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

Pull x86 FPU updates from Ingo Molnar:
 "This tree contains two main changes:

   - The big FPU code rewrite: wide reaching cleanups and reorganization
     that pulls all the FPU code together into a clean base in
     arch/x86/fpu/.

     The resulting code is leaner and faster, and much easier to
     understand.  This enables future work to further simplify the FPU
     code (such as removing lazy FPU restores).

     By its nature these changes have a substantial regression risk: FPU
     code related bugs are long lived, because races are often subtle
     and bugs mask as user-space failures that are difficult to track
     back to kernel side backs.  I'm aware of no unfixed (or even
     suspected) FPU related regression so far.

   - MPX support rework/fixes.  As this is still not a released CPU
     feature, there were some buglets in the code - should be much more
     robust now (Dave Hansen)"

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (250 commits)
  x86/fpu: Fix double-increment in setup_xstate_features()
  x86/mpx: Allow 32-bit binaries on 64-bit kernels again
  x86/mpx: Do not count MPX VMAs as neighbors when unmapping
  x86/mpx: Rewrite the unmap code
  x86/mpx: Support 32-bit binaries on 64-bit kernels
  x86/mpx: Use 32-bit-only cmpxchg() for 32-bit apps
  x86/mpx: Introduce new 'directory entry' to 'addr' helper function
  x86/mpx: Add temporary variable to reduce masking
  x86: Make is_64bit_mm() widely available
  x86/mpx: Trace allocation of new bounds tables
  x86/mpx: Trace the attempts to find bounds tables
  x86/mpx: Trace entry to bounds exception paths
  x86/mpx: Trace #BR exceptions
  x86/mpx: Introduce a boot-time disable flag
  x86/mpx: Restrict the mmap() size check to bounds tables
  x86/mpx: Remove redundant MPX_BNDCFG_ADDR_MASK
  x86/mpx: Clean up the code by not passing a task pointer around when unnecessary
  x86/mpx: Use the new get_xsave_field_ptr()API
  x86/fpu/xstate: Wrap get_xsave_addr() to make it safer
  x86/fpu/xstate: Fix up bad get_xsave_addr() assumptions
  ...

Documentation/kernel-parameters.txt

@@ -937,6 +937,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Enable debug messages at boot time.  See
 			Documentation/dynamic-debug-howto.txt for details.
 
+	nompx		[X86] Disables Intel Memory Protection Extensions.
+			See Documentation/x86/intel_mpx.txt for more
+			information about the feature.
+
 	eagerfpu=	[X86]
 			on	enable eager fpu restore
 			off	disable eager fpu restore

Documentation/preempt-locking.txt

@@ -48,7 +48,7 @@ preemption must be disabled around such regions.
 
 Note, some FPU functions are already explicitly preempt safe.  For example,
 kernel_fpu_begin and kernel_fpu_end will disable and enable preemption.
-However, math_state_restore must be called with preemption disabled.
+However, fpu__restore() must be called with preemption disabled.
 
 
 RULE #3: Lock acquire and release must be performed by same task

arch/x86/Kconfig.debug

@@ -332,4 +332,16 @@ config X86_DEBUG_STATIC_CPU_HAS
 
 	  If unsure, say N.
 
+config X86_DEBUG_FPU
+	bool "Debug the x86 FPU code"
+	depends on DEBUG_KERNEL
+	default y
+	---help---
+	  If this option is enabled then there will be extra sanity
+	  checks and (boot time) debug printouts added to the kernel.
+	  This debugging adds some small amount of runtime overhead
+	  to the kernel.
+
+	  If unsure, say N.
+
 endmenu

arch/x86/crypto/aesni-intel_glue.c

@@ -32,7 +32,7 @@
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/aes.h>
 #include <crypto/ablk_helper.h>
 #include <crypto/scatterwalk.h>

arch/x86/crypto/camellia_aesni_avx2_glue.c

@@ -19,8 +19,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/camellia.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -561,16 +560,15 @@ static struct crypto_alg cmll_algs[10] = { {
 
 static int __init camellia_aesni_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
 	if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
 		pr_info("AVX2 or AES-NI instructions are not detected.\n");
 		return -ENODEV;
 	}
 
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX2 detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 

arch/x86/crypto/camellia_aesni_avx_glue.c

@@ -19,8 +19,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/camellia.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -553,16 +552,10 @@ static struct crypto_alg cmll_algs[10] = { {
 
 static int __init camellia_aesni_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
-		pr_info("AVX or AES-NI instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 

arch/x86/crypto/cast5_avx_glue.c

@@ -31,8 +31,7 @@
 #include <crypto/cast5.h>
 #include <crypto/cryptd.h>
 #include <crypto/ctr.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAST5_PARALLEL_BLOCKS 16
@@ -468,16 +467,10 @@ static struct crypto_alg cast5_algs[6] = { {
 
 static int __init cast5_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		pr_info("AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 

arch/x86/crypto/cast6_avx_glue.c

@@ -36,8 +36,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAST6_PARALLEL_BLOCKS 8
@@ -590,16 +589,10 @@ static struct crypto_alg cast6_algs[10] = { {
 
 static int __init cast6_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		pr_info("AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 

arch/x86/crypto/crc32-pclmul_glue.c

@@ -35,7 +35,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4

arch/x86/crypto/crc32c-intel_glue.c

@@ -32,8 +32,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4

arch/x86/crypto/crct10dif-pclmul_glue.c

@@ -29,7 +29,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
 

arch/x86/crypto/fpu.c

@@ -18,7 +18,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 struct crypto_fpu_ctx {
 	struct crypto_blkcipher *child;

arch/x86/crypto/ghash-clmulni-intel_glue.c

@@ -19,7 +19,7 @@
 #include <crypto/cryptd.h>
 #include <crypto/gf128mul.h>
 #include <crypto/internal/hash.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/cpu_device_id.h>
 
 #define GHASH_BLOCK_SIZE	16

arch/x86/crypto/serpent_avx2_glue.c

@@ -20,8 +20,7 @@
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
 #include <crypto/serpent.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/serpent-avx.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -537,16 +536,14 @@ static struct crypto_alg srp_algs[10] = { {
 
 static int __init init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
 	if (!cpu_has_avx2 || !cpu_has_osxsave) {
 		pr_info("AVX2 instructions are not detected.\n");
 		return -ENODEV;
 	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 

arch/x86/crypto/serpent_avx_glue.c

@@ -36,8 +36,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/serpent-avx.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -596,16 +595,10 @@ static struct crypto_alg serpent_algs[10] = { {
 
 static int __init serpent_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		printk(KERN_INFO "AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		printk(KERN_INFO "AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 

arch/x86/crypto/sha-mb/sha1_mb.c

@@ -65,11 +65,8 @@
 #include <crypto/mcryptd.h>
 #include <crypto/crypto_wq.h>
 #include <asm/byteorder.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
 #include <linux/hardirq.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/api.h>
 #include "sha_mb_ctx.h"
 
 #define FLUSH_INTERVAL 1000 /* in usec */

arch/x86/crypto/sha1_ssse3_glue.c

@@ -29,9 +29,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 
 
 asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
@@ -123,15 +121,9 @@ static struct shash_alg alg = {
 #ifdef CONFIG_AS_AVX
 static bool __init avx_usable(void)
 {
-	u64 xcr0;
-
-	if (!cpu_has_avx || !cpu_has_osxsave)
-		return false;
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
-
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+		if (cpu_has_avx)
+			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
 

arch/x86/crypto/sha256_ssse3_glue.c

@@ -37,9 +37,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <linux/string.h>
 
 asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data,
@@ -132,15 +130,9 @@ static struct shash_alg algs[] = { {
 #ifdef CONFIG_AS_AVX
 static bool __init avx_usable(void)
 {
-	u64 xcr0;
-
-	if (!cpu_has_avx || !cpu_has_osxsave)
-		return false;
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
-
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+		if (cpu_has_avx)
+			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
 

arch/x86/crypto/sha512_ssse3_glue.c

@@ -35,9 +35,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha512_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 
 #include <linux/string.h>
 
@@ -131,15 +129,9 @@ static struct shash_alg algs[] = { {
 #ifdef CONFIG_AS_AVX
 static bool __init avx_usable(void)
 {
-	u64 xcr0;
-
-	if (!cpu_has_avx || !cpu_has_osxsave)
-		return false;
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
-
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+		if (cpu_has_avx)
+			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
 

arch/x86/crypto/twofish_avx_glue.c

@@ -36,9 +36,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/twofish.h>
 #include <asm/crypto/glue_helper.h>
 #include <crypto/scatterwalk.h>
@@ -558,16 +556,10 @@ static struct crypto_alg twofish_algs[10] = { {
 
 static int __init twofish_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		printk(KERN_INFO "AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		printk(KERN_INFO "AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 

arch/x86/ia32/ia32_signal.c

@@ -21,8 +21,8 @@
 #include <linux/binfmts.h>
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
 #include <asm/ptrace.h>
 #include <asm/ia32_unistd.h>
 #include <asm/user32.h>
@@ -198,7 +198,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 		buf = compat_ptr(tmp);
 	} get_user_catch(err);
 
-	err |= restore_xstate_sig(buf, 1);
+	err |= fpu__restore_sig(buf, 1);
 
 	force_iret();
 
@@ -308,6 +308,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 				 size_t frame_size,
 				 void __user **fpstate)
 {
+	struct fpu *fpu = &current->thread.fpu;
 	unsigned long sp;
 
 	/* Default to using normal stack */
@@ -322,12 +323,12 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 		 ksig->ka.sa.sa_restorer)
 		sp = (unsigned long) ksig->ka.sa.sa_restorer;
 
-	if (used_math()) {
+	if (fpu->fpstate_active) {
 		unsigned long fx_aligned, math_size;
 
-		sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size);
+		sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
 		*fpstate = (struct _fpstate_ia32 __user *) sp;
-		if (save_xstate_sig(*fpstate, (void __user *)fx_aligned,
+		if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned,
 				    math_size) < 0)
 			return (void __user *) -1L;
 	}

arch/x86/include/asm/alternative.h

@@ -52,6 +52,12 @@ struct alt_instr {
 	u8  padlen;		/* length of build-time padding */
 } __packed;
 
+/*
+ * Debug flag that can be tested to see whether alternative
+ * instructions were patched in already:
+ */
+extern int alternatives_patched;
+
 extern void alternative_instructions(void);
 extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 

arch/x86/include/asm/crypto/glue_helper.h

@@ -7,7 +7,7 @@
 
 #include <linux/kernel.h>
 #include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <crypto/b128ops.h>
 
 typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);

arch/x86/include/asm/efi.h

@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_EFI_H
 #define _ASM_X86_EFI_H
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/pgtable.h>
 
 /*

arch/x86/include/asm/fpu-internal.h

@@ -1,626 +0,0 @@
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _FPU_INTERNAL_H
-#define _FPU_INTERNAL_H
-
-#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>
-#include <asm/processor.h>
-#include <asm/sigcontext.h>
-#include <asm/user.h>
-#include <asm/uaccess.h>
-#include <asm/xsave.h>
-#include <asm/smap.h>
-
-#ifdef CONFIG_X86_64
-# include <asm/sigcontext32.h>
-# include <asm/user32.h>
-struct ksignal;
-int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
-			compat_sigset_t *set, struct pt_regs *regs);
-int ia32_setup_frame(int sig, struct ksignal *ksig,
-		     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
-
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-/*
- * Must be run with preemption disabled: this clears the fpu_owner_task,
- * on this CPU.
- *
- * This will disable any lazy FPU state restore of the current FPU state,
- * but if the current thread owns the FPU, it will still be saved by.
- */
-static inline void __cpu_disable_lazy_restore(unsigned int cpu)
-{
-	per_cpu(fpu_owner_task, cpu) = NULL;
-}
-
-/*
- * Used to indicate that the FPU state in memory is newer than the FPU
- * state in registers, and the FPU state should be reloaded next time the
- * task is run. Only safe on the current task, or non-running tasks.
- */
-static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk)
-{
-	tsk->thread.fpu.last_cpu = ~0;
-}
-
-static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
-{
-	return new == this_cpu_read_stable(fpu_owner_task) &&
-		cpu == new->thread.fpu.last_cpu;
-}
-
-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_safe(X86_FEATURE_EAGER_FPU);
-}
-
-static __always_inline __pure bool use_xsaveopt(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
-}
-
-static __always_inline __pure bool use_xsave(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_XSAVE);
-}
-
-static __always_inline __pure bool use_fxsr(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_FXSR);
-}
-
-static inline void fx_finit(struct i387_fxsave_struct *fx)
-{
-	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)
-{
-	if (!use_xsaveopt())
-		return;
-	__sanitize_i387_state(tsk);
-}
-
-#define user_insn(insn, output, input...)				\
-({									\
-	int err;							\
-	asm volatile(ASM_STAC "\n"					\
-		     "1:" #insn "\n\t"					\
-		     "2: " ASM_CLAC "\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;								\
-})
-
-#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)
-{
-	return user_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
-}
-
-static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
-{
-	if (config_enabled(CONFIG_X86_32))
-		return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
-	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
-
-	/* See comment in fpu_fxsave() below. */
-	return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
-}
-
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
-	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));
-
-	/* See comment in fpu_fxsave() below. */
-	return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
-			  "m" (*fx));
-}
-
-static inline int fxrstor_user(struct i387_fxsave_struct __user *fx)
-{
-	if (config_enabled(CONFIG_X86_32))
-		return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-
-	/* See comment in fpu_fxsave() below. */
-	return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
-			  "m" (*fx));
-}
-
-static inline int frstor_checking(struct i387_fsave_struct *fx)
-{
-	return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline int frstor_user(struct i387_fsave_struct __user *fx)
-{
-	return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline void fpu_fxsave(struct fpu *fpu)
-{
-	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 %[fx]" : [fx] "=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));
-	}
-}
-
-/*
- * These must be called with preempt disabled. Returns
- * 'true' if the FPU state is still intact.
- */
-static inline int fpu_save_init(struct fpu *fpu)
-{
-	if (use_xsave()) {
-		fpu_xsave(fpu);
-
-		/*
-		 * xsave header may indicate the init state of the FP.
-		 */
-		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
-			return 1;
-	} else if (use_fxsr()) {
-		fpu_fxsave(fpu);
-	} else {
-		asm volatile("fnsave %[fx]; fwait"
-			     : [fx] "=m" (fpu->state->fsave));
-		return 0;
-	}
-
-	/*
-	 * If exceptions are pending, we need to clear them so
-	 * that we don't randomly get exceptions later.
-	 *
-	 * FIXME! Is this perhaps only true for the old-style
-	 * irq13 case? Maybe we could leave the x87 state
-	 * intact otherwise?
-	 */
-	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
-		asm volatile("fnclex");
-		return 0;
-	}
-	return 1;
-}
-
-static inline int __save_init_fpu(struct task_struct *tsk)
-{
-	return fpu_save_init(&tsk->thread.fpu);
-}
-
-static inline int fpu_restore_checking(struct fpu *fpu)
-{
-	if (use_xsave())
-		return fpu_xrstor_checking(&fpu->state->xsave);
-	else if (use_fxsr())
-		return fxrstor_checking(&fpu->state->fxsave);
-	else
-		return frstor_checking(&fpu->state->fsave);
-}
-
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
-	/*
-	 * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
-	 * pending. Clear the x87 state here by setting it to fixed values.
-	 * "m" is a random variable that should be in L1.
-	 */
-	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
-		asm volatile(
-			"fnclex\n\t"
-			"emms\n\t"
-			"fildl %P[addr]"	/* set F?P to defined value */
-			: : [addr] "m" (tsk->thread.fpu.has_fpu));
-	}
-
-	return fpu_restore_checking(&tsk->thread.fpu);
-}
-
-/*
- * Software FPU state helpers. Careful: these need to
- * be preemption protection *and* they need to be
- * properly paired with the CR0.TS changes!
- */
-static inline int __thread_has_fpu(struct task_struct *tsk)
-{
-	return tsk->thread.fpu.has_fpu;
-}
-
-/* Must be paired with an 'stts' after! */
-static inline void __thread_clear_has_fpu(struct task_struct *tsk)
-{
-	tsk->thread.fpu.has_fpu = 0;
-	this_cpu_write(fpu_owner_task, NULL);
-}
-
-/* Must be paired with a 'clts' before! */
-static inline void __thread_set_has_fpu(struct task_struct *tsk)
-{
-	tsk->thread.fpu.has_fpu = 1;
-	this_cpu_write(fpu_owner_task, tsk);
-}
-
-/*
- * Encapsulate the CR0.TS handling together with the
- * software flag.
- *
- * These generally need preemption protection to work,
- * do try to avoid using these on their own.
- */
-static inline void __thread_fpu_end(struct task_struct *tsk)
-{
-	__thread_clear_has_fpu(tsk);
-	if (!use_eager_fpu())
-		stts();
-}
-
-static inline void __thread_fpu_begin(struct task_struct *tsk)
-{
-	if (!use_eager_fpu())
-		clts();
-	__thread_set_has_fpu(tsk);
-}
-
-static inline void drop_fpu(struct task_struct *tsk)
-{
-	/*
-	 * Forget coprocessor state..
-	 */
-	preempt_disable();
-	tsk->thread.fpu_counter = 0;
-
-	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);
-	}
-
-	clear_stopped_child_used_math(tsk);
-	preempt_enable();
-}
-
-static inline void restore_init_xstate(void)
-{
-	if (use_xsave())
-		xrstor_state(init_xstate_buf, -1);
-	else
-		fxrstor_checking(&init_xstate_buf->i387);
-}
-
-/*
- * Reset the FPU state in the eager case and drop it in the lazy case (later use
- * will reinit it).
- */
-static inline void fpu_reset_state(struct task_struct *tsk)
-{
-	if (!use_eager_fpu())
-		drop_fpu(tsk);
-	else
-		restore_init_xstate();
-}
-
-/*
- * FPU state switching for scheduling.
- *
- * This is a two-stage process:
- *
- *  - switch_fpu_prepare() saves the old state and
- *    sets the new state of the CR0.TS bit. This is
- *    done within the context of the old process.
- *
- *  - switch_fpu_finish() restores the new state as
- *    necessary.
- */
-typedef struct { int preload; } fpu_switch_t;
-
-static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
-{
-	fpu_switch_t fpu;
-
-	/*
-	 * 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->thread.fpu_counter > 5);
-
-	if (__thread_has_fpu(old)) {
-		if (!__save_init_fpu(old))
-			task_disable_lazy_fpu_restore(old);
-		else
-			old->thread.fpu.last_cpu = cpu;
-
-		/* But leave fpu_owner_task! */
-		old->thread.fpu.has_fpu = 0;
-
-		/* Don't change CR0.TS if we just switch! */
-		if (fpu.preload) {
-			new->thread.fpu_counter++;
-			__thread_set_has_fpu(new);
-			prefetch(new->thread.fpu.state);
-		} else if (!use_eager_fpu())
-			stts();
-	} else {
-		old->thread.fpu_counter = 0;
-		task_disable_lazy_fpu_restore(old);
-		if (fpu.preload) {
-			new->thread.fpu_counter++;
-			if (fpu_lazy_restore(new, cpu))
-				fpu.preload = 0;
-			else
-				prefetch(new->thread.fpu.state);
-			__thread_fpu_begin(new);
-		}
-	}
-	return fpu;
-}
-
-/*
- * By the time this gets called, we've already cleared CR0.TS and
- * given the process the FPU if we are going to preload the FPU
- * state - all we need to do is to conditionally restore the register
- * state itself.
- */
-static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
-{
-	if (fpu.preload) {
-		if (unlikely(restore_fpu_checking(new)))
-			fpu_reset_state(new);
-	}
-}
-
-/*
- * Signal frame handlers...
- */
-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);
-}
-
-/*
- * Needs to be preemption-safe.
- *
- * NOTE! user_fpu_begin() must be used only immediately before restoring
- * the save state. It does not do any saving/restoring on its own. In
- * lazy FPU mode, it is just an optimization to avoid a #NM exception,
- * the task can lose the FPU right after preempt_enable().
- */
-static inline void user_fpu_begin(void)
-{
-	preempt_disable();
-	if (!user_has_fpu())
-		__thread_fpu_begin(current);
-	preempt_enable();
-}
-
-static inline void __save_fpu(struct task_struct *tsk)
-{
-	if (use_xsave()) {
-		if (unlikely(system_state == SYSTEM_BOOTING))
-			xsave_state_booting(&tsk->thread.fpu.state->xsave, -1);
-		else
-			xsave_state(&tsk->thread.fpu.state->xsave, -1);
-	} else
-		fpu_fxsave(&tsk->thread.fpu);
-}
-
-/*
- * i387 state interaction
- */
-static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
-{
-	if (cpu_has_fxsr) {
-		return tsk->thread.fpu.state->fxsave.cwd;
-	} else {
-		return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
-	}
-}
-
-static inline unsigned short get_fpu_swd(struct task_struct *tsk)
-{
-	if (cpu_has_fxsr) {
-		return tsk->thread.fpu.state->fxsave.swd;
-	} else {
-		return (unsigned short)tsk->thread.fpu.state->fsave.swd;
-	}
-}
-
-static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
-{
-	if (cpu_has_xmm) {
-		return tsk->thread.fpu.state->fxsave.mxcsr;
-	} else {
-		return MXCSR_DEFAULT;
-	}
-}
-
-static bool fpu_allocated(struct fpu *fpu)
-{
-	return fpu->state != NULL;
-}
-
-static inline int fpu_alloc(struct fpu *fpu)
-{
-	if (fpu_allocated(fpu))
-		return 0;
-	fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
-	if (!fpu->state)
-		return -ENOMEM;
-	WARN_ON((unsigned long)fpu->state & 15);
-	return 0;
-}
-
-static inline void fpu_free(struct fpu *fpu)
-{
-	if (fpu->state) {
-		kmem_cache_free(task_xstate_cachep, fpu->state);
-		fpu->state = NULL;
-	}
-}
-
-static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
-{
-	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);
-	}
-}
-
-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

arch/x86/include/asm/fpu/api.h

@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_API_H
+#define _ASM_X86_FPU_API_H
+
+/*
+ * 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);
+extern void kernel_fpu_begin(void);
+extern void kernel_fpu_end(void);
+extern bool irq_fpu_usable(void);
+
+/*
+ * Some instructions like VIA's padlock instructions generate a spurious
+ * DNA fault but don't modify SSE registers. And these instructions
+ * get used from interrupt context as well. To prevent these kernel instructions
+ * in interrupt context interacting wrongly with other user/kernel fpu usage, we
+ * should use them only in the context of irq_ts_save/restore()
+ */
+extern int  irq_ts_save(void);
+extern void irq_ts_restore(int TS_state);
+
+/*
+ * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
+ *
+ * If 'feature_name' is set then put a human-readable description of
+ * the feature there as well - this can be used to print error (or success)
+ * messages.
+ */
+extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
+
+#endif /* _ASM_X86_FPU_API_H */

