Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

125 files changed, 1246 insertions, 681 deletions

diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h
index ccc13e9913..cd8420e8c3 100644
--- a/tools/arch/arm64/include/asm/sysreg.h
+++ b/tools/arch/arm64/include/asm/sysreg.h
@@ -701,18 +701,18 @@
  * Permission Indirection Extension (PIE) permission encodings.
  * Encodings with the _O suffix, have overlays applied (Permission Overlay Extension).
  */
-#define PIE_NONE_O	0x0
-#define PIE_R_O		0x1
-#define PIE_X_O		0x2
-#define PIE_RX_O	0x3
-#define PIE_RW_O	0x5
-#define PIE_RWnX_O	0x6
-#define PIE_RWX_O	0x7
-#define PIE_R		0x8
-#define PIE_GCS		0x9
-#define PIE_RX		0xa
-#define PIE_RW		0xc
-#define PIE_RWX		0xe
+#define PIE_NONE_O	UL(0x0)
+#define PIE_R_O		UL(0x1)
+#define PIE_X_O		UL(0x2)
+#define PIE_RX_O	UL(0x3)
+#define PIE_RW_O	UL(0x5)
+#define PIE_RWnX_O	UL(0x6)
+#define PIE_RWX_O	UL(0x7)
+#define PIE_R		UL(0x8)
+#define PIE_GCS		UL(0x9)
+#define PIE_RX		UL(0xa)
+#define PIE_RW		UL(0xc)
+#define PIE_RWX		UL(0xe)
 
 #define PIRx_ELx_PERM(idx, perm)	((perm) << ((idx) * 4))
 
diff --git a/tools/arch/x86/intel_sdsi/intel_sdsi.c b/tools/arch/x86/intel_sdsi/intel_sdsi.c
index 2cd92761f1..ba2a6b6645 100644
--- a/tools/arch/x86/intel_sdsi/intel_sdsi.c
+++ b/tools/arch/x86/intel_sdsi/intel_sdsi.c
@@ -43,7 +43,6 @@
 #define METER_CERT_MAX_SIZE	4096
 #define STATE_MAX_NUM_LICENSES	16
 #define STATE_MAX_NUM_IN_BUNDLE	(uint32_t)8
-#define METER_MAX_NUM_BUNDLES	8
 
 #define __round_mask(x, y) ((__typeof__(x))((y) - 1))
 #define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
@@ -154,11 +153,12 @@ struct bundle_encoding {
 };
 
 struct meter_certificate {
-	uint32_t block_signature;
-	uint32_t counter_unit;
+	uint32_t signature;
+	uint32_t version;
 	uint64_t ppin;
+	uint32_t counter_unit;
 	uint32_t bundle_length;
-	uint32_t reserved;
+	uint64_t reserved;
 	uint32_t mmrc_encoding;
 	uint32_t mmrc_counter;
 };
@@ -167,6 +167,11 @@ struct bundle_encoding_counter {
 	uint32_t encoding;
 	uint32_t counter;
 };
+#define METER_BUNDLE_SIZE sizeof(struct bundle_encoding_counter)
+#define BUNDLE_COUNT(length) ((length) / METER_BUNDLE_SIZE)
+#define METER_MAX_NUM_BUNDLES							\
+		((METER_CERT_MAX_SIZE - sizeof(struct meter_certificate)) /	\
+		 sizeof(struct bundle_encoding_counter))
 
 struct sdsi_dev {
 	struct sdsi_regs regs;
@@ -334,6 +339,7 @@ static int sdsi_meter_cert_show(struct sdsi_dev *s)
 	uint32_t count = 0;
 	FILE *cert_ptr;
 	int ret, size;
+	char name[4];
 
 	ret = sdsi_update_registers(s);
 	if (ret)
@@ -375,32 +381,40 @@ static int sdsi_meter_cert_show(struct sdsi_dev *s)
 	printf("\n");
 	printf("Meter certificate for device %s\n", s->dev_name);
 	printf("\n");
-	printf("Block Signature:       0x%x\n", mc->block_signature);
-	printf("Count Unit:            %dms\n", mc->counter_unit);
-	printf("PPIN:                  0x%lx\n", mc->ppin);
-	printf("Feature Bundle Length: %d\n", mc->bundle_length);
-	printf("MMRC encoding:         %d\n", mc->mmrc_encoding);
-	printf("MMRC counter:          %d\n", mc->mmrc_counter);
-	if (mc->bundle_length % 8) {
+
+	get_feature(mc->signature, name);
+	printf("Signature:                    %.4s\n", name);
+
+	printf("Version:                      %d\n", mc->version);
+	printf("Count Unit:                   %dms\n", mc->counter_unit);
+	printf("PPIN:                         0x%lx\n", mc->ppin);
+	printf("Feature Bundle Length:        %d\n", mc->bundle_length);
+
+	get_feature(mc->mmrc_encoding, name);
+	printf("MMRC encoding:                %.4s\n", name);
+
+	printf("MMRC counter:                 %d\n", mc->mmrc_counter);
+	if (mc->bundle_length % METER_BUNDLE_SIZE) {
 		fprintf(stderr, "Invalid bundle length\n");
 		return -1;
 	}
 
-	if (mc->bundle_length > METER_MAX_NUM_BUNDLES * 8)  {
-		fprintf(stderr, "More than %d bundles: %d\n",
-			METER_MAX_NUM_BUNDLES, mc->bundle_length / 8);
+	if (mc->bundle_length > METER_MAX_NUM_BUNDLES * METER_BUNDLE_SIZE)  {
+		fprintf(stderr, "More than %ld bundles: actual %ld\n",
+			METER_MAX_NUM_BUNDLES, BUNDLE_COUNT(mc->bundle_length));
 		return -1;
 	}
 
-	bec = (void *)(mc) + sizeof(mc);
+	bec = (struct bundle_encoding_counter *)(mc + 1);
 
-	printf("Number of Feature Counters:          %d\n", mc->bundle_length / 8);
-	while (count++ < mc->bundle_length / 8) {
+	printf("Number of Feature Counters:   %ld\n", BUNDLE_COUNT(mc->bundle_length));
+	while (count < BUNDLE_COUNT(mc->bundle_length)) {
 		char feature[5];
 
 		feature[4] = '\0';
 		get_feature(bec[count].encoding, feature);
 		printf("    %s:          %d\n", feature, bec[count].counter);
+		++count;
 	}
 
 	return 0;
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index 12af572201..da9347552b 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -148,7 +148,7 @@ AVXcode:
 65: SEG=GS (Prefix)
 66: Operand-Size (Prefix)
 67: Address-Size (Prefix)
-68: PUSH Iz (d64)
+68: PUSH Iz
 69: IMUL Gv,Ev,Iz
 6a: PUSH Ib (d64)
 6b: IMUL Gv,Ev,Ib
@@ -698,10 +698,10 @@ AVXcode: 2
 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
 4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
-50: vpdpbusd Vx,Hx,Wx (66),(ev)
-51: vpdpbusds Vx,Hx,Wx (66),(ev)
-52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
-53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)
+50: vpdpbusd Vx,Hx,Wx (66)
+51: vpdpbusds Vx,Hx,Wx (66)
+52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
+53: vpdpwssds Vx,Hx,Wx (66) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)
 54: vpopcntb/w Vx,Wx (66),(ev)
 55: vpopcntd/q Vx,Wx (66),(ev)
 58: vpbroadcastd Vx,Wx (66),(v)
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index cc6e6aae24..958e92acca 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -244,29 +244,101 @@ int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type)
 	return fd;
 }
 
-int mount_bpffs_for_pin(const char *name, bool is_dir)
+int create_and_mount_bpffs_dir(const char *dir_name)
 {
 	char err_str[ERR_MAX_LEN];
-	char *file;
-	char *dir;
+	bool dir_exists;
 	int err = 0;
 
-	if (is_dir && is_bpffs(name))
+	if (is_bpffs(dir_name))
 		return err;
 
-	file = malloc(strlen(name) + 1);
-	if (!file) {
+	dir_exists = access(dir_name, F_OK) == 0;
+
+	if (!dir_exists) {
+		char *temp_name;
+		char *parent_name;
+
+		temp_name = strdup(dir_name);
+		if (!temp_name) {
+			p_err("mem alloc failed");
+			return -1;
+		}
+
+		parent_name = dirname(temp_name);
+
+		if (is_bpffs(parent_name)) {
+			/* nothing to do if already mounted */
+			free(temp_name);
+			return err;
+		}
+
+		if (access(parent_name, F_OK) == -1) {
+			p_err("can't create dir '%s' to pin BPF object: parent dir '%s' doesn't exist",
+			      dir_name, parent_name);
+			free(temp_name);
+			return -1;
+		}
+
+		free(temp_name);
+	}
+
+	if (block_mount) {
+		p_err("no BPF file system found, not mounting it due to --nomount option");
+		return -1;
+	}
+
+	if (!dir_exists) {
+		err = mkdir(dir_name, S_IRWXU);
+		if (err) {
+			p_err("failed to create dir '%s': %s", dir_name, strerror(errno));
+			return err;
+		}
+	}
+
+	err = mnt_fs(dir_name, "bpf", err_str, ERR_MAX_LEN);
+	if (err) {
+		err_str[ERR_MAX_LEN - 1] = '\0';
+		p_err("can't mount BPF file system on given dir '%s': %s",
+		      dir_name, err_str);
+
+		if (!dir_exists)
+			rmdir(dir_name);
+	}
+
+	return err;
+}
+
+int mount_bpffs_for_file(const char *file_name)
+{
+	char err_str[ERR_MAX_LEN];
+	char *temp_name;
+	char *dir;
+	int err = 0;
+
+	if (access(file_name, F_OK) != -1) {
+		p_err("can't pin BPF object: path '%s' already exists", file_name);
+		return -1;
+	}
+
+	temp_name = strdup(file_name);
+	if (!temp_name) {
 		p_err("mem alloc failed");
 		return -1;
 	}
 
-	strcpy(file, name);
-	dir = dirname(file);
+	dir = dirname(temp_name);
 
 	if (is_bpffs(dir))
 		/* nothing to do if already mounted */
 		goto out_free;
 
+	if (access(dir, F_OK) == -1) {
+		p_err("can't pin BPF object: dir '%s' doesn't exist", dir);
+		err = -1;
+		goto out_free;
+	}
+
 	if (block_mount) {
 		p_err("no BPF file system found, not mounting it due to --nomount option");
 		err = -1;
@@ -276,12 +348,12 @@ int mount_bpffs_for_pin(const char *name, bool is_dir)
 	err = mnt_fs(dir, "bpf", err_str, ERR_MAX_LEN);
 	if (err) {
 		err_str[ERR_MAX_LEN - 1] = '\0';
-		p_err("can't mount BPF file system to pin the object (%s): %s",
-		      name, err_str);
+		p_err("can't mount BPF file system to pin the object '%s': %s",
+		      file_name, err_str);
 	}
 
 out_free:
-	free(file);
+	free(temp_name);
 	return err;
 }
 
@@ -289,7 +361,7 @@ int do_pin_fd(int fd, const char *name)
 {
 	int err;
 
-	err = mount_bpffs_for_pin(name, false);
+	err = mount_bpffs_for_file(name);
 	if (err)
 		return err;
 
diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c
index 6b0e5202ca..5c39c2ed36 100644
--- a/tools/bpf/bpftool/iter.c
+++ b/tools/bpf/bpftool/iter.c
@@ -76,7 +76,7 @@ static int do_pin(int argc, char **argv)
 		goto close_obj;
 	}
 
-	err = mount_bpffs_for_pin(path, false);
+	err = mount_bpffs_for_file(path);
 	if (err)
 		goto close_link;
 
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index b8bb08d10d..9eb764fe4c 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -142,7 +142,8 @@ const char *get_fd_type_name(enum bpf_obj_type type);
 char *get_fdinfo(int fd, const char *key);
 int open_obj_pinned(const char *path, bool quiet);
 int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type);
-int mount_bpffs_for_pin(const char *name, bool is_dir);
+int mount_bpffs_for_file(const char *file_name);
+int create_and_mount_bpffs_dir(const char *dir_name);
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***));
 int do_pin_fd(int fd, const char *name);
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 9cb42a3366..4c4cf16a40 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -1778,7 +1778,10 @@ offload_dev:
 		goto err_close_obj;
 	}
 
-	err = mount_bpffs_for_pin(pinfile, !first_prog_only);
+	if (first_prog_only)
+		err = mount_bpffs_for_file(pinfile);
+	else
+		err = create_and_mount_bpffs_dir(pinfile);
 	if (err)
 		goto err_close_obj;
 
diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
index 26004f0c5a..7bdbcac3cf 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -102,8 +102,8 @@ int iter(struct bpf_iter__task_file *ctx)
 				       BPF_LINK_TYPE_PERF_EVENT___local)) {
 		struct bpf_link *link = (struct bpf_link *) file->private_data;
 
-		if (link->type == bpf_core_enum_value(enum bpf_link_type___local,
-						      BPF_LINK_TYPE_PERF_EVENT___local)) {
+		if (BPF_CORE_READ(link, type) == bpf_core_enum_value(enum bpf_link_type___local,
+								     BPF_LINK_TYPE_PERF_EVENT___local)) {
 			e.has_bpf_cookie = true;
 			e.bpf_cookie = get_bpf_cookie(link);
 		}
diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c
index d573f2640d..aa43dead24 100644
--- a/tools/bpf/bpftool/struct_ops.c
+++ b/tools/bpf/bpftool/struct_ops.c
@@ -515,7 +515,7 @@ static int do_register(int argc, char **argv)
 	if (argc == 1)
 		linkdir = GET_ARG();
 
-	if (linkdir && mount_bpffs_for_pin(linkdir, true)) {
+	if (linkdir && create_and_mount_bpffs_dir(linkdir)) {
 		p_err("can't mount bpffs for pinning");
 		return -1;
 	}
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index d9520cb826..af393c7dee 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -728,7 +728,7 @@ static int sets_patch(struct object *obj)
 
 static int symbols_patch(struct object *obj)
 {
-	int err;
+	off_t err;
 
 	if (__symbols_patch(obj, &obj->structs)  ||
 	    __symbols_patch(obj, &obj->unions)   ||
diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h
index bacfd35c51..5be9d3c743 100644
--- a/tools/include/nolibc/stdlib.h
+++ b/tools/include/nolibc/stdlib.h
@@ -185,7 +185,7 @@ void *realloc(void *old_ptr, size_t new_size)
 	if (__builtin_expect(!ret, 0))
 		return NULL;
 
-	memcpy(ret, heap->user_p, heap->len);
+	memcpy(ret, heap->user_p, user_p_len);
 	munmap(heap, heap->len);
 	return ret;
 }
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3c42b9f1ba..bcd84985fa 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7150,7 +7150,7 @@ struct bpf_fib_lookup {
 
 		/* output: MTU value */
 		__u16	mtu_result;
-	};
+	} __attribute__((packed, aligned(2)));
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 97ec005c3c..145b8bd1d5 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -105,7 +105,7 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
  */
 int probe_memcg_account(int token_fd)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd);
 	struct bpf_insn insns[] = {
 		BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns),
 		BPF_EXIT_INSN(),
diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
index 4e783cc7fc..a336786a22 100644
--- a/tools/lib/bpf/features.c
+++ b/tools/lib/bpf/features.c
@@ -22,7 +22,7 @@ int probe_fd(int fd)
 
 static int probe_kern_prog_name(int token_fd)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd);
 	struct bpf_insn insns[] = {
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_EXIT_INSN(),
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a2061fcd61..f515cf264a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7321,9 +7321,9 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	char *cp, errmsg[STRERR_BUFSIZE];
 	size_t log_buf_size = 0;
 	char *log_buf = NULL, *tmp;
-	int btf_fd, ret, err;
 	bool own_log_buf = true;
 	__u32 log_level = prog->log_level;
+	int ret, err;
 
 	if (prog->type == BPF_PROG_TYPE_UNSPEC) {
 		/*
@@ -7347,9 +7347,8 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	load_attr.prog_ifindex = prog->prog_ifindex;
 
 	/* specify func_info/line_info only if kernel supports them */
-	btf_fd = btf__fd(obj->btf);
-	if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) {
-		load_attr.prog_btf_fd = btf_fd;
+	if (obj->btf && btf__fd(obj->btf) >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) {
+		load_attr.prog_btf_fd = btf__fd(obj->btf);
 		load_attr.func_info = prog->func_info;
 		load_attr.func_info_rec_size = prog->func_info_rec_size;
 		load_attr.func_info_cnt = prog->func_info_cnt;
@@ -11476,7 +11475,7 @@ static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, stru
 
 	n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern);
 	if (n < 1) {
-		pr_warn("kprobe multi pattern is invalid: %s\n", pattern);
+		pr_warn("kprobe multi pattern is invalid: %s\n", spec);
 		return -EINVAL;
 	}
 
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index 9fa75943f2..d943d78b78 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -633,11 +633,10 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o
 			const char *const subcommands[], const char *usagestr[], int flags)
 {
 	struct parse_opt_ctx_t ctx;
+	char *buf = NULL;
 
 	/* build usage string if it's not provided */
 	if (subcommands && !usagestr[0]) {
-		char *buf = NULL;
-
 		astrcatf(&buf, "%s %s [<options>] {", subcmd_config.exec_name, argv[0]);
 
 		for (int i = 0; subcommands[i]; i++) {
@@ -679,7 +678,10 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o
 			astrcatf(&error_buf, "unknown switch `%c'", *ctx.opt);
 		usage_with_options(usagestr, options);
 	}
-
+	if (buf) {
+		usagestr[0] = NULL;
+		free(buf);
+	}
 	return parse_options_end(&ctx);
 }
 
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 3b12595193..6bf2468f59 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -71,6 +71,7 @@ counted. The following modifiers exist:
  D - pin the event to the PMU
  W - group is weak and will fallback to non-group if not schedulable,
  e - group or event are exclusive and do not share the PMU
+ b - use BPF aggregration (see perf stat --bpf-counters)
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 04d89d2ed2..d769aa447f 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -458,18 +458,19 @@ SHELL = $(SHELL_PATH)
 
 arm64_gen_sysreg_dir := $(srctree)/tools/arch/arm64/tools
 ifneq ($(OUTPUT),)
-  arm64_gen_sysreg_outdir := $(OUTPUT)
+  arm64_gen_sysreg_outdir := $(abspath $(OUTPUT))
 else
   arm64_gen_sysreg_outdir := $(CURDIR)
 endif
 
 arm64-sysreg-defs: FORCE
-	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir)
+	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) \
+		prefix= subdir=
 
 arm64-sysreg-defs-clean:
 	$(call QUIET_CLEAN,arm64-sysreg-defs)
 	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) \
-		clean > /dev/null
+		prefix= subdir= clean > /dev/null
 
 beauty_linux_dir := $(srctree)/tools/perf/trace/beauty/include/linux/
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c
index 49331743c7..a759eb2328 100644
--- a/tools/perf/bench/inject-buildid.c
+++ b/tools/perf/bench/inject-buildid.c
@@ -362,7 +362,7 @@ static int inject_build_id(struct bench_data *data, u64 *max_rss)
 		return -1;
 
 	for (i = 0; i < nr_mmaps; i++) {
-		int idx = rand() % (nr_dsos - 1);
+		int idx = rand() % nr_dsos;
 		struct bench_dso *dso = &dsos[idx];
 		u64 timestamp = rand() % 1000000;
 
diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c
index 5c71fdc419..b722ff88fe 100644
--- a/tools/perf/bench/uprobe.c
+++ b/tools/perf/bench/uprobe.c
@@ -47,7 +47,7 @@ static const char * const bench_uprobe_usage[] = {
 #define bench_uprobe__attach_uprobe(prog) \
 	skel->links.prog = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.prog, \
 							   /*pid=*/-1, \
-							   /*binary_path=*/"/lib64/libc.so.6", \
+							   /*binary_path=*/"libc.so.6", \
 							   /*func_offset=*/0, \
 							   /*opts=*/&uprobe_opts); \
 	if (!skel->links.prog) { \
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 6c1cc79769..9cd97fd76b 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -809,8 +809,6 @@ int cmd_annotate(int argc, const char **argv)
 		    "Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
-	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
-		    "Show event group information together"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index 83954af367..de76bbc50b 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -523,7 +523,7 @@ static int daemon_session__control(struct daemon_session *session,
 		  session->base, SESSION_CONTROL);
 
 	control = open(control_path, O_WRONLY|O_NONBLOCK);
-	if (!control)
+	if (control < 0)
 		return -1;
 
 	if (do_ack) {
@@ -532,7 +532,7 @@ static int daemon_session__control(struct daemon_session *session,
 			  session->base, SESSION_ACK);
 
 		ack = open(ack_path, O_RDONLY, O_NONBLOCK);
-		if (!ack) {
+		if (ack < 0) {
 			close(control);
 			return -1;
 		}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ff7e1d6cfc..45c755fb50 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1355,8 +1355,6 @@ static int record__open(struct record *rec)
 	struct record_opts *opts = &rec->opts;
 	int rc = 0;
 
