diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 5b5aba4..7306081 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -251,8 +251,6 @@
 	- how to execute Mono-based .NET binaries with the help of BINFMT_MISC.
 moxa-smartio
 	- file with info on installing/using Moxa multiport serial driver.
-mtrr.txt
-	- how to use PPro Memory Type Range Registers to increase performance.
 mutex-design.txt
 	- info on the generic mutex subsystem.
 namespaces/
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index c2371c5..48a3955 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -77,7 +77,8 @@
 When a kernel change causes the interface that the kernel exposes to
 userspace to change, it is recommended that you send the information or
 a patch to the manual pages explaining the change to the manual pages
-maintainer at mtk.manpages@gmail.com.
+maintainer at mtk.manpages@gmail.com, and CC the list
+linux-api@vger.kernel.org.
 
 Here is a list of files that are in the kernel source tree that are
 required reading:
diff --git a/Documentation/SubmitChecklist b/Documentation/SubmitChecklist
index da10e07..21f0795 100644
--- a/Documentation/SubmitChecklist
+++ b/Documentation/SubmitChecklist
@@ -67,6 +67,8 @@
 
 19: All new userspace interfaces are documented in Documentation/ABI/.
     See Documentation/ABI/README for more information.
+    Patches that change userspace interfaces should be CCed to
+    linux-api@vger.kernel.org.
 
 20: Check that it all passes `make headers_check'.
 
diff --git a/Documentation/ioctl/cdrom.txt b/Documentation/ioctl/cdrom.txt
index 62d4af4..59df81c 100644
--- a/Documentation/ioctl/cdrom.txt
+++ b/Documentation/ioctl/cdrom.txt
@@ -271,14 +271,14 @@
 
 	usage:
 
-	  ioctl(fd, CDROMEJECT, 0);
+	  ioctl(fd, CDROMCLOSETRAY, 0);
 
 	inputs:		none
 
 	outputs:	none
 
 	error returns:
-	  ENOSYS	cd drive not capable of ejecting
+	  ENOSYS	cd drive not capable of closing the tray
 	  EBUSY		other processes are accessing drive, or door is locked
 
 	notes:
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1150444..329dcab 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -463,12 +463,6 @@
 			Range: 0 - 8192
 			Default: 64
 
-	disable_8254_timer
-	enable_8254_timer
-			[IA32/X86_64] Disable/Enable interrupt 0 timer routing
-			over the 8254 in addition to over the IO-APIC. The
-			kernel tries to set a sensible default.
-
 	hpet=		[X86-32,HPET] option to control HPET usage
 			Format: { enable (default) | disable | force }
 			disable: disable HPET and use PIT instead
@@ -1882,6 +1876,12 @@
 	shapers=	[NET]
 			Maximal number of shapers.
 
+	show_msr=	[x86] show boot-time MSR settings
+			Format: { <integer> }
+			Show boot-time (BIOS-initialized) MSR settings.
+			The parameter means the number of CPUs to show,
+			for example 1 means boot CPU only.
+
 	sim710=		[SCSI,HW]
 			See header of drivers/scsi/sim710.c.
 
diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX
new file mode 100644
index 0000000..dbe3377
--- /dev/null
+++ b/Documentation/x86/00-INDEX
@@ -0,0 +1,4 @@
+00-INDEX
+	- this file
+mtrr.txt
+	- how to use x86 Memory Type Range Registers to increase performance
diff --git a/Documentation/x86/i386/boot.txt b/Documentation/x86/boot.txt
similarity index 99%
rename from Documentation/x86/i386/boot.txt
rename to Documentation/x86/boot.txt
index 147bfe5..83c0033 100644
--- a/Documentation/x86/i386/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -308,7 +308,7 @@
 
 Field name:	start_sys
 Type:		read
-Offset/size:	0x20c/4
+Offset/size:	0x20c/2
 Protocol:	2.00+
 
   The load low segment (0x1000).  Obsolete.
diff --git a/Documentation/mtrr.txt b/Documentation/x86/mtrr.txt
similarity index 99%
rename from Documentation/mtrr.txt
rename to Documentation/x86/mtrr.txt
index c39ac39..cc071dc 100644
--- a/Documentation/mtrr.txt
+++ b/Documentation/x86/mtrr.txt
@@ -18,7 +18,7 @@
   The AMD K6-2 (stepping 8 and above) and K6-3 processors have two
   MTRRs. These are supported.  The AMD Athlon family provide 8 Intel
   style MTRRs.
-  
+
   The Centaur C6 (WinChip) has 8 MCRs, allowing write-combining. These
   are supported.
 
@@ -87,7 +87,7 @@
 reg01: base=0xfb000000 (4016MB), size=  16MB: write-combining, count=1
 reg02: base=0xfb000000 (4016MB), size=   4kB: uncachable, count=1
 
-Some cards (especially Voodoo Graphics boards) need this 4 kB area 
+Some cards (especially Voodoo Graphics boards) need this 4 kB area
 excluded from the beginning of the region because it is used for
 registers.
 
diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt
index 17965f9..c93ff5f 100644
--- a/Documentation/x86/pat.txt
+++ b/Documentation/x86/pat.txt
@@ -14,6 +14,10 @@
 ones that will be supported at this time are Write-back, Uncached,
 Write-combined and Uncached Minus.
 
+
+PAT APIs
+--------
+
 There are many different APIs in the kernel that allows setting of memory
 attributes at the page level. In order to avoid aliasing, these interfaces
 should be used thoughtfully. Below is a table of interfaces available,
@@ -26,38 +30,38 @@
 API                    |    RAM   |  ACPI,...  |  Reserved/Holes  |
 -----------------------|----------|------------|------------------|
                        |          |            |                  |
-ioremap                |    --    |    UC      |       UC         |
+ioremap                |    --    |    UC-     |       UC-        |
                        |          |            |                  |
 ioremap_cache          |    --    |    WB      |       WB         |
                        |          |            |                  |
-ioremap_nocache        |    --    |    UC      |       UC         |
+ioremap_nocache        |    --    |    UC-     |       UC-        |
                        |          |            |                  |
 ioremap_wc             |    --    |    --      |       WC         |
                        |          |            |                  |
-set_memory_uc          |    UC    |    --      |       --         |
+set_memory_uc          |    UC-   |    --      |       --         |
  set_memory_wb         |          |            |                  |
                        |          |            |                  |
 set_memory_wc          |    WC    |    --      |       --         |
  set_memory_wb         |          |            |                  |
                        |          |            |                  |
-pci sysfs resource     |    --    |    --      |       UC         |
+pci sysfs resource     |    --    |    --      |       UC-        |
                        |          |            |                  |
 pci sysfs resource_wc  |    --    |    --      |       WC         |
  is IORESOURCE_PREFETCH|          |            |                  |
                        |          |            |                  |
-pci proc               |    --    |    --      |       UC         |
+pci proc               |    --    |    --      |       UC-        |
  !PCIIOC_WRITE_COMBINE |          |            |                  |
                        |          |            |                  |
 pci proc               |    --    |    --      |       WC         |
  PCIIOC_WRITE_COMBINE  |          |            |                  |
                        |          |            |                  |
-/dev/mem               |    --    |    UC      |       UC         |
+/dev/mem               |    --    |  WB/WC/UC- |    WB/WC/UC-     |
  read-write            |          |            |                  |
                        |          |            |                  |
-/dev/mem               |    --    |    UC      |       UC         |
+/dev/mem               |    --    |    UC-     |       UC-        |
  mmap SYNC flag        |          |            |                  |
                        |          |            |                  |
-/dev/mem               |    --    |  WB/WC/UC  |    WB/WC/UC      |
+/dev/mem               |    --    |  WB/WC/UC- |    WB/WC/UC-     |
  mmap !SYNC flag       |          |(from exist-|  (from exist-    |
  and                   |          |  ing alias)|    ing alias)    |
  any alias to this area|          |            |                  |
@@ -68,7 +72,7 @@
  and                   |          |            |                  |
  MTRR says WB          |          |            |                  |
                        |          |            |                  |
-/dev/mem               |    --    |    --      |    UC_MINUS      |
+/dev/mem               |    --    |    --      |       UC-        |
  mmap !SYNC flag       |          |            |                  |
  no alias to this area |          |            |                  |
  and                   |          |            |                  |
@@ -98,3 +102,35 @@
 
 Drivers should use set_memory_[uc|wc] to set access type for RAM ranges.
 
+
+PAT debugging
+-------------
+
+With CONFIG_DEBUG_FS enabled, PAT memtype list can be examined by
+
+# mount -t debugfs debugfs /sys/kernel/debug
+# cat /sys/kernel/debug/x86/pat_memtype_list
+PAT memtype list:
+uncached-minus @ 0x7fadf000-0x7fae0000
+uncached-minus @ 0x7fb19000-0x7fb1a000
+uncached-minus @ 0x7fb1a000-0x7fb1b000
+uncached-minus @ 0x7fb1b000-0x7fb1c000
+uncached-minus @ 0x7fb1c000-0x7fb1d000
+uncached-minus @ 0x7fb1d000-0x7fb1e000
+uncached-minus @ 0x7fb1e000-0x7fb25000
+uncached-minus @ 0x7fb25000-0x7fb26000
+uncached-minus @ 0x7fb26000-0x7fb27000
+uncached-minus @ 0x7fb27000-0x7fb28000
+uncached-minus @ 0x7fb28000-0x7fb2e000
+uncached-minus @ 0x7fb2e000-0x7fb2f000
+uncached-minus @ 0x7fb2f000-0x7fb30000
+uncached-minus @ 0x7fb31000-0x7fb32000
+uncached-minus @ 0x80000000-0x90000000
+
+This list shows physical address ranges and various PAT settings used to
+access those physical address ranges.
+
+Another, more verbose way of getting PAT related debug messages is with
+"debugpat" boot parameter. With this parameter, various debug messages are
+printed to dmesg log.
+
diff --git a/Documentation/x86/i386/usb-legacy-support.txt b/Documentation/x86/usb-legacy-support.txt
similarity index 100%
rename from Documentation/x86/i386/usb-legacy-support.txt
rename to Documentation/x86/usb-legacy-support.txt
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index b0c7b6c..72ffb53 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -54,10 +54,6 @@
 		 apicmaintimer. Useful when your PIT timer is totally
 		 broken.
 
-   disable_8254_timer / enable_8254_timer
-		 Enable interrupt 0 timer routing over the 8254 in addition to over
-	         the IO-APIC. The kernel tries to set a sensible default.
-
 Early Console
 
    syntax: earlyprintk=vga
diff --git a/Documentation/x86/i386/zero-page.txt b/Documentation/x86/zero-page.txt
similarity index 100%
rename from Documentation/x86/i386/zero-page.txt
rename to Documentation/x86/zero-page.txt
diff --git a/MAINTAINERS b/MAINTAINERS
index 3596d17..8dae455 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1198,9 +1198,7 @@
 S:	Maintained
 
 CPUSETS
-P:	Paul Jackson
 P:	Paul Menage
-M:	pj@sgi.com
 M:	menage@google.com
 L:	linux-kernel@vger.kernel.org
 W:	http://www.bullopensource.org/cpuset/
@@ -2706,6 +2704,7 @@
 P:	Michael Kerrisk
 M:	mtk.manpages@gmail.com
 W:	http://www.kernel.org/doc/man-pages
+L:	linux-man@vger.kernel.org
 S:	Supported
 
 MARVELL LIBERTAS WIRELESS DRIVER
diff --git a/Makefile b/Makefile
index cab896a..1d03c16 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 27
-EXTRAVERSION = -rc7
+EXTRAVERSION = -rc8
 NAME = Rotary Wombat
 
 # *DOCUMENTATION*
diff --git a/arch/arm/include/asm/cnt32_to_63.h b/arch/arm/include/asm/cnt32_to_63.h
deleted file mode 100644
index 480c873..0000000
--- a/arch/arm/include/asm/cnt32_to_63.h
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- *  include/asm/cnt32_to_63.h -- extend a 32-bit counter to 63 bits
- *
- *  Author:	Nicolas Pitre
- *  Created:	December 3, 2006
- *  Copyright:	MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- */
-
-#ifndef __INCLUDE_CNT32_TO_63_H__
-#define __INCLUDE_CNT32_TO_63_H__
-
-#include <linux/compiler.h>
-#include <asm/types.h>
-#include <asm/byteorder.h>
-
-/*
- * Prototype: u64 cnt32_to_63(u32 cnt)
- * Many hardware clock counters are only 32 bits wide and therefore have
- * a relatively short period making wrap-arounds rather frequent.  This
- * is a problem when implementing sched_clock() for example, where a 64-bit
- * non-wrapping monotonic value is expected to be returned.
- *
- * To overcome that limitation, let's extend a 32-bit counter to 63 bits
- * in a completely lock free fashion. Bits 0 to 31 of the clock are provided
- * by the hardware while bits 32 to 62 are stored in memory.  The top bit in
- * memory is used to synchronize with the hardware clock half-period.  When
- * the top bit of both counters (hardware and in memory) differ then the
- * memory is updated with a new value, incrementing it when the hardware
- * counter wraps around.
- *
- * Because a word store in memory is atomic then the incremented value will
- * always be in synch with the top bit indicating to any potential concurrent
- * reader if the value in memory is up to date or not with regards to the
- * needed increment.  And any race in updating the value in memory is harmless
- * as the same value would simply be stored more than once.
- *
- * The only restriction for the algorithm to work properly is that this
- * code must be executed at least once per each half period of the 32-bit
- * counter to properly update the state bit in memory. This is usually not a
- * problem in practice, but if it is then a kernel timer could be scheduled
- * to manage for this code to be executed often enough.
- *
- * Note that the top bit (bit 63) in the returned value should be considered
- * as garbage.  It is not cleared here because callers are likely to use a
- * multiplier on the returned value which can get rid of the top bit
- * implicitly by making the multiplier even, therefore saving on a runtime
- * clear-bit instruction. Otherwise caller must remember to clear the top
- * bit explicitly.
- */
-
-/* this is used only to give gcc a clue about good code generation */
-typedef union {
-	struct {
-#if defined(__LITTLE_ENDIAN)
-		u32 lo, hi;
-#elif defined(__BIG_ENDIAN)
-		u32 hi, lo;
-#endif
-	};
-	u64 val;
-} cnt32_to_63_t;
-
-#define cnt32_to_63(cnt_lo) \
-({ \
-	static volatile u32 __m_cnt_hi = 0; \
-	cnt32_to_63_t __x; \
-	__x.hi = __m_cnt_hi; \
-	__x.lo = (cnt_lo); \
- 	if (unlikely((s32)(__x.hi ^ __x.lo) < 0)) \
-		__m_cnt_hi = __x.hi = (__x.hi ^ 0x80000000) + (__x.hi >> 31); \
-	__x.val; \
-})
-
-#endif
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index aaffaec..ba8ccfe 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -111,8 +111,6 @@
 	case 'D':
 	case 'k':
 	case 'c':
-		kgdb_contthread = NULL;
-
 		/*
 		 * Try to read optional parameter, pc unchanged if no parm.
 		 * If this was a compiled breakpoint, we need to move
diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h
index f667998..1a873b3 100644
--- a/arch/ia64/include/asm/sections.h
+++ b/arch/ia64/include/asm/sections.h
@@ -11,6 +11,9 @@
 #include <asm-generic/sections.h>
 
 extern char __per_cpu_start[], __per_cpu_end[], __phys_per_cpu_start[];
+#ifdef	CONFIG_SMP
+extern char __cpu0_per_cpu[];
+#endif
 extern char __start___vtop_patchlist[], __end___vtop_patchlist[];
 extern char __start___rse_patchlist[], __end___rse_patchlist[];
 extern char __start___mckinley_e9_bundles[], __end___mckinley_e9_bundles[];
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 8bdea8e..66e491d 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -367,16 +367,17 @@
 	;;
 #else
 (isAP)	br.few 2f
-	mov r20=r19
-	sub r19=r19,r18
+	movl r20=__cpu0_per_cpu
 	;;
 	shr.u r18=r18,3
 1:
-	ld8 r21=[r20],8;;
-	st8[r19]=r21,8
+	ld8 r21=[r19],8;;
+	st8[r20]=r21,8
 	adds r18=-1,r18;;
 	cmp4.lt p7,p6=0,r18
 (p7)	br.cond.dptk.few 1b
+	mov r19=r20
+	;;
 2:
 #endif
 	tpa r19=r19
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index de71da8..10a7d47e 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -215,9 +215,6 @@
   /* Per-cpu data: */
   percpu : { } :percpu
   . = ALIGN(PERCPU_PAGE_SIZE);
-#ifdef	CONFIG_SMP
-  . = . + PERCPU_PAGE_SIZE;	/* cpu0 per-cpu space */
-#endif
   __phys_per_cpu_start = .;
   .data.percpu PERCPU_ADDR : AT(__phys_per_cpu_start - LOAD_OFFSET)
 	{
@@ -233,6 +230,11 @@
   data : { } :data
   .data : AT(ADDR(.data) - LOAD_OFFSET)
 	{
+#ifdef	CONFIG_SMP
+  . = ALIGN(PERCPU_PAGE_SIZE);
+		__cpu0_per_cpu = .;
+  . = . + PERCPU_PAGE_SIZE;	/* cpu0 per-cpu space */
+#endif
 		DATA_DATA
 		*(.data1)
 		*(.gnu.linkonce.d*)
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index e566ff4..0ee085e 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -163,7 +163,7 @@
 	 * get_zeroed_page().
 	 */
 	if (first_time) {
-		void *cpu0_data = __phys_per_cpu_start - PERCPU_PAGE_SIZE;
+		void *cpu0_data = __cpu0_per_cpu;
 
 		first_time=0;
 
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 78026aa..d8c5fcd 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -144,7 +144,7 @@
 
 	for_each_possible_early_cpu(cpu) {
 		if (cpu == 0) {
-			void *cpu0_data = __phys_per_cpu_start - PERCPU_PAGE_SIZE;
+			void *cpu0_data = __cpu0_per_cpu;
 			__per_cpu_offset[cpu] = (char*)cpu0_data -
 				__per_cpu_start;
 		} else if (node == node_cpuid[cpu].nid) {
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index a5f864c..f57113f 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -216,10 +216,6 @@
 	default "01000000" if PLAT_M32104UT
 	default "00800000" if PLAT_OAKS32R
 
-config NOHIGHMEM
-	bool
-	default y
-
 config ARCH_DISCONTIGMEM_ENABLE
 	bool "Internal RAM Support"
 	depends on CHIP_M32700 || CHIP_M32102 || CHIP_VDEC2 || CHIP_OPSP || CHIP_M32104
@@ -410,11 +406,7 @@
 source "drivers/pci/Kconfig"
 
 config ISA
-	bool "ISA support"
-	help
-	  Find out whether you have ISA slots on your motherboard.  ISA is the
-	  name of a bus system, i.e. the way the CPU talks to the other stuff
-	  inside your box.  If you have ISA, say Y, otherwise N.
+	bool
 
 source "drivers/pcmcia/Kconfig"
 
diff --git a/arch/m32r/kernel/entry.S b/arch/m32r/kernel/entry.S
index d4eaa2f..612d35b 100644
--- a/arch/m32r/kernel/entry.S
+++ b/arch/m32r/kernel/entry.S
@@ -143,7 +143,7 @@
 	and3	r4, r4, #0x8000		; check BSM bit
 #endif
 	beqz	r4, resume_kernel
-ENTRY(resume_userspace)
+resume_userspace:
 	DISABLE_INTERRUPTS(r4)		; make sure we don't miss an interrupt
 					; setting need_resched or sigpending
 					; between sampling and the iret
diff --git a/arch/m32r/kernel/head.S b/arch/m32r/kernel/head.S
index dab7436..4018077 100644
--- a/arch/m32r/kernel/head.S
+++ b/arch/m32r/kernel/head.S
@@ -29,7 +29,6 @@
 	.global _end
 ENTRY(stext)
 ENTRY(_stext)
-ENTRY(startup_32)
 	/* Setup up the stack pointer */
 	LDIMM	(r0, spi_stack_top)
 	LDIMM	(r1, spu_stack_top)
diff --git a/arch/m32r/kernel/irq.c b/arch/m32r/kernel/irq.c
index d0c5b0b..2aeae46 100644
--- a/arch/m32r/kernel/irq.c
+++ b/arch/m32r/kernel/irq.c
@@ -22,9 +22,6 @@
 #include <linux/module.h>
 #include <asm/uaccess.h>
 
-atomic_t irq_err_count;
-atomic_t irq_mis_count;
-
 /*
  * Generic, controller-independent functions:
  */
@@ -63,9 +60,6 @@
 		seq_putc(p, '\n');
 skip:
 		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
-	} else if (i == NR_IRQS) {
-		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
-		seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
 	}
 	return 0;
 }
diff --git a/arch/m32r/kernel/m32r_ksyms.c b/arch/m32r/kernel/m32r_ksyms.c
index 16bcb18..22624b5 100644
--- a/arch/m32r/kernel/m32r_ksyms.c
+++ b/arch/m32r/kernel/m32r_ksyms.c
@@ -14,6 +14,7 @@
 #include <asm/delay.h>
 #include <asm/irq.h>
 #include <asm/tlbflush.h>
+#include <asm/pgtable.h>
 
 /* platform dependent support */
 EXPORT_SYMBOL(boot_cpu_data);
@@ -65,6 +66,7 @@
 EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(clear_page);
 EXPORT_SYMBOL(strlen);
+EXPORT_SYMBOL(empty_zero_page);
 
 EXPORT_SYMBOL(_inb);
 EXPORT_SYMBOL(_inw);
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index a689e29..5be4faa 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -35,8 +35,6 @@
 
 #include <linux/err.h>
 
-static int hlt_counter=0;
-
 /*
  * Return saved PC of a blocked thread.
  */
@@ -48,31 +46,16 @@
 /*
  * Powermanagement idle function, if any..
  */
-void (*pm_idle)(void) = NULL;
-EXPORT_SYMBOL(pm_idle);
+static void (*pm_idle)(void) = NULL;
 
 void (*pm_power_off)(void) = NULL;
 EXPORT_SYMBOL(pm_power_off);
 
-void disable_hlt(void)
-{
-	hlt_counter++;
-}
-
-EXPORT_SYMBOL(disable_hlt);
-
-void enable_hlt(void)
-{
-	hlt_counter--;
-}
-
-EXPORT_SYMBOL(enable_hlt);
-
 /*
  * We use this is we don't have any better
  * idle routine..
  */
-void default_idle(void)
+static void default_idle(void)
 {
 	/* M32R_FIXME: Please use "cpu_sleep" mode.  */
 	cpu_relax();
@@ -260,15 +243,6 @@
 	return 0;
 }
 
-/*
- * Capture the user space registers if the task is not running (in user space)
- */
-int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs)
-{
-	/* M32R_FIXME */
-	return 1;
-}
-
 asmlinkage int sys_fork(unsigned long r0, unsigned long r1, unsigned long r2,
 	unsigned long r3, unsigned long r4, unsigned long r5, unsigned long r6,
 	struct pt_regs regs)
diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c
index 7577f97..929e5c9d 100644
--- a/arch/m32r/kernel/smp.c
+++ b/arch/m32r/kernel/smp.c
@@ -84,7 +84,7 @@
 void smp_ipi_timer_interrupt(struct pt_regs *);
 void smp_local_timer_interrupt(void);
 
-void send_IPI_allbutself(int, int);
+static void send_IPI_allbutself(int, int);
 static void send_IPI_mask(cpumask_t, int, int);
 unsigned long send_IPI_mask_phys(cpumask_t, int, int);
 
@@ -722,7 +722,7 @@
  * ---------- --- --------------------------------------------------------
  *
  *==========================================================================*/
-void send_IPI_allbutself(int ipi_num, int try)
+static void send_IPI_allbutself(int ipi_num, int try)
 {
 	cpumask_t cpumask;
 
diff --git a/arch/m32r/kernel/time.c b/arch/m32r/kernel/time.c
index 994cc15..6ea0177 100644
--- a/arch/m32r/kernel/time.c
+++ b/arch/m32r/kernel/time.c
@@ -34,7 +34,6 @@
 #include <asm/hw_irq.h>
 
 #ifdef CONFIG_SMP
-extern void send_IPI_allbutself(int, int);
 extern void smp_local_timer_interrupt(void);
 #endif
 
@@ -188,7 +187,7 @@
  * timer_interrupt() needs to keep up the real-time clock,
  * as well as call the "do_timer()" routine every clocktick
  */
-irqreturn_t timer_interrupt(int irq, void *dev_id)
+static irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
 #ifndef CONFIG_SMP
 	profile_tick(CPU_PROFILING);
@@ -228,7 +227,7 @@
 	return IRQ_HANDLED;
 }
 
-struct irqaction irq0 = {
+static struct irqaction irq0 = {
 	.handler = timer_interrupt,
 	.flags = IRQF_DISABLED,
 	.mask = CPU_MASK_NONE,
diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index 46159a4..03b14e5 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -61,7 +61,7 @@
 	((unsigned long)func - (unsigned long)eit_vector - entry*4)/4 \
 	+ 0xff000000UL
 
-void	set_eit_vector_entries(void)
+static void set_eit_vector_entries(void)
 {
 	extern void default_eit_handler(void);
 	extern void system_call(void);
@@ -121,9 +121,9 @@
 	cpu_init();
 }
 
-int kstack_depth_to_print = 24;
+static int kstack_depth_to_print = 24;
 
-void show_trace(struct task_struct *task, unsigned long *stack)
+static void show_trace(struct task_struct *task, unsigned long *stack)
 {
 	unsigned long addr;
 
@@ -224,7 +224,7 @@
 	printk("\n");
 }
 
-DEFINE_SPINLOCK(die_lock);
+static DEFINE_SPINLOCK(die_lock);
 
 void die(const char * str, struct pt_regs * regs, long err)
 {
diff --git a/arch/m32r/lib/delay.c b/arch/m32r/lib/delay.c
index 59bfc34..ced549b 100644
--- a/arch/m32r/lib/delay.c
+++ b/arch/m32r/lib/delay.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/param.h>
+#include <linux/module.h>
 #ifdef CONFIG_SMP
 #include <linux/sched.h>
 #include <asm/current.h>
@@ -121,3 +122,4 @@
 {
 	__const_udelay(nsecs * 0x00005);  /* 2**32 / 1000000000 (rounded up) */
 }
+EXPORT_SYMBOL(__ndelay);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 49896a2..c930b8c 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1403,7 +1403,6 @@
 	depends on CPU_MIPS32_R2
 	#depends on CPU_MIPS64_R2		# once there is hardware ...
 	depends on SYS_SUPPORTS_MULTITHREADING
-	select GENERIC_CLOCKEVENTS_BROADCAST
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select MIPS_MT
@@ -1451,32 +1450,17 @@
 	  Includes a loader for loading an elf relocatable object
 	  onto another VPE and running it.
 
-config MIPS_MT_SMTC_INSTANT_REPLAY
-	bool "Low-latency Dispatch of Deferred SMTC IPIs"
-	depends on MIPS_MT_SMTC && !PREEMPT
-	default y
-	help
-	  SMTC pseudo-interrupts between TCs are deferred and queued
-	  if the target TC is interrupt-inhibited (IXMT). In the first
-	  SMTC prototypes, these queued IPIs were serviced on return
-	  to user mode, or on entry into the kernel idle loop. The
-	  INSTANT_REPLAY option dispatches them as part of local_irq_restore()
-	  processing, which adds runtime overhead (hence the option to turn
-	  it off), but ensures that IPIs are handled promptly even under
-	  heavy I/O interrupt load.
-
 config MIPS_MT_SMTC_IM_BACKSTOP
 	bool "Use per-TC register bits as backstop for inhibited IM bits"
 	depends on MIPS_MT_SMTC
-	default y
+	default n
 	help
 	  To support multiple TC microthreads acting as "CPUs" within
 	  a VPE, VPE-wide interrupt mask bits must be specially manipulated
 	  during interrupt handling. To support legacy drivers and interrupt
 	  controller management code, SMTC has a "backstop" to track and
 	  if necessary restore the interrupt mask. This has some performance
-	  impact on interrupt service overhead. Disable it only if you know
-	  what you are doing.
+	  impact on interrupt service overhead.
 
 config MIPS_MT_SMTC_IRQAFF
 	bool "Support IRQ affinity API"
@@ -1486,10 +1470,8 @@
 	  Enables SMP IRQ affinity API (/proc/irq/*/smp_affinity, etc.)
 	  for SMTC Linux kernel. Requires platform support, of which
 	  an example can be found in the MIPS kernel i8259 and Malta
-	  platform code.  It is recommended that MIPS_MT_SMTC_INSTANT_REPLAY
-	  be enabled if MIPS_MT_SMTC_IRQAFF is used. Adds overhead to
-	  interrupt dispatch, and should be used only if you know what
-	  you are doing.
+	  platform code.  Adds some overhead to interrupt dispatch, and
+	  should be used only if you know what you are doing.
 
 config MIPS_VPE_LOADER_TOM
 	bool "Load VPE program into memory hidden from linux"
diff --git a/arch/mips/au1000/common/gpio.c b/arch/mips/au1000/common/gpio.c
index 1f05843..e660ddd 100644
--- a/arch/mips/au1000/common/gpio.c
+++ b/arch/mips/au1000/common/gpio.c
@@ -48,7 +48,7 @@
 {
 	gpio -= AU1XXX_GPIO_BASE;
 
-	gpio2->output = (GPIO2_OUTPUT_ENABLE_MASK << gpio) | (value << gpio);
+	gpio2->output = (GPIO2_OUTPUT_ENABLE_MASK << gpio) | ((!!value) << gpio);
 }
 
 static int au1xxx_gpio2_direction_input(unsigned gpio)
@@ -62,7 +62,7 @@
 {
 	gpio -= AU1XXX_GPIO_BASE;
 	gpio2->dir |= 0x01 << gpio;
-	gpio2->output = (GPIO2_OUTPUT_ENABLE_MASK << gpio) | (value << gpio);
+	gpio2->output = (GPIO2_OUTPUT_ENABLE_MASK << gpio) | ((!!value) << gpio);
 	return 0;
 }
 
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 706f939..25775cb 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -10,6 +10,7 @@
 
 obj-$(CONFIG_CEVT_BCM1480)	+= cevt-bcm1480.o
 obj-$(CONFIG_CEVT_R4K)		+= cevt-r4k.o
+obj-$(CONFIG_MIPS_MT_SMTC)	+= cevt-smtc.o
 obj-$(CONFIG_CEVT_DS1287)	+= cevt-ds1287.o
 obj-$(CONFIG_CEVT_GT641XX)	+= cevt-gt641xx.o
 obj-$(CONFIG_CEVT_SB1250)	+= cevt-sb1250.o
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index 24a2d90..4a4c59f 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -12,6 +12,14 @@
 
 #include <asm/smtc_ipi.h>
 #include <asm/time.h>
+#include <asm/cevt-r4k.h>
+
+/*
+ * The SMTC Kernel for the 34K, 1004K, et. al. replaces several
+ * of these routines with SMTC-specific variants.
+ */
+
+#ifndef CONFIG_MIPS_MT_SMTC
 
 static int mips_next_event(unsigned long delta,
                            struct clock_event_device *evt)
@@ -19,60 +27,27 @@
 	unsigned int cnt;
 	int res;
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	{
-	unsigned long flags, vpflags;
-	local_irq_save(flags);
-	vpflags = dvpe();
-#endif
 	cnt = read_c0_count();
 	cnt += delta;
 	write_c0_compare(cnt);
 	res = ((int)(read_c0_count() - cnt) > 0) ? -ETIME : 0;
-#ifdef CONFIG_MIPS_MT_SMTC
-	evpe(vpflags);
-	local_irq_restore(flags);
-	}
-#endif
 	return res;
 }
 
-static void mips_set_mode(enum clock_event_mode mode,
-                          struct clock_event_device *evt)
+#endif /* CONFIG_MIPS_MT_SMTC */
+
+void mips_set_clock_mode(enum clock_event_mode mode,
+				struct clock_event_device *evt)
 {
 	/* Nothing to do ...  */
 }
 
-static DEFINE_PER_CPU(struct clock_event_device, mips_clockevent_device);
-static int cp0_timer_irq_installed;
+DEFINE_PER_CPU(struct clock_event_device, mips_clockevent_device);
+int cp0_timer_irq_installed;
 
-/*
- * Timer ack for an R4k-compatible timer of a known frequency.
- */
-static void c0_timer_ack(void)
-{
-	write_c0_compare(read_c0_compare());
-}
+#ifndef CONFIG_MIPS_MT_SMTC
 
-/*
- * Possibly handle a performance counter interrupt.
- * Return true if the timer interrupt should not be checked
- */
-static inline int handle_perf_irq(int r2)
-{
-	/*
-	 * The performance counter overflow interrupt may be shared with the
-	 * timer interrupt (cp0_perfcount_irq < 0). If it is and a
-	 * performance counter has overflowed (perf_irq() == IRQ_HANDLED)
-	 * and we can't reliably determine if a counter interrupt has also
-	 * happened (!r2) then don't check for a timer interrupt.
-	 */
-	return (cp0_perfcount_irq < 0) &&
-		perf_irq() == IRQ_HANDLED &&
-		!r2;
-}
-
-static irqreturn_t c0_compare_interrupt(int irq, void *dev_id)
+irqreturn_t c0_compare_interrupt(int irq, void *dev_id)
 {
 	const int r2 = cpu_has_mips_r2;
 	struct clock_event_device *cd;
@@ -93,12 +68,8 @@
 	 * interrupt.  Being the paranoiacs we are we check anyway.
 	 */
 	if (!r2 || (read_c0_cause() & (1 << 30))) {
-		c0_timer_ack();
-#ifdef CONFIG_MIPS_MT_SMTC
-		if (cpu_data[cpu].vpe_id)
-			goto out;
-		cpu = 0;
-#endif
+		/* Clear Count/Compare Interrupt */
+		write_c0_compare(read_c0_compare());
 		cd = &per_cpu(mips_clockevent_device, cpu);
 		cd->event_handler(cd);
 	}
@@ -107,65 +78,16 @@
 	return IRQ_HANDLED;
 }
 
-static struct irqaction c0_compare_irqaction = {
+#endif /* Not CONFIG_MIPS_MT_SMTC */
+
+struct irqaction c0_compare_irqaction = {
 	.handler = c0_compare_interrupt,
-#ifdef CONFIG_MIPS_MT_SMTC
-	.flags = IRQF_DISABLED,
-#else
 	.flags = IRQF_DISABLED | IRQF_PERCPU,
-#endif
 	.name = "timer",
 };
 
-#ifdef CONFIG_MIPS_MT_SMTC
-DEFINE_PER_CPU(struct clock_event_device, smtc_dummy_clockevent_device);
 
-static void smtc_set_mode(enum clock_event_mode mode,
-                          struct clock_event_device *evt)
-{
-}
-
-static void mips_broadcast(cpumask_t mask)
-{
-	unsigned int cpu;
-
-	for_each_cpu_mask(cpu, mask)
-		smtc_send_ipi(cpu, SMTC_CLOCK_TICK, 0);
-}
-
-static void setup_smtc_dummy_clockevent_device(void)
-{
-	//uint64_t mips_freq = mips_hpt_^frequency;
-	unsigned int cpu = smp_processor_id();
-	struct clock_event_device *cd;
-
-	cd = &per_cpu(smtc_dummy_clockevent_device, cpu);
-
-	cd->name		= "SMTC";
-	cd->features		= CLOCK_EVT_FEAT_DUMMY;
-
-	/* Calculate the min / max delta */
-	cd->mult	= 0; //div_sc((unsigned long) mips_freq, NSEC_PER_SEC, 32);
-	cd->shift		= 0; //32;
-	cd->max_delta_ns	= 0; //clockevent_delta2ns(0x7fffffff, cd);
-	cd->min_delta_ns	= 0; //clockevent_delta2ns(0x30, cd);
-
-	cd->rating		= 200;
-	cd->irq			= 17; //-1;
-//	if (cpu)
-//		cd->cpumask	= CPU_MASK_ALL; // cpumask_of_cpu(cpu);
-//	else
-		cd->cpumask	= cpumask_of_cpu(cpu);
-
-	cd->set_mode		= smtc_set_mode;
-
-	cd->broadcast		= mips_broadcast;
-
-	clockevents_register_device(cd);
-}
-#endif
-
-static void mips_event_handler(struct clock_event_device *dev)
+void mips_event_handler(struct clock_event_device *dev)
 {
 }
 
@@ -177,7 +99,23 @@
 	return (read_c0_cause() >> cp0_compare_irq) & 0x100;
 }
 
-static int c0_compare_int_usable(void)
+/*
+ * Compare interrupt can be routed and latched outside the core,
+ * so a single execution hazard barrier may not be enough to give
+ * it time to clear as seen in the Cause register.  4 time the
+ * pipeline depth seems reasonably conservative, and empirically
+ * works better in configurations with high CPU/bus clock ratios.
+ */
+
+#define compare_change_hazard() \
+	do { \
+		irq_disable_hazard(); \
+		irq_disable_hazard(); \
+		irq_disable_hazard(); \
+		irq_disable_hazard(); \
+	} while (0)
+
+int c0_compare_int_usable(void)
 {
 	unsigned int delta;
 	unsigned int cnt;
@@ -187,7 +125,7 @@
 	 */
 	if (c0_compare_int_pending()) {
 		write_c0_compare(read_c0_count());
-		irq_disable_hazard();
+		compare_change_hazard();
 		if (c0_compare_int_pending())
 			return 0;
 	}
@@ -196,7 +134,7 @@
 		cnt = read_c0_count();
 		cnt += delta;
 		write_c0_compare(cnt);
-		irq_disable_hazard();
+		compare_change_hazard();
 		if ((int)(read_c0_count() - cnt) < 0)
 		    break;
 		/* increase delta if the timer was already expired */
@@ -205,11 +143,12 @@
 	while ((int)(read_c0_count() - cnt) <= 0)
 		;	/* Wait for expiry  */
 
+	compare_change_hazard();
 	if (!c0_compare_int_pending())
 		return 0;
 
 	write_c0_compare(read_c0_count());
-	irq_disable_hazard();
+	compare_change_hazard();
 	if (c0_compare_int_pending())
 		return 0;
 
@@ -219,6 +158,8 @@
 	return 1;
 }
 
+#ifndef CONFIG_MIPS_MT_SMTC
+
 int __cpuinit mips_clockevent_init(void)
 {
 	uint64_t mips_freq = mips_hpt_frequency;
@@ -229,17 +170,6 @@
 	if (!cpu_has_counter || !mips_hpt_frequency)
 		return -ENXIO;
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	setup_smtc_dummy_clockevent_device();
-
-	/*
-	 * On SMTC we only register VPE0's compare interrupt as clockevent
-	 * device.
-	 */
-	if (cpu)
-		return 0;
-#endif
-
 	if (!c0_compare_int_usable())
 		return -ENXIO;
 
@@ -265,13 +195,9 @@
 
 	cd->rating		= 300;
 	cd->irq			= irq;
-#ifdef CONFIG_MIPS_MT_SMTC
-	cd->cpumask		= CPU_MASK_ALL;
-#else
 	cd->cpumask		= cpumask_of_cpu(cpu);
-#endif
 	cd->set_next_event	= mips_next_event;
-	cd->set_mode		= mips_set_mode;
+	cd->set_mode		= mips_set_clock_mode;
 	cd->event_handler	= mips_event_handler;
 
 	clockevents_register_device(cd);
@@ -281,12 +207,9 @@
 
 	cp0_timer_irq_installed = 1;
 
-#ifdef CONFIG_MIPS_MT_SMTC
-#define CPUCTR_IMASKBIT (0x100 << cp0_compare_irq)
-	setup_irq_smtc(irq, &c0_compare_irqaction, CPUCTR_IMASKBIT);
-#else
 	setup_irq(irq, &c0_compare_irqaction);
-#endif
 
 	return 0;
 }
+
+#endif /* Not CONFIG_MIPS_MT_SMTC */
diff --git a/arch/mips/kernel/cevt-smtc.c b/arch/mips/kernel/cevt-smtc.c
new file mode 100644
index 0000000..5162fe4
--- /dev/null
+++ b/arch/mips/kernel/cevt-smtc.c
@@ -0,0 +1,321 @@
+/*
+ * 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.
+ *
+ * Copyright (C) 2007 MIPS Technologies, Inc.
+ * Copyright (C) 2007 Ralf Baechle <ralf@linux-mips.org>
+ * Copyright (C) 2008 Kevin D. Kissell, Paralogos sarl
+ */
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+
+#include <asm/smtc_ipi.h>
+#include <asm/time.h>
+#include <asm/cevt-r4k.h>
+
+/*
+ * Variant clock event timer support for SMTC on MIPS 34K, 1004K
+ * or other MIPS MT cores.
+ *
+ * Notes on SMTC Support:
+ *
+ * SMTC has multiple microthread TCs pretending to be Linux CPUs.
+ * But there's only one Count/Compare pair per VPE, and Compare
+ * interrupts are taken opportunisitically by available TCs
+ * bound to the VPE with the Count register.  The new timer
+ * framework provides for global broadcasts, but we really
+ * want VPE-level multicasts for best behavior. So instead
+ * of invoking the high-level clock-event broadcast code,
+ * this version of SMTC support uses the historical SMTC
+ * multicast mechanisms "under the hood", appearing to the
+ * generic clock layer as if the interrupts are per-CPU.
+ *
+ * The approach taken here is to maintain a set of NR_CPUS
+ * virtual timers, and track which "CPU" needs to be alerted
+ * at each event.
+ *
+ * It's unlikely that we'll see a MIPS MT core with more than
+ * 2 VPEs, but we *know* that we won't need to handle more
+ * VPEs than we have "CPUs".  So NCPUs arrays of NCPUs elements
+ * is always going to be overkill, but always going to be enough.
+ */
+
+unsigned long smtc_nexttime[NR_CPUS][NR_CPUS];
+static int smtc_nextinvpe[NR_CPUS];
+
+/*
+ * Timestamps stored are absolute values to be programmed
+ * into Count register.  Valid timestamps will never be zero.
+ * If a Zero Count value is actually calculated, it is converted
+ * to be a 1, which will introduce 1 or two CPU cycles of error
+ * roughly once every four billion events, which at 1000 HZ means
+ * about once every 50 days.  If that's actually a problem, one
+ * could alternate squashing 0 to 1 and to -1.
+ */
+
+#define MAKEVALID(x) (((x) == 0L) ? 1L : (x))
+#define ISVALID(x) ((x) != 0L)
+
+/*
+ * Time comparison is subtle, as it's really truncated
+ * modular arithmetic.
+ */
+
+#define IS_SOONER(a, b, reference) \
+    (((a) - (unsigned long)(reference)) < ((b) - (unsigned long)(reference)))
+
+/*
+ * CATCHUP_INCREMENT, used when the function falls behind the counter.
+ * Could be an increasing function instead of a constant;
+ */
+
+#define CATCHUP_INCREMENT 64
+
+static int mips_next_event(unsigned long delta,
+				struct clock_event_device *evt)
+{
+	unsigned long flags;
+	unsigned int mtflags;
+	unsigned long timestamp, reference, previous;
+	unsigned long nextcomp = 0L;
+	int vpe = current_cpu_data.vpe_id;
+	int cpu = smp_processor_id();
+	local_irq_save(flags);
+	mtflags = dmt();
+
+	/*
+	 * Maintain the per-TC virtual timer
+	 * and program the per-VPE shared Count register
+	 * as appropriate here...
+	 */
+	reference = (unsigned long)read_c0_count();
+	timestamp = MAKEVALID(reference + delta);
+	/*
+	 * To really model the clock, we have to catch the case
+	 * where the current next-in-VPE timestamp is the old
+	 * timestamp for the calling CPE, but the new value is
+	 * in fact later.  In that case, we have to do a full
+	 * scan and discover the new next-in-VPE CPU id and
+	 * timestamp.
+	 */
+	previous = smtc_nexttime[vpe][cpu];
+	if (cpu == smtc_nextinvpe[vpe] && ISVALID(previous)
+	    && IS_SOONER(previous, timestamp, reference)) {
+		int i;
+		int soonest = cpu;
+
+		/*
+		 * Update timestamp array here, so that new
+		 * value gets considered along with those of
+		 * other virtual CPUs on the VPE.
+		 */
+		smtc_nexttime[vpe][cpu] = timestamp;
+		for_each_online_cpu(i) {
+			if (ISVALID(smtc_nexttime[vpe][i])
+			    && IS_SOONER(smtc_nexttime[vpe][i],
+				smtc_nexttime[vpe][soonest], reference)) {
+				    soonest = i;
+			}
+		}
+		smtc_nextinvpe[vpe] = soonest;
+		nextcomp = smtc_nexttime[vpe][soonest];
+	/*
+	 * Otherwise, we don't have to process the whole array rank,
+	 * we just have to see if the event horizon has gotten closer.
+	 */
+	} else {
+		if (!ISVALID(smtc_nexttime[vpe][smtc_nextinvpe[vpe]]) ||
+		    IS_SOONER(timestamp,
+			smtc_nexttime[vpe][smtc_nextinvpe[vpe]], reference)) {
+			    smtc_nextinvpe[vpe] = cpu;
+			    nextcomp = timestamp;
+		}
+		/*
+		 * Since next-in-VPE may me the same as the executing
+		 * virtual CPU, we update the array *after* checking
+		 * its value.
+		 */
+		smtc_nexttime[vpe][cpu] = timestamp;
+	}
+
+	/*
+	 * It may be that, in fact, we don't need to update Compare,
+	 * but if we do, we want to make sure we didn't fall into
+	 * a crack just behind Count.
+	 */
+	if (ISVALID(nextcomp)) {
+		write_c0_compare(nextcomp);
+		ehb();
+		/*
+		 * We never return an error, we just make sure
+		 * that we trigger the handlers as quickly as
+		 * we can if we fell behind.
+		 */
+		while ((nextcomp - (unsigned long)read_c0_count())
+			> (unsigned long)LONG_MAX) {
+			nextcomp += CATCHUP_INCREMENT;
+			write_c0_compare(nextcomp);
+			ehb();
+		}
+	}
+	emt(mtflags);
+	local_irq_restore(flags);
+	return 0;
+}
+
+
+void smtc_distribute_timer(int vpe)
+{
+	unsigned long flags;
+	unsigned int mtflags;
+	int cpu;
+	struct clock_event_device *cd;
+	unsigned long nextstamp = 0L;
+	unsigned long reference;
+
+
+repeat:
+	for_each_online_cpu(cpu) {
+	    /*
+	     * Find virtual CPUs within the current VPE who have
+	     * unserviced timer requests whose time is now past.
+	     */
+	    local_irq_save(flags);
+	    mtflags = dmt();
+	    if (cpu_data[cpu].vpe_id == vpe &&
+		ISVALID(smtc_nexttime[vpe][cpu])) {
+		reference = (unsigned long)read_c0_count();
+		if ((smtc_nexttime[vpe][cpu] - reference)
+			 > (unsigned long)LONG_MAX) {
+			    smtc_nexttime[vpe][cpu] = 0L;
+			    emt(mtflags);
+			    local_irq_restore(flags);
+			    /*
+			     * We don't send IPIs to ourself.
+			     */
+			    if (cpu != smp_processor_id()) {
+				smtc_send_ipi(cpu, SMTC_CLOCK_TICK, 0);
+			    } else {
+				cd = &per_cpu(mips_clockevent_device, cpu);
+				cd->event_handler(cd);
+			    }
+		} else {
+			/* Local to VPE but Valid Time not yet reached. */
+			if (!ISVALID(nextstamp) ||
+			    IS_SOONER(smtc_nexttime[vpe][cpu], nextstamp,
+			    reference)) {
+				smtc_nextinvpe[vpe] = cpu;
+				nextstamp = smtc_nexttime[vpe][cpu];
+			}
+			emt(mtflags);
+			local_irq_restore(flags);
+		}
+	    } else {
+		emt(mtflags);
+		local_irq_restore(flags);
+
+	    }
+	}
+	/* Reprogram for interrupt at next soonest timestamp for VPE */
+	if (ISVALID(nextstamp)) {
+		write_c0_compare(nextstamp);
+		ehb();
+		if ((nextstamp - (unsigned long)read_c0_count())
+			> (unsigned long)LONG_MAX)
+				goto repeat;
+	}
+}
+
+
+irqreturn_t c0_compare_interrupt(int irq, void *dev_id)
+{
+	int cpu = smp_processor_id();
+
+	/* If we're running SMTC, we've got MIPS MT and therefore MIPS32R2 */
+	handle_perf_irq(1);
+
+	if (read_c0_cause() & (1 << 30)) {
+		/* Clear Count/Compare Interrupt */
+		write_c0_compare(read_c0_compare());
+		smtc_distribute_timer(cpu_data[cpu].vpe_id);
+	}
+	return IRQ_HANDLED;
+}
+
+
+int __cpuinit mips_clockevent_init(void)
+{
+	uint64_t mips_freq = mips_hpt_frequency;
+	unsigned int cpu = smp_processor_id();
+	struct clock_event_device *cd;
+	unsigned int irq;
+	int i;
+	int j;
+
+	if (!cpu_has_counter || !mips_hpt_frequency)
+		return -ENXIO;
+	if (cpu == 0) {
+		for (i = 0; i < num_possible_cpus(); i++) {
+			smtc_nextinvpe[i] = 0;
+			for (j = 0; j < num_possible_cpus(); j++)
+				smtc_nexttime[i][j] = 0L;
+		}
+		/*
+		 * SMTC also can't have the usablility test
+		 * run by secondary TCs once Compare is in use.
+		 */
+		if (!c0_compare_int_usable())
+			return -ENXIO;
+	}
+
+	/*
+	 * With vectored interrupts things are getting platform specific.
+	 * get_c0_compare_int is a hook to allow a platform to return the
+	 * interrupt number of it's liking.
+	 */
+	irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq;
+	if (get_c0_compare_int)
+		irq = get_c0_compare_int();
+
+	cd = &per_cpu(mips_clockevent_device, cpu);
+
+	cd->name		= "MIPS";
+	cd->features		= CLOCK_EVT_FEAT_ONESHOT;
+
+	/* Calculate the min / max delta */
+	cd->mult	= div_sc((unsigned long) mips_freq, NSEC_PER_SEC, 32);
+	cd->shift		= 32;
+	cd->max_delta_ns	= clockevent_delta2ns(0x7fffffff, cd);
+	cd->min_delta_ns	= clockevent_delta2ns(0x300, cd);
+
+	cd->rating		= 300;
+	cd->irq			= irq;
+	cd->cpumask		= cpumask_of_cpu(cpu);
+	cd->set_next_event	= mips_next_event;
+	cd->set_mode		= mips_set_clock_mode;
+	cd->event_handler	= mips_event_handler;
+
+	clockevents_register_device(cd);
+
+	/*
+	 * On SMTC we only want to do the data structure
+	 * initialization and IRQ setup once.
+	 */
+	if (cpu)
+		return 0;
+	/*
+	 * And we need the hwmask associated with the c0_compare
+	 * vector to be initialized.
+	 */
+	irq_hwmask[irq] = (0x100 << cp0_compare_irq);
+	if (cp0_timer_irq_installed)
+		return 0;
+
+	cp0_timer_irq_installed = 1;
+
+	setup_irq(irq, &c0_compare_irqaction);
+
+	return 0;
+}
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 11c92dc..e621fda 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -54,14 +54,18 @@
  * interrupt is requested" restriction in the MIPS32/MIPS64 architecture makes
  * using this version a gamble.
  */
-static void r4k_wait_irqoff(void)
+void r4k_wait_irqoff(void)
 {
 	local_irq_disable();
 	if (!need_resched())
-		__asm__("	.set	mips3		\n"
+		__asm__("	.set	push		\n"
+			"	.set	mips3		\n"
 			"	wait			\n"
-			"	.set	mips0		\n");
+			"	.set	pop		\n");
 	local_irq_enable();
+	__asm__(" 	.globl __pastwait	\n"
+		"__pastwait:			\n");
+	return;
 }
 
 /*
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index e29598a..ffa3310 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -79,11 +79,6 @@
 
 FEXPORT(restore_all)			# restore full frame
 #ifdef CONFIG_MIPS_MT_SMTC
-/* Detect and execute deferred IPI "interrupts" */
-	LONG_L	s0, TI_REGS($28)
-	LONG_S	sp, TI_REGS($28)
-	jal	deferred_smtc_ipi
-	LONG_S	s0, TI_REGS($28)
 #ifdef CONFIG_MIPS_MT_SMTC_IM_BACKSTOP
 /* Re-arm any temporarily masked interrupts not explicitly "acked" */
 	mfc0	v0, CP0_TCSTATUS
@@ -112,6 +107,11 @@
 	xor	t0, t0, t3
 	mtc0	t0, CP0_TCCONTEXT
 #endif /* CONFIG_MIPS_MT_SMTC_IM_BACKSTOP */
+/* Detect and execute deferred IPI "interrupts" */
+	LONG_L	s0, TI_REGS($28)
+	LONG_S	sp, TI_REGS($28)
+	jal	deferred_smtc_ipi
+	LONG_S	s0, TI_REGS($28)
 #endif /* CONFIG_MIPS_MT_SMTC */
 	.set	noat
 	RESTORE_TEMP
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index f886dd7..01dcbe3 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -282,8 +282,8 @@
 	and	t0, a0, t1
 #ifdef CONFIG_MIPS_MT_SMTC_IM_BACKSTOP
 	mfc0	t2, CP0_TCCONTEXT
-	or	t0, t0, t2
-	mtc0	t0, CP0_TCCONTEXT
+	or	t2, t0, t2
+	mtc0	t2, CP0_TCCONTEXT
 #endif /* CONFIG_MIPS_MT_SMTC_IM_BACKSTOP */
 	xor	t1, t1, t0
 	mtc0	t1, CP0_STATUS
diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c
index 8f6d58e..6e152c8 100644
--- a/arch/mips/kernel/kgdb.c
+++ b/arch/mips/kernel/kgdb.c
@@ -236,8 +236,7 @@
 
 		atomic_set(&kgdb_cpu_doing_single_step, -1);
 		if (remcom_in_buffer[0] == 's')
-			if (kgdb_contthread)
-				atomic_set(&kgdb_cpu_doing_single_step, cpu);
+			atomic_set(&kgdb_cpu_doing_single_step, cpu);
 
 		return 0;
 	}
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index df4d3f2..dc9eb72 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -159,7 +159,7 @@
 /*
  * FPU Use Factor empirically derived from experiments on 34K
  */
-#define FPUSEFACTOR 333
+#define FPUSEFACTOR 2000
 
 static __init int mt_fp_affinity_init(void)
 {
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index ce76843..22fc19b 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -55,7 +55,7 @@
 	while (1) {
 		tick_nohz_stop_sched_tick(1);
 		while (!need_resched()) {
-#ifdef CONFIG_SMTC_IDLE_HOOK_DEBUG
+#ifdef CONFIG_MIPS_MT_SMTC
 			extern void smtc_idle_loop_hook(void);
 
 			smtc_idle_loop_hook();
@@ -145,19 +145,18 @@
 	 */
 	p->thread.cp0_status = read_c0_status() & ~(ST0_CU2|ST0_CU1);
 	childregs->cp0_status &= ~(ST0_CU2|ST0_CU1);
+
+#ifdef CONFIG_MIPS_MT_SMTC
+	/*
+	 * SMTC restores TCStatus after Status, and the CU bits
+	 * are aliased there.
+	 */
+	childregs->cp0_tcstatus &= ~(ST0_CU2|ST0_CU1);
+#endif
 	clear_tsk_thread_flag(p, TIF_USEDFPU);
 
 #ifdef CONFIG_MIPS_MT_FPAFF
 	clear_tsk_thread_flag(p, TIF_FPUBOUND);
-
-	/*
-	 * FPU affinity support is cleaner if we track the
-	 * user-visible CPU affinity from the very beginning.
-	 * The generic cpus_allowed mask will already have
-	 * been copied from the parent before copy_thread
-	 * is invoked.
-	 */
-	p->thread.user_cpus_allowed = p->cpus_allowed;
 #endif /* CONFIG_MIPS_MT_FPAFF */
 
 	if (clone_flags & CLONE_SETTLS)
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 35234b9..96ffc9c 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -238,7 +238,7 @@
 		case FPC_EIR: {	/* implementation / version register */
 			unsigned int flags;
 #ifdef CONFIG_MIPS_MT_SMTC
-			unsigned int irqflags;
+			unsigned long irqflags;
 			unsigned int mtflags;
 #endif /* CONFIG_MIPS_MT_SMTC */
 
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index a516286..897fb2b 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -1,4 +1,21 @@
-/* Copyright (C) 2004 Mips Technologies, 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ *
+ * Copyright (C) 2004 Mips Technologies, Inc
+ * Copyright (C) 2008 Kevin D. Kissell
+ */
 
 #include <linux/clockchips.h>
 #include <linux/kernel.h>
@@ -21,7 +38,6 @@
 #include <asm/time.h>
 #include <asm/addrspace.h>
 #include <asm/smtc.h>
-#include <asm/smtc_ipi.h>
 #include <asm/smtc_proc.h>
 
 /*
@@ -58,11 +74,6 @@
 
 asiduse smtc_live_asid[MAX_SMTC_TLBS][MAX_SMTC_ASIDS];
 
-/*
- * Clock interrupt "latch" buffers, per "CPU"
- */
-
-static atomic_t ipi_timer_latch[NR_CPUS];
 
 /*
  * Number of InterProcessor Interrupt (IPI) message buffers to allocate
@@ -70,7 +81,7 @@
 
 #define IPIBUF_PER_CPU 4
 
-static struct smtc_ipi_q IPIQ[NR_CPUS];
+struct smtc_ipi_q IPIQ[NR_CPUS];
 static struct smtc_ipi_q freeIPIq;
 
 
@@ -282,7 +293,7 @@
  * phys_cpu_present_map and the logical/physical mappings.
  */
 
-int __init mipsmt_build_cpu_map(int start_cpu_slot)
+int __init smtc_build_cpu_map(int start_cpu_slot)
 {
 	int i, ntcs;
 
@@ -325,7 +336,12 @@
 	write_tc_c0_tcstatus((read_tc_c0_tcstatus()
 			& ~(TCSTATUS_TKSU | TCSTATUS_DA | TCSTATUS_IXMT))
 			| TCSTATUS_A);
-	write_tc_c0_tccontext(0);
+	/*
+	 * TCContext gets an offset from the base of the IPIQ array
+	 * to be used in low-level code to detect the presence of
+	 * an active IPI queue
+	 */
+	write_tc_c0_tccontext((sizeof(struct smtc_ipi_q) * cpu) << 16);
 	/* Bind tc to vpe */
 	write_tc_c0_tcbind(vpe);
 	/* In general, all TCs should have the same cpu_data indications */
@@ -336,10 +352,18 @@
 		cpu_data[cpu].options &= ~MIPS_CPU_FPU;
 	cpu_data[cpu].vpe_id = vpe;
 	cpu_data[cpu].tc_id = tc;
+	/* Multi-core SMTC hasn't been tested, but be prepared */
+	cpu_data[cpu].core = (read_vpe_c0_ebase() >> 1) & 0xff;
 }
 
+/*
+ * Tweak to get Count registes in as close a sync as possible.
+ * Value seems good for 34K-class cores.
+ */
 
-void mipsmt_prepare_cpus(void)
+#define CP0_SKEW 8
+
+void smtc_prepare_cpus(int cpus)
 {
 	int i, vpe, tc, ntc, nvpe, tcpervpe[NR_CPUS], slop, cpu;
 	unsigned long flags;
@@ -363,13 +387,13 @@
 		IPIQ[i].head = IPIQ[i].tail = NULL;
 		spin_lock_init(&IPIQ[i].lock);
 		IPIQ[i].depth = 0;
-		atomic_set(&ipi_timer_latch[i], 0);
 	}
 
 	/* cpu_data index starts at zero */
 	cpu = 0;
 	cpu_data[cpu].vpe_id = 0;
 	cpu_data[cpu].tc_id = 0;
+	cpu_data[cpu].core = (read_c0_ebase() >> 1) & 0xff;
 	cpu++;
 
 	/* Report on boot-time options */
@@ -484,7 +508,8 @@
 			write_vpe_c0_compare(0);
 			/* Propagate Config7 */
 			write_vpe_c0_config7(read_c0_config7());
-			write_vpe_c0_count(read_c0_count());
+			write_vpe_c0_count(read_c0_count() + CP0_SKEW);
+			ehb();
 		}
 		/* enable multi-threading within VPE */
 		write_vpe_c0_vpecontrol(read_vpe_c0_vpecontrol() | VPECONTROL_TE);
@@ -556,7 +581,7 @@
 void __cpuinit smtc_boot_secondary(int cpu, struct task_struct *idle)
 {
 	extern u32 kernelsp[NR_CPUS];
-	long flags;
+	unsigned long flags;
 	int mtflags;
 
 	LOCK_MT_PRA();
@@ -585,24 +610,22 @@
 
 void smtc_init_secondary(void)
 {
-	/*
-	 * Start timer on secondary VPEs if necessary.
-	 * plat_timer_setup has already have been invoked by init/main
-	 * on "boot" TC.  Like per_cpu_trap_init() hack, this assumes that
-	 * SMTC init code assigns TCs consdecutively and in ascending order
-	 * to across available VPEs.
-	 */
-	if (((read_c0_tcbind() & TCBIND_CURTC) != 0) &&
-	    ((read_c0_tcbind() & TCBIND_CURVPE)
-	    != cpu_data[smp_processor_id() - 1].vpe_id)){
-		write_c0_compare(read_c0_count() + mips_hpt_frequency/HZ);
-	}
-
 	local_irq_enable();
 }
 
 void smtc_smp_finish(void)
 {
+	int cpu = smp_processor_id();
+
+	/*
+	 * Lowest-numbered CPU per VPE starts a clock tick.
+	 * Like per_cpu_trap_init() hack, this assumes that
+	 * SMTC init code assigns TCs consdecutively and
+	 * in ascending order across available VPEs.
+	 */
+	if (cpu > 0 && (cpu_data[cpu].vpe_id != cpu_data[cpu - 1].vpe_id))
+		write_c0_compare(read_c0_count() + mips_hpt_frequency/HZ);
+
 	printk("TC %d going on-line as CPU %d\n",
 		cpu_data[smp_processor_id()].tc_id, smp_processor_id());
 }
@@ -753,8 +776,10 @@
 {
 	int tcstatus;
 	struct smtc_ipi *pipi;
-	long flags;
+	unsigned long flags;
 	int mtflags;
+	unsigned long tcrestart;
+	extern void r4k_wait_irqoff(void), __pastwait(void);
 
 	if (cpu == smp_processor_id()) {
 		printk("Cannot Send IPI to self!\n");
@@ -771,8 +796,6 @@
 	pipi->arg = (void *)action;
 	pipi->dest = cpu;
 	if (cpu_data[cpu].vpe_id != cpu_data[smp_processor_id()].vpe_id) {
-		if (type == SMTC_CLOCK_TICK)
-			atomic_inc(&ipi_timer_latch[cpu]);
 		/* If not on same VPE, enqueue and send cross-VPE interrupt */
 		smtc_ipi_nq(&IPIQ[cpu], pipi);
 		LOCK_CORE_PRA();
@@ -800,22 +823,29 @@
 
 		if ((tcstatus & TCSTATUS_IXMT) != 0) {
 			/*
-			 * Spin-waiting here can deadlock,
-			 * so we queue the message for the target TC.
+			 * If we're in the the irq-off version of the wait
+			 * loop, we need to force exit from the wait and
+			 * do a direct post of the IPI.
+			 */
+			if (cpu_wait == r4k_wait_irqoff) {
+				tcrestart = read_tc_c0_tcrestart();
+				if (tcrestart >= (unsigned long)r4k_wait_irqoff
+				    && tcrestart < (unsigned long)__pastwait) {
+					write_tc_c0_tcrestart(__pastwait);
+					tcstatus &= ~TCSTATUS_IXMT;
+					write_tc_c0_tcstatus(tcstatus);
+					goto postdirect;
+				}
+			}
+			/*
+			 * Otherwise we queue the message for the target TC
+			 * to pick up when he does a local_irq_restore()
 			 */
 			write_tc_c0_tchalt(0);
 			UNLOCK_CORE_PRA();
-			/* Try to reduce redundant timer interrupt messages */
-			if (type == SMTC_CLOCK_TICK) {
-			    if (atomic_postincrement(&ipi_timer_latch[cpu])!=0){
-				smtc_ipi_nq(&freeIPIq, pipi);
-				return;
-			    }
-			}
 			smtc_ipi_nq(&IPIQ[cpu], pipi);
 		} else {
-			if (type == SMTC_CLOCK_TICK)
-				atomic_inc(&ipi_timer_latch[cpu]);
+postdirect:
 			post_direct_ipi(cpu, pipi);
 			write_tc_c0_tchalt(0);
 			UNLOCK_CORE_PRA();
@@ -883,7 +913,7 @@
 	smp_call_function_interrupt();
 }
 
-DECLARE_PER_CPU(struct clock_event_device, smtc_dummy_clockevent_device);
+DECLARE_PER_CPU(struct clock_event_device, mips_clockevent_device);
 
 void ipi_decode(struct smtc_ipi *pipi)
 {
@@ -891,20 +921,13 @@
 	struct clock_event_device *cd;
 	void *arg_copy = pipi->arg;
 	int type_copy = pipi->type;
-	int ticks;
-
 	smtc_ipi_nq(&freeIPIq, pipi);
 	switch (type_copy) {
 	case SMTC_CLOCK_TICK:
 		irq_enter();
 		kstat_this_cpu.irqs[MIPS_CPU_IRQ_BASE + 1]++;
-		cd = &per_cpu(smtc_dummy_clockevent_device, cpu);
-		ticks = atomic_read(&ipi_timer_latch[cpu]);
-		atomic_sub(ticks, &ipi_timer_latch[cpu]);
-		while (ticks) {
-			cd->event_handler(cd);
-			ticks--;
-		}
+		cd = &per_cpu(mips_clockevent_device, cpu);
+		cd->event_handler(cd);
 		irq_exit();
 		break;
 
@@ -937,24 +960,48 @@
 	}
 }
 
+/*
+ * Similar to smtc_ipi_replay(), but invoked from context restore,
+ * so it reuses the current exception frame rather than set up a
+ * new one with self_ipi.
+ */
+
 void deferred_smtc_ipi(void)
 {
-	struct smtc_ipi *pipi;
-	unsigned long flags;
-/* DEBUG */
-	int q = smp_processor_id();
+	int cpu = smp_processor_id();
 
 	/*
 	 * Test is not atomic, but much faster than a dequeue,
 	 * and the vast majority of invocations will have a null queue.
+	 * If irq_disabled when this was called, then any IPIs queued
+	 * after we test last will be taken on the next irq_enable/restore.
+	 * If interrupts were enabled, then any IPIs added after the
+	 * last test will be taken directly.
 	 */
-	if (IPIQ[q].head != NULL) {
-		while((pipi = smtc_ipi_dq(&IPIQ[q])) != NULL) {
-			/* ipi_decode() should be called with interrupts off */
-			local_irq_save(flags);
+
+	while (IPIQ[cpu].head != NULL) {
+		struct smtc_ipi_q *q = &IPIQ[cpu];
+		struct smtc_ipi *pipi;
+		unsigned long flags;
+
+		/*
+		 * It may be possible we'll come in with interrupts
+		 * already enabled.
+		 */
+		local_irq_save(flags);
+
+		spin_lock(&q->lock);
+		pipi = __smtc_ipi_dq(q);
+		spin_unlock(&q->lock);
+		if (pipi != NULL)
 			ipi_decode(pipi);
-			local_irq_restore(flags);
-		}
+		/*
+		 * The use of the __raw_local restore isn't
+		 * as obviously necessary here as in smtc_ipi_replay(),
+		 * but it's more efficient, given that we're already
+		 * running down the IPI queue.
+		 */
+		__raw_local_irq_restore(flags);
 	}
 }
 
@@ -975,7 +1022,7 @@
 	struct smtc_ipi *pipi;
 	unsigned long tcstatus;
 	int sent;
-	long flags;
+	unsigned long flags;
 	unsigned int mtflags;
 	unsigned int vpflags;
 
@@ -1066,55 +1113,53 @@
 
 /*
  * SMTC-specific hacks invoked from elsewhere in the kernel.
- *
- * smtc_ipi_replay is called from raw_local_irq_restore which is only ever
- * called with interrupts disabled.  We do rely on interrupts being disabled
- * here because using spin_lock_irqsave()/spin_unlock_irqrestore() would
- * result in a recursive call to raw_local_irq_restore().
  */
 
-static void __smtc_ipi_replay(void)
+ /*
+  * smtc_ipi_replay is called from raw_local_irq_restore
+  */
+
+void smtc_ipi_replay(void)
 {
 	unsigned int cpu = smp_processor_id();
 
 	/*
 	 * To the extent that we've ever turned interrupts off,
 	 * we may have accumulated deferred IPIs.  This is subtle.
-	 * If we use the smtc_ipi_qdepth() macro, we'll get an
-	 * exact number - but we'll also disable interrupts
-	 * and create a window of failure where a new IPI gets
-	 * queued after we test the depth but before we re-enable
-	 * interrupts. So long as IXMT never gets set, however,
 	 * we should be OK:  If we pick up something and dispatch
 	 * it here, that's great. If we see nothing, but concurrent
 	 * with this operation, another TC sends us an IPI, IXMT
 	 * is clear, and we'll handle it as a real pseudo-interrupt
-	 * and not a pseudo-pseudo interrupt.
+	 * and not a pseudo-pseudo interrupt.  The important thing
+	 * is to do the last check for queued message *after* the
+	 * re-enabling of interrupts.
 	 */
-	if (IPIQ[cpu].depth > 0) {
-		while (1) {
-			struct smtc_ipi_q *q = &IPIQ[cpu];
-			struct smtc_ipi *pipi;
-			extern void self_ipi(struct smtc_ipi *);
+	while (IPIQ[cpu].head != NULL) {
+		struct smtc_ipi_q *q = &IPIQ[cpu];
+		struct smtc_ipi *pipi;
+		unsigned long flags;
 
-			spin_lock(&q->lock);
-			pipi = __smtc_ipi_dq(q);
-			spin_unlock(&q->lock);
-			if (!pipi)
-				break;
+		/*
+		 * It's just possible we'll come in with interrupts
+		 * already enabled.
+		 */
+		local_irq_save(flags);
 
+		spin_lock(&q->lock);
+		pipi = __smtc_ipi_dq(q);
+		spin_unlock(&q->lock);
+		/*
+		 ** But use a raw restore here to avoid recursion.
+		 */
+		__raw_local_irq_restore(flags);
+
+		if (pipi) {
 			self_ipi(pipi);
 			smtc_cpu_stats[cpu].selfipis++;
 		}
 	}
 }
 
-void smtc_ipi_replay(void)
-{
-	raw_local_irq_disable();
-	__smtc_ipi_replay();
-}
-
 EXPORT_SYMBOL(smtc_ipi_replay);
 
 void smtc_idle_loop_hook(void)
@@ -1193,40 +1238,13 @@
 		}
 	}
 
-	/*
-	 * Now that we limit outstanding timer IPIs, check for hung TC
-	 */
-	for (tc = 0; tc < NR_CPUS; tc++) {
-		/* Don't check ourself - we'll dequeue IPIs just below */
-		if ((tc != smp_processor_id()) &&
-		    atomic_read(&ipi_timer_latch[tc]) > timerq_limit) {
-		    if (clock_hang_reported[tc] == 0) {
-			pdb_msg += sprintf(pdb_msg,
-				"TC %d looks hung with timer latch at %d\n",
-				tc, atomic_read(&ipi_timer_latch[tc]));
-			clock_hang_reported[tc]++;
-			}
-		}
-	}
 	emt(mtflags);
 	local_irq_restore(flags);
 	if (pdb_msg != &id_ho_db_msg[0])
 		printk("CPU%d: %s", smp_processor_id(), id_ho_db_msg);
 #endif /* CONFIG_SMTC_IDLE_HOOK_DEBUG */
 
-	/*
-	 * Replay any accumulated deferred IPIs. If "Instant Replay"
-	 * is in use, there should never be any.
-	 */
-#ifndef CONFIG_MIPS_MT_SMTC_INSTANT_REPLAY
-	{
-		unsigned long flags;
-
-		local_irq_save(flags);
-		__smtc_ipi_replay();
-		local_irq_restore(flags);
-	}
-#endif /* CONFIG_MIPS_MT_SMTC_INSTANT_REPLAY */
+	smtc_ipi_replay();
 }
 
 void smtc_soft_dump(void)
@@ -1242,10 +1260,6 @@
 		printk("%d: %ld\n", i, smtc_cpu_stats[i].selfipis);
 	}
 	smtc_ipi_qdump();
-	printk("Timer IPI Backlogs:\n");
-	for (i=0; i < NR_CPUS; i++) {
-		printk("%d: %d\n", i, atomic_read(&ipi_timer_latch[i]));
-	}
 	printk("%d Recoveries of \"stolen\" FPU\n",
 	       atomic_read(&smtc_fpu_recoveries));
 }
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 5fd0cd0..b602ac6 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -825,8 +825,10 @@
 		if (cpus_intersects(current->cpus_allowed, mt_fpu_cpumask)) {
 			cpumask_t tmask;
 
-			cpus_and(tmask, current->thread.user_cpus_allowed,
-			         mt_fpu_cpumask);
+			current->thread.user_cpus_allowed
+				= current->cpus_allowed;
+			cpus_and(tmask, current->cpus_allowed,
+				mt_fpu_cpumask);
 			set_cpus_allowed(current, tmask);
 			set_thread_flag(TIF_FPUBOUND);
 		}
diff --git a/arch/mips/mti-malta/Makefile b/arch/mips/mti-malta/Makefile
index 3b7dd72..cef2db8 100644
--- a/arch/mips/mti-malta/Makefile
+++ b/arch/mips/mti-malta/Makefile
@@ -15,6 +15,6 @@
 obj-$(CONFIG_PCI)		+= malta-pci.o
 
 # FIXME FIXME FIXME
-obj-$(CONFIG_MIPS_MT_SMTC)	+= malta_smtc.o
+obj-$(CONFIG_MIPS_MT_SMTC)	+= malta-smtc.o
 
 EXTRA_CFLAGS += -Werror
diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c
index 5ea705e..f84a46a 100644
--- a/arch/mips/mti-malta/malta-smtc.c
+++ b/arch/mips/mti-malta/malta-smtc.c
@@ -84,12 +84,17 @@
 
 static void __init msmtc_smp_setup(void)
 {
-	mipsmt_build_cpu_map(0);
+	/*
+	 * we won't get the definitive value until
+	 * we've run smtc_prepare_cpus later, but
+	 * we would appear to need an upper bound now.
+	 */
+	smp_num_siblings = smtc_build_cpu_map(0);
 }
 
 static void __init msmtc_prepare_cpus(unsigned int max_cpus)
 {
-	mipsmt_prepare_cpus();
+	smtc_prepare_cpus(max_cpus);
 }
 
 struct plat_smp_ops msmtc_smp_ops = {
diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile
index 15e01ae..c8c32f4 100644
--- a/arch/mips/pci/Makefile
+++ b/arch/mips/pci/Makefile
@@ -15,6 +15,7 @@
 obj-$(CONFIG_PCI_VR41XX)	+= ops-vr41xx.o pci-vr41xx.o
 obj-$(CONFIG_MARKEINS)		+= ops-emma2rh.o pci-emma2rh.o fixup-emma2rh.o
 obj-$(CONFIG_PCI_TX4927)	+= ops-tx4927.o
+obj-$(CONFIG_BCM47XX)		+= pci-bcm47xx.o
 
 #
 # These are still pretty much in the old state, watch, go blind.
diff --git a/arch/mips/pci/pci-bcm47xx.c b/arch/mips/pci/pci-bcm47xx.c
new file mode 100644
index 0000000..bea9b6c
--- /dev/null
+++ b/arch/mips/pci/pci-bcm47xx.c
@@ -0,0 +1,60 @@
+/*
+ *  Copyright (C) 2008 Aurelien Jarno <aurelien@aurel32.net>
+ *
+ *  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  SOFTWARE  IS PROVIDED   ``AS  IS'' AND   ANY  EXPRESS OR IMPLIED
+ *  WARRANTIES,   INCLUDING, BUT NOT  LIMITED  TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN
+ *  NO  EVENT  SHALL   THE AUTHOR  BE    LIABLE FOR ANY   DIRECT, INDIRECT,
+ *  INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *  NOT LIMITED   TO, PROCUREMENT OF  SUBSTITUTE GOODS  OR SERVICES; LOSS OF
+ *  USE, DATA,  OR PROFITS; OR  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ *  ANY THEORY OF LIABILITY, WHETHER IN  CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ *  THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *  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.,
+ *  675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/ssb/ssb.h>
+
+int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	return 0;
+}
+
+int pcibios_plat_dev_init(struct pci_dev *dev)
+{
+	int res;
+	u8 slot, pin;
+
+	res = ssb_pcibios_plat_dev_init(dev);
+	if (res < 0) {
+		printk(KERN_ALERT "PCI: Failed to init device %s\n",
+		       pci_name(dev));
+		return res;
+	}
+
+	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+	slot = PCI_SLOT(dev->devfn);
+	res = ssb_pcibios_map_irq(dev, slot, pin);
+
+	/* IRQ-0 and IRQ-1 are software interrupts. */
+	if (res < 2) {
+		printk(KERN_ALERT "PCI: Failed to map IRQ of device %s\n",
+		       pci_name(dev));
+		return res;
+	}
+
+	dev->irq = res;
+	return 0;
+}
+
diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c
index bd78368..f97ab14 100644
--- a/arch/mips/pci/pci-ip27.c
+++ b/arch/mips/pci/pci-ip27.c
@@ -143,25 +143,47 @@
  */
 int __devinit pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	struct bridge_controller *bc = BRIDGE_CONTROLLER(dev->bus);
-	int irq = bc->pci_int[slot];
+	return 0;
+}
 
-	if (irq == -1) {
-		irq = bc->pci_int[slot] = request_bridge_irq(bc);
-		if (irq < 0)
-			panic("Can't allocate interrupt for PCI device %s\n",
-			      pci_name(dev));
+/* Most MIPS systems have straight-forward swizzling needs.  */
+static inline u8 bridge_swizzle(u8 pin, u8 slot)
+{
+	return (((pin - 1) + slot) % 4) + 1;
+}
+
+static inline struct pci_dev *bridge_root_dev(struct pci_dev *dev)
+{
+	while (dev->bus->parent) {
+		/* Move up the chain of bridges. */
+		dev = dev->bus->self;
 	}
 
-	irq_to_bridge[irq] = bc;
-	irq_to_slot[irq] = slot;
-
-	return irq;
+	return dev;
 }
 
 /* Do platform specific device initialization at pci_enable_device() time */
 int pcibios_plat_dev_init(struct pci_dev *dev)
 {
+	struct bridge_controller *bc = BRIDGE_CONTROLLER(dev->bus);
+	struct pci_dev *rdev = bridge_root_dev(dev);
+	int slot = PCI_SLOT(rdev->devfn);
+	int irq;
+
+	irq = bc->pci_int[slot];
+	if (irq == -1) {
+		irq = request_bridge_irq(bc);
+		if (irq < 0)
+			return irq;
+
+		bc->pci_int[slot] = irq;
+	}
+
+	irq_to_bridge[irq] = bc;
+	irq_to_slot[irq] = slot;
+
+	dev->irq = irq;
+
 	return 0;
 }
 
diff --git a/arch/mn10300/kernel/irq.c b/arch/mn10300/kernel/irq.c
index 761c434..56c64cc 100644
--- a/arch/mn10300/kernel/irq.c
+++ b/arch/mn10300/kernel/irq.c
@@ -20,22 +20,8 @@
 atomic_t irq_err_count;
 
 /*
- * MN10300 INTC controller operations
+ * MN10300 interrupt controller operations
  */
-static void mn10300_cpupic_disable(unsigned int irq)
-{
-	u16 tmp = GxICR(irq);
-	GxICR(irq) = (tmp & GxICR_LEVEL) | GxICR_DETECT;
-	tmp = GxICR(irq);
-}
-
-static void mn10300_cpupic_enable(unsigned int irq)
-{
-	u16 tmp = GxICR(irq);
-	GxICR(irq) = (tmp & GxICR_LEVEL) | GxICR_ENABLE;
-	tmp = GxICR(irq);
-}
-
 static void mn10300_cpupic_ack(unsigned int irq)
 {
 	u16 tmp;
@@ -60,26 +46,54 @@
 static void mn10300_cpupic_unmask(unsigned int irq)
 {
 	u16 tmp = GxICR(irq);
-	GxICR(irq) = (tmp & GxICR_LEVEL) | GxICR_ENABLE | GxICR_DETECT;
-	tmp = GxICR(irq);
-}
-
-static void mn10300_cpupic_end(unsigned int irq)
-{
-	u16 tmp = GxICR(irq);
 	GxICR(irq) = (tmp & GxICR_LEVEL) | GxICR_ENABLE;
 	tmp = GxICR(irq);
 }
 
