Merging upstream version 6.7.12.

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

46 files changed, 500 insertions, 148 deletions

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 7ec4f5671e..865bfa869a 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -2294,7 +2294,7 @@ static int profile_open_perf_events(struct profiler_bpf *obj)
 	int map_fd;
 
 	profile_perf_events = calloc(
-		sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric);
+		obj->rodata->num_cpu * obj->rodata->num_metric, sizeof(int));
 	if (!profile_perf_events) {
 		p_err("failed to allocate memory for perf_event array: %s",
 		      strerror(errno));
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index 27a23196d5..d9520cb826 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -70,6 +70,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <errno.h>
+#include <linux/btf_ids.h>
 #include <linux/rbtree.h>
 #include <linux/zalloc.h>
 #include <linux/err.h>
@@ -78,7 +79,7 @@
 #include <subcmd/parse-options.h>
 
 #define BTF_IDS_SECTION	".BTF_ids"
-#define BTF_ID		"__BTF_ID__"
+#define BTF_ID_PREFIX	"__BTF_ID__"
 
 #define BTF_STRUCT	"struct"
 #define BTF_UNION	"union"
@@ -89,6 +90,14 @@
 
 #define ADDR_CNT	100
 
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+# define ELFDATANATIVE	ELFDATA2LSB
+#elif __BYTE_ORDER == __BIG_ENDIAN
+# define ELFDATANATIVE	ELFDATA2MSB
+#else
+# error "Unknown machine endianness!"
+#endif
+
 struct btf_id {
 	struct rb_node	 rb_node;
 	char		*name;
@@ -116,6 +125,7 @@ struct object {
 		int		 idlist_shndx;
 		size_t		 strtabidx;
 		unsigned long	 idlist_addr;
+		int		 encoding;
 	} efile;
 
 	struct rb_root	sets;
@@ -161,7 +171,7 @@ static int eprintf(int level, int var, const char *fmt, ...)
 
 static bool is_btf_id(const char *name)
 {
-	return name && !strncmp(name, BTF_ID, sizeof(BTF_ID) - 1);
+	return name && !strncmp(name, BTF_ID_PREFIX, sizeof(BTF_ID_PREFIX) - 1);
 }
 
 static struct btf_id *btf_id__find(struct rb_root *root, const char *name)
@@ -319,6 +329,7 @@ static int elf_collect(struct object *obj)
 {
 	Elf_Scn *scn = NULL;
 	size_t shdrstrndx;
+	GElf_Ehdr ehdr;
 	int idx = 0;
 	Elf *elf;
 	int fd;
@@ -350,6 +361,13 @@ static int elf_collect(struct object *obj)
 		return -1;
 	}
 
+	if (gelf_getehdr(obj->efile.elf, &ehdr) == NULL) {
+		pr_err("FAILED cannot get ELF header: %s\n",
+			elf_errmsg(-1));
+		return -1;
+	}
+	obj->efile.encoding = ehdr.e_ident[EI_DATA];
+
 	/*
 	 * Scan all the elf sections and look for save data
 	 * from .BTF_ids section and symbols.
@@ -441,7 +459,7 @@ static int symbols_collect(struct object *obj)
 		 * __BTF_ID__TYPE__vfs_truncate__0
 		 * prefix =  ^
 		 */
-		prefix = name + sizeof(BTF_ID) - 1;
+		prefix = name + sizeof(BTF_ID_PREFIX) - 1;
 
 		/* struct */
 		if (!strncmp(prefix, BTF_STRUCT, sizeof(BTF_STRUCT) - 1)) {
@@ -649,19 +667,18 @@ static int cmp_id(const void *pa, const void *pb)
 static int sets_patch(struct object *obj)
 {
 	Elf_Data *data = obj->efile.idlist;
-	int *ptr = data->d_buf;
 	struct rb_node *next;
 
 	next = rb_first(&obj->sets);
 	while (next) {
-		unsigned long addr, idx;
+		struct btf_id_set8 *set8;
+		struct btf_id_set *set;
+		unsigned long addr, off;
 		struct btf_id *id;
-		int *base;
-		int cnt;
 
 		id   = rb_entry(next, struct btf_id, rb_node);
 		addr = id->addr[0];
-		idx  = addr - obj->efile.idlist_addr;
+		off = addr - obj->efile.idlist_addr;
 
 		/* sets are unique */
 		if (id->addr_cnt != 1) {
@@ -670,14 +687,39 @@ static int sets_patch(struct object *obj)
 			return -1;
 		}
 
-		idx = idx / sizeof(int);
-		base = &ptr[idx] + (id->is_set8 ? 2 : 1);
-		cnt = ptr[idx];
+		if (id->is_set) {
+			set = data->d_buf + off;
+			qsort(set->ids, set->cnt, sizeof(set->ids[0]), cmp_id);
+		} else {
+			set8 = data->d_buf + off;
+			/*
+			 * Make sure id is at the beginning of the pairs
+			 * struct, otherwise the below qsort would not work.
+			 */
+			BUILD_BUG_ON(set8->pairs != &set8->pairs[0].id);
+			qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id);
 
-		pr_debug("sorting  addr %5lu: cnt %6d [%s]\n",
-			 (idx + 1) * sizeof(int), cnt, id->name);
+			/*
+			 * When ELF endianness does not match endianness of the
+			 * host, libelf will do the translation when updating
+			 * the ELF. This, however, corrupts SET8 flags which are
+			 * already in the target endianness. So, let's bswap
+			 * them to the host endianness and libelf will then
+			 * correctly translate everything.
+			 */
+			if (obj->efile.encoding != ELFDATANATIVE) {
+				int i;
+
+				set8->flags = bswap_32(set8->flags);
+				for (i = 0; i < set8->cnt; i++) {
+					set8->pairs[i].flags =
+						bswap_32(set8->pairs[i].flags);
+				}
+			}
+		}
 
-		qsort(base, cnt, id->is_set8 ? sizeof(uint64_t) : sizeof(int), cmp_id);
+		pr_debug("sorting  addr %5lu: cnt %6d [%s]\n",
+			 off, id->is_set ? set->cnt : set8->cnt, id->name);
 
 		next = rb_next(next);
 	}
diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h
index 2f882d5cb3..72ea363d43 100644
--- a/tools/include/linux/btf_ids.h
+++ b/tools/include/linux/btf_ids.h
@@ -3,11 +3,22 @@
 #ifndef _LINUX_BTF_IDS_H
 #define _LINUX_BTF_IDS_H
 
+#include <linux/types.h> /* for u32 */
+
 struct btf_id_set {
 	u32 cnt;
 	u32 ids[];
 };
 
