diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 9bb1f4ef1ccc0..fd193d53c9d7a 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -474,6 +474,7 @@
 #define X86_FEATURE_CLEAR_BHB_HW	(21*32+ 3) /* BHI_DIS_S HW control enabled */
 #define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */
 #define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32 + 5) /* "" Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_APX			(21*32 + 9) /* Advanced Performance Extensions */
 
 /*
  * BUG word(s)
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index fd5fb43d920b4..a2503049e4b5f 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -123,6 +123,7 @@ enum xfeature {
 	XFEATURE_RSRVD_COMP_16,
 	XFEATURE_XTILE_CFG,
 	XFEATURE_XTILE_DATA,
+	XFEATURE_APX,
 
 	XFEATURE_MAX,
 };
@@ -143,6 +144,7 @@ enum xfeature {
 #define XFEATURE_MASK_LBR		(1 << XFEATURE_LBR)
 #define XFEATURE_MASK_XTILE_CFG		(1 << XFEATURE_XTILE_CFG)
 #define XFEATURE_MASK_XTILE_DATA	(1 << XFEATURE_XTILE_DATA)
+#define XFEATURE_MASK_APX		(1 << XFEATURE_APX)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
 #define XFEATURE_MASK_AVX512		(XFEATURE_MASK_OPMASK \
@@ -301,6 +303,13 @@ struct xtile_data {
 	struct reg_1024_byte		tmm;
 } __packed;
 
+/*
+ * State component 19: 8B extended general purpose register.
+ */
+struct apx_state {
+	u64				egpr[16];
+} __packed;
+
 /*
  * State component 10 is supervisor state used for context-switching the
  * PASID state.
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index d4427b88ee12a..358ac97cf15c1 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -36,7 +36,8 @@
 				      XFEATURE_MASK_PKRU | \
 				      XFEATURE_MASK_BNDREGS | \
 				      XFEATURE_MASK_BNDCSR | \
-				      XFEATURE_MASK_XTILE)
+				      XFEATURE_MASK_XTILE | \
+				      XFEATURE_MASK_APX)
 
 /*
  * Features which are restored when returning to user space.
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 946813d816bfc..482eca653adc2 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -28,6 +28,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_PKU,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_MPX,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_XGETBV1,			X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_APX,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_CMOV,			X86_FEATURE_FXSR      },
 	{ X86_FEATURE_MMX,			X86_FEATURE_FXSR      },
 	{ X86_FEATURE_MMXEXT,			X86_FEATURE_MMX       },
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index af5aa2c754c22..bb1897da8d10d 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
 	{ X86_FEATURE_INTEL_PPIN,	CPUID_EBX,  0, 0x00000007, 1 },
+	{ X86_FEATURE_APX,		CPUID_EDX, 21, 0x00000007, 1 },
 	{ X86_FEATURE_RRSBA_CTRL,	CPUID_EDX,  2, 0x00000007, 2 },
 	{ X86_FEATURE_BHI_CTRL,		CPUID_EDX,  4, 0x00000007, 2 },
 	{ X86_FEATURE_CQM_LLC,		CPUID_EDX,  1, 0x0000000f, 0 },
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index aaed20f46be4c..3ca50fa8d03b4 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -709,7 +709,7 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask)
 /*
  * Reset current->fpu memory state to the init values.
  */
-static void fpu_reset_fpregs(void)
+static void fpu_reset_fpstate_regs(void)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
@@ -744,7 +744,7 @@ void fpu__clear_user_states(struct fpu *fpu)
 
 	fpregs_lock();
 	if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
-		fpu_reset_fpregs();
+		fpu_reset_fpstate_regs();
 		fpregs_unlock();
 		return;
 	}
@@ -774,7 +774,7 @@ void fpu__clear_user_states(struct fpu *fpu)
 void fpu_flush_thread(void)
 {
 	fpstate_reset(&current->thread.fpu);
-	fpu_reset_fpregs();
+	fpu_reset_fpstate_regs();
 }
 /*
  * Load FPU context before returning to userspace.
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 998a08f17e331..45d9664921597 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -94,7 +94,6 @@ static void __init fpu__init_system_early_generic(void)
  * Boot time FPU feature detection code:
  */
 unsigned int mxcsr_feature_mask __ro_after_init = 0xffffffffu;
-EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
 
 static void __init fpu__init_system_mxcsr(void)
 {
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 2b3b9e140dd41..8abe60919e2f9 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -119,7 +119,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 {
 	struct xregs_state __user *x = buf;
 	struct _fpx_sw_bytes sw_bytes = {};
-	u32 xfeatures;
 	int err;
 
 	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
@@ -132,12 +131,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 	err |= __put_user(FP_XSTATE_MAGIC2,
 			  (__u32 __user *)(buf + fpstate->user_size));
 
-	/*
-	 * Read the xfeatures which we copied (directly from the cpu or
-	 * from the state in task struct) to the user buffers.
-	 */
-	err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
-
 	/*
 	 * For legacy compatible, we always set FP/SSE bits in the bit
 	 * vector while saving the state to the user context. This will
@@ -149,9 +142,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 	 * header as well as change any contents in the memory layout.
 	 * xrestore as part of sigreturn will capture all the changes.
 	 */
-	xfeatures |= XFEATURE_MASK_FPSSE;
-
-	err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
+	err |= set_xfeature_in_sigframe(x, XFEATURE_MASK_FPSSE);
 
 	return !err;
 }
@@ -159,7 +150,8 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 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
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 390c6335ee248..ae286cb2303ea 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -13,6 +13,7 @@
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
 #include <linux/vmalloc.h>
+#include <linux/sort.h>
 
 #include <asm/fpu/api.h>
 #include <asm/fpu/regset.h>
@@ -58,6 +59,7 @@ static const char *xfeature_names[] =
 	"unknown xstate feature",
 	"AMX Tile config",
 	"AMX Tile data",
+	"APX registers",
 	"unknown xstate feature",
 };
 
@@ -76,6 +78,7 @@ 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 +87,31 @@ 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)
 
@@ -205,16 +233,20 @@ 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
@@ -228,39 +260,30 @@ 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(XSTATE_CPUID, 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);
 }
 
 /*
@@ -268,19 +291,15 @@ 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);
+	}
 }
 
 /*
@@ -348,7 +367,8 @@ 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
@@ -548,6 +568,7 @@ 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);
@@ -560,13 +581,20 @@ 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];
 }
 
@@ -719,6 +747,8 @@ 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);
@@ -788,6 +818,17 @@ 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;
 
@@ -865,7 +906,7 @@ 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;
 	}
@@ -877,7 +918,7 @@ 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;
 	}
@@ -996,6 +1037,19 @@ void *get_xsave_addr(struct xregs_state *xsave, int 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
 
 /*
@@ -1071,10 +1125,9 @@ 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;
@@ -1143,15 +1196,16 @@ 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
@@ -1161,14 +1215,14 @@ 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:
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index f2611145f3caa..799ecd6860f0b 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -54,6 +54,8 @@ 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 __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr);
+
 static inline u64 xfeatures_mask_supervisor(void)
 {
 	return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
@@ -67,6 +69,38 @@ static inline u64 xfeatures_mask_independent(void)
 	return fpu_kernel_cfg.independent_features;
 }
 
+static inline int set_xfeature_in_sigframe(struct xregs_state __user *xbuf, u64 mask)
+{
+	u64 xfeatures;
+	int err;
+
+	/* Read the xfeatures value already saved in the user buffer */
+	err  = __get_user(xfeatures, &xbuf->header.xfeatures);
+	xfeatures |= mask;
+	err |= __put_user(xfeatures, &xbuf->header.xfeatures);
+
+	return err;
+}
+
+/*
+ * 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, u32 pkru)
+{
+	int err;
+
+	if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
+		return 0;
+
+	/* Mark PKRU as in-use so that it is restored correctly. */
+	err = set_xfeature_in_sigframe(buf, XFEATURE_MASK_PKRU);
+	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
@@ -258,7 +292,7 @@ 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
@@ -283,6 +317,9 @@ 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, pkru);
+
 	return err;
 }
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 876d3b30c2c77..c5ad9e6ff4d78 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -59,6 +59,24 @@ static inline int is_x32_frame(struct ksignal *ksig)
 		ksig->ka.sa.sa_flags & SA_X32_ABI;
 }
 
