1 files changed, 244 insertions, 98 deletions

diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 117e74c44e75..9aa9ac8399ae 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -13,16 +13,22 @@
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
 #include <linux/vmalloc.h>
+#include <linux/coredump.h>
+#include <linux/sort.h>
 
 #include <asm/fpu/api.h>
 #include <asm/fpu/regset.h>
 #include <asm/fpu/signal.h>
 #include <asm/fpu/xcr.h>
 
+#include <asm/cpuid/api.h>
+#include <asm/msr.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"
@@ -58,6 +64,7 @@ static const char *xfeature_names[] =
 	"unknown xstate feature",
 	"AMX Tile config",
 	"AMX Tile data",
+	"APX registers",
 	"unknown xstate feature",
 };
 
@@ -76,6 +83,7 @@ static unsigned short xsave_cpuid_features[] __initdata = {
 	[XFEATURE_CET_USER]			= X86_FEATURE_SHSTK,
 	[XFEATURE_XTILE_CFG]			= X86_FEATURE_AMX_TILE,
 	[XFEATURE_XTILE_DATA]			= X86_FEATURE_AMX_TILE,
+	[XFEATURE_APX]				= X86_FEATURE_APX,
 };
 
 static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init =
@@ -84,6 +92,31 @@ static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init =
 	{ [ 0 ... XFEATURE_MAX - 1] = -1};
 static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init;
 
+/*
+ * Ordering of xstate components in uncompacted format:  The xfeature
+ * number does not necessarily indicate its position in the XSAVE buffer.
+ * This array defines the traversal order of xstate features.
+ */
+static unsigned int xfeature_uncompact_order[XFEATURE_MAX] __ro_after_init =
+	{ [ 0 ... XFEATURE_MAX - 1] = -1};
+
+static inline unsigned int next_xfeature_order(unsigned int i, u64 mask)
+{
+	for (; xfeature_uncompact_order[i] != -1; i++) {
+		if (mask & BIT_ULL(xfeature_uncompact_order[i]))
+			break;
+	}
+
+	return i;
+}
+
+/* Iterate xstate features in uncompacted order: */
+#define for_each_extended_xfeature_in_order(i, mask)	\
+	for (i = 0;					\
+	     i = next_xfeature_order(i, mask),		\
+	     xfeature_uncompact_order[i] != -1;		\
+	     i++)
+
 #define XSTATE_FLAG_SUPERVISOR	BIT(0)
 #define XSTATE_FLAG_ALIGNED64	BIT(1)
 
@@ -178,10 +211,11 @@ void fpu__init_cpu_xstate(void)
 	 * Must happen after CR4 setup and before xsetbv() to allow KVM
 	 * lazy passthrough.  Write independent of the dynamic state static
 	 * key as that does not work on the boot CPU. This also ensures
-	 * that any stale state is wiped out from XFD.
+	 * that any stale state is wiped out from XFD. Reset the per CPU
+	 * xfd cache too.
 	 */
 	if (cpu_feature_enabled(X86_FEATURE_XFD))
-		wrmsrl(MSR_IA32_XFD, init_fpstate.xfd);
+		xfd_set_state(init_fpstate.xfd);
 
 	/*
 	 * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features
@@ -194,7 +228,7 @@ void fpu__init_cpu_xstate(void)
 	 * MSR_IA32_XSS sets supervisor states managed by XSAVES.
 	 */
 	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
-		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+		wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() |
 				     xfeatures_mask_independent());
 	}
 }
@@ -204,16 +238,20 @@ static bool xfeature_enabled(enum xfeature xfeature)
 	return fpu_kernel_cfg.max_features & BIT_ULL(xfeature);
 }
 
+static int compare_xstate_offsets(const void *xfeature1, const void *xfeature2)
+{
+	return  xstate_offsets[*(unsigned int *)xfeature1] -
+		xstate_offsets[*(unsigned int *)xfeature2];
+}
+
 /*
  * Record the offsets and sizes of various xstates contained
- * in the XSAVE state memory layout.
+ * in the XSAVE state memory layout. Also, create an ordered
+ * list of xfeatures for handling out-of-order offsets.
  */
 static void __init setup_xstate_cache(void)
 {
-	u32 eax, ebx, ecx, edx, i;
-	/* start at the beginning of the "extended state" */
-	unsigned int last_good_offset = offsetof(struct xregs_state,
-						 extended_state_area);
+	u32 eax, ebx, ecx, edx, xfeature, i = 0;
 	/*
 	 * The FP xstates and SSE xstates are legacy states. They are always
 	 * in the fixed offsets in the xsave area in either compacted form
@@ -227,39 +265,30 @@ static void __init setup_xstate_cache(void)
 	xstate_sizes[XFEATURE_SSE]	= sizeof_field(struct fxregs_state,
 						       xmm_space);
 
