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

10 files changed, 471 insertions, 596 deletions

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c97bb7b5a9f8..d0e910da16c5 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -165,10 +165,15 @@ void __init check_bugs(void)
 	print_cpu_info(&boot_cpu_data);
 #endif
 	check_config();
-	check_fpu();
 	check_hlt();
 	check_popad();
 	init_utsname()->machine[1] =
 		'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
 	alternative_instructions();
+
+	/*
+	 * kernel_fpu_begin/end() in check_fpu() relies on the patched
+	 * alternative instructions.
+	 */
+	check_fpu();
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 134505e07b09..761cb3547041 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1297,7 +1297,6 @@ void __cpuinit cpu_init(void)
 	dbg_restore_debug_regs();
 
 	fpu_init();
-	xsave_init();
 
 	if (is_uv_system())
 		uv_cpu_init();
@@ -1350,6 +1349,5 @@ void __cpuinit cpu_init(void)
 	dbg_restore_debug_regs();
 
 	fpu_init();
-	xsave_init();
 }
 #endif
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index f250431fb505..675a05012449 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -19,24 +19,17 @@
 #include <asm/fpu-internal.h>
 #include <asm/user.h>
 
-#ifdef CONFIG_X86_64
-# include <asm/sigcontext32.h>
-# include <asm/user32.h>
-#else
-# define save_i387_xstate_ia32		save_i387_xstate
-# define restore_i387_xstate_ia32	restore_i387_xstate
-# define _fpstate_ia32		_fpstate
-# define _xstate_ia32		_xstate
-# define sig_xstate_ia32_size   sig_xstate_size
-# define fx_sw_reserved_ia32	fx_sw_reserved
-# define user_i387_ia32_struct	user_i387_struct
-# define user32_fxsr_struct	user_fxsr_struct
-#endif
-
 /*
  * Were we in an interrupt that interrupted kernel mode?
  *
- * We can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * For now, with eagerfpu we will return interrupted kernel FPU
+ * state as not-idle. TBD: Ideally we can change the return value
+ * to something like __thread_has_fpu(current). But we need to
+ * be careful of doing __thread_clear_has_fpu() before saving
+ * the FPU etc for supporting nested uses etc. For now, take
+ * the simple route!
+ *
+ * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
  * pair does nothing at all: the thread must not have fpu (so
  * that we don't try to save the FPU state), and TS must
  * be set (so that the clts/stts pair does nothing that is
@@ -44,6 +37,9 @@
  */
 static inline bool interrupted_kernel_fpu_idle(void)
 {
+	if (use_eager_fpu())
+		return 0;
+
 	return !__thread_has_fpu(current) &&
 		(read_cr0() & X86_CR0_TS);
 }
@@ -77,29 +73,29 @@ bool irq_fpu_usable(void)
 }
 EXPORT_SYMBOL(irq_fpu_usable);
 
-void kernel_fpu_begin(void)
+void __kernel_fpu_begin(void)
 {
 	struct task_struct *me = current;
 
-	WARN_ON_ONCE(!irq_fpu_usable());
-	preempt_disable();
 	if (__thread_has_fpu(me)) {
 		__save_init_fpu(me);
 		__thread_clear_has_fpu(me);
-		/* We do 'stts()' in kernel_fpu_end() */
-	} else {
+		/* We do 'stts()' in __kernel_fpu_end() */
+	} else if (!use_eager_fpu()) {
 		this_cpu_write(fpu_owner_task, NULL);
 		clts();
 	}
 }
-EXPORT_SYMBOL(kernel_fpu_begin);
+EXPORT_SYMBOL(__kernel_fpu_begin);
 
-void kernel_fpu_end(void)
+void __kernel_fpu_end(void)
 {
-	stts();
-	preempt_enable();
+	if (use_eager_fpu())
+		math_state_restore();
+	else
+		stts();
 }
-EXPORT_SYMBOL(kernel_fpu_end);
+EXPORT_SYMBOL(__kernel_fpu_end);
 
 void unlazy_fpu(struct task_struct *tsk)
 {
@@ -113,23 +109,15 @@ void unlazy_fpu(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(unlazy_fpu);
 