-static struct irq_chip mn10300_cpu_pic = {
-	.name		= "cpu",
-	.disable	= mn10300_cpupic_disable,
-	.enable		= mn10300_cpupic_enable,
+static void mn10300_cpupic_unmask_clear(unsigned int irq)
+{
+	/* the MN10300 PIC latches its interrupt request bit, even after the
+	 * device has ceased to assert its interrupt line and the interrupt
+	 * channel has been disabled in the PIC, so for level-triggered
+	 * interrupts we need to clear the request bit when we re-enable */
+	u16 tmp = GxICR(irq);
+	GxICR(irq) = (tmp & GxICR_LEVEL) | GxICR_ENABLE | GxICR_DETECT;
+	tmp = GxICR(irq);
+}
+
+/*
+ * MN10300 PIC level-triggered IRQ handling.
+ *
+ * The PIC has no 'ACK' function per se.  It is possible to clear individual
+ * channel latches, but each latch relatches whether or not the channel is
+ * masked, so we need to clear the latch when we unmask the channel.
+ *
+ * Also for this reason, we don't supply an ack() op (it's unused anyway if
+ * mask_ack() is provided), and mask_ack() just masks.
+ */
+static struct irq_chip mn10300_cpu_pic_level = {
+	.name		= "cpu_l",
+	.disable	= mn10300_cpupic_mask,
+	.enable		= mn10300_cpupic_unmask_clear,
+	.ack		= NULL,
+	.mask		= mn10300_cpupic_mask,
+	.mask_ack	= mn10300_cpupic_mask,
+	.unmask		= mn10300_cpupic_unmask_clear,
+};
+
+/*
+ * MN10300 PIC edge-triggered IRQ handling.
+ *
+ * We use the latch clearing function of the PIC as the 'ACK' function.
+ */
+static struct irq_chip mn10300_cpu_pic_edge = {
+	.name		= "cpu_e",
+	.disable	= mn10300_cpupic_mask,
+	.enable		= mn10300_cpupic_unmask,
 	.ack		= mn10300_cpupic_ack,
 	.mask		= mn10300_cpupic_mask,
 	.mask_ack	= mn10300_cpupic_mask_ack,
 	.unmask		= mn10300_cpupic_unmask,
-	.end		= mn10300_cpupic_end,
 };
 
 /*
@@ -114,7 +128,8 @@
  */
 void set_intr_postackable(int irq)
 {
-	set_irq_handler(irq, handle_level_irq);
+	set_irq_chip_and_handler(irq, &mn10300_cpu_pic_level,
+				 handle_level_irq);
 }
 
 /*
@@ -126,8 +141,12 @@
 
 	for (irq = 0; irq < NR_IRQS; irq++)
 		if (irq_desc[irq].chip == &no_irq_type)
-			set_irq_chip_and_handler(irq, &mn10300_cpu_pic,
-						 handle_edge_irq);
+			/* due to the PIC latching interrupt requests, even
+			 * when the IRQ is disabled, IRQ_PENDING is superfluous
+			 * and we can use handle_level_irq() for edge-triggered
+			 * interrupts */
+			set_irq_chip_and_handler(irq, &mn10300_cpu_pic_edge,
+						 handle_level_irq);
 	unit_init_IRQ();
 }
 
diff --git a/arch/mn10300/unit-asb2303/unit-init.c b/arch/mn10300/unit-asb2303/unit-init.c
index 14b2c81..70e8cb4 100644
--- a/arch/mn10300/unit-asb2303/unit-init.c
+++ b/arch/mn10300/unit-asb2303/unit-init.c
@@ -51,7 +51,7 @@
 		switch (GET_XIRQ_TRIGGER(extnum)) {
 		case XIRQ_TRIGGER_HILEVEL:
 		case XIRQ_TRIGGER_LOWLEVEL:
-			set_irq_handler(XIRQ2IRQ(extnum), handle_level_irq);
+			set_intr_postackable(XIRQ2IRQ(extnum));
 			break;
 		default:
 			break;
diff --git a/arch/mn10300/unit-asb2305/unit-init.c b/arch/mn10300/unit-asb2305/unit-init.c
index 6a35241..72812a9 100644
--- a/arch/mn10300/unit-asb2305/unit-init.c
+++ b/arch/mn10300/unit-asb2305/unit-init.c
@@ -52,7 +52,7 @@
 		switch (GET_XIRQ_TRIGGER(extnum)) {
 		case XIRQ_TRIGGER_HILEVEL:
 		case XIRQ_TRIGGER_LOWLEVEL:
-			set_irq_handler(XIRQ2IRQ(extnum), handle_level_irq);
+			set_intr_postackable(XIRQ2IRQ(extnum));
 			break;
 		default:
 			break;
diff --git a/arch/powerpc/boot/dts/holly.dts b/arch/powerpc/boot/dts/holly.dts
index f87fe7b..c6e11eb 100644
--- a/arch/powerpc/boot/dts/holly.dts
+++ b/arch/powerpc/boot/dts/holly.dts
@@ -133,61 +133,61 @@
 			reg = <0x00007400 0x00000400>;
 			big-endian;
 		};
+	};
 
-		pci@1000 {
-			device_type = "pci";
-			compatible = "tsi109-pci", "tsi108-pci";
-			#interrupt-cells = <1>;
-			#size-cells = <2>;
-			#address-cells = <3>;
-			reg = <0x00001000 0x00001000>;
-			bus-range = <0x0 0x0>;
-			/*----------------------------------------------------+
-			| PCI memory range.
-			| 01 denotes I/O space
-			| 02 denotes 32-bit memory space
-			+----------------------------------------------------*/
-			ranges = <0x02000000 0x00000000 0x40000000 0x40000000 0x00000000 0x10000000
-				  0x01000000 0x00000000 0x00000000 0x7e000000 0x00000000 0x00010000>;
-			clock-frequency = <133333332>;
-			interrupt-parent = <&MPIC>;
+	pci@c0001000 {
+		device_type = "pci";
+		compatible = "tsi109-pci", "tsi108-pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0xc0001000 0x00001000>;
+		bus-range = <0x0 0x0>;
+		/*----------------------------------------------------+
+		| PCI memory range.
+		| 01 denotes I/O space
+		| 02 denotes 32-bit memory space
+		+----------------------------------------------------*/
+		ranges = <0x02000000 0x00000000 0x40000000 0x40000000 0x00000000 0x10000000
+			  0x01000000 0x00000000 0x00000000 0x7e000000 0x00000000 0x00010000>;
+		clock-frequency = <133333332>;
+		interrupt-parent = <&MPIC>;
+		interrupts = <0x17 0x2>;
+		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+		/*----------------------------------------------------+
+		| The INTA, INTB, INTC, INTD are shared.
+		+----------------------------------------------------*/
+		interrupt-map = <
+			0x800 0x0 0x0 0x1 &RT0 0x24 0x0
+			0x800 0x0 0x0 0x2 &RT0 0x25 0x0
+			0x800 0x0 0x0 0x3 &RT0 0x26 0x0
+			0x800 0x0 0x0 0x4 &RT0 0x27 0x0
+
+			0x1000 0x0 0x0 0x1 &RT0 0x25 0x0
+			0x1000 0x0 0x0 0x2 &RT0 0x26 0x0
+			0x1000 0x0 0x0 0x3 &RT0 0x27 0x0
+			0x1000 0x0 0x0 0x4 &RT0 0x24 0x0
+
+			0x1800 0x0 0x0 0x1 &RT0 0x26 0x0
+			0x1800 0x0 0x0 0x2 &RT0 0x27 0x0
+			0x1800 0x0 0x0 0x3 &RT0 0x24 0x0
+			0x1800 0x0 0x0 0x4 &RT0 0x25 0x0
+
+			0x2000 0x0 0x0 0x1 &RT0 0x27 0x0
+			0x2000 0x0 0x0 0x2 &RT0 0x24 0x0
+			0x2000 0x0 0x0 0x3 &RT0 0x25 0x0
+			0x2000 0x0 0x0 0x4 &RT0 0x26 0x0
+			>;
+
+		RT0: router@1180 {
+			device_type = "pic-router";
+			interrupt-controller;
+			big-endian;
+			clock-frequency = <0>;
+			#address-cells = <0>;
+			#interrupt-cells = <2>;
 			interrupts = <0x17 0x2>;
-			interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-			/*----------------------------------------------------+
-			| The INTA, INTB, INTC, INTD are shared.
-			+----------------------------------------------------*/
-			interrupt-map = <
-				0x800 0x0 0x0 0x1 &RT0 0x24 0x0
-				0x800 0x0 0x0 0x2 &RT0 0x25 0x0
-				0x800 0x0 0x0 0x3 &RT0 0x26 0x0
-				0x800 0x0 0x0 0x4 &RT0 0x27 0x0
-
-				0x1000 0x0 0x0 0x1 &RT0 0x25 0x0
-				0x1000 0x0 0x0 0x2 &RT0 0x26 0x0
-				0x1000 0x0 0x0 0x3 &RT0 0x27 0x0
-				0x1000 0x0 0x0 0x4 &RT0 0x24 0x0
-
-				0x1800 0x0 0x0 0x1 &RT0 0x26 0x0
-				0x1800 0x0 0x0 0x2 &RT0 0x27 0x0
-				0x1800 0x0 0x0 0x3 &RT0 0x24 0x0
-				0x1800 0x0 0x0 0x4 &RT0 0x25 0x0
-
-				0x2000 0x0 0x0 0x1 &RT0 0x27 0x0
-				0x2000 0x0 0x0 0x2 &RT0 0x24 0x0
-				0x2000 0x0 0x0 0x3 &RT0 0x25 0x0
-				0x2000 0x0 0x0 0x4 &RT0 0x26 0x0
-				>;
-
-			RT0: router@1180 {
- 				device_type = "pic-router";
- 				interrupt-controller;
- 				big-endian;
- 				clock-frequency = <0>;
- 				#address-cells = <0>;
- 				#interrupt-cells = <2>;
- 				interrupts = <0x17 0x2>;
-				interrupt-parent = <&MPIC>;
-			};
+			interrupt-parent = <&MPIC>;
 		};
 	};
 
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index d308a9f..31982d0 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -34,11 +34,7 @@
 #include <asm/smp.h>
 
 #ifdef CONFIG_HOTPLUG_CPU
-/* this is used for software suspend, and that shuts down
- * CPUs even while the system is still booting... */
-#define cpu_should_die()	(cpu_is_offline(smp_processor_id()) && \
-				   (system_state == SYSTEM_RUNNING     \
-				 || system_state == SYSTEM_BOOTING))
+#define cpu_should_die()	cpu_is_offline(smp_processor_id())
 #else
 #define cpu_should_die()	0
 #endif
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index b4fdf2f..fe8f71d 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -347,9 +347,8 @@
 			linux_regs->msr |= MSR_SE;
 #endif
 			kgdb_single_step = 1;
-			if (kgdb_contthread)
-				atomic_set(&kgdb_cpu_doing_single_step,
-					   raw_smp_processor_id());
+			atomic_set(&kgdb_cpu_doing_single_step,
+				   raw_smp_processor_id());
 		}
 		return 0;
 	}
diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c
index ef74a07..8c61996 100644
--- a/arch/powerpc/platforms/fsl_uli1575.c
+++ b/arch/powerpc/platforms/fsl_uli1575.c
@@ -219,11 +219,21 @@
 	int i;
 	u8 *dummy;
 	struct pci_bus *bus = dev->bus;
+	resource_size_t end = 0;
+
+	for (i = PCI_BRIDGE_RESOURCES; i < PCI_BRIDGE_RESOURCES+3; i++) {
+		unsigned long flags = pci_resource_flags(dev, i);
+		if ((flags & (IORESOURCE_MEM|IORESOURCE_PREFETCH)) == IORESOURCE_MEM)
+			end = pci_resource_end(dev, i);
+	}
 
 	for (i = 0; i < PCI_BUS_NUM_RESOURCES; i++) {
 		if ((bus->resource[i]) &&
 			(bus->resource[i]->flags & IORESOURCE_MEM)) {
-			dummy = ioremap(bus->resource[i]->end - 3, 0x4);
+			if (bus->resource[i]->end == end)
+				dummy = ioremap(bus->resource[i]->start, 0x4);
+			else
+				dummy = ioremap(bus->resource[i]->end - 3, 0x4);
 			if (dummy) {
 				in_8(dummy);
 				iounmap(dummy);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index ca114fe..06acb1a 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -169,6 +169,8 @@
 
 static void clock_comparator_interrupt(__u16 code)
 {
+	if (S390_lowcore.clock_comparator == -1ULL)
+		set_clock_comparator(S390_lowcore.clock_comparator);
 }
 
 static void etr_timing_alert(struct etr_irq_parm *);
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index fc6ab60..0953cee 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -1,14 +1,9 @@
 /*
- *  arch/s390/lib/delay.c
  *    Precise Delay Loops for S390
  *
- *  S390 version
- *    Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
- *
- *  Derived from "arch/i386/lib/delay.c"
- *    Copyright (C) 1993 Linus Torvalds
- *    Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *    Copyright IBM Corp. 1999,2008
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>,
  */
 
 #include <linux/sched.h>
@@ -29,30 +24,31 @@
 	asm volatile("0: brct %0,0b" : : "d" ((loops/2) + 1));
 }
 
-/*
- * Waits for 'usecs' microseconds using the TOD clock comparator.
- */
-void __udelay(unsigned long usecs)
+static void __udelay_disabled(unsigned long usecs)
 {
-	u64 end, time, old_cc = 0;
-	unsigned long flags, cr0, mask, dummy;
-	int irq_context;
+	unsigned long mask, cr0, cr0_saved;
+	u64 clock_saved;
 
-	irq_context = in_interrupt();
-	if (!irq_context)
-		local_bh_disable();
-	local_irq_save(flags);
-	if (raw_irqs_disabled_flags(flags)) {
-		old_cc = local_tick_disable();
-		S390_lowcore.clock_comparator = -1ULL;
-		__ctl_store(cr0, 0, 0);
-		dummy = (cr0 & 0xffff00e0) | 0x00000800;
-		__ctl_load(dummy , 0, 0);
-		mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT;
-	} else
-		mask = psw_kernel_bits | PSW_MASK_WAIT |
-			PSW_MASK_EXT | PSW_MASK_IO;
+	clock_saved = local_tick_disable();
+	set_clock_comparator(get_clock() + ((u64) usecs << 12));
+	__ctl_store(cr0_saved, 0, 0);
+	cr0 = (cr0_saved & 0xffff00e0) | 0x00000800;
+	__ctl_load(cr0 , 0, 0);
+	mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT;
+	trace_hardirqs_on();
+	__load_psw_mask(mask);
+	local_irq_disable();
+	__ctl_load(cr0_saved, 0, 0);
+	local_tick_enable(clock_saved);
+	set_clock_comparator(S390_lowcore.clock_comparator);
+}
 
+static void __udelay_enabled(unsigned long usecs)
+{
+	unsigned long mask;
+	u64 end, time;
+
+	mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT | PSW_MASK_IO;
 	end = get_clock() + ((u64) usecs << 12);
 	do {
 		time = end < S390_lowcore.clock_comparator ?
@@ -62,13 +58,37 @@
 		__load_psw_mask(mask);
 		local_irq_disable();
 	} while (get_clock() < end);
-
-	if (raw_irqs_disabled_flags(flags)) {
-		__ctl_load(cr0, 0, 0);
-		local_tick_enable(old_cc);
-	}
-	if (!irq_context)
-		_local_bh_enable();
 	set_clock_comparator(S390_lowcore.clock_comparator);
+}
+
+/*
+ * Waits for 'usecs' microseconds using the TOD clock comparator.
+ */
+void __udelay(unsigned long usecs)
+{
+	unsigned long flags;
+
+	preempt_disable();
+	local_irq_save(flags);
+	if (in_irq()) {
+		__udelay_disabled(usecs);
+		goto out;
+	}
+	if (in_softirq()) {
+		if (raw_irqs_disabled_flags(flags))
+			__udelay_disabled(usecs);
+		else
+			__udelay_enabled(usecs);
+		goto out;
+	}
+	if (raw_irqs_disabled_flags(flags)) {
+		local_bh_disable();
+		__udelay_disabled(usecs);
+		_local_bh_enable();
+		goto out;
+	}
+	__udelay_enabled(usecs);
+out:
 	local_irq_restore(flags);
+	preempt_enable();
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 09f6b7f..97f0d2b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -29,6 +29,7 @@
 	select HAVE_FTRACE
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
+	select HAVE_ARCH_TRACEHOOK
 	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 
@@ -1020,7 +1021,7 @@
 
 config ARCH_FLATMEM_ENABLE
 	def_bool y
-	depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && X86_PC && !NUMA
+	depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && !NUMA
 
 config ARCH_DISCONTIGMEM_ENABLE
 	def_bool y
@@ -1036,7 +1037,7 @@
 
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
-	depends on X86_64 || NUMA || (EXPERIMENTAL && X86_PC)
+	depends on X86_64 || NUMA || (EXPERIMENTAL && X86_PC) || X86_GENERICARCH
 	select SPARSEMEM_STATIC if X86_32
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
@@ -1117,7 +1118,7 @@
 	  You can safely say Y even if your machine doesn't have MTRRs, you'll
 	  just add about 9 KB to your kernel.
 
-	  See <file:Documentation/mtrr.txt> for more information.
+	  See <file:Documentation/x86/mtrr.txt> for more information.
 
 config MTRR_SANITIZER
 	def_bool y
@@ -1191,7 +1192,6 @@
 config SECCOMP
 	def_bool y
 	prompt "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
 	help
 	  This kernel feature is useful for number crunching applications
 	  that may need to compute untrusted bytecode during their
@@ -1199,7 +1199,7 @@
 	  the process as file descriptors supporting the read/write
 	  syscalls, it's possible to isolate those applications in
 	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
+	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
 	  and the task is only allowed to execute a few safe syscalls
 	  defined by each seccomp mode.
 
@@ -1356,14 +1356,14 @@
 	  Don't change this unless you know what you are doing.
 
 config HOTPLUG_CPU
-	bool "Support for suspend on SMP and hot-pluggable CPUs (EXPERIMENTAL)"
-	depends on SMP && HOTPLUG && EXPERIMENTAL && !X86_VOYAGER
+	bool "Support for hot-pluggable CPUs"
+	depends on SMP && HOTPLUG && !X86_VOYAGER
 	---help---
-	  Say Y here to experiment with turning CPUs off and on, and to
-	  enable suspend on SMP systems. CPUs can be controlled through
-	  /sys/devices/system/cpu.
-	  Say N if you want to disable CPU hotplug and don't need to
-	  suspend.
+	  Say Y here to allow turning CPUs off and on. CPUs can be
+	  controlled through /sys/devices/system/cpu.
+	  ( Note: power management support will enable this option
+	    automatically on SMP systems. )
+	  Say N if you want to disable CPU hotplug.
 
 config COMPAT_VDSO
 	def_bool y
@@ -1378,6 +1378,51 @@
 
 	  If unsure, say Y.
 
+config CMDLINE_BOOL
+	bool "Built-in kernel command line"
+	default n
+	help
+	  Allow for specifying boot arguments to the kernel at
+	  build time.  On some systems (e.g. embedded ones), it is
+	  necessary or convenient to provide some or all of the
+	  kernel boot arguments with the kernel itself (that is,
+	  to not rely on the boot loader to provide them.)
+
+	  To compile command line arguments into the kernel,
+	  set this option to 'Y', then fill in the
+	  the boot arguments in CONFIG_CMDLINE.
+
+	  Systems with fully functional boot loaders (i.e. non-embedded)
+	  should leave this option set to 'N'.
+
+config CMDLINE
+	string "Built-in kernel command string"
+	depends on CMDLINE_BOOL
+	default ""
+	help
+	  Enter arguments here that should be compiled into the kernel
+	  image and used at boot time.  If the boot loader provides a
+	  command line at boot time, it is appended to this string to
+	  form the full kernel command line, when the system boots.
+
+	  However, you can use the CONFIG_CMDLINE_OVERRIDE option to
+	  change this behavior.
+
+	  In most cases, the command line (whether built-in or provided
+	  by the boot loader) should specify the device for the root
+	  file system.
+
+config CMDLINE_OVERRIDE
+	bool "Built-in command line overrides boot loader arguments"
+	default n
+	depends on CMDLINE_BOOL
+	help
+	  Set this option to 'Y' to have the kernel ignore the boot loader
+	  command line, and use ONLY the built-in command line.
+
+	  This is used to work around broken boot loaders.  This should
+	  be set to 'N' under normal conditions.
+
 endmenu
 
 config ARCH_ENABLE_MEMORY_HOTPLUG
@@ -1773,7 +1818,7 @@
 
 config SYSVIPC_COMPAT
 	def_bool y
-	depends on X86_64 && COMPAT && SYSVIPC
+	depends on COMPAT && SYSVIPC
 
 endmenu
 
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index b225219..60a8576 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -418,3 +418,21 @@
 config X86_DEBUGCTLMSR
 	def_bool y
 	depends on !(MK6 || MWINCHIPC6 || MWINCHIP2 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386)
+
+config X86_DS
+	bool "Debug Store support"
+	default y
+	help
+	  Add support for Debug Store.
+	  This allows the kernel to provide a memory buffer to the hardware
+	  to store various profiling and tracing events.
+
+config X86_PTRACE_BTS
+	bool "ptrace interface to Branch Trace Store"
+	default y
+	depends on (X86_DS && X86_DEBUGCTLMSR)
+	help
+	  Add a ptrace interface to allow collecting an execution trace
+	  of the traced task.
+	  This collects control flow changes in a (cyclic) buffer and allows
+	  debuggers to fill in the gaps and show an execution trace of the debuggee.
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index ba7736c..29c5fbf 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -137,14 +137,15 @@
  */
 	movl output_len(%ebx), %eax
 	pushl %eax
+			# push arguments for decompress_kernel:
 	pushl %ebp	# output address
 	movl input_len(%ebx), %eax
 	pushl %eax	# input_len
 	leal input_data(%ebx), %eax
 	pushl %eax	# input_data
 	leal boot_heap(%ebx), %eax
-	pushl %eax	# heap area as third argument
-	pushl %esi	# real mode pointer as second arg
+	pushl %eax	# heap area
+	pushl %esi	# real mode pointer
 	call decompress_kernel
 	addl $20, %esp
 	popl %ecx
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 9fea737..5780d36 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -16,7 +16,7 @@
  */
 #undef CONFIG_PARAVIRT
 #ifdef CONFIG_X86_32
-#define _ASM_DESC_H_ 1
+#define ASM_X86__DESC_H 1
 #endif
 
 #ifdef CONFIG_X86_64
@@ -27,7 +27,7 @@
 #include <linux/linkage.h>
 #include <linux/screen_info.h>
 #include <linux/elf.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/page.h>
 #include <asm/boot.h>
 #include <asm/bootparam.h>
@@ -251,7 +251,7 @@
 				y--;
 			}
 		} else {
-			vidmem [(x + cols * y) * 2] = c;
+			vidmem[(x + cols * y) * 2] = c;
 			if (++x >= cols) {
 				x = 0;
 				if (++y >= lines) {
@@ -277,7 +277,8 @@
 	int i;
 	char *ss = s;
 
-	for (i = 0; i < n; i++) ss[i] = c;
+	for (i = 0; i < n; i++)
+		ss[i] = c;
 	return s;
 }
 
@@ -287,7 +288,8 @@
 	const char *s = src;
 	char *d = dest;
 
-	for (i = 0; i < n; i++) d[i] = s[i];
+	for (i = 0; i < n; i++)
+		d[i] = s[i];
 	return dest;
 }
 
diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c
index a1310c5..857e492 100644
--- a/arch/x86/boot/compressed/relocs.c
+++ b/arch/x86/boot/compressed/relocs.c
@@ -492,7 +492,7 @@
 			continue;
 		}
 		sh_symtab = sec_symtab->symtab;
-		sym_strtab = sec->link->strtab;
+		sym_strtab = sec_symtab->link->strtab;
 		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) {
 			Elf32_Rel *rel;
 			Elf32_Sym *sym;
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index af86e43..b993062 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -30,7 +30,6 @@
 SYSSIZE		= DEF_SYSSIZE		/* system size: # of 16-byte clicks */
 					/* to be loaded */
 ROOT_DEV	= 0			/* ROOT_DEV is now written by "build" */
-SWAP_DEV	= 0			/* SWAP_DEV is now written by "build" */
 
 #ifndef SVGA_MODE
 #define SVGA_MODE ASK_VGA
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 104275e..ef9a520 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.27-rc4
-# Mon Aug 25 15:04:00 2008
+# Linux kernel version: 2.6.27-rc5
+# Wed Sep  3 17:23:09 2008
 #
 # CONFIG_64BIT is not set
 CONFIG_X86_32=y
@@ -202,7 +202,7 @@
 # CONFIG_M586 is not set
 # CONFIG_M586TSC is not set
 # CONFIG_M586MMX is not set
-# CONFIG_M686 is not set
+CONFIG_M686=y
 # CONFIG_MPENTIUMII is not set
 # CONFIG_MPENTIUMIII is not set
 # CONFIG_MPENTIUMM is not set
@@ -221,13 +221,14 @@
 # CONFIG_MVIAC3_2 is not set
 # CONFIG_MVIAC7 is not set
 # CONFIG_MPSC is not set
-CONFIG_MCORE2=y
+# CONFIG_MCORE2 is not set
 # CONFIG_GENERIC_CPU is not set
 CONFIG_X86_GENERIC=y
 CONFIG_X86_CPU=y
 CONFIG_X86_CMPXCHG=y
 CONFIG_X86_L1_CACHE_SHIFT=7
 CONFIG_X86_XADD=y
+# CONFIG_X86_PPRO_FENCE is not set
 CONFIG_X86_WP_WORKS_OK=y
 CONFIG_X86_INVLPG=y
 CONFIG_X86_BSWAP=y
@@ -235,14 +236,15 @@
 CONFIG_X86_INTEL_USERCOPY=y
 CONFIG_X86_USE_PPRO_CHECKSUM=y
 CONFIG_X86_TSC=y
+CONFIG_X86_CMOV=y
 CONFIG_X86_MINIMUM_CPU_FAMILY=4
 CONFIG_X86_DEBUGCTLMSR=y
 CONFIG_HPET_TIMER=y
 CONFIG_HPET_EMULATE_RTC=y
 CONFIG_DMI=y
 # CONFIG_IOMMU_HELPER is not set
-CONFIG_NR_CPUS=4
-# CONFIG_SCHED_SMT is not set
+CONFIG_NR_CPUS=64
+CONFIG_SCHED_SMT=y
 CONFIG_SCHED_MC=y
 # CONFIG_PREEMPT_NONE is not set
 CONFIG_PREEMPT_VOLUNTARY=y
@@ -254,7 +256,8 @@
 # CONFIG_TOSHIBA is not set
 # CONFIG_I8K is not set
 CONFIG_X86_REBOOTFIXUPS=y
-# CONFIG_MICROCODE is not set
+CONFIG_MICROCODE=y
+CONFIG_MICROCODE_OLD_INTERFACE=y
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
 # CONFIG_NOHIGHMEM is not set
@@ -2115,7 +2118,7 @@
 CONFIG_DEFAULT_IO_DELAY_TYPE=0
 CONFIG_DEBUG_BOOT_PARAMS=y
 # CONFIG_CPA_DEBUG is not set
-# CONFIG_OPTIMIZE_INLINING is not set
+CONFIG_OPTIMIZE_INLINING=y
 
 #
 # Security options
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 678c8ac..e620ea6 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.27-rc4
-# Mon Aug 25 14:40:46 2008
+# Linux kernel version: 2.6.27-rc5
+# Wed Sep  3 17:13:39 2008
 #
 CONFIG_64BIT=y
 # CONFIG_X86_32 is not set
@@ -218,17 +218,14 @@
 # CONFIG_MVIAC3_2 is not set
 # CONFIG_MVIAC7 is not set
 # CONFIG_MPSC is not set
-CONFIG_MCORE2=y
-# CONFIG_GENERIC_CPU is not set
+# CONFIG_MCORE2 is not set
+CONFIG_GENERIC_CPU=y
 CONFIG_X86_CPU=y
-CONFIG_X86_L1_CACHE_BYTES=64
-CONFIG_X86_INTERNODE_CACHE_BYTES=64
+CONFIG_X86_L1_CACHE_BYTES=128
+CONFIG_X86_INTERNODE_CACHE_BYTES=128
 CONFIG_X86_CMPXCHG=y
-CONFIG_X86_L1_CACHE_SHIFT=6
+CONFIG_X86_L1_CACHE_SHIFT=7
 CONFIG_X86_WP_WORKS_OK=y
-CONFIG_X86_INTEL_USERCOPY=y
-CONFIG_X86_USE_PPRO_CHECKSUM=y
-CONFIG_X86_P6_NOP=y
 CONFIG_X86_TSC=y
 CONFIG_X86_CMPXCHG64=y
 CONFIG_X86_CMOV=y
@@ -243,9 +240,8 @@
 CONFIG_AMD_IOMMU=y
 CONFIG_SWIOTLB=y
 CONFIG_IOMMU_HELPER=y
-# CONFIG_MAXSMP is not set
-CONFIG_NR_CPUS=4
-# CONFIG_SCHED_SMT is not set
+CONFIG_NR_CPUS=64
+CONFIG_SCHED_SMT=y
 CONFIG_SCHED_MC=y
 # CONFIG_PREEMPT_NONE is not set
 CONFIG_PREEMPT_VOLUNTARY=y
@@ -254,7 +250,8 @@
 CONFIG_X86_IO_APIC=y
 # CONFIG_X86_MCE is not set
 # CONFIG_I8K is not set
-# CONFIG_MICROCODE is not set
+CONFIG_MICROCODE=y
+CONFIG_MICROCODE_OLD_INTERFACE=y
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
 CONFIG_NUMA=y
@@ -290,7 +287,7 @@
 CONFIG_VIRT_TO_BUS=y
 CONFIG_MTRR=y
 # CONFIG_MTRR_SANITIZER is not set
-# CONFIG_X86_PAT is not set
+CONFIG_X86_PAT=y
 CONFIG_EFI=y
 CONFIG_SECCOMP=y
 # CONFIG_HZ_100 is not set
@@ -2089,7 +2086,7 @@
 CONFIG_DEFAULT_IO_DELAY_TYPE=0
 CONFIG_DEBUG_BOOT_PARAMS=y
 # CONFIG_CPA_DEBUG is not set
-# CONFIG_OPTIMIZE_INLINING is not set
+CONFIG_OPTIMIZE_INLINING=y
 
 #
 # Security options
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index a0e1dbe..127ec3f 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -85,8 +85,10 @@
 	dump->regs.ax = regs->ax;
 	dump->regs.ds = current->thread.ds;
 	dump->regs.es = current->thread.es;
-	asm("movl %%fs,%0" : "=r" (fs)); dump->regs.fs = fs;
-	asm("movl %%gs,%0" : "=r" (gs)); dump->regs.gs = gs;
+	savesegment(fs, fs);
+	dump->regs.fs = fs;
+	savesegment(gs, gs);
+	dump->regs.gs = gs;
 	dump->regs.orig_ax = regs->orig_ax;
 	dump->regs.ip = regs->ip;
 	dump->regs.cs = regs->cs;
@@ -430,8 +432,9 @@
 	current->mm->start_stack =
 		(unsigned long)create_aout_tables((char __user *)bprm->p, bprm);
 	/* start thread */
-	asm volatile("movl %0,%%fs" :: "r" (0)); \
-	asm volatile("movl %0,%%es; movl %0,%%ds": :"r" (__USER32_DS));
+	loadsegment(fs, 0);
+	loadsegment(ds, __USER32_DS);
+	loadsegment(es, __USER32_DS);
 	load_gs_index(0);
 	(regs)->ip = ex.a_entry;
 	(regs)->sp = current->mm->start_stack;
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 20af4c7..f1a2ac7 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -206,7 +206,7 @@
 	{ unsigned int cur;						\
 	  unsigned short pre;						\
 	  err |= __get_user(pre, &sc->seg);				\
-	  asm volatile("movl %%" #seg ",%0" : "=r" (cur));		\
+	  savesegment(seg, cur);					\
 	  pre |= mask;							\
 	  if (pre != cur) loadsegment(seg, pre); }
 
@@ -235,7 +235,7 @@
 	 */
 	err |= __get_user(gs, &sc->gs);
 	gs |= 3;
-	asm("movl %%gs,%0" : "=r" (oldgs));
+	savesegment(gs, oldgs);
 	if (gs != oldgs)
 		load_gs_index(gs);
 
@@ -355,14 +355,13 @@
 {
 	int tmp, err = 0;
 
-	tmp = 0;
-	__asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp));
+	savesegment(gs, tmp);
 	err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
-	__asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp));
+	savesegment(fs, tmp);
 	err |= __put_user(tmp, (unsigned int __user *)&sc->fs);
-	__asm__("movl %%ds,%0" : "=r"(tmp): "0"(tmp));
+	savesegment(ds, tmp);
 	err |= __put_user(tmp, (unsigned int __user *)&sc->ds);
-	__asm__("movl %%es,%0" : "=r"(tmp): "0"(tmp));
+	savesegment(es, tmp);
 	err |= __put_user(tmp, (unsigned int __user *)&sc->es);
 
 	err |= __put_user((u32)regs->di, &sc->di);
@@ -498,8 +497,8 @@
 	regs->dx = 0;
 	regs->cx = 0;
 
-	asm volatile("movl %0,%%ds" :: "r" (__USER32_DS));
-	asm volatile("movl %0,%%es" :: "r" (__USER32_DS));
+	loadsegment(ds, __USER32_DS);
+	loadsegment(es, __USER32_DS);
 
 	regs->cs = __USER32_CS;
 	regs->ss = __USER32_DS;
@@ -591,8 +590,8 @@
 	regs->dx = (unsigned long) &frame->info;
 	regs->cx = (unsigned long) &frame->uc;
 
-	asm volatile("movl %0,%%ds" :: "r" (__USER32_DS));
-	asm volatile("movl %0,%%es" :: "r" (__USER32_DS));
+	loadsegment(ds, __USER32_DS);
+	loadsegment(es, __USER32_DS);
 
 	regs->cs = __USER32_CS;
 	regs->ss = __USER32_DS;
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index d3c6408..beda423 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -556,15 +556,6 @@
 	return ret;
 }
 
-/* These are here just in case some old ia32 binary calls it. */
-asmlinkage long sys32_pause(void)
-{
-	current->state = TASK_INTERRUPTIBLE;
-	schedule();
-	return -ERESTARTNOHAND;
-}
-
-
 #ifdef CONFIG_SYSCTL_SYSCALL
 struct sysctl_ia32 {
 	unsigned int	name;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index bfd10fd..e5032d7 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -58,7 +58,6 @@
 #ifdef	CONFIG_X86_64
 
 #include <asm/proto.h>
-#include <asm/genapic.h>
 
 #else				/* X86 */
 
@@ -97,8 +96,6 @@
 #warning ACPI uses CMPXCHG, i486 and later hardware
 #endif
 
-static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
-
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
    -------------------------------------------------------------------------- */
@@ -160,6 +157,8 @@
 struct acpi_mcfg_allocation *pci_mmcfg_config;
 int pci_mmcfg_config_num;
 
+static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
+
 static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg)
 {
 	if (!strcmp(mcfg->header.oem_id, "SGI"))
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 65a0c1b..fb04e49 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -231,25 +231,25 @@
 			continue;
 		if (*ptr > text_end)
 			continue;
-		text_poke(*ptr, ((unsigned char []){0xf0}), 1); /* add lock prefix */
+		/* turn DS segment override prefix into lock prefix */
+		text_poke(*ptr, ((unsigned char []){0xf0}), 1);
 	};
 }
 
 static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 {
 	u8 **ptr;
-	char insn[1];
 
 	if (noreplace_smp)
 		return;
 
-	add_nops(insn, 1);
 	for (ptr = start; ptr < end; ptr++) {
 		if (*ptr < text)
 			continue;
 		if (*ptr > text_end)
 			continue;
-		text_poke(*ptr, insn, 1);
+		/* turn lock prefix into DS segment override prefix */
+		text_poke(*ptr, ((unsigned char []){0x3E}), 1);
 	};
 }
 
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 44e2182..9a32b37 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -455,11 +455,11 @@
 		   force_iommu ||
 		   valid_agp ||
 		   fallback_aper_force) {
-		printk(KERN_ERR
+		printk(KERN_INFO
 			"Your BIOS doesn't leave a aperture memory hole\n");
-		printk(KERN_ERR
+		printk(KERN_INFO
 			"Please enable the IOMMU option in the BIOS setup\n");
-		printk(KERN_ERR
+		printk(KERN_INFO
 			"This costs you %d MB of RAM\n",
 				32 << fallback_aper_order);
 
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 9ee24e6..5145a6e 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -228,12 +228,12 @@
 #include <linux/suspend.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>
-#include <linux/smp_lock.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/desc.h>
 #include <asm/i8253.h>
+#include <asm/olpc.h>
 #include <asm/paravirt.h>
 #include <asm/reboot.h>
 
@@ -2217,7 +2217,7 @@
 
 	dmi_check_system(apm_dmi_table);
 
-	if (apm_info.bios.version == 0 || paravirt_enabled()) {
+	if (apm_info.bios.version == 0 || paravirt_enabled() || machine_is_olpc()) {
 		printk(KERN_INFO "apm: BIOS not found.\n");
 		return -ENODEV;
 	}
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index aa89387..505543a 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -22,7 +22,7 @@
 
 #define __NO_STUBS 1
 #undef __SYSCALL
-#undef _ASM_X86_64_UNISTD_H_
+#undef ASM_X86__UNISTD_64_H
 #define __SYSCALL(nr, sym) [nr] = 1,
 static char syscalls[] = {
 #include <asm/unistd.h>
diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c
index c639bd5..fdd585f 100644
--- a/arch/x86/kernel/bios_uv.c
+++ b/arch/x86/kernel/bios_uv.c
@@ -25,11 +25,11 @@
 {
 	const char *str;
 	switch (status) {
-	case  0: str = "Call completed without error"; break;
-	case -1: str = "Not implemented"; break;
-	case -2: str = "Invalid argument"; break;
-	case -3: str = "Call completed with error"; break;
-	default: str = "Unknown BIOS status code"; break;
+	case  0: str = "Call completed without error";	break;
+	case -1: str = "Not implemented";		break;
+	case -2: str = "Invalid argument";		break;
+	case -3: str = "Call completed with error";	break;
+	default: str = "Unknown BIOS status code";	break;
 	}
 	return str;
 }
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
index a11f5d4..305b465 100644
--- a/arch/x86/kernel/cpu/common_64.c
+++ b/arch/x86/kernel/cpu/common_64.c
@@ -430,6 +430,49 @@
 }
 __setup("noclflush", setup_noclflush);
 
+struct msr_range {
+	unsigned min;
+	unsigned max;
+};
+
+static struct msr_range msr_range_array[] __cpuinitdata = {
+	{ 0x00000000, 0x00000418},
+	{ 0xc0000000, 0xc000040b},
+	{ 0xc0010000, 0xc0010142},
+	{ 0xc0011000, 0xc001103b},
+};
+
+static void __cpuinit print_cpu_msr(void)
+{
+	unsigned index;
+	u64 val;
+	int i;
+	unsigned index_min, index_max;
+
+	for (i = 0; i < ARRAY_SIZE(msr_range_array); i++) {
+		index_min = msr_range_array[i].min;
+		index_max = msr_range_array[i].max;
+		for (index = index_min; index < index_max; index++) {
+			if (rdmsrl_amd_safe(index, &val))
+				continue;
+			printk(KERN_INFO " MSR%08x: %016llx\n", index, val);
+		}
+	}
+}
+
+static int show_msr __cpuinitdata;
+static __init int setup_show_msr(char *arg)
+{
+	int num;
+
+	get_option(&arg, &num);
+
+	if (num > 0)
+		show_msr = num;
+	return 1;
+}
+__setup("show_msr=", setup_show_msr);
+
 void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
 {
 	if (c->x86_model_id[0])
@@ -439,6 +482,14 @@
 		printk(KERN_CONT " stepping %02x\n", c->x86_mask);
 	else
 		printk(KERN_CONT "\n");
+
+#ifdef CONFIG_SMP
+	if (c->cpu_index < show_msr)
+		print_cpu_msr();
+#else
+	if (show_msr)
+		print_cpu_msr();
+#endif
 }
 
 static __init int setup_disablecpuid(char *arg)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b75f256..f113ef4 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -222,10 +222,11 @@
 			set_cpu_cap(c, X86_FEATURE_BTS);
 		if (!(l1 & (1<<12)))
 			set_cpu_cap(c, X86_FEATURE_PEBS);
+		ds_init_intel(c);
 	}
 
 	if (cpu_has_bts)
-		ds_init_intel(c);
+		ptrace_bts_init_intel(c);
 
 	/*
 	 * See if we have a good local APIC by checking for buggy Pentia,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index cb7d3b6..4e8d77f 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -401,12 +401,7 @@
 		tmp |= ~((1<<(hi - 1)) - 1);
 
 		if (tmp != mask_lo) {
-			static int once = 1;
-
-			if (once) {
-				printk(KERN_INFO "mtrr: your BIOS has set up an incorrect mask, fixing it up.\n");
-				once = 0;
-			}
+			WARN_ONCE(1, KERN_INFO "mtrr: your BIOS has set up an incorrect mask, fixing it up.\n");
 			mask_lo = tmp;
 		}
 	}
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 5994a9f..c78c048 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -729,7 +729,7 @@
 	mtrr_type type;
 };
 
-struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
+static struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
 static int __initdata debug_print;
 
 static int __init
@@ -835,7 +835,7 @@
 		enable_mtrr_cleanup = 1;
 	return 0;
 }
-early_param("enble_mtrr_cleanup", enable_mtrr_cleanup_setup);
+early_param("enable_mtrr_cleanup", enable_mtrr_cleanup_setup);
 
 static int __init mtrr_cleanup_debug_setup(char *str)
 {
@@ -1289,11 +1289,10 @@
 
 	memset(range, 0, sizeof(range));
 	extra_remove_size = 0;
-	if (mtrr_tom2) {
-		extra_remove_base = 1 << (32 - PAGE_SHIFT);
+	extra_remove_base = 1 << (32 - PAGE_SHIFT);
+	if (mtrr_tom2)
 		extra_remove_size =
 			(mtrr_tom2 >> PAGE_SHIFT) - extra_remove_base;
-	}
 	nr_range = x86_get_mtrr_mem_range(range, 0, extra_remove_base,
 					  extra_remove_size);
 	/*
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 05cc22d..6bff382 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -295,13 +295,19 @@
 	/* setup the timer */
 	wrmsr(evntsel_msr, evntsel, 0);
 	write_watchdog_counter(perfctr_msr, "K7_PERFCTR0",nmi_hz);
+
+	/* initialize the wd struct before enabling */
+	wd->perfctr_msr = perfctr_msr;
+	wd->evntsel_msr = evntsel_msr;
+	wd->cccr_msr = 0;  /* unused */
+
+	/* ok, everything is initialized, announce that we're set */
+	cpu_nmi_set_wd_enabled();
+
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 	evntsel |= K7_EVNTSEL_ENABLE;
 	wrmsr(evntsel_msr, evntsel, 0);
 
-	wd->perfctr_msr = perfctr_msr;
-	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = 0;  /* unused */
 	return 1;
 }
 
@@ -379,13 +385,19 @@
 	wrmsr(evntsel_msr, evntsel, 0);
 	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
 	write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0",nmi_hz);
+
+	/* initialize the wd struct before enabling */
+	wd->perfctr_msr = perfctr_msr;
+	wd->evntsel_msr = evntsel_msr;
+	wd->cccr_msr = 0;  /* unused */
+
+	/* ok, everything is initialized, announce that we're set */
+	cpu_nmi_set_wd_enabled();
+
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 	evntsel |= P6_EVNTSEL0_ENABLE;
 	wrmsr(evntsel_msr, evntsel, 0);
 
-	wd->perfctr_msr = perfctr_msr;
-	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = 0;  /* unused */
 	return 1;
 }
 
@@ -432,6 +444,27 @@
 #define P4_CCCR_ENABLE		(1 << 12)
 #define P4_CCCR_OVF 		(1 << 31)
 
+#define P4_CONTROLS 18
+static unsigned int p4_controls[18] = {
+	MSR_P4_BPU_CCCR0,
+	MSR_P4_BPU_CCCR1,
+	MSR_P4_BPU_CCCR2,
+	MSR_P4_BPU_CCCR3,
+	MSR_P4_MS_CCCR0,
+	MSR_P4_MS_CCCR1,
+	MSR_P4_MS_CCCR2,
+	MSR_P4_MS_CCCR3,
+	MSR_P4_FLAME_CCCR0,
+	MSR_P4_FLAME_CCCR1,
+	MSR_P4_FLAME_CCCR2,
+	MSR_P4_FLAME_CCCR3,
+	MSR_P4_IQ_CCCR0,
+	MSR_P4_IQ_CCCR1,
+	MSR_P4_IQ_CCCR2,
+	MSR_P4_IQ_CCCR3,
+	MSR_P4_IQ_CCCR4,
+	MSR_P4_IQ_CCCR5,
+};
 /*
  * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter
  * CRU_ESCR0 (with any non-null event selector) through a complemented
@@ -473,6 +506,26 @@
 		evntsel_msr = MSR_P4_CRU_ESCR0;
 		cccr_msr = MSR_P4_IQ_CCCR0;
 		cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4);
+
+		/*
+		 * If we're on the kdump kernel or other situation, we may
+		 * still have other performance counter registers set to
+		 * interrupt and they'll keep interrupting forever because
+		 * of the P4_CCCR_OVF quirk. So we need to ACK all the
+		 * pending interrupts and disable all the registers here,
+		 * before reenabling the NMI delivery. Refer to p4_rearm()
+		 * about the P4_CCCR_OVF quirk.
+		 */
+		if (reset_devices) {
+			unsigned int low, high;
+			int i;
+
+			for (i = 0; i < P4_CONTROLS; i++) {
+				rdmsr(p4_controls[i], low, high);
+				low &= ~(P4_CCCR_ENABLE | P4_CCCR_OVF);
+				wrmsr(p4_controls[i], low, high);
+			}
+		}
 	} else {
 		/* logical cpu 1 */
 		perfctr_msr = MSR_P4_IQ_PERFCTR1;
@@ -499,12 +552,17 @@
 	wrmsr(evntsel_msr, evntsel, 0);
 	wrmsr(cccr_msr, cccr_val, 0);
 	write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0", nmi_hz);
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	cccr_val |= P4_CCCR_ENABLE;
-	wrmsr(cccr_msr, cccr_val, 0);
+
 	wd->perfctr_msr = perfctr_msr;
 	wd->evntsel_msr = evntsel_msr;
 	wd->cccr_msr = cccr_msr;
+
+	/* ok, everything is initialized, announce that we're set */
+	cpu_nmi_set_wd_enabled();
+
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	cccr_val |= P4_CCCR_ENABLE;
+	wrmsr(cccr_msr, cccr_val, 0);
 	return 1;
 }
 
@@ -620,13 +678,17 @@
 	wrmsr(evntsel_msr, evntsel, 0);
 	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
 	write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0", nmi_hz);
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
-	wrmsr(evntsel_msr, evntsel, 0);
 
 	wd->perfctr_msr = perfctr_msr;
 	wd->evntsel_msr = evntsel_msr;
 	wd->cccr_msr = 0;  /* unused */
+
+	/* ok, everything is initialized, announce that we're set */
+	cpu_nmi_set_wd_enabled();
+
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+	wrmsr(evntsel_msr, evntsel, 0);
 	intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
 	return 1;
 }
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 8e9cd6a..6a44d64 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -36,7 +36,6 @@
 #include <linux/smp_lock.h>
 #include <linux/major.h>
 #include <linux/fs.h>
-#include <linux/smp_lock.h>
 #include <linux/device.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 15e6c6b..e90a60e 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -7,9 +7,8 @@
 
 #include <linux/errno.h>
 #include <linux/crash_dump.h>
-
-#include <asm/uaccess.h>
-#include <asm/io.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
 
 /**
  * copy_oldmem_page - copy one page from "oldmem"
@@ -25,7 +24,7 @@
  * in the current kernel. We stitch up a pte, similar to kmap_atomic.
  */
 ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-                               size_t csize, unsigned long offset, int userbuf)
+		size_t csize, unsigned long offset, int userbuf)
 {
 	void  *vaddr;
 
@@ -33,14 +32,16 @@
 		return 0;
 
 	vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+	if (!vaddr)
+		return -ENOMEM;
 
 	if (userbuf) {
-		if (copy_to_user(buf, (vaddr + offset), csize)) {
+		if (copy_to_user(buf, vaddr + offset, csize)) {
 			iounmap(vaddr);
 			return -EFAULT;
 		}
 	} else
-	memcpy(buf, (vaddr + offset), csize);
+		memcpy(buf, vaddr + offset, csize);
 
 	iounmap(vaddr);
 	return csize;
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index 11c11b8..2b69994 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -2,26 +2,49 @@
  * Debug Store support
  *
  * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for last branch recording (LBR) and
+ * feature that is used for branch trace store (BTS) and
  * precise-event based sampling (PEBS).
  *
- * Different architectures use a different DS layout/pointer size.
- * The below functions therefore work on a void*.
+ * It manages:
+ * - per-thread and per-cpu allocation of BTS and PEBS
+ * - buffer memory allocation (optional)
+ * - buffer overflow handling
+ * - buffer access
+ *
+ * It assumes:
+ * - get_task_struct on all parameter tasks
+ * - current is allowed to trace parameter tasks
  *
  *
- * Since there is no user for PEBS, yet, only LBR (or branch
- * trace store, BTS) is supported.
- *
- *
- * Copyright (C) 2007 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, Dec 2007
+ * Copyright (C) 2007-2008 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
  */
 
+
+#ifdef CONFIG_X86_DS
+
 #include <asm/ds.h>
 
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+
+
+/*
+ * The configuration for a particular DS hardware implementation.
+ */
+struct ds_configuration {
+	/* the size of the DS structure in bytes */
+	unsigned char  sizeof_ds;
+	/* the size of one pointer-typed field in the DS structure in bytes;
+	   this covers the first 8 fields related to buffer management. */
+	unsigned char  sizeof_field;
+	/* the size of a BTS/PEBS record in bytes */
+	unsigned char  sizeof_rec[2];
+};
+static struct ds_configuration ds_cfg;
 
 
 /*
@@ -44,378 +67,747 @@
  *   (interrupt occurs when write pointer passes interrupt pointer)
  * - value to which counter is reset following counter overflow
  *
- * On later architectures, the last branch recording hardware uses
- * 64bit pointers even in 32bit mode.
+ * Later architectures use 64bit pointers throughout, whereas earlier
+ * architectures use 32bit pointers in 32bit mode.
  *
  *
- * Branch Trace Store (BTS) records store information about control
- * flow changes. They at least provide the following information:
- * - source linear address
- * - destination linear address
+ * 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
  *
- * Netburst supported a predicated bit that had been dropped in later
- * architectures. We do not suppor it.
+ * This offset is further used to index various arrays holding
+ * information for BTS and PEBS at the respective index.
  *
- *
- * In order to abstract from the actual DS and BTS layout, we describe
- * the access to the relevant fields.
- * Thanks to Andi Kleen for proposing this design.
- *
- * The implementation, however, is not as general as it might seem. In
- * order to stay somewhat simple and efficient, we assume an
- * underlying unsigned type (mostly a pointer type) and we expect the
- * field to be at least as big as that type.
+ * On later 32bit processors, we only access the lower 32bit of the
+ * 64bit pointer fields. The upper halves will be zeroed out.
  */
 
-/*
- * A special from_ip address to indicate that the BTS record is an
- * info record that needs to be interpreted or skipped.
- */
-#define BTS_ESCAPE_ADDRESS (-1)
-
-/*
- * A field access descriptor
- */
-struct access_desc {
-	unsigned char offset;
-	unsigned char size;
+enum ds_field {
+	ds_buffer_base = 0,
+	ds_index,
+	ds_absolute_maximum,
+	ds_interrupt_threshold,
 };
 
-/*
- * The configuration for a particular DS/BTS hardware implementation.
- */
-struct ds_configuration {
-	/* the DS configuration */
-	unsigned char  sizeof_ds;
-	struct access_desc bts_buffer_base;
-	struct access_desc bts_index;
-	struct access_desc bts_absolute_maximum;
-	struct access_desc bts_interrupt_threshold;
-	/* the BTS configuration */
-	unsigned char  sizeof_bts;
-	struct access_desc from_ip;
-	struct access_desc to_ip;
-	/* BTS variants used to store additional information like
-	   timestamps */
-	struct access_desc info_type;
-	struct access_desc info_data;
-	unsigned long debugctl_mask;
+enum ds_qualifier {
+	ds_bts  = 0,
+	ds_pebs
 };
 
-/*
- * The global configuration used by the below accessor functions
- */
-static struct ds_configuration ds_cfg;
+static inline unsigned long ds_get(const unsigned char *base,
+				   enum ds_qualifier qual, enum ds_field field)
+{
+	base += (ds_cfg.sizeof_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_field * (field + (4 * qual)));
+	(*(unsigned long *)base) = value;
+}
+
 
 /*
- * Accessor functions for some DS and BTS fields using the above
- * global ptrace_bts_cfg.
+ * Locking is done only for allocating BTS or PEBS resources and for
+ * guarding context and buffer memory allocation.
+ *
+ * Most functions require the current task to own the ds context part
+ * they are going to access. All the locking is done when validating
+ * access to the context.
  */
-static inline unsigned long get_bts_buffer_base(char *base)
-{
-	return *(unsigned long *)(base + ds_cfg.bts_buffer_base.offset);
-}
-static inline void set_bts_buffer_base(char *base, unsigned long value)
-{
-	(*(unsigned long *)(base + ds_cfg.bts_buffer_base.offset)) = value;
-}
-static inline unsigned long get_bts_index(char *base)
-{
-	return *(unsigned long *)(base + ds_cfg.bts_index.offset);
-}
-static inline void set_bts_index(char *base, unsigned long value)
-{
-	(*(unsigned long *)(base + ds_cfg.bts_index.offset)) = value;
-}
-static inline unsigned long get_bts_absolute_maximum(char *base)
-{
-	return *(unsigned long *)(base + ds_cfg.bts_absolute_maximum.offset);
-}
-static inline void set_bts_absolute_maximum(char *base, unsigned long value)
-{
-	(*(unsigned long *)(base + ds_cfg.bts_absolute_maximum.offset)) = value;
-}
-static inline unsigned long get_bts_interrupt_threshold(char *base)
-{
-	return *(unsigned long *)(base + ds_cfg.bts_interrupt_threshold.offset);
-}
-static inline void set_bts_interrupt_threshold(char *base, unsigned long value)
-{
-	(*(unsigned long *)(base + ds_cfg.bts_interrupt_threshold.offset)) = value;
-}
-static inline unsigned long get_from_ip(char *base)
-{
-	return *(unsigned long *)(base + ds_cfg.from_ip.offset);
-}
-static inline void set_from_ip(char *base, unsigned long value)
-{
-	(*(unsigned long *)(base + ds_cfg.from_ip.offset)) = value;
-}
-static inline unsigned long get_to_ip(char *base)
-{
-	return *(unsigned long *)(base + ds_cfg.to_ip.offset);
-}
-static inline void set_to_ip(char *base, unsigned long value)
-{
-	(*(unsigned long *)(base + ds_cfg.to_ip.offset)) = value;
-}
-static inline unsigned char get_info_type(char *base)
-{
-	return *(unsigned char *)(base + ds_cfg.info_type.offset);
-}
-static inline void set_info_type(char *base, unsigned char value)
-{
-	(*(unsigned char *)(base + ds_cfg.info_type.offset)) = value;
-}
-static inline unsigned long get_info_data(char *base)
-{
-	return *(unsigned long *)(base + ds_cfg.info_data.offset);
-}
-static inline void set_info_data(char *base, unsigned long value)
-{
-	(*(unsigned long *)(base + ds_cfg.info_data.offset)) = value;
-}
+static spinlock_t ds_lock = __SPIN_LOCK_UNLOCKED(ds_lock);
 
-
-int ds_allocate(void **dsp, size_t bts_size_in_bytes)
+/*
+ * Validate that the current task is allowed to access the BTS/PEBS
+ * buffer of the parameter task.
+ *
+ * Returns 0, if access is granted; -Eerrno, otherwise.
+ */
+static inline int ds_validate_access(struct ds_context *context,
+				     enum ds_qualifier qual)
 {
-	size_t bts_size_in_records;
-	unsigned long bts;
-	void *ds;
+	if (!context)
+		return -EPERM;
 
-	if (!ds_cfg.sizeof_ds || !ds_cfg.sizeof_bts)
-		return -EOPNOTSUPP;
-
-	if (bts_size_in_bytes < 0)
-		return -EINVAL;
-
-	bts_size_in_records =
-		bts_size_in_bytes / ds_cfg.sizeof_bts;
-	bts_size_in_bytes =
-		bts_size_in_records * ds_cfg.sizeof_bts;
-
-	if (bts_size_in_bytes <= 0)
-		return -EINVAL;
-
-	bts = (unsigned long)kzalloc(bts_size_in_bytes, GFP_KERNEL);
-
-	if (!bts)
-		return -ENOMEM;
-
-	ds = kzalloc(ds_cfg.sizeof_ds, GFP_KERNEL);
-
-	if (!ds) {
-		kfree((void *)bts);
-		return -ENOMEM;
-	}
-
-	set_bts_buffer_base(ds, bts);
-	set_bts_index(ds, bts);
-	set_bts_absolute_maximum(ds, bts + bts_size_in_bytes);
-	set_bts_interrupt_threshold(ds, bts + bts_size_in_bytes + 1);
-
-	*dsp = ds;
-	return 0;
-}
-
-int ds_free(void **dsp)
-{
-	if (*dsp) {
-		kfree((void *)get_bts_buffer_base(*dsp));
-		kfree(*dsp);
-		*dsp = NULL;
-	}
-	return 0;
-}
-
-int ds_get_bts_size(void *ds)
-{
-	int size_in_bytes;
-
-	if (!ds_cfg.sizeof_ds || !ds_cfg.sizeof_bts)
-		return -EOPNOTSUPP;
-
-	if (!ds)
+	if (context->owner[qual] == current)
 		return 0;
 
-	size_in_bytes =
-		get_bts_absolute_maximum(ds) -
-		get_bts_buffer_base(ds);
-	return size_in_bytes;
+	return -EPERM;
 }
 
-int ds_get_bts_end(void *ds)
+
+/*
+ * 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
+ *
+ * The below functions to get and put tracers and to check the
+ * allocation type require the ds_lock to be held by the caller.
+ *
+ * Tracers essentially gives the number of ds contexts for a certain
+ * type of allocation.
+ */
+static long tracers;
+
+static inline void get_tracer(struct task_struct *task)
 {
-	int size_in_bytes = ds_get_bts_size(ds);
-
-	if (size_in_bytes <= 0)
-		return size_in_bytes;
-
-	return size_in_bytes / ds_cfg.sizeof_bts;
+	tracers += (task ? 1 : -1);
 }
 
-int ds_get_bts_index(void *ds)
+static inline void put_tracer(struct task_struct *task)
 {
-	int index_offset_in_bytes;
-
-	if (!ds_cfg.sizeof_ds || !ds_cfg.sizeof_bts)
-		return -EOPNOTSUPP;
-
-	index_offset_in_bytes =
-		get_bts_index(ds) -
-		get_bts_buffer_base(ds);
-
-	return index_offset_in_bytes / ds_cfg.sizeof_bts;
+	tracers -= (task ? 1 : -1);
 }
 
-int ds_set_overflow(void *ds, int method)
+static inline int check_tracer(struct task_struct *task)
 {
-	switch (method) {
-	case DS_O_SIGNAL:
-		return -EOPNOTSUPP;
-	case DS_O_WRAP:
-		return 0;
-	default:
-		return -EINVAL;
-	}
+	return (task ? (tracers >= 0) : (tracers <= 0));
 }
 
-int ds_get_overflow(void *ds)
+
+/*
+ * 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.
+ *
+ * We distinguish between an allocating and a non-allocating get of a
+ * context:
+ * - the allocating get is used for requesting BTS/PEBS resources. It
+ *   requires the caller to hold the global ds_lock.
+ * - the non-allocating get is used for all other cases. A
+ *   non-existing context indicates an error. It acquires and releases
+ *   the ds_lock itself for obtaining the context.
+ *
+ * A context and its DS configuration are allocated and deallocated
+ * together. A context always has a DS configuration of the
+ * appropriate size.
+ */
+static DEFINE_PER_CPU(struct ds_context *, system_context);
+
+#define this_system_context per_cpu(system_context, smp_processor_id())
+
+/*
+ * Returns the pointer to the parameter task's context or to the
+ * system-wide context, if task is NULL.
+ *
+ * Increases the use count of the returned context, if not NULL.
+ */
+static inline struct ds_context *ds_get_context(struct task_struct *task)
 {
-	return DS_O_WRAP;
+	struct ds_context *context;
+
+	spin_lock(&ds_lock);
+
+	context = (task ? task->thread.ds_ctx : this_system_context);
+	if (context)
+		context->count++;
+
+	spin_unlock(&ds_lock);
+
+	return context;
 }
 
-int ds_clear(void *ds)
+/*
+ * Same as ds_get_context, but allocates the context and it's DS
+ * structure, if necessary; returns NULL; if out of memory.
+ *
+ * pre: requires ds_lock to be held
+ */
+static inline struct ds_context *ds_alloc_context(struct task_struct *task)
 {
-	int bts_size = ds_get_bts_size(ds);
-	unsigned long bts_base;
+	struct ds_context **p_context =
+		(task ? &task->thread.ds_ctx : &this_system_context);
+	struct ds_context *context = *p_context;
 
-	if (bts_size <= 0)
-		return bts_size;
+	if (!context) {
+		context = kzalloc(sizeof(*context), GFP_KERNEL);
 
-	bts_base = get_bts_buffer_base(ds);
-	memset((void *)bts_base, 0, bts_size);
+		if (!context)
+			return NULL;
 
-	set_bts_index(ds, bts_base);
-	return 0;
-}
+		context->ds = kzalloc(ds_cfg.sizeof_ds, GFP_KERNEL);
+		if (!context->ds) {
+			kfree(context);
+			return NULL;
+		}
 
-int ds_read_bts(void *ds, int index, struct bts_struct *out)
-{
-	void *bts;
+		*p_context = context;
 
-	if (!ds_cfg.sizeof_ds || !ds_cfg.sizeof_bts)
-		return -EOPNOTSUPP;
+		context->this = p_context;
+		context->task = task;
 
-	if (index < 0)
-		return -EINVAL;
+		if (task)
+			set_tsk_thread_flag(task, TIF_DS_AREA_MSR);
 
-	if (index >= ds_get_bts_size(ds))
-		return -EINVAL;
+		if (!task || (task == current))
+			wrmsr(MSR_IA32_DS_AREA, (unsigned long)context->ds, 0);
 
-	bts = (void *)(get_bts_buffer_base(ds) + (index * ds_cfg.sizeof_bts));
-
-	memset(out, 0, sizeof(*out));
-	if (get_from_ip(bts) == BTS_ESCAPE_ADDRESS) {
-		out->qualifier       = get_info_type(bts);
-		out->variant.jiffies = get_info_data(bts);
-	} else {
-		out->qualifier = BTS_BRANCH;
-		out->variant.lbr.from_ip = get_from_ip(bts);
-		out->variant.lbr.to_ip   = get_to_ip(bts);
+		get_tracer(task);
 	}
 
-	return sizeof(*out);;
+	context->count++;
+
+	return context;
 }
 
-int ds_write_bts(void *ds, const struct bts_struct *in)
+/*
+ * Decreases the use count of the parameter context, if not NULL.
+ * Deallocates the context, if the use count reaches zero.
+ */
+static inline void ds_put_context(struct ds_context *context)
 {
-	unsigned long bts;
+	if (!context)
+		return;
 
-	if (!ds_cfg.sizeof_ds || !ds_cfg.sizeof_bts)
+	spin_lock(&ds_lock);
+
+	if (--context->count)
+		goto out;
+
+	*(context->this) = NULL;
+
+	if (context->task)
+		clear_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
+
+	if (!context->task || (context->task == current))
+		wrmsrl(MSR_IA32_DS_AREA, 0);
+
+	put_tracer(context->task);
+
+	/* free any leftover buffers from tracers that did not
+	 * deallocate them properly. */
+	kfree(context->buffer[ds_bts]);
+	kfree(context->buffer[ds_pebs]);
+	kfree(context->ds);
+	kfree(context);
+ out:
+	spin_unlock(&ds_lock);
+}
+
+
+/*
+ * Handle a buffer overflow
+ *
+ * task: the task whose buffers are overflowing;
+ *       NULL for a buffer overflow on the current cpu
+ * context: the ds context
+ * qual: the buffer type
+ */
+static void ds_overflow(struct task_struct *task, struct ds_context *context,
+			enum ds_qualifier qual)
+{
+	if (!context)
+		return;
+
+	if (context->callback[qual])
+		(*context->callback[qual])(task);
+
+	/* todo: do some more overflow handling */
+}
+
+
+/*
+ * Allocate a non-pageable buffer of the parameter size.
+ * Checks the memory and the locked memory rlimit.
+ *
+ * Returns the buffer, if successful;
+ *         NULL, if out of memory or rlimit exceeded.
+ *
+ * size: the requested buffer size in bytes
+ * pages (out): if not NULL, contains the number of pages reserved
+ */
+static inline void *ds_allocate_buffer(size_t size, unsigned int *pages)
+{
+	unsigned long rlim, vm, pgsz;
+	void *buffer;
+
+	pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+	vm   = current->mm->total_vm  + pgsz;
+	if (rlim < vm)
+		return NULL;
+
+	rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+	vm   = current->mm->locked_vm  + pgsz;
+	if (rlim < vm)
+		return NULL;
+
+	buffer = kzalloc(size, GFP_KERNEL);
+	if (!buffer)
+		return NULL;
+
+	current->mm->total_vm  += pgsz;
+	current->mm->locked_vm += pgsz;
+
+	if (pages)
+		*pages = pgsz;
+
+	return buffer;
+}
+
+static int ds_request(struct task_struct *task, void *base, size_t size,
+		      ds_ovfl_callback_t ovfl, enum ds_qualifier qual)
+{
+	struct ds_context *context;
+	unsigned long buffer, adj;
+	const unsigned long alignment = (1 << 3);
+	int error = 0;
+
+	if (!ds_cfg.sizeof_ds)
 		return -EOPNOTSUPP;
 
-	if (ds_get_bts_size(ds) <= 0)
-		return -ENXIO;
-
-	bts = get_bts_index(ds);
-
-	memset((void *)bts, 0, ds_cfg.sizeof_bts);
-	switch (in->qualifier) {
-	case BTS_INVALID:
-		break;
-
-	case BTS_BRANCH:
-		set_from_ip((void *)bts, in->variant.lbr.from_ip);
-		set_to_ip((void *)bts, in->variant.lbr.to_ip);
-		break;
-
-	case BTS_TASK_ARRIVES:
-	case BTS_TASK_DEPARTS:
-		set_from_ip((void *)bts, BTS_ESCAPE_ADDRESS);
-		set_info_type((void *)bts, in->qualifier);
-		set_info_data((void *)bts, in->variant.jiffies);
-		break;
-
-	default:
+	/* we require some space to do alignment adjustments below */
+	if (size < (alignment + ds_cfg.sizeof_rec[qual]))
 		return -EINVAL;
+
+	/* buffer overflow notification is not yet implemented */
+	if (ovfl)
+		return -EOPNOTSUPP;
+
+
+	spin_lock(&ds_lock);
+
+	if (!check_tracer(task))
+		return -EPERM;
+
+	error = -ENOMEM;
+	context = ds_alloc_context(task);
+	if (!context)
+		goto out_unlock;
+
+	error = -EALREADY;
+	if (context->owner[qual] == current)
+		goto out_unlock;
+	error = -EPERM;
+	if (context->owner[qual] != NULL)
+		goto out_unlock;
+	context->owner[qual] = current;
+
+	spin_unlock(&ds_lock);
+
+
+	error = -ENOMEM;
+	if (!base) {
+		base = ds_allocate_buffer(size, &context->pages[qual]);
+		if (!base)
+			goto out_release;
+
+		context->buffer[qual]   = base;
+	}
+	error = 0;
+
+	context->callback[qual] = ovfl;
+
+	/* 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, alignment) - buffer;
+	buffer += adj;
+	size   -= adj;
+
+	size /= ds_cfg.sizeof_rec[qual];
+	size *= ds_cfg.sizeof_rec[qual];
+
+	ds_set(context->ds, qual, ds_buffer_base, buffer);
+	ds_set(context->ds, qual, ds_index, buffer);
+	ds_set(context->ds, qual, ds_absolute_maximum, buffer + size);
+
+	if (ovfl) {
+		/* todo: select a suitable interrupt threshold */
+	} else
+		ds_set(context->ds, qual,
+		       ds_interrupt_threshold, buffer + size + 1);
+
+	/* we keep the context until ds_release */
+	return error;
+
+ out_release:
+	context->owner[qual] = NULL;
+	ds_put_context(context);
+	return error;
+
+ out_unlock:
+	spin_unlock(&ds_lock);
+	ds_put_context(context);
+	return error;
+}
+
+int ds_request_bts(struct task_struct *task, void *base, size_t size,
+		   ds_ovfl_callback_t ovfl)
+{
+	return ds_request(task, base, size, ovfl, ds_bts);
+}
+
+int ds_request_pebs(struct task_struct *task, void *base, size_t size,
+		    ds_ovfl_callback_t ovfl)
+{
+	return ds_request(task, base, size, ovfl, ds_pebs);
+}
+
+static int ds_release(struct task_struct *task, enum ds_qualifier qual)
+{
+	struct ds_context *context;
+	int error;
+
+	context = ds_get_context(task);
+	error = ds_validate_access(context, qual);
+	if (error < 0)
+		goto out;
+
+	kfree(context->buffer[qual]);
+	context->buffer[qual] = NULL;
+
+	current->mm->total_vm  -= context->pages[qual];
+	current->mm->locked_vm -= context->pages[qual];
+	context->pages[qual] = 0;
+	context->owner[qual] = NULL;
+
+	/*
+	 * we put the context twice:
+	 *   once for the ds_get_context
+	 *   once for the corresponding ds_request
+	 */
+	ds_put_context(context);
+ out:
+	ds_put_context(context);
+	return error;
+}
+
+int ds_release_bts(struct task_struct *task)
+{
+	return ds_release(task, ds_bts);
+}
+
+int ds_release_pebs(struct task_struct *task)
+{
+	return ds_release(task, ds_pebs);
+}
+
+static int ds_get_index(struct task_struct *task, size_t *pos,
+			enum ds_qualifier qual)
+{
+	struct ds_context *context;
+	unsigned long base, index;
+	int error;
+
+	context = ds_get_context(task);
+	error = ds_validate_access(context, qual);
+	if (error < 0)
+		goto out;
+
+	base  = ds_get(context->ds, qual, ds_buffer_base);
+	index = ds_get(context->ds, qual, ds_index);
+
+	error = ((index - base) / ds_cfg.sizeof_rec[qual]);
+	if (pos)
+		*pos = error;
+ out:
+	ds_put_context(context);
+	return error;
+}
+
+int ds_get_bts_index(struct task_struct *task, size_t *pos)
+{
+	return ds_get_index(task, pos, ds_bts);
+}
+
+int ds_get_pebs_index(struct task_struct *task, size_t *pos)
+{
+	return ds_get_index(task, pos, ds_pebs);
+}
+
+static int ds_get_end(struct task_struct *task, size_t *pos,
+		      enum ds_qualifier qual)
+{
+	struct ds_context *context;
+	unsigned long base, end;
+	int error;
+
+	context = ds_get_context(task);
+	error = ds_validate_access(context, qual);
+	if (error < 0)
+		goto out;
+
+	base = ds_get(context->ds, qual, ds_buffer_base);
+	end  = ds_get(context->ds, qual, ds_absolute_maximum);
+
+	error = ((end - base) / ds_cfg.sizeof_rec[qual]);
+	if (pos)
+		*pos = error;
+ out:
+	ds_put_context(context);
+	return error;
+}
+
+int ds_get_bts_end(struct task_struct *task, size_t *pos)
+{
+	return ds_get_end(task, pos, ds_bts);
+}
+
+int ds_get_pebs_end(struct task_struct *task, size_t *pos)
+{
+	return ds_get_end(task, pos, ds_pebs);
+}
+
+static int ds_access(struct task_struct *task, size_t index,
+		     const void **record, enum ds_qualifier qual)
+{
+	struct ds_context *context;
+	unsigned long base, idx;
+	int error;
+
+	if (!record)
+		return -EINVAL;
+
+	context = ds_get_context(task);
+	error = ds_validate_access(context, qual);
+	if (error < 0)
+		goto out;
+
+	base = ds_get(context->ds, qual, ds_buffer_base);
+	idx = base + (index * ds_cfg.sizeof_rec[qual]);
+
+	error = -EINVAL;
+	if (idx > ds_get(context->ds, qual, ds_absolute_maximum))
+		goto out;
+
+	*record = (const void *)idx;
+	error = ds_cfg.sizeof_rec[qual];
+ out:
+	ds_put_context(context);
+	return error;
+}
+
+int ds_access_bts(struct task_struct *task, size_t index, const void **record)
+{
+	return ds_access(task, index, record, ds_bts);
+}
+
+int ds_access_pebs(struct task_struct *task, size_t index, const void **record)
+{
+	return ds_access(task, index, record, ds_pebs);
+}
+
+static int ds_write(struct task_struct *task, const void *record, size_t size,
+		    enum ds_qualifier qual, int force)
+{
+	struct ds_context *context;
+	int error;
+
+	if (!record)
+		return -EINVAL;
+
+	error = -EPERM;
+	context = ds_get_context(task);
+	if (!context)
+		goto out;
+
+	if (!force) {
+		error = ds_validate_access(context, qual);
+		if (error < 0)
+			goto out;
 	}
 
-	bts = bts + ds_cfg.sizeof_bts;
-	if (bts >= get_bts_absolute_maximum(ds))
-		bts = get_bts_buffer_base(ds);
-	set_bts_index(ds, bts);
+	error = 0;
+	while (size) {
+		unsigned long base, index, end, write_end, int_th;
+		unsigned long write_size, adj_write_size;
 
-	return ds_cfg.sizeof_bts;
+		/*
+		 * 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)
+			goto out;
+
+		write_size = min((unsigned long) size, write_end - index);
+		memcpy((void *)index, record, write_size);
+
+		record = (const char *)record + write_size;
+		size  -= write_size;
+		error += 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(task, context, qual);
+	}
+
+ out:
+	ds_put_context(context);
+	return error;
 }
 
-unsigned long ds_debugctl_mask(void)
+int ds_write_bts(struct task_struct *task, const void *record, size_t size)
 {
-	return ds_cfg.debugctl_mask;
+	return ds_write(task, record, size, ds_bts, /* force = */ 0);
 }
 
-#ifdef __i386__
-static const struct ds_configuration ds_cfg_netburst = {
-	.sizeof_ds = 9 * 4,
-	.bts_buffer_base = { 0, 4 },
-	.bts_index = { 4, 4 },
-	.bts_absolute_maximum = { 8, 4 },
-	.bts_interrupt_threshold = { 12, 4 },
-	.sizeof_bts = 3 * 4,
-	.from_ip = { 0, 4 },
-	.to_ip = { 4, 4 },
-	.info_type = { 4, 1 },
-	.info_data = { 8, 4 },
-	.debugctl_mask = (1<<2)|(1<<3)
+int ds_write_pebs(struct task_struct *task, const void *record, size_t size)
+{
+	return ds_write(task, record, size, ds_pebs, /* force = */ 0);
+}
+
+int ds_unchecked_write_bts(struct task_struct *task,
+			   const void *record, size_t size)
+{
+	return ds_write(task, record, size, ds_bts, /* force = */ 1);
+}
+
+int ds_unchecked_write_pebs(struct task_struct *task,
+			    const void *record, size_t size)
+{
+	return ds_write(task, record, size, ds_pebs, /* force = */ 1);
+}
+
+static int ds_reset_or_clear(struct task_struct *task,
+			     enum ds_qualifier qual, int clear)
+{
+	struct ds_context *context;
+	unsigned long base, end;
+	int error;
+
+	context = ds_get_context(task);
+	error = ds_validate_access(context, qual);
+	if (error < 0)
+		goto out;
+
+	base = ds_get(context->ds, qual, ds_buffer_base);
+	end  = ds_get(context->ds, qual, ds_absolute_maximum);
+
+	if (clear)
+		memset((void *)base, 0, end - base);
+
+	ds_set(context->ds, qual, ds_index, base);
+
+	error = 0;
+ out:
+	ds_put_context(context);
+	return error;
+}
+
+int ds_reset_bts(struct task_struct *task)
+{
+	return ds_reset_or_clear(task, ds_bts, /* clear = */ 0);
+}
+
+int ds_reset_pebs(struct task_struct *task)
+{
+	return ds_reset_or_clear(task, ds_pebs, /* clear = */ 0);
+}
+
+int ds_clear_bts(struct task_struct *task)
+{
+	return ds_reset_or_clear(task, ds_bts, /* clear = */ 1);
+}
+
+int ds_clear_pebs(struct task_struct *task)
+{
+	return ds_reset_or_clear(task, ds_pebs, /* clear = */ 1);
+}
+
+int ds_get_pebs_reset(struct task_struct *task, u64 *value)
+{
+	struct ds_context *context;
+	int error;
+
+	if (!value)
+		return -EINVAL;
+
+	context = ds_get_context(task);
+	error = ds_validate_access(context, ds_pebs);
+	if (error < 0)
+		goto out;
+
+	*value = *(u64 *)(context->ds + (ds_cfg.sizeof_field * 8));
+
+	error = 0;
+ out:
+	ds_put_context(context);
+	return error;
+}
+
+int ds_set_pebs_reset(struct task_struct *task, u64 value)
+{
+	struct ds_context *context;
+	int error;
+
+	context = ds_get_context(task);
+	error = ds_validate_access(context, ds_pebs);
+	if (error < 0)
+		goto out;
+
+	*(u64 *)(context->ds + (ds_cfg.sizeof_field * 8)) = value;
+
+	error = 0;
+ out:
+	ds_put_context(context);
+	return error;
+}
+
+static const struct ds_configuration ds_cfg_var = {
+	.sizeof_ds    = sizeof(long) * 12,
+	.sizeof_field = sizeof(long),
+	.sizeof_rec[ds_bts]   = sizeof(long) * 3,
+	.sizeof_rec[ds_pebs]  = sizeof(long) * 10
 };
-
-static const struct ds_configuration ds_cfg_pentium_m = {
-	.sizeof_ds = 9 * 4,
-	.bts_buffer_base = { 0, 4 },
-	.bts_index = { 4, 4 },
-	.bts_absolute_maximum = { 8, 4 },
-	.bts_interrupt_threshold = { 12, 4 },
-	.sizeof_bts = 3 * 4,
-	.from_ip = { 0, 4 },
-	.to_ip = { 4, 4 },
-	.info_type = { 4, 1 },
-	.info_data = { 8, 4 },
-	.debugctl_mask = (1<<6)|(1<<7)
-};
-#endif /* _i386_ */
-
-static const struct ds_configuration ds_cfg_core2 = {
-	.sizeof_ds = 9 * 8,
-	.bts_buffer_base = { 0, 8 },
-	.bts_index = { 8, 8 },
-	.bts_absolute_maximum = { 16, 8 },
-	.bts_interrupt_threshold = { 24, 8 },
-	.sizeof_bts = 3 * 8,
-	.from_ip = { 0, 8 },
-	.to_ip = { 8, 8 },
-	.info_type = { 8, 1 },
-	.info_data = { 16, 8 },
-	.debugctl_mask = (1<<6)|(1<<7)|(1<<9)
+static const struct ds_configuration ds_cfg_64 = {
+	.sizeof_ds    = 8 * 12,
+	.sizeof_field = 8,
+	.sizeof_rec[ds_bts]   = 8 * 3,
+	.sizeof_rec[ds_pebs]  = 8 * 10
 };
 
 static inline void
@@ -429,14 +821,13 @@
 	switch (c->x86) {
 	case 0x6:
 		switch (c->x86_model) {
-#ifdef __i386__
 		case 0xD:
 		case 0xE: /* Pentium M */
-			ds_configure(&ds_cfg_pentium_m);
+			ds_configure(&ds_cfg_var);
 			break;
-#endif /* _i386_ */
 		case 0xF: /* Core2 */
-			ds_configure(&ds_cfg_core2);
+		case 0x1C: /* Atom */
+			ds_configure(&ds_cfg_64);
 			break;
 		default:
 			/* sorry, don't know about them */
@@ -445,13 +836,11 @@
 		break;
 	case 0xF:
 		switch (c->x86_model) {
-#ifdef __i386__
 		case 0x0:
 		case 0x1:
 		case 0x2: /* Netburst */
-			ds_configure(&ds_cfg_netburst);
+			ds_configure(&ds_cfg_var);
 			break;
-#endif /* _i386_ */
 		default:
 			/* sorry, don't know about them */
 			break;
@@ -462,3 +851,14 @@
 		break;
 	}
 }
+
+void ds_free(struct ds_context *context)
+{
+	/* This is called when the task owning the parameter context
+	 * is dying. There should not be any user of that context left
+	 * to disturb us, anymore. */
+	unsigned long leftovers = context->count;
+	while (leftovers--)
+		ds_put_context(context);
+}
+#endif /* CONFIG_X86_DS */
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 06cc8d4..945a31c 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -414,9 +414,11 @@
 	if (memmap.map == NULL)
 		printk(KERN_ERR "Could not map the EFI memory map!\n");
 	memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size);
+
 	if (memmap.desc_size != sizeof(efi_memory_desc_t))
-		printk(KERN_WARNING "Kernel-defined memdesc"
-		       "doesn't match the one from EFI!\n");
+		printk(KERN_WARNING
+		  "Kernel-defined memdesc doesn't match the one from EFI!\n");
+
 	if (add_efi_memmap)
 		do_add_efi_memmap();
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 89434d4..cf3a0b2 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -275,9 +275,9 @@
 ENTRY(ret_from_fork)
 	CFI_DEFAULT_STACK
 	push kernel_eflags(%rip)
-	CFI_ADJUST_CFA_OFFSET 4
+	CFI_ADJUST_CFA_OFFSET 8
 	popf				# reset kernel eflags
-	CFI_ADJUST_CFA_OFFSET -4
+	CFI_ADJUST_CFA_OFFSET -8
 	call schedule_tail
 	GET_THREAD_INFO(%rcx)
 	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 9bfc4d7..d16084f 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -108,12 +108,11 @@
 	}
 	load_idt((const struct desc_ptr *)&idt_descr);
 