-	evlist__config(evlist, opts, &callchain_param);
-
 	evlist__for_each_entry(evlist, pos) {
 try_again:
 		if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) {
@@ -1958,8 +1956,7 @@ static void record__read_lost_samples(struct record *rec)
 
 				if (count.lost) {
 					if (!lost) {
-						lost = zalloc(sizeof(*lost) +
-							      session->machines.host.id_hdr_size);
+						lost = zalloc(PERF_SAMPLE_MAX_SIZE);
 						if (!lost) {
 							pr_debug("Memory allocation failed\n");
 							return;
@@ -1975,8 +1972,7 @@ static void record__read_lost_samples(struct record *rec)
 		lost_count = perf_bpf_filter__lost_count(evsel);
 		if (lost_count) {
 			if (!lost) {
-				lost = zalloc(sizeof(*lost) +
-					      session->machines.host.id_hdr_size);
+				lost = zalloc(PERF_SAMPLE_MAX_SIZE);
 				if (!lost) {
 					pr_debug("Memory allocation failed\n");
 					return;
@@ -2483,6 +2479,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	evlist__uniquify_name(rec->evlist);
 
+	evlist__config(rec->evlist, opts, &callchain_param);
+
 	/* Debug message used by test scripts */
 	pr_debug3("perf record opening and mmapping events\n");
 	if (record__open(rec) != 0) {
@@ -2881,10 +2879,10 @@ out_delete_session:
 	}
 #endif
 	zstd_fini(&session->zstd_data);
-	perf_session__delete(session);
-
 	if (!opts->no_bpf_event)
 		evlist__stop_sb_thread(rec->sb_evlist);
+
+	perf_session__delete(session);
 	return status;
 }
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index dcd93ee5fc..5b684d2ab4 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -428,7 +428,7 @@ static int report__setup_sample_type(struct report *rep)
 		 * compatibility, set the bit if it's an old perf data file.
 		 */
 		evlist__for_each_entry(session->evlist, evsel) {
-			if (strstr(evsel->name, "arm_spe") &&
+			if (strstr(evsel__name(evsel), "arm_spe") &&
 				!(sample_type & PERF_SAMPLE_DATA_SRC)) {
 				evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC;
 				sample_type |= PERF_SAMPLE_DATA_SRC;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index b248c43352..1bfb223473 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2963,8 +2963,11 @@ static int timehist_check_attr(struct perf_sched *sched,
 			return -1;
 		}
 
-		if (sched->show_callchain && !evsel__has_callchain(evsel)) {
-			pr_info("Samples do not have callchains.\n");
+		/* only need to save callchain related to sched_switch event */
+		if (sched->show_callchain &&
+		    evsel__name_is(evsel, "sched:sched_switch") &&
+		    !evsel__has_callchain(evsel)) {
+			pr_info("Samples of sched_switch event do not have callchains.\n");
 			sched->show_callchain = 0;
 			symbol_conf.use_callchain = 0;
 		}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 37088cc0ff..2e7148d667 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3806,7 +3806,7 @@ static int parse_insn_trace(const struct option *opt __maybe_unused,
 	if (ret < 0)
 		return ret;
 
-	itrace_parse_synth_opts(opt, "i0ns", 0);
+	itrace_parse_synth_opts(opt, "i0nse", 0);
 	symbol_conf.nanosecs = true;
 	return 0;
 }
diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
index ec2ff78e2b..3ab1d3a663 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
@@ -2,71 +2,71 @@
   {
     "BriefDescription": "Transaction count",
     "MetricName": "transaction",
-    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL if has_event(TX_C_TEND) else 0"
   },
   {
     "BriefDescription": "Cycles per Instruction",
     "MetricName": "cpi",
-    "MetricExpr": "CPU_CYCLES / INSTRUCTIONS"
+    "MetricExpr": "CPU_CYCLES / INSTRUCTIONS if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Problem State Instruction Ratio",
     "MetricName": "prbstate",
-    "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100"
+    "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100 if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Level One Miss per 100 Instructions",
     "MetricName": "l1mp",
-    "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100"
+    "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100 if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 2 cache",
     "MetricName": "l2p",
-    "MetricExpr": "((DCW_REQ + DCW_REQ_IV + ICW_REQ + ICW_REQ_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_REQ + DCW_REQ_IV + ICW_REQ + ICW_REQ_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 3 on same chip cache",
     "MetricName": "l3p",
-    "MetricExpr": "((DCW_REQ_CHIP_HIT + DCW_ON_CHIP + DCW_ON_CHIP_IV + DCW_ON_CHIP_CHIP_HIT + ICW_REQ_CHIP_HIT + ICW_ON_CHIP + ICW_ON_CHIP_IV + ICW_ON_CHIP_CHIP_HIT) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_REQ_CHIP_HIT + DCW_ON_CHIP + DCW_ON_CHIP_IV + DCW_ON_CHIP_CHIP_HIT + ICW_REQ_CHIP_HIT + ICW_ON_CHIP + ICW_ON_CHIP_IV + ICW_ON_CHIP_CHIP_HIT) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ_CHIP_HIT) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 4 Local cache on same book",
     "MetricName": "l4lp",
-    "MetricExpr": "((DCW_REQ_DRAWER_HIT + DCW_ON_CHIP_DRAWER_HIT + DCW_ON_MODULE + DCW_ON_DRAWER + IDCW_ON_MODULE_IV + IDCW_ON_MODULE_CHIP_HIT + IDCW_ON_MODULE_DRAWER_HIT + IDCW_ON_DRAWER_IV + IDCW_ON_DRAWER_CHIP_HIT + IDCW_ON_DRAWER_DRAWER_HIT + ICW_REQ_DRAWER_HIT + ICW_ON_CHIP_DRAWER_HIT + ICW_ON_MODULE + ICW_ON_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_REQ_DRAWER_HIT + DCW_ON_CHIP_DRAWER_HIT + DCW_ON_MODULE + DCW_ON_DRAWER + IDCW_ON_MODULE_IV + IDCW_ON_MODULE_CHIP_HIT + IDCW_ON_MODULE_DRAWER_HIT + IDCW_ON_DRAWER_IV + IDCW_ON_DRAWER_CHIP_HIT + IDCW_ON_DRAWER_DRAWER_HIT + ICW_REQ_DRAWER_HIT + ICW_ON_CHIP_DRAWER_HIT + ICW_ON_MODULE + ICW_ON_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ_DRAWER_HIT) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 4 Remote cache on different book",
     "MetricName": "l4rp",
-    "MetricExpr": "((DCW_OFF_DRAWER + IDCW_OFF_DRAWER_IV + IDCW_OFF_DRAWER_CHIP_HIT + IDCW_OFF_DRAWER_DRAWER_HIT + ICW_OFF_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_OFF_DRAWER + IDCW_OFF_DRAWER_IV + IDCW_OFF_DRAWER_CHIP_HIT + IDCW_OFF_DRAWER_DRAWER_HIT + ICW_OFF_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_OFF_DRAWER) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from memory",
     "MetricName": "memp",
-    "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_ON_CHIP_MEMORY) else 0"
   },
   {
     "BriefDescription": "Cycles per Instructions from Finite cache/memory",
     "MetricName": "finite_cpi",
-    "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS"
+    "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS if has_event(L1C_TLB2_MISSES) else 0"
   },
   {
     "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1",
     "MetricName": "est_cpi",
-    "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS)"
+    "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS) if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss",
     "MetricName": "scpl1m",
-    "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)"
+    "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES) if has_event(L1C_TLB2_MISSES) else 0"
   },
   {
     "BriefDescription": "Estimated TLB CPU percentage of Total CPU",
     "MetricName": "tlb_percent",
-    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100"
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100 if has_event(CPU_CYCLES) else 0"
   },
   {
     "BriefDescription": "Estimated Cycles per TLB Miss",
     "MetricName": "tlb_miss",
-    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))"
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) if has_event(DTLB2_MISSES) else 0"
   }
 ]
diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv
index a918e1af77..b22648d127 100644
--- a/tools/perf/pmu-events/arch/s390/mapfile.csv
+++ b/tools/perf/pmu-events/arch/s390/mapfile.csv
@@ -5,4 +5,4 @@ Family-model,Version,Filename,EventType
 ^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
 ^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
 ^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_z15,core
-^IBM.393[12].*3\.7.[[:xdigit:]]+$,3,cf_z16,core
+^IBM.393[12].*$,3,cf_z16,core
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index d13ee7683d..e05b370b1e 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -274,11 +274,8 @@ static int finish_test(struct child_test *child_test, int width)
 	struct test_suite *t = child_test->test;
 	int i = child_test->test_num;
 	int subi = child_test->subtest;
-	int out = child_test->process.out;
 	int err = child_test->process.err;
-	bool out_done = out <= 0;
 	bool err_done = err <= 0;
-	struct strbuf out_output = STRBUF_INIT;
 	struct strbuf err_output = STRBUF_INIT;
 	int ret;
 
@@ -290,11 +287,9 @@ static int finish_test(struct child_test *child_test, int width)
 		pr_info("%3d: %-*s:\n", i + 1, width, test_description(t, -1));
 
 	/*
-	 * Busy loop reading from the child's stdout and stderr that are set to
-	 * be non-blocking until EOF.
+	 * Busy loop reading from the child's stdout/stderr that are set to be
+	 * non-blocking until EOF.
 	 */
-	if (!out_done)
-		fcntl(out, F_SETFL, O_NONBLOCK);
 	if (!err_done)
 		fcntl(err, F_SETFL, O_NONBLOCK);
 	if (verbose > 1) {
@@ -303,11 +298,8 @@ static int finish_test(struct child_test *child_test, int width)
 		else
 			pr_info("%3d: %s:\n", i + 1, test_description(t, -1));
 	}
-	while (!out_done || !err_done) {
-		struct pollfd pfds[2] = {
-			{ .fd = out,
-			  .events = POLLIN | POLLERR | POLLHUP | POLLNVAL,
-			},
+	while (!err_done) {
+		struct pollfd pfds[1] = {
 			{ .fd = err,
 			  .events = POLLIN | POLLERR | POLLHUP | POLLNVAL,
 			},
@@ -317,21 +309,7 @@ static int finish_test(struct child_test *child_test, int width)
 
 		/* Poll to avoid excessive spinning, timeout set for 1000ms. */
 		poll(pfds, ARRAY_SIZE(pfds), /*timeout=*/1000);
-		if (!out_done && pfds[0].revents) {
-			errno = 0;
-			len = read(out, buf, sizeof(buf) - 1);
-
-			if (len <= 0) {
-				out_done = errno != EAGAIN;
-			} else {
-				buf[len] = '\0';
-				if (verbose > 1)
-					fprintf(stdout, "%s", buf);
-				else
-					strbuf_addstr(&out_output, buf);
-			}
-		}
-		if (!err_done && pfds[1].revents) {
+		if (!err_done && pfds[0].revents) {
 			errno = 0;
 			len = read(err, buf, sizeof(buf) - 1);
 
@@ -354,14 +332,10 @@ static int finish_test(struct child_test *child_test, int width)
 			pr_info("%3d.%1d: %s:\n", i + 1, subi + 1, test_description(t, subi));
 		else
 			pr_info("%3d: %s:\n", i + 1, test_description(t, -1));
-		fprintf(stdout, "%s", out_output.buf);
 		fprintf(stderr, "%s", err_output.buf);
 	}
-	strbuf_release(&out_output);
 	strbuf_release(&err_output);
 	print_test_result(t, i, subi, ret, width);
-	if (out > 0)
-		close(out);
 	if (err > 0)
 		close(err);
 	return 0;
@@ -394,6 +368,7 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes
 		(*child)->process.no_stdout = 1;
 		(*child)->process.no_stderr = 1;
 	} else {
+		(*child)->process.stdout_to_stderr = 1;
 		(*child)->process.out = -1;
 		(*child)->process.err = -1;
 	}
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 7a3a7bbbec..29d2f3ee4e 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -637,11 +637,11 @@ static int do_test_code_reading(bool try_kcore)
 
 		evlist__config(evlist, &opts, NULL);
 
-		evsel = evlist__first(evlist);
-
-		evsel->core.attr.comm = 1;
-		evsel->core.attr.disabled = 1;
-		evsel->core.attr.enable_on_exec = 0;
+		evlist__for_each_entry(evlist, evsel) {
+			evsel->core.attr.comm = 1;
+			evsel->core.attr.disabled = 1;
+			evsel->core.attr.enable_on_exec = 0;
+		}
 
 		ret = evlist__open(evlist);
 		if (ret < 0) {
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
index 65dd852071..3302ea0b96 100755
--- a/tools/perf/tests/shell/test_arm_coresight.sh
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -188,7 +188,7 @@ arm_cs_etm_snapshot_test() {
 
 arm_cs_etm_basic_test() {
 	echo "Recording trace with '$*'"
-	perf record -o ${perfdata} "$@" -- ls > /dev/null 2>&1
+	perf record -o ${perfdata} "$@" -m,8M -- ls > /dev/null 2>&1
 
 	perf_script_branch_samples ls &&
 	perf_report_branch_samples ls &&
diff --git a/tools/perf/tests/workloads/datasym.c b/tools/perf/tests/workloads/datasym.c
index ddd40bc634..8e08fc75a9 100644
--- a/tools/perf/tests/workloads/datasym.c
+++ b/tools/perf/tests/workloads/datasym.c
@@ -16,6 +16,22 @@ static int datasym(int argc __maybe_unused, const char **argv __maybe_unused)
 {
 	for (;;) {
 		buf1.data1++;
+		if (buf1.data1 == 123) {
+			/*
+			 * Add some 'noise' in the loop to work around errata
+			 * 1694299 on Arm N1.
+			 *
+			 * Bias exists in SPE sampling which can cause the load
+			 * and store instructions to be skipped entirely. This
+			 * comes and goes randomly depending on the offset the
+			 * linker places the datasym loop at in the Perf binary.
+			 * With an extra branch in the middle of the loop that
+			 * isn't always taken, the instruction stream is no
+			 * longer a continuous repeating pattern that interacts
+			 * badly with the bias.
+			 */
+			buf1.data1++;
+		}
 		buf1.data2 += buf1.data1;
 	}
 	return 0;
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 603d11283c..19503e8387 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -203,7 +203,7 @@ void ui_browser__refresh_dimensions(struct ui_browser *browser)
 void ui_browser__handle_resize(struct ui_browser *browser)
 {
 	ui__refresh_dimensions(false);
-	ui_browser__show(browser, browser->title, ui_helpline__current);
+	ui_browser__show(browser, browser->title ?: "", ui_helpline__current);
 	ui_browser__refresh(browser);
 }
 
@@ -287,7 +287,8 @@ int ui_browser__show(struct ui_browser *browser, const char *title,
 	mutex_lock(&ui__lock);
 	__ui_browser__show_title(browser, title);
 
-	browser->title = title;
+	free(browser->title);
+	browser->title = strdup(title);
 	zfree(&browser->helpline);
 
 	va_start(ap, helpline);
@@ -304,6 +305,7 @@ void ui_browser__hide(struct ui_browser *browser)
 	mutex_lock(&ui__lock);
 	ui_helpline__pop();
 	zfree(&browser->helpline);
+	zfree(&browser->title);
 	mutex_unlock(&ui__lock);
 }
 
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 510ce45540..6e98d5f8f7 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -21,7 +21,7 @@ struct ui_browser {
 	u8	      extra_title_lines;
 	int	      current_color;
 	void	      *priv;
-	const char    *title;
+	char	      *title;
 	char	      *helpline;
 	const char    *no_samples_msg;
 	void 	      (*refresh_dimensions)(struct ui_browser *browser);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 50ca92255f..79d082155c 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -887,10 +887,17 @@ static struct annotated_source *annotated_source__new(void)
 
 static __maybe_unused void annotated_source__delete(struct annotated_source *src)
 {
+	struct hashmap_entry *cur;
+	size_t bkt;
+
 	if (src == NULL)
 		return;
 
-	hashmap__free(src->samples);
+	if (src->samples) {
+		hashmap__for_each_entry(src->samples, cur, bkt)
+			zfree(&cur->pvalue);
+		hashmap__free(src->samples);
+	}
 	zfree(&src->histograms);
 	free(src);
 }
@@ -3025,7 +3032,7 @@ void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *m
 	annotation__update_column_widths(notes);
 }
 
-static void annotation__calc_lines(struct annotation *notes, struct map *map,
+static void annotation__calc_lines(struct annotation *notes, struct map_symbol *ms,
 				   struct rb_root *root)
 {
 	struct annotation_line *al;
@@ -3033,6 +3040,7 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 
 	list_for_each_entry(al, &notes->src->source, node) {
 		double percent_max = 0.0;
+		u64 addr;
 		int i;
 
 		for (i = 0; i < al->data_nr; i++) {
@@ -3048,8 +3056,9 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 		if (percent_max <= 0.5)
 			continue;
 
-		al->path = get_srcline(map__dso(map), notes->start + al->offset, NULL,
-				       false, true, notes->start + al->offset);
+		addr = map__rip_2objdump(ms->map, ms->sym->start);
+		al->path = get_srcline(map__dso(ms->map), addr + al->offset, NULL,
+				       false, true, ms->sym->start + al->offset);
 		insert_source_line(&tmp_root, al);
 	}
 
@@ -3060,7 +3069,7 @@ static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root)
 {
 	struct annotation *notes = symbol__annotation(ms->sym);
 
-	annotation__calc_lines(notes, ms->map, root);
+	annotation__calc_lines(notes, ms, root);
 }
 
 int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 3684e6009b..ef314a5797 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1466,6 +1466,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 	char *endptr;
 	bool period_type_set = false;
 	bool period_set = false;
+	bool iy = false;
 
 	synth_opts->set = true;
 
@@ -1484,6 +1485,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 		switch (*p++) {
 		case 'i':
 		case 'y':
+			iy = true;
 			if (p[-1] == 'y')
 				synth_opts->cycles = true;
 			else
@@ -1649,7 +1651,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 		}
 	}
 out:
-	if (synth_opts->instructions || synth_opts->cycles) {
+	if (iy) {
 		if (!period_type_set)
 			synth_opts->period_type =
 					PERF_ITRACE_DEFAULT_PERIOD_TYPE;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 2791126069..f93e57e2fc 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1136,6 +1136,68 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
 }
 
+#if defined(HAVE_DWARF_GETLOCATIONS_SUPPORT) || defined(HAVE_DWARF_CFI_SUPPORT)
+static int reg_from_dwarf_op(Dwarf_Op *op)
+{
+	switch (op->atom) {
+	case DW_OP_reg0 ... DW_OP_reg31:
+		return op->atom - DW_OP_reg0;
+	case DW_OP_breg0 ... DW_OP_breg31:
+		return op->atom - DW_OP_breg0;
+	case DW_OP_regx:
+	case DW_OP_bregx:
+		return op->number;
+	default:
+		break;
+	}
+	return -1;
+}
+
+static int offset_from_dwarf_op(Dwarf_Op *op)
+{
+	switch (op->atom) {
+	case DW_OP_reg0 ... DW_OP_reg31:
+	case DW_OP_regx:
+		return 0;
+	case DW_OP_breg0 ... DW_OP_breg31:
+		return op->number;
+	case DW_OP_bregx:
+		return op->number2;
+	default:
+		break;
+	}
+	return -1;
+}
+
+static bool check_allowed_ops(Dwarf_Op *ops, size_t nops)
+{
+	/* The first op is checked separately */
+	ops++;
+	nops--;
+
+	/*
+	 * It needs to make sure if the location expression matches to the given
+	 * register and offset exactly.  Thus it rejects any complex expressions
+	 * and only allows a few of selected operators that doesn't change the
+	 * location.
+	 */
+	while (nops) {
+		switch (ops->atom) {
+		case DW_OP_stack_value:
+		case DW_OP_deref_size:
+		case DW_OP_deref:
+		case DW_OP_piece:
+			break;
+		default:
+			return false;
+		}
+		ops++;
+		nops--;
+	}
+	return true;
+}
+#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT || HAVE_DWARF_CFI_SUPPORT */
+
 #ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 /**
  * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
@@ -1280,7 +1342,7 @@ struct find_var_data {
 #define DWARF_OP_DIRECT_REGS  32
 
 static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
-			     u64 addr_offset, u64 addr_type)
+			     u64 addr_offset, u64 addr_type, bool is_pointer)
 {
 	Dwarf_Die type_die;
 	Dwarf_Word size;
@@ -1294,6 +1356,12 @@ static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
 	if (die_get_real_type(die_mem, &type_die) == NULL)
 		return false;
 
