporary reparsepoint open)"));
+			cFYI(1, "Error closing temporary reparsepoint open");
 		}
 	}
 }
@@ -252,7 +252,7 @@
 	if (full_path == NULL)
 		return -ENOMEM;
 
-	cFYI(1, ("Full path: %s start at: %lld", full_path, file->f_pos));
+	cFYI(1, "Full path: %s start at: %lld", full_path, file->f_pos);
 
 ffirst_retry:
 	/* test for Unix extensions */
@@ -297,7 +297,7 @@
 		if (ustr[len] == 0)
 			return len << 1;
 	}
-	cFYI(1, ("Unicode string longer than PATH_MAX found"));
+	cFYI(1, "Unicode string longer than PATH_MAX found");
 	return len << 1;
 }
 
@@ -314,19 +314,18 @@
 				pfData->FileNameLength;
 	} else
 		new_entry = old_entry + le32_to_cpu(pDirInfo->NextEntryOffset);
-	cFYI(1, ("new entry %p old entry %p", new_entry, old_entry));
+	cFYI(1, "new entry %p old entry %p", new_entry, old_entry);
 	/* validate that new_entry is not past end of SMB */
 	if (new_entry >= end_of_smb) {
-		cERROR(1,
-		      ("search entry %p began after end of SMB %p old entry %p",
-			new_entry, end_of_smb, old_entry));
+		cERROR(1, "search entry %p began after end of SMB %p old entry %p",
+			new_entry, end_of_smb, old_entry);
 		return NULL;
 	} else if (((level == SMB_FIND_FILE_INFO_STANDARD) &&
 		    (new_entry + sizeof(FIND_FILE_STANDARD_INFO) > end_of_smb))
 		  || ((level != SMB_FIND_FILE_INFO_STANDARD) &&
 		   (new_entry + sizeof(FILE_DIRECTORY_INFO) > end_of_smb)))  {
-		cERROR(1, ("search entry %p extends after end of SMB %p",
-			new_entry, end_of_smb));
+		cERROR(1, "search entry %p extends after end of SMB %p",
+			new_entry, end_of_smb);
 		return NULL;
 	} else
 		return new_entry;
@@ -380,8 +379,8 @@
 		filename = &pFindData->FileName[0];
 		len = pFindData->FileNameLength;
 	} else {
-		cFYI(1, ("Unknown findfirst level %d",
-			 cfile->srch_inf.info_level));
+		cFYI(1, "Unknown findfirst level %d",
+			 cfile->srch_inf.info_level);
 	}
 
 	if (filename) {
@@ -481,7 +480,7 @@
 		len = (unsigned int)pFindData->FileNameLength;
 		cifsFile->srch_inf.resume_key = pFindData->ResumeKey;
 	} else {
-		cFYI(1, ("Unknown findfirst level %d", level));
+		cFYI(1, "Unknown findfirst level %d", level);
 		return -EINVAL;
 	}
 	cifsFile->srch_inf.resume_name_len = len;
@@ -525,7 +524,7 @@
 	     is_dir_changed(file)) ||
 	   (index_to_find < first_entry_in_buffer)) {
 		/* close and restart search */
-		cFYI(1, ("search backing up - close and restart search"));
+		cFYI(1, "search backing up - close and restart search");
 		write_lock(&GlobalSMBSeslock);
 		if (!cifsFile->srch_inf.endOfSearch &&
 		    !cifsFile->invalidHandle) {
@@ -535,7 +534,7 @@
 		} else
 			write_unlock(&GlobalSMBSeslock);
 		if (cifsFile->srch_inf.ntwrk_buf_start) {
-			cFYI(1, ("freeing SMB ff cache buf on search rewind"));
+			cFYI(1, "freeing SMB ff cache buf on search rewind");
 			if (cifsFile->srch_inf.smallBuf)
 				cifs_small_buf_release(cifsFile->srch_inf.
 						ntwrk_buf_start);
@@ -546,8 +545,8 @@
 		}
 		rc = initiate_cifs_search(xid, file);
 		if (rc) {
-			cFYI(1, ("error %d reinitiating a search on rewind",
-				 rc));
+			cFYI(1, "error %d reinitiating a search on rewind",
+				 rc);
 			return rc;
 		}
 		cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile);
@@ -555,7 +554,7 @@
 
 	while ((index_to_find >= cifsFile->srch_inf.index_of_last_entry) &&
 	      (rc == 0) && !cifsFile->srch_inf.endOfSearch) {
-		cFYI(1, ("calling findnext2"));
+		cFYI(1, "calling findnext2");
 		rc = CIFSFindNext(xid, pTcon, cifsFile->netfid,
 				  &cifsFile->srch_inf);
 		cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile);
@@ -575,7 +574,7 @@
 		first_entry_in_buffer = cifsFile->srch_inf.index_of_last_entry
 					- cifsFile->srch_inf.entries_in_buffer;
 		pos_in_buf = index_to_find - first_entry_in_buffer;
-		cFYI(1, ("found entry - pos_in_buf %d", pos_in_buf));
+		cFYI(1, "found entry - pos_in_buf %d", pos_in_buf);
 
 		for (i = 0; (i < (pos_in_buf)) && (current_entry != NULL); i++) {
 			/* go entry by entry figuring out which is first */
@@ -584,19 +583,19 @@
 		}
 		if ((current_entry == NULL) && (i < pos_in_buf)) {
 			/* BB fixme - check if we should flag this error */
-			cERROR(1, ("reached end of buf searching for pos in buf"
+			cERROR(1, "reached end of buf searching for pos in buf"
 			  " %d index to find %lld rc %d",
-			  pos_in_buf, index_to_find, rc));
+			  pos_in_buf, index_to_find, rc);
 		}
 		rc = 0;
 		*ppCurrentEntry = current_entry;
 	} else {
-		cFYI(1, ("index not in buffer - could not findnext into it"));
+		cFYI(1, "index not in buffer - could not findnext into it");
 		return 0;
 	}
 
 	if (pos_in_buf >= cifsFile->srch_inf.entries_in_buffer) {
-		cFYI(1, ("can not return entries pos_in_buf beyond last"));
+		cFYI(1, "can not return entries pos_in_buf beyond last");
 		*num_to_ret = 0;
 	} else
 		*num_to_ret = cifsFile->srch_inf.entries_in_buffer - pos_in_buf;
@@ -656,12 +655,12 @@
 		/* one byte length, no name conversion */
 		len = (unsigned int)pFindData->FileNameLength;
 	} else {
-		cFYI(1, ("Unknown findfirst level %d", level));
+		cFYI(1, "Unknown findfirst level %d", level);
 		return -EINVAL;
 	}
 
 	if (len > max_len) {
-		cERROR(1, ("bad search response length %d past smb end", len));
+		cERROR(1, "bad search response length %d past smb end", len);
 		return -EINVAL;
 	}
 
@@ -754,7 +753,7 @@
 	 * case already. Why should we be clobbering other errors from it?
 	 */
 	if (rc) {
-		cFYI(1, ("filldir rc = %d", rc));
+		cFYI(1, "filldir rc = %d", rc);
 		rc = -EOVERFLOW;
 	}
 	dput(tmp_dentry);
@@ -786,7 +785,7 @@
 	case 0:
 		if (filldir(direntry, ".", 1, file->f_pos,
 		     file->f_path.dentry->d_inode->i_ino, DT_DIR) < 0) {
-			cERROR(1, ("Filldir for current dir failed"));
+			cERROR(1, "Filldir for current dir failed");
 			rc = -ENOMEM;
 			break;
 		}
@@ -794,7 +793,7 @@
 	case 1:
 		if (filldir(direntry, "..", 2, file->f_pos,
 		     file->f_path.dentry->d_parent->d_inode->i_ino, DT_DIR) < 0) {
-			cERROR(1, ("Filldir for parent dir failed"));
+			cERROR(1, "Filldir for parent dir failed");
 			rc = -ENOMEM;
 			break;
 		}
@@ -807,7 +806,7 @@
 
 		if (file->private_data == NULL) {
 			rc = initiate_cifs_search(xid, file);
-			cFYI(1, ("initiate cifs search rc %d", rc));
+			cFYI(1, "initiate cifs search rc %d", rc);
 			if (rc) {
 				FreeXid(xid);
 				return rc;
@@ -821,7 +820,7 @@
 		cifsFile = file->private_data;
 		if (cifsFile->srch_inf.endOfSearch) {
 			if (cifsFile->srch_inf.emptyDir) {
-				cFYI(1, ("End of search, empty dir"));
+				cFYI(1, "End of search, empty dir");
 				rc = 0;
 				break;
 			}
@@ -833,16 +832,16 @@
 		rc = find_cifs_entry(xid, pTcon, file,
 				&current_entry, &num_to_fill);
 		if (rc) {
-			cFYI(1, ("fce error %d", rc));
+			cFYI(1, "fce error %d", rc);
 			goto rddir2_exit;
 		} else if (current_entry != NULL) {
-			cFYI(1, ("entry %lld found", file->f_pos));
+			cFYI(1, "entry %lld found", file->f_pos);
 		} else {
-			cFYI(1, ("could not find entry"));
+			cFYI(1, "could not find entry");
 			goto rddir2_exit;
 		}
-		cFYI(1, ("loop through %d times filling dir for net buf %p",
-			num_to_fill, cifsFile->srch_inf.ntwrk_buf_start));
+		cFYI(1, "loop through %d times filling dir for net buf %p",
+			num_to_fill, cifsFile->srch_inf.ntwrk_buf_start);
 		max_len = smbCalcSize((struct smb_hdr *)
 				cifsFile->srch_inf.ntwrk_buf_start);
 		end_of_smb = cifsFile->srch_inf.ntwrk_buf_start + max_len;
@@ -851,8 +850,8 @@
 		for (i = 0; (i < num_to_fill) && (rc == 0); i++) {
 			if (current_entry == NULL) {
 				/* evaluate whether this case is an error */
-				cERROR(1, ("past SMB end,  num to fill %d i %d",
-					  num_to_fill, i));
+				cERROR(1, "past SMB end,  num to fill %d i %d",
+					  num_to_fill, i);
 				break;
 			}
 			/* if buggy server returns . and .. late do
@@ -867,8 +866,8 @@
 			file->f_pos++;
 			if (file->f_pos ==
 				cifsFile->srch_inf.index_of_last_entry) {
-				cFYI(1, ("last entry in buf at pos %lld %s",
-					file->f_pos, tmp_buf));
+				cFYI(1, "last entry in buf at pos %lld %s",
+					file->f_pos, tmp_buf);
 				cifs_save_resume_key(current_entry, cifsFile);
 				break;
 			} else

fs/cifs/sess.c

diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 7c3fd74..7707389 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -35,9 +35,11 @@
 extern void SMBNTencrypt(unsigned char *passwd, unsigned char *c8,
 			 unsigned char *p24);
 
-/* Checks if this is the first smb session to be reconnected after
-   the socket has been reestablished (so we know whether to use vc 0).
-   Called while holding the cifs_tcp_ses_lock, so do not block */
+/*
+ * Checks if this is the first smb session to be reconnected after
+ * the socket has been reestablished (so we know whether to use vc 0).
+ * Called while holding the cifs_tcp_ses_lock, so do not block
+ */
 static bool is_first_ses_reconnect(struct cifsSesInfo *ses)
 {
 	struct list_head *tmp;
@@ -284,7 +286,7 @@
 	int len;
 	char *data = *pbcc_area;
 
-	cFYI(1, ("bleft %d", bleft));
+	cFYI(1, "bleft %d", bleft);
 
 	/*
 	 * Windows servers do not always double null terminate their final
@@ -301,7 +303,7 @@
 
 	kfree(ses->serverOS);
 	ses->serverOS = cifs_strndup_from_ucs(data, bleft, true, nls_cp);
-	cFYI(1, ("serverOS=%s", ses->serverOS));
+	cFYI(1, "serverOS=%s", ses->serverOS);
 	len = (UniStrnlen((wchar_t *) data, bleft / 2) * 2) + 2;
 	data += len;
 	bleft -= len;
@@ -310,7 +312,7 @@
 
 	kfree(ses->serverNOS);
 	ses->serverNOS = cifs_strndup_from_ucs(data, bleft, true, nls_cp);
-	cFYI(1, ("serverNOS=%s", ses->serverNOS));
+	cFYI(1, "serverNOS=%s", ses->serverNOS);
 	len = (UniStrnlen((wchar_t *) data, bleft / 2) * 2) + 2;
 	data += len;
 	bleft -= len;
@@ -319,7 +321,7 @@
 
 	kfree(ses->serverDomain);
 	ses->serverDomain = cifs_strndup_from_ucs(data, bleft, true, nls_cp);
-	cFYI(1, ("serverDomain=%s", ses->serverDomain));
+	cFYI(1, "serverDomain=%s", ses->serverDomain);
 
 	return;
 }
@@ -332,7 +334,7 @@
 	int len;
 	char *bcc_ptr = *pbcc_area;
 
-	cFYI(1, ("decode sessetup ascii. bleft %d", bleft));
+	cFYI(1, "decode sessetup ascii. bleft %d", bleft);
 
 	len = strnlen(bcc_ptr, bleft);
 	if (len >= bleft)
@@ -344,7 +346,7 @@
 	if (ses->serverOS)
 		strncpy(ses->serverOS, bcc_ptr, len);
 	if (strncmp(ses->serverOS, "OS/2", 4) == 0) {
-			cFYI(1, ("OS/2 server"));
+			cFYI(1, "OS/2 server");
 			ses->flags |= CIFS_SES_OS2;
 	}
 
@@ -373,7 +375,7 @@
 	/* BB For newer servers which do not support Unicode,
 	   but thus do return domain here we could add parsing
 	   for it later, but it is not very important */
-	cFYI(1, ("ascii: bytes left %d", bleft));
+	cFYI(1, "ascii: bytes left %d", bleft);
 
 	return rc;
 }
@@ -384,16 +386,16 @@
 	CHALLENGE_MESSAGE *pblob = (CHALLENGE_MESSAGE *)bcc_ptr;
 
 	if (blob_len < sizeof(CHALLENGE_MESSAGE)) {
-		cERROR(1, ("challenge blob len %d too small", blob_len));
+		cERROR(1, "challenge blob len %d too small", blob_len);
 		return -EINVAL;
 	}
 
 	if (memcmp(pblob->Signature, "NTLMSSP", 8)) {
-		cERROR(1, ("blob signature incorrect %s", pblob->Signature));
+		cERROR(1, "blob signature incorrect %s", pblob->Signature);
 		return -EINVAL;
 	}
 	if (pblob->MessageType != NtLmChallenge) {
-		cERROR(1, ("Incorrect message type %d", pblob->MessageType));
+		cERROR(1, "Incorrect message type %d", pblob->MessageType);
 		return -EINVAL;
 	}
 
@@ -447,7 +449,7 @@
    This function returns the length of the data in the blob */
 static int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 				   struct cifsSesInfo *ses,
-				   const struct nls_table *nls_cp, int first)
+				   const struct nls_table *nls_cp, bool first)
 {
 	AUTHENTICATE_MESSAGE *sec_blob = (AUTHENTICATE_MESSAGE *)pbuffer;
 	__u32 flags;
@@ -546,7 +548,7 @@
 
 static int setup_ntlmssp_auth_req(SESSION_SETUP_ANDX *pSMB,
 				  struct cifsSesInfo *ses,
-				  const struct nls_table *nls, int first_time)
+				  const struct nls_table *nls, bool first_time)
 {
 	int bloblen;
 
@@ -559,8 +561,8 @@
 #endif
 
 int
-CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int first_time,
-		const struct nls_table *nls_cp)
+CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses,
+	       const struct nls_table *nls_cp)
 {
 	int rc = 0;
 	int wct;
@@ -577,13 +579,18 @@
 	int bytes_remaining;
 	struct key *spnego_key = NULL;
 	__le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */
+	bool first_time;
 
 	if (ses == NULL)
 		return -EINVAL;
 
+	read_lock(&cifs_tcp_ses_lock);
+	first_time = is_first_ses_reconnect(ses);
+	read_unlock(&cifs_tcp_ses_lock);
+
 	type = ses->server->secType;
 
-	cFYI(1, ("sess setup type %d", type));
+	cFYI(1, "sess setup type %d", type);
 ssetup_ntlmssp_authenticate:
 	if (phase == NtLmChallenge)
 		phase = NtLmAuthenticate; /* if ntlmssp, now final phase */
@@ -664,7 +671,7 @@
 		changed to do higher than lanman dialect and
 		we reconnected would we ever calc signing_key? */
 
-		cFYI(1, ("Negotiating LANMAN setting up strings"));
+		cFYI(1, "Negotiating LANMAN setting up strings");
 		/* Unicode not allowed for LANMAN dialects */
 		ascii_ssetup_strings(&bcc_ptr, ses, nls_cp);
 #endif
@@ -744,7 +751,7 @@
 			unicode_ssetup_strings(&bcc_ptr, ses, nls_cp);
 		} else
 			ascii_ssetup_strings(&bcc_ptr, ses, nls_cp);
-	} else if (type == Kerberos || type == MSKerberos) {
+	} else if (type == Kerberos) {
 #ifdef CONFIG_CIFS_UPCALL
 		struct cifs_spnego_msg *msg;
 		spnego_key = cifs_get_spnego_key(ses);
@@ -758,17 +765,17 @@
 		/* check version field to make sure that cifs.upcall is
 		   sending us a response in an expected form */
 		if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) {
-			cERROR(1, ("incorrect version of cifs.upcall (expected"
+			cERROR(1, "incorrect version of cifs.upcall (expected"
 				   " %d but got %d)",
-				   CIFS_SPNEGO_UPCALL_VERSION, msg->version));
+				   CIFS_SPNEGO_UPCALL_VERSION, msg->version);
 			rc = -EKEYREJECTED;
 			goto ssetup_exit;
 		}
 		/* bail out if key is too long */
 		if (msg->sesskey_len >
 		    sizeof(ses->server->mac_signing_key.data.krb5)) {
-			cERROR(1, ("Kerberos signing key too long (%u bytes)",
-				msg->sesskey_len));
+			cERROR(1, "Kerberos signing key too long (%u bytes)",
+				msg->sesskey_len);
 			rc = -EOVERFLOW;
 			goto ssetup_exit;
 		}
@@ -796,7 +803,7 @@
 		/* BB: is this right? */
 			ascii_ssetup_strings(&bcc_ptr, ses, nls_cp);
 #else /* ! CONFIG_CIFS_UPCALL */
-		cERROR(1, ("Kerberos negotiated but upcall support disabled!"));
+		cERROR(1, "Kerberos negotiated but upcall support disabled!");
 		rc = -ENOSYS;
 		goto ssetup_exit;
 #endif /* CONFIG_CIFS_UPCALL */
@@ -804,12 +811,12 @@
 #ifdef CONFIG_CIFS_EXPERIMENTAL
 		if (type == RawNTLMSSP) {
 			if ((pSMB->req.hdr.Flags2 & SMBFLG2_UNICODE) == 0) {
-				cERROR(1, ("NTLMSSP requires Unicode support"));
+				cERROR(1, "NTLMSSP requires Unicode support");
 				rc = -ENOSYS;
 				goto ssetup_exit;
 			}
 
-			cFYI(1, ("ntlmssp session setup phase %d", phase));
+			cFYI(1, "ntlmssp session setup phase %d", phase);
 			pSMB->req.hdr.Flags2 |= SMBFLG2_EXT_SEC;
 			capabilities |= CAP_EXTENDED_SECURITY;
 			pSMB->req.Capabilities |= cpu_to_le32(capabilities);
@@ -827,7 +834,7 @@
 				   on the response (challenge) */
 				smb_buf->Uid = ses->Suid;
 			} else {
-				cERROR(1, ("invalid phase %d", phase));
+				cERROR(1, "invalid phase %d", phase);
 				rc = -ENOSYS;
 				goto ssetup_exit;
 			}
@@ -839,12 +846,12 @@
 			}
 			unicode_oslm_strings(&bcc_ptr, nls_cp);
 		} else {
-			cERROR(1, ("secType %d not supported!", type));
+			cERROR(1, "secType %d not supported!", type);
 			rc = -ENOSYS;
 			goto ssetup_exit;
 		}
 #else
-		cERROR(1, ("secType %d not supported!", type));
+		cERROR(1, "secType %d not supported!", type);
 		rc = -ENOSYS;
 		goto ssetup_exit;
 #endif
@@ -862,7 +869,7 @@
 			  CIFS_STD_OP /* not long */ | CIFS_LOG_ERROR);
 	/* SMB request buf freed in SendReceive2 */
 
-	cFYI(1, ("ssetup rc from sendrecv2 is %d", rc));
+	cFYI(1, "ssetup rc from sendrecv2 is %d", rc);
 
 	pSMB = (SESSION_SETUP_ANDX *)iov[0].iov_base;
 	smb_buf = (struct smb_hdr *)iov[0].iov_base;
@@ -870,7 +877,7 @@
 	if ((type == RawNTLMSSP) && (smb_buf->Status.CifsError ==
 			cpu_to_le32(NT_STATUS_MORE_PROCESSING_REQUIRED))) {
 		if (phase != NtLmNegotiate) {
-			cERROR(1, ("Unexpected more processing error"));
+			cERROR(1, "Unexpected more processing error");
 			goto ssetup_exit;
 		}
 		/* NTLMSSP Negotiate sent now processing challenge (response) */
@@ -882,14 +889,14 @@
 
 	if ((smb_buf->WordCount != 3) && (smb_buf->WordCount != 4)) {
 		rc = -EIO;
-		cERROR(1, ("bad word count %d", smb_buf->WordCount));
+		cERROR(1, "bad word count %d", smb_buf->WordCount);
 		goto ssetup_exit;
 	}
 	action = le16_to_cpu(pSMB->resp.Action);
 	if (action & GUEST_LOGIN)
-		cFYI(1, ("Guest login")); /* BB mark SesInfo struct? */
+		cFYI(1, "Guest login"); /* BB mark SesInfo struct? */
 	ses->Suid = smb_buf->Uid;   /* UID left in wire format (le) */
-	cFYI(1, ("UID = %d ", ses->Suid));
+	cFYI(1, "UID = %d ", ses->Suid);
 	/* response can have either 3 or 4 word count - Samba sends 3 */
 	/* and lanman response is 3 */
 	bytes_remaining = BCC(smb_buf);
@@ -899,7 +906,7 @@
 		__u16 blob_len;
 		blob_len = le16_to_cpu(pSMB->resp.SecurityBlobLength);
 		if (blob_len > bytes_remaining) {
-			cERROR(1, ("bad security blob length %d", blob_len));
+			cERROR(1, "bad security blob length %d", blob_len);
 			rc = -EINVAL;
 			goto ssetup_exit;
 		}
@@ -933,7 +940,7 @@
 	}
 	kfree(str_area);
 	if (resp_buf_type == CIFS_SMALL_BUFFER) {
-		cFYI(1, ("ssetup freeing small buf %p", iov[0].iov_base));
+		cFYI(1, "ssetup freeing small buf %p", iov[0].iov_base);
 		cifs_small_buf_release(iov[0].iov_base);
 	} else if (resp_buf_type == CIFS_LARGE_BUFFER)
 		cifs_buf_release(iov[0].iov_base);

fs/cifs/transport.c

diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index ad081fe..82f78c4 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -35,7 +35,6 @@
 #include "cifs_debug.h"
 
 extern mempool_t *cifs_mid_poolp;
-extern struct kmem_cache *cifs_oplock_cachep;
 
 static struct mid_q_entry *
 AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
@@ -43,7 +42,7 @@
 	struct mid_q_entry *temp;
 
 	if (server == NULL) {
-		cERROR(1, ("Null TCP session in AllocMidQEntry"));
+		cERROR(1, "Null TCP session in AllocMidQEntry");
 		return NULL;
 	}
 
@@ -55,7 +54,7 @@
 		temp->mid = smb_buffer->Mid;	/* always LE */
 		temp->pid = current->pid;
 		temp->command = smb_buffer->Command;
-		cFYI(1, ("For smb_command %d", temp->command));
+		cFYI(1, "For smb_command %d", temp->command);
 	/*	do_gettimeofday(&temp->when_sent);*/ /* easier to use jiffies */
 		/* when mid allocated can be before when sent */
 		temp->when_alloc = jiffies;
@@ -140,7 +139,7 @@
 		total_len += iov[i].iov_len;
 
 	smb_buffer->smb_buf_length = cpu_to_be32(smb_buffer->smb_buf_length);
-	cFYI(1, ("Sending smb:  total_len %d", total_len));
+	cFYI(1, "Sending smb:  total_len %d", total_len);
 	dump_smb(smb_buffer, len);
 
 	i = 0;
@@ -168,9 +167,8 @@
 			   reconnect which may clear the network problem.
 			*/
 			if ((i >= 14) || (!server->noblocksnd && (i > 2))) {
-				cERROR(1,
-				   ("sends on sock %p stuck for 15 seconds",
-				    ssocket));
+				cERROR(1, "sends on sock %p stuck for 15 seconds",
+				    ssocket);
 				rc = -EAGAIN;
 				break;
 			}
@@ -184,13 +182,13 @@
 			total_len = 0;
 			break;
 		} else if (rc > total_len) {
-			cERROR(1, ("sent %d requested %d", rc, total_len));
+			cERROR(1, "sent %d requested %d", rc, total_len);
 			break;
 		}
 		if (rc == 0) {
 			/* should never happen, letting socket clear before
 			   retrying is our only obvious option here */
-			cERROR(1, ("tcp sent no data"));
+			cERROR(1, "tcp sent no data");
 			msleep(500);
 			continue;
 		}
@@ -213,8 +211,8 @@
 	}
 
 	if ((total_len > 0) && (total_len != smb_buf_length + 4)) {
-		cFYI(1, ("partial send (%d remaining), terminating session",
-			total_len));
+		cFYI(1, "partial send (%d remaining), terminating session",
+			total_len);
 		/* If we have only sent part of an SMB then the next SMB
 		   could be taken as the remainder of this one.  We need
 		   to kill the socket so the server throws away the partial
@@ -223,7 +221,7 @@
 	}
 
 	if (rc < 0) {
-		cERROR(1, ("Error %d sending data on socket to server", rc));
+		cERROR(1, "Error %d sending data on socket to server", rc);
 	} else
 		rc = 0;
 
@@ -296,7 +294,7 @@
 	}
 
 	if (ses->server->tcpStatus == CifsNeedReconnect) {
-		cFYI(1, ("tcp session dead - return to caller to retry"));
+		cFYI(1, "tcp session dead - return to caller to retry");
 		return -EAGAIN;
 	}
 
@@ -348,7 +346,7 @@
 			lrt += time_to_wait;
 			if (time_after(jiffies, lrt)) {
 				/* No replies for time_to_wait. */
-				cERROR(1, ("server not responding"));
+				cERROR(1, "server not responding");
 				return -1;
 			}
 		} else {
@@ -379,7 +377,7 @@
 	iov[0].iov_len = in_buf->smb_buf_length + 4;
 	flags |= CIFS_NO_RESP;
 	rc = SendReceive2(xid, ses, iov, 1, &resp_buf_type, flags);
-	cFYI(DBG2, ("SendRcvNoRsp flags %d rc %d", flags, rc));
+	cFYI(DBG2, "SendRcvNoRsp flags %d rc %d", flags, rc);
 
 	return rc;
 }
@@ -402,7 +400,7 @@
 
 	if ((ses == NULL) || (ses->server == NULL)) {
 		cifs_small_buf_release(in_buf);
-		cERROR(1, ("Null session"));
+		cERROR(1, "Null session");
 		return -EIO;
 	}
 
@@ -471,7 +469,7 @@
 	else if (long_op == CIFS_BLOCKING_OP)
 		timeout = 0x7FFFFFFF; /*  large, but not so large as to wrap */
 	else {
-		cERROR(1, ("unknown timeout flag %d", long_op));
+		cERROR(1, "unknown timeout flag %d", long_op);
 		rc = -EIO;
 		goto out;
 	}
@@ -490,8 +488,8 @@
 	spin_lock(&GlobalMid_Lock);
 
 	if (midQ->resp_buf == NULL) {
-		cERROR(1, ("No response to cmd %d mid %d",
-			midQ->command, midQ->mid));
+		cERROR(1, "No response to cmd %d mid %d",
+			midQ->command, midQ->mid);
 		if (midQ->midState == MID_REQUEST_SUBMITTED) {
 			if (ses->server->tcpStatus == CifsExiting)
 				rc = -EHOSTDOWN;
@@ -504,7 +502,7 @@
 		if (rc != -EHOSTDOWN) {
 			if (midQ->midState == MID_RETRY_NEEDED) {
 				rc = -EAGAIN;
-				cFYI(1, ("marking request for retry"));
+				cFYI(1, "marking request for retry");
 			} else {
 				rc = -EIO;
 			}
@@ -521,8 +519,8 @@
 	receive_len = midQ->resp_buf->smb_buf_length;
 
 	if (receive_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) {
-		cERROR(1, ("Frame too large received.  Length: %d  Xid: %d",
-			receive_len, xid));
+		cERROR(1, "Frame too large received.  Length: %d  Xid: %d",
+			receive_len, xid);
 		rc = -EIO;
 		goto out;
 	}
@@ -548,7 +546,7 @@
 						&ses->server->mac_signing_key,
 						midQ->sequence_number+1);
 			if (rc) {
-				cERROR(1, ("Unexpected SMB signature"));
+				cERROR(1, "Unexpected SMB signature");
 				/* BB FIXME add code to kill session */
 			}
 		}
@@ -569,7 +567,7 @@
 						   DeleteMidQEntry */
 	} else {
 		rc = -EIO;
-		cFYI(1, ("Bad MID state?"));
+		cFYI(1, "Bad MID state?");
 	}
 
 out:
@@ -591,11 +589,11 @@
 	struct mid_q_entry *midQ;
 
 	if (ses == NULL) {
-		cERROR(1, ("Null smb session"));
+		cERROR(1, "Null smb session");
 		return -EIO;
 	}
 	if (ses->server == NULL) {
-		cERROR(1, ("Null tcp session"));
+		cERROR(1, "Null tcp session");
 		return -EIO;
 	}
 
@@ -607,8 +605,8 @@
 	   use ses->maxReq */
 
 	if (in_buf->smb_buf_length > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
-		cERROR(1, ("Illegal length, greater than maximum frame, %d",
-			   in_buf->smb_buf_length));
+		cERROR(1, "Illegal length, greater than maximum frame, %d",
+			   in_buf->smb_buf_length);
 		return -EIO;
 	}
 
@@ -665,7 +663,7 @@
 	else if (long_op == CIFS_BLOCKING_OP)
 		timeout = 0x7FFFFFFF; /* large but no so large as to wrap */
 	else {
-		cERROR(1, ("unknown timeout flag %d", long_op));
+		cERROR(1, "unknown timeout flag %d", long_op);
 		rc = -EIO;
 		goto out;
 	}
@@ -681,8 +679,8 @@
 
 	spin_lock(&GlobalMid_Lock);
 	if (midQ->resp_buf == NULL) {
-		cERROR(1, ("No response for cmd %d mid %d",
-			  midQ->command, midQ->mid));
+		cERROR(1, "No response for cmd %d mid %d",
+			  midQ->command, midQ->mid);
 		if (midQ->midState == MID_REQUEST_SUBMITTED) {
 			if (ses->server->tcpStatus == CifsExiting)
 				rc = -EHOSTDOWN;
@@ -695,7 +693,7 @@
 		if (rc != -EHOSTDOWN) {
 			if (midQ->midState == MID_RETRY_NEEDED) {
 				rc = -EAGAIN;
-				cFYI(1, ("marking request for retry"));
+				cFYI(1, "marking request for retry");
 			} else {
 				rc = -EIO;
 			}
@@ -712,8 +710,8 @@
 	receive_len = midQ->resp_buf->smb_buf_length;
 
 	if (receive_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) {
-		cERROR(1, ("Frame too large received.  Length: %d  Xid: %d",
-			receive_len, xid));
+		cERROR(1, "Frame too large received.  Length: %d  Xid: %d",
+			receive_len, xid);
 		rc = -EIO;
 		goto out;
 	}
@@ -736,7 +734,7 @@
 						&ses->server->mac_signing_key,
 						midQ->sequence_number+1);
 			if (rc) {
-				cERROR(1, ("Unexpected SMB signature"));
+				cERROR(1, "Unexpected SMB signature");
 				/* BB FIXME add code to kill session */
 			}
 		}
@@ -753,7 +751,7 @@
 			BCC(out_buf) = le16_to_cpu(BCC_LE(out_buf));
 	} else {
 		rc = -EIO;
-		cERROR(1, ("Bad MID state?"));
+		cERROR(1, "Bad MID state?");
 	}
 
 out:
@@ -824,13 +822,13 @@
 	struct cifsSesInfo *ses;
 
 	if (tcon == NULL || tcon->ses == NULL) {
-		cERROR(1, ("Null smb session"));
+		cERROR(1, "Null smb session");
 		return -EIO;
 	}
 	ses = tcon->ses;
 
 	if (ses->server == NULL) {
-		cERROR(1, ("Null tcp session"));
+		cERROR(1, "Null tcp session");
 		return -EIO;
 	}
 
@@ -842,8 +840,8 @@
 	   use ses->maxReq */
 
 	if (in_buf->smb_buf_length > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
-		cERROR(1, ("Illegal length, greater than maximum frame, %d",
-			   in_buf->smb_buf_length));
+		cERROR(1, "Illegal length, greater than maximum frame, %d",
+			   in_buf->smb_buf_length);
 		return -EIO;
 	}
 
@@ -933,8 +931,8 @@
 		spin_unlock(&GlobalMid_Lock);
 		receive_len = midQ->resp_buf->smb_buf_length;
 	} else {
-		cERROR(1, ("No response for cmd %d mid %d",
-			  midQ->command, midQ->mid));
+		cERROR(1, "No response for cmd %d mid %d",
+			  midQ->command, midQ->mid);
 		if (midQ->midState == MID_REQUEST_SUBMITTED) {
 			if (ses->server->tcpStatus == CifsExiting)
 				rc = -EHOSTDOWN;
@@ -947,7 +945,7 @@
 		if (rc != -EHOSTDOWN) {
 			if (midQ->midState == MID_RETRY_NEEDED) {
 				rc = -EAGAIN;
-				cFYI(1, ("marking request for retry"));
+				cFYI(1, "marking request for retry");
 			} else {
 				rc = -EIO;
 			}
@@ -958,8 +956,8 @@
 	}
 
 	if (receive_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) {
-		cERROR(1, ("Frame too large received.  Length: %d  Xid: %d",
-			receive_len, xid));
+		cERROR(1, "Frame too large received.  Length: %d  Xid: %d",
+			receive_len, xid);
 		rc = -EIO;
 		goto out;
 	}
@@ -968,7 +966,7 @@
 
 	if ((out_buf == NULL) || (midQ->midState != MID_RESPONSE_RECEIVED)) {
 		rc = -EIO;
-		cERROR(1, ("Bad MID state?"));
+		cERROR(1, "Bad MID state?");
 		goto out;
 	}
 
@@ -986,7 +984,7 @@
 					   &ses->server->mac_signing_key,
 					   midQ->sequence_number+1);
 		if (rc) {
-			cERROR(1, ("Unexpected SMB signature"));
+			cERROR(1, "Unexpected SMB signature");
 			/* BB FIXME add code to kill session */
 		}
 	}

fs/cifs/xattr.c

diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index f555ce0..a150920 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -70,12 +70,12 @@
 		return rc;
 	}
 	if (ea_name == NULL) {
-		cFYI(1, ("Null xattr names not supported"));
+		cFYI(1, "Null xattr names not supported");
 	} else if (strncmp(ea_name, CIFS_XATTR_USER_PREFIX, 5)
 		&& (strncmp(ea_name, CIFS_XATTR_OS2_PREFIX, 4))) {
 		cFYI(1,
-		    ("illegal xattr request %s (only user namespace supported)",
-			ea_name));
+		     "illegal xattr request %s (only user namespace supported)",
+		     ea_name);
 		/* BB what if no namespace prefix? */
 		/* Should we just pass them to server, except for
 		system and perhaps security prefixes? */
@@ -131,19 +131,19 @@
 		search server for EAs or streams to
 		returns as xattrs */
 	if (value_size > MAX_EA_VALUE_SIZE) {
-		cFYI(1, ("size of EA value too large"));
+		cFYI(1, "size of EA value too large");
 		kfree(full_path);
 		FreeXid(xid);
 		return -EOPNOTSUPP;
 	}
 
 	if (ea_name == NULL) {
-		cFYI(1, ("Null xattr names not supported"));
+		cFYI(1, "Null xattr names not supported");
 	} else if (strncmp(ea_name, CIFS_XATTR_USER_PREFIX, 5) == 0) {
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
 			goto set_ea_exit;
 		if (strncmp(ea_name, CIFS_XATTR_DOS_ATTRIB, 14) == 0)
-			cFYI(1, ("attempt to set cifs inode metadata"));
+			cFYI(1, "attempt to set cifs inode metadata");
 
 		ea_name += 5; /* skip past user. prefix */
 		rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, ea_value,
@@ -169,9 +169,9 @@
 					ACL_TYPE_ACCESS, cifs_sb->local_nls,
 					cifs_sb->mnt_cifs_flags &
 						CIFS_MOUNT_MAP_SPECIAL_CHR);
-			cFYI(1, ("set POSIX ACL rc %d", rc));
+			cFYI(1, "set POSIX ACL rc %d", rc);
 #else
-			cFYI(1, ("set POSIX ACL not supported"));
+			cFYI(1, "set POSIX ACL not supported");
 #endif
 		} else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT,
 				   strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) {
@@ -182,13 +182,13 @@
 					ACL_TYPE_DEFAULT, cifs_sb->local_nls,
 					cifs_sb->mnt_cifs_flags &
 						CIFS_MOUNT_MAP_SPECIAL_CHR);
-			cFYI(1, ("set POSIX default ACL rc %d", rc));
+			cFYI(1, "set POSIX default ACL rc %d", rc);
 #else
-			cFYI(1, ("set default POSIX ACL not supported"));
+			cFYI(1, "set default POSIX ACL not supported");
 #endif
 		} else {
-			cFYI(1, ("illegal xattr request %s (only user namespace"
-				 " supported)", ea_name));
+			cFYI(1, "illegal xattr request %s (only user namespace"
+				" supported)", ea_name);
 		  /* BB what if no namespace prefix? */
 		  /* Should we just pass them to server, except for
 		  system and perhaps security prefixes? */
@@ -235,13 +235,13 @@
 	/* return dos attributes as pseudo xattr */
 	/* return alt name if available as pseudo attr */
 	if (ea_name == NULL) {
-		cFYI(1, ("Null xattr names not supported"));
+		cFYI(1, "Null xattr names not supported");
 	} else if (strncmp(ea_name, CIFS_XATTR_USER_PREFIX, 5) == 0) {
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
 			goto get_ea_exit;
 
 		if (strncmp(ea_name, CIFS_XATTR_DOS_ATTRIB, 14) == 0) {
-			cFYI(1, ("attempt to query cifs inode metadata"));
+			cFYI(1, "attempt to query cifs inode metadata");
 			/* revalidate/getattr then populate from inode */
 		} /* BB add else when above is implemented */
 		ea_name += 5; /* skip past user. prefix */
@@ -287,7 +287,7 @@
 		}
 #endif /* EXPERIMENTAL */
 #else
-		cFYI(1, ("query POSIX ACL not supported yet"));
+		cFYI(1, "query POSIX ACL not supported yet");
 #endif /* CONFIG_CIFS_POSIX */
 	} else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT,
 			  strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) {
@@ -299,18 +299,18 @@
 				cifs_sb->mnt_cifs_flags &
 					CIFS_MOUNT_MAP_SPECIAL_CHR);
 #else
-		cFYI(1, ("query POSIX default ACL not supported yet"));
+		cFYI(1, "query POSIX default ACL not supported yet");
 #endif
 	} else if (strncmp(ea_name,
 		  CIFS_XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) == 0) {
-		cFYI(1, ("Trusted xattr namespace not supported yet"));
+		cFYI(1, "Trusted xattr namespace not supported yet");
 	} else if (strncmp(ea_name,
 		  CIFS_XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) == 0) {
-		cFYI(1, ("Security xattr namespace not supported yet"));
+		cFYI(1, "Security xattr namespace not supported yet");
 	} else
 		cFYI(1,
-		    ("illegal xattr request %s (only user namespace supported)",
-			ea_name));
+		    "illegal xattr request %s (only user namespace supported)",
+		     ea_name);
 
 	/* We could add an additional check for streams ie
 	    if proc/fs/cifs/streamstoxattr is set then

fs/compat.c

diff --git a/fs/compat.c b/fs/compat.c
index 4b6ed03..0544873 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1531,8 +1531,6 @@
 	if (retval < 0)
 		goto out;
 
-	current->stack_start = current->mm->start_stack;
-
 	/* execve succeeded */
 	current->fs->in_exec = 0;
 	current->in_execve = 0;

fs/configfs/dir.c

diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 8e48b52..0b502f8 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -645,6 +645,7 @@
 
 		configfs_detach_group(sd->s_element);
 		child->d_inode->i_flags |= S_DEAD;
+		dont_mount(child);
 
 		mutex_unlock(&child->d_inode->i_mutex);
 
@@ -840,6 +841,7 @@
 			mutex_lock(&dentry->d_inode->i_mutex);
 			configfs_remove_dir(item);
 			dentry->d_inode->i_flags |= S_DEAD;
+			dont_mount(dentry);
 			mutex_unlock(&dentry->d_inode->i_mutex);
 			d_delete(dentry);
 		}
@@ -882,6 +884,7 @@
 		if (ret) {
 			configfs_detach_item(item);
 			dentry->d_inode->i_flags |= S_DEAD;
+			dont_mount(dentry);
 		}
 		configfs_adjust_dir_dirent_depth_after_populate(sd);
 		mutex_unlock(&dentry->d_inode->i_mutex);
@@ -1725,6 +1728,7 @@
 	mutex_unlock(&configfs_symlink_mutex);
 	configfs_detach_group(&group->cg_item);
 	dentry->d_inode->i_flags |= S_DEAD;
+	dont_mount(dentry);
 	mutex_unlock(&dentry->d_inode->i_mutex);
 
 	d_delete(dentry);

fs/exec.c

diff --git a/fs/exec.c b/fs/exec.c
index 49cdaa1..e6e94c6 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1387,8 +1387,6 @@
 	if (retval < 0)
 		goto out;
 
-	current->stack_start = current->mm->start_stack;
-
 	/* execve succeeded */
 	current->fs->in_exec = 0;
 	current->in_execve = 0;

fs/jfs/super.c

diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 157382f..b66832a 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -446,10 +446,8 @@
 	/* initialize the mount flag and determine the default error handler */
 	flag = JFS_ERR_REMOUNT_RO;
 
-	if (!parse_options((char *) data, sb, &newLVSize, &flag)) {
-		kfree(sbi);
-		return -EINVAL;
-	}
+	if (!parse_options((char *) data, sb, &newLVSize, &flag))
+		goto out_kfree;
 	sbi->flag = flag;
 
 #ifdef CONFIG_JFS_POSIX_ACL
@@ -458,7 +456,7 @@
 
 	if (newLVSize) {
 		printk(KERN_ERR "resize option for remount only\n");
-		return -EINVAL;
+		goto out_kfree;
 	}
 
 	/*
@@ -478,7 +476,7 @@
 	inode = new_inode(sb);
 	if (inode == NULL) {
 		ret = -ENOMEM;
-		goto out_kfree;
+		goto out_unload;
 	}
 	inode->i_ino = 0;
 	inode->i_nlink = 1;
@@ -550,9 +548,10 @@
 	make_bad_inode(sbi->direct_inode);
 	iput(sbi->direct_inode);
 	sbi->direct_inode = NULL;
-out_kfree:
+out_unload:
 	if (sbi->nls_tab)
 		unload_nls(sbi->nls_tab);
+out_kfree:
 	kfree(sbi);
 	return ret;
 }

fs/logfs/dev_bdev.c

diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index 243c000..9bd2ce2 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -303,6 +303,11 @@
 	close_bdev_exclusive(logfs_super(sb)->s_bdev, FMODE_READ|FMODE_WRITE);
 }
 
+static int bdev_can_write_buf(struct super_block *sb, u64 ofs)
+{
+	return 0;
+}
+
 static const struct logfs_device_ops bd_devops = {
 	.find_first_sb	= bdev_find_first_sb,
 	.find_last_sb	= bdev_find_last_sb,
@@ -310,6 +315,7 @@
 	.readpage	= bdev_readpage,
 	.writeseg	= bdev_writeseg,
 	.erase		= bdev_erase,
+	.can_write_buf	= bdev_can_write_buf,
 	.sync		= bdev_sync,
 	.put_device	= bdev_put_device,
 };

fs/logfs/dev_mtd.c

diff --git a/fs/logfs/dev_mtd.c b/fs/logfs/dev_mtd.c
index cafb6ef..a85d47d 100644
--- a/fs/logfs/dev_mtd.c
+++ b/fs/logfs/dev_mtd.c
@@ -9,6 +9,7 @@
 #include <linux/completion.h>
 #include <linux/mount.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 #define PAGE_OFS(ofs) ((ofs) & (PAGE_SIZE-1))
 
@@ -126,7 +127,8 @@
 
 	err = mtd_read(sb, page->index << PAGE_SHIFT, PAGE_SIZE,
 			page_address(page));
-	if (err == -EUCLEAN) {
+	if (err == -EUCLEAN || err == -EBADMSG) {
+		/* -EBADMSG happens regularly on power failures */
 		err = 0;
 		/* FIXME: force GC this segment */
 	}
@@ -233,12 +235,32 @@
 	put_mtd_device(logfs_super(sb)->s_mtd);
 }
 
+static int mtd_can_write_buf(struct super_block *sb, u64 ofs)
+{
+	struct logfs_super *super = logfs_super(sb);
+	void *buf;
+	int err;
+
+	buf = kmalloc(super->s_writesize, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	err = mtd_read(sb, ofs, super->s_writesize, buf);
+	if (err)
+		goto out;
+	if (memchr_inv(buf, 0xff, super->s_writesize))
+		err = -EIO;
+	kfree(buf);
+out:
+	return err;
+}
+
 static const struct logfs_device_ops mtd_devops = {
 	.find_first_sb	= mtd_find_first_sb,
 	.find_last_sb	= mtd_find_last_sb,
 	.readpage	= mtd_readpage,
 	.writeseg	= mtd_writeseg,
 	.erase		= mtd_erase,
+	.can_write_buf	= mtd_can_write_buf,
 	.sync		= mtd_sync,
 	.put_device	= mtd_put_device,
 };
@@ -250,5 +272,7 @@
 	const struct logfs_device_ops *devops = &mtd_devops;
 
 	mtd = get_mtd_device(NULL, mtdnr);
+	if (IS_ERR(mtd))
+		return PTR_ERR(mtd);
 	return logfs_get_sb_device(type, flags, mtd, NULL, devops, mnt);
 }

fs/logfs/file.c

diff --git a/fs/logfs/file.c b/fs/logfs/file.c
index 370f367..0de5240 100644
--- a/fs/logfs/file.c
+++ b/fs/logfs/file.c
@@ -161,7 +161,17 @@
 
 static void logfs_invalidatepage(struct page *page, unsigned long offset)
 {
-	move_page_to_btree(page);
+	struct logfs_block *block = logfs_block(page);
+
+	if (block->reserved_bytes) {
+		struct super_block *sb = page->mapping->host->i_sb;
+		struct logfs_super *super = logfs_super(sb);
+
+		super->s_dirty_pages -= block->reserved_bytes;
+		block->ops->free_block(sb, block);
+		BUG_ON(bitmap_weight(block->alias_map, LOGFS_BLOCK_FACTOR));
+	} else
+		move_page_to_btree(page);
 	BUG_ON(PagePrivate(page) || page->private);
 }
 
@@ -212,10 +222,8 @@
 int logfs_fsync(struct file *file, struct dentry *dentry, int datasync)
 {
 	struct super_block *sb = dentry->d_inode->i_sb;
-	struct logfs_super *super = logfs_super(sb);
 
-	/* FIXME: write anchor */
-	super->s_devops->sync(sb);
+	logfs_write_anchor(sb);
 	return 0;
 }
 

fs/logfs/gc.c

diff --git a/fs/logfs/gc.c b/fs/logfs/gc.c
index 76c242f..caa4419 100644
--- a/fs/logfs/gc.c
+++ b/fs/logfs/gc.c
@@ -122,7 +122,7 @@
 	logfs_safe_iput(inode, cookie);
 }
 
-static u32 logfs_gc_segment(struct super_block *sb, u32 segno, u8 dist)
+static u32 logfs_gc_segment(struct super_block *sb, u32 segno)
 {
 	struct logfs_super *super = logfs_super(sb);
 	struct logfs_segment_header sh;
@@ -401,7 +401,7 @@
 			segno, (u64)segno << super->s_segshift,
 			dist, no_free_segments(sb), valid,
 			super->s_free_bytes);
-	cleaned = logfs_gc_segment(sb, segno, dist);
+	cleaned = logfs_gc_segment(sb, segno);
 	log_gc("GC segment #%02x complete - now %x valid\n", segno,
 			valid - cleaned);
 	BUG_ON(cleaned != valid);
@@ -632,38 +632,31 @@
 {
 	struct logfs_super *super = logfs_super(sb);
 	struct logfs_area *area = super->s_area[i];
-	struct logfs_object_header oh;
+	gc_level_t gc_level;
+	u32 cleaned, valid, ec;
 	u32 segno = area->a_segno;
-	u32 ofs = area->a_used_bytes;
-	__be32 crc;
-	int err;
+	u64 ofs = dev_ofs(sb, area->a_segno, area->a_written_bytes);
 
 	if (!area->a_is_open)
 		return 0;
 
-	for (ofs = area->a_used_bytes;
-	     ofs <= super->s_segsize - sizeof(oh);
-	     ofs += (u32)be16_to_cpu(oh.len) + sizeof(oh)) {
-		err = wbuf_read(sb, dev_ofs(sb, segno, ofs), sizeof(oh), &oh);
-		if (err)
-			return err;
+	if (super->s_devops->can_write_buf(sb, ofs) == 0)
+		return 0;
 
-		if (!memchr_inv(&oh, 0xff, sizeof(oh)))
-			break;
-
-		crc = logfs_crc32(&oh, sizeof(oh) - 4, 4);
-		if (crc != oh.crc) {
-			printk(KERN_INFO "interrupted header at %llx\n",
-					dev_ofs(sb, segno, ofs));
-			return 0;
-		}
-	}
-	if (ofs != area->a_used_bytes) {
-		printk(KERN_INFO "%x bytes unaccounted data found at %llx\n",
-				ofs - area->a_used_bytes,
-				dev_ofs(sb, segno, area->a_used_bytes));
-		area->a_used_bytes = ofs;
-	}
+	printk(KERN_INFO"LogFS: Possibly incomplete write at %llx\n", ofs);
+	/*
+	 * The device cannot write back the write buffer.  Most likely the
+	 * wbuf was already written out and the system crashed at some point
+	 * before the journal commit happened.  In that case we wouldn't have
+	 * to do anything.  But if the crash happened before the wbuf was
+	 * written out correctly, we must GC this segment.  So assume the
+	 * worst and always do the GC run.
+	 */
+	area->a_is_open = 0;
+	valid = logfs_valid_bytes(sb, segno, &ec, &gc_level);
+	cleaned = logfs_gc_segment(sb, segno);
+	if (cleaned != valid)
+		return -EIO;
 	return 0;
 }
 

fs/logfs/inode.c

diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c
index 14ed272..755a92e 100644
--- a/fs/logfs/inode.c
+++ b/fs/logfs/inode.c
@@ -193,6 +193,7 @@
 	inode->i_ctime	= CURRENT_TIME;
 	inode->i_mtime	= CURRENT_TIME;
 	inode->i_nlink	= 1;
+	li->li_refcount = 1;
 	INIT_LIST_HEAD(&li->li_freeing_list);
 
 	for (i = 0; i < LOGFS_EMBEDDED_FIELDS; i++)
@@ -326,7 +327,7 @@
 	u64 ino;
 
 	mutex_lock(&super->s_journal_mutex);
-	ino = logfs_seek_hole(super->s_master_inode, super->s_last_ino);
+	ino = logfs_seek_hole(super->s_master_inode, super->s_last_ino + 1);
 	super->s_last_ino = ino;
 	super->s_inos_till_wrap--;
 	if (super->s_inos_till_wrap < 0) {
@@ -386,8 +387,7 @@
 
 static int logfs_sync_fs(struct super_block *sb, int wait)
 {
-	/* FIXME: write anchor */
-	logfs_super(sb)->s_devops->sync(sb);
+	logfs_write_anchor(sb);
 	return 0;
 }
 

fs/logfs/journal.c

diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c
index fb0a613..4b0e061 100644
--- a/fs/logfs/journal.c
+++ b/fs/logfs/journal.c
@@ -132,10 +132,9 @@
 
 	ofs = dev_ofs(sb, area->a_segno, area->a_written_bytes);
 	if (super->s_writesize > 1)
-		logfs_buf_recover(area, ofs, a + 1, super->s_writesize);
+		return logfs_buf_recover(area, ofs, a + 1, super->s_writesize);
 	else
-		logfs_buf_recover(area, ofs, NULL, 0);
-	return 0;
+		return logfs_buf_recover(area, ofs, NULL, 0);
 }
 
 static void *unpack(void *from, void *to)
@@ -245,7 +244,7 @@
 		read_erasecount(sb, unpack(jh, scratch));
 		break;
 	case JE_AREA:
-		read_area(sb, unpack(jh, scratch));
+		err = read_area(sb, unpack(jh, scratch));
 		break;
 	case JE_OBJ_ALIAS:
 		err = logfs_load_object_aliases(sb, unpack(jh, scratch),

fs/logfs/logfs.h

diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h
index 0a3df1a..93b55f3 100644
--- a/fs/logfs/logfs.h
+++ b/fs/logfs/logfs.h
@@ -144,6 +144,7 @@
  * @erase:			erase one segment
  * @read:			read from the device
  * @erase:			erase part of the device
+ * @can_write_buf:		decide whether wbuf can be written to ofs
  */
 struct logfs_device_ops {
 	struct page *(*find_first_sb)(struct super_block *sb, u64 *ofs);
@@ -153,6 +154,7 @@
 	void (*writeseg)(struct super_block *sb, u64 ofs, size_t len);
 	int (*erase)(struct super_block *sb, loff_t ofs, size_t len,
 			int ensure_write);
+	int (*can_write_buf)(struct super_block *sb, u64 ofs);
 	void (*sync)(struct super_block *sb);
 	void (*put_device)(struct super_block *sb);
 };
@@ -394,6 +396,7 @@
 	int	 s_lock_count;
 	mempool_t *s_block_pool;		/* struct logfs_block pool */
 	mempool_t *s_shadow_pool;		/* struct logfs_shadow pool */
+	struct list_head s_writeback_list;	/* writeback pages */
 	/*
 	 * Space accounting:
 	 * - s_used_bytes specifies space used to store valid data objects.
@@ -598,19 +601,19 @@
 int logfs_init_areas(struct super_block *sb);
 void logfs_cleanup_areas(struct super_block *sb);
 int logfs_open_area(struct logfs_area *area, size_t bytes);
-void __logfs_buf_write(struct logfs_area *area, u64 ofs, void *buf, size_t len,
+int __logfs_buf_write(struct logfs_area *area, u64 ofs, void *buf, size_t len,
 		int use_filler);
 
-static inline void logfs_buf_write(struct logfs_area *area, u64 ofs,
+static inline int logfs_buf_write(struct logfs_area *area, u64 ofs,
 		void *buf, size_t len)
 {
-	__logfs_buf_write(area, ofs, buf, len, 0);
+	return __logfs_buf_write(area, ofs, buf, len, 0);
 }
 
-static inline void logfs_buf_recover(struct logfs_area *area, u64 ofs,
+static inline int logfs_buf_recover(struct logfs_area *area, u64 ofs,
 		void *buf, size_t len)
 {
-	__logfs_buf_write(area, ofs, buf, len, 1);
+	return __logfs_buf_write(area, ofs, buf, len, 1);
 }
 
 /* super.c */

fs/logfs/readwrite.c

diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 3159db6..0718d11 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -892,6 +892,8 @@
 		return bix;
 	else if (li->li_data[INDIRECT_INDEX] & LOGFS_FULLY_POPULATED)
 		bix = maxbix(li->li_height);
+	else if (bix >= maxbix(li->li_height))
+		return bix;
 	else {
 		bix = seek_holedata_loop(inode, bix, 0);
 		if (bix < maxbix(li->li_height))
@@ -1093,17 +1095,25 @@
 int get_page_reserve(struct inode *inode, struct page *page)
 {
 	struct logfs_super *super = logfs_super(inode->i_sb);
+	struct logfs_block *block = logfs_block(page);
 	int ret;
 
-	if (logfs_block(page) && logfs_block(page)->reserved_bytes)
+	if (block && block->reserved_bytes)
 		return 0;
 
 	logfs_get_wblocks(inode->i_sb, page, WF_LOCK);
-	ret = logfs_reserve_bytes(inode, 6 * LOGFS_MAX_OBJECTSIZE);
+	while ((ret = logfs_reserve_bytes(inode, 6 * LOGFS_MAX_OBJECTSIZE)) &&
+			!list_empty(&super->s_writeback_list)) {
+		block = list_entry(super->s_writeback_list.next,
+				struct logfs_block, alias_list);
+		block->ops->write_block(block);
+	}
 	if (!ret) {
 		alloc_data_block(inode, page);
-		logfs_block(page)->reserved_bytes += 6 * LOGFS_MAX_OBJECTSIZE;
+		block = logfs_block(page);
+		block->reserved_bytes += 6 * LOGFS_MAX_OBJECTSIZE;
 		super->s_dirty_pages += 6 * LOGFS_MAX_OBJECTSIZE;
+		list_move_tail(&block->alias_list, &super->s_writeback_list);
 	}
 	logfs_put_wblocks(inode->i_sb, page, WF_LOCK);
 	return ret;
@@ -1861,7 +1871,7 @@
 			size = target;
 
 		logfs_get_wblocks(sb, NULL, 1);
-		err = __logfs_truncate(inode, target);
+		err = __logfs_truncate(inode, size);
 		if (!err)
 			err = __logfs_write_inode(inode, 0);
 		logfs_put_wblocks(sb, NULL, 1);
@@ -2249,6 +2259,7 @@
 	int min_fill = 3 * super->s_no_blocks;
 
 	INIT_LIST_HEAD(&super->s_object_alias);
+	INIT_LIST_HEAD(&super->s_writeback_list);
 	mutex_init(&super->s_write_mutex);
 	super->s_block_pool = mempool_create_kmalloc_pool(min_fill,
 			sizeof(struct logfs_block));

fs/logfs/segment.c

diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c
index f77ce2b..a9657af 100644
--- a/fs/logfs/segment.c
+++ b/fs/logfs/segment.c
@@ -67,7 +67,7 @@
 	return page;
 }
 
-void __logfs_buf_write(struct logfs_area *area, u64 ofs, void *buf, size_t len,
+int __logfs_buf_write(struct logfs_area *area, u64 ofs, void *buf, size_t len,
 		int use_filler)
 {
 	pgoff_t index = ofs >> PAGE_SHIFT;
@@ -81,8 +81,10 @@
 		copylen = min((ulong)len, PAGE_SIZE - offset);
 
 		page = get_mapping_page(area->a_sb, index, use_filler);
-		SetPageUptodate(page);
+		if (IS_ERR(page))
+			return PTR_ERR(page);
 		BUG_ON(!page); /* FIXME: reserve a pool */
+		SetPageUptodate(page);
 		memcpy(page_address(page) + offset, buf, copylen);
 		SetPagePrivate(page);
 		page_cache_release(page);
@@ -92,6 +94,7 @@
 		offset = 0;
 		index++;
 	} while (len);
+	return 0;
 }
 
 static void pad_partial_page(struct logfs_area *area)

fs/logfs/super.c

diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index 5866ee6..d651e10 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -138,10 +138,14 @@
 	sb->s_fs_info = super;
 	sb->s_mtd = super->s_mtd;
 	sb->s_bdev = super->s_bdev;
+#ifdef CONFIG_BLOCK
 	if (sb->s_bdev)
 		sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info;
+#endif
+#ifdef CONFIG_MTD
 	if (sb->s_mtd)
 		sb->s_bdi = sb->s_mtd->backing_dev_info;
+#endif
 	return 0;
 }
 
@@ -333,27 +337,27 @@
 		goto fail;
 
 	sb->s_root = d_alloc_root(rootdir);
-	if (!sb->s_root)
-		goto fail2;
+	if (!sb->s_root) {
+		iput(rootdir);
+		goto fail;
+	}
 
 	super->s_erase_page = alloc_pages(GFP_KERNEL, 0);
 	if (!super->s_erase_page)
-		goto fail2;
+		goto fail;
 	memset(page_address(super->s_erase_page), 0xFF, PAGE_SIZE);
 
 	/* FIXME: check for read-only mounts */
 	err = logfs_make_writeable(sb);
 	if (err)
-		goto fail3;
+		goto fail1;
 
 	log_super("LogFS: Finished mounting\n");
 	simple_set_mnt(mnt, sb);
 	return 0;
 
-fail3:
+fail1:
 	__free_page(super->s_erase_page);
-fail2:
-	iput(rootdir);
 fail:
 	iput(logfs_super(sb)->s_master_inode);
 	return -EIO;
@@ -382,7 +386,7 @@
 	if (!first || IS_ERR(first))
 		return NULL;
 	last = super->s_devops->find_last_sb(sb, &super->s_sb_ofs[1]);
-	if (!last || IS_ERR(first)) {
+	if (!last || IS_ERR(last)) {
 		page_cache_release(first);
 		return NULL;
 	}
@@ -413,7 +417,7 @@
 
 	page = find_super_block(sb);
 	if (!page)
-		return -EIO;
+		return -EINVAL;
 
 	ds = page_address(page);
 	super->s_size = be64_to_cpu(ds->ds_filesystem_size);

fs/namei.c

diff --git a/fs/namei.c b/fs/namei.c
index a7dce91..b86b96f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1641,7 +1641,7 @@
 	if (nd->last.name[nd->last.len]) {
 		if (open_flag & O_CREAT)
 			goto exit;
-		nd->flags |= LOOKUP_DIRECTORY;
+		nd->flags |= LOOKUP_DIRECTORY | LOOKUP_FOLLOW;
 	}
 
 	/* just plain open? */
@@ -1830,6 +1830,8 @@
 	}
 	if (open_flag & O_DIRECTORY)
 		nd.flags |= LOOKUP_DIRECTORY;
+	if (!(open_flag & O_NOFOLLOW))
+		nd.flags |= LOOKUP_FOLLOW;
 	filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
 	while (unlikely(!filp)) { /* trailing symlink */
 		struct path holder;
@@ -1837,7 +1839,7 @@
 		void *cookie;
 		error = -ELOOP;
 		/* S_ISDIR part is a temporary automount kludge */
-		if ((open_flag & O_NOFOLLOW) && !S_ISDIR(inode->i_mode))
+		if (!(nd.flags & LOOKUP_FOLLOW) && !S_ISDIR(inode->i_mode))
 			goto exit_dput;
 		if (count++ == 32)
 			goto exit_dput;
@@ -2174,8 +2176,10 @@
 		error = security_inode_rmdir(dir, dentry);
 		if (!error) {
 			error = dir->i_op->rmdir(dir, dentry);
-			if (!error)
+			if (!error) {
 				dentry->d_inode->i_flags |= S_DEAD;
+				dont_mount(dentry);
+			}
 		}
 	}
 	mutex_unlock(&dentry->d_inode->i_mutex);
@@ -2259,7 +2263,7 @@
 		if (!error) {
 			error = dir->i_op->unlink(dir, dentry);
 			if (!error)
-				dentry->d_inode->i_flags |= S_DEAD;
+				dont_mount(dentry);
 		}
 	}
 	mutex_unlock(&dentry->d_inode->i_mutex);
@@ -2570,17 +2574,20 @@
 		return error;
 
 	target = new_dentry->d_inode;
-	if (target) {
+	if (target)
 		mutex_lock(&target->i_mutex);
-		dentry_unhash(new_dentry);
-	}
 	if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
 		error = -EBUSY;
-	else 
+	else {
+		if (target)
+			dentry_unhash(new_dentry);
 		error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
+	}
 	if (target) {
-		if (!error)
+		if (!error) {
 			target->i_flags |= S_DEAD;
+			dont_mount(new_dentry);
+		}
 		mutex_unlock(&target->i_mutex);
 		if (d_unhashed(new_dentry))
 			d_rehash(new_dentry);
@@ -2612,7 +2619,7 @@
 		error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
 	if (!error) {
 		if (target)
-			target->i_flags |= S_DEAD;
+			dont_mount(new_dentry);
 		if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
 			d_move(old_dentry, new_dentry);
 	}

fs/namespace.c

diff --git a/fs/namespace.c b/fs/namespace.c
index 8174c8a..f20cb57 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1432,7 +1432,7 @@
 
 	err = -ENOENT;
 	mutex_lock(&path->dentry->d_inode->i_mutex);
-	if (IS_DEADDIR(path->dentry->d_inode))
+	if (cant_mount(path->dentry))
 		goto out_unlock;
 
 	err = security_sb_check_sb(mnt, path);
@@ -1623,7 +1623,7 @@
 
 	err = -ENOENT;
 	mutex_lock(&path->dentry->d_inode->i_mutex);
-	if (IS_DEADDIR(path->dentry->d_inode))
+	if (cant_mount(path->dentry))
 		goto out1;
 
 	if (d_unlinked(path->dentry))
@@ -2234,7 +2234,7 @@
 	if (!check_mnt(root.mnt))
 		goto out2;
 	error = -ENOENT;
-	if (IS_DEADDIR(new.dentry->d_inode))
+	if (cant_mount(old.dentry))
 		goto out2;
 	if (d_unlinked(new.dentry))
 		goto out2;

fs/nfs/delegation.c

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 1567124..ea61d26 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -24,6 +24,8 @@
 
 static void nfs_do_free_delegation(struct nfs_delegation *delegation)
 {
+	if (delegation->cred)
+		put_rpccred(delegation->cred);
 	kfree(delegation);
 }
 
@@ -36,13 +38,7 @@
 
 static void nfs_free_delegation(struct nfs_delegation *delegation)
 {
-	struct rpc_cred *cred;
-
-	cred = rcu_dereference(delegation->cred);
-	rcu_assign_pointer(delegation->cred, NULL);
 	call_rcu(&delegation->rcu, nfs_free_delegation_callback);
-	if (cred)
-		put_rpccred(cred);
 }
 
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation)
@@ -129,21 +125,35 @@
  */
 void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res)
 {
-	struct nfs_delegation *delegation = NFS_I(inode)->delegation;
-	struct rpc_cred *oldcred;
+	struct nfs_delegation *delegation;
+	struct rpc_cred *oldcred = NULL;
 
-	if (delegation == NULL)
-		return;
-	memcpy(delegation->stateid.data, res->delegation.data,
-			sizeof(delegation->stateid.data));
-	delegation->type = res->delegation_type;
-	delegation->maxsize = res->maxsize;
-	oldcred = delegation->cred;
-	delegation->cred = get_rpccred(cred);
-	clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
-	NFS_I(inode)->delegation_state = delegation->type;
-	smp_wmb();
-	put_rpccred(oldcred);
+	rcu_read_lock();
+	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (delegation != NULL) {
+		spin_lock(&delegation->lock);
+		if (delegation->inode != NULL) {
+			memcpy(delegation->stateid.data, res->delegation.data,
+			       sizeof(delegation->stateid.data));
+			delegation->type = res->delegation_type;
+			delegation->maxsize = res->maxsize;
+			oldcred = delegation->cred;
+			delegation->cred = get_rpccred(cred);
+			clear_bit(NFS_DELEGATION_NEED_RECLAIM,
+				  &delegation->flags);
+			NFS_I(inode)->delegation_state = delegation->type;
+			spin_unlock(&delegation->lock);
+			put_rpccred(oldcred);
+			rcu_read_unlock();
+		} else {
+			/* We appear to have raced with a delegation return. */
+			spin_unlock(&delegation->lock);
+			rcu_read_unlock();
+			nfs_inode_set_delegation(inode, cred, res);
+		}
+	} else {
+		rcu_read_unlock();
+	}
 }
 
 static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)
@@ -166,9 +176,13 @@
 	return inode;
 }
 
-static struct nfs_delegation *nfs_detach_delegation_locked(struct nfs_inode *nfsi, const nfs4_stateid *stateid)
+static struct nfs_delegation *nfs_detach_delegation_locked(struct nfs_inode *nfsi,
+							   const nfs4_stateid *stateid,
+							   struct nfs_client *clp)
 {
-	struct nfs_delegation *delegation = rcu_dereference(nfsi->delegation);
+	struct nfs_delegation *delegation =
+		rcu_dereference_protected(nfsi->delegation,
+					  lockdep_is_held(&clp->cl_lock));
 
 	if (delegation == NULL)
 		goto nomatch;
@@ -195,7 +209,7 @@
 {
 	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	struct nfs_delegation *delegation;
+	struct nfs_delegation *delegation, *old_delegation;
 	struct nfs_delegation *freeme = NULL;
 	int status = 0;
 
@@ -213,10 +227,12 @@
 	spin_lock_init(&delegation->lock);
 
 	spin_lock(&clp->cl_lock);
-	if (rcu_dereference(nfsi->delegation) != NULL) {
-		if (memcmp(&delegation->stateid, &nfsi->delegation->stateid,
-					sizeof(delegation->stateid)) == 0 &&
-				delegation->type == nfsi->delegation->type) {
+	old_delegation = rcu_dereference_protected(nfsi->delegation,
+						   lockdep_is_held(&clp->cl_lock));
+	if (old_delegation != NULL) {
+		if (memcmp(&delegation->stateid, &old_delegation->stateid,
+					sizeof(old_delegation->stateid)) == 0 &&
+				delegation->type == old_delegation->type) {
 			goto out;
 		}
 		/*
@@ -226,12 +242,12 @@
 		dfprintk(FILE, "%s: server %s handed out "
 				"a duplicate delegation!\n",
 				__func__, clp->cl_hostname);
-		if (delegation->type <= nfsi->delegation->type) {
+		if (delegation->type <= old_delegation->type) {
 			freeme = delegation;
 			delegation = NULL;
 			goto out;
 		}
-		freeme = nfs_detach_delegation_locked(nfsi, NULL);
+		freeme = nfs_detach_delegation_locked(nfsi, NULL, clp);
 	}
 	list_add_rcu(&delegation->super_list, &clp->cl_delegations);
 	nfsi->delegation_state = delegation->type;
@@ -301,7 +317,7 @@
 		if (inode == NULL)
 			continue;
 		spin_lock(&clp->cl_lock);
-		delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL);
+		delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL, clp);
 		spin_unlock(&clp->cl_lock);
 		rcu_read_unlock();
 		if (delegation != NULL) {
@@ -330,9 +346,9 @@
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_delegation *delegation;
 
-	if (rcu_dereference(nfsi->delegation) != NULL) {
+	if (rcu_access_pointer(nfsi->delegation) != NULL) {
 		spin_lock(&clp->cl_lock);
-		delegation = nfs_detach_delegation_locked(nfsi, NULL);
+		delegation = nfs_detach_delegation_locked(nfsi, NULL, clp);
 		spin_unlock(&clp->cl_lock);
 		if (delegation != NULL)
 			nfs_do_return_delegation(inode, delegation, 0);
@@ -346,9 +362,9 @@
 	struct nfs_delegation *delegation;
 	int err = 0;
 
-	if (rcu_dereference(nfsi->delegation) != NULL) {
+	if (rcu_access_pointer(nfsi->delegation) != NULL) {
 		spin_lock(&clp->cl_lock);
-		delegation = nfs_detach_delegation_locked(nfsi, NULL);
+		delegation = nfs_detach_delegation_locked(nfsi, NULL, clp);
 		spin_unlock(&clp->cl_lock);
 		if (delegation != NULL) {
 			nfs_msync_inode(inode);
@@ -526,7 +542,7 @@
 		if (inode == NULL)
 			continue;
 		spin_lock(&clp->cl_lock);
-		delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL);
+		delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL, clp);
 		spin_unlock(&clp->cl_lock);
 		rcu_read_unlock();
 		if (delegation != NULL)

fs/nilfs2/super.c

diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 0cdbc5e..48145f5 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -749,6 +749,7 @@
 	sb->s_export_op = &nilfs_export_ops;
 	sb->s_root = NULL;
 	sb->s_time_gran = 1;
+	sb->s_bdi = nilfs->ns_bdi;
 
 	err = load_nilfs(nilfs, sbi);
 	if (err)

fs/notify/inotify/Kconfig

diff --git a/fs/notify/inotify/Kconfig b/fs/notify/inotify/Kconfig
index 3e56dbf..b3a159b 100644
--- a/fs/notify/inotify/Kconfig
+++ b/fs/notify/inotify/Kconfig
@@ -15,6 +15,7 @@
 
 config INOTIFY_USER
 	bool "Inotify support for userspace"
+	select ANON_INODES
 	select FSNOTIFY
 	default y
 	---help---

fs/notify/inotify/inotify_fsnotify.c

diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 1afb0a1..e27960c 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -28,6 +28,7 @@
 #include <linux/path.h> /* struct path */
 #include <linux/slab.h> /* kmem_* */
 #include <linux/types.h>
+#include <linux/sched.h>
 
 #include "inotify.h"
 
@@ -146,6 +147,7 @@
 	idr_for_each(&group->inotify_data.idr, idr_callback, group);
 	idr_remove_all(&group->inotify_data.idr);
 	idr_destroy(&group->inotify_data.idr);
+	free_uid(group->inotify_data.user);
 }
 
 void inotify_free_event_priv(struct fsnotify_event_private_data *fsn_event_priv)

fs/notify/inotify/inotify_user.c

diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 472cdf2..e46ca68 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -546,21 +546,24 @@
 	if (unlikely(!idr_pre_get(&group->inotify_data.idr, GFP_KERNEL)))
 		goto out_err;
 
+	/* we are putting the mark on the idr, take a reference */
+	fsnotify_get_mark(&tmp_ientry->fsn_entry);
+
 	spin_lock(&group->inotify_data.idr_lock);
 	ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
 				group->inotify_data.last_wd+1,
 				&tmp_ientry->wd);
 	spin_unlock(&group->inotify_data.idr_lock);
 	if (ret) {
+		/* we didn't get on the idr, drop the idr reference */
+		fsnotify_put_mark(&tmp_ientry->fsn_entry);
+
 		/* idr was out of memory allocate and try again */
 		if (ret == -EAGAIN)
 			goto retry;
 		goto out_err;
 	}
 
-	/* we put the mark on the idr, take a reference */
-	fsnotify_get_mark(&tmp_ientry->fsn_entry);
-
 	/* we are on the idr, now get on the inode */
 	ret = fsnotify_add_mark(&tmp_ientry->fsn_entry, group, inode);
 	if (ret) {
@@ -578,16 +581,13 @@
 	/* return the watch descriptor for this new entry */
 	ret = tmp_ientry->wd;
 
-	/* match the ref from fsnotify_init_markentry() */
-	fsnotify_put_mark(&tmp_ientry->fsn_entry);
-
 	/* if this mark added a new event update the group mask */
 	if (mask & ~group->mask)
 		fsnotify_recalc_group_mask(group);
 
 out_err:
-	if (ret < 0)
-		kmem_cache_free(inotify_inode_mark_cachep, tmp_ientry);
+	/* match the ref from fsnotify_init_markentry() */
+	fsnotify_put_mark(&tmp_ientry->fsn_entry);
 
 	return ret;
 }

fs/ocfs2/buffer_head_io.c

diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index ecebb22..f9d5d3f 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -406,6 +406,7 @@
 				struct buffer_head *bh)
 {
 	int ret = 0;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
 
 	mlog_entry_void();
 
@@ -425,6 +426,7 @@
 
 	get_bh(bh); /* for end_buffer_write_sync() */
 	bh->b_end_io = end_buffer_write_sync;
+	ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &di->i_check);
 	submit_bh(WRITE, bh);
 
 	wait_on_buffer(bh);

fs/ocfs2/dlm/dlmast.c

diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index a795eb9..12d5eb7 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -184,9 +184,8 @@
 	BUG_ON(!lksb);
 
 	/* only updates if this node masters the lockres */
+	spin_lock(&res->spinlock);
 	if (res->owner == dlm->node_num) {
-
-		spin_lock(&res->spinlock);
 		/* check the lksb flags for the direction */
 		if (lksb->flags & DLM_LKSB_GET_LVB) {
 			mlog(0, "getting lvb from lockres for %s node\n",
@@ -201,8 +200,8 @@
  		 * here. In the future we might want to clear it at the time
  		 * the put is actually done.
 		 */
-		spin_unlock(&res->spinlock);
 	}
+	spin_unlock(&res->spinlock);
 
 	/* reset any lvb flags on the lksb */
 	lksb->flags &= ~(DLM_LKSB_PUT_LVB|DLM_LKSB_GET_LVB);

fs/ocfs2/dlmfs/dlmfs.c

diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 1b0de15..b83d610 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -112,20 +112,20 @@
  * O_RDONLY -> PRMODE level
  * O_WRONLY -> EXMODE level
  *
- * O_NONBLOCK -> LKM_NOQUEUE
+ * O_NONBLOCK -> NOQUEUE
  */
 static int dlmfs_decode_open_flags(int open_flags,
 				   int *level,
 				   int *flags)
 {
 	if (open_flags & (O_WRONLY|O_RDWR))
-		*level = LKM_EXMODE;
+		*level = DLM_LOCK_EX;
 	else
-		*level = LKM_PRMODE;
+		*level = DLM_LOCK_PR;
 
 	*flags = 0;
 	if (open_flags & O_NONBLOCK)
-		*flags |= LKM_NOQUEUE;
+		*flags |= DLM_LKF_NOQUEUE;
 
 	return 0;
 }
@@ -166,7 +166,7 @@
 		 * to be able userspace to be able to distinguish a
 		 * valid lock request from one that simply couldn't be
 		 * granted. */
-		if (flags & LKM_NOQUEUE && status == -EAGAIN)
+		if (flags & DLM_LKF_NOQUEUE && status == -EAGAIN)
 			status = -ETXTBSY;
 		kfree(fp);
 		goto bail;
@@ -193,7 +193,7 @@
 	status = 0;
 	if (fp) {
 		level = fp->fp_lock_level;
-		if (level != LKM_IVMODE)
+		if (level != DLM_LOCK_IV)
 			user_dlm_cluster_unlock(&ip->ip_lockres, level);
 
 		kfree(fp);
@@ -262,7 +262,7 @@
 	if ((count + *ppos) > i_size_read(inode))
 		readlen = i_size_read(inode) - *ppos;
 	else
-		readlen = count - *ppos;
+		readlen = count;
 
 	lvb_buf = kmalloc(readlen, GFP_NOFS);
 	if (!lvb_buf)

fs/ocfs2/file.c

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 17947dc..a5fbd9c 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -684,6 +684,7 @@
 		if (why == RESTART_META) {
 			mlog(0, "restarting function.\n");
 			restart_func = 1;
+			status = 0;
 		} else {
 			BUG_ON(why != RESTART_TRANS);
 
@@ -1981,18 +1982,18 @@
 	/* communicate with ocfs2_dio_end_io */
 	ocfs2_iocb_set_rw_locked(iocb, rw_level);
 
+	ret = generic_segment_checks(iov, &nr_segs, &ocount,
+				     VERIFY_READ);
+	if (ret)
+		goto out_dio;
+
+	count = ocount;
+	ret = generic_write_checks(file, ppos, &count,
+				   S_ISBLK(inode->i_mode));
+	if (ret)
+		goto out_dio;
+
 	if (direct_io) {
-		ret = generic_segment_checks(iov, &nr_segs, &ocount,
-					     VERIFY_READ);
-		if (ret)
-			goto out_dio;
-
-		count = ocount;
-		ret = generic_write_checks(file, ppos, &count,
-					   S_ISBLK(inode->i_mode));
-		if (ret)
-			goto out_dio;
-
 		written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos,
 						    ppos, count, ocount);
 		if (written < 0) {
@@ -2007,7 +2008,10 @@
 			goto out_dio;
 		}
 	} else {
-		written = __generic_file_aio_write(iocb, iov, nr_segs, ppos);
+		current->backing_dev_info = file->f_mapping->backing_dev_info;
+		written = generic_file_buffered_write(iocb, iov, nr_segs, *ppos,
+						      ppos, count, 0);
+		current->backing_dev_info = NULL;
 	}
 
 out_dio:
@@ -2021,9 +2025,9 @@
 		if (ret < 0)
 			written = ret;
 
-		if (!ret && (old_size != i_size_read(inode) ||
-		    old_clusters != OCFS2_I(inode)->ip_clusters ||
-		    has_refcount)) {
+		if (!ret && ((old_size != i_size_read(inode)) ||
+			     (old_clusters != OCFS2_I(inode)->ip_clusters) ||
+			     has_refcount)) {
 			ret = jbd2_journal_force_commit(osb->journal->j_journal);
 			if (ret < 0)
 				written = ret;

fs/ocfs2/inode.c

diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 07cc8bb..af18988 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -558,6 +558,7 @@
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
+			handle = NULL;
 			mlog_errno(status);
 			goto out;
 		}
@@ -639,11 +640,13 @@
 		goto bail_unlock;
 	}
 
-	status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode,
-				  orphan_dir_bh);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail_commit;
+	if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
+		status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode,
+					  orphan_dir_bh);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail_commit;
+		}
 	}
 
 	/* set the inodes dtime */
@@ -722,38 +725,39 @@
 static int ocfs2_wipe_inode(struct inode *inode,
 			    struct buffer_head *di_bh)
 {
-	int status, orphaned_slot;
+	int status, orphaned_slot = -1;
 	struct inode *orphan_dir_inode = NULL;
 	struct buffer_head *orphan_dir_bh = NULL;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	struct ocfs2_dinode *di;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
 
-	di = (struct ocfs2_dinode *) di_bh->b_data;
-	orphaned_slot = le16_to_cpu(di->i_orphaned_slot);
+	if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
+		orphaned_slot = le16_to_cpu(di->i_orphaned_slot);
 
-	status = ocfs2_check_orphan_recovery_state(osb, orphaned_slot);
-	if (status)
-		return status;
+		status = ocfs2_check_orphan_recovery_state(osb, orphaned_slot);
+		if (status)
+			return status;
 
-	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
-						       ORPHAN_DIR_SYSTEM_INODE,
-						       orphaned_slot);
-	if (!orphan_dir_inode) {
-		status = -EEXIST;
-		mlog_errno(status);
-		goto bail;
-	}
+		orphan_dir_inode = ocfs2_get_system_file_inode(osb,
+							       ORPHAN_DIR_SYSTEM_INODE,
+							       orphaned_slot);
+		if (!orphan_dir_inode) {
+			status = -EEXIST;
+			mlog_errno(status);
+			goto bail;
+		}
 
-	/* Lock the orphan dir. The lock will be held for the entire
-	 * delete_inode operation. We do this now to avoid races with
-	 * recovery completion on other nodes. */
-	mutex_lock(&orphan_dir_inode->i_mutex);
-	status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
-	if (status < 0) {
-		mutex_unlock(&orphan_dir_inode->i_mutex);
+		/* Lock the orphan dir. The lock will be held for the entire
+		 * delete_inode operation. We do this now to avoid races with
+		 * recovery completion on other nodes. */
+		mutex_lock(&orphan_dir_inode->i_mutex);
+		status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
+		if (status < 0) {
+			mutex_unlock(&orphan_dir_inode->i_mutex);
 
-		mlog_errno(status);
-		goto bail;
+			mlog_errno(status);
+			goto bail;
+		}
 	}
 
 	/* we do this while holding the orphan dir lock because we
@@ -794,6 +798,9 @@
 		mlog_errno(status);
 
 bail_unlock_dir:
+	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)
+		return status;
+
 	ocfs2_inode_unlock(orphan_dir_inode, 1);
 	mutex_unlock(&orphan_dir_inode->i_mutex);
 	brelse(orphan_dir_bh);
@@ -889,7 +896,8 @@
 
 	/* Do some basic inode verification... */
 	di = (struct ocfs2_dinode *) di_bh->b_data;
-	if (!(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL))) {
+	if (!(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL)) &&
+	    !(oi->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
 		/*
 		 * Inodes in the orphan dir must have ORPHANED_FL.  The only
 		 * inodes that come back out of the orphan dir are reflink

fs/ocfs2/inode.h

diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index ba4fe07..0b28e19 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -100,6 +100,8 @@
 #define OCFS2_INODE_MAYBE_ORPHANED	0x00000020
 /* Does someone have the file open O_DIRECT */
 #define OCFS2_INODE_OPEN_DIRECT		0x00000040
+/* Tell the inode wipe code it's not in orphan dir */
+#define OCFS2_INODE_SKIP_ORPHAN_DIR     0x00000080
 
 static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode)
 {

fs/ocfs2/namei.c

diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index b1eb50a..4cbb18f 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -408,6 +408,19 @@
 		}
 	}
 
+	/*
+	 * Do this before adding the entry to the directory. We add
+	 * also set d_op after success so that ->d_iput() will cleanup
+	 * the dentry lock even if ocfs2_add_entry() fails below.
+	 */
+	status = ocfs2_dentry_attach_lock(dentry, inode,
+					  OCFS2_I(dir)->ip_blkno);
+	if (status) {
+		mlog_errno(status);
+		goto leave;
+	}
+	dentry->d_op = &ocfs2_dentry_ops;
+
 	status = ocfs2_add_entry(handle, dentry, inode,
 				 OCFS2_I(inode)->ip_blkno, parent_fe_bh,
 				 &lookup);
@@ -416,15 +429,7 @@
 		goto leave;
 	}
 
-	status = ocfs2_dentry_attach_lock(dentry, inode,
-					  OCFS2_I(dir)->ip_blkno);
-	if (status) {
-		mlog_errno(status);
-		goto leave;
-	}
-
 	insert_inode_hash(inode);
-	dentry->d_op = &ocfs2_dentry_ops;
 	d_instantiate(dentry, inode);
 	status = 0;
 leave:
@@ -445,11 +450,6 @@
 
 	ocfs2_free_dir_lookup_result(&lookup);
 
-	if ((status < 0) && inode) {
-		clear_nlink(inode);
-		iput(inode);
-	}
-
 	if (inode_ac)
 		ocfs2_free_alloc_context(inode_ac);
 
@@ -459,6 +459,17 @@
 	if (meta_ac)
 		ocfs2_free_alloc_context(meta_ac);
 
+	/*
+	 * We should call iput after the i_mutex of the bitmap been
+	 * unlocked in ocfs2_free_alloc_context, or the
+	 * ocfs2_delete_inode will mutex_lock again.
+	 */
+	if ((status < 0) && inode) {
+		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
+		clear_nlink(inode);
+		iput(inode);
+	}
+
 	mlog_exit(status);
 
 	return status;
@@ -1771,6 +1782,18 @@
 		}
 	}
 
+	/*
+	 * Do this before adding the entry to the directory. We add
+	 * also set d_op after success so that ->d_iput() will cleanup
+	 * the dentry lock even if ocfs2_add_entry() fails below.
+	 */
+	status = ocfs2_dentry_attach_lock(dentry, inode, OCFS2_I(dir)->ip_blkno);
+	if (status) {
+		mlog_errno(status);
+		goto bail;
+	}
+	dentry->d_op = &ocfs2_dentry_ops;
+
 	status = ocfs2_add_entry(handle, dentry, inode,
 				 le64_to_cpu(fe->i_blkno), parent_fe_bh,
 				 &lookup);
@@ -1779,14 +1802,7 @@
 		goto bail;
 	}
 
-	status = ocfs2_dentry_attach_lock(dentry, inode, OCFS2_I(dir)->ip_blkno);
-	if (status) {
-		mlog_errno(status);
-		goto bail;
-	}
-
 	insert_inode_hash(inode);
-	dentry->d_op = &ocfs2_dentry_ops;
 	d_instantiate(dentry, inode);
 bail:
 	if (status < 0 && did_quota)
@@ -1811,6 +1827,7 @@
 	if (xattr_ac)
 		ocfs2_free_alloc_context(xattr_ac);
 	if ((status < 0) && inode) {
+		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
 		clear_nlink(inode);
 		iput(inode);
 	}
@@ -1976,6 +1993,7 @@
 	}
 
 	le32_add_cpu(&fe->i_flags, OCFS2_ORPHANED_FL);
+	OCFS2_I(inode)->ip_flags &= ~OCFS2_INODE_SKIP_ORPHAN_DIR;
 
 	/* Record which orphan dir our inode now resides
 	 * in. delete_inode will use this to determine which orphan

fs/ocfs2/refcounttree.c

diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index bd96f6c..5cbcd0f 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4083,6 +4083,9 @@
 	di->i_attr = s_di->i_attr;
 
 	if (preserve) {
+		t_inode->i_uid = s_inode->i_uid;
+		t_inode->i_gid = s_inode->i_gid;
+		t_inode->i_mode = s_inode->i_mode;
 		di->i_uid = s_di->i_uid;
 		di->i_gid = s_di->i_gid;
 		di->i_mode = s_di->i_mode;

fs/proc/array.c

diff --git a/fs/proc/array.c b/fs/proc/array.c
index e51f2ec..885ab55 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -81,7 +81,6 @@
 #include <linux/pid_namespace.h>
 #include <linux/ptrace.h>
 #include <linux/tracehook.h>
-#include <linux/swapops.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -495,7 +494,7 @@
 		rsslim,
 		mm ? mm->start_code : 0,
 		mm ? mm->end_code : 0,
-		(permitted && mm) ? task->stack_start : 0,
+		(permitted && mm) ? mm->start_stack : 0,
 		esp,
 		eip,
 		/* The signal information here is obsolete.

fs/proc/task_mmu.c

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 0705534..47f5b14 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -247,25 +247,6 @@
 				} else if (vma->vm_start <= mm->start_stack &&
 					   vma->vm_end >= mm->start_stack) {
 					name = "[stack]";
-				} else {
-					unsigned long stack_start;
-					struct proc_maps_private *pmp;
-
-					pmp = m->private;
-					stack_start = pmp->task->stack_start;
-
-					if (vma->vm_start <= stack_start &&
-					    vma->vm_end >= stack_start) {
-						pad_len_spaces(m, len);
-						seq_printf(m,
-						 "[threadstack:%08lx]",
-#ifdef CONFIG_STACK_GROWSUP
-						 vma->vm_end - stack_start
-#else
-						 stack_start - vma->vm_start
-#endif
-						);
-					}
 				}
 			} else {
 				name = "[vdso]";

fs/sysv/dir.c

diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c
index 4e50286..1dabed2 100644
--- a/fs/sysv/dir.c
+++ b/fs/sysv/dir.c
@@ -164,8 +164,8 @@
 							name, de->name))
 					goto found;
 			}
+			dir_put_page(page);
 		}
-		dir_put_page(page);
 
 		if (++n >= npages)
 			n = 0;

include/asm-generic/atomic.h

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index c99c64d..c33749f 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -33,7 +33,7 @@
  * Atomically reads the value of @v.  Note that the guaranteed
  * useful range of an atomic_t is only 24 bits.
  */
-#define atomic_read(v)	((v)->counter)
+#define atomic_read(v)	(*(volatile int *)&(v)->counter)
 
 /**
  * atomic_set - set atomic variable

include/asm-generic/dma-mapping-common.h

diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index e694263..6920695 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -131,7 +131,7 @@
 		debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
 
 	} else
-		dma_sync_single_for_cpu(dev, addr, size, dir);
+		dma_sync_single_for_cpu(dev, addr + offset, size, dir);
 }
 
 static inline void dma_sync_single_range_for_device(struct device *dev,
@@ -148,7 +148,7 @@
 		debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir);
 
 	} else
-		dma_sync_single_for_device(dev, addr, size, dir);
+		dma_sync_single_for_device(dev, addr + offset, size, dir);
 }
 
 static inline void

include/drm/ttm/ttm_bo_driver.h

diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index e929c27..6b9db91 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -789,34 +789,6 @@
 extern int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo,
 				  bool interruptible);
 
-/**
- * ttm_bo_block_reservation
- *
- * @bo: A pointer to a struct ttm_buffer_object.
- * @interruptible: Use interruptible sleep when waiting.
- * @no_wait: Don't sleep, but rather return -EBUSY.
- *
- * Block reservation for validation by simply reserving the buffer.
- * This is intended for single buffer use only without eviction,
- * and thus needs no deadlock protection.
- *
- * Returns:
- * -EBUSY: If no_wait == 1 and the buffer is already reserved.
- * -ERESTARTSYS: If interruptible == 1 and the process received a signal
- * while sleeping.
- */
-extern int ttm_bo_block_reservation(struct ttm_buffer_object *bo,
-				    bool interruptible, bool no_wait);
-
-/**
- * ttm_bo_unblock_reservation
- *
- * @bo: A pointer to a struct ttm_buffer_object.
- *
- * Unblocks reservation leaving lru lists untouched.
- */
-extern void ttm_bo_unblock_reservation(struct ttm_buffer_object *bo);
-
 /*
  * ttm_bo_util.c
  */

include/linux/cgroup.h

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b8ad1ea..8f78073 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -530,6 +530,7 @@
 {
 	return rcu_dereference_check(task->cgroups->subsys[subsys_id],
 				     rcu_read_lock_held() ||
+				     lockdep_is_held(&task->alloc_lock) ||
 				     cgroup_lock_is_held());
 }
 

include/linux/dcache.h

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 30b93b2..eebb617 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -186,6 +186,8 @@
 
 #define DCACHE_FSNOTIFY_PARENT_WATCHED	0x0080 /* Parent inode is watched by some fsnotify listener */
 
+#define DCACHE_CANT_MOUNT	0x0100
+
 extern spinlock_t dcache_lock;
 extern seqlock_t rename_lock;
 
@@ -358,6 +360,18 @@
 	return d_unhashed(dentry) && !IS_ROOT(dentry);
 }
 
+static inline int cant_mount(struct dentry *dentry)
+{
+	return (dentry->d_flags & DCACHE_CANT_MOUNT);
+}
+
+static inline void dont_mount(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	dentry->d_flags |= DCACHE_CANT_MOUNT;
+	spin_unlock(&dentry->d_lock);
+}
+
 static inline struct dentry *dget_parent(struct dentry *dentry)
 {
 	struct dentry *ret;

include/linux/debugobjects.h

diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 8c243aa..597692f 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -20,12 +20,14 @@
  * struct debug_obj - representaion of an tracked object
  * @node:	hlist node to link the object into the tracker list
  * @state:	tracked object state
+ * @astate:	current active state
  * @object:	pointer to the real object
  * @descr:	pointer to an object type specific debug description structure
  */
 struct debug_obj {
 	struct hlist_node	node;
 	enum debug_obj_state	state;
+	unsigned int		astate;
 	void			*object;
 	struct debug_obj_descr	*descr;
 };
@@ -60,6 +62,15 @@
 extern void debug_object_destroy   (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_free      (void *addr, struct debug_obj_descr *descr);
 
+/*
+ * Active state:
+ * - Set at 0 upon initialization.
+ * - Must return to 0 before deactivation.
+ */
+extern void
+debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+			  unsigned int expect, unsigned int next);
+
 extern void debug_objects_early_init(void);
 extern void debug_objects_mem_init(void);
 #else

include/linux/ftrace.h

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 01e6ade..cc12b3c 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -504,18 +504,6 @@
 #define INIT_TRACE_RECURSION
 #endif
 
-#ifdef CONFIG_HW_BRANCH_TRACER
-
-void trace_hw_branch(u64 from, u64 to);
-void trace_hw_branch_oops(void);
-
-#else /* CONFIG_HW_BRANCH_TRACER */
-
-static inline void trace_hw_branch(u64 from, u64 to) {}
-static inline void trace_hw_branch_oops(void) {}
-
-#endif /* CONFIG_HW_BRANCH_TRACER */
-
 #ifdef CONFIG_FTRACE_SYSCALLS
 
 unsigned long arch_syscall_addr(int nr);

include/linux/ftrace_event.h

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index c0f4b36..39e71b0 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -58,6 +58,7 @@
 	/* The below is zeroed out in pipe_read */
 	struct trace_seq	seq;
 	struct trace_entry	*ent;
+	unsigned long		lost_events;
 	int			leftover;
 	int			cpu;
 	u64			ts;

include/linux/hw_breakpoint.h

diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index c70d27a..a2d6ea4 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -9,9 +9,22 @@
 };
 
 enum {
-	HW_BREAKPOINT_R = 1,
-	HW_BREAKPOINT_W = 2,
-	HW_BREAKPOINT_X = 4,
+	HW_BREAKPOINT_EMPTY	= 0,
+	HW_BREAKPOINT_R		= 1,
+	HW_BREAKPOINT_W		= 2,
+	HW_BREAKPOINT_RW	= HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+	HW_BREAKPOINT_X		= 4,
+	HW_BREAKPOINT_INVALID   = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
+};
+
+enum bp_type_idx {
+	TYPE_INST 	= 0,
+#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
+	TYPE_DATA	= 0,
+#else
+	TYPE_DATA	= 1,
+#endif
+	TYPE_MAX
 };
 
 #ifdef __KERNEL__
@@ -34,6 +47,12 @@
 	attr->sample_period = 1;
 }
 
+static inline void ptrace_breakpoint_init(struct perf_event_attr *attr)
+{
+	hw_breakpoint_init(attr);
+	attr->exclude_kernel = 1;
+}
+
 static inline unsigned long hw_breakpoint_addr(struct perf_event *bp)
 {
 	return bp->attr.bp_addr;

include/linux/i2c.h

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 0a5da63..6ed1d59 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -355,6 +355,8 @@
 	int nr;
 	char name[48];
 	struct completion dev_released;
+
+	struct list_head userspace_clients;
 };
 #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev)
 

include/linux/if_link.h

diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index c9bf92c..d94963b 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -79,10 +79,7 @@
 	IFLA_NET_NS_PID,
 	IFLA_IFALIAS,
 	IFLA_NUM_VF,		/* Number of VFs if device is SR-IOV PF */
-	IFLA_VF_MAC,		/* Hardware queue specific attributes */
-	IFLA_VF_VLAN,
-	IFLA_VF_TX_RATE,	/* TX Bandwidth Allocation */
-	IFLA_VFINFO,
+	IFLA_VFINFO_LIST,
 	__IFLA_MAX
 };
 
@@ -203,6 +200,24 @@
 
 /* SR-IOV virtual function managment section */
 
+enum {
+	IFLA_VF_INFO_UNSPEC,
+	IFLA_VF_INFO,
+	__IFLA_VF_INFO_MAX,
+};
+
+#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1)
+
+enum {
+	IFLA_VF_UNSPEC,
+	IFLA_VF_MAC,		/* Hardware queue specific attributes */
+	IFLA_VF_VLAN,
+	IFLA_VF_TX_RATE,	/* TX Bandwidth Allocation */
+	__IFLA_VF_MAX,
+};
+
+#define IFLA_VF_MAX (__IFLA_VF_MAX - 1)
+
 struct ifla_vf_mac {
 	__u32 vf;
 	__u8 mac[32]; /* MAX_ADDR_LEN */

include/linux/init_task.h

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index b1ed1cd..7996fc2 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -49,7 +49,6 @@
 		{ .first = &init_task.pids[PIDTYPE_PGID].node },	\
 		{ .first = &init_task.pids[PIDTYPE_SID].node },		\
 	},								\
-	.rcu		= RCU_HEAD_INIT,				\
 	.level		= 0,						\
 	.numbers	= { {						\
 		.nr		= 0,					\

include/linux/iommu.h

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 3af4ffd..be22ad8 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -37,9 +37,9 @@
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
-		   phys_addr_t paddr, size_t size, int prot);
-	void (*unmap)(struct iommu_domain *domain, unsigned long iova,
-		      size_t size);
+		   phys_addr_t paddr, int gfp_order, int prot);
+	int (*unmap)(struct iommu_domain *domain, unsigned long iova,
+		     int gfp_order);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    unsigned long iova);
 	int (*domain_has_cap)(struct iommu_domain *domain,
@@ -56,10 +56,10 @@
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
-extern int iommu_map_range(struct iommu_domain *domain, unsigned long iova,
-			   phys_addr_t paddr, size_t size, int prot);
-extern void iommu_unmap_range(struct iommu_domain *domain, unsigned long iova,
-			      size_t size);
+extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
+		     phys_addr_t paddr, int gfp_order, int prot);
+extern int iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+		       int gfp_order);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
 				      unsigned long iova);
 extern int iommu_domain_has_cap(struct iommu_domain *domain,
@@ -96,16 +96,16 @@
 {
 }
 
-static inline int iommu_map_range(struct iommu_domain *domain,
-				  unsigned long iova, phys_addr_t paddr,
-				  size_t size, int prot)
+static inline int iommu_map(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, int gfp_order, int prot)
 {
 	return -ENODEV;
 }
 
-static inline void iommu_unmap_range(struct iommu_domain *domain,
-				     unsigned long iova, size_t size)
+static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+			      int gfp_order)
 {
+	return -ENODEV;
 }
 
 static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,

include/linux/mm.h

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 462acaf..fb19bb9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -19,7 +19,6 @@
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
-struct rlimit;
 
 #ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
 extern unsigned long max_mapnr;
@@ -1449,9 +1448,6 @@
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
 
-extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
-				 size_t size);
-extern void refund_locked_memory(struct mm_struct *mm, size_t size);
 
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,

include/linux/mod_devicetable.h

diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index f58e9d83..56fde43 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -474,4 +474,13 @@
 			__attribute__((aligned(sizeof(kernel_ulong_t))));
 };
 
+struct zorro_device_id {
+	__u32 id;			/* Device ID or ZORRO_WILDCARD */
+	kernel_ulong_t driver_data;	/* Data private to the driver */
+};
+
+#define ZORRO_WILDCARD			(0xffffffff)	/* not official */
+
+#define ZORRO_DEVICE_MODALIAS_FMT	"zorro:i%08X"
+
 #endif /* LINUX_MOD_DEVICETABLE_H */

include/linux/module.h

diff --git a/include/linux/module.h b/include/linux/module.h
index 515d53a..6914fca 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -465,8 +465,7 @@
 	if (module) {
 		preempt_disable();
 		__this_cpu_inc(module->refptr->incs);
-		trace_module_get(module, _THIS_IP_,
-				 __this_cpu_read(module->refptr->incs));
+		trace_module_get(module, _THIS_IP_);
 		preempt_enable();
 	}
 }
@@ -480,8 +479,7 @@
 
 		if (likely(module_is_live(module))) {
 			__this_cpu_inc(module->refptr->incs);
-			trace_module_get(module, _THIS_IP_,
-				__this_cpu_read(module->refptr->incs));
+			trace_module_get(module, _THIS_IP_);
 		} else
 			ret = 0;
 

include/linux/perf_event.h

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c8e3754..3fd5c82 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -203,8 +203,19 @@
 				enable_on_exec :  1, /* next exec enables     */
 				task           :  1, /* trace fork/exit       */
 				watermark      :  1, /* wakeup_watermark      */
+				/*
+				 * precise_ip:
+				 *
+				 *  0 - SAMPLE_IP can have arbitrary skid
+				 *  1 - SAMPLE_IP must have constant skid
+				 *  2 - SAMPLE_IP requested to have 0 skid
+				 *  3 - SAMPLE_IP must have 0 skid
+				 *
+				 *  See also PERF_RECORD_MISC_EXACT_IP
+				 */
+				precise_ip     :  2, /* skid constraint       */
 
-				__reserved_1   : 49;
+				__reserved_1   : 47;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -287,11 +298,24 @@
 	__u64	data_tail;		/* user-space written tail */
 };
 
-#define PERF_RECORD_MISC_CPUMODE_MASK		(3 << 0)
+#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
 #define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
 #define PERF_RECORD_MISC_KERNEL			(1 << 0)
 #define PERF_RECORD_MISC_USER			(2 << 0)
 #define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
+
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)
 
 struct perf_event_header {
 	__u32	type;
@@ -439,6 +463,12 @@
 # include <asm/perf_event.h>
 #endif
 
+struct perf_guest_info_callbacks {
+	int (*is_in_guest) (void);
+	int (*is_user_mode) (void);
+	unsigned long (*get_guest_ip) (void);
+};
+
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 #include <asm/hw_breakpoint.h>
 #endif
@@ -468,6 +498,17 @@
 	void				*data;
 };
 
+struct perf_branch_entry {
+	__u64				from;
+	__u64				to;
+	__u64				flags;
+};
+
+struct perf_branch_stack {
+	__u64				nr;
+	struct perf_branch_entry	entries[0];
+};
+
 struct task_struct;
 
 /**
@@ -506,6 +547,8 @@
 
 struct perf_event;
 
+#define PERF_EVENT_TXN_STARTED 1
+
 /**
  * struct pmu - generic performance monitoring unit
  */
@@ -516,6 +559,16 @@
 	void (*stop)			(struct perf_event *event);
 	void (*read)			(struct perf_event *event);
 	void (*unthrottle)		(struct perf_event *event);
+
+	/*
+	 * group events scheduling is treated as a transaction,
+	 * add group events as a whole and perform one schedulability test.
+	 * If test fails, roll back the whole group
+	 */
+
+	void (*start_txn)	(const struct pmu *pmu);
+	void (*cancel_txn)	(const struct pmu *pmu);
+	int  (*commit_txn)	(const struct pmu *pmu);
 };
 
 /**
@@ -571,6 +624,14 @@
 	PERF_GROUP_SOFTWARE = 0x1,
 };
 
+#define SWEVENT_HLIST_BITS	8
+#define SWEVENT_HLIST_SIZE	(1 << SWEVENT_HLIST_BITS)
+
+struct swevent_hlist {
+	struct hlist_head	heads[SWEVENT_HLIST_SIZE];
+	struct rcu_head		rcu_head;
+};
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -579,6 +640,7 @@
 	struct list_head		group_entry;
 	struct list_head		event_entry;
 	struct list_head		sibling_list;
+	struct hlist_node		hlist_entry;
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
@@ -726,6 +788,9 @@
 	int				active_oncpu;
 	int				max_pertask;
 	int				exclusive;
+	struct swevent_hlist		*swevent_hlist;
+	struct mutex			hlist_mutex;
+	int				hlist_refcount;
 
 	/*
 	 * Recursion avoidance:
@@ -769,9 +834,6 @@
 extern void perf_enable(void);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
-extern int hw_perf_group_sched_in(struct perf_event *group_leader,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx);
 extern void perf_event_update_userpage(struct perf_event *event);
 extern int perf_event_release_kernel(struct perf_event *event);
 extern struct perf_event *
@@ -902,6 +964,10 @@
 		__perf_event_mmap(vma);
 }
 
+extern struct perf_guest_info_callbacks *perf_guest_cbs;
+extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
+extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
+
 extern void perf_event_comm(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
@@ -971,6 +1037,11 @@
 static inline void
 perf_bp_event(struct perf_event *event, void *data)			{ }
 
+static inline int perf_register_guest_info_callbacks
+(struct perf_guest_info_callbacks *callbacks) { return 0; }
+static inline int perf_unregister_guest_info_callbacks
+(struct perf_guest_info_callbacks *callbacks) { return 0; }
+
 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
 static inline void perf_event_comm(struct task_struct *tsk)		{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }

include/linux/platform_device.h

diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 212da17..5417944 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -44,12 +44,14 @@
 extern int platform_add_devices(struct platform_device **, int);
 
 extern struct platform_device *platform_device_register_simple(const char *, int id,
-					struct resource *, unsigned int);
+					const struct resource *, unsigned int);
 extern struct platform_device *platform_device_register_data(struct device *,
 		const char *, int, const void *, size_t);
 
 extern struct platform_device *platform_device_alloc(const char *name, int id);
-extern int platform_device_add_resources(struct platform_device *pdev, struct resource *res, unsigned int num);
+extern int platform_device_add_resources(struct platform_device *pdev,
+					 const struct resource *res,
+					 unsigned int num);
 extern int platform_device_add_data(struct platform_device *pdev, const void *data, size_t size);
 extern int platform_device_add(struct platform_device *pdev);
 extern void platform_device_del(struct platform_device *pdev);

include/linux/ptrace.h

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index e1fb607..4272521 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -345,18 +345,6 @@
 #define arch_ptrace_stop(code, info)		do { } while (0)
 #endif
 
-#ifndef arch_ptrace_untrace
-/*
- * Do machine-specific work before untracing child.
- *
- * This is called for a normal detach as well as from ptrace_exit()
- * when the tracing task dies.
- *
- * Called with write_lock(&tasklist_lock) held.
- */
-#define arch_ptrace_untrace(task)		do { } while (0)
-#endif
-
 extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);

include/linux/rcupdate.h

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 07db2fe..b653b4a 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -56,8 +56,6 @@
 };
 
 /* Exported common interfaces */
-extern void synchronize_rcu_bh(void);
-extern void synchronize_sched(void);
 extern void rcu_barrier(void);
 extern void rcu_barrier_bh(void);
 extern void rcu_barrier_sched(void);
@@ -66,8 +64,6 @@
 
 /* Internal to kernel */
 extern void rcu_init(void);
-extern int rcu_scheduler_active;
-extern void rcu_scheduler_starting(void);
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 #include <linux/rcutree.h>
@@ -83,6 +79,14 @@
        (ptr)->next = NULL; (ptr)->func = NULL; \
 } while (0)
 
+static inline void init_rcu_head_on_stack(struct rcu_head *head)
+{
+}
+
+static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
+{
+}
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 extern struct lockdep_map rcu_lock_map;
@@ -106,12 +110,13 @@
 /**
  * rcu_read_lock_held - might we be in RCU read-side critical section?
  *
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
- * an RCU read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
+ * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
  * this assumes we are in an RCU read-side critical section unless it can
  * prove otherwise.
  *
- * Check rcu_scheduler_active to prevent false positives during boot.
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
  */
 static inline int rcu_read_lock_held(void)
 {
@@ -129,13 +134,15 @@
 /**
  * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section?
  *
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in an
- * RCU-sched read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
- * this assumes we are in an RCU-sched read-side critical section unless it
- * can prove otherwise.  Note that disabling of preemption (including
- * disabling irqs) counts as an RCU-sched read-side critical section.
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
+ * RCU-sched read-side critical section.  In absence of
+ * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
+ * critical section unless it can prove otherwise.  Note that disabling
+ * of preemption (including disabling irqs) counts as an RCU-sched
+ * read-side critical section.
  *
- * Check rcu_scheduler_active to prevent false positives during boot.
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
  */
 #ifdef CONFIG_PREEMPT
 static inline int rcu_read_lock_sched_held(void)
@@ -177,7 +184,7 @@
 #ifdef CONFIG_PREEMPT
 static inline int rcu_read_lock_sched_held(void)
 {
-	return !rcu_scheduler_active || preempt_count() != 0 || irqs_disabled();
+	return preempt_count() != 0 || irqs_disabled();
 }
 #else /* #ifdef CONFIG_PREEMPT */
 static inline int rcu_read_lock_sched_held(void)
@@ -190,6 +197,17 @@
 
 #ifdef CONFIG_PROVE_RCU
 
+extern int rcu_my_thread_group_empty(void);
+
+#define __do_rcu_dereference_check(c)					\
+	do {								\
+		static bool __warned;					\
+		if (debug_lockdep_rcu_enabled() && !__warned && !(c)) {	\
+			__warned = true;				\
+			lockdep_rcu_dereference(__FILE__, __LINE__);	\
+		}							\
+	} while (0)
+
 /**
  * rcu_dereference_check - rcu_dereference with debug checking
  * @p: The pointer to read, prior to dereferencing
@@ -219,8 +237,7 @@
  */
 #define rcu_dereference_check(p, c) \
 	({ \
-		if (debug_lockdep_rcu_enabled() && !(c)) \
-			lockdep_rcu_dereference(__FILE__, __LINE__); \
+		__do_rcu_dereference_check(c); \
 		rcu_dereference_raw(p); \
 	})
 
@@ -237,8 +254,7 @@
  */
 #define rcu_dereference_protected(p, c) \
 	({ \
-		if (debug_lockdep_rcu_enabled() && !(c)) \
-			lockdep_rcu_dereference(__FILE__, __LINE__); \
+		__do_rcu_dereference_check(c); \
 		(p); \
 	})
 

include/linux/rcutiny.h

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 0006b2d..e2e8931 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -29,6 +29,10 @@
 
 void rcu_sched_qs(int cpu);
 void rcu_bh_qs(int cpu);
+static inline void rcu_note_context_switch(int cpu)
+{
+	rcu_sched_qs(cpu);
+}
 
 #define __rcu_read_lock()	preempt_disable()
 #define __rcu_read_unlock()	preempt_enable()
@@ -72,7 +76,17 @@
 {
 }
 
-#define synchronize_rcu synchronize_sched
+extern void synchronize_sched(void);
+
+static inline void synchronize_rcu(void)
+{
+	synchronize_sched();
+}
+
+static inline void synchronize_rcu_bh(void)
+{
+	synchronize_sched();
+}
 
 static inline void synchronize_rcu_expedited(void)
 {
@@ -112,4 +126,17 @@
 	return 0;
 }
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+extern int rcu_scheduler_active __read_mostly;
+extern void rcu_scheduler_starting(void);
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+static inline void rcu_scheduler_starting(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 #endif /* __LINUX_RCUTINY_H */

include/linux/rcutree.h

diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 24e467e..c0ed1c0 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -34,6 +34,7 @@
 
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
+extern void rcu_note_context_switch(int cpu);
 extern int rcu_needs_cpu(int cpu);
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
@@ -85,6 +86,8 @@
 
 extern void call_rcu_sched(struct rcu_head *head,
 			   void (*func)(struct rcu_head *rcu));
+extern void synchronize_rcu_bh(void);
+extern void synchronize_sched(void);
 extern void synchronize_rcu_expedited(void);
 
 static inline void synchronize_rcu_bh_expedited(void)
@@ -119,4 +122,7 @@
 	return num_online_cpus() == 1;
 }
 
+extern void rcu_scheduler_starting(void);
+extern int rcu_scheduler_active __read_mostly;
+
 #endif /* __LINUX_RCUTREE_H */

include/linux/ring_buffer.h

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 5fcc31e..c829776 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -120,9 +120,11 @@
 		      unsigned long length, void *data);
 
 struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts);
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
+		 unsigned long *lost_events);
 struct ring_buffer_event *
-ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts);
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
+		    unsigned long *lost_events);
 
 struct ring_buffer_iter *
 ring_buffer_read_start(struct ring_buffer *buffer, int cpu);

include/linux/sched.h

diff --git a/include/linux/sched.h b/include/linux/sched.h
index dfea405..b55e988 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -99,7 +99,6 @@
 struct robust_list_head;
 struct bio_list;
 struct fs_struct;
-struct bts_context;
 struct perf_event_context;
 
 /*
@@ -1275,12 +1274,6 @@
 	struct list_head ptraced;
 	struct list_head ptrace_entry;
 
-	/*
-	 * This is the tracer handle for the ptrace BTS extension.
-	 * This field actually belongs to the ptracer task.
-	 */
-	struct bts_context *bts;
-
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
 	struct list_head thread_group;
@@ -1500,7 +1493,6 @@
 	/* bitmask of trace recursion */
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
-	unsigned long stack_start;
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
 	struct memcg_batch_info {
 		int do_batch;	/* incremented when batch uncharge started */
@@ -2127,10 +2119,8 @@
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
-extern void wait_task_context_switch(struct task_struct *p);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
-static inline void wait_task_context_switch(struct task_struct *p) {}
 static inline unsigned long wait_task_inactive(struct task_struct *p,
 					       long match_state)
 {

include/linux/srcu.h

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 4d5ecb2..4d5d2f5 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -27,6 +27,8 @@
 #ifndef _LINUX_SRCU_H
 #define _LINUX_SRCU_H
 
+#include <linux/mutex.h>
+
 struct srcu_struct_array {
 	int c[2];
 };
@@ -84,8 +86,8 @@
 /**
  * srcu_read_lock_held - might we be in SRCU read-side critical section?
  *
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
- * an SRCU read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU
+ * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
  * this assumes we are in an SRCU read-side critical section unless it can
  * prove otherwise.
  */

include/linux/types.h

diff --git a/include/linux/types.h b/include/linux/types.h
index c42724f..23d237a 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -188,12 +188,12 @@
 typedef phys_addr_t resource_size_t;
 
 typedef struct {
-	volatile int counter;
+	int counter;
 } atomic_t;
 
 #ifdef CONFIG_64BIT
 typedef struct {
-	volatile long counter;
+	long counter;
 } atomic64_t;
 #endif
 

include/linux/usb.h

diff --git a/include/linux/usb.h b/include/linux/usb.h
index ce1323c..739f1fd 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1085,7 +1085,7 @@
  * Alternatively, drivers may pass the URB_NO_xxx_DMA_MAP transfer flags,
  * which tell the host controller driver that no such mapping is needed since
  * the device driver is DMA-aware.  For example, a device driver might
- * allocate a DMA buffer with usb_buffer_alloc() or call usb_buffer_map().
+ * allocate a DMA buffer with usb_alloc_coherent() or call usb_buffer_map().
  * When these transfer flags are provided, host controller drivers will
  * attempt to use the dma addresses found in the transfer_dma and/or
  * setup_dma fields rather than determining a dma address themselves.
@@ -1366,11 +1366,23 @@
 	return (urb->transfer_flags & URB_DIR_MASK) == URB_DIR_OUT;
 }
 
