Merge tag 'v5.9-rc2' into drm-misc-fixes

Backmerge requested by Tomi for a fix to omap inconsistent
locking state issue, and because we need at least v5.9-rc2 now.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

296 files changed, 17341 insertions, 1661 deletions

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 1195bd85af38..9018f45d631d 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -6,6 +6,7 @@ TARGETS += breakpoints
 TARGETS += capabilities
 TARGETS += cgroup
 TARGETS += clone3
+TARGETS += core
 TARGETS += cpufreq
 TARGETS += cpu-hotplug
 TARGETS += drivers/dma-buf
@@ -15,6 +16,7 @@ TARGETS += filesystems
 TARGETS += filesystems/binderfs
 TARGETS += filesystems/epoll
 TARGETS += firmware
+TARGETS += fpu
 TARGETS += ftrace
 TARGETS += futex
 TARGETS += gpio
@@ -30,6 +32,7 @@ TARGETS += lkdtm
 TARGETS += membarrier
 TARGETS += memfd
 TARGETS += memory-hotplug
+TARGETS += mincore
 TARGETS += mount
 TARGETS += mqueue
 TARGETS += net
@@ -54,6 +57,7 @@ TARGETS += splice
 TARGETS += static_keys
 TARGETS += sync
 TARGETS += sysctl
+TARGETS += tc-testing
 TARGETS += timens
 ifneq (1, $(quicktest))
 TARGETS += timers
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 1bb204cee853..9a0946ddb705 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -6,7 +6,6 @@ test_lpm_map
 test_tag
 FEATURE-DUMP.libbpf
 fixdep
-test_align
 test_dev_cgroup
 /test_progs*
 test_tcpbpf_user
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 22aaec74ea0a..fc946b7ac288 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -32,7 +32,7 @@ LDLIBS += -lcap -lelf -lz -lrt -lpthread
 
 # Order correspond to 'make run_tests' order
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
+	test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
 	test_cgroup_storage \
 	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl \
@@ -102,7 +102,7 @@ endif
 OVERRIDE_TARGETS := 1
 override define CLEAN
 	$(call msg,CLEAN)
-	$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
+	$(Q)$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
 endef
 
 include ../lib.mk
@@ -111,6 +111,7 @@ SCRATCH_DIR := $(OUTPUT)/tools
 BUILD_DIR := $(SCRATCH_DIR)/build
 INCLUDE_DIR := $(SCRATCH_DIR)/include
 BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a
+RESOLVE_BTFIDS := $(BUILD_DIR)/resolve_btfids/resolve_btfids
 
 # Define simple and short `make test_progs`, `make test_sysctl`, etc targets
 # to build individual tests.
@@ -122,26 +123,32 @@ $(notdir $(TEST_GEN_PROGS)						\
 	 $(TEST_GEN_PROGS_EXTENDED)					\
 	 $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ;
 
+$(OUTPUT)/%.o: %.c
+	$(call msg,CC,,$@)
+	$(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@
+
 $(OUTPUT)/%:%.c
 	$(call msg,BINARY,,$@)
-	$(LINK.c) $^ $(LDLIBS) -o $@
+	$(Q)$(LINK.c) $^ $(LDLIBS) -o $@
 
 $(OUTPUT)/urandom_read: urandom_read.c
 	$(call msg,BINARY,,$@)
-	$(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id
+	$(Q)$(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id
 
 $(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ)
 	$(call msg,CC,,$@)
-	$(CC) -c $(CFLAGS) -o $@ $<
+	$(Q)$(CC) -c $(CFLAGS) -o $@ $<
 
-VMLINUX_BTF_PATHS := $(if $(O),$(O)/vmlinux)				\
+VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
 		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
 		     ../../../../vmlinux				\
 		     /sys/kernel/btf/vmlinux				\
 		     /boot/vmlinux-$(shell uname -r)
-VMLINUX_BTF := $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+
+DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool
 
-$(OUTPUT)/runqslower: $(BPFOBJ)
+$(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL)
 	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower	\
 		    OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF)   \
 		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) &&	\
@@ -163,7 +170,6 @@ $(OUTPUT)/test_netcnt: cgroup_helpers.c
 $(OUTPUT)/test_sock_fields: cgroup_helpers.c
 $(OUTPUT)/test_sysctl: cgroup_helpers.c
 
-DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool
 BPFTOOL ?= $(DEFAULT_BPFTOOL)
 $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    $(BPFOBJ) | $(BUILD_DIR)/bpftool
@@ -177,13 +183,28 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
 		    DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
 
-$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR):
+$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(BUILD_DIR)/resolve_btfids $(INCLUDE_DIR):
 	$(call msg,MKDIR,,$@)
-	mkdir -p $@
+	$(Q)mkdir -p $@
 
 $(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) | $(BPFTOOL) $(INCLUDE_DIR)
+ifeq ($(VMLINUX_H),)
 	$(call msg,GEN,,$@)
-	$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+else
+	$(call msg,CP,,$@)
+	$(Q)cp "$(VMLINUX_H)" $@
+endif
+
+$(RESOLVE_BTFIDS): $(BPFOBJ) | $(BUILD_DIR)/resolve_btfids	\
+		       $(TOOLSDIR)/bpf/resolve_btfids/main.c	\
+		       $(TOOLSDIR)/lib/rbtree.c			\
+		       $(TOOLSDIR)/lib/zalloc.c			\
+		       $(TOOLSDIR)/lib/string.c			\
+		       $(TOOLSDIR)/lib/ctype.c			\
+		       $(TOOLSDIR)/lib/str_error_r.c
+	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids	\
+		OUTPUT=$(BUILD_DIR)/resolve_btfids/ BPFOBJ=$(BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by
 # '-target bpf'. This fixes "missing" files on some architectures/distros,
@@ -221,28 +242,28 @@ $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
 # $4 - LDFLAGS
 define CLANG_BPF_BUILD_RULE
 	$(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
-	($(CLANG) $3 -O2 -target bpf -emit-llvm				\
+	$(Q)($(CLANG) $3 -O2 -target bpf -emit-llvm			\
 		-c $1 -o - || echo "BPF obj compilation failed") | 	\
 	$(LLC) -mattr=dwarfris -march=bpf -mcpu=v3 $4 -filetype=obj -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
 define CLANG_NOALU32_BPF_BUILD_RULE
 	$(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
-	($(CLANG) $3 -O2 -target bpf -emit-llvm				\
+	$(Q)($(CLANG) $3 -O2 -target bpf -emit-llvm			\
 		-c $1 -o - || echo "BPF obj compilation failed") | 	\
 	$(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC
 define CLANG_NATIVE_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	($(CLANG) $3 -O2 -emit-llvm					\
+	$(Q)($(CLANG) $3 -O2 -emit-llvm					\
 		-c $1 -o - || echo "BPF obj compilation failed") | 	\
 	$(LLC) -march=bpf -mcpu=v3 $4 -filetype=obj -o $2
 endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
 	$(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
-	$(BPF_GCC) $3 $4 -O2 -c $1 -o $2
+	$(Q)$(BPF_GCC) $3 $4 -O2 -c $1 -o $2
 endef
 
 SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
@@ -284,7 +305,7 @@ ifeq ($($(TRUNNER_OUTPUT)-dir),)
 $(TRUNNER_OUTPUT)-dir := y
 $(TRUNNER_OUTPUT):
 	$$(call msg,MKDIR,,$$@)
-	mkdir -p $$@
+	$(Q)mkdir -p $$@
 endif
 
 # ensure we set up BPF objects generation rule just once for a given
@@ -304,7 +325,7 @@ $(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h:			\
 		      $(TRUNNER_OUTPUT)/%.o				\
 		      | $(BPFTOOL) $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
-	$$(BPFTOOL) gen skeleton $$< > $$@
+	$(Q)$$(BPFTOOL) gen skeleton $$< > $$@
 endif
 
 # ensure we set up tests.h header generation rule just once
@@ -328,7 +349,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o:			\
 		      $(TRUNNER_BPF_SKELS)				\
 		      $$(BPFOBJ) | $(TRUNNER_OUTPUT)
 	$$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
-	cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
+	$(Q)cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
 
 $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		       %.c						\
@@ -336,20 +357,22 @@ $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		       $(TRUNNER_TESTS_HDR)				\
 		       $$(BPFOBJ) | $(TRUNNER_OUTPUT)
 	$$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@)
-	$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@
+	$(Q)$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@
 
 # only copy extra resources if in flavored build
 $(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT)
 ifneq ($2,)
 	$$(call msg,EXT-COPY,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES))
-	cp -a $$^ $(TRUNNER_OUTPUT)/
+	$(Q)cp -a $$^ $(TRUNNER_OUTPUT)/
 endif
 
 $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS)			\
 			     $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ)		\
+			     $(RESOLVE_BTFIDS)				\
 			     | $(TRUNNER_BINARY)-extras
 	$$(call msg,BINARY,,$$@)
-	$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
+	$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
+	$(Q)$(RESOLVE_BTFIDS) --no-fail --btf btf_data.o $$@
 
 endef
 
@@ -402,17 +425,17 @@ verifier/tests.h: verifier/*.c
 		) > verifier/tests.h)
 $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT)
 	$(call msg,BINARY,,$@)
-	$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
 
 # Make sure we are able to include and link libbpf against c++.
 $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
 	$(call msg,CXX,,$@)
-	$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@
+	$(Q)$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@
 
 # Benchmark runner
 $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h
 	$(call msg,CC,,$@)
-	$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@
+	$(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@
 $(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h
 $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h
 $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \
@@ -425,7 +448,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
 		 $(OUTPUT)/bench_trigger.o \
 		 $(OUTPUT)/bench_ringbufs.o
 	$(call msg,BINARY,,$@)
-	$(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS)
+	$(Q)$(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS)
 
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR)			\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
diff --git a/tools/testing/selftests/bpf/bpf_legacy.h b/tools/testing/selftests/bpf/bpf_legacy.h
index 6f8988738bc1..719ab56cdb5d 100644
--- a/tools/testing/selftests/bpf/bpf_legacy.h
+++ b/tools/testing/selftests/bpf/bpf_legacy.h
@@ -2,20 +2,6 @@
 #ifndef __BPF_LEGACY__
 #define __BPF_LEGACY__
 
-/*
- * legacy bpf_map_def with extra fields supported only by bpf_load(), do not
- * use outside of samples/bpf
- */
-struct bpf_map_def_legacy {
-	unsigned int type;
-	unsigned int key_size;
-	unsigned int value_size;
-	unsigned int max_entries;
-	unsigned int map_flags;
-	unsigned int inner_map_idx;
-	unsigned int numa_node;
-};
-
 #define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val)		\
 	struct ____btf_map_##name {				\
 		type_key key;					\
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 0fb910df5387..033051717ba5 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -290,3 +290,26 @@ free_mem:
 	free(fhp);
 	return ret;
 }
+
+int cgroup_setup_and_join(const char *path) {
+	int cg_fd;
+
+	if (setup_cgroup_environment()) {
+		fprintf(stderr, "Failed to setup cgroup environment\n");
+		return -EINVAL;
+	}
+
+	cg_fd = create_and_get_cgroup(path);
+	if (cg_fd < 0) {
+		fprintf(stderr, "Failed to create test cgroup\n");
+		cleanup_cgroup_environment();
+		return cg_fd;
+	}
+
+	if (join_cgroup(path)) {
+		fprintf(stderr, "Failed to join cgroup\n");
+		cleanup_cgroup_environment();
+		return -EINVAL;
+	}
+	return cg_fd;
+}
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index d64bb8957090..5fe3d88e4f0d 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -9,6 +9,7 @@
 	__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
 
 
+int cgroup_setup_and_join(const char *path);
 int create_and_get_cgroup(const char *path);
 int join_cgroup(const char *path);
 int setup_cgroup_environment(void);
diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c
index e8da7b39158d..b8d6aef99db4 100644
--- a/tools/testing/selftests/bpf/get_cgroup_id_user.c
+++ b/tools/testing/selftests/bpf/get_cgroup_id_user.c
@@ -58,20 +58,10 @@ int main(int argc, char **argv)
 	int exit_code = 1;
 	char buf[256];
 
-	err = setup_cgroup_environment();
-	if (CHECK(err, "setup_cgroup_environment", "err %d errno %d\n", err,
-		  errno))
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
+	if (CHECK(cgroup_fd < 0, "cgroup_setup_and_join", "err %d errno %d\n", cgroup_fd, errno))
 		return 1;
 
-	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
-	if (CHECK(cgroup_fd < 0, "create_and_get_cgroup", "err %d errno %d\n",
-		  cgroup_fd, errno))
-		goto cleanup_cgroup_env;
-
-	err = join_cgroup(TEST_CGROUP);
-	if (CHECK(err, "join_cgroup", "err %d errno %d\n", err, errno))
-		goto cleanup_cgroup_env;
-
 	err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
 	if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno))
 		goto cleanup_cgroup_env;
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index e36dd1a1780d..f56655690f9b 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -7,8 +7,6 @@
 
 #include <arpa/inet.h>
 
-#include <sys/epoll.h>
-
 #include <linux/err.h>
 #include <linux/in.h>
 #include <linux/in6.h>
@@ -17,8 +15,13 @@
 #include "network_helpers.h"
 
 #define clean_errno() (errno == 0 ? "None" : strerror(errno))
-#define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
-	__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
+#define log_err(MSG, ...) ({						\
+			int __save = errno;				\
+			fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
+				__FILE__, __LINE__, clean_errno(),	\
+				##__VA_ARGS__);				\
+			errno = __save;					\
+})
 
 struct ipv4_packet pkt_v4 = {
 	.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
@@ -37,131 +40,169 @@ struct ipv6_packet pkt_v6 = {
 	.tcp.doff = 5,
 };
 
-int start_server_with_port(int family, int type, __u16 port)
+static int settimeo(int fd, int timeout_ms)
 {
-	struct sockaddr_storage addr = {};
-	socklen_t len;
-	int fd;
+	struct timeval timeout = { .tv_sec = 3 };
 
-	if (family == AF_INET) {
-		struct sockaddr_in *sin = (void *)&addr;
+	if (timeout_ms > 0) {
+		timeout.tv_sec = timeout_ms / 1000;
+		timeout.tv_usec = (timeout_ms % 1000) * 1000;
+	}
 
-		sin->sin_family = AF_INET;
-		sin->sin_port = htons(port);
-		len = sizeof(*sin);
-	} else {
-		struct sockaddr_in6 *sin6 = (void *)&addr;
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeout,
+		       sizeof(timeout))) {
+		log_err("Failed to set SO_RCVTIMEO");
+		return -1;
+	}
 
-		sin6->sin6_family = AF_INET6;
-		sin6->sin6_port = htons(port);
-		len = sizeof(*sin6);
+	if (setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeout,
+		       sizeof(timeout))) {
+		log_err("Failed to set SO_SNDTIMEO");
+		return -1;
 	}
 
-	fd = socket(family, type | SOCK_NONBLOCK, 0);
+	return 0;
+}
+
+#define save_errno_close(fd) ({ int __save = errno; close(fd); errno = __save; })
+
+int start_server(int family, int type, const char *addr_str, __u16 port,
+		 int timeout_ms)
+{
+	struct sockaddr_storage addr = {};
+	socklen_t len;
+	int fd;
+
+	if (make_sockaddr(family, addr_str, port, &addr, &len))
+		return -1;
+
+	fd = socket(family, type, 0);
 	if (fd < 0) {
 		log_err("Failed to create server socket");
 		return -1;
 	}
 
+	if (settimeo(fd, timeout_ms))
+		goto error_close;
+
 	if (bind(fd, (const struct sockaddr *)&addr, len) < 0) {
 		log_err("Failed to bind socket");
-		close(fd);
-		return -1;
+		goto error_close;
 	}
 
 	if (type == SOCK_STREAM) {
 		if (listen(fd, 1) < 0) {
 			log_err("Failed to listed on socket");
-			close(fd);
-			return -1;
+			goto error_close;
 		}
 	}
 
 	return fd;
+
+error_close:
+	save_errno_close(fd);
+	return -1;
 }
 
-int start_server(int family, int type)
+static int connect_fd_to_addr(int fd,
+			      const struct sockaddr_storage *addr,
+			      socklen_t addrlen)
 {
-	return start_server_with_port(family, type, 0);
-}
+	if (connect(fd, (const struct sockaddr *)addr, addrlen)) {
+		log_err("Failed to connect to server");
+		return -1;
+	}
 
-static const struct timeval timeo_sec = { .tv_sec = 3 };
-static const size_t timeo_optlen = sizeof(timeo_sec);
+	return 0;
+}
 
-int connect_to_fd(int family, int type, int server_fd)
+int connect_to_fd(int server_fd, int timeout_ms)
 {
-	int fd, save_errno;
+	struct sockaddr_storage addr;
+	struct sockaddr_in *addr_in;
+	socklen_t addrlen, optlen;
+	int fd, type;
 
-	fd = socket(family, type, 0);
-	if (fd < 0) {
-		log_err("Failed to create client socket");
+	optlen = sizeof(type);
+	if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
+		log_err("getsockopt(SOL_TYPE)");
 		return -1;
 	}
 
-	if (connect_fd_to_fd(fd, server_fd) < 0 && errno != EINPROGRESS) {
-		save_errno = errno;
-		close(fd);
-		errno = save_errno;
+	addrlen = sizeof(addr);
+	if (getsockname(server_fd, (struct sockaddr *)&addr, &addrlen)) {
+		log_err("Failed to get server addr");
 		return -1;
 	}
 
+	addr_in = (struct sockaddr_in *)&addr;
+	fd = socket(addr_in->sin_family, type, 0);
+	if (fd < 0) {
+		log_err("Failed to create client socket");
+		return -1;
+	}
+
+	if (settimeo(fd, timeout_ms))
+		goto error_close;
+
+	if (connect_fd_to_addr(fd, &addr, addrlen))
+		goto error_close;
+
 	return fd;
+
+error_close:
+	save_errno_close(fd);
+	return -1;
 }
 
-int connect_fd_to_fd(int client_fd, int server_fd)
+int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms)
 {
 	struct sockaddr_storage addr;
 	socklen_t len = sizeof(addr);
-	int save_errno;
 
-	if (setsockopt(client_fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
-		       timeo_optlen)) {
-		log_err("Failed to set SO_RCVTIMEO");
+	if (settimeo(client_fd, timeout_ms))
 		return -1;
-	}
 
 	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
 		log_err("Failed to get server addr");
 		return -1;
 	}
 
-	if (connect(client_fd, (const struct sockaddr *)&addr, len) < 0) {
-		if (errno != EINPROGRESS) {
-			save_errno = errno;
-			log_err("Failed to connect to server");
-			errno = save_errno;
-		}
+	if (connect_fd_to_addr(client_fd, &addr, len))
 		return -1;
-	}
 
 	return 0;
 }
 
-int connect_wait(int fd)
+int make_sockaddr(int family, const char *addr_str, __u16 port,
+		  struct sockaddr_storage *addr, socklen_t *len)
 {
-	struct epoll_event ev = {}, events[2];
-	int timeout_ms = 1000;
-	int efd, nfd;
-
-	efd = epoll_create1(EPOLL_CLOEXEC);
-	if (efd < 0) {
-		log_err("Failed to open epoll fd");
-		return -1;
-	}
+	if (family == AF_INET) {
+		struct sockaddr_in *sin = (void *)addr;
 
-	ev.events = EPOLLRDHUP | EPOLLOUT;
-	ev.data.fd = fd;
+		sin->sin_family = AF_INET;
+		sin->sin_port = htons(port);
+		if (addr_str &&
+		    inet_pton(AF_INET, addr_str, &sin->sin_addr) != 1) {
+			log_err("inet_pton(AF_INET, %s)", addr_str);
+			return -1;
+		}
+		if (len)
+			*len = sizeof(*sin);
+		return 0;
+	} else if (family == AF_INET6) {
+		struct sockaddr_in6 *sin6 = (void *)addr;
 
-	if (epoll_ctl(efd, EPOLL_CTL_ADD, fd, &ev) < 0) {
-		log_err("Failed to register fd=%d on epoll fd=%d", fd, efd);
-		close(efd);
-		return -1;
+		sin6->sin6_family = AF_INET6;
+		sin6->sin6_port = htons(port);
+		if (addr_str &&
+		    inet_pton(AF_INET6, addr_str, &sin6->sin6_addr) != 1) {
+			log_err("inet_pton(AF_INET6, %s)", addr_str);
+			return -1;
+		}
+		if (len)
+			*len = sizeof(*sin6);
+		return 0;
 	}
-
-	nfd = epoll_wait(efd, events, ARRAY_SIZE(events), timeout_ms);
-	if (nfd < 0)
-		log_err("Failed to wait for I/O event on epoll fd=%d", efd);
-
-	close(efd);
-	return nfd;
+	return -1;
 }
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 6a8009605670..c3728f6667e4 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -33,10 +33,11 @@ struct ipv6_packet {
 } __packed;
 extern struct ipv6_packet pkt_v6;
 
-int start_server(int family, int type);
-int start_server_with_port(int family, int type, __u16 port);
-int connect_to_fd(int family, int type, int server_fd);
-int connect_fd_to_fd(int client_fd, int server_fd);
-int connect_wait(int client_fd);
+int start_server(int family, int type, const char *addr, __u16 port,
+		 int timeout_ms);
+int connect_to_fd(int server_fd, int timeout_ms);
+int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms);
+int make_sockaddr(int family, const char *addr_str, __u16 port,
+		  struct sockaddr_storage *addr, socklen_t *len);
 
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/autoload.c b/tools/testing/selftests/bpf/prog_tests/autoload.c
new file mode 100644
index 000000000000..3693f7d133eb
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/autoload.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+#include <time.h>
+#include "test_autoload.skel.h"
+
+void test_autoload(void)
+{
+	int duration = 0, err;
+	struct test_autoload* skel;
+
+	skel = test_autoload__open_and_load();
+	/* prog3 should be broken */
+	if (CHECK(skel, "skel_open_and_load", "unexpected success\n"))
+		goto cleanup;
+
+	skel = test_autoload__open();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		goto cleanup;
+
+	/* don't load prog3 */
+	bpf_program__set_autoload(skel->progs.prog3, false);
+
+	err = test_autoload__load(skel);
+	if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err))
+		goto cleanup;
+
+	err = test_autoload__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	usleep(1);
+
+	CHECK(!skel->bss->prog1_called, "prog1", "not called\n");
+	CHECK(!skel->bss->prog2_called, "prog2", "not called\n");
+	CHECK(skel->bss->prog3_called, "prog3", "called?!\n");
+
+cleanup:
+	test_autoload__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 87c29dde1cf9..7375d9a6d242 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -5,11 +5,23 @@
 #include "bpf_iter_netlink.skel.h"
 #include "bpf_iter_bpf_map.skel.h"
 #include "bpf_iter_task.skel.h"
+#include "bpf_iter_task_stack.skel.h"
 #include "bpf_iter_task_file.skel.h"
+#include "bpf_iter_tcp4.skel.h"
+#include "bpf_iter_tcp6.skel.h"
+#include "bpf_iter_udp4.skel.h"
+#include "bpf_iter_udp6.skel.h"
 #include "bpf_iter_test_kern1.skel.h"
 #include "bpf_iter_test_kern2.skel.h"
 #include "bpf_iter_test_kern3.skel.h"
 #include "bpf_iter_test_kern4.skel.h"
+#include "bpf_iter_bpf_hash_map.skel.h"
+#include "bpf_iter_bpf_percpu_hash_map.skel.h"
+#include "bpf_iter_bpf_array_map.skel.h"
+#include "bpf_iter_bpf_percpu_array_map.skel.h"
+#include "bpf_iter_bpf_sk_storage_map.skel.h"
+#include "bpf_iter_test_kern5.skel.h"
+#include "bpf_iter_test_kern6.skel.h"
 
 static int duration;
 
@@ -106,6 +118,20 @@ static void test_task(void)
 	bpf_iter_task__destroy(skel);
 }
 
+static void test_task_stack(void)
+{
+	struct bpf_iter_task_stack *skel;
+
+	skel = bpf_iter_task_stack__open_and_load();
+	if (CHECK(!skel, "bpf_iter_task_stack__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	do_dummy_read(skel->progs.dump_task_stack);
+
+	bpf_iter_task_stack__destroy(skel);
+}
+
 static void test_task_file(void)
 {
 	struct bpf_iter_task_file *skel;
@@ -120,6 +146,62 @@ static void test_task_file(void)
 	bpf_iter_task_file__destroy(skel);
 }
 
