Merge git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86

* git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86: (78 commits)
  x86: fix RTC lockdep warning: potential hardirq recursion
  x86: cpa, micro-optimization
  x86: cpa, clean up code flow
  x86: cpa, eliminate CPA_ enum
  x86: cpa, cleanups
  x86: implement gbpages support in change_page_attr()
  x86: support gbpages in pagetable dump
  x86: add gbpages support to lookup_address
  x86: add pgtable accessor functions for gbpages
  x86: add PUD_PAGE_SIZE
  x86: add feature macros for the gbpages cpuid bit
  x86: switch direct mapping setup over to set_pte
  x86: fix page-present check in cpa_flush_range
  x86: remove cpa warning
  x86: remove now unused clear_kernel_mapping
  x86: switch pci-gart over to using set_memory_np() instead of clear_kernel_mapping()
  x86: cpa selftest, skip non present entries
  x86: CPA fix pagetable split
  x86: rename LARGE_PAGE_SIZE to PMD_PAGE_SIZE
  x86: cpa, fix lookup_address
  ...

25 files changed, 98 insertions, 135 deletions

diff --git a/include/asm-generic/rtc.h b/include/asm-generic/rtc.h
index d3238f1f..dd1bed8 100644
--- a/include/asm-generic/rtc.h
+++ b/include/asm-generic/rtc.h
@@ -35,10 +35,11 @@
 static inline unsigned char rtc_is_updating(void)
 {
 	unsigned char uip;
+	unsigned long flags;
 
-	spin_lock_irq(&rtc_lock);
+	spin_lock_irqsave(&rtc_lock, flags);
 	uip = (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP);
-	spin_unlock_irq(&rtc_lock);
+	spin_unlock_irqrestore(&rtc_lock, flags);
 	return uip;
 }
 
@@ -46,6 +47,8 @@ static inline unsigned int get_rtc_time(struct rtc_time *time)
 {
 	unsigned long uip_watchdog = jiffies;
 	unsigned char ctrl;
+	unsigned long flags;
+
 #ifdef CONFIG_MACH_DECSTATION
 	unsigned int real_year;
 #endif
@@ -72,7 +75,7 @@ static inline unsigned int get_rtc_time(struct rtc_time *time)
 	 * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated
 	 * by the RTC when initially set to a non-zero value.
 	 */
-	spin_lock_irq(&rtc_lock);
+	spin_lock_irqsave(&rtc_lock, flags);
 	time->tm_sec = CMOS_READ(RTC_SECONDS);
 	time->tm_min = CMOS_READ(RTC_MINUTES);
 	time->tm_hour = CMOS_READ(RTC_HOURS);
@@ -83,7 +86,7 @@ static inline unsigned int get_rtc_time(struct rtc_time *time)
 	real_year = CMOS_READ(RTC_DEC_YEAR);
 #endif
 	ctrl = CMOS_READ(RTC_CONTROL);
-	spin_unlock_irq(&rtc_lock);
+	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
 	{
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 75f2bfa..f490e43 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -14,7 +14,6 @@
 #define _ASM_GENERIC__TLB_H
 
 #include <linux/swap.h>
-#include <linux/quicklist.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
diff --git a/include/asm-x86/asm.h b/include/asm-x86/asm.h
index 1a6980a..90dec0c 100644
--- a/include/asm-x86/asm.h
+++ b/include/asm-x86/asm.h
@@ -29,4 +29,11 @@
 
 #endif /* CONFIG_X86_32 */
 
+/* Exception table entry */
+# define _ASM_EXTABLE(from,to) \
+	" .section __ex_table,\"a\"\n" \
+	_ASM_ALIGN "\n" \
+	_ASM_PTR #from "," #to "\n" \
+	" .previous\n"
+
 #endif /* _ASM_X86_ASM_H */
diff --git a/include/asm-x86/bugs.h b/include/asm-x86/bugs.h
index 3fcc30d..021cbdd 100644
--- a/include/asm-x86/bugs.h
+++ b/include/asm-x86/bugs.h
@@ -2,6 +2,6 @@
 #define _ASM_X86_BUGS_H
 
 extern void check_bugs(void);
-extern int ppro_with_ram_bug(void);
+int ppro_with_ram_bug(void);
 
 #endif /* _ASM_X86_BUGS_H */
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
index 3fb7dfa..065e929 100644
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -4,9 +4,6 @@
 #ifndef _ASM_X86_CPUFEATURE_H
 #define _ASM_X86_CPUFEATURE_H
 
