x86, fpu: Unify signal handling code paths for x86 and x86_64 kernels

Currently for x86 and x86_32 binaries, fpstate in the user sigframe is copied
to/from the fpstate in the task struct.

And in the case of signal delivery for x86_64 binaries, if the fpstate is live
in the CPU registers, then the live state is copied directly to the user
sigframe. Otherwise  fpstate in the task struct is copied to the user sigframe.
During restore, fpstate in the user sigframe is restored directly to the live
CPU registers.

Historically, different code paths led to different bugs. For example,
x86_64 code path was not preemption safe till recently. Also there is lot
of code duplication for support of new features like xsave etc.

Unify signal handling code paths for x86 and x86_64 kernels.

New strategy is as follows:

Signal delivery: Both for 32/64-bit frames, align the core math frame area to
64bytes as needed by xsave (this where the main fpu/extended state gets copied
to and excludes the legacy compatibility fsave header for the 32-bit [f]xsave
frames). If the state is live, copy the register state directly to the user
frame. If not live, copy the state in the thread struct to the user frame. And
for 32-bit [f]xsave frames, construct the fsave header separately before
the actual [f]xsave area.

Signal return: As the 32-bit frames with [f]xstate has an additional
'fsave' header, copy everything back from the user sigframe to the
fpstate in the task structure and reconstruct the fxstate from the 'fsave'
header (Also user passed pointers may not be correctly aligned for
any attempt to directly restore any partial state). At the next fpstate usage,
everything will be restored to the live CPU registers.
For all the 64-bit frames and the 32-bit fsave frame, restore the state from
the user sigframe directly to the live CPU registers. 64-bit signals always
restored the math frame directly, so we can expect the math frame pointer
to be correctly aligned. For 32-bit fsave frames, there are no alignment
requirements, so we can restore the state directly.

"lat_sig catch" microbenchmark numbers (for x86, x86_64, x86_32 binaries) are
with in the noise range with this change.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Link: http://lkml.kernel.org/r/1343171129-2747-4-git-send-email-suresh.b.siddha@intel.com
[ Merged in compilation fix ]
Link: http://lkml.kernel.org/r/1344544736.8326.17.camel@sbsiddha-desk.sc.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

8 files changed, 348 insertions, 484 deletions

diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 452d4dd0a95..8c77c64fbd2 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -251,7 +251,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 
 		get_user_ex(tmp, &sc->fpstate);
 		buf = compat_ptr(tmp);
-		err |= restore_i387_xstate_ia32(buf);
+		err |= restore_xstate_sig(buf, 1);
 
 		get_user_ex(*pax, &sc->ax);
 	} get_user_catch(err);
@@ -382,9 +382,12 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 		sp = (unsigned long) ka->sa.sa_restorer;
 
 	if (used_math()) {
-		sp = sp - sig_xstate_ia32_size;
+		unsigned long fx_aligned, math_size;
+
+		sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size);
 		*fpstate = (struct _fpstate_ia32 __user *) sp;
-		if (save_i387_xstate_ia32(*fpstate) < 0)
+		if (save_xstate_sig(*fpstate, (void __user *)fx_aligned,
+				    math_size) < 0)
 			return (void __user *) -1L;
 	}
 
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 016acb30fa4..4fbb4195bc6 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -22,11 +22,30 @@
 #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);
 
 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;
@@ -39,19 +58,11 @@ extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
  */
 #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
 
@@ -119,17 +130,6 @@ static inline int fsave_user(struct i387_fsave_struct __user *fx)
 
 static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
-	int err;
-
-	/*
-	 * 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;
-
 	if (config_enabled(CONFIG_X86_32))
 		return check_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
 	else if (config_enabled(CONFIG_AS_FXSAVEQ))
@@ -189,19 +189,6 @@ static inline void fpu_fxsave(struct fpu *fpu)
 			     : [fx] "R" (&fpu->state->fxsave));
 	}
 }
-#ifdef CONFIG_X86_64
-
-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  /* CONFIG_X86_32 */
-
-#define ia32_setup_frame	__setup_frame
-#define ia32_setup_rt_frame	__setup_rt_frame
-
-#endif	/* CONFIG_X86_64 */
 
 /*
  * These must be called with preempt disabled. Returns
@@ -392,10 +379,28 @@ static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
 /*
  * 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 int xstate_sigframe_size(void)
+{
+	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);
+}
 
-static inline void __clear_fpu(struct task_struct *tsk)
+static inline void __drop_fpu(struct task_struct *tsk)
 {
 	if (__thread_has_fpu(tsk)) {
 		/* Ignore delayed exceptions from user space */
@@ -443,11 +448,21 @@ static inline void save_init_fpu(struct task_struct *tsk)
 	preempt_enable();
 }
 
