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

Pull x86/fpu update from Ingo Molnar:
 "The biggest change is the addition of the non-lazy (eager) FPU saving
  support model and enabling it on CPUs with optimized xsaveopt/xrstor
  FPU state saving instructions.

  There are also various Sparse fixes"

Fix up trivial add-add conflict in arch/x86/kernel/traps.c

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, kvm: fix kvm's usage of kernel_fpu_begin/end()
  x86, fpu: remove cpu_has_xmm check in the fx_finit()
  x86, fpu: make eagerfpu= boot param tri-state
  x86, fpu: enable eagerfpu by default for xsaveopt
  x86, fpu: decouple non-lazy/eager fpu restore from xsave
  x86, fpu: use non-lazy fpu restore for processors supporting xsave
  lguest, x86: handle guest TS bit for lazy/non-lazy fpu host models
  x86, fpu: always use kernel_fpu_begin/end() for in-kernel FPU usage
  x86, kvm: use kernel_fpu_begin/end() in kvm_load/put_guest_fpu()
  x86, fpu: remove unnecessary user_fpu_end() in save_xstate_sig()
  x86, fpu: drop_fpu() before restoring new state from sigframe
  x86, fpu: Unify signal handling code paths for x86 and x86_64 kernels
  x86, fpu: Consolidate inline asm routines for saving/restoring fpu state
  x86, signal: Cleanup ifdefs and is_ia32, is_x32

8 files changed, 292 insertions, 318 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 633b6176cf60..16cae425d1f8 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -97,6 +97,7 @@
 #define X86_FEATURE_EXTD_APICID	(3*32+26) /* has extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM     (3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	(3*32+28) /* APERFMPERF */
+#define X86_FEATURE_EAGER_FPU	(3*32+29) /* "eagerfpu" Non lazy FPU restore */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
@@ -300,12 +301,14 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_xmm4_2		boot_cpu_has(X86_FEATURE_XMM4_2)
 #define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
 #define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
+#define cpu_has_xsaveopt	boot_cpu_has(X86_FEATURE_XSAVEOPT)
 #define cpu_has_osxsave		boot_cpu_has(X86_FEATURE_OSXSAVE)
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
 #define cpu_has_perfctr_core	boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
 #define cpu_has_cx8		boot_cpu_has(X86_FEATURE_CX8)
 #define cpu_has_cx16		boot_cpu_has(X86_FEATURE_CX16)
+#define cpu_has_eager_fpu	boot_cpu_has(X86_FEATURE_EAGER_FPU)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg		1
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 75f4c6d6a331..92f3c6ed817f 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -12,6 +12,7 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/regset.h>
+#include <linux/compat.h>
 #include <linux/slab.h>
 #include <asm/asm.h>
 #include <asm/cpufeature.h>
@@ -21,42 +22,74 @@
 #include <asm/uaccess.h>
 #include <asm/xsave.h>
 
-extern unsigned int sig_xstate_size;
+#ifdef CONFIG_X86_64
+# include <asm/sigcontext32.h>
+# include <asm/user32.h>
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+			compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
+		     compat_sigset_t *set, struct pt_regs *regs);
+#else
+# define user_i387_ia32_struct	user_i387_struct
+# define user32_fxsr_struct	user_fxsr_struct
+# define ia32_setup_frame	__setup_frame
+# define ia32_setup_rt_frame	__setup_rt_frame
+#endif
+
+extern unsigned int mxcsr_feature_mask;
 extern void fpu_init(void);
+extern void eager_fpu_init(void);
 
 DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
 
+extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
+			      struct task_struct *tsk);
+extern void convert_to_fxsr(struct task_struct *tsk,
+			    const struct user_i387_ia32_struct *env);
+
 extern user_regset_active_fn fpregs_active, xfpregs_active;
 extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
 				xstateregs_get;
 extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
 				 xstateregs_set;
 
-
 /*
  * xstateregs_active == fpregs_active. Please refer to the comment
  * at the definition of fpregs_active.
  */
 #define xstateregs_active	fpregs_active
 
