Merge remote-tracking branch 'torvalds/master' into perf/core

To pick up fixes.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

25 files changed, 1404 insertions, 195 deletions

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 94d62a92f1a1f..4282ef9ec354a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3925,6 +3925,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	bool draining = false;
 
 	trace->live = true;
+	signal(SIGCHLD, sig_handler);
 
 	if (!trace->raw_augmented_syscalls) {
 		if (trace->trace_syscalls && trace__add_syscall_newtp(trace))
@@ -4876,7 +4877,6 @@ int cmd_trace(int argc, const char **argv)
 
 	signal(SIGSEGV, sighandler_dump_stack);
 	signal(SIGFPE, sighandler_dump_stack);
-	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
 
 	trace.evlist = evlist__new();
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index c7a9fa0ffae9d..2c06abf6dcd26 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -24,16 +24,6 @@
 #include "util/parse-sublevel-options.h"
 
 #include <linux/ctype.h>
-#include <traceevent/event-parse.h>
-
-#define MAKE_LIBTRACEEVENT_VERSION(a, b, c) ((a)*255*255+(b)*255+(c))
-#ifndef LIBTRACEEVENT_VERSION
-/*
- * If LIBTRACEEVENT_VERSION wasn't computed then set to version 1.1.0 that ships
- * with the Linux kernel tools.
- */
-#define LIBTRACEEVENT_VERSION MAKE_LIBTRACEEVENT_VERSION(1, 1, 0)
-#endif
 
 int verbose;
 int debug_peo_args;
@@ -238,15 +228,6 @@ int perf_debug_option(const char *str)
 	/* Allow only verbose value in range (0, 10), otherwise set 0. */
 	verbose = (verbose < 0) || (verbose > 10) ? 0 : verbose;
 
-#if MAKE_LIBTRACEEVENT_VERSION(1, 3, 0) <= LIBTRACEEVENT_VERSION
-	if (verbose == 1)
-		tep_set_loglevel(TEP_LOG_INFO);
-	else if (verbose == 2)
-		tep_set_loglevel(TEP_LOG_DEBUG);
-	else if (verbose >= 3)
-		tep_set_loglevel(TEP_LOG_ALL);
-#endif
-
 	return 0;
 }
 
diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile
index ced910fb40198..1e8d9a8f59df8 100644
--- a/tools/testing/selftests/arm64/Makefile
+++ b/tools/testing/selftests/arm64/Makefile
@@ -4,7 +4,7 @@
 ARCH ?= $(shell uname -m 2>/dev/null || echo not)
 
