Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm updates from Ingo Molnar:
 "The main changes in this cycle were:

   - MSR access API fixes and enhancements (Andy Lutomirski)

   - early exception handling improvements (Andy Lutomirski)

   - user-space FS/GS prctl usage fixes and improvements (Andy
     Lutomirski)

   - Remove the cpu_has_*() APIs and replace them with equivalents
     (Borislav Petkov)

   - task switch micro-optimization (Brian Gerst)

   - 32-bit entry code simplification (Denys Vlasenko)

   - enhance PAT handling in enumated CPUs (Toshi Kani)

  ... and lots of other cleanups/fixlets"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  x86/arch_prctl/64: Restore accidentally removed put_cpu() in ARCH_SET_GS
  x86/entry/32: Remove asmlinkage_protect()
  x86/entry/32: Remove GET_THREAD_INFO() from entry code
  x86/entry, sched/x86: Don't save/restore EFLAGS on task switch
  x86/asm/entry/32: Simplify pushes of zeroed pt_regs->REGs
  selftests/x86/ldt_gdt: Test set_thread_area() deletion of an active segment
  x86/tls: Synchronize segment registers in set_thread_area()
  x86/asm/64: Rename thread_struct's fs and gs to fsbase and gsbase
  x86/arch_prctl/64: Remove FSBASE/GSBASE < 4G optimization
  x86/segments/64: When load_gs_index fails, clear the base
  x86/segments/64: When loadsegment(fs, ...) fails, clear the base
  x86/asm: Make asm/alternative.h safe from assembly
  x86/asm: Stop depending on ptrace.h in alternative.h
  x86/entry: Rename is_{ia32,x32}_task() to in_{ia32,x32}_syscall()
  x86/asm: Make sure verify_cpu() has a good stack
  x86/extable: Add a comment about early exception handlers
  x86/msr: Set the return value to zero when native_rdmsr_safe() fails
  x86/paravirt: Make "unsafe" MSR accesses unsafe even if PARAVIRT=y
  x86/paravirt: Add paravirt_{read,write}_msr()
  x86/msr: Carry on after a non-"safe" MSR access fails
  ...

28 files changed, 177 insertions, 157 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 99afb665a004..e77a6443104f 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -1,11 +1,12 @@
 #ifndef _ASM_X86_ALTERNATIVE_H
 #define _ASM_X86_ALTERNATIVE_H
 
+#ifndef __ASSEMBLY__
+
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
-#include <asm/ptrace.h>
 
 /*
  * Alternative inline assembly for SMP.
@@ -233,36 +234,6 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
 
-struct paravirt_patch_site;
-#ifdef CONFIG_PARAVIRT
-void apply_paravirt(struct paravirt_patch_site *start,
-		    struct paravirt_patch_site *end);
-#else
-static inline void apply_paravirt(struct paravirt_patch_site *start,
-				  struct paravirt_patch_site *end)
-{}
-#define __parainstructions	NULL
-#define __parainstructions_end	NULL
-#endif
-
-extern void *text_poke_early(void *addr, const void *opcode, size_t len);
-
-/*
- * Clear and restore the kernel write-protection flag on the local CPU.
- * Allows the kernel to edit read-only pages.
- * Side-effect: any interrupt handler running between save and restore will have
- * the ability to write to read-only pages.
- *
- * Warning:
- * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and
- * no thread can be preempted in the instructions being modified (no iret to an
- * invalid instruction possible) or if the instructions are changed from a
- * consistent state to another consistent state atomically.
- * On the local CPU you need to be protected again NMI or MCE handlers seeing an
- * inconsistent instruction while you patch.
- */
-extern void *text_poke(void *addr, const void *opcode, size_t len);
-extern int poke_int3_handler(struct pt_regs *regs);
-extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+#endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 98f25bbafac4..bc27611fa58f 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -239,10 +239,10 @@ extern void __init check_x2apic(void);
 extern void x2apic_setup(void);
 static inline int x2apic_enabled(void)
 {
-	return cpu_has_x2apic && apic_is_x2apic_enabled();
+	return boot_cpu_has(X86_FEATURE_X2APIC) && apic_is_x2apic_enabled();
 }
 
