Merge branch 'linus' into x86/apic

Conflicts:
	arch/x86/kernel/acpi/boot.c
	arch/x86/mm/fault.c
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 9c79b24..097a6b6 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -418,9 +418,9 @@
 	orl   $TS_COMPAT,TI_status(%r10)
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10)
 	jnz ia32_tracesys
-ia32_do_syscall:	
 	cmpl $(IA32_NR_syscalls-1),%eax
-	ja  int_ret_from_sys_call	/* ia32_tracesys has set RAX(%rsp) */
+	ja ia32_badsys
+ia32_do_call:
 	IA32_ARG_FIXUP
 	call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
 ia32_sysret:
@@ -435,7 +435,9 @@
 	call syscall_trace_enter
 	LOAD_ARGS32 ARGOFFSET  /* reload args from stack in case ptrace changed it */
 	RESTORE_REST
-	jmp ia32_do_syscall
+	cmpl $(IA32_NR_syscalls-1),%eax
+	ja  int_ret_from_sys_call	/* ia32_tracesys has set RAX(%rsp) */
+	jmp ia32_do_call
 END(ia32_syscall)
 
 ia32_badsys:
diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h
index 3782220..3c601f8 100644
--- a/arch/x86/include/asm/a.out-core.h
+++ b/arch/x86/include/asm/a.out-core.h
@@ -23,8 +23,6 @@
  */
 static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
 {
-	u16 gs;
-
 /* changed the size calculations - should hopefully work better. lbt */
 	dump->magic = CMAGIC;
 	dump->start_code = 0;
@@ -57,7 +55,7 @@
 	dump->regs.ds = (u16)regs->ds;
 	dump->regs.es = (u16)regs->es;
 	dump->regs.fs = (u16)regs->fs;
-	savesegment(gs, gs);
+	savesegment(gs, dump->regs.gs);
 	dump->regs.orig_ax = regs->orig_ax;
 	dump->regs.ip = regs->ip;
 	dump->regs.cs = (u16)regs->cs;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index ea408dc..7301e60 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -93,6 +93,7 @@
 #define X86_FEATURE_XTOPOLOGY	(3*32+22) /* cpu topology enum extensions */
 #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
+#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h
index 5a65b10..031f626 100644
--- a/arch/x86/include/asm/math_emu.h
+++ b/arch/x86/include/asm/math_emu.h
@@ -1,31 +1,18 @@
 #ifndef _ASM_X86_MATH_EMU_H
 #define _ASM_X86_MATH_EMU_H
 
+#include <asm/ptrace.h>
+#include <asm/vm86.h>
+
 /* This structure matches the layout of the data saved to the stack
    following a device-not-present interrupt, part of it saved
    automatically by the 80386/80486.
    */
-struct info {
+struct math_emu_info {
 	long ___orig_eip;
-	long ___ebx;
-	long ___ecx;
-	long ___edx;
-	long ___esi;
-	long ___edi;
-	long ___ebp;
-	long ___eax;
-	long ___ds;
-	long ___es;
-	long ___fs;
-	long ___orig_eax;
-	long ___eip;
-	long ___cs;
-	long ___eflags;
-	long ___esp;
-	long ___ss;
-	long ___vm86_es; /* This and the following only in vm86 mode */
-	long ___vm86_ds;
-	long ___vm86_fs;
-	long ___vm86_gs;
+	union {
+		struct pt_regs *regs;
+		struct kernel_vm86_regs *vm86;
+	};
 };
 #endif /* _ASM_X86_MATH_EMU_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ff69173..1c244b6 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -1482,6 +1482,7 @@
 {
 	return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
 }
+#define __raw_spin_is_contended	__raw_spin_is_contended
 
 static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
 {
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d211f95..a6643f6 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -353,7 +353,7 @@
 	u8			no_update;
 	u8			rm;
 	u8			alimit;
-	struct info		*info;
+	struct math_emu_info	*info;
 	u32			entry_eip;
 };
 