+	if (is_pointer && dwarf_tag(&type_die) == DW_TAG_pointer_type) {
+		/* Get the target type of the pointer */
+		if (die_get_real_type(&type_die, &type_die) == NULL)
+			return false;
+	}
+
 	if (dwarf_aggregate_size(&type_die, &size) < 0)
 		return false;
 
@@ -1305,34 +1373,6 @@ static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
 	return true;
 }
 
-static bool check_allowed_ops(Dwarf_Op *ops, size_t nops)
-{
-	/* The first op is checked separately */
-	ops++;
-	nops--;
-
-	/*
-	 * It needs to make sure if the location expression matches to the given
-	 * register and offset exactly.  Thus it rejects any complex expressions
-	 * and only allows a few of selected operators that doesn't change the
-	 * location.
-	 */
-	while (nops) {
-		switch (ops->atom) {
-		case DW_OP_stack_value:
-		case DW_OP_deref_size:
-		case DW_OP_deref:
-		case DW_OP_piece:
-			break;
-		default:
-			return false;
-		}
-		ops++;
-		nops--;
-	}
-	return true;
-}
-
 /* Only checks direct child DIEs in the given scope. */
 static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 {
@@ -1361,31 +1401,38 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 		if (data->is_fbreg && ops->atom == DW_OP_fbreg &&
 		    data->offset >= (int)ops->number &&
 		    check_allowed_ops(ops, nops) &&
-		    match_var_offset(die_mem, data, data->offset, ops->number))
+		    match_var_offset(die_mem, data, data->offset, ops->number,
+				     /*is_pointer=*/false))
 			return DIE_FIND_CB_END;
 
 		/* Only match with a simple case */
 		if (data->reg < DWARF_OP_DIRECT_REGS) {
 			/* pointer variables saved in a register 0 to 31 */
 			if (ops->atom == (DW_OP_reg0 + data->reg) &&
-			    check_allowed_ops(ops, nops))
+			    check_allowed_ops(ops, nops) &&
+			    match_var_offset(die_mem, data, data->offset, 0,
+					     /*is_pointer=*/true))
 				return DIE_FIND_CB_END;
 
 			/* Local variables accessed by a register + offset */
 			if (ops->atom == (DW_OP_breg0 + data->reg) &&
 			    check_allowed_ops(ops, nops) &&
-			    match_var_offset(die_mem, data, data->offset, ops->number))
+			    match_var_offset(die_mem, data, data->offset, ops->number,
+					     /*is_pointer=*/false))
 				return DIE_FIND_CB_END;
 		} else {
 			/* pointer variables saved in a register 32 or above */
 			if (ops->atom == DW_OP_regx && ops->number == data->reg &&
-			    check_allowed_ops(ops, nops))
+			    check_allowed_ops(ops, nops) &&
+			    match_var_offset(die_mem, data, data->offset, 0,
+					     /*is_pointer=*/true))
 				return DIE_FIND_CB_END;
 
 			/* Local variables accessed by a register + offset */
 			if (ops->atom == DW_OP_bregx && data->reg == ops->number &&
 			    check_allowed_ops(ops, nops) &&
-			    match_var_offset(die_mem, data, data->offset, ops->number2))
+			    match_var_offset(die_mem, data, data->offset, ops->number2,
+					     /*is_poitner=*/false))
 				return DIE_FIND_CB_END;
 		}
 	}
@@ -1447,7 +1494,8 @@ static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
 			continue;
 
 		if (check_allowed_ops(ops, nops) &&
-		    match_var_offset(die_mem, data, data->addr, ops->number))
+		    match_var_offset(die_mem, data, data->addr, ops->number,
+				     /*is_pointer=*/false))
 			return DIE_FIND_CB_END;
 	}
 	return DIE_FIND_CB_SIBLING;
@@ -1479,41 +1527,69 @@ Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
 		*offset = data.offset;
 	return result;
 }
-#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
-#ifdef HAVE_DWARF_CFI_SUPPORT
-static int reg_from_dwarf_op(Dwarf_Op *op)
+static int __die_collect_vars_cb(Dwarf_Die *die_mem, void *arg)
 {
-	switch (op->atom) {
-	case DW_OP_reg0 ... DW_OP_reg31:
-		return op->atom - DW_OP_reg0;
-	case DW_OP_breg0 ... DW_OP_breg31:
-		return op->atom - DW_OP_breg0;
-	case DW_OP_regx:
-	case DW_OP_bregx:
-		return op->number;
-	default:
-		break;
-	}
-	return -1;
+	struct die_var_type **var_types = arg;
+	Dwarf_Die type_die;
+	int tag = dwarf_tag(die_mem);
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Op *ops;
+	size_t nops;
+	struct die_var_type *vt;
+
+	if (tag != DW_TAG_variable && tag != DW_TAG_formal_parameter)
+		return DIE_FIND_CB_SIBLING;
+
+	if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	/*
+	 * Only collect the first location as it can reconstruct the
+	 * remaining state by following the instructions.
+	 * start = 0 means it covers the whole range.
+	 */
+	if (dwarf_getlocations(&attr, 0, &base, &start, &end, &ops, &nops) <= 0)
+		return DIE_FIND_CB_SIBLING;
+
+	if (die_get_real_type(die_mem, &type_die) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	vt = malloc(sizeof(*vt));
+	if (vt == NULL)
+		return DIE_FIND_CB_END;
+
+	vt->die_off = dwarf_dieoffset(&type_die);
+	vt->addr = start;
+	vt->reg = reg_from_dwarf_op(ops);
+	vt->offset = offset_from_dwarf_op(ops);
+	vt->next = *var_types;
+	*var_types = vt;
+
+	return DIE_FIND_CB_SIBLING;
 }
 
-static int offset_from_dwarf_op(Dwarf_Op *op)
+/**
+ * die_collect_vars - Save all variables and parameters
+ * @sc_die: a scope DIE
+ * @var_types: a pointer to save the resulting list
+ *
+ * Save all variables and parameters in the @sc_die and save them to @var_types.
+ * The @var_types is a singly-linked list containing type and location info.
+ * Actual type can be retrieved using dwarf_offdie() with 'die_off' later.
+ *
+ * Callers should free @var_types.
+ */
+void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types)
 {
-	switch (op->atom) {
-	case DW_OP_reg0 ... DW_OP_reg31:
-	case DW_OP_regx:
-		return 0;
-	case DW_OP_breg0 ... DW_OP_breg31:
-		return op->number;
-	case DW_OP_bregx:
-		return op->number2;
-	default:
-		break;
-	}
-	return -1;
+	Dwarf_Die die_mem;
+
+	die_find_child(sc_die, __die_collect_vars_cb, (void *)var_types, &die_mem);
 }
+#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
+#ifdef HAVE_DWARF_CFI_SUPPORT
 /**
  * die_get_cfa - Get frame base information
  * @dwarf: a Dwarf info
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 85dd527ae1..efafd3a1f5 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -135,6 +135,15 @@ void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
 /* Get the list of including scopes */
 int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes);
 
+/* Variable type information */
+struct die_var_type {
+	struct die_var_type *next;
+	u64 die_off;
+	u64 addr;
+	int reg;
+	int offset;
+};
+
 #ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 
 /* Get byte offset range of given variable DIE */
@@ -150,6 +159,9 @@ Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
 				     Dwarf_Addr addr, Dwarf_Die *die_mem,
 				     int *offset);
 
+/* Save all variables and parameters in this scope */
+void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types);
+
 #else /*  HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
@@ -178,6 +190,11 @@ static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unu
 	return NULL;
 }
 
+static inline void die_collect_vars(Dwarf_Die *sc_die __maybe_unused,
+				    struct die_var_type **var_types __maybe_unused)
+{
+}
+
 #endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 #ifdef HAVE_DWARF_CFI_SUPPORT
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index b450178e34..e733f6b1f7 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1319,6 +1319,8 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder, bool no_tip)
 	bool ret = false;
 
 	decoder->state.type &= ~INTEL_PT_BRANCH;
+	decoder->state.insn_op = INTEL_PT_OP_OTHER;
+	decoder->state.insn_len = 0;
 
 	if (decoder->set_fup_cfe_ip || decoder->set_fup_cfe) {
 		bool ip = decoder->set_fup_cfe_ip;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index f38893e0b0..4db9a098f5 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -764,6 +764,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 
 	addr_location__init(&al);
 	intel_pt_insn->length = 0;
+	intel_pt_insn->op = INTEL_PT_OP_OTHER;
 
 	if (to_ip && *ip == to_ip)
 		goto out_no_cache;
@@ -898,6 +899,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 
 			if (to_ip && *ip == to_ip) {
 				intel_pt_insn->length = 0;
+				intel_pt_insn->op = INTEL_PT_OP_OTHER;
 				goto out_no_cache;
 			}
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 527517db31..07c22f765f 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1549,8 +1549,8 @@ static int machine__update_kernel_mmap(struct machine *machine,
 	updated = map__get(orig);
 
 	machine->vmlinux_map = updated;
-	machine__set_kernel_mmap(machine, start, end);
 	maps__remove(machine__kernel_maps(machine), orig);
+	machine__set_kernel_mmap(machine, start, end);
 	err = maps__insert(machine__kernel_maps(machine), updated);
 	map__put(orig);
 
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 8f04d3b7f3..59fbbba796 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -7,6 +7,8 @@
 #include <linux/types.h>
 #include <linux/perf_event.h>
 #include "util/evsel_fprintf.h"
+#include "util/pmu.h"
+#include "util/pmus.h"
 #include "trace-event.h"
 
 struct bit_names {
@@ -75,9 +77,12 @@ static void __p_read_format(char *buf, size_t size, u64 value)
 }
 
 #define ENUM_ID_TO_STR_CASE(x) case x: return (#x);
-static const char *stringify_perf_type_id(u64 value)
+static const char *stringify_perf_type_id(struct perf_pmu *pmu, u32 type)
 {
-	switch (value) {
+	if (pmu)
+		return pmu->name;
+
+	switch (type) {
 	ENUM_ID_TO_STR_CASE(PERF_TYPE_HARDWARE)
 	ENUM_ID_TO_STR_CASE(PERF_TYPE_SOFTWARE)
 	ENUM_ID_TO_STR_CASE(PERF_TYPE_TRACEPOINT)
@@ -175,9 +180,9 @@ do {								\
 #define print_id_unsigned(_s)	PRINT_ID(_s, "%"PRIu64)
 #define print_id_hex(_s)	PRINT_ID(_s, "%#"PRIx64)
 
-static void __p_type_id(char *buf, size_t size, u64 value)
+static void __p_type_id(struct perf_pmu *pmu, char *buf, size_t size, u64 value)
 {
-	print_id_unsigned(stringify_perf_type_id(value));
+	print_id_unsigned(stringify_perf_type_id(pmu, value));
 }
 
 static void __p_config_hw_id(char *buf, size_t size, u64 value)
@@ -217,8 +222,14 @@ static void __p_config_tracepoint_id(char *buf, size_t size, u64 value)
 }
 #endif
 
-static void __p_config_id(char *buf, size_t size, u32 type, u64 value)
+static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type, u64 value)
 {
+	const char *name = perf_pmu__name_from_config(pmu, value);
+
+	if (name) {
+		print_id_hex(name);
+		return;
+	}
 	switch (type) {
 	case PERF_TYPE_HARDWARE:
 		return __p_config_hw_id(buf, size, value);
@@ -246,8 +257,8 @@ static void __p_config_id(char *buf, size_t size, u32 type, u64 value)
 #define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
 #define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
 #define p_read_format(val)	__p_read_format(buf, BUF_SIZE, val)
-#define p_type_id(val)		__p_type_id(buf, BUF_SIZE, val)
-#define p_config_id(val)	__p_config_id(buf, BUF_SIZE, attr->type, val)
+#define p_type_id(val)		__p_type_id(pmu, buf, BUF_SIZE, val)
+#define p_config_id(val)	__p_config_id(pmu, buf, BUF_SIZE, attr->type, val)
 
 #define PRINT_ATTRn(_n, _f, _p, _a)			\
 do {							\
@@ -262,6 +273,7 @@ do {							\
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 			     attr__fprintf_f attr__fprintf, void *priv)
 {
+	struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
 	char buf[BUF_SIZE];
 	int ret = 0;
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index f39cbbc1a7..cc349d9cb0 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -36,6 +36,18 @@ struct perf_pmu perf_pmu__fake = {
 
 #define UNIT_MAX_LEN	31 /* max length for event unit name */
 
+enum event_source {
+	/* An event loaded from /sys/devices/<pmu>/events. */
+	EVENT_SRC_SYSFS,
+	/* An event loaded from a CPUID matched json file. */
+	EVENT_SRC_CPU_JSON,
+	/*
+	 * An event loaded from a /sys/devices/<pmu>/identifier matched json
+	 * file.
+	 */
+	EVENT_SRC_SYS_JSON,
+};
+
 /**
  * struct perf_pmu_alias - An event either read from sysfs or builtin in
  * pmu-events.c, created by parsing the pmu-events json files.
@@ -425,9 +437,30 @@ static struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu,
 {
 	struct perf_pmu_alias *alias;
 
-	if (load && !pmu->sysfs_aliases_loaded)
-		pmu_aliases_parse(pmu);
+	if (load && !pmu->sysfs_aliases_loaded) {
+		bool has_sysfs_event;
+		char event_file_name[FILENAME_MAX + 8];
+
+		/*
+		 * Test if alias/event 'name' exists in the PMU's sysfs/events
+		 * directory. If not skip parsing the sysfs aliases. Sysfs event
+		 * name must be all lower or all upper case.
+		 */
+		scnprintf(event_file_name, sizeof(event_file_name), "events/%s", name);
+		for (size_t i = 7, n = 7 + strlen(name); i < n; i++)
+			event_file_name[i] = tolower(event_file_name[i]);
+
+		has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name);
+		if (!has_sysfs_event) {
+			for (size_t i = 7, n = 7 + strlen(name); i < n; i++)
+				event_file_name[i] = toupper(event_file_name[i]);
+
+			has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name);
+		}
+		if (has_sysfs_event)
+			pmu_aliases_parse(pmu);
 
+	}
 	list_for_each_entry(alias, &pmu->aliases, list) {
 		if (!strcasecmp(alias->name, name))
 			return alias;
@@ -500,7 +533,7 @@ static int update_alias(const struct pmu_event *pe,
 
 static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 				const char *desc, const char *val, FILE *val_fd,
-				const struct pmu_event *pe)
+			        const struct pmu_event *pe, enum event_source src)
 {
 	struct perf_pmu_alias *alias;
 	int ret;
@@ -552,25 +585,30 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 		}
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
-	if (!pe) {
-		/* Update an event from sysfs with json data. */
-		struct update_alias_data data = {
-			.pmu = pmu,
-			.alias = alias,
-		};
-
+	switch (src) {
+	default:
+	case EVENT_SRC_SYSFS:
 		alias->from_sysfs = true;
 		if (pmu->events_table) {
+			/* Update an event from sysfs with json data. */
+			struct update_alias_data data = {
+				.pmu = pmu,
+				.alias = alias,
+			};
 			if (pmu_events_table__find_event(pmu->events_table, pmu, name,
 							 update_alias, &data) == 0)
-				pmu->loaded_json_aliases++;
+				pmu->cpu_json_aliases++;
 		}
-	}
-
-	if (!pe)
 		pmu->sysfs_aliases++;
-	else
-		pmu->loaded_json_aliases++;
+		break;
+	case  EVENT_SRC_CPU_JSON:
+		pmu->cpu_json_aliases++;
+		break;
+	case  EVENT_SRC_SYS_JSON:
+		pmu->sys_json_aliases++;
+		break;
+
+	}
 	list_add_tail(&alias->list, &pmu->aliases);
 	return 0;
 }
@@ -646,7 +684,8 @@ static int pmu_aliases_parse(struct perf_pmu *pmu)
 		}
 
 		if (perf_pmu__new_alias(pmu, name, /*desc=*/ NULL,
-					/*val=*/ NULL, file, /*pe=*/ NULL) < 0)
+					/*val=*/ NULL, file, /*pe=*/ NULL,
+					EVENT_SRC_SYSFS) < 0)
 			pr_debug("Cannot set up %s\n", name);
 		fclose(file);
 	}
@@ -900,7 +939,8 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
 {
 	struct perf_pmu *pmu = vdata;
 
-	perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, pe);
+	perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL,
+			    pe, EVENT_SRC_CPU_JSON);
 	return 0;
 }
 
@@ -935,13 +975,14 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe,
 		return 0;
 
 	if (pmu_uncore_alias_match(pe->pmu, pmu->name) &&
-			pmu_uncore_identifier_match(pe->compat, pmu->id)) {
+	    pmu_uncore_identifier_match(pe->compat, pmu->id)) {
 		perf_pmu__new_alias(pmu,
 				pe->name,
 				pe->desc,
 				pe->event,
 				/*val_fd=*/ NULL,
-				pe);
+				pe,
+				EVENT_SRC_SYS_JSON);
 	}
 
 	return 0;
@@ -1035,6 +1076,12 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 	pmu->max_precise = pmu_max_precise(dirfd, pmu);
 	pmu->alias_name = pmu_find_alias_name(pmu, dirfd);
 	pmu->events_table = perf_pmu__find_events_table(pmu);
+	/*
+	 * Load the sys json events/aliases when loading the PMU as each event
+	 * may have a different compat regular expression. We therefore can't
+	 * know the number of sys json events/aliases without computing the
+	 * regular expressions for them all.
+	 */
 	pmu_add_sys_aliases(pmu);
 	list_add_tail(&pmu->list, pmus);
 
@@ -1632,15 +1679,15 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu)
 {
 	size_t nr;
 
-	if (!pmu->sysfs_aliases_loaded)
-		pmu_aliases_parse(pmu);
-
-	nr = pmu->sysfs_aliases;
+	pmu_aliases_parse(pmu);
+	nr = pmu->sysfs_aliases + pmu->sys_json_aliases;;
 
 	if (pmu->cpu_aliases_added)
-		 nr += pmu->loaded_json_aliases;
+		 nr += pmu->cpu_json_aliases;
 	else if (pmu->events_table)
-		nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->loaded_json_aliases;
+		nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->cpu_json_aliases;
+	else
+		assert(pmu->cpu_json_aliases == 0);
 
 	return pmu->selectable ? nr + 1 : nr;
 }
@@ -1693,6 +1740,7 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 	struct strbuf sb;
 
 	strbuf_init(&sb, /*hint=*/ 0);
+	pmu_aliases_parse(pmu);
 	pmu_add_cpu_aliases(pmu);
 	list_for_each_entry(event, &pmu->aliases, list) {
 		size_t buf_used;
@@ -2085,3 +2133,22 @@ void perf_pmu__delete(struct perf_pmu *pmu)
 	zfree(&pmu->id);
 	free(pmu);
 }
+
+const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config)
+{
+	struct perf_pmu_alias *event;
+
+	if (!pmu)
+		return NULL;
+
+	pmu_aliases_parse(pmu);
+	pmu_add_cpu_aliases(pmu);
+	list_for_each_entry(event, &pmu->aliases, list) {
+		struct perf_event_attr attr = {.config = 0,};
+		int ret = perf_pmu__config(pmu, &attr, &event->terms, NULL);
+
+		if (ret == 0 && config == attr.config)
+			return event->name;
+	}
+	return NULL;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index e35d985206..77c59ebc05 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -123,8 +123,10 @@ struct perf_pmu {
 	const struct pmu_events_table *events_table;
 	/** @sysfs_aliases: Number of sysfs aliases loaded. */
 	uint32_t sysfs_aliases;
-	/** @sysfs_aliases: Number of json event aliases loaded. */
-	uint32_t loaded_json_aliases;
+	/** @cpu_json_aliases: Number of json event aliases loaded specific to the CPUID. */
+	uint32_t cpu_json_aliases;
+	/** @sys_json_aliases: Number of json event aliases loaded matching the PMU's identifier. */
+	uint32_t sys_json_aliases;
 	/** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */
 	bool sysfs_aliases_loaded;
 	/**
@@ -273,5 +275,6 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
 void perf_pmu__delete(struct perf_pmu *pmu);
 struct perf_pmu *perf_pmus__find_core_pmu(void);
+const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config);
 
