6 files changed, 209 insertions, 89 deletions

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 520deb411a70..91d6341f281f 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -60,9 +60,16 @@ bool irq_fpu_usable(void)
 	if (WARN_ON_ONCE(in_nmi()))
 		return false;
 
-	/* In kernel FPU usage already active? */
-	if (this_cpu_read(in_kernel_fpu))
+	/*
+	 * In kernel FPU usage already active?  This detects any explicitly
+	 * nested usage in task or softirq context, which is unsupported.  It
+	 * also detects attempted usage in a hardirq that has interrupted a
+	 * kernel-mode FPU section.
+	 */
+	if (this_cpu_read(in_kernel_fpu)) {
+		WARN_ON_FPU(!in_hardirq());
 		return false;
+	}
 
 	/*
 	 * When not in NMI or hard interrupt context, FPU can be used in:
@@ -145,8 +152,8 @@ void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask)
 		asm volatile(
 			"fnclex\n\t"
 			"emms\n\t"
-			"fildl %P[addr]"	/* set F?P to defined value */
-			: : [addr] "m" (fpstate));
+			"fildl %[addr]"	/* set F?P to defined value */
+			: : [addr] "m" (*fpstate));
 	}
 
 	if (use_xsave()) {
@@ -220,7 +227,7 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 	struct fpstate *fpstate;
 	unsigned int size;
 
-	size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
+	size = fpu_kernel_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
 	fpstate = vzalloc(size);
 	if (!fpstate)
 		return false;
@@ -232,8 +239,8 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 	fpstate->is_guest	= true;
 
 	gfpu->fpstate		= fpstate;
-	gfpu->xfeatures		= fpu_user_cfg.default_features;
-	gfpu->perm		= fpu_user_cfg.default_features;
+	gfpu->xfeatures		= fpu_kernel_cfg.default_features;
+	gfpu->perm		= fpu_kernel_cfg.default_features;
 
 	/*
 	 * KVM sets the FP+SSE bits in the XSAVE header when copying FPU state
@@ -420,7 +427,8 @@ EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);
 
 void kernel_fpu_begin_mask(unsigned int kfpu_mask)
 {
-	preempt_disable();
+	if (!irqs_disabled())
+		fpregs_lock();
 
 	WARN_ON_FPU(!irq_fpu_usable());
 	WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
@@ -448,7 +456,8 @@ void kernel_fpu_end(void)
 	WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
 
 	this_cpu_write(in_kernel_fpu, false);
-	preempt_enable();
+	if (!irqs_disabled())
+		fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 
@@ -499,7 +508,7 @@ static inline void fpstate_init_fstate(struct fpstate *fpstate)
 /*
  * Used in two places:
  * 1) Early boot to setup init_fpstate for non XSAVE systems
- * 2) fpu_init_fpstate_user() which is invoked from KVM
+ * 2) fpu_alloc_guest_fpstate() which is invoked from KVM
  */
 void fpstate_init_user(struct fpstate *fpstate)
 {
diff --git a/arch/x86/kernel/fpu/internal.h b/arch/x86/kernel/fpu/internal.h
index dbdb31f55fc7..975de070c9c9 100644
--- a/arch/x86/kernel/fpu/internal.h
+++ b/arch/x86/kernel/fpu/internal.h
@@ -18,7 +18,7 @@ static __always_inline __pure bool use_fxsr(void)
 #ifdef CONFIG_X86_DEBUG_FPU
 # define WARN_ON_FPU(x) WARN_ON_ONCE(x)
 #else
-# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+# define WARN_ON_FPU(x) ({ BUILD_BUG_ON_INVALID(x); 0; })
 #endif
 
 /* Used in init.c */
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 6bc1eb2a21bd..887b0b8e21e3 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -190,7 +190,8 @@ int ssp_get(struct task_struct *target, const struct user_regset *regset,
 	struct fpu *fpu = &target->thread.fpu;
 	struct cet_user_state *cetregs;
 
