Merge branch 'linus' into x86/mm

Conflicts:
	arch/x86/mm/fault.c

50 files changed, 330 insertions, 180 deletions

diff --git a/arch/x86/boot/video-vesa.c b/arch/x86/boot/video-vesa.c
index 75115849af3..4a58c8ce3f6 100644
--- a/arch/x86/boot/video-vesa.c
+++ b/arch/x86/boot/video-vesa.c
@@ -269,9 +269,8 @@ void vesa_store_edid(void)
 	   we genuinely have to assume all registers are destroyed here. */
 
 	asm("pushw %%es; movw %2,%%es; "INT10"; popw %%es"
-	    : "+a" (ax), "+b" (bx)
-	    :  "c" (cx), "D" (di)
-	    : "esi");
+	    : "+a" (ax), "+b" (bx), "+c" (cx), "+D" (di)
+	    : : "esi", "edx");
 
 	if (ax != 0x004f)
 		return;		/* No EDID */
@@ -285,9 +284,9 @@ void vesa_store_edid(void)
 	dx = 0;			/* EDID block number */
 	di =(size_t) &boot_params.edid_info; /* (ES:)Pointer to block */
 	asm(INT10
-	    : "+a" (ax), "+b" (bx), "+d" (dx), "=m" (boot_params.edid_info)
-	    : "c" (cx), "D" (di)
-	    : "esi");
+	    : "+a" (ax), "+b" (bx), "+d" (dx), "=m" (boot_params.edid_info),
+	      "+c" (cx), "+D" (di)
+	    : : "esi");
 #endif /* CONFIG_FIRMWARE_EDID */
 }
 
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index b30a08ed8eb..edba00d98ac 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1331,8 +1331,8 @@ CONFIG_I2C_I801=y
 # Miscellaneous I2C Chip support
 #
 # CONFIG_DS1682 is not set
-# CONFIG_AT24 is not set
-# CONFIG_SENSORS_EEPROM is not set
+# CONFIG_EEPROM_AT24 is not set
+# CONFIG_EEPROM_LEGACY is not set
 # CONFIG_SENSORS_PCF8574 is not set
 # CONFIG_PCF8575 is not set
 # CONFIG_SENSORS_PCA9539 is not set
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 0e7dbc0a3e4..322dd2748fc 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1311,8 +1311,8 @@ CONFIG_I2C_I801=y
 # Miscellaneous I2C Chip support
 #
 # CONFIG_DS1682 is not set
-# CONFIG_AT24 is not set
-# CONFIG_SENSORS_EEPROM is not set
+# CONFIG_EEPROM_AT24 is not set
+# CONFIG_EEPROM_LEGACY is not set
 # CONFIG_SENSORS_PCF8574 is not set
 # CONFIG_PCF8575 is not set
 # CONFIG_SENSORS_PCA9539 is not set
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index e02a359d2aa..02b47a603fc 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -3,6 +3,9 @@
 
 /*
  * Copyright 1992, Linus Torvalds.
+ *
+ * Note: inlines with more than a single statement should be marked
+ * __always_inline to avoid problems with older gcc's inlining heuristics.
  */
 
 #ifndef _LINUX_BITOPS_H
@@ -53,7 +56,8 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void set_bit(unsigned int nr, volatile unsigned long *addr)
+static __always_inline void
+set_bit(unsigned int nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "orb %1,%0"
@@ -90,7 +94,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
  * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
  * in order to ensure changes are visible on other processors.
  */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+clear_bit(int nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "andb %1,%0"
@@ -204,7 +209,8 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
  *
  * This is the same as test_and_set_bit on x86.
  */
-static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+static __always_inline int
+test_and_set_bit_lock(int nr, volatile unsigned long *addr)
 {
 	return test_and_set_bit(nr, addr);
 }
@@ -300,7 +306,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 	return oldbit;
 }
 
-static inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
+static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
 {
 	return ((1UL << (nr % BITS_PER_LONG)) &
 		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 4035357f5b9..132a134d12f 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -2,8 +2,8 @@
 #define _ASM_X86_DMA_MAPPING_H
 
 /*
- * IOMMU interface. See Documentation/DMA-mapping.txt and DMA-API.txt for
- * documentation.
+ * IOMMU interface. See Documentation/PCI/PCI-DMA-mapping.txt and
+ * Documentation/DMA-API.txt for documentation.
  */
 
 #include <linux/scatterlist.h>
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 3d8ceddbd40..00d41ce4c84 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -49,6 +49,7 @@
 #define E820_RESERVED_KERN        128
 
 #ifndef __ASSEMBLY__
+#include <linux/types.h>
 struct e820entry {
 	__u64 addr;	/* start of memory segment */
 	__u64 size;	/* size of memory segment */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 05cfed4485f..1dbbdf4be9b 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -99,7 +99,6 @@ extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size);
  * A boot-time mapping is currently limited to at most 16 pages.
  */
 extern void early_ioremap_init(void);
-extern void early_ioremap_clear(void);
 extern void early_ioremap_reset(void);
 extern void __iomem *early_ioremap(unsigned long offset, unsigned long size);
 extern void __iomem *early_memremap(unsigned long offset, unsigned long size);
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index b95162af0bf..d2e3bf3608a 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -6,7 +6,7 @@
  *
  */
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <linux/ioctl.h>
 
 /* Architectural interrupt line count. */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 1d6e17c2f23..32c6e17b960 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -3,8 +3,8 @@
 
 #ifdef __x86_64__
 
+#include <linux/types.h>
 #include <asm/ioctls.h>
-#include <asm/types.h>
 
 /*
  * Machine Check support for x86
@@ -115,8 +115,6 @@ extern int mce_notify_user(void);
 
 #endif /* !CONFIG_X86_32 */
 
-
-
 #ifdef CONFIG_X86_MCE
 extern void mcheck_init(struct cpuinfo_x86 *c);
 #else
@@ -126,5 +124,4 @@ extern void stop_mce(void);
 extern void restart_mce(void);
 