+struct btf_id_set8 {
+	u32 cnt;
+	u32 flags;
+	struct {
+		u32 id;
+		u32 flags;
+	} pairs[];
+};
+
 #ifdef CONFIG_DEBUG_INFO_BTF
 
 #include <linux/compiler.h> /* for __PASTE */
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index d0f53772bd..dad7917903 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -35,7 +35,7 @@
 extern "C" {
 #endif
 
-int libbpf_set_memlock_rlim(size_t memlock_bytes);
+LIBBPF_API int libbpf_set_memlock_rlim(size_t memlock_bytes);
 
 struct bpf_map_create_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index df1b550f74..ca83af916c 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -70,6 +70,7 @@
 
 static struct bpf_map *bpf_object__add_map(struct bpf_object *obj);
 static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog);
+static int map_set_def_max_entries(struct bpf_map *map);
 
 static const char * const attach_type_name[] = {
 	[BPF_CGROUP_INET_INGRESS]	= "cgroup_inet_ingress",
@@ -5214,6 +5215,9 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 
 	if (bpf_map_type__is_map_in_map(def->type)) {
 		if (map->inner_map) {
+			err = map_set_def_max_entries(map->inner_map);
+			if (err)
+				return err;
 			err = bpf_object__create_map(obj, map->inner_map, true);
 			if (err) {
 				pr_warn("map '%s': failed to create inner map: %d\n",
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index f0f08635ad..57dec645d6 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -18,6 +18,20 @@
 #include <libelf.h>
 #include "relo_core.h"
 
+/* Android's libc doesn't support AT_EACCESS in faccessat() implementation
+ * ([0]), and just returns -EINVAL even if file exists and is accessible.
+ * See [1] for issues caused by this.
+ *
+ * So just redefine it to 0 on Android.
+ *
+ * [0] https://android.googlesource.com/platform/bionic/+/refs/heads/android13-release/libc/bionic/faccessat.cpp#50
+ * [1] https://github.com/libbpf/libbpf-bootstrap/issues/250#issuecomment-1911324250
+ */
+#ifdef __ANDROID__
+#undef AT_EACCESS
+#define AT_EACCESS 0
+#endif
+
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 090bcf6e3b..68a2def171 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -496,8 +496,8 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
 	if (err)
 		return libbpf_err(err);
 
-	opts->feature_flags = md.flags;
-	opts->xdp_zc_max_segs = md.xdp_zc_max_segs;
+	OPTS_SET(opts, feature_flags, md.flags);
+	OPTS_SET(opts, xdp_zc_max_segs, md.xdp_zc_max_segs);
 
 skip_feature_flags:
 	return 0;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index e94756e09c..167603f839 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3620,6 +3620,18 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 				}
 
 				if (!save_insn->visited) {
+					/*
+					 * If the restore hint insn is at the
+					 * beginning of a basic block and was
+					 * branched to from elsewhere, and the
+					 * save insn hasn't been visited yet,
+					 * defer following this branch for now.
+					 * It will be seen later via the
+					 * straight-line path.
+					 */
+					if (!prev_insn)
+						return 0;
+
 					WARN_INSN(insn, "objtool isn't smart enough to handle this CFI save/restore combo");
 					return 1;
 				}
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 058c9aecf6..af22d539f3 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1148,7 +1148,7 @@ bpf-skel:
 endif # CONFIG_PERF_BPF_SKEL
 
 bpf-skel-clean:
-	$(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS)
+	$(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS) $(SKEL_OUT)/vmlinux.h
 
 clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $(LIBPERF)-clean arm64-sysreg-defs-clean fixdep-clean python-clean bpf-skel-clean tests-coresight-targets-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-iostat $(LANG_BINDINGS)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dcf288a4fb..5d86aa5ff5 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1818,8 +1818,8 @@ static int
 record__switch_output(struct record *rec, bool at_exit)
 {
 	struct perf_data *data = &rec->data;
+	char *new_filename = NULL;
 	int fd, err;
-	char *new_filename;
 
 	/* Same Size:      "2015122520103046"*/
 	char timestamp[] = "InvalidTimestamp";
@@ -2216,32 +2216,6 @@ static void hit_auxtrace_snapshot_trigger(struct record *rec)
 	}
 }
 
-static void record__uniquify_name(struct record *rec)
-{
-	struct evsel *pos;
-	struct evlist *evlist = rec->evlist;
-	char *new_name;
-	int ret;
-
-	if (perf_pmus__num_core_pmus() == 1)
-		return;
-
-	evlist__for_each_entry(evlist, pos) {
-		if (!evsel__is_hybrid(pos))
-			continue;
-
-		if (strchr(pos->name, '/'))
-			continue;
-
-		ret = asprintf(&new_name, "%s/%s/",
-			       pos->pmu_name, pos->name);
-		if (ret) {
-			free(pos->name);
-			pos->name = new_name;
-		}
-	}
-}
-
 static int record__terminate_thread(struct record_thread *thread_data)
 {
 	int err;
@@ -2475,7 +2449,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (data->is_pipe && rec->evlist->core.nr_entries == 1)
 		rec->opts.sample_id = true;
 
-	record__uniquify_name(rec);
+	if (rec->timestamp_filename && perf_data__is_pipe(data)) {
+		rec->timestamp_filename = false;
+		pr_warning("WARNING: --timestamp-filename option is not available in pipe mode.\n");
+	}
+
+	evlist__uniquify_name(rec->evlist);
 
 	/* Debug message used by test scripts */
 	pr_debug3("perf record opening and mmapping events\n");
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ea8c7eca5e..cd64ae44cc 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1027,8 +1027,8 @@ static int perf_top__start_counters(struct perf_top *top)
 
 	evlist__for_each_entry(evlist, counter) {
 try_again:
-		if (evsel__open(counter, top->evlist->core.user_requested_cpus,
-				     top->evlist->core.threads) < 0) {
+		if (evsel__open(counter, counter->core.cpus,
+				counter->core.threads) < 0) {
 
 			/*
 			 * Specially handle overwrite fall back.
@@ -1299,6 +1299,7 @@ static int __cmd_top(struct perf_top *top)
 		}
 	}
 
+	evlist__uniquify_name(top->evlist);
 	ret = perf_top__start_counters(top);
 	if (ret)
 		return ret;
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index c29d8a382b..550675ce0b 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -430,8 +430,6 @@ int perf_data__switch(struct perf_data *data,
 {
 	int ret;
 