-extern struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-extern unsigned int sig_xstate_ia32_size;
-extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
-struct _fpstate_ia32;
-struct _xstate_ia32;
-extern int save_i387_xstate_ia32(void __user *buf);
-extern int restore_i387_xstate_ia32(void __user *buf);
-#endif
-
 #ifdef CONFIG_MATH_EMULATION
+# define HAVE_HWFP		(boot_cpu_data.hard_math)
 extern void finit_soft_fpu(struct i387_soft_struct *soft);
 #else
+# define HAVE_HWFP		1
 static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
 #endif
 
+static inline int is_ia32_compat_frame(void)
+{
+	return config_enabled(CONFIG_IA32_EMULATION) &&
+	       test_thread_flag(TIF_IA32);
+}
+
+static inline int is_ia32_frame(void)
+{
+	return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
+}
+
+static inline int is_x32_frame(void)
+{
+	return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+}
+
 #define X87_FSW_ES (1 << 7)	/* Exception Summary */
 
+static __always_inline __pure bool use_eager_fpu(void)
+{
+	return static_cpu_has(X86_FEATURE_EAGER_FPU);
+}
+
 static __always_inline __pure bool use_xsaveopt(void)
 {
 	return static_cpu_has(X86_FEATURE_XSAVEOPT);
@@ -72,6 +105,13 @@ static __always_inline __pure bool use_fxsr(void)
         return static_cpu_has(X86_FEATURE_FXSR);
 }
 
+static inline void fx_finit(struct i387_fxsave_struct *fx)
+{
+	memset(fx, 0, xstate_size);
+	fx->cwd = 0x37f;
+	fx->mxcsr = MXCSR_DEFAULT;
+}
+
 extern void __sanitize_i387_state(struct task_struct *);
 
 static inline void sanitize_i387_state(struct task_struct *tsk)
@@ -81,131 +121,88 @@ static inline void sanitize_i387_state(struct task_struct *tsk)
 	__sanitize_i387_state(tsk);
 }
 
-#ifdef CONFIG_X86_64
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
+#define check_insn(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile("1:" #insn "\n\t"					\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
+static inline int fsave_user(struct i387_fsave_struct __user *fx)
 {
-	int err;
-
-	/* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
-	asm volatile("1:  fxrstorq %[fx]\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err)
-		     : [fx] "m" (*fx), "0" (0));
-#else
-	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err)
-		     : [fx] "R" (fx), "m" (*fx), "0" (0));
-#endif
-	return err;
+	return check_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
 }
 
 static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
-	int err;
+	if (config_enabled(CONFIG_X86_32))
+		return check_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return check_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
 
-	/*
-	 * Clear the bytes not touched by the fxsave and reserved
-	 * for the SW usage.
-	 */
-	err = __clear_user(&fx->sw_reserved,
-			   sizeof(struct _fpx_sw_bytes));
-	if (unlikely(err))
-		return -EFAULT;
-
-	/* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
-	asm volatile("1:  fxsaveq %[fx]\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err), [fx] "=m" (*fx)
-		     : "0" (0));
-#else
-	asm volatile("1:  rex64/fxsave (%[fx])\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err), "=m" (*fx)
-		     : [fx] "R" (fx), "0" (0));
-#endif
-	if (unlikely(err) &&
-	    __clear_user(fx, sizeof(struct i387_fxsave_struct)))
-		err = -EFAULT;
-	/* No need to clear here because the caller clears USED_MATH */
-	return err;
+	/* See comment in fpu_fxsave() below. */
+	return check_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
 }
 
-static inline void fpu_fxsave(struct fpu *fpu)
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
-	/* Using "rex64; fxsave %0" is broken because, if the memory operand
-	   uses any extended registers for addressing, a second REX prefix
-	   will be generated (to the assembler, rex64 followed by semicolon
-	   is a separate instruction), and hence the 64-bitness is lost. */
+	if (config_enabled(CONFIG_X86_32))
+		return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
 
