Merge tag 'tai-for-tracing' into timers/core

Pull in the NMI safe TAI accessor which was provided for the tracing tree
to prepare for further changes in this area.

40 files changed, 449 insertions, 137 deletions

diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 9afcc6467a09..e09d6908a21d 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -75,6 +75,7 @@
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
 #define ARM_CPU_PART_NEOVERSE_V1	0xD40
 #define ARM_CPU_PART_CORTEX_A78		0xD41
+#define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
 #define ARM_CPU_PART_CORTEX_A710	0xD47
@@ -130,6 +131,7 @@
 #define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
 #define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
 #define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
+#define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 91af2850b505..7678af364793 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -828,8 +828,10 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped)
 			s->map_cnt = %zu;			    \n\
 			s->map_skel_sz = sizeof(*s->maps);	    \n\
 			s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\
-			if (!s->maps)				    \n\
+			if (!s->maps) {				    \n\
+				err = -ENOMEM;			    \n\
 				goto err;			    \n\
+			}					    \n\
 		",
 		map_cnt
 	);
@@ -870,8 +872,10 @@ codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_li
 			s->prog_cnt = %zu;			    \n\
 			s->prog_skel_sz = sizeof(*s->progs);	    \n\
 			s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\
-			if (!s->progs)				    \n\
+			if (!s->progs) {			    \n\
+				err = -ENOMEM;			    \n\
 				goto err;			    \n\
+			}					    \n\
 		",
 		prog_cnt
 	);
@@ -1182,10 +1186,13 @@ static int do_skeleton(int argc, char **argv)
 		%1$s__create_skeleton(struct %1$s *obj)			    \n\
 		{							    \n\
 			struct bpf_object_skeleton *s;			    \n\
+			int err;					    \n\
 									    \n\
 			s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\
-			if (!s)						    \n\
+			if (!s)	{					    \n\
+				err = -ENOMEM;				    \n\
 				goto err;				    \n\
+			}						    \n\
 									    \n\
 			s->sz = sizeof(*s);				    \n\
 			s->name = \"%1$s\";				    \n\
@@ -1206,7 +1213,7 @@ static int do_skeleton(int argc, char **argv)
 			return 0;					    \n\
 		err:							    \n\
 			bpf_object__destroy_skeleton(s);		    \n\
-			return -ENOMEM;					    \n\
+			return err;					    \n\
 		}							    \n\
 									    \n\
 		static inline const void *%2$s__elf_bytes(size_t *sz)	    \n\
@@ -1466,12 +1473,12 @@ static int do_subskeleton(int argc, char **argv)
 									    \n\
 			obj = (struct %1$s *)calloc(1, sizeof(*obj));	    \n\
 			if (!obj) {					    \n\
-				errno = ENOMEM;				    \n\
+				err = -ENOMEM;				    \n\
 				goto err;				    \n\
 			}						    \n\
 			s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\
 			if (!s) {					    \n\
-				errno = ENOMEM;				    \n\
+				err = -ENOMEM;				    \n\
 				goto err;				    \n\
 			}						    \n\
 			s->sz = sizeof(*s);				    \n\
@@ -1483,7 +1490,7 @@ static int do_subskeleton(int argc, char **argv)
 			s->var_cnt = %2$d;				    \n\
 			s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\
 			if (!s->vars) {					    \n\
-				errno = ENOMEM;				    \n\
+				err = -ENOMEM;				    \n\
 				goto err;				    \n\
 			}						    \n\
 		",
@@ -1538,6 +1545,7 @@ static int do_subskeleton(int argc, char **argv)
 			return obj;					    \n\
 		err:							    \n\
 			%1$s__destroy(obj);				    \n\
+			errno = -err;					    \n\
 			return NULL;					    \n\
 		}							    \n\
 									    \n\
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 1480910c792e..de66e1cc0734 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -217,9 +217,16 @@ strip-libs = $(filter-out -l%,$(1))
 PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
 PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
 PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
-PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
 FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
+ifeq ($(CC_NO_CLANG), 0)
+  PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
+  PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS))
+  PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+  FLAGS_PERL_EMBED += -Wno-compound-token-split-by-macro
+endif
+
 $(OUTPUT)test-libperl.bin:
 	$(BUILD) $(FLAGS_PERL_EMBED)
 
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index c998860d7bbc..5d99e7c242a2 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -150,4 +150,11 @@
 /* Get the valid iova range */
 #define VHOST_VDPA_GET_IOVA_RANGE	_IOR(VHOST_VIRTIO, 0x78, \
 					     struct vhost_vdpa_iova_range)
+
+/* Get the config size */
+#define VHOST_VDPA_GET_CONFIG_SIZE	_IOR(VHOST_VIRTIO, 0x79, __u32)
+
+/* Get the count of all virtqueues */
+#define VHOST_VDPA_GET_VQS_COUNT	_IOR(VHOST_VIRTIO, 0x80, __u32)
+
 #endif
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 6de5085e3e5a..bd0c2c828940 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1155,6 +1155,17 @@ static void annotate_call_site(struct objtool_file *file,
 			               : arch_nop_insn(insn->len));
 
 		insn->type = sibling ? INSN_RETURN : INSN_NOP;
+
+		if (sibling) {
+			/*
+			 * We've replaced the tail-call JMP insn by two new
+			 * insn: RET; INT3, except we only have a single struct
+			 * insn here. Mark it retpoline_safe to avoid the SLS
+			 * warning, instead of adding another insn.
+			 */
+			insn->retpoline_safe = true;
+		}
+
 		return;
 	}
 
@@ -1239,11 +1250,20 @@ static bool same_function(struct instruction *insn1, struct instruction *insn2)
 	return insn1->func->pfunc == insn2->func->pfunc;
 }
 