-#ifdef CONFIG_MATH_EMULATION
-# define HAVE_HWFP		(boot_cpu_data.hard_math)
-#else
-# define HAVE_HWFP		1
-#endif
-
-static unsigned int		mxcsr_feature_mask __read_mostly = 0xffffffffu;
+unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
-unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32);
 static struct i387_fxsave_struct fx_scratch __cpuinitdata;
 
 static void __cpuinit mxcsr_feature_mask_init(void)
 {
 	unsigned long mask = 0;
 
-	clts();
 	if (cpu_has_fxsr) {
 		memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
 		asm volatile("fxsave %0" : : "m" (fx_scratch));
@@ -138,7 +126,6 @@ static void __cpuinit mxcsr_feature_mask_init(void)
 			mask = 0x0000ffbf;
 	}
 	mxcsr_feature_mask &= mask;
-	stts();
 }
 
 static void __cpuinit init_thread_xstate(void)
@@ -192,9 +179,8 @@ void __cpuinit fpu_init(void)
 		init_thread_xstate();
 
 	mxcsr_feature_mask_init();
-	/* clean state in init */
-	current_thread_info()->status = 0;
-	clear_used_math();
+	xsave_init();
+	eager_fpu_init();
 }
 
 void fpu_finit(struct fpu *fpu)
@@ -205,12 +191,7 @@ void fpu_finit(struct fpu *fpu)
 	}
 
 	if (cpu_has_fxsr) {
-		struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
-		memset(fx, 0, xstate_size);
-		fx->cwd = 0x37f;
-		if (cpu_has_xmm)
-			fx->mxcsr = MXCSR_DEFAULT;
+		fx_finit(&fpu->state->fxsave);
 	} else {
 		struct i387_fsave_struct *fp = &fpu->state->fsave;
 		memset(fp, 0, xstate_size);
@@ -454,7 +435,7 @@ static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave)
  * FXSR floating point environment conversions.
  */
 
-static void
+void
 convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
 {
 	struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
@@ -491,8 +472,8 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
 		memcpy(&to[i], &from[i], sizeof(to[0]));
 }
 
-static void convert_to_fxsr(struct task_struct *tsk,
-			    const struct user_i387_ia32_struct *env)
+void convert_to_fxsr(struct task_struct *tsk,
+		     const struct user_i387_ia32_struct *env)
 
 {
 	struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
@@ -589,223 +570,6 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 }
 