-#ifdef CONFIG_AS_FXSAVEQ
-	/* Using "fxsaveq %0" would be the ideal choice, but is only supported
-	   starting with gas 2.16. */
-	__asm__ __volatile__("fxsaveq %0"
-			     : "=m" (fpu->state->fxsave));
-#else
-	/* Using, as a workaround, the properly prefixed form below isn't
-	   accepted by any binutils version so far released, complaining that
-	   the same type of prefix is used twice if an extended register is
-	   needed for addressing (fix submitted to mainline 2005-11-21).
-	asm volatile("rex64/fxsave %0"
-		     : "=m" (fpu->state->fxsave));
-	   This, however, we can work around by forcing the compiler to select
-	   an addressing mode that doesn't require extended registers. */
-	asm volatile("rex64/fxsave (%[fx])"
-		     : "=m" (fpu->state->fxsave)
-		     : [fx] "R" (&fpu->state->fxsave));
-#endif
+	/* See comment in fpu_fxsave() below. */
+	return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+			  "m" (*fx));
 }
 
-#else  /* CONFIG_X86_32 */
-
-/* perform fxrstor iff the processor has extended states, otherwise frstor */
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
+static inline int frstor_checking(struct i387_fsave_struct *fx)
 {
-	/*
-	 * The "nop" is needed to make the instructions the same
-	 * length.
-	 */
-	alternative_input(
-		"nop ; frstor %1",
-		"fxrstor %1",
-		X86_FEATURE_FXSR,
-		"m" (*fx));
-
-	return 0;
+	return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
 static inline void fpu_fxsave(struct fpu *fpu)
 {
-	asm volatile("fxsave %[fx]"
-		     : [fx] "=m" (fpu->state->fxsave));
+	if (config_enabled(CONFIG_X86_32))
+		asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		asm volatile("fxsaveq %0" : "=m" (fpu->state->fxsave));
+	else {
+		/* Using "rex64; fxsave %0" is broken because, if the memory
+		 * operand uses any extended registers for addressing, a second
+		 * REX prefix will be generated (to the assembler, rex64
+		 * followed by semicolon is a separate instruction), and hence
+		 * the 64-bitness is lost.
+		 *
+		 * Using "fxsaveq %0" would be the ideal choice, but is only
+		 * supported starting with gas 2.16.
+		 *
+		 * Using, as a workaround, the properly prefixed form below
+		 * isn't accepted by any binutils version so far released,
+		 * complaining that the same type of prefix is used twice if
+		 * an extended register is needed for addressing (fix submitted
+		 * to mainline 2005-11-21).
+		 *
+		 *  asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave));
+		 *
+		 * This, however, we can work around by forcing the compiler to
+		 * select an addressing mode that doesn't require extended
+		 * registers.
+		 */
+		asm volatile( "rex64/fxsave (%[fx])"
+			     : "=m" (fpu->state->fxsave)
+			     : [fx] "R" (&fpu->state->fxsave));
+	}
 }
 
-#endif	/* CONFIG_X86_64 */
-
 /*
  * These must be called with preempt disabled. Returns
  * 'true' if the FPU state is still intact.
@@ -248,17 +245,14 @@ static inline int __save_init_fpu(struct task_struct *tsk)
 	return fpu_save_init(&tsk->thread.fpu);
 }
 
-static inline int fpu_fxrstor_checking(struct fpu *fpu)
-{
-	return fxrstor_checking(&fpu->state->fxsave);
-}
-
 static inline int fpu_restore_checking(struct fpu *fpu)
 {
 	if (use_xsave())
-		return fpu_xrstor_checking(fpu);
+		return fpu_xrstor_checking(&fpu->state->xsave);
+	else if (use_fxsr())
+		return fxrstor_checking(&fpu->state->fxsave);
 	else
-		return fpu_fxrstor_checking(fpu);
+		return frstor_checking(&fpu->state->fsave);
 }
 
 static inline int restore_fpu_checking(struct task_struct *tsk)
@@ -310,15 +304,52 @@ static inline void __thread_set_has_fpu(struct task_struct *tsk)
 static inline void __thread_fpu_end(struct task_struct *tsk)
 {
 	__thread_clear_has_fpu(tsk);
-	stts();
+	if (!use_eager_fpu())
+		stts();
 }
 
 static inline void __thread_fpu_begin(struct task_struct *tsk)
 {
-	clts();
+	if (!use_eager_fpu())
+		clts();
 	__thread_set_has_fpu(tsk);
 }
 
