77 files changed, 2369 insertions, 204 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/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 0eb90d21049e..ee15311b6be1 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -128,9 +128,9 @@
 #define TSX_CTRL_RTM_DISABLE		BIT(0)	/* Disable RTM feature */
 #define TSX_CTRL_CPUID_CLEAR		BIT(1)	/* Disable TSX enumeration */
 
-/* SRBDS support */
 #define MSR_IA32_MCU_OPT_CTRL		0x00000123
-#define RNGDS_MITG_DIS			BIT(0)
+#define RNGDS_MITG_DIS			BIT(0)	/* SRBDS support */
+#define RTM_ALLOW			BIT(1)	/* TSX development mode */
 
 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
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/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 1b15ba13c477..a09315538a30 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -577,7 +577,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 	const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
-	const struct perf_thread_map *threads = evlist->threads;
 
 	if (!ops || !ops->get || !ops->mmap)
 		return -EINVAL;
@@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 	perf_evlist__for_each_entry(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
-		    perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
+		    perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0)
 			return -ENOMEM;
 	}
 
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/bench/numa.c b/tools/perf/bench/numa.c
index f2640179ada9..44e1f8a44087 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -34,6 +34,7 @@
 #include <linux/numa.h>
 #include <linux/zalloc.h>
 
+#include "../util/header.h"
 #include <numa.h>
 #include <numaif.h>
 
@@ -54,7 +55,7 @@
 
 struct thread_data {
 	int			curr_cpu;
-	cpu_set_t		bind_cpumask;
+	cpu_set_t		*bind_cpumask;
 	int			bind_node;
 	u8			*process_data;
 	int			process_nr;
@@ -266,71 +267,115 @@ static bool node_has_cpus(int node)
 	return ret;
 }
 
-static cpu_set_t bind_to_cpu(int target_cpu)
+static cpu_set_t *bind_to_cpu(int target_cpu)
 {
-	cpu_set_t orig_mask, mask;
-	int ret;
+	int nrcpus = numa_num_possible_cpus();
+	cpu_set_t *orig_mask, *mask;
+	size_t size;
 
-	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
-	BUG_ON(ret);
+	orig_mask = CPU_ALLOC(nrcpus);
+	BUG_ON(!orig_mask);
+	size = CPU_ALLOC_SIZE(nrcpus);
+	CPU_ZERO_S(size, orig_mask);
+
+	if (sched_getaffinity(0, size, orig_mask))
+		goto err_out;
+
+	mask = CPU_ALLOC(nrcpus);
+	if (!mask)
+		goto err_out;
 
-	CPU_ZERO(&mask);
+	CPU_ZERO_S(size, mask);
 
 	if (target_cpu == -1) {
 		int cpu;
 
 		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
-			CPU_SET(cpu, &mask);
+			CPU_SET_S(cpu, size, mask);
 	} else {
-		BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus);
-		CPU_SET(target_cpu, &mask);
+		if (target_cpu < 0 || target_cpu >= g->p.nr_cpus)
+			goto err;
+
+		CPU_SET_S(target_cpu, size, mask);
 	}
 
-	ret = sched_setaffinity(0, sizeof(mask), &mask);
-	BUG_ON(ret);
+	if (sched_setaffinity(0, size, mask))
+		goto err;
 
 	return orig_mask;
+
+err:
+	CPU_FREE(mask);
+err_out:
+	CPU_FREE(orig_mask);
+
+	/* BUG_ON due to failure in allocation of orig_mask/mask */
+	BUG_ON(-1);
 }
 
-static cpu_set_t bind_to_node(int target_node)
+static cpu_set_t *bind_to_node(int target_node)
 {
-	cpu_set_t orig_mask, mask;
+	int nrcpus = numa_num_possible_cpus();
+	size_t size;
+	cpu_set_t *orig_mask, *mask;
 	int cpu;
-	int ret;
 
-	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
-	BUG_ON(ret);
+	orig_mask = CPU_ALLOC(nrcpus);
+	BUG_ON(!orig_mask);
+	size = CPU_ALLOC_SIZE(nrcpus);
+	CPU_ZERO_S(size, orig_mask);
 
-	CPU_ZERO(&mask);
+	if (sched_getaffinity(0, size, orig_mask))
+		goto err_out;
+
+	mask = CPU_ALLOC(nrcpus);
+	if (!mask)
+		goto err_out;
+
+	CPU_ZERO_S(size, mask);
 
 	if (target_node == NUMA_NO_NODE) {
 		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
-			CPU_SET(cpu, &mask);
+			CPU_SET_S(cpu, size, mask);
 	} else {
 		struct bitmask *cpumask = numa_allocate_cpumask();
 
-		BUG_ON(!cpumask);
+		if (!cpumask)
+			goto err;
+
 		if (!numa_node_to_cpus(target_node, cpumask)) {
 			for (cpu = 0; cpu < (int)cpumask->size; cpu++) {
 				if (numa_bitmask_isbitset(cpumask, cpu))
-					CPU_SET(cpu, &mask);
+					CPU_SET_S(cpu, size, mask);
 			}
 		}
 		numa_free_cpumask(cpumask);
 	}
 
-	ret = sched_setaffinity(0, sizeof(mask), &mask);
-	BUG_ON(ret);
+	if (sched_setaffinity(0, size, mask))
+		goto err;
 
 	return orig_mask;
+
+err:
+	CPU_FREE(mask);
+err_out:
+	CPU_FREE(orig_mask);
+
+	/* BUG_ON due to failure in allocation of orig_mask/mask */
+	BUG_ON(-1);
 }
 
-static void bind_to_cpumask(cpu_set_t mask)
+static void bind_to_cpumask(cpu_set_t *mask)
 {
 	int ret;
+	size_t size = CPU_ALLOC_SIZE(numa_num_possible_cpus());
 
-	ret = sched_setaffinity(0, sizeof(mask), &mask);
-	BUG_ON(ret);
+	ret = sched_setaffinity(0, size, mask);
+	if (ret) {
+		CPU_FREE(mask);
+		BUG_ON(ret);
+	}
 }
 
 static void mempol_restore(void)
@@ -376,7 +421,7 @@ do {							\
 static u8 *alloc_data(ssize_t bytes0, int map_flags,
 		      int init_zero, int init_cpu0, int thp, int init_random)
 {
-	cpu_set_t orig_mask;
+	cpu_set_t *orig_mask = NULL;
 	ssize_t bytes;
 	u8 *buf;
 	int ret;
@@ -434,6 +479,7 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,
 	/* Restore affinity: */
 	if (init_cpu0) {
 		bind_to_cpumask(orig_mask);
+		CPU_FREE(orig_mask);
 		mempol_restore();
 	}
 
@@ -585,10 +631,16 @@ static int parse_setup_cpu_list(void)
 			return -1;
 		}
 
+		if (is_cpu_online(bind_cpu_0) != 1 || is_cpu_online(bind_cpu_1) != 1) {
+			printf("\nTest not applicable, bind_cpu_0 or bind_cpu_1 is offline\n");
+			return -1;
+		}
+
 		BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0);
 		BUG_ON(bind_cpu_0 > bind_cpu_1);
 
 		for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) {
+			size_t size = CPU_ALLOC_SIZE(g->p.nr_cpus);
 			int i;
 
 			for (i = 0; i < mul; i++) {
@@ -608,10 +660,15 @@ static int parse_setup_cpu_list(void)
 					tprintf("%2d", bind_cpu);
 				}
 
-				CPU_ZERO(&td->bind_cpumask);
+				td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus);
+				BUG_ON(!td->bind_cpumask);
+				CPU_ZERO_S(size, td->bind_cpumask);
 				for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) {
-					BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus);
-					CPU_SET(cpu, &td->bind_cpumask);
+					if (cpu < 0 || cpu >= g->p.nr_cpus) {
+						CPU_FREE(td->bind_cpumask);
+						BUG_ON(-1);
+					}
+					CPU_SET_S(cpu, size, td->bind_cpumask);
 				}
 				t++;
 			}
@@ -752,8 +809,6 @@ static int parse_nodes_opt(const struct option *opt __maybe_unused,
 	return parse_node_list(arg);
 }
 
-#define BIT(x) (1ul << x)
-
 static inline uint32_t lfsr_32(uint32_t lfsr)
 {
 	const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31);
@@ -1241,7 +1296,7 @@ static void *worker_thread(void *__tdata)
 		 * by migrating to CPU#0:
 		 */
 		if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) {
-			cpu_set_t orig_mask;
+			cpu_set_t *orig_mask;
 			int target_cpu;
 			int this_cpu;
 
@@ -1265,6 +1320,7 @@ static void *worker_thread(void *__tdata)
 				printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu);
 
 			bind_to_cpumask(orig_mask);
+			CPU_FREE(orig_mask);
 		}
 
 		if (details >= 3) {
@@ -1398,21 +1454,31 @@ static void init_thread_data(void)
 
 	for (t = 0; t < g->p.nr_tasks; t++) {
 		struct thread_data *td = g->threads + t;
+		size_t cpuset_size = CPU_ALLOC_SIZE(g->p.nr_cpus);
 		int cpu;
 
 		/* Allow all nodes by default: */
 		td->bind_node = NUMA_NO_NODE;
 
 		/* Allow all CPUs by default: */
-		CPU_ZERO(&td->bind_cpumask);
+		td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus);
+		BUG_ON(!td->bind_cpumask);
+		CPU_ZERO_S(cpuset_size, td->bind_cpumask);
 		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
-			CPU_SET(cpu, &td->bind_cpumask);
+			CPU_SET_S(cpu, cpuset_size, td->bind_cpumask);
 	}
 }
 
 static void deinit_thread_data(void)
 {
 	ssize_t size = sizeof(*g->threads)*g->p.nr_tasks;
+	int t;
+
+	/* Free the bind_cpumask allocated for thread_data */
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		struct thread_data *td = g->threads + t;
+		CPU_FREE(td->bind_cpumask);
+	}
 
 	free_data(g->threads, size);
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ba74fab02e62..069825c48d40 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -989,8 +989,11 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru
 	struct mmap *overwrite_mmap = evlist->overwrite_mmap;
 	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 
-	thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
-					      thread_data->mask->maps.nbits);
+	if (cpu_map__is_dummy(cpus))
+		thread_data->nr_mmaps = nr_mmaps;
+	else
+		thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
+						      thread_data->mask->maps.nbits);
 	if (mmap) {
 		thread_data->maps = zalloc(thread_data->nr_mmaps * sizeof(struct mmap *));
 		if (!thread_data->maps)
@@ -1007,16 +1010,17 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru
 		 thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps);
 
 	for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) {
-		if (test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) {
+		if (cpu_map__is_dummy(cpus) ||
+		    test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) {
 			if (thread_data->maps) {
 				thread_data->maps[tm] = &mmap[m];
 				pr_debug2("thread_data[%p]: cpu%d: maps[%d] -> mmap[%d]\n",
-					  thread_data, cpus->map[m].cpu, tm, m);
+					  thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m);
 			}
 			if (thread_data->overwrite_maps) {
 				thread_data->overwrite_maps[tm] = &overwrite_mmap[m];
 				pr_debug2("thread_data[%p]: cpu%d: ow_maps[%d] -> ow_mmap[%d]\n",
-					  thread_data, cpus->map[m].cpu, tm, m);
+					  thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m);
 			}
 			tm++;
 		}
@@ -3329,6 +3333,9 @@ static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_c
 {
 	int c;
 
+	if (cpu_map__is_dummy(cpus))
+		return;
+
 	for (c = 0; c < cpus->nr; c++)
 		set_bit(cpus->map[c].cpu, mask->bits);
 }
@@ -3680,6 +3687,11 @@ static int record__init_thread_masks(struct record *rec)
 	if (!record__threads_enabled(rec))
 		return record__init_thread_default_masks(rec, cpus);
 
