Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - Initial support for the ARMv9 Scalable Matrix Extension (SME).

   SME takes the approach used for vectors in SVE and extends this to
   provide architectural support for matrix operations. No KVM support
   yet, SME is disabled in guests.

 - Support for crashkernel reservations above ZONE_DMA via the
   'crashkernel=X,high' command line option.

 - btrfs search_ioctl() fix for live-lock with sub-page faults.

 - arm64 perf updates: support for the Hisilicon "CPA" PMU for
   monitoring coherent I/O traffic, support for Arm's CMN-650 and
   CMN-700 interconnect PMUs, minor driver fixes, kerneldoc cleanup.

 - Kselftest updates for SME, BTI, MTE.

 - Automatic generation of the system register macros from a 'sysreg'
   file describing the register bitfields.

 - Update the type of the function argument holding the ESR_ELx register
   value to unsigned long to match the architecture register size
   (originally 32-bit but extended since ARMv8.0).

 - stacktrace cleanups.

 - ftrace cleanups.

 - Miscellaneous updates, most notably: arm64-specific huge_ptep_get(),
   avoid executable mappings in kexec/hibernate code, drop TLB flushing
   from get_clear_flush() (and rename it to get_clear_contig()),
   ARCH_NR_GPIO bumped to 2048 for ARCH_APPLE.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (145 commits)
  arm64/sysreg: Generate definitions for FAR_ELx
  arm64/sysreg: Generate definitions for DACR32_EL2
  arm64/sysreg: Generate definitions for CSSELR_EL1
  arm64/sysreg: Generate definitions for CPACR_ELx
  arm64/sysreg: Generate definitions for CONTEXTIDR_ELx
  arm64/sysreg: Generate definitions for CLIDR_EL1
  arm64/sve: Move sve_free() into SVE code section
  arm64: Kconfig.platforms: Add comments
  arm64: Kconfig: Fix indentation and add comments
  arm64: mm: avoid writable executable mappings in kexec/hibernate code
  arm64: lds: move special code sections out of kernel exec segment
  arm64/hugetlb: Implement arm64 specific huge_ptep_get()
  arm64/hugetlb: Use ptep_get() to get the pte value of a huge page
  arm64: kdump: Do not allocate crash low memory if not needed
  arm64/sve: Generate ZCR definitions
  arm64/sme: Generate defintions for SVCR
  arm64/sme: Generate SMPRI_EL1 definitions
  arm64/sme: Automatically generate SMPRIMAP_EL2 definitions
  arm64/sme: Automatically generate SMIDR_EL1 defines
  arm64/sme: Automatically generate defines for SMCR
  ...

42 files changed, 2761 insertions, 116 deletions

diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile
index 1e8d9a8f59df..9460cbe81bcc 100644
--- a/tools/testing/selftests/arm64/Makefile
+++ b/tools/testing/selftests/arm64/Makefile
@@ -17,16 +17,7 @@ top_srcdir = $(realpath ../../../../)
 # Additional include paths needed by kselftest.h and local headers
 CFLAGS += -I$(top_srcdir)/tools/testing/selftests/
 
-# Guessing where the Kernel headers could have been installed
-# depending on ENV config
-ifeq ($(KBUILD_OUTPUT),)
-khdr_dir = $(top_srcdir)/usr/include
-else
-# the KSFT preferred location when KBUILD_OUTPUT is set
-khdr_dir = $(KBUILD_OUTPUT)/kselftest/usr/include
-endif
-
-CFLAGS += -I$(khdr_dir)
+CFLAGS += $(KHDR_INCLUDES)
 
 export CFLAGS
 export top_srcdir
diff --git a/tools/testing/selftests/arm64/abi/.gitignore b/tools/testing/selftests/arm64/abi/.gitignore
index b79cf5814c23..b9e54417250d 100644
--- a/tools/testing/selftests/arm64/abi/.gitignore
+++ b/tools/testing/selftests/arm64/abi/.gitignore
@@ -1 +1,2 @@
 syscall-abi
+tpidr2
diff --git a/tools/testing/selftests/arm64/abi/Makefile b/tools/testing/selftests/arm64/abi/Makefile
index 96eba974ac8d..c8d7f2495eb2 100644
--- a/tools/testing/selftests/arm64/abi/Makefile
+++ b/tools/testing/selftests/arm64/abi/Makefile
@@ -1,8 +1,15 @@
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (C) 2021 ARM Limited
 
-TEST_GEN_PROGS := syscall-abi
+TEST_GEN_PROGS := syscall-abi tpidr2
 
 include ../../lib.mk
 
 $(OUTPUT)/syscall-abi: syscall-abi.c syscall-abi-asm.S
+
+# Build with nolibc since TPIDR2 is intended to be actively managed by
+# libc and we're trying to test the functionality that it depends on here.
+$(OUTPUT)/tpidr2: tpidr2.c
+	$(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+		-static -include ../../../../include/nolibc/nolibc.h \
+		-ffreestanding -Wall $^ -o $@ -lgcc
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
index 983467cfcee0..b523c21c2278 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
+++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
@@ -9,15 +9,42 @@
 // invoked is configured in x8 of the input GPR data.
 //
 // x0:	SVE VL, 0 for FP only
+// x1:	SME VL
 //
 //	GPRs:	gpr_in, gpr_out
 //	FPRs:	fpr_in, fpr_out
 //	Zn:	z_in, z_out
 //	Pn:	p_in, p_out
 //	FFR:	ffr_in, ffr_out
+//	ZA:	za_in, za_out
+//	SVCR:	svcr_in, svcr_out
+
+#include "syscall-abi.h"
 
 .arch_extension sve
 
+/*
+ * LDR (vector to ZA array):
+ *	LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _ldr_za nw, nxbase, offset=0
+	.inst	0xe1000000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * STR (vector from ZA array):
+ *	STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _str_za nw, nxbase, offset=0
+	.inst	0xe1200000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
 .globl do_syscall
 do_syscall:
 	// Store callee saved registers x19-x29 (80 bytes) plus x0 and x1
@@ -30,6 +57,24 @@ do_syscall:
 	stp	x25, x26, [sp, #80]
 	stp	x27, x28, [sp, #96]
 
+	// Set SVCR if we're doing SME
+	cbz	x1, 1f
+	adrp	x2, svcr_in
+	ldr	x2, [x2, :lo12:svcr_in]
+	msr	S3_3_C4_C2_2, x2
+1:
+
+	// Load ZA if it's enabled - uses x12 as scratch due to SME LDR
+	tbz	x2, #SVCR_ZA_SHIFT, 1f
+	mov	w12, #0
+	ldr	x2, =za_in
+2:	_ldr_za 12, 2
+	add	x2, x2, x1
+	add	x12, x12, #1
+	cmp	x1, x12
+	bne	2b
+1:
+
 	// Load GPRs x8-x28, and save our SP/FP for later comparison
 	ldr	x2, =gpr_in
 	add	x2, x2, #64
@@ -68,7 +113,7 @@ do_syscall:
 	ldp	q30, q31, [x2, #16 * 30]
 1:
 
-	// Load the SVE registers if we're doing SVE
+	// Load the SVE registers if we're doing SVE/SME
 	cbz	x0, 1f
 
 	ldr	x2, =z_in
@@ -105,9 +150,14 @@ do_syscall:
 	ldr	z30, [x2, #30, MUL VL]
 	ldr	z31, [x2, #31, MUL VL]
 
+	// Only set a non-zero FFR, test patterns must be zero since the
+	// syscall should clear it - this lets us handle FA64.
 	ldr	x2, =ffr_in
 	ldr	p0, [x2, #0]
+	ldr	x2, [x2, #0]
+	cbz	x2, 2f
 	wrffr	p0.b
+2:
 
 	ldr	x2, =p_in
 	ldr	p0, [x2, #0, MUL VL]
@@ -169,6 +219,24 @@ do_syscall:
 	stp	q28, q29, [x2, #16 * 28]
 	stp	q30, q31, [x2, #16 * 30]
 
+	// Save SVCR if we're doing SME
+	cbz	x1, 1f
+	mrs	x2, S3_3_C4_C2_2
+	adrp	x3, svcr_out
+	str	x2, [x3, :lo12:svcr_out]
+1:
+
+	// Save ZA if it's enabled - uses x12 as scratch due to SME STR
+	tbz	x2, #SVCR_ZA_SHIFT, 1f
+	mov	w12, #0
+	ldr	x2, =za_out
+2:	_str_za 12, 2
+	add	x2, x2, x1
+	add	x12, x12, #1
+	cmp	x1, x12
+	bne	2b
+1:
+
 	// Save the SVE state if we have some
 	cbz	x0, 1f
 
@@ -224,6 +292,10 @@ do_syscall:
 	str	p14, [x2, #14, MUL VL]
 	str	p15, [x2, #15, MUL VL]
 
+	// Only save FFR if we wrote a value for SME
+	ldr	x2, =ffr_in
+	ldr	x2, [x2, #0]
+	cbz	x2, 1f
 	ldr	x2, =ffr_out
 	rdffr	p0.b
 	str	p0, [x2, #0]
@@ -237,4 +309,9 @@ do_syscall:
 	ldp	x27, x28, [sp, #96]
 	ldp	x29, x30, [sp], #112
 
+	// Clear SVCR if we were doing SME so future tests don't have ZA
+	cbz	x1, 1f
+	msr	S3_3_C4_C2_2, xzr
+1:
+
 	ret
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c
index 1e13b7523918..b632bfe9e022 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi.c
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.c
@@ -18,9 +18,13 @@
 
 #include "../../kselftest.h"
 
+#include "syscall-abi.h"
+
 #define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1)
 
-extern void do_syscall(int sve_vl);
+static int default_sme_vl;
+
+extern void do_syscall(int sve_vl, int sme_vl);
 
 static void fill_random(void *buf, size_t size)
 {
@@ -48,14 +52,15 @@ static struct syscall_cfg {
 uint64_t gpr_in[NUM_GPR];
 uint64_t gpr_out[NUM_GPR];
 
-static void setup_gpr(struct syscall_cfg *cfg, int sve_vl)
+static void setup_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		      uint64_t svcr)
 {
 	fill_random(gpr_in, sizeof(gpr_in));
 	gpr_in[8] = cfg->syscall_nr;
 	memset(gpr_out, 0, sizeof(gpr_out));
 }
 
-static int check_gpr(struct syscall_cfg *cfg, int sve_vl)
+static int check_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr)
 {
 	int errors = 0;
 	int i;
@@ -79,13 +84,15 @@ static int check_gpr(struct syscall_cfg *cfg, int sve_vl)
 uint64_t fpr_in[NUM_FPR * 2];
 uint64_t fpr_out[NUM_FPR * 2];
 
-static void setup_fpr(struct syscall_cfg *cfg, int sve_vl)
+static void setup_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		      uint64_t svcr)
 {
 	fill_random(fpr_in, sizeof(fpr_in));
 	memset(fpr_out, 0, sizeof(fpr_out));
 }
 
-static int check_fpr(struct syscall_cfg *cfg, int sve_vl)
+static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		     uint64_t svcr)
 {
 	int errors = 0;
 	int i;
@@ -109,13 +116,15 @@ static uint8_t z_zero[__SVE_ZREG_SIZE(SVE_VQ_MAX)];
 uint8_t z_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
 uint8_t z_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
 
-static void setup_z(struct syscall_cfg *cfg, int sve_vl)
+static void setup_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		    uint64_t svcr)
 {
 	fill_random(z_in, sizeof(z_in));
 	fill_random(z_out, sizeof(z_out));
 }
 
-static int check_z(struct syscall_cfg *cfg, int sve_vl)
+static int check_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		   uint64_t svcr)
 {
 	size_t reg_size = sve_vl;
 	int errors = 0;
@@ -126,13 +135,17 @@ static int check_z(struct syscall_cfg *cfg, int sve_vl)
 
 	/*
 	 * After a syscall the low 128 bits of the Z registers should
-	 * be preserved and the rest be zeroed or preserved.
+	 * be preserved and the rest be zeroed or preserved, except if
+	 * we were in streaming mode in which case the low 128 bits may
+	 * also be cleared by the transition out of streaming mode.
 	 */
 	for (i = 0; i < SVE_NUM_ZREGS; i++) {
 		void *in = &z_in[reg_size * i];
 		void *out = &z_out[reg_size * i];
 
-		if (memcmp(in, out, SVE_VQ_BYTES) != 0) {
+		if ((memcmp(in, out, SVE_VQ_BYTES) != 0) &&
+		    !((svcr & SVCR_SM_MASK) &&
+		      memcmp(z_zero, out, SVE_VQ_BYTES) == 0)) {
 			ksft_print_msg("%s SVE VL %d Z%d low 128 bits changed\n",
 				       cfg->name, sve_vl, i);
 			errors++;
@@ -145,13 +158,15 @@ static int check_z(struct syscall_cfg *cfg, int sve_vl)
 uint8_t p_in[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)];
 uint8_t p_out[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)];
 
-static void setup_p(struct syscall_cfg *cfg, int sve_vl)
+static void setup_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		    uint64_t svcr)
 {
 	fill_random(p_in, sizeof(p_in));
 	fill_random(p_out, sizeof(p_out));
 }
 
-static int check_p(struct syscall_cfg *cfg, int sve_vl)
+static int check_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		   uint64_t svcr)
 {
 	size_t reg_size = sve_vq_from_vl(sve_vl) * 2; /* 1 bit per VL byte */
 
@@ -175,9 +190,20 @@ static int check_p(struct syscall_cfg *cfg, int sve_vl)
 uint8_t ffr_in[__SVE_PREG_SIZE(SVE_VQ_MAX)];
 uint8_t ffr_out[__SVE_PREG_SIZE(SVE_VQ_MAX)];
 
-static void setup_ffr(struct syscall_cfg *cfg, int sve_vl)
+static void setup_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		      uint64_t svcr)
 {
 	/*
+	 * If we are in streaming mode and do not have FA64 then FFR
+	 * is unavailable.
+	 */
+	if ((svcr & SVCR_SM_MASK) &&
+	    !(getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)) {
+		memset(&ffr_in, 0, sizeof(ffr_in));
+		return;
+	}
+
+	/*
 	 * It is only valid to set a contiguous set of bits starting
 	 * at 0.  For now since we're expecting this to be cleared by
 	 * a syscall just set all bits.
@@ -186,7 +212,8 @@ static void setup_ffr(struct syscall_cfg *cfg, int sve_vl)
 	fill_random(ffr_out, sizeof(ffr_out));
 }
 