-#ifndef __ASSEMBLY__
-#include <linux/bitops.h>
-#endif
 #include <asm/required-features.h>
 
 #define NCAPINTS	8	/* N 32-bit words worth of info */
@@ -49,6 +46,7 @@
 #define X86_FEATURE_MP		(1*32+19) /* MP Capable. */
 #define X86_FEATURE_NX		(1*32+20) /* Execute Disable */
 #define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_GBPAGES	(1*32+26) /* GB pages */
 #define X86_FEATURE_RDTSCP	(1*32+27) /* RDTSCP */
 #define X86_FEATURE_LM		(1*32+29) /* Long Mode (x86-64) */
 #define X86_FEATURE_3DNOWEXT	(1*32+30) /* AMD 3DNow! extensions */
@@ -115,6 +113,13 @@
  */
 #define X86_FEATURE_IDA		(7*32+ 0) /* Intel Dynamic Acceleration */
 
+#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+
+#include <linux/bitops.h>
+
+extern const char * const x86_cap_flags[NCAPINTS*32];
+extern const char * const x86_power_flags[32];
+
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) &&					\
 	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||	\
@@ -175,6 +180,7 @@
 #define cpu_has_pebs		boot_cpu_has(X86_FEATURE_PEBS)
 #define cpu_has_clflush		boot_cpu_has(X86_FEATURE_CLFLSH)
 #define cpu_has_bts		boot_cpu_has(X86_FEATURE_BTS)
+#define cpu_has_gbpages		boot_cpu_has(X86_FEATURE_GBPAGES)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg		1
@@ -204,4 +210,6 @@
 
 #endif /* CONFIG_X86_64 */
 
+#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
+
 #endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/include/asm-x86/efi.h b/include/asm-x86/efi.h
index 9c68a1f..ea9734b 100644
--- a/include/asm-x86/efi.h
+++ b/include/asm-x86/efi.h
@@ -33,7 +33,7 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 #define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)	\
 	efi_call_virt(f, a1, a2, a3, a4, a5, a6)
 
-#define efi_ioremap(addr, size)			ioremap(addr, size)
+#define efi_ioremap(addr, size)			ioremap_cache(addr, size)
 
 #else /* !CONFIG_X86_32 */
 
@@ -86,7 +86,7 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 	efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
-extern void *efi_ioremap(unsigned long offset, unsigned long size);
+extern void *efi_ioremap(unsigned long addr, unsigned long size);
 
 #endif /* CONFIG_X86_32 */
 
diff --git a/include/asm-x86/futex.h b/include/asm-x86/futex.h
index 9d91926..cd9f894 100644
--- a/include/asm-x86/futex.h
+++ b/include/asm-x86/futex.h
@@ -17,11 +17,8 @@
 "2:	.section .fixup,\"ax\"\n				\
 3:	mov	%3, %1\n					\
 	jmp	2b\n						\
-	.previous\n						\
-	.section __ex_table,\"a\"\n				\
-	.align	8\n"						\
-	_ASM_PTR "1b,3b\n					\
-	.previous"						\
+	.previous\n"						\
+	_ASM_EXTABLE(1b,3b)					\
 	: "=r" (oldval), "=r" (ret), "+m" (*uaddr)		\
 	: "i" (-EFAULT), "0" (oparg), "1" (0))
 
@@ -35,11 +32,9 @@
 3:	.section .fixup,\"ax\"\n				\
 4:	mov	%5, %1\n					\
 	jmp	3b\n						\
-	.previous\n						\
-	.section __ex_table,\"a\"\n				\
-	.align	8\n"						\
-	_ASM_PTR "1b,4b,2b,4b\n					\
-	.previous"						\
+	.previous\n"						\
+	_ASM_EXTABLE(1b,4b)					\
+	_ASM_EXTABLE(2b,4b)					\
 	: "=&a" (oldval), "=&r" (ret), "+m" (*uaddr),		\
 	  "=&r" (tem)						\
 	: "r" (oparg), "i" (-EFAULT), "1" (0))
@@ -111,18 +106,12 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 		return -EFAULT;
 