-#define x2apic_supported()	(cpu_has_x2apic)
+#define x2apic_supported()	(boot_cpu_has(X86_FEATURE_X2APIC))
 #else /* !CONFIG_X86_X2APIC */
 static inline void check_x2apic(void) { }
 static inline void x2apic_setup(void) { }
diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
index d194266acb28..eae33c7170c8 100644
--- a/arch/x86/include/asm/clocksource.h
+++ b/arch/x86/include/asm/clocksource.h
@@ -3,11 +3,10 @@
 #ifndef _ASM_X86_CLOCKSOURCE_H
 #define _ASM_X86_CLOCKSOURCE_H
 
-#define VCLOCK_NONE	0  /* No vDSO clock available.	*/
-#define VCLOCK_TSC	1  /* vDSO should use vread_tsc.	*/
-#define VCLOCK_HPET	2  /* vDSO should use vread_hpet.	*/
-#define VCLOCK_PVCLOCK	3 /* vDSO should use vread_pvclock. */
-#define VCLOCK_MAX	3
+#define VCLOCK_NONE	0	/* No vDSO clock available.		*/
+#define VCLOCK_TSC	1	/* vDSO should use vread_tsc.		*/
+#define VCLOCK_PVCLOCK	2	/* vDSO should use vread_pvclock.	*/
+#define VCLOCK_MAX	2
 
 struct arch_clocksource_data {
 	int vclock_mode;
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index ebb102e1bbc7..5a3b2c119ed0 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -307,7 +307,7 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 	return (void __user *)round_down(sp - len, 16);
 }
 
-static inline bool is_x32_task(void)
+static inline bool in_x32_syscall(void)
 {
 #ifdef CONFIG_X86_X32_ABI
 	if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)
@@ -318,7 +318,7 @@ static inline bool is_x32_task(void)
 
 static inline bool in_compat_syscall(void)
 {
-	return is_ia32_task() || is_x32_task();
+	return in_ia32_syscall() || in_x32_syscall();
 }
 #define in_compat_syscall in_compat_syscall	/* override the generic impl */
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 53ac9bbf2064..25ebb54905e0 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -119,31 +119,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
-#define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
-#define cpu_has_pse		boot_cpu_has(X86_FEATURE_PSE)
-#define cpu_has_tsc		boot_cpu_has(X86_FEATURE_TSC)
-#define cpu_has_pge		boot_cpu_has(X86_FEATURE_PGE)
-#define cpu_has_apic		boot_cpu_has(X86_FEATURE_APIC)
-#define cpu_has_fxsr		boot_cpu_has(X86_FEATURE_FXSR)
-#define cpu_has_xmm		boot_cpu_has(X86_FEATURE_XMM)
-#define cpu_has_xmm2		boot_cpu_has(X86_FEATURE_XMM2)
-#define cpu_has_aes		boot_cpu_has(X86_FEATURE_AES)
-#define cpu_has_avx		boot_cpu_has(X86_FEATURE_AVX)
-#define cpu_has_avx2		boot_cpu_has(X86_FEATURE_AVX2)
-#define cpu_has_clflush		boot_cpu_has(X86_FEATURE_CLFLUSH)
-#define cpu_has_gbpages		boot_cpu_has(X86_FEATURE_GBPAGES)
-#define cpu_has_arch_perfmon	boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
-#define cpu_has_pat		boot_cpu_has(X86_FEATURE_PAT)
-#define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
-#define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
-#define cpu_has_xsaves		boot_cpu_has(X86_FEATURE_XSAVES)
-#define cpu_has_osxsave		boot_cpu_has(X86_FEATURE_OSXSAVE)
-#define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
-/*
- * Do not add any more of those clumsy macros - use static_cpu_has() for
- * fast paths and boot_cpu_has() otherwise!
- */
-
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 0aee9dd1976e..4a413485f9eb 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -301,6 +301,9 @@
 #define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
 #define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
 #define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_NULL_SEG	X86_BUG(9) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE	X86_BUG(10) /* SWAPGS without input dep on GS */
+
 