-static int check_ffr(struct syscall_cfg *cfg, int sve_vl)
+static int check_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		     uint64_t svcr)
 {
 	size_t reg_size = sve_vq_from_vl(sve_vl) * 2;  /* 1 bit per VL byte */
 	int errors = 0;
@@ -195,6 +222,10 @@ static int check_ffr(struct syscall_cfg *cfg, int sve_vl)
 	if (!sve_vl)
 		return 0;
 
+	if ((svcr & SVCR_SM_MASK) &&
+	    !(getauxval(AT_HWCAP2) & HWCAP2_SME_FA64))
+		return 0;
+
 	/* After a syscall the P registers should be preserved or zeroed */
 	for (i = 0; i < reg_size; i++)
 		if (ffr_out[i] && (ffr_in[i] != ffr_out[i]))
@@ -206,8 +237,65 @@ static int check_ffr(struct syscall_cfg *cfg, int sve_vl)
 	return errors;
 }
 
-typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl);
-typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl);
+uint64_t svcr_in, svcr_out;
+
+static void setup_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		    uint64_t svcr)
+{
+	svcr_in = svcr;
+}
+
+static int check_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		      uint64_t svcr)
+{
+	int errors = 0;
+
+	if (svcr_out & SVCR_SM_MASK) {
+		ksft_print_msg("%s Still in SM, SVCR %llx\n",
+			       cfg->name, svcr_out);
+		errors++;
+	}
+
+	if ((svcr_in & SVCR_ZA_MASK) != (svcr_out & SVCR_ZA_MASK)) {
+		ksft_print_msg("%s PSTATE.ZA changed, SVCR %llx != %llx\n",
+			       cfg->name, svcr_in, svcr_out);
+		errors++;
+	}
+
+	return errors;
+}
+
+uint8_t za_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+uint8_t za_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+
+static void setup_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		     uint64_t svcr)
+{
+	fill_random(za_in, sizeof(za_in));
+	memset(za_out, 0, sizeof(za_out));
+}
+
+static int check_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		    uint64_t svcr)
+{
+	size_t reg_size = sme_vl * sme_vl;
+	int errors = 0;
+
+	if (!(svcr & SVCR_ZA_MASK))
+		return 0;
+
+	if (memcmp(za_in, za_out, reg_size) != 0) {
+		ksft_print_msg("SME VL %d ZA does not match\n", sme_vl);
+		errors++;
+	}
+
+	return errors;
+}
+
+typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+			 uint64_t svcr);
+typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+			uint64_t svcr);
 
 /*
  * Each set of registers has a setup function which is called before
@@ -225,20 +313,23 @@ static struct {
 	{ setup_z, check_z },
 	{ setup_p, check_p },
 	{ setup_ffr, check_ffr },
+	{ setup_svcr, check_svcr },
+	{ setup_za, check_za },
 };
 
-static bool do_test(struct syscall_cfg *cfg, int sve_vl)
+static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		    uint64_t svcr)
 {
 	int errors = 0;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(regset); i++)
-		regset[i].setup(cfg, sve_vl);
+		regset[i].setup(cfg, sve_vl, sme_vl, svcr);
 
-	do_syscall(sve_vl);
+	do_syscall(sve_vl, sme_vl);
 
 	for (i = 0; i < ARRAY_SIZE(regset); i++)
-		errors += regset[i].check(cfg, sve_vl);
+		errors += regset[i].check(cfg, sve_vl, sme_vl, svcr);
 
 	return errors == 0;
 }
@@ -246,9 +337,10 @@ static bool do_test(struct syscall_cfg *cfg, int sve_vl)
 static void test_one_syscall(struct syscall_cfg *cfg)
 {
 	int sve_vq, sve_vl;
+	int sme_vq, sme_vl;
 
 	/* FPSIMD only case */
-	ksft_test_result(do_test(cfg, 0),
+	ksft_test_result(do_test(cfg, 0, default_sme_vl, 0),
 			 "%s FPSIMD\n", cfg->name);
 
 	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
@@ -265,8 +357,36 @@ static void test_one_syscall(struct syscall_cfg *cfg)
 		if (sve_vq != sve_vq_from_vl(sve_vl))
 			sve_vq = sve_vq_from_vl(sve_vl);
 
-		ksft_test_result(do_test(cfg, sve_vl),
+		ksft_test_result(do_test(cfg, sve_vl, default_sme_vl, 0),
 				 "%s SVE VL %d\n", cfg->name, sve_vl);
+
+		if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
+			continue;
+
+		for (sme_vq = SVE_VQ_MAX; sme_vq > 0; --sme_vq) {
+			sme_vl = prctl(PR_SME_SET_VL, sme_vq * 16);
+			if (sme_vl == -1)
+				ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
+						   strerror(errno), errno);
+
+			sme_vl &= PR_SME_VL_LEN_MASK;
+
+			if (sme_vq != sve_vq_from_vl(sme_vl))
+				sme_vq = sve_vq_from_vl(sme_vl);
+
+			ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+						 SVCR_ZA_MASK | SVCR_SM_MASK),
+					 "%s SVE VL %d/SME VL %d SM+ZA\n",
+					 cfg->name, sve_vl, sme_vl);
+			ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+						 SVCR_SM_MASK),
+					 "%s SVE VL %d/SME VL %d SM\n",
+					 cfg->name, sve_vl, sme_vl);
+			ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+						 SVCR_ZA_MASK),
+					 "%s SVE VL %d/SME VL %d ZA\n",
+					 cfg->name, sve_vl, sme_vl);
+		}
 	}
 }
 
@@ -299,14 +419,54 @@ int sve_count_vls(void)
 	return vl_count;
 }
 
+int sme_count_vls(void)
+{
+	unsigned int vq;
+	int vl_count = 0;
+	int vl;
+
+	if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
+		return 0;
+
+	/* Ensure we configure a SME VL, used to flag if SVCR is set */
+	default_sme_vl = 16;
+
+	/*
+	 * Enumerate up to SVE_VQ_MAX vector lengths
+	 */
+	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+		vl = prctl(PR_SME_SET_VL, vq * 16);
+		if (vl == -1)
+			ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
+					   strerror(errno), errno);
+
+		vl &= PR_SME_VL_LEN_MASK;
+
+		if (vq != sve_vq_from_vl(vl))
+			vq = sve_vq_from_vl(vl);
+
+		vl_count++;
+	}
+
+	return vl_count;
+}
+
 int main(void)
 {
 	int i;
+	int tests = 1;  /* FPSIMD */
 
 	srandom(getpid());
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(syscalls) * (sve_count_vls() + 1));
+	tests += sve_count_vls();
+	tests += (sve_count_vls() * sme_count_vls()) * 3;
+	ksft_set_plan(ARRAY_SIZE(syscalls) * tests);
+
+	if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)
+		ksft_print_msg("SME with FA64\n");
+	else if (getauxval(AT_HWCAP2) & HWCAP2_SME)
+		ksft_print_msg("SME without FA64\n");
 
 	for (i = 0; i < ARRAY_SIZE(syscalls); i++)
 		test_one_syscall(&syscalls[i]);
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.h b/tools/testing/selftests/arm64/abi/syscall-abi.h
new file mode 100644
index 000000000000..bda5a87ad381
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 ARM Limited.
+ */
+
+#ifndef SYSCALL_ABI_H
+#define SYSCALL_ABI_H
+
+#define SVCR_ZA_MASK		2
+#define SVCR_SM_MASK		1
+
+#define SVCR_ZA_SHIFT		1
+#define SVCR_SM_SHIFT		0
+
+#endif
diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c
new file mode 100644
index 000000000000..351a098b503a
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/tpidr2.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/sched.h>
+#include <linux/wait.h>
+
+#define SYS_TPIDR2 "S3_3_C13_C0_5"
+
+#define EXPECTED_TESTS 5
+
+static void putstr(const char *str)
+{
+	write(1, str, strlen(str));
+}
+
+static void putnum(unsigned int num)
+{
+	char c;
+
+	if (num / 10)
+		putnum(num / 10);
+
+	c = '0' + (num % 10);
+	write(1, &c, 1);
+}
+
+static int tests_run;
+static int tests_passed;
+static int tests_failed;
+static int tests_skipped;
+
+static void set_tpidr2(uint64_t val)
+{
+	asm volatile (
+		"msr	" SYS_TPIDR2 ", %0\n"
+		:
+		: "r"(val)
+		: "cc");
+}
+
+static uint64_t get_tpidr2(void)
+{
+	uint64_t val;
+
+	asm volatile (
+		"mrs	%0, " SYS_TPIDR2 "\n"
+		: "=r"(val)
+		:
+		: "cc");
+
+	return val;
+}
+
+static void print_summary(void)
+{
+	if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS)
+		putstr("# UNEXPECTED TEST COUNT: ");
+
+	putstr("# Totals: pass:");
+	putnum(tests_passed);
+	putstr(" fail:");
+	putnum(tests_failed);
+	putstr(" xfail:0 xpass:0 skip:");
+	putnum(tests_skipped);
+	putstr(" error:0\n");
+}
+
+/* Processes should start with TPIDR2 == 0 */
+static int default_value(void)
+{
+	return get_tpidr2() == 0;
+}
+
+/* If we set TPIDR2 we should read that value */
+static int write_read(void)
+{
+	set_tpidr2(getpid());
+
+	return getpid() == get_tpidr2();
+}
+
+/* If we set a value we should read the same value after scheduling out */
+static int write_sleep_read(void)
+{
+	set_tpidr2(getpid());
+
+	msleep(100);
+
+	return getpid() == get_tpidr2();
+}
+
+/*
+ * If we fork the value in the parent should be unchanged and the
+ * child should start with the same value and be able to set its own
+ * value.
+ */
+static int write_fork_read(void)
+{
+	pid_t newpid, waiting, oldpid;
+	int status;
+
+	set_tpidr2(getpid());
+
+	oldpid = getpid();
+	newpid = fork();
+	if (newpid == 0) {
+		/* In child */
+		if (get_tpidr2() != oldpid) {
+			putstr("# TPIDR2 changed in child: ");
+			putnum(get_tpidr2());
+			putstr("\n");
+			exit(0);
+		}
+
+		set_tpidr2(getpid());
+		if (get_tpidr2() == getpid()) {
+			exit(1);
+		} else {
+			putstr("# Failed to set TPIDR2 in child\n");
+			exit(0);
+		}
+	}
+	if (newpid < 0) {
+		putstr("# fork() failed: -");
+		putnum(-newpid);
+		putstr("\n");
+		return 0;
+	}
+
+	for (;;) {
+		waiting = waitpid(newpid, &status, 0);
+
+		if (waiting < 0) {
+			if (errno == EINTR)
+				continue;
+			putstr("# waitpid() failed: ");
+			putnum(errno);
+			putstr("\n");
+			return 0;
+		}
+		if (waiting != newpid) {
+			putstr("# waitpid() returned wrong PID\n");
+			return 0;
+		}
+
+		if (!WIFEXITED(status)) {
+			putstr("# child did not exit\n");
+			return 0;
+		}
+
+		if (getpid() != get_tpidr2()) {
+			putstr("# TPIDR2 corrupted in parent\n");
+			return 0;
+		}
+
+		return WEXITSTATUS(status);
+	}
+}
+
+/*
+ * sys_clone() has a lot of per architecture variation so just define
+ * it here rather than adding it to nolibc, plus the raw API is a
+ * little more convenient for this test.
+ */
+static int sys_clone(unsigned long clone_flags, unsigned long newsp,
+		     int *parent_tidptr, unsigned long tls,
+		     int *child_tidptr)
+{
+	return my_syscall5(__NR_clone, clone_flags, newsp, parent_tidptr, tls,
+			   child_tidptr);
+}
+
+/*
+ * If we clone with CLONE_SETTLS then the value in the parent should
+ * be unchanged and the child should start with zero and be able to
+ * set its own value.
+ */
+static int write_clone_read(void)
+{
+	int parent_tid, child_tid;
+	pid_t parent, waiting;
+	int ret, status;
+
+	parent = getpid();
+	set_tpidr2(parent);
+
+	ret = sys_clone(CLONE_SETTLS, 0, &parent_tid, 0, &child_tid);
+	if (ret == -1) {
+		putstr("# clone() failed\n");
+		putnum(errno);
+		putstr("\n");
+		return 0;
+	}
+
+	if (ret == 0) {
+		/* In child */
+		if (get_tpidr2() != 0) {
+			putstr("# TPIDR2 non-zero in child: ");
+			putnum(get_tpidr2());
+			putstr("\n");
+			exit(0);
+		}
+
+		if (gettid() == 0)
+			putstr("# Child TID==0\n");
+		set_tpidr2(gettid());
+		if (get_tpidr2() == gettid()) {
+			exit(1);
+		} else {
+			putstr("# Failed to set TPIDR2 in child\n");
+			exit(0);
+		}
+	}
+
+	for (;;) {
+		waiting = wait4(ret, &status, __WCLONE, NULL);
+
+		if (waiting < 0) {
+			if (errno == EINTR)
+				continue;
+			putstr("# wait4() failed: ");
+			putnum(errno);
+			putstr("\n");
+			return 0;
+		}
+		if (waiting != ret) {
+			putstr("# wait4() returned wrong PID ");
+			putnum(waiting);
+			putstr("\n");
+			return 0;
+		}
+
+		if (!WIFEXITED(status)) {
+			putstr("# child did not exit\n");
+			return 0;
+		}
+
+		if (parent != get_tpidr2()) {
+			putstr("# TPIDR2 corrupted in parent\n");
+			return 0;
+		}
+
+		return WEXITSTATUS(status);
+	}
+}
+
+#define run_test(name)			     \
+	if (name()) {			     \
+		tests_passed++;		     \
+	} else {			     \
+		tests_failed++;		     \
+		putstr("not ");		     \
+	}				     \
+	putstr("ok ");			     \
+	putnum(++tests_run);		     \
+	putstr(" " #name "\n");
+
+int main(int argc, char **argv)
+{
+	int ret, i;
+
+	putstr("TAP version 13\n");
+	putstr("1..");
+	putnum(EXPECTED_TESTS);
+	putstr("\n");
+
+	putstr("# PID: ");
+	putnum(getpid());
+	putstr("\n");
+
+	/*
+	 * This test is run with nolibc which doesn't support hwcap and
+	 * it's probably disproportionate to implement so instead check
+	 * for the default vector length configuration in /proc.
+	 */
+	ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0);
+	if (ret >= 0) {
+		run_test(default_value);
+		run_test(write_read);
+		run_test(write_sleep_read);
+		run_test(write_fork_read);
+		run_test(write_clone_read);
+
+	} else {
+		putstr("# SME support not present\n");
+
+		for (i = 0; i < EXPECTED_TESTS; i++) {
+			putstr("ok ");
+			putnum(i);
+			putstr(" skipped, TPIDR2 not supported\n");
+		}
+
+		tests_skipped += EXPECTED_TESTS;
+	}
+
+	print_summary();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/bti/Makefile b/tools/testing/selftests/arm64/bti/Makefile
index 73e013c082a6..ccdac414ad94 100644
--- a/tools/testing/selftests/arm64/bti/Makefile
+++ b/tools/testing/selftests/arm64/bti/Makefile
@@ -10,7 +10,7 @@ PROGS := $(patsubst %,gen/%,$(TEST_GEN_PROGS))
 # cases for statically linked and dynamically lined binaries are
 # slightly different.
 