 ifneq (,$(filter $(ARCH),aarch64 arm64))
-ARM64_SUBTARGETS ?= tags signal pauth fp mte bti
+ARM64_SUBTARGETS ?= tags signal pauth fp mte bti abi
 else
 ARM64_SUBTARGETS :=
 endif
diff --git a/tools/testing/selftests/arm64/abi/.gitignore b/tools/testing/selftests/arm64/abi/.gitignore
new file mode 100644
index 0000000000000..b79cf5814c230
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/.gitignore
@@ -0,0 +1 @@
+syscall-abi
diff --git a/tools/testing/selftests/arm64/abi/Makefile b/tools/testing/selftests/arm64/abi/Makefile
new file mode 100644
index 0000000000000..96eba974ac8d5
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2021 ARM Limited
+
+TEST_GEN_PROGS := syscall-abi
+
+include ../../lib.mk
+
+$(OUTPUT)/syscall-abi: syscall-abi.c syscall-abi-asm.S
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
new file mode 100644
index 0000000000000..983467cfcee0e
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+//
+// Assembly portion of the syscall ABI test
+
+//
+// Load values from memory into registers, invoke a syscall and save the
+// register values back to memory for later checking.  The syscall to be
+// invoked is configured in x8 of the input GPR data.
+//
+// x0:	SVE VL, 0 for FP only
+//
+//	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
+
+.arch_extension sve
+
+.globl do_syscall
+do_syscall:
+	// Store callee saved registers x19-x29 (80 bytes) plus x0 and x1
+	stp	x29, x30, [sp, #-112]!
+	mov	x29, sp
+	stp	x0, x1, [sp, #16]
+	stp	x19, x20, [sp, #32]
+	stp	x21, x22, [sp, #48]
+	stp	x23, x24, [sp, #64]
+	stp	x25, x26, [sp, #80]
+	stp	x27, x28, [sp, #96]
+
+	// Load GPRs x8-x28, and save our SP/FP for later comparison
+	ldr	x2, =gpr_in
+	add	x2, x2, #64
+	ldp	x8, x9, [x2], #16
+	ldp	x10, x11, [x2], #16
+	ldp	x12, x13, [x2], #16
+	ldp	x14, x15, [x2], #16
+	ldp	x16, x17, [x2], #16
+	ldp	x18, x19, [x2], #16
+	ldp	x20, x21, [x2], #16
+	ldp	x22, x23, [x2], #16
+	ldp	x24, x25, [x2], #16
+	ldp	x26, x27, [x2], #16
+	ldr	x28, [x2], #8
+	str	x29, [x2], #8		// FP
+	str	x30, [x2], #8		// LR
+
+	// Load FPRs if we're not doing SVE
+	cbnz	x0, 1f
+	ldr	x2, =fpr_in
+	ldp	q0, q1, [x2]
+	ldp	q2, q3, [x2, #16 * 2]
+	ldp	q4, q5, [x2, #16 * 4]
+	ldp	q6, q7, [x2, #16 * 6]
+	ldp	q8, q9, [x2, #16 * 8]
+	ldp	q10, q11, [x2, #16 * 10]
+	ldp	q12, q13, [x2, #16 * 12]
+	ldp	q14, q15, [x2, #16 * 14]
+	ldp	q16, q17, [x2, #16 * 16]
+	ldp	q18, q19, [x2, #16 * 18]
+	ldp	q20, q21, [x2, #16 * 20]
+	ldp	q22, q23, [x2, #16 * 22]
+	ldp	q24, q25, [x2, #16 * 24]
+	ldp	q26, q27, [x2, #16 * 26]
+	ldp	q28, q29, [x2, #16 * 28]
+	ldp	q30, q31, [x2, #16 * 30]
+1:
+
+	// Load the SVE registers if we're doing SVE
+	cbz	x0, 1f
+
+	ldr	x2, =z_in
+	ldr	z0, [x2, #0, MUL VL]
+	ldr	z1, [x2, #1, MUL VL]
+	ldr	z2, [x2, #2, MUL VL]
+	ldr	z3, [x2, #3, MUL VL]
+	ldr	z4, [x2, #4, MUL VL]
+	ldr	z5, [x2, #5, MUL VL]
+	ldr	z6, [x2, #6, MUL VL]
+	ldr	z7, [x2, #7, MUL VL]
+	ldr	z8, [x2, #8, MUL VL]
+	ldr	z9, [x2, #9, MUL VL]
+	ldr	z10, [x2, #10, MUL VL]
+	ldr	z11, [x2, #11, MUL VL]
+	ldr	z12, [x2, #12, MUL VL]
+	ldr	z13, [x2, #13, MUL VL]
+	ldr	z14, [x2, #14, MUL VL]
+	ldr	z15, [x2, #15, MUL VL]
+	ldr	z16, [x2, #16, MUL VL]
+	ldr	z17, [x2, #17, MUL VL]
+	ldr	z18, [x2, #18, MUL VL]
+	ldr	z19, [x2, #19, MUL VL]
+	ldr	z20, [x2, #20, MUL VL]
+	ldr	z21, [x2, #21, MUL VL]
+	ldr	z22, [x2, #22, MUL VL]
+	ldr	z23, [x2, #23, MUL VL]
+	ldr	z24, [x2, #24, MUL VL]
+	ldr	z25, [x2, #25, MUL VL]
+	ldr	z26, [x2, #26, MUL VL]
+	ldr	z27, [x2, #27, MUL VL]
+	ldr	z28, [x2, #28, MUL VL]
+	ldr	z29, [x2, #29, MUL VL]
+	ldr	z30, [x2, #30, MUL VL]
+	ldr	z31, [x2, #31, MUL VL]
+
+	ldr	x2, =ffr_in
+	ldr	p0, [x2, #0]
+	wrffr	p0.b
+
+	ldr	x2, =p_in
+	ldr	p0, [x2, #0, MUL VL]
+	ldr	p1, [x2, #1, MUL VL]
+	ldr	p2, [x2, #2, MUL VL]
+	ldr	p3, [x2, #3, MUL VL]
+	ldr	p4, [x2, #4, MUL VL]
+	ldr	p5, [x2, #5, MUL VL]
+	ldr	p6, [x2, #6, MUL VL]
+	ldr	p7, [x2, #7, MUL VL]
+	ldr	p8, [x2, #8, MUL VL]
+	ldr	p9, [x2, #9, MUL VL]
+	ldr	p10, [x2, #10, MUL VL]
+	ldr	p11, [x2, #11, MUL VL]
+	ldr	p12, [x2, #12, MUL VL]
+	ldr	p13, [x2, #13, MUL VL]
+	ldr	p14, [x2, #14, MUL VL]
+	ldr	p15, [x2, #15, MUL VL]
+1:
+
+	// Do the syscall
+	svc	#0
+
+	// Save GPRs x8-x30
+	ldr	x2, =gpr_out
+	add	x2, x2, #64
+	stp	x8, x9, [x2], #16
+	stp	x10, x11, [x2], #16
+	stp	x12, x13, [x2], #16
+	stp	x14, x15, [x2], #16
+	stp	x16, x17, [x2], #16
+	stp	x18, x19, [x2], #16
+	stp	x20, x21, [x2], #16
+	stp	x22, x23, [x2], #16
+	stp	x24, x25, [x2], #16
+	stp	x26, x27, [x2], #16
+	stp	x28, x29, [x2], #16
+	str	x30, [x2]
+
+	// Restore x0 and x1 for feature checks
+	ldp	x0, x1, [sp, #16]
+
+	// Save FPSIMD state
+	ldr	x2, =fpr_out
+	stp	q0, q1, [x2]
+	stp	q2, q3, [x2, #16 * 2]
+	stp	q4, q5, [x2, #16 * 4]
+	stp	q6, q7, [x2, #16 * 6]
+	stp	q8, q9, [x2, #16 * 8]
+	stp	q10, q11, [x2, #16 * 10]
+	stp	q12, q13, [x2, #16 * 12]
+	stp	q14, q15, [x2, #16 * 14]
+	stp	q16, q17, [x2, #16 * 16]
+	stp	q18, q19, [x2, #16 * 18]
+	stp	q20, q21, [x2, #16 * 20]
+	stp	q22, q23, [x2, #16 * 22]
+	stp	q24, q25, [x2, #16 * 24]
+	stp	q26, q27, [x2, #16 * 26]
+	stp	q28, q29, [x2, #16 * 28]
+	stp	q30, q31, [x2, #16 * 30]
+
+	// Save the SVE state if we have some
+	cbz	x0, 1f
+
+	ldr	x2, =z_out
+	str	z0, [x2, #0, MUL VL]
+	str	z1, [x2, #1, MUL VL]
+	str	z2, [x2, #2, MUL VL]
+	str	z3, [x2, #3, MUL VL]
+	str	z4, [x2, #4, MUL VL]
+	str	z5, [x2, #5, MUL VL]
+	str	z6, [x2, #6, MUL VL]
+	str	z7, [x2, #7, MUL VL]
+	str	z8, [x2, #8, MUL VL]
+	str	z9, [x2, #9, MUL VL]
+	str	z10, [x2, #10, MUL VL]
+	str	z11, [x2, #11, MUL VL]
+	str	z12, [x2, #12, MUL VL]
+	str	z13, [x2, #13, MUL VL]
+	str	z14, [x2, #14, MUL VL]
+	str	z15, [x2, #15, MUL VL]
+	str	z16, [x2, #16, MUL VL]
+	str	z17, [x2, #17, MUL VL]
+	str	z18, [x2, #18, MUL VL]
+	str	z19, [x2, #19, MUL VL]
+	str	z20, [x2, #20, MUL VL]
+	str	z21, [x2, #21, MUL VL]
+	str	z22, [x2, #22, MUL VL]
+	str	z23, [x2, #23, MUL VL]
+	str	z24, [x2, #24, MUL VL]
+	str	z25, [x2, #25, MUL VL]
+	str	z26, [x2, #26, MUL VL]
+	str	z27, [x2, #27, MUL VL]
+	str	z28, [x2, #28, MUL VL]
+	str	z29, [x2, #29, MUL VL]
+	str	z30, [x2, #30, MUL VL]
+	str	z31, [x2, #31, MUL VL]
+
+	ldr	x2, =p_out
+	str	p0, [x2, #0, MUL VL]
+	str	p1, [x2, #1, MUL VL]
+	str	p2, [x2, #2, MUL VL]
+	str	p3, [x2, #3, MUL VL]
+	str	p4, [x2, #4, MUL VL]
+	str	p5, [x2, #5, MUL VL]
+	str	p6, [x2, #6, MUL VL]
+	str	p7, [x2, #7, MUL VL]
+	str	p8, [x2, #8, MUL VL]
+	str	p9, [x2, #9, MUL VL]
+	str	p10, [x2, #10, MUL VL]
+	str	p11, [x2, #11, MUL VL]
+	str	p12, [x2, #12, MUL VL]
+	str	p13, [x2, #13, MUL VL]
+	str	p14, [x2, #14, MUL VL]
+	str	p15, [x2, #15, MUL VL]
+
+	ldr	x2, =ffr_out
+	rdffr	p0.b
+	str	p0, [x2, #0]
+1:
+
+	// Restore callee saved registers x19-x30
+	ldp	x19, x20, [sp, #32]
+	ldp	x21, x22, [sp, #48]
+	ldp	x23, x24, [sp, #64]
+	ldp	x25, x26, [sp, #80]
+	ldp	x27, x28, [sp, #96]
+	ldp	x29, x30, [sp], #112
+
+	ret
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c
new file mode 100644
index 0000000000000..d8eeeafb50dcb
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.c
@@ -0,0 +1,318 @@
+// 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 <asm/hwcap.h>
+#include <asm/sigcontext.h>
+#include <asm/unistd.h>
+
+#include "../../kselftest.h"
+
+#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0]))
+#define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1)
+
+extern void do_syscall(int sve_vl);
+
+static void fill_random(void *buf, size_t size)
+{
+	int i;
+	uint32_t *lbuf = buf;
+
+	/* random() returns a 32 bit number regardless of the size of long */
+	for (i = 0; i < size / sizeof(uint32_t); i++)
+		lbuf[i] = random();
+}
+
+/*
+ * We also repeat the test for several syscalls to try to expose different
+ * behaviour.
+ */
+static struct syscall_cfg {
+	int syscall_nr;
+	const char *name;
+} syscalls[] = {
+	{ __NR_getpid,		"getpid()" },
+	{ __NR_sched_yield,	"sched_yield()" },
+};
+
+#define NUM_GPR 31
+uint64_t gpr_in[NUM_GPR];
+uint64_t gpr_out[NUM_GPR];
+
+static void setup_gpr(struct syscall_cfg *cfg, int sve_vl)
+{
+	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)
+{
+	int errors = 0;
+	int i;
+
+	/*
+	 * GPR x0-x7 may be clobbered, and all others should be preserved.
+	 */
+	for (i = 9; i < ARRAY_SIZE(gpr_in); i++) {
+		if (gpr_in[i] != gpr_out[i]) {
+			ksft_print_msg("%s SVE VL %d mismatch in GPR %d: %llx != %llx\n",
+				       cfg->name, sve_vl, i,
+				       gpr_in[i], gpr_out[i]);
+			errors++;
+		}
+	}
+
+	return errors;
+}
+
+#define NUM_FPR 32
+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)
+{
+	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)
+{
+	int errors = 0;
+	int i;
+
+	if (!sve_vl) {
+		for (i = 0; i < ARRAY_SIZE(fpr_in); i++) {
+			if (fpr_in[i] != fpr_out[i]) {
+				ksft_print_msg("%s Q%d/%d mismatch %llx != %llx\n",
+					       cfg->name,
+					       i / 2, i % 2,
+					       fpr_in[i], fpr_out[i]);
+				errors++;
+			}
+		}
+	}
+
+	return errors;
+}
+
+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)
+{
+	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)
+{
+	size_t reg_size = sve_vl;
+	int errors = 0;
+	int i;
+
+	if (!sve_vl)
+		return 0;
+
+	/*
+	 * After a syscall the low 128 bits of the Z registers should
+	 * be preserved and the rest be zeroed or preserved.
+	 */
+	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) {
+			ksft_print_msg("%s SVE VL %d Z%d low 128 bits changed\n",
+				       cfg->name, sve_vl, i);
+			errors++;
+		}
+	}
+
+	return errors;
+}
+
+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)
+{
+	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)
+{
+	size_t reg_size = sve_vq_from_vl(sve_vl) * 2; /* 1 bit per VL byte */
+
+	int errors = 0;
+	int i;
+
+	if (!sve_vl)
+		return 0;
+
+	/* After a syscall the P registers should be preserved or zeroed */
+	for (i = 0; i < SVE_NUM_PREGS * reg_size; i++)
+		if (p_out[i] && (p_in[i] != p_out[i]))
+			errors++;
+	if (errors)
+		ksft_print_msg("%s SVE VL %d predicate registers non-zero\n",
+			       cfg->name, sve_vl);
+
+	return errors;
+}
+
+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)
+{
+	/*
+	 * 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.
+	 */
+	memset(ffr_in, 0xff, sizeof(ffr_in));
+	fill_random(ffr_out, sizeof(ffr_out));
+}
+
+static int check_ffr(struct syscall_cfg *cfg, int sve_vl)
+{
+	size_t reg_size = sve_vq_from_vl(sve_vl) * 2;  /* 1 bit per VL byte */
+	int errors = 0;
+	int i;
+
+	if (!sve_vl)
+		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]))
+			errors++;
+	if (errors)
+		ksft_print_msg("%s SVE VL %d FFR non-zero\n",
+			       cfg->name, 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);
+
+/*
+ * Each set of registers has a setup function which is called before
+ * the syscall to fill values in a global variable for loading by the
+ * test code and a check function which validates that the results are
+ * as expected.  Vector lengths are passed everywhere, a vector length
+ * of 0 should be treated as do not test.
+ */
+static struct {
+	setup_fn setup;
+	check_fn check;
+} regset[] = {
+	{ setup_gpr, check_gpr },
+	{ setup_fpr, check_fpr },
+	{ setup_z, check_z },
+	{ setup_p, check_p },
+	{ setup_ffr, check_ffr },
+};
+
+static bool do_test(struct syscall_cfg *cfg, int sve_vl)
+{
+	int errors = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(regset); i++)
+		regset[i].setup(cfg, sve_vl);
+
+	do_syscall(sve_vl);
+
+	for (i = 0; i < ARRAY_SIZE(regset); i++)
+		errors += regset[i].check(cfg, sve_vl);
+
+	return errors == 0;
+}
+
+static void test_one_syscall(struct syscall_cfg *cfg)
+{
+	int sve_vq, sve_vl;
+
+	/* FPSIMD only case */
+	ksft_test_result(do_test(cfg, 0),
+			 "%s FPSIMD\n", cfg->name);
+
+	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
+		return;
+
+	for (sve_vq = SVE_VQ_MAX; sve_vq > 0; --sve_vq) {
+		sve_vl = prctl(PR_SVE_SET_VL, sve_vq * 16);
+		if (sve_vl == -1)
+			ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n",
+					   strerror(errno), errno);
+
+		sve_vl &= PR_SVE_VL_LEN_MASK;
+
+		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),
+				 "%s SVE VL %d\n", cfg->name, sve_vl);
+	}
+}
+
+int sve_count_vls(void)
+{
+	unsigned int vq;
+	int vl_count = 0;
+	int vl;
+
+	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
+		return 0;
+
+	/*
+	 * 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)
+			ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n",
+					   strerror(errno), errno);
+
+		vl &= PR_SVE_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;
+
+	srandom(getpid());
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(syscalls) * (sve_count_vls() + 1));
+
+	for (i = 0; i < ARRAY_SIZE(syscalls); i++)
+		test_one_syscall(&syscalls[i]);
+
+	ksft_print_cnts();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore
index b67395903b9bb..c50d86331ed2f 100644
--- a/tools/testing/selftests/arm64/fp/.gitignore
+++ b/tools/testing/selftests/arm64/fp/.gitignore
@@ -1,3 +1,4 @@
+fp-pidbench
 fpsimd-test
 rdvl-sve
 sve-probe-vls
diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile
index ba1488c7c3153..95f0b877a060b 100644
--- a/tools/testing/selftests/arm64/fp/Makefile
+++ b/tools/testing/selftests/arm64/fp/Makefile
@@ -2,13 +2,15 @@
 