 	__asm__ __volatile__(
-
 		"1:	lock; cmpxchgl %3, %1			\n"
 		"2:	.section .fixup, \"ax\"			\n"
 		"3:	mov     %2, %0				\n"
 		"	jmp     2b				\n"
 		"	.previous				\n"
-
-		"	.section __ex_table, \"a\"		\n"
-		"	.align  8				\n"
-			_ASM_PTR " 1b,3b			\n"
-		"	.previous				\n"
-
+		_ASM_EXTABLE(1b,3b)
 		: "=a" (oldval), "+m" (*uaddr)
 		: "i" (-EFAULT), "r" (newval), "0" (oldval)
 		: "memory"
diff --git a/include/asm-x86/highmem.h b/include/asm-x86/highmem.h
index 13cdcd6..c25cfca 100644
--- a/include/asm-x86/highmem.h
+++ b/include/asm-x86/highmem.h
@@ -63,8 +63,8 @@ extern pte_t *pkmap_page_table;
 #define PKMAP_NR(virt)  ((virt-PKMAP_BASE) >> PAGE_SHIFT)
 #define PKMAP_ADDR(nr)  (PKMAP_BASE + ((nr) << PAGE_SHIFT))
 
-extern void * FASTCALL(kmap_high(struct page *page));
-extern void FASTCALL(kunmap_high(struct page *page));
+extern void *kmap_high(struct page *page);
+extern void kunmap_high(struct page *page);
 
 void *kmap(struct page *page);
 void kunmap(struct page *page);
diff --git a/include/asm-x86/hw_irq_32.h b/include/asm-x86/hw_irq_32.h
index 6d65fbb..ea88054 100644
--- a/include/asm-x86/hw_irq_32.h
+++ b/include/asm-x86/hw_irq_32.h
@@ -47,7 +47,7 @@ void enable_8259A_irq(unsigned int irq);
 int i8259A_irq_pending(unsigned int irq);
 void make_8259A_irq(unsigned int irq);
 void init_8259A(int aeoi);
-void FASTCALL(send_IPI_self(int vector));
+void send_IPI_self(int vector);
 void init_VISWS_APIC_irqs(void);
 void setup_IO_APIC(void);
 void disable_IO_APIC(void);
diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
index ba8105c..6b1895c 100644
--- a/include/asm-x86/i387.h
+++ b/include/asm-x86/i387.h
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/kernel_stat.h>
 #include <linux/regset.h>
+#include <asm/asm.h>
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
 #include <asm/user.h>
@@ -41,10 +42,7 @@ static inline void tolerant_fwait(void)
 {
 	asm volatile("1: fwait\n"
 		     "2:\n"
-		     "   .section __ex_table,\"a\"\n"
-		     "	.align 8\n"
-		     "	.quad 1b,2b\n"
-		     "	.previous\n");
+		     _ASM_EXTABLE(1b,2b));
 }
 
 static inline int restore_fpu_checking(struct i387_fxsave_struct *fx)
@@ -57,10 +55,7 @@ static inline int restore_fpu_checking(struct i387_fxsave_struct *fx)
 		     "3:  movl $-1,%[err]\n"
 		     "    jmp  2b\n"
 		     ".previous\n"
-		     ".section __ex_table,\"a\"\n"
-		     "   .align 8\n"
-		     "   .quad  1b,3b\n"
-		     ".previous"
+		     _ASM_EXTABLE(1b,3b)
 		     : [err] "=r" (err)
 #if 0 /* See comment in __save_init_fpu() below. */
 		     : [fx] "r" (fx), "m" (*fx), "0" (0));
@@ -99,10 +94,7 @@ static inline int save_i387_checking(struct i387_fxsave_struct __user *fx)
 		     "3:  movl $-1,%[err]\n"
 		     "    jmp  2b\n"
 		     ".previous\n"
-		     ".section __ex_table,\"a\"\n"
-		     "   .align 8\n"
-		     "   .quad  1b,3b\n"
-		     ".previous"
+		     _ASM_EXTABLE(1b,3b)
 		     : [err] "=r" (err), "=m" (*fx)
 #if 0 /* See comment in __fxsave_clear() below. */
 		     : [fx] "r" (fx), "0" (0));
diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h
index 586d7aa..58d2c45 100644
--- a/include/asm-x86/io_32.h
+++ b/include/asm-x86/io_32.h
@@ -275,29 +275,6 @@ static inline void slow_down_io(void) {
 