-static bool is_first_func_insn(struct instruction *insn)
+static bool is_first_func_insn(struct objtool_file *file, struct instruction *insn)
 {
-	return insn->offset == insn->func->offset ||
-	       (insn->type == INSN_ENDBR &&
-		insn->offset == insn->func->offset + insn->len);
+	if (insn->offset == insn->func->offset)
+		return true;
+
+	if (ibt) {
+		struct instruction *prev = prev_insn_same_sym(file, insn);
+
+		if (prev && prev->type == INSN_ENDBR &&
+		    insn->offset == insn->func->offset + prev->len)
+			return true;
+	}
+
+	return false;
 }
 
 /*
@@ -1327,7 +1347,7 @@ static int add_jump_destinations(struct objtool_file *file)
 				insn->jump_dest->func->pfunc = insn->func;
 
 			} else if (!same_function(insn, insn->jump_dest) &&
-				   is_first_func_insn(insn->jump_dest)) {
+				   is_first_func_insn(file, insn->jump_dest)) {
 				/* internal sibling call (without reloc) */
 				add_call_dest(file, insn, insn->jump_dest->func, true);
 			}
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index 9c330cdfa973..71ebdf8125de 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -83,7 +83,7 @@ linkperf:perf-buildid-list[1], linkperf:perf-c2c[1],
 linkperf:perf-config[1], linkperf:perf-data[1], linkperf:perf-diff[1],
 linkperf:perf-evlist[1], linkperf:perf-ftrace[1],
 linkperf:perf-help[1], linkperf:perf-inject[1],
-linkperf:perf-intel-pt[1], linkperf:perf-kallsyms[1],
+linkperf:perf-intel-pt[1], linkperf:perf-iostat[1], linkperf:perf-kallsyms[1],
 linkperf:perf-kmem[1], linkperf:perf-kvm[1], linkperf:perf-lock[1],
 linkperf:perf-mem[1], linkperf:perf-probe[1], linkperf:perf-sched[1],
 linkperf:perf-script[1], linkperf:perf-test[1],
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 96ad944ca6a8..f3bf9297bcc0 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
   PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
+  ifeq ($(CC_NO_CLANG), 0)
+    PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS))
+  endif
 endif
 
 FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
@@ -790,6 +793,9 @@ else
     LDFLAGS += $(PERL_EMBED_LDFLAGS)
     EXTLIBS += $(PERL_EMBED_LIBADD)
     CFLAGS += -DHAVE_LIBPERL_SUPPORT
+    ifeq ($(CC_NO_CLANG), 0)
+      CFLAGS += -Wno-compound-token-split-by-macro
+    endif
     $(call detected,CONFIG_LIBPERL)
   endif
 endif
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 86e2e926aa0e..af4d63af8072 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -239,6 +239,12 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 		arm_spe_set_timestamp(itr, arm_spe_evsel);
 	}
 
+	/*
+	 * Set this only so that perf report knows that SPE generates memory info. It has no effect
+	 * on the opening of the event or the SPE data produced.
+	 */
+	evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
+
 	/* Add dummy event to keep tracking */
 	err = parse_events(evlist, "dummy:u", NULL);
 	if (err)
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index 134612bde0cb..4256dc5d6236 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -222,13 +222,20 @@ static void init_fdmaps(struct worker *w, int pct)
 static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 {
 	pthread_attr_t thread_attr, *attrp = NULL;
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i, j;
 	int ret = 0;
+	int nrcpus;
+	size_t size;
 
 	if (!noaffinity)
 		pthread_attr_init(&thread_attr);
 
+	nrcpus = perf_cpu_map__nr(cpu);
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	for (i = 0; i < nthreads; i++) {
 		struct worker *w = &worker[i];
 
@@ -252,22 +259,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 			init_fdmaps(w, 50);
 
 		if (!noaffinity) {
-			CPU_ZERO(&cpuset);
-			CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+			CPU_ZERO_S(size, cpuset);
+			CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu,
+					size, cpuset);
 
-			ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
-			if (ret)
+			ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset);
+			if (ret) {
+				CPU_FREE(cpuset);
 				err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+			}
 
 			attrp = &thread_attr;
 		}
 
 		ret = pthread_create(&w->thread, attrp, workerfn,
 				     (void *)(struct worker *) w);
-		if (ret)
+		if (ret) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
 
+	CPU_FREE(cpuset);
 	if (!noaffinity)
 		pthread_attr_destroy(&thread_attr);
 
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index 37de970c9743..2728b0140853 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -291,9 +291,11 @@ static void print_summary(void)
 static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 {
 	pthread_attr_t thread_attr, *attrp = NULL;
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i, j;
 	int ret = 0, events = EPOLLIN;
+	int nrcpus;
+	size_t size;
 
 	if (oneshot)
 		events |= EPOLLONESHOT;
@@ -306,6 +308,11 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 	if (!noaffinity)
 		pthread_attr_init(&thread_attr);
 
+	nrcpus = perf_cpu_map__nr(cpu);
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	for (i = 0; i < nthreads; i++) {
 		struct worker *w = &worker[i];
 
@@ -341,22 +348,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 		}
 
 		if (!noaffinity) {
-			CPU_ZERO(&cpuset);
-			CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+			CPU_ZERO_S(size, cpuset);
+			CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu,
+					size, cpuset);
 
-			ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
-			if (ret)
+			ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset);
+			if (ret) {
+				CPU_FREE(cpuset);
 				err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+			}
 
 			attrp = &thread_attr;
 		}
 
 		ret = pthread_create(&w->thread, attrp, workerfn,
 				     (void *)(struct worker *) w);
-		if (ret)
+		if (ret) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
 