-	if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK))
+	if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) ||
+	    !ssp_active(target, regset))
 		return -ENODEV;
 
 	sync_fpstate(fpu);
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 247f2225aa9f..6c69cb28b298 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -27,19 +27,14 @@
 static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 					    struct _fpx_sw_bytes *fx_sw)
 {
-	int min_xstate_size = sizeof(struct fxregs_state) +
-			      sizeof(struct xstate_header);
 	void __user *fpstate = fxbuf;
 	unsigned int magic2;
 
 	if (__copy_from_user(fx_sw, &fxbuf->sw_reserved[0], sizeof(*fx_sw)))
 		return false;
 
-	/* 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 > current->thread.fpu.fpstate->user_size ||
-	    fx_sw->xstate_size > fx_sw->extended_size)
+	/* Check for the first magic field */
+	if (fx_sw->magic1 != FP_XSTATE_MAGIC1)
 		goto setfx;
 
 	/*
@@ -48,7 +43,7 @@ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 	 * fpstate layout with out copying the extended state information
 	 * in the memory layout.
 	 */
-	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)))
+	if (__get_user(magic2, (__u32 __user *)(fpstate + current->thread.fpu.fpstate->user_size)))
 		return false;
 
 	if (likely(magic2 == FP_XSTATE_MAGIC2))
@@ -156,10 +151,11 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 	return !err;
 }
 
-static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
+static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru)
 {
 	if (use_xsave())
-		return xsave_to_user_sigframe(buf);
+		return xsave_to_user_sigframe(buf, pkru);
+
 	if (use_fxsr())
 		return fxsave_to_user_sigframe((struct fxregs_state __user *) buf);
 	else
@@ -185,7 +181,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
  * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
  * indicating the absence/presence of the extended state to the user.
  */
-bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
+bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size, u32 pkru)
 {
 	struct task_struct *tsk = current;
 	struct fpstate *fpstate = tsk->thread.fpu.fpstate;
@@ -228,7 +224,7 @@ retry:
 		fpregs_restore_userregs();
 
 	pagefault_disable();
-	ret = copy_fpregs_to_sigframe(buf_fx);
+	ret = copy_fpregs_to_sigframe(buf_fx, pkru);
 	pagefault_enable();
 	fpregs_unlock();
 
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 33a214b1a4ce..6a41d1610d8b 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -13,16 +13,20 @@
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
 #include <linux/vmalloc.h>
+#include <linux/coredump.h>
 
 #include <asm/fpu/api.h>
 #include <asm/fpu/regset.h>
 #include <asm/fpu/signal.h>
 #include <asm/fpu/xcr.h>
 
+#include <asm/cpuid.h>
 #include <asm/tlbflush.h>
 #include <asm/prctl.h>
 #include <asm/elf.h>
 
+#include <uapi/asm/elf.h>
+
 #include "context.h"
 #include "internal.h"
 #include "legacy.h"
@@ -229,7 +233,7 @@ static void __init setup_xstate_cache(void)
 						       xmm_space);
 
 	for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
-		cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+		cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx);
 
 		xstate_sizes[i] = eax;
 		xstate_flags[i] = ecx;
@@ -255,32 +259,20 @@ static void __init setup_xstate_cache(void)
 	}
 }
 
-static void __init print_xstate_feature(u64 xstate_mask)
-{
-	const char *feature_name;
-
-	if (cpu_has_xfeatures(xstate_mask, &feature_name))
-		pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", xstate_mask, feature_name);
-}
-
 /*
  * Print out all the supported xstate features:
  */
 static void __init print_xstate_features(void)
 {
-	print_xstate_feature(XFEATURE_MASK_FP);
-	print_xstate_feature(XFEATURE_MASK_SSE);
-	print_xstate_feature(XFEATURE_MASK_YMM);
-	print_xstate_feature(XFEATURE_MASK_BNDREGS);
-	print_xstate_feature(XFEATURE_MASK_BNDCSR);
-	print_xstate_feature(XFEATURE_MASK_OPMASK);
-	print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
-	print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
-	print_xstate_feature(XFEATURE_MASK_PKRU);
-	print_xstate_feature(XFEATURE_MASK_PASID);
-	print_xstate_feature(XFEATURE_MASK_CET_USER);
-	print_xstate_feature(XFEATURE_MASK_XTILE_CFG);
-	print_xstate_feature(XFEATURE_MASK_XTILE_DATA);
+	int i;
+
+	for (i = 0; i < XFEATURE_MAX; i++) {
+		u64 mask = BIT_ULL(i);
+		const char *name;
+
+		if (cpu_has_xfeatures(mask, &name))
+			pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", mask, name);
+	}
 }
 
