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

2d724ffd · Linus Torvalds <[email protected]> · 2016-07-25 18:48:27 -07:00

Pull x86 fpu updates from Ingo Molnar:
 "The main x86 FPU changes in this cycle were:

   - a large series of cleanups, fixes and enhancements to re-enable the
     XSAVES instruction on Intel CPUs - which is the most advanced
     instruction to do FPU context switches (Yu-cheng Yu, Fenghua Yu)

   - Add FPU tracepoints for the FPU state machine (Dave Hansen)"

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Do not BUG_ON() in early FPU code
  x86/fpu/xstate: Re-enable XSAVES
  x86/fpu/xstate: Fix fpstate_init() for XRSTORS
  x86/fpu/xstate: Return NULL for disabled xstate component address
  x86/fpu/xstate: Fix __fpu_restore_sig() for XSAVES
  x86/fpu/xstate: Fix xstate_offsets, xstate_sizes for non-extended xstates
  x86/fpu/xstate: Fix XSTATE component offset print out
  x86/fpu/xstate: Fix PTRACE frames for XSAVES
  x86/fpu/xstate: Fix supervisor xstate component offset
  x86/fpu/xstate: Align xstate components according to CPUID
  x86/fpu/xstate: Copy xstate registers directly to the signal frame when compacted format is in use
  x86/fpu/xstate: Keep init_fpstate.xsave.header.xfeatures as zero for init optimization
  x86/fpu/xstate: Rename 'xstate_size' to 'fpu_kernel_xstate_size', to distinguish it from 'fpu_user_xstate_size'
  x86/fpu/xstate: Define and use 'fpu_user_xstate_size'
  x86/fpu: Add tracepoints to dump FPU state at key points

Commit: 2d724ffddd958f21e2711b7400c63bdfee287d75
Parents: 36e635cb · ec3ed4a2

Merge commit. Changes below are compared with the first parent: 36e635cb.

Changes

11 files changed · +608 −158

File	Status	Add	Del	Content
arch/x86/include/asm/fpu/internal.h	modified	+5	−0	View file
arch/x86/include/asm/fpu/types.h	modified	+7	−0	View file
arch/x86/include/asm/fpu/xstate.h	modified	+8	−2	View file
arch/x86/include/asm/processor.h	modified	+2	−1	View file
arch/x86/include/asm/trace/fpu.h	added	+119	−0	View file
arch/x86/kernel/fpu/core.c	modified	+30	−3	View file
arch/x86/kernel/fpu/init.c	modified	+12	−22	View file
arch/x86/kernel/fpu/regset.c	modified	+37	−15	View file
arch/x86/kernel/fpu/signal.c	modified	+35	−11	View file
arch/x86/kernel/fpu/xstate.c	modified	+350	−101	View file
arch/x86/kvm/x86.c	modified	+3	−3	View file

Only the first 600 diff lines are shown. Download the complete patch.

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

View file

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 31ac8e6..116b583 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -18,6 +18,7 @@
 #include <asm/fpu/api.h>
 #include <asm/fpu/xstate.h>
 #include <asm/cpufeature.h>
+#include <asm/trace/fpu.h>
 
 /*
  * High level FPU state handling functions:
@@ -524,6 +525,7 @@ static inline void __fpregs_deactivate(struct fpu *fpu)
 
 	fpu->fpregs_active = 0;
 	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+	trace_x86_fpu_regs_deactivated(fpu);
 }
 
 /* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
@@ -533,6 +535,7 @@ static inline void __fpregs_activate(struct fpu *fpu)
 
 	fpu->fpregs_active = 1;
 	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+	trace_x86_fpu_regs_activated(fpu);
 }
 
 /*
@@ -604,11 +607,13 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 
 		/* But leave fpu_fpregs_owner_ctx! */
 		old_fpu->fpregs_active = 0;
+		trace_x86_fpu_regs_deactivated(old_fpu);
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
 			new_fpu->counter++;
 			__fpregs_activate(new_fpu);
+			trace_x86_fpu_regs_activated(new_fpu);
 			prefetch(&new_fpu->state);
 		} else {
 			__fpregs_deactivate_hw();

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

View file

diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 36b90bb..48df486 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -122,6 +122,7 @@ enum xfeature {
 #define XFEATURE_MASK_OPMASK		(1 << XFEATURE_OPMASK)
 #define XFEATURE_MASK_ZMM_Hi256		(1 << XFEATURE_ZMM_Hi256)
 #define XFEATURE_MASK_Hi16_ZMM		(1 << XFEATURE_Hi16_ZMM)
+#define XFEATURE_MASK_PT		(1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
 #define XFEATURE_MASK_PKRU		(1 << XFEATURE_PKRU)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
@@ -231,6 +232,12 @@ struct xstate_header {
 } __attribute__((packed));
 