 /*
- * Signal frame handlers.
- */
-
-static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf)
-{
-	struct task_struct *tsk = current;
-	struct i387_fsave_struct *fp = &tsk->thread.fpu.state->fsave;
-
-	fp->status = fp->swd;
-	if (__copy_to_user(buf, fp, sizeof(struct i387_fsave_struct)))
-		return -1;
-	return 1;
-}
-
-static int save_i387_fxsave(struct _fpstate_ia32 __user *buf)
-{
-	struct task_struct *tsk = current;
-	struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
-	struct user_i387_ia32_struct env;
-	int err = 0;
-
-	convert_from_fxsr(&env, tsk);
-	if (__copy_to_user(buf, &env, sizeof(env)))
-		return -1;
-
-	err |= __put_user(fx->swd, &buf->status);
-	err |= __put_user(X86_FXSR_MAGIC, &buf->magic);
-	if (err)
-		return -1;
-
-	if (__copy_to_user(&buf->_fxsr_env[0], fx, xstate_size))
-		return -1;
-	return 1;
-}
-
-static int save_i387_xsave(void __user *buf)
-{
-	struct task_struct *tsk = current;
-	struct _fpstate_ia32 __user *fx = buf;
-	int err = 0;
-
-
-	sanitize_i387_state(tsk);
-
-	/*
-	 * For legacy compatible, we always set FP/SSE bits in the bit
-	 * vector while saving the state to the user context.
-	 * This will enable us capturing any changes(during sigreturn) to
-	 * the FP/SSE bits by the legacy applications which don't touch
-	 * xstate_bv in the xsave header.
-	 *
-	 * xsave aware applications can change the xstate_bv in the xsave
-	 * header as well as change any contents in the memory layout.
-	 * xrestore as part of sigreturn will capture all the changes.
-	 */
-	tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
-
-	if (save_i387_fxsave(fx) < 0)
-		return -1;
-
-	err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved_ia32,
-			     sizeof(struct _fpx_sw_bytes));
-	err |= __put_user(FP_XSTATE_MAGIC2,
-			  (__u32 __user *) (buf + sig_xstate_ia32_size
-					    - FP_XSTATE_MAGIC2_SIZE));
-	if (err)
-		return -1;
-
-	return 1;
-}
-
-int save_i387_xstate_ia32(void __user *buf)
-{
-	struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf;
-	struct task_struct *tsk = current;
-
-	if (!used_math())
-		return 0;
-
-	if (!access_ok(VERIFY_WRITE, buf, sig_xstate_ia32_size))
-		return -EACCES;
-	/*
-	 * This will cause a "finit" to be triggered by the next
-	 * attempted FPU operation by the 'current' process.
-	 */
-	clear_used_math();
-
-	if (!HAVE_HWFP) {
-		return fpregs_soft_get(current, NULL,
-				       0, sizeof(struct user_i387_ia32_struct),
-				       NULL, fp) ? -1 : 1;
-	}
-
-	unlazy_fpu(tsk);
-
-	if (cpu_has_xsave)
-		return save_i387_xsave(fp);
-	if (cpu_has_fxsr)
-		return save_i387_fxsave(fp);
-	else
-		return save_i387_fsave(fp);
-}
-
-static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf)
-{
-	struct task_struct *tsk = current;
-
-	return __copy_from_user(&tsk->thread.fpu.state->fsave, buf,
-				sizeof(struct i387_fsave_struct));
-}
-
-static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf,
-			       unsigned int size)
-{
-	struct task_struct *tsk = current;
-	struct user_i387_ia32_struct env;
-	int err;
-
-	err = __copy_from_user(&tsk->thread.fpu.state->fxsave, &buf->_fxsr_env[0],
-			       size);
-	/* mxcsr reserved bits must be masked to zero for security reasons */
-	tsk->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
-	if (err || __copy_from_user(&env, buf, sizeof(env)))
-		return 1;
-	convert_to_fxsr(tsk, &env);
-
-	return 0;
-}
-
-static int restore_i387_xsave(void __user *buf)
-{
-	struct _fpx_sw_bytes fx_sw_user;
-	struct _fpstate_ia32 __user *fx_user =
-			((struct _fpstate_ia32 __user *) buf);
-	struct i387_fxsave_struct __user *fx =
-		(struct i387_fxsave_struct __user *) &fx_user->_fxsr_env[0];
-	struct xsave_hdr_struct *xsave_hdr =
-				&current->thread.fpu.state->xsave.xsave_hdr;
-	u64 mask;
-	int err;
-
-	if (check_for_xstate(fx, buf, &fx_sw_user))
-		goto fx_only;
-
-	mask = fx_sw_user.xstate_bv;
-
-	err = restore_i387_fxsave(buf, fx_sw_user.xstate_size);
-
-	xsave_hdr->xstate_bv &= pcntxt_mask;
-	/*
-	 * These bits must be zero.
-	 */
-	xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
-
-	/*
-	 * Init the state that is not present in the memory layout
-	 * and enabled by the OS.
-	 */
-	mask = ~(pcntxt_mask & ~mask);
-	xsave_hdr->xstate_bv &= mask;
-
-	return err;
-fx_only:
-	/*
-	 * Couldn't find the extended state information in the memory
-	 * layout. Restore the FP/SSE and init the other extended state
-	 * enabled by the OS.
-	 */
-	xsave_hdr->xstate_bv = XSTATE_FPSSE;
-	return restore_i387_fxsave(buf, sizeof(struct i387_fxsave_struct));
-}
-
-int restore_i387_xstate_ia32(void __user *buf)
-{
-	int err;
-	struct task_struct *tsk = current;
-	struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf;
-
-	if (HAVE_HWFP)
-		clear_fpu(tsk);
-
-	if (!buf) {
-		if (used_math()) {
-			clear_fpu(tsk);
-			clear_used_math();
-		}
-
-		return 0;
-	} else
-		if (!access_ok(VERIFY_READ, buf, sig_xstate_ia32_size))
-			return -EACCES;
-
-	if (!used_math()) {
-		err = init_fpu(tsk);
-		if (err)
-			return err;
-	}
-
-	if (HAVE_HWFP) {
-		if (cpu_has_xsave)
-			err = restore_i387_xsave(buf);
-		else if (cpu_has_fxsr)
-			err = restore_i387_fxsave(fp, sizeof(struct
-							   i387_fxsave_struct));
-		else
-			err = restore_i387_fsave(fp);
-	} else {
-		err = fpregs_soft_set(current, NULL,
-				      0, sizeof(struct user_i387_ia32_struct),
-				      NULL, fp) != 0;
-	}
-	set_used_math();
-
-	return err;
-}
-
-/*
  * FPU state for core dumps.
  * This is only used for a.out dumps now.
  * It is declared generically using elf_fpregset_t (which is
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ef6a8456f719..dc3567e083f9 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -66,15 +66,13 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	int ret;
 