+	if (cpu_map__is_dummy(cpus)) {
+		pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n");
+		return -EINVAL;
+	}
+
 	switch (rec->opts.threads_spec) {
 	case THREAD_SPEC__CPU:
 		ret = record__init_thread_cpu_masks(rec, cpus);
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/header.c b/tools/perf/util/header.c
index d546ff724dbe..a27132e5a5ef 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -983,6 +983,57 @@ static int write_dir_format(struct feat_fd *ff,
 	return do_write(ff, &data->dir.version, sizeof(data->dir.version));
 }
 
+/*
+ * Check whether a CPU is online
+ *
+ * Returns:
+ *     1 -> if CPU is online
+ *     0 -> if CPU is offline
+ *    -1 -> error case
+ */
+int is_cpu_online(unsigned int cpu)
+{
+	char *str;
+	size_t strlen;
+	char buf[256];
+	int status = -1;
+	struct stat statbuf;
+
+	snprintf(buf, sizeof(buf),
+		"/sys/devices/system/cpu/cpu%d", cpu);
+	if (stat(buf, &statbuf) != 0)
+		return 0;
+
+	/*
+	 * Check if /sys/devices/system/cpu/cpux/online file
+	 * exists. Some cases cpu0 won't have online file since
+	 * it is not expected to be turned off generally.
+	 * In kernels without CONFIG_HOTPLUG_CPU, this
+	 * file won't exist
+	 */
+	snprintf(buf, sizeof(buf),
+		"/sys/devices/system/cpu/cpu%d/online", cpu);
+	if (stat(buf, &statbuf) != 0)
+		return 1;
+
+	/*
+	 * Read online file using sysfs__read_str.
+	 * If read or open fails, return -1.
+	 * If read succeeds, return value from file
+	 * which gets stored in "str"
+	 */
+	snprintf(buf, sizeof(buf),
+		"devices/system/cpu/cpu%d/online", cpu);
+
+	if (sysfs__read_str(buf, &str, &strlen) < 0)
+		return status;
+
+	status = atoi(str);
+
+	free(str);
+	return status;
+}
+
 #ifdef HAVE_LIBBPF_SUPPORT
 static int write_bpf_prog_info(struct feat_fd *ff,
 			       struct evlist *evlist __maybe_unused)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index c9e3265832d9..0eb4bc29a5a4 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -158,6 +158,7 @@ int do_write(struct feat_fd *fd, const void *buf, size_t size);
 int write_padded(struct feat_fd *fd, const void *bf,
 		 size_t count, size_t count_aligned);
 
+int is_cpu_online(unsigned int cpu);
 /*
  * arch specific callback
  */
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/parse-events.c b/tools/perf/util/parse-events.c
index 24997925ae00..dd84fed698a3 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1523,7 +1523,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 	bool use_uncore_alias;
 	LIST_HEAD(config_terms);
 
-	if (verbose > 1) {
+	pmu = parse_state->fake_pmu ?: perf_pmu__find(name);
+
+	if (verbose > 1 && !(pmu && pmu->selectable)) {
 		fprintf(stderr, "Attempting to add event pmu '%s' with '",
 			name);
 		if (head_config) {
@@ -1536,7 +1538,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		fprintf(stderr, "' that may result in non-fatal errors\n");
 	}
 
-	pmu = parse_state->fake_pmu ?: perf_pmu__find(name);
 	if (!pmu) {
 		char *err_str;
 
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/stat.c b/tools/perf/util/stat.c
index ee6f03481215..817a2de264b4 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
+#include <linux/err.h>
 #include <inttypes.h>
 #include <math.h>
 #include <string.h>
@@ -311,7 +312,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
 
 	if (!mask) {
 		mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL);
-		if (!mask)
+		if (IS_ERR(mask))
 			return -ENOMEM;
 
 		counter->per_pkg_mask = mask;
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/drivers/net/dsa/bridge_locked_port.sh b/tools/testing/selftests/drivers/net/dsa/bridge_locked_port.sh
new file mode 120000
index 000000000000..f5eb940c4c7c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_locked_port.sh
@@ -0,0 +1 @@
+../../../net/forwarding/bridge_locked_port.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh b/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh
new file mode 120000
index 000000000000..76492da525f7
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh
@@ -0,0 +1 @@
+../../../net/forwarding/bridge_mdb.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh b/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh
new file mode 120000
index 000000000000..81a7e0df0474
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh
@@ -0,0 +1 @@
+../../../net/forwarding/bridge_mld.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh
new file mode 120000
index 000000000000..9831ed74376a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh
@@ -0,0 +1 @@
+../../../net/forwarding/bridge_vlan_aware.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh
new file mode 120000
index 000000000000..7f3c3f0bf719
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh
@@ -0,0 +1 @@
+../../../net/forwarding/bridge_vlan_mcast.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh
new file mode 120000
index 000000000000..bf1a57e6bde1
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh
@@ -0,0 +1 @@
+../../../net/forwarding/bridge_vlan_unaware.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/forwarding.config b/tools/testing/selftests/drivers/net/dsa/forwarding.config
new file mode 100644
index 000000000000..7adc1396fae0
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/forwarding.config
@@ -0,0 +1,2 @@
+NETIF_CREATE=no
+STABLE_MAC_ADDRS=yes
diff --git a/tools/testing/selftests/drivers/net/dsa/lib.sh b/tools/testing/selftests/drivers/net/dsa/lib.sh
new file mode 120000
index 000000000000..39c96828c5ef
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/lib.sh
@@ -0,0 +1 @@
+../../../net/forwarding/lib.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/local_termination.sh b/tools/testing/selftests/drivers/net/dsa/local_termination.sh
new file mode 120000
index 000000000000..c08166f84501
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/local_termination.sh
@@ -0,0 +1 @@
+../../../net/forwarding/local_termination.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh b/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh
new file mode 120000
index 000000000000..b9757466bc97
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh
@@ -0,0 +1 @@
+../../../net/forwarding/no_forwarding.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_linecard.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_linecard.sh
new file mode 100755
index 000000000000..53a65f416770
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_linecard.sh
@@ -0,0 +1,341 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# In addition to the common variables, user might use:
+# LC_SLOT - If not set, all probed line cards are going to be tested,
+#	    with an exception of the "activation_16x100G_test".
+#	    It set, only the selected line card is going to be used
+#	    for tests, including "activation_16x100G_test".
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	unprovision_test
+	provision_test
+	activation_16x100G_test
+"
+
+NUM_NETIFS=0
+
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+until_lc_state_is()
+{
+	local state=$1; shift
+	local current=$("$@")
+
+	echo "$current"
+	[ "$current" == "$state" ]
+}
+
+until_lc_state_is_not()
+{
+	! until_lc_state_is "$@"
+}
+
+lc_state_get()
+{
+	local lc=$1
+
+	devlink lc show $DEVLINK_DEV lc $lc -j | jq -e -r ".[][][].state"
+}
+
+lc_wait_until_state_changes()
+{
+	local lc=$1
+	local state=$2
+	local timeout=$3 # ms
+
+	busywait "$timeout" until_lc_state_is_not "$state" lc_state_get "$lc"
+}
+
+lc_wait_until_state_becomes()
+{
+	local lc=$1
+	local state=$2
+	local timeout=$3 # ms
+
+	busywait "$timeout" until_lc_state_is "$state" lc_state_get "$lc"
+}
+
+until_lc_port_count_is()
+{
+	local port_count=$1; shift
+	local current=$("$@")
+
+	echo "$current"
+	[ $current == $port_count ]
+}
+
+lc_port_count_get()
+{
+	local lc=$1
+
+	devlink port -j | jq -e -r ".[][] | select(.lc==$lc) | .port" | wc -l
+}
+
+lc_wait_until_port_count_is()
+{
+	local lc=$1
+	local port_count=$2
+	local timeout=$3 # ms
+
+	busywait "$timeout" until_lc_port_count_is "$port_count" lc_port_count_get "$lc"
+}
+
+PROV_UNPROV_TIMEOUT=8000 # ms
+POST_PROV_ACT_TIMEOUT=2000 # ms
+PROV_PORTS_INSTANTIATION_TIMEOUT=15000 # ms
+
+unprovision_one()
+{
+	local lc=$1
+	local state
+
+	state=$(lc_state_get $lc)
+	check_err $? "Failed to get state of linecard $lc"
+	if [[ "$state" == "unprovisioned" ]]; then
+		return
+	fi
+
+	log_info "Unprovisioning linecard $lc"
+
+	devlink lc set $DEVLINK_DEV lc $lc notype
+	check_err $? "Failed to trigger linecard $lc unprovisioning"
+
+	state=$(lc_wait_until_state_changes $lc "unprovisioning" \
+		$PROV_UNPROV_TIMEOUT)
+	check_err $? "Failed to unprovision linecard $lc (timeout)"
+
+	[ "$state" == "unprovisioned" ]
+	check_err $? "Failed to unprovision linecard $lc (state=$state)"
+}
+
+provision_one()
+{
+	local lc=$1
+	local type=$2
+	local state
+
+	log_info "Provisioning linecard $lc"
+
+	devlink lc set $DEVLINK_DEV lc $lc type $type
+	check_err $? "Failed trigger linecard $lc provisioning"
+
+	state=$(lc_wait_until_state_changes $lc "provisioning" \
+		$PROV_UNPROV_TIMEOUT)
+	check_err $? "Failed to provision linecard $lc (timeout)"
+
+	[ "$state" == "provisioned" ] || [ "$state" == "active" ]
+	check_err $? "Failed to provision linecard $lc (state=$state)"
+
+	provisioned_type=$(devlink lc show $DEVLINK_DEV lc $lc -j | jq -e -r ".[][][].type")
+	[ "$provisioned_type" == "$type" ]
+	check_err $? "Wrong provision type returned for linecard $lc (got \"$provisioned_type\", expected \"$type\")"
+
+	# Wait for possible activation to make sure the state
+	# won't change after return from this function.
+	state=$(lc_wait_until_state_becomes $lc "active" \
+		$POST_PROV_ACT_TIMEOUT)
+}
+
+unprovision_test()
+{
+	RET=0
+	local lc
+
+	lc=$LC_SLOT
+	unprovision_one $lc
+	log_test "Unprovision"
+}
+
+LC_16X100G_TYPE="16x100G"
+LC_16X100G_PORT_COUNT=16
+LC_16X100G_DEVICE_COUNT=4
+
+supported_types_check()
+{
+	local lc=$1
+	local supported_types_count
+	local type_index
+	local lc_16x100_found=false
+
+	supported_types_count=$(devlink lc show $DEVLINK_DEV lc $lc -j | \
+				jq -e -r ".[][][].supported_types | length")
+	[ $supported_types_count != 0 ]
+	check_err $? "No supported types found for linecard $lc"
+	for (( type_index=0; type_index<$supported_types_count; type_index++ ))
+	do
+		type=$(devlink lc show $DEVLINK_DEV lc $lc -j | \
+		       jq -e -r ".[][][].supported_types[$type_index]")
+		if [[ "$type" == "$LC_16X100G_TYPE" ]]; then
+			lc_16x100_found=true
+			break
+		fi
+	done
+	[ $lc_16x100_found = true ]
+	check_err $? "16X100G not found between supported types of linecard $lc"
+}
+
+lc_info_check()
+{
+	local lc=$1
+	local fixed_hw_revision
+	local running_ini_version
+
+	fixed_hw_revision=$(devlink lc -v info $DEVLINK_DEV lc $lc -j | \
+			    jq -e -r '.[][][].versions.fixed."hw.revision"')
+	check_err $? "Failed to get linecard $lc fixed.hw.revision"
+	log_info "Linecard $lc fixed.hw.revision: \"$fixed_hw_revision\""
+	running_ini_version=$(devlink lc -v info $DEVLINK_DEV lc $lc -j | \
+			      jq -e -r '.[][][].versions.running."ini.version"')
+	check_err $? "Failed to get linecard $lc running.ini.version"
+	log_info "Linecard $lc running.ini.version: \"$running_ini_version\""
+}
+
+lc_devices_check()
+{
+	local lc=$1
+	local expected_device_count=$2
+	local device_count
+	local device
+
+	device_count=$(devlink lc show $DEVLINK_DEV lc $lc -j | \
+		       jq -e -r ".[][][].devices |length")
+	check_err $? "Failed to get linecard $lc device count"
+	[ $device_count != 0 ]
+	check_err $? "No device found on linecard $lc"
+	[ $device_count == $expected_device_count ]
+	check_err $? "Unexpected device count on linecard $lc (got $expected_device_count, expected $device_count)"
+	for (( device=0; device<device_count; device++ ))
+	do
+		log_info "Linecard $lc device $device"
+	done
+}
+
+ports_check()
+{
+	local lc=$1
+	local expected_port_count=$2
+	local port_count
+
+	port_count=$(lc_wait_until_port_count_is $lc $expected_port_count \
+		$PROV_PORTS_INSTANTIATION_TIMEOUT)
+	[ $port_count != 0 ]
+	check_err $? "No port associated with linecard $lc"
+	[ $port_count == $expected_port_count ]
+	check_err $? "Unexpected port count linecard $lc (got $port_count, expected $expected_port_count)"
+}
+
+provision_test()
+{
+	RET=0
+	local lc
+	local type
+	local state
+
+	lc=$LC_SLOT
+	supported_types_check $lc
+	state=$(lc_state_get $lc)
+	check_err $? "Failed to get state of linecard $lc"
+	if [[ "$state" != "unprovisioned" ]]; then
+		unprovision_one $lc
+	fi
+	provision_one $lc $LC_16X100G_TYPE
+	lc_devices_check $lc $LC_16X100G_DEVICE_COUNT
+	lc_info_check $lc
+	ports_check $lc $LC_16X100G_PORT_COUNT
+	log_test "Provision"
+}
+
+ACTIVATION_TIMEOUT=20000 # ms
+
+interface_check()
+{
+	ip link set $h1 up
+	ip link set $h2 up
+	ifaces_upped=true
+	setup_wait
+}
+
+lc_devices_info_check()
+{
+	local lc=$1
+	local expected_device_count=$2
+	local device_count
+	local device
+	local running_device_fw
+
+	device_count=$(devlink lc info $DEVLINK_DEV lc $lc -j | \
+		       jq -e -r ".[][][].devices |length")
+	check_err $? "Failed to get linecard $lc device count"
+	for (( device=0; device<device_count; device++ ))
+	do
+		running_device_fw=$(devlink lc -v info $DEVLINK_DEV lc $lc -j | \
+				    jq -e -r ".[][][].devices[$device].versions.running.fw")
+		check_err $? "Failed to get linecard $lc device $device running fw version"
+		log_info "Linecard $lc device $device running.fw: \"$running_device_fw\""
+	done
+}
+
+activation_16x100G_test()
+{
+	RET=0
+	local lc
+	local type
+	local state
+
+	lc=$LC_SLOT
+	type=$LC_16X100G_TYPE
+
+	unprovision_one $lc
+	provision_one $lc $type
+	state=$(lc_wait_until_state_becomes $lc "active" \
+		$ACTIVATION_TIMEOUT)
+	check_err $? "Failed to get linecard $lc activated (timeout)"
+
+	lc_devices_info_check $lc $LC_16X100G_DEVICE_COUNT
+
+	interface_check
+
+	log_test "Activation 16x100G"
+}
+
+setup_prepare()
+{
+	local lc_num=$(devlink lc show -j | jq -e -r ".[][\"$DEVLINK_DEV\"] |length")
+	if [[ $? -ne 0 ]] || [[ $lc_num -eq 0 ]]; then
+		echo "SKIP: No linecard support found"
+		exit $ksft_skip
+	fi
+
+	if [ -z "$LC_SLOT" ]; then
+		echo "SKIP: \"LC_SLOT\" variable not provided"
+		exit $ksft_skip
+	fi
+
+	# Interfaces are not present during the script start,
+	# that's why we define NUM_NETIFS here so dummy
+	# implicit veth pairs are not created.
+	NUM_NETIFS=2
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+	ifaces_upped=false
+}
+
+cleanup()
+{
+	if [ "$ifaces_upped" = true ] ; then
+		ip link set $h1 down
+		ip link set $h2 down
+	fi
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh
index 429f7ee735cf..fd23c80eba31 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh
@@ -159,6 +159,17 @@ flooding_remotes_add()
 	local lsb
 	local i
 