+static inline void __drop_fpu(struct task_struct *tsk)
+{
+	if (__thread_has_fpu(tsk)) {
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
+		__thread_fpu_end(tsk);
+	}
+}
+
+static inline void drop_fpu(struct task_struct *tsk)
+{
+	/*
+	 * Forget coprocessor state..
+	 */
+	preempt_disable();
+	tsk->fpu_counter = 0;
+	__drop_fpu(tsk);
+	clear_used_math();
+	preempt_enable();
+}
+
+static inline void drop_init_fpu(struct task_struct *tsk)
+{
+	if (!use_eager_fpu())
+		drop_fpu(tsk);
+	else {
+		if (use_xsave())
+			xrstor_state(init_xstate_buf, -1);
+		else
+			fxrstor_checking(&init_xstate_buf->i387);
+	}
+}
+
 /*
  * FPU state switching for scheduling.
  *
@@ -352,7 +383,12 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 {
 	fpu_switch_t fpu;
 
-	fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+	/*
+	 * If the task has used the math, pre-load the FPU on xsave processors
+	 * or if the past 5 consecutive context-switches used math.
+	 */
+	fpu.preload = tsk_used_math(new) && (use_eager_fpu() ||
+					     new->fpu_counter > 5);
 	if (__thread_has_fpu(old)) {
 		if (!__save_init_fpu(old))
 			cpu = ~0;
@@ -364,14 +400,14 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 			new->fpu_counter++;
 			__thread_set_has_fpu(new);
 			prefetch(new->thread.fpu.state);
-		} else
+		} else if (!use_eager_fpu())
 			stts();
 	} else {
 		old->fpu_counter = 0;
 		old->thread.fpu.last_cpu = ~0;
 		if (fpu.preload) {
 			new->fpu_counter++;
-			if (fpu_lazy_restore(new, cpu))
+			if (!use_eager_fpu() && fpu_lazy_restore(new, cpu))
 				fpu.preload = 0;
 			else
 				prefetch(new->thread.fpu.state);
@@ -391,44 +427,40 @@ static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
 {
 	if (fpu.preload) {
 		if (unlikely(restore_fpu_checking(new)))
-			__thread_fpu_end(new);
+			drop_init_fpu(new);
 	}
 }
 
 /*
  * Signal frame handlers...
  */
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
+extern int save_xstate_sig(void __user *buf, void __user *fx, int size);
+extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size);
 
-static inline void __clear_fpu(struct task_struct *tsk)
+static inline int xstate_sigframe_size(void)
 {
-	if (__thread_has_fpu(tsk)) {
-		/* Ignore delayed exceptions from user space */
-		asm volatile("1: fwait\n"
-			     "2:\n"
-			     _ASM_EXTABLE(1b, 2b));
-		__thread_fpu_end(tsk);
+	return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+}
+
+static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
+{
+	void __user *buf_fx = buf;
+	int size = xstate_sigframe_size();
+
+	if (ia32_frame && use_fxsr()) {
+		buf_fx = buf + sizeof(struct i387_fsave_struct);
+		size += sizeof(struct i387_fsave_struct);
 	}
+
+	return __restore_xstate_sig(buf, buf_fx, size);
 }
 