-	unlazy_fpu(src);
-
 	*dst = *src;
 	if (fpu_allocated(&src->thread.fpu)) {
 		memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu));
 		ret = fpu_alloc(&dst->thread.fpu);
 		if (ret)
 			return ret;
-		fpu_copy(&dst->thread.fpu, &src->thread.fpu);
+		fpu_copy(dst, src);
 	}
 	return 0;
 }
@@ -97,16 +95,6 @@ void arch_task_cache_init(void)
 				  SLAB_PANIC | SLAB_NOTRACK, NULL);
 }
 
-static inline void drop_fpu(struct task_struct *tsk)
-{
-	/*
-	 * Forget coprocessor state..
-	 */
-	tsk->fpu_counter = 0;
-	clear_fpu(tsk);
-	clear_used_math();
-}
-
 /*
  * Free current thread data structures etc..
  */
@@ -163,7 +151,13 @@ void flush_thread(void)
 
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
-	drop_fpu(tsk);
+	drop_init_fpu(tsk);
+	/*
+	 * Free the FPU state for non xsave platforms. They get reallocated
+	 * lazily at the first use.
+	 */
+	if (!use_eager_fpu())
+		free_thread_xstate(tsk);
 }
 
 static void hard_disable_TSC(void)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 516fa186121b..b9ff83c7135b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -190,10 +190,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 	regs->cs		= __USER_CS;
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
-	/*
-	 * Free the old FP and other extended state
-	 */
-	free_thread_xstate(current);
 }
 EXPORT_SYMBOL_GPL(start_thread);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 0a980c9d7cb8..8a6d20ce1978 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -232,10 +232,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 	regs->cs		= _cs;
 	regs->ss		= _ss;
 	regs->flags		= X86_EFLAGS_IF;
-	/*
-	 * Free the old FP and other extended state
-	 */
-	free_thread_xstate(current);
 }
 
 void
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 9f94f8ec26e4..b00b33a18390 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1333,9 +1333,6 @@ static const struct user_regset_view user_x86_64_view = {
 #define genregs32_get		genregs_get
 #define genregs32_set		genregs_set
 