-	early_printk("Kernel alive\n");
+	if (console_loglevel == 10)
+		early_printk("Kernel alive\n");
 
 	x86_64_init_pda();
 
-	early_printk("Kernel really alive\n");
-
 	x86_64_start_reservations(real_mode_data);
 }
 
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 50e5e4a..1919143 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/thread_info.h>
 #include <linux/syscalls.h>
+#include <asm/syscalls.h>
 
 /* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */
 static void set_bitmap(unsigned long *bitmap, unsigned int base,
diff --git a/arch/x86/kernel/ipi.c b/arch/x86/kernel/ipi.c
index 3f7537b..f1c688e 100644
--- a/arch/x86/kernel/ipi.c
+++ b/arch/x86/kernel/ipi.c
@@ -20,6 +20,8 @@
 
 #ifdef CONFIG_X86_32
 #include <mach_apic.h>
+#include <mach_ipi.h>
+
 /*
  * the following functions deal with sending IPIs between CPUs.
  *
@@ -147,7 +149,6 @@
 }
 
 /* must come after the send_IPI functions above for inlining */
-#include <mach_ipi.h>
 static int convert_apicid_to_cpu(int apic_id)
 {
 	int i;
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 1cf8c1f..b71e02d 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -325,7 +325,7 @@
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ",
 				per_cpu(irq_stat,j).irq_call_count);
-		seq_printf(p, "  function call interrupts\n");
+		seq_printf(p, "  Function call interrupts\n");
 		seq_printf(p, "TLB: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ",
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 1f78b23..f065fe9 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -129,7 +129,7 @@
 		seq_printf(p, "CAL: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->irq_call_count);
-		seq_printf(p, "  function call interrupts\n");
+		seq_printf(p, "  Function call interrupts\n");
 		seq_printf(p, "TLB: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count);
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index f47f0eb..8282a21 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -69,6 +69,9 @@
  */
 void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 {
+#ifndef CONFIG_X86_32
+	u32 *gdb_regs32 = (u32 *)gdb_regs;
+#endif
 	gdb_regs[GDB_AX]	= regs->ax;
 	gdb_regs[GDB_BX]	= regs->bx;
 	gdb_regs[GDB_CX]	= regs->cx;
@@ -76,9 +79,9 @@
 	gdb_regs[GDB_SI]	= regs->si;
 	gdb_regs[GDB_DI]	= regs->di;
 	gdb_regs[GDB_BP]	= regs->bp;
-	gdb_regs[GDB_PS]	= regs->flags;
 	gdb_regs[GDB_PC]	= regs->ip;
 #ifdef CONFIG_X86_32
+	gdb_regs[GDB_PS]	= regs->flags;
 	gdb_regs[GDB_DS]	= regs->ds;
 	gdb_regs[GDB_ES]	= regs->es;
 	gdb_regs[GDB_CS]	= regs->cs;
@@ -94,6 +97,9 @@
 	gdb_regs[GDB_R13]	= regs->r13;
 	gdb_regs[GDB_R14]	= regs->r14;
 	gdb_regs[GDB_R15]	= regs->r15;
+	gdb_regs32[GDB_PS]	= regs->flags;
+	gdb_regs32[GDB_CS]	= regs->cs;
+	gdb_regs32[GDB_SS]	= regs->ss;
 #endif
 	gdb_regs[GDB_SP]	= regs->sp;
 }
@@ -112,6 +118,9 @@
  */
 void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 {
+#ifndef CONFIG_X86_32
+	u32 *gdb_regs32 = (u32 *)gdb_regs;
+#endif
 	gdb_regs[GDB_AX]	= 0;
 	gdb_regs[GDB_BX]	= 0;
 	gdb_regs[GDB_CX]	= 0;
@@ -129,8 +138,10 @@
 	gdb_regs[GDB_FS]	= 0xFFFF;
 	gdb_regs[GDB_GS]	= 0xFFFF;
 #else
-	gdb_regs[GDB_PS]	= *(unsigned long *)(p->thread.sp + 8);
-	gdb_regs[GDB_PC]	= 0;
+	gdb_regs32[GDB_PS]	= *(unsigned long *)(p->thread.sp + 8);
+	gdb_regs32[GDB_CS]	= __KERNEL_CS;
+	gdb_regs32[GDB_SS]	= __KERNEL_DS;
+	gdb_regs[GDB_PC]	= p->thread.ip;
 	gdb_regs[GDB_R8]	= 0;
 	gdb_regs[GDB_R9]	= 0;
 	gdb_regs[GDB_R10]	= 0;
@@ -153,6 +164,9 @@
  */
 void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 {
+#ifndef CONFIG_X86_32
+	u32 *gdb_regs32 = (u32 *)gdb_regs;
+#endif
 	regs->ax		= gdb_regs[GDB_AX];
 	regs->bx		= gdb_regs[GDB_BX];
 	regs->cx		= gdb_regs[GDB_CX];
@@ -160,9 +174,9 @@
 	regs->si		= gdb_regs[GDB_SI];
 	regs->di		= gdb_regs[GDB_DI];
 	regs->bp		= gdb_regs[GDB_BP];
-	regs->flags		= gdb_regs[GDB_PS];
 	regs->ip		= gdb_regs[GDB_PC];
 #ifdef CONFIG_X86_32
+	regs->flags		= gdb_regs[GDB_PS];
 	regs->ds		= gdb_regs[GDB_DS];
 	regs->es		= gdb_regs[GDB_ES];
 	regs->cs		= gdb_regs[GDB_CS];
@@ -175,6 +189,9 @@
 	regs->r13		= gdb_regs[GDB_R13];
 	regs->r14		= gdb_regs[GDB_R14];
 	regs->r15		= gdb_regs[GDB_R15];
+	regs->flags		= gdb_regs32[GDB_PS];
+	regs->cs		= gdb_regs32[GDB_CS];
+	regs->ss		= gdb_regs32[GDB_SS];
 #endif
 }
 
@@ -378,10 +395,8 @@
 		if (remcomInBuffer[0] == 's') {
 			linux_regs->flags |= X86_EFLAGS_TF;
 			kgdb_single_step = 1;
-			if (kgdb_contthread) {
-				atomic_set(&kgdb_cpu_doing_single_step,
-					   raw_smp_processor_id());
-			}
+			atomic_set(&kgdb_cpu_doing_single_step,
+				   raw_smp_processor_id());
 		}
 
 		get_debugreg(dr6, 6);
@@ -466,9 +481,15 @@
 
 	case DIE_DEBUG:
 		if (atomic_read(&kgdb_cpu_doing_single_step) ==
-			raw_smp_processor_id() &&
-			user_mode(regs))
-			return single_step_cont(regs, args);
+		    raw_smp_processor_id()) {
+			if (user_mode(regs))
+				return single_step_cont(regs, args);
+			break;
+		} else if (test_thread_flag(TIF_SINGLESTEP))
+			/* This means a user thread is single stepping
+			 * a system call which should be ignored
+			 */
+			return NOTIFY_DONE;
 		/* fall through */
 	default:
 		if (user_mode(regs))
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 8b7a3cf..478bca9 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -178,7 +178,7 @@
 	kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
 }
 
-static void kvm_release_pt(u32 pfn)
+static void kvm_release_pt(unsigned long pfn)
 {
 	struct kvm_mmu_op_release_pt rpt = {
 		.header.op = KVM_MMU_OP_RELEASE_PT,
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index b68e21f..0ed5f93 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -18,6 +18,7 @@
 #include <asm/ldt.h>
 #include <asm/desc.h>
 #include <asm/mmu_context.h>
+#include <asm/syscalls.h>
 
 #ifdef CONFIG_SMP
 static void flush_ldt(void *current_mm)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index abb78a2..2c97f07 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -299,6 +299,15 @@
 		on_each_cpu(__acpi_nmi_disable, NULL, 1);
 }
 
+/*
+ * This function is called as soon the LAPIC NMI watchdog driver has everything
+ * in place and it's ready to check if the NMIs belong to the NMI watchdog
+ */
+void cpu_nmi_set_wd_enabled(void)
+{
+	__get_cpu_var(wd_enabled) = 1;
+}
+
 void setup_apic_nmi_watchdog(void *unused)
 {
 	if (__get_cpu_var(wd_enabled))
@@ -311,8 +320,6 @@
 
 	switch (nmi_watchdog) {
 	case NMI_LOCAL_APIC:
-		 /* enable it before to avoid race with handler */
-		__get_cpu_var(wd_enabled) = 1;
 		if (lapic_watchdog_init(nmi_hz) < 0) {
 			__get_cpu_var(wd_enabled) = 0;
 			return;
diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c
index 3e66722..7a13fac 100644
--- a/arch/x86/kernel/olpc.c
+++ b/arch/x86/kernel/olpc.c
@@ -190,12 +190,12 @@
 static void __init platform_detect(void)
 {
 	size_t propsize;
-	u32 rev;
+	__be32 rev;
 
 	if (ofw("getprop", 4, 1, NULL, "board-revision-int", &rev, 4,
 			&propsize) || propsize != 4) {
 		printk(KERN_ERR "ofw: getprop call failed!\n");
-		rev = 0;
+		rev = cpu_to_be32(0);
 	}
 	olpc_platform_info.boardrev = be32_to_cpu(rev);
 }
@@ -203,7 +203,7 @@
 static void __init platform_detect(void)
 {
 	/* stopgap until OFW support is added to the kernel */
-	olpc_platform_info.boardrev = be32_to_cpu(0xc2);
+	olpc_platform_info.boardrev = 0xc2;
 }
 #endif
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 300da17..e2f4376 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -330,6 +330,7 @@
 #endif
 	.wbinvd = native_wbinvd,
 	.read_msr = native_read_msr_safe,
+	.read_msr_amd = native_read_msr_amd_safe,
 	.write_msr = native_write_msr_safe,
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 5826221..9fe644f 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -23,7 +23,7 @@
 			start = start_##ops##_##x;		\
 			end = end_##ops##_##x;			\
 			goto patch_site
-	switch(type) {
+	switch (type) {
 		PATCH_SITE(pv_irq_ops, irq_disable);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, restore_fl);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 87d4d69..f704cb5 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -82,7 +82,7 @@
 	 * using 512M as goal
 	 */
 	align = 64ULL<<20;
-	size = round_up(dma32_bootmem_size, align);
+	size = roundup(dma32_bootmem_size, align);
 	dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align,
 				 512ULL<<20);
 	if (dma32_bootmem_ptr)
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 49285f8..1a895a5 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -82,7 +82,8 @@
 static unsigned long next_bit;  /* protected by iommu_bitmap_lock */
 static int need_flush;		/* global flush state. set for each gart wrap */
 
-static unsigned long alloc_iommu(struct device *dev, int size)
+static unsigned long alloc_iommu(struct device *dev, int size,
+				 unsigned long align_mask)
 {
 	unsigned long offset, flags;
 	unsigned long boundary_size;
@@ -90,16 +91,17 @@
 
 	base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev),
 			   PAGE_SIZE) >> PAGE_SHIFT;
-	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+	boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
 			      PAGE_SIZE) >> PAGE_SHIFT;
 
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
 	offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit,
-				  size, base_index, boundary_size, 0);
+				  size, base_index, boundary_size, align_mask);
 	if (offset == -1) {
 		need_flush = 1;
 		offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, 0,
-					  size, base_index, boundary_size, 0);
+					  size, base_index, boundary_size,
+					  align_mask);
 	}
 	if (offset != -1) {
 		next_bit = offset+size;
@@ -236,10 +238,10 @@
  * Caller needs to check if the iommu is needed and flush.
  */
 static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
-				size_t size, int dir)
+				size_t size, int dir, unsigned long align_mask)
 {
 	unsigned long npages = iommu_num_pages(phys_mem, size);
-	unsigned long iommu_page = alloc_iommu(dev, npages);
+	unsigned long iommu_page = alloc_iommu(dev, npages, align_mask);
 	int i;
 
 	if (iommu_page == -1) {
@@ -262,7 +264,11 @@
 static dma_addr_t
 gart_map_simple(struct device *dev, phys_addr_t paddr, size_t size, int dir)
 {
-	dma_addr_t map = dma_map_area(dev, paddr, size, dir);
+	dma_addr_t map;
+	unsigned long align_mask;
+
+	align_mask = (1UL << get_order(size)) - 1;
+	map = dma_map_area(dev, paddr, size, dir, align_mask);
 
 	flush_gart();
 
@@ -281,7 +287,8 @@
 	if (!need_iommu(dev, paddr, size))
 		return paddr;
 
-	bus = gart_map_simple(dev, paddr, size, dir);
+	bus = dma_map_area(dev, paddr, size, dir, 0);
+	flush_gart();
 
 	return bus;
 }
@@ -340,7 +347,7 @@
 		unsigned long addr = sg_phys(s);
 
 		if (nonforced_iommu(dev, addr, s->length)) {
-			addr = dma_map_area(dev, addr, s->length, dir);
+			addr = dma_map_area(dev, addr, s->length, dir, 0);
 			if (addr == bad_dma_address) {
 				if (i > 0)
 					gart_unmap_sg(dev, sg, i, dir);
@@ -362,7 +369,7 @@
 			  int nelems, struct scatterlist *sout,
 			  unsigned long pages)
 {
-	unsigned long iommu_start = alloc_iommu(dev, pages);
+	unsigned long iommu_start = alloc_iommu(dev, pages, 0);
 	unsigned long iommu_page = iommu_start;
 	struct scatterlist *s;
 	int i;
@@ -626,7 +633,6 @@
 	struct pci_dev *dev;
 	void *gatt;
 	int i, error;
-	unsigned long start_pfn, end_pfn;
 
 	printk(KERN_INFO "PCI-DMA: Disabling AGP.\n");
 	aper_size = aper_base = info->aper_size = 0;
@@ -672,12 +678,6 @@
 	printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n",
 	       aper_base, aper_size>>10);
 
-	/* need to map that range */
-	end_pfn = (aper_base>>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT);
-	if (end_pfn > max_low_pfn_mapped) {
-		start_pfn = (aper_base>>PAGE_SHIFT);
-		init_memory_mapping(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
-	}
 	return 0;
 
  nommu:
@@ -727,7 +727,8 @@
 {
 	struct agp_kern_info info;
 	unsigned long iommu_start;
-	unsigned long aper_size;
+	unsigned long aper_base, aper_size;
+	unsigned long start_pfn, end_pfn;
 	unsigned long scratch;
 	long i;
 
@@ -765,8 +766,16 @@
 		return;
 	}
 
+	/* need to map that range */
+	aper_size = info.aper_size << 20;
+	aper_base = info.aper_base;
+	end_pfn = (aper_base>>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT);
+	if (end_pfn > max_low_pfn_mapped) {
+		start_pfn = (aper_base>>PAGE_SHIFT);
+		init_memory_mapping(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
+	}
+
 	printk(KERN_INFO "PCI-DMA: using GART IOMMU.\n");
-	aper_size = info.aper_size * 1024 * 1024;
 	iommu_size = check_iommu_size(info.aper_base, aper_size);
 	iommu_pages = iommu_size >> PAGE_SHIFT;
 
diff --git a/arch/x86/kernel/pcspeaker.c b/arch/x86/kernel/pcspeaker.c
index bc1f2d3..a311ffc 100644
--- a/arch/x86/kernel/pcspeaker.c
+++ b/arch/x86/kernel/pcspeaker.c
@@ -1,20 +1,13 @@
 #include <linux/platform_device.h>
-#include <linux/errno.h>
+#include <linux/err.h>
 #include <linux/init.h>
 
 static __init int add_pcspkr(void)
 {
 	struct platform_device *pd;
-	int ret;
 
-	pd = platform_device_alloc("pcspkr", -1);
-	if (!pd)
-		return -ENOMEM;
+	pd = platform_device_register_simple("pcspkr", -1, NULL, 0);
 
-	ret = platform_device_add(pd);
-	if (ret)
-		platform_device_put(pd);
-
-	return ret;
+	return IS_ERR(pd) ? PTR_ERR(pd) : 0;
 }
 device_initcall(add_pcspkr);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 876e918..ec7a2ba 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -185,7 +185,8 @@
 static void poll_idle(void)
 {
 	local_irq_enable();
-	cpu_relax();
+	while (!need_resched())
+		cpu_relax();
 }
 
 /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 31f40b2..205188d 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -37,6 +37,7 @@
 #include <linux/tick.h>
 #include <linux/percpu.h>
 #include <linux/prctl.h>
+#include <linux/dmi.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -56,6 +57,8 @@
 #include <asm/cpu.h>
 #include <asm/kdebug.h>
 #include <asm/idle.h>
+#include <asm/syscalls.h>
+#include <asm/smp.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
@@ -161,6 +164,7 @@
 	unsigned long d0, d1, d2, d3, d6, d7;
 	unsigned long sp;
 	unsigned short ss, gs;
+	const char *board;
 
 	if (user_mode_vm(regs)) {
 		sp = regs->sp;
@@ -173,11 +177,15 @@
 	}
 
 	printk("\n");
-	printk("Pid: %d, comm: %s %s (%s %.*s)\n",
+
+	board = dmi_get_system_info(DMI_PRODUCT_NAME);
+	if (!board)
+		board = "";
+	printk("Pid: %d, comm: %s %s (%s %.*s) %s\n",
 			task_pid_nr(current), current->comm,
 			print_tainted(), init_utsname()->release,
 			(int)strcspn(init_utsname()->version, " "),
-			init_utsname()->version);
+			init_utsname()->version, board);
 
 	printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
 			(u16)regs->cs, regs->ip, regs->flags,
@@ -277,6 +285,14 @@
 		tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
 		put_cpu();
 	}
+#ifdef CONFIG_X86_DS
+	/* Free any DS contexts that have not been properly released. */
+	if (unlikely(current->thread.ds_ctx)) {
+		/* we clear debugctl to make sure DS is not used. */
+		update_debugctlmsr(0);
+		ds_free(current->thread.ds_ctx);
+	}
+#endif /* CONFIG_X86_DS */
 }
 
 void flush_thread(void)
@@ -438,6 +454,35 @@
 	return 0;
 }
 
+#ifdef CONFIG_X86_DS
+static int update_debugctl(struct thread_struct *prev,
+			struct thread_struct *next, unsigned long debugctl)
+{
+	unsigned long ds_prev = 0;
+	unsigned long ds_next = 0;
+
+	if (prev->ds_ctx)
+		ds_prev = (unsigned long)prev->ds_ctx->ds;
+	if (next->ds_ctx)
+		ds_next = (unsigned long)next->ds_ctx->ds;
+
+	if (ds_next != ds_prev) {
+		/* we clear debugctl to make sure DS
+		 * is not in use when we change it */
+		debugctl = 0;
+		update_debugctlmsr(0);
+		wrmsr(MSR_IA32_DS_AREA, ds_next, 0);
+	}
+	return debugctl;
+}
+#else
+static int update_debugctl(struct thread_struct *prev,
+			struct thread_struct *next, unsigned long debugctl)
+{
+	return debugctl;
+}
+#endif /* CONFIG_X86_DS */
+
 static noinline void
 __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		 struct tss_struct *tss)
@@ -448,14 +493,7 @@
 	prev = &prev_p->thread;
 	next = &next_p->thread;
 
-	debugctl = prev->debugctlmsr;
-	if (next->ds_area_msr != prev->ds_area_msr) {
-		/* we clear debugctl to make sure DS
-		 * is not in use when we change it */
-		debugctl = 0;
-		update_debugctlmsr(0);
-		wrmsr(MSR_IA32_DS_AREA, next->ds_area_msr, 0);
-	}
+	debugctl = update_debugctl(prev, next, prev->debugctlmsr);
 
 	if (next->debugctlmsr != debugctl)
 		update_debugctlmsr(next->debugctlmsr);
@@ -479,13 +517,13 @@
 			hard_enable_TSC();
 	}
 
-#ifdef X86_BTS
+#ifdef CONFIG_X86_PTRACE_BTS
 	if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
 
 	if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
-#endif
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 
 	if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e12e0e4..2a8ccb9 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -37,11 +37,11 @@
 #include <linux/kdebug.h>
 #include <linux/tick.h>
 #include <linux/prctl.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
 
-#include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/system.h>
-#include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/mmu_context.h>
@@ -51,6 +51,7 @@
 #include <asm/proto.h>
 #include <asm/ia32.h>
 #include <asm/idle.h>
+#include <asm/syscalls.h>
 
 asmlinkage extern void ret_from_fork(void);
 
@@ -88,7 +89,7 @@
 #ifdef CONFIG_HOTPLUG_CPU
 DECLARE_PER_CPU(int, cpu_state);
 
-#include <asm/nmi.h>
+#include <linux/nmi.h>
 /* We halt the CPU with physical CPU hotplug */
 static inline void play_dead(void)
 {
@@ -153,7 +154,7 @@
 }
 
 /* Prints also some state that isn't saved in the pt_regs */
-void __show_regs(struct pt_regs * regs)
+void __show_regs(struct pt_regs *regs)
 {
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
 	unsigned long d0, d1, d2, d3, d6, d7;
@@ -162,59 +163,61 @@
 
 	printk("\n");
 	print_modules();
-	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
+	printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s\n",
 		current->pid, current->comm, print_tainted(),
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
-	printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
+	printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
 	printk_address(regs->ip, 1);
-	printk("RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss, regs->sp,
-		regs->flags);
-	printk("RAX: %016lx RBX: %016lx RCX: %016lx\n",
+	printk(KERN_INFO "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
+			regs->sp, regs->flags);
+	printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n",
 	       regs->ax, regs->bx, regs->cx);
-	printk("RDX: %016lx RSI: %016lx RDI: %016lx\n",
+	printk(KERN_INFO "RDX: %016lx RSI: %016lx RDI: %016lx\n",
 	       regs->dx, regs->si, regs->di);
-	printk("RBP: %016lx R08: %016lx R09: %016lx\n",
+	printk(KERN_INFO "RBP: %016lx R08: %016lx R09: %016lx\n",
 	       regs->bp, regs->r8, regs->r9);
-	printk("R10: %016lx R11: %016lx R12: %016lx\n",
-	       regs->r10, regs->r11, regs->r12); 
-	printk("R13: %016lx R14: %016lx R15: %016lx\n",
-	       regs->r13, regs->r14, regs->r15); 
+	printk(KERN_INFO "R10: %016lx R11: %016lx R12: %016lx\n",
+	       regs->r10, regs->r11, regs->r12);
+	printk(KERN_INFO "R13: %016lx R14: %016lx R15: %016lx\n",
+	       regs->r13, regs->r14, regs->r15);
 
-	asm("movl %%ds,%0" : "=r" (ds)); 
-	asm("movl %%cs,%0" : "=r" (cs)); 
-	asm("movl %%es,%0" : "=r" (es)); 
+	asm("movl %%ds,%0" : "=r" (ds));
+	asm("movl %%cs,%0" : "=r" (cs));
+	asm("movl %%es,%0" : "=r" (es));
 	asm("movl %%fs,%0" : "=r" (fsindex));
 	asm("movl %%gs,%0" : "=r" (gsindex));
 
 	rdmsrl(MSR_FS_BASE, fs);
-	rdmsrl(MSR_GS_BASE, gs); 
-	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); 
+	rdmsrl(MSR_GS_BASE, gs);
+	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
 
 	cr0 = read_cr0();
 	cr2 = read_cr2();
 	cr3 = read_cr3();
 	cr4 = read_cr4();
 
-	printk("FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", 
-	       fs,fsindex,gs,gsindex,shadowgs); 
-	printk("CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0); 
-	printk("CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, cr4);
+	printk(KERN_INFO "FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
+	       fs, fsindex, gs, gsindex, shadowgs);
+	printk(KERN_INFO "CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
+			es, cr0);
+	printk(KERN_INFO "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
+			cr4);
 
 	get_debugreg(d0, 0);
 	get_debugreg(d1, 1);
 	get_debugreg(d2, 2);
-	printk("DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
+	printk(KERN_INFO "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
 	get_debugreg(d3, 3);
 	get_debugreg(d6, 6);
 	get_debugreg(d7, 7);
-	printk("DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
+	printk(KERN_INFO "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
 }
 
 void show_regs(struct pt_regs *regs)
 {
-	printk("CPU %d:", smp_processor_id());
+	printk(KERN_INFO "CPU %d:", smp_processor_id());
 	__show_regs(regs);
 	show_trace(NULL, regs, (void *)(regs + 1), regs->bp);
 }
@@ -240,6 +243,14 @@
 		t->io_bitmap_max = 0;
 		put_cpu();
 	}
+#ifdef CONFIG_X86_DS
+	/* Free any DS contexts that have not been properly released. */
+	if (unlikely(t->ds_ctx)) {
+		/* we clear debugctl to make sure DS is not used. */
+		update_debugctlmsr(0);
+		ds_free(t->ds_ctx);
+	}
+#endif /* CONFIG_X86_DS */
 }
 
 void flush_thread(void)
@@ -315,10 +326,10 @@
 
 int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
 		unsigned long unused,
-	struct task_struct * p, struct pt_regs * regs)
+	struct task_struct *p, struct pt_regs *regs)
 {
 	int err;
-	struct pt_regs * childregs;
+	struct pt_regs *childregs;
 	struct task_struct *me = current;
 
 	childregs = ((struct pt_regs *)
@@ -363,10 +374,10 @@
 		if (test_thread_flag(TIF_IA32))
 			err = do_set_thread_area(p, -1,
 				(struct user_desc __user *)childregs->si, 0);
-		else 			
-#endif	 
-			err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); 
-		if (err) 
+		else
+#endif
+			err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8);
+		if (err)
 			goto out;
 	}
 	err = 0;
@@ -473,13 +484,27 @@
 	next = &next_p->thread;
 
 	debugctl = prev->debugctlmsr;
-	if (next->ds_area_msr != prev->ds_area_msr) {
-		/* we clear debugctl to make sure DS
-		 * is not in use when we change it */
-		debugctl = 0;
-		update_debugctlmsr(0);
-		wrmsrl(MSR_IA32_DS_AREA, next->ds_area_msr);
+
+#ifdef CONFIG_X86_DS
+	{
+		unsigned long ds_prev = 0, ds_next = 0;
+
+		if (prev->ds_ctx)
+			ds_prev = (unsigned long)prev->ds_ctx->ds;
+		if (next->ds_ctx)
+			ds_next = (unsigned long)next->ds_ctx->ds;
+
+		if (ds_next != ds_prev) {
+			/*
+			 * We clear debugctl to make sure DS
+			 * is not in use when we change it:
+			 */
+			debugctl = 0;
+			update_debugctlmsr(0);
+			wrmsrl(MSR_IA32_DS_AREA, ds_next);
+		}
 	}
+#endif /* CONFIG_X86_DS */
 
 	if (next->debugctlmsr != debugctl)
 		update_debugctlmsr(next->debugctlmsr);
@@ -517,13 +542,13 @@
 		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
 	}
 
-#ifdef X86_BTS
+#ifdef CONFIG_X86_PTRACE_BTS
 	if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
 
 	if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
-#endif
+#endif /* CONFIG_X86_PTRACE_BTS */
 }
 
 /*
@@ -545,7 +570,7 @@
 	unsigned fsindex, gsindex;
 
 	/* we're going to use this soon, after a few expensive things */
-	if (next_p->fpu_counter>5)
+	if (next_p->fpu_counter > 5)
 		prefetch(next->xstate);
 
 	/*
@@ -553,13 +578,13 @@
 	 */
 	load_sp0(tss, next);
 
-	/* 
+	/*
 	 * Switch DS and ES.
 	 * This won't pick up thread selector changes, but I guess that is ok.
 	 */
 	savesegment(es, prev->es);
 	if (unlikely(next->es | prev->es))
-		loadsegment(es, next->es); 
+		loadsegment(es, next->es);
 
 	savesegment(ds, prev->ds);
 	if (unlikely(next->ds | prev->ds))
@@ -585,7 +610,7 @@
 	 */
 	arch_leave_lazy_cpu_mode();
 
-	/* 
+	/*
 	 * Switch FS and GS.
 	 *
 	 * Segment register != 0 always requires a reload.  Also
@@ -594,13 +619,13 @@
 	 */
 	if (unlikely(fsindex | next->fsindex | prev->fs)) {
 		loadsegment(fs, next->fsindex);
-		/* 
+		/*
 		 * Check if the user used a selector != 0; if yes
 		 *  clear 64bit base, since overloaded base is always
 		 *  mapped to the Null selector
 		 */
 		if (fsindex)
-			prev->fs = 0;				
+			prev->fs = 0;
 	}
 	/* when next process has a 64bit base use it */
 	if (next->fs)
@@ -610,7 +635,7 @@
 	if (unlikely(gsindex | next->gsindex | prev->gs)) {
 		load_gs_index(next->gsindex);
 		if (gsindex)
-			prev->gs = 0;				
+			prev->gs = 0;
 	}
 	if (next->gs)
 		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
@@ -619,12 +644,12 @@
 	/* Must be after DS reload */
 	unlazy_fpu(prev_p);
 
-	/* 
+	/*
 	 * Switch the PDA and FPU contexts.
 	 */
 	prev->usersp = read_pda(oldrsp);
 	write_pda(oldrsp, next->usersp);
-	write_pda(pcurrent, next_p); 
+	write_pda(pcurrent, next_p);
 
 	write_pda(kernelstack,
 		  (unsigned long)task_stack_page(next_p) +
@@ -665,7 +690,7 @@
 		char __user * __user *envp, struct pt_regs *regs)
 {
 	long error;
-	char * filename;
+	char *filename;
 
 	filename = getname(name);
 	error = PTR_ERR(filename);
@@ -723,55 +748,55 @@
 unsigned long get_wchan(struct task_struct *p)
 {
 	unsigned long stack;
-	u64 fp,ip;
+	u64 fp, ip;
 	int count = 0;
 
-	if (!p || p == current || p->state==TASK_RUNNING)
-		return 0; 
+	if (!p || p == current || p->state == TASK_RUNNING)
+		return 0;
 	stack = (unsigned long)task_stack_page(p);
 	if (p->thread.sp < stack || p->thread.sp > stack+THREAD_SIZE)
 		return 0;
 	fp = *(u64 *)(p->thread.sp);
-	do { 
+	do {
 		if (fp < (unsigned long)stack ||
 		    fp > (unsigned long)stack+THREAD_SIZE)
-			return 0; 
+			return 0;
 		ip = *(u64 *)(fp+8);
 		if (!in_sched_functions(ip))
 			return ip;
-		fp = *(u64 *)fp; 
-	} while (count++ < 16); 
+		fp = *(u64 *)fp;
+	} while (count++ < 16);
 	return 0;
 }
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
-{ 
-	int ret = 0; 
+{
+	int ret = 0;
 	int doit = task == current;
 	int cpu;
 
-	switch (code) { 
+	switch (code) {
 	case ARCH_SET_GS:
 		if (addr >= TASK_SIZE_OF(task))
-			return -EPERM; 
+			return -EPERM;
 		cpu = get_cpu();
-		/* handle small bases via the GDT because that's faster to 
+		/* handle small bases via the GDT because that's faster to
 		   switch. */
-		if (addr <= 0xffffffff) {  
-			set_32bit_tls(task, GS_TLS, addr); 
-			if (doit) { 
+		if (addr <= 0xffffffff) {
+			set_32bit_tls(task, GS_TLS, addr);
+			if (doit) {
 				load_TLS(&task->thread, cpu);
-				load_gs_index(GS_TLS_SEL); 
+				load_gs_index(GS_TLS_SEL);
 			}
-			task->thread.gsindex = GS_TLS_SEL; 
+			task->thread.gsindex = GS_TLS_SEL;
 			task->thread.gs = 0;
-		} else { 
+		} else {
 			task->thread.gsindex = 0;
 			task->thread.gs = addr;
 			if (doit) {
 				load_gs_index(0);
 				ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr);
-			} 
+			}
 		}
 		put_cpu();
 		break;
@@ -825,8 +850,7 @@
 				rdmsrl(MSR_KERNEL_GS_BASE, base);
 			else
 				base = task->thread.gs;
-		}
-		else
+		} else
 			base = task->thread.gs;
 		ret = put_user(base, (unsigned long __user *)addr);
 		break;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index e37dccc..e375b65 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -14,6 +14,7 @@
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/regset.h>
+#include <linux/tracehook.h>
 #include <linux/user.h>
 #include <linux/elf.h>
 #include <linux/security.h>
@@ -69,7 +70,7 @@
 
 #define FLAG_MASK		FLAG_MASK_32
 
-static long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
+static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
 {
 	BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
 	regno >>= 2;
@@ -554,45 +555,115 @@
 	return 0;
 }
 
-#ifdef X86_BTS
+#ifdef CONFIG_X86_PTRACE_BTS
+/*
+ * The configuration for a particular BTS hardware implementation.
+ */
+struct bts_configuration {
+	/* the size of a BTS record in bytes; at most BTS_MAX_RECORD_SIZE */
+	unsigned char  sizeof_bts;
+	/* the size of a field in the BTS record in bytes */
+	unsigned char  sizeof_field;
+	/* a bitmask to enable/disable BTS in DEBUGCTL MSR */
+	unsigned long debugctl_mask;
+};
+static struct bts_configuration bts_cfg;
 
-static int ptrace_bts_get_size(struct task_struct *child)
+#define BTS_MAX_RECORD_SIZE (8 * 3)
+
+
+/*
+ * 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 first 8 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.
+ */
+
+enum bts_field {
+	bts_from = 0,
+	bts_to,
+	bts_flags,
+
+	bts_escape = (unsigned long)-1,
+	bts_qual = bts_to,
+	bts_jiffies = bts_flags
+};
+
+static inline unsigned long bts_get(const char *base, enum bts_field field)
 {
-	if (!child->thread.ds_area_msr)
-		return -ENXIO;
-
-	return ds_get_bts_index((void *)child->thread.ds_area_msr);
+	base += (bts_cfg.sizeof_field * field);
+	return *(unsigned long *)base;
 }
 
-static int ptrace_bts_read_record(struct task_struct *child,
-				  long index,
+static inline void bts_set(char *base, enum bts_field field, unsigned long val)
+{
+	base += (bts_cfg.sizeof_field * field);;
+	(*(unsigned long *)base) = val;
+}
+
+/*
+ * Translate a BTS record from the raw format into the bts_struct format
+ *
+ * out (out): bts_struct interpretation
+ * raw: raw BTS record
+ */
+static void ptrace_bts_translate_record(struct bts_struct *out, const void *raw)
+{
+	memset(out, 0, sizeof(*out));
+	if (bts_get(raw, bts_from) == bts_escape) {
+		out->qualifier       = bts_get(raw, bts_qual);
+		out->variant.jiffies = bts_get(raw, bts_jiffies);
+	} else {
+		out->qualifier = BTS_BRANCH;
+		out->variant.lbr.from_ip = bts_get(raw, bts_from);
+		out->variant.lbr.to_ip   = bts_get(raw, bts_to);
+	}
+}
+
+static int ptrace_bts_read_record(struct task_struct *child, size_t index,
 				  struct bts_struct __user *out)
 {
 	struct bts_struct ret;
-	int retval;
-	int bts_end;
-	int bts_index;
+	const void *bts_record;
+	size_t bts_index, bts_end;
+	int error;
 
-	if (!child->thread.ds_area_msr)
-		return -ENXIO;
+	error = ds_get_bts_end(child, &bts_end);
+	if (error < 0)
+		return error;
 
-	if (index < 0)
-		return -EINVAL;
-
-	bts_end = ds_get_bts_end((void *)child->thread.ds_area_msr);
 	if (bts_end <= index)
 		return -EINVAL;
 
-	/* translate the ptrace bts index into the ds bts index */
-	bts_index = ds_get_bts_index((void *)child->thread.ds_area_msr);
-	bts_index -= (index + 1);
-	if (bts_index < 0)
-		bts_index += bts_end;
+	error = ds_get_bts_index(child, &bts_index);
+	if (error < 0)
+		return error;
 
-	retval = ds_read_bts((void *)child->thread.ds_area_msr,
-			     bts_index, &ret);
-	if (retval < 0)
-		return retval;
+	/* translate the ptrace bts index into the ds bts index */
+	bts_index += bts_end - (index + 1);
+	if (bts_end <= bts_index)
+		bts_index -= bts_end;
+
+	error = ds_access_bts(child, bts_index, &bts_record);
+	if (error < 0)
+		return error;
+
+	ptrace_bts_translate_record(&ret, bts_record);
 
 	if (copy_to_user(out, &ret, sizeof(ret)))
 		return -EFAULT;
@@ -600,101 +671,106 @@
 	return sizeof(ret);
 }
 
-static int ptrace_bts_clear(struct task_struct *child)
-{
-	if (!child->thread.ds_area_msr)
-		return -ENXIO;
-
-	return ds_clear((void *)child->thread.ds_area_msr);
-}
-
 static int ptrace_bts_drain(struct task_struct *child,
 			    long size,
 			    struct bts_struct __user *out)
 {
-	int end, i;
-	void *ds = (void *)child->thread.ds_area_msr;
+	struct bts_struct ret;
+	const unsigned char *raw;
+	size_t end, i;
+	int error;
 
-	if (!ds)
-		return -ENXIO;
-
-	end = ds_get_bts_index(ds);
-	if (end <= 0)
-		return end;
+	error = ds_get_bts_index(child, &end);
+	if (error < 0)
+		return error;
 
 	if (size < (end * sizeof(struct bts_struct)))
 		return -EIO;
 
-	for (i = 0; i < end; i++, out++) {
-		struct bts_struct ret;
-		int retval;
+	error = ds_access_bts(child, 0, (const void **)&raw);
+	if (error < 0)
+		return error;
 
-		retval = ds_read_bts(ds, i, &ret);
-		if (retval < 0)
-			return retval;
+	for (i = 0; i < end; i++, out++, raw += bts_cfg.sizeof_bts) {
+		ptrace_bts_translate_record(&ret, raw);
 
 		if (copy_to_user(out, &ret, sizeof(ret)))
 			return -EFAULT;
 	}
 
-	ds_clear(ds);
+	error = ds_clear_bts(child);
+	if (error < 0)
+		return error;
 
 	return end;
 }
 
+static void ptrace_bts_ovfl(struct task_struct *child)
+{
+	send_sig(child->thread.bts_ovfl_signal, child, 0);
+}
+
 static int ptrace_bts_config(struct task_struct *child,
 			     long cfg_size,
 			     const struct ptrace_bts_config __user *ucfg)
 {
 	struct ptrace_bts_config cfg;
-	int bts_size, ret = 0;
-	void *ds;
+	int error = 0;
 
+	error = -EOPNOTSUPP;
+	if (!bts_cfg.sizeof_bts)
+		goto errout;
+
+	error = -EIO;
 	if (cfg_size < sizeof(cfg))
-		return -EIO;
+		goto errout;
 
+	error = -EFAULT;
 	if (copy_from_user(&cfg, ucfg, sizeof(cfg)))
-		return -EFAULT;
+		goto errout;
 
-	if ((int)cfg.size < 0)
-		return -EINVAL;
+	error = -EINVAL;
+	if ((cfg.flags & PTRACE_BTS_O_SIGNAL) &&
+	    !(cfg.flags & PTRACE_BTS_O_ALLOC))
+		goto errout;
 
-	bts_size = 0;
-	ds = (void *)child->thread.ds_area_msr;
-	if (ds) {
-		bts_size = ds_get_bts_size(ds);
-		if (bts_size < 0)
-			return bts_size;
-	}
-	cfg.size = PAGE_ALIGN(cfg.size);
+	if (cfg.flags & PTRACE_BTS_O_ALLOC) {
+		ds_ovfl_callback_t ovfl = NULL;
+		unsigned int sig = 0;
 
-	if (bts_size != cfg.size) {
-		ret = ptrace_bts_realloc(child, cfg.size,
-					 cfg.flags & PTRACE_BTS_O_CUT_SIZE);
-		if (ret < 0)
+		/* we ignore the error in case we were not tracing child */
+		(void)ds_release_bts(child);
+
+		if (cfg.flags & PTRACE_BTS_O_SIGNAL) {
+			if (!cfg.signal)
+				goto errout;
+
+			sig  = cfg.signal;
+			ovfl = ptrace_bts_ovfl;
+		}
+
+		error = ds_request_bts(child, /* base = */ NULL, cfg.size, ovfl);
+		if (error < 0)
 			goto errout;
 
-		ds = (void *)child->thread.ds_area_msr;
+		child->thread.bts_ovfl_signal = sig;
 	}
 
-	if (cfg.flags & PTRACE_BTS_O_SIGNAL)
-		ret = ds_set_overflow(ds, DS_O_SIGNAL);
-	else
-		ret = ds_set_overflow(ds, DS_O_WRAP);
-	if (ret < 0)
+	error = -EINVAL;
+	if (!child->thread.ds_ctx && cfg.flags)
 		goto errout;
 
 	if (cfg.flags & PTRACE_BTS_O_TRACE)
-		child->thread.debugctlmsr |= ds_debugctl_mask();
+		child->thread.debugctlmsr |= bts_cfg.debugctl_mask;
 	else
-		child->thread.debugctlmsr &= ~ds_debugctl_mask();
+		child->thread.debugctlmsr &= ~bts_cfg.debugctl_mask;
 
 	if (cfg.flags & PTRACE_BTS_O_SCHED)
 		set_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
 	else
 		clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
 
-	ret = sizeof(cfg);
+	error = sizeof(cfg);
 
 out:
 	if (child->thread.debugctlmsr)
@@ -702,10 +778,10 @@
 	else
 		clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
 
-	return ret;
+	return error;
 
 errout:
-	child->thread.debugctlmsr &= ~ds_debugctl_mask();
+	child->thread.debugctlmsr &= ~bts_cfg.debugctl_mask;
 	clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
 	goto out;
 }
@@ -714,119 +790,79 @@
 			     long cfg_size,
 			     struct ptrace_bts_config __user *ucfg)
 {
-	void *ds = (void *)child->thread.ds_area_msr;
 	struct ptrace_bts_config cfg;
+	size_t end;
+	const void *base, *max;
+	int error;
 
 	if (cfg_size < sizeof(cfg))
 		return -EIO;
 
+	error = ds_get_bts_end(child, &end);
+	if (error < 0)
+		return error;
+
+	error = ds_access_bts(child, /* index = */ 0, &base);
+	if (error < 0)
+		return error;
+
+	error = ds_access_bts(child, /* index = */ end, &max);
+	if (error < 0)
+		return error;
+
 	memset(&cfg, 0, sizeof(cfg));
-
-	if (ds) {
-		cfg.size = ds_get_bts_size(ds);
-
-		if (ds_get_overflow(ds) == DS_O_SIGNAL)
-			cfg.flags |= PTRACE_BTS_O_SIGNAL;
-
-		if (test_tsk_thread_flag(child, TIF_DEBUGCTLMSR) &&
-		    child->thread.debugctlmsr & ds_debugctl_mask())
-			cfg.flags |= PTRACE_BTS_O_TRACE;
-
-		if (test_tsk_thread_flag(child, TIF_BTS_TRACE_TS))
-			cfg.flags |= PTRACE_BTS_O_SCHED;
-	}
-
+	cfg.size = (max - base);
+	cfg.signal = child->thread.bts_ovfl_signal;
 	cfg.bts_size = sizeof(struct bts_struct);
 
+	if (cfg.signal)
+		cfg.flags |= PTRACE_BTS_O_SIGNAL;
+
+	if (test_tsk_thread_flag(child, TIF_DEBUGCTLMSR) &&
+	    child->thread.debugctlmsr & bts_cfg.debugctl_mask)
+		cfg.flags |= PTRACE_BTS_O_TRACE;
+
+	if (test_tsk_thread_flag(child, TIF_BTS_TRACE_TS))
+		cfg.flags |= PTRACE_BTS_O_SCHED;
+
 	if (copy_to_user(ucfg, &cfg, sizeof(cfg)))
 		return -EFAULT;
 
 	return sizeof(cfg);
 }
 
-
 static int ptrace_bts_write_record(struct task_struct *child,
 				   const struct bts_struct *in)
 {
-	int retval;
+	unsigned char bts_record[BTS_MAX_RECORD_SIZE];
 
-	if (!child->thread.ds_area_msr)
-		return -ENXIO;
+	BUG_ON(BTS_MAX_RECORD_SIZE < bts_cfg.sizeof_bts);
 
-	retval = ds_write_bts((void *)child->thread.ds_area_msr, in);
-	if (retval)
-		return retval;
+	memset(bts_record, 0, bts_cfg.sizeof_bts);
+	switch (in->qualifier) {
+	case BTS_INVALID:
+		break;
 
-	return sizeof(*in);
-}
+	case BTS_BRANCH:
+		bts_set(bts_record, bts_from, in->variant.lbr.from_ip);
+		bts_set(bts_record, bts_to,   in->variant.lbr.to_ip);
+		break;
 
-static int ptrace_bts_realloc(struct task_struct *child,
-			      int size, int reduce_size)
-{
-	unsigned long rlim, vm;
-	int ret, old_size;
+	case BTS_TASK_ARRIVES:
+	case BTS_TASK_DEPARTS:
+		bts_set(bts_record, bts_from,    bts_escape);
+		bts_set(bts_record, bts_qual,    in->qualifier);
+		bts_set(bts_record, bts_jiffies, in->variant.jiffies);
+		break;
 
-	if (size < 0)
+	default:
 		return -EINVAL;
-
-	old_size = ds_get_bts_size((void *)child->thread.ds_area_msr);
-	if (old_size < 0)
-		return old_size;
-
-	ret = ds_free((void **)&child->thread.ds_area_msr);
-	if (ret < 0)
-		goto out;
-
-	size >>= PAGE_SHIFT;
-	old_size >>= PAGE_SHIFT;
-
-	current->mm->total_vm  -= old_size;
-	current->mm->locked_vm -= old_size;
-
-	if (size == 0)
-		goto out;
-
-	rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
-	vm = current->mm->total_vm  + size;
-	if (rlim < vm) {
-		ret = -ENOMEM;
-
-		if (!reduce_size)
-			goto out;
-
-		size = rlim - current->mm->total_vm;
-		if (size <= 0)
-			goto out;
 	}
 
-	rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
-	vm = current->mm->locked_vm  + size;
-	if (rlim < vm) {
-		ret = -ENOMEM;
-
-		if (!reduce_size)
-			goto out;
-
-		size = rlim - current->mm->locked_vm;
-		if (size <= 0)
-			goto out;
-	}
-
-	ret = ds_allocate((void **)&child->thread.ds_area_msr,
-			  size << PAGE_SHIFT);
-	if (ret < 0)
-		goto out;
-
-	current->mm->total_vm  += size;
-	current->mm->locked_vm += size;
-
-out:
-	if (child->thread.ds_area_msr)
-		set_tsk_thread_flag(child, TIF_DS_AREA_MSR);
-	else
-		clear_tsk_thread_flag(child, TIF_DS_AREA_MSR);
-
-	return ret;
+	/* The writing task will be the switched-to task on a context
+	 * switch. It needs to write into the switched-from task's BTS
+	 * buffer. */
+	return ds_unchecked_write_bts(child, bts_record, bts_cfg.sizeof_bts);
 }
 
 void ptrace_bts_take_timestamp(struct task_struct *tsk,
@@ -839,7 +875,66 @@
 
 	ptrace_bts_write_record(tsk, &rec);
 }
-#endif /* X86_BTS */
+
+static const struct bts_configuration bts_cfg_netburst = {
+	.sizeof_bts    = sizeof(long) * 3,
+	.sizeof_field  = sizeof(long),
+	.debugctl_mask = (1<<2)|(1<<3)|(1<<5)
+};
+
+static const struct bts_configuration bts_cfg_pentium_m = {
+	.sizeof_bts    = sizeof(long) * 3,
+	.sizeof_field  = sizeof(long),
+	.debugctl_mask = (1<<6)|(1<<7)
+};
+
+static const struct bts_configuration bts_cfg_core2 = {
+	.sizeof_bts    = 8 * 3,
+	.sizeof_field  = 8,
+	.debugctl_mask = (1<<6)|(1<<7)|(1<<9)
+};
+
+static inline void bts_configure(const struct bts_configuration *cfg)
+{
+	bts_cfg = *cfg;
+}
+
+void __cpuinit ptrace_bts_init_intel(struct cpuinfo_x86 *c)
+{
+	switch (c->x86) {
+	case 0x6:
+		switch (c->x86_model) {
+		case 0xD:
+		case 0xE: /* Pentium M */
+			bts_configure(&bts_cfg_pentium_m);
+			break;
+		case 0xF: /* Core2 */
+        case 0x1C: /* Atom */
+			bts_configure(&bts_cfg_core2);
+			break;
+		default:
+			/* sorry, don't know about them */
+			break;
+		}
+		break;
+	case 0xF:
+		switch (c->x86_model) {
+		case 0x0:
+		case 0x1:
+		case 0x2: /* Netburst */
+			bts_configure(&bts_cfg_netburst);
+			break;
+		default:
+			/* sorry, don't know about them */
+			break;
+		}
+		break;
+	default:
+		/* sorry, don't know about them */
+		break;
+	}
+}
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 /*
  * Called by kernel/ptrace.c when detaching..
@@ -852,15 +947,15 @@
 #ifdef TIF_SYSCALL_EMU
 	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
 #endif
-	if (child->thread.ds_area_msr) {
-#ifdef X86_BTS
-		ptrace_bts_realloc(child, 0, 0);
-#endif
-		child->thread.debugctlmsr &= ~ds_debugctl_mask();
-		if (!child->thread.debugctlmsr)
-			clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
-		clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
-	}
+#ifdef CONFIG_X86_PTRACE_BTS
+	(void)ds_release_bts(child);
+
+	child->thread.debugctlmsr &= ~bts_cfg.debugctl_mask;
+	if (!child->thread.debugctlmsr)
+		clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
+
+	clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
+#endif /* CONFIG_X86_PTRACE_BTS */
 }
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
@@ -980,7 +1075,7 @@
 	/*
 	 * These bits need more cooking - not enabled yet:
 	 */
-#ifdef X86_BTS
+#ifdef CONFIG_X86_PTRACE_BTS
 	case PTRACE_BTS_CONFIG:
 		ret = ptrace_bts_config
 			(child, data, (struct ptrace_bts_config __user *)addr);
@@ -992,7 +1087,7 @@
 		break;
 
 	case PTRACE_BTS_SIZE:
-		ret = ptrace_bts_get_size(child);
+		ret = ds_get_bts_index(child, /* pos = */ NULL);
 		break;
 
 	case PTRACE_BTS_GET:
@@ -1001,14 +1096,14 @@
 		break;
 
 	case PTRACE_BTS_CLEAR:
-		ret = ptrace_bts_clear(child);
+		ret = ds_clear_bts(child);
 		break;
 
 	case PTRACE_BTS_DRAIN:
 		ret = ptrace_bts_drain
 			(child, data, (struct bts_struct __user *) addr);
 		break;
-#endif
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 	default:
 		ret = ptrace_request(child, request, addr, data);
@@ -1375,30 +1470,6 @@
 	force_sig_info(SIGTRAP, &info, tsk);
 }
 
-static void syscall_trace(struct pt_regs *regs)
-{
-	if (!(current->ptrace & PT_PTRACED))
-		return;
-
-#if 0
-	printk("trace %s ip %lx sp %lx ax %d origrax %d caller %lx tiflags %x ptrace %x\n",
-	       current->comm,
-	       regs->ip, regs->sp, regs->ax, regs->orig_ax, __builtin_return_address(0),
-	       current_thread_info()->flags, current->ptrace);
-#endif
-
-	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
-				? 0x80 : 0));
-	/*
-	 * this isn't the same as continuing with a signal, but it will do
-	 * for normal use.  strace only continues with a signal if the
-	 * stopping signal is not SIGTRAP.  -brl
-	 */
-	if (current->exit_code) {
-		send_sig(current->exit_code, current, 1);
-		current->exit_code = 0;
-	}
-}
 
 #ifdef CONFIG_X86_32
 # define IS_IA32	1
@@ -1432,8 +1503,9 @@
 	if (unlikely(test_thread_flag(TIF_SYSCALL_EMU)))
 		ret = -1L;
 
-	if (ret || test_thread_flag(TIF_SYSCALL_TRACE))
-		syscall_trace(regs);
+	if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) &&
+	    tracehook_report_syscall_entry(regs))
+		ret = -1L;
 
 	if (unlikely(current->audit_context)) {
 		if (IS_IA32)
@@ -1459,7 +1531,7 @@
 		audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
-		syscall_trace(regs);
+		tracehook_report_syscall_exit(regs, 0);
 
 	/*
 	 * If TIF_SYSCALL_EMU is set, we only get here because of
@@ -1475,6 +1547,6 @@
 	 * system call instruction.
 	 */
 	if (test_thread_flag(TIF_SINGLESTEP) &&
-	    (current->ptrace & PT_PTRACED))
+	    tracehook_consider_fatal_signal(current, SIGTRAP, SIG_DFL))
 		send_sigtrap(current, regs, 0);
 }
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 724adfc..f4c93f1 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -29,7 +29,11 @@
 
 static const struct desc_ptr no_idt = {};
 static int reboot_mode;
-enum reboot_type reboot_type = BOOT_KBD;
+/*
+ * Keyboard reset and triple fault may result in INIT, not RESET, which
+ * doesn't work when we're in vmx root mode.  Try ACPI first.
+ */
+enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
 
 #if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9838f25..141efab 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -223,6 +223,9 @@
 #define RAMDISK_LOAD_FLAG		0x4000
 
 static char __initdata command_line[COMMAND_LINE_SIZE];
+#ifdef CONFIG_CMDLINE_BOOL
+static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
+#endif
 
 #if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
 struct edd edd;
@@ -665,6 +668,19 @@
 	bss_resource.start = virt_to_phys(&__bss_start);
 	bss_resource.end = virt_to_phys(&__bss_stop)-1;
 
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+	if (builtin_cmdline[0]) {
+		/* append boot loader cmdline to builtin */
+		strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+		strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+		strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+	}
+#endif
+#endif
+
 	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = command_line;
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 76e305e..0e67f72 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -162,9 +162,16 @@
 			printk(KERN_INFO
 			       "cpu %d has no node %d or node-local memory\n",
 				cpu, node);
+			if (ptr)
+				printk(KERN_DEBUG "per cpu data for cpu%d at %016lx\n",
+					 cpu, __pa(ptr));
 		}
-		else
+		else {
 			ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
+			if (ptr)
+				printk(KERN_DEBUG "per cpu data for cpu%d on node%d at %016lx\n",
+					 cpu, node, __pa(ptr));
+		}
 #endif
 		per_cpu_offset(cpu) = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
diff --git a/arch/x86/kernel/sigframe.h b/arch/x86/kernel/sigframe.h
index 72bbb51..8b4956e 100644
--- a/arch/x86/kernel/sigframe.h
+++ b/arch/x86/kernel/sigframe.h
@@ -24,4 +24,9 @@
 	struct ucontext uc;
 	struct siginfo info;
 };
+
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+		sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
+		sigset_t *set, struct pt_regs *regs);
 #endif
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 6fb5bcd..2a2435d 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/tracehook.h>
 #include <linux/elf.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
@@ -26,6 +27,7 @@
 #include <asm/uaccess.h>
 #include <asm/i387.h>
 #include <asm/vdso.h>
+#include <asm/syscalls.h>
 
 #include "sigframe.h"
 
@@ -558,8 +560,6 @@
 	 * handler too.
 	 */
 	regs->flags &= ~X86_EFLAGS_TF;
-	if (test_thread_flag(TIF_SINGLESTEP))
-		ptrace_notify(SIGTRAP);
 
 	spin_lock_irq(&current->sighand->siglock);
 	sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
@@ -568,6 +568,9 @@
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
 
+	tracehook_signal_handler(sig, info, ka, regs,
+				 test_thread_flag(TIF_SINGLESTEP));
+
 	return 0;
 }
 
@@ -661,5 +664,10 @@
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
+	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+		clear_thread_flag(TIF_NOTIFY_RESUME);
+		tracehook_notify_resume(regs);
+	}
+
 	clear_thread_flag(TIF_IRET);
 }
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index ca316b5..694aa88 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -15,17 +15,21 @@
 #include <linux/errno.h>
 #include <linux/wait.h>
 #include <linux/ptrace.h>
+#include <linux/tracehook.h>
 #include <linux/unistd.h>
 #include <linux/stddef.h>
 #include <linux/personality.h>
 #include <linux/compiler.h>
+#include <linux/uaccess.h>
+
 #include <asm/processor.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
 #include <asm/i387.h>
 #include <asm/proto.h>
 #include <asm/ia32_unistd.h>
 #include <asm/mce.h>
+#include <asm/syscall.h>
+#include <asm/syscalls.h>
 #include "sigframe.h"
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
@@ -41,11 +45,6 @@
 # define FIX_EFLAGS	__FIX_EFLAGS
 #endif
 
-int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
-               sigset_t *set, struct pt_regs * regs); 
-int ia32_setup_frame(int sig, struct k_sigaction *ka,
-            sigset_t *set, struct pt_regs * regs); 
-
 asmlinkage long
 sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
 		struct pt_regs *regs)
@@ -128,7 +127,7 @@
 	/* Always make any pending restarted system calls return -EINTR */
 	current_thread_info()->restart_block.fn = do_no_restart_syscall;
 
-#define COPY(x)		err |= __get_user(regs->x, &sc->x)
+#define COPY(x)		(err |= __get_user(regs->x, &sc->x))
 
 	COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
 	COPY(dx); COPY(cx); COPY(ip);
@@ -158,7 +157,7 @@
 	}
 
 	{
-		struct _fpstate __user * buf;
+		struct _fpstate __user *buf;
 		err |= __get_user(buf, &sc->fpstate);
 
 		if (buf) {
@@ -198,7 +197,7 @@
 	current->blocked = set;
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
-	
+
 	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
 		goto badframe;
 
@@ -208,16 +207,17 @@
 	return ax;
 
 badframe:
-	signal_fault(regs,frame,"sigreturn");
+	signal_fault(regs, frame, "sigreturn");
 	return 0;
-}	
+}
 
 /*
  * Set up a signal frame.
  */
 
 static inline int
-setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, unsigned long mask, struct task_struct *me)
+setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
+		unsigned long mask, struct task_struct *me)
 {
 	int err = 0;
 
@@ -273,35 +273,35 @@
 }
 
 static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
-			   sigset_t *set, struct pt_regs * regs)
+			   sigset_t *set, struct pt_regs *regs)
 {
 	struct rt_sigframe __user *frame;
-	struct _fpstate __user *fp = NULL; 
+	struct _fpstate __user *fp = NULL;
 	int err = 0;
 	struct task_struct *me = current;
 
 	if (used_math()) {
-		fp = get_stack(ka, regs, sizeof(struct _fpstate)); 
+		fp = get_stack(ka, regs, sizeof(struct _fpstate));
 		frame = (void __user *)round_down(
 			(unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
 
 		if (!access_ok(VERIFY_WRITE, fp, sizeof(struct _fpstate)))
 			goto give_sigsegv;
 
-		if (save_i387(fp) < 0) 
-			err |= -1; 
+		if (save_i387(fp) < 0)
+			err |= -1;
 	} else
 		frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8;
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		goto give_sigsegv;
 
-	if (ka->sa.sa_flags & SA_SIGINFO) { 
+	if (ka->sa.sa_flags & SA_SIGINFO) {
 		err |= copy_siginfo_to_user(&frame->info, info);
 		if (err)
 			goto give_sigsegv;
 	}
-		
+
 	/* Create the ucontext.  */
 	err |= __put_user(0, &frame->uc.uc_flags);
 	err |= __put_user(0, &frame->uc.uc_link);
@@ -311,9 +311,9 @@
 	err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
 	err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0], me);
 	err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate);
-	if (sizeof(*set) == 16) { 
+	if (sizeof(*set) == 16) {
 		__put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
-		__put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]); 
+		__put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
 	} else
 		err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
 
@@ -324,7 +324,7 @@
 		err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
 	} else {
 		/* could use a vstub here */
-		goto give_sigsegv; 
+		goto give_sigsegv;
 	}
 
 	if (err)
@@ -332,7 +332,7 @@
 
 	/* Set up registers for signal handler */
 	regs->di = sig;
-	/* In case the signal handler was declared without prototypes */ 
+	/* In case the signal handler was declared without prototypes */
 	regs->ax = 0;
 
 	/* This also works for non SA_SIGINFO handlers because they expect the
@@ -355,37 +355,8 @@
 }
 
 /*
- * Return -1L or the syscall number that @regs is executing.
- */
-static long current_syscall(struct pt_regs *regs)
-{
-	/*
-	 * We always sign-extend a -1 value being set here,
-	 * so this is always either -1L or a syscall number.
-	 */
-	return regs->orig_ax;
-}
-
-/*
- * Return a value that is -EFOO if the system call in @regs->orig_ax
- * returned an error.  This only works for @regs from @current.
- */
-static long current_syscall_ret(struct pt_regs *regs)
-{
-#ifdef CONFIG_IA32_EMULATION
-	if (test_thread_flag(TIF_IA32))
-		/*
-		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
-		 * and will match correctly in comparisons.
-		 */
-		return (int) regs->ax;
-#endif
-	return regs->ax;
-}
-
-/*
  * OK, we're invoking a handler
- */	
+ */
 
 static int
 handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
@@ -394,9 +365,9 @@
 	int ret;
 
 	/* Are we from a system call? */
-	if (current_syscall(regs) >= 0) {
+	if (syscall_get_nr(current, regs) >= 0) {
 		/* If so, check system call restarting.. */
-		switch (current_syscall_ret(regs)) {
+		switch (syscall_get_error(current, regs)) {
 		case -ERESTART_RESTARTBLOCK:
 		case -ERESTARTNOHAND:
 			regs->ax = -EINTR;
@@ -429,7 +400,7 @@
 			ret = ia32_setup_rt_frame(sig, ka, info, oldset, regs);
 		else
 			ret = ia32_setup_frame(sig, ka, oldset, regs);
-	} else 
+	} else
 #endif
 	ret = setup_rt_frame(sig, ka, info, oldset, regs);
 
@@ -453,15 +424,16 @@
 		 * handler too.
 		 */
 		regs->flags &= ~X86_EFLAGS_TF;
-		if (test_thread_flag(TIF_SINGLESTEP))
-			ptrace_notify(SIGTRAP);
 
 		spin_lock_irq(&current->sighand->siglock);
-		sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
+		sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
 		if (!(ka->sa.sa_flags & SA_NODEFER))
-			sigaddset(&current->blocked,sig);
+			sigaddset(&current->blocked, sig);
 		recalc_sigpending();
 		spin_unlock_irq(&current->sighand->siglock);
+
+		tracehook_signal_handler(sig, info, ka, regs,
+					 test_thread_flag(TIF_SINGLESTEP));
 	}
 
 	return ret;
@@ -518,9 +490,9 @@
 	}
 
 	/* Did we come from a system call? */
-	if (current_syscall(regs) >= 0) {
+	if (syscall_get_nr(current, regs) >= 0) {
 		/* Restart the system call - no handlers present */
-		switch (current_syscall_ret(regs)) {
+		switch (syscall_get_error(current, regs)) {
 		case -ERESTARTNOHAND:
 		case -ERESTARTSYS:
 		case -ERESTARTNOINTR:
@@ -558,17 +530,23 @@
 	/* deal with pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
+
+	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+		clear_thread_flag(TIF_NOTIFY_RESUME);
+		tracehook_notify_resume(regs);
+	}
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
-{ 
-	struct task_struct *me = current; 
+{
+	struct task_struct *me = current;
 	if (show_unhandled_signals && printk_ratelimit()) {
 		printk("%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
-	       me->comm,me->pid,where,frame,regs->ip,regs->sp,regs->orig_ax);
+	       me->comm, me->pid, where, frame, regs->ip,
+		   regs->sp, regs->orig_ax);
 		print_vma_addr(" in ", regs->ip);
 		printk("\n");
 	}
 
-	force_sig(SIGSEGV, me); 
-} 
+	force_sig(SIGSEGV, me);
+}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7985c5b..45531e3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -88,7 +88,7 @@
 #define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
 #define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
 #else
-struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
+static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
 #define get_idle_for_cpu(x)      (idle_thread_array[(x)])
 #define set_idle_for_cpu(x, p)   (idle_thread_array[(x)] = (p))
 #endif
@@ -129,7 +129,7 @@
 static cpumask_t cpu_sibling_setup_map;
 
 /* Set if we find a B stepping CPU */
-int __cpuinitdata smp_b_stepping;
+static int __cpuinitdata smp_b_stepping;
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
 
@@ -1313,16 +1313,13 @@
 	if (!num_processors)
 		num_processors = 1;
 
-#ifdef CONFIG_HOTPLUG_CPU
 	if (additional_cpus == -1) {
 		if (disabled_cpus > 0)
 			additional_cpus = disabled_cpus;
 		else
 			additional_cpus = 0;
 	}
-#else
-	additional_cpus = 0;
-#endif
+
 	possible = num_processors + additional_cpus;
 	if (possible > NR_CPUS)
 		possible = NR_CPUS;
diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c
index 7066cb8..1884a8d 100644
--- a/arch/x86/kernel/sys_i386_32.c
+++ b/arch/x86/kernel/sys_i386_32.c
@@ -22,6 +22,8 @@
 #include <linux/uaccess.h>
 #include <linux/unistd.h>
 
+#include <asm/syscalls.h>
+
 asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
 			  unsigned long prot, unsigned long flags,
 			  unsigned long fd, unsigned long pgoff)
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 3b360ef..6bc211a 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -13,15 +13,17 @@
 #include <linux/utsname.h>
 #include <linux/personality.h>
 #include <linux/random.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/ia32.h>
+#include <asm/syscalls.h>
 
-asmlinkage long sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags,
-	unsigned long fd, unsigned long off)
+asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
+		unsigned long prot, unsigned long flags,
+		unsigned long fd, unsigned long off)
 {
 	long error;
-	struct file * file;
+	struct file *file;
 
 	error = -EINVAL;
 	if (off & ~PAGE_MASK)
@@ -56,9 +58,9 @@
 		   unmapped base down for this case. This can give
 		   conflicts with the heap, but we assume that glibc
 		   malloc knows how to fall back to mmap. Give it 1GB
-		   of playground for now. -AK */ 
-		*begin = 0x40000000; 
-		*end = 0x80000000;		
+		   of playground for now. -AK */
+		*begin = 0x40000000;
+		*end = 0x80000000;
 		if (current->flags & PF_RANDOMIZE) {
 			new_begin = randomize_range(*begin, *begin + 0x02000000, 0);
 			if (new_begin)
@@ -66,9 +68,9 @@
 		}
 	} else {
 		*begin = TASK_UNMAPPED_BASE;
-		*end = TASK_SIZE; 
+		*end = TASK_SIZE;
 	}
-} 
+}
 
 unsigned long
 arch_get_unmapped_area(struct file *filp, unsigned long addr,
@@ -78,11 +80,11 @@
 	struct vm_area_struct *vma;
 	unsigned long start_addr;
 	unsigned long begin, end;
-	
+
 	if (flags & MAP_FIXED)
 		return addr;
 
-	find_start_end(flags, &begin, &end); 
+	find_start_end(flags, &begin, &end);
 
 	if (len > end)
 		return -ENOMEM;
@@ -96,12 +98,12 @@
 	}
 	if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32))
 	    && len <= mm->cached_hole_size) {
-	        mm->cached_hole_size = 0;
+		mm->cached_hole_size = 0;
 		mm->free_area_cache = begin;
 	}
 	addr = mm->free_area_cache;
-	if (addr < begin) 
-		addr = begin; 
+	if (addr < begin)
+		addr = begin;
 	start_addr = addr;
 
 full_search:
@@ -127,7 +129,7 @@
 			return addr;
 		}
 		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
+			mm->cached_hole_size = vma->vm_start - addr;
 
 		addr = vma->vm_end;
 	}
@@ -177,7 +179,7 @@
 		vma = find_vma(mm, addr-len);
 		if (!vma || addr <= vma->vm_start)
 			/* remember the address as a hint for next time */
-			return (mm->free_area_cache = addr-len);
+			return mm->free_area_cache = addr-len;
 	}
 
 	if (mm->mmap_base < len)
@@ -194,7 +196,7 @@
 		vma = find_vma(mm, addr);
 		if (!vma || addr+len <= vma->vm_start)
 			/* remember the address as a hint for next time */
-			return (mm->free_area_cache = addr);
+			return mm->free_area_cache = addr;
 
 		/* remember the largest hole we saw so far */
 		if (addr + mm->cached_hole_size < vma->vm_start)
@@ -224,13 +226,13 @@
 }
 
 
-asmlinkage long sys_uname(struct new_utsname __user * name)
+asmlinkage long sys_uname(struct new_utsname __user *name)
 {
 	int err;
 	down_read(&uts_sem);
-	err = copy_to_user(name, utsname(), sizeof (*name));
+	err = copy_to_user(name, utsname(), sizeof(*name));
 	up_read(&uts_sem);
-	if (personality(current->personality) == PER_LINUX32) 
-		err |= copy_to_user(&name->machine, "i686", 5); 		
+	if (personality(current->personality) == PER_LINUX32)
+		err |= copy_to_user(&name->machine, "i686", 5);
 	return err ? -EFAULT : 0;
 }
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c
index 170d43c..3d1be4f 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/kernel/syscall_64.c
@@ -8,12 +8,12 @@
 #define __NO_STUBS
 
 #define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ;
-#undef _ASM_X86_64_UNISTD_H_
+#undef ASM_X86__UNISTD_64_H
 #include <asm/unistd_64.h>
 
 #undef __SYSCALL
 #define __SYSCALL(nr, sym) [nr] = sym,
-#undef _ASM_X86_64_UNISTD_H_
+#undef ASM_X86__UNISTD_64_H
 
 typedef void (*sys_call_ptr_t)(void);
 
diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c
index ffe3c66..bbecf8b 100644
--- a/arch/x86/kernel/time_32.c
+++ b/arch/x86/kernel/time_32.c
@@ -36,6 +36,7 @@
 #include <asm/arch_hooks.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
+#include <asm/timer.h>
 
 #include "do_timer.h"
 
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index ab6bf37..6bb7b85 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -10,6 +10,7 @@
 #include <asm/ldt.h>
 #include <asm/processor.h>
 #include <asm/proto.h>
+#include <asm/syscalls.h>
 
 #include "tls.h"
 
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index 513caac..7a31f10 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -32,6 +32,8 @@
 #include <linux/bug.h>
 #include <linux/nmi.h>
 #include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/io.h>
 
 #if defined(CONFIG_EDAC)
 #include <linux/edac.h>
@@ -45,9 +47,6 @@
 #include <asm/unwind.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
-#include <asm/nmi.h>
-#include <asm/smp.h>
-#include <asm/io.h>
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
 #include <asm/pda.h>
@@ -85,7 +84,8 @@
 
 void printk_address(unsigned long address, int reliable)
 {
-	printk(" [<%016lx>] %s%pS\n", address, reliable ? "": "? ", (void *) address);
+	printk(" [<%016lx>] %s%pS\n",
+			address, reliable ?	"" : "? ", (void *) address);
 }
 
 static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
@@ -98,7 +98,8 @@
 		[STACKFAULT_STACK - 1] = "#SS",
 		[MCE_STACK - 1] = "#MC",
 #if DEBUG_STKSZ > EXCEPTION_STKSZ
-		[N_EXCEPTION_STACKS ... N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
+		[N_EXCEPTION_STACKS ...
+			N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
 #endif
 	};
 	unsigned k;
@@ -163,7 +164,7 @@
 }
 
 /*
- * x86-64 can have up to three kernel stacks: 
+ * x86-64 can have up to three kernel stacks:
  * process stack
  * interrupt stack
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
@@ -219,7 +220,7 @@
 		const struct stacktrace_ops *ops, void *data)
 {
 	const unsigned cpu = get_cpu();
-	unsigned long *irqstack_end = (unsigned long*)cpu_pda(cpu)->irqstackptr;
+	unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr;
 	unsigned used = 0;
 	struct thread_info *tinfo;
 
@@ -237,7 +238,7 @@
 	if (!bp) {
 		if (task == current) {
 			/* Grab bp right from our regs */
-			asm("movq %%rbp, %0" : "=r" (bp) :);
+			asm("movq %%rbp, %0" : "=r" (bp) : );
 		} else {
 			/* bp is the last reg pushed by switch_to */
 			bp = *(unsigned long *) task->thread.sp;
@@ -339,9 +340,8 @@
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp, char *log_lvl)
 {
-	printk("\nCall Trace:\n");
+	printk("Call Trace:\n");
 	dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
-	printk("\n");
 }
 
 void show_trace(struct task_struct *task, struct pt_regs *regs,
@@ -357,11 +357,15 @@
 	unsigned long *stack;
 	int i;
 	const int cpu = smp_processor_id();
-	unsigned long *irqstack_end = (unsigned long *) (cpu_pda(cpu)->irqstackptr);
-	unsigned long *irqstack = (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
+	unsigned long *irqstack_end =
+		(unsigned long *) (cpu_pda(cpu)->irqstackptr);
+	unsigned long *irqstack =
+		(unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
 
-	// debugging aid: "show_stack(NULL, NULL);" prints the
-	// back trace for this cpu.
+	/*
+	 * debugging aid: "show_stack(NULL, NULL);" prints the
+	 * back trace for this cpu.
+	 */
 
 	if (sp == NULL) {
 		if (task)
@@ -386,6 +390,7 @@
 		printk(" %016lx", *stack++);
 		touch_nmi_watchdog();
 	}
+	printk("\n");
 	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
 
@@ -404,7 +409,7 @@
 
 #ifdef CONFIG_FRAME_POINTER
 	if (!bp)
-		asm("movq %%rbp, %0" : "=r" (bp):);
+		asm("movq %%rbp, %0" : "=r" (bp) : );
 #endif
 
 	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
@@ -414,7 +419,6 @@
 		init_utsname()->version);
 	show_trace(NULL, NULL, &stack, bp);
 }
-
 EXPORT_SYMBOL(dump_stack);
 
 void show_registers(struct pt_regs *regs)
@@ -443,7 +447,6 @@
 		printk("Stack: ");
 		show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
 				regs->bp, "");
-		printk("\n");
 
 		printk(KERN_EMERG "Code: ");
 
@@ -493,7 +496,7 @@
 	raw_local_irq_save(flags);
 	cpu = smp_processor_id();
 	if (!__raw_spin_trylock(&die_lock)) {
-		if (cpu == die_owner) 
+		if (cpu == die_owner)
 			/* nested oops. should stop eventually */;
 		else
 			__raw_spin_lock(&die_lock);
@@ -638,7 +641,7 @@
 }
 
 #define DO_ERROR(trapnr, signr, str, name) \
-asmlinkage void do_##name(struct pt_regs * regs, long error_code)	\
+asmlinkage void do_##name(struct pt_regs *regs, long error_code)	\
 {									\
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr)	\
 							== NOTIFY_STOP)	\
@@ -648,7 +651,7 @@
 }
 
 #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr)		\
-asmlinkage void do_##name(struct pt_regs * regs, long error_code)	\
+asmlinkage void do_##name(struct pt_regs *regs, long error_code)	\
 {									\
 	siginfo_t info;							\
 	info.si_signo = signr;						\
@@ -683,7 +686,7 @@
 	preempt_conditional_cli(regs);
 }
 
-asmlinkage void do_double_fault(struct pt_regs * regs, long error_code)
+asmlinkage void do_double_fault(struct pt_regs *regs, long error_code)
 {
 	static const char str[] = "double fault";
 	struct task_struct *tsk = current;
@@ -778,9 +781,10 @@
 }
 
 static notrace __kprobes void
-unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
+unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 {
-	if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
+	if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) ==
+			NOTIFY_STOP)
 		return;
 	printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n",
 		reason);
@@ -882,7 +886,7 @@
 	else if (user_mode(eregs))
 		regs = task_pt_regs(current);
 	/* Exception from kernel and interrupts are enabled. Move to
- 	   kernel process stack. */
+	   kernel process stack. */
 	else if (eregs->flags & X86_EFLAGS_IF)
 		regs = (struct pt_regs *)(eregs->sp -= sizeof(struct pt_regs));
 	if (eregs != regs)
@@ -891,7 +895,7 @@
 }
 
 /* runs on IST stack. */
-asmlinkage void __kprobes do_debug(struct pt_regs * regs,
+asmlinkage void __kprobes do_debug(struct pt_regs *regs,
 				   unsigned long error_code)
 {
 	struct task_struct *tsk = current;
@@ -1035,7 +1039,7 @@
 
 asmlinkage void bad_intr(void)
 {
-	printk("bad interrupt"); 
+	printk("bad interrupt");
 }
 
 asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs)
@@ -1047,7 +1051,7 @@
 
 	conditional_sti(regs);
 	if (!user_mode(regs) &&
-        	kernel_math_error(regs, "kernel simd math error", 19))
+			kernel_math_error(regs, "kernel simd math error", 19))
 		return;
 
 	/*
@@ -1092,7 +1096,7 @@
 	force_sig_info(SIGFPE, &info, task);
 }
 
-asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs)
+asmlinkage void do_spurious_interrupt_bug(struct pt_regs *regs)
 {
 }
 
@@ -1149,8 +1153,10 @@
 	set_intr_gate(0, &divide_error);
 	set_intr_gate_ist(1, &debug, DEBUG_STACK);
 	set_intr_gate_ist(2, &nmi, NMI_STACK);
- 	set_system_gate_ist(3, &int3, DEBUG_STACK); /* int3 can be called from all */
-	set_system_gate(4, &overflow); /* int4 can be called from all */
+	/* int3 can be called from all */
+	set_system_gate_ist(3, &int3, DEBUG_STACK);
+	/* int4 can be called from all */
+	set_system_gate(4, &overflow);
 	set_intr_gate(5, &bounds);
 	set_intr_gate(6, &invalid_op);
 	set_intr_gate(7, &device_not_available);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 8f98e9d..161bb85 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -104,7 +104,7 @@
 /*
  * Read TSC and the reference counters. Take care of SMI disturbance
  */
-static u64 tsc_read_refs(u64 *pm, u64 *hpet)
+static u64 tsc_read_refs(u64 *p, int hpet)
 {
 	u64 t1, t2;
 	int i;
@@ -112,9 +112,9 @@
 	for (i = 0; i < MAX_RETRIES; i++) {
 		t1 = get_cycles();
 		if (hpet)
-			*hpet = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF;
+			*p = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF;
 		else
-			*pm = acpi_pm_read_early();
+			*p = acpi_pm_read_early();
 		t2 = get_cycles();
 		if ((t2 - t1) < SMI_TRESHOLD)
 			return t2;
@@ -123,13 +123,59 @@
 }
 
 /*
+ * Calculate the TSC frequency from HPET reference
+ */
+static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2)
+{
+	u64 tmp;
+
+	if (hpet2 < hpet1)
+		hpet2 += 0x100000000ULL;
+	hpet2 -= hpet1;
+	tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
+	do_div(tmp, 1000000);
+	do_div(deltatsc, tmp);
+
+	return (unsigned long) deltatsc;
+}
+
+/*
+ * Calculate the TSC frequency from PMTimer reference
+ */
+static unsigned long calc_pmtimer_ref(u64 deltatsc, u64 pm1, u64 pm2)
+{
+	u64 tmp;
+
+	if (!pm1 && !pm2)
+		return ULONG_MAX;
+
+	if (pm2 < pm1)
+		pm2 += (u64)ACPI_PM_OVRRUN;
+	pm2 -= pm1;
+	tmp = pm2 * 1000000000LL;
+	do_div(tmp, PMTMR_TICKS_PER_SEC);
+	do_div(deltatsc, tmp);
+
+	return (unsigned long) deltatsc;
+}
+
+#define CAL_MS		10
+#define CAL_LATCH	(CLOCK_TICK_RATE / (1000 / CAL_MS))
+#define CAL_PIT_LOOPS	1000
+
+#define CAL2_MS		50
+#define CAL2_LATCH	(CLOCK_TICK_RATE / (1000 / CAL2_MS))
+#define CAL2_PIT_LOOPS	5000
+
+
+/*
  * Try to calibrate the TSC against the Programmable
  * Interrupt Timer and return the frequency of the TSC
  * in kHz.
  *
  * Return ULONG_MAX on failure to calibrate.
  */
-static unsigned long pit_calibrate_tsc(void)
+static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin)
 {
 	u64 tsc, t1, t2, delta;
 	unsigned long tscmin, tscmax;
@@ -144,8 +190,8 @@
 	 * (LSB then MSB) to begin countdown.
 	 */
 	outb(0xb0, 0x43);
-	outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
-	outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42);
+	outb(latch & 0xff, 0x42);
+	outb(latch >> 8, 0x42);
 
 	tsc = t1 = t2 = get_cycles();
 
@@ -166,31 +212,154 @@
 	/*
 	 * Sanity checks:
 	 *
-	 * If we were not able to read the PIT more than 5000
+	 * If we were not able to read the PIT more than loopmin
 	 * times, then we have been hit by a massive SMI
 	 *
 	 * If the maximum is 10 times larger than the minimum,
 	 * then we got hit by an SMI as well.
 	 */
-	if (pitcnt < 5000 || tscmax > 10 * tscmin)
+	if (pitcnt < loopmin || tscmax > 10 * tscmin)
 		return ULONG_MAX;
 
 	/* Calculate the PIT value */
 	delta = t2 - t1;
-	do_div(delta, 50);
+	do_div(delta, ms);
 	return delta;
 }
 