+	# Prevent unwanted packets from entering the bridge and interfering
+	# with the test.
+	tc qdisc add dev br0 clsact
+	tc filter add dev br0 egress protocol all pref 1 handle 1 \
+		matchall skip_hw action drop
+	tc qdisc add dev $h1 clsact
+	tc filter add dev $h1 egress protocol all pref 1 handle 1 \
+		flower skip_hw dst_mac de:ad:be:ef:13:37 action pass
+	tc filter add dev $h1 egress protocol all pref 2 handle 2 \
+		matchall skip_hw action drop
+
 	for i in $(eval echo {1..$num_remotes}); do
 		lsb=$((i + 1))
 
@@ -195,6 +206,12 @@ flooding_filters_del()
 	done
 
 	tc qdisc del dev $rp2 clsact
+
+	tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall
+	tc filter del dev $h1 egress protocol all pref 1 handle 1 flower
+	tc qdisc del dev $h1 clsact
+	tc filter del dev br0 egress protocol all pref 1 handle 1 matchall
+	tc qdisc del dev br0 clsact
 }
 
 flooding_check_packets()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
index fedcb7b35af9..af5ea50ed5c0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
@@ -172,6 +172,17 @@ flooding_filters_add()
 	local lsb
 	local i
 
+	# Prevent unwanted packets from entering the bridge and interfering
+	# with the test.
+	tc qdisc add dev br0 clsact
+	tc filter add dev br0 egress protocol all pref 1 handle 1 \
+		matchall skip_hw action drop
+	tc qdisc add dev $h1 clsact
+	tc filter add dev $h1 egress protocol all pref 1 handle 1 \
+		flower skip_hw dst_mac de:ad:be:ef:13:37 action pass
+	tc filter add dev $h1 egress protocol all pref 2 handle 2 \
+		matchall skip_hw action drop
+
 	tc qdisc add dev $rp2 clsact
 
 	for i in $(eval echo {1..$num_remotes}); do
@@ -194,6 +205,12 @@ flooding_filters_del()
 	done
 
 	tc qdisc del dev $rp2 clsact
+
+	tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall
+	tc filter del dev $h1 egress protocol all pref 1 handle 1 flower
+	tc qdisc del dev $h1 clsact
+	tc filter del dev br0 egress protocol all pref 1 handle 1 matchall
+	tc qdisc del dev br0 clsact
 }
 
 flooding_check_packets()
diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
index eaf8a04a7ca5..7e684e27a682 100755
--- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
@@ -215,15 +215,15 @@ test_vlan_pop()
 
 	sleep 1
 
-	tcpdump_stop
+	tcpdump_stop $eth2
 
-	if tcpdump_show | grep -q "$eth3_mac > $eth2_mac, ethertype IPv4"; then
+	if tcpdump_show $eth2 | grep -q "$eth3_mac > $eth2_mac, ethertype IPv4"; then
 		echo "OK"
 	else
 		echo "FAIL"
 	fi
 
-	tcpdump_cleanup
+	tcpdump_cleanup $eth2
 }
 
 test_vlan_push()
@@ -236,15 +236,15 @@ test_vlan_push()
 
 	sleep 1
 
-	tcpdump_stop
+	tcpdump_stop $eth3.100
 
-	if tcpdump_show | grep -q "$eth2_mac > $eth3_mac"; then
+	if tcpdump_show $eth3.100 | grep -q "$eth2_mac > $eth3_mac"; then
 		echo "OK"
 	else
 		echo "FAIL"
 	fi
 
-	tcpdump_cleanup
+	tcpdump_cleanup $eth3.100
 }
 
 test_vlan_ingress_modify()
@@ -267,15 +267,15 @@ test_vlan_ingress_modify()
 
 	sleep 1
 
-	tcpdump_stop
+	tcpdump_stop $eth2
 
-	if tcpdump_show | grep -q "$eth3_mac > $eth2_mac, .* vlan 300"; then
+	if tcpdump_show $eth2 | grep -q "$eth3_mac > $eth2_mac, .* vlan 300"; then
 		echo "OK"
 	else
 		echo "FAIL"
 	fi
 
-	tcpdump_cleanup
+	tcpdump_cleanup $eth2
 
 	tc filter del dev $eth0 ingress chain $(IS1 2) pref 3
 
@@ -305,15 +305,15 @@ test_vlan_egress_modify()
 
 	sleep 1
 
-	tcpdump_stop
+	tcpdump_stop $eth2
 
-	if tcpdump_show | grep -q "$eth3_mac > $eth2_mac, .* vlan 300"; then
+	if tcpdump_show $eth2 | grep -q "$eth3_mac > $eth2_mac, .* vlan 300"; then
 		echo "OK"
 	else
 		echo "FAIL"
 	fi
 
-	tcpdump_cleanup
+	tcpdump_cleanup $eth2
 
 	tc filter del dev $eth1 egress chain $(ES0) pref 3
 	tc qdisc del dev $eth1 clsact
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/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index d1e8f5237469..0b0e4402bba6 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -3,6 +3,7 @@
 /aarch64/debug-exceptions
 /aarch64/get-reg-list
 /aarch64/psci_cpu_on_test
+/aarch64/vcpu_width_config
 /aarch64/vgic_init
 /aarch64/vgic_irq
 /s390x/memop
@@ -33,6 +34,7 @@
 /x86_64/state_test
 /x86_64/svm_vmcall_test
 /x86_64/svm_int_ctl_test
+/x86_64/tsc_scaling_sync
 /x86_64/sync_regs_test
 /x86_64/tsc_msrs_test
 /x86_64/userspace_io_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 21c2dbd21a81..681b173aa87c 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -106,6 +106,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/arch_timer
 TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
 TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
+TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
 TEST_GEN_PROGS_aarch64 += demand_paging_test
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index b08d30bf71c5..3b940a101bc0 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -362,11 +362,12 @@ static void test_init_timer_irq(struct kvm_vm *vm)
 	pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq);
 }
 
+static int gic_fd;
+
 static struct kvm_vm *test_vm_create(void)
 {
 	struct kvm_vm *vm;
 	unsigned int i;
-	int ret;
 	int nr_vcpus = test_args.nr_vcpus;
 
 	vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
@@ -383,8 +384,8 @@ static struct kvm_vm *test_vm_create(void)
 
 	ucall_init(vm, NULL);
 	test_init_timer_irq(vm);
-	ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
-	if (ret < 0) {
+	gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+	if (gic_fd < 0) {
 		print_skip("Failed to create vgic-v3");
 		exit(KSFT_SKIP);
 	}
@@ -395,6 +396,12 @@ static struct kvm_vm *test_vm_create(void)
 	return vm;
 }
 