-void *usb_buffer_alloc(struct usb_device *dev, size_t size,
+void *usb_alloc_coherent(struct usb_device *dev, size_t size,
 	gfp_t mem_flags, dma_addr_t *dma);
-void usb_buffer_free(struct usb_device *dev, size_t size,
+void usb_free_coherent(struct usb_device *dev, size_t size,
 	void *addr, dma_addr_t dma);
 
+/* Compatible macros while we switch over */
+static inline void *usb_buffer_alloc(struct usb_device *dev, size_t size,
+				     gfp_t mem_flags, dma_addr_t *dma)
+{
+	return usb_alloc_coherent(dev, size, mem_flags, dma);
+}
+static inline void usb_buffer_free(struct usb_device *dev, size_t size,
+				   void *addr, dma_addr_t dma)
+{
+	return usb_free_coherent(dev, size, addr, dma);
+}
+
 #if 0
 struct urb *usb_buffer_map(struct urb *urb);
 void usb_buffer_dmasync(struct urb *urb);

include/linux/zorro.h

diff --git a/include/linux/zorro.h b/include/linux/zorro.h
index 913bfc2..7bf9db5 100644
--- a/include/linux/zorro.h
+++ b/include/linux/zorro.h
@@ -38,8 +38,6 @@
 typedef __u32 zorro_id;
 
 
-#define ZORRO_WILDCARD		(0xffffffff)	/* not official */
-
 /* Include the ID list */
 #include <linux/zorro_ids.h>
 
@@ -116,6 +114,7 @@
 
 #include <linux/init.h>
 #include <linux/ioport.h>
+#include <linux/mod_devicetable.h>
 
 #include <asm/zorro.h>
 
@@ -142,29 +141,10 @@
      *  Zorro bus
      */
 
-struct zorro_bus {
-    struct list_head devices;		/* list of devices on this bus */
-    unsigned int num_resources;		/* number of resources */
-    struct resource resources[4];	/* address space routed to this bus */
-    struct device dev;
-    char name[10];
-};
-
-extern struct zorro_bus zorro_bus;	/* single Zorro bus */
 extern struct bus_type zorro_bus_type;
 
 
     /*
-     *  Zorro device IDs
-     */
-
-struct zorro_device_id {
-	zorro_id id;			/* Device ID or ZORRO_WILDCARD */
-	unsigned long driver_data;	/* Data private to the driver */
-};
-
-
-    /*
      *  Zorro device drivers
      */
 

include/media/saa7146_vv.h

diff --git a/include/media/saa7146_vv.h b/include/media/saa7146_vv.h
index b9da1f5..4aeff96 100644
--- a/include/media/saa7146_vv.h
+++ b/include/media/saa7146_vv.h
@@ -188,7 +188,6 @@
 void saa7146_dma_free(struct saa7146_dev* dev,struct videobuf_queue *q,
 						struct saa7146_buf *buf);
 
-int saa7146_vv_devinit(struct saa7146_dev *dev);
 int saa7146_vv_init(struct saa7146_dev* dev, struct saa7146_ext_vv *ext_vv);
 int saa7146_vv_release(struct saa7146_dev* dev);
 

include/net/sctp/sm.h

diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 851c813..61d73e3 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -279,6 +279,7 @@
 /* 2nd level prototypes */
 void sctp_generate_t3_rtx_event(unsigned long peer);
 void sctp_generate_heartbeat_event(unsigned long peer);
+void sctp_generate_proto_unreach_event(unsigned long peer);
 
 void sctp_ootb_pkt_free(struct sctp_packet *);
 

include/net/sctp/structs.h

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index ff30177..219043a 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -778,6 +778,7 @@
 			  struct iovec *data);
 void sctp_chunk_free(struct sctp_chunk *);
 void  *sctp_addto_chunk(struct sctp_chunk *, int len, const void *data);
+void  *sctp_addto_chunk_fixed(struct sctp_chunk *, int len, const void *data);
 struct sctp_chunk *sctp_chunkify(struct sk_buff *,
 				 const struct sctp_association *,
 				 struct sock *);
@@ -1009,6 +1010,9 @@
 	/* Heartbeat timer is per destination. */
 	struct timer_list hb_timer;
 
+	/* Timer to handle ICMP proto unreachable envets */
+	struct timer_list proto_unreach_timer;
+
 	/* Since we're using per-destination retransmission timers
 	 * (see above), we're also using per-destination "transmitted"
 	 * queues.  This probably ought to be a private struct

include/net/sock.h

diff --git a/include/net/sock.h b/include/net/sock.h
index b4603cd..1ad6435 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -74,7 +74,7 @@
 					printk(KERN_DEBUG msg); } while (0)
 #else
 /* Validate arguments and do nothing */
-static void inline int __attribute__ ((format (printf, 2, 3)))
+static inline void __attribute__ ((format (printf, 2, 3)))
 SOCK_DEBUG(struct sock *sk, const char *msg, ...)
 {
 }

include/net/tcp.h

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 75be5a2..aa04b9a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1197,30 +1197,15 @@
 extern struct tcp_md5sig_pool * __percpu *tcp_alloc_md5sig_pool(struct sock *);
 extern void			tcp_free_md5sig_pool(void);
 
-extern struct tcp_md5sig_pool	*__tcp_get_md5sig_pool(int cpu);
-extern void			__tcp_put_md5sig_pool(void);
+extern struct tcp_md5sig_pool	*tcp_get_md5sig_pool(void);
+extern void			tcp_put_md5sig_pool(void);
+
 extern int tcp_md5_hash_header(struct tcp_md5sig_pool *, struct tcphdr *);
 extern int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, struct sk_buff *,
 				 unsigned header_len);
 extern int tcp_md5_hash_key(struct tcp_md5sig_pool *hp,
 			    struct tcp_md5sig_key *key);
 
-static inline
-struct tcp_md5sig_pool		*tcp_get_md5sig_pool(void)
-{
-	int cpu = get_cpu();
-	struct tcp_md5sig_pool *ret = __tcp_get_md5sig_pool(cpu);
-	if (!ret)
-		put_cpu();
-	return ret;
-}
-
-static inline void		tcp_put_md5sig_pool(void)
-{
-	__tcp_put_md5sig_pool();
-	put_cpu();
-}
-
 /* write queue abstraction */
 static inline void tcp_write_queue_purge(struct sock *sk)
 {

include/trace/events/lock.h

diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index 5c1dcfc..2821b86 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -35,37 +35,15 @@
 		  __get_str(name))
 );
 
-TRACE_EVENT(lock_release,
-
-	TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
-
-	TP_ARGS(lock, nested, ip),
-
-	TP_STRUCT__entry(
-		__string(name, lock->name)
-		__field(void *, lockdep_addr)
-	),
-
-	TP_fast_assign(
-		__assign_str(name, lock->name);
-		__entry->lockdep_addr = lock;
-	),
-
-	TP_printk("%p %s",
-		  __entry->lockdep_addr, __get_str(name))
-);
-
-#ifdef CONFIG_LOCK_STAT
-
-TRACE_EVENT(lock_contended,
+DECLARE_EVENT_CLASS(lock,
 
 	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
 	TP_ARGS(lock, ip),
 
 	TP_STRUCT__entry(
-		__string(name, lock->name)
-		__field(void *, lockdep_addr)
+		__string(	name, 	lock->name	)
+		__field(	void *, lockdep_addr	)
 	),
 
 	TP_fast_assign(
@@ -73,29 +51,30 @@
 		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%p %s",
-		  __entry->lockdep_addr, __get_str(name))
+	TP_printk("%p %s",  __entry->lockdep_addr, __get_str(name))
 );
 
-TRACE_EVENT(lock_acquired,
-	TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+DEFINE_EVENT(lock, lock_release,
 
-	TP_ARGS(lock, ip, waittime),
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	TP_STRUCT__entry(
-		__string(name, lock->name)
-		__field(s64, wait_nsec)
-		__field(void *, lockdep_addr)
-	),
+	TP_ARGS(lock, ip)
+);
 
-	TP_fast_assign(
-		__assign_str(name, lock->name);
-		__entry->wait_nsec = waittime;
-		__entry->lockdep_addr = lock;
-	),
-	TP_printk("%p %s (%llu ns)", __entry->lockdep_addr,
-		  __get_str(name),
-		  __entry->wait_nsec)
+#ifdef CONFIG_LOCK_STAT
+
+DEFINE_EVENT(lock, lock_contended,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
+);
+
+DEFINE_EVENT(lock, lock_acquired,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
 );
 
 #endif

include/trace/events/module.h

diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 4b0f48b..c7bb2f0 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -51,11 +51,14 @@
 	TP_printk("%s", __get_str(name))
 );
 
+#ifdef CONFIG_MODULE_UNLOAD
+/* trace_module_get/put are only used if CONFIG_MODULE_UNLOAD is defined */
+
 DECLARE_EVENT_CLASS(module_refcnt,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt),
+	TP_ARGS(mod, ip),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	ip		)
@@ -65,7 +68,7 @@
 
 	TP_fast_assign(
 		__entry->ip	= ip;
-		__entry->refcnt	= refcnt;
+		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs);
 		__assign_str(name, mod->name);
 	),
 
@@ -75,17 +78,18 @@
 
 DEFINE_EVENT(module_refcnt, module_get,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt)
+	TP_ARGS(mod, ip)
 );
 
 DEFINE_EVENT(module_refcnt, module_put,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt)
+	TP_ARGS(mod, ip)
 );
+#endif /* CONFIG_MODULE_UNLOAD */
 
 TRACE_EVENT(module_request,
 

include/trace/events/signal.h

diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h
index a510b75..814566c 100644
--- a/include/trace/events/signal.h
+++ b/include/trace/events/signal.h
@@ -100,18 +100,7 @@
 		  __entry->sa_handler, __entry->sa_flags)
 );
 
-/**
- * signal_overflow_fail - called when signal queue is overflow
- * @sig: signal number
- * @group: signal to process group or not (bool)
- * @info: pointer to struct siginfo
- *
- * Kernel fails to generate 'sig' signal with 'info' siginfo, because
- * siginfo queue is overflow, and the signal is dropped.
- * 'group' is not 0 if the signal will be sent to a process group.
- * 'sig' is always one of RT signals.
- */
-TRACE_EVENT(signal_overflow_fail,
+DECLARE_EVENT_CLASS(signal_queue_overflow,
 
 	TP_PROTO(int sig, int group, struct siginfo *info),
 
@@ -135,6 +124,24 @@
 );
 
 /**
+ * signal_overflow_fail - called when signal queue is overflow
+ * @sig: signal number
+ * @group: signal to process group or not (bool)
+ * @info: pointer to struct siginfo
+ *
+ * Kernel fails to generate 'sig' signal with 'info' siginfo, because
+ * siginfo queue is overflow, and the signal is dropped.
+ * 'group' is not 0 if the signal will be sent to a process group.
+ * 'sig' is always one of RT signals.
+ */
+DEFINE_EVENT(signal_queue_overflow, signal_overflow_fail,
+
+	TP_PROTO(int sig, int group, struct siginfo *info),
+
+	TP_ARGS(sig, group, info)
+);
+
+/**
  * signal_lose_info - called when siginfo is lost
  * @sig: signal number
  * @group: signal to process group or not (bool)
@@ -145,28 +152,13 @@
  * 'group' is not 0 if the signal will be sent to a process group.
  * 'sig' is always one of non-RT signals.
  */
-TRACE_EVENT(signal_lose_info,
+DEFINE_EVENT(signal_queue_overflow, signal_lose_info,
 
 	TP_PROTO(int sig, int group, struct siginfo *info),
 
-	TP_ARGS(sig, group, info),
-
-	TP_STRUCT__entry(
-		__field(	int,	sig	)
-		__field(	int,	group	)
-		__field(	int,	errno	)
-		__field(	int,	code	)
-	),
-
-	TP_fast_assign(
-		__entry->sig	= sig;
-		__entry->group	= group;
-		TP_STORE_SIGINFO(__entry, info);
-	),
-
-	TP_printk("sig=%d group=%d errno=%d code=%d",
-		  __entry->sig, __entry->group, __entry->errno, __entry->code)
+	TP_ARGS(sig, group, info)
 );
+
 #endif /* _TRACE_SIGNAL_H */
 
 /* This part must be outside protection */

include/trace/ftrace.h

diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index ea6f9d4..16253db 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -154,9 +154,11 @@
  *
  *	field = (typeof(field))entry;
  *
- *	p = get_cpu_var(ftrace_event_seq);
+ *	p = &get_cpu_var(ftrace_event_seq);
  *	trace_seq_init(p);
- *	ret = trace_seq_printf(s, <TP_printk> "\n");
+ *	ret = trace_seq_printf(s, "%s: ", <call>);
+ *	if (ret)
+ *		ret = trace_seq_printf(s, <TP_printk> "\n");
  *	put_cpu();
  *	if (!ret)
  *		return TRACE_TYPE_PARTIAL_LINE;
@@ -450,38 +452,38 @@
  *
  * static void ftrace_raw_event_<call>(proto)
  * {
+ *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *	struct ring_buffer_event *event;
  *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
  *	struct ring_buffer *buffer;
  *	unsigned long irq_flags;
+ *	int __data_size;
  *	int pc;
  *
  *	local_save_flags(irq_flags);
  *	pc = preempt_count();
  *
+ *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *
  *	event = trace_current_buffer_lock_reserve(&buffer,
  *				  event_<call>.id,
- *				  sizeof(struct ftrace_raw_<call>),
+ *				  sizeof(*entry) + __data_size,
  *				  irq_flags, pc);
  *	if (!event)
  *		return;
  *	entry	= ring_buffer_event_data(event);
  *
- *	<assign>;  <-- Here we assign the entries by the __field and
- *			__array macros.
+ *	{ <assign>; }  <-- Here we assign the entries by the __field and
+ *			   __array macros.
  *
- *	trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ *	if (!filter_current_check_discard(buffer, event_call, entry, event))
+ *		trace_current_buffer_unlock_commit(buffer,
+ *						   event, irq_flags, pc);
  * }
  *
  * static int ftrace_raw_reg_event_<call>(struct ftrace_event_call *unused)
  * {
- *	int ret;
- *
- *	ret = register_trace_<call>(ftrace_raw_event_<call>);
- *	if (!ret)
- *		pr_info("event trace: Could not activate trace point "
- *			"probe to <call>");
- *	return ret;
+ *	return register_trace_<call>(ftrace_raw_event_<call>);
  * }
  *
  * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
@@ -493,6 +495,8 @@
  *	.trace			= ftrace_raw_output_<call>, <-- stage 2
  * };
  *
+ * static const char print_fmt_<call>[] = <TP_printk>;
+ *
  * static struct ftrace_event_call __used
  * __attribute__((__aligned__(4)))
  * __attribute__((section("_ftrace_events"))) event_<call> = {
@@ -501,6 +505,8 @@
  *	.raw_init		= trace_event_raw_init,
  *	.regfunc		= ftrace_reg_event_<call>,
  *	.unregfunc		= ftrace_unreg_event_<call>,
+ *	.print_fmt		= print_fmt_<call>,
+ *	.define_fields		= ftrace_define_fields_<call>,
  * }
  *
  */
@@ -569,7 +575,6 @@
 		return;							\
 	entry	= ring_buffer_event_data(event);			\
 									\
-									\
 	tstruct								\
 									\
 	{ assign; }							\
@@ -758,13 +763,12 @@
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static notrace void							\
 perf_trace_templ_##call(struct ftrace_event_call *event_call,		\
-			    proto)					\
+			struct pt_regs *__regs, proto)			\
 {									\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ftrace_raw_##call *entry;				\
 	u64 __addr = 0, __count = 1;					\
 	unsigned long irq_flags;					\
-	struct pt_regs *__regs;						\
 	int __entry_size;						\
 	int __data_size;						\
 	int rctx;							\
@@ -785,20 +789,22 @@
 									\
 	{ assign; }							\
 									\
-	__regs = &__get_cpu_var(perf_trace_regs);			\
-	perf_fetch_caller_regs(__regs, 2);				\
-									\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
 			       __count, irq_flags, __regs);		\
 }
 
 #undef DEFINE_EVENT
-#define DEFINE_EVENT(template, call, proto, args)		\
-static notrace void perf_trace_##call(proto)			\
-{								\
-	struct ftrace_event_call *event_call = &event_##call;	\
-								\
-	perf_trace_templ_##template(event_call, args);		\
+#define DEFINE_EVENT(template, call, proto, args)			\
+static notrace void perf_trace_##call(proto)				\
+{									\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	struct pt_regs *__regs = &get_cpu_var(perf_trace_regs);		\
+									\
+	perf_fetch_caller_regs(__regs, 1);				\
+									\
+	perf_trace_templ_##template(event_call, __regs, args);		\
+									\
+	put_cpu_var(perf_trace_regs);					\
 }
 
 #undef DEFINE_EVENT_PRINT

ipc/mqueue.c

diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 722b013..59a009d 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -158,7 +158,7 @@
 		 	    u->mq_bytes + mq_bytes >
 			    task_rlimit(p, RLIMIT_MSGQUEUE)) {
 				spin_unlock(&mq_lock);
-				kfree(info->messages);
+				/* mqueue_delete_inode() releases info->messages */
 				goto out_inode;
 			}
 			u->mq_bytes += mq_bytes;

kernel/acct.c

diff --git a/kernel/acct.c b/kernel/acct.c
index 24f8c81..e4c0e1f 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -353,17 +353,18 @@
 
 void acct_exit_ns(struct pid_namespace *ns)
 {
-	struct bsd_acct_struct *acct;
+	struct bsd_acct_struct *acct = ns->bacct;
 
+	if (acct == NULL)
+		return;
+
+	del_timer_sync(&acct->timer);
 	spin_lock(&acct_lock);
-	acct = ns->bacct;
-	if (acct != NULL) {
-		if (acct->file != NULL)
-			acct_file_reopen(acct, NULL, NULL);
-
-		kfree(acct);
-	}
+	if (acct->file != NULL)
+		acct_file_reopen(acct, NULL, NULL);
 	spin_unlock(&acct_lock);
+
+	kfree(acct);
 }
 
 /*

kernel/cgroup.c

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 4a07d05..e9ec642 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1646,7 +1646,9 @@
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
 	char *start;
-	struct dentry *dentry = rcu_dereference(cgrp->dentry);
+	struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
+						      rcu_read_lock_held() ||
+						      cgroup_lock_is_held());
 
 	if (!dentry || cgrp == dummytop) {
 		/*
@@ -1662,13 +1664,17 @@
 	*--start = '\0';
 	for (;;) {
 		int len = dentry->d_name.len;
+
 		if ((start -= len) < buf)
 			return -ENAMETOOLONG;
-		memcpy(start, cgrp->dentry->d_name.name, len);
+		memcpy(start, dentry->d_name.name, len);
 		cgrp = cgrp->parent;
 		if (!cgrp)
 			break;
-		dentry = rcu_dereference(cgrp->dentry);
+
+		dentry = rcu_dereference_check(cgrp->dentry,
+					       rcu_read_lock_held() ||
+					       cgroup_lock_is_held());
 		if (!cgrp->parent)
 			continue;
 		if (--start < buf)
@@ -4429,7 +4435,15 @@
  */
 unsigned short css_id(struct cgroup_subsys_state *css)
 {
-	struct css_id *cssid = rcu_dereference(css->id);
+	struct css_id *cssid;
+
+	/*
+	 * This css_id() can return correct value when somone has refcnt
+	 * on this or this is under rcu_read_lock(). Once css->id is allocated,
+	 * it's unchanged until freed.
+	 */
+	cssid = rcu_dereference_check(css->id,
+			rcu_read_lock_held() || atomic_read(&css->refcnt));
 
 	if (cssid)
 		return cssid->id;
@@ -4439,7 +4453,10 @@
 
 unsigned short css_depth(struct cgroup_subsys_state *css)
 {
-	struct css_id *cssid = rcu_dereference(css->id);
+	struct css_id *cssid;
+
+	cssid = rcu_dereference_check(css->id,
+			rcu_read_lock_held() || atomic_read(&css->refcnt));
 
 	if (cssid)
 		return cssid->depth;
@@ -4447,15 +4464,36 @@
 }
 EXPORT_SYMBOL_GPL(css_depth);
 
+/**
+ *  css_is_ancestor - test "root" css is an ancestor of "child"
+ * @child: the css to be tested.
+ * @root: the css supporsed to be an ancestor of the child.
+ *
+ * Returns true if "root" is an ancestor of "child" in its hierarchy. Because
+ * this function reads css->id, this use rcu_dereference() and rcu_read_lock().
+ * But, considering usual usage, the csses should be valid objects after test.
+ * Assuming that the caller will do some action to the child if this returns
+ * returns true, the caller must take "child";s reference count.
+ * If "child" is valid object and this returns true, "root" is valid, too.
+ */
+
 bool css_is_ancestor(struct cgroup_subsys_state *child,
 		    const struct cgroup_subsys_state *root)
 {
-	struct css_id *child_id = rcu_dereference(child->id);
-	struct css_id *root_id = rcu_dereference(root->id);
+	struct css_id *child_id;
+	struct css_id *root_id;
+	bool ret = true;
 
-	if (!child_id || !root_id || (child_id->depth < root_id->depth))
-		return false;
-	return child_id->stack[root_id->depth] == root_id->id;
+	rcu_read_lock();
+	child_id  = rcu_dereference(child->id);
+	root_id = rcu_dereference(root->id);
+	if (!child_id
+	    || !root_id
+	    || (child_id->depth < root_id->depth)
+	    || (child_id->stack[root_id->depth] != root_id->id))
+		ret = false;
+	rcu_read_unlock();
+	return ret;
 }
 
 static void __free_css_id_cb(struct rcu_head *head)
@@ -4555,13 +4593,13 @@
 {
 	int subsys_id, i, depth = 0;
 	struct cgroup_subsys_state *parent_css, *child_css;
-	struct css_id *child_id, *parent_id = NULL;
+	struct css_id *child_id, *parent_id;
 
 	subsys_id = ss->subsys_id;
 	parent_css = parent->subsys[subsys_id];
 	child_css = child->subsys[subsys_id];
-	depth = css_depth(parent_css) + 1;
 	parent_id = parent_css->id;
+	depth = parent_id->depth;
 
 	child_id = get_new_cssid(ss, depth);
 	if (IS_ERR(child_id))

kernel/cgroup_freezer.c

diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index da5e139..e5c0244 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -205,9 +205,12 @@
 	 * No lock is needed, since the task isn't on tasklist yet,
 	 * so it can't be moved to another cgroup, which means the
 	 * freezer won't be removed and will be valid during this
-	 * function call.
+	 * function call.  Nevertheless, apply RCU read-side critical
+	 * section to suppress RCU lockdep false positives.
 	 */
+	rcu_read_lock();
 	freezer = task_freezer(task);
+	rcu_read_unlock();
 
 	/*
 	 * The root cgroup is non-freezable, so we can skip the

kernel/fork.c

diff --git a/kernel/fork.c b/kernel/fork.c
index 44b0791..4d57d9e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1112,10 +1112,6 @@
 	p->memcg_batch.memcg = NULL;
 #endif
 
-	p->bts = NULL;
-
-	p->stack_start = stack_start;
-
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	sched_fork(p, clone_flags);
 

kernel/hw_breakpoint.c

diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 03808ed..7a56b22 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -40,23 +40,29 @@
 #include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
 
 #include <linux/hw_breakpoint.h>
 
+
 /*
  * Constraints data
  */
 
 /* Number of pinned cpu breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned);
+static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned[TYPE_MAX]);
 
 /* Number of pinned task breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_task_bp_pinned[HBP_NUM]);
+static DEFINE_PER_CPU(unsigned int *, nr_task_bp_pinned[TYPE_MAX]);
 
 /* Number of non-pinned cpu/task breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_bp_flexible);
+static DEFINE_PER_CPU(unsigned int, nr_bp_flexible[TYPE_MAX]);
+
+static int nr_slots[TYPE_MAX];
+
+static int constraints_initialized;
 
 /* Gather the number of total pinned and un-pinned bp in a cpuset */
 struct bp_busy_slots {
@@ -67,16 +73,29 @@
 /* Serialize accesses to the above constraints */
 static DEFINE_MUTEX(nr_bp_mutex);
 
+__weak int hw_breakpoint_weight(struct perf_event *bp)
+{
+	return 1;
+}
+
+static inline enum bp_type_idx find_slot_idx(struct perf_event *bp)
+{
+	if (bp->attr.bp_type & HW_BREAKPOINT_RW)
+		return TYPE_DATA;
+
+	return TYPE_INST;
+}
+
 /*
  * Report the maximum number of pinned breakpoints a task
  * have in this cpu
  */
-static unsigned int max_task_bp_pinned(int cpu)
+static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
 {
 	int i;
-	unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
+	unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
 
-	for (i = HBP_NUM -1; i >= 0; i--) {
+	for (i = nr_slots[type] - 1; i >= 0; i--) {
 		if (tsk_pinned[i] > 0)
 			return i + 1;
 	}
@@ -84,7 +103,7 @@
 	return 0;
 }
 
-static int task_bp_pinned(struct task_struct *tsk)
+static int task_bp_pinned(struct task_struct *tsk, enum bp_type_idx type)
 {
 	struct perf_event_context *ctx = tsk->perf_event_ctxp;
 	struct list_head *list;
@@ -105,7 +124,8 @@
 	 */
 	list_for_each_entry(bp, list, event_entry) {
 		if (bp->attr.type == PERF_TYPE_BREAKPOINT)
-			count++;
+			if (find_slot_idx(bp) == type)
+				count += hw_breakpoint_weight(bp);
 	}
 
 	raw_spin_unlock_irqrestore(&ctx->lock, flags);
@@ -118,18 +138,19 @@
  * a given cpu (cpu > -1) or in all of them (cpu = -1).
  */
 static void
-fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp)
+fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
+		    enum bp_type_idx type)
 {
 	int cpu = bp->cpu;
 	struct task_struct *tsk = bp->ctx->task;
 
 	if (cpu >= 0) {
-		slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu);
+		slots->pinned = per_cpu(nr_cpu_bp_pinned[type], cpu);
 		if (!tsk)
-			slots->pinned += max_task_bp_pinned(cpu);
+			slots->pinned += max_task_bp_pinned(cpu, type);
 		else
-			slots->pinned += task_bp_pinned(tsk);
-		slots->flexible = per_cpu(nr_bp_flexible, cpu);
+			slots->pinned += task_bp_pinned(tsk, type);
+		slots->flexible = per_cpu(nr_bp_flexible[type], cpu);
 
 		return;
 	}
@@ -137,16 +158,16 @@
 	for_each_online_cpu(cpu) {
 		unsigned int nr;
 
-		nr = per_cpu(nr_cpu_bp_pinned, cpu);
+		nr = per_cpu(nr_cpu_bp_pinned[type], cpu);
 		if (!tsk)
-			nr += max_task_bp_pinned(cpu);
+			nr += max_task_bp_pinned(cpu, type);
 		else
-			nr += task_bp_pinned(tsk);
+			nr += task_bp_pinned(tsk, type);
 
 		if (nr > slots->pinned)
 			slots->pinned = nr;
 
-		nr = per_cpu(nr_bp_flexible, cpu);
+		nr = per_cpu(nr_bp_flexible[type], cpu);
 
 		if (nr > slots->flexible)
 			slots->flexible = nr;
@@ -154,31 +175,49 @@
 }
 
 /*
+ * For now, continue to consider flexible as pinned, until we can
+ * ensure no flexible event can ever be scheduled before a pinned event
+ * in a same cpu.
+ */
+static void
+fetch_this_slot(struct bp_busy_slots *slots, int weight)
+{
+	slots->pinned += weight;
+}
+
+/*
  * Add a pinned breakpoint for the given task in our constraint table
  */
-static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable)
+static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable,
+				enum bp_type_idx type, int weight)
 {
 	unsigned int *tsk_pinned;
-	int count = 0;
+	int old_count = 0;
+	int old_idx = 0;
+	int idx = 0;
 
-	count = task_bp_pinned(tsk);
+	old_count = task_bp_pinned(tsk, type);
+	old_idx = old_count - 1;
+	idx = old_idx + weight;
 
-	tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
+	tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
 	if (enable) {
-		tsk_pinned[count]++;
-		if (count > 0)
-			tsk_pinned[count-1]--;
+		tsk_pinned[idx]++;
+		if (old_count > 0)
+			tsk_pinned[old_idx]--;
 	} else {
-		tsk_pinned[count]--;
-		if (count > 0)
-			tsk_pinned[count-1]++;
+		tsk_pinned[idx]--;
+		if (old_count > 0)
+			tsk_pinned[old_idx]++;
 	}
 }
 
 /*
  * Add/remove the given breakpoint in our constraint table
  */
-static void toggle_bp_slot(struct perf_event *bp, bool enable)
+static void
+toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
+	       int weight)
 {
 	int cpu = bp->cpu;
 	struct task_struct *tsk = bp->ctx->task;
@@ -186,20 +225,20 @@
 	/* Pinned counter task profiling */
 	if (tsk) {
 		if (cpu >= 0) {
-			toggle_bp_task_slot(tsk, cpu, enable);
+			toggle_bp_task_slot(tsk, cpu, enable, type, weight);
 			return;
 		}
 
 		for_each_online_cpu(cpu)
-			toggle_bp_task_slot(tsk, cpu, enable);
+			toggle_bp_task_slot(tsk, cpu, enable, type, weight);
 		return;
 	}
 
 	/* Pinned counter cpu profiling */
 	if (enable)
-		per_cpu(nr_cpu_bp_pinned, bp->cpu)++;
+		per_cpu(nr_cpu_bp_pinned[type], bp->cpu) += weight;
 	else
-		per_cpu(nr_cpu_bp_pinned, bp->cpu)--;
+		per_cpu(nr_cpu_bp_pinned[type], bp->cpu) -= weight;
 }
 
 /*
@@ -246,14 +285,29 @@
 static int __reserve_bp_slot(struct perf_event *bp)
 {
 	struct bp_busy_slots slots = {0};
+	enum bp_type_idx type;
+	int weight;
 
-	fetch_bp_busy_slots(&slots, bp);
+	/* We couldn't initialize breakpoint constraints on boot */
+	if (!constraints_initialized)
+		return -ENOMEM;
+
+	/* Basic checks */
+	if (bp->attr.bp_type == HW_BREAKPOINT_EMPTY ||
+	    bp->attr.bp_type == HW_BREAKPOINT_INVALID)
+		return -EINVAL;
+
+	type = find_slot_idx(bp);
+	weight = hw_breakpoint_weight(bp);
+
+	fetch_bp_busy_slots(&slots, bp, type);
+	fetch_this_slot(&slots, weight);
 
 	/* Flexible counters need to keep at least one slot */
-	if (slots.pinned + (!!slots.flexible) == HBP_NUM)
+	if (slots.pinned + (!!slots.flexible) > nr_slots[type])
 		return -ENOSPC;
 
-	toggle_bp_slot(bp, true);
+	toggle_bp_slot(bp, true, type, weight);
 
 	return 0;
 }
@@ -273,7 +327,12 @@
 
 static void __release_bp_slot(struct perf_event *bp)
 {
-	toggle_bp_slot(bp, false);
+	enum bp_type_idx type;
+	int weight;
+
+	type = find_slot_idx(bp);
+	weight = hw_breakpoint_weight(bp);
+	toggle_bp_slot(bp, false, type, weight);
 }
 
 void release_bp_slot(struct perf_event *bp)
@@ -308,6 +367,28 @@
 	return 0;
 }
 
+static int validate_hw_breakpoint(struct perf_event *bp)
+{
+	int ret;
+
+	ret = arch_validate_hwbkpt_settings(bp);
+	if (ret)
+		return ret;
+
+	if (arch_check_bp_in_kernelspace(bp)) {
+		if (bp->attr.exclude_kernel)
+			return -EINVAL;
+		/*
+		 * Don't let unprivileged users set a breakpoint in the trap
+		 * path to avoid trap recursion attacks.
+		 */
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+	}
+
+	return 0;
+}
+
 int register_perf_hw_breakpoint(struct perf_event *bp)
 {
 	int ret;
@@ -316,17 +397,7 @@
 	if (ret)
 		return ret;
 
-	/*
-	 * Ptrace breakpoints can be temporary perf events only
-	 * meant to reserve a slot. In this case, it is created disabled and
-	 * we don't want to check the params right now (as we put a null addr)
-	 * But perf tools create events as disabled and we want to check
-	 * the params for them.
-	 * This is a quick hack that will be removed soon, once we remove
-	 * the tmp breakpoints from ptrace
-	 */
-	if (!bp->attr.disabled || !bp->overflow_handler)
-		ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+	ret = validate_hw_breakpoint(bp);
 
 	/* if arch_validate_hwbkpt_settings() fails then release bp slot */
 	if (ret)
@@ -373,7 +444,7 @@
 	if (attr->disabled)
 		goto end;
 
-	err = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+	err = validate_hw_breakpoint(bp);
 	if (!err)
 		perf_event_enable(bp);
 
@@ -480,7 +551,36 @@
 
 static int __init init_hw_breakpoint(void)
 {
+	unsigned int **task_bp_pinned;
+	int cpu, err_cpu;
+	int i;
+
+	for (i = 0; i < TYPE_MAX; i++)
+		nr_slots[i] = hw_breakpoint_slots(i);
+
+	for_each_possible_cpu(cpu) {
+		for (i = 0; i < TYPE_MAX; i++) {
+			task_bp_pinned = &per_cpu(nr_task_bp_pinned[i], cpu);
+			*task_bp_pinned = kzalloc(sizeof(int) * nr_slots[i],
+						  GFP_KERNEL);
+			if (!*task_bp_pinned)
+				goto err_alloc;
+		}
+	}
+
+	constraints_initialized = 1;
+
 	return register_die_notifier(&hw_breakpoint_exceptions_nb);
+
+ err_alloc:
+	for_each_possible_cpu(err_cpu) {
+		if (err_cpu == cpu)
+			break;
+		for (i = 0; i < TYPE_MAX; i++)
+			kfree(per_cpu(nr_task_bp_pinned[i], cpu));
+	}
+
+	return -ENOMEM;
 }
 core_initcall(init_hw_breakpoint);
 

kernel/kexec.c

diff --git a/kernel/kexec.c b/kernel/kexec.c
index 87ebe8a..474a847 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1134,11 +1134,9 @@
 
 	free_reserved_phys_range(end, crashk_res.end);
 
-	if (start == end) {
-		crashk_res.end = end;
+	if (start == end)
 		release_resource(&crashk_res);
-	} else
-		crashk_res.end = end - 1;
+	crashk_res.end = end - 1;
 
 unlock:
 	mutex_unlock(&kexec_mutex);

kernel/kprobes.c

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 0ed46f3..282035f 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1588,6 +1588,72 @@
 	arch_remove_kprobe(p);
 }
 
+/* Disable one kprobe */
+int __kprobes disable_kprobe(struct kprobe *kp)
+{
+	int ret = 0;
+	struct kprobe *p;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* Check whether specified probe is valid. */
+	p = __get_valid_kprobe(kp);
+	if (unlikely(p == NULL)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* If the probe is already disabled (or gone), just return */
+	if (kprobe_disabled(kp))
+		goto out;
+
+	kp->flags |= KPROBE_FLAG_DISABLED;
+	if (p != kp)
+		/* When kp != p, p is always enabled. */
+		try_to_disable_aggr_kprobe(p);
+
+	if (!kprobes_all_disarmed && kprobe_disabled(p))
+		disarm_kprobe(p);
+out:
+	mutex_unlock(&kprobe_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(disable_kprobe);
+
+/* Enable one kprobe */
+int __kprobes enable_kprobe(struct kprobe *kp)
+{
+	int ret = 0;
+	struct kprobe *p;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* Check whether specified probe is valid. */
+	p = __get_valid_kprobe(kp);
+	if (unlikely(p == NULL)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (kprobe_gone(kp)) {
+		/* This kprobe has gone, we couldn't enable it. */
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (p != kp)
+		kp->flags &= ~KPROBE_FLAG_DISABLED;
+
+	if (!kprobes_all_disarmed && kprobe_disabled(p)) {
+		p->flags &= ~KPROBE_FLAG_DISABLED;
+		arm_kprobe(p);
+	}
+out:
+	mutex_unlock(&kprobe_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(enable_kprobe);
+
 void __kprobes dump_kprobe(struct kprobe *kp)
 {
 	printk(KERN_WARNING "Dumping kprobe:\n");
@@ -1805,72 +1871,6 @@
 	.release        = seq_release,
 };
 
-/* Disable one kprobe */
-int __kprobes disable_kprobe(struct kprobe *kp)
-{
-	int ret = 0;
-	struct kprobe *p;
-
-	mutex_lock(&kprobe_mutex);
-
-	/* Check whether specified probe is valid. */
-	p = __get_valid_kprobe(kp);
-	if (unlikely(p == NULL)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* If the probe is already disabled (or gone), just return */
-	if (kprobe_disabled(kp))
-		goto out;
-
-	kp->flags |= KPROBE_FLAG_DISABLED;
-	if (p != kp)
-		/* When kp != p, p is always enabled. */
-		try_to_disable_aggr_kprobe(p);
-
-	if (!kprobes_all_disarmed && kprobe_disabled(p))
-		disarm_kprobe(p);
-out:
-	mutex_unlock(&kprobe_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(disable_kprobe);
-
-/* Enable one kprobe */
-int __kprobes enable_kprobe(struct kprobe *kp)
-{
-	int ret = 0;
-	struct kprobe *p;
-
-	mutex_lock(&kprobe_mutex);
-
-	/* Check whether specified probe is valid. */
-	p = __get_valid_kprobe(kp);
-	if (unlikely(p == NULL)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (kprobe_gone(kp)) {
-		/* This kprobe has gone, we couldn't enable it. */
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (p != kp)
-		kp->flags &= ~KPROBE_FLAG_DISABLED;
-
-	if (!kprobes_all_disarmed && kprobe_disabled(p)) {
-		p->flags &= ~KPROBE_FLAG_DISABLED;
-		arm_kprobe(p);
-	}
-out:
-	mutex_unlock(&kprobe_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(enable_kprobe);
-
 static void __kprobes arm_all_kprobes(void)
 {
 	struct hlist_head *head;

kernel/lockdep.c

diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 2594e1c..ec21304 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -431,20 +431,7 @@
 /*
  * Various lockdep statistics:
  */
-atomic_t chain_lookup_hits;
-atomic_t chain_lookup_misses;
-atomic_t hardirqs_on_events;
-atomic_t hardirqs_off_events;
-atomic_t redundant_hardirqs_on;
-atomic_t redundant_hardirqs_off;
-atomic_t softirqs_on_events;
-atomic_t softirqs_off_events;
-atomic_t redundant_softirqs_on;
-atomic_t redundant_softirqs_off;
-atomic_t nr_unused_locks;
-atomic_t nr_cyclic_checks;
-atomic_t nr_find_usage_forwards_checks;
-atomic_t nr_find_usage_backwards_checks;
+DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats);
 #endif
 
 /*
@@ -748,7 +735,7 @@
 		return NULL;
 	}
 	class = lock_classes + nr_lock_classes++;
-	debug_atomic_inc(&nr_unused_locks);
+	debug_atomic_inc(nr_unused_locks);
 	class->key = key;
 	class->name = lock->name;
 	class->subclass = subclass;
@@ -818,7 +805,8 @@
  * Add a new dependency to the head of the list:
  */
 static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
-			    struct list_head *head, unsigned long ip, int distance)
+			    struct list_head *head, unsigned long ip,
+			    int distance, struct stack_trace *trace)
 {
 	struct lock_list *entry;
 	/*
@@ -829,11 +817,9 @@
 	if (!entry)
 		return 0;
 
-	if (!save_trace(&entry->trace))
-		return 0;
-
 	entry->class = this;
 	entry->distance = distance;
+	entry->trace = *trace;
 	/*
 	 * Since we never remove from the dependency list, the list can
 	 * be walked lockless by other CPUs, it's only allocation
@@ -1205,7 +1191,7 @@
 {
 	int result;
 
-	debug_atomic_inc(&nr_cyclic_checks);
+	debug_atomic_inc(nr_cyclic_checks);
 
 	result = __bfs_forwards(root, target, class_equal, target_entry);
 
@@ -1242,7 +1228,7 @@
 {
 	int result;
 
-	debug_atomic_inc(&nr_find_usage_forwards_checks);
+	debug_atomic_inc(nr_find_usage_forwards_checks);
 
 	result = __bfs_forwards(root, (void *)bit, usage_match, target_entry);
 
@@ -1265,7 +1251,7 @@
 {
 	int result;
 
-	debug_atomic_inc(&nr_find_usage_backwards_checks);
+	debug_atomic_inc(nr_find_usage_backwards_checks);
 
 	result = __bfs_backwards(root, (void *)bit, usage_match, target_entry);
 
@@ -1635,12 +1621,20 @@
  */
 static int
 check_prev_add(struct task_struct *curr, struct held_lock *prev,
-	       struct held_lock *next, int distance)
+	       struct held_lock *next, int distance, int trylock_loop)
 {
 	struct lock_list *entry;
 	int ret;
 	struct lock_list this;
 	struct lock_list *uninitialized_var(target_entry);
+	/*
+	 * Static variable, serialized by the graph_lock().
+	 *
+	 * We use this static variable to save the stack trace in case
+	 * we call into this function multiple times due to encountering
+	 * trylocks in the held lock stack.
+	 */
+	static struct stack_trace trace;
 
 	/*
 	 * Prove that the new <prev> -> <next> dependency would not
@@ -1688,20 +1682,23 @@
 		}
 	}
 
+	if (!trylock_loop && !save_trace(&trace))
+		return 0;
+
 	/*
 	 * Ok, all validations passed, add the new lock
 	 * to the previous lock's dependency list:
 	 */
 	ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
 			       &hlock_class(prev)->locks_after,
-			       next->acquire_ip, distance);
+			       next->acquire_ip, distance, &trace);
 
 	if (!ret)
 		return 0;
 
 	ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
 			       &hlock_class(next)->locks_before,
-			       next->acquire_ip, distance);
+			       next->acquire_ip, distance, &trace);
 	if (!ret)
 		return 0;
 
@@ -1731,6 +1728,7 @@
 check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
 	int depth = curr->lockdep_depth;
+	int trylock_loop = 0;
 	struct held_lock *hlock;
 
 	/*
@@ -1756,7 +1754,8 @@
 		 * added:
 		 */
 		if (hlock->read != 2) {
-			if (!check_prev_add(curr, hlock, next, distance))
+			if (!check_prev_add(curr, hlock, next,
+						distance, trylock_loop))
 				return 0;
 			/*
 			 * Stop after the first non-trylock entry,
@@ -1779,6 +1778,7 @@
 		if (curr->held_locks[depth].irq_context !=
 				curr->held_locks[depth-1].irq_context)
 			break;
+		trylock_loop = 1;
 	}
 	return 1;
 out_bug:
@@ -1825,7 +1825,7 @@
 	list_for_each_entry(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 cache_hit:
-			debug_atomic_inc(&chain_lookup_hits);
+			debug_atomic_inc(chain_lookup_hits);
 			if (very_verbose(class))
 				printk("\nhash chain already cached, key: "
 					"%016Lx tail class: [%p] %s\n",
@@ -1890,7 +1890,7 @@
 		chain_hlocks[chain->base + j] = class - lock_classes;
 	}
 	list_add_tail_rcu(&chain->entry, hash_head);
-	debug_atomic_inc(&chain_lookup_misses);
+	debug_atomic_inc(chain_lookup_misses);
 	inc_chains();
 
 	return 1;
@@ -2311,7 +2311,12 @@
 		return;
 
 	if (unlikely(curr->hardirqs_enabled)) {
-		debug_atomic_inc(&redundant_hardirqs_on);
+		/*
+		 * Neither irq nor preemption are disabled here
+		 * so this is racy by nature but loosing one hit
+		 * in a stat is not a big deal.
+		 */
+		__debug_atomic_inc(redundant_hardirqs_on);
 		return;
 	}
 	/* we'll do an OFF -> ON transition: */
@@ -2338,7 +2343,7 @@
 
 	curr->hardirq_enable_ip = ip;
 	curr->hardirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(&hardirqs_on_events);
+	debug_atomic_inc(hardirqs_on_events);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
 
@@ -2370,9 +2375,9 @@
 		curr->hardirqs_enabled = 0;
 		curr->hardirq_disable_ip = ip;
 		curr->hardirq_disable_event = ++curr->irq_events;
-		debug_atomic_inc(&hardirqs_off_events);
+		debug_atomic_inc(hardirqs_off_events);
 	} else
-		debug_atomic_inc(&redundant_hardirqs_off);
+		debug_atomic_inc(redundant_hardirqs_off);
 }
 EXPORT_SYMBOL(trace_hardirqs_off_caller);
 
@@ -2396,7 +2401,7 @@
 		return;
 
 	if (curr->softirqs_enabled) {
-		debug_atomic_inc(&redundant_softirqs_on);
+		debug_atomic_inc(redundant_softirqs_on);
 		return;
 	}
 
@@ -2406,7 +2411,7 @@
 	curr->softirqs_enabled = 1;
 	curr->softirq_enable_ip = ip;
 	curr->softirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(&softirqs_on_events);
+	debug_atomic_inc(softirqs_on_events);
 	/*
 	 * We are going to turn softirqs on, so set the
 	 * usage bit for all held locks, if hardirqs are
@@ -2436,10 +2441,10 @@
 		curr->softirqs_enabled = 0;
 		curr->softirq_disable_ip = ip;
 		curr->softirq_disable_event = ++curr->irq_events;
-		debug_atomic_inc(&softirqs_off_events);
+		debug_atomic_inc(softirqs_off_events);
 		DEBUG_LOCKS_WARN_ON(!softirq_count());
 	} else
-		debug_atomic_inc(&redundant_softirqs_off);
+		debug_atomic_inc(redundant_softirqs_off);
 }
 
 static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags)
@@ -2644,7 +2649,7 @@
 			return 0;
 		break;
 	case LOCK_USED:
-		debug_atomic_dec(&nr_unused_locks);
+		debug_atomic_dec(nr_unused_locks);
 		break;
 	default:
 		if (!debug_locks_off_graph_unlock())
@@ -2750,7 +2755,7 @@
 		if (!class)
 			return 0;
 	}
-	debug_atomic_inc((atomic_t *)&class->ops);
+	atomic_inc((atomic_t *)&class->ops);
 	if (very_verbose(class)) {
 		printk("\nacquire class [%p] %s", class->key, class->name);
 		if (class->name_version > 1)
@@ -3227,7 +3232,7 @@
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion = 1;
-	trace_lock_release(lock, nested, ip);
+	trace_lock_release(lock, ip);
 	__lock_release(lock, nested, ip);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
@@ -3380,7 +3385,7 @@
 		hlock->holdtime_stamp = now;
 	}
 
-	trace_lock_acquired(lock, ip, waittime);
+	trace_lock_acquired(lock, ip);
 
 	stats = get_lock_stats(hlock_class(hlock));
 	if (waittime) {
@@ -3801,8 +3806,11 @@
 {
 	struct task_struct *curr = current;
 
+#ifndef CONFIG_PROVE_RCU_REPEATEDLY
 	if (!debug_locks_off())
 		return;
+#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */
+	/* Note: the following can be executed concurrently, so be careful. */
 	printk("\n===================================================\n");
 	printk(  "[ INFO: suspicious rcu_dereference_check() usage. ]\n");
 	printk(  "---------------------------------------------------\n");

kernel/lockdep_internals.h

diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index a2ee95a..4f560cf 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -110,30 +110,60 @@
 #endif
 
 #ifdef CONFIG_DEBUG_LOCKDEP
+
+#include <asm/local.h>
 /*
- * Various lockdep statistics:
+ * Various lockdep statistics.
+ * We want them per cpu as they are often accessed in fast path
+ * and we want to avoid too much cache bouncing.
  */
-extern atomic_t chain_lookup_hits;
-extern atomic_t chain_lookup_misses;
-extern atomic_t hardirqs_on_events;
-extern atomic_t hardirqs_off_events;
-extern atomic_t redundant_hardirqs_on;
-extern atomic_t redundant_hardirqs_off;
-extern atomic_t softirqs_on_events;
-extern atomic_t softirqs_off_events;
-extern atomic_t redundant_softirqs_on;
-extern atomic_t redundant_softirqs_off;
-extern atomic_t nr_unused_locks;
-extern atomic_t nr_cyclic_checks;
-extern atomic_t nr_cyclic_check_recursions;
-extern atomic_t nr_find_usage_forwards_checks;
-extern atomic_t nr_find_usage_forwards_recursions;
-extern atomic_t nr_find_usage_backwards_checks;
-extern atomic_t nr_find_usage_backwards_recursions;
-# define debug_atomic_inc(ptr)		atomic_inc(ptr)
-# define debug_atomic_dec(ptr)		atomic_dec(ptr)
-# define debug_atomic_read(ptr)		atomic_read(ptr)
+struct lockdep_stats {
+	int	chain_lookup_hits;
+	int	chain_lookup_misses;
+	int	hardirqs_on_events;
+	int	hardirqs_off_events;
+	int	redundant_hardirqs_on;
+	int	redundant_hardirqs_off;
+	int	softirqs_on_events;
+	int	softirqs_off_events;
+	int	redundant_softirqs_on;
+	int	redundant_softirqs_off;
+	int	nr_unused_locks;
+	int	nr_cyclic_checks;
+	int	nr_cyclic_check_recursions;
+	int	nr_find_usage_forwards_checks;
+	int	nr_find_usage_forwards_recursions;
+	int	nr_find_usage_backwards_checks;
+	int	nr_find_usage_backwards_recursions;
+};
+
+DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats);
+
+#define __debug_atomic_inc(ptr)					\
+	this_cpu_inc(lockdep_stats.ptr);
+
+#define debug_atomic_inc(ptr)			{		\
+	WARN_ON_ONCE(!irqs_disabled());				\
+	__this_cpu_inc(lockdep_stats.ptr);			\
+}
+
+#define debug_atomic_dec(ptr)			{		\
+	WARN_ON_ONCE(!irqs_disabled());				\
+	__this_cpu_dec(lockdep_stats.ptr);			\
+}
+
+#define debug_atomic_read(ptr)		({				\
+	struct lockdep_stats *__cpu_lockdep_stats;			\
+	unsigned long long __total = 0;					\
+	int __cpu;							\
+	for_each_possible_cpu(__cpu) {					\
+		__cpu_lockdep_stats = &per_cpu(lockdep_stats, __cpu);	\
+		__total += __cpu_lockdep_stats->ptr;			\
+	}								\
+	__total;							\
+})
 #else
+# define __debug_atomic_inc(ptr)	do { } while (0)
 # define debug_atomic_inc(ptr)		do { } while (0)
 # define debug_atomic_dec(ptr)		do { } while (0)
 # define debug_atomic_read(ptr)		0

kernel/lockdep_proc.c

diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index d4aba4f..59b76c8 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -184,34 +184,34 @@
 static void lockdep_stats_debug_show(struct seq_file *m)
 {
 #ifdef CONFIG_DEBUG_LOCKDEP
-	unsigned int hi1 = debug_atomic_read(&hardirqs_on_events),
-		     hi2 = debug_atomic_read(&hardirqs_off_events),
-		     hr1 = debug_atomic_read(&redundant_hardirqs_on),
-		     hr2 = debug_atomic_read(&redundant_hardirqs_off),
-		     si1 = debug_atomic_read(&softirqs_on_events),
-		     si2 = debug_atomic_read(&softirqs_off_events),
-		     sr1 = debug_atomic_read(&redundant_softirqs_on),
-		     sr2 = debug_atomic_read(&redundant_softirqs_off);
+	unsigned long long hi1 = debug_atomic_read(hardirqs_on_events),
+			   hi2 = debug_atomic_read(hardirqs_off_events),
+			   hr1 = debug_atomic_read(redundant_hardirqs_on),
+			   hr2 = debug_atomic_read(redundant_hardirqs_off),
+			   si1 = debug_atomic_read(softirqs_on_events),
+			   si2 = debug_atomic_read(softirqs_off_events),
+			   sr1 = debug_atomic_read(redundant_softirqs_on),
+			   sr2 = debug_atomic_read(redundant_softirqs_off);
 
-	seq_printf(m, " chain lookup misses:           %11u\n",
-		debug_atomic_read(&chain_lookup_misses));
-	seq_printf(m, " chain lookup hits:             %11u\n",
-		debug_atomic_read(&chain_lookup_hits));
-	seq_printf(m, " cyclic checks:                 %11u\n",
-		debug_atomic_read(&nr_cyclic_checks));
-	seq_printf(m, " find-mask forwards checks:     %11u\n",
-		debug_atomic_read(&nr_find_usage_forwards_checks));
-	seq_printf(m, " find-mask backwards checks:    %11u\n",
-		debug_atomic_read(&nr_find_usage_backwards_checks));
+	seq_printf(m, " chain lookup misses:           %11llu\n",
+		debug_atomic_read(chain_lookup_misses));
+	seq_printf(m, " chain lookup hits:             %11llu\n",
+		debug_atomic_read(chain_lookup_hits));
+	seq_printf(m, " cyclic checks:                 %11llu\n",
+		debug_atomic_read(nr_cyclic_checks));
+	seq_printf(m, " find-mask forwards checks:     %11llu\n",
+		debug_atomic_read(nr_find_usage_forwards_checks));
+	seq_printf(m, " find-mask backwards checks:    %11llu\n",
+		debug_atomic_read(nr_find_usage_backwards_checks));
 
-	seq_printf(m, " hardirq on events:             %11u\n", hi1);
-	seq_printf(m, " hardirq off events:            %11u\n", hi2);
-	seq_printf(m, " redundant hardirq ons:         %11u\n", hr1);
-	seq_printf(m, " redundant hardirq offs:        %11u\n", hr2);
-	seq_printf(m, " softirq on events:             %11u\n", si1);
-	seq_printf(m, " softirq off events:            %11u\n", si2);
-	seq_printf(m, " redundant softirq ons:         %11u\n", sr1);
-	seq_printf(m, " redundant softirq offs:        %11u\n", sr2);
+	seq_printf(m, " hardirq on events:             %11llu\n", hi1);
+	seq_printf(m, " hardirq off events:            %11llu\n", hi2);
+	seq_printf(m, " redundant hardirq ons:         %11llu\n", hr1);
+	seq_printf(m, " redundant hardirq offs:        %11llu\n", hr2);
+	seq_printf(m, " softirq on events:             %11llu\n", si1);
+	seq_printf(m, " softirq off events:            %11llu\n", si2);
+	seq_printf(m, " redundant softirq ons:         %11llu\n", sr1);
+	seq_printf(m, " redundant softirq offs:        %11llu\n", sr2);
 #endif
 }
 
@@ -263,7 +263,7 @@
 #endif
 	}
 #ifdef CONFIG_DEBUG_LOCKDEP
-	DEBUG_LOCKS_WARN_ON(debug_atomic_read(&nr_unused_locks) != nr_unused);
+	DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused);
 #endif
 	seq_printf(m, " lock-classes:                  %11lu [max: %lu]\n",
 			nr_lock_classes, MAX_LOCKDEP_KEYS);

kernel/module.c

diff --git a/kernel/module.c b/kernel/module.c
index 0838246..e256458 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -59,8 +59,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
 
-EXPORT_TRACEPOINT_SYMBOL(module_get);
-
 #if 0
 #define DEBUGP printk
 #else
@@ -515,6 +513,9 @@
 static char last_unloaded_module[MODULE_NAME_LEN+1];
 
 #ifdef CONFIG_MODULE_UNLOAD
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
@@ -857,8 +858,7 @@
 		smp_wmb(); /* see comment in module_refcount */
 		__this_cpu_inc(module->refptr->decs);
 
-		trace_module_put(module, _RET_IP_,
-				 __this_cpu_read(module->refptr->decs));
+		trace_module_put(module, _RET_IP_);
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);

kernel/perf_event.c

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 2f3fbf8..a4fa381 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -16,6 +16,7 @@
 #include <linux/file.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
+#include <linux/hash.h>
 #include <linux/sysfs.h>
 #include <linux/dcache.h>
 #include <linux/percpu.h>
@@ -82,14 +83,6 @@
 void __weak hw_perf_disable(void)		{ barrier(); }
 void __weak hw_perf_enable(void)		{ barrier(); }
 
-int __weak
-hw_perf_group_sched_in(struct perf_event *group_leader,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx)
-{
-	return 0;
-}
-
 void __weak perf_event_print_debug(void)	{ }
 
 static DEFINE_PER_CPU(int, perf_disable_count);
@@ -262,6 +255,18 @@
 	event->total_time_running = run_end - event->tstamp_running;
 }
 
+/*
+ * Update total_time_enabled and total_time_running for all events in a group.
+ */
+static void update_group_times(struct perf_event *leader)
+{
+	struct perf_event *event;
+
+	update_event_times(leader);
+	list_for_each_entry(event, &leader->sibling_list, group_entry)
+		update_event_times(event);
+}
+
 static struct list_head *
 ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 {
@@ -315,8 +320,6 @@
 static void
 list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 {
-	struct perf_event *sibling, *tmp;
-
 	if (list_empty(&event->group_entry))
 		return;
 	ctx->nr_events--;
@@ -329,7 +332,7 @@
 	if (event->group_leader != event)
 		event->group_leader->nr_siblings--;
 
-	update_event_times(event);
+	update_group_times(event);
 
 	/*
 	 * If event was in error state, then keep it
@@ -340,6 +343,12 @@
 	 */
 	if (event->state > PERF_EVENT_STATE_OFF)
 		event->state = PERF_EVENT_STATE_OFF;
+}
+
+static void
+perf_destroy_group(struct perf_event *event, struct perf_event_context *ctx)
+{
+	struct perf_event *sibling, *tmp;
 
 	/*
 	 * If this was a group event with sibling events then
@@ -505,18 +514,6 @@
 }
 
 /*
- * Update total_time_enabled and total_time_running for all events in a group.
- */
-static void update_group_times(struct perf_event *leader)
-{
-	struct perf_event *event;
-
-	update_event_times(leader);
-	list_for_each_entry(event, &leader->sibling_list, group_entry)
-		update_event_times(event);
-}
-
-/*
  * Cross CPU call to disable a performance event
  */
 static void __perf_event_disable(void *info)
@@ -640,15 +637,20 @@
 	       struct perf_cpu_context *cpuctx,
 	       struct perf_event_context *ctx)
 {
-	struct perf_event *event, *partial_group;
+	struct perf_event *event, *partial_group = NULL;
+	const struct pmu *pmu = group_event->pmu;
+	bool txn = false;
 	int ret;
 
 	if (group_event->state == PERF_EVENT_STATE_OFF)
 		return 0;
 
-	ret = hw_perf_group_sched_in(group_event, cpuctx, ctx);
-	if (ret)
-		return ret < 0 ? ret : 0;
+	/* Check if group transaction availabe */
+	if (pmu->start_txn)
+		txn = true;
+
+	if (txn)
+		pmu->start_txn(pmu);
 
 	if (event_sched_in(group_event, cpuctx, ctx))
 		return -EAGAIN;
@@ -663,9 +665,19 @@
 		}
 	}
 
-	return 0;
+	if (!txn)
+		return 0;
+
+	ret = pmu->commit_txn(pmu);
+	if (!ret) {
+		pmu->cancel_txn(pmu);
+		return 0;
+	}
 
 group_error:
+	if (txn)
+		pmu->cancel_txn(pmu);
+
 	/*
 	 * Groups can be scheduled in as one unit only, so undo any
 	 * partial group before returning:
@@ -1367,6 +1379,8 @@
 	if (cpuctx->task_ctx == ctx)
 		return;
 
+	perf_disable();
+
 	/*
 	 * We want to keep the following priority order:
 	 * cpu pinned (that don't need to move), task pinned,
@@ -1379,6 +1393,8 @@
 	ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
 
 	cpuctx->task_ctx = ctx;
+
+	perf_enable();
 }
 
 #define MAX_INTERRUPTS (~0ULL)
@@ -1856,9 +1872,30 @@
 {
 	struct perf_event_context *ctx = event->ctx;
 
+	/*
+	 * Remove from the PMU, can't get re-enabled since we got
+	 * here because the last ref went.
+	 */
+	perf_event_disable(event);
+
 	WARN_ON_ONCE(ctx->parent_ctx);
-	mutex_lock(&ctx->mutex);
-	perf_event_remove_from_context(event);
+	/*
+	 * There are two ways this annotation is useful:
+	 *
+	 *  1) there is a lock recursion from perf_event_exit_task
+	 *     see the comment there.
+	 *
+	 *  2) there is a lock-inversion with mmap_sem through
+	 *     perf_event_read_group(), which takes faults while
+	 *     holding ctx->mutex, however this is called after
+	 *     the last filedesc died, so there is no possibility
+	 *     to trigger the AB-BA case.
+	 */
+	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
+	raw_spin_lock_irq(&ctx->lock);
+	list_del_event(event, ctx);
+	perf_destroy_group(event, ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 	mutex_unlock(&ctx->mutex);
 
 	mutex_lock(&event->owner->perf_event_mutex);
@@ -2642,6 +2679,7 @@
 }
 
 static const struct file_operations perf_fops = {
+	.llseek			= no_llseek,
 	.release		= perf_release,
 	.read			= perf_read,
 	.poll			= perf_poll,
@@ -2792,6 +2830,27 @@
 
 
 /*
+ * We assume there is only KVM supporting the callbacks.
+ * Later on, we might change it to a list if there is
+ * another virtualization implementation supporting the callbacks.
+ */
+struct perf_guest_info_callbacks *perf_guest_cbs;
+
+int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
+{
+	perf_guest_cbs = cbs;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks);
+
+int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
+{
+	perf_guest_cbs = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
+
+/*
  * Output
  */
 static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail,
@@ -3743,7 +3802,7 @@
 		.event_id  = {
 			.header = {
 				.type = PERF_RECORD_MMAP,
-				.misc = 0,
+				.misc = PERF_RECORD_MISC_USER,
 				/* .size */
 			},
 			/* .pid */
@@ -3961,36 +4020,6 @@
 	perf_swevent_overflow(event, 0, nmi, data, regs);
 }
 
-static int perf_swevent_is_counting(struct perf_event *event)
-{
-	/*
-	 * The event is active, we're good!
-	 */
-	if (event->state == PERF_EVENT_STATE_ACTIVE)
-		return 1;
-
-	/*
-	 * The event is off/error, not counting.
-	 */
-	if (event->state != PERF_EVENT_STATE_INACTIVE)
-		return 0;
-
-	/*
-	 * The event is inactive, if the context is active
-	 * we're part of a group that didn't make it on the 'pmu',
-	 * not counting.
-	 */
-	if (event->ctx->is_active)
-		return 0;
-
-	/*
-	 * We're inactive and the context is too, this means the
-	 * task is scheduled out, we're counting events that happen
-	 * to us, like migration events.
-	 */
-	return 1;
-}
-
 static int perf_tp_event_match(struct perf_event *event,
 				struct perf_sample_data *data);
 
@@ -4014,12 +4043,6 @@
 				struct perf_sample_data *data,
 				struct pt_regs *regs)
 {
-	if (event->cpu != -1 && event->cpu != smp_processor_id())
-		return 0;
-
-	if (!perf_swevent_is_counting(event))
-		return 0;
-
 	if (event->attr.type != type)
 		return 0;
 
@@ -4036,18 +4059,53 @@
 	return 1;
 }
 
-static void perf_swevent_ctx_event(struct perf_event_context *ctx,
-				     enum perf_type_id type,
-				     u32 event_id, u64 nr, int nmi,
-				     struct perf_sample_data *data,
-				     struct pt_regs *regs)
+static inline u64 swevent_hash(u64 type, u32 event_id)
 {
-	struct perf_event *event;
+	u64 val = event_id | (type << 32);
 
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+	return hash_64(val, SWEVENT_HLIST_BITS);
+}
+
+static struct hlist_head *
+find_swevent_head(struct perf_cpu_context *ctx, u64 type, u32 event_id)
+{
+	u64 hash;
+	struct swevent_hlist *hlist;
+
+	hash = swevent_hash(type, event_id);
+
+	hlist = rcu_dereference(ctx->swevent_hlist);
+	if (!hlist)
+		return NULL;
+
+	return &hlist->heads[hash];
+}
+
+static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
+				    u64 nr, int nmi,
+				    struct perf_sample_data *data,
+				    struct pt_regs *regs)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event *event;
+	struct hlist_node *node;
+	struct hlist_head *head;
+
+	cpuctx = &__get_cpu_var(perf_cpu_context);
+
+	rcu_read_lock();
+
+	head = find_swevent_head(cpuctx, type, event_id);
+
+	if (!head)
+		goto end;
+
+	hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
 		if (perf_swevent_match(event, type, event_id, data, regs))
 			perf_swevent_add(event, nr, nmi, data, regs);
 	}
+end:
+	rcu_read_unlock();
 }
 
 int perf_swevent_get_recursion_context(void)
@@ -4085,27 +4143,6 @@
 }
 EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context);
 
-static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
-				    u64 nr, int nmi,
-				    struct perf_sample_data *data,
-				    struct pt_regs *regs)
-{
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
-
-	cpuctx = &__get_cpu_var(perf_cpu_context);
-	rcu_read_lock();
-	perf_swevent_ctx_event(&cpuctx->ctx, type, event_id,
-				 nr, nmi, data, regs);
-	/*
-	 * doesn't really matter which of the child contexts the
-	 * events ends up in.
-	 */
-	ctx = rcu_dereference(current->perf_event_ctxp);
-	if (ctx)
-		perf_swevent_ctx_event(ctx, type, event_id, nr, nmi, data, regs);
-	rcu_read_unlock();
-}
 
 void __perf_sw_event(u32 event_id, u64 nr, int nmi,
 			    struct pt_regs *regs, u64 addr)
@@ -4131,16 +4168,28 @@
 static int perf_swevent_enable(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct perf_cpu_context *cpuctx;
+	struct hlist_head *head;
+
+	cpuctx = &__get_cpu_var(perf_cpu_context);
 
 	if (hwc->sample_period) {
 		hwc->last_period = hwc->sample_period;
 		perf_swevent_set_period(event);
 	}
+
+	head = find_swevent_head(cpuctx, event->attr.type, event->attr.config);
+	if (WARN_ON_ONCE(!head))
+		return -EINVAL;
+
+	hlist_add_head_rcu(&event->hlist_entry, head);
+
 	return 0;
 }
 
 static void perf_swevent_disable(struct perf_event *event)
 {
+	hlist_del_rcu(&event->hlist_entry);
 }
 
 static const struct pmu perf_ops_generic = {
@@ -4168,15 +4217,8 @@
 	perf_sample_data_init(&data, 0);
 	data.period = event->hw.last_period;
 	regs = get_irq_regs();
-	/*
-	 * In case we exclude kernel IPs or are somehow not in interrupt
-	 * context, provide the next best thing, the user IP.
-	 */
-	if ((event->attr.exclude_kernel || !regs) &&
-			!event->attr.exclude_user)
-		regs = task_pt_regs(current);
 
-	if (regs) {
+	if (regs && !perf_exclude_event(event, regs)) {
 		if (!(event->attr.exclude_idle && current->pid == 0))
 			if (perf_event_overflow(event, 0, &data, regs))
 				ret = HRTIMER_NORESTART;
@@ -4324,6 +4366,105 @@
 	.read		= task_clock_perf_event_read,
 };
 
+static void swevent_hlist_release_rcu(struct rcu_head *rcu_head)
+{
+	struct swevent_hlist *hlist;
+
+	hlist = container_of(rcu_head, struct swevent_hlist, rcu_head);
+	kfree(hlist);
+}
+
+static void swevent_hlist_release(struct perf_cpu_context *cpuctx)
+{
+	struct swevent_hlist *hlist;
+
+	if (!cpuctx->swevent_hlist)
+		return;
+
+	hlist = cpuctx->swevent_hlist;
+	rcu_assign_pointer(cpuctx->swevent_hlist, NULL);
+	call_rcu(&hlist->rcu_head, swevent_hlist_release_rcu);
+}
+
+static void swevent_hlist_put_cpu(struct perf_event *event, int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+
+	mutex_lock(&cpuctx->hlist_mutex);
+
+	if (!--cpuctx->hlist_refcount)
+		swevent_hlist_release(cpuctx);
+
+	mutex_unlock(&cpuctx->hlist_mutex);
+}
+
+static void swevent_hlist_put(struct perf_event *event)
+{
+	int cpu;
+
+	if (event->cpu != -1) {
+		swevent_hlist_put_cpu(event, event->cpu);
+		return;
+	}
+
+	for_each_possible_cpu(cpu)
+		swevent_hlist_put_cpu(event, cpu);
+}
+
+static int swevent_hlist_get_cpu(struct perf_event *event, int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	int err = 0;
+
+	mutex_lock(&cpuctx->hlist_mutex);
+
+	if (!cpuctx->swevent_hlist && cpu_online(cpu)) {
+		struct swevent_hlist *hlist;
+
+		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
+		if (!hlist) {
+			err = -ENOMEM;
+			goto exit;
+		}
+		rcu_assign_pointer(cpuctx->swevent_hlist, hlist);
+	}
+	cpuctx->hlist_refcount++;
+ exit:
+	mutex_unlock(&cpuctx->hlist_mutex);
+
+	return err;
+}
+
+static int swevent_hlist_get(struct perf_event *event)
+{
+	int err;
+	int cpu, failed_cpu;
+
+	if (event->cpu != -1)
+		return swevent_hlist_get_cpu(event, event->cpu);
+
+	get_online_cpus();
+	for_each_possible_cpu(cpu) {
+		err = swevent_hlist_get_cpu(event, cpu);
+		if (err) {
+			failed_cpu = cpu;
+			goto fail;
+		}
+	}
+	put_online_cpus();
+
+	return 0;
+ fail:
+	for_each_possible_cpu(cpu) {
+		if (cpu == failed_cpu)
+			break;
+		swevent_hlist_put_cpu(event, cpu);
+	}
+
+	put_online_cpus();
+	return err;
+}
+
 #ifdef CONFIG_EVENT_TRACING
 
 void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
@@ -4357,10 +4498,13 @@
 static void tp_perf_event_destroy(struct perf_event *event)
 {
 	perf_trace_disable(event->attr.config);
+	swevent_hlist_put(event);
 }
 
 static const struct pmu *tp_perf_event_init(struct perf_event *event)
 {
+	int err;
+
 	/*
 	 * Raw tracepoint data is a severe data leak, only allow root to
 	 * have these.
@@ -4374,6 +4518,11 @@
 		return NULL;
 
 	event->destroy = tp_perf_event_destroy;
+	err = swevent_hlist_get(event);
+	if (err) {
+		perf_trace_disable(event->attr.config);
+		return ERR_PTR(err);
+	}
 
 	return &perf_ops_generic;
 }
@@ -4474,6 +4623,7 @@
 	WARN_ON(event->parent);
 
 	atomic_dec(&perf_swevent_enabled[event_id]);
+	swevent_hlist_put(event);
 }
 
 static const struct pmu *sw_perf_event_init(struct perf_event *event)
@@ -4512,6 +4662,12 @@
 	case PERF_COUNT_SW_ALIGNMENT_FAULTS:
 	case PERF_COUNT_SW_EMULATION_FAULTS:
 		if (!event->parent) {
+			int err;
+
+			err = swevent_hlist_get(event);
+			if (err)
+				return ERR_PTR(err);
+
 			atomic_inc(&perf_swevent_enabled[event_id]);
 			event->destroy = sw_perf_event_destroy;
 		}
@@ -4897,7 +5053,7 @@
 
 err_free_put_context:
 	if (err < 0)
-		kfree(event);
+		free_event(event);
 
 err_put_context:
 	if (err < 0)
@@ -5176,7 +5332,7 @@
 	 *
 	 * But since its the parent context it won't be the same instance.
 	 */
-	mutex_lock_nested(&child_ctx->mutex, SINGLE_DEPTH_NESTING);
+	mutex_lock(&child_ctx->mutex);
 
 again:
 	list_for_each_entry_safe(child_event, tmp, &child_ctx->pinned_groups,
@@ -5384,6 +5540,7 @@
 
 	for_each_possible_cpu(cpu) {
 		cpuctx = &per_cpu(perf_cpu_context, cpu);
+		mutex_init(&cpuctx->hlist_mutex);
 		__perf_event_init_context(&cpuctx->ctx, NULL);
 	}
 }
@@ -5397,6 +5554,16 @@
 	spin_lock(&perf_resource_lock);
 	cpuctx->max_pertask = perf_max_events - perf_reserved_percpu;
 	spin_unlock(&perf_resource_lock);
+
+	mutex_lock(&cpuctx->hlist_mutex);
+	if (cpuctx->hlist_refcount > 0) {
+		struct swevent_hlist *hlist;
+
+		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
+		WARN_ON_ONCE(!hlist);
+		rcu_assign_pointer(cpuctx->swevent_hlist, hlist);
+	}
+	mutex_unlock(&cpuctx->hlist_mutex);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -5416,6 +5583,10 @@
 	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
 	struct perf_event_context *ctx = &cpuctx->ctx;
 
+	mutex_lock(&cpuctx->hlist_mutex);
+	swevent_hlist_release(cpuctx);
+	mutex_unlock(&cpuctx->hlist_mutex);
+
 	mutex_lock(&ctx->mutex);
 	smp_call_function_single(cpu, __perf_event_exit_cpu, NULL, 1);
 	mutex_unlock(&ctx->mutex);

kernel/profile.c

diff --git a/kernel/profile.c b/kernel/profile.c
index a55d3a3..dfadc5b 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -127,8 +127,10 @@
 		return 0;
 
 	prof_buffer = vmalloc(buffer_bytes);
-	if (prof_buffer)
+	if (prof_buffer) {
+		memset(prof_buffer, 0, buffer_bytes);
 		return 0;
+	}
 
 	free_cpumask_var(prof_cpu_mask);
 	return -ENOMEM;

kernel/ptrace.c

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 42ad8ae..6af9cdd 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -14,7 +14,6 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <linux/ptrace.h>
 #include <linux/security.h>
 #include <linux/signal.h>
@@ -76,7 +75,6 @@
 	child->parent = child->real_parent;
 	list_del_init(&child->ptrace_entry);
 
-	arch_ptrace_untrace(child);
 	if (task_is_traced(child))
 		ptrace_untrace(child);
 }
@@ -666,10 +664,6 @@
 	struct task_struct *child;
 	long ret;
 
-	/*
-	 * This lock_kernel fixes a subtle race with suid exec
-	 */
-	lock_kernel();
 	if (request == PTRACE_TRACEME) {
 		ret = ptrace_traceme();
 		if (!ret)
@@ -703,7 +697,6 @@
  out_put_task_struct:
 	put_task_struct(child);
  out:
-	unlock_kernel();
 	return ret;
 }
 
@@ -813,10 +806,6 @@
 	struct task_struct *child;
 	long ret;
 
-	/*
-	 * This lock_kernel fixes a subtle race with suid exec
-	 */
-	lock_kernel();
 	if (request == PTRACE_TRACEME) {
 		ret = ptrace_traceme();
 		goto out;
@@ -846,7 +835,6 @@
  out_put_task_struct:
 	put_task_struct(child);
  out:
-	unlock_kernel();
 	return ret;
 }
 #endif	/* CONFIG_COMPAT */

kernel/rcupdate.c

diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 03a7ea1..72a8dc9 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,7 +44,6 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
-#include <linux/kernel_stat.h>
 #include <linux/hardirq.h>
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -64,9 +63,6 @@
 EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 #endif
 
-int rcu_scheduler_active __read_mostly;
-EXPORT_SYMBOL_GPL(rcu_scheduler_active);
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 int debug_lockdep_rcu_enabled(void)
@@ -97,21 +93,6 @@
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /*
- * This function is invoked towards the end of the scheduler's initialization
- * process.  Before this is called, the idle task might contain
- * RCU read-side critical sections (during which time, this idle
- * task is booting the system).  After this function is called, the
- * idle tasks are prohibited from containing RCU read-side critical
- * sections.
- */
-void rcu_scheduler_starting(void)
-{
-	WARN_ON(num_online_cpus() != 1);
-	WARN_ON(nr_context_switches() > 0);
-	rcu_scheduler_active = 1;
-}
-
-/*
  * Awaken the corresponding synchronize_rcu() instance now that a
  * grace period has elapsed.
  */
@@ -122,3 +103,14 @@
 	rcu = container_of(head, struct rcu_synchronize, head);
 	complete(&rcu->completion);
 }
+
+#ifdef CONFIG_PROVE_RCU
+/*
+ * wrapper function to avoid #include problems.
+ */
+int rcu_my_thread_group_empty(void)
+{
+	return thread_group_empty(current);
+}
+EXPORT_SYMBOL_GPL(rcu_my_thread_group_empty);
+#endif /* #ifdef CONFIG_PROVE_RCU */

kernel/rcutiny.c

diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 9f6d9ff..38729d3 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -44,9 +44,9 @@
 };
 
 /* Definition for rcupdate control block. */
-static struct rcu_ctrlblk rcu_ctrlblk = {
-	.donetail	= &rcu_ctrlblk.rcucblist,
-	.curtail	= &rcu_ctrlblk.rcucblist,
+static struct rcu_ctrlblk rcu_sched_ctrlblk = {
+	.donetail	= &rcu_sched_ctrlblk.rcucblist,
+	.curtail	= &rcu_sched_ctrlblk.rcucblist,
 };
 
 static struct rcu_ctrlblk rcu_bh_ctrlblk = {
@@ -54,6 +54,11 @@
 	.curtail	= &rcu_bh_ctrlblk.rcucblist,
 };
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 #ifdef CONFIG_NO_HZ
 
 static long rcu_dynticks_nesting = 1;
@@ -108,7 +113,8 @@
  */
 void rcu_sched_qs(int cpu)
 {
-	if (rcu_qsctr_help(&rcu_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk))
+	if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
+	    rcu_qsctr_help(&rcu_bh_ctrlblk))
 		raise_softirq(RCU_SOFTIRQ);
 }
 
@@ -173,7 +179,7 @@
  */
 static void rcu_process_callbacks(struct softirq_action *unused)
 {
-	__rcu_process_callbacks(&rcu_ctrlblk);
+	__rcu_process_callbacks(&rcu_sched_ctrlblk);
 	__rcu_process_callbacks(&rcu_bh_ctrlblk);
 }
 
@@ -187,7 +193,8 @@
  *
  * Cool, huh?  (Due to Josh Triplett.)
  *
- * But we want to make this a static inline later.
+ * But we want to make this a static inline later.  The cond_resched()
+ * currently makes this problematic.
  */
 void synchronize_sched(void)
 {
@@ -195,12 +202,6 @@
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
-void synchronize_rcu_bh(void)
-{
-	synchronize_sched();
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
-
 /*
  * Helper function for call_rcu() and call_rcu_bh().
  */
@@ -226,7 +227,7 @@
  */
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_ctrlblk);
+	__call_rcu(head, func, &rcu_sched_ctrlblk);
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
@@ -244,11 +245,13 @@
 {
 	struct rcu_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
@@ -256,11 +259,13 @@
 {
 	struct rcu_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_bh(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_bh);
 
@@ -268,11 +273,13 @@
 {
 	struct rcu_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_sched(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 
@@ -280,3 +287,5 @@
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 }
+
+#include "rcutiny_plugin.h"

kernel/rcutiny_plugin.h

diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
new file mode 100644
index 0000000..d223a92bc
--- /dev/null
+++ b/kernel/rcutiny_plugin.h
@@ -0,0 +1,39 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ * Internal non-public definitions that provide either classic
+ * or preemptable semantics.
+ *
+ * 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 IBM Corporation, 2009
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+#include <linux/kernel_stat.h>
+
+/*
+ * During boot, we forgive RCU lockdep issues.  After this function is
+ * invoked, we start taking RCU lockdep issues seriously.
+ */
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
+
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

kernel/rcutorture.c

diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 2b676f3..6535ac8 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -464,9 +464,11 @@
 {
 	struct rcu_bh_torture_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	call_rcu_bh(&rcu.head, rcu_bh_torture_wakeme_after_cb);
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 
 static struct rcu_torture_ops rcu_bh_ops = {

kernel/rcutree.c

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 3ec8160..d443734 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -46,6 +46,7 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/time.h>
+#include <linux/kernel_stat.h>
 
 #include "rcutree.h"
 
@@ -53,8 +54,8 @@
 
 static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
 
-#define RCU_STATE_INITIALIZER(name) { \
-	.level = { &name.node[0] }, \
+#define RCU_STATE_INITIALIZER(structname) { \
+	.level = { &structname.node[0] }, \
 	.levelcnt = { \
 		NUM_RCU_LVL_0,  /* root of hierarchy. */ \
 		NUM_RCU_LVL_1, \
@@ -65,13 +66,14 @@
 	.signaled = RCU_GP_IDLE, \
 	.gpnum = -300, \
 	.completed = -300, \
-	.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&name.onofflock), \
+	.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname.onofflock), \
 	.orphan_cbs_list = NULL, \
-	.orphan_cbs_tail = &name.orphan_cbs_list, \
+	.orphan_cbs_tail = &structname.orphan_cbs_list, \
 	.orphan_qlen = 0, \
-	.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&name.fqslock), \
+	.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname.fqslock), \
 	.n_force_qs = 0, \
 	.n_force_qs_ngp = 0, \
+	.name = #structname, \
 }
 
 struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched_state);
@@ -80,6 +82,9 @@
 struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+
 /*
  * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
  * permit this function to be invoked without holding the root rcu_node
@@ -97,25 +102,32 @@
  */
 void rcu_sched_qs(int cpu)
 {
-	struct rcu_data *rdp;
+	struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
 
-	rdp = &per_cpu(rcu_sched_data, cpu);
 	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
-	rcu_preempt_note_context_switch(cpu);
 }
 
 void rcu_bh_qs(int cpu)
 {
-	struct rcu_data *rdp;
+	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
 
-	rdp = &per_cpu(rcu_bh_data, cpu);
 	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
 }
 
+/*
+ * Note a context switch.  This is a quiescent state for RCU-sched,
+ * and requires special handling for preemptible RCU.
+ */
+void rcu_note_context_switch(int cpu)
+{
+	rcu_sched_qs(cpu);
+	rcu_preempt_note_context_switch(cpu);
+}
+
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = 1,
@@ -438,6 +450,8 @@
 
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 
+int rcu_cpu_stall_panicking __read_mostly;
+
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
 	rsp->gp_start = jiffies;
@@ -470,7 +484,8 @@
 
 	/* OK, time to rat on our buddy... */
 
-	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
+	printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks: {",
+	       rsp->name);
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rcu_print_task_stall(rnp);
@@ -481,7 +496,7 @@
 			if (rnp->qsmask & (1UL << cpu))
 				printk(" %d", rnp->grplo + cpu);
 	}
-	printk(" (detected by %d, t=%ld jiffies)\n",
+	printk("} (detected by %d, t=%ld jiffies)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start));
 	trigger_all_cpu_backtrace();
 
@@ -497,8 +512,8 @@
 	unsigned long flags;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
-			smp_processor_id(), jiffies - rsp->gp_start);
+	printk(KERN_ERR "INFO: %s detected stall on CPU %d (t=%lu jiffies)\n",
+	       rsp->name, smp_processor_id(), jiffies - rsp->gp_start);
 	trigger_all_cpu_backtrace();
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -515,6 +530,8 @@
 	long delta;
 	struct rcu_node *rnp;
 
+	if (rcu_cpu_stall_panicking)
+		return;
 	delta = jiffies - rsp->jiffies_stall;
 	rnp = rdp->mynode;
 	if ((rnp->qsmask & rdp->grpmask) && delta >= 0) {
@@ -529,6 +546,21 @@
 	}
 }
 
+static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
+{
+	rcu_cpu_stall_panicking = 1;
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block rcu_panic_block = {
+	.notifier_call = rcu_panic,
+};
+
+static void __init check_cpu_stall_init(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
+}
+
 #else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
@@ -539,6 +571,10 @@
 {
 }
 
+static void __init check_cpu_stall_init(void)
+{
+}
+
 #endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
@@ -1125,8 +1161,6 @@
  */
 void rcu_check_callbacks(int cpu, int user)
 {
-	if (!rcu_pending(cpu))
-		return; /* if nothing for RCU to do. */
 	if (user ||
 	    (idle_cpu(cpu) && rcu_scheduler_active &&
 	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
@@ -1158,7 +1192,8 @@
 		rcu_bh_qs(cpu);
 	}
 	rcu_preempt_check_callbacks(cpu);
-	raise_softirq(RCU_SOFTIRQ);
+	if (rcu_pending(cpu))
+		raise_softirq(RCU_SOFTIRQ);
 }
 
 #ifdef CONFIG_SMP
@@ -1236,11 +1271,11 @@
 		break; /* grace period idle or initializing, ignore. */
 
 	case RCU_SAVE_DYNTICK:
-
-		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
 		if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK)
 			break; /* So gcc recognizes the dead code. */
 
+		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
+
 		/* Record dyntick-idle state. */
 		force_qs_rnp(rsp, dyntick_save_progress_counter);
 		raw_spin_lock(&rnp->lock);  /* irqs already disabled */
@@ -1449,11 +1484,13 @@
 	if (rcu_blocking_is_gp())
 		return;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_sched(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
@@ -1473,11 +1510,13 @@
 	if (rcu_blocking_is_gp())
 		return;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_bh(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
 
@@ -1498,8 +1537,20 @@
 	check_cpu_stall(rsp, rdp);
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
-	if (rdp->qs_pending) {
+	if (rdp->qs_pending && !rdp->passed_quiesc) {
+
+		/*
+		 * If force_quiescent_state() coming soon and this CPU
+		 * needs a quiescent state, and this is either RCU-sched
+		 * or RCU-bh, force a local reschedule.
+		 */
 		rdp->n_rp_qs_pending++;
+		if (!rdp->preemptable &&
+		    ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1,
+				 jiffies))
+			set_need_resched();
+	} else if (rdp->qs_pending && rdp->passed_quiesc) {
+		rdp->n_rp_report_qs++;
 		return 1;
 	}
 
@@ -1767,6 +1818,21 @@
 }
 
 /*
+ * This function is invoked towards the end of the scheduler's initialization
+ * process.  Before this is called, the idle task might contain
+ * RCU read-side critical sections (during which time, this idle
+ * task is booting the system).  After this function is called, the
+ * idle tasks are prohibited from containing RCU read-side critical
+ * sections.  This function also enables RCU lockdep checking.
+ */
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
+
+/*
  * Compute the per-level fanout, either using the exact fanout specified
  * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
  */
@@ -1849,6 +1915,14 @@
 			INIT_LIST_HEAD(&rnp->blocked_tasks[3]);
 		}
 	}
+
+	rnp = rsp->level[NUM_RCU_LVLS - 1];
+	for_each_possible_cpu(i) {
+		while (i > rnp->grphi)
+			rnp++;
+		rsp->rda[i]->mynode = rnp;
+		rcu_boot_init_percpu_data(i, rsp);
+	}
 }
 
 /*
@@ -1859,19 +1933,11 @@
 #define RCU_INIT_FLAVOR(rsp, rcu_data) \
 do { \
 	int i; \
-	int j; \
-	struct rcu_node *rnp; \
 	\
-	rcu_init_one(rsp); \
-	rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \
-	j = 0; \
 	for_each_possible_cpu(i) { \
-		if (i > rnp[j].grphi) \
-			j++; \
-		per_cpu(rcu_data, i).mynode = &rnp[j]; \
 		(rsp)->rda[i] = &per_cpu(rcu_data, i); \
-		rcu_boot_init_percpu_data(i, rsp); \
 	} \
+	rcu_init_one(rsp); \
 } while (0)
 
 void __init rcu_init(void)
@@ -1879,12 +1945,6 @@
 	int cpu;
 
 	rcu_bootup_announce();
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#if NUM_RCU_LVL_4 != 0
-	printk(KERN_INFO "Experimental four-level hierarchy is enabled.\n");
-#endif /* #if NUM_RCU_LVL_4 != 0 */
 	RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
 	RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
 	__rcu_init_preempt();
@@ -1898,6 +1958,7 @@
 	cpu_notifier(rcu_cpu_notify, 0);
 	for_each_online_cpu(cpu)
 		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
+	check_cpu_stall_init();
 }
 
 #include "rcutree_plugin.h"

kernel/rcutree.h

diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 4a525a3..14c040b 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -223,6 +223,7 @@
 	/* 5) __rcu_pending() statistics. */
 	unsigned long n_rcu_pending;	/* rcu_pending() calls since boot. */
 	unsigned long n_rp_qs_pending;
+	unsigned long n_rp_report_qs;
 	unsigned long n_rp_cb_ready;
 	unsigned long n_rp_cpu_needs_gp;
 	unsigned long n_rp_gp_completed;
@@ -326,6 +327,7 @@
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+	char *name;				/* Name of structure. */
 };
 
 /* Return values for rcu_preempt_offline_tasks(). */

kernel/rcutree_plugin.h

diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 79b53bd..0e4f420 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -26,6 +26,45 @@
 
 #include <linux/delay.h>
 
+/*
+ * Check the RCU kernel configuration parameters and print informative
+ * messages about anything out of the ordinary.  If you like #ifdef, you
+ * will love this function.
+ */
+static void __init rcu_bootup_announce_oddness(void)
+{
+#ifdef CONFIG_RCU_TRACE
+	printk(KERN_INFO "\tRCU debugfs-based tracing is enabled.\n");
+#endif
+#if (defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || (!defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)
+	printk(KERN_INFO "\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
+	       CONFIG_RCU_FANOUT);
+#endif
+#ifdef CONFIG_RCU_FANOUT_EXACT
+	printk(KERN_INFO "\tHierarchical RCU autobalancing is disabled.\n");
+#endif
+#ifdef CONFIG_RCU_FAST_NO_HZ
+	printk(KERN_INFO
+	       "\tRCU dyntick-idle grace-period acceleration is enabled.\n");
+#endif
+#ifdef CONFIG_PROVE_RCU
+	printk(KERN_INFO "\tRCU lockdep checking is enabled.\n");
+#endif
+#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
+	printk(KERN_INFO "\tRCU torture testing starts during boot.\n");
+#endif
+#ifndef CONFIG_RCU_CPU_STALL_DETECTOR
+	printk(KERN_INFO
+	       "\tRCU-based detection of stalled CPUs is disabled.\n");
+#endif
+#ifndef CONFIG_RCU_CPU_STALL_VERBOSE
+	printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n");
+#endif
+#if NUM_RCU_LVL_4 != 0
+	printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n");
+#endif
+}
+
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
@@ -38,8 +77,8 @@
  */
 static void __init rcu_bootup_announce(void)
 {
-	printk(KERN_INFO
-	       "Experimental preemptable hierarchical RCU implementation.\n");
+	printk(KERN_INFO "Preemptable hierarchical RCU implementation.\n");
+	rcu_bootup_announce_oddness();
 }
 
 /*
@@ -75,13 +114,19 @@
  * that this just means that the task currently running on the CPU is
  * not in a quiescent state.  There might be any number of tasks blocked
  * while in an RCU read-side critical section.
+ *
+ * Unlike the other rcu_*_qs() functions, callers to this function
+ * must disable irqs in order to protect the assignment to
+ * ->rcu_read_unlock_special.
  */
 static void rcu_preempt_qs(int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
+
 	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
+	current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
 }
 
 /*
@@ -144,9 +189,8 @@
 	 * grace period, then the fact that the task has been enqueued
 	 * means that we continue to block the current grace period.
 	 */
-	rcu_preempt_qs(cpu);
 	local_irq_save(flags);
-	t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+	rcu_preempt_qs(cpu);
 	local_irq_restore(flags);
 }
 
@@ -236,7 +280,6 @@
 	 */
 	special = t->rcu_read_unlock_special;
 	if (special & RCU_READ_UNLOCK_NEED_QS) {
-		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
 		rcu_preempt_qs(smp_processor_id());
 	}
 
@@ -473,7 +516,6 @@
 	struct task_struct *t = current;
 
 	if (t->rcu_read_lock_nesting == 0) {
-		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
 		rcu_preempt_qs(cpu);
 		return;
 	}
@@ -515,11 +557,13 @@
 	if (!rcu_scheduler_active)
 		return;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
@@ -754,6 +798,7 @@
 static void __init rcu_bootup_announce(void)
 {
 	printk(KERN_INFO "Hierarchical RCU implementation.\n");
+	rcu_bootup_announce_oddness();
 }
 
 /*
@@ -1008,6 +1053,8 @@
 int rcu_needs_cpu(int cpu)
 {
 	int c = 0;
+	int snap;
+	int snap_nmi;
 	int thatcpu;
 
 	/* Check for being in the holdoff period. */
@@ -1015,12 +1062,18 @@
 		return rcu_needs_cpu_quick_check(cpu);
 
 	/* Don't bother unless we are the last non-dyntick-idle CPU. */
-	for_each_cpu_not(thatcpu, nohz_cpu_mask)
-		if (thatcpu != cpu) {
+	for_each_online_cpu(thatcpu) {
+		if (thatcpu == cpu)
+			continue;
+		snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
+		snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
+		smp_mb(); /* Order sampling of snap with end of grace period. */
+		if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
 			per_cpu(rcu_dyntick_drain, cpu) = 0;
 			per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
 			return rcu_needs_cpu_quick_check(cpu);
 		}
+	}
 
 	/* Check and update the rcu_dyntick_drain sequencing. */
 	if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {

kernel/rcutree_trace.c

diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index d45db2e..36c95b4 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -241,11 +241,13 @@
 static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
 {
 	seq_printf(m, "%3d%cnp=%ld "
-		   "qsp=%ld cbr=%ld cng=%ld gpc=%ld gps=%ld nf=%ld nn=%ld\n",
+		   "qsp=%ld rpq=%ld cbr=%ld cng=%ld "
+		   "gpc=%ld gps=%ld nf=%ld nn=%ld\n",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   rdp->n_rcu_pending,
 		   rdp->n_rp_qs_pending,
+		   rdp->n_rp_report_qs,
 		   rdp->n_rp_cb_ready,
 		   rdp->n_rp_cpu_needs_gp,
 		   rdp->n_rp_gp_completed,

kernel/sched.c

diff --git a/kernel/sched.c b/kernel/sched.c
index b531d79..1d93cd0 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -323,6 +323,15 @@
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
 static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 {
+	/*
+	 * Strictly speaking this rcu_read_lock() is not needed since the
+	 * task_group is tied to the cgroup, which in turn can never go away
+	 * as long as there are tasks attached to it.
+	 *
+	 * However since task_group() uses task_subsys_state() which is an
+	 * rcu_dereference() user, this quiets CONFIG_PROVE_RCU.
+	 */
+	rcu_read_lock();
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
 	p->se.parent = task_group(p)->se[cpu];
@@ -332,6 +341,7 @@
 	p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
 	p->rt.parent = task_group(p)->rt_se[cpu];
 #endif
+	rcu_read_unlock();
 }
 
 #else
@@ -2058,49 +2068,6 @@
 }
 
 /*
- * wait_task_context_switch -	wait for a thread to complete at least one
- *				context switch.
- *
- * @p must not be current.
- */
-void wait_task_context_switch(struct task_struct *p)
-{
-	unsigned long nvcsw, nivcsw, flags;
-	int running;
-	struct rq *rq;
-
-	nvcsw	= p->nvcsw;
-	nivcsw	= p->nivcsw;
-	for (;;) {
-		/*
-		 * The runqueue is assigned before the actual context
-		 * switch. We need to take the runqueue lock.
-		 *
-		 * We could check initially without the lock but it is
-		 * very likely that we need to take the lock in every
-		 * iteration.
-		 */
-		rq = task_rq_lock(p, &flags);
-		running = task_running(rq, p);
-		task_rq_unlock(rq, &flags);
-
-		if (likely(!running))
-			break;
-		/*
-		 * The switch count is incremented before the actual
-		 * context switch. We thus wait for two switches to be
-		 * sure at least one completed.
-		 */
-		if ((p->nvcsw - nvcsw) > 1)
-			break;
-		if ((p->nivcsw - nivcsw) > 1)
-			break;
-
-		cpu_relax();
-	}
-}
-
-/*
  * wait_task_inactive - wait for a thread to unschedule.
  *
  * If @match_state is nonzero, it's the @p->state value just checked and
@@ -3641,7 +3608,7 @@
 	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
-	rcu_sched_qs(cpu);
+	rcu_note_context_switch(cpu);
 	prev = rq->curr;
 	switch_count = &prev->nivcsw;
 
@@ -3724,7 +3691,7 @@
 	 * the mutex owner just released it and exited.
 	 */
 	if (probe_kernel_address(&owner->cpu, cpu))
-		goto out;
+		return 0;
 #else
 	cpu = owner->cpu;
 #endif
@@ -3734,14 +3701,14 @@
 	 * the cpu field may no longer be valid.
 	 */
 	if (cpu >= nr_cpumask_bits)
-		goto out;
+		return 0;
 
 	/*
 	 * We need to validate that we can do a
 	 * get_cpu() and that we have the percpu area.
 	 */
 	if (!cpu_online(cpu))
-		goto out;
+		return 0;
 
 	rq = cpu_rq(cpu);
 
@@ -3760,7 +3727,7 @@
 
 		cpu_relax();
 	}
-out:
+
 	return 1;
 }
 #endif

kernel/sched_debug.c

diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 9cf1baf..87a330a 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -114,7 +114,9 @@
 	{
 		char path[64];
 
+		rcu_read_lock();
 		cgroup_path(task_group(p)->css.cgroup, path, sizeof(path));
+		rcu_read_unlock();
 		SEQ_printf(m, " %s", path);
 	}
 #endif

kernel/softirq.c

diff --git a/kernel/softirq.c b/kernel/softirq.c
index 7c1a67e..0db913a 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -716,7 +716,7 @@
 			preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
-			rcu_sched_qs((long)__bind_cpu);
+			rcu_note_context_switch((long)__bind_cpu);
 		}
 		preempt_enable();
 		set_current_state(TASK_INTERRUPTIBLE);

kernel/trace/Kconfig

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 13e13d4..8b1797c 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -44,9 +44,6 @@
 	help
 	  See Documentation/trace/ftrace-design.txt
 
-config HAVE_HW_BRANCH_TRACER
-	bool
-
 config HAVE_SYSCALL_TRACEPOINTS
 	bool
 	help
@@ -374,14 +371,6 @@
 
 	  Say N if unsure.
 
-config HW_BRANCH_TRACER
-	depends on HAVE_HW_BRANCH_TRACER
-	bool "Trace hw branches"
-	select GENERIC_TRACER
-	help
-	  This tracer records all branches on the system in a circular
-	  buffer, giving access to the last N branches for each cpu.
-
 config KMEMTRACE
 	bool "Trace SLAB allocations"
 	select GENERIC_TRACER

kernel/trace/Makefile

diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 78edc64..ffb1a5b 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -41,7 +41,6 @@
 obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
-obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
 obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o

kernel/trace/ring_buffer.c

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 41ca394..5885cdf 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -319,6 +319,11 @@
 #define TS_MASK		((1ULL << TS_SHIFT) - 1)
 #define TS_DELTA_TEST	(~TS_MASK)
 
+/* Flag when events were overwritten */
+#define RB_MISSED_EVENTS	(1 << 31)
+/* Missed count stored at end */
+#define RB_MISSED_STORED	(1 << 30)
+
 struct buffer_data_page {
 	u64		 time_stamp;	/* page time stamp */
 	local_t		 commit;	/* write committed index */
@@ -338,6 +343,7 @@
 	local_t		 write;		/* index for next write */
 	unsigned	 read;		/* index for next read */
 	local_t		 entries;	/* entries on this page */
+	unsigned long	 real_end;	/* real end of data */
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
@@ -417,6 +423,12 @@
 			       (unsigned int)sizeof(field.commit),
 			       (unsigned int)is_signed_type(long));
 
+	ret = trace_seq_printf(s, "\tfield: int overwrite;\t"
+			       "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			       (unsigned int)offsetof(typeof(field), commit),
+			       1,
+			       (unsigned int)is_signed_type(long));
+
 	ret = trace_seq_printf(s, "\tfield: char data;\t"
 			       "offset:%u;\tsize:%u;\tsigned:%u;\n",
 			       (unsigned int)offsetof(typeof(field), data),
@@ -440,6 +452,8 @@
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
 	struct buffer_page		*reader_page;
+	unsigned long			lost_events;
+	unsigned long			last_overrun;
 	local_t				commit_overrun;
 	local_t				overrun;
 	local_t				entries;
@@ -1762,6 +1776,13 @@
 	kmemcheck_annotate_bitfield(event, bitfield);
 
 	/*
+	 * Save the original length to the meta data.
+	 * This will be used by the reader to add lost event
+	 * counter.
+	 */
+	tail_page->real_end = tail;
+
+	/*
 	 * If this event is bigger than the minimum size, then
 	 * we need to be careful that we don't subtract the
 	 * write counter enough to allow another writer to slip
@@ -2838,6 +2859,7 @@
 rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = NULL;
+	unsigned long overwrite;
 	unsigned long flags;
 	int nr_loops = 0;
 	int ret;
@@ -2879,6 +2901,7 @@
 	local_set(&cpu_buffer->reader_page->write, 0);
 	local_set(&cpu_buffer->reader_page->entries, 0);
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
+	cpu_buffer->reader_page->real_end = 0;
 
  spin:
 	/*
@@ -2899,6 +2922,18 @@
 	rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
 
 	/*
+	 * We want to make sure we read the overruns after we set up our
+	 * pointers to the next object. The writer side does a
+	 * cmpxchg to cross pages which acts as the mb on the writer
+	 * side. Note, the reader will constantly fail the swap
+	 * while the writer is updating the pointers, so this
+	 * guarantees that the overwrite recorded here is the one we
+	 * want to compare with the last_overrun.
+	 */
+	smp_mb();
+	overwrite = local_read(&(cpu_buffer->overrun));
+
+	/*
 	 * Here's the tricky part.
 	 *
 	 * We need to move the pointer past the header page.
@@ -2929,6 +2964,11 @@
 	cpu_buffer->reader_page = reader;
 	rb_reset_reader_page(cpu_buffer);
 
+	if (overwrite != cpu_buffer->last_overrun) {
+		cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun;
+		cpu_buffer->last_overrun = overwrite;
+	}
+
 	goto again;
 
  out:
@@ -3005,8 +3045,14 @@
 		rb_advance_iter(iter);
 }
 
+static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	return cpu_buffer->lost_events;
+}
+
 static struct ring_buffer_event *
-rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
+rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
+	       unsigned long *lost_events)
 {
 	struct ring_buffer_event *event;
 	struct buffer_page *reader;
@@ -3058,6 +3104,8 @@
 			ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
 							 cpu_buffer->cpu, ts);
 		}
+		if (lost_events)
+			*lost_events = rb_lost_events(cpu_buffer);
 		return event;
 
 	default:
@@ -3168,12 +3216,14 @@
  * @buffer: The ring buffer to read
  * @cpu: The cpu to peak at
  * @ts: The timestamp counter of this event.
+ * @lost_events: a variable to store if events were lost (may be NULL)
  *
  * This will return the event that will be read next, but does
  * not consume the data.
  */
 struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
+		 unsigned long *lost_events)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
@@ -3188,7 +3238,7 @@
 	local_irq_save(flags);
 	if (dolock)
 		spin_lock(&cpu_buffer->reader_lock);
-	event = rb_buffer_peek(cpu_buffer, ts);
+	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
 	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		rb_advance_reader(cpu_buffer);
 	if (dolock)
@@ -3230,13 +3280,17 @@
 /**
  * ring_buffer_consume - return an event and consume it
  * @buffer: The ring buffer to get the next event from
+ * @cpu: the cpu to read the buffer from
+ * @ts: a variable to store the timestamp (may be NULL)
+ * @lost_events: a variable to store if events were lost (may be NULL)
  *
  * Returns the next event in the ring buffer, and that event is consumed.
  * Meaning, that sequential reads will keep returning a different event,
  * and eventually empty the ring buffer if the producer is slower.
  */
 struct ring_buffer_event *
-ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
+		    unsigned long *lost_events)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event = NULL;
@@ -3257,9 +3311,11 @@
 	if (dolock)
 		spin_lock(&cpu_buffer->reader_lock);
 
-	event = rb_buffer_peek(cpu_buffer, ts);
-	if (event)
+	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
+	if (event) {
+		cpu_buffer->lost_events = 0;
 		rb_advance_reader(cpu_buffer);
+	}
 
 	if (dolock)
 		spin_unlock(&cpu_buffer->reader_lock);
@@ -3408,6 +3464,9 @@
 	cpu_buffer->write_stamp = 0;
 	cpu_buffer->read_stamp = 0;
 
+	cpu_buffer->lost_events = 0;
+	cpu_buffer->last_overrun = 0;
+
 	rb_head_page_activate(cpu_buffer);
 }
 
@@ -3683,6 +3742,7 @@
 	struct ring_buffer_event *event;
 	struct buffer_data_page *bpage;
 	struct buffer_page *reader;
+	unsigned long missed_events;
 	unsigned long flags;
 	unsigned int commit;
 	unsigned int read;
@@ -3719,6 +3779,9 @@
 	read = reader->read;
 	commit = rb_page_commit(reader);
 
+	/* Check if any events were dropped */
+	missed_events = cpu_buffer->lost_events;
+
 	/*
 	 * If this page has been partially read or
 	 * if len is not big enough to read the rest of the page or
@@ -3779,9 +3842,35 @@
 		local_set(&reader->entries, 0);
 		reader->read = 0;
 		*data_page = bpage;
+
+		/*
+		 * Use the real_end for the data size,
+		 * This gives us a chance to store the lost events
+		 * on the page.
+		 */
+		if (reader->real_end)
+			local_set(&bpage->commit, reader->real_end);
 	}
 	ret = read;
 
+	cpu_buffer->lost_events = 0;
+	/*
+	 * Set a flag in the commit field if we lost events
+	 */
+	if (missed_events) {
+		commit = local_read(&bpage->commit);
+
+		/* If there is room at the end of the page to save the
+		 * missed events, then record it there.
+		 */
+		if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+			memcpy(&bpage->data[commit], &missed_events,
+			       sizeof(missed_events));
+			local_add(RB_MISSED_STORED, &bpage->commit);
+		}
+		local_add(RB_MISSED_EVENTS, &bpage->commit);
+	}
+
  out_unlock:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 

kernel/trace/ring_buffer_benchmark.c

diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index df74c79..dc56556 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -81,7 +81,7 @@
 	int *entry;
 	u64 ts;
 
-	event = ring_buffer_consume(buffer, cpu, &ts);
+	event = ring_buffer_consume(buffer, cpu, &ts, NULL);
 	if (!event)
 		return EVENT_DROPPED;
 

kernel/trace/trace.c

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 44f916a..60f3b62 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1545,7 +1545,8 @@
 }
 
 static struct trace_entry *
-peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
+		unsigned long *lost_events)
 {
 	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
@@ -1556,7 +1557,8 @@
 	if (buf_iter)
 		event = ring_buffer_iter_peek(buf_iter, ts);
 	else
-		event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+		event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+					 lost_events);
 
 	ftrace_enable_cpu();
 
@@ -1564,10 +1566,12 @@
 }
 
 static struct trace_entry *
-__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
+		  unsigned long *missing_events, u64 *ent_ts)
 {
 	struct ring_buffer *buffer = iter->tr->buffer;
 	struct trace_entry *ent, *next = NULL;
+	unsigned long lost_events, next_lost = 0;
 	int cpu_file = iter->cpu_file;
 	u64 next_ts = 0, ts;
 	int next_cpu = -1;
@@ -1580,7 +1584,7 @@
 	if (cpu_file > TRACE_PIPE_ALL_CPU) {
 		if (ring_buffer_empty_cpu(buffer, cpu_file))
 			return NULL;
-		ent = peek_next_entry(iter, cpu_file, ent_ts);
+		ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
 		if (ent_cpu)
 			*ent_cpu = cpu_file;
 
@@ -1592,7 +1596,7 @@
 		if (ring_buffer_empty_cpu(buffer, cpu))
 			continue;
 
-		ent = peek_next_entry(iter, cpu, &ts);
+		ent = peek_next_entry(iter, cpu, &ts, &lost_events);
 
 		/*
 		 * Pick the entry with the smallest timestamp:
@@ -1601,6 +1605,7 @@
 			next = ent;
 			next_cpu = cpu;
 			next_ts = ts;
+			next_lost = lost_events;
 		}
 	}
 
@@ -1610,6 +1615,9 @@
 	if (ent_ts)
 		*ent_ts = next_ts;
 
+	if (missing_events)
+		*missing_events = next_lost;
+
 	return next;
 }
 
@@ -1617,13 +1625,14 @@
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts)
 {
-	return __find_next_entry(iter, ent_cpu, ent_ts);
+	return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
 static void *find_next_entry_inc(struct trace_iterator *iter)
 {
-	iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+	iter->ent = __find_next_entry(iter, &iter->cpu,
+				      &iter->lost_events, &iter->ts);
 
 	if (iter->ent)
 		trace_iterator_increment(iter);
@@ -1635,7 +1644,8 @@
 {
 	/* Don't allow ftrace to trace into the ring buffers */
 	ftrace_disable_cpu();
-	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+			    &iter->lost_events);
 	ftrace_enable_cpu();
 }
 
@@ -2030,6 +2040,10 @@
 {
 	enum print_line_t ret;
 
+	if (iter->lost_events)
+		trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+				 iter->cpu, iter->lost_events);
+
 	if (iter->trace && iter->trace->print_line) {
 		ret = iter->trace->print_line(iter);
 		if (ret != TRACE_TYPE_UNHANDLED)

kernel/trace/trace.h

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2825ef2..3ebdb6b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -34,7 +34,6 @@
 	TRACE_GRAPH_RET,
 	TRACE_GRAPH_ENT,
 	TRACE_USER_STACK,
-	TRACE_HW_BRANCHES,
 	TRACE_KMEM_ALLOC,
 	TRACE_KMEM_FREE,
 	TRACE_BLK,
@@ -103,29 +102,17 @@
 	long			ret;
 };
 
-struct kprobe_trace_entry {
+struct kprobe_trace_entry_head {
 	struct trace_entry	ent;
 	unsigned long		ip;
-	int			nargs;
-	unsigned long		args[];
 };
 
-#define SIZEOF_KPROBE_TRACE_ENTRY(n)			\
-	(offsetof(struct kprobe_trace_entry, args) +	\
-	(sizeof(unsigned long) * (n)))
-
-struct kretprobe_trace_entry {
+struct kretprobe_trace_entry_head {
 	struct trace_entry	ent;
 	unsigned long		func;
 	unsigned long		ret_ip;
-	int			nargs;
-	unsigned long		args[];
 };
 
-#define SIZEOF_KRETPROBE_TRACE_ENTRY(n)			\
-	(offsetof(struct kretprobe_trace_entry, args) +	\
-	(sizeof(unsigned long) * (n)))
-
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
@@ -229,7 +216,6 @@
 			  TRACE_GRAPH_ENT);		\
 		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
 			  TRACE_GRAPH_RET);		\
-		IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
 		IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry,	\
 			  TRACE_KMEM_ALLOC);	\
 		IF_ASSIGN(var, ent, struct kmemtrace_free_entry,	\
@@ -467,8 +453,6 @@
 					       struct trace_array *tr);
 extern int trace_selftest_startup_branch(struct tracer *trace,
 					 struct trace_array *tr);
-extern int trace_selftest_startup_hw_branches(struct tracer *trace,
-					      struct trace_array *tr);
 extern int trace_selftest_startup_ksym(struct tracer *trace,
 					 struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */

kernel/trace/trace_entries.h

diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index c16a08f..dc008c1 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -318,18 +318,6 @@
 		 __entry->func, __entry->file, __entry->correct)
 );
 
-FTRACE_ENTRY(hw_branch, hw_branch_entry,
-
-	TRACE_HW_BRANCHES,
-
-	F_STRUCT(
-		__field(	u64,	from	)
-		__field(	u64,	to	)
-	),
-
-	F_printk("from: %llx to: %llx", __entry->from, __entry->to)
-);
-
 FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
 
 	TRACE_KMEM_ALLOC,

kernel/trace/trace_events_filter.c

diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 88c0b6d..58092d8 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1398,7 +1398,7 @@
 	}
 
 	err = -EINVAL;
-	if (!call)
+	if (&call->list == &ftrace_events)
 		goto out_unlock;
 
 	err = -EEXIST;

kernel/trace/trace_functions_graph.c

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 9aed1a5..669b9c3 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -490,9 +490,10 @@
 			 * We need to consume the current entry to see
 			 * the next one.
 			 */
-			ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+			ring_buffer_consume(iter->tr->buffer, iter->cpu,
+					    NULL, NULL);
 			event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
-						 NULL);
+						 NULL, NULL);
 		}
 
 		if (!event)

kernel/trace/trace_hw_branches.c

diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
deleted file mode 100644
index 7b97000..0000000
--- a/kernel/trace/trace_hw_branches.c
+++ /dev/null
@@ -1,312 +0,0 @@
-/*
- * h/w branch tracer for x86 based on BTS
- *
- * Copyright (C) 2008-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009
- */
-#include <linux/kallsyms.h>
-#include <linux/debugfs.h>
-#include <linux/ftrace.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/fs.h>
-
-#include <asm/ds.h>
-
-#include "trace_output.h"
-#include "trace.h"
-
-
-#define BTS_BUFFER_SIZE (1 << 13)
-
-static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer);
-static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer);
-
-#define this_tracer per_cpu(hwb_tracer, smp_processor_id())
-
-static int trace_hw_branches_enabled __read_mostly;
-static int trace_hw_branches_suspended __read_mostly;
-static struct trace_array *hw_branch_trace __read_mostly;
-
-
-static void bts_trace_init_cpu(int cpu)
-{
-	per_cpu(hwb_tracer, cpu) =
-		ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu),
-				   BTS_BUFFER_SIZE, NULL, (size_t)-1,
-				   BTS_KERNEL);
-
-	if (IS_ERR(per_cpu(hwb_tracer, cpu)))
-		per_cpu(hwb_tracer, cpu) = NULL;
-}
-
-static int bts_trace_init(struct trace_array *tr)
-{
-	int cpu;
-
-	hw_branch_trace = tr;
-	trace_hw_branches_enabled = 0;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		bts_trace_init_cpu(cpu);
-
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			trace_hw_branches_enabled = 1;
-	}
-	trace_hw_branches_suspended = 0;
-	put_online_cpus();
-
-	/* If we could not enable tracing on a single cpu, we fail. */
-	return trace_hw_branches_enabled ? 0 : -EOPNOTSUPP;
-}
-
-static void bts_trace_reset(struct trace_array *tr)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		if (likely(per_cpu(hwb_tracer, cpu))) {
-			ds_release_bts(per_cpu(hwb_tracer, cpu));
-			per_cpu(hwb_tracer, cpu) = NULL;
-		}
-	}
-	trace_hw_branches_enabled = 0;
-	trace_hw_branches_suspended = 0;
-	put_online_cpus();
-}
-
-static void bts_trace_start(struct trace_array *tr)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_resume_bts(per_cpu(hwb_tracer, cpu));
-	trace_hw_branches_suspended = 0;
-	put_online_cpus();
-}
-
-static void bts_trace_stop(struct trace_array *tr)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_suspend_bts(per_cpu(hwb_tracer, cpu));
-	trace_hw_branches_suspended = 1;
-	put_online_cpus();
-}
-
-static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
-				     unsigned long action, void *hcpu)
-{
-	int cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-		/* The notification is sent with interrupts enabled. */
-		if (trace_hw_branches_enabled) {
-			bts_trace_init_cpu(cpu);
-
-			if (trace_hw_branches_suspended &&
-			    likely(per_cpu(hwb_tracer, cpu)))
-				ds_suspend_bts(per_cpu(hwb_tracer, cpu));
-		}
-		break;
-
-	case CPU_DOWN_PREPARE:
-		/* The notification is sent with interrupts enabled. */
-		if (likely(per_cpu(hwb_tracer, cpu))) {
-			ds_release_bts(per_cpu(hwb_tracer, cpu));
-			per_cpu(hwb_tracer, cpu) = NULL;
-		}
-	}
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block bts_hotcpu_notifier __cpuinitdata = {
-	.notifier_call = bts_hotcpu_handler
-};
-
-static void bts_trace_print_header(struct seq_file *m)
-{
-	seq_puts(m, "# CPU#        TO  <-  FROM\n");
-}
-
-static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
-{
-	unsigned long symflags = TRACE_ITER_SYM_OFFSET;
-	struct trace_entry *entry = iter->ent;
-	struct trace_seq *seq = &iter->seq;
-	struct hw_branch_entry *it;
-
-	trace_assign_type(it, entry);
-
-	if (entry->type == TRACE_HW_BRANCHES) {
-		if (trace_seq_printf(seq, "%4d  ", iter->cpu) &&
-		    seq_print_ip_sym(seq, it->to, symflags) &&
-		    trace_seq_printf(seq, "\t  <-  ") &&
-		    seq_print_ip_sym(seq, it->from, symflags) &&
-		    trace_seq_printf(seq, "\n"))
-			return TRACE_TYPE_HANDLED;
-		return TRACE_TYPE_PARTIAL_LINE;
-	}
-	return TRACE_TYPE_UNHANDLED;
-}
-
-void trace_hw_branch(u64 from, u64 to)
-{
-	struct ftrace_event_call *call = &event_hw_branch;
-	struct trace_array *tr = hw_branch_trace;
-	struct ring_buffer_event *event;
-	struct ring_buffer *buf;
-	struct hw_branch_entry *entry;
-	unsigned long irq1;
-	int cpu;
-
-	if (unlikely(!tr))
-		return;
-
-	if (unlikely(!trace_hw_branches_enabled))
-		return;
-
-	local_irq_save(irq1);
-	cpu = raw_smp_processor_id();
-	if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
-		goto out;
-
-	buf = tr->buffer;
-	event = trace_buffer_lock_reserve(buf, TRACE_HW_BRANCHES,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		goto out;
-	entry	= ring_buffer_event_data(event);
-	tracing_generic_entry_update(&entry->ent, 0, from);
-	entry->ent.type = TRACE_HW_BRANCHES;
-	entry->from = from;
-	entry->to   = to;
-	if (!filter_check_discard(call, entry, buf, event))
-		trace_buffer_unlock_commit(buf, event, 0, 0);
-
- out:
-	atomic_dec(&tr->data[cpu]->disabled);
-	local_irq_restore(irq1);
-}
-
-static void trace_bts_at(const struct bts_trace *trace, void *at)
-{
-	struct bts_struct bts;
-	int err = 0;
-
-	WARN_ON_ONCE(!trace->read);
-	if (!trace->read)
-		return;
-
-	err = trace->read(this_tracer, at, &bts);
-	if (err < 0)
-		return;
-
-	switch (bts.qualifier) {
-	case BTS_BRANCH:
-		trace_hw_branch(bts.variant.lbr.from, bts.variant.lbr.to);
-		break;
-	}
-}
-
-/*
- * Collect the trace on the current cpu and write it into the ftrace buffer.
- *
- * pre: tracing must be suspended on the current cpu
- */
-static void trace_bts_cpu(void *arg)
-{
-	struct trace_array *tr = (struct trace_array *)arg;
-	const struct bts_trace *trace;
-	unsigned char *at;
-
-	if (unlikely(!tr))
-		return;
-
-	if (unlikely(atomic_read(&tr->data[raw_smp_processor_id()]->disabled)))
-		return;
-
-	if (unlikely(!this_tracer))
-		return;
-
-	trace = ds_read_bts(this_tracer);
-	if (!trace)
-		return;
-
-	for (at = trace->ds.top; (void *)at < trace->ds.end;
-	     at += trace->ds.size)
-		trace_bts_at(trace, at);
-
-	for (at = trace->ds.begin; (void *)at < trace->ds.top;
-	     at += trace->ds.size)
-		trace_bts_at(trace, at);
-}
-
-static void trace_bts_prepare(struct trace_iterator *iter)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_suspend_bts(per_cpu(hwb_tracer, cpu));
-	/*
-	 * We need to collect the trace on the respective cpu since ftrace
-	 * implicitly adds the record for the current cpu.
-	 * Once that is more flexible, we could collect the data from any cpu.
-	 */
-	on_each_cpu(trace_bts_cpu, iter->tr, 1);
-
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_resume_bts(per_cpu(hwb_tracer, cpu));
-	put_online_cpus();
-}
-
-static void trace_bts_close(struct trace_iterator *iter)
-{
-	tracing_reset_online_cpus(iter->tr);
-}
-
-void trace_hw_branch_oops(void)
-{
-	if (this_tracer) {
-		ds_suspend_bts_noirq(this_tracer);
-		trace_bts_cpu(hw_branch_trace);
-		ds_resume_bts_noirq(this_tracer);
-	}
-}
-
-struct tracer bts_tracer __read_mostly =
-{
-	.name		= "hw-branch-tracer",
-	.init		= bts_trace_init,
-	.reset		= bts_trace_reset,
-	.print_header	= bts_trace_print_header,
-	.print_line	= bts_trace_print_line,
-	.start		= bts_trace_start,
-	.stop		= bts_trace_stop,
-	.open		= trace_bts_prepare,
-	.close		= trace_bts_close,
-#ifdef CONFIG_FTRACE_SELFTEST
-	.selftest	= trace_selftest_startup_hw_branches,
-#endif /* CONFIG_FTRACE_SELFTEST */
-};
-
-__init static int init_bts_trace(void)
-{
-	register_hotcpu_notifier(&bts_hotcpu_notifier);
-	return register_tracer(&bts_tracer);
-}
-device_initcall(init_bts_trace);

kernel/trace/trace_kprobe.c

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 1251e36..a751432 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -29,6 +29,8 @@
 #include <linux/ctype.h>
 #include <linux/ptrace.h>
 #include <linux/perf_event.h>
+#include <linux/stringify.h>
+#include <asm/bitsperlong.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -40,7 +42,6 @@
 