+/*
+ * This reads the current MSB of the PIT counter, and
+ * checks if we are running on sufficiently fast and
+ * non-virtualized hardware.
+ *
+ * Our expectations are:
+ *
+ *  - the PIT is running at roughly 1.19MHz
+ *
+ *  - each IO is going to take about 1us on real hardware,
+ *    but we allow it to be much faster (by a factor of 10) or
+ *    _slightly_ slower (ie we allow up to a 2us read+counter
+ *    update - anything else implies a unacceptably slow CPU
+ *    or PIT for the fast calibration to work.
+ *
+ *  - with 256 PIT ticks to read the value, we have 214us to
+ *    see the same MSB (and overhead like doing a single TSC
+ *    read per MSB value etc).
+ *
+ *  - We're doing 2 reads per loop (LSB, MSB), and we expect
+ *    them each to take about a microsecond on real hardware.
+ *    So we expect a count value of around 100. But we'll be
+ *    generous, and accept anything over 50.
+ *
+ *  - if the PIT is stuck, and we see *many* more reads, we
+ *    return early (and the next caller of pit_expect_msb()
+ *    then consider it a failure when they don't see the
+ *    next expected value).
+ *
+ * These expectations mean that we know that we have seen the
+ * transition from one expected value to another with a fairly
+ * high accuracy, and we didn't miss any events. We can thus
+ * use the TSC value at the transitions to calculate a pretty
+ * good value for the TSC frequencty.
+ */
+static inline int pit_expect_msb(unsigned char val)
+{
+	int count = 0;
+
+	for (count = 0; count < 50000; count++) {
+		/* Ignore LSB */
+		inb(0x42);
+		if (inb(0x42) != val)
+			break;
+	}
+	return count > 50;
+}
+
+/*
+ * How many MSB values do we want to see? We aim for a
+ * 15ms calibration, which assuming a 2us counter read
+ * error should give us roughly 150 ppm precision for
+ * the calibration.
+ */
+#define QUICK_PIT_MS 15
+#define QUICK_PIT_ITERATIONS (QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
+
+static unsigned long quick_pit_calibrate(void)
+{
+	/* Set the Gate high, disable speaker */
+	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
+
+	/*
+	 * Counter 2, mode 0 (one-shot), binary count
+	 *
+	 * NOTE! Mode 2 decrements by two (and then the
+	 * output is flipped each time, giving the same
+	 * final output frequency as a decrement-by-one),
+	 * so mode 0 is much better when looking at the
+	 * individual counts.
+	 */
+	outb(0xb0, 0x43);
+
+	/* Start at 0xffff */
+	outb(0xff, 0x42);
+	outb(0xff, 0x42);
+
+	if (pit_expect_msb(0xff)) {
+		int i;
+		u64 t1, t2, delta;
+		unsigned char expect = 0xfe;
+
+		t1 = get_cycles();
+		for (i = 0; i < QUICK_PIT_ITERATIONS; i++, expect--) {
+			if (!pit_expect_msb(expect))
+				goto failed;
+		}
+		t2 = get_cycles();
+
+		/*
+		 * Make sure we can rely on the second TSC timestamp:
+		 */
+		if (!pit_expect_msb(expect))
+			goto failed;
+
+		/*
+		 * Ok, if we get here, then we've seen the
+		 * MSB of the PIT decrement QUICK_PIT_ITERATIONS
+		 * times, and each MSB had many hits, so we never
+		 * had any sudden jumps.
+		 *
+		 * As a result, we can depend on there not being
+		 * any odd delays anywhere, and the TSC reads are
+		 * reliable.
+		 *
+		 * kHz = ticks / time-in-seconds / 1000;
+		 * kHz = (t2 - t1) / (QPI * 256 / PIT_TICK_RATE) / 1000
+		 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (QPI * 256 * 1000)
+		 */
+		delta = (t2 - t1)*PIT_TICK_RATE;
+		do_div(delta, QUICK_PIT_ITERATIONS*256*1000);
+		printk("Fast TSC calibration using PIT\n");
+		return delta;
+	}
+failed:
+	return 0;
+}
 
 /**
  * native_calibrate_tsc - calibrate the tsc on boot
  */
 unsigned long native_calibrate_tsc(void)
 {
-	u64 tsc1, tsc2, delta, pm1, pm2, hpet1, hpet2;
+	u64 tsc1, tsc2, delta, ref1, ref2;
 	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-	unsigned long flags;
-	int hpet = is_hpet_enabled(), i;
+	unsigned long flags, latch, ms, fast_calibrate;
+	int hpet = is_hpet_enabled(), i, loopmin;
+
+	local_irq_save(flags);
+	fast_calibrate = quick_pit_calibrate();
+	local_irq_restore(flags);
+	if (fast_calibrate)
+		return fast_calibrate;
 
 	/*
 	 * Run 5 calibration loops to get the lowest frequency value
@@ -216,7 +385,13 @@
 	 * calibration delay loop as we have to wait for a certain
 	 * amount of time anyway.
 	 */
-	for (i = 0; i < 5; i++) {
+
+	/* Preset PIT loop values */
+	latch = CAL_LATCH;
+	ms = CAL_MS;
+	loopmin = CAL_PIT_LOOPS;
+
+	for (i = 0; i < 3; i++) {
 		unsigned long tsc_pit_khz;
 
 		/*
@@ -226,16 +401,16 @@
 		 * read the end value.
 		 */
 		local_irq_save(flags);
-		tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL);
-		tsc_pit_khz = pit_calibrate_tsc();
-		tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL);
+		tsc1 = tsc_read_refs(&ref1, hpet);
+		tsc_pit_khz = pit_calibrate_tsc(latch, ms, loopmin);
+		tsc2 = tsc_read_refs(&ref2, hpet);
 		local_irq_restore(flags);
 
 		/* Pick the lowest PIT TSC calibration so far */
 		tsc_pit_min = min(tsc_pit_min, tsc_pit_khz);
 
 		/* hpet or pmtimer available ? */
-		if (!hpet && !pm1 && !pm2)
+		if (!hpet && !ref1 && !ref2)
 			continue;
 
 		/* Check, whether the sampling was disturbed by an SMI */
@@ -243,23 +418,41 @@
 			continue;
 
 		tsc2 = (tsc2 - tsc1) * 1000000LL;
+		if (hpet)
+			tsc2 = calc_hpet_ref(tsc2, ref1, ref2);
+		else
+			tsc2 = calc_pmtimer_ref(tsc2, ref1, ref2);
 
-		if (hpet) {
-			if (hpet2 < hpet1)
-				hpet2 += 0x100000000ULL;
-			hpet2 -= hpet1;
-			tsc1 = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
-			do_div(tsc1, 1000000);
-		} else {
-			if (pm2 < pm1)
-				pm2 += (u64)ACPI_PM_OVRRUN;
-			pm2 -= pm1;
-			tsc1 = pm2 * 1000000000LL;
-			do_div(tsc1, PMTMR_TICKS_PER_SEC);
+		tsc_ref_min = min(tsc_ref_min, (unsigned long) tsc2);
+
+		/* Check the reference deviation */
+		delta = ((u64) tsc_pit_min) * 100;
+		do_div(delta, tsc_ref_min);
+
+		/*
+		 * If both calibration results are inside a 10% window
+		 * then we can be sure, that the calibration
+		 * succeeded. We break out of the loop right away. We
+		 * use the reference value, as it is more precise.
+		 */
+		if (delta >= 90 && delta <= 110) {
+			printk(KERN_INFO
+			       "TSC: PIT calibration matches %s. %d loops\n",
+			       hpet ? "HPET" : "PMTIMER", i + 1);
+			return tsc_ref_min;
 		}
 
-		do_div(tsc2, tsc1);
-		tsc_ref_min = min(tsc_ref_min, (unsigned long) tsc2);
+		/*
+		 * Check whether PIT failed more than once. This
+		 * happens in virtualized environments. We need to
+		 * give the virtual PC a slightly longer timeframe for
+		 * the HPET/PMTIMER to make the result precise.
+		 */
+		if (i == 1 && tsc_pit_min == ULONG_MAX) {
+			latch = CAL2_LATCH;
+			ms = CAL2_MS;
+			loopmin = CAL2_PIT_LOOPS;
+		}
 	}
 
 	/*
@@ -270,7 +463,7 @@
 		printk(KERN_WARNING "TSC: Unable to calibrate against PIT\n");
 
 		/* We don't have an alternative source, disable TSC */
-		if (!hpet && !pm1 && !pm2) {
+		if (!hpet && !ref1 && !ref2) {
 			printk("TSC: No reference (HPET/PMTIMER) available\n");
 			return 0;
 		}
@@ -278,7 +471,7 @@
 		/* The alternative source failed as well, disable TSC */
 		if (tsc_ref_min == ULONG_MAX) {
 			printk(KERN_WARNING "TSC: HPET/PMTIMER calibration "
-			       "failed due to SMI disturbance.\n");
+			       "failed.\n");
 			return 0;
 		}
 
@@ -290,44 +483,25 @@
 	}
 
 	/* We don't have an alternative source, use the PIT calibration value */
-	if (!hpet && !pm1 && !pm2) {
+	if (!hpet && !ref1 && !ref2) {
 		printk(KERN_INFO "TSC: Using PIT calibration value\n");
 		return tsc_pit_min;
 	}
 
 	/* The alternative source failed, use the PIT calibration value */
 	if (tsc_ref_min == ULONG_MAX) {
-		printk(KERN_WARNING "TSC: HPET/PMTIMER calibration failed due "
-		       "to SMI disturbance. Using PIT calibration\n");
+		printk(KERN_WARNING "TSC: HPET/PMTIMER calibration failed. "
+		       "Using PIT calibration\n");
 		return tsc_pit_min;
 	}
 
-	/* Check the reference deviation */
-	delta = ((u64) tsc_pit_min) * 100;
-	do_div(delta, tsc_ref_min);
-
-	/*
-	 * If both calibration results are inside a 5% window, the we
-	 * use the lower frequency of those as it is probably the
-	 * closest estimate.
-	 */
-	if (delta >= 95 && delta <= 105) {
-		printk(KERN_INFO "TSC: PIT calibration confirmed by %s.\n",
-		       hpet ? "HPET" : "PMTIMER");
-		printk(KERN_INFO "TSC: using %s calibration value\n",
-		       tsc_pit_min <= tsc_ref_min ? "PIT" :
-		       hpet ? "HPET" : "PMTIMER");
-		return tsc_pit_min <= tsc_ref_min ? tsc_pit_min : tsc_ref_min;
-	}
-
-	printk(KERN_WARNING "TSC: PIT calibration deviates from %s: %lu %lu.\n",
-	       hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min);
-
 	/*
 	 * The calibration values differ too much. In doubt, we use
 	 * the PIT value as we know that there are PMTIMERs around
-	 * running at double speed.
+	 * running at double speed. At least we let the user know:
 	 */
+	printk(KERN_WARNING "TSC: PIT calibration deviates from %s: %lu %lu.\n",
+	       hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min);
 	printk(KERN_INFO "TSC: Using PIT calibration value\n");
 	return tsc_pit_min;
 }
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 594ef47..61a97e6 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -25,45 +25,31 @@
 #include <asm/visws/cobalt.h>
 #include <asm/visws/piix4.h>
 #include <asm/arch_hooks.h>
+#include <asm/io_apic.h>
 #include <asm/fixmap.h>
 #include <asm/reboot.h>
 #include <asm/setup.h>
 #include <asm/e820.h>
-#include <asm/smp.h>
 #include <asm/io.h>
 
 #include <mach_ipi.h>
 
 #include "mach_apic.h"
 
-#include <linux/init.h>
-#include <linux/smp.h>
-
 #include <linux/kernel_stat.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
 
-#include <asm/io.h>
-#include <asm/apic.h>
 #include <asm/i8259.h>
 #include <asm/irq_vectors.h>
-#include <asm/visws/cobalt.h>
 #include <asm/visws/lithium.h>
-#include <asm/visws/piix4.h>
 
 #include <linux/sched.h>
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
 
 extern int no_broadcast;
 
-#include <asm/io.h>
 #include <asm/apic.h>
-#include <asm/arch_hooks.h>
-#include <asm/visws/cobalt.h>
-#include <asm/visws/lithium.h>
 
 char visws_board_type	= -1;
 char visws_board_rev	= -1;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 38f566f..4eeb5cf 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -46,6 +46,7 @@
 #include <asm/io.h>
 #include <asm/tlbflush.h>
 #include <asm/irq.h>
+#include <asm/syscalls.h>
 
 /*
  * Known problems:
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 6ca515d..8c9ad02 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -235,7 +235,7 @@
 				const void *desc)
 {
 	u32 *ldt_entry = (u32 *)desc;
-	vmi_ops.write_idt_entry(dt, entry, ldt_entry[0], ldt_entry[1]);
+	vmi_ops.write_ldt_entry(dt, entry, ldt_entry[0], ldt_entry[1]);
 }
 
 static void vmi_load_sp0(struct tss_struct *tss,
@@ -393,13 +393,13 @@
 }
 #endif
 
-static void vmi_allocate_pte(struct mm_struct *mm, u32 pfn)
+static void vmi_allocate_pte(struct mm_struct *mm, unsigned long pfn)
 {
 	vmi_set_page_type(pfn, VMI_PAGE_L1);
 	vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
 }
 
-static void vmi_allocate_pmd(struct mm_struct *mm, u32 pfn)
+static void vmi_allocate_pmd(struct mm_struct *mm, unsigned long pfn)
 {
  	/*
 	 * This call comes in very early, before mem_map is setup.
@@ -410,20 +410,20 @@
 	vmi_ops.allocate_page(pfn, VMI_PAGE_L2, 0, 0, 0);
 }
 
-static void vmi_allocate_pmd_clone(u32 pfn, u32 clonepfn, u32 start, u32 count)
+static void vmi_allocate_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count)
 {
  	vmi_set_page_type(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE);
 	vmi_check_page_type(clonepfn, VMI_PAGE_L2);
 	vmi_ops.allocate_page(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE, clonepfn, start, count);
 }
 
-static void vmi_release_pte(u32 pfn)
+static void vmi_release_pte(unsigned long pfn)
 {
 	vmi_ops.release_page(pfn, VMI_PAGE_L1);
 	vmi_set_page_type(pfn, VMI_PAGE_NORMAL);
 }
 
-static void vmi_release_pmd(u32 pfn)
+static void vmi_release_pmd(unsigned long pfn)
 {
 	vmi_ops.release_page(pfn, VMI_PAGE_L2);
 	vmi_set_page_type(pfn, VMI_PAGE_NORMAL);
diff --git a/arch/x86/lib/msr-on-cpu.c b/arch/x86/lib/msr-on-cpu.c
index 01b868b..321cf72 100644
--- a/arch/x86/lib/msr-on-cpu.c
+++ b/arch/x86/lib/msr-on-cpu.c
@@ -16,37 +16,46 @@
 	rdmsr(rv->msr_no, rv->l, rv->h);
 }
 
-static void __rdmsr_safe_on_cpu(void *info)
+static void __wrmsr_on_cpu(void *info)
 {
 	struct msr_info *rv = info;
 
-	rv->err = rdmsr_safe(rv->msr_no, &rv->l, &rv->h);
+	wrmsr(rv->msr_no, rv->l, rv->h);
 }
 
-static int _rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h, int safe)
+int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
 {
-	int err = 0;
+	int err;
 	struct msr_info rv;
 
 	rv.msr_no = msr_no;
-	if (safe) {
-		err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu,
-					       &rv, 1);
-		err = err ? err : rv.err;
-	} else {
-		err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
-	}
+	err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
 	*l = rv.l;
 	*h = rv.h;
 
 	return err;
 }
 
-static void __wrmsr_on_cpu(void *info)
+int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+	int err;
+	struct msr_info rv;
+
+	rv.msr_no = msr_no;
+	rv.l = l;
+	rv.h = h;
+	err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
+
+	return err;
+}
+
+/* These "safe" variants are slower and should be used when the target MSR
+   may not actually exist. */
+static void __rdmsr_safe_on_cpu(void *info)
 {
 	struct msr_info *rv = info;
 
-	wrmsr(rv->msr_no, rv->l, rv->h);
+	rv->err = rdmsr_safe(rv->msr_no, &rv->l, &rv->h);
 }
 
 static void __wrmsr_safe_on_cpu(void *info)
@@ -56,45 +65,30 @@
 	rv->err = wrmsr_safe(rv->msr_no, rv->l, rv->h);
 }
 
-static int _wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h, int safe)
+int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
 {
-	int err = 0;
+	int err;
+	struct msr_info rv;
+
+	rv.msr_no = msr_no;
+	err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
+	*l = rv.l;
+	*h = rv.h;
+
+	return err ? err : rv.err;
+}
+
+int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+	int err;
 	struct msr_info rv;
 
 	rv.msr_no = msr_no;
 	rv.l = l;
 	rv.h = h;
-	if (safe) {
-		err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu,
-					       &rv, 1);
-		err = err ? err : rv.err;
-	} else {
-		err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
-	}
+	err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
 
-	return err;
-}
-
-int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
-	return _wrmsr_on_cpu(cpu, msr_no, l, h, 0);
-}
-
-int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
-	return _rdmsr_on_cpu(cpu, msr_no, l, h, 0);
-}
-
-/* These "safe" variants are slower and should be used when the target MSR
-   may not actually exist. */
-int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
-	return _wrmsr_on_cpu(cpu, msr_no, l, h, 1);
-}
-
-int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
-	return _rdmsr_on_cpu(cpu, msr_no, l, h, 1);
+	return err ? err : rv.err;
 }
 
 EXPORT_SYMBOL(rdmsr_on_cpu);
diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
index 94972e7..82004d2 100644
--- a/arch/x86/lib/string_32.c
+++ b/arch/x86/lib/string_32.c
@@ -22,7 +22,7 @@
 		"testb %%al,%%al\n\t"
 		"jne 1b"
 		: "=&S" (d0), "=&D" (d1), "=&a" (d2)
-		:"0" (src), "1" (dest) : "memory");
+		: "0" (src), "1" (dest) : "memory");
 	return dest;
 }
 EXPORT_SYMBOL(strcpy);
@@ -42,7 +42,7 @@
 		"stosb\n"
 		"2:"
 		: "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
-		:"0" (src), "1" (dest), "2" (count) : "memory");
+		: "0" (src), "1" (dest), "2" (count) : "memory");
 	return dest;
 }
 EXPORT_SYMBOL(strncpy);
@@ -60,7 +60,7 @@
 		"testb %%al,%%al\n\t"
 		"jne 1b"
 		: "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
-		: "0" (src), "1" (dest), "2" (0), "3" (0xffffffffu): "memory");
+		: "0" (src), "1" (dest), "2" (0), "3" (0xffffffffu) : "memory");
 	return dest;
 }
 EXPORT_SYMBOL(strcat);
@@ -105,9 +105,9 @@
 		"2:\tsbbl %%eax,%%eax\n\t"
 		"orb $1,%%al\n"
 		"3:"
-		:"=a" (res), "=&S" (d0), "=&D" (d1)
-		:"1" (cs), "2" (ct)
-		:"memory");
+		: "=a" (res), "=&S" (d0), "=&D" (d1)
+		: "1" (cs), "2" (ct)
+		: "memory");
 	return res;
 }
 EXPORT_SYMBOL(strcmp);
@@ -130,9 +130,9 @@
 		"3:\tsbbl %%eax,%%eax\n\t"
 		"orb $1,%%al\n"
 		"4:"
-		:"=a" (res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
-		:"1" (cs), "2" (ct), "3" (count)
-		:"memory");
+		: "=a" (res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
+		: "1" (cs), "2" (ct), "3" (count)
+		: "memory");
 	return res;
 }
 EXPORT_SYMBOL(strncmp);
@@ -152,9 +152,9 @@
 		"movl $1,%1\n"
 		"2:\tmovl %1,%0\n\t"
 		"decl %0"
-		:"=a" (res), "=&S" (d0)
-		:"1" (s), "0" (c)
-		:"memory");
+		: "=a" (res), "=&S" (d0)
+		: "1" (s), "0" (c)
+		: "memory");
 	return res;
 }
 EXPORT_SYMBOL(strchr);
@@ -169,9 +169,9 @@
 		"scasb\n\t"
 		"notl %0\n\t"
 		"decl %0"
-		:"=c" (res), "=&D" (d0)
-		:"1" (s), "a" (0), "0" (0xffffffffu)
-		:"memory");
+		: "=c" (res), "=&D" (d0)
+		: "1" (s), "a" (0), "0" (0xffffffffu)
+		: "memory");
 	return res;
 }
 EXPORT_SYMBOL(strlen);
@@ -189,9 +189,9 @@
 		"je 1f\n\t"
 		"movl $1,%0\n"
 		"1:\tdecl %0"
-		:"=D" (res), "=&c" (d0)
-		:"a" (c), "0" (cs), "1" (count)
-		:"memory");
+		: "=D" (res), "=&c" (d0)
+		: "a" (c), "0" (cs), "1" (count)
+		: "memory");
 	return res;
 }
 EXPORT_SYMBOL(memchr);
@@ -228,9 +228,9 @@
 		"cmpl $-1,%1\n\t"
 		"jne 1b\n"
 		"3:\tsubl %2,%0"
-		:"=a" (res), "=&d" (d0)
-		:"c" (s), "1" (count)
-		:"memory");
+		: "=a" (res), "=&d" (d0)
+		: "c" (s), "1" (count)
+		: "memory");
 	return res;
 }
 EXPORT_SYMBOL(strnlen);
diff --git a/arch/x86/lib/strstr_32.c b/arch/x86/lib/strstr_32.c
index 42e8a50..8e2d55f 100644
--- a/arch/x86/lib/strstr_32.c
+++ b/arch/x86/lib/strstr_32.c
@@ -23,9 +23,9 @@
 	"jne 1b\n\t"
 	"xorl %%eax,%%eax\n\t"
 	"2:"
-	:"=a" (__res), "=&c" (d0), "=&S" (d1)
-	:"0" (0), "1" (0xffffffff), "2" (cs), "g" (ct)
-	:"dx", "di");
+	: "=a" (__res), "=&c" (d0), "=&S" (d1)
+	: "0" (0), "1" (0xffffffff), "2" (cs), "g" (ct)
+	: "dx", "di");
 return __res;
 }
 
diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c
index 3d31783..3f2cf11 100644
--- a/arch/x86/mach-default/setup.c
+++ b/arch/x86/mach-default/setup.c
@@ -10,13 +10,15 @@
 #include <asm/e820.h>
 #include <asm/setup.h>
 
+#include <mach_ipi.h>
+
 #ifdef CONFIG_HOTPLUG_CPU
 #define DEFAULT_SEND_IPI	(1)
 #else
 #define DEFAULT_SEND_IPI	(0)
 #endif
 
-int no_broadcast=DEFAULT_SEND_IPI;
+int no_broadcast = DEFAULT_SEND_IPI;
 
 /**
  * pre_intr_init_hook - initialisation prior to setting up interrupt vectors
diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c
index 62fa440..847c164 100644
--- a/arch/x86/mm/discontig_32.c
+++ b/arch/x86/mm/discontig_32.c
@@ -328,7 +328,7 @@
 
 	get_memcfg_numa();
 
-	kva_pages = round_up(calculate_numa_remap_pages(), PTRS_PER_PTE);
+	kva_pages = roundup(calculate_numa_remap_pages(), PTRS_PER_PTE);
 
 	kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
 	do {
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index a20d1fa..e7277cb 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -148,8 +148,8 @@
 	 * we have now. "break" is either changing perms, levels or
 	 * address space marker.
 	 */
-	prot = pgprot_val(new_prot) & ~(PTE_PFN_MASK);
-	cur = pgprot_val(st->current_prot) & ~(PTE_PFN_MASK);
+	prot = pgprot_val(new_prot) & PTE_FLAGS_MASK;
+	cur = pgprot_val(st->current_prot) & PTE_FLAGS_MASK;
 
 	if (!st->level) {
 		/* First entry */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 455f3fe..8f92cac 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -35,6 +35,7 @@
 #include <asm/tlbflush.h>
 #include <asm/proto.h>
 #include <asm-generic/sections.h>
+#include <asm/traps.h>
 
 /*
  * Page fault error code bits
@@ -357,8 +358,6 @@
 	return 0;
 }
 
-void do_invalid_op(struct pt_regs *, unsigned long);
-
 static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
 {
 #ifdef CONFIG_X86_F00F_BUG
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 60ec1d0..6b9a935 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -47,6 +47,7 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
+#include <asm/smp.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index d3746ef..770536e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -225,7 +225,7 @@
 void __init cleanup_highmap(void)
 {
 	unsigned long vaddr = __START_KERNEL_map;
-	unsigned long end = round_up((unsigned long)_end, PMD_SIZE) - 1;
+	unsigned long end = roundup((unsigned long)_end, PMD_SIZE) - 1;
 	pmd_t *pmd = level2_kernel_pgt;
 	pmd_t *last_pmd = pmd + PTRS_PER_PMD;
 
@@ -451,14 +451,14 @@
 	unsigned long puds, pmds, ptes, tables, start;
 
 	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
-	tables = round_up(puds * sizeof(pud_t), PAGE_SIZE);
+	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
 	if (direct_gbpages) {
 		unsigned long extra;
 		extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
 		pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
 	} else
 		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
-	tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
+	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
 
 	if (cpu_has_pse) {
 		unsigned long extra;
@@ -466,7 +466,7 @@
 		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	} else
 		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	tables += round_up(ptes * sizeof(pte_t), PAGE_SIZE);
+	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
 
 	/*
 	 * RED-PEN putting page tables only on node 0 could
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index d4b6e6a..cac6da5 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -421,7 +421,7 @@
 	return;
 }
 
-int __initdata early_ioremap_debug;
+static int __initdata early_ioremap_debug;
 
 static int __init early_ioremap_debug_setup(char *str)
 {
@@ -547,7 +547,7 @@
 }
 
 
-int __initdata early_ioremap_nested;
+static int __initdata early_ioremap_nested;
 
 static int __init check_early_ioremap_leak(void)
 {
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index a4dd793..cebcbf1 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -79,7 +79,7 @@
 		return 0;
 
 	addr = 0x8000;
-	nodemap_size = round_up(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
+	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
 	nodemap_addr = find_e820_area(addr, max_pfn<<PAGE_SHIFT,
 				      nodemap_size, L1_CACHE_BYTES);
 	if (nodemap_addr == -1UL) {
@@ -176,10 +176,10 @@
 	unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
 	unsigned long bootmap_start, nodedata_phys;
 	void *bootmap;
-	const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE);
+	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	int nid;
 
-	start = round_up(start, ZONE_ALIGN);
+	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
 	       start, end);
@@ -210,9 +210,9 @@
 	bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
 	nid = phys_to_nid(nodedata_phys);
 	if (nid == nodeid)
-		bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+		bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
 	else
-		bootmap_start = round_up(start, PAGE_SIZE);
+		bootmap_start = roundup(start, PAGE_SIZE);
 	/*
 	 * SMP_CACHE_BYTES could be enough, but init_bootmem_node like
 	 * to use that to align to PAGE_SIZE
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 43e2f84..898fad6 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -84,7 +84,7 @@
 
 static inline unsigned long highmap_end_pfn(void)
 {
-	return __pa(round_up((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT;
+	return __pa(roundup((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT;
 }
 
 #endif
@@ -906,11 +906,13 @@
 {
 	return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_RW));
 }
+EXPORT_SYMBOL_GPL(set_memory_ro);
 
 int set_memory_rw(unsigned long addr, int numpages)
 {
 	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_RW));
 }
+EXPORT_SYMBOL_GPL(set_memory_rw);
 
 int set_memory_np(unsigned long addr, int numpages)
 {
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index d503027..86f2ffc 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -63,10 +63,8 @@
 #define UNSHARED_PTRS_PER_PGD				\
 	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
 
-static void pgd_ctor(void *p)
+static void pgd_ctor(pgd_t *pgd)
 {
-	pgd_t *pgd = p;
-
 	/* If the pgd points to a shared pagetable level (either the
 	   ptes in non-PAE, or shared PMD in PAE), then just copy the
 	   references from swapper_pg_dir. */
@@ -87,7 +85,7 @@
 		pgd_list_add(pgd);
 }
 
-static void pgd_dtor(void *pgd)
+static void pgd_dtor(pgd_t *pgd)
 {
 	unsigned long flags; /* can be called from interrupt context */
 
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index cab0abb..0951db9 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -123,7 +123,8 @@
 	if (!arg)
 		return -EINVAL;
 
-	__VMALLOC_RESERVE = memparse(arg, &arg);
+	/* Add VMALLOC_OFFSET to the parsed value due to vm area guard hole*/
+	__VMALLOC_RESERVE = memparse(arg, &arg) + VMALLOC_OFFSET;
 	return 0;
 }
 early_param("vmalloc", parse_vmalloc);
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 56b4757..43ac5af 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -10,11 +10,12 @@
 
 #include <linux/oprofile.h>
 #include <linux/smp.h>
+#include <linux/ptrace.h>
+#include <linux/nmi.h>
 #include <asm/msr.h>
-#include <asm/ptrace.h>
 #include <asm/fixmap.h>
 #include <asm/apic.h>
-#include <asm/nmi.h>
+
 
 #include "op_x86_model.h"
 #include "op_counter.h"
@@ -40,7 +41,7 @@
 static inline void setup_num_counters(void)
 {
 #ifdef CONFIG_SMP
-	if (smp_num_siblings == 2){
+	if (smp_num_siblings == 2) {
 		num_counters = NUM_COUNTERS_HT2;
 		num_controls = NUM_CONTROLS_HT2;
 	}
@@ -86,7 +87,7 @@
 #define CTR_FLAME_2    (1 << 6)
 #define CTR_IQ_5       (1 << 7)
 
-static struct p4_counter_binding p4_counters [NUM_COUNTERS_NON_HT] = {
+static struct p4_counter_binding p4_counters[NUM_COUNTERS_NON_HT] = {
 	{ CTR_BPU_0,   MSR_P4_BPU_PERFCTR0,   MSR_P4_BPU_CCCR0 },
 	{ CTR_MS_0,    MSR_P4_MS_PERFCTR0,    MSR_P4_MS_CCCR0 },
 	{ CTR_FLAME_0, MSR_P4_FLAME_PERFCTR0, MSR_P4_FLAME_CCCR0 },
@@ -97,32 +98,32 @@
 	{ CTR_IQ_5,    MSR_P4_IQ_PERFCTR5,    MSR_P4_IQ_CCCR5 }
 };
 
-#define NUM_UNUSED_CCCRS	NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT
+#define NUM_UNUSED_CCCRS (NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT)
 
 /* p4 event codes in libop/op_event.h are indices into this table. */
 
 static struct p4_event_binding p4_events[NUM_EVENTS] = {
-	
+
 	{ /* BRANCH_RETIRED */
-		0x05, 0x06, 
+		0x05, 0x06,
 		{ {CTR_IQ_4, MSR_P4_CRU_ESCR2},
 		  {CTR_IQ_5, MSR_P4_CRU_ESCR3} }
 	},
-	
+
 	{ /* MISPRED_BRANCH_RETIRED */
-		0x04, 0x03, 
+		0x04, 0x03,
 		{ { CTR_IQ_4, MSR_P4_CRU_ESCR0},
 		  { CTR_IQ_5, MSR_P4_CRU_ESCR1} }
 	},
-	
+
 	{ /* TC_DELIVER_MODE */
 		0x01, 0x01,
-		{ { CTR_MS_0, MSR_P4_TC_ESCR0},  
+		{ { CTR_MS_0, MSR_P4_TC_ESCR0},
 		  { CTR_MS_2, MSR_P4_TC_ESCR1} }
 	},
-	
+
 	{ /* BPU_FETCH_REQUEST */
-		0x00, 0x03, 
+		0x00, 0x03,
 		{ { CTR_BPU_0, MSR_P4_BPU_ESCR0},
 		  { CTR_BPU_2, MSR_P4_BPU_ESCR1} }
 	},
@@ -146,7 +147,7 @@
 	},
 
 	{ /* LOAD_PORT_REPLAY */
-		0x02, 0x04, 
+		0x02, 0x04,
 		{ { CTR_FLAME_0, MSR_P4_SAAT_ESCR0},
 		  { CTR_FLAME_2, MSR_P4_SAAT_ESCR1} }
 	},
@@ -170,43 +171,43 @@
 	},
 
 	{ /* BSQ_CACHE_REFERENCE */
-		0x07, 0x0c, 
+		0x07, 0x0c,
 		{ { CTR_BPU_0, MSR_P4_BSU_ESCR0},
 		  { CTR_BPU_2, MSR_P4_BSU_ESCR1} }
 	},
 
 	{ /* IOQ_ALLOCATION */
-		0x06, 0x03, 
+		0x06, 0x03,
 		{ { CTR_BPU_0, MSR_P4_FSB_ESCR0},
 		  { 0, 0 } }
 	},
 
 	{ /* IOQ_ACTIVE_ENTRIES */
-		0x06, 0x1a, 
+		0x06, 0x1a,
 		{ { CTR_BPU_2, MSR_P4_FSB_ESCR1},
 		  { 0, 0 } }
 	},
 
 	{ /* FSB_DATA_ACTIVITY */
-		0x06, 0x17, 
+		0x06, 0x17,
 		{ { CTR_BPU_0, MSR_P4_FSB_ESCR0},
 		  { CTR_BPU_2, MSR_P4_FSB_ESCR1} }
 	},
 
 	{ /* BSQ_ALLOCATION */
-		0x07, 0x05, 
+		0x07, 0x05,
 		{ { CTR_BPU_0, MSR_P4_BSU_ESCR0},
 		  { 0, 0 } }
 	},
 
 	{ /* BSQ_ACTIVE_ENTRIES */
 		0x07, 0x06,
-		{ { CTR_BPU_2, MSR_P4_BSU_ESCR1 /* guess */},  
+		{ { CTR_BPU_2, MSR_P4_BSU_ESCR1 /* guess */},
 		  { 0, 0 } }
 	},
 
 	{ /* X87_ASSIST */
-		0x05, 0x03, 
+		0x05, 0x03,
 		{ { CTR_IQ_4, MSR_P4_CRU_ESCR2},
 		  { CTR_IQ_5, MSR_P4_CRU_ESCR3} }
 	},
@@ -216,21 +217,21 @@
 		{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
 		  { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
 	},
-  
+
 	{ /* PACKED_SP_UOP */
-		0x01, 0x08, 
+		0x01, 0x08,
 		{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
 		  { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
 	},
-  
+
 	{ /* PACKED_DP_UOP */
-		0x01, 0x0c, 
+		0x01, 0x0c,
 		{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
 		  { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
 	},
 
 	{ /* SCALAR_SP_UOP */
-		0x01, 0x0a, 
+		0x01, 0x0a,
 		{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
 		  { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
 	},
@@ -242,31 +243,31 @@
 	},
 
 	{ /* 64BIT_MMX_UOP */
-		0x01, 0x02, 
+		0x01, 0x02,
 		{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
 		  { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
 	},
-  
+
 	{ /* 128BIT_MMX_UOP */
-		0x01, 0x1a, 
+		0x01, 0x1a,
 		{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
 		  { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
 	},
 
 	{ /* X87_FP_UOP */
-		0x01, 0x04, 
+		0x01, 0x04,
 		{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
 		  { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
 	},
-  
+
 	{ /* X87_SIMD_MOVES_UOP */
-		0x01, 0x2e, 
+		0x01, 0x2e,
 		{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
 		  { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
 	},
-  
+
 	{ /* MACHINE_CLEAR */
-		0x05, 0x02, 
+		0x05, 0x02,
 		{ { CTR_IQ_4, MSR_P4_CRU_ESCR2},
 		  { CTR_IQ_5, MSR_P4_CRU_ESCR3} }
 	},
@@ -276,9 +277,9 @@
 		{ { CTR_BPU_0, MSR_P4_FSB_ESCR0},
 		  { CTR_BPU_2, MSR_P4_FSB_ESCR1} }
 	},
-  
+
 	{ /* TC_MS_XFER */
-		0x00, 0x05, 
+		0x00, 0x05,
 		{ { CTR_MS_0, MSR_P4_MS_ESCR0},
 		  { CTR_MS_2, MSR_P4_MS_ESCR1} }
 	},
@@ -308,7 +309,7 @@
 	},
 
 	{ /* INSTR_RETIRED */
-		0x04, 0x02, 
+		0x04, 0x02,
 		{ { CTR_IQ_4, MSR_P4_CRU_ESCR0},
 		  { CTR_IQ_5, MSR_P4_CRU_ESCR1} }
 	},
@@ -319,14 +320,14 @@
 		  { CTR_IQ_5, MSR_P4_CRU_ESCR1} }
 	},
 
-	{ /* UOP_TYPE */    
-		0x02, 0x02, 
+	{ /* UOP_TYPE */
+		0x02, 0x02,
 		{ { CTR_IQ_4, MSR_P4_RAT_ESCR0},
 		  { CTR_IQ_5, MSR_P4_RAT_ESCR1} }
 	},
 
 	{ /* RETIRED_MISPRED_BRANCH_TYPE */
-		0x02, 0x05, 
+		0x02, 0x05,
 		{ { CTR_MS_0, MSR_P4_TBPU_ESCR0},
 		  { CTR_MS_2, MSR_P4_TBPU_ESCR1} }
 	},
@@ -349,8 +350,8 @@
 #define ESCR_SET_OS_1(escr, os) ((escr) |= (((os) & 1) << 1))
 #define ESCR_SET_EVENT_SELECT(escr, sel) ((escr) |= (((sel) & 0x3f) << 25))
 #define ESCR_SET_EVENT_MASK(escr, mask) ((escr) |= (((mask) & 0xffff) << 9))
-#define ESCR_READ(escr,high,ev,i) do {rdmsr(ev->bindings[(i)].escr_address, (escr), (high));} while (0)
-#define ESCR_WRITE(escr,high,ev,i) do {wrmsr(ev->bindings[(i)].escr_address, (escr), (high));} while (0)
+#define ESCR_READ(escr, high, ev, i) do {rdmsr(ev->bindings[(i)].escr_address, (escr), (high)); } while (0)
+#define ESCR_WRITE(escr, high, ev, i) do {wrmsr(ev->bindings[(i)].escr_address, (escr), (high)); } while (0)
 
 #define CCCR_RESERVED_BITS 0x38030FFF
 #define CCCR_CLEAR(cccr) ((cccr) &= CCCR_RESERVED_BITS)
@@ -360,15 +361,15 @@
 #define CCCR_SET_PMI_OVF_1(cccr) ((cccr) |= (1<<27))
 #define CCCR_SET_ENABLE(cccr) ((cccr) |= (1<<12))
 #define CCCR_SET_DISABLE(cccr) ((cccr) &= ~(1<<12))
-#define CCCR_READ(low, high, i) do {rdmsr(p4_counters[(i)].cccr_address, (low), (high));} while (0)
-#define CCCR_WRITE(low, high, i) do {wrmsr(p4_counters[(i)].cccr_address, (low), (high));} while (0)
+#define CCCR_READ(low, high, i) do {rdmsr(p4_counters[(i)].cccr_address, (low), (high)); } while (0)
+#define CCCR_WRITE(low, high, i) do {wrmsr(p4_counters[(i)].cccr_address, (low), (high)); } while (0)
 #define CCCR_OVF_P(cccr) ((cccr) & (1U<<31))
 #define CCCR_CLEAR_OVF(cccr) ((cccr) &= (~(1U<<31)))
 
-#define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0)
-#define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0)
-#define CTR_READ(l,h,i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h));} while (0)
-#define CTR_WRITE(l,i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1);} while (0)
+#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
+#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
+#define CTR_READ(l, h, i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h)); } while (0)
+#define CTR_WRITE(l, i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1); } while (0)
 #define CTR_OVERFLOW_P(ctr) (!((ctr) & 0x80000000))
 
 
@@ -380,7 +381,7 @@
 #ifdef CONFIG_SMP
 	int cpu = smp_processor_id();
 	return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu)));
-#endif	
+#endif
 	return 0;
 }
 
@@ -395,25 +396,23 @@
 
 static void p4_fill_in_addresses(struct op_msrs * const msrs)
 {
-	unsigned int i; 
+	unsigned int i;
 	unsigned int addr, cccraddr, stag;
 
 	setup_num_counters();
 	stag = get_stagger();
 
 	/* initialize some registers */
-	for (i = 0; i < num_counters; ++i) {
+	for (i = 0; i < num_counters; ++i)
 		msrs->counters[i].addr = 0;
-	}
-	for (i = 0; i < num_controls; ++i) {
+	for (i = 0; i < num_controls; ++i)
 		msrs->controls[i].addr = 0;
-	}
-	
+
 	/* the counter & cccr registers we pay attention to */
 	for (i = 0; i < num_counters; ++i) {
 		addr = p4_counters[VIRT_CTR(stag, i)].counter_address;
 		cccraddr = p4_counters[VIRT_CTR(stag, i)].cccr_address;
-		if (reserve_perfctr_nmi(addr)){
+		if (reserve_perfctr_nmi(addr)) {
 			msrs->counters[i].addr = addr;
 			msrs->controls[i].addr = cccraddr;
 		}
@@ -447,22 +446,22 @@
 		if (reserve_evntsel_nmi(addr))
 			msrs->controls[i].addr = addr;
 	}
-	
+
 	for (addr = MSR_P4_MS_ESCR0 + stag;
-	     addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) { 
+	     addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) {
 		if (reserve_evntsel_nmi(addr))
 			msrs->controls[i].addr = addr;
 	}
-	
+
 	for (addr = MSR_P4_IX_ESCR0 + stag;
-	     addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) { 
+	     addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) {
 		if (reserve_evntsel_nmi(addr))
 			msrs->controls[i].addr = addr;
 	}
 
 	/* there are 2 remaining non-contiguously located ESCRs */
 
-	if (num_counters == NUM_COUNTERS_NON_HT) {		
+	if (num_counters == NUM_COUNTERS_NON_HT) {
 		/* standard non-HT CPUs handle both remaining ESCRs*/
 		if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR5))
 			msrs->controls[i++].addr = MSR_P4_CRU_ESCR5;
@@ -498,20 +497,20 @@
 	unsigned int stag;
 
 	stag = get_stagger();
-	
+
 	/* convert from counter *number* to counter *bit* */
 	counter_bit = 1 << VIRT_CTR(stag, ctr);
-	
+
 	/* find our event binding structure. */
 	if (counter_config[ctr].event <= 0 || counter_config[ctr].event > NUM_EVENTS) {
-		printk(KERN_ERR 
-		       "oprofile: P4 event code 0x%lx out of range\n", 
+		printk(KERN_ERR
+		       "oprofile: P4 event code 0x%lx out of range\n",
 		       counter_config[ctr].event);
 		return;
 	}
-	
+
 	ev = &(p4_events[counter_config[ctr].event - 1]);
-	
+
 	for (i = 0; i < maxbind; i++) {
 		if (ev->bindings[i].virt_counter & counter_bit) {
 
@@ -526,25 +525,24 @@
 				ESCR_SET_OS_1(escr, counter_config[ctr].kernel);
 			}
 			ESCR_SET_EVENT_SELECT(escr, ev->event_select);
-			ESCR_SET_EVENT_MASK(escr, counter_config[ctr].unit_mask);			
+			ESCR_SET_EVENT_MASK(escr, counter_config[ctr].unit_mask);
 			ESCR_WRITE(escr, high, ev, i);
-		       
+
 			/* modify CCCR */
 			CCCR_READ(cccr, high, VIRT_CTR(stag, ctr));
 			CCCR_CLEAR(cccr);
 			CCCR_SET_REQUIRED_BITS(cccr);
 			CCCR_SET_ESCR_SELECT(cccr, ev->escr_select);
-			if (stag == 0) {
+			if (stag == 0)
 				CCCR_SET_PMI_OVF_0(cccr);
-			} else {
+			else
 				CCCR_SET_PMI_OVF_1(cccr);
-			}
 			CCCR_WRITE(cccr, high, VIRT_CTR(stag, ctr));
 			return;
 		}
 	}
 
-	printk(KERN_ERR 
+	printk(KERN_ERR
 	       "oprofile: P4 event code 0x%lx no binding, stag %d ctr %d\n",
 	       counter_config[ctr].event, stag, ctr);
 }
@@ -559,14 +557,14 @@
 	stag = get_stagger();
 
 	rdmsr(MSR_IA32_MISC_ENABLE, low, high);
-	if (! MISC_PMC_ENABLED_P(low)) {
+	if (!MISC_PMC_ENABLED_P(low)) {
 		printk(KERN_ERR "oprofile: P4 PMC not available\n");
 		return;
 	}
 
 	/* clear the cccrs we will use */
 	for (i = 0 ; i < num_counters ; i++) {
-		if (unlikely(!CTRL_IS_RESERVED(msrs,i)))
+		if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
 			continue;
 		rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high);
 		CCCR_CLEAR(low);
@@ -576,14 +574,14 @@
 
 	/* clear all escrs (including those outside our concern) */
 	for (i = num_counters; i < num_controls; i++) {
-		if (unlikely(!CTRL_IS_RESERVED(msrs,i)))
+		if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
 			continue;
 		wrmsr(msrs->controls[i].addr, 0, 0);
 	}
 
 	/* setup all counters */
 	for (i = 0 ; i < num_counters ; ++i) {
-		if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs,i))) {
+		if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs, i))) {
 			reset_value[i] = counter_config[i].count;
 			pmc_setup_one_p4_counter(i);
 			CTR_WRITE(counter_config[i].count, VIRT_CTR(stag, i));
@@ -603,11 +601,11 @@
 	stag = get_stagger();
 
 	for (i = 0; i < num_counters; ++i) {
-		
-		if (!reset_value[i]) 
+
+		if (!reset_value[i])
 			continue;
 
-		/* 
+		/*
 		 * there is some eccentricity in the hardware which
 		 * requires that we perform 2 extra corrections:
 		 *
@@ -616,24 +614,24 @@
 		 *
 		 * - write the counter back twice to ensure it gets
 		 *   updated properly.
-		 * 
+		 *
 		 * the former seems to be related to extra NMIs happening
 		 * during the current NMI; the latter is reported as errata
 		 * N15 in intel doc 249199-029, pentium 4 specification
 		 * update, though their suggested work-around does not
 		 * appear to solve the problem.
 		 */
-		
+
 		real = VIRT_CTR(stag, i);
 
 		CCCR_READ(low, high, real);
- 		CTR_READ(ctr, high, real);
+		CTR_READ(ctr, high, real);
 		if (CCCR_OVF_P(low) || CTR_OVERFLOW_P(ctr)) {
 			oprofile_add_sample(regs, i);
- 			CTR_WRITE(reset_value[i], real);
+			CTR_WRITE(reset_value[i], real);
 			CCCR_CLEAR_OVF(low);
 			CCCR_WRITE(low, high, real);
- 			CTR_WRITE(reset_value[i], real);
+			CTR_WRITE(reset_value[i], real);
 		}
 	}
 
@@ -683,15 +681,16 @@
 	int i;
 
 	for (i = 0 ; i < num_counters ; ++i) {
-		if (CTR_IS_RESERVED(msrs,i))
+		if (CTR_IS_RESERVED(msrs, i))
 			release_perfctr_nmi(msrs->counters[i].addr);
 	}
-	/* some of the control registers are specially reserved in
+	/*
+	 * 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 (CTRL_IS_RESERVED(msrs,i))
+		if (CTRL_IS_RESERVED(msrs, i))
 			release_evntsel_nmi(msrs->controls[i].addr);
 	}
 }
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 6a0fca7..22e0576 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -580,7 +580,7 @@
 				    unsigned long action, void *hcpu)
 {
 	int cpu = (long)hcpu;
-	switch(action) {
+	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
 		smp_call_function_single(cpu, enable_pci_io_ecs, NULL, 0);
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 8e07718..006599d 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1043,35 +1043,44 @@
 		if (io_apic_assign_pci_irqs) {
 			int irq;
 
-			if (pin) {
-				/*
-				 * interrupt pins are numbered starting
-				 * from 1
-				 */
-				pin--;
-				irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
-					PCI_SLOT(dev->devfn), pin);
-	/*
-	 * Busses behind bridges are typically not listed in the MP-table.
-	 * In this case we have to look up the IRQ based on the parent bus,
-	 * parent slot, and pin number. The SMP code detects such bridged
-	 * busses itself so we should get into this branch reliably.
-	 */
-				if (irq < 0 && dev->bus->parent) { /* go back to the bridge */
-					struct pci_dev *bridge = dev->bus->self;
+			if (!pin)
+				continue;
 
-					pin = (pin + PCI_SLOT(dev->devfn)) % 4;
-					irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
-							PCI_SLOT(bridge->devfn), pin);
-					if (irq >= 0)
-						dev_warn(&dev->dev, "using bridge %s INT %c to get IRQ %d\n",
-							 pci_name(bridge),
-							 'A' + pin, irq);
-				}
-				if (irq >= 0) {
-					dev_info(&dev->dev, "PCI->APIC IRQ transform: INT %c -> IRQ %d\n", 'A' + pin, irq);
-					dev->irq = irq;
-				}
+			/*
+			 * interrupt pins are numbered starting from 1
+			 */
+			pin--;
+			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
+				PCI_SLOT(dev->devfn), pin);
+			/*
+			 * Busses behind bridges are typically not listed in the
+			 * MP-table.  In this case we have to look up the IRQ
+			 * based on the parent bus, parent slot, and pin number.
+			 * The SMP code detects such bridged busses itself so we
+			 * should get into this branch reliably.
+			 */
+			if (irq < 0 && dev->bus->parent) {
+				/* go back to the bridge */
+				struct pci_dev *bridge = dev->bus->self;
+				int bus;
+
+				pin = (pin + PCI_SLOT(dev->devfn)) % 4;
+				bus = bridge->bus->number;
+				irq = IO_APIC_get_PCI_irq_vector(bus,
+						PCI_SLOT(bridge->devfn), pin);
+				if (irq >= 0)
+					dev_warn(&dev->dev,
+						"using bridge %s INT %c to "
+							"get IRQ %d\n",
+						 pci_name(bridge),
+						 'A' + pin, irq);
+			}
+			if (irq >= 0) {
+				dev_info(&dev->dev,
+					"PCI->APIC IRQ transform: INT %c "
+						"-> IRQ %d\n",
+					'A' + pin, irq);
+				dev->irq = irq;
 			}
 		}
 #endif
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index 4fc7e87..d1e9b53 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -1,5 +1,3 @@
-.text
-
 /*
  * This may not use any stack, nor any variable that is not "NoSave":
  *
@@ -12,17 +10,18 @@
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>
 
-	.text
+.text
 
 ENTRY(swsusp_arch_suspend)
-
 	movl %esp, saved_context_esp
 	movl %ebx, saved_context_ebx
 	movl %ebp, saved_context_ebp
 	movl %esi, saved_context_esi
 	movl %edi, saved_context_edi
-	pushfl ; popl saved_context_eflags
+	pushfl
+	popl saved_context_eflags
 
 	call swsusp_save
 	ret
@@ -59,7 +58,7 @@
 	movl	mmu_cr4_features, %ecx
 	jecxz	1f	# cr4 Pentium and higher, skip if zero
 	movl	%ecx, %edx
-	andl	$~(1<<7), %edx;  # PGE
+	andl	$~(X86_CR4_PGE), %edx
 	movl	%edx, %cr4;  # turn off PGE
 1:
 	movl	%cr3, %eax;  # flush TLB
@@ -74,7 +73,8 @@
 	movl saved_context_esi, %esi
 	movl saved_context_edi, %edi
 
-	pushl saved_context_eflags ; popfl
+	pushl saved_context_eflags
+	popfl
 
 	xorl	%eax, %eax
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index a4e201b..7dcd321 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -812,7 +812,7 @@
 
 /* Early in boot, while setting up the initial pagetable, assume
    everything is pinned. */
-static __init void xen_alloc_pte_init(struct mm_struct *mm, u32 pfn)
+static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
 {
 #ifdef CONFIG_FLATMEM
 	BUG_ON(mem_map);	/* should only be used early */
@@ -822,7 +822,7 @@
 
 /* Early release_pte assumes that all pts are pinned, since there's
    only init_mm and anything attached to that is pinned. */
-static void xen_release_pte_init(u32 pfn)
+static void xen_release_pte_init(unsigned long pfn)
 {
 	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
@@ -838,7 +838,7 @@
 
 /* This needs to make sure the new pte page is pinned iff its being
    attached to a pinned pagetable. */
-static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level)
+static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level)
 {
 	struct page *page = pfn_to_page(pfn);
 
@@ -856,12 +856,12 @@
 	}
 }
 
-static void xen_alloc_pte(struct mm_struct *mm, u32 pfn)
+static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PTE);
 }
 
-static void xen_alloc_pmd(struct mm_struct *mm, u32 pfn)
+static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PMD);
 }
@@ -909,7 +909,7 @@
 }
 
 /* This should never happen until we're OK to use struct page */
-static void xen_release_ptpage(u32 pfn, unsigned level)
+static void xen_release_ptpage(unsigned long pfn, unsigned level)
 {
 	struct page *page = pfn_to_page(pfn);
 
@@ -923,23 +923,23 @@
 	}
 }
 
-static void xen_release_pte(u32 pfn)
+static void xen_release_pte(unsigned long pfn)
 {
 	xen_release_ptpage(pfn, PT_PTE);
 }
 
-static void xen_release_pmd(u32 pfn)
+static void xen_release_pmd(unsigned long pfn)
 {
 	xen_release_ptpage(pfn, PT_PMD);
 }
 
 #if PAGETABLE_LEVELS == 4
-static void xen_alloc_pud(struct mm_struct *mm, u32 pfn)
+static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PUD);
 }
 
-static void xen_release_pud(u32 pfn)
+static void xen_release_pud(unsigned long pfn)
 {
 	xen_release_ptpage(pfn, PT_PUD);
 }
diff --git a/drivers/accessibility/braille/braille_console.c b/drivers/accessibility/braille/braille_console.c
index 0a5f6b2..d672cfe 100644
--- a/drivers/accessibility/braille/braille_console.c
+++ b/drivers/accessibility/braille/braille_console.c
@@ -376,6 +376,8 @@
 	console->flags |= CON_ENABLED;
 	console->index = index;
 	braille_co = console;
+	register_keyboard_notifier(&keyboard_notifier_block);
+	register_vt_notifier(&vt_notifier_block);
 	return 0;
 }
 
@@ -383,15 +385,8 @@
 {
 	if (braille_co != console)
 		return -EINVAL;
+	unregister_keyboard_notifier(&keyboard_notifier_block);
+	unregister_vt_notifier(&vt_notifier_block);
 	braille_co = NULL;
 	return 0;
 }
-
-static int __init braille_init(void)
-{
-	register_keyboard_notifier(&keyboard_notifier_block);
-	register_vt_notifier(&vt_notifier_block);
-	return 0;
-}
-
-console_initcall(braille_init);
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 0841095..8dd3336 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -165,8 +165,11 @@
 				"firmware_node");
 		ret = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj,
 				"physical_node");
-		if (acpi_dev->wakeup.flags.valid)
+		if (acpi_dev->wakeup.flags.valid) {
 			device_set_wakeup_capable(dev, true);
+			device_set_wakeup_enable(dev,
+						acpi_dev->wakeup.state.enabled);
+		}
 	}
 
 	return 0;
diff --git a/drivers/acpi/sleep/proc.c b/drivers/acpi/sleep/proc.c
index 4ebbba2..bf5b04d 100644
--- a/drivers/acpi/sleep/proc.c
+++ b/drivers/acpi/sleep/proc.c
@@ -377,6 +377,14 @@
 	return 0;
 }
 
+static void physical_device_enable_wakeup(struct acpi_device *adev)
+{
+	struct device *dev = acpi_get_physical_device(adev->handle);
+
+	if (dev && device_can_wakeup(dev))
+		device_set_wakeup_enable(dev, adev->wakeup.state.enabled);
+}
+
 static ssize_t
 acpi_system_write_wakeup_device(struct file *file,
 				const char __user * buffer,
@@ -411,6 +419,7 @@
 		}
 	}
 	if (found_dev) {
+		physical_device_enable_wakeup(found_dev);
 		list_for_each_safe(node, next, &acpi_wakeup_device_list) {
 			struct acpi_device *dev = container_of(node,
 							       struct
@@ -428,6 +437,7 @@
 				       dev->pnp.bus_id, found_dev->pnp.bus_id);
 				dev->wakeup.state.enabled =
 				    found_dev->wakeup.state.enabled;
+				physical_device_enable_wakeup(dev);
 			}
 		}
 	}
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 1e1f3f3..14601dc 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -309,6 +309,8 @@
 static void nv_nf2_thaw(struct ata_port *ap);
 static void nv_ck804_freeze(struct ata_port *ap);
 static void nv_ck804_thaw(struct ata_port *ap);
+static int nv_hardreset(struct ata_link *link, unsigned int *class,
+			unsigned long deadline);
 static int nv_adma_slave_config(struct scsi_device *sdev);
 static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc);
 static void nv_adma_qc_prep(struct ata_queued_cmd *qc);
@@ -403,28 +405,45 @@
 	.slave_configure	= nv_swncq_slave_config,
 };
 
-static struct ata_port_operations nv_generic_ops = {
+/* OSDL bz3352 reports that some nv controllers can't determine device
+ * signature reliably and nv_hardreset is implemented to work around
+ * the problem.  This was reported on nf3 and it's unclear whether any
+ * other controllers are affected.  However, the workaround has been
+ * applied to all variants and there isn't much to gain by trying to
+ * find out exactly which ones are affected at this point especially
+ * because NV has moved over to ahci for newer controllers.
+ */
+static struct ata_port_operations nv_common_ops = {
 	.inherits		= &ata_bmdma_port_ops,
-	.hardreset		= ATA_OP_NULL,
+	.hardreset		= nv_hardreset,
 	.scr_read		= nv_scr_read,
 	.scr_write		= nv_scr_write,
 };
 
+/* OSDL bz11195 reports that link doesn't come online after hardreset
+ * on generic nv's and there have been several other similar reports
+ * on linux-ide.  Disable hardreset for generic nv's.
+ */
+static struct ata_port_operations nv_generic_ops = {
+	.inherits		= &nv_common_ops,
+	.hardreset		= ATA_OP_NULL,
+};
+
 static struct ata_port_operations nv_nf2_ops = {
-	.inherits		= &nv_generic_ops,
+	.inherits		= &nv_common_ops,
 	.freeze			= nv_nf2_freeze,
 	.thaw			= nv_nf2_thaw,
 };
 
 static struct ata_port_operations nv_ck804_ops = {
-	.inherits		= &nv_generic_ops,
+	.inherits		= &nv_common_ops,
 	.freeze			= nv_ck804_freeze,
 	.thaw			= nv_ck804_thaw,
 	.host_stop		= nv_ck804_host_stop,
 };
 
 static struct ata_port_operations nv_adma_ops = {
-	.inherits		= &nv_generic_ops,
+	.inherits		= &nv_common_ops,
 
 	.check_atapi_dma	= nv_adma_check_atapi_dma,
 	.sff_tf_read		= nv_adma_tf_read,
@@ -448,7 +467,7 @@
 };
 
 static struct ata_port_operations nv_swncq_ops = {
-	.inherits		= &nv_generic_ops,
+	.inherits		= &nv_common_ops,
 
 	.qc_defer		= ata_std_qc_defer,
 	.qc_prep		= nv_swncq_qc_prep,
@@ -1586,6 +1605,21 @@
 	ata_sff_thaw(ap);
 }
 
+static int nv_hardreset(struct ata_link *link, unsigned int *class,
+			unsigned long deadline)
+{
+	int rc;
+
+	/* SATA hardreset fails to retrieve proper device signature on
+	 * some controllers.  Request follow up SRST.  For more info,
+	 * see http://bugzilla.kernel.org/show_bug.cgi?id=3352
+	 */
+	rc = sata_sff_hardreset(link, class, deadline);
+	if (rc)
+		return rc;
+	return -EAGAIN;
+}
+
 static void nv_adma_error_handler(struct ata_port *ap)
 {
 	struct nv_adma_port_priv *pp = ap->private_data;
diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c
index daeb8f7..e4dce87 100644
--- a/drivers/char/tty_io.c
+++ b/drivers/char/tty_io.c
@@ -695,13 +695,23 @@
 {
 	struct tty_driver *p, *res = NULL;
 	int tty_line = 0;
+	int len;
 	char *str;
 
+	for (str = name; *str; str++)
+		if ((*str >= '0' && *str <= '9') || *str == ',')
+			break;
+	if (!*str)
+		return NULL;
+
+	len = str - name;
+	tty_line = simple_strtoul(str, &str, 10);
+
 	mutex_lock(&tty_mutex);
 	/* Search through the tty devices to look for a match */
 	list_for_each_entry(p, &tty_drivers, tty_drivers) {
-		str = name + strlen(p->name);
-		tty_line = simple_strtoul(str, &str, 10);
+		if (strncmp(name, p->name, len) != 0)
+			continue;
 		if (*str == ',')
 			str++;
 		if (*str == '\0')
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index 94df917..0778d99 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -364,7 +364,7 @@
 	int i;
 
 	status_block = dma_readl(dw, RAW.BLOCK);
-	status_xfer = dma_readl(dw, RAW.BLOCK);
+	status_xfer = dma_readl(dw, RAW.XFER);
 	status_err = dma_readl(dw, RAW.ERROR);
 
 	dev_vdbg(dw->dma.dev, "tasklet: status_block=%x status_err=%x\n",
diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig
index fc735ab..8e93a79 100644
--- a/drivers/ide/Kconfig
+++ b/drivers/ide/Kconfig
@@ -292,6 +292,20 @@
 	tristate "generic/default IDE chipset support"
 	depends on ALPHA || X86 || IA64 || M32R || MIPS
 	help
+	  This is the generic IDE driver.  This driver attaches to the
+	  fixed legacy ports (e.g. on PCs 0x1f0/0x170, 0x1e8/0x168 and
+	  so on).  Please note that if this driver is built into the
+	  kernel or loaded before other ATA (IDE or libata) drivers
+	  and the controller is located at legacy ports, this driver
+	  may grab those ports and thus can prevent the controller
+	  specific driver from attaching.
+
+	  Also, currently, IDE generic doesn't allow IRQ sharing
+	  meaning that the IRQs it grabs won't be available to other
+	  controllers sharing those IRQs which usually makes drivers
+	  for those controllers fail.  Generally, it's not a good idea
+	  to load IDE generic driver on modern systems.
+
 	  If unsure, say N.
 
 config BLK_DEV_PLATFORM
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 1bce84b..3833189 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -2338,7 +2338,7 @@
 {
 	idetape_tape_t *tape = drive->driver_data;
 	struct ide_atapi_pc pc;
-	char fw_rev[6], vendor_id[10], product_id[18];
+	char fw_rev[4], vendor_id[8], product_id[16];
 
 	idetape_create_inquiry_cmd(&pc);
 	if (idetape_queue_pc_tail(drive, &pc)) {
@@ -2350,11 +2350,11 @@
 	memcpy(product_id, &pc.buf[16], 16);
 	memcpy(fw_rev, &pc.buf[32], 4);
 
-	ide_fixstring(vendor_id, 10, 0);
-	ide_fixstring(product_id, 18, 0);
-	ide_fixstring(fw_rev, 6, 0);
+	ide_fixstring(vendor_id, 8, 0);
+	ide_fixstring(product_id, 16, 0);
+	ide_fixstring(fw_rev, 4, 0);
 
-	printk(KERN_INFO "ide-tape: %s <-> %s: %s %s rev %s\n",
+	printk(KERN_INFO "ide-tape: %s <-> %s: %.8s %.16s rev %.4s\n",
 			drive->name, tape->name, vendor_id, product_id, fw_rev);
 }
 
diff --git a/drivers/ide/mips/swarm.c b/drivers/ide/mips/swarm.c
index badf79f..39c9ee9 100644
--- a/drivers/ide/mips/swarm.c
+++ b/drivers/ide/mips/swarm.c
@@ -107,6 +107,7 @@
 
 	base = ioremap(offset, size);
 
+	memset(&hw, 0, sizeof(hw));
 	for (i = 0; i <= 7; i++)
 		hw.io_ports_array[i] =
 				(unsigned long)(base + ((0x1f0 + i) << 5));
diff --git a/drivers/leds/leds-fsg.c b/drivers/leds/leds-fsg.c
index be0e121..3493515 100644
--- a/drivers/leds/leds-fsg.c
+++ b/drivers/leds/leds-fsg.c
@@ -161,6 +161,16 @@
 {
 	int ret;
 
+	/* Map the LED chip select address space */
+	latch_address = (unsigned short *) ioremap(IXP4XX_EXP_BUS_BASE(2), 512);
+	if (!latch_address) {
+		ret = -ENOMEM;
+		goto failremap;
+	}
+
+	latch_value = 0xffff;
+	*latch_address = latch_value;
+
 	ret = led_classdev_register(&pdev->dev, &fsg_wlan_led);
 	if (ret < 0)
 		goto failwlan;
@@ -185,20 +195,8 @@
 	if (ret < 0)
 		goto failring;
 
-	/* Map the LED chip select address space */
-	latch_address = (unsigned short *) ioremap(IXP4XX_EXP_BUS_BASE(2), 512);
-	if (!latch_address) {
-		ret = -ENOMEM;
-		goto failremap;
-	}
-
-	latch_value = 0xffff;
-	*latch_address = latch_value;
-
 	return ret;
 
- failremap:
-	led_classdev_unregister(&fsg_ring_led);
  failring:
 	led_classdev_unregister(&fsg_sync_led);
  failsync:
@@ -210,14 +208,14 @@
  failwan:
 	led_classdev_unregister(&fsg_wlan_led);
  failwlan:
+	iounmap(latch_address);
+ failremap:
 
 	return ret;
 }
 
 static int fsg_led_remove(struct platform_device *pdev)
 {
-	iounmap(latch_address);
-
 	led_classdev_unregister(&fsg_wlan_led);
 	led_classdev_unregister(&fsg_wan_led);
 	led_classdev_unregister(&fsg_sata_led);
@@ -225,6 +223,8 @@
 	led_classdev_unregister(&fsg_sync_led);
 	led_classdev_unregister(&fsg_ring_led);
 
+	iounmap(latch_address);
+
 	return 0;
 }
 
diff --git a/drivers/leds/leds-pca955x.c b/drivers/leds/leds-pca955x.c
index 146c069..f508729 100644
--- a/drivers/leds/leds-pca955x.c
+++ b/drivers/leds/leds-pca955x.c
@@ -248,11 +248,10 @@
 					const struct i2c_device_id *id)
 {
 	struct pca955x_led *pca955x;
-	int i;
-	int err = -ENODEV;
 	struct pca955x_chipdef *chip;
 	struct i2c_adapter *adapter;
 	struct led_platform_data *pdata;
+	int i, err;
 
 	chip = &pca955x_chipdefs[id->driver_data];
 	adapter = to_i2c_adapter(client->dev.parent);
@@ -282,43 +281,41 @@
 		}
 	}
 
-	for (i = 0; i < chip->bits; i++) {
-		pca955x = kzalloc(sizeof(struct pca955x_led), GFP_KERNEL);
-		if (!pca955x) {
-			err = -ENOMEM;
-			goto exit;
-		}
+	pca955x = kzalloc(sizeof(*pca955x) * chip->bits, GFP_KERNEL);
+	if (!pca955x)
+		return -ENOMEM;
 
-		pca955x->chipdef = chip;
-		pca955x->client = client;
-		pca955x->led_num = i;
+	i2c_set_clientdata(client, pca955x);
+
+	for (i = 0; i < chip->bits; i++) {
+		pca955x[i].chipdef = chip;
+		pca955x[i].client = client;
+		pca955x[i].led_num = i;
+
 		/* Platform data can specify LED names and default triggers */
 		if (pdata) {
 			if (pdata->leds[i].name)
-				snprintf(pca955x->name, 32, "pca955x:%s",
-							pdata->leds[i].name);
+				snprintf(pca955x[i].name,
+					 sizeof(pca955x[i].name), "pca955x:%s",
+					 pdata->leds[i].name);
 			if (pdata->leds[i].default_trigger)
-				pca955x->led_cdev.default_trigger =
+				pca955x[i].led_cdev.default_trigger =
 					pdata->leds[i].default_trigger;
 		} else {
-			snprintf(pca955x->name, 32, "pca955x:%d", i);
+			snprintf(pca955x[i].name, sizeof(pca955x[i].name),
+				 "pca955x:%d", i);
 		}
-		spin_lock_init(&pca955x->lock);
 
-		pca955x->led_cdev.name = pca955x->name;
-		pca955x->led_cdev.brightness_set =
-				pca955x_led_set;
+		spin_lock_init(&pca955x[i].lock);
 
-		/*
-		 * Client data is a pointer to the _first_ pca955x_led
-		 * struct
-		 */
-		if (i == 0)
-			i2c_set_clientdata(client, pca955x);
+		pca955x[i].led_cdev.name = pca955x[i].name;
+		pca955x[i].led_cdev.brightness_set = pca955x_led_set;
 
-		INIT_WORK(&(pca955x->work), pca955x_led_work);
+		INIT_WORK(&pca955x[i].work, pca955x_led_work);
 
-		led_classdev_register(&client->dev, &(pca955x->led_cdev));
+		err = led_classdev_register(&client->dev, &pca955x[i].led_cdev);
+		if (err < 0)
+			goto exit;
 	}
 
 	/* Turn off LEDs */
@@ -336,23 +333,32 @@
 	pca955x_write_psc(client, 1, 0);
 
 	return 0;
+
 exit:
+	while (i--) {
+		led_classdev_unregister(&pca955x[i].led_cdev);
+		cancel_work_sync(&pca955x[i].work);
+	}
+
+	kfree(pca955x);
+	i2c_set_clientdata(client, NULL);
+
 	return err;
 }
 
 static int __devexit pca955x_remove(struct i2c_client *client)
 {
 	struct pca955x_led *pca955x = i2c_get_clientdata(client);
-	int leds = pca955x->chipdef->bits;
 	int i;
 
-	for (i = 0; i < leds; i++) {
-		led_classdev_unregister(&(pca955x->led_cdev));
-		cancel_work_sync(&(pca955x->work));
-		kfree(pca955x);
-		pca955x = pca955x + 1;
+	for (i = 0; i < pca955x->chipdef->bits; i++) {
+		led_classdev_unregister(&pca955x[i].led_cdev);
+		cancel_work_sync(&pca955x[i].work);
 	}
 
+	kfree(pca955x);
+	i2c_set_clientdata(client, NULL);
+
 	return 0;
 }
 
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 71dd65a..c2fcf28 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -63,6 +63,7 @@
 
 	const char *hw_handler_name;
 	struct work_struct activate_path;
+	struct pgpath *pgpath_to_activate;
 	unsigned nr_priority_groups;
 	struct list_head priority_groups;
 	unsigned pg_init_required;	/* pg_init needs calling? */
@@ -146,6 +147,7 @@
 
 static void free_pgpaths(struct list_head *pgpaths, struct dm_target *ti)
 {
+	unsigned long flags;
 	struct pgpath *pgpath, *tmp;
 	struct multipath *m = ti->private;
 
@@ -154,6 +156,10 @@
 		if (m->hw_handler_name)
 			scsi_dh_detach(bdev_get_queue(pgpath->path.dev->bdev));
 		dm_put_device(ti, pgpath->path.dev);
+		spin_lock_irqsave(&m->lock, flags);
+		if (m->pgpath_to_activate == pgpath)
+			m->pgpath_to_activate = NULL;
+		spin_unlock_irqrestore(&m->lock, flags);
 		free_pgpath(pgpath);
 	}
 }
@@ -421,6 +427,7 @@
 		__choose_pgpath(m);
 
 	pgpath = m->current_pgpath;
+	m->pgpath_to_activate = m->current_pgpath;
 
 	if ((pgpath && !m->queue_io) ||
 	    (!pgpath && !m->queue_if_no_path))
@@ -1093,8 +1100,15 @@
 	int ret;
 	struct multipath *m =
 		container_of(work, struct multipath, activate_path);
-	struct dm_path *path = &m->current_pgpath->path;
+	struct dm_path *path;
+	unsigned long flags;
 
+	spin_lock_irqsave(&m->lock, flags);
+	path = &m->pgpath_to_activate->path;
+	m->pgpath_to_activate = NULL;
+	spin_unlock_irqrestore(&m->lock, flags);
+	if (!path)
+		return;
 	ret = scsi_dh_activate(bdev_get_queue(path->dev->bdev));
 	pg_init_done(path, ret);
 }
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index bca448e..ace998c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -837,12 +837,14 @@
 	struct dm_table *map = dm_get_table(md);
 	struct dm_target *ti;
 	sector_t max_sectors;
-	int max_size;
+	int max_size = 0;
 
 	if (unlikely(!map))
-		return 0;
+		goto out;
 
 	ti = dm_table_find_target(map, bvm->bi_sector);
+	if (!dm_target_is_valid(ti))
+		goto out_table;
 
 	/*
 	 * Find maximum amount of I/O that won't need splitting
@@ -861,14 +863,16 @@
 	if (max_size && ti->type->merge)
 		max_size = ti->type->merge(ti, bvm, biovec, max_size);
 
+out_table:
+	dm_table_put(map);
+
+out:
 	/*
 	 * Always allow an entire first page
 	 */
 	if (max_size <= biovec->bv_len && !(bvm->bi_size >> SECTOR_SHIFT))
 		max_size = biovec->bv_len;
 
-	dm_table_put(map);
-
 	return max_size;
 }
 
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 10c44d3..68dc8d9 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -21,7 +21,7 @@
 
 config MFD_SM501_GPIO
 	bool "Export GPIO via GPIO layer"
-	depends on MFD_SM501 && HAVE_GPIO_LIB
+	depends on MFD_SM501 && GPIOLIB
 	 ---help---
 	 This option uses the gpio library layer to export the 64 GPIO
 	 lines on the SM501. The platform data is used to supply the
@@ -29,7 +29,7 @@
 
 config MFD_ASIC3
 	bool "Support for Compaq ASIC3"
-	depends on GENERIC_HARDIRQS && HAVE_GPIO_LIB && ARM
+	depends on GENERIC_HARDIRQS && GPIOLIB && ARM
 	 ---help---
 	  This driver supports the ASIC3 multifunction chip found on many
 	  PDAs (mainly iPAQ and HTC based ones)
diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c
index bc2a807..ba5aa20 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -312,7 +312,6 @@
 	struct asic3 *asic = platform_get_drvdata(pdev);
 	unsigned long clksel = 0;
 	unsigned int irq, irq_base;
-	int map_size;
 	int ret;
 
 	ret = platform_get_irq(pdev, 0);
@@ -534,6 +533,7 @@
 	struct asic3 *asic;
 	struct resource *mem;
 	unsigned long clksel;
+	int map_size;
 	int ret = 0;
 
 	asic = kzalloc(sizeof(struct asic3), GFP_KERNEL);
diff --git a/drivers/net/e1000e/e1000.h b/drivers/net/e1000e/e1000.h
index ac4e506..5ea6b60 100644
--- a/drivers/net/e1000e/e1000.h
+++ b/drivers/net/e1000e/e1000.h
@@ -257,7 +257,6 @@
 	struct net_device *netdev;
 	struct pci_dev *pdev;
 	struct net_device_stats net_stats;
-	spinlock_t stats_lock;      /* prevent concurrent stats updates */
 
 	/* structs defined in e1000_hw.h */
 	struct e1000_hw hw;
@@ -284,6 +283,8 @@
 	unsigned long led_status;
 
 	unsigned int flags;
+	struct work_struct downshift_task;
+	struct work_struct update_phy_task;
 };
 
 struct e1000_info {
@@ -305,6 +306,7 @@
 #define FLAG_HAS_CTRLEXT_ON_LOAD          (1 << 5)
 #define FLAG_HAS_SWSM_ON_LOAD             (1 << 6)
 #define FLAG_HAS_JUMBO_FRAMES             (1 << 7)
+#define FLAG_READ_ONLY_NVM                (1 << 8)
 #define FLAG_IS_ICH                       (1 << 9)
 #define FLAG_HAS_SMART_POWER_DOWN         (1 << 11)
 #define FLAG_IS_QUAD_PORT_A               (1 << 12)
@@ -385,6 +387,7 @@
 extern bool e1000e_get_laa_state_82571(struct e1000_hw *hw);
 extern void e1000e_set_laa_state_82571(struct e1000_hw *hw, bool state);
 
+extern void e1000e_write_protect_nvm_ich8lan(struct e1000_hw *hw);
 extern void e1000e_set_kmrn_lock_loss_workaround_ich8lan(struct e1000_hw *hw,
 						 bool state);
 extern void e1000e_igp3_phy_powerdown_workaround_ich8lan(struct e1000_hw *hw);
diff --git a/drivers/net/e1000e/ethtool.c b/drivers/net/e1000e/ethtool.c
index e21c9e0..33a3ff1 100644
--- a/drivers/net/e1000e/ethtool.c
+++ b/drivers/net/e1000e/ethtool.c
@@ -432,6 +432,10 @@
 	regs_buff[11] = er32(TIDV);
 
 	regs_buff[12] = adapter->hw.phy.type;  /* PHY type (IGP=1, M88=0) */
+
+	/* ethtool doesn't use anything past this point, so all this
+	 * code is likely legacy junk for apps that may or may not
+	 * exist */
 	if (hw->phy.type == e1000_phy_m88) {
 		e1e_rphy(hw, M88E1000_PHY_SPEC_STATUS, &phy_data);
 		regs_buff[13] = (u32)phy_data; /* cable length */
@@ -447,7 +451,7 @@
 		regs_buff[22] = adapter->phy_stats.receive_errors;
 		regs_buff[23] = regs_buff[13]; /* mdix mode */
 	}
-	regs_buff[21] = adapter->phy_stats.idle_errors;  /* phy idle errors */
+	regs_buff[21] = 0; /* was idle_errors */
 	e1e_rphy(hw, PHY_1000T_STATUS, &phy_data);
 	regs_buff[24] = (u32)phy_data;  /* phy local receiver status */
 	regs_buff[25] = regs_buff[24];  /* phy remote receiver status */
@@ -529,6 +533,9 @@
 	if (eeprom->magic != (adapter->pdev->vendor | (adapter->pdev->device << 16)))
 		return -EFAULT;
 
+	if (adapter->flags & FLAG_READ_ONLY_NVM)
+		return -EINVAL;
+
 	max_len = hw->nvm.word_size * 2;
 
 	first_word = eeprom->offset >> 1;
diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c
index 9e38452..bcd2bc4 100644
--- a/drivers/net/e1000e/ich8lan.c
+++ b/drivers/net/e1000e/ich8lan.c
@@ -58,6 +58,7 @@
 #define ICH_FLASH_HSFCTL		0x0006
 #define ICH_FLASH_FADDR			0x0008
 #define ICH_FLASH_FDATA0		0x0010
+#define ICH_FLASH_PR0			0x0074
 
 #define ICH_FLASH_READ_COMMAND_TIMEOUT	500
 #define ICH_FLASH_WRITE_COMMAND_TIMEOUT	500
@@ -150,6 +151,19 @@
 	u16 regval;
 };
 
+/* ICH Flash Protected Region */
+union ich8_flash_protected_range {
+	struct ich8_pr {
+		u32 base:13;     /* 0:12 Protected Range Base */
+		u32 reserved1:2; /* 13:14 Reserved */
+		u32 rpe:1;       /* 15 Read Protection Enable */
+		u32 limit:13;    /* 16:28 Protected Range Limit */
+		u32 reserved2:2; /* 29:30 Reserved */
+		u32 wpe:1;       /* 31 Write Protection Enable */
+	} range;
+	u32 regval;
+};
+
 static s32 e1000_setup_link_ich8lan(struct e1000_hw *hw);
 static void e1000_clear_hw_cntrs_ich8lan(struct e1000_hw *hw);
 static void e1000_initialize_hw_bits_ich8lan(struct e1000_hw *hw);
@@ -366,6 +380,9 @@
 	return 0;
 }
 
+static DEFINE_MUTEX(nvm_mutex);
+static pid_t nvm_owner = -1;
+
 /**
  *  e1000_acquire_swflag_ich8lan - Acquire software control flag
  *  @hw: pointer to the HW structure
@@ -379,6 +396,15 @@
 	u32 extcnf_ctrl;
 	u32 timeout = PHY_CFG_TIMEOUT;
 
+	might_sleep();
+
+	if (!mutex_trylock(&nvm_mutex)) {
+		WARN(1, KERN_ERR "e1000e mutex contention. Owned by pid %d\n",
+		     nvm_owner);
+		mutex_lock(&nvm_mutex);
+	}
+	nvm_owner = current->pid;
+
 	while (timeout) {
 		extcnf_ctrl = er32(EXTCNF_CTRL);
 		extcnf_ctrl |= E1000_EXTCNF_CTRL_SWFLAG;
@@ -393,6 +419,8 @@
 
 	if (!timeout) {
 		hw_dbg(hw, "FW or HW has locked the resource for too long.\n");
+		nvm_owner = -1;
+		mutex_unlock(&nvm_mutex);
 		return -E1000_ERR_CONFIG;
 	}
 
@@ -414,6 +442,9 @@
 	extcnf_ctrl = er32(EXTCNF_CTRL);
 	extcnf_ctrl &= ~E1000_EXTCNF_CTRL_SWFLAG;
 	ew32(EXTCNF_CTRL, extcnf_ctrl);
+
+	nvm_owner = -1;
+	mutex_unlock(&nvm_mutex);
 }
 
 /**
@@ -1284,6 +1315,7 @@
 	 * programming failed.
 	 */
 	if (ret_val) {
+		/* Possibly read-only, see e1000e_write_protect_nvm_ich8lan() */
 		hw_dbg(hw, "Flash commit failed.\n");
 		e1000_release_swflag_ich8lan(hw);
 		return ret_val;
@@ -1374,6 +1406,49 @@
 }
 