+	CPU_FREE(cpuset);
 	if (!noaffinity)
 		pthread_attr_destroy(&thread_attr);
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index dbcecec4eeda..f05db4cf983d 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -122,12 +122,14 @@ static void print_summary(void)
 int bench_futex_hash(int argc, const char **argv)
 {
 	int ret = 0;
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	struct sigaction act;
 	unsigned int i;
 	pthread_attr_t thread_attr;
 	struct worker *worker = NULL;
 	struct perf_cpu_map *cpu;
+	int nrcpus;
+	size_t size;
 
 	argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
 	if (argc) {
@@ -170,25 +172,35 @@ int bench_futex_hash(int argc, const char **argv)
 	threads_starting = params.nthreads;
 	pthread_attr_init(&thread_attr);
 	gettimeofday(&bench__start, NULL);
+
+	nrcpus = perf_cpu_map__nr(cpu);
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	for (i = 0; i < params.nthreads; i++) {
 		worker[i].tid = i;
 		worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex));
 		if (!worker[i].futex)
 			goto errmem;
 
-		CPU_ZERO(&cpuset);
-		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+		CPU_ZERO_S(size, cpuset);
 
-		ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
-		if (ret)
+		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
+		ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset);
+		if (ret) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
-
+		}
 		ret = pthread_create(&worker[i].thread, &thread_attr, workerfn,
 				     (void *)(struct worker *) &worker[i]);
-		if (ret)
+		if (ret) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 
 	}
+	CPU_FREE(cpuset);
 	pthread_attr_destroy(&thread_attr);
 
 	pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 6fc9a3d55c1f..0abb3f7ee24f 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -120,11 +120,17 @@ static void *workerfn(void *arg)
 static void create_threads(struct worker *w, pthread_attr_t thread_attr,
 			   struct perf_cpu_map *cpu)
 {
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i;
+	int nrcpus =  perf_cpu_map__nr(cpu);
+	size_t size;
 
 	threads_starting = params.nthreads;
 
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	for (i = 0; i < params.nthreads; i++) {
 		worker[i].tid = i;
 
@@ -135,15 +141,20 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr,
 		} else
 			worker[i].futex = &global_futex;
 
-		CPU_ZERO(&cpuset);
-		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+		CPU_ZERO_S(size, cpuset);
+		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+		if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+		}
 
-		if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i]))
+		if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
+	CPU_FREE(cpuset);
 }
 
 int bench_futex_lock_pi(int argc, const char **argv)
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 2f59d5d1c509..b6faabfafb8e 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -123,22 +123,33 @@ static void *workerfn(void *arg __maybe_unused)
 static void block_threads(pthread_t *w,
 			  pthread_attr_t thread_attr, struct perf_cpu_map *cpu)
 {
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i;
+	int nrcpus = perf_cpu_map__nr(cpu);
+	size_t size;
 
 	threads_starting = params.nthreads;
 
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	/* create and block all threads */
 	for (i = 0; i < params.nthreads; i++) {
-		CPU_ZERO(&cpuset);
-		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+		CPU_ZERO_S(size, cpuset);
+		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+		if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+		}
 
-		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+		if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
+	CPU_FREE(cpuset);
 }
 
 static void toggle_done(int sig __maybe_unused,
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 861deb934745..e47f46a3a47e 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -144,22 +144,33 @@ static void *blocked_workerfn(void *arg __maybe_unused)
 static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
 			  struct perf_cpu_map *cpu)
 {
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i;
+	int nrcpus = perf_cpu_map__nr(cpu);
+	size_t size;
 
 	threads_starting = params.nthreads;
 
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	/* create and block all threads */
 	for (i = 0; i < params.nthreads; i++) {
-		CPU_ZERO(&cpuset);
-		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+		CPU_ZERO_S(size, cpuset);
+		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+		if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+		}
 
-		if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
+		if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
+	CPU_FREE(cpuset);
 }
 
 static void print_run(struct thread_data *waking_worker, unsigned int run_num)
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index cfda48bef1d7..201a3555f09a 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -97,22 +97,32 @@ static void print_summary(void)
 static void block_threads(pthread_t *w,
 			  pthread_attr_t thread_attr, struct perf_cpu_map *cpu)
 {
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i;
-
+	size_t size;
+	int nrcpus = perf_cpu_map__nr(cpu);
 	threads_starting = params.nthreads;
 
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	/* create and block all threads */
 	for (i = 0; i < params.nthreads; i++) {
-		CPU_ZERO(&cpuset);
-		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+		CPU_ZERO_S(size, cpuset);
+		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+		if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+		}
 
-		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+		if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
+	CPU_FREE(cpuset);
 }
 
 static void toggle_done(int sig __maybe_unused,
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 2f6b67189b42..0170cb0819d6 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -55,6 +55,7 @@ struct cmd_struct {
 };
 
 static struct cmd_struct commands[] = {
+	{ "archive",	NULL,	0 },
 	{ "buildid-cache", cmd_buildid_cache, 0 },
 	{ "buildid-list", cmd_buildid_list, 0 },
 	{ "config",	cmd_config,	0 },
@@ -62,6 +63,7 @@ static struct cmd_struct commands[] = {
 	{ "diff",	cmd_diff,	0 },
 	{ "evlist",	cmd_evlist,	0 },
 	{ "help",	cmd_help,	0 },
+	{ "iostat",	NULL,	0 },
 	{ "kallsyms",	cmd_kallsyms,	0 },
 	{ "list",	cmd_list,	0 },
 	{ "record",	cmd_record,	0 },
@@ -360,6 +362,8 @@ static void handle_internal_command(int argc, const char **argv)
 
 	for (i = 0; i < ARRAY_SIZE(commands); i++) {
 		struct cmd_struct *p = commands+i;
+		if (p->fn == NULL)
+			continue;
 		if (strcmp(p->cmd, cmd))
 			continue;
 		exit(run_builtin(p, argc, argv));
@@ -434,7 +438,7 @@ void pthread__unblock_sigwinch(void)
 static int libperf_print(enum libperf_print_level level,
 			 const char *fmt, va_list ap)
 {
-	return eprintf(level, verbose, fmt, ap);
+	return veprintf(level, verbose, fmt, ap);
 }
 
 int main(int argc, const char **argv)
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 2dab2d262060..afdca7f2959f 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr
 	}
 
 	err = unwind__get_entries(unwind_entry, &cnt, thread,
-				  &sample, MAX_STACK);
+				  &sample, MAX_STACK, false);
 	if (err)
 		pr_debug("unwind failed\n");
 	else if (cnt != MAX_STACK) {
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index d12d0ad81801..cc6df49a65a1 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -47,6 +47,17 @@
 	}					\
 }
 