 /* Reserved field names */
 #define FIELD_STRING_IP "__probe_ip"
-#define FIELD_STRING_NARGS "__probe_nargs"
 #define FIELD_STRING_RETIP "__probe_ret_ip"
 #define FIELD_STRING_FUNC "__probe_func"
 
@@ -52,56 +53,102 @@
 	"common_tgid",
 	"common_lock_depth",
 	FIELD_STRING_IP,
-	FIELD_STRING_NARGS,
 	FIELD_STRING_RETIP,
 	FIELD_STRING_FUNC,
 };
 
-struct fetch_func {
-	unsigned long (*func)(struct pt_regs *, void *);
+/* Printing function type */
+typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *);
+#define PRINT_TYPE_FUNC_NAME(type)	print_type_##type
+#define PRINT_TYPE_FMT_NAME(type)	print_type_format_##type
+
+/* Printing  in basic type function template */
+#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast)			\
+static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s,	\
+						const char *name, void *data)\
+{									\
+	return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\
+}									\
+static const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
+
+DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long)
+
+/* Data fetch function type */
+typedef	void (*fetch_func_t)(struct pt_regs *, void *, void *);
+
+struct fetch_param {
+	fetch_func_t	fn;
 	void *data;
 };
 
-static __kprobes unsigned long call_fetch(struct fetch_func *f,
-					  struct pt_regs *regs)
+static __kprobes void call_fetch(struct fetch_param *fprm,
+				 struct pt_regs *regs, void *dest)
 {
-	return f->func(regs, f->data);
+	return fprm->fn(regs, fprm->data, dest);
 }
 
-/* fetch handlers */
-static __kprobes unsigned long fetch_register(struct pt_regs *regs,
-					      void *offset)
-{
-	return regs_get_register(regs, (unsigned int)((unsigned long)offset));
-}
+#define FETCH_FUNC_NAME(kind, type)	fetch_##kind##_##type
+/*
+ * Define macro for basic types - we don't need to define s* types, because
+ * we have to care only about bitwidth at recording time.
+ */
+#define DEFINE_BASIC_FETCH_FUNCS(kind)  \
+DEFINE_FETCH_##kind(u8)			\
+DEFINE_FETCH_##kind(u16)		\
+DEFINE_FETCH_##kind(u32)		\
+DEFINE_FETCH_##kind(u64)
 
-static __kprobes unsigned long fetch_stack(struct pt_regs *regs,
-					   void *num)
-{
-	return regs_get_kernel_stack_nth(regs,
-					 (unsigned int)((unsigned long)num));
-}
+#define CHECK_BASIC_FETCH_FUNCS(kind, fn)	\
+	((FETCH_FUNC_NAME(kind, u8) == fn) ||	\
+	 (FETCH_FUNC_NAME(kind, u16) == fn) ||	\
+	 (FETCH_FUNC_NAME(kind, u32) == fn) ||	\
+	 (FETCH_FUNC_NAME(kind, u64) == fn))
 
-static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr)
-{
-	unsigned long retval;
-
-	if (probe_kernel_address(addr, retval))
-		return 0;
-	return retval;
+/* Data fetch function templates */
+#define DEFINE_FETCH_reg(type)						\
+static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs,	\
+					  void *offset, void *dest)	\
+{									\
+	*(type *)dest = (type)regs_get_register(regs,			\
+				(unsigned int)((unsigned long)offset));	\
 }
+DEFINE_BASIC_FETCH_FUNCS(reg)
 
-static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs,
-					      void *dummy)
-{
-	return regs_return_value(regs);
+#define DEFINE_FETCH_stack(type)					\
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+					  void *offset, void *dest)	\
+{									\
+	*(type *)dest = (type)regs_get_kernel_stack_nth(regs,		\
+				(unsigned int)((unsigned long)offset));	\
 }
+DEFINE_BASIC_FETCH_FUNCS(stack)
 
-static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs,
-						   void *dummy)
-{
-	return kernel_stack_pointer(regs);
+#define DEFINE_FETCH_retval(type)					\
+static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
+					  void *dummy, void *dest)	\
+{									\
+	*(type *)dest = (type)regs_return_value(regs);			\
 }
+DEFINE_BASIC_FETCH_FUNCS(retval)
+
+#define DEFINE_FETCH_memory(type)					\
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+					  void *addr, void *dest)	\
+{									\
+	type retval;							\
+	if (probe_kernel_address(addr, retval))				\
+		*(type *)dest = 0;					\
+	else								\
+		*(type *)dest = retval;					\
+}
+DEFINE_BASIC_FETCH_FUNCS(memory)
 
 /* Memory fetching by symbol */
 struct symbol_cache {
@@ -145,51 +192,126 @@
 	return sc;
 }
 
-static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data)
-{
-	struct symbol_cache *sc = data;
-
-	if (sc->addr)
-		return fetch_memory(regs, (void *)sc->addr);
-	else
-		return 0;
+#define DEFINE_FETCH_symbol(type)					\
+static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\
+					  void *data, void *dest)	\
+{									\
+	struct symbol_cache *sc = data;					\
+	if (sc->addr)							\
+		fetch_memory_##type(regs, (void *)sc->addr, dest);	\
+	else								\
+		*(type *)dest = 0;					\
 }
+DEFINE_BASIC_FETCH_FUNCS(symbol)
 
-/* Special indirect memory access interface */
-struct indirect_fetch_data {
-	struct fetch_func orig;
+/* Dereference memory access function */
+struct deref_fetch_param {
+	struct fetch_param orig;
 	long offset;
 };
 
-static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data)
-{
-	struct indirect_fetch_data *ind = data;
-	unsigned long addr;
-
-	addr = call_fetch(&ind->orig, regs);
-	if (addr) {
-		addr += ind->offset;
-		return fetch_memory(regs, (void *)addr);
-	} else
-		return 0;
+#define DEFINE_FETCH_deref(type)					\
+static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
+					    void *data, void *dest)	\
+{									\
+	struct deref_fetch_param *dprm = data;				\
+	unsigned long addr;						\
+	call_fetch(&dprm->orig, regs, &addr);				\
+	if (addr) {							\
+		addr += dprm->offset;					\
+		fetch_memory_##type(regs, (void *)addr, dest);		\
+	} else								\
+		*(type *)dest = 0;					\
 }
+DEFINE_BASIC_FETCH_FUNCS(deref)
 
-static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data)
+static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 {
-	if (data->orig.func == fetch_indirect)
-		free_indirect_fetch_data(data->orig.data);
-	else if (data->orig.func == fetch_symbol)
+	if (CHECK_BASIC_FETCH_FUNCS(deref, data->orig.fn))
+		free_deref_fetch_param(data->orig.data);
+	else if (CHECK_BASIC_FETCH_FUNCS(symbol, data->orig.fn))
 		free_symbol_cache(data->orig.data);
 	kfree(data);
 }
 
+/* Default (unsigned long) fetch type */
+#define __DEFAULT_FETCH_TYPE(t) u##t
+#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
+#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
+#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
+
+#define ASSIGN_FETCH_FUNC(kind, type)	\
+	.kind = FETCH_FUNC_NAME(kind, type)
+
+#define ASSIGN_FETCH_TYPE(ptype, ftype, sign)	\
+	{.name = #ptype,			\
+	 .size = sizeof(ftype),			\
+	 .is_signed = sign,			\
+	 .print = PRINT_TYPE_FUNC_NAME(ptype),	\
+	 .fmt = PRINT_TYPE_FMT_NAME(ptype),	\
+ASSIGN_FETCH_FUNC(reg, ftype),			\
+ASSIGN_FETCH_FUNC(stack, ftype),		\
+ASSIGN_FETCH_FUNC(retval, ftype),		\
+ASSIGN_FETCH_FUNC(memory, ftype),		\
+ASSIGN_FETCH_FUNC(symbol, ftype),		\
+ASSIGN_FETCH_FUNC(deref, ftype),		\
+	}
+
+/* Fetch type information table */
+static const struct fetch_type {
+	const char	*name;		/* Name of type */
+	size_t		size;		/* Byte size of type */
+	int		is_signed;	/* Signed flag */
+	print_type_func_t	print;	/* Print functions */
+	const char	*fmt;		/* Fromat string */
+	/* Fetch functions */
+	fetch_func_t	reg;
+	fetch_func_t	stack;
+	fetch_func_t	retval;
+	fetch_func_t	memory;
+	fetch_func_t	symbol;
+	fetch_func_t	deref;
+} fetch_type_table[] = {
+	ASSIGN_FETCH_TYPE(u8,  u8,  0),
+	ASSIGN_FETCH_TYPE(u16, u16, 0),
+	ASSIGN_FETCH_TYPE(u32, u32, 0),
+	ASSIGN_FETCH_TYPE(u64, u64, 0),
+	ASSIGN_FETCH_TYPE(s8,  u8,  1),
+	ASSIGN_FETCH_TYPE(s16, u16, 1),
+	ASSIGN_FETCH_TYPE(s32, u32, 1),
+	ASSIGN_FETCH_TYPE(s64, u64, 1),
+};
+
+static const struct fetch_type *find_fetch_type(const char *type)
+{
+	int i;
+
+	if (!type)
+		type = DEFAULT_FETCH_TYPE_STR;
+
+	for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
+		if (strcmp(type, fetch_type_table[i].name) == 0)
+			return &fetch_type_table[i];
+	return NULL;
+}
+
+/* Special function : only accept unsigned long */
+static __kprobes void fetch_stack_address(struct pt_regs *regs,
+					  void *dummy, void *dest)
+{
+	*(unsigned long *)dest = kernel_stack_pointer(regs);
+}
+
 /**
  * Kprobe event core functions
  */
 
 struct probe_arg {
-	struct fetch_func	fetch;
-	const char		*name;
+	struct fetch_param	fetch;
+	unsigned int		offset;	/* Offset from argument entry */
+	const char		*name;	/* Name of this argument */
+	const char		*comm;	/* Command of this argument */
+	const struct fetch_type	*type;	/* Type of this argument */
 };
 
 /* Flags for trace_probe */
@@ -204,6 +326,7 @@
 	const char		*symbol;	/* symbol name */
 	struct ftrace_event_call	call;
 	struct trace_event		event;
+	ssize_t			size;		/* trace entry size */
 	unsigned int		nr_args;
 	struct probe_arg	args[];
 };
@@ -212,6 +335,7 @@
 	(offsetof(struct trace_probe, args) +	\
 	(sizeof(struct probe_arg) * (n)))
 
+
 static __kprobes int probe_is_return(struct trace_probe *tp)
 {
 	return tp->rp.handler != NULL;
@@ -222,49 +346,6 @@
 	return tp->symbol ? tp->symbol : "unknown";
 }
 
-static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff)
-{
-	int ret = -EINVAL;
-
-	if (ff->func == fetch_register) {
-		const char *name;
-		name = regs_query_register_name((unsigned int)((long)ff->data));
-		ret = snprintf(buf, n, "%%%s", name);
-	} else if (ff->func == fetch_stack)
-		ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data);
-	else if (ff->func == fetch_memory)
-		ret = snprintf(buf, n, "@0x%p", ff->data);
-	else if (ff->func == fetch_symbol) {
-		struct symbol_cache *sc = ff->data;
-		if (sc->offset)
-			ret = snprintf(buf, n, "@%s%+ld", sc->symbol,
-					sc->offset);
-		else
-			ret = snprintf(buf, n, "@%s", sc->symbol);
-	} else if (ff->func == fetch_retvalue)
-		ret = snprintf(buf, n, "$retval");
-	else if (ff->func == fetch_stack_address)
-		ret = snprintf(buf, n, "$stack");
-	else if (ff->func == fetch_indirect) {
-		struct indirect_fetch_data *id = ff->data;
-		size_t l = 0;
-		ret = snprintf(buf, n, "%+ld(", id->offset);
-		if (ret >= n)
-			goto end;
-		l += ret;
-		ret = probe_arg_string(buf + l, n - l, &id->orig);
-		if (ret < 0)
-			goto end;
-		l += ret;
-		ret = snprintf(buf + l, n - l, ")");
-		ret += l;
-	}
-end:
-	if (ret >= n)
-		return -ENOSPC;
-	return ret;
-}
-
 static int register_probe_event(struct trace_probe *tp);
 static void unregister_probe_event(struct trace_probe *tp);
 
@@ -347,11 +428,12 @@
 
 static void free_probe_arg(struct probe_arg *arg)
 {
-	if (arg->fetch.func == fetch_symbol)
+	if (CHECK_BASIC_FETCH_FUNCS(deref, arg->fetch.fn))
+		free_deref_fetch_param(arg->fetch.data);
+	else if (CHECK_BASIC_FETCH_FUNCS(symbol, arg->fetch.fn))
 		free_symbol_cache(arg->fetch.data);
-	else if (arg->fetch.func == fetch_indirect)
-		free_indirect_fetch_data(arg->fetch.data);
 	kfree(arg->name);
+	kfree(arg->comm);
 }
 
 static void free_trace_probe(struct trace_probe *tp)
@@ -457,28 +539,30 @@
 #define PARAM_MAX_ARGS 16
 #define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
 
-static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return)
+static int parse_probe_vars(char *arg, const struct fetch_type *t,
+			    struct fetch_param *f, int is_return)
 {
 	int ret = 0;
 	unsigned long param;
 
 	if (strcmp(arg, "retval") == 0) {
-		if (is_return) {
-			ff->func = fetch_retvalue;
-			ff->data = NULL;
-		} else
+		if (is_return)
+			f->fn = t->retval;
+		else
 			ret = -EINVAL;
 	} else if (strncmp(arg, "stack", 5) == 0) {
 		if (arg[5] == '\0') {
-			ff->func = fetch_stack_address;
-			ff->data = NULL;
+			if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0)
+				f->fn = fetch_stack_address;
+			else
+				ret = -EINVAL;
 		} else if (isdigit(arg[5])) {
 			ret = strict_strtoul(arg + 5, 10, &param);
 			if (ret || param > PARAM_MAX_STACK)
 				ret = -EINVAL;
 			else {
-				ff->func = fetch_stack;
-				ff->data = (void *)param;
+				f->fn = t->stack;
+				f->data = (void *)param;
 			}
 		} else
 			ret = -EINVAL;
@@ -488,7 +572,8 @@
 }
 
 /* Recursive argument parser */
-static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+static int __parse_probe_arg(char *arg, const struct fetch_type *t,
+			     struct fetch_param *f, int is_return)
 {
 	int ret = 0;
 	unsigned long param;
@@ -497,13 +582,13 @@
 
 	switch (arg[0]) {
 	case '$':
-		ret = parse_probe_vars(arg + 1, ff, is_return);
+		ret = parse_probe_vars(arg + 1, t, f, is_return);
 		break;
 	case '%':	/* named register */
 		ret = regs_query_register_offset(arg + 1);
 		if (ret >= 0) {
-			ff->func = fetch_register;
-			ff->data = (void *)(unsigned long)ret;
+			f->fn = t->reg;
+			f->data = (void *)(unsigned long)ret;
 			ret = 0;
 		}
 		break;
@@ -512,26 +597,22 @@
 			ret = strict_strtoul(arg + 1, 0, &param);
 			if (ret)
 				break;
-			ff->func = fetch_memory;
-			ff->data = (void *)param;
+			f->fn = t->memory;
+			f->data = (void *)param;
 		} else {
 			ret = split_symbol_offset(arg + 1, &offset);
 			if (ret)
 				break;
-			ff->data = alloc_symbol_cache(arg + 1, offset);
-			if (ff->data)
-				ff->func = fetch_symbol;
-			else
-				ret = -EINVAL;
+			f->data = alloc_symbol_cache(arg + 1, offset);
+			if (f->data)
+				f->fn = t->symbol;
 		}
 		break;
-	case '+':	/* indirect memory */
+	case '+':	/* deref memory */
 	case '-':
 		tmp = strchr(arg, '(');
-		if (!tmp) {
-			ret = -EINVAL;
+		if (!tmp)
 			break;
-		}
 		*tmp = '\0';
 		ret = strict_strtol(arg + 1, 0, &offset);
 		if (ret)
@@ -541,38 +622,58 @@
 		arg = tmp + 1;
 		tmp = strrchr(arg, ')');
 		if (tmp) {
-			struct indirect_fetch_data *id;
+			struct deref_fetch_param *dprm;
+			const struct fetch_type *t2 = find_fetch_type(NULL);
 			*tmp = '\0';
-			id = kzalloc(sizeof(struct indirect_fetch_data),
-				     GFP_KERNEL);
-			if (!id)
+			dprm = kzalloc(sizeof(struct deref_fetch_param),
+				       GFP_KERNEL);
+			if (!dprm)
 				return -ENOMEM;
-			id->offset = offset;
-			ret = __parse_probe_arg(arg, &id->orig, is_return);
+			dprm->offset = offset;
+			ret = __parse_probe_arg(arg, t2, &dprm->orig,
+						is_return);
 			if (ret)
-				kfree(id);
+				kfree(dprm);
 			else {
-				ff->func = fetch_indirect;
-				ff->data = (void *)id;
+				f->fn = t->deref;
+				f->data = (void *)dprm;
 			}
-		} else
-			ret = -EINVAL;
+		}
 		break;
-	default:
-		/* TODO: support custom handler */
-		ret = -EINVAL;
 	}
+	if (!ret && !f->fn)
+		ret = -EINVAL;
 	return ret;
 }
 
 /* String length checking wrapper */
-static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+static int parse_probe_arg(char *arg, struct trace_probe *tp,
+			   struct probe_arg *parg, int is_return)
 {
+	const char *t;
+
 	if (strlen(arg) > MAX_ARGSTR_LEN) {
 		pr_info("Argument is too long.: %s\n",  arg);
 		return -ENOSPC;
 	}
-	return __parse_probe_arg(arg, ff, is_return);
+	parg->comm = kstrdup(arg, GFP_KERNEL);
+	if (!parg->comm) {
+		pr_info("Failed to allocate memory for command '%s'.\n", arg);
+		return -ENOMEM;
+	}
+	t = strchr(parg->comm, ':');
+	if (t) {
+		arg[t - parg->comm] = '\0';
+		t++;
+	}
+	parg->type = find_fetch_type(t);
+	if (!parg->type) {
+		pr_info("Unsupported type: %s\n", t);
+		return -EINVAL;
+	}
+	parg->offset = tp->size;
+	tp->size += parg->type->size;
+	return __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
 }
 
 /* Return 1 if name is reserved or already used by another argument */
@@ -602,15 +703,18 @@
 	 *  @ADDR	: fetch memory at ADDR (ADDR should be in kernel)
 	 *  @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
 	 *  %REG	: fetch register REG
-	 * Indirect memory fetch:
+	 * Dereferencing memory fetch:
 	 *  +|-offs(ARG) : fetch memory at ARG +|- offs address.
 	 * Alias name of args:
 	 *  NAME=FETCHARG : set NAME as alias of FETCHARG.
+	 * Type of args:
+	 *  FETCHARG:TYPE : use TYPE instead of unsigned long.
 	 */
 	struct trace_probe *tp;
 	int i, ret = 0;
 	int is_return = 0, is_delete = 0;
-	char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
+	char *symbol = NULL, *event = NULL, *group = NULL;
+	char *arg, *tmp;
 	unsigned long offset = 0;
 	void *addr = NULL;
 	char buf[MAX_EVENT_NAME_LEN];
@@ -723,13 +827,6 @@
 		else
 			arg = argv[i];
 
-		if (conflict_field_name(argv[i], tp->args, i)) {
-			pr_info("Argument%d name '%s' conflicts with "
-				"another field.\n", i, argv[i]);
-			ret = -EINVAL;
-			goto error;
-		}
-
 		tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
 		if (!tp->args[i].name) {
 			pr_info("Failed to allocate argument%d name '%s'.\n",
@@ -737,9 +834,19 @@
 			ret = -ENOMEM;
 			goto error;
 		}
+		tmp = strchr(tp->args[i].name, ':');
+		if (tmp)
+			*tmp = '_';	/* convert : to _ */
+
+		if (conflict_field_name(tp->args[i].name, tp->args, i)) {
+			pr_info("Argument%d name '%s' conflicts with "
+				"another field.\n", i, argv[i]);
+			ret = -EINVAL;
+			goto error;
+		}
 
 		/* Parse fetch argument */
-		ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
+		ret = parse_probe_arg(arg, tp, &tp->args[i], is_return);
 		if (ret) {
 			pr_info("Parse error at argument%d. (%d)\n", i, ret);
 			kfree(tp->args[i].name);
@@ -794,8 +901,7 @@
 static int probes_seq_show(struct seq_file *m, void *v)
 {
 	struct trace_probe *tp = v;
-	int i, ret;
-	char buf[MAX_ARGSTR_LEN + 1];
+	int i;
 
 	seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
 	seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);
@@ -807,15 +913,10 @@
 	else
 		seq_printf(m, " %s", probe_symbol(tp));
 
-	for (i = 0; i < tp->nr_args; i++) {
-		ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch);
-		if (ret < 0) {
-			pr_warning("Argument%d decoding error(%d).\n", i, ret);
-			return ret;
-		}
-		seq_printf(m, " %s=%s", tp->args[i].name, buf);
-	}
+	for (i = 0; i < tp->nr_args; i++)
+		seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm);
 	seq_printf(m, "\n");
+
 	return 0;
 }
 
@@ -945,9 +1046,10 @@
 static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 {
 	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
-	struct kprobe_trace_entry *entry;
+	struct kprobe_trace_entry_head *entry;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
+	u8 *data;
 	int size, i, pc;
 	unsigned long irq_flags;
 	struct ftrace_event_call *call = &tp->call;
@@ -957,7 +1059,7 @@
 	local_save_flags(irq_flags);
 	pc = preempt_count();
 
-	size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+	size = sizeof(*entry) + tp->size;
 
 	event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
 						  irq_flags, pc);
@@ -965,10 +1067,10 @@
 		return;
 
 	entry = ring_buffer_event_data(event);
-	entry->nargs = tp->nr_args;
 	entry->ip = (unsigned long)kp->addr;
+	data = (u8 *)&entry[1];
 	for (i = 0; i < tp->nr_args; i++)
-		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
 		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
@@ -979,9 +1081,10 @@
 					  struct pt_regs *regs)
 {
 	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
-	struct kretprobe_trace_entry *entry;
+	struct kretprobe_trace_entry_head *entry;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
+	u8 *data;
 	int size, i, pc;
 	unsigned long irq_flags;
 	struct ftrace_event_call *call = &tp->call;
@@ -989,7 +1092,7 @@
 	local_save_flags(irq_flags);
 	pc = preempt_count();
 
-	size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+	size = sizeof(*entry) + tp->size;
 
 	event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
 						  irq_flags, pc);
@@ -997,11 +1100,11 @@
 		return;
 
 	entry = ring_buffer_event_data(event);
-	entry->nargs = tp->nr_args;
 	entry->func = (unsigned long)tp->rp.kp.addr;
 	entry->ret_ip = (unsigned long)ri->ret_addr;
+	data = (u8 *)&entry[1];
 	for (i = 0; i < tp->nr_args; i++)
-		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
 		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
@@ -1011,13 +1114,14 @@
 enum print_line_t
 print_kprobe_event(struct trace_iterator *iter, int flags)
 {
-	struct kprobe_trace_entry *field;
+	struct kprobe_trace_entry_head *field;
 	struct trace_seq *s = &iter->seq;
 	struct trace_event *event;
 	struct trace_probe *tp;
+	u8 *data;
 	int i;
 
-	field = (struct kprobe_trace_entry *)iter->ent;
+	field = (struct kprobe_trace_entry_head *)iter->ent;
 	event = ftrace_find_event(field->ent.type);
 	tp = container_of(event, struct trace_probe, event);
 
@@ -1030,9 +1134,10 @@
 	if (!trace_seq_puts(s, ")"))
 		goto partial;
 
-	for (i = 0; i < field->nargs; i++)
-		if (!trace_seq_printf(s, " %s=%lx",
-				      tp->args[i].name, field->args[i]))
+	data = (u8 *)&field[1];
+	for (i = 0; i < tp->nr_args; i++)
+		if (!tp->args[i].type->print(s, tp->args[i].name,
+					     data + tp->args[i].offset))
 			goto partial;
 
 	if (!trace_seq_puts(s, "\n"))
@@ -1046,13 +1151,14 @@
 enum print_line_t
 print_kretprobe_event(struct trace_iterator *iter, int flags)
 {
-	struct kretprobe_trace_entry *field;
+	struct kretprobe_trace_entry_head *field;
 	struct trace_seq *s = &iter->seq;
 	struct trace_event *event;
 	struct trace_probe *tp;
+	u8 *data;
 	int i;
 
-	field = (struct kretprobe_trace_entry *)iter->ent;
+	field = (struct kretprobe_trace_entry_head *)iter->ent;
 	event = ftrace_find_event(field->ent.type);
 	tp = container_of(event, struct trace_probe, event);
 
@@ -1071,9 +1177,10 @@
 	if (!trace_seq_puts(s, ")"))
 		goto partial;
 
-	for (i = 0; i < field->nargs; i++)
-		if (!trace_seq_printf(s, " %s=%lx",
-				      tp->args[i].name, field->args[i]))
+	data = (u8 *)&field[1];
+	for (i = 0; i < tp->nr_args; i++)
+		if (!tp->args[i].type->print(s, tp->args[i].name,
+					     data + tp->args[i].offset))
 			goto partial;
 
 	if (!trace_seq_puts(s, "\n"))
@@ -1129,29 +1236,43 @@
 static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
 {
 	int ret, i;
-	struct kprobe_trace_entry field;
+	struct kprobe_trace_entry_head field;
 	struct trace_probe *tp = (struct trace_probe *)event_call->data;
 
 	DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
-	DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
 	/* Set argument names as fields */
-	for (i = 0; i < tp->nr_args; i++)
-		DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+	for (i = 0; i < tp->nr_args; i++) {
+		ret = trace_define_field(event_call, tp->args[i].type->name,
+					 tp->args[i].name,
+					 sizeof(field) + tp->args[i].offset,
+					 tp->args[i].type->size,
+					 tp->args[i].type->is_signed,
+					 FILTER_OTHER);
+		if (ret)
+			return ret;
+	}
 	return 0;
 }
 
 static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
 {
 	int ret, i;
-	struct kretprobe_trace_entry field;
+	struct kretprobe_trace_entry_head field;
 	struct trace_probe *tp = (struct trace_probe *)event_call->data;
 
 	DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
 	DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
-	DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
 	/* Set argument names as fields */
-	for (i = 0; i < tp->nr_args; i++)
-		DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+	for (i = 0; i < tp->nr_args; i++) {
+		ret = trace_define_field(event_call, tp->args[i].type->name,
+					 tp->args[i].name,
+					 sizeof(field) + tp->args[i].offset,
+					 tp->args[i].type->size,
+					 tp->args[i].type->is_signed,
+					 FILTER_OTHER);
+		if (ret)
+			return ret;
+	}
 	return 0;
 }
 
@@ -1176,8 +1297,8 @@
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
 
 	for (i = 0; i < tp->nr_args; i++) {
-		pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%%lx",
-				tp->args[i].name);
+		pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
+				tp->args[i].name, tp->args[i].type->fmt);
 	}
 
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
@@ -1219,12 +1340,13 @@
 {
 	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
 	struct ftrace_event_call *call = &tp->call;
-	struct kprobe_trace_entry *entry;
+	struct kprobe_trace_entry_head *entry;
+	u8 *data;
 	int size, __size, i;
 	unsigned long irq_flags;
 	int rctx;
 
-	__size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+	__size = sizeof(*entry) + tp->size;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
@@ -1235,10 +1357,10 @@
 	if (!entry)
 		return;
 
-	entry->nargs = tp->nr_args;
 	entry->ip = (unsigned long)kp->addr;
+	data = (u8 *)&entry[1];
 	for (i = 0; i < tp->nr_args; i++)
-		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
 	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs);
 }
@@ -1249,12 +1371,13 @@
 {
 	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
 	struct ftrace_event_call *call = &tp->call;
-	struct kretprobe_trace_entry *entry;
+	struct kretprobe_trace_entry_head *entry;
+	u8 *data;
 	int size, __size, i;
 	unsigned long irq_flags;
 	int rctx;
 
-	__size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+	__size = sizeof(*entry) + tp->size;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
@@ -1265,11 +1388,11 @@
 	if (!entry)
 		return;
 
-	entry->nargs = tp->nr_args;
 	entry->func = (unsigned long)tp->rp.kp.addr;
 	entry->ret_ip = (unsigned long)ri->ret_addr;
+	data = (u8 *)&entry[1];
 	for (i = 0; i < tp->nr_args; i++)
-		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
 	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
 			       irq_flags, regs);

kernel/trace/trace_ksym.c

diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
index d59cd68..8eaf007 100644
--- a/kernel/trace/trace_ksym.c
+++ b/kernel/trace/trace_ksym.c
@@ -34,12 +34,6 @@
 
 #include <asm/atomic.h>
 
-/*
- * For now, let us restrict the no. of symbols traced simultaneously to number
- * of available hardware breakpoint registers.
- */
-#define KSYM_TRACER_MAX HBP_NUM
-
 #define KSYM_TRACER_OP_LEN 3 /* rw- */
 
 struct trace_ksym {
@@ -53,7 +47,6 @@
 
 static struct trace_array *ksym_trace_array;
 
-static unsigned int ksym_filter_entry_count;
 static unsigned int ksym_tracing_enabled;
 
 static HLIST_HEAD(ksym_filter_head);
@@ -181,13 +174,6 @@
 	struct trace_ksym *entry;
 	int ret = -ENOMEM;
 
-	if (ksym_filter_entry_count >= KSYM_TRACER_MAX) {
-		printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No"
-		" new requests for tracing can be accepted now.\n",
-			KSYM_TRACER_MAX);
-		return -ENOSPC;
-	}
-
 	entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
 	if (!entry)
 		return -ENOMEM;
@@ -203,13 +189,17 @@
 
 	if (IS_ERR(entry->ksym_hbp)) {
 		ret = PTR_ERR(entry->ksym_hbp);
-		printk(KERN_INFO "ksym_tracer request failed. Try again"
-					" later!!\n");
+		if (ret == -ENOSPC) {
+			printk(KERN_ERR "ksym_tracer: Maximum limit reached."
+			" No new requests for tracing can be accepted now.\n");
+		} else {
+			printk(KERN_INFO "ksym_tracer request failed. Try again"
+					 " later!!\n");
+		}
 		goto err;
 	}
 
 	hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
-	ksym_filter_entry_count++;
 
 	return 0;
 
@@ -265,7 +255,6 @@
 	hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head,
 								ksym_hlist) {
 		unregister_wide_hw_breakpoint(entry->ksym_hbp);
-		ksym_filter_entry_count--;
 		hlist_del_rcu(&(entry->ksym_hlist));
 		synchronize_rcu();
 		kfree(entry);
@@ -338,7 +327,6 @@
 				goto out_unlock;
 		}
 		/* Error or "symbol:---" case: drop it */
-		ksym_filter_entry_count--;
 		hlist_del_rcu(&(entry->ksym_hlist));
 		synchronize_rcu();
 		kfree(entry);

kernel/trace/trace_selftest.c

diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 81003b4..71fa771 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -17,7 +17,6 @@
 	case TRACE_BRANCH:
 	case TRACE_GRAPH_ENT:
 	case TRACE_GRAPH_RET:
-	case TRACE_HW_BRANCHES:
 	case TRACE_KSYM:
 		return 1;
 	}
@@ -30,7 +29,7 @@
 	struct trace_entry *entry;
 	unsigned int loops = 0;
 
-	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
+	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) {
 		entry = ring_buffer_event_data(event);
 
 		/*
@@ -755,62 +754,6 @@
 }
 #endif /* CONFIG_BRANCH_TRACER */
 
-#ifdef CONFIG_HW_BRANCH_TRACER
-int
-trace_selftest_startup_hw_branches(struct tracer *trace,
-				   struct trace_array *tr)
-{
-	struct trace_iterator *iter;
-	struct tracer tracer;
-	unsigned long count;
-	int ret;
-
-	if (!trace->open) {
-		printk(KERN_CONT "missing open function...");
-		return -1;
-	}
-
-	ret = tracer_init(trace, tr);
-	if (ret) {
-		warn_failed_init_tracer(trace, ret);
-		return ret;
-	}
-
-	/*
-	 * The hw-branch tracer needs to collect the trace from the various
-	 * cpu trace buffers - before tracing is stopped.
-	 */
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-	if (!iter)
-		return -ENOMEM;
-
-	memcpy(&tracer, trace, sizeof(tracer));
-
-	iter->trace = &tracer;
-	iter->tr = tr;
-	iter->pos = -1;
-	mutex_init(&iter->mutex);
-
-	trace->open(iter);
-
-	mutex_destroy(&iter->mutex);
-	kfree(iter);
-
-	tracing_stop();
-
-	ret = trace_test_buffer(tr, &count);
-	trace->reset(tr);
-	tracing_start();
-
-	if (!ret && !count) {
-		printk(KERN_CONT "no entries found..");
-		ret = -1;
-	}
-
-	return ret;
-}
-#endif /* CONFIG_HW_BRANCH_TRACER */
-
 #ifdef CONFIG_KSYM_TRACER
 static int ksym_selftest_dummy;
 

kernel/workqueue.c

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index dee4865..5bfb213 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -774,7 +774,7 @@
 {
 	if (del_timer_sync(&dwork->timer)) {
 		struct cpu_workqueue_struct *cwq;
-		cwq = wq_per_cpu(keventd_wq, get_cpu());
+		cwq = wq_per_cpu(get_wq_data(&dwork->work)->wq, get_cpu());
 		__queue_work(cwq, &dwork->work);
 		put_cpu();
 	}

lib/Kconfig.debug

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 935248b..930a9e5 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -512,6 +512,18 @@
 
 	 Say N if you are unsure.
 
+config PROVE_RCU_REPEATEDLY
+	bool "RCU debugging: don't disable PROVE_RCU on first splat"
+	depends on PROVE_RCU
+	default n
+	help
+	 By itself, PROVE_RCU will disable checking upon issuing the
+	 first warning (or "splat").  This feature prevents such
+	 disabling, allowing multiple RCU-lockdep warnings to be printed
+	 on a single reboot.
+
+	 Say N if you are unsure.
+
 config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
@@ -793,7 +805,7 @@
 config RCU_CPU_STALL_VERBOSE
 	bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR"
 	depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU
-	default n
+	default y
 	help
 	  This option causes RCU to printk detailed per-task information
 	  for any tasks that are stalling the current RCU grace period.

lib/btree.c

diff --git a/lib/btree.c b/lib/btree.c
index 41859a8..c9c6f03 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -95,7 +95,8 @@
 	unsigned long *node;
 
 	node = mempool_alloc(head->mempool, gfp);
-	memset(node, 0, NODESIZE);
+	if (likely(node))
+		memset(node, 0, NODESIZE);
 	return node;
 }
 

lib/debugobjects.c

diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index b862b30..deebcc5 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -141,6 +141,7 @@
 		obj->object = addr;
 		obj->descr  = descr;
 		obj->state  = ODEBUG_STATE_NONE;
+		obj->astate = 0;
 		hlist_del(&obj->node);
 
 		hlist_add_head(&obj->node, &b->list);
@@ -252,8 +253,10 @@
 
 	if (limit < 5 && obj->descr != descr_test) {
 		limit++;
-		WARN(1, KERN_ERR "ODEBUG: %s %s object type: %s\n", msg,
-		       obj_states[obj->state], obj->descr->name);
+		WARN(1, KERN_ERR "ODEBUG: %s %s (active state %u) "
+				 "object type: %s\n",
+			msg, obj_states[obj->state], obj->astate,
+			obj->descr->name);
 	}
 	debug_objects_warnings++;
 }
@@ -447,7 +450,10 @@
 		case ODEBUG_STATE_INIT:
 		case ODEBUG_STATE_INACTIVE:
 		case ODEBUG_STATE_ACTIVE:
-			obj->state = ODEBUG_STATE_INACTIVE;
+			if (!obj->astate)
+				obj->state = ODEBUG_STATE_INACTIVE;
+			else
+				debug_print_object(obj, "deactivate");
 			break;
 
 		case ODEBUG_STATE_DESTROYED:
@@ -553,6 +559,53 @@
 	raw_spin_unlock_irqrestore(&db->lock, flags);
 }
 
+/**
+ * debug_object_active_state - debug checks object usage state machine
+ * @addr:	address of the object
+ * @descr:	pointer to an object specific debug description structure
+ * @expect:	expected state
+ * @next:	state to move to if expected state is found
+ */
+void
+debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+			  unsigned int expect, unsigned int next)
+{
+	struct debug_bucket *db;
+	struct debug_obj *obj;
+	unsigned long flags;
+
+	if (!debug_objects_enabled)
+		return;
+
+	db = get_bucket((unsigned long) addr);
+
+	raw_spin_lock_irqsave(&db->lock, flags);
+
+	obj = lookup_object(addr, db);
+	if (obj) {
+		switch (obj->state) {
+		case ODEBUG_STATE_ACTIVE:
+			if (obj->astate == expect)
+				obj->astate = next;
+			else
+				debug_print_object(obj, "active_state");
+			break;
+
+		default:
+			debug_print_object(obj, "active_state");
+			break;
+		}
+	} else {
+		struct debug_obj o = { .object = addr,
+				       .state = ODEBUG_STATE_NOTAVAILABLE,
+				       .descr = descr };
+
+		debug_print_object(&o, "active_state");
+	}
+
+	raw_spin_unlock_irqrestore(&db->lock, flags);
+}
+
 #ifdef CONFIG_DEBUG_OBJECTS_FREE
 static void __debug_check_no_obj_freed(const void *address, unsigned long size)
 {
@@ -774,7 +827,7 @@
 	}
 }
 
-static int
+static int __init
 check_results(void *addr, enum debug_obj_state state, int fixups, int warnings)
 {
 	struct debug_bucket *db;
@@ -917,7 +970,7 @@
 /*
  * Convert the statically allocated objects to dynamic ones:
  */
-static int debug_objects_replace_static_objects(void)
+static int __init debug_objects_replace_static_objects(void)
 {
 	struct debug_bucket *db = obj_hash;
 	struct hlist_node *node, *tmp;

lib/rwsem.c

diff --git a/lib/rwsem.c b/lib/rwsem.c
index 3e3365e..ceba8e2 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -136,9 +136,10 @@
  out:
 	return sem;
 
-	/* undo the change to count, but check for a transition 1->0 */
+	/* undo the change to the active count, but check for a transition
+	 * 1->0 */
  undo:
-	if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) != 0)
+	if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) & RWSEM_ACTIVE_MASK)
 		goto out;
 	goto try_again;
 }

mm/hugetlb.c

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ffbdfc8..4c9e6bb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1039,7 +1039,7 @@
 		page = alloc_buddy_huge_page(h, vma, addr);
 		if (!page) {
 			hugetlb_put_quota(inode->i_mapping, chg);
-			return ERR_PTR(-VM_FAULT_OOM);
+			return ERR_PTR(-VM_FAULT_SIGBUS);
 		}
 	}
 

mm/memcontrol.c

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6c755de..8a79a6f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1601,7 +1601,6 @@
 			 * There is a small race that "from" or "to" can be
 			 * freed by rmdir, so we use css_tryget().
 			 */
-			rcu_read_lock();
 			from = mc.from;
 			to = mc.to;
 			if (from && css_tryget(&from->css)) {
@@ -1622,7 +1621,6 @@
 					do_continue = (to == mem_over_limit);
 				css_put(&to->css);
 			}
-			rcu_read_unlock();
 			if (do_continue) {
 				DEFINE_WAIT(wait);
 				prepare_to_wait(&mc.waitq, &wait,

mm/mlock.c

diff --git a/mm/mlock.c b/mm/mlock.c
index 8f4e2df..3f82720 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -607,44 +607,3 @@
 	spin_unlock(&shmlock_user_lock);
 	free_uid(user);
 }
-
-int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
-			  size_t size)
-{
-	unsigned long lim, vm, pgsz;
-	int error = -ENOMEM;
-
-	pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	down_write(&mm->mmap_sem);
-
-	lim = ACCESS_ONCE(rlim[RLIMIT_AS].rlim_cur) >> PAGE_SHIFT;
-	vm   = mm->total_vm + pgsz;
-	if (lim < vm)
-		goto out;
-
-	lim = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur) >> PAGE_SHIFT;
-	vm   = mm->locked_vm + pgsz;
-	if (lim < vm)
-		goto out;
-
-	mm->total_vm  += pgsz;
-	mm->locked_vm += pgsz;
-
-	error = 0;
- out:
-	up_write(&mm->mmap_sem);
-	return error;
-}
-
-void refund_locked_memory(struct mm_struct *mm, size_t size)
-{
-	unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	down_write(&mm->mmap_sem);
-
-	mm->total_vm  -= pgsz;
-	mm->locked_vm -= pgsz;
-
-	up_write(&mm->mmap_sem);
-}

mm/rmap.c

diff --git a/mm/rmap.c b/mm/rmap.c
index 07fc947..0feeef8 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -336,14 +336,13 @@
 
 /*
  * At what user virtual address is page expected in vma?
- * checking that the page matches the vma.
+ * Caller should check the page is actually part of the vma.
  */
 unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 {
-	if (PageAnon(page)) {
-		if (vma->anon_vma != page_anon_vma(page))
-			return -EFAULT;
-	} else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
+	if (PageAnon(page))
+		;
+	else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
 		if (!vma->vm_file ||
 		    vma->vm_file->f_mapping != page->mapping)
 			return -EFAULT;

mm/slub.c

diff --git a/mm/slub.c b/mm/slub.c
index 7d6c8b1..d2a54fe 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2153,7 +2153,7 @@
 	int local_node;
 
 	if (slab_state >= UP && (s < kmalloc_caches ||
-			s > kmalloc_caches + KMALLOC_CACHES))
+			s >= kmalloc_caches + KMALLOC_CACHES))
 		local_node = page_to_nid(virt_to_page(s));
 	else
 		local_node = 0;

net/core/dev.c

diff --git a/net/core/dev.c b/net/core/dev.c
index f769098..264137f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1451,7 +1451,7 @@
  *
  * return values:
  *	NET_RX_SUCCESS	(no congestion)
- *	NET_RX_DROP     (packet was dropped)
+ *	NET_RX_DROP     (packet was dropped, but freed)
  *
  * dev_forward_skb can be used for injecting an skb from the
  * start_xmit function of one device into the receive queue
@@ -1465,12 +1465,11 @@
 {
 	skb_orphan(skb);
 
-	if (!(dev->flags & IFF_UP))
+	if (!(dev->flags & IFF_UP) ||
+	    (skb->len > (dev->mtu + dev->hard_header_len))) {
+		kfree_skb(skb);
 		return NET_RX_DROP;
-
-	if (skb->len > (dev->mtu + dev->hard_header_len))
-		return NET_RX_DROP;
-
+	}
 	skb_set_dev(skb, dev);
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;

net/core/rtnetlink.c

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fe776c9..31e85d3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -602,12 +602,19 @@
 	a->tx_compressed = b->tx_compressed;
 };
 
+/* All VF info */
 static inline int rtnl_vfinfo_size(const struct net_device *dev)
 {
-	if (dev->dev.parent && dev_is_pci(dev->dev.parent))
-		return dev_num_vf(dev->dev.parent) *
-			sizeof(struct ifla_vf_info);
-	else
+	if (dev->dev.parent && dev_is_pci(dev->dev.parent)) {
+
+		int num_vfs = dev_num_vf(dev->dev.parent);
+		size_t size = nlmsg_total_size(sizeof(struct nlattr));
+		size += nlmsg_total_size(num_vfs * sizeof(struct nlattr));
+		size += num_vfs * (sizeof(struct ifla_vf_mac) +
+				  sizeof(struct ifla_vf_vlan) +
+				  sizeof(struct ifla_vf_tx_rate));
+		return size;
+	} else
 		return 0;
 }
 
@@ -629,7 +636,7 @@
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_NUM_VF */
-	       + nla_total_size(rtnl_vfinfo_size(dev)) /* IFLA_VFINFO */
+	       + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */
 	       + rtnl_link_get_size(dev); /* IFLA_LINKINFO */
 }
 
@@ -700,14 +707,37 @@
 
 	if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) {
 		int i;
-		struct ifla_vf_info ivi;
 
-		NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent));
-		for (i = 0; i < dev_num_vf(dev->dev.parent); i++) {
+		struct nlattr *vfinfo, *vf;
+		int num_vfs = dev_num_vf(dev->dev.parent);
+
+		NLA_PUT_U32(skb, IFLA_NUM_VF, num_vfs);
+		vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST);
+		if (!vfinfo)
+			goto nla_put_failure;
+		for (i = 0; i < num_vfs; i++) {
+			struct ifla_vf_info ivi;
+			struct ifla_vf_mac vf_mac;
+			struct ifla_vf_vlan vf_vlan;
+			struct ifla_vf_tx_rate vf_tx_rate;
 			if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi))
 				break;
-			NLA_PUT(skb, IFLA_VFINFO, sizeof(ivi), &ivi);
+			vf_mac.vf = vf_vlan.vf = vf_tx_rate.vf = ivi.vf;
+			memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
+			vf_vlan.vlan = ivi.vlan;
+			vf_vlan.qos = ivi.qos;
+			vf_tx_rate.rate = ivi.tx_rate;
+			vf = nla_nest_start(skb, IFLA_VF_INFO);
+			if (!vf) {
+				nla_nest_cancel(skb, vfinfo);
+				goto nla_put_failure;
+			}
+			NLA_PUT(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac);
+			NLA_PUT(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan);
+			NLA_PUT(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), &vf_tx_rate);
+			nla_nest_end(skb, vf);
 		}
+		nla_nest_end(skb, vfinfo);
 	}
 	if (dev->rtnl_link_ops) {
 		if (rtnl_link_fill(skb, dev) < 0)
@@ -769,12 +799,7 @@
 	[IFLA_LINKINFO]		= { .type = NLA_NESTED },
 	[IFLA_NET_NS_PID]	= { .type = NLA_U32 },
 	[IFLA_IFALIAS]	        = { .type = NLA_STRING, .len = IFALIASZ-1 },
-	[IFLA_VF_MAC]		= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_mac) },
-	[IFLA_VF_VLAN]		= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_vlan) },
-	[IFLA_VF_TX_RATE]	= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_tx_rate) },
+	[IFLA_VFINFO_LIST]	= {. type = NLA_NESTED },
 };
 EXPORT_SYMBOL(ifla_policy);
 
@@ -783,6 +808,19 @@
 	[IFLA_INFO_DATA]	= { .type = NLA_NESTED },
 };
 
+static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
+	[IFLA_VF_INFO]		= { .type = NLA_NESTED },
+};
+
+static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
+	[IFLA_VF_MAC]		= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_mac) },
+	[IFLA_VF_VLAN]		= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_vlan) },
+	[IFLA_VF_TX_RATE]	= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_tx_rate) },
+};
+
 struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[])
 {
 	struct net *net;
@@ -812,6 +850,52 @@
 	return 0;
 }
 
+static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
+{
+	int rem, err = -EINVAL;
+	struct nlattr *vf;
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	nla_for_each_nested(vf, attr, rem) {
+		switch (nla_type(vf)) {
+		case IFLA_VF_MAC: {
+			struct ifla_vf_mac *ivm;
+			ivm = nla_data(vf);
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_mac)
+				err = ops->ndo_set_vf_mac(dev, ivm->vf,
+							  ivm->mac);
+			break;
+		}
+		case IFLA_VF_VLAN: {
+			struct ifla_vf_vlan *ivv;
+			ivv = nla_data(vf);
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_vlan)
+				err = ops->ndo_set_vf_vlan(dev, ivv->vf,
+							   ivv->vlan,
+							   ivv->qos);
+			break;
+		}
+		case IFLA_VF_TX_RATE: {
+			struct ifla_vf_tx_rate *ivt;
+			ivt = nla_data(vf);
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_tx_rate)
+				err = ops->ndo_set_vf_tx_rate(dev, ivt->vf,
+							      ivt->rate);
+			break;
+		}
+		default:
+			err = -EINVAL;
+			break;
+		}
+		if (err)
+			break;
+	}
+	return err;
+}
+
 static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 		      struct nlattr **tb, char *ifname, int modified)
 {
@@ -942,40 +1026,17 @@
 		write_unlock_bh(&dev_base_lock);
 	}
 
-	if (tb[IFLA_VF_MAC]) {
-		struct ifla_vf_mac *ivm;
-		ivm = nla_data(tb[IFLA_VF_MAC]);
-		err = -EOPNOTSUPP;
-		if (ops->ndo_set_vf_mac)
-			err = ops->ndo_set_vf_mac(dev, ivm->vf, ivm->mac);
-		if (err < 0)
-			goto errout;
-		modified = 1;
-	}
-
-	if (tb[IFLA_VF_VLAN]) {
-		struct ifla_vf_vlan *ivv;
-		ivv = nla_data(tb[IFLA_VF_VLAN]);
-		err = -EOPNOTSUPP;
-		if (ops->ndo_set_vf_vlan)
-			err = ops->ndo_set_vf_vlan(dev, ivv->vf,
-						   ivv->vlan,
-						   ivv->qos);
-		if (err < 0)
-			goto errout;
-		modified = 1;
-	}
-	err = 0;
-
-	if (tb[IFLA_VF_TX_RATE]) {
-		struct ifla_vf_tx_rate *ivt;
-		ivt = nla_data(tb[IFLA_VF_TX_RATE]);
-		err = -EOPNOTSUPP;
-		if (ops->ndo_set_vf_tx_rate)
-			err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, ivt->rate);
-		if (err < 0)
-			goto errout;
-		modified = 1;
+	if (tb[IFLA_VFINFO_LIST]) {
+		struct nlattr *attr;
+		int rem;
+		nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
+			if (nla_type(attr) != IFLA_VF_INFO)
+				goto errout;
+			err = do_setvfinfo(dev, attr);
+			if (err < 0)
+				goto errout;
+			modified = 1;
+		}
 	}
 	err = 0;
 

net/ipv4/arp.c

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 6e74706..80769f1 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -661,13 +661,13 @@
 #endif
 #endif
 
-#ifdef CONFIG_FDDI
+#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE)
 	case ARPHRD_FDDI:
 		arp->ar_hrd = htons(ARPHRD_ETHER);
 		arp->ar_pro = htons(ETH_P_IP);
 		break;
 #endif
-#ifdef CONFIG_TR
+#if defined(CONFIG_TR) || defined(CONFIG_TR_MODULE)
 	case ARPHRD_IEEE802_TR:
 		arp->ar_hrd = htons(ARPHRD_IEEE802);
 		arp->ar_pro = htons(ETH_P_IP);
@@ -1051,7 +1051,7 @@
 			return -EINVAL;
 	}
 	switch (dev->type) {
-#ifdef CONFIG_FDDI
+#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE)
 	case ARPHRD_FDDI:
 		/*
 		 * According to RFC 1390, FDDI devices should accept ARP

net/ipv4/ipmr.c

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d4f6d1..ec19a89 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -754,7 +754,8 @@
 		c->next = mfc_unres_queue;
 		mfc_unres_queue = c;
 
-		mod_timer(&ipmr_expire_timer, c->mfc_un.unres.expires);
+		if (atomic_read(&net->ipv4.cache_resolve_queue_len) == 1)
+			mod_timer(&ipmr_expire_timer, c->mfc_un.unres.expires);
 	}
 
 	/*

net/ipv4/tcp.c

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0f8caf6..296150b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2839,7 +2839,6 @@
 			if (p->md5_desc.tfm)
 				crypto_free_hash(p->md5_desc.tfm);
 			kfree(p);
-			p = NULL;
 		}
 	}
 	free_percpu(pool);
@@ -2937,25 +2936,40 @@
 
 EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
 
-struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu)
+
+/**
+ *	tcp_get_md5sig_pool - get md5sig_pool for this user
+ *
+ *	We use percpu structure, so if we succeed, we exit with preemption
+ *	and BH disabled, to make sure another thread or softirq handling
+ *	wont try to get same context.
+ */
+struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 {
 	struct tcp_md5sig_pool * __percpu *p;
-	spin_lock_bh(&tcp_md5sig_pool_lock);
+
+	local_bh_disable();
+
+	spin_lock(&tcp_md5sig_pool_lock);
 	p = tcp_md5sig_pool;
 	if (p)
 		tcp_md5sig_users++;
-	spin_unlock_bh(&tcp_md5sig_pool_lock);
-	return (p ? *per_cpu_ptr(p, cpu) : NULL);
+	spin_unlock(&tcp_md5sig_pool_lock);
+
+	if (p)
+		return *per_cpu_ptr(p, smp_processor_id());
+
+	local_bh_enable();
+	return NULL;
 }
+EXPORT_SYMBOL(tcp_get_md5sig_pool);
 
-EXPORT_SYMBOL(__tcp_get_md5sig_pool);
-
-void __tcp_put_md5sig_pool(void)
+void tcp_put_md5sig_pool(void)
 {
+	local_bh_enable();
 	tcp_free_md5sig_pool();
 }
-
-EXPORT_SYMBOL(__tcp_put_md5sig_pool);
+EXPORT_SYMBOL(tcp_put_md5sig_pool);
 
 int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
 			struct tcphdr *th)

net/ipv4/udp.c

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8fef859..c36522a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1527,6 +1527,9 @@
 
 	uh   = udp_hdr(skb);
 	ulen = ntohs(uh->len);
+	saddr = ip_hdr(skb)->saddr;
+	daddr = ip_hdr(skb)->daddr;
+
 	if (ulen > skb->len)
 		goto short_packet;
 
@@ -1540,9 +1543,6 @@
 	if (udp4_csum_init(skb, uh, proto))
 		goto csum_error;
 
-	saddr = ip_hdr(skb)->saddr;
-	daddr = ip_hdr(skb)->daddr;
-
 	if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
 		return __udp4_lib_mcast_deliver(net, skb, uh,
 				saddr, daddr, udptable);

net/ipv6/af_inet6.c

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3192aa0..3f9e86b 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -200,7 +200,7 @@
 
 	inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
 	np->hop_limit	= -1;
-	np->mcast_hops	= -1;
+	np->mcast_hops	= IPV6_DEFAULT_MCASTHOPS;
 	np->mc_loop	= 1;
 	np->pmtudisc	= IPV6_PMTUDISC_WANT;
 	np->ipv6only	= net->ipv6.sysctl.bindv6only;

net/ipv6/datagram.c

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 622dc79..6157388 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -222,6 +222,8 @@
 	if (!skb)
 		return;
 
+	skb->protocol = htons(ETH_P_IPV6);
+
 	serr = SKB_EXT_ERR(skb);
 	serr->ee.ee_errno = err;
 	serr->ee.ee_origin = SO_EE_ORIGIN_ICMP6;
@@ -255,6 +257,8 @@
 	if (!skb)
 		return;
 
+	skb->protocol = htons(ETH_P_IPV6);
+
 	skb_put(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	iph = ipv6_hdr(skb);
@@ -319,7 +323,7 @@
 		sin->sin6_flowinfo = 0;
 		sin->sin6_port = serr->port;
 		sin->sin6_scope_id = 0;
-		if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) {
+		if (skb->protocol == htons(ETH_P_IPV6)) {
 			ipv6_addr_copy(&sin->sin6_addr,
 				  (struct in6_addr *)(nh + serr->addr_offset));
 			if (np->sndflow)
@@ -341,7 +345,7 @@
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
 		sin->sin6_scope_id = 0;
-		if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) {
+		if (skb->protocol == htons(ETH_P_IPV6)) {
 			ipv6_addr_copy(&sin->sin6_addr, &ipv6_hdr(skb)->saddr);
 			if (np->rxopt.all)
 				datagram_recv_ctl(sk, msg, skb);

net/llc/llc_sap.c

diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index a432f0e..94e7fca 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -31,7 +31,7 @@
 	case ARPHRD_ETHER:
 	case ARPHRD_LOOPBACK:
 		return sizeof(struct ethhdr);
-#ifdef CONFIG_TR
+#if defined(CONFIG_TR) || defined(CONFIG_TR_MODULE)
 	case ARPHRD_IEEE802_TR:
 		return sizeof(struct trh_hdr);
 #endif

net/mac80211/mlme.c

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 4aefa6d..875c8de 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2030,7 +2030,8 @@
 				continue;
 
 			if (wk->type != IEEE80211_WORK_DIRECT_PROBE &&
-			    wk->type != IEEE80211_WORK_AUTH)
+			    wk->type != IEEE80211_WORK_AUTH &&
+			    wk->type != IEEE80211_WORK_ASSOC)
 				continue;
 
 			if (memcmp(req->bss->bssid, wk->filter_ta, ETH_ALEN))

net/sctp/input.c

diff --git a/net/sctp/input.c b/net/sctp/input.c
index 2a57018..ea21924 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -440,11 +440,25 @@
 {
 	SCTP_DEBUG_PRINTK("%s\n",  __func__);
 
-	sctp_do_sm(SCTP_EVENT_T_OTHER,
-		   SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH),
-		   asoc->state, asoc->ep, asoc, t,
-		   GFP_ATOMIC);
+	if (sock_owned_by_user(sk)) {
+		if (timer_pending(&t->proto_unreach_timer))
+			return;
+		else {
+			if (!mod_timer(&t->proto_unreach_timer,
+						jiffies + (HZ/20)))
+				sctp_association_hold(asoc);
+		}
+			
+	} else {
+		if (timer_pending(&t->proto_unreach_timer) &&
+		    del_timer(&t->proto_unreach_timer))
+			sctp_association_put(asoc);
 
+		sctp_do_sm(SCTP_EVENT_T_OTHER,
+			   SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH),
+			   asoc->state, asoc->ep, asoc, t,
+			   GFP_ATOMIC);
+	}
 }
 
 /* Common lookup code for icmp/icmpv6 error handler. */

net/sctp/sm_make_chunk.c

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 0fd5b4c..30c1767 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -108,7 +108,7 @@
 	cpu_to_be16(sizeof(struct sctp_paramhdr)),
 };
 
-/* A helper to initialize to initialize an op error inside a
+/* A helper to initialize an op error inside a
  * provided chunk, as most cause codes will be embedded inside an
  * abort chunk.
  */
@@ -125,6 +125,29 @@
 	chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(sctp_errhdr_t), &err);
 }
 
+/* A helper to initialize an op error inside a
+ * provided chunk, as most cause codes will be embedded inside an
+ * abort chunk.  Differs from sctp_init_cause in that it won't oops
+ * if there isn't enough space in the op error chunk
+ */
+int sctp_init_cause_fixed(struct sctp_chunk *chunk, __be16 cause_code,
+		      size_t paylen)
+{
+	sctp_errhdr_t err;
+	__u16 len;
+
+	/* Cause code constants are now defined in network order.  */
+	err.cause = cause_code;
+	len = sizeof(sctp_errhdr_t) + paylen;
+	err.length  = htons(len);
+
+	if (skb_tailroom(chunk->skb) >  len)
+		return -ENOSPC;
+	chunk->subh.err_hdr = sctp_addto_chunk_fixed(chunk,
+						     sizeof(sctp_errhdr_t),
+						     &err);
+	return 0;
+}
 /* 3.3.2 Initiation (INIT) (1)
  *
  * This chunk is used to initiate a SCTP association between two
@@ -1132,6 +1155,24 @@
 	return retval;
 }
 
+/* Create an Operation Error chunk of a fixed size,
+ * specifically, max(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT)
+ * This is a helper function to allocate an error chunk for
+ * for those invalid parameter codes in which we may not want
+ * to report all the errors, if the incomming chunk is large
+ */
+static inline struct sctp_chunk *sctp_make_op_error_fixed(
+	const struct sctp_association *asoc,
+	const struct sctp_chunk *chunk)
+{
+	size_t size = asoc ? asoc->pathmtu : 0;
+
+	if (!size)
+		size = SCTP_DEFAULT_MAXSEGMENT;
+
+	return sctp_make_op_error_space(asoc, chunk, size);
+}
+
 /* Create an Operation Error chunk.  */
 struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc,
 				 const struct sctp_chunk *chunk,
@@ -1374,6 +1415,18 @@
 	return target;
 }
 
+/* Append bytes to the end of a chunk. Returns NULL if there isn't sufficient
+ * space in the chunk
+ */
+void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk,
+			     int len, const void *data)
+{
+	if (skb_tailroom(chunk->skb) > len)
+		return sctp_addto_chunk(chunk, len, data);
+	else
+		return NULL;
+}
+
 /* Append bytes from user space to the end of a chunk.  Will panic if
  * chunk is not big enough.
  * Returns a kernel err value.
@@ -1977,13 +2030,12 @@
 		 * returning multiple unknown parameters.
 		 */
 		if (NULL == *errp)
-			*errp = sctp_make_op_error_space(asoc, chunk,
-					ntohs(chunk->chunk_hdr->length));
+			*errp = sctp_make_op_error_fixed(asoc, chunk);
 
 		if (*errp) {
-			sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM,
+			sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM,
 					WORD_ROUND(ntohs(param.p->length)));
-			sctp_addto_chunk(*errp,
+			sctp_addto_chunk_fixed(*errp,
 					WORD_ROUND(ntohs(param.p->length)),
 					param.v);
 		} else {

net/sctp/sm_sideeffect.c

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index d5ae450..eb1f42f 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -397,6 +397,41 @@
 	sctp_transport_put(transport);
 }
 
+/* Handle the timeout of the ICMP protocol unreachable timer.  Trigger
+ * the correct state machine transition that will close the association.
+ */
+void sctp_generate_proto_unreach_event(unsigned long data)
+{
+	struct sctp_transport *transport = (struct sctp_transport *) data;
+	struct sctp_association *asoc = transport->asoc;
+	
+	sctp_bh_lock_sock(asoc->base.sk);
+	if (sock_owned_by_user(asoc->base.sk)) {
+		SCTP_DEBUG_PRINTK("%s:Sock is busy.\n", __func__);
+
+		/* Try again later.  */
+		if (!mod_timer(&transport->proto_unreach_timer,
+				jiffies + (HZ/20)))
+			sctp_association_hold(asoc);
+		goto out_unlock;
+	}
+
+	/* Is this structure just waiting around for us to actually
+	 * get destroyed?
+	 */
+	if (asoc->base.dead)
+		goto out_unlock;
+
+	sctp_do_sm(SCTP_EVENT_T_OTHER,
+		   SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH),
+		   asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC);
+
+out_unlock:
+	sctp_bh_unlock_sock(asoc->base.sk);
+	sctp_association_put(asoc);
+}
+
+
 /* Inject a SACK Timeout event into the state machine.  */
 static void sctp_generate_sack_event(unsigned long data)
 {

net/sctp/transport.c

diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index be4d63d..165d54e 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -108,6 +108,8 @@
 			(unsigned long)peer);
 	setup_timer(&peer->hb_timer, sctp_generate_heartbeat_event,
 			(unsigned long)peer);
+	setup_timer(&peer->proto_unreach_timer,
+		    sctp_generate_proto_unreach_event, (unsigned long)peer);
 
 	/* Initialize the 64-bit random nonce sent with heartbeat. */
 	get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce));
@@ -171,6 +173,10 @@
 	    del_timer(&transport->T3_rtx_timer))
 		sctp_transport_put(transport);
 
+	/* Delete the ICMP proto unreachable timer if it's active. */
+	if (timer_pending(&transport->proto_unreach_timer) &&
+	    del_timer(&transport->proto_unreach_timer))
+		sctp_association_put(transport->asoc);
 
 	sctp_transport_put(transport);
 }

scripts/mod/file2alias.c

diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 220213e..df90f31 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -796,6 +796,16 @@
 	return 1;
 }
 
+/* Looks like: zorro:iN. */
+static int do_zorro_entry(const char *filename, struct zorro_device_id *id,
+			  char *alias)
+{
+	id->id = TO_NATIVE(id->id);
+	strcpy(alias, "zorro:");
+	ADD(alias, "i", id->id != ZORRO_WILDCARD, id->id);
+	return 1;
+}
+
 /* Ignore any prefix, eg. some architectures prepend _ */
 static inline int sym_is(const char *symbol, const char *name)
 {
@@ -943,6 +953,10 @@
 		do_table(symval, sym->st_size,
 			 sizeof(struct platform_device_id), "platform",
 			 do_platform_entry, mod);
+	else if (sym_is(symname, "__mod_zorro_device_table"))
+		do_table(symval, sym->st_size,
+			 sizeof(struct zorro_device_id), "zorro",
+			 do_zorro_entry, mod);
 	free(zeros);
 }
 

security/keys/gc.c

diff --git a/security/keys/gc.c b/security/keys/gc.c
index 1990231..a46e825 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -77,10 +77,10 @@
 		goto dont_gc;
 
 	/* scan the keyring looking for dead keys */
-	klist = rcu_dereference_check(keyring->payload.subscriptions,
-				      lockdep_is_held(&key_serial_lock));
+	rcu_read_lock();
+	klist = rcu_dereference(keyring->payload.subscriptions);
 	if (!klist)
-		goto dont_gc;
+		goto unlock_dont_gc;
 
 	for (loop = klist->nkeys - 1; loop >= 0; loop--) {
 		key = klist->keys[loop];
@@ -89,11 +89,14 @@
 			goto do_gc;
 	}
 
+unlock_dont_gc:
+	rcu_read_unlock();
 dont_gc:
 	kleave(" = false");
 	return false;
 
 do_gc:
+	rcu_read_unlock();
 	key_gc_cursor = keyring->serial;
 	key_get(keyring);
 	spin_unlock(&key_serial_lock);

security/keys/keyring.c

diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index dd7cd0f..1e4b003 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -20,6 +20,11 @@
 #include <asm/uaccess.h>
 #include "internal.h"
 
+#define rcu_dereference_locked_keyring(keyring)				\
+	(rcu_dereference_protected(					\
+		(keyring)->payload.subscriptions,			\
+		rwsem_is_locked((struct rw_semaphore *)&(keyring)->sem)))
+
 /*
  * when plumbing the depths of the key tree, this sets a hard limit set on how
  * deep we're willing to go
@@ -201,8 +206,7 @@
 	int loop, ret;
 
 	ret = 0;
-	klist = keyring->payload.subscriptions;
-
+	klist = rcu_dereference_locked_keyring(keyring);
 	if (klist) {
 		/* calculate how much data we could return */
 		qty = klist->nkeys * sizeof(key_serial_t);
@@ -526,9 +530,8 @@
 	struct key *keyring;
 	int bucket;
 
-	keyring = ERR_PTR(-EINVAL);
 	if (!name)
-		goto error;
+		return ERR_PTR(-EINVAL);
 
 	bucket = keyring_hash(name);
 
@@ -555,17 +558,18 @@
 					   KEY_SEARCH) < 0)
 				continue;
 
-			/* we've got a match */
-			atomic_inc(&keyring->usage);
-			read_unlock(&keyring_name_lock);
-			goto error;
+			/* we've got a match but we might end up racing with
+			 * key_cleanup() if the keyring is currently 'dead'
+			 * (ie. it has a zero usage count) */
+			if (!atomic_inc_not_zero(&keyring->usage))
+				continue;
+			goto out;
 		}
 	}
 
-	read_unlock(&keyring_name_lock);
 	keyring = ERR_PTR(-ENOKEY);
-
- error:
+out:
+	read_unlock(&keyring_name_lock);
 	return keyring;
 
 } /* end find_keyring_by_name() */
@@ -720,8 +724,7 @@
 	}
 
 	/* see if there's a matching key we can displace */
-	klist = keyring->payload.subscriptions;
-
+	klist = rcu_dereference_locked_keyring(keyring);
 	if (klist && klist->nkeys > 0) {
 		struct key_type *type = key->type;
 
@@ -765,8 +768,6 @@
 	if (ret < 0)
 		goto error2;
 
-	klist = keyring->payload.subscriptions;
-
 	if (klist && klist->nkeys < klist->maxkeys) {
 		/* there's sufficient slack space to add directly */
 		atomic_inc(&key->usage);
@@ -868,7 +869,7 @@
 
 	down_write(&keyring->sem);
 
-	klist = keyring->payload.subscriptions;
+	klist = rcu_dereference_locked_keyring(keyring);
 	if (klist) {
 		/* search the keyring for the key */
 		for (loop = 0; loop < klist->nkeys; loop++)
@@ -959,7 +960,7 @@
 		/* detach the pointer block with the locks held */
 		down_write(&keyring->sem);
 
-		klist = keyring->payload.subscriptions;
+		klist = rcu_dereference_locked_keyring(keyring);
 		if (klist) {
 			/* adjust the quota */
 			key_payload_reserve(keyring,
@@ -991,7 +992,9 @@
  */
 static void keyring_revoke(struct key *keyring)
 {
-	struct keyring_list *klist = keyring->payload.subscriptions;
+	struct keyring_list *klist;
+
+	klist = rcu_dereference_locked_keyring(keyring);
 
 	/* adjust the quota */
 	key_payload_reserve(keyring, 0);
@@ -1025,7 +1028,7 @@
 
 	down_write(&keyring->sem);
 
-	klist = keyring->payload.subscriptions;
+	klist = rcu_dereference_locked_keyring(keyring);
 	if (!klist)
 		goto no_klist;
 

security/keys/request_key.c

diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index d737cea..d8c1a6a 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -94,7 +94,7 @@
 	}
 
 	/* attach the auth key to the session keyring */
-	ret = __key_link(keyring, authkey);
+	ret = key_link(keyring, authkey);
 	if (ret < 0)
 		goto error_link;
 

security/keys/user_defined.c

diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 7c687d5..e9aa079 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -199,7 +199,8 @@
 	struct user_key_payload *upayload;
 	long ret;
 
-	upayload = rcu_dereference(key->payload.data);
+	upayload = rcu_dereference_protected(
+		key->payload.data, rwsem_is_locked(&((struct key *)key)->sem));
 	ret = upayload->datalen;
 
 	/* we can return the data as is */

security/min_addr.c

diff --git a/security/min_addr.c b/security/min_addr.c
index e86f297..f728728 100644
--- a/security/min_addr.c
+++ b/security/min_addr.c
@@ -33,7 +33,7 @@
 {
 	int ret;
 
-	if (!capable(CAP_SYS_RAWIO))
+	if (write && !capable(CAP_SYS_RAWIO))
 		return -EPERM;
 
 	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);

sound/core/pcm_native.c

diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 8728876..20b5982 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -36,6 +36,9 @@
 #include <sound/timer.h>
 #include <sound/minors.h>
 #include <asm/io.h>
+#if defined(CONFIG_MIPS) && defined(CONFIG_DMA_NONCOHERENT)
+#include <dma-coherence.h>
+#endif
 
 /*
  *  Compatibility
@@ -3184,6 +3187,10 @@
 					 substream->runtime->dma_area,
 					 substream->runtime->dma_addr,
 					 area->vm_end - area->vm_start);
+#elif defined(CONFIG_MIPS) && defined(CONFIG_DMA_NONCOHERENT)
+	if (substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV &&
+	    !plat_device_is_coherent(substream->dma_buffer.dev.dev))
+		area->vm_page_prot = pgprot_noncached(area->vm_page_prot);
 #endif /* ARCH_HAS_DMA_MMAP_COHERENT */
 	/* mmap with fault handler */
 	area->vm_ops = &snd_pcm_vm_ops_data_fault;

sound/core/timer.c

diff --git a/sound/core/timer.c b/sound/core/timer.c
index 7394365..5040c7b 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -1160,6 +1160,7 @@
 {
 	struct snd_timer_user *tu = timeri->callback_data;
 	struct snd_timer_tread r1;
+	unsigned long flags;
 
 	if (event >= SNDRV_TIMER_EVENT_START &&
 	    event <= SNDRV_TIMER_EVENT_PAUSE)
@@ -1169,9 +1170,9 @@
 	r1.event = event;
 	r1.tstamp = *tstamp;
 	r1.val = resolution;
-	spin_lock(&tu->qlock);
+	spin_lock_irqsave(&tu->qlock, flags);
 	snd_timer_user_append_to_tqueue(tu, &r1);
-	spin_unlock(&tu->qlock);
+	spin_unlock_irqrestore(&tu->qlock, flags);
 	kill_fasync(&tu->fasync, SIGIO, POLL_IN);
 	wake_up(&tu->qchange_sleep);
 }

sound/drivers/pcsp/pcsp.h

diff --git a/sound/drivers/pcsp/pcsp.h b/sound/drivers/pcsp/pcsp.h
index 1e12307..4ff6c8c 100644
--- a/sound/drivers/pcsp/pcsp.h
+++ b/sound/drivers/pcsp/pcsp.h
@@ -16,7 +16,7 @@
 #include <asm/i8253.h>
 #else
 #include <asm/8253pit.h>
-static DEFINE_SPINLOCK(i8253_lock);
+static DEFINE_RAW_SPINLOCK(i8253_lock);
 #endif
 
 #define PCSP_SOUND_VERSION 0x400	/* read 4.00 */

sound/drivers/pcsp/pcsp_input.c

diff --git a/sound/drivers/pcsp/pcsp_input.c b/sound/drivers/pcsp/pcsp_input.c
index 0444cde..b5e2b54 100644
--- a/sound/drivers/pcsp/pcsp_input.c
+++ b/sound/drivers/pcsp/pcsp_input.c
@@ -21,7 +21,7 @@
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 
 	if (count) {
 		/* set command for counter 2, 2 byte write */
@@ -36,7 +36,7 @@
 		outb(inb_p(0x61) & 0xFC, 0x61);
 	}
 
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 }
 
 void pcspkr_stop_sound(void)

sound/drivers/pcsp/pcsp_lib.c

diff --git a/sound/drivers/pcsp/pcsp_lib.c b/sound/drivers/pcsp/pcsp_lib.c
index d77ffa9..ce9e7d1 100644
--- a/sound/drivers/pcsp/pcsp_lib.c
+++ b/sound/drivers/pcsp/pcsp_lib.c
@@ -66,7 +66,7 @@
 	timer_cnt = val * CUR_DIV() / 256;
 
 	if (timer_cnt && chip->enable) {
-		spin_lock_irqsave(&i8253_lock, flags);
+		raw_spin_lock_irqsave(&i8253_lock, flags);
 		if (!nforce_wa) {
 			outb_p(chip->val61, 0x61);
 			outb_p(timer_cnt, 0x42);
@@ -75,7 +75,7 @@
 			outb(chip->val61 ^ 2, 0x61);
 			chip->thalf = 1;
 		}
-		spin_unlock_irqrestore(&i8253_lock, flags);
+		raw_spin_unlock_irqrestore(&i8253_lock, flags);
 	}
 
 	chip->ns_rem = PCSP_PERIOD_NS();
@@ -159,10 +159,10 @@
 		return -EIO;
 	}
 
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 	chip->val61 = inb(0x61) | 0x03;
 	outb_p(0x92, 0x43);	/* binary, mode 1, LSB only, ch 2 */
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 	atomic_set(&chip->timer_active, 1);
 	chip->thalf = 0;
 
@@ -179,11 +179,11 @@
 		return;
 
 	atomic_set(&chip->timer_active, 0);
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 	/* restore the timer */
 	outb_p(0xb6, 0x43);	/* binary, mode 3, LSB/MSB, ch 2 */
 	outb(chip->val61 & 0xFC, 0x61);
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 }
 
 /*

sound/isa/sb/es968.c

diff --git a/sound/isa/sb/es968.c b/sound/isa/sb/es968.c
index cafc3a7..ff18286f 100644
--- a/sound/isa/sb/es968.c
+++ b/sound/isa/sb/es968.c
@@ -93,7 +93,7 @@
 		return err;
 	}
 	port[dev] = pnp_port_start(pdev, 0);
-	dma8[dev] = pnp_dma(pdev, 1);
+	dma8[dev] = pnp_dma(pdev, 0);
 	irq[dev] = pnp_irq(pdev, 0);
 
 	return 0;

sound/oss/dmasound/dmasound_paula.c

diff --git a/sound/oss/dmasound/dmasound_paula.c b/sound/oss/dmasound/dmasound_paula.c
index bb14e4c..87910e9 100644
--- a/sound/oss/dmasound/dmasound_paula.c
+++ b/sound/oss/dmasound/dmasound_paula.c
@@ -21,6 +21,7 @@
 #include <linux/ioport.h>
 #include <linux/soundcard.h>
 #include <linux/interrupt.h>
+#include <linux/platform_device.h>
 
 #include <asm/uaccess.h>
 #include <asm/setup.h>
@@ -710,31 +711,41 @@
 /*** Config & Setup **********************************************************/
 
 
-static int __init dmasound_paula_init(void)
+static int __init amiga_audio_probe(struct platform_device *pdev)
 {
-	int err;
-
-	if (MACH_IS_AMIGA && AMIGAHW_PRESENT(AMI_AUDIO)) {
-	    if (!request_mem_region(CUSTOM_PHYSADDR+0xa0, 0x40,
-				    "dmasound [Paula]"))
-		return -EBUSY;
-	    dmasound.mach = machAmiga;
-	    dmasound.mach.default_hard = def_hard ;
-	    dmasound.mach.default_soft = def_soft ;
-	    err = dmasound_init();
-	    if (err)
-		release_mem_region(CUSTOM_PHYSADDR+0xa0, 0x40);
-	    return err;
-	} else
-	    return -ENODEV;
+	dmasound.mach = machAmiga;
+	dmasound.mach.default_hard = def_hard ;
+	dmasound.mach.default_soft = def_soft ;
+	return dmasound_init();
 }
 
-static void __exit dmasound_paula_cleanup(void)
+static int __exit amiga_audio_remove(struct platform_device *pdev)
 {
 	dmasound_deinit();
-	release_mem_region(CUSTOM_PHYSADDR+0xa0, 0x40);
+	return 0;
 }
 
-module_init(dmasound_paula_init);
-module_exit(dmasound_paula_cleanup);
+static struct platform_driver amiga_audio_driver = {
+	.remove = __exit_p(amiga_audio_remove),
+	.driver   = {
+		.name	= "amiga-audio",
+		.owner	= THIS_MODULE,
+	},
+};
+
+static int __init amiga_audio_init(void)
+{
+	return platform_driver_probe(&amiga_audio_driver, amiga_audio_probe);
+}
+
+module_init(amiga_audio_init);
+
+static void __exit amiga_audio_exit(void)
+{
+	platform_driver_unregister(&amiga_audio_driver);
+}
+
+module_exit(amiga_audio_exit);
+
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:amiga-audio");

sound/pci/hda/patch_cirrus.c

diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index 7de782a..350ee8a 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -766,7 +766,7 @@
 		for (n = 0; n < AUTO_PIN_LAST; n++) {
 			if (!spec->adc_nid[n])
 				continue;
-			err = snd_hda_add_nid(codec, kctl, 0, spec->adc_nid[i]);
+			err = snd_hda_add_nid(codec, kctl, 0, spec->adc_nid[n]);
 			if (err < 0)
 				return err;
 		}

sound/pci/hda/patch_conexant.c

diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 61682e1..feabb44 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -1195,10 +1195,12 @@
 
 	switch (codec->subsystem_id >> 16) {
 	case 0x103c:
+	case 0x1631:
 	case 0x1734:
-		/* HP & Fujitsu-Siemens laptops have really bad sound over 0dB
-		 * on NID 0x17. Fix max PCM level to 0 dB
-		 * (originally it has 0x2b steps with 0dB offset 0x14)
+	case 0x17aa:
+		/* HP, Packard Bell, Fujitsu-Siemens & Lenovo laptops have
+		 * really bad sound over 0dB on NID 0x17. Fix max PCM level to
+		 * 0 dB (originally it has 0x2b steps with 0dB offset 0x14)
 		 */
 		snd_hda_override_amp_caps(codec, 0x17, HDA_INPUT,
 					  (0x14 << AC_AMPCAP_OFFSET_SHIFT) |
@@ -2842,6 +2844,10 @@
 		      CXT5066_DELL_LAPTOP),
 	SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT5066_OLPC_XO_1_5),
 	SND_PCI_QUIRK(0x1028, 0x0402, "Dell Vostro", CXT5066_DELL_VOSTO),
+	SND_PCI_QUIRK(0x1028, 0x0408, "Dell Inspiron One 19T", CXT5066_IDEAPAD),
+	SND_PCI_QUIRK(0x1179, 0xff50, "Toshiba Satellite P500-PSPGSC-01800T", CXT5066_OLPC_XO_1_5),
+	SND_PCI_QUIRK(0x1179, 0xffe0, "Toshiba Satellite Pro T130-15F", CXT5066_OLPC_XO_1_5),
+	SND_PCI_QUIRK(0x17aa, 0x21b2, "Thinkpad X100e", CXT5066_IDEAPAD),
 	SND_PCI_QUIRK(0x17aa, 0x3a0d, "ideapad", CXT5066_IDEAPAD),
 	{}
 };

sound/pci/hda/patch_realtek.c

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 7404dba..886d8e4 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -17871,7 +17871,6 @@
 					ALC662_3ST_6ch_DIG),
 	SND_PCI_QUIRK_MASK(0x1854, 0xf000, 0x2000, "ASUS H13-200x",
 			   ALC663_ASUS_H13),
-	SND_PCI_QUIRK(0x8086, 0xd604, "Intel mobo", ALC662_3ST_2ch_DIG),
 	{}
 };
 

sound/pci/hda/patch_sigmatel.c

diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 7fb7d01..a0e06d8 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -104,6 +104,7 @@
 	STAC_DELL_M4_2,
 	STAC_DELL_M4_3,
 	STAC_HP_M4,
+	STAC_HP_DV4,
 	STAC_HP_DV5,
 	STAC_HP_HDX,
 	STAC_HP_DV4_1222NR,
@@ -1544,11 +1545,9 @@
 	0x904601b0,
 };
 
-static unsigned int intel_dg45id_pin_configs[14] = {
+static unsigned int intel_dg45id_pin_configs[13] = {
 	0x02214230, 0x02A19240, 0x01013214, 0x01014210,
-	0x01A19250, 0x01011212, 0x01016211, 0x40f000f0,
-	0x40f000f0, 0x40f000f0, 0x40f000f0, 0x014510A0,
-	0x074510B0, 0x40f000f0
+	0x01A19250, 0x01011212, 0x01016211
 };
 
 static unsigned int *stac92hd73xx_brd_tbl[STAC_92HD73XX_MODELS] = {
@@ -1693,6 +1692,7 @@
 	[STAC_DELL_M4_2]	= dell_m4_2_pin_configs,
 	[STAC_DELL_M4_3]	= dell_m4_3_pin_configs,
 	[STAC_HP_M4]		= NULL,
+	[STAC_HP_DV4]		= NULL,
 	[STAC_HP_DV5]		= NULL,
 	[STAC_HP_HDX]           = NULL,
 	[STAC_HP_DV4_1222NR]	= NULL,
@@ -1705,6 +1705,7 @@
 	[STAC_DELL_M4_2] = "dell-m4-2",
 	[STAC_DELL_M4_3] = "dell-m4-3",
 	[STAC_HP_M4] = "hp-m4",
+	[STAC_HP_DV4] = "hp-dv4",
 	[STAC_HP_DV5] = "hp-dv5",
 	[STAC_HP_HDX] = "hp-hdx",
 	[STAC_HP_DV4_1222NR] = "hp-dv4-1222nr",
@@ -1723,7 +1724,7 @@
 	SND_PCI_QUIRK_MASK(PCI_VENDOR_ID_HP, 0xfff0, 0x3080,
 		      "HP", STAC_HP_DV5),
 	SND_PCI_QUIRK_MASK(PCI_VENDOR_ID_HP, 0xfff0, 0x30f0,
-		      "HP dv4-7", STAC_HP_DV5),
+		      "HP dv4-7", STAC_HP_DV4),
 	SND_PCI_QUIRK_MASK(PCI_VENDOR_ID_HP, 0xfff0, 0x3600,
 		      "HP dv4-7", STAC_HP_DV5),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x3610,
@@ -4768,6 +4769,9 @@
 	struct sigmatel_spec *spec = codec->spec;
 	unsigned int gpio;
 
+	if (spec->gpio_led)
+		return;
+
 	gpio = snd_hda_param_read(codec, codec->afg, AC_PAR_GPIO_CAP);
 	gpio &= AC_GPIO_IO_COUNT;
 	if (gpio > 3)
@@ -5677,6 +5681,9 @@
 		spec->num_smuxes = 1;
 		spec->num_dmuxes = 1;
 		/* fallthrough */
+	case STAC_HP_DV4:
+		spec->gpio_led = 0x01;
+		/* fallthrough */
 	case STAC_HP_DV5:
 		snd_hda_codec_set_pincfg(codec, 0x0d, 0x90170010);
 		stac92xx_auto_set_pinctl(codec, 0x0d, AC_PINCTL_OUT_EN);
@@ -5690,6 +5697,7 @@
 		spec->num_dmics = 1;
 		spec->num_dmuxes = 1;
 		spec->num_smuxes = 1;
+		spec->gpio_led = 0x08;
 		break;
 	}
 
@@ -5746,7 +5754,8 @@
 	}
 
 	/* enable bass on HP dv7 */
-	if (spec->board_config == STAC_HP_DV5) {
+	if (spec->board_config == STAC_HP_DV4 ||
+	    spec->board_config == STAC_HP_DV5) {
 		unsigned int cap;
 		cap = snd_hda_param_read(codec, 0x1, AC_PAR_GPIO_CAP);
 		cap &= AC_GPIO_IO_COUNT;

sound/pci/ice1712/maya44.c

diff --git a/sound/pci/ice1712/maya44.c b/sound/pci/ice1712/maya44.c
index 3e1c20a..726fd4b 100644
--- a/sound/pci/ice1712/maya44.c
+++ b/sound/pci/ice1712/maya44.c
@@ -347,7 +347,7 @@
 
 /* known working input slots (0-4) */
 #define MAYA_LINE_IN	1	/* in-2 */
-#define MAYA_MIC_IN	4	/* in-5 */
+#define MAYA_MIC_IN	3	/* in-4 */
 
 static void wm8776_select_input(struct snd_maya44 *chip, int idx, int line)
 {
@@ -393,8 +393,8 @@
 	int changed;
 
 	mutex_lock(&chip->mutex);
-	changed = maya_set_gpio_bits(chip->ice, GPIO_MIC_RELAY,
-				     sel ? GPIO_MIC_RELAY : 0);
+	changed = maya_set_gpio_bits(chip->ice, 1 << GPIO_MIC_RELAY,
+				     sel ? (1 << GPIO_MIC_RELAY) : 0);
 	wm8776_select_input(chip, 0, sel ? MAYA_MIC_IN : MAYA_LINE_IN);
 	mutex_unlock(&chip->mutex);
 	return changed;

sound/pci/oxygen/xonar_cs43xx.c

diff --git a/sound/pci/oxygen/xonar_cs43xx.c b/sound/pci/oxygen/xonar_cs43xx.c
index 16c226b..7c4986b 100644
--- a/sound/pci/oxygen/xonar_cs43xx.c
+++ b/sound/pci/oxygen/xonar_cs43xx.c
@@ -56,6 +56,7 @@
 #include <sound/pcm_params.h>
 #include <sound/tlv.h>
 #include "xonar.h"
+#include "cm9780.h"
 #include "cs4398.h"
 #include "cs4362a.h"
 
@@ -172,6 +173,8 @@
 	oxygen_clear_bits16(chip, OXYGEN_GPIO_DATA,
 			    GPIO_D1_FRONT_PANEL | GPIO_D1_INPUT_ROUTE);
 
+	oxygen_ac97_set_bits(chip, 0, CM9780_JACK, CM9780_FMIC2MIC);
+
 	xonar_init_cs53x1(chip);
 	xonar_enable_output(chip);
 

sound/soc/txx9/txx9aclc-ac97.c

diff --git a/sound/soc/txx9/txx9aclc-ac97.c b/sound/soc/txx9/txx9aclc-ac97.c
index 612e18b..0ec20b6 100644
--- a/sound/soc/txx9/txx9aclc-ac97.c
+++ b/sound/soc/txx9/txx9aclc-ac97.c
@@ -254,3 +254,4 @@
 MODULE_AUTHOR("Atsushi Nemoto <anemo@mba.ocn.ne.jp>");
 MODULE_DESCRIPTION("TXx9 ACLC AC97 driver");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:txx9aclc-ac97");

sound/soc/txx9/txx9aclc-generic.c

diff --git a/sound/soc/txx9/txx9aclc-generic.c b/sound/soc/txx9/txx9aclc-generic.c
index 3175de9..95b17f7 100644
--- a/sound/soc/txx9/txx9aclc-generic.c
+++ b/sound/soc/txx9/txx9aclc-generic.c
@@ -96,3 +96,4 @@
 MODULE_AUTHOR("Atsushi Nemoto <anemo@mba.ocn.ne.jp>");
 MODULE_DESCRIPTION("Generic TXx9 ACLC ALSA SoC audio driver");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:txx9aclc-generic");

tools/perf/Documentation/perf-annotate.txt

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index c9dcade..5164a65 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -1,5 +1,5 @@
 perf-annotate(1)
-==============
+================
 
 NAME
 ----

tools/perf/Documentation/perf-bench.txt

diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index ae525ac..a3dbadb 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -1,5 +1,5 @@
 perf-bench(1)
-============
+=============
 
 NAME
 ----
@@ -19,12 +19,12 @@
 -f::
 --format=::
 Specify format style.
-Current available format styles are,
+Current available format styles are:
 
 'default'::
 Default style. This is mainly for human reading.
 ---------------------
-% perf bench sched pipe                      # with no style specify
+% perf bench sched pipe                      # with no style specified
 (executing 1000000 pipe operations between two tasks)
         Total time:5.855 sec
                 5.855061 usecs/op
@@ -79,7 +79,7 @@
 
       Total time:0.308 sec
 
-% perf bench sched messaging -t -g 20        # be multi-thread,with 20 groups
+% perf bench sched messaging -t -g 20        # be multi-thread, with 20 groups
 (20 sender and receiver threads per group)
 (20 groups == 800 threads run)
 

tools/perf/Documentation/perf-buildid-cache.txt

diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index 88bc3b5..5d1a950 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -8,7 +8,7 @@
 SYNOPSIS
 --------
 [verse]
-'perf buildid-list <options>'
+'perf buildid-cache <options>'
 
 DESCRIPTION
 -----------
@@ -30,4 +30,4 @@
 
 SEE ALSO
 --------
-linkperf:perf-record[1], linkperf:perf-report[1]
+linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1]

tools/perf/Documentation/perf-diff.txt

diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 8974e20..20d97d8 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -1,5 +1,5 @@
 perf-diff(1)
-==============
+============
 
 NAME
 ----

tools/perf/Documentation/perf-inject.txt

diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
new file mode 100644
index 0000000..025630d
--- /dev/null
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -0,0 +1,35 @@
+perf-inject(1)
+==============
+
+NAME
+----
+perf-inject - Filter to augment the events stream with additional information
+
+SYNOPSIS
+--------
+[verse]
+'perf inject <options>'
+
+DESCRIPTION
+-----------
+perf-inject reads a perf-record event stream and repipes it to stdout.  At any
+point the processing code can inject other events into the event stream - in
+this case build-ids (-b option) are read and injected as needed into the event
+stream.
+
+Build-ids are just the first user of perf-inject - potentially anything that
+needs userspace processing to augment the events stream with additional
+information could make use of this facility.
+
+OPTIONS
+-------
+-b::
+--build-ids=::
+        Inject build-ids into the output stream
+-v::
+--verbose::
+	Be more verbose.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]

tools/perf/Documentation/perf-kmem.txt

diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index eac4d852e..a52fcde 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -1,5 +1,5 @@
 perf-kmem(1)
-==============
+============
 
 NAME
 ----

tools/perf/Documentation/perf-kvm.txt

diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
new file mode 100644
index 0000000..d004e19
--- /dev/null
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -0,0 +1,68 @@
+perf-kvm(1)
+===========
+
+NAME
+----
+perf-kvm - Tool to trace/measure kvm guest os
+
+SYNOPSIS
+--------
+[verse]
+'perf kvm' [--host] [--guest] [--guestmount=<path>
+	[--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]]
+	{top|record|report|diff|buildid-list}
+'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path>
+	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list}
+
+DESCRIPTION
+-----------
+There are a couple of variants of perf kvm:
+
+  'perf kvm [options] top <command>' to generates and displays
+  a performance counter profile of guest os in realtime
+  of an arbitrary workload.
+
+  'perf kvm record <command>' to record the performance couinter profile
+  of an arbitrary workload and save it into a perf data file. If both
+  --host and --guest are input, the perf data file name is perf.data.kvm.
+  If there is  no --host but --guest, the file name is perf.data.guest.
+  If there is no --guest but --host, the file name is perf.data.host.
+
+  'perf kvm report' to display the performance counter profile information
+  recorded via perf kvm record.
+
+  'perf kvm diff' to displays the performance difference amongst two perf.data
+  files captured via perf record.
+
+  'perf kvm buildid-list' to  display the buildids found in a perf data file,
+  so that other tools can be used to fetch packages with matching symbol tables
+  for use by perf report.
+
+OPTIONS
+-------
+--host=::
+        Collect host side performance profile.
+--guest=::
+        Collect guest side performance profile.
+--guestmount=<path>::
+	Guest os root file system mount directory. Users mounts guest os
+        root directories under <path> by a specific filesystem access method,
+	typically, sshfs. For example, start 2 guest os. The one's pid is 8888
+	and the other's is 9999.
+        #mkdir ~/guestmount; cd ~/guestmount
+        #sshfs -o allow_other,direct_io -p 5551 localhost:/ 8888/
+        #sshfs -o allow_other,direct_io -p 5552 localhost:/ 9999/
+        #perf kvm --host --guest --guestmount=~/guestmount top
+--guestkallsyms=<path>::
+        Guest os /proc/kallsyms file copy. 'perf' kvm' reads it to get guest
+	kernel symbols. Users copy it out from guest os.
+--guestmodules=<path>::
+	Guest os /proc/modules file copy. 'perf' kvm' reads it to get guest
+	kernel module information. Users copy it out from guest os.
+--guestvmlinux=<path>::
+	Guest os kernel vmlinux.
+
+SEE ALSO
+--------
+linkperf:perf-top[1], linkperf:perf-record[1], linkperf:perf-report[1],
+linkperf:perf-diff[1], linkperf:perf-buildid-list[1]

tools/perf/Documentation/perf-list.txt

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 8290b94..43e3dd2 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -15,6 +15,35 @@
 This command displays the symbolic event types which can be selected in the
 various perf commands with the -e option.
 
+RAW HARDWARE EVENT DESCRIPTOR
+-----------------------------
+Even when an event is not available in a symbolic form within perf right now,
+it can be encoded in a per processor specific way.
+
+For instance For x86 CPUs NNN represents the raw register encoding with the
+layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout
+of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
+Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
+
+Example:
+
+If the Intel docs for a QM720 Core i7 describe an event as:
+
+  Event  Umask  Event Mask
+  Num.   Value  Mnemonic    Description                        Comment
+
+  A8H      01H  LSD.UOPS    Counts the number of micro-ops     Use cmask=1 and
+                            delivered by loop stream detector  invert to count
+                                                               cycles
+
+raw encoding of 0x1A8 can be used:
+
+ perf stat -e r1a8 -a sleep 1
+ perf record -e r1a8 ...
+
+You should refer to the processor specific documentation for getting these
+details. Some of them are referenced in the SEE ALSO section below.
+
 OPTIONS
 -------
 None
@@ -22,4 +51,6 @@
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-top[1],
-linkperf:perf-record[1]
+linkperf:perf-record[1],
+http://www.intel.com/Assets/PDF/manual/253669.pdf[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
+http://support.amd.com/us/Processor_TechDocs/24593.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]

tools/perf/Documentation/perf-probe.txt

diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 34202b1..94a258c 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -57,6 +57,14 @@
 --force::
 	Forcibly add events with existing name.
 
+-n::
+--dry-run::
+	Dry run. With this option, --add and --del doesn't execute actual
+	adding and removal operations.
+
+--max-probes::
+	Set the maximum number of probe points for an event. Default is 128.
+
 PROBE SYNTAX
 ------------
 Probe points are defined by following syntax.
@@ -74,13 +82,22 @@
 'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'.
 'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition.  In addition, '@SRC' specifies a source file which has that function.
 It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
-'ARG' specifies the arguments of this probe point. You can use the name of local variable, or kprobe-tracer argument format (e.g. $retval, %ax, etc).
+'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT).
+
+PROBE ARGUMENT
+--------------
+Each probe argument follows below syntax.
+
+ [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
+
+'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), 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.
 
 LINE SYNTAX
 -----------
 Line range is descripted by following syntax.
 
- "FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]"
+ "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]"
 
 FUNC specifies the function name of showing lines. 'RLN' is the start line
 number from function entry line, and 'RLN2' is the end line number. As same as

tools/perf/Documentation/perf-record.txt

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index fc46c0b..34e255f 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -58,7 +58,7 @@
 
 -f::
 --force::
-	Overwrite existing data file.
+	Overwrite existing data file. (deprecated)
 
 -c::
 --count=::
@@ -69,8 +69,8 @@
 	Output file name.
 
 -i::
---inherit::
-	Child tasks inherit counters.
+--no-inherit::
+	Child tasks do not inherit counters.
 -F::
 --freq=::
 	Profile at this frequency.
@@ -101,7 +101,7 @@
 
 -R::
 --raw-samples::
-Collect raw sample records from all opened counters (typically for tracepoint counters).
+Collect raw sample records from all opened counters (default for tracepoint counters).
 
 SEE ALSO
 --------

tools/perf/Documentation/perf-sched.txt

diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 1ce7919..8417644 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -12,7 +12,7 @@
 
 DESCRIPTION
 -----------
-There's four variants of perf sched:
+There are four variants of perf sched:
 
   'perf sched record <command>' to record the scheduling events
   of an arbitrary workload.
@@ -27,7 +27,7 @@
   via perf sched record. (this is done by starting up mockup threads
   that mimic the workload based on the events in the trace. These
   threads can then replay the timings (CPU runtime and sleep patterns)
-  of the workload as it occured when it was recorded - and can repeat
+  of the workload as it occurred when it was recorded - and can repeat
   it a number of times, measuring its performance.)
 
 OPTIONS

tools/perf/Documentation/perf-stat.txt

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 484080d..2cab8e8 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -31,8 +31,8 @@
 	 hexadecimal event descriptor.
 
 -i::
---inherit::
-        child tasks inherit counters
+--no-inherit::
+        child tasks do not inherit counters
 -p::
 --pid=<pid>::
         stat events on existing pid

tools/perf/Documentation/perf-test.txt

diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
new file mode 100644
index 0000000..1c4b5f5
--- /dev/null
+++ b/tools/perf/Documentation/perf-test.txt
@@ -0,0 +1,22 @@
+perf-test(1)
+============
+
+NAME
+----
+perf-test - Runs sanity tests.
+
+SYNOPSIS
+--------
+[verse]
+'perf test <options>'
+
+DESCRIPTION
+-----------
+This command does assorted sanity tests, initially thru linked routines but
+also will look for a directory with more tests in the form of scripts.
+
+OPTIONS
+-------
+-v::
+--verbose::
+	Be more verbose.

tools/perf/Documentation/perf-trace-perl.txt

diff --git a/tools/perf/Documentation/perf-trace-perl.txt b/tools/perf/Documentation/perf-trace-perl.txt
index d729cee..ee6525e 100644
--- a/tools/perf/Documentation/perf-trace-perl.txt
+++ b/tools/perf/Documentation/perf-trace-perl.txt
@@ -49,12 +49,10 @@
 As an example, the following perf record command can be used to record
 all sched_wakeup events in the system:
 
- # perf record -c 1 -f -a -M -R -e sched:sched_wakeup
+ # perf record -a -e sched:sched_wakeup
 
 Traces meant to be processed using a script should be recorded with
-the above options: -c 1 says to sample every event, -a to enable
-system-wide collection, -M to multiplex the output, and -R to collect
-raw samples.
+the above option: -a to enable system-wide collection.
 
 The format file for the sched_wakep event defines the following fields
 (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):

tools/perf/Documentation/perf-trace-python.txt

diff --git a/tools/perf/Documentation/perf-trace-python.txt b/tools/perf/Documentation/perf-trace-python.txt
index a241aca..693be80 100644
--- a/tools/perf/Documentation/perf-trace-python.txt
+++ b/tools/perf/Documentation/perf-trace-python.txt
@@ -1,5 +1,5 @@
 perf-trace-python(1)
-==================
+====================
 
 NAME
 ----
@@ -93,7 +93,7 @@
 the sys_enter events:
 
 ----
-# perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+# perf record -a -e raw_syscalls:sys_enter
 
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 56.545 MB perf.data (~2470503 samples) ]
@@ -182,7 +182,7 @@
 really interested in, or the script was run against a trace file that
 doesn't correspond to the script.
 
-The script generated by -g option option simply prints a line for each
+The script generated by -g option simply prints a line for each
 event found in the trace stream i.e. it basically just dumps the event
 and its parameter values to stdout.  The print_header() function is
 simply a utility function used for that purpose.  Let's rename the
@@ -359,7 +359,7 @@
 # cat kernel-source/tools/perf/scripts/python/bin/syscall-counts-record
 
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+perf record -a -e raw_syscalls:sys_enter
 ----
 
 The 'report' script is also a shell script with the same base name as
@@ -449,12 +449,10 @@
 As an example, the following perf record command can be used to record
 all sched_wakeup events in the system:
 
- # perf record -c 1 -f -a -M -R -e sched:sched_wakeup
+ # perf record -a -e sched:sched_wakeup
 
 Traces meant to be processed using a script should be recorded with
-the above options: -c 1 says to sample every event, -a to enable
-system-wide collection, -M to multiplex the output, and -R to collect
-raw samples.
+the above option: -a to enable system-wide collection.
 
 The format file for the sched_wakep event defines the following fields
 (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):
@@ -584,7 +582,7 @@
   flag_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the flag field field_name of event event_name
   symbol_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the symbolic field field_name of event event_name
 
-The *autodict* function returns a special special kind of Python
+The *autodict* function returns a special kind of Python
 dictionary that implements Perl's 'autovivifying' hashes in Python
 i.e. with autovivifying hashes, you can assign nested hash values
 without having to go to the trouble of creating intermediate levels if

tools/perf/Documentation/perf-trace.txt

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 8879299..122ec9d 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -1,5 +1,5 @@
 perf-trace(1)
-==============
+=============
 
 NAME
 ----

tools/perf/Makefile

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index bc0f670..3d8f31e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -1,3 +1,7 @@
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
 # The default target of this Makefile is...
 all::
 
@@ -150,10 +154,17 @@
 # Define LDFLAGS=-static to build a static binary.
 #
 # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
+#
+# Define NO_DWARF if you do not want debug-info analysis feature at all.
 
-PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
-	@$(SHELL_PATH) util/PERF-VERSION-GEN
--include PERF-VERSION-FILE
+$(shell sh -c 'mkdir -p $(OUTPUT)scripts/python/Perf-Trace-Util/' 2> /dev/null)
+$(shell sh -c 'mkdir -p $(OUTPUT)scripts/perl/Perf-Trace-Util/' 2> /dev/null)
+$(shell sh -c 'mkdir -p $(OUTPUT)util/scripting-engines/' 2> /dev/null)
+$(shell sh -c 'mkdir $(OUTPUT)bench' 2> /dev/null)
+
+$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
+	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
+-include $(OUTPUT)PERF-VERSION-FILE
 
 uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not')
 uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not')
@@ -162,6 +173,22 @@
 uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not')
 uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not')
 
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
+				  -e s/arm.*/arm/ -e s/sa110/arm/ \
+				  -e s/s390x/s390/ -e s/parisc64/parisc/ \
+				  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
+				  -e s/sh[234].*/sh/ )
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),i386)
+        ARCH := x86
+endif
+ifeq ($(ARCH),x86_64)
+        ARCH := x86
+endif
+
+$(shell sh -c 'mkdir -p $(OUTPUT)arch/$(ARCH)/util/' 2> /dev/null)
+
 # CFLAGS and LDFLAGS are for the users to override from the command line.
 