 /**
+ *  e1000e_write_protect_nvm_ich8lan - Make the NVM read-only
+ *  @hw: pointer to the HW structure
+ *
+ *  To prevent malicious write/erase of the NVM, set it to be read-only
+ *  so that the hardware ignores all write/erase cycles of the NVM via
+ *  the flash control registers.  The shadow-ram copy of the NVM will
+ *  still be updated, however any updates to this copy will not stick
+ *  across driver reloads.
+ **/
+void e1000e_write_protect_nvm_ich8lan(struct e1000_hw *hw)
+{
+	union ich8_flash_protected_range pr0;
+	union ich8_hws_flash_status hsfsts;
+	u32 gfpreg;
+	s32 ret_val;
+
+	ret_val = e1000_acquire_swflag_ich8lan(hw);
+	if (ret_val)
+		return;
+
+	gfpreg = er32flash(ICH_FLASH_GFPREG);
+
+	/* Write-protect GbE Sector of NVM */
+	pr0.regval = er32flash(ICH_FLASH_PR0);
+	pr0.range.base = gfpreg & FLASH_GFPREG_BASE_MASK;
+	pr0.range.limit = ((gfpreg >> 16) & FLASH_GFPREG_BASE_MASK);
+	pr0.range.wpe = true;
+	ew32flash(ICH_FLASH_PR0, pr0.regval);
+
+	/*
+	 * Lock down a subset of GbE Flash Control Registers, e.g.
+	 * PR0 to prevent the write-protection from being lifted.
+	 * Once FLOCKDN is set, the registers protected by it cannot
+	 * be written until FLOCKDN is cleared by a hardware reset.
+	 */
+	hsfsts.regval = er16flash(ICH_FLASH_HSFSTS);
+	hsfsts.hsf_status.flockdn = true;
+	ew32flash(ICH_FLASH_HSFSTS, hsfsts.regval);
+
+	e1000_release_swflag_ich8lan(hw);
+}
+
+/**
  *  e1000_write_flash_data_ich8lan - Writes bytes to the NVM
  *  @hw: pointer to the HW structure
  *  @offset: The offset (in bytes) of the byte/word to read.
@@ -1720,6 +1795,9 @@
 	ew32(CTRL, (ctrl | E1000_CTRL_RST));
 	msleep(20);
 
+	/* release the swflag because it is not reset by hardware reset */
+	e1000_release_swflag_ich8lan(hw);
+
 	ret_val = e1000e_get_auto_rd_done(hw);
 	if (ret_val) {
 		/*
diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index d266510..b81c423 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -47,7 +47,7 @@
 
 #include "e1000.h"
 
-#define DRV_VERSION "0.3.3.3-k2"
+#define DRV_VERSION "0.3.3.3-k6"
 char e1000e_driver_name[] = "e1000e";
 const char e1000e_driver_version[] = DRV_VERSION;
 
@@ -1115,6 +1115,14 @@
 	writel(0, adapter->hw.hw_addr + rx_ring->tail);
 }
 
+static void e1000e_downshift_workaround(struct work_struct *work)
+{
+	struct e1000_adapter *adapter = container_of(work,
+					struct e1000_adapter, downshift_task);
+
+	e1000e_gig_downshift_workaround_ich8lan(&adapter->hw);
+}
+
 /**
  * e1000_intr_msi - Interrupt Handler
  * @irq: interrupt number
@@ -1139,7 +1147,7 @@
 		 */
 		if ((adapter->flags & FLAG_LSC_GIG_SPEED_DROP) &&
 		    (!(er32(STATUS) & E1000_STATUS_LU)))
-			e1000e_gig_downshift_workaround_ich8lan(hw);
+			schedule_work(&adapter->downshift_task);
 
 		/*
 		 * 80003ES2LAN workaround-- For packet buffer work-around on
@@ -1205,7 +1213,7 @@
 		 */
 		if ((adapter->flags & FLAG_LSC_GIG_SPEED_DROP) &&
 		    (!(er32(STATUS) & E1000_STATUS_LU)))
-			e1000e_gig_downshift_workaround_ich8lan(hw);
+			schedule_work(&adapter->downshift_task);
 
 		/*
 		 * 80003ES2LAN workaround--
@@ -2592,8 +2600,6 @@
 	/* Explicitly disable IRQ since the NIC can be in any state. */
 	e1000_irq_disable(adapter);
 
-	spin_lock_init(&adapter->stats_lock);
-
 	set_bit(__E1000_DOWN, &adapter->state);
 	return 0;
 
@@ -2912,6 +2918,21 @@
 	return 0;
 }
 
+/**
+ * e1000e_update_phy_task - work thread to update phy
+ * @work: pointer to our work struct
+ *
+ * this worker thread exists because we must acquire a
+ * semaphore to read the phy, which we could msleep while
+ * waiting for it, and we can't msleep in a timer.
+ **/
+static void e1000e_update_phy_task(struct work_struct *work)
+{
+	struct e1000_adapter *adapter = container_of(work,
+					struct e1000_adapter, update_phy_task);
+	e1000_get_phy_info(&adapter->hw);
+}
+
 /*
  * Need to wait a few seconds after link up to get diagnostic information from
  * the phy
@@ -2919,7 +2940,7 @@
 static void e1000_update_phy_info(unsigned long data)
 {
 	struct e1000_adapter *adapter = (struct e1000_adapter *) data;
-	e1000_get_phy_info(&adapter->hw);
+	schedule_work(&adapter->update_phy_task);
 }
 
 /**
@@ -2930,10 +2951,6 @@
 {
 	struct e1000_hw *hw = &adapter->hw;
 	struct pci_dev *pdev = adapter->pdev;
-	unsigned long irq_flags;
-	u16 phy_tmp;
-
-#define PHY_IDLE_ERROR_COUNT_MASK 0x00FF
 
 	/*
 	 * Prevent stats update while adapter is being reset, or if the pci
@@ -2944,14 +2961,6 @@
 	if (pci_channel_offline(pdev))
 		return;
 
-	spin_lock_irqsave(&adapter->stats_lock, irq_flags);
-
-	/*
-	 * these counters are modified from e1000_adjust_tbi_stats,
-	 * called from the interrupt context, so they must only
-	 * be written while holding adapter->stats_lock
-	 */
-
 	adapter->stats.crcerrs += er32(CRCERRS);
 	adapter->stats.gprc += er32(GPRC);
 	adapter->stats.gorc += er32(GORCL);
@@ -3022,21 +3031,10 @@
 
 	/* Tx Dropped needs to be maintained elsewhere */
 
-	/* Phy Stats */
-	if (hw->phy.media_type == e1000_media_type_copper) {
-		if ((adapter->link_speed == SPEED_1000) &&
-		   (!e1e_rphy(hw, PHY_1000T_STATUS, &phy_tmp))) {
-			phy_tmp &= PHY_IDLE_ERROR_COUNT_MASK;
-			adapter->phy_stats.idle_errors += phy_tmp;
-		}
-	}
-
 	/* Management Stats */
 	adapter->stats.mgptc += er32(MGTPTC);
 	adapter->stats.mgprc += er32(MGTPRC);
 	adapter->stats.mgpdc += er32(MGTPDC);
-
-	spin_unlock_irqrestore(&adapter->stats_lock, irq_flags);
 }
 
 /**
@@ -3048,10 +3046,6 @@
 	struct e1000_hw *hw = &adapter->hw;
 	struct e1000_phy_regs *phy = &adapter->phy_regs;
 	int ret_val;
-	unsigned long irq_flags;
-
-
-	spin_lock_irqsave(&adapter->stats_lock, irq_flags);
 
 	if ((er32(STATUS) & E1000_STATUS_LU) &&
 	    (adapter->hw.phy.media_type == e1000_media_type_copper)) {
@@ -3082,8 +3076,6 @@
 		phy->stat1000 = 0;
 		phy->estatus = (ESTATUS_1000_TFULL | ESTATUS_1000_THALF);
 	}
-
-	spin_unlock_irqrestore(&adapter->stats_lock, irq_flags);
 }
 
 static void e1000_print_link_info(struct e1000_adapter *adapter)
@@ -4467,6 +4459,8 @@
 
 	adapter->bd_number = cards_found++;
 
+	e1000e_check_options(adapter);
+
 	/* setup adapter struct */
 	err = e1000_sw_init(adapter);
 	if (err)
@@ -4482,6 +4476,10 @@
 	if (err)
 		goto err_hw_init;
 
+	if ((adapter->flags & FLAG_IS_ICH) &&
+	    (adapter->flags & FLAG_READ_ONLY_NVM))
+		e1000e_write_protect_nvm_ich8lan(&adapter->hw);
+
 	hw->mac.ops.get_bus_info(&adapter->hw);
 
 	adapter->hw.phy.autoneg_wait_to_complete = 0;
@@ -4572,8 +4570,8 @@
 
 	INIT_WORK(&adapter->reset_task, e1000_reset_task);
 	INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task);
-
-	e1000e_check_options(adapter);
+	INIT_WORK(&adapter->downshift_task, e1000e_downshift_workaround);
+	INIT_WORK(&adapter->update_phy_task, e1000e_update_phy_task);
 
 	/* Initialize link parameters. User can change them with ethtool */
 	adapter->hw.mac.autoneg = 1;
diff --git a/drivers/net/e1000e/param.c b/drivers/net/e1000e/param.c
index ed912e0..d91dbf7 100644
--- a/drivers/net/e1000e/param.c
+++ b/drivers/net/e1000e/param.c
@@ -133,6 +133,15 @@
  */
 E1000_PARAM(KumeranLockLoss, "Enable Kumeran lock loss workaround");
 
+/*
+ * Write Protect NVM
+ *
+ * Valid Range: 0, 1
+ *
+ * Default Value: 1 (enabled)
+ */
+E1000_PARAM(WriteProtectNVM, "Write-protect NVM [WARNING: disabling this can lead to corrupted NVM]");
+
 struct e1000_option {
 	enum { enable_option, range_option, list_option } type;
 	const char *name;
@@ -388,4 +397,25 @@
 								       opt.def);
 		}
 	}
+	{ /* Write-protect NVM */
+		const struct e1000_option opt = {
+			.type = enable_option,
+			.name = "Write-protect NVM",
+			.err  = "defaulting to Enabled",
+			.def  = OPTION_ENABLED
+		};
+
+		if (adapter->flags & FLAG_IS_ICH) {
+			if (num_WriteProtectNVM > bd) {
+				unsigned int write_protect_nvm = WriteProtectNVM[bd];
+				e1000_validate_option(&write_protect_nvm, &opt,
+						      adapter);
+				if (write_protect_nvm)
+					adapter->flags |= FLAG_READ_ONLY_NVM;
+			} else {
+				if (opt.def)
+					adapter->flags |= FLAG_READ_ONLY_NVM;
+			}
+		}
+	}
 }
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 9c71858..77baff0 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -16,6 +16,7 @@
 
 
 #include <linux/kernel.h>
+#include <linux/sched.h>
 #include <linux/pci.h>
 #include <linux/stat.h>
 #include <linux/topology.h>
@@ -484,6 +485,21 @@
 #endif /* HAVE_PCI_LEGACY */
 
 #ifdef HAVE_PCI_MMAP
+
+static int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma)
+{
+	unsigned long nr, start, size;
+
+	nr = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	start = vma->vm_pgoff;
+	size = pci_resource_len(pdev, resno) >> PAGE_SHIFT;
+	if (start < size && size - start >= nr)
+		return 1;
+	WARN(1, "process \"%s\" tried to map 0x%08lx-0x%08lx on %s BAR %d (size 0x%08lx)\n",
+		current->comm, start, start+nr, pci_name(pdev), resno, size);
+	return 0;
+}
+
 /**
  * pci_mmap_resource - map a PCI resource into user memory space
  * @kobj: kobject for mapping
@@ -510,6 +526,9 @@
 	if (i >= PCI_ROM_RESOURCE)
 		return -ENODEV;
 
+	if (!pci_mmap_fits(pdev, i, vma))
+		return -EINVAL;
+
 	/* pci_mmap_page_range() expects the same kind of entry as coming
 	 * from /proc/bus/pci/ which is a "user visible" value. If this is
 	 * different from the resource itself, arch will do necessary fixup.
diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c
index f118252..52e2743 100644
--- a/drivers/rtc/rtc-dev.c
+++ b/drivers/rtc/rtc-dev.c
@@ -422,6 +422,12 @@
 	return err;
 }
 
+static int rtc_dev_fasync(int fd, struct file *file, int on)
+{
+	struct rtc_device *rtc = file->private_data;
+	return fasync_helper(fd, file, on, &rtc->async_queue);
+}
+
 static int rtc_dev_release(struct inode *inode, struct file *file)
 {
 	struct rtc_device *rtc = file->private_data;
@@ -434,16 +440,13 @@
 	if (rtc->ops->release)
 		rtc->ops->release(rtc->dev.parent);
 
+	if (file->f_flags & FASYNC)
+		rtc_dev_fasync(-1, file, 0);
+
 	clear_bit_unlock(RTC_DEV_BUSY, &rtc->flags);
 	return 0;
 }
 
-static int rtc_dev_fasync(int fd, struct file *file, int on)
-{
-	struct rtc_device *rtc = file->private_data;
-	return fasync_helper(fd, file, on, &rtc->async_queue);
-}
-
 static const struct file_operations rtc_dev_fops = {
 	.owner		= THIS_MODULE,
 	.llseek		= no_llseek,
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index 1679e2f..a0b6b46 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -447,51 +447,36 @@
 {
 	char s[80];
 
-	sprintf(s, "%s sc:%x ", cdev->dev.bus_id, irq_ptr->schid.sch_no);
-
+	sprintf(s, "qdio: %s ", dev_name(&cdev->dev));
 	switch (irq_ptr->qib.qfmt) {
 	case QDIO_QETH_QFMT:
-		sprintf(s + strlen(s), "OSADE ");
+		sprintf(s + strlen(s), "OSA ");
 		break;
 	case QDIO_ZFCP_QFMT:
 		sprintf(s + strlen(s), "ZFCP ");
 		break;
 	case QDIO_IQDIO_QFMT:
-		sprintf(s + strlen(s), "HiperSockets ");
+		sprintf(s + strlen(s), "HS ");
 		break;
 	}
-	sprintf(s + strlen(s), "using: ");
-
-	if (!is_thinint_irq(irq_ptr))
-		sprintf(s + strlen(s), "no");
-	sprintf(s + strlen(s), "AdapterInterrupts ");
-	if (!(irq_ptr->sch_token != 0))
-		sprintf(s + strlen(s), "no");
-	sprintf(s + strlen(s), "QEBSM ");
-	if (!(irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED))
-		sprintf(s + strlen(s), "no");
-	sprintf(s + strlen(s), "OutboundPCI ");
-	if (!css_general_characteristics.aif_tdd)
-		sprintf(s + strlen(s), "no");
-	sprintf(s + strlen(s), "TDD\n");
-	printk(KERN_INFO "qdio: %s", s);
-
-	memset(s, 0, sizeof(s));
-	sprintf(s, "%s SIGA required: ", cdev->dev.bus_id);
-	if (irq_ptr->siga_flag.input)
-		sprintf(s + strlen(s), "Read ");
-	if (irq_ptr->siga_flag.output)
-		sprintf(s + strlen(s), "Write ");
-	if (irq_ptr->siga_flag.sync)
-		sprintf(s + strlen(s), "Sync ");
-	if (!irq_ptr->siga_flag.no_sync_ti)
-		sprintf(s + strlen(s), "SyncAI ");
-	if (!irq_ptr->siga_flag.no_sync_out_ti)
-		sprintf(s + strlen(s), "SyncOutAI ");
-	if (!irq_ptr->siga_flag.no_sync_out_pci)
-		sprintf(s + strlen(s), "SyncOutPCI");
+	sprintf(s + strlen(s), "on SC %x using ", irq_ptr->schid.sch_no);
+	sprintf(s + strlen(s), "AI:%d ", is_thinint_irq(irq_ptr));
+	sprintf(s + strlen(s), "QEBSM:%d ", (irq_ptr->sch_token) ? 1 : 0);
+	sprintf(s + strlen(s), "PCI:%d ",
+		(irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED) ? 1 : 0);
+	sprintf(s + strlen(s), "TDD:%d ", css_general_characteristics.aif_tdd);
+	sprintf(s + strlen(s), "SIGA:");
+	sprintf(s + strlen(s), "%s", (irq_ptr->siga_flag.input) ? "R" : " ");
+	sprintf(s + strlen(s), "%s", (irq_ptr->siga_flag.output) ? "W" : " ");
+	sprintf(s + strlen(s), "%s", (irq_ptr->siga_flag.sync) ? "S" : " ");
+	sprintf(s + strlen(s), "%s",
+		(!irq_ptr->siga_flag.no_sync_ti) ? "A" : " ");
+	sprintf(s + strlen(s), "%s",
+		(!irq_ptr->siga_flag.no_sync_out_ti) ? "O" : " ");
+	sprintf(s + strlen(s), "%s",
+		(!irq_ptr->siga_flag.no_sync_out_pci) ? "P" : " ");
 	sprintf(s + strlen(s), "\n");
-	printk(KERN_INFO "qdio: %s", s);
+	printk(KERN_INFO "%s", s);
 }
 
 int __init qdio_setup_init(void)
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 45a3b93..bf41887 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1834,7 +1834,6 @@
 		WRT_REG_WORD(&reg->isp.hccr, HCCR_CLR_HOST_INT);
 	}
 	spin_unlock_irq(&ha->hardware_lock);
-	ha->isp_ops->enable_intrs(ha);
 
 fail:
 	return ret;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 26afe44..6d0f0e5 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1740,6 +1740,8 @@
 	if (ret)
 		goto probe_failed;
 
+	ha->isp_ops->enable_intrs(ha);
+
 	scsi_scan_host(host);
 
 	qla2x00_alloc_sysfs_attr(ha);
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index 4a1cf63..9053508 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -914,6 +914,7 @@
 				ds[i].d_count = sg_dma_len(s);
 			}
 			sg_count -= n;
+			sg = s;
 		}
 	} else {
 		cmd->dataseg[0].d_base = 0;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index ff5d56b..62307bd 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -852,7 +852,7 @@
 void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 {
 	int result = cmd->result;
-	int this_count = scsi_bufflen(cmd);
+	int this_count;
 	struct request_queue *q = cmd->device->request_queue;
 	struct request *req = cmd->request;
 	int error = 0;
@@ -908,6 +908,7 @@
 	 */
 	if (scsi_end_request(cmd, error, good_bytes, result == 0) == NULL)
 		return;
+	this_count = blk_rq_bytes(req);
 
 	/* good_bytes = 0, or (inclusive) there were leftovers and
 	 * result = 0, so scsi_end_request couldn't retry.
diff --git a/drivers/spi/orion_spi.c b/drivers/spi/orion_spi.c
index c4eaacd..b872bfa 100644
--- a/drivers/spi/orion_spi.c
+++ b/drivers/spi/orion_spi.c
@@ -427,7 +427,7 @@
 			goto msg_rejected;
 		}
 
-		if (t->speed_hz < orion_spi->min_speed) {
+		if (t->speed_hz && t->speed_hz < orion_spi->min_speed) {
 			dev_err(&spi->dev,
 				"message rejected : "
 				"device min speed (%d Hz) exceeds "
diff --git a/drivers/spi/pxa2xx_spi.c b/drivers/spi/pxa2xx_spi.c
index 0e53354..d47d363 100644
--- a/drivers/spi/pxa2xx_spi.c
+++ b/drivers/spi/pxa2xx_spi.c
@@ -49,7 +49,7 @@
 
 #define DMA_INT_MASK		(DCSR_ENDINTR | DCSR_STARTINTR | DCSR_BUSERR)
 #define RESET_DMA_CHANNEL	(DCSR_NODESC | DMA_INT_MASK)
-#define IS_DMA_ALIGNED(x)	(((x) & 0x07) == 0)
+#define IS_DMA_ALIGNED(x)	((((u32)(x)) & 0x07) == 0)
 #define MAX_DMA_LEN		8191
 
 /*
@@ -896,7 +896,7 @@
 				|| transfer->rx_dma || transfer->tx_dma) {
 			dev_err(&drv_data->pdev->dev,
 				"pump_transfers: mapped transfer length "
-				"of %lu is greater than %d\n",
+				"of %u is greater than %d\n",
 				transfer->len, MAX_DMA_LEN);
 			message->status = -EINVAL;
 			giveback(drv_data);
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 87ab244..0ffabf5 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -471,6 +471,7 @@
 #endif
 			break;
 		case SSB_BUSTYPE_SSB:
+			dev->dma_mask = &dev->coherent_dma_mask;
 			break;
 		}
 
diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
index c6299e8..9cbff84 100644
--- a/drivers/video/console/fbcon.c
+++ b/drivers/video/console/fbcon.c
@@ -2400,11 +2400,15 @@
 
  	if (!fbcon_is_inactive(vc, info)) {
 		if (ops->blank_state != blank) {
+			int ret = 1;
+
 			ops->blank_state = blank;
 			fbcon_cursor(vc, blank ? CM_ERASE : CM_DRAW);
 			ops->cursor_flash = (!blank);
 
-			if (fb_blank(info, blank))
+			if (info->fbops->fb_blank)
+				ret = info->fbops->fb_blank(blank, info);
+			if (ret)
 				fbcon_generic_blank(vc, info, blank);
 		}
 
diff --git a/drivers/video/console/fbcon.h b/drivers/video/console/fbcon.h
index a6e38e9..89a34688 100644
--- a/drivers/video/console/fbcon.h
+++ b/drivers/video/console/fbcon.h
@@ -110,7 +110,7 @@
 	__u32 max_len;
 	max_len = max(info->var.green.length, info->var.red.length);
 	max_len = max(info->var.blue.length, max_len);
-	return ~(0xfff << (max_len & 0xff));
+	return (~(0xfff << max_len)) & 0xff;
 }
 
 static inline int attr_col_ec(int shift, struct vc_data *vc,
diff --git a/fs/dcache.c b/fs/dcache.c
index 80e9395..e7a1a99 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1395,6 +1395,10 @@
 		if (dentry->d_parent != parent)
 			goto next;
 
+		/* non-existing due to RCU? */
+		if (d_unhashed(dentry))
+			goto next;
+
 		/*
 		 * It is safe to compare names since d_move() cannot
 		 * change the qstr (protected by d_lock).
@@ -1410,10 +1414,8 @@
 				goto next;
 		}
 
-		if (!d_unhashed(dentry)) {
-			atomic_inc(&dentry->d_count);
-			found = dentry;
-		}
+		atomic_inc(&dentry->d_count);
+		found = dentry;
 		spin_unlock(&dentry->d_lock);
 		break;
 next:
diff --git a/fs/exec.c b/fs/exec.c
index 32993be..cecee50 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -752,11 +752,11 @@
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
 	task_unlock(tsk);
-	mm_update_next_owner(old_mm);
 	arch_pick_mmap_layout(mm);
 	if (old_mm) {
 		up_read(&old_mm->mmap_sem);
 		BUG_ON(active_mm != old_mm);
+		mm_update_next_owner(old_mm);
 		mmput(old_mm);
 		return 0;
 	}
diff --git a/fs/inotify_user.c b/fs/inotify_user.c
index 6024942..d85c7d9 100644
--- a/fs/inotify_user.c
+++ b/fs/inotify_user.c
@@ -323,7 +323,7 @@
 }
 
 /*
- * remove_kevent - cleans up and ultimately frees the given kevent
+ * remove_kevent - cleans up the given kevent
  *
  * Caller must hold dev->ev_mutex.
  */
@@ -334,7 +334,13 @@
 
 	dev->event_count--;
 	dev->queue_size -= sizeof(struct inotify_event) + kevent->event.len;
+}
 
+/*
+ * free_kevent - frees the given kevent.
+ */
+static void free_kevent(struct inotify_kernel_event *kevent)
+{
 	kfree(kevent->name);
 	kmem_cache_free(event_cachep, kevent);
 }
@@ -350,6 +356,7 @@
 		struct inotify_kernel_event *kevent;
 		kevent = inotify_dev_get_event(dev);
 		remove_kevent(dev, kevent);
+		free_kevent(kevent);
 	}
 }
 
@@ -433,17 +440,15 @@
 	dev = file->private_data;
 
 	while (1) {
-		int events;
 
 		prepare_to_wait(&dev->wq, &wait, TASK_INTERRUPTIBLE);
 
 		mutex_lock(&dev->ev_mutex);
-		events = !list_empty(&dev->events);
-		mutex_unlock(&dev->ev_mutex);
-		if (events) {
+		if (!list_empty(&dev->events)) {
 			ret = 0;
 			break;
 		}
+		mutex_unlock(&dev->ev_mutex);
 
 		if (file->f_flags & O_NONBLOCK) {
 			ret = -EAGAIN;
@@ -462,7 +467,6 @@
 	if (ret)
 		return ret;
 
-	mutex_lock(&dev->ev_mutex);
 	while (1) {
 		struct inotify_kernel_event *kevent;
 
@@ -481,6 +485,13 @@
 			}
 			break;
 		}
+		remove_kevent(dev, kevent);
+
+		/*
+		 * Must perform the copy_to_user outside the mutex in order
+		 * to avoid a lock order reversal with mmap_sem.
+		 */
+		mutex_unlock(&dev->ev_mutex);
 
 		if (copy_to_user(buf, &kevent->event, event_size)) {
 			ret = -EFAULT;
@@ -498,7 +509,9 @@
 			count -= kevent->event.len;
 		}
 
-		remove_kevent(dev, kevent);
+		free_kevent(kevent);
+
+		mutex_lock(&dev->ev_mutex);
 	}
 	mutex_unlock(&dev->ev_mutex);
 
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 52312ec..5145cb9 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -58,7 +58,7 @@
  * size 0 on the assumption that it's going to be used for an mmap of shared
  * memory
  */
-static int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
+int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 {
 	struct pagevec lru_pvec;
 	unsigned long npages, xpages, loop, limit;
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index b9cb774..d7f7645 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -538,7 +538,7 @@
 		printk(KERN_DEBUG "\t%d orphan inode numbers:\n", n);
 		for (i = 0; i < n; i++)
 			printk(KERN_DEBUG "\t  ino %llu\n",
-			       le64_to_cpu(orph->inos[i]));
+			       (unsigned long long)le64_to_cpu(orph->inos[i]));
 		break;
 	}
 	default:
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 2b267c9..526c01e 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -426,7 +426,7 @@
 
 	while (1) {
 		dbg_gen("feed '%s', ino %llu, new f_pos %#x",
-			dent->name, le64_to_cpu(dent->inum),
+			dent->name, (unsigned long long)le64_to_cpu(dent->inum),
 			key_hash_flash(c, &dent->key));
 		ubifs_assert(dent->ch.sqnum > ubifs_inode(dir)->creat_sqnum);
 
diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c
index e045c8b..47814cd 100644
--- a/fs/ubifs/find.c
+++ b/fs/ubifs/find.c
@@ -507,7 +507,6 @@
 		rsvd_idx_lebs = 0;
 	lebs = c->lst.empty_lebs + c->freeable_cnt + c->idx_gc_cnt -
 	       c->lst.taken_empty_lebs;
-	ubifs_assert(lebs + c->lst.idx_lebs >= c->min_idx_lebs);
 	if (rsvd_idx_lebs < lebs)
 		/*
 		 * OK to allocate an empty LEB, but we still don't want to go
diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c
index 13f1019..02aba36 100644
--- a/fs/ubifs/gc.c
+++ b/fs/ubifs/gc.c
@@ -334,15 +334,15 @@
 
 		err = move_nodes(c, sleb);
 		if (err)
-			goto out;
+			goto out_inc_seq;
 
 		err = gc_sync_wbufs(c);
 		if (err)
-			goto out;
+			goto out_inc_seq;
 
 		err = ubifs_change_one_lp(c, lnum, c->leb_size, 0, 0, 0, 0);
 		if (err)
-			goto out;
+			goto out_inc_seq;
 
 		/* Allow for races with TNC */
 		c->gced_lnum = lnum;
@@ -369,6 +369,14 @@
 out:
 	ubifs_scan_destroy(sleb);
 	return err;
+
+out_inc_seq:
+	/* We may have moved at least some nodes so allow for races with TNC */
+	c->gced_lnum = lnum;
+	smp_wmb();
+	c->gc_seq += 1;
+	smp_wmb();
+	goto out;
 }
 
 /**
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 7562464..3f49020 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1024,14 +1024,13 @@
 		goto out_dereg;
 	}
 
+	sprintf(c->bgt_name, BGT_NAME_PATTERN, c->vi.ubi_num, c->vi.vol_id);
 	if (!mounted_read_only) {
 		err = alloc_wbufs(c);
 		if (err)
 			goto out_cbuf;
 
 		/* Create background thread */
-		sprintf(c->bgt_name, BGT_NAME_PATTERN, c->vi.ubi_num,
-			c->vi.vol_id);
 		c->bgt = kthread_create(ubifs_bg_thread, c, c->bgt_name);
 		if (!c->bgt)
 			c->bgt = ERR_PTR(-EINVAL);
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 7da209a..7634c59 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -1476,7 +1476,7 @@
 	}
 
 	err = fallible_read_node(c, key, &zbr, node);
-	if (maybe_leb_gced(c, zbr.lnum, gc_seq1)) {
+	if (err <= 0 || maybe_leb_gced(c, zbr.lnum, gc_seq1)) {
 		/*
 		 * The node may have been GC'ed out from under us so try again
 		 * while keeping the TNC mutex locked.
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 00e80df..dbd9cef 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -4118,7 +4118,7 @@
 	ASSERT(nextents <= XFS_LINEAR_EXTS);
 	size = nextents * sizeof(xfs_bmbt_rec_t);
 
-	xfs_iext_irec_compact_full(ifp);
+	xfs_iext_irec_compact_pages(ifp);
 	ASSERT(ifp->if_real_bytes == XFS_IEXT_BUFSZ);
 
 	ep = ifp->if_u1.if_ext_irec->er_extbuf;
@@ -4449,8 +4449,7 @@
  * compaction policy is as follows:
  *
  *    Full Compaction: Extents fit into a single page (or inline buffer)
- *    Full Compaction: Extents occupy less than 10% of allocated space
- * Partial Compaction: Extents occupy > 10% and < 50% of allocated space
+ * Partial Compaction: Extents occupy less than 50% of allocated space
  *      No Compaction: Extents occupy at least 50% of allocated space
  */
 void
@@ -4471,8 +4470,6 @@
 		xfs_iext_direct_to_inline(ifp, nextents);
 	} else if (nextents <= XFS_LINEAR_EXTS) {
 		xfs_iext_indirect_to_direct(ifp);
-	} else if (nextents < (nlists * XFS_LINEAR_EXTS) >> 3) {
-		xfs_iext_irec_compact_full(ifp);
 	} else if (nextents < (nlists * XFS_LINEAR_EXTS) >> 1) {
 		xfs_iext_irec_compact_pages(ifp);
 	}
@@ -4496,7 +4493,7 @@
 		erp_next = erp + 1;
 		if (erp_next->er_extcount <=
 		    (XFS_LINEAR_EXTS - erp->er_extcount)) {
-			memmove(&erp->er_extbuf[erp->er_extcount],
+			memcpy(&erp->er_extbuf[erp->er_extcount],
 				erp_next->er_extbuf, erp_next->er_extcount *
 				sizeof(xfs_bmbt_rec_t));
 			erp->er_extcount += erp_next->er_extcount;
@@ -4516,91 +4513,6 @@
 }
 
 /*
- * Fully compact the extent records managed by the indirection array.
- */
-void
-xfs_iext_irec_compact_full(
-	xfs_ifork_t	*ifp)			/* inode fork pointer */
-{
-	xfs_bmbt_rec_host_t *ep, *ep_next;	/* extent record pointers */
-	xfs_ext_irec_t	*erp, *erp_next;	/* extent irec pointers */
-	int		erp_idx = 0;		/* extent irec index */
-	int		ext_avail;		/* empty entries in ex list */
-	int		ext_diff;		/* number of exts to add */
-	int		nlists;			/* number of irec's (ex lists) */
-
-	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
-
-	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
-	erp = ifp->if_u1.if_ext_irec;
-	ep = &erp->er_extbuf[erp->er_extcount];
-	erp_next = erp + 1;
-	ep_next = erp_next->er_extbuf;
-
-	while (erp_idx < nlists - 1) {
-		/*
-		 * Check how many extent records are available in this irec.
-		 * If there is none skip the whole exercise.
-		 */
-		ext_avail = XFS_LINEAR_EXTS - erp->er_extcount;
-		if (ext_avail) {
-
-			/*
-			 * Copy over as many as possible extent records into
-			 * the previous page.
-			 */
-			ext_diff = MIN(ext_avail, erp_next->er_extcount);
-			memcpy(ep, ep_next, ext_diff * sizeof(xfs_bmbt_rec_t));
-			erp->er_extcount += ext_diff;
-			erp_next->er_extcount -= ext_diff;
-
-			/*
-			 * If the next irec is empty now we can simply
-			 * remove it.
-			 */
-			if (erp_next->er_extcount == 0) {
-				/*
-				 * Free page before removing extent record
-				 * so er_extoffs don't get modified in
-				 * xfs_iext_irec_remove.
-				 */
-				kmem_free(erp_next->er_extbuf);
-				erp_next->er_extbuf = NULL;
-				xfs_iext_irec_remove(ifp, erp_idx + 1);
-				erp = &ifp->if_u1.if_ext_irec[erp_idx];
-				nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
-
-			/*
-			 * If the next irec is not empty move up the content
-			 * that has not been copied to the previous page to
-			 * the beggining of this one.
-			 */
-			} else {
-				memmove(erp_next->er_extbuf, &ep_next[ext_diff],
-					erp_next->er_extcount *
-					sizeof(xfs_bmbt_rec_t));
-				ep_next = erp_next->er_extbuf;
-				memset(&ep_next[erp_next->er_extcount], 0,
-					(XFS_LINEAR_EXTS -
-						erp_next->er_extcount) *
-					sizeof(xfs_bmbt_rec_t));
-			}
-		}
-
-		if (erp->er_extcount == XFS_LINEAR_EXTS) {
-			erp_idx++;
-			if (erp_idx < nlists)
-				erp = &ifp->if_u1.if_ext_irec[erp_idx];
-			else
-				break;
-		}
-		ep = &erp->er_extbuf[erp->er_extcount];
-		erp_next = erp + 1;
-		ep_next = erp_next->er_extbuf;
-	}
-}
-
-/*
  * This is called to update the er_extoff field in the indirection
  * array when extents have been added or removed from one of the
  * extent lists. erp_idx contains the irec index to begin updating
diff --git a/include/asm-mips/cevt-r4k.h b/include/asm-mips/cevt-r4k.h
new file mode 100644
index 0000000..fa4328f
--- /dev/null
+++ b/include/asm-mips/cevt-r4k.h
@@ -0,0 +1,46 @@
+/*
+ * 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.
+ *
+ * Copyright (C) 2008 Kevin D. Kissell
+ */
+
+/*
+ * Definitions used for common event timer implementation
+ * for MIPS 4K-type processors and their MIPS MT variants.
+ * Avoids unsightly extern declarations in C files.
+ */
+#ifndef __ASM_CEVT_R4K_H
+#define __ASM_CEVT_R4K_H
+
+DECLARE_PER_CPU(struct clock_event_device, mips_clockevent_device);
+
+void mips_event_handler(struct clock_event_device *dev);
+int c0_compare_int_usable(void);
+void mips_set_clock_mode(enum clock_event_mode, struct clock_event_device *);
+irqreturn_t c0_compare_interrupt(int, void *);
+
+extern struct irqaction c0_compare_irqaction;
+extern int cp0_timer_irq_installed;
+
+/*
+ * Possibly handle a performance counter interrupt.
+ * Return true if the timer interrupt should not be checked
+ */
+
+static inline int handle_perf_irq(int r2)
+{
+	/*
+	 * The performance counter overflow interrupt may be shared with the
+	 * timer interrupt (cp0_perfcount_irq < 0). If it is and a
+	 * performance counter has overflowed (perf_irq() == IRQ_HANDLED)
+	 * and we can't reliably determine if a counter interrupt has also
+	 * happened (!r2) then don't check for a timer interrupt.
+	 */
+	return (cp0_perfcount_irq < 0) &&
+		perf_irq() == IRQ_HANDLED &&
+		!r2;
+}
+
+#endif /* __ASM_CEVT_R4K_H */
diff --git a/include/asm-mips/irqflags.h b/include/asm-mips/irqflags.h
index 881e886..701ec0b 100644
--- a/include/asm-mips/irqflags.h
+++ b/include/asm-mips/irqflags.h
@@ -38,8 +38,17 @@
 	"	.set	pop						\n"
 	"	.endm");
 
+extern void smtc_ipi_replay(void);
+
 static inline void raw_local_irq_enable(void)
 {
+#ifdef CONFIG_MIPS_MT_SMTC
+	/*
+	 * SMTC kernel needs to do a software replay of queued
+	 * IPIs, at the cost of call overhead on each local_irq_enable()
+	 */
+	smtc_ipi_replay();
+#endif
 	__asm__ __volatile__(
 		"raw_local_irq_enable"
 		: /* no outputs */
@@ -47,6 +56,7 @@
 		: "memory");
 }
 
+
 /*
  * For cli() we have to insert nops to make sure that the new value
  * has actually arrived in the status register before the end of this
@@ -185,15 +195,14 @@
 	"	.set	pop						\n"
 	"	.endm							\n");
 
-extern void smtc_ipi_replay(void);
 
 static inline void raw_local_irq_restore(unsigned long flags)
 {
 	unsigned long __tmp1;
 
-#ifdef CONFIG_MIPS_MT_SMTC_INSTANT_REPLAY
+#ifdef CONFIG_MIPS_MT_SMTC
 	/*
-	 * CONFIG_MIPS_MT_SMTC_INSTANT_REPLAY does prompt replay of deferred
+	 * SMTC kernel needs to do a software replay of queued
 	 * IPIs, at the cost of branch and call overhead on each
 	 * local_irq_restore()
 	 */
@@ -208,6 +217,17 @@
 		: "memory");
 }
 
+static inline void __raw_local_irq_restore(unsigned long flags)
+{
+	unsigned long __tmp1;
+
+	__asm__ __volatile__(
+		"raw_local_irq_restore\t%0"
+		: "=r" (__tmp1)
+		: "0" (flags)
+		: "memory");
+}
+
 static inline int raw_irqs_disabled_flags(unsigned long flags)
 {
 #ifdef CONFIG_MIPS_MT_SMTC
diff --git a/include/asm-mips/mipsregs.h b/include/asm-mips/mipsregs.h
index a46f8e2..9798660 100644
--- a/include/asm-mips/mipsregs.h
+++ b/include/asm-mips/mipsregs.h
@@ -1462,7 +1462,7 @@
 {								\
 	unsigned int res;					\
 	unsigned int omt;					\
-	unsigned int flags;					\
+	unsigned long flags;					\
 								\
 	local_irq_save(flags);					\
 	omt = __dmt();						\
@@ -1480,7 +1480,7 @@
 {								\
 	unsigned int res;					\
 	unsigned int omt;					\
-	unsigned int flags;					\
+	unsigned long flags;					\
 								\
 	local_irq_save(flags);					\
 	omt = __dmt();						\
@@ -1498,7 +1498,7 @@
 {								\
 	unsigned int res;					\
 	unsigned int omt;					\
-	unsigned int flags;					\
+	unsigned long flags;					\
 								\
 	local_irq_save(flags);					\
 								\
diff --git a/include/asm-mips/smtc.h b/include/asm-mips/smtc.h
index 3639b28..ea60bf0 100644
--- a/include/asm-mips/smtc.h
+++ b/include/asm-mips/smtc.h
@@ -6,6 +6,7 @@
  */
 
 #include <asm/mips_mt.h>
+#include <asm/smtc_ipi.h>
 
 /*
  * System-wide SMTC status information
@@ -38,14 +39,15 @@
 struct task_struct;
 
 void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu);
-
+void self_ipi(struct smtc_ipi *);
 void smtc_flush_tlb_asid(unsigned long asid);
-extern int mipsmt_build_cpu_map(int startslot);
-extern void mipsmt_prepare_cpus(void);
+extern int smtc_build_cpu_map(int startslot);
+extern void smtc_prepare_cpus(int cpus);
 extern void smtc_smp_finish(void);
 extern void smtc_boot_secondary(int cpu, struct task_struct *t);
 extern void smtc_cpus_done(void);
 
+
 /*
  * Sharing the TLB between multiple VPEs means that the
  * "random" index selection function is not allowed to
diff --git a/include/asm-mips/stackframe.h b/include/asm-mips/stackframe.h
index 051e1af..4c37c4e5 100644
--- a/include/asm-mips/stackframe.h
+++ b/include/asm-mips/stackframe.h
@@ -297,14 +297,31 @@
 #ifdef CONFIG_MIPS_MT_SMTC
 		.set	mips32r2
 		/*
-		 * This may not really be necessary if ints are already
-		 * inhibited here.
+		 * We need to make sure the read-modify-write
+		 * of Status below isn't perturbed by an interrupt
+		 * or cross-TC access, so we need to do at least a DMT,
+		 * protected by an interrupt-inhibit. But setting IXMT
+		 * also creates a few-cycle window where an IPI could
+		 * be queued and not be detected before potentially
+		 * returning to a WAIT or user-mode loop. It must be
+		 * replayed.
+		 *
+		 * We're in the middle of a context switch, and
+		 * we can't dispatch it directly without trashing
+		 * some registers, so we'll try to detect this unlikely
+		 * case and program a software interrupt in the VPE,
+		 * as would be done for a cross-VPE IPI.  To accomodate
+		 * the handling of that case, we're doing a DVPE instead
+		 * of just a DMT here to protect against other threads.
+		 * This is a lot of cruft to cover a tiny window.
+		 * If you can find a better design, implement it!
+		 *
 		 */
 		mfc0	v0, CP0_TCSTATUS
 		ori	v0, TCSTATUS_IXMT
 		mtc0	v0, CP0_TCSTATUS
 		_ehb
-		DMT	5				# dmt a1
+		DVPE	5				# dvpe a1
 		jal	mips_ihb
 #endif /* CONFIG_MIPS_MT_SMTC */
 		mfc0	a0, CP0_STATUS
@@ -325,17 +342,50 @@
  */
 		LONG_L	v1, PT_TCSTATUS(sp)
 		_ehb
-		mfc0	v0, CP0_TCSTATUS
+		mfc0	a0, CP0_TCSTATUS
 		andi	v1, TCSTATUS_IXMT
-		/* We know that TCStatua.IXMT should be set from above */
-		xori	v0, v0, TCSTATUS_IXMT
-		or	v0, v0, v1
-		mtc0	v0, CP0_TCSTATUS
-		_ehb
-		andi	a1, a1, VPECONTROL_TE
+		bnez	v1, 0f
+
+/*
+ * We'd like to detect any IPIs queued in the tiny window
+ * above and request an software interrupt to service them
+ * when we ERET.
+ *
+ * Computing the offset into the IPIQ array of the executing
+ * TC's IPI queue in-line would be tedious.  We use part of
+ * the TCContext register to hold 16 bits of offset that we
+ * can add in-line to find the queue head.
+ */
+		mfc0	v0, CP0_TCCONTEXT
+		la	a2, IPIQ
+		srl	v0, v0, 16
+		addu	a2, a2, v0
+		LONG_L	v0, 0(a2)
+		beqz	v0, 0f
+/*
+ * If we have a queue, provoke dispatch within the VPE by setting C_SW1
+ */
+		mfc0	v0, CP0_CAUSE
+		ori	v0, v0, C_SW1
+		mtc0	v0, CP0_CAUSE
+0:
+		/*
+		 * This test should really never branch but
+		 * let's be prudent here.  Having atomized
+		 * the shared register modifications, we can
+		 * now EVPE, and must do so before interrupts
+		 * are potentially re-enabled.
+		 */
+		andi	a1, a1, MVPCONTROL_EVP
 		beqz	a1, 1f
-		emt
+		evpe
 1:
+		/* We know that TCStatua.IXMT should be set from above */
+		xori	a0, a0, TCSTATUS_IXMT
+		or	a0, a0, v1
+		mtc0	a0, CP0_TCSTATUS
+		_ehb
+
 		.set	mips0
 #endif /* CONFIG_MIPS_MT_SMTC */
 		LONG_L	v1, PT_EPC(sp)
diff --git a/include/asm-x86/a.out-core.h b/include/asm-x86/a.out-core.h
index 714207a..f570576 100644
--- a/include/asm-x86/a.out-core.h
+++ b/include/asm-x86/a.out-core.h
@@ -9,8 +9,8 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
-#ifndef _ASM_A_OUT_CORE_H
-#define _ASM_A_OUT_CORE_H
+#ifndef ASM_X86__A_OUT_CORE_H
+#define ASM_X86__A_OUT_CORE_H
 
 #ifdef __KERNEL__
 #ifdef CONFIG_X86_32
@@ -70,4 +70,4 @@
 
 #endif /* CONFIG_X86_32 */
 #endif /* __KERNEL__ */
-#endif /* _ASM_A_OUT_CORE_H */
+#endif /* ASM_X86__A_OUT_CORE_H */
diff --git a/include/asm-x86/a.out.h b/include/asm-x86/a.out.h
index 4684f97..0948748 100644
--- a/include/asm-x86/a.out.h
+++ b/include/asm-x86/a.out.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_A_OUT_H
-#define _ASM_X86_A_OUT_H
+#ifndef ASM_X86__A_OUT_H
+#define ASM_X86__A_OUT_H
 
 struct exec
 {
@@ -17,4 +17,4 @@
 #define N_DRSIZE(a)	((a).a_drsize)
 #define N_SYMSIZE(a)	((a).a_syms)
 
-#endif /* _ASM_X86_A_OUT_H */
+#endif /* ASM_X86__A_OUT_H */
diff --git a/include/asm-x86/acpi.h b/include/asm-x86/acpi.h
index 35d1743..392e173 100644
--- a/include/asm-x86/acpi.h
+++ b/include/asm-x86/acpi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_ACPI_H
-#define _ASM_X86_ACPI_H
+#ifndef ASM_X86__ACPI_H
+#define ASM_X86__ACPI_H
 
 /*
  *  Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
@@ -175,4 +175,4 @@
 
 #define acpi_unlazy_tlb(x)	leave_mm(x)
 
-#endif /*__X86_ASM_ACPI_H*/
+#endif /* ASM_X86__ACPI_H */
diff --git a/include/asm-x86/agp.h b/include/asm-x86/agp.h
index e4004a9..3617fd4 100644
--- a/include/asm-x86/agp.h
+++ b/include/asm-x86/agp.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_AGP_H
-#define _ASM_X86_AGP_H
+#ifndef ASM_X86__AGP_H
+#define ASM_X86__AGP_H
 
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
@@ -32,4 +32,4 @@
 #define free_gatt_pages(table, order)	\
 	free_pages((unsigned long)(table), (order))
 
-#endif
+#endif /* ASM_X86__AGP_H */
diff --git a/include/asm-x86/alternative.h b/include/asm-x86/alternative.h
index f6aa18e..22d3c98 100644
--- a/include/asm-x86/alternative.h
+++ b/include/asm-x86/alternative.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_ALTERNATIVE_H
-#define _ASM_X86_ALTERNATIVE_H
+#ifndef ASM_X86__ALTERNATIVE_H
+#define ASM_X86__ALTERNATIVE_H
 
 #include <linux/types.h>
 #include <linux/stddef.h>
@@ -180,4 +180,4 @@
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_early(void *addr, const void *opcode, size_t len);
 
-#endif /* _ASM_X86_ALTERNATIVE_H */
+#endif /* ASM_X86__ALTERNATIVE_H */
diff --git a/include/asm-x86/amd_iommu.h b/include/asm-x86/amd_iommu.h
index 30a1204..783f43e 100644
--- a/include/asm-x86/amd_iommu.h
+++ b/include/asm-x86/amd_iommu.h
@@ -17,8 +17,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef _ASM_X86_AMD_IOMMU_H
-#define _ASM_X86_AMD_IOMMU_H
+#ifndef ASM_X86__AMD_IOMMU_H
+#define ASM_X86__AMD_IOMMU_H
 
 #ifdef CONFIG_AMD_IOMMU
 extern int amd_iommu_init(void);
@@ -29,4 +29,4 @@
 static inline void amd_iommu_detect(void) { }
 #endif
 
-#endif
+#endif /* ASM_X86__AMD_IOMMU_H */
diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h
index dcc8120..1ffa4e5 100644
--- a/include/asm-x86/amd_iommu_types.h
+++ b/include/asm-x86/amd_iommu_types.h
@@ -17,8 +17,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef __AMD_IOMMU_TYPES_H__
-#define __AMD_IOMMU_TYPES_H__
+#ifndef ASM_X86__AMD_IOMMU_TYPES_H
+#define ASM_X86__AMD_IOMMU_TYPES_H
 
 #include <linux/types.h>
 #include <linux/list.h>
@@ -341,4 +341,4 @@
 	return (((u16)bus) << 8) | devfn;
 }
 
-#endif
+#endif /* ASM_X86__AMD_IOMMU_TYPES_H */
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index 133c998..65590c9 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_APIC_H
-#define _ASM_X86_APIC_H
+#ifndef ASM_X86__APIC_H
+#define ASM_X86__APIC_H
 
 #include <linux/pm.h>
 #include <linux/delay.h>
@@ -54,6 +54,11 @@
 #endif
 
 extern int is_vsmp_box(void);
+extern void xapic_wait_icr_idle(void);
+extern u32 safe_xapic_wait_icr_idle(void);
+extern u64 xapic_icr_read(void);
+extern void xapic_icr_write(u32, u32);
+extern int setup_profiling_timer(unsigned int);
 
 static inline void native_apic_write(unsigned long reg, u32 v)
 {
@@ -76,9 +81,7 @@
 static inline void ack_APIC_irq(void)
 {
 	/*
-	 * ack_APIC_irq() actually gets compiled as a single instruction:
-	 * - a single rmw on Pentium/82489DX
-	 * - a single write on P6+ cores (CONFIG_X86_GOOD_APIC)
+	 * ack_APIC_irq() actually gets compiled as a single instruction
 	 * ... yummie.
 	 */
 
@@ -128,4 +131,4 @@
 
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
-#endif /* __ASM_APIC_H */
+#endif /* ASM_X86__APIC_H */
diff --git a/include/asm-x86/apicdef.h b/include/asm-x86/apicdef.h
index 6b9008c..c40687d 100644
--- a/include/asm-x86/apicdef.h
+++ b/include/asm-x86/apicdef.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_APICDEF_H
-#define _ASM_X86_APICDEF_H
+#ifndef ASM_X86__APICDEF_H
+#define ASM_X86__APICDEF_H
 
 /*
  * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
@@ -411,4 +411,4 @@
 #else
  #define BAD_APICID 0xFFFFu
 #endif
-#endif
+#endif /* ASM_X86__APICDEF_H */
diff --git a/include/asm-x86/arch_hooks.h b/include/asm-x86/arch_hooks.h
index 8411750..72adc3a 100644
--- a/include/asm-x86/arch_hooks.h
+++ b/include/asm-x86/arch_hooks.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_ARCH_HOOKS_H
-#define _ASM_ARCH_HOOKS_H
+#ifndef ASM_X86__ARCH_HOOKS_H
+#define ASM_X86__ARCH_HOOKS_H
 
 #include <linux/interrupt.h>
 
@@ -25,4 +25,4 @@
 extern void time_init_hook(void);
 extern void mca_nmi_hook(void);
 
-#endif
+#endif /* ASM_X86__ARCH_HOOKS_H */
diff --git a/include/asm-x86/asm.h b/include/asm-x86/asm.h
index 9722032..e1355f4 100644
--- a/include/asm-x86/asm.h
+++ b/include/asm-x86/asm.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_ASM_H
-#define _ASM_X86_ASM_H
+#ifndef ASM_X86__ASM_H
+#define ASM_X86__ASM_H
 
 #ifdef __ASSEMBLY__
 # define __ASM_FORM(x)	x
@@ -20,17 +20,22 @@
 
 #define _ASM_PTR	__ASM_SEL(.long, .quad)
 #define _ASM_ALIGN	__ASM_SEL(.balign 4, .balign 8)
-#define _ASM_MOV_UL	__ASM_SIZE(mov)
 
+#define _ASM_MOV	__ASM_SIZE(mov)
 #define _ASM_INC	__ASM_SIZE(inc)
 #define _ASM_DEC	__ASM_SIZE(dec)
 #define _ASM_ADD	__ASM_SIZE(add)
 #define _ASM_SUB	__ASM_SIZE(sub)
 #define _ASM_XADD	__ASM_SIZE(xadd)
+
 #define _ASM_AX		__ASM_REG(ax)
 #define _ASM_BX		__ASM_REG(bx)
 #define _ASM_CX		__ASM_REG(cx)
 #define _ASM_DX		__ASM_REG(dx)
+#define _ASM_SP		__ASM_REG(sp)
+#define _ASM_BP		__ASM_REG(bp)
+#define _ASM_SI		__ASM_REG(si)
+#define _ASM_DI		__ASM_REG(di)
 
 /* Exception table entry */
 # define _ASM_EXTABLE(from,to) \
@@ -39,4 +44,4 @@
 	_ASM_PTR #from "," #to "\n" \
 	" .previous\n"
 
-#endif /* _ASM_X86_ASM_H */
+#endif /* ASM_X86__ASM_H */
diff --git a/include/asm-x86/atomic_32.h b/include/asm-x86/atomic_32.h
index 21a4825..14d3f0b 100644
--- a/include/asm-x86/atomic_32.h
+++ b/include/asm-x86/atomic_32.h
@@ -1,5 +1,5 @@
-#ifndef __ARCH_I386_ATOMIC__
-#define __ARCH_I386_ATOMIC__
+#ifndef ASM_X86__ATOMIC_32_H
+#define ASM_X86__ATOMIC_32_H
 
 #include <linux/compiler.h>
 #include <asm/processor.h>
@@ -256,4 +256,4 @@
 #define smp_mb__after_atomic_inc()	barrier()
 
 #include <asm-generic/atomic.h>
-#endif
+#endif /* ASM_X86__ATOMIC_32_H */
diff --git a/include/asm-x86/atomic_64.h b/include/asm-x86/atomic_64.h
index 91c7d03..2cb218c 100644
--- a/include/asm-x86/atomic_64.h
+++ b/include/asm-x86/atomic_64.h
@@ -1,5 +1,5 @@
-#ifndef __ARCH_X86_64_ATOMIC__
-#define __ARCH_X86_64_ATOMIC__
+#ifndef ASM_X86__ATOMIC_64_H
+#define ASM_X86__ATOMIC_64_H
 
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
@@ -470,4 +470,4 @@
 #define smp_mb__after_atomic_inc()	barrier()
 
 #include <asm-generic/atomic.h>
-#endif
+#endif /* ASM_X86__ATOMIC_64_H */
diff --git a/include/asm-x86/auxvec.h b/include/asm-x86/auxvec.h
index 87f5e6d..12c7cac 100644
--- a/include/asm-x86/auxvec.h
+++ b/include/asm-x86/auxvec.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_AUXVEC_H
-#define _ASM_X86_AUXVEC_H
+#ifndef ASM_X86__AUXVEC_H
+#define ASM_X86__AUXVEC_H
 /*
  * Architecture-neutral AT_ values in 0-17, leave some room
  * for more of them, start the x86-specific ones at 32.
@@ -9,4 +9,4 @@
 #endif
 #define AT_SYSINFO_EHDR		33
 
-#endif
+#endif /* ASM_X86__AUXVEC_H */
diff --git a/include/asm-x86/bios_ebda.h b/include/asm-x86/bios_ebda.h
index 0033e50..ec42ed8 100644
--- a/include/asm-x86/bios_ebda.h
+++ b/include/asm-x86/bios_ebda.h
@@ -1,5 +1,5 @@
-#ifndef _MACH_BIOS_EBDA_H
-#define _MACH_BIOS_EBDA_H
+#ifndef ASM_X86__BIOS_EBDA_H
+#define ASM_X86__BIOS_EBDA_H
 
 #include <asm/io.h>
 
@@ -16,4 +16,4 @@
 
 void reserve_ebda_region(void);
 
-#endif /* _MACH_BIOS_EBDA_H */
+#endif /* ASM_X86__BIOS_EBDA_H */
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
index cfb2b64..61989b9 100644
--- a/include/asm-x86/bitops.h
+++ b/include/asm-x86/bitops.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_BITOPS_H
-#define _ASM_X86_BITOPS_H
+#ifndef ASM_X86__BITOPS_H
+#define ASM_X86__BITOPS_H
 
 /*
  * Copyright 1992, Linus Torvalds.
@@ -458,4 +458,4 @@
 #include <asm-generic/bitops/minix.h>
 
 #endif /* __KERNEL__ */
-#endif	/* _ASM_X86_BITOPS_H */
+#endif /* ASM_X86__BITOPS_H */
diff --git a/include/asm-x86/boot.h b/include/asm-x86/boot.h
index 2faed7e..825de5d 100644
--- a/include/asm-x86/boot.h
+++ b/include/asm-x86/boot.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_BOOT_H
-#define _ASM_BOOT_H
+#ifndef ASM_X86__BOOT_H
+#define ASM_X86__BOOT_H
 
 /* Don't touch these, unless you really know what you're doing. */
 #define DEF_INITSEG	0x9000
@@ -25,4 +25,4 @@
 #define BOOT_STACK_SIZE	0x1000
 #endif
 
-#endif /* _ASM_BOOT_H */
+#endif /* ASM_X86__BOOT_H */
diff --git a/include/asm-x86/bootparam.h b/include/asm-x86/bootparam.h
index ae22bdf..ccf027e 100644
--- a/include/asm-x86/bootparam.h
+++ b/include/asm-x86/bootparam.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_BOOTPARAM_H
-#define _ASM_BOOTPARAM_H
+#ifndef ASM_X86__BOOTPARAM_H
+#define ASM_X86__BOOTPARAM_H
 
 #include <linux/types.h>
 #include <linux/screen_info.h>
@@ -108,4 +108,4 @@
 	__u8  _pad9[276];				/* 0xeec */
 } __attribute__((packed));
 
-#endif /* _ASM_BOOTPARAM_H */
+#endif /* ASM_X86__BOOTPARAM_H */
diff --git a/include/asm-x86/bug.h b/include/asm-x86/bug.h
index b69aa64..91ad43a 100644
--- a/include/asm-x86/bug.h
+++ b/include/asm-x86/bug.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_BUG_H
-#define _ASM_X86_BUG_H
+#ifndef ASM_X86__BUG_H
+#define ASM_X86__BUG_H
 
 #ifdef CONFIG_BUG
 #define HAVE_ARCH_BUG
@@ -36,4 +36,4 @@
 #endif /* !CONFIG_BUG */
 
 #include <asm-generic/bug.h>
-#endif
+#endif /* ASM_X86__BUG_H */
diff --git a/include/asm-x86/bugs.h b/include/asm-x86/bugs.h
index 021cbdd..4761c46 100644
--- a/include/asm-x86/bugs.h
+++ b/include/asm-x86/bugs.h
@@ -1,7 +1,7 @@
-#ifndef _ASM_X86_BUGS_H
-#define _ASM_X86_BUGS_H
+#ifndef ASM_X86__BUGS_H
+#define ASM_X86__BUGS_H
 
 extern void check_bugs(void);
 int ppro_with_ram_bug(void);
 
-#endif /* _ASM_X86_BUGS_H */
+#endif /* ASM_X86__BUGS_H */
diff --git a/include/asm-x86/byteorder.h b/include/asm-x86/byteorder.h
index e02ae2d..722f27d 100644
--- a/include/asm-x86/byteorder.h
+++ b/include/asm-x86/byteorder.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_BYTEORDER_H
-#define _ASM_X86_BYTEORDER_H
+#ifndef ASM_X86__BYTEORDER_H
+#define ASM_X86__BYTEORDER_H
 
 #include <asm/types.h>
 #include <linux/compiler.h>
@@ -78,4 +78,4 @@
 
 #include <linux/byteorder/little_endian.h>
 
-#endif /* _ASM_X86_BYTEORDER_H */
+#endif /* ASM_X86__BYTEORDER_H */
diff --git a/include/asm-x86/cache.h b/include/asm-x86/cache.h
index 1e0bac8..ea3f1cc 100644
--- a/include/asm-x86/cache.h
+++ b/include/asm-x86/cache.h
@@ -1,5 +1,5 @@
-#ifndef _ARCH_X86_CACHE_H
-#define _ARCH_X86_CACHE_H
+#ifndef ASM_X86__CACHE_H
+#define ASM_X86__CACHE_H
 
 /* L1 cache line size */
 #define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
@@ -17,4 +17,4 @@
 #endif
 #endif
 
-#endif
+#endif /* ASM_X86__CACHE_H */
diff --git a/include/asm-x86/cacheflush.h b/include/asm-x86/cacheflush.h
index f4c0ab5..59859cb 100644
--- a/include/asm-x86/cacheflush.h
+++ b/include/asm-x86/cacheflush.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_CACHEFLUSH_H
-#define _ASM_X86_CACHEFLUSH_H
+#ifndef ASM_X86__CACHEFLUSH_H
+#define ASM_X86__CACHEFLUSH_H
 
 /* Keep includes the same across arches.  */
 #include <linux/mm.h>
@@ -112,4 +112,4 @@
 }
 #endif
 
-#endif
+#endif /* ASM_X86__CACHEFLUSH_H */
diff --git a/include/asm-x86/calgary.h b/include/asm-x86/calgary.h
index 67f6040..933fd27 100644
--- a/include/asm-x86/calgary.h
+++ b/include/asm-x86/calgary.h
@@ -21,8 +21,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef _ASM_X86_64_CALGARY_H
-#define _ASM_X86_64_CALGARY_H
+#ifndef ASM_X86__CALGARY_H
+#define ASM_X86__CALGARY_H
 
 #include <linux/spinlock.h>
 #include <linux/device.h>
@@ -69,4 +69,4 @@
 static inline void detect_calgary(void) { return; }
 #endif
 
-#endif /* _ASM_X86_64_CALGARY_H */
+#endif /* ASM_X86__CALGARY_H */
diff --git a/include/asm-x86/checksum_32.h b/include/asm-x86/checksum_32.h
index 52bbb0d..d041e8c 100644
--- a/include/asm-x86/checksum_32.h
+++ b/include/asm-x86/checksum_32.h
@@ -1,5 +1,5 @@
-#ifndef _I386_CHECKSUM_H
-#define _I386_CHECKSUM_H
+#ifndef ASM_X86__CHECKSUM_32_H
+#define ASM_X86__CHECKSUM_32_H
 
 #include <linux/in6.h>
 
@@ -186,4 +186,4 @@
 	return (__force __wsum)-1; /* invalid checksum */
 }
 
-#endif
+#endif /* ASM_X86__CHECKSUM_32_H */
diff --git a/include/asm-x86/checksum_64.h b/include/asm-x86/checksum_64.h
index 8bd861c..110f403 100644
--- a/include/asm-x86/checksum_64.h
+++ b/include/asm-x86/checksum_64.h
@@ -1,5 +1,5 @@
-#ifndef _X86_64_CHECKSUM_H
-#define _X86_64_CHECKSUM_H
+#ifndef ASM_X86__CHECKSUM_64_H
+#define ASM_X86__CHECKSUM_64_H
 
 /*
  * Checksums for x86-64
@@ -188,4 +188,4 @@
 	return a;
 }
 
-#endif
+#endif /* ASM_X86__CHECKSUM_64_H */
diff --git a/include/asm-x86/cmpxchg_32.h b/include/asm-x86/cmpxchg_32.h
index bf5a69d..0622e45 100644
--- a/include/asm-x86/cmpxchg_32.h
+++ b/include/asm-x86/cmpxchg_32.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_CMPXCHG_H
-#define __ASM_CMPXCHG_H
+#ifndef ASM_X86__CMPXCHG_32_H
+#define ASM_X86__CMPXCHG_32_H
 
 #include <linux/bitops.h> /* for LOCK_PREFIX */
 
@@ -341,4 +341,4 @@
 
 #endif
 
-#endif
+#endif /* ASM_X86__CMPXCHG_32_H */
diff --git a/include/asm-x86/cmpxchg_64.h b/include/asm-x86/cmpxchg_64.h
index 17463cc..63c1a5e 100644
--- a/include/asm-x86/cmpxchg_64.h
+++ b/include/asm-x86/cmpxchg_64.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_CMPXCHG_H
-#define __ASM_CMPXCHG_H
+#ifndef ASM_X86__CMPXCHG_64_H
+#define ASM_X86__CMPXCHG_64_H
 
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
@@ -182,4 +182,4 @@
 	cmpxchg_local((ptr), (o), (n));					\
 })
 
-#endif
+#endif /* ASM_X86__CMPXCHG_64_H */
diff --git a/include/asm-x86/compat.h b/include/asm-x86/compat.h
index 1793ac3..6732b15 100644
--- a/include/asm-x86/compat.h
+++ b/include/asm-x86/compat.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_COMPAT_H
-#define _ASM_X86_64_COMPAT_H
+#ifndef ASM_X86__COMPAT_H
+#define ASM_X86__COMPAT_H
 
 /*
  * Architecture specific compatibility types
@@ -215,4 +215,4 @@
 	return current_thread_info()->status & TS_COMPAT;
 }
 
-#endif /* _ASM_X86_64_COMPAT_H */
+#endif /* ASM_X86__COMPAT_H */
diff --git a/include/asm-x86/cpu.h b/include/asm-x86/cpu.h
index 73f2ea8..83a1150 100644
--- a/include/asm-x86/cpu.h
+++ b/include/asm-x86/cpu.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_I386_CPU_H_
-#define _ASM_I386_CPU_H_
+#ifndef ASM_X86__CPU_H
+#define ASM_X86__CPU_H
 
 #include <linux/device.h>
 #include <linux/cpu.h>
@@ -17,4 +17,4 @@
 #endif
 
 DECLARE_PER_CPU(int, cpu_state);
-#endif /* _ASM_I386_CPU_H_ */
+#endif /* ASM_X86__CPU_H */
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
index cfcfb0a..250fa0c 100644
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -1,8 +1,8 @@
 /*
  * Defines x86 CPU feature bits
  */
-#ifndef _ASM_X86_CPUFEATURE_H
-#define _ASM_X86_CPUFEATURE_H
+#ifndef ASM_X86__CPUFEATURE_H
+#define ASM_X86__CPUFEATURE_H
 
 #include <asm/required-features.h>
 
@@ -224,4 +224,4 @@
 
 #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
 
-#endif /* _ASM_X86_CPUFEATURE_H */
+#endif /* ASM_X86__CPUFEATURE_H */
diff --git a/include/asm-x86/current.h b/include/asm-x86/current.h
index 7515c19..a863ead 100644
--- a/include/asm-x86/current.h
+++ b/include/asm-x86/current.h
@@ -1,5 +1,5 @@
-#ifndef _X86_CURRENT_H
-#define _X86_CURRENT_H
+#ifndef ASM_X86__CURRENT_H
+#define ASM_X86__CURRENT_H
 
 #ifdef CONFIG_X86_32
 #include <linux/compiler.h>
@@ -36,4 +36,4 @@
 
 #define current get_current()
 
-#endif /* X86_CURRENT_H */
+#endif /* ASM_X86__CURRENT_H */
diff --git a/include/asm-x86/debugreg.h b/include/asm-x86/debugreg.h
index c6344d5..ecb6907 100644
--- a/include/asm-x86/debugreg.h
+++ b/include/asm-x86/debugreg.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_DEBUGREG_H
-#define _ASM_X86_DEBUGREG_H
+#ifndef ASM_X86__DEBUGREG_H
+#define ASM_X86__DEBUGREG_H
 
 
 /* Indicate the register numbers for a number of the specific
@@ -67,4 +67,4 @@
 #define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
 #define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
 
-#endif
+#endif /* ASM_X86__DEBUGREG_H */
diff --git a/include/asm-x86/delay.h b/include/asm-x86/delay.h
index 409a649..8a0da95 100644
--- a/include/asm-x86/delay.h
+++ b/include/asm-x86/delay.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_DELAY_H
-#define _ASM_X86_DELAY_H
+#ifndef ASM_X86__DELAY_H
+#define ASM_X86__DELAY_H
 
 /*
  * Copyright (C) 1993 Linus Torvalds
@@ -28,4 +28,4 @@
 
 void use_tsc_delay(void);
 
-#endif /* _ASM_X86_DELAY_H */
+#endif /* ASM_X86__DELAY_H */
diff --git a/include/asm-x86/desc.h b/include/asm-x86/desc.h
index a44c4dc..b73fea5 100644
--- a/include/asm-x86/desc.h
+++ b/include/asm-x86/desc.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_DESC_H_
-#define _ASM_DESC_H_
+#ifndef ASM_X86__DESC_H
+#define ASM_X86__DESC_H
 
 #ifndef __ASSEMBLY__
 #include <asm/desc_defs.h>
@@ -397,4 +397,4 @@
 
 #endif /* __ASSEMBLY__ */
 
-#endif
+#endif /* ASM_X86__DESC_H */
diff --git a/include/asm-x86/desc_defs.h b/include/asm-x86/desc_defs.h
index f7bacf3..b881db6 100644
--- a/include/asm-x86/desc_defs.h
+++ b/include/asm-x86/desc_defs.h
@@ -1,6 +1,6 @@
 /* Written 2000 by Andi Kleen */
-#ifndef __ARCH_DESC_DEFS_H
-#define __ARCH_DESC_DEFS_H
+#ifndef ASM_X86__DESC_DEFS_H
+#define ASM_X86__DESC_DEFS_H
 
 /*
  * Segment descriptor structure definitions, usable from both x86_64 and i386
@@ -92,4 +92,4 @@
 
 #endif /* !__ASSEMBLY__ */
 
-#endif
+#endif /* ASM_X86__DESC_DEFS_H */
diff --git a/include/asm-x86/device.h b/include/asm-x86/device.h
index 3c034f4..1bece04 100644
--- a/include/asm-x86/device.h
+++ b/include/asm-x86/device.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_DEVICE_H
-#define _ASM_X86_DEVICE_H
+#ifndef ASM_X86__DEVICE_H
+#define ASM_X86__DEVICE_H
 
 struct dev_archdata {
 #ifdef CONFIG_ACPI
@@ -13,4 +13,4 @@
 #endif
 };
 
-#endif /* _ASM_X86_DEVICE_H */
+#endif /* ASM_X86__DEVICE_H */
diff --git a/include/asm-x86/div64.h b/include/asm-x86/div64.h
index 9a2d644..f9530f2 100644
--- a/include/asm-x86/div64.h
+++ b/include/asm-x86/div64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_DIV64_H
-#define _ASM_X86_DIV64_H
+#ifndef ASM_X86__DIV64_H
+#define ASM_X86__DIV64_H
 
 #ifdef CONFIG_X86_32
 
@@ -57,4 +57,4 @@
 # include <asm-generic/div64.h>
 #endif /* CONFIG_X86_32 */
 
-#endif /* _ASM_X86_DIV64_H */
+#endif /* ASM_X86__DIV64_H */
diff --git a/include/asm-x86/dma-mapping.h b/include/asm-x86/dma-mapping.h
index ad9cd6d..5d200e7 100644
--- a/include/asm-x86/dma-mapping.h
+++ b/include/asm-x86/dma-mapping.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_DMA_MAPPING_H_
-#define _ASM_DMA_MAPPING_H_
+#ifndef ASM_X86__DMA_MAPPING_H
+#define ASM_X86__DMA_MAPPING_H
 
 /*
  * IOMMU interface. See Documentation/DMA-mapping.txt and DMA-API.txt for
@@ -250,4 +250,4 @@
 #define dma_is_consistent(d, h)	(1)
 
 #include <asm-generic/dma-coherent.h>
-#endif
+#endif /* ASM_X86__DMA_MAPPING_H */
diff --git a/include/asm-x86/dma.h b/include/asm-x86/dma.h
index ca1098a..c9f7a4e 100644
--- a/include/asm-x86/dma.h
+++ b/include/asm-x86/dma.h
@@ -5,8 +5,8 @@
  * and John Boyd, Nov. 1992.
  */
 
-#ifndef _ASM_X86_DMA_H
-#define _ASM_X86_DMA_H
+#ifndef ASM_X86__DMA_H
+#define ASM_X86__DMA_H
 
 #include <linux/spinlock.h>	/* And spinlocks */
 #include <asm/io.h>		/* need byte IO */
@@ -315,4 +315,4 @@
 #define isa_dma_bridge_buggy	(0)
 #endif
 
-#endif /* _ASM_X86_DMA_H */
+#endif /* ASM_X86__DMA_H */
diff --git a/include/asm-x86/dmi.h b/include/asm-x86/dmi.h
index 58a8657..1cff6fe 100644
--- a/include/asm-x86/dmi.h
+++ b/include/asm-x86/dmi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_DMI_H
-#define _ASM_X86_DMI_H
+#ifndef ASM_X86__DMI_H
+#define ASM_X86__DMI_H
 
 #include <asm/io.h>
 
@@ -23,4 +23,4 @@
 #define dmi_ioremap early_ioremap
 #define dmi_iounmap early_iounmap
 
-#endif
+#endif /* ASM_X86__DMI_H */
diff --git a/include/asm-x86/ds.h b/include/asm-x86/ds.h
index 7881368..c3c953a 100644
--- a/include/asm-x86/ds.h
+++ b/include/asm-x86/ds.h
@@ -2,71 +2,237 @@
  * Debug Store (DS) support
  *
  * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for last branch recording (LBR) and
+ * feature that is used for branch trace store (BTS) and
  * precise-event based sampling (PEBS).
  *
- * Different architectures use a different DS layout/pointer size.
- * The below functions therefore work on a void*.
+ * It manages:
+ * - per-thread and per-cpu allocation of BTS and PEBS
+ * - buffer memory allocation (optional)
+ * - buffer overflow handling
+ * - buffer access
+ *
+ * It assumes:
+ * - get_task_struct on all parameter tasks
+ * - current is allowed to trace parameter tasks
  *
  *
- * Since there is no user for PEBS, yet, only LBR (or branch
- * trace store, BTS) is supported.
- *
- *
- * Copyright (C) 2007 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, Dec 2007
+ * Copyright (C) 2007-2008 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
  */
 
-#ifndef _ASM_X86_DS_H
-#define _ASM_X86_DS_H
+#ifndef ASM_X86__DS_H
+#define ASM_X86__DS_H
+
+#ifdef CONFIG_X86_DS
 
 #include <linux/types.h>
 #include <linux/init.h>
 
-struct cpuinfo_x86;
 
+struct task_struct;
 
-/* a branch trace record entry
+/*
+ * Request BTS or PEBS
  *
- * In order to unify the interface between various processor versions,
- * we use the below data structure for all processors.
+ * Due to alignement constraints, the actual buffer may be slightly
+ * smaller than the requested or provided buffer.
+ *
+ * Returns 0 on success; -Eerrno otherwise
+ *
+ * task: the task to request recording for;
+ *       NULL for per-cpu recording on the current cpu
+ * base: the base pointer for the (non-pageable) buffer;
+ *       NULL if buffer allocation requested
+ * size: the size of the requested or provided buffer
+ * ovfl: pointer to a function to be called on buffer overflow;
+ *       NULL if cyclic buffer requested
  */
-enum bts_qualifier {
-	BTS_INVALID = 0,
-	BTS_BRANCH,
-	BTS_TASK_ARRIVES,
-	BTS_TASK_DEPARTS
+typedef void (*ds_ovfl_callback_t)(struct task_struct *);
+extern int ds_request_bts(struct task_struct *task, void *base, size_t size,
+			  ds_ovfl_callback_t ovfl);
+extern int ds_request_pebs(struct task_struct *task, void *base, size_t size,
+			   ds_ovfl_callback_t ovfl);
+
+/*
+ * Release BTS or PEBS resources
+ *
+ * Frees buffers allocated on ds_request.
+ *
+ * Returns 0 on success; -Eerrno otherwise
+ *
+ * task: the task to release resources for;
+ *       NULL to release resources for the current cpu
+ */
+extern int ds_release_bts(struct task_struct *task);
+extern int ds_release_pebs(struct task_struct *task);
+
+/*
+ * Return the (array) index of the write pointer.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * Returns -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * pos (out): if not NULL, will hold the result
+ */
+extern int ds_get_bts_index(struct task_struct *task, size_t *pos);
+extern int ds_get_pebs_index(struct task_struct *task, size_t *pos);
+
+/*
+ * Return the (array) index one record beyond the end of the array.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * Returns -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * pos (out): if not NULL, will hold the result
+ */
+extern int ds_get_bts_end(struct task_struct *task, size_t *pos);
+extern int ds_get_pebs_end(struct task_struct *task, size_t *pos);
+
+/*
+ * Provide a pointer to the BTS/PEBS record at parameter index.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * The pointer points directly into the buffer. The user is
+ * responsible for copying the record.
+ *
+ * Returns the size of a single record on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * index: the index of the requested record
+ * record (out): pointer to the requested record
+ */
+extern int ds_access_bts(struct task_struct *task,
+			 size_t index, const void **record);
+extern int ds_access_pebs(struct task_struct *task,
+			  size_t index, const void **record);
+
+/*
+ * Write one or more BTS/PEBS records at the write pointer index and
+ * advance the write pointer.
+ *
+ * If size is not a multiple of the record size, trailing bytes are
+ * zeroed out.
+ *
+ * May result in one or more overflow notifications.
+ *
+ * If called during overflow handling, that is, with index >=
+ * interrupt threshold, the write will wrap around.
+ *
+ * An overflow notification is given if and when the interrupt
+ * threshold is reached during or after the write.
+ *
+ * Returns the number of bytes written or -Eerrno.
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * buffer: the buffer to write
+ * size: the size of the buffer
+ */
+extern int ds_write_bts(struct task_struct *task,
+			const void *buffer, size_t size);
+extern int ds_write_pebs(struct task_struct *task,
+			 const void *buffer, size_t size);
+
+/*
+ * Same as ds_write_bts/pebs, but omit ownership checks.
+ *
+ * This is needed to have some other task than the owner of the
+ * BTS/PEBS buffer or the parameter task itself write into the
+ * respective buffer.
+ */
+extern int ds_unchecked_write_bts(struct task_struct *task,
+				  const void *buffer, size_t size);
+extern int ds_unchecked_write_pebs(struct task_struct *task,
+				   const void *buffer, size_t size);
+
+/*
+ * Reset the write pointer of the BTS/PEBS buffer.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ */
+extern int ds_reset_bts(struct task_struct *task);
+extern int ds_reset_pebs(struct task_struct *task);
+
+/*
+ * Clear the BTS/PEBS buffer and reset the write pointer.
+ * The entire buffer will be zeroed out.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ */
+extern int ds_clear_bts(struct task_struct *task);
+extern int ds_clear_pebs(struct task_struct *task);
+
+/*
+ * Provide the PEBS counter reset value.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * value (out): the counter reset value
+ */
+extern int ds_get_pebs_reset(struct task_struct *task, u64 *value);
+
+/*
+ * Set the PEBS counter reset value.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * value: the new counter reset value
+ */
+extern int ds_set_pebs_reset(struct task_struct *task, u64 value);
+
+/*
+ * Initialization
+ */
+struct cpuinfo_x86;
+extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
+
+
+
+/*
+ * The DS context - part of struct thread_struct.
+ */
+struct ds_context {
+	/* pointer to the DS configuration; goes into MSR_IA32_DS_AREA */
+	unsigned char *ds;
+	/* the owner of the BTS and PEBS configuration, respectively */
+	struct task_struct *owner[2];
+	/* buffer overflow notification function for BTS and PEBS */
+	ds_ovfl_callback_t callback[2];
+	/* the original buffer address */
+	void *buffer[2];
+	/* the number of allocated pages for on-request allocated buffers */
+	unsigned int pages[2];
+	/* use count */
+	unsigned long count;
+	/* a pointer to the context location inside the thread_struct
+	 * or the per_cpu context array */
+	struct ds_context **this;
+	/* a pointer to the task owning this context, or NULL, if the
+	 * context is owned by a cpu */
+	struct task_struct *task;
 };
 
-struct bts_struct {
-	u64 qualifier;
-	union {
-		/* BTS_BRANCH */
-		struct {
-			u64 from_ip;
-			u64 to_ip;
-		} lbr;
-		/* BTS_TASK_ARRIVES or
-		   BTS_TASK_DEPARTS */
-		u64 jiffies;
-	} variant;
-};
+/* called by exit_thread() to free leftover contexts */
+extern void ds_free(struct ds_context *context);
 
-/* Overflow handling mechanisms */
-#define DS_O_SIGNAL	1 /* send overflow signal */
-#define DS_O_WRAP	2 /* wrap around */
+#else /* CONFIG_X86_DS */
 
-extern int ds_allocate(void **, size_t);
-extern int ds_free(void **);
-extern int ds_get_bts_size(void *);
-extern int ds_get_bts_end(void *);
-extern int ds_get_bts_index(void *);
-extern int ds_set_overflow(void *, int);
-extern int ds_get_overflow(void *);
-extern int ds_clear(void *);
-extern int ds_read_bts(void *, int, struct bts_struct *);
-extern int ds_write_bts(void *, const struct bts_struct *);
-extern unsigned long ds_debugctl_mask(void);
-extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *c);
+#define ds_init_intel(config) do {} while (0)
 
-#endif /* _ASM_X86_DS_H */
+#endif /* CONFIG_X86_DS */
+#endif /* ASM_X86__DS_H */
diff --git a/include/asm-x86/dwarf2.h b/include/asm-x86/dwarf2.h
index 738bb9f..21d1bc3 100644
--- a/include/asm-x86/dwarf2.h
+++ b/include/asm-x86/dwarf2.h
@@ -1,5 +1,5 @@
-#ifndef _DWARF2_H
-#define _DWARF2_H
+#ifndef ASM_X86__DWARF2_H
+#define ASM_X86__DWARF2_H
 
 #ifndef __ASSEMBLY__
 #warning "asm/dwarf2.h should be only included in pure assembly files"
@@ -58,4 +58,4 @@
 
 #endif
 
-#endif
+#endif /* ASM_X86__DWARF2_H */
diff --git a/include/asm-x86/e820.h b/include/asm-x86/e820.h
index 16a31e2..f52daf1 100644
--- a/include/asm-x86/e820.h
+++ b/include/asm-x86/e820.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_E820_H
-#define __ASM_E820_H
+#ifndef ASM_X86__E820_H
+#define ASM_X86__E820_H
 #define E820MAP	0x2d0		/* our map */
 #define E820MAX	128		/* number of entries in E820MAP */
 