 #endif /* __KERNEL__ */
-
 #endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index cb58643947b..358acc59ae0 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -202,6 +202,35 @@
 #define MSR_IA32_THERM_STATUS		0x0000019c
 #define MSR_IA32_MISC_ENABLE		0x000001a0
 
+/* MISC_ENABLE bits: architectural */
+#define MSR_IA32_MISC_ENABLE_FAST_STRING	(1ULL << 0)
+#define MSR_IA32_MISC_ENABLE_TCC		(1ULL << 1)
+#define MSR_IA32_MISC_ENABLE_EMON		(1ULL << 7)
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL	(1ULL << 11)
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL	(1ULL << 12)
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP	(1ULL << 16)
+#define MSR_IA32_MISC_ENABLE_MWAIT		(1ULL << 18)
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID	(1ULL << 22)
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE	(1ULL << 23)
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE		(1ULL << 34)
+
+/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT		(1ULL << 2)
+#define MSR_IA32_MISC_ENABLE_TM1		(1ULL << 3)
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE	(1ULL << 4)
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE	(1ULL << 6)
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK	(1ULL << 8)
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE	(1ULL << 9)
+#define MSR_IA32_MISC_ENABLE_FERR		(1ULL << 10)
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX	(1ULL << 10)
+#define MSR_IA32_MISC_ENABLE_TM2		(1ULL << 13)
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE	(1ULL << 19)
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK	(1ULL << 20)
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT	(1ULL << 24)
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE	(1ULL << 37)
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE	(1ULL << 38)
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE	(1ULL << 39)
+
 /* Intel Model 6 */
 #define MSR_P6_EVNTSEL0			0x00000186
 #define MSR_P6_EVNTSEL1			0x00000187
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index 14080d22edb..a51ada8467d 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -23,6 +23,7 @@
 #ifndef _ASM_X86_MTRR_H
 #define _ASM_X86_MTRR_H
 
+#include <linux/types.h>
 #include <linux/ioctl.h>
 #include <linux/errno.h>
 
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index cb7c151a8bf..dd14c54ac71 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -42,6 +42,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 
 static inline void pte_free(struct mm_struct *mm, struct page *pte)
 {
+	pgtable_page_dtor(pte);
 	__free_page(pte);
 }
 
diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h
index 25f1bb8fc62..8e0f8d199e0 100644
--- a/arch/x86/include/asm/ptrace-abi.h
+++ b/arch/x86/include/asm/ptrace-abi.h
@@ -83,7 +83,7 @@
 #ifdef CONFIG_X86_PTRACE_BTS
 
 #ifndef __ASSEMBLY__
-#include <asm/types.h>
+#include <linux/types.h>
 
 /* configuration/status structure used in PTRACE_BTS_CONFIG and
    PTRACE_BTS_STATUS commands.
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 0afcb5e58ac..ec666491aaa 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -2,7 +2,7 @@
 #define _ASM_X86_SIGCONTEXT_H
 
 #include <linux/compiler.h>
-#include <asm/types.h>
+#include <linux/types.h>
 
 #define FP_XSTATE_MAGIC1	0x46505853U
 #define FP_XSTATE_MAGIC2	0x46505845U
diff --git a/arch/x86/include/asm/sigcontext32.h b/arch/x86/include/asm/sigcontext32.h
index 6126188cf3a..ad1478c4ae1 100644
--- a/arch/x86/include/asm/sigcontext32.h
+++ b/arch/x86/include/asm/sigcontext32.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_SIGCONTEXT32_H
 #define _ASM_X86_SIGCONTEXT32_H
 
+#include <linux/types.h>
+
 /* signal context for 32bit programs. */
 
 #define X86_FXSR_MAGIC		0x0000
diff --git a/arch/x86/include/asm/swab.h b/arch/x86/include/asm/swab.h
index 306d4178ffc..557cd9f0066 100644
--- a/arch/x86/include/asm/swab.h
+++ b/arch/x86/include/asm/swab.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_SWAB_H
 #define _ASM_X86_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <linux/compiler.h>
 
 static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 9c6797c3e56..c0b0bda754e 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -40,7 +40,7 @@ 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(struct pt_regs);
+asmlinkage int sys_rt_sigreturn(unsigned long);
 
 /* kernel/ioport.c */
 asmlinkage long sys_iopl(unsigned long);
diff --git a/arch/x86/include/asm/timex.h b/arch/x86/include/asm/timex.h
index 1287dc1347d..b5c9d45c981 100644
--- a/arch/x86/include/asm/timex.h
+++ b/arch/x86/include/asm/timex.h
@@ -1,18 +1,13 @@
-/* x86 architecture timex specifications */
 #ifndef _ASM_X86_TIMEX_H
 #define _ASM_X86_TIMEX_H
 
 #include <asm/processor.h>
 #include <asm/tsc.h>
 
-#ifdef CONFIG_X86_ELAN
-#  define PIT_TICK_RATE 1189200 /* AMD Elan has different frequency! */
-#elif defined(CONFIG_X86_RDC321X)
-#  define PIT_TICK_RATE 1041667 /* Underlying HZ for R8610 */
-#else
-#  define PIT_TICK_RATE 1193182 /* Underlying HZ */
-#endif
-#define CLOCK_TICK_RATE	PIT_TICK_RATE
+/* The PIT ticks at this frequency (in HZ): */
+#define PIT_TICK_RATE		1193182
+
+#define CLOCK_TICK_RATE		PIT_TICK_RATE
 
 #define ARCH_HAS_READ_CURRENT_TIMER
 
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 0f830e4f567..115449f869e 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -895,6 +895,10 @@ void disable_local_APIC(void)
 {
 	unsigned int value;
 
+	/* APIC hasn't been mapped yet */
+	if (!apic_phys)
+		return;
+
 	clear_local_APIC();
 