-static inline void clear_fpu(struct task_struct *tsk)
+static inline void stop_fpu_preload(struct task_struct *tsk)
 {
+	tsk->fpu_counter = 0;
+}
+
+static inline void drop_fpu(struct task_struct *tsk)
+{
+	/*
+	 * Forget coprocessor state..
+	 */
+	stop_fpu_preload(tsk);
 	preempt_disable();
-	__clear_fpu(tsk);
+	__drop_fpu(tsk);
 	preempt_enable();
+	clear_used_math();
 }
 
 /*
@@ -511,4 +526,20 @@ static inline void fpu_copy(struct fpu *dst, struct fpu *src)
 
 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/xsave.h b/arch/x86/include/asm/xsave.h
index aaac810e861..c1d989a1519 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -38,9 +38,6 @@ extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 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 xsave_struct *fx)
 {
@@ -68,8 +65,7 @@ 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;
 
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index f250431fb50..ab6a2e8028a 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -19,20 +19,6 @@
 #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?
  *
@@ -113,16 +99,9 @@ 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)
@@ -454,7 +433,7 @@ 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 +470,8 @@ 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 +568,6 @@ 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 ef6a8456f71..30069d1a6a4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -97,16 +97,6 @@ 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..
  */
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index c4c6a5c2bf0..861a9d1a463 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1332,9 +1332,6 @@ 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 bed431a3816..e10f96a7e04 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);
@@ -206,7 +206,9 @@ 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);
 
 	/* redzone */
@@ -228,10 +230,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	}
 
 	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;
 	}
 
@@ -244,8 +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;
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 7a3d4df9eaf..0923d27f23d 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>
 
 /*
@@ -25,11 +23,7 @@ u64 pcntxt_mask;
  */
 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
-
+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;
@@ -104,215 +98,314 @@ 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.
  */
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
+{
+	if (use_fxsr()) {
+		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct user_i387_ia32_struct env;
+		struct _fpstate_ia32 __user *fp = buf;
 
-int save_i387_xstate(void __user *buf)
+		convert_from_fxsr(&env, tsk);
+
+		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 {
+		struct i387_fsave_struct __user *fp = buf;
+		u32 swd;
+		if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
+			return -1;
+	}
+
+	return 0;
+}
+
+static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
 {
-	struct task_struct *tsk = current;
-	int err = 0;
+	struct xsave_struct __user *x = buf;
+	struct _fpx_sw_bytes *sw_bytes;
+	u32 xstate_bv;
+	int err;
 
-	if (!access_ok(VERIFY_WRITE, buf, sig_xstate_size))
-		return -EACCES;
+	/* 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));
 
-	BUG_ON(sig_xstate_size < xstate_size);
+	if (!use_xsave())
+		return err;
 
-	if ((unsigned long)buf % 64)
-		pr_err("%s: bad fpstate %p\n", __func__, buf);
+	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
 
-	if (!used_math())
-		return 0;
+	/*
+	 * Read the xstate_bv which we copied (directly from the cpu or
+	 * from the state in task struct) to the user buffers.
+	 */
+	err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
 
-	if (user_has_fpu()) {
-		if (use_xsave())
-			err = xsave_user(buf);
-		else
-			err = fxsave_user(buf);
+	/*
+	 * 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 apps 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.
+	 */
+	xstate_bv |= XSTATE_FPSSE;
 
-		if (unlikely(err)) {
-			__clear_user(buf, xstate_size);
-			return err;
-		}
+	err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
+
+	return err;
+}
+
+static inline int save_user_xstate(struct xsave_struct __user *buf)
+{
+	int err;
+
+	if (use_xsave())
+		err = xsave_user(buf);
+	else if (use_fxsr())
+		err = fxsave_user((struct i387_fxsave_struct __user *) buf);
+	else
+		err = fsave_user((struct i387_fsave_struct __user *) buf);
+
+	if (unlikely(err) && __clear_user(buf, xstate_size))
+		err = -EFAULT;
+	return err;
+}
+
+/*
+ * Save the fpu, extended register state to the user signal frame.
+ *
+ * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
+ *  state is copied.
+ *  'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
+ *
+ *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
+ *	buf != buf_fx for 32-bit frames with fxstate.
+ *
+ * If the fpu, extended register state is live, save the state directly
+ * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
+ * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ *
+ * If this is a 32-bit frame with fxstate, put a fsave header before
+ * the aligned state at 'buf_fx'.
+ *
+ * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
+ * indicating the absence/presence of the extended state to the user.
+ */
+int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
+{
+	struct xsave_struct *xsave = &current->thread.fpu.state->xsave;
+	struct task_struct *tsk = current;
+	int ia32_fxstate = (buf != buf_fx);
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
+
+	if (!access_ok(VERIFY_WRITE, buf, size))
+		return -EACCES;
+
+	if (!HAVE_HWFP)
+		return fpregs_soft_get(current, NULL, 0,
+			sizeof(struct user_i387_ia32_struct), NULL,
+			(struct _fpstate_ia32 __user *) buf) ? -1 : 1;
+
+	if (user_has_fpu()) {
+		/* Save the live register state to the user directly. */
+		if (save_user_xstate(buf_fx))
+			return -1;
+		/* Update the thread's fxstate to save the fsave header. */
+		if (ia32_fxstate)
+			fpu_fxsave(&tsk->thread.fpu);
 		user_fpu_end();
 	} else {
 		sanitize_i387_state(tsk);
-		if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
-				   xstate_size))
+		if (__copy_to_user(buf_fx, xsave, xstate_size))
 			return -1;
 	}
 