 CFLAGS += -I../../../../../usr/include/
 TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg
-TEST_PROGS_EXTENDED := fpsimd-test fpsimd-stress \
+TEST_PROGS_EXTENDED := fp-pidbench fpsimd-test fpsimd-stress \
 	rdvl-sve \
 	sve-test sve-stress \
 	vlset
 
 all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED)
 
+fp-pidbench: fp-pidbench.S asm-utils.o
+	$(CC) -nostdlib $^ -o $@
 fpsimd-test: fpsimd-test.o asm-utils.o
 	$(CC) -nostdlib $^ -o $@
 rdvl-sve: rdvl-sve.o rdvl.o
diff --git a/tools/testing/selftests/arm64/fp/fp-pidbench.S b/tools/testing/selftests/arm64/fp/fp-pidbench.S
new file mode 100644
index 0000000000000..16a436389bfcd
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/fp-pidbench.S
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+//
+// Trivial syscall overhead benchmark.
+//
+// This is implemented in asm to ensure that we don't have any issues with
+// system libraries using instructions that disrupt the test.
+
+#include <asm/unistd.h>
+#include "assembler.h"
+
+.arch_extension sve
+
+.macro test_loop per_loop
+	mov	x10, x20
+	mov	x8, #__NR_getpid
+	mrs	x11, CNTVCT_EL0
+1:
+	\per_loop
+	svc	#0
+	sub	x10, x10, #1
+	cbnz	x10, 1b
+
+	mrs	x12, CNTVCT_EL0
+	sub	x0, x12, x11
+	bl	putdec
+	puts	"\n"
+.endm
+
+// Main program entry point
+.globl _start
+function _start
+_start:
+	puts	"Iterations per test: "
+	mov	x20, #10000
+	lsl	x20, x20, #8
+	mov	x0, x20
+	bl	putdec
+	puts	"\n"
+
+	// Test having never used SVE
+	puts	"No SVE: "
+	test_loop
+
+	// Check for SVE support - should use hwcap but that's hard in asm
+	mrs	x0, ID_AA64PFR0_EL1
+	ubfx	x0, x0, #32, #4
+	cbnz	x0, 1f
+	puts	"System does not support SVE\n"
+	b	out
+1:
+
+	// Execute a SVE instruction
+	puts	"SVE VL: "
+	rdvl	x0, #8
+	bl	putdec
+	puts	"\n"
+
+	puts	"SVE used once: "
+	test_loop
+
+	// Use SVE per syscall
+	puts	"SVE used per syscall: "
+	test_loop "rdvl x0, #8"
+
+	//  And we're done
+out:
+	mov	x0, #0
+	mov	x8, #__NR_exit
+	svc	#0
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index c4417bc48d4f8..af798b9d232cc 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -21,16 +21,37 @@
 
 #include "../../kselftest.h"
 
-#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
-#define FPSIMD_TESTS 5
-
-#define EXPECTED_TESTS (VL_TESTS + FPSIMD_TESTS)
+#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0]))
 
 /* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
 #ifndef NT_ARM_SVE
 #define NT_ARM_SVE 0x405
 #endif
 
+struct vec_type {
+	const char *name;
+	unsigned long hwcap_type;
+	unsigned long hwcap;
+	int regset;
+	int prctl_set;
+};
+
+static const struct vec_type vec_types[] = {
+	{
+		.name = "SVE",
+		.hwcap_type = AT_HWCAP,
+		.hwcap = HWCAP_SVE,
+		.regset = NT_ARM_SVE,
+		.prctl_set = PR_SVE_SET_VL,
+	},
+};
+
+#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
+#define FLAG_TESTS 2
+#define FPSIMD_TESTS 3
+
+#define EXPECTED_TESTS ((VL_TESTS + FLAG_TESTS + FPSIMD_TESTS) * ARRAY_SIZE(vec_types))
+
 static void fill_buf(char *buf, size_t size)
 {
 	int i;
@@ -59,7 +80,8 @@ static int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
 	return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov);
 }
 
-static struct user_sve_header *get_sve(pid_t pid, void **buf, size_t *size)
+static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type,
+				       void **buf, size_t *size)
 {
 	struct user_sve_header *sve;
 	void *p;
@@ -80,7 +102,7 @@ static struct user_sve_header *get_sve(pid_t pid, void **buf, size_t *size)
 
 		iov.iov_base = *buf;
 		iov.iov_len = sz;
-		if (ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov))
+		if (ptrace(PTRACE_GETREGSET, pid, type->regset, &iov))
 			goto error;
 
 		sve = *buf;
@@ -96,17 +118,18 @@ error:
 	return NULL;
 }
 
-static int set_sve(pid_t pid, const struct user_sve_header *sve)
+static int set_sve(pid_t pid, const struct vec_type *type,
+		   const struct user_sve_header *sve)
 {
 	struct iovec iov;
 
 	iov.iov_base = (void *)sve;
 	iov.iov_len = sve->size;
-	return ptrace(PTRACE_SETREGSET, pid, NT_ARM_SVE, &iov);
+	return ptrace(PTRACE_SETREGSET, pid, type->regset, &iov);
 }
 
 /* Validate setting and getting the inherit flag */
-static void ptrace_set_get_inherit(pid_t child)
+static void ptrace_set_get_inherit(pid_t child, const struct vec_type *type)
 {
 	struct user_sve_header sve;
 	struct user_sve_header *new_sve = NULL;
@@ -118,9 +141,10 @@ static void ptrace_set_get_inherit(pid_t child)
 	sve.size = sizeof(sve);
 	sve.vl = sve_vl_from_vq(SVE_VQ_MIN);
 	sve.flags = SVE_PT_VL_INHERIT;
-	ret = set_sve(child, &sve);
+	ret = set_sve(child, type, &sve);
 	if (ret != 0) {
-		ksft_test_result_fail("Failed to set SVE_PT_VL_INHERIT\n");
+		ksft_test_result_fail("Failed to set %s SVE_PT_VL_INHERIT\n",
+				      type->name);
 		return;
 	}
 
@@ -128,35 +152,39 @@ static void ptrace_set_get_inherit(pid_t child)
 	 * Read back the new register state and verify that we have
 	 * set the flags we expected.
 	 */
-	if (!get_sve(child, (void **)&new_sve, &new_sve_size)) {
-		ksft_test_result_fail("Failed to read SVE flags\n");
+	if (!get_sve(child, type, (void **)&new_sve, &new_sve_size)) {
+		ksft_test_result_fail("Failed to read %s SVE flags\n",
+				      type->name);
 		return;
 	}
 
 	ksft_test_result(new_sve->flags & SVE_PT_VL_INHERIT,
-			 "SVE_PT_VL_INHERIT set\n");
+			 "%s SVE_PT_VL_INHERIT set\n", type->name);
 
 	/* Now clear */
 	sve.flags &= ~SVE_PT_VL_INHERIT;
-	ret = set_sve(child, &sve);
+	ret = set_sve(child, type, &sve);
 	if (ret != 0) {
-		ksft_test_result_fail("Failed to clear SVE_PT_VL_INHERIT\n");
+		ksft_test_result_fail("Failed to clear %s SVE_PT_VL_INHERIT\n",
+				      type->name);
 		return;
 	}
 
-	if (!get_sve(child, (void **)&new_sve, &new_sve_size)) {
-		ksft_test_result_fail("Failed to read SVE flags\n");
+	if (!get_sve(child, type, (void **)&new_sve, &new_sve_size)) {
+		ksft_test_result_fail("Failed to read %s SVE flags\n",
+				      type->name);
 		return;
 	}
 
 	ksft_test_result(!(new_sve->flags & SVE_PT_VL_INHERIT),
-			 "SVE_PT_VL_INHERIT cleared\n");
+			 "%s SVE_PT_VL_INHERIT cleared\n", type->name);
 
 	free(new_sve);
 }
 
 /* Validate attempting to set the specfied VL via ptrace */
-static void ptrace_set_get_vl(pid_t child, unsigned int vl, bool *supported)
+static void ptrace_set_get_vl(pid_t child, const struct vec_type *type,
+			      unsigned int vl, bool *supported)
 {
 	struct user_sve_header sve;
 	struct user_sve_header *new_sve = NULL;
@@ -166,10 +194,10 @@ static void ptrace_set_get_vl(pid_t child, unsigned int vl, bool *supported)
 	*supported = false;
 
 	/* Check if the VL is supported in this process */
-	prctl_vl = prctl(PR_SVE_SET_VL, vl);
+	prctl_vl = prctl(type->prctl_set, vl);
 	if (prctl_vl == -1)
-		ksft_exit_fail_msg("prctl(PR_SVE_SET_VL) failed: %s (%d)\n",
-				   strerror(errno), errno);
+		ksft_exit_fail_msg("prctl(PR_%s_SET_VL) failed: %s (%d)\n",
+				   type->name, strerror(errno), errno);
 