-	if (check_pipe(data))
-		return -EINVAL;
 	if (perf_data__is_read(data))
 		return -EINVAL;
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b0ed14a6da..eb1dd29c53 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -2525,3 +2525,28 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis
 	}
 	perf_cpu_map__put(user_requested_cpus);
 }
+
+void evlist__uniquify_name(struct evlist *evlist)
+{
+	struct evsel *pos;
+	char *new_name;
+	int ret;
+
+	if (perf_pmus__num_core_pmus() == 1)
+		return;
+
+	evlist__for_each_entry(evlist, pos) {
+		if (!evsel__is_hybrid(pos))
+			continue;
+
+		if (strchr(pos->name, '/'))
+			continue;
+
+		ret = asprintf(&new_name, "%s/%s/",
+			       pos->pmu_name, pos->name);
+		if (ret) {
+			free(pos->name);
+			pos->name = new_name;
+		}
+	}
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 98e7ddb2bd..cb91dc9117 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -442,5 +442,6 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx);
 int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf);
 void evlist__check_mem_load_aux(struct evlist *evlist);
 void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_list);
+void evlist__uniquify_name(struct evlist *evlist);
 
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 72a5dfc38d..1fb24ca8ae 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2340,7 +2340,6 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 	data->period = evsel->core.attr.sample_period;
 	data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	data->misc    = event->header.misc;
-	data->id = -1ULL;
 	data->data_src = PERF_MEM_DATA_SRC_NONE;
 	data->vcpu = -1;
 
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 7be23b3ac0..b8875aac8f 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -500,7 +500,25 @@ double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const
 	tmp = evlist__new();
 	if (!tmp)
 		return NAN;
-	ret = parse_event(tmp, id) ? 0 : 1;
+
+	if (strchr(id, '@')) {
+		char *tmp_id, *p;
+
+		tmp_id = strdup(id);
+		if (!tmp_id) {
+			ret = NAN;
+			goto out;
+		}
+		p = strchr(tmp_id, '@');
+		*p = '/';
+		p = strrchr(tmp_id, '@');
+		*p = '/';
+		ret = parse_event(tmp, tmp_id) ? 0 : 1;
+		free(tmp_id);
+	} else {
+		ret = parse_event(tmp, id) ? 0 : 1;
+	}
+out:
 	evlist__delete(tmp);
 	return ret;
 }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d3c9aa4326..aaa013af52 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1019,10 +1019,9 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 	 * type value and format definitions. Load both right
 	 * now.
 	 */
-	if (pmu_format(pmu, dirfd, name)) {
-		free(pmu);
-		return NULL;
-	}
+	if (pmu_format(pmu, dirfd, name))
+		goto err;
+
 	pmu->is_core = is_pmu_core(name);
 	pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core);
 
@@ -1756,6 +1755,12 @@ bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name)
 
 bool perf_pmu__is_software(const struct perf_pmu *pmu)
 {
+	const char *known_sw_pmus[] = {
+		"kprobe",
+		"msr",
+		"uprobe",
+	};
+
 	if (pmu->is_core || pmu->is_uncore || pmu->auxtrace)
 		return false;
 	switch (pmu->type) {
@@ -1767,7 +1772,11 @@ bool perf_pmu__is_software(const struct perf_pmu *pmu)
 	case PERF_TYPE_BREAKPOINT:	return true;
 	default: break;
 	}
-	return !strcmp(pmu->name, "kprobe") || !strcmp(pmu->name, "uprobe");
+	for (size_t i = 0; i < ARRAY_SIZE(known_sw_pmus); i++) {
+		if (!strcmp(pmu->name, known_sw_pmus[i]))
+			return true;
+	}
+	return false;
 }
 
 FILE *perf_pmu__open_file(const struct perf_pmu *pmu, const char *name)
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index b0fc48be62..4f67e8f00a 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -232,7 +232,6 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state)
 bool is_event_supported(u8 type, u64 config)
 {
 	bool ret = true;
-	int open_return;
 	struct evsel *evsel;
 	struct perf_event_attr attr = {
 		.type = type,
@@ -246,20 +245,32 @@ bool is_event_supported(u8 type, u64 config)
 
 	evsel = evsel__new(&attr);
 	if (evsel) {
-		open_return = evsel__open(evsel, NULL, tmap);
-		ret = open_return >= 0;
+		ret = evsel__open(evsel, NULL, tmap) >= 0;
 
-		if (open_return == -EACCES) {
+		if (!ret) {
 			/*
-			 * This happens if the paranoid value
+			 * The event may fail to open if the paranoid value
 			 * /proc/sys/kernel/perf_event_paranoid is set to 2
-			 * Re-run with exclude_kernel set; we don't do that
-			 * by default as some ARM machines do not support it.
-			 *
+			 * Re-run with exclude_kernel set; we don't do that by
+			 * default as some ARM machines do not support it.
 			 */
 			evsel->core.attr.exclude_kernel = 1;
 			ret = evsel__open(evsel, NULL, tmap) >= 0;
 		}
+
+		if (!ret) {
+			/*
+			 * The event may fail to open if the PMU requires
+			 * exclude_guest to be set (e.g. as the Apple M1 PMU
+			 * requires).
+			 * Re-run with exclude_guest set; we don't do that by
+			 * default as it's equally legitimate for another PMU
+			 * driver to require that exclude_guest is clear.
+			 */
+			evsel->core.attr.exclude_guest = 1;
+			ret = evsel__open(evsel, NULL, tmap) >= 0;
+		}
+
 		evsel__delete(evsel);
 	}
 
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 034b496df2..7addc34afc 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -399,6 +399,8 @@ static void addr2line_subprocess_cleanup(struct child_process *a2l)
 		kill(a2l->pid, SIGKILL);
 		finish_command(a2l); /* ignore result, we don't care */
 		a2l->pid = -1;
+		close(a2l->in);
+		close(a2l->out);
 	}
 
 	free(a2l);
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index afe6db8e7b..969ce40096 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -560,7 +560,7 @@ static void print_metric_only(struct perf_stat_config *config,
 	if (color)
 		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
 
-	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+	color_snprintf(str, sizeof(str), color ?: "", fmt ?: "", val);
 	fprintf(out, "%*s ", mlen, str);
 	os->first = false;
 }
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index e314261678..cf573ff3fa 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -414,12 +414,7 @@ static int prepare_metric(struct evsel **metric_events,
 				val = NAN;
 				source_count = 0;
 			} else {
-				/*
-				 * If an event was scaled during stat gathering,
-				 * reverse the scale before computing the
-				 * metric.
-				 */
-				val = aggr->counts.val * (1.0 / metric_events[i]->scale);
+				val = aggr->counts.val;
 				source_count = evsel__source_count(metric_events[i]);
 			}
 		}
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index e848579e61..ea3b431b97 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -280,13 +280,13 @@ struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str)
 		threads->nr = ntasks;
 	}
 out:
+	strlist__delete(slist);
 	if (threads)
 		refcount_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
 	zfree(&threads);
-	strlist__delete(slist);
 	goto out;
 }
 