 #
@@ -274,7 +301,7 @@
 # Those must not be GNU-specific; they are shared with perl/ which may
 # be built by a different compiler. (Note that this is an artifact now
 # but it still might be nice to keep that distinction.)
-BASIC_CFLAGS = -Iutil/include
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include
 BASIC_LDFLAGS =
 
 # Guard against environment variables
@@ -308,7 +335,7 @@
 #
 # Single 'perf' binary right now:
 #
-PROGRAMS += perf
+PROGRAMS += $(OUTPUT)perf
 
 # List built-in command $C whose implementation cmd_$C() is not in
 # builtin-$C.o but is linked in as part of some other command.
@@ -318,7 +345,7 @@
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
 # what 'all' will build but not install in perfexecdir
-OTHER_PROGRAMS = perf$X
+OTHER_PROGRAMS = $(OUTPUT)perf$X
 
 # Set paths to tools early so that they can be used for version tests.
 ifndef SHELL_PATH
@@ -330,7 +357,7 @@
 
 export PERL_PATH
 
-LIB_FILE=libperf.a
+LIB_FILE=$(OUTPUT)libperf.a
 
 LIB_H += ../../include/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
@@ -350,12 +377,13 @@
 LIB_H += util/include/linux/string.h
 LIB_H += util/include/linux/types.h
 LIB_H += util/include/asm/asm-offsets.h
-LIB_H += util/include/asm/bitops.h
 LIB_H += util/include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
+LIB_H += util/include/asm/hweight.h
 LIB_H += util/include/asm/swab.h
 LIB_H += util/include/asm/system.h
 LIB_H += util/include/asm/uaccess.h
+LIB_H += util/include/dwarf-regs.h
 LIB_H += perf.h
 LIB_H += util/cache.h
 LIB_H += util/callchain.h
@@ -375,7 +403,6 @@
 LIB_H += util/help.h
 LIB_H += util/session.h
 LIB_H += util/strbuf.h
-LIB_H += util/string.h
 LIB_H += util/strlist.h
 LIB_H += util/svghelper.h
 LIB_H += util/run-command.h
@@ -389,79 +416,83 @@
 LIB_H += util/trace-event.h
 LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
+LIB_H += util/pstack.h
 LIB_H += util/cpumap.h
 
-LIB_OBJS += util/abspath.o
-LIB_OBJS += util/alias.o
-LIB_OBJS += util/build-id.o
-LIB_OBJS += util/config.o
-LIB_OBJS += util/ctype.o
-LIB_OBJS += util/debugfs.o
-LIB_OBJS += util/environment.o
-LIB_OBJS += util/event.o
-LIB_OBJS += util/exec_cmd.o
-LIB_OBJS += util/help.o
-LIB_OBJS += util/levenshtein.o
-LIB_OBJS += util/parse-options.o
-LIB_OBJS += util/parse-events.o
-LIB_OBJS += util/path.o
-LIB_OBJS += util/rbtree.o
-LIB_OBJS += util/bitmap.o
-LIB_OBJS += util/hweight.o
-LIB_OBJS += util/find_next_bit.o
-LIB_OBJS += util/run-command.o
-LIB_OBJS += util/quote.o
-LIB_OBJS += util/strbuf.o
-LIB_OBJS += util/string.o
-LIB_OBJS += util/strlist.o
-LIB_OBJS += util/usage.o
-LIB_OBJS += util/wrapper.o
-LIB_OBJS += util/sigchain.o
-LIB_OBJS += util/symbol.o
-LIB_OBJS += util/color.o
-LIB_OBJS += util/pager.o
-LIB_OBJS += util/header.o
-LIB_OBJS += util/callchain.o
-LIB_OBJS += util/values.o
-LIB_OBJS += util/debug.o
-LIB_OBJS += util/map.o
-LIB_OBJS += util/session.o
-LIB_OBJS += util/thread.o
-LIB_OBJS += util/trace-event-parse.o
-LIB_OBJS += util/trace-event-read.o
-LIB_OBJS += util/trace-event-info.o
-LIB_OBJS += util/trace-event-scripting.o
-LIB_OBJS += util/svghelper.o
-LIB_OBJS += util/sort.o
-LIB_OBJS += util/hist.o
-LIB_OBJS += util/probe-event.o
-LIB_OBJS += util/util.o
-LIB_OBJS += util/cpumap.o
+LIB_OBJS += $(OUTPUT)util/abspath.o
+LIB_OBJS += $(OUTPUT)util/alias.o
+LIB_OBJS += $(OUTPUT)util/build-id.o
+LIB_OBJS += $(OUTPUT)util/config.o
+LIB_OBJS += $(OUTPUT)util/ctype.o
+LIB_OBJS += $(OUTPUT)util/debugfs.o
+LIB_OBJS += $(OUTPUT)util/environment.o
+LIB_OBJS += $(OUTPUT)util/event.o
+LIB_OBJS += $(OUTPUT)util/exec_cmd.o
+LIB_OBJS += $(OUTPUT)util/help.o
+LIB_OBJS += $(OUTPUT)util/levenshtein.o
+LIB_OBJS += $(OUTPUT)util/parse-options.o
+LIB_OBJS += $(OUTPUT)util/parse-events.o
+LIB_OBJS += $(OUTPUT)util/path.o
+LIB_OBJS += $(OUTPUT)util/rbtree.o
+LIB_OBJS += $(OUTPUT)util/bitmap.o
+LIB_OBJS += $(OUTPUT)util/hweight.o
+LIB_OBJS += $(OUTPUT)util/run-command.o
+LIB_OBJS += $(OUTPUT)util/quote.o
+LIB_OBJS += $(OUTPUT)util/strbuf.o
+LIB_OBJS += $(OUTPUT)util/string.o
+LIB_OBJS += $(OUTPUT)util/strlist.o
+LIB_OBJS += $(OUTPUT)util/usage.o
+LIB_OBJS += $(OUTPUT)util/wrapper.o
+LIB_OBJS += $(OUTPUT)util/sigchain.o
+LIB_OBJS += $(OUTPUT)util/symbol.o
+LIB_OBJS += $(OUTPUT)util/color.o
+LIB_OBJS += $(OUTPUT)util/pager.o
+LIB_OBJS += $(OUTPUT)util/header.o
+LIB_OBJS += $(OUTPUT)util/callchain.o
+LIB_OBJS += $(OUTPUT)util/values.o
+LIB_OBJS += $(OUTPUT)util/debug.o
+LIB_OBJS += $(OUTPUT)util/map.o
+LIB_OBJS += $(OUTPUT)util/pstack.o
+LIB_OBJS += $(OUTPUT)util/session.o
+LIB_OBJS += $(OUTPUT)util/thread.o
+LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
+LIB_OBJS += $(OUTPUT)util/trace-event-read.o
+LIB_OBJS += $(OUTPUT)util/trace-event-info.o
+LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
+LIB_OBJS += $(OUTPUT)util/svghelper.o
+LIB_OBJS += $(OUTPUT)util/sort.o
+LIB_OBJS += $(OUTPUT)util/hist.o
+LIB_OBJS += $(OUTPUT)util/probe-event.o
+LIB_OBJS += $(OUTPUT)util/util.o
+LIB_OBJS += $(OUTPUT)util/cpumap.o
 
-BUILTIN_OBJS += builtin-annotate.o
+BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 
-BUILTIN_OBJS += builtin-bench.o
+BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
 
 # Benchmark modules
-BUILTIN_OBJS += bench/sched-messaging.o
-BUILTIN_OBJS += bench/sched-pipe.o
-BUILTIN_OBJS += bench/mem-memcpy.o
+BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
+BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
 
-BUILTIN_OBJS += builtin-diff.o
-BUILTIN_OBJS += builtin-help.o
-BUILTIN_OBJS += builtin-sched.o
-BUILTIN_OBJS += builtin-buildid-list.o
-BUILTIN_OBJS += builtin-buildid-cache.o
-BUILTIN_OBJS += builtin-list.o
-BUILTIN_OBJS += builtin-record.o
-BUILTIN_OBJS += builtin-report.o
-BUILTIN_OBJS += builtin-stat.o
-BUILTIN_OBJS += builtin-timechart.o
-BUILTIN_OBJS += builtin-top.o
-BUILTIN_OBJS += builtin-trace.o
-BUILTIN_OBJS += builtin-probe.o
-BUILTIN_OBJS += builtin-kmem.o
-BUILTIN_OBJS += builtin-lock.o
+BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
+BUILTIN_OBJS += $(OUTPUT)builtin-help.o
+BUILTIN_OBJS += $(OUTPUT)builtin-sched.o
+BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o
+BUILTIN_OBJS += $(OUTPUT)builtin-buildid-cache.o
+BUILTIN_OBJS += $(OUTPUT)builtin-list.o
+BUILTIN_OBJS += $(OUTPUT)builtin-record.o
+BUILTIN_OBJS += $(OUTPUT)builtin-report.o
+BUILTIN_OBJS += $(OUTPUT)builtin-stat.o
+BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o
+BUILTIN_OBJS += $(OUTPUT)builtin-top.o
+BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
+BUILTIN_OBJS += $(OUTPUT)builtin-probe.o
+BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o
+BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
+BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o
+BUILTIN_OBJS += $(OUTPUT)builtin-test.o
+BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
 
 PERFLIBS = $(LIB_FILE)
 
@@ -476,6 +507,15 @@
 -include config.mak.autogen
 -include config.mak
 
+ifndef NO_DWARF
+ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo '\#include <version.h>'; echo '\#ifndef _ELFUTILS_PREREQ'; echo '\#error'; echo '\#endif'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+	msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+	NO_DWARF := 1
+endif # Dwarf support
+endif # NO_DWARF
+
+-include arch/$(ARCH)/Makefile
+
 ifeq ($(uname_S),Darwin)
 	ifndef NO_FINK
 		ifeq ($(shell test -d /sw/lib && echo y),y)
@@ -492,6 +532,10 @@
 	PTHREAD_LIBS =
 endif
 
+ifneq ($(OUTPUT),)
+	BASIC_CFLAGS += -I$(OUTPUT)
+endif
+
 ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
 ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
 	msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
@@ -504,14 +548,29 @@
 	msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]);
 endif
 
-ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-	msg := $(warning No libdw.h found or old libdw.h found, disables dwarf support. Please install elfutils-devel/elfutils-dev);
-	BASIC_CFLAGS += -DNO_DWARF_SUPPORT
+ifndef NO_DWARF
+ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
+	msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
 else
-	BASIC_CFLAGS += -I/usr/include/elfutils
+	BASIC_CFLAGS += -I/usr/include/elfutils -DDWARF_SUPPORT
 	EXTLIBS += -lelf -ldw
-	LIB_OBJS += util/probe-finder.o
+	LIB_OBJS += $(OUTPUT)util/probe-finder.o
+endif # PERF_HAVE_DWARF_REGS
+endif # NO_DWARF
+
+ifdef NO_NEWT
+	BASIC_CFLAGS += -DNO_NEWT_SUPPORT
+else
+ifneq ($(shell sh -c "(echo '\#include <newt.h>'; echo 'int main(void) { newtInit(); newtCls(); return newtFinished(); }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -lnewt -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+	msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev);
+	BASIC_CFLAGS += -DNO_NEWT_SUPPORT
+else
+	# Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
+	BASIC_CFLAGS += -I/usr/include/slang
+	EXTLIBS += -lnewt -lslang
+	LIB_OBJS += $(OUTPUT)util/newt.o
 endif
+endif # NO_NEWT
 
 ifndef NO_LIBPERL
 PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null`
@@ -522,8 +581,8 @@
 	BASIC_CFLAGS += -DNO_LIBPERL
 else
 	ALL_LDFLAGS += $(PERL_EMBED_LDOPTS)
-	LIB_OBJS += util/scripting-engines/trace-event-perl.o
-	LIB_OBJS += scripts/perl/Perf-Trace-Util/Context.o
+	LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
+	LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
 endif
 
 ifndef NO_LIBPYTHON
@@ -531,16 +590,19 @@
 PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
 endif
 
-ifneq ($(shell sh -c "(echo '\#include <Python.h>'; echo 'int main(void) { Py_Initialize(); return 0; }') | $(CC) -x c - $(PYTHON_EMBED_CCOPTS) -o /dev/null $(PYTHON_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
+ifneq ($(shell sh -c "(echo '\#include <Python.h>'; echo 'int main(void) { Py_Initialize(); return 0; }') | $(CC) -x c - $(PYTHON_EMBED_CCOPTS) -o $(BITBUCKET) $(PYTHON_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
 	BASIC_CFLAGS += -DNO_LIBPYTHON
 else
 	ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS)
-	LIB_OBJS += util/scripting-engines/trace-event-python.o
-	LIB_OBJS += scripts/python/Perf-Trace-Util/Context.o
+	LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
+	LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
 endif
 
 ifdef NO_DEMANGLE
 	BASIC_CFLAGS += -DNO_DEMANGLE
+else ifdef HAVE_CPLUS_DEMANGLE
+	EXTLIBS += -liberty
+	BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
 else
 	has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y")
 
@@ -607,53 +669,53 @@
 endif
 ifdef SNPRINTF_RETURNS_BOGUS
 	COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS
-	COMPAT_OBJS += compat/snprintf.o
+	COMPAT_OBJS += $(OUTPUT)compat/snprintf.o
 endif
 ifdef FREAD_READS_DIRECTORIES
 	COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES
-	COMPAT_OBJS += compat/fopen.o
+	COMPAT_OBJS += $(OUTPUT)compat/fopen.o
 endif
 ifdef NO_SYMLINK_HEAD
 	BASIC_CFLAGS += -DNO_SYMLINK_HEAD
 endif
 ifdef NO_STRCASESTR
 	COMPAT_CFLAGS += -DNO_STRCASESTR
-	COMPAT_OBJS += compat/strcasestr.o
+	COMPAT_OBJS += $(OUTPUT)compat/strcasestr.o
 endif
 ifdef NO_STRTOUMAX
 	COMPAT_CFLAGS += -DNO_STRTOUMAX
-	COMPAT_OBJS += compat/strtoumax.o
+	COMPAT_OBJS += $(OUTPUT)compat/strtoumax.o
 endif
 ifdef NO_STRTOULL
 	COMPAT_CFLAGS += -DNO_STRTOULL
 endif
 ifdef NO_SETENV
 	COMPAT_CFLAGS += -DNO_SETENV
-	COMPAT_OBJS += compat/setenv.o
+	COMPAT_OBJS += $(OUTPUT)compat/setenv.o
 endif
 ifdef NO_MKDTEMP
 	COMPAT_CFLAGS += -DNO_MKDTEMP
-	COMPAT_OBJS += compat/mkdtemp.o
+	COMPAT_OBJS += $(OUTPUT)compat/mkdtemp.o
 endif
 ifdef NO_UNSETENV
 	COMPAT_CFLAGS += -DNO_UNSETENV
-	COMPAT_OBJS += compat/unsetenv.o
+	COMPAT_OBJS += $(OUTPUT)compat/unsetenv.o
 endif
 ifdef NO_SYS_SELECT_H
 	BASIC_CFLAGS += -DNO_SYS_SELECT_H
 endif
 ifdef NO_MMAP
 	COMPAT_CFLAGS += -DNO_MMAP
-	COMPAT_OBJS += compat/mmap.o
+	COMPAT_OBJS += $(OUTPUT)compat/mmap.o
 else
 	ifdef USE_WIN32_MMAP
 		COMPAT_CFLAGS += -DUSE_WIN32_MMAP
-		COMPAT_OBJS += compat/win32mmap.o
+		COMPAT_OBJS += $(OUTPUT)compat/win32mmap.o
 	endif
 endif
 ifdef NO_PREAD
 	COMPAT_CFLAGS += -DNO_PREAD
-	COMPAT_OBJS += compat/pread.o
+	COMPAT_OBJS += $(OUTPUT)compat/pread.o
 endif
 ifdef NO_FAST_WORKING_DIRECTORY
 	BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY
@@ -675,10 +737,10 @@
 endif
 endif
 ifdef NO_INET_NTOP
-	LIB_OBJS += compat/inet_ntop.o
+	LIB_OBJS += $(OUTPUT)compat/inet_ntop.o
 endif
 ifdef NO_INET_PTON
-	LIB_OBJS += compat/inet_pton.o
+	LIB_OBJS += $(OUTPUT)compat/inet_pton.o
 endif
 
 ifdef NO_ICONV
@@ -695,15 +757,15 @@
 
 ifdef PPC_SHA1
 	SHA1_HEADER = "ppc/sha1.h"
-	LIB_OBJS += ppc/sha1.o ppc/sha1ppc.o
+	LIB_OBJS += $(OUTPUT)ppc/sha1.o ppc/sha1ppc.o
 else
 ifdef ARM_SHA1
 	SHA1_HEADER = "arm/sha1.h"
-	LIB_OBJS += arm/sha1.o arm/sha1_arm.o
+	LIB_OBJS += $(OUTPUT)arm/sha1.o $(OUTPUT)arm/sha1_arm.o
 else
 ifdef MOZILLA_SHA1
 	SHA1_HEADER = "mozilla-sha1/sha1.h"
-	LIB_OBJS += mozilla-sha1/sha1.o
+	LIB_OBJS += $(OUTPUT)mozilla-sha1/sha1.o
 else
 	SHA1_HEADER = <openssl/sha.h>
 	EXTLIBS += $(LIB_4_CRYPTO)
@@ -715,15 +777,15 @@
 endif
 ifdef NO_HSTRERROR
 	COMPAT_CFLAGS += -DNO_HSTRERROR
-	COMPAT_OBJS += compat/hstrerror.o
+	COMPAT_OBJS += $(OUTPUT)compat/hstrerror.o
 endif
 ifdef NO_MEMMEM
 	COMPAT_CFLAGS += -DNO_MEMMEM
-	COMPAT_OBJS += compat/memmem.o
+	COMPAT_OBJS += $(OUTPUT)compat/memmem.o
 endif
 ifdef INTERNAL_QSORT
 	COMPAT_CFLAGS += -DINTERNAL_QSORT
-	COMPAT_OBJS += compat/qsort.o
+	COMPAT_OBJS += $(OUTPUT)compat/qsort.o
 endif
 ifdef RUNTIME_PREFIX
 	COMPAT_CFLAGS += -DRUNTIME_PREFIX
@@ -803,7 +865,7 @@
 
 SHELL = $(SHELL_PATH)
 
-all:: .perf.dev.null shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) PERF-BUILD-OPTIONS
+all:: .perf.dev.null shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS
 ifneq (,$X)
 	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';)
 endif
@@ -815,39 +877,39 @@
 
 shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
 
-strip: $(PROGRAMS) perf$X
-	$(STRIP) $(STRIP_OPTS) $(PROGRAMS) perf$X
+strip: $(PROGRAMS) $(OUTPUT)perf$X
+	$(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf$X
 
-perf.o: perf.c common-cmds.h PERF-CFLAGS
+$(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
-		$(ALL_CFLAGS) -c $(filter %.c,$^)
+		$(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
 
-perf$X: perf.o $(BUILTIN_OBJS) $(PERFLIBS)
-	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ perf.o \
+$(OUTPUT)perf$X: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
+	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(OUTPUT)perf.o \
 		$(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS)
 
-builtin-help.o: builtin-help.c common-cmds.h PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \
+$(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
 		'-DPERF_MAN_PATH="$(mandir_SQ)"' \
 		'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
 
-builtin-timechart.o: builtin-timechart.c common-cmds.h PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \
+$(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
 		'-DPERF_MAN_PATH="$(mandir_SQ)"' \
 		'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
 
-$(BUILT_INS): perf$X
+$(BUILT_INS): $(OUTPUT)perf$X
 	$(QUIET_BUILT_IN)$(RM) $@ && \
 	ln perf$X $@ 2>/dev/null || \
 	ln -s perf$X $@ 2>/dev/null || \
 	cp perf$X $@
 
-common-cmds.h: util/generate-cmdlist.sh command-list.txt
+$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt
 
-common-cmds.h: $(wildcard Documentation/perf-*.txt)
+$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
 	$(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
 
 $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
@@ -859,7 +921,7 @@
 	    -e 's/@@NO_CURL@@/$(NO_CURL)/g' \
 	    $@.sh >$@+ && \
 	chmod +x $@+ && \
-	mv $@+ $@
+	mv $@+ $(OUTPUT)$@
 
 configure: configure.ac
 	$(QUIET_GEN)$(RM) $@ $<+ && \
@@ -869,60 +931,50 @@
 	$(RM) $<+
 
 # These can record PERF_VERSION
-perf.o perf.spec \
+$(OUTPUT)perf.o perf.spec \
 	$(patsubst %.sh,%,$(SCRIPT_SH)) \
 	$(patsubst %.perl,%,$(SCRIPT_PERL)) \
-	: PERF-VERSION-FILE
+	: $(OUTPUT)PERF-VERSION-FILE
 
-%.o: %.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $<
-%.s: %.c PERF-CFLAGS
+$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
-%.o: %.S
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.o: %.S
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
 
-util/exec_cmd.o: util/exec_cmd.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \
+$(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
 		'-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \
 		'-DBINDIR="$(bindir_relative_SQ)"' \
 		'-DPREFIX="$(prefix_SQ)"' \
 		$<
 
-builtin-init-db.o: builtin-init-db.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $<
+$(OUTPUT)builtin-init-db.o: builtin-init-db.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $<
 
-util/config.o: util/config.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
-util/rbtree.o: ../../lib/rbtree.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/rbtree.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+$(OUTPUT)util/newt.o: util/newt.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
-# some perf warning policies can't fit to lib/bitmap.c, eg: it warns about variable shadowing
-# from <string.h> that comes from kernel headers wrapping.
-KBITMAP_FLAGS=`echo $(ALL_CFLAGS) | sed s/-Wshadow// | sed s/-Wswitch-default// | sed s/-Wextra//`
+$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
-util/bitmap.o: ../../lib/bitmap.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/bitmap.o -c $(KBITMAP_FLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+$(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 
-util/hweight.o: ../../lib/hweight.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/hweight.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+$(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 
-util/find_next_bit.o: ../../lib/find_next_bit.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/find_next_bit.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+$(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 
-util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/scripting-engines/trace-event-perl.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+$(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 
-scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o scripts/perl/Perf-Trace-Util/Context.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
-
-util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/scripting-engines/trace-event-python.o -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
-
-scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o scripts/python/Perf-Trace-Util/Context.o -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
-
-perf-%$X: %.o $(PERFLIBS)
+$(OUTPUT)perf-%$X: %.o $(PERFLIBS)
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
 
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
@@ -963,17 +1015,17 @@
 TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\
              $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
 
-PERF-CFLAGS: .FORCE-PERF-CFLAGS
+$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
 	@FLAGS='$(TRACK_CFLAGS)'; \
-	    if test x"$$FLAGS" != x"`cat PERF-CFLAGS 2>/dev/null`" ; then \
+	    if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \
 		echo 1>&2 "    * new build flags or prefix"; \
-		echo "$$FLAGS" >PERF-CFLAGS; \
+		echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \
             fi
 
 # We need to apply sq twice, once to protect from the shell
-# that runs PERF-BUILD-OPTIONS, and then again to protect it
+# that runs $(OUTPUT)PERF-BUILD-OPTIONS, and then again to protect it
 # and the first level quoting from the shell that runs "echo".
-PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS
+$(OUTPUT)PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS
 	@echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@
 	@echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@
 	@echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@
@@ -994,7 +1046,7 @@
 
 export NO_SVN_TESTS
 
-check: common-cmds.h
+check: $(OUTPUT)common-cmds.h
 	if sparse; \
 	then \
 		for i in *.c */*.c; \
@@ -1028,10 +1080,10 @@
 
 install: all
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
-	$(INSTALL) perf$X '$(DESTDIR_SQ)$(bindir_SQ)'
+	$(INSTALL) $(OUTPUT)perf$X '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
-	$(INSTALL) perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+	$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
 	$(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'
 	$(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
@@ -1045,7 +1097,7 @@
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifneq (,$X)
-	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';)
+	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) $(OUTPUT)perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';)
 endif
 endif
 
@@ -1129,14 +1181,14 @@
 	$(RM) *.o */*.o */*/*.o */*/*/*.o $(LIB_FILE)
 	$(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X
 	$(RM) $(TEST_PROGRAMS)
-	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags cscope*
+	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(RM) -r autom4te.cache
 	$(RM) config.log config.mak.autogen config.mak.append config.status config.cache
 	$(RM) -r $(PERF_TARNAME) .doc-tmp-dir
 	$(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz
 	$(RM) $(htmldocs).tar.gz $(manpages).tar.gz
 	$(MAKE) -C Documentation/ clean
-	$(RM) PERF-VERSION-FILE PERF-CFLAGS PERF-BUILD-OPTIONS
+	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-BUILD-OPTIONS
 
 .PHONY: all install clean strip
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell

tools/perf/arch/powerpc/Makefile

diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
new file mode 100644
index 0000000..15130b5
--- /dev/null
+++ b/tools/perf/arch/powerpc/Makefile
@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif

tools/perf/arch/powerpc/util/dwarf-regs.c

diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c
new file mode 100644
index 0000000..48ae0c5
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/dwarf-regs.c
@@ -0,0 +1,88 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Ian Munsie, IBM 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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <libio.h>
+#include <dwarf-regs.h>
+
+
+struct pt_regs_dwarfnum {
+	const char *name;
+	unsigned int dwarfnum;
+};
+
+#define STR(s) #s
+#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
+#define GPR_DWARFNUM_NAME(num)	\
+	{.name = STR(%gpr##num), .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+
+/*
+ * Reference:
+ * http://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi-1.9.html
+ */
+static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
+	GPR_DWARFNUM_NAME(0),
+	GPR_DWARFNUM_NAME(1),
+	GPR_DWARFNUM_NAME(2),
+	GPR_DWARFNUM_NAME(3),
+	GPR_DWARFNUM_NAME(4),
+	GPR_DWARFNUM_NAME(5),
+	GPR_DWARFNUM_NAME(6),
+	GPR_DWARFNUM_NAME(7),
+	GPR_DWARFNUM_NAME(8),
+	GPR_DWARFNUM_NAME(9),
+	GPR_DWARFNUM_NAME(10),
+	GPR_DWARFNUM_NAME(11),
+	GPR_DWARFNUM_NAME(12),
+	GPR_DWARFNUM_NAME(13),
+	GPR_DWARFNUM_NAME(14),
+	GPR_DWARFNUM_NAME(15),
+	GPR_DWARFNUM_NAME(16),
+	GPR_DWARFNUM_NAME(17),
+	GPR_DWARFNUM_NAME(18),
+	GPR_DWARFNUM_NAME(19),
+	GPR_DWARFNUM_NAME(20),
+	GPR_DWARFNUM_NAME(21),
+	GPR_DWARFNUM_NAME(22),
+	GPR_DWARFNUM_NAME(23),
+	GPR_DWARFNUM_NAME(24),
+	GPR_DWARFNUM_NAME(25),
+	GPR_DWARFNUM_NAME(26),
+	GPR_DWARFNUM_NAME(27),
+	GPR_DWARFNUM_NAME(28),
+	GPR_DWARFNUM_NAME(29),
+	GPR_DWARFNUM_NAME(30),
+	GPR_DWARFNUM_NAME(31),
+	REG_DWARFNUM_NAME("%msr",   66),
+	REG_DWARFNUM_NAME("%ctr",   109),
+	REG_DWARFNUM_NAME("%link",  108),
+	REG_DWARFNUM_NAME("%xer",   101),
+	REG_DWARFNUM_NAME("%dar",   119),
+	REG_DWARFNUM_NAME("%dsisr", 118),
+	REG_DWARFNUM_END,
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:	the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+	const struct pt_regs_dwarfnum *roff;
+	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+		if (roff->dwarfnum == n)
+			return roff->name;
+	return NULL;
+}

tools/perf/arch/x86/Makefile

diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
new file mode 100644
index 0000000..15130b5
--- /dev/null
+++ b/tools/perf/arch/x86/Makefile
@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif

tools/perf/arch/x86/util/dwarf-regs.c

diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
new file mode 100644
index 0000000..a794d30
--- /dev/null
+++ b/tools/perf/arch/x86/util/dwarf-regs.c
@@ -0,0 +1,75 @@
+/*
+ * dwarf-regs.c : Mapping of DWARF debug register numbers into register names.
+ * Extracted from probe-finder.c
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+#include <libio.h>
+#include <dwarf-regs.h>
+
+/*
+ * Generic dwarf analysis helpers
+ */
+
+#define X86_32_MAX_REGS 8
+const char *x86_32_regs_table[X86_32_MAX_REGS] = {
+	"%ax",
+	"%cx",
+	"%dx",
+	"%bx",
+	"$stack",	/* Stack address instead of %sp */
+	"%bp",
+	"%si",
+	"%di",
+};
+
+#define X86_64_MAX_REGS 16
+const char *x86_64_regs_table[X86_64_MAX_REGS] = {
+	"%ax",
+	"%dx",
+	"%cx",
+	"%bx",
+	"%si",
+	"%di",
+	"%bp",
+	"%sp",
+	"%r8",
+	"%r9",
+	"%r10",
+	"%r11",
+	"%r12",
+	"%r13",
+	"%r14",
+	"%r15",
+};
+
+/* TODO: switching by dwarf address size */
+#ifdef __x86_64__
+#define ARCH_MAX_REGS X86_64_MAX_REGS
+#define arch_regs_table x86_64_regs_table
+#else
+#define ARCH_MAX_REGS X86_32_MAX_REGS
+#define arch_regs_table x86_32_regs_table
+#endif
+
+/* Return architecture dependent register string (for kprobe-tracer) */
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n <= ARCH_MAX_REGS) ? arch_regs_table[n] : NULL;
+}

tools/perf/bench/mem-memcpy.c

diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 8977317..38dae74 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -10,7 +10,6 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/parse-options.h"
-#include "../util/string.h"
 #include "../util/header.h"
 #include "bench.h"
 
@@ -24,7 +23,7 @@
 
 static const char	*length_str	= "1MB";
 static const char	*routine	= "default";
-static int		use_clock	= 0;
+static bool		use_clock	= false;
 static int		clock_fd;
 
 static const struct option options[] = {

tools/perf/bench/sched-messaging.c

diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 81cee78..d1d1b30 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -31,9 +31,9 @@
 
 #define DATASIZE 100
 
-static int use_pipes = 0;
+static bool use_pipes = false;
 static unsigned int loops = 100;
-static unsigned int thread_mode = 0;
+static bool thread_mode = false;
 static unsigned int num_groups = 10;
 
 struct sender_context {
@@ -256,10 +256,8 @@
 		    "Use pipe() instead of socketpair()"),
 	OPT_BOOLEAN('t', "thread", &thread_mode,
 		    "Be multi thread instead of multi process"),
-	OPT_INTEGER('g', "group", &num_groups,
-		    "Specify number of groups"),
-	OPT_INTEGER('l', "loop", &loops,
-		    "Specify number of loops"),
+	OPT_UINTEGER('g', "group", &num_groups, "Specify number of groups"),
+	OPT_UINTEGER('l', "loop", &loops, "Specify number of loops"),
 	OPT_END()
 };
 

tools/perf/bench/sched-pipe.c

diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 4f77c7c..d9ab3ce 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -93,7 +93,7 @@
 
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
-		printf("# Extecuted %d pipe operations between two tasks\n\n",
+		printf("# Executed %d pipe operations between two tasks\n\n",
 			loops);
 
 		result_usec = diff.tv_sec * 1000000;

tools/perf/builtin-annotate.c

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 6ad7148..77bcc9b 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -14,7 +14,6 @@
 #include "util/cache.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
-#include "util/string.h"
 
 #include "perf.h"
 #include "util/debug.h"
@@ -29,80 +28,16 @@
 
 static char		const *input_name = "perf.data";
 
-static int		force;
+static bool		force;
 
-static int		full_paths;
+static bool		full_paths;
 
-static int		print_line;
-
-struct sym_hist {
-	u64		sum;
-	u64		ip[0];
-};
-
-struct sym_ext {
-	struct rb_node	node;
-	double		percent;
-	char		*path;
-};
-
-struct sym_priv {
-	struct sym_hist	*hist;
-	struct sym_ext	*ext;
-};
+static bool		print_line;
 
 static const char *sym_hist_filter;
 
-static int sym__alloc_hist(struct symbol *self)
+static int hists__add_entry(struct hists *self, struct addr_location *al)
 {
-	struct sym_priv *priv = symbol__priv(self);
-	const int size = (sizeof(*priv->hist) +
-			  (self->end - self->start) * sizeof(u64));
-
-	priv->hist = zalloc(size);
-	return priv->hist == NULL ? -1 : 0;
-}
-
-/*
- * collect histogram counts
- */
-static int annotate__hist_hit(struct hist_entry *he, u64 ip)
-{
-	unsigned int sym_size, offset;
-	struct symbol *sym = he->sym;
-	struct sym_priv *priv;
-	struct sym_hist *h;
-
-	he->count++;
-
-	if (!sym || !he->map)
-		return 0;
-
-	priv = symbol__priv(sym);
-	if (priv->hist == NULL && sym__alloc_hist(sym) < 0)
-		return -ENOMEM;
-
-	sym_size = sym->end - sym->start;
-	offset = ip - sym->start;
-
-	pr_debug3("%s: ip=%#Lx\n", __func__, he->map->unmap_ip(he->map, ip));
-
-	if (offset >= sym_size)
-		return 0;
-
-	h = priv->hist;
-	h->sum++;
-	h->ip[offset]++;
-
-	pr_debug3("%#Lx %s: count++ [ip: %#Lx, %#Lx] => %Ld\n", he->sym->start,
-		  he->sym->name, ip, ip - he->sym->start, h->ip[offset]);
-	return 0;
-}
-
-static int perf_session__add_hist_entry(struct perf_session *self,
-					struct addr_location *al, u64 count)
-{
-	bool hit;
 	struct hist_entry *he;
 
 	if (sym_hist_filter != NULL &&
@@ -116,11 +51,11 @@
 		return 0;
 	}
 
-	he = __perf_session__add_hist_entry(&self->hists, al, NULL, count, &hit);
+	he = __hists__add_entry(self, al, NULL, 1);
 	if (he == NULL)
 		return -ENOMEM;
 
-	return annotate__hist_hit(he, al->addr);
+	return hist_entry__inc_addr_samples(he, al->addr);
 }
 
 static int process_sample_event(event_t *event, struct perf_session *session)
@@ -136,7 +71,7 @@
 		return -1;
 	}
 
-	if (!al.filtered && perf_session__add_hist_entry(session, &al, 1)) {
+	if (!al.filtered && hists__add_entry(&session->hists, &al)) {
 		pr_warning("problem incrementing symbol count, "
 			   "skipping event\n");
 		return -1;
@@ -145,106 +80,11 @@
 	return 0;
 }
 
-struct objdump_line {
-	struct list_head node;
-	s64		 offset;
-	char		 *line;
-};
-
-static struct objdump_line *objdump_line__new(s64 offset, char *line)
-{
-	struct objdump_line *self = malloc(sizeof(*self));
-
-	if (self != NULL) {
-		self->offset = offset;
-		self->line = line;
-	}
-
-	return self;
-}
-
-static void objdump_line__free(struct objdump_line *self)
-{
-	free(self->line);
-	free(self);
-}
-
-static void objdump__add_line(struct list_head *head, struct objdump_line *line)
-{
-	list_add_tail(&line->node, head);
-}
-
-static struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
-						      struct objdump_line *pos)
-{
-	list_for_each_entry_continue(pos, head, node)
-		if (pos->offset >= 0)
-			return pos;
-
-	return NULL;
-}
-
-static int parse_line(FILE *file, struct hist_entry *he,
-		      struct list_head *head)
-{
-	struct symbol *sym = he->sym;
-	struct objdump_line *objdump_line;
-	char *line = NULL, *tmp, *tmp2;
-	size_t line_len;
-	s64 line_ip, offset = -1;
-	char *c;
-
-	if (getline(&line, &line_len, file) < 0)
-		return -1;
-
-	if (!line)
-		return -1;
-
-	c = strchr(line, '\n');
-	if (c)
-		*c = 0;
-
-	line_ip = -1;
-
-	/*
-	 * Strip leading spaces:
-	 */
-	tmp = line;
-	while (*tmp) {
-		if (*tmp != ' ')
-			break;
-		tmp++;
-	}
-
-	if (*tmp) {
-		/*
-		 * Parse hexa addresses followed by ':'
-		 */
-		line_ip = strtoull(tmp, &tmp2, 16);
-		if (*tmp2 != ':')
-			line_ip = -1;
-	}
-
-	if (line_ip != -1) {
-		u64 start = map__rip_2objdump(he->map, sym->start);
-		offset = line_ip - start;
-	}
-
-	objdump_line = objdump_line__new(offset, line);
-	if (objdump_line == NULL) {
-		free(line);
-		return -1;
-	}
-	objdump__add_line(head, objdump_line);
-
-	return 0;
-}
-
 static int objdump_line__print(struct objdump_line *self,
 			       struct list_head *head,
 			       struct hist_entry *he, u64 len)
 {
-	struct symbol *sym = he->sym;
+	struct symbol *sym = he->ms.sym;
 	static const char *prev_line;
 	static const char *prev_color;
 
@@ -327,7 +167,7 @@
 
 static void free_source_line(struct hist_entry *he, int len)
 {
-	struct sym_priv *priv = symbol__priv(he->sym);
+	struct sym_priv *priv = symbol__priv(he->ms.sym);
 	struct sym_ext *sym_ext = priv->ext;
 	int i;
 
@@ -346,7 +186,7 @@
 static void
 get_source_line(struct hist_entry *he, int len, const char *filename)
 {
-	struct symbol *sym = he->sym;
+	struct symbol *sym = he->ms.sym;
 	u64 start;
 	int i;
 	char cmd[PATH_MAX * 2];
@@ -361,7 +201,7 @@
 	if (!priv->ext)
 		return;
 
-	start = he->map->unmap_ip(he->map, sym->start);
+	start = he->ms.map->unmap_ip(he->ms.map, sym->start);
 
 	for (i = 0; i < len; i++) {
 		char *path = NULL;
@@ -425,7 +265,7 @@
 
 static void hist_entry__print_hits(struct hist_entry *self)
 {
-	struct symbol *sym = self->sym;
+	struct symbol *sym = self->ms.sym;
 	struct sym_priv *priv = symbol__priv(sym);
 	struct sym_hist *h = priv->hist;
 	u64 len = sym->end - sym->start, offset;
@@ -439,23 +279,17 @@
 
 static void annotate_sym(struct hist_entry *he)
 {
-	struct map *map = he->map;
+	struct map *map = he->ms.map;
 	struct dso *dso = map->dso;
-	struct symbol *sym = he->sym;
+	struct symbol *sym = he->ms.sym;
 	const char *filename = dso->long_name, *d_filename;
 	u64 len;
-	char command[PATH_MAX*2];
-	FILE *file;
 	LIST_HEAD(head);
 	struct objdump_line *pos, *n;
 
-	if (!filename)
+	if (hist_entry__annotate(he, &head) < 0)
 		return;
 
-	pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__,
-		 filename, sym->name, map->unmap_ip(map, sym->start),
-		 map->unmap_ip(map, sym->end));
-
 	if (full_paths)
 		d_filename = filename;
 	else
@@ -472,29 +306,6 @@
 	printf(" Percent |	Source code & Disassembly of %s\n", d_filename);
 	printf("------------------------------------------------\n");
 
-	if (verbose >= 2)
-		printf("annotating [%p] %30s : [%p] %30s\n",
-		       dso, dso->long_name, sym, sym->name);
-
-	sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s",
-		map__rip_2objdump(map, sym->start),
-		map__rip_2objdump(map, sym->end),
-		filename, filename);
-
-	if (verbose >= 3)
-		printf("doing: %s\n", command);
-
-	file = popen(command, "r");
-	if (!file)
-		return;
-
-	while (!feof(file)) {
-		if (parse_line(file, he, &head) < 0)
-			break;
-	}
-
-	pclose(file);
-
 	if (verbose)
 		hist_entry__print_hits(he);
 
@@ -508,25 +319,25 @@
 		free_source_line(he, len);
 }
 
-static void perf_session__find_annotations(struct perf_session *self)
+static void hists__find_annotations(struct hists *self)
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->hists); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
 		struct sym_priv *priv;
 
-		if (he->sym == NULL)
+		if (he->ms.sym == NULL)
 			continue;
 
-		priv = symbol__priv(he->sym);
+		priv = symbol__priv(he->ms.sym);
 		if (priv->hist == NULL)
 			continue;
 
 		annotate_sym(he);
 		/*
 		 * Since we have a hist_entry per IP for the same symbol, free
-		 * he->sym->hist to signal we already processed this symbol.
+		 * he->ms.sym->hist to signal we already processed this symbol.
 		 */
 		free(priv->hist);
 		priv->hist = NULL;
@@ -545,7 +356,7 @@
 	int ret;
 	struct perf_session *session;
 
-	session = perf_session__new(input_name, O_RDONLY, force);
+	session = perf_session__new(input_name, O_RDONLY, force, false);
 	if (session == NULL)
 		return -ENOMEM;
 
@@ -554,7 +365,7 @@
 		goto out_delete;
 
 	if (dump_trace) {
-		event__print_totals();
+		perf_session__fprintf_nr_events(session, stdout);
 		goto out_delete;
 	}
 
@@ -562,11 +373,11 @@
 		perf_session__fprintf(session, stdout);
 
 	if (verbose > 2)
-		dsos__fprintf(stdout);
+		perf_session__fprintf_dsos(session, stdout);
 
-	perf_session__collapse_resort(&session->hists);
-	perf_session__output_resort(&session->hists, session->event_total[0]);
-	perf_session__find_annotations(session);
+	hists__collapse_resort(&session->hists);
+	hists__output_resort(&session->hists);
+	hists__find_annotations(&session->hists);
 out_delete:
 	perf_session__delete(session);
 
@@ -581,10 +392,12 @@
 static const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
+	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
+		   "only consider symbols in these dsos"),
 	OPT_STRING('s', "symbol", &sym_hist_filter, "symbol",
 		    "symbol to annotate"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),

tools/perf/builtin-bench.c

diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 4699677..fcb9626 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -95,7 +95,7 @@
 	return;
 }
 
-static char *bench_format_str;
+static const char *bench_format_str;
 int bench_format = BENCH_FORMAT_DEFAULT;
 
 static const struct option bench_options[] = {
@@ -126,7 +126,7 @@
 	printf("\n");
 }
 
-static int bench_str2int(char *str)
+static int bench_str2int(const char *str)
 {
 	if (!str)
 		return BENCH_FORMAT_DEFAULT;

tools/perf/builtin-buildid-cache.c

diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 30a05f5..f8e3d18 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -27,7 +27,7 @@
 		   "file list", "file(s) to add"),
 	OPT_STRING('r', "remove", &remove_name_list_str, "file list",
 		    "file(s) to remove"),
-	OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose"),
+	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
 	OPT_END()
 };
 

tools/perf/builtin-buildid-list.c

diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index d0675c0..44a47e1 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -16,7 +16,7 @@
 #include "util/symbol.h"
 
 static char const *input_name = "perf.data";
-static int force;
+static bool force;
 static bool with_hits;
 
 static const char * const buildid_list_usage[] = {
@@ -29,7 +29,7 @@
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose"),
 	OPT_END()
 };
@@ -39,14 +39,14 @@
 	int err = -1;
 	struct perf_session *session;
 
-	session = perf_session__new(input_name, O_RDONLY, force);
+	session = perf_session__new(input_name, O_RDONLY, force, false);
 	if (session == NULL)
 		return -1;
 
 	if (with_hits)
 		perf_session__process_events(session, &build_id__mark_dso_hit_ops);
 
-	dsos__fprintf_buildid(stdout, with_hits);
+	perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
 
 	perf_session__delete(session);
 	return err;

tools/perf/builtin-diff.c

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 1ea15d8..a6e2fdc 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -19,23 +19,15 @@
 static char const *input_old = "perf.data.old",
 		  *input_new = "perf.data";
 static char	  diff__default_sort_order[] = "dso,symbol";
-static int  force;
+static bool  force;
 static bool show_displacement;
 
-static int perf_session__add_hist_entry(struct perf_session *self,
-					struct addr_location *al, u64 count)
+static int hists__add_entry(struct hists *self,
+			    struct addr_location *al, u64 period)
 {
-	bool hit;
-	struct hist_entry *he = __perf_session__add_hist_entry(&self->hists,
-							       al, NULL,
-							       count, &hit);
-	if (he == NULL)
-		return -ENOMEM;
-
-	if (hit)
-		he->count += count;
-
-	return 0;
+	if (__hists__add_entry(self, al, NULL, period) != NULL)
+		return 0;
+	return -ENOMEM;
 }
 
 static int diff__process_sample_event(event_t *event, struct perf_session *session)
@@ -57,12 +49,12 @@
 
 	event__parse_sample(event, session->sample_type, &data);
 
-	if (perf_session__add_hist_entry(session, &al, data.period)) {
-		pr_warning("problem incrementing symbol count, skipping event\n");
+	if (hists__add_entry(&session->hists, &al, data.period)) {
+		pr_warning("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
 
-	session->events_stats.total += data.period;
+	session->hists.stats.total_period += data.period;
 	return 0;
 }
 
@@ -95,35 +87,34 @@
 	rb_insert_color(&he->rb_node, root);
 }
 
-static void perf_session__resort_hist_entries(struct perf_session *self)
+static void hists__resort_entries(struct hists *self)
 {
 	unsigned long position = 1;
 	struct rb_root tmp = RB_ROOT;
-	struct rb_node *next = rb_first(&self->hists);
+	struct rb_node *next = rb_first(&self->entries);
 
 	while (next != NULL) {
 		struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node);
 
 		next = rb_next(&n->rb_node);
-		rb_erase(&n->rb_node, &self->hists);
+		rb_erase(&n->rb_node, &self->entries);
 		n->position = position++;
 		perf_session__insert_hist_entry_by_name(&tmp, n);
 	}
 
-	self->hists = tmp;
+	self->entries = tmp;
 }
 
-static void perf_session__set_hist_entries_positions(struct perf_session *self)
+static void hists__set_positions(struct hists *self)
 {
-	perf_session__output_resort(&self->hists, self->events_stats.total);
-	perf_session__resort_hist_entries(self);
+	hists__output_resort(self);
+	hists__resort_entries(self);
 }
 
-static struct hist_entry *
-perf_session__find_hist_entry(struct perf_session *self,
-			      struct hist_entry *he)
+static struct hist_entry *hists__find_entry(struct hists *self,
+					    struct hist_entry *he)
 {
-	struct rb_node *n = self->hists.rb_node;
+	struct rb_node *n = self->entries.rb_node;
 
 	while (n) {
 		struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node);
@@ -140,14 +131,13 @@
 	return NULL;
 }
 
-static void perf_session__match_hists(struct perf_session *old_session,
-				      struct perf_session *new_session)
+static void hists__match(struct hists *older, struct hists *newer)
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(&new_session->hists); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&newer->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *pos = rb_entry(nd, struct hist_entry, rb_node);
-		pos->pair = perf_session__find_hist_entry(old_session, pos);
+		pos->pair = hists__find_entry(older, pos);
 	}
 }
 
@@ -156,8 +146,8 @@
 	int ret, i;
 	struct perf_session *session[2];
 
-	session[0] = perf_session__new(input_old, O_RDONLY, force);
-	session[1] = perf_session__new(input_new, O_RDONLY, force);
+	session[0] = perf_session__new(input_old, O_RDONLY, force, false);
+	session[1] = perf_session__new(input_new, O_RDONLY, force, false);
 	if (session[0] == NULL || session[1] == NULL)
 		return -ENOMEM;
 
@@ -167,15 +157,13 @@
 			goto out_delete;
 	}
 
-	perf_session__output_resort(&session[1]->hists,
-				    session[1]->events_stats.total);
+	hists__output_resort(&session[1]->hists);
 	if (show_displacement)
-		perf_session__set_hist_entries_positions(session[0]);
+		hists__set_positions(&session[0]->hists);
 
-	perf_session__match_hists(session[0], session[1]);
-	perf_session__fprintf_hists(&session[1]->hists, session[0],
-				    show_displacement, stdout,
-				    session[1]->events_stats.total);
+	hists__match(&session[0]->hists, &session[1]->hists);
+	hists__fprintf(&session[1]->hists, &session[0]->hists,
+		       show_displacement, stdout);
 out_delete:
 	for (i = 0; i < 2; ++i)
 		perf_session__delete(session[i]);
@@ -188,7 +176,7 @@
 };
 
 static const struct option options[] = {
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('m', "displacement", &show_displacement,
 		    "Show position displacement relative to baseline"),
@@ -225,6 +213,10 @@
 			input_new = argv[1];
 		} else
 			input_new = argv[0];
+	} else if (symbol_conf.default_guest_vmlinux_name ||
+		   symbol_conf.default_guest_kallsyms) {
+		input_old = "perf.data.host";
+		input_new = "perf.data.guest";
 	}
 
 	symbol_conf.exclude_other = false;

tools/perf/builtin-help.c

diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 215b584..6d5a8a7 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -29,14 +29,14 @@
 	HELP_FORMAT_WEB,
 };
 
-static int show_all = 0;
+static bool show_all = false;
 static enum help_format help_format = HELP_FORMAT_MAN;
 static struct option builtin_help_options[] = {
 	OPT_BOOLEAN('a', "all", &show_all, "print all available commands"),
-	OPT_SET_INT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN),
-	OPT_SET_INT('w', "web", &help_format, "show manual in web browser",
+	OPT_SET_UINT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN),
+	OPT_SET_UINT('w', "web", &help_format, "show manual in web browser",
 			HELP_FORMAT_WEB),
-	OPT_SET_INT('i', "info", &help_format, "show info page",
+	OPT_SET_UINT('i', "info", &help_format, "show info page",
 			HELP_FORMAT_INFO),
 	OPT_END(),
 };

tools/perf/builtin-inject.c

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
new file mode 100644
index 0000000..8e3e47b
--- /dev/null
+++ b/tools/perf/builtin-inject.c
@@ -0,0 +1,228 @@
+/*
+ * builtin-inject.c
+ *
+ * Builtin inject command: Examine the live mode (stdin) event stream
+ * and repipe it to stdout while optionally injecting additional
+ * events into it.
+ */
+#include "builtin.h"
+
+#include "perf.h"
+#include "util/session.h"
+#include "util/debug.h"
+
+#include "util/parse-options.h"
+
+static char		const *input_name = "-";
+static bool		inject_build_ids;
+
+static int event__repipe(event_t *event __used,
+			 struct perf_session *session __used)
+{
+	uint32_t size;
+	void *buf = event;
+
+	size = event->header.size;
+
+	while (size) {
+		int ret = write(STDOUT_FILENO, buf, size);
+		if (ret < 0)
+			return -errno;
+
+		size -= ret;
+		buf += ret;
+	}
+
+	return 0;
+}
+
+static int event__repipe_mmap(event_t *self, struct perf_session *session)
+{
+	int err;
+
+	err = event__process_mmap(self, session);
+	event__repipe(self, session);
+
+	return err;
+}
+
+static int event__repipe_task(event_t *self, struct perf_session *session)
+{
+	int err;
+
+	err = event__process_task(self, session);
+	event__repipe(self, session);
+
+	return err;
+}
+
+static int event__repipe_tracing_data(event_t *self,
+				      struct perf_session *session)
+{
+	int err;
+
+	event__repipe(self, session);
+	err = event__process_tracing_data(self, session);
+
+	return err;
+}
+
+static int dso__read_build_id(struct dso *self)
+{
+	if (self->has_build_id)
+		return 0;
+
+	if (filename__read_build_id(self->long_name, self->build_id,
+				    sizeof(self->build_id)) > 0) {
+		self->has_build_id = true;
+		return 0;
+	}
+
+	return -1;
+}
+
+static int dso__inject_build_id(struct dso *self, struct perf_session *session)
+{
+	u16 misc = PERF_RECORD_MISC_USER;
+	struct machine *machine;
+	int err;
+
+	if (dso__read_build_id(self) < 0) {
+		pr_debug("no build_id found for %s\n", self->long_name);
+		return -1;
+	}
+
+	machine = perf_session__find_host_machine(session);
+	if (machine == NULL) {
+		pr_err("Can't find machine for session\n");
+		return -1;
+	}
+
+	if (self->kernel)
+		misc = PERF_RECORD_MISC_KERNEL;
+
+	err = event__synthesize_build_id(self, misc, event__repipe,
+					 machine, session);
+	if (err) {
+		pr_err("Can't synthesize build_id event for %s\n", self->long_name);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int event__inject_buildid(event_t *event, struct perf_session *session)
+{
+	struct addr_location al;
+	struct thread *thread;
+	u8 cpumode;
+
+	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	thread = perf_session__findnew(session, event->ip.pid);
+	if (thread == NULL) {
+		pr_err("problem processing %d event, skipping it.\n",
+		       event->header.type);
+		goto repipe;
+	}
+
+	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
+			      event->ip.pid, event->ip.ip, &al);
+
+	if (al.map != NULL) {
+		if (!al.map->dso->hit) {
+			al.map->dso->hit = 1;
+			if (map__load(al.map, NULL) >= 0) {
+				dso__inject_build_id(al.map->dso, session);
+				/*
+				 * If this fails, too bad, let the other side
+				 * account this as unresolved.
+				 */
+			} else
+				pr_warning("no symbols found in %s, maybe "
+					   "install a debug package?\n",
+					   al.map->dso->long_name);
+		}
+	}
+
+repipe:
+	event__repipe(event, session);
+	return 0;
+}
+
+struct perf_event_ops inject_ops = {
+	.sample		= event__repipe,
+	.mmap		= event__repipe,
+	.comm		= event__repipe,
+	.fork		= event__repipe,
+	.exit		= event__repipe,
+	.lost		= event__repipe,
+	.read		= event__repipe,
+	.throttle	= event__repipe,
+	.unthrottle	= event__repipe,
+	.attr		= event__repipe,
+	.event_type 	= event__repipe,
+	.tracing_data 	= event__repipe,
+	.build_id 	= event__repipe,
+};
+
+extern volatile int session_done;
+
+static void sig_handler(int sig __attribute__((__unused__)))
+{
+	session_done = 1;
+}
+
+static int __cmd_inject(void)
+{
+	struct perf_session *session;
+	int ret = -EINVAL;
+
+	signal(SIGINT, sig_handler);
+
+	if (inject_build_ids) {
+		inject_ops.sample	= event__inject_buildid;
+		inject_ops.mmap		= event__repipe_mmap;
+		inject_ops.fork		= event__repipe_task;
+		inject_ops.tracing_data	= event__repipe_tracing_data;
+	}
+
+	session = perf_session__new(input_name, O_RDONLY, false, true);
+	if (session == NULL)
+		return -ENOMEM;
+
+	ret = perf_session__process_events(session, &inject_ops);
+
+	perf_session__delete(session);
+
+	return ret;
+}
+
+static const char * const report_usage[] = {
+	"perf inject [<options>]",
+	NULL
+};
+
+static const struct option options[] = {
+	OPT_BOOLEAN('b', "build-ids", &inject_build_ids,
+		    "Inject build-ids into the output stream"),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show build ids, etc)"),
+	OPT_END()
+};
+
+int cmd_inject(int argc, const char **argv, const char *prefix __used)
+{
+	argc = parse_options(argc, argv, options, report_usage, 0);
+
+	/*
+	 * Any (unrecognized) arguments left?
+	 */
+	if (argc)
+		usage_with_options(report_usage, options);
+
+	if (symbol__init() < 0)
+		return -1;
+
+	return __cmd_inject();
+}

tools/perf/builtin-kmem.c

diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 924a951..31f60a2 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -335,8 +335,9 @@
 }
 
 static struct perf_event_ops event_ops = {
-	.sample	= process_sample_event,
-	.comm	= event__process_comm,
+	.sample			= process_sample_event,
+	.comm			= event__process_comm,
+	.ordered_samples	= true,
 };
 
 static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -351,6 +352,7 @@
 			   int n_lines, int is_caller)
 {
 	struct rb_node *next;
+	struct machine *machine;
 
 	printf("%.102s\n", graph_dotted_line);
 	printf(" %-34s |",  is_caller ? "Callsite": "Alloc Ptr");
@@ -359,23 +361,29 @@
 
 	next = rb_first(root);
 
+	machine = perf_session__find_host_machine(session);
+	if (!machine) {
+		pr_err("__print_result: couldn't find kernel information\n");
+		return;
+	}
 	while (next && n_lines--) {
 		struct alloc_stat *data = rb_entry(next, struct alloc_stat,
 						   node);
 		struct symbol *sym = NULL;
+		struct map *map;
 		char buf[BUFSIZ];
 		u64 addr;
 
 		if (is_caller) {
 			addr = data->call_site;
 			if (!raw_ip)
-				sym = map_groups__find_function(&session->kmaps, addr, NULL);
+				sym = machine__find_kernel_function(machine, addr, &map, NULL);
 		} else
 			addr = data->ptr;
 
 		if (sym != NULL)
 			snprintf(buf, sizeof(buf), "%s+%Lx", sym->name,
-				 addr - sym->start);
+				 addr - map->unmap_ip(map, sym->start));
 		else
 			snprintf(buf, sizeof(buf), "%#Lx", addr);
 		printf(" %-34s |", buf);
@@ -484,10 +492,13 @@
 static int __cmd_kmem(void)
 {
 	int err = -EINVAL;
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0);
+	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (perf_session__create_kernel_maps(session) < 0)
+		goto out_delete;
+
 	if (!perf_session__has_traces(session, "kmem record"))
 		goto out_delete;
 
@@ -718,7 +729,6 @@
 	"record",
 	"-a",
 	"-R",
-	"-M",
 	"-f",
 	"-c", "1",
 	"-e", "kmem:kmalloc",

tools/perf/builtin-kvm.c

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
new file mode 100644
index 0000000..34d1e85
--- /dev/null
+++ b/tools/perf/builtin-kvm.c
@@ -0,0 +1,144 @@
+#include "builtin.h"
+#include "perf.h"
+
+#include "util/util.h"
+#include "util/cache.h"
+#include "util/symbol.h"
+#include "util/thread.h"
+#include "util/header.h"
+#include "util/session.h"
+
+#include "util/parse-options.h"
+#include "util/trace-event.h"
+
+#include "util/debug.h"
+
+#include <sys/prctl.h>
+
+#include <semaphore.h>
+#include <pthread.h>
+#include <math.h>
+
+static const char		*file_name;
+static char			name_buffer[256];
+
+bool				perf_host = 1;
+bool				perf_guest;
+
+static const char * const kvm_usage[] = {
+	"perf kvm [<options>] {top|record|report|diff|buildid-list}",
+	NULL
+};
+
+static const struct option kvm_options[] = {
+	OPT_STRING('i', "input", &file_name, "file",
+		   "Input file name"),
+	OPT_STRING('o', "output", &file_name, "file",
+		   "Output file name"),
+	OPT_BOOLEAN(0, "guest", &perf_guest,
+		    "Collect guest os data"),
+	OPT_BOOLEAN(0, "host", &perf_host,
+		    "Collect guest os data"),
+	OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory",
+		   "guest mount directory under which every guest os"
+		   " instance has a subdir"),
+	OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name,
+		   "file", "file saving guest os vmlinux"),
+	OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms,
+		   "file", "file saving guest os /proc/kallsyms"),
+	OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
+		   "file", "file saving guest os /proc/modules"),
+	OPT_END()
+};
+
+static int __cmd_record(int argc, const char **argv)
+{
+	int rec_argc, i = 0, j;
+	const char **rec_argv;
+
+	rec_argc = argc + 2;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+	rec_argv[i++] = strdup("record");
+	rec_argv[i++] = strdup("-o");
+	rec_argv[i++] = strdup(file_name);
+	for (j = 1; j < argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	BUG_ON(i != rec_argc);
+
+	return cmd_record(i, rec_argv, NULL);
+}
+
+static int __cmd_report(int argc, const char **argv)
+{
+	int rec_argc, i = 0, j;
+	const char **rec_argv;
+
+	rec_argc = argc + 2;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+	rec_argv[i++] = strdup("report");
+	rec_argv[i++] = strdup("-i");
+	rec_argv[i++] = strdup(file_name);
+	for (j = 1; j < argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	BUG_ON(i != rec_argc);
+
+	return cmd_report(i, rec_argv, NULL);
+}
+
+static int __cmd_buildid_list(int argc, const char **argv)
+{
+	int rec_argc, i = 0, j;
+	const char **rec_argv;
+
+	rec_argc = argc + 2;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+	rec_argv[i++] = strdup("buildid-list");
+	rec_argv[i++] = strdup("-i");
+	rec_argv[i++] = strdup(file_name);
+	for (j = 1; j < argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	BUG_ON(i != rec_argc);
+
+	return cmd_buildid_list(i, rec_argv, NULL);
+}
+
+int cmd_kvm(int argc, const char **argv, const char *prefix __used)
+{
+	perf_host = perf_guest = 0;
+
+	argc = parse_options(argc, argv, kvm_options, kvm_usage,
+			PARSE_OPT_STOP_AT_NON_OPTION);
+	if (!argc)
+		usage_with_options(kvm_usage, kvm_options);
+
+	if (!perf_host)
+		perf_guest = 1;
+
+	if (!file_name) {
+		if (perf_host && !perf_guest)
+			sprintf(name_buffer, "perf.data.host");
+		else if (!perf_host && perf_guest)
+			sprintf(name_buffer, "perf.data.guest");
+		else
+			sprintf(name_buffer, "perf.data.kvm");
+		file_name = name_buffer;
+	}
+
+	if (!strncmp(argv[0], "rec", 3))
+		return __cmd_record(argc, argv);
+	else if (!strncmp(argv[0], "rep", 3))
+		return __cmd_report(argc, argv);
+	else if (!strncmp(argv[0], "diff", 4))
+		return cmd_diff(argc, argv, NULL);
+	else if (!strncmp(argv[0], "top", 3))
+		return cmd_top(argc, argv, NULL);
+	else if (!strncmp(argv[0], "buildid-list", 12))
+		return __cmd_buildid_list(argc, argv);
+	else
+		usage_with_options(kvm_usage, kvm_options);
+
+	return 0;
+}

tools/perf/builtin-lock.c

diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index e12c844..821c158 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -23,6 +23,8 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 
+static struct perf_session *session;
+
 /* based on kernel/lockdep.c */
 #define LOCKHASH_BITS		12
 #define LOCKHASH_SIZE		(1UL << LOCKHASH_BITS)
@@ -32,9 +34,6 @@
 #define __lockhashfn(key)	hash_long((unsigned long)key, LOCKHASH_BITS)
 #define lockhashentry(key)	(lockhash_table + __lockhashfn((key)))
 
-#define LOCK_STATE_UNLOCKED	0	       /* initial state */
-#define LOCK_STATE_LOCKED	1
-
 struct lock_stat {
 	struct list_head	hash_entry;
 	struct rb_node		rb;		/* used for sorting */
@@ -47,20 +46,151 @@
 	void			*addr;		/* address of lockdep_map, used as ID */
 	char			*name;		/* for strcpy(), we cannot use const */
 
-	int			state;
-	u64			prev_event_time; /* timestamp of previous event */
-
-	unsigned int		nr_acquired;
 	unsigned int		nr_acquire;
+	unsigned int		nr_acquired;
 	unsigned int		nr_contended;
 	unsigned int		nr_release;
 
+	unsigned int		nr_readlock;
+	unsigned int		nr_trylock;
 	/* these times are in nano sec. */
 	u64			wait_time_total;
 	u64			wait_time_min;
 	u64			wait_time_max;
+
+	int			discard; /* flag of blacklist */
 };
 
+/*
+ * States of lock_seq_stat
+ *
+ * UNINITIALIZED is required for detecting first event of acquire.
+ * As the nature of lock events, there is no guarantee
+ * that the first event for the locks are acquire,
+ * it can be acquired, contended or release.
+ */
+#define SEQ_STATE_UNINITIALIZED      0	       /* initial state */
+#define SEQ_STATE_RELEASED	1
+#define SEQ_STATE_ACQUIRING	2
+#define SEQ_STATE_ACQUIRED	3
+#define SEQ_STATE_READ_ACQUIRED	4
+#define SEQ_STATE_CONTENDED	5
+
+/*
+ * MAX_LOCK_DEPTH
+ * Imported from include/linux/sched.h.
+ * Should this be synchronized?
+ */
+#define MAX_LOCK_DEPTH 48
+
+/*
+ * struct lock_seq_stat:
+ * Place to put on state of one lock sequence
+ * 1) acquire -> acquired -> release
+ * 2) acquire -> contended -> acquired -> release
+ * 3) acquire (with read or try) -> release
+ * 4) Are there other patterns?
+ */
+struct lock_seq_stat {
+	struct list_head        list;
+	int			state;
+	u64			prev_event_time;
+	void                    *addr;
+
+	int                     read_count;
+};
+
+struct thread_stat {
+	struct rb_node		rb;
+
+	u32                     tid;
+	struct list_head        seq_list;
+};
+
+static struct rb_root		thread_stats;
+
+static struct thread_stat *thread_stat_find(u32 tid)
+{
+	struct rb_node *node;
+	struct thread_stat *st;
+
+	node = thread_stats.rb_node;
+	while (node) {
+		st = container_of(node, struct thread_stat, rb);
+		if (st->tid == tid)
+			return st;
+		else if (tid < st->tid)
+			node = node->rb_left;
+		else
+			node = node->rb_right;
+	}
+
+	return NULL;
+}
+
+static void thread_stat_insert(struct thread_stat *new)
+{
+	struct rb_node **rb = &thread_stats.rb_node;
+	struct rb_node *parent = NULL;
+	struct thread_stat *p;
+
+	while (*rb) {
+		p = container_of(*rb, struct thread_stat, rb);
+		parent = *rb;
+
+		if (new->tid < p->tid)
+			rb = &(*rb)->rb_left;
+		else if (new->tid > p->tid)
+			rb = &(*rb)->rb_right;
+		else
+			BUG_ON("inserting invalid thread_stat\n");
+	}
+
+	rb_link_node(&new->rb, parent, rb);
+	rb_insert_color(&new->rb, &thread_stats);
+}
+
+static struct thread_stat *thread_stat_findnew_after_first(u32 tid)
+{
+	struct thread_stat *st;
+
+	st = thread_stat_find(tid);
+	if (st)
+		return st;
+
+	st = zalloc(sizeof(struct thread_stat));
+	if (!st)
+		die("memory allocation failed\n");
+
+	st->tid = tid;
+	INIT_LIST_HEAD(&st->seq_list);
+
+	thread_stat_insert(st);
+
+	return st;
+}
+
+static struct thread_stat *thread_stat_findnew_first(u32 tid);
+static struct thread_stat *(*thread_stat_findnew)(u32 tid) =
+	thread_stat_findnew_first;
+
+static struct thread_stat *thread_stat_findnew_first(u32 tid)
+{
+	struct thread_stat *st;
+
+	st = zalloc(sizeof(struct thread_stat));
+	if (!st)
+		die("memory allocation failed\n");
+	st->tid = tid;
+	INIT_LIST_HEAD(&st->seq_list);
+
+	rb_link_node(&st->rb, NULL, &thread_stats.rb_node);
+	rb_insert_color(&st->rb, &thread_stats);
+
+	thread_stat_findnew = thread_stat_findnew_after_first;
+	return st;
+}
+
 /* build simple key function one is bigger than two */
 #define SINGLE_KEY(member)						\
 	static int lock_stat_key_ ## member(struct lock_stat *one,	\
@@ -175,8 +305,6 @@
 		goto alloc_failed;
 	strcpy(new->name, name);
 
-	/* LOCK_STATE_UNLOCKED == 0 isn't guaranteed forever */
-	new->state = LOCK_STATE_UNLOCKED;
 	new->wait_time_min = ULLONG_MAX;
 
 	list_add(&new->hash_entry, entry);
@@ -188,8 +316,6 @@
 
 static char			const *input_name = "perf.data";
 
-static int			profile_cpu = -1;
-
 struct raw_event_sample {
 	u32			size;
 	char			data[0];
@@ -198,6 +324,7 @@
 struct trace_acquire_event {
 	void			*addr;
 	const char		*name;
+	int			flag;
 };
 
 struct trace_acquired_event {
@@ -241,120 +368,258 @@
 			      struct thread *thread);
 };
 
+static struct lock_seq_stat *get_seq(struct thread_stat *ts, void *addr)
+{
+	struct lock_seq_stat *seq;
+
+	list_for_each_entry(seq, &ts->seq_list, list) {
+		if (seq->addr == addr)
+			return seq;
+	}
+
+	seq = zalloc(sizeof(struct lock_seq_stat));
+	if (!seq)
+		die("Not enough memory\n");
+	seq->state = SEQ_STATE_UNINITIALIZED;
+	seq->addr = addr;
+
+	list_add(&seq->list, &ts->seq_list);
+	return seq;
+}
+
+enum broken_state {
+	BROKEN_ACQUIRE,
+	BROKEN_ACQUIRED,
+	BROKEN_CONTENDED,
+	BROKEN_RELEASE,
+	BROKEN_MAX,
+};
+
+static int bad_hist[BROKEN_MAX];
+
+enum acquire_flags {
+	TRY_LOCK = 1,
+	READ_LOCK = 2,
+};
+
 static void
 report_lock_acquire_event(struct trace_acquire_event *acquire_event,
 			struct event *__event __used,
 			int cpu __used,
-			u64 timestamp,
+			u64 timestamp __used,
 			struct thread *thread __used)
 {
-	struct lock_stat *st;
+	struct lock_stat *ls;
+	struct thread_stat *ts;
+	struct lock_seq_stat *seq;
 
-	st = lock_stat_findnew(acquire_event->addr, acquire_event->name);
+	ls = lock_stat_findnew(acquire_event->addr, acquire_event->name);
+	if (ls->discard)
+		return;
 
-	switch (st->state) {
-	case LOCK_STATE_UNLOCKED:
+	ts = thread_stat_findnew(thread->pid);
+	seq = get_seq(ts, acquire_event->addr);
+
+	switch (seq->state) {
+	case SEQ_STATE_UNINITIALIZED:
+	case SEQ_STATE_RELEASED:
+		if (!acquire_event->flag) {
+			seq->state = SEQ_STATE_ACQUIRING;
+		} else {
+			if (acquire_event->flag & TRY_LOCK)
+				ls->nr_trylock++;
+			if (acquire_event->flag & READ_LOCK)
+				ls->nr_readlock++;
+			seq->state = SEQ_STATE_READ_ACQUIRED;
+			seq->read_count = 1;
+			ls->nr_acquired++;
+		}
 		break;
-	case LOCK_STATE_LOCKED:
+	case SEQ_STATE_READ_ACQUIRED:
+		if (acquire_event->flag & READ_LOCK) {
+			seq->read_count++;
+			ls->nr_acquired++;
+			goto end;
+		} else {
+			goto broken;
+		}
+		break;
+	case SEQ_STATE_ACQUIRED:
+	case SEQ_STATE_ACQUIRING:
+	case SEQ_STATE_CONTENDED:
+broken:
+		/* broken lock sequence, discard it */
+		ls->discard = 1;
+		bad_hist[BROKEN_ACQUIRE]++;
+		list_del(&seq->list);
+		free(seq);
+		goto end;
 		break;
 	default:
-		BUG_ON(1);
+		BUG_ON("Unknown state of lock sequence found!\n");
 		break;
 	}
 
-	st->prev_event_time = timestamp;
+	ls->nr_acquire++;
+	seq->prev_event_time = timestamp;
+end:
+	return;
 }
 
 static void
 report_lock_acquired_event(struct trace_acquired_event *acquired_event,
 			 struct event *__event __used,
 			 int cpu __used,
-			 u64 timestamp,
+			 u64 timestamp __used,
 			 struct thread *thread __used)
 {
-	struct lock_stat *st;
+	struct lock_stat *ls;
+	struct thread_stat *ts;
+	struct lock_seq_stat *seq;
+	u64 contended_term;
 
-	st = lock_stat_findnew(acquired_event->addr, acquired_event->name);
+	ls = lock_stat_findnew(acquired_event->addr, acquired_event->name);
+	if (ls->discard)
+		return;
 
-	switch (st->state) {
-	case LOCK_STATE_UNLOCKED:
-		st->state = LOCK_STATE_LOCKED;
-		st->nr_acquired++;
+	ts = thread_stat_findnew(thread->pid);
+	seq = get_seq(ts, acquired_event->addr);
+
+	switch (seq->state) {
+	case SEQ_STATE_UNINITIALIZED:
+		/* orphan event, do nothing */
+		return;
+	case SEQ_STATE_ACQUIRING:
 		break;
-	case LOCK_STATE_LOCKED:
+	case SEQ_STATE_CONTENDED:
+		contended_term = timestamp - seq->prev_event_time;
+		ls->wait_time_total += contended_term;
+		if (contended_term < ls->wait_time_min)
+			ls->wait_time_min = contended_term;
+		if (ls->wait_time_max < contended_term)
+			ls->wait_time_max = contended_term;
 		break;
+	case SEQ_STATE_RELEASED:
+	case SEQ_STATE_ACQUIRED:
+	case SEQ_STATE_READ_ACQUIRED:
+		/* broken lock sequence, discard it */
+		ls->discard = 1;
+		bad_hist[BROKEN_ACQUIRED]++;
+		list_del(&seq->list);
+		free(seq);
+		goto end;
+		break;
+
 	default:
-		BUG_ON(1);
+		BUG_ON("Unknown state of lock sequence found!\n");
 		break;
 	}
 
-	st->prev_event_time = timestamp;
+	seq->state = SEQ_STATE_ACQUIRED;
+	ls->nr_acquired++;
+	seq->prev_event_time = timestamp;
+end:
+	return;
 }
 
 static void
 report_lock_contended_event(struct trace_contended_event *contended_event,
 			  struct event *__event __used,
 			  int cpu __used,
-			  u64 timestamp,
+			  u64 timestamp __used,
 			  struct thread *thread __used)
 {
-	struct lock_stat *st;
+	struct lock_stat *ls;
+	struct thread_stat *ts;
+	struct lock_seq_stat *seq;
 
-	st = lock_stat_findnew(contended_event->addr, contended_event->name);
+	ls = lock_stat_findnew(contended_event->addr, contended_event->name);
+	if (ls->discard)
+		return;
 
-	switch (st->state) {
-	case LOCK_STATE_UNLOCKED:
+	ts = thread_stat_findnew(thread->pid);
+	seq = get_seq(ts, contended_event->addr);
+
+	switch (seq->state) {
+	case SEQ_STATE_UNINITIALIZED:
+		/* orphan event, do nothing */
+		return;
+	case SEQ_STATE_ACQUIRING:
 		break;
-	case LOCK_STATE_LOCKED:
-		st->nr_contended++;
+	case SEQ_STATE_RELEASED:
+	case SEQ_STATE_ACQUIRED:
+	case SEQ_STATE_READ_ACQUIRED:
+	case SEQ_STATE_CONTENDED:
+		/* broken lock sequence, discard it */
+		ls->discard = 1;
+		bad_hist[BROKEN_CONTENDED]++;
+		list_del(&seq->list);
+		free(seq);
+		goto end;
 		break;
 	default:
-		BUG_ON(1);
+		BUG_ON("Unknown state of lock sequence found!\n");
 		break;
 	}
 
-	st->prev_event_time = timestamp;
+	seq->state = SEQ_STATE_CONTENDED;
+	ls->nr_contended++;
+	seq->prev_event_time = timestamp;
+end:
+	return;
 }
 
 static void
 report_lock_release_event(struct trace_release_event *release_event,
 			struct event *__event __used,
 			int cpu __used,
-			u64 timestamp,
+			u64 timestamp __used,
 			struct thread *thread __used)
 {
-	struct lock_stat *st;
-	u64 hold_time;
+	struct lock_stat *ls;
+	struct thread_stat *ts;
+	struct lock_seq_stat *seq;
 
-	st = lock_stat_findnew(release_event->addr, release_event->name);
+	ls = lock_stat_findnew(release_event->addr, release_event->name);
+	if (ls->discard)
+		return;
 
-	switch (st->state) {
-	case LOCK_STATE_UNLOCKED:
+	ts = thread_stat_findnew(thread->pid);
+	seq = get_seq(ts, release_event->addr);
+
+	switch (seq->state) {
+	case SEQ_STATE_UNINITIALIZED:
+		goto end;
 		break;
-	case LOCK_STATE_LOCKED:
-		st->state = LOCK_STATE_UNLOCKED;
-		hold_time = timestamp - st->prev_event_time;
-
-		if (timestamp < st->prev_event_time) {
-			/* terribly, this can happen... */
+	case SEQ_STATE_ACQUIRED:
+		break;
+	case SEQ_STATE_READ_ACQUIRED:
+		seq->read_count--;
+		BUG_ON(seq->read_count < 0);
+		if (!seq->read_count) {
+			ls->nr_release++;
 			goto end;
 		}
-
-		if (st->wait_time_min > hold_time)
-			st->wait_time_min = hold_time;
-		if (st->wait_time_max < hold_time)
-			st->wait_time_max = hold_time;
-		st->wait_time_total += hold_time;
-
-		st->nr_release++;
+		break;
+	case SEQ_STATE_ACQUIRING:
+	case SEQ_STATE_CONTENDED:
+	case SEQ_STATE_RELEASED:
+		/* broken lock sequence, discard it */
+		ls->discard = 1;
+		bad_hist[BROKEN_RELEASE]++;
+		goto free_seq;
 		break;
 	default:
-		BUG_ON(1);
+		BUG_ON("Unknown state of lock sequence found!\n");
 		break;
 	}
 
+	ls->nr_release++;
+free_seq:
+	list_del(&seq->list);
+	free(seq);
 end:
-	st->prev_event_time = timestamp;
+	return;
 }
 
 /* lock oriented handlers */
@@ -381,6 +646,7 @@
 	tmp = raw_field_value(event, "lockdep_addr", data);
 	memcpy(&acquire_event.addr, &tmp, sizeof(void *));
 	acquire_event.name = (char *)raw_field_ptr(event, "name", data);
+	acquire_event.flag = (int)raw_field_value(event, "flag", data);
 
 	if (trace_handler->acquire_event)
 		trace_handler->acquire_event(&acquire_event, event, cpu, timestamp, thread);
@@ -441,8 +707,7 @@
 }
 
 static void
-process_raw_event(void *data, int cpu,
-		  u64 timestamp, struct thread *thread)
+process_raw_event(void *data, int cpu, u64 timestamp, struct thread *thread)
 {
 	struct event *event;
 	int type;
@@ -460,173 +725,19 @@
 		process_lock_release_event(data, event, cpu, timestamp, thread);
 }
 
-struct raw_event_queue {
-	u64			timestamp;
-	int			cpu;
-	void			*data;
-	struct thread		*thread;
-	struct list_head	list;
-};
-
-static LIST_HEAD(raw_event_head);
-
-#define FLUSH_PERIOD	(5 * NSEC_PER_SEC)
-
-static u64 flush_limit = ULLONG_MAX;
-static u64 last_flush = 0;
-struct raw_event_queue *last_inserted;
-
-static void flush_raw_event_queue(u64 limit)
+static void print_bad_events(int bad, int total)
 {
-	struct raw_event_queue *tmp, *iter;
+	/* Output for debug, this have to be removed */
+	int i;
+	const char *name[4] =
+		{ "acquire", "acquired", "contended", "release" };
 
-	list_for_each_entry_safe(iter, tmp, &raw_event_head, list) {
-		if (iter->timestamp > limit)
-			return;
-
-		if (iter == last_inserted)
-			last_inserted = NULL;
-
-		process_raw_event(iter->data, iter->cpu, iter->timestamp,
-				  iter->thread);
-
-		last_flush = iter->timestamp;
-		list_del(&iter->list);
-		free(iter->data);
-		free(iter);
-	}
-}
-
-static void __queue_raw_event_end(struct raw_event_queue *new)
-{
-	struct raw_event_queue *iter;
-
-	list_for_each_entry_reverse(iter, &raw_event_head, list) {
-		if (iter->timestamp < new->timestamp) {
-			list_add(&new->list, &iter->list);
-			return;
-		}
-	}
-
-	list_add(&new->list, &raw_event_head);
-}
-
-static void __queue_raw_event_before(struct raw_event_queue *new,
-				     struct raw_event_queue *iter)
-{
-	list_for_each_entry_continue_reverse(iter, &raw_event_head, list) {
-		if (iter->timestamp < new->timestamp) {
-			list_add(&new->list, &iter->list);
-			return;
-		}
-	}
-
-	list_add(&new->list, &raw_event_head);
-}
-
-static void __queue_raw_event_after(struct raw_event_queue *new,
-				     struct raw_event_queue *iter)
-{
-	list_for_each_entry_continue(iter, &raw_event_head, list) {
-		if (iter->timestamp > new->timestamp) {
-			list_add_tail(&new->list, &iter->list);
-			return;
-		}
-	}
-	list_add_tail(&new->list, &raw_event_head);
-}
-
-/* The queue is ordered by time */
-static void __queue_raw_event(struct raw_event_queue *new)
-{
-	if (!last_inserted) {
-		__queue_raw_event_end(new);
-		return;
-	}
-
-	/*
-	 * Most of the time the current event has a timestamp
-	 * very close to the last event inserted, unless we just switched
-	 * to another event buffer. Having a sorting based on a list and
-	 * on the last inserted event that is close to the current one is
-	 * probably more efficient than an rbtree based sorting.
-	 */
-	if (last_inserted->timestamp >= new->timestamp)
-		__queue_raw_event_before(new, last_inserted);
-	else
-		__queue_raw_event_after(new, last_inserted);
-}
-
-static void queue_raw_event(void *data, int raw_size, int cpu,
-			    u64 timestamp, struct thread *thread)
-{
-	struct raw_event_queue *new;
-
-	if (flush_limit == ULLONG_MAX)
-		flush_limit = timestamp + FLUSH_PERIOD;
-
-	if (timestamp < last_flush) {
-		printf("Warning: Timestamp below last timeslice flush\n");
-		return;
-	}
-
-	new = malloc(sizeof(*new));
-	if (!new)
-		die("Not enough memory\n");
-
-	new->timestamp = timestamp;
-	new->cpu = cpu;
-	new->thread = thread;
-
-	new->data = malloc(raw_size);
-	if (!new->data)
-		die("Not enough memory\n");
-
-	memcpy(new->data, data, raw_size);
-
-	__queue_raw_event(new);
-	last_inserted = new;
-
-	/*
-	 * We want to have a slice of events covering 2 * FLUSH_PERIOD
-	 * If FLUSH_PERIOD is big enough, it ensures every events that occured
-	 * in the first half of the timeslice have all been buffered and there
-	 * are none remaining (we need that because of the weakly ordered
-	 * event recording we have). Then once we reach the 2 * FLUSH_PERIOD
-	 * timeslice, we flush the first half to be gentle with the memory
-	 * (the second half can still get new events in the middle, so wait
-	 * another period to flush it)
-	 */
-	if (new->timestamp > flush_limit &&
-		new->timestamp - flush_limit > FLUSH_PERIOD) {
-		flush_limit += FLUSH_PERIOD;
-		flush_raw_event_queue(flush_limit);
-	}
-}
-
-static int process_sample_event(event_t *event, struct perf_session *session)
-{
-	struct thread *thread;
-	struct sample_data data;
-
-	bzero(&data, sizeof(struct sample_data));
-	event__parse_sample(event, session->sample_type, &data);
-	thread = perf_session__findnew(session, data.pid);
-
-	if (thread == NULL) {
-		pr_debug("problem processing %d event, skipping it.\n",
-			 event->header.type);
-		return -1;
-	}
-
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
-
-	if (profile_cpu != -1 && profile_cpu != (int) data.cpu)
-		return 0;
-
-	queue_raw_event(data.raw_data, data.raw_size, data.cpu, data.time, thread);
-
-	return 0;
+	pr_info("\n=== output for debug===\n\n");
+	pr_info("bad: %d, total: %d\n", bad, total);
+	pr_info("bad rate: %f %%\n", (double)bad / (double)total * 100);
+	pr_info("histogram of events caused bad sequence\n");
+	for (i = 0; i < BROKEN_MAX; i++)
+		pr_info(" %10s: %d\n", name[i], bad_hist[i]);
 }
 
 /* TODO: various way to print, coloring, nano or milli sec */
@@ -634,26 +745,30 @@
 {
 	struct lock_stat *st;
 	char cut_name[20];
+	int bad, total;
 
-	printf("%18s ", "ID");
-	printf("%20s ", "Name");
-	printf("%10s ", "acquired");
-	printf("%10s ", "contended");
+	pr_info("%20s ", "Name");
+	pr_info("%10s ", "acquired");
+	pr_info("%10s ", "contended");
 
-	printf("%15s ", "total wait (ns)");
-	printf("%15s ", "max wait (ns)");
-	printf("%15s ", "min wait (ns)");
+	pr_info("%15s ", "total wait (ns)");
+	pr_info("%15s ", "max wait (ns)");
+	pr_info("%15s ", "min wait (ns)");
 
-	printf("\n\n");
+	pr_info("\n\n");
 
+	bad = total = 0;
 	while ((st = pop_from_result())) {
+		total++;
+		if (st->discard) {
+			bad++;
+			continue;
+		}
 		bzero(cut_name, 20);
 
-		printf("%p ", st->addr);
-
 		if (strlen(st->name) < 16) {
 			/* output raw name */
-			printf("%20s ", st->name);
+			pr_info("%20s ", st->name);
 		} else {
 			strncpy(cut_name, st->name, 16);
 			cut_name[16] = '.';
@@ -661,18 +776,39 @@
 			cut_name[18] = '.';
 			cut_name[19] = '\0';
 			/* cut off name for saving output style */
-			printf("%20s ", cut_name);
+			pr_info("%20s ", cut_name);
 		}
 
-		printf("%10u ", st->nr_acquired);
-		printf("%10u ", st->nr_contended);
+		pr_info("%10u ", st->nr_acquired);
+		pr_info("%10u ", st->nr_contended);
 
-		printf("%15llu ", st->wait_time_total);
-		printf("%15llu ", st->wait_time_max);
-		printf("%15llu ", st->wait_time_min == ULLONG_MAX ?
+		pr_info("%15llu ", st->wait_time_total);
+		pr_info("%15llu ", st->wait_time_max);
+		pr_info("%15llu ", st->wait_time_min == ULLONG_MAX ?
 		       0 : st->wait_time_min);
-		printf("\n");
+		pr_info("\n");
 	}
+
+	print_bad_events(bad, total);
+}
+
+static bool info_threads, info_map;
+
+static void dump_threads(void)
+{
+	struct thread_stat *st;
+	struct rb_node *node;
+	struct thread *t;
+
+	pr_info("%10s: comm\n", "Thread ID");
+
+	node = rb_first(&thread_stats);
+	while (node) {
+		st = container_of(node, struct thread_stat, rb);
+		t = perf_session__findnew(session, st->tid);
+		pr_info("%10d: %s\n", st->tid, t->comm);
+		node = rb_next(node);
+	};
 }
 
 static void dump_map(void)
@@ -680,23 +816,53 @@
 	unsigned int i;
 	struct lock_stat *st;
 
+	pr_info("Address of instance: name of class\n");
 	for (i = 0; i < LOCKHASH_SIZE; i++) {
 		list_for_each_entry(st, &lockhash_table[i], hash_entry) {
-			printf("%p: %s\n", st->addr, st->name);
+			pr_info(" %p: %s\n", st->addr, st->name);
 		}
 	}
 }
 
+static void dump_info(void)
+{
+	if (info_threads)
+		dump_threads();
+	else if (info_map)
+		dump_map();
+	else
+		die("Unknown type of information\n");
+}
+
+static int process_sample_event(event_t *self, struct perf_session *s)
+{
+	struct sample_data data;
+	struct thread *thread;
+
+	bzero(&data, sizeof(data));
+	event__parse_sample(self, s->sample_type, &data);
+
+	thread = perf_session__findnew(s, data.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing %d event, skipping it.\n",
+			self->header.type);
+		return -1;
+	}
+
+	process_raw_event(data.raw_data, data.cpu, data.time, thread);
+
+	return 0;
+}
+
 static struct perf_event_ops eops = {
 	.sample			= process_sample_event,
 	.comm			= event__process_comm,
+	.ordered_samples	= true,
 };
 
-static struct perf_session *session;
-
 static int read_events(void)
 {
-	session = perf_session__new(input_name, O_RDONLY, 0);
+	session = perf_session__new(input_name, O_RDONLY, 0, false);
 	if (!session)
 		die("Initializing perf session failed\n");
 
@@ -720,7 +886,6 @@
 	setup_pager();
 	select_key();
 	read_events();
-	flush_raw_event_queue(ULLONG_MAX);
 	sort_result();
 	print_result();
 }
@@ -737,6 +902,19 @@
 	OPT_END()
 };
 
+static const char * const info_usage[] = {
+	"perf lock info [<options>]",
+	NULL
+};
+
+static const struct option info_options[] = {
+	OPT_BOOLEAN('t', "threads", &info_threads,
+		    "dump thread list in perf.data"),
+	OPT_BOOLEAN('m', "map", &info_map,
+		    "map of lock instances (name:address table)"),
+	OPT_END()
+};
+
 static const char * const lock_usage[] = {
 	"perf lock [<options>] {record|trace|report}",
 	NULL
@@ -744,14 +922,13 @@
 
 static const struct option lock_options[] = {
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
-	OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"),
+	OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"),
 	OPT_END()
 };
 
 static const char *record_args[] = {
 	"record",
-	"-a",
 	"-R",
 	"-f",
 	"-m", "1024",
@@ -808,12 +985,18 @@
 	} else if (!strcmp(argv[0], "trace")) {
 		/* Aliased to 'perf trace' */
 		return cmd_trace(argc, argv, prefix);
-	} else if (!strcmp(argv[0], "map")) {
+	} else if (!strcmp(argv[0], "info")) {
+		if (argc) {
+			argc = parse_options(argc, argv,
+					     info_options, info_usage, 0);
+			if (argc)
+				usage_with_options(info_usage, info_options);
+		}
 		/* recycling report_lock_ops */
 		trace_handler = &report_lock_ops;
 		setup_pager();
 		read_events();
-		dump_map();
+		dump_info();
 	} else {
 		usage_with_options(lock_usage, lock_options);
 	}

tools/perf/builtin-probe.c

diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 152d6c9..61c6d70 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -36,13 +36,10 @@
 #include "builtin.h"
 #include "util/util.h"
 #include "util/strlist.h"
-#include "util/event.h"
+#include "util/symbol.h"
 #include "util/debug.h"
 #include "util/debugfs.h"
-#include "util/symbol.h"
-#include "util/thread.h"
 #include "util/parse-options.h"
-#include "util/parse-events.h"	/* For debugfs_path */
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
 
@@ -50,103 +47,84 @@
 
 /* Session management structure */
 static struct {
-	bool need_dwarf;
 	bool list_events;
 	bool force_add;
 	bool show_lines;
-	int nr_probe;
-	struct probe_point probes[MAX_PROBES];
+	int nevents;
+	struct perf_probe_event events[MAX_PROBES];
 	struct strlist *dellist;
-	struct map_groups kmap_groups;
-	struct map *kmaps[MAP__NR_TYPES];
 	struct line_range line_range;
-} session;
+	int max_probe_points;
+} params;
 
 
 /* Parse an event definition. Note that any error must die. */
-static void parse_probe_event(const char *str)
+static int parse_probe_event(const char *str)
 {
-	struct probe_point *pp = &session.probes[session.nr_probe];
+	struct perf_probe_event *pev = &params.events[params.nevents];
+	int ret;
 
-	pr_debug("probe-definition(%d): %s\n", session.nr_probe, str);
-	if (++session.nr_probe == MAX_PROBES)
+	pr_debug("probe-definition(%d): %s\n", params.nevents, str);
+	if (++params.nevents == MAX_PROBES)
 		die("Too many probes (> %d) are specified.", MAX_PROBES);
 
-	/* Parse perf-probe event into probe_point */
-	parse_perf_probe_event(str, pp, &session.need_dwarf);
+	/* Parse a perf-probe command into event */
+	ret = parse_perf_probe_command(str, pev);
+	pr_debug("%d arguments\n", pev->nargs);
 
-	pr_debug("%d arguments\n", pp->nr_args);
+	return ret;
 }
 
-static void parse_probe_event_argv(int argc, const char **argv)
+static int parse_probe_event_argv(int argc, const char **argv)
 {
-	int i, len;
+	int i, len, ret;
 	char *buf;
 
 	/* Bind up rest arguments */
 	len = 0;
 	for (i = 0; i < argc; i++)
 		len += strlen(argv[i]) + 1;
-	buf = zalloc(len + 1);
-	if (!buf)
-		die("Failed to allocate memory for binding arguments.");
+	buf = xzalloc(len + 1);
 	len = 0;
 	for (i = 0; i < argc; i++)
 		len += sprintf(&buf[len], "%s ", argv[i]);
-	parse_probe_event(buf);
+	ret = parse_probe_event(buf);
 	free(buf);
+	return ret;
 }
 
 static int opt_add_probe_event(const struct option *opt __used,
 			      const char *str, int unset __used)
 {
 	if (str)
-		parse_probe_event(str);
-	return 0;
+		return parse_probe_event(str);
+	else
+		return 0;
 }
 
 static int opt_del_probe_event(const struct option *opt __used,
 			       const char *str, int unset __used)
 {
 	if (str) {
-		if (!session.dellist)
-			session.dellist = strlist__new(true, NULL);
-		strlist__add(session.dellist, str);
+		if (!params.dellist)
+			params.dellist = strlist__new(true, NULL);
+		strlist__add(params.dellist, str);
 	}
 	return 0;
 }
 
-/* Currently just checking function name from symbol map */
-static void evaluate_probe_point(struct probe_point *pp)
-{
-	struct symbol *sym;
-	sym = map__find_symbol_by_name(session.kmaps[MAP__FUNCTION],
-				       pp->function, NULL);
-	if (!sym)
-		die("Kernel symbol \'%s\' not found - probe not added.",
-		    pp->function);
-}
-
-#ifndef NO_DWARF_SUPPORT
-static int open_vmlinux(void)
-{
-	if (map__load(session.kmaps[MAP__FUNCTION], NULL) < 0) {
-		pr_debug("Failed to load kernel map.\n");
-		return -EINVAL;
-	}
-	pr_debug("Try to open %s\n",
-		 session.kmaps[MAP__FUNCTION]->dso->long_name);
-	return open(session.kmaps[MAP__FUNCTION]->dso->long_name, O_RDONLY);
-}
-
+#ifdef DWARF_SUPPORT
 static int opt_show_lines(const struct option *opt __used,
 			  const char *str, int unset __used)
 {
+	int ret = 0;
+
 	if (str)
-		parse_line_range_desc(str, &session.line_range);
-	INIT_LIST_HEAD(&session.line_range.line_list);
-	session.show_lines = true;
-	return 0;
+		ret = parse_line_range_desc(str, &params.line_range);
+	INIT_LIST_HEAD(&params.line_range.line_list);
+	params.show_lines = true;
+
+	return ret;
 }
 #endif
 
@@ -155,29 +133,25 @@
 	"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
 	"perf probe [<options>] --del '[GROUP:]EVENT' ...",
 	"perf probe --list",
-#ifndef NO_DWARF_SUPPORT
+#ifdef DWARF_SUPPORT
 	"perf probe --line 'LINEDESC'",
 #endif
 	NULL
 };
 
 static const struct option options[] = {
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show parsed arguments, etc)"),
-#ifndef NO_DWARF_SUPPORT
-	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
-		   "file", "vmlinux pathname"),
-#endif
-	OPT_BOOLEAN('l', "list", &session.list_events,
+	OPT_BOOLEAN('l', "list", &params.list_events,
 		    "list up current probe events"),
 	OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
 		opt_del_probe_event),
 	OPT_CALLBACK('a', "add", NULL,
-#ifdef NO_DWARF_SUPPORT
-		"[EVENT=]FUNC[+OFF|%return] [ARG ...]",
-#else
+#ifdef DWARF_SUPPORT
 		"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
-		" [ARG ...]",
+		" [[NAME=]ARG ...]",
+#else
+		"[EVENT=]FUNC[+OFF|%return] [[NAME=]ARG ...]",
 #endif
 		"probe point definition, where\n"
 		"\t\tGROUP:\tGroup name (optional)\n"
@@ -185,51 +159,35 @@
 		"\t\tFUNC:\tFunction name\n"
 		"\t\tOFF:\tOffset from function entry (in byte)\n"
 		"\t\t%return:\tPut the probe at function return\n"
-#ifdef NO_DWARF_SUPPORT
-		"\t\tARG:\tProbe argument (only \n"
-#else
+#ifdef DWARF_SUPPORT
 		"\t\tSRC:\tSource code path\n"
 		"\t\tRL:\tRelative line number from function entry.\n"
 		"\t\tAL:\tAbsolute line number in file.\n"
 		"\t\tPT:\tLazy expression of line code.\n"
 		"\t\tARG:\tProbe argument (local variable name or\n"
-#endif
 		"\t\t\tkprobe-tracer argument format.)\n",
-		opt_add_probe_event),
-	OPT_BOOLEAN('f', "force", &session.force_add, "forcibly add events"
-		    " with existing name"),
-#ifndef NO_DWARF_SUPPORT
-	OPT_CALLBACK('L', "line", NULL,
-		     "FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]",
-		     "Show source code lines.", opt_show_lines),
+#else
+		"\t\tARG:\tProbe argument (kprobe-tracer argument format.)\n",
 #endif
+		opt_add_probe_event),
+	OPT_BOOLEAN('f', "force", &params.force_add, "forcibly add events"
+		    " with existing name"),
+#ifdef DWARF_SUPPORT
+	OPT_CALLBACK('L', "line", NULL,
+		     "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]",
+		     "Show source code lines.", opt_show_lines),
+	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
+		   "file", "vmlinux pathname"),
+#endif
+	OPT__DRY_RUN(&probe_event_dry_run),
+	OPT_INTEGER('\0', "max-probes", &params.max_probe_points,
+		 "Set how many probe points can be found for a probe."),
 	OPT_END()
 };
 
-/* Initialize symbol maps for vmlinux */
-static void init_vmlinux(void)
-{
-	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);
-	if (symbol__init() < 0)
-		die("Failed to init symbol map.");
-
-	map_groups__init(&session.kmap_groups);
-	if (map_groups__create_kernel_maps(&session.kmap_groups,
-					   session.kmaps) < 0)
-		die("Failed to create kernel maps.");
-}
-
 int cmd_probe(int argc, const char **argv, const char *prefix __used)
 {
-	int i, ret;
-#ifndef NO_DWARF_SUPPORT
-	int fd;
-#endif
-	struct probe_point *pp;
+	int ret;
 
 	argc = parse_options(argc, argv, options, probe_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
@@ -238,123 +196,69 @@
 			pr_warning("  Error: '-' is not supported.\n");
 			usage_with_options(probe_usage, options);
 		}
-		parse_probe_event_argv(argc, argv);
+		ret = parse_probe_event_argv(argc, argv);
+		if (ret < 0) {
+			pr_err("  Error: Parse Error.  (%d)\n", ret);
+			return ret;
+		}
 	}
 
-	if ((!session.nr_probe && !session.dellist && !session.list_events &&
-	     !session.show_lines))
+	if (params.max_probe_points == 0)
+		params.max_probe_points = MAX_PROBES;
+
+	if ((!params.nevents && !params.dellist && !params.list_events &&
+	     !params.show_lines))
 		usage_with_options(probe_usage, options);
 
-	if (debugfs_valid_mountpoint(debugfs_path) < 0)
-		die("Failed to find debugfs path.");
-
-	if (session.list_events) {
-		if (session.nr_probe != 0 || session.dellist) {
-			pr_warning("  Error: Don't use --list with"
-				   " --add/--del.\n");
+	if (params.list_events) {
+		if (params.nevents != 0 || params.dellist) {
+			pr_err("  Error: Don't use --list with --add/--del.\n");
 			usage_with_options(probe_usage, options);
 		}
-		if (session.show_lines) {
-			pr_warning("  Error: Don't use --list with --line.\n");
+		if (params.show_lines) {
+			pr_err("  Error: Don't use --list with --line.\n");
 			usage_with_options(probe_usage, options);
 		}
-		show_perf_probe_events();
-		return 0;
+		ret = show_perf_probe_events();
+		if (ret < 0)
+			pr_err("  Error: Failed to show event list. (%d)\n",
+			       ret);
+		return ret;
 	}
 
-#ifndef NO_DWARF_SUPPORT
-	if (session.show_lines) {
-		if (session.nr_probe != 0 || session.dellist) {
+#ifdef DWARF_SUPPORT
+	if (params.show_lines) {
+		if (params.nevents != 0 || params.dellist) {
 			pr_warning("  Error: Don't use --line with"
 				   " --add/--del.\n");
 			usage_with_options(probe_usage, options);
 		}
-		init_vmlinux();
-		fd = open_vmlinux();
-		if (fd < 0)
-			die("Could not open debuginfo file.");
-		ret = find_line_range(fd, &session.line_range);
-		if (ret <= 0)
-			die("Source line is not found.\n");
-		close(fd);
-		show_line_range(&session.line_range);
-		return 0;
+
+		ret = show_line_range(&params.line_range);
+		if (ret < 0)
+			pr_err("  Error: Failed to show lines. (%d)\n", ret);
+		return ret;
 	}
 #endif
 
-	if (session.dellist) {
-		del_trace_kprobe_events(session.dellist);
-		strlist__delete(session.dellist);
-		if (session.nr_probe == 0)
-			return 0;
-	}
-
-	/* Add probes */
-	init_vmlinux();
-
-	if (session.need_dwarf)
-#ifdef NO_DWARF_SUPPORT
-		die("Debuginfo-analysis is not supported");
-#else	/* !NO_DWARF_SUPPORT */
-		pr_debug("Some probes require debuginfo.\n");
-
-	fd = open_vmlinux();
-	if (fd < 0) {
-		if (session.need_dwarf)
-			die("Could not open debuginfo file.");
-
-		pr_debug("Could not open vmlinux/module file."
-			 " Try to use symbols.\n");
-		goto end_dwarf;
-	}
-
-	/* Searching probe points */
-	for (i = 0; i < session.nr_probe; i++) {
-		pp = &session.probes[i];
-		if (pp->found)
-			continue;
-
-		lseek(fd, SEEK_SET, 0);
-		ret = find_probe_point(fd, pp);
-		if (ret > 0)
-			continue;
-		if (ret == 0) {	/* No error but failed to find probe point. */
-			synthesize_perf_probe_point(pp);
-			die("Probe point '%s' not found. - probe not added.",
-			    pp->probes[0]);
+	if (params.dellist) {
+		ret = del_perf_probe_events(params.dellist);
+		strlist__delete(params.dellist);
+		if (ret < 0) {
+			pr_err("  Error: Failed to delete events. (%d)\n", ret);
+			return ret;
 		}
-		/* Error path */
-		if (session.need_dwarf) {
-			if (ret == -ENOENT)
-				pr_warning("No dwarf info found in the vmlinux - please rebuild with CONFIG_DEBUG_INFO=y.\n");
-			die("Could not analyze debuginfo.");
+	}
+
+	if (params.nevents) {
+		ret = add_perf_probe_events(params.events, params.nevents,
+					    params.force_add,
+					    params.max_probe_points);
+		if (ret < 0) {
+			pr_err("  Error: Failed to add events. (%d)\n", ret);
+			return ret;
 		}
-		pr_debug("An error occurred in debuginfo analysis."
-			 " Try to use symbols.\n");
-		break;
 	}
-	close(fd);
-
-end_dwarf:
-#endif /* !NO_DWARF_SUPPORT */
-
-	/* Synthesize probes without dwarf */
-	for (i = 0; i < session.nr_probe; i++) {
-		pp = &session.probes[i];
-		if (pp->found)	/* This probe is already found. */
-			continue;
-
-		evaluate_probe_point(pp);
-		ret = synthesize_trace_kprobe_event(pp);
-		if (ret == -E2BIG)
-			die("probe point definition becomes too long.");
-		else if (ret < 0)
-			die("Failed to synthesize a probe point.");
-	}
-
-	/* Settng up probe points */
-	add_trace_kprobe_events(session.probes, session.nr_probe,
-				session.force_add);
 	return 0;
 }
 

tools/perf/builtin-record.c

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3b8b638..cb46c7d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -15,7 +15,6 @@
 #include "util/util.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"
-#include "util/string.h"
 
 #include "util/header.h"
 #include "util/event.h"
@@ -27,31 +26,41 @@
 #include <unistd.h>
 #include <sched.h>
 
-static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
+enum write_mode_t {
+	WRITE_FORCE,
+	WRITE_APPEND
+};
 
-static long			default_interval		=      0;
+static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
+
+static u64			user_interval			= ULLONG_MAX;
+static u64			default_interval		=      0;
 
 static int			nr_cpus				=      0;
 static unsigned int		page_size;
 static unsigned int		mmap_pages			=    128;
+static unsigned int		user_freq 			= UINT_MAX;
 static int			freq				=   1000;
 static int			output;
+static int			pipe_output			=      0;
 static const char		*output_name			= "perf.data";
 static int			group				=      0;
-static unsigned int		realtime_prio			=      0;
-static int			raw_samples			=      0;
-static int			system_wide			=      0;
+static int			realtime_prio			=      0;
+static bool			raw_samples			=  false;
+static bool			system_wide			=  false;
 static int			profile_cpu			=     -1;
 static pid_t			target_pid			=     -1;
+static pid_t			target_tid			=     -1;
+static pid_t			*all_tids			=      NULL;
+static int			thread_num			=      0;
 static pid_t			child_pid			=     -1;
-static int			inherit				=      1;
-static int			force				=      0;
-static int			append_file			=      0;
-static int			call_graph			=      0;
-static int			inherit_stat			=      0;
-static int			no_samples			=      0;
-static int			sample_address			=      0;
-static int			multiplex			=      0;
+static bool			no_inherit			=  false;
+static enum write_mode_t	write_mode			= WRITE_FORCE;
+static bool			call_graph			=  false;
+static bool			inherit_stat			=  false;
+static bool			no_samples			=  false;
+static bool			sample_address			=  false;
+static bool			multiplex			=  false;
 static int			multiplex_fd			=     -1;
 
 static long			samples				=      0;
@@ -60,7 +69,7 @@
 
 static u64			bytes_written			=      0;
 
-static struct pollfd		event_array[MAX_NR_CPUS * MAX_COUNTERS];
+static struct pollfd		*event_array;
 
 static int			nr_poll				=      0;
 static int			nr_cpu				=      0;
@@ -77,7 +86,7 @@
 	unsigned int		prev;
 };
 
-static struct mmap_data		mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
+static struct mmap_data		*mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
 
 static unsigned long mmap_read_head(struct mmap_data *md)
 {
@@ -101,6 +110,11 @@
 	pc->data_tail = tail;
 }
 
+static void advance_output(size_t size)
+{
+	bytes_written += size;
+}
+
 static void write_output(void *buf, size_t size)
 {
 	while (size) {
@@ -225,12 +239,13 @@
 	return h_attr;
 }
 
-static void create_counter(int counter, int cpu, pid_t pid)
+static void create_counter(int counter, int cpu)
 {
 	char *filter = filters[counter];
 	struct perf_event_attr *attr = attrs + counter;
 	struct perf_header_attr *h_attr;
 	int track = !counter; /* only the first counter needs these */
+	int thread_index;
 	int ret;
 	struct {
 		u64 count;
@@ -248,10 +263,19 @@
 	if (nr_counters > 1)
 		attr->sample_type |= PERF_SAMPLE_ID;
 
-	if (freq) {
-		attr->sample_type	|= PERF_SAMPLE_PERIOD;
-		attr->freq		= 1;
-		attr->sample_freq	= freq;
+	/*
+	 * We default some events to a 1 default interval. But keep
+	 * it a weak assumption overridable by the user.
+	 */
+	if (!attr->sample_period || (user_freq != UINT_MAX &&
+				     user_interval != ULLONG_MAX)) {
+		if (freq) {
+			attr->sample_type	|= PERF_SAMPLE_PERIOD;
+			attr->freq		= 1;
+			attr->sample_freq	= freq;
+		} else {
+			attr->sample_period = default_interval;
+		}
 	}
 
 	if (no_samples)
@@ -274,119 +298,130 @@
 
 	attr->mmap		= track;
 	attr->comm		= track;
-	attr->inherit		= inherit;
-	attr->disabled		= 1;
+	attr->inherit		= !no_inherit;
+	if (target_pid == -1 && target_tid == -1 && !system_wide) {
+		attr->disabled = 1;
+		attr->enable_on_exec = 1;
+	}
 
+	for (thread_index = 0; thread_index < thread_num; thread_index++) {
 try_again:
-	fd[nr_cpu][counter] = sys_perf_event_open(attr, pid, cpu, group_fd, 0);
+		fd[nr_cpu][counter][thread_index] = sys_perf_event_open(attr,
+				all_tids[thread_index], cpu, group_fd, 0);
 
-	if (fd[nr_cpu][counter] < 0) {
-		int err = errno;
+		if (fd[nr_cpu][counter][thread_index] < 0) {
+			int err = errno;
 
-		if (err == EPERM || err == EACCES)
-			die("Permission error - are you root?\n");
-		else if (err ==  ENODEV && profile_cpu != -1)
-			die("No such device - did you specify an out-of-range profile CPU?\n");
+			if (err == EPERM || err == EACCES)
+				die("Permission error - are you root?\n"
+					"\t Consider tweaking"
+					" /proc/sys/kernel/perf_event_paranoid.\n");
+			else if (err ==  ENODEV && profile_cpu != -1) {
+				die("No such device - did you specify"
+					" an out-of-range profile CPU?\n");
+			}
 
-		/*
-		 * If it's cycles then fall back to hrtimer
-		 * based cpu-clock-tick sw counter, which
-		 * is always available even if no PMU support:
-		 */
-		if (attr->type == PERF_TYPE_HARDWARE
-			&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+			/*
+			 * If it's cycles then fall back to hrtimer
+			 * based cpu-clock-tick sw counter, which
+			 * is always available even if no PMU support:
+			 */
+			if (attr->type == PERF_TYPE_HARDWARE
+					&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
 
-			if (verbose)
-				warning(" ... trying to fall back to cpu-clock-ticks\n");
-			attr->type = PERF_TYPE_SOFTWARE;
-			attr->config = PERF_COUNT_SW_CPU_CLOCK;
-			goto try_again;
-		}
-		printf("\n");
-		error("perfcounter syscall returned with %d (%s)\n",
-			fd[nr_cpu][counter], strerror(err));
+				if (verbose)
+					warning(" ... trying to fall back to cpu-clock-ticks\n");
+				attr->type = PERF_TYPE_SOFTWARE;
+				attr->config = PERF_COUNT_SW_CPU_CLOCK;
+				goto try_again;
+			}
+			printf("\n");
+			error("perfcounter syscall returned with %d (%s)\n",
+					fd[nr_cpu][counter][thread_index], strerror(err));
 
 #if defined(__i386__) || defined(__x86_64__)
-		if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
-			die("No hardware sampling interrupt available. No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.\n");
+			if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
+				die("No hardware sampling interrupt available."
+				    " No APIC? If so then you can boot the kernel"
+				    " with the \"lapic\" boot parameter to"
+				    " force-enable it.\n");
 #endif
 
-		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-		exit(-1);
-	}
-
-	h_attr = get_header_attr(attr, counter);
-	if (h_attr == NULL)
-		die("nomem\n");
-
-	if (!file_new) {
-		if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
-			fprintf(stderr, "incompatible append\n");
+			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
 			exit(-1);
 		}
-	}
 
-	if (read(fd[nr_cpu][counter], &read_data, sizeof(read_data)) == -1) {
-		perror("Unable to read perf file descriptor\n");
-		exit(-1);
-	}
+		h_attr = get_header_attr(attr, counter);
+		if (h_attr == NULL)
+			die("nomem\n");
 
-	if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
-		pr_warning("Not enough memory to add id\n");
-		exit(-1);
-	}
+		if (!file_new) {
+			if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
+				fprintf(stderr, "incompatible append\n");
+				exit(-1);
+			}
+		}
 
-	assert(fd[nr_cpu][counter] >= 0);
-	fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK);
-
-	/*
-	 * First counter acts as the group leader:
-	 */
-	if (group && group_fd == -1)
-		group_fd = fd[nr_cpu][counter];
-	if (multiplex && multiplex_fd == -1)
-		multiplex_fd = fd[nr_cpu][counter];
-
-	if (multiplex && fd[nr_cpu][counter] != multiplex_fd) {
-
-		ret = ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd);
-		assert(ret != -1);
-	} else {
-		event_array[nr_poll].fd = fd[nr_cpu][counter];
-		event_array[nr_poll].events = POLLIN;
-		nr_poll++;
-
-		mmap_array[nr_cpu][counter].counter = counter;
-		mmap_array[nr_cpu][counter].prev = 0;
-		mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1;
-		mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
-				PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter], 0);
-		if (mmap_array[nr_cpu][counter].base == MAP_FAILED) {
-			error("failed to mmap with %d (%s)\n", errno, strerror(errno));
+		if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) {
+			perror("Unable to read perf file descriptor\n");
 			exit(-1);
 		}
-	}
 
-	if (filter != NULL) {
-		ret = ioctl(fd[nr_cpu][counter],
-			    PERF_EVENT_IOC_SET_FILTER, filter);
-		if (ret) {
-			error("failed to set filter with %d (%s)\n", errno,
-			      strerror(errno));
+		if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
+			pr_warning("Not enough memory to add id\n");
 			exit(-1);
 		}
-	}
 
-	ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_ENABLE);
+		assert(fd[nr_cpu][counter][thread_index] >= 0);
+		fcntl(fd[nr_cpu][counter][thread_index], F_SETFL, O_NONBLOCK);
+
+		/*
+		 * First counter acts as the group leader:
+		 */
+		if (group && group_fd == -1)
+			group_fd = fd[nr_cpu][counter][thread_index];
+		if (multiplex && multiplex_fd == -1)
+			multiplex_fd = fd[nr_cpu][counter][thread_index];
+
+		if (multiplex && fd[nr_cpu][counter][thread_index] != multiplex_fd) {
+
+			ret = ioctl(fd[nr_cpu][counter][thread_index], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd);
+			assert(ret != -1);
+		} else {
+			event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index];
+			event_array[nr_poll].events = POLLIN;
+			nr_poll++;
+
+			mmap_array[nr_cpu][counter][thread_index].counter = counter;
+			mmap_array[nr_cpu][counter][thread_index].prev = 0;
+			mmap_array[nr_cpu][counter][thread_index].mask = mmap_pages*page_size - 1;
+			mmap_array[nr_cpu][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
+				PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter][thread_index], 0);
+			if (mmap_array[nr_cpu][counter][thread_index].base == MAP_FAILED) {
+				error("failed to mmap with %d (%s)\n", errno, strerror(errno));
+				exit(-1);
+			}
+		}
+
+		if (filter != NULL) {
+			ret = ioctl(fd[nr_cpu][counter][thread_index],
+					PERF_EVENT_IOC_SET_FILTER, filter);
+			if (ret) {
+				error("failed to set filter with %d (%s)\n", errno,
+						strerror(errno));
+				exit(-1);
+			}
+		}
+	}
 }
 
-static void open_counters(int cpu, pid_t pid)
+static void open_counters(int cpu)
 {
 	int counter;
 
 	group_fd = -1;
 	for (counter = 0; counter < nr_counters; counter++)
-		create_counter(counter, cpu, pid);
+		create_counter(counter, cpu);
 
 	nr_cpu++;
 }
@@ -406,10 +441,80 @@
 
 static void atexit_header(void)
 {
-	session->header.data_size += bytes_written;
+	if (!pipe_output) {
+		session->header.data_size += bytes_written;
 
-	process_buildids();
-	perf_header__write(&session->header, output, true);
+		process_buildids();
+		perf_header__write(&session->header, output, true);
+	}
+}
+
+static void event__synthesize_guest_os(struct machine *machine, void *data)
+{
+	int err;
+	char *guest_kallsyms;
+	char path[PATH_MAX];
+	struct perf_session *psession = data;
+
+	if (machine__is_host(machine))
+		return;
+
+	/*
+	 *As for guest kernel when processing subcommand record&report,
+	 *we arrange module mmap prior to guest kernel mmap and trigger
+	 *a preload dso because default guest module symbols are loaded
+	 *from guest kallsyms instead of /lib/modules/XXX/XXX. This
+	 *method is used to avoid symbol missing when the first addr is
+	 *in module instead of in guest kernel.
+	 */
+	err = event__synthesize_modules(process_synthesized_event,
+					psession, machine);
+	if (err < 0)
+		pr_err("Couldn't record guest kernel [%d]'s reference"
+		       " relocation symbol.\n", machine->pid);
+
+	if (machine__is_default_guest(machine))
+		guest_kallsyms = (char *) symbol_conf.default_guest_kallsyms;
+	else {
+		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+		guest_kallsyms = path;
+	}
+
+	/*
+	 * We use _stext for guest kernel because guest kernel's /proc/kallsyms
+	 * have no _text sometimes.
+	 */
+	err = event__synthesize_kernel_mmap(process_synthesized_event,
+					    psession, machine, "_text");
+	if (err < 0)
+		err = event__synthesize_kernel_mmap(process_synthesized_event,
+						    psession, machine, "_stext");
+	if (err < 0)
+		pr_err("Couldn't record guest kernel [%d]'s reference"
+		       " relocation symbol.\n", machine->pid);
+}
+
+static struct perf_event_header finished_round_event = {
+	.size = sizeof(struct perf_event_header),
+	.type = PERF_RECORD_FINISHED_ROUND,
+};
+
+static void mmap_read_all(void)
+{
+	int i, counter, thread;
+
+	for (i = 0; i < nr_cpu; i++) {
+		for (counter = 0; counter < nr_counters; counter++) {
+			for (thread = 0; thread < thread_num; thread++) {
+				if (mmap_array[i][counter][thread].base)
+					mmap_read(&mmap_array[i][counter][thread]);
+			}
+
+		}
+	}
+
+	if (perf_header__has_feat(&session->header, HEADER_TRACE_INFO))
+		write_output(&finished_round_event, sizeof(finished_round_event));
 }
 
 static int __cmd_record(int argc, const char **argv)
@@ -421,8 +526,9 @@
 	int err;
 	unsigned long waking = 0;
 	int child_ready_pipe[2], go_pipe[2];
-	const bool forks = target_pid == -1 && argc > 0;
+	const bool forks = argc > 0;
 	char buf;
+	struct machine *machine;
 
 	page_size = sysconf(_SC_PAGE_SIZE);
 
@@ -435,70 +541,63 @@
 		exit(-1);
 	}
 
-	if (!stat(output_name, &st) && st.st_size) {
-		if (!force) {
-			if (!append_file) {
-				pr_err("Error, output file %s exists, use -A "
-				       "to append or -f to overwrite.\n",
-				       output_name);
-				exit(-1);
-			}
-		} else {
+	if (!strcmp(output_name, "-"))
+		pipe_output = 1;
+	else if (!stat(output_name, &st) && st.st_size) {
+		if (write_mode == WRITE_FORCE) {
 			char oldname[PATH_MAX];
 			snprintf(oldname, sizeof(oldname), "%s.old",
 				 output_name);
 			unlink(oldname);
 			rename(output_name, oldname);
 		}
-	} else {
-		append_file = 0;
+	} else if (write_mode == WRITE_APPEND) {
+		write_mode = WRITE_FORCE;
 	}
 
 	flags = O_CREAT|O_RDWR;
-	if (append_file)
+	if (write_mode == WRITE_APPEND)
 		file_new = 0;
 	else
 		flags |= O_TRUNC;
 
-	output = open(output_name, flags, S_IRUSR|S_IWUSR);
+	if (pipe_output)
+		output = STDOUT_FILENO;
+	else
+		output = open(output_name, flags, S_IRUSR | S_IWUSR);
 	if (output < 0) {
 		perror("failed to create output file");
 		exit(-1);
 	}
 
-	session = perf_session__new(output_name, O_WRONLY, force);
+	session = perf_session__new(output_name, O_WRONLY,
+				    write_mode == WRITE_FORCE, false);
 	if (session == NULL) {
 		pr_err("Not enough memory for reading perf file header\n");
 		return -1;
 	}
 
 	if (!file_new) {
-		err = perf_header__read(&session->header, output);
+		err = perf_header__read(session, output);
 		if (err < 0)
 			return err;
 	}
 
-	if (raw_samples) {
+	if (have_tracepoints(attrs, nr_counters))
 		perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
-	} else {
-		for (i = 0; i < nr_counters; i++) {
-			if (attrs[i].sample_type & PERF_SAMPLE_RAW) {
-				perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
-				break;
-			}
-		}
-	}
 
 	atexit(atexit_header);
 
 	if (forks) {
-		pid = fork();
+		child_pid = fork();
 		if (pid < 0) {
 			perror("failed to fork");
 			exit(-1);
 		}
 
-		if (!pid) {
+		if (!child_pid) {
+			if (pipe_output)
+				dup2(2, 1);
 			close(child_ready_pipe[0]);
 			close(go_pipe[1]);
 			fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
@@ -527,10 +626,8 @@
 			exit(-1);
 		}
 
-		child_pid = pid;
-
-		if (!system_wide)
-			target_pid = pid;
+		if (!system_wide && target_tid == -1 && target_pid == -1)
+			all_tids[0] = child_pid;
 
 		close(child_ready_pipe[1]);
 		close(go_pipe[0]);
@@ -544,16 +641,19 @@
 		close(child_ready_pipe[0]);
 	}
 
-
-	if ((!system_wide && !inherit) || profile_cpu != -1) {
-		open_counters(profile_cpu, target_pid);
+	if ((!system_wide && no_inherit) || profile_cpu != -1) {
+		open_counters(profile_cpu);
 	} else {
 		nr_cpus = read_cpu_map();
 		for (i = 0; i < nr_cpus; i++)
-			open_counters(cpumap[i], target_pid);
+			open_counters(cpumap[i]);
 	}
 
-	if (file_new) {
+	if (pipe_output) {
+		err = perf_header__write_pipe(output);
+		if (err < 0)
+			return err;
+	} else if (file_new) {
 		err = perf_header__write(&session->header, output, false);
 		if (err < 0)
 			return err;
@@ -561,21 +661,70 @@
 
 	post_processing_offset = lseek(output, 0, SEEK_CUR);
 
+	if (pipe_output) {
+		err = event__synthesize_attrs(&session->header,
+					      process_synthesized_event,
+					      session);
+		if (err < 0) {
+			pr_err("Couldn't synthesize attrs.\n");
+			return err;
+		}
+
+		err = event__synthesize_event_types(process_synthesized_event,
+						    session);
+		if (err < 0) {
+			pr_err("Couldn't synthesize event_types.\n");
+			return err;
+		}
+
+		if (have_tracepoints(attrs, nr_counters)) {
+			/*
+			 * FIXME err <= 0 here actually means that
+			 * there were no tracepoints so its not really
+			 * an error, just that we don't need to
+			 * synthesize anything.  We really have to
+			 * return this more properly and also
+			 * propagate errors that now are calling die()
+			 */
+			err = event__synthesize_tracing_data(output, attrs,
+							     nr_counters,
+							     process_synthesized_event,
+							     session);
+			if (err <= 0) {
+				pr_err("Couldn't record tracing data.\n");
+				return err;
+			}
+			advance_output(err);
+		}
+	}
+
+	machine = perf_session__find_host_machine(session);
+	if (!machine) {
+		pr_err("Couldn't find native kernel information.\n");
+		return -1;
+	}
+
 	err = event__synthesize_kernel_mmap(process_synthesized_event,
-					    session, "_text");
+					    session, machine, "_text");
+	if (err < 0)
+		err = event__synthesize_kernel_mmap(process_synthesized_event,
+						    session, machine, "_stext");
 	if (err < 0) {
 		pr_err("Couldn't record kernel reference relocation symbol.\n");
 		return err;
 	}
 
-	err = event__synthesize_modules(process_synthesized_event, session);
+	err = event__synthesize_modules(process_synthesized_event,
+					session, machine);
 	if (err < 0) {
 		pr_err("Couldn't record kernel reference relocation symbol.\n");
 		return err;
 	}
+	if (perf_guest)
+		perf_session__process_machines(session, event__synthesize_guest_os);
 
 	if (!system_wide && profile_cpu == -1)
-		event__synthesize_thread(target_pid, process_synthesized_event,
+		event__synthesize_thread(target_tid, process_synthesized_event,
 					 session);
 	else
 		event__synthesize_threads(process_synthesized_event, session);
@@ -598,13 +747,9 @@
 
 	for (;;) {
 		int hits = samples;
+		int thread;
 
-		for (i = 0; i < nr_cpu; i++) {
-			for (counter = 0; counter < nr_counters; counter++) {
-				if (mmap_array[i][counter].base)
-					mmap_read(&mmap_array[i][counter]);
-			}
-		}
+		mmap_read_all();
 
 		if (hits == samples) {
 			if (done)
@@ -615,8 +760,15 @@
 
 		if (done) {
 			for (i = 0; i < nr_cpu; i++) {
-				for (counter = 0; counter < nr_counters; counter++)
-					ioctl(fd[i][counter], PERF_EVENT_IOC_DISABLE);
+				for (counter = 0;
+					counter < nr_counters;
+					counter++) {
+					for (thread = 0;
+						thread < thread_num;
+						thread++)
+						ioctl(fd[i][counter][thread],
+							PERF_EVENT_IOC_DISABLE);
+				}
 			}
 		}
 	}
@@ -641,6 +793,8 @@
 	NULL
 };
 