 	/* If the VL is not supported then a supported VL will be returned */
 	*supported = (prctl_vl == vl);
@@ -178,9 +206,10 @@ static void ptrace_set_get_vl(pid_t child, unsigned int vl, bool *supported)
 	memset(&sve, 0, sizeof(sve));
 	sve.size = sizeof(sve);
 	sve.vl = vl;
-	ret = set_sve(child, &sve);
+	ret = set_sve(child, type, &sve);
 	if (ret != 0) {
-		ksft_test_result_fail("Failed to set VL %u\n", vl);
+		ksft_test_result_fail("Failed to set %s VL %u\n",
+				      type->name, vl);
 		return;
 	}
 
@@ -188,12 +217,14 @@ static void ptrace_set_get_vl(pid_t child, unsigned int vl, bool *supported)
 	 * Read back the new register state and verify that we have the
 	 * same VL that we got from prctl() on ourselves.
 	 */
-	if (!get_sve(child, (void **)&new_sve, &new_sve_size)) {
-		ksft_test_result_fail("Failed to read VL %u\n", vl);
+	if (!get_sve(child, type, (void **)&new_sve, &new_sve_size)) {
+		ksft_test_result_fail("Failed to read %s VL %u\n",
+				      type->name, vl);
 		return;
 	}
 
-	ksft_test_result(new_sve->vl = prctl_vl, "Set VL %u\n", vl);
+	ksft_test_result(new_sve->vl = prctl_vl, "Set %s VL %u\n",
+			 type->name, vl);
 
 	free(new_sve);
 }
@@ -209,7 +240,7 @@ 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)
+static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
 {
 	void *svebuf = NULL;
 	size_t svebufsz = 0;
@@ -219,17 +250,18 @@ static void ptrace_sve_fpsimd(pid_t child)
 	unsigned char *p;
 
 	/* New process should start with FPSIMD registers only */
-	sve = get_sve(child, &svebuf, &svebufsz);
+	sve = get_sve(child, type, &svebuf, &svebufsz);
 	if (!sve) {
-		ksft_test_result_fail("get_sve: %s\n", strerror(errno));
+		ksft_test_result_fail("get_sve(%s): %s\n",
+				      type->name, strerror(errno));
 
 		return;
 	} else {
-		ksft_test_result_pass("get_sve(FPSIMD)\n");
+		ksft_test_result_pass("get_sve(%s FPSIMD)\n", type->name);
 	}
 
 	ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD,
-			 "Set FPSIMD registers\n");
+			 "Set FPSIMD registers via %s\n", type->name);
 	if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD)
 		goto out;
 
@@ -243,9 +275,9 @@ static void ptrace_sve_fpsimd(pid_t child)
 			p[j] = j;
 	}
 
-	if (set_sve(child, sve)) {
-		ksft_test_result_fail("set_sve(FPSIMD): %s\n",
-				      strerror(errno));
+	if (set_sve(child, type, sve)) {
+		ksft_test_result_fail("set_sve(%s FPSIMD): %s\n",
+				      type->name, strerror(errno));
 
 		goto out;
 	}
@@ -257,16 +289,20 @@ static void ptrace_sve_fpsimd(pid_t child)
 		goto out;
 	}
 	if (memcmp(fpsimd, &new_fpsimd, sizeof(*fpsimd)) == 0)
-		ksft_test_result_pass("get_fpsimd() gave same state\n");
+		ksft_test_result_pass("%s get_fpsimd() gave same state\n",
+				      type->name);
 	else
-		ksft_test_result_fail("get_fpsimd() gave different state\n");
+		ksft_test_result_fail("%s get_fpsimd() gave different state\n",
+				      type->name);
 
 out:
 	free(svebuf);
 }
 
 /* Validate attempting to set SVE data and read SVE data */
-static void ptrace_set_sve_get_sve_data(pid_t child, unsigned int vl)
+static void ptrace_set_sve_get_sve_data(pid_t child,
+					const struct vec_type *type,
+					unsigned int vl)
 {
 	void *write_buf;
 	void *read_buf = NULL;
@@ -281,8 +317,8 @@ static void ptrace_set_sve_get_sve_data(pid_t child, unsigned int vl)
 	data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
 	write_buf = malloc(data_size);
 	if (!write_buf) {
-		ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n",
-				      data_size, vl);
+		ksft_test_result_fail("Error allocating %d byte buffer for %s VL %u\n",
+				      data_size, type->name, vl);
 		return;
 	}
 	write_sve = write_buf;
@@ -306,23 +342,26 @@ static void ptrace_set_sve_get_sve_data(pid_t child, unsigned int vl)
 
 	/* TODO: Generate a valid FFR pattern */
 
-	ret = set_sve(child, write_sve);
+	ret = set_sve(child, type, write_sve);
 	if (ret != 0) {
-		ksft_test_result_fail("Failed to set VL %u data\n", vl);
+		ksft_test_result_fail("Failed to set %s VL %u data\n",
+				      type->name, vl);
 		goto out;
 	}
 
 	/* Read the data back */
-	if (!get_sve(child, (void **)&read_buf, &read_sve_size)) {
-		ksft_test_result_fail("Failed to read VL %u data\n", vl);
+	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);
 		goto out;
 	}
 	read_sve = read_buf;
 
 	/* We might read more data if there's extensions we don't know */
 	if (read_sve->size < write_sve->size) {
-		ksft_test_result_fail("Wrote %d bytes, only read %d\n",
-				      write_sve->size, read_sve->size);
+		ksft_test_result_fail("%s wrote %d bytes, only read %d\n",
+				      type->name, write_sve->size,
+				      read_sve->size);
 		goto out_read;
 	}
 
@@ -349,7 +388,8 @@ static void ptrace_set_sve_get_sve_data(pid_t child, unsigned int vl)
 	check_u32(vl, "FPCR", write_buf + SVE_PT_SVE_FPCR_OFFSET(vq),
 		  read_buf + SVE_PT_SVE_FPCR_OFFSET(vq), &errors);
 
-	ksft_test_result(errors == 0, "Set and get SVE data for VL %u\n", vl);
+	ksft_test_result(errors == 0, "Set and get %s data for VL %u\n",
+			 type->name, vl);
 
 out_read:
 	free(read_buf);
@@ -358,7 +398,9 @@ out:
 }
 
 /* Validate attempting to set SVE data and read SVE data */
-static void ptrace_set_sve_get_fpsimd_data(pid_t child, unsigned int vl)
+static void ptrace_set_sve_get_fpsimd_data(pid_t child,
+					   const struct vec_type *type,
+					   unsigned int vl)
 {
 	void *write_buf;
 	struct user_sve_header *write_sve;
@@ -376,8 +418,8 @@ static void ptrace_set_sve_get_fpsimd_data(pid_t child, unsigned int vl)
 	data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
 	write_buf = malloc(data_size);
 	if (!write_buf) {
-		ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n",
-				      data_size, vl);
+		ksft_test_result_fail("Error allocating %d byte buffer for %s VL %u\n",
+				      data_size, type->name, vl);
 		return;
 	}
 	write_sve = write_buf;
@@ -395,16 +437,17 @@ static void ptrace_set_sve_get_fpsimd_data(pid_t child, unsigned int vl)
 	fill_buf(write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), SVE_PT_SVE_FPSR_SIZE);
 	fill_buf(write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), SVE_PT_SVE_FPCR_SIZE);
 
-	ret = set_sve(child, write_sve);
+	ret = set_sve(child, type, write_sve);
 	if (ret != 0) {
-		ksft_test_result_fail("Failed to set VL %u data\n", vl);
+		ksft_test_result_fail("Failed to set %s VL %u data\n",
+				      type->name, vl);
 		goto out;
 	}
 
 	/* Read the data back */
 	if (get_fpsimd(child, &fpsimd_state)) {
-		ksft_test_result_fail("Failed to read VL %u FPSIMD data\n",
-				      vl);
+		ksft_test_result_fail("Failed to read %s VL %u FPSIMD data\n",
+				      type->name, vl);
 		goto out;
 	}
 
@@ -419,7 +462,8 @@ static void ptrace_set_sve_get_fpsimd_data(pid_t child, unsigned int vl)
 		       sizeof(tmp));
 
 		if (tmp != fpsimd_state.vregs[i]) {
-			printf("# Mismatch in FPSIMD for VL %u Z%d\n", vl, i);
+			printf("# Mismatch in FPSIMD for %s VL %u Z%d\n",
+			       type->name, vl, i);
 			errors++;
 		}
 	}
@@ -429,8 +473,8 @@ static void ptrace_set_sve_get_fpsimd_data(pid_t child, unsigned int vl)
 	check_u32(vl, "FPCR", write_buf + SVE_PT_SVE_FPCR_OFFSET(vq),
 		  &fpsimd_state.fpcr, &errors);
 
-	ksft_test_result(errors == 0, "Set and get FPSIMD data for VL %u\n",
-			 vl);
+	ksft_test_result(errors == 0, "Set and get FPSIMD data for %s VL %u\n",
+			 type->name, vl);
 
 out:
 	free(write_buf);
@@ -440,7 +484,7 @@ static int do_parent(pid_t child)
 {
 	int ret = EXIT_FAILURE;
 	pid_t pid;
-	int status;
+	int status, i;
 	siginfo_t si;
 	unsigned int vq, vl;
 	bool vl_supported;
@@ -499,26 +543,47 @@ static int do_parent(pid_t child)
 		}
 	}
 
-	/* FPSIMD via SVE regset */
-	ptrace_sve_fpsimd(child);
-
-	/* prctl() flags */
-	ptrace_set_get_inherit(child);
-
-	/* Step through every possible VQ */
-	for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
-		vl = sve_vl_from_vq(vq);
+	for (i = 0; i < ARRAY_SIZE(vec_types); i++) {
+		/* FPSIMD via SVE regset */
+		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",
+					      vec_types[i].name);
+		}
 