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 91907b321f..e7c9e1c7fd 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2020 Facebook */
 #include <linux/btf.h>
 #include <linux/btf_ids.h>
+#include <linux/delay.h>
 #include <linux/error-injection.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -544,6 +545,14 @@ static int bpf_testmod_init(void)
 
 static void bpf_testmod_exit(void)
 {
+        /* Need to wait for all references to be dropped because
+         * bpf_kfunc_call_test_release() which currently resides in kernel can
+         * be called after bpf_testmod is unloaded. Once release function is
+         * moved into the module this wait can be removed.
+         */
+	while (refcount_read(&prog_test_struct.cnt) > 1)
+		msleep(20);
+
 	return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
index 59b38569f3..2bc932a18c 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
@@ -203,6 +203,7 @@ static int setup_redirect_target(const char *target_dev, bool need_mac)
 	if (!ASSERT_GE(target_index, 0, "if_nametoindex"))
 		goto fail;
 
+	SYS(fail, "sysctl -w net.ipv6.conf.all.disable_ipv6=1");
 	SYS(fail, "ip link add link_err type dummy");
 	SYS(fail, "ip link set lo up");
 	SYS(fail, "ip addr add dev lo " LOCAL_SRC "/32");
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index 518f143c5b..dbe06aeaa2 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -188,6 +188,7 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 {
 	struct nstoken *nstoken = NULL;
 	char src_fwd_addr[IFADDR_STR_LEN+1] = {};
+	char src_addr[IFADDR_STR_LEN + 1] = {};
 	int err;
 
 	if (result->dev_mode == MODE_VETH) {
@@ -208,6 +209,9 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	if (get_ifaddr("src_fwd", src_fwd_addr))
 		goto fail;
 
+	if (get_ifaddr("src", src_addr))
+		goto fail;
+
 	result->ifindex_src = if_nametoindex("src");
 	if (!ASSERT_GT(result->ifindex_src, 0, "ifindex_src"))
 		goto fail;
@@ -270,6 +274,13 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	SYS(fail, "ip route add " IP4_DST "/32 dev dst_fwd scope global");
 	SYS(fail, "ip route add " IP6_DST "/128 dev dst_fwd scope global");
 
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip neigh add " IP4_SRC " dev src_fwd lladdr %s", src_addr);
+		SYS(fail, "ip neigh add " IP6_SRC " dev src_fwd lladdr %s", src_addr);
+		SYS(fail, "ip neigh add " IP4_DST " dev dst_fwd lladdr %s", MAC_DST);
+		SYS(fail, "ip neigh add " IP6_DST " dev dst_fwd lladdr %s", MAC_DST);
+	}
+
 	close_netns(nstoken);
 
 	/** setup in 'dst' namespace */
@@ -280,6 +291,7 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	SYS(fail, "ip addr add " IP4_DST "/32 dev dst");
 	SYS(fail, "ip addr add " IP6_DST "/128 dev dst nodad");
 	SYS(fail, "ip link set dev dst up");
+	SYS(fail, "ip link set dev lo up");
 
 	SYS(fail, "ip route add " IP4_SRC "/32 dev dst scope global");
 	SYS(fail, "ip route add " IP4_NET "/16 dev dst scope global");
@@ -457,7 +469,7 @@ static int set_forwarding(bool enable)
 	return 0;
 }
 
-static void rcv_tstamp(int fd, const char *expected, size_t s)
+static int __rcv_tstamp(int fd, const char *expected, size_t s, __u64 *tstamp)
 {
 	struct __kernel_timespec pkt_ts = {};
 	char ctl[CMSG_SPACE(sizeof(pkt_ts))];
@@ -478,7 +490,7 @@ static void rcv_tstamp(int fd, const char *expected, size_t s)
 
 	ret = recvmsg(fd, &msg, 0);
 	if (!ASSERT_EQ(ret, s, "recvmsg"))
-		return;
+		return -1;
 	ASSERT_STRNEQ(data, expected, s, "expected rcv data");
 
 	cmsg = CMSG_FIRSTHDR(&msg);
@@ -487,6 +499,12 @@ static void rcv_tstamp(int fd, const char *expected, size_t s)
 		memcpy(&pkt_ts, CMSG_DATA(cmsg), sizeof(pkt_ts));
 
 	pkt_ns = pkt_ts.tv_sec * NSEC_PER_SEC + pkt_ts.tv_nsec;
+	if (tstamp) {
+		/* caller will check the tstamp itself */
+		*tstamp = pkt_ns;
+		return 0;
+	}
+
 	ASSERT_NEQ(pkt_ns, 0, "pkt rcv tstamp");
 
 	ret = clock_gettime(CLOCK_REALTIME, &now_ts);
@@ -496,6 +514,60 @@ static void rcv_tstamp(int fd, const char *expected, size_t s)
 	if (ASSERT_GE(now_ns, pkt_ns, "check rcv tstamp"))
 		ASSERT_LT(now_ns - pkt_ns, 5 * NSEC_PER_SEC,
 			  "check rcv tstamp");
+	return 0;
+}
+
+static void rcv_tstamp(int fd, const char *expected, size_t s)
+{
+	__rcv_tstamp(fd, expected, s, NULL);
+}
+
+static int wait_netstamp_needed_key(void)
+{
+	int opt = 1, srv_fd = -1, cli_fd = -1, nretries = 0, err, n;
+	char buf[] = "testing testing";
+	struct nstoken *nstoken;
+	__u64 tstamp = 0;
+
+	nstoken = open_netns(NS_DST);
+	if (!nstoken)
+		return -1;
+
+	srv_fd = start_server(AF_INET6, SOCK_DGRAM, "::1", 0, 0);
+	if (!ASSERT_GE(srv_fd, 0, "start_server"))
+		goto done;
+
+	err = setsockopt(srv_fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW,
+			 &opt, sizeof(opt));
+	if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS_NEW)"))
+		goto done;
+
+	cli_fd = connect_to_fd(srv_fd, TIMEOUT_MILLIS);
+	if (!ASSERT_GE(cli_fd, 0, "connect_to_fd"))
+		goto done;
+
+again:
+	n = write(cli_fd, buf, sizeof(buf));
+	if (!ASSERT_EQ(n, sizeof(buf), "send to server"))
+		goto done;
+	err = __rcv_tstamp(srv_fd, buf, sizeof(buf), &tstamp);
+	if (!ASSERT_OK(err, "__rcv_tstamp"))
+		goto done;
+	if (!tstamp && nretries++ < 5) {
+		sleep(1);
+		printf("netstamp_needed_key retry#%d\n", nretries);
+		goto again;
+	}
+
+done:
+	if (!tstamp && srv_fd != -1) {
+		close(srv_fd);
+		srv_fd = -1;
+	}
+	if (cli_fd != -1)
+		close(cli_fd);
+	close_netns(nstoken);
+	return srv_fd;
 }
 
