4 files changed, 116 insertions, 57 deletions

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 97027545a72d..c759bd01ec99 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -12,6 +12,9 @@
 
 #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 +195,7 @@ 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 +204,7 @@ void fpu__save(struct fpu *fpu)
 				fpregs_deactivate(fpu);
 		}
 	}
+	trace_x86_fpu_after_save(fpu);
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(fpu__save);
@@ -222,7 +227,7 @@ void fpstate_init(union fpregs_state *state)
 		return;
 	}
 
-	memset(state, 0, xstate_size);
+	memset(state, 0, fpu_kernel_xstate_size);
 
 	if (static_cpu_has(X86_FEATURE_FXSR))
 		fpstate_init_fxstate(&state->fxsave);
@@ -247,7 +252,7 @@ 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 +271,8 @@ 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 +281,9 @@ 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 +297,9 @@ 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 +325,9 @@ 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 +360,9 @@ 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 +447,11 @@ 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 +480,8 @@ void fpu__drop(struct fpu *fpu)
 
 	fpu->fpstate_active = 0;
 
+	trace_x86_fpu_dropped(fpu);
+
 	preempt_enable();
 }
 
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index aacfd7a82cec..60f3839c5bfa 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().
 	 */
 
@@ -219,13 +219,18 @@ 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);
 	}
+
+	fpu_user_xstate_size = fpu_kernel_xstate_size;
+
 	/*
 	 * Quirk: we don't yet handle the XSAVES* instructions
 	 * correctly, as we don't correctly convert between
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 31c6a60505e6..8aa96cbb5dfb 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;
 	}
 
@@ -250,7 +264,7 @@ 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;
+	int state_size = fpu_kernel_xstate_size;
 	u64 xfeatures = 0;
 	int fx_only = 0;
 
@@ -282,6 +296,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 			 */
 			state_size = sizeof(struct fxregs_state);
 			fx_only = 1;
+			trace_x86_fpu_xstate_check_failed(fpu);
 		} else {
 			state_size = fx_sw_user.xstate_size;
 			xfeatures = fx_sw_user.xfeatures;
@@ -311,6 +326,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		if (__copy_from_user(&fpu->state.xsave, buf_fx, state_size) ||
 		    __copy_from_user(&env, buf, sizeof(env))) {
 			fpstate_init(&fpu->state);
+			trace_x86_fpu_init_state(fpu);
 			err = -1;
 		} else {
 			sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
@@ -341,7 +357,8 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 
 static inline int xstate_sigframe_size(void)
 {
-	return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+	return use_xsave() ? fpu_user_xstate_size + FP_XSTATE_MAGIC2_SIZE :
+			fpu_user_xstate_size;
 }
 
 /*
@@ -385,12 +402,12 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
  */
 void fpu__init_prepare_fx_sw_frame(void)
 {
-	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
+	int size = fpu_user_xstate_size + FP_XSTATE_MAGIC2_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;
+	fx_sw_reserved.xstate_size = fpu_user_xstate_size;
 
 	if (config_enabled(CONFIG_IA32_EMULATION) ||
 	    config_enabled(CONFIG_X86_32)) {
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 4ea2a59483c7..0b01f003df8b 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -44,6 +44,13 @@ static unsigned int xstate_sizes[XFEATURE_MAX]   = { [ 0 ... XFEATURE_MAX - 1] =
 static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
 
 /*
+ * The XSAVE area of kernel can be in standard or compacted format;
+ * it is always in standard format for user mode. This is the user
+ * mode standard format size used for signal and ptrace frames.
+ */
+unsigned int fpu_user_xstate_size;
+
+/*
  * Clear all of the X86_FEATURE_* bits that are unavailable
  * when the CPU has no XSAVE support.
  */
@@ -171,7 +178,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
 	 */
 	while (xfeatures) {
 		if (xfeatures & 0x1) {
-			int offset = xstate_offsets[feature_bit];
+			int offset = xstate_comp_offsets[feature_bit];
 			int size = xstate_sizes[feature_bit];
 
 			memcpy((void *)fx + offset,
@@ -322,13 +329,11 @@ static void __init setup_init_fpu_buf(void)
 	setup_xstate_features();
 	print_xstate_features();
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+	if (boot_cpu_has(X86_FEATURE_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
+	 * Init all the features state with header.xfeatures being 0x0
 	 */
 	copy_kernel_to_xregs_booting(&init_fpstate.xsave);
 