arch/x86/include/asm/fpu/internal.h

@@ -0,0 +1,694 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_INTERNAL_H
+#define _ASM_X86_FPU_INTERNAL_H
+
+#include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/user.h>
+#include <asm/fpu/api.h>
+#include <asm/fpu/xstate.h>
+
+/*
+ * High level FPU state handling functions:
+ */
+extern void fpu__activate_curr(struct fpu *fpu);
+extern void fpu__activate_fpstate_read(struct fpu *fpu);
+extern void fpu__activate_fpstate_write(struct fpu *fpu);
+extern void fpu__save(struct fpu *fpu);
+extern void fpu__restore(struct fpu *fpu);
+extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
+extern void fpu__drop(struct fpu *fpu);
+extern int  fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu);
+extern void fpu__clear(struct fpu *fpu);
+extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
+extern int  dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
+
+/*
+ * Boot time FPU initialization functions:
+ */
+extern void fpu__init_cpu(void);
+extern void fpu__init_system_xstate(void);
+extern void fpu__init_cpu_xstate(void);
+extern void fpu__init_system(struct cpuinfo_x86 *c);
+extern void fpu__init_check_bugs(void);
+extern void fpu__resume_cpu(void);
+
+/*
+ * Debugging facility:
+ */
+#ifdef CONFIG_X86_DEBUG_FPU
+# define WARN_ON_FPU(x) WARN_ON_ONCE(x)
+#else
+# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+#endif
+
+/*
+ * FPU related CPU feature flag helper routines:
+ */
+static __always_inline __pure bool use_eager_fpu(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
+}
+
+static __always_inline __pure bool use_xsaveopt(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
+}
+
+static __always_inline __pure bool use_xsave(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_FXSR);
+}
+
+/*
+ * fpstate handling functions:
+ */
+
+extern union fpregs_state init_fpstate;
+
+extern void fpstate_init(union fpregs_state *state);
+#ifdef CONFIG_MATH_EMULATION
+extern void fpstate_init_soft(struct swregs_state *soft);
+#else
+static inline void fpstate_init_soft(struct swregs_state *soft) {}
+#endif
+static inline void fpstate_init_fxstate(struct fxregs_state *fx)
+{
+	fx->cwd = 0x37f;
+	fx->mxcsr = MXCSR_DEFAULT;
+}
+extern void fpstate_sanitize_xstate(struct fpu *fpu);
+
+#define user_insn(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile(ASM_STAC "\n"					\
+		     "1:" #insn "\n\t"					\
+		     "2: " ASM_CLAC "\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;								\
+})
+
+#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 copy_fregs_to_user(struct fregs_state __user *fx)
+{
+	return user_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
+}
+
+static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
+{
+	if (config_enabled(CONFIG_X86_32))
+		return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
+
+	/* See comment in copy_fxregs_to_kernel() below. */
+	return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
+}
+
+static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
+{
+	int err;
+
+	if (config_enabled(CONFIG_X86_32)) {
+		err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	} else {
+		if (config_enabled(CONFIG_AS_FXSAVEQ)) {
+			err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+		} else {
+			/* See comment in copy_fxregs_to_kernel() below. */
+			err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+		}
+	}
+	/* Copying from a kernel buffer to FPU registers should never fail: */
+	WARN_ON_FPU(err);
+}
+
+static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
+{
+	if (config_enabled(CONFIG_X86_32))
+		return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+	/* See comment in copy_fxregs_to_kernel() below. */
+	return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+			  "m" (*fx));
+}
+
+static inline void copy_kernel_to_fregs(struct fregs_state *fx)
+{
+	int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+	WARN_ON_FPU(err);
+}
+
+static inline int copy_user_to_fregs(struct fregs_state __user *fx)
+{
+	return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void copy_fxregs_to_kernel(struct fpu *fpu)
+{
+	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 %[fx]" : [fx] "=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));
+	}
+}
+
+/* These macros all use (%edi)/(%rdi) as the single memory argument. */
+#define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
+#define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
+#define XSAVES		".byte " REX_PREFIX "0x0f,0xc7,0x2f"
+#define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
+#define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+
+/* xstate instruction fault handler: */
+#define xstate_fault(__err)		\
+					\
+	".section .fixup,\"ax\"\n"	\
+					\
+	"3:  movl $-2,%[_err]\n"	\
+	"    jmp  2b\n"			\
+					\
+	".previous\n"			\
+					\
+	_ASM_EXTABLE(1b, 3b)		\
+	: [_err] "=r" (__err)
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
+{
+	u64 mask = -1;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		asm volatile("1:"XSAVES"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+	else
+		asm volatile("1:"XSAVE"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+
+	/* We should never fault when copying to a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
+{
+	u64 mask = -1;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		asm volatile("1:"XRSTORS"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+	else
+		asm volatile("1:"XRSTOR"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+
+	/* We should never fault when copying from a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Save processor xstate to xsave area.
+ */
+static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
+{
+	u64 mask = -1;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(!alternatives_patched);
+
+	/*
+	 * If xsaves is enabled, xsaves replaces xsaveopt because
+	 * it supports compact format and supervisor states in addition to
+	 * modified optimization in xsaveopt.
+	 *
+	 * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
+	 * because xsaveopt supports modified optimization which is not
+	 * supported by xsave.
+	 *
+	 * If none of xsaves and xsaveopt is enabled, use xsave.
+	 */
+	alternative_input_2(
+		"1:"XSAVE,
+		XSAVEOPT,
+		X86_FEATURE_XSAVEOPT,
+		XSAVES,
+		X86_FEATURE_XSAVES,
+		[xstate] "D" (xstate), "a" (lmask), "d" (hmask) :
+		"memory");
+	asm volatile("2:\n\t"
+		     xstate_fault(err)
+		     : "0" (err)
+		     : "memory");
+
+	/* We should never fault when copying to a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Restore processor xstate from xsave area.
+ */
+static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	/*
+	 * Use xrstors to restore context if it is enabled. xrstors supports
+	 * compacted format of xsave area which is not supported by xrstor.
+	 */
+	alternative_input(
+		"1: " XRSTOR,
+		XRSTORS,
+		X86_FEATURE_XSAVES,
+		"D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask)
+		: "memory");
+
+	asm volatile("2:\n"
+		     xstate_fault(err)
+		     : "0" (err)
+		     : "memory");
+
+	/* We should never fault when copying from a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Save xstate to user space xsave area.
+ *
+ * We don't use modified optimization because xrstor/xrstors might track
+ * a different application.
+ *
+ * We don't use compacted format xsave area for
+ * backward compatibility for old applications which don't understand
+ * compacted format of xsave area.
+ */
+static inline int copy_xregs_to_user(struct xregs_state __user *buf)
+{
+	int err;
+
+	/*
+	 * Clear the xsave header first, so that reserved fields are
+	 * initialized to zero.
+	 */
+	err = __clear_user(&buf->header, sizeof(buf->header));
+	if (unlikely(err))
+		return -EFAULT;
+
+	__asm__ __volatile__(ASM_STAC "\n"
+			     "1:"XSAVE"\n"
+			     "2: " ASM_CLAC "\n"
+			     xstate_fault(err)
+			     : "D" (buf), "a" (-1), "d" (-1), "0" (err)
+			     : "memory");
+	return err;
+}
+
+/*
+ * Restore xstate from user space xsave area.
+ */
+static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask)
+{
+	struct xregs_state *xstate = ((__force struct xregs_state *)buf);
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	__asm__ __volatile__(ASM_STAC "\n"
+			     "1:"XRSTOR"\n"
+			     "2: " ASM_CLAC "\n"
+			     xstate_fault(err)
+			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err)
+			     : "memory");	/* memory required? */
+	return err;
+}
+
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact and we can
+ * keep registers active.
+ *
+ * The legacy FNSAVE instruction cleared all FPU state
+ * unconditionally, so registers are essentially destroyed.
+ * Modern FPU state can be kept in registers, if there are
+ * no pending FP exceptions.
+ */
+static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
+{
+	if (likely(use_xsave())) {
+		copy_xregs_to_kernel(&fpu->state.xsave);
+		return 1;
+	}
+
+	if (likely(use_fxsr())) {
+		copy_fxregs_to_kernel(fpu);
+		return 1;
+	}
+
+	/*
+	 * Legacy FPU register saving, FNSAVE always clears FPU registers,
+	 * so we have to mark them inactive:
+	 */
+	asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
+
+	return 0;
+}
+
+static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+	if (use_xsave()) {
+		copy_kernel_to_xregs(&fpstate->xsave, -1);
+	} else {
+		if (use_fxsr())
+			copy_kernel_to_fxregs(&fpstate->fxsave);
+		else
+			copy_kernel_to_fregs(&fpstate->fsave);
+	}
+}
+
+static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+	/*
+	 * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
+	 * pending. Clear the x87 state here by setting it to fixed values.
+	 * "m" is a random variable that should be in L1.
+	 */
+	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
+		asm volatile(
+			"fnclex\n\t"
+			"emms\n\t"
+			"fildl %P[addr]"	/* set F?P to defined value */
+			: : [addr] "m" (fpstate));
+	}
+
+	__copy_kernel_to_fpregs(fpstate);
+}
+
+extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
+
+/*
+ * FPU context switch related helper methods:
+ */
+
+DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+/*
+ * Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx,
+ * on this CPU.
+ *
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
+ */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
+}
+
+static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu)
+{
+	return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+}
+
+
+/*
+ * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation'
+ * idiom, which is then paired with the sw-flag (fpregs_active) later on:
+ */
+
+static inline void __fpregs_activate_hw(void)
+{
+	if (!use_eager_fpu())
+		clts();
+}
+
+static inline void __fpregs_deactivate_hw(void)
+{
+	if (!use_eager_fpu())
+		stts();
+}
+
+/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */
+static inline void __fpregs_deactivate(struct fpu *fpu)
+{
+	WARN_ON_FPU(!fpu->fpregs_active);
+
+	fpu->fpregs_active = 0;
+	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+}
+
+/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
+static inline void __fpregs_activate(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu->fpregs_active);
+
+	fpu->fpregs_active = 1;
+	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+}
+
+/*
+ * The question "does this thread have fpu access?"
+ * is slightly racy, since preemption could come in
+ * and revoke it immediately after the test.
+ *
+ * However, even in that very unlikely scenario,
+ * we can just assume we have FPU access - typically
+ * to save the FP state - we'll just take a #NM
+ * fault and get the FPU access back.
+ */
+static inline int fpregs_active(void)
+{
+	return current->thread.fpu.fpregs_active;
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void fpregs_activate(struct fpu *fpu)
+{
+	__fpregs_activate_hw();
+	__fpregs_activate(fpu);
+}
+
+static inline void fpregs_deactivate(struct fpu *fpu)
+{
+	__fpregs_deactivate(fpu);
+	__fpregs_deactivate_hw();
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ *  - switch_fpu_prepare() saves the old state and
+ *    sets the new state of the CR0.TS bit. This is
+ *    done within the context of the old process.
+ *
+ *  - switch_fpu_finish() restores the new state as
+ *    necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+static inline fpu_switch_t
+switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
+{
+	fpu_switch_t fpu;
+
+	/*
+	 * 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 = new_fpu->fpstate_active &&
+		      (use_eager_fpu() || new_fpu->counter > 5);
+
+	if (old_fpu->fpregs_active) {
+		if (!copy_fpregs_to_fpstate(old_fpu))
+			old_fpu->last_cpu = -1;
+		else
+			old_fpu->last_cpu = cpu;
+
+		/* But leave fpu_fpregs_owner_ctx! */
+		old_fpu->fpregs_active = 0;
+
+		/* Don't change CR0.TS if we just switch! */
+		if (fpu.preload) {
+			new_fpu->counter++;
+			__fpregs_activate(new_fpu);
+			prefetch(&new_fpu->state);
+		} else {
+			__fpregs_deactivate_hw();
+		}
+	} else {
+		old_fpu->counter = 0;
+		old_fpu->last_cpu = -1;
+		if (fpu.preload) {
+			new_fpu->counter++;
+			if (fpu_want_lazy_restore(new_fpu, cpu))
+				fpu.preload = 0;
+			else
+				prefetch(&new_fpu->state);
+			fpregs_activate(new_fpu);
+		}
+	}
+	return fpu;
+}
+
+/*
+ * Misc helper functions:
+ */
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch)
+{
+	if (fpu_switch.preload)
+		copy_kernel_to_fpregs(&new_fpu->state);
+}
+
+/*
+ * Needs to be preemption-safe.
+ *
+ * NOTE! user_fpu_begin() must be used only immediately before restoring
+ * the save state. It does not do any saving/restoring on its own. In
+ * lazy FPU mode, it is just an optimization to avoid a #NM exception,
+ * the task can lose the FPU right after preempt_enable().
+ */
+static inline void user_fpu_begin(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	preempt_disable();
+	if (!fpregs_active())
+		fpregs_activate(fpu);
+	preempt_enable();
+}
+
+/*
+ * MXCSR and XCR definitions:
+ */
+
+extern unsigned int mxcsr_feature_mask;
+
+#define XCR_XFEATURE_ENABLED_MASK	0x00000000
+
+static inline u64 xgetbv(u32 index)
+{
+	u32 eax, edx;
+
+	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
+		     : "=a" (eax), "=d" (edx)
+		     : "c" (index));
+	return eax + ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+	u32 eax = value;
+	u32 edx = value >> 32;
+
+	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
+		     : : "a" (eax), "d" (edx), "c" (index));
+}
+
+#endif /* _ASM_X86_FPU_INTERNAL_H */

arch/x86/include/asm/fpu/regset.h

@@ -0,0 +1,21 @@
+/*
+ * FPU regset handling methods:
+ */
+#ifndef _ASM_X86_FPU_REGSET_H
+#define _ASM_X86_FPU_REGSET_H
+
+#include <linux/regset.h>
+
+extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_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 == regset_fpregs_active. Please refer to the comment
+ * at the definition of regset_fpregs_active.
+ */
+#define xstateregs_active	regset_fpregs_active
+
+#endif /* _ASM_X86_FPU_REGSET_H */

arch/x86/include/asm/fpu/signal.h

@@ -0,0 +1,33 @@
+/*
+ * x86 FPU signal frame handling methods:
+ */
+#ifndef _ASM_X86_FPU_SIGNAL_H
+#define _ASM_X86_FPU_SIGNAL_H
+
+#ifdef CONFIG_X86_64
+# include <asm/sigcontext32.h>
+# include <asm/user32.h>
+struct ksignal;
+int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
+			compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct ksignal *ksig,
+		     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 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);
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+		     unsigned long *buf_fx, unsigned long *size);
+
+extern void fpu__init_prepare_fx_sw_frame(void);
+
+#endif /* _ASM_X86_FPU_SIGNAL_H */

arch/x86/include/asm/fpu/types.h

@@ -0,0 +1,293 @@
+/*
+ * FPU data structures:
+ */
+#ifndef _ASM_X86_FPU_H
+#define _ASM_X86_FPU_H
+
+/*
+ * The legacy x87 FPU state format, as saved by FSAVE and
+ * restored by the FRSTOR instructions:
+ */
+struct fregs_state {
+	u32			cwd;	/* FPU Control Word		*/
+	u32			swd;	/* FPU Status Word		*/
+	u32			twd;	/* FPU Tag Word			*/
+	u32			fip;	/* FPU IP Offset		*/
+	u32			fcs;	/* FPU IP Selector		*/
+	u32			foo;	/* FPU Operand Pointer Offset	*/
+	u32			fos;	/* FPU Operand Pointer Selector	*/
+
+	/* 8*10 bytes for each FP-reg = 80 bytes:			*/
+	u32			st_space[20];
+
+	/* Software status information [not touched by FSAVE]:		*/
+	u32			status;
+};
+
+/*
+ * The legacy fx SSE/MMX FPU state format, as saved by FXSAVE and
+ * restored by the FXRSTOR instructions. It's similar to the FSAVE
+ * format, but differs in some areas, plus has extensions at
+ * the end for the XMM registers.
+ */
+struct fxregs_state {
+	u16			cwd; /* Control Word			*/
+	u16			swd; /* Status Word			*/
+	u16			twd; /* Tag Word			*/
+	u16			fop; /* Last Instruction Opcode		*/
+	union {
+		struct {
+			u64	rip; /* Instruction Pointer		*/
+			u64	rdp; /* Data Pointer			*/
+		};
+		struct {
+			u32	fip; /* FPU IP Offset			*/
+			u32	fcs; /* FPU IP Selector			*/
+			u32	foo; /* FPU Operand Offset		*/
+			u32	fos; /* FPU Operand Selector		*/
+		};
+	};
+	u32			mxcsr;		/* MXCSR Register State */
+	u32			mxcsr_mask;	/* MXCSR Mask		*/
+
+	/* 8*16 bytes for each FP-reg = 128 bytes:			*/
+	u32			st_space[32];
+
+	/* 16*16 bytes for each XMM-reg = 256 bytes:			*/
+	u32			xmm_space[64];
+
+	u32			padding[12];
+
+	union {
+		u32		padding1[12];
+		u32		sw_reserved[12];
+	};
+
+} __attribute__((aligned(16)));
+
+/* Default value for fxregs_state.mxcsr: */
+#define MXCSR_DEFAULT		0x1f80
+
+/*
+ * Software based FPU emulation state. This is arbitrary really,
+ * it matches the x87 format to make it easier to understand:
+ */
+struct swregs_state {
+	u32			cwd;
+	u32			swd;
+	u32			twd;
+	u32			fip;
+	u32			fcs;
+	u32			foo;
+	u32			fos;
+	/* 8*10 bytes for each FP-reg = 80 bytes: */
+	u32			st_space[20];
+	u8			ftop;
+	u8			changed;
+	u8			lookahead;
+	u8			no_update;
+	u8			rm;
+	u8			alimit;
+	struct math_emu_info	*info;
+	u32			entry_eip;
+};
+
+/*
+ * List of XSAVE features Linux knows about:
+ */
+enum xfeature_bit {
+	XSTATE_BIT_FP,
+	XSTATE_BIT_SSE,
+	XSTATE_BIT_YMM,
+	XSTATE_BIT_BNDREGS,
+	XSTATE_BIT_BNDCSR,
+	XSTATE_BIT_OPMASK,
+	XSTATE_BIT_ZMM_Hi256,
+	XSTATE_BIT_Hi16_ZMM,
+
+	XFEATURES_NR_MAX,
+};
+
+#define XSTATE_FP		(1 << XSTATE_BIT_FP)
+#define XSTATE_SSE		(1 << XSTATE_BIT_SSE)
+#define XSTATE_YMM		(1 << XSTATE_BIT_YMM)
+#define XSTATE_BNDREGS		(1 << XSTATE_BIT_BNDREGS)
+#define XSTATE_BNDCSR		(1 << XSTATE_BIT_BNDCSR)
+#define XSTATE_OPMASK		(1 << XSTATE_BIT_OPMASK)
+#define XSTATE_ZMM_Hi256	(1 << XSTATE_BIT_ZMM_Hi256)
+#define XSTATE_Hi16_ZMM		(1 << XSTATE_BIT_Hi16_ZMM)
+
+#define XSTATE_FPSSE		(XSTATE_FP | XSTATE_SSE)
+#define XSTATE_AVX512		(XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+
+/*
+ * There are 16x 256-bit AVX registers named YMM0-YMM15.
+ * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15)
+ * and are stored in 'struct fxregs_state::xmm_space[]'.
+ *
+ * The high 128 bits are stored here:
+ *    16x 128 bits == 256 bytes.
+ */
+struct ymmh_struct {
+	u8				ymmh_space[256];
+};
+
+/* We don't support LWP yet: */
+struct lwp_struct {
+	u8				reserved[128];
+};
+
+/* Intel MPX support: */
+struct bndreg {
+	u64				lower_bound;
+	u64				upper_bound;
+} __packed;
+
+struct bndcsr {
+	u64				bndcfgu;
+	u64				bndstatus;
+} __packed;
+
+struct mpx_struct {
+	struct bndreg			bndreg[4];
+	struct bndcsr			bndcsr;
+};
+
+struct xstate_header {
+	u64				xfeatures;
+	u64				xcomp_bv;
+	u64				reserved[6];
+} __attribute__((packed));
+
+/* New processor state extensions should be added here: */
+#define XSTATE_RESERVE			(sizeof(struct ymmh_struct) + \
+					 sizeof(struct lwp_struct)  + \
+					 sizeof(struct mpx_struct)  )
+/*
+ * This is our most modern FPU state format, as saved by the XSAVE
+ * and restored by the XRSTOR instructions.
+ *
+ * It consists of a legacy fxregs portion, an xstate header and
+ * subsequent fixed size areas as defined by the xstate header.
+ * Not all CPUs support all the extensions.
+ */
+struct xregs_state {
+	struct fxregs_state		i387;
+	struct xstate_header		header;
+	u8				__reserved[XSTATE_RESERVE];
+} __attribute__ ((packed, aligned (64)));
+
+/*
+ * This is a union of all the possible FPU state formats
+ * put together, so that we can pick the right one runtime.
+ *
+ * The size of the structure is determined by the largest
+ * member - which is the xsave area:
+ */
+union fpregs_state {
+	struct fregs_state		fsave;
+	struct fxregs_state		fxsave;
+	struct swregs_state		soft;
+	struct xregs_state		xsave;
+};
+
+/*
+ * Highest level per task FPU state data structure that
+ * contains the FPU register state plus various FPU
+ * state fields:
+ */
+struct fpu {
+	/*
+	 * @state:
+	 *
+	 * In-memory copy of all FPU registers that we save/restore
+	 * over context switches. If the task is using the FPU then
+	 * the registers in the FPU are more recent than this state
+	 * copy. If the task context-switches away then they get
+	 * saved here and represent the FPU state.
+	 *
+	 * After context switches there may be a (short) time period
+	 * during which the in-FPU hardware registers are unchanged
+	 * and still perfectly match this state, if the tasks
+	 * scheduled afterwards are not using the FPU.
+	 *
+	 * This is the 'lazy restore' window of optimization, which
+	 * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
+	 *
+	 * We detect whether a subsequent task uses the FPU via setting
+	 * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
+	 *
+	 * During this window, if the task gets scheduled again, we
+	 * might be able to skip having to do a restore from this
+	 * memory buffer to the hardware registers - at the cost of
+	 * incurring the overhead of #NM fault traps.
+	 *
+	 * Note that on modern CPUs that support the XSAVEOPT (or other
+	 * optimized XSAVE instructions), we don't use #NM traps anymore,
+	 * as the hardware can track whether FPU registers need saving
+	 * or not. On such CPUs we activate the non-lazy ('eagerfpu')
+	 * logic, which unconditionally saves/restores all FPU state
+	 * across context switches. (if FPU state exists.)
+	 */
+	union fpregs_state		state;
+
+	/*
+	 * @last_cpu:
+	 *
+	 * Records the last CPU on which this context was loaded into
+	 * FPU registers. (In the lazy-restore case we might be
+	 * able to reuse FPU registers across multiple context switches
+	 * this way, if no intermediate task used the FPU.)
+	 *
+	 * A value of -1 is used to indicate that the FPU state in context
+	 * memory is newer than the FPU state in registers, and that the
+	 * FPU state should be reloaded next time the task is run.
+	 */
+	unsigned int			last_cpu;
+
+	/*
+	 * @fpstate_active:
+	 *
+	 * This flag indicates whether this context is active: if the task
+	 * is not running then we can restore from this context, if the task
+	 * is running then we should save into this context.
+	 */
+	unsigned char			fpstate_active;
+
+	/*
+	 * @fpregs_active:
+	 *
+	 * This flag determines whether a given context is actively
+	 * loaded into the FPU's registers and that those registers
+	 * represent the task's current FPU state.
+	 *
+	 * Note the interaction with fpstate_active:
+	 *
+	 *   # task does not use the FPU:
+	 *   fpstate_active == 0
+	 *
+	 *   # task uses the FPU and regs are active:
+	 *   fpstate_active == 1 && fpregs_active == 1
+	 *
+	 *   # the regs are inactive but still match fpstate:
+	 *   fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu
+	 *
+	 * The third state is what we use for the lazy restore optimization
+	 * on lazy-switching CPUs.
+	 */
+	unsigned char			fpregs_active;
+
+	/*
+	 * @counter:
+	 *
+	 * This counter contains the number of consecutive context switches
+	 * during which the FPU stays used. If this is over a threshold, the
+	 * lazy FPU restore logic becomes eager, to save the trap overhead.
+	 * This is an unsigned char so that after 256 iterations the counter
+	 * wraps and the context switch behavior turns lazy again; this is to
+	 * deal with bursty apps that only use the FPU for a short time:
+	 */
+	unsigned char			counter;
+};
+
+#endif /* _ASM_X86_FPU_H */

arch/x86/include/asm/fpu/xstate.h

@@ -0,0 +1,46 @@
+#ifndef __ASM_X86_XSAVE_H
+#define __ASM_X86_XSAVE_H
+
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <linux/uaccess.h>
+
+/* Bit 63 of XCR0 is reserved for future expansion */
+#define XSTATE_EXTEND_MASK	(~(XSTATE_FPSSE | (1ULL << 63)))
+
+#define XSTATE_CPUID		0x0000000d
+
+#define FXSAVE_SIZE	512
+
+#define XSAVE_HDR_SIZE	    64
+#define XSAVE_HDR_OFFSET    FXSAVE_SIZE
+
+#define XSAVE_YMM_SIZE	    256
+#define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
+
+/* Supported features which support lazy state saving */
+#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM		      \
+			| XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+
+/* Supported features which require eager state saving */
+#define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
+
+/* All currently supported features */
+#define XCNTXT_MASK	(XSTATE_LAZY | XSTATE_EAGER)
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX	"0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+extern unsigned int xstate_size;
+extern u64 xfeatures_mask;
+extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
+
+extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
+
+void *get_xsave_addr(struct xregs_state *xsave, int xstate);
+const void *get_xsave_field_ptr(int xstate_field);
+
+#endif

arch/x86/include/asm/i387.h

@@ -1,108 +0,0 @@
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _ASM_X86_I387_H
-#define _ASM_X86_I387_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/sched.h>
-#include <linux/hardirq.h>
-
-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);
-
-/*
- * 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)
-{
-	preempt_disable();
-	WARN_ON_ONCE(!irq_fpu_usable());
-	__kernel_fpu_begin();
-}
-
-static inline void kernel_fpu_end(void)
-{
-	__kernel_fpu_end();
-	preempt_enable();
-}
-
-/* Must be called with preempt disabled */
-extern void kernel_fpu_disable(void);
-extern void kernel_fpu_enable(void);
-
-/*
- * Some instructions like VIA's padlock instructions generate a spurious
- * DNA fault but don't modify SSE registers. And these instructions
- * get used from interrupt context as well. To prevent these kernel instructions
- * in interrupt context interacting wrongly with other user/kernel fpu usage, we
- * should use them only in the context of irq_ts_save/restore()
- */
-static inline int irq_ts_save(void)
-{
-	/*
-	 * If in process context and not atomic, we can take a spurious DNA fault.
-	 * Otherwise, doing clts() in process context requires disabling preemption
-	 * or some heavy lifting like kernel_fpu_begin()
-	 */
-	if (!in_atomic())
-		return 0;
-
-	if (read_cr0() & X86_CR0_TS) {
-		clts();
-		return 1;
-	}
-
-	return 0;
-}
-
-static inline void irq_ts_restore(int TS_state)
-{
-	if (TS_state)
-		stts();
-}
-
-/*
- * The question "does this thread have fpu access?"
- * is slightly racy, since preemption could come in
- * and revoke it immediately after the test.
- *
- * However, even in that very unlikely scenario,
- * we can just assume we have FPU access - typically
- * to save the FP state - we'll just take a #NM
- * fault and get the FPU access back.
- */
-static inline int user_has_fpu(void)
-{
-	return current->thread.fpu.has_fpu;
-}
-
-extern void unlazy_fpu(struct task_struct *tsk);
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_X86_I387_H */

arch/x86/include/asm/kvm_host.h

@@ -1002,8 +1002,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
-int fx_init(struct kvm_vcpu *vcpu);
-
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes);
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);

arch/x86/include/asm/mmu_context.h

@@ -142,6 +142,19 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
 	paravirt_arch_exit_mmap(mm);
 }
 
+#ifdef CONFIG_X86_64
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+	return	!config_enabled(CONFIG_IA32_EMULATION) ||
+		!(mm->context.ia32_compat == TIF_IA32);
+}
+#else
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+	return false;
+}
+#endif
+
 static inline void arch_bprm_mm_init(struct mm_struct *mm,
 		struct vm_area_struct *vma)
 {

arch/x86/include/asm/mpx.h

@@ -13,55 +13,50 @@
 #define MPX_BNDCFG_ENABLE_FLAG	0x1
 #define MPX_BD_ENTRY_VALID_FLAG	0x1
 
-#ifdef CONFIG_X86_64
-
-/* upper 28 bits [47:20] of the virtual address in 64-bit used to
- * index into bounds directory (BD).
- */
-#define MPX_BD_ENTRY_OFFSET	28
-#define MPX_BD_ENTRY_SHIFT	3
-/* bits [19:3] of the virtual address in 64-bit used to index into
- * bounds table (BT).
+/*
+ * The upper 28 bits [47:20] of the virtual address in 64-bit
+ * are used to index into bounds directory (BD).
+ *
+ * The directory is 2G (2^31) in size, and with 8-byte entries
+ * it has 2^28 entries.
  */
-#define MPX_BT_ENTRY_OFFSET	17
-#define MPX_BT_ENTRY_SHIFT	5
-#define MPX_IGN_BITS		3
-#define MPX_BD_ENTRY_TAIL	3
+#define MPX_BD_SIZE_BYTES_64	(1UL<<31)
+#define MPX_BD_ENTRY_BYTES_64	8
+#define MPX_BD_NR_ENTRIES_64	(MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64)
 
-#else
-
-#define MPX_BD_ENTRY_OFFSET	20
-#define MPX_BD_ENTRY_SHIFT	2
-#define MPX_BT_ENTRY_OFFSET	10
-#define MPX_BT_ENTRY_SHIFT	4
-#define MPX_IGN_BITS		2
-#define MPX_BD_ENTRY_TAIL	2
+/*
+ * The 32-bit directory is 4MB (2^22) in size, and with 4-byte
+ * entries it has 2^20 entries.
+ */
+#define MPX_BD_SIZE_BYTES_32	(1UL<<22)
+#define MPX_BD_ENTRY_BYTES_32	4
+#define MPX_BD_NR_ENTRIES_32	(MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32)
 
-#endif
+/*
+ * A 64-bit table is 4MB total in size, and an entry is
+ * 4 64-bit pointers in size.
+ */
+#define MPX_BT_SIZE_BYTES_64	(1UL<<22)
+#define MPX_BT_ENTRY_BYTES_64	32
+#define MPX_BT_NR_ENTRIES_64	(MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64)
 
-#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT))
-#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT))
+/*
+ * A 32-bit table is 16kB total in size, and an entry is
+ * 4 32-bit pointers in size.
+ */
+#define MPX_BT_SIZE_BYTES_32	(1UL<<14)
+#define MPX_BT_ENTRY_BYTES_32	16
+#define MPX_BT_NR_ENTRIES_32	(MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32)
 
 #define MPX_BNDSTA_TAIL		2
 #define MPX_BNDCFG_TAIL		12
 #define MPX_BNDSTA_ADDR_MASK	(~((1UL<<MPX_BNDSTA_TAIL)-1))
-#define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
-#define MPX_BT_ADDR_MASK	(~((1UL<<MPX_BD_ENTRY_TAIL)-1))
-
 #define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
 #define MPX_BNDSTA_ERROR_CODE	0x3
 
-#define MPX_BD_ENTRY_MASK	((1<<MPX_BD_ENTRY_OFFSET)-1)
-#define MPX_BT_ENTRY_MASK	((1<<MPX_BT_ENTRY_OFFSET)-1)
-#define MPX_GET_BD_ENTRY_OFFSET(addr)	((((addr)>>(MPX_BT_ENTRY_OFFSET+ \
-		MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT)
-#define MPX_GET_BT_ENTRY_OFFSET(addr)	((((addr)>>MPX_IGN_BITS) & \
-		MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT)
-
 #ifdef CONFIG_X86_INTEL_MPX
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-				struct xsave_struct *xsave_buf);
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf);
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs);
+int mpx_handle_bd_fault(void);
 static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
 {
 	return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
@@ -77,12 +72,11 @@ static inline void mpx_mm_init(struct mm_struct *mm)
 void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long start, unsigned long end);
 #else
-static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-					      struct xsave_struct *xsave_buf)
+static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 {
 	return NULL;
 }
-static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+static inline int mpx_handle_bd_fault(void)
 {
 	return -EINVAL;
 }

arch/x86/include/asm/processor.h

@@ -21,6 +21,7 @@ struct mm_struct;
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
 #include <asm/special_insns.h>
+#include <asm/fpu/types.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -52,11 +53,16 @@ static inline void *current_text_addr(void)
 	return pc;
 }
 
+/*
+ * These alignment constraints are for performance in the vSMP case,
+ * but in the task_struct case we must also meet hardware imposed
+ * alignment requirements of the FPU state:
+ */
 #ifdef CONFIG_X86_VSMP
 # define ARCH_MIN_TASKALIGN		(1 << INTERNODE_CACHE_SHIFT)
 # define ARCH_MIN_MMSTRUCT_ALIGN	(1 << INTERNODE_CACHE_SHIFT)
 #else
-# define ARCH_MIN_TASKALIGN		16
+# define ARCH_MIN_TASKALIGN		__alignof__(union fpregs_state)
 # define ARCH_MIN_MMSTRUCT_ALIGN	0
 #endif
 