-#define user_i387_ia32_struct	user_i387_struct
-#define user32_fxsr_struct	user_fxsr_struct
-
 #endif	/* CONFIG_X86_64 */
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index bca0ab903e57..3160c26db5e7 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -114,7 +114,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 		regs->orig_ax = -1;		/* disable syscall checks */
 
 		get_user_ex(buf, &sc->fpstate);
-		err |= restore_i387_xstate(buf);
+		err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
 
 		get_user_ex(*pax, &sc->ax);
 	} get_user_catch(err);
@@ -206,35 +206,32 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	     void __user **fpstate)
 {
 	/* Default to using normal stack */
+	unsigned long math_size = 0;
 	unsigned long sp = regs->sp;
+	unsigned long buf_fx = 0;
 	int onsigstack = on_sig_stack(sp);
 
-#ifdef CONFIG_X86_64
 	/* redzone */
-	sp -= 128;
-#endif /* CONFIG_X86_64 */
+	if (config_enabled(CONFIG_X86_64))
+		sp -= 128;
 
 	if (!onsigstack) {
 		/* This is the X/Open sanctioned signal stack switching.  */
 		if (ka->sa.sa_flags & SA_ONSTACK) {
 			if (current->sas_ss_size)
 				sp = current->sas_ss_sp + current->sas_ss_size;
-		} else {
-#ifdef CONFIG_X86_32
-			/* This is the legacy signal stack switching. */
-			if ((regs->ss & 0xffff) != __USER_DS &&
-				!(ka->sa.sa_flags & SA_RESTORER) &&
-					ka->sa.sa_restorer)
+		} else if (config_enabled(CONFIG_X86_32) &&
+			   (regs->ss & 0xffff) != __USER_DS &&
+			   !(ka->sa.sa_flags & SA_RESTORER) &&
+			   ka->sa.sa_restorer) {
+				/* This is the legacy signal stack switching. */
 				sp = (unsigned long) ka->sa.sa_restorer;
-#endif /* CONFIG_X86_32 */
 		}
 	}
 
 	if (used_math()) {
-		sp -= sig_xstate_size;
-#ifdef CONFIG_X86_64
-		sp = round_down(sp, 64);
-#endif /* CONFIG_X86_64 */
+		sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
+				     &buf_fx, &math_size);
 		*fpstate = (void __user *)sp;
 	}
 
@@ -247,8 +244,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	if (onsigstack && !likely(on_sig_stack(sp)))
 		return (void __user *)-1L;
 
-	/* save i387 state */
-	if (used_math() && save_i387_xstate(*fpstate) < 0)
+	/* save i387 and extended state */
+	if (used_math() &&
+	    save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0)
 		return (void __user *)-1L;
 
 	return (void __user *)sp;
@@ -474,6 +472,74 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 }
 #endif /* CONFIG_X86_32 */
 
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+			      siginfo_t *info, compat_sigset_t *set,
+			      struct pt_regs *regs)
+{
+#ifdef CONFIG_X86_X32_ABI
+	struct rt_sigframe_x32 __user *frame;
+	void __user *restorer;
+	int err = 0;
+	void __user *fpstate = NULL;
+
+	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+
+	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+		return -EFAULT;
+
+	if (ka->sa.sa_flags & SA_SIGINFO) {
+		if (copy_siginfo_to_user32(&frame->info, info))
+			return -EFAULT;
+	}
+
+	put_user_try {
+		/* Create the ucontext.  */
+		if (cpu_has_xsave)
+			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+		else
+			put_user_ex(0, &frame->uc.uc_flags);
+		put_user_ex(0, &frame->uc.uc_link);
+		put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+		put_user_ex(sas_ss_flags(regs->sp),
+			    &frame->uc.uc_stack.ss_flags);
+		put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+		put_user_ex(0, &frame->uc.uc__pad0);
+		err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+					regs, set->sig[0]);
+		err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+		if (ka->sa.sa_flags & SA_RESTORER) {
+			restorer = ka->sa.sa_restorer;
+		} else {
+			/* could use a vstub here */
+			restorer = NULL;
+			err |= -EFAULT;
+		}
+		put_user_ex(restorer, &frame->pretcode);
+	} put_user_catch(err);
+
+	if (err)
+		return -EFAULT;
+
+	/* Set up registers for signal handler */
+	regs->sp = (unsigned long) frame;
+	regs->ip = (unsigned long) ka->sa.sa_handler;
+
+	/* We use the x32 calling convention here... */
+	regs->di = sig;
+	regs->si = (unsigned long) &frame->info;
+	regs->dx = (unsigned long) &frame->uc;
+
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
+
+	regs->cs = __USER_CS;
+	regs->ss = __USER_DS;
+#endif	/* CONFIG_X86_X32_ABI */
+
+	return 0;
+}
+
 #ifdef CONFIG_X86_32
 /*
  * Atomically swap in the new signal mask, and wait for a signal.
@@ -612,55 +678,22 @@ static int signr_convert(int sig)
 	return sig;
 }
 