-CFLAGS_NOBTI = -DBTI=0
+CFLAGS_NOBTI = -mbranch-protection=none -DBTI=0
 CFLAGS_BTI = -mbranch-protection=standard -DBTI=1
 
 CFLAGS_COMMON = -ffreestanding -Wall -Wextra $(CFLAGS)
@@ -39,7 +39,7 @@ BTI_OBJS =                                      \
 	teststubs-bti.o                         \
 	trampoline-bti.o
 gen/btitest: $(BTI_OBJS)
-	$(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -o $@ $^
+	$(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^
 
 NOBTI_OBJS =                                    \
 	test-nobti.o                         \
@@ -50,7 +50,7 @@ NOBTI_OBJS =                                    \
 	teststubs-nobti.o                       \
 	trampoline-nobti.o
 gen/nobtitest: $(NOBTI_OBJS)
-	$(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -o $@ $^
+	$(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^
 
 # Including KSFT lib.mk here will also mangle the TEST_GEN_PROGS list
 # to account for any OUTPUT target-dirs optionally provided by
diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore
index c50d86331ed2..ea947af63882 100644
--- a/tools/testing/selftests/arm64/fp/.gitignore
+++ b/tools/testing/selftests/arm64/fp/.gitignore
@@ -1,8 +1,13 @@
 fp-pidbench
 fpsimd-test
+rdvl-sme
 rdvl-sve
 sve-probe-vls
 sve-ptrace
 sve-test
+ssve-test
 vec-syscfg
 vlset
+za-fork
+za-ptrace
+za-test
diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile
index 95f0b877a060..a7c2286bf65b 100644
--- a/tools/testing/selftests/arm64/fp/Makefile
+++ b/tools/testing/selftests/arm64/fp/Makefile
@@ -1,24 +1,42 @@
 # SPDX-License-Identifier: GPL-2.0
 
-CFLAGS += -I../../../../../usr/include/
-TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg
-TEST_PROGS_EXTENDED := fp-pidbench fpsimd-test fpsimd-stress \
-	rdvl-sve \
-	sve-test sve-stress \
+# A proper top_srcdir is needed by KSFT(lib.mk)
+top_srcdir = $(realpath ../../../../../)
+
+CFLAGS += -I$(top_srcdir)/usr/include/
+
+TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg za-fork za-ptrace
+TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \
+	rdvl-sme rdvl-sve \
+	sve-test \
+	ssve-test \
+	za-test \
 	vlset
+TEST_PROGS_EXTENDED := fpsimd-stress sve-stress ssve-stress za-stress
 
-all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED)
+EXTRA_CLEAN += $(OUTPUT)/asm-utils.o $(OUTPUT)/rdvl.o $(OUTPUT)/za-fork-asm.o
 
-fp-pidbench: fp-pidbench.S asm-utils.o
+# Build with nolibc to avoid effects due to libc's clone() support
+$(OUTPUT)/fp-pidbench: fp-pidbench.S $(OUTPUT)/asm-utils.o
+	$(CC) -nostdlib $^ -o $@
+$(OUTPUT)/fpsimd-test: fpsimd-test.S $(OUTPUT)/asm-utils.o
 	$(CC) -nostdlib $^ -o $@
-fpsimd-test: fpsimd-test.o asm-utils.o
+$(OUTPUT)/rdvl-sve: rdvl-sve.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/rdvl-sme: rdvl-sme.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/sve-ptrace: sve-ptrace.c
+$(OUTPUT)/sve-probe-vls: sve-probe-vls.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/sve-test: sve-test.S $(OUTPUT)/asm-utils.o
 	$(CC) -nostdlib $^ -o $@
-rdvl-sve: rdvl-sve.o rdvl.o
-sve-ptrace: sve-ptrace.o
-sve-probe-vls: sve-probe-vls.o rdvl.o
-sve-test: sve-test.o asm-utils.o
+$(OUTPUT)/ssve-test: sve-test.S $(OUTPUT)/asm-utils.o
+	$(CC) -DSSVE -nostdlib $^ -o $@
+$(OUTPUT)/vec-syscfg: vec-syscfg.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/vlset: vlset.c
+$(OUTPUT)/za-fork: za-fork.c $(OUTPUT)/za-fork-asm.o
+	$(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+		-include ../../../../include/nolibc/nolibc.h \
+		-static -ffreestanding -Wall $^ -o $@
+$(OUTPUT)/za-ptrace: za-ptrace.c
+$(OUTPUT)/za-test: za-test.S $(OUTPUT)/asm-utils.o
 	$(CC) -nostdlib $^ -o $@
-vec-syscfg: vec-syscfg.o rdvl.o
-vlset: vlset.o
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/arm64/fp/rdvl-sme.c b/tools/testing/selftests/arm64/fp/rdvl-sme.c
new file mode 100644
index 000000000000..49b0b2e08bac
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/rdvl-sme.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <stdio.h>
+
+#include "rdvl.h"
+
+int main(void)
+{
+	int vl = rdvl_sme();
+
+	printf("%d\n", vl);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/fp/rdvl.S b/tools/testing/selftests/arm64/fp/rdvl.S
index c916c1c9defd..20dc29996dc6 100644
--- a/tools/testing/selftests/arm64/fp/rdvl.S
+++ b/tools/testing/selftests/arm64/fp/rdvl.S
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
 // Copyright (C) 2021 ARM Limited.
 
+#include "sme-inst.h"
+
 .arch_extension sve
 
 .globl rdvl_sve
@@ -8,3 +10,11 @@ rdvl_sve:
 	hint	34			// BTI C
 	rdvl	x0, #1
 	ret
+
+.globl rdvl_sme
+rdvl_sme:
+	hint	34			// BTI C
+
+	rdsvl	0, 1
+
+	ret
diff --git a/tools/testing/selftests/arm64/fp/rdvl.h b/tools/testing/selftests/arm64/fp/rdvl.h
index 7c9d953fc9e7..5d323679fbc9 100644
--- a/tools/testing/selftests/arm64/fp/rdvl.h
+++ b/tools/testing/selftests/arm64/fp/rdvl.h
@@ -3,6 +3,7 @@
 #ifndef RDVL_H
 #define RDVL_H
 
+int rdvl_sme(void);
 int rdvl_sve(void);
 
 #endif
diff --git a/tools/testing/selftests/arm64/fp/sme-inst.h b/tools/testing/selftests/arm64/fp/sme-inst.h
new file mode 100644
index 000000000000..7191e53ca1c0
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/sme-inst.h
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021-2 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+
+#ifndef SME_INST_H
+#define SME_INST_H
+
+/*
+ * RDSVL X\nx, #\imm
+ */
+.macro rdsvl nx, imm
+	.inst	0x4bf5800			\
+		| (\imm << 5)			\
+		| (\nx)
+.endm
+
+.macro smstop
+	msr	S0_3_C4_C6_3, xzr
+.endm
+
+.macro smstart_za
+	msr	S0_3_C4_C5_3, xzr
+.endm
+
+.macro smstart_sm
+	msr	S0_3_C4_C3_3, xzr
+.endm
+
+/*
+ * LDR (vector to ZA array):
+ *	LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _ldr_za nw, nxbase, offset=0
+	.inst	0xe1000000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * STR (vector from ZA array):
+ *	STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _str_za nw, nxbase, offset=0
+	.inst	0xe1200000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+#endif
diff --git a/tools/testing/selftests/arm64/fp/ssve-stress b/tools/testing/selftests/arm64/fp/ssve-stress
new file mode 100644
index 000000000000..e2bd2cc184ad
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/ssve-stress
@@ -0,0 +1,59 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2015-2019 ARM Limited.
+# Original author: Dave Martin <Dave.Martin@arm.com>
+
+set -ue
+
+NR_CPUS=`nproc`
+
+pids=
+logs=
+
+cleanup () {
+	trap - INT TERM CHLD
+	set +e
+
+	if [ -n "$pids" ]; then
+		kill $pids
+		wait $pids
+		pids=
+	fi
+
+	if [ -n "$logs" ]; then
+		cat $logs
+		rm $logs
+		logs=
+	fi
+}
+
+interrupt () {
+	cleanup
+	exit 0
+}
+
+child_died () {
+	cleanup
+	exit 1
+}
+
+trap interrupt INT TERM EXIT
+
+for x in `seq 0 $((NR_CPUS * 4))`; do
+	log=`mktemp`
+	logs=$logs\ $log
+	./ssve-test >$log &
+	pids=$pids\ $!
+done
+
+# Wait for all child processes to be created:
+sleep 10
+
+while :; do
+	kill -USR1 $pids
+done &
+pids=$pids\ $!
+
+wait
+
+exit 1
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index 4c418b2021e0..8c4847977583 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -26,6 +26,10 @@
 #define NT_ARM_SVE 0x405
 #endif
 
+#ifndef NT_ARM_SSVE
+#define NT_ARM_SSVE 0x40b
+#endif
+
 struct vec_type {
 	const char *name;
 	unsigned long hwcap_type;
@@ -42,11 +46,18 @@ static const struct vec_type vec_types[] = {
 		.regset = NT_ARM_SVE,
 		.prctl_set = PR_SVE_SET_VL,
 	},
+	{
+		.name = "Streaming SVE",
+		.hwcap_type = AT_HWCAP2,
+		.hwcap = HWCAP2_SME,
+		.regset = NT_ARM_SSVE,
+		.prctl_set = PR_SME_SET_VL,
+	},
 };
 
-#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
+#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 4)
 #define FLAG_TESTS 2
-#define FPSIMD_TESTS 3
+#define FPSIMD_TESTS 2
 
 #define EXPECTED_TESTS ((VL_TESTS + FLAG_TESTS + FPSIMD_TESTS) * ARRAY_SIZE(vec_types))
 
@@ -78,6 +89,15 @@ static int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
 	return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov);
 }
 
+static int set_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
+{
+	struct iovec iov;
+
+	iov.iov_base = fpsimd;
+	iov.iov_len = sizeof(*fpsimd);
+	return ptrace(PTRACE_SETREGSET, pid, NT_PRFPREG, &iov);
+}
+
 static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type,
 				       void **buf, size_t *size)
 {
@@ -240,28 +260,24 @@ static void check_u32(unsigned int vl, const char *reg,
 /* Access the FPSIMD registers via the SVE regset */
 static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
 {
-	void *svebuf = NULL;
-	size_t svebufsz = 0;
+	void *svebuf;
 	struct user_sve_header *sve;
 	struct user_fpsimd_state *fpsimd, new_fpsimd;
 	unsigned int i, j;
 	unsigned char *p;
+	int ret;
 
-	/* New process should start with FPSIMD registers only */
-	sve = get_sve(child, type, &svebuf, &svebufsz);
-	if (!sve) {
-		ksft_test_result_fail("get_sve(%s): %s\n",
-				      type->name, strerror(errno));
-
+	svebuf = malloc(SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD));
+	if (!svebuf) {
+		ksft_test_result_fail("Failed to allocate FPSIMD buffer\n");
 		return;
-	} else {
-		ksft_test_result_pass("get_sve(%s FPSIMD)\n", type->name);
 	}
 
-	ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD,
-			 "Got FPSIMD registers via %s\n", type->name);
-	if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD)
-		goto out;
+	memset(svebuf, 0, SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD));
+	sve = svebuf;
+	sve->flags = SVE_PT_REGS_FPSIMD;
+	sve->size = SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD);
+	sve->vl = 16;  /* We don't care what the VL is */
 
 	/* Try to set a known FPSIMD state via PT_REGS_SVE */
 	fpsimd = (struct user_fpsimd_state *)((char *)sve +
@@ -273,12 +289,11 @@ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
 			p[j] = j;
 	}
 
-	if (set_sve(child, type, sve)) {
-		ksft_test_result_fail("set_sve(%s FPSIMD): %s\n",
-				      type->name, strerror(errno));
-
+	ret = set_sve(child, type, sve);
+	ksft_test_result(ret == 0, "%s FPSIMD set via SVE: %d\n",
+			 type->name, ret);
+	if (ret)
 		goto out;
-	}
 
 	/* Verify via the FPSIMD regset */
 	if (get_fpsimd(child, &new_fpsimd)) {
@@ -395,7 +410,7 @@ out:
 	free(write_buf);
 }
 
-/* Validate attempting to set SVE data and read SVE data */
+/* Validate attempting to set SVE data and read it via the FPSIMD regset */
 static void ptrace_set_sve_get_fpsimd_data(pid_t child,
 					   const struct vec_type *type,
 					   unsigned int vl)
@@ -478,6 +493,115 @@ out:
 	free(write_buf);
 }
 