+static void test_vm_cleanup(struct kvm_vm *vm)
+{
+	close(gic_fd);
+	kvm_vm_free(vm);
+}
+
 static void test_print_help(char *name)
 {
 	pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n",
@@ -478,7 +485,7 @@ int main(int argc, char *argv[])
 
 	vm = test_vm_create();
 	test_run(vm);
-	kvm_vm_free(vm);
+	test_vm_cleanup(vm);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index f12147c43464..0b571f3fe64c 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -503,8 +503,13 @@ static void run_test(struct vcpu_config *c)
 		++missing_regs;
 
 	if (new_regs || missing_regs) {
+		n = 0;
+		for_each_reg_filtered(i)
+			++n;
+
 		printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n);
-		printf("%s: Number registers:         %5lld\n", config_name(c), reg_list->n);
+		printf("%s: Number registers:         %5lld (includes %lld filtered registers)\n",
+		       config_name(c), reg_list->n, reg_list->n - n);
 	}
 
 	if (new_regs) {
@@ -683,9 +688,10 @@ static __u64 base_regs[] = {
 	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]),
 	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr),
 	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr),
-	KVM_REG_ARM_FW_REG(0),
-	KVM_REG_ARM_FW_REG(1),
-	KVM_REG_ARM_FW_REG(2),
+	KVM_REG_ARM_FW_REG(0),		/* KVM_REG_ARM_PSCI_VERSION */
+	KVM_REG_ARM_FW_REG(1),		/* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 */
+	KVM_REG_ARM_FW_REG(2),		/* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 */
+	KVM_REG_ARM_FW_REG(3),		/* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 */
 	ARM64_SYS_REG(3, 3, 14, 3, 1),	/* CNTV_CTL_EL0 */
 	ARM64_SYS_REG(3, 3, 14, 3, 2),	/* CNTV_CVAL_EL0 */
 	ARM64_SYS_REG(3, 3, 14, 0, 2),
diff --git a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c
new file mode 100644
index 000000000000..6e9402679229
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vcpu_width_config - Test KVM_ARM_VCPU_INIT() with KVM_ARM_VCPU_EL1_32BIT.
+ *
+ * Copyright (c) 2022 Google LLC.
+ *
+ * This is a test that ensures that non-mixed-width vCPUs (all 64bit vCPUs
+ * or all 32bit vcPUs) can be configured and mixed-width vCPUs cannot be
+ * configured.
+ */
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+
+/*
+ * Add a vCPU, run KVM_ARM_VCPU_INIT with @init1, and then
+ * add another vCPU, and run KVM_ARM_VCPU_INIT with @init2.
+ */
+static int add_init_2vcpus(struct kvm_vcpu_init *init1,
+			   struct kvm_vcpu_init *init2)
+{
+	struct kvm_vm *vm;
+	int ret;
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+
+	vm_vcpu_add(vm, 0);
+	ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1);
+	if (ret)
+		goto free_exit;
+
+	vm_vcpu_add(vm, 1);
+	ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2);
+
+free_exit:
+	kvm_vm_free(vm);
+	return ret;
+}
+
+/*
+ * Add two vCPUs, then run KVM_ARM_VCPU_INIT for one vCPU with @init1,
+ * and run KVM_ARM_VCPU_INIT for another vCPU with @init2.
+ */
+static int add_2vcpus_init_2vcpus(struct kvm_vcpu_init *init1,
+				  struct kvm_vcpu_init *init2)
+{
+	struct kvm_vm *vm;
+	int ret;
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+
+	vm_vcpu_add(vm, 0);
+	vm_vcpu_add(vm, 1);
+
+	ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1);
+	if (ret)
+		goto free_exit;
+
+	ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2);
+
+free_exit:
+	kvm_vm_free(vm);
+	return ret;
+}
+
+/*
+ * Tests that two 64bit vCPUs can be configured, two 32bit vCPUs can be
+ * configured, and two mixed-width vCPUs cannot be configured.
+ * Each of those three cases, configure vCPUs in two different orders.
+ * The one is running KVM_CREATE_VCPU for 2 vCPUs, and then running
+ * KVM_ARM_VCPU_INIT for them.
+ * The other is running KVM_CREATE_VCPU and KVM_ARM_VCPU_INIT for a vCPU,
+ * and then run those commands for another vCPU.
+ */
+int main(void)
+{
+	struct kvm_vcpu_init init1, init2;
+	struct kvm_vm *vm;
+	int ret;
+
+	if (!kvm_check_cap(KVM_CAP_ARM_EL1_32BIT)) {
+		print_skip("KVM_CAP_ARM_EL1_32BIT is not supported");
+		exit(KSFT_SKIP);
+	}
+
+	/* Get the preferred target type and copy that to init2 for later use */
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init1);
+	kvm_vm_free(vm);
+	init2 = init1;
+
+	/* Test with 64bit vCPUs */
+	ret = add_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 64bit EL1 vCPUs failed unexpectedly");
+	ret = add_2vcpus_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 64bit EL1 vCPUs failed unexpectedly");
+
+	/* Test with 32bit vCPUs */
+	init1.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT);
+	ret = add_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 32bit EL1 vCPUs failed unexpectedly");
+	ret = add_2vcpus_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 32bit EL1 vCPUs failed unexpectedly");
+
+	/* Test with mixed-width vCPUs  */
+	init1.features[0] = 0;
+	init2.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT);
+	ret = add_init_2vcpus(&init1, &init2);
+	TEST_ASSERT(ret != 0,
+		    "Configuring mixed-width vCPUs worked unexpectedly");
+	ret = add_2vcpus_init_2vcpus(&init1, &init2);
+	TEST_ASSERT(ret != 0,
+		    "Configuring mixed-width vCPUs worked unexpectedly");
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index c9d9e513ca04..7b47ae4f952e 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -18,11 +18,40 @@
 #include "test_util.h"
 #include "perf_test_util.h"
 #include "guest_modes.h"
+
 #ifdef __aarch64__
 #include "aarch64/vgic.h"
 
 #define GICD_BASE_GPA			0x8000000ULL
 #define GICR_BASE_GPA			0x80A0000ULL
+
+static int gic_fd;
+
+static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
+{
+	/*
+	 * The test can still run even if hardware does not support GICv3, as it
+	 * is only an optimization to reduce guest exits.
+	 */
+	gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+}
+
+static void arch_cleanup_vm(struct kvm_vm *vm)
+{
+	if (gic_fd > 0)
+		close(gic_fd);
+}
+
+#else /* __aarch64__ */
+
+static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
+{
+}
+
+static void arch_cleanup_vm(struct kvm_vm *vm)
+{
+}
+
 #endif
 
 /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
@@ -206,9 +235,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
-#ifdef __aarch64__
-	vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
-#endif
+	arch_setup_vm(vm, nr_vcpus);
 
 	/* Start the iterations */
 	iteration = 0;
@@ -302,6 +329,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	}
 
 	free_bitmaps(bitmaps, p->slots);
+	arch_cleanup_vm(vm);
 	perf_test_destroy_vm(vm);
 }
 
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
index dc284c6bdbc3..eca5c622efd2 100644
--- a/tools/testing/selftests/kvm/include/riscv/processor.h
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -101,7 +101,9 @@ static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id,
 #define PGTBL_PTE_WRITE_SHIFT			2
 #define PGTBL_PTE_READ_MASK			0x0000000000000002ULL
 #define PGTBL_PTE_READ_SHIFT			1
-#define PGTBL_PTE_PERM_MASK			(PGTBL_PTE_EXECUTE_MASK | \
+#define PGTBL_PTE_PERM_MASK			(PGTBL_PTE_ACCESSED_MASK | \
+						 PGTBL_PTE_DIRTY_MASK | \
+						 PGTBL_PTE_EXECUTE_MASK | \
 						 PGTBL_PTE_WRITE_MASK | \
 						 PGTBL_PTE_READ_MASK)
 #define PGTBL_PTE_VALID_MASK			0x0000000000000001ULL
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index d377f2603d98..3961487a4870 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -268,7 +268,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 		core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6);
 }
 
-static void guest_hang(void)
+static void __aligned(16) guest_hang(void)
 {
 	while (1)
 		;
diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c
index b019e0b8221c..84fda3b49073 100644
--- a/tools/testing/selftests/mqueue/mq_perf_tests.c
+++ b/tools/testing/selftests/mqueue/mq_perf_tests.c
@@ -180,6 +180,9 @@ void shutdown(int exit_val, char *err_cause, int line_no)
 	if (in_shutdown++)
 		return;
 
+	/* Free the cpu_set allocated using CPU_ALLOC in main function */
+	CPU_FREE(cpu_set);
+
 	for (i = 0; i < num_cpus_to_pin; i++)
 		if (cpu_threads[i]) {
 			pthread_kill(cpu_threads[i], SIGUSR1);
@@ -551,6 +554,12 @@ int main(int argc, char *argv[])
 		perror("sysconf(_SC_NPROCESSORS_ONLN)");
 		exit(1);
 	}
+
+	if (getuid() != 0)
+		ksft_exit_skip("Not running as root, but almost all tests "
+			"require root in order to modify\nsystem settings.  "
+			"Exiting.\n");
+
 	cpus_online = min(MAX_CPUS, sysconf(_SC_NPROCESSORS_ONLN));
 	cpu_set = CPU_ALLOC(cpus_online);
 	if (cpu_set == NULL) {
@@ -589,7 +598,7 @@ int main(int argc, char *argv[])
 						cpu_set)) {
 					fprintf(stderr, "Any given CPU may "
 						"only be given once.\n");
-					exit(1);
+					goto err_code;
 				} else
 					CPU_SET_S(cpus_to_pin[cpu],
 						  cpu_set_size, cpu_set);
@@ -607,7 +616,7 @@ int main(int argc, char *argv[])
 				queue_path = malloc(strlen(option) + 2);
 				if (!queue_path) {
 					perror("malloc()");
-					exit(1);
+					goto err_code;
 				}
 				queue_path[0] = '/';
 				queue_path[1] = 0;
@@ -622,17 +631,12 @@ int main(int argc, char *argv[])
 		fprintf(stderr, "Must pass at least one CPU to continuous "
 			"mode.\n");
 		poptPrintUsage(popt_context, stderr, 0);
-		exit(1);
+		goto err_code;
 	} else if (!continuous_mode) {
 		num_cpus_to_pin = 1;
 		cpus_to_pin[0] = cpus_online - 1;
 	}
 
-	if (getuid() != 0)
-		ksft_exit_skip("Not running as root, but almost all tests "
-			"require root in order to modify\nsystem settings.  "
-			"Exiting.\n");
-
 	max_msgs = fopen(MAX_MSGS, "r+");
 	max_msgsize = fopen(MAX_MSGSIZE, "r+");
 	if (!max_msgs)
@@ -740,4 +744,9 @@ int main(int argc, char *argv[])
 			sleep(1);
 	}
 	shutdown(0, "", 0);
+
+err_code:
+	CPU_FREE(cpu_set);
+	exit(1);
+
 }
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 3fe2515aa616..af7f6e6ff182 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -36,6 +36,7 @@ TEST_PROGS += srv6_end_dt4_l3vpn_test.sh
 TEST_PROGS += srv6_end_dt6_l3vpn_test.sh
 TEST_PROGS += vrf_strict_mode_test.sh
 TEST_PROGS += arp_ndisc_evict_nocarrier.sh
+TEST_PROGS += ndisc_unsolicited_na_test.sh
 TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh
 TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh
 TEST_GEN_FILES =  socket nettest
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 4f70baad867d..bbe3b379927a 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -20,6 +20,7 @@ SRC_IP6=2001:db8:1::3
 DEV_ADDR=192.51.100.1
 DEV_ADDR6=2001:db8:1::1
 DEV=dummy0
+TESTS="fib_rule6 fib_rule4"
 
 log_test()
 {
@@ -316,7 +317,16 @@ fi
 # start clean
 cleanup &> /dev/null
 setup
-run_fibrule_tests
+for t in $TESTS
+do
+	case $t in
+	fib_rule6_test|fib_rule6)		fib_rule6_test;;
+	fib_rule4_test|fib_rule4)		fib_rule4_test;;
+
+	help) echo "Test names: $TESTS"; exit 0;;
+
+	esac
+done
 cleanup
 
 if [ "$TESTS" != "none" ]; then
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 8fa97ae9af9e..ae80c2aef577 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -2,6 +2,7 @@
 