 static void snd_tstamp(int fd, char *b, size_t s)
@@ -832,11 +904,20 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result)
 {
 	struct test_tc_dtime *skel;
 	struct nstoken *nstoken;
-	int err;
+	int hold_tstamp_fd, err;
+
+	/* Hold a sk with the SOCK_TIMESTAMP set to ensure there
+	 * is no delay in the kernel net_enable_timestamp().
+	 * This ensures the following tests must have
+	 * non zero rcv tstamp in the recvmsg().
+	 */
+	hold_tstamp_fd = wait_netstamp_needed_key();
+	if (!ASSERT_GE(hold_tstamp_fd, 0, "wait_netstamp_needed_key"))
+		return;
 
 	skel = test_tc_dtime__open();
 	if (!ASSERT_OK_PTR(skel, "test_tc_dtime__open"))
-		return;
+		goto done;
 
 	skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd;
 	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
@@ -881,6 +962,7 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result)
 
 done:
 	test_tc_dtime__destroy(skel);
+	close(hold_tstamp_fd);
 }
 
 static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result)
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index c3b45745cb..6d8b54124c 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -511,7 +511,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons)
 	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
 		goto out;
 
-	if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK,
+	if (!ASSERT_EQ(query_opts.feature_flags, 0,
 		       "bond query_opts.feature_flags"))
 		goto out;
 
@@ -601,7 +601,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons)
 	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
 		goto out;
 
-	ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK,
+	ASSERT_EQ(query_opts.feature_flags, 0,
 		  "bond query_opts.feature_flags");
 out:
 	bpf_link__destroy(link);
diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c
index f416032ba8..b295f9b721 100644
--- a/tools/testing/selftests/bpf/progs/test_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c
@@ -21,6 +21,32 @@ struct {
 	__type(value, __u32);
 } mim_hash SEC(".maps");
 
+/* The following three maps are used to test
+ * perf_event_array map can be an inner
+ * map of hash/array_of_maps.
+ */
+struct perf_event_array {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+} inner_map0 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__array(values, struct perf_event_array);
+} mim_array_pe SEC(".maps") = {
+	.values = {&inner_map0}};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__array(values, struct perf_event_array);
+} mim_hash_pe SEC(".maps") = {
+	.values = {&inner_map0}};
+
 SEC("xdp")
 int xdp_mimtest0(struct xdp_md *ctx)
 {
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 7fc00e423e..e0dd101c9f 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1190,7 +1190,11 @@ static void test_map_in_map(void)
 		goto out_map_in_map;
 	}
 
-	bpf_object__load(obj);
+	err = bpf_object__load(obj);
+	if (err) {
+		printf("Failed to load test prog\n");
+		goto out_map_in_map;
+	}
 
 	map = bpf_object__find_map_by_name(obj, "mim_array");
 	if (!map) {
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 4faa898ff7..27fd7ed3e4 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -271,7 +271,7 @@ ssize_t get_uprobe_offset(const void *addr)
 	 * addi  r2,r2,XXXX
 	 */
 	{
-		const u32 *insn = (const u32 *)(uintptr_t)addr;
+		const __u32 *insn = (const __u32 *)(uintptr_t)addr;
 
 		if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) ||
 		     ((*insn & OP_RT_RA_MASK) == LIS_R2)) &&
diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c
index ec22291363..18a49c70d4 100644
--- a/tools/testing/selftests/mm/gup_test.c
+++ b/tools/testing/selftests/mm/gup_test.c
@@ -50,39 +50,41 @@ static char *cmd_to_str(unsigned long cmd)
 void *gup_thread(void *data)
 {
 	struct gup_test gup = *(struct gup_test *)data;
-	int i;
+	int i, status;
 
 	/* Only report timing information on the *_BENCHMARK commands: */
 	if ((cmd == PIN_FAST_BENCHMARK) || (cmd == GUP_FAST_BENCHMARK) ||
 	     (cmd == PIN_LONGTERM_BENCHMARK)) {
 		for (i = 0; i < repeats; i++) {
 			gup.size = size;
-			if (ioctl(gup_fd, cmd, &gup))
-				perror("ioctl"), exit(1);
+			status = ioctl(gup_fd, cmd, &gup);
+			if (status)
+				break;
 
 			pthread_mutex_lock(&print_mutex);
-			printf("%s: Time: get:%lld put:%lld us",
-			       cmd_to_str(cmd), gup.get_delta_usec,
-			       gup.put_delta_usec);
+			ksft_print_msg("%s: Time: get:%lld put:%lld us",
+				       cmd_to_str(cmd), gup.get_delta_usec,
+				       gup.put_delta_usec);
 			if (gup.size != size)
-				printf(", truncated (size: %lld)", gup.size);
-			printf("\n");
+				ksft_print_msg(", truncated (size: %lld)", gup.size);
+			ksft_print_msg("\n");
 			pthread_mutex_unlock(&print_mutex);
 		}
 	} else {
 		gup.size = size;
-		if (ioctl(gup_fd, cmd, &gup)) {
-			perror("ioctl");
-			exit(1);
-		}
+		status = ioctl(gup_fd, cmd, &gup);
+		if (status)
+			goto return_;
 
 		pthread_mutex_lock(&print_mutex);
-		printf("%s: done\n", cmd_to_str(cmd));
+		ksft_print_msg("%s: done\n", cmd_to_str(cmd));
 		if (gup.size != size)
-			printf("Truncated (size: %lld)\n", gup.size);
+			ksft_print_msg("Truncated (size: %lld)\n", gup.size);
 		pthread_mutex_unlock(&print_mutex);
 	}
 
+return_:
+	ksft_test_result(!status, "ioctl status %d\n", status);
 	return NULL;
 }
 
@@ -170,7 +172,7 @@ int main(int argc, char **argv)
 			touch = 1;
 			break;
 		default:
-			return -1;
+			ksft_exit_fail_msg("Wrong argument\n");
 		}
 	}
 