+/* Validate attempting to set FPSIMD data and read it via the SVE regset */
+static void ptrace_set_fpsimd_get_sve_data(pid_t child,
+					   const struct vec_type *type,
+					   unsigned int vl)
+{
+	void *read_buf = NULL;
+	unsigned char *p;
+	struct user_sve_header *read_sve;
+	unsigned int vq = sve_vq_from_vl(vl);
+	struct user_fpsimd_state write_fpsimd;
+	int ret, i, j;
+	size_t read_sve_size = 0;
+	size_t expected_size;
+	int errors = 0;
+
+	if (__BYTE_ORDER == __BIG_ENDIAN) {
+		ksft_test_result_skip("Big endian not supported\n");
+		return;
+	}
+
+	for (i = 0; i < 32; ++i) {
+		p = (unsigned char *)&write_fpsimd.vregs[i];
+
+		for (j = 0; j < sizeof(write_fpsimd.vregs[i]); ++j)
+			p[j] = j;
+	}
+
+	ret = set_fpsimd(child, &write_fpsimd);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set FPSIMD state: %d\n)",
+				      ret);
+		return;
+	}
+
+	if (!get_sve(child, type, (void **)&read_buf, &read_sve_size)) {
+		ksft_test_result_fail("Failed to read %s VL %u data\n",
+				      type->name, vl);
+		return;
+	}
+	read_sve = read_buf;
+
+	if (read_sve->vl != vl) {
+		ksft_test_result_fail("Child VL != expected VL %d\n",
+				      read_sve->vl, vl);
+		goto out;
+	}
+
+	/* The kernel may return either SVE or FPSIMD format */
+	switch (read_sve->flags & SVE_PT_REGS_MASK) {
+	case SVE_PT_REGS_FPSIMD:
+		expected_size = SVE_PT_FPSIMD_SIZE(vq, SVE_PT_REGS_FPSIMD);
+		if (read_sve_size < expected_size) {
+			ksft_test_result_fail("Read %d bytes, expected %d\n",
+					      read_sve_size, expected_size);
+			goto out;
+		}
+
+		ret = memcmp(&write_fpsimd, read_buf + SVE_PT_FPSIMD_OFFSET,
+			     sizeof(write_fpsimd));
+		if (ret != 0) {
+			ksft_print_msg("Read FPSIMD data mismatch\n");
+			errors++;
+		}
+		break;
+
+	case SVE_PT_REGS_SVE:
+		expected_size = SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
+		if (read_sve_size < expected_size) {
+			ksft_test_result_fail("Read %d bytes, expected %d\n",
+					      read_sve_size, expected_size);
+			goto out;
+		}
+
+		for (i = 0; i < __SVE_NUM_ZREGS; i++) {
+			__uint128_t tmp = 0;
+
+			/*
+			 * Z regs are stored endianness invariant, this won't
+			 * work for big endian
+			 */
+			memcpy(&tmp, read_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i),
+			       sizeof(tmp));
+
+			if (tmp != write_fpsimd.vregs[i]) {
+				ksft_print_msg("Mismatch in FPSIMD for %s VL %u Z%d/V%d\n",
+					       type->name, vl, i, i);
+				errors++;
+			}
+		}
+
+		check_u32(vl, "FPSR", &write_fpsimd.fpsr,
+			  read_buf + SVE_PT_SVE_FPSR_OFFSET(vq), &errors);
+		check_u32(vl, "FPCR", &write_fpsimd.fpcr,
+			  read_buf + SVE_PT_SVE_FPCR_OFFSET(vq), &errors);
+		break;
+	default:
+		ksft_print_msg("Unexpected regs type %d\n",
+			       read_sve->flags & SVE_PT_REGS_MASK);
+		errors++;
+		break;
+	}
+
+	ksft_test_result(errors == 0, "Set FPSIMD, read via SVE for %s VL %u\n",
+			 type->name, vl);
+
+out:
+	free(read_buf);
+}
+
 static int do_parent(pid_t child)
 {
 	int ret = EXIT_FAILURE;
@@ -548,11 +672,9 @@ static int do_parent(pid_t child)
 		if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) {
 			ptrace_sve_fpsimd(child, &vec_types[i]);
 		} else {
-			ksft_test_result_skip("%s FPSIMD get via SVE\n",
-					      vec_types[i].name);
 			ksft_test_result_skip("%s FPSIMD set via SVE\n",
 					      vec_types[i].name);
-			ksft_test_result_skip("%s set read via FPSIMD\n",
+			ksft_test_result_skip("%s FPSIMD read\n",
 					      vec_types[i].name);
 		}
 
@@ -585,11 +707,14 @@ static int do_parent(pid_t child)
 			if (vl_supported) {
 				ptrace_set_sve_get_sve_data(child, &vec_types[i], vl);
 				ptrace_set_sve_get_fpsimd_data(child, &vec_types[i], vl);
+				ptrace_set_fpsimd_get_sve_data(child, &vec_types[i], vl);
 			} else {
 				ksft_test_result_skip("%s set SVE get SVE for VL %d\n",
 						      vec_types[i].name, vl);
 				ksft_test_result_skip("%s set SVE get FPSIMD for VL %d\n",
 						      vec_types[i].name, vl);
+				ksft_test_result_skip("%s set FPSIMD get SVE for VL %d\n",
+						      vec_types[i].name, vl);
 			}
 		}
 	}
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index f5b1b48ffff2..589264231a2d 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -13,6 +13,7 @@
 #include <asm/unistd.h>
 #include "assembler.h"
 #include "asm-offsets.h"
+#include "sme-inst.h"
 
 #define NZR	32
 #define NPR	16
@@ -156,6 +157,7 @@ endfunction
 // We fill the upper lanes of FFR with zeros.
 // Beware: corrupts P0.
 function setup_ffr
+#ifndef SSVE
 	mov	x4, x30
 
 	and	w0, w0, #0x3
@@ -178,6 +180,9 @@ function setup_ffr
 	wrffr	p0.b
 
 	ret	x4
+#else
+	ret
+#endif
 endfunction
 
 // Trivial memory compare: compare x2 bytes starting at address x0 with
@@ -260,6 +265,7 @@ endfunction
 // Beware -- corrupts P0.
 // Clobbers x0-x5.
 function check_ffr
+#ifndef SSVE
 	mov	x3, x30
 
 	ldr	x4, =scratch
@@ -280,6 +286,9 @@ function check_ffr
 	mov	x2, x5
 	mov	x30, x3
 	b	memcmp
+#else
+	ret
+#endif
 endfunction
 
 // Any SVE register modified here can cause corruption in the main
@@ -295,10 +304,12 @@ function irritator_handler
 	movi	v0.8b, #1
 	movi	v9.16b, #2
 	movi	v31.8b, #3
+#ifndef SSVE
 	// And P0
 	rdffr	p0.b
 	// And FFR
 	wrffr	p15.b
+#endif
 
 	ret
 endfunction
@@ -359,6 +370,11 @@ endfunction
 .globl _start
 function _start
 _start:
+#ifdef SSVE
+	puts	"Streaming mode "
+	smstart_sm
+#endif
+
 	// Sanity-check and report the vector length
 
 	rdvl	x19, #8
@@ -407,6 +423,10 @@ _start:
 	orr	w2, w2, #SA_NODEFER
 	bl	setsignal
 
+#ifdef SSVE
+	smstart_sm		// syscalls will have exited streaming mode
+#endif
+
 	mov	x22, #0		// generation number, increments per iteration
 .Ltest_loop:
 	rdvl	x0, #8
diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c
index c90658811a83..9bcfcdc34ee9 100644
--- a/tools/testing/selftests/arm64/fp/vec-syscfg.c
+++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c
@@ -51,6 +51,16 @@ static struct vec_data vec_data[] = {
 		.prctl_set = PR_SVE_SET_VL,
 		.default_vl_file = "/proc/sys/abi/sve_default_vector_length",
 	},
+	{
+		.name = "SME",
+		.hwcap_type = AT_HWCAP2,
+		.hwcap = HWCAP2_SME,
+		.rdvl = rdvl_sme,
+		.rdvl_binary = "./rdvl-sme",
+		.prctl_get = PR_SME_GET_VL,
+		.prctl_set = PR_SME_SET_VL,
+		.default_vl_file = "/proc/sys/abi/sme_default_vector_length",
+	},
 };
 
 static int stdio_read_integer(FILE *f, const char *what, int *val)
diff --git a/tools/testing/selftests/arm64/fp/vlset.c b/tools/testing/selftests/arm64/fp/vlset.c
index 308d27a68226..76912a581a95 100644
--- a/tools/testing/selftests/arm64/fp/vlset.c
+++ b/tools/testing/selftests/arm64/fp/vlset.c
@@ -22,12 +22,15 @@ static int inherit = 0;
 static int no_inherit = 0;
 static int force = 0;
 static unsigned long vl;
+static int set_ctl = PR_SVE_SET_VL;
+static int get_ctl = PR_SVE_GET_VL;
 
 static const struct option options[] = {
 	{ "force",	no_argument, NULL, 'f' },
 	{ "inherit",	no_argument, NULL, 'i' },
 	{ "max",	no_argument, NULL, 'M' },
 	{ "no-inherit",	no_argument, &no_inherit, 1 },
+	{ "sme",	no_argument, NULL, 's' },
 	{ "help",	no_argument, NULL, '?' },
 	{}
 };
@@ -50,6 +53,9 @@ static int parse_options(int argc, char **argv)
 		case 'M':	vl = SVE_VL_MAX; break;
 		case 'f':	force = 1; break;
 		case 'i':	inherit = 1; break;
+		case 's':	set_ctl = PR_SME_SET_VL;
+				get_ctl = PR_SME_GET_VL;
+				break;
 		case 0:		break;
 		default:	goto error;
 		}
@@ -125,14 +131,14 @@ int main(int argc, char **argv)
 	if (inherit)
 		flags |= PR_SVE_VL_INHERIT;
 
-	t = prctl(PR_SVE_SET_VL, vl | flags);
+	t = prctl(set_ctl, vl | flags);
 	if (t < 0) {
 		fprintf(stderr, "%s: PR_SVE_SET_VL: %s\n",
 			program_name, strerror(errno));
 		goto error;
 	}
 