 /*
+ * xstate_header.xcomp_bv[63] indicates that the extended_state_area
+ * is in compacted format.
+ */
+#define XCOMP_BV_COMPACTED_FORMAT ((u64)1 << 63)
+
+/*
  * This is our most modern FPU state format, as saved by the XSAVE
  * and restored by the XRSTOR instructions.
  *

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

View file

diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 38951b0..ae55a43 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -18,6 +18,9 @@
 #define XSAVE_YMM_SIZE	    256
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
+/* Supervisor features */
+#define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT)
+
 /* Supported features which support lazy state saving */
 #define XFEATURE_MASK_LAZY	(XFEATURE_MASK_FP | \
 				 XFEATURE_MASK_SSE | \
@@ -39,7 +42,6 @@
 #define REX_PREFIX
 #endif
 
-extern unsigned int xstate_size;
 extern u64 xfeatures_mask;
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
@@ -48,5 +50,9 @@ extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 void fpu__xstate_clear_all_cpu_caps(void);
 void *get_xsave_addr(struct xregs_state *xsave, int xstate);
 const void *get_xsave_field_ptr(int xstate_field);
-
+int using_compacted_format(void);
+int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
+			void __user *ubuf, struct xregs_state *xsave);
+int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
+		     struct xregs_state *xsave);
 #endif

arch/x86/include/asm/processor.h

View file

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 89314ed..63def95 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -367,7 +367,8 @@ DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
 DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif	/* X86_64 */
 
-extern unsigned int xstate_size;
+extern unsigned int fpu_kernel_xstate_size;
+extern unsigned int fpu_user_xstate_size;
 
 struct perf_event;
 

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

View file

diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
new file mode 100644
index 0000000..9217ab1
--- /dev/null
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -0,0 +1,119 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM x86_fpu
+
+#if !defined(_TRACE_FPU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_FPU_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(x86_fpu,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu),
+
+	TP_STRUCT__entry(
+		__field(struct fpu *, fpu)
+		__field(bool, fpregs_active)
+		__field(bool, fpstate_active)
+		__field(int, counter)
+		__field(u64, xfeatures)
+		__field(u64, xcomp_bv)
+		),
+
+	TP_fast_assign(
+		__entry->fpu		= fpu;
+		__entry->fpregs_active	= fpu->fpregs_active;
+		__entry->fpstate_active	= fpu->fpstate_active;
+		__entry->counter	= fpu->counter;
+		if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
+			__entry->xfeatures = fpu->state.xsave.header.xfeatures;
+			__entry->xcomp_bv  = fpu->state.xsave.header.xcomp_bv;
+		}
+	),
+	TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d counter: %d xfeatures: %llx xcomp_bv: %llx",
+			__entry->fpu,
+			__entry->fpregs_active,
+			__entry->fpstate_active,
+			__entry->counter,
+			__entry->xfeatures,
+			__entry->xcomp_bv
+	)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_before_save,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_after_save,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_before_restore,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_after_restore,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_activate_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_deactivate_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_init_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_dropped,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_copy_src,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_xstate_check_failed,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/trace/
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE fpu
+#endif /* _TRACE_FPU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

arch/x86/kernel/fpu/core.c

View file

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 9702754..3fc03a0 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -8,10 +8,14 @@
 #include <asm/fpu/internal.h>
 #include <asm/fpu/regset.h>
 #include <asm/fpu/signal.h>
+#include <asm/fpu/types.h>
 #include <asm/traps.h>
 
 #include <linux/hardirq.h>
 
+#define CREATE_TRACE_POINTS
+#include <asm/trace/fpu.h>
+
 /*
  * Represents the initial FPU state. It's mostly (but not completely) zeroes,
  * depending on the FPU hardware format:
@@ -192,6 +196,7 @@ void fpu__save(struct fpu *fpu)
 	WARN_ON_FPU(fpu != &current->thread.fpu);
 
 	preempt_disable();
+	trace_x86_fpu_before_save(fpu);
 	if (fpu->fpregs_active) {
 		if (!copy_fpregs_to_fpstate(fpu)) {
 			if (use_eager_fpu())
@@ -200,6 +205,7 @@ void fpu__save(struct fpu *fpu)
 				fpregs_deactivate(fpu);
 		}
 	}
+	trace_x86_fpu_after_save(fpu);
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(fpu__save);
@@ -222,7 +228,14 @@ void fpstate_init(union fpregs_state *state)
 		return;
 	}
 