+/*
+ * Enable all pkeys temporarily, so as to ensure that both the current
+ * execution stack as well as the alternate signal stack are writeable.
+ * The application can use any of the available pkeys to protect the
+ * alternate signal stack, and we don't know which one it is, so enable
+ * all. The PKRU register will be reset to init_pkru later in the flow,
+ * in fpu__clear_user_states(), and it is the application's responsibility
+ * to enable the appropriate pkey as the first step in the signal handler
+ * so that the handler does not segfault.
+ */
+static inline u32 sig_prepare_pkru(void)
+{
+	u32 orig_pkru = read_pkru();
+
+	write_pkru(0);
+	return orig_pkru;
+}
+
 /*
  * Set up a signal frame.
  */
@@ -83,7 +101,7 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size,
 	unsigned long math_size = 0;
 	unsigned long sp = regs->sp;
 	unsigned long buf_fx = 0;
-	u32 pkru = read_pkru();
+	u32 pkru;
 
 	/* redzone */
 	if (!ia32_frame)
@@ -138,9 +156,17 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size,
 		return (void __user *)-1L;
 	}
 
+	/* Update PKRU to enable access to the alternate signal stack. */
+	pkru = sig_prepare_pkru();
 	/* save i387 and extended state */
-	if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size, pkru))
+	if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size, pkru)) {
+		/*
+		 * Restore PKRU to the original, user-defined value; disable
+		 * extra pkeys enabled for the alternate signal stack, if any.
+		 */
+		write_pkru(pkru);
 		return (void __user *)-1L;
+	}
 
 	return (void __user *)sp;
 }
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 8f52bdaf99e92..9d93ec409cfe6 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -374,6 +374,7 @@
 #define X86_FEATURE_V_SPEC_CTRL		(15*32+20) /* Virtual SPEC_CTRL */
 #define X86_FEATURE_VNMI		(15*32+25) /* Virtual NMI */
 #define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* "" SVME addr check */
+#define X86_FEATURE_BUS_LOCK_THRESHOLD	(15*32+29) /* Bus lock threshold */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
 #define X86_FEATURE_AVX512VBMI		(16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
@@ -438,6 +439,7 @@
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* "" Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
 #define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* AMD SEV-ES full debug state swap support */
+#define X86_FEATURE_ALLOWED_SEV_FEATURES (19*32+27) /* Allowed SEV Features */
 
 /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" No Nested Data Breakpoints */
@@ -445,6 +447,8 @@
 #define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* "" Null Selector Clears Base */
 #define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* "" Automatic IBRS */
 #define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* "" SMM_CTL MSR is not present */
+#define X86_FEATURE_PREFETCHI		(20*32+20) /* Prefetch Data/Instruction to Cache Level */
+#define X86_FEATURE_APX			(21*32+ 9) /* Advanced Performance Extensions */
 
 /*
  * BUG word(s)
@@ -488,4 +492,15 @@
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
 
+/* BUG word 2 */
+#define X86_BUG_SRSO			X86_BUG( 1*32+ 0) /* "srso" AMD SRSO bug */
+#define X86_BUG_DIV0			X86_BUG( 1*32+ 1) /* "div0" AMD DIV0 speculation bug */
+#define X86_BUG_RFDS			X86_BUG( 1*32+ 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI			X86_BUG( 1*32+ 3) /* "bhi" CPU is affected by Branch History Injection */
+#define X86_BUG_IBPB_NO_RET		X86_BUG( 1*32+ 4) /* "ibpb_no_ret" IBPB omits return target predictions */
+#define X86_BUG_SPECTRE_V2_USER		X86_BUG( 1*32+ 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
+#define X86_BUG_OLD_MICROCODE		X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
+#define X86_BUG_ITS			X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
+#define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
+
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 13ce9a53d5dec..5fae3c52f21fc 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -18,7 +18,7 @@ TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
 TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \
-			corrupt_xstate_header amx lam test_shadow_stack
+			corrupt_xstate_header amx lam test_shadow_stack avx apx
 # Some selftests require 32bit support enabled also on 64bit systems
 TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall
 
@@ -72,10 +72,10 @@ all_64: $(BINARIES_64)
 EXTRA_CLEAN := $(BINARIES_32) $(BINARIES_64)
 
 $(BINARIES_32): $(OUTPUT)/%_32: %.c helpers.h
-	$(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl -lm
+	$(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $< $(EXTRA_FILES) -lrt -ldl -lm
 
 $(BINARIES_64): $(OUTPUT)/%_64: %.c helpers.h
-	$(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl
+	$(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $< $(EXTRA_FILES) -lrt -ldl
 
 # x86_64 users should be encouraged to install 32-bit libraries
 ifeq ($(CAN_BUILD_I386)$(CAN_BUILD_X86_64),01)
@@ -99,13 +99,27 @@ warn_32bit_failure:
 	exit 0;
 endif
 
-# Some tests have additional dependencies.
-$(OUTPUT)/sysret_ss_attrs_64: thunks.S
-$(OUTPUT)/ptrace_syscall_32: raw_syscall_helper_32.S
-$(OUTPUT)/test_syscall_vdso_32: thunks_32.S
+# Add an additional file to the source file list for a given target, and also
+# add a Makefile dependency on that same file. However, do these separately, so
+# that the compiler invocation ("$(CC) file1.c file2.S") is not combined with
+# the dependencies ("header3.h"), because clang, unlike gcc, will not accept
+# header files as an input to the compiler invocation.
+define extra-files
+$(OUTPUT)/$(1): EXTRA_FILES := $(2)
+$(OUTPUT)/$(1): $(2)
+endef
+
+$(eval $(call extra-files,sysret_ss_attrs_64,thunks.S))
+$(eval $(call extra-files,ptrace_syscall_32,raw_syscall_helper_32.S))
+$(eval $(call extra-files,test_syscall_vdso_32,thunks_32.S))
 
 # check_initial_reg_state is special: it needs a custom entry, and it
 # needs to be static so that its interpreter doesn't destroy its initial
 # state.
 $(OUTPUT)/check_initial_reg_state_32: CFLAGS += -Wl,-ereal_start -static
 $(OUTPUT)/check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static
+
+$(OUTPUT)/avx_64: CFLAGS += -mno-avx -mno-avx512f
+$(OUTPUT)/amx_64: EXTRA_FILES += xstate.c
+$(OUTPUT)/avx_64: EXTRA_FILES += xstate.c
+$(OUTPUT)/apx_64: EXTRA_FILES += xstate.c
diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
index d884fd69dd510..40769c16de1bb 100644
--- a/tools/testing/selftests/x86/amx.c
+++ b/tools/testing/selftests/x86/amx.c
@@ -3,7 +3,6 @@
 #define _GNU_SOURCE
 #include <err.h>
 #include <errno.h>
-#include <pthread.h>
 #include <setjmp.h>
 #include <stdio.h>
 #include <string.h>
@@ -14,200 +13,27 @@
 #include <sys/auxv.h>
 #include <sys/mman.h>
 #include <sys/shm.h>
-#include <sys/ptrace.h>
 #include <sys/syscall.h>
 #include <sys/wait.h>
-#include <sys/uio.h>
 
-#include "../kselftest.h" /* For __cpuid_count() */
+#include "helpers.h"
+#include "xstate.h"
 
 #ifndef __x86_64__
 # error This test is 64-bit only
 #endif
 
-#define XSAVE_HDR_OFFSET	512
-#define XSAVE_HDR_SIZE		64
-
-struct xsave_buffer {
-	union {
-		struct {
-			char legacy[XSAVE_HDR_OFFSET];
-			char header[XSAVE_HDR_SIZE];
-			char extended[0];
-		};
-		char bytes[0];
-	};
-};
-
-static inline uint64_t xgetbv(uint32_t index)
-{
-	uint32_t eax, edx;
-
-	asm volatile("xgetbv;"
-		     : "=a" (eax), "=d" (edx)
-		     : "c" (index));
-	return eax + ((uint64_t)edx << 32);
-}
-
-static inline void xsave(struct xsave_buffer *xbuf, uint64_t rfbm)
-{
-	uint32_t rfbm_lo = rfbm;
-	uint32_t rfbm_hi = rfbm >> 32;
-
-	asm volatile("xsave (%%rdi)"
-		     : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi)
-		     : "memory");
-}
-
-static inline void xrstor(struct xsave_buffer *xbuf, uint64_t rfbm)
-{
-	uint32_t rfbm_lo = rfbm;
-	uint32_t rfbm_hi = rfbm >> 32;
-
-	asm volatile("xrstor (%%rdi)"
-		     : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi));
-}
-
 /* err() exits and will not return */
 #define fatal_error(msg, ...)	err(1, "[FAIL]\t" msg, ##__VA_ARGS__)
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		fatal_error("sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		fatal_error("sigaction");
-}
-
-#define XFEATURE_XTILECFG	17
-#define XFEATURE_XTILEDATA	18
 #define XFEATURE_MASK_XTILECFG	(1 << XFEATURE_XTILECFG)
 #define XFEATURE_MASK_XTILEDATA	(1 << XFEATURE_XTILEDATA)
 #define XFEATURE_MASK_XTILE	(XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
 