@@ -166,7 +172,6 @@ extern const struct seq_operations cpuinfo_op;
 #define cache_line_size()	(boot_cpu_data.x86_cache_alignment)
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
-extern void fpu_detect(struct cpuinfo_x86 *c);
 
 extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
@@ -313,128 +318,6 @@ struct orig_ist {
 	unsigned long		ist[7];
 };
 
-#define	MXCSR_DEFAULT		0x1f80
-
-struct i387_fsave_struct {
-	u32			cwd;	/* FPU Control Word		*/
-	u32			swd;	/* FPU Status Word		*/
-	u32			twd;	/* FPU Tag Word			*/
-	u32			fip;	/* FPU IP Offset		*/
-	u32			fcs;	/* FPU IP Selector		*/
-	u32			foo;	/* FPU Operand Pointer Offset	*/
-	u32			fos;	/* FPU Operand Pointer Selector	*/
-
-	/* 8*10 bytes for each FP-reg = 80 bytes:			*/
-	u32			st_space[20];
-
-	/* Software status information [not touched by FSAVE ]:		*/
-	u32			status;
-};
-
-struct i387_fxsave_struct {
-	u16			cwd; /* Control Word			*/
-	u16			swd; /* Status Word			*/
-	u16			twd; /* Tag Word			*/
-	u16			fop; /* Last Instruction Opcode		*/
-	union {
-		struct {
-			u64	rip; /* Instruction Pointer		*/
-			u64	rdp; /* Data Pointer			*/
-		};
-		struct {
-			u32	fip; /* FPU IP Offset			*/
-			u32	fcs; /* FPU IP Selector			*/
-			u32	foo; /* FPU Operand Offset		*/
-			u32	fos; /* FPU Operand Selector		*/
-		};
-	};
-	u32			mxcsr;		/* MXCSR Register State */
-	u32			mxcsr_mask;	/* MXCSR Mask		*/
-
-	/* 8*16 bytes for each FP-reg = 128 bytes:			*/
-	u32			st_space[32];
-
-	/* 16*16 bytes for each XMM-reg = 256 bytes:			*/
-	u32			xmm_space[64];
-
-	u32			padding[12];
-
-	union {
-		u32		padding1[12];
-		u32		sw_reserved[12];
-	};
-
-} __attribute__((aligned(16)));
-
-struct i387_soft_struct {
-	u32			cwd;
-	u32			swd;
-	u32			twd;
-	u32			fip;
-	u32			fcs;
-	u32			foo;
-	u32			fos;
-	/* 8*10 bytes for each FP-reg = 80 bytes: */
-	u32			st_space[20];
-	u8			ftop;
-	u8			changed;
-	u8			lookahead;
-	u8			no_update;
-	u8			rm;
-	u8			alimit;
-	struct math_emu_info	*info;
-	u32			entry_eip;
-};
-
-struct ymmh_struct {
-	/* 16 * 16 bytes for each YMMH-reg = 256 bytes */
-	u32 ymmh_space[64];
-};
-
-/* We don't support LWP yet: */
-struct lwp_struct {
-	u8 reserved[128];
-};
-
-struct bndreg {
-	u64 lower_bound;
-	u64 upper_bound;
-} __packed;
-
-struct bndcsr {
-	u64 bndcfgu;
-	u64 bndstatus;
-} __packed;
-
-struct xsave_hdr_struct {
-	u64 xstate_bv;
-	u64 xcomp_bv;
-	u64 reserved[6];
-} __attribute__((packed));
-
-struct xsave_struct {
-	struct i387_fxsave_struct i387;
-	struct xsave_hdr_struct xsave_hdr;
-	struct ymmh_struct ymmh;
-	struct lwp_struct lwp;
-	struct bndreg bndreg[4];
-	struct bndcsr bndcsr;
-	/* new processor state extensions will go here */
-} __attribute__ ((packed, aligned (64)));
-
-union thread_xstate {
-	struct i387_fsave_struct	fsave;
-	struct i387_fxsave_struct	fxsave;
-	struct i387_soft_struct		soft;
-	struct xsave_struct		xsave;
-};
-
-struct fpu {
-	unsigned int last_cpu;
-	unsigned int has_fpu;
-	union thread_xstate *state;
-};
-
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(struct orig_ist, orig_ist);
 
@@ -483,8 +366,6 @@ DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif	/* X86_64 */
 
 extern unsigned int xstate_size;
-extern void free_thread_xstate(struct task_struct *);
-extern struct kmem_cache *task_xstate_cachep;
 
 struct perf_event;
 
@@ -508,6 +389,10 @@ struct thread_struct {
 	unsigned long		fs;
 #endif
 	unsigned long		gs;
+
+	/* Floating point and extended processor state */
+	struct fpu		fpu;
+
 	/* Save middle states of ptrace breakpoints */
 	struct perf_event	*ptrace_bps[HBP_NUM];
 	/* Debug status used for traps, single steps, etc... */
@@ -518,8 +403,6 @@ struct thread_struct {
 	unsigned long		cr2;
 	unsigned long		trap_nr;
 	unsigned long		error_code;
-	/* floating point and extended processor state */
-	struct fpu		fpu;
 #ifdef CONFIG_X86_32
 	/* Virtual 86 mode info */
 	struct vm86_struct __user *vm86_info;
@@ -535,15 +418,6 @@ struct thread_struct {
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
-	/*
-	 * fpu_counter contains the number of consecutive context switches
-	 * that the FPU is used. If this is over a threshold, the lazy fpu
-	 * saving becomes unlazy to save the trap. This is an unsigned char
-	 * so that after 256 times the counter wraps and the behavior turns
-	 * lazy again; this to deal with bursty apps that only use FPU for
-	 * a short time
-	 */
-	unsigned char fpu_counter;
 };
 
 /*
@@ -928,18 +802,18 @@ extern int get_tsc_mode(unsigned long adr);
 extern int set_tsc_mode(unsigned int val);
 
 /* Register/unregister a process' MPX related resource */
-#define MPX_ENABLE_MANAGEMENT(tsk)	mpx_enable_management((tsk))
-#define MPX_DISABLE_MANAGEMENT(tsk)	mpx_disable_management((tsk))
+#define MPX_ENABLE_MANAGEMENT()	mpx_enable_management()
+#define MPX_DISABLE_MANAGEMENT()	mpx_disable_management()
 
 #ifdef CONFIG_X86_INTEL_MPX
-extern int mpx_enable_management(struct task_struct *tsk);
-extern int mpx_disable_management(struct task_struct *tsk);
+extern int mpx_enable_management(void);
+extern int mpx_disable_management(void);
 #else
-static inline int mpx_enable_management(struct task_struct *tsk)
+static inline int mpx_enable_management(void)
 {
 	return -EINVAL;
 }
-static inline int mpx_disable_management(struct task_struct *tsk)
+static inline int mpx_disable_management(void)
 {
 	return -EINVAL;
 }

arch/x86/include/asm/simd.h

@@ -1,5 +1,5 @@
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * may_use_simd - whether it is allowable at this time to issue SIMD

arch/x86/include/asm/stackprotector.h

@@ -39,7 +39,9 @@
 #include <asm/processor.h>
 #include <asm/percpu.h>
 #include <asm/desc.h>
+
 #include <linux/random.h>
+#include <linux/sched.h>
 
 /*
  * 24 byte read-only segment initializer for stack canary.  Linker

arch/x86/include/asm/suspend_32.h

@@ -7,7 +7,7 @@
 #define _ASM_X86_SUSPEND_32_H
 
 #include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /* image of the saved processor state */
 struct saved_context {

arch/x86/include/asm/suspend_64.h

@@ -7,7 +7,7 @@
 #define _ASM_X86_SUSPEND_64_H
 
 #include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * Image of the saved processor state, used by the low level ACPI suspend to

arch/x86/include/asm/trace/mpx.h

@@ -0,0 +1,132 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mpx
+
+#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MPX_H
+
+#include <linux/tracepoint.h>
+
+#ifdef CONFIG_X86_INTEL_MPX
+
+TRACE_EVENT(mpx_bounds_register_exception,
+
+	TP_PROTO(void *addr_referenced,
+		 const struct bndreg *bndreg),
+	TP_ARGS(addr_referenced, bndreg),
+
+	TP_STRUCT__entry(
+		__field(void *, addr_referenced)
+		__field(u64, lower_bound)
+		__field(u64, upper_bound)
+	),
+
+	TP_fast_assign(
+		__entry->addr_referenced = addr_referenced;
+		__entry->lower_bound = bndreg->lower_bound;
+		__entry->upper_bound = bndreg->upper_bound;
+	),
+	/*
+	 * Note that we are printing out the '~' of the upper
+	 * bounds register here.  It is actually stored in its
+	 * one's complement form so that its 'init' state
+	 * corresponds to all 0's.  But, that looks like
+	 * gibberish when printed out, so print out the 1's
+	 * complement instead of the actual value here.  Note
+	 * though that you still need to specify filters for the
+	 * actual value, not the displayed one.
+	 */
+	TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx",
+		__entry->addr_referenced,
+		__entry->lower_bound,
+		~__entry->upper_bound
+	)
+);
+
+TRACE_EVENT(bounds_exception_mpx,
+
+	TP_PROTO(const struct bndcsr *bndcsr),
+	TP_ARGS(bndcsr),
+
+	TP_STRUCT__entry(
+		__field(u64, bndcfgu)
+		__field(u64, bndstatus)
+	),
+
+	TP_fast_assign(
+		/* need to get rid of the 'const' on bndcsr */
+		__entry->bndcfgu   = (u64)bndcsr->bndcfgu;
+		__entry->bndstatus = (u64)bndcsr->bndstatus;
+	),
+
+	TP_printk("bndcfgu:0x%llx bndstatus:0x%llx",
+		__entry->bndcfgu,
+		__entry->bndstatus)
+);
+
+DECLARE_EVENT_CLASS(mpx_range_trace,
+
+	TP_PROTO(unsigned long start,
+		 unsigned long end),
+	TP_ARGS(start, end),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, start)
+		__field(unsigned long, end)
+	),
+
+	TP_fast_assign(
+		__entry->start = start;
+		__entry->end   = end;
+	),
+
+	TP_printk("[0x%p:0x%p]",
+		(void *)__entry->start,
+		(void *)__entry->end
+	)
+);
+
+DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end)
+);
+
+DEFINE_EVENT(mpx_range_trace, mpx_unmap_search,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end)
+);
+
+TRACE_EVENT(mpx_new_bounds_table,
+
+	TP_PROTO(unsigned long table_vaddr),
+	TP_ARGS(table_vaddr),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, table_vaddr)
+	),
+
+	TP_fast_assign(
+		__entry->table_vaddr = table_vaddr;
+	),
+
+	TP_printk("table vaddr:%p", (void *)__entry->table_vaddr)
+);
+
+#else
+
+/*
+ * This gets used outside of MPX-specific code, so we need a stub.
+ */
+static inline void trace_bounds_exception_mpx(const struct bndcsr *bndcsr)
+{
+}
+
+#endif /* CONFIG_X86_INTEL_MPX */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/trace/
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE mpx
+#endif /* _TRACE_MPX_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

arch/x86/include/asm/user.h

@@ -14,8 +14,8 @@ struct user_ymmh_regs {
 	__u32 ymmh_space[64];
 };
 
-struct user_xsave_hdr {
-	__u64 xstate_bv;
+struct user_xstate_header {
+	__u64 xfeatures;
 	__u64 reserved1[2];
 	__u64 reserved2[5];
 };
@@ -41,11 +41,11 @@ struct user_xsave_hdr {
  * particular process/thread.
  *
  * Also when the user modifies certain state FP/SSE/etc through the
- * ptrace interface, they must ensure that the xsave_hdr.xstate_bv
+ * ptrace interface, they must ensure that the header.xfeatures
  * bytes[512..519] of the memory layout are updated correspondingly.
  * i.e., for example when FP state is modified to a non-init state,
- * xsave_hdr.xstate_bv's bit 0 must be set to '1', when SSE is modified to
- * non-init state, xsave_hdr.xstate_bv's bit 1 must to be set to '1', etc.
+ * header.xfeatures's bit 0 must be set to '1', when SSE is modified to
+ * non-init state, header.xfeatures's bit 1 must to be set to '1', etc.
  */
 #define USER_XSTATE_FX_SW_WORDS 6
 #define USER_XSTATE_XCR0_WORD	0
@@ -55,7 +55,7 @@ struct user_xstateregs {
 		__u64 fpx_space[58];
 		__u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS];
 	} i387;
-	struct user_xsave_hdr xsave_hdr;
+	struct user_xstate_header header;
 	struct user_ymmh_regs ymmh;
 	/* further processor state extensions go here */
 };

arch/x86/include/asm/xcr.h

@@ -1,49 +0,0 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- *   Copyright 2008 rPath, Inc. - All Rights Reserved
- *
- *   This file is part of the Linux kernel, and is made available under
- *   the terms of the GNU General Public License version 2 or (at your
- *   option) any later version; incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * asm-x86/xcr.h
- *
- * Definitions for the eXtended Control Register instructions
- */
-
-#ifndef _ASM_X86_XCR_H
-#define _ASM_X86_XCR_H
-
-#define XCR_XFEATURE_ENABLED_MASK	0x00000000
-
-#ifdef __KERNEL__
-# ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-
-static inline u64 xgetbv(u32 index)
-{
-	u32 eax, edx;
-
-	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
-		     : "=a" (eax), "=d" (edx)
-		     : "c" (index));
-	return eax + ((u64)edx << 32);
-}
-
-static inline void xsetbv(u32 index, u64 value)
-{
-	u32 eax = value;
-	u32 edx = value >> 32;
-
-	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
-		     : : "a" (eax), "d" (edx), "c" (index));
-}
-
-# endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_XCR_H */

arch/x86/include/asm/xor.h

@@ -36,7 +36,7 @@
  * no advantages to be gotten from x86-64 here anyways.
  */
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #ifdef CONFIG_X86_32
 /* reduce register pressure */

arch/x86/include/asm/xor_32.h

@@ -26,7 +26,7 @@
 #define XO3(x, y)	"       pxor   8*("#x")(%4), %%mm"#y"   ;\n"
 #define XO4(x, y)	"       pxor   8*("#x")(%5), %%mm"#y"   ;\n"
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 static void
 xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)

arch/x86/include/asm/xor_avx.h

@@ -18,7 +18,7 @@
 #ifdef CONFIG_AS_AVX
 
 #include <linux/compiler.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #define BLOCK4(i) \
 		BLOCK(32 * i, 0) \

arch/x86/include/asm/xsave.h

@@ -1,257 +0,0 @@
-#ifndef __ASM_X86_XSAVE_H
-#define __ASM_X86_XSAVE_H
-
-#include <linux/types.h>
-#include <asm/processor.h>
-
-#define XSTATE_CPUID		0x0000000d
-
-#define XSTATE_FP		0x1
-#define XSTATE_SSE		0x2
-#define XSTATE_YMM		0x4
-#define XSTATE_BNDREGS		0x8
-#define XSTATE_BNDCSR		0x10
-#define XSTATE_OPMASK		0x20
-#define XSTATE_ZMM_Hi256	0x40
-#define XSTATE_Hi16_ZMM		0x80
-
-#define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
-#define XSTATE_AVX512	(XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
-/* Bit 63 of XCR0 is reserved for future expansion */
-#define XSTATE_EXTEND_MASK	(~(XSTATE_FPSSE | (1ULL << 63)))
-
-#define FXSAVE_SIZE	512
-
-#define XSAVE_HDR_SIZE	    64
-#define XSAVE_HDR_OFFSET    FXSAVE_SIZE
-
-#define XSAVE_YMM_SIZE	    256
-#define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
-
-/* Supported features which support lazy state saving */
-#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM		      \
-			| XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
-
-/* Supported features which require eager state saving */
-#define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
-
-/* All currently supported features */
-#define XCNTXT_MASK	(XSTATE_LAZY | XSTATE_EAGER)
-
-#ifdef CONFIG_X86_64
-#define REX_PREFIX	"0x48, "
-#else
-#define REX_PREFIX
-#endif
-
-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);
-
-/* These macros all use (%edi)/(%rdi) as the single memory argument. */
-#define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
-#define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
-#define XSAVES		".byte " REX_PREFIX "0x0f,0xc7,0x2f"
-#define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
-#define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
-
-#define xstate_fault	".section .fixup,\"ax\"\n"	\
-			"3:  movl $-1,%[err]\n"		\
-			"    jmp  2b\n"			\
-			".previous\n"			\
-			_ASM_EXTABLE(1b, 3b)		\
-			: [err] "=r" (err)
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err = 0;
-
-	WARN_ON(system_state != SYSTEM_BOOTING);
-
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		asm volatile("1:"XSAVES"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	else
-		asm volatile("1:"XSAVE"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	return err;
-}
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err = 0;
-
-	WARN_ON(system_state != SYSTEM_BOOTING);
-
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		asm volatile("1:"XRSTORS"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	else
-		asm volatile("1:"XRSTOR"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	return err;
-}
-
-/*
- * Save processor xstate to xsave area.
- */
-static inline int xsave_state(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err = 0;
-
-	/*
-	 * If xsaves is enabled, xsaves replaces xsaveopt because
-	 * it supports compact format and supervisor states in addition to
-	 * modified optimization in xsaveopt.
-	 *
-	 * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
-	 * because xsaveopt supports modified optimization which is not
-	 * supported by xsave.
-	 *
-	 * If none of xsaves and xsaveopt is enabled, use xsave.
-	 */
-	alternative_input_2(
-		"1:"XSAVE,
-		XSAVEOPT,
-		X86_FEATURE_XSAVEOPT,
-		XSAVES,
-		X86_FEATURE_XSAVES,
-		[fx] "D" (fx), "a" (lmask), "d" (hmask) :
-		"memory");
-	asm volatile("2:\n\t"
-		     xstate_fault
-		     : "0" (0)
-		     : "memory");
-
-	return err;
-}
-
-/*
- * Restore processor xstate from xsave area.
- */
-static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
-{
-	int err = 0;
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-
-	/*
-	 * Use xrstors to restore context if it is enabled. xrstors supports
-	 * compacted format of xsave area which is not supported by xrstor.
-	 */
-	alternative_input(
-		"1: " XRSTOR,
-		XRSTORS,
-		X86_FEATURE_XSAVES,
-		"D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-		: "memory");
-
-	asm volatile("2:\n"
-		     xstate_fault
-		     : "0" (0)
-		     : "memory");
-
-	return err;
-}
-
-/*
- * Save xstate context for old process during context switch.
- */
-static inline void fpu_xsave(struct fpu *fpu)
-{
-	xsave_state(&fpu->state->xsave, -1);
-}
-
-/*
- * Restore xstate context for new process during context switch.
- */
-static inline int fpu_xrstor_checking(struct xsave_struct *fx)
-{
-	return xrstor_state(fx, -1);
-}
-
-/*
- * Save xstate to user space xsave area.
- *
- * We don't use modified optimization because xrstor/xrstors might track
- * a different application.
- *
- * We don't use compacted format xsave area for
- * backward compatibility for old applications which don't understand
- * compacted format of xsave area.
- */
-static inline int xsave_user(struct xsave_struct __user *buf)
-{
-	int err;
-
-	/*
-	 * Clear the xsave header first, so that reserved fields are
-	 * initialized to zero.
-	 */
-	err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr));
-	if (unlikely(err))
-		return -EFAULT;
-
-	__asm__ __volatile__(ASM_STAC "\n"
-			     "1:"XSAVE"\n"
-			     "2: " ASM_CLAC "\n"
-			     xstate_fault
-			     : "D" (buf), "a" (-1), "d" (-1), "0" (0)
-			     : "memory");
-	return err;
-}
-
-/*
- * Restore xstate from user space xsave area.
- */
-static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
-{
-	int err = 0;
-	struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-
-	__asm__ __volatile__(ASM_STAC "\n"
-			     "1:"XRSTOR"\n"
-			     "2: " ASM_CLAC "\n"
-			     xstate_fault
-			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
-			     : "memory");	/* memory required? */
-	return err;
-}
-
-void *get_xsave_addr(struct xsave_struct *xsave, int xstate);
-void setup_xstate_comp(void);
-
-#endif

arch/x86/include/uapi/asm/sigcontext.h

@@ -25,7 +25,7 @@ struct _fpx_sw_bytes {
 	__u32 extended_size;	/* total size of the layout referred by
 				 * fpstate pointer in the sigcontext.
 				 */
-	__u64 xstate_bv;
+	__u64 xfeatures;
 				/* feature bit mask (including fp/sse/extended
 				 * state) that is present in the memory
 				 * layout.
@@ -209,8 +209,8 @@ struct sigcontext {
 
 #endif /* !__i386__ */
 
-struct _xsave_hdr {
-	__u64 xstate_bv;
+struct _header {
+	__u64 xfeatures;
 	__u64 reserved1[2];
 	__u64 reserved2[5];
 };
@@ -228,7 +228,7 @@ struct _ymmh_state {
  */
 struct _xstate {
 	struct _fpstate fpstate;
-	struct _xsave_hdr xstate_hdr;
+	struct _header xstate_hdr;
 	struct _ymmh_state ymmh;
 	/* new processor state extensions go here */
 };

arch/x86/kernel/Makefile

@@ -44,7 +44,7 @@ obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 
 obj-y				+= process.o
-obj-y				+= i387.o xsave.o
+obj-y				+= fpu/
 obj-y				+= ptrace.o
 obj-$(CONFIG_X86_32)		+= tls.o
 obj-$(CONFIG_IA32_EMULATION)	+= tls.o

arch/x86/kernel/alternative.c

@@ -21,6 +21,10 @@
 #include <asm/io.h>
 #include <asm/fixmap.h>
 
+int __read_mostly alternatives_patched;
+
+EXPORT_SYMBOL_GPL(alternatives_patched);
+
 #define MAX_PATCH_LEN (255-1)
 
 static int __initdata_or_module debug_alternative;
@@ -627,6 +631,7 @@ void __init alternative_instructions(void)
 	apply_paravirt(__parainstructions, __parainstructions_end);
 
 	restart_nmi();
+	alternatives_patched = 1;
 }
 
 /**

arch/x86/kernel/cpu/bugs.c

@@ -12,57 +12,11 @@
 #include <asm/bugs.h>
 #include <asm/processor.h>
 #include <asm/processor-flags.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
 #include <asm/msr.h>
 #include <asm/paravirt.h>
 #include <asm/alternative.h>
 
-static double __initdata x = 4195835.0;
-static double __initdata y = 3145727.0;
-
-/*
- * This used to check for exceptions..
- * However, it turns out that to support that,
- * the XMM trap handlers basically had to
- * be buggy. So let's have a correct XMM trap
- * handler, and forget about printing out
- * some status at boot.
- *
- * We should really only care about bugs here
- * anyway. Not features.
- */
-static void __init check_fpu(void)
-{
-	s32 fdiv_bug;
-
-	kernel_fpu_begin();
-
-	/*
-	 * trap_init() enabled FXSR and company _before_ testing for FP
-	 * problems here.
-	 *
-	 * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
-	 */
-	__asm__("fninit\n\t"
-		"fldl %1\n\t"
-		"fdivl %2\n\t"
-		"fmull %2\n\t"
-		"fldl %1\n\t"
-		"fsubp %%st,%%st(1)\n\t"
-		"fistpl %0\n\t"
-		"fwait\n\t"
-		"fninit"
-		: "=m" (*&fdiv_bug)
-		: "m" (*&x), "m" (*&y));
-
-	kernel_fpu_end();
-
-	if (fdiv_bug) {
-		set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
-		pr_warn("Hmm, FPU with FDIV bug\n");
-	}
-}
-
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -85,10 +39,5 @@ void __init check_bugs(void)
 		'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.
-	 */
-	if (cpu_has_fpu)
-		check_fpu();
+	fpu__init_check_bugs();
 }

arch/x86/kernel/cpu/common.c

@@ -32,8 +32,7 @@
 #include <asm/setup.h>
 #include <asm/apic.h>
 #include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/mtrr.h>
 #include <linux/numa.h>
 #include <asm/asm.h>
@@ -146,32 +145,21 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
-static int __init x86_xsave_setup(char *s)
+static int __init x86_mpx_setup(char *s)
 {
+	/* require an exact match without trailing characters */
 	if (strlen(s))
 		return 0;
-	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-	setup_clear_cpu_cap(X86_FEATURE_AVX);
-	setup_clear_cpu_cap(X86_FEATURE_AVX2);
-	return 1;
-}
-__setup("noxsave", x86_xsave_setup);
 
-static int __init x86_xsaveopt_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-	return 1;
-}
-__setup("noxsaveopt", x86_xsaveopt_setup);
+	/* do not emit a message if the feature is not present */
+	if (!boot_cpu_has(X86_FEATURE_MPX))
+		return 1;
 
-static int __init x86_xsaves_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+	setup_clear_cpu_cap(X86_FEATURE_MPX);
+	pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n");
 	return 1;
 }
-__setup("noxsaves", x86_xsaves_setup);
+__setup("nompx", x86_mpx_setup);
 
 #ifdef CONFIG_X86_32
 static int cachesize_override = -1;
@@ -184,14 +172,6 @@ static int __init cachesize_setup(char *str)
 }
 __setup("cachesize=", cachesize_setup);
 
-static int __init x86_fxsr_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FXSR);
-	setup_clear_cpu_cap(X86_FEATURE_XMM);
-	return 1;
-}
-__setup("nofxsr", x86_fxsr_setup);
-
 static int __init x86_sep_setup(char *s)
 {
 	setup_clear_cpu_cap(X86_FEATURE_SEP);
@@ -762,7 +742,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	cpu_detect(c);
 	get_cpu_vendor(c);
 	get_cpu_cap(c);
-	fpu_detect(c);
+	fpu__init_system(c);
 
 	if (this_cpu->c_early_init)
 		this_cpu->c_early_init(c);
@@ -1186,8 +1166,6 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
-
 /*
  * Special IST stacks which the CPU switches to when it calls
  * an IST-marked descriptor entry. Up to 7 stacks (hardware
@@ -1278,7 +1256,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
 