 /*
- * The actual user_fpu_begin/end() functions
- * need to be preemption-safe.
+ * Need to be preemption-safe.
  *
- * NOTE! user_fpu_end() must be used only after you
- * have saved the FP state, and user_fpu_begin() must
- * be used only immediately before restoring it.
- * These functions do not do any save/restore on
- * their own.
+ * NOTE! user_fpu_begin() must be used only immediately before restoring
+ * it. This function does not do any save/restore on their own.
  */
-static inline void user_fpu_end(void)
-{
-	preempt_disable();
-	__thread_fpu_end(current);
-	preempt_enable();
-}
-
 static inline void user_fpu_begin(void)
 {
 	preempt_disable();
@@ -437,25 +469,32 @@ static inline void user_fpu_begin(void)
 	preempt_enable();
 }
 
+static inline void __save_fpu(struct task_struct *tsk)
+{
+	if (use_xsave())
+		xsave_state(&tsk->thread.fpu.state->xsave, -1);
+	else
+		fpu_fxsave(&tsk->thread.fpu);
+}
+
 /*
  * These disable preemption on their own and are safe
  */
 static inline void save_init_fpu(struct task_struct *tsk)
 {
 	WARN_ON_ONCE(!__thread_has_fpu(tsk));
+
+	if (use_eager_fpu()) {
+		__save_fpu(tsk);
+		return;
+	}
+
 	preempt_disable();
 	__save_init_fpu(tsk);
 	__thread_fpu_end(tsk);
 	preempt_enable();
 }
 
-static inline void clear_fpu(struct task_struct *tsk)
-{
-	preempt_disable();
-	__clear_fpu(tsk);
-	preempt_enable();
-}
-
 /*
  * i387 state interaction
  */
@@ -510,11 +549,34 @@ static inline void fpu_free(struct fpu *fpu)
 	}
 }
 
-static inline void fpu_copy(struct fpu *dst, struct fpu *src)
+static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
 {
-	memcpy(dst->state, src->state, xstate_size);
+	if (use_eager_fpu()) {
+		memset(&dst->thread.fpu.state->xsave, 0, xstate_size);
+		__save_fpu(dst);
+	} else {
+		struct fpu *dfpu = &dst->thread.fpu;
+		struct fpu *sfpu = &src->thread.fpu;
+
+		unlazy_fpu(src);
+		memcpy(dfpu->state, sfpu->state, xstate_size);
+	}
 }
 
-extern void fpu_finit(struct fpu *fpu);
+static inline unsigned long
+alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx,
+		unsigned long *size)
+{
+	unsigned long frame_size = xstate_sigframe_size();
+
+	*buf_fx = sp = round_down(sp - frame_size, 64);
+	if (ia32_frame && use_fxsr()) {
+		frame_size += sizeof(struct i387_fsave_struct);
+		sp -= sizeof(struct i387_fsave_struct);
+	}
+
+	*size = frame_size;
+	return sp;
+}
 
 #endif
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 257d9cca214f..ed8089d69094 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -19,12 +19,37 @@ struct pt_regs;
 struct user_i387_struct;
 
 extern int init_fpu(struct task_struct *child);
+extern void fpu_finit(struct fpu *fpu);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 extern void math_state_restore(void);
 
 extern bool irq_fpu_usable(void);
-extern void kernel_fpu_begin(void);
-extern void kernel_fpu_end(void);
+
+/*
+ * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
+ * and they don't touch the preempt state on their own.
+ * If you enable preemption after __kernel_fpu_begin(), preempt notifier
+ * should call the __kernel_fpu_end() to prevent the kernel/user FPU
+ * state from getting corrupted. KVM for example uses this model.
+ *
+ * All other cases use kernel_fpu_begin/end() which disable preemption
+ * during kernel FPU usage.
+ */
+extern void __kernel_fpu_begin(void);
+extern void __kernel_fpu_end(void);
+
+static inline void kernel_fpu_begin(void)
+{
+	WARN_ON_ONCE(!irq_fpu_usable());
+	preempt_disable();
+	__kernel_fpu_begin();
+}
+
+static inline void kernel_fpu_end(void)
+{
+	__kernel_fpu_end();
+	preempt_enable();
+}
 