 #endif /* __PMU_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 2a0ad9ecf0..5c12459e97 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -11,6 +11,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <errno.h>
+#include <libgen.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <stdlib.h>
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 075c0f79b1..0aeb97c11c 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -103,6 +103,16 @@ int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char
 	return EOF;
 }
 
+const char *perf_pmu__name_from_config(struct perf_pmu *pmu __maybe_unused, u64 config __maybe_unused)
+{
+	return NULL;
+}
+
+struct perf_pmu *perf_pmus__find_by_type(unsigned int type __maybe_unused)
+{
+	return NULL;
+}
+
 int perf_pmus__num_core_pmus(void)
 {
 	return 1;
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index bfc1d705f4..91d2f7f65d 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -1223,6 +1223,9 @@ static void print_metric_headers(struct perf_stat_config *config,
 
 	/* Print metrics headers only */
 	evlist__for_each_entry(evlist, counter) {
+		if (config->aggr_mode != AGGR_NONE && counter->metric_leader != counter)
+			continue;
+
 		os.evsel = counter;
 
 		perf_stat__print_shadow_stats(config, counter, 0,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 9ebdb8e13c..68dbeae8d2 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1287,7 +1287,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 {
 	struct maps *kmaps = map__kmaps(map);
 	struct kcore_mapfn_data md;
-	struct map *replacement_map = NULL;
+	struct map *map_ref, *replacement_map = NULL;
 	struct machine *machine;
 	bool is_64_bit;
 	int err, fd;
@@ -1365,6 +1365,24 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	if (!replacement_map)
 		replacement_map = list_entry(md.maps.next, struct map_list_node, node)->map;
 
+	/*
+	 * Update addresses of vmlinux map. Re-insert it to ensure maps are
+	 * correctly ordered. Do this before using maps__merge_in() for the
+	 * remaining maps so vmlinux gets split if necessary.
+	 */
+	map_ref = map__get(map);
+	maps__remove(kmaps, map_ref);
+
+	map__set_start(map_ref, map__start(replacement_map));
+	map__set_end(map_ref, map__end(replacement_map));
+	map__set_pgoff(map_ref, map__pgoff(replacement_map));
+	map__set_mapping_type(map_ref, map__mapping_type(replacement_map));
+
+	err = maps__insert(kmaps, map_ref);
+	map__put(map_ref);
+	if (err)
+		goto out_err;
+
 	/* Add new maps */
 	while (!list_empty(&md.maps)) {
 		struct map_list_node *new_node = list_entry(md.maps.next, struct map_list_node, node);
@@ -1372,22 +1390,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 
 		list_del_init(&new_node->node);
 
-		if (RC_CHK_EQUAL(new_map, replacement_map)) {
-			struct map *map_ref;
-
-			map__set_start(map, map__start(new_map));
-			map__set_end(map, map__end(new_map));
-			map__set_pgoff(map, map__pgoff(new_map));
-			map__set_mapping_type(map, map__mapping_type(new_map));
-			/* Ensure maps are correctly ordered */
-			map_ref = map__get(map);
-			maps__remove(kmaps, map_ref);
-			err = maps__insert(kmaps, map_ref);
-			map__put(map_ref);
-			map__put(new_map);
-			if (err)
-				goto out_err;
-		} else {
+		/* skip if replacement_map, already inserted above */
+		if (!RC_CHK_EQUAL(new_map, replacement_map)) {
 			/*
 			 * Merge kcore map into existing maps,
 			 * and ensure that current maps (eBPF)
@@ -1969,6 +1973,10 @@ out:
 	return ret;
 }
 
+/*
+ * Always takes ownership of vmlinux when vmlinux_allocated == true, even if
+ * it returns an error.
+ */
 int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, bool vmlinux_allocated)
 {
@@ -1987,8 +1995,11 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	else
 		symtab_type = DSO_BINARY_TYPE__VMLINUX;
 
-	if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type))
+	if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type)) {
+		if (vmlinux_allocated)
+			free((char *) vmlinux);
 		return -1;
+	}
 
 	/*
 	 * dso__load_sym() may copy 'dso' which will result in the copies having
@@ -2031,7 +2042,6 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map)
 		err = dso__load_vmlinux(dso, map, filename, true);
 		if (err > 0)
 			goto out;
-		free(filename);
 	}
 out:
 	return err;
@@ -2183,7 +2193,6 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map)
 		err = dso__load_vmlinux(dso, map, filename, true);
 		if (err > 0)
 			return err;
-		free(filename);
 	}
 
 	if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1aa8962dcf..515726489e 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -39,12 +39,13 @@ int thread__init_maps(struct thread *thread, struct machine *machine)
 
 struct thread *thread__new(pid_t pid, pid_t tid)
 {
-	char *comm_str;
-	struct comm *comm;
 	RC_STRUCT(thread) *_thread = zalloc(sizeof(*_thread));
 	struct thread *thread;
 
 	if (ADD_RC_CHK(thread, _thread) != NULL) {
+		struct comm *comm;
+		char comm_str[32];
+
 		thread__set_pid(thread, pid);
 		thread__set_tid(thread, tid);
 		thread__set_ppid(thread, -1);
@@ -56,13 +57,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		init_rwsem(thread__namespaces_lock(thread));
 		init_rwsem(thread__comm_lock(thread));
 
-		comm_str = malloc(32);
-		if (!comm_str)
-			goto err_thread;
-
-		snprintf(comm_str, 32, ":%d", tid);
+		snprintf(comm_str, sizeof(comm_str), ":%d", tid);
 		comm = comm__new(comm_str, 0, false);
-		free(comm_str);
 		if (!comm)
 			goto err_thread;
 
@@ -76,7 +72,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 	return thread;
 
 err_thread:
-	free(thread);
+	thread__delete(thread);
 	return NULL;
 }
 
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 35ee41e435..0d0ca63de8 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -3,6 +3,7 @@
 
 #include <linux/platform_device.h>
 #include <linux/mod_devicetable.h>
+#include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/sizes.h>
diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile
index 5af9ba8a46..c1ce39874e 100644
--- a/tools/testing/selftests/alsa/Makefile
+++ b/tools/testing/selftests/alsa/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 #
 
-CFLAGS += $(shell pkg-config --cflags alsa)
+CFLAGS += $(shell pkg-config --cflags alsa) $(KHDR_INCLUDES)
 LDLIBS += $(shell pkg-config --libs alsa)
 ifeq ($(LDLIBS),)
 LDLIBS += -lasound
diff --git a/tools/testing/selftests/arm64/tags/tags_test.c b/tools/testing/selftests/arm64/tags/tags_test.c
index 5701163460..955f87c117 100644
--- a/tools/testing/selftests/arm64/tags/tags_test.c
+++ b/tools/testing/selftests/arm64/tags/tags_test.c
@@ -6,6 +6,7 @@
 #include <stdint.h>
 #include <sys/prctl.h>
 #include <sys/utsname.h>
+#include "../../kselftest.h"
 
 #define SHIFT_TAG(tag)		((uint64_t)(tag) << 56)
 #define SET_TAG(ptr, tag)	(((uint64_t)(ptr) & ~SHIFT_TAG(0xff)) | \
@@ -21,6 +22,9 @@ int main(void)
 	if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE, 0, 0, 0) == 0)
 		tbi_enabled = 1;
 	ptr = (struct utsname *)malloc(sizeof(*ptr));
+	if (!ptr)
+		ksft_exit_fail_msg("Failed to allocate utsname buffer\n");
+
 	if (tbi_enabled)
 		tag = 0x42;
 	ptr = (struct utsname *)SET_TAG(ptr, tag);
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 19be9c63d5..e812876d79 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -508,6 +508,9 @@ int cgroup_setup_and_join(const char *path) {
 /**
  * setup_classid_environment() - Setup the cgroupv1 net_cls environment
  *
+ * This function should only be called in a custom mount namespace, e.g.
+ * created by running setup_cgroup_environment.
+ *
  * After calling this function, cleanup_classid_environment should be called
  * once testing is complete.
  *
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 6db27a9088..be96bf0223 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -461,6 +461,8 @@ struct nstoken *open_netns(const char *name)
 
 	return token;
 fail:
+	if (token->orig_netns_fd != -1)
+		close(token->orig_netns_fd);
 	free(token);
 	return NULL;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
index a8b53b8736..f66ceccd70 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
@@ -25,7 +25,7 @@ static void test_lookup_update(void)
 	int map1_fd, map2_fd, map3_fd, map4_fd, map5_fd, map1_id, map2_id;
 	int outer_arr_fd, outer_hash_fd, outer_arr_dyn_fd;
 	struct test_btf_map_in_map *skel;
-	int err, key = 0, val, i, fd;
+	int err, key = 0, val, i;
 
 	skel = test_btf_map_in_map__open_and_load();
 	if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n"))
@@ -102,30 +102,6 @@ static void test_lookup_update(void)
 	CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n");
 	CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n");
 
-	test_btf_map_in_map__destroy(skel);
-	skel = NULL;
-
-	/* we need to either wait for or force synchronize_rcu(), before
-	 * checking for "still exists" condition, otherwise map could still be
-	 * resolvable by ID, causing false positives.
-	 *
-	 * Older kernels (5.8 and earlier) freed map only after two
-	 * synchronize_rcu()s, so trigger two, to be entirely sure.
-	 */
-	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
-	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
-
-	fd = bpf_map_get_fd_by_id(map1_id);
-	if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) {
-		close(fd);
-		goto cleanup;
-	}
-	fd = bpf_map_get_fd_by_id(map2_id);
-	if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) {
-		close(fd);
-		goto cleanup;
-	}
-
 cleanup:
 	test_btf_map_in_map__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
index 74d6d7546f..25332e5967 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
@@ -87,9 +87,12 @@ void test_cgroup1_hierarchy(void)
 		goto destroy;
 
 	/* Setup cgroup1 hierarchy */
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto destroy;
 	err = setup_classid_environment();
 	if (!ASSERT_OK(err, "setup_classid_environment"))
-		goto destroy;
+		goto cleanup_cgroup;
 
 	err = join_classid();
 	if (!ASSERT_OK(err, "join_cgroup1"))
@@ -153,6 +156,8 @@ void test_cgroup1_hierarchy(void)
 
 cleanup:
 	cleanup_classid_environment();
+cleanup_cgroup:
+	cleanup_cgroup_environment();
 destroy:
 	test_cgroup1_hierarchy__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 8269cdee33..38fda42fd7 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -397,7 +397,7 @@ static void test_attach_api_fails(void)
 	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
 	if (!ASSERT_ERR(link_fd, "link_fd"))
 		goto cleanup;
-	ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong");
+	ASSERT_EQ(link_fd, -EINVAL, "pid_is_wrong");
 
 cleanup:
 	if (link_fd >= 0)
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
index 498d3bdaa4..bad0ea167b 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
@@ -107,8 +107,8 @@ void test_xdp_do_redirect(void)
 			    .attach_point = BPF_TC_INGRESS);
 
 	memcpy(&data[sizeof(__u64)], &pkt_udp, sizeof(pkt_udp));
-	*((__u32 *)data) = 0x42; /* metadata test value */
-	*((__u32 *)data + 4) = 0;
+	((__u32 *)data)[0] = 0x42; /* metadata test value */
+	((__u32 *)data)[1] = 0;
 
 	skel = test_xdp_do_redirect__open();
 	if (!ASSERT_OK_PTR(skel, "skel"))
diff --git a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c
index e4bfbba6c1..c8ec0d0368 100644
--- a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c
+++ b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c
@@ -61,14 +61,15 @@ SEC("lsm.s/socket_post_create")
 int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 	     int protocol, int kern)
 {
+	struct sock *sk = sock->sk;
 	struct storage *stg;
 	__u32 pid;
 
 	pid = bpf_get_current_pid_tgid() >> 32;
-	if (pid != bench_pid)
+	if (pid != bench_pid || !sk)
 		return 0;
 
-	stg = bpf_sk_storage_get(&sk_storage_map, sock->sk, NULL,
+	stg = bpf_sk_storage_get(&sk_storage_map, sk, NULL,
 				 BPF_LOCAL_STORAGE_GET_F_CREATE);
 
 	if (stg)
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index e5e3a8b8dd..637e75df2e 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -140,11 +140,12 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
 	struct local_storage *storage;
+	struct sock *sk = sock->sk;
 
-	if (pid != monitored_pid)
+	if (pid != monitored_pid || !sk)
 		return 0;
 
-	storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0, 0);
+	storage = bpf_sk_storage_get(&sk_storage_map, sk, 0, 0);
 	if (!storage)
 		return 0;
 
@@ -155,24 +156,24 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
 	/* This tests that we can associate multiple elements
 	 * with the local storage.
 	 */
-	storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0,
+	storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0,
 				     BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
 
-	if (bpf_sk_storage_delete(&sk_storage_map2, sock->sk))
+	if (bpf_sk_storage_delete(&sk_storage_map2, sk))
 		return 0;
 
-	storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0,
+	storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0,
 				     BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
 
-	if (bpf_sk_storage_delete(&sk_storage_map, sock->sk))
+	if (bpf_sk_storage_delete(&sk_storage_map, sk))
 		return 0;
 
 	/* Ensure that the sk_storage_map is disconnected from the storage. */
-	if (!sock->sk->sk_bpf_storage || sock->sk->sk_bpf_storage->smap)
+	if (!sk->sk_bpf_storage || sk->sk_bpf_storage->smap)
 		return 0;
 
 	sk_storage_result = 0;
@@ -185,11 +186,12 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
 	struct local_storage *storage;
+	struct sock *sk = sock->sk;
 
-	if (pid != monitored_pid)
+	if (pid != monitored_pid || !sk)
 		return 0;
 
-	storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
+	storage = bpf_sk_storage_get(&sk_storage_map, sk, 0,
 				     BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/lsm_cgroup.c b/tools/testing/selftests/bpf/progs/lsm_cgroup.c
index 02c11d16b6..d7598538aa 100644
--- a/tools/testing/selftests/bpf/progs/lsm_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/lsm_cgroup.c
@@ -103,11 +103,15 @@ static __always_inline int real_bind(struct socket *sock,
 				     int addrlen)
 {
 	struct sockaddr_ll sa = {};
+	struct sock *sk = sock->sk;
 
-	if (sock->sk->__sk_common.skc_family != AF_PACKET)
+	if (!sk)
+		return 1;
+
+	if (sk->__sk_common.skc_family != AF_PACKET)
 		return 1;
 
-	if (sock->sk->sk_kern_sock)
+	if (sk->sk_kern_sock)
 		return 1;
 
 	bpf_probe_read_kernel(&sa, sizeof(sa), address);
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
index baff5ffe94..a9fc30ed4d 100644
--- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
+++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
@@ -8,6 +8,13 @@
 #include "xdp_metadata.h"
 #include "bpf_kfuncs.h"
 
+/* The compiler may be able to detect the access to uninitialized
+   memory in the routines performing out of bound memory accesses and
+   emit warnings about it.  This is the case of GCC. */
+#if !defined(__clang__)
+#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
+#endif
+
 int arr[1];
 int unkn_idx;
 const volatile bool call_dead_subprog = false;
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 024a0faafb..43612de44f 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -2104,9 +2104,9 @@ out:
 		free(options.whitelist);
 	if (options.blacklist)
 		free(options.blacklist);
+	close(cg_fd);
 	if (cg_created)
 		cleanup_cgroup_environment();
-	close(cg_fd);
 	return err;
 }
 
diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh
index 910044f089..7989ec6084 100755
--- a/tools/testing/selftests/bpf/test_tc_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh
@@ -72,7 +72,6 @@ cleanup() {
 server_listen() {
 	ip netns exec "${ns2}" nc "${netcat_opt}" -l "${port}" > "${outfile}" &
 	server_pid=$!
-	sleep 0.2
 }
 
 client_connect() {
@@ -93,6 +92,16 @@ verify_data() {
 	fi
 }
 
+wait_for_port() {
+	for i in $(seq 20); do
+		if ip netns exec "${ns2}" ss ${2:--4}OHntl | grep -q "$1"; then
+			return 0
+		fi
+		sleep 0.1
+	done
+	return 1
+}
+
 set -e
 
 # no arguments: automated test, run all
@@ -193,6 +202,7 @@ setup
 # basic communication works
 echo "test basic connectivity"
 server_listen
+wait_for_port ${port} ${netcat_opt}
 client_connect
 verify_data
 
@@ -204,6 +214,7 @@ ip netns exec "${ns1}" tc filter add dev veth1 egress \
 	section "encap_${tuntype}_${mac}"
 echo "test bpf encap without decap (expect failure)"
 server_listen
+wait_for_port ${port} ${netcat_opt}
 ! client_connect
 
 if [[ "$tuntype" =~ "udp" ]]; then
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 0340d4ca8f..432db923bc 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -195,10 +195,10 @@ int cg_write_numeric(const char *cgroup, const char *control, long value)
 	return cg_write(cgroup, control, buf);
 }
 
-int cg_find_unified_root(char *root, size_t len)
+int cg_find_unified_root(char *root, size_t len, bool *nsdelegate)
 {
 	char buf[10 * PAGE_SIZE];
-	char *fs, *mount, *type;
+	char *fs, *mount, *type, *options;
 	const char delim[] = "\n\t ";
 
 	if (read_text("/proc/self/mounts", buf, sizeof(buf)) <= 0)
@@ -211,12 +211,14 @@ int cg_find_unified_root(char *root, size_t len)
 	for (fs = strtok(buf, delim); fs; fs = strtok(NULL, delim)) {
 		mount = strtok(NULL, delim);
 		type = strtok(NULL, delim);
-		strtok(NULL, delim);
+		options = strtok(NULL, delim);
 		strtok(NULL, delim);
 		strtok(NULL, delim);
 
 		if (strcmp(type, "cgroup2") == 0) {
 			strncpy(root, mount, len);
+			if (nsdelegate)
+				*nsdelegate = !!strstr(options, "nsdelegate");
 			return 0;
 		}
 	}
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index 1df7f20221..89e8519fb2 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -21,7 +21,7 @@ static inline int values_close(long a, long b, int err)
 	return abs(a - b) <= (a + b) / 100 * err;
 }
 
-extern int cg_find_unified_root(char *root, size_t len);
+extern int cg_find_unified_root(char *root, size_t len, bool *nsdelegate);
 extern char *cg_name(const char *root, const char *name);
 extern char *cg_name_indexed(const char *root, const char *name, int index);
 extern char *cg_control(const char *cgroup, const char *control);
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 80aa6b2373..a5672a91d2 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -18,6 +18,8 @@
 #include "../kselftest.h"
 #include "cgroup_util.h"
 
+static bool nsdelegate;
+
 static int touch_anon(char *buf, size_t size)
 {
 	int fd;
@@ -775,6 +777,9 @@ static int test_cgcore_lesser_ns_open(const char *root)
 	pid_t pid;
 	int status;
 
+	if (!nsdelegate)
+		return KSFT_SKIP;
+
 	cg_test_a = cg_name(root, "cg_test_a");
 	cg_test_b = cg_name(root, "cg_test_b");
 