@@ -64,6 +64,7 @@
 extern struct e820map e820;
 extern struct e820map e820_saved;
 
+extern unsigned long pci_mem_start;
 extern int e820_any_mapped(u64 start, u64 end, unsigned type);
 extern int e820_all_mapped(u64 start, u64 end, unsigned type);
 extern void e820_add_region(u64 start, u64 size, int type);
@@ -140,4 +141,4 @@
 #define HIGH_MEMORY	(1024*1024)
 #endif /* __KERNEL__ */
 
-#endif  /* __ASM_E820_H */
+#endif /* ASM_X86__E820_H */
diff --git a/include/asm-x86/edac.h b/include/asm-x86/edac.h
index a8088f6..9493c5b 100644
--- a/include/asm-x86/edac.h
+++ b/include/asm-x86/edac.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_EDAC_H
-#define _ASM_X86_EDAC_H
+#ifndef ASM_X86__EDAC_H
+#define ASM_X86__EDAC_H
 
 /* ECC atomic, DMA, SMP and interrupt safe scrub function */
 
@@ -15,4 +15,4 @@
 		asm volatile("lock; addl $0, %0"::"m" (*virt_addr));
 }
 
-#endif
+#endif /* ASM_X86__EDAC_H */
diff --git a/include/asm-x86/efi.h b/include/asm-x86/efi.h
index d4f2b0a..ed2de22 100644
--- a/include/asm-x86/efi.h
+++ b/include/asm-x86/efi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_EFI_H
-#define _ASM_X86_EFI_H
+#ifndef ASM_X86__EFI_H
+#define ASM_X86__EFI_H
 
 #ifdef CONFIG_X86_32
 
@@ -94,4 +94,4 @@
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 
-#endif
+#endif /* ASM_X86__EFI_H */
diff --git a/include/asm-x86/elf.h b/include/asm-x86/elf.h
index 7be4733..5c4745b 100644
--- a/include/asm-x86/elf.h
+++ b/include/asm-x86/elf.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_ELF_H
-#define _ASM_X86_ELF_H
+#ifndef ASM_X86__ELF_H
+#define ASM_X86__ELF_H
 
 /*
  * ELF register definitions..
@@ -148,8 +148,9 @@
 
 static inline void start_ia32_thread(struct pt_regs *regs, u32 ip, u32 sp)
 {
-	asm volatile("movl %0,%%fs" :: "r" (0));
-	asm volatile("movl %0,%%es; movl %0,%%ds" : : "r" (__USER32_DS));
+	loadsegment(fs, 0);
+	loadsegment(ds, __USER32_DS);
+	loadsegment(es, __USER32_DS);
 	load_gs_index(0);
 	regs->ip = ip;
 	regs->sp = sp;
@@ -332,4 +333,4 @@
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
-#endif
+#endif /* ASM_X86__ELF_H */
diff --git a/include/asm-x86/emergency-restart.h b/include/asm-x86/emergency-restart.h
index 8e6aef1..190d0d8 100644
--- a/include/asm-x86/emergency-restart.h
+++ b/include/asm-x86/emergency-restart.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
+#ifndef ASM_X86__EMERGENCY_RESTART_H
+#define ASM_X86__EMERGENCY_RESTART_H
 
 enum reboot_type {
 	BOOT_TRIPLE = 't',
@@ -15,4 +15,4 @@
 
 extern void machine_emergency_restart(void);
 
-#endif /* _ASM_EMERGENCY_RESTART_H */
+#endif /* ASM_X86__EMERGENCY_RESTART_H */
diff --git a/include/asm-x86/fb.h b/include/asm-x86/fb.h
index 5301846..aca38dbd 100644
--- a/include/asm-x86/fb.h
+++ b/include/asm-x86/fb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_FB_H
-#define _ASM_X86_FB_H
+#ifndef ASM_X86__FB_H
+#define ASM_X86__FB_H
 
 #include <linux/fb.h>
 #include <linux/fs.h>
@@ -18,4 +18,4 @@
 static inline int fb_is_primary_device(struct fb_info *info) { return 0; }
 #endif
 
-#endif /* _ASM_X86_FB_H */
+#endif /* ASM_X86__FB_H */
diff --git a/include/asm-x86/fixmap.h b/include/asm-x86/fixmap.h
index 44d4f82..78e33a1 100644
--- a/include/asm-x86/fixmap.h
+++ b/include/asm-x86/fixmap.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_FIXMAP_H
-#define _ASM_FIXMAP_H
+#ifndef ASM_X86__FIXMAP_H
+#define ASM_X86__FIXMAP_H
 
 #ifdef CONFIG_X86_32
 # include "fixmap_32.h"
@@ -65,4 +65,4 @@
 	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
 	return __virt_to_fix(vaddr);
 }
-#endif
+#endif /* ASM_X86__FIXMAP_H */
diff --git a/include/asm-x86/fixmap_32.h b/include/asm-x86/fixmap_32.h
index f1ac2b2..784e3e7 100644
--- a/include/asm-x86/fixmap_32.h
+++ b/include/asm-x86/fixmap_32.h
@@ -10,8 +10,8 @@
  * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
  */
 
-#ifndef _ASM_FIXMAP_32_H
-#define _ASM_FIXMAP_32_H
+#ifndef ASM_X86__FIXMAP_32_H
+#define ASM_X86__FIXMAP_32_H
 
 
 /* used by vmalloc.c, vsyscall.lds.S.
@@ -120,4 +120,4 @@
 #define FIXADDR_BOOT_START	(FIXADDR_TOP - __FIXADDR_BOOT_SIZE)
 
 #endif /* !__ASSEMBLY__ */
-#endif
+#endif /* ASM_X86__FIXMAP_32_H */
diff --git a/include/asm-x86/fixmap_64.h b/include/asm-x86/fixmap_64.h
index 00f3d74..dafb24b 100644
--- a/include/asm-x86/fixmap_64.h
+++ b/include/asm-x86/fixmap_64.h
@@ -8,8 +8,8 @@
  * Copyright (C) 1998 Ingo Molnar
  */
 
-#ifndef _ASM_FIXMAP_64_H
-#define _ASM_FIXMAP_64_H
+#ifndef ASM_X86__FIXMAP_64_H
+#define ASM_X86__FIXMAP_64_H
 
 #include <linux/kernel.h>
 #include <asm/acpi.h>
@@ -80,4 +80,4 @@
 #define FIXADDR_USER_START	((unsigned long)VSYSCALL32_VSYSCALL)
 #define FIXADDR_USER_END	(FIXADDR_USER_START + PAGE_SIZE)
 
-#endif
+#endif /* ASM_X86__FIXMAP_64_H */
diff --git a/include/asm-x86/floppy.h b/include/asm-x86/floppy.h
index dbe82a5..7d83a3a 100644
--- a/include/asm-x86/floppy.h
+++ b/include/asm-x86/floppy.h
@@ -7,8 +7,8 @@
  *
  * Copyright (C) 1995
  */
-#ifndef _ASM_X86_FLOPPY_H
-#define _ASM_X86_FLOPPY_H
+#ifndef ASM_X86__FLOPPY_H
+#define ASM_X86__FLOPPY_H
 
 #include <linux/vmalloc.h>
 
@@ -278,4 +278,4 @@
 
 #define EXTRA_FLOPPY_PARAMS
 
-#endif /* _ASM_X86_FLOPPY_H */
+#endif /* ASM_X86__FLOPPY_H */
diff --git a/include/asm-x86/ftrace.h b/include/asm-x86/ftrace.h
index 5c68b32..be0e004 100644
--- a/include/asm-x86/ftrace.h
+++ b/include/asm-x86/ftrace.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_FTRACE
-#define _ASM_X86_FTRACE
+#ifndef ASM_X86__FTRACE_H
+#define ASM_X86__FTRACE_H
 
 #ifdef CONFIG_FTRACE
 #define MCOUNT_ADDR		((long)(mcount))
@@ -11,4 +11,4 @@
 
 #endif /* CONFIG_FTRACE */
 
-#endif /* _ASM_X86_FTRACE */
+#endif /* ASM_X86__FTRACE_H */
diff --git a/include/asm-x86/futex.h b/include/asm-x86/futex.h
index e7a76b3..06b924e 100644
--- a/include/asm-x86/futex.h
+++ b/include/asm-x86/futex.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_FUTEX_H
-#define _ASM_X86_FUTEX_H
+#ifndef ASM_X86__FUTEX_H
+#define ASM_X86__FUTEX_H
 
 #ifdef __KERNEL__
 
@@ -25,7 +25,7 @@
 	asm volatile("1:\tmovl	%2, %0\n"			\
 		     "\tmovl\t%0, %3\n"				\
 		     "\t" insn "\n"				\
-		     "2:\tlock; cmpxchgl %3, %2\n"		\
+		     "2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"	\
 		     "\tjnz\t1b\n"				\
 		     "3:\t.section .fixup,\"ax\"\n"		\
 		     "4:\tmov\t%5, %1\n"			\
@@ -64,7 +64,7 @@
 		__futex_atomic_op1("xchgl %0, %2", ret, oldval, uaddr, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op1("lock; xaddl %0, %2", ret, oldval,
+		__futex_atomic_op1(LOCK_PREFIX "xaddl %0, %2", ret, oldval,
 				   uaddr, oparg);
 		break;
 	case FUTEX_OP_OR:
@@ -122,7 +122,7 @@
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	asm volatile("1:\tlock; cmpxchgl %3, %1\n"
+	asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n"
 		     "2:\t.section .fixup, \"ax\"\n"
 		     "3:\tmov     %2, %0\n"
 		     "\tjmp     2b\n"
@@ -137,4 +137,4 @@
 }
 
 #endif
-#endif
+#endif /* ASM_X86__FUTEX_H */
diff --git a/include/asm-x86/gart.h b/include/asm-x86/gart.h
index 3f62a83..baa54fa 100644
--- a/include/asm-x86/gart.h
+++ b/include/asm-x86/gart.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X8664_GART_H
-#define _ASM_X8664_GART_H 1
+#ifndef ASM_X86__GART_H
+#define ASM_X86__GART_H
 
 #include <asm/e820.h>
 
@@ -52,15 +52,15 @@
 		return 0;
 
 	if (aper_base + aper_size > 0x100000000ULL) {
-		printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n");
+		printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n");
 		return 0;
 	}
 	if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
-		printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n");
+		printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n");
 		return 0;
 	}
 	if (aper_size < min_size) {
-		printk(KERN_ERR "Aperture too small (%d MB) than (%d MB)\n",
+		printk(KERN_INFO "Aperture too small (%d MB) than (%d MB)\n",
 				 aper_size>>20, min_size>>20);
 		return 0;
 	}
@@ -68,4 +68,4 @@
 	return 1;
 }
 
-#endif
+#endif /* ASM_X86__GART_H */
diff --git a/include/asm-x86/genapic_32.h b/include/asm-x86/genapic_32.h
index 754d635..34280f0 100644
--- a/include/asm-x86/genapic_32.h
+++ b/include/asm-x86/genapic_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_GENAPIC_H
-#define _ASM_GENAPIC_H 1
+#ifndef ASM_X86__GENAPIC_32_H
+#define ASM_X86__GENAPIC_32_H
 
 #include <asm/mpspec.h>
 
@@ -121,4 +121,4 @@
 #define uv_system_init()		do {} while (0)
 
 
-#endif
+#endif /* ASM_X86__GENAPIC_32_H */
diff --git a/include/asm-x86/genapic_64.h b/include/asm-x86/genapic_64.h
index a47d631..25097a8 100644
--- a/include/asm-x86/genapic_64.h
+++ b/include/asm-x86/genapic_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_GENAPIC_H
-#define _ASM_GENAPIC_H 1
+#ifndef ASM_X86__GENAPIC_64_H
+#define ASM_X86__GENAPIC_64_H
 
 /*
  * Copyright 2004 James Cleverdon, IBM.
@@ -47,4 +47,4 @@
 
 extern void setup_apic_routing(void);
 
-#endif
+#endif /* ASM_X86__GENAPIC_64_H */
diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h
index 2c1cda0..3f3444b 100644
--- a/include/asm-x86/geode.h
+++ b/include/asm-x86/geode.h
@@ -7,8 +7,8 @@
  * as published by the Free Software Foundation.
  */
 
-#ifndef _ASM_GEODE_H_
-#define _ASM_GEODE_H_
+#ifndef ASM_X86__GEODE_H
+#define ASM_X86__GEODE_H
 
 #include <asm/processor.h>
 #include <linux/io.h>
@@ -250,4 +250,4 @@
 static inline int mfgpt_timer_setup(void) { return 0; }
 #endif
 
-#endif
+#endif /* ASM_X86__GEODE_H */
diff --git a/include/asm-x86/gpio.h b/include/asm-x86/gpio.h
index c4c91b3..497fb98 100644
--- a/include/asm-x86/gpio.h
+++ b/include/asm-x86/gpio.h
@@ -53,4 +53,4 @@
 
 #endif /* CONFIG_GPIOLIB */
 
-#endif /* _ASM_I386_GPIO_H */
+#endif /* ASM_X86__GPIO_H */
diff --git a/include/asm-x86/hardirq_32.h b/include/asm-x86/hardirq_32.h
index 4f85f0f..700fe23 100644
--- a/include/asm-x86/hardirq_32.h
+++ b/include/asm-x86/hardirq_32.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_HARDIRQ_H
-#define __ASM_HARDIRQ_H
+#ifndef ASM_X86__HARDIRQ_32_H
+#define ASM_X86__HARDIRQ_32_H
 
 #include <linux/threads.h>
 #include <linux/irq.h>
@@ -25,4 +25,4 @@
 void ack_bad_irq(unsigned int irq);
 #include <linux/irq_cpustat.h>
 
-#endif /* __ASM_HARDIRQ_H */
+#endif /* ASM_X86__HARDIRQ_32_H */
diff --git a/include/asm-x86/hardirq_64.h b/include/asm-x86/hardirq_64.h
index 95d5e09..f8bd291 100644
--- a/include/asm-x86/hardirq_64.h
+++ b/include/asm-x86/hardirq_64.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_HARDIRQ_H
-#define __ASM_HARDIRQ_H
+#ifndef ASM_X86__HARDIRQ_64_H
+#define ASM_X86__HARDIRQ_64_H
 
 #include <linux/threads.h>
 #include <linux/irq.h>
@@ -20,4 +20,4 @@
 
 extern void ack_bad_irq(unsigned int irq);
 
-#endif /* __ASM_HARDIRQ_H */
+#endif /* ASM_X86__HARDIRQ_64_H */
diff --git a/include/asm-x86/highmem.h b/include/asm-x86/highmem.h
index 4514b16..bc3f6a2 100644
--- a/include/asm-x86/highmem.h
+++ b/include/asm-x86/highmem.h
@@ -15,8 +15,8 @@
  * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
  */
 
-#ifndef _ASM_HIGHMEM_H
-#define _ASM_HIGHMEM_H
+#ifndef ASM_X86__HIGHMEM_H
+#define ASM_X86__HIGHMEM_H
 
 #ifdef __KERNEL__
 
@@ -79,4 +79,4 @@
 
 #endif /* __KERNEL__ */
 
-#endif /* _ASM_HIGHMEM_H */
+#endif /* ASM_X86__HIGHMEM_H */
diff --git a/include/asm-x86/hpet.h b/include/asm-x86/hpet.h
index 82f1ac6..cbbbb6d 100644
--- a/include/asm-x86/hpet.h
+++ b/include/asm-x86/hpet.h
@@ -1,5 +1,5 @@
-#ifndef ASM_X86_HPET_H
-#define ASM_X86_HPET_H
+#ifndef ASM_X86__HPET_H
+#define ASM_X86__HPET_H
 
 #ifdef CONFIG_HPET_TIMER
 
@@ -90,4 +90,4 @@
 #define hpet_readl(a) 0
 
 #endif
-#endif /* ASM_X86_HPET_H */
+#endif /* ASM_X86__HPET_H */
diff --git a/include/asm-x86/hugetlb.h b/include/asm-x86/hugetlb.h
index 439a9ac..0b7ec5d 100644
--- a/include/asm-x86/hugetlb.h
+++ b/include/asm-x86/hugetlb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_HUGETLB_H
-#define _ASM_X86_HUGETLB_H
+#ifndef ASM_X86__HUGETLB_H
+#define ASM_X86__HUGETLB_H
 
 #include <asm/page.h>
 
@@ -90,4 +90,4 @@
 {
 }
 
-#endif /* _ASM_X86_HUGETLB_H */
+#endif /* ASM_X86__HUGETLB_H */
diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h
index edd0b95..65997b1 100644
--- a/include/asm-x86/hw_irq.h
+++ b/include/asm-x86/hw_irq.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_HW_IRQ_H
-#define _ASM_HW_IRQ_H
+#ifndef ASM_X86__HW_IRQ_H
+#define ASM_X86__HW_IRQ_H
 
 /*
  * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
@@ -93,6 +93,26 @@
 extern asmlinkage void qic_enable_irq_interrupt(void);
 extern asmlinkage void qic_call_function_interrupt(void);
 
+/* SMP */
+extern void smp_apic_timer_interrupt(struct pt_regs *);
+#ifdef CONFIG_X86_32
+extern void smp_spurious_interrupt(struct pt_regs *);
+extern void smp_error_interrupt(struct pt_regs *);
+#else
+extern asmlinkage void smp_spurious_interrupt(void);
+extern asmlinkage void smp_error_interrupt(void);
+#endif
+#ifdef CONFIG_X86_SMP
+extern void smp_reschedule_interrupt(struct pt_regs *);
+extern void smp_call_function_interrupt(struct pt_regs *);
+extern void smp_call_function_single_interrupt(struct pt_regs *);
+#ifdef CONFIG_X86_32
+extern void smp_invalidate_interrupt(struct pt_regs *);
+#else
+extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
+#endif
+#endif
+
 #ifdef CONFIG_X86_32
 extern void (*const interrupt[NR_IRQS])(void);
 #else
@@ -112,4 +132,4 @@
 
 #endif /* !ASSEMBLY_ */
 
-#endif
+#endif /* ASM_X86__HW_IRQ_H */
diff --git a/include/asm-x86/hypertransport.h b/include/asm-x86/hypertransport.h
index d2bbd23..cc011a3 100644
--- a/include/asm-x86/hypertransport.h
+++ b/include/asm-x86/hypertransport.h
@@ -1,5 +1,5 @@
-#ifndef ASM_HYPERTRANSPORT_H
-#define ASM_HYPERTRANSPORT_H
+#ifndef ASM_X86__HYPERTRANSPORT_H
+#define ASM_X86__HYPERTRANSPORT_H
 
 /*
  * Constants for x86 Hypertransport Interrupts.
@@ -42,4 +42,4 @@
 #define HT_IRQ_HIGH_DEST_ID(v)						\
 	((((v) >> 8) << HT_IRQ_HIGH_DEST_ID_SHIFT) & HT_IRQ_HIGH_DEST_ID_MASK)
 
-#endif /* ASM_HYPERTRANSPORT_H */
+#endif /* ASM_X86__HYPERTRANSPORT_H */
diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
index 56d00e3..1ecdc3e 100644
--- a/include/asm-x86/i387.h
+++ b/include/asm-x86/i387.h
@@ -7,8 +7,8 @@
  * x86-64 work by Andi Kleen 2002
  */
 
-#ifndef _ASM_X86_I387_H
-#define _ASM_X86_I387_H
+#ifndef ASM_X86__I387_H
+#define ASM_X86__I387_H
 
 #include <linux/sched.h>
 #include <linux/kernel_stat.h>
@@ -25,6 +25,7 @@
 extern int init_fpu(struct task_struct *child);
 extern asmlinkage void math_state_restore(void);
 extern void init_thread_xstate(void);
+extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
 extern user_regset_active_fn fpregs_active, xfpregs_active;
 extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get;
@@ -336,4 +337,4 @@
 	}
 }
 
-#endif	/* _ASM_X86_I387_H */
+#endif /* ASM_X86__I387_H */
diff --git a/include/asm-x86/i8253.h b/include/asm-x86/i8253.h
index b51c048..15a5b53 100644
--- a/include/asm-x86/i8253.h
+++ b/include/asm-x86/i8253.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_I8253_H__
-#define __ASM_I8253_H__
+#ifndef ASM_X86__I8253_H
+#define ASM_X86__I8253_H
 
 /* i8253A PIT registers */
 #define PIT_MODE		0x43
@@ -15,4 +15,4 @@
 #define inb_pit		inb_p
 #define outb_pit	outb_p
 
-#endif	/* __ASM_I8253_H__ */
+#endif /* ASM_X86__I8253_H */
diff --git a/include/asm-x86/i8259.h b/include/asm-x86/i8259.h
index 2f98df9..c586559 100644
--- a/include/asm-x86/i8259.h
+++ b/include/asm-x86/i8259.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_I8259_H__
-#define __ASM_I8259_H__
+#ifndef ASM_X86__I8259_H
+#define ASM_X86__I8259_H
 
 #include <linux/delay.h>
 
@@ -57,4 +57,4 @@
 
 extern struct irq_chip i8259A_chip;
 
-#endif	/* __ASM_I8259_H__ */
+#endif /* ASM_X86__I8259_H */
diff --git a/include/asm-x86/ia32.h b/include/asm-x86/ia32.h
index 55d3abe..f932f7a 100644
--- a/include/asm-x86/ia32.h
+++ b/include/asm-x86/ia32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_IA32_H
-#define _ASM_X86_64_IA32_H
+#ifndef ASM_X86__IA32_H
+#define ASM_X86__IA32_H
 
 
 #ifdef CONFIG_IA32_EMULATION
@@ -167,4 +167,4 @@
 
 #endif /* !CONFIG_IA32_SUPPORT */
 
-#endif
+#endif /* ASM_X86__IA32_H */
diff --git a/include/asm-x86/ia32_unistd.h b/include/asm-x86/ia32_unistd.h
index 61cea9e..dbd887d 100644
--- a/include/asm-x86/ia32_unistd.h
+++ b/include/asm-x86/ia32_unistd.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_IA32_UNISTD_H_
-#define _ASM_X86_64_IA32_UNISTD_H_
+#ifndef ASM_X86__IA32_UNISTD_H
+#define ASM_X86__IA32_UNISTD_H
 
 /*
  * This file contains the system call numbers of the ia32 port,
@@ -15,4 +15,4 @@
 #define __NR_ia32_sigreturn	119
 #define __NR_ia32_rt_sigreturn	173
 
-#endif /* _ASM_X86_64_IA32_UNISTD_H_ */
+#endif /* ASM_X86__IA32_UNISTD_H */
diff --git a/include/asm-x86/idle.h b/include/asm-x86/idle.h
index cbb6491..baa3f783 100644
--- a/include/asm-x86/idle.h
+++ b/include/asm-x86/idle.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_IDLE_H
-#define _ASM_X86_64_IDLE_H 1
+#ifndef ASM_X86__IDLE_H
+#define ASM_X86__IDLE_H
 
 #define IDLE_START 1
 #define IDLE_END 2
@@ -12,4 +12,4 @@
 
 void c1e_remove_cpu(int cpu);
 
-#endif
+#endif /* ASM_X86__IDLE_H */
diff --git a/include/asm-x86/intel_arch_perfmon.h b/include/asm-x86/intel_arch_perfmon.h
index fa0fd06..07c03c6 100644
--- a/include/asm-x86/intel_arch_perfmon.h
+++ b/include/asm-x86/intel_arch_perfmon.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_INTEL_ARCH_PERFMON_H
-#define _ASM_X86_INTEL_ARCH_PERFMON_H
+#ifndef ASM_X86__INTEL_ARCH_PERFMON_H
+#define ASM_X86__INTEL_ARCH_PERFMON_H
 
 #define MSR_ARCH_PERFMON_PERFCTR0		0xc1
 #define MSR_ARCH_PERFMON_PERFCTR1		0xc2
@@ -28,4 +28,4 @@
 	unsigned int full;
 };
 
-#endif /* _ASM_X86_INTEL_ARCH_PERFMON_H */
+#endif /* ASM_X86__INTEL_ARCH_PERFMON_H */
diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h
index 0f954dc..72b7719 100644
--- a/include/asm-x86/io.h
+++ b/include/asm-x86/io.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_IO_H
-#define _ASM_X86_IO_H
+#ifndef ASM_X86__IO_H
+#define ASM_X86__IO_H
 
 #define ARCH_HAS_IOREMAP_WC
 
@@ -73,6 +73,8 @@
 #define writeq writeq
 #endif
 
+extern int iommu_bio_merge;
+
 #ifdef CONFIG_X86_32
 # include "io_32.h"
 #else
@@ -99,4 +101,4 @@
 extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 
 
-#endif /* _ASM_X86_IO_H */
+#endif /* ASM_X86__IO_H */
diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h
index e876d89..4f7d878 100644
--- a/include/asm-x86/io_32.h
+++ b/include/asm-x86/io_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IO_H
-#define _ASM_IO_H
+#ifndef ASM_X86__IO_32_H
+#define ASM_X86__IO_32_H
 
 #include <linux/string.h>
 #include <linux/compiler.h>
@@ -281,4 +281,4 @@
 BUILDIO(w, w, short)
 BUILDIO(l, , int)
 
-#endif
+#endif /* ASM_X86__IO_32_H */
diff --git a/include/asm-x86/io_64.h b/include/asm-x86/io_64.h
index 22995c5..64429e9 100644
--- a/include/asm-x86/io_64.h
+++ b/include/asm-x86/io_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IO_H
-#define _ASM_IO_H
+#ifndef ASM_X86__IO_64_H
+#define ASM_X86__IO_64_H
 
 
 /*
@@ -235,7 +235,6 @@
 
 #define flush_write_buffers()
 
-extern int iommu_bio_merge;
 #define BIO_VMERGE_BOUNDARY iommu_bio_merge
 
 /*
@@ -245,4 +244,4 @@
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__IO_64_H */
diff --git a/include/asm-x86/io_apic.h b/include/asm-x86/io_apic.h
index 14f82bb..be62847 100644
--- a/include/asm-x86/io_apic.h
+++ b/include/asm-x86/io_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_IO_APIC_H
-#define __ASM_IO_APIC_H
+#ifndef ASM_X86__IO_APIC_H
+#define ASM_X86__IO_APIC_H
 
 #include <linux/types.h>
 #include <asm/mpspec.h>
@@ -189,4 +189,4 @@
 static inline void ioapic_init_mappings(void) { }
 #endif
 
-#endif
+#endif /* ASM_X86__IO_APIC_H */
diff --git a/include/asm-x86/ioctls.h b/include/asm-x86/ioctls.h
index c0c338b..3366035 100644
--- a/include/asm-x86/ioctls.h
+++ b/include/asm-x86/ioctls.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_IOCTLS_H
-#define _ASM_X86_IOCTLS_H
+#ifndef ASM_X86__IOCTLS_H
+#define ASM_X86__IOCTLS_H
 
 #include <asm/ioctl.h>
 
@@ -85,4 +85,4 @@
 
 #define TIOCSER_TEMT    0x01	/* Transmitter physically empty */
 
-#endif
+#endif /* ASM_X86__IOCTLS_H */
diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h
index 5f888cc..e86f441 100644
--- a/include/asm-x86/iommu.h
+++ b/include/asm-x86/iommu.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X8664_IOMMU_H
-#define _ASM_X8664_IOMMU_H 1
+#ifndef ASM_X86__IOMMU_H
+#define ASM_X86__IOMMU_H
 
 extern void pci_iommu_shutdown(void);
 extern void no_iommu_init(void);
@@ -42,4 +42,4 @@
 }
 #endif
 
-#endif
+#endif /* ASM_X86__IOMMU_H */
diff --git a/include/asm-x86/ipcbuf.h b/include/asm-x86/ipcbuf.h
index ee678fd..910304f 100644
--- a/include/asm-x86/ipcbuf.h
+++ b/include/asm-x86/ipcbuf.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_IPCBUF_H
-#define _ASM_X86_IPCBUF_H
+#ifndef ASM_X86__IPCBUF_H
+#define ASM_X86__IPCBUF_H
 
 /*
  * The ipc64_perm structure for x86 architecture.
@@ -25,4 +25,4 @@
 	unsigned long		__unused2;
 };
 
-#endif /* _ASM_X86_IPCBUF_H */
+#endif /* ASM_X86__IPCBUF_H */
diff --git a/include/asm-x86/ipi.h b/include/asm-x86/ipi.h
index bb1c09f..c1b2267 100644
--- a/include/asm-x86/ipi.h
+++ b/include/asm-x86/ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_IPI_H
-#define __ASM_IPI_H
+#ifndef ASM_X86__IPI_H
+#define ASM_X86__IPI_H
 
 /*
  * Copyright 2004 James Cleverdon, IBM.
@@ -129,4 +129,4 @@
 	local_irq_restore(flags);
 }
 
-#endif /* __ASM_IPI_H */
+#endif /* ASM_X86__IPI_H */
diff --git a/include/asm-x86/irq.h b/include/asm-x86/irq.h
index 1a29257..1e5f290 100644
--- a/include/asm-x86/irq.h
+++ b/include/asm-x86/irq.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IRQ_H
-#define _ASM_IRQ_H
+#ifndef ASM_X86__IRQ_H
+#define ASM_X86__IRQ_H
 /*
  *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
  *
@@ -47,4 +47,4 @@
 /* Interrupt vector management */
 extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
 
-#endif /* _ASM_IRQ_H */
+#endif /* ASM_X86__IRQ_H */
diff --git a/include/asm-x86/irq_regs_32.h b/include/asm-x86/irq_regs_32.h
index 3368b20..316a3b2 100644
--- a/include/asm-x86/irq_regs_32.h
+++ b/include/asm-x86/irq_regs_32.h
@@ -4,8 +4,8 @@
  *
  * Jeremy Fitzhardinge <jeremy@goop.org>
  */
-#ifndef _ASM_I386_IRQ_REGS_H
-#define _ASM_I386_IRQ_REGS_H
+#ifndef ASM_X86__IRQ_REGS_32_H
+#define ASM_X86__IRQ_REGS_32_H
 
 #include <asm/percpu.h>
 
@@ -26,4 +26,4 @@
 	return old_regs;
 }
 
-#endif /* _ASM_I386_IRQ_REGS_H */
+#endif /* ASM_X86__IRQ_REGS_32_H */
diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h
index a48c7f2..c5d2d76 100644
--- a/include/asm-x86/irq_vectors.h
+++ b/include/asm-x86/irq_vectors.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IRQ_VECTORS_H
-#define _ASM_IRQ_VECTORS_H
+#ifndef ASM_X86__IRQ_VECTORS_H
+#define ASM_X86__IRQ_VECTORS_H
 
 #include <linux/threads.h>
 
@@ -179,4 +179,4 @@
 #define VIC_CPU_BOOT_ERRATA_CPI		(VIC_CPI_LEVEL0 + 8)
 
 
-#endif /* _ASM_IRQ_VECTORS_H */
+#endif /* ASM_X86__IRQ_VECTORS_H */
diff --git a/include/asm-x86/ist.h b/include/asm-x86/ist.h
index 6ec6cee..35a2fe9 100644
--- a/include/asm-x86/ist.h
+++ b/include/asm-x86/ist.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IST_H
-#define _ASM_IST_H
+#ifndef ASM_X86__IST_H
+#define ASM_X86__IST_H
 
 /*
  * Include file for the interface to IST BIOS
@@ -31,4 +31,4 @@
 extern struct ist_info ist_info;
 
 #endif	/* __KERNEL__ */
-#endif	/* _ASM_IST_H */
+#endif /* ASM_X86__IST_H */
diff --git a/include/asm-x86/k8.h b/include/asm-x86/k8.h
index 452e2b6..2bbaf43 100644
--- a/include/asm-x86/k8.h
+++ b/include/asm-x86/k8.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_K8_H
-#define _ASM_K8_H 1
+#ifndef ASM_X86__K8_H
+#define ASM_X86__K8_H
 
 #include <linux/pci.h>
 
@@ -12,4 +12,4 @@
 extern void k8_flush_garts(void);
 extern int k8_scan_nodes(unsigned long start, unsigned long end);
 
-#endif
+#endif /* ASM_X86__K8_H */
diff --git a/include/asm-x86/kdebug.h b/include/asm-x86/kdebug.h
index 96651bb..5ec3ad3 100644
--- a/include/asm-x86/kdebug.h
+++ b/include/asm-x86/kdebug.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_KDEBUG_H
-#define _ASM_X86_KDEBUG_H
+#ifndef ASM_X86__KDEBUG_H
+#define ASM_X86__KDEBUG_H
 
 #include <linux/notifier.h>
 
@@ -35,4 +35,4 @@
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
 
-#endif
+#endif /* ASM_X86__KDEBUG_H */
diff --git a/include/asm-x86/kexec.h b/include/asm-x86/kexec.h
index 4246ab7..ea09600 100644
--- a/include/asm-x86/kexec.h
+++ b/include/asm-x86/kexec.h
@@ -1,5 +1,5 @@
-#ifndef _KEXEC_H
-#define _KEXEC_H
+#ifndef ASM_X86__KEXEC_H
+#define ASM_X86__KEXEC_H
 
 #ifdef CONFIG_X86_32
 # define PA_CONTROL_PAGE	0
@@ -172,4 +172,4 @@
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* _KEXEC_H */
+#endif /* ASM_X86__KEXEC_H */
diff --git a/include/asm-x86/kgdb.h b/include/asm-x86/kgdb.h
index 484c475..d283863 100644
--- a/include/asm-x86/kgdb.h
+++ b/include/asm-x86/kgdb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_KGDB_H_
-#define _ASM_KGDB_H_
+#ifndef ASM_X86__KGDB_H
+#define ASM_X86__KGDB_H
 
 /*
  * Copyright (C) 2001-2004 Amit S. Kale
@@ -39,12 +39,13 @@
 	GDB_FS,			/* 14 */
 	GDB_GS,			/* 15 */
 };
+#define NUMREGBYTES		((GDB_GS+1)*4)
 #else /* ! CONFIG_X86_32 */
-enum regnames {
+enum regnames64 {
 	GDB_AX,			/* 0 */
-	GDB_DX,			/* 1 */
+	GDB_BX,			/* 1 */
 	GDB_CX,			/* 2 */
-	GDB_BX,			/* 3 */
+	GDB_DX,			/* 3 */
 	GDB_SI,			/* 4 */
 	GDB_DI,			/* 5 */
 	GDB_BP,			/* 6 */
@@ -58,18 +59,15 @@
 	GDB_R14,		/* 14 */
 	GDB_R15,		/* 15 */
 	GDB_PC,			/* 16 */
-	GDB_PS,			/* 17 */
 };
-#endif /* CONFIG_X86_32 */
 
-/*
- * Number of bytes of registers:
- */
-#ifdef CONFIG_X86_32
-# define NUMREGBYTES		64
-#else
-# define NUMREGBYTES		((GDB_PS+1)*8)
-#endif
+enum regnames32 {
+	GDB_PS = 34,
+	GDB_CS,
+	GDB_SS,
+};
+#define NUMREGBYTES		((GDB_SS+1)*4)
+#endif /* CONFIG_X86_32 */
 
 static inline void arch_kgdb_breakpoint(void)
 {
@@ -78,4 +76,4 @@
 #define BREAK_INSTR_SIZE	1
 #define CACHE_FLUSH_IS_SAFE	1
 
-#endif				/* _ASM_KGDB_H_ */
+#endif /* ASM_X86__KGDB_H */
diff --git a/include/asm-x86/kmap_types.h b/include/asm-x86/kmap_types.h
index 5f41741..89f4449 100644
--- a/include/asm-x86/kmap_types.h
+++ b/include/asm-x86/kmap_types.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_KMAP_TYPES_H
-#define _ASM_X86_KMAP_TYPES_H
+#ifndef ASM_X86__KMAP_TYPES_H
+#define ASM_X86__KMAP_TYPES_H
 
 #if defined(CONFIG_X86_32) && defined(CONFIG_DEBUG_HIGHMEM)
 # define D(n) __KM_FENCE_##n ,
@@ -26,4 +26,4 @@
 
 #undef D
 
-#endif
+#endif /* ASM_X86__KMAP_TYPES_H */
diff --git a/include/asm-x86/kprobes.h b/include/asm-x86/kprobes.h
index 54980b0..bd840786 100644
--- a/include/asm-x86/kprobes.h
+++ b/include/asm-x86/kprobes.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_KPROBES_H
-#define _ASM_KPROBES_H
+#ifndef ASM_X86__KPROBES_H
+#define ASM_X86__KPROBES_H
 /*
  *  Kernel Probes (KProbes)
  *
@@ -94,4 +94,4 @@
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_exceptions_notify(struct notifier_block *self,
 				    unsigned long val, void *data);
-#endif				/* _ASM_KPROBES_H */
+#endif /* ASM_X86__KPROBES_H */
diff --git a/include/asm-x86/kvm.h b/include/asm-x86/kvm.h
index 6f18408..78e954d 100644
--- a/include/asm-x86/kvm.h
+++ b/include/asm-x86/kvm.h
@@ -1,5 +1,5 @@
-#ifndef __LINUX_KVM_X86_H
-#define __LINUX_KVM_X86_H
+#ifndef ASM_X86__KVM_H
+#define ASM_X86__KVM_H
 
 /*
  * KVM x86 specific structures and definitions
@@ -230,4 +230,4 @@
 #define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
 #define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
 
-#endif
+#endif /* ASM_X86__KVM_H */
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
index c2e34c2..6979454 100644
--- a/include/asm-x86/kvm_host.h
+++ b/include/asm-x86/kvm_host.h
@@ -1,4 +1,4 @@
-#/*
+/*
  * Kernel-based Virtual Machine driver for Linux
  *
  * This header defines architecture specific interfaces, x86 version
@@ -8,8 +8,8 @@
  *
  */
 
-#ifndef ASM_KVM_HOST_H
-#define ASM_KVM_HOST_H
+#ifndef ASM_X86__KVM_HOST_H
+#define ASM_X86__KVM_HOST_H
 
 #include <linux/types.h>
 #include <linux/mm.h>
@@ -735,4 +735,4 @@
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
 
-#endif
+#endif /* ASM_X86__KVM_HOST_H */
diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h
index 76f3921..30054fd 100644
--- a/include/asm-x86/kvm_para.h
+++ b/include/asm-x86/kvm_para.h
@@ -1,5 +1,5 @@
-#ifndef __X86_KVM_PARA_H
-#define __X86_KVM_PARA_H
+#ifndef ASM_X86__KVM_PARA_H
+#define ASM_X86__KVM_PARA_H
 
 /* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx.  It
  * should be used to determine that a VM is running under KVM.
@@ -144,4 +144,4 @@
 
 #endif
 
-#endif
+#endif /* ASM_X86__KVM_PARA_H */
diff --git a/include/asm-x86/kvm_x86_emulate.h b/include/asm-x86/kvm_x86_emulate.h
index 4e8c1e4..e2d9b03 100644
--- a/include/asm-x86/kvm_x86_emulate.h
+++ b/include/asm-x86/kvm_x86_emulate.h
@@ -8,8 +8,8 @@
  * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4
  */
 
-#ifndef __X86_EMULATE_H__
-#define __X86_EMULATE_H__
+#ifndef ASM_X86__KVM_X86_EMULATE_H
+#define ASM_X86__KVM_X86_EMULATE_H
 
 struct x86_emulate_ctxt;
 
@@ -181,4 +181,4 @@
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
 		     struct x86_emulate_ops *ops);
 
-#endif				/* __X86_EMULATE_H__ */
+#endif /* ASM_X86__KVM_X86_EMULATE_H */
diff --git a/include/asm-x86/ldt.h b/include/asm-x86/ldt.h
index 20c5972..a522850 100644
--- a/include/asm-x86/ldt.h
+++ b/include/asm-x86/ldt.h
@@ -3,8 +3,8 @@
  *
  * Definitions of structures used with the modify_ldt system call.
  */
-#ifndef _ASM_X86_LDT_H
-#define _ASM_X86_LDT_H
+#ifndef ASM_X86__LDT_H
+#define ASM_X86__LDT_H
 
 /* Maximum number of LDT entries supported. */
 #define LDT_ENTRIES	8192
@@ -37,4 +37,4 @@
 #define MODIFY_LDT_CONTENTS_CODE	2
 
 #endif /* !__ASSEMBLY__ */
-#endif
+#endif /* ASM_X86__LDT_H */
diff --git a/include/asm-x86/lguest.h b/include/asm-x86/lguest.h
index be4a724..7505e94 100644
--- a/include/asm-x86/lguest.h
+++ b/include/asm-x86/lguest.h
@@ -1,5 +1,5 @@
-#ifndef _X86_LGUEST_H
-#define _X86_LGUEST_H
+#ifndef ASM_X86__LGUEST_H
+#define ASM_X86__LGUEST_H
 
 #define GDT_ENTRY_LGUEST_CS	10
 #define GDT_ENTRY_LGUEST_DS	11
@@ -91,4 +91,4 @@
 
 #endif /* __ASSEMBLY__ */
 
-#endif
+#endif /* ASM_X86__LGUEST_H */
diff --git a/include/asm-x86/lguest_hcall.h b/include/asm-x86/lguest_hcall.h
index a3241f2..8f034ba 100644
--- a/include/asm-x86/lguest_hcall.h
+++ b/include/asm-x86/lguest_hcall.h
@@ -1,6 +1,6 @@
 /* Architecture specific portion of the lguest hypercalls */
-#ifndef _X86_LGUEST_HCALL_H
-#define _X86_LGUEST_HCALL_H
+#ifndef ASM_X86__LGUEST_HCALL_H
+#define ASM_X86__LGUEST_HCALL_H
 
 #define LHCALL_FLUSH_ASYNC	0
 #define LHCALL_LGUEST_INIT	1
@@ -68,4 +68,4 @@
 };
 
 #endif /* !__ASSEMBLY__ */
-#endif	/* _I386_LGUEST_HCALL_H */
+#endif /* ASM_X86__LGUEST_HCALL_H */
diff --git a/include/asm-x86/linkage.h b/include/asm-x86/linkage.h
index 64e444f..42d8b62 100644
--- a/include/asm-x86/linkage.h
+++ b/include/asm-x86/linkage.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_LINKAGE_H
-#define __ASM_LINKAGE_H
+#ifndef ASM_X86__LINKAGE_H
+#define ASM_X86__LINKAGE_H
 
 #undef notrace
 #define notrace __attribute__((no_instrument_function))
@@ -57,5 +57,5 @@
 #define __ALIGN_STR ".align 16,0x90"
 #endif
 
-#endif
+#endif /* ASM_X86__LINKAGE_H */
 
diff --git a/include/asm-x86/local.h b/include/asm-x86/local.h
index 330a724..ae91994 100644
--- a/include/asm-x86/local.h
+++ b/include/asm-x86/local.h
@@ -1,5 +1,5 @@
-#ifndef _ARCH_LOCAL_H
-#define _ARCH_LOCAL_H
+#ifndef ASM_X86__LOCAL_H
+#define ASM_X86__LOCAL_H
 
 #include <linux/percpu.h>
 
@@ -232,4 +232,4 @@
 #define __cpu_local_add(i, l)	cpu_local_add((i), (l))
 #define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
 
-#endif /* _ARCH_LOCAL_H */
+#endif /* ASM_X86__LOCAL_H */
diff --git a/include/asm-x86/mach-bigsmp/mach_apic.h b/include/asm-x86/mach-bigsmp/mach_apic.h
index c3b9dc6..05362d4 100644
--- a/include/asm-x86/mach-bigsmp/mach_apic.h
+++ b/include/asm-x86/mach-bigsmp/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_BIGSMP__MACH_APIC_H
+#define ASM_X86__MACH_BIGSMP__MACH_APIC_H
 
 #define xapic_phys_to_log_apicid(cpu) (per_cpu(x86_bios_cpu_apicid, cpu))
 #define esr_disable (1)
@@ -141,4 +141,4 @@
 	return cpuid_apic >> index_msb;
 }
 
-#endif /* __ASM_MACH_APIC_H */
+#endif /* ASM_X86__MACH_BIGSMP__MACH_APIC_H */
diff --git a/include/asm-x86/mach-bigsmp/mach_apicdef.h b/include/asm-x86/mach-bigsmp/mach_apicdef.h
index a58ab5a..811935d 100644
--- a/include/asm-x86/mach-bigsmp/mach_apicdef.h
+++ b/include/asm-x86/mach-bigsmp/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef ASM_X86__MACH_BIGSMP__MACH_APICDEF_H
+#define ASM_X86__MACH_BIGSMP__MACH_APICDEF_H
 
 #define		APIC_ID_MASK		(0xFF<<24)
 
@@ -10,4 +10,4 @@
 
 #define		GET_APIC_ID(x)	get_apic_id(x)
 
-#endif
+#endif /* ASM_X86__MACH_BIGSMP__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-bigsmp/mach_ipi.h b/include/asm-x86/mach-bigsmp/mach_ipi.h
index 9404c53..b1b0f96 100644
--- a/include/asm-x86/mach-bigsmp/mach_ipi.h
+++ b/include/asm-x86/mach-bigsmp/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef ASM_X86__MACH_BIGSMP__MACH_IPI_H
+#define ASM_X86__MACH_BIGSMP__MACH_IPI_H
 
 void send_IPI_mask_sequence(cpumask_t mask, int vector);
 
@@ -22,4 +22,4 @@
 	send_IPI_mask(cpu_online_map, vector);
 }
 
-#endif /* __ASM_MACH_IPI_H */
+#endif /* ASM_X86__MACH_BIGSMP__MACH_IPI_H */
diff --git a/include/asm-x86/mach-default/apm.h b/include/asm-x86/mach-default/apm.h
index 989f34c..2aa61b5 100644
--- a/include/asm-x86/mach-default/apm.h
+++ b/include/asm-x86/mach-default/apm.h
@@ -3,8 +3,8 @@
  *  Split out from apm.c by Osamu Tomita <tomita@cinet.co.jp>
  */
 
-#ifndef _ASM_APM_H
-#define _ASM_APM_H
+#ifndef ASM_X86__MACH_DEFAULT__APM_H
+#define ASM_X86__MACH_DEFAULT__APM_H
 
 #ifdef APM_ZERO_SEGS
 #	define APM_DO_ZERO_SEGS \
@@ -70,4 +70,4 @@
 	return error;
 }
 
-#endif /* _ASM_APM_H */
+#endif /* ASM_X86__MACH_DEFAULT__APM_H */
diff --git a/include/asm-x86/mach-default/mach_apic.h b/include/asm-x86/mach-default/mach_apic.h
index f3226b9..b615f40 100644
--- a/include/asm-x86/mach-default/mach_apic.h
+++ b/include/asm-x86/mach-default/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_APIC_H
+#define ASM_X86__MACH_DEFAULT__MACH_APIC_H
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
@@ -138,4 +138,4 @@
 }
 
 #endif /* CONFIG_X86_LOCAL_APIC */
-#endif /* __ASM_MACH_APIC_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_APIC_H */
diff --git a/include/asm-x86/mach-default/mach_apicdef.h b/include/asm-x86/mach-default/mach_apicdef.h
index e4b29ba..936704f 100644
--- a/include/asm-x86/mach-default/mach_apicdef.h
+++ b/include/asm-x86/mach-default/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_APICDEF_H
+#define ASM_X86__MACH_DEFAULT__MACH_APICDEF_H
 
 #include <asm/apic.h>
 
@@ -21,4 +21,4 @@
 #define		GET_APIC_ID(x)	get_apic_id(x)
 #endif
 
-#endif
+#endif /* ASM_X86__MACH_DEFAULT__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-default/mach_ipi.h b/include/asm-x86/mach-default/mach_ipi.h
index be32336..674bc7e 100644
--- a/include/asm-x86/mach-default/mach_ipi.h
+++ b/include/asm-x86/mach-default/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_IPI_H
+#define ASM_X86__MACH_DEFAULT__MACH_IPI_H
 
 /* Avoid include hell */
 #define NMI_VECTOR 0x02
@@ -61,4 +61,4 @@
 }
 #endif
 
-#endif /* __ASM_MACH_IPI_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_IPI_H */
diff --git a/include/asm-x86/mach-default/mach_mpparse.h b/include/asm-x86/mach-default/mach_mpparse.h
index d141085..9c381f2 100644
--- a/include/asm-x86/mach-default/mach_mpparse.h
+++ b/include/asm-x86/mach-default/mach_mpparse.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H
+#define ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H
 
 static inline int mps_oem_check(struct mp_config_table *mpc, char *oem, 
 		char *productid)
@@ -14,4 +14,4 @@
 }
 
 
-#endif /* __ASM_MACH_MPPARSE_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-default/mach_mpspec.h b/include/asm-x86/mach-default/mach_mpspec.h
index 51c9a97..d77646f 100644
--- a/include/asm-x86/mach-default/mach_mpspec.h
+++ b/include/asm-x86/mach-default/mach_mpspec.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H
+#define ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H
 
 #define MAX_IRQ_SOURCES 256
 
@@ -9,4 +9,4 @@
 #define MAX_MP_BUSSES 32
 #endif
 
-#endif /* __ASM_MACH_MPSPEC_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-default/mach_timer.h b/include/asm-x86/mach-default/mach_timer.h
index 4b76e53..990b158 100644
--- a/include/asm-x86/mach-default/mach_timer.h
+++ b/include/asm-x86/mach-default/mach_timer.h
@@ -10,8 +10,8 @@
  * directly because of the awkward 8-bit access mechanism of the 82C54
  * device.
  */
-#ifndef _MACH_TIMER_H
-#define _MACH_TIMER_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_TIMER_H
+#define ASM_X86__MACH_DEFAULT__MACH_TIMER_H
 
 #define CALIBRATE_TIME_MSEC 30 /* 30 msecs */
 #define CALIBRATE_LATCH	\
@@ -45,4 +45,4 @@
 	*count_p = count;
 }
 
-#endif /* !_MACH_TIMER_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_TIMER_H */
diff --git a/include/asm-x86/mach-default/mach_traps.h b/include/asm-x86/mach-default/mach_traps.h
index 2fe7705..de9ac3f 100644
--- a/include/asm-x86/mach-default/mach_traps.h
+++ b/include/asm-x86/mach-default/mach_traps.h
@@ -2,8 +2,8 @@
  *  Machine specific NMI handling for generic.
  *  Split out from traps.c by Osamu Tomita <tomita@cinet.co.jp>
  */
-#ifndef _MACH_TRAPS_H
-#define _MACH_TRAPS_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_TRAPS_H
+#define ASM_X86__MACH_DEFAULT__MACH_TRAPS_H
 
 #include <asm/mc146818rtc.h>
 
@@ -36,4 +36,4 @@
 		unlock_cmos();
 }
 
-#endif /* !_MACH_TRAPS_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_TRAPS_H */
diff --git a/include/asm-x86/mach-default/mach_wakecpu.h b/include/asm-x86/mach-default/mach_wakecpu.h
index 3ebb178..361b810 100644
--- a/include/asm-x86/mach-default/mach_wakecpu.h
+++ b/include/asm-x86/mach-default/mach_wakecpu.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_WAKECPU_H
-#define __ASM_MACH_WAKECPU_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H
+#define ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H
 
 /* 
  * This file copes with machines that wakeup secondary CPUs by the
@@ -39,4 +39,4 @@
  #define inquire_remote_apic(apicid) {}
 #endif
 
-#endif /* __ASM_MACH_WAKECPU_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H */
diff --git a/include/asm-x86/mach-es7000/mach_apic.h b/include/asm-x86/mach-es7000/mach_apic.h
index 0a3fdf9..c1f6f68 100644
--- a/include/asm-x86/mach-es7000/mach_apic.h
+++ b/include/asm-x86/mach-es7000/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_ES7000__MACH_APIC_H
+#define ASM_X86__MACH_ES7000__MACH_APIC_H
 
 #define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu)
 #define esr_disable (1)
@@ -191,4 +191,4 @@
 	return cpuid_apic >> index_msb;
 }
 
-#endif /* __ASM_MACH_APIC_H */
+#endif /* ASM_X86__MACH_ES7000__MACH_APIC_H */
diff --git a/include/asm-x86/mach-es7000/mach_apicdef.h b/include/asm-x86/mach-es7000/mach_apicdef.h
index a58ab5a..a07e567 100644
--- a/include/asm-x86/mach-es7000/mach_apicdef.h
+++ b/include/asm-x86/mach-es7000/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef ASM_X86__MACH_ES7000__MACH_APICDEF_H
+#define ASM_X86__MACH_ES7000__MACH_APICDEF_H
 
 #define		APIC_ID_MASK		(0xFF<<24)
 
@@ -10,4 +10,4 @@
 
 #define		GET_APIC_ID(x)	get_apic_id(x)
 
-#endif
+#endif /* ASM_X86__MACH_ES7000__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-es7000/mach_ipi.h b/include/asm-x86/mach-es7000/mach_ipi.h
index 5e61bd2..3a21240 100644
--- a/include/asm-x86/mach-es7000/mach_ipi.h
+++ b/include/asm-x86/mach-es7000/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef ASM_X86__MACH_ES7000__MACH_IPI_H
+#define ASM_X86__MACH_ES7000__MACH_IPI_H
 
 void send_IPI_mask_sequence(cpumask_t mask, int vector);
 
@@ -21,4 +21,4 @@
 	send_IPI_mask(cpu_online_map, vector);
 }
 
-#endif /* __ASM_MACH_IPI_H */
+#endif /* ASM_X86__MACH_ES7000__MACH_IPI_H */
diff --git a/include/asm-x86/mach-es7000/mach_mpparse.h b/include/asm-x86/mach-es7000/mach_mpparse.h
index ef26d35..befde24 100644
--- a/include/asm-x86/mach-es7000/mach_mpparse.h
+++ b/include/asm-x86/mach-es7000/mach_mpparse.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
+#ifndef ASM_X86__MACH_ES7000__MACH_MPPARSE_H
+#define ASM_X86__MACH_ES7000__MACH_MPPARSE_H
 
 #include <linux/acpi.h>
 
@@ -26,4 +26,4 @@
 }
 #endif
 
-#endif /* __ASM_MACH_MPPARSE_H */
+#endif /* ASM_X86__MACH_ES7000__MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-es7000/mach_wakecpu.h b/include/asm-x86/mach-es7000/mach_wakecpu.h
index 84ff583..97c776c 100644
--- a/include/asm-x86/mach-es7000/mach_wakecpu.h
+++ b/include/asm-x86/mach-es7000/mach_wakecpu.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_WAKECPU_H
-#define __ASM_MACH_WAKECPU_H
+#ifndef ASM_X86__MACH_ES7000__MACH_WAKECPU_H
+#define ASM_X86__MACH_ES7000__MACH_WAKECPU_H
 
 /* 
  * This file copes with machines that wakeup secondary CPUs by the
@@ -56,4 +56,4 @@
  #define inquire_remote_apic(apicid) {}
 #endif
 
-#endif /* __ASM_MACH_WAKECPU_H */
+#endif /* ASM_X86__MACH_ES7000__MACH_WAKECPU_H */
diff --git a/include/asm-x86/mach-generic/gpio.h b/include/asm-x86/mach-generic/gpio.h
index 5305dcb..6ce0f77 100644
--- a/include/asm-x86/mach-generic/gpio.h
+++ b/include/asm-x86/mach-generic/gpio.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_GENERIC_GPIO_H
-#define __ASM_MACH_GENERIC_GPIO_H
+#ifndef ASM_X86__MACH_GENERIC__GPIO_H
+#define ASM_X86__MACH_GENERIC__GPIO_H
 
 int gpio_request(unsigned gpio, const char *label);
 void gpio_free(unsigned gpio);
@@ -12,4 +12,4 @@
 
 #include <asm-generic/gpio.h>           /* cansleep wrappers */
 
-#endif /* __ASM_MACH_GENERIC_GPIO_H */
+#endif /* ASM_X86__MACH_GENERIC__GPIO_H */
diff --git a/include/asm-x86/mach-generic/irq_vectors_limits.h b/include/asm-x86/mach-generic/irq_vectors_limits.h
index 890ce3f..f7870e1 100644
--- a/include/asm-x86/mach-generic/irq_vectors_limits.h
+++ b/include/asm-x86/mach-generic/irq_vectors_limits.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IRQ_VECTORS_LIMITS_H
-#define _ASM_IRQ_VECTORS_LIMITS_H
+#ifndef ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H
+#define ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H
 
 /*
  * For Summit or generic (i.e. installer) kernels, we have lots of I/O APICs,
@@ -11,4 +11,4 @@
 #define NR_IRQS	224
 #define NR_IRQ_VECTORS	1024
 
-#endif /* _ASM_IRQ_VECTORS_LIMITS_H */
+#endif /* ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H */
diff --git a/include/asm-x86/mach-generic/mach_apic.h b/include/asm-x86/mach-generic/mach_apic.h
index 6eff343..5d010c6 100644
--- a/include/asm-x86/mach-generic/mach_apic.h
+++ b/include/asm-x86/mach-generic/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_GENERIC__MACH_APIC_H
+#define ASM_X86__MACH_GENERIC__MACH_APIC_H
 
 #include <asm/genapic.h>
 
@@ -29,4 +29,4 @@
 
 extern void generic_bigsmp_probe(void);
 
-#endif /* __ASM_MACH_APIC_H */
+#endif /* ASM_X86__MACH_GENERIC__MACH_APIC_H */
diff --git a/include/asm-x86/mach-generic/mach_apicdef.h b/include/asm-x86/mach-generic/mach_apicdef.h
index 28ed989..1657f38 100644
--- a/include/asm-x86/mach-generic/mach_apicdef.h
+++ b/include/asm-x86/mach-generic/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef _GENAPIC_MACH_APICDEF_H
-#define _GENAPIC_MACH_APICDEF_H 1
+#ifndef ASM_X86__MACH_GENERIC__MACH_APICDEF_H
+#define ASM_X86__MACH_GENERIC__MACH_APICDEF_H
 
 #ifndef APIC_DEFINITION
 #include <asm/genapic.h>
@@ -8,4 +8,4 @@
 #define APIC_ID_MASK (genapic->apic_id_mask)
 #endif
 
-#endif
+#endif /* ASM_X86__MACH_GENERIC__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-generic/mach_ipi.h b/include/asm-x86/mach-generic/mach_ipi.h
index 441b0fe..f67433d 100644
--- a/include/asm-x86/mach-generic/mach_ipi.h
+++ b/include/asm-x86/mach-generic/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef _MACH_IPI_H
-#define _MACH_IPI_H 1
+#ifndef ASM_X86__MACH_GENERIC__MACH_IPI_H
+#define ASM_X86__MACH_GENERIC__MACH_IPI_H
 
 #include <asm/genapic.h>
 
@@ -7,4 +7,4 @@
 #define send_IPI_allbutself (genapic->send_IPI_allbutself)
 #define send_IPI_all (genapic->send_IPI_all)
 
-#endif
+#endif /* ASM_X86__MACH_GENERIC__MACH_IPI_H */
diff --git a/include/asm-x86/mach-generic/mach_mpparse.h b/include/asm-x86/mach-generic/mach_mpparse.h
index 586cadb..3115564 100644
--- a/include/asm-x86/mach-generic/mach_mpparse.h
+++ b/include/asm-x86/mach-generic/mach_mpparse.h
@@ -1,5 +1,5 @@
-#ifndef _MACH_MPPARSE_H
-#define _MACH_MPPARSE_H 1
+#ifndef ASM_X86__MACH_GENERIC__MACH_MPPARSE_H
+#define ASM_X86__MACH_GENERIC__MACH_MPPARSE_H
 
 
 extern int mps_oem_check(struct mp_config_table *mpc, char *oem,
@@ -7,4 +7,4 @@
 
 extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
 
-#endif
+#endif /* ASM_X86__MACH_GENERIC__MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-generic/mach_mpspec.h b/include/asm-x86/mach-generic/mach_mpspec.h
index c83c120..6061b15 100644
--- a/include/asm-x86/mach-generic/mach_mpspec.h
+++ b/include/asm-x86/mach-generic/mach_mpspec.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
+#ifndef ASM_X86__MACH_GENERIC__MACH_MPSPEC_H
+#define ASM_X86__MACH_GENERIC__MACH_MPSPEC_H
 
 #define MAX_IRQ_SOURCES 256
 
@@ -9,4 +9,4 @@
 
 extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
 				char *productid);
-#endif /* __ASM_MACH_MPSPEC_H */
+#endif /* ASM_X86__MACH_GENERIC__MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-numaq/mach_apic.h b/include/asm-x86/mach-numaq/mach_apic.h
index d802465..7a0d39e 100644
--- a/include/asm-x86/mach-numaq/mach_apic.h
+++ b/include/asm-x86/mach-numaq/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_NUMAQ__MACH_APIC_H
+#define ASM_X86__MACH_NUMAQ__MACH_APIC_H
 
 #include <asm/io.h>
 #include <linux/mmzone.h>
@@ -135,4 +135,4 @@
 	return cpuid_apic >> index_msb;
 }
 
-#endif /* __ASM_MACH_APIC_H */
+#endif /* ASM_X86__MACH_NUMAQ__MACH_APIC_H */
diff --git a/include/asm-x86/mach-numaq/mach_apicdef.h b/include/asm-x86/mach-numaq/mach_apicdef.h
index bf439d0..f870ec5 100644
--- a/include/asm-x86/mach-numaq/mach_apicdef.h
+++ b/include/asm-x86/mach-numaq/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef ASM_X86__MACH_NUMAQ__MACH_APICDEF_H
+#define ASM_X86__MACH_NUMAQ__MACH_APICDEF_H
 
 
 #define APIC_ID_MASK (0xF<<24)
@@ -11,4 +11,4 @@
 
 #define         GET_APIC_ID(x)  get_apic_id(x)
 
-#endif
+#endif /* ASM_X86__MACH_NUMAQ__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-numaq/mach_ipi.h b/include/asm-x86/mach-numaq/mach_ipi.h
index c604448..1e83582 100644
--- a/include/asm-x86/mach-numaq/mach_ipi.h
+++ b/include/asm-x86/mach-numaq/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef ASM_X86__MACH_NUMAQ__MACH_IPI_H
+#define ASM_X86__MACH_NUMAQ__MACH_IPI_H
 
 void send_IPI_mask_sequence(cpumask_t, int vector);
 
@@ -22,4 +22,4 @@
 	send_IPI_mask(cpu_online_map, vector);
 }
 
-#endif /* __ASM_MACH_IPI_H */
+#endif /* ASM_X86__MACH_NUMAQ__MACH_IPI_H */
diff --git a/include/asm-x86/mach-numaq/mach_mpparse.h b/include/asm-x86/mach-numaq/mach_mpparse.h
index 626aef6..74ade18 100644
--- a/include/asm-x86/mach-numaq/mach_mpparse.h
+++ b/include/asm-x86/mach-numaq/mach_mpparse.h
@@ -1,7 +1,7 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
+#ifndef ASM_X86__MACH_NUMAQ__MACH_MPPARSE_H
+#define ASM_X86__MACH_NUMAQ__MACH_MPPARSE_H
 
 extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
 				char *productid);
 
-#endif /* __ASM_MACH_MPPARSE_H */
+#endif /* ASM_X86__MACH_NUMAQ__MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-numaq/mach_wakecpu.h b/include/asm-x86/mach-numaq/mach_wakecpu.h
index 0053004..0db8cea 100644
--- a/include/asm-x86/mach-numaq/mach_wakecpu.h
+++ b/include/asm-x86/mach-numaq/mach_wakecpu.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_WAKECPU_H
-#define __ASM_MACH_WAKECPU_H
+#ifndef ASM_X86__MACH_NUMAQ__MACH_WAKECPU_H
+#define ASM_X86__MACH_NUMAQ__MACH_WAKECPU_H
 
 /* This file copes with machines that wakeup secondary CPUs by NMIs */
 
@@ -40,4 +40,4 @@
 
 #define inquire_remote_apic(apicid) {}
 
-#endif /* __ASM_MACH_WAKECPU_H */
+#endif /* ASM_X86__MACH_NUMAQ__MACH_WAKECPU_H */
diff --git a/include/asm-x86/mach-rdc321x/gpio.h b/include/asm-x86/mach-rdc321x/gpio.h
index acce0b7..94b6cdf 100644
--- a/include/asm-x86/mach-rdc321x/gpio.h
+++ b/include/asm-x86/mach-rdc321x/gpio.h
@@ -1,5 +1,7 @@
-#ifndef _RDC321X_GPIO_H
-#define _RDC321X_GPIO_H
+#ifndef ASM_X86__MACH_RDC321X__GPIO_H
+#define ASM_X86__MACH_RDC321X__GPIO_H
+
+#include <linux/kernel.h>
 
 extern int rdc_gpio_get_value(unsigned gpio);
 extern void rdc_gpio_set_value(unsigned gpio, int value);
@@ -18,6 +20,7 @@
 
 static inline void gpio_free(unsigned gpio)
 {
+	might_sleep();
 	rdc_gpio_free(gpio);
 }
 
@@ -54,4 +57,4 @@
 /* For cansleep */
 #include <asm-generic/gpio.h>
 
-#endif /* _RDC321X_GPIO_H_ */
+#endif /* ASM_X86__MACH_RDC321X__GPIO_H */
diff --git a/include/asm-x86/mach-summit/irq_vectors_limits.h b/include/asm-x86/mach-summit/irq_vectors_limits.h
index 890ce3f..22f376a 100644
--- a/include/asm-x86/mach-summit/irq_vectors_limits.h
+++ b/include/asm-x86/mach-summit/irq_vectors_limits.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IRQ_VECTORS_LIMITS_H
-#define _ASM_IRQ_VECTORS_LIMITS_H
+#ifndef ASM_X86__MACH_SUMMIT__IRQ_VECTORS_LIMITS_H
+#define ASM_X86__MACH_SUMMIT__IRQ_VECTORS_LIMITS_H
 
 /*
  * For Summit or generic (i.e. installer) kernels, we have lots of I/O APICs,
@@ -11,4 +11,4 @@
 #define NR_IRQS	224
 #define NR_IRQ_VECTORS	1024
 
-#endif /* _ASM_IRQ_VECTORS_LIMITS_H */
+#endif /* ASM_X86__MACH_SUMMIT__IRQ_VECTORS_LIMITS_H */
diff --git a/include/asm-x86/mach-summit/mach_apic.h b/include/asm-x86/mach-summit/mach_apic.h
index c47e2ab..7a66758 100644
--- a/include/asm-x86/mach-summit/mach_apic.h
+++ b/include/asm-x86/mach-summit/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_SUMMIT__MACH_APIC_H
+#define ASM_X86__MACH_SUMMIT__MACH_APIC_H
 
 #include <asm/smp.h>
 
@@ -182,4 +182,4 @@
 	return hard_smp_processor_id() >> index_msb;
 }
 
-#endif /* __ASM_MACH_APIC_H */
+#endif /* ASM_X86__MACH_SUMMIT__MACH_APIC_H */
diff --git a/include/asm-x86/mach-summit/mach_apicdef.h b/include/asm-x86/mach-summit/mach_apicdef.h
index a58ab5a..d4bc859 100644
--- a/include/asm-x86/mach-summit/mach_apicdef.h
+++ b/include/asm-x86/mach-summit/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef ASM_X86__MACH_SUMMIT__MACH_APICDEF_H
+#define ASM_X86__MACH_SUMMIT__MACH_APICDEF_H
 
 #define		APIC_ID_MASK		(0xFF<<24)
 
@@ -10,4 +10,4 @@
 
 #define		GET_APIC_ID(x)	get_apic_id(x)
 
-#endif
+#endif /* ASM_X86__MACH_SUMMIT__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-summit/mach_ipi.h b/include/asm-x86/mach-summit/mach_ipi.h
index 9404c53..a3b31c5 100644
--- a/include/asm-x86/mach-summit/mach_ipi.h
+++ b/include/asm-x86/mach-summit/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef ASM_X86__MACH_SUMMIT__MACH_IPI_H
+#define ASM_X86__MACH_SUMMIT__MACH_IPI_H
 
 void send_IPI_mask_sequence(cpumask_t mask, int vector);
 
@@ -22,4 +22,4 @@
 	send_IPI_mask(cpu_online_map, vector);
 }
 
-#endif /* __ASM_MACH_IPI_H */
+#endif /* ASM_X86__MACH_SUMMIT__MACH_IPI_H */
diff --git a/include/asm-x86/mach-summit/mach_mpparse.h b/include/asm-x86/mach-summit/mach_mpparse.h
index fdf5917..92396f2 100644
--- a/include/asm-x86/mach-summit/mach_mpparse.h
+++ b/include/asm-x86/mach-summit/mach_mpparse.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
+#ifndef ASM_X86__MACH_SUMMIT__MACH_MPPARSE_H
+#define ASM_X86__MACH_SUMMIT__MACH_MPPARSE_H
 
 #include <mach_apic.h>
 #include <asm/tsc.h>
@@ -107,4 +107,4 @@
 		rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
 }
 
-#endif /* __ASM_MACH_MPPARSE_H */
+#endif /* ASM_X86__MACH_SUMMIT__MACH_MPPARSE_H */
diff --git a/include/asm-x86/math_emu.h b/include/asm-x86/math_emu.h
index 9bf4ae9..5768d8e 100644
--- a/include/asm-x86/math_emu.h
+++ b/include/asm-x86/math_emu.h
@@ -1,5 +1,5 @@
-#ifndef _I386_MATH_EMU_H
-#define _I386_MATH_EMU_H
+#ifndef ASM_X86__MATH_EMU_H
+#define ASM_X86__MATH_EMU_H
 
 /* This structure matches the layout of the data saved to the stack
    following a device-not-present interrupt, part of it saved
@@ -28,4 +28,4 @@
 	long ___vm86_fs;
 	long ___vm86_gs;
 };
-#endif
+#endif /* ASM_X86__MATH_EMU_H */
diff --git a/include/asm-x86/mc146818rtc.h b/include/asm-x86/mc146818rtc.h
index daf1ccd..a995f33 100644
--- a/include/asm-x86/mc146818rtc.h
+++ b/include/asm-x86/mc146818rtc.h
@@ -1,8 +1,8 @@
 /*
  * Machine dependent access functions for RTC registers.
  */
-#ifndef _ASM_MC146818RTC_H
-#define _ASM_MC146818RTC_H
+#ifndef ASM_X86__MC146818RTC_H
+#define ASM_X86__MC146818RTC_H
 
 #include <asm/io.h>
 #include <asm/system.h>
@@ -101,4 +101,4 @@
 
 #define RTC_IRQ 8
 
-#endif /* _ASM_MC146818RTC_H */
+#endif /* ASM_X86__MC146818RTC_H */
diff --git a/include/asm-x86/mca.h b/include/asm-x86/mca.h
index 09adf2e..60d1ed2 100644
--- a/include/asm-x86/mca.h
+++ b/include/asm-x86/mca.h
@@ -1,8 +1,8 @@
 /* -*- mode: c; c-basic-offset: 8 -*- */
 
 /* Platform specific MCA defines */
-#ifndef _ASM_MCA_H
-#define _ASM_MCA_H
+#ifndef ASM_X86__MCA_H
+#define ASM_X86__MCA_H
 
 /* Maximal number of MCA slots - actually, some machines have less, but
  * they all have sufficient number of POS registers to cover 8.
@@ -40,4 +40,4 @@
  */
 #define MCA_NUMADAPTERS (MCA_MAX_SLOT_NR+3)
 
-#endif
+#endif /* ASM_X86__MCA_H */
diff --git a/include/asm-x86/mca_dma.h b/include/asm-x86/mca_dma.h
index c3dca6e..49f22be 100644
--- a/include/asm-x86/mca_dma.h
+++ b/include/asm-x86/mca_dma.h
@@ -1,5 +1,5 @@
-#ifndef MCA_DMA_H
-#define MCA_DMA_H
+#ifndef ASM_X86__MCA_DMA_H
+#define ASM_X86__MCA_DMA_H
 
 #include <asm/io.h>
 #include <linux/ioport.h>
@@ -198,4 +198,4 @@
 	outb(mode, MCA_DMA_REG_EXE);
 }
 
-#endif /* MCA_DMA_H */
+#endif /* ASM_X86__MCA_DMA_H */
diff --git a/include/asm-x86/mce.h b/include/asm-x86/mce.h
index 531eaa5..036133e 100644
--- a/include/asm-x86/mce.h
+++ b/include/asm-x86/mce.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_MCE_H
-#define _ASM_X86_MCE_H
+#ifndef ASM_X86__MCE_H
+#define ASM_X86__MCE_H
 
 #ifdef __x86_64__
 
@@ -127,4 +127,4 @@
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__MCE_H */
diff --git a/include/asm-x86/mman.h b/include/asm-x86/mman.h
index 90bc410..4ef28e6 100644
--- a/include/asm-x86/mman.h
+++ b/include/asm-x86/mman.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_MMAN_H
-#define _ASM_X86_MMAN_H
+#ifndef ASM_X86__MMAN_H
+#define ASM_X86__MMAN_H
 
 #include <asm-generic/mman.h>
 
@@ -17,4 +17,4 @@
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
 
-#endif /* _ASM_X86_MMAN_H */
+#endif /* ASM_X86__MMAN_H */
diff --git a/include/asm-x86/mmconfig.h b/include/asm-x86/mmconfig.h
index e293ab8..fb79b1c 100644
--- a/include/asm-x86/mmconfig.h
+++ b/include/asm-x86/mmconfig.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_MMCONFIG_H
-#define _ASM_MMCONFIG_H
+#ifndef ASM_X86__MMCONFIG_H
+#define ASM_X86__MMCONFIG_H
 
 #ifdef CONFIG_PCI_MMCONFIG
 extern void __cpuinit fam10h_check_enable_mmcfg(void);
@@ -9,4 +9,4 @@
 static inline void check_enable_amd_mmconf_dmi(void) { }
 #endif
 
-#endif
+#endif /* ASM_X86__MMCONFIG_H */
diff --git a/include/asm-x86/mmu.h b/include/asm-x86/mmu.h
index 00e8867..9d5aff1 100644
--- a/include/asm-x86/mmu.h
+++ b/include/asm-x86/mmu.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_MMU_H
-#define _ASM_X86_MMU_H
+#ifndef ASM_X86__MMU_H
+#define ASM_X86__MMU_H
 
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
@@ -7,14 +7,9 @@
 /*
  * The x86 doesn't have a mmu context, but
  * we put the segment information here.
- *
- * cpu_vm_mask is used to optimize ldt flushing.
  */
 typedef struct {
 	void *ldt;
-#ifdef CONFIG_X86_64
-	rwlock_t ldtlock;
-#endif
 	int size;
 	struct mutex lock;
 	void *vdso;
@@ -28,4 +23,4 @@
 }
 #endif
 
-#endif /* _ASM_X86_MMU_H */
+#endif /* ASM_X86__MMU_H */
diff --git a/include/asm-x86/mmu_context.h b/include/asm-x86/mmu_context.h
index fac5701..8ec940b 100644
--- a/include/asm-x86/mmu_context.h
+++ b/include/asm-x86/mmu_context.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_X86_MMU_CONTEXT_H
-#define __ASM_X86_MMU_CONTEXT_H
+#ifndef ASM_X86__MMU_CONTEXT_H
+#define ASM_X86__MMU_CONTEXT_H
 
 #include <asm/desc.h>
 #include <asm/atomic.h>
@@ -34,4 +34,4 @@
 } while (0);
 
 
-#endif /* __ASM_X86_MMU_CONTEXT_H */
+#endif /* ASM_X86__MMU_CONTEXT_H */
diff --git a/include/asm-x86/mmu_context_32.h b/include/asm-x86/mmu_context_32.h
index 824fc57..cce6f6e 100644
--- a/include/asm-x86/mmu_context_32.h
+++ b/include/asm-x86/mmu_context_32.h
@@ -1,5 +1,5 @@
-#ifndef __I386_SCHED_H
-#define __I386_SCHED_H
+#ifndef ASM_X86__MMU_CONTEXT_32_H
+#define ASM_X86__MMU_CONTEXT_32_H
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
@@ -53,4 +53,4 @@
 #define deactivate_mm(tsk, mm)			\
 	asm("movl %0,%%gs": :"r" (0));
 
-#endif
+#endif /* ASM_X86__MMU_CONTEXT_32_H */
diff --git a/include/asm-x86/mmu_context_64.h b/include/asm-x86/mmu_context_64.h
index c700063..2675867 100644
--- a/include/asm-x86/mmu_context_64.h
+++ b/include/asm-x86/mmu_context_64.h
@@ -1,5 +1,5 @@
-#ifndef __X86_64_MMU_CONTEXT_H
-#define __X86_64_MMU_CONTEXT_H
+#ifndef ASM_X86__MMU_CONTEXT_64_H
+#define ASM_X86__MMU_CONTEXT_64_H
 
 #include <asm/pda.h>
 
@@ -51,4 +51,4 @@
 	asm volatile("movl %0,%%fs"::"r"(0));	\
 } while (0)
 
-#endif
+#endif /* ASM_X86__MMU_CONTEXT_64_H */
diff --git a/include/asm-x86/mmx.h b/include/asm-x86/mmx.h
index 9408812..2e7299b 100644
--- a/include/asm-x86/mmx.h
+++ b/include/asm-x86/mmx.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_MMX_H
-#define _ASM_MMX_H
+#ifndef ASM_X86__MMX_H
+#define ASM_X86__MMX_H
 
 /*
  *	MMX 3Dnow! helper operations
@@ -11,4 +11,4 @@
 extern void mmx_clear_page(void *page);
 extern void mmx_copy_page(void *to, void *from);
 
-#endif
+#endif /* ASM_X86__MMX_H */
diff --git a/include/asm-x86/mmzone_32.h b/include/asm-x86/mmzone_32.h
index 5862e64..121b65d 100644
--- a/include/asm-x86/mmzone_32.h
+++ b/include/asm-x86/mmzone_32.h
@@ -3,8 +3,8 @@
  *
  */
 
-#ifndef _ASM_MMZONE_H_
-#define _ASM_MMZONE_H_
+#ifndef ASM_X86__MMZONE_32_H
+#define ASM_X86__MMZONE_32_H
 
 #include <asm/smp.h>
 
@@ -131,4 +131,4 @@
 })
 #endif /* CONFIG_NEED_MULTIPLE_NODES */
 
-#endif /* _ASM_MMZONE_H_ */
+#endif /* ASM_X86__MMZONE_32_H */
diff --git a/include/asm-x86/mmzone_64.h b/include/asm-x86/mmzone_64.h
index 594bd0d..626b03a 100644
--- a/include/asm-x86/mmzone_64.h
+++ b/include/asm-x86/mmzone_64.h
@@ -1,8 +1,8 @@
 /* K8 NUMA support */
 /* Copyright 2002,2003 by Andi Kleen, SuSE Labs */
 /* 2.5 Version loosely based on the NUMAQ Code by Pat Gaughen. */
-#ifndef _ASM_X86_64_MMZONE_H
-#define _ASM_X86_64_MMZONE_H 1
+#ifndef ASM_X86__MMZONE_64_H
+#define ASM_X86__MMZONE_64_H
 
 
 #ifdef CONFIG_NUMA
@@ -49,4 +49,4 @@
 #endif
 
 #endif
-#endif
+#endif /* ASM_X86__MMZONE_64_H */
diff --git a/include/asm-x86/module.h b/include/asm-x86/module.h
index bfedb24..48dc3e0 100644
--- a/include/asm-x86/module.h
+++ b/include/asm-x86/module.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_MODULE_H
-#define _ASM_MODULE_H
+#ifndef ASM_X86__MODULE_H
+#define ASM_X86__MODULE_H
 
 /* x86_32/64 are simple */
 struct mod_arch_specific {};
@@ -79,4 +79,4 @@
 # define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
 #endif
 
-#endif /* _ASM_MODULE_H */
+#endif /* ASM_X86__MODULE_H */
diff --git a/include/asm-x86/mpspec.h b/include/asm-x86/mpspec.h
index b6995e5..118da36 100644
--- a/include/asm-x86/mpspec.h
+++ b/include/asm-x86/mpspec.h
@@ -1,5 +1,5 @@
-#ifndef _AM_X86_MPSPEC_H
-#define _AM_X86_MPSPEC_H
+#ifndef ASM_X86__MPSPEC_H
+#define ASM_X86__MPSPEC_H
 
 #include <linux/init.h>
 
@@ -141,4 +141,4 @@
 
 extern physid_mask_t phys_cpu_present_map;
 
-#endif
+#endif /* ASM_X86__MPSPEC_H */
diff --git a/include/asm-x86/mpspec_def.h b/include/asm-x86/mpspec_def.h
index 38d1e73..79166b0 100644
--- a/include/asm-x86/mpspec_def.h
+++ b/include/asm-x86/mpspec_def.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MPSPEC_DEF_H
-#define __ASM_MPSPEC_DEF_H
+#ifndef ASM_X86__MPSPEC_DEF_H
+#define ASM_X86__MPSPEC_DEF_H
 
 /*
  * Structure definitions for SMP machines following the
@@ -177,4 +177,4 @@
 	MP_BUS_PCI,
 	MP_BUS_MCA,
 };
-#endif
+#endif /* ASM_X86__MPSPEC_DEF_H */
diff --git a/include/asm-x86/msgbuf.h b/include/asm-x86/msgbuf.h
index 7e4e948..1b538c9 100644
--- a/include/asm-x86/msgbuf.h
+++ b/include/asm-x86/msgbuf.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_MSGBUF_H
-#define _ASM_X86_MSGBUF_H
+#ifndef ASM_X86__MSGBUF_H
+#define ASM_X86__MSGBUF_H
 
 /*
  * The msqid64_ds structure for i386 architecture.
@@ -36,4 +36,4 @@
 	unsigned long  __unused5;
 };
 