 #endif
 
-#ifdef CONFIG_X86_NUMAQ
-extern void *xquad_portio;    /* Where the IO area was mapped */
-#define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port)
-#define __BUILDIO(bwl,bw,type) \
-static inline void out##bwl##_quad(unsigned type value, int port, int quad) { \
-	if (xquad_portio) \
-		write##bwl(value, XQUAD_PORT_ADDR(port, quad)); \
-	else \
-		out##bwl##_local(value, port); \
-} \
-static inline void out##bwl(unsigned type value, int port) { \
-	out##bwl##_quad(value, port, 0); \
-} \
-static inline unsigned type in##bwl##_quad(int port, int quad) { \
-	if (xquad_portio) \
-		return read##bwl(XQUAD_PORT_ADDR(port, quad)); \
-	else \
-		return in##bwl##_local(port); \
-} \
-static inline unsigned type in##bwl(int port) { \
-	return in##bwl##_quad(port, 0); \
-}
-#else
 #define __BUILDIO(bwl,bw,type) \
 static inline void out##bwl(unsigned type value, int port) { \
 	out##bwl##_local(value, port); \
@@ -305,8 +282,6 @@ static inline void out##bwl(unsigned type value, int port) { \
 static inline unsigned type in##bwl(int port) { \
 	return in##bwl##_local(port); \
 }
-#endif
-
 
 #define BUILDIO(bwl,bw,type) \
 static inline void out##bwl##_local(unsigned type value, int port) { \
diff --git a/include/asm-x86/mach-numaq/mach_apic.h b/include/asm-x86/mach-numaq/mach_apic.h
index 17e183b..3b637fa 100644
--- a/include/asm-x86/mach-numaq/mach_apic.h
+++ b/include/asm-x86/mach-numaq/mach_apic.h
@@ -109,6 +109,8 @@ static inline int mpc_apic_id(struct mpc_config_processor *m,
 	return logical_apicid;
 }
 
+extern void *xquad_portio;
+
 static inline void setup_portio_remap(void)
 {
 	int num_quads = num_online_nodes();
diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h
index 204a8a3..3ca29eb 100644
--- a/include/asm-x86/msr.h
+++ b/include/asm-x86/msr.h
@@ -57,10 +57,7 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 		     ".section .fixup,\"ax\"\n\t"
 		     "3:  mov %3,%0 ; jmp 1b\n\t"
 		     ".previous\n\t"
-		     ".section __ex_table,\"a\"\n"
-		     _ASM_ALIGN "\n\t"
-		     _ASM_PTR " 2b,3b\n\t"
-		     ".previous"
+		     _ASM_EXTABLE(2b,3b)
 		     : "=r" (*err), EAX_EDX_RET(val, low, high)
 		     : "c" (msr), "i" (-EFAULT));
 	return EAX_EDX_VAL(val, low, high);
@@ -81,10 +78,7 @@ static inline int native_write_msr_safe(unsigned int msr,
 		     ".section .fixup,\"ax\"\n\t"
 		     "3:  mov %4,%0 ; jmp 1b\n\t"
 		     ".previous\n\t"
-		     ".section __ex_table,\"a\"\n"
-		     _ASM_ALIGN "\n\t"
-		     _ASM_PTR " 2b,3b\n\t"
-		     ".previous"
+		     _ASM_EXTABLE(2b,3b)
 		     : "=a" (err)
 		     : "c" (msr), "0" (low), "d" (high),
 		       "i" (-EFAULT));
diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h
index c8b30ef..1cb7c51 100644
--- a/include/asm-x86/page.h
+++ b/include/asm-x86/page.h
@@ -13,8 +13,8 @@
 #define PHYSICAL_PAGE_MASK	(PAGE_MASK & __PHYSICAL_MASK)
 #define PTE_MASK		(_AT(long, PHYSICAL_PAGE_MASK))
 
-#define LARGE_PAGE_SIZE		(_AC(1,UL) << PMD_SHIFT)
-#define LARGE_PAGE_MASK		(~(LARGE_PAGE_SIZE-1))
+#define PMD_PAGE_SIZE		(_AC(1, UL) << PMD_SHIFT)
+#define PMD_PAGE_MASK		(~(PMD_PAGE_SIZE-1))
 
 #define HPAGE_SHIFT		PMD_SHIFT
 #define HPAGE_SIZE		(_AC(1,UL) << HPAGE_SHIFT)
diff --git a/include/asm-x86/page_64.h b/include/asm-x86/page_64.h
index c1ac42d..dcf0c07 100644
--- a/include/asm-x86/page_64.h
+++ b/include/asm-x86/page_64.h
@@ -23,6 +23,9 @@
 #define MCE_STACK 5
 #define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
 