 #ifdef CONFIG_X86_32
 /*
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 15340e36ddcb..fea7724141a0 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -176,7 +176,7 @@ static inline void elf_common_init(struct thread_struct *t,
 	regs->si = regs->di = regs->bp = 0;
 	regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0;
 	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
-	t->fs = t->gs = 0;
+	t->fsbase = t->gsbase = 0;
 	t->fsindex = t->gsindex = 0;
 	t->ds = t->es = ds;
 }
@@ -226,8 +226,8 @@ do {								\
 	(pr_reg)[18] = (regs)->flags;				\
 	(pr_reg)[19] = (regs)->sp;				\
 	(pr_reg)[20] = (regs)->ss;				\
-	(pr_reg)[21] = current->thread.fs;			\
-	(pr_reg)[22] = current->thread.gs;			\
+	(pr_reg)[21] = current->thread.fsbase;			\
+	(pr_reg)[22] = current->thread.gsbase;			\
 	asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v;	\
 	asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v;	\
 	asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v;	\
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index e6a8613fbfb0..3a106165e03a 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -4,7 +4,7 @@
 #include <asm/page.h>
 #include <asm-generic/hugetlb.h>
 
-#define hugepages_supported() cpu_has_pse
+#define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE)
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h
index d0afb05c84fc..f70604125286 100644
--- a/arch/x86/include/asm/irq_work.h
+++ b/arch/x86/include/asm/irq_work.h
@@ -5,7 +5,7 @@
 
 static inline bool arch_irq_work_has_interrupt(void)
 {
-	return cpu_has_apic;
+	return boot_cpu_has(X86_FEATURE_APIC);
 }
 
 #endif /* _ASM_IRQ_WORK_H */
diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h
index 332f98c9111f..22a8537eb780 100644
--- a/arch/x86/include/asm/kgdb.h
+++ b/arch/x86/include/asm/kgdb.h
@@ -6,6 +6,8 @@
  * Copyright (C) 2008 Wind River Systems, Inc.
  */
 
+#include <asm/ptrace.h>
+
 /*
  * BUFMAX defines the maximum number of characters in inbound/outbound
  * buffers at least NUMREGBYTES*2 are needed for register packets
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 79327e9483a3..0ccb26dda126 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -8,40 +8,6 @@
 
 #ifdef CONFIG_X86_32
 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
-
-/*
- * Make sure the compiler doesn't do anything stupid with the
- * arguments on the stack - they are owned by the *caller*, not
- * the callee. This just fools gcc into not spilling into them,
- * and keeps it from doing tailcall recursion and/or using the
- * stack slots for temporaries, since they are live and "used"
- * all the way to the end of the function.
- *
- * NOTE! On x86-64, all the arguments are in registers, so this
- * only matters on a 32-bit kernel.
- */
-#define asmlinkage_protect(n, ret, args...) \
-	__asmlinkage_protect##n(ret, ##args)
-#define __asmlinkage_protect_n(ret, args...) \
-	__asm__ __volatile__ ("" : "=r" (ret) : "0" (ret), ##args)
-#define __asmlinkage_protect0(ret) \
-	__asmlinkage_protect_n(ret)
-#define __asmlinkage_protect1(ret, arg1) \
-	__asmlinkage_protect_n(ret, "m" (arg1))
-#define __asmlinkage_protect2(ret, arg1, arg2) \
-	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2))
-#define __asmlinkage_protect3(ret, arg1, arg2, arg3) \
-	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3))
-#define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \
-	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
-			      "m" (arg4))
-#define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \
-	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
-			      "m" (arg4), "m" (arg5))
-#define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \
-	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
-			      "m" (arg4), "m" (arg5), "m" (arg6))
-
 #endif /* CONFIG_X86_32 */
 