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 598457cbd0f8..323973f4abf1 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -31,6 +31,10 @@ typedef struct {
 	unsigned long sig[_NSIG_WORDS];
 } sigset_t;
 
+#ifndef CONFIG_COMPAT
+typedef sigset_t compat_sigset_t;
+#endif
+
 #else
 /* Here we must cater to libcs that poke about in kernel headers.  */
 
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index 454570891bdc..aabd5850bdb9 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -534,38 +534,6 @@ static struct xor_block_template xor_block_p5_mmx = {
  * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
  */
 
-#define XMMS_SAVE				\
-do {						\
-	preempt_disable();			\
-	cr0 = read_cr0();			\
-	clts();					\
-	asm volatile(				\
-		"movups %%xmm0,(%0)	;\n\t"	\
-		"movups %%xmm1,0x10(%0)	;\n\t"	\
-		"movups %%xmm2,0x20(%0)	;\n\t"	\
-		"movups %%xmm3,0x30(%0)	;\n\t"	\
-		:				\
-		: "r" (xmm_save) 		\
-		: "memory");			\
-} while (0)
-
-#define XMMS_RESTORE				\
-do {						\
-	asm volatile(				\
-		"sfence			;\n\t"	\
-		"movups (%0),%%xmm0	;\n\t"	\
-		"movups 0x10(%0),%%xmm1	;\n\t"	\
-		"movups 0x20(%0),%%xmm2	;\n\t"	\
-		"movups 0x30(%0),%%xmm3	;\n\t"	\
-		:				\
-		: "r" (xmm_save)		\
-		: "memory");			\
-	write_cr0(cr0);				\
-	preempt_enable();			\
-} while (0)
-
-#define ALIGN16 __attribute__((aligned(16)))
-
 #define OFFS(x)		"16*("#x")"
 #define PF_OFFS(x)	"256+16*("#x")"
 #define	PF0(x)		"	prefetchnta "PF_OFFS(x)"(%1)		;\n"
@@ -587,10 +555,8 @@ static void
 xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
 {
 	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -633,7 +599,7 @@ xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
 	:
 	: "memory");
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -641,10 +607,8 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	  unsigned long *p3)
 {
 	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -694,7 +658,7 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	:
 	: "memory" );
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -702,10 +666,8 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	  unsigned long *p3, unsigned long *p4)
 {
 	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -762,7 +724,7 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	:
 	: "memory" );
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -770,10 +732,8 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	  unsigned long *p3, unsigned long *p4, unsigned long *p5)
 {
 	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	/* Make sure GCC forgets anything it knows about p4 or p5,
 	   such that it won't pass to the asm volatile below a
@@ -850,7 +810,7 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	   like assuming they have some legal value.  */
 	asm("" : "=r" (p4), "=r" (p5));
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static struct xor_block_template xor_block_pIII_sse = {
diff --git a/arch/x86/include/asm/xor_64.h b/arch/x86/include/asm/xor_64.h
index b9b2323e90fe..5fc06d0b7eb5 100644
--- a/arch/x86/include/asm/xor_64.h
+++ b/arch/x86/include/asm/xor_64.h
@@ -34,41 +34,7 @@
  * no advantages to be gotten from x86-64 here anyways.
  */
 
-typedef struct {
-	unsigned long a, b;
-} __attribute__((aligned(16))) xmm_store_t;
-
-/* Doesn't use gcc to save the XMM registers, because there is no easy way to
-   tell it to do a clts before the register saving. */
-#define XMMS_SAVE				\
-do {						\
-	preempt_disable();			\
-	asm volatile(				\
-		"movq %%cr0,%0		;\n\t"	\
-		"clts			;\n\t"	\
-		"movups %%xmm0,(%1)	;\n\t"	\
-		"movups %%xmm1,0x10(%1)	;\n\t"	\
-		"movups %%xmm2,0x20(%1)	;\n\t"	\
-		"movups %%xmm3,0x30(%1)	;\n\t"	\
-		: "=&r" (cr0)			\
-		: "r" (xmm_save) 		\
-		: "memory");			\
-} while (0)
-
-#define XMMS_RESTORE				\
-do {						\
-	asm volatile(				\
-		"sfence			;\n\t"	\
-		"movups (%1),%%xmm0	;\n\t"	\
-		"movups 0x10(%1),%%xmm1	;\n\t"	\
-		"movups 0x20(%1),%%xmm2	;\n\t"	\
-		"movups 0x30(%1),%%xmm3	;\n\t"	\
-		"movq 	%0,%%cr0	;\n\t"	\
-		:				\
-		: "r" (cr0), "r" (xmm_save)	\
-		: "memory");			\
-	preempt_enable();			\
-} while (0)
+#include <asm/i387.h>
 