-#define CPUID_LEAF1_ECX_XSAVE_MASK	(1 << 26)
-#define CPUID_LEAF1_ECX_OSXSAVE_MASK	(1 << 27)
-static inline void check_cpuid_xsave(void)
-{
-	uint32_t eax, ebx, ecx, edx;
-
-	/*
-	 * CPUID.1:ECX.XSAVE[bit 26] enumerates general
-	 * support for the XSAVE feature set, including
-	 * XGETBV.
-	 */
-	__cpuid_count(1, 0, eax, ebx, ecx, edx);
-	if (!(ecx & CPUID_LEAF1_ECX_XSAVE_MASK))
-		fatal_error("cpuid: no CPU xsave support");
-	if (!(ecx & CPUID_LEAF1_ECX_OSXSAVE_MASK))
-		fatal_error("cpuid: no OS xsave support");
-}
-
-static uint32_t xbuf_size;
-
-static struct {
-	uint32_t xbuf_offset;
-	uint32_t size;
-} xtiledata;
-
-#define CPUID_LEAF_XSTATE		0xd
-#define CPUID_SUBLEAF_XSTATE_USER	0x0
-#define TILE_CPUID			0x1d
-#define TILE_PALETTE_ID			0x1
-
-static void check_cpuid_xtiledata(void)
-{
-	uint32_t eax, ebx, ecx, edx;
-
-	__cpuid_count(CPUID_LEAF_XSTATE, CPUID_SUBLEAF_XSTATE_USER,
-		      eax, ebx, ecx, edx);
-
-	/*
-	 * 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.
-	 *
-	 * Stash that off so it can be used to allocate buffers later.
-	 */
-	xbuf_size = ebx;
-
-	__cpuid_count(CPUID_LEAF_XSTATE, XFEATURE_XTILEDATA,
-		      eax, ebx, ecx, edx);
-	/*
-	 * eax: XTILEDATA state component size
-	 * ebx: XTILEDATA state component offset in user buffer
-	 */
-	if (!eax || !ebx)
-		fatal_error("xstate cpuid: invalid tile data size/offset: %d/%d",
-				eax, ebx);
-
-	xtiledata.size	      = eax;
-	xtiledata.xbuf_offset = ebx;
-}
+struct xstate_info xtiledata;
 
 /* The helpers for managing XSAVE buffer and tile states: */
 
-struct xsave_buffer *alloc_xbuf(void)
-{
-	struct xsave_buffer *xbuf;
-
-	/* XSAVE buffer should be 64B-aligned. */
-	xbuf = aligned_alloc(64, xbuf_size);
-	if (!xbuf)
-		fatal_error("aligned_alloc()");
-	return xbuf;
-}
-
-static inline void clear_xstate_header(struct xsave_buffer *buffer)
-{
-	memset(&buffer->header, 0, sizeof(buffer->header));
-}
-
-static inline uint64_t get_xstatebv(struct xsave_buffer *buffer)
-{
-	/* XSTATE_BV is at the beginning of the header: */
-	return *(uint64_t *)&buffer->header;
-}
-
-static inline void set_xstatebv(struct xsave_buffer *buffer, uint64_t bv)
-{
-	/* XSTATE_BV is at the beginning of the header: */
-	*(uint64_t *)(&buffer->header) = bv;
-}
-
-static void set_rand_tiledata(struct xsave_buffer *xbuf)
-{
-	int *ptr = (int *)&xbuf->bytes[xtiledata.xbuf_offset];
-	int data;
-	int i;
-
-	/*
-	 * Ensure that 'data' is never 0.  This ensures that
-	 * the registers are never in their initial configuration
-	 * and thus never tracked as being in the init state.
-	 */
-	data = rand() | 1;
-
-	for (i = 0; i < xtiledata.size / sizeof(int); i++, ptr++)
-		*ptr = data;
-}
-
 struct xsave_buffer *stashed_xsave;
 
 static void init_stashed_xsave(void)
@@ -223,21 +49,6 @@ static void free_stashed_xsave(void)
 	free(stashed_xsave);
 }
 
-/* See 'struct _fpx_sw_bytes' at sigcontext.h */
-#define SW_BYTES_OFFSET		464
-/* N.B. The struct's field name varies so read from the offset. */
-#define SW_BYTES_BV_OFFSET	(SW_BYTES_OFFSET + 8)
-
-static inline struct _fpx_sw_bytes *get_fpx_sw_bytes(void *buffer)
-{
-	return (struct _fpx_sw_bytes *)(buffer + SW_BYTES_OFFSET);
-}
-
-static inline uint64_t get_fpx_sw_bytes_features(void *buffer)
-{
-	return *(uint64_t *)(buffer + SW_BYTES_BV_OFFSET);
-}
-
 /* Work around printf() being unsafe in signals: */
 #define SIGNAL_BUF_LEN 1000
 char signal_message_buffer[SIGNAL_BUF_LEN];
@@ -335,21 +146,15 @@ static inline bool load_rand_tiledata(struct xsave_buffer *xbuf)
 {
 	clear_xstate_header(xbuf);
 	set_xstatebv(xbuf, XFEATURE_MASK_XTILEDATA);
-	set_rand_tiledata(xbuf);
+	set_rand_data(&xtiledata, xbuf);
 	return xrstor_safe(xbuf, XFEATURE_MASK_XTILEDATA);
 }
 
-/* Return XTILEDATA to its initial configuration. */
-static inline void init_xtiledata(void)
-{
-	clear_xstate_header(stashed_xsave);
-	xrstor_safe(stashed_xsave, XFEATURE_MASK_XTILEDATA);
-}
-
 enum expected_result { FAIL_EXPECTED, SUCCESS_EXPECTED };
 
 /* arch_prctl() and sigaltstack() test */
 
+#define ARCH_GET_XCOMP_SUPP	0x1021
 #define ARCH_GET_XCOMP_PERM	0x1022
 #define ARCH_REQ_XCOMP_PERM	0x1023
 
@@ -617,14 +422,6 @@ static inline bool __validate_tiledata_regs(struct xsave_buffer *xbuf1)
 	return true;
 }
 
-static inline void validate_tiledata_regs_same(struct xsave_buffer *xbuf)
-{
-	int ret = __validate_tiledata_regs(xbuf);
-
-	if (ret != 0)
-		fatal_error("TILEDATA registers changed");
-}
-
 static inline void validate_tiledata_regs_changed(struct xsave_buffer *xbuf)
 {
 	int ret = __validate_tiledata_regs(xbuf);
@@ -681,257 +478,23 @@ static void test_fork(void)
 	_exit(0);
 }
 