-	clear_used_math(); /* trigger finit */
+	/* Save the fsave header for the 32-bit frames. */
+	if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
+		return -1;
 
-	if (use_xsave()) {
-		struct _fpstate __user *fx = buf;
-		struct _xstate __user *x = buf;
-		u64 xstate_bv;
+	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
+		return -1;
+
+	drop_fpu(tsk);	/* trigger finit */
+
+	return 0;
+}
 
-		err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved,
-				     sizeof(struct _fpx_sw_bytes));
+static inline void
+sanitize_restored_xstate(struct task_struct *tsk,
+			 struct user_i387_ia32_struct *ia32_env,
+			 u64 xstate_bv, int fx_only)
+{
+	struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+	struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr;
 
-		err |= __put_user(FP_XSTATE_MAGIC2,
-				  (__u32 __user *) (buf + sig_xstate_size
-						    - FP_XSTATE_MAGIC2_SIZE));
+	if (use_xsave()) {
+		/* These bits must be zero. */
+		xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
 
 		/*
-		 * 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.
+		 * Init the state that is not present in the memory
+		 * layout and not enabled by the OS.
 		 */
-		err |= __get_user(xstate_bv, &x->xstate_hdr.xstate_bv);
+		if (fx_only)
+			xsave_hdr->xstate_bv = XSTATE_FPSSE;
+		else
+			xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
+	}
 
+	if (use_fxsr()) {
 		/*
-		 * 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 apps 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.
+		 * mscsr reserved bits must be masked to zero for security
+		 * reasons.
 		 */
-		xstate_bv |= XSTATE_FPSSE;
-
-		err |= __put_user(xstate_bv, &x->xstate_hdr.xstate_bv);
+		xsave->i387.mxcsr &= mxcsr_feature_mask;
 
-		if (err)
-			return err;
+		convert_to_fxsr(tsk, ia32_env);
 	}
-
-	return 1;
 }
 
 /*
- * Restore the extended state if present. Otherwise, restore the FP/SSE
- * state.
+ * Restore the extended state if present. Otherwise, restore the FP/SSE state.
  */
-static int restore_user_xstate(void __user *buf)
+static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
 {
-	struct _fpx_sw_bytes fx_sw_user;
-	u64 mask;
-	int err;
-
-	if (((unsigned long)buf % 64) ||
-	     check_for_xstate(buf, buf, &fx_sw_user))
-		goto fx_only;
-
-	mask = fx_sw_user.xstate_bv;
-
-	/*
-	 * restore the state passed by the user.
-	 */
-	err = xrestore_user(buf, mask);
-	if (err)
-		return err;
-
-	/*
-	 * init the state skipped by the user.
-	 */
-	mask = pcntxt_mask & ~mask;
-	if (unlikely(mask))
-		xrstor_state(init_xstate_buf, mask);
-
-	return 0;
-
-fx_only:
-	/*
-	 * couldn't find the extended state information in the
-	 * memory layout. Restore just the FP/SSE and init all
-	 * the other extended state.
-	 */
-	xrstor_state(init_xstate_buf, pcntxt_mask & ~XSTATE_FPSSE);
-	return fxrstor_checking((__force struct i387_fxsave_struct *)buf);
+	if (use_xsave()) {
+		if ((unsigned long)buf % 64 || fx_only) {
+			u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE;
+			xrstor_state(init_xstate_buf, init_bv);
+			return fxrstor_checking((__force void *) buf);
+		} else {
+			u64 init_bv = pcntxt_mask & ~xbv;
+			if (unlikely(init_bv))
+				xrstor_state(init_xstate_buf, init_bv);
+			return xrestore_user(buf, xbv);
+		}
+	} else if (use_fxsr()) {
+		return fxrstor_checking((__force void *) buf);
+	} else
+		return frstor_checking((__force void *) buf);
 }
 