 /*
  * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
@@ -1442,7 +1419,7 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	fpu_init();
+	fpu__init_cpu();
 
 	if (is_uv_system())
 		uv_cpu_init();
@@ -1498,7 +1475,7 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	fpu_init();
+	fpu__init_cpu();
 }
 #endif
 

arch/x86/kernel/fpu/Makefile

@@ -0,0 +1,5 @@
+#
+# Build rules for the FPU support code:
+#
+
+obj-y				+= init.o bugs.o core.o regset.o signal.o xstate.o

arch/x86/kernel/fpu/bugs.c

@@ -0,0 +1,71 @@
+/*
+ * x86 FPU bug checks:
+ */
+#include <asm/fpu/internal.h>
+
+/*
+ * Boot time CPU/FPU FDIV bug detection code:
+ */
+
+static double __initdata x = 4195835.0;
+static double __initdata y = 3145727.0;
+
+/*
+ * This used to check for exceptions..
+ * However, it turns out that to support that,
+ * the XMM trap handlers basically had to
+ * be buggy. So let's have a correct XMM trap
+ * handler, and forget about printing out
+ * some status at boot.
+ *
+ * We should really only care about bugs here
+ * anyway. Not features.
+ */
+static void __init check_fpu(void)
+{
+	u32 cr0_saved;
+	s32 fdiv_bug;
+
+	/* We might have CR0::TS set already, clear it: */
+	cr0_saved = read_cr0();
+	write_cr0(cr0_saved & ~X86_CR0_TS);
+
+	kernel_fpu_begin();
+
+	/*
+	 * trap_init() enabled FXSR and company _before_ testing for FP
+	 * problems here.
+	 *
+	 * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
+	 */
+	__asm__("fninit\n\t"
+		"fldl %1\n\t"
+		"fdivl %2\n\t"
+		"fmull %2\n\t"
+		"fldl %1\n\t"
+		"fsubp %%st,%%st(1)\n\t"
+		"fistpl %0\n\t"
+		"fwait\n\t"
+		"fninit"
+		: "=m" (*&fdiv_bug)
+		: "m" (*&x), "m" (*&y));
+
+	kernel_fpu_end();
+
+	write_cr0(cr0_saved);
+
+	if (fdiv_bug) {
+		set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
+		pr_warn("Hmm, FPU with FDIV bug\n");
+	}
+}
+
+void __init fpu__init_check_bugs(void)
+{
+	/*
+	 * kernel_fpu_begin/end() in check_fpu() relies on the patched
+	 * alternative instructions.
+	 */
+	if (cpu_has_fpu)
+		check_fpu();
+}

arch/x86/kernel/fpu/core.c

@@ -0,0 +1,523 @@
+/*
+ *  Copyright (C) 1994 Linus Torvalds
+ *
+ *  Pentium III FXSR, SSE support
+ *  General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+#include <asm/fpu/internal.h>
+#include <asm/fpu/regset.h>
+#include <asm/fpu/signal.h>
+#include <asm/traps.h>
+
+#include <linux/hardirq.h>
+
+/*
+ * Represents the initial FPU state. It's mostly (but not completely) zeroes,
+ * depending on the FPU hardware format:
+ */
+union fpregs_state init_fpstate __read_mostly;
+
+/*
+ * Track whether the kernel is using the FPU state
+ * currently.
+ *
+ * This flag is used:
+ *
+ *   - by IRQ context code to potentially use the FPU
+ *     if it's unused.
+ *
+ *   - to debug kernel_fpu_begin()/end() correctness
+ */
+static DEFINE_PER_CPU(bool, in_kernel_fpu);
+
+/*
+ * Track which context is using the FPU on the CPU:
+ */
+DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+static void kernel_fpu_disable(void)
+{
+	WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, true);
+}
+
+static void kernel_fpu_enable(void)
+{
+	WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, false);
+}
+
+static bool kernel_fpu_disabled(void)
+{
+	return this_cpu_read(in_kernel_fpu);
+}
+
+/*
+ * Were we in an interrupt that interrupted kernel mode?
+ *
+ * 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
+ * visible in the interrupted kernel thread).
+ *
+ * Except for the eagerfpu case when we return true; in the likely case
+ * the thread has FPU but we are not going to set/clear TS.
+ */
+static bool interrupted_kernel_fpu_idle(void)
+{
+	if (kernel_fpu_disabled())
+		return false;
+
+	if (use_eager_fpu())
+		return true;
+
+	return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS);
+}
+
+/*
+ * Were we in user mode (or vm86 mode) when we were
+ * interrupted?
+ *
+ * Doing kernel_fpu_begin/end() is ok if we are running
+ * in an interrupt context from user mode - we'll just
+ * save the FPU state as required.
+ */
+static bool interrupted_user_mode(void)
+{
+	struct pt_regs *regs = get_irq_regs();
+	return regs && user_mode(regs);
+}
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ *
+ * It's always ok in process context (ie "not interrupt")
+ * but it is sometimes ok even from an irq.
+ */
+bool irq_fpu_usable(void)
+{
+	return !in_interrupt() ||
+		interrupted_user_mode() ||
+		interrupted_kernel_fpu_idle();
+}
+EXPORT_SYMBOL(irq_fpu_usable);
+
+void __kernel_fpu_begin(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	WARN_ON_FPU(!irq_fpu_usable());
+
+	kernel_fpu_disable();
+
+	if (fpu->fpregs_active) {
+		copy_fpregs_to_fpstate(fpu);
+	} else {
+		this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+		__fpregs_activate_hw();
+	}
+}
+EXPORT_SYMBOL(__kernel_fpu_begin);
+
+void __kernel_fpu_end(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	if (fpu->fpregs_active)
+		copy_kernel_to_fpregs(&fpu->state);
+	else
+		__fpregs_deactivate_hw();
+
+	kernel_fpu_enable();
+}
+EXPORT_SYMBOL(__kernel_fpu_end);
+
+void kernel_fpu_begin(void)
+{
+	preempt_disable();
+	__kernel_fpu_begin();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+
+void kernel_fpu_end(void)
+{
+	__kernel_fpu_end();
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);
+
+/*
+ * CR0::TS save/restore functions:
+ */
+int irq_ts_save(void)
+{
+	/*
+	 * If in process context and not atomic, we can take a spurious DNA fault.
+	 * Otherwise, doing clts() in process context requires disabling preemption
+	 * or some heavy lifting like kernel_fpu_begin()
+	 */
+	if (!in_atomic())
+		return 0;
+
+	if (read_cr0() & X86_CR0_TS) {
+		clts();
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_ts_save);
+
+void irq_ts_restore(int TS_state)
+{
+	if (TS_state)
+		stts();
+}
+EXPORT_SYMBOL_GPL(irq_ts_restore);
+
+/*
+ * Save the FPU state (mark it for reload if necessary):
+ *
+ * This only ever gets called for the current task.
+ */
+void fpu__save(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu != &current->thread.fpu);
+
+	preempt_disable();
+	if (fpu->fpregs_active) {
+		if (!copy_fpregs_to_fpstate(fpu))
+			fpregs_deactivate(fpu);
+	}
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(fpu__save);
+
+/*
+ * Legacy x87 fpstate state init:
+ */
+static inline void fpstate_init_fstate(struct fregs_state *fp)
+{
+	fp->cwd = 0xffff037fu;
+	fp->swd = 0xffff0000u;
+	fp->twd = 0xffffffffu;
+	fp->fos = 0xffff0000u;
+}
+
+void fpstate_init(union fpregs_state *state)
+{
+	if (!cpu_has_fpu) {
+		fpstate_init_soft(&state->soft);
+		return;
+	}
+
+	memset(state, 0, xstate_size);
+
+	if (cpu_has_fxsr)
+		fpstate_init_fxstate(&state->fxsave);
+	else
+		fpstate_init_fstate(&state->fsave);
+}
+EXPORT_SYMBOL_GPL(fpstate_init);
+
+/*
+ * Copy the current task's FPU state to a new task's FPU context.
+ *
+ * In both the 'eager' and the 'lazy' case we save hardware registers
+ * directly to the destination buffer.
+ */
+static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+{
+	WARN_ON_FPU(src_fpu != &current->thread.fpu);
+
+	/*
+	 * Don't let 'init optimized' areas of the XSAVE area
+	 * leak into the child task:
+	 */
+	if (use_eager_fpu())
+		memset(&dst_fpu->state.xsave, 0, xstate_size);
+
+	/*
+	 * Save current FPU registers directly into the child
+	 * FPU context, without any memory-to-memory copying.
+	 *
+	 * If the FPU context got destroyed in the process (FNSAVE
+	 * done on old CPUs) then copy it back into the source
+	 * context and mark the current task for lazy restore.
+	 *
+	 * We have to do all this with preemption disabled,
+	 * mostly because of the FNSAVE case, because in that
+	 * case we must not allow preemption in the window
+	 * between the FNSAVE and us marking the context lazy.
+	 *
+	 * It shouldn't be an issue as even FNSAVE is plenty
+	 * fast in terms of critical section length.
+	 */
+	preempt_disable();
+	if (!copy_fpregs_to_fpstate(dst_fpu)) {
+		memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
+		fpregs_deactivate(src_fpu);
+	}
+	preempt_enable();
+}
+
+int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+{
+	dst_fpu->counter = 0;
+	dst_fpu->fpregs_active = 0;
+	dst_fpu->last_cpu = -1;
+
+	if (src_fpu->fpstate_active)
+		fpu_copy(dst_fpu, src_fpu);
+
+	return 0;
+}
+
+/*
+ * Activate the current task's in-memory FPU context,
+ * if it has not been used before:
+ */
+void fpu__activate_curr(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu != &current->thread.fpu);
+
+	if (!fpu->fpstate_active) {
+		fpstate_init(&fpu->state);
+
+		/* Safe to do for the current task: */
+		fpu->fpstate_active = 1;
+	}
+}
+EXPORT_SYMBOL_GPL(fpu__activate_curr);
+
+/*
+ * This function must be called before we read a task's fpstate.
+ *
+ * If the task has not used the FPU before then initialize its
+ * fpstate.
+ *
+ * If the task has used the FPU before then save it.
+ */
+void fpu__activate_fpstate_read(struct fpu *fpu)
+{
+	/*
+	 * If fpregs are active (in the current CPU), then
+	 * copy them to the fpstate:
+	 */
+	if (fpu->fpregs_active) {
+		fpu__save(fpu);
+	} else {
+		if (!fpu->fpstate_active) {
+			fpstate_init(&fpu->state);
+
+			/* Safe to do for current and for stopped child tasks: */
+			fpu->fpstate_active = 1;
+		}
+	}
+}
+
+/*
+ * This function must be called before we write a task's fpstate.
+ *
+ * If the task has used the FPU before then unlazy it.
+ * If the task has not used the FPU before then initialize its fpstate.
+ *
+ * After this function call, after registers in the fpstate are
+ * modified and the child task has woken up, the child task will
+ * restore the modified FPU state from the modified context. If we
+ * didn't clear its lazy status here then the lazy in-registers
+ * state pending on its former CPU could be restored, corrupting
+ * the modifications.
+ */
+void fpu__activate_fpstate_write(struct fpu *fpu)
+{
+	/*
+	 * Only stopped child tasks can be used to modify the FPU
+	 * state in the fpstate buffer:
+	 */
+	WARN_ON_FPU(fpu == &current->thread.fpu);
+
+	if (fpu->fpstate_active) {
+		/* Invalidate any lazy state: */
+		fpu->last_cpu = -1;
+	} else {
+		fpstate_init(&fpu->state);
+
+		/* Safe to do for stopped child tasks: */
+		fpu->fpstate_active = 1;
+	}
+}
+
+/*
+ * 'fpu__restore()' is called to copy FPU registers from
+ * the FPU fpstate to the live hw registers and to activate
+ * access to the hardware registers, so that FPU instructions
+ * can be used afterwards.
+ *
+ * Must be called with kernel preemption disabled (for example
+ * with local interrupts disabled, as it is in the case of
+ * do_device_not_available()).
+ */
+void fpu__restore(struct fpu *fpu)
+{
+	fpu__activate_curr(fpu);
+
+	/* Avoid __kernel_fpu_begin() right after fpregs_activate() */
+	kernel_fpu_disable();
+	fpregs_activate(fpu);
+	copy_kernel_to_fpregs(&fpu->state);
+	fpu->counter++;
+	kernel_fpu_enable();
+}
+EXPORT_SYMBOL_GPL(fpu__restore);
+
+/*
+ * Drops current FPU state: deactivates the fpregs and
+ * the fpstate. NOTE: it still leaves previous contents
+ * in the fpregs in the eager-FPU case.
+ *
+ * This function can be used in cases where we know that
+ * a state-restore is coming: either an explicit one,
+ * or a reschedule.
+ */
+void fpu__drop(struct fpu *fpu)
+{
+	preempt_disable();
+	fpu->counter = 0;
+
+	if (fpu->fpregs_active) {
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
+		fpregs_deactivate(fpu);
+	}
+
+	fpu->fpstate_active = 0;
+
+	preempt_enable();
+}
+
+/*
+ * Clear FPU registers by setting them up from
+ * the init fpstate:
+ */
+static inline void copy_init_fpstate_to_fpregs(void)
+{
+	if (use_xsave())
+		copy_kernel_to_xregs(&init_fpstate.xsave, -1);
+	else
+		copy_kernel_to_fxregs(&init_fpstate.fxsave);
+}
+
+/*
+ * Clear the FPU state back to init state.
+ *
+ * Called by sys_execve(), by the signal handler code and by various
+ * error paths.
+ */
+void fpu__clear(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
+
+	if (!use_eager_fpu()) {
+		/* FPU state will be reallocated lazily at the first use. */
+		fpu__drop(fpu);
+	} else {
+		if (!fpu->fpstate_active) {
+			fpu__activate_curr(fpu);
+			user_fpu_begin();
+		}
+		copy_init_fpstate_to_fpregs();
+	}
+}
+
+/*
+ * x87 math exception handling:
+ */
+
+static inline unsigned short get_fpu_cwd(struct fpu *fpu)
+{
+	if (cpu_has_fxsr) {
+		return fpu->state.fxsave.cwd;
+	} else {
+		return (unsigned short)fpu->state.fsave.cwd;
+	}
+}
+
+static inline unsigned short get_fpu_swd(struct fpu *fpu)
+{
+	if (cpu_has_fxsr) {
+		return fpu->state.fxsave.swd;
+	} else {
+		return (unsigned short)fpu->state.fsave.swd;
+	}
+}
+
+static inline unsigned short get_fpu_mxcsr(struct fpu *fpu)
+{
+	if (cpu_has_xmm) {
+		return fpu->state.fxsave.mxcsr;
+	} else {
+		return MXCSR_DEFAULT;
+	}
+}
+
+int fpu__exception_code(struct fpu *fpu, int trap_nr)
+{
+	int err;
+
+	if (trap_nr == X86_TRAP_MF) {
+		unsigned short cwd, swd;
+		/*
+		 * (~cwd & swd) will mask out exceptions that are not set to unmasked
+		 * status.  0x3f is the exception bits in these regs, 0x200 is the
+		 * C1 reg you need in case of a stack fault, 0x040 is the stack
+		 * fault bit.  We should only be taking one exception at a time,
+		 * so if this combination doesn't produce any single exception,
+		 * then we have a bad program that isn't synchronizing its FPU usage
+		 * and it will suffer the consequences since we won't be able to
+		 * fully reproduce the context of the exception
+		 */
+		cwd = get_fpu_cwd(fpu);
+		swd = get_fpu_swd(fpu);
+
+		err = swd & ~cwd;
+	} else {
+		/*
+		 * The SIMD FPU exceptions are handled a little differently, as there
+		 * is only a single status/control register.  Thus, to determine which
+		 * unmasked exception was caught we must mask the exception mask bits
+		 * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+		 */
+		unsigned short mxcsr = get_fpu_mxcsr(fpu);
+		err = ~(mxcsr >> 7) & mxcsr;
+	}
+
+	if (err & 0x001) {	/* Invalid op */
+		/*
+		 * swd & 0x240 == 0x040: Stack Underflow
+		 * swd & 0x240 == 0x240: Stack Overflow
+		 * User must clear the SF bit (0x40) if set
+		 */
+		return FPE_FLTINV;
+	} else if (err & 0x004) { /* Divide by Zero */
+		return FPE_FLTDIV;
+	} else if (err & 0x008) { /* Overflow */
+		return FPE_FLTOVF;
+	} else if (err & 0x012) { /* Denormal, Underflow */
+		return FPE_FLTUND;
+	} else if (err & 0x020) { /* Precision */
+		return FPE_FLTRES;
+	}
+
+	/*
+	 * If we're using IRQ 13, or supposedly even some trap
+	 * X86_TRAP_MF implementations, it's possible
+	 * we get a spurious trap, which is not an error.
+	 */
+	return 0;
+}

arch/x86/kernel/fpu/init.c

@@ -0,0 +1,354 @@
+/*
+ * x86 FPU boot time init code:
+ */
+#include <asm/fpu/internal.h>
+#include <asm/tlbflush.h>
+
+/*
+ * Initialize the TS bit in CR0 according to the style of context-switches
+ * we are using:
+ */
+static void fpu__init_cpu_ctx_switch(void)
+{
+	if (!cpu_has_eager_fpu)
+		stts();
+	else
+		clts();
+}
+
+/*
+ * Initialize the registers found in all CPUs, CR0 and CR4:
+ */
+static void fpu__init_cpu_generic(void)
+{
+	unsigned long cr0;
+	unsigned long cr4_mask = 0;
+
+	if (cpu_has_fxsr)
+		cr4_mask |= X86_CR4_OSFXSR;
+	if (cpu_has_xmm)
+		cr4_mask |= X86_CR4_OSXMMEXCPT;
+	if (cr4_mask)
+		cr4_set_bits(cr4_mask);
+
+	cr0 = read_cr0();
+	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
+	if (!cpu_has_fpu)
+		cr0 |= X86_CR0_EM;
+	write_cr0(cr0);
+
+	/* Flush out any pending x87 state: */
+	asm volatile ("fninit");
+}
+
+/*
+ * Enable all supported FPU features. Called when a CPU is brought online:
+ */
+void fpu__init_cpu(void)
+{
+	fpu__init_cpu_generic();
+	fpu__init_cpu_xstate();
+	fpu__init_cpu_ctx_switch();
+}
+
+/*
+ * The earliest FPU detection code.
+ *
+ * Set the X86_FEATURE_FPU CPU-capability bit based on
+ * trying to execute an actual sequence of FPU instructions:
+ */
+static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+{
+	unsigned long cr0;
+	u16 fsw, fcw;
+
+	fsw = fcw = 0xffff;
+
+	cr0 = read_cr0();
+	cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
+	write_cr0(cr0);
+
+	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+		     : "+m" (fsw), "+m" (fcw));
+
+	if (fsw == 0 && (fcw & 0x103f) == 0x003f)
+		set_cpu_cap(c, X86_FEATURE_FPU);
+	else
+		clear_cpu_cap(c, X86_FEATURE_FPU);
+
+#ifndef CONFIG_MATH_EMULATION
+	if (!cpu_has_fpu) {
+		pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
+		for (;;)
+			asm volatile("hlt");
+	}
+#endif
+}
+
+/*
+ * Boot time FPU feature detection code:
+ */
+unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+
+static void __init fpu__init_system_mxcsr(void)
+{
+	unsigned int mask = 0;
+
+	if (cpu_has_fxsr) {
+		struct fxregs_state fx_tmp __aligned(32) = { };
+
+		asm volatile("fxsave %0" : "+m" (fx_tmp));
+
+		mask = fx_tmp.mxcsr_mask;
+
+		/*
+		 * If zero then use the default features mask,
+		 * which has all features set, except the
+		 * denormals-are-zero feature bit:
+		 */
+		if (mask == 0)
+			mask = 0x0000ffbf;
+	}
+	mxcsr_feature_mask &= mask;
+}
+
+/*
+ * Once per bootup FPU initialization sequences that will run on most x86 CPUs:
+ */
+static void __init fpu__init_system_generic(void)
+{
+	/*
+	 * Set up the legacy init FPU context. (xstate init might overwrite this
+	 * with a more modern format, if the CPU supports it.)
+	 */
+	fpstate_init_fxstate(&init_fpstate.fxsave);
+
+	fpu__init_system_mxcsr();
+}
+
+/*
+ * Size of the FPU context state. All tasks in the system use the
+ * same context size, regardless of what portion they use.
+ * This is inherent to the XSAVE architecture which puts all state
+ * components into a single, continuous memory block:
+ */
+unsigned int xstate_size;
+EXPORT_SYMBOL_GPL(xstate_size);
+
+/*
+ * Set up the xstate_size based on the legacy FPU context size.
+ *
+ * We set this up first, and later it will be overwritten by
+ * fpu__init_system_xstate() if the CPU knows about xstates.
+ */
+static void __init fpu__init_system_xstate_size_legacy(void)
+{
+	static int on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	/*
+	 * Note that xstate_size might be overwriten later during
+	 * fpu__init_system_xstate().
+	 */
+
+	if (!cpu_has_fpu) {
+		/*
+		 * Disable xsave as we do not support it if i387
+		 * emulation is enabled.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+		xstate_size = sizeof(struct swregs_state);
+	} else {
+		if (cpu_has_fxsr)
+			xstate_size = sizeof(struct fxregs_state);
+		else
+			xstate_size = sizeof(struct fregs_state);
+	}
+	/*
+	 * Quirk: we don't yet handle the XSAVES* instructions
+	 * correctly, as we don't correctly convert between
+	 * standard and compacted format when interfacing
+	 * with user-space - so disable it for now.
+	 *
+	 * The difference is small: with recent CPUs the
+	 * compacted format is only marginally smaller than
+	 * the standard FPU state format.
+	 *
+	 * ( This is easy to backport while we are fixing
+	 *   XSAVES* support. )
+	 */
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+}
+
+/*
+ * FPU context switching strategies:
+ *
+ * Against popular belief, we don't do lazy FPU saves, due to the
+ * task migration complications it brings on SMP - we only do
+ * lazy FPU restores.
+ *
+ * 'lazy' is the traditional strategy, which is based on setting
+ * CR0::TS to 1 during context-switch (instead of doing a full
+ * restore of the FPU state), which causes the first FPU instruction
+ * after the context switch (whenever it is executed) to fault - at
+ * which point we lazily restore the FPU state into FPU registers.
+ *
+ * Tasks are of course under no obligation to execute FPU instructions,
+ * so it can easily happen that another context-switch occurs without
+ * a single FPU instruction being executed. If we eventually switch
+ * back to the original task (that still owns the FPU) then we have
+ * not only saved the restores along the way, but we also have the
+ * FPU ready to be used for the original task.
+ *
+ * 'eager' switching is used on modern CPUs, there we switch the FPU
+ * state during every context switch, regardless of whether the task
+ * has used FPU instructions in that time slice or not. This is done
+ * because modern FPU context saving instructions are able to optimize
+ * state saving and restoration in hardware: they can detect both
+ * unused and untouched FPU state and optimize accordingly.
+ *
+ * [ Note that even in 'lazy' mode we might optimize context switches
+ *   to use 'eager' restores, if we detect that a task is using the FPU
+ *   frequently. See the fpu->counter logic in fpu/internal.h for that. ]
+ */
+static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+
+static int __init eager_fpu_setup(char *s)
+{
+	if (!strcmp(s, "on"))
+		eagerfpu = ENABLE;
+	else if (!strcmp(s, "off"))
+		eagerfpu = DISABLE;
+	else if (!strcmp(s, "auto"))
+		eagerfpu = AUTO;
+	return 1;
+}
+__setup("eagerfpu=", eager_fpu_setup);
+
+/*
+ * Pick the FPU context switching strategy:
+ */
+static void __init fpu__init_system_ctx_switch(void)
+{
+	static bool on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	WARN_ON_FPU(current->thread.fpu.fpstate_active);
+	current_thread_info()->status = 0;
+
+	/* Auto enable eagerfpu for xsaveopt */
+	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
+		eagerfpu = ENABLE;
+
+	if (xfeatures_mask & XSTATE_EAGER) {
+		if (eagerfpu == DISABLE) {
+			pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
+			       xfeatures_mask & XSTATE_EAGER);
+			xfeatures_mask &= ~XSTATE_EAGER;
+		} else {
+			eagerfpu = ENABLE;
+		}
+	}
+
+	if (eagerfpu == ENABLE)
+		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
+
+	printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy");
+}
+
+/*
+ * Called on the boot CPU once per system bootup, to set up the initial
+ * FPU state that is later cloned into all processes:
+ */
+void __init fpu__init_system(struct cpuinfo_x86 *c)
+{
+	fpu__init_system_early_generic(c);
+
+	/*
+	 * The FPU has to be operational for some of the
+	 * later FPU init activities:
+	 */
+	fpu__init_cpu();
+
+	/*
+	 * But don't leave CR0::TS set yet, as some of the FPU setup
+	 * methods depend on being able to execute FPU instructions
+	 * that will fault on a set TS, such as the FXSAVE in
+	 * fpu__init_system_mxcsr().
+	 */
+	clts();
+
+	fpu__init_system_generic();
+	fpu__init_system_xstate_size_legacy();
+	fpu__init_system_xstate();
+
+	fpu__init_system_ctx_switch();
+}
+
+/*
+ * Boot parameter to turn off FPU support and fall back to math-emu:
+ */
+static int __init no_387(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_FPU);
+	return 1;
+}
+__setup("no387", no_387);
+
+/*
+ * Disable all xstate CPU features:
+ */
+static int __init x86_noxsave_setup(char *s)
+{
+	if (strlen(s))
+		return 0;
+
+	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+	setup_clear_cpu_cap(X86_FEATURE_AVX);
+	setup_clear_cpu_cap(X86_FEATURE_AVX2);
+
+	return 1;
+}
+__setup("noxsave", x86_noxsave_setup);
+
+/*
+ * Disable the XSAVEOPT instruction specifically:
+ */
+static int __init x86_noxsaveopt_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+
+	return 1;
+}
+__setup("noxsaveopt", x86_noxsaveopt_setup);
+
+/*
+ * Disable the XSAVES instruction:
+ */
+static int __init x86_noxsaves_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+
+	return 1;
+}
+__setup("noxsaves", x86_noxsaves_setup);
+
+/*
+ * Disable FX save/restore and SSE support:
+ */
+static int __init x86_nofxsr_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_FXSR);
+	setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
+	setup_clear_cpu_cap(X86_FEATURE_XMM);
+
+	return 1;
+}
+__setup("nofxsr", x86_nofxsr_setup);