+static void test_tcp4(void)
+{
+	struct bpf_iter_tcp4 *skel;
+
+	skel = bpf_iter_tcp4__open_and_load();
+	if (CHECK(!skel, "bpf_iter_tcp4__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	do_dummy_read(skel->progs.dump_tcp4);
+
+	bpf_iter_tcp4__destroy(skel);
+}
+
+static void test_tcp6(void)
+{
+	struct bpf_iter_tcp6 *skel;
+
+	skel = bpf_iter_tcp6__open_and_load();
+	if (CHECK(!skel, "bpf_iter_tcp6__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	do_dummy_read(skel->progs.dump_tcp6);
+
+	bpf_iter_tcp6__destroy(skel);
+}
+
+static void test_udp4(void)
+{
+	struct bpf_iter_udp4 *skel;
+
+	skel = bpf_iter_udp4__open_and_load();
+	if (CHECK(!skel, "bpf_iter_udp4__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	do_dummy_read(skel->progs.dump_udp4);
+
+	bpf_iter_udp4__destroy(skel);
+}
+
+static void test_udp6(void)
+{
+	struct bpf_iter_udp6 *skel;
+
+	skel = bpf_iter_udp6__open_and_load();
+	if (CHECK(!skel, "bpf_iter_udp6__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	do_dummy_read(skel->progs.dump_udp6);
+
+	bpf_iter_udp6__destroy(skel);
+}
+
 /* The expected string is less than 16 bytes */
 static int do_read_with_fd(int iter_fd, const char *expected,
 			   bool read_one_char)
@@ -380,6 +462,464 @@ out:
 	bpf_iter_test_kern4__destroy(skel);
 }
 
+static void test_bpf_hash_map(void)
+{
+	__u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0;
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct bpf_iter_bpf_hash_map *skel;
+	int err, i, len, map_fd, iter_fd;
+	union bpf_iter_link_info linfo;
+	__u64 val, expected_val = 0;
+	struct bpf_link *link;
+	struct key_t {
+		int a;
+		int b;
+		int c;
+	} key;
+	char buf[64];
+
+	skel = bpf_iter_bpf_hash_map__open();
+	if (CHECK(!skel, "bpf_iter_bpf_hash_map__open",
+		  "skeleton open failed\n"))
+		return;
+
+	skel->bss->in_test_mode = true;
+
+	err = bpf_iter_bpf_hash_map__load(skel);
+	if (CHECK(!skel, "bpf_iter_bpf_hash_map__load",
+		  "skeleton load failed\n"))
+		goto out;
+
+	/* iterator with hashmap2 and hashmap3 should fail */
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap2);
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
+	if (CHECK(!IS_ERR(link), "attach_iter",
+		  "attach_iter for hashmap2 unexpected succeeded\n"))
+		goto out;
+
+	linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap3);
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
+	if (CHECK(!IS_ERR(link), "attach_iter",
+		  "attach_iter for hashmap3 unexpected succeeded\n"))
+		goto out;
+
+	/* hashmap1 should be good, update map values here */
+	map_fd = bpf_map__fd(skel->maps.hashmap1);
+	for (i = 0; i < bpf_map__max_entries(skel->maps.hashmap1); i++) {
+		key.a = i + 1;
+		key.b = i + 2;
+		key.c = i + 3;
+		val = i + 4;
+		expected_key_a += key.a;
+		expected_key_b += key.b;
+		expected_key_c += key.c;
+		expected_val += val;
+
+		err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY);
+		if (CHECK(err, "map_update", "map_update failed\n"))
+			goto out;
+	}
+
+	linfo.map.map_fd = map_fd;
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	if (CHECK(skel->bss->key_sum_a != expected_key_a,
+		  "key_sum_a", "got %u expected %u\n",
+		  skel->bss->key_sum_a, expected_key_a))
+		goto close_iter;
+	if (CHECK(skel->bss->key_sum_b != expected_key_b,
+		  "key_sum_b", "got %u expected %u\n",
+		  skel->bss->key_sum_b, expected_key_b))
+		goto close_iter;
+	if (CHECK(skel->bss->val_sum != expected_val,
+		  "val_sum", "got %llu expected %llu\n",
+		  skel->bss->val_sum, expected_val))
+		goto close_iter;
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	bpf_iter_bpf_hash_map__destroy(skel);
+}
+
+static void test_bpf_percpu_hash_map(void)
+{
+	__u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0;
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct bpf_iter_bpf_percpu_hash_map *skel;
+	int err, i, j, len, map_fd, iter_fd;
+	union bpf_iter_link_info linfo;
+	__u32 expected_val = 0;
+	struct bpf_link *link;
+	struct key_t {
+		int a;
+		int b;
+		int c;
+	} key;
+	char buf[64];
+	void *val;
+
+	val = malloc(8 * bpf_num_possible_cpus());
+
+	skel = bpf_iter_bpf_percpu_hash_map__open();
+	if (CHECK(!skel, "bpf_iter_bpf_percpu_hash_map__open",
+		  "skeleton open failed\n"))
+		return;
+
+	skel->rodata->num_cpus = bpf_num_possible_cpus();
+
+	err = bpf_iter_bpf_percpu_hash_map__load(skel);
+	if (CHECK(!skel, "bpf_iter_bpf_percpu_hash_map__load",
+		  "skeleton load failed\n"))
+		goto out;
+
+	/* update map values here */
+	map_fd = bpf_map__fd(skel->maps.hashmap1);
+	for (i = 0; i < bpf_map__max_entries(skel->maps.hashmap1); i++) {
+		key.a = i + 1;
+		key.b = i + 2;
+		key.c = i + 3;
+		expected_key_a += key.a;
+		expected_key_b += key.b;
+		expected_key_c += key.c;
+
+		for (j = 0; j < bpf_num_possible_cpus(); j++) {
+			*(__u32 *)(val + j * 8) = i + j;
+			expected_val += i + j;
+		}
+
+		err = bpf_map_update_elem(map_fd, &key, val, BPF_ANY);
+		if (CHECK(err, "map_update", "map_update failed\n"))
+			goto out;
+	}
+
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.map.map_fd = map_fd;
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_hash_map, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	if (CHECK(skel->bss->key_sum_a != expected_key_a,
+		  "key_sum_a", "got %u expected %u\n",
+		  skel->bss->key_sum_a, expected_key_a))
+		goto close_iter;
+	if (CHECK(skel->bss->key_sum_b != expected_key_b,
+		  "key_sum_b", "got %u expected %u\n",
+		  skel->bss->key_sum_b, expected_key_b))
+		goto close_iter;
+	if (CHECK(skel->bss->val_sum != expected_val,
+		  "val_sum", "got %u expected %u\n",
+		  skel->bss->val_sum, expected_val))
+		goto close_iter;
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	bpf_iter_bpf_percpu_hash_map__destroy(skel);
+}
+
+static void test_bpf_array_map(void)
+{
+	__u64 val, expected_val = 0, res_first_val, first_val = 0;
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	__u32 expected_key = 0, res_first_key;
+	struct bpf_iter_bpf_array_map *skel;
+	union bpf_iter_link_info linfo;
+	int err, i, map_fd, iter_fd;
+	struct bpf_link *link;
+	char buf[64] = {};
+	int len, start;
+
+	skel = bpf_iter_bpf_array_map__open_and_load();
+	if (CHECK(!skel, "bpf_iter_bpf_array_map__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	map_fd = bpf_map__fd(skel->maps.arraymap1);
+	for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) {
+		val = i + 4;
+		expected_key += i;
+		expected_val += val;
+
+		if (i == 0)
+			first_val = val;
+
+		err = bpf_map_update_elem(map_fd, &i, &val, BPF_ANY);
+		if (CHECK(err, "map_update", "map_update failed\n"))
+			goto out;
+	}
+
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.map.map_fd = map_fd;
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_array_map, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	start = 0;
+	while ((len = read(iter_fd, buf + start, sizeof(buf) - start)) > 0)
+		start += len;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	res_first_key = *(__u32 *)buf;
+	res_first_val = *(__u64 *)(buf + sizeof(__u32));
+	if (CHECK(res_first_key != 0 || res_first_val != first_val,
+		  "bpf_seq_write",
+		  "seq_write failure: first key %u vs expected 0, "
+		  " first value %llu vs expected %llu\n",
+		  res_first_key, res_first_val, first_val))
+		goto close_iter;
+
+	if (CHECK(skel->bss->key_sum != expected_key,
+		  "key_sum", "got %u expected %u\n",
+		  skel->bss->key_sum, expected_key))
+		goto close_iter;
+	if (CHECK(skel->bss->val_sum != expected_val,
+		  "val_sum", "got %llu expected %llu\n",
+		  skel->bss->val_sum, expected_val))
+		goto close_iter;
+
+	for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) {
+		err = bpf_map_lookup_elem(map_fd, &i, &val);
+		if (CHECK(err, "map_lookup", "map_lookup failed\n"))
+			goto out;
+		if (CHECK(i != val, "invalid_val",
+			  "got value %llu expected %u\n", val, i))
+			goto out;
+	}
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	bpf_iter_bpf_array_map__destroy(skel);
+}
+
+static void test_bpf_percpu_array_map(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct bpf_iter_bpf_percpu_array_map *skel;
+	__u32 expected_key = 0, expected_val = 0;
+	union bpf_iter_link_info linfo;
+	int err, i, j, map_fd, iter_fd;
+	struct bpf_link *link;
+	char buf[64];
+	void *val;
+	int len;
+
+	val = malloc(8 * bpf_num_possible_cpus());
+
+	skel = bpf_iter_bpf_percpu_array_map__open();
+	if (CHECK(!skel, "bpf_iter_bpf_percpu_array_map__open",
+		  "skeleton open failed\n"))
+		return;
+
+	skel->rodata->num_cpus = bpf_num_possible_cpus();
+
+	err = bpf_iter_bpf_percpu_array_map__load(skel);
+	if (CHECK(!skel, "bpf_iter_bpf_percpu_array_map__load",
+		  "skeleton load failed\n"))
+		goto out;
+
+	/* update map values here */
+	map_fd = bpf_map__fd(skel->maps.arraymap1);
+	for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) {
+		expected_key += i;
+
+		for (j = 0; j < bpf_num_possible_cpus(); j++) {
+			*(__u32 *)(val + j * 8) = i + j;
+			expected_val += i + j;
+		}
+
+		err = bpf_map_update_elem(map_fd, &i, val, BPF_ANY);
+		if (CHECK(err, "map_update", "map_update failed\n"))
+			goto out;
+	}
+
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.map.map_fd = map_fd;
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_array_map, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	if (CHECK(skel->bss->key_sum != expected_key,
+		  "key_sum", "got %u expected %u\n",
+		  skel->bss->key_sum, expected_key))
+		goto close_iter;
+	if (CHECK(skel->bss->val_sum != expected_val,
+		  "val_sum", "got %u expected %u\n",
+		  skel->bss->val_sum, expected_val))
+		goto close_iter;
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	bpf_iter_bpf_percpu_array_map__destroy(skel);
+}
+
+static void test_bpf_sk_storage_map(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	int err, i, len, map_fd, iter_fd, num_sockets;
+	struct bpf_iter_bpf_sk_storage_map *skel;
+	union bpf_iter_link_info linfo;
+	int sock_fd[3] = {-1, -1, -1};
+	__u32 val, expected_val = 0;
+	struct bpf_link *link;
+	char buf[64];
+
+	skel = bpf_iter_bpf_sk_storage_map__open_and_load();
+	if (CHECK(!skel, "bpf_iter_bpf_sk_storage_map__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	map_fd = bpf_map__fd(skel->maps.sk_stg_map);
+	num_sockets = ARRAY_SIZE(sock_fd);
+	for (i = 0; i < num_sockets; i++) {
+		sock_fd[i] = socket(AF_INET6, SOCK_STREAM, 0);
+		if (CHECK(sock_fd[i] < 0, "socket", "errno: %d\n", errno))
+			goto out;
+
+		val = i + 1;
+		expected_val += val;
+
+		err = bpf_map_update_elem(map_fd, &sock_fd[i], &val,
+					  BPF_NOEXIST);
+		if (CHECK(err, "map_update", "map_update failed\n"))
+			goto out;
+	}
+
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.map.map_fd = map_fd;
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_sk_storage_map, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	if (CHECK(skel->bss->ipv6_sk_count != num_sockets,
+		  "ipv6_sk_count", "got %u expected %u\n",
+		  skel->bss->ipv6_sk_count, num_sockets))
+		goto close_iter;
+
+	if (CHECK(skel->bss->val_sum != expected_val,
+		  "val_sum", "got %u expected %u\n",
+		  skel->bss->val_sum, expected_val))
+		goto close_iter;
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	for (i = 0; i < num_sockets; i++) {
+		if (sock_fd[i] >= 0)
+			close(sock_fd[i]);
+	}
+	bpf_iter_bpf_sk_storage_map__destroy(skel);
+}
+
+static void test_rdonly_buf_out_of_bound(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct bpf_iter_test_kern5 *skel;
+	union bpf_iter_link_info linfo;
+	struct bpf_link *link;
+
+	skel = bpf_iter_test_kern5__open_and_load();
+	if (CHECK(!skel, "bpf_iter_test_kern5__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap1);
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
+	if (CHECK(!IS_ERR(link), "attach_iter", "unexpected success\n"))
+		bpf_link__destroy(link);
+
+	bpf_iter_test_kern5__destroy(skel);
+}
+
+static void test_buf_neg_offset(void)
+{
+	struct bpf_iter_test_kern6 *skel;
+
+	skel = bpf_iter_test_kern6__open_and_load();
+	if (CHECK(skel, "bpf_iter_test_kern6__open_and_load",
+		  "skeleton open_and_load unexpected success\n"))
+		bpf_iter_test_kern6__destroy(skel);
+}
+
 void test_bpf_iter(void)
 {
 	if (test__start_subtest("btf_id_or_null"))
@@ -392,8 +932,18 @@ void test_bpf_iter(void)
 		test_bpf_map();
 	if (test__start_subtest("task"))
 		test_task();
+	if (test__start_subtest("task_stack"))
+		test_task_stack();
 	if (test__start_subtest("task_file"))
 		test_task_file();
+	if (test__start_subtest("tcp4"))
+		test_tcp4();
+	if (test__start_subtest("tcp6"))
+		test_tcp6();
+	if (test__start_subtest("udp4"))
+		test_udp4();
+	if (test__start_subtest("udp6"))
+		test_udp6();
 	if (test__start_subtest("anon"))
 		test_anon_iter(false);
 	if (test__start_subtest("anon-read-one-char"))
@@ -406,4 +956,18 @@ void test_bpf_iter(void)
 		test_overflow(true, false);
 	if (test__start_subtest("prog-ret-1"))
 		test_overflow(false, true);
+	if (test__start_subtest("bpf_hash_map"))
+		test_bpf_hash_map();
+	if (test__start_subtest("bpf_percpu_hash_map"))
+		test_bpf_percpu_hash_map();
+	if (test__start_subtest("bpf_array_map"))
+		test_bpf_array_map();
+	if (test__start_subtest("bpf_percpu_array_map"))
+		test_bpf_percpu_array_map();
+	if (test__start_subtest("bpf_sk_storage_map"))
+		test_bpf_sk_storage_map();
+	if (test__start_subtest("rdonly-buf-out-of-bound"))
+		test_rdonly_buf_out_of_bound();
+	if (test__start_subtest("buf-neg-offset"))
+		test_buf_neg_offset();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
index 7afa4160416f..284d5921c345 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -159,15 +159,15 @@ void test_bpf_obj_id(void)
 		/* Check getting link info */
 		info_len = sizeof(struct bpf_link_info) * 2;
 		bzero(&link_infos[i], info_len);
-		link_infos[i].raw_tracepoint.tp_name = (__u64)&tp_name;
+		link_infos[i].raw_tracepoint.tp_name = ptr_to_u64(&tp_name);
 		link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name);
 		err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]),
 					     &link_infos[i], &info_len);
 		if (CHECK(err ||
 			  link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT ||
 			  link_infos[i].prog_id != prog_infos[i].id ||
-			  link_infos[i].raw_tracepoint.tp_name != (__u64)&tp_name ||
-			  strcmp((char *)link_infos[i].raw_tracepoint.tp_name,
+			  link_infos[i].raw_tracepoint.tp_name != ptr_to_u64(&tp_name) ||
+			  strcmp(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name),
 				 "sys_enter") ||
 			  info_len != sizeof(struct bpf_link_info),
 			  "get-link-info(fd)",
@@ -178,7 +178,7 @@ void test_bpf_obj_id(void)
 			  link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT,
 			  link_infos[i].id,
 			  link_infos[i].prog_id, prog_infos[i].id,
-			  (char *)link_infos[i].raw_tracepoint.tp_name,
+			  (const char *)u64_to_ptr(link_infos[i].raw_tracepoint.tp_name),
 			  "sys_enter"))
 			goto done;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index cb33a7ee4e04..39fb81d9daeb 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -12,15 +12,16 @@ void btf_dump_printf(void *ctx, const char *fmt, va_list args)
 static struct btf_dump_test_case {
 	const char *name;
 	const char *file;
+	bool known_ptr_sz;
 	struct btf_dump_opts opts;
 } btf_dump_test_cases[] = {
-	{"btf_dump: syntax", "btf_dump_test_case_syntax", {}},
-	{"btf_dump: ordering", "btf_dump_test_case_ordering", {}},
-	{"btf_dump: padding", "btf_dump_test_case_padding", {}},
-	{"btf_dump: packing", "btf_dump_test_case_packing", {}},
-	{"btf_dump: bitfields", "btf_dump_test_case_bitfields", {}},
-	{"btf_dump: multidim", "btf_dump_test_case_multidim", {}},
-	{"btf_dump: namespacing", "btf_dump_test_case_namespacing", {}},
+	{"btf_dump: syntax", "btf_dump_test_case_syntax", true, {}},
+	{"btf_dump: ordering", "btf_dump_test_case_ordering", false, {}},
+	{"btf_dump: padding", "btf_dump_test_case_padding", true, {}},
+	{"btf_dump: packing", "btf_dump_test_case_packing", true, {}},
+	{"btf_dump: bitfields", "btf_dump_test_case_bitfields", true, {}},
+	{"btf_dump: multidim", "btf_dump_test_case_multidim", false, {}},
+	{"btf_dump: namespacing", "btf_dump_test_case_namespacing", false, {}},
 };
 
 static int btf_dump_all_types(const struct btf *btf,
@@ -62,6 +63,18 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t)
 		goto done;
 	}
 
+	/* tests with t->known_ptr_sz have no "long" or "unsigned long" type,
+	 * so it's impossible to determine correct pointer size; but if they
+	 * do, it should be 8 regardless of host architecture, becaues BPF
+	 * target is always 64-bit
+	 */
+	if (!t->known_ptr_sz) {
+		btf__set_pointer_size(btf, 8);
+	} else {
+		CHECK(btf__pointer_size(btf) != 8, "ptr_sz", "exp %d, got %zu\n",
+		      8, btf__pointer_size(btf));
+	}
+
 	snprintf(out_file, sizeof(out_file), "/tmp/%s.output.XXXXXX", t->file);
 	fd = mkstemp(out_file);
 	if (CHECK(fd < 0, "create_tmp", "failed to create file: %d\n", fd)) {
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
index f7ee8fa377ad..6ccecbd39476 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
@@ -5,10 +5,60 @@
 
 #include "test_btf_map_in_map.skel.h"
 
+static int duration;
+
+static __u32 bpf_map_id(struct bpf_map *map)
+{
+	struct bpf_map_info info;
+	__u32 info_len = sizeof(info);
+	int err;
+
+	memset(&info, 0, info_len);
+	err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len);
+	if (err)
+		return 0;
+	return info.id;
+}
+
+/*
+ * Trigger synchronize_rcu() in kernel.
+ *
+ * ARRAY_OF_MAPS/HASH_OF_MAPS lookup/update operations trigger synchronize_rcu()
+ * if looking up an existing non-NULL element or updating the map with a valid
+ * inner map FD. Use this fact to trigger synchronize_rcu(): create map-in-map,
+ * create a trivial ARRAY map, update map-in-map with ARRAY inner map. Then
+ * cleanup. At the end, at least one synchronize_rcu() would be called.
+ */
+static int kern_sync_rcu(void)
+{
+	int inner_map_fd, outer_map_fd, err, zero = 0;
+
+	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0);
+	if (CHECK(inner_map_fd < 0, "inner_map_create", "failed %d\n", -errno))
+		return -1;
+
+	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL,
+					     sizeof(int), inner_map_fd, 1, 0);
+	if (CHECK(outer_map_fd < 0, "outer_map_create", "failed %d\n", -errno)) {
+		close(inner_map_fd);
+		return -1;
+	}
+
+	err = bpf_map_update_elem(outer_map_fd, &zero, &inner_map_fd, 0);
+	if (err)
+		err = -errno;
+	CHECK(err, "outer_map_update", "failed %d\n", err);
+	close(inner_map_fd);
+	close(outer_map_fd);
+	return err;
+}
+
 void test_btf_map_in_map(void)
 {
-	int duration = 0, err, key = 0, val;
-	struct test_btf_map_in_map* skel;
+	int err, key = 0, val, i;
+	struct test_btf_map_in_map *skel;
+	int outer_arr_fd, outer_hash_fd;
+	int fd, map1_fd, map2_fd, map1_id, map2_id;
 
 	skel = test_btf_map_in_map__open_and_load();
 	if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n"))
@@ -18,32 +68,78 @@ void test_btf_map_in_map(void)
 	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
 		goto cleanup;
 
+	map1_fd = bpf_map__fd(skel->maps.inner_map1);
+	map2_fd = bpf_map__fd(skel->maps.inner_map2);
+	outer_arr_fd = bpf_map__fd(skel->maps.outer_arr);
+	outer_hash_fd = bpf_map__fd(skel->maps.outer_hash);
+
 	/* inner1 = input, inner2 = input + 1 */
-	val = bpf_map__fd(skel->maps.inner_map1);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0);
-	val = bpf_map__fd(skel->maps.inner_map2);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0);
+	map1_fd = bpf_map__fd(skel->maps.inner_map1);
+	bpf_map_update_elem(outer_arr_fd, &key, &map1_fd, 0);
+	map2_fd = bpf_map__fd(skel->maps.inner_map2);
+	bpf_map_update_elem(outer_hash_fd, &key, &map2_fd, 0);
 	skel->bss->input = 1;
 	usleep(1);
 
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val);
+	bpf_map_lookup_elem(map1_fd, &key, &val);
 	CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1);
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val);
+	bpf_map_lookup_elem(map2_fd, &key, &val);
 	CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2);
 
 	/* inner1 = input + 1, inner2 = input */
-	val = bpf_map__fd(skel->maps.inner_map2);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0);
-	val = bpf_map__fd(skel->maps.inner_map1);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0);
+	bpf_map_update_elem(outer_arr_fd, &key, &map2_fd, 0);
+	bpf_map_update_elem(outer_hash_fd, &key, &map1_fd, 0);
 	skel->bss->input = 3;
 	usleep(1);
 
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val);
+	bpf_map_lookup_elem(map1_fd, &key, &val);
 	CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4);
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val);
+	bpf_map_lookup_elem(map2_fd, &key, &val);
 	CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3);
 