-		/* First, try to set this vector length */
-		ptrace_set_get_vl(child, vl, &vl_supported);
+		/* prctl() flags */
+		ptrace_set_get_inherit(child, &vec_types[i]);
+
+		/* 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 */
+			if (getauxval(vec_types[i].hwcap_type) &
+			    vec_types[i].hwcap) {
+				ptrace_set_get_vl(child, &vec_types[i], vl,
+						  &vl_supported);
+			} else {
+				ksft_test_result_skip("%s get/set VL %d\n",
+						      vec_types[i].name, vl);
+				vl_supported = false;
+			}
 
-		/* If the VL is supported validate data set/get */
-		if (vl_supported) {
-			ptrace_set_sve_get_sve_data(child, vl);
-			ptrace_set_sve_get_fpsimd_data(child, vl);
-		} else {
-			ksft_test_result_skip("set SVE get SVE for VL %d\n", vl);
-			ksft_test_result_skip("set SVE get FPSIMD for VL %d\n", vl);
+			/* If the VL is supported validate data set/get */
+			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);
+			} 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);
+			}
 		}
 	}
 
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c
index 22722abc9dfa9..2f8c23af3b5e0 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.c
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c
@@ -310,14 +310,12 @@ int test_setup(struct tdescr *td)
 
 int test_run(struct tdescr *td)
 {
-	if (td->sig_trig) {
-		if (td->trigger)
-			return td->trigger(td);
-		else
-			return default_trigger(td);
-	} else {
+	if (td->trigger)
+		return td->trigger(td);
+	else if (td->sig_trig)
+		return default_trigger(td);
+	else
 		return td->run(td, NULL, NULL);
-	}
 }
 
 void test_result(struct tdescr *td)
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index 4d347bc53aa28..359f3e8f8b604 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -1078,7 +1078,7 @@
 	.errstr_unpriv = "R0 pointer -= pointer prohibited",
 },
 {
-	"map access: trying to leak tained dst reg",
+	"map access: trying to leak tainted dst reg",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 623cec04ad422..0cf7e90c0052e 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -221,7 +221,7 @@ int cg_find_unified_root(char *root, size_t len)
 
 int cg_create(const char *cgroup)
 {
-	return mkdir(cgroup, 0644);
+	return mkdir(cgroup, 0755);
 }
 
 int cg_wait_for_proc_count(const char *cgroup, int count)
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 3df648c378765..6001235030631 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -1,11 +1,14 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
+#define _GNU_SOURCE
 #include <linux/limits.h>
+#include <linux/sched.h>
 #include <sys/types.h>
 #include <sys/mman.h>
 #include <sys/wait.h>
 #include <unistd.h>
 #include <fcntl.h>
+#include <sched.h>
 #include <stdio.h>
 #include <errno.h>
 #include <signal.h>
@@ -674,6 +677,166 @@ cleanup:
 	return ret;
 }
 
+/*
+ * cgroup migration permission check should be performed based on the
+ * credentials at the time of open instead of write.
+ */
+static int test_cgcore_lesser_euid_open(const char *root)
+{
+	const uid_t test_euid = 65534;	/* usually nobody, any !root is fine */
+	int ret = KSFT_FAIL;
+	char *cg_test_a = NULL, *cg_test_b = NULL;
+	char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL;
+	int cg_test_b_procs_fd = -1;
+	uid_t saved_uid;
+
+	cg_test_a = cg_name(root, "cg_test_a");
+	cg_test_b = cg_name(root, "cg_test_b");
+
+	if (!cg_test_a || !cg_test_b)
+		goto cleanup;
+
+	cg_test_a_procs = cg_name(cg_test_a, "cgroup.procs");
+	cg_test_b_procs = cg_name(cg_test_b, "cgroup.procs");
+
+	if (!cg_test_a_procs || !cg_test_b_procs)
+		goto cleanup;
+
+	if (cg_create(cg_test_a) || cg_create(cg_test_b))
+		goto cleanup;
+
+	if (cg_enter_current(cg_test_a))
+		goto cleanup;
+
+	if (chown(cg_test_a_procs, test_euid, -1) ||
+	    chown(cg_test_b_procs, test_euid, -1))
+		goto cleanup;
+
+	saved_uid = geteuid();
+	if (seteuid(test_euid))
+		goto cleanup;
+
+	cg_test_b_procs_fd = open(cg_test_b_procs, O_RDWR);
+
+	if (seteuid(saved_uid))
+		goto cleanup;
+
+	if (cg_test_b_procs_fd < 0)
+		goto cleanup;
+
+	if (write(cg_test_b_procs_fd, "0", 1) >= 0 || errno != EACCES)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (cg_test_b_procs_fd >= 0)
+		close(cg_test_b_procs_fd);
+	if (cg_test_b)
+		cg_destroy(cg_test_b);
+	if (cg_test_a)
+		cg_destroy(cg_test_a);
+	free(cg_test_b_procs);
+	free(cg_test_a_procs);
+	free(cg_test_b);
+	free(cg_test_a);
+	return ret;
+}
+
+struct lesser_ns_open_thread_arg {
+	const char	*path;
+	int		fd;
+	int		err;
+};
+
+static int lesser_ns_open_thread_fn(void *arg)
+{
+	struct lesser_ns_open_thread_arg *targ = arg;
+
+	targ->fd = open(targ->path, O_RDWR);
+	targ->err = errno;
+	return 0;
+}
+
+/*
+ * cgroup migration permission check should be performed based on the cgroup
+ * namespace at the time of open instead of write.
+ */
+static int test_cgcore_lesser_ns_open(const char *root)
+{
+	static char stack[65536];
+	const uid_t test_euid = 65534;	/* usually nobody, any !root is fine */
+	int ret = KSFT_FAIL;
+	char *cg_test_a = NULL, *cg_test_b = NULL;
+	char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL;
+	int cg_test_b_procs_fd = -1;
+	struct lesser_ns_open_thread_arg targ = { .fd = -1 };
+	pid_t pid;
+	int status;
+
+	cg_test_a = cg_name(root, "cg_test_a");
+	cg_test_b = cg_name(root, "cg_test_b");
+
+	if (!cg_test_a || !cg_test_b)
+		goto cleanup;
+
+	cg_test_a_procs = cg_name(cg_test_a, "cgroup.procs");
+	cg_test_b_procs = cg_name(cg_test_b, "cgroup.procs");
+
+	if (!cg_test_a_procs || !cg_test_b_procs)
+		goto cleanup;
+
+	if (cg_create(cg_test_a) || cg_create(cg_test_b))
+		goto cleanup;
+
+	if (cg_enter_current(cg_test_b))
+		goto cleanup;
+
+	if (chown(cg_test_a_procs, test_euid, -1) ||
+	    chown(cg_test_b_procs, test_euid, -1))
+		goto cleanup;
+
+	targ.path = cg_test_b_procs;
+	pid = clone(lesser_ns_open_thread_fn, stack + sizeof(stack),
+		    CLONE_NEWCGROUP | CLONE_FILES | CLONE_VM | SIGCHLD,
+		    &targ);
+	if (pid < 0)
+		goto cleanup;
+
+	if (waitpid(pid, &status, 0) < 0)
+		goto cleanup;
+
+	if (!WIFEXITED(status))
+		goto cleanup;
+
+	cg_test_b_procs_fd = targ.fd;
+	if (cg_test_b_procs_fd < 0)
+		goto cleanup;
+
+	if (cg_enter_current(cg_test_a))
+		goto cleanup;
+
+	if ((status = write(cg_test_b_procs_fd, "0", 1)) >= 0 || errno != ENOENT)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (cg_test_b_procs_fd >= 0)
+		close(cg_test_b_procs_fd);
+	if (cg_test_b)
+		cg_destroy(cg_test_b);
+	if (cg_test_a)
+		cg_destroy(cg_test_a);
+	free(cg_test_b_procs);
+	free(cg_test_a_procs);
+	free(cg_test_b);
+	free(cg_test_a);
+	return ret;
+}
+
 #define T(x) { x, #x }
 struct corecg_test {
 	int (*fn)(const char *root);
@@ -689,6 +852,8 @@ struct corecg_test {
 	T(test_cgcore_proc_migration),
 	T(test_cgcore_thread_migration),
 	T(test_cgcore_destroy),
+	T(test_cgcore_lesser_euid_open),
+	T(test_cgcore_lesser_ns_open),
 };
 #undef T
 
diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh
index 75528788cb95e..75528788cb95e 100644..100755
--- a/tools/testing/selftests/net/amt.sh
+++ b/tools/testing/selftests/net/amt.sh
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index 3ea73013d9568..6f05e06f67613 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -193,7 +193,8 @@ for family in 4 6; do
 		SUFFIX="64 nodad"
 		VXDEV=vxlan6
 		IPT=ip6tables
-		PING="ping6"
+		# Use ping6 on systems where ping doesn't handle IPv6
+		ping -w 1 -c 1 ::1 > /dev/null 2>&1 || PING="ping6"
 	fi
 
 	echo "IPv$family"
diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile
index 7f12d55b97f86..2956584e1e37f 100644
--- a/tools/testing/selftests/sgx/Makefile
+++ b/tools/testing/selftests/sgx/Makefile
@@ -45,7 +45,7 @@ $(OUTPUT)/sign_key.o: sign_key.S
 	$(CC) $(HOST_CFLAGS) -c $< -o $@
 
 $(OUTPUT)/test_encl.elf: test_encl.lds test_encl.c test_encl_bootstrap.S
-	$(CC) $(ENCL_CFLAGS) -T $^ -o $@
+	$(CC) $(ENCL_CFLAGS) -T $^ -o $@ -Wl,--build-id=none
 
 EXTRA_CLEAN := \
 	$(OUTPUT)/test_encl.elf \
diff --git a/tools/testing/selftests/sgx/defines.h b/tools/testing/selftests/sgx/defines.h
index f88562afcaa08..02d775789ea7b 100644
--- a/tools/testing/selftests/sgx/defines.h
+++ b/tools/testing/selftests/sgx/defines.h
@@ -19,13 +19,38 @@
 #include "../../../../arch/x86/include/uapi/asm/sgx.h"
 
 enum encl_op_type {
-	ENCL_OP_PUT,
-	ENCL_OP_GET,
+	ENCL_OP_PUT_TO_BUFFER,
+	ENCL_OP_GET_FROM_BUFFER,
+	ENCL_OP_PUT_TO_ADDRESS,
+	ENCL_OP_GET_FROM_ADDRESS,
+	ENCL_OP_NOP,
+	ENCL_OP_MAX,
 };
 