-/* Context switching test */
-
-static struct _ctxtswtest_cfg {
-	unsigned int iterations;
-	unsigned int num_threads;
-} ctxtswtest_config;
-
-struct futex_info {
-	pthread_t thread;
-	int nr;
-	pthread_mutex_t mutex;
-	struct futex_info *next;
-};
-
-static void *check_tiledata(void *info)
-{
-	struct futex_info *finfo = (struct futex_info *)info;
-	struct xsave_buffer *xbuf;
-	int i;
-
-	xbuf = alloc_xbuf();
-	if (!xbuf)
-		fatal_error("unable to allocate XSAVE buffer");
-
-	/*
-	 * Load random data into 'xbuf' and then restore
-	 * it to the tile registers themselves.
-	 */
-	load_rand_tiledata(xbuf);
-	for (i = 0; i < ctxtswtest_config.iterations; i++) {
-		pthread_mutex_lock(&finfo->mutex);
-
-		/*
-		 * Ensure the register values have not
-		 * diverged from those recorded in 'xbuf'.
-		 */
-		validate_tiledata_regs_same(xbuf);
-
-		/* Load new, random values into xbuf and registers */
-		load_rand_tiledata(xbuf);
-
-		/*
-		 * The last thread's last unlock will be for
-		 * thread 0's mutex.  However, thread 0 will
-		 * have already exited the loop and the mutex
-		 * will already be unlocked.
-		 *
-		 * Because this is not an ERRORCHECK mutex,
-		 * that inconsistency will be silently ignored.
-		 */
-		pthread_mutex_unlock(&finfo->next->mutex);
-	}
-
-	free(xbuf);
-	/*
-	 * Return this thread's finfo, which is
-	 * a unique value for this thread.
-	 */
-	return finfo;
-}
-
-static int create_threads(int num, struct futex_info *finfo)
-{
-	int i;
-
-	for (i = 0; i < num; i++) {
-		int next_nr;
-
-		finfo[i].nr = i;
-		/*
-		 * Thread 'i' will wait on this mutex to
-		 * be unlocked.  Lock it immediately after
-		 * initialization:
-		 */
-		pthread_mutex_init(&finfo[i].mutex, NULL);
-		pthread_mutex_lock(&finfo[i].mutex);
-
-		next_nr = (i + 1) % num;
-		finfo[i].next = &finfo[next_nr];
-
-		if (pthread_create(&finfo[i].thread, NULL, check_tiledata, &finfo[i]))
-			fatal_error("pthread_create()");
-	}
-	return 0;
-}
-
-static void affinitize_cpu0(void)
-{
-	cpu_set_t cpuset;
-
-	CPU_ZERO(&cpuset);
-	CPU_SET(0, &cpuset);
-
-	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
-		fatal_error("sched_setaffinity to CPU 0");
-}
-
-static void test_context_switch(void)
+int main(void)
 {
-	struct futex_info *finfo;
-	int i;
-
-	/* Affinitize to one CPU to force context switches */
-	affinitize_cpu0();
-
-	req_xtiledata_perm();
-
-	printf("[RUN]\tCheck tiledata context switches, %d iterations, %d threads.\n",
-	       ctxtswtest_config.iterations,
-	       ctxtswtest_config.num_threads);
-
-
-	finfo = malloc(sizeof(*finfo) * ctxtswtest_config.num_threads);
-	if (!finfo)
-		fatal_error("malloc()");
-
-	create_threads(ctxtswtest_config.num_threads, finfo);
-
-	/*
-	 * This thread wakes up thread 0
-	 * Thread 0 will wake up 1
-	 * Thread 1 will wake up 2
-	 * ...
-	 * the last thread will wake up 0
-	 *
-	 * ... this will repeat for the configured
-	 * number of iterations.
-	 */
-	pthread_mutex_unlock(&finfo[0].mutex);
-
-	/* Wait for all the threads to finish: */
-	for (i = 0; i < ctxtswtest_config.num_threads; i++) {
-		void *thread_retval;
-		int rc;
-
-		rc = pthread_join(finfo[i].thread, &thread_retval);
-
-		if (rc)
-			fatal_error("pthread_join() failed for thread %d err: %d\n",
-					i, rc);
-
-		if (thread_retval != &finfo[i])
-			fatal_error("unexpected thread retval for thread %d: %p\n",
-					i, thread_retval);
+	unsigned long features;
+	long rc;
 
+	rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_SUPP, &features);
+	if (rc || (features & XFEATURE_MASK_XTILE) != XFEATURE_MASK_XTILE) {
+		ksft_print_msg("no AMX support\n");
+		return KSFT_SKIP;
 	}
 
-	printf("[OK]\tNo incorrect case was found.\n");
-
-	free(finfo);
-}
-
-/* Ptrace test */
-
-/*
- * Make sure the ptracee has the expanded kernel buffer on the first
- * use. Then, initialize the state before performing the state
- * injection from the ptracer.
- */
-static inline void ptracee_firstuse_tiledata(void)
-{
-	load_rand_tiledata(stashed_xsave);
-	init_xtiledata();
-}
-
-/*
- * Ptracer injects the randomized tile data state. It also reads
- * before and after that, which will execute the kernel's state copy
- * functions. So, the tester is advised to double-check any emitted
- * kernel messages.
- */
-static void ptracer_inject_tiledata(pid_t target)
-{
-	struct xsave_buffer *xbuf;
-	struct iovec iov;
-
-	xbuf = alloc_xbuf();
-	if (!xbuf)
-		fatal_error("unable to allocate XSAVE buffer");
-
-	printf("\tRead the init'ed tiledata via ptrace().\n");
-
-	iov.iov_base = xbuf;
-	iov.iov_len = xbuf_size;
-
-	memset(stashed_xsave, 0, xbuf_size);
-
-	if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
-		fatal_error("PTRACE_GETREGSET");
-
-	if (!__compare_tiledata_state(stashed_xsave, xbuf))
-		printf("[OK]\tThe init'ed tiledata was read from ptracee.\n");
-	else
-		printf("[FAIL]\tThe init'ed tiledata was not read from ptracee.\n");
-
-	printf("\tInject tiledata via ptrace().\n");
-
-	load_rand_tiledata(xbuf);
-
-	memcpy(&stashed_xsave->bytes[xtiledata.xbuf_offset],
-	       &xbuf->bytes[xtiledata.xbuf_offset],
-	       xtiledata.size);
-
-	if (ptrace(PTRACE_SETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
-		fatal_error("PTRACE_SETREGSET");
-
-	if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
-		fatal_error("PTRACE_GETREGSET");
-
-	if (!__compare_tiledata_state(stashed_xsave, xbuf))
-		printf("[OK]\tTiledata was correctly written to ptracee.\n");
-	else
-		printf("[FAIL]\tTiledata was not correctly written to ptracee.\n");
-}
-
-static void test_ptrace(void)
-{
-	pid_t child;
-	int status;
-
-	child = fork();
-	if (child < 0) {
-		err(1, "fork");
-	} else if (!child) {
-		if (ptrace(PTRACE_TRACEME, 0, NULL, NULL))
-			err(1, "PTRACE_TRACEME");
-
-		ptracee_firstuse_tiledata();
-
-		raise(SIGTRAP);
-		_exit(0);
+	xtiledata = get_xstate_info(XFEATURE_XTILEDATA);
+	if (!xtiledata.size || !xtiledata.xbuf_offset) {
+		fatal_error("xstate cpuid: invalid tile data size/offset: %d/%d",
+			    xtiledata.size, xtiledata.xbuf_offset);
 	}
 
-	do {
-		wait(&status);
-	} while (WSTOPSIG(status) != SIGTRAP);
-
-	ptracer_inject_tiledata(child);
-
-	ptrace(PTRACE_DETACH, child, NULL, NULL);
-	wait(&status);
-	if (!WIFEXITED(status) || WEXITSTATUS(status))
-		err(1, "ptrace test");
-}
-
-int main(void)
-{
-	/* Check hardware availability at first */
-	check_cpuid_xsave();
-	check_cpuid_xtiledata();
-
 	init_stashed_xsave();
 	sethandler(SIGILL, handle_noperm, 0);
 
@@ -942,11 +505,11 @@ int main(void)
 
 	test_fork();
 
-	ctxtswtest_config.iterations = 10;
-	ctxtswtest_config.num_threads = 5;
-	test_context_switch();
-
-	test_ptrace();
+	/*
+	 * Perform generic xstate tests for context switching, ptrace,
+	 * and signal.
+	 */
+	test_xstate(XFEATURE_XTILEDATA);
 
 	clearhandler(SIGILL);
 	free_stashed_xsave();
diff --git a/tools/testing/selftests/x86/apx.c b/tools/testing/selftests/x86/apx.c
new file mode 100644
index 0000000000000..d9c8d41b8c5a3
--- /dev/null
+++ b/tools/testing/selftests/x86/apx.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include "xstate.h"
+
+int main(void)
+{
+	test_xstate(XFEATURE_APX);
+}
diff --git a/tools/testing/selftests/x86/avx.c b/tools/testing/selftests/x86/avx.c
new file mode 100644
index 0000000000000..11d5367c235fc
--- /dev/null
+++ b/tools/testing/selftests/x86/avx.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE /* Required for inline xstate helpers */
+#include "xstate.h"
+
+int main(void)
+{
+	test_xstate(XFEATURE_YMM);
+	test_xstate(XFEATURE_OPMASK);
+	test_xstate(XFEATURE_ZMM_Hi256);
+	test_xstate(XFEATURE_Hi16_ZMM);
+}
diff --git a/tools/testing/selftests/x86/corrupt_xstate_header.c b/tools/testing/selftests/x86/corrupt_xstate_header.c
index cf9ce8fbb656c..93a89a5997ca8 100644
--- a/tools/testing/selftests/x86/corrupt_xstate_header.c
+++ b/tools/testing/selftests/x86/corrupt_xstate_header.c
@@ -18,6 +18,7 @@
 #include <sys/wait.h>
 
 #include "../kselftest.h" /* For __cpuid_count() */
+#include "helpers.h"
 
 static inline int xsave_enabled(void)
 {
@@ -29,19 +30,6 @@ static inline int xsave_enabled(void)
 	return ecx & (1U << 27);
 }
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static void sigusr1(int sig, siginfo_t *info, void *uc_void)
 {
 	ucontext_t *uc = uc_void;
diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c
index d1e919b0c1dc8..5cb8393737d05 100644
--- a/tools/testing/selftests/x86/entry_from_vm86.c
+++ b/tools/testing/selftests/x86/entry_from_vm86.c
@@ -24,31 +24,11 @@
 #include <errno.h>
 #include <sys/vm86.h>
 