-	t = prctl(PR_SVE_GET_VL);
+	t = prctl(get_ctl);
 	if (t == -1) {
 		fprintf(stderr, "%s: PR_SVE_GET_VL: %s\n",
 			program_name, strerror(errno));
diff --git a/tools/testing/selftests/arm64/fp/za-fork-asm.S b/tools/testing/selftests/arm64/fp/za-fork-asm.S
new file mode 100644
index 000000000000..2fafadd491c3
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-fork-asm.S
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+
+#include "sme-inst.h"
+
+.arch_extension sve
+
+#define MAGIC     42
+
+#define MAXVL     2048
+#define MAXVL_B   (MAXVL / 8)
+
+.pushsection .text
+.data
+.align 4
+scratch:
+	.space	MAXVL_B
+.popsection
+
+.globl fork_test
+fork_test:
+	smstart_za
+
+	// For simplicity just set one word in one vector, other tests
+	// cover general data corruption issues.
+	ldr	x0, =scratch
+	mov	x1, #MAGIC
+	str	x1, [x0]
+	mov	w12, wzr
+	_ldr_za 12, 0			// ZA.H[W12] loaded from [X0]
+
+	// Tail call into the C portion that does the fork & verify
+	b	fork_test_c
+
+.globl verify_fork
+verify_fork:
+	// SVCR should have ZA=1, SM=0
+	mrs	x0, S3_3_C4_C2_2
+	and	x1, x0, #3
+	cmp	x1, #2
+	beq	1f
+	mov	x0, xzr
+	b	100f
+1:
+
+	// ZA should still have the value we loaded
+	ldr	x0, =scratch
+	mov	w12, wzr
+	_str_za 12, 0			// ZA.H[W12] stored to [X0]
+	ldr	x1, [x0]
+	cmp	x1, #MAGIC
+	beq	2f
+	mov	x0, xzr
+	b	100f
+
+2:
+	// All tests passed
+	mov	x0, #1
+100:
+	ret
+
diff --git a/tools/testing/selftests/arm64/fp/za-fork.c b/tools/testing/selftests/arm64/fp/za-fork.c
new file mode 100644
index 000000000000..ff475c649e96
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-fork.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 ARM Limited.
+ * Original author: Mark Brown <broonie@kernel.org>
+ */
+
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/sched.h>
+#include <linux/wait.h>
+
+#define EXPECTED_TESTS 1
+
+static void putstr(const char *str)
+{
+	write(1, str, strlen(str));
+}
+
+static void putnum(unsigned int num)
+{
+	char c;
+
+	if (num / 10)
+		putnum(num / 10);
+
+	c = '0' + (num % 10);
+	write(1, &c, 1);
+}
+
+static int tests_run;
+static int tests_passed;
+static int tests_failed;
+static int tests_skipped;
+
+static void print_summary(void)
+{
+	if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS)
+		putstr("# UNEXPECTED TEST COUNT: ");
+
+	putstr("# Totals: pass:");
+	putnum(tests_passed);
+	putstr(" fail:");
+	putnum(tests_failed);
+	putstr(" xfail:0 xpass:0 skip:");
+	putnum(tests_skipped);
+	putstr(" error:0\n");
+}
+
+int fork_test(void);
+int verify_fork(void);
+
+/*
+ * If we fork the value in the parent should be unchanged and the
+ * child should start with the same value.  This is called from the
+ * fork_test() asm function.
+ */
+int fork_test_c(void)
+{
+	pid_t newpid, waiting;
+	int child_status, parent_result;
+
+	newpid = fork();
+	if (newpid == 0) {
+		/* In child */
+		if (!verify_fork()) {
+			putstr("# ZA state invalid in child\n");
+			exit(0);
+		} else {
+			exit(1);
+		}
+	}
+	if (newpid < 0) {
+		putstr("# fork() failed: -");
+		putnum(-newpid);
+		putstr("\n");
+		return 0;
+	}
+
+	parent_result = verify_fork();
+	if (!parent_result)
+		putstr("# ZA state invalid in parent\n");
+
+	for (;;) {
+		waiting = waitpid(newpid, &child_status, 0);
+
+		if (waiting < 0) {
+			if (errno == EINTR)
+				continue;
+			putstr("# waitpid() failed: ");
+			putnum(errno);
+			putstr("\n");
+			return 0;
+		}
+		if (waiting != newpid) {
+			putstr("# waitpid() returned wrong PID\n");
+			return 0;
+		}
+
+		if (!WIFEXITED(child_status)) {
+			putstr("# child did not exit\n");
+			return 0;
+		}
+
+		return WEXITSTATUS(child_status) && parent_result;
+	}
+}
+
+#define run_test(name)			     \
+	if (name()) {			     \
+		tests_passed++;		     \
+	} else {			     \
+		tests_failed++;		     \
+		putstr("not ");		     \
+	}				     \
+	putstr("ok ");			     \
+	putnum(++tests_run);		     \
+	putstr(" " #name "\n");
+
+int main(int argc, char **argv)
+{
+	int ret, i;
+
+	putstr("TAP version 13\n");
+	putstr("1..");
+	putnum(EXPECTED_TESTS);
+	putstr("\n");
+
+	putstr("# PID: ");
+	putnum(getpid());
+	putstr("\n");
+
+	/*
+	 * This test is run with nolibc which doesn't support hwcap and
+	 * it's probably disproportionate to implement so instead check
+	 * for the default vector length configuration in /proc.
+	 */
+	ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0);
+	if (ret >= 0) {
+		run_test(fork_test);
+
+	} else {
+		putstr("# SME support not present\n");
+
+		for (i = 0; i < EXPECTED_TESTS; i++) {
+			putstr("ok ");
+			putnum(i);
+			putstr(" skipped\n");
+		}
+
+		tests_skipped += EXPECTED_TESTS;
+	}
+
+	print_summary();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/fp/za-ptrace.c b/tools/testing/selftests/arm64/fp/za-ptrace.c
new file mode 100644
index 000000000000..bf6158654056
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-ptrace.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 ARM Limited.
+ */
+#include <errno.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+#include <asm/sigcontext.h>
+#include <asm/ptrace.h>
+
+#include "../../kselftest.h"
+
+/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
+#ifndef NT_ARM_ZA
+#define NT_ARM_ZA 0x40c
+#endif
+
+#define EXPECTED_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
+
+static void fill_buf(char *buf, size_t size)
+{
+	int i;
+
+	for (i = 0; i < size; i++)
+		buf[i] = random();
+}
+
+static int do_child(void)
+{
+	if (ptrace(PTRACE_TRACEME, -1, NULL, NULL))
+		ksft_exit_fail_msg("PTRACE_TRACEME", strerror(errno));
+
+	if (raise(SIGSTOP))
+		ksft_exit_fail_msg("raise(SIGSTOP)", strerror(errno));
+
+	return EXIT_SUCCESS;
+}
+
+static struct user_za_header *get_za(pid_t pid, void **buf, size_t *size)
+{
+	struct user_za_header *za;
+	void *p;
+	size_t sz = sizeof(*za);
+	struct iovec iov;
+
+	while (1) {
+		if (*size < sz) {
+			p = realloc(*buf, sz);
+			if (!p) {
+				errno = ENOMEM;
+				goto error;
+			}
+
+			*buf = p;
+			*size = sz;
+		}
+
+		iov.iov_base = *buf;
+		iov.iov_len = sz;
+		if (ptrace(PTRACE_GETREGSET, pid, NT_ARM_ZA, &iov))
+			goto error;
+
+		za = *buf;
+		if (za->size <= sz)
+			break;
+
+		sz = za->size;
+	}
+
+	return za;
+
+error:
+	return NULL;
+}
+
+static int set_za(pid_t pid, const struct user_za_header *za)
+{
+	struct iovec iov;
+
+	iov.iov_base = (void *)za;
+	iov.iov_len = za->size;
+	return ptrace(PTRACE_SETREGSET, pid, NT_ARM_ZA, &iov);
+}
+
+/* Validate attempting to set the specfied VL via ptrace */
+static void ptrace_set_get_vl(pid_t child, unsigned int vl, bool *supported)
+{
+	struct user_za_header za;
+	struct user_za_header *new_za = NULL;
+	size_t new_za_size = 0;
+	int ret, prctl_vl;
+
+	*supported = false;
+
+	/* Check if the VL is supported in this process */
+	prctl_vl = prctl(PR_SME_SET_VL, vl);
+	if (prctl_vl == -1)
+		ksft_exit_fail_msg("prctl(PR_SME_SET_VL) failed: %s (%d)\n",
+				   strerror(errno), errno);
+
+	/* If the VL is not supported then a supported VL will be returned */
+	*supported = (prctl_vl == vl);
+
+	/* Set the VL by doing a set with no register payload */
+	memset(&za, 0, sizeof(za));
+	za.size = sizeof(za);
+	za.vl = vl;
+	ret = set_za(child, &za);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set VL %u\n", vl);
+		return;
+	}
+
+	/*
+	 * Read back the new register state and verify that we have the
+	 * same VL that we got from prctl() on ourselves.
+	 */
+	if (!get_za(child, (void **)&new_za, &new_za_size)) {
+		ksft_test_result_fail("Failed to read VL %u\n", vl);
+		return;
+	}
+
+	ksft_test_result(new_za->vl = prctl_vl, "Set VL %u\n", vl);
+
+	free(new_za);
+}
+
+/* Validate attempting to set no ZA data and read it back */
+static void ptrace_set_no_data(pid_t child, unsigned int vl)
+{
+	void *read_buf = NULL;
+	struct user_za_header write_za;
+	struct user_za_header *read_za;
+	size_t read_za_size = 0;
+	int ret;
+
+	/* Set up some data and write it out */
+	memset(&write_za, 0, sizeof(write_za));
+	write_za.size = ZA_PT_ZA_OFFSET;
+	write_za.vl = vl;
+
+	ret = set_za(child, &write_za);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set VL %u no data\n", vl);
+		return;
+	}
+
+	/* Read the data back */
+	if (!get_za(child, (void **)&read_buf, &read_za_size)) {
+		ksft_test_result_fail("Failed to read VL %u no data\n", vl);
+		return;
+	}
+	read_za = read_buf;
+
+	/* We might read more data if there's extensions we don't know */
+	if (read_za->size < write_za.size) {
+		ksft_test_result_fail("VL %u wrote %d bytes, only read %d\n",
+				      vl, write_za.size, read_za->size);
+		goto out_read;
+	}
+
+	ksft_test_result(read_za->size == write_za.size,
+			 "Disabled ZA for VL %u\n", vl);
+
+out_read:
+	free(read_buf);
+}
+
+/* Validate attempting to set data and read it back */
+static void ptrace_set_get_data(pid_t child, unsigned int vl)
+{
+	void *write_buf;
+	void *read_buf = NULL;
+	struct user_za_header *write_za;
+	struct user_za_header *read_za;
+	size_t read_za_size = 0;
+	unsigned int vq = sve_vq_from_vl(vl);
+	int ret;
+	size_t data_size;
+
+	data_size = ZA_PT_SIZE(vq);
+	write_buf = malloc(data_size);
+	if (!write_buf) {
+		ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n",
+				      data_size, vl);
+		return;
+	}
+	write_za = write_buf;
+
+	/* Set up some data and write it out */
+	memset(write_za, 0, data_size);
+	write_za->size = data_size;
+	write_za->vl = vl;
+
+	fill_buf(write_buf + ZA_PT_ZA_OFFSET, ZA_PT_ZA_SIZE(vq));
+
+	ret = set_za(child, write_za);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set VL %u data\n", vl);
+		goto out;
+	}
+
+	/* Read the data back */
+	if (!get_za(child, (void **)&read_buf, &read_za_size)) {
+		ksft_test_result_fail("Failed to read VL %u data\n", vl);
+		goto out;
+	}
+	read_za = read_buf;
+
+	/* We might read more data if there's extensions we don't know */
+	if (read_za->size < write_za->size) {
+		ksft_test_result_fail("VL %u wrote %d bytes, only read %d\n",
+				      vl, write_za->size, read_za->size);
+		goto out_read;
+	}
+
+	ksft_test_result(memcmp(write_buf + ZA_PT_ZA_OFFSET,
+				read_buf + ZA_PT_ZA_OFFSET,
+				ZA_PT_ZA_SIZE(vq)) == 0,
+			 "Data match for VL %u\n", vl);
+
+out_read:
+	free(read_buf);
+out:
+	free(write_buf);
+}
+
+static int do_parent(pid_t child)
+{
+	int ret = EXIT_FAILURE;
+	pid_t pid;
+	int status;
+	siginfo_t si;
+	unsigned int vq, vl;
+	bool vl_supported;
+
+	/* Attach to the child */
+	while (1) {
+		int sig;
+
+		pid = wait(&status);
+		if (pid == -1) {
+			perror("wait");
+			goto error;
+		}
+
+		/*
+		 * This should never happen but it's hard to flag in
+		 * the framework.
+		 */
+		if (pid != child)
+			continue;
+
+		if (WIFEXITED(status) || WIFSIGNALED(status))
+			ksft_exit_fail_msg("Child died unexpectedly\n");
+
+		if (!WIFSTOPPED(status))
+			goto error;
+
+		sig = WSTOPSIG(status);
+
+		if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &si)) {
+			if (errno == ESRCH)
+				goto disappeared;
+
+			if (errno == EINVAL) {
+				sig = 0; /* bust group-stop */
+				goto cont;
+			}
+
+			ksft_test_result_fail("PTRACE_GETSIGINFO: %s\n",
+					      strerror(errno));
+			goto error;
+		}
+
+		if (sig == SIGSTOP && si.si_code == SI_TKILL &&
+		    si.si_pid == pid)
+			break;
+
+	cont:
+		if (ptrace(PTRACE_CONT, pid, NULL, sig)) {
+			if (errno == ESRCH)
+				goto disappeared;
+
+			ksft_test_result_fail("PTRACE_CONT: %s\n",
+					      strerror(errno));
+			goto error;
+		}
+	}
+
+	ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
+
+	/* Step through every possible VQ */
+	for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
+		vl = sve_vl_from_vq(vq);
+
+		/* First, try to set this vector length */
+		ptrace_set_get_vl(child, vl, &vl_supported);
+
+		/* If the VL is supported validate data set/get */
+		if (vl_supported) {
+			ptrace_set_no_data(child, vl);
+			ptrace_set_get_data(child, vl);
+		} else {
+			ksft_test_result_skip("Disabled ZA for VL %u\n", vl);
+			ksft_test_result_skip("Get and set data for VL %u\n",
+					      vl);
+		}
+	}
+
+	ret = EXIT_SUCCESS;
+
+error:
+	kill(child, SIGKILL);
+
+disappeared:
+	return ret;
+}
+
+int main(void)
+{
+	int ret = EXIT_SUCCESS;
+	pid_t child;
+
+	srandom(getpid());
+
+	ksft_print_header();
+
+	if (!(getauxval(AT_HWCAP2) & HWCAP2_SME)) {
+		ksft_set_plan(1);
+		ksft_exit_skip("SME not available\n");
+	}
+
+	ksft_set_plan(EXPECTED_TESTS);
+
+	child = fork();
+	if (!child)
+		return do_child();
+
+	if (do_parent(child))
+		ret = EXIT_FAILURE;
+
+	ksft_print_cnts();
+
+	return ret;
+}
diff --git a/tools/testing/selftests/arm64/fp/za-stress b/tools/testing/selftests/arm64/fp/za-stress
new file mode 100644
index 000000000000..5ac386b55b95
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-stress
@@ -0,0 +1,59 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2015-2019 ARM Limited.
+# Original author: Dave Martin <Dave.Martin@arm.com>
+
+set -ue
+
+NR_CPUS=`nproc`
+
+pids=
+logs=
+
+cleanup () {
+	trap - INT TERM CHLD
+	set +e
+
+	if [ -n "$pids" ]; then
+		kill $pids
+		wait $pids
+		pids=
+	fi
+
+	if [ -n "$logs" ]; then
+		cat $logs
+		rm $logs
+		logs=
+	fi
+}
+
+interrupt () {
+	cleanup
+	exit 0
+}
+
+child_died () {
+	cleanup
+	exit 1
+}
+
+trap interrupt INT TERM EXIT
+
+for x in `seq 0 $((NR_CPUS * 4))`; do
+	log=`mktemp`
+	logs=$logs\ $log
+	./za-test >$log &
+	pids=$pids\ $!
+done
+
+# Wait for all child processes to be created:
+sleep 10
+
+while :; do
+	kill -USR1 $pids
+done &
+pids=$pids\ $!
+
+wait
+
+exit 1
diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S
new file mode 100644
index 000000000000..9ab6f9cd9623
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-test.S
@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+//
+// Scalable Matrix Extension ZA context switch test
+// Repeatedly writes unique test patterns into each ZA tile
+// and reads them back to verify integrity.
+//
+// for x in `seq 1 NR_CPUS`; do sve-test & pids=$pids\ $! ; done
+// (leave it running for as long as you want...)
+// kill $pids
+
+#include <asm/unistd.h>
+#include "assembler.h"
+#include "asm-offsets.h"
+#include "sme-inst.h"
+
+.arch_extension sve
+
+#define MAXVL     2048
+#define MAXVL_B   (MAXVL / 8)
+
+// Declare some storage space to shadow ZA register contents and a
+// scratch buffer for a vector.
+.pushsection .text
+.data
+.align 4
+zaref:
+	.space	MAXVL_B * MAXVL_B
+scratch:
+	.space	MAXVL_B
+.popsection
+
+// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0.
+// Clobbers x0-x3
+function memcpy
+	cmp	x2, #0
+	b.eq	1f
+0:	ldrb	w3, [x1], #1
+	strb	w3, [x0], #1
+	subs	x2, x2, #1
+	b.ne	0b
+1:	ret
+endfunction
+
+// Generate a test pattern for storage in ZA
+// x0: pid
+// x1: row in ZA
+// x2: generation
+
+// These values are used to constuct a 32-bit pattern that is repeated in the
+// scratch buffer as many times as will fit:
+// bits 31:28	generation number (increments once per test_loop)
+// bits 27:16	pid
+// bits 15: 8	row number
+// bits  7: 0	32-bit lane index
+
+function pattern
+	mov	w3, wzr
+	bfi	w3, w0, #16, #12	// PID
+	bfi	w3, w1, #8, #8		// Row
+	bfi	w3, w2, #28, #4		// Generation
+
+	ldr	x0, =scratch
+	mov	w1, #MAXVL_B / 4
+
+0:	str	w3, [x0], #4
+	add	w3, w3, #1		// Lane
+	subs	w1, w1, #1
+	b.ne	0b
+
+	ret
+endfunction
+
+// Get the address of shadow data for ZA horizontal vector xn
+.macro _adrza xd, xn, nrtmp
+	ldr	\xd, =zaref
+	rdsvl	\nrtmp, 1
+	madd	\xd, x\nrtmp, \xn, \xd
+.endm
+
+// Set up test pattern in a ZA horizontal vector
+// x0: pid
+// x1: row number
+// x2: generation
+function setup_za
+	mov	x4, x30
+	mov	x12, x1			// Use x12 for vector select
+
+	bl	pattern			// Get pattern in scratch buffer
+	_adrza	x0, x12, 2		// Shadow buffer pointer to x0 and x5
+	mov	x5, x0
+	ldr	x1, =scratch
+	bl	memcpy			// length set up in x2 by _adrza
+
+	_ldr_za 12, 5			// load vector w12 from pointer x5
+
+	ret	x4
+endfunction
+
+// Trivial memory compare: compare x2 bytes starting at address x0 with
+// bytes starting at address x1.
+// Returns only if all bytes match; otherwise, the program is aborted.
+// Clobbers x0-x5.
+function memcmp
+	cbz	x2, 2f
+
+	stp	x0, x1, [sp, #-0x20]!
+	str	x2, [sp, #0x10]
+
+	mov	x5, #0
+0:	ldrb	w3, [x0, x5]
+	ldrb	w4, [x1, x5]
+	add	x5, x5, #1
+	cmp	w3, w4
+	b.ne	1f
+	subs	x2, x2, #1
+	b.ne	0b
+
+1:	ldr	x2, [sp, #0x10]
+	ldp	x0, x1, [sp], #0x20
+	b.ne	barf
+
+2:	ret
+endfunction
+
+// Verify that a ZA vector matches its shadow in memory, else abort
+// x0: row number
+// Clobbers x0-x7 and x12.
+function check_za
+	mov	x3, x30
+
+	mov	x12, x0
+	_adrza	x5, x0, 6		// pointer to expected value in x5
+	mov	x4, x0
+	ldr	x7, =scratch		// x7 is scratch
+
+	mov	x0, x7			// Poison scratch
+	mov	x1, x6
+	bl	memfill_ae
+
+	_str_za 12, 7			// save vector w12 to pointer x7
+
+	mov	x0, x5
+	mov	x1, x7
+	mov	x2, x6
+	mov	x30, x3
+	b	memcmp
+endfunction
+
+// Any SME register modified here can cause corruption in the main
+// thread -- but *only* the locations modified here.
+function irritator_handler
+	// Increment the irritation signal count (x23):
+	ldr	x0, [x2, #ucontext_regs + 8 * 23]
+	add	x0, x0, #1
+	str	x0, [x2, #ucontext_regs + 8 * 23]
+
+	// Corrupt some random ZA data
+#if 0
+	adr	x0, .text + (irritator_handler - .text) / 16 * 16
+	movi	v0.8b, #1
+	movi	v9.16b, #2
+	movi	v31.8b, #3
+#endif
+
+	ret
+endfunction
+
+function terminate_handler
+	mov	w21, w0
+	mov	x20, x2
+
+	puts	"Terminated by signal "
+	mov	w0, w21
+	bl	putdec
+	puts	", no error, iterations="
+	ldr	x0, [x20, #ucontext_regs + 8 * 22]
+	bl	putdec
+	puts	", signals="
+	ldr	x0, [x20, #ucontext_regs + 8 * 23]
+	bl	putdecn
+
+	mov	x0, #0
+	mov	x8, #__NR_exit
+	svc	#0
+endfunction
+
+// w0: signal number
+// x1: sa_action
+// w2: sa_flags
+// Clobbers x0-x6,x8
+function setsignal
+	str	x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]!
+
+	mov	w4, w0
+	mov	x5, x1
+	mov	w6, w2
+
+	add	x0, sp, #16
+	mov	x1, #sa_sz
+	bl	memclr
+
+	mov	w0, w4
+	add	x1, sp, #16
+	str	w6, [x1, #sa_flags]
+	str	x5, [x1, #sa_handler]
+	mov	x2, #0
+	mov	x3, #sa_mask_sz
+	mov	x8, #__NR_rt_sigaction
+	svc	#0
+
+	cbz	w0, 1f
+
+	puts	"sigaction failure\n"
+	b	.Labort
+
+1:	ldr	x30, [sp], #((sa_sz + 15) / 16 * 16 + 16)
+	ret
+endfunction
+
+// Main program entry point
+.globl _start
+function _start
+_start:
+	puts	"Streaming mode "
+	smstart_za
+
+	// Sanity-check and report the vector length
+
+	rdsvl	19, 8
+	cmp	x19, #128
+	b.lo	1f
+	cmp	x19, #2048
+	b.hi	1f
+	tst	x19, #(8 - 1)
+	b.eq	2f
+
+1:	puts	"bad vector length: "
+	mov	x0, x19
+	bl	putdecn
+	b	.Labort
+
+2:	puts	"vector length:\t"
+	mov	x0, x19
+	bl	putdec
+	puts	" bits\n"
+
+	// Obtain our PID, to ensure test pattern uniqueness between processes
+	mov	x8, #__NR_getpid
+	svc	#0
+	mov	x20, x0
+
+	puts	"PID:\t"
+	mov	x0, x20
+	bl	putdecn
+
+	mov	x23, #0		// Irritation signal count
+
+	mov	w0, #SIGINT
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGTERM
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGUSR1
+	adr	x1, irritator_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	mov	x22, #0		// generation number, increments per iteration
+.Ltest_loop:
+	rdsvl	0, 8
+	cmp	x0, x19
+	b.ne	vl_barf
+
+	rdsvl	21, 1		// Set up ZA & shadow with test pattern
+0:	mov	x0, x20
+	sub	x1, x21, #1
+	mov	x2, x22
+	bl	setup_za
+	subs	x21, x21, #1
+	b.ne	0b
+
+	and	x8, x22, #127		// Every 128 interations...
+	cbz	x8, 0f
+	mov	x8, #__NR_getpid	// (otherwise minimal syscall)
+	b	1f
+0:
+	mov	x8, #__NR_sched_yield	// ...encourage preemption
+1:
+	svc	#0
+
+	mrs	x0, S3_3_C4_C2_2	// SVCR should have ZA=1,SM=0
+	and	x1, x0, #3
+	cmp	x1, #2
+	b.ne	svcr_barf
+
+	rdsvl	21, 1			// Verify that the data made it through
+	rdsvl	24, 1			// Verify that the data made it through
+0:	sub	x0, x24, x21
+	bl	check_za
+	subs	x21, x21, #1
+	bne	0b
+
+	add	x22, x22, #1	// Everything still working
+	b	.Ltest_loop
+
+.Labort:
+	mov	x0, #0
+	mov	x1, #SIGABRT
+	mov	x8, #__NR_kill
+	svc	#0
+endfunction
+
+function barf
+// fpsimd.c acitivty log dump hack
+//	ldr	w0, =0xdeadc0de
+//	mov	w8, #__NR_exit
+//	svc	#0
+// end hack
+	smstop
+	mov	x10, x0	// expected data
+	mov	x11, x1	// actual data
+	mov	x12, x2	// data size
+
+	puts	"Mismatch: PID="
+	mov	x0, x20
+	bl	putdec
+	puts	", iteration="
+	mov	x0, x22
+	bl	putdec
+	puts	", row="
+	mov	x0, x21
+	bl	putdecn
+	puts	"\tExpected ["
+	mov	x0, x10
+	mov	x1, x12
+	bl	dumphex
+	puts	"]\n\tGot      ["
+	mov	x0, x11
+	mov	x1, x12
+	bl	dumphex
+	puts	"]\n"
+
+	mov	x8, #__NR_getpid
+	svc	#0
+// fpsimd.c acitivty log dump hack
+//	ldr	w0, =0xdeadc0de
+//	mov	w8, #__NR_exit
+//	svc	#0
+// ^ end of hack
+	mov	x1, #SIGABRT
+	mov	x8, #__NR_kill
+	svc	#0
+//	mov	x8, #__NR_exit
+//	mov	x1, #1
+//	svc	#0
+endfunction
+
+function vl_barf
+	mov	x10, x0
+
+	puts	"Bad active VL: "
+	mov	x0, x10
+	bl	putdecn
+
+	mov	x8, #__NR_exit
+	mov	x1, #1
+	svc	#0
+endfunction
+
+function svcr_barf
+	mov	x10, x0
+
+	puts	"Bad SVCR: "
+	mov	x0, x10
+	bl	putdecn
+
+	mov	x8, #__NR_exit
+	mov	x1, #1
+	svc	#0
+endfunction
diff --git a/tools/testing/selftests/arm64/mte/.gitignore b/tools/testing/selftests/arm64/mte/.gitignore
index d1fe4ddf1669..052d0f9f92b3 100644
--- a/tools/testing/selftests/arm64/mte/.gitignore
+++ b/tools/testing/selftests/arm64/mte/.gitignore
@@ -3,5 +3,6 @@ check_gcr_el1_cswitch
 check_tags_inclusion
 check_child_memory
 check_mmap_options
+check_prctl
 check_ksm_options
 check_user_mem
diff --git a/tools/testing/selftests/arm64/mte/check_child_memory.c b/tools/testing/selftests/arm64/mte/check_child_memory.c
index 43bd94f853ba..7597fc632cad 100644
--- a/tools/testing/selftests/arm64/mte/check_child_memory.c
+++ b/tools/testing/selftests/arm64/mte/check_child_memory.c
@@ -85,9 +85,9 @@ static int check_child_memory_mapping(int mem_type, int mode, int mapping)
 {
 	char *ptr;
 	int run, result;
-	int item = sizeof(sizes)/sizeof(int);
+	int item = ARRAY_SIZE(sizes);
 