+	for (i = 0; i < 5; i++) {
+		val = i % 2 ? map1_fd : map2_fd;
+		err = bpf_map_update_elem(outer_hash_fd, &key, &val, 0);
+		if (CHECK_FAIL(err)) {
+			printf("failed to update hash_of_maps on iter #%d\n", i);
+			goto cleanup;
+		}
+		err = bpf_map_update_elem(outer_arr_fd, &key, &val, 0);
+		if (CHECK_FAIL(err)) {
+			printf("failed to update hash_of_maps on iter #%d\n", i);
+			goto cleanup;
+		}
+	}
+
+	map1_id = bpf_map_id(skel->maps.inner_map1);
+	map2_id = bpf_map_id(skel->maps.inner_map2);
+	CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n");
+	CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n");
+
+	test_btf_map_in_map__destroy(skel);
+	skel = NULL;
+
+	/* we need to either wait for or force synchronize_rcu(), before
+	 * checking for "still exists" condition, otherwise map could still be
+	 * resolvable by ID, causing false positives.
+	 *
+	 * Older kernels (5.8 and earlier) freed map only after two
+	 * synchronize_rcu()s, so trigger two, to be entirely sure.
+	 */
+	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
+	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
+
+	fd = bpf_map_get_fd_by_id(map1_id);
+	if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) {
+		close(fd);
+		goto cleanup;
+	}
+	fd = bpf_map_get_fd_by_id(map2_id);
+	if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) {
+		close(fd);
+		goto cleanup;
+	}
+
 cleanup:
 	test_btf_map_in_map__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
new file mode 100644
index 000000000000..643dfa35419c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
@@ -0,0 +1,417 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <test_progs.h>
+#include <cgroup_helpers.h>
+#include <network_helpers.h>
+
+#include "progs/cg_storage_multi.h"
+
+#include "cg_storage_multi_egress_only.skel.h"
+#include "cg_storage_multi_isolated.skel.h"
+#include "cg_storage_multi_shared.skel.h"
+
+#define PARENT_CGROUP "/cgroup_storage"
+#define CHILD_CGROUP "/cgroup_storage/child"
+
+static int duration;
+
+static bool assert_storage(struct bpf_map *map, const void *key,
+			   struct cgroup_value *expected)
+{
+	struct cgroup_value value;
+	int map_fd;
+
+	map_fd = bpf_map__fd(map);
+
+	if (CHECK(bpf_map_lookup_elem(map_fd, key, &value) < 0,
+		  "map-lookup", "errno %d", errno))
+		return true;
+	if (CHECK(memcmp(&value, expected, sizeof(struct cgroup_value)),
+		  "assert-storage", "storages differ"))
+		return true;
+
+	return false;
+}
+
+static bool assert_storage_noexist(struct bpf_map *map, const void *key)
+{
+	struct cgroup_value value;
+	int map_fd;
+
+	map_fd = bpf_map__fd(map);
+
+	if (CHECK(bpf_map_lookup_elem(map_fd, key, &value) == 0,
+		  "map-lookup", "succeeded, expected ENOENT"))
+		return true;
+	if (CHECK(errno != ENOENT,
+		  "map-lookup", "errno %d, expected ENOENT", errno))
+		return true;
+
+	return false;
+}
+
+static bool connect_send(const char *cgroup_path)
+{
+	bool res = true;
+	int server_fd = -1, client_fd = -1;
+
+	if (join_cgroup(cgroup_path))
+		goto out_clean;
+
+	server_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 0, 0);
+	if (server_fd < 0)
+		goto out_clean;
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (client_fd < 0)
+		goto out_clean;
+
+	if (send(client_fd, "message", strlen("message"), 0) < 0)
+		goto out_clean;
+
+	res = false;
+
+out_clean:
+	close(client_fd);
+	close(server_fd);
+	return res;
+}
+
+static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd)
+{
+	struct cg_storage_multi_egress_only *obj;
+	struct cgroup_value expected_cgroup_value;
+	struct bpf_cgroup_storage_key key;
+	struct bpf_link *parent_link = NULL, *child_link = NULL;
+	bool err;
+
+	key.attach_type = BPF_CGROUP_INET_EGRESS;
+
+	obj = cg_storage_multi_egress_only__open_and_load();
+	if (CHECK(!obj, "skel-load", "errno %d", errno))
+		return;
+
+	/* Attach to parent cgroup, trigger packet from child.
+	 * Assert that there is only one run and in that run the storage is
+	 * parent cgroup's storage.
+	 * Also assert that child cgroup's storage does not exist
+	 */
+	parent_link = bpf_program__attach_cgroup(obj->progs.egress,
+						 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_link), "parent-cg-attach",
+		  "err %ld", PTR_ERR(parent_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "first-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 1,
+		  "first-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 1 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP);
+	if (assert_storage_noexist(obj->maps.cgroup_storage, &key))
+		goto close_bpf_object;
+
+	/* Attach to parent and child cgroup, trigger packet from child.
+	 * Assert that there are two additional runs, one that run with parent
+	 * cgroup's storage and one with child cgroup's storage.
+	 */
+	child_link = bpf_program__attach_cgroup(obj->progs.egress,
+						child_cgroup_fd);
+	if (CHECK(IS_ERR(child_link), "child-cg-attach",
+		  "err %ld", PTR_ERR(child_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "second-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 3,
+		  "second-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 1 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+
+close_bpf_object:
+	if (!IS_ERR(parent_link))
+		bpf_link__destroy(parent_link);
+	if (!IS_ERR(child_link))
+		bpf_link__destroy(child_link);
+
+	cg_storage_multi_egress_only__destroy(obj);
+}
+
+static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd)
+{
+	struct cg_storage_multi_isolated *obj;
+	struct cgroup_value expected_cgroup_value;
+	struct bpf_cgroup_storage_key key;
+	struct bpf_link *parent_egress1_link = NULL, *parent_egress2_link = NULL;
+	struct bpf_link *child_egress1_link = NULL, *child_egress2_link = NULL;
+	struct bpf_link *parent_ingress_link = NULL, *child_ingress_link = NULL;
+	bool err;
+
+	obj = cg_storage_multi_isolated__open_and_load();
+	if (CHECK(!obj, "skel-load", "errno %d", errno))
+		return;
+
+	/* Attach to parent cgroup, trigger packet from child.
+	 * Assert that there is three runs, two with parent cgroup egress and
+	 * one with parent cgroup ingress, stored in separate parent storages.
+	 * Also assert that child cgroup's storages does not exist
+	 */
+	parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach",
+		  "err %ld", PTR_ERR(parent_egress1_link)))
+		goto close_bpf_object;
+	parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach",
+		  "err %ld", PTR_ERR(parent_egress2_link)))
+		goto close_bpf_object;
+	parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach",
+		  "err %ld", PTR_ERR(parent_ingress_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "first-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 3,
+		  "first-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP);
+	key.attach_type = BPF_CGROUP_INET_EGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.attach_type = BPF_CGROUP_INET_INGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 1 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP);
+	key.attach_type = BPF_CGROUP_INET_EGRESS;
+	if (assert_storage_noexist(obj->maps.cgroup_storage, &key))
+		goto close_bpf_object;
+	key.attach_type = BPF_CGROUP_INET_INGRESS;
+	if (assert_storage_noexist(obj->maps.cgroup_storage, &key))
+		goto close_bpf_object;
+
+	/* Attach to parent and child cgroup, trigger packet from child.
+	 * Assert that there is six additional runs, parent cgroup egresses and
+	 * ingress, child cgroup egresses and ingress.
+	 * Assert that egree and ingress storages are separate.
+	 */
+	child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach",
+		  "err %ld", PTR_ERR(child_egress1_link)))
+		goto close_bpf_object;
+	child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach",
+		  "err %ld", PTR_ERR(child_egress2_link)))
+		goto close_bpf_object;
+	child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach",
+		  "err %ld", PTR_ERR(child_ingress_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "second-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 9,
+		  "second-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP);
+	key.attach_type = BPF_CGROUP_INET_EGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 4 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.attach_type = BPF_CGROUP_INET_INGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 2 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP);
+	key.attach_type = BPF_CGROUP_INET_EGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.attach_type = BPF_CGROUP_INET_INGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 1 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+
+close_bpf_object:
+	if (!IS_ERR(parent_egress1_link))
+		bpf_link__destroy(parent_egress1_link);
+	if (!IS_ERR(parent_egress2_link))
+		bpf_link__destroy(parent_egress2_link);
+	if (!IS_ERR(parent_ingress_link))
+		bpf_link__destroy(parent_ingress_link);
+	if (!IS_ERR(child_egress1_link))
+		bpf_link__destroy(child_egress1_link);
+	if (!IS_ERR(child_egress2_link))
+		bpf_link__destroy(child_egress2_link);
+	if (!IS_ERR(child_ingress_link))
+		bpf_link__destroy(child_ingress_link);
+
+	cg_storage_multi_isolated__destroy(obj);
+}
+
+static void test_shared(int parent_cgroup_fd, int child_cgroup_fd)
+{
+	struct cg_storage_multi_shared *obj;
+	struct cgroup_value expected_cgroup_value;
+	__u64 key;
+	struct bpf_link *parent_egress1_link = NULL, *parent_egress2_link = NULL;
+	struct bpf_link *child_egress1_link = NULL, *child_egress2_link = NULL;
+	struct bpf_link *parent_ingress_link = NULL, *child_ingress_link = NULL;
+	bool err;
+
+	obj = cg_storage_multi_shared__open_and_load();
+	if (CHECK(!obj, "skel-load", "errno %d", errno))
+		return;
+
+	/* Attach to parent cgroup, trigger packet from child.
+	 * Assert that there is three runs, two with parent cgroup egress and
+	 * one with parent cgroup ingress.
+	 * Also assert that child cgroup's storage does not exist
+	 */
+	parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach",
+		  "err %ld", PTR_ERR(parent_egress1_link)))
+		goto close_bpf_object;
+	parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach",
+		  "err %ld", PTR_ERR(parent_egress2_link)))
+		goto close_bpf_object;
+	parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach",
+		  "err %ld", PTR_ERR(parent_ingress_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "first-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 3,
+		  "first-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key = get_cgroup_id(PARENT_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) {
+		.egress_pkts = 2,
+		.ingress_pkts = 1,
+	};
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key = get_cgroup_id(CHILD_CGROUP);
+	if (assert_storage_noexist(obj->maps.cgroup_storage, &key))
+		goto close_bpf_object;
+
+	/* Attach to parent and child cgroup, trigger packet from child.
+	 * Assert that there is six additional runs, parent cgroup egresses and
+	 * ingress, child cgroup egresses and ingress.
+	 */
+	child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach",
+		  "err %ld", PTR_ERR(child_egress1_link)))
+		goto close_bpf_object;
+	child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach",
+		  "err %ld", PTR_ERR(child_egress2_link)))
+		goto close_bpf_object;
+	child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach",
+		  "err %ld", PTR_ERR(child_ingress_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "second-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 9,
+		  "second-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key = get_cgroup_id(PARENT_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) {
+		.egress_pkts = 4,
+		.ingress_pkts = 2,
+	};
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key = get_cgroup_id(CHILD_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) {
+		.egress_pkts = 2,
+		.ingress_pkts = 1,
+	};
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+
+close_bpf_object:
+	if (!IS_ERR(parent_egress1_link))
+		bpf_link__destroy(parent_egress1_link);
+	if (!IS_ERR(parent_egress2_link))
+		bpf_link__destroy(parent_egress2_link);
+	if (!IS_ERR(parent_ingress_link))
+		bpf_link__destroy(parent_ingress_link);
+	if (!IS_ERR(child_egress1_link))
+		bpf_link__destroy(child_egress1_link);
+	if (!IS_ERR(child_egress2_link))
+		bpf_link__destroy(child_egress2_link);
+	if (!IS_ERR(child_ingress_link))
+		bpf_link__destroy(child_ingress_link);
+
+	cg_storage_multi_shared__destroy(obj);
+}
+
+void test_cg_storage_multi(void)
+{
+	int parent_cgroup_fd = -1, child_cgroup_fd = -1;
+
+	parent_cgroup_fd = test__join_cgroup(PARENT_CGROUP);
+	if (CHECK(parent_cgroup_fd < 0, "cg-create-parent", "errno %d", errno))
+		goto close_cgroup_fd;
+	child_cgroup_fd = create_and_get_cgroup(CHILD_CGROUP);
+	if (CHECK(child_cgroup_fd < 0, "cg-create-child", "errno %d", errno))
+		goto close_cgroup_fd;
+
+	if (test__start_subtest("egress_only"))
+		test_egress_only(parent_cgroup_fd, child_cgroup_fd);
+
+	if (test__start_subtest("isolated"))
+		test_isolated(parent_cgroup_fd, child_cgroup_fd);
+
+	if (test__start_subtest("shared"))
+		test_shared(parent_cgroup_fd, child_cgroup_fd);
+
+close_cgroup_fd:
+	close(child_cgroup_fd);
+	close(parent_cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
index 6e04f8d1d15b..4d9b514b3fd9 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
@@ -2,6 +2,7 @@
 
 #include <test_progs.h>
 #include "cgroup_helpers.h"
+#include "testing_helpers.h"
 #include "test_cgroup_link.skel.h"
 
 static __u32 duration = 0;
@@ -37,7 +38,8 @@ void test_cgroup_link(void)
 	int last_cg = ARRAY_SIZE(cgs) - 1, cg_nr = ARRAY_SIZE(cgs);
 	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, link_upd_opts);
 	struct bpf_link *links[ARRAY_SIZE(cgs)] = {}, *tmp_link;
-	__u32 prog_ids[ARRAY_SIZE(cgs)], prog_cnt = 0, attach_flags;
+	__u32 prog_ids[ARRAY_SIZE(cgs)], prog_cnt = 0, attach_flags, prog_id;
+	struct bpf_link_info info;
 	int i = 0, err, prog_fd;
 	bool detach_legacy = false;
 
@@ -219,6 +221,22 @@ void test_cgroup_link(void)
 	/* BPF programs should still get called */
 	ping_and_check(0, cg_nr);
 
+	prog_id = link_info_prog_id(links[0], &info);
+	CHECK(prog_id == 0, "link_info", "failed\n");
+	CHECK(info.cgroup.cgroup_id == 0, "cgroup_id", "unexpected %llu\n", info.cgroup.cgroup_id);
+
+	err = bpf_link__detach(links[0]);
+	if (CHECK(err, "link_detach", "failed %d\n", err))
+		goto cleanup;
+
+	/* cgroup_id should be zero in link_info */
+	prog_id = link_info_prog_id(links[0], &info);
+	CHECK(prog_id == 0, "link_info", "failed\n");
+	CHECK(info.cgroup.cgroup_id != 0, "cgroup_id", "unexpected %llu\n", info.cgroup.cgroup_id);
+
+	/* First BPF program shouldn't be called anymore */
+	ping_and_check(0, cg_nr - 1);
+
 	/* leave cgroup and remove them, don't detach programs */
 	cleanup_cgroup_environment();
 
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c
index 059047af7df3..464edc1c1708 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c
@@ -13,7 +13,7 @@ static void run_lookup_test(__u16 *g_serv_port, int out_sk)
 	socklen_t addr_len = sizeof(addr);
 	__u32 duration = 0;
 
-	serv_sk = start_server(AF_INET6, SOCK_STREAM);
+	serv_sk = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
 	if (CHECK(serv_sk < 0, "start_server", "failed to start server\n"))
 		return;
 
@@ -24,17 +24,13 @@ static void run_lookup_test(__u16 *g_serv_port, int out_sk)
 	*g_serv_port = addr.sin6_port;
 
 	/* Client outside of test cgroup should fail to connect by timeout. */
-	err = connect_fd_to_fd(out_sk, serv_sk);
+	err = connect_fd_to_fd(out_sk, serv_sk, 1000);
 	if (CHECK(!err || errno != EINPROGRESS, "connect_fd_to_fd",
 		  "unexpected result err %d errno %d\n", err, errno))
 		goto cleanup;
 
-	err = connect_wait(out_sk);
-	if (CHECK(err, "connect_wait", "unexpected result %d\n", err))
-		goto cleanup;
-
 	/* Client inside test cgroup should connect just fine. */
-	in_sk = connect_to_fd(AF_INET6, SOCK_STREAM, serv_sk);
+	in_sk = connect_to_fd(serv_sk, 0);
 	if (CHECK(in_sk < 0, "connect_to_fd", "errno %d\n", errno))
 		goto cleanup;
 
@@ -85,7 +81,7 @@ void test_cgroup_skb_sk_lookup(void)
 	 * differs from that of testing cgroup. Moving selftests process to
 	 * testing cgroup won't change cgroup id of an already created socket.
 	 */
-	out_sk = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0);
+	out_sk = socket(AF_INET6, SOCK_STREAM, 0);
 	if (CHECK_FAIL(out_sk < 0))
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
index 17bbf76812ca..9229db2f5ca5 100644
--- a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
+++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
@@ -114,7 +114,7 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type)
 		goto close_bpf_object;
 	}
 
-	fd = connect_to_fd(family, type, server_fd);
+	fd = connect_to_fd(server_fd, 0);
 	if (fd < 0) {
 		err = -1;
 		goto close_bpf_object;
@@ -137,25 +137,25 @@ void test_connect_force_port(void)
 	if (CHECK_FAIL(cgroup_fd < 0))
 		return;
 
-	server_fd = start_server_with_port(AF_INET, SOCK_STREAM, 60123);
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 60123, 0);
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_cgroup_fd;
 	CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_STREAM));
 	close(server_fd);
 
-	server_fd = start_server_with_port(AF_INET6, SOCK_STREAM, 60124);
+	server_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 60124, 0);
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_cgroup_fd;
 	CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_STREAM));
 	close(server_fd);
 
-	server_fd = start_server_with_port(AF_INET, SOCK_DGRAM, 60123);
+	server_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 60123, 0);
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_cgroup_fd;
 	CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_DGRAM));
 	close(server_fd);
 
-	server_fd = start_server_with_port(AF_INET6, SOCK_DGRAM, 60124);
+	server_fd = start_server(AF_INET6, SOCK_DGRAM, NULL, 60124, 0);
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_cgroup_fd;
 	CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_DGRAM));
diff --git a/tools/testing/selftests/bpf/prog_tests/core_extern.c b/tools/testing/selftests/bpf/prog_tests/core_extern.c
index b093787e9448..1931a158510e 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_extern.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_extern.c
@@ -159,8 +159,8 @@ void test_core_extern(void)
 		exp = (uint64_t *)&t->data;
 		for (j = 0; j < n; j++) {
 			CHECK(got[j] != exp[j], "check_res",
-			      "result #%d: expected %lx, but got %lx\n",
-			       j, exp[j], got[j]);
+			      "result #%d: expected %llx, but got %llx\n",
+			       j, (__u64)exp[j], (__u64)got[j]);
 		}
 cleanup:
 		test_core_extern__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 084ed26a7d78..a54eafc5e4b3 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -237,8 +237,8 @@
 		.union_sz = sizeof(((type *)0)->union_field),		\
 		.arr_sz = sizeof(((type *)0)->arr_field),		\
 		.arr_elem_sz = sizeof(((type *)0)->arr_field[0]),	\
-		.ptr_sz = sizeof(((type *)0)->ptr_field),		\
-		.enum_sz = sizeof(((type *)0)->enum_field),	\
+		.ptr_sz = 8, /* always 8-byte pointer for BPF */	\
+		.enum_sz = sizeof(((type *)0)->enum_field),		\
 	}
 
 #define SIZE_CASE(name) {						\
@@ -432,20 +432,20 @@ static struct core_reloc_test_case test_cases[] = {
 		.sb4 = -1,
 		.sb20 = -0x17654321,
 		.u32 = 0xBEEF,
-		.s32 = -0x3FEDCBA987654321,
+		.s32 = -0x3FEDCBA987654321LL,
 	}),
 	BITFIELDS_CASE(bitfields___bitfield_vs_int, {
-		.ub1 = 0xFEDCBA9876543210,
+		.ub1 = 0xFEDCBA9876543210LL,
 		.ub2 = 0xA6,
-		.ub7 = -0x7EDCBA987654321,
-		.sb4 = -0x6123456789ABCDE,
-		.sb20 = 0xD00D,
+		.ub7 = -0x7EDCBA987654321LL,
+		.sb4 = -0x6123456789ABCDELL,
+		.sb20 = 0xD00DLL,
 		.u32 = -0x76543,
-		.s32 = 0x0ADEADBEEFBADB0B,
+		.s32 = 0x0ADEADBEEFBADB0BLL,
 	}),
 	BITFIELDS_CASE(bitfields___just_big_enough, {
-		.ub1 = 0xF,
-		.ub2 = 0x0812345678FEDCBA,
+		.ub1 = 0xFLL,
+		.ub2 = 0x0812345678FEDCBALL,
 	}),
 	BITFIELDS_ERR_CASE(bitfields___err_too_big_bitfield),
 
diff --git a/tools/testing/selftests/bpf/prog_tests/core_retro.c b/tools/testing/selftests/bpf/prog_tests/core_retro.c
new file mode 100644
index 000000000000..6acb0e94d4d7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/core_retro.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include "test_core_retro.skel.h"
+
+void test_core_retro(void)
+{
+	int err, zero = 0, res, duration = 0, my_pid = getpid();
+	struct test_core_retro *skel;
+
+	/* load program */
+	skel = test_core_retro__open_and_load();
+	if (CHECK(!skel, "skel_load", "skeleton open/load failed\n"))
+		goto out_close;
+
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.exp_tgid_map), &zero, &my_pid, 0);
+	if (CHECK(err, "map_update", "failed to set expected PID: %d\n", errno))
+		goto out_close;
+
+	/* attach probe */
+	err = test_core_retro__attach(skel);
+	if (CHECK(err, "attach_kprobe", "err %d\n", err))
+		goto out_close;
+
+	/* trigger */
+	usleep(1);
+
+	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.results), &zero, &res);
+	if (CHECK(err, "map_lookup", "failed to lookup result: %d\n", errno))
+		goto out_close;
+
+	CHECK(res != my_pid, "pid_check", "got %d != exp %d\n", res, my_pid);
+
+out_close:
+	test_core_retro__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/endian.c b/tools/testing/selftests/bpf/prog_tests/endian.c
new file mode 100644
index 000000000000..1a11612ace6c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/endian.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+#include "test_endian.skel.h"
+
+static int duration;
+
+#define IN16 0x1234
+#define IN32 0x12345678U
+#define IN64 0x123456789abcdef0ULL
+
+#define OUT16 0x3412
+#define OUT32 0x78563412U
+#define OUT64 0xf0debc9a78563412ULL
+
+void test_endian(void)
+{
+	struct test_endian* skel;
+	struct test_endian__bss *bss;
+	int err;
+
+	skel = test_endian__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+	bss = skel->bss;
+
+	bss->in16 = IN16;
+	bss->in32 = IN32;
+	bss->in64 = IN64;
+
+	err = test_endian__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	usleep(1);
+
+	CHECK(bss->out16 != OUT16, "out16", "got 0x%llx != exp 0x%llx\n",
+	      (__u64)bss->out16, (__u64)OUT16);
+	CHECK(bss->out32 != OUT32, "out32", "got 0x%llx != exp 0x%llx\n",
+	      (__u64)bss->out32, (__u64)OUT32);
+	CHECK(bss->out64 != OUT64, "out16", "got 0x%llx != exp 0x%llx\n",
+	      (__u64)bss->out64, (__u64)OUT64);
+
+	CHECK(bss->const16 != OUT16, "const16", "got 0x%llx != exp 0x%llx\n",
+	      (__u64)bss->const16, (__u64)OUT16);
+	CHECK(bss->const32 != OUT32, "const32", "got 0x%llx != exp 0x%llx\n",
+	      (__u64)bss->const32, (__u64)OUT32);
+	CHECK(bss->const64 != OUT64, "const64", "got 0x%llx != exp 0x%llx\n",
+	      (__u64)bss->const64, (__u64)OUT64);
+cleanup:
+	test_endian__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index a895bfed55db..197d0d217b56 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -16,7 +16,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 	__u32 duration = 0, retval;
 	struct bpf_map *data_map;
 	const int zero = 0;
-	u64 *result = NULL;
+	__u64 *result = NULL;
 
 	err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC,
 			    &pkt_obj, &pkt_fd);
@@ -29,7 +29,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 
 	link = calloc(sizeof(struct bpf_link *), prog_cnt);
 	prog = calloc(sizeof(struct bpf_program *), prog_cnt);
-	result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64));
+	result = malloc((prog_cnt + 32 /* spare */) * sizeof(__u64));
 	if (CHECK(!link || !prog || !result, "alloc_memory",
 		  "failed to alloc memory"))
 		goto close_prog;
@@ -72,7 +72,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 		goto close_prog;
 