+static int test__tsc_is_supported(struct test_suite *test __maybe_unused,
+				  int subtest __maybe_unused)
+{
+	if (!TSC_IS_SUPPORTED) {
+		pr_debug("Test not supported on this architecture\n");
+		return TEST_SKIP;
+	}
+
+	return TEST_OK;
+}
+
 /**
  * test__perf_time_to_tsc - test converting perf time to TSC.
  *
@@ -70,7 +81,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 	struct perf_cpu_map *cpus = NULL;
 	struct evlist *evlist = NULL;
 	struct evsel *evsel = NULL;
-	int err = -1, ret, i;
+	int err = TEST_FAIL, ret, i;
 	const char *comm1, *comm2;
 	struct perf_tsc_conversion tc;
 	struct perf_event_mmap_page *pc;
@@ -79,10 +90,6 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 	u64 test_time, comm1_time = 0, comm2_time = 0;
 	struct mmap *md;
 
-	if (!TSC_IS_SUPPORTED) {
-		pr_debug("Test not supported on this architecture");
-		return TEST_SKIP;
-	}
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
@@ -124,8 +131,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 	ret = perf_read_tsc_conversion(pc, &tc);
 	if (ret) {
 		if (ret == -EOPNOTSUPP) {
-			fprintf(stderr, " (not supported)");
-			return 0;
+			pr_debug("perf_read_tsc_conversion is not supported in current kernel\n");
+			err = TEST_SKIP;
 		}
 		goto out_err;
 	}
@@ -191,7 +198,7 @@ next_event:
 	    test_tsc >= comm2_tsc)
 		goto out_err;
 
-	err = 0;
+	err = TEST_OK;
 
 out_err:
 	evlist__delete(evlist);
@@ -200,4 +207,15 @@ out_err:
 	return err;
 }
 
-DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc);
+static struct test_case time_to_tsc_tests[] = {
+	TEST_CASE_REASON("TSC support", tsc_is_supported,
+			 "This architecture does not support"),
+	TEST_CASE_REASON("Perf time to TSC", perf_time_to_tsc,
+			 "perf_read_tsc_conversion is not supported"),
+	{ .name = NULL, }
+};
+
+struct test_suite suite__perf_time_to_tsc = {
+	.desc = "Convert perf time to TSC",
+	.test_cases = time_to_tsc_tests,
+};
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e4c641b240df..82cc396ef516 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2047,6 +2047,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	objdump_process.argv = objdump_argv;
 	objdump_process.out = -1;
 	objdump_process.err = -1;
+	objdump_process.no_stderr = 1;
 	if (start_command(&objdump_process)) {
 		pr_err("Failure starting to run %s\n", command);
 		err = -1;
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c
index 2242a885fbd7..4940be4a0569 100644
--- a/tools/perf/util/arm64-frame-pointer-unwind-support.c
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c
@@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr
 		sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
 	}
 
-	ret = unwind__get_entries(add_entry, &entries, thread, sample, 2);
+	ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true);
 	sample->user_regs = old_regs;
 
 	if (ret || entries.length != 2)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b80048546451..95391236f5f6 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2987,7 +2987,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread,
 		return 0;
 
 	return unwind__get_entries(unwind_entry, cursor,
-				   thread, sample, max_stack);
+				   thread, sample, max_stack, false);
 }
 
 int thread__resolve_callchain(struct thread *thread,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 3b8dfe603e50..45a30040ec8d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2095,6 +2095,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size,
 	       bool needs_swap, union perf_event *error)
 {
 	union perf_event *event;
+	u16 event_size;
 
 	/*
 	 * Ensure we have enough space remaining to read
@@ -2107,15 +2108,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size,
 	if (needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	if (head + event->header.size <= mmap_size)
+	event_size = event->header.size;
+	if (head + event_size <= mmap_size)
 		return event;
 
 	/* We're not fetching the event so swap back again */
 	if (needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:"
-		 " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size);
+	/* Check if the event fits into the next mmapped buf. */
+	if (event_size <= mmap_size - head % page_size) {
+		/* Remap buf and fetch again. */
+		return NULL;
+	}
+
+	/* Invalid input. Event size should never exceed mmap_size. */
+	pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:"
+		 " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size);
 
 	return error;
 }
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 483f05004e68..c255a2c90cd6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,12 +1,14 @@
-from os import getenv
+from os import getenv, path
 from subprocess import Popen, PIPE
 from re import sub
 
 cc = getenv("CC")
 cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline()
+src_feature_tests  = getenv('srctree') + '/tools/build/feature'
 
 def clang_has_option(option):
-    return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
+    cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines()
+    return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ]
 
 if cc_is_clang:
     from distutils.sysconfig import get_config_vars
@@ -23,6 +25,8 @@ if cc_is_clang:
             vars[var] = sub("-fstack-protector-strong", "", vars[var])
         if not clang_has_option("-fno-semantic-interposition"):
             vars[var] = sub("-fno-semantic-interposition", "", vars[var])
+        if not clang_has_option("-ffat-lto-objects"):
+            vars[var] = sub("-ffat-lto-objects", "", vars[var])
 
 from distutils.core import setup, Extension
 
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index a74b517f7497..94aa40f6e348 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
 	bool isactivation;
 
 	if (!dwfl_frame_pc(state, &pc, NULL)) {
-		pr_err("%s", dwfl_errmsg(-1));
+		if (!ui->best_effort)
+			pr_err("%s", dwfl_errmsg(-1));
 		return DWARF_CB_ABORT;
 	}
 