 	/*
@@ -1432,7 +1436,7 @@ static int __init detect_init_APIC(void)
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_AMD:
 		if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model > 1) ||
-		    (boot_cpu_data.x86 == 15))
+		    (boot_cpu_data.x86 >= 15))
 			break;
 		goto no_apic;
 	case X86_VENDOR_INTEL:
@@ -1833,6 +1837,11 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	num_processors++;
 	cpu = cpumask_next_zero(-1, cpu_present_mask);
 
+	if (version != apic_version[boot_cpu_physical_apicid])
+		WARN_ONCE(1,
+			"ACPI: apic version mismatch, bootcpu: %x cpu %d: %x\n",
+			apic_version[boot_cpu_physical_apicid], cpu, version);
+
 	physid_set(apicid, phys_cpu_present_map);
 	if (apicid == boot_cpu_physical_apicid) {
 		/*
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 6f11e029e8c..4b1c319d30c 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -145,13 +145,14 @@ typedef union {
 
 struct drv_cmd {
 	unsigned int type;
-	cpumask_var_t mask;
+	const struct cpumask *mask;
 	drv_addr_union addr;
 	u32 val;
 };
 
-static void do_drv_read(struct drv_cmd *cmd)
+static long do_drv_read(void *_cmd)
 {
+	struct drv_cmd *cmd = _cmd;
 	u32 h;
 
 	switch (cmd->type) {
@@ -166,10 +167,12 @@ static void do_drv_read(struct drv_cmd *cmd)
 	default:
 		break;
 	}
+	return 0;
 }
 
-static void do_drv_write(struct drv_cmd *cmd)
+static long do_drv_write(void *_cmd)
 {
+	struct drv_cmd *cmd = _cmd;
 	u32 lo, hi;
 
 	switch (cmd->type) {
@@ -186,30 +189,23 @@ static void do_drv_write(struct drv_cmd *cmd)
 	default:
 		break;
 	}
+	return 0;
 }
 
 static void drv_read(struct drv_cmd *cmd)
 {
-	cpumask_t saved_mask = current->cpus_allowed;
 	cmd->val = 0;
 
-	set_cpus_allowed_ptr(current, cmd->mask);
-	do_drv_read(cmd);
-	set_cpus_allowed_ptr(current, &saved_mask);
+	work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd);
 }
 
 static void drv_write(struct drv_cmd *cmd)
 {
-	cpumask_t saved_mask = current->cpus_allowed;
 	unsigned int i;
 
 	for_each_cpu(i, cmd->mask) {
-		set_cpus_allowed_ptr(current, cpumask_of(i));
-		do_drv_write(cmd);
+		work_on_cpu(i, do_drv_write, cmd);
 	}
-
-	set_cpus_allowed_ptr(current, &saved_mask);
-	return;
 }
 
 static u32 get_cur_val(const struct cpumask *mask)
@@ -235,8 +231,7 @@ static u32 get_cur_val(const struct cpumask *mask)
 		return 0;
 	}
 
-	cpumask_copy(cmd.mask, mask);
-
+	cmd.mask = mask;
 	drv_read(&cmd);
 
 	dprintk("get_cur_val = %u\n", cmd.val);
@@ -368,7 +363,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 	return freq;
 }
 
-static unsigned int check_freqs(const cpumask_t *mask, unsigned int freq,
+static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
 				struct acpi_cpufreq_data *data)
 {
 	unsigned int cur_freq;
@@ -403,9 +398,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 		return -ENODEV;
 	}
 
-	if (unlikely(!alloc_cpumask_var(&cmd.mask, GFP_KERNEL)))
-		return -ENOMEM;
-
 	perf = data->acpi_data;
 	result = cpufreq_frequency_table_target(policy,
 						data->freq_table,
@@ -450,9 +442,9 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 
 	/* cpufreq holds the hotplug lock, so we are safe from here on */
 	if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY)
-		cpumask_and(cmd.mask, cpu_online_mask, policy->cpus);
+		cmd.mask = policy->cpus;
 	else
-		cpumask_copy(cmd.mask, cpumask_of(policy->cpu));
+		cmd.mask = cpumask_of(policy->cpu);
 
 	freqs.old = perf->states[perf->state].core_frequency * 1000;
 	freqs.new = data->freq_table[next_state].frequency;
@@ -479,7 +471,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	perf->state = next_perf_state;
 
 out:
-	free_cpumask_var(cmd.mask);
 	return result;
 }
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 8ea6929e974..430e5c38a54 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -29,6 +29,19 @@
 
 static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 {
+	/* Unmask CPUID levels if masked: */
+	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
+		u64 misc_enable;
+
+		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+
+		if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
+			misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID;
+			wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+			c->cpuid_level = cpuid_eax(0);
+		}
+	}
+
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
 		(c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 48533d77be7..da299eb85fc 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -36,8 +36,11 @@ static struct _cache_table cache_table[] __cpuinitdata =
 {
 	{ 0x06, LVL_1_INST, 8 },	/* 4-way set assoc, 32 byte line size */
 	{ 0x08, LVL_1_INST, 16 },	/* 4-way set assoc, 32 byte line size */
+	{ 0x09, LVL_1_INST, 32 },	/* 4-way set assoc, 64 byte line size */
 	{ 0x0a, LVL_1_DATA, 8 },	/* 2 way set assoc, 32 byte line size */
 	{ 0x0c, LVL_1_DATA, 16 },	/* 4-way set assoc, 32 byte line size */
+	{ 0x0d, LVL_1_DATA, 16 },	/* 4-way set assoc, 64 byte line size */
+	{ 0x21, LVL_2,      256 },	/* 8-way set assoc, 64 byte line size */
 	{ 0x22, LVL_3,      512 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x23, LVL_3,      1024 },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x25, LVL_3,      2048 },	/* 8-way set assoc, sectored cache, 64 byte line size */
@@ -85,6 +88,18 @@ static struct _cache_table cache_table[] __cpuinitdata =
 	{ 0x85, LVL_2,    2048 },	/* 8-way set assoc, 32 byte line size */
 	{ 0x86, LVL_2,     512 },	/* 4-way set assoc, 64 byte line size */
 	{ 0x87, LVL_2,    1024 },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd0, LVL_3,     512 },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd1, LVL_3,    1024 },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd2, LVL_3,    2048 },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd6, LVL_3,    1024 },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd7, LVL_3,    2038 },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd8, LVL_3,    4096 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xdc, LVL_3,    2048 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xdd, LVL_3,    4096 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xde, LVL_3,    8192 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xe2, LVL_3,    2048 },	/* 16-way set assoc, 64 byte line size */
+	{ 0xe3, LVL_3,    4096 },	/* 16-way set assoc, 64 byte line size */
+	{ 0xe4, LVL_3,    8192 },	/* 16-way set assoc, 64 byte line size */
 	{ 0x00, 0, 0}
 };
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index b59ddcc88cd..0c0a455fe95 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -33,11 +33,13 @@ u64 mtrr_tom2;
 struct mtrr_state_type mtrr_state = {};
 EXPORT_SYMBOL_GPL(mtrr_state);
 