 #ifdef __ASSEMBLY__
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 7a79ee2778b3..7dc1d8fef7fd 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -84,7 +84,10 @@ static inline unsigned long long native_read_msr(unsigned int msr)
 {
 	DECLARE_ARGS(val, low, high);
 
-	asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr));
+	asm volatile("1: rdmsr\n"
+		     "2:\n"
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe)
+		     : EAX_EDX_RET(val, low, high) : "c" (msr));
 	if (msr_tracepoint_active(__tracepoint_read_msr))
 		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0);
 	return EAX_EDX_VAL(val, low, high);
@@ -98,7 +101,10 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 	asm volatile("2: rdmsr ; xor %[err],%[err]\n"
 		     "1:\n\t"
 		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
+		     "3: mov %[fault],%[err]\n\t"
+		     "xorl %%eax, %%eax\n\t"
+		     "xorl %%edx, %%edx\n\t"
+		     "jmp 1b\n\t"
 		     ".previous\n\t"
 		     _ASM_EXTABLE(2b, 3b)
 		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
@@ -108,10 +114,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static inline void native_write_msr(unsigned int msr,
-				    unsigned low, unsigned high)
+/* Can be uninlined because referenced by paravirt */
+notrace static inline void native_write_msr(unsigned int msr,
+					    unsigned low, unsigned high)
 {
-	asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
+	asm volatile("1: wrmsr\n"
+		     "2:\n"
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
+		     : : "c" (msr), "a"(low), "d" (high) : "memory");
 	if (msr_tracepoint_active(__tracepoint_read_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
 }
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index b94f6f64e23d..dbff1456d215 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -24,6 +24,7 @@
 #define _ASM_X86_MTRR_H
 
 #include <uapi/asm/mtrr.h>
+#include <asm/pat.h>
 
 
 /*
@@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
 static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
 {
 }
+static inline void mtrr_bp_init(void)
+{
+	pat_disable("MTRRs disabled, skipping PAT initialization too.");
+}
 
 #define mtrr_ap_init() do {} while (0)
-#define mtrr_bp_init() do {} while (0)
 #define set_mtrr_aps_delayed_init() do {} while (0)
 #define mtrr_aps_init() do {} while (0)
 #define mtrr_bp_restore() do {} while (0)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 601f1b8f9961..3c731413f1de 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -130,21 +130,31 @@ static inline void wbinvd(void)
 
 #define get_kernel_rpl()  (pv_info.kernel_rpl)
 
-static inline u64 paravirt_read_msr(unsigned msr, int *err)
+static inline u64 paravirt_read_msr(unsigned msr)
 {
-	return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
+	return PVOP_CALL1(u64, pv_cpu_ops.read_msr, msr);
 }
 
-static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
+static inline void paravirt_write_msr(unsigned msr,
+				      unsigned low, unsigned high)
 {
-	return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
+	return PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high);
+}
+
+static inline u64 paravirt_read_msr_safe(unsigned msr, int *err)
+{
+	return PVOP_CALL2(u64, pv_cpu_ops.read_msr_safe, msr, err);
+}
+
+static inline int paravirt_write_msr_safe(unsigned msr,
+					  unsigned low, unsigned high)
+{
+	return PVOP_CALL3(int, pv_cpu_ops.write_msr_safe, msr, low, high);
 }
 
-/* These should all do BUG_ON(_err), but our headers are too tangled. */
 #define rdmsr(msr, val1, val2)			\
 do {						\
-	int _err;				\
-	u64 _l = paravirt_read_msr(msr, &_err);	\
+	u64 _l = paravirt_read_msr(msr);	\
 	val1 = (u32)_l;				\
 	val2 = _l >> 32;			\
 } while (0)
@@ -156,8 +166,7 @@ do {						\
 