-#ifdef CONFIG_X86_32
-
-#define is_ia32	1
-#define ia32_setup_frame	__setup_frame
-#define ia32_setup_rt_frame	__setup_rt_frame
-
-#else /* !CONFIG_X86_32 */
-
-#ifdef CONFIG_IA32_EMULATION
-#define is_ia32	test_thread_flag(TIF_IA32)
-#else /* !CONFIG_IA32_EMULATION */
-#define is_ia32	0
-#endif /* CONFIG_IA32_EMULATION */
-
-#ifdef CONFIG_X86_X32_ABI
-#define is_x32	test_thread_flag(TIF_X32)
-
-static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
-			      siginfo_t *info, compat_sigset_t *set,
-			      struct pt_regs *regs);
-#else /* !CONFIG_X86_X32_ABI */
-#define is_x32	0
-#endif /* CONFIG_X86_X32_ABI */
-
-int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
-		sigset_t *set, struct pt_regs *regs);
-int ia32_setup_frame(int sig, struct k_sigaction *ka,
-		sigset_t *set, struct pt_regs *regs);
-
-#endif /* CONFIG_X86_32 */
-
 static int
 setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		struct pt_regs *regs)
 {
 	int usig = signr_convert(sig);
 	sigset_t *set = sigmask_to_save();
+	compat_sigset_t *cset = (compat_sigset_t *) set;
 
 	/* Set up the stack frame */
-	if (is_ia32) {
+	if (is_ia32_frame()) {
 		if (ka->sa.sa_flags & SA_SIGINFO)
-			return ia32_setup_rt_frame(usig, ka, info, set, regs);
+			return ia32_setup_rt_frame(usig, ka, info, cset, regs);
 		else
-			return ia32_setup_frame(usig, ka, set, regs);
-#ifdef CONFIG_X86_X32_ABI
-	} else if (is_x32) {
-		return x32_setup_rt_frame(usig, ka, info,
-					 (compat_sigset_t *)set, regs);
-#endif
+			return ia32_setup_frame(usig, ka, cset, regs);
+	} else if (is_x32_frame()) {
+		return x32_setup_rt_frame(usig, ka, info, cset, regs);
 	} else {
 		return __setup_rt_frame(sig, ka, info, set, regs);
 	}
@@ -828,72 +861,6 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 }
 