 TEST_PROGS = bridge_igmp.sh \
 	bridge_locked_port.sh \
+	bridge_mdb.sh \
 	bridge_port_isolation.sh \
 	bridge_sticky_fdb.sh \
 	bridge_vlan_aware.sh \
diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
new file mode 100755
index 000000000000..b1ba6876dd86
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
@@ -0,0 +1,103 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Verify that adding host mdb entries work as intended for all types of
+# multicast filters: ipv4, ipv6, and mac
+
+ALL_TESTS="mdb_add_del_test"
+NUM_NETIFS=2
+
+TEST_GROUP_IP4="225.1.2.3"
+TEST_GROUP_IP6="ff02::42"
+TEST_GROUP_MAC="01:00:01:c0:ff:ee"
+
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+switch_create()
+{
+	# Enable multicast filtering
+	ip link add dev br0 type bridge mcast_snooping 1
+
+	ip link set dev $swp1 master br0
+
+	ip link set dev br0 up
+	ip link set dev $swp1 up
+}
+
+switch_destroy()
+{
+	ip link set dev $swp1 down
+	ip link del dev br0
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	vrf_prepare
+
+	h1_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+do_mdb_add_del()
+{
+	local group=$1
+	local flag=$2
+
+	RET=0
+	bridge mdb add dev br0 port br0 grp $group $flag 2>/dev/null
+	check_err $? "Failed adding $group to br0, port br0"
+
+	if [ -z "$flag" ]; then
+	    flag="temp"
+	fi
+
+	bridge mdb show dev br0 | grep $group | grep -q $flag 2>/dev/null
+	check_err $? "$group not added with $flag flag"
+
+	bridge mdb del dev br0 port br0 grp $group 2>/dev/null
+	check_err $? "Failed deleting $group from br0, port br0"
+
+	bridge mdb show dev br0 | grep -q $group >/dev/null
+	check_err_fail 1 $? "$group still in mdb after delete"
+
+	log_test "MDB add/del group $group to bridge port br0"
+}
+
+mdb_add_del_test()
+{
+	do_mdb_add_del $TEST_GROUP_MAC permanent
+	do_mdb_add_del $TEST_GROUP_IP4
+	do_mdb_add_del $TEST_GROUP_IP6
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 664b9ecaf228..5386c826e46a 100644..100755
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -27,6 +27,9 @@ INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600}
 LOW_AGEING_TIME=${LOW_AGEING_TIME:=1000}
 REQUIRE_JQ=${REQUIRE_JQ:=yes}
 REQUIRE_MZ=${REQUIRE_MZ:=yes}
+REQUIRE_MTOOLS=${REQUIRE_MTOOLS:=no}
+STABLE_MAC_ADDRS=${STABLE_MAC_ADDRS:=no}
+TCPDUMP_EXTRA_FLAGS=${TCPDUMP_EXTRA_FLAGS:=}
 
 relative_path="${BASH_SOURCE%/*}"
 if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
@@ -159,6 +162,12 @@ fi
 if [[ "$REQUIRE_MZ" = "yes" ]]; then
 	require_command $MZ
 fi
+if [[ "$REQUIRE_MTOOLS" = "yes" ]]; then
+	# https://github.com/vladimiroltean/mtools/
+	# patched for IPv6 support
+	require_command msend
+	require_command mreceive
+fi
 
 if [[ ! -v NUM_NETIFS ]]; then
 	echo "SKIP: importer does not define \"NUM_NETIFS\""
@@ -214,10 +223,41 @@ create_netif()
 	esac
 }
 
+declare -A MAC_ADDR_ORIG
+mac_addr_prepare()
+{
+	local new_addr=
+	local dev=
+
+	for ((i = 1; i <= NUM_NETIFS; ++i)); do
+		dev=${NETIFS[p$i]}
+		new_addr=$(printf "00:01:02:03:04:%02x" $i)
+
+		MAC_ADDR_ORIG["$dev"]=$(ip -j link show dev $dev | jq -e '.[].address')
+		# Strip quotes
+		MAC_ADDR_ORIG["$dev"]=${MAC_ADDR_ORIG["$dev"]//\"/}
+		ip link set dev $dev address $new_addr
+	done
+}
+
+mac_addr_restore()
+{
+	local dev=
+
+	for ((i = 1; i <= NUM_NETIFS; ++i)); do
+		dev=${NETIFS[p$i]}
+		ip link set dev $dev address ${MAC_ADDR_ORIG["$dev"]}
+	done
+}
+
 if [[ "$NETIF_CREATE" = "yes" ]]; then
 	create_netif
 fi
 
+if [[ "$STABLE_MAC_ADDRS" = "yes" ]]; then
+	mac_addr_prepare
+fi
+
 for ((i = 1; i <= NUM_NETIFS; ++i)); do
 	ip link show dev ${NETIFS[p$i]} &> /dev/null
 	if [[ $? -ne 0 ]]; then
@@ -503,6 +543,10 @@ pre_cleanup()
 		echo "Pausing before cleanup, hit any key to continue"
 		read
 	fi
+
+	if [[ "$STABLE_MAC_ADDRS" = "yes" ]]; then
+		mac_addr_restore
+	fi
 }
 
 vrf_prepare()
@@ -824,6 +868,15 @@ mac_get()
 	ip -j link show dev $if_name | jq -r '.[]["address"]'
 }
 
+ipv6_lladdr_get()
+{
+	local if_name=$1
+
+	ip -j addr show dev $if_name | \
+		jq -r '.[]["addr_info"][] | select(.scope == "link").local' | \
+		head -1
+}
+
 bridge_ageing_time_get()
 {
 	local bridge=$1
@@ -1349,13 +1402,17 @@ stop_traffic()
 	{ kill %% && wait %%; } 2>/dev/null
 }
 
+declare -A cappid
+declare -A capfile
+declare -A capout
+
 tcpdump_start()
 {
 	local if_name=$1; shift
 	local ns=$1; shift
 
-	capfile=$(mktemp)
-	capout=$(mktemp)
+	capfile[$if_name]=$(mktemp)
+	capout[$if_name]=$(mktemp)
 
 	if [ -z $ns ]; then
 		ns_cmd=""
@@ -1369,27 +1426,35 @@ tcpdump_start()
 		capuser="-Z $SUDO_USER"
 	fi
 
-	$ns_cmd tcpdump -e -n -Q in -i $if_name \
-		-s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 &
-	cappid=$!
+	$ns_cmd tcpdump $TCPDUMP_EXTRA_FLAGS -e -n -Q in -i $if_name \
+		-s 65535 -B 32768 $capuser -w ${capfile[$if_name]} \
+		> "${capout[$if_name]}" 2>&1 &
+	cappid[$if_name]=$!
 
 	sleep 1
 }
 
 tcpdump_stop()
 {
-	$ns_cmd kill $cappid
+	local if_name=$1
+	local pid=${cappid[$if_name]}
+
+	$ns_cmd kill "$pid" && wait "$pid"
 	sleep 1
 }
 
 tcpdump_cleanup()
 {
-	rm $capfile $capout
+	local if_name=$1
+
+	rm ${capfile[$if_name]} ${capout[$if_name]}
 }
 
 tcpdump_show()
 {
-	tcpdump -e -n -r $capfile 2>&1
+	local if_name=$1
+
+	tcpdump -e -n -r ${capfile[$if_name]} 2>&1
 }
 
 # return 0 if the packet wasn't seen on host2_if or 1 if it was
@@ -1499,6 +1564,37 @@ brmcast_check_sg_state()
 	done
 }
 
