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

Pull x86/xsave changes from Peter Anvin:
 "This is a patchset to support the XSAVES instruction required to
  support context switch of supervisor-only features in upcoming
  silicon.

  This patchset missed the 3.16 merge window, which is why it is based
  on 3.15-rc7"

* 'x86-xsave-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, xsave: Add forgotten inline annotation
  x86/xsaves: Clean up code in xstate offsets computation in xsave area
  x86/xsave: Make it clear that the XSAVE macros use (%edi)/(%rdi)
  Define kernel API to get address of each state in xsave area
  x86/xsaves: Enable xsaves/xrstors
  x86/xsaves: Call booting time xsaves and xrstors in setup_init_fpu_buf
  x86/xsaves: Save xstate to task's xsave area in __save_fpu during booting time
  x86/xsaves: Add xsaves and xrstors support for booting time
  x86/xsaves: Clear reserved bits in xsave header
  x86/xsaves: Use xsave/xrstor for saving and restoring user space context
  x86/xsaves: Use xsaves/xrstors for context switch
  x86/xsaves: Use xsaves/xrstors to save and restore xsave area
  x86/xsaves: Define a macro for handling xsave/xrstor instruction fault
  x86/xsaves: Define macros for xsave instructions
  x86/xsaves: Change compacted format xsave area header
  x86/alternative: Add alternative_input_2 to support alternative with two features and input
  x86/xsaves: Add a kernel parameter noxsaves to disable xsaves/xrstors

Documentation/kernel-parameters.txt

@@ -2200,6 +2200,21 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
 
+	noxsaveopt	[X86] Disables xsaveopt used in saving x86 extended
+			register states. The kernel will fall back to use
+			xsave to save the states. By using this parameter,
+			performance of saving the states is degraded because
+			xsave doesn't support modified optimization while
+			xsaveopt supports it on xsaveopt enabled systems.
+
+	noxsaves	[X86] Disables xsaves and xrstors used in saving and
+			restoring x86 extended register state in compacted
+			form of xsave area. The kernel will fall back to use
+			xsaveopt and xrstor to save and restore the states
+			in standard form of xsave area. By using this
+			parameter, xsave area per process might occupy more
+			memory on xsaves enabled systems.
+
 	eagerfpu=	[X86]
 			on	enable eager fpu restore
 			off	disable eager fpu restore

arch/x86/include/asm/alternative.h

@@ -161,6 +161,20 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)		\
 		: : "i" (0), ## input)
 
+/*
+ * This is similar to alternative_input. But it has two features and
+ * respective instructions.
+ *
+ * If CPU has feature2, newinstr2 is used.
+ * Otherwise, if CPU has feature1, newinstr1 is used.
+ * Otherwise, oldinstr is used.
+ */
+#define alternative_input_2(oldinstr, newinstr1, feature1, newinstr2,	     \
+			   feature2, input...)				     \
+	asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1,	     \
+		newinstr2, feature2)					     \
+		: : "i" (0), ## input)
+
 /* Like alternative_input, but with a single output argument */
 #define alternative_io(oldinstr, newinstr, feature, output, input...)	\
 	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)		\

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

@@ -508,9 +508,12 @@ static inline void user_fpu_begin(void)
 
 static inline void __save_fpu(struct task_struct *tsk)
 {
-	if (use_xsave())
-		xsave_state(&tsk->thread.fpu.state->xsave, -1);
-	else
+	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);
 }
 

arch/x86/include/asm/processor.h

@@ -385,8 +385,8 @@ struct bndcsr_struct {
 
 struct xsave_hdr_struct {
 	u64 xstate_bv;
-	u64 reserved1[2];
-	u64 reserved2[5];
+	u64 xcomp_bv;
+	u64 reserved[6];
 } __attribute__((packed));
 
 struct xsave_struct {

arch/x86/include/asm/xsave.h

@@ -52,24 +52,170 @@ 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);
 
-static inline int fpu_xrstor_checking(struct xsave_struct *fx)
+/* 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)
 {
-	int err;
+	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"
+			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			:   "memory");
+	else
+		asm volatile("1:"XSAVE"\n\t"
+			"2:\n\t"
+			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			:   "memory");
+
+	asm volatile(xstate_fault
+		     : "0" (0)
+		     : "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);
 