-	memset(state, 0, xstate_size);
+	memset(state, 0, fpu_kernel_xstate_size);
+
+	/*
+	 * XRSTORS requires that this bit is set in xcomp_bv, or
+	 * it will #GP. Make sure it is replaced after the memset().
+	 */
+	if (static_cpu_has(X86_FEATURE_XSAVES))
+		state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT;
 
 	if (static_cpu_has(X86_FEATURE_FXSR))
 		fpstate_init_fxstate(&state->fxsave);
@@ -247,7 +260,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	 * leak into the child task:
 	 */
 	if (use_eager_fpu())
-		memset(&dst_fpu->state.xsave, 0, xstate_size);
+		memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size);
 
 	/*
 	 * Save current FPU registers directly into the child
@@ -266,7 +279,8 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	 */
 	preempt_disable();
 	if (!copy_fpregs_to_fpstate(dst_fpu)) {
-		memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
+		memcpy(&src_fpu->state, &dst_fpu->state,
+		       fpu_kernel_xstate_size);
 
 		if (use_eager_fpu())
 			copy_kernel_to_fpregs(&src_fpu->state);
@@ -275,6 +289,9 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	}
 	preempt_enable();
 
+	trace_x86_fpu_copy_src(src_fpu);
+	trace_x86_fpu_copy_dst(dst_fpu);
+
 	return 0;
 }
 
@@ -288,7 +305,9 @@ void fpu__activate_curr(struct fpu *fpu)
 
 	if (!fpu->fpstate_active) {
 		fpstate_init(&fpu->state);
+		trace_x86_fpu_init_state(fpu);
 
+		trace_x86_fpu_activate_state(fpu);
 		/* Safe to do for the current task: */
 		fpu->fpstate_active = 1;
 	}
@@ -314,7 +333,9 @@ void fpu__activate_fpstate_read(struct fpu *fpu)
 	} else {
 		if (!fpu->fpstate_active) {
 			fpstate_init(&fpu->state);
+			trace_x86_fpu_init_state(fpu);
 
+			trace_x86_fpu_activate_state(fpu);
 			/* Safe to do for current and for stopped child tasks: */
 			fpu->fpstate_active = 1;
 		}
@@ -347,7 +368,9 @@ void fpu__activate_fpstate_write(struct fpu *fpu)
 		fpu->last_cpu = -1;
 	} else {
 		fpstate_init(&fpu->state);
+		trace_x86_fpu_init_state(fpu);
 
+		trace_x86_fpu_activate_state(fpu);
 		/* Safe to do for stopped child tasks: */
 		fpu->fpstate_active = 1;
 	}
@@ -432,9 +455,11 @@ void fpu__restore(struct fpu *fpu)
 
 	/* Avoid __kernel_fpu_begin() right after fpregs_activate() */
 	kernel_fpu_disable();
+	trace_x86_fpu_before_restore(fpu);
 	fpregs_activate(fpu);
 	copy_kernel_to_fpregs(&fpu->state);
 	fpu->counter++;
+	trace_x86_fpu_after_restore(fpu);
 	kernel_fpu_enable();
 }
 EXPORT_SYMBOL_GPL(fpu__restore);
@@ -463,6 +488,8 @@ void fpu__drop(struct fpu *fpu)
 
 	fpu->fpstate_active = 0;
 
+	trace_x86_fpu_dropped(fpu);
+
 	preempt_enable();
 }
 

arch/x86/kernel/fpu/init.c

View file

diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index aacfd7a..93982ae 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -145,8 +145,8 @@ static void __init fpu__init_system_generic(void)
  * 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);
+unsigned int fpu_kernel_xstate_size;
+EXPORT_SYMBOL_GPL(fpu_kernel_xstate_size);
 
 /* Get alignment of the TYPE. */
 #define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test)
@@ -178,7 +178,7 @@ static void __init fpu__init_task_struct_size(void)
 	 * Add back the dynamically-calculated register state
 	 * size.
 	 */
-	task_size += xstate_size;
+	task_size += fpu_kernel_xstate_size;
 
 	/*
 	 * We dynamically size 'struct fpu', so we require that
@@ -195,7 +195,7 @@ static void __init fpu__init_task_struct_size(void)
 }
 
 /*
- * Set up the xstate_size based on the legacy FPU context size.
+ * Set up the user and kernel xstate sizes 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.
@@ -208,7 +208,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 	on_boot_cpu = 0;
 
 	/*
-	 * Note that xstate_size might be overwriten later during
+	 * Note that xstate sizes might be overwritten later during
 	 * fpu__init_system_xstate().
 	 */
 