 #define rdmsrl(msr, val)			\
 do {						\
-	int _err;				\
-	val = paravirt_read_msr(msr, &_err);	\
+	val = paravirt_read_msr(msr);		\
 } while (0)
 
 static inline void wrmsrl(unsigned msr, u64 val)
@@ -165,23 +174,23 @@ static inline void wrmsrl(unsigned msr, u64 val)
 	wrmsr(msr, (u32)val, (u32)(val>>32));
 }
 
-#define wrmsr_safe(msr, a, b)	paravirt_write_msr(msr, a, b)
+#define wrmsr_safe(msr, a, b)	paravirt_write_msr_safe(msr, a, b)
 
 /* rdmsr with exception handling */
-#define rdmsr_safe(msr, a, b)			\
-({						\
-	int _err;				\
-	u64 _l = paravirt_read_msr(msr, &_err);	\
-	(*a) = (u32)_l;				\
-	(*b) = _l >> 32;			\
-	_err;					\
+#define rdmsr_safe(msr, a, b)				\
+({							\
+	int _err;					\
+	u64 _l = paravirt_read_msr_safe(msr, &_err);	\
+	(*a) = (u32)_l;					\
+	(*b) = _l >> 32;				\
+	_err;						\
 })
 
 static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 {
 	int err;
 
-	*p = paravirt_read_msr(msr, &err);
+	*p = paravirt_read_msr_safe(msr, &err);
 	return err;
 }
 
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index e8c2326478c8..b4a23eafa1b9 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -155,10 +155,16 @@ struct pv_cpu_ops {
 	void (*cpuid)(unsigned int *eax, unsigned int *ebx,
 		      unsigned int *ecx, unsigned int *edx);
 
-	/* MSR, PMC and TSR operations.
-	   err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
-	u64 (*read_msr)(unsigned int msr, int *err);
-	int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+	/* Unsafe MSR operations.  These will warn or panic on failure. */
+	u64 (*read_msr)(unsigned int msr);
+	void (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+
+	/*
+	 * Safe MSR operations.
+	 * read sets err to 0 or -EIO.  write returns 0 or -EIO.
+	 */
+	u64 (*read_msr_safe)(unsigned int msr, int *err);
+	int (*write_msr_safe)(unsigned int msr, unsigned low, unsigned high);
 
 	u64 (*read_pmc)(int counter);
 
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index ca6c228d5e62..0b1ff4c1c14e 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -5,8 +5,8 @@
 #include <asm/pgtable_types.h>
 
 bool pat_enabled(void);
+void pat_disable(const char *reason);
 extern void pat_init(void);
-void pat_init_cache_modes(u64);
 
 extern int reserve_memtype(u64 start, u64 end,
 		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 97f3242e133c..f86491a7bc9d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -183,7 +183,7 @@ static inline int pmd_trans_huge(pmd_t pmd)
 
 static inline int has_transparent_hugepage(void)
 {
-	return cpu_has_pse;
+	return boot_cpu_has(X86_FEATURE_PSE);
 }
 
 #ifdef __HAVE_ARCH_PTE_DEVMAP
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 9264476f3d57..9251aa962721 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -388,9 +388,16 @@ struct thread_struct {
 	unsigned long		ip;
 #endif
 #ifdef CONFIG_X86_64
-	unsigned long		fs;
+	unsigned long		fsbase;
+	unsigned long		gsbase;
+#else
+	/*
+	 * XXX: this could presumably be unsigned short.  Alternatively,
+	 * 32-bit kernels could be taught to use fsindex instead.
+	 */
+	unsigned long fs;
+	unsigned long gs;
 #endif
-	unsigned long		gs;
 
 	/* Save middle states of ptrace breakpoints */
 	struct perf_event	*ptrace_bps[HBP_NUM];
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 7d5a1929d76b..1549caa098f0 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_SEGMENT_H
 
