x86/xsaves: Fix XSAVES known issues

index af30fde..c6667f2 100644
@@ -39,7 +39,6 @@
 #define REX_PREFIX
 #endif
 
-extern unsigned int xstate_size;
 extern u64 xfeatures_mask;
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 

index 20c11d1..01e127e 100644
@@ -366,6 +366,7 @@ DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif	/* X86_64 */
 
 extern unsigned int xstate_size;
+extern unsigned int user_xstate_size;
 
 struct perf_event;
 

index 6d9f0a7..4ac2561 100644
@@ -193,7 +193,7 @@ 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_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.

@@ -224,6 +224,9 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 		else
 			xstate_size = sizeof(struct fregs_state);
 	}
+
+	user_xstate_size = xstate_size;
+
 	/*
 	 * Quirk: we don't yet handle the XSAVES* instructions
 	 * correctly, as we don't correctly convert between

index 31c6a60..ee6d662 100644
@@ -31,7 +31,7 @@ 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 > user_xstate_size ||
 	    fx_sw->xstate_size > fx_sw->extended_size)
 		return -1;
 

@@ -88,7 +88,7 @@ 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 + user_xstate_size));
 
 	/*
 	 * Read the xfeatures which we copied (directly from the cpu or

@@ -125,7 +125,7 @@ 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, user_xstate_size))
 		err = -EFAULT;
 	return err;
 }

@@ -175,8 +175,19 @@ 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, user_xstate_size))
 			return -1;
 	}
 

@@ -341,7 +352,8 @@ 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() ? user_xstate_size + FP_XSTATE_MAGIC2_SIZE :
+			user_xstate_size;
 }
 
 /*

@@ -385,12 +397,12 @@ 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 = 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 = user_xstate_size;
 
 	if (config_enabled(CONFIG_IA32_EMULATION) ||
 	    config_enabled(CONFIG_X86_32)) {

111 lines not on this page · raw message

index 01e127e..68a5fa4 100644
@@ -365,7 +365,7 @@ 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 kernel_xstate_size;
 extern unsigned int user_xstate_size;
 
 struct perf_event;

index d25097c..faa00c0 100644
@@ -214,7 +214,7 @@ void fpstate_init(union fpregs_state *state)
 		return;
 	}
 
-	memset(state, 0, xstate_size);
+	memset(state, 0, kernel_xstate_size);
 
 	if (cpu_has_fxsr)
 		fpstate_init_fxstate(&state->fxsave);

@@ -238,7 +238,7 @@ static void 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, kernel_xstate_size);
 
 	/*
 	 * Save current FPU registers directly into the child

@@ -258,7 +258,7 @@ static void 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, kernel_xstate_size);
 		fpregs_deactivate(src_fpu);
 	}
 	preempt_enable();

index 4ac2561..b5952d5 100644
@@ -143,8 +143,8 @@ 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 kernel_xstate_size;
+EXPORT_SYMBOL_GPL(kernel_xstate_size);
 
 /* Get alignment of the TYPE. */
 #define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test)

@@ -176,7 +176,7 @@ static void __init fpu__init_task_struct_size(void)
 	 * Add back the dynamically-calculated register state
 	 * size.
 	 */
-	task_size += xstate_size;
+	task_size += kernel_xstate_size;
 
 	/*
 	 * We dynamically size 'struct fpu', so we require that

@@ -193,7 +193,7 @@ static void __init fpu__init_task_struct_size(void)
 }
 
 /*
- * Set up the user and kernel 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.

@@ -206,7 +206,7 @@ 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 overwriten later during
 	 * fpu__init_system_xstate().
 	 */
 

@@ -217,15 +217,15 @@ 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);
+		kernel_xstate_size = sizeof(struct swregs_state);
 	} else {
 		if (cpu_has_fxsr)
-			xstate_size = sizeof(struct fxregs_state);
+			kernel_xstate_size = sizeof(struct fxregs_state);
 		else
-			xstate_size = sizeof(struct fregs_state);
+			kernel_xstate_size = sizeof(struct fregs_state);
 	}
 
-	user_xstate_size = xstate_size;
+	user_xstate_size = kernel_xstate_size;
 