arch/x86/kernel/fpu/regset.c

@@ -0,0 +1,356 @@
+/*
+ * FPU register's regset abstraction, for ptrace, core dumps, etc.
+ */
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+/*
+ * The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
+ * as the "regset->n" for the xstate regset will be updated based on the feature
+ * capabilites supported by the xsave.
+ */
+int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+	struct fpu *target_fpu = &target->thread.fpu;
+
+	return target_fpu->fpstate_active ? regset->n : 0;
+}
+
+int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+	struct fpu *target_fpu = &target->thread.fpu;
+
+	return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0;
+}
+
+int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		void *kbuf, void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+
+	if (!cpu_has_fxsr)
+		return -ENODEV;
+
+	fpu__activate_fpstate_read(fpu);
+	fpstate_sanitize_xstate(fpu);
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &fpu->state.fxsave, 0, -1);
+}
+
+int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	int ret;
+
+	if (!cpu_has_fxsr)
+		return -ENODEV;
+
+	fpu__activate_fpstate_write(fpu);
+	fpstate_sanitize_xstate(fpu);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &fpu->state.fxsave, 0, -1);
+
+	/*
+	 * mxcsr reserved bits must be masked to zero for security reasons.
+	 */
+	fpu->state.fxsave.mxcsr &= mxcsr_feature_mask;
+
+	/*
+	 * update the header bits in the xsave header, indicating the
+	 * presence of FP and SSE state.
+	 */
+	if (cpu_has_xsave)
+		fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE;
+
+	return ret;
+}
+
+int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		void *kbuf, void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct xregs_state *xsave;
+	int ret;
+
+	if (!cpu_has_xsave)
+		return -ENODEV;
+
+	fpu__activate_fpstate_read(fpu);
+
+	xsave = &fpu->state.xsave;
+
+	/*
+	 * Copy the 48bytes defined by the software first into the xstate
+	 * memory layout in the thread struct, so that we can copy the entire
+	 * xstateregs to the user using one user_regset_copyout().
+	 */
+	memcpy(&xsave->i387.sw_reserved,
+		xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
+	/*
+	 * Copy the xstate memory layout.
+	 */
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+	return ret;
+}
+
+int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
+		  unsigned int pos, unsigned int count,
+		  const void *kbuf, const void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct xregs_state *xsave;
+	int ret;
+
+	if (!cpu_has_xsave)
+		return -ENODEV;
+
+	fpu__activate_fpstate_write(fpu);
+
+	xsave = &fpu->state.xsave;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+	/*
+	 * mxcsr reserved bits must be masked to zero for security reasons.
+	 */
+	xsave->i387.mxcsr &= mxcsr_feature_mask;
+	xsave->header.xfeatures &= xfeatures_mask;
+	/*
+	 * These bits must be zero.
+	 */
+	memset(&xsave->header.reserved, 0, 48);
+
+	return ret;
+}
+
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+
+/*
+ * FPU tag word conversions.
+ */
+
+static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
+{
+	unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+
+	/* Transform each pair of bits into 01 (valid) or 00 (empty) */
+	tmp = ~twd;
+	tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+	/* and move the valid bits to the lower byte. */
+	tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+	tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+	tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+
+	return tmp;
+}
+
+#define FPREG_ADDR(f, n)	((void *)&(f)->st_space + (n) * 16)
+#define FP_EXP_TAG_VALID	0
+#define FP_EXP_TAG_ZERO		1
+#define FP_EXP_TAG_SPECIAL	2
+#define FP_EXP_TAG_EMPTY	3
+
+static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave)
+{
+	struct _fpxreg *st;
+	u32 tos = (fxsave->swd >> 11) & 7;
+	u32 twd = (unsigned long) fxsave->twd;
+	u32 tag;
+	u32 ret = 0xffff0000u;
+	int i;
+
+	for (i = 0; i < 8; i++, twd >>= 1) {
+		if (twd & 0x1) {
+			st = FPREG_ADDR(fxsave, (i - tos) & 7);
+
+			switch (st->exponent & 0x7fff) {
+			case 0x7fff:
+				tag = FP_EXP_TAG_SPECIAL;
+				break;
+			case 0x0000:
+				if (!st->significand[0] &&
+				    !st->significand[1] &&
+				    !st->significand[2] &&
+				    !st->significand[3])
+					tag = FP_EXP_TAG_ZERO;
+				else
+					tag = FP_EXP_TAG_SPECIAL;
+				break;
+			default:
+				if (st->significand[3] & 0x8000)
+					tag = FP_EXP_TAG_VALID;
+				else
+					tag = FP_EXP_TAG_SPECIAL;
+				break;
+			}
+		} else {
+			tag = FP_EXP_TAG_EMPTY;
+		}
+		ret |= tag << (2 * i);
+	}
+	return ret;
+}
+
+/*
+ * FXSR floating point environment conversions.
+ */
+
+void
+convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
+{
+	struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
+	struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
+	struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
+	int i;
+
+	env->cwd = fxsave->cwd | 0xffff0000u;
+	env->swd = fxsave->swd | 0xffff0000u;
+	env->twd = twd_fxsr_to_i387(fxsave);
+
+#ifdef CONFIG_X86_64
+	env->fip = fxsave->rip;
+	env->foo = fxsave->rdp;
+	/*
+	 * should be actually ds/cs at fpu exception time, but
+	 * that information is not available in 64bit mode.
+	 */
+	env->fcs = task_pt_regs(tsk)->cs;
+	if (tsk == current) {
+		savesegment(ds, env->fos);
+	} else {
+		env->fos = tsk->thread.ds;
+	}
+	env->fos |= 0xffff0000;
+#else
+	env->fip = fxsave->fip;
+	env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
+	env->foo = fxsave->foo;
+	env->fos = fxsave->fos;
+#endif
+
+	for (i = 0; i < 8; ++i)
+		memcpy(&to[i], &from[i], sizeof(to[0]));
+}
+
+void convert_to_fxsr(struct task_struct *tsk,
+		     const struct user_i387_ia32_struct *env)
+
+{
+	struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
+	struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
+	struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
+	int i;
+
+	fxsave->cwd = env->cwd;
+	fxsave->swd = env->swd;
+	fxsave->twd = twd_i387_to_fxsr(env->twd);
+	fxsave->fop = (u16) ((u32) env->fcs >> 16);
+#ifdef CONFIG_X86_64
+	fxsave->rip = env->fip;
+	fxsave->rdp = env->foo;
+	/* cs and ds ignored */
+#else
+	fxsave->fip = env->fip;
+	fxsave->fcs = (env->fcs & 0xffff);
+	fxsave->foo = env->foo;
+	fxsave->fos = env->fos;
+#endif
+
+	for (i = 0; i < 8; ++i)
+		memcpy(&to[i], &from[i], sizeof(from[0]));
+}
+
+int fpregs_get(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       void *kbuf, void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct user_i387_ia32_struct env;
+
+	fpu__activate_fpstate_read(fpu);
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
+
+	if (!cpu_has_fxsr)
+		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					   &fpu->state.fsave, 0,
+					   -1);
+
+	fpstate_sanitize_xstate(fpu);
+
+	if (kbuf && pos == 0 && count == sizeof(env)) {
+		convert_from_fxsr(kbuf, target);
+		return 0;
+	}
+
+	convert_from_fxsr(&env, target);
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+}
+
+int fpregs_set(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       const void *kbuf, const void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct user_i387_ia32_struct env;
+	int ret;
+
+	fpu__activate_fpstate_write(fpu);
+	fpstate_sanitize_xstate(fpu);
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
+
+	if (!cpu_has_fxsr)
+		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					  &fpu->state.fsave, 0,
+					  -1);
+
+	if (pos > 0 || count < sizeof(env))
+		convert_from_fxsr(&env, target);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+	if (!ret)
+		convert_to_fxsr(target, &env);
+
+	/*
+	 * update the header bit in the xsave header, indicating the
+	 * presence of FP.
+	 */
+	if (cpu_has_xsave)
+		fpu->state.xsave.header.xfeatures |= XSTATE_FP;
+	return ret;
+}
+
+/*
+ * FPU state for core dumps.
+ * This is only used for a.out dumps now.
+ * It is declared generically using elf_fpregset_t (which is
+ * struct user_i387_struct) but is in fact only used for 32-bit
+ * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
+ */
+int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
+{
+	struct task_struct *tsk = current;
+	struct fpu *fpu = &tsk->thread.fpu;
+	int fpvalid;
+
+	fpvalid = fpu->fpstate_active;
+	if (fpvalid)
+		fpvalid = !fpregs_get(tsk, NULL,
+				      0, sizeof(struct user_i387_ia32_struct),
+				      ufpu, NULL);
+
+	return fpvalid;
+}
+EXPORT_SYMBOL(dump_fpu);
+
+#endif	/* CONFIG_X86_32 || CONFIG_IA32_EMULATION */

arch/x86/kernel/fpu/signal.c

@@ -0,0 +1,404 @@
+/*
+ * FPU signal frame handling routines.
+ */
+
+#include <linux/compat.h>
+#include <linux/cpu.h>
+
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include <asm/sigframe.h>
+
+static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
+
+/*
+ * Check for the presence of extended state information in the
+ * user fpstate pointer in the sigcontext.
+ */
+static inline int check_for_xstate(struct fxregs_state __user *buf,
+				   void __user *fpstate,
+				   struct _fpx_sw_bytes *fx_sw)
+{
+	int min_xstate_size = sizeof(struct fxregs_state) +
+			      sizeof(struct xstate_header);
+	unsigned int magic2;
+
+	if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
+		return -1;
+
+	/* 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 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 (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
+	    || magic2 != FP_XSTATE_MAGIC2)
+		return -1;
+
+	return 0;
+}
+
+/*
+ * Signal frame handlers.
+ */
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
+{
+	if (use_fxsr()) {
+		struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+		struct user_i387_ia32_struct env;
+		struct _fpstate_ia32 __user *fp = 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 fregs_state __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 xregs_state __user *x = buf;
+	struct _fpx_sw_bytes *sw_bytes;
+	u32 xfeatures;
+	int err;
+
+	/* 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));
+
+	if (!use_xsave())
+		return err;
+
+	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
+
+	/*
+	 * Read the xfeatures which we copied (directly from the cpu or
+	 * from the state in task struct) to the user buffers.
+	 */
+	err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures);
+
+	/*
+	 * 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
+	 * xfeatures in the xsave header.
+	 *
+	 * xsave aware apps can change the xfeatures in the xsave
+	 * header as well as change any contents in the memory layout.
+	 * xrestore as part of sigreturn will capture all the changes.
+	 */
+	xfeatures |= XSTATE_FPSSE;
+
+	err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures);
+
+	return err;
+}
+
+static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
+{
+	int err;
+
+	if (use_xsave())
+		err = copy_xregs_to_user(buf);
+	else if (use_fxsr())
+		err = copy_fxregs_to_user((struct fxregs_state __user *) buf);
+	else
+		err = copy_fregs_to_user((struct fregs_state __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 copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
+{
+	struct xregs_state *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 (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_get(current, NULL, 0,
+			sizeof(struct user_i387_ia32_struct), NULL,
+			(struct _fpstate_ia32 __user *) buf) ? -1 : 1;
+
+	if (fpregs_active()) {
+		/* Save the live register state to the user directly. */
+		if (copy_fpregs_to_sigframe(buf_fx))
+			return -1;
+		/* Update the thread's fxstate to save the fsave header. */
+		if (ia32_fxstate)
+			copy_fxregs_to_kernel(&tsk->thread.fpu);
+	} else {
+		fpstate_sanitize_xstate(&tsk->thread.fpu);
+		if (__copy_to_user(buf_fx, xsave, xstate_size))
+			return -1;
+	}
+
+	/* Save the fsave header for the 32-bit frames. */
+	if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
+		return -1;
+
+	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
+		return -1;
+
+	return 0;
+}
+
+static inline void
+sanitize_restored_xstate(struct task_struct *tsk,
+			 struct user_i387_ia32_struct *ia32_env,
+			 u64 xfeatures, int fx_only)
+{
+	struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+	struct xstate_header *header = &xsave->header;
+
+	if (use_xsave()) {
+		/* These bits must be zero. */
+		memset(header->reserved, 0, 48);
+
+		/*
+		 * Init the state that is not present in the memory
+		 * layout and not enabled by the OS.
+		 */
+		if (fx_only)
+			header->xfeatures = XSTATE_FPSSE;
+		else
+			header->xfeatures &= (xfeatures_mask & xfeatures);
+	}
+
+	if (use_fxsr()) {
+		/*
+		 * mscsr reserved bits must be masked to zero for security
+		 * reasons.
+		 */
+		xsave->i387.mxcsr &= mxcsr_feature_mask;
+
+		convert_to_fxsr(tsk, ia32_env);
+	}
+}
+
+/*
+ * Restore the extended state if present. Otherwise, restore the FP/SSE state.
+ */
+static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
+{
+	if (use_xsave()) {
+		if ((unsigned long)buf % 64 || fx_only) {
+			u64 init_bv = xfeatures_mask & ~XSTATE_FPSSE;
+			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+			return copy_user_to_fxregs(buf);
+		} else {
+			u64 init_bv = xfeatures_mask & ~xbv;
+			if (unlikely(init_bv))
+				copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+			return copy_user_to_xregs(buf, xbv);
+		}
+	} else if (use_fxsr()) {
+		return copy_user_to_fxregs(buf);
+	} else
+		return copy_user_to_fregs(buf);
+}
+
+static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
+{
+	int ia32_fxstate = (buf != buf_fx);
+	struct task_struct *tsk = current;
+	struct fpu *fpu = &tsk->thread.fpu;
+	int state_size = xstate_size;
+	u64 xfeatures = 0;
+	int fx_only = 0;
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
+
+	if (!buf) {
+		fpu__clear(fpu);
+		return 0;
+	}
+
+	if (!access_ok(VERIFY_READ, buf, size))
+		return -EACCES;
+
+	fpu__activate_curr(fpu);
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_set(current, NULL,
+				       0, sizeof(struct user_i387_ia32_struct),
+				       NULL, buf) != 0;
+
+	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 fxregs_state);
+			fx_only = 1;
+		} else {
+			state_size = fx_sw_user.xstate_size;
+			xfeatures = fx_sw_user.xfeatures;
+		}
+	}
+
+	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 fpu *fpu = &tsk->thread.fpu;
+		struct user_i387_ia32_struct env;
+		int err = 0;
+
+		/*
+		 * Drop the current fpu which clears fpu->fpstate_active. This ensures
+		 * that any context-switch during the copy of the new state,
+		 * avoids the intermediate state from getting restored/saved.
+		 * Thus avoiding the new restored state from getting corrupted.
+		 * We will be ready to restore/save the state only after
+		 * fpu->fpstate_active is again set.
+		 */
+		fpu__drop(fpu);
+
+		if (__copy_from_user(&fpu->state.xsave, buf_fx, state_size) ||
+		    __copy_from_user(&env, buf, sizeof(env))) {
+			fpstate_init(&fpu->state);
+			err = -1;
+		} else {
+			sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
+		}
+
+		fpu->fpstate_active = 1;
+		if (use_eager_fpu()) {
+			preempt_disable();
+			fpu__restore(fpu);
+			preempt_enable();
+		}
+
+		return err;
+	} else {
+		/*
+		 * For 64-bit frames and 32-bit fsave frames, restore the user
+		 * state to the registers directly (with exceptions handled).
+		 */
+		user_fpu_begin();
+		if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) {
+			fpu__clear(fpu);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static inline int xstate_sigframe_size(void)
+{
+	return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+}
+
+/*
+ * Restore FPU state from a sigframe:
+ */
+int fpu__restore_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 fregs_state);
+		size += sizeof(struct fregs_state);
+	}
+
+	return __fpu__restore_sig(buf, buf_fx, size);
+}
+
+unsigned long
+fpu__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 fregs_state);
+		sp -= sizeof(struct fregs_state);
+	}
+
+	*size = frame_size;
+
+	return sp;
+}
+/*
+ * Prepare the SW reserved portion of the fxsave memory layout, indicating
+ * the presence of the extended state information in the memory layout
+ * pointed by the fpstate pointer in the sigcontext.
+ * This will be saved when ever the FP and extended state context is
+ * saved on the user stack during the signal handler delivery to the user.
+ */
+void fpu__init_prepare_fx_sw_frame(void)
+{
+	int fsave_header_size = sizeof(struct fregs_state);
+	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
+
+	if (config_enabled(CONFIG_X86_32))
+		size += fsave_header_size;
+
+	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
+	fx_sw_reserved.extended_size = size;
+	fx_sw_reserved.xfeatures = xfeatures_mask;
+	fx_sw_reserved.xstate_size = xstate_size;
+
+	if (config_enabled(CONFIG_IA32_EMULATION)) {
+		fx_sw_reserved_ia32 = fx_sw_reserved;
+		fx_sw_reserved_ia32.extended_size += fsave_header_size;
+	}
+}
+

arch/x86/kernel/fpu/xstate.c

@@ -0,0 +1,461 @@
+/*
+ * xsave/xrstor support.
+ *
+ * Author: Suresh Siddha <suresh.b.siddha@intel.com>
+ */
+#include <linux/compat.h>
+#include <linux/cpu.h>
+
+#include <asm/fpu/api.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include <asm/tlbflush.h>
+
+static const char *xfeature_names[] =
+{
+	"x87 floating point registers"	,
+	"SSE registers"			,
+	"AVX registers"			,
+	"MPX bounds registers"		,
+	"MPX CSR"			,
+	"AVX-512 opmask"		,
+	"AVX-512 Hi256"			,
+	"AVX-512 ZMM_Hi256"		,
+	"unknown xstate feature"	,
+};
+
+/*
+ * Mask of xstate features supported by the CPU and the kernel:
+ */
+u64 xfeatures_mask __read_mostly;
+
+static unsigned int xstate_offsets[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1};
+static unsigned int xstate_sizes[XFEATURES_NR_MAX]   = { [ 0 ... XFEATURES_NR_MAX - 1] = -1};
+static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
+
+/* The number of supported xfeatures in xfeatures_mask: */
+static unsigned int xfeatures_nr;
+
+/*
+ * Return whether the system supports a given xfeature.
+ *
+ * Also return the name of the (most advanced) feature that the caller requested:
+ */
+int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
+{
+	u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask;
+
+	if (unlikely(feature_name)) {
+		long xfeature_idx, max_idx;
+		u64 xfeatures_print;
+		/*
+		 * So we use FLS here to be able to print the most advanced
+		 * feature that was requested but is missing. So if a driver
+		 * asks about "XSTATE_SSE | XSTATE_YMM" we'll print the
+		 * missing AVX feature - this is the most informative message
+		 * to users:
+		 */
+		if (xfeatures_missing)
+			xfeatures_print = xfeatures_missing;
+		else
+			xfeatures_print = xfeatures_needed;
+
+		xfeature_idx = fls64(xfeatures_print)-1;
+		max_idx = ARRAY_SIZE(xfeature_names)-1;
+		xfeature_idx = min(xfeature_idx, max_idx);
+
+		*feature_name = xfeature_names[xfeature_idx];
+	}
+
+	if (xfeatures_missing)
+		return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
+
+/*
+ * When executing XSAVEOPT (or other optimized XSAVE instructions), if
+ * a processor implementation detects that an FPU state component is still
+ * (or is again) in its initialized state, it may clear the corresponding
+ * bit in the header.xfeatures field, and can skip the writeout of registers
+ * to the corresponding memory layout.
+ *
+ * This means that when the bit is zero, the state component might still contain
+ * some previous - non-initialized register state.
+ *
+ * Before writing xstate information to user-space we sanitize those components,
+ * to always ensure that the memory layout of a feature will be in the init state
+ * if the corresponding header bit is zero. This is to ensure that user-space doesn't
+ * see some stale state in the memory layout during signal handling, debugging etc.
+ */
+void fpstate_sanitize_xstate(struct fpu *fpu)
+{
+	struct fxregs_state *fx = &fpu->state.fxsave;
+	int feature_bit;
+	u64 xfeatures;
+
+	if (!use_xsaveopt())
+		return;
+
+	xfeatures = fpu->state.xsave.header.xfeatures;
+
+	/*
+	 * None of the feature bits are in init state. So nothing else
+	 * to do for us, as the memory layout is up to date.
+	 */
+	if ((xfeatures & xfeatures_mask) == xfeatures_mask)
+		return;
+
+	/*
+	 * FP is in init state
+	 */
+	if (!(xfeatures & XSTATE_FP)) {
+		fx->cwd = 0x37f;
+		fx->swd = 0;
+		fx->twd = 0;
+		fx->fop = 0;
+		fx->rip = 0;
+		fx->rdp = 0;
+		memset(&fx->st_space[0], 0, 128);
+	}
+
+	/*
+	 * SSE is in init state
+	 */
+	if (!(xfeatures & XSTATE_SSE))
+		memset(&fx->xmm_space[0], 0, 256);
+
+	/*
+	 * First two features are FPU and SSE, which above we handled
+	 * in a special way already:
+	 */
+	feature_bit = 0x2;
+	xfeatures = (xfeatures_mask & ~xfeatures) >> 2;
+
+	/*
+	 * Update all the remaining memory layouts according to their
+	 * standard xstate layout, if their header bit is in the init
+	 * state:
+	 */
+	while (xfeatures) {
+		if (xfeatures & 0x1) {
+			int offset = xstate_offsets[feature_bit];
+			int size = xstate_sizes[feature_bit];
+
+			memcpy((void *)fx + offset,
+			       (void *)&init_fpstate.xsave + offset,
+			       size);
+		}
+
+		xfeatures >>= 1;
+		feature_bit++;
+	}
+}
+
+/*
+ * Enable the extended processor state save/restore feature.
+ * Called once per CPU onlining.
+ */
+void fpu__init_cpu_xstate(void)
+{
+	if (!cpu_has_xsave || !xfeatures_mask)
+		return;
+
+	cr4_set_bits(X86_CR4_OSXSAVE);
+	xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+}
+
+/*
+ * Record the offsets and sizes of various xstates contained
+ * in the XSAVE state memory layout.
+ *
+ * ( Note that certain features might be non-present, for them
+ *   we'll have 0 offset and 0 size. )
+ */
+static void __init setup_xstate_features(void)
+{
+	u32 eax, ebx, ecx, edx, leaf;
+
+	xfeatures_nr = fls64(xfeatures_mask);
+
+	for (leaf = 2; leaf < xfeatures_nr; leaf++) {
+		cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
+
+		xstate_offsets[leaf] = ebx;
+		xstate_sizes[leaf] = eax;
+
+		printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %04x, xstate_sizes[%d]: %04x\n", leaf, ebx, leaf, eax);
+	}
+}
+
+static void __init print_xstate_feature(u64 xstate_mask)
+{
+	const char *feature_name;
+
+	if (cpu_has_xfeatures(xstate_mask, &feature_name))
+		pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name);
+}
+
+/*
+ * Print out all the supported xstate features:
+ */
+static void __init print_xstate_features(void)
+{
+	print_xstate_feature(XSTATE_FP);
+	print_xstate_feature(XSTATE_SSE);
+	print_xstate_feature(XSTATE_YMM);
+	print_xstate_feature(XSTATE_BNDREGS);
+	print_xstate_feature(XSTATE_BNDCSR);
+	print_xstate_feature(XSTATE_OPMASK);
+	print_xstate_feature(XSTATE_ZMM_Hi256);
+	print_xstate_feature(XSTATE_Hi16_ZMM);
+}
+
+/*
+ * This function sets up offsets and sizes of all extended states in
+ * xsave area. This supports both standard format and compacted format
+ * of the xsave aread.
+ */
+static void __init setup_xstate_comp(void)
+{
+	unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8];
+	int i;
+
+	/*
+	 * The FP xstates and SSE xstates are legacy states. They are always
+	 * in the fixed offsets in the xsave area in either compacted form
+	 * or standard form.
+	 */
+	xstate_comp_offsets[0] = 0;
+	xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space);
+
+	if (!cpu_has_xsaves) {
+		for (i = 2; i < xfeatures_nr; i++) {
+			if (test_bit(i, (unsigned long *)&xfeatures_mask)) {
+				xstate_comp_offsets[i] = xstate_offsets[i];
+				xstate_comp_sizes[i] = xstate_sizes[i];
+			}
+		}
+		return;
+	}
+
+	xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+
+	for (i = 2; i < xfeatures_nr; i++) {
+		if (test_bit(i, (unsigned long *)&xfeatures_mask))
+			xstate_comp_sizes[i] = xstate_sizes[i];
+		else
+			xstate_comp_sizes[i] = 0;
+
+		if (i > 2)
+			xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
+					+ xstate_comp_sizes[i-1];
+
+	}
+}
+
+/*
+ * setup the xstate image representing the init state
+ */
+static void __init setup_init_fpu_buf(void)
+{
+	static int on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	if (!cpu_has_xsave)
+		return;
+
+	setup_xstate_features();
+	print_xstate_features();
+
+	if (cpu_has_xsaves) {
+		init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
+		init_fpstate.xsave.header.xfeatures = xfeatures_mask;
+	}
+
+	/*
+	 * Init all the features state with header_bv being 0x0
+	 */
+	copy_kernel_to_xregs_booting(&init_fpstate.xsave);
+
+	/*
+	 * Dump the init state again. This is to identify the init state
+	 * of any feature which is not represented by all zero's.
+	 */
+	copy_xregs_to_kernel_booting(&init_fpstate.xsave);
+}
+
+/*
+ * Calculate total size of enabled xstates in XCR0/xfeatures_mask.
+ */
+static void __init init_xstate_size(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	int i;
+
+	if (!cpu_has_xsaves) {
+		cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+		xstate_size = ebx;
+		return;
+	}
+
+	xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+	for (i = 2; i < 64; i++) {
+		if (test_bit(i, (unsigned long *)&xfeatures_mask)) {
+			cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+			xstate_size += eax;
+		}
+	}
+}
+
+/*
+ * Enable and initialize the xsave feature.
+ * Called once per system bootup.
+ */
+void __init fpu__init_system_xstate(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	static int on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	if (!cpu_has_xsave) {
+		pr_info("x86/fpu: Legacy x87 FPU detected.\n");
+		return;
+	}
+
+	if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
+		WARN_ON_FPU(1);
+		return;
+	}
+
+	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+	xfeatures_mask = eax + ((u64)edx << 32);
+
+	if ((xfeatures_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
+		pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask);
+		BUG();
+	}
+
+	/* Support only the state known to the OS: */
+	xfeatures_mask = xfeatures_mask & XCNTXT_MASK;
+
+	/* Enable xstate instructions to be able to continue with initialization: */
+	fpu__init_cpu_xstate();
+
+	/* Recompute the context size for enabled features: */
+	init_xstate_size();
+
+	update_regset_xstate_info(xstate_size, xfeatures_mask);
+	fpu__init_prepare_fx_sw_frame();
+	setup_init_fpu_buf();
+	setup_xstate_comp();
+
+	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is 0x%x bytes, using '%s' format.\n",
+		xfeatures_mask,
+		xstate_size,
+		cpu_has_xsaves ? "compacted" : "standard");
+}
+
+/*
+ * Restore minimal FPU state after suspend:
+ */
+void fpu__resume_cpu(void)
+{
+	/*
+	 * Restore XCR0 on xsave capable CPUs:
+	 */
+	if (cpu_has_xsave)
+		xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+}
+
+/*
+ * Given the xsave area and a state inside, this function returns the
+ * address of the state.
+ *
+ * This is the API that is called to get xstate address in either
+ * standard format or compacted format of xsave area.
+ *
+ * Note that if there is no data for the field in the xsave buffer
+ * this will return NULL.
+ *
+ * Inputs:
+ *	xstate: the thread's storage area for all FPU data
+ *	xstate_feature: state which is defined in xsave.h (e.g.
+ *	XSTATE_FP, XSTATE_SSE, etc...)
+ * Output:
+ *	address of the state in the xsave area, or NULL if the
+ *	field is not present in the xsave buffer.
+ */
+void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
+{
+	int feature_nr = fls64(xstate_feature) - 1;
+	/*
+	 * Do we even *have* xsave state?
+	 */
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
+		return NULL;
+
+	xsave = &current->thread.fpu.state.xsave;
+	/*
+	 * We should not ever be requesting features that we
+	 * have not enabled.  Remember that pcntxt_mask is
+	 * what we write to the XCR0 register.
+	 */
+	WARN_ONCE(!(xfeatures_mask & xstate_feature),
+		  "get of unsupported state");
+	/*
+	 * This assumes the last 'xsave*' instruction to
+	 * have requested that 'xstate_feature' be saved.
+	 * If it did not, we might be seeing and old value
+	 * of the field in the buffer.
+	 *
+	 * This can happen because the last 'xsave' did not
+	 * request that this feature be saved (unlikely)
+	 * or because the "init optimization" caused it
+	 * to not be saved.
+	 */
+	if (!(xsave->header.xfeatures & xstate_feature))
+		return NULL;
+
+	return (void *)xsave + xstate_comp_offsets[feature_nr];
+}
+EXPORT_SYMBOL_GPL(get_xsave_addr);
+
+/*
+ * This wraps up the common operations that need to occur when retrieving
+ * data from xsave state.  It first ensures that the current task was
+ * using the FPU and retrieves the data in to a buffer.  It then calculates
+ * the offset of the requested field in the buffer.
+ *
+ * This function is safe to call whether the FPU is in use or not.
+ *
+ * Note that this only works on the current task.
+ *
+ * Inputs:
+ *	@xsave_state: state which is defined in xsave.h (e.g. XSTATE_FP,
+ *	XSTATE_SSE, etc...)
+ * Output:
+ *	address of the state in the xsave area or NULL if the state
+ *	is not present or is in its 'init state'.
+ */
+const void *get_xsave_field_ptr(int xsave_state)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	if (!fpu->fpstate_active)
+		return NULL;
+	/*
+	 * fpu__save() takes the CPU's xstate registers
+	 * and saves them off to the 'fpu memory buffer.
+	 */
+	fpu__save(fpu);
+
+	return get_xsave_addr(&fpu->state.xsave, xsave_state);
+}