 	for (i = 0; i < prog_cnt; i++)
-		if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %ld\n",
+		if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %llu\n",
 			  result[i]))
 			goto close_prog;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index f11f187990e9..cd6dc80edf18 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -591,7 +591,7 @@ void test_flow_dissector(void)
 		CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) ||
 			   err || tattr.retval != 1,
 			   tests[i].name,
-			   "err %d errno %d retval %d duration %d size %u/%lu\n",
+			   "err %d errno %d retval %d duration %d size %u/%zu\n",
 			   err, errno, tattr.retval, tattr.duration,
 			   tattr.data_size_out, sizeof(flow_keys));
 		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c
new file mode 100644
index 000000000000..d884b2ed5bc5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#include <test_progs.h>
+#include "test_stacktrace_build_id.skel.h"
+
+void test_get_stackid_cannot_attach(void)
+{
+	struct perf_event_attr attr = {
+		/* .type = PERF_TYPE_SOFTWARE, */
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+		.precise_ip = 1,
+		.sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_BRANCH_STACK,
+		.branch_sample_type = PERF_SAMPLE_BRANCH_USER |
+			PERF_SAMPLE_BRANCH_NO_FLAGS |
+			PERF_SAMPLE_BRANCH_NO_CYCLES |
+			PERF_SAMPLE_BRANCH_CALL_STACK,
+		.sample_period = 5000,
+		.size = sizeof(struct perf_event_attr),
+	};
+	struct test_stacktrace_build_id *skel;
+	__u32 duration = 0;
+	int pmu_fd, err;
+
+	skel = test_stacktrace_build_id__open();
+	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
+		return;
+
+	/* override program type */
+	bpf_program__set_perf_event(skel->progs.oncpu);
+
+	err = test_stacktrace_build_id__load(skel);
+	if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err))
+		goto cleanup;
+
+	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+			 0 /* cpu 0 */, -1 /* group id */,
+			 0 /* flags */);
+	if (pmu_fd < 0 && (errno == ENOENT || errno == EOPNOTSUPP)) {
+		printf("%s:SKIP:cannot open PERF_COUNT_HW_CPU_CYCLES with precise_ip > 0\n",
+		       __func__);
+		test__skip();
+		goto cleanup;
+	}
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
+		  pmu_fd, errno))
+		goto cleanup;
+
+	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
+							   pmu_fd);
+	CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_no_callchain",
+	      "should have failed\n");
+	close(pmu_fd);
+
+	/* add PERF_SAMPLE_CALLCHAIN, attach should succeed */
+	attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
+
+	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+			 0 /* cpu 0 */, -1 /* group id */,
+			 0 /* flags */);
+
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
+		  pmu_fd, errno))
+		goto cleanup;
+
+	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
+							   pmu_fd);
+	CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event_callchain",
+	      "err: %ld\n", PTR_ERR(skel->links.oncpu));
+	close(pmu_fd);
+
+	/* add exclude_callchain_kernel, attach should fail */
+	attr.exclude_callchain_kernel = 1;
+
+	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+			 0 /* cpu 0 */, -1 /* group id */,
+			 0 /* flags */);
+
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
+		  pmu_fd, errno))
+		goto cleanup;
+
+	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
+							   pmu_fd);
+	CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_exclude_callchain_kernel",
+	      "should have failed\n");
+	close(pmu_fd);
+
+cleanup:
+	test_stacktrace_build_id__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c
index e3cb62b0a110..9efa7e50eab2 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data.c
@@ -5,7 +5,7 @@
 static void test_global_data_number(struct bpf_object *obj, __u32 duration)
 {
 	int i, err, map_fd;
-	uint64_t num;
+	__u64 num;
 
 	map_fd = bpf_find_map(__func__, obj, "result_number");
 	if (CHECK_FAIL(map_fd < 0))
@@ -14,7 +14,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration)
 	struct {
 		char *name;
 		uint32_t key;
-		uint64_t num;
+		__u64 num;
 	} tests[] = {
 		{ "relocate .bss reference",     0, 0 },
 		{ "relocate .data reference",    1, 42 },
@@ -32,7 +32,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration)
 	for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
 		err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num);
 		CHECK(err || num != tests[i].num, tests[i].name,
-		      "err %d result %lx expected %lx\n",
+		      "err %d result %llx expected %llx\n",
 		      err, num, tests[i].num);
 	}
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms.c b/tools/testing/selftests/bpf/prog_tests/ksyms.c
new file mode 100644
index 000000000000..e3d6777226a8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <test_progs.h>
+#include "test_ksyms.skel.h"
+#include <sys/stat.h>
+
+static int duration;
+
+static __u64 kallsyms_find(const char *sym)
+{
+	char type, name[500];
+	__u64 addr, res = 0;
+	FILE *f;
+
+	f = fopen("/proc/kallsyms", "r");
+	if (CHECK(!f, "kallsyms_fopen", "failed to open: %d\n", errno))
+		return 0;
+
+	while (fscanf(f, "%llx %c %499s%*[^\n]\n", &addr, &type, name) > 0) {
+		if (strcmp(name, sym) == 0) {
+			res = addr;
+			goto out;
+		}
+	}
+
+	CHECK(false, "not_found", "symbol %s not found\n", sym);
+out:
+	fclose(f);
+	return res;
+}
+
+void test_ksyms(void)
+{
+	__u64 link_fops_addr = kallsyms_find("bpf_link_fops");
+	const char *btf_path = "/sys/kernel/btf/vmlinux";
+	struct test_ksyms *skel;
+	struct test_ksyms__data *data;
+	struct stat st;
+	__u64 btf_size;
+	int err;
+
+	if (CHECK(stat(btf_path, &st), "stat_btf", "err %d\n", errno))
+		return;
+	btf_size = st.st_size;
+
+	skel = test_ksyms__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open and load skeleton\n"))
+		return;
+
+	err = test_ksyms__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	/* trigger tracepoint */
+	usleep(1);
+
+	data = skel->data;
+	CHECK(data->out__bpf_link_fops != link_fops_addr, "bpf_link_fops",
+	      "got 0x%llx, exp 0x%llx\n",
+	      data->out__bpf_link_fops, link_fops_addr);
+	CHECK(data->out__bpf_link_fops1 != 0, "bpf_link_fops1",
+	      "got %llu, exp %llu\n", data->out__bpf_link_fops1, (__u64)0);
+	CHECK(data->out__btf_size != btf_size, "btf_size",
+	      "got %llu, exp %llu\n", data->out__btf_size, btf_size);
+	CHECK(data->out__per_cpu_start != 0, "__per_cpu_start",
+	      "got %llu, exp %llu\n", data->out__per_cpu_start, (__u64)0);
+
+cleanup:
+	test_ksyms__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c b/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c
index c1168e4a9036..5a2a689dbb68 100644
--- a/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c
+++ b/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c
@@ -23,7 +23,7 @@ void test_load_bytes_relative(void)
 	if (CHECK_FAIL(cgroup_fd < 0))
 		return;
 
-	server_fd = start_server(AF_INET, SOCK_STREAM);
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_cgroup_fd;
 
@@ -49,7 +49,7 @@ void test_load_bytes_relative(void)
 	if (CHECK_FAIL(err))
 		goto close_bpf_object;
 
-	client_fd = connect_to_fd(AF_INET, SOCK_STREAM, server_fd);
+	client_fd = connect_to_fd(server_fd, 0);
 	if (CHECK_FAIL(client_fd < 0))
 		goto close_bpf_object;
 	close(client_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/map_ptr.c b/tools/testing/selftests/bpf/prog_tests/map_ptr.c
new file mode 100644
index 000000000000..c230a573c373
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_ptr.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "map_ptr_kern.skel.h"
+
+void test_map_ptr(void)
+{
+	struct map_ptr_kern *skel;
+	__u32 duration = 0, retval;
+	char buf[128];
+	int err;
+
+	skel = map_ptr_kern__open_and_load();
+	if (CHECK(!skel, "skel_open_load", "open_load failed\n"))
+		return;
+
+	err = bpf_prog_test_run(bpf_program__fd(skel->progs.cg_skb), 1, &pkt_v4,
+				sizeof(pkt_v4), buf, NULL, &retval, NULL);
+
+	if (CHECK(err, "test_run", "err=%d errno=%d\n", err, errno))
+		goto cleanup;
+
+	if (CHECK(!retval, "retval", "retval=%d map_type=%u line=%u\n", retval,
+		  skel->bss->g_map_type, skel->bss->g_line))
+		goto cleanup;
+
+cleanup:
+	map_ptr_kern__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c
index 43d0b5578f46..9c3c5c0f068f 100644
--- a/tools/testing/selftests/bpf/prog_tests/mmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/mmap.c
@@ -21,7 +21,7 @@ void test_mmap(void)
 	const long page_size = sysconf(_SC_PAGE_SIZE);
 	int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd, rdmap_fd;
 	struct bpf_map *data_map, *bss_map;
-	void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2;
+	void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp0, *tmp1, *tmp2;
 	struct test_mmap__bss *bss_data;
 	struct bpf_map_info map_info;
 	__u32 map_info_sz = sizeof(map_info);
@@ -183,16 +183,23 @@ void test_mmap(void)
 
 	/* check some more advanced mmap() manipulations */
 
+	tmp0 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_ANONYMOUS,
+			  -1, 0);
+	if (CHECK(tmp0 == MAP_FAILED, "adv_mmap0", "errno %d\n", errno))
+		goto cleanup;
+
 	/* map all but last page: pages 1-3 mapped */
-	tmp1 = mmap(NULL, 3 * page_size, PROT_READ, MAP_SHARED,
+	tmp1 = mmap(tmp0, 3 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED,
 			  data_map_fd, 0);
-	if (CHECK(tmp1 == MAP_FAILED, "adv_mmap1", "errno %d\n", errno))
+	if (CHECK(tmp0 != tmp1, "adv_mmap1", "tmp0: %p, tmp1: %p\n", tmp0, tmp1)) {
+		munmap(tmp0, 4 * page_size);
 		goto cleanup;
+	}
 
 	/* unmap second page: pages 1, 3 mapped */
 	err = munmap(tmp1 + page_size, page_size);
 	if (CHECK(err, "adv_mmap2", "errno %d\n", errno)) {
-		munmap(tmp1, map_sz);
+		munmap(tmp1, 4 * page_size);
 		goto cleanup;
 	}
 
@@ -201,7 +208,7 @@ void test_mmap(void)
 		    MAP_SHARED | MAP_FIXED, data_map_fd, 0);
 	if (CHECK(tmp2 == MAP_FAILED, "adv_mmap3", "errno %d\n", errno)) {
 		munmap(tmp1, page_size);
-		munmap(tmp1 + 2*page_size, page_size);
+		munmap(tmp1 + 2*page_size, 2 * page_size);
 		goto cleanup;
 	}
 	CHECK(tmp1 + page_size != tmp2, "adv_mmap4",
@@ -211,7 +218,7 @@ void test_mmap(void)
 	tmp2 = mmap(tmp1, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED,
 		    data_map_fd, 0);
 	if (CHECK(tmp2 == MAP_FAILED, "adv_mmap5", "errno %d\n", errno)) {
-		munmap(tmp1, 3 * page_size); /* unmap page 1 */
+		munmap(tmp1, 4 * page_size); /* unmap page 1 */
 		goto cleanup;
 	}
 	CHECK(tmp1 != tmp2, "adv_mmap6", "tmp1: %p, tmp2: %p\n", tmp1, tmp2);
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index a122ce3b360e..c33ec180b3f2 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -4,6 +4,7 @@
 #include <sched.h>
 #include <sys/socket.h>
 #include <test_progs.h>
+#include "test_perf_buffer.skel.h"
 #include "bpf/libbpf_internal.h"
 
 /* AddressSanitizer sometimes crashes due to data dereference below, due to
@@ -25,16 +26,11 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 
 void test_perf_buffer(void)
 {
-	int err, prog_fd, on_len, nr_on_cpus = 0,  nr_cpus, i, duration = 0;
-	const char *prog_name = "kprobe/sys_nanosleep";
-	const char *file = "./test_perf_buffer.o";
+	int err, on_len, nr_on_cpus = 0,  nr_cpus, i, duration = 0;
 	struct perf_buffer_opts pb_opts = {};
-	struct bpf_map *perf_buf_map;
+	struct test_perf_buffer *skel;
 	cpu_set_t cpu_set, cpu_seen;
-	struct bpf_program *prog;
-	struct bpf_object *obj;
 	struct perf_buffer *pb;
-	struct bpf_link *link;
 	bool *online;
 
 	nr_cpus = libbpf_num_possible_cpus();
@@ -51,33 +47,21 @@ void test_perf_buffer(void)
 			nr_on_cpus++;
 
 	/* load program */
-	err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd);
-	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) {
-		obj = NULL;
-		goto out_close;
-	}
-
-	prog = bpf_object__find_program_by_title(obj, prog_name);
-	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name))
+	skel = test_perf_buffer__open_and_load();
+	if (CHECK(!skel, "skel_load", "skeleton open/load failed\n"))
 		goto out_close;
 
-	/* load map */
-	perf_buf_map = bpf_object__find_map_by_name(obj, "perf_buf_map");
-	if (CHECK(!perf_buf_map, "find_perf_buf_map", "not found\n"))
-		goto out_close;
-
-	/* attach kprobe */
-	link = bpf_program__attach_kprobe(prog, false /* retprobe */,
-					  SYS_NANOSLEEP_KPROBE_NAME);
-	if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link)))
+	/* attach probe */
+	err = test_perf_buffer__attach(skel);
+	if (CHECK(err, "attach_kprobe", "err %d\n", err))
 		goto out_close;
 
 	/* set up perf buffer */
 	pb_opts.sample_cb = on_sample;
 	pb_opts.ctx = &cpu_seen;
-	pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1, &pb_opts);
+	pb = perf_buffer__new(bpf_map__fd(skel->maps.perf_buf_map), 1, &pb_opts);
 	if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
-		goto out_detach;
+		goto out_close;
 
 	/* trigger kprobe on every CPU */
 	CPU_ZERO(&cpu_seen);
@@ -94,7 +78,7 @@ void test_perf_buffer(void)
 					     &cpu_set);
 		if (err && CHECK(err, "set_affinity", "cpu #%d, err %d\n",
 				 i, err))
-			goto out_detach;
+			goto out_close;
 
 		usleep(1);
 	}
@@ -110,9 +94,7 @@ void test_perf_buffer(void)
 
 out_free_pb:
 	perf_buffer__free(pb);
-out_detach:
-	bpf_link__destroy(link);
 out_close:
-	bpf_object__close(obj);
+	test_perf_buffer__destroy(skel);
 	free(online);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c
new file mode 100644
index 000000000000..72c3690844fb
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sched.h>
+#include <test_progs.h>
+#include "perf_event_stackmap.skel.h"
+
+#ifndef noinline
+#define noinline __attribute__((noinline))
+#endif
+
+noinline int func_1(void)
+{
+	static int val = 1;
+
+	val += 1;
+
+	usleep(100);
+	return val;
+}
+
+noinline int func_2(void)
+{
+	return func_1();
+}
+
+noinline int func_3(void)
+{
+	return func_2();
+}
+
+noinline int func_4(void)
+{
+	return func_3();
+}
+
+noinline int func_5(void)
+{
+	return func_4();
+}
+
+noinline int func_6(void)
+{
+	int i, val = 1;
+
+	for (i = 0; i < 100; i++)
+		val += func_5();
+
+	return val;
+}
+
+void test_perf_event_stackmap(void)
+{
+	struct perf_event_attr attr = {
+		/* .type = PERF_TYPE_SOFTWARE, */
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+		.precise_ip = 2,
+		.sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_BRANCH_STACK |
+			PERF_SAMPLE_CALLCHAIN,
+		.branch_sample_type = PERF_SAMPLE_BRANCH_USER |
+			PERF_SAMPLE_BRANCH_NO_FLAGS |
+			PERF_SAMPLE_BRANCH_NO_CYCLES |
+			PERF_SAMPLE_BRANCH_CALL_STACK,
+		.sample_period = 5000,
+		.size = sizeof(struct perf_event_attr),
+	};
+	struct perf_event_stackmap *skel;
+	__u32 duration = 0;
+	cpu_set_t cpu_set;
+	int pmu_fd, err;
+
+	skel = perf_event_stackmap__open();
+
+	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
+		return;
+
+	err = perf_event_stackmap__load(skel);
+	if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err))
+		goto cleanup;
+
+	CPU_ZERO(&cpu_set);
+	CPU_SET(0, &cpu_set);
+	err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
+	if (CHECK(err, "set_affinity", "err %d, errno %d\n", err, errno))
+		goto cleanup;
+
+	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+			 0 /* cpu 0 */, -1 /* group id */,
+			 0 /* flags */);
+	if (pmu_fd < 0) {
+		printf("%s:SKIP:cpu doesn't support the event\n", __func__);
+		test__skip();
+		goto cleanup;
+	}
+
+	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
+							   pmu_fd);
+	if (CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event",
+		  "err %ld\n", PTR_ERR(skel->links.oncpu))) {
+		close(pmu_fd);
+		goto cleanup;
+	}
+
+	/* create kernel and user stack traces for testing */
+	func_6();
+
+	CHECK(skel->data->stackid_kernel != 2, "get_stackid_kernel", "failed\n");
+	CHECK(skel->data->stackid_user != 2, "get_stackid_user", "failed\n");
+	CHECK(skel->data->stack_kernel != 2, "get_stack_kernel", "failed\n");
+	CHECK(skel->data->stack_user != 2, "get_stack_user", "failed\n");
+
+cleanup:
+	perf_event_stackmap__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
index dde2b7ae7bc9..935a294f049a 100644
--- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
+++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
@@ -28,7 +28,7 @@ void test_prog_run_xattr(void)
 	      "err %d errno %d retval %d\n", err, errno, tattr.retval);
 
 	CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out",
-	      "incorrect output size, want %lu have %u\n",
+	      "incorrect output size, want %zu have %u\n",
 	      sizeof(pkt_v4), tattr.data_size_out);
 
 	CHECK_ATTR(buf[5] != 0, "overflow",
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
new file mode 100644
index 000000000000..3b127cab4864
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/err.h>
+#include <string.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include <linux/btf.h>
+#include <linux/kernel.h>
+#define CONFIG_DEBUG_INFO_BTF
+#include <linux/btf_ids.h>
+#include "test_progs.h"
+
+static int duration;
+
+struct symbol {
+	const char	*name;
+	int		 type;
+	int		 id;
+};
+
+struct symbol test_symbols[] = {
+	{ "unused",  BTF_KIND_UNKN,     0 },
+	{ "S",       BTF_KIND_TYPEDEF, -1 },
+	{ "T",       BTF_KIND_TYPEDEF, -1 },
+	{ "U",       BTF_KIND_TYPEDEF, -1 },
+	{ "S",       BTF_KIND_STRUCT,  -1 },
+	{ "U",       BTF_KIND_UNION,   -1 },
+	{ "func",    BTF_KIND_FUNC,    -1 },
+};
+
+BTF_ID_LIST(test_list_local)
+BTF_ID_UNUSED
+BTF_ID(typedef, S)
+BTF_ID(typedef, T)
+BTF_ID(typedef, U)
+BTF_ID(struct,  S)
+BTF_ID(union,   U)
+BTF_ID(func,    func)
+
+extern __u32 test_list_global[];
+BTF_ID_LIST_GLOBAL(test_list_global)
+BTF_ID_UNUSED
+BTF_ID(typedef, S)
+BTF_ID(typedef, T)
+BTF_ID(typedef, U)
+BTF_ID(struct,  S)
+BTF_ID(union,   U)
+BTF_ID(func,    func)
+
+static int
+__resolve_symbol(struct btf *btf, int type_id)
+{
+	const struct btf_type *type;
+	const char *str;
+	unsigned int i;
+
+	type = btf__type_by_id(btf, type_id);
+	if (!type) {
+		PRINT_FAIL("Failed to get type for ID %d\n", type_id);
+		return -1;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(test_symbols); i++) {
+		if (test_symbols[i].id != -1)
+			continue;
+
+		if (BTF_INFO_KIND(type->info) != test_symbols[i].type)
+			continue;
+
+		str = btf__name_by_offset(btf, type->name_off);
+		if (!str) {
+			PRINT_FAIL("Failed to get name for BTF ID %d\n", type_id);
+			return -1;
+		}
+
+		if (!strcmp(str, test_symbols[i].name))
+			test_symbols[i].id = type_id;
+	}
+
+	return 0;
+}
+
+static int resolve_symbols(void)
+{
+	struct btf *btf;
+	int type_id;
+	__u32 nr;
+
+	btf = btf__parse_elf("btf_data.o", NULL);
+	if (CHECK(libbpf_get_error(btf), "resolve",
+		  "Failed to load BTF from btf_data.o\n"))
+		return -1;
+
+	nr = btf__get_nr_types(btf);
+
+	for (type_id = 1; type_id <= nr; type_id++) {
+		if (__resolve_symbol(btf, type_id))
+			break;
+	}
+
+	btf__free(btf);
+	return 0;
+}
+
+int test_resolve_btfids(void)
+{
+	__u32 *test_list, *test_lists[] = { test_list_local, test_list_global };
+	unsigned int i, j;
+	int ret = 0;
+
+	if (resolve_symbols())
+		return -1;
+
+	/* Check BTF_ID_LIST(test_list_local) and
+	 * BTF_ID_LIST_GLOBAL(test_list_global) IDs
+	 */
+	for (j = 0; j < ARRAY_SIZE(test_lists); j++) {
+		test_list = test_lists[j];
+		for (i = 0; i < ARRAY_SIZE(test_symbols) && !ret; i++) {
+			ret = CHECK(test_list[i] != test_symbols[i].id,
+				    "id_check",
+				    "wrong ID for %s (%d != %d)\n",
+				    test_symbols[i].name,
+				    test_list[i], test_symbols[i].id);
+		}
+	}
+
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c
index 713167449c98..8b571890c57e 100644
--- a/tools/testing/selftests/bpf/prog_tests/section_names.c
+++ b/tools/testing/selftests/bpf/prog_tests/section_names.c
@@ -35,7 +35,7 @@ static struct sec_name_test tests[] = {
 		{-EINVAL, 0},
 	},
 	{"raw_tp/", {0, BPF_PROG_TYPE_RAW_TRACEPOINT, 0}, {-EINVAL, 0} },
-	{"xdp", {0, BPF_PROG_TYPE_XDP, 0}, {-EINVAL, 0} },
+	{"xdp", {0, BPF_PROG_TYPE_XDP, BPF_XDP}, {0, BPF_XDP} },
 	{"perf_event", {0, BPF_PROG_TYPE_PERF_EVENT, 0}, {-EINVAL, 0} },
 	{"lwt_in", {0, BPF_PROG_TYPE_LWT_IN, 0}, {-EINVAL, 0} },
 	{"lwt_out", {0, BPF_PROG_TYPE_LWT_OUT, 0}, {-EINVAL, 0} },
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index 504abb7bfb95..7043e6ded0e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -48,21 +48,19 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 		close(pipe_p2c[1]); /* close write */
 
 		/* notify parent signal handler is installed */
-		write(pipe_c2p[1], buf, 1);
+		CHECK(write(pipe_c2p[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno);
 
 		/* make sure parent enabled bpf program to send_signal */
-		read(pipe_p2c[0], buf, 1);
+		CHECK(read(pipe_p2c[0], buf, 1) != 1, "pipe_read", "err %d\n", -errno);
 
 		/* wait a little for signal handler */
 		sleep(1);
 
-		if (sigusr1_received)
-			write(pipe_c2p[1], "2", 1);
-		else
-			write(pipe_c2p[1], "0", 1);
+		buf[0] = sigusr1_received ? '2' : '0';
+		CHECK(write(pipe_c2p[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno);
 
 		/* wait for parent notification and exit */
-		read(pipe_p2c[0], buf, 1);
+		CHECK(read(pipe_p2c[0], buf, 1) != 1, "pipe_read", "err %d\n", -errno);
 
 		close(pipe_c2p[1]);
 		close(pipe_p2c[0]);
@@ -99,7 +97,7 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	}
 
 	/* wait until child signal handler installed */
-	read(pipe_c2p[0], buf, 1);
+	CHECK(read(pipe_c2p[0], buf, 1) != 1, "pipe_read", "err %d\n", -errno);
 
 	/* trigger the bpf send_signal */
 	skel->bss->pid = pid;
@@ -107,7 +105,7 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	skel->bss->signal_thread = signal_thread;
 
 	/* notify child that bpf program can send_signal now */
-	write(pipe_p2c[1], buf, 1);
+	CHECK(write(pipe_p2c[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno);
 
 	/* wait for result */
 	err = read(pipe_c2p[0], buf, 1);
@@ -121,7 +119,7 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	CHECK(buf[0] != '2', test_name, "incorrect result\n");
 