@@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
 	report_module(pc, ui);
 
 	if (!dwfl_frame_pc(state, &pc, &isactivation)) {
-		pr_err("%s", dwfl_errmsg(-1));
+		if (!ui->best_effort)
+			pr_err("%s", dwfl_errmsg(-1));
 		return DWARF_CB_ABORT;
 	}
 
@@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
 			struct perf_sample *data,
-			int max_stack)
+			int max_stack,
+			bool best_effort)
 {
 	struct unwind_info *ui, ui_buf = {
 		.sample		= data,
@@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 		.cb		= cb,
 		.arg		= arg,
 		.max_stack	= max_stack,
+		.best_effort    = best_effort
 	};
 	Dwarf_Word ip;
 	int err = -EINVAL, i;
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 0cbd2650e280..8c88bc4f2304 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -20,6 +20,7 @@ struct unwind_info {
 	void			*arg;
 	int			max_stack;
 	int			idx;
+	bool			best_effort;
 	struct unwind_entry	entries[];
 };
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 71a353349181..41e29fc7648a 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -96,6 +96,7 @@ struct unwind_info {
 	struct perf_sample	*sample;
 	struct machine		*machine;
 	struct thread		*thread;
+	bool			 best_effort;
 };
 
 #define dw_read(ptr, type, end) ({	\
@@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as,
 
 	ret = perf_reg_value(&val, &ui->sample->user_regs, id);
 	if (ret) {
-		pr_err("unwind: can't read reg %d\n", regnum);
+		if (!ui->best_effort)
+			pr_err("unwind: can't read reg %d\n", regnum);
 		return ret;
 	}
 
@@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 			return -1;
 
 		ret = unw_init_remote(&c, addr_space, ui);
-		if (ret)
+		if (ret && !ui->best_effort)
 			display_error(ret);
 
 		while (!ret && (unw_step(&c) > 0) && i < max_stack) {
@@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 
 static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
-			struct perf_sample *data, int max_stack)
+			struct perf_sample *data, int max_stack,
+			bool best_effort)
 {
 	struct unwind_info ui = {
 		.sample       = data,
 		.thread       = thread,
 		.machine      = thread->maps->machine,
+		.best_effort  = best_effort
 	};
 
 	if (!data->user_regs.regs)
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index e89a5479b361..509c287ee762 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps)
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			 struct thread *thread,
-			 struct perf_sample *data, int max_stack)
+			 struct perf_sample *data, int max_stack,
+			 bool best_effort)
 {
 	if (thread->maps->unwind_libunwind_ops)
-		return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack);
+		return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data,
+								       max_stack, best_effort);
 	return 0;
 }
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index ab8ad469c8de..b2a03fa5289b 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -23,13 +23,19 @@ struct unwind_libunwind_ops {
 	void (*finish_access)(struct maps *maps);
 	int (*get_entries)(unwind_entry_cb_t cb, void *arg,
 			   struct thread *thread,
-			   struct perf_sample *data, int max_stack);
+			   struct perf_sample *data, int max_stack, bool best_effort);
 };
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
+/*
+ * When best_effort is set, don't report errors and fail silently. This could
+ * be expanded in the future to be more permissive about things other than
+ * error messages.
+ */
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
-			struct perf_sample *data, int max_stack);
+			struct perf_sample *data, int max_stack,
+			bool best_effort);
 /* libunwind specific */
 #ifdef HAVE_LIBUNWIND_SUPPORT
 #ifndef LIBUNWIND__ARCH_REG_ID
@@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 		    void *arg __maybe_unused,
 		    struct thread *thread __maybe_unused,
 		    struct perf_sample *data __maybe_unused,
-		    int max_stack __maybe_unused)
+		    int max_stack __maybe_unused,
+		    bool best_effort __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 65dbdda3a054..1da76ccde448 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -1842,7 +1842,7 @@ static int nfit_test_dimm_init(struct nfit_test *t)
 	return 0;
 }
 
-static void security_init(struct nfit_test *t)
+static void nfit_security_init(struct nfit_test *t)
 {
 	int i;
 
@@ -1938,7 +1938,7 @@ static int nfit_test0_alloc(struct nfit_test *t)
 	if (nfit_test_dimm_init(t))
 		return -ENOMEM;
 	smart_init(t);
-	security_init(t);
+	nfit_security_init(t);
 	return ars_state_init(&t->pdev.dev, &t->ars_state);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
index 5aa52cc31dc2..c11832657d2b 100644
--- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
+++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2021. Huawei Technologies Co., Ltd */
 #include <test_progs.h>
 #include "dummy_st_ops.skel.h"
+#include "trace_dummy_st_ops.skel.h"
 
 /* Need to keep consistent with definition in include/linux/bpf.h */
 struct bpf_dummy_ops_state {
@@ -56,6 +57,7 @@ static void test_dummy_init_ptr_arg(void)
 		.ctx_in = args,
 		.ctx_size_in = sizeof(args),
 	);
+	struct trace_dummy_st_ops *trace_skel;
 	struct dummy_st_ops *skel;
 	int fd, err;
 