-#undef MODULE_PARAM_PREFIX
-#define MODULE_PARAM_PREFIX "mtrr."
-
-static int mtrr_show;
-module_param_named(show, mtrr_show, bool, 0);
+static int __initdata mtrr_show;
+static int __init mtrr_debug(char *opt)
+{
+	mtrr_show = 1;
+	return 0;
+}
+early_param("mtrr.show", mtrr_debug);
 
 /*
  * Returns the effective MTRR type for the region
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index d259e5d2e05..236a401b825 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -1594,8 +1594,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 
 	/* kvm/qemu doesn't have mtrr set right, don't trim them all */
 	if (!highest_pfn) {
-		WARN(!kvm_para_available(), KERN_WARNING
-				"WARNING: strange, CPU MTRRs all blank?\n");
+		printk(KERN_INFO "CPU MTRRs all blank - virtualized system.\n");
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index da91701a234..169a120587b 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -15,8 +15,8 @@
  * - buffer allocation (memory accounting)
  *
  *
- * Copyright (C) 2007-2008 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
+ * Copyright (C) 2007-2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
  */
 
 
@@ -890,7 +890,7 @@ int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value)
 }
 
 static const struct ds_configuration ds_cfg_netburst = {
-	.name = "netburst",
+	.name = "Netburst",
 	.ctl[dsf_bts]		= (1 << 2) | (1 << 3),
 	.ctl[dsf_bts_kernel]	= (1 << 5),
 	.ctl[dsf_bts_user]	= (1 << 6),
@@ -904,7 +904,7 @@ static const struct ds_configuration ds_cfg_netburst = {
 #endif
 };
 static const struct ds_configuration ds_cfg_pentium_m = {
-	.name = "pentium m",
+	.name = "Pentium M",
 	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
 
 	.sizeof_field		= sizeof(long),
@@ -915,8 +915,8 @@ static const struct ds_configuration ds_cfg_pentium_m = {
 	.sizeof_rec[ds_pebs]	= sizeof(long) * 18,
 #endif
 };
-static const struct ds_configuration ds_cfg_core2 = {
-	.name = "core 2",
+static const struct ds_configuration ds_cfg_core2_atom = {
+	.name = "Core 2/Atom",
 	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
 	.ctl[dsf_bts_kernel]	= (1 << 9),
 	.ctl[dsf_bts_user]	= (1 << 10),
@@ -949,19 +949,22 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
 	switch (c->x86) {
 	case 0x6:
 		switch (c->x86_model) {
-		case 0 ... 0xC:
-			/* sorry, don't know about them */
-			break;
-		case 0xD:
-		case 0xE: /* Pentium M */
+		case 0x9:
+		case 0xd: /* Pentium M */
 			ds_configure(&ds_cfg_pentium_m);
 			break;
-		default: /* Core2, Atom, ... */
-			ds_configure(&ds_cfg_core2);
+		case 0xf:
+		case 0x17: /* Core2 */
+		case 0x1c: /* Atom */
+			ds_configure(&ds_cfg_core2_atom);
+			break;
+		case 0x1a: /* i7 */
+		default:
+			/* sorry, don't know about them */
 			break;
 		}
 		break;
-	case 0xF:
+	case 0xf:
 		switch (c->x86_model) {
 		case 0x0:
 		case 0x1:
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e28c7a98779..a1346217e43 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -346,6 +346,7 @@ ENTRY(save_args)
 	popq_cfi %rax			/* move return address... */
 	mov %gs:pda_irqstackptr,%rsp
 	EMPTY_FRAME 0
+	pushq_cfi %rbp			/* backlink for unwinder */
 	pushq_cfi %rax			/* ... to the new stack */
 	/*
 	 * We entered an interrupt context - irqs are off:
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index cd759ad9069..64d5ad0b8ad 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -628,11 +628,12 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
 
 	switch (action & 0xf) {
 	case CPU_ONLINE:
-		INIT_DELAYED_WORK(&work.work, hpet_work);
+		INIT_DELAYED_WORK_ON_STACK(&work.work, hpet_work);
 		init_completion(&work.complete);
 		/* FIXME: add schedule_work_on() */
 		schedule_delayed_work_on(cpu, &work.work, 0);
 		wait_for_completion(&work.complete);
+		destroy_timer_on_stack(&work.work.timer);
 		break;
 	case CPU_DEAD:
 		if (hdev) {
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 1c4a1302536..9b0c480c383 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -2528,14 +2528,15 @@ static void irq_complete_move(struct irq_desc **descp)
 
 	vector = ~get_irq_regs()->orig_ax;
 	me = smp_processor_id();
+
+	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
 #ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
 		*descp = desc = move_irq_desc(desc, me);
 		/* get the new one */
 		cfg = desc->chip_data;
 #endif
-
-	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
 		send_cleanup_vector(cfg);
+	}
 }
 #else
 static inline void irq_complete_move(struct irq_desc **descp) {}
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 1507ad4e674..10a09c2f182 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -78,15 +78,6 @@ void __init init_ISA_irqs(void)
 	}
 }
 