+static bool force, append_file;
+
 static const struct option options[] = {
 	OPT_CALLBACK('e', "event", NULL, "event",
 		     "event selector. use 'perf list' to list available events",
@@ -648,7 +802,9 @@
 	OPT_CALLBACK(0, "filter", NULL, "filter",
 		     "event filter", parse_filter),
 	OPT_INTEGER('p', "pid", &target_pid,
-		    "record events on existing pid"),
+		    "record events on existing process id"),
+	OPT_INTEGER('t', "tid", &target_tid,
+		    "record events on existing thread id"),
 	OPT_INTEGER('r', "realtime", &realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
 	OPT_BOOLEAN('R', "raw-samples", &raw_samples,
@@ -660,20 +816,17 @@
 	OPT_INTEGER('C', "profile_cpu", &profile_cpu,
 			    "CPU to profile on"),
 	OPT_BOOLEAN('f', "force", &force,
-			"overwrite existing data file"),
-	OPT_LONG('c', "count", &default_interval,
-		    "event period to sample"),
+			"overwrite existing data file (deprecated)"),
+	OPT_U64('c', "count", &user_interval, "event period to sample"),
 	OPT_STRING('o', "output", &output_name, "file",
 		    "output file name"),
-	OPT_BOOLEAN('i', "inherit", &inherit,
-		    "child tasks inherit counters"),
-	OPT_INTEGER('F', "freq", &freq,
-		    "profile at this frequency"),
-	OPT_INTEGER('m', "mmap-pages", &mmap_pages,
-		    "number of mmap data pages"),
+	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+		    "child tasks do not inherit counters"),
+	OPT_UINTEGER('F', "freq", &user_freq, "profile at this frequency"),
+	OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
 	OPT_BOOLEAN('g', "call-graph", &call_graph,
 		    "do call-graph (stack chain/backtrace) recording"),
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_BOOLEAN('s', "stat", &inherit_stat,
 		    "per thread counts"),
@@ -688,13 +841,24 @@
 
 int cmd_record(int argc, const char **argv, const char *prefix __used)
 {
-	int counter;
+	int i,j;
 
 	argc = parse_options(argc, argv, options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && target_pid == -1 && !system_wide && profile_cpu == -1)
+	if (!argc && target_pid == -1 && target_tid == -1 &&
+		!system_wide && profile_cpu == -1)
 		usage_with_options(record_usage, options);
 
+	if (force && append_file) {
+		fprintf(stderr, "Can't overwrite and append at the same time."
+				" You need to choose between -f and -A");
+		usage_with_options(record_usage, options);
+	} else if (append_file) {
+		write_mode = WRITE_APPEND;
+	} else {
+		write_mode = WRITE_FORCE;
+	}
+
 	symbol__init();
 
 	if (!nr_counters) {
@@ -703,6 +867,42 @@
 		attrs[0].config = PERF_COUNT_HW_CPU_CYCLES;
 	}
 
+	if (target_pid != -1) {
+		target_tid = target_pid;
+		thread_num = find_all_tid(target_pid, &all_tids);
+		if (thread_num <= 0) {
+			fprintf(stderr, "Can't find all threads of pid %d\n",
+					target_pid);
+			usage_with_options(record_usage, options);
+		}
+	} else {
+		all_tids=malloc(sizeof(pid_t));
+		if (!all_tids)
+			return -ENOMEM;
+
+		all_tids[0] = target_tid;
+		thread_num = 1;
+	}
+
+	for (i = 0; i < MAX_NR_CPUS; i++) {
+		for (j = 0; j < MAX_COUNTERS; j++) {
+			fd[i][j] = malloc(sizeof(int)*thread_num);
+			mmap_array[i][j] = zalloc(
+				sizeof(struct mmap_data)*thread_num);
+			if (!fd[i][j] || !mmap_array[i][j])
+				return -ENOMEM;
+		}
+	}
+	event_array = malloc(
+		sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
+	if (!event_array)
+		return -ENOMEM;
+
+	if (user_interval != ULLONG_MAX)
+		default_interval = user_interval;
+	if (user_freq != UINT_MAX)
+		freq = user_freq;
+
 	/*
 	 * User specified count overrides default frequency.
 	 */
@@ -715,12 +915,5 @@
 		exit(EXIT_FAILURE);
 	}
 
-	for (counter = 0; counter < nr_counters; counter++) {
-		if (attrs[counter].sample_period)
-			continue;
-
-		attrs[counter].sample_period = default_interval;
-	}
-
 	return __cmd_record(argc, argv);
 }

tools/perf/builtin-report.c

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f815de2..1d3c100 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -14,7 +14,6 @@
 #include "util/cache.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
-#include "util/string.h"
 #include "util/callchain.h"
 #include "util/strlist.h"
 #include "util/values.h"
@@ -33,28 +32,29 @@
 
 static char		const *input_name = "perf.data";
 
-static int		force;
+static bool		force;
 static bool		hide_unresolved;
 static bool		dont_use_callchains;
 
-static int		show_threads;
+static bool		show_threads;
 static struct perf_read_values	show_threads_values;
 
-static char		default_pretty_printing_style[] = "normal";
-static char		*pretty_printing_style = default_pretty_printing_style;
+static const char	default_pretty_printing_style[] = "normal";
+static const char	*pretty_printing_style = default_pretty_printing_style;
 
 static char		callchain_default_opt[] = "fractal,0.5";
 
-static struct event_stat_id *get_stats(struct perf_session *self,
-				       u64 event_stream, u32 type, u64 config)
+static struct hists *perf_session__hists_findnew(struct perf_session *self,
+						 u64 event_stream, u32 type,
+						 u64 config)
 {
-	struct rb_node **p = &self->stats_by_id.rb_node;
+	struct rb_node **p = &self->hists_tree.rb_node;
 	struct rb_node *parent = NULL;
-	struct event_stat_id *iter, *new;
+	struct hists *iter, *new;
 
 	while (*p != NULL) {
 		parent = *p;
-		iter = rb_entry(parent, struct event_stat_id, rb_node);
+		iter = rb_entry(parent, struct hists, rb_node);
 		if (iter->config == config)
 			return iter;
 
@@ -65,15 +65,15 @@
 			p = &(*p)->rb_left;
 	}
 
-	new = malloc(sizeof(struct event_stat_id));
+	new = malloc(sizeof(struct hists));
 	if (new == NULL)
 		return NULL;
-	memset(new, 0, sizeof(struct event_stat_id));
+	memset(new, 0, sizeof(struct hists));
 	new->event_stream = event_stream;
 	new->config = config;
 	new->type = type;
 	rb_link_node(&new->rb_node, parent, p);
-	rb_insert_color(&new->rb_node, &self->stats_by_id);
+	rb_insert_color(&new->rb_node, &self->hists_tree);
 	return new;
 }
 
@@ -81,70 +81,71 @@
 					struct addr_location *al,
 					struct sample_data *data)
 {
-	struct symbol **syms = NULL, *parent = NULL;
-	bool hit;
+	struct map_symbol *syms = NULL;
+	struct symbol *parent = NULL;
+	int err = -ENOMEM;
 	struct hist_entry *he;
-	struct event_stat_id *stats;
+	struct hists *hists;
 	struct perf_event_attr *attr;
 
-	if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain)
+	if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) {
 		syms = perf_session__resolve_callchain(self, al->thread,
 						       data->callchain, &parent);
+		if (syms == NULL)
+			return -ENOMEM;
+	}
 
 	attr = perf_header__find_attr(data->id, &self->header);
 	if (attr)
-		stats = get_stats(self, data->id, attr->type, attr->config);
+		hists = perf_session__hists_findnew(self, data->id, attr->type, attr->config);
 	else
-		stats = get_stats(self, data->id, 0, 0);
-	if (stats == NULL)
-		return -ENOMEM;
-	he = __perf_session__add_hist_entry(&stats->hists, al, parent,
-					    data->period, &hit);
+		hists = perf_session__hists_findnew(self, data->id, 0, 0);
+	if (hists == NULL)
+		goto out_free_syms;
+	he = __hists__add_entry(hists, al, parent, data->period);
 	if (he == NULL)
-		return -ENOMEM;
-
-	if (hit)
-		he->count += data->period;
-
+		goto out_free_syms;
+	err = 0;
 	if (symbol_conf.use_callchain) {
-		if (!hit)
-			callchain_init(&he->callchain);
-		append_chain(&he->callchain, data->callchain, syms);
-		free(syms);
+		err = append_chain(he->callchain, data->callchain, syms);
+		if (err)
+			goto out_free_syms;
 	}
-
-	return 0;
-}
-
-static int validate_chain(struct ip_callchain *chain, event_t *event)
-{
-	unsigned int chain_size;
-
-	chain_size = event->header.size;
-	chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
-
-	if (chain->nr*sizeof(u64) > chain_size)
-		return -1;
-
-	return 0;
+	/*
+	 * Only in the newt browser we are doing integrated annotation,
+	 * so we don't allocated the extra space needed because the stdio
+	 * code will not use it.
+	 */
+	if (use_browser)
+		err = hist_entry__inc_addr_samples(he, al->addr);
+out_free_syms:
+	free(syms);
+	return err;
 }
 
 static int add_event_total(struct perf_session *session,
 			   struct sample_data *data,
 			   struct perf_event_attr *attr)
 {
-	struct event_stat_id *stats;
+	struct hists *hists;
 
 	if (attr)
-		stats = get_stats(session, data->id, attr->type, attr->config);
+		hists = perf_session__hists_findnew(session, data->id,
+						    attr->type, attr->config);
 	else
-		stats = get_stats(session, data->id, 0, 0);
+		hists = perf_session__hists_findnew(session, data->id, 0, 0);
 
-	if (!stats)
+	if (!hists)
 		return -ENOMEM;
 
-	stats->stats.total += data->period;
-	session->events_stats.total += data->period;
+	hists->stats.total_period += data->period;
+	/*
+	 * FIXME: add_event_total should be moved from here to
+	 * perf_session__process_event so that the proper hist is passed to
+	 * the event_op methods.
+	 */
+	hists__inc_nr_events(hists, PERF_RECORD_SAMPLE);
+	session->hists.stats.total_period += data->period;
 	return 0;
 }
 
@@ -164,7 +165,7 @@
 
 		dump_printf("... chain: nr:%Lu\n", data.callchain->nr);
 
-		if (validate_chain(data.callchain, event) < 0) {
+		if (!ip_callchain__valid(data.callchain, event)) {
 			pr_debug("call-chain problem with event, "
 				 "skipping it.\n");
 			return 0;
@@ -187,14 +188,14 @@
 		return 0;
 
 	if (perf_session__add_hist_entry(session, &al, &data)) {
-		pr_debug("problem incrementing symbol count, skipping event\n");
+		pr_debug("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
 
 	attr = perf_header__find_attr(data.id, &session->header);
 
 	if (add_event_total(session, &data, attr)) {
-		pr_debug("problem adding event count\n");
+		pr_debug("problem adding event period\n");
 		return -1;
 	}
 
@@ -260,15 +261,43 @@
 	.fork	= event__process_task,
 	.lost	= event__process_lost,
 	.read	= process_read_event,
+	.attr	= event__process_attr,
+	.event_type = event__process_event_type,
+	.tracing_data = event__process_tracing_data,
+	.build_id = event__process_build_id,
 };
 
+extern volatile int session_done;
+
+static void sig_handler(int sig __used)
+{
+	session_done = 1;
+}
+
+static size_t hists__fprintf_nr_sample_events(struct hists *self,
+					      const char *evname, FILE *fp)
+{
+	size_t ret;
+	char unit;
+	unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE];
+
+	nr_events = convert_unit(nr_events, &unit);
+	ret = fprintf(fp, "# Events: %lu%c", nr_events, unit);
+	if (evname != NULL)
+		ret += fprintf(fp, " %s", evname);
+	return ret + fprintf(fp, "\n#\n");
+}
+
 static int __cmd_report(void)
 {
 	int ret = -EINVAL;
 	struct perf_session *session;
 	struct rb_node *next;
+	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 
-	session = perf_session__new(input_name, O_RDONLY, force);
+	signal(SIGINT, sig_handler);
+
+	session = perf_session__new(input_name, O_RDONLY, force, false);
 	if (session == NULL)
 		return -ENOMEM;
 
@@ -284,7 +313,7 @@
 		goto out_delete;
 
 	if (dump_trace) {
-		event__print_totals();
+		perf_session__fprintf_nr_events(session, stdout);
 		goto out_delete;
 	}
 
@@ -292,39 +321,42 @@
 		perf_session__fprintf(session, stdout);
 
 	if (verbose > 2)
-		dsos__fprintf(stdout);
+		perf_session__fprintf_dsos(session, stdout);
 
-	next = rb_first(&session->stats_by_id);
+	next = rb_first(&session->hists_tree);
 	while (next) {
-		struct event_stat_id *stats;
+		struct hists *hists;
 
-		stats = rb_entry(next, struct event_stat_id, rb_node);
-		perf_session__collapse_resort(&stats->hists);
-		perf_session__output_resort(&stats->hists, stats->stats.total);
-		if (rb_first(&session->stats_by_id) ==
-		    rb_last(&session->stats_by_id))
-			fprintf(stdout, "# Samples: %Ld\n#\n",
-				stats->stats.total);
-		else
-			fprintf(stdout, "# Samples: %Ld %s\n#\n",
-				stats->stats.total,
-				__event_name(stats->type, stats->config));
+		hists = rb_entry(next, struct hists, rb_node);
+		hists__collapse_resort(hists);
+		hists__output_resort(hists);
+		if (use_browser)
+			hists__browse(hists, help, input_name);
+		else {
+			const char *evname = NULL;
+			if (rb_first(&session->hists.entries) !=
+			    rb_last(&session->hists.entries))
+				evname = __event_name(hists->type, hists->config);
 
-		perf_session__fprintf_hists(&stats->hists, NULL, false, stdout,
-					    stats->stats.total);
-		fprintf(stdout, "\n\n");
-		next = rb_next(&stats->rb_node);
+			hists__fprintf_nr_sample_events(hists, evname, stdout);
+
+			hists__fprintf(hists, NULL, false, stdout);
+			fprintf(stdout, "\n\n");
+		}
+
+		next = rb_next(&hists->rb_node);
 	}
 
-	if (sort_order == default_sort_order &&
-	    parent_pattern == default_parent_pattern)
-		fprintf(stdout, "#\n# (For a higher level overview, try: perf report --sort comm,dso)\n#\n");
+	if (!use_browser && sort_order == default_sort_order &&
+	    parent_pattern == default_parent_pattern) {
+		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
-	if (show_threads) {
-		bool raw_printing_style = !strcmp(pretty_printing_style, "raw");
-		perf_read_values_display(stdout, &show_threads_values,
-					 raw_printing_style);
-		perf_read_values_destroy(&show_threads_values);
+		if (show_threads) {
+			bool style = !strcmp(pretty_printing_style, "raw");
+			perf_read_values_display(stdout, &show_threads_values,
+						 style);
+			perf_read_values_destroy(&show_threads_values);
+		}
 	}
 out_delete:
 	perf_session__delete(session);
@@ -335,7 +367,7 @@
 parse_callchain_opt(const struct option *opt __used, const char *arg,
 		    int unset)
 {
-	char *tok;
+	char *tok, *tok2;
 	char *endptr;
 
 	/*
@@ -380,10 +412,13 @@
 	if (!tok)
 		goto setup;
 
+	tok2 = strtok(NULL, ",");
 	callchain_param.min_percent = strtod(tok, &endptr);
 	if (tok == endptr)
 		return -1;
 
+	if (tok2)
+		callchain_param.print_limit = strtod(tok2, &endptr);
 setup:
 	if (register_callchain_param(&callchain_param) < 0) {
 		fprintf(stderr, "Can't register callchain params\n");
@@ -400,7 +435,7 @@
 static const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
@@ -419,12 +454,14 @@
 		   "sort by key(s): pid, comm, dso, symbol, parent"),
 	OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths,
 		    "Don't shorten the pathnames taking into account the cwd"),
+	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
+		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
 		   "regex filter to identify parent, see: '--sort parent'"),
 	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
 		    "Only display entries with parent-match"),
 	OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent",
-		     "Display callchains using output_type and min percent threshold. "
+		     "Display callchains using output_type (graph, flat, fractal, or none) and min percent threshold. "
 		     "Default: fractal,0.5", &parse_callchain_opt, callchain_default_opt),
 	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
 		   "only consider symbols in these dsos"),
@@ -447,7 +484,15 @@
 {
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
-	setup_pager();
+	if (strcmp(input_name, "-") != 0)
+		setup_browser();
+	/*
+	 * Only in the newt browser we are doing integrated annotation,
+	 * so don't allocate extra space that won't be used in the stdio
+	 * implementation.
+	 */
+	if (use_browser)
+		symbol_conf.priv_size = sizeof(struct sym_priv);
 
 	if (symbol__init() < 0)
 		return -1;
@@ -455,7 +500,8 @@
 	setup_sorting(report_usage, options);
 
 	if (parent_pattern != default_parent_pattern) {
-		sort_dimension__add("parent");
+		if (sort_dimension__add("parent") < 0)
+			return -1;
 		sort_parent.elide = 1;
 	} else
 		symbol_conf.exclude_other = false;

tools/perf/builtin-sched.c

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 4f5a03e..f67bce2 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -22,7 +22,7 @@
 static char			const *input_name = "perf.data";
 
 static char			default_sort_order[] = "avg, max, switch, runtime";
-static char			*sort_order = default_sort_order;
+static const char		*sort_order = default_sort_order;
 
 static int			profile_cpu = -1;
 
@@ -68,10 +68,10 @@
 
 struct sched_atom {
 	enum sched_event_type	type;
+	int			specific_wait;
 	u64			timestamp;
 	u64			duration;
 	unsigned long		nr;
-	int			specific_wait;
 	sem_t			*wait_sem;
 	struct task_desc	*wakee;
 };
@@ -105,7 +105,7 @@
 static u64			sum_fluct;
 static u64			run_avg;
 
-static unsigned long		replay_repeat = 10;
+static unsigned int		replay_repeat = 10;
 static unsigned long		nr_timestamps;
 static unsigned long		nr_unordered_timestamps;
 static unsigned long		nr_state_machine_bugs;
@@ -1641,30 +1641,26 @@
 	return 0;
 }
 
-static int process_lost_event(event_t *event __used,
-			      struct perf_session *session __used)
-{
-	nr_lost_chunks++;
-	nr_lost_events += event->lost.lost;
-
-	return 0;
-}
-
 static struct perf_event_ops event_ops = {
-	.sample	= process_sample_event,
-	.comm	= event__process_comm,
-	.lost	= process_lost_event,
+	.sample			= process_sample_event,
+	.comm			= event__process_comm,
+	.lost			= event__process_lost,
+	.ordered_samples	= true,
 };
 
 static int read_events(void)
 {
 	int err = -EINVAL;
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0);
+	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
 	if (session == NULL)
 		return -ENOMEM;
 
-	if (perf_session__has_traces(session, "record -R"))
+	if (perf_session__has_traces(session, "record -R")) {
 		err = perf_session__process_events(session, &event_ops);
+		nr_events      = session->hists.stats.nr_events[0];
+		nr_lost_events = session->hists.stats.total_lost;
+		nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST];
+	}
 
 	perf_session__delete(session);
 	return err;
@@ -1790,7 +1786,7 @@
 static const struct option sched_options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
@@ -1805,7 +1801,7 @@
 static const struct option latency_options[] = {
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): runtime, switch, avg, max"),
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_INTEGER('C', "CPU", &profile_cpu,
 		    "CPU to profile on"),
@@ -1820,9 +1816,9 @@
 };
 
 static const struct option replay_options[] = {
-	OPT_INTEGER('r', "repeat", &replay_repeat,
-		    "repeat the workload replay N times (-1: infinite)"),
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_UINTEGER('r', "repeat", &replay_repeat,
+		     "repeat the workload replay N times (-1: infinite)"),
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
@@ -1850,7 +1846,6 @@
 	"record",
 	"-a",
 	"-R",
-	"-M",
 	"-f",
 	"-m", "1024",
 	"-c", "1",

tools/perf/builtin-stat.c

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 95db31c..ff8c413 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -46,6 +46,7 @@
 #include "util/debug.h"
 #include "util/header.h"
 #include "util/cpumap.h"
+#include "util/thread.h"
 
 #include <sys/prctl.h>
 #include <math.h>
@@ -66,18 +67,21 @@
 
 };
 
-static int			system_wide			=  0;
+static bool			system_wide			=  false;
 static unsigned int		nr_cpus				=  0;
 static int			run_idx				=  0;
 
 static int			run_count			=  1;
-static int			inherit				=  1;
-static int			scale				=  1;
+static bool			no_inherit			= false;
+static bool			scale				=  true;
 static pid_t			target_pid			= -1;
+static pid_t			target_tid			= -1;
+static pid_t			*all_tids			=  NULL;
+static int			thread_num			=  0;
 static pid_t			child_pid			= -1;
-static int			null_run			=  0;
+static bool			null_run			=  false;
 
-static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
+static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
 
 static int			event_scaled[MAX_COUNTERS];
 
@@ -140,9 +144,11 @@
 #define ERR_PERF_OPEN \
 "Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n"
 
-static void create_perf_stat_counter(int counter, int pid)
+static int create_perf_stat_counter(int counter)
 {
 	struct perf_event_attr *attr = attrs + counter;
+	int thread;
+	int ncreated = 0;
 
 	if (scale)
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
@@ -152,21 +158,33 @@
 		unsigned int cpu;
 
 		for (cpu = 0; cpu < nr_cpus; cpu++) {
-			fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0);
-			if (fd[cpu][counter] < 0 && verbose)
-				fprintf(stderr, ERR_PERF_OPEN, counter,
-					fd[cpu][counter], strerror(errno));
+			fd[cpu][counter][0] = sys_perf_event_open(attr,
+					-1, cpumap[cpu], -1, 0);
+			if (fd[cpu][counter][0] < 0)
+				pr_debug(ERR_PERF_OPEN, counter,
+					 fd[cpu][counter][0], strerror(errno));
+			else
+				++ncreated;
 		}
 	} else {
-		attr->inherit	     = inherit;
-		attr->disabled	     = 1;
-		attr->enable_on_exec = 1;
-
-		fd[0][counter] = sys_perf_event_open(attr, pid, -1, -1, 0);
-		if (fd[0][counter] < 0 && verbose)
-			fprintf(stderr, ERR_PERF_OPEN, counter,
-				fd[0][counter], strerror(errno));
+		attr->inherit = !no_inherit;
+		if (target_pid == -1 && target_tid == -1) {
+			attr->disabled = 1;
+			attr->enable_on_exec = 1;
+		}
+		for (thread = 0; thread < thread_num; thread++) {
+			fd[0][counter][thread] = sys_perf_event_open(attr,
+				all_tids[thread], -1, -1, 0);
+			if (fd[0][counter][thread] < 0)
+				pr_debug(ERR_PERF_OPEN, counter,
+					 fd[0][counter][thread],
+					 strerror(errno));
+			else
+				++ncreated;
+		}
 	}
+
+	return ncreated;
 }
 
 /*
@@ -190,25 +208,28 @@
 	unsigned int cpu;
 	size_t res, nv;
 	int scaled;
-	int i;
+	int i, thread;
 
 	count[0] = count[1] = count[2] = 0;
 
 	nv = scale ? 3 : 1;
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		if (fd[cpu][counter] < 0)
-			continue;
+		for (thread = 0; thread < thread_num; thread++) {
+			if (fd[cpu][counter][thread] < 0)
+				continue;
 
-		res = read(fd[cpu][counter], single_count, nv * sizeof(u64));
-		assert(res == nv * sizeof(u64));
+			res = read(fd[cpu][counter][thread],
+					single_count, nv * sizeof(u64));
+			assert(res == nv * sizeof(u64));
 
-		close(fd[cpu][counter]);
-		fd[cpu][counter] = -1;
+			close(fd[cpu][counter][thread]);
+			fd[cpu][counter][thread] = -1;
 
-		count[0] += single_count[0];
-		if (scale) {
-			count[1] += single_count[1];
-			count[2] += single_count[2];
+			count[0] += single_count[0];
+			if (scale) {
+				count[1] += single_count[1];
+				count[2] += single_count[2];
+			}
 		}
 	}
 
@@ -250,10 +271,9 @@
 {
 	unsigned long long t0, t1;
 	int status = 0;
-	int counter;
-	int pid = target_pid;
+	int counter, ncreated = 0;
 	int child_ready_pipe[2], go_pipe[2];
-	const bool forks = (target_pid == -1 && argc > 0);
+	const bool forks = (argc > 0);
 	char buf;
 
 	if (!system_wide)
@@ -265,10 +285,10 @@
 	}
 
 	if (forks) {
-		if ((pid = fork()) < 0)
+		if ((child_pid = fork()) < 0)
 			perror("failed to fork");
 
-		if (!pid) {
+		if (!child_pid) {
 			close(child_ready_pipe[0]);
 			close(go_pipe[1]);
 			fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
@@ -297,7 +317,8 @@
 			exit(-1);
 		}
 
-		child_pid = pid;
+		if (target_tid == -1 && target_pid == -1 && !system_wide)
+			all_tids[0] = child_pid;
 
 		/*
 		 * Wait for the child to be ready to exec.
@@ -310,7 +331,16 @@
 	}
 
 	for (counter = 0; counter < nr_counters; counter++)
-		create_perf_stat_counter(counter, pid);
+		ncreated += create_perf_stat_counter(counter);
+
+	if (ncreated == 0) {
+		pr_err("No permission to collect %sstats.\n"
+		       "Consider tweaking /proc/sys/kernel/perf_event_paranoid.\n",
+		       system_wide ? "system-wide " : "");
+		if (child_pid != -1)
+			kill(child_pid, SIGTERM);
+		return -1;
+	}
 
 	/*
 	 * Enable counters and exec the command:
@@ -321,7 +351,7 @@
 		close(go_pipe[1]);
 		wait(&status);
 	} else {
-		while(!done);
+		while(!done) sleep(1);
 	}
 
 	t1 = rdclock();
@@ -429,12 +459,14 @@
 
 	fprintf(stderr, "\n");
 	fprintf(stderr, " Performance counter stats for ");
-	if(target_pid == -1) {
+	if(target_pid == -1 && target_tid == -1) {
 		fprintf(stderr, "\'%s", argv[0]);
 		for (i = 1; i < argc; i++)
 			fprintf(stderr, " %s", argv[i]);
-	}else
-		fprintf(stderr, "task pid \'%d", target_pid);
+	} else if (target_pid != -1)
+		fprintf(stderr, "process id \'%d", target_pid);
+	else
+		fprintf(stderr, "thread id \'%d", target_tid);
 
 	fprintf(stderr, "\'");
 	if (run_count > 1)
@@ -459,7 +491,7 @@
 
 static void skip_signal(int signo)
 {
-	if(target_pid != -1)
+	if(child_pid == -1)
 		done = 1;
 
 	signr = signo;
@@ -486,15 +518,17 @@
 	OPT_CALLBACK('e', "event", NULL, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events),
-	OPT_BOOLEAN('i', "inherit", &inherit,
-		    "child tasks inherit counters"),
+	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+		    "child tasks do not inherit counters"),
 	OPT_INTEGER('p', "pid", &target_pid,
-		    "stat events on existing pid"),
+		    "stat events on existing process id"),
+	OPT_INTEGER('t', "tid", &target_tid,
+		    "stat events on existing thread id"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_BOOLEAN('c', "scale", &scale,
 		    "scale/normalize counters"),
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_INTEGER('r', "repeat", &run_count,
 		    "repeat command and print average + stddev (max: 100)"),
@@ -506,10 +540,11 @@
 int cmd_stat(int argc, const char **argv, const char *prefix __used)
 {
 	int status;
+	int i,j;
 
 	argc = parse_options(argc, argv, options, stat_usage,
 		PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && target_pid == -1)
+	if (!argc && target_pid == -1 && target_tid == -1)
 		usage_with_options(stat_usage, options);
 	if (run_count <= 0)
 		usage_with_options(stat_usage, options);
@@ -525,6 +560,31 @@
 	else
 		nr_cpus = 1;
 
+	if (target_pid != -1) {
+		target_tid = target_pid;
+		thread_num = find_all_tid(target_pid, &all_tids);
+		if (thread_num <= 0) {
+			fprintf(stderr, "Can't find all threads of pid %d\n",
+					target_pid);
+			usage_with_options(stat_usage, options);
+		}
+	} else {
+		all_tids=malloc(sizeof(pid_t));
+		if (!all_tids)
+			return -ENOMEM;
+
+		all_tids[0] = target_tid;
+		thread_num = 1;
+	}
+
+	for (i = 0; i < MAX_NR_CPUS; i++) {
+		for (j = 0; j < MAX_COUNTERS; j++) {
+			fd[i][j] = malloc(sizeof(int)*thread_num);
+			if (!fd[i][j])
+				return -ENOMEM;
+		}
+	}
+
 	/*
 	 * We dont want to block the signals - that would cause
 	 * child tasks to inherit that and Ctrl-C would not work.
@@ -543,7 +603,8 @@
 		status = run_perf_stat(argc, argv);
 	}
 
-	print_stat(argc, argv);
+	if (status != -1)
+		print_stat(argc, argv);
 
 	return status;
 }

tools/perf/builtin-test.c

diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
new file mode 100644
index 0000000..035b9fa
--- /dev/null
+++ b/tools/perf/builtin-test.c
@@ -0,0 +1,281 @@
+/*
+ * builtin-test.c
+ *
+ * Builtin regression testing command: ever growing number of sanity tests
+ */
+#include "builtin.h"
+
+#include "util/cache.h"
+#include "util/debug.h"
+#include "util/parse-options.h"
+#include "util/session.h"
+#include "util/symbol.h"
+#include "util/thread.h"
+
+static long page_size;
+
+static int vmlinux_matches_kallsyms_filter(struct map *map __used, struct symbol *sym)
+{
+	bool *visited = symbol__priv(sym);
+	*visited = true;
+	return 0;
+}
+
+static int test__vmlinux_matches_kallsyms(void)
+{
+	int err = -1;
+	struct rb_node *nd;
+	struct symbol *sym;
+	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", };
+
+	/*
+	 * Step 1:
+	 *
+	 * Init the machines that will hold kernel, modules obtained from
+	 * both vmlinux + .ko files and from /proc/kallsyms split by modules.
+	 */
+	machine__init(&kallsyms, "", HOST_KERNEL_ID);
+	machine__init(&vmlinux, "", HOST_KERNEL_ID);
+
+	/*
+	 * Step 2:
+	 *
+	 * Create the kernel maps for kallsyms and the DSO where we will then
+	 * load /proc/kallsyms. Also create the modules maps from /proc/modules
+	 * and find the .ko files that match them in /lib/modules/`uname -r`/.
+	 */
+	if (machine__create_kernel_maps(&kallsyms) < 0) {
+		pr_debug("machine__create_kernel_maps ");
+		return -1;
+	}
+
+	/*
+	 * Step 3:
+	 *
+	 * Load and split /proc/kallsyms into multiple maps, one per module.
+	 */
+	if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, NULL) <= 0) {
+		pr_debug("dso__load_kallsyms ");
+		goto out;
+	}
+
+	/*
+	 * Step 4:
+	 *
+	 * kallsyms will be internally on demand sorted by name so that we can
+	 * find the reference relocation * symbol, i.e. the symbol we will use
+	 * to see if the running kernel was relocated by checking if it has the
+	 * same value in the vmlinux file we load.
+	 */
+	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 = sym->start;
+
+	/*
+	 * Step 5:
+	 *
+	 * Now repeat step 2, this time for the vmlinux file we'll auto-locate.
+	 */
+	if (machine__create_kernel_maps(&vmlinux) < 0) {
+		pr_debug("machine__create_kernel_maps ");
+		goto out;
+	}
+
+	vmlinux_map = machine__kernel_map(&vmlinux, type);
+	map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym;
+
+	/*
+	 * Step 6:
+	 *
+	 * Locate a vmlinux file in the vmlinux path that has a buildid that
+	 * matches the one of the running kernel.
+	 *
+	 * While doing that look if we find the ref reloc symbol, if we find it
+	 * we'll have its ref_reloc_symbol.unrelocated_addr and then
+	 * maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines
+	 * to fixup the symbols.
+	 */
+	if (machine__load_vmlinux_path(&vmlinux, type,
+				       vmlinux_matches_kallsyms_filter) <= 0) {
+		pr_debug("machine__load_vmlinux_path ");
+		goto out;
+	}
+
+	err = 0;
+	/*
+	 * Step 7:
+	 *
+	 * Now look at the symbols in the vmlinux DSO and check if we find all of them
+	 * in the kallsyms dso. For the ones that are in both, check its names and
+	 * end addresses too.
+	 */
+	for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
+		struct symbol *pair;
+
+		sym  = rb_entry(nd, struct symbol, rb_node);
+		pair = machine__find_kernel_symbol(&kallsyms, type, sym->start, NULL, NULL);
+
+		if (pair && pair->start == sym->start) {
+next_pair:
+			if (strcmp(sym->name, pair->name) == 0) {
+				/*
+				 * kallsyms don't have the symbol end, so we
+				 * set that by using the next symbol start - 1,
+				 * in some cases we get this up to a page
+				 * wrong, trace_kmalloc when I was developing
+				 * this code was one such example, 2106 bytes
+				 * off the real size. More than that and we
+				 * _really_ have a problem.
+				 */
+				s64 skew = sym->end - pair->end;
+				if (llabs(skew) < page_size)
+					continue;
+
+				pr_debug("%#Lx: diff end addr for %s v: %#Lx k: %#Lx\n",
+					 sym->start, sym->name, sym->end, pair->end);
+			} else {
+				struct rb_node *nnd = rb_prev(&pair->rb_node);
+
+				if (nnd) {
+					struct symbol *next = rb_entry(nnd, struct symbol, rb_node);
+
+					if (next->start == sym->start) {
+						pair = next;
+						goto next_pair;
+					}
+				}
+				pr_debug("%#Lx: diff name v: %s k: %s\n",
+					 sym->start, sym->name, pair->name);
+			}
+		} else
+			pr_debug("%#Lx: %s not on kallsyms\n", sym->start, sym->name);
+
+		err = -1;
+	}
+
+	if (!verbose)
+		goto out;
+
+	pr_info("Maps only in vmlinux:\n");
+
+	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+		/*
+		 * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
+		 * the kernel will have the path for the vmlinux file being used,
+		 * so use the short name, less descriptive but the same ("[kernel]" in
+		 * both cases.
+		 */
+		pair = map_groups__find_by_name(&kallsyms.kmaps, type,
+						(pos->dso->kernel ?
+							pos->dso->short_name :
+							pos->dso->name));
+		if (pair)
+			pair->priv = 1;
+		else
+			map__fprintf(pos, stderr);
+	}
+
+	pr_info("Maps in vmlinux with a different name in kallsyms:\n");
+
+	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+
+		pair = map_groups__find(&kallsyms.kmaps, type, pos->start);
+		if (pair == NULL || pair->priv)
+			continue;
+
+		if (pair->start == pos->start) {
+			pair->priv = 1;
+			pr_info(" %Lx-%Lx %Lx %s in kallsyms as",
+				pos->start, pos->end, pos->pgoff, pos->dso->name);
+			if (pos->pgoff != pair->pgoff || pos->end != pair->end)
+				pr_info(": \n*%Lx-%Lx %Lx",
+					pair->start, pair->end, pair->pgoff);
+			pr_info(" %s\n", pair->dso->name);
+			pair->priv = 1;
+		}
+	}
+
+	pr_info("Maps only in kallsyms:\n");
+
+	for (nd = rb_first(&kallsyms.kmaps.maps[type]);
+	     nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node);
+
+		if (!pos->priv)
+			map__fprintf(pos, stderr);
+	}
+out:
+	return err;
+}
+
+static struct test {
+	const char *desc;
+	int (*func)(void);
+} tests[] = {
+	{
+		.desc = "vmlinux symtab matches kallsyms",
+		.func = test__vmlinux_matches_kallsyms,
+	},
+	{
+		.func = NULL,
+	},
+};
+
+static int __cmd_test(void)
+{
+	int i = 0;
+
+	page_size = sysconf(_SC_PAGE_SIZE);
+
+	while (tests[i].func) {
+		int err;
+		pr_info("%2d: %s:", i + 1, tests[i].desc);
+		pr_debug("\n--- start ---\n");
+		err = tests[i].func();
+		pr_debug("---- end ----\n%s:", tests[i].desc);
+		pr_info(" %s\n", err ? "FAILED!\n" : "Ok");
+		++i;
+	}
+
+	return 0;
+}
+
+static const char * const test_usage[] = {
+	"perf test [<options>]",
+	NULL,
+};
+
+static const struct option test_options[] = {
+	OPT_INTEGER('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_END()
+};
+
+int cmd_test(int argc, const char **argv, const char *prefix __used)
+{
+	argc = parse_options(argc, argv, test_options, test_usage, 0);
+	if (argc)
+		usage_with_options(test_usage, test_options);
+
+	symbol_conf.priv_size = sizeof(int);
+	symbol_conf.sort_by_name = true;
+	symbol_conf.try_vmlinux_path = true;
+
+	if (symbol__init() < 0)
+		return -1;
+
+	setup_pager();
+
+	return __cmd_test();
+}

tools/perf/builtin-timechart.c

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 0d4d8ff..5a52ed9 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -21,7 +21,6 @@
 #include "util/cache.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
-#include "util/string.h"
 #include "util/callchain.h"
 #include "util/strlist.h"
 
@@ -43,7 +42,7 @@
 
 static u64		first_time, last_time;
 
-static int		power_only;
+static bool		power_only;
 
 
 struct per_pid;
@@ -78,8 +77,6 @@
 
 	struct per_pidcomm *all;
 	struct per_pidcomm *current;
-
-	int painted;
 };
 
 
@@ -146,9 +143,6 @@
 static struct power_event    *power_events;
 static struct wake_event     *wake_events;
 
-struct sample_wrapper *all_samples;
-
-
 struct process_filter;
 struct process_filter {
 	char			*name;
@@ -569,88 +563,6 @@
 	}
 }
 
-static u64 sample_time(event_t *event, const struct perf_session *session)
-{
-	int cursor;
-
-	cursor = 0;
-	if (session->sample_type & PERF_SAMPLE_IP)
-		cursor++;
-	if (session->sample_type & PERF_SAMPLE_TID)
-		cursor++;
-	if (session->sample_type & PERF_SAMPLE_TIME)
-		return event->sample.array[cursor];
-	return 0;
-}
-
-
-/*
- * We first queue all events, sorted backwards by insertion.
- * The order will get flipped later.
- */
-static int queue_sample_event(event_t *event, struct perf_session *session)
-{
-	struct sample_wrapper *copy, *prev;
-	int size;
-
-	size = event->sample.header.size + sizeof(struct sample_wrapper) + 8;
-
-	copy = malloc(size);
-	if (!copy)
-		return 1;
-
-	memset(copy, 0, size);
-
-	copy->next = NULL;
-	copy->timestamp = sample_time(event, session);
-
-	memcpy(&copy->data, event, event->sample.header.size);
-
-	/* insert in the right place in the list */
-
-	if (!all_samples) {
-		/* first sample ever */
-		all_samples = copy;
-		return 0;
-	}
-
-	if (all_samples->timestamp < copy->timestamp) {
-		/* insert at the head of the list */
-		copy->next = all_samples;
-		all_samples = copy;
-		return 0;
-	}
-
-	prev = all_samples;
-	while (prev->next) {
-		if (prev->next->timestamp < copy->timestamp) {
-			copy->next = prev->next;
-			prev->next = copy;
-			return 0;
-		}
-		prev = prev->next;
-	}
-	/* insert at the end of the list */
-	prev->next = copy;
-
-	return 0;
-}
-
-static void sort_queued_samples(void)
-{
-	struct sample_wrapper *cursor, *next;
-
-	cursor = all_samples;
-	all_samples = NULL;
-
-	while (cursor) {
-		next = cursor->next;
-		cursor->next = all_samples;
-		all_samples = cursor;
-		cursor = next;
-	}
-}
-
 /*
  * Sort the pid datastructure
  */
@@ -1014,31 +926,17 @@
 	svg_close();
 }
 
-static void process_samples(struct perf_session *session)
-{
-	struct sample_wrapper *cursor;
-	event_t *event;
-
-	sort_queued_samples();
-
-	cursor = all_samples;
-	while (cursor) {
-		event = (void *)&cursor->data;
-		cursor = cursor->next;
-		process_sample_event(event, session);
-	}
-}
-
 static struct perf_event_ops event_ops = {
-	.comm	= process_comm_event,
-	.fork	= process_fork_event,
-	.exit	= process_exit_event,
-	.sample	= queue_sample_event,
+	.comm			= process_comm_event,
+	.fork			= process_fork_event,
+	.exit			= process_exit_event,
+	.sample			= process_sample_event,
+	.ordered_samples	= true,
 };
 
 static int __cmd_timechart(void)
 {
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0);
+	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
 	int ret = -EINVAL;
 
 	if (session == NULL)
@@ -1051,8 +949,6 @@
 	if (ret)
 		goto out_delete;
 
-	process_samples(session);
-
 	end_sample_processing();
 
 	sort_pids();
@@ -1075,7 +971,6 @@
 	"record",
 	"-a",
 	"-R",
-	"-M",
 	"-f",
 	"-c", "1",
 	"-e", "power:power_start",

tools/perf/builtin-top.c

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1f52932..397290a 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -55,9 +55,9 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
+static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
 
-static int			system_wide			=      0;
+static bool			system_wide			=  false;
 
 static int			default_interval		=      0;
 
@@ -65,18 +65,21 @@
 static int			print_entries;
 
 static int			target_pid			=     -1;
-static int			inherit				=      0;
+static int			target_tid			=     -1;
+static pid_t			*all_tids			=      NULL;
+static int			thread_num			=      0;
+static bool			inherit				=  false;
 static int			profile_cpu			=     -1;
 static int			nr_cpus				=      0;
-static unsigned int		realtime_prio			=      0;
-static int			group				=      0;
+static int			realtime_prio			=      0;
+static bool			group				=  false;
 static unsigned int		page_size;
 static unsigned int		mmap_pages			=     16;
 static int			freq				=   1000; /* 1 KHz */
 
 static int			delay_secs			=      2;
-static int			zero                            =      0;
-static int			dump_symtab                     =      0;
+static bool			zero                            =  false;
+static bool			dump_symtab                     =  false;
 
 static bool			hide_kernel_symbols		=  false;
 static bool			hide_user_symbols		=  false;
@@ -93,7 +96,7 @@
 	struct source_line	*next;
 };
 
-static char			*sym_filter			=   NULL;
+static const char		*sym_filter			=   NULL;
 struct sym_entry		*sym_filter_entry		=   NULL;
 struct sym_entry		*sym_filter_entry_sched		=   NULL;
 static int			sym_pcnt_filter			=      5;
@@ -133,7 +136,7 @@
        return ((void *)self) + symbol_conf.priv_size;
 }
 
-static void get_term_dimensions(struct winsize *ws)
+void get_term_dimensions(struct winsize *ws)
 {
 	char *s = getenv("LINES");
 
@@ -169,7 +172,7 @@
 	update_print_entries(&winsize);
 }
 
-static void parse_source(struct sym_entry *syme)
+static int parse_source(struct sym_entry *syme)
 {
 	struct symbol *sym;
 	struct sym_entry_source *source;
@@ -180,12 +183,21 @@
 	u64 len;
 
 	if (!syme)
-		return;
+		return -1;
+
+	sym = sym_entry__symbol(syme);
+	map = syme->map;
+
+	/*
+	 * We can't annotate with just /proc/kallsyms
+	 */
+	if (map->dso->origin == DSO__ORIG_KERNEL)
+		return -1;
 
 	if (syme->src == NULL) {
 		syme->src = zalloc(sizeof(*source));
 		if (syme->src == NULL)
-			return;
+			return -1;
 		pthread_mutex_init(&syme->src->lock, NULL);
 	}
 
@@ -195,9 +207,6 @@
 		pthread_mutex_lock(&source->lock);
 		goto out_assign;
 	}
-
-	sym = sym_entry__symbol(syme);
-	map = syme->map;
 	path = map->dso->long_name;
 
 	len = sym->end - sym->start;
@@ -209,7 +218,7 @@
 
 	file = popen(command, "r");
 	if (!file)
-		return;
+		return -1;
 
 	pthread_mutex_lock(&source->lock);
 	source->lines_tail = &source->lines;
@@ -245,6 +254,7 @@
 out_assign:
 	sym_filter_entry = syme;
 	pthread_mutex_unlock(&source->lock);
+	return 0;
 }
 
 static void __zero_source_counters(struct sym_entry *syme)
@@ -410,7 +420,9 @@
 }
 
 static long			samples;
-static long			userspace_samples;
+static long			kernel_samples, us_samples;
+static long			exact_samples;
+static long			guest_us_samples, guest_kernel_samples;
 static const char		CONSOLE_CLEAR[] = "";
 
 static void __list_insert_active_sym(struct sym_entry *syme)
@@ -450,7 +462,11 @@
 	int printed = 0, j;
 	int counter, snap = !display_weighted ? sym_counter : 0;
 	float samples_per_sec = samples/delay_secs;
-	float ksamples_per_sec = (samples-userspace_samples)/delay_secs;
+	float ksamples_per_sec = kernel_samples/delay_secs;
+	float us_samples_per_sec = (us_samples)/delay_secs;
+	float guest_kernel_samples_per_sec = (guest_kernel_samples)/delay_secs;
+	float guest_us_samples_per_sec = (guest_us_samples)/delay_secs;
+	float esamples_percent = (100.0*exact_samples)/samples;
 	float sum_ksamples = 0.0;
 	struct sym_entry *syme, *n;
 	struct rb_root tmp = RB_ROOT;
@@ -458,7 +474,8 @@
 	int sym_width = 0, dso_width = 0, dso_short_width = 0;
 	const int win_width = winsize.ws_col - 1;
 
-	samples = userspace_samples = 0;
+	samples = us_samples = kernel_samples = exact_samples = 0;
+	guest_kernel_samples = guest_us_samples = 0;
 
 	/* Sort the active symbols */
 	pthread_mutex_lock(&active_symbols_lock);
@@ -489,9 +506,30 @@
 	puts(CONSOLE_CLEAR);
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
-	printf( "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% [",
-		samples_per_sec,
-		100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)));
+	if (!perf_guest) {
+		printf("   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%"
+			"  exact: %4.1f%% [",
+			samples_per_sec,
+			100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+					 samples_per_sec)),
+			esamples_percent);
+	} else {
+		printf("   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% us:%4.1f%%"
+			" guest kernel:%4.1f%% guest us:%4.1f%%"
+			" exact: %4.1f%% [",
+			samples_per_sec,
+			100.0 - (100.0 * ((samples_per_sec-ksamples_per_sec) /
+					  samples_per_sec)),
+			100.0 - (100.0 * ((samples_per_sec-us_samples_per_sec) /
+					  samples_per_sec)),
+			100.0 - (100.0 * ((samples_per_sec -
+						guest_kernel_samples_per_sec) /
+					  samples_per_sec)),
+			100.0 - (100.0 * ((samples_per_sec -
+					   guest_us_samples_per_sec) /
+					  samples_per_sec)),
+			esamples_percent);
+	}
 
 	if (nr_counters == 1 || !display_weighted) {
 		printf("%Ld", (u64)attrs[0].sample_period);
@@ -514,13 +552,15 @@
 
 	if (target_pid != -1)
 		printf(" (target_pid: %d", target_pid);
+	else if (target_tid != -1)
+		printf(" (target_tid: %d", target_tid);
 	else
 		printf(" (all");
 
 	if (profile_cpu != -1)
 		printf(", cpu: %d)\n", profile_cpu);
 	else {
-		if (target_pid != -1)
+		if (target_tid != -1)
 			printf(")\n");
 		else
 			printf(", %d CPUs)\n", nr_cpus);
@@ -582,7 +622,6 @@
 
 		syme = rb_entry(nd, struct sym_entry, rb_node);
 		sym = sym_entry__symbol(syme);
-
 		if (++printed > print_entries || (int)syme->snap_count < count_filter)
 			continue;
 
@@ -746,7 +785,7 @@
 	return 0;
 }
 
-static void handle_keypress(int c)
+static void handle_keypress(struct perf_session *session, int c)
 {
 	if (!key_mapped(c)) {
 		struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
@@ -815,7 +854,7 @@
 		case 'Q':
 			printf("exiting.\n");
 			if (dump_symtab)
-				dsos__fprintf(stderr);
+				perf_session__fprintf_dsos(session, stderr);
 			exit(0);
 		case 's':
 			prompt_symbol(&sym_filter_entry, "Enter details symbol");
@@ -839,7 +878,7 @@
 			display_weighted = ~display_weighted;
 			break;
 		case 'z':
-			zero = ~zero;
+			zero = !zero;
 			break;
 		default:
 			break;
@@ -851,6 +890,7 @@
 	struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
 	struct termios tc, save;
 	int delay_msecs, c;
+	struct perf_session *session = (struct perf_session *) arg;
 
 	tcgetattr(0, &save);
 	tc = save;
@@ -871,7 +911,7 @@
 	c = getc(stdin);
 	tcsetattr(0, TCSAFLUSH, &save);
 
-	handle_keypress(c);
+	handle_keypress(session, c);
 	goto repeat;
 
 	return NULL;
@@ -942,24 +982,48 @@
 	u64 ip = self->ip.ip;
 	struct sym_entry *syme;
 	struct addr_location al;
+	struct machine *machine;
 	u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	++samples;
 
 	switch (origin) {
 	case PERF_RECORD_MISC_USER:
-		++userspace_samples;
+		++us_samples;
 		if (hide_user_symbols)
 			return;
+		machine = perf_session__find_host_machine(session);
 		break;
 	case PERF_RECORD_MISC_KERNEL:
+		++kernel_samples;
 		if (hide_kernel_symbols)
 			return;
+		machine = perf_session__find_host_machine(session);
 		break;
+	case PERF_RECORD_MISC_GUEST_KERNEL:
+		++guest_kernel_samples;
+		machine = perf_session__find_machine(session, self->ip.pid);
+		break;
+	case PERF_RECORD_MISC_GUEST_USER:
+		++guest_us_samples;
+		/*
+		 * TODO: we don't process guest user from host side
+		 * except simple counting.
+		 */
+		return;
 	default:
 		return;
 	}
 
+	if (!machine && perf_guest) {
+		pr_err("Can't find guest [%d]'s kernel information\n",
+			self->ip.pid);
+		return;
+	}
+
+	if (self->header.misc & PERF_RECORD_MISC_EXACT_IP)
+		exact_samples++;
+
 	if (event__preprocess_sample(self, session, &al, symbol_filter) < 0 ||
 	    al.filtered)
 		return;
@@ -976,7 +1040,7 @@
 		 * --hide-kernel-symbols, even if the user specifies an
 		 * invalid --vmlinux ;-)
 		 */
-		if (al.map == session->vmlinux_maps[MAP__FUNCTION] &&
+		if (al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
 		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
 			pr_err("The %s file can't be used\n",
 			       symbol_conf.vmlinux_name);
@@ -990,7 +1054,17 @@
 	if (sym_filter_entry_sched) {
 		sym_filter_entry = sym_filter_entry_sched;
 		sym_filter_entry_sched = NULL;
-		parse_source(sym_filter_entry);
+		if (parse_source(sym_filter_entry) < 0) {
+			struct symbol *sym = sym_entry__symbol(sym_filter_entry);
+
+			pr_err("Can't annotate %s", sym->name);
+			if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
+				pr_err(": No vmlinux file was found in the path:\n");
+				vmlinux_path__fprintf(stderr);
+			} else
+				pr_err(".\n");
+			exit(1);
+		}
 	}
 
 	syme = symbol__priv(al.sym);
@@ -1106,16 +1180,21 @@
 	md->prev = old;
 }
 
-static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS];
-static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
+static struct pollfd *event_array;
+static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
 
 static void perf_session__mmap_read(struct perf_session *self)
 {
-	int i, counter;
+	int i, counter, thread_index;
 
 	for (i = 0; i < nr_cpus; i++) {
 		for (counter = 0; counter < nr_counters; counter++)
-			perf_session__mmap_read_counter(self, &mmap_array[i][counter]);
+			for (thread_index = 0;
+				thread_index < thread_num;
+				thread_index++) {
+				perf_session__mmap_read_counter(self,
+					&mmap_array[i][counter][thread_index]);
+			}
 	}
 }
 
@@ -1126,9 +1205,10 @@
 {
 	struct perf_event_attr *attr;
 	int cpu;
+	int thread_index;
 
 	cpu = profile_cpu;
-	if (target_pid == -1 && profile_cpu == -1)
+	if (target_tid == -1 && profile_cpu == -1)
 		cpu = cpumap[i];
 
 	attr = attrs + counter;
@@ -1144,55 +1224,58 @@
 	attr->inherit		= (cpu < 0) && inherit;
 	attr->mmap		= 1;
 
+	for (thread_index = 0; thread_index < thread_num; thread_index++) {
 try_again:
-	fd[i][counter] = sys_perf_event_open(attr, target_pid, cpu, group_fd, 0);
+		fd[i][counter][thread_index] = sys_perf_event_open(attr,
+				all_tids[thread_index], cpu, group_fd, 0);
 
-	if (fd[i][counter] < 0) {
-		int err = errno;
+		if (fd[i][counter][thread_index] < 0) {
+			int err = errno;
 
-		if (err == EPERM || err == EACCES)
-			die("No permission - are you root?\n");
-		/*
-		 * If it's cycles then fall back to hrtimer
-		 * based cpu-clock-tick sw counter, which
-		 * is always available even if no PMU support:
-		 */
-		if (attr->type == PERF_TYPE_HARDWARE
-			&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+			if (err == EPERM || err == EACCES)
+				die("No permission - are you root?\n");
+			/*
+			 * If it's cycles then fall back to hrtimer
+			 * based cpu-clock-tick sw counter, which
+			 * is always available even if no PMU support:
+			 */
+			if (attr->type == PERF_TYPE_HARDWARE
+					&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
 
-			if (verbose)
-				warning(" ... trying to fall back to cpu-clock-ticks\n");
+				if (verbose)
+					warning(" ... trying to fall back to cpu-clock-ticks\n");
 
-			attr->type = PERF_TYPE_SOFTWARE;
-			attr->config = PERF_COUNT_SW_CPU_CLOCK;
-			goto try_again;
+				attr->type = PERF_TYPE_SOFTWARE;
+				attr->config = PERF_COUNT_SW_CPU_CLOCK;
+				goto try_again;
+			}
+			printf("\n");
+			error("perfcounter syscall returned with %d (%s)\n",
+					fd[i][counter][thread_index], strerror(err));
+			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+			exit(-1);
 		}
-		printf("\n");
-		error("perfcounter syscall returned with %d (%s)\n",
-			fd[i][counter], strerror(err));
-		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-		exit(-1);
+		assert(fd[i][counter][thread_index] >= 0);
+		fcntl(fd[i][counter][thread_index], F_SETFL, O_NONBLOCK);
+
+		/*
+		 * First counter acts as the group leader:
+		 */
+		if (group && group_fd == -1)
+			group_fd = fd[i][counter][thread_index];
+
+		event_array[nr_poll].fd = fd[i][counter][thread_index];
+		event_array[nr_poll].events = POLLIN;
+		nr_poll++;
+
+		mmap_array[i][counter][thread_index].counter = counter;
+		mmap_array[i][counter][thread_index].prev = 0;
+		mmap_array[i][counter][thread_index].mask = mmap_pages*page_size - 1;
+		mmap_array[i][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
+				PROT_READ, MAP_SHARED, fd[i][counter][thread_index], 0);
+		if (mmap_array[i][counter][thread_index].base == MAP_FAILED)
+			die("failed to mmap with %d (%s)\n", errno, strerror(errno));
 	}
-	assert(fd[i][counter] >= 0);
-	fcntl(fd[i][counter], F_SETFL, O_NONBLOCK);
-
-	/*
-	 * First counter acts as the group leader:
-	 */
-	if (group && group_fd == -1)
-		group_fd = fd[i][counter];
-
-	event_array[nr_poll].fd = fd[i][counter];
-	event_array[nr_poll].events = POLLIN;
-	nr_poll++;
-
-	mmap_array[i][counter].counter = counter;
-	mmap_array[i][counter].prev = 0;
-	mmap_array[i][counter].mask = mmap_pages*page_size - 1;
-	mmap_array[i][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
-			PROT_READ, MAP_SHARED, fd[i][counter], 0);
-	if (mmap_array[i][counter].base == MAP_FAILED)
-		die("failed to mmap with %d (%s)\n", errno, strerror(errno));
 }
 
 static int __cmd_top(void)
@@ -1204,12 +1287,12 @@
 	 * FIXME: perf_session__new should allow passing a O_MMAP, so that all this
 	 * mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
 	 */
-	struct perf_session *session = perf_session__new(NULL, O_WRONLY, false);
+	struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false);
 	if (session == NULL)
 		return -ENOMEM;
 
-	if (target_pid != -1)
-		event__synthesize_thread(target_pid, event__process, session);
+	if (target_tid != -1)
+		event__synthesize_thread(target_tid, event__process, session);
 	else
 		event__synthesize_threads(event__process, session);
 
@@ -1220,11 +1303,11 @@
 	}
 
 	/* Wait for a minimal set of events before starting the snapshot */
-	poll(event_array, nr_poll, 100);
+	poll(&event_array[0], nr_poll, 100);
 
 	perf_session__mmap_read(session);
 
-	if (pthread_create(&thread, NULL, display_thread, NULL)) {
+	if (pthread_create(&thread, NULL, display_thread, session)) {
 		printf("Could not create display thread.\n");
 		exit(-1);
 	}
@@ -1263,7 +1346,9 @@
 	OPT_INTEGER('c', "count", &default_interval,
 		    "event period to sample"),
 	OPT_INTEGER('p', "pid", &target_pid,
-		    "profile events on existing pid"),
+		    "profile events on existing process id"),
+	OPT_INTEGER('t', "tid", &target_tid,
+		    "profile events on existing thread id"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 			    "system-wide collection from all CPUs"),
 	OPT_INTEGER('C', "CPU", &profile_cpu,
@@ -1272,8 +1357,7 @@
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN('K', "hide_kernel_symbols", &hide_kernel_symbols,
 		    "hide kernel symbols"),
-	OPT_INTEGER('m', "mmap-pages", &mmap_pages,
-		    "number of mmap data pages"),
+	OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
 	OPT_INTEGER('r', "realtime", &realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
 	OPT_INTEGER('d', "delay", &delay_secs,
@@ -1296,7 +1380,7 @@
 		    "display this many functions"),
 	OPT_BOOLEAN('U', "hide_user_symbols", &hide_user_symbols,
 		    "hide user symbols"),
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_END()
 };
@@ -1304,6 +1388,7 @@
 int cmd_top(int argc, const char **argv, const char *prefix __used)
 {
 	int counter;
+	int i,j;
 
 	page_size = sysconf(_SC_PAGE_SIZE);
 
@@ -1311,8 +1396,39 @@
 	if (argc)
 		usage_with_options(top_usage, options);
 
+	if (target_pid != -1) {
+		target_tid = target_pid;
+		thread_num = find_all_tid(target_pid, &all_tids);
+		if (thread_num <= 0) {
+			fprintf(stderr, "Can't find all threads of pid %d\n",
+				target_pid);
+			usage_with_options(top_usage, options);
+		}
+	} else {
+		all_tids=malloc(sizeof(pid_t));
+		if (!all_tids)
+			return -ENOMEM;
+
+		all_tids[0] = target_tid;
+		thread_num = 1;
+	}
+
+	for (i = 0; i < MAX_NR_CPUS; i++) {
+		for (j = 0; j < MAX_COUNTERS; j++) {
+			fd[i][j] = malloc(sizeof(int)*thread_num);
+			mmap_array[i][j] = zalloc(
+				sizeof(struct mmap_data)*thread_num);
+			if (!fd[i][j] || !mmap_array[i][j])
+				return -ENOMEM;
+		}
+	}
+	event_array = malloc(
+		sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
+	if (!event_array)
+		return -ENOMEM;
+
 	/* CPU and PID are mutually exclusive */
-	if (target_pid != -1 && profile_cpu != -1) {
+	if (target_tid > 0 && profile_cpu != -1) {
 		printf("WARNING: PID switch overriding CPU\n");
 		sleep(1);
 		profile_cpu = -1;
@@ -1353,7 +1469,7 @@
 		attrs[counter].sample_period = default_interval;
 	}
 
-	if (target_pid != -1 || profile_cpu != -1)
+	if (target_tid != -1 || profile_cpu != -1)
 		nr_cpus = 1;
 	else
 		nr_cpus = read_cpu_map();

tools/perf/builtin-trace.c

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 407041d..dddf3f0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -11,6 +11,8 @@
 
 static char const		*script_name;
 static char const		*generate_script_lang;
+static bool			debug_ordering;
+static u64			last_timestamp;
 
 static int default_start_script(const char *script __unused,
 				int argc __unused,
@@ -51,6 +53,8 @@
 
 static int cleanup_scripting(void)
 {
+	pr_debug("\nperf trace script stopped\n");
+
 	return scripting_ops->stop_script();
 }
 
@@ -87,6 +91,14 @@
 	}
 
 	if (session->sample_type & PERF_SAMPLE_RAW) {
+		if (debug_ordering) {
+			if (data.time < last_timestamp) {
+				pr_err("Samples misordered, previous: %llu "
+					"this: %llu\n", last_timestamp,
+					data.time);
+			}
+			last_timestamp = data.time;
+		}
 		/*
 		 * FIXME: better resolve from pid from the struct trace_entry
 		 * field, although it should be the same than this perf
@@ -97,17 +109,31 @@
 					     data.time, thread->comm);
 	}
 
-	session->events_stats.total += data.period;
+	session->hists.stats.total_period += data.period;
 	return 0;
 }
 
 static struct perf_event_ops event_ops = {
 	.sample	= process_sample_event,
 	.comm	= event__process_comm,
+	.attr	= event__process_attr,
+	.event_type = event__process_event_type,
+	.tracing_data = event__process_tracing_data,
+	.build_id = event__process_build_id,
+	.ordered_samples = true,
 };
 
+extern volatile int session_done;
+
+static void sig_handler(int sig __unused)
+{
+	session_done = 1;
+}
+
 static int __cmd_trace(struct perf_session *session)
 {
+	signal(SIGINT, sig_handler);
+
 	return perf_session__process_events(session, &event_ops);
 }
 
@@ -505,7 +531,7 @@
 static const struct option options[] = {
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
-	OPT_BOOLEAN('v', "verbose", &verbose,
+	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('L', "Latency", &latency_format,
 		    "show latency attributes (irqs/preemption disabled, etc)"),
@@ -518,6 +544,8 @@
 		   "generate perf-trace.xx script in specified language"),
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
+	OPT_BOOLEAN('d', "debug-ordering", &debug_ordering,
+		   "check that samples time ordering is monotonic"),
 
 	OPT_END()
 };
@@ -548,6 +576,65 @@
 		suffix = REPORT_SUFFIX;
 	}
 
+	if (!suffix && argc >= 2 && strncmp(argv[1], "-", strlen("-")) != 0) {
+		char *record_script_path, *report_script_path;
+		int live_pipe[2];
+		pid_t pid;
+
+		record_script_path = get_script_path(argv[1], RECORD_SUFFIX);
+		if (!record_script_path) {
+			fprintf(stderr, "record script not found\n");
+			return -1;
+		}
+
+		report_script_path = get_script_path(argv[1], REPORT_SUFFIX);
+		if (!report_script_path) {
+			fprintf(stderr, "report script not found\n");
+			return -1;
+		}
+
+		if (pipe(live_pipe) < 0) {
+			perror("failed to create pipe");
+			exit(-1);
+		}
+
+		pid = fork();
+		if (pid < 0) {
+			perror("failed to fork");
+			exit(-1);
+		}
+
+		if (!pid) {
+			dup2(live_pipe[1], 1);
+			close(live_pipe[0]);
+
+			__argv = malloc(5 * sizeof(const char *));
+			__argv[0] = "/bin/sh";
+			__argv[1] = record_script_path;
+			__argv[2] = "-o";
+			__argv[3] = "-";
+			__argv[4] = NULL;
+
+			execvp("/bin/sh", (char **)__argv);
+			exit(-1);
+		}
+
+		dup2(live_pipe[0], 0);
+		close(live_pipe[1]);
+
+		__argv = malloc((argc + 3) * sizeof(const char *));
+		__argv[0] = "/bin/sh";
+		__argv[1] = report_script_path;
+		for (i = 2; i < argc; i++)
+			__argv[i] = argv[i];
+		__argv[i++] = "-i";
+		__argv[i++] = "-";
+		__argv[i++] = NULL;
+
+		execvp("/bin/sh", (char **)__argv);
+		exit(-1);
+	}
+
 	if (suffix) {
 		script_path = get_script_path(argv[2], suffix);
 		if (!script_path) {
@@ -576,11 +663,12 @@
 	if (!script_name)
 		setup_pager();
 
-	session = perf_session__new(input_name, O_RDONLY, 0);
+	session = perf_session__new(input_name, O_RDONLY, 0, false);
 	if (session == NULL)
 		return -ENOMEM;
 
-	if (!perf_session__has_traces(session, "record -R"))
+	if (strcmp(input_name, "-") &&
+	    !perf_session__has_traces(session, "record -R"))
 		return -EINVAL;
 
 	if (generate_script_lang) {
@@ -617,6 +705,7 @@
 		err = scripting_ops->start_script(script_name, argc, argv);
 		if (err)
 			goto out;
+		pr_debug("perf trace started with script %s\n\n", script_name);
 	}
 
 	err = __cmd_trace(session);

tools/perf/builtin.h

diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 10fe49e..921245b 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -32,5 +32,8 @@
 extern int cmd_probe(int argc, const char **argv, const char *prefix);
 extern int cmd_kmem(int argc, const char **argv, const char *prefix);
 extern int cmd_lock(int argc, const char **argv, const char *prefix);
+extern int cmd_kvm(int argc, const char **argv, const char *prefix);
+extern int cmd_test(int argc, const char **argv, const char *prefix);
+extern int cmd_inject(int argc, const char **argv, const char *prefix);
 
 #endif

tools/perf/command-list.txt

diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index db6ee94..949d77f 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -8,6 +8,7 @@
 perf-buildid-cache		mainporcelain common
 perf-buildid-list		mainporcelain common
 perf-diff			mainporcelain common
+perf-inject			mainporcelain common
 perf-list			mainporcelain common
 perf-sched			mainporcelain common
 perf-record			mainporcelain common
@@ -19,3 +20,5 @@
 perf-probe			mainporcelain common
 perf-kmem			mainporcelain common
 perf-lock			mainporcelain common
+perf-kvm			mainporcelain common
+perf-test			mainporcelain common

tools/perf/perf-archive.sh

diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 910468e..2e7a4f4 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -30,4 +30,7 @@
 
 tar cfj $PERF_DATA.tar.bz2 -C $DEBUGDIR -T $MANIFEST
 rm -f $MANIFEST $BUILDIDS
+echo -e "Now please run:\n"
+echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n"
+echo "wherever you need to run 'perf report' on."
 exit 0

tools/perf/perf.c

diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index cd32c20..08e0e5d 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -13,9 +13,10 @@
 #include "util/quote.h"
 #include "util/run-command.h"
 #include "util/parse-events.h"
-#include "util/string.h"
 #include "util/debugfs.h"
 
+bool use_browser;
+
 const char perf_usage_string[] =
 	"perf [--version] [--help] COMMAND [ARGS]";
 
@@ -262,6 +263,8 @@
 	set_debugfs_path();
 
 	status = p->fn(argc, argv, prefix);
+	exit_browser(status);
+
 	if (status)
 		return status & 0xff;
 
@@ -304,6 +307,9 @@
 		{ "probe",	cmd_probe,	0 },
 		{ "kmem",	cmd_kmem,	0 },
 		{ "lock",	cmd_lock,	0 },
+		{ "kvm",	cmd_kvm,	0 },
+		{ "test",	cmd_test,	0 },
+		{ "inject",	cmd_inject,	0 },
 	};
 	unsigned int i;
 	static const char ext[] = STRIP_EXTENSION;

tools/perf/perf.h

diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 6fb379b..ef7aa0a 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -1,6 +1,10 @@
 #ifndef _PERF_PERF_H
 #define _PERF_PERF_H
 
+struct winsize;
+
+void get_term_dimensions(struct winsize *ws);
+
 #if defined(__i386__)
 #include "../../arch/x86/include/asm/unistd.h"
 #define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
@@ -76,6 +80,7 @@
 
 #include "../../include/linux/perf_event.h"
 #include "util/types.h"
+#include <stdbool.h>
 
 /*
  * prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all
@@ -102,8 +107,6 @@
 #define __user
 #define asmlinkage
 
-#define __used		__attribute__((__unused__))
-
 #define unlikely(x)	__builtin_expect(!!(x), 0)
 #define min(x, y) ({				\
 	typeof(x) _min1 = (x);			\
@@ -129,4 +132,6 @@
 	u64 ips[0];
 };
 
+extern bool perf_host, perf_guest;
+
 #endif

tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm

diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
index f869c48..d94b40c 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
@@ -15,6 +15,7 @@
 
 our @EXPORT = qw(
 avg nsecs nsecs_secs nsecs_nsecs nsecs_usecs print_nsecs
+clear_term
 );
 
 our $VERSION = '0.01';
@@ -55,6 +56,11 @@
     return $str;
 }
 
+sub clear_term
+{
+    print "\x1b[H\x1b[2J";
+}
+
 1;
 __END__
 =head1 NAME

tools/perf/scripts/perl/bin/check-perf-trace-record

diff --git a/tools/perf/scripts/perl/bin/check-perf-trace-record b/tools/perf/scripts/perl/bin/check-perf-trace-record
index e6cb147..423ad6a 100644
--- a/tools/perf/scripts/perl/bin/check-perf-trace-record
+++ b/tools/perf/scripts/perl/bin/check-perf-trace-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e kmem:kmalloc -e irq:softirq_entry -e kmem:kfree
+perf record -a -e kmem:kmalloc -e irq:softirq_entry -e kmem:kfree

tools/perf/scripts/perl/bin/failed-syscalls-record

diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record
index f8885d3..eb5846b 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-record
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit
+perf record -a -e raw_syscalls:sys_exit $@

tools/perf/scripts/perl/bin/failed-syscalls-report

diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-report b/tools/perf/scripts/perl/bin/failed-syscalls-report
index 8bfc660..e3a5e55 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-report
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-report
@@ -1,4 +1,10 @@
 #!/bin/bash
 # description: system-wide failed syscalls
 # args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $1
+if [ $# -gt 0 ] ; then
+    if ! expr match "$1" "-" > /dev/null ; then
+	comm=$1
+	shift
+    fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $comm

tools/perf/scripts/perl/bin/rw-by-file-record

diff --git a/tools/perf/scripts/perl/bin/rw-by-file-record b/tools/perf/scripts/perl/bin/rw-by-file-record
index b25056e..5bfaae5 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-record
+++ b/tools/perf/scripts/perl/bin/rw-by-file-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_enter_write
+perf record -a -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
+

tools/perf/scripts/perl/bin/rw-by-file-report

diff --git a/tools/perf/scripts/perl/bin/rw-by-file-report b/tools/perf/scripts/perl/bin/rw-by-file-report
index eddb9cc..d83070b 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-report
+++ b/tools/perf/scripts/perl/bin/rw-by-file-report
@@ -1,7 +1,13 @@
 #!/bin/bash
 # description: r/w activity for a program, by file
 # args: <comm>
-perf trace -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl $1
+if [ $# -lt 1 ] ; then
+    echo "usage: rw-by-file <comm>"
+    exit
+fi
+comm=$1
+shift
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl $comm
 
 
 

tools/perf/scripts/perl/bin/rw-by-pid-record

diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-record b/tools/perf/scripts/perl/bin/rw-by-pid-record
index 8903979..6e0b2f7 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-record
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write
+perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@

tools/perf/scripts/perl/bin/rw-by-pid-report

diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-report b/tools/perf/scripts/perl/bin/rw-by-pid-report
index 7f44c25..7ef4698 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-report
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-report
@@ -1,6 +1,6 @@
 #!/bin/bash
 # description: system-wide r/w activity
-perf trace -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl
 
 
 

tools/perf/scripts/perl/bin/rwtop-record

diff --git a/tools/perf/scripts/perl/bin/rwtop-record b/tools/perf/scripts/perl/bin/rwtop-record
new file mode 100644
index 0000000..6e0b2f7
--- /dev/null
+++ b/tools/perf/scripts/perl/bin/rwtop-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@

tools/perf/scripts/perl/bin/rwtop-report

diff --git a/tools/perf/scripts/perl/bin/rwtop-report b/tools/perf/scripts/perl/bin/rwtop-report
new file mode 100644
index 0000000..93e698c
--- /dev/null
+++ b/tools/perf/scripts/perl/bin/rwtop-report
@@ -0,0 +1,23 @@
+#!/bin/bash
+# description: system-wide r/w top
+# args: [interval]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+	break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 1 ] ; then
+    echo "usage: rwtop-report [interval]"
+    exit
+fi
+if [ "$n_args" -gt 0 ] ; then
+    interval=$1
+    shift
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/rwtop.pl $interval
+
+
+

tools/perf/scripts/perl/bin/wakeup-latency-record

diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-record b/tools/perf/scripts/perl/bin/wakeup-latency-record
index 6abedda..9f2acaa 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-record
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-record
@@ -1,5 +1,5 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e sched:sched_switch -e sched:sched_wakeup
+perf record -a -e sched:sched_switch -e sched:sched_wakeup $@
 
 
 

tools/perf/scripts/perl/bin/wakeup-latency-report

diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-report b/tools/perf/scripts/perl/bin/wakeup-latency-report
index fce3adc..a0d898f 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-report
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-report
@@ -1,6 +1,6 @@
 #!/bin/bash
 # description: system-wide min/max/avg wakeup latency
-perf trace -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl
 
 
 

tools/perf/scripts/perl/bin/workqueue-stats-record

diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record
index fce6637..85301f2 100644
--- a/tools/perf/scripts/perl/bin/workqueue-stats-record
+++ b/tools/perf/scripts/perl/bin/workqueue-stats-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion
+perf record -a -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@

tools/perf/scripts/perl/bin/workqueue-stats-report

diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-report b/tools/perf/scripts/perl/bin/workqueue-stats-report
index 71cfbd1..3508113 100644
--- a/tools/perf/scripts/perl/bin/workqueue-stats-report
+++ b/tools/perf/scripts/perl/bin/workqueue-stats-report
@@ -1,6 +1,6 @@
 #!/bin/bash
 # description: workqueue stats (ins/exe/create/destroy)
-perf trace -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl
 
 
 

tools/perf/scripts/perl/failed-syscalls.pl

diff --git a/tools/perf/scripts/perl/failed-syscalls.pl b/tools/perf/scripts/perl/failed-syscalls.pl
index c18e7e2..94bc25a 100644
--- a/tools/perf/scripts/perl/failed-syscalls.pl
+++ b/tools/perf/scripts/perl/failed-syscalls.pl
@@ -11,6 +11,8 @@
 use Perf::Trace::Context;
 use Perf::Trace::Util;
 
+my $for_comm = shift;
+
 my %failed_syscalls;
 
 sub raw_syscalls::sys_exit
@@ -33,6 +35,8 @@
 
     foreach my $comm (sort {$failed_syscalls{$b} <=> $failed_syscalls{$a}}
 		      keys %failed_syscalls) {
-	    printf("%-20s  %10s\n", $comm, $failed_syscalls{$comm});
+	next if ($for_comm && $comm ne $for_comm);
+
+	printf("%-20s  %10s\n", $comm, $failed_syscalls{$comm});
     }
 }

tools/perf/scripts/perl/rw-by-pid.pl

diff --git a/tools/perf/scripts/perl/rw-by-pid.pl b/tools/perf/scripts/perl/rw-by-pid.pl
index da601fa..9db23c9 100644
--- a/tools/perf/scripts/perl/rw-by-pid.pl
+++ b/tools/perf/scripts/perl/rw-by-pid.pl
@@ -79,12 +79,12 @@
     printf("%6s  %-20s  %10s  %10s  %10s\n", "------", "--------------------",
 	   "-----------", "----------", "----------");
 
-    foreach my $pid (sort {$reads{$b}{bytes_read} <=>
-			       $reads{$a}{bytes_read}} keys %reads) {
-	my $comm = $reads{$pid}{comm};
-	my $total_reads = $reads{$pid}{total_reads};
-	my $bytes_requested = $reads{$pid}{bytes_requested};
-	my $bytes_read = $reads{$pid}{bytes_read};
+    foreach my $pid (sort { ($reads{$b}{bytes_read} || 0) <=>
+				($reads{$a}{bytes_read} || 0) } keys %reads) {
+	my $comm = $reads{$pid}{comm} || "";
+	my $total_reads = $reads{$pid}{total_reads} || 0;
+	my $bytes_requested = $reads{$pid}{bytes_requested} || 0;
+	my $bytes_read = $reads{$pid}{bytes_read} || 0;
 
 	printf("%6s  %-20s  %10s  %10s  %10s\n", $pid, $comm,
 	       $total_reads, $bytes_requested, $bytes_read);
@@ -96,16 +96,23 @@
     printf("%6s  %20s  %6s  %10s\n", "------", "--------------------",
 	   "------", "----------");
 
-    foreach my $pid (keys %reads) {
-	my $comm = $reads{$pid}{comm};
-	foreach my $err (sort {$reads{$b}{comm} cmp $reads{$a}{comm}}
-			 keys %{$reads{$pid}{errors}}) {
-	    my $errors = $reads{$pid}{errors}{$err};
+    my @errcounts = ();
 
-	    printf("%6d  %-20s  %6d  %10s\n", $pid, $comm, $err, $errors);
+    foreach my $pid (keys %reads) {
+	foreach my $error (keys %{$reads{$pid}{errors}}) {
+	    my $comm = $reads{$pid}{comm} || "";
+	    my $errcount = $reads{$pid}{errors}{$error} || 0;
+	    push @errcounts, [$pid, $comm, $error, $errcount];
 	}
     }
 
+    @errcounts = sort { $b->[3] <=> $a->[3] } @errcounts;
+
+    for my $i (0 .. $#errcounts) {
+	printf("%6d  %-20s  %6d  %10s\n", $errcounts[$i][0],
+	       $errcounts[$i][1], $errcounts[$i][2], $errcounts[$i][3]);
+    }
+
     printf("\nwrite counts by pid:\n\n");
 
     printf("%6s  %20s  %10s  %10s\n", "pid", "comm",
@@ -113,11 +120,11 @@
     printf("%6s  %-20s  %10s  %10s\n", "------", "--------------------",
 	   "-----------", "----------");
 
-    foreach my $pid (sort {$writes{$b}{bytes_written} <=>
-			       $writes{$a}{bytes_written}} keys %writes) {
-	my $comm = $writes{$pid}{comm};
-	my $total_writes = $writes{$pid}{total_writes};
-	my $bytes_written = $writes{$pid}{bytes_written};
+    foreach my $pid (sort { ($writes{$b}{bytes_written} || 0) <=>
+			($writes{$a}{bytes_written} || 0)} keys %writes) {
+	my $comm = $writes{$pid}{comm} || "";
+	my $total_writes = $writes{$pid}{total_writes} || 0;
+	my $bytes_written = $writes{$pid}{bytes_written} || 0;
 
 	printf("%6s  %-20s  %10s  %10s\n", $pid, $comm,
 	       $total_writes, $bytes_written);
@@ -129,16 +136,23 @@
     printf("%6s  %20s  %6s  %10s\n", "------", "--------------------",
 	   "------", "----------");
 
-    foreach my $pid (keys %writes) {
-	my $comm = $writes{$pid}{comm};
-	foreach my $err (sort {$writes{$b}{comm} cmp $writes{$a}{comm}}
-			 keys %{$writes{$pid}{errors}}) {
-	    my $errors = $writes{$pid}{errors}{$err};
+    @errcounts = ();
 
-	    printf("%6d  %-20s  %6d  %10s\n", $pid, $comm, $err, $errors);
+    foreach my $pid (keys %writes) {
+	foreach my $error (keys %{$writes{$pid}{errors}}) {
+	    my $comm = $writes{$pid}{comm} || "";
+	    my $errcount = $writes{$pid}{errors}{$error} || 0;
+	    push @errcounts, [$pid, $comm, $error, $errcount];
 	}
     }
 
+    @errcounts = sort { $b->[3] <=> $a->[3] } @errcounts;
+
+    for my $i (0 .. $#errcounts) {
+	printf("%6d  %-20s  %6d  %10s\n", $errcounts[$i][0],
+	       $errcounts[$i][1], $errcounts[$i][2], $errcounts[$i][3]);
+    }
+
     print_unhandled();
 }
 

tools/perf/scripts/perl/rwtop.pl

diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl
new file mode 100644
index 0000000..4bb3ecd
--- /dev/null
+++ b/tools/perf/scripts/perl/rwtop.pl
@@ -0,0 +1,199 @@
+#!/usr/bin/perl -w
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+
+# read/write top
+#
+# Periodically displays system-wide r/w call activity, broken down by
+# pid.  If an [interval] arg is specified, the display will be
+# refreshed every [interval] seconds.  The default interval is 3
+# seconds.
+
+use 5.010000;
+use strict;
+use warnings;
+
+use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+use lib "./Perf-Trace-Util/lib";
+use Perf::Trace::Core;
+use Perf::Trace::Util;
+
+my $default_interval = 3;
+my $nlines = 20;
+my $print_thread;
+my $print_pending = 0;
+
+my %reads;
+my %writes;
+
+my $interval = shift;
+if (!$interval) {
+    $interval = $default_interval;
+}
+
+sub syscalls::sys_exit_read
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm,
+	$nr, $ret) = @_;
+
+    print_check();
+
+    if ($ret > 0) {
+	$reads{$common_pid}{bytes_read} += $ret;
+    } else {
+	if (!defined ($reads{$common_pid}{bytes_read})) {
+	    $reads{$common_pid}{bytes_read} = 0;
+	}
+	$reads{$common_pid}{errors}{$ret}++;
+    }
+}
+
+sub syscalls::sys_enter_read
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm,
+	$nr, $fd, $buf, $count) = @_;
+
+    print_check();
+
+    $reads{$common_pid}{bytes_requested} += $count;
+    $reads{$common_pid}{total_reads}++;
+    $reads{$common_pid}{comm} = $common_comm;
+}
+
+sub syscalls::sys_exit_write
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm,
+	$nr, $ret) = @_;
+
+    print_check();
+
+    if ($ret <= 0) {
+	$writes{$common_pid}{errors}{$ret}++;
+    }
+}
+
+sub syscalls::sys_enter_write
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm,
+	$nr, $fd, $buf, $count) = @_;
+
+    print_check();
+
+    $writes{$common_pid}{bytes_written} += $count;
+    $writes{$common_pid}{total_writes}++;
+    $writes{$common_pid}{comm} = $common_comm;
+}
+
+sub trace_begin
+{
+    $SIG{ALRM} = \&set_print_pending;
+    alarm 1;
+}
+
+sub trace_end
+{
+    print_unhandled();
+    print_totals();
+}
+
+sub print_check()
+{
+    if ($print_pending == 1) {
+	$print_pending = 0;
+	print_totals();
+    }
+}
+
+sub set_print_pending()
+{
+    $print_pending = 1;
+    alarm $interval;
+}
+
+sub print_totals
+{
+    my $count;
+
+    $count = 0;
+
+    clear_term();
+
+    printf("\nread counts by pid:\n\n");
+
+    printf("%6s  %20s  %10s  %10s  %10s\n", "pid", "comm",
+	   "# reads", "bytes_req", "bytes_read");
+    printf("%6s  %-20s  %10s  %10s  %10s\n", "------", "--------------------",
+	   "----------", "----------", "----------");
+
+    foreach my $pid (sort { ($reads{$b}{bytes_read} || 0) <=>
+			       ($reads{$a}{bytes_read} || 0) } keys %reads) {
+	my $comm = $reads{$pid}{comm} || "";
+	my $total_reads = $reads{$pid}{total_reads} || 0;
+	my $bytes_requested = $reads{$pid}{bytes_requested} || 0;
+	my $bytes_read = $reads{$pid}{bytes_read} || 0;
+
+	printf("%6s  %-20s  %10s  %10s  %10s\n", $pid, $comm,
+	       $total_reads, $bytes_requested, $bytes_read);
+
+	if (++$count == $nlines) {
+	    last;
+	}
+    }
+
+    $count = 0;
+
+    printf("\nwrite counts by pid:\n\n");
+
+    printf("%6s  %20s  %10s  %13s\n", "pid", "comm",
+	   "# writes", "bytes_written");
+    printf("%6s  %-20s  %10s  %13s\n", "------", "--------------------",
+	   "----------", "-------------");
+
+    foreach my $pid (sort { ($writes{$b}{bytes_written} || 0) <=>
+			($writes{$a}{bytes_written} || 0)} keys %writes) {
+	my $comm = $writes{$pid}{comm} || "";
+	my $total_writes = $writes{$pid}{total_writes} || 0;
+	my $bytes_written = $writes{$pid}{bytes_written} || 0;
+
+	printf("%6s  %-20s  %10s  %13s\n", $pid, $comm,
+	       $total_writes, $bytes_written);
+
+	if (++$count == $nlines) {
+	    last;
+	}
+    }
+
+    %reads = ();
+    %writes = ();
+}
+
+my %unhandled;
+
+sub print_unhandled
+{
+    if ((scalar keys %unhandled) == 0) {
+	return;
+    }
+
+    print "\nunhandled events:\n\n";
+
+    printf("%-40s  %10s\n", "event", "count");
+    printf("%-40s  %10s\n", "----------------------------------------",
+	   "-----------");
+
+    foreach my $event_name (keys %unhandled) {
+	printf("%-40s  %10d\n", $event_name, $unhandled{$event_name});
+    }
+}
+
+sub trace_unhandled
+{
+    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+	$common_pid, $common_comm) = @_;
+
+    $unhandled{$event_name}++;
+}

tools/perf/scripts/perl/wakeup-latency.pl

diff --git a/tools/perf/scripts/perl/wakeup-latency.pl b/tools/perf/scripts/perl/wakeup-latency.pl
index ed58ef2..d9143dc 100644
--- a/tools/perf/scripts/perl/wakeup-latency.pl
+++ b/tools/perf/scripts/perl/wakeup-latency.pl
@@ -22,8 +22,8 @@
 
 my $max_wakeup_latency;
 my $min_wakeup_latency;
-my $total_wakeup_latency;
-my $total_wakeups;
+my $total_wakeup_latency = 0;
+my $total_wakeups = 0;
 
 sub sched::sched_switch
 {
@@ -67,8 +67,12 @@
 {
     printf("wakeup_latency stats:\n\n");
     print "total_wakeups: $total_wakeups\n";
-    printf("avg_wakeup_latency (ns): %u\n",
-	   avg($total_wakeup_latency, $total_wakeups));
+    if ($total_wakeups) {
+	printf("avg_wakeup_latency (ns): %u\n",
+	       avg($total_wakeup_latency, $total_wakeups));
+    } else {
+	printf("avg_wakeup_latency (ns): N/A\n");
+    }
     printf("min_wakeup_latency (ns): %u\n", $min_wakeup_latency);
     printf("max_wakeup_latency (ns): %u\n", $max_wakeup_latency);
 

tools/perf/scripts/perl/workqueue-stats.pl

diff --git a/tools/perf/scripts/perl/workqueue-stats.pl b/tools/perf/scripts/perl/workqueue-stats.pl
index 511302c..b84b126 100644
--- a/tools/perf/scripts/perl/workqueue-stats.pl
+++ b/tools/perf/scripts/perl/workqueue-stats.pl
@@ -71,9 +71,9 @@
     printf("%3s %6s %6s\t%-20s\n", "---", "---", "----", "----");
     foreach my $pidhash (@cpus) {
 	while ((my $pid, my $wqhash) = each %$pidhash) {
-	    my $ins = $$wqhash{'inserted'};
-	    my $exe = $$wqhash{'executed'};
-	    my $comm = $$wqhash{'comm'};
+	    my $ins = $$wqhash{'inserted'} || 0;
+	    my $exe = $$wqhash{'executed'} || 0;
+	    my $comm = $$wqhash{'comm'} || "";
 	    if ($ins || $exe) {
 		printf("%3u %6u %6u\t%-20s\n", $cpu, $ins, $exe, $comm);
 	    }
@@ -87,9 +87,9 @@
     printf("%3s %6s %6s\t%-20s\n", "---", "-------", "---------", "----");
     foreach my $pidhash (@cpus) {
 	while ((my $pid, my $wqhash) = each %$pidhash) {
-	    my $created = $$wqhash{'created'};
-	    my $destroyed = $$wqhash{'destroyed'};
-	    my $comm = $$wqhash{'comm'};
+	    my $created = $$wqhash{'created'} || 0;
+	    my $destroyed = $$wqhash{'destroyed'} || 0;
+	    my $comm = $$wqhash{'comm'} || "";
 	    if ($created || $destroyed) {
 		printf("%3u %6u %6u\t%-20s\n", $cpu, $created, $destroyed,
 		       $comm);

tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py

diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 83e9143..9689bc0 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -23,3 +23,6 @@
 def nsecs_str(nsecs):
     str = "%5u.%09u" % (nsecs_secs(nsecs), nsecs_nsecs(nsecs)),
     return str
+
+def clear_term():
+    print("\x1b[H\x1b[2J")

tools/perf/scripts/python/bin/failed-syscalls-by-pid-record

diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
index f8885d3..eb5846b 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit
+perf record -a -e raw_syscalls:sys_exit $@

tools/perf/scripts/python/bin/failed-syscalls-by-pid-report

diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
index 1e0c0a8..3029354 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
@@ -1,4 +1,10 @@
 #!/bin/bash
 # description: system-wide failed syscalls, by pid
 # args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $1
+if [ $# -gt 0 ] ; then
+    if ! expr match "$1" "-" > /dev/null ; then
+	comm=$1
+	shift
+    fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $comm

tools/perf/scripts/python/bin/sctop-record

diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record
new file mode 100644
index 0000000..1fc5998
--- /dev/null
+++ b/tools/perf/scripts/python/bin/sctop-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -a -e raw_syscalls:sys_enter $@

tools/perf/scripts/python/bin/sctop-report

diff --git a/tools/perf/scripts/python/bin/sctop-report b/tools/perf/scripts/python/bin/sctop-report
new file mode 100644
index 0000000..b01c842
--- /dev/null
+++ b/tools/perf/scripts/python/bin/sctop-report
@@ -0,0 +1,24 @@
+#!/bin/bash
+# description: syscall top
+# args: [comm] [interval]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+	break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 2 ] ; then
+    echo "usage: sctop-report [comm] [interval]"
+    exit
+fi
+if [ "$n_args" -gt 1 ] ; then
+    comm=$1
+    interval=$2
+    shift 2
+elif [ "$n_args" -gt 0 ] ; then
+    interval=$1
+    shift
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/sctop.py $comm $interval

tools/perf/scripts/python/bin/syscall-counts-by-pid-record

diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
index 45a8c50..1fc5998 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+perf record -a -e raw_syscalls:sys_enter $@

tools/perf/scripts/python/bin/syscall-counts-by-pid-report

diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
index f8044d1..9e9d8dd 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
@@ -1,4 +1,10 @@
 #!/bin/bash
 # description: system-wide syscall counts, by pid
 # args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $1
+if [ $# -gt 0 ] ; then
+    if ! expr match "$1" "-" > /dev/null ; then
+	comm=$1
+	shift
+    fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $comm

tools/perf/scripts/python/bin/syscall-counts-record

diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record
index 45a8c50..1fc5998 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+perf record -a -e raw_syscalls:sys_enter $@

tools/perf/scripts/python/bin/syscall-counts-report

diff --git a/tools/perf/scripts/python/bin/syscall-counts-report b/tools/perf/scripts/python/bin/syscall-counts-report
index a366aa61..dc076b6 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-report
+++ b/tools/perf/scripts/python/bin/syscall-counts-report
@@ -1,4 +1,10 @@
 #!/bin/bash
 # description: system-wide syscall counts
 # args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts.py $1
+if [ $# -gt 0 ] ; then
+    if ! expr match "$1" "-" > /dev/null ; then
+	comm=$1
+	shift
+    fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts.py $comm

tools/perf/scripts/python/sctop.py

diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py
new file mode 100644
index 0000000..6cafad4
--- /dev/null
+++ b/tools/perf/scripts/python/sctop.py
@@ -0,0 +1,78 @@
+# system call top
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Periodically displays system-wide system call totals, broken down by
+# syscall.  If a [comm] arg is specified, only syscalls called by
+# [comm] are displayed. If an [interval] arg is specified, the display
+# will be refreshed every [interval] seconds.  The default interval is
+# 3 seconds.
+
+import thread
+import time
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+usage = "perf trace -s syscall-counts.py [comm] [interval]\n";
+
+for_comm = None
+default_interval = 3
+interval = default_interval
+
+if len(sys.argv) > 3:
+	sys.exit(usage)
+
+if len(sys.argv) > 2:
+	for_comm = sys.argv[1]
+	interval = int(sys.argv[2])
+elif len(sys.argv) > 1:
+	try:
+		interval = int(sys.argv[1])
+	except ValueError:
+		for_comm = sys.argv[1]
+		interval = default_interval
+
+syscalls = autodict()
+
+def trace_begin():
+	thread.start_new_thread(print_syscall_totals, (interval,))
+	pass
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+	if for_comm is not None:
+		if common_comm != for_comm:
+			return
+	try:
+		syscalls[id] += 1
+	except TypeError:
+		syscalls[id] = 1
+
+def print_syscall_totals(interval):
+	while 1:
+		clear_term()
+		if for_comm is not None:
+			print "\nsyscall events for %s:\n\n" % (for_comm),
+		else:
+			print "\nsyscall events:\n\n",
+
+		print "%-40s  %10s\n" % ("event", "count"),
+		print "%-40s  %10s\n" % ("----------------------------------------", \
+						 "----------"),
+
+		for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \
+					      reverse = True):
+			try:
+				print "%-40d  %10d\n" % (id, val),
+			except TypeError:
+				pass
+		syscalls.clear()
+		time.sleep(interval)

tools/perf/util/PERF-VERSION-GEN

diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 54552a0..49ece79 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -1,6 +1,10 @@
 #!/bin/sh
 
-GVF=PERF-VERSION-FILE
+if [ $# -eq 1 ]  ; then
+	OUTPUT=$1
+fi
+
+GVF=${OUTPUT}PERF-VERSION-FILE
 DEF_VER=v0.0.2.PERF
 
 LF='

tools/perf/util/bitmap.c

diff --git a/tools/perf/util/bitmap.c b/tools/perf/util/bitmap.c
new file mode 100644
index 0000000..5e230ac
--- /dev/null
+++ b/tools/perf/util/bitmap.c
@@ -0,0 +1,21 @@
+/*
+ * From lib/bitmap.c
+ * Helper functions for bitmap.h.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+#include <linux/bitmap.h>
+
+int __bitmap_weight(const unsigned long *bitmap, int bits)
+{
+	int k, w = 0, lim = bits/BITS_PER_LONG;
+
+	for (k = 0; k < lim; k++)
+		w += hweight_long(bitmap[k]);
+
+	if (bits % BITS_PER_LONG)
+		w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
+
+	return w;
+}

tools/perf/util/build-id.c

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 04904b3..0f60a39 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -24,7 +24,7 @@
 	}
 
 	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
-			      event->ip.ip, &al);
+			      event->ip.pid, event->ip.ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;

tools/perf/util/cache.h

diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 918eb37..4b9aab7 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_CACHE_H
 #define __PERF_CACHE_H
 
+#include <stdbool.h>
 #include "util.h"
 #include "strbuf.h"
 #include "../perf.h"
@@ -69,6 +70,19 @@
 extern int pager_in_use(void);
 extern int pager_use_color;
 
+extern bool use_browser;
+
+#ifdef NO_NEWT_SUPPORT
+static inline void setup_browser(void)
+{
+	setup_pager();
+}
+static inline void exit_browser(bool wait_for_ok __used) {}
+#else
+void setup_browser(void);
+void exit_browser(bool wait_for_ok);
+#endif
+
 extern const char *editor_program;
 extern const char *excludes_file;
 

tools/perf/util/callchain.c

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index b3b7125..21a52e0 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com>
  *
  * Handle the callchains from the stream in an ad-hoc radix tree and then
  * sort them in an rbtree.
@@ -17,6 +17,13 @@
 
 #include "callchain.h"
 
+bool ip_callchain__valid(struct ip_callchain *chain, event_t *event)
+{
+	unsigned int chain_size = event->header.size;
+	chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
+	return chain->nr * sizeof(u64) <= chain_size;
+}
+
 #define chain_for_each_child(child, parent)	\
 	list_for_each_entry(child, &parent->children, brothers)
 
@@ -160,7 +167,7 @@
 {
 	struct callchain_node *new;
 
-	new = malloc(sizeof(*new));
+	new = zalloc(sizeof(*new));
 	if (!new) {
 		perror("not enough memory to create child for code path tree");
 		return NULL;
@@ -183,25 +190,36 @@
 	return new;
 }
 
+
+struct resolved_ip {
+	u64		  ip;
+	struct map_symbol ms;
+};
+
+struct resolved_chain {
+	u64			nr;
+	struct resolved_ip	ips[0];
+};
+
+
 /*
  * Fill the node with callchain values
  */
 static void
-fill_node(struct callchain_node *node, struct ip_callchain *chain,
-	  int start, struct symbol **syms)
+fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
 {
 	unsigned int i;
 
 	for (i = start; i < chain->nr; i++) {
 		struct callchain_list *call;
 
-		call = malloc(sizeof(*call));
+		call = zalloc(sizeof(*call));
 		if (!call) {
 			perror("not enough memory for the code path tree");
 			return;
 		}
-		call->ip = chain->ips[i];
-		call->sym = syms[i];
+		call->ip = chain->ips[i].ip;
+		call->ms = chain->ips[i].ms;
 		list_add_tail(&call->list, &node->val);
 	}
 	node->val_nr = chain->nr - start;
@@ -210,13 +228,13 @@
 }
 
 static void
-add_child(struct callchain_node *parent, struct ip_callchain *chain,
-	  int start, struct symbol **syms)
+add_child(struct callchain_node *parent, struct resolved_chain *chain,
+	  int start)
 {
 	struct callchain_node *new;
 
 	new = create_child(parent, false);
-	fill_node(new, chain, start, syms);
+	fill_node(new, chain, start);
 
 	new->children_hit = 0;
 	new->hit = 1;
@@ -228,9 +246,8 @@
  * Then create another child to host the given callchain of new branch
  */
 static void
-split_add_child(struct callchain_node *parent, struct ip_callchain *chain,
-		struct callchain_list *to_split, int idx_parents, int idx_local,
-		struct symbol **syms)
+split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
+		struct callchain_list *to_split, int idx_parents, int idx_local)
 {
 	struct callchain_node *new;
 	struct list_head *old_tail;
@@ -257,7 +274,7 @@
 	/* create a new child for the new branch if any */
 	if (idx_total < chain->nr) {
 		parent->hit = 0;
-		add_child(parent, chain, idx_total, syms);
+		add_child(parent, chain, idx_total);
 		parent->children_hit++;
 	} else {
 		parent->hit = 1;
@@ -265,32 +282,33 @@
 }
 
 static int
-__append_chain(struct callchain_node *root, struct ip_callchain *chain,
-	       unsigned int start, struct symbol **syms);
+__append_chain(struct callchain_node *root, struct resolved_chain *chain,
+	       unsigned int start);
 
 static void
-__append_chain_children(struct callchain_node *root, struct ip_callchain *chain,
-			struct symbol **syms, unsigned int start)
+__append_chain_children(struct callchain_node *root,
+			struct resolved_chain *chain,
+			unsigned int start)
 {
 	struct callchain_node *rnode;
 
 	/* lookup in childrens */
 	chain_for_each_child(rnode, root) {
-		unsigned int ret = __append_chain(rnode, chain, start, syms);
+		unsigned int ret = __append_chain(rnode, chain, start);
 
 		if (!ret)
 			goto inc_children_hit;
 	}
 	/* nothing in children, add to the current node */
-	add_child(root, chain, start, syms);
+	add_child(root, chain, start);
 
 inc_children_hit:
 	root->children_hit++;
 }
 
 static int
-__append_chain(struct callchain_node *root, struct ip_callchain *chain,
-	       unsigned int start, struct symbol **syms)
+__append_chain(struct callchain_node *root, struct resolved_chain *chain,
+	       unsigned int start)
 {
 	struct callchain_list *cnode;
 	unsigned int i = start;
@@ -302,13 +320,19 @@
 	 * anywhere inside a function.
 	 */
 	list_for_each_entry(cnode, &root->val, list) {
+		struct symbol *sym;
+
 		if (i == chain->nr)
 			break;
-		if (cnode->sym && syms[i]) {
-			if (cnode->sym->start != syms[i]->start)
+
+		sym = chain->ips[i].ms.sym;
+
+		if (cnode->ms.sym && sym) {
+			if (cnode->ms.sym->start != sym->start)
 				break;
-		} else if (cnode->ip != chain->ips[i])
+		} else if (cnode->ip != chain->ips[i].ip)
 			break;
+
 		if (!found)
 			found = true;
 		i++;
@@ -320,7 +344,7 @@
 
 	/* we match only a part of the node. Split it and add the new chain */
 	if (i - start < root->val_nr) {
-		split_add_child(root, chain, cnode, start, i - start, syms);
+		split_add_child(root, chain, cnode, start, i - start);
 		return 0;
 	}
 
@@ -331,15 +355,50 @@
 	}
 
 	/* We match the node and still have a part remaining */
-	__append_chain_children(root, chain, syms, i);
+	__append_chain_children(root, chain, i);
 
 	return 0;
 }
 
-void append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		  struct symbol **syms)
+static void filter_context(struct ip_callchain *old, struct resolved_chain *new,
+			   struct map_symbol *syms)
 {
+	int i, j = 0;
+
+	for (i = 0; i < (int)old->nr; i++) {
+		if (old->ips[i] >= PERF_CONTEXT_MAX)
+			continue;
+
+		new->ips[j].ip = old->ips[i];
+		new->ips[j].ms = syms[i];
+		j++;
+	}
+
+	new->nr = j;
+}
+
+
+int append_chain(struct callchain_node *root, struct ip_callchain *chain,
+		 struct map_symbol *syms)
+{
+	struct resolved_chain *filtered;
+
 	if (!chain->nr)
-		return;
-	__append_chain_children(root, chain, syms, 0);
+		return 0;
+
+	filtered = zalloc(sizeof(*filtered) +
+			  chain->nr * sizeof(struct resolved_ip));
+	if (!filtered)
+		return -ENOMEM;
+
+	filter_context(chain, filtered, syms);
+
+	if (!filtered->nr)
+		goto end;
+
+	__append_chain_children(root, filtered, 0);
+end:
+	free(filtered);
+
+	return 0;
 }

tools/perf/util/callchain.h

diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index ad4626d..1cba1f5 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -4,6 +4,7 @@
 #include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include "event.h"
 #include "util.h"
 #include "symbol.h"
 
@@ -33,13 +34,14 @@
 
 struct callchain_param {
 	enum chain_mode 	mode;
+	u32			print_limit;
 	double			min_percent;
 	sort_chain_func_t	sort;
 };
 
 struct callchain_list {
 	u64			ip;
-	struct symbol		*sym;
+	struct map_symbol	ms;
 	struct list_head	list;
 };
 
@@ -56,6 +58,8 @@
 }
 
 int register_callchain_param(struct callchain_param *param);
-void append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		  struct symbol **syms);
+int append_chain(struct callchain_node *root, struct ip_callchain *chain,
+		 struct map_symbol *syms);
+
+bool ip_callchain__valid(struct ip_callchain *chain, event_t *event);
 #endif	/* __PERF_CALLCHAIN_H */

tools/perf/util/color.c

diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index e88bca5..e191eb9 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -166,6 +166,31 @@
 	return perf_default_config(var, value, cb);
 }
 
+static int __color_vsnprintf(char *bf, size_t size, const char *color,
+			     const char *fmt, va_list args, const char *trail)
+{
+	int r = 0;
+
+	/*
+	 * Auto-detect:
+	 */
+	if (perf_use_color_default < 0) {
+		if (isatty(1) || pager_in_use())
+			perf_use_color_default = 1;
+		else
+			perf_use_color_default = 0;
+	}
+
+	if (perf_use_color_default && *color)
+		r += snprintf(bf, size, "%s", color);
+	r += vsnprintf(bf + r, size - r, fmt, args);
+	if (perf_use_color_default && *color)
+		r += snprintf(bf + r, size - r, "%s", PERF_COLOR_RESET);
+	if (trail)
+		r += snprintf(bf + r, size - r, "%s", trail);
+	return r;
+}
+
 static int __color_vfprintf(FILE *fp, const char *color, const char *fmt,
 		va_list args, const char *trail)
 {
@@ -191,11 +216,28 @@
 	return r;
 }
 
+int color_vsnprintf(char *bf, size_t size, const char *color,
+		    const char *fmt, va_list args)
+{
+	return __color_vsnprintf(bf, size, color, fmt, args, NULL);
+}
+
 int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args)
 {
 	return __color_vfprintf(fp, color, fmt, args, NULL);
 }
 
+int color_snprintf(char *bf, size_t size, const char *color,
+		   const char *fmt, ...)
+{
+	va_list args;
+	int r;
+
+	va_start(args, fmt);
+	r = color_vsnprintf(bf, size, color, fmt, args);
+	va_end(args);
+	return r;
+}
 
 int color_fprintf(FILE *fp, const char *color, const char *fmt, ...)
 {
@@ -274,3 +316,9 @@
 
 	return r;
 }
+
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent)
+{
+	const char *color = get_percent_color(percent);
+	return color_snprintf(bf, size, color, fmt, percent);
+}

tools/perf/util/color.h

diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 24e8809..dea082b 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -32,10 +32,14 @@
 int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty);
 void color_parse(const char *value, const char *var, char *dst);
 void color_parse_mem(const char *value, int len, const char *var, char *dst);
+int color_vsnprintf(char *bf, size_t size, const char *color,
+		    const char *fmt, va_list args);
 int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args);
 int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
+int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
 int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
 

tools/perf/util/debug.c

diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 0905600..dd824cf 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -6,13 +6,14 @@
 #include <stdarg.h>
 #include <stdio.h>
 
+#include "cache.h"
 #include "color.h"
 #include "event.h"
 #include "debug.h"
 #include "util.h"
 
 int verbose = 0;
-int dump_trace = 0;
+bool dump_trace = false;
 
 int eprintf(int level, const char *fmt, ...)
 {
@@ -21,7 +22,10 @@
 
 	if (verbose >= level) {
 		va_start(args, fmt);
-		ret = vfprintf(stderr, fmt, args);
+		if (use_browser)
+			ret = browser__show_help(fmt, args);
+		else
+			ret = vfprintf(stderr, fmt, args);
 		va_end(args);
 	}
 

tools/perf/util/debug.h

diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index c6c24c5..047ac33 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -2,14 +2,38 @@
 #ifndef __PERF_DEBUG_H
 #define __PERF_DEBUG_H
 
+#include <stdbool.h>
 #include "event.h"
 
 extern int verbose;
-extern int dump_trace;
+extern bool dump_trace;
 
-int eprintf(int level,
-	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(event_t *event);
 
+struct ui_progress;
+
+#ifdef NO_NEWT_SUPPORT
+static inline int browser__show_help(const char *format __used, va_list ap __used)
+{
+	return 0;
+}
+
+static inline struct ui_progress *ui_progress__new(const char *title __used,
+						   u64 total __used)
+{
+	return (struct ui_progress *)1;
+}
+
+static inline void ui_progress__update(struct ui_progress *self __used,
+				       u64 curr __used) {}
+
+static inline void ui_progress__delete(struct ui_progress *self __used) {}
+#else
+int browser__show_help(const char *format, va_list ap);
+struct ui_progress *ui_progress__new(const char *title, u64 total);
+void ui_progress__update(struct ui_progress *self, u64 curr);
+void ui_progress__delete(struct ui_progress *self);
+#endif
+
 #endif	/* __PERF_DEBUG_H */

tools/perf/util/event.c

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 705ec63..50771b5 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -7,6 +7,23 @@
 #include "strlist.h"
 #include "thread.h"
 
+const char *event__name[] = {
+	[0]			 = "TOTAL",
+	[PERF_RECORD_MMAP]	 = "MMAP",
+	[PERF_RECORD_LOST]	 = "LOST",
+	[PERF_RECORD_COMM]	 = "COMM",
+	[PERF_RECORD_EXIT]	 = "EXIT",
+	[PERF_RECORD_THROTTLE]	 = "THROTTLE",
+	[PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
+	[PERF_RECORD_FORK]	 = "FORK",
+	[PERF_RECORD_READ]	 = "READ",
+	[PERF_RECORD_SAMPLE]	 = "SAMPLE",
+	[PERF_RECORD_HEADER_ATTR]	 = "ATTR",
+	[PERF_RECORD_HEADER_EVENT_TYPE]	 = "EVENT_TYPE",
+	[PERF_RECORD_HEADER_TRACING_DATA]	 = "TRACING_DATA",
+	[PERF_RECORD_HEADER_BUILD_ID]	 = "BUILD_ID",
+};
+
 static pid_t event__synthesize_comm(pid_t pid, int full,
 				    event__handler_t process,
 				    struct perf_session *session)
@@ -112,7 +129,11 @@
 		event_t ev = {
 			.header = {
 				.type = PERF_RECORD_MMAP,
-				.misc = 0, /* Just like the kernel, see kernel/perf_event.c __perf_event_mmap */
+				/*
+				 * Just like the kernel, see __perf_event_mmap
+				 * in kernel/perf_event.c
+				 */
+				.misc = PERF_RECORD_MISC_USER,
 			 },
 		};
 		int n;
@@ -130,6 +151,7 @@
 			continue;
 		pbf += n + 3;
 		if (*pbf == 'x') { /* vm_exec */
+			u64 vm_pgoff;
 			char *execname = strchr(bf, '/');
 
 			/* Catch VDSO */
@@ -139,6 +161,14 @@
 			if (execname == NULL)
 				continue;
 
+			pbf += 3;
+			n = hex2u64(pbf, &vm_pgoff);
+			/* pgoff is in bytes, not pages */
+			if (n >= 0)
+				ev.mmap.pgoff = vm_pgoff << getpagesize();
+			else
+				ev.mmap.pgoff = 0;
+
 			size = strlen(execname);
 			execname[size - 1] = '\0'; /* Remove \n */
 			memcpy(ev.mmap.filename, execname, size);
@@ -158,11 +188,23 @@
 }
 
 int event__synthesize_modules(event__handler_t process,
-			      struct perf_session *session)
+			      struct perf_session *session,
+			      struct machine *machine)
 {
 	struct rb_node *nd;
+	struct map_groups *kmaps = &machine->kmaps;
+	u16 misc;
 
-	for (nd = rb_first(&session->kmaps.maps[MAP__FUNCTION]);
+	/*
+	 * kernel uses 0 for user space maps, see kernel/perf_event.c
+	 * __perf_event_mmap
+	 */
+	if (machine__is_host(machine))
+		misc = PERF_RECORD_MISC_KERNEL;
+	else
+		misc = PERF_RECORD_MISC_GUEST_KERNEL;
+
+	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
 	     nd; nd = rb_next(nd)) {
 		event_t ev;
 		size_t size;
@@ -173,12 +215,13 @@
 
 		size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
 		memset(&ev, 0, sizeof(ev));
-		ev.mmap.header.misc = 1; /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */
+		ev.mmap.header.misc = misc;
 		ev.mmap.header.type = PERF_RECORD_MMAP;
 		ev.mmap.header.size = (sizeof(ev.mmap) -
 				        (sizeof(ev.mmap.filename) - size));
 		ev.mmap.start = pos->start;
 		ev.mmap.len   = pos->end - pos->start;
+		ev.mmap.pid   = machine->pid;
 
 		memcpy(ev.mmap.filename, pos->dso->long_name,
 		       pos->dso->long_name_len + 1);
@@ -241,13 +284,18 @@
 
 int event__synthesize_kernel_mmap(event__handler_t process,
 				  struct perf_session *session,
+				  struct machine *machine,
 				  const char *symbol_name)
 {
 	size_t size;
+	const char *filename, *mmap_name;
+	char path[PATH_MAX];
+	char name_buff[PATH_MAX];
+	struct map *map;
+
 	event_t ev = {
 		.header = {
 			.type = PERF_RECORD_MMAP,
-			.misc = 1, /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */
 		},
 	};
 	/*
@@ -257,16 +305,37 @@
 	 */
 	struct process_symbol_args args = { .name = symbol_name, };
 
-	if (kallsyms__parse("/proc/kallsyms", &args, find_symbol_cb) <= 0)
+	mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff));
+	if (machine__is_host(machine)) {
+		/*
+		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
+		 * see kernel/perf_event.c __perf_event_mmap
+		 */
+		ev.header.misc = PERF_RECORD_MISC_KERNEL;
+		filename = "/proc/kallsyms";
+	} else {
+		ev.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)
 		return -ENOENT;
 
+	map = machine->vmlinux_maps[MAP__FUNCTION];
 	size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename),
-			"[kernel.kallsyms.%s]", symbol_name) + 1;
+			"%s%s", mmap_name, symbol_name) + 1;
 	size = ALIGN(size, sizeof(u64));
-	ev.mmap.header.size = (sizeof(ev.mmap) - (sizeof(ev.mmap.filename) - size));
+	ev.mmap.header.size = (sizeof(ev.mmap) -
+			(sizeof(ev.mmap.filename) - size));
 	ev.mmap.pgoff = args.start;
-	ev.mmap.start = session->vmlinux_maps[MAP__FUNCTION]->start;
-	ev.mmap.len   = session->vmlinux_maps[MAP__FUNCTION]->end - ev.mmap.start ;
+	ev.mmap.start = map->start;
+	ev.mmap.len   = map->end - ev.mmap.start;
+	ev.mmap.pid   = machine->pid;
 
 	return process(&ev, session);
 }
@@ -316,26 +385,54 @@
 int event__process_lost(event_t *self, struct perf_session *session)
 {
 	dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost);
-	session->events_stats.lost += self->lost.lost;
+	session->hists.stats.total_lost += self->lost.lost;
 	return 0;
 }
 
-int event__process_mmap(event_t *self, struct perf_session *session)
+static void event_set_kernel_mmap_len(struct map **maps, event_t *self)
 {
-	struct thread *thread;
+	maps[MAP__FUNCTION]->start = self->mmap.start;
+	maps[MAP__FUNCTION]->end   = self->mmap.start + self->mmap.len;
+	/*
+	 * Be a bit paranoid here, some perf.data file came with
+	 * a zero sized synthesized MMAP event for the kernel.
+	 */
+	if (maps[MAP__FUNCTION]->end == 0)
+		maps[MAP__FUNCTION]->end = ~0UL;
+}
+
+static int event__process_kernel_mmap(event_t *self,
+			struct perf_session *session)
+{
 	struct map *map;
+	char kmmap_prefix[PATH_MAX];
+	struct machine *machine;
+	enum dso_kernel_type kernel_type;
+	bool is_kernel_mmap;
 
-	dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n",
-		    self->mmap.pid, self->mmap.tid, self->mmap.start,
-		    self->mmap.len, self->mmap.pgoff, self->mmap.filename);
+	machine = perf_session__findnew_machine(session, self->mmap.pid);
+	if (!machine) {
+		pr_err("Can't find id %d's machine\n", self->mmap.pid);
+		goto out_problem;
+	}
 
-	if (self->mmap.pid == 0) {
-		static const char kmmap_prefix[] = "[kernel.kallsyms.";
+	machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
+	if (machine__is_host(machine))
+		kernel_type = DSO_TYPE_KERNEL;
+	else
+		kernel_type = DSO_TYPE_GUEST_KERNEL;
+
+	is_kernel_mmap = memcmp(self->mmap.filename,
+				kmmap_prefix,
+				strlen(kmmap_prefix)) == 0;
+	if (self->mmap.filename[0] == '/' ||
+	    (!is_kernel_mmap && self->mmap.filename[0] == '[')) {
+
+		char short_module_name[1024];
+		char *name, *dot;
 
 		if (self->mmap.filename[0] == '/') {
-			char short_module_name[1024];
-			char *name = strrchr(self->mmap.filename, '/'), *dot;
-
+			name = strrchr(self->mmap.filename, '/');
 			if (name == NULL)
 				goto out_problem;
 
@@ -343,58 +440,84 @@
 			dot = strrchr(name, '.');
 			if (dot == NULL)
 				goto out_problem;
-
 			snprintf(short_module_name, sizeof(short_module_name),
-				 "[%.*s]", (int)(dot - name), name);
+					"[%.*s]", (int)(dot - name), name);
 			strxfrchar(short_module_name, '-', '_');
+		} else
+			strcpy(short_module_name, self->mmap.filename);
 
-			map = perf_session__new_module_map(session,
-							   self->mmap.start,
-							   self->mmap.filename);
-			if (map == NULL)
-				goto out_problem;
+		map = machine__new_module(machine, self->mmap.start,
+					  self->mmap.filename);
+		if (map == NULL)
+			goto out_problem;
 
-			name = strdup(short_module_name);
-			if (name == NULL)
-				goto out_problem;
+		name = strdup(short_module_name);
+		if (name == NULL)
+			goto out_problem;
 