 #include <linux/const.h>
+#include <asm/alternative.h>
 
 /*
  * Constructor for a conventional segment GDT (or LDT) entry.
@@ -207,13 +208,6 @@
 #define __USER_CS			(GDT_ENTRY_DEFAULT_USER_CS*8 + 3)
 #define __PER_CPU_SEG			(GDT_ENTRY_PER_CPU*8 + 3)
 
-/* TLS indexes for 64-bit - hardcoded in arch_prctl(): */
-#define FS_TLS				0
-#define GS_TLS				1
-
-#define GS_TLS_SEL			((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3)
-#define FS_TLS_SEL			((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3)
-
 #endif
 
 #ifndef CONFIG_PARAVIRT
@@ -249,10 +243,13 @@ extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDL
 #endif
 
 /*
- * Load a segment. Fall back on loading the zero
- * segment if something goes wrong..
+ * Load a segment. Fall back on loading the zero segment if something goes
+ * wrong.  This variant assumes that loading zero fully clears the segment.
+ * This is always the case on Intel CPUs and, even on 64-bit AMD CPUs, any
+ * failure to fully clear the cached descriptor is only observable for
+ * FS and GS.
  */
-#define loadsegment(seg, value)						\
+#define __loadsegment_simple(seg, value)				\
 do {									\
 	unsigned short __val = (value);					\
 									\
@@ -269,6 +266,38 @@ do {									\
 		     : "+r" (__val) : : "memory");			\
 } while (0)
 
+#define __loadsegment_ss(value) __loadsegment_simple(ss, (value))
+#define __loadsegment_ds(value) __loadsegment_simple(ds, (value))
+#define __loadsegment_es(value) __loadsegment_simple(es, (value))
+
+#ifdef CONFIG_X86_32
+
+/*
+ * On 32-bit systems, the hidden parts of FS and GS are unobservable if
+ * the selector is NULL, so there's no funny business here.
+ */
+#define __loadsegment_fs(value) __loadsegment_simple(fs, (value))
+#define __loadsegment_gs(value) __loadsegment_simple(gs, (value))
+
+#else
+
+static inline void __loadsegment_fs(unsigned short value)
+{
+	asm volatile("						\n"
+		     "1:	movw %0, %%fs			\n"
+		     "2:					\n"
+
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_clear_fs)
+
+		     : : "rm" (value) : "memory");
+}
+
+/* __loadsegment_gs is intentionally undefined.  Use load_gs_index instead. */
+
+#endif
+
+#define loadsegment(seg, value) __loadsegment_ ## seg (value)
+
 /*
  * Save a segment register away:
  */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 11af24e09c8a..ac1d5da14734 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -6,6 +6,7 @@
 #define COMMAND_LINE_SIZE 2048
 