@@ -219,27 +219,17 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 		 */
 		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-		xstate_size = sizeof(struct swregs_state);
+		fpu_kernel_xstate_size = sizeof(struct swregs_state);
 	} else {
 		if (boot_cpu_has(X86_FEATURE_FXSR))
-			xstate_size = sizeof(struct fxregs_state);
+			fpu_kernel_xstate_size =
+				sizeof(struct fxregs_state);
 		else
-			xstate_size = sizeof(struct fregs_state);
+			fpu_kernel_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_user_xstate_size = fpu_kernel_xstate_size;
 }
 
 /*

arch/x86/kernel/fpu/regset.c

View file

diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 81422df..c114b13 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -4,6 +4,7 @@
 #include <asm/fpu/internal.h>
 #include <asm/fpu/signal.h>
 #include <asm/fpu/regset.h>
+#include <asm/fpu/xstate.h>
 
 /*
  * The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
@@ -85,21 +86,26 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
 	if (!boot_cpu_has(X86_FEATURE_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);
+	fpu__activate_fpstate_read(fpu);
+
+	if (using_compacted_format()) {
+		ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave);
+	} else {
+		fpstate_sanitize_xstate(fpu);
+		/*
+		 * Copy the 48 bytes defined by the software into the xsave
+		 * area in the thread struct, so that we can copy the whole
+		 * area to 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;
 }
 
@@ -114,11 +120,27 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return -ENODEV;
 
-	fpu__activate_fpstate_write(fpu);
+	/*
+	 * A whole standard-format XSAVE buffer is needed:
+	 */
+	if ((pos != 0) || (count < fpu_user_xstate_size))
+		return -EFAULT;
 
 	xsave = &fpu->state.xsave;
 
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+	fpu__activate_fpstate_write(fpu);
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		ret = copyin_to_xsaves(kbuf, ubuf, xsave);
+	else
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+
+	/*
+	 * In case of failure, mark all states as init:
+	 */
+	if (ret)
+		fpstate_init(&fpu->state);
+
 	/*
 	 * mxcsr reserved bits must be masked to zero for security reasons.
 	 */

arch/x86/kernel/fpu/signal.c

View file

diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 31c6a60..9e231d8 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -8,8 +8,10 @@
 #include <asm/fpu/internal.h>
 #include <asm/fpu/signal.h>
 #include <asm/fpu/regset.h>
+#include <asm/fpu/xstate.h>
 
 #include <asm/sigframe.h>
+#include <asm/trace/fpu.h>
 
 static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
 
@@ -31,7 +33,7 @@ static inline int check_for_xstate(struct fxregs_state __user *buf,
 	/* 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 > fpu_user_xstate_size ||
 	    fx_sw->xstate_size > fx_sw->extended_size)
 		return -1;
 
@@ -88,7 +90,8 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
 	if (!use_xsave())
 		return err;
 
-	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
+	err |= __put_user(FP_XSTATE_MAGIC2,
+			  (__u32 *)(buf + fpu_user_xstate_size));
 
 	/*
 	 * Read the xfeatures which we copied (directly from the cpu or
@@ -125,7 +128,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
 	else
 		err = copy_fregs_to_user((struct fregs_state __user *) buf);
 
-	if (unlikely(err) && __clear_user(buf, xstate_size))
+	if (unlikely(err) && __clear_user(buf, fpu_user_xstate_size))
 		err = -EFAULT;
 	return err;
 }
@@ -167,7 +170,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 			sizeof(struct user_i387_ia32_struct), NULL,
 			(struct _fpstate_32 __user *) buf) ? -1 : 1;
 
-	if (fpregs_active()) {
+	if (fpregs_active() || using_compacted_format()) {
 		/* Save the live register state to the user directly. */
 		if (copy_fpregs_to_sigframe(buf_fx))
 			return -1;
@@ -175,8 +178,19 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 		if (ia32_fxstate)
 			copy_fxregs_to_kernel(&tsk->thread.fpu);
 	} else {
+		/*
+		 * It is a *bug* if kernel uses compacted-format for xsave
+		 * area and we copy it out directly to a signal frame. It
+		 * should have been handled above by saving the registers
+		 * directly.
+		 */
+		if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+			WARN_ONCE(1, "x86/fpu: saving compacted-format xsave area to a signal frame!\n");
+			return -1;
+		}
+
 		fpstate_sanitize_xstate(&tsk->thread.fpu);
-		if (__copy_to_user(buf_fx, xsave, xstate_size))
+		if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size))
 			return -1;

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

Changes

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

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

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

arch/x86/include/asm/processor.h

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

arch/x86/kernel/fpu/core.c

arch/x86/kernel/fpu/init.c

arch/x86/kernel/fpu/regset.c

arch/x86/kernel/fpu/signal.c

arch/x86/kernel/fpu/xstate.c

arch/x86/kvm/x86.c