@@ -415,7 +420,7 @@ static int xfeature_size(int xfeature_nr)
  * that it is obvious which aspect of 'XSAVES' is being handled
  * by the calling code.
  */
-static int using_compacted_format(void)
+int using_compacted_format(void)
 {
 	return boot_cpu_has(X86_FEATURE_XSAVES);
 }
@@ -530,11 +535,12 @@ static void do_extra_xstate_size_checks(void)
 		 */
 		paranoid_xstate_size += xfeature_size(i);
 	}
-	XSTATE_WARN_ON(paranoid_xstate_size != xstate_size);
+	XSTATE_WARN_ON(paranoid_xstate_size != fpu_kernel_xstate_size);
 }
 
+
 /*
- * Calculate total size of enabled xstates in XCR0/xfeatures_mask.
+ * Get total size of enabled xstates in XCR0/xfeatures_mask.
  *
  * Note the SDM's wording here.  "sub-function 0" only enumerates
  * the size of the *user* states.  If we use it to size a buffer
@@ -544,34 +550,33 @@ static void do_extra_xstate_size_checks(void)
  * Note that we do not currently set any bits on IA32_XSS so
  * 'XCR0 | IA32_XSS == XCR0' for now.
  */
-static unsigned int __init calculate_xstate_size(void)
+static unsigned int __init get_xsaves_size(void)
 {
 	unsigned int eax, ebx, ecx, edx;
-	unsigned int calculated_xstate_size;
+	/*
+	 * - CPUID function 0DH, sub-function 1:
+	 *    EBX enumerates the size (in bytes) required by
+	 *    the XSAVES instruction for an XSAVE area
+	 *    containing all the state components
+	 *    corresponding to bits currently set in
+	 *    XCR0 | IA32_XSS.
+	 */
+	cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
+	return ebx;
+}
 
-	if (!boot_cpu_has(X86_FEATURE_XSAVES)) {
-		/*
-		 * - CPUID function 0DH, sub-function 0:
-		 *    EBX enumerates the size (in bytes) required by
-		 *    the XSAVE instruction for an XSAVE area
-		 *    containing all the *user* state components
-		 *    corresponding to bits currently set in XCR0.
-		 */
-		cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-		calculated_xstate_size = ebx;
-	} else {
-		/*
-		 * - CPUID function 0DH, sub-function 1:
-		 *    EBX enumerates the size (in bytes) required by
-		 *    the XSAVES instruction for an XSAVE area
-		 *    containing all the state components
-		 *    corresponding to bits currently set in
-		 *    XCR0 | IA32_XSS.
-		 */
-		cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
-		calculated_xstate_size = ebx;
-	}
-	return calculated_xstate_size;
+static unsigned int __init get_xsave_size(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	/*
+	 * - CPUID function 0DH, sub-function 0:
+	 *    EBX enumerates the size (in bytes) required by
+	 *    the XSAVE instruction for an XSAVE area
+	 *    containing all the *user* state components
+	 *    corresponding to bits currently set in XCR0.
+	 */
+	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+	return ebx;
 }
 
 /*
@@ -591,7 +596,15 @@ static bool is_supported_xstate_size(unsigned int test_xstate_size)
 static int init_xstate_size(void)
 {
 	/* Recompute the context size for enabled features: */
-	unsigned int possible_xstate_size = calculate_xstate_size();
+	unsigned int possible_xstate_size;
+	unsigned int xsave_size;
+
+	xsave_size = get_xsave_size();
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		possible_xstate_size = get_xsaves_size();
+	else
+		possible_xstate_size = xsave_size;
 
 	/* Ensure we have the space to store all enabled: */
 	if (!is_supported_xstate_size(possible_xstate_size))
@@ -601,8 +614,13 @@ static int init_xstate_size(void)
 	 * The size is OK, we are definitely going to use xsave,
 	 * make it known to the world that we need more space.
 	 */
-	xstate_size = possible_xstate_size;
+	fpu_kernel_xstate_size = possible_xstate_size;
 	do_extra_xstate_size_checks();
+
+	/*
+	 * User space is always in standard format.
+	 */
+	fpu_user_xstate_size = xsave_size;
 	return 0;
 }
 
@@ -659,14 +677,14 @@ void __init fpu__init_system_xstate(void)
 		return;
 	}
 
-	update_regset_xstate_info(xstate_size, xfeatures_mask);
+	update_regset_xstate_info(fpu_kernel_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 %d bytes, using '%s' format.\n",
 		xfeatures_mask,
-		xstate_size,
+		fpu_kernel_xstate_size,
 		boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
 }