-#endif /* _ASM_X86_MSGBUF_H */
+#endif /* ASM_X86__MSGBUF_H */
diff --git a/include/asm-x86/msidef.h b/include/asm-x86/msidef.h
index 296f29c..3139666 100644
--- a/include/asm-x86/msidef.h
+++ b/include/asm-x86/msidef.h
@@ -1,5 +1,5 @@
-#ifndef ASM_MSIDEF_H
-#define ASM_MSIDEF_H
+#ifndef ASM_X86__MSIDEF_H
+#define ASM_X86__MSIDEF_H
 
 /*
  * Constants for Intel APIC based MSI messages.
@@ -48,4 +48,4 @@
 #define  MSI_ADDR_DEST_ID(dest)		(((dest) << MSI_ADDR_DEST_ID_SHIFT) & \
 					 MSI_ADDR_DEST_ID_MASK)
 
-#endif /* ASM_MSIDEF_H */
+#endif /* ASM_X86__MSIDEF_H */
diff --git a/include/asm-x86/msr-index.h b/include/asm-x86/msr-index.h
index 44bce77..3052f05 100644
--- a/include/asm-x86/msr-index.h
+++ b/include/asm-x86/msr-index.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MSR_INDEX_H
-#define __ASM_MSR_INDEX_H
+#ifndef ASM_X86__MSR_INDEX_H
+#define ASM_X86__MSR_INDEX_H
 
 /* CPU model specific register (MSR) numbers */
 
@@ -310,4 +310,4 @@
 /* Geode defined MSRs */
 #define MSR_GEODE_BUSCONT_CONF0		0x00001900
 
-#endif /* __ASM_MSR_INDEX_H */
+#endif /* ASM_X86__MSR_INDEX_H */
diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h
index 2362cfd..530af1f 100644
--- a/include/asm-x86/msr.h
+++ b/include/asm-x86/msr.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_X86_MSR_H_
-#define __ASM_X86_MSR_H_
+#ifndef ASM_X86__MSR_H
+#define ASM_X86__MSR_H
 
 #include <asm/msr-index.h>
 
@@ -63,6 +63,22 @@
 	return EAX_EDX_VAL(val, low, high);
 }
 
+static inline unsigned long long native_read_msr_amd_safe(unsigned int msr,
+						      int *err)
+{
+	DECLARE_ARGS(val, low, high);
+
+	asm volatile("2: rdmsr ; xor %0,%0\n"
+		     "1:\n\t"
+		     ".section .fixup,\"ax\"\n\t"
+		     "3:  mov %3,%0 ; jmp 1b\n\t"
+		     ".previous\n\t"
+		     _ASM_EXTABLE(2b, 3b)
+		     : "=r" (*err), EAX_EDX_RET(val, low, high)
+		     : "c" (msr), "D" (0x9c5a203a), "i" (-EFAULT));
+	return EAX_EDX_VAL(val, low, high);
+}
+
 static inline void native_write_msr(unsigned int msr,
 				    unsigned low, unsigned high)
 {
@@ -158,6 +174,13 @@
 	*p = native_read_msr_safe(msr, &err);
 	return err;
 }
+static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+{
+	int err;
+
+	*p = native_read_msr_amd_safe(msr, &err);
+	return err;
+}
 
 #define rdtscl(low)						\
 	((low) = (u32)native_read_tsc())
@@ -221,4 +244,4 @@
 #endif /* __KERNEL__ */
 
 
-#endif
+#endif /* ASM_X86__MSR_H */
diff --git a/include/asm-x86/mtrr.h b/include/asm-x86/mtrr.h
index a69a01a..23a7f83 100644
--- a/include/asm-x86/mtrr.h
+++ b/include/asm-x86/mtrr.h
@@ -20,8 +20,8 @@
     The postal address is:
       Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
 */
-#ifndef _ASM_X86_MTRR_H
-#define _ASM_X86_MTRR_H
+#ifndef ASM_X86__MTRR_H
+#define ASM_X86__MTRR_H
 
 #include <linux/ioctl.h>
 #include <linux/errno.h>
@@ -170,4 +170,4 @@
 
 #endif /* __KERNEL__ */
 
-#endif  /*  _ASM_X86_MTRR_H  */
+#endif /* ASM_X86__MTRR_H */
diff --git a/include/asm-x86/mutex_32.h b/include/asm-x86/mutex_32.h
index 73e928e..25c16d8 100644
--- a/include/asm-x86/mutex_32.h
+++ b/include/asm-x86/mutex_32.h
@@ -6,8 +6,8 @@
  *
  *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
-#ifndef _ASM_MUTEX_H
-#define _ASM_MUTEX_H
+#ifndef ASM_X86__MUTEX_32_H
+#define ASM_X86__MUTEX_32_H
 
 #include <asm/alternative.h>
 
@@ -122,4 +122,4 @@
 #endif
 }
 
-#endif
+#endif /* ASM_X86__MUTEX_32_H */
diff --git a/include/asm-x86/mutex_64.h b/include/asm-x86/mutex_64.h
index f3fae9b..918ba21 100644
--- a/include/asm-x86/mutex_64.h
+++ b/include/asm-x86/mutex_64.h
@@ -6,8 +6,8 @@
  *
  *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
-#ifndef _ASM_MUTEX_H
-#define _ASM_MUTEX_H
+#ifndef ASM_X86__MUTEX_64_H
+#define ASM_X86__MUTEX_64_H
 
 /**
  * __mutex_fastpath_lock - decrement and call function if negative
@@ -97,4 +97,4 @@
 		return 0;
 }
 
-#endif
+#endif /* ASM_X86__MUTEX_64_H */
diff --git a/include/asm-x86/nmi.h b/include/asm-x86/nmi.h
index 21f8d02..d5e715f 100644
--- a/include/asm-x86/nmi.h
+++ b/include/asm-x86/nmi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_NMI_H_
-#define _ASM_X86_NMI_H_
+#ifndef ASM_X86__NMI_H
+#define ASM_X86__NMI_H
 
 #include <linux/pm.h>
 #include <asm/irq.h>
@@ -34,6 +34,7 @@
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
 extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason);
+extern void cpu_nmi_set_wd_enabled(void);
 
 extern atomic_t nmi_active;
 extern unsigned int nmi_watchdog;
@@ -81,4 +82,4 @@
 void stop_nmi(void);
 void restart_nmi(void);
 
-#endif
+#endif /* ASM_X86__NMI_H */
diff --git a/include/asm-x86/nops.h b/include/asm-x86/nops.h
index ad0bedd..ae74272 100644
--- a/include/asm-x86/nops.h
+++ b/include/asm-x86/nops.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_NOPS_H
-#define _ASM_NOPS_H 1
+#ifndef ASM_X86__NOPS_H
+#define ASM_X86__NOPS_H
 
 /* Define nops for use with alternative() */
 
@@ -115,4 +115,4 @@
 
 #define ASM_NOP_MAX 8
 
-#endif
+#endif /* ASM_X86__NOPS_H */
diff --git a/include/asm-x86/numa_32.h b/include/asm-x86/numa_32.h
index 220d7b7..44cb078 100644
--- a/include/asm-x86/numa_32.h
+++ b/include/asm-x86/numa_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_32_NUMA_H
-#define _ASM_X86_32_NUMA_H 1
+#ifndef ASM_X86__NUMA_32_H
+#define ASM_X86__NUMA_32_H
 
 extern int pxm_to_nid(int pxm);
 extern void numa_remove_cpu(int cpu);
@@ -8,4 +8,4 @@
 extern void set_highmem_pages_init(void);
 #endif
 
-#endif /* _ASM_X86_32_NUMA_H */
+#endif /* ASM_X86__NUMA_32_H */
diff --git a/include/asm-x86/numa_64.h b/include/asm-x86/numa_64.h
index 3830094..15c9903 100644
--- a/include/asm-x86/numa_64.h
+++ b/include/asm-x86/numa_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X8664_NUMA_H
-#define _ASM_X8664_NUMA_H 1
+#ifndef ASM_X86__NUMA_64_H
+#define ASM_X86__NUMA_64_H
 
 #include <linux/nodemask.h>
 #include <asm/apicdef.h>
@@ -40,4 +40,4 @@
 static inline void numa_remove_cpu(int cpu)		{ }
 #endif
 
-#endif
+#endif /* ASM_X86__NUMA_64_H */
diff --git a/include/asm-x86/numaq.h b/include/asm-x86/numaq.h
index 34b92d5..124bf7d 100644
--- a/include/asm-x86/numaq.h
+++ b/include/asm-x86/numaq.h
@@ -23,8 +23,8 @@
  * Send feedback to <gone@us.ibm.com>
  */
 
-#ifndef NUMAQ_H
-#define NUMAQ_H
+#ifndef ASM_X86__NUMAQ_H
+#define ASM_X86__NUMAQ_H
 
 #ifdef CONFIG_X86_NUMAQ
 
@@ -165,5 +165,5 @@
 	return 0;
 }
 #endif /* CONFIG_X86_NUMAQ */
-#endif /* NUMAQ_H */
+#endif /* ASM_X86__NUMAQ_H */
 
diff --git a/include/asm-x86/olpc.h b/include/asm-x86/olpc.h
index 97d4713..d7328b1 100644
--- a/include/asm-x86/olpc.h
+++ b/include/asm-x86/olpc.h
@@ -1,7 +1,7 @@
 /* OLPC machine specific definitions */
 
-#ifndef ASM_OLPC_H_
-#define ASM_OLPC_H_
+#ifndef ASM_X86__OLPC_H
+#define ASM_X86__OLPC_H
 
 #include <asm/geode.h>
 
@@ -129,4 +129,4 @@
 #define OLPC_GPIO_LID		geode_gpio(26)
 #define OLPC_GPIO_ECSCI		geode_gpio(27)
 
-#endif
+#endif /* ASM_X86__OLPC_H */
diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h
index 4998211..79544e6 100644
--- a/include/asm-x86/page.h
+++ b/include/asm-x86/page.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PAGE_H
-#define _ASM_X86_PAGE_H
+#ifndef ASM_X86__PAGE_H
+#define ASM_X86__PAGE_H
 
 #include <linux/const.h>
 
@@ -199,4 +199,4 @@
 #define __HAVE_ARCH_GATE_AREA 1
 
 #endif	/* __KERNEL__ */
-#endif	/* _ASM_X86_PAGE_H */
+#endif /* ASM_X86__PAGE_H */
diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h
index ab85287..72f7305 100644
--- a/include/asm-x86/page_32.h
+++ b/include/asm-x86/page_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PAGE_32_H
-#define _ASM_X86_PAGE_32_H
+#ifndef ASM_X86__PAGE_32_H
+#define ASM_X86__PAGE_32_H
 
 /*
  * This handles the memory map.
@@ -89,13 +89,11 @@
 extern unsigned int __VMALLOC_RESERVE;
 extern int sysctl_legacy_va_layout;
 
-#define VMALLOC_RESERVE		((unsigned long)__VMALLOC_RESERVE)
-#define MAXMEM			(-__PAGE_OFFSET - __VMALLOC_RESERVE)
-
 extern void find_low_pfn_range(void);
 extern unsigned long init_memory_mapping(unsigned long start,
 					 unsigned long end);
 extern void initmem_init(unsigned long, unsigned long);
+extern void free_initmem(void);
 extern void setup_bootmem_allocator(void);
 
 
@@ -126,4 +124,4 @@
 #endif	/* CONFIG_X86_3DNOW */
 #endif	/* !__ASSEMBLY__ */
 
-#endif /* _ASM_X86_PAGE_32_H */
+#endif /* ASM_X86__PAGE_32_H */
diff --git a/include/asm-x86/page_64.h b/include/asm-x86/page_64.h
index c6916c8..5e64acf 100644
--- a/include/asm-x86/page_64.h
+++ b/include/asm-x86/page_64.h
@@ -1,5 +1,5 @@
-#ifndef _X86_64_PAGE_H
-#define _X86_64_PAGE_H
+#ifndef ASM_X86__PAGE_64_H
+#define ASM_X86__PAGE_64_H
 
 #define PAGETABLE_LEVELS	4
 
@@ -91,6 +91,7 @@
 					 unsigned long end);
 
 extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
+extern void free_initmem(void);
 
 extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
 extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
@@ -102,4 +103,4 @@
 #endif
 
 
-#endif /* _X86_64_PAGE_H */
+#endif /* ASM_X86__PAGE_64_H */
diff --git a/include/asm-x86/param.h b/include/asm-x86/param.h
index 6f0d042..0009cfb 100644
--- a/include/asm-x86/param.h
+++ b/include/asm-x86/param.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PARAM_H
-#define _ASM_X86_PARAM_H
+#ifndef ASM_X86__PARAM_H
+#define ASM_X86__PARAM_H
 
 #ifdef __KERNEL__
 # define HZ		CONFIG_HZ	/* Internal kernel timer frequency */
@@ -19,4 +19,4 @@
 
 #define MAXHOSTNAMELEN	64	/* max length of hostname */
 
-#endif /* _ASM_X86_PARAM_H */
+#endif /* ASM_X86__PARAM_H */
diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
index fbbde93..891971f 100644
--- a/include/asm-x86/paravirt.h
+++ b/include/asm-x86/paravirt.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_PARAVIRT_H
-#define __ASM_PARAVIRT_H
+#ifndef ASM_X86__PARAVIRT_H
+#define ASM_X86__PARAVIRT_H
 /* Various instructions on x86 need to be replaced for
  * para-virtualization: those hooks are defined here. */
 
@@ -137,6 +137,7 @@
 
 	/* MSR, PMC and TSR operations.
 	   err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
+	u64 (*read_msr_amd)(unsigned int msr, int *err);
 	u64 (*read_msr)(unsigned int msr, int *err);
 	int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
 
@@ -257,13 +258,13 @@
 	 * Hooks for allocating/releasing pagetable pages when they're
 	 * attached to a pagetable
 	 */
-	void (*alloc_pte)(struct mm_struct *mm, u32 pfn);
-	void (*alloc_pmd)(struct mm_struct *mm, u32 pfn);
-	void (*alloc_pmd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count);
-	void (*alloc_pud)(struct mm_struct *mm, u32 pfn);
-	void (*release_pte)(u32 pfn);
-	void (*release_pmd)(u32 pfn);
-	void (*release_pud)(u32 pfn);
+	void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
+	void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
+	void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count);
+	void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
+	void (*release_pte)(unsigned long pfn);
+	void (*release_pmd)(unsigned long pfn);
+	void (*release_pud)(unsigned long pfn);
 
 	/* Pagetable manipulation functions */
 	void (*set_pte)(pte_t *ptep, pte_t pteval);
@@ -726,6 +727,10 @@
 {
 	return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
 }
+static inline u64 paravirt_read_msr_amd(unsigned msr, int *err)
+{
+	return PVOP_CALL2(u64, pv_cpu_ops.read_msr_amd, msr, err);
+}
 static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
 {
 	return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
@@ -771,6 +776,13 @@
 	*p = paravirt_read_msr(msr, &err);
 	return err;
 }
+static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+{
+	int err;
+
+	*p = paravirt_read_msr_amd(msr, &err);
+	return err;
+}
 
 static inline u64 paravirt_read_tsc(void)
 {
@@ -993,35 +1005,35 @@
 	PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd);
 }
 
-static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned pfn)
+static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)
 {
 	PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn);
 }
-static inline void paravirt_release_pte(unsigned pfn)
+static inline void paravirt_release_pte(unsigned long pfn)
 {
 	PVOP_VCALL1(pv_mmu_ops.release_pte, pfn);
 }
 
-static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned pfn)
+static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
 {
 	PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
 }
 
-static inline void paravirt_alloc_pmd_clone(unsigned pfn, unsigned clonepfn,
-					    unsigned start, unsigned count)
+static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
+					    unsigned long start, unsigned long count)
 {
 	PVOP_VCALL4(pv_mmu_ops.alloc_pmd_clone, pfn, clonepfn, start, count);
 }
-static inline void paravirt_release_pmd(unsigned pfn)
+static inline void paravirt_release_pmd(unsigned long pfn)
 {
 	PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
 }
 
-static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned pfn)
+static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
 	PVOP_VCALL2(pv_mmu_ops.alloc_pud, mm, pfn);
 }
-static inline void paravirt_release_pud(unsigned pfn)
+static inline void paravirt_release_pud(unsigned long pfn)
 {
 	PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
 }
@@ -1634,4 +1646,4 @@
 
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_PARAVIRT */
-#endif	/* __ASM_PARAVIRT_H */
+#endif /* ASM_X86__PARAVIRT_H */
diff --git a/include/asm-x86/parport.h b/include/asm-x86/parport.h
index 3c4ffeb..2e3dda4 100644
--- a/include/asm-x86/parport.h
+++ b/include/asm-x86/parport.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PARPORT_H
-#define _ASM_X86_PARPORT_H
+#ifndef ASM_X86__PARPORT_H
+#define ASM_X86__PARPORT_H
 
 static int __devinit parport_pc_find_isa_ports(int autoirq, int autodma);
 static int __devinit parport_pc_find_nonpci_ports(int autoirq, int autodma)
@@ -7,4 +7,4 @@
 	return parport_pc_find_isa_ports(autoirq, autodma);
 }
 
-#endif /* _ASM_X86_PARPORT_H */
+#endif /* ASM_X86__PARPORT_H */
diff --git a/include/asm-x86/pat.h b/include/asm-x86/pat.h
index 7edc473..482c3e3 100644
--- a/include/asm-x86/pat.h
+++ b/include/asm-x86/pat.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_PAT_H
-#define _ASM_PAT_H
+#ifndef ASM_X86__PAT_H
+#define ASM_X86__PAT_H
 
 #include <linux/types.h>
 
@@ -19,4 +19,4 @@
 
 extern void pat_disable(char *reason);
 
-#endif
+#endif /* ASM_X86__PAT_H */
diff --git a/include/asm-x86/pci-direct.h b/include/asm-x86/pci-direct.h
index 80c775d..da42be0 100644
--- a/include/asm-x86/pci-direct.h
+++ b/include/asm-x86/pci-direct.h
@@ -1,5 +1,5 @@
-#ifndef ASM_PCI_DIRECT_H
-#define ASM_PCI_DIRECT_H 1
+#ifndef ASM_X86__PCI_DIRECT_H
+#define ASM_X86__PCI_DIRECT_H
 
 #include <linux/types.h>
 
@@ -18,4 +18,4 @@
 extern unsigned int pci_early_dump_regs;
 extern void early_dump_pci_device(u8 bus, u8 slot, u8 func);
 extern void early_dump_pci_devices(void);
-#endif
+#endif /* ASM_X86__PCI_DIRECT_H */
diff --git a/include/asm-x86/pci.h b/include/asm-x86/pci.h
index 2db14cf..6025831 100644
--- a/include/asm-x86/pci.h
+++ b/include/asm-x86/pci.h
@@ -1,5 +1,5 @@
-#ifndef __x86_PCI_H
-#define __x86_PCI_H
+#ifndef ASM_X86__PCI_H
+#define ASM_X86__PCI_H
 
 #include <linux/mm.h> /* for struct page */
 #include <linux/types.h>
@@ -111,4 +111,4 @@
 }
 #endif
 
-#endif
+#endif /* ASM_X86__PCI_H */
diff --git a/include/asm-x86/pci_32.h b/include/asm-x86/pci_32.h
index a50d468..3f22882 100644
--- a/include/asm-x86/pci_32.h
+++ b/include/asm-x86/pci_32.h
@@ -1,5 +1,5 @@
-#ifndef __i386_PCI_H
-#define __i386_PCI_H
+#ifndef ASM_X86__PCI_32_H
+#define ASM_X86__PCI_32_H
 
 
 #ifdef __KERNEL__
@@ -31,4 +31,4 @@
 #endif /* __KERNEL__ */
 
 
-#endif /* __i386_PCI_H */
+#endif /* ASM_X86__PCI_32_H */
diff --git a/include/asm-x86/pci_64.h b/include/asm-x86/pci_64.h
index f330234..f72e12d 100644
--- a/include/asm-x86/pci_64.h
+++ b/include/asm-x86/pci_64.h
@@ -1,5 +1,5 @@
-#ifndef __x8664_PCI_H
-#define __x8664_PCI_H
+#ifndef ASM_X86__PCI_64_H
+#define ASM_X86__PCI_64_H
 
 #ifdef __KERNEL__
 
@@ -63,4 +63,4 @@
 
 #endif /* __KERNEL__ */
 
-#endif /* __x8664_PCI_H */
+#endif /* ASM_X86__PCI_64_H */
diff --git a/include/asm-x86/pda.h b/include/asm-x86/pda.h
index b34e9a7..80860af 100644
--- a/include/asm-x86/pda.h
+++ b/include/asm-x86/pda.h
@@ -1,5 +1,5 @@
-#ifndef X86_64_PDA_H
-#define X86_64_PDA_H
+#ifndef ASM_X86__PDA_H
+#define ASM_X86__PDA_H
 
 #ifndef __ASSEMBLY__
 #include <linux/stddef.h>
@@ -134,4 +134,4 @@
 
 #define PDA_STACKOFFSET (5*8)
 
-#endif
+#endif /* ASM_X86__PDA_H */
diff --git a/include/asm-x86/percpu.h b/include/asm-x86/percpu.h
index f643a3a..e10a1d0 100644
--- a/include/asm-x86/percpu.h
+++ b/include/asm-x86/percpu.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PERCPU_H_
-#define _ASM_X86_PERCPU_H_
+#ifndef ASM_X86__PERCPU_H
+#define ASM_X86__PERCPU_H
 
 #ifdef CONFIG_X86_64
 #include <linux/compiler.h>
@@ -215,4 +215,4 @@
 
 #endif	/* !CONFIG_SMP */
 
-#endif /* _ASM_X86_PERCPU_H_ */
+#endif /* ASM_X86__PERCPU_H */
diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h
index d63ea43..3cd23ad 100644
--- a/include/asm-x86/pgalloc.h
+++ b/include/asm-x86/pgalloc.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PGALLOC_H
-#define _ASM_X86_PGALLOC_H
+#ifndef ASM_X86__PGALLOC_H
+#define ASM_X86__PGALLOC_H
 
 #include <linux/threads.h>
 #include <linux/mm.h>		/* for struct page */
@@ -111,4 +111,4 @@
 #endif	/* PAGETABLE_LEVELS > 3 */
 #endif	/* PAGETABLE_LEVELS > 2 */
 
-#endif	/* _ASM_X86_PGALLOC_H */
+#endif /* ASM_X86__PGALLOC_H */
diff --git a/include/asm-x86/pgtable-2level-defs.h b/include/asm-x86/pgtable-2level-defs.h
index 0f71c9f..7ec48f4 100644
--- a/include/asm-x86/pgtable-2level-defs.h
+++ b/include/asm-x86/pgtable-2level-defs.h
@@ -1,5 +1,5 @@
-#ifndef _I386_PGTABLE_2LEVEL_DEFS_H
-#define _I386_PGTABLE_2LEVEL_DEFS_H
+#ifndef ASM_X86__PGTABLE_2LEVEL_DEFS_H
+#define ASM_X86__PGTABLE_2LEVEL_DEFS_H
 
 #define SHARED_KERNEL_PMD	0
 
@@ -17,4 +17,4 @@
 
 #define PTRS_PER_PTE	1024
 
-#endif /* _I386_PGTABLE_2LEVEL_DEFS_H */
+#endif /* ASM_X86__PGTABLE_2LEVEL_DEFS_H */
diff --git a/include/asm-x86/pgtable-2level.h b/include/asm-x86/pgtable-2level.h
index 46bc52c..8176208 100644
--- a/include/asm-x86/pgtable-2level.h
+++ b/include/asm-x86/pgtable-2level.h
@@ -1,5 +1,5 @@
-#ifndef _I386_PGTABLE_2LEVEL_H
-#define _I386_PGTABLE_2LEVEL_H
+#ifndef ASM_X86__PGTABLE_2LEVEL_H
+#define ASM_X86__PGTABLE_2LEVEL_H
 
 #define pte_ERROR(e) \
 	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
@@ -53,9 +53,7 @@
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
-#define pte_page(x)		pfn_to_page(pte_pfn(x))
 #define pte_none(x)		(!(x).pte_low)
-#define pte_pfn(x)		(pte_val(x) >> PAGE_SHIFT)
 
 /*
  * Bits 0, 6 and 7 are taken, split up the 29 bits of offset
@@ -78,4 +76,4 @@
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
 
-#endif /* _I386_PGTABLE_2LEVEL_H */
+#endif /* ASM_X86__PGTABLE_2LEVEL_H */
diff --git a/include/asm-x86/pgtable-3level-defs.h b/include/asm-x86/pgtable-3level-defs.h
index 448ac95..c05fe6f 100644
--- a/include/asm-x86/pgtable-3level-defs.h
+++ b/include/asm-x86/pgtable-3level-defs.h
@@ -1,5 +1,5 @@
-#ifndef _I386_PGTABLE_3LEVEL_DEFS_H
-#define _I386_PGTABLE_3LEVEL_DEFS_H
+#ifndef ASM_X86__PGTABLE_3LEVEL_DEFS_H
+#define ASM_X86__PGTABLE_3LEVEL_DEFS_H
 
 #ifdef CONFIG_PARAVIRT
 #define SHARED_KERNEL_PMD	(pv_info.shared_kernel_pmd)
@@ -25,4 +25,4 @@
  */
 #define PTRS_PER_PTE	512
 
-#endif /* _I386_PGTABLE_3LEVEL_DEFS_H */
+#endif /* ASM_X86__PGTABLE_3LEVEL_DEFS_H */
diff --git a/include/asm-x86/pgtable-3level.h b/include/asm-x86/pgtable-3level.h
index 105057f..75f4276 100644
--- a/include/asm-x86/pgtable-3level.h
+++ b/include/asm-x86/pgtable-3level.h
@@ -1,5 +1,5 @@
-#ifndef _I386_PGTABLE_3LEVEL_H
-#define _I386_PGTABLE_3LEVEL_H
+#ifndef ASM_X86__PGTABLE_3LEVEL_H
+#define ASM_X86__PGTABLE_3LEVEL_H
 
 /*
  * Intel Physical Address Extension (PAE) Mode - three-level page
@@ -151,18 +151,11 @@
 	return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
 }
 
-#define pte_page(x)	pfn_to_page(pte_pfn(x))
-
 static inline int pte_none(pte_t pte)
 {
 	return !pte.pte_low && !pte.pte_high;
 }
 
-static inline unsigned long pte_pfn(pte_t pte)
-{
-	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
-}
-
 /*
  * Bits 0, 6 and 7 are taken in the low part of the pte,
  * put the 32 bits of offset into the high part.
@@ -179,4 +172,4 @@
 #define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
 #define __swp_entry_to_pte(x)		((pte_t){ { .pte_high = (x).val } })
 
-#endif /* _I386_PGTABLE_3LEVEL_H */
+#endif /* ASM_X86__PGTABLE_3LEVEL_H */
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
index 04caa2f..888add7 100644
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PGTABLE_H
-#define _ASM_X86_PGTABLE_H
+#ifndef ASM_X86__PGTABLE_H
+#define ASM_X86__PGTABLE_H
 
 #define FIRST_USER_ADDRESS	0
 
@@ -186,6 +186,13 @@
 	return pte_val(pte) & _PAGE_SPECIAL;
 }
 
+static inline unsigned long pte_pfn(pte_t pte)
+{
+	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
+#define pte_page(pte)	pfn_to_page(pte_pfn(pte))
+
 static inline int pmd_large(pmd_t pte)
 {
 	return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
@@ -313,6 +320,8 @@
 static inline void native_pagetable_setup_done(pgd_t *base) {}
 #endif
 
+extern int arch_report_meminfo(char *page);
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else  /* !CONFIG_PARAVIRT */
@@ -521,4 +530,4 @@
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
-#endif	/* _ASM_X86_PGTABLE_H */
+#endif /* ASM_X86__PGTABLE_H */
diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h
index 5c3b265..8de702d 100644
--- a/include/asm-x86/pgtable_32.h
+++ b/include/asm-x86/pgtable_32.h
@@ -1,5 +1,5 @@
-#ifndef _I386_PGTABLE_H
-#define _I386_PGTABLE_H
+#ifndef ASM_X86__PGTABLE_32_H
+#define ASM_X86__PGTABLE_32_H
 
 
 /*
@@ -31,6 +31,7 @@
 static inline void check_pgt_cache(void) { }
 void paging_init(void);
 
+extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
 
 /*
  * The Linux x86 paging architecture is 'compile-time dual-mode', it
@@ -56,8 +57,7 @@
  * area for the same reason. ;)
  */
 #define VMALLOC_OFFSET	(8 * 1024 * 1024)
-#define VMALLOC_START	(((unsigned long)high_memory + 2 * VMALLOC_OFFSET - 1) \
-			 & ~(VMALLOC_OFFSET - 1))
+#define VMALLOC_START	((unsigned long)high_memory + VMALLOC_OFFSET)
 #ifdef CONFIG_X86_PAE
 #define LAST_PKMAP 512
 #else
@@ -73,6 +73,8 @@
 # define VMALLOC_END	(FIXADDR_START - 2 * PAGE_SIZE)
 #endif
 
+#define MAXMEM	(VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)
+
 /*
  * Define this if things work differently on an i386 and an i486:
  * it will (on an i486) warn about kernel memory accesses that are
@@ -186,4 +188,4 @@
 #define io_remap_pfn_range(vma, vaddr, pfn, size, prot)	\
 	remap_pfn_range(vma, vaddr, pfn, size, prot)
 
-#endif /* _I386_PGTABLE_H */
+#endif /* ASM_X86__PGTABLE_32_H */
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index 549144d..fde9770 100644
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -1,5 +1,5 @@
-#ifndef _X86_64_PGTABLE_H
-#define _X86_64_PGTABLE_H
+#ifndef ASM_X86__PGTABLE_64_H
+#define ASM_X86__PGTABLE_64_H
 
 #include <linux/const.h>
 #ifndef __ASSEMBLY__
@@ -175,8 +175,6 @@
 #define pte_present(x)	(pte_val((x)) & (_PAGE_PRESENT | _PAGE_PROTNONE))
 
 #define pages_to_mb(x)	((x) >> (20 - PAGE_SHIFT))   /* FIXME: is this right? */
-#define pte_page(x)	pfn_to_page(pte_pfn((x)))
-#define pte_pfn(x)	((pte_val((x)) & __PHYSICAL_MASK) >> PAGE_SHIFT)
 
 /*
  * Macro to mark a page protection value as "uncacheable".
@@ -284,4 +282,4 @@
 #define __HAVE_ARCH_PTE_SAME
 #endif /* !__ASSEMBLY__ */
 
-#endif /* _X86_64_PGTABLE_H */
+#endif /* ASM_X86__PGTABLE_64_H */
diff --git a/include/asm-x86/posix_types_32.h b/include/asm-x86/posix_types_32.h
index b031efd..70cf2bb 100644
--- a/include/asm-x86/posix_types_32.h
+++ b/include/asm-x86/posix_types_32.h
@@ -1,5 +1,5 @@
-#ifndef __ARCH_I386_POSIX_TYPES_H
-#define __ARCH_I386_POSIX_TYPES_H
+#ifndef ASM_X86__POSIX_TYPES_32_H
+#define ASM_X86__POSIX_TYPES_32_H
 
 /*
  * This file is generally used by user-level software, so you need to
@@ -82,4 +82,4 @@
 
 #endif /* defined(__KERNEL__) */
 
-#endif
+#endif /* ASM_X86__POSIX_TYPES_32_H */
diff --git a/include/asm-x86/posix_types_64.h b/include/asm-x86/posix_types_64.h
index d6624c9..388b4e7 100644
--- a/include/asm-x86/posix_types_64.h
+++ b/include/asm-x86/posix_types_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_POSIX_TYPES_H
-#define _ASM_X86_64_POSIX_TYPES_H
+#ifndef ASM_X86__POSIX_TYPES_64_H
+#define ASM_X86__POSIX_TYPES_64_H
 
 /*
  * This file is generally used by user-level software, so you need to
@@ -116,4 +116,4 @@
 
 #endif /* defined(__KERNEL__) */
 
-#endif
+#endif /* ASM_X86__POSIX_TYPES_64_H */
diff --git a/include/asm-x86/prctl.h b/include/asm-x86/prctl.h
index 52952ad..e7ae34e 100644
--- a/include/asm-x86/prctl.h
+++ b/include/asm-x86/prctl.h
@@ -1,5 +1,5 @@
-#ifndef X86_64_PRCTL_H
-#define X86_64_PRCTL_H 1
+#ifndef ASM_X86__PRCTL_H
+#define ASM_X86__PRCTL_H
 
 #define ARCH_SET_GS 0x1001
 #define ARCH_SET_FS 0x1002
@@ -7,4 +7,4 @@
 #define ARCH_GET_GS 0x1004
 
 
-#endif
+#endif /* ASM_X86__PRCTL_H */
diff --git a/include/asm-x86/processor-flags.h b/include/asm-x86/processor-flags.h
index eff2ecd..5dd7977 100644
--- a/include/asm-x86/processor-flags.h
+++ b/include/asm-x86/processor-flags.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_I386_PROCESSOR_FLAGS_H
-#define __ASM_I386_PROCESSOR_FLAGS_H
+#ifndef ASM_X86__PROCESSOR_FLAGS_H
+#define ASM_X86__PROCESSOR_FLAGS_H
 /* Various flags defined: can be included from assembler. */
 
 /*
@@ -96,4 +96,4 @@
 #endif
 #endif
 
-#endif	/* __ASM_I386_PROCESSOR_FLAGS_H */
+#endif /* ASM_X86__PROCESSOR_FLAGS_H */
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index 4df3e2f..5eaf9bf 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_X86_PROCESSOR_H
-#define __ASM_X86_PROCESSOR_H
+#ifndef ASM_X86__PROCESSOR_H
+#define ASM_X86__PROCESSOR_H
 
 #include <asm/processor-flags.h>
 
@@ -20,6 +20,7 @@
 #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>
@@ -140,6 +141,8 @@
 #define current_cpu_data	boot_cpu_data
 #endif
 
+extern const struct seq_operations cpuinfo_op;
+
 static inline int hlt_works(int cpu)
 {
 #ifdef CONFIG_X86_32
@@ -153,6 +156,8 @@
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
 
+extern struct pt_regs *idle_regs(struct pt_regs *);
+
 extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
 extern void identify_secondary_cpu(struct cpuinfo_x86 *);
@@ -411,9 +416,14 @@
 	unsigned		io_bitmap_max;
 /* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
 	unsigned long	debugctlmsr;
-/* Debug Store - if not 0 points to a DS Save Area configuration;
- *               goes into MSR_IA32_DS_AREA */
-	unsigned long	ds_area_msr;
+#ifdef CONFIG_X86_DS
+/* Debug Store context; see include/asm-x86/ds.h; goes into MSR_IA32_DS_AREA */
+	struct ds_context	*ds_ctx;
+#endif /* CONFIG_X86_DS */
+#ifdef CONFIG_X86_PTRACE_BTS
+/* the signal to send on a bts buffer overflow */
+	unsigned int	bts_ovfl_signal;
+#endif /* CONFIG_X86_PTRACE_BTS */
 };
 
 static inline unsigned long native_get_debugreg(int regno)
@@ -943,4 +953,4 @@
 extern int get_tsc_mode(unsigned long adr);
 extern int set_tsc_mode(unsigned int val);
 
-#endif
+#endif /* ASM_X86__PROCESSOR_H */
diff --git a/include/asm-x86/proto.h b/include/asm-x86/proto.h
index 3dd458c..6e89e8b 100644
--- a/include/asm-x86/proto.h
+++ b/include/asm-x86/proto.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X8664_PROTO_H
-#define _ASM_X8664_PROTO_H 1
+#ifndef ASM_X86__PROTO_H
+#define ASM_X86__PROTO_H
 
 #include <asm/ldt.h>
 
@@ -29,4 +29,4 @@
 #define round_up(x, y) (((x) + (y) - 1) & ~((y) - 1))
 #define round_down(x, y) ((x) & ~((y) - 1))
 
-#endif
+#endif /* ASM_X86__PROTO_H */
diff --git a/include/asm-x86/ptrace-abi.h b/include/asm-x86/ptrace-abi.h
index 72e7b9d..4298b88 100644
--- a/include/asm-x86/ptrace-abi.h
+++ b/include/asm-x86/ptrace-abi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PTRACE_ABI_H
-#define _ASM_X86_PTRACE_ABI_H
+#ifndef ASM_X86__PTRACE_ABI_H
+#define ASM_X86__PTRACE_ABI_H
 
 #ifdef __i386__
 
@@ -80,8 +80,9 @@
 
 #define PTRACE_SINGLEBLOCK	33	/* resume execution until next branch */
 
-#ifndef __ASSEMBLY__
+#ifdef CONFIG_X86_PTRACE_BTS
 
+#ifndef __ASSEMBLY__
 #include <asm/types.h>
 
 /* configuration/status structure used in PTRACE_BTS_CONFIG and
@@ -97,20 +98,20 @@
 	/* actual size of bts_struct in bytes */
 	__u32 bts_size;
 };
-#endif
+#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_CUT_SIZE	0x8 /* cut requested size to max available
-				       instead of failing */
+#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, iff the size changes.
+   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
@@ -119,7 +120,7 @@
    Returns the number of bytes written.
 */
 #define PTRACE_BTS_SIZE		42
-/* Return the number of available BTS records.
+/* Return the number of available BTS records for draining.
    DATA and ADDR are ignored.
 */
 #define PTRACE_BTS_GET		43
@@ -139,5 +140,6 @@
    BTS records are read from oldest to newest.
    Returns number of BTS records drained.
 */
+#endif /* CONFIG_X86_PTRACE_BTS */
 
-#endif
+#endif /* ASM_X86__PTRACE_ABI_H */
diff --git a/include/asm-x86/ptrace.h b/include/asm-x86/ptrace.h
index 8a71db8..d64a610 100644
--- a/include/asm-x86/ptrace.h
+++ b/include/asm-x86/ptrace.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PTRACE_H
-#define _ASM_X86_PTRACE_H
+#ifndef ASM_X86__PTRACE_H
+#define ASM_X86__PTRACE_H
 
 #include <linux/compiler.h>	/* For __user */
 #include <asm/ptrace-abi.h>
@@ -127,14 +127,48 @@
 #endif /* __KERNEL__ */
 #endif /* !__i386__ */
 
+
+#ifdef CONFIG_X86_PTRACE_BTS
+/* a branch trace record entry
+ *
+ * In order to unify the interface between various processor versions,
+ * we use the below data structure for all processors.
+ */
+enum bts_qualifier {
+	BTS_INVALID = 0,
+	BTS_BRANCH,
+	BTS_TASK_ARRIVES,
+	BTS_TASK_DEPARTS
+};
+
+struct bts_struct {
+	__u64 qualifier;
+	union {
+		/* BTS_BRANCH */
+		struct {
+			__u64 from_ip;
+			__u64 to_ip;
+		} lbr;
+		/* BTS_TASK_ARRIVES or
+		   BTS_TASK_DEPARTS */
+		__u64 jiffies;
+	} variant;
+};
+#endif /* CONFIG_X86_PTRACE_BTS */
+
 #ifdef __KERNEL__
 
-/* the DS BTS struct is used for ptrace as well */
-#include <asm/ds.h>
+#include <linux/init.h>
 
+struct cpuinfo_x86;
 struct task_struct;
 
+#ifdef CONFIG_X86_PTRACE_BTS
+extern void __cpuinit ptrace_bts_init_intel(struct cpuinfo_x86 *);
 extern void ptrace_bts_take_timestamp(struct task_struct *, enum bts_qualifier);
+#else
+#define ptrace_bts_init_intel(config) do {} while (0)
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 extern unsigned long profile_pc(struct pt_regs *regs);
 
@@ -148,6 +182,9 @@
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
 #endif
 
+extern long syscall_trace_enter(struct pt_regs *);
+extern void syscall_trace_leave(struct pt_regs *);
+
 static inline unsigned long regs_return_value(struct pt_regs *regs)
 {
 	return regs->ax;
@@ -213,6 +250,11 @@
 	return regs->bp;
 }
 
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+	return regs->sp;
+}
+
 /*
  * These are defined as per linux/ptrace.h, which see.
  */
@@ -239,4 +281,4 @@
 
 #endif /* !__ASSEMBLY__ */
 
-#endif
+#endif /* ASM_X86__PTRACE_H */
diff --git a/include/asm-x86/pvclock-abi.h b/include/asm-x86/pvclock-abi.h
index 6857f84..edb3b4e 100644
--- a/include/asm-x86/pvclock-abi.h
+++ b/include/asm-x86/pvclock-abi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PVCLOCK_ABI_H_
-#define _ASM_X86_PVCLOCK_ABI_H_
+#ifndef ASM_X86__PVCLOCK_ABI_H
+#define ASM_X86__PVCLOCK_ABI_H
 #ifndef __ASSEMBLY__
 
 /*
@@ -39,4 +39,4 @@
 } __attribute__((__packed__));
 
 #endif /* __ASSEMBLY__ */
-#endif /* _ASM_X86_PVCLOCK_ABI_H_ */
+#endif /* ASM_X86__PVCLOCK_ABI_H */
diff --git a/include/asm-x86/pvclock.h b/include/asm-x86/pvclock.h
index 85b1bba..1a38f68 100644
--- a/include/asm-x86/pvclock.h
+++ b/include/asm-x86/pvclock.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PVCLOCK_H_
-#define _ASM_X86_PVCLOCK_H_
+#ifndef ASM_X86__PVCLOCK_H
+#define ASM_X86__PVCLOCK_H
 
 #include <linux/clocksource.h>
 #include <asm/pvclock-abi.h>
@@ -10,4 +10,4 @@
 			    struct pvclock_vcpu_time_info *vcpu,
 			    struct timespec *ts);
 
-#endif /* _ASM_X86_PVCLOCK_H_ */
+#endif /* ASM_X86__PVCLOCK_H */
diff --git a/include/asm-x86/reboot.h b/include/asm-x86/reboot.h
index 206f355..1c2f0ce 100644
--- a/include/asm-x86/reboot.h
+++ b/include/asm-x86/reboot.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_REBOOT_H
-#define _ASM_REBOOT_H
+#ifndef ASM_X86__REBOOT_H
+#define ASM_X86__REBOOT_H
 
 struct pt_regs;
 
@@ -18,4 +18,4 @@
 void native_machine_shutdown(void);
 void machine_real_restart(const unsigned char *code, int length);
 
-#endif	/* _ASM_REBOOT_H */
+#endif /* ASM_X86__REBOOT_H */
diff --git a/include/asm-x86/reboot_fixups.h b/include/asm-x86/reboot_fixups.h
index 0cb7d87..2c2987d 100644
--- a/include/asm-x86/reboot_fixups.h
+++ b/include/asm-x86/reboot_fixups.h
@@ -1,6 +1,6 @@
-#ifndef _LINUX_REBOOT_FIXUPS_H
-#define _LINUX_REBOOT_FIXUPS_H
+#ifndef ASM_X86__REBOOT_FIXUPS_H
+#define ASM_X86__REBOOT_FIXUPS_H
 
 extern void mach_reboot_fixups(void);
 
-#endif /* _LINUX_REBOOT_FIXUPS_H */
+#endif /* ASM_X86__REBOOT_FIXUPS_H */
diff --git a/include/asm-x86/required-features.h b/include/asm-x86/required-features.h
index 5c2ff4b..a01c4e3 100644
--- a/include/asm-x86/required-features.h
+++ b/include/asm-x86/required-features.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_REQUIRED_FEATURES_H
-#define _ASM_REQUIRED_FEATURES_H 1
+#ifndef ASM_X86__REQUIRED_FEATURES_H
+#define ASM_X86__REQUIRED_FEATURES_H
 
 /* Define minimum CPUID feature set for kernel These bits are checked
    really early to actually display a visible error message before the
@@ -79,4 +79,4 @@
 #define REQUIRED_MASK6	0
 #define REQUIRED_MASK7	0
 
-#endif
+#endif /* ASM_X86__REQUIRED_FEATURES_H */
diff --git a/include/asm-x86/resume-trace.h b/include/asm-x86/resume-trace.h
index 8d9f0b4..e39376d 100644
--- a/include/asm-x86/resume-trace.h
+++ b/include/asm-x86/resume-trace.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_RESUME_TRACE_H
-#define _ASM_X86_RESUME_TRACE_H
+#ifndef ASM_X86__RESUME_TRACE_H
+#define ASM_X86__RESUME_TRACE_H
 
 #include <asm/asm.h>
 
@@ -7,7 +7,7 @@
 do {								\
 	if (pm_trace_enabled) {					\
 		const void *tracedata;				\
-		asm volatile(_ASM_MOV_UL " $1f,%0\n"		\
+		asm volatile(_ASM_MOV " $1f,%0\n"		\
 			     ".section .tracedata,\"a\"\n"	\
 			     "1:\t.word %c1\n\t"		\
 			     _ASM_PTR " %c2\n"			\
@@ -18,4 +18,4 @@
 	}							\
 } while (0)
 
-#endif
+#endif /* ASM_X86__RESUME_TRACE_H */
diff --git a/include/asm-x86/rio.h b/include/asm-x86/rio.h
index c9448bd..5e1256b 100644
--- a/include/asm-x86/rio.h
+++ b/include/asm-x86/rio.h
@@ -5,8 +5,8 @@
  * Author: Laurent Vivier <Laurent.Vivier@bull.net>
  */
 
-#ifndef __ASM_RIO_H
-#define __ASM_RIO_H
+#ifndef ASM_X86__RIO_H
+#define ASM_X86__RIO_H
 
 #define RIO_TABLE_VERSION	3
 
@@ -60,4 +60,4 @@
 	ALT_CALGARY	= 5,	/* Second Planar Calgary      */
 };
 
-#endif /* __ASM_RIO_H */
+#endif /* ASM_X86__RIO_H */
diff --git a/include/asm-x86/rwlock.h b/include/asm-x86/rwlock.h
index 6a8c0d6..48a3109 100644
--- a/include/asm-x86/rwlock.h
+++ b/include/asm-x86/rwlock.h
@@ -1,8 +1,8 @@
-#ifndef _ASM_X86_RWLOCK_H
-#define _ASM_X86_RWLOCK_H
+#ifndef ASM_X86__RWLOCK_H
+#define ASM_X86__RWLOCK_H
 
 #define RW_LOCK_BIAS		 0x01000000
 
 /* Actual code is in asm/spinlock.h or in arch/x86/lib/rwlock.S */
 
-#endif /* _ASM_X86_RWLOCK_H */
+#endif /* ASM_X86__RWLOCK_H */
diff --git a/include/asm-x86/rwsem.h b/include/asm-x86/rwsem.h
index 750f2a3..3ff3015 100644
--- a/include/asm-x86/rwsem.h
+++ b/include/asm-x86/rwsem.h
@@ -29,8 +29,8 @@
  * front, then they'll all be woken up, but no other readers will be.
  */
 
-#ifndef _I386_RWSEM_H
-#define _I386_RWSEM_H
+#ifndef ASM_X86__RWSEM_H
+#define ASM_X86__RWSEM_H
 
 #ifndef _LINUX_RWSEM_H
 #error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
@@ -262,4 +262,4 @@
 }
 
 #endif /* __KERNEL__ */
-#endif /* _I386_RWSEM_H */
+#endif /* ASM_X86__RWSEM_H */
diff --git a/include/asm-x86/scatterlist.h b/include/asm-x86/scatterlist.h
index c043206..ee48f88 100644
--- a/include/asm-x86/scatterlist.h
+++ b/include/asm-x86/scatterlist.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SCATTERLIST_H
-#define _ASM_X86_SCATTERLIST_H
+#ifndef ASM_X86__SCATTERLIST_H
+#define ASM_X86__SCATTERLIST_H
 
 #include <asm/types.h>
 
@@ -30,4 +30,4 @@
 # define sg_dma_len(sg)		((sg)->dma_length)
 #endif
 
-#endif
+#endif /* ASM_X86__SCATTERLIST_H */
diff --git a/include/asm-x86/seccomp_32.h b/include/asm-x86/seccomp_32.h
index 36e71c5..cf9ab2d 100644
--- a/include/asm-x86/seccomp_32.h
+++ b/include/asm-x86/seccomp_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_SECCOMP_H
-#define _ASM_SECCOMP_H
+#ifndef ASM_X86__SECCOMP_32_H
+#define ASM_X86__SECCOMP_32_H
 
 #include <linux/thread_info.h>
 
@@ -14,4 +14,4 @@
 #define __NR_seccomp_exit __NR_exit
 #define __NR_seccomp_sigreturn __NR_sigreturn
 
-#endif /* _ASM_SECCOMP_H */
+#endif /* ASM_X86__SECCOMP_32_H */
diff --git a/include/asm-x86/seccomp_64.h b/include/asm-x86/seccomp_64.h
index 76cfe69..03274ce 100644
--- a/include/asm-x86/seccomp_64.h
+++ b/include/asm-x86/seccomp_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_SECCOMP_H
-#define _ASM_SECCOMP_H
+#ifndef ASM_X86__SECCOMP_64_H
+#define ASM_X86__SECCOMP_64_H
 
 #include <linux/thread_info.h>
 
@@ -22,4 +22,4 @@
 #define __NR_seccomp_exit_32 __NR_ia32_exit
 #define __NR_seccomp_sigreturn_32 __NR_ia32_sigreturn
 
-#endif /* _ASM_SECCOMP_H */
+#endif /* ASM_X86__SECCOMP_64_H */
diff --git a/include/asm-x86/segment.h b/include/asm-x86/segment.h
index 646452e..ea5f0a8 100644
--- a/include/asm-x86/segment.h
+++ b/include/asm-x86/segment.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SEGMENT_H_
-#define _ASM_X86_SEGMENT_H_
+#ifndef ASM_X86__SEGMENT_H
+#define ASM_X86__SEGMENT_H
 
 /* Constructor for a conventional segment GDT (or LDT) entry */
 /* This is a macro so it can be used in initializers */
@@ -212,4 +212,4 @@
 #endif
 #endif
 
-#endif
+#endif /* ASM_X86__SEGMENT_H */
diff --git a/include/asm-x86/sembuf.h b/include/asm-x86/sembuf.h
index ee50c80..81f06b7 100644
--- a/include/asm-x86/sembuf.h
+++ b/include/asm-x86/sembuf.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SEMBUF_H
-#define _ASM_X86_SEMBUF_H
+#ifndef ASM_X86__SEMBUF_H
+#define ASM_X86__SEMBUF_H
 
 /*
  * The semid64_ds structure for x86 architecture.
@@ -21,4 +21,4 @@
 	unsigned long	__unused4;
 };
 
-#endif /* _ASM_X86_SEMBUF_H */
+#endif /* ASM_X86__SEMBUF_H */
diff --git a/include/asm-x86/serial.h b/include/asm-x86/serial.h
index 628c801..303660b 100644
--- a/include/asm-x86/serial.h
+++ b/include/asm-x86/serial.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SERIAL_H
-#define _ASM_X86_SERIAL_H
+#ifndef ASM_X86__SERIAL_H
+#define ASM_X86__SERIAL_H
 
 /*
  * This assumes you have a 1.8432 MHz clock for your UART.
@@ -26,4 +26,4 @@
 	{ 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },	/* ttyS2 */	\
 	{ 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },	/* ttyS3 */
 
-#endif /* _ASM_X86_SERIAL_H */
+#endif /* ASM_X86__SERIAL_H */
diff --git a/include/asm-x86/setup.h b/include/asm-x86/setup.h
index a07c6f1..9030cb7 100644
--- a/include/asm-x86/setup.h
+++ b/include/asm-x86/setup.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SETUP_H
-#define _ASM_X86_SETUP_H
+#ifndef ASM_X86__SETUP_H
+#define ASM_X86__SETUP_H
 
 #define COMMAND_LINE_SIZE 2048
 
@@ -41,6 +41,7 @@
 };
 
 extern struct x86_quirks *x86_quirks;
+extern unsigned long saved_video_mode;
 
 #ifndef CONFIG_PARAVIRT
 #define paravirt_post_allocator_init()	do {} while (0)
@@ -100,4 +101,4 @@
 #endif /* __ASSEMBLY__ */
 #endif  /*  __KERNEL__  */
 
-#endif /* _ASM_X86_SETUP_H */
+#endif /* ASM_X86__SETUP_H */
diff --git a/include/asm-x86/shmbuf.h b/include/asm-x86/shmbuf.h
index b51413b..f51aec2 100644
--- a/include/asm-x86/shmbuf.h
+++ b/include/asm-x86/shmbuf.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SHMBUF_H
-#define _ASM_X86_SHMBUF_H
+#ifndef ASM_X86__SHMBUF_H
+#define ASM_X86__SHMBUF_H
 
 /*
  * The shmid64_ds structure for x86 architecture.
@@ -48,4 +48,4 @@
 	unsigned long	__unused4;
 };
 
-#endif /* _ASM_X86_SHMBUF_H */
+#endif /* ASM_X86__SHMBUF_H */
diff --git a/include/asm-x86/shmparam.h b/include/asm-x86/shmparam.h
index 0880cf0..a83a1fd 100644
--- a/include/asm-x86/shmparam.h
+++ b/include/asm-x86/shmparam.h
@@ -1,6 +1,6 @@
-#ifndef _ASM_X86_SHMPARAM_H
-#define _ASM_X86_SHMPARAM_H
+#ifndef ASM_X86__SHMPARAM_H
+#define ASM_X86__SHMPARAM_H
 
 #define SHMLBA PAGE_SIZE	 /* attach addr a multiple of this */
 
-#endif /* _ASM_X86_SHMPARAM_H */
+#endif /* ASM_X86__SHMPARAM_H */
diff --git a/include/asm-x86/sigcontext.h b/include/asm-x86/sigcontext.h
index 2f9c884..24879c8 100644
--- a/include/asm-x86/sigcontext.h
+++ b/include/asm-x86/sigcontext.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SIGCONTEXT_H
-#define _ASM_X86_SIGCONTEXT_H
+#ifndef ASM_X86__SIGCONTEXT_H
+#define ASM_X86__SIGCONTEXT_H
 
 #include <linux/compiler.h>
 #include <asm/types.h>
@@ -202,4 +202,4 @@
 
 #endif /* !__i386__ */
 
-#endif
+#endif /* ASM_X86__SIGCONTEXT_H */
diff --git a/include/asm-x86/sigcontext32.h b/include/asm-x86/sigcontext32.h
index 57a9686..4e2ec73 100644
--- a/include/asm-x86/sigcontext32.h
+++ b/include/asm-x86/sigcontext32.h
@@ -1,5 +1,5 @@
-#ifndef _SIGCONTEXT32_H
-#define _SIGCONTEXT32_H 1
+#ifndef ASM_X86__SIGCONTEXT32_H
+#define ASM_X86__SIGCONTEXT32_H
 
 /* signal context for 32bit programs. */
 
@@ -68,4 +68,4 @@
        unsigned int cr2;
 };
 
-#endif
+#endif /* ASM_X86__SIGCONTEXT32_H */
diff --git a/include/asm-x86/siginfo.h b/include/asm-x86/siginfo.h
index a477bea..808bdfb 100644
--- a/include/asm-x86/siginfo.h
+++ b/include/asm-x86/siginfo.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SIGINFO_H
-#define _ASM_X86_SIGINFO_H
+#ifndef ASM_X86__SIGINFO_H
+#define ASM_X86__SIGINFO_H
 
 #ifdef __x86_64__
 # define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
@@ -7,4 +7,4 @@
 
 #include <asm-generic/siginfo.h>
 
-#endif
+#endif /* ASM_X86__SIGINFO_H */
diff --git a/include/asm-x86/signal.h b/include/asm-x86/signal.h
index 6dac493..65acc82 100644
--- a/include/asm-x86/signal.h
+++ b/include/asm-x86/signal.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SIGNAL_H
-#define _ASM_X86_SIGNAL_H
+#ifndef ASM_X86__SIGNAL_H
+#define ASM_X86__SIGNAL_H
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
@@ -140,6 +140,9 @@
 struct k_sigaction {
 	struct sigaction sa;
 };
+
+extern void do_notify_resume(struct pt_regs *, void *, __u32);
+
 # else /* __KERNEL__ */
 /* Here we must cater to libcs that poke about in kernel headers.  */
 
@@ -256,4 +259,4 @@
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 
-#endif
+#endif /* ASM_X86__SIGNAL_H */
diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h
index 3c877f7..04f84f4 100644
--- a/include/asm-x86/smp.h
+++ b/include/asm-x86/smp.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SMP_H_
-#define _ASM_X86_SMP_H_
+#ifndef ASM_X86__SMP_H
+#define ASM_X86__SMP_H
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
 #include <linux/init.h>
@@ -34,6 +34,9 @@
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
+#ifdef CONFIG_X86_32
+DECLARE_PER_CPU(int, cpu_number);
+#endif
 
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
@@ -142,7 +145,6 @@
  * from the initial startup. We map APIC_BASE very early in page_setup(),
  * so this is correct in the x86 case.
  */
-DECLARE_PER_CPU(int, cpu_number);
 #define raw_smp_processor_id() (x86_read_percpu(cpu_number))
 extern int safe_smp_processor_id(void);
 
@@ -205,4 +207,4 @@
 #endif
 
 #endif /* __ASSEMBLY__ */
-#endif
+#endif /* ASM_X86__SMP_H */
diff --git a/include/asm-x86/socket.h b/include/asm-x86/socket.h
index 80af9c4..db73274 100644
--- a/include/asm-x86/socket.h
+++ b/include/asm-x86/socket.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_SOCKET_H
-#define _ASM_SOCKET_H
+#ifndef ASM_X86__SOCKET_H
+#define ASM_X86__SOCKET_H
 
 #include <asm/sockios.h>
 
@@ -54,4 +54,4 @@
 
 #define SO_MARK			36
 
-#endif /* _ASM_SOCKET_H */
+#endif /* ASM_X86__SOCKET_H */
diff --git a/include/asm-x86/sockios.h b/include/asm-x86/sockios.h
index 49cc72b..a006704 100644
--- a/include/asm-x86/sockios.h
+++ b/include/asm-x86/sockios.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SOCKIOS_H
-#define _ASM_X86_SOCKIOS_H
+#ifndef ASM_X86__SOCKIOS_H
+#define ASM_X86__SOCKIOS_H
 
 /* Socket-level I/O control calls. */
 #define FIOSETOWN	0x8901
@@ -10,4 +10,4 @@
 #define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
 #define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
 
-#endif /* _ASM_X86_SOCKIOS_H */
+#endif /* ASM_X86__SOCKIOS_H */
diff --git a/include/asm-x86/sparsemem.h b/include/asm-x86/sparsemem.h
index 9bd48b0..38f8e6b 100644
--- a/include/asm-x86/sparsemem.h
+++ b/include/asm-x86/sparsemem.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SPARSEMEM_H
-#define _ASM_X86_SPARSEMEM_H
+#ifndef ASM_X86__SPARSEMEM_H
+#define ASM_X86__SPARSEMEM_H
 
 #ifdef CONFIG_SPARSEMEM
 /*
@@ -31,4 +31,4 @@
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
-#endif
+#endif /* ASM_X86__SPARSEMEM_H */
diff --git a/include/asm-x86/spinlock.h b/include/asm-x86/spinlock.h
index e39c790..93adae3 100644
--- a/include/asm-x86/spinlock.h
+++ b/include/asm-x86/spinlock.h
@@ -1,5 +1,5 @@
-#ifndef _X86_SPINLOCK_H_
-#define _X86_SPINLOCK_H_
+#ifndef ASM_X86__SPINLOCK_H
+#define ASM_X86__SPINLOCK_H
 
 #include <asm/atomic.h>
 #include <asm/rwlock.h>
@@ -97,7 +97,7 @@
 		     "jne 1f\n\t"
 		     "movw %w0,%w1\n\t"
 		     "incb %h1\n\t"
-		     "lock ; cmpxchgw %w1,%2\n\t"
+		     LOCK_PREFIX "cmpxchgw %w1,%2\n\t"
 		     "1:"
 		     "sete %b1\n\t"
 		     "movzbl %b1,%0\n\t"
@@ -135,7 +135,7 @@
 	int inc = 0x00010000;
 	int tmp;
 
-	asm volatile("lock ; xaddl %0, %1\n"
+	asm volatile(LOCK_PREFIX "xaddl %0, %1\n"
 		     "movzwl %w0, %2\n\t"
 		     "shrl $16, %0\n\t"
 		     "1:\t"
@@ -162,7 +162,7 @@
 		     "cmpl %0,%1\n\t"
 		     "jne 1f\n\t"
 		     "addl $0x00010000, %1\n\t"
-		     "lock ; cmpxchgl %1,%2\n\t"
+		     LOCK_PREFIX "cmpxchgl %1,%2\n\t"
 		     "1:"
 		     "sete %b1\n\t"
 		     "movzbl %b1,%0\n\t"
@@ -366,4 +366,4 @@
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()
 
-#endif
+#endif /* ASM_X86__SPINLOCK_H */
diff --git a/include/asm-x86/spinlock_types.h b/include/asm-x86/spinlock_types.h
index 06c071c..6aa9b56 100644
--- a/include/asm-x86/spinlock_types.h
+++ b/include/asm-x86/spinlock_types.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_SPINLOCK_TYPES_H
-#define __ASM_SPINLOCK_TYPES_H
+#ifndef ASM_X86__SPINLOCK_TYPES_H
+#define ASM_X86__SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_H
 # error "please don't include this file directly"
@@ -17,4 +17,4 @@
 
 #define __RAW_RW_LOCK_UNLOCKED		{ RW_LOCK_BIAS }
 
-#endif
+#endif /* ASM_X86__SPINLOCK_TYPES_H */
diff --git a/include/asm-x86/srat.h b/include/asm-x86/srat.h
index 774c919..5363e4f 100644
--- a/include/asm-x86/srat.h
+++ b/include/asm-x86/srat.h
@@ -24,8 +24,8 @@
  * Send feedback to Pat Gaughen <gone@us.ibm.com>
  */
 
-#ifndef _ASM_SRAT_H_
-#define _ASM_SRAT_H_
+#ifndef ASM_X86__SRAT_H
+#define ASM_X86__SRAT_H
 
 #ifdef CONFIG_ACPI_NUMA
 extern int get_memcfg_from_srat(void);
@@ -36,4 +36,4 @@
 }
 #endif
 
-#endif /* _ASM_SRAT_H_ */
+#endif /* ASM_X86__SRAT_H */
diff --git a/include/asm-x86/stacktrace.h b/include/asm-x86/stacktrace.h
index 30f8252..f43517e 100644
--- a/include/asm-x86/stacktrace.h
+++ b/include/asm-x86/stacktrace.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_STACKTRACE_H
-#define _ASM_STACKTRACE_H 1
+#ifndef ASM_X86__STACKTRACE_H
+#define ASM_X86__STACKTRACE_H
 
 extern int kstack_depth_to_print;
 
@@ -18,4 +18,4 @@
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data);
 
-#endif
+#endif /* ASM_X86__STACKTRACE_H */
diff --git a/include/asm-x86/stat.h b/include/asm-x86/stat.h
index 5c22dcb..1e120f6 100644
--- a/include/asm-x86/stat.h
+++ b/include/asm-x86/stat.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_STAT_H
-#define _ASM_X86_STAT_H
+#ifndef ASM_X86__STAT_H
+#define ASM_X86__STAT_H
 
 #define STAT_HAVE_NSEC 1
 
@@ -111,4 +111,4 @@
 #endif
 };
 
-#endif
+#endif /* ASM_X86__STAT_H */
diff --git a/include/asm-x86/statfs.h b/include/asm-x86/statfs.h
index 7c651aa..3f005bc 100644
--- a/include/asm-x86/statfs.h
+++ b/include/asm-x86/statfs.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_STATFS_H
-#define _ASM_X86_STATFS_H
+#ifndef ASM_X86__STATFS_H
+#define ASM_X86__STATFS_H
 
 #ifdef __i386__
 #include <asm-generic/statfs.h>
@@ -60,4 +60,4 @@
 } __attribute__((packed));
 
 #endif /* !__i386__ */
-#endif
+#endif /* ASM_X86__STATFS_H */
diff --git a/include/asm-x86/string_32.h b/include/asm-x86/string_32.h
index 193578c..487843e 100644
--- a/include/asm-x86/string_32.h
+++ b/include/asm-x86/string_32.h
@@ -1,5 +1,5 @@
-#ifndef _I386_STRING_H_
-#define _I386_STRING_H_
+#ifndef ASM_X86__STRING_32_H
+#define ASM_X86__STRING_32_H
 
 #ifdef __KERNEL__
 
@@ -323,4 +323,4 @@
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__STRING_32_H */
diff --git a/include/asm-x86/string_64.h b/include/asm-x86/string_64.h
index 52b5ab3..a2add11d 100644
--- a/include/asm-x86/string_64.h
+++ b/include/asm-x86/string_64.h
@@ -1,5 +1,5 @@
-#ifndef _X86_64_STRING_H_
-#define _X86_64_STRING_H_
+#ifndef ASM_X86__STRING_64_H
+#define ASM_X86__STRING_64_H
 
 #ifdef __KERNEL__
 
@@ -57,4 +57,4 @@
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__STRING_64_H */
diff --git a/include/asm-x86/suspend_32.h b/include/asm-x86/suspend_32.h
index 8675c67..acb6d4d 100644
--- a/include/asm-x86/suspend_32.h
+++ b/include/asm-x86/suspend_32.h
@@ -3,8 +3,8 @@
  * Based on code
  * Copyright 2001 Patrick Mochel <mochel@osdl.org>
  */
-#ifndef __ASM_X86_32_SUSPEND_H
-#define __ASM_X86_32_SUSPEND_H
+#ifndef ASM_X86__SUSPEND_32_H
+#define ASM_X86__SUSPEND_32_H
 
 #include <asm/desc.h>
 #include <asm/i387.h>
@@ -48,4 +48,4 @@
 extern int acpi_save_state_mem(void);
 #endif
 
-#endif /* __ASM_X86_32_SUSPEND_H */
+#endif /* ASM_X86__SUSPEND_32_H */
diff --git a/include/asm-x86/suspend_64.h b/include/asm-x86/suspend_64.h
index dc3262b..cf821dd 100644
--- a/include/asm-x86/suspend_64.h
+++ b/include/asm-x86/suspend_64.h
@@ -3,8 +3,8 @@
  * Based on code
  * Copyright 2001 Patrick Mochel <mochel@osdl.org>
  */
-#ifndef __ASM_X86_64_SUSPEND_H
-#define __ASM_X86_64_SUSPEND_H
+#ifndef ASM_X86__SUSPEND_64_H
+#define ASM_X86__SUSPEND_64_H
 
 #include <asm/desc.h>
 #include <asm/i387.h>
@@ -49,4 +49,4 @@
 extern char core_restore_code;
 extern char restore_registers;
 
-#endif /* __ASM_X86_64_SUSPEND_H */
+#endif /* ASM_X86__SUSPEND_64_H */
diff --git a/include/asm-x86/swiotlb.h b/include/asm-x86/swiotlb.h
index 2730b35..1e20adb 100644
--- a/include/asm-x86/swiotlb.h
+++ b/include/asm-x86/swiotlb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_SWIOTLB_H
-#define _ASM_SWIOTLB_H 1
+#ifndef ASM_X86__SWIOTLB_H
+#define ASM_X86__SWIOTLB_H
 
 #include <asm/dma-mapping.h>
 
@@ -55,4 +55,4 @@
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
 
-#endif /* _ASM_SWIOTLB_H */
+#endif /* ASM_X86__SWIOTLB_H */
diff --git a/include/asm-x86/sync_bitops.h b/include/asm-x86/sync_bitops.h
index b47a1d0..b689bee 100644
--- a/include/asm-x86/sync_bitops.h
+++ b/include/asm-x86/sync_bitops.h
@@ -1,5 +1,5 @@
-#ifndef _I386_SYNC_BITOPS_H
-#define _I386_SYNC_BITOPS_H
+#ifndef ASM_X86__SYNC_BITOPS_H
+#define ASM_X86__SYNC_BITOPS_H
 
 /*
  * Copyright 1992, Linus Torvalds.
@@ -127,4 +127,4 @@
 
 #undef ADDR
 
-#endif /* _I386_SYNC_BITOPS_H */
+#endif /* ASM_X86__SYNC_BITOPS_H */
diff --git a/include/asm-x86/syscall.h b/include/asm-x86/syscall.h
new file mode 100644
index 0000000..04c47dc
--- /dev/null
+++ b/include/asm-x86/syscall.h
@@ -0,0 +1,211 @@
+/*
+ * Access to user system call parameters and results
+ *
+ * Copyright (C) 2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_SYSCALL_H
+#define _ASM_SYSCALL_H	1
+
+#include <linux/sched.h>
+#include <linux/err.h>
+
+static inline long syscall_get_nr(struct task_struct *task,
+				  struct pt_regs *regs)
+{
+	/*
+	 * We always sign-extend a -1 value being set here,
+	 * so this is always either -1L or a syscall number.
+	 */
+	return regs->orig_ax;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	regs->ax = regs->orig_ax;
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	unsigned long error = regs->ax;
+#ifdef CONFIG_IA32_EMULATION
+	/*
+	 * TS_COMPAT is set for 32-bit syscall entries and then
+	 * remains set until we return to user mode.
+	 */
+	if (task_thread_info(task)->status & TS_COMPAT)
+		/*
+		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
+		 * and will match correctly in comparisons.
+		 */
+		error = (long) (int) error;
+#endif
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->ax;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	regs->ax = (long) error ?: val;
+}
+
+#ifdef CONFIG_X86_32
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+	BUG_ON(i + n > 6);
+	memcpy(args, &regs->bx + i, n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	BUG_ON(i + n > 6);
+	memcpy(&regs->bx + i, args, n * sizeof(args[0]));
+}
+
+#else	 /* CONFIG_X86_64 */
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+# ifdef CONFIG_IA32_EMULATION
+	if (task_thread_info(task)->status & TS_COMPAT)
+		switch (i + n) {
+		case 6:
+			if (!n--) break;
+			*args++ = regs->bp;
+		case 5:
+			if (!n--) break;
+			*args++ = regs->di;
+		case 4:
+			if (!n--) break;
+			*args++ = regs->si;
+		case 3:
+			if (!n--) break;
+			*args++ = regs->dx;
+		case 2:
+			if (!n--) break;
+			*args++ = regs->cx;
+		case 1:
+			if (!n--) break;
+			*args++ = regs->bx;
+		case 0:
+			if (!n--) break;
+		default:
+			BUG();
+			break;
+		}
+	else
+# endif
+		switch (i + n) {
+		case 6:
+			if (!n--) break;
+			*args++ = regs->r9;
+		case 5:
+			if (!n--) break;
+			*args++ = regs->r8;
+		case 4:
+			if (!n--) break;
+			*args++ = regs->r10;
+		case 3:
+			if (!n--) break;
+			*args++ = regs->dx;
+		case 2:
+			if (!n--) break;
+			*args++ = regs->si;
+		case 1:
+			if (!n--) break;
+			*args++ = regs->di;
+		case 0:
+			if (!n--) break;
+		default:
+			BUG();
+			break;
+		}
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+# ifdef CONFIG_IA32_EMULATION
+	if (task_thread_info(task)->status & TS_COMPAT)
+		switch (i + n) {
+		case 6:
+			if (!n--) break;
+			regs->bp = *args++;
+		case 5:
+			if (!n--) break;
+			regs->di = *args++;
+		case 4:
+			if (!n--) break;
+			regs->si = *args++;
+		case 3:
+			if (!n--) break;
+			regs->dx = *args++;
+		case 2:
+			if (!n--) break;
+			regs->cx = *args++;
+		case 1:
+			if (!n--) break;
+			regs->bx = *args++;
+		case 0:
+			if (!n--) break;
+		default:
+			BUG();
+		}
+	else
+# endif
+		switch (i + n) {
+		case 6:
+			if (!n--) break;
+			regs->r9 = *args++;
+		case 5:
+			if (!n--) break;
+			regs->r8 = *args++;
+		case 4:
+			if (!n--) break;
+			regs->r10 = *args++;
+		case 3:
+			if (!n--) break;
+			regs->dx = *args++;
+		case 2:
+			if (!n--) break;
+			regs->si = *args++;
+		case 1:
+			if (!n--) break;
+			regs->di = *args++;
+		case 0:
+			if (!n--) break;
+		default:
+			BUG();
+		}
+}
+
+#endif	/* CONFIG_X86_32 */
+
+#endif	/* _ASM_SYSCALL_H */
diff --git a/include/asm-x86/syscalls.h b/include/asm-x86/syscalls.h
new file mode 100644
index 0000000..87803da
--- /dev/null
+++ b/include/asm-x86/syscalls.h
@@ -0,0 +1,93 @@
+/*
+ * syscalls.h - Linux syscall interfaces (arch-specific)
+ *
+ * Copyright (c) 2008 Jaswinder Singh
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#ifndef _ASM_X86_SYSCALLS_H
+#define _ASM_X86_SYSCALLS_H
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <linux/signal.h>
+
+/* Common in X86_32 and X86_64 */
+/* kernel/ioport.c */
+asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
+
+/* X86_32 only */
+#ifdef CONFIG_X86_32
+/* kernel/process_32.c */
+asmlinkage int sys_fork(struct pt_regs);
+asmlinkage int sys_clone(struct pt_regs);
+asmlinkage int sys_vfork(struct pt_regs);
+asmlinkage int sys_execve(struct pt_regs);
+
+/* kernel/signal_32.c */
+asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
+asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
+			     struct old_sigaction __user *);
+asmlinkage int sys_sigaltstack(unsigned long);
+asmlinkage unsigned long sys_sigreturn(unsigned long);
+asmlinkage int sys_rt_sigreturn(unsigned long);
+
+/* kernel/ioport.c */
+asmlinkage long sys_iopl(unsigned long);
+
+/* kernel/ldt.c */
+asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
+
+/* kernel/sys_i386_32.c */
+asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
+			  unsigned long, unsigned long, unsigned long);
+struct mmap_arg_struct;
+asmlinkage int old_mmap(struct mmap_arg_struct __user *);
+struct sel_arg_struct;
+asmlinkage int old_select(struct sel_arg_struct __user *);
+asmlinkage int sys_ipc(uint, int, int, int, void __user *, long);
+struct old_utsname;
+asmlinkage int sys_uname(struct old_utsname __user *);
+struct oldold_utsname;
+asmlinkage int sys_olduname(struct oldold_utsname __user *);
+
+/* kernel/tls.c */
+asmlinkage int sys_set_thread_area(struct user_desc __user *);
+asmlinkage int sys_get_thread_area(struct user_desc __user *);
+
+/* kernel/vm86_32.c */
+asmlinkage int sys_vm86old(struct pt_regs);
+asmlinkage int sys_vm86(struct pt_regs);
+
+#else /* CONFIG_X86_32 */
+
+/* X86_64 only */
+/* kernel/process_64.c */
+asmlinkage long sys_fork(struct pt_regs *);
+asmlinkage long sys_clone(unsigned long, unsigned long,
+			  void __user *, void __user *,
+			  struct pt_regs *);
+asmlinkage long sys_vfork(struct pt_regs *);
+asmlinkage long sys_execve(char __user *, char __user * __user *,
+			   char __user * __user *,
+			   struct pt_regs *);
+
+/* kernel/ioport.c */
+asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
+
+/* kernel/signal_64.c */
+asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
+				struct pt_regs *);
+asmlinkage long sys_rt_sigreturn(struct pt_regs *);
+
+/* kernel/sys_x86_64.c */
+asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
+			 unsigned long, unsigned long, unsigned long);
+struct new_utsname;
+asmlinkage long sys_uname(struct new_utsname __user *);
+
+#endif /* CONFIG_X86_32 */
+#endif /* _ASM_X86_SYSCALLS_H */
diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h
index 983ce37..34505dd 100644
--- a/include/asm-x86/system.h
+++ b/include/asm-x86/system.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SYSTEM_H_
-#define _ASM_X86_SYSTEM_H_
+#ifndef ASM_X86__SYSTEM_H
+#define ASM_X86__SYSTEM_H
 
 #include <asm/asm.h>
 #include <asm/segment.h>
@@ -419,4 +419,4 @@
 	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
 }
 
-#endif
+#endif /* ASM_X86__SYSTEM_H */
diff --git a/include/asm-x86/system_64.h b/include/asm-x86/system_64.h
index 97fa251..5aedb8b 100644
--- a/include/asm-x86/system_64.h
+++ b/include/asm-x86/system_64.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_SYSTEM_H
-#define __ASM_SYSTEM_H
+#ifndef ASM_X86__SYSTEM_64_H
+#define ASM_X86__SYSTEM_64_H
 
 #include <asm/segment.h>
 #include <asm/cmpxchg.h>
@@ -19,4 +19,4 @@
 
 #include <linux/irqflags.h>
 
-#endif
+#endif /* ASM_X86__SYSTEM_64_H */
diff --git a/include/asm-x86/tce.h b/include/asm-x86/tce.h
index b1a4ea0..e7932d7 100644
--- a/include/asm-x86/tce.h
+++ b/include/asm-x86/tce.h
@@ -21,8 +21,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef _ASM_X86_64_TCE_H
-#define _ASM_X86_64_TCE_H
+#ifndef ASM_X86__TCE_H
+#define ASM_X86__TCE_H
 
 extern unsigned int specified_table_size;
 struct iommu_table;
@@ -45,4 +45,4 @@
 extern void __init free_tce_table(void *tbl);
 extern int __init build_tce_table(struct pci_dev *dev, void __iomem *bbar);
 
-#endif /* _ASM_X86_64_TCE_H */
+#endif /* ASM_X86__TCE_H */
diff --git a/include/asm-x86/termbits.h b/include/asm-x86/termbits.h
index af1b70e..3d00dc5 100644
--- a/include/asm-x86/termbits.h
+++ b/include/asm-x86/termbits.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TERMBITS_H
-#define _ASM_X86_TERMBITS_H
+#ifndef ASM_X86__TERMBITS_H
+#define ASM_X86__TERMBITS_H
 
 #include <linux/posix_types.h>
 
@@ -195,4 +195,4 @@
 #define	TCSADRAIN	1
 #define	TCSAFLUSH	2
 
-#endif /* _ASM_X86_TERMBITS_H */
+#endif /* ASM_X86__TERMBITS_H */
diff --git a/include/asm-x86/termios.h b/include/asm-x86/termios.h
index f729563..e235db2 100644
--- a/include/asm-x86/termios.h
+++ b/include/asm-x86/termios.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TERMIOS_H
-#define _ASM_X86_TERMIOS_H
+#ifndef ASM_X86__TERMIOS_H
+#define ASM_X86__TERMIOS_H
 
 #include <asm/termbits.h>
 #include <asm/ioctls.h>
@@ -110,4 +110,4 @@
 
 #endif	/* __KERNEL__ */
 
-#endif /* _ASM_X86_TERMIOS_H */
+#endif /* ASM_X86__TERMIOS_H */
diff --git a/include/asm-x86/therm_throt.h b/include/asm-x86/therm_throt.h
index 399bf60..1c7f57b 100644
--- a/include/asm-x86/therm_throt.h
+++ b/include/asm-x86/therm_throt.h
@@ -1,9 +1,9 @@
-#ifndef __ASM_I386_THERM_THROT_H__
-#define __ASM_I386_THERM_THROT_H__ 1
+#ifndef ASM_X86__THERM_THROT_H
+#define ASM_X86__THERM_THROT_H
 
 #include <asm/atomic.h>
 
 extern atomic_t therm_throt_en;
 int therm_throt_process(int curr);
 
-#endif /* __ASM_I386_THERM_THROT_H__ */
+#endif /* ASM_X86__THERM_THROT_H */
diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h
index da0a675..4db0066 100644
--- a/include/asm-x86/thread_info.h
+++ b/include/asm-x86/thread_info.h
@@ -4,8 +4,8 @@
  * - Incorporating suggestions made by Linus Torvalds and Dave Miller
  */
 
-#ifndef _ASM_X86_THREAD_INFO_H
-#define _ASM_X86_THREAD_INFO_H
+#ifndef ASM_X86__THREAD_INFO_H
+#define ASM_X86__THREAD_INFO_H
 
 #include <linux/compiler.h>
 #include <asm/page.h>
@@ -71,6 +71,7 @@
  * Warning: layout of LSW is hardcoded in entry.S
  */
 #define TIF_SYSCALL_TRACE	0	/* syscall trace active */
+#define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
 #define TIF_SIGPENDING		2	/* signal pending */
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
 #define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
@@ -93,6 +94,7 @@
 #define TIF_BTS_TRACE_TS	27      /* record scheduling event timestamps */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
@@ -133,7 +135,7 @@
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
-	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY)
+	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
@@ -258,4 +260,4 @@
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #define arch_task_cache_init arch_task_cache_init
 #endif
-#endif /* _ASM_X86_THREAD_INFO_H */
+#endif /* ASM_X86__THREAD_INFO_H */
diff --git a/include/asm-x86/time.h b/include/asm-x86/time.h
index a17fa47..3e724ee 100644
--- a/include/asm-x86/time.h
+++ b/include/asm-x86/time.h
@@ -1,5 +1,5 @@
-#ifndef _ASMX86_TIME_H
-#define _ASMX86_TIME_H
+#ifndef ASM_X86__TIME_H
+#define ASM_X86__TIME_H
 
 extern void hpet_time_init(void);
 
@@ -46,6 +46,8 @@
 
 #endif
 
+extern void time_init(void);
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else /* !CONFIG_PARAVIRT */
@@ -58,4 +60,4 @@
 
 extern unsigned long __init calibrate_cpu(void);
 
-#endif
+#endif /* ASM_X86__TIME_H */
diff --git a/include/asm-x86/timer.h b/include/asm-x86/timer.h
index fb2a4dd..d0babce 100644
--- a/include/asm-x86/timer.h
+++ b/include/asm-x86/timer.h
@@ -1,5 +1,5 @@
-#ifndef _ASMi386_TIMER_H
-#define _ASMi386_TIMER_H
+#ifndef ASM_X86__TIMER_H
+#define ASM_X86__TIMER_H
 #include <linux/init.h>
 #include <linux/pm.h>
 #include <linux/percpu.h>
@@ -9,9 +9,12 @@
 unsigned long long native_sched_clock(void);
 unsigned long native_calibrate_tsc(void);
 