+mc_join()
+{
+	local if_name=$1
+	local group=$2
+	local vrf_name=$(master_name_get $if_name)
+
+	# We don't care about actual reception, just about joining the
+	# IP multicast group and adding the L2 address to the device's
+	# MAC filtering table
+	ip vrf exec $vrf_name \
+		mreceive -g $group -I $if_name > /dev/null 2>&1 &
+	mreceive_pid=$!
+
+	sleep 1
+}
+
+mc_leave()
+{
+	kill "$mreceive_pid" && wait "$mreceive_pid"
+}
+
+mc_send()
+{
+	local if_name=$1
+	local groups=$2
+	local vrf_name=$(master_name_get $if_name)
+
+	ip vrf exec $vrf_name \
+		msend -g $groups -I $if_name -c 1 > /dev/null 2>&1
+}
+
 start_ip_monitor()
 {
 	local mtype=$1; shift
diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
new file mode 100755
index 000000000000..c5b0cbc85b3e
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -0,0 +1,299 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="standalone bridge"
+NUM_NETIFS=2
+PING_COUNT=1
+REQUIRE_MTOOLS=yes
+REQUIRE_MZ=no
+
+source lib.sh
+
+H1_IPV4="192.0.2.1"
+H2_IPV4="192.0.2.2"
+H1_IPV6="2001:db8:1::1"
+H2_IPV6="2001:db8:1::2"
+
+BRIDGE_ADDR="00:00:de:ad:be:ee"
+MACVLAN_ADDR="00:00:de:ad:be:ef"
+UNKNOWN_UC_ADDR1="de:ad:be:ef:ee:03"
+UNKNOWN_UC_ADDR2="de:ad:be:ef:ee:04"
+UNKNOWN_UC_ADDR3="de:ad:be:ef:ee:05"
+JOINED_IPV4_MC_ADDR="225.1.2.3"
+UNKNOWN_IPV4_MC_ADDR1="225.1.2.4"
+UNKNOWN_IPV4_MC_ADDR2="225.1.2.5"
+UNKNOWN_IPV4_MC_ADDR3="225.1.2.6"
+JOINED_IPV6_MC_ADDR="ff2e::0102:0304"
+UNKNOWN_IPV6_MC_ADDR1="ff2e::0102:0305"
+UNKNOWN_IPV6_MC_ADDR2="ff2e::0102:0306"
+UNKNOWN_IPV6_MC_ADDR3="ff2e::0102:0307"
+
+JOINED_MACV4_MC_ADDR="01:00:5e:01:02:03"
+UNKNOWN_MACV4_MC_ADDR1="01:00:5e:01:02:04"
+UNKNOWN_MACV4_MC_ADDR2="01:00:5e:01:02:05"
+UNKNOWN_MACV4_MC_ADDR3="01:00:5e:01:02:06"
+JOINED_MACV6_MC_ADDR="33:33:01:02:03:04"
+UNKNOWN_MACV6_MC_ADDR1="33:33:01:02:03:05"
+UNKNOWN_MACV6_MC_ADDR2="33:33:01:02:03:06"
+UNKNOWN_MACV6_MC_ADDR3="33:33:01:02:03:07"
+
+NON_IP_MC="01:02:03:04:05:06"
+NON_IP_PKT="00:04 48:45:4c:4f"
+BC="ff:ff:ff:ff:ff:ff"
+
+# Disable promisc to ensure we don't receive unknown MAC DA packets
+export TCPDUMP_EXTRA_FLAGS="-pl"
+
+h1=${NETIFS[p1]}
+h2=${NETIFS[p2]}
+
+send_non_ip()
+{
+	local if_name=$1
+	local smac=$2
+	local dmac=$3
+
+	$MZ -q $if_name "$dmac $smac $NON_IP_PKT"
+}
+
+send_uc_ipv4()
+{
+	local if_name=$1
+	local dmac=$2
+
+	ip neigh add $H2_IPV4 lladdr $dmac dev $if_name
+	ping_do $if_name $H2_IPV4
+	ip neigh del $H2_IPV4 dev $if_name
+}
+
+check_rcv()
+{
+	local if_name=$1
+	local type=$2
+	local pattern=$3
+	local should_receive=$4
+	local should_fail=
+
+	[ $should_receive = true ] && should_fail=0 || should_fail=1
+	RET=0
+
+	tcpdump_show $if_name | grep -q "$pattern"
+
+	check_err_fail "$should_fail" "$?" "reception"
+
+	log_test "$if_name: $type"
+}
+
+mc_route_prepare()
+{
+	local if_name=$1
+	local vrf_name=$(master_name_get $if_name)
+
+	ip route add 225.100.1.0/24 dev $if_name vrf $vrf_name
+	ip -6 route add ff2e::/64 dev $if_name vrf $vrf_name
+}
+
+mc_route_destroy()
+{
+	local if_name=$1
+	local vrf_name=$(master_name_get $if_name)
+
+	ip route del 225.100.1.0/24 dev $if_name vrf $vrf_name
+	ip -6 route del ff2e::/64 dev $if_name vrf $vrf_name
+}
+
+run_test()
+{
+	local rcv_if_name=$1
+	local smac=$(mac_get $h1)
+	local rcv_dmac=$(mac_get $rcv_if_name)
+
+	tcpdump_start $rcv_if_name
+
+	mc_route_prepare $h1
+	mc_route_prepare $rcv_if_name
+
+	send_uc_ipv4 $h1 $rcv_dmac
+	send_uc_ipv4 $h1 $MACVLAN_ADDR
+	send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR1
+
+	ip link set dev $rcv_if_name promisc on
+	send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR2
+	mc_send $h1 $UNKNOWN_IPV4_MC_ADDR2
+	mc_send $h1 $UNKNOWN_IPV6_MC_ADDR2
+	ip link set dev $rcv_if_name promisc off
+
+	mc_join $rcv_if_name $JOINED_IPV4_MC_ADDR
+	mc_send $h1 $JOINED_IPV4_MC_ADDR
+	mc_leave
+
+	mc_join $rcv_if_name $JOINED_IPV6_MC_ADDR
+	mc_send $h1 $JOINED_IPV6_MC_ADDR
+	mc_leave
+
+	mc_send $h1 $UNKNOWN_IPV4_MC_ADDR1
+	mc_send $h1 $UNKNOWN_IPV6_MC_ADDR1
+
+	ip link set dev $rcv_if_name allmulticast on
+	send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR3
+	mc_send $h1 $UNKNOWN_IPV4_MC_ADDR3
+	mc_send $h1 $UNKNOWN_IPV6_MC_ADDR3
+	ip link set dev $rcv_if_name allmulticast off
+
+	mc_route_destroy $rcv_if_name
+	mc_route_destroy $h1
+
+	sleep 1
+
+	tcpdump_stop $rcv_if_name
+
+	check_rcv $rcv_if_name "Unicast IPv4 to primary MAC address" \
+		"$smac > $rcv_dmac, ethertype IPv4 (0x0800)" \
+		true
+
+	check_rcv $rcv_if_name "Unicast IPv4 to macvlan MAC address" \
+		"$smac > $MACVLAN_ADDR, ethertype IPv4 (0x0800)" \
+		true
+
+	check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \
+		"$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \
+		false
+
+	check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address, promisc" \
+		"$smac > $UNKNOWN_UC_ADDR2, ethertype IPv4 (0x0800)" \
+		true
+
+	check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address, allmulti" \
+		"$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \
+		false
+
+	check_rcv $rcv_if_name "Multicast IPv4 to joined group" \
+		"$smac > $JOINED_MACV4_MC_ADDR, ethertype IPv4 (0x0800)" \
+		true
+
+	check_rcv $rcv_if_name "Multicast IPv4 to unknown group" \
+		"$smac > $UNKNOWN_MACV4_MC_ADDR1, ethertype IPv4 (0x0800)" \
+		false
+
+	check_rcv $rcv_if_name "Multicast IPv4 to unknown group, promisc" \
+		"$smac > $UNKNOWN_MACV4_MC_ADDR2, ethertype IPv4 (0x0800)" \
+		true
+
+	check_rcv $rcv_if_name "Multicast IPv4 to unknown group, allmulti" \
+		"$smac > $UNKNOWN_MACV4_MC_ADDR3, ethertype IPv4 (0x0800)" \
+		true
+
+	check_rcv $rcv_if_name "Multicast IPv6 to joined group" \
+		"$smac > $JOINED_MACV6_MC_ADDR, ethertype IPv6 (0x86dd)" \
+		true
+
+	check_rcv $rcv_if_name "Multicast IPv6 to unknown group" \
+		"$smac > $UNKNOWN_MACV6_MC_ADDR1, ethertype IPv6 (0x86dd)" \
+		false
+
+	check_rcv $rcv_if_name "Multicast IPv6 to unknown group, promisc" \
+		"$smac > $UNKNOWN_MACV6_MC_ADDR2, ethertype IPv6 (0x86dd)" \
+		true
+
+	check_rcv $rcv_if_name "Multicast IPv6 to unknown group, allmulti" \
+		"$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \
+		true
+
+	tcpdump_cleanup $rcv_if_name
+}
+
+h1_create()
+{
+	simple_if_init $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+h2_destroy()
+{
+	simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+bridge_create()
+{
+	ip link add br0 type bridge
+	ip link set br0 address $BRIDGE_ADDR
+	ip link set br0 up
+
+	ip link set $h2 master br0
+	ip link set $h2 up
+
+	simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64
+}
+
+bridge_destroy()
+{
+	simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64
+
+	ip link del br0
+}
+
+standalone()
+{
+	h1_create
+	h2_create
+
+	ip link add link $h2 name macvlan0 type macvlan mode private
+	ip link set macvlan0 address $MACVLAN_ADDR
+	ip link set macvlan0 up
+
+	run_test $h2
+
+	ip link del macvlan0
+
+	h2_destroy
+	h1_destroy
+}
+
+bridge()
+{
+	h1_create
+	bridge_create
+
+	ip link add link br0 name macvlan0 type macvlan mode private
+	ip link set macvlan0 address $MACVLAN_ADDR
+	ip link set macvlan0 up
+
+	run_test br0
+
+	ip link del macvlan0
+
+	bridge_destroy
+	h1_destroy
+}
+
+cleanup()
+{
+	pre_cleanup
+	vrf_cleanup
+}
+
+setup_prepare()
+{
+	vrf_prepare
+	# setup_wait() needs this
+	ip link set $h1 up
+	ip link set $h2 up
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/no_forwarding.sh b/tools/testing/selftests/net/forwarding/no_forwarding.sh
new file mode 100755
index 000000000000..af3b398d13f0
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/no_forwarding.sh
@@ -0,0 +1,261 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="standalone two_bridges one_bridge_two_pvids"
+NUM_NETIFS=4
+
+source lib.sh
+
+h1=${NETIFS[p1]}
+h2=${NETIFS[p3]}
+swp1=${NETIFS[p2]}
+swp2=${NETIFS[p4]}
+
+H1_IPV4="192.0.2.1"
+H2_IPV4="192.0.2.2"
+H1_IPV6="2001:db8:1::1"
+H2_IPV6="2001:db8:1::2"
+
+IPV4_ALLNODES="224.0.0.1"
+IPV6_ALLNODES="ff02::1"
+MACV4_ALLNODES="01:00:5e:00:00:01"
+MACV6_ALLNODES="33:33:00:00:00:01"
+NON_IP_MC="01:02:03:04:05:06"
+NON_IP_PKT="00:04 48:45:4c:4f"
+BC="ff:ff:ff:ff:ff:ff"
+
+# The full 4K VLAN space is too much to check, so strategically pick some
+# values which should provide reasonable coverage
+vids=(0 1 2 5 10 20 50 100 200 500 1000 1000 2000 4000 4094)
+
+send_non_ip()
+{
+	local if_name=$1
+	local smac=$2
+	local dmac=$3
+
+	$MZ -q $if_name "$dmac $smac $NON_IP_PKT"
+}
+
+send_uc_ipv4()
+{
+	local if_name=$1
+	local dmac=$2
+
+	ip neigh add $H2_IPV4 lladdr $dmac dev $if_name
+	ping_do $if_name $H2_IPV4
+	ip neigh del $H2_IPV4 dev $if_name
+}
+
+send_mc_ipv4()
+{
+	local if_name=$1
+
+	ping_do $if_name $IPV4_ALLNODES "-I $if_name"
+}
+
+send_uc_ipv6()
+{
+	local if_name=$1
+	local dmac=$2
+
+	ip -6 neigh add $H2_IPV6 lladdr $dmac dev $if_name
+	ping6_do $if_name $H2_IPV6
+	ip -6 neigh del $H2_IPV6 dev $if_name
+}
+
+send_mc_ipv6()
+{
+	local if_name=$1
+
+	ping6_do $if_name $IPV6_ALLNODES%$if_name
+}
+
+check_rcv()
+{
+	local if_name=$1
+	local type=$2
+	local pattern=$3
+	local should_fail=1
+
+	RET=0
+
+	tcpdump_show $if_name | grep -q "$pattern"
+
+	check_err_fail "$should_fail" "$?" "reception"
+
+	log_test "$type"
+}
+
+run_test()
+{
+	local test_name="$1"
+	local smac=$(mac_get $h1)
+	local dmac=$(mac_get $h2)
+	local h1_ipv6_lladdr=$(ipv6_lladdr_get $h1)
+	local vid=
+
+	echo "$test_name: Sending packets"
+
+	tcpdump_start $h2
+
+	send_non_ip $h1 $smac $dmac
+	send_non_ip $h1 $smac $NON_IP_MC
+	send_non_ip $h1 $smac $BC
+	send_uc_ipv4 $h1 $dmac
+	send_mc_ipv4 $h1
+	send_uc_ipv6 $h1 $dmac
+	send_mc_ipv6 $h1
+
+	for vid in "${vids[@]}"; do
+		vlan_create $h1 $vid
+		simple_if_init $h1.$vid $H1_IPV4/24 $H1_IPV6/64
+
+		send_non_ip $h1.$vid $smac $dmac
+		send_non_ip $h1.$vid $smac $NON_IP_MC
+		send_non_ip $h1.$vid $smac $BC
+		send_uc_ipv4 $h1.$vid $dmac
+		send_mc_ipv4 $h1.$vid
+		send_uc_ipv6 $h1.$vid $dmac
+		send_mc_ipv6 $h1.$vid
+
+		simple_if_fini $h1.$vid $H1_IPV4/24 $H1_IPV6/64
+		vlan_destroy $h1 $vid
+	done
+
+	sleep 1
+
+	echo "$test_name: Checking which packets were received"
+
+	tcpdump_stop $h2
+
+	check_rcv $h2 "$test_name: Unicast non-IP untagged" \
+		"$smac > $dmac, 802.3, length 4:"
+
+	check_rcv $h2 "$test_name: Multicast non-IP untagged" \
+		"$smac > $NON_IP_MC, 802.3, length 4:"
+
+	check_rcv $h2 "$test_name: Broadcast non-IP untagged" \
+		"$smac > $BC, 802.3, length 4:"
+
+	check_rcv $h2 "$test_name: Unicast IPv4 untagged" \
+		"$smac > $dmac, ethertype IPv4 (0x0800)"
+
+	check_rcv $h2 "$test_name: Multicast IPv4 untagged" \
+		"$smac > $MACV4_ALLNODES, ethertype IPv4 (0x0800).*: $H1_IPV4 > $IPV4_ALLNODES"
+
+	check_rcv $h2 "$test_name: Unicast IPv6 untagged" \
+		"$smac > $dmac, ethertype IPv6 (0x86dd).*8: $H1_IPV6 > $H2_IPV6"
+
+	check_rcv $h2 "$test_name: Multicast IPv6 untagged" \
+		"$smac > $MACV6_ALLNODES, ethertype IPv6 (0x86dd).*: $h1_ipv6_lladdr > $IPV6_ALLNODES"
+
+	for vid in "${vids[@]}"; do
+		check_rcv $h2 "$test_name: Unicast non-IP VID $vid" \
+			"$smac > $dmac, ethertype 802.1Q (0x8100).*vlan $vid,.*length 4"
+
+		check_rcv $h2 "$test_name: Multicast non-IP VID $vid" \
+			"$smac > $NON_IP_MC, ethertype 802.1Q (0x8100).*vlan $vid,.*length 4"
+
+		check_rcv $h2 "$test_name: Broadcast non-IP VID $vid" \
+			"$smac > $BC, ethertype 802.1Q (0x8100).*vlan $vid,.*length 4"
+
+		check_rcv $h2 "$test_name: Unicast IPv4 VID $vid" \
+			"$smac > $dmac, ethertype 802.1Q (0x8100).*vlan $vid,.*ethertype IPv4 (0x0800), $H1_IPV4 > $H2_IPV4"
+
+		check_rcv $h2 "$test_name: Multicast IPv4 VID $vid" \
+			"$smac > $MACV4_ALLNODES, ethertype 802.1Q (0x8100).*vlan $vid,.*ethertype IPv4 (0x0800), $H1_IPV4 > $IPV4_ALLNODES"
+
+		check_rcv $h2 "$test_name: Unicast IPv6 VID $vid" \
+			"$smac > $dmac, ethertype 802.1Q (0x8100).*vlan $vid,.*ethertype IPv6 (0x86dd), $H1_IPV6 > $H2_IPV6"
+
+		check_rcv $h2 "$test_name: Multicast IPv6 VID $vid" \
+			"$smac > $MACV6_ALLNODES, ethertype 802.1Q (0x8100).*vlan $vid,.*ethertype IPv6 (0x86dd), $h1_ipv6_lladdr > $IPV6_ALLNODES"
+	done
+
+	tcpdump_cleanup $h2
+}
+
+standalone()
+{
+	run_test "Standalone switch ports"
+}
+
+two_bridges()
+{
+	ip link add br0 type bridge && ip link set br0 up
+	ip link add br1 type bridge && ip link set br1 up
+	ip link set $swp1 master br0
+	ip link set $swp2 master br1
+
+	run_test "Switch ports in different bridges"
+
+	ip link del br1
+	ip link del br0
+}
+
+one_bridge_two_pvids()
+{
+	ip link add br0 type bridge vlan_filtering 1 vlan_default_pvid 0
+	ip link set br0 up
+	ip link set $swp1 master br0
+	ip link set $swp2 master br0
+
+	bridge vlan add dev $swp1 vid 1 pvid untagged
+	bridge vlan add dev $swp1 vid 2 pvid untagged
+
+	run_test "Switch ports in VLAN-aware bridge with different PVIDs"
+
+	ip link del br0
+}
+
+h1_create()
+{
+	simple_if_init $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+h2_destroy()
+{
+	simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+setup_prepare()
+{
+	vrf_prepare
+
+	h1_create
+	h2_create
+	# we call simple_if_init from the test itself, but setup_wait expects
+	# that we call it from here, and waits until the interfaces are up
+	ip link set dev $swp1 up
+	ip link set dev $swp2 up
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index d36b7da5082a..38021a0dd527 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -12,6 +12,9 @@ CONFIG_NF_TABLES=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XTABLES=m
 CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NETFILTER_XT_MATCH_LENGTH=m
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
+CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NFT_TPROXY=m
 CONFIG_NFT_SOCKET=m
@@ -19,3 +22,8 @@ CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTIPLE_TABLES=y
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_PEDIT=m
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_CLS_FW=m
+CONFIG_NET_SCH_INGRESS=m
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index ff821025d309..9dd43d7d957b 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -71,6 +71,43 @@ chk_msk_remote_key_nr()
 		__chk_nr "grep -c remote_key" $*
 }
 