-struct encl_op {
+struct encl_op_header {
 	uint64_t type;
-	uint64_t buffer;
+};
+
+struct encl_op_put_to_buf {
+	struct encl_op_header header;
+	uint64_t value;
+};
+
+struct encl_op_get_from_buf {
+	struct encl_op_header header;
+	uint64_t value;
+};
+
+struct encl_op_put_to_addr {
+	struct encl_op_header header;
+	uint64_t value;
+	uint64_t addr;
+};
+
+struct encl_op_get_from_addr {
+	struct encl_op_header header;
+	uint64_t value;
+	uint64_t addr;
 };
 
 #endif /* DEFINES_H */
diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c
index 3ebe5d1fe3370..9d4322c946e2b 100644
--- a/tools/testing/selftests/sgx/load.c
+++ b/tools/testing/selftests/sgx/load.c
@@ -21,6 +21,8 @@
 
 void encl_delete(struct encl *encl)
 {
+	struct encl_segment *heap_seg = &encl->segment_tbl[encl->nr_segments - 1];
+
 	if (encl->encl_base)
 		munmap((void *)encl->encl_base, encl->encl_size);
 
@@ -30,6 +32,8 @@ void encl_delete(struct encl *encl)
 	if (encl->fd)
 		close(encl->fd);
 
+	munmap(heap_seg->src, heap_seg->size);
+
 	if (encl->segment_tbl)
 		free(encl->segment_tbl);
 
@@ -107,11 +111,14 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg)
 	memset(&secinfo, 0, sizeof(secinfo));
 	secinfo.flags = seg->flags;
 
-	ioc.src = (uint64_t)encl->src + seg->offset;
+	ioc.src = (uint64_t)seg->src;
 	ioc.offset = seg->offset;
 	ioc.length = seg->size;
 	ioc.secinfo = (unsigned long)&secinfo;
-	ioc.flags = SGX_PAGE_MEASURE;
+	if (seg->measure)
+		ioc.flags = SGX_PAGE_MEASURE;
+	else
+		ioc.flags = 0;
 
 	rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_ADD_PAGES, &ioc);
 	if (rc < 0) {
@@ -122,11 +129,10 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg)
 	return true;
 }
 
-
-
-bool encl_load(const char *path, struct encl *encl)
+bool encl_load(const char *path, struct encl *encl, unsigned long heap_size)
 {
 	const char device_path[] = "/dev/sgx_enclave";
+	struct encl_segment *seg;
 	Elf64_Phdr *phdr_tbl;
 	off_t src_offset;
 	Elf64_Ehdr *ehdr;
@@ -178,6 +184,8 @@ bool encl_load(const char *path, struct encl *encl)
 	ehdr = encl->bin;
 	phdr_tbl = encl->bin + ehdr->e_phoff;
 
+	encl->nr_segments = 1; /* one for the heap */
+
 	for (i = 0; i < ehdr->e_phnum; i++) {
 		Elf64_Phdr *phdr = &phdr_tbl[i];
 
@@ -193,7 +201,6 @@ bool encl_load(const char *path, struct encl *encl)
 	for (i = 0, j = 0; i < ehdr->e_phnum; i++) {
 		Elf64_Phdr *phdr = &phdr_tbl[i];
 		unsigned int flags = phdr->p_flags;
-		struct encl_segment *seg;
 
 		if (phdr->p_type != PT_LOAD)
 			continue;
@@ -216,6 +223,7 @@ bool encl_load(const char *path, struct encl *encl)
 
 		if (j == 0) {
 			src_offset = phdr->p_offset & PAGE_MASK;
+			encl->src = encl->bin + src_offset;
 
 			seg->prot = PROT_READ | PROT_WRITE;
 			seg->flags = SGX_PAGE_TYPE_TCS << 8;
@@ -228,15 +236,27 @@ bool encl_load(const char *path, struct encl *encl)
 
 		seg->offset = (phdr->p_offset & PAGE_MASK) - src_offset;
 		seg->size = (phdr->p_filesz + PAGE_SIZE - 1) & PAGE_MASK;
+		seg->src = encl->src + seg->offset;
+		seg->measure = true;
 
 		j++;
 	}
 
-	assert(j == encl->nr_segments);
+	assert(j == encl->nr_segments - 1);
+
+	seg = &encl->segment_tbl[j];
+	seg->offset =  encl->segment_tbl[j - 1].offset + encl->segment_tbl[j - 1].size;
+	seg->size = heap_size;
+	seg->src = mmap(NULL, heap_size, PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	seg->prot = PROT_READ | PROT_WRITE;
+	seg->flags = (SGX_PAGE_TYPE_REG << 8) | seg->prot;
+	seg->measure = false;
+
+	if (seg->src == MAP_FAILED)
+		goto err;
 
-	encl->src = encl->bin + src_offset;
-	encl->src_size = encl->segment_tbl[j - 1].offset +
-			 encl->segment_tbl[j - 1].size;
+	encl->src_size = encl->segment_tbl[j].offset + encl->segment_tbl[j].size;
 
 	for (encl->encl_size = 4096; encl->encl_size < encl->src_size; )
 		encl->encl_size <<= 1;
diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c
index e252015e0c154..370c4995f7c4a 100644
--- a/tools/testing/selftests/sgx/main.c
+++ b/tools/testing/selftests/sgx/main.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*  Copyright(c) 2016-20 Intel Corporation. */
 
+#include <cpuid.h>
 #include <elf.h>
 #include <errno.h>
 #include <fcntl.h>
@@ -21,6 +22,7 @@
 #include "main.h"
 
 static const uint64_t MAGIC = 0x1122334455667788ULL;
+static const uint64_t MAGIC2 = 0x8877665544332211ULL;
 vdso_sgx_enter_enclave_t vdso_sgx_enter_enclave;
 
 struct vdso_symtab {
@@ -107,12 +109,32 @@ static Elf64_Sym *vdso_symtab_get(struct vdso_symtab *symtab, const char *name)
 	return NULL;
 }
 
+/*
+ * Return the offset in the enclave where the data segment can be found.
+ * The first RW segment loaded is the TCS, skip that to get info on the
+ * data segment.
+ */
+static off_t encl_get_data_offset(struct encl *encl)
+{
+	int i;
+
+	for (i = 1; i < encl->nr_segments; i++) {
+		struct encl_segment *seg = &encl->segment_tbl[i];
+
+		if (seg->prot == (PROT_READ | PROT_WRITE))
+			return seg->offset;
+	}
+
+	return -1;
+}
+
 FIXTURE(enclave) {
 	struct encl encl;
 	struct sgx_enclave_run run;
 };
 
-FIXTURE_SETUP(enclave)
+static bool setup_test_encl(unsigned long heap_size, struct encl *encl,
+			    struct __test_metadata *_metadata)
 {
 	Elf64_Sym *sgx_enter_enclave_sym = NULL;
 	struct vdso_symtab symtab;
@@ -122,31 +144,25 @@ FIXTURE_SETUP(enclave)
 	unsigned int i;
 	void *addr;
 
-	if (!encl_load("test_encl.elf", &self->encl)) {
-		encl_delete(&self->encl);
-		ksft_exit_skip("cannot load enclaves\n");
+	if (!encl_load("test_encl.elf", encl, heap_size)) {
+		encl_delete(encl);
+		TH_LOG("Failed to load the test enclave.\n");
 	}
 
-	for (i = 0; i < self->encl.nr_segments; i++) {
-		seg = &self->encl.segment_tbl[i];
-
-		TH_LOG("0x%016lx 0x%016lx 0x%02x", seg->offset, seg->size, seg->prot);
-	}
-
-	if (!encl_measure(&self->encl))
+	if (!encl_measure(encl))
 		goto err;
 
-	if (!encl_build(&self->encl))
+	if (!encl_build(encl))
 		goto err;
 
 	/*
 	 * An enclave consumer only must do this.
 	 */
-	for (i = 0; i < self->encl.nr_segments; i++) {
-		struct encl_segment *seg = &self->encl.segment_tbl[i];
+	for (i = 0; i < encl->nr_segments; i++) {
+		struct encl_segment *seg = &encl->segment_tbl[i];
 
-		addr = mmap((void *)self->encl.encl_base + seg->offset, seg->size,
-			    seg->prot, MAP_SHARED | MAP_FIXED, self->encl.fd, 0);
+		addr = mmap((void *)encl->encl_base + seg->offset, seg->size,
+			    seg->prot, MAP_SHARED | MAP_FIXED, encl->fd, 0);
 		EXPECT_NE(addr, MAP_FAILED);
 		if (addr == MAP_FAILED)
 			goto err;
@@ -166,8 +182,16 @@ FIXTURE_SETUP(enclave)
 
 	vdso_sgx_enter_enclave = addr + sgx_enter_enclave_sym->st_value;
 
-	memset(&self->run, 0, sizeof(self->run));
-	self->run.tcs = self->encl.encl_base;
+	return true;
+
+err:
+	encl_delete(encl);
+
+	for (i = 0; i < encl->nr_segments; i++) {
+		seg = &encl->segment_tbl[i];
+
+		TH_LOG("0x%016lx 0x%016lx 0x%02x", seg->offset, seg->size, seg->prot);
+	}
 
 	maps_file = fopen("/proc/self/maps", "r");
 	if (maps_file != NULL)  {
@@ -181,11 +205,13 @@ FIXTURE_SETUP(enclave)
 		fclose(maps_file);
 	}
 
-err:
-	if (!sgx_enter_enclave_sym)
-		encl_delete(&self->encl);
+	TH_LOG("Failed to initialize the test enclave.\n");
+
+	return false;
+}
 