 #ifdef CONFIG_X86_X32_ABI
-static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
-			      siginfo_t *info, compat_sigset_t *set,
-			      struct pt_regs *regs)
-{
-	struct rt_sigframe_x32 __user *frame;
-	void __user *restorer;
-	int err = 0;
-	void __user *fpstate = NULL;
-
-	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
-
-	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
-		return -EFAULT;
-
-	if (ka->sa.sa_flags & SA_SIGINFO) {
-		if (copy_siginfo_to_user32(&frame->info, info))
-			return -EFAULT;
-	}
-
-	put_user_try {
-		/* Create the ucontext.  */
-		if (cpu_has_xsave)
-			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
-		else
-			put_user_ex(0, &frame->uc.uc_flags);
-		put_user_ex(0, &frame->uc.uc_link);
-		put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
-		put_user_ex(sas_ss_flags(regs->sp),
-			    &frame->uc.uc_stack.ss_flags);
-		put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
-		put_user_ex(0, &frame->uc.uc__pad0);
-		err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
-					regs, set->sig[0]);
-		err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-
-		if (ka->sa.sa_flags & SA_RESTORER) {
-			restorer = ka->sa.sa_restorer;
-		} else {
-			/* could use a vstub here */
-			restorer = NULL;
-			err |= -EFAULT;
-		}
-		put_user_ex(restorer, &frame->pretcode);
-	} put_user_catch(err);
-
-	if (err)
-		return -EFAULT;
-
-	/* Set up registers for signal handler */
-	regs->sp = (unsigned long) frame;
-	regs->ip = (unsigned long) ka->sa.sa_handler;
-
-	/* We use the x32 calling convention here... */
-	regs->di = sig;
-	regs->si = (unsigned long) &frame->info;
-	regs->dx = (unsigned long) &frame->uc;
-
-	loadsegment(ds, __USER_DS);
-	loadsegment(es, __USER_DS);
-
-	regs->cs = __USER_CS;
-	regs->ss = __USER_DS;
-
-	return 0;
-}
-
 asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_sigframe_x32 __user *frame;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index cfbe3fc41586..8276dc6794cc 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -628,11 +628,12 @@ void math_state_restore(void)
 	}
 
 	__thread_fpu_begin(tsk);
+
 	/*
 	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
 	 */
 	if (unlikely(restore_fpu_checking(tsk))) {
-		__thread_fpu_end(tsk);
+		drop_init_fpu(tsk);
 		force_sig(SIGSEGV, tsk);
 		return;
 	}
@@ -645,6 +646,8 @@ dotraplinkage void __kprobes
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
 	exception_enter(regs);
+	BUG_ON(use_eager_fpu());
+
 #ifdef CONFIG_MATH_EMULATION
 	if (read_cr0() & X86_CR0_EM) {
 		struct math_emu_info info = { };
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 9e1a8a7ba6e6..4e89b3dd408d 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -10,9 +10,7 @@
 #include <linux/compat.h>
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
-#ifdef CONFIG_IA32_EMULATION
-#include <asm/sigcontext32.h>
-#endif
+#include <asm/sigframe.h>
 #include <asm/xcr.h>
 
 /*
@@ -23,13 +21,9 @@ u64 pcntxt_mask;
 /*
  * Represents init state for the supported extended state.
  */
-static struct xsave_struct *init_xstate_buf;
-
-struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-struct _fpx_sw_bytes fx_sw_reserved_ia32;
-#endif
+struct xsave_struct *init_xstate_buf;
 
+static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
 static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
 
 /*
@@ -44,9 +38,9 @@ static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
  */
 void __sanitize_i387_state(struct task_struct *tsk)
 {
-	u64 xstate_bv;
-	int feature_bit = 0x2;
 	struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
+	int feature_bit = 0x2;
+	u64 xstate_bv;
 
 	if (!fx)
 		return;
@@ -104,213 +98,326 @@ void __sanitize_i387_state(struct task_struct *tsk)
  * Check for the presence of extended state information in the
  * user fpstate pointer in the sigcontext.
  */
-int check_for_xstate(struct i387_fxsave_struct __user *buf,
-		     void __user *fpstate,
-		     struct _fpx_sw_bytes *fx_sw_user)
+static inline int check_for_xstate(struct i387_fxsave_struct __user *buf,
+				   void __user *fpstate,
+				   struct _fpx_sw_bytes *fx_sw)
 {
 	int min_xstate_size = sizeof(struct i387_fxsave_struct) +
 			      sizeof(struct xsave_hdr_struct);
 	unsigned int magic2;
-	int err;
 