 /*
@@ -395,7 +387,7 @@ int xfeature_size(int xfeature_nr)
 	u32 eax, ebx, ecx, edx;
 
 	CHECK_XFEATURE(xfeature_nr);
-	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
+	cpuid_count(CPUID_LEAF_XSTATE, xfeature_nr, &eax, &ebx, &ecx, &edx);
 	return eax;
 }
 
@@ -438,9 +430,9 @@ static void __init __xstate_dump_leaves(void)
 	 * just in case there are some goodies up there
 	 */
 	for (i = 0; i < XFEATURE_MAX + 10; i++) {
-		cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+		cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx);
 		pr_warn("CPUID[%02x, %02x]: eax=%08x ebx=%08x ecx=%08x edx=%08x\n",
-			XSTATE_CPUID, i, eax, ebx, ecx, edx);
+			CPUID_LEAF_XSTATE, i, eax, ebx, ecx, edx);
 	}
 }
 
@@ -481,7 +473,7 @@ static int __init check_xtile_data_against_struct(int size)
 	 * Check the maximum palette id:
 	 *   eax: the highest numbered palette subleaf.
 	 */
-	cpuid_count(TILE_CPUID, 0, &max_palid, &ebx, &ecx, &edx);
+	cpuid_count(CPUID_LEAF_TILE, 0, &max_palid, &ebx, &ecx, &edx);
 
 	/*
 	 * Cross-check each tile size and find the maximum number of
@@ -495,7 +487,7 @@ static int __init check_xtile_data_against_struct(int size)
 		 *   eax[31:16]:  bytes per title
 		 *   ebx[31:16]:  the max names (or max number of tiles)
 		 */
-		cpuid_count(TILE_CPUID, palid, &eax, &ebx, &edx, &edx);
+		cpuid_count(CPUID_LEAF_TILE, palid, &eax, &ebx, &edx, &edx);
 		tile_size = eax >> 16;
 		max = ebx >> 16;
 
@@ -630,7 +622,7 @@ static unsigned int __init get_compacted_size(void)
 	 * are no supervisor states, but XSAVEC still uses compacted
 	 * format.
 	 */
-	cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
+	cpuid_count(CPUID_LEAF_XSTATE, 1, &eax, &ebx, &ecx, &edx);
 	return ebx;
 }
 
@@ -671,7 +663,7 @@ static unsigned int __init get_xsave_size_user(void)
 	 *    containing all the *user* state components
 	 *    corresponding to bits currently set in XCR0.
 	 */
-	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+	cpuid_count(CPUID_LEAF_XSTATE, 0, &eax, &ebx, &ecx, &edx);
 	return ebx;
 }
 
@@ -760,21 +752,16 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 		return;
 	}
 
-	if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
-		WARN_ON_FPU(1);
-		return;
-	}
-
 	/*
 	 * Find user xstates supported by the processor.
 	 */
-	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+	cpuid_count(CPUID_LEAF_XSTATE, 0, &eax, &ebx, &ecx, &edx);
 	fpu_kernel_cfg.max_features = eax + ((u64)edx << 32);
 
 	/*
 	 * Find supervisor xstates supported by the processor.
 	 */
-	cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
+	cpuid_count(CPUID_LEAF_XSTATE, 1, &eax, &ebx, &ecx, &edx);
 	fpu_kernel_cfg.max_features |= ecx + ((u64)edx << 32);
 
 	if ((fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
@@ -788,6 +775,9 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 		goto out_disable;
 	}
 
+	fpu_kernel_cfg.independent_features = fpu_kernel_cfg.max_features &
+					      XFEATURE_MASK_INDEPENDENT;
+
 	/*
 	 * Clear XSAVE features that are disabled in the normal CPUID.
 	 */
@@ -991,6 +981,20 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 
 	return __raw_xsave_addr(xsave, xfeature_nr);
 }
+EXPORT_SYMBOL_GPL(get_xsave_addr);
+
+/*
+ * Given an xstate feature nr, calculate where in the xsave buffer the state is.
+ * The xsave buffer should be in standard format, not compacted (e.g. user mode
+ * signal frames).
+ */
+void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr)
+{
+	if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr)))
+		return NULL;
+
+	return (void __user *)xsave + xstate_offsets[xfeature_nr];
+}
 