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 139b424..3a56966 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -183,6 +183,7 @@
 {
 	return __ticket_spin_is_contended(lock);
 }
+#define __raw_spin_is_contended	__raw_spin_is_contended
 
 static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
 {
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 2ee0a3b..cf3bb05 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -41,7 +41,7 @@
 dotraplinkage void do_overflow(struct pt_regs *, long);
 dotraplinkage void do_bounds(struct pt_regs *, long);
 dotraplinkage void do_invalid_op(struct pt_regs *, long);
-dotraplinkage void do_device_not_available(struct pt_regs *, long);
+dotraplinkage void do_device_not_available(struct pt_regs);
 dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long);
 dotraplinkage void do_invalid_TSS(struct pt_regs *, long);
 dotraplinkage void do_segment_not_present(struct pt_regs *, long);
@@ -77,7 +77,7 @@
 extern int kstack_depth_to_print;
 
 void math_error(void __user *);
-asmlinkage void math_emulate(long);
+void math_emulate(struct math_emu_info *);
 #ifdef CONFIG_X86_32
 unsigned long patch_espfix_desc(unsigned long, unsigned long);
 #else
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 4abff45..7c243a2 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -157,11 +157,11 @@
 #ifdef CONFIG_HIBERNATION
 		if (strncmp(str, "s4_nohwsig", 10) == 0)
 			acpi_no_s4_hw_signature();
+		if (strncmp(str, "s4_nonvs", 8) == 0)
+			acpi_s4_no_nvs();
 #endif
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
-		if (strncmp(str, "s4_nonvs", 8) == 0)
-			acpi_s4_no_nvs();
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index efae3b2..65792c2 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -245,17 +245,6 @@
 
 comment "shared options"
 
-config X86_ACPI_CPUFREQ_PROC_INTF
-	bool "/proc/acpi/processor/../performance interface (deprecated)"
-	depends on PROC_FS
-	depends on X86_ACPI_CPUFREQ || X86_POWERNOW_K7_ACPI || X86_POWERNOW_K8_ACPI
-	help
-	  This enables the deprecated /proc/acpi/processor/../performance
-	  interface. While it is helpful for debugging, the generic,
-	  cross-architecture cpufreq interfaces should be used.
-
-	  If in doubt, say N.
-
 config X86_SPEEDSTEP_LIB
 	tristate
 	default (X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD)
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 5c28b37..fb039cd 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -939,10 +939,25 @@
 	free_cpumask_var(data->acpi_data.shared_cpu_map);
 }
 
+static int get_transition_latency(struct powernow_k8_data *data)
+{
+	int max_latency = 0;
+	int i;
+	for (i = 0; i < data->acpi_data.state_count; i++) {
+		int cur_latency = data->acpi_data.states[i].transition_latency
+			+ data->acpi_data.states[i].bus_master_latency;
+		if (cur_latency > max_latency)
+			max_latency = cur_latency;
+	}
+	/* value in usecs, needs to be in nanoseconds */
+	return 1000 * max_latency;
+}
+
 #else
 static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { return -ENODEV; }
 static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { return; }
 static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { return; }
+static int get_transition_latency(struct powernow_k8_data *data) { return 0; }
 #endif /* CONFIG_X86_POWERNOW_K8_ACPI */
 
 /* Take a frequency, and issue the fid/vid transition command */
@@ -1173,7 +1188,13 @@
 		if (rc) {
 			goto err_out;
 		}
-	}
+		/* Take a crude guess here.
+		 * That guess was in microseconds, so multiply with 1000 */
+		pol->cpuinfo.transition_latency = (
+			 ((data->rvo + 8) * data->vstable * VST_UNITS_20US) +
+			 ((1 << data->irt) * 30)) * 1000;
+	} else /* ACPI _PSS objects available */
+		pol->cpuinfo.transition_latency = get_transition_latency(data);
 
 	/* only run on specific CPU from here on */
 	oldmask = current->cpus_allowed;
@@ -1204,11 +1225,6 @@
 		cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu));
 	data->available_cores = pol->cpus;
 