 #include <linux/linkage.h>
+#include <asm/page_types.h>
 
 #ifdef __i386__
 
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 751bf4b7bf11..8f321a1b03a1 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -39,8 +39,7 @@ do {									\
 	 */								\
 	unsigned long ebx, ecx, edx, esi, edi;				\
 									\
-	asm volatile("pushfl\n\t"		/* save    flags */	\
-		     "pushl %%ebp\n\t"		/* save    EBP   */	\
+	asm volatile("pushl %%ebp\n\t"		/* save    EBP   */	\
 		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
 		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
 		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
@@ -49,7 +48,6 @@ do {									\
 		     "jmp __switch_to\n"	/* regparm call  */	\
 		     "1:\t"						\
 		     "popl %%ebp\n\t"		/* restore EBP   */	\
-		     "popfl\n"			/* restore flags */	\
 									\
 		     /* output parameters */				\
 		     : [prev_sp] "=m" (prev->thread.sp),		\
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
new file mode 100644
index 000000000000..90395063383c
--- /dev/null
+++ b/arch/x86/include/asm/text-patching.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_X86_TEXT_PATCHING_H
+#define _ASM_X86_TEXT_PATCHING_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <asm/ptrace.h>
+
+struct paravirt_patch_site;
+#ifdef CONFIG_PARAVIRT
+void apply_paravirt(struct paravirt_patch_site *start,
+		    struct paravirt_patch_site *end);
+#else
+static inline void apply_paravirt(struct paravirt_patch_site *start,
+				  struct paravirt_patch_site *end)
+{}
+#define __parainstructions	NULL
+#define __parainstructions_end	NULL
+#endif
+
+extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+
+/*
+ * Clear and restore the kernel write-protection flag on the local CPU.
+ * Allows the kernel to edit read-only pages.
+ * Side-effect: any interrupt handler running between save and restore will have
+ * the ability to write to read-only pages.
+ *
+ * Warning:
+ * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and
+ * no thread can be preempted in the instructions being modified (no iret to an
+ * invalid instruction possible) or if the instructions are changed from a
+ * consistent state to another consistent state atomically.
+ * On the local CPU you need to be protected again NMI or MCE handlers seeing an
+ * inconsistent instruction while you patch.
+ */
+extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern int poke_int3_handler(struct pt_regs *regs);
+extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+
+#endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index ffae84df8a93..30c133ac05cd 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -255,7 +255,7 @@ static inline bool test_and_clear_restore_sigmask(void)
 	return true;
 }
 
-static inline bool is_ia32_task(void)
+static inline bool in_ia32_syscall(void)
 {
 #ifdef CONFIG_X86_32
 	return true;
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 1fde8d580a5b..4e5be94e079a 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -181,7 +181,7 @@ static inline void __native_flush_tlb_single(unsigned long addr)
 
 static inline void __flush_tlb_all(void)
 {
-	if (cpu_has_pge)
+	if (static_cpu_has(X86_FEATURE_PGE))
 		__flush_tlb_global();
 	else
 		__flush_tlb();
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 174c4212780a..7428697c5b8d 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -22,7 +22,7 @@ extern void disable_TSC(void);
 static inline cycles_t get_cycles(void)
 {
 #ifndef CONFIG_X86_TSC
-	if (!cpu_has_tsc)
+	if (!boot_cpu_has(X86_FEATURE_TSC))
 		return 0;
 #endif
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 2e7513d1f1f4..12f9653bde8d 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -118,7 +118,7 @@ struct exception_table_entry {
 
 extern int fixup_exception(struct pt_regs *regs, int trapnr);
 extern bool ex_has_fault_handler(unsigned long ip);
-extern int early_fixup_exception(unsigned long *ip);
+extern void early_fixup_exception(struct pt_regs *regs, int trapnr);
 
 /*
  * These are the main single-value transfer routines.  They automatically
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index c54beb44c4c1..635eac543922 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -550,7 +550,7 @@ static struct xor_block_template xor_block_pIII_sse = {
 #define XOR_TRY_TEMPLATES				\
 do {							\
 	AVX_XOR_SPEED;					\
-	if (cpu_has_xmm) {				\
+	if (boot_cpu_has(X86_FEATURE_XMM)) {				\
 		xor_speed(&xor_block_pIII_sse);		\
 		xor_speed(&xor_block_sse_pf64);		\
 	} else if (boot_cpu_has(X86_FEATURE_MMX)) {	\
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 7c0a517ec751..22a7b1870a31 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -167,12 +167,12 @@ static struct xor_block_template xor_block_avx = {
 
 #define AVX_XOR_SPEED \
 do { \
-	if (cpu_has_avx && cpu_has_osxsave) \
+	if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE)) \
 		xor_speed(&xor_block_avx); \
 } while (0)
 
 #define AVX_SELECT(FASTEST) \
-	(cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST)
+	(boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE) ? &xor_block_avx : FASTEST)
 
 #else