+#ifdef CONFIG_X86_32
 extern int timer_ack;
-extern int no_timer_check;
 extern int recalibrate_cpu_khz(void);
+#endif /* CONFIG_X86_32 */
+
+extern int no_timer_check;
 
 #ifndef CONFIG_PARAVIRT
 #define calibrate_tsc() native_calibrate_tsc()
@@ -60,4 +63,4 @@
 	return ns;
 }
 
-#endif
+#endif /* ASM_X86__TIMER_H */
diff --git a/include/asm-x86/timex.h b/include/asm-x86/timex.h
index 43e5a78..d1ce241 100644
--- a/include/asm-x86/timex.h
+++ b/include/asm-x86/timex.h
@@ -1,6 +1,6 @@
 /* x86 architecture timex specifications */
-#ifndef _ASM_X86_TIMEX_H
-#define _ASM_X86_TIMEX_H
+#ifndef ASM_X86__TIMEX_H
+#define ASM_X86__TIMEX_H
 
 #include <asm/processor.h>
 #include <asm/tsc.h>
@@ -16,4 +16,4 @@
 
 #define ARCH_HAS_READ_CURRENT_TIMER
 
-#endif
+#endif /* ASM_X86__TIMEX_H */
diff --git a/include/asm-x86/tlb.h b/include/asm-x86/tlb.h
index e4e9e2d..db36e9e 100644
--- a/include/asm-x86/tlb.h
+++ b/include/asm-x86/tlb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TLB_H
-#define _ASM_X86_TLB_H
+#ifndef ASM_X86__TLB_H
+#define ASM_X86__TLB_H
 
 #define tlb_start_vma(tlb, vma) do { } while (0)
 #define tlb_end_vma(tlb, vma) do { } while (0)
@@ -8,4 +8,4 @@
 
 #include <asm-generic/tlb.h>
 
-#endif
+#endif /* ASM_X86__TLB_H */
diff --git a/include/asm-x86/tlbflush.h b/include/asm-x86/tlbflush.h
index 35c76ce..ef68b76 100644
--- a/include/asm-x86/tlbflush.h
+++ b/include/asm-x86/tlbflush.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TLBFLUSH_H
-#define _ASM_X86_TLBFLUSH_H
+#ifndef ASM_X86__TLBFLUSH_H
+#define ASM_X86__TLBFLUSH_H
 
 #include <linux/mm.h>
 #include <linux/sched.h>
@@ -165,4 +165,4 @@
 	flush_tlb_all();
 }
 
-#endif /* _ASM_X86_TLBFLUSH_H */
+#endif /* ASM_X86__TLBFLUSH_H */
diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
index 90ac771..7eca9bc 100644
--- a/include/asm-x86/topology.h
+++ b/include/asm-x86/topology.h
@@ -22,8 +22,8 @@
  *
  * Send feedback to <colpatch@us.ibm.com>
  */
-#ifndef _ASM_X86_TOPOLOGY_H
-#define _ASM_X86_TOPOLOGY_H
+#ifndef ASM_X86__TOPOLOGY_H
+#define ASM_X86__TOPOLOGY_H
 
 #ifdef CONFIG_X86_32
 # ifdef CONFIG_X86_HT
@@ -255,4 +255,4 @@
 }
 #endif
 
-#endif /* _ASM_X86_TOPOLOGY_H */
+#endif /* ASM_X86__TOPOLOGY_H */
diff --git a/include/asm-x86/trampoline.h b/include/asm-x86/trampoline.h
index b156b08..0406bbd 100644
--- a/include/asm-x86/trampoline.h
+++ b/include/asm-x86/trampoline.h
@@ -1,5 +1,5 @@
-#ifndef __TRAMPOLINE_HEADER
-#define __TRAMPOLINE_HEADER
+#ifndef ASM_X86__TRAMPOLINE_H
+#define ASM_X86__TRAMPOLINE_H
 
 #ifndef __ASSEMBLY__
 
@@ -18,4 +18,4 @@
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* __TRAMPOLINE_HEADER */
+#endif /* ASM_X86__TRAMPOLINE_H */
diff --git a/include/asm-x86/traps.h b/include/asm-x86/traps.h
index a4b65a7..2ccebc6 100644
--- a/include/asm-x86/traps.h
+++ b/include/asm-x86/traps.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TRAPS_H
-#define _ASM_X86_TRAPS_H
+#ifndef ASM_X86__TRAPS_H
+#define ASM_X86__TRAPS_H
 
 /* Common in X86_32 and X86_64 */
 asmlinkage void divide_error(void);
@@ -51,6 +51,8 @@
 unsigned long patch_espfix_desc(unsigned long, unsigned long);
 asmlinkage void math_emulate(long);
 
+void do_page_fault(struct pt_regs *regs, unsigned long error_code);
+
 #else /* CONFIG_X86_32 */
 
 asmlinkage void double_fault(void);
@@ -62,5 +64,7 @@
 asmlinkage void do_simd_coprocessor_error(struct pt_regs *);
 asmlinkage void do_spurious_interrupt_bug(struct pt_regs *);
 
+asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code);
+
 #endif /* CONFIG_X86_32 */
-#endif /* _ASM_X86_TRAPS_H */
+#endif /* ASM_X86__TRAPS_H */
diff --git a/include/asm-x86/tsc.h b/include/asm-x86/tsc.h
index cb6f6ee..ad0f5c4 100644
--- a/include/asm-x86/tsc.h
+++ b/include/asm-x86/tsc.h
@@ -1,8 +1,8 @@
 /*
  * x86 TSC related functions
  */
-#ifndef _ASM_X86_TSC_H
-#define _ASM_X86_TSC_H
+#ifndef ASM_X86__TSC_H
+#define ASM_X86__TSC_H
 
 #include <asm/processor.h>
 
@@ -59,4 +59,4 @@
 
 extern int notsc_setup(char *);
 
-#endif
+#endif /* ASM_X86__TSC_H */
diff --git a/include/asm-x86/types.h b/include/asm-x86/types.h
index 1ac80cd..e78b52e 100644
--- a/include/asm-x86/types.h
+++ b/include/asm-x86/types.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TYPES_H
-#define _ASM_X86_TYPES_H
+#ifndef ASM_X86__TYPES_H
+#define ASM_X86__TYPES_H
 
 #include <asm-generic/int-ll64.h>
 
@@ -33,4 +33,4 @@
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__TYPES_H */
diff --git a/include/asm-x86/uaccess.h b/include/asm-x86/uaccess.h
index 5f702d1..48ebc0a 100644
--- a/include/asm-x86/uaccess.h
+++ b/include/asm-x86/uaccess.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_UACCES_H_
-#define _ASM_UACCES_H_
+#ifndef ASM_X86__UACCESS_H
+#define ASM_X86__UACCESS_H
 /*
  * User space memory access functions
  */
@@ -450,5 +450,5 @@
 # include "uaccess_64.h"
 #endif
 
-#endif
+#endif /* ASM_X86__UACCESS_H */
 
diff --git a/include/asm-x86/uaccess_32.h b/include/asm-x86/uaccess_32.h
index 6fdef39..6b5b57d 100644
--- a/include/asm-x86/uaccess_32.h
+++ b/include/asm-x86/uaccess_32.h
@@ -1,5 +1,5 @@
-#ifndef __i386_UACCESS_H
-#define __i386_UACCESS_H
+#ifndef ASM_X86__UACCESS_32_H
+#define ASM_X86__UACCESS_32_H
 
 /*
  * User space memory access functions
@@ -215,4 +215,4 @@
 unsigned long __must_check clear_user(void __user *mem, unsigned long len);
 unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
 
-#endif /* __i386_UACCESS_H */
+#endif /* ASM_X86__UACCESS_32_H */
diff --git a/include/asm-x86/uaccess_64.h b/include/asm-x86/uaccess_64.h
index 515d4dc..c96c1f5 100644
--- a/include/asm-x86/uaccess_64.h
+++ b/include/asm-x86/uaccess_64.h
@@ -1,5 +1,5 @@
-#ifndef __X86_64_UACCESS_H
-#define __X86_64_UACCESS_H
+#ifndef ASM_X86__UACCESS_64_H
+#define ASM_X86__UACCESS_64_H
 
 /*
  * User space memory access functions
@@ -7,6 +7,7 @@
 #include <linux/compiler.h>
 #include <linux/errno.h>
 #include <linux/prefetch.h>
+#include <linux/lockdep.h>
 #include <asm/page.h>
 
 /*
@@ -198,4 +199,4 @@
 unsigned long
 copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest);
 
-#endif /* __X86_64_UACCESS_H */
+#endif /* ASM_X86__UACCESS_64_H */
diff --git a/include/asm-x86/ucontext.h b/include/asm-x86/ucontext.h
index 50a79f7..9948dd3 100644
--- a/include/asm-x86/ucontext.h
+++ b/include/asm-x86/ucontext.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_UCONTEXT_H
-#define _ASM_X86_UCONTEXT_H
+#ifndef ASM_X86__UCONTEXT_H
+#define ASM_X86__UCONTEXT_H
 
 struct ucontext {
 	unsigned long	  uc_flags;
@@ -9,4 +9,4 @@
 	sigset_t	  uc_sigmask;	/* mask last for extensibility */
 };
 
-#endif /* _ASM_X86_UCONTEXT_H */
+#endif /* ASM_X86__UCONTEXT_H */
diff --git a/include/asm-x86/unaligned.h b/include/asm-x86/unaligned.h
index a7bd416..59dcdec 100644
--- a/include/asm-x86/unaligned.h
+++ b/include/asm-x86/unaligned.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_UNALIGNED_H
-#define _ASM_X86_UNALIGNED_H
+#ifndef ASM_X86__UNALIGNED_H
+#define ASM_X86__UNALIGNED_H
 
 /*
  * The x86 can do unaligned accesses itself.
@@ -11,4 +11,4 @@
 #define get_unaligned __get_unaligned_le
 #define put_unaligned __put_unaligned_le
 
-#endif /* _ASM_X86_UNALIGNED_H */
+#endif /* ASM_X86__UNALIGNED_H */
diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h
index d739467..017f4a8 100644
--- a/include/asm-x86/unistd_32.h
+++ b/include/asm-x86/unistd_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_I386_UNISTD_H_
-#define _ASM_I386_UNISTD_H_
+#ifndef ASM_X86__UNISTD_32_H
+#define ASM_X86__UNISTD_32_H
 
 /*
  * This file contains the system call numbers.
@@ -376,4 +376,4 @@
 #endif
 
 #endif /* __KERNEL__ */
-#endif /* _ASM_I386_UNISTD_H_ */
+#endif /* ASM_X86__UNISTD_32_H */
diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h
index 3a341d7..ace83f1 100644
--- a/include/asm-x86/unistd_64.h
+++ b/include/asm-x86/unistd_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_UNISTD_H_
-#define _ASM_X86_64_UNISTD_H_
+#ifndef ASM_X86__UNISTD_64_H
+#define ASM_X86__UNISTD_64_H
 
 #ifndef __SYSCALL
 #define __SYSCALL(a, b)
@@ -690,4 +690,4 @@
 #define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
 #endif	/* __KERNEL__ */
 
-#endif /* _ASM_X86_64_UNISTD_H_ */
+#endif /* ASM_X86__UNISTD_64_H */
diff --git a/include/asm-x86/unwind.h b/include/asm-x86/unwind.h
index 8b064bd..a215156 100644
--- a/include/asm-x86/unwind.h
+++ b/include/asm-x86/unwind.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_UNWIND_H
-#define _ASM_X86_UNWIND_H
+#ifndef ASM_X86__UNWIND_H
+#define ASM_X86__UNWIND_H
 
 #define UNW_PC(frame) ((void)(frame), 0UL)
 #define UNW_SP(frame) ((void)(frame), 0UL)
@@ -10,4 +10,4 @@
 	return 0;
 }
 
-#endif /* _ASM_X86_UNWIND_H */
+#endif /* ASM_X86__UNWIND_H */
diff --git a/include/asm-x86/user32.h b/include/asm-x86/user32.h
index a3d9100..aa66c18 100644
--- a/include/asm-x86/user32.h
+++ b/include/asm-x86/user32.h
@@ -1,5 +1,5 @@
-#ifndef USER32_H
-#define USER32_H 1
+#ifndef ASM_X86__USER32_H
+#define ASM_X86__USER32_H
 
 /* IA32 compatible user structures for ptrace.
  * These should be used for 32bit coredumps too. */
@@ -67,4 +67,4 @@
 };
 
 
-#endif
+#endif /* ASM_X86__USER32_H */
diff --git a/include/asm-x86/user_32.h b/include/asm-x86/user_32.h
index d6e51ed..e0fe2f5 100644
--- a/include/asm-x86/user_32.h
+++ b/include/asm-x86/user_32.h
@@ -1,5 +1,5 @@
-#ifndef _I386_USER_H
-#define _I386_USER_H
+#ifndef ASM_X86__USER_32_H
+#define ASM_X86__USER_32_H
 
 #include <asm/page.h>
 /* Core file format: The core file is written in such a way that gdb
@@ -128,4 +128,4 @@
 #define HOST_TEXT_START_ADDR (u.start_code)
 #define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
 
-#endif /* _I386_USER_H */
+#endif /* ASM_X86__USER_32_H */
diff --git a/include/asm-x86/user_64.h b/include/asm-x86/user_64.h
index 6037b63..38b5799 100644
--- a/include/asm-x86/user_64.h
+++ b/include/asm-x86/user_64.h
@@ -1,5 +1,5 @@
-#ifndef _X86_64_USER_H
-#define _X86_64_USER_H
+#ifndef ASM_X86__USER_64_H
+#define ASM_X86__USER_64_H
 
 #include <asm/types.h>
 #include <asm/page.h>
@@ -134,4 +134,4 @@
 #define HOST_TEXT_START_ADDR (u.start_code)
 #define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
 
-#endif /* _X86_64_USER_H */
+#endif /* ASM_X86__USER_64_H */
diff --git a/include/asm-x86/uv/bios.h b/include/asm-x86/uv/bios.h
index aa73362..7cd6d7e 100644
--- a/include/asm-x86/uv/bios.h
+++ b/include/asm-x86/uv/bios.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_BIOS_H
-#define _ASM_X86_BIOS_H
+#ifndef ASM_X86__UV__BIOS_H
+#define ASM_X86__UV__BIOS_H
 
 /*
  * BIOS layer definitions.
@@ -65,4 +65,4 @@
 		   unsigned long *drift_info);
 extern const char *x86_bios_strerror(long status);
 
-#endif /* _ASM_X86_BIOS_H */
+#endif /* ASM_X86__UV__BIOS_H */
diff --git a/include/asm-x86/uv/uv_bau.h b/include/asm-x86/uv/uv_bau.h
index 610b6b3..77153fb 100644
--- a/include/asm-x86/uv/uv_bau.h
+++ b/include/asm-x86/uv/uv_bau.h
@@ -8,8 +8,8 @@
  * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
  */
 
-#ifndef __ASM_X86_UV_BAU__
-#define __ASM_X86_UV_BAU__
+#ifndef ASM_X86__UV__UV_BAU_H
+#define ASM_X86__UV__UV_BAU_H
 
 #include <linux/bitmap.h>
 #define BITSPERBYTE 8
@@ -329,4 +329,4 @@
 extern void uv_bau_message_intr1(void);
 extern void uv_bau_timeout_intr1(void);
 
-#endif /* __ASM_X86_UV_BAU__ */
+#endif /* ASM_X86__UV__UV_BAU_H */
diff --git a/include/asm-x86/uv/uv_hub.h b/include/asm-x86/uv/uv_hub.h
index a4ef26e..bdb5b01 100644
--- a/include/asm-x86/uv/uv_hub.h
+++ b/include/asm-x86/uv/uv_hub.h
@@ -8,8 +8,8 @@
  * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
  */
 
-#ifndef __ASM_X86_UV_HUB_H__
-#define __ASM_X86_UV_HUB_H__
+#ifndef ASM_X86__UV__UV_HUB_H
+#define ASM_X86__UV__UV_HUB_H
 
 #include <linux/numa.h>
 #include <linux/percpu.h>
@@ -350,5 +350,5 @@
 	return uv_possible_blades;
 }
 
-#endif /* __ASM_X86_UV_HUB__ */
+#endif /* ASM_X86__UV__UV_HUB_H */
 
diff --git a/include/asm-x86/uv/uv_mmrs.h b/include/asm-x86/uv/uv_mmrs.h
index 151fd7f..8b03d89 100644
--- a/include/asm-x86/uv/uv_mmrs.h
+++ b/include/asm-x86/uv/uv_mmrs.h
@@ -8,8 +8,8 @@
  * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
  */
 
-#ifndef __ASM_X86_UV_MMRS__
-#define __ASM_X86_UV_MMRS__
+#ifndef ASM_X86__UV__UV_MMRS_H
+#define ASM_X86__UV__UV_MMRS_H
 
 #define UV_MMR_ENABLE		(1UL << 63)
 
@@ -1292,4 +1292,4 @@
 };
 
 
-#endif /* __ASM_X86_UV_MMRS__ */
+#endif /* ASM_X86__UV__UV_MMRS_H */
diff --git a/include/asm-x86/vdso.h b/include/asm-x86/vdso.h
index 8e18fb8..4ab3209 100644
--- a/include/asm-x86/vdso.h
+++ b/include/asm-x86/vdso.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_VDSO_H
-#define _ASM_X86_VDSO_H	1
+#ifndef ASM_X86__VDSO_H
+#define ASM_X86__VDSO_H
 
 #ifdef CONFIG_X86_64
 extern const char VDSO64_PRELINK[];
@@ -44,4 +44,4 @@
 extern const char vdso32_syscall_start, vdso32_syscall_end;
 extern const char vdso32_sysenter_start, vdso32_sysenter_end;
 
-#endif	/* asm-x86/vdso.h */
+#endif /* ASM_X86__VDSO_H */
diff --git a/include/asm-x86/vga.h b/include/asm-x86/vga.h
index 0ccf804..b9e493d 100644
--- a/include/asm-x86/vga.h
+++ b/include/asm-x86/vga.h
@@ -4,8 +4,8 @@
  *	(c) 1998 Martin Mares <mj@ucw.cz>
  */
 
-#ifndef _LINUX_ASM_VGA_H_
-#define _LINUX_ASM_VGA_H_
+#ifndef ASM_X86__VGA_H
+#define ASM_X86__VGA_H
 
 /*
  *	On the PC, we can just recalculate addresses and then
@@ -17,4 +17,4 @@
 #define vga_readb(x) (*(x))
 #define vga_writeb(x, y) (*(y) = (x))
 
-#endif
+#endif /* ASM_X86__VGA_H */
diff --git a/include/asm-x86/vgtod.h b/include/asm-x86/vgtod.h
index 3301f09..38fd133 100644
--- a/include/asm-x86/vgtod.h
+++ b/include/asm-x86/vgtod.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_VGTOD_H
-#define _ASM_VGTOD_H 1
+#ifndef ASM_X86__VGTOD_H
+#define ASM_X86__VGTOD_H
 
 #include <asm/vsyscall.h>
 #include <linux/clocksource.h>
@@ -26,4 +26,4 @@
 __section_vsyscall_gtod_data;
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
-#endif
+#endif /* ASM_X86__VGTOD_H */
diff --git a/include/asm-x86/visws/cobalt.h b/include/asm-x86/visws/cobalt.h
index 9952588..9627a8f 100644
--- a/include/asm-x86/visws/cobalt.h
+++ b/include/asm-x86/visws/cobalt.h
@@ -1,5 +1,5 @@
-#ifndef __I386_SGI_COBALT_H
-#define __I386_SGI_COBALT_H
+#ifndef ASM_X86__VISWS__COBALT_H
+#define ASM_X86__VISWS__COBALT_H
 
 #include <asm/fixmap.h>
 
@@ -122,4 +122,4 @@
 
 extern char visws_board_rev;
 
-#endif /* __I386_SGI_COBALT_H */
+#endif /* ASM_X86__VISWS__COBALT_H */
diff --git a/include/asm-x86/visws/lithium.h b/include/asm-x86/visws/lithium.h
index dfcd4f0..b36d3b3 100644
--- a/include/asm-x86/visws/lithium.h
+++ b/include/asm-x86/visws/lithium.h
@@ -1,5 +1,5 @@
-#ifndef __I386_SGI_LITHIUM_H
-#define __I386_SGI_LITHIUM_H
+#ifndef ASM_X86__VISWS__LITHIUM_H
+#define ASM_X86__VISWS__LITHIUM_H
 
 #include <asm/fixmap.h>
 
@@ -49,5 +49,5 @@
 	return *((volatile unsigned short *)(LI_PCIB_VADDR+reg));
 }
 
-#endif
+#endif /* ASM_X86__VISWS__LITHIUM_H */
 
diff --git a/include/asm-x86/visws/piix4.h b/include/asm-x86/visws/piix4.h
index 83ea4f4..61c9380 100644
--- a/include/asm-x86/visws/piix4.h
+++ b/include/asm-x86/visws/piix4.h
@@ -1,5 +1,5 @@
-#ifndef __I386_SGI_PIIX_H
-#define __I386_SGI_PIIX_H
+#ifndef ASM_X86__VISWS__PIIX4_H
+#define ASM_X86__VISWS__PIIX4_H
 
 /*
  * PIIX4 as used on SGI Visual Workstations
@@ -104,4 +104,4 @@
  */
 #define	PIIX_GPI_STPCLK		0x4	// STPCLK signal routed back in
 
-#endif
+#endif /* ASM_X86__VISWS__PIIX4_H */
diff --git a/include/asm-x86/vm86.h b/include/asm-x86/vm86.h
index 5ce3513..998bd18 100644
--- a/include/asm-x86/vm86.h
+++ b/include/asm-x86/vm86.h
@@ -1,5 +1,5 @@
-#ifndef _LINUX_VM86_H
-#define _LINUX_VM86_H
+#ifndef ASM_X86__VM86_H
+#define ASM_X86__VM86_H
 
 /*
  * I'm guessing at the VIF/VIP flag usage, but hope that this is how
@@ -205,4 +205,4 @@
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__VM86_H */
diff --git a/include/asm-x86/vmi_time.h b/include/asm-x86/vmi_time.h
index c3118c3..b2d39e6 100644
--- a/include/asm-x86/vmi_time.h
+++ b/include/asm-x86/vmi_time.h
@@ -22,8 +22,8 @@
  *
  */
 
-#ifndef __VMI_TIME_H
-#define __VMI_TIME_H
+#ifndef ASM_X86__VMI_TIME_H
+#define ASM_X86__VMI_TIME_H
 
 /*
  * Raw VMI call indices for timer functions
@@ -95,4 +95,4 @@
 
 #define CONFIG_VMI_ALARM_HZ	100
 
-#endif
+#endif /* ASM_X86__VMI_TIME_H */
diff --git a/include/asm-x86/vsyscall.h b/include/asm-x86/vsyscall.h
index 6b66ff9..dcd4682 100644
--- a/include/asm-x86/vsyscall.h
+++ b/include/asm-x86/vsyscall.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_VSYSCALL_H_
-#define _ASM_X86_64_VSYSCALL_H_
+#ifndef ASM_X86__VSYSCALL_H
+#define ASM_X86__VSYSCALL_H
 
 enum vsyscall_num {
 	__NR_vgettimeofday,
@@ -41,4 +41,4 @@
 
 #endif /* __KERNEL__ */
 
-#endif /* _ASM_X86_64_VSYSCALL_H_ */
+#endif /* ASM_X86__VSYSCALL_H */
diff --git a/include/asm-x86/xen/events.h b/include/asm-x86/xen/events.h
index 8ded747..8151f5b 100644
--- a/include/asm-x86/xen/events.h
+++ b/include/asm-x86/xen/events.h
@@ -1,5 +1,5 @@
-#ifndef __XEN_EVENTS_H
-#define __XEN_EVENTS_H
+#ifndef ASM_X86__XEN__EVENTS_H
+#define ASM_X86__XEN__EVENTS_H
 
 enum ipi_vector {
 	XEN_RESCHEDULE_VECTOR,
@@ -21,4 +21,4 @@
 	do_IRQ(regs);
 }
 
-#endif /* __XEN_EVENTS_H */
+#endif /* ASM_X86__XEN__EVENTS_H */
diff --git a/include/asm-x86/xen/grant_table.h b/include/asm-x86/xen/grant_table.h
index 2444d45..c4baab4 100644
--- a/include/asm-x86/xen/grant_table.h
+++ b/include/asm-x86/xen/grant_table.h
@@ -1,7 +1,7 @@
-#ifndef __XEN_GRANT_TABLE_H
-#define __XEN_GRANT_TABLE_H
+#ifndef ASM_X86__XEN__GRANT_TABLE_H
+#define ASM_X86__XEN__GRANT_TABLE_H
 
 #define xen_alloc_vm_area(size)	alloc_vm_area(size)
 #define xen_free_vm_area(area)	free_vm_area(area)
 
-#endif /* __XEN_GRANT_TABLE_H */
+#endif /* ASM_X86__XEN__GRANT_TABLE_H */
diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h
index 91cb7fd..44f4259 100644
--- a/include/asm-x86/xen/hypercall.h
+++ b/include/asm-x86/xen/hypercall.h
@@ -30,8 +30,8 @@
  * IN THE SOFTWARE.
  */
 
-#ifndef __HYPERCALL_H__
-#define __HYPERCALL_H__
+#ifndef ASM_X86__XEN__HYPERCALL_H
+#define ASM_X86__XEN__HYPERCALL_H
 
 #include <linux/errno.h>
 #include <linux/string.h>
@@ -524,4 +524,4 @@
 	mcl->args[1] = esp;
 }
 
-#endif /* __HYPERCALL_H__ */
+#endif /* ASM_X86__XEN__HYPERCALL_H */
diff --git a/include/asm-x86/xen/hypervisor.h b/include/asm-x86/xen/hypervisor.h
index 04ee061..0ef3a88 100644
--- a/include/asm-x86/xen/hypervisor.h
+++ b/include/asm-x86/xen/hypervisor.h
@@ -30,8 +30,8 @@
  * IN THE SOFTWARE.
  */
 
-#ifndef __HYPERVISOR_H__
-#define __HYPERVISOR_H__
+#ifndef ASM_X86__XEN__HYPERVISOR_H
+#define ASM_X86__XEN__HYPERVISOR_H
 
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -69,4 +69,4 @@
 
 #define is_running_on_xen()	(xen_start_info ? 1 : 0)
 
-#endif /* __HYPERVISOR_H__ */
+#endif /* ASM_X86__XEN__HYPERVISOR_H */
diff --git a/include/asm-x86/xen/interface.h b/include/asm-x86/xen/interface.h
index 9d810f2..d077bba 100644
--- a/include/asm-x86/xen/interface.h
+++ b/include/asm-x86/xen/interface.h
@@ -6,8 +6,8 @@
  * Copyright (c) 2004, K A Fraser
  */
 
-#ifndef __ASM_X86_XEN_INTERFACE_H
-#define __ASM_X86_XEN_INTERFACE_H
+#ifndef ASM_X86__XEN__INTERFACE_H
+#define ASM_X86__XEN__INTERFACE_H
 
 #ifdef __XEN__
 #define __DEFINE_GUEST_HANDLE(name, type) \
@@ -172,4 +172,4 @@
 #define XEN_CPUID          XEN_EMULATE_PREFIX "cpuid"
 #endif
 
-#endif	/* __ASM_X86_XEN_INTERFACE_H */
+#endif /* ASM_X86__XEN__INTERFACE_H */
diff --git a/include/asm-x86/xen/interface_32.h b/include/asm-x86/xen/interface_32.h
index d8ac41d..08167e1 100644
--- a/include/asm-x86/xen/interface_32.h
+++ b/include/asm-x86/xen/interface_32.h
@@ -6,8 +6,8 @@
  * Copyright (c) 2004, K A Fraser
  */
 
-#ifndef __ASM_X86_XEN_INTERFACE_32_H
-#define __ASM_X86_XEN_INTERFACE_32_H
+#ifndef ASM_X86__XEN__INTERFACE_32_H
+#define ASM_X86__XEN__INTERFACE_32_H
 
 
 /*
@@ -94,4 +94,4 @@
 #define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20))
 #define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20))
 
-#endif	/* __ASM_X86_XEN_INTERFACE_32_H */
+#endif /* ASM_X86__XEN__INTERFACE_32_H */
diff --git a/include/asm-x86/xen/interface_64.h b/include/asm-x86/xen/interface_64.h
index 842266c..046c0f1 100644
--- a/include/asm-x86/xen/interface_64.h
+++ b/include/asm-x86/xen/interface_64.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_X86_XEN_INTERFACE_64_H
-#define __ASM_X86_XEN_INTERFACE_64_H
+#ifndef ASM_X86__XEN__INTERFACE_64_H
+#define ASM_X86__XEN__INTERFACE_64_H
 
 /*
  * 64-bit segment selectors
@@ -156,4 +156,4 @@
 #endif /* !__ASSEMBLY__ */
 
 
-#endif	/* __ASM_X86_XEN_INTERFACE_64_H */
+#endif /* ASM_X86__XEN__INTERFACE_64_H */
diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h
index 7b3835d..c50185d 100644
--- a/include/asm-x86/xen/page.h
+++ b/include/asm-x86/xen/page.h
@@ -1,5 +1,5 @@
-#ifndef __XEN_PAGE_H
-#define __XEN_PAGE_H
+#ifndef ASM_X86__XEN__PAGE_H
+#define ASM_X86__XEN__PAGE_H
 
 #include <linux/pfn.h>
 
@@ -162,4 +162,4 @@
 void make_lowmem_page_readonly(void *vaddr);
 void make_lowmem_page_readwrite(void *vaddr);
 
-#endif /* __XEN_PAGE_H */
+#endif /* ASM_X86__XEN__PAGE_H */
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 6d93dce..2f245fe 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -47,14 +47,22 @@
  *	HRTIMER_CB_IRQSAFE:		Callback may run in hardirq context
  *	HRTIMER_CB_IRQSAFE_NO_RESTART:	Callback may run in hardirq context and
  *					does not restart the timer
- *	HRTIMER_CB_IRQSAFE_NO_SOFTIRQ:	Callback must run in hardirq context
- *					Special mode for tick emultation
+ *	HRTIMER_CB_IRQSAFE_PERCPU:	Callback must run in hardirq context
+ *					Special mode for tick emulation and
+ *					scheduler timer. Such timers are per
+ *					cpu and not allowed to be migrated on
+ *					cpu unplug.
+ *	HRTIMER_CB_IRQSAFE_UNLOCKED:	Callback should run in hardirq context
+ *					with timer->base lock unlocked
+ *					used for timers which call wakeup to
+ *					avoid lock order problems with rq->lock
  */
 enum hrtimer_cb_mode {
 	HRTIMER_CB_SOFTIRQ,
 	HRTIMER_CB_IRQSAFE,
 	HRTIMER_CB_IRQSAFE_NO_RESTART,
-	HRTIMER_CB_IRQSAFE_NO_SOFTIRQ,
+	HRTIMER_CB_IRQSAFE_PERCPU,
+	HRTIMER_CB_IRQSAFE_UNLOCKED,
 };
 
 /*
@@ -67,9 +75,10 @@
  * 0x02		callback function running
  * 0x04		callback pending (high resolution mode)
  *
- * Special case:
+ * Special cases:
  * 0x03		callback function running and enqueued
  *		(was requeued on another CPU)
+ * 0x09		timer was migrated on CPU hotunplug
  * The "callback function running and enqueued" status is only possible on
  * SMP. It happens for example when a posix timer expired and the callback
  * queued a signal. Between dropping the lock which protects the posix timer
@@ -87,6 +96,7 @@
 #define HRTIMER_STATE_ENQUEUED	0x01
 #define HRTIMER_STATE_CALLBACK	0x02
 #define HRTIMER_STATE_PENDING	0x04
+#define HRTIMER_STATE_MIGRATE	0x08
 
 /**
  * struct hrtimer - the basic hrtimer structure
diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h
index b160fb18..37aaf2b 100644
--- a/include/linux/ramfs.h
+++ b/include/linux/ramfs.h
@@ -6,6 +6,7 @@
 	 int flags, const char *dev_name, void *data, struct vfsmount *mnt);
 
 #ifndef CONFIG_MMU
+extern int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize);
 extern unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
 						   unsigned long addr,
 						   unsigned long len,
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index 5da9794..b106fd8 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_STACKTRACE_H
 #define __LINUX_STACKTRACE_H
 
+struct task_struct;
+
 #ifdef CONFIG_STACKTRACE
 struct stack_trace {
 	unsigned int nr_entries, max_entries;
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 2481173..029a54a 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -227,6 +227,9 @@
 				   const struct sctp_chunk *,
 				   const __u8 *,
 				   const size_t );
+struct sctp_chunk *sctp_make_violation_paramlen(const struct sctp_association *,
+				   const struct sctp_chunk *,
+				   struct sctp_paramhdr *);
 struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *,
 				  const struct sctp_transport *,
 				  const void *payload,
diff --git a/init/main.c b/init/main.c
index f6f7042..3820323 100644
--- a/init/main.c
+++ b/init/main.c
@@ -708,7 +708,7 @@
 	int result;
 
 	if (initcall_debug) {
-		print_fn_descriptor_symbol("calling  %s\n", fn);
+		printk("calling  %pF\n", fn);
 		t0 = ktime_get();
 	}
 
@@ -718,8 +718,8 @@
 		t1 = ktime_get();
 		delta = ktime_sub(t1, t0);
 
-		print_fn_descriptor_symbol("initcall %s", fn);
-		printk(" returned %d after %Ld msecs\n", result,
+		printk("initcall %pF returned %d after %Ld msecs\n",
+			fn, result,
 			(unsigned long long) delta.tv64 >> 20);
 	}
 
@@ -737,8 +737,7 @@
 		local_irq_enable();
 	}
 	if (msgbuf[0]) {
-		print_fn_descriptor_symbol(KERN_WARNING "initcall %s", fn);
-		printk(" returned with %s\n", msgbuf);
+		printk("initcall %pF returned with %s\n", fn, msgbuf);
 	}
 
 	return result;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 13932abd..a0123d7 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2738,14 +2738,15 @@
  */
 void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
 {
-	struct cgroup *oldcgrp, *newcgrp;
+	struct cgroup *oldcgrp, *newcgrp = NULL;
 
 	if (need_mm_owner_callback) {
 		int i;
 		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 			struct cgroup_subsys *ss = subsys[i];
 			oldcgrp = task_cgroup(old, ss->subsys_id);
-			newcgrp = task_cgroup(new, ss->subsys_id);
+			if (new)
+				newcgrp = task_cgroup(new, ss->subsys_id);
 			if (oldcgrp == newcgrp)
 				continue;
 			if (ss->mm_owner_changed)
diff --git a/kernel/exit.c b/kernel/exit.c
index 1639564..85a83c8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -583,8 +583,6 @@
 	 * If there are other users of the mm and the owner (us) is exiting
 	 * we need to find a new owner to take on the responsibility.
 	 */
-	if (!mm)
-		return 0;
 	if (atomic_read(&mm->mm_users) <= 1)
 		return 0;
 	if (mm->owner != p)
@@ -627,6 +625,16 @@
 	} while_each_thread(g, c);
 
 	read_unlock(&tasklist_lock);
+	/*
+	 * We found no owner yet mm_users > 1: this implies that we are
+	 * most likely racing with swapoff (try_to_unuse()) or /proc or
+	 * ptrace or page migration (get_task_mm()).  Mark owner as NULL,
+	 * so that subsystems can understand the callback and take action.
+	 */
+	down_write(&mm->mmap_sem);
+	cgroup_mm_owner_callbacks(mm->owner, NULL);
+	mm->owner = NULL;
+	up_write(&mm->mmap_sem);
 	return;
 
 assign_new_owner:
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index b8e4dce..cdec83e 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -672,13 +672,14 @@
 			 */
 			BUG_ON(timer->function(timer) != HRTIMER_NORESTART);
 			return 1;
-		case HRTIMER_CB_IRQSAFE_NO_SOFTIRQ:
+		case HRTIMER_CB_IRQSAFE_PERCPU:
+		case HRTIMER_CB_IRQSAFE_UNLOCKED:
 			/*
 			 * This is solely for the sched tick emulation with
 			 * dynamic tick support to ensure that we do not
 			 * restart the tick right on the edge and end up with
 			 * the tick timer in the softirq ! The calling site
-			 * takes care of this.
+			 * takes care of this. Also used for hrtimer sleeper !
 			 */
 			debug_hrtimer_deactivate(timer);
 			return 1;
@@ -1245,7 +1246,8 @@
 	timer_stats_account_hrtimer(timer);
 
 	fn = timer->function;
-	if (timer->cb_mode == HRTIMER_CB_IRQSAFE_NO_SOFTIRQ) {
+	if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
+	    timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) {
 		/*
 		 * Used for scheduler timers, avoid lock inversion with
 		 * rq->lock and tasklist_lock.
@@ -1452,7 +1454,7 @@
 	sl->timer.function = hrtimer_wakeup;
 	sl->task = task;
 #ifdef CONFIG_HIGH_RES_TIMERS
-	sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+	sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
 #endif
 }
 
@@ -1591,29 +1593,95 @@
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
-				struct hrtimer_clock_base *new_base)
+static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
+				struct hrtimer_clock_base *new_base, int dcpu)
 {
 	struct hrtimer *timer;
 	struct rb_node *node;
+	int raise = 0;
 
 	while ((node = rb_first(&old_base->active))) {
 		timer = rb_entry(node, struct hrtimer, node);
 		BUG_ON(hrtimer_callback_running(timer));
 		debug_hrtimer_deactivate(timer);
-		__remove_hrtimer(timer, old_base, HRTIMER_STATE_INACTIVE, 0);
+
+		/*
+		 * Should not happen. Per CPU timers should be
+		 * canceled _before_ the migration code is called
+		 */
+		if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU) {
+			__remove_hrtimer(timer, old_base,
+					 HRTIMER_STATE_INACTIVE, 0);
+			WARN(1, "hrtimer (%p %p)active but cpu %d dead\n",
+			     timer, timer->function, dcpu);
+			continue;
+		}
+
+		/*
+		 * Mark it as STATE_MIGRATE not INACTIVE otherwise the
+		 * timer could be seen as !active and just vanish away
+		 * under us on another CPU
+		 */
+		__remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
 		timer->base = new_base;
 		/*
 		 * Enqueue the timer. Allow reprogramming of the event device
 		 */
 		enqueue_hrtimer(timer, new_base, 1);
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+		/*
+		 * Happens with high res enabled when the timer was
+		 * already expired and the callback mode is
+		 * HRTIMER_CB_IRQSAFE_UNLOCKED (hrtimer_sleeper). The
+		 * enqueue code does not move them to the soft irq
+		 * pending list for performance/latency reasons, but
+		 * in the migration state, we need to do that
+		 * otherwise we end up with a stale timer.
+		 */
+		if (timer->state == HRTIMER_STATE_MIGRATE) {
+			timer->state = HRTIMER_STATE_PENDING;
+			list_add_tail(&timer->cb_entry,
+				      &new_base->cpu_base->cb_pending);
+			raise = 1;
+		}
+#endif
+		/* Clear the migration state bit */
+		timer->state &= ~HRTIMER_STATE_MIGRATE;
 	}
+	return raise;
 }
 
+#ifdef CONFIG_HIGH_RES_TIMERS
+static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
+				   struct hrtimer_cpu_base *new_base)
+{
+	struct hrtimer *timer;
+	int raise = 0;
+
+	while (!list_empty(&old_base->cb_pending)) {
+		timer = list_entry(old_base->cb_pending.next,
+				   struct hrtimer, cb_entry);
+
+		__remove_hrtimer(timer, timer->base, HRTIMER_STATE_PENDING, 0);
+		timer->base = &new_base->clock_base[timer->base->index];
+		list_add_tail(&timer->cb_entry, &new_base->cb_pending);
+		raise = 1;
+	}
+	return raise;
+}
+#else
+static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
+				   struct hrtimer_cpu_base *new_base)
+{
+	return 0;
+}
+#endif
+
 static void migrate_hrtimers(int cpu)
 {
 	struct hrtimer_cpu_base *old_base, *new_base;
-	int i;
+	int i, raise = 0;
 
 	BUG_ON(cpu_online(cpu));
 	old_base = &per_cpu(hrtimer_bases, cpu);
@@ -1626,14 +1694,21 @@
 	spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
-		migrate_hrtimer_list(&old_base->clock_base[i],
-				     &new_base->clock_base[i]);
+		if (migrate_hrtimer_list(&old_base->clock_base[i],
+					 &new_base->clock_base[i], cpu))
+			raise = 1;
 	}
 
+	if (migrate_hrtimer_pending(old_base, new_base))
+		raise = 1;
+
 	spin_unlock(&old_base->lock);
 	spin_unlock(&new_base->lock);
 	local_irq_enable();
 	put_cpu_var(hrtimer_bases);
+
+	if (raise)
+		hrtimer_raise_softirq();
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index eaa21fc..25d955d 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -488,7 +488,7 @@
 		if (err)
 			return err;
 		if (CACHE_FLUSH_IS_SAFE)
-			flush_icache_range(addr, addr + length + 1);
+			flush_icache_range(addr, addr + length);
 		return 0;
 	}
 
@@ -1462,7 +1462,7 @@
 	 * Get the passive CPU lock which will hold all the non-primary
 	 * CPU in a spin state while the debugger is active
 	 */
-	if (!kgdb_single_step || !kgdb_contthread) {
+	if (!kgdb_single_step) {
 		for (i = 0; i < NR_CPUS; i++)
 			atomic_set(&passive_cpu_wait[i], 1);
 	}
@@ -1475,7 +1475,7 @@
 
 #ifdef CONFIG_SMP
 	/* Signal the other CPUs to enter kgdb_wait() */
-	if ((!kgdb_single_step || !kgdb_contthread) && kgdb_do_roundup)
+	if ((!kgdb_single_step) && kgdb_do_roundup)
 		kgdb_roundup_cpus(flags);
 #endif
 
@@ -1494,7 +1494,7 @@
 	kgdb_post_primary_code(ks->linux_regs, ks->ex_vector, ks->err_code);
 	kgdb_deactivate_sw_breakpoints();
 	kgdb_single_step = 0;
-	kgdb_contthread = NULL;
+	kgdb_contthread = current;
 	exception_level = 0;
 
 	/* Talk to debugger with gdbserial protocol */
@@ -1508,7 +1508,7 @@
 	kgdb_info[ks->cpu].task = NULL;
 	atomic_set(&cpu_in_kgdb[ks->cpu], 0);
 
-	if (!kgdb_single_step || !kgdb_contthread) {
+	if (!kgdb_single_step) {
 		for (i = NR_CPUS-1; i >= 0; i--)
 			atomic_set(&passive_cpu_wait[i], 0);
 		/*
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index e36d579..5131e54 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -441,7 +441,7 @@
 		return tmr;
 	if (unlikely(!(tmr->sigq = sigqueue_alloc()))) {
 		kmem_cache_free(posix_timers_cache, tmr);
-		tmr = NULL;
+		return NULL;
 	}
 	memset(&tmr->sigq->info, 0, sizeof(siginfo_t));
 	return tmr;
diff --git a/kernel/sched.c b/kernel/sched.c
index 13dd2db..ad1962d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -201,7 +201,7 @@
 	hrtimer_init(&rt_b->rt_period_timer,
 			CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	rt_b->rt_period_timer.function = sched_rt_period_timer;
-	rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+	rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
 }
 
 static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
@@ -1119,7 +1119,7 @@
 
 	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	rq->hrtick_timer.function = hrtick;
-	rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+	rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 }
 #else
 static inline void hrtick_clear(struct rq *rq)
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index bd70345..cb01cd8 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -235,7 +235,8 @@
 	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
 		if (!cpu_isset(cpu, tick_broadcast_mask)) {
 			cpu_set(cpu, tick_broadcast_mask);
-			if (bc->mode == TICKDEV_MODE_PERIODIC)
+			if (tick_broadcast_device.mode ==
+			    TICKDEV_MODE_PERIODIC)
 				clockevents_shutdown(dev);
 		}
 		if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
@@ -245,7 +246,8 @@
 		if (!tick_broadcast_force &&
 		    cpu_isset(cpu, tick_broadcast_mask)) {
 			cpu_clear(cpu, tick_broadcast_mask);
-			if (bc->mode == TICKDEV_MODE_PERIODIC)
+			if (tick_broadcast_device.mode ==
+			    TICKDEV_MODE_PERIODIC)
 				tick_setup_periodic(dev, 0);
 		}
 		break;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 39019b3f..cb02324 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -625,7 +625,7 @@
 	 */
 	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	ts->sched_timer.function = tick_sched_timer;
-	ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+	ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 
 	/* Get the next period (per cpu) */
 	ts->sched_timer.expires = tick_init_jiffy_update();
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index bb948e5..db58fb6 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -202,7 +202,7 @@
 
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = stack_trace_timer_fn;
-	hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+	hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 
 	hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL);
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c0500e4..36896f3 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -250,6 +250,14 @@
 
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 {
+	/*
+	 * mm_update_next_owner() may clear mm->owner to NULL
+	 * if it races with swapoff, page migration, etc.
+	 * So this can be called with p == NULL.
+	 */
+	if (unlikely(!p))
+		return NULL;
+
 	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
 				struct mem_cgroup, css);
 }
@@ -549,6 +557,11 @@
 	if (likely(!memcg)) {
 		rcu_read_lock();
 		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+		if (unlikely(!mem)) {
+			rcu_read_unlock();
+			kmem_cache_free(page_cgroup_cache, pc);
+			return 0;
+		}
 		/*
 		 * For every charge from the cgroup, increment reference count
 		 */
@@ -801,6 +814,10 @@
 
 	rcu_read_lock();
 	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (unlikely(!mem)) {
+		rcu_read_unlock();
+		return 0;
+	}
 	css_get(&mem->css);
 	rcu_read_unlock();
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e293c58..27b8681 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -268,13 +268,14 @@
 {
 	int i;
 	int nr_pages = 1 << order;
+	struct page *p = page + 1;
 
 	set_compound_page_dtor(page, free_compound_page);
 	set_compound_order(page, order);
 	__SetPageHead(page);
-	for (i = 1; i < nr_pages; i++) {
-		struct page *p = page + i;
-
+	for (i = 1; i < nr_pages; i++, p++) {
+		if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0))
+			p = pfn_to_page(page_to_pfn(page) + i);
 		__SetPageTail(p);
 		p->first_page = page;
 	}
@@ -284,6 +285,7 @@
 {
 	int i;
 	int nr_pages = 1 << order;
+	struct page *p = page + 1;
 
 	if (unlikely(compound_order(page) != order))
 		bad_page(page);
@@ -291,8 +293,9 @@
 	if (unlikely(!PageHead(page)))
 			bad_page(page);
 	__ClearPageHead(page);
-	for (i = 1; i < nr_pages; i++) {
-		struct page *p = page + i;
+	for (i = 1; i < nr_pages; i++, p++) {
+		if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0))
+			p = pfn_to_page(page_to_pfn(page) + i);
 
 		if (unlikely(!PageTail(p) |
 				(p->first_page != page)))
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index c69f84f..b70a7fe 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -114,8 +114,10 @@
 
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long pfn;
+	unsigned long pfn, flags;
 	struct page *page;
+	struct zone *zone;
+	int ret;
 
 	pfn = start_pfn;
 	/*
@@ -131,7 +133,9 @@
 	if (pfn < end_pfn)
 		return -EBUSY;
 	/* Check all pages are free or Marked as ISOLATED */
-	if (__test_page_isolated_in_pageblock(start_pfn, end_pfn))
-		return 0;
-	return -EBUSY;
+	zone = page_zone(pfn_to_page(pfn));
+	spin_lock_irqsave(&zone->lock, flags);
+	ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn);
+	spin_unlock_irqrestore(&zone->lock, flags);
+	return ret ? 0 : -EBUSY;
 }
diff --git a/mm/tiny-shmem.c b/mm/tiny-shmem.c
index d17cb6f..8d7a27a 100644
--- a/mm/tiny-shmem.c
+++ b/mm/tiny-shmem.c
@@ -80,6 +80,12 @@
 	inode->i_nlink = 0;	/* It is unlinked */
 	init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
 			&ramfs_file_operations);
+
+#ifndef CONFIG_MMU
+	error = ramfs_nommu_expand_for_mapping(inode, size);
+	if (error)
+		goto close_file;
+#endif
 	return file;
 
 close_file:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1b4fee2..011478e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -618,7 +618,7 @@
 			];
 	} rep;
 	struct ip_reply_arg arg;
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net(skb->dst->dev);
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
 	memset(&arg, 0, sizeof(arg));
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9af6115..63442a1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2688,6 +2688,8 @@
 	if (ret)
 		goto out_kmem_cache;
 
+	ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
+
 	/* Registering of the loopback is done before this portion of code,
 	 * the loopback reference in rt6_info will not be taken, do it
 	 * manually for init_net */
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b585c85..10e22fd 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1050,7 +1050,7 @@
 	struct tcphdr *th = tcp_hdr(skb), *t1;
 	struct sk_buff *buff;
 	struct flowi fl;
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net(skb->dst->dev);
 	struct sock *ctl_sk = net->ipv6.tcp_sk;
 	unsigned int tot_len = sizeof(struct tcphdr);
 	__be32 *topt;
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 705959b..d7b54b5 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -524,7 +524,6 @@
 	get_online_cpus();
 	for_each_online_cpu(cpu)
 		smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1);
-	preempt_enable();
 	if (cpus_empty(iucv_buffer_cpumask))
 		/* No cpu could declare an iucv buffer. */
 		goto out_path;
@@ -547,7 +546,9 @@
  */
 static void iucv_disable(void)
 {
+	get_online_cpus();
 	on_each_cpu(iucv_retrieve_cpu, NULL, 1);
+	put_online_cpus();
 	kfree(iucv_path_table);
 }
 
diff --git a/net/key/af_key.c b/net/key/af_key.c
index d628df9..b7f5a1c 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -73,22 +73,18 @@
 	return 0;
 }
 
-static int pfkey_do_dump(struct pfkey_sock *pfk)
+static void pfkey_terminate_dump(struct pfkey_sock *pfk)
 {
-	int rc;
-
-	rc = pfk->dump.dump(pfk);
-	if (rc == -ENOBUFS)
-		return 0;
-
-	pfk->dump.done(pfk);
-	pfk->dump.dump = NULL;
-	pfk->dump.done = NULL;
-	return rc;
+	if (pfk->dump.dump) {
+		pfk->dump.done(pfk);
+		pfk->dump.dump = NULL;
+		pfk->dump.done = NULL;
+	}
 }
 
 static void pfkey_sock_destruct(struct sock *sk)
 {
+	pfkey_terminate_dump(pfkey_sk(sk));
 	skb_queue_purge(&sk->sk_receive_queue);
 
 	if (!sock_flag(sk, SOCK_DEAD)) {
@@ -310,6 +306,18 @@
 	return err;
 }
 
+static int pfkey_do_dump(struct pfkey_sock *pfk)
+{
+	int rc;
+
+	rc = pfk->dump.dump(pfk);
+	if (rc == -ENOBUFS)
+		return 0;
+
+	pfkey_terminate_dump(pfk);
+	return rc;
+}
+
 static inline void pfkey_hdr_dup(struct sadb_msg *new, struct sadb_msg *orig)
 {
 	*new = *orig;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index b599cbba..d68869f 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1012,6 +1012,29 @@
 	return retval;
 }
 
+struct sctp_chunk *sctp_make_violation_paramlen(
+	const struct sctp_association *asoc,
+	const struct sctp_chunk *chunk,
+	struct sctp_paramhdr *param)
+{
+	struct sctp_chunk *retval;
+	static const char error[] = "The following parameter had invalid length:";
+	size_t payload_len = sizeof(error) + sizeof(sctp_errhdr_t) +
+				sizeof(sctp_paramhdr_t);
+
+	retval = sctp_make_abort(asoc, chunk, payload_len);
+	if (!retval)
+		goto nodata;
+
+	sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION,
+			sizeof(error) + sizeof(sctp_paramhdr_t));
+	sctp_addto_chunk(retval, sizeof(error), error);
+	sctp_addto_param(retval, sizeof(sctp_paramhdr_t), param);
+
+nodata:
+	return retval;
+}
+
 /* Make a HEARTBEAT chunk.  */
 struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
 				  const struct sctp_transport *transport,
@@ -1782,11 +1805,6 @@
 					const struct sctp_chunk *chunk,
 					struct sctp_chunk **errp)
 {
-	static const char error[] = "The following parameter had invalid length:";
-	size_t		payload_len = WORD_ROUND(sizeof(error)) +
-						sizeof(sctp_paramhdr_t);
-
-
 	/* This is a fatal error.  Any accumulated non-fatal errors are
 	 * not reported.
 	 */
@@ -1794,14 +1812,7 @@
 		sctp_chunk_free(*errp);
 
 	/* Create an error chunk and fill it in with our payload. */
-	*errp = sctp_make_op_error_space(asoc, chunk, payload_len);
-
-	if (*errp) {
-		sctp_init_cause(*errp, SCTP_ERROR_PROTO_VIOLATION,
-				sizeof(error) + sizeof(sctp_paramhdr_t));
-		sctp_addto_chunk(*errp, sizeof(error), error);
-		sctp_addto_param(*errp, sizeof(sctp_paramhdr_t), param);
-	}
+	*errp = sctp_make_violation_paramlen(asoc, chunk, param);
 
 	return 0;
 }
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 8848d32..7c622af 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -119,7 +119,7 @@
 				     const struct sctp_endpoint *ep,
 				     const struct sctp_association *asoc,
 				     const sctp_subtype_t type,
-				     void *arg,
+				     void *arg, void *ext,
 				     sctp_cmd_seq_t *commands);
 
 static sctp_disposition_t sctp_sf_violation_ctsn(
@@ -3425,7 +3425,7 @@
 	addr_param = (union sctp_addr_param *)hdr->params;
 	length = ntohs(addr_param->p.length);
 	if (length < sizeof(sctp_paramhdr_t))
-		return sctp_sf_violation_paramlen(ep, asoc, type,
+		return sctp_sf_violation_paramlen(ep, asoc, type, arg,
 			   (void *)addr_param, commands);
 
 	/* Verify the ASCONF chunk before processing it. */
@@ -3433,8 +3433,8 @@
 			    (sctp_paramhdr_t *)((void *)addr_param + length),
 			    (void *)chunk->chunk_end,
 			    &err_param))
-		return sctp_sf_violation_paramlen(ep, asoc, type,
-						  (void *)&err_param, commands);
+		return sctp_sf_violation_paramlen(ep, asoc, type, arg,
+						  (void *)err_param, commands);
 
 	/* ADDIP 5.2 E1) Compare the value of the serial number to the value
 	 * the endpoint stored in a new association variable
@@ -3542,8 +3542,8 @@
 	    (sctp_paramhdr_t *)addip_hdr->params,
 	    (void *)asconf_ack->chunk_end,
 	    &err_param))
-		return sctp_sf_violation_paramlen(ep, asoc, type,
-			   (void *)&err_param, commands);
+		return sctp_sf_violation_paramlen(ep, asoc, type, arg,
+			   (void *)err_param, commands);
 
 	if (last_asconf) {
 		addip_hdr = (sctp_addiphdr_t *)last_asconf->subh.addip_hdr;
@@ -4240,12 +4240,38 @@
 				     const struct sctp_endpoint *ep,
 				     const struct sctp_association *asoc,
 				     const sctp_subtype_t type,
-				     void *arg,
-				     sctp_cmd_seq_t *commands) {
-	static const char err_str[] = "The following parameter had invalid length:";
+				     void *arg, void *ext,
+				     sctp_cmd_seq_t *commands)
+{
+	struct sctp_chunk *chunk =  arg;
+	struct sctp_paramhdr *param = ext;
+	struct sctp_chunk *abort = NULL;
 
-	return sctp_sf_abort_violation(ep, asoc, arg, commands, err_str,
-					sizeof(err_str));
+	if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc))
+		goto discard;
+
+	/* Make the abort chunk. */
+	abort = sctp_make_violation_paramlen(asoc, chunk, param);
+	if (!abort)
+		goto nomem;
+
+	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
+	SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS);
+
+	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+			SCTP_ERROR(ECONNABORTED));
+	sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
+			SCTP_PERR(SCTP_ERROR_PROTO_VIOLATION));
+	SCTP_DEC_STATS(SCTP_MIB_CURRESTAB);
+
+discard:
+	sctp_sf_pdiscard(ep, asoc, SCTP_ST_CHUNK(0), arg, commands);
+
+	SCTP_INC_STATS(SCTP_MIB_ABORTEDS);
+
+	return SCTP_DISPOSITION_ABORT;
+nomem:
+	return SCTP_DISPOSITION_NOMEM;
 }
 
 /* Handle a protocol violation when the peer trying to advance the
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index ac25b4c..dc50f1e 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -27,10 +27,14 @@
 		- skb_headroom(skb);
 	int ntail = dst->dev->needed_tailroom - skb_tailroom(skb);
 
-	if (nhead > 0 || ntail > 0)
-		return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC);
+	if (nhead <= 0) {
+		if (ntail <= 0)
+			return 0;
+		nhead = 0;
+	} else if (ntail < 0)
+		ntail = 0;
 
-	return 0;
+	return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC);
 }
 
 static int xfrm_output_one(struct sk_buff *skb, int err)
diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index 36b5eed..3e1057f 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -32,6 +32,7 @@
 
 static int indent = 1;
 static int valid_stdin = 1;
+static int sync_kconfig;
 static int conf_cnt;
 static char line[128];
 static struct menu *rootEntry;
@@ -65,7 +66,7 @@
 
 static void check_stdin(void)
 {
-	if (!valid_stdin && input_mode == ask_silent) {
+	if (!valid_stdin) {
 		printf(_("aborted!\n\n"));
 		printf(_("Console input/output is redirected. "));
 		printf(_("Run 'make oldconfig' to update configuration.\n\n"));
@@ -427,43 +428,6 @@
 		check_conf(child);
 }
 
-static void conf_do_update(void)
-{
-	/* Update until a loop caused no more changes */
-	do {
-		conf_cnt = 0;
-		check_conf(&rootmenu);
-	} while (conf_cnt);
-}
-
-static int conf_silent_update(void)
-{
-	const char *name;
-
-	if (conf_get_changed()) {
-		name = getenv("KCONFIG_NOSILENTUPDATE");
-		if (name && *name) {
-			fprintf(stderr,
-			_("\n*** Kernel configuration requires explicit update.\n\n"));
-			return 1;
-		}
-		conf_do_update();
-	}
-	return 0;
-}
-
-static int conf_update(void)
-{
-	rootEntry = &rootmenu;
-	conf(&rootmenu);
-	if (input_mode == ask_all) {
-		input_mode = ask_silent;
-		valid_stdin = 1;
-	}
-	conf_do_update();
-	return 0;
-}
-
 int main(int ac, char **av)
 {
 	int opt;
@@ -477,11 +441,11 @@
 	while ((opt = getopt(ac, av, "osdD:nmyrh")) != -1) {
 		switch (opt) {
 		case 'o':
-			input_mode = ask_new;
+			input_mode = ask_silent;
 			break;
 		case 's':
 			input_mode = ask_silent;
-			valid_stdin = isatty(0) && isatty(1) && isatty(2);
+			sync_kconfig = 1;
 			break;
 		case 'd':
 			input_mode = set_default;
@@ -519,6 +483,19 @@
 	name = av[optind];
 	conf_parse(name);
 	//zconfdump(stdout);
+	if (sync_kconfig) {
+		if (stat(".config", &tmpstat)) {
+			fprintf(stderr, _("***\n"
+				"*** You have not yet configured your kernel!\n"
+				"*** (missing kernel .config file)\n"
+				"***\n"
+				"*** Please run some configurator (e.g. \"make oldconfig\" or\n"
+				"*** \"make menuconfig\" or \"make xconfig\").\n"
+				"***\n"));
+			exit(1);
+		}
+	}
+
 	switch (input_mode) {
 	case set_default:
 		if (!defconfig_file)
@@ -531,16 +508,6 @@
 		}
 		break;
 	case ask_silent:
-		if (stat(".config", &tmpstat)) {
-			printf(_("***\n"
-				"*** You have not yet configured your kernel!\n"
-				"*** (missing kernel .config file)\n"
-				"***\n"
-				"*** Please run some configurator (e.g. \"make oldconfig\" or\n"
-				"*** \"make menuconfig\" or \"make xconfig\").\n"
-				"***\n"));
-			exit(1);
-		}
 	case ask_all:
 	case ask_new:
 		conf_read(NULL);
@@ -569,6 +536,19 @@
 	default:
 		break;
 	}
+
+	if (sync_kconfig) {
+		if (conf_get_changed()) {
+			name = getenv("KCONFIG_NOSILENTUPDATE");
+			if (name && *name) {
+				fprintf(stderr,
+					_("\n*** Kernel configuration requires explicit update.\n\n"));
+				return 1;
+			}
+		}
+		valid_stdin = isatty(0) && isatty(1) && isatty(2);
+	}
+
 	switch (input_mode) {
 	case set_no:
 		conf_set_all_new_symbols(def_no);
@@ -585,27 +565,38 @@
 	case set_default:
 		conf_set_all_new_symbols(def_default);
 		break;
-	case ask_silent:
 	case ask_new:
-		if (conf_silent_update())
-			exit(1);
-		break;
 	case ask_all:
-		if (conf_update())
-			exit(1);
+		rootEntry = &rootmenu;
+		conf(&rootmenu);
+		input_mode = ask_silent;
+		/* fall through */
+	case ask_silent:
+		/* Update until a loop caused no more changes */
+		do {
+			conf_cnt = 0;
+			check_conf(&rootmenu);
+		} while (conf_cnt);
 		break;
 	}
 
-	if (conf_write(NULL)) {
-		fprintf(stderr, _("\n*** Error during writing of the kernel configuration.\n\n"));
-		exit(1);
-	}
-	/* ask_silent is used during the build so we shall update autoconf.
-	 * All other commands are only used to generate a config.
-	 */
-	if (input_mode == ask_silent && conf_write_autoconf()) {
-		fprintf(stderr, _("\n*** Error during writing of the kernel configuration.\n\n"));
-		return 1;
+	if (sync_kconfig) {
+		/* silentoldconfig is used during the build so we shall update autoconf.
+		 * All other commands are only used to generate a config.
+		 */
+		if (conf_get_changed() && conf_write(NULL)) {
+			fprintf(stderr, _("\n*** Error during writing of the kernel configuration.\n\n"));
+			exit(1);
+		}
+		if (conf_write_autoconf()) {
+			fprintf(stderr, _("\n*** Error during update of the kernel configuration.\n\n"));
+			return 1;
+		}
+	} else {
+		if (conf_write(NULL)) {
+			fprintf(stderr, _("\n*** Error during writing of the kernel configuration.\n\n"));
+			exit(1);
+		}
 	}
 	return 0;
 }
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index df6a188..b91cf24 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -222,8 +222,10 @@
 				continue;
 			if (def == S_DEF_USER) {
 				sym = sym_find(line + 9);
-				if (!sym)
+				if (!sym) {
+					sym_add_change_count(1);
 					break;
+				}
 			} else {
 				sym = sym_lookup(line + 9, 0);
 				if (sym->type == S_UNKNOWN)
@@ -259,8 +261,10 @@
 			}
 			if (def == S_DEF_USER) {
 				sym = sym_find(line + 7);
-				if (!sym)
+				if (!sym) {
+					sym_add_change_count(1);
 					break;
+				}
 			} else {
 				sym = sym_lookup(line + 7, 0);
 				if (sym->type == S_UNKNOWN)
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index d11a815..8551952 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -2737,6 +2737,7 @@
 		if (ctx == NULL)
 			goto netlbl_secattr_to_sid_return;
 
+		context_init(&ctx_new);
 		ctx_new.user = ctx->user;
 		ctx_new.role = ctx->role;
 		ctx_new.type = ctx->type;
@@ -2745,13 +2746,9 @@
 			if (ebitmap_netlbl_import(&ctx_new.range.level[0].cat,
 						  secattr->attr.mls.cat) != 0)
 				goto netlbl_secattr_to_sid_return;
-			ctx_new.range.level[1].cat.highbit =
-				ctx_new.range.level[0].cat.highbit;
-			ctx_new.range.level[1].cat.node =
-				ctx_new.range.level[0].cat.node;
-		} else {
-			ebitmap_init(&ctx_new.range.level[0].cat);
-			ebitmap_init(&ctx_new.range.level[1].cat);
+			memcpy(&ctx_new.range.level[1].cat,
+			       &ctx_new.range.level[0].cat,
+			       sizeof(ctx_new.range.level[0].cat));
 		}
 		if (mls_context_isvalid(&policydb, &ctx_new) != 1)
 			goto netlbl_secattr_to_sid_return_cleanup;
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 9dd9bc7..ece25c7 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -781,7 +781,7 @@
 		return -ENODEV;
 
 	card = pcm->card;
-	down_read(&card->controls_rwsem);
+	read_lock(&card->ctl_files_rwlock);
 	list_for_each_entry(kctl, &card->ctl_files, list) {
 		if (kctl->pid == current->pid) {
 			prefer_subdevice = kctl->prefer_pcm_subdevice;
@@ -789,7 +789,7 @@
 				break;
 		}
 	}
-	up_read(&card->controls_rwsem);
+	read_unlock(&card->ctl_files_rwlock);
 
 	switch (stream) {
 	case SNDRV_PCM_STREAM_PLAYBACK:
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index c49b9d9..c487025 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -1546,16 +1546,10 @@
 	card = substream->pcm->card;
 
 	if (runtime->status->state == SNDRV_PCM_STATE_OPEN ||
-	    runtime->status->state == SNDRV_PCM_STATE_DISCONNECTED)
+	    runtime->status->state == SNDRV_PCM_STATE_DISCONNECTED ||
+	    runtime->status->state == SNDRV_PCM_STATE_SUSPENDED)
 		return -EBADFD;
 
-	snd_power_lock(card);
-	if (runtime->status->state == SNDRV_PCM_STATE_SUSPENDED) {
-		result = snd_power_wait(card, SNDRV_CTL_POWER_D0);
-		if (result < 0)
-			goto _unlock;
-	}
-
 	snd_pcm_stream_lock_irq(substream);
 	/* resume pause */
 	if (runtime->status->state == SNDRV_PCM_STATE_PAUSED)
@@ -1564,8 +1558,7 @@
 	snd_pcm_stop(substream, SNDRV_PCM_STATE_SETUP);
 	/* runtime->control->appl_ptr = runtime->status->hw_ptr; */
 	snd_pcm_stream_unlock_irq(substream);
- _unlock:
-	snd_power_unlock(card);
+
 	return result;
 }
 
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index f7ea728..b917a9f 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -418,7 +418,7 @@
 	mutex_lock(&rmidi->open_mutex);
 	while (1) {
 		subdevice = -1;
-		down_read(&card->controls_rwsem);
+		read_lock(&card->ctl_files_rwlock);
 		list_for_each_entry(kctl, &card->ctl_files, list) {
 			if (kctl->pid == current->pid) {
 				subdevice = kctl->prefer_rawmidi_subdevice;
@@ -426,7 +426,7 @@
 					break;
 			}
 		}
-		up_read(&card->controls_rwsem);
+		read_unlock(&card->ctl_files_rwlock);
 		err = snd_rawmidi_kernel_open(rmidi->card, rmidi->device,
 					      subdevice, fflags, rawmidi_file);
 		if (err >= 0)
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index ad994fc..f3da621 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -1683,8 +1683,8 @@
 	/* Dell 3 stack systems with verb table in BIOS */
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x01f3, "Dell Inspiron 1420", STAC_DELL_BIOS),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x0227, "Dell Vostro 1400  ", STAC_DELL_BIOS),
-	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x022f, "Dell     ", STAC_DELL_BIOS),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x022e, "Dell     ", STAC_DELL_BIOS),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x022f, "Dell Inspiron 1525", STAC_DELL_3ST),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x0242, "Dell     ", STAC_DELL_BIOS),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x0243, "Dell     ", STAC_DELL_BIOS),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x02ff, "Dell     ", STAC_DELL_BIOS),
diff --git a/sound/ppc/awacs.c b/sound/ppc/awacs.c
index 566a6d0..106c482 100644
--- a/sound/ppc/awacs.c
+++ b/sound/ppc/awacs.c
@@ -621,6 +621,13 @@
 	AWACS_SWITCH("CD Capture Switch", 0, SHIFT_MUX_CD, 0),
 };
 
+static struct snd_kcontrol_new snd_pmac_screamer_mixers_g4agp[] __initdata = {
+	AWACS_VOLUME("Line out Playback Volume", 2, 6, 1),
+	AWACS_VOLUME("Master Playback Volume", 5, 6, 1),
+	AWACS_SWITCH("CD Capture Switch", 0, SHIFT_MUX_CD, 0),
+	AWACS_SWITCH("Line Capture Switch", 0, SHIFT_MUX_MIC, 0),
+};
+
 static struct snd_kcontrol_new snd_pmac_awacs_mixers_pmac7500[] __initdata = {
 	AWACS_VOLUME("Line out Playback Volume", 2, 6, 1),
 	AWACS_SWITCH("CD Capture Switch", 0, SHIFT_MUX_CD, 0),
@@ -688,7 +695,10 @@
 static struct snd_kcontrol_new snd_pmac_awacs_speaker_sw __initdata =
 AWACS_SWITCH("PC Speaker Playback Switch", 1, SHIFT_SPKMUTE, 1);
 
-static struct snd_kcontrol_new snd_pmac_awacs_speaker_sw_imac __initdata =
+static struct snd_kcontrol_new snd_pmac_awacs_speaker_sw_imac1 __initdata =
+AWACS_SWITCH("PC Speaker Playback Switch", 1, SHIFT_PAROUT1, 1);
+
+static struct snd_kcontrol_new snd_pmac_awacs_speaker_sw_imac2 __initdata =
 AWACS_SWITCH("PC Speaker Playback Switch", 1, SHIFT_PAROUT1, 0);
 
 
@@ -765,11 +775,12 @@
 
 #define IS_PM7500 (machine_is_compatible("AAPL,7500"))
 #define IS_BEIGE (machine_is_compatible("AAPL,Gossamer"))
-#define IS_IMAC (machine_is_compatible("PowerMac2,1") \
-		|| machine_is_compatible("PowerMac2,2") \
+#define IS_IMAC1 (machine_is_compatible("PowerMac2,1"))
+#define IS_IMAC2 (machine_is_compatible("PowerMac2,2") \
 		|| machine_is_compatible("PowerMac4,1"))
+#define IS_G4AGP (machine_is_compatible("PowerMac3,1"))
 
-static int imac;
+static int imac1, imac2;
 
 #ifdef PMAC_SUPPORT_AUTOMUTE
 /*
@@ -815,13 +826,18 @@
 		{
 			int reg = chip->awacs_reg[1]
 				| (MASK_HDMUTE | MASK_SPKMUTE);
-			if (imac) {
+			if (imac1) {
+				reg &= ~MASK_SPKMUTE;
+				reg |= MASK_PAROUT1;
+			} else if (imac2) {
 				reg &= ~MASK_SPKMUTE;
 				reg &= ~MASK_PAROUT1;
 			}
 			if (snd_pmac_awacs_detect_headphone(chip))
 				reg &= ~MASK_HDMUTE;
-			else if (imac)
+			else if (imac1)
+				reg &= ~MASK_PAROUT1;
+			else if (imac2)
 				reg |= MASK_PAROUT1;
 			else
 				reg &= ~MASK_SPKMUTE;
@@ -850,9 +866,13 @@
 {
 	int pm7500 = IS_PM7500;
 	int beige = IS_BEIGE;
+	int g4agp = IS_G4AGP;
+	int imac;
 	int err, vol;
 
-	imac = IS_IMAC;
+	imac1 = IS_IMAC1;
+	imac2 = IS_IMAC2;
+	imac = imac1 || imac2;
 	/* looks like MASK_GAINLINE triggers something, so we set here
 	 * as start-up
 	 */
@@ -939,7 +959,7 @@
 				snd_pmac_awacs_mixers);
 	if (err < 0)
 		return err;
-	if (beige)
+	if (beige || g4agp)
 		;
 	else if (chip->model == PMAC_SCREAMER)
 		err = build_mixers(chip, ARRAY_SIZE(snd_pmac_screamer_mixers2),
@@ -961,13 +981,17 @@
 		err = build_mixers(chip,
 				   ARRAY_SIZE(snd_pmac_screamer_mixers_imac),
 				   snd_pmac_screamer_mixers_imac);
+	else if (g4agp)
+		err = build_mixers(chip,
+				   ARRAY_SIZE(snd_pmac_screamer_mixers_g4agp),
+				   snd_pmac_screamer_mixers_g4agp);
 	else
 		err = build_mixers(chip,
 				   ARRAY_SIZE(snd_pmac_awacs_mixers_pmac),
 				   snd_pmac_awacs_mixers_pmac);
 	if (err < 0)
 		return err;
-	chip->master_sw_ctl = snd_ctl_new1((pm7500 || imac)
+	chip->master_sw_ctl = snd_ctl_new1((pm7500 || imac || g4agp)
 			? &snd_pmac_awacs_master_sw_imac
 			: &snd_pmac_awacs_master_sw, chip);
 	err = snd_ctl_add(chip->card, chip->master_sw_ctl);
@@ -1004,15 +1028,17 @@
 					snd_pmac_awacs_speaker_vol);
 		if (err < 0)
 			return err;
-		chip->speaker_sw_ctl = snd_ctl_new1(imac
-				? &snd_pmac_awacs_speaker_sw_imac
+		chip->speaker_sw_ctl = snd_ctl_new1(imac1
+				? &snd_pmac_awacs_speaker_sw_imac1
+				: imac2
+				? &snd_pmac_awacs_speaker_sw_imac2
 				: &snd_pmac_awacs_speaker_sw, chip);
 		err = snd_ctl_add(chip->card, chip->speaker_sw_ctl);
 		if (err < 0)
 			return err;
 	}
 
-	if (beige)
+	if (beige || g4agp)
 		err = build_mixers(chip,
 				ARRAY_SIZE(snd_pmac_screamer_mic_boost_beige),
 				snd_pmac_screamer_mic_boost_beige);
diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c
index 9deb8c7..0bbd945 100644
--- a/sound/soc/codecs/cs4270.c
+++ b/sound/soc/codecs/cs4270.c
@@ -490,34 +490,7 @@
 
 #endif
 
-static int cs4270_i2c_probe(struct i2c_adapter *adap, int addr, int kind);
-
-/*
- * Notify the driver that a new I2C bus has been found.
- *
- * This function is called for each I2C bus in the system.  The function
- * then asks the I2C subsystem to probe that bus at the addresses on which
- * our device (the CS4270) could exist.  If a device is found at one of
- * those addresses, then our probe function (cs4270_i2c_probe) is called.
- */
-static int cs4270_i2c_attach(struct i2c_adapter *adapter)
-{
-	return i2c_probe(adapter, &addr_data, cs4270_i2c_probe);
-}
-
-static int cs4270_i2c_detach(struct i2c_client *client)
-{
-	struct snd_soc_codec *codec = i2c_get_clientdata(client);
-
-	i2c_detach_client(client);
-	codec->control_data = NULL;
-
-	kfree(codec->reg_cache);
-	codec->reg_cache = NULL;
-
-	kfree(client);
-	return 0;
-}
+static int cs4270_i2c_probe(struct i2c_client *, const struct i2c_device_id *);
 
 /* A list of non-DAPM controls that the CS4270 supports */
 static const struct snd_kcontrol_new cs4270_snd_controls[] = {
@@ -525,14 +498,19 @@
 		CS4270_VOLA, CS4270_VOLB, 0, 0xFF, 1)
 };
 
+static const struct i2c_device_id cs4270_id[] = {
+	{"cs4270", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, cs4270_id);
+
 static struct i2c_driver cs4270_i2c_driver = {
 	.driver = {
 		.name = "CS4270 I2C",
 		.owner = THIS_MODULE,
 	},
-	.id =             I2C_DRIVERID_CS4270,
-	.attach_adapter = cs4270_i2c_attach,
-	.detach_client =  cs4270_i2c_detach,
+	.id_table = cs4270_id,
+	.probe = cs4270_i2c_probe,
 };
 
 /*
@@ -561,11 +539,11 @@
  * Note: snd_soc_new_pcms() must be called before this function can be called,
  * because of snd_ctl_add().
  */
-static int cs4270_i2c_probe(struct i2c_adapter *adapter, int addr, int kind)
+static int cs4270_i2c_probe(struct i2c_client *i2c_client,
+	const struct i2c_device_id *id)
 {
 	struct snd_soc_device *socdev = cs4270_socdev;
 	struct snd_soc_codec *codec = socdev->codec;
-	struct i2c_client *i2c_client = NULL;
 	int i;
 	int ret = 0;
 
@@ -578,12 +556,6 @@
 
 	/* Note: codec_dai->codec is NULL here */
 
-	i2c_client = kzalloc(sizeof(struct i2c_client), GFP_KERNEL);
-	if (!i2c_client) {
-		printk(KERN_ERR "cs4270: could not allocate I2C client\n");
-		return -ENOMEM;
-	}
-
 	codec->reg_cache = kzalloc(CS4270_NUMREGS, GFP_KERNEL);
 	if (!codec->reg_cache) {
 		printk(KERN_ERR "cs4270: could not allocate register cache\n");
@@ -591,13 +563,6 @@
 		goto error;
 	}
 
-	i2c_set_clientdata(i2c_client, codec);
-	strcpy(i2c_client->name, "CS4270");
-
-	i2c_client->driver = &cs4270_i2c_driver;
-	i2c_client->adapter = adapter;
-	i2c_client->addr = addr;
-
 	/* Verify that we have a CS4270 */
 
 	ret = i2c_smbus_read_byte_data(i2c_client, CS4270_CHIPID);
@@ -612,18 +577,10 @@
 		goto error;
 	}
 
-	printk(KERN_INFO "cs4270: found device at I2C address %X\n", addr);
+	printk(KERN_INFO "cs4270: found device at I2C address %X\n",
+		i2c_client->addr);
 	printk(KERN_INFO "cs4270: hardware revision %X\n", ret & 0xF);
 
-	/* Tell the I2C layer a new client has arrived */
-
-	ret = i2c_attach_client(i2c_client);
-	if (ret) {
-		printk(KERN_ERR "cs4270: could not attach codec, "
-			"I2C address %x, error code %i\n", addr, ret);
-		goto error;
-	}
-
 	codec->control_data = i2c_client;
 	codec->read = cs4270_read_reg_cache;
 	codec->write = cs4270_i2c_write;
@@ -648,20 +605,17 @@
 			goto error;
 	}
 
+	i2c_set_clientdata(i2c_client, codec);
+
 	return 0;
 
 error:
-	if (codec->control_data) {
-		i2c_detach_client(i2c_client);
-		codec->control_data = NULL;
-	}
+	codec->control_data = NULL;
 
 	kfree(codec->reg_cache);
 	codec->reg_cache = NULL;
 	codec->reg_cache_size = 0;
 
-	kfree(i2c_client);
-
 	return ret;
 }
 
@@ -727,7 +681,7 @@
 	ret = snd_soc_new_pcms(socdev, SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1);
 	if (ret < 0) {
 		printk(KERN_ERR "cs4270: failed to create PCMs\n");
-		return ret;
+		goto error_free_codec;
 	}
 
 #ifdef USE_I2C
@@ -736,8 +690,7 @@
 	ret = i2c_add_driver(&cs4270_i2c_driver);
 	if (ret) {
 		printk(KERN_ERR "cs4270: failed to attach driver");
-		snd_soc_free_pcms(socdev);
-		return ret;
+		goto error_free_pcms;
 	}
 
 	/* Did we find a CS4270 on the I2C bus? */
@@ -759,10 +712,23 @@
 	ret = snd_soc_register_card(socdev);
 	if (ret < 0) {
 		printk(KERN_ERR "cs4270: failed to register card\n");
-		snd_soc_free_pcms(socdev);
-		return ret;
+		goto error_del_driver;
 	}
 
+	return 0;
+
+error_del_driver:
+#ifdef USE_I2C
+	i2c_del_driver(&cs4270_i2c_driver);
+
+error_free_pcms:
+#endif
+	snd_soc_free_pcms(socdev);
+
+error_free_codec:
+	kfree(socdev->codec);
+	socdev->codec = NULL;
+
 	return ret;
 }
 
@@ -773,8 +739,7 @@
 	snd_soc_free_pcms(socdev);
 
 #ifdef USE_I2C
-	if (socdev->codec->control_data)
-		i2c_del_driver(&cs4270_i2c_driver);
+	i2c_del_driver(&cs4270_i2c_driver);
 #endif
 
 	kfree(socdev->codec);
diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c
index 5761164..e873414 100644
--- a/sound/soc/codecs/wm8753.c
+++ b/sound/soc/codecs/wm8753.c
@@ -583,7 +583,7 @@
 
 	/* out 4 */
 	{"Out4 Mux", "VREF", "VREF"},
-	{"Out4 Mux", "Capture ST", "Capture ST Mixer"},
+	{"Out4 Mux", "Capture ST", "Playback Mixer"},
 	{"Out4 Mux", "LOUT2", "LOUT2"},
 	{"Out 4", NULL, "Out4 Mux"},
 	{"OUT4", NULL, "Out 4"},
@@ -607,7 +607,7 @@
 	/* Capture Right Mux */
 	{"Capture Right Mux", "PGA", "Right Capture Volume"},
 	{"Capture Right Mux", "Line or RXP-RXN", "Line Right Mux"},
-	{"Capture Right Mux", "Sidetone", "Capture ST Mixer"},
+	{"Capture Right Mux", "Sidetone", "Playback Mixer"},
 
 	/* Mono Capture mixer-mux */
 	{"Capture Right Mixer", "Stereo", "Capture Right Mux"},