 #define OFFS(x)		"16*("#x")"
 #define PF_OFFS(x)	"256+16*("#x")"
@@ -91,10 +57,8 @@ static void
 xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
 {
 	unsigned int lines = bytes >> 8;
-	unsigned long cr0;
-	xmm_store_t xmm_save[4];
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -135,7 +99,7 @@ xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
 	: [inc] "r" (256UL)
 	: "memory");
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -143,11 +107,8 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	  unsigned long *p3)
 {
 	unsigned int lines = bytes >> 8;
-	xmm_store_t xmm_save[4];
-	unsigned long cr0;
-
-	XMMS_SAVE;
 
+	kernel_fpu_begin();
 	asm volatile(
 #undef BLOCK
 #define BLOCK(i) \
@@ -194,7 +155,7 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	  [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
 	: [inc] "r" (256UL)
 	: "memory");
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -202,10 +163,8 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	  unsigned long *p3, unsigned long *p4)
 {
 	unsigned int lines = bytes >> 8;
-	xmm_store_t xmm_save[4];
-	unsigned long cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -261,7 +220,7 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	: [inc] "r" (256UL)
 	: "memory" );
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -269,10 +228,8 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	  unsigned long *p3, unsigned long *p4, unsigned long *p5)
 {
 	unsigned int lines = bytes >> 8;
-	xmm_store_t xmm_save[4];
-	unsigned long cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -336,7 +293,7 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 	: [inc] "r" (256UL)
 	: "memory");
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static struct xor_block_template xor_block_sse = {
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 2510d35f480e..7ea79c5fa1f2 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -20,32 +20,6 @@
 #include <linux/compiler.h>
 #include <asm/i387.h>
 
-#define ALIGN32 __aligned(32)
-
-#define YMM_SAVED_REGS 4
-
-#define YMMS_SAVE \
-do { \
-	preempt_disable(); \
-	cr0 = read_cr0(); \
-	clts(); \
-	asm volatile("vmovaps %%ymm0, %0" : "=m" (ymm_save[0]) : : "memory"); \
-	asm volatile("vmovaps %%ymm1, %0" : "=m" (ymm_save[32]) : : "memory"); \
-	asm volatile("vmovaps %%ymm2, %0" : "=m" (ymm_save[64]) : : "memory"); \
-	asm volatile("vmovaps %%ymm3, %0" : "=m" (ymm_save[96]) : : "memory"); \
-} while (0);
-
-#define YMMS_RESTORE \
-do { \
-	asm volatile("sfence" : : : "memory"); \
-	asm volatile("vmovaps %0, %%ymm3" : : "m" (ymm_save[96])); \
-	asm volatile("vmovaps %0, %%ymm2" : : "m" (ymm_save[64])); \
-	asm volatile("vmovaps %0, %%ymm1" : : "m" (ymm_save[32])); \
-	asm volatile("vmovaps %0, %%ymm0" : : "m" (ymm_save[0])); \
-	write_cr0(cr0); \
-	preempt_enable(); \
-} while (0);
-
 #define BLOCK4(i) \
 		BLOCK(32 * i, 0) \
 		BLOCK(32 * (i + 1), 1) \
@@ -60,10 +34,9 @@ do { \
 
 static void xor_avx_2(unsigned long bytes, unsigned long *p0, unsigned long *p1)
 {
-	unsigned long cr0, lines = bytes >> 9;
-	char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+	unsigned long lines = bytes >> 9;
 
