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 cleans up the FPU fault handling methods to be more robust, and
  moves eligible variables to .init.data"

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Put a few variables in .init.data
  x86/fpu: Get rid of xstate_fault()
  x86/fpu: Add an XSTATE_OP() macro

3 files changed, 87 insertions, 94 deletions

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 3c3550c3a4a3..eadcdd5bb946 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -224,18 +224,67 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
 #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)
+#define XSTATE_OP(op, st, lmask, hmask, err)				\
+	asm volatile("1:" op "\n\t"					\
+		     "xor %[err], %[err]\n"				\
+		     "2:\n\t"						\
+		     ".pushsection .fixup,\"ax\"\n\t"			\
+		     "3: movl $-2,%[err]\n\t"				\
+		     "jmp 2b\n\t"					\
+		     ".popsection\n\t"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
+
+/*
+ * If XSAVES is enabled, it replaces XSAVEOPT because it supports a 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.
+ *
+ * We use XSAVE as a fallback.
+ *
+ * The 661 label is defined in the ALTERNATIVE* macros as the address of the
+ * original instruction which gets replaced. We need to use it here as the
+ * address of the instruction where we might get an exception at.
+ */
+#define XSTATE_XSAVE(st, lmask, hmask, err)				\
+	asm volatile(ALTERNATIVE_2(XSAVE,				\
+				   XSAVEOPT, X86_FEATURE_XSAVEOPT,	\
+				   XSAVES,   X86_FEATURE_XSAVES)	\
+		     "\n"						\
+		     "xor %[err], %[err]\n"				\
+		     "3:\n"						\
+		     ".pushsection .fixup,\"ax\"\n"			\
+		     "4: movl $-2, %[err]\n"				\
+		     "jmp 3b\n"						\
+		     ".popsection\n"					\
+		     _ASM_EXTABLE(661b, 4b)				\
+		     : [err] "=r" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
+
+/*
+ * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
+ * XSAVE area format.
+ */
+#define XSTATE_XRESTORE(st, lmask, hmask, err)				\
+	asm volatile(ALTERNATIVE(XRSTOR,				\
+				 XRSTORS, X86_FEATURE_XSAVES)		\
+		     "\n"						\
+		     "xor %[err], %[err]\n"				\
+		     "3:\n"						\
+		     ".pushsection .fixup,\"ax\"\n"			\
+		     "4: movl $-2, %[err]\n"				\
+		     "jmp 3b\n"						\
+		     ".popsection\n"					\
+		     _ASM_EXTABLE(661b, 4b)				\
+		     : [err] "=r" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
 
 /*
  * This function is called only during boot time when x86 caps are not set
@@ -246,22 +295,14 @@ 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;
+	int err;
 
 	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");
+	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
 	else
-		asm volatile("1:"XSAVE"\n\t"
-			"2:\n\t"
-			     xstate_fault(err)
-			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
-			: "memory");
+		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
 
 	/* We should never fault when copying to a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -276,22 +317,14 @@ 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;
+	int err;
 
 	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");
+	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
 	else
-		asm volatile("1:"XRSTOR"\n\t"
-			"2:\n\t"
-			     xstate_fault(err)
-			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
-			: "memory");
+		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
 
 	/* We should never fault when copying from a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -305,33 +338,11 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
 	u64 mask = -1;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
 	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");
+	XSTATE_XSAVE(xstate, lmask, hmask, err);
 
 	/* We should never fault when copying to a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -344,23 +355,9 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
 {
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
-	/*
-	 * 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");
+	XSTATE_XRESTORE(xstate, lmask, hmask, err);
 
 	/* We should never fault when copying from a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -388,12 +385,10 @@ static inline int copy_xregs_to_user(struct xregs_state __user *buf)
 	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");
+	stac();
+	XSTATE_OP(XSAVE, buf, -1, -1, err);
+	clac();
+
 	return err;
 }
 
@@ -405,14 +400,12 @@ 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? */
+	int err;
+
+	stac();
+	XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+	clac();
+
 	return err;
 }
 
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 0d4e092ae1bf..7b2978ab30df 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -197,7 +197,7 @@ static void __init fpu__init_task_struct_size(void)
  */
 static void __init fpu__init_system_xstate_size_legacy(void)
 {
-	static int on_boot_cpu = 1;
+	static int on_boot_cpu __initdata = 1;
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
@@ -287,7 +287,7 @@ __setup("eagerfpu=", eager_fpu_setup);
  */
 static void __init fpu__init_system_ctx_switch(void)
 {
-	static bool on_boot_cpu = 1;
+	static bool on_boot_cpu __initdata = 1;
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 70fc312221fc..40f100285984 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -297,7 +297,7 @@ static void __init setup_xstate_comp(void)
  */
 static void __init setup_init_fpu_buf(void)
 {
-	static int on_boot_cpu = 1;
+	static int on_boot_cpu __initdata = 1;
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
@@ -608,7 +608,7 @@ static void fpu__init_disable_system_xstate(void)
 void __init fpu__init_system_xstate(void)
 {
 	unsigned int eax, ebx, ecx, edx;
-	static int on_boot_cpu = 1;
+	static int on_boot_cpu __initdata = 1;
 	int err;
 
 	WARN_ON_FPU(!on_boot_cpu);