 	/*
 	 * Quirk: we don't yet handle the XSAVES* instructions

index ee6d662..0fbf60c 100644
@@ -261,7 +261,7 @@ 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 = kernel_xstate_size;
 	u64 xfeatures = 0;
 	int fx_only = 0;
 

index 9d41c0f..b8d6d98 100644
@@ -517,7 +517,7 @@ 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 != kernel_xstate_size);
 }
 
 

@@ -596,7 +596,7 @@ 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;
+	kernel_xstate_size = possible_xstate_size;
 	do_extra_xstate_size_checks();
 
 	/*

@@ -659,14 +659,14 @@ void __init fpu__init_system_xstate(void)
 		return;
 	}
 
-	update_regset_xstate_info(xstate_size, xfeatures_mask);
+	update_regset_xstate_info(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,
+		kernel_xstate_size,
 		cpu_has_xsaves ? "compacted" : "standard");
 }
 

index b8d6d98..25e11a1 100644
@@ -311,13 +311,11 @@ static void __init setup_init_fpu_buf(void)
 	setup_xstate_features();
 	print_xstate_features();
 
-	if (cpu_has_xsaves) {
+	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
+	 * Init all the features state with header.xfeatures being 0x0
 	 */
 	copy_kernel_to_xregs_booting(&init_fpstate.xsave);
 

index 0fbf60c..09945f1 100644
@@ -130,6 +130,45 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
 	return err;
 }
 
+static int may_copy_fpregs_to_sigframe(void)
+{
+	/*
+	 * In signal handling path, the kernel already checks if
+	 * FPU instructions have been used before it calls
+	 * copy_fpstate_to_sigframe(). We check this here again
+	 * to detect any potential mis-use and saving invalid
+	 * register values directly to a signal frame.
+	 */
+	WARN_ONCE(!current->thread.fpu.fpstate_active,
+		  "direct FPU save with no math use\n");
+
+	/*
+	 * In the case that we are using a compacted kernel
+	 * xsave area, we can not copy the thread.fpu.state
+	 * directly to userspace and *must* save it from the
+	 * registers directly.
+	 */
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		return 1;
+
+	/*
+	 * fpregs_active() means "Can I use the FPU hardware
+	 * without taking a device-not-available exception?" This
+	 * means that saving the registers directly will be
+	 * cheaper than copying their contents out of
+	 * thread.fpu.state.
+	 *
+	 * Note that fpregs_active() is inherently racy and may
+	 * become false at any time.  If this race happens, we
+	 * will take a harmless device-not-available exception
+	 * when we attempt the FPU save instruction.
+	 */
+	if (fpregs_active())
+		return 1;
+
+	return 0;
+}
+
 /*
  * Save the fpu, extended register state to the user signal frame.
  *

@@ -167,7 +206,7 @@ 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 (may_copy_fpregs_to_sigframe()) {
 		/* Save the live register state to the user directly. */
 		if (copy_fpregs_to_sigframe(buf_fx))
 			return -1;

index 25e11a1..6e42b87 100644
@@ -252,6 +252,33 @@ static void __init print_xstate_features(void)
 }
 
 /*
+ * This check is important because it is easy to get XSTATE_*
+ * confused with XSTATE_BIT_*.
+ */
+#define CHECK_XFEATURE(nr) do {		\
+	WARN_ON(nr < FIRST_EXTENDED_XFEATURE);	\
+	WARN_ON(nr >= XFEATURE_MAX);	\
+} while (0)
+
+/*
+ * We could cache this like xstate_size[], but we only use
+ * it here, so it would be a waste of space.
+ */
+static int xfeature_is_aligned(int xfeature_nr)
+{
+	u32 eax, ebx, ecx, edx;
+
+	CHECK_XFEATURE(xfeature_nr);
+	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
+	/*
+	 * The value returned by ECX[1] indicates the alignment
+	 * of state component i when the compacted format
+	 * of the extended region of an XSAVE area is used
+	 */
+	return !!(ecx & 2);
+}
+
+/*
  * 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.