-	for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
-		cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+	for_each_extended_xfeature(xfeature, fpu_kernel_cfg.max_features) {
+		cpuid_count(CPUID_LEAF_XSTATE, xfeature, &eax, &ebx, &ecx, &edx);
 
-		xstate_sizes[i] = eax;
-		xstate_flags[i] = ecx;
+		xstate_sizes[xfeature] = eax;
+		xstate_flags[xfeature] = ecx;
 
 		/*
 		 * If an xfeature is supervisor state, the offset in EBX is
 		 * invalid, leave it to -1.
 		 */
-		if (xfeature_is_supervisor(i))
+		if (xfeature_is_supervisor(xfeature))
 			continue;
 
-		xstate_offsets[i] = ebx;
-
-		/*
-		 * In our xstate size checks, we assume that the highest-numbered
-		 * xstate feature has the highest offset in the buffer.  Ensure
-		 * it does.
-		 */
-		WARN_ONCE(last_good_offset > xstate_offsets[i],
-			  "x86/fpu: misordered xstate at %d\n", last_good_offset);
+		xstate_offsets[xfeature] = ebx;
 
-		last_good_offset = xstate_offsets[i];
+		/* Populate the list of xfeatures before sorting */
+		xfeature_uncompact_order[i++] = xfeature;
 	}
-}
-
-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);
+	/*
+	 * Sort xfeatures by their offsets to support out-of-order
+	 * offsets in the uncompacted format.
+	 */
+	sort(xfeature_uncompact_order, i, sizeof(unsigned int), compare_xstate_offsets, NULL);
 }
 
 /*
@@ -267,19 +296,15 @@ static void __init print_xstate_feature(u64 xstate_mask)
  */
 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);
+	}
 }
 
 /*
@@ -347,7 +372,8 @@ static __init void os_xrstor_booting(struct xregs_state *xstate)
 	 XFEATURE_MASK_BNDCSR |			\
 	 XFEATURE_MASK_PASID |			\
 	 XFEATURE_MASK_CET_USER |		\
-	 XFEATURE_MASK_XTILE)
+	 XFEATURE_MASK_XTILE |			\
+	 XFEATURE_MASK_APX)
 
 /*
  * setup the xstate image representing the init state
@@ -394,7 +420,7 @@ 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;
 }
 
@@ -437,9 +463,9 @@ 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);
 	}
 }
 
@@ -480,7 +506,7 @@ 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
@@ -494,7 +520,7 @@ 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;
 
@@ -547,6 +573,7 @@ static bool __init check_xstate_against_struct(int nr)
 	case XFEATURE_PASID:	  return XCHECK_SZ(sz, nr, struct ia32_pasid_state);
 	case XFEATURE_XTILE_CFG:  return XCHECK_SZ(sz, nr, struct xtile_cfg);
 	case XFEATURE_CET_USER:	  return XCHECK_SZ(sz, nr, struct cet_user_state);
+	case XFEATURE_APX:        return XCHECK_SZ(sz, nr, struct apx_state);
 	case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true;
 	default:
 		XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr);
@@ -559,13 +586,20 @@ static bool __init check_xstate_against_struct(int nr)
 static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted)
 {
 	unsigned int topmost = fls64(xfeatures) -  1;
-	unsigned int offset = xstate_offsets[topmost];
+	unsigned int offset, i;
 
 	if (topmost <= XFEATURE_SSE)
 		return sizeof(struct xregs_state);
 
-	if (compacted)
+	if (compacted) {
 		offset = xfeature_get_offset(xfeatures, topmost);
+	} else {
+		/* Walk through the xfeature order to pick the last */
+		for_each_extended_xfeature_in_order(i, xfeatures)
+			topmost = xfeature_uncompact_order[i];
+		offset = xstate_offsets[topmost];
+	}
+
 	return offset + xstate_sizes[topmost];
 }
 
@@ -629,7 +663,7 @@ 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;
 }
 
@@ -646,7 +680,7 @@ static unsigned int __init get_xsave_compacted_size(void)
 		return get_compacted_size();
 
 	/* Disable independent features. */
-	wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+	wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor());
 
 	/*
 	 * Ask the hardware what size is required of the buffer.
@@ -655,7 +689,7 @@ static unsigned int __init get_xsave_compacted_size(void)
 	size = get_compacted_size();
 