-	/* Take a crude guess here.
-	 * That guess was in microseconds, so multiply with 1000 */
-	pol->cpuinfo.transition_latency = (((data->rvo + 8) * data->vstable * VST_UNITS_20US)
-	    + (3 * (1 << data->irt) * 10)) * 1000;
-
 	if (cpu_family == CPU_HW_PSTATE)
 		pol->cur = find_khz_freq_from_pstate(data->powernow_table, data->currpstate);
 	else
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 1cef0aa..1f137a8 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -303,6 +303,9 @@
 		ds_init_intel(c);
 	}
 
+	if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)
+		set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);
+
 #ifdef CONFIG_X86_64
 	if (c->x86 == 15)
 		c->x86_cache_alignment = c->x86_clflush_size * 2;
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1b43086..231bdd3 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -488,20 +488,21 @@
 	 * ignore such a protection.
 	 */
 	asm volatile(
-		"1: " _ASM_MOV " (%[parent_old]), %[old]\n"
-		"2: " _ASM_MOV " %[return_hooker], (%[parent_replaced])\n"
+		"1: " _ASM_MOV " (%[parent]), %[old]\n"
+		"2: " _ASM_MOV " %[return_hooker], (%[parent])\n"
 		"   movl $0, %[faulted]\n"
+		"3:\n"
 
 		".section .fixup, \"ax\"\n"
-		"3: movl $1, %[faulted]\n"
+		"4: movl $1, %[faulted]\n"
+		"   jmp 3b\n"
 		".previous\n"
 
-		_ASM_EXTABLE(1b, 3b)
-		_ASM_EXTABLE(2b, 3b)
+		_ASM_EXTABLE(1b, 4b)
+		_ASM_EXTABLE(2b, 4b)
 
-		: [parent_replaced] "=r" (parent), [old] "=r" (old),
-		  [faulted] "=r" (faulted)
-		: [parent_old] "0" (parent), [return_hooker] "r" (return_hooker)
+		: [old] "=r" (old), [faulted] "=r" (faulted)
+		: [parent] "r" (parent), [return_hooker] "r" (return_hooker)
 		: "memory"
 	);
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 64d5ad0..388254f 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -897,7 +897,7 @@
 static int hpet_prev_update_sec;
 static struct rtc_time hpet_alarm_time;
 static unsigned long hpet_pie_count;
-static unsigned long hpet_t1_cmp;
+static u32 hpet_t1_cmp;
 static unsigned long hpet_default_delta;
 static unsigned long hpet_pie_delta;
 static unsigned long hpet_pie_limit;
@@ -905,6 +905,14 @@
 static rtc_irq_handler irq_handler;
 
 /*
+ * Check that the hpet counter c1 is ahead of the c2
+ */
+static inline int hpet_cnt_ahead(u32 c1, u32 c2)
+{
+	return (s32)(c2 - c1) < 0;
+}
+
+/*
  * Registers a IRQ handler.
  */
 int hpet_register_irq_handler(rtc_irq_handler handler)
@@ -1075,7 +1083,7 @@
 		hpet_t1_cmp += delta;
 		hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
 		lost_ints++;
-	} while ((long)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0);
+	} while (!hpet_cnt_ahead(hpet_t1_cmp, hpet_readl(HPET_COUNTER)));
 
 	if (lost_ints) {
 		if (hpet_rtc_flags & RTC_PIE)
diff --git a/arch/x86/kernel/i8237.c b/arch/x86/kernel/i8237.c
index dbd6c1d..b42ca69 100644
--- a/arch/x86/kernel/i8237.c
+++ b/arch/x86/kernel/i8237.c
@@ -28,10 +28,10 @@
 
 	flags = claim_dma_lock();
 
-	dma_outb(DMA1_RESET_REG, 0);
-	dma_outb(DMA2_RESET_REG, 0);
+	dma_outb(0, DMA1_RESET_REG);
+	dma_outb(0, DMA2_RESET_REG);
 