@@ -288,10 +315,14 @@ static void __init setup_xstate_comp(void)
 		else
 			xstate_comp_sizes[i] = 0;
 
-		if (i > FIRST_EXTENDED_XFEATURE)
+		if (i > FIRST_EXTENDED_XFEATURE) {
 			xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
 					+ xstate_comp_sizes[i-1];
 
+			if (xfeature_is_aligned(i))
+				xstate_comp_offsets[i] =
+					ALIGN(xstate_comp_offsets[i], 64);
+		}
 	}
 }
 

@@ -348,33 +379,6 @@ static int xfeature_is_user(int xfeature_nr)
 }
 */
 
-/*
- * This check is important because it is easy to get XSTATE_*
- * confused with XSTATE_BIT_*.
- */
-#define CHECK_XFEATURE(nr) do {		\
-	WARN_ON(nr < FIRST_EXTENDED_XFEATURE);	\
-	WARN_ON(nr >= XFEATURE_MAX);	\
-} while (0)
-
-/*
- * We could cache this like xstate_size[], but we only use
- * it here, so it would be a waste of space.
- */
-static int xfeature_is_aligned(int xfeature_nr)
-{
-	u32 eax, ebx, ecx, edx;
-
-	CHECK_XFEATURE(xfeature_nr);
-	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
-	/*
-	 * The value returned by ECX[1] indicates the alignment
-	 * of state component i when the compacted format
-	 * of the extended region of an XSAVE area is used
-	 */
-	return !!(ecx & 2);
-}
-
 static int xfeature_uncompacted_offset(int xfeature_nr)
 {
 	u32 eax, ebx, ecx, edx;

index 1c6f6ac..11466cf 100644
@@ -108,6 +108,7 @@ enum xfeature {
 	XFEATURE_OPMASK,
 	XFEATURE_ZMM_Hi256,
 	XFEATURE_Hi16_ZMM,
+	XFEATURE_PT,
 
 	XFEATURE_MAX,
 };

@@ -120,6 +121,7 @@ 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)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
 #define XFEATURE_MASK_AVX512		(XFEATURE_MASK_OPMASK \

index c6667f2..b4f5d94 100644
@@ -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)

84 lines not on this page · raw message

index b4f5d94..a5cd808 100644
@@ -50,5 +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 copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
+			void __user *ubuf, const struct xregs_state *xsave);
+int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
+		     struct xregs_state *xsave);
 
 #endif

80 lines not on this page · raw message

194 lines not on this page · raw message

index b9d4d59..2e80d6f 100644
@@ -251,8 +251,6 @@ static void __init setup_xstate_features(void)
 		WARN_ONCE(last_good_offset > xstate_offsets[i],
 			"x86/fpu: misordered xstate at %d\n", last_good_offset);
 		last_good_offset = xstate_offsets[i];
-
-		printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n", i, ebx, i, eax);
 	}
 }
 

@@ -355,6 +353,21 @@ static void __init setup_xstate_comp(void)
 }
 
 /*
+ * Print out xstate component offsets and sizes
+ */
+static void __init print_xstate_offset_size(void)
+{
+	int i;
+
+	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
+		if (!xfeature_enabled(i))
+			continue;
+		pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n",
+			 i, xstate_comp_offsets[i], i, xstate_sizes[i]);
+	}
+}
+
+/*
  * setup the xstate image representing the init state
  */
 static void __init setup_init_fpu_buf(void)

@@ -687,6 +700,7 @@ void __init fpu__init_system_xstate(void)
 	fpu__init_prepare_fx_sw_frame();
 	setup_init_fpu_buf();
 	setup_xstate_comp();
+	print_xstate_offset_size();
 
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
 		xfeatures_mask,

index b5952d5..21e0d52 100644
@@ -228,19 +228,11 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 	user_xstate_size = kernel_xstate_size;
 
 	/*
-	 * 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. )
+	 * Most recent CPUs supporting XSAVES can run 64-bit mode.
+	 * Enable XSAVES for 64-bit.
 	 */
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+	if (!config_enabled(CONFIG_X86_64))
+		setup_clear_cpu_cap(X86_FEATURE_XSAVES);
 }
 
 /*

index 2e80d6f..cb2a484 100644
@@ -204,6 +204,14 @@ void fpu__init_cpu_xstate(void)
 	if (!cpu_has_xsave || !xfeatures_mask)
 		return;
 
+	/*
+	 * Make it clear that XSAVES supervisor states are not yet
+	 * implemented should anyone expect it to work by changing
+	 * bits in XFEATURE_MASK_* macros and XCR0.
+	 */
+	WARN_ONCE((xfeatures_mask & XFEATURE_MASK_SUPERVISOR),
+		"x86/fpu: XSAVES supervisor states are not yet implemented.\n");
+
 	cr4_set_bits(X86_CR4_OSXSAVE);
 	xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
 }