arch/x86/kernel/i387.c

@@ -1,671 +0,0 @@
-/*
- *  Copyright (C) 1994 Linus Torvalds
- *
- *  Pentium III FXSR, SSE support
- *  General FPU state handling cleanups
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- */
-#include <linux/module.h>
-#include <linux/regset.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-
-#include <asm/sigcontext.h>
-#include <asm/processor.h>
-#include <asm/math_emu.h>
-#include <asm/tlbflush.h>
-#include <asm/uaccess.h>
-#include <asm/ptrace.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
-#include <asm/user.h>
-
-static DEFINE_PER_CPU(bool, in_kernel_fpu);
-
-void kernel_fpu_disable(void)
-{
-	WARN_ON(this_cpu_read(in_kernel_fpu));
-	this_cpu_write(in_kernel_fpu, true);
-}
-
-void kernel_fpu_enable(void)
-{
-	this_cpu_write(in_kernel_fpu, false);
-}
-
-/*
- * Were we in an interrupt that interrupted kernel mode?
- *
- * 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
- * visible in the interrupted kernel thread).
- *
- * Except for the eagerfpu case when we return true; in the likely case
- * the thread has FPU but we are not going to set/clear TS.
- */
-static inline bool interrupted_kernel_fpu_idle(void)
-{
-	if (this_cpu_read(in_kernel_fpu))
-		return false;
-
-	if (use_eager_fpu())
-		return true;
-
-	return !__thread_has_fpu(current) &&
-		(read_cr0() & X86_CR0_TS);
-}
-
-/*
- * Were we in user mode (or vm86 mode) when we were
- * interrupted?
- *
- * Doing kernel_fpu_begin/end() is ok if we are running
- * in an interrupt context from user mode - we'll just
- * save the FPU state as required.
- */
-static inline bool interrupted_user_mode(void)
-{
-	struct pt_regs *regs = get_irq_regs();
-	return regs && user_mode(regs);
-}
-
-/*
- * Can we use the FPU in kernel mode with the
- * whole "kernel_fpu_begin/end()" sequence?
- *
- * It's always ok in process context (ie "not interrupt")
- * but it is sometimes ok even from an irq.
- */
-bool irq_fpu_usable(void)
-{
-	return !in_interrupt() ||
-		interrupted_user_mode() ||
-		interrupted_kernel_fpu_idle();
-}
-EXPORT_SYMBOL(irq_fpu_usable);
-
-void __kernel_fpu_begin(void)
-{
-	struct task_struct *me = current;
-
-	this_cpu_write(in_kernel_fpu, true);
-
-	if (__thread_has_fpu(me)) {
-		__save_init_fpu(me);
-	} else {
-		this_cpu_write(fpu_owner_task, NULL);
-		if (!use_eager_fpu())
-			clts();
-	}
-}
-EXPORT_SYMBOL(__kernel_fpu_begin);
-
-void __kernel_fpu_end(void)
-{
-	struct task_struct *me = current;
-
-	if (__thread_has_fpu(me)) {
-		if (WARN_ON(restore_fpu_checking(me)))
-			fpu_reset_state(me);
-	} else if (!use_eager_fpu()) {
-		stts();
-	}
-
-	this_cpu_write(in_kernel_fpu, false);
-}
-EXPORT_SYMBOL(__kernel_fpu_end);
-
-void unlazy_fpu(struct task_struct *tsk)
-{
-	preempt_disable();
-	if (__thread_has_fpu(tsk)) {
-		if (use_eager_fpu()) {
-			__save_fpu(tsk);
-		} else {
-			__save_init_fpu(tsk);
-			__thread_fpu_end(tsk);
-		}
-	}
-	preempt_enable();
-}
-EXPORT_SYMBOL(unlazy_fpu);
-
-unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
-unsigned int xstate_size;
-EXPORT_SYMBOL_GPL(xstate_size);
-static struct i387_fxsave_struct fx_scratch;
-
-static void mxcsr_feature_mask_init(void)
-{
-	unsigned long mask = 0;
-
-	if (cpu_has_fxsr) {
-		memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
-		asm volatile("fxsave %0" : "+m" (fx_scratch));
-		mask = fx_scratch.mxcsr_mask;
-		if (mask == 0)
-			mask = 0x0000ffbf;
-	}
-	mxcsr_feature_mask &= mask;
-}
-
-static void init_thread_xstate(void)
-{
-	/*
-	 * Note that xstate_size might be overwriten later during
-	 * xsave_init().
-	 */
-
-	if (!cpu_has_fpu) {
-		/*
-		 * Disable xsave as we do not support it if i387
-		 * emulation is enabled.
-		 */
-		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-		xstate_size = sizeof(struct i387_soft_struct);
-		return;
-	}
-
-	if (cpu_has_fxsr)
-		xstate_size = sizeof(struct i387_fxsave_struct);
-	else
-		xstate_size = sizeof(struct i387_fsave_struct);
-
-	/*
-	 * Quirk: we don't yet handle the XSAVES* instructions
-	 * correctly, as we don't correctly convert between
-	 * standard and compacted format when interfacing
-	 * with user-space - so disable it for now.
-	 *
-	 * The difference is small: with recent CPUs the
-	 * compacted format is only marginally smaller than
-	 * the standard FPU state format.
-	 *
-	 * ( This is easy to backport while we are fixing
-	 *   XSAVES* support. )
-	 */
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-}
-
-/*
- * Called at bootup to set up the initial FPU state that is later cloned
- * into all processes.
- */
-
-void fpu_init(void)
-{
-	unsigned long cr0;
-	unsigned long cr4_mask = 0;
-
-#ifndef CONFIG_MATH_EMULATION
-	if (!cpu_has_fpu) {
-		pr_emerg("No FPU found and no math emulation present\n");
-		pr_emerg("Giving up\n");
-		for (;;)
-			asm volatile("hlt");
-	}
-#endif
-	if (cpu_has_fxsr)
-		cr4_mask |= X86_CR4_OSFXSR;
-	if (cpu_has_xmm)
-		cr4_mask |= X86_CR4_OSXMMEXCPT;
-	if (cr4_mask)
-		cr4_set_bits(cr4_mask);
-
-	cr0 = read_cr0();
-	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
-	if (!cpu_has_fpu)
-		cr0 |= X86_CR0_EM;
-	write_cr0(cr0);
-
-	/*
-	 * init_thread_xstate is only called once to avoid overriding
-	 * xstate_size during boot time or during CPU hotplug.
-	 */
-	if (xstate_size == 0)
-		init_thread_xstate();
-
-	mxcsr_feature_mask_init();
-	xsave_init();
-	eager_fpu_init();
-}
-
-void fpu_finit(struct fpu *fpu)
-{
-	if (!cpu_has_fpu) {
-		finit_soft_fpu(&fpu->state->soft);
-		return;
-	}
-
-	memset(fpu->state, 0, xstate_size);
-
-	if (cpu_has_fxsr) {
-		fx_finit(&fpu->state->fxsave);
-	} else {
-		struct i387_fsave_struct *fp = &fpu->state->fsave;
-		fp->cwd = 0xffff037fu;
-		fp->swd = 0xffff0000u;
-		fp->twd = 0xffffffffu;
-		fp->fos = 0xffff0000u;
-	}
-}
-EXPORT_SYMBOL_GPL(fpu_finit);
-
-/*
- * The _current_ task is using the FPU for the first time
- * so initialize it and set the mxcsr to its default
- * value at reset if we support XMM instructions and then
- * remember the current task has used the FPU.
- */
-int init_fpu(struct task_struct *tsk)
-{
-	int ret;
-
-	if (tsk_used_math(tsk)) {
-		if (cpu_has_fpu && tsk == current)
-			unlazy_fpu(tsk);
-		task_disable_lazy_fpu_restore(tsk);
-		return 0;
-	}
-
-	/*
-	 * Memory allocation at the first usage of the FPU and other state.
-	 */
-	ret = fpu_alloc(&tsk->thread.fpu);
-	if (ret)
-		return ret;
-
-	fpu_finit(&tsk->thread.fpu);
-
-	set_stopped_child_used_math(tsk);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(init_fpu);
-
-/*
- * The xstateregs_active() routine is the same as the fpregs_active() routine,
- * as the "regset->n" for the xstate regset will be updated based on the feature
- * capabilites supported by the xsave.
- */
-int fpregs_active(struct task_struct *target, const struct user_regset *regset)
-{
-	return tsk_used_math(target) ? regset->n : 0;
-}
-
-int xfpregs_active(struct task_struct *target, const struct user_regset *regset)
-{
-	return (cpu_has_fxsr && tsk_used_math(target)) ? regset->n : 0;
-}
-
-int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_fxsr)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	sanitize_i387_state(target);
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.fpu.state->fxsave, 0, -1);
-}
-
-int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_fxsr)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	sanitize_i387_state(target);
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &target->thread.fpu.state->fxsave, 0, -1);
-
-	/*
-	 * mxcsr reserved bits must be masked to zero for security reasons.
-	 */
-	target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
-
-	/*
-	 * update the header bits in the xsave header, indicating the
-	 * presence of FP and SSE state.
-	 */
-	if (cpu_has_xsave)
-		target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
-
-	return ret;
-}
-
-int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		void *kbuf, void __user *ubuf)
-{
-	struct xsave_struct *xsave;
-	int ret;
-
-	if (!cpu_has_xsave)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	xsave = &target->thread.fpu.state->xsave;
-
-	/*
-	 * Copy the 48bytes defined by the software first into the xstate
-	 * memory layout in the thread struct, so that we can copy the entire
-	 * xstateregs to the user using one user_regset_copyout().
-	 */
-	memcpy(&xsave->i387.sw_reserved,
-		xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
-	/*
-	 * Copy the xstate memory layout.
-	 */
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
-	return ret;
-}
-
-int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
-		  unsigned int pos, unsigned int count,
-		  const void *kbuf, const void __user *ubuf)
-{
-	struct xsave_struct *xsave;
-	int ret;
-
-	if (!cpu_has_xsave)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	xsave = &target->thread.fpu.state->xsave;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
-	/*
-	 * mxcsr reserved bits must be masked to zero for security reasons.
-	 */
-	xsave->i387.mxcsr &= mxcsr_feature_mask;
-	xsave->xsave_hdr.xstate_bv &= pcntxt_mask;
-	/*
-	 * These bits must be zero.
-	 */
-	memset(&xsave->xsave_hdr.reserved, 0, 48);
-	return ret;
-}
-
-#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
-
-/*
- * FPU tag word conversions.
- */
-
-static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
-{
-	unsigned int tmp; /* to avoid 16 bit prefixes in the code */
-
-	/* Transform each pair of bits into 01 (valid) or 00 (empty) */
-	tmp = ~twd;
-	tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
-	/* and move the valid bits to the lower byte. */
-	tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
-	tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
-	tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
-
-	return tmp;
-}
-
-#define FPREG_ADDR(f, n)	((void *)&(f)->st_space + (n) * 16)
-#define FP_EXP_TAG_VALID	0
-#define FP_EXP_TAG_ZERO		1
-#define FP_EXP_TAG_SPECIAL	2
-#define FP_EXP_TAG_EMPTY	3
-
-static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave)
-{
-	struct _fpxreg *st;
-	u32 tos = (fxsave->swd >> 11) & 7;
-	u32 twd = (unsigned long) fxsave->twd;
-	u32 tag;
-	u32 ret = 0xffff0000u;
-	int i;
-
-	for (i = 0; i < 8; i++, twd >>= 1) {
-		if (twd & 0x1) {
-			st = FPREG_ADDR(fxsave, (i - tos) & 7);
-
-			switch (st->exponent & 0x7fff) {
-			case 0x7fff:
-				tag = FP_EXP_TAG_SPECIAL;
-				break;
-			case 0x0000:
-				if (!st->significand[0] &&
-				    !st->significand[1] &&
-				    !st->significand[2] &&
-				    !st->significand[3])
-					tag = FP_EXP_TAG_ZERO;
-				else
-					tag = FP_EXP_TAG_SPECIAL;
-				break;
-			default:
-				if (st->significand[3] & 0x8000)
-					tag = FP_EXP_TAG_VALID;
-				else
-					tag = FP_EXP_TAG_SPECIAL;
-				break;
-			}
-		} else {
-			tag = FP_EXP_TAG_EMPTY;
-		}
-		ret |= tag << (2 * i);
-	}
-	return ret;
-}
-
-/*
- * FXSR floating point environment conversions.
- */
-
-void
-convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
-{
-	struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
-	struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
-	struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
-	int i;
-
-	env->cwd = fxsave->cwd | 0xffff0000u;
-	env->swd = fxsave->swd | 0xffff0000u;
-	env->twd = twd_fxsr_to_i387(fxsave);
-
-#ifdef CONFIG_X86_64
-	env->fip = fxsave->rip;
-	env->foo = fxsave->rdp;
-	/*
-	 * should be actually ds/cs at fpu exception time, but
-	 * that information is not available in 64bit mode.
-	 */
-	env->fcs = task_pt_regs(tsk)->cs;
-	if (tsk == current) {
-		savesegment(ds, env->fos);
-	} else {
-		env->fos = tsk->thread.ds;
-	}
-	env->fos |= 0xffff0000;
-#else
-	env->fip = fxsave->fip;
-	env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
-	env->foo = fxsave->foo;
-	env->fos = fxsave->fos;
-#endif
-
-	for (i = 0; i < 8; ++i)
-		memcpy(&to[i], &from[i], sizeof(to[0]));
-}
-
-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;
-	struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
-	struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
-	int i;
-
-	fxsave->cwd = env->cwd;
-	fxsave->swd = env->swd;
-	fxsave->twd = twd_i387_to_fxsr(env->twd);
-	fxsave->fop = (u16) ((u32) env->fcs >> 16);
-#ifdef CONFIG_X86_64
-	fxsave->rip = env->fip;
-	fxsave->rdp = env->foo;
-	/* cs and ds ignored */
-#else
-	fxsave->fip = env->fip;
-	fxsave->fcs = (env->fcs & 0xffff);
-	fxsave->foo = env->foo;
-	fxsave->fos = env->fos;
-#endif
-
-	for (i = 0; i < 8; ++i)
-		memcpy(&to[i], &from[i], sizeof(from[0]));
-}
-
-int fpregs_get(struct task_struct *target, const struct user_regset *regset,
-	       unsigned int pos, unsigned int count,
-	       void *kbuf, void __user *ubuf)
-{
-	struct user_i387_ia32_struct env;
-	int ret;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
-
-	if (!cpu_has_fxsr)
-		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					   &target->thread.fpu.state->fsave, 0,
-					   -1);
-
-	sanitize_i387_state(target);
-
-	if (kbuf && pos == 0 && count == sizeof(env)) {
-		convert_from_fxsr(kbuf, target);
-		return 0;
-	}
-
-	convert_from_fxsr(&env, target);
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
-}
-
-int fpregs_set(struct task_struct *target, const struct user_regset *regset,
-	       unsigned int pos, unsigned int count,
-	       const void *kbuf, const void __user *ubuf)
-{
-	struct user_i387_ia32_struct env;
-	int ret;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	sanitize_i387_state(target);
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
-
-	if (!cpu_has_fxsr)
-		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					  &target->thread.fpu.state->fsave, 0,
-					  -1);
-
-	if (pos > 0 || count < sizeof(env))
-		convert_from_fxsr(&env, target);
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
-	if (!ret)
-		convert_to_fxsr(target, &env);
-
-	/*
-	 * update the header bit in the xsave header, indicating the
-	 * presence of FP.
-	 */
-	if (cpu_has_xsave)
-		target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP;
-	return ret;
-}
-
-/*
- * FPU state for core dumps.
- * This is only used for a.out dumps now.
- * It is declared generically using elf_fpregset_t (which is
- * struct user_i387_struct) but is in fact only used for 32-bit
- * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
- */
-int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu)
-{
-	struct task_struct *tsk = current;
-	int fpvalid;
-
-	fpvalid = !!used_math();
-	if (fpvalid)
-		fpvalid = !fpregs_get(tsk, NULL,
-				      0, sizeof(struct user_i387_ia32_struct),
-				      fpu, NULL);
-
-	return fpvalid;
-}
-EXPORT_SYMBOL(dump_fpu);
-
-#endif	/* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
-
-static int __init no_387(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FPU);
-	return 1;
-}
-
-__setup("no387", no_387);
-
-void fpu_detect(struct cpuinfo_x86 *c)
-{
-	unsigned long cr0;
-	u16 fsw, fcw;
-
-	fsw = fcw = 0xffff;
-
-	cr0 = read_cr0();
-	cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
-	write_cr0(cr0);
-
-	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
-		     : "+m" (fsw), "+m" (fcw));
-
-	if (fsw == 0 && (fcw & 0x103f) == 0x003f)
-		set_cpu_cap(c, X86_FEATURE_FPU);
-	else
-		clear_cpu_cap(c, X86_FEATURE_FPU);
-
-	/* The final cr0 value is set in fpu_init() */
-}

arch/x86/kernel/process.c

@@ -25,8 +25,7 @@
 #include <asm/idle.h>
 #include <asm/uaccess.h>
 #include <asm/mwait.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
 #include <asm/nmi.h>
 #include <asm/tlbflush.h>
@@ -76,9 +75,6 @@ void idle_notifier_unregister(struct notifier_block *n)
 EXPORT_SYMBOL_GPL(idle_notifier_unregister);
 #endif
 
-struct kmem_cache *task_xstate_cachep;
-EXPORT_SYMBOL_GPL(task_xstate_cachep);
-
 /*
  * this gets called so that we can store lazy state into memory and copy the
  * current task into the new thread.
@@ -87,36 +83,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	*dst = *src;
 
-	dst->thread.fpu_counter = 0;
-	dst->thread.fpu.has_fpu = 0;
-	dst->thread.fpu.state = NULL;
-	task_disable_lazy_fpu_restore(dst);
-	if (tsk_used_math(src)) {
-		int err = fpu_alloc(&dst->thread.fpu);
-		if (err)
-			return err;
-		fpu_copy(dst, src);
-	}
-	return 0;
-}
-
-void free_thread_xstate(struct task_struct *tsk)
-{
-	fpu_free(&tsk->thread.fpu);
-}
-
-void arch_release_task_struct(struct task_struct *tsk)
-{
-	free_thread_xstate(tsk);
-}
-
-void arch_task_cache_init(void)
-{
-        task_xstate_cachep =
-        	kmem_cache_create("task_xstate", xstate_size,
-				  __alignof__(union thread_xstate),
-				  SLAB_PANIC | SLAB_NOTRACK, NULL);
-	setup_xstate_comp();
+	return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
 }
 
 /*
@@ -127,6 +94,7 @@ void exit_thread(void)
 	struct task_struct *me = current;
 	struct thread_struct *t = &me->thread;
 	unsigned long *bp = t->io_bitmap_ptr;
+	struct fpu *fpu = &t->fpu;
 
 	if (bp) {
 		struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu());
@@ -142,7 +110,7 @@ void exit_thread(void)
 		kfree(bp);
 	}
 
-	drop_fpu(me);
+	fpu__drop(fpu);
 }
 
 void flush_thread(void)
@@ -152,19 +120,7 @@ void flush_thread(void)
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 
-	if (!use_eager_fpu()) {
-		/* FPU state will be reallocated lazily at the first use. */
-		drop_fpu(tsk);
-		free_thread_xstate(tsk);
-	} else {
-		if (!tsk_used_math(tsk)) {
-			/* kthread execs. TODO: cleanup this horror. */
-			if (WARN_ON(init_fpu(tsk)))
-				force_sig(SIGKILL, tsk);
-			user_fpu_begin();
-		}
-		restore_init_xstate();
-	}
+	fpu__clear(&tsk->thread.fpu);
 }
 
 static void hard_disable_TSC(void)

arch/x86/kernel/process_32.c

@@ -39,8 +39,7 @@
 #include <asm/pgtable.h>
 #include <asm/ldt.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/desc.h>
 #ifdef CONFIG_MATH_EMULATION
 #include <asm/math_emu.h>
@@ -242,14 +241,16 @@ __visible __notrace_funcgraph struct task_struct *
 __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread,
-				 *next = &next_p->thread;
+			     *next = &next_p->thread;
+	struct fpu *prev_fpu = &prev->fpu;
+	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
-	fpu_switch_t fpu;
+	fpu_switch_t fpu_switch;
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
 
 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -296,7 +297,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
 	 * the GDT and LDT are properly updated, and must be
-	 * done before math_state_restore, so the TS bit is up
+	 * done before fpu__restore(), so the TS bit is up
 	 * to date.
 	 */
 	arch_end_context_switch(next_p);
@@ -319,7 +320,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
-	switch_fpu_finish(next_p, fpu);
+	switch_fpu_finish(next_fpu, fpu_switch);
 
 	this_cpu_write(current_task, next_p);
 

arch/x86/kernel/process_64.c

@@ -38,8 +38,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/mmu_context.h>
 #include <asm/prctl.h>
 #include <asm/desc.h>
@@ -274,12 +273,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread;
 	struct thread_struct *next = &next_p->thread;
+	struct fpu *prev_fpu = &prev->fpu;
+	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
 	unsigned fsindex, gsindex;
-	fpu_switch_t fpu;
+	fpu_switch_t fpu_switch;
 
-	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
 
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -299,7 +300,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Leave lazy mode, flushing any hypercalls made here.  This
 	 * must be done after loading TLS entries in the GDT but before
 	 * loading segments that might reference them, and and it must
-	 * be done before math_state_restore, so the TS bit is up to
+	 * be done before fpu__restore(), so the TS bit is up to
 	 * date.
 	 */
 	arch_end_context_switch(next_p);
@@ -391,7 +392,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
 	prev->gsindex = gsindex;
 
-	switch_fpu_finish(next_p, fpu);
+	switch_fpu_finish(next_fpu, fpu_switch);
 
 	/*
 	 * Switch the PDA and FPU contexts.

arch/x86/kernel/ptrace.c

@@ -11,7 +11,6 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/ptrace.h>
-#include <linux/regset.h>
 #include <linux/tracehook.h>
 #include <linux/user.h>
 #include <linux/elf.h>
@@ -28,8 +27,9 @@
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
 #include <asm/debugreg.h>
 #include <asm/ldt.h>
 #include <asm/desc.h>
@@ -1297,7 +1297,7 @@ static struct user_regset x86_64_regsets[] __read_mostly = {
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(struct user_i387_struct) / sizeof(long),
 		.size = sizeof(long), .align = sizeof(long),
-		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+		.active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set
 	},
 	[REGSET_XSTATE] = {
 		.core_note_type = NT_X86_XSTATE,
@@ -1338,13 +1338,13 @@ static struct user_regset x86_32_regsets[] __read_mostly = {
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(struct user_i387_ia32_struct) / sizeof(u32),
 		.size = sizeof(u32), .align = sizeof(u32),
-		.active = fpregs_active, .get = fpregs_get, .set = fpregs_set
+		.active = regset_fpregs_active, .get = fpregs_get, .set = fpregs_set
 	},
 	[REGSET_XFP] = {
 		.core_note_type = NT_PRXFPREG,
 		.n = sizeof(struct user32_fxsr_struct) / sizeof(u32),
 		.size = sizeof(u32), .align = sizeof(u32),
-		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+		.active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set
 	},
 	[REGSET_XSTATE] = {
 		.core_note_type = NT_X86_XSTATE,

arch/x86/kernel/signal.c

@@ -26,8 +26,8 @@
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
 #include <asm/vdso.h>
 #include <asm/mce.h>
 #include <asm/sighandling.h>
@@ -103,7 +103,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		get_user_ex(buf, &sc->fpstate);
 	} get_user_catch(err);
 
-	err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
+	err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32));
 
 	force_iret();
 
@@ -199,6 +199,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	unsigned long sp = regs->sp;
 	unsigned long buf_fx = 0;
 	int onsigstack = on_sig_stack(sp);
+	struct fpu *fpu = &current->thread.fpu;
 
 	/* redzone */
 	if (config_enabled(CONFIG_X86_64))
@@ -218,9 +219,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		}
 	}
 
-	if (used_math()) {
-		sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
-				     &buf_fx, &math_size);
+	if (fpu->fpstate_active) {
+		sp = fpu__alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
+					  &buf_fx, &math_size);
 		*fpstate = (void __user *)sp;
 	}
 
@@ -234,8 +235,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		return (void __user *)-1L;
 
 	/* save i387 and extended state */
-	if (used_math() &&
-	    save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0)
+	if (fpu->fpstate_active &&
+	    copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0)
 		return (void __user *)-1L;
 
 	return (void __user *)sp;
@@ -593,6 +594,22 @@ badframe:
 	return 0;
 }
 
+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);
+}
+
 static int
 setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 {
@@ -617,6 +634,7 @@ static void
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
 	bool stepping, failed;
+	struct fpu *fpu = &current->thread.fpu;
 
 	/* Are we from a system call? */
 	if (syscall_get_nr(current, regs) >= 0) {
@@ -665,8 +683,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		/*
 		 * Ensure the signal handler starts with the new fpu state.
 		 */
-		if (used_math())
-			fpu_reset_state(current);
+		if (fpu->fpstate_active)
+			fpu__clear(fpu);
 	}
 	signal_setup_done(failed, ksig, stepping);
 }

arch/x86/kernel/smpboot.c

@@ -68,8 +68,7 @@
 #include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>

arch/x86/kernel/traps.c

@@ -54,12 +54,13 @@
 #include <asm/ftrace.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/mce.h>
 #include <asm/fixmap.h>
 #include <asm/mach_traps.h>
 #include <asm/alternative.h>
+#include <asm/fpu/xstate.h>
+#include <asm/trace/mpx.h>
 #include <asm/mpx.h>
 
 #ifdef CONFIG_X86_64
@@ -371,10 +372,8 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 
 dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 {
-	struct task_struct *tsk = current;
-	struct xsave_struct *xsave_buf;
 	enum ctx_state prev_state;
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
 	siginfo_t *info;
 
 	prev_state = exception_enter();
@@ -393,15 +392,15 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 
 	/*
 	 * We need to look at BNDSTATUS to resolve this exception.
-	 * It is not directly accessible, though, so we need to
-	 * do an xsave and then pull it out of the xsave buffer.
+	 * A NULL here might mean that it is in its 'init state',
+	 * which is all zeros which indicates MPX was not
+	 * responsible for the exception.
 	 */
-	fpu_save_init(&tsk->thread.fpu);
-	xsave_buf = &(tsk->thread.fpu.state->xsave);
-	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		goto exit_trap;
 
+	trace_bounds_exception_mpx(bndcsr);
 	/*
 	 * The error code field of the BNDSTATUS register communicates status
 	 * information of a bound range exception #BR or operation involving
@@ -409,11 +408,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	 */
 	switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
 	case 2:	/* Bound directory has invalid entry. */
-		if (mpx_handle_bd_fault(xsave_buf))
+		if (mpx_handle_bd_fault())
 			goto exit_trap;
 		break; /* Success, it was handled */
 	case 1: /* Bound violation. */
-		info = mpx_generate_siginfo(regs, xsave_buf);
+		info = mpx_generate_siginfo(regs);
 		if (IS_ERR(info)) {
 			/*
 			 * We failed to decode the MPX instruction.  Act as if
@@ -709,8 +708,8 @@ NOKPROBE_SYMBOL(do_debug);
 static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 {
 	struct task_struct *task = current;
+	struct fpu *fpu = &task->thread.fpu;
 	siginfo_t info;
-	unsigned short err;
 	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
 						"simd exception";
 
@@ -718,8 +717,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 		return;
 	conditional_sti(regs);
 
-	if (!user_mode(regs))
-	{
+	if (!user_mode(regs)) {
 		if (!fixup_exception(regs)) {
 			task->thread.error_code = error_code;
 			task->thread.trap_nr = trapnr;
@@ -731,62 +729,20 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	/*
 	 * Save the info for the exception handler and clear the error.
 	 */
-	unlazy_fpu(task);
-	task->thread.trap_nr = trapnr;
+	fpu__save(fpu);
+
+	task->thread.trap_nr	= trapnr;
 	task->thread.error_code = error_code;
-	info.si_signo = SIGFPE;
-	info.si_errno = 0;
-	info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
-	if (trapnr == X86_TRAP_MF) {
-		unsigned short cwd, swd;
-		/*
-		 * (~cwd & swd) will mask out exceptions that are not set to unmasked
-		 * status.  0x3f is the exception bits in these regs, 0x200 is the
-		 * C1 reg you need in case of a stack fault, 0x040 is the stack
-		 * fault bit.  We should only be taking one exception at a time,
-		 * so if this combination doesn't produce any single exception,
-		 * then we have a bad program that isn't synchronizing its FPU usage
-		 * and it will suffer the consequences since we won't be able to
-		 * fully reproduce the context of the exception
-		 */
-		cwd = get_fpu_cwd(task);
-		swd = get_fpu_swd(task);
+	info.si_signo		= SIGFPE;
+	info.si_errno		= 0;
+	info.si_addr		= (void __user *)uprobe_get_trap_addr(regs);
 
-		err = swd & ~cwd;
-	} else {
-		/*
-		 * The SIMD FPU exceptions are handled a little differently, as there
-		 * is only a single status/control register.  Thus, to determine which
-		 * unmasked exception was caught we must mask the exception mask bits
-		 * at 0x1f80, and then use these to mask the exception bits at 0x3f.
-		 */
-		unsigned short mxcsr = get_fpu_mxcsr(task);
-		err = ~(mxcsr >> 7) & mxcsr;
-	}
+	info.si_code = fpu__exception_code(fpu, trapnr);
 
-	if (err & 0x001) {	/* Invalid op */
-		/*
-		 * swd & 0x240 == 0x040: Stack Underflow
-		 * swd & 0x240 == 0x240: Stack Overflow
-		 * User must clear the SF bit (0x40) if set
-		 */
-		info.si_code = FPE_FLTINV;
-	} else if (err & 0x004) { /* Divide by Zero */
-		info.si_code = FPE_FLTDIV;
-	} else if (err & 0x008) { /* Overflow */
-		info.si_code = FPE_FLTOVF;
-	} else if (err & 0x012) { /* Denormal, Underflow */
-		info.si_code = FPE_FLTUND;
-	} else if (err & 0x020) { /* Precision */
-		info.si_code = FPE_FLTRES;
-	} else {
-		/*
-		 * If we're using IRQ 13, or supposedly even some trap
-		 * X86_TRAP_MF implementations, it's possible
-		 * we get a spurious trap, which is not an error.
-		 */
+	/* Retry when we get spurious exceptions: */
+	if (!info.si_code)
 		return;
-	}
+
 	force_sig_info(SIGFPE, &info, task);
 }
 
@@ -827,48 +783,6 @@ asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void)
 {
 }
 