-			map->dso->short_name = name;
-			map->end = map->start + self->mmap.len;
-		} else if (memcmp(self->mmap.filename, kmmap_prefix,
-				sizeof(kmmap_prefix) - 1) == 0) {
-			const char *symbol_name = (self->mmap.filename +
-						   sizeof(kmmap_prefix) - 1);
+		map->dso->short_name = name;
+		map->end = map->start + self->mmap.len;
+	} else if (is_kernel_mmap) {
+		const char *symbol_name = (self->mmap.filename +
+				strlen(kmmap_prefix));
+		/*
+		 * Should be there already, from the build-id table in
+		 * the header.
+		 */
+		struct dso *kernel = __dsos__findnew(&machine->kernel_dsos,
+						     kmmap_prefix);
+		if (kernel == NULL)
+			goto out_problem;
+
+		kernel->kernel = kernel_type;
+		if (__machine__create_kernel_maps(machine, kernel) < 0)
+			goto out_problem;
+
+		event_set_kernel_mmap_len(machine->vmlinux_maps, self);
+		perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+							 symbol_name,
+							 self->mmap.pgoff);
+		if (machine__is_default_guest(machine)) {
 			/*
-			 * Should be there already, from the build-id table in
-			 * the header.
+			 * preload dso of guest kernel and modules
 			 */
-			struct dso *kernel = __dsos__findnew(&dsos__kernel,
-							     "[kernel.kallsyms]");
-			if (kernel == NULL)
-				goto out_problem;
-
-			kernel->kernel = 1;
-			if (__perf_session__create_kernel_maps(session, kernel) < 0)
-				goto out_problem;
-
-			session->vmlinux_maps[MAP__FUNCTION]->start = self->mmap.start;
-			session->vmlinux_maps[MAP__FUNCTION]->end   = self->mmap.start + self->mmap.len;
-			/*
-			 * Be a bit paranoid here, some perf.data file came with
-			 * a zero sized synthesized MMAP event for the kernel.
-			 */
-			if (session->vmlinux_maps[MAP__FUNCTION]->end == 0)
-				session->vmlinux_maps[MAP__FUNCTION]->end = ~0UL;
-
-			perf_session__set_kallsyms_ref_reloc_sym(session, symbol_name,
-								 self->mmap.pgoff);
+			dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION],
+				  NULL);
 		}
+	}
+	return 0;
+out_problem:
+	return -1;
+}
+
+int event__process_mmap(event_t *self, struct perf_session *session)
+{
+	struct machine *machine;
+	struct thread *thread;
+	struct map *map;
+	u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	int ret = 0;
+
+	dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n",
+			self->mmap.pid, self->mmap.tid, self->mmap.start,
+			self->mmap.len, self->mmap.pgoff, self->mmap.filename);
+
+	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	    cpumode == PERF_RECORD_MISC_KERNEL) {
+		ret = event__process_kernel_mmap(self, session);
+		if (ret < 0)
+			goto out_problem;
 		return 0;
 	}
 
+	machine = perf_session__find_host_machine(session);
+	if (machine == NULL)
+		goto out_problem;
 	thread = perf_session__findnew(session, self->mmap.pid);
-	map = map__new(&self->mmap, MAP__FUNCTION,
-		       session->cwd, session->cwdlen);
+	map = map__new(&machine->user_dsos, self->mmap.start,
+			self->mmap.len, self->mmap.pgoff,
+			self->mmap.pid, self->mmap.filename,
+			MAP__FUNCTION, session->cwd, session->cwdlen);
 
 	if (thread == NULL || map == NULL)
 		goto out_problem;
@@ -434,22 +557,56 @@
 
 void thread__find_addr_map(struct thread *self,
 			   struct perf_session *session, u8 cpumode,
-			   enum map_type type, u64 addr,
+			   enum map_type type, pid_t pid, u64 addr,
 			   struct addr_location *al)
 {
 	struct map_groups *mg = &self->mg;
+	struct machine *machine = NULL;
 
 	al->thread = self;
 	al->addr = addr;
+	al->cpumode = cpumode;
+	al->filtered = false;
 
-	if (cpumode == PERF_RECORD_MISC_KERNEL) {
+	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
 		al->level = 'k';
-		mg = &session->kmaps;
-	} else if (cpumode == PERF_RECORD_MISC_USER)
+		machine = perf_session__find_host_machine(session);
+		if (machine == NULL) {
+			al->map = NULL;
+			return;
+		}
+		mg = &machine->kmaps;
+	} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
 		al->level = '.';
-	else {
-		al->level = 'H';
+		machine = perf_session__find_host_machine(session);
+	} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
+		al->level = 'g';
+		machine = perf_session__find_machine(session, pid);
+		if (machine == NULL) {
+			al->map = NULL;
+			return;
+		}
+		mg = &machine->kmaps;
+	} else {
+		/*
+		 * 'u' means guest os user space.
+		 * TODO: We don't support guest user space. Might support late.
+		 */
+		if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest)
+			al->level = 'u';
+		else
+			al->level = 'H';
 		al->map = NULL;
+
+		if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
+			cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
+			!perf_guest)
+			al->filtered = true;
+		if ((cpumode == PERF_RECORD_MISC_USER ||
+			cpumode == PERF_RECORD_MISC_KERNEL) &&
+			!perf_host)
+			al->filtered = true;
+
 		return;
 	}
 try_again:
@@ -464,8 +621,10 @@
 		 * "[vdso]" dso, but for now lets use the old trick of looking
 		 * in the whole kernel symbol list.
 		 */
-		if ((long long)al->addr < 0 && mg != &session->kmaps) {
-			mg = &session->kmaps;
+		if ((long long)al->addr < 0 &&
+		    cpumode == PERF_RECORD_MISC_KERNEL &&
+		    machine && mg != &machine->kmaps) {
+			mg = &machine->kmaps;
 			goto try_again;
 		}
 	} else
@@ -474,11 +633,11 @@
 
 void thread__find_addr_location(struct thread *self,
 				struct perf_session *session, u8 cpumode,
-				enum map_type type, u64 addr,
+				enum map_type type, pid_t pid, u64 addr,
 				struct addr_location *al,
 				symbol_filter_t filter)
 {
-	thread__find_addr_map(self, session, cpumode, type, addr, al);
+	thread__find_addr_map(self, session, cpumode, type, pid, addr, al);
 	if (al->map != NULL)
 		al->sym = map__find_symbol(al->map, al->addr, filter);
 	else
@@ -490,8 +649,10 @@
 	if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
 	    (!symbol_conf.dso_list ||
 	     strlist__has_entry(symbol_conf.dso_list, self->name))) {
-		unsigned int slen = strlen(self->name);
-		if (slen > dsos__col_width)
+		u16 slen = self->short_name_len;
+		if (verbose)
+			slen = self->long_name_len;
+		if (dsos__col_width < slen)
 			dsos__col_width = slen;
 	}
 
@@ -512,31 +673,55 @@
 		goto out_filtered;
 
 	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	/*
+	 * Have we already created the kernel maps for the host machine?
+	 *
+	 * This should have happened earlier, when we processed the kernel MMAP
+	 * events, but for older perf.data files there was no such thing, so do
+	 * it now.
+	 */
+	if (cpumode == PERF_RECORD_MISC_KERNEL &&
+	    session->host_machine.vmlinux_maps[MAP__FUNCTION] == NULL)
+		machine__create_kernel_maps(&session->host_machine);
 
-	thread__find_addr_location(thread, session, cpumode, MAP__FUNCTION,
-				   self->ip.ip, al, filter);
+	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
+			      self->ip.pid, self->ip.ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
-	/*
-	 * We have to do this here as we may have a dso with no symbol hit that
-	 * has a name longer than the ones with symbols sampled.
-	 */
-	if (al->map && !sort_dso.elide && !al->map->dso->slen_calculated)
-		dso__calc_col_width(al->map->dso);
+	al->sym = NULL;
 
-	if (symbol_conf.dso_list &&
-	    (!al->map || !al->map->dso ||
-	     !(strlist__has_entry(symbol_conf.dso_list, al->map->dso->short_name) ||
-	       (al->map->dso->short_name != al->map->dso->long_name &&
-		strlist__has_entry(symbol_conf.dso_list, al->map->dso->long_name)))))
-		goto out_filtered;
+	if (al->map) {
+		if (symbol_conf.dso_list &&
+		    (!al->map || !al->map->dso ||
+		     !(strlist__has_entry(symbol_conf.dso_list,
+					  al->map->dso->short_name) ||
+		       (al->map->dso->short_name != al->map->dso->long_name &&
+			strlist__has_entry(symbol_conf.dso_list,
+					   al->map->dso->long_name)))))
+			goto out_filtered;
+		/*
+		 * We have to do this here as we may have a dso with no symbol
+		 * hit that has a name longer than the ones with symbols
+		 * sampled.
+		 */
+		if (!sort_dso.elide && !al->map->dso->slen_calculated)
+			dso__calc_col_width(al->map->dso);
+
+		al->sym = map__find_symbol(al->map, al->addr, filter);
+	} else {
+		const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+
+		if (dsos__col_width < unresolved_col_width &&
+		    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
+		    !symbol_conf.dso_list)
+			dsos__col_width = unresolved_col_width;
+	}
 
 	if (symbol_conf.sym_list && al->sym &&
 	    !strlist__has_entry(symbol_conf.sym_list, al->sym->name))
 		goto out_filtered;
 
-	al->filtered = false;
 	return 0;
 
 out_filtered:
@@ -570,6 +755,7 @@
 		array++;
 	}
 
+	data->id = -1ULL;
 	if (type & PERF_SAMPLE_ID) {
 		data->id = *array;
 		array++;

tools/perf/util/event.h

diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a33b949..8577085 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -68,21 +68,54 @@
 	u64 addr;
 	u64 id;
 	u64 stream_id;
-	u32 cpu;
 	u64 period;
-	struct ip_callchain *callchain;
+	u32 cpu;
 	u32 raw_size;
 	void *raw_data;
+	struct ip_callchain *callchain;
 };
 
 #define BUILD_ID_SIZE 20
 
 struct build_id_event {
 	struct perf_event_header header;
+	pid_t			 pid;
 	u8			 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
 	char			 filename[];
 };
 
+enum perf_user_event_type { /* above any possible kernel type */
+	PERF_RECORD_HEADER_ATTR			= 64,
+	PERF_RECORD_HEADER_EVENT_TYPE		= 65,
+	PERF_RECORD_HEADER_TRACING_DATA		= 66,
+	PERF_RECORD_HEADER_BUILD_ID		= 67,
+	PERF_RECORD_FINISHED_ROUND		= 68,
+	PERF_RECORD_HEADER_MAX
+};
+
+struct attr_event {
+	struct perf_event_header header;
+	struct perf_event_attr attr;
+	u64 id[];
+};
+
+#define MAX_EVENT_NAME 64
+
+struct perf_trace_event_type {
+	u64	event_id;
+	char	name[MAX_EVENT_NAME];
+};
+
+struct event_type_event {
+	struct perf_event_header header;
+	struct perf_trace_event_type event_type;
+};
+
+struct tracing_data_event {
+	struct perf_event_header header;
+	u32 size;
+};
+
 typedef union event_union {
 	struct perf_event_header	header;
 	struct ip_event			ip;
@@ -92,22 +125,12 @@
 	struct lost_event		lost;
 	struct read_event		read;
 	struct sample_event		sample;
+	struct attr_event		attr;
+	struct event_type_event		event_type;
+	struct tracing_data_event	tracing_data;
+	struct build_id_event		build_id;
 } event_t;
 
-struct events_stats {
-	u64 total;
-	u64 lost;
-};
-
-struct event_stat_id {
-	struct rb_node		rb_node;
-	struct rb_root		hists;
-	struct events_stats	stats;
-	u64			config;
-	u64			event_stream;
-	u32			type;
-};
-
 void event__print_totals(void);
 
 struct perf_session;
@@ -119,10 +142,13 @@
 void event__synthesize_threads(event__handler_t process,
 			       struct perf_session *session);
 int event__synthesize_kernel_mmap(event__handler_t process,
-				  struct perf_session *session,
-				  const char *symbol_name);
+				struct perf_session *session,
+				struct machine *machine,
+				const char *symbol_name);
+
 int event__synthesize_modules(event__handler_t process,
-			      struct perf_session *session);
+			      struct perf_session *session,
+			      struct machine *machine);
 
 int event__process_comm(event_t *self, struct perf_session *session);
 int event__process_lost(event_t *self, struct perf_session *session);
@@ -134,4 +160,6 @@
 			     struct addr_location *al, symbol_filter_t filter);
 int event__parse_sample(event_t *event, u64 type, struct sample_data *data);
 
+extern const char *event__name[];
+
 #endif /* __PERF_RECORD_H */

tools/perf/util/header.c

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 6c9aa16..8847bec 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -99,13 +99,6 @@
 	return 0;
 }
 
-#define MAX_EVENT_NAME 64
-
-struct perf_trace_event_type {
-	u64	event_id;
-	char	name[MAX_EVENT_NAME];
-};
-
 static int event_count;
 static struct perf_trace_event_type *events;
 
@@ -197,7 +190,8 @@
 			continue;		\
 		else
 
-static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd)
+static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
+				u16 misc, int fd)
 {
 	struct dso *pos;
 
@@ -212,6 +206,7 @@
 		len = ALIGN(len, NAME_ALIGN);
 		memset(&b, 0, sizeof(b));
 		memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id));
+		b.pid = pid;
 		b.header.misc = misc;
 		b.header.size = sizeof(b) + len;
 		err = do_write(fd, &b, sizeof(b));
@@ -226,13 +221,32 @@
 	return 0;
 }
 
-static int dsos__write_buildid_table(int fd)
+static int dsos__write_buildid_table(struct perf_header *header, int fd)
 {
-	int err = __dsos__write_buildid_table(&dsos__kernel,
-					      PERF_RECORD_MISC_KERNEL, fd);
-	if (err == 0)
-		err = __dsos__write_buildid_table(&dsos__user,
-						  PERF_RECORD_MISC_USER, fd);
+	struct perf_session *session = container_of(header,
+			struct perf_session, header);
+	struct rb_node *nd;
+	int err = 0;
+	u16 kmisc, umisc;
+
+	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		if (machine__is_host(pos)) {
+			kmisc = PERF_RECORD_MISC_KERNEL;
+			umisc = PERF_RECORD_MISC_USER;
+		} else {
+			kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+			umisc = PERF_RECORD_MISC_GUEST_USER;
+		}
+
+		err = __dsos__write_buildid_table(&pos->kernel_dsos, pos->pid,
+						  kmisc, fd);
+		if (err == 0)
+			err = __dsos__write_buildid_table(&pos->user_dsos,
+							  pos->pid, umisc, fd);
+		if (err)
+			break;
+	}
 	return err;
 }
 
@@ -349,9 +363,12 @@
 	return err;
 }
 
-static int dsos__cache_build_ids(void)
+static int dsos__cache_build_ids(struct perf_header *self)
 {
-	int err_kernel, err_user;
+	struct perf_session *session = container_of(self,
+			struct perf_session, header);
+	struct rb_node *nd;
+	int ret = 0;
 	char debugdir[PATH_MAX];
 
 	snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
@@ -360,9 +377,28 @@
 	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
 		return -1;
 
-	err_kernel = __dsos__cache_build_ids(&dsos__kernel, debugdir);
-	err_user   = __dsos__cache_build_ids(&dsos__user, debugdir);
-	return err_kernel || err_user ? -1 : 0;
+	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret |= __dsos__cache_build_ids(&pos->kernel_dsos, debugdir);
+		ret |= __dsos__cache_build_ids(&pos->user_dsos, debugdir);
+	}
+	return ret ? -1 : 0;
+}
+
+static bool dsos__read_build_ids(struct perf_header *self, bool with_hits)
+{
+	bool ret = false;
+	struct perf_session *session = container_of(self,
+			struct perf_session, header);
+	struct rb_node *nd;
+
+	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret |= __dsos__read_build_ids(&pos->kernel_dsos, with_hits);
+		ret |= __dsos__read_build_ids(&pos->user_dsos, with_hits);
+	}
+
+	return ret;
 }
 
 static int perf_header__adds_write(struct perf_header *self, int fd)
@@ -373,7 +409,7 @@
 	u64 sec_start;
 	int idx = 0, err;
 
-	if (dsos__read_build_ids(true))
+	if (dsos__read_build_ids(self, true))
 		perf_header__set_feat(self, HEADER_BUILD_ID);
 
 	nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
@@ -400,7 +436,6 @@
 		trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset;
 	}
 
-
 	if (perf_header__has_feat(self, HEADER_BUILD_ID)) {
 		struct perf_file_section *buildid_sec;
 
@@ -408,14 +443,14 @@
 
 		/* Write build-ids */
 		buildid_sec->offset = lseek(fd, 0, SEEK_CUR);
-		err = dsos__write_buildid_table(fd);
+		err = dsos__write_buildid_table(self, fd);
 		if (err < 0) {
 			pr_debug("failed to write buildid table\n");
 			goto out_free;
 		}
 		buildid_sec->size = lseek(fd, 0, SEEK_CUR) -
 					  buildid_sec->offset;
-		dsos__cache_build_ids();
+		dsos__cache_build_ids(self);
 	}
 
 	lseek(fd, sec_start, SEEK_SET);
@@ -427,6 +462,25 @@
 	return err;
 }
 
+int perf_header__write_pipe(int fd)
+{
+	struct perf_pipe_file_header f_header;
+	int err;
+
+	f_header = (struct perf_pipe_file_header){
+		.magic	   = PERF_MAGIC,
+		.size	   = sizeof(f_header),
+	};
+
+	err = do_write(fd, &f_header, sizeof(f_header));
+	if (err < 0) {
+		pr_debug("failed to write perf pipe header\n");
+		return err;
+	}
+
+	return 0;
+}
+
 int perf_header__write(struct perf_header *self, int fd, bool at_exit)
 {
 	struct perf_file_header f_header;
@@ -518,25 +572,10 @@
 	return 0;
 }
 
-static int do_read(int fd, void *buf, size_t size)
-{
-	while (size) {
-		int ret = read(fd, buf, size);
-
-		if (ret <= 0)
-			return -1;
-
-		size -= ret;
-		buf += ret;
-	}
-
-	return 0;
-}
-
 static int perf_header__getbuffer64(struct perf_header *self,
 				    int fd, void *buf, size_t size)
 {
-	if (do_read(fd, buf, size))
+	if (do_read(fd, buf, size) <= 0)
 		return -1;
 
 	if (self->needs_swap)
@@ -592,7 +631,7 @@
 {
 	lseek(fd, 0, SEEK_SET);
 
-	if (do_read(fd, self, sizeof(*self)) ||
+	if (do_read(fd, self, sizeof(*self)) <= 0 ||
 	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
 		return -1;
 
@@ -636,6 +675,93 @@
 	return 0;
 }
 
+static int __event_process_build_id(struct build_id_event *bev,
+				    char *filename,
+				    struct perf_session *session)
+{
+	int err = -1;
+	struct list_head *head;
+	struct machine *machine;
+	u16 misc;
+	struct dso *dso;
+	enum dso_kernel_type dso_type;
+
+	machine = perf_session__findnew_machine(session, bev->pid);
+	if (!machine)
+		goto out;
+
+	misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	switch (misc) {
+	case PERF_RECORD_MISC_KERNEL:
+		dso_type = DSO_TYPE_KERNEL;
+		head = &machine->kernel_dsos;
+		break;
+	case PERF_RECORD_MISC_GUEST_KERNEL:
+		dso_type = DSO_TYPE_GUEST_KERNEL;
+		head = &machine->kernel_dsos;
+		break;
+	case PERF_RECORD_MISC_USER:
+	case PERF_RECORD_MISC_GUEST_USER:
+		dso_type = DSO_TYPE_USER;
+		head = &machine->user_dsos;
+		break;
+	default:
+		goto out;
+	}
+
+	dso = __dsos__findnew(head, filename);
+	if (dso != NULL) {
+		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+		dso__set_build_id(dso, &bev->build_id);
+
+		if (filename[0] == '[')
+			dso->kernel = dso_type;
+
+		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
+				  sbuild_id);
+		pr_debug("build id event received for %s: %s\n",
+			 dso->long_name, sbuild_id);
+	}
+
+	err = 0;
+out:
+	return err;
+}
+
+static int perf_header__read_build_ids(struct perf_header *self,
+			int input, u64 offset, u64 size)
+{
+	struct perf_session *session = container_of(self,
+			struct perf_session, header);
+	struct build_id_event bev;
+	char filename[PATH_MAX];
+	u64 limit = offset + size;
+	int err = -1;
+
+	while (offset < limit) {
+		ssize_t len;
+
+		if (read(input, &bev, sizeof(bev)) != sizeof(bev))
+			goto out;
+
+		if (self->needs_swap)
+			perf_event_header__bswap(&bev.header);
+
+		len = bev.header.size - sizeof(bev);
+		if (read(input, filename, len) != len)
+			goto out;
+
+		__event_process_build_id(&bev, filename, session);
+
+		offset += bev.header.size;
+	}
+	err = 0;
+out:
+	return err;
+}
+
 static int perf_file_section__process(struct perf_file_section *self,
 				      struct perf_header *ph,
 				      int feat, int fd)
@@ -648,7 +774,7 @@
 
 	switch (feat) {
 	case HEADER_TRACE_INFO:
-		trace_report(fd);
+		trace_report(fd, false);
 		break;
 
 	case HEADER_BUILD_ID:
@@ -662,13 +788,56 @@
 	return 0;
 }
 
-int perf_header__read(struct perf_header *self, int fd)
+static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
+				       struct perf_header *ph, int fd,
+				       bool repipe)
 {
+	if (do_read(fd, self, sizeof(*self)) <= 0 ||
+	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+		return -1;
+
+	if (repipe && do_write(STDOUT_FILENO, self, sizeof(*self)) < 0)
+		return -1;
+
+	if (self->size != sizeof(*self)) {
+		u64 size = bswap_64(self->size);
+
+		if (size != sizeof(*self))
+			return -1;
+
+		ph->needs_swap = true;
+	}
+
+	return 0;
+}
+
+static int perf_header__read_pipe(struct perf_session *session, int fd)
+{
+	struct perf_header *self = &session->header;
+	struct perf_pipe_file_header f_header;
+
+	if (perf_file_header__read_pipe(&f_header, self, fd,
+					session->repipe) < 0) {
+		pr_debug("incompatible file format\n");
+		return -EINVAL;
+	}
+
+	session->fd = fd;
+
+	return 0;
+}
+
+int perf_header__read(struct perf_session *session, int fd)
+{
+	struct perf_header *self = &session->header;
 	struct perf_file_header	f_header;
 	struct perf_file_attr	f_attr;
 	u64			f_id;
 	int nr_attrs, nr_ids, i, j;
 
+	if (session->fd_pipe)
+		return perf_header__read_pipe(session, fd);
+
 	if (perf_file_header__read(&f_header, self, fd) < 0) {
 		pr_debug("incompatible file format\n");
 		return -EINVAL;
@@ -753,6 +922,14 @@
 {
 	int i;
 
+	/*
+	 * We set id to -1 if the data file doesn't contain sample
+	 * ids. Check for this and avoid walking through the entire
+	 * list of ids which may be large.
+	 */
+	if (id == -1ULL)
+		return NULL;
+
 	for (i = 0; i < header->attrs; i++) {
 		struct perf_header_attr *attr = header->attr[i];
 		int j;
@@ -765,3 +942,231 @@
 
 	return NULL;
 }
+
+int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+			   event__handler_t process,
+			   struct perf_session *session)
+{
+	event_t *ev;
+	size_t size;
+	int err;
+
+	size = sizeof(struct perf_event_attr);
+	size = ALIGN(size, sizeof(u64));
+	size += sizeof(struct perf_event_header);
+	size += ids * sizeof(u64);
+
+	ev = malloc(size);
+
+	ev->attr.attr = *attr;
+	memcpy(ev->attr.id, id, ids * sizeof(u64));
+
+	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
+	ev->attr.header.size = size;
+
+	err = process(ev, session);
+
+	free(ev);
+
+	return err;
+}
+
+int event__synthesize_attrs(struct perf_header *self,
+			    event__handler_t process,
+			    struct perf_session *session)
+{
+	struct perf_header_attr	*attr;
+	int i, err = 0;
+
+	for (i = 0; i < self->attrs; i++) {
+		attr = self->attr[i];
+
+		err = event__synthesize_attr(&attr->attr, attr->ids, attr->id,
+					     process, session);
+		if (err) {
+			pr_debug("failed to create perf header attribute\n");
+			return err;
+		}
+	}
+
+	return err;
+}
+
+int event__process_attr(event_t *self, struct perf_session *session)
+{
+	struct perf_header_attr *attr;
+	unsigned int i, ids, n_ids;
+
+	attr = perf_header_attr__new(&self->attr.attr);
+	if (attr == NULL)
+		return -ENOMEM;
+
+	ids = self->header.size;
+	ids -= (void *)&self->attr.id - (void *)self;
+	n_ids = ids / sizeof(u64);
+
+	for (i = 0; i < n_ids; i++) {
+		if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) {
+			perf_header_attr__delete(attr);
+			return -ENOMEM;
+		}
+	}
+
+	if (perf_header__add_attr(&session->header, attr) < 0) {
+		perf_header_attr__delete(attr);
+		return -ENOMEM;
+	}
+
+	perf_session__update_sample_type(session);
+
+	return 0;
+}
+
+int event__synthesize_event_type(u64 event_id, char *name,
+				 event__handler_t process,
+				 struct perf_session *session)
+{
+	event_t ev;
+	size_t size = 0;
+	int err = 0;
+
+	memset(&ev, 0, sizeof(ev));
+
+	ev.event_type.event_type.event_id = event_id;
+	memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME);
+	strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1);
+
+	ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
+	size = strlen(name);
+	size = ALIGN(size, sizeof(u64));
+	ev.event_type.header.size = sizeof(ev.event_type) -
+		(sizeof(ev.event_type.event_type.name) - size);
+
+	err = process(&ev, session);
+
+	return err;
+}
+
+int event__synthesize_event_types(event__handler_t process,
+				  struct perf_session *session)
+{
+	struct perf_trace_event_type *type;
+	int i, err = 0;
+
+	for (i = 0; i < event_count; i++) {
+		type = &events[i];
+
+		err = event__synthesize_event_type(type->event_id, type->name,
+						   process, session);
+		if (err) {
+			pr_debug("failed to create perf header event type\n");
+			return err;
+		}
+	}
+
+	return err;
+}
+
+int event__process_event_type(event_t *self,
+			      struct perf_session *session __unused)
+{
+	if (perf_header__push_event(self->event_type.event_type.event_id,
+				    self->event_type.event_type.name) < 0)
+		return -ENOMEM;
+
+	return 0;
+}
+
+int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
+				   int nb_events,
+				   event__handler_t process,
+				   struct perf_session *session __unused)
+{
+	event_t ev;
+	ssize_t size = 0, aligned_size = 0, padding;
+	int err = 0;
+
+	memset(&ev, 0, sizeof(ev));
+
+	ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
+	size = read_tracing_data_size(fd, pattrs, nb_events);
+	if (size <= 0)
+		return size;
+	aligned_size = ALIGN(size, sizeof(u64));
+	padding = aligned_size - size;
+	ev.tracing_data.header.size = sizeof(ev.tracing_data);
+	ev.tracing_data.size = aligned_size;
+
+	process(&ev, session);
+
+	err = read_tracing_data(fd, pattrs, nb_events);
+	write_padded(fd, NULL, 0, padding);
+
+	return aligned_size;
+}
+
+int event__process_tracing_data(event_t *self,
+				struct perf_session *session)
+{
+	ssize_t size_read, padding, size = self->tracing_data.size;
+	off_t offset = lseek(session->fd, 0, SEEK_CUR);
+	char buf[BUFSIZ];
+
+	/* setup for reading amidst mmap */
+	lseek(session->fd, offset + sizeof(struct tracing_data_event),
+	      SEEK_SET);
+
+	size_read = trace_report(session->fd, session->repipe);
+
+	padding = ALIGN(size_read, sizeof(u64)) - size_read;
+
+	if (read(session->fd, buf, padding) < 0)
+		die("reading input file");
+	if (session->repipe) {
+		int retw = write(STDOUT_FILENO, buf, padding);
+		if (retw <= 0 || retw != padding)
+			die("repiping tracing data padding");
+	}
+
+	if (size_read + padding != size)
+		die("tracing data size mismatch");
+
+	return size_read + padding;
+}
+
+int event__synthesize_build_id(struct dso *pos, u16 misc,
+			       event__handler_t process,
+			       struct machine *machine,
+			       struct perf_session *session)
+{
+	event_t ev;
+	size_t len;
+	int err = 0;
+
+	if (!pos->hit)
+		return err;
+
+	memset(&ev, 0, sizeof(ev));
+
+	len = pos->long_name_len + 1;
+	len = ALIGN(len, NAME_ALIGN);
+	memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
+	ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
+	ev.build_id.header.misc = misc;
+	ev.build_id.pid = machine->pid;
+	ev.build_id.header.size = sizeof(ev.build_id) + len;
+	memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
+
+	err = process(&ev, session);
+
+	return err;
+}
+
+int event__process_build_id(event_t *self,
+			    struct perf_session *session)
+{
+	__event_process_build_id(&self->build_id,
+				 self->build_id.filename,
+				 session);
+	return 0;
+}

tools/perf/util/header.h

diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 82a6af7..402ac24 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -39,6 +39,11 @@
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
 
+struct perf_pipe_file_header {
+	u64				magic;
+	u64				size;
+};
+
 struct perf_header;
 
 int perf_file_header__read(struct perf_file_header *self,
@@ -47,21 +52,22 @@
 struct perf_header {
 	int			frozen;
 	int			attrs, size;
+	bool			needs_swap;
 	struct perf_header_attr **attr;
 	s64			attr_offset;
 	u64			data_offset;
 	u64			data_size;
 	u64			event_offset;
 	u64			event_size;
-	bool			needs_swap;
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
 
 int perf_header__init(struct perf_header *self);
 void perf_header__exit(struct perf_header *self);
 
-int perf_header__read(struct perf_header *self, int fd);
+int perf_header__read(struct perf_session *session, int fd);
 int perf_header__write(struct perf_header *self, int fd, bool at_exit);
+int perf_header__write_pipe(int fd);
 
 int perf_header__add_attr(struct perf_header *self,
 			  struct perf_header_attr *attr);
@@ -89,4 +95,33 @@
 			  const char *name, bool is_kallsyms);
 int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
 
+int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+			   event__handler_t process,
+			   struct perf_session *session);
+int event__synthesize_attrs(struct perf_header *self,
+			    event__handler_t process,
+			    struct perf_session *session);
+int event__process_attr(event_t *self, struct perf_session *session);
+
+int event__synthesize_event_type(u64 event_id, char *name,
+				 event__handler_t process,
+				 struct perf_session *session);
+int event__synthesize_event_types(event__handler_t process,
+				  struct perf_session *session);
+int event__process_event_type(event_t *self,
+			      struct perf_session *session);
+
+int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
+				   int nb_events,
+				   event__handler_t process,
+				   struct perf_session *session);
+int event__process_tracing_data(event_t *self,
+				struct perf_session *session);
+
+int event__synthesize_build_id(struct dso *pos, u16 misc,
+			       event__handler_t process,
+			       struct machine *machine,
+			       struct perf_session *session);
+int event__process_build_id(event_t *self, struct perf_session *session);
+
 #endif /* __PERF_HEADER_H */

tools/perf/util/hist.c

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 2be33c7..9a71c94 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,3 +1,4 @@
+#include "util.h"
 #include "hist.h"
 #include "session.h"
 #include "sort.h"
@@ -8,25 +9,69 @@
 	.min_percent = 0.5
 };
 
+static void hist_entry__add_cpumode_period(struct hist_entry *self,
+					   unsigned int cpumode, u64 period)
+{
+	switch (cpumode) {
+	case PERF_RECORD_MISC_KERNEL:
+		self->period_sys += period;
+		break;
+	case PERF_RECORD_MISC_USER:
+		self->period_us += period;
+		break;
+	case PERF_RECORD_MISC_GUEST_KERNEL:
+		self->period_guest_sys += period;
+		break;
+	case PERF_RECORD_MISC_GUEST_USER:
+		self->period_guest_us += period;
+		break;
+	default:
+		break;
+	}
+}
+
 /*
- * histogram, sorted on item, collects counts
+ * histogram, sorted on item, collects periods
  */
 
-struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
-						  struct addr_location *al,
-						  struct symbol *sym_parent,
-						  u64 count, bool *hit)
+static struct hist_entry *hist_entry__new(struct hist_entry *template)
 {
-	struct rb_node **p = &hists->rb_node;
+	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_node) : 0;
+	struct hist_entry *self = malloc(sizeof(*self) + callchain_size);
+
+	if (self != NULL) {
+		*self = *template;
+		self->nr_events = 1;
+		if (symbol_conf.use_callchain)
+			callchain_init(self->callchain);
+	}
+
+	return self;
+}
+
+static void hists__inc_nr_entries(struct hists *self, struct hist_entry *entry)
+{
+	if (entry->ms.sym && self->max_sym_namelen < entry->ms.sym->namelen)
+		self->max_sym_namelen = entry->ms.sym->namelen;
+	++self->nr_entries;
+}
+
+struct hist_entry *__hists__add_entry(struct hists *self,
+				      struct addr_location *al,
+				      struct symbol *sym_parent, u64 period)
+{
+	struct rb_node **p = &self->entries.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
 	struct hist_entry entry = {
 		.thread	= al->thread,
-		.map	= al->map,
-		.sym	= al->sym,
+		.ms = {
+			.map	= al->map,
+			.sym	= al->sym,
+		},
 		.ip	= al->addr,
 		.level	= al->level,
-		.count	= count,
+		.period	= period,
 		.parent = sym_parent,
 	};
 	int cmp;
@@ -38,8 +83,9 @@
 		cmp = hist_entry__cmp(&entry, he);
 
 		if (!cmp) {
-			*hit = true;
-			return he;
+			he->period += period;
+			++he->nr_events;
+			goto out;
 		}
 
 		if (cmp < 0)
@@ -48,13 +94,14 @@
 			p = &(*p)->rb_right;
 	}
 
-	he = malloc(sizeof(*he));
+	he = hist_entry__new(&entry);
 	if (!he)
 		return NULL;
-	*he = entry;
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, hists);
-	*hit = false;
+	rb_insert_color(&he->rb_node, &self->entries);
+	hists__inc_nr_entries(self, he);
+out:
+	hist_entry__add_cpumode_period(he, al->cpumode, period);
 	return he;
 }
 
@@ -65,7 +112,7 @@
 	int64_t cmp = 0;
 
 	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		cmp = se->cmp(left, right);
+		cmp = se->se_cmp(left, right);
 		if (cmp)
 			break;
 	}
@@ -82,7 +129,7 @@
 	list_for_each_entry(se, &hist_entry__sort_list, list) {
 		int64_t (*f)(struct hist_entry *, struct hist_entry *);
 
-		f = se->collapse ?: se->cmp;
+		f = se->se_collapse ?: se->se_cmp;
 
 		cmp = f(left, right);
 		if (cmp)
@@ -101,7 +148,7 @@
  * collapse the histogram
  */
 
-static void collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
+static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -115,9 +162,9 @@
 		cmp = hist_entry__collapse(iter, he);
 
 		if (!cmp) {
-			iter->count += he->count;
+			iter->period += he->period;
 			hist_entry__free(he);
-			return;
+			return false;
 		}
 
 		if (cmp < 0)
@@ -128,9 +175,10 @@
 
 	rb_link_node(&he->rb_node, parent, p);
 	rb_insert_color(&he->rb_node, root);
+	return true;
 }
 
-void perf_session__collapse_resort(struct rb_root *hists)
+void hists__collapse_resort(struct hists *self)
 {
 	struct rb_root tmp;
 	struct rb_node *next;
@@ -140,72 +188,77 @@
 		return;
 
 	tmp = RB_ROOT;
-	next = rb_first(hists);
+	next = rb_first(&self->entries);
+	self->nr_entries = 0;
+	self->max_sym_namelen = 0;
 
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node);
 		next = rb_next(&n->rb_node);
 
-		rb_erase(&n->rb_node, hists);
-		collapse__insert_entry(&tmp, n);
+		rb_erase(&n->rb_node, &self->entries);
+		if (collapse__insert_entry(&tmp, n))
+			hists__inc_nr_entries(self, n);
 	}
 
-	*hists = tmp;
+	self->entries = tmp;
 }
 
 /*
- * reverse the map, sort on count.
+ * reverse the map, sort on period.
  */
 
-static void perf_session__insert_output_hist_entry(struct rb_root *root,
-						   struct hist_entry *he,
-						   u64 min_callchain_hits)
+static void __hists__insert_output_entry(struct rb_root *entries,
+					 struct hist_entry *he,
+					 u64 min_callchain_hits)
 {
-	struct rb_node **p = &root->rb_node;
+	struct rb_node **p = &entries->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 
 	if (symbol_conf.use_callchain)
-		callchain_param.sort(&he->sorted_chain, &he->callchain,
+		callchain_param.sort(&he->sorted_chain, he->callchain,
 				      min_callchain_hits, &callchain_param);
 
 	while (*p != NULL) {
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node);
 
-		if (he->count > iter->count)
+		if (he->period > iter->period)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
 	}
 
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, root);
+	rb_insert_color(&he->rb_node, entries);
 }
 
-void perf_session__output_resort(struct rb_root *hists, u64 total_samples)
+void hists__output_resort(struct hists *self)
 {
 	struct rb_root tmp;
 	struct rb_node *next;
 	struct hist_entry *n;
 	u64 min_callchain_hits;
 
-	min_callchain_hits =
-		total_samples * (callchain_param.min_percent / 100);
+	min_callchain_hits = self->stats.total_period * (callchain_param.min_percent / 100);
 
 	tmp = RB_ROOT;
-	next = rb_first(hists);
+	next = rb_first(&self->entries);
+
+	self->nr_entries = 0;
+	self->max_sym_namelen = 0;
 
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node);
 		next = rb_next(&n->rb_node);
 
-		rb_erase(&n->rb_node, hists);
-		perf_session__insert_output_hist_entry(&tmp, n,
-						       min_callchain_hits);
+		rb_erase(&n->rb_node, &self->entries);
+		__hists__insert_output_entry(&tmp, n, min_callchain_hits);
+		hists__inc_nr_entries(self, n);
 	}
 
-	*hists = tmp;
+	self->entries = tmp;
 }
 
 static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
@@ -237,7 +290,7 @@
 }
 
 static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
-				     int depth, int depth_mask, int count,
+				     int depth, int depth_mask, int period,
 				     u64 total_samples, int hits,
 				     int left_margin)
 {
@@ -250,7 +303,7 @@
 			ret += fprintf(fp, "|");
 		else
 			ret += fprintf(fp, " ");
-		if (!count && i == depth - 1) {
+		if (!period && i == depth - 1) {
 			double percent;
 
 			percent = hits * 100.0 / total_samples;
@@ -258,8 +311,8 @@
 		} else
 			ret += fprintf(fp, "%s", "          ");
 	}
-	if (chain->sym)
-		ret += fprintf(fp, "%s\n", chain->sym->name);
+	if (chain->ms.sym)
+		ret += fprintf(fp, "%s\n", chain->ms.sym->name);
 	else
 		ret += fprintf(fp, "%p\n", (void *)(long)chain->ip);
 
@@ -278,7 +331,7 @@
 	}
 
 	strcpy(rem_sq_bracket->name, "[...]");
-	rem_hits.sym = rem_sq_bracket;
+	rem_hits.ms.sym = rem_sq_bracket;
 }
 
 static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
@@ -293,6 +346,7 @@
 	u64 remaining;
 	size_t ret = 0;
 	int i;
+	uint entries_printed = 0;
 
 	if (callchain_param.mode == CHAIN_GRAPH_REL)
 		new_total = self->children_hit;
@@ -328,8 +382,6 @@
 						   left_margin);
 		i = 0;
 		list_for_each_entry(chain, &child->val, list) {
-			if (chain->ip >= PERF_CONTEXT_MAX)
-				continue;
 			ret += ipchain__fprintf_graph(fp, chain, depth,
 						      new_depth_mask, i++,
 						      new_total,
@@ -341,6 +393,8 @@
 						  new_depth_mask | (1 << depth),
 						  left_margin);
 		node = next;
+		if (++entries_printed == callchain_param.print_limit)
+			break;
 	}
 
 	if (callchain_param.mode == CHAIN_GRAPH_REL &&
@@ -366,11 +420,9 @@
 	bool printed = false;
 	int i = 0;
 	int ret = 0;
+	u32 entries_printed = 0;
 
 	list_for_each_entry(chain, &self->val, list) {
-		if (chain->ip >= PERF_CONTEXT_MAX)
-			continue;
-
 		if (!i++ && sort__first_dimension == SORT_SYM)
 			continue;
 
@@ -385,10 +437,13 @@
 		} else
 			ret += callchain__fprintf_left_margin(fp, left_margin);
 
-		if (chain->sym)
-			ret += fprintf(fp, " %s\n", chain->sym->name);
+		if (chain->ms.sym)
+			ret += fprintf(fp, " %s\n", chain->ms.sym->name);
 		else
 			ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
+
+		if (++entries_printed == callchain_param.print_limit)
+			break;
 	}
 
 	ret += __callchain__fprintf_graph(fp, self, total_samples, 1, 1, left_margin);
@@ -411,8 +466,8 @@
 	list_for_each_entry(chain, &self->val, list) {
 		if (chain->ip >= PERF_CONTEXT_MAX)
 			continue;
-		if (chain->sym)
-			ret += fprintf(fp, "                %s\n", chain->sym->name);
+		if (chain->ms.sym)
+			ret += fprintf(fp, "                %s\n", chain->ms.sym->name);
 		else
 			ret += fprintf(fp, "                %p\n",
 					(void *)(long)chain->ip);
@@ -427,6 +482,7 @@
 	struct rb_node *rb_node;
 	struct callchain_node *chain;
 	size_t ret = 0;
+	u32 entries_printed = 0;
 
 	rb_node = rb_first(&self->sorted_chain);
 	while (rb_node) {
@@ -449,55 +505,88 @@
 			break;
 		}
 		ret += fprintf(fp, "\n");
+		if (++entries_printed == callchain_param.print_limit)
+			break;
 		rb_node = rb_next(rb_node);
 	}
 
 	return ret;
 }
 
-static size_t hist_entry__fprintf(struct hist_entry *self,
-				  struct perf_session *pair_session,
-				  bool show_displacement,
-				  long displacement, FILE *fp,
-				  u64 session_total)
+int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
+			 struct hists *pair_hists, bool show_displacement,
+			 long displacement, bool color, u64 session_total)
 {
 	struct sort_entry *se;
-	u64 count, total;
+	u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us;
 	const char *sep = symbol_conf.field_sep;
-	size_t ret;
+	int ret;
 
 	if (symbol_conf.exclude_other && !self->parent)
 		return 0;
 
-	if (pair_session) {
-		count = self->pair ? self->pair->count : 0;
-		total = pair_session->events_stats.total;
+	if (pair_hists) {
+		period = self->pair ? self->pair->period : 0;
+		total = pair_hists->stats.total_period;
+		period_sys = self->pair ? self->pair->period_sys : 0;
+		period_us = self->pair ? self->pair->period_us : 0;
+		period_guest_sys = self->pair ? self->pair->period_guest_sys : 0;
+		period_guest_us = self->pair ? self->pair->period_guest_us : 0;
 	} else {
-		count = self->count;
+		period = self->period;
 		total = session_total;
+		period_sys = self->period_sys;
+		period_us = self->period_us;
+		period_guest_sys = self->period_guest_sys;
+		period_guest_us = self->period_guest_us;
 	}
 
-	if (total)
-		ret = percent_color_fprintf(fp, sep ? "%.2f" : "   %6.2f%%",
-					    (count * 100.0) / total);
-	else
-		ret = fprintf(fp, sep ? "%lld" : "%12lld ", count);
+	if (total) {
+		if (color)
+			ret = percent_color_snprintf(s, size,
+						     sep ? "%.2f" : "   %6.2f%%",
+						     (period * 100.0) / total);
+		else
+			ret = snprintf(s, size, sep ? "%.2f" : "   %6.2f%%",
+				       (period * 100.0) / total);
+		if (symbol_conf.show_cpu_utilization) {
+			ret += percent_color_snprintf(s + ret, size - ret,
+					sep ? "%.2f" : "   %6.2f%%",
+					(period_sys * 100.0) / total);
+			ret += percent_color_snprintf(s + ret, size - ret,
+					sep ? "%.2f" : "   %6.2f%%",
+					(period_us * 100.0) / total);
+			if (perf_guest) {
+				ret += percent_color_snprintf(s + ret,
+						size - ret,
+						sep ? "%.2f" : "   %6.2f%%",
+						(period_guest_sys * 100.0) /
+								total);
+				ret += percent_color_snprintf(s + ret,
+						size - ret,
+						sep ? "%.2f" : "   %6.2f%%",
+						(period_guest_us * 100.0) /
+								total);
+			}
+		}
+	} else
+		ret = snprintf(s, size, sep ? "%lld" : "%12lld ", period);
 
 	if (symbol_conf.show_nr_samples) {
 		if (sep)
-			fprintf(fp, "%c%lld", *sep, count);
+			ret += snprintf(s + ret, size - ret, "%c%lld", *sep, period);
 		else
-			fprintf(fp, "%11lld", count);
+			ret += snprintf(s + ret, size - ret, "%11lld", period);
 	}
 
-	if (pair_session) {
+	if (pair_hists) {
 		char bf[32];
 		double old_percent = 0, new_percent = 0, diff;
 
 		if (total > 0)
-			old_percent = (count * 100.0) / total;
+			old_percent = (period * 100.0) / total;
 		if (session_total > 0)
-			new_percent = (self->count * 100.0) / session_total;
+			new_percent = (self->period * 100.0) / session_total;
 
 		diff = new_percent - old_percent;
 
@@ -507,9 +596,9 @@
 			snprintf(bf, sizeof(bf), " ");
 
 		if (sep)
-			ret += fprintf(fp, "%c%s", *sep, bf);
+			ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf);
 		else
-			ret += fprintf(fp, "%11.11s", bf);
+			ret += snprintf(s + ret, size - ret, "%11.11s", bf);
 
 		if (show_displacement) {
 			if (displacement)
@@ -518,9 +607,9 @@
 				snprintf(bf, sizeof(bf), " ");
 
 			if (sep)
-				fprintf(fp, "%c%s", *sep, bf);
+				ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf);
 			else
-				fprintf(fp, "%6.6s", bf);
+				ret += snprintf(s + ret, size - ret, "%6.6s", bf);
 		}
 	}
 
@@ -528,33 +617,43 @@
 		if (se->elide)
 			continue;
 
-		fprintf(fp, "%s", sep ?: "  ");
-		ret += se->print(fp, self, se->width ? *se->width : 0);
-	}
-
-	ret += fprintf(fp, "\n");
-
-	if (symbol_conf.use_callchain) {
-		int left_margin = 0;
-
-		if (sort__first_dimension == SORT_COMM) {
-			se = list_first_entry(&hist_entry__sort_list, typeof(*se),
-						list);
-			left_margin = se->width ? *se->width : 0;
-			left_margin -= thread__comm_len(self->thread);
-		}
-
-		hist_entry_callchain__fprintf(fp, self, session_total,
-					      left_margin);
+		ret += snprintf(s + ret, size - ret, "%s", sep ?: "  ");
+		ret += se->se_snprintf(self, s + ret, size - ret,
+				       se->se_width ? *se->se_width : 0);
 	}
 
 	return ret;
 }
 
-size_t perf_session__fprintf_hists(struct rb_root *hists,
-				   struct perf_session *pair,
-				   bool show_displacement, FILE *fp,
-				   u64 session_total)
+int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists,
+			bool show_displacement, long displacement, FILE *fp,
+			u64 session_total)
+{
+	char bf[512];
+	hist_entry__snprintf(self, bf, sizeof(bf), pair_hists,
+			     show_displacement, displacement,
+			     true, session_total);
+	return fprintf(fp, "%s\n", bf);
+}
+
+static size_t hist_entry__fprintf_callchain(struct hist_entry *self, FILE *fp,
+					    u64 session_total)
+{
+	int left_margin = 0;
+
+	if (sort__first_dimension == SORT_COMM) {
+		struct sort_entry *se = list_first_entry(&hist_entry__sort_list,
+							 typeof(*se), list);
+		left_margin = se->se_width ? *se->se_width : 0;
+		left_margin -= thread__comm_len(self->thread);
+	}
+
+	return hist_entry_callchain__fprintf(fp, self, session_total,
+					     left_margin);
+}
+
+size_t hists__fprintf(struct hists *self, struct hists *pair,
+		      bool show_displacement, FILE *fp)
 {
 	struct sort_entry *se;
 	struct rb_node *nd;
@@ -563,7 +662,7 @@
 	long displacement = 0;
 	unsigned int width;
 	const char *sep = symbol_conf.field_sep;
-	char *col_width = symbol_conf.col_width_list_str;
+	const char *col_width = symbol_conf.col_width_list_str;
 
 	init_rem_hits();
 
@@ -576,6 +675,24 @@
 			fputs("  Samples  ", fp);
 	}
 
+	if (symbol_conf.show_cpu_utilization) {
+		if (sep) {
+			ret += fprintf(fp, "%csys", *sep);
+			ret += fprintf(fp, "%cus", *sep);
+			if (perf_guest) {
+				ret += fprintf(fp, "%cguest sys", *sep);
+				ret += fprintf(fp, "%cguest us", *sep);
+			}
+		} else {
+			ret += fprintf(fp, "  sys  ");
+			ret += fprintf(fp, "  us  ");
+			if (perf_guest) {
+				ret += fprintf(fp, "  guest sys  ");
+				ret += fprintf(fp, "  guest us  ");
+			}
+		}
+	}
+
 	if (pair) {
 		if (sep)
 			ret += fprintf(fp, "%cDelta", *sep);
@@ -594,22 +711,22 @@
 		if (se->elide)
 			continue;
 		if (sep) {
-			fprintf(fp, "%c%s", *sep, se->header);
+			fprintf(fp, "%c%s", *sep, se->se_header);
 			continue;
 		}
-		width = strlen(se->header);
-		if (se->width) {
+		width = strlen(se->se_header);
+		if (se->se_width) {
 			if (symbol_conf.col_width_list_str) {
 				if (col_width) {
-					*se->width = atoi(col_width);
+					*se->se_width = atoi(col_width);
 					col_width = strchr(col_width, ',');
 					if (col_width)
 						++col_width;
 				}
 			}
-			width = *se->width = max(*se->width, width);
+			width = *se->se_width = max(*se->se_width, width);
 		}
-		fprintf(fp, "  %*s", width, se->header);
+		fprintf(fp, "  %*s", width, se->se_header);
 	}
 	fprintf(fp, "\n");
 
@@ -631,10 +748,10 @@
 			continue;
 
 		fprintf(fp, "  ");
-		if (se->width)
-			width = *se->width;
+		if (se->se_width)
+			width = *se->se_width;
 		else
-			width = strlen(se->header);
+			width = strlen(se->se_header);
 		for (i = 0; i < width; i++)
 			fprintf(fp, ".");
 	}
@@ -642,7 +759,7 @@
 	fprintf(fp, "\n#\n");
 
 print_entries:
-	for (nd = rb_first(hists); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		if (show_displacement) {
@@ -654,10 +771,14 @@
 			++position;
 		}
 		ret += hist_entry__fprintf(h, pair, show_displacement,
-					   displacement, fp, session_total);
-		if (h->map == NULL && verbose > 1) {
+					   displacement, fp, self->stats.total_period);
+
+		if (symbol_conf.use_callchain)
+			ret += hist_entry__fprintf_callchain(h, fp, self->stats.total_period);
+
+		if (h->ms.map == NULL && verbose > 1) {
 			__map_groups__fprintf_maps(&h->thread->mg,
-						   MAP__FUNCTION, fp);
+						   MAP__FUNCTION, verbose, fp);
 			fprintf(fp, "%.10s end\n", graph_dotted_line);
 		}
 	}
@@ -666,3 +787,271 @@
 
 	return ret;
 }
+
+enum hist_filter {
+	HIST_FILTER__DSO,
+	HIST_FILTER__THREAD,
+};
+
+void hists__filter_by_dso(struct hists *self, const struct dso *dso)
+{
+	struct rb_node *nd;
+
+	self->nr_entries = self->stats.total_period = 0;
+	self->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	self->max_sym_namelen = 0;
+
+	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (symbol_conf.exclude_other && !h->parent)
+			continue;
+
+		if (dso != NULL && (h->ms.map == NULL || h->ms.map->dso != dso)) {
+			h->filtered |= (1 << HIST_FILTER__DSO);
+			continue;
+		}
+
+		h->filtered &= ~(1 << HIST_FILTER__DSO);
+		if (!h->filtered) {
+			++self->nr_entries;
+			self->stats.total_period += h->period;
+			self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events;
+			if (h->ms.sym &&
+			    self->max_sym_namelen < h->ms.sym->namelen)
+				self->max_sym_namelen = h->ms.sym->namelen;
+		}
+	}
+}
+
+void hists__filter_by_thread(struct hists *self, const struct thread *thread)
+{
+	struct rb_node *nd;
+
+	self->nr_entries = self->stats.total_period = 0;
+	self->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	self->max_sym_namelen = 0;
+
+	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (thread != NULL && h->thread != thread) {
+			h->filtered |= (1 << HIST_FILTER__THREAD);
+			continue;
+		}
+		h->filtered &= ~(1 << HIST_FILTER__THREAD);
+		if (!h->filtered) {
+			++self->nr_entries;
+			self->stats.total_period += h->period;
+			self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events;
+			if (h->ms.sym &&
+			    self->max_sym_namelen < h->ms.sym->namelen)
+				self->max_sym_namelen = h->ms.sym->namelen;
+		}
+	}
+}
+
+static int symbol__alloc_hist(struct symbol *self)
+{
+	struct sym_priv *priv = symbol__priv(self);
+	const int size = (sizeof(*priv->hist) +
+			  (self->end - self->start) * sizeof(u64));
+
+	priv->hist = zalloc(size);
+	return priv->hist == NULL ? -1 : 0;
+}
+
+int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip)
+{
+	unsigned int sym_size, offset;
+	struct symbol *sym = self->ms.sym;
+	struct sym_priv *priv;
+	struct sym_hist *h;
+
+	if (!sym || !self->ms.map)
+		return 0;
+
+	priv = symbol__priv(sym);
+	if (priv->hist == NULL && symbol__alloc_hist(sym) < 0)
+		return -ENOMEM;
+
+	sym_size = sym->end - sym->start;
+	offset = ip - sym->start;
+
+	pr_debug3("%s: ip=%#Lx\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip));
+
+	if (offset >= sym_size)
+		return 0;
+
+	h = priv->hist;
+	h->sum++;
+	h->ip[offset]++;
+
+	pr_debug3("%#Lx %s: period++ [ip: %#Lx, %#Lx] => %Ld\n", self->ms.sym->start,
+		  self->ms.sym->name, ip, ip - self->ms.sym->start, h->ip[offset]);
+	return 0;
+}
+
+static struct objdump_line *objdump_line__new(s64 offset, char *line)
+{
+	struct objdump_line *self = malloc(sizeof(*self));
+
+	if (self != NULL) {
+		self->offset = offset;
+		self->line = line;
+	}
+
+	return self;
+}
+
+void objdump_line__free(struct objdump_line *self)
+{
+	free(self->line);
+	free(self);
+}
+
+static void objdump__add_line(struct list_head *head, struct objdump_line *line)
+{
+	list_add_tail(&line->node, head);
+}
+
+struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+					       struct objdump_line *pos)
+{
+	list_for_each_entry_continue(pos, head, node)
+		if (pos->offset >= 0)
+			return pos;
+
+	return NULL;
+}
+
+static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file,
+					  struct list_head *head)
+{
+	struct symbol *sym = self->ms.sym;
+	struct objdump_line *objdump_line;
+	char *line = NULL, *tmp, *tmp2, *c;
+	size_t line_len;
+	s64 line_ip, offset = -1;
+
+	if (getline(&line, &line_len, file) < 0)
+		return -1;
+
+	if (!line)
+		return -1;
+
+	while (line_len != 0 && isspace(line[line_len - 1]))
+		line[--line_len] = '\0';
+
+	c = strchr(line, '\n');
+	if (c)
+		*c = 0;
+
+	line_ip = -1;
+
+	/*
+	 * Strip leading spaces:
+	 */
+	tmp = line;
+	while (*tmp) {
+		if (*tmp != ' ')
+			break;
+		tmp++;
+	}
+
+	if (*tmp) {
+		/*
+		 * Parse hexa addresses followed by ':'
+		 */
+		line_ip = strtoull(tmp, &tmp2, 16);
+		if (*tmp2 != ':')
+			line_ip = -1;
+	}
+
+	if (line_ip != -1) {
+		u64 start = map__rip_2objdump(self->ms.map, sym->start);
+		offset = line_ip - start;
+	}
+
+	objdump_line = objdump_line__new(offset, line);
+	if (objdump_line == NULL) {
+		free(line);
+		return -1;
+	}
+	objdump__add_line(head, objdump_line);
+
+	return 0;
+}
+
+int hist_entry__annotate(struct hist_entry *self, struct list_head *head)
+{
+	struct symbol *sym = self->ms.sym;
+	struct map *map = self->ms.map;
+	struct dso *dso = map->dso;
+	const char *filename = dso->long_name;
+	char command[PATH_MAX * 2];
+	FILE *file;
+	u64 len;
+
+	if (!filename)
+		return -1;
+
+	if (dso->origin == DSO__ORIG_KERNEL) {
+		if (dso->annotate_warned)
+			return 0;
+		dso->annotate_warned = 1;
+		pr_err("Can't annotate %s: No vmlinux file was found in the "
+		       "path:\n", sym->name);
+		vmlinux_path__fprintf(stderr);
+		return -1;
+	}
+
+	pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__,
+		 filename, sym->name, map->unmap_ip(map, sym->start),
+		 map->unmap_ip(map, sym->end));
+
+	len = sym->end - sym->start;
+
+	pr_debug("annotating [%p] %30s : [%p] %30s\n",
+		 dso, dso->long_name, sym, sym->name);
+
+	snprintf(command, sizeof(command),
+		 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s|expand",
+		 map__rip_2objdump(map, sym->start),
+		 map__rip_2objdump(map, sym->end),
+		 filename, filename);
+
+	pr_debug("Executing: %s\n", command);
+
+	file = popen(command, "r");
+	if (!file)
+		return -1;
+
+	while (!feof(file))
+		if (hist_entry__parse_objdump_line(self, file, head) < 0)
+			break;
+
+	pclose(file);
+	return 0;
+}
+
+void hists__inc_nr_events(struct hists *self, u32 type)
+{
+	++self->stats.nr_events[0];
+	++self->stats.nr_events[type];
+}
+
+size_t hists__fprintf_nr_events(struct hists *self, FILE *fp)
+{
+	int i;
+	size_t ret = 0;
+
+	for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
+		if (!event__name[i])
+			continue;
+		ret += fprintf(fp, "%10s events: %10d\n",
+			       event__name[i], self->stats.nr_events[i]);
+	}
+
+	return ret;
+}

tools/perf/util/hist.h

diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 16f360c..6f17dcd 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -6,24 +6,104 @@
 
 extern struct callchain_param callchain_param;
 
-struct perf_session;
 struct hist_entry;
 struct addr_location;
 struct symbol;
 struct rb_root;
 
-struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
-						  struct addr_location *al,
-						  struct symbol *parent,
-						  u64 count, bool *hit);
+struct objdump_line {
+	struct list_head node;
+	s64		 offset;
+	char		 *line;
+};
+
+void objdump_line__free(struct objdump_line *self);
+struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+					       struct objdump_line *pos);
+
+struct sym_hist {
+	u64		sum;
+	u64		ip[0];
+};
+
+struct sym_ext {
+	struct rb_node	node;
+	double		percent;
+	char		*path;
+};
+
+struct sym_priv {
+	struct sym_hist	*hist;
+	struct sym_ext	*ext;
+};
+
+/*
+ * 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
+ * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
+ * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
+ * the sum of all struct lost_event.lost fields reported.
+ *
+ * The total_period is needed because by default auto-freq is used, so
+ * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
+ * the total number of low level events, it is necessary to to sum all struct
+ * sample_event.period and stash the result in total_period.
+ */
+struct events_stats {
+	u64 total_period;
+	u64 total_lost;
+	u32 nr_events[PERF_RECORD_HEADER_MAX];
+	u32 nr_unknown_events;
+};
+
+struct hists {
+	struct rb_node		rb_node;
+	struct rb_root		entries;
+	u64			nr_entries;
+	struct events_stats	stats;
+	u64			config;
+	u64			event_stream;
+	u32			type;
+	u32			max_sym_namelen;
+};
+
+struct hist_entry *__hists__add_entry(struct hists *self,
+				      struct addr_location *al,
+				      struct symbol *parent, u64 period);
 extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *);
 extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *);
+int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists,
+			bool show_displacement, long displacement, FILE *fp,
+			u64 total);
+int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size,
+			 struct hists *pair_hists, bool show_displacement,
+			 long displacement, bool color, u64 total);
 void hist_entry__free(struct hist_entry *);
 
-void perf_session__output_resort(struct rb_root *hists, u64 total_samples);
-void perf_session__collapse_resort(struct rb_root *hists);
-size_t perf_session__fprintf_hists(struct rb_root *hists,
-				   struct perf_session *pair,
-				   bool show_displacement, FILE *fp,
-				   u64 session_total);
+void hists__output_resort(struct hists *self);
+void hists__collapse_resort(struct hists *self);
+
+void hists__inc_nr_events(struct hists *self, u32 type);
+size_t hists__fprintf_nr_events(struct hists *self, FILE *fp);
+
+size_t hists__fprintf(struct hists *self, struct hists *pair,
+		      bool show_displacement, FILE *fp);
+
+int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip);
+int hist_entry__annotate(struct hist_entry *self, struct list_head *head);
+
+void hists__filter_by_dso(struct hists *self, const struct dso *dso);
+void hists__filter_by_thread(struct hists *self, const struct thread *thread);
+
+#ifdef NO_NEWT_SUPPORT
+static inline int hists__browse(struct hists *self __used,
+				const char *helpline __used,
+				const char *input_name __used)
+{
+	return 0;
+}
+#else
+int hists__browse(struct hists *self, const char *helpline,
+		  const char *input_name);
+#endif
 #endif	/* __PERF_HIST_H */

tools/perf/util/hweight.c

diff --git a/tools/perf/util/hweight.c b/tools/perf/util/hweight.c
new file mode 100644
index 0000000..5c1d0d0
--- /dev/null
+++ b/tools/perf/util/hweight.c
@@ -0,0 +1,31 @@
+#include <linux/bitops.h>
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+unsigned int hweight32(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x55555555);
+	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
+	res = (res + (res >> 4)) & 0x0F0F0F0F;
+	res = res + (res >> 8);
+	return (res + (res >> 16)) & 0x000000FF;
+}
+
+unsigned long hweight64(__u64 w)
+{
+#if BITS_PER_LONG == 32
+	return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
+#elif BITS_PER_LONG == 64
+	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
+	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
+	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
+	res = res + (res >> 8);
+	res = res + (res >> 16);
+	return (res + (res >> 32)) & 0x00000000000000FFul;
+#endif
+}

tools/perf/util/include/asm/bitops.h

diff --git a/tools/perf/util/include/asm/bitops.h b/tools/perf/util/include/asm/bitops.h
deleted file mode 100644
index 58e9817..0000000
--- a/tools/perf/util/include/asm/bitops.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef _PERF_ASM_BITOPS_H_
-#define _PERF_ASM_BITOPS_H_
-
-#include <sys/types.h>
-#include "../../types.h"
-#include <linux/compiler.h>
-
-/* CHECKME: Not sure both always match */
-#define BITS_PER_LONG	__WORDSIZE
-
-#include "../../../../include/asm-generic/bitops/__fls.h"
-#include "../../../../include/asm-generic/bitops/fls.h"
-#include "../../../../include/asm-generic/bitops/fls64.h"
-#include "../../../../include/asm-generic/bitops/__ffs.h"
-#include "../../../../include/asm-generic/bitops/ffz.h"
-#include "../../../../include/asm-generic/bitops/hweight.h"
-
-#endif

tools/perf/util/include/asm/hweight.h

diff --git a/tools/perf/util/include/asm/hweight.h b/tools/perf/util/include/asm/hweight.h
new file mode 100644
index 0000000..36cf26d
--- /dev/null
+++ b/tools/perf/util/include/asm/hweight.h
@@ -0,0 +1,8 @@
+#ifndef PERF_HWEIGHT_H
+#define PERF_HWEIGHT_H
+
+#include <linux/types.h>
+unsigned int hweight32(unsigned int w);
+unsigned long hweight64(__u64 w);
+
+#endif /* PERF_HWEIGHT_H */

tools/perf/util/include/dwarf-regs.h

diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
new file mode 100644
index 0000000..cf6727e
--- /dev/null
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_DWARF_REGS_H_
+#define _PERF_DWARF_REGS_H_
+
+#ifdef DWARF_SUPPORT
+const char *get_arch_regstr(unsigned int n);
+#endif
+
+#endif

tools/perf/util/include/linux/bitmap.h

diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
index 9450763..eda4416 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/perf/util/include/linux/bitmap.h
@@ -1,3 +1,35 @@
-#include "../../../../include/linux/bitmap.h"
-#include "../../../../include/asm-generic/bitops/find.h"
-#include <linux/errno.h>
+#ifndef _PERF_BITOPS_H
+#define _PERF_BITOPS_H
+
+#include <string.h>
+#include <linux/bitops.h>
+
+int __bitmap_weight(const unsigned long *bitmap, int bits);
+
+#define BITMAP_LAST_WORD_MASK(nbits)					\
+(									\
+	((nbits) % BITS_PER_LONG) ?					\
+		(1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL		\
+)
+
+#define small_const_nbits(nbits) \
+	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
+
+static inline void bitmap_zero(unsigned long *dst, int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = 0UL;
+	else {
+		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		memset(dst, 0, len);
+	}
+}
+
+static inline int bitmap_weight(const unsigned long *src, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
+	return __bitmap_weight(src, nbits);
+}
+
+#endif /* _PERF_BITOPS_H */

tools/perf/util/include/linux/bitops.h

diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index 8d63116..bb4ac2e 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -1,13 +1,12 @@
 #ifndef _PERF_LINUX_BITOPS_H_
 #define _PERF_LINUX_BITOPS_H_
 
-#define __KERNEL__
+#include <linux/kernel.h>
+#include <asm/hweight.h>
 
-#define CONFIG_GENERIC_FIND_NEXT_BIT
-#define CONFIG_GENERIC_FIND_FIRST_BIT
-#include "../../../../include/linux/bitops.h"
-
-#undef __KERNEL__
+#define BITS_PER_LONG __WORDSIZE
+#define BITS_PER_BYTE           8
+#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 
 static inline void set_bit(int nr, unsigned long *addr)
 {
@@ -20,10 +19,9 @@
 		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
 }
 
-unsigned long generic_find_next_zero_le_bit(const unsigned long *addr, unsigned
-		long size, unsigned long offset);
-
-unsigned long generic_find_next_le_bit(const unsigned long *addr, unsigned
-		long size, unsigned long offset);
+static inline unsigned long hweight_long(unsigned long w)
+{
+	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+}
 
 #endif

tools/perf/util/include/linux/compiler.h

diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
index dfb0713..791f9dd 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/perf/util/include/linux/compiler.h
@@ -7,4 +7,6 @@
 #define __user
 #define __attribute_const__
 
+#define __used		__attribute__((__unused__))
+
 #endif

tools/perf/util/include/linux/kernel.h

diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index f261165..1eb804f 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -28,6 +28,8 @@
 	(type *)((char *)__mptr - offsetof(type, member)); })
 #endif
 
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+
 #ifndef max
 #define max(x, y) ({				\
 	typeof(x) _max1 = (x);			\
@@ -85,16 +87,19 @@
 	return strtoul(nptr, endptr, base);
 }
 
+int eprintf(int level,
+	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
+
 #ifndef pr_fmt
 #define pr_fmt(fmt) fmt
 #endif
 
 #define pr_err(fmt, ...) \
-	do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0)
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_warning(fmt, ...) \
-	do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0)
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_info(fmt, ...) \
-	do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0)
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug(fmt, ...) \
 	eprintf(1, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debugN(n, fmt, ...) \

tools/perf/util/map.c

diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index e509cd5..e672f2f 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,9 +1,11 @@
-#include "event.h"
 #include "symbol.h"
+#include <errno.h>
+#include <limits.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stdio.h>
-#include "debug.h"
+#include <unistd.h>
+#include "map.h"
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -36,15 +38,16 @@
 	self->map_ip   = map__map_ip;
 	self->unmap_ip = map__unmap_ip;
 	RB_CLEAR_NODE(&self->rb_node);
+	self->groups   = NULL;
 }
 
-struct map *map__new(struct mmap_event *event, enum map_type type,
-		     char *cwd, int cwdlen)
+struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
+		     u64 pgoff, u32 pid, char *filename,
+		     enum map_type type, char *cwd, int cwdlen)
 {
 	struct map *self = malloc(sizeof(*self));
 
 	if (self != NULL) {
-		const char *filename = event->filename;
 		char newfilename[PATH_MAX];
 		struct dso *dso;
 		int anon;
@@ -62,16 +65,15 @@
 		anon = is_anon_memory(filename);
 
 		if (anon) {
-			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", event->pid);
+			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
 			filename = newfilename;
 		}
 
-		dso = dsos__findnew(filename);
+		dso = __dsos__findnew(dsos__list, filename);
 		if (dso == NULL)
 			goto out_delete;
 
-		map__init(self, type, event->start, event->start + event->len,
-			  event->pgoff, dso);
+		map__init(self, type, start, start + len, pgoff, dso);
 
 		if (anon) {
 set_identity:
@@ -235,3 +237,392 @@
 			map->unmap_ip(map, addr);	/* RIP -> IP */
 	return ip;
 }
+
+void map_groups__init(struct map_groups *self)
+{
+	int i;
+	for (i = 0; i < MAP__NR_TYPES; ++i) {
+		self->maps[i] = RB_ROOT;
+		INIT_LIST_HEAD(&self->removed_maps[i]);
+	}
+	self->machine = NULL;
+}
+
+void map_groups__flush(struct map_groups *self)
+{
+	int type;
+
+	for (type = 0; type < MAP__NR_TYPES; type++) {
+		struct rb_root *root = &self->maps[type];
+		struct rb_node *next = rb_first(root);
+
+		while (next) {
+			struct map *pos = rb_entry(next, struct map, rb_node);
+			next = rb_next(&pos->rb_node);
+			rb_erase(&pos->rb_node, root);
+			/*
+			 * We may have references to this map, for
+			 * instance in some hist_entry instances, so
+			 * just move them to a separate list.
+			 */
+			list_add_tail(&pos->node, &self->removed_maps[pos->type]);
+		}
+	}
+}
+
+struct symbol *map_groups__find_symbol(struct map_groups *self,
+				       enum map_type type, u64 addr,
+				       struct map **mapp,
+				       symbol_filter_t filter)
+{
+	struct map *map = map_groups__find(self, type, addr);
+
+	if (map != NULL) {
+		if (mapp != NULL)
+			*mapp = map;
+		return map__find_symbol(map, map->map_ip(map, addr), filter);
+	}
+
+	return NULL;
+}
+
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+					       enum map_type type,
+					       const char *name,
+					       struct map **mapp,
+					       symbol_filter_t filter)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node);
+		struct symbol *sym = map__find_symbol_by_name(pos, name, filter);
+
+		if (sym == NULL)
+			continue;
+		if (mapp != NULL)
+			*mapp = pos;
+		return sym;
+	}
+
+	return NULL;
+}
+
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+				  enum map_type type, int verbose, FILE *fp)
+{
+	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+	struct rb_node *nd;
+
+	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node);
+		printed += fprintf(fp, "Map:");
+		printed += map__fprintf(pos, fp);
+		if (verbose > 2) {
+			printed += dso__fprintf(pos->dso, type, fp);
+			printed += fprintf(fp, "--\n");
+		}
+	}
+
+	return printed;
+}
+
+size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp)
+{
+	size_t printed = 0, i;
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		printed += __map_groups__fprintf_maps(self, i, verbose, fp);
+	return printed;
+}
+
+static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
+						 enum map_type type,
+						 int verbose, FILE *fp)
+{
+	struct map *pos;
+	size_t printed = 0;
+
+	list_for_each_entry(pos, &self->removed_maps[type], node) {
+		printed += fprintf(fp, "Map:");
+		printed += map__fprintf(pos, fp);
+		if (verbose > 1) {
+			printed += dso__fprintf(pos->dso, type, fp);
+			printed += fprintf(fp, "--\n");
+		}
+	}
+	return printed;
+}
+
+static size_t map_groups__fprintf_removed_maps(struct map_groups *self,
+					       int verbose, FILE *fp)
+{
+	size_t printed = 0, i;
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		printed += __map_groups__fprintf_removed_maps(self, i, verbose, fp);
+	return printed;
+}
+
+size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp)
+{
+	size_t printed = map_groups__fprintf_maps(self, verbose, fp);
+	printed += fprintf(fp, "Removed maps:\n");
+	return printed + map_groups__fprintf_removed_maps(self, verbose, fp);
+}
+
+int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+				   int verbose, FILE *fp)
+{
+	struct rb_root *root = &self->maps[map->type];
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node);
+		next = rb_next(&pos->rb_node);
+
+		if (!map__overlap(pos, map))
+			continue;
+
+		if (verbose >= 2) {
+			fputs("overlapping maps:\n", fp);
+			map__fprintf(map, fp);
+			map__fprintf(pos, fp);
+		}
+
+		rb_erase(&pos->rb_node, root);
+		/*
+		 * We may have references to this map, for instance in some
+		 * hist_entry instances, so just move them to a separate
+		 * list.
+		 */
+		list_add_tail(&pos->node, &self->removed_maps[map->type]);
+		/*
+		 * Now check if we need to create new maps for areas not
+		 * overlapped by the new map:
+		 */
+		if (map->start > pos->start) {
+			struct map *before = map__clone(pos);
+
+			if (before == NULL)
+				return -ENOMEM;
+
+			before->end = map->start - 1;
+			map_groups__insert(self, before);
+			if (verbose >= 2)
+				map__fprintf(before, fp);
+		}
+
+		if (map->end < pos->end) {
+			struct map *after = map__clone(pos);
+
+			if (after == NULL)
+				return -ENOMEM;
+
+			after->start = map->end + 1;
+			map_groups__insert(self, after);
+			if (verbose >= 2)
+				map__fprintf(after, fp);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * XXX This should not really _copy_ te maps, but refcount them.
+ */
+int map_groups__clone(struct map_groups *self,
+		      struct map_groups *parent, enum map_type type)
+{
+	struct rb_node *nd;
+	for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
+		struct map *map = rb_entry(nd, struct map, rb_node);
+		struct map *new = map__clone(map);
+		if (new == NULL)
+			return -ENOMEM;
+		map_groups__insert(self, new);
+	}
+	return 0;
+}
+
+static u64 map__reloc_map_ip(struct map *map, u64 ip)
+{
+	return ip + (s64)map->pgoff;
+}
+
+static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
+{
+	return ip - (s64)map->pgoff;
+}
+
+void map__reloc_vmlinux(struct map *self)
+{
+	struct kmap *kmap = map__kmap(self);
+	s64 reloc;
+
+	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
+		return;
+
+	reloc = (kmap->ref_reloc_sym->unrelocated_addr -
+		 kmap->ref_reloc_sym->addr);
+
+	if (!reloc)
+		return;
+
+	self->map_ip   = map__reloc_map_ip;
+	self->unmap_ip = map__reloc_unmap_ip;
+	self->pgoff    = reloc;
+}
+
+void maps__insert(struct rb_root *maps, struct map *map)
+{
+	struct rb_node **p = &maps->rb_node;
+	struct rb_node *parent = NULL;
+	const u64 ip = map->start;
+	struct map *m;
+
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct map, rb_node);
+		if (ip < m->start)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&map->rb_node, parent, p);
+	rb_insert_color(&map->rb_node, maps);
+}
+
+struct map *maps__find(struct rb_root *maps, u64 ip)
+{
+	struct rb_node **p = &maps->rb_node;
+	struct rb_node *parent = NULL;
+	struct map *m;
+
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct map, rb_node);
+		if (ip < m->start)
+			p = &(*p)->rb_left;
+		else if (ip > m->end)
+			p = &(*p)->rb_right;
+		else
+			return m;
+	}
+
+	return NULL;
+}
+
+int machine__init(struct machine *self, const char *root_dir, pid_t pid)
+{
+	map_groups__init(&self->kmaps);
+	RB_CLEAR_NODE(&self->rb_node);
+	INIT_LIST_HEAD(&self->user_dsos);
+	INIT_LIST_HEAD(&self->kernel_dsos);
+
+	self->kmaps.machine = self;
+	self->pid	    = pid;
+	self->root_dir      = strdup(root_dir);
+	return self->root_dir == NULL ? -ENOMEM : 0;
+}
+
+struct machine *machines__add(struct rb_root *self, pid_t pid,
+			      const char *root_dir)
+{
+	struct rb_node **p = &self->rb_node;
+	struct rb_node *parent = NULL;
+	struct machine *pos, *machine = malloc(sizeof(*machine));
+
+	if (!machine)
+		return NULL;
+
+	if (machine__init(machine, root_dir, pid) != 0) {
+		free(machine);
+		return NULL;
+	}
+
+	while (*p != NULL) {
+		parent = *p;
+		pos = rb_entry(parent, struct machine, rb_node);
+		if (pid < pos->pid)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&machine->rb_node, parent, p);
+	rb_insert_color(&machine->rb_node, self);
+
+	return machine;
+}
+
+struct machine *machines__find(struct rb_root *self, pid_t pid)
+{
+	struct rb_node **p = &self->rb_node;
+	struct rb_node *parent = NULL;
+	struct machine *machine;
+	struct machine *default_machine = NULL;
+
+	while (*p != NULL) {
+		parent = *p;
+		machine = rb_entry(parent, struct machine, rb_node);
+		if (pid < machine->pid)
+			p = &(*p)->rb_left;
+		else if (pid > machine->pid)
+			p = &(*p)->rb_right;
+		else
+			return machine;
+		if (!machine->pid)
+			default_machine = machine;
+	}
+
+	return default_machine;
+}
+
+struct machine *machines__findnew(struct rb_root *self, pid_t pid)
+{
+	char path[PATH_MAX];
+	const char *root_dir;
+	struct machine *machine = machines__find(self, pid);
+
+	if (!machine || machine->pid != pid) {
+		if (pid == HOST_KERNEL_ID || pid == DEFAULT_GUEST_KERNEL_ID)
+			root_dir = "";
+		else {
+			if (!symbol_conf.guestmount)
+				goto out;
+			sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
+			if (access(path, R_OK)) {
+				pr_err("Can't access file %s\n", path);
+				goto out;
+			}
+			root_dir = path;
+		}
+		machine = machines__add(self, pid, root_dir);
+	}
+
+out:
+	return machine;
+}
+
+void machines__process(struct rb_root *self, machine__process_t process, void *data)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		process(pos, data);
+	}
+}
+
+char *machine__mmap_name(struct machine *self, char *bf, size_t size)
+{
+	if (machine__is_host(self))
+		snprintf(bf, size, "[%s]", "kernel.kallsyms");
+	else if (machine__is_default_guest(self))
+		snprintf(bf, size, "[%s]", "guest.kernel.kallsyms");
+	else
+		snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms", self->pid);
+
+	return bf;
+}

tools/perf/util/map.h

diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index b756368..f391345 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -4,7 +4,9 @@
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
-#include <linux/types.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include "types.h"
 
 enum map_type {
 	MAP__FUNCTION = 0,
@@ -18,6 +20,7 @@
 struct dso;
 struct ref_reloc_sym;
 struct map_groups;
+struct machine;
 
 struct map {
 	union {
@@ -27,6 +30,7 @@
 	u64			start;
 	u64			end;
 	enum map_type		type;
+	u32			priv;
 	u64			pgoff;
 
 	/* ip -> dso rip */
@@ -35,6 +39,7 @@
 	u64			(*unmap_ip)(struct map *, u64);
 
 	struct dso		*dso;
+	struct map_groups	*groups;
 };
 
 struct kmap {
@@ -42,6 +47,32 @@
 	struct map_groups	*kmaps;
 };
 
+struct map_groups {
+	struct rb_root	 maps[MAP__NR_TYPES];
+	struct list_head removed_maps[MAP__NR_TYPES];
+	struct machine	 *machine;
+};
+
+/* Native host kernel uses -1 as pid index in machine */
+#define	HOST_KERNEL_ID			(-1)
+#define	DEFAULT_GUEST_KERNEL_ID		(0)
+
+struct machine {
+	struct rb_node	  rb_node;
+	pid_t		  pid;
+	char		  *root_dir;
+	struct list_head  user_dsos;
+	struct list_head  kernel_dsos;
+	struct map_groups kmaps;
+	struct map	  *vmlinux_maps[MAP__NR_TYPES];
+};
+
+static inline
+struct map *machine__kernel_map(struct machine *self, enum map_type type)
+{
+	return self->vmlinux_maps[type];
+}
+
 static inline struct kmap *map__kmap(struct map *self)
 {
 	return (struct kmap *)(self + 1);
@@ -68,14 +99,14 @@
 u64 map__objdump_2ip(struct map *map, u64 addr);
 
 struct symbol;
-struct mmap_event;
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *self, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
-struct map *map__new(struct mmap_event *event, enum map_type,
-		     char *cwd, int cwdlen);
+struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
+		     u64 pgoff, u32 pid, char *filename,
+		     enum map_type type, char *cwd, int cwdlen);
 void map__delete(struct map *self);
 struct map *map__clone(struct map *self);
 int map__overlap(struct map *l, struct map *r);
@@ -91,4 +122,96 @@
 
 void map__reloc_vmlinux(struct map *self);
 
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+				  enum map_type type, int verbose, FILE *fp);
+void maps__insert(struct rb_root *maps, struct map *map);
+struct map *maps__find(struct rb_root *maps, u64 addr);
+void map_groups__init(struct map_groups *self);
+int map_groups__clone(struct map_groups *self,
+		      struct map_groups *parent, enum map_type type);
+size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp);
+size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp);
+
+typedef void (*machine__process_t)(struct machine *self, void *data);
+
+void machines__process(struct rb_root *self, machine__process_t process, void *data);
+struct machine *machines__add(struct rb_root *self, pid_t pid,
+			      const char *root_dir);
+struct machine *machines__find_host(struct rb_root *self);
+struct machine *machines__find(struct rb_root *self, pid_t pid);
+struct machine *machines__findnew(struct rb_root *self, pid_t pid);
+char *machine__mmap_name(struct machine *self, char *bf, size_t size);
+int machine__init(struct machine *self, const char *root_dir, pid_t pid);
+
+/*
+ * Default guest kernel is defined by parameter --guestkallsyms
+ * and --guestmodules
+ */
+static inline bool machine__is_default_guest(struct machine *self)
+{
+	return self ? self->pid == DEFAULT_GUEST_KERNEL_ID : false;
+}
+
+static inline bool machine__is_host(struct machine *self)
+{
+	return self ? self->pid == HOST_KERNEL_ID : false;
+}
+
+static inline void map_groups__insert(struct map_groups *self, struct map *map)
+{
+	maps__insert(&self->maps[map->type], map);
+	map->groups = self;
+}
+
+static inline struct map *map_groups__find(struct map_groups *self,
+					   enum map_type type, u64 addr)
+{
+	return maps__find(&self->maps[type], addr);
+}
+
+struct symbol *map_groups__find_symbol(struct map_groups *self,
+				       enum map_type type, u64 addr,
+				       struct map **mapp,
+				       symbol_filter_t filter);
+
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+					       enum map_type type,
+					       const char *name,
+					       struct map **mapp,
+					       symbol_filter_t filter);
+
+static inline
+struct symbol *machine__find_kernel_symbol(struct machine *self,
+					   enum map_type type, u64 addr,
+					   struct map **mapp,
+					   symbol_filter_t filter)
+{
+	return map_groups__find_symbol(&self->kmaps, type, addr, mapp, filter);
+}
+
+static inline
+struct symbol *machine__find_kernel_function(struct machine *self, u64 addr,
+					     struct map **mapp,
+					     symbol_filter_t filter)
+{
+	return machine__find_kernel_symbol(self, MAP__FUNCTION, addr, mapp, filter);
+}
+
+static inline
+struct symbol *map_groups__find_function_by_name(struct map_groups *self,
+						 const char *name, struct map **mapp,
+						 symbol_filter_t filter)
+{
+	return map_groups__find_symbol_by_name(self, MAP__FUNCTION, name, mapp, filter);
+}
+
+int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+				   int verbose, FILE *fp);
+
+struct map *map_groups__find_by_name(struct map_groups *self,
+				     enum map_type type, const char *name);
+struct map *machine__new_module(struct machine *self, u64 start, const char *filename);
+
+void map_groups__flush(struct map_groups *self);
+
 #endif /* __PERF_MAP_H */

tools/perf/util/newt.c

diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c
new file mode 100644
index 0000000..ccb7c5b
--- /dev/null
+++ b/tools/perf/util/newt.c
@@ -0,0 +1,1084 @@
+#define _GNU_SOURCE
+#include <stdio.h>
+#undef _GNU_SOURCE
+
+#include <slang.h>
+#include <stdlib.h>
+#include <newt.h>
+#include <sys/ttydefaults.h>
+
+#include "cache.h"
+#include "hist.h"
+#include "pstack.h"
+#include "session.h"
+#include "sort.h"
+#include "symbol.h"
+
+#if SLANG_VERSION < 20104
+#define slsmg_printf(msg, args...) SLsmg_printf((char *)msg, ##args)
+#define slsmg_write_nstring(msg, len) SLsmg_write_nstring((char *)msg, len)
+#define sltt_set_color(obj, name, fg, bg) SLtt_set_color(obj,(char *)name,\
+							 (char *)fg, (char *)bg)
+#else
+#define slsmg_printf SLsmg_printf
+#define slsmg_write_nstring SLsmg_write_nstring
+#define sltt_set_color SLtt_set_color
+#endif
+
+struct ui_progress {
+	newtComponent form, scale;
+};
+
+struct ui_progress *ui_progress__new(const char *title, u64 total)
+{
+	struct ui_progress *self = malloc(sizeof(*self));
+
+	if (self != NULL) {
+		int cols;
+		newtGetScreenSize(&cols, NULL);
+		cols -= 4;
+		newtCenteredWindow(cols, 1, title);
+		self->form  = newtForm(NULL, NULL, 0);
+		if (self->form == NULL)
+			goto out_free_self;
+		self->scale = newtScale(0, 0, cols, total);
+		if (self->scale == NULL)
+			goto out_free_form;
+		newtFormAddComponent(self->form, self->scale);
+		newtRefresh();
+	}
+
+	return self;
+
+out_free_form:
+	newtFormDestroy(self->form);
+out_free_self:
+	free(self);
+	return NULL;
+}
+
+void ui_progress__update(struct ui_progress *self, u64 curr)
+{
+	newtScaleSet(self->scale, curr);
+	newtRefresh();
+}
+
+void ui_progress__delete(struct ui_progress *self)
+{
+	newtFormDestroy(self->form);
+	newtPopWindow();
+	free(self);
+}
+
+static void ui_helpline__pop(void)
+{
+	newtPopHelpLine();
+}
+
+static void ui_helpline__push(const char *msg)
+{
+	newtPushHelpLine(msg);
+}
+
+static void ui_helpline__vpush(const char *fmt, va_list ap)
+{
+	char *s;
+
+	if (vasprintf(&s, fmt, ap) < 0)
+		vfprintf(stderr, fmt, ap);
+	else {
+		ui_helpline__push(s);
+		free(s);
+	}
+}
+
+static void ui_helpline__fpush(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	ui_helpline__vpush(fmt, ap);
+	va_end(ap);
+}
+
+static void ui_helpline__puts(const char *msg)
+{
+	ui_helpline__pop();
+	ui_helpline__push(msg);
+}
+
+static char browser__last_msg[1024];
+
+int browser__show_help(const char *format, va_list ap)
+{
+	int ret;
+	static int backlog;
+
+        ret = vsnprintf(browser__last_msg + backlog,
+			sizeof(browser__last_msg) - backlog, format, ap);
+	backlog += ret;
+
+	if (browser__last_msg[backlog - 1] == '\n') {
+		ui_helpline__puts(browser__last_msg);
+		newtRefresh();
+		backlog = 0;
+	}
+
+	return ret;
+}
+
+static void newt_form__set_exit_keys(newtComponent self)
+{
+	newtFormAddHotKey(self, NEWT_KEY_LEFT);
+	newtFormAddHotKey(self, NEWT_KEY_ESCAPE);
+	newtFormAddHotKey(self, 'Q');
+	newtFormAddHotKey(self, 'q');
+	newtFormAddHotKey(self, CTRL('c'));
+}
+
+static newtComponent newt_form__new(void)
+{
+	newtComponent self = newtForm(NULL, NULL, 0);
+	if (self)
+		newt_form__set_exit_keys(self);
+	return self;
+}
+
+static int popup_menu(int argc, char * const argv[])
+{
+	struct newtExitStruct es;
+	int i, rc = -1, max_len = 5;
+	newtComponent listbox, form = newt_form__new();
+
+	if (form == NULL)
+		return -1;
+
+	listbox = newtListbox(0, 0, argc, NEWT_FLAG_RETURNEXIT);
+	if (listbox == NULL)
+		goto out_destroy_form;
+
+	newtFormAddComponent(form, listbox);
+
+	for (i = 0; i < argc; ++i) {
+		int len = strlen(argv[i]);
+		if (len > max_len)
+			max_len = len;
+		if (newtListboxAddEntry(listbox, argv[i], (void *)(long)i))
+			goto out_destroy_form;
+	}
+
+	newtCenteredWindow(max_len, argc, NULL);
+	newtFormRun(form, &es);
+	rc = newtListboxGetCurrent(listbox) - NULL;
+	if (es.reason == NEWT_EXIT_HOTKEY)
+		rc = -1;
+	newtPopWindow();
+out_destroy_form:
+	newtFormDestroy(form);
+	return rc;
+}
+
+static int ui__help_window(const char *text)
+{
+	struct newtExitStruct es;
+	newtComponent tb, form = newt_form__new();
+	int rc = -1;
+	int max_len = 0, nr_lines = 0;
+	const char *t;
+
+	if (form == NULL)
+		return -1;
+
+	t = text;
+	while (1) {
+		const char *sep = strchr(t, '\n');
+		int len;
+
+		if (sep == NULL)
+			sep = strchr(t, '\0');
+		len = sep - t;
+		if (max_len < len)
+			max_len = len;
+		++nr_lines;
+		if (*sep == '\0')
+			break;
+		t = sep + 1;
+	}
+
+	tb = newtTextbox(0, 0, max_len, nr_lines, 0);
+	if (tb == NULL)
+		goto out_destroy_form;
+
+	newtTextboxSetText(tb, text);
+	newtFormAddComponent(form, tb);
+	newtCenteredWindow(max_len, nr_lines, NULL);
+	newtFormRun(form, &es);
+	newtPopWindow();
+	rc = 0;
+out_destroy_form:
+	newtFormDestroy(form);
+	return rc;
+}
+
+static bool dialog_yesno(const char *msg)
+{
+	/* newtWinChoice should really be accepting const char pointers... */
+	char yes[] = "Yes", no[] = "No";
+	return newtWinChoice(NULL, yes, no, (char *)msg) == 1;
+}
+
+#define HE_COLORSET_TOP		50
+#define HE_COLORSET_MEDIUM	51
+#define HE_COLORSET_NORMAL	52
+#define HE_COLORSET_SELECTED	53
+#define HE_COLORSET_CODE	54
+
+static int ui_browser__percent_color(double percent, bool current)
+{
+	if (current)
+		return HE_COLORSET_SELECTED;
+	if (percent >= MIN_RED)
+		return HE_COLORSET_TOP;
+	if (percent >= MIN_GREEN)
+		return HE_COLORSET_MEDIUM;
+	return HE_COLORSET_NORMAL;
+}
+
+struct ui_browser {
+	newtComponent	form, sb;
+	u64		index, first_visible_entry_idx;
+	void		*first_visible_entry, *entries;
+	u16		top, left, width, height;
+	void		*priv;
+	u32		nr_entries;
+};
+
+static void ui_browser__refresh_dimensions(struct ui_browser *self)
+{
+	int cols, rows;
+	newtGetScreenSize(&cols, &rows);
+
+	if (self->width > cols - 4)
+		self->width = cols - 4;
+	self->height = rows - 5;
+	if (self->height > self->nr_entries)
+		self->height = self->nr_entries;
+	self->top  = (rows - self->height) / 2;
+	self->left = (cols - self->width) / 2;
+}
+
+static void ui_browser__reset_index(struct ui_browser *self)
+{
+        self->index = self->first_visible_entry_idx = 0;
+        self->first_visible_entry = NULL;
+}
+
+static int objdump_line__show(struct objdump_line *self, struct list_head *head,
+			      int width, struct hist_entry *he, int len,
+			      bool current_entry)
+{
+	if (self->offset != -1) {
+		struct symbol *sym = he->ms.sym;
+		unsigned int hits = 0;
+		double percent = 0.0;
+		int color;
+		struct sym_priv *priv = symbol__priv(sym);
+		struct sym_ext *sym_ext = priv->ext;
+		struct sym_hist *h = priv->hist;
+		s64 offset = self->offset;
+		struct objdump_line *next = objdump__get_next_ip_line(head, self);
+
+		while (offset < (s64)len &&
+		       (next == NULL || offset < next->offset)) {
+			if (sym_ext) {
+				percent += sym_ext[offset].percent;
+			} else
+				hits += h->ip[offset];
+
+			++offset;
+		}
+
+		if (sym_ext == NULL && h->sum)
+			percent = 100.0 * hits / h->sum;
+
+		color = ui_browser__percent_color(percent, current_entry);
+		SLsmg_set_color(color);
+		slsmg_printf(" %7.2f ", percent);
+		if (!current_entry)
+			SLsmg_set_color(HE_COLORSET_CODE);
+	} else {
+		int color = ui_browser__percent_color(0, current_entry);
+		SLsmg_set_color(color);
+		slsmg_write_nstring(" ", 9);
+	}
+
+	SLsmg_write_char(':');
+	slsmg_write_nstring(" ", 8);
+	if (!*self->line)
+		slsmg_write_nstring(" ", width - 18);
+	else
+		slsmg_write_nstring(self->line, width - 18);
+
+	return 0;
+}
+
+static int ui_browser__refresh_entries(struct ui_browser *self)
+{
+	struct objdump_line *pos;
+	struct list_head *head = self->entries;
+	struct hist_entry *he = self->priv;
+	int row = 0;
+	int len = he->ms.sym->end - he->ms.sym->start;
+
+	if (self->first_visible_entry == NULL || self->first_visible_entry == self->entries)
+                self->first_visible_entry = head->next;
+
+	pos = list_entry(self->first_visible_entry, struct objdump_line, node);
+
+	list_for_each_entry_from(pos, head, node) {
+		bool current_entry = (self->first_visible_entry_idx + row) == self->index;
+		SLsmg_gotorc(self->top + row, self->left);
+		objdump_line__show(pos, head, self->width,
+				   he, len, current_entry);
+		if (++row == self->height)
+			break;
+	}
+
+	SLsmg_set_color(HE_COLORSET_NORMAL);
+	SLsmg_fill_region(self->top + row, self->left,
+			  self->height - row, self->width, ' ');
+
+	return 0;
+}
+
+static int ui_browser__run(struct ui_browser *self, const char *title,
+			   struct newtExitStruct *es)
+{
+	if (self->form) {
+		newtFormDestroy(self->form);
+		newtPopWindow();
+	}
+
+	ui_browser__refresh_dimensions(self);
+	newtCenteredWindow(self->width + 2, self->height, title);
+	self->form = newt_form__new();
+	if (self->form == NULL)
+		return -1;
+
+	self->sb = newtVerticalScrollbar(self->width + 1, 0, self->height,
+					 HE_COLORSET_NORMAL,
+					 HE_COLORSET_SELECTED);
+	if (self->sb == NULL)
+		return -1;
+
+	newtFormAddHotKey(self->form, NEWT_KEY_UP);
+	newtFormAddHotKey(self->form, NEWT_KEY_DOWN);
+	newtFormAddHotKey(self->form, NEWT_KEY_PGUP);
+	newtFormAddHotKey(self->form, NEWT_KEY_PGDN);
+	newtFormAddHotKey(self->form, NEWT_KEY_HOME);
+	newtFormAddHotKey(self->form, NEWT_KEY_END);
+
+	if (ui_browser__refresh_entries(self) < 0)
+		return -1;
+	newtFormAddComponent(self->form, self->sb);
+
+	while (1) {
+		unsigned int offset;
+
+		newtFormRun(self->form, es);
+
+		if (es->reason != NEWT_EXIT_HOTKEY)
+			break;
+		switch (es->u.key) {
+		case NEWT_KEY_DOWN:
+			if (self->index == self->nr_entries - 1)
+				break;
+			++self->index;
+			if (self->index == self->first_visible_entry_idx + self->height) {
+				struct list_head *pos = self->first_visible_entry;
+				++self->first_visible_entry_idx;
+				self->first_visible_entry = pos->next;
+			}
+			break;
+		case NEWT_KEY_UP:
+			if (self->index == 0)
+				break;
+			--self->index;
+			if (self->index < self->first_visible_entry_idx) {
+				struct list_head *pos = self->first_visible_entry;
+				--self->first_visible_entry_idx;
+				self->first_visible_entry = pos->prev;
+			}
+			break;
+		case NEWT_KEY_PGDN:
+			if (self->first_visible_entry_idx + self->height > self->nr_entries - 1)
+				break;
+
+			offset = self->height;
+			if (self->index + offset > self->nr_entries - 1)
+				offset = self->nr_entries - 1 - self->index;
+			self->index += offset;
+			self->first_visible_entry_idx += offset;
+
+			while (offset--) {
+				struct list_head *pos = self->first_visible_entry;
+				self->first_visible_entry = pos->next;
+			}
+
+			break;
+		case NEWT_KEY_PGUP:
+			if (self->first_visible_entry_idx == 0)
+				break;
+
+			if (self->first_visible_entry_idx < self->height)
+				offset = self->first_visible_entry_idx;
+			else
+				offset = self->height;
+
+			self->index -= offset;
+			self->first_visible_entry_idx -= offset;
+
+			while (offset--) {
+				struct list_head *pos = self->first_visible_entry;
+				self->first_visible_entry = pos->prev;
+			}
+			break;
+		case NEWT_KEY_HOME:
+			ui_browser__reset_index(self);
+			break;
+		case NEWT_KEY_END: {
+			struct list_head *head = self->entries;
+			offset = self->height - 1;
+
+			if (offset > self->nr_entries)
+				offset = self->nr_entries;
+
+			self->index = self->first_visible_entry_idx = self->nr_entries - 1 - offset;
+			self->first_visible_entry = head->prev;
+			while (offset-- != 0) {
+				struct list_head *pos = self->first_visible_entry;
+				self->first_visible_entry = pos->prev;
+			}
+		}
+			break;
+		case NEWT_KEY_ESCAPE:
+		case NEWT_KEY_LEFT:
+		case CTRL('c'):
+		case 'Q':
+		case 'q':
+			return 0;
+		default:
+			continue;
+		}
+		if (ui_browser__refresh_entries(self) < 0)
+			return -1;
+	}
+	return 0;
+}
+
+/*
+ * When debugging newt problems it was useful to be able to "unroll"
+ * the calls to newtCheckBoxTreeAdd{Array,Item}, so that we can generate
+ * a source file with the sequence of calls to these methods, to then
+ * tweak the arrays to get the intended results, so I'm keeping this code
+ * here, may be useful again in the future.
+ */
+#undef NEWT_DEBUG
+
+static void newt_checkbox_tree__add(newtComponent tree, const char *str,
+				    void *priv, int *indexes)
+{
+#ifdef NEWT_DEBUG
+	/* Print the newtCheckboxTreeAddArray to tinker with its index arrays */
+	int i = 0, len = 40 - strlen(str);
+
+	fprintf(stderr,
+		"\tnewtCheckboxTreeAddItem(tree, %*.*s\"%s\", (void *)%p, 0, ",
+		len, len, " ", str, priv);
+	while (indexes[i] != NEWT_ARG_LAST) {
+		if (indexes[i] != NEWT_ARG_APPEND)
+			fprintf(stderr, " %d,", indexes[i]);
+		else
+			fprintf(stderr, " %s,", "NEWT_ARG_APPEND");
+		++i;
+	}
+	fprintf(stderr, " %s", " NEWT_ARG_LAST);\n");
+	fflush(stderr);
+#endif
+	newtCheckboxTreeAddArray(tree, str, priv, 0, indexes);
+}
+
+static char *callchain_list__sym_name(struct callchain_list *self,
+				      char *bf, size_t bfsize)
+{
+	if (self->ms.sym)
+		return self->ms.sym->name;
+
+	snprintf(bf, bfsize, "%#Lx", self->ip);
+	return bf;
+}
+
+static void __callchain__append_graph_browser(struct callchain_node *self,
+					      newtComponent tree, u64 total,
+					      int *indexes, int depth)
+{
+	struct rb_node *node;
+	u64 new_total, remaining;
+	int idx = 0;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		new_total = self->children_hit;
+	else
+		new_total = total;
+
+	remaining = new_total;
+	node = rb_first(&self->rb_root);
+	while (node) {
+		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+		struct rb_node *next = rb_next(node);
+		u64 cumul = cumul_hits(child);
+		struct callchain_list *chain;
+		int first = true, printed = 0;
+		int chain_idx = -1;
+		remaining -= cumul;
+
+		indexes[depth] = NEWT_ARG_APPEND;
+		indexes[depth + 1] = NEWT_ARG_LAST;
+
+		list_for_each_entry(chain, &child->val, list) {
+			char ipstr[BITS_PER_LONG / 4 + 1],
+			     *alloc_str = NULL;
+			const char *str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+
+			if (first) {
+				double percent = cumul * 100.0 / new_total;
+
+				first = false;
+				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
+					str = "Not enough memory!";
+				else
+					str = alloc_str;
+			} else {
+				indexes[depth] = idx;
+				indexes[depth + 1] = NEWT_ARG_APPEND;
+				indexes[depth + 2] = NEWT_ARG_LAST;
+				++chain_idx;
+			}
+			newt_checkbox_tree__add(tree, str, &chain->ms, indexes);
+			free(alloc_str);
+			++printed;
+		}
+
+		indexes[depth] = idx;
+		if (chain_idx != -1)
+			indexes[depth + 1] = chain_idx;
+		if (printed != 0)
+			++idx;
+		__callchain__append_graph_browser(child, tree, new_total, indexes,
+						  depth + (chain_idx != -1 ? 2 : 1));
+		node = next;
+	}
+}
+
+static void callchain__append_graph_browser(struct callchain_node *self,
+					    newtComponent tree, u64 total,
+					    int *indexes, int parent_idx)
+{
+	struct callchain_list *chain;
+	int i = 0;
+
+	indexes[1] = NEWT_ARG_APPEND;
+	indexes[2] = NEWT_ARG_LAST;
+
+	list_for_each_entry(chain, &self->val, list) {
+		char ipstr[BITS_PER_LONG / 4 + 1], *str;
+
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+
+		if (!i++ && sort__first_dimension == SORT_SYM)
+			continue;
+
+		str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+		newt_checkbox_tree__add(tree, str, &chain->ms, indexes);
+	}
+
+	indexes[1] = parent_idx;
+	indexes[2] = NEWT_ARG_APPEND;
+	indexes[3] = NEWT_ARG_LAST;
+	__callchain__append_graph_browser(self, tree, total, indexes, 2);
+}
+
+static void hist_entry__append_callchain_browser(struct hist_entry *self,
+						 newtComponent tree, u64 total, int parent_idx)
+{
+	struct rb_node *rb_node;
+	int indexes[1024] = { [0] = parent_idx, };
+	int idx = 0;
+	struct callchain_node *chain;
+
+	rb_node = rb_first(&self->sorted_chain);
+	while (rb_node) {
+		chain = rb_entry(rb_node, struct callchain_node, rb_node);
+		switch (callchain_param.mode) {
+		case CHAIN_FLAT:
+			break;
+		case CHAIN_GRAPH_ABS: /* falldown */
+		case CHAIN_GRAPH_REL:
+			callchain__append_graph_browser(chain, tree, total, indexes, idx++);
+			break;
+		case CHAIN_NONE:
+		default:
+			break;
+		}
+		rb_node = rb_next(rb_node);
+	}
+}
+
+static size_t hist_entry__append_browser(struct hist_entry *self,
+					 newtComponent tree, u64 total)
+{
+	char s[256];
+	size_t ret;
+
+	if (symbol_conf.exclude_other && !self->parent)
+		return 0;
+
+	ret = hist_entry__snprintf(self, s, sizeof(s), NULL,
+				   false, 0, false, total);
+	if (symbol_conf.use_callchain) {
+		int indexes[2];
+
+		indexes[0] = NEWT_ARG_APPEND;
+		indexes[1] = NEWT_ARG_LAST;
+		newt_checkbox_tree__add(tree, s, &self->ms, indexes);
+	} else
+		newtListboxAppendEntry(tree, s, &self->ms);
+
+	return ret;
+}
+
+static void hist_entry__annotate_browser(struct hist_entry *self)
+{
+	struct ui_browser browser;
+	struct newtExitStruct es;
+	struct objdump_line *pos, *n;
+	LIST_HEAD(head);
+
+	if (self->ms.sym == NULL)
+		return;
+
+	if (hist_entry__annotate(self, &head) < 0)
+		return;
+
+	ui_helpline__push("Press <- or ESC to exit");
+
+	memset(&browser, 0, sizeof(browser));
+	browser.entries = &head;
+	browser.priv = self;
+	list_for_each_entry(pos, &head, node) {
+		size_t line_len = strlen(pos->line);
+		if (browser.width < line_len)
+			browser.width = line_len;
+		++browser.nr_entries;
+	}
+
+	browser.width += 18; /* Percentage */
+	ui_browser__run(&browser, self->ms.sym->name, &es);
+	newtFormDestroy(browser.form);
+	newtPopWindow();
+	list_for_each_entry_safe(pos, n, &head, node) {
+		list_del(&pos->node);
+		objdump_line__free(pos);
+	}
+	ui_helpline__pop();
+}
+
+static const void *newt__symbol_tree_get_current(newtComponent self)
+{
+	if (symbol_conf.use_callchain)
+		return newtCheckboxTreeGetCurrent(self);
+	return newtListboxGetCurrent(self);
+}
+
+static void hist_browser__selection(newtComponent self, void *data)
+{
+	const struct map_symbol **symbol_ptr = data;
+	*symbol_ptr = newt__symbol_tree_get_current(self);
+}
+
+struct hist_browser {
+	newtComponent		form, tree;
+	const struct map_symbol *selection;
+};
+
+static struct hist_browser *hist_browser__new(void)
+{
+	struct hist_browser *self = malloc(sizeof(*self));
+
+	if (self != NULL)
+		self->form = NULL;
+
+	return self;
+}
+
+static void hist_browser__delete(struct hist_browser *self)
+{
+	newtFormDestroy(self->form);
+	newtPopWindow();
+	free(self);
+}
+
+static int hist_browser__populate(struct hist_browser *self, struct hists *hists,
+				  const char *title)
+{
+	int max_len = 0, idx, cols, rows;
+	struct ui_progress *progress;
+	struct rb_node *nd;
+	u64 curr_hist = 0;
+	char seq[] = ".", unit;
+	char str[256];
+	unsigned long nr_events = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+
+	if (self->form) {
+		newtFormDestroy(self->form);
+		newtPopWindow();
+	}
+
+	nr_events = convert_unit(nr_events, &unit);
+	snprintf(str, sizeof(str), "Events: %lu%c                            ",
+		 nr_events, unit);
+	newtDrawRootText(0, 0, str);
+
+	newtGetScreenSize(NULL, &rows);
+
+	if (symbol_conf.use_callchain)
+		self->tree = newtCheckboxTreeMulti(0, 0, rows - 5, seq,
+						   NEWT_FLAG_SCROLL);
+	else
+		self->tree = newtListbox(0, 0, rows - 5,
+					(NEWT_FLAG_SCROLL |
+					 NEWT_FLAG_RETURNEXIT));
+
+	newtComponentAddCallback(self->tree, hist_browser__selection,
+				 &self->selection);
+
+	progress = ui_progress__new("Adding entries to the browser...",
+				    hists->nr_entries);
+	if (progress == NULL)
+		return -1;
+
+	idx = 0;
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		int len;
+
+		if (h->filtered)
+			continue;
+
+		len = hist_entry__append_browser(h, self->tree, hists->stats.total_period);
+		if (len > max_len)
+			max_len = len;
+		if (symbol_conf.use_callchain)
+			hist_entry__append_callchain_browser(h, self->tree,
+							     hists->stats.total_period, idx++);
+		++curr_hist;
+		if (curr_hist % 5)
+			ui_progress__update(progress, curr_hist);
+	}
+
+	ui_progress__delete(progress);
+
+	newtGetScreenSize(&cols, &rows);
+
+	if (max_len > cols)
+		max_len = cols - 3;
+
+	if (!symbol_conf.use_callchain)
+		newtListboxSetWidth(self->tree, max_len);
+
+	newtCenteredWindow(max_len + (symbol_conf.use_callchain ? 5 : 0),
+			   rows - 5, title);
+	self->form = newt_form__new();
+	if (self->form == NULL)
+		return -1;
+
+	newtFormAddHotKey(self->form, 'A');
+	newtFormAddHotKey(self->form, 'a');
+	newtFormAddHotKey(self->form, 'D');
+	newtFormAddHotKey(self->form, 'd');
+	newtFormAddHotKey(self->form, 'T');
+	newtFormAddHotKey(self->form, 't');
+	newtFormAddHotKey(self->form, '?');
+	newtFormAddHotKey(self->form, 'H');
+	newtFormAddHotKey(self->form, 'h');
+	newtFormAddHotKey(self->form, NEWT_KEY_F1);
+	newtFormAddHotKey(self->form, NEWT_KEY_RIGHT);
+	newtFormAddComponents(self->form, self->tree, NULL);
+	self->selection = newt__symbol_tree_get_current(self->tree);
+
+	return 0;
+}
+
+static struct hist_entry *hist_browser__selected_entry(struct hist_browser *self)
+{
+	int *indexes;
+
+	if (!symbol_conf.use_callchain)
+		goto out;
+
+	indexes = newtCheckboxTreeFindItem(self->tree, (void *)self->selection);
+	if (indexes) {
+		bool is_hist_entry = indexes[1] == NEWT_ARG_LAST;
+		free(indexes);
+		if (is_hist_entry)
+			goto out;
+	}
+	return NULL;
+out:
+	return container_of(self->selection, struct hist_entry, ms);
+}
+
+static struct thread *hist_browser__selected_thread(struct hist_browser *self)
+{
+	struct hist_entry *he = hist_browser__selected_entry(self);
+	return he ? he->thread : NULL;
+}
+
+static int hist_browser__title(char *bf, size_t size, const char *input_name,
+			       const struct dso *dso, const struct thread *thread)
+{
+	int printed = 0;
+
+	if (thread)
+		printed += snprintf(bf + printed, size - printed,
+				    "Thread: %s(%d)",
+				    (thread->comm_set ?  thread->comm : ""),
+				    thread->pid);
+	if (dso)
+		printed += snprintf(bf + printed, size - printed,
+				    "%sDSO: %s", thread ? " " : "",
+				    dso->short_name);
+	return printed ?: snprintf(bf, size, "Report: %s", input_name);
+}
+
+int hists__browse(struct hists *self, const char *helpline, const char *input_name)
+{
+	struct hist_browser *browser = hist_browser__new();
+	struct pstack *fstack = pstack__new(2);
+	const struct thread *thread_filter = NULL;
+	const struct dso *dso_filter = NULL;
+	struct newtExitStruct es;
+	char msg[160];
+	int err = -1;
+
+	if (browser == NULL)
+		return -1;
+
+	fstack = pstack__new(2);
+	if (fstack == NULL)
+		goto out;
+
+	ui_helpline__push(helpline);
+
+	hist_browser__title(msg, sizeof(msg), input_name,
+			    dso_filter, thread_filter);
+	if (hist_browser__populate(browser, self, msg) < 0)
+		goto out_free_stack;
+
+	while (1) {
+		const struct thread *thread;
+		const struct dso *dso;
+		char *options[16];
+		int nr_options = 0, choice = 0, i,
+		    annotate = -2, zoom_dso = -2, zoom_thread = -2;
+
+		newtFormRun(browser->form, &es);
+
+		thread = hist_browser__selected_thread(browser);
+		dso = browser->selection->map ? browser->selection->map->dso : NULL;
+
+		if (es.reason == NEWT_EXIT_HOTKEY) {
+			if (es.u.key == NEWT_KEY_F1)
+				goto do_help;
+
+			switch (toupper(es.u.key)) {
+			case 'A':
+				goto do_annotate;
+			case 'D':
+				goto zoom_dso;
+			case 'T':
+				goto zoom_thread;
+			case 'H':
+			case '?':
+do_help:
+				ui__help_window("->        Zoom into DSO/Threads & Annotate current symbol\n"
+						"<-        Zoom out\n"
+						"a         Annotate current symbol\n"
+						"h/?/F1    Show this window\n"
+						"d         Zoom into current DSO\n"
+						"t         Zoom into current Thread\n"
+						"q/CTRL+C  Exit browser");
+				continue;
+			default:;
+			}
+			if (toupper(es.u.key) == 'Q' ||
+			    es.u.key == CTRL('c'))
+				break;
+			if (es.u.key == NEWT_KEY_ESCAPE) {
+				if (dialog_yesno("Do you really want to exit?"))
+					break;
+				else
+					continue;
+			}
+
+			if (es.u.key == NEWT_KEY_LEFT) {
+				const void *top;
+
+				if (pstack__empty(fstack))
+					continue;
+				top = pstack__pop(fstack);
+				if (top == &dso_filter)
+					goto zoom_out_dso;
+				if (top == &thread_filter)
+					goto zoom_out_thread;
+				continue;
+			}
+		}
+
+		if (browser->selection->sym != NULL &&
+		    asprintf(&options[nr_options], "Annotate %s",
+			     browser->selection->sym->name) > 0)
+			annotate = nr_options++;
+
+		if (thread != NULL &&
+		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
+			     (thread_filter ? "out of" : "into"),
+			     (thread->comm_set ? thread->comm : ""),
+			     thread->pid) > 0)
+			zoom_thread = nr_options++;
+
+		if (dso != NULL &&
+		    asprintf(&options[nr_options], "Zoom %s %s DSO",
+			     (dso_filter ? "out of" : "into"),
+			     (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
+			zoom_dso = nr_options++;
+
+		options[nr_options++] = (char *)"Exit";
+
+		choice = popup_menu(nr_options, options);
+
+		for (i = 0; i < nr_options - 1; ++i)
+			free(options[i]);
+
+		if (choice == nr_options - 1)
+			break;
+
+		if (choice == -1)
+			continue;
+
+		if (choice == annotate) {
+			struct hist_entry *he;
+do_annotate:
+			if (browser->selection->map->dso->origin == DSO__ORIG_KERNEL) {
+				ui_helpline__puts("No vmlinux file found, can't "
+						 "annotate with just a "
+						 "kallsyms file");
+				continue;
+			}
+
+			he = hist_browser__selected_entry(browser);
+			if (he == NULL)
+				continue;
+
+			hist_entry__annotate_browser(he);
+		} else if (choice == zoom_dso) {
+zoom_dso:
+			if (dso_filter) {
+				pstack__remove(fstack, &dso_filter);
+zoom_out_dso:
+				ui_helpline__pop();
+				dso_filter = NULL;
+			} else {
+				if (dso == NULL)
+					continue;
+				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
+						   dso->kernel ? "the Kernel" : dso->short_name);
+				dso_filter = dso;
+				pstack__push(fstack, &dso_filter);
+			}
+			hists__filter_by_dso(self, dso_filter);
+			hist_browser__title(msg, sizeof(msg), input_name,
+					    dso_filter, thread_filter);
+			if (hist_browser__populate(browser, self, msg) < 0)
+				goto out;
+		} else if (choice == zoom_thread) {
+zoom_thread:
+			if (thread_filter) {
+				pstack__remove(fstack, &thread_filter);
+zoom_out_thread:
+				ui_helpline__pop();
+				thread_filter = NULL;
+			} else {
+				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
+						   thread->comm_set ? thread->comm : "",
+						   thread->pid);
+				thread_filter = thread;
+				pstack__push(fstack, &thread_filter);
+			}
+			hists__filter_by_thread(self, thread_filter);
+			hist_browser__title(msg, sizeof(msg), input_name,
+					    dso_filter, thread_filter);
+			if (hist_browser__populate(browser, self, msg) < 0)
+				goto out;
+		}
+	}
+	err = 0;
+out_free_stack:
+	pstack__delete(fstack);
+out:
+	hist_browser__delete(browser);
+	return err;
+}
+
+static struct newtPercentTreeColors {
+	const char *topColorFg, *topColorBg;
+	const char *mediumColorFg, *mediumColorBg;
+	const char *normalColorFg, *normalColorBg;
+	const char *selColorFg, *selColorBg;
+	const char *codeColorFg, *codeColorBg;
+} defaultPercentTreeColors = {
+	"red",       "lightgray",
+	"green",     "lightgray",
+	"black",     "lightgray",
+	"lightgray", "magenta",
+	"blue",	     "lightgray",
+};
+
+void setup_browser(void)
+{
+	struct newtPercentTreeColors *c = &defaultPercentTreeColors;
+	if (!isatty(1))
+		return;
+
+	use_browser = true;
+	newtInit();
+	newtCls();
+	ui_helpline__puts(" ");
+	sltt_set_color(HE_COLORSET_TOP, NULL, c->topColorFg, c->topColorBg);
+	sltt_set_color(HE_COLORSET_MEDIUM, NULL, c->mediumColorFg, c->mediumColorBg);
+	sltt_set_color(HE_COLORSET_NORMAL, NULL, c->normalColorFg, c->normalColorBg);
+	sltt_set_color(HE_COLORSET_SELECTED, NULL, c->selColorFg, c->selColorBg);
+	sltt_set_color(HE_COLORSET_CODE, NULL, c->codeColorFg, c->codeColorBg);
+}
+
+void exit_browser(bool wait_for_ok)
+{
+	if (use_browser) {
+		if (wait_for_ok) {
+			char title[] = "Fatal Error", ok[] = "Ok";
+			newtWinMessage(title, ok, browser__last_msg);
+		}
+		newtFinished();
+	}
+}

tools/perf/util/parse-events.c

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 05d0c5c..9bf0f40 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -5,6 +5,7 @@
 #include "parse-events.h"
 #include "exec_cmd.h"
 #include "string.h"
+#include "symbol.h"
 #include "cache.h"
 #include "header.h"
 #include "debugfs.h"
@@ -409,7 +410,6 @@
 parse_single_tracepoint_event(char *sys_name,
 			      const char *evt_name,
 			      unsigned int evt_length,
-			      char *flags,
 			      struct perf_event_attr *attr,
 			      const char **strp)
 {
@@ -418,14 +418,6 @@
 	u64 id;
 	int fd;
 