+#define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
+#define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
+
 #define __PAGE_OFFSET           _AC(0xffff810000000000, UL)
 
 #define __PHYSICAL_START	CONFIG_PHYSICAL_START
diff --git a/include/asm-x86/pgalloc_32.h b/include/asm-x86/pgalloc_32.h
index 7641e7b..6c21ef9 100644
--- a/include/asm-x86/pgalloc_32.h
+++ b/include/asm-x86/pgalloc_32.h
@@ -80,8 +80,10 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 	set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT));
 
 	/*
-	 * Pentium-II erratum A13: in PAE mode we explicitly have to flush
-	 * the TLB via cr3 if the top-level pgd is changed...
+	 * According to Intel App note "TLBs, Paging-Structure Caches,
+	 * and Their Invalidation", April 2007, document 317080-001,
+	 * section 8.1: in PAE mode we explicitly have to flush the
+	 * TLB via cr3 if the top-level pgd is changed...
 	 */
 	if (mm == current->active_mm)
 		write_cr3(read_cr3());
diff --git a/include/asm-x86/pgtable-3level.h b/include/asm-x86/pgtable-3level.h
index a195c3e..1d763ee 100644
--- a/include/asm-x86/pgtable-3level.h
+++ b/include/asm-x86/pgtable-3level.h
@@ -93,26 +93,22 @@ static inline void native_pmd_clear(pmd_t *pmd)
 
 static inline void pud_clear(pud_t *pudp)
 {
+	unsigned long pgd;
+
 	set_pud(pudp, __pud(0));
 
 	/*
-	 * In principle we need to do a cr3 reload here to make sure
-	 * the processor recognizes the changed pgd.  In practice, all
-	 * the places where pud_clear() gets called are followed by
-	 * full tlb flushes anyway, so we can defer the cost here.
-	 *
-	 * Specifically:
-	 *
-	 * mm/memory.c:free_pmd_range() - immediately after the
-	 * pud_clear() it does a pmd_free_tlb().  We change the
-	 * mmu_gather structure to do a full tlb flush (which has the
-	 * effect of reloading cr3) when the pagetable free is
-	 * complete.
+	 * According to Intel App note "TLBs, Paging-Structure Caches,
+	 * and Their Invalidation", April 2007, document 317080-001,
+	 * section 8.1: in PAE mode we explicitly have to flush the
+	 * TLB via cr3 if the top-level pgd is changed...
 	 *
-	 * arch/x86/mm/hugetlbpage.c:huge_pmd_unshare() - the call to
-	 * this is followed by a flush_tlb_range, which on x86 does a
-	 * full tlb flush.
+	 * Make sure the pud entry we're updating is within the
+	 * current pgd to avoid unnecessary TLB flushes.
 	 */
+	pgd = read_cr3();
+	if (__pa(pudp) >= pgd && __pa(pudp) < (pgd + sizeof(pgd_t)*PTRS_PER_PGD))
+		write_cr3(pgd);
 }
 
 #define pud_page(pud) \
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
index cd2524f..44c0a4f 100644
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -13,10 +13,12 @@
 #define _PAGE_BIT_DIRTY		6
 #define _PAGE_BIT_FILE		6
 #define _PAGE_BIT_PSE		7	/* 4 MB (or 2MB) page */
+#define _PAGE_BIT_PAT		7	/* on 4KB pages */
 #define _PAGE_BIT_GLOBAL	8	/* Global TLB entry PPro+ */
 #define _PAGE_BIT_UNUSED1	9	/* available for programmer */
 #define _PAGE_BIT_UNUSED2	10
 #define _PAGE_BIT_UNUSED3	11
+#define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
 /*
@@ -36,6 +38,8 @@
 #define _PAGE_UNUSED1	(_AC(1, L)<<_PAGE_BIT_UNUSED1)
 #define _PAGE_UNUSED2	(_AC(1, L)<<_PAGE_BIT_UNUSED2)
 #define _PAGE_UNUSED3	(_AC(1, L)<<_PAGE_BIT_UNUSED3)
+#define _PAGE_PAT	(_AC(1, L)<<_PAGE_BIT_PAT)
+#define _PAGE_PAT_LARGE (_AC(1, L)<<_PAGE_BIT_PAT_LARGE)
 