-	for (i = 0;i < 8;i++) {
+	for (i = 0; i < 8; i++) {
 		set_dma_addr(i, 0x000000);
 		/* DMA count is a bit weird so this is not 0 */
 		set_dma_count(i, 1);
@@ -51,14 +51,14 @@
 }
 
 static struct sysdev_class i8237_sysdev_class = {
-	.name = "i8237",
-	.suspend = i8237A_suspend,
-	.resume = i8237A_resume,
+	.name		= "i8237",
+	.suspend	= i8237A_suspend,
+	.resume		= i8237A_resume,
 };
 
 static struct sys_device device_i8237A = {
-	.id	= 0,
-	.cls	= &i8237_sysdev_class,
+	.id		= 0,
+	.cls		= &i8237_sysdev_class,
 };
 
 static int __init i8237A_init_sysfs(void)
@@ -68,5 +68,4 @@
 		error = sysdev_register(&device_i8237A);
 	return error;
 }
-
 device_initcall(i8237A_init_sysfs);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 89537f6..87b69d4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -180,6 +180,9 @@
 
 	trace_power_start(&it, POWER_CSTATE, (ax>>4)+1);
 	if (!need_resched()) {
+		if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
+			clflush((void *)&current_thread_info()->flags);
+
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
 		if (!need_resched())
@@ -194,6 +197,9 @@
 	struct power_trace it;
 	if (!need_resched()) {
 		trace_power_start(&it, POWER_CSTATE, 1);
+		if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
+			clflush((void *)&current_thread_info()->flags);
+
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
 		if (!need_resched())
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 214bc327..0d032d2 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -895,7 +895,7 @@
 EXPORT_SYMBOL_GPL(math_state_restore);
 
 #ifndef CONFIG_MATH_EMULATION
-asmlinkage void math_emulate(long arg)
+void math_emulate(struct math_emu_info *info)
 {
 	printk(KERN_EMERG
 		"math-emulation not enabled and no coprocessor found.\n");
@@ -905,16 +905,19 @@
 }
 #endif /* CONFIG_MATH_EMULATION */
 
-dotraplinkage void __kprobes
-do_device_not_available(struct pt_regs *regs, long error)
+dotraplinkage void __kprobes do_device_not_available(struct pt_regs regs)
 {
 #ifdef CONFIG_X86_32
 	if (read_cr0() & X86_CR0_EM) {
-		conditional_sti(regs);
-		math_emulate(0);
+		struct math_emu_info info = { };
+
+		conditional_sti(&regs);
+
+		info.regs = &regs;
+		math_emulate(&info);
 	} else {
 		math_state_restore(); /* interrupts still off */
-		conditional_sti(regs);
+		conditional_sti(&regs);
 	}
 #else
 	math_state_restore();
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index eb9e734..f052c84 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -321,6 +321,16 @@
 }
 
 /*
+ * We use the pgd_free hook for releasing the pgd page:
+ */
+static void vmi_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	unsigned long pfn = __pa(pgd) >> PAGE_SHIFT;
+
+	vmi_ops.release_page(pfn, VMI_PAGE_L2);
+}
+
+/*
  * Helper macros for MMU update flags.  We can defer updates until a flush
  * or page invalidation only if the update is to the current address space
  * (otherwise, there is no flush).  We must check against init_mm, since
@@ -763,6 +773,7 @@
 	if (vmi_ops.release_page) {
 		pv_mmu_ops.release_pte = vmi_release_pte;
 		pv_mmu_ops.release_pmd = vmi_release_pmd;
+		pv_mmu_ops.pgd_free = vmi_pgd_free;
 	}
 
 	/* Set linear is needed in all cases */
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index c7b06fe..5d87f58 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -131,7 +131,7 @@
 static int valid_prefix(u_char *Byte, u_char __user ** fpu_eip,
 			overrides * override);
 
-asmlinkage void math_emulate(long arg)
+void math_emulate(struct math_emu_info *info)
 {
 	u_char FPU_modrm, byte1;
 	unsigned short code;
@@ -161,7 +161,7 @@
 	RE_ENTRANT_CHECK_ON;
 #endif /* RE_ENTRANT_CHECKING */
 
-	SETUP_DATA_AREA(arg);
+	FPU_info = info;
 
 	FPU_ORIG_EIP = FPU_EIP;
 