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-static struct irqaction irq2 = {
-	.handler = no_action,
-	.mask = CPU_MASK_NONE,
-	.name = "cascade",
-};
-
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
 	[0 ... IRQ0_VECTOR - 1] = -1,
 	[IRQ0_VECTOR] = 0,
@@ -178,9 +169,6 @@ void __init native_init_IRQ(void)
 	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
 #endif
 
-	if (!acpi_ioapic)
-		setup_irq(2, &irq2);
-
 	/* setup after call gates are initialised (usually add in
 	 * the architecture specific gates)
 	 */
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 00c2bcd4146..d5768b1af08 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -5,7 +5,7 @@
  * This allows to use PCI devices that only support 32bit addresses on systems
  * with more than 4GB.
  *
- * See Documentation/DMA-mapping.txt for the interface specification.
+ * See Documentation/PCI/PCI-DMA-mapping.txt for the interface specification.
  *
  * Copyright 2002 Andi Kleen, SuSE Labs.
  * Subject to the GNU General Public License v2 only.
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 55c46074eba..01161077a49 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -136,7 +136,7 @@ static void __init setup_cpu_pda_map(void)
 #ifdef CONFIG_X86_64
 
 /* correctly size the local cpu masks */
-static void setup_cpu_local_masks(void)
+static void __init setup_cpu_local_masks(void)
 {
 	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
 	alloc_bootmem_cpumask_var(&cpu_callin_mask);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 89bb7668041..df0587f24c5 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -632,9 +632,16 @@ badframe:
 }
 
 #ifdef CONFIG_X86_32
-asmlinkage int sys_rt_sigreturn(struct pt_regs regs)
+/*
+ * Note: do not pass in pt_regs directly as with tail-call optimization
+ * GCC will incorrectly stomp on the caller's frame and corrupt user-space
+ * register state:
+ */
+asmlinkage int sys_rt_sigreturn(unsigned long __unused)
 {
-	return do_rt_sigreturn(&regs);
+	struct pt_regs *regs = (struct pt_regs *)&__unused;
+
+	return do_rt_sigreturn(regs);
 }
 #else /* !CONFIG_X86_32 */
 asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index f885023167e..6812b829ed8 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -200,6 +200,7 @@ static int uv_wait_completion(struct bau_desc *bau_desc,
 				destination_timeouts = 0;
 			}
 		}
+		cpu_relax();
 	}
 	return FLUSH_COMPLETE;
 }
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 23206ba1687..1d3302cc2dd 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -858,7 +858,7 @@ void __init vmi_init(void)
 #endif
 }
 
-void vmi_activate(void)
+void __init vmi_activate(void)
 {
 	unsigned long flags;
 
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index a7ed208f81e..92f1c6f3e19 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -931,7 +931,7 @@ static void lguest_restart(char *reason)
  * that we can fit comfortably.
  *
  * First we need assembly templates of each of the patchable Guest operations,
- * and these are in lguest_asm.S. */
+ * and these are in i386_head.S. */
 
 /*G:060 We construct a table from the assembler templates: */
 static const struct lguest_insns
@@ -1093,7 +1093,7 @@ __init void lguest_init(void)
 	acpi_ht = 0;
 #endif
 
-	/* We set the perferred console to "hvc".  This is the "hypervisor
+	/* We set the preferred console to "hvc".  This is the "hypervisor
 	 * virtual console" driver written by the PowerPC people, which we also
 	 * adapted for lguest's use. */
 	add_preferred_console("hvc", 0, NULL);
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 4a20b2f9a38..7c8ca91bb9e 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -56,7 +56,7 @@ do {									   \
 		"	jmp 2b\n"					   \
 		".previous\n"						   \
 		_ASM_EXTABLE(0b,3b)					   \
-		: "=d"(res), "=c"(count), "=&a" (__d0), "=&S" (__d1),	   \
+		: "=&d"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1),	   \
 		  "=&D" (__d2)						   \
 		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
 		: "memory");						   \
@@ -218,7 +218,7 @@ long strnlen_user(const char __user *s, long n)
 		"	.align 4\n"
 		"	.long 0b,2b\n"
 		".previous"
-		:"=r" (n), "=D" (s), "=a" (res), "=c" (tmp)
+		:"=&r" (n), "=&D" (s), "=&a" (res), "=&c" (tmp)
 		:"0" (n), "1" (s), "2" (0), "3" (mask)
 		:"cc");
 	return res & mask;
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 64d6c84e635..ec13cb5f17e 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -32,7 +32,7 @@ do {									   \
 		"	jmp 2b\n"					   \
 		".previous\n"						   \
 		_ASM_EXTABLE(0b,3b)					   \
-		: "=r"(res), "=c"(count), "=&a" (__d0), "=&S" (__d1),	   \
+		: "=&r"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1),	   \
 		  "=&D" (__d2)						   \
 		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
 		: "memory");						   \
@@ -86,7 +86,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
 		".previous\n"
 		_ASM_EXTABLE(0b,3b)
 		_ASM_EXTABLE(1b,2b)
-		: [size8] "=c"(size), [dst] "=&D" (__d0)
+		: [size8] "=&c"(size), [dst] "=&D" (__d0)
 		: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr),
 		  [zero] "r" (0UL), [eight] "r" (8UL));
 	return size;
diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c
index df167f26562..a265a7c6319 100644
--- a/arch/x86/mach-default/setup.c
+++ b/arch/x86/mach-default/setup.c
@@ -38,6 +38,15 @@ void __init pre_intr_init_hook(void)
 	init_ISA_irqs();
 }
 