 #ifdef CONFIG_ARCH_HAS_PKEYS
 
@@ -1434,8 +1438,8 @@ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor)
 		return rstor;
 
 	/*
-	 * XSAVE(S): clone(), fpu_swap_kvm_fpu()
-	 * XRSTORS(S): fpu_swap_kvm_fpu()
+	 * XSAVE(S): clone(), fpu_swap_kvm_fpstate()
+	 * XRSTORS(S): fpu_swap_kvm_fpstate()
 	 */
 
 	/*
@@ -1837,3 +1841,89 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
 	return 0;
 }
 #endif /* CONFIG_PROC_PID_ARCH_STATUS */
+
+#ifdef CONFIG_COREDUMP
+static const char owner_name[] = "LINUX";
+
+/*
+ * Dump type, size, offset and flag values for every xfeature that is present.
+ */
+static int dump_xsave_layout_desc(struct coredump_params *cprm)
+{
+	int num_records = 0;
+	int i;
+
+	for_each_extended_xfeature(i, fpu_user_cfg.max_features) {
+		struct x86_xfeat_component xc = {
+			.type   = i,
+			.size   = xstate_sizes[i],
+			.offset = xstate_offsets[i],
+			/* reserved for future use */
+			.flags  = 0,
+		};
+
+		if (!dump_emit(cprm, &xc, sizeof(xc)))
+			return 0;
+
+		num_records++;
+	}
+	return num_records;
+}
+
+static u32 get_xsave_desc_size(void)
+{
+	u32 cnt = 0;
+	u32 i;
+
+	for_each_extended_xfeature(i, fpu_user_cfg.max_features)
+		cnt++;
+
+	return cnt * (sizeof(struct x86_xfeat_component));
+}
+
+int elf_coredump_extra_notes_write(struct coredump_params *cprm)
+{
+	int num_records = 0;
+	struct elf_note en;
+
+	if (!fpu_user_cfg.max_features)
+		return 0;
+
+	en.n_namesz = sizeof(owner_name);
+	en.n_descsz = get_xsave_desc_size();
+	en.n_type = NT_X86_XSAVE_LAYOUT;
+
+	if (!dump_emit(cprm, &en, sizeof(en)))
+		return 1;
+	if (!dump_emit(cprm, owner_name, en.n_namesz))
+		return 1;
+	if (!dump_align(cprm, 4))
+		return 1;
+
+	num_records = dump_xsave_layout_desc(cprm);
+	if (!num_records)
+		return 1;
+
+	/* Total size should be equal to the number of records */
+	if ((sizeof(struct x86_xfeat_component) * num_records) != en.n_descsz)
+		return 1;
+
+	return 0;
+}
+
+int elf_coredump_extra_notes_size(void)
+{
+	int size;
+
+	if (!fpu_user_cfg.max_features)
+		return 0;
+
+	/* .note header */
+	size  = sizeof(struct elf_note);
+	/*  Name plus alignment to 4 bytes */
+	size += roundup(sizeof(owner_name), 4);
+	size += get_xsave_desc_size();
+
+	return size;
+}
+#endif /* CONFIG_COREDUMP */
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 19ca623ffa2a..0fd34f53f025 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -54,7 +54,7 @@ extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void
 extern void fpu__init_cpu_xstate(void);
 extern void fpu__init_system_xstate(unsigned int legacy_size);
 
-extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
+extern void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr);
 
 static inline u64 xfeatures_mask_supervisor(void)
 {
@@ -64,38 +64,63 @@ static inline u64 xfeatures_mask_supervisor(void)
 static inline u64 xfeatures_mask_independent(void)
 {
 	if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR))
-		return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR;
+		return fpu_kernel_cfg.independent_features & ~XFEATURE_MASK_LBR;
 