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AC(1, ULL) << _PAGE_BIT_NX)
diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h
index 21e70fb..935630d 100644
--- a/include/asm-x86/pgtable_32.h
+++ b/include/asm-x86/pgtable_32.h
@@ -148,6 +148,8 @@ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
  */
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
+static inline int pud_large(pud_t pud) { return 0; }
+
 /*
  * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
  *
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index 6e615a1..bd4740a 100644
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -21,7 +21,6 @@ extern pgd_t init_level4_pgt[];
 #define swapper_pg_dir init_level4_pgt
 
 extern void paging_init(void);
-extern void clear_kernel_mapping(unsigned long addr, unsigned long size);
 
 #endif /* !__ASSEMBLY__ */
 
@@ -199,6 +198,12 @@ static inline unsigned long pmd_bad(pmd_t pmd)
 #define pud_offset(pgd, address) ((pud_t *) pgd_page_vaddr(*(pgd)) + pud_index(address))
 #define pud_present(pud) (pud_val(pud) & _PAGE_PRESENT)
 
+static inline int pud_large(pud_t pte)
+{
+	return (pud_val(pte) & (_PAGE_PSE|_PAGE_PRESENT)) ==
+		(_PAGE_PSE|_PAGE_PRESENT);
+}
+
 /* PMD  - Level 2 access */
 #define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val(pmd) & PTE_MASK))
 #define pmd_page(pmd)		(pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
diff --git a/include/asm-x86/string_32.h b/include/asm-x86/string_32.h
index 55bfa30..c5d13a8 100644
--- a/include/asm-x86/string_32.h
+++ b/include/asm-x86/string_32.h
@@ -213,14 +213,14 @@ static __always_inline void * __constant_c_and_count_memset(void * s, unsigned l
 		case 0:
 			return s;
 		case 1:
-			*(unsigned char *)s = pattern;
+			*(unsigned char *)s = pattern & 0xff;
 			return s;
 		case 2:
-			*(unsigned short *)s = pattern;
+			*(unsigned short *)s = pattern & 0xffff;
 			return s;
 		case 3:
-			*(unsigned short *)s = pattern;
-			*(2+(unsigned char *)s) = pattern;
+			*(unsigned short *)s = pattern & 0xffff;
+			*(2+(unsigned char *)s) = pattern & 0xff;
 			return s;
 		case 4:
 			*(unsigned long *)s = pattern;
diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h
index ee32ef9..9cff02f 100644
--- a/include/asm-x86/system.h
+++ b/include/asm-x86/system.h
@@ -20,8 +20,8 @@
 #ifdef CONFIG_X86_32
 
 struct task_struct; /* one of the stranger aspects of C forward declarations */
-extern struct task_struct *FASTCALL(__switch_to(struct task_struct *prev,
-						struct task_struct *next));
+struct task_struct *__switch_to(struct task_struct *prev,
+				struct task_struct *next);
 
 /*
  * Saving eflags is important. It switches not only IOPL between tasks,
@@ -130,10 +130,7 @@ extern void load_gs_index(unsigned);
 		"movl %k1, %%" #seg "\n\t"	\
 		"jmp 2b\n"			\
 		".previous\n"			\
-		".section __ex_table,\"a\"\n\t"	\
-		_ASM_ALIGN "\n\t"		\
-		_ASM_PTR " 1b,3b\n"		\
-		".previous"			\
+		_ASM_EXTABLE(1b,3b)		\
 		: :"r" (value), "r" (0))
 
 
@@ -214,12 +211,10 @@ static inline unsigned long native_read_cr4_safe(void)
 	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
 	 * exists, so it will never fail. */
 #ifdef CONFIG_X86_32
-	asm volatile("1: mov %%cr4, %0		\n"
-		"2:				\n"
-		".section __ex_table,\"a\"	\n"
-		".long 1b,2b			\n"
-		".previous			\n"
-		: "=r" (val), "=m" (__force_order) : "0" (0));
+	asm volatile("1: mov %%cr4, %0\n"
+		     "2:\n"
+		     _ASM_EXTABLE(1b,2b)
+		     : "=r" (val), "=m" (__force_order) : "0" (0));
 #else
 	val = native_read_cr4();
 #endif
@@ -276,9 +271,9 @@ static inline void native_wbinvd(void)
 