@@ -862,7 +867,7 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), &nsdelegate))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
index 24020a2c68..186bf96f6a 100644
--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -700,7 +700,7 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	if (cg_read_strstr(root, "cgroup.subtree_control", "cpu"))
diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c
index b061ed1e05..4034d14ba6 100644
--- a/tools/testing/selftests/cgroup/test_cpuset.c
+++ b/tools/testing/selftests/cgroup/test_cpuset.c
@@ -249,7 +249,7 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	if (cg_read_strstr(root, "cgroup.subtree_control", "cpuset"))
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
index 8845353aca..8730645d36 100644
--- a/tools/testing/selftests/cgroup/test_freezer.c
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -827,7 +827,7 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
diff --git a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
index f0fefeb4cc..856f9508ea 100644
--- a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
+++ b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
@@ -214,7 +214,7 @@ int main(int argc, char **argv)
 		return ret;
 	}
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	switch (test_hugetlb_memcg(root)) {
diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c
index 6153690319..0e5bb6c730 100644
--- a/tools/testing/selftests/cgroup/test_kill.c
+++ b/tools/testing/selftests/cgroup/test_kill.c
@@ -276,7 +276,7 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index c82f974b85..137506db03 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -420,7 +420,7 @@ int main(int argc, char **argv)
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	/*
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index c7c9572003..b462416b38 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -1314,7 +1314,7 @@ int main(int argc, char **argv)
 	char root[PATH_MAX];
 	int i, proc_status, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	/*
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
index f0e488ed90..ef7f395453 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -440,7 +440,7 @@ int main(int argc, char **argv)
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	if (!zswap_configured())
diff --git a/tools/testing/selftests/damon/_damon_sysfs.py b/tools/testing/selftests/damon/_damon_sysfs.py
index d23d7398a2..fe77d7e73a 100644
--- a/tools/testing/selftests/damon/_damon_sysfs.py
+++ b/tools/testing/selftests/damon/_damon_sysfs.py
@@ -287,6 +287,8 @@ class DamonCtx:
         nr_schemes_file = os.path.join(
                 self.sysfs_dir(), 'schemes', 'nr_schemes')
         content, err = read_file(nr_schemes_file)
+        if err is not None:
+            return err
         if int(content) != len(self.schemes):
             err = write_file(nr_schemes_file, '%d' % len(self.schemes))
             if err != None:
diff --git a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
index 6369927e9c..48395cfd4f 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
@@ -42,7 +42,7 @@ __mlxsw_only_on_spectrum()
 	local src=$1; shift
 
 	if ! mlxsw_on_spectrum "$rev"; then
-		log_test_skip $src:$caller "(Spectrum-$rev only)"
+		log_test_xfail $src:$caller "(Spectrum-$rev only)"
 		return 1
 	fi
 }
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
index a88d8a8c85..899b689260 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
@@ -47,7 +47,6 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
 		RET=0
 		target=$(${current_test}_get_target "$should_fail")
 		if ((target == 0)); then
-			log_test_skip "'$current_test' should_fail=$should_fail test"
 			continue
 		fi
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index f981c957f0..482ebb744e 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -52,7 +52,6 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
 			RET=0
 			target=$(${current_test}_get_target "$should_fail")
 			if ((target == 0)); then
-				log_test_skip "'$current_test' [$profile] should_fail=$should_fail test"
 				continue
 			fi
 			${current_test}_setup_prepare
diff --git a/tools/testing/selftests/filesystems/binderfs/Makefile b/tools/testing/selftests/filesystems/binderfs/Makefile
index c2f7cef919..eb4c3b4119 100644
--- a/tools/testing/selftests/filesystems/binderfs/Makefile
+++ b/tools/testing/selftests/filesystems/binderfs/Makefile
@@ -3,6 +3,4 @@
 CFLAGS += $(KHDR_INCLUDES) -pthread
 TEST_GEN_PROGS := binderfs_test
 
-binderfs_test: binderfs_test.c ../../kselftest.h ../../kselftest_harness.h
-
 include ../../lib.mk
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc
index b9c21a81d2..c0cdad4c40 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc
@@ -53,7 +53,7 @@ fi
 
 echo > dynamic_events
 
-if [ "$FIELDS" ] ; then
+if [ "$FIELDS" -a "$FPROBES" ] ; then
 echo "t:tpevent ${TP2} obj_size=s->object_size" >> dynamic_events
 echo "f:fpevent ${TP3}%return path=\$retval->name:string" >> dynamic_events
 echo "t:tpevent2 ${TP4} p->se.group_node.next->prev" >> dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_entry_arg.tc b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_entry_arg.tc
index d183b8a8ec..1e251ce299 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_entry_arg.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_entry_arg.tc
@@ -11,7 +11,7 @@ echo 1 > events/tests/enable
 echo > trace
 cat trace > /dev/null
 
-function streq() {
+streq() {
 	test $1 = $2
 }
 
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc b/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc
index d3a79da215..5f72abe6fa 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc
@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 # description: Generic dynamic event - check if duplicate events are caught
-# requires: dynamic_events "e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]":README
+# requires: dynamic_events "e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]":README events/syscalls/sys_enter_openat
 
 echo 0 > events/enable
 
diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
index 3f74c09c56..118247b8dd 100644
--- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
+++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
@@ -10,7 +10,6 @@ fail() { #msg
 }
 
 sample_events() {
-    echo > trace
     echo 1 > events/kmem/kmem_cache_free/enable
     echo 1 > tracing_on
     ls > /dev/null
@@ -22,6 +21,7 @@ echo 0 > tracing_on
 echo 0 > events/enable
 
 echo "Get the most frequently calling function"
+echo > trace
 sample_events
 
 target_func=`cat trace | grep -o 'call_site=\([^+]*\)' | sed 's/call_site=//' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'`
@@ -32,7 +32,16 @@ echo > trace
 
 echo "Test event filter function name"
 echo "call_site.function == $target_func" > events/kmem/kmem_cache_free/filter
+
+sample_events
+max_retry=10
+while [ `grep kmem_cache_free trace| wc -l` -eq 0 ]; do
 sample_events
+max_retry=$((max_retry - 1))
+if [ $max_retry -eq 0 ]; then
+	exit_fail
+fi
+done
 
 hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l`
 misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l`
@@ -49,7 +58,16 @@ address=`grep " ${target_func}\$" /proc/kallsyms | cut -d' ' -f1`
 
 echo "Test event filter function address"
 echo "call_site.function == 0x$address" > events/kmem/kmem_cache_free/filter
+echo > trace
+sample_events
+max_retry=10
+while [ `grep kmem_cache_free trace| wc -l` -eq 0 ]; do
 sample_events
+max_retry=$((max_retry - 1))
+if [ $max_retry -eq 0 ]; then
+	exit_fail
+fi
+done
 
 hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l`
 misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l`
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
index 1f6981ef7a..ba19b81cef 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
@@ -30,7 +30,8 @@ find_dot_func() {
 	fi
 
 	grep " [tT] .*\.isra\..*" /proc/kallsyms | cut -f 3 -d " " | while read f; do
-		if grep -s $f available_filter_functions; then
+		cnt=`grep -s $f available_filter_functions | wc -l`;
+		if [ $cnt -eq 1 ]; then
 			echo $f
 			break
 		fi
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_entry_arg.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_entry_arg.tc
index 53b82f36a1..e50470b531 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_entry_arg.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_entry_arg.tc
@@ -11,7 +11,7 @@ echo 1 > events/kprobes/enable
 echo > trace
 cat trace > /dev/null
 
-function streq() {
+streq() {
 	test $1 = $2
 }
 
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
index 7f3ca5c78d..215c6cb539 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
@@ -360,7 +360,7 @@ out:
 
 int main(int argc, char *argv[])
 {
-	const char *test_name;
+	char *test_name;
 	int c, ret;
 
 	while ((c = getopt(argc, argv, "bchlot:v:")) != -1) {
diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c
index 25110c7c0b..d7a8e321bb 100644
--- a/tools/testing/selftests/kcmp/kcmp_test.c
+++ b/tools/testing/selftests/kcmp/kcmp_test.c
@@ -91,7 +91,7 @@ int main(int argc, char **argv)
 		ksft_print_header();
 		ksft_set_plan(3);
 
-		fd2 = open(kpath, O_RDWR, 0644);
+		fd2 = open(kpath, O_RDWR);
 		if (fd2 < 0) {
 			perror("Can't open file");
 			ksft_exit_fail();
diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh
index f2fbb914e0..79a125eb24 100644
--- a/tools/testing/selftests/kselftest/ktap_helpers.sh
+++ b/tools/testing/selftests/kselftest/ktap_helpers.sh
@@ -43,7 +43,7 @@ __ktap_test() {
 	directive="$3" # optional
 
 	local directive_str=
-	[[ ! -z "$directive" ]] && directive_str="# $directive"
+	[ ! -z "$directive" ] && directive_str="# $directive"
 
 	echo $result $KTAP_TESTNO $description $directive_str
 
@@ -99,7 +99,7 @@ ktap_exit_fail_msg() {
 ktap_finished() {
 	ktap_print_totals
 
-	if [ $(("$KTAP_CNT_PASS" + "$KTAP_CNT_SKIP")) -eq "$KSFT_NUM_TESTS" ]; then
+	if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP)) -eq "$KSFT_NUM_TESTS" ]; then
 		exit "$KSFT_PASS"
 	else
 		exit "$KSFT_FAIL"
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 3c8f2965c2..b634969cbb 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -1216,7 +1216,7 @@ void __run_test(struct __fixture_metadata *f,
 		struct __test_metadata *t)
 {
 	struct __test_xfail *xfail;
-	char *test_name;
+	char test_name[1024];
 	const char *diagnostic;
 
 	/* reset test struct */
@@ -1227,12 +1227,8 @@ void __run_test(struct __fixture_metadata *f,
 	memset(t->env, 0, sizeof(t->env));
 	memset(t->results->reason, 0, sizeof(t->results->reason));
 
-	if (asprintf(&test_name, "%s%s%s.%s", f->name,
-		variant->name[0] ? "." : "", variant->name, t->name) == -1) {
-		ksft_print_msg("ERROR ALLOCATING MEMORY\n");
-		t->exit_code = KSFT_FAIL;
-		_exit(t->exit_code);
-	}
+	snprintf(test_name, sizeof(test_name), "%s%s%s.%s",
+		 f->name, variant->name[0] ? "." : "", variant->name, t->name);
 
 	ksft_print_msg(" RUN           %s ...\n", test_name);
 
@@ -1270,7 +1266,6 @@ void __run_test(struct __fixture_metadata *f,
 
 	ksft_test_result_code(t->exit_code, test_name,
 			      diagnostic ? "%s" : NULL, diagnostic);
-	free(test_name);
 }
 
 static int test_harness_run(int argc, char **argv)
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index da2cade3ba..8ae203d8ed 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -7,6 +7,8 @@ else ifneq ($(filter -%,$(LLVM)),)
 LLVM_SUFFIX := $(LLVM)
 endif
 
+CLANG := $(LLVM_PREFIX)clang$(LLVM_SUFFIX)
+
 CLANG_TARGET_FLAGS_arm          := arm-linux-gnueabi
 CLANG_TARGET_FLAGS_arm64        := aarch64-linux-gnu
 CLANG_TARGET_FLAGS_hexagon      := hexagon-linux-musl
@@ -18,7 +20,13 @@ CLANG_TARGET_FLAGS_riscv        := riscv64-linux-gnu
 CLANG_TARGET_FLAGS_s390         := s390x-linux-gnu
 CLANG_TARGET_FLAGS_x86          := x86_64-linux-gnu
 CLANG_TARGET_FLAGS_x86_64       := x86_64-linux-gnu
-CLANG_TARGET_FLAGS              := $(CLANG_TARGET_FLAGS_$(ARCH))
+
+# Default to host architecture if ARCH is not explicitly given.
+ifeq ($(ARCH),)
+CLANG_TARGET_FLAGS := $(shell $(CLANG) -print-target-triple)
+else
+CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH))
+endif
 
 ifeq ($(CROSS_COMPILE),)
 ifeq ($(CLANG_TARGET_FLAGS),)
@@ -30,7 +38,7 @@ else
 CLANG_FLAGS     += --target=$(notdir $(CROSS_COMPILE:%-=%))
 endif # CROSS_COMPILE
 
-CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as
+CC := $(CLANG) $(CLANG_FLAGS) -fintegrated-as
 else
 CC := $(CROSS_COMPILE)gcc
 endif # LLVM
diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c
index 533999b6c2..e140558e6f 100644
--- a/tools/testing/selftests/mm/compaction_test.c
+++ b/tools/testing/selftests/mm/compaction_test.c
@@ -82,12 +82,16 @@ int prereq(void)
 	return -1;
 }
 
-int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
+int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
+		     unsigned long initial_nr_hugepages)
 {
+	unsigned long nr_hugepages_ul;
 	int fd, ret = -1;
 	int compaction_index = 0;
-	char initial_nr_hugepages[10] = {0};
-	char nr_hugepages[10] = {0};
+	char nr_hugepages[20] = {0};
+	char init_nr_hugepages[20] = {0};
+
+	sprintf(init_nr_hugepages, "%lu", initial_nr_hugepages);
 
 	/* We want to test with 80% of available memory. Else, OOM killer comes
 	   in to play */
@@ -101,21 +105,6 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 		goto out;
 	}
 
-	if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) {
-		ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n",
-			       strerror(errno));
-		goto close_fd;
-	}
-
-	/* Start with the initial condition of 0 huge pages*/
-	if (write(fd, "0", sizeof(char)) != sizeof(char)) {
-		ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n",
-			       strerror(errno));
-		goto close_fd;
-	}
-
-	lseek(fd, 0, SEEK_SET);
-
 	/* Request a large number of huge pages. The Kernel will allocate
 	   as much as it can */
 	if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
@@ -134,22 +123,27 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 
 	/* We should have been able to request at least 1/3 rd of the memory in
 	   huge pages */
-	compaction_index = mem_free/(atoi(nr_hugepages) * hugepage_size);
+	nr_hugepages_ul = strtoul(nr_hugepages, NULL, 10);
+	if (!nr_hugepages_ul) {
+		ksft_print_msg("ERROR: No memory is available as huge pages\n");
+		goto close_fd;
+	}
+	compaction_index = mem_free/(nr_hugepages_ul * hugepage_size);
 
 	lseek(fd, 0, SEEK_SET);
 
-	if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages))
-	    != strlen(initial_nr_hugepages)) {
+	if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages))
+	    != strlen(init_nr_hugepages)) {
 		ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n",
 			       strerror(errno));
 		goto close_fd;
 	}
 
-	ksft_print_msg("Number of huge pages allocated = %d\n",
-		       atoi(nr_hugepages));
+	ksft_print_msg("Number of huge pages allocated = %lu\n",
+		       nr_hugepages_ul);
 
 	if (compaction_index > 3) {
-		ksft_print_msg("ERROR: Less that 1/%d of memory is available\n"
+		ksft_print_msg("ERROR: Less than 1/%d of memory is available\n"
 			       "as huge pages\n", compaction_index);
 		goto close_fd;
 	}
@@ -163,6 +157,41 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 	return ret;
 }
 
+int set_zero_hugepages(unsigned long *initial_nr_hugepages)
+{
+	int fd, ret = -1;
+	char nr_hugepages[20] = {0};
+
+	fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK);
+	if (fd < 0) {
+		ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n",
+			       strerror(errno));
+		goto out;
+	}
+	if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) {
+		ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n",
+			       strerror(errno));
+		goto close_fd;
+	}
+
+	lseek(fd, 0, SEEK_SET);
+
+	/* Start with the initial condition of 0 huge pages */
+	if (write(fd, "0", sizeof(char)) != sizeof(char)) {
+		ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n",
+			       strerror(errno));
+		goto close_fd;
+	}
+
+	*initial_nr_hugepages = strtoul(nr_hugepages, NULL, 10);
+	ret = 0;
+
+ close_fd:
+	close(fd);
+
+ out:
+	return ret;
+}
 
 int main(int argc, char **argv)
 {
@@ -173,14 +202,19 @@ int main(int argc, char **argv)
 	unsigned long mem_free = 0;
 	unsigned long hugepage_size = 0;
 	long mem_fragmentable_MB = 0;
+	unsigned long initial_nr_hugepages;
 
 	ksft_print_header();
 
 	if (prereq() || geteuid())
-		return ksft_exit_skip("Prerequisites unsatisfied\n");
+		ksft_exit_skip("Prerequisites unsatisfied\n");
 
 	ksft_set_plan(1);
 
+	/* Start the test without hugepages reducing mem_free */
+	if (set_zero_hugepages(&initial_nr_hugepages))
+		ksft_exit_fail();
+
 	lim.rlim_cur = RLIM_INFINITY;
 	lim.rlim_max = RLIM_INFINITY;
 	if (setrlimit(RLIMIT_MEMLOCK, &lim))
@@ -224,8 +258,9 @@ int main(int argc, char **argv)
 		entry = entry->next;
 	}
 
-	if (check_compaction(mem_free, hugepage_size) == 0)
-		return ksft_exit_pass();
+	if (check_compaction(mem_free, hugepage_size,
+			     initial_nr_hugepages) == 0)
+		ksft_exit_pass();
 
-	return ksft_exit_fail();
+	ksft_exit_fail();
 }
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index 363bf5f801..fe078d6e18 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -1779,5 +1779,5 @@ int main(int argc, char **argv)
 	if (err)
 		ksft_exit_fail_msg("%d out of %d tests failed\n",
 				   err, ksft_test_num());
-	return ksft_exit_pass();
+	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c
index ad168d35b2..d7eaca5bbe 100644
--- a/tools/testing/selftests/mm/gup_longterm.c
+++ b/tools/testing/selftests/mm/gup_longterm.c
@@ -456,5 +456,5 @@ int main(int argc, char **argv)
 	if (err)
 		ksft_exit_fail_msg("%d out of %d tests failed\n",
 				   err, ksft_test_num());
-	return ksft_exit_pass();
+	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c
index 18a49c70d4..bdeaac67ff 100644
--- a/tools/testing/selftests/mm/gup_test.c
+++ b/tools/testing/selftests/mm/gup_test.c
@@ -1,3 +1,4 @@
+#define __SANE_USERSPACE_TYPES__ // Use ll64
 #include <fcntl.h>
 #include <errno.h>
 #include <stdio.h>
@@ -228,7 +229,7 @@ int main(int argc, char **argv)
 			break;
 		}
 		ksft_test_result_skip("Please run this test as root\n");
-		return ksft_exit_pass();
+		ksft_exit_pass();
 	}
 
 	p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
@@ -267,5 +268,5 @@ int main(int argc, char **argv)
 
 	free(tid);
 
-	return ksft_exit_pass();
+	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c
index d615767e39..508287560c 100644
--- a/tools/testing/selftests/mm/ksm_functional_tests.c
+++ b/tools/testing/selftests/mm/ksm_functional_tests.c
@@ -646,5 +646,5 @@ int main(int argc, char **argv)
 	if (err)
 		ksft_exit_fail_msg("%d out of %d tests failed\n",
 				   err, ksft_test_num());
-	return ksft_exit_pass();
+	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/mm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c
index 17bcb07f19..ef7d911da1 100644
--- a/tools/testing/selftests/mm/madv_populate.c
+++ b/tools/testing/selftests/mm/madv_populate.c
@@ -307,5 +307,5 @@ int main(int argc, char **argv)
 	if (err)
 		ksft_exit_fail_msg("%d out of %d tests failed\n",
 				   err, ksft_test_num());
-	return ksft_exit_pass();
+	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c
index 1e01d3ddc1..200bedcdc3 100644
--- a/tools/testing/selftests/mm/mdwe_test.c
+++ b/tools/testing/selftests/mm/mdwe_test.c
@@ -7,7 +7,6 @@
 #include <linux/mman.h>
 #include <linux/prctl.h>
 
-#define _GNU_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <sys/auxv.h>
diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c
index 301abb99e0..b8a7efe920 100644
--- a/tools/testing/selftests/mm/mkdirty.c
+++ b/tools/testing/selftests/mm/mkdirty.c
@@ -375,5 +375,5 @@ int main(void)
 	if (err)
 		ksft_exit_fail_msg("%d out of %d tests failed\n",
 				   err, ksft_test_num());
-	return ksft_exit_pass();
+	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c
index d59517ed3d..2d785aca72 100644
--- a/tools/testing/selftests/mm/pagemap_ioctl.c
+++ b/tools/testing/selftests/mm/pagemap_ioctl.c
@@ -1484,7 +1484,7 @@ int main(int argc, char *argv[])
 	ksft_print_header();
 
 	if (init_uffd())
-		return ksft_exit_pass();
+		ksft_exit_pass();
 
 	ksft_set_plan(115);
 