+/*
+ * IRQ2 is cascade interrupt to second interrupt controller
+ */
+static struct irqaction irq2 = {
+	.handler = no_action,
+	.mask = CPU_MASK_NONE,
+	.name = "cascade",
+};
+
 /**
  * intr_init_hook - post gate setup interrupt initialisation
  *
@@ -53,6 +62,9 @@ void __init intr_init_hook(void)
 		if (x86_quirks->arch_intr_init())
 			return;
 	}
+	if (!acpi_ioapic)
+		setup_irq(2, &irq2);
+
 }
 
 /**
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
index a580b9562e7..d914a7996a6 100644
--- a/arch/x86/mach-voyager/setup.c
+++ b/arch/x86/mach-voyager/setup.c
@@ -33,13 +33,23 @@ void __init intr_init_hook(void)
 	setup_irq(2, &irq2);
 }
 
-void __init pre_setup_arch_hook(void)
+static void voyager_disable_tsc(void)
 {
 	/* Voyagers run their CPUs from independent clocks, so disable
 	 * the TSC code because we can't sync them */
 	setup_clear_cpu_cap(X86_FEATURE_TSC);
 }
 
+void __init pre_setup_arch_hook(void)
+{
+	voyager_disable_tsc();
+}
+
+void __init pre_time_init_hook(void)
+{
+	voyager_disable_tsc();
+}
+
 void __init trap_init_hook(void)
 {
 }
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 9840b7ec749..7ffcdeec463 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -81,7 +81,7 @@ static void enable_local_vic_irq(unsigned int irq);
 static void disable_local_vic_irq(unsigned int irq);
 static void before_handle_vic_irq(unsigned int irq);
 static void after_handle_vic_irq(unsigned int irq);
-static void set_vic_irq_affinity(unsigned int irq, cpumask_t mask);
+static void set_vic_irq_affinity(unsigned int irq, const struct cpumask *mask);
 static void ack_vic_irq(unsigned int irq);
 static void vic_enable_cpi(void);
 static void do_boot_cpu(__u8 cpuid);
@@ -211,8 +211,6 @@ static __u32 cpu_booted_map;
 static cpumask_t smp_commenced_mask = CPU_MASK_NONE;
 
 /* This is for the new dynamic CPU boot code */
-cpumask_t cpu_callin_map = CPU_MASK_NONE;
-cpumask_t cpu_callout_map = CPU_MASK_NONE;
 
 /* The per processor IRQ masks (these are usually kept in sync) */
 static __u16 vic_irq_mask[NR_CPUS] __cacheline_aligned;
@@ -378,7 +376,7 @@ void __init find_smp_config(void)
 	cpus_addr(phys_cpu_present_map)[0] |=
 	    voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK +
 				       3) << 24;
-	cpu_possible_map = phys_cpu_present_map;
+	init_cpu_possible(&phys_cpu_present_map);
 	printk("VOYAGER SMP: phys_cpu_present_map = 0x%lx\n",
 	       cpus_addr(phys_cpu_present_map)[0]);
 	/* Here we set up the VIC to enable SMP */
@@ -1599,16 +1597,16 @@ static void after_handle_vic_irq(unsigned int irq)
  * change the mask and then do an interrupt enable CPI to re-enable on
  * the selected processors */
 
-void set_vic_irq_affinity(unsigned int irq, cpumask_t mask)
+void set_vic_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	/* Only extended processors handle interrupts */
 	unsigned long real_mask;
 	unsigned long irq_mask = 1 << irq;
 	int cpu;
 
-	real_mask = cpus_addr(mask)[0] & voyager_extended_vic_processors;
+	real_mask = cpus_addr(*mask)[0] & voyager_extended_vic_processors;
 
-	if (cpus_addr(mask)[0] == 0)
+	if (cpus_addr(*mask)[0] == 0)
 		/* can't have no CPUs to accept the interrupt -- extremely
 		 * bad things will happen */
 		return;
@@ -1750,10 +1748,11 @@ static void __cpuinit voyager_smp_prepare_boot_cpu(void)
 	init_gdt(smp_processor_id());
 	switch_to_new_gdt();
 
-	cpu_set(smp_processor_id(), cpu_online_map);
-	cpu_set(smp_processor_id(), cpu_callout_map);
-	cpu_set(smp_processor_id(), cpu_possible_map);
-	cpu_set(smp_processor_id(), cpu_present_map);
+	cpu_online_map = cpumask_of_cpu(smp_processor_id());
+	cpu_callout_map = cpumask_of_cpu(smp_processor_id());
+	cpu_callin_map = CPU_MASK_NONE;
+	cpu_present_map = cpumask_of_cpu(smp_processor_id());
+
 }
 
 static int __cpuinit voyager_cpu_up(unsigned int cpu)
@@ -1783,9 +1782,9 @@ void __init smp_setup_processor_id(void)
 	x86_write_percpu(cpu_number, hard_smp_processor_id());
 }
 
-static void voyager_send_call_func(cpumask_t callmask)
+static void voyager_send_call_func(const struct cpumask *callmask)
 {
-	__u32 mask = cpus_addr(callmask)[0] & ~(1 << smp_processor_id());
+	__u32 mask = cpus_addr(*callmask)[0] & ~(1 << smp_processor_id());
 	send_CPI(mask, VIC_CALL_FUNCTION_CPI);
 }
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 8e9b0f1fd87..817a78d5aca 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -808,8 +808,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	/* get the address */
 	address = read_cr2();
 
-	if (unlikely(notify_page_fault(regs)))
-		return;
 	if (unlikely(kmmio_fault(regs, address)))
 		return;
 
@@ -835,6 +833,9 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		if (spurious_fault(error_code, address))
 			return;
 
+		/* kprobes don't want to hook the spurious faults. */
+		if (notify_page_fault(regs))
+			return;
 		/*
 		 * Don't take the mm semaphore here. If we fixup a prefetch
 		 * fault we could otherwise deadlock.
@@ -843,6 +844,8 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		return;
 	}
 