-	asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\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)
-		     : "D" (fx), "m" (*fx), "a" (-1), "d" (-1), "0" (0)
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		asm volatile("1:"XRSTORS"\n\t"
+			"2:\n\t"
+			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			:   "memory");
+	else
+		asm volatile("1:"XRSTOR"\n\t"
+			"2:\n\t"
+			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			:   "memory");
+
+	asm volatile(xstate_fault
+		     : "0" (0)
+		     : "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,
+		"1:"XSAVEOPT,
+		X86_FEATURE_XSAVEOPT,
+		"1:"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,
+		"1: " 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;
@@ -83,69 +229,34 @@ static inline int xsave_user(struct xsave_struct __user *buf)
 		return -EFAULT;
 
 	__asm__ __volatile__(ASM_STAC "\n"
-			     "1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
+			     "1:"XSAVE"\n"
 			     "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)
+			     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;
+	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: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
+			     "1:"XRSTOR"\n"
 			     "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)
+			     xstate_fault
 			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
 			     : "memory");	/* memory required? */
 	return err;
 }
 
-static inline void xrstor_state(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-
-	asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
-		     : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-		     :   "memory");
-}
-
-static inline void xsave_state(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
+void *get_xsave_addr(struct xsave_struct *xsave, int xstate);
+void setup_xstate_comp(void);
 
-	asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x27\n\t"
-		     : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-		     :   "memory");
-}
-
-static inline void fpu_xsave(struct fpu *fpu)
-{
-	/* This, however, we can work around by forcing the compiler to select
-	   an addressing mode that doesn't require extended registers. */
-	alternative_input(
-		".byte " REX_PREFIX "0x0f,0xae,0x27",
-		".byte " REX_PREFIX "0x0f,0xae,0x37",
-		X86_FEATURE_XSAVEOPT,
-		[fx] "D" (&fpu->state->xsave), "a" (-1), "d" (-1) :
-		"memory");
-}
 #endif

arch/x86/kernel/cpu/common.c

@@ -148,6 +148,7 @@ static int __init x86_xsave_setup(char *s)
 {
 	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;
@@ -161,6 +162,13 @@ static int __init x86_xsaveopt_setup(char *s)
 }
 __setup("noxsaveopt", x86_xsaveopt_setup);
 
+static int __init x86_xsaves_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+	return 1;
+}
+__setup("noxsaves", x86_xsaves_setup);
+
 #ifdef CONFIG_X86_32
 static int cachesize_override = -1;
 static int disable_x86_serial_nr = 1;

arch/x86/kernel/i387.c

@@ -375,7 +375,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 	/*
 	 * These bits must be zero.
 	 */
-	xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+	memset(xsave_hdr->reserved, 0, 48);
 
 	return ret;
 }

arch/x86/kernel/process.c

@@ -93,6 +93,7 @@ void arch_task_cache_init(void)
         	kmem_cache_create("task_xstate", xstate_size,
 				  __alignof__(union thread_xstate),
 				  SLAB_PANIC | SLAB_NOTRACK, NULL);
+	setup_xstate_comp();
 }
 
 /*

arch/x86/kernel/xsave.c

@@ -8,6 +8,7 @@
 
 #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>
@@ -24,7 +25,9 @@ u64 pcntxt_mask;
 struct xsave_struct *init_xstate_buf;
 
 static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
-static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
+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
@@ -283,7 +286,7 @@ sanitize_restored_xstate(struct task_struct *tsk,
 
 	if (use_xsave()) {
 		/* These bits must be zero. */
-		xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+		memset(xsave_hdr->reserved, 0, 48);
 
 		/*
 		 * Init the state that is not present in the memory
@@ -478,6 +481,52 @@ static void __init setup_xstate_features(void)
 	} 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
  */
@@ -496,15 +545,21 @@ static void __init setup_init_fpu_buf(void)
 
 	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(init_xstate_buf, -1);
+	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(init_xstate_buf, -1);
+	xsave_state_booting(init_xstate_buf, -1);
 }
 
 static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
@@ -520,6 +575,30 @@ static int __init eager_fpu_setup(char *s)
 }
 __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.
  */
@@ -551,8 +630,7 @@ static void __init xstate_enable_boot_cpu(void)
 	/*
 	 * Recompute the context size for enabled features
 	 */
-	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-	xstate_size = ebx;
+	init_xstate_size();
 
 	update_regset_xstate_info(xstate_size, pcntxt_mask);
 	prepare_fx_sw_frame();
@@ -572,8 +650,9 @@ static void __init xstate_enable_boot_cpu(void)
 		}
 	}
 
-	pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n",
-		pcntxt_mask, xstate_size);
+	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");
 }
 
 /*
@@ -635,3 +714,26 @@ void eager_fpu_init(void)
 	else
 		fxrstor_checking(&init_xstate_buf->i387);
 }
+
+/*
+ * 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];
+}