@@ -1660,5 +1660,5 @@ int main(int argc, char *argv[])
 	userfaultfd_tests();
 
 	close(pagemap_fd);
-	return ksft_exit_pass();
+	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c
index 7dbfa53d93..d9dbf87974 100644
--- a/tools/testing/selftests/mm/soft-dirty.c
+++ b/tools/testing/selftests/mm/soft-dirty.c
@@ -209,5 +209,5 @@ int main(int argc, char **argv)
 
 	close(pagemap_fd);
 
-	return ksft_exit_pass();
+	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
index cc5629c3d2..a70ae10b5f 100644
--- a/tools/testing/selftests/mm/uffd-common.h
+++ b/tools/testing/selftests/mm/uffd-common.h
@@ -8,6 +8,7 @@
 #define __UFFD_COMMON_H__
 
 #define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__ // Use ll64
 #include <stdio.h>
 #include <errno.h>
 #include <unistd.h>
diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh
index 75528788cb..7e7ed6c558 100755
--- a/tools/testing/selftests/net/amt.sh
+++ b/tools/testing/selftests/net/amt.sh
@@ -77,6 +77,7 @@ readonly LISTENER=$(mktemp -u listener-XXXXXXXX)
 readonly GATEWAY=$(mktemp -u gateway-XXXXXXXX)
 readonly RELAY=$(mktemp -u relay-XXXXXXXX)
 readonly SOURCE=$(mktemp -u source-XXXXXXXX)
+readonly SMCROUTEDIR="$(mktemp -d)"
 ERR=4
 err=0
 
@@ -85,6 +86,11 @@ exit_cleanup()
 	for ns in "$@"; do
 		ip netns delete "${ns}" 2>/dev/null || true
 	done
+	if [ -f "$SMCROUTEDIR/amt.pid" ]; then
+		smcpid=$(< $SMCROUTEDIR/amt.pid)
+		kill $smcpid
+	fi
+	rm -rf $SMCROUTEDIR
 
 	exit $ERR
 }
@@ -167,7 +173,7 @@ setup_iptables()
 
 setup_mcast_routing()
 {
-	ip netns exec "${RELAY}" smcrouted
+	ip netns exec "${RELAY}" smcrouted -P $SMCROUTEDIR/amt.pid
 	ip netns exec "${RELAY}" smcroutectl a relay_src \
 		172.17.0.2 239.0.0.1 amtr
 	ip netns exec "${RELAY}" smcroutectl a relay_src \
@@ -210,8 +216,8 @@ check_features()
 
 test_ipv4_forward()
 {
-	RESULT4=$(ip netns exec "${LISTENER}" nc -w 1 -l -u 239.0.0.1 4000)
-	if [ "$RESULT4" == "172.17.0.2" ]; then
+	RESULT4=$(ip netns exec "${LISTENER}" timeout 15 socat - UDP4-LISTEN:4000,readbytes=128 || true)
+	if echo "$RESULT4" | grep -q "172.17.0.2"; then
 		printf "TEST: %-60s  [ OK ]\n" "IPv4 amt multicast forwarding"
 		exit 0
 	else
@@ -222,8 +228,8 @@ test_ipv4_forward()
 
 test_ipv6_forward()
 {
-	RESULT6=$(ip netns exec "${LISTENER}" nc -w 1 -l -u ff0e::5:6 6000)
-	if [ "$RESULT6" == "2001:db8:3::2" ]; then
+	RESULT6=$(ip netns exec "${LISTENER}" timeout 15 socat - UDP6-LISTEN:6000,readbytes=128 || true)
+	if echo "$RESULT6" | grep -q "2001:db8:3::2"; then
 		printf "TEST: %-60s  [ OK ]\n" "IPv6 amt multicast forwarding"
 		exit 0
 	else
@@ -236,14 +242,14 @@ send_mcast4()
 {
 	sleep 2
 	ip netns exec "${SOURCE}" bash -c \
-		'echo 172.17.0.2 | nc -w 1 -u 239.0.0.1 4000' &
+		'printf "%s %128s" 172.17.0.2 | nc -w 1 -u 239.0.0.1 4000' &
 }
 
 send_mcast6()
 {
 	sleep 2
 	ip netns exec "${SOURCE}" bash -c \
-		'echo 2001:db8:3::2 | nc -w 1 -u ff0e::5:6 6000' &
+		'printf "%s %128s" 2001:db8:3::2 | nc -w 1 -u ff0e::5:6 6000' &
 }
 
 check_features
diff --git a/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh b/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh
index a40c0e9bd0..eef5cbf6ee 100755
--- a/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh
+++ b/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh
@@ -73,25 +73,19 @@ setup_v6() {
 	# namespaces. veth0 is veth-router, veth1 is veth-host.
 	# first, set up the inteface's link to the namespace
 	# then, set the interface "up"
-	ip -6 -netns ${ROUTER_NS_V6} link add name ${ROUTER_INTF} \
-		type veth peer name ${HOST_INTF}
-
-	ip -6 -netns ${ROUTER_NS_V6} link set dev ${ROUTER_INTF} up
-	ip -6 -netns ${ROUTER_NS_V6} link set dev ${HOST_INTF} netns \
-		${HOST_NS_V6}
+	ip -n ${ROUTER_NS_V6} link add name ${ROUTER_INTF} \
+		type veth peer name ${HOST_INTF} netns ${HOST_NS_V6}
 
-	ip -6 -netns ${HOST_NS_V6} link set dev ${HOST_INTF} up
-	ip -6 -netns ${ROUTER_NS_V6} addr add \
-		${ROUTER_ADDR_V6}/${PREFIX_WIDTH_V6} dev ${ROUTER_INTF} nodad
+	# Add tc rule to filter out host na message
+	tc -n ${ROUTER_NS_V6} qdisc add dev ${ROUTER_INTF} clsact
+	tc -n ${ROUTER_NS_V6} filter add dev ${ROUTER_INTF} \
+		ingress protocol ipv6 pref 1 handle 101 \
+		flower src_ip ${HOST_ADDR_V6} ip_proto icmpv6 type 136 skip_hw action pass
 
 	HOST_CONF=net.ipv6.conf.${HOST_INTF}
 	ip netns exec ${HOST_NS_V6} sysctl -qw ${HOST_CONF}.ndisc_notify=1
 	ip netns exec ${HOST_NS_V6} sysctl -qw ${HOST_CONF}.disable_ipv6=0
-	ip -6 -netns ${HOST_NS_V6} addr add ${HOST_ADDR_V6}/${PREFIX_WIDTH_V6} \
-		dev ${HOST_INTF}
-
 	ROUTER_CONF=net.ipv6.conf.${ROUTER_INTF}
-
 	ip netns exec ${ROUTER_NS_V6} sysctl -w \
 		${ROUTER_CONF}.forwarding=1 >/dev/null 2>&1
 	ip netns exec ${ROUTER_NS_V6} sysctl -w \
@@ -99,6 +93,13 @@ setup_v6() {
 	ip netns exec ${ROUTER_NS_V6} sysctl -w \
 		${ROUTER_CONF}.accept_untracked_na=${accept_untracked_na} \
 		>/dev/null 2>&1
+
+	ip -n ${ROUTER_NS_V6} link set dev ${ROUTER_INTF} up
+	ip -n ${HOST_NS_V6} link set dev ${HOST_INTF} up
+	ip -n ${ROUTER_NS_V6} addr add ${ROUTER_ADDR_V6}/${PREFIX_WIDTH_V6} \
+		dev ${ROUTER_INTF} nodad
+	ip -n ${HOST_NS_V6} addr add ${HOST_ADDR_V6}/${PREFIX_WIDTH_V6} \
+		dev ${HOST_INTF}
 	set +e
 }
 
@@ -162,26 +163,6 @@ arp_test_gratuitous_combinations() {
 	arp_test_gratuitous 2 1
 }
 
-cleanup_tcpdump() {
-	set -e
-	[[ ! -z  ${tcpdump_stdout} ]] && rm -f ${tcpdump_stdout}
-	[[ ! -z  ${tcpdump_stderr} ]] && rm -f ${tcpdump_stderr}
-	tcpdump_stdout=
-	tcpdump_stderr=
-	set +e
-}
-
-start_tcpdump() {
-	set -e
-	tcpdump_stdout=`mktemp`
-	tcpdump_stderr=`mktemp`
-	ip netns exec ${ROUTER_NS_V6} timeout 15s \
-		tcpdump --immediate-mode -tpni ${ROUTER_INTF} -c 1 \
-		"icmp6 && icmp6[0] == 136 && src ${HOST_ADDR_V6}" \
-		> ${tcpdump_stdout} 2> /dev/null
-	set +e
-}
-
 verify_ndisc() {
 	local accept_untracked_na=$1
 	local same_subnet=$2
@@ -222,8 +203,9 @@ ndisc_test_untracked_advertisements() {
 			HOST_ADDR_V6=2001:db8:abcd:0012::3
 		fi
 	fi
-	setup_v6 $1 $2
-	start_tcpdump
+	setup_v6 $1
+	slowwait_for_counter 15 1 \
+		tc_rule_handle_stats_get "dev ${ROUTER_INTF} ingress" 101 ".packets" "-n ${ROUTER_NS_V6}"
 
 	if verify_ndisc $1 $2; then
 		printf "    TEST: %-60s  [ OK ]\n" "${test_msg[*]}"
@@ -231,7 +213,6 @@ ndisc_test_untracked_advertisements() {
 		printf "    TEST: %-60s  [FAIL]\n" "${test_msg[*]}"
 	fi
 
-	cleanup_tcpdump
 	cleanup_v6
 	set +e
 }
diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index c79e65581d..161db24e3c 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -333,16 +333,17 @@ static const char *cs_ts_info2str(unsigned int info)
 	return "unknown";
 }
 
-static void
+static unsigned long
 cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz)
 {
 	struct sock_extended_err *see;
 	struct scm_timestamping *ts;
+	unsigned long ts_seen = 0;
 	struct cmsghdr *cmsg;
 	int i, err;
 
 	if (!opt.ts.ena)
-		return;
+		return 0;
 	msg->msg_control = cbuf;
 	msg->msg_controllen = cbuf_sz;
 
@@ -396,8 +397,11 @@ cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz)
 			printf(" %5s ts%d %lluus\n",
 			       cs_ts_info2str(see->ee_info),
 			       i, rel_time);
+			ts_seen |= 1 << see->ee_info;
 		}
 	}
+
+	return ts_seen;
 }
 
 static void ca_set_sockopts(int fd)
@@ -509,10 +513,16 @@ int main(int argc, char *argv[])
 	err = ERN_SUCCESS;
 
 	if (opt.ts.ena) {
-		/* Make sure all timestamps have time to loop back */
-		usleep(opt.txtime.delay);
+		unsigned long seen;
+		int i;
 
-		cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf));
+		/* Make sure all timestamps have time to loop back */
+		for (i = 0; i < 40; i++) {
+			seen = cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf));
+			if (seen & (1 << SCM_TSTAMP_SND))
+				break;
+			usleep(opt.txtime.delay / 20);
+		}
 	}
 
 err_out:
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 5e4390cac1..04de7a6ba6 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -30,6 +30,7 @@ CONFIG_IP_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_IPV6_MROUTE=y
 CONFIG_IPV6_SIT=y
 CONFIG_IP_DCCP=m
 CONFIG_NF_NAT=m
diff --git a/tools/testing/selftests/net/forwarding/bridge_igmp.sh b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
index 2aa66d2a17..e6a3e04fd8 100755
--- a/tools/testing/selftests/net/forwarding/bridge_igmp.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
@@ -478,10 +478,10 @@ v3exc_timeout_test()
 	RET=0
 	local X=("192.0.2.20" "192.0.2.30")
 
-	# GMI should be 3 seconds
+	# GMI should be 5 seconds
 	ip link set dev br0 type bridge mcast_query_interval 100 \
 					mcast_query_response_interval 100 \
-					mcast_membership_interval 300
+					mcast_membership_interval 500
 
 	v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
 	ip link set dev br0 type bridge mcast_query_interval 500 \
@@ -489,7 +489,7 @@ v3exc_timeout_test()
 					mcast_membership_interval 1500
 
 	$MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW2" -q
-	sleep 3
+	sleep 5
 	bridge -j -d -s mdb show dev br0 \
 		| jq -e ".[].mdb[] | \
 			 select(.grp == \"$TEST_GROUP\" and \
diff --git a/tools/testing/selftests/net/forwarding/bridge_mld.sh b/tools/testing/selftests/net/forwarding/bridge_mld.sh
index e2b9ff773c..f84ab2e657 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mld.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mld.sh
@@ -478,10 +478,10 @@ mldv2exc_timeout_test()
 	RET=0
 	local X=("2001:db8:1::20" "2001:db8:1::30")
 
-	# GMI should be 3 seconds
+	# GMI should be 5 seconds
 	ip link set dev br0 type bridge mcast_query_interval 100 \
 					mcast_query_response_interval 100 \
-					mcast_membership_interval 300
+					mcast_membership_interval 500
 
 	mldv2exclude_prepare $h1
 	ip link set dev br0 type bridge mcast_query_interval 500 \
@@ -489,7 +489,7 @@ mldv2exc_timeout_test()
 					mcast_membership_interval 1500
 
 	$MZ $h1 -c 1 $MZPKT_ALLOW2 -q
-	sleep 3
+	sleep 5
 	bridge -j -d -s mdb show dev br0 \
 		| jq -e ".[].mdb[] | \
 			 select(.grp == \"$TEST_GROUP\" and \
diff --git a/tools/testing/selftests/net/forwarding/ethtool_rmon.sh b/tools/testing/selftests/net/forwarding/ethtool_rmon.sh
index 41a34a61f7..e78776db85 100755
--- a/tools/testing/selftests/net/forwarding/ethtool_rmon.sh
+++ b/tools/testing/selftests/net/forwarding/ethtool_rmon.sh
@@ -78,7 +78,7 @@ rmon_histogram()
 
 		for if in $iface $neigh; do
 			if ! ensure_mtu $if ${bucket[0]}; then
-				log_test_skip "$if does not support the required MTU for $step"
+				log_test_xfail "$if does not support the required MTU for $step"
 				return
 			fi
 		done
@@ -93,7 +93,7 @@ rmon_histogram()
 		jq -r ".[0].rmon[\"${set}-pktsNtoM\"][]|[.low, .high]|@tsv" 2>/dev/null)
 
 	if [ $nbuckets -eq 0 ]; then
-		log_test_skip "$iface does not support $set histogram counters"
+		log_test_xfail "$iface does not support $set histogram counters"
 		return
 	fi
 }
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index e579c2e0c4..e78f11140e 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -38,32 +38,6 @@ fi
 
 source "$net_forwarding_dir/../lib.sh"
 
-# timeout in seconds
-slowwait()
-{
-	local timeout=$1; shift
-
-	local start_time="$(date -u +%s)"
-	while true
-	do
-		local out
-		out=$("$@")
-		local ret=$?
-		if ((!ret)); then
-			echo -n "$out"
-			return 0
-		fi
-
-		local current_time="$(date -u +%s)"
-		if ((current_time - start_time > timeout)); then
-			echo -n "$out"
-			return 1
-		fi
-
-		sleep 0.1
-	done
-}
-
 ##############################################################################
 # Sanity checks
 
@@ -358,14 +332,24 @@ EXIT_STATUS=0
 # Per-test return value. Clear at the beginning of each test.
 RET=0
 
+ret_set_ksft_status()
+{
+	local ksft_status=$1; shift
+	local msg=$1; shift
+
+	RET=$(ksft_status_merge $RET $ksft_status)
+	if (( $? )); then
+		retmsg=$msg
+	fi
+}
+
 check_err()
 {
 	local err=$1
 	local msg=$2
 
-	if [[ $RET -eq 0 && $err -ne 0 ]]; then
-		RET=$err
-		retmsg=$msg
+	if ((err)); then
+		ret_set_ksft_status $ksft_fail "$msg"
 	fi
 }
 
@@ -374,10 +358,7 @@ check_fail()
 	local err=$1
 	local msg=$2
 
-	if [[ $RET -eq 0 && $err -eq 0 ]]; then
-		RET=1
-		retmsg=$msg
-	fi
+	check_err $((!err)) "$msg"
 }
 
 check_err_fail()
@@ -393,6 +374,62 @@ check_err_fail()
 	fi
 }
 
+log_test_result()
+{
+	local test_name=$1; shift
+	local opt_str=$1; shift
+	local result=$1; shift
+	local retmsg=$1; shift
+
+	printf "TEST: %-60s  [%s]\n" "$test_name $opt_str" "$result"
+	if [[ $retmsg ]]; then
+		printf "\t%s\n" "$retmsg"
+	fi
+}
+
+pause_on_fail()
+{
+	if [[ $PAUSE_ON_FAIL == yes ]]; then
+		echo "Hit enter to continue, 'q' to quit"
+		read a
+		[[ $a == q ]] && exit 1
+	fi
+}
+
+handle_test_result_pass()
+{
+	local test_name=$1; shift
+	local opt_str=$1; shift
+
+	log_test_result "$test_name" "$opt_str" " OK "
+}
+
+handle_test_result_fail()
+{
+	local test_name=$1; shift
+	local opt_str=$1; shift
+
+	log_test_result "$test_name" "$opt_str" FAIL "$retmsg"
+	pause_on_fail
+}
+
+handle_test_result_xfail()
+{
+	local test_name=$1; shift
+	local opt_str=$1; shift
+
+	log_test_result "$test_name" "$opt_str" XFAIL "$retmsg"
+	pause_on_fail
+}
+
+handle_test_result_skip()
+{
+	local test_name=$1; shift
+	local opt_str=$1; shift
+
+	log_test_result "$test_name" "$opt_str" SKIP "$retmsg"
+}
+
 log_test()
 {
 	local test_name=$1
@@ -402,31 +439,28 @@ log_test()
 		opt_str="($opt_str)"
 	fi
 
-	if [[ $RET -ne 0 ]]; then
-		EXIT_STATUS=1
-		printf "TEST: %-60s  [FAIL]\n" "$test_name $opt_str"
-		if [[ ! -z "$retmsg" ]]; then
-			printf "\t%s\n" "$retmsg"
-		fi
-		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
-			echo "Hit enter to continue, 'q' to quit"
-			read a
-			[ "$a" = "q" ] && exit 1
-		fi
-		return 1
+	if ((RET == ksft_pass)); then
+		handle_test_result_pass "$test_name" "$opt_str"
+	elif ((RET == ksft_xfail)); then
+		handle_test_result_xfail "$test_name" "$opt_str"
+	elif ((RET == ksft_skip)); then
+		handle_test_result_skip "$test_name" "$opt_str"
+	else
+		handle_test_result_fail "$test_name" "$opt_str"
 	fi
 
-	printf "TEST: %-60s  [ OK ]\n" "$test_name $opt_str"
-	return 0
+	EXIT_STATUS=$(ksft_exit_status_merge $EXIT_STATUS $RET)
+	return $RET
 }
 
 log_test_skip()
 {
-	local test_name=$1
-	local opt_str=$2
+	RET=$ksft_skip retmsg= log_test "$@"
+}
 
-	printf "TEST: %-60s  [SKIP]\n" "$test_name $opt_str"
-	return 0
+log_test_xfail()
+{
+	RET=$ksft_xfail retmsg= log_test "$@"
 }
 
 log_info()
@@ -487,33 +521,6 @@ wait_for_trap()
 	"$@" | grep -q trap
 }
 
-until_counter_is()
-{
-	local expr=$1; shift
-	local current=$("$@")
-
-	echo $((current))
-	((current $expr))
-}
-
-busywait_for_counter()
-{
-	local timeout=$1; shift
-	local delta=$1; shift
-
-	local base=$("$@")
-	busywait "$timeout" until_counter_is ">= $((base + delta))" "$@"
-}
-
-slowwait_for_counter()
-{
-	local timeout=$1; shift
-	local delta=$1; shift
-
-	local base=$("$@")
-	slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@"
-}
-
 setup_wait_dev()
 {
 	local dev=$1; shift
@@ -819,29 +826,6 @@ link_stats_rx_errors_get()
 	link_stats_get $1 rx errors
 }
 