 	/* Re-enable independent features so XSAVES will work on them again. */
-	wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
+	wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
 
 	return size;
 }
@@ -670,7 +704,7 @@ 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;
 }
 
@@ -718,6 +752,8 @@ static int __init init_xstate_size(void)
  */
 static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
 {
+	pr_info("x86/fpu: XSAVE disabled\n");
+
 	fpu_kernel_cfg.max_features = 0;
 	cr4_clear_bits(X86_CR4_OSXSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
@@ -734,7 +770,7 @@ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
 	 */
 	init_fpstate.xfd = 0;
 
-	fpstate_reset(&current->thread.fpu);
+	fpstate_reset(x86_task_fpu(current));
 }
 
 /*
@@ -759,21 +795,16 @@ 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) {
@@ -787,6 +818,20 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 		goto out_disable;
 	}
 
+	if (fpu_kernel_cfg.max_features & XFEATURE_MASK_APX &&
+	    fpu_kernel_cfg.max_features & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) {
+		/*
+		 * This is a problematic CPU configuration where two
+		 * conflicting state components are both enumerated.
+		 */
+		pr_err("x86/fpu: Both APX/MPX present in the CPU's xstate features: 0x%llx.\n",
+		       fpu_kernel_cfg.max_features);
+		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.
 	 */
@@ -843,9 +888,6 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	if (err)
 		goto out_disable;
 
-	/* Reset the state for the current task */
-	fpstate_reset(&current->thread.fpu);
-
 	/*
 	 * Update info used for ptrace frames; use standard-format size and no
 	 * supervisor xstates:
@@ -861,7 +903,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	init_fpstate.xfeatures		= fpu_kernel_cfg.default_features;
 
 	if (init_fpstate.size > sizeof(init_fpstate.regs)) {
-		pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n",
+		pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d)\n",
 			sizeof(init_fpstate.regs), init_fpstate.size);
 		goto out_disable;
 	}
@@ -873,7 +915,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	 * xfeatures mask.
 	 */
 	if (xfeatures != fpu_kernel_cfg.max_features) {
-		pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n",
+		pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init\n",
 		       xfeatures, fpu_kernel_cfg.max_features);
 		goto out_disable;
 	}
@@ -913,12 +955,12 @@ void fpu__resume_cpu(void)
 	 * of XSAVES and MSR_IA32_XSS.
 	 */
 	if (cpu_feature_enabled(X86_FEATURE_XSAVES)) {
-		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()  |
+		wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor()  |
 				     xfeatures_mask_independent());
 	}
 
 	if (fpu_state_size_dynamic())
-		wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd);
+		wrmsrq(MSR_IA32_XFD, x86_task_fpu(current)->fpstate->xfd);
 }
 
 /*
@@ -990,6 +1032,20 @@ 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
 
@@ -1066,10 +1122,9 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
 	struct xregs_state *xinit = &init_fpstate.regs.xsave;
 	struct xregs_state *xsave = &fpstate->regs.xsave;
+	unsigned int zerofrom, i, xfeature;
 	struct xstate_header header;
-	unsigned int zerofrom;
 	u64 mask;
-	int i;
 
 	memset(&header, 0, sizeof(header));
 	header.xfeatures = xsave->header.xfeatures;
@@ -1138,15 +1193,16 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	 */
 	mask = header.xfeatures;
 
-	for_each_extended_xfeature(i, mask) {
+	for_each_extended_xfeature_in_order(i, mask) {
+		xfeature = xfeature_uncompact_order[i];
 		/*
 		 * If there was a feature or alignment gap, zero the space
 		 * in the destination buffer.
 		 */
-		if (zerofrom < xstate_offsets[i])
-			membuf_zero(&to, xstate_offsets[i] - zerofrom);
+		if (zerofrom < xstate_offsets[xfeature])
+			membuf_zero(&to, xstate_offsets[xfeature] - zerofrom);
 