+#include "helpers.h"
+
 static unsigned long load_addr = 0x10000;
 static int nerrs = 0;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static sig_atomic_t got_signal;
 
 static void sighandler(int sig, siginfo_t *info, void *ctx_void)
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 8c780cce941da..0a75252d31b6a 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -28,6 +28,8 @@
 #include <sys/wait.h>
 #include <setjmp.h>
 
+#include "helpers.h"
+
 #ifndef __x86_64__
 # error This test is 64-bit only
 #endif
@@ -39,28 +41,6 @@ static unsigned short *shared_scratch;
 
 static int nerrs;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static void sigsegv(int sig, siginfo_t *si, void *ctx_void)
 {
 	ucontext_t *ctx = (ucontext_t*)ctx_void;
@@ -109,11 +89,6 @@ static inline void wrgsbase(unsigned long gsbase)
 	asm volatile("wrgsbase %0" :: "r" (gsbase) : "memory");
 }
 
-static inline void wrfsbase(unsigned long fsbase)
-{
-	asm volatile("wrfsbase %0" :: "r" (fsbase) : "memory");
-}
-
 enum which_base { FS, GS };
 
 static unsigned long read_base(enum which_base which)
@@ -212,7 +187,6 @@ static void mov_0_gs(unsigned long initial_base, bool schedule)
 }
 
 static volatile unsigned long remote_base;
-static volatile bool remote_hard_zero;
 static volatile unsigned int ftx;
 
 /*
diff --git a/tools/testing/selftests/x86/helpers.h b/tools/testing/selftests/x86/helpers.h
index 4ef42c4559a9e..6deaad035161a 100644
--- a/tools/testing/selftests/x86/helpers.h
+++ b/tools/testing/selftests/x86/helpers.h
@@ -2,8 +2,13 @@
 #ifndef __SELFTESTS_X86_HELPERS_H
 #define __SELFTESTS_X86_HELPERS_H
 
+#include <signal.h>
+#include <string.h>
+
 #include <asm/processor-flags.h>
 
+#include "../kselftest.h"
+
 static inline unsigned long get_eflags(void)
 {
 #ifdef __x86_64__
@@ -22,4 +27,27 @@ static inline void set_eflags(unsigned long eflags)
 #endif
 }
 
+static inline void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		ksft_exit_fail_msg("sigaction failed");
+}
+
+static inline void clearhandler(int sig)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = SIG_DFL;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		ksft_exit_fail_msg("sigaction failed");
+}
+
 #endif /* __SELFTESTS_X86_HELPERS_H */
diff --git a/tools/testing/selftests/x86/ioperm.c b/tools/testing/selftests/x86/ioperm.c
index 57ec5e99edb93..69d5fb7050c25 100644
--- a/tools/testing/selftests/x86/ioperm.c
+++ b/tools/testing/selftests/x86/ioperm.c
@@ -20,30 +20,9 @@
 #include <sched.h>
 #include <sys/io.h>
 
-static int nerrs = 0;
-
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-
-}
+#include "helpers.h"
 
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
+static int nerrs = 0;
 
 static jmp_buf jmpbuf;
 
diff --git a/tools/testing/selftests/x86/iopl.c b/tools/testing/selftests/x86/iopl.c
index 7e3e09c1abac6..457b6715542bd 100644
--- a/tools/testing/selftests/x86/iopl.c
+++ b/tools/testing/selftests/x86/iopl.c
@@ -20,30 +20,9 @@
 #include <sched.h>
 #include <sys/io.h>
 
-static int nerrs = 0;
-
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-
-}
+#include "helpers.h"
 
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
+static int nerrs = 0;
 
 static jmp_buf jmpbuf;
 
diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index 8f9b06d9ce039..edc14b15da34f 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -1183,7 +1183,7 @@ int main(int argc, char **argv)
 
 	if (!cpu_has_lam()) {
 		ksft_print_msg("Unsupported LAM feature!\n");
-		return -1;
+		return KSFT_SKIP;
 	}
 
 	while ((c = getopt(argc, argv, "ht:")) != -1) {
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 3a29346e1452d..bb99a71380a5f 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -26,6 +26,8 @@
 #include <asm/prctl.h>
 #include <sys/prctl.h>
 
+#include "helpers.h"
+
 #define AR_ACCESSED		(1<<8)
 
 #define AR_TYPE_RODATA		(0 * (1<<9))
@@ -506,20 +508,6 @@ static void fix_sa_restorer(int sig)
 }
 #endif
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-
-	fix_sa_restorer(sig);
-}
-
 static jmp_buf jmpbuf;
 
 static void sigsegv(int sig, siginfo_t *info, void *ctx_void)
@@ -549,9 +537,11 @@ static void do_multicpu_tests(void)
 	}
 
 	sethandler(SIGSEGV, sigsegv, 0);
+	fix_sa_restorer(SIGSEGV);
 #ifdef __i386__
 	/* True 32-bit kernels send SIGILL instead of SIGSEGV on IRET faults. */
 	sethandler(SIGILL, sigsegv, 0);
+	fix_sa_restorer(SIGILL);
 #endif
 
 	printf("[RUN]\tCross-CPU LDT invalidation\n");
diff --git a/tools/testing/selftests/x86/mov_ss_trap.c b/tools/testing/selftests/x86/mov_ss_trap.c
index cc3de6ff9fba1..f22cb6b382f9c 100644
--- a/tools/testing/selftests/x86/mov_ss_trap.c
+++ b/tools/testing/selftests/x86/mov_ss_trap.c
@@ -36,7 +36,7 @@
 #include <setjmp.h>
 #include <sys/prctl.h>
 
-#define X86_EFLAGS_RF (1UL << 16)
+#include "helpers.h"
 
 #if __x86_64__
 # define REG_IP REG_RIP
@@ -94,18 +94,6 @@ static void enable_watchpoint(void)
 	}
 }
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static char const * const signames[] = {
 	[SIGSEGV] = "SIGSEGV",
 	[SIGBUS] = "SIBGUS",
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index 12aaa063196e7..360ec88d5432c 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -15,6 +15,8 @@
 #include <asm/ptrace-abi.h>
 #include <sys/auxv.h>
 
+#include "helpers.h"
+
 /* Bitness-agnostic defines for user_regs_struct fields. */
 #ifdef __x86_64__
 # define user_syscall_nr	orig_rax
@@ -93,18 +95,6 @@ static siginfo_t wait_trap(pid_t chld)
 	return si;
 }
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static void setsigign(int sig, int flags)
 {
 	struct sigaction sa;
@@ -116,16 +106,6 @@ static void setsigign(int sig, int flags)
 		err(1, "sigaction");
 }
 
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 #ifdef __x86_64__
 # define REG_BP REG_RBP
 #else
diff --git a/tools/testing/selftests/x86/sigaltstack.c b/tools/testing/selftests/x86/sigaltstack.c
index f689af75e979e..0ae1b784498cc 100644
--- a/tools/testing/selftests/x86/sigaltstack.c
+++ b/tools/testing/selftests/x86/sigaltstack.c
@@ -14,6 +14,8 @@
 #include <sys/resource.h>
 #include <setjmp.h>
 
+#include "helpers.h"
+
 /* sigaltstack()-enforced minimum stack */
 #define ENFORCED_MINSIGSTKSZ	2048
 
@@ -27,30 +29,6 @@ static bool sigalrm_expected;
 
 static unsigned long at_minstack_size;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static int setup_altstack(void *start, unsigned long size)
 {
 	stack_t ss;
diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c
index 5d7961a5f7f6e..d04937bfefc35 100644
--- a/tools/testing/selftests/x86/sigreturn.c
+++ b/tools/testing/selftests/x86/sigreturn.c
@@ -46,6 +46,8 @@
 #include <sys/ptrace.h>
 #include <sys/user.h>
 
+#include "helpers.h"
+
 /* Pull in AR_xyz defines. */
 typedef unsigned int u32;
 typedef unsigned short u16;
@@ -138,28 +140,6 @@ static unsigned short LDT3(int idx)
 	return (idx << 3) | 7;
 }
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static void add_ldt(const struct user_desc *desc, unsigned short *var,
 		    const char *name)
 {
diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c
index 9a30f443e9286..280d7a22b9c9b 100644
--- a/tools/testing/selftests/x86/single_step_syscall.c
+++ b/tools/testing/selftests/x86/single_step_syscall.c
@@ -33,28 +33,6 @@
 
 #include "helpers.h"
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static volatile sig_atomic_t sig_traps, sig_eflags;
 sigjmp_buf jmpbuf;
 
diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c
index 461fa41a4d02a..f67a2df335ba0 100644
--- a/tools/testing/selftests/x86/syscall_arg_fault.c
+++ b/tools/testing/selftests/x86/syscall_arg_fault.c
@@ -17,19 +17,6 @@
 