-tc_rule_stats_get()
-{
-	local dev=$1; shift
-	local pref=$1; shift
-	local dir=$1; shift
-	local selector=${1:-.packets}; shift
-
-	tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \
-	    | jq ".[1].options.actions[].stats$selector"
-}
-
-tc_rule_handle_stats_get()
-{
-	local id=$1; shift
-	local handle=$1; shift
-	local selector=${1:-.packets}; shift
-	local netns=${1:-""}; shift
-
-	tc $netns -j -s filter show $id \
-	    | jq ".[] | select(.options.handle == $handle) | \
-		  .options.actions[0].stats$selector"
-}
-
 ethtool_stats_get()
 {
 	local dev=$1; shift
diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh
index 7e7d62161c..b2d2c6cecc 100644
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh
@@ -69,7 +69,7 @@ nh_stats_test_dispatch_swhw()
 		nh_stats_do_test "HW $what" "$nh1_id" "$nh2_id" "$group_id" \
 				 nh_stats_get_hw "${mz[@]}"
 	elif [[ $kind == veth ]]; then
-		log_test_skip "HW stats not offloaded on veth topology"
+		log_test_xfail "HW stats not offloaded on veth topology"
 	fi
 }
 
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index f9fe182dfb..16372ca167 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -10,33 +10,116 @@ BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 # namespace list created by setup_ns
-NS_LIST=""
+NS_LIST=()
 
 ##############################################################################
 # Helpers
-busywait()
+
+__ksft_status_merge()
 {
-	local timeout=$1; shift
+	local a=$1; shift
+	local b=$1; shift
+	local -A weights
+	local weight=0
+
+	local i
+	for i in "$@"; do
+		weights[$i]=$((weight++))
+	done
+
+	if [[ ${weights[$a]} > ${weights[$b]} ]]; then
+		echo "$a"
+		return 0
+	else
+		echo "$b"
+		return 1
+	fi
+}
+
+ksft_status_merge()
+{
+	local a=$1; shift
+	local b=$1; shift
+
+	__ksft_status_merge "$a" "$b" \
+		$ksft_pass $ksft_xfail $ksft_skip $ksft_fail
+}
+
+ksft_exit_status_merge()
+{
+	local a=$1; shift
+	local b=$1; shift
+
+	__ksft_status_merge "$a" "$b" \
+		$ksft_xfail $ksft_pass $ksft_skip $ksft_fail
+}
+
+loopy_wait()
+{
+	local sleep_cmd=$1; shift
+	local timeout_ms=$1; shift
 
 	local start_time="$(date -u +%s%3N)"
 	while true
 	do
 		local out
-		out=$("$@")
-		local ret=$?
-		if ((!ret)); then
+		if out=$("$@"); then
 			echo -n "$out"
 			return 0
 		fi
 
 		local current_time="$(date -u +%s%3N)"
-		if ((current_time - start_time > timeout)); then
+		if ((current_time - start_time > timeout_ms)); then
 			echo -n "$out"
 			return 1
 		fi
+
+		$sleep_cmd
 	done
 }
 
+busywait()
+{
+	local timeout_ms=$1; shift
+
+	loopy_wait : "$timeout_ms" "$@"
+}
+
+# timeout in seconds
+slowwait()
+{
+	local timeout_sec=$1; shift
+
+	loopy_wait "sleep 0.1" "$((timeout_sec * 1000))" "$@"
+}
+
+until_counter_is()
+{
+	local expr=$1; shift
+	local current=$("$@")
+
+	echo $((current))
+	((current $expr))
+}
+
+busywait_for_counter()
+{
+	local timeout=$1; shift
+	local delta=$1; shift
+
+	local base=$("$@")
+	busywait "$timeout" until_counter_is ">= $((base + delta))" "$@"
+}
+
+slowwait_for_counter()
+{
+	local timeout=$1; shift
+	local delta=$1; shift
+
+	local base=$("$@")
+	slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@"
+}
+
 cleanup_ns()
 {
 	local ns=""
@@ -50,6 +133,7 @@ cleanup_ns()
 	fi
 
 	for ns in "$@"; do
+		[ -z "${ns}" ] && continue
 		ip netns delete "${ns}" &> /dev/null
 		if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then
 			echo "Warn: Failed to remove namespace $ns"
@@ -63,7 +147,7 @@ cleanup_ns()
 
 cleanup_all_ns()
 {
-	cleanup_ns $NS_LIST
+	cleanup_ns "${NS_LIST[@]}"
 }
 
 # setup netns with given names as prefix. e.g
@@ -72,25 +156,50 @@ setup_ns()
 {
 	local ns=""
 	local ns_name=""
-	local ns_list=""
+	local ns_list=()
+	local ns_exist=
 	for ns_name in "$@"; do
 		# Some test may setup/remove same netns multi times
 		if unset ${ns_name} 2> /dev/null; then
 			ns="${ns_name,,}-$(mktemp -u XXXXXX)"
 			eval readonly ${ns_name}="$ns"
+			ns_exist=false
 		else
 			eval ns='$'${ns_name}
 			cleanup_ns "$ns"
-
+			ns_exist=true
 		fi
 
 		if ! ip netns add "$ns"; then
 			echo "Failed to create namespace $ns_name"
-			cleanup_ns "$ns_list"
+			cleanup_ns "${ns_list[@]}"
 			return $ksft_skip
 		fi
 		ip -n "$ns" link set lo up
-		ns_list="$ns_list $ns"
+		! $ns_exist && ns_list+=("$ns")
 	done
-	NS_LIST="$NS_LIST $ns_list"
+	NS_LIST+=("${ns_list[@]}")
+}
+
+tc_rule_stats_get()
+{
+	local dev=$1; shift
+	local pref=$1; shift
+	local dir=$1; shift
+	local selector=${1:-.packets}; shift
+
+	tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \
+	    | jq ".[1].options.actions[].stats$selector"
+}
+
+tc_rule_handle_stats_get()
+{
+	local id=$1; shift
+	local handle=$1; shift
+	local selector=${1:-.packets}; shift
+	local netns=${1:-""}; shift
+
+	tc $netns -j -s filter show $id \
+	    | jq ".[] | select(.options.handle == $handle) | \
+		  .options.actions[0].stats$selector"
 }
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index e4403236f6..2290125f6d 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -125,8 +125,8 @@ init_shapers()
 {
 	local i
 	for i in $(seq 1 4); do
-		tc -n $ns1 qdisc add dev ns1eth$i root netem rate 20mbit delay 1
-		tc -n $ns2 qdisc add dev ns2eth$i root netem rate 20mbit delay 1
+		tc -n $ns1 qdisc add dev ns1eth$i root netem rate 20mbit delay 1ms
+		tc -n $ns2 qdisc add dev ns2eth$i root netem rate 20mbit delay 1ms
 	done
 }
 
@@ -262,6 +262,8 @@ reset()
 
 	TEST_NAME="${1}"
 
+	MPTCP_LIB_SUBTEST_FLAKY=0 # reset if modified
+
 	if skip_test; then
 		MPTCP_LIB_TEST_COUNTER=$((MPTCP_LIB_TEST_COUNTER+1))
 		last_test_ignored=1
@@ -449,7 +451,9 @@ reset_with_tcp_filter()
 # $1: err msg
 fail_test()
 {
-	ret=${KSFT_FAIL}
+	if ! mptcp_lib_subtest_is_flaky; then
+		ret=${KSFT_FAIL}
+	fi
 
 	if [ ${#} -gt 0 ]; then
 		print_fail "${@}"
@@ -2354,9 +2358,10 @@ remove_tests()
 	if reset "remove invalid addresses"; then
 		pm_nl_set_limits $ns1 3 3
 		pm_nl_add_endpoint $ns1 10.0.12.1 flags signal
+		# broadcast IP: no packet for this address will be received on ns1
+		pm_nl_add_endpoint $ns1 224.0.0.1 flags signal
 		pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
-		pm_nl_add_endpoint $ns1 10.0.14.1 flags signal
-		pm_nl_set_limits $ns2 3 3
+		pm_nl_set_limits $ns2 2 2
 		addr_nr_ns1=-3 speed=10 \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
@@ -3178,6 +3183,7 @@ fullmesh_tests()
 fastclose_tests()
 {
 	if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=1024 fastclose=client \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
@@ -3186,6 +3192,7 @@ fastclose_tests()
 	fi
 
 	if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=1024 fastclose=server \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0 0 0 0 1
@@ -3204,6 +3211,7 @@ fail_tests()
 {
 	# single subflow
 	if reset_with_fail "Infinite map" 1; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=128 \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)"
@@ -3212,7 +3220,8 @@ fail_tests()
 
 	# multiple subflows
 	if reset_with_fail "MP_FAIL MP_RST" 2; then
-		tc -n $ns2 qdisc add dev ns2eth1 root netem rate 1mbit delay 5
+		MPTCP_LIB_SUBTEST_FLAKY=1
+		tc -n $ns2 qdisc add dev ns2eth1 root netem rate 1mbit delay 5ms
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 1b23662203..7322e1e4e5 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -216,8 +216,8 @@ run_test()
 	shift 4
 	local msg=$*
 
-	[ $delay1 -gt 0 ] && delay1="delay $delay1" || delay1=""
-	[ $delay2 -gt 0 ] && delay2="delay $delay2" || delay2=""
+	[ $delay1 -gt 0 ] && delay1="delay ${delay1}ms" || delay1=""
+	[ $delay2 -gt 0 ] && delay2="delay ${delay2}ms" || delay2=""
 
 	for dev in ns1eth1 ns1eth2; do
 		tc -n $ns1 qdisc del dev $dev root >/dev/null 2>&1
@@ -243,7 +243,7 @@ run_test()
 	do_transfer $small $large $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
-	if [ $lret -ne 0 ]; then
+	if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
 	fi
@@ -253,7 +253,7 @@ run_test()
 	do_transfer $large $small $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
-	if [ $lret -ne 0 ]; then
+	if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
 	fi
@@ -286,7 +286,7 @@ run_test 10 10 0 0 "balanced bwidth"
 run_test 10 10 1 25 "balanced bwidth with unbalanced delay"
 
 # we still need some additional infrastructure to pass the following test-cases
-run_test 10 3 0 0 "unbalanced bwidth"
+MPTCP_LIB_SUBTEST_FLAKY=1 run_test 10 3 0 0 "unbalanced bwidth"
 run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay"
 run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay"
 
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 9e2981f2d7..9cb0597826 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -160,10 +160,12 @@ make_connection()
 	local is_v6=$1
 	local app_port=$app4_port
 	local connect_addr="10.0.1.1"
+	local client_addr="10.0.1.2"
 	local listen_addr="0.0.0.0"
 	if [ "$is_v6" = "v6" ]
 	then
 		connect_addr="dead:beef:1::1"
+		client_addr="dead:beef:1::2"
 		listen_addr="::"
 		app_port=$app6_port
 	else
@@ -206,6 +208,7 @@ make_connection()
 		   [ "$server_serverside" = 1 ]
 	then
 		test_pass
+		print_title "Connection info: ${client_addr}:${client_port} -> ${connect_addr}:${app_port}"
 	else
 		test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})"
 		mptcp_lib_result_print_all_tap
@@ -297,7 +300,7 @@ test_announce()
 	ip netns exec "$ns2"\
 	   ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id $client_addr_id dev\
 	   ns2eth1
-	print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, reuse port"
+	print_test "ADD_ADDR id:client 10.0.2.2 (ns2) => ns1, reuse port"
 	sleep 0.5
 	verify_announce_event $server_evts $ANNOUNCED $server4_token "10.0.2.2" $client_addr_id \
 			      "$client4_port"
@@ -306,7 +309,7 @@ test_announce()
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl ann\
 	   dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1
-	print_test "ADD_ADDR6 id:${client_addr_id} dead:beef:2::2 (ns2) => ns1, reuse port"
+	print_test "ADD_ADDR6 id:client dead:beef:2::2 (ns2) => ns1, reuse port"
 	sleep 0.5
 	verify_announce_event "$server_evts" "$ANNOUNCED" "$server6_token" "dead:beef:2::2"\
 			      "$client_addr_id" "$client6_port" "v6"
@@ -316,7 +319,7 @@ test_announce()
 	client_addr_id=$((client_addr_id+1))
 	ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\
 	   $client_addr_id dev ns2eth1 port $new4_port
-	print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, new port"
+	print_test "ADD_ADDR id:client+1 10.0.2.2 (ns2) => ns1, new port"
 	sleep 0.5
 	verify_announce_event "$server_evts" "$ANNOUNCED" "$server4_token" "10.0.2.2"\
 			      "$client_addr_id" "$new4_port"
@@ -327,7 +330,7 @@ test_announce()
 	# ADD_ADDR from the server to client machine reusing the subflow port
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
 	   $server_addr_id dev ns1eth2
-	print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port"
+	print_test "ADD_ADDR id:server 10.0.2.1 (ns1) => ns2, reuse port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\
 			      "$server_addr_id" "$app4_port"
@@ -336,7 +339,7 @@ test_announce()
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\
 	   $server_addr_id dev ns1eth2
-	print_test "ADD_ADDR6 id:${server_addr_id} dead:beef:2::1 (ns1) => ns2, reuse port"
+	print_test "ADD_ADDR6 id:server dead:beef:2::1 (ns1) => ns2, reuse port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "dead:beef:2::1"\
 			      "$server_addr_id" "$app6_port" "v6"
@@ -346,7 +349,7 @@ test_announce()
 	server_addr_id=$((server_addr_id+1))
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
 	   $server_addr_id dev ns1eth2 port $new4_port
-	print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, new port"
+	print_test "ADD_ADDR id:server+1 10.0.2.1 (ns1) => ns2, new port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\
 			      "$server_addr_id" "$new4_port"
@@ -380,7 +383,7 @@ test_remove()
 	local invalid_token=$(( client4_token - 1 ))
 	ip netns exec "$ns2" ./pm_nl_ctl rem token $invalid_token id\
 	   $client_addr_id > /dev/null 2>&1
-	print_test "RM_ADDR id:${client_addr_id} ns2 => ns1, invalid token"
+	print_test "RM_ADDR id:client ns2 => ns1, invalid token"
 	local type
 	type=$(mptcp_lib_evts_get_info type "$server_evts")
 	if [ "$type" = "" ]
@@ -394,7 +397,7 @@ test_remove()
 	local invalid_id=$(( client_addr_id + 1 ))
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
 	   $invalid_id > /dev/null 2>&1
-	print_test "RM_ADDR id:${invalid_id} ns2 => ns1, invalid id"
+	print_test "RM_ADDR id:client+1 ns2 => ns1, invalid id"
 	type=$(mptcp_lib_evts_get_info type "$server_evts")
 	if [ "$type" = "" ]
 	then
@@ -407,7 +410,7 @@ test_remove()
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
 	   $client_addr_id
-	print_test "RM_ADDR id:${client_addr_id} ns2 => ns1"
+	print_test "RM_ADDR id:client ns2 => ns1"
 	sleep 0.5
 	verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id"
 
@@ -416,7 +419,7 @@ test_remove()
 	client_addr_id=$(( client_addr_id - 1 ))
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
 	   $client_addr_id
-	print_test "RM_ADDR id:${client_addr_id} ns2 => ns1"
+	print_test "RM_ADDR id:client-1 ns2 => ns1"
 	sleep 0.5
 	verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id"
 
@@ -424,7 +427,7 @@ test_remove()
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client6_token" id\
 	   $client_addr_id
-	print_test "RM_ADDR6 id:${client_addr_id} ns2 => ns1"
+	print_test "RM_ADDR6 id:client-1 ns2 => ns1"
 	sleep 0.5
 	verify_remove_event "$server_evts" "$REMOVED" "$server6_token" "$client_addr_id"
 
@@ -434,7 +437,7 @@ test_remove()
 	# RM_ADDR from the server to client machine
 	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\
 	   $server_addr_id
-	print_test "RM_ADDR id:${server_addr_id} ns1 => ns2"
+	print_test "RM_ADDR id:server ns1 => ns2"
 	sleep 0.5
 	verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id"
 
@@ -443,7 +446,7 @@ test_remove()
 	server_addr_id=$(( server_addr_id - 1 ))
 	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\
 	   $server_addr_id
-	print_test "RM_ADDR id:${server_addr_id} ns1 => ns2"
+	print_test "RM_ADDR id:server-1 ns1 => ns2"
 	sleep 0.5
 	verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id"
 
@@ -451,7 +454,7 @@ test_remove()
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server6_token" id\
 	   $server_addr_id
-	print_test "RM_ADDR6 id:${server_addr_id} ns1 => ns2"
+	print_test "RM_ADDR6 id:server-1 ns1 => ns2"
 	sleep 0.5
 	verify_remove_event "$client_evts" "$REMOVED" "$client6_token" "$server_addr_id"
 }
@@ -479,8 +482,14 @@ verify_subflow_events()
 	local locid
 	local remid
 	local info
+	local e_dport_txt
 
-	info="${e_saddr} (${e_from}) => ${e_daddr}:${e_dport} (${e_to})"
+	# only display the fixed ports
+	if [ "${e_dport}" -ge "${app4_port}" ] && [ "${e_dport}" -le "${app6_port}" ]; then
+		e_dport_txt=":${e_dport}"
+	fi
+
+	info="${e_saddr} (${e_from}) => ${e_daddr}${e_dport_txt} (${e_to})"
 
 	if [ "$e_type" = "$SUB_ESTABLISHED" ]
 	then
@@ -766,7 +775,7 @@ test_subflows_v4_v6_mix()
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\
 	   $server_addr_id dev ns1eth2
-	print_test "ADD_ADDR4 id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port"
+	print_test "ADD_ADDR4 id:server 10.0.2.1 (ns1) => ns2, reuse port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\
 			      "$server_addr_id" "$app6_port"
@@ -861,7 +870,7 @@ test_listener()
 	local listener_pid=$!
 
 	sleep 0.5
-	print_test "CREATE_LISTENER 10.0.2.2:$client4_port"
+	print_test "CREATE_LISTENER 10.0.2.2 (client port)"
 	verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port
 
 	# ADD_ADDR from client to server machine reusing the subflow port
@@ -878,13 +887,14 @@ test_listener()
 	mptcp_lib_kill_wait $listener_pid
 
 	sleep 0.5
-	print_test "CLOSE_LISTENER 10.0.2.2:$client4_port"
+	print_test "CLOSE_LISTENER 10.0.2.2 (client port)"
 	verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port
 }
 
 print_title "Make connections"
 make_connection
 make_connection "v6"
+print_title "Will be using address IDs ${client_addr_id} (client) and ${server_addr_id} (server)"
 
 test_announce
 test_remove
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index 5cae535438..15bca07087 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 #
 # OVS kernel module self tests
diff --git a/tools/testing/selftests/power_supply/test_power_supply_properties.sh b/tools/testing/selftests/power_supply/test_power_supply_properties.sh
index df272dfe1d..a66b1313ed 100755
--- a/tools/testing/selftests/power_supply/test_power_supply_properties.sh
+++ b/tools/testing/selftests/power_supply/test_power_supply_properties.sh
@@ -23,7 +23,7 @@ count_tests() {
 	total_tests=0
 
 	for i in $SUPPLIES; do
-		total_tests=$(("$total_tests" + "$NUM_TESTS"))
+		total_tests=$((total_tests + NUM_TESTS))
 	done
 
 	echo "$total_tests"
diff --git a/tools/testing/selftests/powerpc/dexcr/Makefile b/tools/testing/selftests/powerpc/dexcr/Makefile
index 76210f2bce..829ad075b4 100644
--- a/tools/testing/selftests/powerpc/dexcr/Makefile
+++ b/tools/testing/selftests/powerpc/dexcr/Makefile
@@ -3,7 +3,7 @@ TEST_GEN_FILES := lsdexcr
 
 include ../../lib.mk
 
-$(OUTPUT)/hashchk_test: CFLAGS += -fno-pie $(call cc-option,-mno-rop-protect)
+$(OUTPUT)/hashchk_test: CFLAGS += -fno-pie -no-pie $(call cc-option,-mno-rop-protect)
 
 $(TEST_GEN_PROGS): ../harness.c ../utils.c ./dexcr.c
 $(TEST_GEN_FILES): ../utils.c ./dexcr.c
diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile
index 2deac2031d..021863f860 100644
--- a/tools/testing/selftests/resctrl/Makefile
+++ b/tools/testing/selftests/resctrl/Makefile
@@ -5,6 +5,8 @@ CFLAGS += $(KHDR_INCLUDES)
 