-/*
- * 'math_state_restore()' saves the current math information in the
- * old math state array, and gets the new ones from the current task
- *
- * Careful.. There are problems with IBM-designed IRQ13 behaviour.
- * Don't touch unless you *really* know how it works.
- *
- * Must be called with kernel preemption disabled (eg with local
- * local interrupts as in the case of do_device_not_available).
- */
-void math_state_restore(void)
-{
-	struct task_struct *tsk = current;
-
-	if (!tsk_used_math(tsk)) {
-		local_irq_enable();
-		/*
-		 * does a slab alloc which can sleep
-		 */
-		if (init_fpu(tsk)) {
-			/*
-			 * ran out of memory!
-			 */
-			do_group_exit(SIGKILL);
-			return;
-		}
-		local_irq_disable();
-	}
-
-	/* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */
-	kernel_fpu_disable();
-	__thread_fpu_begin(tsk);
-	if (unlikely(restore_fpu_checking(tsk))) {
-		fpu_reset_state(tsk);
-		force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
-	} else {
-		tsk->thread.fpu_counter++;
-	}
-	kernel_fpu_enable();
-}
-EXPORT_SYMBOL_GPL(math_state_restore);
-
 dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
@@ -889,7 +803,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 		return;
 	}
 #endif
-	math_state_restore(); /* interrupts still off */
+	fpu__restore(&current->thread.fpu); /* interrupts still off */
 #ifdef CONFIG_X86_32
 	conditional_sti(regs);
 #endif

arch/x86/kernel/uprobes.c

@@ -29,6 +29,7 @@
 #include <linux/kdebug.h>
 #include <asm/processor.h>
 #include <asm/insn.h>
+#include <asm/mmu_context.h>
 
 /* Post-execution fixups. */
 
@@ -312,11 +313,6 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 }
 
 #ifdef CONFIG_X86_64
-static inline bool is_64bit_mm(struct mm_struct *mm)
-{
-	return	!config_enabled(CONFIG_IA32_EMULATION) ||
-		!(mm->context.ia32_compat == TIF_IA32);
-}
 /*
  * If arch_uprobe->insn doesn't use rip-relative addressing, return
  * immediately.  Otherwise, rewrite the instruction so that it accesses
@@ -497,10 +493,6 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	}
 }
 #else /* 32-bit: */
-static inline bool is_64bit_mm(struct mm_struct *mm)
-{
-	return false;
-}
 /*
  * No RIP-relative addressing on 32-bit
  */

arch/x86/kernel/xsave.c

@@ -1,724 +0,0 @@
-/*
- * xsave/xrstor support.
- *
- * Author: Suresh Siddha <suresh.b.siddha@intel.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/bootmem.h>
-#include <linux/compat.h>
-#include <linux/cpu.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
-#include <asm/sigframe.h>
-#include <asm/tlbflush.h>
-#include <asm/xcr.h>
-
-/*
- * Supported feature mask by the CPU and the kernel.
- */
-u64 pcntxt_mask;
-
-/*
- * Represents init state for the supported extended state.
- */
-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;
-static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8];
-static unsigned int xstate_features;
-
-/*
- * If a processor implementation discern that a processor state component is
- * in its initialized state it may modify the corresponding bit in the
- * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory
- * layout in the case of xsaveopt. While presenting the xstate information to
- * the user, we always ensure that the memory layout of a feature will be in
- * the init state if the corresponding header bit is zero. This is to ensure
- * that the user doesn't see some stale state in the memory layout during
- * signal handling, debugging etc.
- */
-void __sanitize_i387_state(struct task_struct *tsk)
-{
-	struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
-	int feature_bit = 0x2;
-	u64 xstate_bv;
-
-	if (!fx)
-		return;
-
-	xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
-
-	/*
-	 * None of the feature bits are in init state. So nothing else
-	 * to do for us, as the memory layout is up to date.
-	 */
-	if ((xstate_bv & pcntxt_mask) == pcntxt_mask)
-		return;
-
-	/*
-	 * FP is in init state
-	 */
-	if (!(xstate_bv & XSTATE_FP)) {
-		fx->cwd = 0x37f;
-		fx->swd = 0;
-		fx->twd = 0;
-		fx->fop = 0;
-		fx->rip = 0;
-		fx->rdp = 0;
-		memset(&fx->st_space[0], 0, 128);
-	}
-
-	/*
-	 * SSE is in init state
-	 */
-	if (!(xstate_bv & XSTATE_SSE))
-		memset(&fx->xmm_space[0], 0, 256);
-
-	xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2;
-
-	/*
-	 * Update all the other memory layouts for which the corresponding
-	 * header bit is in the init state.
-	 */
-	while (xstate_bv) {
-		if (xstate_bv & 0x1) {
-			int offset = xstate_offsets[feature_bit];
-			int size = xstate_sizes[feature_bit];
-
-			memcpy(((void *) fx) + offset,
-			       ((void *) init_xstate_buf) + offset,
-			       size);
-		}
-
-		xstate_bv >>= 1;
-		feature_bit++;
-	}
-}
-
-/*
- * Check for the presence of extended state information in the
- * user fpstate pointer in the sigcontext.
- */
-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;
-
-	if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
-		return -1;
-
-	/* 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 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 (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
-	    || magic2 != FP_XSTATE_MAGIC2)
-		return -1;
-
-	return 0;
-}
-
-/*
- * 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;
-
-		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 xsave_struct __user *x = buf;
-	struct _fpx_sw_bytes *sw_bytes;
-	u32 xstate_bv;
-	int err;
-
-	/* 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));
-
-	if (!use_xsave())
-		return err;
-
-	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
-
-	/*
-	 * 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);
-
-	/*
-	 * 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;
-
-	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 (!static_cpu_has(X86_FEATURE_FPU))
-		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);
-	} else {
-		sanitize_i387_state(tsk);
-		if (__copy_to_user(buf_fx, xsave, xstate_size))
-			return -1;
-	}
-
-	/* Save the fsave header for the 32-bit frames. */
-	if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
-		return -1;
-
-	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
-		return -1;
-
-	return 0;
-}
-
-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;
-
-	if (use_xsave()) {
-		/* These bits must be zero. */
-		memset(xsave_hdr->reserved, 0, 48);
-
-		/*
-		 * Init the state that is not present in the memory
-		 * layout and not enabled by the OS.
-		 */
-		if (fx_only)
-			xsave_hdr->xstate_bv = XSTATE_FPSSE;
-		else
-			xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
-	}
-
-	if (use_fxsr()) {
-		/*
-		 * mscsr reserved bits must be masked to zero for security
-		 * reasons.
-		 */
-		xsave->i387.mxcsr &= mxcsr_feature_mask;
-
-		convert_to_fxsr(tsk, ia32_env);
-	}
-}
-
-/*
- * Restore the extended state if present. Otherwise, restore the FP/SSE state.
- */
-static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
-{
-	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_user(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_user(buf);
-	} else
-		return frstor_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 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) {
-		fpu_reset_state(tsk);
-		return 0;
-	}
-
-	if (!access_ok(VERIFY_READ, buf, size))
-		return -EACCES;
-
-	if (!used_math() && init_fpu(tsk))
-		return -1;
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_set(current, NULL,
-				       0, sizeof(struct user_i387_ia32_struct),
-				       NULL, buf) != 0;
-
-	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 fpu *fpu = &tsk->thread.fpu;
-		struct user_i387_ia32_struct env;
-		int err = 0;
-
-		/*
-		 * Drop the current fpu which clears used_math(). This ensures
-		 * that any context-switch during the copy of the new state,
-		 * avoids the intermediate state from getting restored/saved.
-		 * Thus avoiding the new restored state from getting corrupted.
-		 * We will be ready to restore/save the state only after
-		 * set_used_math() is again set.
-		 */
-		drop_fpu(tsk);
-
-		if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
-		    __copy_from_user(&env, buf, sizeof(env))) {
-			fpu_finit(fpu);
-			err = -1;
-		} else {
-			sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
-		}
-
-		set_used_math();
-		if (use_eager_fpu()) {
-			preempt_disable();
-			math_state_restore();
-			preempt_enable();
-		}
-
-		return err;
-	} else {
-		/*
-		 * For 64-bit frames and 32-bit fsave frames, restore the user
-		 * state to the registers directly (with exceptions handled).
-		 */
-		user_fpu_begin();
-		if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
-			fpu_reset_state(tsk);
-			return -1;
-		}
-	}
-
-	return 0;
-}
-
-/*
- * Prepare the SW reserved portion of the fxsave memory layout, indicating
- * the presence of the extended state information in the memory layout
- * pointed by the fpstate pointer in the sigcontext.
- * This will be saved when ever the FP and extended state context is
- * saved on the user stack during the signal handler delivery to the user.
- */
-static void prepare_fx_sw_frame(void)
-{
-	int fsave_header_size = sizeof(struct i387_fsave_struct);
-	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
-
-	if (config_enabled(CONFIG_X86_32))
-		size += fsave_header_size;
-
-	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
-	fx_sw_reserved.extended_size = size;
-	fx_sw_reserved.xstate_bv = pcntxt_mask;
-	fx_sw_reserved.xstate_size = xstate_size;
-
-	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
- */
-static inline void xstate_enable(void)
-{
-	cr4_set_bits(X86_CR4_OSXSAVE);
-	xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
-}
-
-/*
- * Record the offsets and sizes of different state managed by the xsave
- * memory layout.
- */
-static void __init setup_xstate_features(void)
-{
-	int eax, ebx, ecx, edx, leaf = 0x2;
-
-	xstate_features = fls64(pcntxt_mask);
-	xstate_offsets = alloc_bootmem(xstate_features * sizeof(int));
-	xstate_sizes = alloc_bootmem(xstate_features * sizeof(int));
-
-	do {
-		cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
-
-		if (eax == 0)
-			break;
-
-		xstate_offsets[leaf] = ebx;
-		xstate_sizes[leaf] = eax;
-
-		leaf++;
-	} while (1);
-}
-
-/*
- * This function sets up offsets and sizes of all extended states in
- * xsave area. This supports both standard format and compacted format
- * of the xsave aread.
- *
- * Input: void
- * Output: void
- */
-void setup_xstate_comp(void)
-{
-	unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8];
-	int i;
-
-	/*
-	 * The FP xstates and SSE xstates are legacy states. They are always
-	 * in the fixed offsets in the xsave area in either compacted form
-	 * or standard form.
-	 */
-	xstate_comp_offsets[0] = 0;
-	xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space);
-
-	if (!cpu_has_xsaves) {
-		for (i = 2; i < xstate_features; i++) {
-			if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
-				xstate_comp_offsets[i] = xstate_offsets[i];
-				xstate_comp_sizes[i] = xstate_sizes[i];
-			}
-		}
-		return;
-	}
-
-	xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-
-	for (i = 2; i < xstate_features; i++) {
-		if (test_bit(i, (unsigned long *)&pcntxt_mask))
-			xstate_comp_sizes[i] = xstate_sizes[i];
-		else
-			xstate_comp_sizes[i] = 0;
-
-		if (i > 2)
-			xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
-					+ xstate_comp_sizes[i-1];
-
-	}
-}
-
-/*
- * setup the xstate image representing the init state
- */
-static void __init setup_init_fpu_buf(void)
-{
-	/*
-	 * Setup init_xstate_buf to represent the init state of
-	 * all the features managed by the xsave
-	 */
-	init_xstate_buf = alloc_bootmem_align(xstate_size,
-					      __alignof__(struct xsave_struct));
-	fx_finit(&init_xstate_buf->i387);
-
-	if (!cpu_has_xsave)
-		return;
-
-	setup_xstate_features();
-
-	if (cpu_has_xsaves) {
-		init_xstate_buf->xsave_hdr.xcomp_bv =
-						(u64)1 << 63 | pcntxt_mask;
-		init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask;
-	}
-
-	/*
-	 * Init all the features state with header_bv being 0x0
-	 */
-	xrstor_state_booting(init_xstate_buf, -1);
-	/*
-	 * Dump the init state again. This is to identify the init state
-	 * of any feature which is not represented by all zero's.
-	 */
-	xsave_state_booting(init_xstate_buf, -1);
-}
-
-static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
-static int __init eager_fpu_setup(char *s)
-{
-	if (!strcmp(s, "on"))
-		eagerfpu = ENABLE;
-	else if (!strcmp(s, "off"))
-		eagerfpu = DISABLE;
-	else if (!strcmp(s, "auto"))
-		eagerfpu = AUTO;
-	return 1;
-}
-__setup("eagerfpu=", eager_fpu_setup);
-
-
-/*
- * Calculate total size of enabled xstates in XCR0/pcntxt_mask.
- */
-static void __init init_xstate_size(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	int i;
-
-	if (!cpu_has_xsaves) {
-		cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-		xstate_size = ebx;
-		return;
-	}
-
-	xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-	for (i = 2; i < 64; i++) {
-		if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
-			cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
-			xstate_size += eax;
-		}
-	}
-}
-
-/*
- * Enable and initialize the xsave feature.
- */
-static void __init xstate_enable_boot_cpu(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
-		WARN(1, KERN_ERR "XSTATE_CPUID missing\n");
-		return;
-	}
-
-	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-	pcntxt_mask = eax + ((u64)edx << 32);
-
-	if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
-		pr_err("FP/SSE not shown under xsave features 0x%llx\n",
-		       pcntxt_mask);
-		BUG();
-	}
-
-	/*
-	 * Support only the state known to OS.
-	 */
-	pcntxt_mask = pcntxt_mask & XCNTXT_MASK;
-
-	xstate_enable();
-
-	/*
-	 * Recompute the context size for enabled features
-	 */
-	init_xstate_size();
-
-	update_regset_xstate_info(xstate_size, pcntxt_mask);
-	prepare_fx_sw_frame();
-	setup_init_fpu_buf();
-
-	/* Auto enable eagerfpu for xsaveopt */
-	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
-		eagerfpu = ENABLE;
-
-	if (pcntxt_mask & XSTATE_EAGER) {
-		if (eagerfpu == DISABLE) {
-			pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n",
-					pcntxt_mask & XSTATE_EAGER);
-			pcntxt_mask &= ~XSTATE_EAGER;
-		} else {
-			eagerfpu = ENABLE;
-		}
-	}
-
-	pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n",
-		pcntxt_mask, xstate_size,
-		cpu_has_xsaves ? "compacted form" : "standard form");
-}
-
-/*
- * For the very first instance, this calls xstate_enable_boot_cpu();
- * for all subsequent instances, this calls xstate_enable().
- *
- * This is somewhat obfuscated due to the lack of powerful enough
- * overrides for the section checks.
- */
-void xsave_init(void)
-{
-	static __refdata void (*next_func)(void) = xstate_enable_boot_cpu;
-	void (*this_func)(void);
-
-	if (!cpu_has_xsave)
-		return;
-
-	this_func = next_func;
-	next_func = xstate_enable;
-	this_func();
-}
-
-/*
- * setup_init_fpu_buf() is __init and it is OK to call it here because
- * init_xstate_buf will be unset only once during boot.
- */
-void __init_refok eager_fpu_init(void)
-{
-	WARN_ON(used_math());
-	current_thread_info()->status = 0;
-
-	if (eagerfpu == ENABLE)
-		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
-
-	if (!cpu_has_eager_fpu) {
-		stts();
-		return;
-	}
-
-	if (!init_xstate_buf)
-		setup_init_fpu_buf();
-}
-
-/*
- * Given the xsave area and a state inside, this function returns the
- * address of the state.
- *
- * This is the API that is called to get xstate address in either
- * standard format or compacted format of xsave area.
- *
- * Inputs:
- *	xsave: base address of the xsave area;
- *	xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE,
- *	etc.)
- * Output:
- *	address of the state in the xsave area.
- */
-void *get_xsave_addr(struct xsave_struct *xsave, int xstate)
-{
-	int feature = fls64(xstate) - 1;
-	if (!test_bit(feature, (unsigned long *)&pcntxt_mask))
-		return NULL;
-
-	return (void *)xsave + xstate_comp_offsets[feature];
-}
-EXPORT_SYMBOL_GPL(get_xsave_addr);

arch/x86/kvm/cpuid.c

@@ -16,10 +16,8 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
-#include <asm/i387.h> /* For use_eager_fpu.  Ugh! */
-#include <asm/fpu-internal.h> /* For use_eager_fpu.  Ugh! */
 #include <asm/user.h>
-#include <asm/xsave.h>
+#include <asm/fpu/xstate.h>
 #include "cpuid.h"
 #include "lapic.h"
 #include "mmu.h"

arch/x86/kvm/vmx.c

@@ -40,8 +40,7 @@
 #include <asm/vmx.h>
 #include <asm/virtext.h>
 #include <asm/mce.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
+#include <asm/fpu/internal.h>
 #include <asm/perf_event.h>
 #include <asm/debugreg.h>
 #include <asm/kexec.h>
@@ -1883,7 +1882,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 	 * If the FPU is not active (through the host task or
 	 * the guest vcpu), then restore the cr0.TS bit.
 	 */
-	if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
+	if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded)
 		stts();
 	load_gdt(this_cpu_ptr(&host_gdt));
 }

arch/x86/kvm/x86.c

@@ -59,9 +59,8 @@
 #include <asm/desc.h>
 #include <asm/mtrr.h>
 #include <asm/mce.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h> /* Ugh! */
-#include <asm/xcr.h>
+#include <linux/kernel_stat.h>
+#include <asm/fpu/internal.h> /* Ugh! */
 #include <asm/pvclock.h>
 #include <asm/div64.h>
 
@@ -3194,8 +3193,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 
 static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 {
-	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
-	u64 xstate_bv = xsave->xsave_hdr.xstate_bv;
+	struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
+	u64 xstate_bv = xsave->header.xfeatures;
 	u64 valid;
 
 	/*
@@ -3230,7 +3229,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 
 static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 {
-	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+	struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
 	u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
 	u64 valid;
 
@@ -3241,9 +3240,9 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 	memcpy(xsave, src, XSAVE_HDR_OFFSET);
 
 	/* Set XSTATE_BV and possibly XCOMP_BV.  */
-	xsave->xsave_hdr.xstate_bv = xstate_bv;
+	xsave->header.xfeatures = xstate_bv;
 	if (cpu_has_xsaves)
-		xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
+		xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
 	 * Copy each region from the non-compacted offset to the
@@ -3275,8 +3274,8 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 		fill_xsave((u8 *) guest_xsave->region, vcpu);
 	} else {
 		memcpy(guest_xsave->region,
-			&vcpu->arch.guest_fpu.state->fxsave,
-			sizeof(struct i387_fxsave_struct));
+			&vcpu->arch.guest_fpu.state.fxsave,
+			sizeof(struct fxregs_state));
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
 			XSTATE_FPSSE;
 	}
@@ -3300,8 +3299,8 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 	} else {
 		if (xstate_bv & ~XSTATE_FPSSE)
 			return -EINVAL;
-		memcpy(&vcpu->arch.guest_fpu.state->fxsave,
-			guest_xsave->region, sizeof(struct i387_fxsave_struct));
+		memcpy(&vcpu->arch.guest_fpu.state.fxsave,
+			guest_xsave->region, sizeof(struct fxregs_state));
 	}
 	return 0;
 }
@@ -6597,11 +6596,11 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
+	struct fpu *fpu = &current->thread.fpu;
 	int r;
 	sigset_t sigsaved;
 
-	if (!tsk_used_math(current) && init_fpu(current))
-		return -ENOMEM;
+	fpu__activate_curr(fpu);
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
@@ -6971,8 +6970,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	struct i387_fxsave_struct *fxsave =
-			&vcpu->arch.guest_fpu.state->fxsave;
+	struct fxregs_state *fxsave =
+			&vcpu->arch.guest_fpu.state.fxsave;
 
 	memcpy(fpu->fpr, fxsave->st_space, 128);
 	fpu->fcw = fxsave->cwd;
@@ -6988,8 +6987,8 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	struct i387_fxsave_struct *fxsave =
-			&vcpu->arch.guest_fpu.state->fxsave;
+	struct fxregs_state *fxsave =
+			&vcpu->arch.guest_fpu.state.fxsave;
 
 	memcpy(fxsave->st_space, fpu->fpr, 128);
 	fxsave->cwd = fpu->fcw;
@@ -7003,17 +7002,11 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	return 0;
 }
 
-int fx_init(struct kvm_vcpu *vcpu)
+static void fx_init(struct kvm_vcpu *vcpu)
 {
-	int err;
-
-	err = fpu_alloc(&vcpu->arch.guest_fpu);
-	if (err)
-		return err;
-
-	fpu_finit(&vcpu->arch.guest_fpu);
+	fpstate_init(&vcpu->arch.guest_fpu.state);
 	if (cpu_has_xsaves)
-		vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv =
+		vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv =
 			host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
@@ -7022,14 +7015,6 @@ int fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.xcr0 = XSTATE_FP;
 
 	vcpu->arch.cr0 |= X86_CR0_ET;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(fx_init);
-
-static void fx_free(struct kvm_vcpu *vcpu)
-{
-	fpu_free(&vcpu->arch.guest_fpu);
 }
 
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
@@ -7045,7 +7030,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
-	fpu_restore_checking(&vcpu->arch.guest_fpu);
+	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
 	trace_kvm_fpu(1);
 }
 
@@ -7057,7 +7042,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 		return;
 
 	vcpu->guest_fpu_loaded = 0;
-	fpu_save_init(&vcpu->arch.guest_fpu);
+	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
 	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
 	if (!vcpu->arch.eager_fpu)
@@ -7071,7 +7056,6 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	kvmclock_reset(vcpu);
 
 	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
-	fx_free(vcpu);
 	kvm_x86_ops->vcpu_free(vcpu);
 }
 
@@ -7137,7 +7121,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_mmu_unload(vcpu);
 	vcpu_put(vcpu);
 
-	fx_free(vcpu);
 	kvm_x86_ops->vcpu_free(vcpu);
 }
 
@@ -7363,9 +7346,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		goto fail_free_mce_banks;
 	}
 
-	r = fx_init(vcpu);
-	if (r)
-		goto fail_free_wbinvd_dirty_mask;
+	fx_init(vcpu);
 
 	vcpu->arch.ia32_tsc_adjust_msr = 0x0;
 	vcpu->arch.pv_time_enabled = false;
@@ -7379,8 +7360,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	kvm_pmu_init(vcpu);
 
 	return 0;
-fail_free_wbinvd_dirty_mask:
-	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
+
 fail_free_mce_banks:
 	kfree(vcpu->arch.mce_banks);
 fail_free_lapic:

arch/x86/lguest/boot.c

@@ -70,7 +70,7 @@
 #include <asm/e820.h>
 #include <asm/mce.h>
 #include <asm/io.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/stackprotector.h>
 #include <asm/reboot.h>		/* for struct machine_ops */
 #include <asm/kvm_para.h>

arch/x86/lib/mmx_32.c

@@ -22,7 +22,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/asm.h>
 
 void *_mmx_memcpy(void *to, const void *from, size_t len)

arch/x86/math-emu/fpu_aux.c

@@ -30,7 +30,7 @@ static void fclex(void)
 }
 
 /* Needs to be externally visible */
-void finit_soft_fpu(struct i387_soft_struct *soft)
+void fpstate_init_soft(struct swregs_state *soft)
 {
 	struct address *oaddr, *iaddr;
 	memset(soft, 0, sizeof(*soft));
@@ -52,7 +52,7 @@ void finit_soft_fpu(struct i387_soft_struct *soft)
 
 void finit(void)
 {
-	finit_soft_fpu(&current->thread.fpu.state->soft);
+	fpstate_init_soft(&current->thread.fpu.state.soft);
 }
 
 /*

arch/x86/math-emu/fpu_entry.c

@@ -31,7 +31,7 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/user.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
 
 #include "fpu_system.h"
 #include "fpu_emu.h"
@@ -147,13 +147,9 @@ void math_emulate(struct math_emu_info *info)
 	unsigned long code_base = 0;
 	unsigned long code_limit = 0;	/* Initialized to stop compiler warnings */
 	struct desc_struct code_descriptor;
+	struct fpu *fpu = &current->thread.fpu;
 
-	if (!used_math()) {
-		if (init_fpu(current)) {
-			do_group_exit(SIGKILL);
-			return;
-		}
-	}
+	fpu__activate_curr(fpu);
 
 #ifdef RE_ENTRANT_CHECKING
 	if (emulating) {
@@ -673,7 +669,7 @@ void math_abort(struct math_emu_info *info, unsigned int signal)
 #endif /* PARANOID */
 }
 
-#define S387 ((struct i387_soft_struct *)s387)
+#define S387 ((struct swregs_state *)s387)
 #define sstatus_word() \
   ((S387->swd & ~SW_Top & 0xffff) | ((S387->ftop << SW_Top_Shift) & SW_Top))
 
@@ -682,14 +678,14 @@ int fpregs_soft_set(struct task_struct *target,
 		    unsigned int pos, unsigned int count,
 		    const void *kbuf, const void __user *ubuf)
 {
-	struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+	struct swregs_state *s387 = &target->thread.fpu.state.soft;
 	void *space = s387->st_space;
 	int ret;
 	int offset, other, i, tags, regnr, tag, newtop;
 
 	RE_ENTRANT_CHECK_OFF;
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, s387, 0,
-				 offsetof(struct i387_soft_struct, st_space));
+				 offsetof(struct swregs_state, st_space));
 	RE_ENTRANT_CHECK_ON;
 
 	if (ret)
@@ -734,7 +730,7 @@ int fpregs_soft_get(struct task_struct *target,
 		    unsigned int pos, unsigned int count,
 		    void *kbuf, void __user *ubuf)
 {
-	struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+	struct swregs_state *s387 = &target->thread.fpu.state.soft;
 	const void *space = s387->st_space;
 	int ret;
 	int offset = (S387->ftop & 7) * 10, other = 80 - offset;
@@ -752,7 +748,7 @@ int fpregs_soft_get(struct task_struct *target,
 #endif /* PECULIAR_486 */
 
 	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, s387, 0,
-				  offsetof(struct i387_soft_struct, st_space));
+				  offsetof(struct swregs_state, st_space));
 
 	/* Copy all registers in stack order. */
 	if (!ret)

arch/x86/math-emu/fpu_system.h

@@ -31,7 +31,7 @@
 #define SEG_EXPAND_DOWN(s)	(((s).b & ((1 << 11) | (1 << 10))) \
 				 == (1 << 10))
 
-#define I387			(current->thread.fpu.state)
+#define I387			(&current->thread.fpu.state)
 #define FPU_info		(I387->soft.info)
 
 #define FPU_CS			(*(unsigned short *) &(FPU_info->regs->cs))

arch/x86/mm/mpx.c

@@ -10,13 +10,15 @@
 #include <linux/syscalls.h>
 #include <linux/sched/sysctl.h>
 
-#include <asm/i387.h>
 #include <asm/insn.h>
 #include <asm/mman.h>
 #include <asm/mmu_context.h>
 #include <asm/mpx.h>
 #include <asm/processor.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+
+#define CREATE_TRACE_POINTS
+#include <asm/trace/mpx.h>
 
 static const char *mpx_mapping_name(struct vm_area_struct *vma)
 {
@@ -32,6 +34,22 @@ static int is_mpx_vma(struct vm_area_struct *vma)
 	return (vma->vm_ops == &mpx_vma_ops);
 }
 
+static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
+{
+	if (is_64bit_mm(mm))
+		return MPX_BD_SIZE_BYTES_64;
+	else
+		return MPX_BD_SIZE_BYTES_32;
+}
+
+static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
+{
+	if (is_64bit_mm(mm))
+		return MPX_BT_SIZE_BYTES_64;
+	else
+		return MPX_BT_SIZE_BYTES_32;
+}
+
 /*
  * This is really a simplified "vm_mmap". it only handles MPX
  * bounds tables (the bounds directory is user-allocated).
@@ -47,8 +65,8 @@ static unsigned long mpx_mmap(unsigned long len)
 	vm_flags_t vm_flags;
 	struct vm_area_struct *vma;
 