 #include "helpers.h"
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static volatile sig_atomic_t sig_traps;
 static sigjmp_buf jmpbuf;
 
 static volatile sig_atomic_t n_errs;
diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c
index a108b80dd0823..f9c9814160f09 100644
--- a/tools/testing/selftests/x86/syscall_nt.c
+++ b/tools/testing/selftests/x86/syscall_nt.c
@@ -18,18 +18,6 @@
 
 static unsigned int nerrs;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static void sigtrap(int sig, siginfo_t *si, void *ctx_void)
 {
 }
diff --git a/tools/testing/selftests/x86/sysret_rip.c b/tools/testing/selftests/x86/sysret_rip.c
index 84d74be1d9020..0365350d21fc2 100644
--- a/tools/testing/selftests/x86/sysret_rip.c
+++ b/tools/testing/selftests/x86/sysret_rip.c
@@ -21,7 +21,7 @@
 #include <sys/user.h>
 #include <sys/mman.h>
 #include <assert.h>
-
+#include "helpers.h"
 
 asm (
 	".pushsection \".text\", \"ax\"\n\t"
@@ -39,28 +39,6 @@ asm (
 extern const char test_page[];
 static void const *current_test_page_addr = test_page;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 /* State used by our signal handlers. */
 static gregset_t initial_regs;
 
diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c
index 47cab972807c4..43ac6bc880c40 100644
--- a/tools/testing/selftests/x86/test_vsyscall.c
+++ b/tools/testing/selftests/x86/test_vsyscall.c
@@ -39,18 +39,6 @@
 /* max length of lines in /proc/self/maps - anything longer is skipped here */
 #define MAPS_LINE_LEN 128
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 /* vsyscalls and vDSO */
 bool vsyscall_map_r = false, vsyscall_map_x = false;
 
@@ -160,11 +148,6 @@ static inline long sys_gtod(struct timeval *tv, struct timezone *tz)
 	return syscall(SYS_gettimeofday, tv, tz);
 }
 