 	/* notify child safe to exit */
-	write(pipe_p2c[1], buf, 1);
+	CHECK(write(pipe_p2c[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno);
 
 disable_pmu:
 	close(pmu_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
new file mode 100644
index 000000000000..9ff0412e1fd3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -0,0 +1,1330 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+// Copyright (c) 2020 Cloudflare
+/*
+ * Test BPF attach point for INET socket lookup (BPF_SK_LOOKUP).
+ *
+ * Tests exercise:
+ *  - attaching/detaching/querying programs to BPF_SK_LOOKUP hook,
+ *  - redirecting socket lookup to a socket selected by BPF program,
+ *  - failing a socket lookup on BPF program's request,
+ *  - error scenarios for selecting a socket from BPF program,
+ *  - accessing BPF program context,
+ *  - attaching and running multiple BPF programs.
+ *
+ * Tests run in a dedicated network namespace.
+ */
+
+#define _GNU_SOURCE
+#include <arpa/inet.h>
+#include <assert.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+
+#include "test_progs.h"
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+#include "testing_helpers.h"
+#include "test_sk_lookup.skel.h"
+
+/* External (address, port) pairs the client sends packets to. */
+#define EXT_IP4		"127.0.0.1"
+#define EXT_IP6		"fd00::1"
+#define EXT_PORT	7007
+
+/* Internal (address, port) pairs the server listens/receives at. */
+#define INT_IP4		"127.0.0.2"
+#define INT_IP4_V6	"::ffff:127.0.0.2"
+#define INT_IP6		"fd00::2"
+#define INT_PORT	8008
+
+#define IO_TIMEOUT_SEC	3
+
+enum server {
+	SERVER_A = 0,
+	SERVER_B = 1,
+	MAX_SERVERS,
+};
+
+enum {
+	PROG1 = 0,
+	PROG2,
+};
+
+struct inet_addr {
+	const char *ip;
+	unsigned short port;
+};
+
+struct test {
+	const char *desc;
+	struct bpf_program *lookup_prog;
+	struct bpf_program *reuseport_prog;
+	struct bpf_map *sock_map;
+	int sotype;
+	struct inet_addr connect_to;
+	struct inet_addr listen_at;
+	enum server accept_on;
+	bool reuseport_has_conns; /* Add a connected socket to reuseport group */
+};
+
+static __u32 duration;		/* for CHECK macro */
+
+static bool is_ipv6(const char *ip)
+{
+	return !!strchr(ip, ':');
+}
+
+static int attach_reuseport(int sock_fd, struct bpf_program *reuseport_prog)
+{
+	int err, prog_fd;
+
+	prog_fd = bpf_program__fd(reuseport_prog);
+	if (prog_fd < 0) {
+		errno = -prog_fd;
+		return -1;
+	}
+
+	err = setsockopt(sock_fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF,
+			 &prog_fd, sizeof(prog_fd));
+	if (err)
+		return -1;
+
+	return 0;
+}
+
+static socklen_t inetaddr_len(const struct sockaddr_storage *addr)
+{
+	return (addr->ss_family == AF_INET ? sizeof(struct sockaddr_in) :
+		addr->ss_family == AF_INET6 ? sizeof(struct sockaddr_in6) : 0);
+}
+
+static int make_socket(int sotype, const char *ip, int port,
+		       struct sockaddr_storage *addr)
+{
+	struct timeval timeo = { .tv_sec = IO_TIMEOUT_SEC };
+	int err, family, fd;
+
+	family = is_ipv6(ip) ? AF_INET6 : AF_INET;
+	err = make_sockaddr(family, ip, port, addr, NULL);
+	if (CHECK(err, "make_address", "failed\n"))
+		return -1;
+
+	fd = socket(addr->ss_family, sotype, 0);
+	if (CHECK(fd < 0, "socket", "failed\n")) {
+		log_err("failed to make socket");
+		return -1;
+	}
+
+	err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo, sizeof(timeo));
+	if (CHECK(err, "setsockopt(SO_SNDTIMEO)", "failed\n")) {
+		log_err("failed to set SNDTIMEO");
+		close(fd);
+		return -1;
+	}
+
+	err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo, sizeof(timeo));
+	if (CHECK(err, "setsockopt(SO_RCVTIMEO)", "failed\n")) {
+		log_err("failed to set RCVTIMEO");
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+static int make_server(int sotype, const char *ip, int port,
+		       struct bpf_program *reuseport_prog)
+{
+	struct sockaddr_storage addr = {0};
+	const int one = 1;
+	int err, fd = -1;
+
+	fd = make_socket(sotype, ip, port, &addr);
+	if (fd < 0)
+		return -1;
+
+	/* Enabled for UDPv6 sockets for IPv4-mapped IPv6 to work. */
+	if (sotype == SOCK_DGRAM) {
+		err = setsockopt(fd, SOL_IP, IP_RECVORIGDSTADDR, &one,
+				 sizeof(one));
+		if (CHECK(err, "setsockopt(IP_RECVORIGDSTADDR)", "failed\n")) {
+			log_err("failed to enable IP_RECVORIGDSTADDR");
+			goto fail;
+		}
+	}
+
+	if (sotype == SOCK_DGRAM && addr.ss_family == AF_INET6) {
+		err = setsockopt(fd, SOL_IPV6, IPV6_RECVORIGDSTADDR, &one,
+				 sizeof(one));
+		if (CHECK(err, "setsockopt(IPV6_RECVORIGDSTADDR)", "failed\n")) {
+			log_err("failed to enable IPV6_RECVORIGDSTADDR");
+			goto fail;
+		}
+	}
+
+	if (sotype == SOCK_STREAM) {
+		err = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &one,
+				 sizeof(one));
+		if (CHECK(err, "setsockopt(SO_REUSEADDR)", "failed\n")) {
+			log_err("failed to enable SO_REUSEADDR");
+			goto fail;
+		}
+	}
+
+	if (reuseport_prog) {
+		err = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &one,
+				 sizeof(one));
+		if (CHECK(err, "setsockopt(SO_REUSEPORT)", "failed\n")) {
+			log_err("failed to enable SO_REUSEPORT");
+			goto fail;
+		}
+	}
+
+	err = bind(fd, (void *)&addr, inetaddr_len(&addr));
+	if (CHECK(err, "bind", "failed\n")) {
+		log_err("failed to bind listen socket");
+		goto fail;
+	}
+
+	if (sotype == SOCK_STREAM) {
+		err = listen(fd, SOMAXCONN);
+		if (CHECK(err, "make_server", "listen")) {
+			log_err("failed to listen on port %d", port);
+			goto fail;
+		}
+	}
+
+	/* Late attach reuseport prog so we can have one init path */
+	if (reuseport_prog) {
+		err = attach_reuseport(fd, reuseport_prog);
+		if (CHECK(err, "attach_reuseport", "failed\n")) {
+			log_err("failed to attach reuseport prog");
+			goto fail;
+		}
+	}
+
+	return fd;
+fail:
+	close(fd);
+	return -1;
+}
+
+static int make_client(int sotype, const char *ip, int port)
+{
+	struct sockaddr_storage addr = {0};
+	int err, fd;
+
+	fd = make_socket(sotype, ip, port, &addr);
+	if (fd < 0)
+		return -1;
+
+	err = connect(fd, (void *)&addr, inetaddr_len(&addr));
+	if (CHECK(err, "make_client", "connect")) {
+		log_err("failed to connect client socket");
+		goto fail;
+	}
+
+	return fd;
+fail:
+	close(fd);
+	return -1;
+}
+
+static int send_byte(int fd)
+{
+	ssize_t n;
+
+	errno = 0;
+	n = send(fd, "a", 1, 0);
+	if (CHECK(n <= 0, "send_byte", "send")) {
+		log_err("failed/partial send");
+		return -1;
+	}
+	return 0;
+}
+
+static int recv_byte(int fd)
+{
+	char buf[1];
+	ssize_t n;
+
+	n = recv(fd, buf, sizeof(buf), 0);
+	if (CHECK(n <= 0, "recv_byte", "recv")) {
+		log_err("failed/partial recv");
+		return -1;
+	}
+	return 0;
+}
+
+static int tcp_recv_send(int server_fd)
+{
+	char buf[1];
+	int ret, fd;
+	ssize_t n;
+
+	fd = accept(server_fd, NULL, NULL);
+	if (CHECK(fd < 0, "accept", "failed\n")) {
+		log_err("failed to accept");
+		return -1;
+	}
+
+	n = recv(fd, buf, sizeof(buf), 0);
+	if (CHECK(n <= 0, "recv", "failed\n")) {
+		log_err("failed/partial recv");
+		ret = -1;
+		goto close;
+	}
+
+	n = send(fd, buf, n, 0);
+	if (CHECK(n <= 0, "send", "failed\n")) {
+		log_err("failed/partial send");
+		ret = -1;
+		goto close;
+	}
+
+	ret = 0;
+close:
+	close(fd);
+	return ret;
+}
+
+static void v4_to_v6(struct sockaddr_storage *ss)
+{
+	struct sockaddr_in6 *v6 = (struct sockaddr_in6 *)ss;
+	struct sockaddr_in v4 = *(struct sockaddr_in *)ss;
+
+	v6->sin6_family = AF_INET6;
+	v6->sin6_port = v4.sin_port;
+	v6->sin6_addr.s6_addr[10] = 0xff;
+	v6->sin6_addr.s6_addr[11] = 0xff;
+	memcpy(&v6->sin6_addr.s6_addr[12], &v4.sin_addr.s_addr, 4);
+	memset(&v6->sin6_addr.s6_addr[0], 0, 10);
+}
+
+static int udp_recv_send(int server_fd)
+{
+	char cmsg_buf[CMSG_SPACE(sizeof(struct sockaddr_storage))];
+	struct sockaddr_storage _src_addr = { 0 };
+	struct sockaddr_storage *src_addr = &_src_addr;
+	struct sockaddr_storage *dst_addr = NULL;
+	struct msghdr msg = { 0 };
+	struct iovec iov = { 0 };
+	struct cmsghdr *cm;
+	char buf[1];
+	int ret, fd;
+	ssize_t n;
+
+	iov.iov_base = buf;
+	iov.iov_len = sizeof(buf);
+
+	msg.msg_name = src_addr;
+	msg.msg_namelen = sizeof(*src_addr);
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cmsg_buf;
+	msg.msg_controllen = sizeof(cmsg_buf);
+
+	errno = 0;
+	n = recvmsg(server_fd, &msg, 0);
+	if (CHECK(n <= 0, "recvmsg", "failed\n")) {
+		log_err("failed to receive");
+		return -1;
+	}
+	if (CHECK(msg.msg_flags & MSG_CTRUNC, "recvmsg", "truncated cmsg\n"))
+		return -1;
+
+	for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+		if ((cm->cmsg_level == SOL_IP &&
+		     cm->cmsg_type == IP_ORIGDSTADDR) ||
+		    (cm->cmsg_level == SOL_IPV6 &&
+		     cm->cmsg_type == IPV6_ORIGDSTADDR)) {
+			dst_addr = (struct sockaddr_storage *)CMSG_DATA(cm);
+			break;
+		}
+		log_err("warning: ignored cmsg at level %d type %d",
+			cm->cmsg_level, cm->cmsg_type);
+	}
+	if (CHECK(!dst_addr, "recvmsg", "missing ORIGDSTADDR\n"))
+		return -1;
+
+	/* Server socket bound to IPv4-mapped IPv6 address */
+	if (src_addr->ss_family == AF_INET6 &&
+	    dst_addr->ss_family == AF_INET) {
+		v4_to_v6(dst_addr);
+	}
+
+	/* Reply from original destination address. */
+	fd = socket(dst_addr->ss_family, SOCK_DGRAM, 0);
+	if (CHECK(fd < 0, "socket", "failed\n")) {
+		log_err("failed to create tx socket");
+		return -1;
+	}
+
+	ret = bind(fd, (struct sockaddr *)dst_addr, sizeof(*dst_addr));
+	if (CHECK(ret, "bind", "failed\n")) {
+		log_err("failed to bind tx socket");
+		goto out;
+	}
+
+	msg.msg_control = NULL;
+	msg.msg_controllen = 0;
+	n = sendmsg(fd, &msg, 0);
+	if (CHECK(n <= 0, "sendmsg", "failed\n")) {
+		log_err("failed to send echo reply");
+		ret = -1;
+		goto out;
+	}
+
+	ret = 0;
+out:
+	close(fd);
+	return ret;
+}
+
+static int tcp_echo_test(int client_fd, int server_fd)
+{
+	int err;
+
+	err = send_byte(client_fd);
+	if (err)
+		return -1;
+	err = tcp_recv_send(server_fd);
+	if (err)
+		return -1;
+	err = recv_byte(client_fd);
+	if (err)
+		return -1;
+
+	return 0;
+}
+
+static int udp_echo_test(int client_fd, int server_fd)
+{
+	int err;
+
+	err = send_byte(client_fd);
+	if (err)
+		return -1;
+	err = udp_recv_send(server_fd);
+	if (err)
+		return -1;
+	err = recv_byte(client_fd);
+	if (err)
+		return -1;
+
+	return 0;
+}
+
+static struct bpf_link *attach_lookup_prog(struct bpf_program *prog)
+{
+	struct bpf_link *link;
+	int net_fd;
+
+	net_fd = open("/proc/self/ns/net", O_RDONLY);
+	if (CHECK(net_fd < 0, "open", "failed\n")) {
+		log_err("failed to open /proc/self/ns/net");
+		return NULL;
+	}
+
+	link = bpf_program__attach_netns(prog, net_fd);
+	if (CHECK(IS_ERR(link), "bpf_program__attach_netns", "failed\n")) {
+		errno = -PTR_ERR(link);
+		log_err("failed to attach program '%s' to netns",
+			bpf_program__name(prog));
+		link = NULL;
+	}
+
+	close(net_fd);
+	return link;
+}
+
+static int update_lookup_map(struct bpf_map *map, int index, int sock_fd)
+{
+	int err, map_fd;
+	uint64_t value;
+
+	map_fd = bpf_map__fd(map);
+	if (CHECK(map_fd < 0, "bpf_map__fd", "failed\n")) {
+		errno = -map_fd;
+		log_err("failed to get map FD");
+		return -1;
+	}
+
+	value = (uint64_t)sock_fd;
+	err = bpf_map_update_elem(map_fd, &index, &value, BPF_NOEXIST);
+	if (CHECK(err, "bpf_map_update_elem", "failed\n")) {
+		log_err("failed to update redir_map @ %d", index);
+		return -1;
+	}
+
+	return 0;
+}
+
+static void query_lookup_prog(struct test_sk_lookup *skel)
+{
+	struct bpf_link *link[3] = {};
+	struct bpf_link_info info;
+	__u32 attach_flags = 0;
+	__u32 prog_ids[3] = {};
+	__u32 prog_cnt = 3;
+	__u32 prog_id;
+	int net_fd;
+	int err;
+
+	net_fd = open("/proc/self/ns/net", O_RDONLY);
+	if (CHECK(net_fd < 0, "open", "failed\n")) {
+		log_err("failed to open /proc/self/ns/net");
+		return;
+	}
+
+	link[0] = attach_lookup_prog(skel->progs.lookup_pass);
+	if (!link[0])
+		goto close;
+	link[1] = attach_lookup_prog(skel->progs.lookup_pass);
+	if (!link[1])
+		goto detach;
+	link[2] = attach_lookup_prog(skel->progs.lookup_drop);
+	if (!link[2])
+		goto detach;
+
+	err = bpf_prog_query(net_fd, BPF_SK_LOOKUP, 0 /* query flags */,
+			     &attach_flags, prog_ids, &prog_cnt);
+	if (CHECK(err, "bpf_prog_query", "failed\n")) {
+		log_err("failed to query lookup prog");
+		goto detach;
+	}
+
+	errno = 0;
+	if (CHECK(attach_flags != 0, "bpf_prog_query",
+		  "wrong attach_flags on query: %u", attach_flags))
+		goto detach;
+	if (CHECK(prog_cnt != 3, "bpf_prog_query",
+		  "wrong program count on query: %u", prog_cnt))
+		goto detach;
+	prog_id = link_info_prog_id(link[0], &info);
+	CHECK(prog_ids[0] != prog_id, "bpf_prog_query",
+	      "invalid program #0 id on query: %u != %u\n",
+	      prog_ids[0], prog_id);
+	CHECK(info.netns.netns_ino == 0, "netns_ino",
+	      "unexpected netns_ino: %u\n", info.netns.netns_ino);
+	prog_id = link_info_prog_id(link[1], &info);
+	CHECK(prog_ids[1] != prog_id, "bpf_prog_query",
+	      "invalid program #1 id on query: %u != %u\n",
+	      prog_ids[1], prog_id);
+	CHECK(info.netns.netns_ino == 0, "netns_ino",
+	      "unexpected netns_ino: %u\n", info.netns.netns_ino);
+	prog_id = link_info_prog_id(link[2], &info);
+	CHECK(prog_ids[2] != prog_id, "bpf_prog_query",
+	      "invalid program #2 id on query: %u != %u\n",
+	      prog_ids[2], prog_id);
+	CHECK(info.netns.netns_ino == 0, "netns_ino",
+	      "unexpected netns_ino: %u\n", info.netns.netns_ino);
+
+	err = bpf_link__detach(link[0]);
+	if (CHECK(err, "link_detach", "failed %d\n", err))
+		goto detach;
+
+	/* prog id is still there, but netns_ino is zeroed out */
+	prog_id = link_info_prog_id(link[0], &info);
+	CHECK(prog_ids[0] != prog_id, "bpf_prog_query",
+	      "invalid program #0 id on query: %u != %u\n",
+	      prog_ids[0], prog_id);
+	CHECK(info.netns.netns_ino != 0, "netns_ino",
+	      "unexpected netns_ino: %u\n", info.netns.netns_ino);
+
+detach:
+	if (link[2])
+		bpf_link__destroy(link[2]);
+	if (link[1])
+		bpf_link__destroy(link[1]);
+	if (link[0])
+		bpf_link__destroy(link[0]);
+close:
+	close(net_fd);
+}
+
+static void run_lookup_prog(const struct test *t)
+{
+	int server_fds[MAX_SERVERS] = { -1 };
+	int client_fd, reuse_conn_fd = -1;
+	struct bpf_link *lookup_link;
+	int i, err;
+
+	lookup_link = attach_lookup_prog(t->lookup_prog);
+	if (!lookup_link)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(server_fds); i++) {
+		server_fds[i] = make_server(t->sotype, t->listen_at.ip,
+					    t->listen_at.port,
+					    t->reuseport_prog);
+		if (server_fds[i] < 0)
+			goto close;
+
+		err = update_lookup_map(t->sock_map, i, server_fds[i]);
+		if (err)
+			goto close;
+
+		/* want just one server for non-reuseport test */
+		if (!t->reuseport_prog)
+			break;
+	}
+
+	/* Regular UDP socket lookup with reuseport behaves
+	 * differently when reuseport group contains connected
+	 * sockets. Check that adding a connected UDP socket to the
+	 * reuseport group does not affect how reuseport works with
+	 * BPF socket lookup.
+	 */
+	if (t->reuseport_has_conns) {
+		struct sockaddr_storage addr = {};
+		socklen_t len = sizeof(addr);
+
+		/* Add an extra socket to reuseport group */
+		reuse_conn_fd = make_server(t->sotype, t->listen_at.ip,
+					    t->listen_at.port,
+					    t->reuseport_prog);
+		if (reuse_conn_fd < 0)
+			goto close;
+
+		/* Connect the extra socket to itself */
+		err = getsockname(reuse_conn_fd, (void *)&addr, &len);
+		if (CHECK(err, "getsockname", "errno %d\n", errno))
+			goto close;
+		err = connect(reuse_conn_fd, (void *)&addr, len);
+		if (CHECK(err, "connect", "errno %d\n", errno))
+			goto close;
+	}
+
+	client_fd = make_client(t->sotype, t->connect_to.ip, t->connect_to.port);
+	if (client_fd < 0)
+		goto close;
+
+	if (t->sotype == SOCK_STREAM)
+		tcp_echo_test(client_fd, server_fds[t->accept_on]);
+	else
+		udp_echo_test(client_fd, server_fds[t->accept_on]);
+
+	close(client_fd);
+close:
+	if (reuse_conn_fd != -1)
+		close(reuse_conn_fd);
+	for (i = 0; i < ARRAY_SIZE(server_fds); i++) {
+		if (server_fds[i] != -1)
+			close(server_fds[i]);
+	}
+	bpf_link__destroy(lookup_link);
+}
+
+static void test_redirect_lookup(struct test_sk_lookup *skel)
+{
+	const struct test tests[] = {
+		{
+			.desc		= "TCP IPv4 redir port",
+			.lookup_prog	= skel->progs.redir_port,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { EXT_IP4, INT_PORT },
+		},
+		{
+			.desc		= "TCP IPv4 redir addr",
+			.lookup_prog	= skel->progs.redir_ip4,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4, EXT_PORT },
+		},
+		{
+			.desc		= "TCP IPv4 redir with reuseport",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4, INT_PORT },
+			.accept_on	= SERVER_B,
+		},
+		{
+			.desc		= "TCP IPv4 redir skip reuseport",
+			.lookup_prog	= skel->progs.select_sock_a_no_reuseport,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4, INT_PORT },
+			.accept_on	= SERVER_A,
+		},
+		{
+			.desc		= "TCP IPv6 redir port",
+			.lookup_prog	= skel->progs.redir_port,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { EXT_IP6, INT_PORT },
+		},
+		{
+			.desc		= "TCP IPv6 redir addr",
+			.lookup_prog	= skel->progs.redir_ip6,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { INT_IP6, EXT_PORT },
+		},
+		{
+			.desc		= "TCP IPv4->IPv6 redir port",
+			.lookup_prog	= skel->progs.redir_port,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4_V6, INT_PORT },
+		},
+		{
+			.desc		= "TCP IPv6 redir with reuseport",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { INT_IP6, INT_PORT },
+			.accept_on	= SERVER_B,
+		},
+		{
+			.desc		= "TCP IPv6 redir skip reuseport",
+			.lookup_prog	= skel->progs.select_sock_a_no_reuseport,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { INT_IP6, INT_PORT },
+			.accept_on	= SERVER_A,
+		},
+		{
+			.desc		= "UDP IPv4 redir port",
+			.lookup_prog	= skel->progs.redir_port,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { EXT_IP4, INT_PORT },
+		},
+		{
+			.desc		= "UDP IPv4 redir addr",
+			.lookup_prog	= skel->progs.redir_ip4,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4, EXT_PORT },
+		},
+		{
+			.desc		= "UDP IPv4 redir with reuseport",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4, INT_PORT },
+			.accept_on	= SERVER_B,
+		},
+		{
+			.desc		= "UDP IPv4 redir and reuseport with conns",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4, INT_PORT },
+			.accept_on	= SERVER_B,
+			.reuseport_has_conns = true,
+		},
+		{
+			.desc		= "UDP IPv4 redir skip reuseport",
+			.lookup_prog	= skel->progs.select_sock_a_no_reuseport,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4, INT_PORT },
+			.accept_on	= SERVER_A,
+		},
+		{
+			.desc		= "UDP IPv6 redir port",
+			.lookup_prog	= skel->progs.redir_port,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { EXT_IP6, INT_PORT },
+		},
+		{
+			.desc		= "UDP IPv6 redir addr",
+			.lookup_prog	= skel->progs.redir_ip6,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { INT_IP6, EXT_PORT },
+		},
+		{
+			.desc		= "UDP IPv4->IPv6 redir port",
+			.lookup_prog	= skel->progs.redir_port,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.listen_at	= { INT_IP4_V6, INT_PORT },
+			.connect_to	= { EXT_IP4, EXT_PORT },
+		},
+		{
+			.desc		= "UDP IPv6 redir and reuseport",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { INT_IP6, INT_PORT },
+			.accept_on	= SERVER_B,
+		},
+		{
+			.desc		= "UDP IPv6 redir and reuseport with conns",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { INT_IP6, INT_PORT },
+			.accept_on	= SERVER_B,
+			.reuseport_has_conns = true,
+		},
+		{
+			.desc		= "UDP IPv6 redir skip reuseport",
+			.lookup_prog	= skel->progs.select_sock_a_no_reuseport,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { INT_IP6, INT_PORT },
+			.accept_on	= SERVER_A,
+		},
+	};
+	const struct test *t;
+
+	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+		if (test__start_subtest(t->desc))
+			run_lookup_prog(t);
+	}
+}
+
+static void drop_on_lookup(const struct test *t)
+{
+	struct sockaddr_storage dst = {};
+	int client_fd, server_fd, err;
+	struct bpf_link *lookup_link;
+	ssize_t n;
+
+	lookup_link = attach_lookup_prog(t->lookup_prog);
+	if (!lookup_link)
+		return;
+
+	server_fd = make_server(t->sotype, t->listen_at.ip, t->listen_at.port,
+				t->reuseport_prog);
+	if (server_fd < 0)
+		goto detach;
+
+	client_fd = make_socket(t->sotype, t->connect_to.ip,
+				t->connect_to.port, &dst);
+	if (client_fd < 0)
+		goto close_srv;
+
+	err = connect(client_fd, (void *)&dst, inetaddr_len(&dst));
+	if (t->sotype == SOCK_DGRAM) {
+		err = send_byte(client_fd);
+		if (err)
+			goto close_all;
+
+		/* Read out asynchronous error */
+		n = recv(client_fd, NULL, 0, 0);
+		err = n == -1;
+	}
+	if (CHECK(!err || errno != ECONNREFUSED, "connect",
+		  "unexpected success or error\n"))
+		log_err("expected ECONNREFUSED on connect");
+
+close_all:
+	close(client_fd);
+close_srv:
+	close(server_fd);
+detach:
+	bpf_link__destroy(lookup_link);
+}
+
+static void test_drop_on_lookup(struct test_sk_lookup *skel)
+{
+	const struct test tests[] = {
+		{
+			.desc		= "TCP IPv4 drop on lookup",
+			.lookup_prog	= skel->progs.lookup_drop,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { EXT_IP4, EXT_PORT },
+		},
+		{
+			.desc		= "TCP IPv6 drop on lookup",
+			.lookup_prog	= skel->progs.lookup_drop,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { EXT_IP6, EXT_PORT },
+		},
+		{
+			.desc		= "UDP IPv4 drop on lookup",
+			.lookup_prog	= skel->progs.lookup_drop,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { EXT_IP4, EXT_PORT },
+		},
+		{
+			.desc		= "UDP IPv6 drop on lookup",
+			.lookup_prog	= skel->progs.lookup_drop,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { EXT_IP6, INT_PORT },
+		},
+	};
+	const struct test *t;
+
+	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+		if (test__start_subtest(t->desc))
+			drop_on_lookup(t);
+	}
+}
+
+static void drop_on_reuseport(const struct test *t)
+{
+	struct sockaddr_storage dst = { 0 };
+	int client, server1, server2, err;
+	struct bpf_link *lookup_link;
+	ssize_t n;
+
+	lookup_link = attach_lookup_prog(t->lookup_prog);
+	if (!lookup_link)
+		return;
+
+	server1 = make_server(t->sotype, t->listen_at.ip, t->listen_at.port,
+			      t->reuseport_prog);
+	if (server1 < 0)
+		goto detach;
+
+	err = update_lookup_map(t->sock_map, SERVER_A, server1);
+	if (err)
+		goto detach;
+
+	/* second server on destination address we should never reach */
+	server2 = make_server(t->sotype, t->connect_to.ip, t->connect_to.port,
+			      NULL /* reuseport prog */);
+	if (server2 < 0)
+		goto close_srv1;
+
+	client = make_socket(t->sotype, t->connect_to.ip,
+			     t->connect_to.port, &dst);
+	if (client < 0)
+		goto close_srv2;
+
+	err = connect(client, (void *)&dst, inetaddr_len(&dst));
+	if (t->sotype == SOCK_DGRAM) {
+		err = send_byte(client);
+		if (err)
+			goto close_all;
+
+		/* Read out asynchronous error */
+		n = recv(client, NULL, 0, 0);
+		err = n == -1;
+	}
+	if (CHECK(!err || errno != ECONNREFUSED, "connect",
+		  "unexpected success or error\n"))
+		log_err("expected ECONNREFUSED on connect");
+
+close_all:
+	close(client);
+close_srv2:
+	close(server2);
+close_srv1:
+	close(server1);
+detach:
+	bpf_link__destroy(lookup_link);
+}
+
+static void test_drop_on_reuseport(struct test_sk_lookup *skel)
+{
+	const struct test tests[] = {
+		{
+			.desc		= "TCP IPv4 drop on reuseport",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.reuseport_drop,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4, INT_PORT },
+		},
+		{
+			.desc		= "TCP IPv6 drop on reuseport",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.reuseport_drop,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { INT_IP6, INT_PORT },
+		},
+		{
+			.desc		= "UDP IPv4 drop on reuseport",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.reuseport_drop,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4, INT_PORT },
+		},
+		{
+			.desc		= "TCP IPv6 drop on reuseport",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.reuseport_drop,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_STREAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { INT_IP6, INT_PORT },
+		},
+	};
+	const struct test *t;
+
+	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+		if (test__start_subtest(t->desc))
+			drop_on_reuseport(t);
+	}
+}
+
+static void run_sk_assign(struct test_sk_lookup *skel,
+			  struct bpf_program *lookup_prog,
+			  const char *listen_ip, const char *connect_ip)
+{
+	int client_fd, peer_fd, server_fds[MAX_SERVERS] = { -1 };
+	struct bpf_link *lookup_link;
+	int i, err;
+
+	lookup_link = attach_lookup_prog(lookup_prog);
+	if (!lookup_link)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(server_fds); i++) {
+		server_fds[i] = make_server(SOCK_STREAM, listen_ip, 0, NULL);
+		if (server_fds[i] < 0)
+			goto close_servers;
+
+		err = update_lookup_map(skel->maps.redir_map, i,
+					server_fds[i]);
+		if (err)
+			goto close_servers;
+	}
+
+	client_fd = make_client(SOCK_STREAM, connect_ip, EXT_PORT);
+	if (client_fd < 0)
+		goto close_servers;
+
+	peer_fd = accept(server_fds[SERVER_B], NULL, NULL);
+	if (CHECK(peer_fd < 0, "accept", "failed\n"))
+		goto close_client;
+
+	close(peer_fd);
+close_client:
+	close(client_fd);
+close_servers:
+	for (i = 0; i < ARRAY_SIZE(server_fds); i++) {
+		if (server_fds[i] != -1)
+			close(server_fds[i]);
+	}
+	bpf_link__destroy(lookup_link);
+}
+
+static void run_sk_assign_v4(struct test_sk_lookup *skel,
+			     struct bpf_program *lookup_prog)
+{
+	run_sk_assign(skel, lookup_prog, INT_IP4, EXT_IP4);
+}
+
+static void run_sk_assign_v6(struct test_sk_lookup *skel,
+			     struct bpf_program *lookup_prog)
+{
+	run_sk_assign(skel, lookup_prog, INT_IP6, EXT_IP6);
+}
+
+static void run_sk_assign_connected(struct test_sk_lookup *skel,
+				    int sotype)
+{
+	int err, client_fd, connected_fd, server_fd;
+	struct bpf_link *lookup_link;
+
+	server_fd = make_server(sotype, EXT_IP4, EXT_PORT, NULL);
+	if (server_fd < 0)
+		return;
+
+	connected_fd = make_client(sotype, EXT_IP4, EXT_PORT);
+	if (connected_fd < 0)
+		goto out_close_server;
+
+	/* Put a connected socket in redirect map */
+	err = update_lookup_map(skel->maps.redir_map, SERVER_A, connected_fd);
+	if (err)
+		goto out_close_connected;
+
+	lookup_link = attach_lookup_prog(skel->progs.sk_assign_esocknosupport);
+	if (!lookup_link)
+		goto out_close_connected;
+
+	/* Try to redirect TCP SYN / UDP packet to a connected socket */
+	client_fd = make_client(sotype, EXT_IP4, EXT_PORT);
+	if (client_fd < 0)
+		goto out_unlink_prog;
+	if (sotype == SOCK_DGRAM) {
+		send_byte(client_fd);
+		recv_byte(server_fd);
+	}
+
+	close(client_fd);
+out_unlink_prog:
+	bpf_link__destroy(lookup_link);
+out_close_connected:
+	close(connected_fd);
+out_close_server:
+	close(server_fd);
+}
+
+static void test_sk_assign_helper(struct test_sk_lookup *skel)
+{
+	if (test__start_subtest("sk_assign returns EEXIST"))
+		run_sk_assign_v4(skel, skel->progs.sk_assign_eexist);
+	if (test__start_subtest("sk_assign honors F_REPLACE"))
+		run_sk_assign_v4(skel, skel->progs.sk_assign_replace_flag);
+	if (test__start_subtest("sk_assign accepts NULL socket"))
+		run_sk_assign_v4(skel, skel->progs.sk_assign_null);
+	if (test__start_subtest("access ctx->sk"))
+		run_sk_assign_v4(skel, skel->progs.access_ctx_sk);
+	if (test__start_subtest("narrow access to ctx v4"))
+		run_sk_assign_v4(skel, skel->progs.ctx_narrow_access);
+	if (test__start_subtest("narrow access to ctx v6"))
+		run_sk_assign_v6(skel, skel->progs.ctx_narrow_access);
+	if (test__start_subtest("sk_assign rejects TCP established"))
+		run_sk_assign_connected(skel, SOCK_STREAM);
+	if (test__start_subtest("sk_assign rejects UDP connected"))
+		run_sk_assign_connected(skel, SOCK_DGRAM);
+}
+
+struct test_multi_prog {
+	const char *desc;
+	struct bpf_program *prog1;
+	struct bpf_program *prog2;
+	struct bpf_map *redir_map;
+	struct bpf_map *run_map;
+	int expect_errno;
+	struct inet_addr listen_at;
+};
+
+static void run_multi_prog_lookup(const struct test_multi_prog *t)
+{
+	struct sockaddr_storage dst = {};
+	int map_fd, server_fd, client_fd;
+	struct bpf_link *link1, *link2;
+	int prog_idx, done, err;
+
+	map_fd = bpf_map__fd(t->run_map);
+
+	done = 0;
+	prog_idx = PROG1;
+	err = bpf_map_update_elem(map_fd, &prog_idx, &done, BPF_ANY);
+	if (CHECK(err, "bpf_map_update_elem", "failed\n"))
+		return;
+	prog_idx = PROG2;
+	err = bpf_map_update_elem(map_fd, &prog_idx, &done, BPF_ANY);
+	if (CHECK(err, "bpf_map_update_elem", "failed\n"))
+		return;
+
+	link1 = attach_lookup_prog(t->prog1);
+	if (!link1)
+		return;
+	link2 = attach_lookup_prog(t->prog2);
+	if (!link2)
+		goto out_unlink1;
+
+	server_fd = make_server(SOCK_STREAM, t->listen_at.ip,
+				t->listen_at.port, NULL);
+	if (server_fd < 0)
+		goto out_unlink2;
+
+	err = update_lookup_map(t->redir_map, SERVER_A, server_fd);
+	if (err)
+		goto out_close_server;
+
+	client_fd = make_socket(SOCK_STREAM, EXT_IP4, EXT_PORT, &dst);
+	if (client_fd < 0)
+		goto out_close_server;
+
+	err = connect(client_fd, (void *)&dst, inetaddr_len(&dst));
+	if (CHECK(err && !t->expect_errno, "connect",
+		  "unexpected error %d\n", errno))
+		goto out_close_client;
+	if (CHECK(err && t->expect_errno && errno != t->expect_errno,
+		  "connect", "unexpected error %d\n", errno))
+		goto out_close_client;
+
+	done = 0;
+	prog_idx = PROG1;
+	err = bpf_map_lookup_elem(map_fd, &prog_idx, &done);
+	CHECK(err, "bpf_map_lookup_elem", "failed\n");
+	CHECK(!done, "bpf_map_lookup_elem", "PROG1 !done\n");
+
+	done = 0;
+	prog_idx = PROG2;
+	err = bpf_map_lookup_elem(map_fd, &prog_idx, &done);
+	CHECK(err, "bpf_map_lookup_elem", "failed\n");
+	CHECK(!done, "bpf_map_lookup_elem", "PROG2 !done\n");
+
+out_close_client:
+	close(client_fd);
+out_close_server:
+	close(server_fd);
+out_unlink2:
+	bpf_link__destroy(link2);
+out_unlink1:
+	bpf_link__destroy(link1);
+}
+
+static void test_multi_prog_lookup(struct test_sk_lookup *skel)
+{
+	struct test_multi_prog tests[] = {
+		{
+			.desc		= "multi prog - pass, pass",
+			.prog1		= skel->progs.multi_prog_pass1,
+			.prog2		= skel->progs.multi_prog_pass2,
+			.listen_at	= { EXT_IP4, EXT_PORT },
+		},
+		{
+			.desc		= "multi prog - drop, drop",
+			.prog1		= skel->progs.multi_prog_drop1,
+			.prog2		= skel->progs.multi_prog_drop2,
+			.listen_at	= { EXT_IP4, EXT_PORT },
+			.expect_errno	= ECONNREFUSED,
+		},
+		{
+			.desc		= "multi prog - pass, drop",
+			.prog1		= skel->progs.multi_prog_pass1,
+			.prog2		= skel->progs.multi_prog_drop2,
+			.listen_at	= { EXT_IP4, EXT_PORT },
+			.expect_errno	= ECONNREFUSED,
+		},
+		{
+			.desc		= "multi prog - drop, pass",
+			.prog1		= skel->progs.multi_prog_drop1,
+			.prog2		= skel->progs.multi_prog_pass2,
+			.listen_at	= { EXT_IP4, EXT_PORT },
+			.expect_errno	= ECONNREFUSED,
+		},
+		{
+			.desc		= "multi prog - pass, redir",
+			.prog1		= skel->progs.multi_prog_pass1,
+			.prog2		= skel->progs.multi_prog_redir2,
+			.listen_at	= { INT_IP4, INT_PORT },
+		},
+		{
+			.desc		= "multi prog - redir, pass",
+			.prog1		= skel->progs.multi_prog_redir1,
+			.prog2		= skel->progs.multi_prog_pass2,
+			.listen_at	= { INT_IP4, INT_PORT },
+		},
+		{
+			.desc		= "multi prog - drop, redir",
+			.prog1		= skel->progs.multi_prog_drop1,
+			.prog2		= skel->progs.multi_prog_redir2,
+			.listen_at	= { INT_IP4, INT_PORT },
+		},
+		{
+			.desc		= "multi prog - redir, drop",
+			.prog1		= skel->progs.multi_prog_redir1,
+			.prog2		= skel->progs.multi_prog_drop2,
+			.listen_at	= { INT_IP4, INT_PORT },
+		},
+		{
+			.desc		= "multi prog - redir, redir",
+			.prog1		= skel->progs.multi_prog_redir1,
+			.prog2		= skel->progs.multi_prog_redir2,
+			.listen_at	= { INT_IP4, INT_PORT },
+		},
+	};
+	struct test_multi_prog *t;
+
+	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+		t->redir_map = skel->maps.redir_map;
+		t->run_map = skel->maps.run_map;
+		if (test__start_subtest(t->desc))
+			run_multi_prog_lookup(t);
+	}
+}
+
+static void run_tests(struct test_sk_lookup *skel)
+{
+	if (test__start_subtest("query lookup prog"))
+		query_lookup_prog(skel);
+	test_redirect_lookup(skel);
+	test_drop_on_lookup(skel);
+	test_drop_on_reuseport(skel);
+	test_sk_assign_helper(skel);
+	test_multi_prog_lookup(skel);
+}
+
+static int switch_netns(void)
+{
+	static const char * const setup_script[] = {
+		"ip -6 addr add dev lo " EXT_IP6 "/128",
+		"ip -6 addr add dev lo " INT_IP6 "/128",
+		"ip link set dev lo up",
+		NULL,
+	};
+	const char * const *cmd;
+	int err;
+
+	err = unshare(CLONE_NEWNET);
+	if (CHECK(err, "unshare", "failed\n")) {
+		log_err("unshare(CLONE_NEWNET)");
+		return -1;
+	}
+
+	for (cmd = setup_script; *cmd; cmd++) {
+		err = system(*cmd);
+		if (CHECK(err, "system", "failed\n")) {
+			log_err("system(%s)", *cmd);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+void test_sk_lookup(void)
+{
+	struct test_sk_lookup *skel;
+	int err;
+
+	err = switch_netns();
+	if (err)
+		return;
+
+	skel = test_sk_lookup__open_and_load();
+	if (CHECK(!skel, "skel open_and_load", "failed\n"))
+		return;
+
+	run_tests(skel);
+
+	test_sk_lookup__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
index 7021b92af313..fafeddaad6a9 100644
--- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -11,6 +11,7 @@ void test_skb_ctx(void)
 		.cb[3] = 4,
 		.cb[4] = 5,
 		.priority = 6,
+		.ifindex = 1,
 		.tstamp = 7,
 		.wire_len = 100,
 		.gso_segs = 8,
@@ -80,7 +81,7 @@ void test_skb_ctx(void)
 