-		if (i == XFEATURE_PKRU) {
+		if (xfeature == XFEATURE_PKRU) {
 			struct pkru_state pkru = {0};
 			/*
 			 * PKRU is not necessarily up to date in the
@@ -1156,14 +1212,14 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 			membuf_write(&to, &pkru, sizeof(pkru));
 		} else {
 			membuf_write(&to,
-				     __raw_xsave_addr(xsave, i),
-				     xstate_sizes[i]);
+				     __raw_xsave_addr(xsave, xfeature),
+				     xstate_sizes[xfeature]);
 		}
 		/*
 		 * Keep track of the last copied state in the non-compacted
 		 * target buffer for gap zeroing.
 		 */
-		zerofrom = xstate_offsets[i] + xstate_sizes[i];
+		zerofrom = xstate_offsets[xfeature] + xstate_sizes[xfeature];
 	}
 
 out:
@@ -1186,8 +1242,8 @@ out:
 void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
 			     enum xstate_copy_mode copy_mode)
 {
-	__copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
-				  tsk->thread.fpu.fpstate->user_xfeatures,
+	__copy_xstate_to_uabi_buf(to, x86_task_fpu(tsk)->fpstate,
+				  x86_task_fpu(tsk)->fpstate->user_xfeatures,
 				  tsk->thread.pkru, copy_mode);
 }
 
@@ -1327,7 +1383,7 @@ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u
 int copy_sigframe_from_user_to_xstate(struct task_struct *tsk,
 				      const void __user *ubuf)
 {
-	return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru);
+	return copy_uabi_to_xstate(x86_task_fpu(tsk)->fpstate, NULL, ubuf, &tsk->thread.pkru);
 }
 
 static bool validate_independent_components(u64 mask)
@@ -1393,9 +1449,9 @@ void xrstors(struct xregs_state *xstate, u64 mask)
 }
 
 #if IS_ENABLED(CONFIG_KVM)
-void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature)
+void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature)
 {
-	void *addr = get_xsave_addr(&fps->regs.xsave, xfeature);
+	void *addr = get_xsave_addr(&fpstate->regs.xsave, xfeature);
 
 	if (addr)
 		memset(addr, 0, xstate_sizes[xfeature]);
@@ -1421,7 +1477,7 @@ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor)
 	  * The XFD MSR does not match fpstate->xfd. That's invalid when
 	  * the passed in fpstate is current's fpstate.
 	  */
-	if (fpstate->xfd == current->thread.fpu.fpstate->xfd)
+	if (fpstate->xfd == x86_task_fpu(current)->fpstate->xfd)
 		return false;
 
 	/*
@@ -1433,8 +1489,8 @@ 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()
 	 */
 
 	/*
@@ -1498,7 +1554,7 @@ void fpstate_free(struct fpu *fpu)
 static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
 			   unsigned int usize, struct fpu_guest *guest_fpu)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	struct fpstate *curfps, *newfps = NULL;
 	unsigned int fpsize;
 	bool in_use;
@@ -1591,7 +1647,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
 	 * AVX512.
 	 */
 	bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED);
-	struct fpu *fpu = &current->group_leader->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current->group_leader);
 	struct fpu_state_perm *perm;
 	unsigned int ksize, usize;
 	u64 mask;
@@ -1601,16 +1657,20 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
 	if ((permitted & requested) == requested)
 		return 0;
 
-	/* Calculate the resulting kernel state size */
+	/*
+	 * Calculate the resulting kernel state size.  Note, @permitted also
+	 * contains supervisor xfeatures even though supervisor are always
+	 * permitted for kernel and guest FPUs, and never permitted for user
+	 * FPUs.
+	 */
 	mask = permitted | requested;
-	/* Take supervisor states into account on the host */
-	if (!guest)
-		mask |= xfeatures_mask_supervisor();
 	ksize = xstate_calculate_size(mask, compacted);
 
-	/* Calculate the resulting user state size */
-	mask &= XFEATURE_MASK_USER_SUPPORTED;
-	usize = xstate_calculate_size(mask, false);
+	/*
+	 * Calculate the resulting user state size.  Take care not to clobber
+	 * the supervisor xfeatures in the new mask!
+	 */
+	usize = xstate_calculate_size(mask & XFEATURE_MASK_USER_SUPPORTED, false);
 
 	if (!guest) {
 		ret = validate_sigaltstack(usize);
@@ -1694,7 +1754,7 @@ int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu)
 		return -EPERM;
 	}
 
-	fpu = &current->group_leader->thread.fpu;
+	fpu = x86_task_fpu(current->group_leader);
 	perm = guest_fpu ? &fpu->guest_perm : &fpu->perm;
 	ksize = perm->__state_size;
 	usize = perm->__user_state_size;
@@ -1799,7 +1859,7 @@ long fpu_xstate_prctl(int option, unsigned long arg2)
  */
 static void avx512_status(struct seq_file *m, struct task_struct *task)
 {
-	unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp);
+	unsigned long timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp);
 	long delta;
 
 	if (!timestamp) {
@@ -1836,3 +1896,89 @@ 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 */