@@ -198,11 +200,12 @@ int main(int argc, char **argv)
 		}
 	}
 
-	filed = open(file, O_RDWR|O_CREAT);
-	if (filed < 0) {
-		perror("open");
-		exit(filed);
-	}
+	ksft_print_header();
+	ksft_set_plan(nthreads);
+
+	filed = open(file, O_RDWR|O_CREAT, 0664);
+	if (filed < 0)
+		ksft_exit_fail_msg("Unable to open %s: %s\n", file, strerror(errno));
 
 	gup.nr_pages_per_call = nr_pages;
 	if (write)
@@ -213,27 +216,24 @@ int main(int argc, char **argv)
 		switch (errno) {
 		case EACCES:
 			if (getuid())
-				printf("Please run this test as root\n");
+				ksft_print_msg("Please run this test as root\n");
 			break;
 		case ENOENT:
-			if (opendir("/sys/kernel/debug") == NULL) {
-				printf("mount debugfs at /sys/kernel/debug\n");
-				break;
-			}
-			printf("check if CONFIG_GUP_TEST is enabled in kernel config\n");
+			if (opendir("/sys/kernel/debug") == NULL)
+				ksft_print_msg("mount debugfs at /sys/kernel/debug\n");
+			ksft_print_msg("check if CONFIG_GUP_TEST is enabled in kernel config\n");
 			break;
 		default:
-			perror("failed to open " GUP_TEST_FILE);
+			ksft_print_msg("failed to open %s: %s\n", GUP_TEST_FILE, strerror(errno));
 			break;
 		}
-		exit(KSFT_SKIP);
+		ksft_test_result_skip("Please run this test as root\n");
+		return ksft_exit_pass();
 	}
 
 	p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
-	if (p == MAP_FAILED) {
-		perror("mmap");
-		exit(1);
-	}
+	if (p == MAP_FAILED)
+		ksft_exit_fail_msg("mmap: %s\n", strerror(errno));
 	gup.addr = (unsigned long)p;
 
 	if (thp == 1)
@@ -264,7 +264,8 @@ int main(int argc, char **argv)
 		ret = pthread_join(tid[i], NULL);
 		assert(ret == 0);
 	}
+
 	free(tid);
 
-	return 0;
+	return ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c
index cc5f144430..7dbfa53d93 100644
--- a/tools/testing/selftests/mm/soft-dirty.c
+++ b/tools/testing/selftests/mm/soft-dirty.c
@@ -137,7 +137,7 @@ static void test_mprotect(int pagemap_fd, int pagesize, bool anon)
 		if (!map)
 			ksft_exit_fail_msg("anon mmap failed\n");
 	} else {
-		test_fd = open(fname, O_RDWR | O_CREAT);
+		test_fd = open(fname, O_RDWR | O_CREAT, 0664);
 		if (test_fd < 0) {
 			ksft_test_result_skip("Test %s open() file failed\n", __func__);
 			return;
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index 0e74635c8c..dff3be2348 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -253,7 +253,7 @@ void split_file_backed_thp(void)
 		goto cleanup;
 	}
 
-	fd = open(testfile, O_CREAT|O_WRONLY);
+	fd = open(testfile, O_CREAT|O_WRONLY, 0664);
 	if (fd == -1) {
 		perror("Cannot open testing file\n");
 		goto cleanup;
diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
index 02b89860e1..ba6777cdf4 100644
--- a/tools/testing/selftests/mm/uffd-common.c
+++ b/tools/testing/selftests/mm/uffd-common.c
@@ -17,6 +17,7 @@ bool map_shared;
 bool test_uffdio_wp = true;
 unsigned long long *count_verify;
 uffd_test_ops_t *uffd_test_ops;
+atomic_bool ready_for_fork;
 
 static int uffd_mem_fd_create(off_t mem_size, bool hugetlb)
 {
@@ -507,6 +508,8 @@ void *uffd_poll_thread(void *arg)
 	pollfd[1].fd = pipefd[cpu*2];
 	pollfd[1].events = POLLIN;
 
+	ready_for_fork = true;
+
 	for (;;) {
 		ret = poll(pollfd, 2, -1);
 		if (ret <= 0) {
diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
index 7c4fa964c3..1f0d573f30 100644
--- a/tools/testing/selftests/mm/uffd-common.h
+++ b/tools/testing/selftests/mm/uffd-common.h
@@ -32,6 +32,7 @@
 #include <inttypes.h>
 #include <stdint.h>
 #include <sys/random.h>
+#include <stdatomic.h>
 
 #include "../kselftest.h"
 #include "vm_util.h"
@@ -97,6 +98,7 @@ extern bool map_shared;
 extern bool test_uffdio_wp;
 extern unsigned long long *count_verify;
 extern volatile bool test_uffdio_copy_eexist;
+extern atomic_bool ready_for_fork;
 
 extern uffd_test_ops_t anon_uffd_test_ops;
 extern uffd_test_ops_t shmem_uffd_test_ops;
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index 2c68709062..92d51768b7 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -770,6 +770,8 @@ static void uffd_sigbus_test_common(bool wp)
 	char c;
 	struct uffd_args args = { 0 };
 
+	ready_for_fork = false;
+
 	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
 
 	if (uffd_register(uffd, area_dst, nr_pages * page_size,
@@ -785,6 +787,9 @@ static void uffd_sigbus_test_common(bool wp)
 	if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
 		err("uffd_poll_thread create");
 
+	while (!ready_for_fork)
+		; /* Wait for the poll_thread to start executing before forking */
+
 	pid = fork();
 	if (pid < 0)
 		err("fork");
@@ -824,6 +829,8 @@ static void uffd_events_test_common(bool wp)
 	char c;
 	struct uffd_args args = { 0 };
 
+	ready_for_fork = false;
+
 	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
 	if (uffd_register(uffd, area_dst, nr_pages * page_size,
 			  true, wp, false))
@@ -833,6 +840,9 @@ static void uffd_events_test_common(bool wp)
 	if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
 		err("uffd_poll_thread create");
 