-	ASSERT_NE(sgx_enter_enclave_sym, NULL);
+FIXTURE_SETUP(enclave)
+{
 }
 
 FIXTURE_TEARDOWN(enclave)
@@ -215,44 +241,130 @@ FIXTURE_TEARDOWN(enclave)
 
 TEST_F(enclave, unclobbered_vdso)
 {
-	struct encl_op op;
+	struct encl_op_get_from_buf get_op;
+	struct encl_op_put_to_buf put_op;
+
+	ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata));
+
+	memset(&self->run, 0, sizeof(self->run));
+	self->run.tcs = self->encl.encl_base;
+
+	put_op.header.type = ENCL_OP_PUT_TO_BUFFER;
+	put_op.value = MAGIC;
+
+	EXPECT_EQ(ENCL_CALL(&put_op, &self->run, false), 0);
+
+	EXPECT_EEXIT(&self->run);
+	EXPECT_EQ(self->run.user_data, 0);
+
+	get_op.header.type = ENCL_OP_GET_FROM_BUFFER;
+	get_op.value = 0;
+
+	EXPECT_EQ(ENCL_CALL(&get_op, &self->run, false), 0);
+
+	EXPECT_EQ(get_op.value, MAGIC);
+	EXPECT_EEXIT(&self->run);
+	EXPECT_EQ(self->run.user_data, 0);
+}
+
+/*
+ * A section metric is concatenated in a way that @low bits 12-31 define the
+ * bits 12-31 of the metric and @high bits 0-19 define the bits 32-51 of the
+ * metric.
+ */
+static unsigned long sgx_calc_section_metric(unsigned int low,
+					     unsigned int high)
+{
+	return (low & GENMASK_ULL(31, 12)) +
+	       ((high & GENMASK_ULL(19, 0)) << 32);
+}
+
+/*
+ * Sum total available physical SGX memory across all EPC sections
+ *
+ * Return: total available physical SGX memory available on system
+ */
+static unsigned long get_total_epc_mem(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	unsigned long total_size = 0;
+	unsigned int type;
+	int section = 0;
+
+	while (true) {
+		__cpuid_count(SGX_CPUID, section + SGX_CPUID_EPC, eax, ebx, ecx, edx);
+
+		type = eax & SGX_CPUID_EPC_MASK;
+		if (type == SGX_CPUID_EPC_INVALID)
+			break;
 
-	op.type = ENCL_OP_PUT;
-	op.buffer = MAGIC;
+		if (type != SGX_CPUID_EPC_SECTION)
+			break;
 
-	EXPECT_EQ(ENCL_CALL(&op, &self->run, false), 0);
+		total_size += sgx_calc_section_metric(ecx, edx);
+
+		section++;
+	}
+
+	return total_size;
+}
+
+TEST_F(enclave, unclobbered_vdso_oversubscribed)
+{
+	struct encl_op_get_from_buf get_op;
+	struct encl_op_put_to_buf put_op;
+	unsigned long total_mem;
+
+	total_mem = get_total_epc_mem();
+	ASSERT_NE(total_mem, 0);
+	ASSERT_TRUE(setup_test_encl(total_mem, &self->encl, _metadata));
+
+	memset(&self->run, 0, sizeof(self->run));
+	self->run.tcs = self->encl.encl_base;
+
+	put_op.header.type = ENCL_OP_PUT_TO_BUFFER;
+	put_op.value = MAGIC;
+
+	EXPECT_EQ(ENCL_CALL(&put_op, &self->run, false), 0);
 
 	EXPECT_EEXIT(&self->run);
 	EXPECT_EQ(self->run.user_data, 0);
 
-	op.type = ENCL_OP_GET;
-	op.buffer = 0;
+	get_op.header.type = ENCL_OP_GET_FROM_BUFFER;
+	get_op.value = 0;
 
-	EXPECT_EQ(ENCL_CALL(&op, &self->run, false), 0);
+	EXPECT_EQ(ENCL_CALL(&get_op, &self->run, false), 0);
 
-	EXPECT_EQ(op.buffer, MAGIC);
+	EXPECT_EQ(get_op.value, MAGIC);
 	EXPECT_EEXIT(&self->run);
 	EXPECT_EQ(self->run.user_data, 0);
+
 }
 
 TEST_F(enclave, clobbered_vdso)
 {
-	struct encl_op op;
+	struct encl_op_get_from_buf get_op;
+	struct encl_op_put_to_buf put_op;
 
-	op.type = ENCL_OP_PUT;
-	op.buffer = MAGIC;
+	ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata));
 
-	EXPECT_EQ(ENCL_CALL(&op, &self->run, true), 0);
+	memset(&self->run, 0, sizeof(self->run));
+	self->run.tcs = self->encl.encl_base;
+
+	put_op.header.type = ENCL_OP_PUT_TO_BUFFER;
+	put_op.value = MAGIC;
+
+	EXPECT_EQ(ENCL_CALL(&put_op, &self->run, true), 0);
 
 	EXPECT_EEXIT(&self->run);
 	EXPECT_EQ(self->run.user_data, 0);
 
-	op.type = ENCL_OP_GET;
-	op.buffer = 0;
+	get_op.header.type = ENCL_OP_GET_FROM_BUFFER;
+	get_op.value = 0;
 
-	EXPECT_EQ(ENCL_CALL(&op, &self->run, true), 0);
+	EXPECT_EQ(ENCL_CALL(&get_op, &self->run, true), 0);
 
-	EXPECT_EQ(op.buffer, MAGIC);
+	EXPECT_EQ(get_op.value, MAGIC);
 	EXPECT_EEXIT(&self->run);
 	EXPECT_EQ(self->run.user_data, 0);
 }
@@ -267,27 +379,179 @@ static int test_handler(long rdi, long rsi, long rdx, long ursp, long r8, long r
 
 TEST_F(enclave, clobbered_vdso_and_user_function)
 {
-	struct encl_op op;
+	struct encl_op_get_from_buf get_op;
+	struct encl_op_put_to_buf put_op;
+
+	ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata));
+
+	memset(&self->run, 0, sizeof(self->run));
+	self->run.tcs = self->encl.encl_base;
 
 	self->run.user_handler = (__u64)test_handler;
 	self->run.user_data = 0xdeadbeef;
 
-	op.type = ENCL_OP_PUT;
-	op.buffer = MAGIC;
+	put_op.header.type = ENCL_OP_PUT_TO_BUFFER;
+	put_op.value = MAGIC;
 
-	EXPECT_EQ(ENCL_CALL(&op, &self->run, true), 0);
+	EXPECT_EQ(ENCL_CALL(&put_op, &self->run, true), 0);
 
 	EXPECT_EEXIT(&self->run);
 	EXPECT_EQ(self->run.user_data, 0);
 
-	op.type = ENCL_OP_GET;
-	op.buffer = 0;
+	get_op.header.type = ENCL_OP_GET_FROM_BUFFER;
+	get_op.value = 0;
 
-	EXPECT_EQ(ENCL_CALL(&op, &self->run, true), 0);
+	EXPECT_EQ(ENCL_CALL(&get_op, &self->run, true), 0);
 
-	EXPECT_EQ(op.buffer, MAGIC);
+	EXPECT_EQ(get_op.value, MAGIC);
 	EXPECT_EEXIT(&self->run);
 	EXPECT_EQ(self->run.user_data, 0);
 }
 