@@ -659,7 +659,7 @@
 	}
 }
 
-void math_abort(struct info *info, unsigned int signal)
+void math_abort(struct math_emu_info *info, unsigned int signal)
 {
 	FPU_EIP = FPU_ORIG_EIP;
 	current->thread.trap_no = 16;
diff --git a/arch/x86/math-emu/fpu_proto.h b/arch/x86/math-emu/fpu_proto.h
index aa49b6a..9779df4 100644
--- a/arch/x86/math-emu/fpu_proto.h
+++ b/arch/x86/math-emu/fpu_proto.h
@@ -51,8 +51,8 @@
 extern void fst_i_(void);
 extern void fstp_i(void);
 /* fpu_entry.c */
-asmlinkage extern void math_emulate(long arg);
-extern void math_abort(struct info *info, unsigned int signal);
+extern void math_emulate(struct math_emu_info *info);
+extern void math_abort(struct math_emu_info *info, unsigned int signal);
 /* fpu_etc.c */
 extern void FPU_etc(void);
 /* fpu_tags.c */
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 13488fa..50fa0ec 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -16,10 +16,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 
-/* This sets the pointer FPU_info to point to the argument part
-   of the stack frame of math_emulate() */
-#define SETUP_DATA_AREA(arg)	FPU_info = (struct info *) &arg
-
 /* s is always from a cpu register, and the cpu does bounds checking
  * during register load --> no further bounds checks needed */
 #define LDT_DESCRIPTOR(s)	(((struct desc_struct *)current->mm->context.ldt)[(s) >> 3])
@@ -38,12 +34,12 @@
 #define I387			(current->thread.xstate)
 #define FPU_info		(I387->soft.info)
 
-#define FPU_CS			(*(unsigned short *) &(FPU_info->___cs))
-#define FPU_SS			(*(unsigned short *) &(FPU_info->___ss))
-#define FPU_DS			(*(unsigned short *) &(FPU_info->___ds))
-#define FPU_EAX			(FPU_info->___eax)
-#define FPU_EFLAGS		(FPU_info->___eflags)
-#define FPU_EIP			(FPU_info->___eip)
+#define FPU_CS			(*(unsigned short *) &(FPU_info->regs->cs))
+#define FPU_SS			(*(unsigned short *) &(FPU_info->regs->ss))
+#define FPU_DS			(*(unsigned short *) &(FPU_info->regs->ds))
+#define FPU_EAX			(FPU_info->regs->ax)
+#define FPU_EFLAGS		(FPU_info->regs->flags)
+#define FPU_EIP			(FPU_info->regs->ip)
 #define FPU_ORIG_EIP		(FPU_info->___orig_eip)
 
 #define FPU_lookahead           (I387->soft.lookahead)
diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c
index d701e2b..420b3b6 100644
--- a/arch/x86/math-emu/get_address.c
+++ b/arch/x86/math-emu/get_address.c
@@ -29,46 +29,43 @@
 #define FPU_WRITE_BIT 0x10
 
 static int reg_offset[] = {
-	offsetof(struct info, ___eax),
-	offsetof(struct info, ___ecx),
-	offsetof(struct info, ___edx),
-	offsetof(struct info, ___ebx),
-	offsetof(struct info, ___esp),
-	offsetof(struct info, ___ebp),
-	offsetof(struct info, ___esi),
-	offsetof(struct info, ___edi)
+	offsetof(struct pt_regs, ax),
+	offsetof(struct pt_regs, cx),
+	offsetof(struct pt_regs, dx),
+	offsetof(struct pt_regs, bx),
+	offsetof(struct pt_regs, sp),
+	offsetof(struct pt_regs, bp),
+	offsetof(struct pt_regs, si),
+	offsetof(struct pt_regs, di)
 };
 