@@ -64,12 +66,33 @@ static void test_dummy_init_ptr_arg(void)
 		return;
 
 	fd = bpf_program__fd(skel->progs.test_1);
+
+	trace_skel = trace_dummy_st_ops__open();
+	if (!ASSERT_OK_PTR(trace_skel, "trace_dummy_st_ops__open"))
+		goto done;
+
+	err = bpf_program__set_attach_target(trace_skel->progs.fentry_test_1,
+					     fd, "test_1");
+	if (!ASSERT_OK(err, "set_attach_target(fentry_test_1)"))
+		goto done;
+
+	err = trace_dummy_st_ops__load(trace_skel);
+	if (!ASSERT_OK(err, "load(trace_skel)"))
+		goto done;
+
+	err = trace_dummy_st_ops__attach(trace_skel);
+	if (!ASSERT_OK(err, "attach(trace_skel)"))
+		goto done;
+
 	err = bpf_prog_test_run_opts(fd, &attr);
 	ASSERT_OK(err, "test_run");
 	ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret");
 	ASSERT_EQ(attr.retval, exp_retval, "test_ret");
+	ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val");
 
+done:
 	dummy_st_ops__destroy(skel);
+	trace_dummy_st_ops__destroy(trace_skel);
 }
 
 static void test_dummy_multiple_args(void)
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index b64df94ec476..db388f593d0a 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -367,7 +367,7 @@ static inline int check_array_of_maps(void)
 
 	VERIFY(check_default(&array_of_maps->map, map));
 	inner_map = bpf_map_lookup_elem(array_of_maps, &key);
-	VERIFY(inner_map != 0);
+	VERIFY(inner_map != NULL);
 	VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES);
 
 	return 1;
@@ -394,7 +394,7 @@ static inline int check_hash_of_maps(void)
 
 	VERIFY(check_default(&hash_of_maps->map, map));
 	inner_map = bpf_map_lookup_elem(hash_of_maps, &key);
-	VERIFY(inner_map != 0);
+	VERIFY(inner_map != NULL);
 	VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES);
 
 	return 1;
diff --git a/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c
new file mode 100644
index 000000000000..00a4be9d3074
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int val = 0;
+
+SEC("fentry/test_1")
+int BPF_PROG(fentry_test_1, __u64 *st_ops_ctx)
+{
+	__u64 state;
+
+	/* Read the traced st_ops arg1 which is a pointer */
+	bpf_probe_read_kernel(&state, sizeof(__u64), (void *)st_ops_ctx);
+	/* Read state->val */
+	bpf_probe_read_kernel(&val, sizeof(__u32), (void *)state);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
index b9e991d43155..e7775d3bbe08 100644
--- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
+++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
@@ -18,8 +18,9 @@
 #include "bpf_rlimit.h"
 #include "cgroup_helpers.h"
 
-static int start_server(const struct sockaddr *addr, socklen_t len)
+static int start_server(const struct sockaddr *addr, socklen_t len, bool dual)
 {
+	int mode = !dual;
 	int fd;
 
 	fd = socket(addr->sa_family, SOCK_STREAM, 0);
@@ -28,6 +29,14 @@ static int start_server(const struct sockaddr *addr, socklen_t len)
 		goto out;
 	}
 
+	if (addr->sa_family == AF_INET6) {
+		if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *)&mode,
+			       sizeof(mode)) == -1) {
+			log_err("Failed to set the dual-stack mode");
+			goto close_out;
+		}
+	}
+
 	if (bind(fd, addr, len) == -1) {
 		log_err("Failed to bind server socket");
 		goto close_out;
@@ -47,24 +56,17 @@ out:
 	return fd;
 }
 
-static int connect_to_server(int server_fd)
+static int connect_to_server(const struct sockaddr *addr, socklen_t len)
 {
-	struct sockaddr_storage addr;
-	socklen_t len = sizeof(addr);
 	int fd = -1;
 
-	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
-		log_err("Failed to get server addr");
-		goto out;
-	}
-
-	fd = socket(addr.ss_family, SOCK_STREAM, 0);
+	fd = socket(addr->sa_family, SOCK_STREAM, 0);
 	if (fd == -1) {
 		log_err("Failed to create client socket");
 		goto out;
 	}
 
-	if (connect(fd, (const struct sockaddr *)&addr, len) == -1) {
+	if (connect(fd, (const struct sockaddr *)addr, len) == -1) {
 		log_err("Fail to connect to server");
 		goto close_out;
 	}
@@ -116,7 +118,8 @@ err:
 	return map_fd;
 }
 
-static int run_test(int server_fd, int results_fd, bool xdp)
+static int run_test(int server_fd, int results_fd, bool xdp,
+		    const struct sockaddr *addr, socklen_t len)
 {
 	int client = -1, srv_client = -1;
 	int ret = 0;
@@ -142,7 +145,7 @@ static int run_test(int server_fd, int results_fd, bool xdp)
 		goto err;
 	}
 
-	client = connect_to_server(server_fd);
+	client = connect_to_server(addr, len);
 	if (client == -1)
 		goto err;
 
@@ -199,12 +202,30 @@ out:
 	return ret;
 }
 
+static bool get_port(int server_fd, in_port_t *port)
+{
+	struct sockaddr_in addr;
+	socklen_t len = sizeof(addr);
+
+	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
+		log_err("Failed to get server addr");
+		return false;
+	}
+
+	/* sin_port and sin6_port are located at the same offset. */
+	*port = addr.sin_port;
+	return true;
+}
+
 int main(int argc, char **argv)
 {
 	struct sockaddr_in addr4;
 	struct sockaddr_in6 addr6;
+	struct sockaddr_in addr4dual;
+	struct sockaddr_in6 addr6dual;
 	int server = -1;
 	int server_v6 = -1;
+	int server_dual = -1;
 	int results = -1;
 	int err = 0;
 	bool xdp;
@@ -224,25 +245,43 @@ int main(int argc, char **argv)
 	addr4.sin_family = AF_INET;
 	addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
 	addr4.sin_port = 0;
+	memcpy(&addr4dual, &addr4, sizeof(addr4dual));
 
 	memset(&addr6, 0, sizeof(addr6));
 	addr6.sin6_family = AF_INET6;
 	addr6.sin6_addr = in6addr_loopback;
 	addr6.sin6_port = 0;
 