-	return XFEATURE_MASK_INDEPENDENT;
+	return fpu_kernel_cfg.independent_features;
+}
+
+/*
+ * Update the value of PKRU register that was already pushed onto the signal frame.
+ */
+static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru)
+{
+	u64 xstate_bv;
+	int err;
+
+	if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
+		return 0;
+
+	/* Mark PKRU as in-use so that it is restored correctly. */
+	xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU;
+
+	err =  __put_user(xstate_bv, &buf->header.xfeatures);
+	if (err)
+		return err;
+
+	/* Update PKRU value in the userspace xsave buffer. */
+	return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU));
 }
 
 /* XSAVE/XRSTOR wrapper functions */
 
 #ifdef CONFIG_X86_64
-#define REX_PREFIX	"0x48, "
+#define REX_SUFFIX	"64"
 #else
-#define REX_PREFIX
+#define REX_SUFFIX
 #endif
 
-/* 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 XSAVEC		".byte " REX_PREFIX "0x0f,0xc7,0x27"
-#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 XSAVE		"xsave" REX_SUFFIX " %[xa]"
+#define XSAVEOPT	"xsaveopt" REX_SUFFIX " %[xa]"
+#define XSAVEC		"xsavec" REX_SUFFIX " %[xa]"
+#define XSAVES		"xsaves" REX_SUFFIX " %[xa]"
+#define XRSTOR		"xrstor" REX_SUFFIX " %[xa]"
+#define XRSTORS		"xrstors" REX_SUFFIX " %[xa]"
 
 /*
  * After this @err contains 0 on success or the trap number when the
  * operation raises an exception.
+ *
+ * The [xa] input parameter below represents the struct xregs_state pointer
+ * and the asm symbolic name for the argument used in the XSAVE/XRSTOR insns
+ * above.
  */
 #define XSTATE_OP(op, st, lmask, hmask, err)				\
 	asm volatile("1:" op "\n\t"					\
 		     "xor %[err], %[err]\n"				\
-		     "2:\n\t"						\
+		     "2:\n"						\
 		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE)	\
 		     : [err] "=a" (err)					\
-		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : [xa] "m" (*(st)), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
 /*
@@ -108,23 +133,19 @@ static inline u64 xfeatures_mask_independent(void)
  * 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.
+ * Use XSAVE as a fallback.
  */
 #define XSTATE_XSAVE(st, lmask, hmask, err)				\
-	asm volatile(ALTERNATIVE_3(XSAVE,				\
+	asm volatile("1: " ALTERNATIVE_3(XSAVE,				\
 				   XSAVEOPT, X86_FEATURE_XSAVEOPT,	\
 				   XSAVEC,   X86_FEATURE_XSAVEC,	\
 				   XSAVES,   X86_FEATURE_XSAVES)	\
-		     "\n"						\
+		     "\n\t"						\
 		     "xor %[err], %[err]\n"				\
 		     "3:\n"						\
-		     _ASM_EXTABLE_TYPE_REG(661b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
+		     _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
 		     : [err] "=r" (err)					\
-		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : [xa] "m" (*(st)), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
 /*
@@ -132,13 +153,13 @@ static inline u64 xfeatures_mask_independent(void)
  * XSAVE area format.
  */
 #define XSTATE_XRESTORE(st, lmask, hmask)				\
-	asm volatile(ALTERNATIVE(XRSTOR,				\
+	asm volatile("1: " ALTERNATIVE(XRSTOR,				\
 				 XRSTORS, X86_FEATURE_XSAVES)		\
 		     "\n"						\
 		     "3:\n"						\
-		     _ASM_EXTABLE_TYPE(661b, 3b, EX_TYPE_FPU_RESTORE)	\
+		     _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE)	\
 		     :							\
-		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : [xa] "m" (*(st)), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU)
@@ -260,7 +281,7 @@ static inline u64 xfeatures_need_sigframe_write(void)
  * The caller has to zero buf::header before calling this because XSAVE*
  * does not touch the reserved fields in the header.
  */
-static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
+static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkru)
 {
 	/*
 	 * Include the features which are not xsaved/rstored by the kernel
@@ -285,6 +306,9 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
 	XSTATE_OP(XSAVE, buf, lmask, hmask, err);
 	clac();
 
+	if (!err)
+		err = update_pkru_in_sigframe(buf, mask, pkru);
+
 	return err;
 }