-	/* Only bounds table and bounds directory can be allocated here */
-	if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES)
+	/* Only bounds table can be allocated here */
+	if (len != mpx_bt_size_bytes(mm))
 		return -EINVAL;
 
 	down_write(&mm->mmap_sem);
@@ -272,10 +290,9 @@ bad_opcode:
  *
  * The caller is expected to kfree() the returned siginfo_t.
  */
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-				struct xsave_struct *xsave_buf)
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 {
-	struct bndreg *bndregs, *bndreg;
+	const struct bndreg *bndregs, *bndreg;
 	siginfo_t *info = NULL;
 	struct insn insn;
 	uint8_t bndregno;
@@ -295,8 +312,8 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 		err = -EINVAL;
 		goto err_out;
 	}
-	/* get the bndregs _area_ of the xsave structure */
-	bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS);
+	/* get bndregs field from current task's xsave area */
+	bndregs = get_xsave_field_ptr(XSTATE_BNDREGS);
 	if (!bndregs) {
 		err = -EINVAL;
 		goto err_out;
@@ -334,6 +351,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 		err = -EINVAL;
 		goto err_out;
 	}
+	trace_mpx_bounds_register_exception(info->si_addr, bndreg);
 	return info;
 err_out:
 	/* info might be NULL, but kfree() handles that */
@@ -341,25 +359,18 @@ err_out:
 	return ERR_PTR(err);
 }
 
-static __user void *task_get_bounds_dir(struct task_struct *tsk)
+static __user void *mpx_get_bounds_dir(void)
 {
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
 
 	if (!cpu_feature_enabled(X86_FEATURE_MPX))
 		return MPX_INVALID_BOUNDS_DIR;
 
-	/*
-	 * 32-bit binaries on 64-bit kernels are currently
-	 * unsupported.
-	 */
-	if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32))
-		return MPX_INVALID_BOUNDS_DIR;
 	/*
 	 * The bounds directory pointer is stored in a register
 	 * only accessible if we first do an xsave.
 	 */
-	fpu_save_init(&tsk->thread.fpu);
-	bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		return MPX_INVALID_BOUNDS_DIR;
 
@@ -378,10 +389,10 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk)
 		(bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
 }
 
-int mpx_enable_management(struct task_struct *tsk)
+int mpx_enable_management(void)
 {
 	void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
-	struct mm_struct *mm = tsk->mm;
+	struct mm_struct *mm = current->mm;
 	int ret = 0;
 
 	/*
@@ -390,11 +401,12 @@ int mpx_enable_management(struct task_struct *tsk)
 	 * directory into XSAVE/XRSTOR Save Area and enable MPX through
 	 * XRSTOR instruction.
 	 *
-	 * fpu_xsave() is expected to be very expensive. Storing the bounds
-	 * directory here means that we do not have to do xsave in the unmap
-	 * path; we can just use mm->bd_addr instead.
+	 * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
+	 * expected to be relatively expensive. Storing the bounds
+	 * directory here means that we do not have to do xsave in the
+	 * unmap path; we can just use mm->bd_addr instead.
 	 */
-	bd_base = task_get_bounds_dir(tsk);
+	bd_base = mpx_get_bounds_dir();
 	down_write(&mm->mmap_sem);
 	mm->bd_addr = bd_base;
 	if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
@@ -404,7 +416,7 @@ int mpx_enable_management(struct task_struct *tsk)
 	return ret;
 }
 
-int mpx_disable_management(struct task_struct *tsk)
+int mpx_disable_management(void)
 {
 	struct mm_struct *mm = current->mm;
 
@@ -417,29 +429,59 @@ int mpx_disable_management(struct task_struct *tsk)
 	return 0;
 }
 
+static int mpx_cmpxchg_bd_entry(struct mm_struct *mm,
+		unsigned long *curval,
+		unsigned long __user *addr,
+		unsigned long old_val, unsigned long new_val)
+{
+	int ret;
+	/*
+	 * user_atomic_cmpxchg_inatomic() actually uses sizeof()
+	 * the pointer that we pass to it to figure out how much
+	 * data to cmpxchg.  We have to be careful here not to
+	 * pass a pointer to a 64-bit data type when we only want
+	 * a 32-bit copy.
+	 */
+	if (is_64bit_mm(mm)) {
+		ret = user_atomic_cmpxchg_inatomic(curval,
+				addr, old_val, new_val);
+	} else {
+		u32 uninitialized_var(curval_32);
+		u32 old_val_32 = old_val;
+		u32 new_val_32 = new_val;
+		u32 __user *addr_32 = (u32 __user *)addr;
+
+		ret = user_atomic_cmpxchg_inatomic(&curval_32,
+				addr_32, old_val_32, new_val_32);
+		*curval = curval_32;
+	}
+	return ret;
+}
+
 /*
- * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each
- * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB,
+ * With 32-bit mode, a bounds directory is 4MB, and the size of each
+ * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB,
  * and the size of each bounds table is 4MB.
  */
-static int allocate_bt(long __user *bd_entry)
+static int allocate_bt(struct mm_struct *mm, long __user *bd_entry)
 {
 	unsigned long expected_old_val = 0;
 	unsigned long actual_old_val = 0;
 	unsigned long bt_addr;
+	unsigned long bd_new_entry;
 	int ret = 0;
 
 	/*
 	 * Carve the virtual space out of userspace for the new
 	 * bounds table:
 	 */
-	bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES);
+	bt_addr = mpx_mmap(mpx_bt_size_bytes(mm));
 	if (IS_ERR((void *)bt_addr))
 		return PTR_ERR((void *)bt_addr);
 	/*
 	 * Set the valid flag (kinda like _PAGE_PRESENT in a pte)
 	 */
-	bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+	bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
 
 	/*
 	 * Go poke the address of the new bounds table in to the
@@ -452,8 +494,8 @@ static int allocate_bt(long __user *bd_entry)
 	 * mmap_sem at this point, unlike some of the other part
 	 * of the MPX code that have to pagefault_disable().
 	 */
-	ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
-					   expected_old_val, bt_addr);
+	ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,	bd_entry,
+				   expected_old_val, bd_new_entry);
 	if (ret)
 		goto out_unmap;
 
@@ -481,9 +523,10 @@ static int allocate_bt(long __user *bd_entry)
 		ret = -EINVAL;
 		goto out_unmap;
 	}
+	trace_mpx_new_bounds_table(bt_addr);
 	return 0;
 out_unmap:
-	vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES);
+	vm_munmap(bt_addr, mpx_bt_size_bytes(mm));
 	return ret;
 }
 
@@ -498,12 +541,13 @@ out_unmap:
  * bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
  * and the size of each bound table is 4MB.
  */
-static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
+static int do_mpx_bt_fault(void)
 {
 	unsigned long bd_entry, bd_base;
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
+	struct mm_struct *mm = current->mm;
 
-	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		return -EINVAL;
 	/*
@@ -520,13 +564,13 @@ static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
 	 * the directory is.
 	 */
 	if ((bd_entry < bd_base) ||
-	    (bd_entry >= bd_base + MPX_BD_SIZE_BYTES))
+	    (bd_entry >= bd_base + mpx_bd_size_bytes(mm)))
 		return -EINVAL;
 
-	return allocate_bt((long __user *)bd_entry);
+	return allocate_bt(mm, (long __user *)bd_entry);
 }
 
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+int mpx_handle_bd_fault(void)
 {
 	/*
 	 * Userspace never asked us to manage the bounds tables,
@@ -535,7 +579,7 @@ int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
 	if (!kernel_managing_mpx_tables(current->mm))
 		return -EINVAL;
 
-	if (do_mpx_bt_fault(xsave_buf)) {
+	if (do_mpx_bt_fault()) {
 		force_sig(SIGSEGV, current);
 		/*
 		 * The force_sig() is essentially "handling" this
@@ -572,29 +616,55 @@ static int mpx_resolve_fault(long __user *addr, int write)
 	return 0;
 }
 
+static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
+					     unsigned long bd_entry)
+{
+	unsigned long bt_addr = bd_entry;
+	int align_to_bytes;
+	/*
+	 * Bit 0 in a bt_entry is always the valid bit.
+	 */
+	bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG;
+	/*
+	 * Tables are naturally aligned at 8-byte boundaries
+	 * on 64-bit and 4-byte boundaries on 32-bit.  The
+	 * documentation makes it appear that the low bits
+	 * are ignored by the hardware, so we do the same.
+	 */
+	if (is_64bit_mm(mm))
+		align_to_bytes = 8;
+	else
+		align_to_bytes = 4;
+	bt_addr &= ~(align_to_bytes-1);
+	return bt_addr;
+}
+
 /*
  * Get the base of bounds tables pointed by specific bounds
  * directory entry.
  */
 static int get_bt_addr(struct mm_struct *mm,
-			long __user *bd_entry, unsigned long *bt_addr)
+			long __user *bd_entry_ptr,
+			unsigned long *bt_addr_result)
 {
 	int ret;
 	int valid_bit;
+	unsigned long bd_entry;
+	unsigned long bt_addr;
 
-	if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry)))
+	if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr)))
 		return -EFAULT;
 
 	while (1) {
 		int need_write = 0;
 
 		pagefault_disable();
-		ret = get_user(*bt_addr, bd_entry);
+		ret = get_user(bd_entry, bd_entry_ptr);
 		pagefault_enable();
 		if (!ret)
 			break;
 		if (ret == -EFAULT)
-			ret = mpx_resolve_fault(bd_entry, need_write);
+			ret = mpx_resolve_fault(bd_entry_ptr, need_write);
 		/*
 		 * If we could not resolve the fault, consider it
 		 * userspace's fault and error out.
@@ -603,8 +673,8 @@ static int get_bt_addr(struct mm_struct *mm,
 			return ret;
 	}
 
-	valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG;
-	*bt_addr &= MPX_BT_ADDR_MASK;
+	valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG;
+	bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry);
 
 	/*
 	 * When the kernel is managing bounds tables, a bounds directory
@@ -613,7 +683,7 @@ static int get_bt_addr(struct mm_struct *mm,
 	 * data in the address field, we know something is wrong. This
 	 * -EINVAL return will cause a SIGSEGV.
 	 */
-	if (!valid_bit && *bt_addr)
+	if (!valid_bit && bt_addr)
 		return -EINVAL;
 	/*
 	 * Do we have an completely zeroed bt entry?  That is OK.  It
@@ -624,19 +694,100 @@ static int get_bt_addr(struct mm_struct *mm,
 	if (!valid_bit)
 		return -ENOENT;
 
+	*bt_addr_result = bt_addr;
 	return 0;
 }
 
+static inline int bt_entry_size_bytes(struct mm_struct *mm)
+{
+	if (is_64bit_mm(mm))
+		return MPX_BT_ENTRY_BYTES_64;
+	else
+		return MPX_BT_ENTRY_BYTES_32;
+}
+
+/*
+ * Take a virtual address and turns it in to the offset in bytes
+ * inside of the bounds table where the bounds table entry
+ * controlling 'addr' can be found.
+ */
+static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm,
+		unsigned long addr)
+{
+	unsigned long bt_table_nr_entries;
+	unsigned long offset = addr;
+
+	if (is_64bit_mm(mm)) {
+		/* Bottom 3 bits are ignored on 64-bit */
+		offset >>= 3;
+		bt_table_nr_entries = MPX_BT_NR_ENTRIES_64;
+	} else {
+		/* Bottom 2 bits are ignored on 32-bit */
+		offset >>= 2;
+		bt_table_nr_entries = MPX_BT_NR_ENTRIES_32;
+	}
+	/*
+	 * We know the size of the table in to which we are
+	 * indexing, and we have eliminated all the low bits
+	 * which are ignored for indexing.
+	 *
+	 * Mask out all the high bits which we do not need
+	 * to index in to the table.  Note that the tables
+	 * are always powers of two so this gives us a proper
+	 * mask.
+	 */
+	offset &= (bt_table_nr_entries-1);
+	/*
+	 * We now have an entry offset in terms of *entries* in
+	 * the table.  We need to scale it back up to bytes.
+	 */
+	offset *= bt_entry_size_bytes(mm);
+	return offset;
+}
+
+/*
+ * How much virtual address space does a single bounds
+ * directory entry cover?
+ *
+ * Note, we need a long long because 4GB doesn't fit in
+ * to a long on 32-bit.
+ */
+static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
+{
+	unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
+	if (is_64bit_mm(mm))
+		return virt_space / MPX_BD_NR_ENTRIES_64;
+	else
+		return virt_space / MPX_BD_NR_ENTRIES_32;
+}
+
 /*
  * Free the backing physical pages of bounds table 'bt_addr'.
  * Assume start...end is within that bounds table.
  */
-static int zap_bt_entries(struct mm_struct *mm,
+static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
 		unsigned long bt_addr,
-		unsigned long start, unsigned long end)
+		unsigned long start_mapping, unsigned long end_mapping)
 {
 	struct vm_area_struct *vma;
 	unsigned long addr, len;
+	unsigned long start;
+	unsigned long end;
+
+	/*
+	 * if we 'end' on a boundary, the offset will be 0 which
+	 * is not what we want.  Back it up a byte to get the
+	 * last bt entry.  Then once we have the entry itself,
+	 * move 'end' back up by the table entry size.
+	 */
+	start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping);
+	end   = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1);
+	/*
+	 * Move end back up by one entry.  Among other things
+	 * this ensures that it remains page-aligned and does
+	 * not screw up zap_page_range()
+	 */
+	end += bt_entry_size_bytes(mm);
 
 	/*
 	 * Find the first overlapping vma. If vma->vm_start > start, there
@@ -648,7 +799,7 @@ static int zap_bt_entries(struct mm_struct *mm,
 		return -EINVAL;
 
 	/*
-	 * A NUMA policy on a VM_MPX VMA could cause this bouds table to
+	 * A NUMA policy on a VM_MPX VMA could cause this bounds table to
 	 * be split. So we need to look across the entire 'start -> end'
 	 * range of this bounds table, find all of the VM_MPX VMAs, and
 	 * zap only those.
@@ -666,27 +817,65 @@ static int zap_bt_entries(struct mm_struct *mm,
 
 		len = min(vma->vm_end, end) - addr;
 		zap_page_range(vma, addr, len, NULL);
+		trace_mpx_unmap_zap(addr, addr+len);
 
 		vma = vma->vm_next;
 		addr = vma->vm_start;
 	}
-
 	return 0;
 }
 
-static int unmap_single_bt(struct mm_struct *mm,
+static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm,
+		unsigned long addr)
+{
+	/*
+	 * There are several ways to derive the bd offsets.  We
+	 * use the following approach here:
+	 * 1. We know the size of the virtual address space
+	 * 2. We know the number of entries in a bounds table
+	 * 3. We know that each entry covers a fixed amount of
+	 *    virtual address space.
+	 * So, we can just divide the virtual address by the
+	 * virtual space used by one entry to determine which
+	 * entry "controls" the given virtual address.
+	 */
+	if (is_64bit_mm(mm)) {
+		int bd_entry_size = 8; /* 64-bit pointer */
+		/*
+		 * Take the 64-bit addressing hole in to account.
+		 */
+		addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1);
+		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+	} else {
+		int bd_entry_size = 4; /* 32-bit pointer */
+		/*
+		 * 32-bit has no hole so this case needs no mask
+		 */
+		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+	}
+	/*
+	 * The two return calls above are exact copies.  If we
+	 * pull out a single copy and put it in here, gcc won't
+	 * realize that we're doing a power-of-2 divide and use
+	 * shifts.  It uses a real divide.  If we put them up
+	 * there, it manages to figure it out (gcc 4.8.3).
+	 */
+}
+
+static int unmap_entire_bt(struct mm_struct *mm,
 		long __user *bd_entry, unsigned long bt_addr)
 {
 	unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
-	unsigned long actual_old_val = 0;
+	unsigned long uninitialized_var(actual_old_val);
 	int ret;
 
 	while (1) {
 		int need_write = 1;
+		unsigned long cleared_bd_entry = 0;
 
 		pagefault_disable();
-		ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
-						   expected_old_val, 0);
+		ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,
+				bd_entry, expected_old_val, cleared_bd_entry);
 		pagefault_enable();
 		if (!ret)
 			break;
@@ -705,9 +894,8 @@ static int unmap_single_bt(struct mm_struct *mm,
 	if (actual_old_val != expected_old_val) {
 		/*
 		 * Someone else raced with us to unmap the table.
-		 * There was no bounds table pointed to by the
-		 * directory, so declare success.  Somebody freed
-		 * it.
+		 * That is OK, since we were both trying to do
+		 * the same thing.  Declare success.
 		 */
 		if (!actual_old_val)
 			return 0;
@@ -720,176 +908,113 @@ static int unmap_single_bt(struct mm_struct *mm,
 		 */
 		return -EINVAL;
 	}
-
 	/*
 	 * Note, we are likely being called under do_munmap() already. To
 	 * avoid recursion, do_munmap() will check whether it comes
 	 * from one bounds table through VM_MPX flag.
 	 */
-	return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES);
+	return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm));
 }
 
-/*
- * If the bounds table pointed by bounds directory 'bd_entry' is
- * not shared, unmap this whole bounds table. Otherwise, only free
- * those backing physical pages of bounds table entries covered
- * in this virtual address region start...end.
- */
-static int unmap_shared_bt(struct mm_struct *mm,
-		long __user *bd_entry, unsigned long start,
-		unsigned long end, bool prev_shared, bool next_shared)
+static int try_unmap_single_bt(struct mm_struct *mm,
+	       unsigned long start, unsigned long end)
 {
-	unsigned long bt_addr;
-	int ret;
-
-	ret = get_bt_addr(mm, bd_entry, &bt_addr);
+	struct vm_area_struct *next;
+	struct vm_area_struct *prev;
 	/*
-	 * We could see an "error" ret for not-present bounds
-	 * tables (not really an error), or actual errors, but
-	 * stop unmapping either way.
+	 * "bta" == Bounds Table Area: the area controlled by the
+	 * bounds table that we are unmapping.
 	 */
-	if (ret)
-		return ret;
-
-	if (prev_shared && next_shared)
-		ret = zap_bt_entries(mm, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
-	else if (prev_shared)
-		ret = zap_bt_entries(mm, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
-				bt_addr+MPX_BT_SIZE_BYTES);
-	else if (next_shared)
-		ret = zap_bt_entries(mm, bt_addr, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
-	else
-		ret = unmap_single_bt(mm, bd_entry, bt_addr);
-
-	return ret;
-}
-
-/*
- * A virtual address region being munmap()ed might share bounds table
- * with adjacent VMAs. We only need to free the backing physical
- * memory of these shared bounds tables entries covered in this virtual
- * address region.
- */
-static int unmap_edge_bts(struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
+	unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1);
+	unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm);
+	unsigned long uninitialized_var(bt_addr);
+	void __user *bde_vaddr;
 	int ret;
-	long __user *bde_start, *bde_end;
-	struct vm_area_struct *prev, *next;
-	bool prev_shared = false, next_shared = false;
-
-	bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
-	bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
-
 	/*
-	 * Check whether bde_start and bde_end are shared with adjacent
-	 * VMAs.
-	 *
-	 * We already unliked the VMAs from the mm's rbtree so 'start'
+	 * We already unlinked the VMAs from the mm's rbtree so 'start'
 	 * is guaranteed to be in a hole. This gets us the first VMA
 	 * before the hole in to 'prev' and the next VMA after the hole
 	 * in to 'next'.
 	 */
 	next = find_vma_prev(mm, start, &prev);
-	if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1))
-			== bde_start)
-		prev_shared = true;
-	if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start))
-			== bde_end)
-		next_shared = true;
-
 	/*
-	 * This virtual address region being munmap()ed is only
-	 * covered by one bounds table.
-	 *
-	 * In this case, if this table is also shared with adjacent
-	 * VMAs, only part of the backing physical memory of the bounds
-	 * table need be freeed. Otherwise the whole bounds table need
-	 * be unmapped.
-	 */
-	if (bde_start == bde_end) {
-		return unmap_shared_bt(mm, bde_start, start, end,
-				prev_shared, next_shared);
+	 * Do not count other MPX bounds table VMAs as neighbors.
+	 * Although theoretically possible, we do not allow bounds
+	 * tables for bounds tables so our heads do not explode.
+	 * If we count them as neighbors here, we may end up with
+	 * lots of tables even though we have no actual table
+	 * entries in use.
+	 */
+	while (next && is_mpx_vma(next))
+		next = next->vm_next;
+	while (prev && is_mpx_vma(prev))
+		prev = prev->vm_prev;
+	/*
+	 * We know 'start' and 'end' lie within an area controlled
+	 * by a single bounds table.  See if there are any other
+	 * VMAs controlled by that bounds table.  If there are not
+	 * then we can "expand" the are we are unmapping to possibly
+	 * cover the entire table.
+	 */
+	next = find_vma_prev(mm, start, &prev);
+	if ((!prev || prev->vm_end <= bta_start_vaddr) &&
+	    (!next || next->vm_start >= bta_end_vaddr)) {
+		/*
+		 * No neighbor VMAs controlled by same bounds
+		 * table.  Try to unmap the whole thing
+		 */
+		start = bta_start_vaddr;
+		end = bta_end_vaddr;
 	}
 
+	bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start);
+	ret = get_bt_addr(mm, bde_vaddr, &bt_addr);
 	/*
-	 * If more than one bounds tables are covered in this virtual
-	 * address region being munmap()ed, we need to separately check
-	 * whether bde_start and bde_end are shared with adjacent VMAs.
+	 * No bounds table there, so nothing to unmap.
 	 */
-	ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false);
-	if (ret)
-		return ret;
-	ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared);
+	if (ret == -ENOENT) {
+		ret = 0;
+		return 0;
+	}
 	if (ret)
 		return ret;
-
-	return 0;
+	/*
+	 * We are unmapping an entire table.  Either because the
+	 * unmap that started this whole process was large enough
+	 * to cover an entire table, or that the unmap was small
+	 * but was the area covered by a bounds table.
+	 */
+	if ((start == bta_start_vaddr) &&
+	    (end == bta_end_vaddr))
+		return unmap_entire_bt(mm, bde_vaddr, bt_addr);
+	return zap_bt_entries_mapping(mm, bt_addr, start, end);
 }
 
 static int mpx_unmap_tables(struct mm_struct *mm,
 		unsigned long start, unsigned long end)
 {
-	int ret;
-	long __user *bd_entry, *bde_start, *bde_end;
-	unsigned long bt_addr;
-
-	/*
-	 * "Edge" bounds tables are those which are being used by the region
-	 * (start -> end), but that may be shared with adjacent areas.  If they
-	 * turn out to be completely unshared, they will be freed.  If they are
-	 * shared, we will free the backing store (like an MADV_DONTNEED) for
-	 * areas used by this region.
-	 */
-	ret = unmap_edge_bts(mm, start, end);
-	switch (ret) {
-		/* non-present tables are OK */
-		case 0:
-		case -ENOENT:
-			/* Success, or no tables to unmap */
-			break;
-		case -EINVAL:
-		case -EFAULT:
-		default:
-			return ret;
-	}
-
-	/*
-	 * Only unmap the bounds table that are
-	 *   1. fully covered
-	 *   2. not at the edges of the mapping, even if full aligned
-	 */
-	bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
-	bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
-	for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) {
-		ret = get_bt_addr(mm, bd_entry, &bt_addr);
-		switch (ret) {
-			case 0:
-				break;
-			case -ENOENT:
-				/* No table here, try the next one */
-				continue;
-			case -EINVAL:
-			case -EFAULT:
-			default:
-				/*
-				 * Note: we are being strict here.
-				 * Any time we run in to an issue
-				 * unmapping tables, we stop and
-				 * SIGSEGV.
-				 */
-				return ret;
-		}
-
-		ret = unmap_single_bt(mm, bd_entry, bt_addr);
+	unsigned long one_unmap_start;
+	trace_mpx_unmap_search(start, end);
+
+	one_unmap_start = start;
+	while (one_unmap_start < end) {
+		int ret;
+		unsigned long next_unmap_start = ALIGN(one_unmap_start+1,
+						       bd_entry_virt_space(mm));
+		unsigned long one_unmap_end = end;
+		/*
+		 * if the end is beyond the current bounds table,
+		 * move it back so we only deal with a single one
+		 * at a time
+		 */
+		if (one_unmap_end > next_unmap_start)
+			one_unmap_end = next_unmap_start;
+		ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end);
 		if (ret)
 			return ret;
-	}
 
+		one_unmap_start = next_unmap_start;
+	}
 	return 0;
 }
 

arch/x86/power/cpu.c

@@ -18,10 +18,9 @@
 #include <asm/mtrr.h>
 #include <asm/page.h>
 #include <asm/mce.h>
-#include <asm/xcr.h>
 #include <asm/suspend.h>
+#include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
-#include <asm/fpu-internal.h> /* pcntxt_mask */
 #include <asm/cpu.h>
 
 #ifdef CONFIG_X86_32
@@ -155,6 +154,8 @@ static void fix_processor_context(void)
 #endif
 	load_TR_desc();				/* This does ltr */
 	load_LDT(&current->active_mm->context);	/* This does lldt */
+
+	fpu__resume_cpu();
 }
 
 /**
@@ -221,12 +222,6 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
 #endif
 
-	/*
-	 * restore XCR0 for xsave capable cpu's.
-	 */
-	if (cpu_has_xsave)
-		xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
-
 	fix_processor_context();
 
 	do_fpu_end();

arch/x86/xen/enlighten.c

@@ -1423,7 +1423,7 @@ static void xen_pvh_set_cr_flags(int cpu)
 		return;
 	/*
 	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
-	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init.
+	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
 	*/
 	if (cpu_has_pse)
 		cr4_set_bits_and_update_boot(X86_CR4_PSE);

drivers/char/hw_random/via-rng.c

@@ -33,7 +33,7 @@
 #include <asm/io.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 
 

drivers/crypto/padlock-aes.c

@@ -22,7 +22,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/byteorder.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * Number of data blocks actually fetched for each xcrypt insn.

drivers/crypto/padlock-sha.c

@@ -23,7 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/scatterlist.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 struct padlock_sha_desc {
 	struct shash_desc fallback;

drivers/lguest/x86/core.c

@@ -46,7 +46,7 @@
 #include <asm/setup.h>
 #include <asm/lguest.h>
 #include <asm/uaccess.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
 #include "../lg.h"
 
@@ -251,7 +251,7 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 	 * we set it now, so we can trap and pass that trap to the Guest if it
 	 * uses the FPU.
 	 */
-	if (cpu->ts && user_has_fpu())
+	if (cpu->ts && fpregs_active())
 		stts();
 
 	/*
@@ -283,7 +283,7 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 		wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
 
 	/* Clear the host TS bit if it was set above. */
-	if (cpu->ts && user_has_fpu())
+	if (cpu->ts && fpregs_active())
 		clts();
 
 	/*
@@ -297,12 +297,12 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 	/*
 	 * Similarly, if we took a trap because the Guest used the FPU,
 	 * we have to restore the FPU it expects to see.
-	 * math_state_restore() may sleep and we may even move off to
+	 * fpu__restore() may sleep and we may even move off to
 	 * a different CPU. So all the critical stuff should be done
 	 * before this.
 	 */
-	else if (cpu->regs->trapnum == 7 && !user_has_fpu())
-		math_state_restore();
+	else if (cpu->regs->trapnum == 7 && !fpregs_active())
+		fpu__restore(&current->thread.fpu);
 }
 
 /*H:130

kernel/sys.c

@@ -92,10 +92,10 @@
 # define SET_TSC_CTL(a)		(-EINVAL)
 #endif
 #ifndef MPX_ENABLE_MANAGEMENT
-# define MPX_ENABLE_MANAGEMENT(a)	(-EINVAL)
+# define MPX_ENABLE_MANAGEMENT()	(-EINVAL)
 #endif
 #ifndef MPX_DISABLE_MANAGEMENT
-# define MPX_DISABLE_MANAGEMENT(a)	(-EINVAL)
+# define MPX_DISABLE_MANAGEMENT()	(-EINVAL)
 #endif
 #ifndef GET_FP_MODE
 # define GET_FP_MODE(a)		(-EINVAL)
@@ -2230,12 +2230,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_MPX_ENABLE_MANAGEMENT:
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
-		error = MPX_ENABLE_MANAGEMENT(me);
+		error = MPX_ENABLE_MANAGEMENT();
 		break;
 	case PR_MPX_DISABLE_MANAGEMENT:
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
-		error = MPX_DISABLE_MANAGEMENT(me);
+		error = MPX_DISABLE_MANAGEMENT();
 		break;
 	case PR_SET_FP_MODE:
 		error = SET_FP_MODE(me, arg2);

lib/raid6/x86.h

@@ -23,7 +23,7 @@
 
 #ifdef __KERNEL__ /* Real code */
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #else /* Dummy code for user space testing */