+	while (!ready_for_fork)
+		; /* Wait for the poll_thread to start executing before forking */
+
 	pid = fork();
 	if (pid < 0)
 		err("fork");
@@ -1219,7 +1229,8 @@ uffd_test_case_t uffd_tests[] = {
 		.uffd_fn = uffd_sigbus_wp_test,
 		.mem_targets = MEM_ALL,
 		.uffd_feature_required = UFFD_FEATURE_SIGBUS |
-		UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_PAGEFAULT_FLAG_WP,
+		UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_PAGEFAULT_FLAG_WP |
+		UFFD_FEATURE_WP_HUGETLBFS_SHMEM,
 	},
 	{
 		.name = "events",
diff --git a/tools/testing/selftests/mqueue/setting b/tools/testing/selftests/mqueue/setting
new file mode 100644
index 0000000000..a953c96aa1
--- /dev/null
+++ b/tools/testing/selftests/mqueue/setting
@@ -0,0 +1 @@
+timeout=180
diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config
index 697994a927..8d7a1a004b 100644
--- a/tools/testing/selftests/net/forwarding/config
+++ b/tools/testing/selftests/net/forwarding/config
@@ -6,14 +6,49 @@ CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_NET_VRF=m
 CONFIG_BPF_SYSCALL=y
 CONFIG_CGROUP_BPF=y
+CONFIG_DUMMY=m
+CONFIG_IPV6=y
+CONFIG_IPV6_GRE=m
+CONFIG_IPV6_MROUTE=y
+CONFIG_IPV6_MROUTE_MULTIPLE_TABLES=y
+CONFIG_IPV6_PIMSM_V2=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_MACVLAN=m
 CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_NET_ACT_MPLS=m
+CONFIG_NET_ACT_PEDIT=m
+CONFIG_NET_ACT_POLICE=m
+CONFIG_NET_ACT_SAMPLE=m
+CONFIG_NET_ACT_SKBEDIT=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
 CONFIG_NET_ACT_VLAN=m
 CONFIG_NET_CLS_FLOWER=m
 CONFIG_NET_CLS_MATCHALL=m
+CONFIG_NET_CLS_BASIC=m
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_META=m
+CONFIG_NET_IPGRE=m
+CONFIG_NET_IPGRE_DEMUX=m
+CONFIG_NET_IPIP=m
+CONFIG_NET_SCH_ETS=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_ACT_GACT=m
+CONFIG_NET_SCH_PRIO=m
+CONFIG_NET_SCH_RED=m
+CONFIG_NET_SCH_TBF=m
+CONFIG_NET_TC_SKB_EXT=y
+CONFIG_NET_TEAM=y
+CONFIG_NET_TEAM_MODE_LOADBALANCE=y
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_FLOW_TABLE=m
+CONFIG_NF_TABLES=m
 CONFIG_VETH=m
 CONFIG_NAMESPACES=y
 CONFIG_NET_NS=y
+CONFIG_VXLAN=m
+CONFIG_XFRM_USER=m
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh
index ac97f07e5c..bd3f7d492a 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh
@@ -354,7 +354,7 @@ __ping_ipv4()
 
 	# Send 100 packets and verify that at least 100 packets hit the rule,
 	# to overcome ARP noise.
-	PING_COUNT=100 PING_TIMEOUT=11 ping_do $dev $dst_ip
+	PING_COUNT=100 PING_TIMEOUT=20 ping_do $dev $dst_ip
 	check_err $? "Ping failed"
 
 	tc_check_at_least_x_packets "dev $rp1 egress" 101 10 100
@@ -410,7 +410,7 @@ __ping_ipv6()
 
 	# Send 100 packets and verify that at least 100 packets hit the rule,
 	# to overcome neighbor discovery noise.
-	PING_COUNT=100 PING_TIMEOUT=11 ping6_do $dev $dst_ip
+	PING_COUNT=100 PING_TIMEOUT=20 ping6_do $dev $dst_ip
 	check_err $? "Ping failed"
 
 	tc_check_at_least_x_packets "dev $rp1 egress" 101 100
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh
index d880df89bc..e83fde79f4 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh
@@ -457,7 +457,7 @@ __ping_ipv4()
 
 	# Send 100 packets and verify that at least 100 packets hit the rule,
 	# to overcome ARP noise.
-	PING_COUNT=100 PING_TIMEOUT=11 ping_do $dev $dst_ip
+	PING_COUNT=100 PING_TIMEOUT=20 ping_do $dev $dst_ip
 	check_err $? "Ping failed"
 
 	tc_check_at_least_x_packets "dev $rp1 egress" 101 10 100
@@ -522,7 +522,7 @@ __ping_ipv6()
 
 	# Send 100 packets and verify that at least 100 packets hit the rule,
 	# to overcome neighbor discovery noise.
-	PING_COUNT=100 PING_TIMEOUT=11 ping6_do $dev $dst_ip
+	PING_COUNT=100 PING_TIMEOUT=20 ping6_do $dev $dst_ip
 	check_err $? "Ping failed"
 
 	tc_check_at_least_x_packets "dev $rp1 egress" 101 100
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 4d8c59be1b..7f89623f10 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -69,7 +69,7 @@ __chk_nr()
 		else
 			echo "[ fail ] expected $expected found $nr"
 			mptcp_lib_result_fail "${msg}"
-			ret=$test_cnt
+			ret=${KSFT_FAIL}
 		fi
 	else
 		echo "[  ok  ]"
@@ -115,11 +115,11 @@ wait_msk_nr()
 	if [ $i -ge $timeout ]; then
 		echo "[ fail ] timeout while expecting $expected max $max last $nr"
 		mptcp_lib_result_fail "${msg} # timeout"
-		ret=$test_cnt
+		ret=${KSFT_FAIL}
 	elif [ $nr != $expected ]; then
 		echo "[ fail ] expected $expected found $nr"
 		mptcp_lib_result_fail "${msg} # unexpected result"
-		ret=$test_cnt
+		ret=${KSFT_FAIL}
 	else
 		echo "[  ok  ]"
 		mptcp_lib_result_pass "${msg}"
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 9096bf5794..25693b37f8 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -302,12 +302,12 @@ done
 
 setup
 run_test 10 10 0 0 "balanced bwidth"
-run_test 10 10 1 50 "balanced bwidth with unbalanced delay"
+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 30 10 0 0 "unbalanced bwidth"
-run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay"
-run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay"
+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"
 
 mptcp_lib_result_print_all_tap
 exit $ret
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index f8499d4c87..36e40256ab 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -502,9 +502,22 @@ test_netlink_checks () {
 	    wc -l) == 2 ] || \
 	      return 1
 