-	err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0],
-			       sizeof(struct _fpx_sw_bytes));
-	if (err)
-		return -EFAULT;
+	if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
+		return -1;
 
-	/*
-	 * First Magic check failed.
-	 */
-	if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1)
-		return -EINVAL;
+	/* Check for the first magic field and other error scenarios. */
+	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
+	    fx_sw->xstate_size < min_xstate_size ||
+	    fx_sw->xstate_size > xstate_size ||
+	    fx_sw->xstate_size > fx_sw->extended_size)
+		return -1;
 
 	/*
-	 * Check for error scenarios.
-	 */
-	if (fx_sw_user->xstate_size < min_xstate_size ||
-	    fx_sw_user->xstate_size > xstate_size ||
-	    fx_sw_user->xstate_size > fx_sw_user->extended_size)
-		return -EINVAL;
-
-	err = __get_user(magic2, (__u32 __user *) (fpstate +
-						   fx_sw_user->extended_size -
-						   FP_XSTATE_MAGIC2_SIZE));
-	if (err)
-		return err;
-	/*
 	 * Check for the presence of second magic word at the end of memory
 	 * layout. This detects the case where the user just copied the legacy
 	 * fpstate layout with out copying the extended state information
 	 * in the memory layout.
 	 */
-	if (magic2 != FP_XSTATE_MAGIC2)
-		return -EFAULT;
+	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
+	    || magic2 != FP_XSTATE_MAGIC2)
+		return -1;
 
 	return 0;
 }
 
-#ifdef CONFIG_X86_64
 /*
  * Signal frame handlers.
  */
-
-int save_i387_xstate(void __user *buf)
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
 {
-	struct task_struct *tsk = current;
-	int err = 0;
-
-	if (!access_ok(VERIFY_WRITE, buf, sig_xstate_size))
-		return -EACCES;
+	if (use_fxsr()) {
+		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct user_i387_ia32_struct env;
+		struct _fpstate_ia32 __user *fp = buf;
 
-	BUG_ON(sig_xstate_size < xstate_size);
+		convert_from_fxsr(&env, tsk);
 
-	if ((unsigned long)buf % 64)
-		pr_err("%s: bad fpstate %p\n", __func__, buf);
-
-	if (!used_math())
-		return 0;
-
-	if (user_has_fpu()) {
-		if (use_xsave())
-			err = xsave_user(buf);
-		else
-			err = fxsave_user(buf);
-
-		if (err)
-			return err;
-		user_fpu_end();
+		if (__copy_to_user(buf, &env, sizeof(env)) ||
+		    __put_user(xsave->i387.swd, &fp->status) ||
+		    __put_user(X86_FXSR_MAGIC, &fp->magic))
+			return -1;
 	} else {
-		sanitize_i387_state(tsk);
-		if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
-				   xstate_size))
+		struct i387_fsave_struct __user *fp = buf;
+		u32 swd;
+		if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
 			return -1;
 	}
 
-	clear_used_math(); /* trigger finit */
+	return 0;
+}
 
-	if (use_xsave()) {
-		struct _fpstate __user *fx = buf;
-		struct _xstate __user *x = buf;
-		u64 xstate_bv;
+static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
+{
+	struct xsave_struct __user *x = buf;
+	struct _fpx_sw_bytes *sw_bytes;
+	u32 xstate_bv;
+	int err;
 
-		err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved,
-				     sizeof(struct _fpx_sw_bytes));
+	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
+	sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
+	err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
 
-		err |= __put_user(FP_XSTATE_MAGIC2,
-				  (__u32 __user *) (buf + sig_xstate_size
-						    - FP_XSTATE_MAGIC2_SIZE));
+	if (!use_xsave())
+		return err;
 
-		/*
-		 * Read the xstate_bv which we copied (directly from the cpu or
-		 * from the state in task struct) to the user buffers and
-		 * set the FP/SSE bits.
-		 */
-		err |= __get_user(xstate_bv, &x->xstate_hdr.xstate_bv);