 #endif /* __KERNEL__ */
 
-static inline void clflush(void *__p)
+static inline void clflush(volatile void *__p)
 {
-	asm volatile("clflush %0" : "+m" (*(char __force *)__p));
+	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
 }
 
 #define nop() __asm__ __volatile__ ("nop")
diff --git a/include/asm-x86/uaccess_32.h b/include/asm-x86/uaccess_32.h
index d2a4f7b..fcc570e 100644
--- a/include/asm-x86/uaccess_32.h
+++ b/include/asm-x86/uaccess_32.h
@@ -8,6 +8,7 @@
 #include <linux/thread_info.h>
 #include <linux/prefetch.h>
 #include <linux/string.h>
+#include <asm/asm.h>
 #include <asm/page.h>
 
 #define VERIFY_READ 0
@@ -287,11 +288,8 @@ extern void __put_user_8(void);
 		"4:	movl %3,%0\n"				\
 		"	jmp 3b\n"				\
 		".previous\n"					\
-		".section __ex_table,\"a\"\n"			\
-		"	.align 4\n"				\
-		"	.long 1b,4b\n"				\
-		"	.long 2b,4b\n"				\
-		".previous"					\
+		_ASM_EXTABLE(1b,4b)				\
+		_ASM_EXTABLE(2b,4b)				\
 		: "=r"(err)					\
 		: "A" (x), "r" (addr), "i"(-EFAULT), "0"(err))
 
@@ -338,10 +336,7 @@ struct __large_struct { unsigned long buf[100]; };
 		"3:	movl %3,%0\n"					\
 		"	jmp 2b\n"					\
 		".previous\n"						\
-		".section __ex_table,\"a\"\n"				\
-		"	.align 4\n"					\
-		"	.long 1b,3b\n"					\
-		".previous"						\
+		_ASM_EXTABLE(1b,3b)					\
 		: "=r"(err)						\
 		: ltype (x), "m"(__m(addr)), "i"(errret), "0"(err))
 
@@ -378,10 +373,7 @@ do {									\
 		"	xor"itype" %"rtype"1,%"rtype"1\n"		\
 		"	jmp 2b\n"					\
 		".previous\n"						\
-		".section __ex_table,\"a\"\n"				\
-		"	.align 4\n"					\
-		"	.long 1b,3b\n"					\
-		".previous"						\
+		_ASM_EXTABLE(1b,3b)					\
 		: "=r"(err), ltype (x)					\
 		: "m"(__m(addr)), "i"(errret), "0"(err))
 
diff --git a/include/asm-x86/uaccess_64.h b/include/asm-x86/uaccess_64.h
index 31d7947..b87eb4b 100644
--- a/include/asm-x86/uaccess_64.h
+++ b/include/asm-x86/uaccess_64.h
@@ -181,10 +181,7 @@ struct __large_struct { unsigned long buf[100]; };
 		"3:	mov %3,%0\n"				\
 		"	jmp 2b\n"				\
 		".previous\n"					\
-		".section __ex_table,\"a\"\n"			\
-		"	.align 8\n"				\
-		"	.quad 1b,3b\n"				\
-		".previous"					\
+		_ASM_EXTABLE(1b,3b)				\
 		: "=r"(err)					\
 		: ltype (x), "m"(__m(addr)), "i"(errno), "0"(err))
 
@@ -226,10 +223,7 @@ do {									\
 		"	xor"itype" %"rtype"1,%"rtype"1\n"	\
 		"	jmp 2b\n"				\
 		".previous\n"					\
-		".section __ex_table,\"a\"\n"			\
-		"	.align 8\n"				\
-		"	.quad 1b,3b\n"				\
-		".previous"					\
+		_ASM_EXTABLE(1b,3b)				\
 		: "=r"(err), ltype (x)				\
 		: "m"(__m(addr)), "i"(errno), "0"(err))
 
diff --git a/include/asm-x86/vm86.h b/include/asm-x86/vm86.h
index a5edf51..c92fe4a 100644
--- a/include/asm-x86/vm86.h
+++ b/include/asm-x86/vm86.h
@@ -195,6 +195,7 @@ struct kernel_vm86_struct {
 
 void handle_vm86_fault(struct kernel_vm86_regs *, long);
 int handle_vm86_trap(struct kernel_vm86_regs *, long, int);
+struct pt_regs *save_v86_state(struct kernel_vm86_regs *);
 
 struct task_struct;
 void release_vm86_irqs(struct task_struct *);