-/*
- * This restores directly out of user space. Exceptions are handled.
- */
-int restore_i387_xstate(void __user *buf)
+int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 {
+	int ia32_fxstate = (buf != buf_fx);
 	struct task_struct *tsk = current;
-	int err = 0;
+	int state_size = xstate_size;
+	u64 xstate_bv = 0;
+	int fx_only = 0;
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
 
 	if (!buf) {
-		if (used_math())
-			goto clear;
+		drop_fpu(tsk);
 		return 0;
-	} else
-		if (!access_ok(VERIFY_READ, buf, sig_xstate_size))
-			return -EACCES;
+	}
+
+	if (!access_ok(VERIFY_READ, buf, size))
+		return -EACCES;
+
+	if (!used_math() && init_fpu(tsk))
+		return -1;
 
-	if (!used_math()) {
-		err = init_fpu(tsk);
-		if (err)
-			return err;
+	if (!HAVE_HWFP) {
+		return fpregs_soft_set(current, NULL,
+				       0, sizeof(struct user_i387_ia32_struct),
+				       NULL, buf) != 0;
 	}
 
-	user_fpu_begin();
-	if (use_xsave())
-		err = restore_user_xstate(buf);
-	else
-		err = fxrstor_checking((__force struct i387_fxsave_struct *)
-				       buf);
-	if (unlikely(err)) {
+	if (use_xsave()) {
+		struct _fpx_sw_bytes fx_sw_user;
+		if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
+			/*
+			 * Couldn't find the extended state information in the
+			 * memory layout. Restore just the FP/SSE and init all
+			 * the other extended state.
+			 */
+			state_size = sizeof(struct i387_fxsave_struct);
+			fx_only = 1;
+		} else {
+			state_size = fx_sw_user.xstate_size;
+			xstate_bv = fx_sw_user.xstate_bv;
+		}
+	}
+
+	if (ia32_fxstate) {
+		/*
+		 * For 32-bit frames with fxstate, copy the user state to the
+		 * thread's fpu state, reconstruct fxstate from the fsave
+		 * header. Sanitize the copied state etc.
+		 */
+		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct user_i387_ia32_struct env;
+
+		stop_fpu_preload(tsk);
+		unlazy_fpu(tsk);
+
+		if (__copy_from_user(xsave, buf_fx, state_size) ||
+		    __copy_from_user(&env, buf, sizeof(env))) {
+			drop_fpu(tsk);
+			return -1;
+		}
+
+		sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
+	} else {
 		/*
-		 * Encountered an error while doing the restore from the
-		 * user buffer, clear the fpu state.
+		 * For 64-bit frames and 32-bit fsave frames, restore the user
+		 * state to the registers directly (with exceptions handled).
 		 */
-clear:
-		clear_fpu(tsk);
-		clear_used_math();
+		user_fpu_begin();
+		if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
+			drop_fpu(tsk);
+			return -1;
+		}
 	}
-	return err;
+
+	return 0;
 }
-#endif
 
 /*
  * Prepare the SW reserved portion of the fxsave memory layout, indicating
@@ -323,31 +416,22 @@ clear:
  */
 static void prepare_fx_sw_frame(void)
 {
-	int size_extended = (xstate_size - sizeof(struct i387_fxsave_struct)) +
-			     FP_XSTATE_MAGIC2_SIZE;
-
-	sig_xstate_size = sizeof(struct _fpstate) + size_extended;
-
-#ifdef CONFIG_IA32_EMULATION
-	sig_xstate_ia32_size = sizeof(struct _fpstate_ia32) + size_extended;
-#endif
+	int fsave_header_size = sizeof(struct i387_fsave_struct);
+	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
 
-	memset(&fx_sw_reserved, 0, sizeof(fx_sw_reserved));
+	if (config_enabled(CONFIG_X86_32))
+		size += fsave_header_size;
 
 	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
-	fx_sw_reserved.extended_size = sig_xstate_size;
+	fx_sw_reserved.extended_size = size;
 	fx_sw_reserved.xstate_bv = pcntxt_mask;
 	fx_sw_reserved.xstate_size = xstate_size;
-#ifdef CONFIG_IA32_EMULATION
-	memcpy(&fx_sw_reserved_ia32, &fx_sw_reserved,
-	       sizeof(struct _fpx_sw_bytes));
-	fx_sw_reserved_ia32.extended_size = sig_xstate_ia32_size;
-#endif
-}
 
-#ifdef CONFIG_X86_64
-unsigned int sig_xstate_size = sizeof(struct _fpstate);
-#endif
+	if (config_enabled(CONFIG_IA32_EMULATION)) {
+		fx_sw_reserved_ia32 = fx_sw_reserved;
+		fx_sw_reserved_ia32.extended_size += fsave_header_size;
+	}
+}
 
 /*
  * Enable the extended processor state save/restore feature