+__chk_listen()
+{
+	local filter="$1"
+	local expected=$2
+
+	shift 2
+	msg=$*
+
+	nr=$(ss -N $ns -Ml "$filter" | grep -c LISTEN)
+	printf "%-50s" "$msg"
+
+	if [ $nr != $expected ]; then
+		echo "[ fail ] expected $expected found $nr"
+		ret=$test_cnt
+	else
+		echo "[  ok  ]"
+	fi
+}
+
+chk_msk_listen()
+{
+	lport=$1
+	local msg="check for listen socket"
+
+	# destination port search should always return empty list
+	__chk_listen "dport $lport" 0 "listen match for dport $lport"
+
+	# should return 'our' mptcp listen socket
+	__chk_listen "sport $lport" 1 "listen match for sport $lport"
+
+	__chk_listen "src inet:0.0.0.0:$lport" 1 "listen match for saddr and sport"
+
+	__chk_listen "" 1 "all listen sockets"
+
+	nr=$(ss -Ml $filter | wc -l)
+}
+
 # $1: ns, $2: port
 wait_local_port_listen()
 {
@@ -113,6 +150,7 @@ echo "a" | \
 				0.0.0.0 >/dev/null &
 wait_local_port_listen $ns 10000
 chk_msk_nr 0 "no msk on netns creation"
+chk_msk_listen 10000
 
 echo "b" | \
 	timeout ${timeout_test} \
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 7314257d248a..e5c8fc2816fb 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -266,6 +266,58 @@ reset_with_allow_join_id0()
 	ip netns exec $ns2 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns2_enable
 }
 
+# Modify TCP payload without corrupting the TCP packet
+#
+# This rule inverts a 8-bit word at byte offset 148 for the 2nd TCP ACK packets
+# carrying enough data.
+# Once it is done, the TCP Checksum field is updated so the packet is still
+# considered as valid at the TCP level.
+# Because the MPTCP checksum, covering the TCP options and data, has not been
+# updated, the modification will be detected and an MP_FAIL will be emitted:
+# what we want to validate here without corrupting "random" MPTCP options.
+#
+# To avoid having tc producing this pr_info() message for each TCP ACK packets
+# not carrying enough data:
+#
+#     tc action pedit offset 162 out of bounds
+#
+# Netfilter is used to mark packets with enough data.
+reset_with_fail()
+{
+	reset "${1}" || return 1
+
+	ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=1
+	ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=1
+
+	check_invert=1
+	validate_checksum=1
+	local i="$2"
+	local ip="${3:-4}"
+	local tables
+
+	tables="iptables"
+	if [ $ip -eq 6 ]; then
+		tables="ip6tables"
+	fi
+
+	ip netns exec $ns2 $tables \
+		-t mangle \
+		-A OUTPUT \
+		-o ns2eth$i \
+		-p tcp \
+		-m length --length 150:9999 \
+		-m statistic --mode nth --packet 1 --every 99999 \
+		-j MARK --set-mark 42 || exit 1
+
+	tc -n $ns2 qdisc add dev ns2eth$i clsact || exit 1
+	tc -n $ns2 filter add dev ns2eth$i egress \
+		protocol ip prio 1000 \
+		handle 42 fw \
+		action pedit munge offset 148 u8 invert \
+		pipe csum tcp \
+		index 100 || exit 1
+}
+
 fail_test()
 {
 	ret=1
@@ -961,6 +1013,7 @@ chk_csum_nr()
 	local csum_ns2=${2:-0}
 	local count
 	local dump_stats
+	local extra_msg=""
 	local allow_multi_errors_ns1=0
 	local allow_multi_errors_ns2=0
 
@@ -976,6 +1029,9 @@ chk_csum_nr()
 	printf "%-${nr_blank}s %s" " " "sum"
 	count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}')
 	[ -z "$count" ] && count=0
+	if [ "$count" != "$csum_ns1" ]; then
+		extra_msg="$extra_msg ns1=$count"
+	fi
 	if { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } ||
 	   { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then
 		echo "[fail] got $count data checksum error[s] expected $csum_ns1"
@@ -987,28 +1043,58 @@ chk_csum_nr()
 	echo -n " - csum  "
 	count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}')
 	[ -z "$count" ] && count=0
+	if [ "$count" != "$csum_ns2" ]; then
+		extra_msg="$extra_msg ns2=$count"
+	fi
 	if { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } ||
 	   { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then
 		echo "[fail] got $count data checksum error[s] expected $csum_ns2"
 		fail_test
 		dump_stats=1
 	else
-		echo "[ ok ]"
+		echo -n "[ ok ]"
 	fi
 	[ "${dump_stats}" = 1 ] && dump_stats
+
+	echo "$extra_msg"
 }
 
 chk_fail_nr()
 {
 	local fail_tx=$1
 	local fail_rx=$2
+	local ns_invert=${3:-""}
 	local count
 	local dump_stats
+	local ns_tx=$ns1
+	local ns_rx=$ns2
+	local extra_msg=""
+	local allow_tx_lost=0
+	local allow_rx_lost=0
+
+	if [[ $ns_invert = "invert" ]]; then
+		ns_tx=$ns2
+		ns_rx=$ns1
+		extra_msg=" invert"
+	fi
+
+	if [[ "${fail_tx}" = "-"* ]]; then
+		allow_tx_lost=1
+		fail_tx=${fail_tx:1}
+	fi
+	if [[ "${fail_rx}" = "-"* ]]; then
+		allow_rx_lost=1
+		fail_rx=${fail_rx:1}
+	fi
 
 	printf "%-${nr_blank}s %s" " " "ftx"
-	count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}')
+	count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}')
 	[ -z "$count" ] && count=0
 	if [ "$count" != "$fail_tx" ]; then
+		extra_msg="$extra_msg,tx=$count"
+	fi
+	if { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } ||
+	   { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then
 		echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx"
 		fail_test
 		dump_stats=1
@@ -1017,17 +1103,23 @@ chk_fail_nr()
 	fi
 
 	echo -n " - failrx"
-	count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}')
+	count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}')
 	[ -z "$count" ] && count=0
 	if [ "$count" != "$fail_rx" ]; then
+		extra_msg="$extra_msg,rx=$count"
+	fi
+	if { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } ||
+	   { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then
 		echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx"
 		fail_test
 		dump_stats=1
 	else
-		echo "[ ok ]"
+		echo -n "[ ok ]"
 	fi
 
 	[ "${dump_stats}" = 1 ] && dump_stats
+
+	echo "$extra_msg"
 }
 
 chk_fclose_nr()
@@ -1106,6 +1198,38 @@ chk_rst_nr()
 	echo "$extra_msg"
 }
 
+chk_infi_nr()
+{
+	local infi_tx=$1
+	local infi_rx=$2
+	local count
+	local dump_stats
+
+	printf "%-${nr_blank}s %s" " " "itx"
+	count=$(ip netns exec $ns2 nstat -as | grep InfiniteMapTx | awk '{print $2}')
+	[ -z "$count" ] && count=0
+	if [ "$count" != "$infi_tx" ]; then
+		echo "[fail] got $count infinite map[s] TX expected $infi_tx"
+		fail_test
+		dump_stats=1
+	else
+		echo -n "[ ok ]"
+	fi
+
+	echo -n " - infirx"
+	count=$(ip netns exec $ns1 nstat -as | grep InfiniteMapRx | awk '{print $2}')
+	[ -z "$count" ] && count=0
+	if [ "$count" != "$infi_rx" ]; then
+		echo "[fail] got $count infinite map[s] RX expected $infi_rx"
+		fail_test
+		dump_stats=1
+	else
+		echo "[ ok ]"
+	fi
+
+	[ "${dump_stats}" = 1 ] && dump_stats
+}
+
 chk_join_nr()
 {
 	local syn_nr=$1
@@ -1115,7 +1239,8 @@ chk_join_nr()
 	local csum_ns2=${5:-0}
 	local fail_nr=${6:-0}
 	local rst_nr=${7:-0}
-	local corrupted_pkts=${8:-0}
+	local infi_nr=${8:-0}
+	local corrupted_pkts=${9:-0}
 	local count
 	local dump_stats
 	local with_cookie
@@ -1166,10 +1291,11 @@ chk_join_nr()
 		echo "[ ok ]"
 	fi
 	[ "${dump_stats}" = 1 ] && dump_stats
-	if [ $checksum -eq 1 ]; then
+	if [ $validate_checksum -eq 1 ]; then
 		chk_csum_nr $csum_ns1 $csum_ns2
 		chk_fail_nr $fail_nr $fail_nr
 		chk_rst_nr $rst_nr $rst_nr
+		chk_infi_nr $infi_nr $infi_nr
 	fi
 }
 