-	item = sizeof(sizes)/sizeof(int);
+	item = ARRAY_SIZE(sizes);
 	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
 	for (run = 0; run < item; run++) {
 		ptr = (char *)mte_allocate_memory_tag_range(sizes[run], mem_type, mapping,
@@ -107,7 +107,7 @@ static int check_child_file_mapping(int mem_type, int mode, int mapping)
 {
 	char *ptr, *map_ptr;
 	int run, fd, map_size, result = KSFT_PASS;
-	int total = sizeof(sizes)/sizeof(int);
+	int total = ARRAY_SIZE(sizes);
 
 	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
 	for (run = 0; run < total; run++) {
@@ -144,7 +144,7 @@ static int check_child_file_mapping(int mem_type, int mode, int mapping)
 int main(int argc, char *argv[])
 {
 	int err;
-	int item = sizeof(sizes)/sizeof(int);
+	int item = ARRAY_SIZE(sizes);
 
 	page_size = getpagesize();
 	if (!page_size) {
diff --git a/tools/testing/selftests/arm64/mte/check_prctl.c b/tools/testing/selftests/arm64/mte/check_prctl.c
new file mode 100644
index 000000000000..f139a33a43ef
--- /dev/null
+++ b/tools/testing/selftests/arm64/mte/check_prctl.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2022 ARM Limited
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+
+#include <asm/hwcap.h>
+
+#include "kselftest.h"
+
+static int set_tagged_addr_ctrl(int val)
+{
+	int ret;
+
+	ret = prctl(PR_SET_TAGGED_ADDR_CTRL, val, 0, 0, 0);
+	if (ret < 0)
+		ksft_print_msg("PR_SET_TAGGED_ADDR_CTRL: failed %d %d (%s)\n",
+			       ret, errno, strerror(errno));
+	return ret;
+}
+
+static int get_tagged_addr_ctrl(void)
+{
+	int ret;
+
+	ret = prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0);
+	if (ret < 0)
+		ksft_print_msg("PR_GET_TAGGED_ADDR_CTRL failed: %d %d (%s)\n",
+			       ret, errno, strerror(errno));
+	return ret;
+}
+
+/*
+ * Read the current mode without having done any configuration, should
+ * run first.
+ */
+void check_basic_read(void)
+{
+	int ret;
+
+	ret = get_tagged_addr_ctrl();
+	if (ret < 0) {
+		ksft_test_result_fail("check_basic_read\n");
+		return;
+	}
+
+	if (ret & PR_MTE_TCF_SYNC)
+		ksft_print_msg("SYNC enabled\n");
+	if (ret & PR_MTE_TCF_ASYNC)
+		ksft_print_msg("ASYNC enabled\n");
+
+	/* Any configuration is valid */
+	ksft_test_result_pass("check_basic_read\n");
+}
+
+/*
+ * Attempt to set a specified combination of modes.
+ */
+void set_mode_test(const char *name, int hwcap2, int mask)
+{
+	int ret;
+
+	if ((getauxval(AT_HWCAP2) & hwcap2) != hwcap2) {
+		ksft_test_result_skip("%s\n", name);
+		return;
+	}
+
+	ret = set_tagged_addr_ctrl(mask);
+	if (ret < 0) {
+		ksft_test_result_fail("%s\n", name);
+		return;
+	}
+
+	ret = get_tagged_addr_ctrl();
+	if (ret < 0) {
+		ksft_test_result_fail("%s\n", name);
+		return;
+	}
+
+	if ((ret & PR_MTE_TCF_MASK) == mask) {
+		ksft_test_result_pass("%s\n", name);
+	} else {
+		ksft_print_msg("Got %x, expected %x\n",
+			       (ret & PR_MTE_TCF_MASK), mask);
+		ksft_test_result_fail("%s\n", name);
+	}
+}
+
+struct mte_mode {
+	int mask;
+	int hwcap2;
+	const char *name;
+} mte_modes[] = {
+	{ PR_MTE_TCF_NONE,  0,          "NONE"  },
+	{ PR_MTE_TCF_SYNC,  HWCAP2_MTE, "SYNC"  },
+	{ PR_MTE_TCF_ASYNC, HWCAP2_MTE, "ASYNC" },
+	{ PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC,  HWCAP2_MTE, "SYNC+ASYNC"  },
+};
+
+int main(void)
+{
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(5);
+
+	check_basic_read();
+	for (i = 0; i < ARRAY_SIZE(mte_modes); i++)
+		set_mode_test(mte_modes[i].name, mte_modes[i].hwcap2,
+			      mte_modes[i].mask);
+
+	ksft_print_cnts();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
index deaef1f61076..2b1425b92b69 100644
--- a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
+++ b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
@@ -23,10 +23,13 @@ static int verify_mte_pointer_validity(char *ptr, int mode)
 {
 	mte_initialize_current_context(mode, (uintptr_t)ptr, BUFFER_SIZE);
 	/* Check the validity of the tagged pointer */
-	memset((void *)ptr, '1', BUFFER_SIZE);
+	memset(ptr, '1', BUFFER_SIZE);
 	mte_wait_after_trig();
-	if (cur_mte_cxt.fault_valid)
+	if (cur_mte_cxt.fault_valid) {
+		ksft_print_msg("Unexpected fault recorded for %p-%p in mode %x\n",
+			       ptr, ptr + BUFFER_SIZE, mode);
 		return KSFT_FAIL;
+	}
 	/* Proceed further for nonzero tags */
 	if (!MT_FETCH_TAG((uintptr_t)ptr))
 		return KSFT_PASS;
@@ -34,27 +37,32 @@ static int verify_mte_pointer_validity(char *ptr, int mode)
 	/* Check the validity outside the range */
 	ptr[BUFFER_SIZE] = '2';
 	mte_wait_after_trig();
-	if (!cur_mte_cxt.fault_valid)
+	if (!cur_mte_cxt.fault_valid) {
+		ksft_print_msg("No valid fault recorded for %p in mode %x\n",
+			       ptr, mode);
 		return KSFT_FAIL;
-	else
+	} else {
 		return KSFT_PASS;
+	}
 }
 
 static int check_single_included_tags(int mem_type, int mode)
 {
 	char *ptr;
-	int tag, run, result = KSFT_PASS;
+	int tag, run, ret, result = KSFT_PASS;
 