+	if (unlikely(notify_page_fault(regs)))
+		return;
 	/*
 	 * It's safe to allow irq's after cr2 has been saved and the
 	 * vmalloc fault has been handled.
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 88f1b10de3b..2cef0507441 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -138,6 +138,47 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 	return pte_offset_kernel(pmd, 0);
 }
 
+static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
+					   unsigned long vaddr, pte_t *lastpte)
+{
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * Something (early fixmap) may already have put a pte
+	 * page here, which causes the page table allocation
+	 * to become nonlinear. Attempt to fix it, and if it
+	 * is still nonlinear then we have to bug.
+	 */
+	int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
+	int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
+
+	if (pmd_idx_kmap_begin != pmd_idx_kmap_end
+	    && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
+	    && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
+	    && ((__pa(pte) >> PAGE_SHIFT) < table_start
+		|| (__pa(pte) >> PAGE_SHIFT) >= table_end)) {
+		pte_t *newpte;
+		int i;
+
+		BUG_ON(after_init_bootmem);
+		newpte = alloc_low_page();
+		for (i = 0; i < PTRS_PER_PTE; i++)
+			set_pte(newpte + i, pte[i]);
+
+		paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT);
+		set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE));
+		BUG_ON(newpte != pte_offset_kernel(pmd, 0));
+		__flush_tlb_all();
+
+		paravirt_release_pte(__pa(pte) >> PAGE_SHIFT);
+		pte = newpte;
+	}
+	BUG_ON(vaddr < fix_to_virt(FIX_KMAP_BEGIN - 1)
+	       && vaddr > fix_to_virt(FIX_KMAP_END)
+	       && lastpte && lastpte + PTRS_PER_PTE != pte);
+#endif
+	return pte;
+}
+
 /*
  * This function initializes a certain range of kernel virtual memory
  * with new bootmem page tables, everywhere page tables are missing in
@@ -154,6 +195,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 	unsigned long vaddr;
 	pgd_t *pgd;
 	pmd_t *pmd;
+	pte_t *pte = NULL;
 
 	vaddr = start;
 	pgd_idx = pgd_index(vaddr);
@@ -165,7 +207,8 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 		pmd = pmd + pmd_index(vaddr);
 		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
 							pmd++, pmd_idx++) {
-			one_page_table_init(pmd);
+			pte = page_table_kmap_check(one_page_table_init(pmd),
+			                            pmd, vaddr, pte);
 
 			vaddr += PMD_SIZE;
 		}
@@ -508,7 +551,6 @@ static void __init early_ioremap_page_table_range_init(pgd_t *pgd_base)
 	 * Fixed mappings, only the page table structure has to be
 	 * created - mappings will be set by set_fixmap():
 	 */
-	early_ioremap_clear();
 	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
 	end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
 	page_table_range_init(vaddr, end, pgd_base);
@@ -801,7 +843,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse)
 	tables += PAGE_ALIGN(ptes * sizeof(pte_t));
 
 	/* for fixmap */
-	tables += PAGE_SIZE * 2;
+	tables += PAGE_ALIGN(__end_of_fixed_addresses * sizeof(pte_t));
 
 	/*
 	 * RED-PEN putting page tables only on node 0 could
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 23f68e77ad1..e6d36b49025 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -596,7 +596,7 @@ static void __init init_gbpages(void)
 		direct_gbpages = 0;
 }
 
-static unsigned long __init kernel_physical_mapping_init(unsigned long start,
+static unsigned long __meminit kernel_physical_mapping_init(unsigned long start,
 						unsigned long end,
 						unsigned long page_size_mask)
 {
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index d0151d8ce45..ca53224fc56 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -17,6 +17,7 @@
  */
 
 #include <asm/iomap.h>
+#include <asm/pat.h>
 #include <linux/module.h>
 
 /* Map 'pfn' using fixed map 'type' and protections 'prot'
@@ -29,6 +30,15 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 
 	pagefault_disable();
 
+	/*
+	 * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS.
+	 * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the
+	 * MTRR is UC or WC.  UC_MINUS gets the real intention, of the
+	 * user, which is "WC if the MTRR is WC, UC if you can't do that."
+	 */
+	if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC))
+		prot = PAGE_KERNEL_UC_MINUS;
+
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	set_pte(kmap_pte-idx, pfn_pte(pfn, prot));
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index bd85d42819e..af750ab973b 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -557,34 +557,9 @@ void __init early_ioremap_init(void)
 	}
 }
 
-void __init early_ioremap_clear(void)
-{
-	pmd_t *pmd;
-
-	if (early_ioremap_debug)
-		printk(KERN_INFO "early_ioremap_clear()\n");
-
-	pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
-	pmd_clear(pmd);
-	paravirt_release_pte(__pa(bm_pte) >> PAGE_SHIFT);
-	__flush_tlb_all();
-}
-
 void __init early_ioremap_reset(void)
 {
-	enum fixed_addresses idx;
-	unsigned long addr, phys;
-	pte_t *pte;
-
 	after_paging_init = 1;
-	for (idx = FIX_BTMAP_BEGIN; idx >= FIX_BTMAP_END; idx--) {
-		addr = fix_to_virt(idx);
-		pte = early_ioremap_pte(addr);
-		if (pte_present(*pte)) {
-			phys = pte_val(*pte) & PAGE_MASK;
-			set_fixmap(idx, phys);
-		}
-	}
 }
 
 static void __init __early_set_fixmap(enum fixed_addresses idx,
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e89d24815f2..84ba74820ad 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -534,6 +534,36 @@ out_unlock:
 	return 0;
 }
 