-	server = start_server((const struct sockaddr *)&addr4, sizeof(addr4));
-	if (server == -1)
+	memset(&addr6dual, 0, sizeof(addr6dual));
+	addr6dual.sin6_family = AF_INET6;
+	addr6dual.sin6_addr = in6addr_any;
+	addr6dual.sin6_port = 0;
+
+	server = start_server((const struct sockaddr *)&addr4, sizeof(addr4),
+			      false);
+	if (server == -1 || !get_port(server, &addr4.sin_port))
 		goto err;
 
 	server_v6 = start_server((const struct sockaddr *)&addr6,
-				 sizeof(addr6));
-	if (server_v6 == -1)
+				 sizeof(addr6), false);
+	if (server_v6 == -1 || !get_port(server_v6, &addr6.sin6_port))
+		goto err;
+
+	server_dual = start_server((const struct sockaddr *)&addr6dual,
+				   sizeof(addr6dual), true);
+	if (server_dual == -1 || !get_port(server_dual, &addr4dual.sin_port))
+		goto err;
+
+	if (run_test(server, results, xdp,
+		     (const struct sockaddr *)&addr4, sizeof(addr4)))
 		goto err;
 
-	if (run_test(server, results, xdp))
+	if (run_test(server_v6, results, xdp,
+		     (const struct sockaddr *)&addr6, sizeof(addr6)))
 		goto err;
 
-	if (run_test(server_v6, results, xdp))
+	if (run_test(server_dual, results, xdp,
+		     (const struct sockaddr *)&addr4dual, sizeof(addr4dual)))
 		goto err;
 
 	printf("ok\n");
@@ -252,6 +291,7 @@ err:
 out:
 	close(server);
 	close(server_v6);
+	close(server_dual);
 	close(results);
 	return err;
 }
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 11779405dc80..25f4d54067c0 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -64,6 +64,7 @@
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <unistd.h>
+#include <setjmp.h>
 
 #include "kselftest.h"
 
@@ -183,7 +184,10 @@
 		struct __test_metadata *_metadata, \
 		struct __fixture_variant_metadata *variant) \
 	{ \
-		test_name(_metadata); \
+		_metadata->setup_completed = true; \
+		if (setjmp(_metadata->env) == 0) \
+			test_name(_metadata); \
+		__test_check_assert(_metadata); \
 	} \
 	static struct __test_metadata _##test_name##_object = \
 		{ .name = #test_name, \
@@ -287,7 +291,9 @@
 #define FIXTURE_TEARDOWN(fixture_name) \
 	void fixture_name##_teardown( \
 		struct __test_metadata __attribute__((unused)) *_metadata, \
-		FIXTURE_DATA(fixture_name) __attribute__((unused)) *self)
+		FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \
+		const FIXTURE_VARIANT(fixture_name) \
+			__attribute__((unused)) *variant)
 
 /**
  * FIXTURE_VARIANT() - Optionally called once per fixture
@@ -302,9 +308,9 @@
  *       ...
  *     };
  *
- * Defines type of constant parameters provided to FIXTURE_SETUP() and TEST_F()
- * as *variant*. Variants allow the same tests to be run with different
- * arguments.
+ * Defines type of constant parameters provided to FIXTURE_SETUP(), TEST_F() and
+ * FIXTURE_TEARDOWN as *variant*. Variants allow the same tests to be run with
+ * different arguments.
  */
 #define FIXTURE_VARIANT(fixture_name) struct _fixture_variant_##fixture_name
 
@@ -356,10 +362,7 @@
  * Defines a test that depends on a fixture (e.g., is part of a test case).
  * Very similar to TEST() except that *self* is the setup instance of fixture's
  * datatype exposed for use by the implementation.
- *
- * Warning: use of ASSERT_* here will skip TEARDOWN.
  */
-/* TODO(wad) register fixtures on dedicated test lists. */
 #define TEST_F(fixture_name, test_name) \
 	__TEST_F_IMPL(fixture_name, test_name, -1, TEST_TIMEOUT_DEFAULT)
 
@@ -381,12 +384,17 @@
 		/* fixture data is alloced, setup, and torn down per call. */ \
 		FIXTURE_DATA(fixture_name) self; \
 		memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \
-		fixture_name##_setup(_metadata, &self, variant->data); \
-		/* Let setup failure terminate early. */ \
-		if (!_metadata->passed) \
-			return; \
-		fixture_name##_##test_name(_metadata, &self, variant->data); \
-		fixture_name##_teardown(_metadata, &self); \
+		if (setjmp(_metadata->env) == 0) { \
+			fixture_name##_setup(_metadata, &self, variant->data); \
+			/* Let setup failure terminate early. */ \
+			if (!_metadata->passed) \
+				return; \
+			_metadata->setup_completed = true; \
+			fixture_name##_##test_name(_metadata, &self, variant->data); \
+		} \
+		if (_metadata->setup_completed) \
+			fixture_name##_teardown(_metadata, &self, variant->data); \
+		__test_check_assert(_metadata); \
 	} \
 	static struct __test_metadata \
 		      _##fixture_name##_##test_name##_object = { \
@@ -683,7 +691,7 @@
  */
 #define OPTIONAL_HANDLER(_assert) \
 	for (; _metadata->trigger; _metadata->trigger = \
-			__bail(_assert, _metadata->no_print, _metadata->step))
+			__bail(_assert, _metadata))
 