-	ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
+	ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
 	if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE,
 				   mem_type, false) != KSFT_PASS)
 		return KSFT_FAIL;
 
 	for (tag = 0; (tag < MT_TAG_COUNT) && (result == KSFT_PASS); tag++) {
-		mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag));
+		ret = mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag));
+		if (ret != 0)
+			result = KSFT_FAIL;
 		/* Try to catch a excluded tag by a number of tries. */
 		for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) {
-			ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE);
+			ptr = mte_insert_tags(ptr, BUFFER_SIZE);
 			/* Check tag value */
 			if (MT_FETCH_TAG((uintptr_t)ptr) == tag) {
 				ksft_print_msg("FAIL: wrong tag = 0x%x with include mask=0x%x\n",
@@ -66,7 +74,7 @@ static int check_single_included_tags(int mem_type, int mode)
 			result = verify_mte_pointer_validity(ptr, mode);
 		}
 	}
-	mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
+	mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
 	return result;
 }
 
@@ -76,7 +84,7 @@ static int check_multiple_included_tags(int mem_type, int mode)
 	int tag, run, result = KSFT_PASS;
 	unsigned long excl_mask = 0;
 
-	ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
+	ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
 	if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE,
 				   mem_type, false) != KSFT_PASS)
 		return KSFT_FAIL;
@@ -86,7 +94,7 @@ static int check_multiple_included_tags(int mem_type, int mode)
 		mte_switch_mode(mode, MT_INCLUDE_VALID_TAGS(excl_mask));
 		/* Try to catch a excluded tag by a number of tries. */
 		for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) {
-			ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE);
+			ptr = mte_insert_tags(ptr, BUFFER_SIZE);
 			/* Check tag value */
 			if (MT_FETCH_TAG((uintptr_t)ptr) < tag) {
 				ksft_print_msg("FAIL: wrong tag = 0x%x with include mask=0x%x\n",
@@ -98,21 +106,23 @@ static int check_multiple_included_tags(int mem_type, int mode)
 			result = verify_mte_pointer_validity(ptr, mode);
 		}
 	}
-	mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
+	mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
 	return result;
 }
 
 static int check_all_included_tags(int mem_type, int mode)
 {
 	char *ptr;
-	int run, result = KSFT_PASS;
+	int run, ret, result = KSFT_PASS;
 
-	ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
+	ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
 	if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE,
 				   mem_type, false) != KSFT_PASS)
 		return KSFT_FAIL;
 
-	mte_switch_mode(mode, MT_INCLUDE_TAG_MASK);
+	ret = mte_switch_mode(mode, MT_INCLUDE_TAG_MASK);
+	if (ret != 0)
+		return KSFT_FAIL;
 	/* Try to catch a excluded tag by a number of tries. */
 	for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) {
 		ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE);
@@ -122,20 +132,22 @@ static int check_all_included_tags(int mem_type, int mode)
 		 */
 		result = verify_mte_pointer_validity(ptr, mode);
 	}
-	mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
+	mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
 	return result;
 }
 
 static int check_none_included_tags(int mem_type, int mode)
 {
 	char *ptr;
-	int run;
+	int run, ret;
 
-	ptr = (char *)mte_allocate_memory(BUFFER_SIZE, mem_type, 0, false);
+	ptr = mte_allocate_memory(BUFFER_SIZE, mem_type, 0, false);
 	if (check_allocated_memory(ptr, BUFFER_SIZE, mem_type, false) != KSFT_PASS)
 		return KSFT_FAIL;
 
-	mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK);
+	ret = mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK);
+	if (ret != 0)
+		return KSFT_FAIL;
 	/* Try to catch a excluded tag by a number of tries. */
 	for (run = 0; run < RUNS; run++) {
 		ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE);
@@ -147,12 +159,12 @@ static int check_none_included_tags(int mem_type, int mode)
 		}
 		mte_initialize_current_context(mode, (uintptr_t)ptr, BUFFER_SIZE);
 		/* Check the write validity of the untagged pointer */
-		memset((void *)ptr, '1', BUFFER_SIZE);
+		memset(ptr, '1', BUFFER_SIZE);
 		mte_wait_after_trig();
 		if (cur_mte_cxt.fault_valid)
 			break;
 	}
-	mte_free_memory((void *)ptr, BUFFER_SIZE, mem_type, false);
+	mte_free_memory(ptr, BUFFER_SIZE, mem_type, false);
 	if (cur_mte_cxt.fault_valid)
 		return KSFT_FAIL;
 	else
diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.c b/tools/testing/selftests/arm64/mte/mte_common_util.c
index 0328a1e08f65..00ffd34c66d3 100644
--- a/tools/testing/selftests/arm64/mte/mte_common_util.c
+++ b/tools/testing/selftests/arm64/mte/mte_common_util.c
@@ -37,6 +37,10 @@ void mte_default_handler(int signum, siginfo_t *si, void *uc)
 		if (si->si_code == SEGV_MTEAERR) {
 			if (cur_mte_cxt.trig_si_code == si->si_code)
 				cur_mte_cxt.fault_valid = true;
+			else
+				ksft_print_msg("Got unexpected SEGV_MTEAERR at pc=$lx, fault addr=%lx\n",
+					       ((ucontext_t *)uc)->uc_mcontext.pc,
+					       addr);
 			return;
 		}
 		/* Compare the context for precise error */
@@ -124,13 +128,16 @@ static void *__mte_allocate_memory_range(size_t size, int mem_type, int mapping,
 	int prot_flag, map_flag;
 	size_t entire_size = size + range_before + range_after;
 
-	if (mem_type != USE_MALLOC && mem_type != USE_MMAP &&
-	    mem_type != USE_MPROTECT) {
+	switch (mem_type) {
+	case USE_MALLOC:
+		return malloc(entire_size) + range_before;
+	case USE_MMAP:
+	case USE_MPROTECT:
+		break;
+	default:
 		ksft_print_msg("FAIL: Invalid allocate request\n");
 		return NULL;
 	}
-	if (mem_type == USE_MALLOC)
-		return malloc(entire_size) + range_before;
 
 	prot_flag = PROT_READ | PROT_WRITE;
 	if (mem_type == USE_MMAP)
@@ -269,18 +276,33 @@ int mte_switch_mode(int mte_option, unsigned long incl_mask)
 {
 	unsigned long en = 0;
 
-	if (!(mte_option == MTE_SYNC_ERR || mte_option == MTE_ASYNC_ERR ||
-	      mte_option == MTE_NONE_ERR || incl_mask <= MTE_ALLOW_NON_ZERO_TAG)) {
-		ksft_print_msg("FAIL: Invalid mte config option\n");
+	switch (mte_option) {
+	case MTE_NONE_ERR:
+	case MTE_SYNC_ERR:
+	case MTE_ASYNC_ERR:
+		break;
+	default:
+		ksft_print_msg("FAIL: Invalid MTE option %x\n", mte_option);
+		return -EINVAL;
+	}
+
+	if (incl_mask & ~MT_INCLUDE_TAG_MASK) {
+		ksft_print_msg("FAIL: Invalid incl_mask %lx\n", incl_mask);
 		return -EINVAL;
 	}
+
 	en = PR_TAGGED_ADDR_ENABLE;
-	if (mte_option == MTE_SYNC_ERR)
+	switch (mte_option) {
+	case MTE_SYNC_ERR:
 		en |= PR_MTE_TCF_SYNC;
-	else if (mte_option == MTE_ASYNC_ERR)
+		break;
+	case MTE_ASYNC_ERR:
 		en |= PR_MTE_TCF_ASYNC;
-	else if (mte_option == MTE_NONE_ERR)
+		break;
+	case MTE_NONE_ERR:
 		en |= PR_MTE_TCF_NONE;
+		break;
+	}
 
 	en |= (incl_mask << PR_MTE_TAG_SHIFT);
 	/* Enable address tagging ABI, mte error reporting mode and tag inclusion mask. */
diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.h b/tools/testing/selftests/arm64/mte/mte_common_util.h
index 195a7d1879e6..2d3e71724e55 100644
--- a/tools/testing/selftests/arm64/mte/mte_common_util.h
+++ b/tools/testing/selftests/arm64/mte/mte_common_util.h
@@ -75,10 +75,21 @@ unsigned int mte_get_pstate_tco(void);
 /* Test framework static inline functions/macros */
 static inline void evaluate_test(int err, const char *msg)
 {
-	if (err == KSFT_PASS)
+	switch (err) {
+	case KSFT_PASS:
 		ksft_test_result_pass(msg);
-	else if (err == KSFT_FAIL)
+		break;
+	case KSFT_FAIL:
 		ksft_test_result_fail(msg);
+		break;
+	case KSFT_SKIP:
+		ksft_test_result_skip(msg);
+		break;
+	default:
+		ksft_test_result_error("Unknown return code %d from %s",
+				       err, msg);
+		break;
+	}
 }
 
 static inline int check_allocated_memory(void *ptr, size_t size,
diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore
index c1742755abb9..e8d2b57f73ec 100644
--- a/tools/testing/selftests/arm64/signal/.gitignore
+++ b/tools/testing/selftests/arm64/signal/.gitignore
@@ -1,5 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 mangle_*
 fake_sigreturn_*
+sme_*
+ssve_*
 sve_*
+za_*
 !*.[ch]
diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h
index f909b70d9e98..c70fdec7d7c4 100644
--- a/tools/testing/selftests/arm64/signal/test_signals.h
+++ b/tools/testing/selftests/arm64/signal/test_signals.h
@@ -34,11 +34,15 @@
 enum {
 	FSSBS_BIT,
 	FSVE_BIT,
+	FSME_BIT,
+	FSME_FA64_BIT,
 	FMAX_END
 };
 
 #define FEAT_SSBS		(1UL << FSSBS_BIT)
 #define FEAT_SVE		(1UL << FSVE_BIT)
+#define FEAT_SME		(1UL << FSME_BIT)
+#define FEAT_SME_FA64		(1UL << FSME_FA64_BIT)
 
 /*
  * A descriptor used to describe and configure a test case.
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c
index 5743897984b0..b588d10afd5b 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.c
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c
@@ -27,6 +27,8 @@ static int sig_copyctx = SIGTRAP;
 static char const *const feats_names[FMAX_END] = {
 	" SSBS ",
 	" SVE ",
+	" SME ",
+	" FA64 ",
 };
 