+static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
+			       int primary)
+{
+	/*
+	 * Ignore all non primary paths.
+	 */
+	if (!primary)
+		return 0;
+
+	/*
+	 * Ignore the NULL PTE for kernel identity mapping, as it is expected
+	 * to have holes.
+	 * Also set numpages to '1' indicating that we processed cpa req for
+	 * one virtual address page and its pfn. TBD: numpages can be set based
+	 * on the initial value and the level returned by lookup_address().
+	 */
+	if (within(vaddr, PAGE_OFFSET,
+		   PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) {
+		cpa->numpages = 1;
+		cpa->pfn = __pa(vaddr) >> PAGE_SHIFT;
+		return 0;
+	} else {
+		WARN(1, KERN_WARNING "CPA: called for zero pte. "
+			"vaddr = %lx cpa->vaddr = %lx\n", vaddr,
+			*cpa->vaddr);
+
+		return -EFAULT;
+	}
+}
+
 static int __change_page_attr(struct cpa_data *cpa, int primary)
 {
 	unsigned long address;
@@ -549,17 +579,11 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 repeat:
 	kpte = lookup_address(address, &level);
 	if (!kpte)
-		return 0;
+		return __cpa_process_fault(cpa, address, primary);
 
 	old_pte = *kpte;
-	if (!pte_val(old_pte)) {
-		if (!primary)
-			return 0;
-		WARN(1, KERN_WARNING "CPA: called for zero pte. "
-		       "vaddr = %lx cpa->vaddr = %lx\n", address,
-		       *cpa->vaddr);
-		return -EINVAL;
-	}
+	if (!pte_val(old_pte))
+		return __cpa_process_fault(cpa, address, primary);
 
 	if (level == PG_LEVEL_4K) {
 		pte_t new_pte;
@@ -657,12 +681,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		vaddr = *cpa->vaddr;
 
 	if (!(within(vaddr, PAGE_OFFSET,
-		    PAGE_OFFSET + (max_low_pfn_mapped << PAGE_SHIFT))
-#ifdef CONFIG_X86_64
-		|| within(vaddr, PAGE_OFFSET + (1UL<<32),
-		    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))
-#endif
-	)) {
+		    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) {
 
 		alias_cpa = *cpa;
 		temp_cpa_vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 8b08fb95527..7b61036427d 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -333,11 +333,23 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 					      req_type & _PAGE_CACHE_MASK);
 	}
 
-	is_range_ram = pagerange_is_ram(start, end);
-	if (is_range_ram == 1)
-		return reserve_ram_pages_type(start, end, req_type, new_type);
-	else if (is_range_ram < 0)
-		return -EINVAL;
+	if (new_type)
+		*new_type = actual_type;
+
+	/*
+	 * For legacy reasons, some parts of the physical address range in the
+	 * legacy 1MB region is treated as non-RAM (even when listed as RAM in
+	 * the e820 tables).  So we will track the memory attributes of this
+	 * legacy 1MB region using the linear memtype_list always.
+	 */
+	if (end >= ISA_END_ADDRESS) {
+		is_range_ram = pagerange_is_ram(start, end);
+		if (is_range_ram == 1)
+			return reserve_ram_pages_type(start, end, req_type,
+						      new_type);
+		else if (is_range_ram < 0)
+			return -EINVAL;
+	}
 
 	new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
 	if (!new)
@@ -347,9 +359,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	new->end	= end;
 	new->type	= actual_type;
 
-	if (new_type)
-		*new_type = actual_type;
-
 	spin_lock(&memtype_lock);
 
 	if (cached_entry && start >= cached_start)
@@ -437,11 +446,19 @@ int free_memtype(u64 start, u64 end)
 	if (is_ISA_range(start, end - 1))
 		return 0;
 
-	is_range_ram = pagerange_is_ram(start, end);
-	if (is_range_ram == 1)
-		return free_ram_pages_type(start, end);
-	else if (is_range_ram < 0)
-		return -EINVAL;
+	/*
+	 * For legacy reasons, some parts of the physical address range in the
+	 * legacy 1MB region is treated as non-RAM (even when listed as RAM in
+	 * the e820 tables).  So we will track the memory attributes of this
+	 * legacy 1MB region using the linear memtype_list always.
+	 */
+	if (end >= ISA_END_ADDRESS) {
+		is_range_ram = pagerange_is_ram(start, end);
+		if (is_range_ram == 1)
+			return free_ram_pages_type(start, end);
+		else if (is_range_ram < 0)
+			return -EINVAL;
+	}
 
 	spin_lock(&memtype_lock);
 	list_for_each_entry(entry, &memtype_list, nd) {
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 4064345cf14..fecbce6e7d7 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -572,6 +572,7 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route
 	case PCI_DEVICE_ID_INTEL_ICH7_1:
 	case PCI_DEVICE_ID_INTEL_ICH7_30:
 	case PCI_DEVICE_ID_INTEL_ICH7_31:
+	case PCI_DEVICE_ID_INTEL_TGP_LPC:
 	case PCI_DEVICE_ID_INTEL_ESB2_0:
 	case PCI_DEVICE_ID_INTEL_ICH8_0:
 	case PCI_DEVICE_ID_INTEL_ICH8_1:
diff --git a/arch/x86/scripts/strip-symbols b/arch/x86/scripts/strip-symbols
deleted file mode 100644
index a2f1ccb827c..00000000000
--- a/arch/x86/scripts/strip-symbols
+++ /dev/null
@@ -1 +0,0 @@
-__cpu_vendor_dev_X86_VENDOR_*
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 85893824161..fa3e10725d9 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -19,8 +19,10 @@ DECLARE_PER_CPU(unsigned long, xen_mc_irq_flags);
    paired with xen_mc_issue() */
 static inline void xen_mc_batch(void)
 {
+	unsigned long flags;
 	/* need to disable interrupts until this entry is complete */
-	local_irq_save(__get_cpu_var(xen_mc_irq_flags));
+	local_irq_save(flags);
+	__get_cpu_var(xen_mc_irq_flags) = flags;
 }
 
 static inline struct multicall_space xen_mc_entry(size_t args)