-	if (flags) {
-		if (!strncmp(flags, "record", strlen(flags))) {
-			attr->sample_type |= PERF_SAMPLE_RAW;
-			attr->sample_type |= PERF_SAMPLE_TIME;
-			attr->sample_type |= PERF_SAMPLE_CPU;
-		}
-	}
-
 	snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path,
 		 sys_name, evt_name);
 
@@ -444,6 +436,13 @@
 	attr->type = PERF_TYPE_TRACEPOINT;
 	*strp = evt_name + evt_length;
 
+	attr->sample_type |= PERF_SAMPLE_RAW;
+	attr->sample_type |= PERF_SAMPLE_TIME;
+	attr->sample_type |= PERF_SAMPLE_CPU;
+
+	attr->sample_period = 1;
+
+
 	return EVT_HANDLED;
 }
 
@@ -532,8 +531,7 @@
 						       flags);
 	} else
 		return parse_single_tracepoint_event(sys_name, evt_name,
-						     evt_length, flags,
-						     attr, strp);
+						     evt_length, attr, strp);
 }
 
 static enum event_result
@@ -690,19 +688,29 @@
 parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 {
 	const char *str = *strp;
-	int eu = 1, ek = 1, eh = 1;
+	int exclude = 0;
+	int eu = 0, ek = 0, eh = 0, precise = 0;
 
 	if (*str++ != ':')
 		return 0;
 	while (*str) {
-		if (*str == 'u')
+		if (*str == 'u') {
+			if (!exclude)
+				exclude = eu = ek = eh = 1;
 			eu = 0;
-		else if (*str == 'k')
+		} else if (*str == 'k') {
+			if (!exclude)
+				exclude = eu = ek = eh = 1;
 			ek = 0;
-		else if (*str == 'h')
+		} else if (*str == 'h') {
+			if (!exclude)
+				exclude = eu = ek = eh = 1;
 			eh = 0;
-		else
+		} else if (*str == 'p') {
+			precise++;
+		} else
 			break;
+
 		++str;
 	}
 	if (str >= *strp + 2) {
@@ -710,6 +718,7 @@
 		attr->exclude_user   = eu;
 		attr->exclude_kernel = ek;
 		attr->exclude_hv     = eh;
+		attr->precise_ip     = precise;
 		return 1;
 	}
 	return 0;
@@ -934,7 +943,8 @@
 
 	printf("\n");
 	printf("  %-42s [%s]\n",
-		"rNNN", event_type_descriptors[PERF_TYPE_RAW]);
+		"rNNN (see 'perf list --help' on how to encode it)",
+	       event_type_descriptors[PERF_TYPE_RAW]);
 	printf("\n");
 
 	printf("  %-42s [%s]\n",

tools/perf/util/parse-events.h

diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index b8c1f64..fc4ab3f 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -13,6 +13,7 @@
 };
 
 extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
+extern bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events);
 
 extern int			nr_counters;
 

tools/perf/util/parse-options.c

diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index efebd5b..99d02aa 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -49,8 +49,9 @@
 				break;
 			/* FALLTHROUGH */
 		case OPTION_BOOLEAN:
+		case OPTION_INCR:
 		case OPTION_BIT:
-		case OPTION_SET_INT:
+		case OPTION_SET_UINT:
 		case OPTION_SET_PTR:
 			return opterror(opt, "takes no value", flags);
 		case OPTION_END:
@@ -58,7 +59,9 @@
 		case OPTION_GROUP:
 		case OPTION_STRING:
 		case OPTION_INTEGER:
+		case OPTION_UINTEGER:
 		case OPTION_LONG:
+		case OPTION_U64:
 		default:
 			break;
 		}
@@ -73,11 +76,15 @@
 		return 0;
 
 	case OPTION_BOOLEAN:
+		*(bool *)opt->value = unset ? false : true;
+		return 0;
+
+	case OPTION_INCR:
 		*(int *)opt->value = unset ? 0 : *(int *)opt->value + 1;
 		return 0;
 
-	case OPTION_SET_INT:
-		*(int *)opt->value = unset ? 0 : opt->defval;
+	case OPTION_SET_UINT:
+		*(unsigned int *)opt->value = unset ? 0 : opt->defval;
 		return 0;
 
 	case OPTION_SET_PTR:
@@ -120,6 +127,22 @@
 			return opterror(opt, "expects a numerical value", flags);
 		return 0;
 
+	case OPTION_UINTEGER:
+		if (unset) {
+			*(unsigned int *)opt->value = 0;
+			return 0;
+		}
+		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+			*(unsigned int *)opt->value = opt->defval;
+			return 0;
+		}
+		if (get_arg(p, opt, flags, &arg))
+			return -1;
+		*(unsigned int *)opt->value = strtol(arg, (char **)&s, 10);
+		if (*s)
+			return opterror(opt, "expects a numerical value", flags);
+		return 0;
+
 	case OPTION_LONG:
 		if (unset) {
 			*(long *)opt->value = 0;
@@ -136,6 +159,22 @@
 			return opterror(opt, "expects a numerical value", flags);
 		return 0;
 
+	case OPTION_U64:
+		if (unset) {
+			*(u64 *)opt->value = 0;
+			return 0;
+		}
+		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+			*(u64 *)opt->value = opt->defval;
+			return 0;
+		}
+		if (get_arg(p, opt, flags, &arg))
+			return -1;
+		*(u64 *)opt->value = strtoull(arg, (char **)&s, 10);
+		if (*s)
+			return opterror(opt, "expects a numerical value", flags);
+		return 0;
+
 	case OPTION_END:
 	case OPTION_ARGUMENT:
 	case OPTION_GROUP:
@@ -441,7 +480,10 @@
 		switch (opts->type) {
 		case OPTION_ARGUMENT:
 			break;
+		case OPTION_LONG:
+		case OPTION_U64:
 		case OPTION_INTEGER:
+		case OPTION_UINTEGER:
 			if (opts->flags & PARSE_OPT_OPTARG)
 				if (opts->long_name)
 					pos += fprintf(stderr, "[=<n>]");
@@ -473,14 +515,14 @@
 					pos += fprintf(stderr, " ...");
 			}
 			break;
-		default: /* OPTION_{BIT,BOOLEAN,SET_INT,SET_PTR} */
+		default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */
 		case OPTION_END:
 		case OPTION_GROUP:
 		case OPTION_BIT:
 		case OPTION_BOOLEAN:
-		case OPTION_SET_INT:
+		case OPTION_INCR:
+		case OPTION_SET_UINT:
 		case OPTION_SET_PTR:
-		case OPTION_LONG:
 			break;
 		}
 
@@ -500,6 +542,7 @@
 void usage_with_options(const char * const *usagestr,
 			const struct option *opts)
 {
+	exit_browser(false);
 	usage_with_options_internal(usagestr, opts, 0);
 	exit(129);
 }

tools/perf/util/parse-options.h

diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index 948805a..c7d72dc 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -1,6 +1,9 @@
 #ifndef __PERF_PARSE_OPTIONS_H
 #define __PERF_PARSE_OPTIONS_H
 
+#include <linux/kernel.h>
+#include <stdbool.h>
+
 enum parse_opt_type {
 	/* special types */
 	OPTION_END,
@@ -8,14 +11,17 @@
 	OPTION_GROUP,
 	/* options with no arguments */
 	OPTION_BIT,
-	OPTION_BOOLEAN, /* _INCR would have been a better name */
-	OPTION_SET_INT,
+	OPTION_BOOLEAN,
+	OPTION_INCR,
+	OPTION_SET_UINT,
 	OPTION_SET_PTR,
 	/* options with arguments (usually) */
 	OPTION_STRING,
 	OPTION_INTEGER,
 	OPTION_LONG,
 	OPTION_CALLBACK,
+	OPTION_U64,
+	OPTION_UINTEGER,
 };
 
 enum parse_opt_flags {
@@ -73,7 +79,7 @@
  *
  * `defval`::
  *   default value to fill (*->value) with for PARSE_OPT_OPTARG.
- *   OPTION_{BIT,SET_INT,SET_PTR} store the {mask,integer,pointer} to put in
+ *   OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
  *   the value when met.
  *   CALLBACKS can use it like they want.
  */
@@ -90,16 +96,21 @@
 	intptr_t defval;
 };
 
+#define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
+
 #define OPT_END()                   { .type = OPTION_END }
 #define OPT_ARGUMENT(l, h)          { .type = OPTION_ARGUMENT, .long_name = (l), .help = (h) }
 #define OPT_GROUP(h)                { .type = OPTION_GROUP, .help = (h) }
-#define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (b) }
-#define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = (v), .help = (h) }
-#define OPT_SET_INT(s, l, v, h, i)  { .type = OPTION_SET_INT, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (i) }
+#define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
+#define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) }
+#define OPT_INCR(s, l, v, h)        { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
+#define OPT_SET_UINT(s, l, v, h, i)  { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) }
 #define OPT_SET_PTR(s, l, v, h, p)  { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) }
-#define OPT_INTEGER(s, l, v, h)     { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = (v), .help = (h) }
-#define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = (v), .help = (h) }
-#define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h) }
+#define OPT_INTEGER(s, l, v, h)     { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
+#define OPT_UINTEGER(s, l, v, h)    { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
+#define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
+#define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
+#define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
 #define OPT_CALLBACK(s, l, v, a, h, f) \

tools/perf/util/probe-event.c

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 7c004b6..914c670 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -33,20 +33,27 @@
 #include <limits.h>
 
 #undef _GNU_SOURCE
+#include "util.h"
 #include "event.h"
 #include "string.h"
 #include "strlist.h"
 #include "debug.h"
 #include "cache.h"
 #include "color.h"
-#include "parse-events.h"  /* For debugfs_path */
+#include "symbol.h"
+#include "thread.h"
+#include "debugfs.h"
+#include "trace-event.h"	/* For __unused */
 #include "probe-event.h"
+#include "probe-finder.h"
 
 #define MAX_CMDLEN 256
 #define MAX_PROBE_ARGS 128
 #define PERFPROBE_GROUP "probe"
 
-#define semantic_error(msg ...) die("Semantic error :" msg)
+bool probe_event_dry_run;	/* Dry run flag */
+
+#define semantic_error(msg ...) pr_err("Semantic error :" msg)
 
 /* If there is no space to write, returns -E2BIG. */
 static int e_snprintf(char *str, size_t size, const char *format, ...)
@@ -64,7 +71,275 @@
 	return ret;
 }
 
-void parse_line_range_desc(const char *arg, struct line_range *lr)
+static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
+static struct machine machine;
+
+/* Initialize symbol maps and path of vmlinux */
+static int init_vmlinux(void)
+{
+	struct dso *kernel;
+	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, "/", 0);
+	if (ret < 0)
+		goto out;
+
+	kernel = dso__new_kernel(symbol_conf.vmlinux_name);
+	if (kernel == NULL)
+		die("Failed to create kernel dso.");
+
+	ret = __machine__create_kernel_maps(&machine, kernel);
+	if (ret < 0)
+		pr_debug("Failed to create kernel maps.\n");
+
+out:
+	if (ret < 0)
+		pr_warning("Failed to init vmlinux path.\n");
+	return ret;
+}
+
+#ifdef DWARF_SUPPORT
+static int open_vmlinux(void)
+{
+	if (map__load(machine.vmlinux_maps[MAP__FUNCTION], NULL) < 0) {
+		pr_debug("Failed to load kernel map.\n");
+		return -EINVAL;
+	}
+	pr_debug("Try to open %s\n", machine.vmlinux_maps[MAP__FUNCTION]->dso->long_name);
+	return open(machine.vmlinux_maps[MAP__FUNCTION]->dso->long_name, O_RDONLY);
+}
+
+/* Convert trace point to probe point with debuginfo */
+static int convert_to_perf_probe_point(struct kprobe_trace_point *tp,
+				       struct perf_probe_point *pp)
+{
+	struct symbol *sym;
+	int fd, ret = -ENOENT;
+
+	sym = map__find_symbol_by_name(machine.vmlinux_maps[MAP__FUNCTION],
+				       tp->symbol, NULL);
+	if (sym) {
+		fd = open_vmlinux();
+		if (fd >= 0) {
+			ret = find_perf_probe_point(fd,
+						 sym->start + tp->offset, pp);
+			close(fd);
+		}
+	}
+	if (ret <= 0) {
+		pr_debug("Failed to find corresponding probes from "
+			 "debuginfo. Use kprobe event information.\n");
+		pp->function = strdup(tp->symbol);
+		if (pp->function == NULL)
+			return -ENOMEM;
+		pp->offset = tp->offset;
+	}
+	pp->retprobe = tp->retprobe;
+
+	return 0;
+}
+
+/* Try to find perf_probe_event with debuginfo */
+static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev,
+					   struct kprobe_trace_event **tevs,
+					   int max_tevs)
+{
+	bool need_dwarf = perf_probe_event_need_dwarf(pev);
+	int fd, ntevs;
+
+	fd = open_vmlinux();
+	if (fd < 0) {
+		if (need_dwarf) {
+			pr_warning("Failed to open debuginfo file.\n");
+			return fd;
+		}
+		pr_debug("Could not open vmlinux. Try to use symbols.\n");
+		return 0;
+	}
+
+	/* Searching trace events corresponding to probe event */
+	ntevs = find_kprobe_trace_events(fd, pev, tevs, max_tevs);
+	close(fd);
+
+	if (ntevs > 0) {	/* Succeeded to find trace events */
+		pr_debug("find %d kprobe_trace_events.\n", ntevs);
+		return ntevs;
+	}
+
+	if (ntevs == 0)	{	/* No error but failed to find probe point. */
+		pr_warning("Probe point '%s' not found.\n",
+			   synthesize_perf_probe_point(&pev->point));
+		return -ENOENT;
+	}
+	/* Error path : ntevs < 0 */
+	pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
+	if (ntevs == -EBADF) {
+		pr_warning("Warning: No dwarf info found in the vmlinux - "
+			"please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
+		if (!need_dwarf) {
+			pr_debug("Trying to use symbols.\nn");
+			return 0;
+		}
+	}
+	return ntevs;
+}
+
+#define LINEBUF_SIZE 256
+#define NR_ADDITIONAL_LINES 2
+
+static int show_one_line(FILE *fp, int l, bool skip, bool show_num)
+{
+	char buf[LINEBUF_SIZE];
+	const char *color = PERF_COLOR_BLUE;
+
+	if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
+		goto error;
+	if (!skip) {
+		if (show_num)
+			fprintf(stdout, "%7d  %s", l, buf);
+		else
+			color_fprintf(stdout, color, "         %s", buf);
+	}
+
+	while (strlen(buf) == LINEBUF_SIZE - 1 &&
+	       buf[LINEBUF_SIZE - 2] != '\n') {
+		if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
+			goto error;
+		if (!skip) {
+			if (show_num)
+				fprintf(stdout, "%s", buf);
+			else
+				color_fprintf(stdout, color, "%s", buf);
+		}
+	}
+
+	return 0;
+error:
+	if (feof(fp))
+		pr_warning("Source file is shorter than expected.\n");
+	else
+		pr_warning("File read error: %s\n", strerror(errno));
+
+	return -1;
+}
+
+/*
+ * Show line-range always requires debuginfo to find source file and
+ * line number.
+ */
+int show_line_range(struct line_range *lr)
+{
+	int l = 1;
+	struct line_node *ln;
+	FILE *fp;
+	int fd, ret;
+
+	/* Search a line range */
+	ret = init_vmlinux();
+	if (ret < 0)
+		return ret;
+
+	fd = open_vmlinux();
+	if (fd < 0) {
+		pr_warning("Failed to open debuginfo file.\n");
+		return fd;
+	}
+
+	ret = find_line_range(fd, lr);
+	close(fd);
+	if (ret == 0) {
+		pr_warning("Specified source line is not found.\n");
+		return -ENOENT;
+	} else if (ret < 0) {
+		pr_warning("Debuginfo analysis failed. (%d)\n", ret);
+		return ret;
+	}
+
+	setup_pager();
+
+	if (lr->function)
+		fprintf(stdout, "<%s:%d>\n", lr->function,
+			lr->start - lr->offset);
+	else
+		fprintf(stdout, "<%s:%d>\n", lr->file, lr->start);
+
+	fp = fopen(lr->path, "r");
+	if (fp == NULL) {
+		pr_warning("Failed to open %s: %s\n", lr->path,
+			   strerror(errno));
+		return -errno;
+	}
+	/* Skip to starting line number */
+	while (l < lr->start && ret >= 0)
+		ret = show_one_line(fp, l++, true, false);
+	if (ret < 0)
+		goto end;
+
+	list_for_each_entry(ln, &lr->line_list, list) {
+		while (ln->line > l && ret >= 0)
+			ret = show_one_line(fp, (l++) - lr->offset,
+					    false, false);
+		if (ret >= 0)
+			ret = show_one_line(fp, (l++) - lr->offset,
+					    false, true);
+		if (ret < 0)
+			goto end;
+	}
+
+	if (lr->end == INT_MAX)
+		lr->end = l + NR_ADDITIONAL_LINES;
+	while (l <= lr->end && !feof(fp) && ret >= 0)
+		ret = show_one_line(fp, (l++) - lr->offset, false, false);
+end:
+	fclose(fp);
+	return ret;
+}
+
+#else	/* !DWARF_SUPPORT */
+
+static int convert_to_perf_probe_point(struct kprobe_trace_point *tp,
+					struct perf_probe_point *pp)
+{
+	pp->function = strdup(tp->symbol);
+	if (pp->function == NULL)
+		return -ENOMEM;
+	pp->offset = tp->offset;
+	pp->retprobe = tp->retprobe;
+
+	return 0;
+}
+
+static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev,
+				struct kprobe_trace_event **tevs __unused,
+				int max_tevs __unused)
+{
+	if (perf_probe_event_need_dwarf(pev)) {
+		pr_warning("Debuginfo-analysis is not supported.\n");
+		return -ENOSYS;
+	}
+	return 0;
+}
+
+int show_line_range(struct line_range *lr __unused)
+{
+	pr_warning("Debuginfo-analysis is not supported.\n");
+	return -ENOSYS;
+}
+
+#endif
+
+int parse_line_range_desc(const char *arg, struct line_range *lr)
 {
 	const char *ptr;
 	char *tmp;
@@ -75,29 +350,45 @@
 	 */
 	ptr = strchr(arg, ':');
 	if (ptr) {
-		lr->start = (unsigned int)strtoul(ptr + 1, &tmp, 0);
-		if (*tmp == '+')
-			lr->end = lr->start + (unsigned int)strtoul(tmp + 1,
-								    &tmp, 0);
-		else if (*tmp == '-')
-			lr->end = (unsigned int)strtoul(tmp + 1, &tmp, 0);
+		lr->start = (int)strtoul(ptr + 1, &tmp, 0);
+		if (*tmp == '+') {
+			lr->end = lr->start + (int)strtoul(tmp + 1, &tmp, 0);
+			lr->end--;	/*
+					 * Adjust the number of lines here.
+					 * If the number of lines == 1, the
+					 * the end of line should be equal to
+					 * the start of line.
+					 */
+		} else if (*tmp == '-')
+			lr->end = (int)strtoul(tmp + 1, &tmp, 0);
 		else
-			lr->end = 0;
-		pr_debug("Line range is %u to %u\n", lr->start, lr->end);
-		if (lr->end && lr->start > lr->end)
+			lr->end = INT_MAX;
+		pr_debug("Line range is %d to %d\n", lr->start, lr->end);
+		if (lr->start > lr->end) {
 			semantic_error("Start line must be smaller"
-				       " than end line.");
-		if (*tmp != '\0')
-			semantic_error("Tailing with invalid character '%d'.",
+				       " than end line.\n");
+			return -EINVAL;
+		}
+		if (*tmp != '\0') {
+			semantic_error("Tailing with invalid character '%d'.\n",
 				       *tmp);
+			return -EINVAL;
+		}
 		tmp = strndup(arg, (ptr - arg));
-	} else
+	} else {
 		tmp = strdup(arg);
+		lr->end = INT_MAX;
+	}
+
+	if (tmp == NULL)
+		return -ENOMEM;
 
 	if (strchr(tmp, '.'))
 		lr->file = tmp;
 	else
 		lr->function = tmp;
+
+	return 0;
 }
 
 /* Check the name is good for event/group */
@@ -113,8 +404,9 @@
 }
 
 /* Parse probepoint definition. */
-static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
+static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 {
+	struct perf_probe_point *pp = &pev->point;
 	char *ptr, *tmp;
 	char c, nc = 0;
 	/*
@@ -129,13 +421,19 @@
 	if (ptr && *ptr == '=') {	/* Event name */
 		*ptr = '\0';
 		tmp = ptr + 1;
-		ptr = strchr(arg, ':');
-		if (ptr)	/* Group name is not supported yet. */
-			semantic_error("Group name is not supported yet.");
-		if (!check_event_name(arg))
+		if (strchr(arg, ':')) {
+			semantic_error("Group name is not supported yet.\n");
+			return -ENOTSUP;
+		}
+		if (!check_event_name(arg)) {
 			semantic_error("%s is bad for event name -it must "
-				       "follow C symbol-naming rule.", arg);
-		pp->event = strdup(arg);
+				       "follow C symbol-naming rule.\n", arg);
+			return -EINVAL;
+		}
+		pev->event = strdup(arg);
+		if (pev->event == NULL)
+			return -ENOMEM;
+		pev->group = NULL;
 		arg = tmp;
 	}
 
@@ -145,12 +443,15 @@
 		*ptr++ = '\0';
 	}
 
+	tmp = strdup(arg);
+	if (tmp == NULL)
+		return -ENOMEM;
+
 	/* Check arg is function or file and copy it */
-	if (strchr(arg, '.'))	/* File */
-		pp->file = strdup(arg);
+	if (strchr(tmp, '.'))	/* File */
+		pp->file = tmp;
 	else			/* Function */
-		pp->function = strdup(arg);
-	DIE_IF(pp->file == NULL && pp->function == NULL);
+		pp->function = tmp;
 
 	/* Parse other options */
 	while (ptr) {
@@ -158,6 +459,8 @@
 		c = nc;
 		if (c == ';') {	/* Lazy pattern must be the last part */
 			pp->lazy_line = strdup(arg);
+			if (pp->lazy_line == NULL)
+				return -ENOMEM;
 			break;
 		}
 		ptr = strpbrk(arg, ";:+@%");
@@ -168,266 +471,658 @@
 		switch (c) {
 		case ':':	/* Line number */
 			pp->line = strtoul(arg, &tmp, 0);
-			if (*tmp != '\0')
+			if (*tmp != '\0') {
 				semantic_error("There is non-digit char"
-					       " in line number.");
+					       " in line number.\n");
+				return -EINVAL;
+			}
 			break;
 		case '+':	/* Byte offset from a symbol */
 			pp->offset = strtoul(arg, &tmp, 0);
-			if (*tmp != '\0')
+			if (*tmp != '\0') {
 				semantic_error("There is non-digit character"
-						" in offset.");
+						" in offset.\n");
+				return -EINVAL;
+			}
 			break;
 		case '@':	/* File name */
-			if (pp->file)
-				semantic_error("SRC@SRC is not allowed.");
+			if (pp->file) {
+				semantic_error("SRC@SRC is not allowed.\n");
+				return -EINVAL;
+			}
 			pp->file = strdup(arg);
-			DIE_IF(pp->file == NULL);
+			if (pp->file == NULL)
+				return -ENOMEM;
 			break;
 		case '%':	/* Probe places */
 			if (strcmp(arg, "return") == 0) {
 				pp->retprobe = 1;
-			} else	/* Others not supported yet */
-				semantic_error("%%%s is not supported.", arg);
+			} else {	/* Others not supported yet */
+				semantic_error("%%%s is not supported.\n", arg);
+				return -ENOTSUP;
+			}
 			break;
-		default:
-			DIE_IF("Program has a bug.");
+		default:	/* Buggy case */
+			pr_err("This program has a bug at %s:%d.\n",
+				__FILE__, __LINE__);
+			return -ENOTSUP;
 			break;
 		}
 	}
 
 	/* Exclusion check */
-	if (pp->lazy_line && pp->line)
+	if (pp->lazy_line && pp->line) {
 		semantic_error("Lazy pattern can't be used with line number.");
-
-	if (pp->lazy_line && pp->offset)
-		semantic_error("Lazy pattern can't be used with offset.");
-
-	if (pp->line && pp->offset)
-		semantic_error("Offset can't be used with line number.");
-
-	if (!pp->line && !pp->lazy_line && pp->file && !pp->function)
-		semantic_error("File always requires line number or "
-			       "lazy pattern.");
-
-	if (pp->offset && !pp->function)
-		semantic_error("Offset requires an entry function.");
-
-	if (pp->retprobe && !pp->function)
-		semantic_error("Return probe requires an entry function.");
-
-	if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe)
-		semantic_error("Offset/Line/Lazy pattern can't be used with "
-			       "return probe.");
-
-	pr_debug("symbol:%s file:%s line:%d offset:%d return:%d lazy:%s\n",
-		 pp->function, pp->file, pp->line, pp->offset, pp->retprobe,
-		 pp->lazy_line);
-}
-
-/* Parse perf-probe event definition */
-void parse_perf_probe_event(const char *str, struct probe_point *pp,
-			    bool *need_dwarf)
-{
-	char **argv;
-	int argc, i;
-
-	*need_dwarf = false;
-
-	argv = argv_split(str, &argc);
-	if (!argv)
-		die("argv_split failed.");
-	if (argc > MAX_PROBE_ARGS + 1)
-		semantic_error("Too many arguments");
-
-	/* Parse probe point */
-	parse_perf_probe_probepoint(argv[0], pp);
-	if (pp->file || pp->line || pp->lazy_line)
-		*need_dwarf = true;
-
-	/* Copy arguments and ensure return probe has no C argument */
-	pp->nr_args = argc - 1;
-	pp->args = zalloc(sizeof(char *) * pp->nr_args);
-	for (i = 0; i < pp->nr_args; i++) {
-		pp->args[i] = strdup(argv[i + 1]);
-		if (!pp->args[i])
-			die("Failed to copy argument.");
-		if (is_c_varname(pp->args[i])) {
-			if (pp->retprobe)
-				semantic_error("You can't specify local"
-						" variable for kretprobe");
-			*need_dwarf = true;
-		}
+		return -EINVAL;
 	}
 
+	if (pp->lazy_line && pp->offset) {
+		semantic_error("Lazy pattern can't be used with offset.");
+		return -EINVAL;
+	}
+
+	if (pp->line && pp->offset) {
+		semantic_error("Offset can't be used with line number.");
+		return -EINVAL;
+	}
+
+	if (!pp->line && !pp->lazy_line && pp->file && !pp->function) {
+		semantic_error("File always requires line number or "
+			       "lazy pattern.");
+		return -EINVAL;
+	}
+
+	if (pp->offset && !pp->function) {
+		semantic_error("Offset requires an entry function.");
+		return -EINVAL;
+	}
+
+	if (pp->retprobe && !pp->function) {
+		semantic_error("Return probe requires an entry function.");
+		return -EINVAL;
+	}
+
+	if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) {
+		semantic_error("Offset/Line/Lazy pattern can't be used with "
+			       "return probe.");
+		return -EINVAL;
+	}
+
+	pr_debug("symbol:%s file:%s line:%d offset:%lu return:%d lazy:%s\n",
+		 pp->function, pp->file, pp->line, pp->offset, pp->retprobe,
+		 pp->lazy_line);
+	return 0;
+}
+
+/* Parse perf-probe event argument */
+static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
+{
+	char *tmp;
+	struct perf_probe_arg_field **fieldp;
+
+	pr_debug("parsing arg: %s into ", str);
+
+	tmp = strchr(str, '=');
+	if (tmp) {
+		arg->name = strndup(str, tmp - str);
+		if (arg->name == NULL)
+			return -ENOMEM;
+		pr_debug("name:%s ", arg->name);
+		str = tmp + 1;
+	}
+
+	tmp = strchr(str, ':');
+	if (tmp) {	/* Type setting */
+		*tmp = '\0';
+		arg->type = strdup(tmp + 1);
+		if (arg->type == NULL)
+			return -ENOMEM;
+		pr_debug("type:%s ", arg->type);
+	}
+
+	tmp = strpbrk(str, "-.");
+	if (!is_c_varname(str) || !tmp) {
+		/* A variable, register, symbol or special value */
+		arg->var = strdup(str);
+		if (arg->var == NULL)
+			return -ENOMEM;
+		pr_debug("%s\n", arg->var);
+		return 0;
+	}
+
+	/* Structure fields */
+	arg->var = strndup(str, tmp - str);
+	if (arg->var == NULL)
+		return -ENOMEM;
+	pr_debug("%s, ", arg->var);
+	fieldp = &arg->field;
+
+	do {
+		*fieldp = zalloc(sizeof(struct perf_probe_arg_field));
+		if (*fieldp == NULL)
+			return -ENOMEM;
+		if (*tmp == '.') {
+			str = tmp + 1;
+			(*fieldp)->ref = false;
+		} else if (tmp[1] == '>') {
+			str = tmp + 2;
+			(*fieldp)->ref = true;
+		} else {
+			semantic_error("Argument parse error: %s\n", str);
+			return -EINVAL;
+		}
+
+		tmp = strpbrk(str, "-.");
+		if (tmp) {
+			(*fieldp)->name = strndup(str, tmp - str);
+			if ((*fieldp)->name == NULL)
+				return -ENOMEM;
+			pr_debug("%s(%d), ", (*fieldp)->name, (*fieldp)->ref);
+			fieldp = &(*fieldp)->next;
+		}
+	} while (tmp);
+	(*fieldp)->name = strdup(str);
+	if ((*fieldp)->name == NULL)
+		return -ENOMEM;
+	pr_debug("%s(%d)\n", (*fieldp)->name, (*fieldp)->ref);
+
+	/* If no name is specified, set the last field name */
+	if (!arg->name) {
+		arg->name = strdup((*fieldp)->name);
+		if (arg->name == NULL)
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+/* Parse perf-probe event command */
+int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev)
+{
+	char **argv;
+	int argc, i, ret = 0;
+
+	argv = argv_split(cmd, &argc);
+	if (!argv) {
+		pr_debug("Failed to split arguments.\n");
+		return -ENOMEM;
+	}
+	if (argc - 1 > MAX_PROBE_ARGS) {
+		semantic_error("Too many probe arguments (%d).\n", argc - 1);
+		ret = -ERANGE;
+		goto out;
+	}
+	/* Parse probe point */
+	ret = parse_perf_probe_point(argv[0], pev);
+	if (ret < 0)
+		goto out;
+
+	/* Copy arguments and ensure return probe has no C argument */
+	pev->nargs = argc - 1;
+	pev->args = zalloc(sizeof(struct perf_probe_arg) * pev->nargs);
+	if (pev->args == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	for (i = 0; i < pev->nargs && ret >= 0; i++) {
+		ret = parse_perf_probe_arg(argv[i + 1], &pev->args[i]);
+		if (ret >= 0 &&
+		    is_c_varname(pev->args[i].var) && pev->point.retprobe) {
+			semantic_error("You can't specify local variable for"
+				       " kretprobe.\n");
+			ret = -EINVAL;
+		}
+	}
+out:
 	argv_free(argv);
+
+	return ret;
+}
+
+/* Return true if this perf_probe_event requires debuginfo */
+bool perf_probe_event_need_dwarf(struct perf_probe_event *pev)
+{
+	int i;
+
+	if (pev->point.file || pev->point.line || pev->point.lazy_line)
+		return true;
+
+	for (i = 0; i < pev->nargs; i++)
+		if (is_c_varname(pev->args[i].var))
+			return true;
+
+	return false;
 }
 
 /* Parse kprobe_events event into struct probe_point */
-void parse_trace_kprobe_event(const char *str, struct probe_point *pp)
+int parse_kprobe_trace_command(const char *cmd, struct kprobe_trace_event *tev)
 {
+	struct kprobe_trace_point *tp = &tev->point;
 	char pr;
 	char *p;
 	int ret, i, argc;
 	char **argv;
 
-	pr_debug("Parsing kprobe_events: %s\n", str);
-	argv = argv_split(str, &argc);
-	if (!argv)
-		die("argv_split failed.");
-	if (argc < 2)
-		semantic_error("Too less arguments.");
+	pr_debug("Parsing kprobe_events: %s\n", cmd);
+	argv = argv_split(cmd, &argc);
+	if (!argv) {
+		pr_debug("Failed to split arguments.\n");
+		return -ENOMEM;
+	}
+	if (argc < 2) {
+		semantic_error("Too few probe arguments.\n");
+		ret = -ERANGE;
+		goto out;
+	}
 
 	/* Scan event and group name. */
 	ret = sscanf(argv[0], "%c:%a[^/ \t]/%a[^ \t]",
-		     &pr, (float *)(void *)&pp->group,
-		     (float *)(void *)&pp->event);
-	if (ret != 3)
-		semantic_error("Failed to parse event name: %s", argv[0]);
-	pr_debug("Group:%s Event:%s probe:%c\n", pp->group, pp->event, pr);
+		     &pr, (float *)(void *)&tev->group,
+		     (float *)(void *)&tev->event);
+	if (ret != 3) {
+		semantic_error("Failed to parse event name: %s\n", argv[0]);
+		ret = -EINVAL;
+		goto out;
+	}
+	pr_debug("Group:%s Event:%s probe:%c\n", tev->group, tev->event, pr);
 
-	pp->retprobe = (pr == 'r');
+	tp->retprobe = (pr == 'r');
 
 	/* Scan function name and offset */
-	ret = sscanf(argv[1], "%a[^+]+%d", (float *)(void *)&pp->function,
-		     &pp->offset);
+	ret = sscanf(argv[1], "%a[^+]+%lu", (float *)(void *)&tp->symbol,
+		     &tp->offset);
 	if (ret == 1)
-		pp->offset = 0;
+		tp->offset = 0;
 
-	/* kprobe_events doesn't have this information */
-	pp->line = 0;
-	pp->file = NULL;
-
-	pp->nr_args = argc - 2;
-	pp->args = zalloc(sizeof(char *) * pp->nr_args);
-	for (i = 0; i < pp->nr_args; i++) {
+	tev->nargs = argc - 2;
+	tev->args = zalloc(sizeof(struct kprobe_trace_arg) * tev->nargs);
+	if (tev->args == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	for (i = 0; i < tev->nargs; i++) {
 		p = strchr(argv[i + 2], '=');
 		if (p)	/* We don't need which register is assigned. */
-			*p = '\0';
-		pp->args[i] = strdup(argv[i + 2]);
-		if (!pp->args[i])
-			die("Failed to copy argument.");
+			*p++ = '\0';
+		else
+			p = argv[i + 2];
+		tev->args[i].name = strdup(argv[i + 2]);
+		/* TODO: parse regs and offset */
+		tev->args[i].value = strdup(p);
+		if (tev->args[i].name == NULL || tev->args[i].value == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
-
+	ret = 0;
+out:
 	argv_free(argv);
+	return ret;
 }
 
-/* Synthesize only probe point (not argument) */
-int synthesize_perf_probe_point(struct probe_point *pp)
+/* Compose only probe arg */
+int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
 {
-	char *buf;
-	char offs[64] = "", line[64] = "";
+	struct perf_probe_arg_field *field = pa->field;
 	int ret;
+	char *tmp = buf;
 
-	pp->probes[0] = buf = zalloc(MAX_CMDLEN);
-	pp->found = 1;
-	if (!buf)
-		die("Failed to allocate memory by zalloc.");
+	if (pa->name && pa->var)
+		ret = e_snprintf(tmp, len, "%s=%s", pa->name, pa->var);
+	else
+		ret = e_snprintf(tmp, len, "%s", pa->name ? pa->name : pa->var);
+	if (ret <= 0)
+		goto error;
+	tmp += ret;
+	len -= ret;
+
+	while (field) {
+		ret = e_snprintf(tmp, len, "%s%s", field->ref ? "->" : ".",
+				 field->name);
+		if (ret <= 0)
+			goto error;
+		tmp += ret;
+		len -= ret;
+		field = field->next;
+	}
+
+	if (pa->type) {
+		ret = e_snprintf(tmp, len, ":%s", pa->type);
+		if (ret <= 0)
+			goto error;
+		tmp += ret;
+		len -= ret;
+	}
+
+	return tmp - buf;
+error:
+	pr_debug("Failed to synthesize perf probe argument: %s",
+		 strerror(-ret));
+	return ret;
+}
+
+/* Compose only probe point (not argument) */
+static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
+{
+	char *buf, *tmp;
+	char offs[32] = "", line[32] = "", file[32] = "";
+	int ret, len;
+
+	buf = zalloc(MAX_CMDLEN);
+	if (buf == NULL) {
+		ret = -ENOMEM;
+		goto error;
+	}
 	if (pp->offset) {
-		ret = e_snprintf(offs, 64, "+%d", pp->offset);
+		ret = e_snprintf(offs, 32, "+%lu", pp->offset);
 		if (ret <= 0)
 			goto error;
 	}
 	if (pp->line) {
-		ret = e_snprintf(line, 64, ":%d", pp->line);
+		ret = e_snprintf(line, 32, ":%d", pp->line);
+		if (ret <= 0)
+			goto error;
+	}
+	if (pp->file) {
+		len = strlen(pp->file) - 31;
+		if (len < 0)
+			len = 0;
+		tmp = strchr(pp->file + len, '/');
+		if (!tmp)
+			tmp = pp->file + len;
+		ret = e_snprintf(file, 32, "@%s", tmp + 1);
 		if (ret <= 0)
 			goto error;
 	}
 
 	if (pp->function)
-		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s", pp->function,
-				 offs, pp->retprobe ? "%return" : "", line);
+		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s%s", pp->function,
+				 offs, pp->retprobe ? "%return" : "", line,
+				 file);
 	else
-		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", pp->file, line);
-	if (ret <= 0) {
-error:
-		free(pp->probes[0]);
-		pp->probes[0] = NULL;
-		pp->found = 0;
-	}
-	return ret;
-}
-
-int synthesize_perf_probe_event(struct probe_point *pp)
-{
-	char *buf;
-	int i, len, ret;
-
-	len = synthesize_perf_probe_point(pp);
-	if (len < 0)
-		return 0;
-
-	buf = pp->probes[0];
-	for (i = 0; i < pp->nr_args; i++) {
-		ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s",
-				 pp->args[i]);
-		if (ret <= 0)
-			goto error;
-		len += ret;
-	}
-	pp->found = 1;
-
-	return pp->found;
-error:
-	free(pp->probes[0]);
-	pp->probes[0] = NULL;
-
-	return ret;
-}
-
-int synthesize_trace_kprobe_event(struct probe_point *pp)
-{
-	char *buf;
-	int i, len, ret;
-
-	pp->probes[0] = buf = zalloc(MAX_CMDLEN);
-	if (!buf)
-		die("Failed to allocate memory by zalloc.");
-	ret = e_snprintf(buf, MAX_CMDLEN, "%s+%d", pp->function, pp->offset);
+		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", file, line);
 	if (ret <= 0)
 		goto error;
-	len = ret;
 
-	for (i = 0; i < pp->nr_args; i++) {
+	return buf;
+error:
+	pr_debug("Failed to synthesize perf probe point: %s",
+		 strerror(-ret));
+	if (buf)
+		free(buf);
+	return NULL;
+}
+
+#if 0
+char *synthesize_perf_probe_command(struct perf_probe_event *pev)
+{
+	char *buf;
+	int i, len, ret;
+
+	buf = synthesize_perf_probe_point(&pev->point);
+	if (!buf)
+		return NULL;
+
+	len = strlen(buf);
+	for (i = 0; i < pev->nargs; i++) {
 		ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s",
-				 pp->args[i]);
+				 pev->args[i].name);
+		if (ret <= 0) {
+			free(buf);
+			return NULL;
+		}
+		len += ret;
+	}
+
+	return buf;
+}
+#endif
+
+static int __synthesize_kprobe_trace_arg_ref(struct kprobe_trace_arg_ref *ref,
+					     char **buf, size_t *buflen,
+					     int depth)
+{
+	int ret;
+	if (ref->next) {
+		depth = __synthesize_kprobe_trace_arg_ref(ref->next, buf,
+							 buflen, depth + 1);
+		if (depth < 0)
+			goto out;
+	}
+
+	ret = e_snprintf(*buf, *buflen, "%+ld(", ref->offset);
+	if (ret < 0)
+		depth = ret;
+	else {
+		*buf += ret;
+		*buflen -= ret;
+	}
+out:
+	return depth;
+
+}
+
+static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg,
+				       char *buf, size_t buflen)
+{
+	int ret, depth = 0;
+	char *tmp = buf;
+
+	/* Argument name or separator */
+	if (arg->name)
+		ret = e_snprintf(buf, buflen, " %s=", arg->name);
+	else
+		ret = e_snprintf(buf, buflen, " ");
+	if (ret < 0)
+		return ret;
+	buf += ret;
+	buflen -= ret;
+
+	/* Dereferencing arguments */
+	if (arg->ref) {
+		depth = __synthesize_kprobe_trace_arg_ref(arg->ref, &buf,
+							  &buflen, 1);
+		if (depth < 0)
+			return depth;
+	}
+
+	/* Print argument value */
+	ret = e_snprintf(buf, buflen, "%s", arg->value);
+	if (ret < 0)
+		return ret;
+	buf += ret;
+	buflen -= ret;
+
+	/* Closing */
+	while (depth--) {
+		ret = e_snprintf(buf, buflen, ")");
+		if (ret < 0)
+			return ret;
+		buf += ret;
+		buflen -= ret;
+	}
+	/* Print argument type */
+	if (arg->type) {
+		ret = e_snprintf(buf, buflen, ":%s", arg->type);
+		if (ret <= 0)
+			return ret;
+		buf += ret;
+	}
+
+	return buf - tmp;
+}
+
+char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev)
+{
+	struct kprobe_trace_point *tp = &tev->point;
+	char *buf;
+	int i, len, ret;
+
+	buf = zalloc(MAX_CMDLEN);
+	if (buf == NULL)
+		return NULL;
+
+	len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s+%lu",
+			 tp->retprobe ? 'r' : 'p',
+			 tev->group, tev->event,
+			 tp->symbol, tp->offset);
+	if (len <= 0)
+		goto error;
+
+	for (i = 0; i < tev->nargs; i++) {
+		ret = synthesize_kprobe_trace_arg(&tev->args[i], buf + len,
+						  MAX_CMDLEN - len);
 		if (ret <= 0)
 			goto error;
 		len += ret;
 	}
-	pp->found = 1;
 
-	return pp->found;
+	return buf;
 error:
-	free(pp->probes[0]);
-	pp->probes[0] = NULL;
+	free(buf);
+	return NULL;
+}
+
+int convert_to_perf_probe_event(struct kprobe_trace_event *tev,
+				struct perf_probe_event *pev)
+{
+	char buf[64] = "";
+	int i, ret;
+
+	/* Convert event/group name */
+	pev->event = strdup(tev->event);
+	pev->group = strdup(tev->group);
+	if (pev->event == NULL || pev->group == NULL)
+		return -ENOMEM;
+
+	/* Convert trace_point to probe_point */
+	ret = convert_to_perf_probe_point(&tev->point, &pev->point);
+	if (ret < 0)
+		return ret;
+
+	/* Convert trace_arg to probe_arg */
+	pev->nargs = tev->nargs;
+	pev->args = zalloc(sizeof(struct perf_probe_arg) * pev->nargs);
+	if (pev->args == NULL)
+		return -ENOMEM;
+	for (i = 0; i < tev->nargs && ret >= 0; i++) {
+		if (tev->args[i].name)
+			pev->args[i].name = strdup(tev->args[i].name);
+		else {
+			ret = synthesize_kprobe_trace_arg(&tev->args[i],
+							  buf, 64);
+			pev->args[i].name = strdup(buf);
+		}
+		if (pev->args[i].name == NULL && ret >= 0)
+			ret = -ENOMEM;
+	}
+
+	if (ret < 0)
+		clear_perf_probe_event(pev);
 
 	return ret;
 }
 
-static int open_kprobe_events(int flags, int mode)
+void clear_perf_probe_event(struct perf_probe_event *pev)
+{
+	struct perf_probe_point *pp = &pev->point;
+	struct perf_probe_arg_field *field, *next;
+	int i;
+
+	if (pev->event)
+		free(pev->event);
+	if (pev->group)
+		free(pev->group);
+	if (pp->file)
+		free(pp->file);
+	if (pp->function)
+		free(pp->function);
+	if (pp->lazy_line)
+		free(pp->lazy_line);
+	for (i = 0; i < pev->nargs; i++) {
+		if (pev->args[i].name)
+			free(pev->args[i].name);
+		if (pev->args[i].var)
+			free(pev->args[i].var);
+		if (pev->args[i].type)
+			free(pev->args[i].type);
+		field = pev->args[i].field;
+		while (field) {
+			next = field->next;
+			if (field->name)
+				free(field->name);
+			free(field);
+			field = next;
+		}
+	}
+	if (pev->args)
+		free(pev->args);
+	memset(pev, 0, sizeof(*pev));
+}
+
+void clear_kprobe_trace_event(struct kprobe_trace_event *tev)
+{
+	struct kprobe_trace_arg_ref *ref, *next;
+	int i;
+
+	if (tev->event)
+		free(tev->event);
+	if (tev->group)
+		free(tev->group);
+	if (tev->point.symbol)
+		free(tev->point.symbol);
+	for (i = 0; i < tev->nargs; i++) {
+		if (tev->args[i].name)
+			free(tev->args[i].name);
+		if (tev->args[i].value)
+			free(tev->args[i].value);
+		if (tev->args[i].type)
+			free(tev->args[i].type);
+		ref = tev->args[i].ref;
+		while (ref) {
+			next = ref->next;
+			free(ref);
+			ref = next;
+		}
+	}
+	if (tev->args)
+		free(tev->args);
+	memset(tev, 0, sizeof(*tev));
+}
+
+static int open_kprobe_events(bool readwrite)
 {
 	char buf[PATH_MAX];
+	const char *__debugfs;
 	int ret;
 
-	ret = e_snprintf(buf, PATH_MAX, "%s/../kprobe_events", debugfs_path);
-	if (ret < 0)
-		die("Failed to make kprobe_events path.");
+	__debugfs = debugfs_find_mountpoint();
+	if (__debugfs == NULL) {
+		pr_warning("Debugfs is not mounted.\n");
+		return -ENOENT;
+	}
 
-	ret = open(buf, flags, mode);
+	ret = e_snprintf(buf, PATH_MAX, "%stracing/kprobe_events", __debugfs);
+	if (ret >= 0) {
+		pr_debug("Opening %s write=%d\n", buf, readwrite);
+		if (readwrite && !probe_event_dry_run)
+			ret = open(buf, O_RDWR, O_APPEND);
+		else
+			ret = open(buf, O_RDONLY, 0);
+	}
+
 	if (ret < 0) {
 		if (errno == ENOENT)
-			die("kprobe_events file does not exist -"
-			    " please rebuild with CONFIG_KPROBE_EVENT.");
+			pr_warning("kprobe_events file does not exist - please"
+				 " rebuild kernel with CONFIG_KPROBE_EVENT.\n");
 		else
-			die("Could not open kprobe_events file: %s",
-			    strerror(errno));
+			pr_warning("Failed to open kprobe_events file: %s\n",
+				   strerror(errno));
 	}
 	return ret;
 }
 
 /* Get raw string list of current kprobe_events */
-static struct strlist *get_trace_kprobe_event_rawlist(int fd)
+static struct strlist *get_kprobe_trace_command_rawlist(int fd)
 {
 	int ret, idx;
 	FILE *fp;
@@ -447,271 +1142,486 @@
 		if (p[idx] == '\n')
 			p[idx] = '\0';
 		ret = strlist__add(sl, buf);
-		if (ret < 0)
-			die("strlist__add failed: %s", strerror(-ret));
+		if (ret < 0) {
+			pr_debug("strlist__add failed: %s\n", strerror(-ret));
+			strlist__delete(sl);
+			return NULL;
+		}
 	}
 	fclose(fp);
 
 	return sl;
 }
 
-/* Free and zero clear probe_point */
-static void clear_probe_point(struct probe_point *pp)
-{
-	int i;
-
-	if (pp->event)
-		free(pp->event);
-	if (pp->group)
-		free(pp->group);
-	if (pp->function)
-		free(pp->function);
-	if (pp->file)
-		free(pp->file);
-	if (pp->lazy_line)
-		free(pp->lazy_line);
-	for (i = 0; i < pp->nr_args; i++)
-		free(pp->args[i]);
-	if (pp->args)
-		free(pp->args);
-	for (i = 0; i < pp->found; i++)
-		free(pp->probes[i]);
-	memset(pp, 0, sizeof(*pp));
-}
-
 /* Show an event */
-static void show_perf_probe_event(const char *event, const char *place,
-				  struct probe_point *pp)
+static int show_perf_probe_event(struct perf_probe_event *pev)
 {
 	int i, ret;
 	char buf[128];
+	char *place;
 
-	ret = e_snprintf(buf, 128, "%s:%s", pp->group, event);
+	/* Synthesize only event probe point */
+	place = synthesize_perf_probe_point(&pev->point);
+	if (!place)
+		return -EINVAL;
+
+	ret = e_snprintf(buf, 128, "%s:%s", pev->group, pev->event);
 	if (ret < 0)
-		die("Failed to copy event: %s", strerror(-ret));
-	printf("  %-40s (on %s", buf, place);
+		return ret;
 
-	if (pp->nr_args > 0) {
+	printf("  %-20s (on %s", buf, place);
+
+	if (pev->nargs > 0) {
 		printf(" with");
-		for (i = 0; i < pp->nr_args; i++)
-			printf(" %s", pp->args[i]);
+		for (i = 0; i < pev->nargs; i++) {
+			ret = synthesize_perf_probe_arg(&pev->args[i],
+							buf, 128);
+			if (ret < 0)
+				break;
+			printf(" %s", buf);
+		}
 	}
 	printf(")\n");
+	free(place);
+	return ret;
 }
 
 /* List up current perf-probe events */
-void show_perf_probe_events(void)
+int show_perf_probe_events(void)
 {
-	int fd;
-	struct probe_point pp;
+	int fd, ret;
+	struct kprobe_trace_event tev;
+	struct perf_probe_event pev;
 	struct strlist *rawlist;
 	struct str_node *ent;
 
 	setup_pager();
-	memset(&pp, 0, sizeof(pp));
+	ret = init_vmlinux();
+	if (ret < 0)
+		return ret;
 
-	fd = open_kprobe_events(O_RDONLY, 0);
-	rawlist = get_trace_kprobe_event_rawlist(fd);
+	memset(&tev, 0, sizeof(tev));
+	memset(&pev, 0, sizeof(pev));
+
+	fd = open_kprobe_events(false);
+	if (fd < 0)
+		return fd;
+
+	rawlist = get_kprobe_trace_command_rawlist(fd);
 	close(fd);
+	if (!rawlist)
+		return -ENOENT;
 
 	strlist__for_each(ent, rawlist) {
-		parse_trace_kprobe_event(ent->s, &pp);
-		/* Synthesize only event probe point */
-		synthesize_perf_probe_point(&pp);
-		/* Show an event */
-		show_perf_probe_event(pp.event, pp.probes[0], &pp);
-		clear_probe_point(&pp);
+		ret = parse_kprobe_trace_command(ent->s, &tev);
+		if (ret >= 0) {
+			ret = convert_to_perf_probe_event(&tev, &pev);
+			if (ret >= 0)
+				ret = show_perf_probe_event(&pev);
+		}
+		clear_perf_probe_event(&pev);
+		clear_kprobe_trace_event(&tev);
+		if (ret < 0)
+			break;
 	}
-
 	strlist__delete(rawlist);
+
+	return ret;
 }
 
 /* Get current perf-probe event names */
-static struct strlist *get_perf_event_names(int fd, bool include_group)
+static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group)
 {
 	char buf[128];
 	struct strlist *sl, *rawlist;
 	struct str_node *ent;
-	struct probe_point pp;
+	struct kprobe_trace_event tev;
+	int ret = 0;
 
-	memset(&pp, 0, sizeof(pp));
-	rawlist = get_trace_kprobe_event_rawlist(fd);
+	memset(&tev, 0, sizeof(tev));
 
+	rawlist = get_kprobe_trace_command_rawlist(fd);
 	sl = strlist__new(true, NULL);
 	strlist__for_each(ent, rawlist) {
-		parse_trace_kprobe_event(ent->s, &pp);
+		ret = parse_kprobe_trace_command(ent->s, &tev);
+		if (ret < 0)
+			break;
 		if (include_group) {
-			if (e_snprintf(buf, 128, "%s:%s", pp.group,
-				       pp.event) < 0)
-				die("Failed to copy group:event name.");
-			strlist__add(sl, buf);
+			ret = e_snprintf(buf, 128, "%s:%s", tev.group,
+					tev.event);
+			if (ret >= 0)
+				ret = strlist__add(sl, buf);
 		} else
-			strlist__add(sl, pp.event);
-		clear_probe_point(&pp);
+			ret = strlist__add(sl, tev.event);
+		clear_kprobe_trace_event(&tev);
+		if (ret < 0)
+			break;
 	}
-
 	strlist__delete(rawlist);
 
+	if (ret < 0) {
+		strlist__delete(sl);
+		return NULL;
+	}
 	return sl;
 }
 
-static void write_trace_kprobe_event(int fd, const char *buf)
+static int write_kprobe_trace_event(int fd, struct kprobe_trace_event *tev)
 {
-	int ret;
+	int ret = 0;
+	char *buf = synthesize_kprobe_trace_command(tev);
+
+	if (!buf) {
+		pr_debug("Failed to synthesize kprobe trace event.\n");
+		return -EINVAL;
+	}
 
 	pr_debug("Writing event: %s\n", buf);
-	ret = write(fd, buf, strlen(buf));
-	if (ret <= 0)
-		die("Failed to write event: %s", strerror(errno));
+	if (!probe_event_dry_run) {
+		ret = write(fd, buf, strlen(buf));
+		if (ret <= 0)
+			pr_warning("Failed to write event: %s\n",
+				   strerror(errno));
+	}
+	free(buf);
+	return ret;
 }
 
-static void get_new_event_name(char *buf, size_t len, const char *base,
-			       struct strlist *namelist, bool allow_suffix)
+static int get_new_event_name(char *buf, size_t len, const char *base,
+			      struct strlist *namelist, bool allow_suffix)
 {
 	int i, ret;
 
 	/* Try no suffix */
 	ret = e_snprintf(buf, len, "%s", base);
-	if (ret < 0)
-		die("snprintf() failed: %s", strerror(-ret));
+	if (ret < 0) {
+		pr_debug("snprintf() failed: %s\n", strerror(-ret));
+		return ret;
+	}
 	if (!strlist__has_entry(namelist, buf))
-		return;
+		return 0;
 
 	if (!allow_suffix) {
 		pr_warning("Error: event \"%s\" already exists. "
 			   "(Use -f to force duplicates.)\n", base);
-		die("Can't add new event.");
+		return -EEXIST;
 	}
 
 	/* Try to add suffix */
 	for (i = 1; i < MAX_EVENT_INDEX; i++) {
 		ret = e_snprintf(buf, len, "%s_%d", base, i);
-		if (ret < 0)
-			die("snprintf() failed: %s", strerror(-ret));
+		if (ret < 0) {
+			pr_debug("snprintf() failed: %s\n", strerror(-ret));
+			return ret;
+		}
 		if (!strlist__has_entry(namelist, buf))
 			break;
 	}
-	if (i == MAX_EVENT_INDEX)
-		die("Too many events are on the same function.");
+	if (i == MAX_EVENT_INDEX) {
+		pr_warning("Too many events are on the same function.\n");
+		ret = -ERANGE;
+	}
+
+	return ret;
 }
 
-void add_trace_kprobe_events(struct probe_point *probes, int nr_probes,
-			     bool force_add)
+static int __add_kprobe_trace_events(struct perf_probe_event *pev,
+				     struct kprobe_trace_event *tevs,
+				     int ntevs, bool allow_suffix)
 {
-	int i, j, fd;
-	struct probe_point *pp;
-	char buf[MAX_CMDLEN];
-	char event[64];
+	int i, fd, ret;
+	struct kprobe_trace_event *tev = NULL;
+	char buf[64];
+	const char *event, *group;
 	struct strlist *namelist;
-	bool allow_suffix;
 
-	fd = open_kprobe_events(O_RDWR, O_APPEND);
+	fd = open_kprobe_events(true);
+	if (fd < 0)
+		return fd;
 	/* Get current event names */
-	namelist = get_perf_event_names(fd, false);
-
-	for (j = 0; j < nr_probes; j++) {
-		pp = probes + j;
-		if (!pp->event)
-			pp->event = strdup(pp->function);
-		if (!pp->group)
-			pp->group = strdup(PERFPROBE_GROUP);
-		DIE_IF(!pp->event || !pp->group);
-		/* If force_add is true, suffix search is allowed */
-		allow_suffix = force_add;
-		for (i = 0; i < pp->found; i++) {
-			/* Get an unused new event name */
-			get_new_event_name(event, 64, pp->event, namelist,
-					   allow_suffix);
-			snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s\n",
-				 pp->retprobe ? 'r' : 'p',
-				 pp->group, event,
-				 pp->probes[i]);
-			write_trace_kprobe_event(fd, buf);
-			printf("Added new event:\n");
-			/* Get the first parameter (probe-point) */
-			sscanf(pp->probes[i], "%s", buf);
-			show_perf_probe_event(event, buf, pp);
-			/* Add added event name to namelist */
-			strlist__add(namelist, event);
-			/*
-			 * Probes after the first probe which comes from same
-			 * user input are always allowed to add suffix, because
-			 * there might be several addresses corresponding to
-			 * one code line.
-			 */
-			allow_suffix = true;
-		}
+	namelist = get_kprobe_trace_event_names(fd, false);
+	if (!namelist) {
+		pr_debug("Failed to get current event list.\n");
+		return -EIO;
 	}
-	/* Show how to use the event. */
-	printf("\nYou can now use it on all perf tools, such as:\n\n");
-	printf("\tperf record -e %s:%s -a sleep 1\n\n", PERFPROBE_GROUP, event);
+
+	ret = 0;
+	printf("Add new event%s\n", (ntevs > 1) ? "s:" : ":");
+	for (i = 0; i < ntevs; i++) {
+		tev = &tevs[i];
+		if (pev->event)
+			event = pev->event;
+		else
+			if (pev->point.function)
+				event = pev->point.function;
+			else
+				event = tev->point.symbol;
+		if (pev->group)
+			group = pev->group;
+		else
+			group = PERFPROBE_GROUP;
+
+		/* Get an unused new event name */
+		ret = get_new_event_name(buf, 64, event,
+					 namelist, allow_suffix);
+		if (ret < 0)
+			break;
+		event = buf;
+
+		tev->event = strdup(event);
+		tev->group = strdup(group);
+		if (tev->event == NULL || tev->group == NULL) {
+			ret = -ENOMEM;
+			break;
+		}
+		ret = write_kprobe_trace_event(fd, tev);
+		if (ret < 0)
+			break;
+		/* Add added event name to namelist */
+		strlist__add(namelist, event);
+
+		/* Trick here - save current event/group */
+		event = pev->event;
+		group = pev->group;
+		pev->event = tev->event;
+		pev->group = tev->group;
+		show_perf_probe_event(pev);
+		/* Trick here - restore current event/group */
+		pev->event = (char *)event;
+		pev->group = (char *)group;
+
+		/*
+		 * Probes after the first probe which comes from same
+		 * user input are always allowed to add suffix, because
+		 * there might be several addresses corresponding to
+		 * one code line.
+		 */
+		allow_suffix = true;
+	}
+
+	if (ret >= 0) {
+		/* Show how to use the event. */
+		printf("\nYou can now use it on all perf tools, such as:\n\n");
+		printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
+			 tev->event);
+	}
 
 	strlist__delete(namelist);
 	close(fd);
+	return ret;
 }
 
-static void __del_trace_kprobe_event(int fd, struct str_node *ent)
+static int convert_to_kprobe_trace_events(struct perf_probe_event *pev,
+					  struct kprobe_trace_event **tevs,
+					  int max_tevs)
+{
+	struct symbol *sym;
+	int ret = 0, i;
+	struct kprobe_trace_event *tev;
+
+	/* Convert perf_probe_event with debuginfo */
+	ret = try_to_find_kprobe_trace_events(pev, tevs, max_tevs);
+	if (ret != 0)
+		return ret;
+
+	/* Allocate trace event buffer */
+	tev = *tevs = zalloc(sizeof(struct kprobe_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;
+	}
+	tev->point.offset = pev->point.offset;
+	tev->nargs = pev->nargs;
+	if (tev->nargs) {
+		tev->args = zalloc(sizeof(struct kprobe_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;
+				}
+			}
+		}
+	}
+
+	/* Currently just checking function name from symbol map */
+	sym = map__find_symbol_by_name(machine.vmlinux_maps[MAP__FUNCTION],
+				       tev->point.symbol, NULL);
+	if (!sym) {
+		pr_warning("Kernel symbol \'%s\' not found.\n",
+			   tev->point.symbol);
+		ret = -ENOENT;
+		goto error;
+	}
+
+	return 1;
+error:
+	clear_kprobe_trace_event(tev);
+	free(tev);
+	*tevs = NULL;
+	return ret;
+}
+
+struct __event_package {
+	struct perf_probe_event		*pev;
+	struct kprobe_trace_event	*tevs;
+	int				ntevs;
+};
+
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
+			  bool force_add, int max_tevs)
+{
+	int i, j, ret;
+	struct __event_package *pkgs;
+
+	pkgs = zalloc(sizeof(struct __event_package) * npevs);
+	if (pkgs == NULL)
+		return -ENOMEM;
+
+	/* Init vmlinux path */
+	ret = init_vmlinux();
+	if (ret < 0)
+		return ret;
+
+	/* Loop 1: convert all events */
+	for (i = 0; i < npevs; i++) {
+		pkgs[i].pev = &pevs[i];
+		/* Convert with or without debuginfo */
+		ret  = convert_to_kprobe_trace_events(pkgs[i].pev,
+						      &pkgs[i].tevs, max_tevs);
+		if (ret < 0)
+			goto end;
+		pkgs[i].ntevs = ret;
+	}
+
+	/* Loop 2: add all events */
+	for (i = 0; i < npevs && ret >= 0; i++)
+		ret = __add_kprobe_trace_events(pkgs[i].pev, pkgs[i].tevs,
+						pkgs[i].ntevs, force_add);
+end:
+	/* Loop 3: cleanup trace events  */
+	for (i = 0; i < npevs; i++)
+		for (j = 0; j < pkgs[i].ntevs; j++)
+			clear_kprobe_trace_event(&pkgs[i].tevs[j]);
+
+	return ret;
+}
+
+static int __del_trace_kprobe_event(int fd, struct str_node *ent)
 {
 	char *p;
 	char buf[128];
+	int ret;
 
 	/* Convert from perf-probe event to trace-kprobe event */
-	if (e_snprintf(buf, 128, "-:%s", ent->s) < 0)
-		die("Failed to copy event.");
+	ret = e_snprintf(buf, 128, "-:%s", ent->s);
+	if (ret < 0)
+		goto error;
+
 	p = strchr(buf + 2, ':');
-	if (!p)
-		die("Internal error: %s should have ':' but not.", ent->s);
+	if (!p) {
+		pr_debug("Internal error: %s should have ':' but not.\n",
+			 ent->s);
+		ret = -ENOTSUP;
+		goto error;
+	}
 	*p = '/';
 
-	write_trace_kprobe_event(fd, buf);
+	pr_debug("Writing event: %s\n", buf);
+	ret = write(fd, buf, strlen(buf));
+	if (ret < 0)
+		goto error;
+
 	printf("Remove event: %s\n", ent->s);
+	return 0;
+error:
+	pr_warning("Failed to delete event: %s\n", strerror(-ret));
+	return ret;
 }
 
-static void del_trace_kprobe_event(int fd, const char *group,
-				   const char *event, struct strlist *namelist)
+static int del_trace_kprobe_event(int fd, const char *group,
+				  const char *event, struct strlist *namelist)
 {
 	char buf[128];
 	struct str_node *ent, *n;
-	int found = 0;
+	int found = 0, ret = 0;
 
-	if (e_snprintf(buf, 128, "%s:%s", group, event) < 0)
-		die("Failed to copy event.");
+	ret = e_snprintf(buf, 128, "%s:%s", group, event);
+	if (ret < 0) {
+		pr_err("Failed to copy event.");
+		return ret;
+	}
 
 	if (strpbrk(buf, "*?")) { /* Glob-exp */
 		strlist__for_each_safe(ent, n, namelist)
 			if (strglobmatch(ent->s, buf)) {
 				found++;
-				__del_trace_kprobe_event(fd, ent);
+				ret = __del_trace_kprobe_event(fd, ent);
+				if (ret < 0)
+					break;
 				strlist__remove(namelist, ent);
 			}
 	} else {
 		ent = strlist__find(namelist, buf);
 		if (ent) {
 			found++;
-			__del_trace_kprobe_event(fd, ent);
-			strlist__remove(namelist, ent);
+			ret = __del_trace_kprobe_event(fd, ent);
+			if (ret >= 0)
+				strlist__remove(namelist, ent);
 		}
 	}
-	if (found == 0)
-		pr_info("Info: event \"%s\" does not exist, could not remove it.\n", buf);
+	if (found == 0 && ret >= 0)
+		pr_info("Info: Event \"%s\" does not exist.\n", buf);
+
+	return ret;
 }
 
-void del_trace_kprobe_events(struct strlist *dellist)
+int del_perf_probe_events(struct strlist *dellist)
 {
-	int fd;
+	int fd, ret = 0;
 	const char *group, *event;
 	char *p, *str;
 	struct str_node *ent;
 	struct strlist *namelist;
 
-	fd = open_kprobe_events(O_RDWR, O_APPEND);
+	fd = open_kprobe_events(true);
+	if (fd < 0)
+		return fd;
+
 	/* Get current event names */
-	namelist = get_perf_event_names(fd, true);
+	namelist = get_kprobe_trace_event_names(fd, true);
+	if (namelist == NULL)
+		return -EINVAL;
 
 	strlist__for_each(ent, dellist) {
 		str = strdup(ent->s);
-		if (!str)
-			die("Failed to copy event.");
+		if (str == NULL) {
+			ret = -ENOMEM;
+			break;
+		}
 		pr_debug("Parsing: %s\n", str);
 		p = strchr(str, ':');
 		if (p) {
@@ -723,80 +1633,14 @@
 			event = str;
 		}
 		pr_debug("Group: %s, Event: %s\n", group, event);
-		del_trace_kprobe_event(fd, group, event, namelist);
+		ret = del_trace_kprobe_event(fd, group, event, namelist);
 		free(str);
+		if (ret < 0)
+			break;
 	}
 	strlist__delete(namelist);
 	close(fd);
+
+	return ret;
 }
 
-#define LINEBUF_SIZE 256
-#define NR_ADDITIONAL_LINES 2
-
-static void show_one_line(FILE *fp, unsigned int l, bool skip, bool show_num)
-{
-	char buf[LINEBUF_SIZE];
-	const char *color = PERF_COLOR_BLUE;
-
-	if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
-		goto error;
-	if (!skip) {
-		if (show_num)
-			fprintf(stdout, "%7u  %s", l, buf);
-		else
-			color_fprintf(stdout, color, "         %s", buf);
-	}
-
-	while (strlen(buf) == LINEBUF_SIZE - 1 &&
-	       buf[LINEBUF_SIZE - 2] != '\n') {
-		if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
-			goto error;
-		if (!skip) {
-			if (show_num)
-				fprintf(stdout, "%s", buf);
-			else
-				color_fprintf(stdout, color, "%s", buf);
-		}
-	}
-	return;
-error:
-	if (feof(fp))
-		die("Source file is shorter than expected.");
-	else
-		die("File read error: %s", strerror(errno));
-}
-
-void show_line_range(struct line_range *lr)
-{
-	unsigned int l = 1;
-	struct line_node *ln;
-	FILE *fp;
-
-	setup_pager();
-
-	if (lr->function)
-		fprintf(stdout, "<%s:%d>\n", lr->function,
-			lr->start - lr->offset);
-	else
-		fprintf(stdout, "<%s:%d>\n", lr->file, lr->start);
-
-	fp = fopen(lr->path, "r");
-	if (fp == NULL)
-		die("Failed to open %s: %s", lr->path, strerror(errno));
-	/* Skip to starting line number */
-	while (l < lr->start)
-		show_one_line(fp, l++, true, false);
-
-	list_for_each_entry(ln, &lr->line_list, list) {
-		while (ln->line > l)
-			show_one_line(fp, (l++) - lr->offset, false, false);
-		show_one_line(fp, (l++) - lr->offset, false, true);
-	}
-
-	if (lr->end == INT_MAX)
-		lr->end = l + NR_ADDITIONAL_LINES;
-	while (l < lr->end && !feof(fp))
-		show_one_line(fp, (l++) - lr->offset, false, false);
-
-	fclose(fp);
-}

tools/perf/util/probe-event.h

diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 711287d..e9db1a2 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -2,21 +2,125 @@
 #define _PROBE_EVENT_H
 
 #include <stdbool.h>
-#include "probe-finder.h"
 #include "strlist.h"
 
-extern void parse_line_range_desc(const char *arg, struct line_range *lr);
-extern void parse_perf_probe_event(const char *str, struct probe_point *pp,
-				   bool *need_dwarf);
-extern int synthesize_perf_probe_point(struct probe_point *pp);
-extern int synthesize_perf_probe_event(struct probe_point *pp);
-extern void parse_trace_kprobe_event(const char *str, struct probe_point *pp);
-extern int synthesize_trace_kprobe_event(struct probe_point *pp);
-extern void add_trace_kprobe_events(struct probe_point *probes, int nr_probes,
-				    bool force_add);
-extern void del_trace_kprobe_events(struct strlist *dellist);
-extern void show_perf_probe_events(void);
-extern void show_line_range(struct line_range *lr);
+extern bool probe_event_dry_run;
+
+/* kprobe-tracer tracing point */
+struct kprobe_trace_point {
+	char		*symbol;	/* Base symbol */
+	unsigned long	offset;		/* Offset from symbol */
+	bool		retprobe;	/* Return probe flag */
+};
+
+/* kprobe-tracer tracing argument referencing offset */
+struct kprobe_trace_arg_ref {
+	struct kprobe_trace_arg_ref	*next;	/* Next reference */
+	long				offset;	/* Offset value */
+};
+
+/* kprobe-tracer tracing argument */
+struct kprobe_trace_arg {
+	char				*name;	/* Argument name */
+	char				*value;	/* Base value */
+	char				*type;	/* Type name */
+	struct kprobe_trace_arg_ref	*ref;	/* Referencing offset */
+};
+
+/* kprobe-tracer tracing event (point + arg) */
+struct kprobe_trace_event {
+	char				*event;	/* Event name */
+	char				*group;	/* Group name */
+	struct kprobe_trace_point	point;	/* Trace point */
+	int				nargs;	/* Number of args */
+	struct kprobe_trace_arg		*args;	/* Arguments */
+};
+
+/* Perf probe probing point */
+struct perf_probe_point {
+	char		*file;		/* File path */
+	char		*function;	/* Function name */
+	int		line;		/* Line number */
+	bool		retprobe;	/* Return probe flag */
+	char		*lazy_line;	/* Lazy matching pattern */
+	unsigned long	offset;		/* Offset from function entry */
+};
+
+/* Perf probe probing argument field chain */
+struct perf_probe_arg_field {
+	struct perf_probe_arg_field	*next;	/* Next field */
+	char				*name;	/* Name of the field */
+	bool				ref;	/* Referencing flag */
+};
+
+/* Perf probe probing argument */
+struct perf_probe_arg {
+	char				*name;	/* Argument name */
+	char				*var;	/* Variable name */
+	char				*type;	/* Type name */
+	struct perf_probe_arg_field	*field;	/* Structure fields */
+};
+
+/* Perf probe probing event (point + arg) */
+struct perf_probe_event {
+	char			*event;	/* Event name */
+	char			*group;	/* Group name */
+	struct perf_probe_point	point;	/* Probe point */
+	int			nargs;	/* Number of arguments */
+	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 */
+	char			*function;	/* Function name */
+	int			start;		/* Start line number */
+	int			end;		/* End line number */
+	int			offset;		/* Start line offset */
+	char			*path;		/* Real path name */
+	struct list_head	line_list;	/* Visible lines */
+};
+
+/* Command string to events */
+extern int parse_perf_probe_command(const char *cmd,
+				    struct perf_probe_event *pev);
+extern int parse_kprobe_trace_command(const char *cmd,
+				      struct kprobe_trace_event *tev);
+
+/* Events to command string */
+extern char *synthesize_perf_probe_command(struct perf_probe_event *pev);
+extern char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev);
+extern int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf,
+				     size_t len);
+
+/* Check the perf_probe_event needs debuginfo */
+extern bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
+
+/* Convert from kprobe_trace_event to perf_probe_event */
+extern int convert_to_perf_probe_event(struct kprobe_trace_event *tev,
+				       struct perf_probe_event *pev);
+
+/* Release event contents */
+extern void clear_perf_probe_event(struct perf_probe_event *pev);
+extern void clear_kprobe_trace_event(struct kprobe_trace_event *tev);
+
+/* Command string to line-range */
+extern int parse_line_range_desc(const char *cmd, struct line_range *lr);
+
+
+extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
+				 bool force_add, int max_probe_points);
+extern int del_perf_probe_events(struct strlist *dellist);
+extern int show_perf_probe_events(void);
+extern int show_line_range(struct line_range *lr);
+
 
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX	1024

tools/perf/util/probe-finder.c

diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c171a24..562b144 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -31,6 +31,7 @@
 #include <string.h>
 #include <stdarg.h>
 #include <ctype.h>
+#include <dwarf-regs.h>
 
 #include "string.h"
 #include "event.h"
@@ -38,57 +39,8 @@
 #include "util.h"
 #include "probe-finder.h"
 
-
-/*
- * Generic dwarf analysis helpers
- */
-
-#define X86_32_MAX_REGS 8
-const char *x86_32_regs_table[X86_32_MAX_REGS] = {
-	"%ax",
-	"%cx",
-	"%dx",
-	"%bx",
-	"$stack",	/* Stack address instead of %sp */
-	"%bp",
-	"%si",
-	"%di",
-};
-
-#define X86_64_MAX_REGS 16
-const char *x86_64_regs_table[X86_64_MAX_REGS] = {
-	"%ax",
-	"%dx",
-	"%cx",
-	"%bx",
-	"%si",
-	"%di",
-	"%bp",
-	"%sp",
-	"%r8",
-	"%r9",
-	"%r10",
-	"%r11",
-	"%r12",
-	"%r13",
-	"%r14",
-	"%r15",
-};
-
-/* TODO: switching by dwarf address size */
-#ifdef __x86_64__
-#define ARCH_MAX_REGS X86_64_MAX_REGS
-#define arch_regs_table x86_64_regs_table
-#else
-#define ARCH_MAX_REGS X86_32_MAX_REGS
-#define arch_regs_table x86_32_regs_table
-#endif
-
-/* Return architecture dependent register string (for kprobe-tracer) */
-static const char *get_arch_regstr(unsigned int n)
-{
-	return (n <= ARCH_MAX_REGS) ? arch_regs_table[n] : NULL;
-}
+/* Kprobe tracer basic type is up to u64 */
+#define MAX_BASIC_TYPE_BITS	64
 
 /*
  * Compare the tail of two strings.
@@ -108,7 +60,7 @@
 /* Line number list operations */
 
 /* Add a line to line number list */
-static void line_list__add_line(struct list_head *head, unsigned int line)
+static int line_list__add_line(struct list_head *head, int line)
 {
 	struct line_node *ln;
 	struct list_head *p;
@@ -119,21 +71,23 @@
 			p = &ln->list;
 			goto found;
 		} else if (ln->line == line)	/* Already exist */
-			return ;
+			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));
-	DIE_IF(ln == NULL);
+	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, unsigned int line)
+static int line_list__has_line(struct list_head *head, int line)
 {
 	struct line_node *ln;
 
@@ -184,9 +138,129 @@
 		if (strtailcmp(src, fname) == 0)
 			break;
 	}
+	if (i == nfiles)
+		return NULL;
 	return src;
 }
 
+/* Compare diename and tname */
+static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
+{
+	const char *name;
+	name = dwarf_diename(dw_die);
+	return name ? strcmp(tname, name) : -1;
+}
+
+/* Get type die, but skip qualifiers and typedef */
+static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
+{
+	Dwarf_Attribute attr;
+	int tag;
+
+	do {
+		if (dwarf_attr(vr_die, DW_AT_type, &attr) == NULL ||
+		    dwarf_formref_die(&attr, die_mem) == NULL)
+			return NULL;
+
+		tag = dwarf_tag(die_mem);
+		vr_die = die_mem;
+	} while (tag == DW_TAG_const_type ||
+		 tag == DW_TAG_restrict_type ||
+		 tag == DW_TAG_volatile_type ||
+		 tag == DW_TAG_shared_type ||
+		 tag == DW_TAG_typedef);
+
+	return die_mem;
+}
+
+static bool die_is_signed_type(Dwarf_Die *tp_die)
+{
+	Dwarf_Attribute attr;
+	Dwarf_Word ret;
+
+	if (dwarf_attr(tp_die, DW_AT_encoding, &attr) == NULL ||
+	    dwarf_formudata(&attr, &ret) != 0)
+		return false;
+
+	return (ret == DW_ATE_signed_char || ret == DW_ATE_signed ||
+		ret == DW_ATE_signed_fixed);
+}
+
+static int die_get_byte_size(Dwarf_Die *tp_die)
+{
+	Dwarf_Attribute attr;
+	Dwarf_Word ret;
+
+	if (dwarf_attr(tp_die, DW_AT_byte_size, &attr) == NULL ||
+	    dwarf_formudata(&attr, &ret) != 0)
+		return 0;
+
+	return (int)ret;
+}
+
+/* Get data_member_location offset */
+static int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs)
+{
+	Dwarf_Attribute attr;
+	Dwarf_Op *expr;
+	size_t nexpr;
+	int ret;
+
+	if (dwarf_attr(mb_die, DW_AT_data_member_location, &attr) == NULL)
+		return -ENOENT;
+
+	if (dwarf_formudata(&attr, offs) != 0) {
+		/* DW_AT_data_member_location should be DW_OP_plus_uconst */
+		ret = dwarf_getlocation(&attr, &expr, &nexpr);
+		if (ret < 0 || nexpr == 0)
+			return -ENOENT;
+
+		if (expr[0].atom != DW_OP_plus_uconst || nexpr != 1) {
+			pr_debug("Unable to get offset:Unexpected OP %x (%zd)\n",
+				 expr[0].atom, nexpr);
+			return -ENOTSUP;
+		}
+		*offs = (Dwarf_Word)expr[0].number;
+	}
+	return 0;
+}
+
+/* Return values for die_find callbacks */
+enum {
+	DIE_FIND_CB_FOUND = 0,		/* End of Search */
+	DIE_FIND_CB_CHILD = 1,		/* Search only children */
+	DIE_FIND_CB_SIBLING = 2,	/* Search only siblings */
+	DIE_FIND_CB_CONTINUE = 3,	/* Search children and siblings */
+};
+
+/* Search a child die */
+static Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
+				 int (*callback)(Dwarf_Die *, void *),
+				 void *data, Dwarf_Die *die_mem)
+{
+	Dwarf_Die child_die;
+	int ret;
+
+	ret = dwarf_child(rt_die, die_mem);
+	if (ret != 0)
+		return NULL;
+
+	do {
+		ret = callback(die_mem, data);
+		if (ret == DIE_FIND_CB_FOUND)
+			return die_mem;
+
+		if ((ret & DIE_FIND_CB_CHILD) &&
+		    die_find_child(die_mem, callback, data, &child_die)) {
+			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
+			return die_mem;
+		}
+	} while ((ret & DIE_FIND_CB_SIBLING) &&
+		 dwarf_siblingof(die_mem, die_mem) == 0);
+
+	return NULL;
+}
+
 struct __addr_die_search_param {
 	Dwarf_Addr	addr;
 	Dwarf_Die	*die_mem;
@@ -205,8 +279,8 @@
 }
 
 /* Search a real subprogram including this line, */
-static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
-					  Dwarf_Die *die_mem)
+static Dwarf_Die *die_find_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
+					   Dwarf_Die *die_mem)
 {
 	struct __addr_die_search_param ad;
 	ad.addr = addr;
@@ -218,77 +292,64 @@
 		return die_mem;
 }
 
+/* die_find callback for inline function search */
+static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
+{
+	Dwarf_Addr *addr = data;
+
+	if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine &&
+	    dwarf_haspc(die_mem, *addr))
+		return DIE_FIND_CB_FOUND;
+
+	return DIE_FIND_CB_CONTINUE;
+}
+
 /* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */
-static Dwarf_Die *die_get_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
-				     Dwarf_Die *die_mem)
+static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+				      Dwarf_Die *die_mem)
 {
-	Dwarf_Die child_die;
-	int ret;
-
-	ret = dwarf_child(sp_die, die_mem);
-	if (ret != 0)
-		return NULL;
-
-	do {
-		if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine &&
-		    dwarf_haspc(die_mem, addr))
-			return die_mem;
-
-		if (die_get_inlinefunc(die_mem, addr, &child_die)) {
-			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
-			return die_mem;
-		}
-	} while (dwarf_siblingof(die_mem, die_mem) == 0);
-
-	return NULL;
+	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
 }
 
-/* Compare diename and tname */
-static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
+static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data)
 {
-	const char *name;
-	name = dwarf_diename(dw_die);
-	DIE_IF(name == NULL);
-	return strcmp(tname, name);
+	const char *name = data;
+	int tag;
+
+	tag = dwarf_tag(die_mem);
+	if ((tag == DW_TAG_formal_parameter ||
+	     tag == DW_TAG_variable) &&
+	    (die_compare_name(die_mem, name) == 0))
+		return DIE_FIND_CB_FOUND;
+
+	return DIE_FIND_CB_CONTINUE;
 }
 
-/* Get entry pc(or low pc, 1st entry of ranges)  of the die */
-static Dwarf_Addr die_get_entrypc(Dwarf_Die *dw_die)
-{
-	Dwarf_Addr epc;
-	int ret;
-
-	ret = dwarf_entrypc(dw_die, &epc);
-	DIE_IF(ret == -1);
-	return epc;
-}
-
-/* Get a variable die */
+/* Find a variable called 'name' */
 static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name,
 				    Dwarf_Die *die_mem)
 {
-	Dwarf_Die child_die;
-	int tag;
-	int ret;
+	return die_find_child(sp_die, __die_find_variable_cb, (void *)name,
+			      die_mem);
+}
 
-	ret = dwarf_child(sp_die, die_mem);
-	if (ret != 0)
-		return NULL;
+static int __die_find_member_cb(Dwarf_Die *die_mem, void *data)
+{
+	const char *name = data;
 
-	do {
-		tag = dwarf_tag(die_mem);
-		if ((tag == DW_TAG_formal_parameter ||
-		     tag == DW_TAG_variable) &&
-		    (die_compare_name(die_mem, name) == 0))
-			return die_mem;
+	if ((dwarf_tag(die_mem) == DW_TAG_member) &&
+	    (die_compare_name(die_mem, name) == 0))
+		return DIE_FIND_CB_FOUND;
 
-		if (die_find_variable(die_mem, name, &child_die)) {
-			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
-			return die_mem;
-		}
-	} while (dwarf_siblingof(die_mem, die_mem) == 0);
+	return DIE_FIND_CB_SIBLING;
+}
 
-	return NULL;
+/* Find a member called 'name' */
+static Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
+				  Dwarf_Die *die_mem)
+{
+	return die_find_child(st_die, __die_find_member_cb, (void *)name,
+			      die_mem);
 }
 
 /*
@@ -296,19 +357,22 @@
  */
 
 /* Show a location */
-static void show_location(Dwarf_Op *op, struct probe_finder *pf)
+static int convert_location(Dwarf_Op *op, struct probe_finder *pf)
 {
 	unsigned int regn;
 	Dwarf_Word offs = 0;
-	int deref = 0, ret;
+	bool ref = false;
 	const char *regs;
+	struct kprobe_trace_arg *tvar = pf->tvar;
 
-	/* TODO: support CFA */
 	/* If this is based on frame buffer, set the offset */
 	if (op->atom == DW_OP_fbreg) {
-		if (pf->fb_ops == NULL)
-			die("The attribute of frame base is not supported.\n");
-		deref = 1;
+		if (pf->fb_ops == NULL) {
+			pr_warning("The attribute of frame base is not "
+				   "supported.\n");
+			return -ENOTSUP;
+		}
+		ref = true;
 		offs = op->number;
 		op = &pf->fb_ops[0];
 	}
@@ -316,35 +380,164 @@
 	if (op->atom >= DW_OP_breg0 && op->atom <= DW_OP_breg31) {
 		regn = op->atom - DW_OP_breg0;
 		offs += op->number;
-		deref = 1;
+		ref = true;
 	} else if (op->atom >= DW_OP_reg0 && op->atom <= DW_OP_reg31) {
 		regn = op->atom - DW_OP_reg0;
 	} else if (op->atom == DW_OP_bregx) {
 		regn = op->number;
 		offs += op->number2;
-		deref = 1;
+		ref = true;
 	} else if (op->atom == DW_OP_regx) {
 		regn = op->number;
-	} else
-		die("DW_OP %d is not supported.", op->atom);
+	} else {
+		pr_warning("DW_OP %x is not supported.\n", op->atom);
+		return -ENOTSUP;
+	}
 
 	regs = get_arch_regstr(regn);
-	if (!regs)
-		die("%u exceeds max register number.", regn);
+	if (!regs) {
+		pr_warning("Mapping for DWARF register number %u missing on this architecture.", regn);
+		return -ERANGE;
+	}
 
-	if (deref)
-		ret = snprintf(pf->buf, pf->len, " %s=%+jd(%s)",
-			       pf->var, (intmax_t)offs, regs);
+	tvar->value = strdup(regs);
+	if (tvar->value == NULL)
+		return -ENOMEM;
+
+	if (ref) {
+		tvar->ref = zalloc(sizeof(struct kprobe_trace_arg_ref));
+		if (tvar->ref == NULL)
+			return -ENOMEM;
+		tvar->ref->offset = (long)offs;
+	}
+	return 0;
+}
+
+static int convert_variable_type(Dwarf_Die *vr_die,
+				 struct kprobe_trace_arg *targ)
+{
+	Dwarf_Die type;
+	char buf[16];
+	int ret;
+
+	if (die_get_real_type(vr_die, &type) == NULL) {
+		pr_warning("Failed to get a type information of %s.\n",
+			   dwarf_diename(vr_die));
+		return -ENOENT;
+	}
+
+	ret = die_get_byte_size(&type) * 8;
+	if (ret) {
+		/* Check the bitwidth */
+		if (ret > MAX_BASIC_TYPE_BITS) {
+			pr_info("%s exceeds max-bitwidth."
+				" Cut down to %d bits.\n",
+				dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
+			ret = MAX_BASIC_TYPE_BITS;
+		}
+
+		ret = snprintf(buf, 16, "%c%d",
+			       die_is_signed_type(&type) ? 's' : 'u', ret);
+		if (ret < 0 || ret >= 16) {
+			if (ret >= 16)
+				ret = -E2BIG;
+			pr_warning("Failed to convert variable type: %s\n",
+				   strerror(-ret));
+			return ret;
+		}
+		targ->type = strdup(buf);
+		if (targ->type == NULL)
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
+				    struct perf_probe_arg_field *field,
+				    struct kprobe_trace_arg_ref **ref_ptr,
+				    Dwarf_Die *die_mem)
+{
+	struct kprobe_trace_arg_ref *ref = *ref_ptr;
+	Dwarf_Die type;
+	Dwarf_Word offs;
+	int ret;
+
+	pr_debug("converting %s in %s\n", field->name, varname);
+	if (die_get_real_type(vr_die, &type) == NULL) {
+		pr_warning("Failed to get the type of %s.\n", varname);
+		return -ENOENT;
+	}
+
+	/* Check the pointer and dereference */
+	if (dwarf_tag(&type) == DW_TAG_pointer_type) {
+		if (!field->ref) {
+			pr_err("Semantic error: %s must be referred by '->'\n",
+			       field->name);
+			return -EINVAL;
+		}
+		/* Get the type pointed by this pointer */
+		if (die_get_real_type(&type, &type) == NULL) {
+			pr_warning("Failed to get the type of %s.\n", varname);
+			return -ENOENT;
+		}
+		/* Verify it is a data structure  */
+		if (dwarf_tag(&type) != DW_TAG_structure_type) {
+			pr_warning("%s is not a data structure.\n", varname);
+			return -EINVAL;
+		}
+
+		ref = zalloc(sizeof(struct kprobe_trace_arg_ref));
+		if (ref == NULL)
+			return -ENOMEM;
+		if (*ref_ptr)
+			(*ref_ptr)->next = ref;
+		else
+			*ref_ptr = ref;
+	} else {
+		/* Verify it is a data structure  */
+		if (dwarf_tag(&type) != DW_TAG_structure_type) {
+			pr_warning("%s is not a data structure.\n", varname);
+			return -EINVAL;
+		}
+		if (field->ref) {
+			pr_err("Semantic error: %s must be referred by '.'\n",
+			       field->name);
+			return -EINVAL;
+		}
+		if (!ref) {
+			pr_warning("Structure on a register is not "
+				   "supported yet.\n");
+			return -ENOTSUP;
+		}
+	}
+
+	if (die_find_member(&type, field->name, die_mem) == NULL) {
+		pr_warning("%s(tyep:%s) has no member %s.\n", varname,
+			   dwarf_diename(&type), field->name);
+		return -EINVAL;
+	}
+
+	/* Get the offset of the field */
+	ret = die_get_data_member_location(die_mem, &offs);
+	if (ret < 0) {
+		pr_warning("Failed to get the offset of %s.\n", field->name);
+		return ret;
+	}
+	ref->offset += (long)offs;
+
+	/* Converting next field */
+	if (field->next)
+		return convert_variable_fields(die_mem, field->name,
+					field->next, &ref, die_mem);
 	else
-		ret = snprintf(pf->buf, pf->len, " %s=%s", pf->var, regs);
-	DIE_IF(ret < 0);
-	DIE_IF(ret >= pf->len);
+		return 0;
 }
 
 /* Show a variables in kprobe event format */
-static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
+static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 {
 	Dwarf_Attribute attr;
+	Dwarf_Die die_mem;
 	Dwarf_Op *expr;
 	size_t nexpr;
 	int ret;
@@ -356,142 +549,191 @@
 	if (ret <= 0 || nexpr == 0)
 		goto error;
 
-	show_location(expr, pf);
+	ret = convert_location(expr, pf);
+	if (ret == 0 && pf->pvar->field) {
+		ret = convert_variable_fields(vr_die, pf->pvar->var,
+					      pf->pvar->field, &pf->tvar->ref,
+					      &die_mem);
+		vr_die = &die_mem;
+	}
+	if (ret == 0) {
+		if (pf->pvar->type) {
+			pf->tvar->type = strdup(pf->pvar->type);
+			if (pf->tvar->type == NULL)
+				ret = -ENOMEM;
+		} else
+			ret = convert_variable_type(vr_die, pf->tvar);
+	}
 	/* *expr will be cached in libdw. Don't free it. */
-	return ;
+	return ret;
 error:
 	/* TODO: Support const_value */
-	die("Failed to find the location of %s at this address.\n"
-	    " Perhaps, it has been optimized out.", pf->var);
+	pr_err("Failed to find the location of %s at this address.\n"
+	       " Perhaps, it has been optimized out.\n", pf->pvar->var);
+	return -ENOENT;
 }
 
 /* Find a variable in a subprogram die */
-static void find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
+static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
-	int ret;
 	Dwarf_Die vr_die;
+	char buf[32], *ptr;
+	int ret;
 
-	/* TODO: Support struct members and arrays */
-	if (!is_c_varname(pf->var)) {
-		/* Output raw parameters */
-		ret = snprintf(pf->buf, pf->len, " %s", pf->var);
-		DIE_IF(ret < 0);
-		DIE_IF(ret >= pf->len);
-		return ;
+	/* TODO: Support arrays */
+	if (pf->pvar->name)
+		pf->tvar->name = strdup(pf->pvar->name);
+	else {
+		ret = synthesize_perf_probe_arg(pf->pvar, buf, 32);
+		if (ret < 0)
+			return ret;
+		ptr = strchr(buf, ':');	/* Change type separator to _ */
+		if (ptr)
+			*ptr = '_';
+		pf->tvar->name = strdup(buf);
+	}
+	if (pf->tvar->name == NULL)
+		return -ENOMEM;
+
+	if (!is_c_varname(pf->pvar->var)) {
+		/* Copy raw parameters */
+		pf->tvar->value = strdup(pf->pvar->var);
+		if (pf->tvar->value == NULL)
+			return -ENOMEM;
+		else
+			return 0;
 	}
 
-	pr_debug("Searching '%s' variable in context.\n", pf->var);
+	pr_debug("Searching '%s' variable in context.\n",
+		 pf->pvar->var);
 	/* Search child die for local variables and parameters. */
-	if (!die_find_variable(sp_die, pf->var, &vr_die))
-		die("Failed to find '%s' in this function.", pf->var);
-
-	show_variable(&vr_die, pf);
+	if (!die_find_variable(sp_die, pf->pvar->var, &vr_die)) {
+		pr_warning("Failed to find '%s' in this function.\n",
+			   pf->pvar->var);
+		return -ENOENT;
+	}
+	return convert_variable(&vr_die, pf);
 }
 
 /* Show a probe point to output buffer */
-static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
+static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
-	struct probe_point *pp = pf->pp;
+	struct kprobe_trace_event *tev;
 	Dwarf_Addr eaddr;
 	Dwarf_Die die_mem;
 	const char *name;
-	char tmp[MAX_PROBE_BUFFER];
-	int ret, i, len;
+	int ret, i;
 	Dwarf_Attribute fb_attr;
 	size_t nops;
 
+	if (pf->ntevs == pf->max_tevs) {
+		pr_warning("Too many( > %d) probe point found.\n",
+			   pf->max_tevs);
+		return -ERANGE;
+	}
+	tev = &pf->tevs[pf->ntevs++];
+
 	/* If no real subprogram, find a real one */
 	if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) {
-		sp_die = die_get_real_subprogram(&pf->cu_die,
+		sp_die = die_find_real_subprogram(&pf->cu_die,
 						 pf->addr, &die_mem);
-		if (!sp_die)
-			die("Probe point is not found in subprograms.");
+		if (!sp_die) {
+			pr_warning("Failed to find probe point in any "
+				   "functions.\n");
+			return -ENOENT;
+		}
 	}
 
-	/* Output name of probe point */
+	/* Copy the name of probe point */
 	name = dwarf_diename(sp_die);
 	if (name) {
-		dwarf_entrypc(sp_die, &eaddr);
-		ret = snprintf(tmp, MAX_PROBE_BUFFER, "%s+%lu", name,
-				(unsigned long)(pf->addr - eaddr));
-		/* Copy the function name if possible */
-		if (!pp->function) {
-			pp->function = strdup(name);
-			pp->offset = (size_t)(pf->addr - eaddr);
+		if (dwarf_entrypc(sp_die, &eaddr) != 0) {
+			pr_warning("Failed to get entry pc of %s\n",
+				   dwarf_diename(sp_die));
+			return -ENOENT;
 		}
-	} else {
+		tev->point.symbol = strdup(name);
+		if (tev->point.symbol == NULL)
+			return -ENOMEM;
+		tev->point.offset = (unsigned long)(pf->addr - eaddr);
+	} else
 		/* This function has no name. */
-		ret = snprintf(tmp, MAX_PROBE_BUFFER, "0x%jx",
-			       (uintmax_t)pf->addr);
-		if (!pp->function) {
-			/* TODO: Use _stext */
-			pp->function = strdup("");
-			pp->offset = (size_t)pf->addr;
-		}
-	}
-	DIE_IF(ret < 0);
-	DIE_IF(ret >= MAX_PROBE_BUFFER);
-	len = ret;
-	pr_debug("Probe point found: %s\n", tmp);
+		tev->point.offset = (unsigned long)pf->addr;
+
+	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
+		 tev->point.offset);
 
 	/* Get the frame base attribute/ops */
 	dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr);
 	ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
-	if (ret <= 0 || nops == 0)
+	if (ret <= 0 || nops == 0) {
 		pf->fb_ops = NULL;
+	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
+		   pf->cfi != NULL) {
+		Dwarf_Frame *frame;
+		if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
+		    dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
+			pr_warning("Failed to get CFA on 0x%jx\n",
+				   (uintmax_t)pf->addr);
+			return -ENOENT;
+		}
+	}
 
 	/* Find each argument */
-	/* TODO: use dwarf_cfi_addrframe */
-	for (i = 0; i < pp->nr_args; i++) {
-		pf->var = pp->args[i];
-		pf->buf = &tmp[len];
-		pf->len = MAX_PROBE_BUFFER - len;
-		find_variable(sp_die, pf);
-		len += strlen(pf->buf);
+	tev->nargs = pf->pev->nargs;
+	tev->args = zalloc(sizeof(struct kprobe_trace_arg) * tev->nargs);
+	if (tev->args == NULL)
+		return -ENOMEM;
+	for (i = 0; i < pf->pev->nargs; i++) {
+		pf->pvar = &pf->pev->args[i];
+		pf->tvar = &tev->args[i];
+		ret = find_variable(sp_die, pf);
+		if (ret != 0)
+			return ret;
 	}
 
 	/* *pf->fb_ops will be cached in libdw. Don't free it. */
 	pf->fb_ops = NULL;
-
-	if (pp->found == MAX_PROBES)
-		die("Too many( > %d) probe point found.\n", MAX_PROBES);
-
-	pp->probes[pp->found] = strdup(tmp);
-	pp->found++;
+	return 0;
 }
 
 /* Find probe point from its line number */
-static void find_probe_point_by_line(struct probe_finder *pf)
+static int find_probe_point_by_line(struct probe_finder *pf)
 {
 	Dwarf_Lines *lines;
 	Dwarf_Line *line;
 	size_t nlines, i;
 	Dwarf_Addr addr;
 	int lineno;
-	int ret;
+	int ret = 0;
 
-	ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines);
-	DIE_IF(ret != 0);
+	if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
+		pr_warning("No source lines found in this CU.\n");
+		return -ENOENT;
+	}
 
-	for (i = 0; i < nlines; i++) {
+	for (i = 0; i < nlines && ret == 0; i++) {
 		line = dwarf_onesrcline(lines, i);
-		dwarf_lineno(line, &lineno);
-		if (lineno != pf->lno)
+		if (dwarf_lineno(line, &lineno) != 0 ||
+		    lineno != pf->lno)
 			continue;
 
 		/* TODO: Get fileno from line, but how? */
 		if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
 			continue;
 
-		ret = dwarf_lineaddr(line, &addr);
-		DIE_IF(ret != 0);
+		if (dwarf_lineaddr(line, &addr) != 0) {
+			pr_warning("Failed to get the address of the line.\n");
+			return -ENOENT;
+		}
 		pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n",
 			 (int)i, lineno, (uintmax_t)addr);
 		pf->addr = addr;
 
-		show_probe_point(NULL, pf);
+		ret = convert_probe_point(NULL, pf);
 		/* Continuing, because target line might be inlined. */
 	}
+	return ret;
 }
 
 /* Find lines which match lazy pattern */
@@ -499,16 +741,27 @@
 				 const char *fname, const char *pat)
 {
 	char *fbuf, *p1, *p2;
-	int fd, line, nlines = 0;
+	int fd, ret, line, nlines = 0;
 	struct stat st;
 
 	fd = open(fname, O_RDONLY);
-	if (fd < 0)
-		die("failed to open %s", fname);
-	DIE_IF(fstat(fd, &st) < 0);
-	fbuf = malloc(st.st_size + 2);
-	DIE_IF(fbuf == NULL);
-	DIE_IF(read(fd, fbuf, st.st_size) < 0);
+	if (fd < 0) {
+		pr_warning("Failed to open %s: %s\n", fname, strerror(-fd));
+		return fd;
+	}
+
+	ret = fstat(fd, &st);
+	if (ret < 0) {
+		pr_warning("Failed to get the size of %s: %s\n",
+			   fname, strerror(errno));
+		return ret;
+	}
+	fbuf = xmalloc(st.st_size + 2);
+	ret = read(fd, fbuf, st.st_size);
+	if (ret < 0) {
+		pr_warning("Failed to read %s: %s\n", fname, strerror(errno));
+		return ret;
+	}
 	close(fd);
 	fbuf[st.st_size] = '\n';	/* Dummy line */
 	fbuf[st.st_size + 1] = '\0';
@@ -528,7 +781,7 @@
 }
 
 /* Find probe points from lazy pattern  */
-static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
+static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
 	Dwarf_Lines *lines;
 	Dwarf_Line *line;
@@ -536,37 +789,46 @@
 	Dwarf_Addr addr;
 	Dwarf_Die die_mem;
 	int lineno;
-	int ret;
+	int ret = 0;
 
 	if (list_empty(&pf->lcache)) {
 		/* Matching lazy line pattern */
 		ret = find_lazy_match_lines(&pf->lcache, pf->fname,
-					    pf->pp->lazy_line);
-		if (ret <= 0)
-			die("No matched lines found in %s.", pf->fname);
+					    pf->pev->point.lazy_line);
+		if (ret == 0) {
+			pr_debug("No matched lines found in %s.\n", pf->fname);
+			return 0;
+		} else if (ret < 0)
+			return ret;
 	}
 
-	ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines);
-	DIE_IF(ret != 0);
-	for (i = 0; i < nlines; i++) {
+	if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
+		pr_warning("No source lines found in this CU.\n");
+		return -ENOENT;
+	}
+
+	for (i = 0; i < nlines && ret >= 0; i++) {
 		line = dwarf_onesrcline(lines, i);
 
-		dwarf_lineno(line, &lineno);
-		if (!line_list__has_line(&pf->lcache, lineno))
+		if (dwarf_lineno(line, &lineno) != 0 ||
+		    !line_list__has_line(&pf->lcache, lineno))
 			continue;
 
 		/* TODO: Get fileno from line, but how? */
 		if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
 			continue;
 
-		ret = dwarf_lineaddr(line, &addr);
-		DIE_IF(ret != 0);
+		if (dwarf_lineaddr(line, &addr) != 0) {
+			pr_debug("Failed to get the address of line %d.\n",
+				 lineno);
+			continue;
+		}
 		if (sp_die) {
 			/* Address filtering 1: does sp_die include addr? */
 			if (!dwarf_haspc(sp_die, addr))
 				continue;
 			/* Address filtering 2: No child include addr? */
-			if (die_get_inlinefunc(sp_die, addr, &die_mem))
+			if (die_find_inlinefunc(sp_die, addr, &die_mem))
 				continue;
 		}
 
@@ -574,27 +836,44 @@
 			 (int)i, lineno, (unsigned long long)addr);
 		pf->addr = addr;
 
-		show_probe_point(sp_die, pf);
+		ret = convert_probe_point(sp_die, pf);
 		/* Continuing, because target line might be inlined. */
 	}
 	/* TODO: deallocate lines, but how? */
+	return ret;
 }
 
+/* Callback parameter with return value */
+struct dwarf_callback_param {
+	void *data;
+	int retval;
+};
+
 static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 {
-	struct probe_finder *pf = (struct probe_finder *)data;
-	struct probe_point *pp = pf->pp;
+	struct dwarf_callback_param *param = data;
+	struct probe_finder *pf = param->data;
+	struct perf_probe_point *pp = &pf->pev->point;
+	Dwarf_Addr addr;
 
 	if (pp->lazy_line)
-		find_probe_point_lazy(in_die, pf);
+		param->retval = find_probe_point_lazy(in_die, pf);
 	else {
 		/* Get probe address */
-		pf->addr = die_get_entrypc(in_die);
+		if (dwarf_entrypc(in_die, &addr) != 0) {
+			pr_warning("Failed to get entry pc of %s.\n",
+				   dwarf_diename(in_die));
+			param->retval = -ENOENT;
+			return DWARF_CB_ABORT;
+		}
+		pf->addr = addr;
 		pf->addr += pp->offset;
 		pr_debug("found inline addr: 0x%jx\n",
 			 (uintmax_t)pf->addr);
 
-		show_probe_point(in_die, pf);
+		param->retval = convert_probe_point(in_die, pf);
+		if (param->retval < 0)
+			return DWARF_CB_ABORT;
 	}
 
 	return DWARF_CB_OK;
@@ -603,59 +882,88 @@
 /* Search function from function name */
 static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 {
-	struct probe_finder *pf = (struct probe_finder *)data;
-	struct probe_point *pp = pf->pp;
+	struct dwarf_callback_param *param = data;
+	struct probe_finder *pf = param->data;
+	struct perf_probe_point *pp = &pf->pev->point;
 
 	/* Check tag and diename */
 	if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
 	    die_compare_name(sp_die, pp->function) != 0)
-		return 0;
+		return DWARF_CB_OK;
 
 	pf->fname = dwarf_decl_file(sp_die);
 	if (pp->line) { /* Function relative line */
 		dwarf_decl_line(sp_die, &pf->lno);
 		pf->lno += pp->line;
-		find_probe_point_by_line(pf);
+		param->retval = find_probe_point_by_line(pf);
 	} else if (!dwarf_func_inline(sp_die)) {
 		/* Real function */
 		if (pp->lazy_line)
-			find_probe_point_lazy(sp_die, pf);
+			param->retval = find_probe_point_lazy(sp_die, pf);
 		else {
-			pf->addr = die_get_entrypc(sp_die);
+			if (dwarf_entrypc(sp_die, &pf->addr) != 0) {
+				pr_warning("Failed to get entry pc of %s.\n",
+					   dwarf_diename(sp_die));
+				param->retval = -ENOENT;
+				return DWARF_CB_ABORT;
+			}
 			pf->addr += pp->offset;
 			/* TODO: Check the address in this function */
-			show_probe_point(sp_die, pf);
+			param->retval = convert_probe_point(sp_die, pf);
 		}
-	} else
+	} else {
+		struct dwarf_callback_param _param = {.data = (void *)pf,
+						      .retval = 0};
 		/* Inlined function: search instances */
-		dwarf_func_inline_instances(sp_die, probe_point_inline_cb, pf);
+		dwarf_func_inline_instances(sp_die, probe_point_inline_cb,
+					    &_param);
+		param->retval = _param.retval;
+	}
 
-	return 1; /* Exit; no same symbol in this CU. */
+	return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */
 }
 
-static void find_probe_point_by_func(struct probe_finder *pf)
+static int find_probe_point_by_func(struct probe_finder *pf)
 {
-	dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, pf, 0);
+	struct dwarf_callback_param _param = {.data = (void *)pf,
+					      .retval = 0};
+	dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, &_param, 0);
+	return _param.retval;
 }
 
-/* Find a probe point */
-int find_probe_point(int fd, struct probe_point *pp)
+/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */
+int find_kprobe_trace_events(int fd, struct perf_probe_event *pev,
+			     struct kprobe_trace_event **tevs, int max_tevs)
 {
-	struct probe_finder pf = {.pp = pp};
+	struct probe_finder pf = {.pev = pev, .max_tevs = max_tevs};
+	struct perf_probe_point *pp = &pev->point;
 	Dwarf_Off off, noff;
 	size_t cuhl;
 	Dwarf_Die *diep;
 	Dwarf *dbg;
+	int ret = 0;
+
+	pf.tevs = zalloc(sizeof(struct kprobe_trace_event) * max_tevs);
+	if (pf.tevs == NULL)
+		return -ENOMEM;
+	*tevs = pf.tevs;
+	pf.ntevs = 0;
 
 	dbg = dwarf_begin(fd, DWARF_C_READ);
-	if (!dbg)
-		return -ENOENT;
+	if (!dbg) {
+		pr_warning("No dwarf info found in the vmlinux - "
+			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		return -EBADF;
+	}
 
-	pp->found = 0;
+	/* Get the call frame information from this dwarf */
+	pf.cfi = dwarf_getcfi(dbg);
+
 	off = 0;
 	line_list__init(&pf.lcache);
 	/* Loop on CUs (Compilation Unit) */
-	while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
+	while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) &&
+	       ret >= 0) {
 		/* Get the DIE(Debugging Information Entry) of this CU */
 		diep = dwarf_offdie(dbg, off + cuhl, &pf.cu_die);
 		if (!diep)
@@ -669,12 +977,12 @@
 
 		if (!pp->file || pf.fname) {
 			if (pp->function)
-				find_probe_point_by_func(&pf);
+				ret = find_probe_point_by_func(&pf);
 			else if (pp->lazy_line)
-				find_probe_point_lazy(NULL, &pf);
+				ret = find_probe_point_lazy(NULL, &pf);
 			else {
 				pf.lno = pp->line;
-				find_probe_point_by_line(&pf);
+				ret = find_probe_point_by_line(&pf);
 			}
 		}
 		off = noff;
@@ -682,41 +990,169 @@
 	line_list__free(&pf.lcache);
 	dwarf_end(dbg);
 
-	return pp->found;
+	return (ret < 0) ? ret : pf.ntevs;
+}
+
+/* Reverse search */
+int find_perf_probe_point(int fd, unsigned long addr,
+			  struct perf_probe_point *ppt)
+{
+	Dwarf_Die cudie, spdie, indie;
+	Dwarf *dbg;
+	Dwarf_Line *line;
+	Dwarf_Addr laddr, eaddr;
+	const char *tmp;
+	int lineno, ret = 0;
+	bool found = false;
+
+	dbg = dwarf_begin(fd, DWARF_C_READ);
+	if (!dbg)
+		return -EBADF;
+
+	/* Find cu die */
+	if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr, &cudie)) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	/* Find a corresponding line */
+	line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr);
+	if (line) {
+		if (dwarf_lineaddr(line, &laddr) == 0 &&
+		    (Dwarf_Addr)addr == laddr &&
+		    dwarf_lineno(line, &lineno) == 0) {
+			tmp = dwarf_linesrc(line, NULL, NULL);
+			if (tmp) {
+				ppt->line = lineno;
+				ppt->file = strdup(tmp);
+				if (ppt->file == NULL) {
+					ret = -ENOMEM;
+					goto end;
+				}
+				found = true;
+			}
+		}
+	}
+
+	/* Find a corresponding function */
+	if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) {
+		tmp = dwarf_diename(&spdie);
+		if (!tmp || dwarf_entrypc(&spdie, &eaddr) != 0)
+			goto end;
+
+		if (ppt->line) {
+			if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
+						&indie)) {
+				/* addr in an inline function */
+				tmp = dwarf_diename(&indie);
+				if (!tmp)
+					goto end;
+				ret = dwarf_decl_line(&indie, &lineno);
+			} else {
+				if (eaddr == addr) {	/* Function entry */
+					lineno = ppt->line;
+					ret = 0;
+				} else
+					ret = dwarf_decl_line(&spdie, &lineno);
+			}
+			if (ret == 0) {
+				/* Make a relative line number */
+				ppt->line -= lineno;
+				goto found;
+			}
+		}
+		/* We don't have a line number, let's use offset */
+		ppt->offset = addr - (unsigned long)eaddr;
+found:
+		ppt->function = strdup(tmp);
+		if (ppt->function == NULL) {
+			ret = -ENOMEM;
+			goto end;
+		}
+		found = true;
+	}
+
+end:
+	dwarf_end(dbg);
+	if (ret >= 0)
+		ret = found ? 1 : 0;
+	return ret;
+}
+
+/* Add a line and store the src path */
+static int line_range_add_line(const char *src, unsigned int lineno,
+			       struct line_range *lr)
+{
+	/* Copy real path */
+	if (!lr->path) {
+		lr->path = strdup(src);
+		if (lr->path == NULL)
+			return -ENOMEM;
+	}
+	return line_list__add_line(&lr->line_list, lineno);
+}
+
+/* Search function declaration lines */
+static int line_range_funcdecl_cb(Dwarf_Die *sp_die, void *data)
+{
+	struct dwarf_callback_param *param = data;
+	struct line_finder *lf = param->data;
+	const char *src;
+	int lineno;
+
+	src = dwarf_decl_file(sp_die);
+	if (src && strtailcmp(src, lf->fname) != 0)
+		return DWARF_CB_OK;
+
+	if (dwarf_decl_line(sp_die, &lineno) != 0 ||
+	    (lf->lno_s > lineno || lf->lno_e < lineno))
+		return DWARF_CB_OK;
+
+	param->retval = line_range_add_line(src, lineno, lf->lr);
+	if (param->retval < 0)
+		return DWARF_CB_ABORT;
+	return DWARF_CB_OK;
+}
+
+static int find_line_range_func_decl_lines(struct line_finder *lf)
+{
+	struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0};
+	dwarf_getfuncs(&lf->cu_die, line_range_funcdecl_cb, &param, 0);
+	return param.retval;
 }
 
 /* Find line range from its line number */
-static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
+static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 {
 	Dwarf_Lines *lines;
 	Dwarf_Line *line;
 	size_t nlines, i;
 	Dwarf_Addr addr;
-	int lineno;
-	int ret;
+	int lineno, ret = 0;
 	const char *src;
 	Dwarf_Die die_mem;
 
 	line_list__init(&lf->lr->line_list);
-	ret = dwarf_getsrclines(&lf->cu_die, &lines, &nlines);
-	DIE_IF(ret != 0);
+	if (dwarf_getsrclines(&lf->cu_die, &lines, &nlines) != 0) {
+		pr_warning("No source lines found in this CU.\n");
+		return -ENOENT;
+	}
 
+	/* Search probable lines on lines list */
 	for (i = 0; i < nlines; i++) {
 		line = dwarf_onesrcline(lines, i);
-		ret = dwarf_lineno(line, &lineno);
-		DIE_IF(ret != 0);
-		if (lf->lno_s > lineno || lf->lno_e < lineno)
+		if (dwarf_lineno(line, &lineno) != 0 ||
+		    (lf->lno_s > lineno || lf->lno_e < lineno))
 			continue;
 
 		if (sp_die) {
 			/* Address filtering 1: does sp_die include addr? */
-			ret = dwarf_lineaddr(line, &addr);
-			DIE_IF(ret != 0);
-			if (!dwarf_haspc(sp_die, addr))
+			if (dwarf_lineaddr(line, &addr) != 0 ||
+			    !dwarf_haspc(sp_die, addr))
 				continue;
 
 			/* Address filtering 2: No child include addr? */
-			if (die_get_inlinefunc(sp_die, addr, &die_mem))
+			if (die_find_inlinefunc(sp_die, addr, &die_mem))
 				continue;
 		}
 
@@ -725,30 +1161,49 @@
 		if (strtailcmp(src, lf->fname) != 0)
 			continue;
 