-	YMMS_SAVE
+	kernel_fpu_begin();
 
 	while (lines--) {
 #undef BLOCK
@@ -82,16 +55,15 @@ do { \
 		p1 = (unsigned long *)((uintptr_t)p1 + 512);
 	}
 
-	YMMS_RESTORE
+	kernel_fpu_end();
 }
 
 static void xor_avx_3(unsigned long bytes, unsigned long *p0, unsigned long *p1,
 	unsigned long *p2)
 {
-	unsigned long cr0, lines = bytes >> 9;
-	char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+	unsigned long lines = bytes >> 9;
 
-	YMMS_SAVE
+	kernel_fpu_begin();
 
 	while (lines--) {
 #undef BLOCK
@@ -113,16 +85,15 @@ do { \
 		p2 = (unsigned long *)((uintptr_t)p2 + 512);
 	}
 
-	YMMS_RESTORE
+	kernel_fpu_end();
 }
 
 static void xor_avx_4(unsigned long bytes, unsigned long *p0, unsigned long *p1,
 	unsigned long *p2, unsigned long *p3)
 {
-	unsigned long cr0, lines = bytes >> 9;
-	char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+	unsigned long lines = bytes >> 9;
 
-	YMMS_SAVE
+	kernel_fpu_begin();
 
 	while (lines--) {
 #undef BLOCK
@@ -147,16 +118,15 @@ do { \
 		p3 = (unsigned long *)((uintptr_t)p3 + 512);
 	}
 
-	YMMS_RESTORE
+	kernel_fpu_end();
 }
 
 static void xor_avx_5(unsigned long bytes, unsigned long *p0, unsigned long *p1,
 	unsigned long *p2, unsigned long *p3, unsigned long *p4)
 {
-	unsigned long cr0, lines = bytes >> 9;
-	char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+	unsigned long lines = bytes >> 9;
 
-	YMMS_SAVE
+	kernel_fpu_begin();
 
 	while (lines--) {
 #undef BLOCK
@@ -184,7 +154,7 @@ do { \
 		p4 = (unsigned long *)((uintptr_t)p4 + 512);
 	}
 
-	YMMS_RESTORE
+	kernel_fpu_end();
 }
 
 static struct xor_block_template xor_block_avx = {
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 8a1b6f9b594a..2ddee1b87793 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -34,17 +34,14 @@
 extern unsigned int xstate_size;
 extern u64 pcntxt_mask;
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
+extern struct xsave_struct *init_xstate_buf;
 
 extern void xsave_init(void);
 extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 extern int init_fpu(struct task_struct *child);
-extern int check_for_xstate(struct i387_fxsave_struct __user *buf,
-			    void __user *fpstate,
-			    struct _fpx_sw_bytes *sw);
 
-static inline int fpu_xrstor_checking(struct fpu *fpu)
+static inline int fpu_xrstor_checking(struct xsave_struct *fx)
 {
-	struct xsave_struct *fx = &fpu->state->xsave;
 	int err;
 
 	asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
@@ -69,8 +66,7 @@ static inline int xsave_user(struct xsave_struct __user *buf)
 	 * Clear the xsave header first, so that reserved fields are
 	 * initialized to zero.
 	 */
-	err = __clear_user(&buf->xsave_hdr,
-			   sizeof(struct xsave_hdr_struct));
+	err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr));
 	if (unlikely(err))
 		return -EFAULT;
 
@@ -84,9 +80,6 @@ static inline int xsave_user(struct xsave_struct __user *buf)
 			     : [err] "=r" (err)
 			     : "D" (buf), "a" (-1), "d" (-1), "0" (0)
 			     : "memory");
-	if (unlikely(err) && __clear_user(buf, xstate_size))
-		err = -EFAULT;
-	/* No need to clear here because the caller clears USED_MATH */
 	return err;
 }