-static inline int sys_clock_gettime(clockid_t id, struct timespec *ts)
-{
-	return syscall(SYS_clock_gettime, id, ts);
-}
-
 static inline long sys_time(time_t *t)
 {
 	return syscall(SYS_time, t);
diff --git a/tools/testing/selftests/x86/unwind_vdso.c b/tools/testing/selftests/x86/unwind_vdso.c
index 4c311e1af4c7a..9cc17588d8189 100644
--- a/tools/testing/selftests/x86/unwind_vdso.c
+++ b/tools/testing/selftests/x86/unwind_vdso.c
@@ -43,18 +43,6 @@ int main()
 #include <dlfcn.h>
 #include <unwind.h>
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static volatile sig_atomic_t nerrs;
 static unsigned long sysinfo;
 static bool got_sysinfo = false;
diff --git a/tools/testing/selftests/x86/vdso_restorer.c b/tools/testing/selftests/x86/vdso_restorer.c
index fe99f24341554..ac8d8e1e9805d 100644
--- a/tools/testing/selftests/x86/vdso_restorer.c
+++ b/tools/testing/selftests/x86/vdso_restorer.c
@@ -92,4 +92,6 @@ int main()
 		printf("[FAIL]\t!SA_SIGINFO handler was not called\n");
 		nerrs++;
 	}
+
+	return nerrs;
 }
diff --git a/tools/testing/selftests/x86/xstate.c b/tools/testing/selftests/x86/xstate.c
new file mode 100644
index 0000000000000..47c74fcdce020
--- /dev/null
+++ b/tools/testing/selftests/x86/xstate.c
@@ -0,0 +1,478 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <elf.h>
+#include <pthread.h>
+#include <stdbool.h>
+
+#include <asm/prctl.h>
+#include <sys/ptrace.h>
+#include <sys/syscall.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+
+#include "helpers.h"
+#include "xstate.h"
+
+/*
+ * The userspace xstate test suite is designed to be generic and operates
+ * with randomized xstate data. However, some states require special handling:
+ *
+ * - PKRU and XTILECFG need specific adjustments, such as modifying
+ *   randomization behavior or using fixed values.
+ * - But, PKRU already has a dedicated test suite in /tools/selftests/mm.
+ * - Legacy states (FP and SSE) are excluded, as they are not considered
+ *   part of extended states (xstates) and their usage is already deeply
+ *   integrated into user-space libraries.
+ */
+#define XFEATURE_MASK_TEST_SUPPORTED	\
+	((1 << XFEATURE_YMM) |		\
+	 (1 << XFEATURE_OPMASK)	|	\
+	 (1 << XFEATURE_ZMM_Hi256) |	\
+	 (1 << XFEATURE_Hi16_ZMM) |	\
+	 (1 << XFEATURE_XTILEDATA) |	\
+	 (1 << XFEATURE_APX))
+
+static inline uint64_t xgetbv(uint32_t index)
+{
+	uint32_t eax, edx;
+
+	asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index));
+	return eax + ((uint64_t)edx << 32);
+}
+
+static inline uint64_t get_xstatebv(struct xsave_buffer *xbuf)
+{
+	return *(uint64_t *)(&xbuf->header);
+}
+
+static struct xstate_info xstate;
+
+struct futex_info {
+	unsigned int iterations;
+	struct futex_info *next;
+	pthread_mutex_t mutex;
+	pthread_t thread;
+	bool valid;
+	int nr;
+};
+
+static inline void load_rand_xstate(struct xstate_info *xstate, struct xsave_buffer *xbuf)
+{
+	clear_xstate_header(xbuf);
+	set_xstatebv(xbuf, xstate->mask);
+	set_rand_data(xstate, xbuf);
+	xrstor(xbuf, xstate->mask);
+}
+
+static inline void load_init_xstate(struct xstate_info *xstate, struct xsave_buffer *xbuf)
+{
+	clear_xstate_header(xbuf);
+	xrstor(xbuf, xstate->mask);
+}
+
+static inline void copy_xstate(struct xsave_buffer *xbuf_dst, struct xsave_buffer *xbuf_src)
+{
+	memcpy(&xbuf_dst->bytes[xstate.xbuf_offset],
+	       &xbuf_src->bytes[xstate.xbuf_offset],
+	       xstate.size);
+}
+
+static inline bool validate_xstate_same(struct xsave_buffer *xbuf1, struct xsave_buffer *xbuf2)
+{
+	int ret;
+
+	ret = memcmp(&xbuf1->bytes[xstate.xbuf_offset],
+		     &xbuf2->bytes[xstate.xbuf_offset],
+		     xstate.size);
+	return ret == 0;
+}
+
+static inline bool validate_xregs_same(struct xsave_buffer *xbuf1)
+{
+	struct xsave_buffer *xbuf2;
+	bool ret;
+
+	xbuf2 = alloc_xbuf();
+	if (!xbuf2)
+		ksft_exit_fail_msg("failed to allocate XSAVE buffer\n");
+
+	xsave(xbuf2, xstate.mask);
+	ret = validate_xstate_same(xbuf1, xbuf2);
+
+	free(xbuf2);
+	return ret;
+}
+
+/* Context switching test */
+
+static void *check_xstate(void *info)
+{
+	struct futex_info *finfo = (struct futex_info *)info;
+	struct xsave_buffer *xbuf;
+	int i;
+
+	xbuf = alloc_xbuf();
+	if (!xbuf)
+		ksft_exit_fail_msg("unable to allocate XSAVE buffer\n");
+
+	/*
+	 * Load random data into 'xbuf' and then restore it to the xstate
+	 * registers.
+	 */
+	load_rand_xstate(&xstate, xbuf);
+	finfo->valid = true;
+
+	for (i = 0; i < finfo->iterations; i++) {
+		pthread_mutex_lock(&finfo->mutex);
+
+		/*
+		 * Ensure the register values have not diverged from the
+		 * record. Then reload a new random value.  If it failed
+		 * ever before, skip it.
+		 */
+		if (finfo->valid) {
+			finfo->valid = validate_xregs_same(xbuf);
+			load_rand_xstate(&xstate, xbuf);
+		}
+
+		/*
+		 * The last thread's last unlock will be for thread 0's
+		 * mutex. However, thread 0 will have already exited the
+		 * loop and the mutex will already be unlocked.
+		 *
+		 * Because this is not an ERRORCHECK mutex, that
+		 * inconsistency will be silently ignored.
+		 */
+		pthread_mutex_unlock(&finfo->next->mutex);
+	}
+
+	free(xbuf);
+	return finfo;
+}
+
+static void create_threads(uint32_t num_threads, uint32_t iterations, struct futex_info *finfo)
+{
+	int i;
+
+	for (i = 0; i < num_threads; i++) {
+		int next_nr;
+
+		finfo[i].nr = i;
+		finfo[i].iterations = iterations;
+
+		/*
+		 * Thread 'i' will wait on this mutex to be unlocked.
+		 * Lock it immediately after initialization:
+		 */
+		pthread_mutex_init(&finfo[i].mutex, NULL);
+		pthread_mutex_lock(&finfo[i].mutex);
+
+		next_nr = (i + 1) % num_threads;
+		finfo[i].next = &finfo[next_nr];
+
+		if (pthread_create(&finfo[i].thread, NULL, check_xstate, &finfo[i]))
+			ksft_exit_fail_msg("pthread_create() failed\n");
+	}
+}
+
+static bool checkout_threads(uint32_t num_threads, struct futex_info *finfo)
+{
+	void *thread_retval;
+	bool valid = true;
+	int err, i;
+
+	for (i = 0; i < num_threads; i++) {
+		err = pthread_join(finfo[i].thread, &thread_retval);
+		if (err)
+			ksft_exit_fail_msg("pthread_join() failed for thread %d err: %d\n", i, err);
+
+		if (thread_retval != &finfo[i]) {
+			ksft_exit_fail_msg("unexpected thread retval for thread %d: %p\n",
+					   i, thread_retval);
+		}
+
+		valid &= finfo[i].valid;
+	}
+
+	return valid;
+}
+
+static void affinitize_cpu0(void)
+{
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+		ksft_exit_fail_msg("sched_setaffinity to CPU 0 failed\n");
+}
+
+static void test_context_switch(uint32_t num_threads, uint32_t iterations)
+{
+	struct futex_info *finfo;
+
+	/* Affinitize to one CPU to force context switches */
+	affinitize_cpu0();
+
+	printf("[RUN]\t%s: check context switches, %d iterations, %d threads.\n",
+	       xstate.name, iterations, num_threads);
+
+	finfo = malloc(sizeof(*finfo) * num_threads);
+	if (!finfo)
+		ksft_exit_fail_msg("unable allocate memory\n");
+
+	create_threads(num_threads, iterations, finfo);
+
+	/*
+	 * This thread wakes up thread 0
+	 * Thread 0 will wake up 1
+	 * Thread 1 will wake up 2
+	 * ...
+	 * The last thread will wake up 0
+	 *
+	 * This will repeat for the configured
+	 * number of iterations.
+	 */
+	pthread_mutex_unlock(&finfo[0].mutex);
+
+	/* Wait for all the threads to finish: */
+	if (checkout_threads(num_threads, finfo))
+		printf("[OK]\tNo incorrect case was found.\n");
+	else
+		printf("[FAIL]\tFailed with context switching test.\n");
+
+	free(finfo);
+}
+
+/*
+ * Ptrace test for the ABI format as described in arch/x86/include/asm/user.h
+ */
+
+/*
+ * Make sure the ptracee has the expanded kernel buffer on the first use.
+ * Then, initialize the state before performing the state injection from
+ * the ptracer. For non-dynamic states, this is benign.
+ */
+static inline void ptracee_touch_xstate(void)
+{
+	struct xsave_buffer *xbuf;
+
+	xbuf = alloc_xbuf();
+
+	load_rand_xstate(&xstate, xbuf);
+	load_init_xstate(&xstate, xbuf);
+
+	free(xbuf);
+}
+
+/*
+ * Ptracer injects the randomized xstate data. It also reads before and
+ * after that, which will execute the kernel's state copy functions.
+ */
+static void ptracer_inject_xstate(pid_t target)
+{
+	uint32_t xbuf_size = get_xbuf_size();
+	struct xsave_buffer *xbuf1, *xbuf2;
+	struct iovec iov;
+
+	/*
+	 * Allocate buffers to keep data while ptracer can write the
+	 * other buffer
+	 */
+	xbuf1 = alloc_xbuf();
+	xbuf2 = alloc_xbuf();
+	if (!xbuf1 || !xbuf2)
+		ksft_exit_fail_msg("unable to allocate XSAVE buffer\n");
+
+	iov.iov_base = xbuf1;
+	iov.iov_len  = xbuf_size;
+
+	if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
+		ksft_exit_fail_msg("PTRACE_GETREGSET failed\n");
+
+	printf("[RUN]\t%s: inject xstate via ptrace().\n", xstate.name);
+
+	load_rand_xstate(&xstate, xbuf1);
+	copy_xstate(xbuf2, xbuf1);
+
+	if (ptrace(PTRACE_SETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
+		ksft_exit_fail_msg("PTRACE_SETREGSET failed\n");
+
+	if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
+		ksft_exit_fail_msg("PTRACE_GETREGSET failed\n");
+
+	if (*(uint64_t *)get_fpx_sw_bytes(xbuf1) == xgetbv(0))
+		printf("[OK]\t'xfeatures' in SW reserved area was correctly written\n");
+	else