+/*
+ * Sanity check that it is possible to enter either of the two hardcoded TCS
+ */
+TEST_F(enclave, tcs_entry)
+{
+	struct encl_op_header op;
+
+	ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata));
+
+	memset(&self->run, 0, sizeof(self->run));
+	self->run.tcs = self->encl.encl_base;
+
+	op.type = ENCL_OP_NOP;
+
+	EXPECT_EQ(ENCL_CALL(&op, &self->run, true), 0);
+
+	EXPECT_EEXIT(&self->run);
+	EXPECT_EQ(self->run.exception_vector, 0);
+	EXPECT_EQ(self->run.exception_error_code, 0);
+	EXPECT_EQ(self->run.exception_addr, 0);
+
+	/* Move to the next TCS. */
+	self->run.tcs = self->encl.encl_base + PAGE_SIZE;
+
+	EXPECT_EQ(ENCL_CALL(&op, &self->run, true), 0);
+
+	EXPECT_EEXIT(&self->run);
+	EXPECT_EQ(self->run.exception_vector, 0);
+	EXPECT_EQ(self->run.exception_error_code, 0);
+	EXPECT_EQ(self->run.exception_addr, 0);
+}
+
+/*
+ * Second page of .data segment is used to test changing PTE permissions.
+ * This spans the local encl_buffer within the test enclave.
+ *
+ * 1) Start with a sanity check: a value is written to the target page within
+ *    the enclave and read back to ensure target page can be written to.
+ * 2) Change PTE permissions (RW -> RO) of target page within enclave.
+ * 3) Repeat (1) - this time expecting a regular #PF communicated via the
+ *    vDSO.
+ * 4) Change PTE permissions of target page within enclave back to be RW.
+ * 5) Repeat (1) by resuming enclave, now expected to be possible to write to
+ *    and read from target page within enclave.
+ */
+TEST_F(enclave, pte_permissions)
+{
+	struct encl_op_get_from_addr get_addr_op;
+	struct encl_op_put_to_addr put_addr_op;
+	unsigned long data_start;
+	int ret;
+
+	ASSERT_TRUE(setup_test_encl(ENCL_HEAP_SIZE_DEFAULT, &self->encl, _metadata));
+
+	memset(&self->run, 0, sizeof(self->run));
+	self->run.tcs = self->encl.encl_base;
+
+	data_start = self->encl.encl_base +
+		     encl_get_data_offset(&self->encl) +
+		     PAGE_SIZE;
+
+	/*
+	 * Sanity check to ensure it is possible to write to page that will
+	 * have its permissions manipulated.
+	 */
+
+	/* Write MAGIC to page */
+	put_addr_op.value = MAGIC;
+	put_addr_op.addr = data_start;
+	put_addr_op.header.type = ENCL_OP_PUT_TO_ADDRESS;
+
+	EXPECT_EQ(ENCL_CALL(&put_addr_op, &self->run, true), 0);
+
+	EXPECT_EEXIT(&self->run);
+	EXPECT_EQ(self->run.exception_vector, 0);
+	EXPECT_EQ(self->run.exception_error_code, 0);
+	EXPECT_EQ(self->run.exception_addr, 0);
+
+	/*
+	 * Read memory that was just written to, confirming that it is the
+	 * value previously written (MAGIC).
+	 */
+	get_addr_op.value = 0;
+	get_addr_op.addr = data_start;
+	get_addr_op.header.type = ENCL_OP_GET_FROM_ADDRESS;
+
+	EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0);
+
+	EXPECT_EQ(get_addr_op.value, MAGIC);
+	EXPECT_EEXIT(&self->run);
+	EXPECT_EQ(self->run.exception_vector, 0);
+	EXPECT_EQ(self->run.exception_error_code, 0);
+	EXPECT_EQ(self->run.exception_addr, 0);
+
+	/* Change PTE permissions of target page within the enclave */
+	ret = mprotect((void *)data_start, PAGE_SIZE, PROT_READ);
+	if (ret)
+		perror("mprotect");
+
+	/*
+	 * PTE permissions of target page changed to read-only, EPCM
+	 * permissions unchanged (EPCM permissions are RW), attempt to
+	 * write to the page, expecting a regular #PF.
+	 */
+
+	put_addr_op.value = MAGIC2;
+
+	EXPECT_EQ(ENCL_CALL(&put_addr_op, &self->run, true), 0);
+
+	EXPECT_EQ(self->run.exception_vector, 14);
+	EXPECT_EQ(self->run.exception_error_code, 0x7);
+	EXPECT_EQ(self->run.exception_addr, data_start);
+
+	self->run.exception_vector = 0;
+	self->run.exception_error_code = 0;
+	self->run.exception_addr = 0;
+
+	/*
+	 * Change PTE permissions back to enable enclave to write to the
+	 * target page and resume enclave - do not expect any exceptions this
+	 * time.
+	 */
+	ret = mprotect((void *)data_start, PAGE_SIZE, PROT_READ | PROT_WRITE);
+	if (ret)
+		perror("mprotect");
+
+	EXPECT_EQ(vdso_sgx_enter_enclave((unsigned long)&put_addr_op, 0,
+					 0, ERESUME, 0, 0, &self->run),
+		 0);
+
+	EXPECT_EEXIT(&self->run);
+	EXPECT_EQ(self->run.exception_vector, 0);
+	EXPECT_EQ(self->run.exception_error_code, 0);
+	EXPECT_EQ(self->run.exception_addr, 0);
+
+	get_addr_op.value = 0;
+
+	EXPECT_EQ(ENCL_CALL(&get_addr_op, &self->run, true), 0);
+
+	EXPECT_EQ(get_addr_op.value, MAGIC2);
+	EXPECT_EEXIT(&self->run);
+	EXPECT_EQ(self->run.exception_vector, 0);
+	EXPECT_EQ(self->run.exception_error_code, 0);
+	EXPECT_EQ(self->run.exception_addr, 0);
+}
+
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/sgx/main.h b/tools/testing/selftests/sgx/main.h
index 68672fd86cf94..b45c52ec7ab3b 100644
--- a/tools/testing/selftests/sgx/main.h
+++ b/tools/testing/selftests/sgx/main.h
@@ -6,11 +6,15 @@
 #ifndef MAIN_H
 #define MAIN_H
 
+#define ENCL_HEAP_SIZE_DEFAULT	4096
+
 struct encl_segment {
+	void *src;
 	off_t offset;
 	size_t size;
 	unsigned int prot;
 	unsigned int flags;
+	bool measure;
 };
 
 struct encl {
@@ -31,7 +35,7 @@ extern unsigned char sign_key[];
 extern unsigned char sign_key_end[];
 
 void encl_delete(struct encl *ctx);
-bool encl_load(const char *path, struct encl *encl);
+bool encl_load(const char *path, struct encl *encl, unsigned long heap_size);
 bool encl_measure(struct encl *encl);
 bool encl_build(struct encl *encl);
 
diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c
index 92bbc5a15c39f..50c5ab1aa6fa1 100644
--- a/tools/testing/selftests/sgx/sigstruct.c
+++ b/tools/testing/selftests/sgx/sigstruct.c
@@ -289,15 +289,17 @@ static bool mrenclave_eextend(EVP_MD_CTX *ctx, uint64_t offset,
 static bool mrenclave_segment(EVP_MD_CTX *ctx, struct encl *encl,
 			      struct encl_segment *seg)
 {
-	uint64_t end = seg->offset + seg->size;
+	uint64_t end = seg->size;
 	uint64_t offset;
 
-	for (offset = seg->offset; offset < end; offset += PAGE_SIZE) {
-		if (!mrenclave_eadd(ctx, offset, seg->flags))
+	for (offset = 0; offset < end; offset += PAGE_SIZE) {
+		if (!mrenclave_eadd(ctx, seg->offset + offset, seg->flags))
 			return false;
 
-		if (!mrenclave_eextend(ctx, offset, encl->src + offset))
-			return false;
+		if (seg->measure) {
+			if (!mrenclave_eextend(ctx, seg->offset + offset, seg->src + offset))
+				return false;
+		}
 	}
 
 	return true;
diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c
index 734ea52f99244..4fca01cfd8981 100644
--- a/tools/testing/selftests/sgx/test_encl.c
+++ b/tools/testing/selftests/sgx/test_encl.c
@@ -4,6 +4,11 @@
 #include <stddef.h>
 #include "defines.h"
 
+/*
+ * Data buffer spanning two pages that will be placed first in .data
+ * segment. Even if not used internally the second page is needed by
+ * external test manipulating page permissions.
+ */
 static uint8_t encl_buffer[8192] = { 1 };
 
 static void *memcpy(void *dest, const void *src, size_t n)
@@ -16,20 +21,51 @@ static void *memcpy(void *dest, const void *src, size_t n)
 	return dest;
 }
 
-void encl_body(void *rdi,  void *rsi)
+static void do_encl_op_put_to_buf(void *op)
+{
+	struct encl_op_put_to_buf *op2 = op;
+
+	memcpy(&encl_buffer[0], &op2->value, 8);
+}
+
+static void do_encl_op_get_from_buf(void *op)
 {
-	struct encl_op *op = (struct encl_op *)rdi;
+	struct encl_op_get_from_buf *op2 = op;
+
+	memcpy(&op2->value, &encl_buffer[0], 8);
+}
+
+static void do_encl_op_put_to_addr(void *_op)
+{
+	struct encl_op_put_to_addr *op = _op;
+
+	memcpy((void *)op->addr, &op->value, 8);
+}
 
-	switch (op->type) {
-	case ENCL_OP_PUT:
-		memcpy(&encl_buffer[0], &op->buffer, 8);
-		break;
+static void do_encl_op_get_from_addr(void *_op)
+{
+	struct encl_op_get_from_addr *op = _op;
+
+	memcpy(&op->value, (void *)op->addr, 8);
+}
+
+static void do_encl_op_nop(void *_op)
+{
+
+}
+
+void encl_body(void *rdi,  void *rsi)
+{
+	const void (*encl_op_array[ENCL_OP_MAX])(void *) = {
+		do_encl_op_put_to_buf,
+		do_encl_op_get_from_buf,
+		do_encl_op_put_to_addr,
+		do_encl_op_get_from_addr,
+		do_encl_op_nop,
+	};
 
-	case ENCL_OP_GET:
-		memcpy(&op->buffer, &encl_buffer[0], 8);
-		break;
+	struct encl_op_header *op = (struct encl_op_header *)rdi;
 
-	default:
-		break;
-	}
+	if (op->type < ENCL_OP_MAX)
+		(*encl_op_array[op->type])(op);
 }
diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S
index 5d5680d4ea396..82fb0dfcbd238 100644
--- a/tools/testing/selftests/sgx/test_encl_bootstrap.S
+++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S
@@ -12,7 +12,7 @@
 
 	.fill	1, 8, 0			# STATE (set by CPU)
 	.fill	1, 8, 0			# FLAGS
-	.quad	encl_ssa		# OSSA
+	.quad	encl_ssa_tcs1		# OSSA
 	.fill	1, 4, 0			# CSSA (set by CPU)
 	.fill	1, 4, 1			# NSSA
 	.quad	encl_entry		# OENTRY
@@ -23,10 +23,10 @@
 	.fill	1, 4, 0xFFFFFFFF	# GSLIMIT
 	.fill	4024, 1, 0		# Reserved
 
-	# Identical to the previous TCS.
+	# TCS2
 	.fill	1, 8, 0			# STATE (set by CPU)
 	.fill	1, 8, 0			# FLAGS
-	.quad	encl_ssa		# OSSA
+	.quad	encl_ssa_tcs2		# OSSA
 	.fill	1, 4, 0			# CSSA (set by CPU)
 	.fill	1, 4, 1			# NSSA
 	.quad	encl_entry		# OENTRY
@@ -40,8 +40,9 @@
 	.text
 
 encl_entry:
-	# RBX contains the base address for TCS, which is also the first address
-	# inside the enclave. By adding the value of le_stack_end to it, we get
+	# RBX contains the base address for TCS, which is the first address
+	# inside the enclave for TCS #1 and one page into the enclave for
+	# TCS #2. By adding the value of encl_stack to it, we get
 	# the absolute address for the stack.
 	lea	(encl_stack)(%rbx), %rax
 	xchg	%rsp, %rax
@@ -81,9 +82,15 @@ encl_entry:
 
 	.section ".data", "aw"
 
-encl_ssa:
+encl_ssa_tcs1:
+	.space 4096
+encl_ssa_tcs2:
 	.space 4096
 
 	.balign 4096
-	.space 8192
+	# Stack of TCS #1
+	.space 4096
 encl_stack:
+	.balign 4096
+	# Stack of TCS #2
+	.space 4096