 	CHECK_ATTR(tattr.ctx_size_out != sizeof(skb),
 		   "ctx_size_out",
-		   "incorrect output size, want %lu have %u\n",
+		   "incorrect output size, want %zu have %u\n",
 		   sizeof(skb), tattr.ctx_size_out);
 
 	for (i = 0; i < 5; i++)
@@ -92,6 +93,10 @@ void test_skb_ctx(void)
 		   "ctx_out_priority",
 		   "skb->priority == %d, expected %d\n",
 		   skb.priority, 7);
+	CHECK_ATTR(skb.ifindex != 1,
+		   "ctx_out_ifindex",
+		   "skb->ifindex == %d, expected %d\n",
+		   skb.ifindex, 1);
 	CHECK_ATTR(skb.tstamp != 8,
 		   "ctx_out_tstamp",
 		   "skb->tstamp == %lld, expected %d\n",
diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c
index fa153cf67b1b..fe87b77af459 100644
--- a/tools/testing/selftests/bpf/prog_tests/skeleton.c
+++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c
@@ -41,7 +41,7 @@ void test_skeleton(void)
 	CHECK(bss->in4 != 0, "in4", "got %lld != exp %lld\n", bss->in4, 0LL);
 	CHECK(bss->out4 != 0, "out4", "got %lld != exp %lld\n", bss->out4, 0LL);
 
-	CHECK(rodata->in6 != 0, "in6", "got %d != exp %d\n", rodata->in6, 0);
+	CHECK(rodata->in.in6 != 0, "in6", "got %d != exp %d\n", rodata->in.in6, 0);
 	CHECK(bss->out6 != 0, "out6", "got %d != exp %d\n", bss->out6, 0);
 
 	/* validate we can pre-setup global variables, even in .bss */
@@ -49,7 +49,7 @@ void test_skeleton(void)
 	data->in2 = 11;
 	bss->in3 = 12;
 	bss->in4 = 13;
-	rodata->in6 = 14;
+	rodata->in.in6 = 14;
 
 	err = test_skeleton__load(skel);
 	if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err))
@@ -60,7 +60,7 @@ void test_skeleton(void)
 	CHECK(data->in2 != 11, "in2", "got %lld != exp %lld\n", data->in2, 11LL);
 	CHECK(bss->in3 != 12, "in3", "got %d != exp %d\n", bss->in3, 12);
 	CHECK(bss->in4 != 13, "in4", "got %lld != exp %lld\n", bss->in4, 13LL);
-	CHECK(rodata->in6 != 14, "in6", "got %d != exp %d\n", rodata->in6, 14);
+	CHECK(rodata->in.in6 != 14, "in6", "got %d != exp %d\n", rodata->in.in6, 14);
 
 	/* now set new values and attach to get them into outX variables */
 	data->in1 = 1;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
index 8547ecbdc61f..ec281b0363b8 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
@@ -193,11 +193,10 @@ static void run_test(int cgroup_fd)
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_bpf_object;
 
+	pthread_mutex_lock(&server_started_mtx);
 	if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread,
 				      (void *)&server_fd)))
 		goto close_server_fd;
-
-	pthread_mutex_lock(&server_started_mtx);
 	pthread_cond_wait(&server_started, &server_started_mtx);
 	pthread_mutex_unlock(&server_started_mtx);
 
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
index f002e3090d92..11a769e18f5d 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@@ -6,11 +6,13 @@ static __u64 read_perf_max_sample_freq(void)
 {
 	__u64 sample_freq = 5000; /* fallback to 5000 on error */
 	FILE *f;
+	__u32 duration = 0;
 
 	f = fopen("/proc/sys/kernel/perf_event_max_sample_rate", "r");
 	if (f == NULL)
 		return sample_freq;
-	fscanf(f, "%llu", &sample_freq);
+	CHECK(fscanf(f, "%llu", &sample_freq) != 1, "Get max sample rate",
+		  "return default value: 5000,err %d\n", -errno);
 	fclose(f);
 	return sample_freq;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index 9013a0c01eed..d207e968e6b1 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -118,7 +118,7 @@ static int run_test(int cgroup_fd, int server_fd)
 		goto close_bpf_object;
 	}
 
-	client_fd = connect_to_fd(AF_INET, SOCK_STREAM, server_fd);
+	client_fd = connect_to_fd(server_fd, 0);
 	if (client_fd < 0) {
 		err = -1;
 		goto close_bpf_object;
@@ -161,7 +161,7 @@ void test_tcp_rtt(void)
 	if (CHECK_FAIL(cgroup_fd < 0))
 		return;
 