 #define __INC_STEP(_metadata) \
 	/* Keep "step" below 255 (which is used for "SKIP" reporting). */	\
@@ -830,6 +838,9 @@ struct __test_metadata {
 	bool timed_out;	/* did this test timeout instead of exiting? */
 	__u8 step;
 	bool no_print; /* manual trigger when TH_LOG_STREAM is not available */
+	bool aborted;	/* stopped test due to failed ASSERT */
+	bool setup_completed; /* did setup finish? */
+	jmp_buf env;	/* for exiting out of test early */
 	struct __test_results *results;
 	struct __test_metadata *prev, *next;
 };
@@ -848,16 +859,26 @@ static inline void __register_test(struct __test_metadata *t)
 	__LIST_APPEND(t->fixture->tests, t);
 }
 
-static inline int __bail(int for_realz, bool no_print, __u8 step)
+static inline int __bail(int for_realz, struct __test_metadata *t)
 {
+	/* if this is ASSERT, return immediately. */
 	if (for_realz) {
-		if (no_print)
-			_exit(step);
-		abort();
+		t->aborted = true;
+		longjmp(t->env, 1);
 	}
+	/* otherwise, end the for loop and continue. */
 	return 0;
 }
 
+static inline void __test_check_assert(struct __test_metadata *t)
+{
+	if (t->aborted) {
+		if (t->no_print)
+			_exit(t->step);
+		abort();
+	}
+}
+
 struct __test_metadata *__active_test;
 static void __timeout_handler(int sig, siginfo_t *info, void *ucontext)
 {
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index d444ee6aa3cb..b3bf5319bb0e 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -1208,6 +1208,20 @@ ipv4_fcnal()
 	set +e
 	check_nexthop "dev veth1" ""
 	log_test $? 0 "Nexthops removed on admin down"
+
+	# nexthop route delete warning: route add with nhid and delete
+	# using device
+	run_cmd "$IP li set dev veth1 up"
+	run_cmd "$IP nexthop add id 12 via 172.16.1.3 dev veth1"
+	out1=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l`
+	run_cmd "$IP route add 172.16.101.1/32 nhid 12"
+	run_cmd "$IP route delete 172.16.101.1/32 dev veth1"
+	out2=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l`
+	[ $out1 -eq $out2 ]
+	rc=$?
+	log_test $rc 0 "Delete nexthop route warning"
+	run_cmd "$IP route delete 172.16.101.1/32 nhid 12"
+	run_cmd "$IP nexthop del id 12"
 }
 
 ipv4_grp_fcnal()
diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile
index dcaefa224ca0..edafaca1aeb3 100644
--- a/tools/testing/selftests/pid_namespace/Makefile
+++ b/tools/testing/selftests/pid_namespace/Makefile
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -g -I../../../../usr/include/
 
-TEST_GEN_PROGS := regression_enomem
+TEST_GEN_PROGS = regression_enomem
 
-include ../lib.mk
+LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h
 
-$(OUTPUT)/regression_enomem: regression_enomem.c ../pidfd/pidfd.h
+include ../lib.mk
diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c
index 17999e082aa7..070c1c876df1 100644
--- a/tools/testing/selftests/pidfd/pidfd_wait.c
+++ b/tools/testing/selftests/pidfd/pidfd_wait.c
@@ -95,7 +95,6 @@ TEST(wait_states)
 		.flags = CLONE_PIDFD | CLONE_PARENT_SETTID,
 		.exit_signal = SIGCHLD,
 	};
-	int ret;
 	pid_t pid;
 	siginfo_t info = {
 		.si_signo = 0,
diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c
index 18a3bde8bc96..28604c9f805c 100644
--- a/tools/testing/selftests/proc/proc-pid-vm.c
+++ b/tools/testing/selftests/proc/proc-pid-vm.c
@@ -46,6 +46,8 @@
 #include <sys/time.h>
 #include <sys/resource.h>
 
+#include "../kselftest.h"
+
 static inline long sys_execveat(int dirfd, const char *pathname, char **argv, char **envp, int flags)
 {
 	return syscall(SYS_execveat, dirfd, pathname, argv, envp, flags);
@@ -368,7 +370,7 @@ int main(void)
 		};
 		int i;
 
-		for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) {
+		for (i = 0; i < ARRAY_SIZE(S); i++) {
 			assert(memmem(buf, rv, S[i], strlen(S[i])));
 		}
 
@@ -417,7 +419,7 @@ int main(void)
 		};
 		int i;
 
-		for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) {
+		for (i = 0; i < ARRAY_SIZE(S); i++) {
 			assert(memmem(buf, rv, S[i], strlen(S[i])));
 		}
 	}
diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c
index c4aea794725a..e691a3cf1491 100644
--- a/tools/testing/selftests/vDSO/vdso_test_correctness.c
+++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c
@@ -20,6 +20,7 @@
 #include <limits.h>
 
 #include "vdso_config.h"
+#include "../kselftest.h"
 
 static const char **name;
 
@@ -306,10 +307,8 @@ static void test_clock_gettime(void)
 		return;
 	}
 
-	for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]);
-	     clock++) {
+	for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++)
 		test_one_clock_gettime(clock, clocknames[clock]);
-	}
 
 	/* Also test some invalid clock ids */
 	test_one_clock_gettime(-1, "invalid");
@@ -370,10 +369,8 @@ static void test_clock_gettime64(void)
 		return;
 	}
 
-	for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]);
-	     clock++) {
+	for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++)
 		test_one_clock_gettime64(clock, clocknames[clock]);
-	}
 
 	/* Also test some invalid clock ids */
 	test_one_clock_gettime64(-1, "invalid");
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 53df7d3893d3..0388c4d60af0 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -92,6 +92,10 @@ warn_32bit_failure:
 	echo "If you are using a Fedora-like distribution, try:";	\
 	echo "";							\
 	echo "  yum install glibc-devel.*i686";				\
+	echo "";							\
+	echo "If you are using a SUSE-like distribution, try:";		\
+	echo "";							\
+	echo "  zypper install gcc-32bit glibc-devel-static-32bit";	\
 	exit 0;
 endif