+		printf("[FAIL]\t'xfeatures' in SW reserved area was not correctly written\n");
+
+	if (validate_xstate_same(xbuf2, xbuf1))
+		printf("[OK]\txstate was correctly updated.\n");
+	else
+		printf("[FAIL]\txstate was not correctly updated.\n");
+
+	free(xbuf1);
+	free(xbuf2);
+}
+
+static void test_ptrace(void)
+{
+	pid_t child;
+	int status;
+
+	child = fork();
+	if (child < 0) {
+		ksft_exit_fail_msg("fork() failed\n");
+	} else if (!child) {
+		if (ptrace(PTRACE_TRACEME, 0, NULL, NULL))
+			ksft_exit_fail_msg("PTRACE_TRACEME failed\n");
+
+		ptracee_touch_xstate();
+
+		raise(SIGTRAP);
+		_exit(0);
+	}
+
+	do {
+		wait(&status);
+	} while (WSTOPSIG(status) != SIGTRAP);
+
+	ptracer_inject_xstate(child);
+
+	ptrace(PTRACE_DETACH, child, NULL, NULL);
+	wait(&status);
+	if (!WIFEXITED(status) || WEXITSTATUS(status))
+		ksft_exit_fail_msg("ptracee exit error\n");
+}
+
+/*
+ * Test signal delivery for the ABI compatibility.
+ * See the ABI format: arch/x86/include/uapi/asm/sigcontext.h
+ */
+
+/*
+ * Avoid using printf() in signal handlers as it is not
+ * async-signal-safe.
+ */
+#define SIGNAL_BUF_LEN 1000
+static char signal_message_buffer[SIGNAL_BUF_LEN];
+static void sig_print(char *msg)
+{
+	int left = SIGNAL_BUF_LEN - strlen(signal_message_buffer) - 1;
+
+	strncat(signal_message_buffer, msg, left);
+}
+
+static struct xsave_buffer *stashed_xbuf;
+
+static void validate_sigfpstate(int sig, siginfo_t *si, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t *)ctx_void;
+	void *xbuf = ctx->uc_mcontext.fpregs;
+	struct _fpx_sw_bytes *sw_bytes;
+	uint32_t magic2;
+
+	/* Reset the signal message buffer: */
+	signal_message_buffer[0] = '\0';
+
+	sw_bytes = get_fpx_sw_bytes(xbuf);
+	if (sw_bytes->magic1 == FP_XSTATE_MAGIC1)
+		sig_print("[OK]\t'magic1' is valid\n");
+	else
+		sig_print("[FAIL]\t'magic1' is not valid\n");
+
+	if (get_fpx_sw_bytes_features(xbuf) & xstate.mask)
+		sig_print("[OK]\t'xfeatures' in SW reserved area is valid\n");
+	else
+		sig_print("[FAIL]\t'xfeatures' in SW reserved area is not valid\n");
+
+	if (get_xstatebv(xbuf) & xstate.mask)
+		sig_print("[OK]\t'xfeatures' in XSAVE header is valid\n");
+	else
+		sig_print("[FAIL]\t'xfeatures' in XSAVE hader is not valid\n");
+
+	if (validate_xstate_same(stashed_xbuf, xbuf))
+		sig_print("[OK]\txstate delivery was successful\n");
+	else
+		sig_print("[FAIL]\txstate delivery was not successful\n");
+
+	magic2 = *(uint32_t *)(xbuf + sw_bytes->xstate_size);
+	if (magic2 == FP_XSTATE_MAGIC2)
+		sig_print("[OK]\t'magic2' is valid\n");
+	else
+		sig_print("[FAIL]\t'magic2' is not valid\n");
+
+	set_rand_data(&xstate, xbuf);
+	copy_xstate(stashed_xbuf, xbuf);
+}
+
+static void test_signal(void)
+{
+	bool valid_xstate;
+
+	/*
+	 * The signal handler will access this to verify xstate context
+	 * preservation.
+	 */
+	stashed_xbuf = alloc_xbuf();
+	if (!stashed_xbuf)
+		ksft_exit_fail_msg("unable to allocate XSAVE buffer\n");
+
+	printf("[RUN]\t%s: load xstate and raise SIGUSR1\n", xstate.name);
+
+	sethandler(SIGUSR1, validate_sigfpstate, 0);
+
+	load_rand_xstate(&xstate, stashed_xbuf);
+
+	raise(SIGUSR1);
+
+	/*
+	 * Immediately record the test result, deferring printf() to
+	 * prevent unintended state contamination by that.
+	 */
+	valid_xstate = validate_xregs_same(stashed_xbuf);
+	printf("%s", signal_message_buffer);
+
+	printf("[RUN]\t%s: load new xstate from sighandler and check it after sigreturn\n",
+	       xstate.name);
+
+	if (valid_xstate)
+		printf("[OK]\txstate was restored correctly\n");
+	else
+		printf("[FAIL]\txstate restoration failed\n");
+
+	clearhandler(SIGUSR1);
+	free(stashed_xbuf);
+}
+
+void test_xstate(uint32_t feature_num)
+{
+	const unsigned int ctxtsw_num_threads = 5, ctxtsw_iterations = 10;
+	unsigned long features;
+	long rc;
+
+	if (!(XFEATURE_MASK_TEST_SUPPORTED & (1 << feature_num))) {
+		ksft_print_msg("The xstate test does not fully support the component %u, yet.\n",
+			       feature_num);
+		return;
+	}
+
+	rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_SUPP, &features);
+	if (rc || !(features & (1 << feature_num))) {
+		ksft_print_msg("The kernel does not support feature number: %u\n", feature_num);
+		return;
+	}
+
+	xstate = get_xstate_info(feature_num);
+	if (!xstate.size || !xstate.xbuf_offset) {
+		ksft_exit_fail_msg("invalid state size/offset (%d/%d)\n",
+				   xstate.size, xstate.xbuf_offset);
+	}
+
+	test_context_switch(ctxtsw_num_threads, ctxtsw_iterations);
+	test_ptrace();
+	test_signal();
+}
diff --git a/tools/testing/selftests/x86/xstate.h b/tools/testing/selftests/x86/xstate.h
new file mode 100644
index 0000000000000..e91e3092b5d24
--- /dev/null
+++ b/tools/testing/selftests/x86/xstate.h
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef __SELFTESTS_X86_XSTATE_H
+#define __SELFTESTS_X86_XSTATE_H
+
+#include <stdint.h>
+
+#include "../kselftest.h"
+
+#define XSAVE_HDR_OFFSET	512
+#define XSAVE_HDR_SIZE		64
+
+/*
+ * List of XSAVE features Linux knows about. Copied from
+ * arch/x86/include/asm/fpu/types.h
+ */
+enum xfeature {
+	XFEATURE_FP,
+	XFEATURE_SSE,
+	XFEATURE_YMM,
+	XFEATURE_BNDREGS,
+	XFEATURE_BNDCSR,
+	XFEATURE_OPMASK,
+	XFEATURE_ZMM_Hi256,
+	XFEATURE_Hi16_ZMM,
+	XFEATURE_PT_UNIMPLEMENTED_SO_FAR,
+	XFEATURE_PKRU,
+	XFEATURE_PASID,
+	XFEATURE_CET_USER,
+	XFEATURE_CET_KERNEL_UNUSED,
+	XFEATURE_RSRVD_COMP_13,
+	XFEATURE_RSRVD_COMP_14,
+	XFEATURE_LBR,
+	XFEATURE_RSRVD_COMP_16,
+	XFEATURE_XTILECFG,
+	XFEATURE_XTILEDATA,
+	XFEATURE_APX,
+
+	XFEATURE_MAX,
+};
+
+/* Copied from arch/x86/kernel/fpu/xstate.c */
+static const char *xfeature_names[] =
+{
+	"x87 floating point registers",
+	"SSE registers",
+	"AVX registers",
+	"MPX bounds registers",
+	"MPX CSR",
+	"AVX-512 opmask",
+	"AVX-512 Hi256",
+	"AVX-512 ZMM_Hi256",
+	"Processor Trace (unused)",
+	"Protection Keys User registers",
+	"PASID state",
+	"Control-flow User registers",
+	"Control-flow Kernel registers (unused)",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"AMX Tile config",
+	"AMX Tile data",
+	"APX registers",
+	"unknown xstate feature",
+};
+
+struct xsave_buffer {
+	union {
+		struct {
+			char legacy[XSAVE_HDR_OFFSET];
+			char header[XSAVE_HDR_SIZE];
+			char extended[0];
+		};
+		char bytes[0];
+	};
+};
+
+static inline void xsave(struct xsave_buffer *xbuf, uint64_t rfbm)
+{
+	uint32_t rfbm_hi = rfbm >> 32;
+	uint32_t rfbm_lo = rfbm;
+
+	asm volatile("xsave (%%rdi)"
+		     : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi)
+		     : "memory");
+}
+
+static inline void xrstor(struct xsave_buffer *xbuf, uint64_t rfbm)
+{
+	uint32_t rfbm_hi = rfbm >> 32;
+	uint32_t rfbm_lo = rfbm;
+
+	asm volatile("xrstor (%%rdi)"
+		     : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi));
+}
+
+#define CPUID_LEAF_XSTATE		0xd
+#define CPUID_SUBLEAF_XSTATE_USER	0x0
+
+static inline uint32_t get_xbuf_size(void)
+{
+	uint32_t eax, ebx, ecx, edx;
+
+	__cpuid_count(CPUID_LEAF_XSTATE, CPUID_SUBLEAF_XSTATE_USER,
+		      eax, ebx, ecx, edx);
+
+	/*
+	 * 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.
+	 */
+	return ebx;
+}
+
+struct xstate_info {
+	const char *name;
+	uint32_t num;
+	uint32_t mask;
+	uint32_t xbuf_offset;
+	uint32_t size;
+};
+
+static inline struct xstate_info get_xstate_info(uint32_t xfeature_num)
+{
+	struct xstate_info xstate = { };
+	uint32_t eax, ebx, ecx, edx;
+
+	if (xfeature_num >= XFEATURE_MAX) {
+		ksft_print_msg("unknown state\n");
+		return xstate;
+	}
+
+	xstate.name = xfeature_names[xfeature_num];
+	xstate.num  = xfeature_num;
+	xstate.mask = 1 << xfeature_num;
+
+	__cpuid_count(CPUID_LEAF_XSTATE, xfeature_num,
+		      eax, ebx, ecx, edx);
+	xstate.size        = eax;
+	xstate.xbuf_offset = ebx;
+	return xstate;
+}
+
+static inline struct xsave_buffer *alloc_xbuf(void)
+{
+	uint32_t xbuf_size = get_xbuf_size();
+
+	/* XSAVE buffer should be 64B-aligned. */
+	return aligned_alloc(64, xbuf_size);
+}
+
+static inline void clear_xstate_header(struct xsave_buffer *xbuf)
+{
+	memset(&xbuf->header, 0, sizeof(xbuf->header));
+}
+
+static inline void set_xstatebv(struct xsave_buffer *xbuf, uint64_t bv)
+{
+	/* XSTATE_BV is at the beginning of the header: */
+	*(uint64_t *)(&xbuf->header) = bv;
+}
+
+/* See 'struct _fpx_sw_bytes' at sigcontext.h */
+#define SW_BYTES_OFFSET		464
+/* N.B. The struct's field name varies so read from the offset. */
+#define SW_BYTES_BV_OFFSET	(SW_BYTES_OFFSET + 8)
+
+static inline struct _fpx_sw_bytes *get_fpx_sw_bytes(void *xbuf)
+{
+	return xbuf + SW_BYTES_OFFSET;
+}
+
+static inline uint64_t get_fpx_sw_bytes_features(void *buffer)
+{
+	return *(uint64_t *)(buffer + SW_BYTES_BV_OFFSET);
+}
+
+static inline void set_rand_data(struct xstate_info *xstate, struct xsave_buffer *xbuf)
+{
+	int *ptr = (int *)&xbuf->bytes[xstate->xbuf_offset];
+	int data, i;
+
+	/*
+	 * Ensure that 'data' is never 0.  This ensures that
+	 * the registers are never in their initial configuration
+	 * and thus never tracked as being in the init state.
+	 */
+	data = rand() | 1;
+
+	for (i = 0; i < xstate->size / sizeof(int); i++, ptr++)
+		*ptr = data;
+}
+
+/* Testing kernel's context switching and ABI support for the xstate. */
+void test_xstate(uint32_t feature_num);
+
+#endif /* __SELFTESTS_X86_XSTATE_H */