@@ -2556,6 +2682,22 @@ fastclose_tests()
 	fi
 }
 
+pedit_action_pkts()
+{
+	tc -n $ns2 -j -s action show action pedit index 100 | \
+		sed 's/.*"packets":\([0-9]\+\),.*/\1/'
+}
+
+fail_tests()
+{
+	# single subflow
+	if reset_with_fail "Infinite map" 1; then
+		run_tests $ns1 $ns2 10.0.1.1 128
+		chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)"
+		chk_fail_nr 1 -1 invert
+	fi
+}
+
 implicit_tests()
 {
 	# userspace pm type prevents add_addr
@@ -2624,6 +2766,7 @@ all_tests_sorted=(
 	d@deny_join_id0_tests
 	m@fullmesh_tests
 	z@fastclose_tests
+	F@fail_tests
 	I@implicit_tests
 )
 
diff --git a/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh b/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh
new file mode 100755
index 000000000000..f508657ee126
--- /dev/null
+++ b/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh
@@ -0,0 +1,255 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test is for the accept_unsolicited_na feature to
+# enable RFC9131 behaviour. The following is the test-matrix.
+# drop   accept  fwding                   behaviour
+# ----   ------  ------  ----------------------------------------------
+#    1        X       X  Drop NA packet and don't pass up the stack
+#    0        0       X  Pass NA packet up the stack, don't update NC
+#    0        1       0  Pass NA packet up the stack, don't update NC
+#    0        1       1  Pass NA packet up the stack, and add a STALE
+#                           NC entry
+
+ret=0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+PAUSE_ON_FAIL=no
+PAUSE=no
+
+HOST_NS="ns-host"
+ROUTER_NS="ns-router"
+
+HOST_INTF="veth-host"
+ROUTER_INTF="veth-router"
+
+ROUTER_ADDR="2000:20::1"
+HOST_ADDR="2000:20::2"
+SUBNET_WIDTH=64
+ROUTER_ADDR_WITH_MASK="${ROUTER_ADDR}/${SUBNET_WIDTH}"
+HOST_ADDR_WITH_MASK="${HOST_ADDR}/${SUBNET_WIDTH}"
+
+IP_HOST="ip -6 -netns ${HOST_NS}"
+IP_HOST_EXEC="ip netns exec ${HOST_NS}"
+IP_ROUTER="ip -6 -netns ${ROUTER_NS}"
+IP_ROUTER_EXEC="ip netns exec ${ROUTER_NS}"
+
+tcpdump_stdout=
+tcpdump_stderr=
+
+log_test()
+{
+	local rc=$1
+	local expected=$2
+	local msg="$3"
+
+	if [ ${rc} -eq ${expected} ]; then
+		printf "    TEST: %-60s  [ OK ]\n" "${msg}"
+		nsuccess=$((nsuccess+1))
+	else
+		ret=1
+		nfail=$((nfail+1))
+		printf "    TEST: %-60s  [FAIL]\n" "${msg}"
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+		echo
+			echo "hit enter to continue, 'q' to quit"
+			read a
+			[ "$a" = "q" ] && exit 1
+		fi
+	fi
+
+	if [ "${PAUSE}" = "yes" ]; then
+		echo
+		echo "hit enter to continue, 'q' to quit"
+		read a
+		[ "$a" = "q" ] && exit 1
+	fi
+}
+
+setup()
+{
+	set -e
+
+	local drop_unsolicited_na=$1
+	local accept_unsolicited_na=$2
+	local forwarding=$3
+
+	# Setup two namespaces and a veth tunnel across them.
+	# On end of the tunnel is a router and the other end is a host.
+	ip netns add ${HOST_NS}
+	ip netns add ${ROUTER_NS}
+	${IP_ROUTER} link add ${ROUTER_INTF} type veth \
+                peer name ${HOST_INTF} netns ${HOST_NS}
+
+	# Enable IPv6 on both router and host, and configure static addresses.
+	# The router here is the DUT
+	# Setup router configuration as specified by the arguments.
+	# forwarding=0 case is to check that a non-router
+	# doesn't add neighbour entries.
+        ROUTER_CONF=net.ipv6.conf.${ROUTER_INTF}
+	${IP_ROUTER_EXEC} sysctl -qw \
+                ${ROUTER_CONF}.forwarding=${forwarding}
+	${IP_ROUTER_EXEC} sysctl -qw \
+                ${ROUTER_CONF}.drop_unsolicited_na=${drop_unsolicited_na}
+	${IP_ROUTER_EXEC} sysctl -qw \
+                ${ROUTER_CONF}.accept_unsolicited_na=${accept_unsolicited_na}
+	${IP_ROUTER_EXEC} sysctl -qw ${ROUTER_CONF}.disable_ipv6=0
+	${IP_ROUTER} addr add ${ROUTER_ADDR_WITH_MASK} dev ${ROUTER_INTF}
+
+	# Turn on ndisc_notify on host interface so that
+	# the host sends unsolicited NAs.
+	HOST_CONF=net.ipv6.conf.${HOST_INTF}
+	${IP_HOST_EXEC} sysctl -qw ${HOST_CONF}.ndisc_notify=1
+	${IP_HOST_EXEC} sysctl -qw ${HOST_CONF}.disable_ipv6=0
+	${IP_HOST} addr add ${HOST_ADDR_WITH_MASK} dev ${HOST_INTF}
+
+	set +e
+}
+
+start_tcpdump() {
+	set -e
+	tcpdump_stdout=`mktemp`
+	tcpdump_stderr=`mktemp`
+	${IP_ROUTER_EXEC} timeout 15s \
+                tcpdump --immediate-mode -tpni ${ROUTER_INTF} -c 1 \
+                "icmp6 && icmp6[0] == 136 && src ${HOST_ADDR}" \
+                > ${tcpdump_stdout} 2> /dev/null
+	set +e
+}
+
+cleanup_tcpdump()
+{
+	set -e
+	[[ ! -z  ${tcpdump_stdout} ]] && rm -f ${tcpdump_stdout}
+	[[ ! -z  ${tcpdump_stderr} ]] && rm -f ${tcpdump_stderr}
+	tcpdump_stdout=
+	tcpdump_stderr=
+	set +e
+}
+
+cleanup()
+{
+	cleanup_tcpdump
+	ip netns del ${HOST_NS}
+	ip netns del ${ROUTER_NS}
+}
+
+link_up() {
+	set -e
+	${IP_ROUTER} link set dev ${ROUTER_INTF} up
+	${IP_HOST} link set dev ${HOST_INTF} up
+	set +e
+}
+
+verify_ndisc() {
+	local drop_unsolicited_na=$1
+	local accept_unsolicited_na=$2
+	local forwarding=$3
+
+	neigh_show_output=$(${IP_ROUTER} neigh show \
+                to ${HOST_ADDR} dev ${ROUTER_INTF} nud stale)
+	if [ ${drop_unsolicited_na} -eq 0 ] && \
+			[ ${accept_unsolicited_na} -eq 1 ] && \
+			[ ${forwarding} -eq 1 ]; then
+		# Neighbour entry expected to be present for 011 case
+		[[ ${neigh_show_output} ]]
+	else
+		# Neighbour entry expected to be absent for all other cases
+		[[ -z ${neigh_show_output} ]]
+	fi
+}
+
+test_unsolicited_na_common()
+{
+	# Setup the test bed, but keep links down
+	setup $1 $2 $3
+
+	# Bring the link up, wait for the NA,
+	# and add a delay to ensure neighbour processing is done.
+	link_up
+	start_tcpdump
+
+	# Verify the neighbour table
+	verify_ndisc $1 $2 $3
+
+}
+
+test_unsolicited_na_combination() {
+	test_unsolicited_na_common $1 $2 $3
+	test_msg=("test_unsolicited_na: "
+		"drop_unsolicited_na=$1 "
+		"accept_unsolicited_na=$2 "
+		"forwarding=$3")
+	log_test $? 0 "${test_msg[*]}"
+	cleanup
+}
+
+test_unsolicited_na_combinations() {
+	# Args: drop_unsolicited_na accept_unsolicited_na forwarding
+
+	# Expect entry
+	test_unsolicited_na_combination 0 1 1
+
+	# Expect no entry
+	test_unsolicited_na_combination 0 0 0
+	test_unsolicited_na_combination 0 0 1
+	test_unsolicited_na_combination 0 1 0
+	test_unsolicited_na_combination 1 0 0
+	test_unsolicited_na_combination 1 0 1
+	test_unsolicited_na_combination 1 1 0
+	test_unsolicited_na_combination 1 1 1
+}
+
+###############################################################################
+# usage
+
+usage()
+{
+	cat <<EOF
+usage: ${0##*/} OPTS
+        -p          Pause on fail
+        -P          Pause after each test before cleanup
+EOF
+}
+
+###############################################################################
+# main
+
+while getopts :pPh o
+do
+	case $o in
+		p) PAUSE_ON_FAIL=yes;;
+		P) PAUSE=yes;;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
+# make sure we don't pause twice
+[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no
+
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit $ksft_skip;
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v tcpdump)" ]; then
+	echo "SKIP: Could not run test without tcpdump tool"
+	exit $ksft_skip
+fi
+
+# start clean
+cleanup &> /dev/null
+
+test_unsolicited_na_combinations
+
+printf "\nTests passed: %3d\n" ${nsuccess}
+printf "Tests failed: %3d\n"   ${nfail}
+
+exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh
index 695a1958723f..fd76b69635a4 100755
--- a/tools/testing/selftests/netfilter/nft_fib.sh
+++ b/tools/testing/selftests/netfilter/nft_fib.sh
@@ -66,6 +66,20 @@ table inet filter {
 EOF
 }
 
+load_pbr_ruleset() {
+	local netns=$1
+
+ip netns exec ${netns} nft -f /dev/stdin <<EOF
+table inet filter {
+	chain forward {
+		type filter hook forward priority raw;
+		fib saddr . iif oif gt 0 accept
+		log drop
+	}
+}
+EOF
+}
+
 load_ruleset_count() {
 	local netns=$1
 
@@ -219,4 +233,40 @@ sleep 2
 ip netns exec ${ns1} ping -c 3 -q 1c3::c01d > /dev/null
 check_fib_counter 3 ${nsrouter} 1c3::c01d || exit 1
 
+# delete all rules
+ip netns exec ${ns1} nft flush ruleset
+ip netns exec ${ns2} nft flush ruleset
+ip netns exec ${nsrouter} nft flush ruleset
+
+ip -net ${ns1} addr add 10.0.1.99/24 dev eth0
+ip -net ${ns1} addr add dead:1::99/64 dev eth0
+
+ip -net ${ns1} addr del 10.0.2.99/24 dev eth0
+ip -net ${ns1} addr del dead:2::99/64 dev eth0
+
+ip -net ${nsrouter} addr del dead:2::1/64 dev veth0
+
+# ... pbr ruleset for the router, check iif+oif.
+load_pbr_ruleset ${nsrouter}
+if [ $? -ne 0 ] ; then
+	echo "SKIP: Could not load fib forward ruleset"
+	exit $ksft_skip
+fi
+
+ip -net ${nsrouter} rule add from all table 128
+ip -net ${nsrouter} rule add from all iif veth0 table 129
+ip -net ${nsrouter} route add table 128 to 10.0.1.0/24 dev veth0
+ip -net ${nsrouter} route add table 129 to 10.0.2.0/24 dev veth1
+
+# drop main ipv4 table
+ip -net ${nsrouter} -4 rule delete table main
+
+test_ping 10.0.2.99 dead:2::99
+if [ $? -ne 0 ] ; then
+	ip -net ${nsrouter} nft list ruleset
+	echo "FAIL: fib mismatch in pbr setup"
+	exit 1
+fi
+
+echo "PASS: fib expression forward check with policy based routing"
 exit 0
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