 #define MAX_FEATS_SZ	128
@@ -268,6 +270,10 @@ int test_init(struct tdescr *td)
 			td->feats_supported |= FEAT_SSBS;
 		if (getauxval(AT_HWCAP) & HWCAP_SVE)
 			td->feats_supported |= FEAT_SVE;
+		if (getauxval(AT_HWCAP2) & HWCAP2_SME)
+			td->feats_supported |= FEAT_SME;
+		if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)
+			td->feats_supported |= FEAT_SME_FA64;
 		if (feats_ok(td)) {
 			if (td->feats_required & td->feats_supported)
 				fprintf(stderr,
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
new file mode 100644
index 000000000000..7ed762b7202f
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Attempt to change the streaming SVE vector length in a signal
+ * handler, this is not supported and is expected to segfault.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+static unsigned int vls[SVE_VQ_MAX];
+unsigned int nvls = 0;
+
+static bool sme_get_vls(struct tdescr *td)
+{
+	int vq, vl;
+
+	/*
+	 * Enumerate up to SVE_VQ_MAX vector lengths
+	 */
+	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+		vl = prctl(PR_SVE_SET_VL, vq * 16);
+		if (vl == -1)
+			return false;
+
+		vl &= PR_SME_VL_LEN_MASK;
+
+		/* Skip missing VLs */
+		vq = sve_vq_from_vl(vl);
+
+		vls[nvls++] = vl;
+	}
+
+	/* We need at least two VLs */
+	if (nvls < 2) {
+		fprintf(stderr, "Only %d VL supported\n", nvls);
+		return false;
+	}
+
+	return true;
+}
+
+static int fake_sigreturn_ssve_change_vl(struct tdescr *td,
+					 siginfo_t *si, ucontext_t *uc)
+{
+	size_t resv_sz, offset;
+	struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+	struct sve_context *sve;
+
+	/* Get a signal context with a SME ZA frame in it */
+	if (!get_current_context(td, &sf.uc))
+		return 1;
+
+	resv_sz = GET_SF_RESV_SIZE(sf);
+	head = get_header(head, SVE_MAGIC, resv_sz, &offset);
+	if (!head) {
+		fprintf(stderr, "No SVE context\n");
+		return 1;
+	}
+
+	if (head->size != sizeof(struct sve_context)) {
+		fprintf(stderr, "Register data present, aborting\n");
+		return 1;
+	}
+
+	sve = (struct sve_context *)head;
+
+	/* No changes are supported; init left us at minimum VL so go to max */
+	fprintf(stderr, "Attempting to change VL from %d to %d\n",
+		sve->vl, vls[0]);
+	sve->vl = vls[0];
+
+	fake_sigreturn(&sf, sizeof(sf), 0);
+
+	return 1;
+}
+
+struct tdescr tde = {
+	.name = "FAKE_SIGRETURN_SSVE_CHANGE",
+	.descr = "Attempt to change Streaming SVE VL",
+	.feats_required = FEAT_SME,
+	.sig_ok = SIGSEGV,
+	.timeout = 3,
+	.init = sme_get_vls,
+	.run = fake_sigreturn_ssve_change_vl,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c
new file mode 100644
index 000000000000..f9d76ae32bba
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that using a streaming mode instruction without enabling it
+ * generates a SIGILL.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+int sme_trap_no_sm_trigger(struct tdescr *td)
+{
+	/* SMSTART ZA ; ADDHA ZA0.S, P0/M, P0/M, Z0.S */
+	asm volatile(".inst 0xd503457f ; .inst 0xc0900000");
+
+	return 0;
+}
+
+int sme_trap_no_sm_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	return 1;
+}
+
+struct tdescr tde = {
+	.name = "SME trap without SM",
+	.descr = "Check that we get a SIGILL if we use streaming mode without enabling it",
+	.timeout = 3,
+	.feats_required = FEAT_SME,   /* We need a SMSTART ZA */
+	.sanity_disabled = true,
+	.trigger = sme_trap_no_sm_trigger,
+	.run = sme_trap_no_sm_run,
+	.sig_ok = SIGILL,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c
new file mode 100644
index 000000000000..e469ae5348e3
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that using an instruction not supported in streaming mode
+ * traps when in streaming mode.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+int sme_trap_non_streaming_trigger(struct tdescr *td)
+{
+	/*
+	 * The framework will handle SIGILL so we need to exit SM to
+	 * stop any other code triggering a further SIGILL down the
+	 * line from using a streaming-illegal instruction.
+	 */
+	asm volatile(".inst 0xd503437f; /* SMSTART ZA */ \
+		      cnt v0.16b, v0.16b; \
+                      .inst 0xd503447f  /* SMSTOP ZA */");
+
+	return 0;
+}
+
+int sme_trap_non_streaming_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	return 1;
+}
+
+struct tdescr tde = {
+	.name = "SME SM trap unsupported instruction",
+	.descr = "Check that we get a SIGILL if we use an unsupported instruction in streaming mode",
+	.feats_required = FEAT_SME,
+	.feats_incompatible = FEAT_SME_FA64,
+	.timeout = 3,
+	.sanity_disabled = true,
+	.trigger = sme_trap_non_streaming_trigger,
+	.run = sme_trap_non_streaming_run,
+	.sig_ok = SIGILL,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c
new file mode 100644
index 000000000000..3a7747af4715
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that accessing ZA without enabling it generates a SIGILL.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+int sme_trap_za_trigger(struct tdescr *td)
+{
+	/* ZERO ZA */
+	asm volatile(".inst 0xc00800ff");
+
+	return 0;
+}
+
+int sme_trap_za_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	return 1;
+}
+
+struct tdescr tde = {
+	.name = "SME ZA trap",
+	.descr = "Check that we get a SIGILL if we access ZA without enabling",
+	.timeout = 3,
+	.sanity_disabled = true,
+	.trigger = sme_trap_za_trigger,
+	.run = sme_trap_za_run,
+	.sig_ok = SIGILL,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_vl.c b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c
new file mode 100644
index 000000000000..13ff3b35cbaf
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Check that the SME vector length reported in signal contexts is the
+ * expected one.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+unsigned int vl;
+
+static bool get_sme_vl(struct tdescr *td)
+{
+	int ret = prctl(PR_SME_GET_VL);
+	if (ret == -1)
+		return false;
+
+	vl = ret;
+
+	return true;
+}
+
+static int sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	size_t resv_sz, offset;
+	struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+	struct za_context *za;
+
+	/* Get a signal context which should have a ZA frame in it */
+	if (!get_current_context(td, &sf.uc))
+		return 1;
+
+	resv_sz = GET_SF_RESV_SIZE(sf);
+	head = get_header(head, ZA_MAGIC, resv_sz, &offset);
+	if (!head) {
+		fprintf(stderr, "No ZA context\n");
+		return 1;
+	}
+	za = (struct za_context *)head;
+
+	if (za->vl != vl) {
+		fprintf(stderr, "ZA sigframe VL %u, expected %u\n",
+			za->vl, vl);
+		return 1;
+	} else {
+		fprintf(stderr, "got expected VL %u\n", vl);
+	}
+
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "SME VL",
+	.descr = "Check that we get the right SME VL reported",
+	.feats_required = FEAT_SME,
+	.timeout = 3,
+	.init = get_sme_vl,
+	.run = sme_vl,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
new file mode 100644
index 000000000000..9022a6cab4b3
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that the streaming SVE register context in signal frames is
+ * set up as expected.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+static unsigned int vls[SVE_VQ_MAX];
+unsigned int nvls = 0;
+
+static bool sme_get_vls(struct tdescr *td)
+{
+	int vq, vl;
+
+	/*
+	 * Enumerate up to SVE_VQ_MAX vector lengths
+	 */
+	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+		vl = prctl(PR_SME_SET_VL, vq * 16);
+		if (vl == -1)
+			return false;
+
+		vl &= PR_SME_VL_LEN_MASK;
+
+		/* Skip missing VLs */
+		vq = sve_vq_from_vl(vl);
+
+		vls[nvls++] = vl;
+	}
+
+	/* We need at least one VL */
+	if (nvls < 1) {
+		fprintf(stderr, "Only %d VL supported\n", nvls);
+		return false;
+	}
+
+	return true;
+}
+
+static void setup_ssve_regs(void)
+{
+	/* smstart sm; real data is TODO */
+	asm volatile(".inst 0xd503437f" : : : );
+}
+
+static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
+			 unsigned int vl)
+{
+	size_t resv_sz, offset;
+	struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+	struct sve_context *ssve;
+	int ret;
+
+	fprintf(stderr, "Testing VL %d\n", vl);
+
+	ret = prctl(PR_SME_SET_VL, vl);
+	if (ret != vl) {
+		fprintf(stderr, "Failed to set VL, got %d\n", ret);
+		return 1;
+	}
+
+	/*
+	 * Get a signal context which should have a SVE frame and registers
+	 * in it.
+	 */
+	setup_ssve_regs();
+	if (!get_current_context(td, &sf.uc))
+		return 1;
+
+	resv_sz = GET_SF_RESV_SIZE(sf);
+	head = get_header(head, SVE_MAGIC, resv_sz, &offset);
+	if (!head) {
+		fprintf(stderr, "No SVE context\n");
+		return 1;
+	}
+
+	ssve = (struct sve_context *)head;
+	if (ssve->vl != vl) {
+		fprintf(stderr, "Got VL %d, expected %d\n", ssve->vl, vl);
+		return 1;
+	}
+
+	/* The actual size validation is done in get_current_context() */
+	fprintf(stderr, "Got expected size %u and VL %d\n",
+		head->size, ssve->vl);
+
+	return 0;
+}
+
+static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	int i;
+
+	for (i = 0; i < nvls; i++) {
+		/*
+		 * TODO: the signal test helpers can't currently cope
+		 * with signal frames bigger than struct sigcontext,
+		 * skip VLs that will trigger that.
+		 */
+		if (vls[i] > 64) {
+			printf("Skipping VL %u due to stack size\n", vls[i]);
+			continue;
+		}
+
+		if (do_one_sme_vl(td, si, uc, vls[i]))
+			return 1;
+	}
+
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "Streaming SVE registers",
+	.descr = "Check that we get the right Streaming SVE registers reported",
+	/*
+	 * We shouldn't require FA64 but things like memset() used in the
+	 * helpers might use unsupported instructions so for now disable
+	 * the test unless we've got the full instruction set.
+	 */
+	.feats_required = FEAT_SME | FEAT_SME_FA64,
+	.timeout = 3,
+	.init = sme_get_vls,
+	.run = sme_regs,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c
index 8c2a57fc2f9c..84c36bee4d82 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.c
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c
@@ -75,6 +75,31 @@ bool validate_sve_context(struct sve_context *sve, char **err)
 	return true;
 }
 
+bool validate_za_context(struct za_context *za, char **err)
+{
+	/* Size will be rounded up to a multiple of 16 bytes */
+	size_t regs_size
+		= ((ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za->vl)) + 15) / 16) * 16;
+
+	if (!za || !err)
+		return false;
+
+	/* Either a bare za_context or a za_context followed by regs data */
+	if ((za->head.size != sizeof(struct za_context)) &&
+	    (za->head.size != regs_size)) {
+		*err = "bad size for ZA context";
+		return false;
+	}
+
+	if (!sve_vl_valid(za->vl)) {
+		*err = "SME VL in ZA context invalid";
+
+		return false;
+	}
+
+	return true;
+}
+
 bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 {
 	bool terminated = false;
@@ -82,6 +107,7 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 	int flags = 0;
 	struct extra_context *extra = NULL;
 	struct sve_context *sve = NULL;
+	struct za_context *za = NULL;
 	struct _aarch64_ctx *head =
 		(struct _aarch64_ctx *)uc->uc_mcontext.__reserved;
 
@@ -120,6 +146,13 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 			sve = (struct sve_context *)head;
 			flags |= SVE_CTX;
 			break;
+		case ZA_MAGIC:
+			if (flags & ZA_CTX)
+				*err = "Multiple ZA_MAGIC";
+			/* Size is validated in validate_za_context() */
+			za = (struct za_context *)head;
+			flags |= ZA_CTX;
+			break;
 		case EXTRA_MAGIC:
 			if (flags & EXTRA_CTX)
 				*err = "Multiple EXTRA_MAGIC";
@@ -165,6 +198,9 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 		if (flags & SVE_CTX)
 			if (!validate_sve_context(sve, err))
 				return false;
+		if (flags & ZA_CTX)
+			if (!validate_za_context(za, err))
+				return false;
 
 		head = GET_RESV_NEXT_HEAD(head);
 	}
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h
index ad884c135314..49f1d5de7b5b 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.h
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h
@@ -16,7 +16,8 @@
 
 #define FPSIMD_CTX	(1 << 0)
 #define SVE_CTX		(1 << 1)
-#define EXTRA_CTX	(1 << 2)
+#define ZA_CTX		(1 << 2)
+#define EXTRA_CTX	(1 << 3)
 
 #define KSFT_BAD_MAGIC	0xdeadbeef
 
diff --git a/tools/testing/selftests/arm64/signal/testcases/za_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
new file mode 100644
index 000000000000..b94e4f99fcac
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that the ZA register context in signal frames is set up as
+ * expected.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+static unsigned int vls[SVE_VQ_MAX];
+unsigned int nvls = 0;
+
+static bool sme_get_vls(struct tdescr *td)
+{
+	int vq, vl;
+
+	/*
+	 * Enumerate up to SVE_VQ_MAX vector lengths
+	 */
+	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+		vl = prctl(PR_SVE_SET_VL, vq * 16);
+		if (vl == -1)
+			return false;
+
+		vl &= PR_SME_VL_LEN_MASK;
+
+		/* Skip missing VLs */
+		vq = sve_vq_from_vl(vl);
+
+		vls[nvls++] = vl;
+	}
+
+	/* We need at least one VL */
+	if (nvls < 1) {
+		fprintf(stderr, "Only %d VL supported\n", nvls);
+		return false;
+	}
+
+	return true;
+}
+
+static void setup_za_regs(void)
+{
+	/* smstart za; real data is TODO */
+	asm volatile(".inst 0xd503457f" : : : );
+}
+
+static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
+			 unsigned int vl)
+{
+	size_t resv_sz, offset;
+	struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+	struct za_context *za;
+
+	fprintf(stderr, "Testing VL %d\n", vl);
+
+	if (prctl(PR_SME_SET_VL, vl) != vl) {
+		fprintf(stderr, "Failed to set VL\n");
+		return 1;
+	}
+
+	/*
+	 * Get a signal context which should have a SVE frame and registers
+	 * in it.
+	 */
+	setup_za_regs();
+	if (!get_current_context(td, &sf.uc))
+		return 1;
+
+	resv_sz = GET_SF_RESV_SIZE(sf);
+	head = get_header(head, ZA_MAGIC, resv_sz, &offset);
+	if (!head) {
+		fprintf(stderr, "No ZA context\n");
+		return 1;
+	}
+
+	za = (struct za_context *)head;
+	if (za->vl != vl) {
+		fprintf(stderr, "Got VL %d, expected %d\n", za->vl, vl);
+		return 1;
+	}
+
+	/* The actual size validation is done in get_current_context() */
+	fprintf(stderr, "Got expected size %u and VL %d\n",
+		head->size, za->vl);
+
+	return 0;
+}
+
+static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	int i;
+
+	for (i = 0; i < nvls; i++) {
+		/*
+		 * TODO: the signal test helpers can't currently cope
+		 * with signal frames bigger than struct sigcontext,
+		 * skip VLs that will trigger that.
+		 */
+		if (vls[i] > 32) {
+			printf("Skipping VL %u due to stack size\n", vls[i]);
+			continue;
+		}
+
+		if (do_one_sme_vl(td, si, uc, vls[i]))
+			return 1;
+	}
+
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "ZA register",
+	.descr = "Check that we get the right ZA registers reported",
+	.feats_required = FEAT_SME,
+	.timeout = 3,
+	.init = sme_get_vls,
+	.run = sme_regs,
+};