-#define REG_(x) (*(long *)(reg_offset[(x)]+(u_char *) FPU_info))
+#define REG_(x) (*(long *)(reg_offset[(x)] + (u_char *)FPU_info->regs))
 
 static int reg_offset_vm86[] = {
-	offsetof(struct info, ___cs),
-	offsetof(struct info, ___vm86_ds),
-	offsetof(struct info, ___vm86_es),
-	offsetof(struct info, ___vm86_fs),
-	offsetof(struct info, ___vm86_gs),
-	offsetof(struct info, ___ss),
-	offsetof(struct info, ___vm86_ds)
+	offsetof(struct pt_regs, cs),
+	offsetof(struct kernel_vm86_regs, ds),
+	offsetof(struct kernel_vm86_regs, es),
+	offsetof(struct kernel_vm86_regs, fs),
+	offsetof(struct kernel_vm86_regs, gs),
+	offsetof(struct pt_regs, ss),
+	offsetof(struct kernel_vm86_regs, ds)
 };
 
 #define VM86_REG_(x) (*(unsigned short *) \
-		      (reg_offset_vm86[((unsigned)x)]+(u_char *) FPU_info))
-
-/* This dummy, gs is not saved on the stack. */
-#define ___GS ___ds
+		(reg_offset_vm86[((unsigned)x)] + (u_char *)FPU_info->regs))
 
 static int reg_offset_pm[] = {
-	offsetof(struct info, ___cs),
-	offsetof(struct info, ___ds),
-	offsetof(struct info, ___es),
-	offsetof(struct info, ___fs),
-	offsetof(struct info, ___GS),
-	offsetof(struct info, ___ss),
-	offsetof(struct info, ___ds)
+	offsetof(struct pt_regs, cs),
+	offsetof(struct pt_regs, ds),
+	offsetof(struct pt_regs, es),
+	offsetof(struct pt_regs, fs),
+	offsetof(struct pt_regs, ds),	/* dummy, not saved on stack */
+	offsetof(struct pt_regs, ss),
+	offsetof(struct pt_regs, ds)
 };
 
 #define PM_REG_(x) (*(unsigned short *) \
-		      (reg_offset_pm[((unsigned)x)]+(u_char *) FPU_info))
+		(reg_offset_pm[((unsigned)x)] + (u_char *)FPU_info->regs))
 
 /* Decode the SIB byte. This function assumes mod != 0 */
 static int sib(int mod, unsigned long *fpu_eip)
@@ -349,34 +346,34 @@
 	}
 	switch (rm) {
 	case 0:
-		address += FPU_info->___ebx + FPU_info->___esi;
+		address += FPU_info->regs->bx + FPU_info->regs->si;
 		break;
 	case 1:
-		address += FPU_info->___ebx + FPU_info->___edi;
+		address += FPU_info->regs->bx + FPU_info->regs->di;
 		break;
 	case 2:
-		address += FPU_info->___ebp + FPU_info->___esi;
+		address += FPU_info->regs->bp + FPU_info->regs->si;
 		if (addr_modes.override.segment == PREFIX_DEFAULT)
 			addr_modes.override.segment = PREFIX_SS_;
 		break;
 	case 3:
-		address += FPU_info->___ebp + FPU_info->___edi;
+		address += FPU_info->regs->bp + FPU_info->regs->di;
 		if (addr_modes.override.segment == PREFIX_DEFAULT)
 			addr_modes.override.segment = PREFIX_SS_;
 		break;
 	case 4:
-		address += FPU_info->___esi;
+		address += FPU_info->regs->si;
 		break;
 	case 5:
-		address += FPU_info->___edi;
+		address += FPU_info->regs->di;
 		break;
 	case 6:
-		address += FPU_info->___ebp;
+		address += FPU_info->regs->bp;
 		if (addr_modes.override.segment == PREFIX_DEFAULT)
 			addr_modes.override.segment = PREFIX_SS_;
 		break;
 	case 7:
-		address += FPU_info->___ebx;
+		address += FPU_info->regs->bx;
 		break;
 	}
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index d3eee74..2a9ea3a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -806,8 +806,6 @@
 	/* get the address */
 	address = read_cr2();
 
-	if (unlikely(notify_page_fault(regs)))
-		return;
 	if (unlikely(kmmio_fault(regs, address)))
 		return;
 
@@ -837,6 +835,9 @@
 		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.
@@ -845,6 +846,8 @@
 		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.