-	server_fd = start_server(AF_INET, SOCK_STREAM);
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_cgroup_fd;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
index 25b068591e9a..193002b14d7f 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -19,7 +19,7 @@ static int libbpf_debug_print(enum libbpf_print_level level,
 	log_buf = va_arg(args, char *);
 	if (!log_buf)
 		goto out;
-	if (strstr(log_buf, err_str) == 0)
+	if (err_str && strstr(log_buf, err_str) == 0)
 		found = true;
 out:
 	printf(format, log_buf);
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
new file mode 100644
index 000000000000..39b0decb1bb2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Oracle and/or its affiliates. */
+
+#include <test_progs.h>
+
+#include "trace_printk.skel.h"
+
+#define TRACEBUF	"/sys/kernel/debug/tracing/trace_pipe"
+#define SEARCHMSG	"testing,testing"
+
+void test_trace_printk(void)
+{
+	int err, iter = 0, duration = 0, found = 0;
+	struct trace_printk__bss *bss;
+	struct trace_printk *skel;
+	char *buf = NULL;
+	FILE *fp = NULL;
+	size_t buflen;
+
+	skel = trace_printk__open();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+
+	err = trace_printk__load(skel);
+	if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err))
+		goto cleanup;
+
+	bss = skel->bss;
+
+	err = trace_printk__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	fp = fopen(TRACEBUF, "r");
+	if (CHECK(fp == NULL, "could not open trace buffer",
+		  "error %d opening %s", errno, TRACEBUF))
+		goto cleanup;
+
+	/* We do not want to wait forever if this test fails... */
+	fcntl(fileno(fp), F_SETFL, O_NONBLOCK);
+
+	/* wait for tracepoint to trigger */
+	usleep(1);
+	trace_printk__detach(skel);
+
+	if (CHECK(bss->trace_printk_ran == 0,
+		  "bpf_trace_printk never ran",
+		  "ran == %d", bss->trace_printk_ran))
+		goto cleanup;
+
+	if (CHECK(bss->trace_printk_ret <= 0,
+		  "bpf_trace_printk returned <= 0 value",
+		  "got %d", bss->trace_printk_ret))
+		goto cleanup;
+
+	/* verify our search string is in the trace buffer */
+	while (getline(&buf, &buflen, fp) >= 0 || errno == EAGAIN) {
+		if (strstr(buf, SEARCHMSG) != NULL)
+			found++;
+		if (found == bss->trace_printk_ran)
+			break;
+		if (++iter > 1000)
+			break;
+	}
+
+	if (CHECK(!found, "message from bpf_trace_printk not found",
+		  "no instance of %s in %s", SEARCHMSG, TRACEBUF))
+		goto cleanup;
+
+cleanup:
+	trace_printk__destroy(skel);
+	free(buf);
+	if (fp)
+		fclose(fp);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/udp_limit.c b/tools/testing/selftests/bpf/prog_tests/udp_limit.c
new file mode 100644
index 000000000000..2aba09d4d01b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/udp_limit.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "udp_limit.skel.h"
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+static int duration;
+
+void test_udp_limit(void)
+{
+	struct udp_limit *skel;
+	int fd1 = -1, fd2 = -1;
+	int cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/udp_limit");
+	if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno))
+		return;
+
+	skel = udp_limit__open_and_load();
+	if (CHECK(!skel, "skel-load", "errno %d", errno))
+		goto close_cgroup_fd;
+
+	skel->links.sock = bpf_program__attach_cgroup(skel->progs.sock, cgroup_fd);
+	skel->links.sock_release = bpf_program__attach_cgroup(skel->progs.sock_release, cgroup_fd);
+	if (CHECK(IS_ERR(skel->links.sock) || IS_ERR(skel->links.sock_release),
+		  "cg-attach", "sock %ld sock_release %ld",
+		  PTR_ERR(skel->links.sock),
+		  PTR_ERR(skel->links.sock_release)))
+		goto close_skeleton;
+
+	/* BPF program enforces a single UDP socket per cgroup,
+	 * verify that.
+	 */
+	fd1 = socket(AF_INET, SOCK_DGRAM, 0);
+	if (CHECK(fd1 < 0, "fd1", "errno %d", errno))
+		goto close_skeleton;
+
+	fd2 = socket(AF_INET, SOCK_DGRAM, 0);
+	if (CHECK(fd2 >= 0, "fd2", "errno %d", errno))
+		goto close_skeleton;
+
+	/* We can reopen again after close. */
+	close(fd1);
+	fd1 = -1;
+
+	fd1 = socket(AF_INET, SOCK_DGRAM, 0);
+	if (CHECK(fd1 < 0, "fd1-again", "errno %d", errno))
+		goto close_skeleton;
+
+	/* Make sure the program was invoked the expected
+	 * number of times:
+	 * - open fd1           - BPF_CGROUP_INET_SOCK_CREATE
+	 * - attempt to openfd2 - BPF_CGROUP_INET_SOCK_CREATE
+	 * - close fd1          - BPF_CGROUP_INET_SOCK_RELEASE
+	 * - open fd1 again     - BPF_CGROUP_INET_SOCK_CREATE
+	 */
+	if (CHECK(skel->bss->invocations != 4, "bss-invocations",
+		  "invocations=%d", skel->bss->invocations))
+		goto close_skeleton;
+
+	/* We should still have a single socket in use */
+	if (CHECK(skel->bss->in_use != 1, "bss-in_use",
+		  "in_use=%d", skel->bss->in_use))
+		goto close_skeleton;
+
+close_skeleton:
+	if (fd1 >= 0)
+		close(fd1);
+	if (fd2 >= 0)
+		close(fd2);
+	udp_limit__destroy(skel);
+close_cgroup_fd:
+	close(cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/varlen.c b/tools/testing/selftests/bpf/prog_tests/varlen.c
new file mode 100644
index 000000000000..dd324b4933db
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/varlen.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+#include <time.h>
+#include "test_varlen.skel.h"
+
+#define CHECK_VAL(got, exp) \
+	CHECK((got) != (exp), "check", "got %ld != exp %ld\n", \
+	      (long)(got), (long)(exp))
+
+void test_varlen(void)
+{
+	int duration = 0, err;
+	struct test_varlen* skel;
+	struct test_varlen__bss *bss;
+	struct test_varlen__data *data;
+	const char str1[] = "Hello, ";
+	const char str2[] = "World!";
+	const char exp_str[] = "Hello, \0World!\0";
+	const int size1 = sizeof(str1);
+	const int size2 = sizeof(str2);
+
+	skel = test_varlen__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+	bss = skel->bss;
+	data = skel->data;
+
+	err = test_varlen__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	bss->test_pid = getpid();
+
+	/* trigger everything */
+	memcpy(bss->buf_in1, str1, size1);
+	memcpy(bss->buf_in2, str2, size2);
+	bss->capture = true;
+	usleep(1);
+	bss->capture = false;
+
+	CHECK_VAL(bss->payload1_len1, size1);
+	CHECK_VAL(bss->payload1_len2, size2);
+	CHECK_VAL(bss->total1, size1 + size2);
+	CHECK(memcmp(bss->payload1, exp_str, size1 + size2), "content_check",
+	      "doesn't match!\n");
+
+	CHECK_VAL(data->payload2_len1, size1);
+	CHECK_VAL(data->payload2_len2, size2);
+	CHECK_VAL(data->total2, size1 + size2);
+	CHECK(memcmp(data->payload2, exp_str, size1 + size2), "content_check",
+	      "doesn't match!\n");
+
+	CHECK_VAL(data->payload3_len1, size1);
+	CHECK_VAL(data->payload3_len2, size2);
+	CHECK_VAL(data->total3, size1 + size2);
+	CHECK(memcmp(data->payload3, exp_str, size1 + size2), "content_check",
+	      "doesn't match!\n");
+
+	CHECK_VAL(data->payload4_len1, size1);
+	CHECK_VAL(data->payload4_len2, size2);
+	CHECK_VAL(data->total4, size1 + size2);
+	CHECK(memcmp(data->payload4, exp_str, size1 + size2), "content_check",
+	      "doesn't match!\n");
+cleanup:
+	test_varlen__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
new file mode 100644
index 000000000000..0176573fe4e7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/bpf.h>
+#include <linux/if_link.h>
+#include <test_progs.h>
+
+#include "test_xdp_with_cpumap_helpers.skel.h"
+
+#define IFINDEX_LO	1
+
+void test_xdp_with_cpumap_helpers(void)
+{
+	struct test_xdp_with_cpumap_helpers *skel;
+	struct bpf_prog_info info = {};
+	struct bpf_cpumap_val val = {
+		.qsize = 192,
+	};
+	__u32 duration = 0, idx = 0;
+	__u32 len = sizeof(info);
+	int err, prog_fd, map_fd;
+
+	skel = test_xdp_with_cpumap_helpers__open_and_load();
+	if (CHECK_FAIL(!skel)) {
+		perror("test_xdp_with_cpumap_helpers__open_and_load");
+		return;
+	}
+
+	/* can not attach program with cpumaps that allow programs
+	 * as xdp generic
+	 */
+	prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE);
+	CHECK(err == 0, "Generic attach of program with 8-byte CPUMAP",
+	      "should have failed\n");
+
+	prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm);
+	map_fd = bpf_map__fd(skel->maps.cpu_map);
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &len);
+	if (CHECK_FAIL(err))
+		goto out_close;
+
+	val.bpf_prog.fd = prog_fd;
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	CHECK(err, "Add program to cpumap entry", "err %d errno %d\n",
+	      err, errno);
+
+	err = bpf_map_lookup_elem(map_fd, &idx, &val);
+	CHECK(err, "Read cpumap entry", "err %d errno %d\n", err, errno);
+	CHECK(info.id != val.bpf_prog.id, "Expected program id in cpumap entry",
+	      "expected %u read %u\n", info.id, val.bpf_prog.id);
+
+	/* can not attach BPF_XDP_CPUMAP program to a device */
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE);
+	CHECK(err == 0, "Attach of BPF_XDP_CPUMAP program",
+	      "should have failed\n");
+
+	val.qsize = 192;
+	val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog);
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	CHECK(err == 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry",
+	      "should have failed\n");
+
+out_close:
+	test_xdp_with_cpumap_helpers__destroy(skel);
+}
+
+void test_xdp_cpumap_attach(void)
+{
+	if (test__start_subtest("cpumap_with_progs"))
+		test_xdp_with_cpumap_helpers();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
new file mode 100644
index 000000000000..6f814999b395
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <uapi/linux/if_link.h>
+#include <test_progs.h>
+#include "test_xdp_link.skel.h"
+
+#define IFINDEX_LO 1
+
+void test_xdp_link(void)
+{
+	__u32 duration = 0, id1, id2, id0 = 0, prog_fd1, prog_fd2, err;
+	DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1);
+	struct test_xdp_link *skel1 = NULL, *skel2 = NULL;
+	struct bpf_link_info link_info;
+	struct bpf_prog_info prog_info;
+	struct bpf_link *link;
+	__u32 link_info_len = sizeof(link_info);
+	__u32 prog_info_len = sizeof(prog_info);
+
+	skel1 = test_xdp_link__open_and_load();
+	if (CHECK(!skel1, "skel_load", "skeleton open and load failed\n"))
+		goto cleanup;
+	prog_fd1 = bpf_program__fd(skel1->progs.xdp_handler);
+
+	skel2 = test_xdp_link__open_and_load();
+	if (CHECK(!skel2, "skel_load", "skeleton open and load failed\n"))
+		goto cleanup;
+	prog_fd2 = bpf_program__fd(skel2->progs.xdp_handler);
+
+	memset(&prog_info, 0, sizeof(prog_info));
+	err = bpf_obj_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len);
+	if (CHECK(err, "fd_info1", "failed %d\n", -errno))
+		goto cleanup;
+	id1 = prog_info.id;
+
+	memset(&prog_info, 0, sizeof(prog_info));
+	err = bpf_obj_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len);
+	if (CHECK(err, "fd_info2", "failed %d\n", -errno))
+		goto cleanup;
+	id2 = prog_info.id;
+
+	/* set initial prog attachment */
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts);
+	if (CHECK(err, "fd_attach", "initial prog attach failed: %d\n", err))
+		goto cleanup;
+
+	/* validate prog ID */
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+	CHECK(err || id0 != id1, "id1_check",
+	      "loaded prog id %u != id1 %u, err %d", id0, id1, err);
+
+	/* BPF link is not allowed to replace prog attachment */
+	link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO);
+	if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) {
+		bpf_link__destroy(link);
+		/* best-effort detach prog */
+		opts.old_fd = prog_fd1;
+		bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts);
+		goto cleanup;
+	}
+
+	/* detach BPF program */
+	opts.old_fd = prog_fd1;
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts);
+	if (CHECK(err, "prog_detach", "failed %d\n", err))
+		goto cleanup;
+
+	/* now BPF link should attach successfully */
+	link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO);
+	if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link)))
+		goto cleanup;
+	skel1->links.xdp_handler = link;
+
+	/* validate prog ID */
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+	if (CHECK(err || id0 != id1, "id1_check",
+		  "loaded prog id %u != id1 %u, err %d", id0, id1, err))
+		goto cleanup;
+
+	/* BPF prog attach is not allowed to replace BPF link */
+	opts.old_fd = prog_fd1;
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts);
+	if (CHECK(!err, "prog_attach_fail", "unexpected success\n"))
+		goto cleanup;
+
+	/* Can't force-update when BPF link is active */
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd2, 0);
+	if (CHECK(!err, "prog_update_fail", "unexpected success\n"))
+		goto cleanup;
+
+	/* Can't force-detach when BPF link is active */
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0);
+	if (CHECK(!err, "prog_detach_fail", "unexpected success\n"))
+		goto cleanup;
+
+	/* BPF link is not allowed to replace another BPF link */
+	link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO);
+	if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	bpf_link__destroy(skel1->links.xdp_handler);
+	skel1->links.xdp_handler = NULL;
+
+	/* new link attach should succeed */
+	link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO);
+	if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link)))
+		goto cleanup;
+	skel2->links.xdp_handler = link;
+
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+	if (CHECK(err || id0 != id2, "id2_check",
+		  "loaded prog id %u != id2 %u, err %d", id0, id1, err))
+		goto cleanup;
+
+	/* updating program under active BPF link works as expected */
+	err = bpf_link__update_program(link, skel1->progs.xdp_handler);
+	if (CHECK(err, "link_upd", "failed: %d\n", err))
+		goto cleanup;
+
+	memset(&link_info, 0, sizeof(link_info));
+	err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
+	if (CHECK(err, "link_info", "failed: %d\n", err))
+		goto cleanup;
+
+	CHECK(link_info.type != BPF_LINK_TYPE_XDP, "link_type",
+	      "got %u != exp %u\n", link_info.type, BPF_LINK_TYPE_XDP);
+	CHECK(link_info.prog_id != id1, "link_prog_id",
+	      "got %u != exp %u\n", link_info.prog_id, id1);
+	CHECK(link_info.xdp.ifindex != IFINDEX_LO, "link_ifindex",
+	      "got %u != exp %u\n", link_info.xdp.ifindex, IFINDEX_LO);
+
+	err = bpf_link__detach(link);
+	if (CHECK(err, "link_detach", "failed %d\n", err))
+		goto cleanup;
+
+	memset(&link_info, 0, sizeof(link_info));
+	err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
+	if (CHECK(err, "link_info", "failed: %d\n", err))
+		goto cleanup;
+	CHECK(link_info.prog_id != id1, "link_prog_id",
+	      "got %u != exp %u\n", link_info.prog_id, id1);
+	/* ifindex should be zeroed out */
+	CHECK(link_info.xdp.ifindex != 0, "link_ifindex",
+	      "got %u != exp %u\n", link_info.xdp.ifindex, 0);
+
+cleanup:
+	test_xdp_link__destroy(skel1);
+	test_xdp_link__destroy(skel2);
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h
new file mode 100644
index 000000000000..c196280df90d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter.h
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used
+#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used
+#define bpf_iter__netlink bpf_iter__netlink___not_used
+#define bpf_iter__task bpf_iter__task___not_used
+#define bpf_iter__task_file bpf_iter__task_file___not_used
+#define bpf_iter__tcp bpf_iter__tcp___not_used
+#define tcp6_sock tcp6_sock___not_used
+#define bpf_iter__udp bpf_iter__udp___not_used
+#define udp6_sock udp6_sock___not_used
+#define bpf_iter__bpf_map_elem bpf_iter__bpf_map_elem___not_used
+#define bpf_iter__bpf_sk_storage_map bpf_iter__bpf_sk_storage_map___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__bpf_map
+#undef bpf_iter__ipv6_route
+#undef bpf_iter__netlink
+#undef bpf_iter__task
+#undef bpf_iter__task_file
+#undef bpf_iter__tcp
+#undef tcp6_sock
+#undef bpf_iter__udp
+#undef udp6_sock
+#undef bpf_iter__bpf_map_elem
+#undef bpf_iter__bpf_sk_storage_map
+
+struct bpf_iter_meta {
+	struct seq_file *seq;
+	__u64 session_id;
+	__u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__ipv6_route {
+	struct bpf_iter_meta *meta;
+	struct fib6_info *rt;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__netlink {
+	struct bpf_iter_meta *meta;
+	struct netlink_sock *sk;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task {
+	struct bpf_iter_meta *meta;
+	struct task_struct *task;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task_file {
+	struct bpf_iter_meta *meta;
+	struct task_struct *task;
+	__u32 fd;
+	struct file *file;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__bpf_map {
+	struct bpf_iter_meta *meta;
+	struct bpf_map *map;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__tcp {
+	struct bpf_iter_meta *meta;
+	struct sock_common *sk_common;
+	uid_t uid;
+} __attribute__((preserve_access_index));
+
+struct tcp6_sock {
+	struct tcp_sock	tcp;
+	struct ipv6_pinfo inet6;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__udp {
+	struct bpf_iter_meta *meta;
+	struct udp_sock *udp_sk;
+	uid_t uid __attribute__((aligned(8)));
+	int bucket __attribute__((aligned(8)));
+} __attribute__((preserve_access_index));
+
+struct udp6_sock {
+	struct udp_sock	udp;
+	struct ipv6_pinfo inet6;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__bpf_map_elem {
+	struct bpf_iter_meta *meta;
+	struct bpf_map *map;
+	void *key;
+	void *value;
+};
+
+struct bpf_iter__bpf_sk_storage_map {
+	struct bpf_iter_meta *meta;
+	struct bpf_map *map;
+	struct sock *sk;
+	void *value;
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c
new file mode 100644
index 000000000000..6286023fd62b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct key_t {
+	int a;
+	int b;
+	int c;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 3);
+	__type(key, __u32);
+	__type(value, __u64);
+} arraymap1 SEC(".maps");
+
+__u32 key_sum = 0;
+__u64 val_sum = 0;
+
+SEC("iter/bpf_map_elem")
+int dump_bpf_array_map(struct bpf_iter__bpf_map_elem *ctx)
+{
+	__u32 *key = ctx->key;
+	__u64 *val = ctx->value;
+
+	if (key == (void *)0 || val == (void *)0)
+		return 0;
+
+	bpf_seq_write(ctx->meta->seq, key, sizeof(__u32));
+	bpf_seq_write(ctx->meta->seq, val, sizeof(__u64));
+	key_sum += *key;
+	val_sum += *val;
+	*val = *key;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
new file mode 100644
index 000000000000..07ddbfdbcab7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct key_t {
+	int a;
+	int b;
+	int c;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 3);
+	__type(key, struct key_t);
+	__type(value, __u64);
+} hashmap1 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 3);
+	__type(key, __u64);
+	__type(value, __u64);
+} hashmap2 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 3);
+	__type(key, struct key_t);
+	__type(value, __u32);
+} hashmap3 SEC(".maps");
+
+/* will set before prog run */
+bool in_test_mode = 0;
+
+/* will collect results during prog run */
+__u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0;
+__u64 val_sum = 0;
+
+SEC("iter/bpf_map_elem")
+int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	__u32 seq_num = ctx->meta->seq_num;
+	struct bpf_map *map = ctx->map;
+	struct key_t *key = ctx->key;
+	__u64 *val = ctx->value;
+
+	if (in_test_mode) {
+		/* test mode is used by selftests to
+		 * test functionality of bpf_hash_map iter.
+		 *
+		 * the above hashmap1 will have correct size
+		 * and will be accepted, hashmap2 and hashmap3
+		 * should be rejected due to smaller key/value
+		 * size.
+		 */
+		if (key == (void *)0 || val == (void *)0)
+			return 0;
+
+		key_sum_a += key->a;
+		key_sum_b += key->b;
+		key_sum_c += key->c;
+		val_sum += *val;
+		return 0;
+	}
+
+	/* non-test mode, the map is prepared with the
+	 * below bpftool command sequence:
+	 *   bpftool map create /sys/fs/bpf/m1 type hash \
+	 *   	key 12 value 8 entries 3 name map1
+	 *   bpftool map update id 77 key 0 0 0 1 0 0 0 0 0 0 0 1 \
+	 *   	value 0 0 0 1 0 0 0 1
+	 *   bpftool map update id 77 key 0 0 0 1 0 0 0 0 0 0 0 2 \
+	 *   	value 0 0 0 1 0 0 0 2
+	 * The bpftool iter command line:
+	 *   bpftool iter pin ./bpf_iter_bpf_hash_map.o /sys/fs/bpf/p1 \
+	 *   	map id 77
+	 * The below output will be:
+	 *   map dump starts
+	 *   77: (1000000 0 2000000) (200000001000000)
+	 *   77: (1000000 0 1000000) (100000001000000)
+	 *   map dump ends
+	 */
+	if (seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "map dump starts\n");
+
+	if (key == (void *)0 || val == (void *)0) {
+		BPF_SEQ_PRINTF(seq, "map dump ends\n");
+		return 0;
+	}
+
+	BPF_SEQ_PRINTF(seq, "%d: (%x %d %x) (%llx)\n", map->id,
+		       key->a, key->b, key->c, *val);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
index b57bd6fef208..08651b23edba 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
@@ -1,27 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-/* "undefine" structs in vmlinux.h, because we "override" them below */
-#define bpf_iter_meta bpf_iter_meta___not_used
-#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used
-#include "vmlinux.h"
-#undef bpf_iter_meta
-#undef bpf_iter__bpf_map
+#include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
-struct bpf_iter_meta {
-	struct seq_file *seq;
-	__u64 session_id;
-	__u64 seq_num;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__bpf_map {
-	struct bpf_iter_meta *meta;
-	struct bpf_map *map;
-} __attribute__((preserve_access_index));
-
 SEC("iter/bpf_map")
 int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c
new file mode 100644
index 000000000000..85fa710fad90
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct key_t {
+	int a;
+	int b;
+	int c;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 3);
+	__type(key, __u32);
+	__type(value, __u32);
+} arraymap1 SEC(".maps");
+
+/* will set before prog run */
+volatile const __u32 num_cpus = 0;
+
+__u32 key_sum = 0, val_sum = 0;
+
+SEC("iter/bpf_map_elem")
+int dump_bpf_percpu_array_map(struct bpf_iter__bpf_map_elem *ctx)
+{
+	__u32 *key = ctx->key;
+	void *pptr = ctx->value;
+	__u32 step;
+	int i;
+
+	if (key == (void *)0 || pptr == (void *)0)
+		return 0;
+
+	key_sum += *key;
+
+	step = 8;
+	for (i = 0; i < num_cpus; i++) {
+		val_sum += *(__u32 *)pptr;
+		pptr += step;
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
new file mode 100644
index 000000000000..feaaa2b89c57
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct key_t {
+	int a;
+	int b;
+	int c;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(max_entries, 3);
+	__type(key, struct key_t);
+	__type(value, __u32);
+} hashmap1 SEC(".maps");
+
+/* will set before prog run */
+volatile const __u32 num_cpus = 0;
+
+/* will collect results during prog run */
+__u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0;
+__u32 val_sum = 0;
+
+SEC("iter/bpf_map_elem")
+int dump_bpf_percpu_hash_map(struct bpf_iter__bpf_map_elem *ctx)
+{
+	struct key_t *key = ctx->key;
+	void *pptr = ctx->value;
+	__u32 step;
+	int i;
+
+	if (key == (void *)0 || pptr == (void *)0)
+		return 0;
+
+	key_sum_a += key->a;
+	key_sum_b += key->b;
+	key_sum_c += key->c;
+
+	step = 8;
+	for (i = 0; i < num_cpus; i++) {
+		val_sum += *(__u32 *)pptr;
+		pptr += step;
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c
new file mode 100644
index 000000000000..6b70ccaba301
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} sk_stg_map SEC(".maps");
+
+__u32 val_sum = 0;
+__u32 ipv6_sk_count = 0;
+
+SEC("iter/bpf_sk_storage_map")
+int dump_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx)
+{
+	struct sock *sk = ctx->sk;
+	__u32 *val = ctx->value;
+
+	if (sk == (void *)0 || val == (void *)0)
+		return 0;
+
+	if (sk->sk_family == AF_INET6)
+		ipv6_sk_count++;
+
+	val_sum += *val;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
index c8e9ca74c87b..d58d9f1642b5 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
@@ -1,35 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-/* "undefine" structs in vmlinux.h, because we "override" them below */
-#define bpf_iter_meta bpf_iter_meta___not_used
-#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used
-#include "vmlinux.h"
-#undef bpf_iter_meta
-#undef bpf_iter__ipv6_route
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-struct bpf_iter_meta {
-	struct seq_file *seq;
-	__u64 session_id;
-	__u64 seq_num;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__ipv6_route {
-	struct bpf_iter_meta *meta;
-	struct fib6_info *rt;
-} __attribute__((preserve_access_index));
-
 char _license[] SEC("license") = "GPL";
 
 extern bool CONFIG_IPV6_SUBTREES __kconfig __weak;
 