+	info "Checking clone depth"
 	ERR_MSG="Flow actions may not be safe on all matching packets"
 	PRE_TEST=$(dmesg | grep -c "${ERR_MSG}")
 	ovs_add_flow "test_netlink_checks" nv0 \
+		'in_port(1),eth(),eth_type(0x800),ipv4()' \
+		'clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(drop)))))))))))))))))' \
+		>/dev/null 2>&1 && return 1
+	POST_TEST=$(dmesg | grep -c "${ERR_MSG}")
+
+	if [ "$PRE_TEST" == "$POST_TEST" ]; then
+		info "failed - clone depth too large"
+		return 1
+	fi
+
+	PRE_TEST=$(dmesg | grep -c "${ERR_MSG}")
+	ovs_add_flow "test_netlink_checks" nv0 \
 		'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(0),2' \
 		&> /dev/null && return 1
 	POST_TEST=$(dmesg | grep -c "${ERR_MSG}")
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index b97e621fac..5e0e539a32 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -299,7 +299,7 @@ class ovsactions(nla):
         ("OVS_ACTION_ATTR_PUSH_NSH", "none"),
         ("OVS_ACTION_ATTR_POP_NSH", "flag"),
         ("OVS_ACTION_ATTR_METER", "none"),
-        ("OVS_ACTION_ATTR_CLONE", "none"),
+        ("OVS_ACTION_ATTR_CLONE", "recursive"),
         ("OVS_ACTION_ATTR_CHECK_PKT_LEN", "none"),
         ("OVS_ACTION_ATTR_ADD_MPLS", "none"),
         ("OVS_ACTION_ATTR_DEC_TTL", "none"),
@@ -465,29 +465,42 @@ class ovsactions(nla):
                     print_str += "pop_mpls"
             else:
                 datum = self.get_attr(field[0])
-                print_str += datum.dpstr(more)
+                if field[0] == "OVS_ACTION_ATTR_CLONE":
+                    print_str += "clone("
+                    print_str += datum.dpstr(more)
+                    print_str += ")"
+                else:
+                    print_str += datum.dpstr(more)
 
         return print_str
 
     def parse(self, actstr):
+        totallen = len(actstr)
         while len(actstr) != 0:
             parsed = False
+            parencount = 0
             if actstr.startswith("drop"):
                 # If no reason is provided, the implicit drop is used (i.e no
                 # action). If some reason is given, an explicit action is used.
-                actstr, reason = parse_extract_field(
-                    actstr,
-                    "drop(",
-                    "([0-9]+)",
-                    lambda x: int(x, 0),
-                    False,
-                    None,
-                )
+                reason = None
+                if actstr.startswith("drop("):
+                    parencount += 1
+
+                    actstr, reason = parse_extract_field(
+                        actstr,
+                        "drop(",
+                        "([0-9]+)",
+                        lambda x: int(x, 0),
+                        False,
+                        None,
+                    )
+
                 if reason is not None:
                     self["attrs"].append(["OVS_ACTION_ATTR_DROP", reason])
                     parsed = True
                 else:
-                    return
+                    actstr = actstr[len("drop"): ]
+                    return (totallen - len(actstr))
 
             elif parse_starts_block(actstr, "^(\d+)", False, True):
                 actstr, output = parse_extract_field(
@@ -504,6 +517,7 @@ class ovsactions(nla):
                     False,
                     0,
                 )
+                parencount += 1
                 self["attrs"].append(["OVS_ACTION_ATTR_RECIRC", recircid])
                 parsed = True
 
@@ -516,12 +530,22 @@ class ovsactions(nla):
 
             for flat_act in parse_flat_map:
                 if parse_starts_block(actstr, flat_act[0], False):
-                    actstr += len(flat_act[0])
+                    actstr = actstr[len(flat_act[0]):]
                     self["attrs"].append([flat_act[1]])
                     actstr = actstr[strspn(actstr, ", ") :]
                     parsed = True
 
-            if parse_starts_block(actstr, "ct(", False):
+            if parse_starts_block(actstr, "clone(", False):
+                parencount += 1
+                subacts = ovsactions()
+                actstr = actstr[len("clone("):]
+                parsedLen = subacts.parse(actstr)
+                lst = []
+                self["attrs"].append(("OVS_ACTION_ATTR_CLONE", subacts))
+                actstr = actstr[parsedLen:]
+                parsed = True
+            elif parse_starts_block(actstr, "ct(", False):
+                parencount += 1
                 actstr = actstr[len("ct(") :]
                 ctact = ovsactions.ctact()
 
@@ -553,6 +577,7 @@ class ovsactions(nla):
                         natact = ovsactions.ctact.natattr()
 
                         if actstr.startswith("("):
+                            parencount += 1
                             t = None
                             actstr = actstr[1:]
                             if actstr.startswith("src"):
@@ -607,15 +632,29 @@ class ovsactions(nla):
                                     actstr = actstr[strspn(actstr, ", ") :]
 
                         ctact["attrs"].append(["OVS_CT_ATTR_NAT", natact])
-                        actstr = actstr[strspn(actstr, ",) ") :]
+                        actstr = actstr[strspn(actstr, ", ") :]
 
                 self["attrs"].append(["OVS_ACTION_ATTR_CT", ctact])
                 parsed = True
 
-            actstr = actstr[strspn(actstr, "), ") :]
+            actstr = actstr[strspn(actstr, ", ") :]
+            while parencount > 0:
+                parencount -= 1
+                actstr = actstr[strspn(actstr, " "):]
+                if len(actstr) and actstr[0] != ")":
+                    raise ValueError("Action str: '%s' unbalanced" % actstr)
+                actstr = actstr[1:]
+
+            if len(actstr) and actstr[0] == ")":
+                return (totallen - len(actstr))
+
+            actstr = actstr[strspn(actstr, ", ") :]
+
             if not parsed:
                 raise ValueError("Action str: '%s' not supported" % actstr)
 
+        return (totallen - len(actstr))
+
 
 class ovskey(nla):
     nla_flags = NLA_F_NESTED
@@ -2111,6 +2150,8 @@ def main(argv):
     ovsflow = OvsFlow()
     ndb = NDB()
 
+    sys.setrecursionlimit(100000)
+
     if hasattr(args, "showdp"):
         found = False
         for iface in ndb.interfaces:
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 464853a7f9..ad993ab3ac 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -988,12 +988,12 @@ TEST_F(tls, recv_partial)
 
 	memset(recv_mem, 0, sizeof(recv_mem));
 	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
-	EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first),
-		       MSG_WAITALL), -1);
+	EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_first),
+		       MSG_WAITALL), strlen(test_str_first));
 	EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0);
 	memset(recv_mem, 0, sizeof(recv_mem));
-	EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second),
-		       MSG_WAITALL), -1);
+	EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_second),
+		       MSG_WAITALL), strlen(test_str_second));
 	EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)),
 		  0);
 }
diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config
index 2fc36efb16..a7f8e8a956 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config
@@ -3,6 +3,7 @@ CONFIG_ARCH_RV32I=y
 CONFIG_MMU=y
 CONFIG_FPU=y
 CONFIG_SOC_VIRT=y
+CONFIG_RISCV_ISA_FALLBACK=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config
index dc266f3b19..daeb3e5e09 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config
@@ -2,6 +2,7 @@ CONFIG_ARCH_RV64I=y
 CONFIG_MMU=y
 CONFIG_FPU=y
 CONFIG_SOC_VIRT=y
+CONFIG_RISCV_ISA_FALLBACK=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y