-		/* Copy real path */
-		if (!lf->lr->path)
-			lf->lr->path = strdup(src);
-		line_list__add_line(&lf->lr->line_list, (unsigned int)lineno);
+		ret = line_range_add_line(src, lineno, lf->lr);
+		if (ret < 0)
+			return ret;
 	}
+
+	/*
+	 * Dwarf lines doesn't include function declarations. We have to
+	 * check functions list or given function.
+	 */
+	if (sp_die) {
+		src = dwarf_decl_file(sp_die);
+		if (src && dwarf_decl_line(sp_die, &lineno) == 0 &&
+		    (lf->lno_s <= lineno && lf->lno_e >= lineno))
+			ret = line_range_add_line(src, lineno, lf->lr);
+	} else
+		ret = find_line_range_func_decl_lines(lf);
+
 	/* Update status */
-	if (!list_empty(&lf->lr->line_list))
-		lf->found = 1;
+	if (ret >= 0)
+		if (!list_empty(&lf->lr->line_list))
+			ret = lf->found = 1;
+		else
+			ret = 0;	/* Lines are not found */
 	else {
 		free(lf->lr->path);
 		lf->lr->path = NULL;
 	}
+	return ret;
 }
 
 static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
 {
-	find_line_range_by_line(in_die, (struct line_finder *)data);
+	struct dwarf_callback_param *param = data;
+
+	param->retval = find_line_range_by_line(in_die, param->data);
 	return DWARF_CB_ABORT;	/* No need to find other instances */
 }
 
 /* Search function from function name */
 static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 {
-	struct line_finder *lf = (struct line_finder *)data;
+	struct dwarf_callback_param *param = data;
+	struct line_finder *lf = param->data;
 	struct line_range *lr = lf->lr;
 
 	if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
@@ -757,44 +1212,55 @@
 		dwarf_decl_line(sp_die, &lr->offset);
 		pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
 		lf->lno_s = lr->offset + lr->start;
-		if (!lr->end)
+		if (lf->lno_s < 0)	/* Overflow */
+			lf->lno_s = INT_MAX;
+		lf->lno_e = lr->offset + lr->end;
+		if (lf->lno_e < 0)	/* Overflow */
 			lf->lno_e = INT_MAX;
-		else
-			lf->lno_e = lr->offset + lr->end;
+		pr_debug("New line range: %d to %d\n", lf->lno_s, lf->lno_e);
 		lr->start = lf->lno_s;
 		lr->end = lf->lno_e;
-		if (dwarf_func_inline(sp_die))
+		if (dwarf_func_inline(sp_die)) {
+			struct dwarf_callback_param _param;
+			_param.data = (void *)lf;
+			_param.retval = 0;
 			dwarf_func_inline_instances(sp_die,
-						    line_range_inline_cb, lf);
-		else
-			find_line_range_by_line(sp_die, lf);
-		return 1;
+						    line_range_inline_cb,
+						    &_param);
+			param->retval = _param.retval;
+		} else
+			param->retval = find_line_range_by_line(sp_die, lf);
+		return DWARF_CB_ABORT;
 	}
-	return 0;
+	return DWARF_CB_OK;
 }
 
-static void find_line_range_by_func(struct line_finder *lf)
+static int find_line_range_by_func(struct line_finder *lf)
 {
-	dwarf_getfuncs(&lf->cu_die, line_range_search_cb, lf, 0);
+	struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0};
+	dwarf_getfuncs(&lf->cu_die, line_range_search_cb, &param, 0);
+	return param.retval;
 }
 
 int find_line_range(int fd, struct line_range *lr)
 {
 	struct line_finder lf = {.lr = lr, .found = 0};
-	int ret;
+	int ret = 0;
 	Dwarf_Off off = 0, noff;
 	size_t cuhl;
 	Dwarf_Die *diep;
 	Dwarf *dbg;
 
 	dbg = dwarf_begin(fd, DWARF_C_READ);
-	if (!dbg)
-		return -ENOENT;
+	if (!dbg) {
+		pr_warning("No dwarf info found in the vmlinux - "
+			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		return -EBADF;
+	}
 
 	/* Loop on CUs (Compilation Unit) */
-	while (!lf.found) {
-		ret = dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL);
-		if (ret != 0)
+	while (!lf.found && ret >= 0) {
+		if (dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0)
 			break;
 
 		/* Get the DIE(Debugging Information Entry) of this CU */
@@ -810,20 +1276,18 @@
 
 		if (!lr->file || lf.fname) {
 			if (lr->function)
-				find_line_range_by_func(&lf);
+				ret = find_line_range_by_func(&lf);
 			else {
 				lf.lno_s = lr->start;
-				if (!lr->end)
-					lf.lno_e = INT_MAX;
-				else
-					lf.lno_e = lr->end;
-				find_line_range_by_line(NULL, &lf);
+				lf.lno_e = lr->end;
+				ret = find_line_range_by_line(NULL, &lf);
 			}
 		}
 		off = noff;
 	}
 	pr_debug("path: %lx\n", (unsigned long)lr->path);
 	dwarf_end(dbg);
-	return lf.found;
+
+	return (ret < 0) ? ret : lf.found;
 }
 

tools/perf/util/probe-finder.h

diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 21f7354..66f1980 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 "probe-event.h"
 
 #define MAX_PATH_LEN		 256
 #define MAX_PROBE_BUFFER	1024
@@ -14,67 +15,39 @@
 	return isalpha(name[0]) || name[0] == '_';
 }
 
-struct probe_point {
-	char			*event;			/* Event name */
-	char			*group;			/* Event group */
+#ifdef DWARF_SUPPORT
+/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */
+extern int find_kprobe_trace_events(int fd, struct perf_probe_event *pev,
+				    struct kprobe_trace_event **tevs,
+				    int max_tevs);
 
-	/* Inputs */
-	char			*file;			/* File name */
-	int			line;			/* Line number */
-	char			*lazy_line;		/* Lazy line pattern */
+/* Find a perf_probe_point from debuginfo */
+extern int find_perf_probe_point(int fd, unsigned long addr,
+				 struct perf_probe_point *ppt);
 
-	char			*function;		/* Function name */
-	int			offset;			/* Offset bytes */
-
-	int			nr_args;		/* Number of arguments */
-	char			**args;			/* Arguments */
-
-	int			retprobe;		/* Return probe */
-
-	/* Output */
-	int			found;			/* Number of found probe points */
-	char			*probes[MAX_PROBES];	/* Output buffers (will be allocated)*/
-};
-
-/* Line number container */
-struct line_node {
-	struct list_head	list;
-	unsigned int		line;
-};
-
-/* Line range */
-struct line_range {
-	char			*file;			/* File name */
-	char			*function;		/* Function name */
-	unsigned int		start;			/* Start line number */
-	unsigned int		end;			/* End line number */
-	int			offset;			/* Start line offset */
-	char			*path;			/* Real path name */
-	struct list_head	line_list;		/* Visible lines */
-};
-
-#ifndef NO_DWARF_SUPPORT
-extern int find_probe_point(int fd, struct probe_point *pp);
 extern int find_line_range(int fd, struct line_range *lr);
 
 #include <dwarf.h>
 #include <libdw.h>
 
 struct probe_finder {
-	struct probe_point	*pp;		/* Target probe point */
+	struct perf_probe_event	*pev;		/* Target probe event */
+	struct kprobe_trace_event *tevs;	/* Result trace events */
+	int			ntevs;		/* Number of trace events */
+	int			max_tevs;	/* Max number of trace events */
 
 	/* For function searching */
-	Dwarf_Addr		addr;		/* Address */
-	const char		*fname;		/* File name */
 	int			lno;		/* Line number */
+	Dwarf_Addr		addr;		/* Address */
+	const char		*fname;		/* Real file name */
 	Dwarf_Die		cu_die;		/* Current CU */
+	struct list_head	lcache;		/* Line cache for lazy match */
 
 	/* For variable searching */
+	Dwarf_CFI		*cfi;		/* Call Frame Information */
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
-	const char		*var;		/* Current variable name */
-	char			*buf;		/* Current output buffer */
-	int			len;		/* Length of output buffer */
-	struct list_head	lcache;		/* Line cache for lazy match */
+	struct perf_probe_arg	*pvar;		/* Current target variable */
+	struct kprobe_trace_arg	*tvar;		/* Current result variable */
 };
 
 struct line_finder {
@@ -87,6 +60,6 @@
 	int			found;
 };
 
-#endif /* NO_DWARF_SUPPORT */
+#endif /* DWARF_SUPPORT */
 
 #endif /*_PROBE_FINDER_H */

tools/perf/util/pstack.c

diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
new file mode 100644
index 0000000..13d36fa
--- /dev/null
+++ b/tools/perf/util/pstack.c
@@ -0,0 +1,75 @@
+/*
+ * Simple pointer stack
+ *
+ * (c) 2010 Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "util.h"
+#include "pstack.h"
+#include <linux/kernel.h>
+#include <stdlib.h>
+
+struct pstack {
+	unsigned short	top;
+	unsigned short	max_nr_entries;
+	void		*entries[0];
+};
+
+struct pstack *pstack__new(unsigned short max_nr_entries)
+{
+	struct pstack *self = zalloc((sizeof(*self) +
+				     max_nr_entries * sizeof(void *)));
+	if (self != NULL)
+		self->max_nr_entries = max_nr_entries;
+	return self;
+}
+
+void pstack__delete(struct pstack *self)
+{
+	free(self);
+}
+
+bool pstack__empty(const struct pstack *self)
+{
+	return self->top == 0;
+}
+
+void pstack__remove(struct pstack *self, void *key)
+{
+	unsigned short i = self->top, last_index = self->top - 1;
+
+	while (i-- != 0) {
+		if (self->entries[i] == key) {
+			if (i < last_index)
+				memmove(self->entries + i,
+					self->entries + i + 1,
+					(last_index - i) * sizeof(void *));
+			--self->top;
+			return;
+		}
+	}
+	pr_err("%s: %p not on the pstack!\n", __func__, key);
+}
+
+void pstack__push(struct pstack *self, void *key)
+{
+	if (self->top == self->max_nr_entries) {
+		pr_err("%s: top=%d, overflow!\n", __func__, self->top);
+		return;
+	}
+	self->entries[self->top++] = key;
+}
+
+void *pstack__pop(struct pstack *self)
+{
+	void *ret;
+
+	if (self->top == 0) {
+		pr_err("%s: underflow!\n", __func__);
+		return NULL;
+	}
+
+	ret = self->entries[--self->top];
+	self->entries[self->top] = NULL;
+	return ret;
+}

tools/perf/util/pstack.h

diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h
new file mode 100644
index 0000000..5ad0702
--- /dev/null
+++ b/tools/perf/util/pstack.h
@@ -0,0 +1,12 @@
+#ifndef _PERF_PSTACK_
+#define _PERF_PSTACK_
+
+struct pstack;
+struct pstack *pstack__new(unsigned short max_nr_entries);
+void pstack__delete(struct pstack *self);
+bool pstack__empty(const struct pstack *self);
+void pstack__remove(struct pstack *self, void *key);
+void pstack__push(struct pstack *self, void *key);
+void *pstack__pop(struct pstack *self);
+
+#endif /* _PERF_PSTACK_ */

tools/perf/util/scripting-engines/trace-event-perl.c

diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 5376378..b059dc5 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -371,7 +371,6 @@
 	run_start_sub();
 
 	free(command_line);
-	fprintf(stderr, "perf trace started with Perl script %s\n\n", script);
 	return 0;
 error:
 	perl_free(my_perl);
@@ -394,8 +393,6 @@
 	perl_destruct(my_perl);
 	perl_free(my_perl);
 
-	fprintf(stderr, "\nperf trace Perl script stopped\n");
-
 	return 0;
 }
 

tools/perf/util/scripting-engines/trace-event-python.c

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 6a72f14..81f39ca 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -374,8 +374,6 @@
 	}
 
 	free(command_line);
-	fprintf(stderr, "perf trace started with Python script %s\n\n",
-		script);
 
 	return err;
 error:
@@ -407,8 +405,6 @@
 	Py_XDECREF(main_module);
 	Py_Finalize();
 
-	fprintf(stderr, "\nperf trace Python script stopped\n");
-
 	return err;
 }
 

tools/perf/util/session.c

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index eed1cb8..25bfca4 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,16 @@
 {
 	struct stat input_stat;
 
+	if (!strcmp(self->filename, "-")) {
+		self->fd_pipe = true;
+		self->fd = STDIN_FILENO;
+
+		if (perf_header__read(self, self->fd) < 0)
+			pr_err("incompatible file format");
+
+		return 0;
+	}
+
 	self->fd = open(self->filename, O_RDONLY);
 	if (self->fd < 0) {
 		pr_err("failed to open file: %s", self->filename);
@@ -38,7 +48,7 @@
 		goto out_close;
 	}
 
-	if (perf_header__read(&self->header, self->fd) < 0) {
+	if (perf_header__read(self, self->fd) < 0) {
 		pr_err("incompatible file format");
 		goto out_close;
 	}
@@ -52,12 +62,21 @@
 	return -1;
 }
 
-static inline int perf_session__create_kernel_maps(struct perf_session *self)
+void perf_session__update_sample_type(struct perf_session *self)
 {
-	return map_groups__create_kernel_maps(&self->kmaps, self->vmlinux_maps);
+	self->sample_type = perf_header__sample_type(&self->header);
 }
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force)
+int perf_session__create_kernel_maps(struct perf_session *self)
+{
+	int ret = machine__create_kernel_maps(&self->host_machine);
+
+	if (ret >= 0)
+		ret = machines__create_guest_kernel_maps(&self->machines);
+	return ret;
+}
+
+struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe)
 {
 	size_t len = filename ? strlen(filename) + 1 : 0;
 	struct perf_session *self = zalloc(sizeof(*self) + len);
@@ -70,13 +89,15 @@
 
 	memcpy(self->filename, filename, len);
 	self->threads = RB_ROOT;
-	self->stats_by_id = RB_ROOT;
+	self->hists_tree = RB_ROOT;
 	self->last_match = NULL;
 	self->mmap_window = 32;
 	self->cwd = NULL;
 	self->cwdlen = 0;
-	self->unknown_events = 0;
-	map_groups__init(&self->kmaps);
+	self->machines = RB_ROOT;
+	self->repipe = repipe;
+	INIT_LIST_HEAD(&self->ordered_samples.samples_head);
+	machine__init(&self->host_machine, "", HOST_KERNEL_ID);
 
 	if (mode == O_RDONLY) {
 		if (perf_session__open(self, force) < 0)
@@ -90,7 +111,7 @@
 			goto out_delete;
 	}
 
-	self->sample_type = perf_header__sample_type(&self->header);
+	perf_session__update_sample_type(self);
 out:
 	return self;
 out_free:
@@ -117,22 +138,17 @@
 	return 0;
 }
 
-struct symbol **perf_session__resolve_callchain(struct perf_session *self,
-						struct thread *thread,
-						struct ip_callchain *chain,
-						struct symbol **parent)
+struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
+						   struct thread *thread,
+						   struct ip_callchain *chain,
+						   struct symbol **parent)
 {
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	struct symbol **syms = NULL;
 	unsigned int i;
+	struct map_symbol *syms = calloc(chain->nr, sizeof(*syms));
 
-	if (symbol_conf.use_callchain) {
-		syms = calloc(chain->nr, sizeof(*syms));
-		if (!syms) {
-			fprintf(stderr, "Can't allocate memory for symbols\n");
-			exit(-1);
-		}
-	}
+	if (!syms)
+		return NULL;
 
 	for (i = 0; i < chain->nr; i++) {
 		u64 ip = chain->ips[i];
@@ -152,15 +168,17 @@
 			continue;
 		}
 
+		al.filtered = false;
 		thread__find_addr_location(thread, self, cpumode,
-					   MAP__FUNCTION, ip, &al, NULL);
+				MAP__FUNCTION, thread->pid, ip, &al, NULL);
 		if (al.sym != NULL) {
 			if (sort__has_parent && !*parent &&
 			    symbol__match_parent_regex(al.sym))
 				*parent = al.sym;
 			if (!symbol_conf.use_callchain)
 				break;
-			syms[i] = al.sym;
+			syms[i].map = al.map;
+			syms[i].sym = al.sym;
 		}
 	}
 
@@ -174,6 +192,18 @@
 	return 0;
 }
 
+static int process_finished_round_stub(event_t *event __used,
+				       struct perf_session *session __used,
+				       struct perf_event_ops *ops __used)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static int process_finished_round(event_t *event,
+				  struct perf_session *session,
+				  struct perf_event_ops *ops);
+
 static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
 {
 	if (handler->sample == NULL)
@@ -194,29 +224,20 @@
 		handler->throttle = process_event_stub;
 	if (handler->unthrottle == NULL)
 		handler->unthrottle = process_event_stub;
-}
-
-static const char *event__name[] = {
-	[0]			 = "TOTAL",
-	[PERF_RECORD_MMAP]	 = "MMAP",
-	[PERF_RECORD_LOST]	 = "LOST",
-	[PERF_RECORD_COMM]	 = "COMM",
-	[PERF_RECORD_EXIT]	 = "EXIT",
-	[PERF_RECORD_THROTTLE]	 = "THROTTLE",
-	[PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
-	[PERF_RECORD_FORK]	 = "FORK",
-	[PERF_RECORD_READ]	 = "READ",
-	[PERF_RECORD_SAMPLE]	 = "SAMPLE",
-};
-
-unsigned long event__total[PERF_RECORD_MAX];
-
-void event__print_totals(void)
-{
-	int i;
-	for (i = 0; i < PERF_RECORD_MAX; ++i)
-		pr_info("%10s events: %10ld\n",
-			event__name[i], event__total[i]);
+	if (handler->attr == NULL)
+		handler->attr = process_event_stub;
+	if (handler->event_type == NULL)
+		handler->event_type = process_event_stub;
+	if (handler->tracing_data == NULL)
+		handler->tracing_data = process_event_stub;
+	if (handler->build_id == NULL)
+		handler->build_id = process_event_stub;
+	if (handler->finished_round == NULL) {
+		if (handler->ordered_samples)
+			handler->finished_round = process_finished_round;
+		else
+			handler->finished_round = process_finished_round_stub;
+	}
 }
 
 void mem_bswap_64(void *src, int byte_size)
@@ -270,6 +291,37 @@
 	self->read.id		= bswap_64(self->read.id);
 }
 
+static void event__attr_swap(event_t *self)
+{
+	size_t size;
+
+	self->attr.attr.type		= bswap_32(self->attr.attr.type);
+	self->attr.attr.size		= bswap_32(self->attr.attr.size);
+	self->attr.attr.config		= bswap_64(self->attr.attr.config);
+	self->attr.attr.sample_period	= bswap_64(self->attr.attr.sample_period);
+	self->attr.attr.sample_type	= bswap_64(self->attr.attr.sample_type);
+	self->attr.attr.read_format	= bswap_64(self->attr.attr.read_format);
+	self->attr.attr.wakeup_events	= bswap_32(self->attr.attr.wakeup_events);
+	self->attr.attr.bp_type		= bswap_32(self->attr.attr.bp_type);
+	self->attr.attr.bp_addr		= bswap_64(self->attr.attr.bp_addr);
+	self->attr.attr.bp_len		= bswap_64(self->attr.attr.bp_len);
+
+	size = self->header.size;
+	size -= (void *)&self->attr.id - (void *)self;
+	mem_bswap_64(self->attr.id, size);
+}
+
+static void event__event_type_swap(event_t *self)
+{
+	self->event_type.event_type.event_id =
+		bswap_64(self->event_type.event_type.event_id);
+}
+
+static void event__tracing_data_swap(event_t *self)
+{
+	self->tracing_data.size = bswap_32(self->tracing_data.size);
+}
+
 typedef void (*event__swap_op)(event_t *self);
 
 static event__swap_op event__swap_ops[] = {
@@ -280,9 +332,212 @@
 	[PERF_RECORD_LOST]   = event__all64_swap,
 	[PERF_RECORD_READ]   = event__read_swap,
 	[PERF_RECORD_SAMPLE] = event__all64_swap,
-	[PERF_RECORD_MAX]    = NULL,
+	[PERF_RECORD_HEADER_ATTR]   = event__attr_swap,
+	[PERF_RECORD_HEADER_EVENT_TYPE]   = event__event_type_swap,
+	[PERF_RECORD_HEADER_TRACING_DATA]   = event__tracing_data_swap,
+	[PERF_RECORD_HEADER_BUILD_ID]   = NULL,
+	[PERF_RECORD_HEADER_MAX]    = NULL,
 };
 
+struct sample_queue {
+	u64			timestamp;
+	struct sample_event	*event;
+	struct list_head	list;
+};
+
+static void flush_sample_queue(struct perf_session *s,
+			       struct perf_event_ops *ops)
+{
+	struct list_head *head = &s->ordered_samples.samples_head;
+	u64 limit = s->ordered_samples.next_flush;
+	struct sample_queue *tmp, *iter;
+
+	if (!ops->ordered_samples || !limit)
+		return;
+
+	list_for_each_entry_safe(iter, tmp, head, list) {
+		if (iter->timestamp > limit)
+			return;
+
+		if (iter == s->ordered_samples.last_inserted)
+			s->ordered_samples.last_inserted = NULL;
+
+		ops->sample((event_t *)iter->event, s);
+
+		s->ordered_samples.last_flush = iter->timestamp;
+		list_del(&iter->list);
+		free(iter->event);
+		free(iter);
+	}
+}
+
+/*
+ * When perf record finishes a pass on every buffers, it records this pseudo
+ * event.
+ * We record the max timestamp t found in the pass n.
+ * Assuming these timestamps are monotonic across cpus, we know that if
+ * a buffer still has events with timestamps below t, they will be all
+ * available and then read in the pass n + 1.
+ * Hence when we start to read the pass n + 2, we can safely flush every
+ * events with timestamps below t.
+ *
+ *    ============ PASS n =================
+ *       CPU 0         |   CPU 1
+ *                     |
+ *    cnt1 timestamps  |   cnt2 timestamps
+ *          1          |         2
+ *          2          |         3
+ *          -          |         4  <--- max recorded
+ *
+ *    ============ PASS n + 1 ==============
+ *       CPU 0         |   CPU 1
+ *                     |
+ *    cnt1 timestamps  |   cnt2 timestamps
+ *          3          |         5
+ *          4          |         6
+ *          5          |         7 <---- max recorded
+ *
+ *      Flush every events below timestamp 4
+ *
+ *    ============ PASS n + 2 ==============
+ *       CPU 0         |   CPU 1
+ *                     |
+ *    cnt1 timestamps  |   cnt2 timestamps
+ *          6          |         8
+ *          7          |         9
+ *          -          |         10
+ *
+ *      Flush every events below timestamp 7
+ *      etc...
+ */
+static int process_finished_round(event_t *event __used,
+				  struct perf_session *session,
+				  struct perf_event_ops *ops)
+{
+	flush_sample_queue(session, ops);
+	session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
+
+	return 0;
+}
+
+static void __queue_sample_end(struct sample_queue *new, struct list_head *head)
+{
+	struct sample_queue *iter;
+
+	list_for_each_entry_reverse(iter, head, list) {
+		if (iter->timestamp < new->timestamp) {
+			list_add(&new->list, &iter->list);
+			return;
+		}
+	}
+
+	list_add(&new->list, head);
+}
+
+static void __queue_sample_before(struct sample_queue *new,
+				  struct sample_queue *iter,
+				  struct list_head *head)
+{
+	list_for_each_entry_continue_reverse(iter, head, list) {
+		if (iter->timestamp < new->timestamp) {
+			list_add(&new->list, &iter->list);
+			return;
+		}
+	}
+
+	list_add(&new->list, head);
+}
+
+static void __queue_sample_after(struct sample_queue *new,
+				 struct sample_queue *iter,
+				 struct list_head *head)
+{
+	list_for_each_entry_continue(iter, head, list) {
+		if (iter->timestamp > new->timestamp) {
+			list_add_tail(&new->list, &iter->list);
+			return;
+		}
+	}
+	list_add_tail(&new->list, head);
+}
+
+/* The queue is ordered by time */
+static void __queue_sample_event(struct sample_queue *new,
+				 struct perf_session *s)
+{
+	struct sample_queue *last_inserted = s->ordered_samples.last_inserted;
+	struct list_head *head = &s->ordered_samples.samples_head;
+
+
+	if (!last_inserted) {
+		__queue_sample_end(new, head);
+		return;
+	}
+
+	/*
+	 * Most of the time the current event has a timestamp
+	 * very close to the last event inserted, unless we just switched
+	 * to another event buffer. Having a sorting based on a list and
+	 * on the last inserted event that is close to the current one is
+	 * probably more efficient than an rbtree based sorting.
+	 */
+	if (last_inserted->timestamp >= new->timestamp)
+		__queue_sample_before(new, last_inserted, head);
+	else
+		__queue_sample_after(new, last_inserted, head);
+}
+
+static int queue_sample_event(event_t *event, struct sample_data *data,
+			      struct perf_session *s)
+{
+	u64 timestamp = data->time;
+	struct sample_queue *new;
+
+
+	if (timestamp < s->ordered_samples.last_flush) {
+		printf("Warning: Timestamp below last timeslice flush\n");
+		return -EINVAL;
+	}
+
+	new = malloc(sizeof(*new));
+	if (!new)
+		return -ENOMEM;
+
+	new->timestamp = timestamp;
+
+	new->event = malloc(event->header.size);
+	if (!new->event) {
+		free(new);
+		return -ENOMEM;
+	}
+
+	memcpy(new->event, event, event->header.size);
+
+	__queue_sample_event(new, s);
+	s->ordered_samples.last_inserted = new;
+
+	if (new->timestamp > s->ordered_samples.max_timestamp)
+		s->ordered_samples.max_timestamp = new->timestamp;
+
+	return 0;
+}
+
+static int perf_session__process_sample(event_t *event, struct perf_session *s,
+					struct perf_event_ops *ops)
+{
+	struct sample_data data;
+
+	if (!ops->ordered_samples)
+		return ops->sample(event, s);
+
+	bzero(&data, sizeof(struct sample_data));
+	event__parse_sample(event, s->sample_type, &data);
+
+	queue_sample_event(event, &data, s);
+
+	return 0;
+}
+
 static int perf_session__process_event(struct perf_session *self,
 				       event_t *event,
 				       struct perf_event_ops *ops,
@@ -290,12 +545,11 @@
 {
 	trace_event(event);
 
-	if (event->header.type < PERF_RECORD_MAX) {
+	if (event->header.type < PERF_RECORD_HEADER_MAX) {
 		dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
 			    offset + head, event->header.size,
 			    event__name[event->header.type]);
-		++event__total[0];
-		++event__total[event->header.type];
+		hists__inc_nr_events(&self->hists, event->header.type);
 	}
 
 	if (self->header.needs_swap && event__swap_ops[event->header.type])
@@ -303,7 +557,7 @@
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-		return ops->sample(event, self);
+		return perf_session__process_sample(event, self, ops);
 	case PERF_RECORD_MMAP:
 		return ops->mmap(event, self);
 	case PERF_RECORD_COMM:
@@ -320,8 +574,20 @@
 		return ops->throttle(event, self);
 	case PERF_RECORD_UNTHROTTLE:
 		return ops->unthrottle(event, self);
+	case PERF_RECORD_HEADER_ATTR:
+		return ops->attr(event, self);
+	case PERF_RECORD_HEADER_EVENT_TYPE:
+		return ops->event_type(event, self);
+	case PERF_RECORD_HEADER_TRACING_DATA:
+		/* setup for reading amidst mmap */
+		lseek(self->fd, offset + head, SEEK_SET);
+		return ops->tracing_data(event, self);
+	case PERF_RECORD_HEADER_BUILD_ID:
+		return ops->build_id(event, self);
+	case PERF_RECORD_FINISHED_ROUND:
+		return ops->finished_round(event, self, ops);
 	default:
-		self->unknown_events++;
+		++self->hists.stats.nr_unknown_events;
 		return -1;
 	}
 }
@@ -333,46 +599,6 @@
 	self->size = bswap_16(self->size);
 }
 
-int perf_header__read_build_ids(struct perf_header *self,
-				int input, u64 offset, u64 size)
-{
-	struct build_id_event bev;
-	char filename[PATH_MAX];
-	u64 limit = offset + size;
-	int err = -1;
-
-	while (offset < limit) {
-		struct dso *dso;
-		ssize_t len;
-		struct list_head *head = &dsos__user;
-
-		if (read(input, &bev, sizeof(bev)) != sizeof(bev))
-			goto out;
-
-		if (self->needs_swap)
-			perf_event_header__bswap(&bev.header);
-
-		len = bev.header.size - sizeof(bev);
-		if (read(input, filename, len) != len)
-			goto out;
-
-		if (bev.header.misc & PERF_RECORD_MISC_KERNEL)
-			head = &dsos__kernel;
-
-		dso = __dsos__findnew(head, filename);
-		if (dso != NULL) {
-			dso__set_build_id(dso, &bev.build_id);
-			if (head == &dsos__kernel && filename[0] == '[')
-				dso->kernel = 1;
-		}
-
-		offset += bev.header.size;
-	}
-	err = 0;
-out:
-	return err;
-}
-
 static struct thread *perf_session__register_idle_thread(struct perf_session *self)
 {
 	struct thread *thread = perf_session__findnew(self, 0);
@@ -385,6 +611,104 @@
 	return thread;
 }
 
+int do_read(int fd, void *buf, size_t size)
+{
+	void *buf_start = buf;
+
+	while (size) {
+		int ret = read(fd, buf, size);
+
+		if (ret <= 0)
+			return ret;
+
+		size -= ret;
+		buf += ret;
+	}
+
+	return buf - buf_start;
+}
+
+#define session_done()	(*(volatile int *)(&session_done))
+volatile int session_done;
+
+static int __perf_session__process_pipe_events(struct perf_session *self,
+					       struct perf_event_ops *ops)
+{
+	event_t event;
+	uint32_t size;
+	int skip = 0;
+	u64 head;
+	int err;
+	void *p;
+
+	perf_event_ops__fill_defaults(ops);
+
+	head = 0;
+more:
+	err = do_read(self->fd, &event, sizeof(struct perf_event_header));
+	if (err <= 0) {
+		if (err == 0)
+			goto done;
+
+		pr_err("failed to read event header\n");
+		goto out_err;
+	}
+
+	if (self->header.needs_swap)
+		perf_event_header__bswap(&event.header);
+
+	size = event.header.size;
+	if (size == 0)
+		size = 8;
+
+	p = &event;
+	p += sizeof(struct perf_event_header);
+
+	if (size - sizeof(struct perf_event_header)) {
+		err = do_read(self->fd, p,
+			      size - sizeof(struct perf_event_header));
+		if (err <= 0) {
+			if (err == 0) {
+				pr_err("unexpected end of event stream\n");
+				goto done;
+			}
+
+			pr_err("failed to read event data\n");
+			goto out_err;
+		}
+	}
+
+	if (size == 0 ||
+	    (skip = perf_session__process_event(self, &event, ops,
+						0, head)) < 0) {
+		dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
+			    head, event.header.size, event.header.type);
+		/*
+		 * assume we lost track of the stream, check alignment, and
+		 * increment a single u64 in the hope to catch on again 'soon'.
+		 */
+		if (unlikely(head & 7))
+			head &= ~7ULL;
+
+		size = 8;
+	}
+
+	head += size;
+
+	dump_printf("\n%#Lx [%#x]: event: %d\n",
+		    head, event.header.size, event.header.type);
+
+	if (skip > 0)
+		head += skip;
+
+	if (!session_done())
+		goto more;
+done:
+	err = 0;
+out_err:
+	return err;
+}
+
 int __perf_session__process_events(struct perf_session *self,
 				   u64 data_offset, u64 data_size,
 				   u64 file_size, struct perf_event_ops *ops)
@@ -396,6 +720,10 @@
 	event_t *event;
 	uint32_t size;
 	char *buf;
+	struct ui_progress *progress = ui_progress__new("Processing events...",
+							self->size);
+	if (progress == NULL)
+		return -1;
 
 	perf_event_ops__fill_defaults(ops);
 
@@ -424,6 +752,7 @@
 
 more:
 	event = (event_t *)(buf + head);
+	ui_progress__update(progress, offset);
 
 	if (self->header.needs_swap)
 		perf_event_header__bswap(&event->header);
@@ -473,7 +802,11 @@
 		goto more;
 done:
 	err = 0;
+	/* do the final flush for ordered samples */
+	self->ordered_samples.next_flush = ULLONG_MAX;
+	flush_sample_queue(self, ops);
 out_err:
+	ui_progress__delete(progress);
 	return err;
 }
 
@@ -502,9 +835,13 @@
 		self->cwdlen = strlen(self->cwd);
 	}
 
-	err = __perf_session__process_events(self, self->header.data_offset,
-					     self->header.data_size,
-					     self->size, ops);
+	if (!self->fd_pipe)
+		err = __perf_session__process_events(self,
+						     self->header.data_offset,
+						     self->header.data_size,
+						     self->size, ops);
+	else
+		err = __perf_session__process_pipe_events(self, ops);
 out_err:
 	return err;
 }
@@ -519,56 +856,41 @@
 	return true;
 }
 
-int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self,
+int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps,
 					     const char *symbol_name,
 					     u64 addr)
 {
 	char *bracket;
 	enum map_type i;
+	struct ref_reloc_sym *ref;
 
-	self->ref_reloc_sym.name = strdup(symbol_name);
-	if (self->ref_reloc_sym.name == NULL)
+	ref = zalloc(sizeof(struct ref_reloc_sym));
+	if (ref == NULL)
 		return -ENOMEM;
 
-	bracket = strchr(self->ref_reloc_sym.name, ']');
+	ref->name = strdup(symbol_name);
+	if (ref->name == NULL) {
+		free(ref);
+		return -ENOMEM;
+	}
+
+	bracket = strchr(ref->name, ']');
 	if (bracket)
 		*bracket = '\0';
 
-	self->ref_reloc_sym.addr = addr;
+	ref->addr = addr;
 
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		struct kmap *kmap = map__kmap(self->vmlinux_maps[i]);
-		kmap->ref_reloc_sym = &self->ref_reloc_sym;
+		struct kmap *kmap = map__kmap(maps[i]);
+		kmap->ref_reloc_sym = ref;
 	}
 
 	return 0;
 }
 
-static u64 map__reloc_map_ip(struct map *map, u64 ip)
+size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp)
 {
-	return ip + (s64)map->pgoff;
-}
-
-static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
-{
-	return ip - (s64)map->pgoff;
-}
-
-void map__reloc_vmlinux(struct map *self)
-{
-	struct kmap *kmap = map__kmap(self);
-	s64 reloc;
-
-	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
-		return;
-
-	reloc = (kmap->ref_reloc_sym->unrelocated_addr -
-		 kmap->ref_reloc_sym->addr);
-
-	if (!reloc)
-		return;
-
-	self->map_ip   = map__reloc_map_ip;
-	self->unmap_ip = map__reloc_unmap_ip;
-	self->pgoff    = reloc;
+	return __dsos__fprintf(&self->host_machine.kernel_dsos, fp) +
+	       __dsos__fprintf(&self->host_machine.user_dsos, fp) +
+	       machines__fprintf_dsos(&self->machines, fp);
 }

tools/perf/util/session.h

diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 5c33417..e7fce48 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_SESSION_H
 #define __PERF_SESSION_H
 
+#include "hist.h"
 #include "event.h"
 #include "header.h"
 #include "symbol.h"
@@ -8,45 +9,69 @@
 #include <linux/rbtree.h>
 #include "../../../include/linux/perf_event.h"
 
+struct sample_queue;
 struct ip_callchain;
 struct thread;
 
+struct ordered_samples {
+	u64			last_flush;
+	u64			next_flush;
+	u64			max_timestamp;
+	struct list_head	samples_head;
+	struct sample_queue	*last_inserted;
+};
+
 struct perf_session {
 	struct perf_header	header;
 	unsigned long		size;
 	unsigned long		mmap_window;
-	struct map_groups	kmaps;
 	struct rb_root		threads;
 	struct thread		*last_match;
-	struct map		*vmlinux_maps[MAP__NR_TYPES];
-	struct events_stats	events_stats;
-	struct rb_root		stats_by_id;
-	unsigned long		event_total[PERF_RECORD_MAX];
-	unsigned long		unknown_events;
-	struct rb_root		hists;
+	struct machine		host_machine;
+	struct rb_root		machines;
+	struct rb_root		hists_tree;
+	/*
+	 * FIXME: should point to the first entry in hists_tree and
+	 *        be a hists instance. Right now its only 'report'
+	 *        that is using ->hists_tree while all the rest use
+	 *        ->hists.
+	 */
+	struct hists		hists;
 	u64			sample_type;
-	struct ref_reloc_sym	ref_reloc_sym;
 	int			fd;
+	bool			fd_pipe;
+	bool			repipe;
 	int			cwdlen;
 	char			*cwd;
+	struct ordered_samples	ordered_samples;
 	char filename[0];
 };
 
+struct perf_event_ops;
+
 typedef int (*event_op)(event_t *self, struct perf_session *session);
+typedef int (*event_op2)(event_t *self, struct perf_session *session,
+			 struct perf_event_ops *ops);
 
 struct perf_event_ops {
-	event_op sample,
-		 mmap,
-		 comm,
-		 fork,
-		 exit,
-		 lost,
-		 read,
-		 throttle,
-		 unthrottle;
+	event_op	sample,
+			mmap,
+			comm,
+			fork,
+			exit,
+			lost,
+			read,
+			throttle,
+			unthrottle,
+			attr,
+			event_type,
+			tracing_data,
+			build_id;
+	event_op2	finished_round;
+	bool		ordered_samples;
 };
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force);
+struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe);
 void perf_session__delete(struct perf_session *self);
 
 void perf_event_header__bswap(struct perf_event_header *self);
@@ -57,33 +82,66 @@
 int perf_session__process_events(struct perf_session *self,
 				 struct perf_event_ops *event_ops);
 
-struct symbol **perf_session__resolve_callchain(struct perf_session *self,
-						struct thread *thread,
-						struct ip_callchain *chain,
-						struct symbol **parent);
+struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
+						   struct thread *thread,
+						   struct ip_callchain *chain,
+						   struct symbol **parent);
 
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
-int perf_header__read_build_ids(struct perf_header *self, int input,
-				u64 offset, u64 file_size);
-
-int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self,
+int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps,
 					     const char *symbol_name,
 					     u64 addr);
 
 void mem_bswap_64(void *src, int byte_size);
 
-static inline int __perf_session__create_kernel_maps(struct perf_session *self,
-						struct dso *kernel)
+int perf_session__create_kernel_maps(struct perf_session *self);
+
+int do_read(int fd, void *buf, size_t size);
+void perf_session__update_sample_type(struct perf_session *self);
+
+static inline
+struct machine *perf_session__find_host_machine(struct perf_session *self)
 {
-	return __map_groups__create_kernel_maps(&self->kmaps,
-						self->vmlinux_maps, kernel);
+	return &self->host_machine;
 }
 
-static inline struct map *
-	perf_session__new_module_map(struct perf_session *self,
-				     u64 start, const char *filename)
+static inline
+struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid)
 {
-	return map_groups__new_module(&self->kmaps, start, filename);
+	if (pid == HOST_KERNEL_ID)
+		return &self->host_machine;
+	return machines__find(&self->machines, pid);
+}
+
+static inline
+struct machine *perf_session__findnew_machine(struct perf_session *self, pid_t pid)
+{
+	if (pid == HOST_KERNEL_ID)
+		return &self->host_machine;
+	return machines__findnew(&self->machines, pid);
+}
+
+static inline
+void perf_session__process_machines(struct perf_session *self,
+				    machine__process_t process)
+{
+	process(&self->host_machine, self);
+	return machines__process(&self->machines, process, self);
+}
+
+size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp);
+
+static inline
+size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp,
+					  bool with_hits)
+{
+	return machines__fprintf_dsos_buildid(&self->machines, fp, with_hits);
+}
+
+static inline
+size_t perf_session__fprintf_nr_events(struct perf_session *self, FILE *fp)
+{
+	return hists__fprintf_nr_events(&self->hists, fp);
 }
 #endif /* __PERF_SESSION_H */

tools/perf/util/sort.c

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index cb0f327..2316cb5 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,10 +1,10 @@
 #include "sort.h"
 
 regex_t		parent_regex;
-char		default_parent_pattern[] = "^sys_|^do_page_fault";
-char		*parent_pattern = default_parent_pattern;
-char		default_sort_order[] = "comm,dso,symbol";
-char		*sort_order = default_sort_order;
+const char	default_parent_pattern[] = "^sys_|^do_page_fault";
+const char	*parent_pattern = default_parent_pattern;
+const char	default_sort_order[] = "comm,dso,symbol";
+const char	*sort_order = default_sort_order;
 int		sort__need_collapse = 0;
 int		sort__has_parent = 0;
 
@@ -18,39 +18,50 @@
 
 LIST_HEAD(hist_entry__sort_list);
 
+static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width);
+static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
+				     size_t size, unsigned int width);
+static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width);
+static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width);
+static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width);
+
 struct sort_entry sort_thread = {
-	.header = "Command:  Pid",
-	.cmp	= sort__thread_cmp,
-	.print	= sort__thread_print,
-	.width	= &threads__col_width,
+	.se_header	= "Command:  Pid",
+	.se_cmp		= sort__thread_cmp,
+	.se_snprintf	= hist_entry__thread_snprintf,
+	.se_width	= &threads__col_width,
 };
 
 struct sort_entry sort_comm = {
-	.header		= "Command",
-	.cmp		= sort__comm_cmp,
-	.collapse	= sort__comm_collapse,
-	.print		= sort__comm_print,
-	.width		= &comms__col_width,
+	.se_header	= "Command",
+	.se_cmp		= sort__comm_cmp,
+	.se_collapse	= sort__comm_collapse,
+	.se_snprintf	= hist_entry__comm_snprintf,
+	.se_width	= &comms__col_width,
 };
 
 struct sort_entry sort_dso = {
-	.header = "Shared Object",
-	.cmp	= sort__dso_cmp,
-	.print	= sort__dso_print,
-	.width	= &dsos__col_width,
+	.se_header	= "Shared Object",
+	.se_cmp		= sort__dso_cmp,
+	.se_snprintf	= hist_entry__dso_snprintf,
+	.se_width	= &dsos__col_width,
 };
 
 struct sort_entry sort_sym = {
-	.header = "Symbol",
-	.cmp	= sort__sym_cmp,
-	.print	= sort__sym_print,
+	.se_header	= "Symbol",
+	.se_cmp		= sort__sym_cmp,
+	.se_snprintf	= hist_entry__sym_snprintf,
 };
 
 struct sort_entry sort_parent = {
-	.header = "Parent symbol",
-	.cmp	= sort__parent_cmp,
-	.print	= sort__parent_print,
-	.width	= &parent_symbol__col_width,
+	.se_header	= "Parent symbol",
+	.se_cmp		= sort__parent_cmp,
+	.se_snprintf	= hist_entry__parent_snprintf,
+	.se_width	= &parent_symbol__col_width,
 };
 
 struct sort_dimension {
@@ -85,45 +96,38 @@
 	return right->thread->pid - left->thread->pid;
 }
 
-int repsep_fprintf(FILE *fp, const char *fmt, ...)
+static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
 	int n;
 	va_list ap;
 
 	va_start(ap, fmt);
-	if (!field_sep)
-		n = vfprintf(fp, fmt, ap);
-	else {
-		char *bf = NULL;
-		n = vasprintf(&bf, fmt, ap);
-		if (n > 0) {
-			char *sep = bf;
+	n = vsnprintf(bf, size, fmt, ap);
+	if (field_sep && n > 0) {
+		char *sep = bf;
 
-			while (1) {
-				sep = strchr(sep, *field_sep);
-				if (sep == NULL)
-					break;
-				*sep = '.';
-			}
+		while (1) {
+			sep = strchr(sep, *field_sep);
+			if (sep == NULL)
+				break;
+			*sep = '.';
 		}
-		fputs(bf, fp);
-		free(bf);
 	}
 	va_end(ap);
 	return n;
 }
 
-size_t
-sort__thread_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width)
 {
-	return repsep_fprintf(fp, "%*s:%5d", width - 6,
+	return repsep_snprintf(bf, size, "%*s:%5d", width,
 			      self->thread->comm ?: "", self->thread->pid);
 }
 
-size_t
-sort__comm_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
+				     size_t size, unsigned int width)
 {
-	return repsep_fprintf(fp, "%*s", width, self->thread->comm);
+	return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
 }
 
 /* --sort dso */
@@ -131,8 +135,8 @@
 int64_t
 sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	struct dso *dso_l = left->map ? left->map->dso : NULL;
-	struct dso *dso_r = right->map ? right->map->dso : NULL;
+	struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL;
+	struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL;
 	const char *dso_name_l, *dso_name_r;
 
 	if (!dso_l || !dso_r)
@@ -149,16 +153,16 @@
 	return strcmp(dso_name_l, dso_name_r);
 }
 
-size_t
-sort__dso_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
 {
-	if (self->map && self->map->dso) {
-		const char *dso_name = !verbose ? self->map->dso->short_name :
-						  self->map->dso->long_name;
-		return repsep_fprintf(fp, "%-*s", width, dso_name);
+	if (self->ms.map && self->ms.map->dso) {
+		const char *dso_name = !verbose ? self->ms.map->dso->short_name :
+						  self->ms.map->dso->long_name;
+		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
 	}
 
-	return repsep_fprintf(fp, "%*llx", width, (u64)self->ip);
+	return repsep_snprintf(bf, size, "%*Lx", width, self->ip);
 }
 
 /* --sort symbol */
@@ -168,31 +172,31 @@
 {
 	u64 ip_l, ip_r;
 
-	if (left->sym == right->sym)
+	if (left->ms.sym == right->ms.sym)
 		return 0;
 
-	ip_l = left->sym ? left->sym->start : left->ip;
-	ip_r = right->sym ? right->sym->start : right->ip;
+	ip_l = left->ms.sym ? left->ms.sym->start : left->ip;
+	ip_r = right->ms.sym ? right->ms.sym->start : right->ip;
 
 	return (int64_t)(ip_r - ip_l);
 }
 
-
-size_t
-sort__sym_print(FILE *fp, struct hist_entry *self, unsigned int width __used)
+static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width __used)
 {
 	size_t ret = 0;
 
 	if (verbose) {
-		char o = self->map ? dso__symtab_origin(self->map->dso) : '!';
-		ret += repsep_fprintf(fp, "%#018llx %c ", (u64)self->ip, o);
+		char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
+		ret += repsep_snprintf(bf, size, "%#018llx %c ", self->ip, o);
 	}
 
-	ret += repsep_fprintf(fp, "[%c] ", self->level);
-	if (self->sym)
-		ret += repsep_fprintf(fp, "%s", self->sym->name);
+	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level);
+	if (self->ms.sym)
+		ret += repsep_snprintf(bf + ret, size - ret, "%s",
+				       self->ms.sym->name);
 	else
-		ret += repsep_fprintf(fp, "%#016llx", (u64)self->ip);
+		ret += repsep_snprintf(bf + ret, size - ret, "%#016llx", self->ip);
 
 	return ret;
 }
@@ -231,10 +235,10 @@
 	return strcmp(sym_l->name, sym_r->name);
 }
 
-size_t
-sort__parent_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width)
 {
-	return repsep_fprintf(fp, "%-*s", width,
+	return repsep_snprintf(bf, size, "%-*s", width,
 			      self->parent ? self->parent->name : "[other]");
 }
 
@@ -251,7 +255,7 @@
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		if (sd->entry->collapse)
+		if (sd->entry->se_collapse)
 			sort__need_collapse = 1;
 
 		if (sd->entry == &sort_parent) {
@@ -260,9 +264,8 @@
 				char err[BUFSIZ];
 
 				regerror(ret, &parent_regex, err, sizeof(err));
-				fprintf(stderr, "Invalid regex: %s\n%s",
-					parent_pattern, err);
-				exit(-1);
+				pr_err("Invalid regex: %s\n%s", parent_pattern, err);
+				return -EINVAL;
 			}
 			sort__has_parent = 1;
 		}

tools/perf/util/sort.h

diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 753f9ea..0d61c40 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -25,10 +25,10 @@
 #include "sort.h"
 
 extern regex_t parent_regex;
-extern char *sort_order;
-extern char default_parent_pattern[];
-extern char *parent_pattern;
-extern char default_sort_order[];
+extern const char *sort_order;
+extern const char default_parent_pattern[];
+extern const char *parent_pattern;
+extern const char default_sort_order[];
 extern int sort__need_collapse;
 extern int sort__has_parent;
 extern char *field_sep;
@@ -43,19 +43,24 @@
 
 struct hist_entry {
 	struct rb_node		rb_node;
-	u64			count;
+	u64			period;
+	u64			period_sys;
+	u64			period_us;
+	u64			period_guest_sys;
+	u64			period_guest_us;
+	struct map_symbol	ms;
 	struct thread		*thread;
-	struct map		*map;
-	struct symbol		*sym;
 	u64			ip;
+	u32			nr_events;
 	char			level;
-	struct symbol	  *parent;
-	struct callchain_node	callchain;
+	u8			filtered;
+	struct symbol		*parent;
 	union {
 		unsigned long	  position;
 		struct hist_entry *pair;
 		struct rb_root	  sorted_chain;
 	};
+	struct callchain_node	callchain[0];
 };
 
 enum sort_type {
@@ -73,12 +78,13 @@
 struct sort_entry {
 	struct list_head list;
 
-	const char *header;
+	const char *se_header;
 
-	int64_t (*cmp)(struct hist_entry *, struct hist_entry *);
-	int64_t (*collapse)(struct hist_entry *, struct hist_entry *);
-	size_t	(*print)(FILE *fp, struct hist_entry *, unsigned int width);
-	unsigned int *width;
+	int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
+	int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *);
+	int	(*se_snprintf)(struct hist_entry *self, char *bf, size_t size,
+			       unsigned int width);
+	unsigned int *se_width;
 	bool	elide;
 };
 
@@ -87,7 +93,6 @@
 
 void setup_sorting(const char * const usagestr[], const struct option *opts);
 
-extern int repsep_fprintf(FILE *fp, const char *fmt, ...);
 extern size_t sort__thread_print(FILE *, struct hist_entry *, unsigned int);
 extern size_t sort__comm_print(FILE *, struct hist_entry *, unsigned int);
 extern size_t sort__dso_print(FILE *, struct hist_entry *, unsigned int);

tools/perf/util/string.c

diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index a175949..0409fc7 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -1,48 +1,5 @@
-#include "string.h"
 #include "util.h"
-
-static int hex(char ch)
-{
-	if ((ch >= '0') && (ch <= '9'))
-		return ch - '0';
-	if ((ch >= 'a') && (ch <= 'f'))
-		return ch - 'a' + 10;
-	if ((ch >= 'A') && (ch <= 'F'))
-		return ch - 'A' + 10;
-	return -1;
-}
-
-/*
- * While we find nice hex chars, build a long_val.
- * Return number of chars processed.
- */
-int hex2u64(const char *ptr, u64 *long_val)
-{
-	const char *p = ptr;
-	*long_val = 0;
-
-	while (*p) {
-		const int hex_val = hex(*p);
-
-		if (hex_val < 0)
-			break;
-
-		*long_val = (*long_val << 4) | hex_val;
-		p++;
-	}
-
-	return p - ptr;
-}
-
-char *strxfrchar(char *s, char from, char to)
-{
-	char *p = s;
-
-	while ((p = strchr(p, from)) != NULL)
-		*p++ = to;
-
-	return s;
-}
+#include "string.h"
 
 #define K 1024LL
 /*

tools/perf/util/string.h

diff --git a/tools/perf/util/string.h b/tools/perf/util/string.h
deleted file mode 100644
index 542e44d..0000000
--- a/tools/perf/util/string.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef __PERF_STRING_H_
-#define __PERF_STRING_H_
-
-#include <stdbool.h>
-#include "types.h"
-
-int hex2u64(const char *ptr, u64 *val);
-char *strxfrchar(char *s, char from, char to);
-s64 perf_atoll(const char *str);
-char **argv_split(const char *str, int *argcp);
-void argv_free(char **argv);
-bool strglobmatch(const char *str, const char *pat);
-bool strlazymatch(const char *str, const char *pat);
-
-#define _STR(x) #x
-#define STR(x) _STR(x)
-
-#endif /* __PERF_STRING_H */

tools/perf/util/symbol.c

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c458c4a..a06131f 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,13 +1,19 @@
-#include "util.h"
-#include "../perf.h"
-#include "sort.h"
-#include "string.h"
+#define _GNU_SOURCE
+#include <ctype.h>
+#include <dirent.h>
+#include <errno.h>
+#include <libgen.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/param.h>
+#include <fcntl.h>
+#include <unistd.h>
 #include "symbol.h"
-#include "thread.h"
+#include "strlist.h"
 
-#include "debug.h"
-
-#include <asm/bug.h>
 #include <libelf.h>
 #include <gelf.h>
 #include <elf.h>
@@ -18,22 +24,12 @@
 #define NT_GNU_BUILD_ID 3
 #endif
 
-enum dso_origin {
-	DSO__ORIG_KERNEL = 0,
-	DSO__ORIG_JAVA_JIT,
-	DSO__ORIG_BUILD_ID_CACHE,
-	DSO__ORIG_FEDORA,
-	DSO__ORIG_UBUNTU,
-	DSO__ORIG_BUILDID,
-	DSO__ORIG_DSO,
-	DSO__ORIG_KMODULE,
-	DSO__ORIG_NOT_FOUND,
-};
-
 static void dsos__add(struct list_head *head, struct dso *dso);
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 static int dso__load_kernel_sym(struct dso *self, struct map *map,
 				symbol_filter_t filter);
+static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
+			symbol_filter_t filter);
 static int vmlinux_path__nr_entries;
 static char **vmlinux_path;
 
@@ -126,16 +122,17 @@
 static struct symbol *symbol__new(u64 start, u64 len, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
-	struct symbol *self = zalloc(symbol_conf.priv_size +
-				     sizeof(*self) + namelen);
+	struct symbol *self = calloc(1, (symbol_conf.priv_size +
+					 sizeof(*self) + namelen));
 	if (self == NULL)
 		return NULL;
 
 	if (symbol_conf.priv_size)
 		self = ((void *)self) + symbol_conf.priv_size;
 
-	self->start = start;
-	self->end   = len ? start + len - 1 : start;
+	self->start   = start;
+	self->end     = len ? start + len - 1 : start;
+	self->namelen = namelen - 1;
 
 	pr_debug4("%s: %s %#Lx-%#Lx\n", __func__, name, start, self->end);
 
@@ -178,7 +175,7 @@
 
 struct dso *dso__new(const char *name)
 {
-	struct dso *self = zalloc(sizeof(*self) + strlen(name) + 1);
+	struct dso *self = calloc(1, sizeof(*self) + strlen(name) + 1);
 
 	if (self != NULL) {
 		int i;
@@ -192,6 +189,8 @@
 		self->loaded = 0;
 		self->sorted_by_name = 0;
 		self->has_build_id = 0;
+		self->kernel = DSO_TYPE_USER;
+		INIT_LIST_HEAD(&self->node);
 	}
 
 	return self;
@@ -408,12 +407,9 @@
 		char *symbol_name;
 
 		line_len = getline(&line, &n, file);
-		if (line_len < 0)
+		if (line_len < 0 || !line)
 			break;
 
-		if (!line)
-			goto out_failure;
-
 		line[--line_len] = '\0'; /* \n */
 
 		len = hex2u64(line, &start);
@@ -465,6 +461,7 @@
 	 * map__split_kallsyms, when we have split the maps per module
 	 */
 	symbols__insert(root, sym);
+
 	return 0;
 }
 
@@ -489,6 +486,7 @@
 			       symbol_filter_t filter)
 {
 	struct map_groups *kmaps = map__kmap(map)->kmaps;
+	struct machine *machine = kmaps->machine;
 	struct map *curr_map = map;
 	struct symbol *pos;
 	int count = 0;
@@ -510,15 +508,33 @@
 			*module++ = '\0';
 
 			if (strcmp(curr_map->dso->short_name, module)) {
-				curr_map = map_groups__find_by_name(kmaps, map->type, module);
-				if (curr_map == NULL) {
-					pr_debug("/proc/{kallsyms,modules} "
-					         "inconsistency while looking "
-						 "for \"%s\" module!\n", module);
-					return -1;
+				if (curr_map != map &&
+				    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+				    machine__is_default_guest(machine)) {
+					/*
+					 * We assume all symbols of a module are
+					 * continuous in * kallsyms, so curr_map
+					 * points to a module and all its
+					 * symbols are in its kmap. Mark it as
+					 * loaded.
+					 */
+					dso__set_loaded(curr_map->dso,
+							curr_map->type);
 				}
 
-				if (curr_map->dso->loaded)
+				curr_map = map_groups__find_by_name(kmaps,
+							map->type, module);
+				if (curr_map == NULL) {
+					pr_debug("%s/proc/{kallsyms,modules} "
+					         "inconsistency while looking "
+						 "for \"%s\" module!\n",
+						 machine->root_dir, module);
+					curr_map = map;
+					goto discard_symbol;
+				}
+
+				if (curr_map->dso->loaded &&
+				    !machine__is_default_guest(machine))
 					goto discard_symbol;
 			}
 			/*
@@ -531,13 +547,21 @@
 			char dso_name[PATH_MAX];
 			struct dso *dso;
 
-			snprintf(dso_name, sizeof(dso_name), "[kernel].%d",
-				 kernel_range++);
+			if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+				snprintf(dso_name, sizeof(dso_name),
+					"[guest.kernel].%d",
+					kernel_range++);
+			else
+				snprintf(dso_name, sizeof(dso_name),
+					"[kernel].%d",
+					kernel_range++);
 
 			dso = dso__new(dso_name);
 			if (dso == NULL)
 				return -1;
 
+			dso->kernel = self->kernel;
+
 			curr_map = map__new2(pos->start, dso, map->type);
 			if (curr_map == NULL) {
 				dso__delete(dso);
@@ -561,6 +585,12 @@
 		}
 	}
 
+	if (curr_map != map &&
+	    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+	    machine__is_default_guest(kmaps->machine)) {
+		dso__set_loaded(curr_map->dso, curr_map->type);
+	}
+
 	return count;
 }
 
@@ -571,7 +601,10 @@
 		return -1;
 
 	symbols__fixup_end(&self->symbols[map->type]);
-	self->origin = DSO__ORIG_KERNEL;
+	if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+		self->origin = DSO__ORIG_GUEST_KERNEL;
+	else
+		self->origin = DSO__ORIG_KERNEL;
 
 	return dso__split_kallsyms(self, map, filter);
 }
@@ -870,8 +903,8 @@
 	if (err == 0)
 		return nr;
 out:
-	pr_warning("%s: problems reading %s PLT info.\n",
-		   __func__, self->long_name);
+	pr_debug("%s: problems reading %s PLT info.\n",
+		 __func__, self->long_name);
 	return 0;
 }
 
@@ -958,7 +991,7 @@
 	nr_syms = shdr.sh_size / shdr.sh_entsize;
 
 	memset(&sym, 0, sizeof(sym));
-	if (!self->kernel) {
+	if (self->kernel == DSO_TYPE_USER) {
 		self->adjust_symbols = (ehdr.e_type == ET_EXEC ||
 				elf_section_by_name(elf, &ehdr, &shdr,
 						     ".gnu.prelink_undo",
@@ -990,7 +1023,7 @@
 
 		section_name = elf_sec__name(&shdr, secstrs);
 
-		if (self->kernel || kmodule) {
+		if (self->kernel != DSO_TYPE_USER || kmodule) {
 			char dso_name[PATH_MAX];
 
 			if (strcmp(section_name,
@@ -1017,6 +1050,7 @@
 				curr_dso = dso__new(dso_name);
 				if (curr_dso == NULL)
 					goto out_elf_end;
+				curr_dso->kernel = self->kernel;
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
 				if (curr_map == NULL) {
@@ -1025,9 +1059,9 @@
 				}
 				curr_map->map_ip = identity__map_ip;
 				curr_map->unmap_ip = identity__map_ip;
-				curr_dso->origin = DSO__ORIG_KERNEL;
+				curr_dso->origin = self->origin;
 				map_groups__insert(kmap->kmaps, curr_map);
-				dsos__add(&dsos__kernel, curr_dso);
+				dsos__add(&self->node, curr_dso);
 				dso__set_loaded(curr_dso, map->type);
 			} else
 				curr_dso = curr_map->dso;
@@ -1089,7 +1123,7 @@
 	return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0;
 }
 
-static bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
+bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 {
 	bool have_build_id = false;
 	struct dso *pos;
@@ -1107,13 +1141,6 @@
 	return have_build_id;
 }
 
-bool dsos__read_build_ids(bool with_hits)
-{
-	bool kbuildids = __dsos__read_build_ids(&dsos__kernel, with_hits),
-	     ubuildids = __dsos__read_build_ids(&dsos__user, with_hits);
-	return kbuildids || ubuildids;
-}
-
 /*
  * Align offset to 4 bytes as needed for note name and descriptor data.
  */
@@ -1248,6 +1275,8 @@
 		[DSO__ORIG_BUILDID] =  'b',
 		[DSO__ORIG_DSO] =      'd',
 		[DSO__ORIG_KMODULE] =  'K',
+		[DSO__ORIG_GUEST_KERNEL] =  'g',
+		[DSO__ORIG_GUEST_KMODULE] =  'G',
 	};
 
 	if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND)
@@ -1263,11 +1292,20 @@
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 	int ret = -1;
 	int fd;
+	struct machine *machine;
+	const char *root_dir;
 
 	dso__set_loaded(self, map->type);
 
-	if (self->kernel)
+	if (self->kernel == DSO_TYPE_KERNEL)
 		return dso__load_kernel_sym(self, map, filter);
+	else if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+		return dso__load_guest_kernel_sym(self, map, filter);
+
+	if (map->groups && map->groups->machine)
+		machine = map->groups->machine;
+	else
+		machine = NULL;
 
 	name = malloc(size);
 	if (!name)
@@ -1321,6 +1359,13 @@
 		case DSO__ORIG_DSO:
 			snprintf(name, size, "%s", self->long_name);
 			break;
+		case DSO__ORIG_GUEST_KMODULE:
+			if (map->groups && map->groups->machine)
+				root_dir = map->groups->machine->root_dir;
+			else
+				root_dir = "";
+			snprintf(name, size, "%s%s", root_dir, self->long_name);
+			break;
 
 		default:
 			goto out;
@@ -1374,7 +1419,8 @@
 	return NULL;
 }
 
-static int dso__kernel_module_get_build_id(struct dso *self)
+static int dso__kernel_module_get_build_id(struct dso *self,
+				const char *root_dir)
 {
 	char filename[PATH_MAX];
 	/*
@@ -1384,8 +1430,8 @@
 	const char *name = self->short_name + 1;
 
 	snprintf(filename, sizeof(filename),
-		 "/sys/module/%.*s/notes/.note.gnu.build-id",
-		 (int)strlen(name - 1), name);
+		 "%s/sys/module/%.*s/notes/.note.gnu.build-id",
+		 root_dir, (int)strlen(name) - 1, name);
 
 	if (sysfs__read_build_id(filename, self->build_id,
 				 sizeof(self->build_id)) == 0)
@@ -1394,26 +1440,33 @@
 	return 0;
 }
 
-static int map_groups__set_modules_path_dir(struct map_groups *self, char *dirname)
+static int map_groups__set_modules_path_dir(struct map_groups *self,
+				const char *dir_name)
 {
 	struct dirent *dent;
-	DIR *dir = opendir(dirname);
+	DIR *dir = opendir(dir_name);
 
 	if (!dir) {
-		pr_debug("%s: cannot open %s dir\n", __func__, dirname);
+		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
 		return -1;
 	}
 
 	while ((dent = readdir(dir)) != NULL) {
 		char path[PATH_MAX];
+		struct stat st;
 
-		if (dent->d_type == DT_DIR) {
+		/*sshfs might return bad dent->d_type, so we have to stat*/
+		sprintf(path, "%s/%s", dir_name, dent->d_name);
+		if (stat(path, &st))
+			continue;
+
+		if (S_ISDIR(st.st_mode)) {
 			if (!strcmp(dent->d_name, ".") ||
 			    !strcmp(dent->d_name, ".."))
 				continue;
 
 			snprintf(path, sizeof(path), "%s/%s",
-				 dirname, dent->d_name);
+				 dir_name, dent->d_name);
 			if (map_groups__set_modules_path_dir(self, path) < 0)
 				goto failure;
 		} else {
@@ -1433,13 +1486,13 @@
 				continue;
 
 			snprintf(path, sizeof(path), "%s/%s",
-				 dirname, dent->d_name);
+				 dir_name, dent->d_name);
 
 			long_name = strdup(path);
 			if (long_name == NULL)
 				goto failure;
 			dso__set_long_name(map->dso, long_name);
-			dso__kernel_module_get_build_id(map->dso);
+			dso__kernel_module_get_build_id(map->dso, "");
 		}
 	}
 
@@ -1449,18 +1502,47 @@
 	return -1;
 }
 
-static int map_groups__set_modules_path(struct map_groups *self)
+static char *get_kernel_version(const char *root_dir)
 {
-	struct utsname uts;
+	char version[PATH_MAX];
+	FILE *file;
+	char *name, *tmp;
+	const char *prefix = "Linux version ";
+
+	sprintf(version, "%s/proc/version", root_dir);
+	file = fopen(version, "r");
+	if (!file)
+		return NULL;
+
+	version[0] = '\0';
+	tmp = fgets(version, sizeof(version), file);
+	fclose(file);
+
+	name = strstr(version, prefix);
+	if (!name)
+		return NULL;
+	name += strlen(prefix);
+	tmp = strchr(name, ' ');
+	if (tmp)
+		*tmp = '\0';
+
+	return strdup(name);
+}
+
+static int machine__set_modules_path(struct machine *self)
+{
+	char *version;
 	char modules_path[PATH_MAX];
 
-	if (uname(&uts) < 0)
+	version = get_kernel_version(self->root_dir);
+	if (!version)
 		return -1;
 
-	snprintf(modules_path, sizeof(modules_path), "/lib/modules/%s/kernel",
-		 uts.release);
+	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
+		 self->root_dir, version);
+	free(version);
 
-	return map_groups__set_modules_path_dir(self, modules_path);
+	return map_groups__set_modules_path_dir(&self->kmaps, modules_path);
 }
 
 /*
@@ -1470,8 +1552,8 @@
  */
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 {
-	struct map *self = zalloc(sizeof(*self) +
-				  (dso->kernel ? sizeof(struct kmap) : 0));
+	struct map *self = calloc(1, (sizeof(*self) +
+				      (dso->kernel ? sizeof(struct kmap) : 0)));
 	if (self != NULL) {
 		/*
 		 * ->end will be filled after we load all the symbols
@@ -1482,11 +1564,11 @@
 	return self;
 }
 
-struct map *map_groups__new_module(struct map_groups *self, u64 start,
-				   const char *filename)
+struct map *machine__new_module(struct machine *self, u64 start,
+				const char *filename)
 {
 	struct map *map;
-	struct dso *dso = __dsos__findnew(&dsos__kernel, filename);
+	struct dso *dso = __dsos__findnew(&self->kernel_dsos, filename);
 
 	if (dso == NULL)
 		return NULL;
@@ -1495,18 +1577,31 @@
 	if (map == NULL)
 		return NULL;
 
-	dso->origin = DSO__ORIG_KMODULE;
-	map_groups__insert(self, map);
+	if (machine__is_host(self))
+		dso->origin = DSO__ORIG_KMODULE;
+	else
+		dso->origin = DSO__ORIG_GUEST_KMODULE;
+	map_groups__insert(&self->kmaps, map);
 	return map;
 }
 
-static int map_groups__create_modules(struct map_groups *self)
+static int machine__create_modules(struct machine *self)
 {
 	char *line = NULL;
 	size_t n;
-	FILE *file = fopen("/proc/modules", "r");
+	FILE *file;
 	struct map *map;
+	const char *modules;
+	char path[PATH_MAX];
 
+	if (machine__is_default_guest(self))
+		modules = symbol_conf.default_guest_modules;
+	else {
+		sprintf(path, "%s/proc/modules", self->root_dir);
+		modules = path;
+	}
+
+	file = fopen(modules, "r");
 	if (file == NULL)
 		return -1;
 
@@ -1538,16 +1633,16 @@
 		*sep = '\0';
 
 		snprintf(name, sizeof(name), "[%s]", line);
-		map = map_groups__new_module(self, start, name);
+		map = machine__new_module(self, start, name);
 		if (map == NULL)
 			goto out_delete_line;
-		dso__kernel_module_get_build_id(map->dso);
+		dso__kernel_module_get_build_id(map->dso, self->root_dir);
 	}
 
 	free(line);
 	fclose(file);
 
-	return map_groups__set_modules_path(self);
+	return machine__set_modules_path(self);
 
 out_delete_line:
 	free(line);
@@ -1714,8 +1809,56 @@
 	return err;
 }
 
-LIST_HEAD(dsos__user);
-LIST_HEAD(dsos__kernel);
+static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
+				symbol_filter_t filter)
+{
+	int err;
+	const char *kallsyms_filename = NULL;
+	struct machine *machine;
+	char path[PATH_MAX];
+
+	if (!map->groups) {
+		pr_debug("Guest kernel map hasn't the point to groups\n");
+		return -1;
+	}
+	machine = map->groups->machine;
+
+	if (machine__is_default_guest(machine)) {
+		/*
+		 * if the user specified a vmlinux filename, use it and only
+		 * it, reporting errors to the user if it cannot be used.
+		 * Or use file guest_kallsyms inputted by user on commandline
+		 */
+		if (symbol_conf.default_guest_vmlinux_name != NULL) {
+			err = dso__load_vmlinux(self, map,
+				symbol_conf.default_guest_vmlinux_name, filter);
+			goto out_try_fixup;
+		}
+
+		kallsyms_filename = symbol_conf.default_guest_kallsyms;
+		if (!kallsyms_filename)
+			return -1;
+	} else {
+		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+		kallsyms_filename = path;
+	}
+
+	err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+	if (err > 0)
+		pr_debug("Using %s for symbols\n", kallsyms_filename);
+
+out_try_fixup:
+	if (err > 0) {
+		if (kallsyms_filename != NULL) {
+			machine__mmap_name(machine, path, sizeof(path));
+			dso__set_long_name(self, strdup(path));
+		}
+		map__fixup_start(map);
+		map__fixup_end(map);
+	}
+
+	return err;
+}
 
 static void dsos__add(struct list_head *head, struct dso *dso)
 {
@@ -1747,21 +1890,32 @@
 	return dso;
 }
 
-static void __dsos__fprintf(struct list_head *head, FILE *fp)
+size_t __dsos__fprintf(struct list_head *head, FILE *fp)
 {
 	struct dso *pos;
+	size_t ret = 0;
 
 	list_for_each_entry(pos, head, node) {
 		int i;
 		for (i = 0; i < MAP__NR_TYPES; ++i)
-			dso__fprintf(pos, i, fp);
+			ret += dso__fprintf(pos, i, fp);
 	}
+
+	return ret;
 }
 
-void dsos__fprintf(FILE *fp)
+size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp)
 {
-	__dsos__fprintf(&dsos__kernel, fp);
-	__dsos__fprintf(&dsos__user, fp);
+	struct rb_node *nd;
+	size_t ret = 0;
+
+	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
+		ret += __dsos__fprintf(&pos->user_dsos, fp);
+	}
+
+	return ret;
 }
 
 static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
@@ -1779,10 +1933,17 @@
 	return ret;
 }
 
-size_t dsos__fprintf_buildid(FILE *fp, bool with_hits)
+size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits)
 {
-	return (__dsos__fprintf_buildid(&dsos__kernel, fp, with_hits) +
-		__dsos__fprintf_buildid(&dsos__user, fp, with_hits));
+	struct rb_node *nd;
+	size_t ret = 0;
+
+	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret += __dsos__fprintf_buildid(&pos->kernel_dsos, fp, with_hits);
+		ret += __dsos__fprintf_buildid(&pos->user_dsos, fp, with_hits);
+	}
+	return ret;
 }
 
 struct dso *dso__new_kernel(const char *name)
@@ -1791,55 +1952,98 @@
 
 	if (self != NULL) {
 		dso__set_short_name(self, "[kernel]");
-		self->kernel	 = 1;
+		self->kernel = DSO_TYPE_KERNEL;
 	}
 
 	return self;
 }
 
-void dso__read_running_kernel_build_id(struct dso *self)
+static struct dso *dso__new_guest_kernel(struct machine *machine,
+					const char *name)
 {
-	if (sysfs__read_build_id("/sys/kernel/notes", self->build_id,
+	char bf[PATH_MAX];
+	struct dso *self = dso__new(name ?: machine__mmap_name(machine, bf, sizeof(bf)));
+
+	if (self != NULL) {
+		dso__set_short_name(self, "[guest.kernel]");
+		self->kernel = DSO_TYPE_GUEST_KERNEL;
+	}
+
+	return self;
+}
+
+void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine)
+{
+	char path[PATH_MAX];
+
+	if (machine__is_default_guest(machine))
+		return;
+	sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
+	if (sysfs__read_build_id(path, self->build_id,
 				 sizeof(self->build_id)) == 0)
 		self->has_build_id = true;
 }
 
-static struct dso *dsos__create_kernel(const char *vmlinux)
+static struct dso *machine__create_kernel(struct machine *self)
 {
-	struct dso *kernel = dso__new_kernel(vmlinux);
+	const char *vmlinux_name = NULL;
+	struct dso *kernel;
 
-	if (kernel != NULL) {
-		dso__read_running_kernel_build_id(kernel);
-		dsos__add(&dsos__kernel, kernel);
+	if (machine__is_host(self)) {
+		vmlinux_name = symbol_conf.vmlinux_name;
+		kernel = dso__new_kernel(vmlinux_name);
+	} else {
+		if (machine__is_default_guest(self))
+			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
+		kernel = dso__new_guest_kernel(self, vmlinux_name);
 	}
 
+	if (kernel != NULL) {
+		dso__read_running_kernel_build_id(kernel, self);
+		dsos__add(&self->kernel_dsos, kernel);
+	}
 	return kernel;
 }
 
-int __map_groups__create_kernel_maps(struct map_groups *self,
-				     struct map *vmlinux_maps[MAP__NR_TYPES],
-				     struct dso *kernel)
+int __machine__create_kernel_maps(struct machine *self, struct dso *kernel)
 {
 	enum map_type type;
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
 
-		vmlinux_maps[type] = map__new2(0, kernel, type);
-		if (vmlinux_maps[type] == NULL)
+		self->vmlinux_maps[type] = map__new2(0, kernel, type);
+		if (self->vmlinux_maps[type] == NULL)
 			return -1;
 
-		vmlinux_maps[type]->map_ip =
-			vmlinux_maps[type]->unmap_ip = identity__map_ip;
+		self->vmlinux_maps[type]->map_ip =
+			self->vmlinux_maps[type]->unmap_ip = identity__map_ip;
 
-		kmap = map__kmap(vmlinux_maps[type]);
-		kmap->kmaps = self;
-		map_groups__insert(self, vmlinux_maps[type]);
+		kmap = map__kmap(self->vmlinux_maps[type]);
+		kmap->kmaps = &self->kmaps;
+		map_groups__insert(&self->kmaps, self->vmlinux_maps[type]);
 	}
 
 	return 0;
 }
 
+int machine__create_kernel_maps(struct machine *self)
+{
+	struct dso *kernel = machine__create_kernel(self);
+
+	if (kernel == NULL ||
+	    __machine__create_kernel_maps(self, kernel) < 0)
+		return -1;
+
+	if (symbol_conf.use_modules && machine__create_modules(self) < 0)
+		pr_debug("Problems creating module maps, continuing anyway...\n");
+	/*
+	 * Now that we have all the maps created, just set the ->end of them:
+	 */
+	map_groups__fixup_end(&self->kmaps);
+	return 0;
+}
+
 static void vmlinux_path__exit(void)
 {
 	while (--vmlinux_path__nr_entries >= 0) {
@@ -1895,6 +2099,17 @@
 	return -1;
 }
 
+size_t vmlinux_path__fprintf(FILE *fp)
+{
+	int i;
+	size_t printed = 0;
+
+	for (i = 0; i < vmlinux_path__nr_entries; ++i)
+		printed += fprintf(fp, "[%d] %s\n", i, vmlinux_path[i]);
+
+	return printed;
+}
+
 static int setup_list(struct strlist **list, const char *list_str,
 		      const char *list_name)
 {
@@ -1945,22 +2160,129 @@
 	return -1;
 }
 
-int map_groups__create_kernel_maps(struct map_groups *self,
-				   struct map *vmlinux_maps[MAP__NR_TYPES])
+int machines__create_kernel_maps(struct rb_root *self, pid_t pid)
 {
-	struct dso *kernel = dsos__create_kernel(symbol_conf.vmlinux_name);
+	struct machine *machine = machines__findnew(self, pid);
 
-	if (kernel == NULL)
+	if (machine == NULL)
 		return -1;
 
-	if (__map_groups__create_kernel_maps(self, vmlinux_maps, kernel) < 0)
-		return -1;
+	return machine__create_kernel_maps(machine);
+}
 
-	if (symbol_conf.use_modules && map_groups__create_modules(self) < 0)
-		pr_debug("Problems creating module maps, continuing anyway...\n");
-	/*
-	 * Now that we have all the maps created, just set the ->end of them:
-	 */
-	map_groups__fixup_end(self);
-	return 0;
+static int hex(char ch)
+{
+	if ((ch >= '0') && (ch <= '9'))
+		return ch - '0';
+	if ((ch >= 'a') && (ch <= 'f'))
+		return ch - 'a' + 10;
+	if ((ch >= 'A') && (ch <= 'F'))
+		return ch - 'A' + 10;
+	return -1;
+}
+
+/*
+ * While we find nice hex chars, build a long_val.
+ * Return number of chars processed.
+ */
+int hex2u64(const char *ptr, u64 *long_val)
+{
+	const char *p = ptr;
+	*long_val = 0;
+
+	while (*p) {
+		const int hex_val = hex(*p);
+
+		if (hex_val < 0)
+			break;
+
+		*long_val = (*long_val << 4) | hex_val;
+		p++;
+	}
+
+	return p - ptr;
+}
+
+char *strxfrchar(char *s, char from, char to)
+{
+	char *p = s;
+
+	while ((p = strchr(p, from)) != NULL)
+		*p++ = to;
+
+	return s;
+}
+
+int machines__create_guest_kernel_maps(struct rb_root *self)
+{
+	int ret = 0;
+	struct dirent **namelist = NULL;
+	int i, items = 0;
+	char path[PATH_MAX];
+	pid_t pid;
+
+	if (symbol_conf.default_guest_vmlinux_name ||
+	    symbol_conf.default_guest_modules ||
+	    symbol_conf.default_guest_kallsyms) {
+		machines__create_kernel_maps(self, DEFAULT_GUEST_KERNEL_ID);
+	}
+
+	if (symbol_conf.guestmount) {
+		items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL);
+		if (items <= 0)
+			return -ENOENT;
+		for (i = 0; i < items; i++) {
+			if (!isdigit(namelist[i]->d_name[0])) {
+				/* Filter out . and .. */
+				continue;
+			}
+			pid = atoi(namelist[i]->d_name);
+			sprintf(path, "%s/%s/proc/kallsyms",
+				symbol_conf.guestmount,
+				namelist[i]->d_name);
+			ret = access(path, R_OK);
+			if (ret) {
+				pr_debug("Can't access file %s\n", path);
+				goto failure;
+			}
+			machines__create_kernel_maps(self, pid);
+		}
+failure:
+		free(namelist);
+	}
+
+	return ret;
+}
+
+int machine__load_kallsyms(struct machine *self, const char *filename,
+			   enum map_type type, symbol_filter_t filter)
+{
+	struct map *map = self->vmlinux_maps[type];
+	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
+
+	if (ret > 0) {
+		dso__set_loaded(map->dso, type);
+		/*
+		 * Since /proc/kallsyms will have multiple sessions for the
+		 * kernel, with modules between them, fixup the end of all
+		 * sections.
+		 */
+		__map_groups__fixup_end(&self->kmaps, type);
+	}
+
+	return ret;
+}
+
+int machine__load_vmlinux_path(struct machine *self, enum map_type type,
+			       symbol_filter_t filter)
+{
+	struct map *map = self->vmlinux_maps[type];
+	int ret = dso__load_vmlinux_path(map->dso, map, filter);
+
+	if (ret > 0) {
+		dso__set_loaded(map->dso, type);
+		map__reloc_vmlinux(map);
+	}
+
+	return ret;
 }

tools/perf/util/symbol.h

diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f30a374..032469e 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -3,10 +3,11 @@
 
 #include <linux/types.h>
 #include <stdbool.h>
-#include "types.h"
+#include <stdint.h>
+#include "map.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
-#include "event.h"
+#include <stdio.h>
 
 #define DEBUG_CACHE_DIR ".debug"
 
@@ -29,6 +30,9 @@
 #endif
 #endif
 
+int hex2u64(const char *ptr, u64 *val);
+char *strxfrchar(char *s, char from, char to);
+
 /*
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
  * for newer versions we can use mmap to reduce memory usage:
@@ -44,10 +48,13 @@
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
 
+#define BUILD_ID_SIZE 20
+
 struct symbol {
 	struct rb_node	rb_node;
 	u64		start;
 	u64		end;
+	u16		namelen;
 	char		name[0];
 };
 
@@ -63,10 +70,15 @@
 			show_nr_samples,
 			use_callchain,
 			exclude_other,
-			full_paths;
+			full_paths,
+			show_cpu_utilization;
 	const char	*vmlinux_name,
 			*field_sep;
-	char            *dso_list_str,
+	const char	*default_guest_vmlinux_name,
+			*default_guest_kallsyms,
+			*default_guest_modules;
+	const char	*guestmount;
+	const char	*dso_list_str,
 			*comm_list_str,
 			*sym_list_str,
 			*col_width_list_str;
@@ -88,6 +100,11 @@
 	u64		unrelocated_addr;
 };
 
+struct map_symbol {
+	struct map    *map;
+	struct symbol *sym;
+};
+
 struct addr_location {
 	struct thread *thread;
 	struct map    *map;
@@ -95,6 +112,13 @@
 	u64	      addr;
 	char	      level;
 	bool	      filtered;
+	unsigned int  cpumode;
+};
+
+enum dso_kernel_type {
+	DSO_TYPE_USER = 0,
+	DSO_TYPE_KERNEL,
+	DSO_TYPE_GUEST_KERNEL
 };
 
 struct dso {
@@ -104,8 +128,9 @@
 	u8		 adjust_symbols:1;
 	u8		 slen_calculated:1;
 	u8		 has_build_id:1;
-	u8		 kernel:1;
+	enum dso_kernel_type	kernel;
 	u8		 hit:1;
+	u8		 annotate_warned:1;
 	unsigned char	 origin;
 	u8		 sorted_by_name;
 	u8		 loaded;
@@ -131,42 +156,65 @@
 
 void dso__sort_by_name(struct dso *self, enum map_type type);
 
-extern struct list_head dsos__user, dsos__kernel;
-
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 
-static inline struct dso *dsos__findnew(const char *name)
-{
-	return __dsos__findnew(&dsos__user, name);
-}
-
 int dso__load(struct dso *self, struct map *map, symbol_filter_t filter);
 int dso__load_vmlinux_path(struct dso *self, struct map *map,
 			   symbol_filter_t filter);
 int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map,
 		       symbol_filter_t filter);
-void dsos__fprintf(FILE *fp);
-size_t dsos__fprintf_buildid(FILE *fp, bool with_hits);
+int machine__load_kallsyms(struct machine *self, const char *filename,
+			   enum map_type type, symbol_filter_t filter);
+int machine__load_vmlinux_path(struct machine *self, enum map_type type,
+			       symbol_filter_t filter);
+
+size_t __dsos__fprintf(struct list_head *head, FILE *fp);
+
+size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp);
+size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits);
 
 size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
 size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
+
+enum dso_origin {
+	DSO__ORIG_KERNEL = 0,
+	DSO__ORIG_GUEST_KERNEL,
+	DSO__ORIG_JAVA_JIT,
+	DSO__ORIG_BUILD_ID_CACHE,
+	DSO__ORIG_FEDORA,
+	DSO__ORIG_UBUNTU,
+	DSO__ORIG_BUILDID,
+	DSO__ORIG_DSO,
+	DSO__ORIG_GUEST_KMODULE,
+	DSO__ORIG_KMODULE,
+	DSO__ORIG_NOT_FOUND,
+};
+
 char dso__symtab_origin(const struct dso *self);
 void dso__set_long_name(struct dso *self, char *name);
 void dso__set_build_id(struct dso *self, void *build_id);
-void dso__read_running_kernel_build_id(struct dso *self);
+void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine);
 struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
 					const char *name);
 
 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);
-bool dsos__read_build_ids(bool with_hits);
+bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 int build_id__sprintf(const u8 *self, int len, char *bf);
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start));
 
+int __machine__create_kernel_maps(struct machine *self, struct dso *kernel);
+int machine__create_kernel_maps(struct machine *self);
+
+int machines__create_kernel_maps(struct rb_root *self, pid_t pid);
+int machines__create_guest_kernel_maps(struct rb_root *self);
+
 int symbol__init(void);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
+size_t vmlinux_path__fprintf(FILE *fp);
+
 #endif /* __PERF_SYMBOL */

tools/perf/util/thread.c

diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index fa96831..1f7ecd4 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,13 +7,35 @@
 #include "util.h"
 #include "debug.h"
 
-void map_groups__init(struct map_groups *self)
+int find_all_tid(int pid, pid_t ** all_tid)
 {
+	char name[256];
+	int items;
+	struct dirent **namelist = NULL;
+	int ret = 0;
 	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		self->maps[i] = RB_ROOT;
-		INIT_LIST_HEAD(&self->removed_maps[i]);
+
+	sprintf(name, "/proc/%d/task", pid);
+	items = scandir(name, &namelist, NULL, NULL);
+	if (items <= 0)
+                return -ENOENT;
+	*all_tid = malloc(sizeof(pid_t) * items);
+	if (!*all_tid) {
+		ret = -ENOMEM;
+		goto failure;
 	}
+
+	for (i = 0; i < items; i++)
+		(*all_tid)[i] = atoi(namelist[i]->d_name);
+
+	ret = items;
+
+failure:
+	for (i=0; i<items; i++)
+		free(namelist[i]);
+	free(namelist);
+
+	return ret;
 }
 
 static struct thread *thread__new(pid_t pid)
@@ -31,28 +53,6 @@
 	return self;
 }
 
-static void map_groups__flush(struct map_groups *self)
-{
-	int type;
-
-	for (type = 0; type < MAP__NR_TYPES; type++) {
-		struct rb_root *root = &self->maps[type];
-		struct rb_node *next = rb_first(root);
-
-		while (next) {
-			struct map *pos = rb_entry(next, struct map, rb_node);
-			next = rb_next(&pos->rb_node);
-			rb_erase(&pos->rb_node, root);
-			/*
-			 * We may have references to this map, for
-			 * instance in some hist_entry instances, so
-			 * just move them to a separate list.
-			 */
-			list_add_tail(&pos->node, &self->removed_maps[pos->type]);
-		}
-	}
-}
-
 int thread__set_comm(struct thread *self, const char *comm)
 {
 	int err;
@@ -79,69 +79,10 @@
 	return self->comm_len;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *self,
-				  enum map_type type, FILE *fp)
-{
-	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
-	struct rb_node *nd;
-
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos, fp);
-		if (verbose > 2) {
-			printed += dso__fprintf(pos->dso, type, fp);
-			printed += fprintf(fp, "--\n");
-		}
-	}
-
-	return printed;
-}
-
-size_t map_groups__fprintf_maps(struct map_groups *self, FILE *fp)
-{
-	size_t printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(self, i, fp);
-	return printed;
-}
-
-static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
-						 enum map_type type, FILE *fp)
-{
-	struct map *pos;
-	size_t printed = 0;
-
-	list_for_each_entry(pos, &self->removed_maps[type], node) {
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos, fp);
-		if (verbose > 1) {
-			printed += dso__fprintf(pos->dso, type, fp);
-			printed += fprintf(fp, "--\n");
-		}
-	}
-	return printed;
-}
-
-static size_t map_groups__fprintf_removed_maps(struct map_groups *self, FILE *fp)
-{
-	size_t printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_removed_maps(self, i, fp);
-	return printed;
-}
-
-static size_t map_groups__fprintf(struct map_groups *self, FILE *fp)
-{
-	size_t printed = map_groups__fprintf_maps(self, fp);
-	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(self, fp);
-}
-
 static size_t thread__fprintf(struct thread *self, FILE *fp)
 {
 	return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) +
-	       map_groups__fprintf(&self->mg, fp);
+	       map_groups__fprintf(&self->mg, verbose, fp);
 }
 
 struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
@@ -183,127 +124,12 @@
 	return th;
 }
 
-static int map_groups__fixup_overlappings(struct map_groups *self,
-					  struct map *map)
-{
-	struct rb_root *root = &self->maps[map->type];
-	struct rb_node *next = rb_first(root);
-
-	while (next) {
-		struct map *pos = rb_entry(next, struct map, rb_node);
-		next = rb_next(&pos->rb_node);
-
-		if (!map__overlap(pos, map))
-			continue;
-
-		if (verbose >= 2) {
-			fputs("overlapping maps:\n", stderr);
-			map__fprintf(map, stderr);
-			map__fprintf(pos, stderr);
-		}
-
-		rb_erase(&pos->rb_node, root);
-		/*
-		 * We may have references to this map, for instance in some
-		 * hist_entry instances, so just move them to a separate
-		 * list.
-		 */
-		list_add_tail(&pos->node, &self->removed_maps[map->type]);
-		/*
-		 * Now check if we need to create new maps for areas not
-		 * overlapped by the new map:
-		 */
-		if (map->start > pos->start) {
-			struct map *before = map__clone(pos);
-
-			if (before == NULL)
-				return -ENOMEM;
-
-			before->end = map->start - 1;
-			map_groups__insert(self, before);
-			if (verbose >= 2)
-				map__fprintf(before, stderr);
-		}
-
-		if (map->end < pos->end) {
-			struct map *after = map__clone(pos);
-
-			if (after == NULL)
-				return -ENOMEM;
-
-			after->start = map->end + 1;
-			map_groups__insert(self, after);
-			if (verbose >= 2)
-				map__fprintf(after, stderr);
-		}
-	}
-
-	return 0;
-}
-
-void maps__insert(struct rb_root *maps, struct map *map)
-{
-	struct rb_node **p = &maps->rb_node;
-	struct rb_node *parent = NULL;
-	const u64 ip = map->start;
-	struct map *m;
-
-	while (*p != NULL) {
-		parent = *p;
-		m = rb_entry(parent, struct map, rb_node);
-		if (ip < m->start)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&map->rb_node, parent, p);
-	rb_insert_color(&map->rb_node, maps);
-}
-
-struct map *maps__find(struct rb_root *maps, u64 ip)
-{
-	struct rb_node **p = &maps->rb_node;
-	struct rb_node *parent = NULL;
-	struct map *m;
-
-	while (*p != NULL) {
-		parent = *p;
-		m = rb_entry(parent, struct map, rb_node);
-		if (ip < m->start)
-			p = &(*p)->rb_left;
-		else if (ip > m->end)
-			p = &(*p)->rb_right;
-		else
-			return m;
-	}
-
-	return NULL;
-}
-
 void thread__insert_map(struct thread *self, struct map *map)
 {
-	map_groups__fixup_overlappings(&self->mg, map);
+	map_groups__fixup_overlappings(&self->mg, map, verbose, stderr);
 	map_groups__insert(&self->mg, map);
 }
 
-/*
- * XXX This should not really _copy_ te maps, but refcount them.
- */
-static int map_groups__clone(struct map_groups *self,
-			     struct map_groups *parent, enum map_type type)
-{
-	struct rb_node *nd;
-	for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
-		struct map *new = map__clone(map);
-		if (new == NULL)
-			return -ENOMEM;
-		map_groups__insert(self, new);
-	}
-	return 0;
-}
-
 int thread__fork(struct thread *self, struct thread *parent)
 {
 	int i;
@@ -336,15 +162,3 @@
 
 	return ret;
 }
-
-struct symbol *map_groups__find_symbol(struct map_groups *self,
-				       enum map_type type, u64 addr,
-				       symbol_filter_t filter)
-{
-	struct map *map = map_groups__find(self, type, addr);
-
-	if (map != NULL)
-		return map__find_symbol(map, map->map_ip(map, addr), filter);
-
-	return NULL;
-}

tools/perf/util/thread.h

diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index dcf7030..1dfd9ff 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -5,14 +5,6 @@
 #include <unistd.h>
 #include "symbol.h"
 
-struct map_groups {
-	struct rb_root		maps[MAP__NR_TYPES];
-	struct list_head	removed_maps[MAP__NR_TYPES];
-};
-
-size_t __map_groups__fprintf_maps(struct map_groups *self,
-				  enum map_type type, FILE *fp);
-
 struct thread {
 	struct rb_node		rb_node;
 	struct map_groups	mg;
@@ -23,29 +15,16 @@
 	int			comm_len;
 };
 
-void map_groups__init(struct map_groups *self);
+struct perf_session;
+
+int find_all_tid(int pid, pid_t ** all_tid);
 int thread__set_comm(struct thread *self, const char *comm);
 int thread__comm_len(struct thread *self);
 struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
 void thread__insert_map(struct thread *self, struct map *map);
 int thread__fork(struct thread *self, struct thread *parent);
-size_t map_groups__fprintf_maps(struct map_groups *self, FILE *fp);
 size_t perf_session__fprintf(struct perf_session *self, FILE *fp);
 
-void maps__insert(struct rb_root *maps, struct map *map);
-struct map *maps__find(struct rb_root *maps, u64 addr);
-
-static inline void map_groups__insert(struct map_groups *self, struct map *map)
-{
-	 maps__insert(&self->maps[map->type], map);
-}
-
-static inline struct map *map_groups__find(struct map_groups *self,
-					   enum map_type type, u64 addr)
-{
-	return maps__find(&self->maps[type], addr);
-}
-
 static inline struct map *thread__find_map(struct thread *self,
 					   enum map_type type, u64 addr)
 {
@@ -54,34 +33,12 @@
 
 void thread__find_addr_map(struct thread *self,
 			   struct perf_session *session, u8 cpumode,
-			   enum map_type type, u64 addr,
+			   enum map_type type, pid_t pid, u64 addr,
 			   struct addr_location *al);
 
 void thread__find_addr_location(struct thread *self,
 				struct perf_session *session, u8 cpumode,
-				enum map_type type, u64 addr,
+				enum map_type type, pid_t pid, u64 addr,
 				struct addr_location *al,
 				symbol_filter_t filter);
-struct symbol *map_groups__find_symbol(struct map_groups *self,
-				       enum map_type type, u64 addr,
-				       symbol_filter_t filter);
-
-static inline struct symbol *map_groups__find_function(struct map_groups *self,
-						       u64 addr,
-						       symbol_filter_t filter)
-{
-	return map_groups__find_symbol(self, MAP__FUNCTION, addr, filter);
-}
-
-struct map *map_groups__find_by_name(struct map_groups *self,
-				     enum map_type type, const char *name);
-
-int __map_groups__create_kernel_maps(struct map_groups *self,
-				     struct map *vmlinux_maps[MAP__NR_TYPES],
-				     struct dso *kernel);
-int map_groups__create_kernel_maps(struct map_groups *self,
-				   struct map *vmlinux_maps[MAP__NR_TYPES]);
-
-struct map *map_groups__new_module(struct map_groups *self, u64 start,
-				   const char *filename);
 #endif	/* __PERF_THREAD_H */

tools/perf/util/trace-event-info.c

diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 5ea8973..b157260 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -154,10 +154,17 @@
 	free(file);
 }
 
+static ssize_t calc_data_size;
+
 static ssize_t write_or_die(const void *buf, size_t len)
 {
 	int ret;
 
+	if (calc_data_size) {
+		calc_data_size += len;
+		return len;
+	}
+
 	ret = write(output_fd, buf, len);
 	if (ret < 0)
 		die("writing to '%s'", output_file);
@@ -480,6 +487,17 @@
 	return nr_tracepoints > 0 ? path.next : NULL;
 }
 
+bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events)
+{
+	int i;
+
+	for (i = 0; i < nb_events; i++)
+		if (pattrs[i].type == PERF_TYPE_TRACEPOINT)
+			return true;
+
+	return false;
+}
+
 int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
 {
 	char buf[BUFSIZ];
@@ -526,3 +544,20 @@
 
 	return 0;
 }
+
+ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
+			       int nb_events)
+{
+	ssize_t size;
+	int err = 0;
+
+	calc_data_size = 1;
+	err = read_tracing_data(fd, pattrs, nb_events);
+	size = calc_data_size - 1;
+	calc_data_size = 0;
+
+	if (err < 0)
+		return err;
+
+	return size;
+}

tools/perf/util/trace-event-parse.c

diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 9b3c20f..73a0222 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -37,10 +37,12 @@
 int header_page_ts_size;
 int header_page_size_offset;
 int header_page_size_size;
+int header_page_overwrite_offset;
+int header_page_overwrite_size;
 int header_page_data_offset;
 int header_page_data_size;
 
-int latency_format;
+bool latency_format;
 
 static char *input_buf;
 static unsigned long long input_buf_ptr;
@@ -628,23 +630,32 @@
 	return 0;
 }
 
-static int test_type_token(enum event_type type, char *token,
-		    enum event_type expect, const char *expect_tok)
+static int __test_type_token(enum event_type type, char *token,
+			     enum event_type expect, const char *expect_tok,
+			     bool warn)
 {
 	if (type != expect) {
-		warning("Error: expected type %d but read %d",
-		    expect, type);
+		if (warn)
+			warning("Error: expected type %d but read %d",
+				expect, type);
 		return -1;
 	}
 
 	if (strcmp(token, expect_tok) != 0) {
-		warning("Error: expected '%s' but read '%s'",
-		    expect_tok, token);
+		if (warn)
+			warning("Error: expected '%s' but read '%s'",
+				expect_tok, token);
 		return -1;
 	}
 	return 0;
 }
 
+static int test_type_token(enum event_type type, char *token,
+			   enum event_type expect, const char *expect_tok)
+{
+	return __test_type_token(type, token, expect, expect_tok, true);
+}
+
 static int __read_expect_type(enum event_type expect, char **tok, int newline_ok)
 {
 	enum event_type type;
@@ -661,7 +672,8 @@
 	return __read_expect_type(expect, tok, 1);
 }
 
-static int __read_expected(enum event_type expect, const char *str, int newline_ok)
+static int __read_expected(enum event_type expect, const char *str,
+			   int newline_ok, bool warn)
 {
 	enum event_type type;
 	char *token;
@@ -672,7 +684,7 @@
 	else
 		type = read_token_item(&token);
 
-	ret = test_type_token(type, token, expect, str);
+	ret = __test_type_token(type, token, expect, str, warn);
 
 	free_token(token);
 
@@ -681,12 +693,12 @@
 
 static int read_expected(enum event_type expect, const char *str)
 {
-	return __read_expected(expect, str, 1);
+	return __read_expected(expect, str, 1, true);
 }
 
 static int read_expected_item(enum event_type expect, const char *str)
 {
-	return __read_expected(expect, str, 0);
+	return __read_expected(expect, str, 0, true);
 }
 
 static char *event_read_name(void)
@@ -744,7 +756,7 @@
 
 static int field_is_dynamic(struct format_field *field)
 {
-	if (!strcmp(field->type, "__data_loc"))
+	if (!strncmp(field->type, "__data_loc", 10))
 		return 1;
 
 	return 0;
@@ -1925,7 +1937,7 @@
 	if (!field)
 		return NULL;
 
-	if (field->flags & FIELD_IS_STRING) {
+	if (field->flags & FIELD_IS_DYNAMIC) {
 		int offset;
 
 		offset = *(int *)(data + field->offset);
@@ -3087,88 +3099,6 @@
 	}
 }
 
-static void parse_header_field(const char *field,
-			       int *offset, int *size)
-{
-	char *token;
-	int type;
-
-	if (read_expected(EVENT_ITEM, "field") < 0)
-		return;
-	if (read_expected(EVENT_OP, ":") < 0)
-		return;
-
-	/* type */
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-	free_token(token);
-
-	if (read_expected(EVENT_ITEM, field) < 0)
-		return;
-	if (read_expected(EVENT_OP, ";") < 0)
-		return;
-	if (read_expected(EVENT_ITEM, "offset") < 0)
-		return;
-	if (read_expected(EVENT_OP, ":") < 0)
-		return;
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-	*offset = atoi(token);
-	free_token(token);
-	if (read_expected(EVENT_OP, ";") < 0)
-		return;
-	if (read_expected(EVENT_ITEM, "size") < 0)
-		return;
-	if (read_expected(EVENT_OP, ":") < 0)
-		return;
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-	*size = atoi(token);
-	free_token(token);
-	if (read_expected(EVENT_OP, ";") < 0)
-		return;
-	type = read_token(&token);
-	if (type != EVENT_NEWLINE) {
-		/* newer versions of the kernel have a "signed" type */
-		if (type != EVENT_ITEM)
-			goto fail;
-
-		if (strcmp(token, "signed") != 0)
-			goto fail;
-
-		free_token(token);
-
-		if (read_expected(EVENT_OP, ":") < 0)
-			return;
-
-		if (read_expect_type(EVENT_ITEM, &token))
-			goto fail;
-
-		free_token(token);
-		if (read_expected(EVENT_OP, ";") < 0)
-			return;
-
-		if (read_expect_type(EVENT_NEWLINE, &token))
-			goto fail;
-	}
- fail:
-	free_token(token);
-}
-
-int parse_header_page(char *buf, unsigned long size)
-{
-	init_input_buf(buf, size);
-
-	parse_header_field("timestamp", &header_page_ts_offset,
-			   &header_page_ts_size);
-	parse_header_field("commit", &header_page_size_offset,
-			   &header_page_size_size);
-	parse_header_field("data", &header_page_data_offset,
-			   &header_page_data_size);
-
-	return 0;
-}
-
 int parse_ftrace_file(char *buf, unsigned long size)
 {
 	struct format_field *field;

tools/perf/util/trace-event-read.c

diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 7cd1193..cb54cd0 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -50,14 +50,51 @@
 
 static unsigned long	page_size;
 
+static ssize_t calc_data_size;
+static bool repipe;
+
+/* If it fails, the next read will report it */
+static void skip(int size)
+{
+	lseek(input_fd, size, SEEK_CUR);
+}
+
+static int do_read(int fd, void *buf, int size)
+{
+	int rsize = size;
+
+	while (size) {
+		int ret = read(fd, buf, size);
+
+		if (ret <= 0)
+			return -1;
+
+		if (repipe) {
+			int retw = write(STDOUT_FILENO, buf, ret);
+
+			if (retw <= 0 || retw != ret)
+				die("repiping input file");
+		}
+
+		size -= ret;
+		buf += ret;
+	}
+
+	return rsize;
+}
+
 static int read_or_die(void *data, int size)
 {
 	int r;
 
-	r = read(input_fd, data, size);
-	if (r != size)
+	r = do_read(input_fd, data, size);
+	if (r <= 0)
 		die("reading input file (size expected=%d received=%d)",
 		    size, r);
+
+	if (calc_data_size)
+		calc_data_size += r;
+
 	return r;
 }
 
@@ -82,56 +119,35 @@
 	char buf[BUFSIZ];
 	char *str = NULL;
 	int size = 0;
-	int i;
 	off_t r;
+	char c;
 
 	for (;;) {
-		r = read(input_fd, buf, BUFSIZ);
+		r = read(input_fd, &c, 1);
 		if (r < 0)
 			die("reading input file");
 
 		if (!r)
 			die("no data");
 
-		for (i = 0; i < r; i++) {
-			if (!buf[i])
-				break;
+		if (repipe) {
+			int retw = write(STDOUT_FILENO, &c, 1);
+
+			if (retw <= 0 || retw != r)
+				die("repiping input file string");
 		}
-		if (i < r)
+
+		buf[size++] = c;
+
+		if (!c)
 			break;
-
-		if (str) {
-			size += BUFSIZ;
-			str = realloc(str, size);
-			if (!str)
-				die("malloc of size %d", size);
-			memcpy(str + (size - BUFSIZ), buf, BUFSIZ);
-		} else {
-			size = BUFSIZ;
-			str = malloc_or_die(size);
-			memcpy(str, buf, size);
-		}
 	}
 
-	/* trailing \0: */
-	i++;
+	if (calc_data_size)
+		calc_data_size += size;
 
-	/* move the file descriptor to the end of the string */
-	r = lseek(input_fd, -(r - i), SEEK_CUR);
-	if (r == (off_t)-1)
-		die("lseek");
-
-	if (str) {
-		size += i;
-		str = realloc(str, size);
-		if (!str)
-			die("malloc of size %d", size);
-		memcpy(str + (size - i), buf, i);
-	} else {
-		size = i;
-		str = malloc_or_die(i);
-		memcpy(str, buf, i);
-	}
+	str = malloc_or_die(size);
+	memcpy(str, buf, size);
 
 	return str;
 }
@@ -174,7 +190,6 @@
 static void read_header_files(void)
 {
 	unsigned long long size;
-	char *header_page;
 	char *header_event;
 	char buf[BUFSIZ];
 
@@ -184,10 +199,7 @@
 		die("did not read header page");
 
 	size = read8();
-	header_page = malloc_or_die(size);
-	read_or_die(header_page, size);
-	parse_header_page(header_page, size);
-	free(header_page);
+	skip(size);
 
 	/*
 	 * The size field in the page is of type long,
@@ -459,7 +471,7 @@
 	return data;
 }
 
-void trace_report(int fd)
+ssize_t trace_report(int fd, bool __repipe)
 {
 	char buf[BUFSIZ];
 	char test[] = { 23, 8, 68 };
@@ -467,6 +479,10 @@
 	int show_version = 0;
 	int show_funcs = 0;
 	int show_printk = 0;
+	ssize_t size;
+
+	calc_data_size = 1;
+	repipe = __repipe;
 
 	input_fd = fd;
 
@@ -499,14 +515,18 @@
 	read_proc_kallsyms();
 	read_ftrace_printk();
 
+	size = calc_data_size - 1;
+	calc_data_size = 0;
+	repipe = false;
+
 	if (show_funcs) {
 		print_funcs();
-		return;
+		return size;
 	}
 	if (show_printk) {
 		print_printk();
-		return;
+		return size;
 	}
 
-	return;
+	return size;
 }

tools/perf/util/trace-event.h

diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index c3269b9..406d452 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_TRACE_EVENTS_H
 #define __PERF_TRACE_EVENTS_H
 
+#include <stdbool.h>
 #include "parse-events.h"
 
 #define __unused __attribute__((unused))
@@ -162,7 +163,7 @@
 
 void parse_set_info(int nr_cpus, int long_sz);
 
-void trace_report(int fd);
+ssize_t trace_report(int fd, bool repipe);
 
 void *malloc_or_die(unsigned int size);
 
@@ -241,9 +242,8 @@
 extern int header_page_data_offset;
 extern int header_page_data_size;
 
-extern int latency_format;
+extern bool latency_format;
 
-int parse_header_page(char *buf, unsigned long size);
 int trace_parse_common_type(void *data);
 int trace_parse_common_pid(void *data);
 int parse_common_pc(void *data);
@@ -258,6 +258,8 @@
 unsigned long long eval_flag(const char *flag);
 
 int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events);
+ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
+			       int nb_events);
 
 /* taken from kernel/trace/trace.h */
 enum trace_flag_type {

tools/perf/util/util.c

diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index f9b890f..2142656 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -92,3 +92,25 @@
 out:
 	return err;
 }
+
+unsigned long convert_unit(unsigned long value, char *unit)
+{
+	*unit = ' ';
+
+	if (value > 1000) {
+		value /= 1000;
+		*unit = 'K';
+	}
+
+	if (value > 1000) {
+		value /= 1000;
+		*unit = 'M';
+	}
+
+	if (value > 1000) {
+		value /= 1000;
+		*unit = 'G';
+	}
+
+	return value;
+}

tools/perf/util/util.h

diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 0f5b2a6..0795bf30 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -42,12 +42,14 @@
 #define _ALL_SOURCE 1
 #define _GNU_SOURCE 1
 #define _BSD_SOURCE 1
+#define HAS_BOOL
 
 #include <unistd.h>
 #include <stdio.h>
 #include <sys/stat.h>
 #include <sys/statfs.h>
 #include <fcntl.h>
+#include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
 #include <stdarg.h>
@@ -78,6 +80,7 @@
 #include <pwd.h>
 #include <inttypes.h>
 #include "../../../include/linux/magic.h"
+#include "types.h"
 
 
 #ifndef NO_ICONV
@@ -295,6 +298,13 @@
 extern char *xstrndup(const char *str, size_t len);
 extern void *xrealloc(void *ptr, size_t size) __attribute__((weak));
 
+static inline void *xzalloc(size_t size)
+{
+	void *buf = xmalloc(size);
+
+	return memset(buf, 0, size);
+}
+
 static inline void *zalloc(size_t size)
 {
 	return calloc(1, size);
@@ -309,6 +319,7 @@
 {
 	size_t len = strlen(filename);
 	size_t extlen = strlen(ext);
+
 	return len > extlen && !memcmp(filename + len - extlen, ext, extlen);
 }
 
@@ -322,6 +333,7 @@
 #undef isalnum
 #undef tolower
 #undef toupper
+
 extern unsigned char sane_ctype[256];
 #define GIT_SPACE		0x01
 #define GIT_DIGIT		0x02
@@ -406,4 +418,14 @@
 int mkdir_p(char *path, mode_t mode);
 int copyfile(const char *from, const char *to);
 
+s64 perf_atoll(const char *str);
+char **argv_split(const char *str, int *argcp);
+void argv_free(char **argv);
+bool strglobmatch(const char *str, const char *pat);
+bool strlazymatch(const char *str, const char *pat);
+unsigned long convert_unit(unsigned long value, char *unit);
+
+#define _STR(x) #x
+#define STR(x) _STR(x)
+
 #endif

virt/kvm/ioapic.c

diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 03a5eb2..7c79c1d 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -197,7 +197,7 @@
 	union kvm_ioapic_redirect_entry entry;
 	int ret = 1;
 
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
 		entry = ioapic->redirtbl[irq];
 		level ^= entry.fields.polarity;
@@ -214,7 +214,7 @@
 		}
 		trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
 	}
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 
 	return ret;
 }
@@ -238,9 +238,9 @@
 		 * is dropped it will be put into irr and will be delivered
 		 * after ack notifier returns.
 		 */
-		mutex_unlock(&ioapic->lock);
+		spin_unlock(&ioapic->lock);
 		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
-		mutex_lock(&ioapic->lock);
+		spin_lock(&ioapic->lock);
 
 		if (trigger_mode != IOAPIC_LEVEL_TRIG)
 			continue;
@@ -259,9 +259,9 @@
 	smp_rmb();
 	if (!test_bit(vector, ioapic->handled_vectors))
 		return;
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	__kvm_ioapic_update_eoi(ioapic, vector, trigger_mode);
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 }
 
 static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
@@ -287,7 +287,7 @@
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
 	addr &= 0xff;
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	switch (addr) {
 	case IOAPIC_REG_SELECT:
 		result = ioapic->ioregsel;
@@ -301,7 +301,7 @@
 		result = 0;
 		break;
 	}
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 
 	switch (len) {
 	case 8:
@@ -338,7 +338,7 @@
 	}
 
 	addr &= 0xff;
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	switch (addr) {
 	case IOAPIC_REG_SELECT:
 		ioapic->ioregsel = data;
@@ -356,7 +356,7 @@
 	default:
 		break;
 	}
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 	return 0;
 }
 
@@ -386,7 +386,7 @@
 	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
 	if (!ioapic)
 		return -ENOMEM;
-	mutex_init(&ioapic->lock);
+	spin_lock_init(&ioapic->lock);
 	kvm->arch.vioapic = ioapic;
 	kvm_ioapic_reset(ioapic);
 	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
@@ -419,9 +419,9 @@
 	if (!ioapic)
 		return -EINVAL;
 
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	memcpy(state, ioapic, sizeof(struct kvm_ioapic_state));
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 	return 0;
 }
 
@@ -431,9 +431,9 @@
 	if (!ioapic)
 		return -EINVAL;
 
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
 	update_handled_vectors(ioapic);
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 	return 0;
 }

virt/kvm/ioapic.h

diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 8a751b7..0b190c3 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -45,7 +45,7 @@
 	struct kvm_io_device dev;
 	struct kvm *kvm;
 	void (*ack_notifier)(void *opaque, int irq);
-	struct mutex lock;
+	spinlock_t lock;
 	DECLARE_BITMAP(handled_vectors, 256);
 };
 

virt/kvm/iommu.c

diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 80fd3ad..11692b9 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -32,12 +32,30 @@
 static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages);
 
+static pfn_t kvm_pin_pages(struct kvm *kvm, struct kvm_memory_slot *slot,
+			   gfn_t gfn, unsigned long size)
+{
+	gfn_t end_gfn;
+	pfn_t pfn;
+
+	pfn     = gfn_to_pfn_memslot(kvm, slot, gfn);
+	end_gfn = gfn + (size >> PAGE_SHIFT);
+	gfn    += 1;
+
+	if (is_error_pfn(pfn))
+		return pfn;
+
+	while (gfn < end_gfn)
+		gfn_to_pfn_memslot(kvm, slot, gfn++);
+
+	return pfn;
+}
+
 int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
-	gfn_t gfn = slot->base_gfn;
-	unsigned long npages = slot->npages;
+	gfn_t gfn, end_gfn;
 	pfn_t pfn;
-	int i, r = 0;
+	int r = 0;
 	struct iommu_domain *domain = kvm->arch.iommu_domain;
 	int flags;
 
@@ -45,31 +63,62 @@
 	if (!domain)
 		return 0;
 
+	gfn     = slot->base_gfn;
+	end_gfn = gfn + slot->npages;
+
 	flags = IOMMU_READ | IOMMU_WRITE;
 	if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)
 		flags |= IOMMU_CACHE;
 
-	for (i = 0; i < npages; i++) {
-		/* check if already mapped */
-		if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn)))
-			continue;
 
-		pfn = gfn_to_pfn_memslot(kvm, slot, gfn);
-		r = iommu_map_range(domain,
-				    gfn_to_gpa(gfn),
-				    pfn_to_hpa(pfn),
-				    PAGE_SIZE, flags);
+	while (gfn < end_gfn) {
+		unsigned long page_size;
+
+		/* Check if already mapped */
+		if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) {
+			gfn += 1;
+			continue;
+		}
+
+		/* Get the page size we could use to map */
+		page_size = kvm_host_page_size(kvm, gfn);
+
+		/* Make sure the page_size does not exceed the memslot */
+		while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn)
+			page_size >>= 1;
+
+		/* Make sure gfn is aligned to the page size we want to map */
+		while ((gfn << PAGE_SHIFT) & (page_size - 1))
+			page_size >>= 1;
+
+		/*
+		 * Pin all pages we are about to map in memory. This is
+		 * important because we unmap and unpin in 4kb steps later.
+		 */
+		pfn = kvm_pin_pages(kvm, slot, gfn, page_size);
+		if (is_error_pfn(pfn)) {
+			gfn += 1;
+			continue;
+		}
+
+		/* Map into IO address space */
+		r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn),
+			      get_order(page_size), flags);
 		if (r) {
 			printk(KERN_ERR "kvm_iommu_map_address:"
 			       "iommu failed to map pfn=%lx\n", pfn);
 			goto unmap_pages;
 		}
-		gfn++;
+
+		gfn += page_size >> PAGE_SHIFT;
+
+
 	}
+
 	return 0;
 
 unmap_pages:
-	kvm_iommu_put_pages(kvm, slot->base_gfn, i);
+	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
 	return r;
 }
 
@@ -189,27 +238,47 @@
 	return r;
 }
 
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+	unsigned long i;
+
+	for (i = 0; i < npages; ++i)
+		kvm_release_pfn_clean(pfn + i);
+}
+
 static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages)
 {
-	gfn_t gfn = base_gfn;
+	struct iommu_domain *domain;
+	gfn_t end_gfn, gfn;
 	pfn_t pfn;
-	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	unsigned long i;
 	u64 phys;
 
+	domain  = kvm->arch.iommu_domain;
+	end_gfn = base_gfn + npages;
+	gfn     = base_gfn;
+
 	/* check if iommu exists and in use */
 	if (!domain)
 		return;
 
-	for (i = 0; i < npages; i++) {
-		phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
-		pfn = phys >> PAGE_SHIFT;
-		kvm_release_pfn_clean(pfn);
-		gfn++;
-	}
+	while (gfn < end_gfn) {
+		unsigned long unmap_pages;
+		int order;
 
-	iommu_unmap_range(domain, gfn_to_gpa(base_gfn), PAGE_SIZE * npages);
+		/* Get physical address */
+		phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
+		pfn  = phys >> PAGE_SHIFT;
+
+		/* Unmap address from IO address space */
+		order       = iommu_unmap(domain, gfn_to_gpa(gfn), PAGE_SIZE);
+		unmap_pages = 1ULL << order;
+
+		/* Unpin all pages we just unmapped to not leak any memory */
+		kvm_unpin_pages(kvm, pfn, unmap_pages);
+
+		gfn += unmap_pages;
+	}
 }
 
 static int kvm_iommu_unmap_memslots(struct kvm *kvm)