 TEST_GEN_PROGS := resctrl_tests
 
+LOCAL_HDRS += $(wildcard *.h)
+
 include ../lib.mk
 
-$(OUTPUT)/resctrl_tests: $(wildcard *.[ch])
+$(OUTPUT)/resctrl_tests: $(wildcard *.c)
diff --git a/tools/testing/selftests/riscv/hwprobe/.gitignore b/tools/testing/selftests/riscv/hwprobe/.gitignore
index 8113dc3bdd..6e384e80ea 100644
--- a/tools/testing/selftests/riscv/hwprobe/.gitignore
+++ b/tools/testing/selftests/riscv/hwprobe/.gitignore
@@ -1 +1,3 @@
 hwprobe
+cbo
+which-cpus
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
index 12da0a939e..557fb074ac 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
@@ -133,6 +133,50 @@
         ]
     },
     {
+        "id": "6f62",
+        "name": "Add taprio Qdisc with too short interval",
+        "category": [
+            "qdisc",
+            "taprio"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 8\" > /sys/bus/netdevsim/new_device"
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 300 sched-entry S 02 1700 clockid CLOCK_TAI",
+        "expExitCode": "2",
+        "verifyCmd": "$TC qdisc show dev $ETH",
+        "matchPattern": "qdisc taprio 1: root refcnt",
+        "matchCount": "0",
+        "teardown": [
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
+    {
+        "id": "831f",
+        "name": "Add taprio Qdisc with too short cycle-time",
+        "category": [
+            "qdisc",
+            "taprio"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 8\" > /sys/bus/netdevsim/new_device"
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 200000 sched-entry S 02 200000 cycle-time 100 clockid CLOCK_TAI",
+        "expExitCode": "2",
+        "verifyCmd": "$TC qdisc show dev $ETH",
+        "matchPattern": "qdisc taprio 1: root refcnt",
+        "matchCount": "0",
+        "teardown": [
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
+    {
         "id": "3e1e",
         "name": "Add taprio Qdisc with an invalid cycle-time",
         "category": [
diff --git a/tools/tracing/latency/latency-collector.c b/tools/tracing/latency/latency-collector.c
index 0fd9c747d3..cf263fe9de 100644
--- a/tools/tracing/latency/latency-collector.c
+++ b/tools/tracing/latency/latency-collector.c
@@ -935,12 +935,12 @@ static void show_available(void)
 	}
 
 	if (!tracers) {
-		warnx(no_tracer_msg);
+		warnx("%s", no_tracer_msg);
 		return;
 	}
 
 	if (!found) {
-		warnx(no_latency_tr_msg);
+		warnx("%s", no_latency_tr_msg);
 		tracefs_list_free(tracers);
 		return;
 	}
@@ -983,7 +983,7 @@ static const char *find_default_tracer(void)
 	for (i = 0; relevant_tracers[i]; i++) {
 		valid = tracer_valid(relevant_tracers[i], &notracer);
 		if (notracer)
-			errx(EXIT_FAILURE, no_tracer_msg);
+			errx(EXIT_FAILURE, "%s", no_tracer_msg);
 		if (valid)
 			return relevant_tracers[i];
 	}
@@ -1878,7 +1878,7 @@ static void scan_arguments(int argc, char *argv[])
 			}
 			valid = tracer_valid(current_tracer, &notracer);
 			if (notracer)
-				errx(EXIT_FAILURE, no_tracer_msg);
+				errx(EXIT_FAILURE, "%s", no_tracer_msg);
 			if (!valid)
 				errx(EXIT_FAILURE,
 "The tracer %s is not supported by your kernel!\n", current_tracer);
diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c
index 7093fd5333..7bd80ee2a5 100644
--- a/tools/tracing/rtla/src/timerlat_aa.c
+++ b/tools/tracing/rtla/src/timerlat_aa.c
@@ -16,6 +16,9 @@ enum timelat_state {
 	TIMERLAT_WAITING_THREAD,
 };
 
+/* Used to fill spaces in the output */
+static const char *spaces  = "                                                         ";
+
 #define MAX_COMM		24
 
 /*
@@ -274,14 +277,17 @@ static int timerlat_aa_nmi_handler(struct trace_seq *s, struct tep_record *recor
 		taa_data->prev_irq_timstamp = start;
 
 		trace_seq_reset(taa_data->prev_irqs_seq);
-		trace_seq_printf(taa_data->prev_irqs_seq, "\t%24s	\t\t\t%9.2f us\n",
-			 "nmi", ns_to_usf(duration));
+		trace_seq_printf(taa_data->prev_irqs_seq, "  %24s %.*s %9.2f us\n",
+				 "nmi",
+				 24, spaces,
+				 ns_to_usf(duration));
 		return 0;
 	}
 
 	taa_data->thread_nmi_sum += duration;
-	trace_seq_printf(taa_data->nmi_seq, "	%24s	\t\t\t%9.2f us\n",
-		 "nmi", ns_to_usf(duration));
+	trace_seq_printf(taa_data->nmi_seq, "  %24s %.*s %9.2f us\n",
+			 "nmi",
+			 24, spaces, ns_to_usf(duration));
 
 	return 0;
 }
@@ -323,8 +329,10 @@ static int timerlat_aa_irq_handler(struct trace_seq *s, struct tep_record *recor
 		taa_data->prev_irq_timstamp = start;
 
 		trace_seq_reset(taa_data->prev_irqs_seq);
-		trace_seq_printf(taa_data->prev_irqs_seq, "\t%24s:%-3llu	\t\t%9.2f us\n",
-				 desc, vector, ns_to_usf(duration));
+		trace_seq_printf(taa_data->prev_irqs_seq, "  %24s:%-3llu %.*s %9.2f us\n",
+				 desc, vector,
+				 15, spaces,
+				 ns_to_usf(duration));
 		return 0;
 	}
 
@@ -372,8 +380,10 @@ static int timerlat_aa_irq_handler(struct trace_seq *s, struct tep_record *recor
 	 * IRQ interference.
 	 */
 	taa_data->thread_irq_sum += duration;
-	trace_seq_printf(taa_data->irqs_seq, "	%24s:%-3llu	\t	%9.2f us\n",
-			 desc, vector, ns_to_usf(duration));
+	trace_seq_printf(taa_data->irqs_seq, "  %24s:%-3llu %.*s %9.2f us\n",
+			 desc, vector,
+			 24, spaces,
+			 ns_to_usf(duration));
 
 	return 0;
 }
@@ -408,8 +418,10 @@ static int timerlat_aa_softirq_handler(struct trace_seq *s, struct tep_record *r
 
 	taa_data->thread_softirq_sum += duration;
 
-	trace_seq_printf(taa_data->softirqs_seq, "\t%24s:%-3llu	\t	%9.2f us\n",
-			 softirq_name[vector], vector, ns_to_usf(duration));
+	trace_seq_printf(taa_data->softirqs_seq, "  %24s:%-3llu %.*s %9.2f us\n",
+			 softirq_name[vector], vector,
+			 24, spaces,
+			 ns_to_usf(duration));
 	return 0;
 }
 
@@ -452,8 +464,10 @@ static int timerlat_aa_thread_handler(struct trace_seq *s, struct tep_record *re
 	} else {
 		taa_data->thread_thread_sum += duration;
 
-		trace_seq_printf(taa_data->threads_seq, "\t%24s:%-3llu	\t\t%9.2f us\n",
-			 comm, pid, ns_to_usf(duration));
+		trace_seq_printf(taa_data->threads_seq, "  %24s:%-12llu %.*s %9.2f us\n",
+				 comm, pid,
+				 15, spaces,
+				 ns_to_usf(duration));
 	}
 
 	return 0;
@@ -482,7 +496,8 @@ static int timerlat_aa_stack_handler(struct trace_seq *s, struct tep_record *rec
 			function = tep_find_function(taa_ctx->tool->trace.tep, caller[i]);
 			if (!function)
 				break;
-			trace_seq_printf(taa_data->stack_seq, "\t\t-> %s\n", function);
+			trace_seq_printf(taa_data->stack_seq, " %.*s -> %s\n",
+					 14, spaces, function);
 		}
 	}
 	return 0;
@@ -568,23 +583,24 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu,
 	exp_irq_ts = taa_data->timer_irq_start_time - taa_data->timer_irq_start_delay;
 	if (exp_irq_ts < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) {
 		if (taa_data->prev_irq_timstamp < taa_data->timer_irq_start_time)
-			printf("  Previous IRQ interference:	\t\t up to  %9.2f us\n",
-				ns_to_usf(taa_data->prev_irq_duration));
+			printf("  Previous IRQ interference: %.*s up to  %9.2f us\n",
+			       16, spaces,
+			       ns_to_usf(taa_data->prev_irq_duration));
 	}
 
 	/*
 	 * The delay that the IRQ suffered before starting.
 	 */
-	printf("  IRQ handler delay:		%16s	%9.2f us (%.2f %%)\n",
-		(ns_to_usf(taa_data->timer_exit_from_idle) > 10) ? "(exit from idle)" : "",
-		ns_to_usf(taa_data->timer_irq_start_delay),
-		ns_to_per(total, taa_data->timer_irq_start_delay));
+	printf("  IRQ handler delay: %.*s %16s  %9.2f us (%.2f %%)\n", 16, spaces,
+	       (ns_to_usf(taa_data->timer_exit_from_idle) > 10) ? "(exit from idle)" : "",
+	       ns_to_usf(taa_data->timer_irq_start_delay),
+	       ns_to_per(total, taa_data->timer_irq_start_delay));
 
 	/*
 	 * Timerlat IRQ.
 	 */
-	printf("  IRQ latency:	\t\t\t\t	%9.2f us\n",
-		ns_to_usf(taa_data->tlat_irq_latency));
+	printf("  IRQ latency: %.*s %9.2f us\n", 40, spaces,
+	       ns_to_usf(taa_data->tlat_irq_latency));
 
 	if (irq) {
 		/*
@@ -595,15 +611,16 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu,
 		 * so it will be displayed, it is the key.
 		 */
 		printf("  Blocking thread:\n");
-		printf("	%24s:%-9llu\n",
-			taa_data->run_thread_comm, taa_data->run_thread_pid);
+		printf(" %.*s %24s:%-9llu\n", 6, spaces, taa_data->run_thread_comm,
+		       taa_data->run_thread_pid);
 	} else  {
 		/*
 		 * The duration of the IRQ handler that handled the timerlat IRQ.
 		 */
-		printf("  Timerlat IRQ duration:	\t\t	%9.2f us (%.2f %%)\n",
-			ns_to_usf(taa_data->timer_irq_duration),
-			ns_to_per(total, taa_data->timer_irq_duration));
+		printf("  Timerlat IRQ duration: %.*s %9.2f us (%.2f %%)\n",
+		       30, spaces,
+		       ns_to_usf(taa_data->timer_irq_duration),
+		       ns_to_per(total, taa_data->timer_irq_duration));
 
 		/*
 		 * The amount of time that the current thread postponed the scheduler.
@@ -611,13 +628,13 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu,
 		 * Recalling that it is net from NMI/IRQ/Softirq interference, so there
 		 * is no need to compute values here.
 		 */
-		printf("  Blocking thread:	\t\t\t	%9.2f us (%.2f %%)\n",
-			ns_to_usf(taa_data->thread_blocking_duration),
-			ns_to_per(total, taa_data->thread_blocking_duration));
+		printf("  Blocking thread: %.*s %9.2f us (%.2f %%)\n", 36, spaces,
+		       ns_to_usf(taa_data->thread_blocking_duration),
+		       ns_to_per(total, taa_data->thread_blocking_duration));
 
-		printf("	%24s:%-9llu		%9.2f us\n",
-			taa_data->run_thread_comm, taa_data->run_thread_pid,
-			ns_to_usf(taa_data->thread_blocking_duration));
+		printf(" %.*s %24s:%-9llu %.*s %9.2f us\n", 6, spaces,
+		       taa_data->run_thread_comm, taa_data->run_thread_pid,
+		       12, spaces, ns_to_usf(taa_data->thread_blocking_duration));
 	}
 
 	/*
@@ -629,9 +646,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu,
 	 * NMIs can happen during the IRQ, so they are always possible.
 	 */
 	if (taa_data->thread_nmi_sum)
-		printf("  NMI interference	\t\t\t	%9.2f us (%.2f %%)\n",
-			ns_to_usf(taa_data->thread_nmi_sum),
-			ns_to_per(total, taa_data->thread_nmi_sum));
+		printf("  NMI interference %.*s %9.2f us (%.2f %%)\n", 36, spaces,
+		       ns_to_usf(taa_data->thread_nmi_sum),
+		       ns_to_per(total, taa_data->thread_nmi_sum));
 
 	/*
 	 * If it is an IRQ latency, the other factors can be skipped.
@@ -643,9 +660,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu,
 	 * Prints the interference caused by IRQs to the thread latency.
 	 */
 	if (taa_data->thread_irq_sum) {
-		printf("  IRQ interference	\t\t\t	%9.2f us (%.2f %%)\n",
-			ns_to_usf(taa_data->thread_irq_sum),
-			ns_to_per(total, taa_data->thread_irq_sum));
+		printf("  IRQ interference %.*s %9.2f us (%.2f %%)\n", 36, spaces,
+		       ns_to_usf(taa_data->thread_irq_sum),
+		       ns_to_per(total, taa_data->thread_irq_sum));
 
 		trace_seq_do_printf(taa_data->irqs_seq);
 	}
@@ -654,9 +671,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu,
 	 * Prints the interference caused by Softirqs to the thread latency.
 	 */
 	if (taa_data->thread_softirq_sum) {
-		printf("  Softirq interference	\t\t\t	%9.2f us (%.2f %%)\n",
-			ns_to_usf(taa_data->thread_softirq_sum),
-			ns_to_per(total, taa_data->thread_softirq_sum));
+		printf("  Softirq interference %.*s %9.2f us (%.2f %%)\n", 32, spaces,
+		       ns_to_usf(taa_data->thread_softirq_sum),
+		       ns_to_per(total, taa_data->thread_softirq_sum));
 
 		trace_seq_do_printf(taa_data->softirqs_seq);
 	}
@@ -670,9 +687,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu,
 	 * timer handling latency.
 	 */
 	if (taa_data->thread_thread_sum) {
-		printf("  Thread interference	\t\t\t	%9.2f us (%.2f %%)\n",
-			ns_to_usf(taa_data->thread_thread_sum),
-			ns_to_per(total, taa_data->thread_thread_sum));
+		printf("  Thread interference %.*s %9.2f us (%.2f %%)\n", 33, spaces,
+		       ns_to_usf(taa_data->thread_thread_sum),
+		       ns_to_per(total, taa_data->thread_thread_sum));
 
 		trace_seq_do_printf(taa_data->threads_seq);
 	}
@@ -682,8 +699,8 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu,
 	 */
 print_total:
 	printf("------------------------------------------------------------------------\n");
-	printf("  %s latency:	\t\t\t	%9.2f us (100%%)\n", irq ? "IRQ" : "Thread",
-		ns_to_usf(total));
+	printf("  %s latency: %.*s %9.2f us (100%%)\n", irq ? "   IRQ" : "Thread",
+	       37, spaces, ns_to_usf(total));
 }
 
 static int timerlat_auto_analysis_collect_trace(struct timerlat_aa_context *taa_ctx)
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 8bd51aab65..5b869caed1 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -324,17 +324,29 @@ timerlat_print_summary(struct timerlat_hist_params *params,
 		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
 			continue;
 
-		if (!params->no_irq)
-			trace_seq_printf(trace->seq, "%9llu ",
-					data->hist[cpu].min_irq);
+		if (!params->no_irq) {
+			if (data->hist[cpu].irq_count)
+				trace_seq_printf(trace->seq, "%9llu ",
+						data->hist[cpu].min_irq);
+			else
+				trace_seq_printf(trace->seq, "        - ");
+		}
 
-		if (!params->no_thread)
-			trace_seq_printf(trace->seq, "%9llu ",
-					data->hist[cpu].min_thread);
+		if (!params->no_thread) {
+			if (data->hist[cpu].thread_count)
+				trace_seq_printf(trace->seq, "%9llu ",
+						data->hist[cpu].min_thread);
+			else
+				trace_seq_printf(trace->seq, "        - ");
+		}
 
-		if (params->user_hist)
-			trace_seq_printf(trace->seq, "%9llu ",
-					data->hist[cpu].min_user);
+		if (params->user_hist) {
+			if (data->hist[cpu].user_count)
+				trace_seq_printf(trace->seq, "%9llu ",
+						data->hist[cpu].min_user);
+			else
+				trace_seq_printf(trace->seq, "        - ");
+		}
 	}
 	trace_seq_printf(trace->seq, "\n");
 
@@ -384,17 +396,29 @@ timerlat_print_summary(struct timerlat_hist_params *params,
 		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
 			continue;
 
-		if (!params->no_irq)
-			trace_seq_printf(trace->seq, "%9llu ",
-					data->hist[cpu].max_irq);
+		if (!params->no_irq) {
+			if (data->hist[cpu].irq_count)
+				trace_seq_printf(trace->seq, "%9llu ",
+						 data->hist[cpu].max_irq);
+			else
+				trace_seq_printf(trace->seq, "        - ");
+		}
 
-		if (!params->no_thread)
-			trace_seq_printf(trace->seq, "%9llu ",
-					data->hist[cpu].max_thread);
+		if (!params->no_thread) {
+			if (data->hist[cpu].thread_count)
+				trace_seq_printf(trace->seq, "%9llu ",
+						data->hist[cpu].max_thread);
+			else
+				trace_seq_printf(trace->seq, "        - ");
+		}
 
-		if (params->user_hist)
-			trace_seq_printf(trace->seq, "%9llu ",
-					data->hist[cpu].max_user);
+		if (params->user_hist) {
+			if (data->hist[cpu].user_count)
+				trace_seq_printf(trace->seq, "%9llu ",
+						data->hist[cpu].max_user);
+			else
+				trace_seq_printf(trace->seq, "        - ");
+		}
 	}
 	trace_seq_printf(trace->seq, "\n");
 	trace_seq_do_printf(trace->seq);
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 8a3fa64319..2665e0bb5f 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -212,6 +212,8 @@ static void timerlat_top_header(struct osnoise_tool *top)
 	trace_seq_printf(s, "\n");
 }
 
+static const char *no_value = "        -";
+
 /*
  * timerlat_top_print - prints the output of a given CPU
  */
@@ -239,10 +241,7 @@ static void timerlat_top_print(struct osnoise_tool *top, int cpu)
 	trace_seq_printf(s, "%3d #%-9d |", cpu, cpu_data->irq_count);
 
 	if (!cpu_data->irq_count) {
-		trace_seq_printf(s, "        - ");
-		trace_seq_printf(s, "        - ");
-		trace_seq_printf(s, "        - ");
-		trace_seq_printf(s, "        - |");
+		trace_seq_printf(s, "%s %s %s %s |", no_value, no_value, no_value, no_value);
 	} else {
 		trace_seq_printf(s, "%9llu ", cpu_data->cur_irq / params->output_divisor);
 		trace_seq_printf(s, "%9llu ", cpu_data->min_irq / params->output_divisor);
@@ -251,10 +250,7 @@ static void timerlat_top_print(struct osnoise_tool *top, int cpu)
 	}
 
 	if (!cpu_data->thread_count) {
-		trace_seq_printf(s, "        - ");
-		trace_seq_printf(s, "        - ");
-		trace_seq_printf(s, "        - ");
-		trace_seq_printf(s, "        -\n");
+		trace_seq_printf(s, "%s %s %s %s", no_value, no_value, no_value, no_value);
 	} else {
 		trace_seq_printf(s, "%9llu ", cpu_data->cur_thread / divisor);
 		trace_seq_printf(s, "%9llu ", cpu_data->min_thread / divisor);
@@ -271,10 +267,7 @@ static void timerlat_top_print(struct osnoise_tool *top, int cpu)
 	trace_seq_printf(s, " |");
 
 	if (!cpu_data->user_count) {
-		trace_seq_printf(s, "        - ");
-		trace_seq_printf(s, "        - ");
-		trace_seq_printf(s, "        - ");
-		trace_seq_printf(s, "        -\n");
+		trace_seq_printf(s, "%s %s %s %s\n", no_value, no_value, no_value, no_value);
 	} else {
 		trace_seq_printf(s, "%9llu ", cpu_data->cur_user / divisor);
 		trace_seq_printf(s, "%9llu ", cpu_data->min_user / divisor);