-#define RTF_GATEWAY		0x0002
-#define IFNAMSIZ		16
-#define fib_nh_gw_family	nh_common.nhc_gw_family
-#define fib_nh_gw6		nh_common.nhc_gw.ipv6
-#define fib_nh_dev		nh_common.nhc_dev
-
 SEC("iter/ipv6_route")
 int dump_ipv6_route(struct bpf_iter__ipv6_route *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
index 75ecf956a2df..95989f4c99b5 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
@@ -1,30 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-/* "undefine" structs in vmlinux.h, because we "override" them below */
-#define bpf_iter_meta bpf_iter_meta___not_used
-#define bpf_iter__netlink bpf_iter__netlink___not_used
-#include "vmlinux.h"
-#undef bpf_iter_meta
-#undef bpf_iter__netlink
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
-#define sk_rmem_alloc	sk_backlog.rmem_alloc
-#define sk_refcnt	__sk_common.skc_refcnt
-
-struct bpf_iter_meta {
-	struct seq_file *seq;
-	__u64 session_id;
-	__u64 seq_num;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__netlink {
-	struct bpf_iter_meta *meta;
-	struct netlink_sock *sk;
-} __attribute__((preserve_access_index));
-
 static __attribute__((noinline)) struct inode *SOCK_INODE(struct socket *socket)
 {
 	return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
@@ -54,10 +36,10 @@ int dump_netlink(struct bpf_iter__netlink *ctx)
 	if (!nlk->groups)  {
 		group = 0;
 	} else {
-		/* FIXME: temporary use bpf_probe_read here, needs
+		/* FIXME: temporary use bpf_probe_read_kernel here, needs
 		 * verifier support to do direct access.
 		 */
-		bpf_probe_read(&group, sizeof(group), &nlk->groups[0]);
+		bpf_probe_read_kernel(&group, sizeof(group), &nlk->groups[0]);
 	}
 	BPF_SEQ_PRINTF(seq, "%-10u %08x %-8d %-8d %-5d %-8d ",
 		       nlk->portid, (u32)group,
@@ -74,7 +56,7 @@ int dump_netlink(struct bpf_iter__netlink *ctx)
 		 * with current verifier.
 		 */
 		inode = SOCK_INODE(sk);
-		bpf_probe_read(&ino, sizeof(ino), &inode->i_ino);
+		bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino);
 	}
 	BPF_SEQ_PRINTF(seq, "%-8u %-8lu\n", s->sk_drops.counter, ino);
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
index ee754021f98e..4983087852a0 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
@@ -1,27 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-/* "undefine" structs in vmlinux.h, because we "override" them below */
-#define bpf_iter_meta bpf_iter_meta___not_used
-#define bpf_iter__task bpf_iter__task___not_used
-#include "vmlinux.h"
-#undef bpf_iter_meta
-#undef bpf_iter__task
+#include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
-struct bpf_iter_meta {
-	struct seq_file *seq;
-	__u64 session_id;
-	__u64 seq_num;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__task {
-	struct bpf_iter_meta *meta;
-	struct task_struct *task;
-} __attribute__((preserve_access_index));
-
 SEC("iter/task")
 int dump_task(struct bpf_iter__task *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
index 0f0ec3db20ba..8b787baa2654 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
@@ -1,29 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-/* "undefine" structs in vmlinux.h, because we "override" them below */
-#define bpf_iter_meta bpf_iter_meta___not_used
-#define bpf_iter__task_file bpf_iter__task_file___not_used
-#include "vmlinux.h"
-#undef bpf_iter_meta
-#undef bpf_iter__task_file
+#include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
-struct bpf_iter_meta {
-	struct seq_file *seq;
-	__u64 session_id;
-	__u64 seq_num;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__task_file {
-	struct bpf_iter_meta *meta;
-	struct task_struct *task;
-	__u32 fd;
-	struct file *file;
-} __attribute__((preserve_access_index));
-
 SEC("iter/task_file")
 int dump_task_file(struct bpf_iter__task_file *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
new file mode 100644
index 000000000000..50e59a2e142e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+#define MAX_STACK_TRACE_DEPTH   64
+unsigned long entries[MAX_STACK_TRACE_DEPTH] = {};
+#define SIZE_OF_ULONG (sizeof(unsigned long))
+
+SEC("iter/task")
+int dump_task_stack(struct bpf_iter__task *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+	long i, retlen;
+
+	if (task == (void *)0)
+		return 0;
+
+	retlen = bpf_get_task_stack(task, entries,
+				    MAX_STACK_TRACE_DEPTH * SIZE_OF_ULONG, 0);
+	if (retlen < 0)
+		return 0;
+
+	BPF_SEQ_PRINTF(seq, "pid: %8u num_entries: %8u\n", task->pid,
+		       retlen / SIZE_OF_ULONG);
+	for (i = 0; i < MAX_STACK_TRACE_DEPTH; i++) {
+		if (retlen > i * SIZE_OF_ULONG)
+			BPF_SEQ_PRINTF(seq, "[<0>] %pB\n", (void *)entries[i]);
+	}
+	BPF_SEQ_PRINTF(seq, "\n");
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
new file mode 100644
index 000000000000..54380c5e1069
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+
+static int hlist_unhashed_lockless(const struct hlist_node *h)
+{
+        return !(h->pprev);
+}
+
+static int timer_pending(const struct timer_list * timer)
+{
+	return !hlist_unhashed_lockless(&timer->entry);
+}
+
+extern unsigned CONFIG_HZ __kconfig;
+
+#define USER_HZ		100
+#define NSEC_PER_SEC	1000000000ULL
+static clock_t jiffies_to_clock_t(unsigned long x)
+{
+	/* The implementation here tailored to a particular
+	 * setting of USER_HZ.
+	 */
+	u64 tick_nsec = (NSEC_PER_SEC + CONFIG_HZ/2) / CONFIG_HZ;
+	u64 user_hz_nsec = NSEC_PER_SEC / USER_HZ;
+
+	if ((tick_nsec % user_hz_nsec) == 0) {
+		if (CONFIG_HZ < USER_HZ)
+			return x * (USER_HZ / CONFIG_HZ);
+		else
+			return x / (CONFIG_HZ / USER_HZ);
+	}
+	return x * tick_nsec/user_hz_nsec;
+}
+
+static clock_t jiffies_delta_to_clock_t(long delta)
+{
+	if (delta <= 0)
+		return 0;
+
+	return jiffies_to_clock_t(delta);
+}
+
+static long sock_i_ino(const struct sock *sk)
+{
+	const struct socket *sk_socket = sk->sk_socket;
+	const struct inode *inode;
+	unsigned long ino;
+
+	if (!sk_socket)
+		return 0;
+
+	inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode;
+	bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino);
+	return ino;
+}
+
+static bool
+inet_csk_in_pingpong_mode(const struct inet_connection_sock *icsk)
+{
+	return icsk->icsk_ack.pingpong >= TCP_PINGPONG_THRESH;
+}
+
+static bool tcp_in_initial_slowstart(const struct tcp_sock *tcp)
+{
+	return tcp->snd_ssthresh >= TCP_INFINITE_SSTHRESH;
+}
+
+static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp,
+			 uid_t uid, __u32 seq_num)
+{
+	const struct inet_connection_sock *icsk;
+	const struct fastopen_queue *fastopenq;
+	const struct inet_sock *inet;
+	unsigned long timer_expires;
+	const struct sock *sp;
+	__u16 destp, srcp;
+	__be32 dest, src;
+	int timer_active;
+	int rx_queue;
+	int state;
+
+	icsk = &tp->inet_conn;
+	inet = &icsk->icsk_inet;
+	sp = &inet->sk;
+	fastopenq = &icsk->icsk_accept_queue.fastopenq;
+
+	dest = inet->inet_daddr;
+	src = inet->inet_rcv_saddr;
+	destp = bpf_ntohs(inet->inet_dport);
+	srcp = bpf_ntohs(inet->inet_sport);
+
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
+		timer_active = 1;
+		timer_expires = icsk->icsk_timeout;
+	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
+		timer_active = 4;
+		timer_expires = icsk->icsk_timeout;
+	} else if (timer_pending(&sp->sk_timer)) {
+		timer_active = 2;
+		timer_expires = sp->sk_timer.expires;
+	} else {
+		timer_active = 0;
+		timer_expires = bpf_jiffies64();
+	}
+
+	state = sp->sk_state;
+	if (state == TCP_LISTEN) {
+		rx_queue = sp->sk_ack_backlog;
+	} else {
+		rx_queue = tp->rcv_nxt - tp->copied_seq;
+		if (rx_queue < 0)
+			rx_queue = 0;
+	}
+
+	BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ",
+		       seq_num, src, srcp, destp, destp);
+	BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d ",
+		       state,
+		       tp->write_seq - tp->snd_una, rx_queue,
+		       timer_active,
+		       jiffies_delta_to_clock_t(timer_expires - bpf_jiffies64()),
+		       icsk->icsk_retransmits, uid,
+		       icsk->icsk_probes_out,
+		       sock_i_ino(sp),
+		       sp->sk_refcnt.refs.counter);
+	BPF_SEQ_PRINTF(seq, "%pK %lu %lu %u %u %d\n",
+		       tp,
+		       jiffies_to_clock_t(icsk->icsk_rto),
+		       jiffies_to_clock_t(icsk->icsk_ack.ato),
+		       (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(icsk),
+		       tp->snd_cwnd,
+		       state == TCP_LISTEN ? fastopenq->max_qlen
+				: (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)
+		      );
+
+	return 0;
+}
+
+static int dump_tw_sock(struct seq_file *seq, struct tcp_timewait_sock *ttw,
+			uid_t uid, __u32 seq_num)
+{
+	struct inet_timewait_sock *tw = &ttw->tw_sk;
+	__u16 destp, srcp;
+	__be32 dest, src;
+	long delta;
+
+	delta = tw->tw_timer.expires - bpf_jiffies64();
+	dest = tw->tw_daddr;
+	src  = tw->tw_rcv_saddr;
+	destp = bpf_ntohs(tw->tw_dport);
+	srcp  = bpf_ntohs(tw->tw_sport);
+
+	BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ",
+		       seq_num, src, srcp, dest, destp);
+
+	BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n",
+		       tw->tw_substate, 0, 0,
+		       3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
+		       tw->tw_refcnt.refs.counter, tw);
+
+	return 0;
+}
+
+static int dump_req_sock(struct seq_file *seq, struct tcp_request_sock *treq,
+			 uid_t uid, __u32 seq_num)
+{
+	struct inet_request_sock *irsk = &treq->req;
+	struct request_sock *req = &irsk->req;
+	long ttd;
+
+	ttd = req->rsk_timer.expires - bpf_jiffies64();
+
+	if (ttd < 0)
+		ttd = 0;
+
+	BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ",
+		       seq_num, irsk->ir_loc_addr,
+		       irsk->ir_num, irsk->ir_rmt_addr,
+		       bpf_ntohs(irsk->ir_rmt_port));
+	BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n",
+		       TCP_SYN_RECV, 0, 0, 1, jiffies_to_clock_t(ttd),
+		       req->num_timeout, uid, 0, 0, 0, req);
+
+	return 0;
+}
+
+SEC("iter/tcp")
+int dump_tcp4(struct bpf_iter__tcp *ctx)
+{
+	struct sock_common *sk_common = ctx->sk_common;
+	struct seq_file *seq = ctx->meta->seq;
+	struct tcp_timewait_sock *tw;
+	struct tcp_request_sock *req;
+	struct tcp_sock *tp;
+	uid_t uid = ctx->uid;
+	__u32 seq_num;
+
+	if (sk_common == (void *)0)
+		return 0;
+
+	seq_num = ctx->meta->seq_num;
+	if (seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "  sl  "
+				    "local_address "
+				    "rem_address   "
+				    "st tx_queue rx_queue tr tm->when retrnsmt"
+				    "   uid  timeout inode\n");
+
+	if (sk_common->skc_family != AF_INET)
+		return 0;
+
+	tp = bpf_skc_to_tcp_sock(sk_common);
+	if (tp)
+		return dump_tcp_sock(seq, tp, uid, seq_num);
+
+	tw = bpf_skc_to_tcp_timewait_sock(sk_common);
+	if (tw)
+		return dump_tw_sock(seq, tw, uid, seq_num);
+
+	req = bpf_skc_to_tcp_request_sock(sk_common);
+	if (req)
+		return dump_req_sock(seq, req, uid, seq_num);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c
new file mode 100644
index 000000000000..b4fbddfa4e10
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+
+static int hlist_unhashed_lockless(const struct hlist_node *h)
+{
+        return !(h->pprev);
+}
+
+static int timer_pending(const struct timer_list * timer)
+{
+	return !hlist_unhashed_lockless(&timer->entry);
+}
+
+extern unsigned CONFIG_HZ __kconfig;
+
+#define USER_HZ		100
+#define NSEC_PER_SEC	1000000000ULL
+static clock_t jiffies_to_clock_t(unsigned long x)
+{
+	/* The implementation here tailored to a particular
+	 * setting of USER_HZ.
+	 */
+	u64 tick_nsec = (NSEC_PER_SEC + CONFIG_HZ/2) / CONFIG_HZ;
+	u64 user_hz_nsec = NSEC_PER_SEC / USER_HZ;
+
+	if ((tick_nsec % user_hz_nsec) == 0) {
+		if (CONFIG_HZ < USER_HZ)
+			return x * (USER_HZ / CONFIG_HZ);
+		else
+			return x / (CONFIG_HZ / USER_HZ);
+	}
+	return x * tick_nsec/user_hz_nsec;
+}
+
+static clock_t jiffies_delta_to_clock_t(long delta)
+{
+	if (delta <= 0)
+		return 0;
+
+	return jiffies_to_clock_t(delta);
+}
+
+static long sock_i_ino(const struct sock *sk)
+{
+	const struct socket *sk_socket = sk->sk_socket;
+	const struct inode *inode;
+	unsigned long ino;
+
+	if (!sk_socket)
+		return 0;
+
+	inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode;
+	bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino);
+	return ino;
+}
+
+static bool
+inet_csk_in_pingpong_mode(const struct inet_connection_sock *icsk)
+{
+	return icsk->icsk_ack.pingpong >= TCP_PINGPONG_THRESH;
+}
+
+static bool tcp_in_initial_slowstart(const struct tcp_sock *tcp)
+{
+	return tcp->snd_ssthresh >= TCP_INFINITE_SSTHRESH;
+}
+
+static int dump_tcp6_sock(struct seq_file *seq, struct tcp6_sock *tp,
+			 uid_t uid, __u32 seq_num)
+{
+	const struct inet_connection_sock *icsk;
+	const struct fastopen_queue *fastopenq;
+	const struct in6_addr *dest, *src;
+	const struct inet_sock *inet;
+	unsigned long timer_expires;
+	const struct sock *sp;
+	__u16 destp, srcp;
+	int timer_active;
+	int rx_queue;
+	int state;
+
+	icsk = &tp->tcp.inet_conn;
+	inet = &icsk->icsk_inet;
+	sp = &inet->sk;
+	fastopenq = &icsk->icsk_accept_queue.fastopenq;
+
+	dest = &sp->sk_v6_daddr;
+	src = &sp->sk_v6_rcv_saddr;
+	destp = bpf_ntohs(inet->inet_dport);
+	srcp = bpf_ntohs(inet->inet_sport);
+
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
+		timer_active = 1;
+		timer_expires = icsk->icsk_timeout;
+	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
+		timer_active = 4;
+		timer_expires = icsk->icsk_timeout;
+	} else if (timer_pending(&sp->sk_timer)) {
+		timer_active = 2;
+		timer_expires = sp->sk_timer.expires;
+	} else {
+		timer_active = 0;
+		timer_expires = bpf_jiffies64();
+	}
+
+	state = sp->sk_state;
+	if (state == TCP_LISTEN) {
+		rx_queue = sp->sk_ack_backlog;
+	} else {
+		rx_queue = tp->tcp.rcv_nxt - tp->tcp.copied_seq;
+		if (rx_queue < 0)
+			rx_queue = 0;
+	}
+
+	BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ",
+		       seq_num,
+		       src->s6_addr32[0], src->s6_addr32[1],
+		       src->s6_addr32[2], src->s6_addr32[3], srcp,
+		       dest->s6_addr32[0], dest->s6_addr32[1],
+		       dest->s6_addr32[2], dest->s6_addr32[3], destp);
+	BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d ",
+		       state,
+		       tp->tcp.write_seq - tp->tcp.snd_una, rx_queue,
+		       timer_active,
+		       jiffies_delta_to_clock_t(timer_expires - bpf_jiffies64()),
+		       icsk->icsk_retransmits, uid,
+		       icsk->icsk_probes_out,
+		       sock_i_ino(sp),
+		       sp->sk_refcnt.refs.counter);
+	BPF_SEQ_PRINTF(seq, "%pK %lu %lu %u %u %d\n",
+		       tp,
+		       jiffies_to_clock_t(icsk->icsk_rto),
+		       jiffies_to_clock_t(icsk->icsk_ack.ato),
+		       (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(icsk),
+		       tp->tcp.snd_cwnd,
+		       state == TCP_LISTEN ? fastopenq->max_qlen
+				: (tcp_in_initial_slowstart(&tp->tcp) ? -1
+								      : tp->tcp.snd_ssthresh)
+		      );
+
+	return 0;
+}
+
+static int dump_tw_sock(struct seq_file *seq, struct tcp_timewait_sock *ttw,
+			uid_t uid, __u32 seq_num)
+{
+	struct inet_timewait_sock *tw = &ttw->tw_sk;
+	const struct in6_addr *dest, *src;
+	__u16 destp, srcp;
+	long delta;
+
+	delta = tw->tw_timer.expires - bpf_jiffies64();
+	dest = &tw->tw_v6_daddr;
+	src  = &tw->tw_v6_rcv_saddr;
+	destp = bpf_ntohs(tw->tw_dport);
+	srcp  = bpf_ntohs(tw->tw_sport);
+
+	BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ",
+		       seq_num,
+		       src->s6_addr32[0], src->s6_addr32[1],
+		       src->s6_addr32[2], src->s6_addr32[3], srcp,
+		       dest->s6_addr32[0], dest->s6_addr32[1],
+		       dest->s6_addr32[2], dest->s6_addr32[3], destp);
+
+	BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n",
+		       tw->tw_substate, 0, 0,
+		       3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
+		       tw->tw_refcnt.refs.counter, tw);
+
+	return 0;
+}
+
+static int dump_req_sock(struct seq_file *seq, struct tcp_request_sock *treq,
+			 uid_t uid, __u32 seq_num)
+{
+	struct inet_request_sock *irsk = &treq->req;
+	struct request_sock *req = &irsk->req;
+	struct in6_addr *src, *dest;
+	long ttd;
+
+	ttd = req->rsk_timer.expires - bpf_jiffies64();
+	src = &irsk->ir_v6_loc_addr;
+	dest = &irsk->ir_v6_rmt_addr;
+
+	if (ttd < 0)
+		ttd = 0;
+
+	BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ",
+		       seq_num,
+		       src->s6_addr32[0], src->s6_addr32[1],
+		       src->s6_addr32[2], src->s6_addr32[3],
+		       irsk->ir_num,
+		       dest->s6_addr32[0], dest->s6_addr32[1],
+		       dest->s6_addr32[2], dest->s6_addr32[3],
+		       bpf_ntohs(irsk->ir_rmt_port));
+	BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n",
+		       TCP_SYN_RECV, 0, 0, 1, jiffies_to_clock_t(ttd),
+		       req->num_timeout, uid, 0, 0, 0, req);
+
+	return 0;
+}
+
+SEC("iter/tcp")
+int dump_tcp6(struct bpf_iter__tcp *ctx)
+{
+	struct sock_common *sk_common = ctx->sk_common;
+	struct seq_file *seq = ctx->meta->seq;
+	struct tcp_timewait_sock *tw;
+	struct tcp_request_sock *req;
+	struct tcp6_sock *tp;
+	uid_t uid = ctx->uid;
+	__u32 seq_num;
+
+	if (sk_common == (void *)0)
+		return 0;
+
+	seq_num = ctx->meta->seq_num;
+	if (seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "  sl  "
+				    "local_address                         "
+				    "remote_address                        "
+				    "st tx_queue rx_queue tr tm->when retrnsmt"
+				    "   uid  timeout inode\n");
+
+	if (sk_common->skc_family != AF_INET6)
+		return 0;
+
+	tp = bpf_skc_to_tcp6_sock(sk_common);
+	if (tp)
+		return dump_tcp6_sock(seq, tp, uid, seq_num);
+
+	tw = bpf_skc_to_tcp_timewait_sock(sk_common);
+	if (tw)
+		return dump_tw_sock(seq, tw, uid, seq_num);
+
+	req = bpf_skc_to_tcp_request_sock(sk_common);
+	if (req)
+		return dump_req_sock(seq, req, uid, seq_num);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c
index 13c2c90c835f..2a4647f20c46 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c
@@ -1,25 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#define bpf_iter_meta bpf_iter_meta___not_used
-#define bpf_iter__task bpf_iter__task___not_used
-#include "vmlinux.h"
-#undef bpf_iter_meta
-#undef bpf_iter__task
+#include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
 
-struct bpf_iter_meta {
-	struct seq_file *seq;
-	__u64 session_id;
-	__u64 seq_num;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__task {
-	struct bpf_iter_meta *meta;
-	struct task_struct *task;
-} __attribute__((preserve_access_index));
-
 SEC("iter/task")
 int dump_task(struct bpf_iter__task *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
index 0aa71b333cf3..ee49493dc125 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
@@ -1,25 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#define bpf_iter_meta bpf_iter_meta___not_used
-#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used
-#include "vmlinux.h"
-#undef bpf_iter_meta
-#undef bpf_iter__bpf_map
+#include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
 
-struct bpf_iter_meta {
-	struct seq_file *seq;
-	__u64 session_id;
-	__u64 seq_num;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__bpf_map {
-	struct bpf_iter_meta *meta;
-	struct bpf_map *map;
-} __attribute__((preserve_access_index));
-
 __u32 map1_id = 0, map2_id = 0;
 __u32 map1_accessed = 0, map2_accessed = 0;
 __u64 map1_seqnum = 0, map2_seqnum1 = 0, map2_seqnum2 = 0;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c
new file mode 100644
index 000000000000..e3a7575e81d2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct key_t {
+	int a;
+	int b;
+	int c;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 3);
+	__type(key, struct key_t);
+	__type(value, __u64);
+} hashmap1 SEC(".maps");
+
+__u32 key_sum = 0;
+
+SEC("iter/bpf_map_elem")
+int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx)
+{
+	void *key = ctx->key;
+
+	if (key == (void *)0)
+		return 0;
+
+	/* out of bound access w.r.t. hashmap1 */
+	key_sum += *(__u32 *)(key + sizeof(struct key_t));
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c
new file mode 100644
index 000000000000..1c7304f56b1e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u32 value_sum = 0;
+
+SEC("iter/bpf_map_elem")
+int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx)
+{
+	void *value = ctx->value;
+
+	if (value == (void *)0)
+		return 0;
+
+	/* negative offset, verifier failure. */
+	value_sum += *(__u32 *)(value - 4);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h
index dee1339e6905..d5e3df66ad9a 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h
@@ -1,27 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2020 Facebook */
-/* "undefine" structs in vmlinux.h, because we "override" them below */
-#define bpf_iter_meta bpf_iter_meta___not_used
-#define bpf_iter__task bpf_iter__task___not_used
-#include "vmlinux.h"
-#undef bpf_iter_meta
-#undef bpf_iter__task
+#include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
 int count = 0;
 
-struct bpf_iter_meta {
-	struct seq_file *seq;
-	__u64 session_id;
-	__u64 seq_num;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__task {
-	struct bpf_iter_meta *meta;
-	struct task_struct *task;
-} __attribute__((preserve_access_index));
-
 SEC("iter/task")
 int dump_task(struct bpf_iter__task *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
new file mode 100644
index 000000000000..f258583afbbd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+
+static long sock_i_ino(const struct sock *sk)
+{
+	const struct socket *sk_socket = sk->sk_socket;
+	const struct inode *inode;
+	unsigned long ino;
+
+	if (!sk_socket)
+		return 0;
+
+	inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode;
+	bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino);
+	return ino;
+}
+
+SEC("iter/udp")
+int dump_udp4(struct bpf_iter__udp *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct udp_sock *udp_sk = ctx->udp_sk;
+	struct inet_sock *inet;
+	__u16 srcp, destp;
+	__be32 dest, src;
+	__u32 seq_num;
+	int rqueue;
+
+	if (udp_sk == (void *)0)
+		return 0;
+
+	seq_num = ctx->meta->seq_num;
+	if (seq_num == 0)
+		BPF_SEQ_PRINTF(seq,
+			       "  sl  local_address rem_address   st tx_queue "
+			       "rx_queue tr tm->when retrnsmt   uid  timeout "
+			       "inode ref pointer drops\n");
+
+	/* filter out udp6 sockets */
+	inet = &udp_sk->inet;
+	if (inet->sk.sk_family == AF_INET6)
+		return 0;
+
+	inet = &udp_sk->inet;
+	dest = inet->inet_daddr;
+	src = inet->inet_rcv_saddr;
+	srcp = bpf_ntohs(inet->inet_sport);
+	destp = bpf_ntohs(inet->inet_dport);
+	rqueue = inet->sk.sk_rmem_alloc.counter - udp_sk->forward_deficit;
+
+	BPF_SEQ_PRINTF(seq, "%5d: %08X:%04X %08X:%04X ",
+		       ctx->bucket, src, srcp, dest, destp);
+
+	BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n",
+		       inet->sk.sk_state,
+		       inet->sk.sk_wmem_alloc.refs.counter - 1,
+		       rqueue,
+		       0, 0L, 0, ctx->uid, 0,
+		       sock_i_ino(&inet->sk),
+		       inet->sk.sk_refcnt.refs.counter, udp_sk,
+		       inet->sk.sk_drops.counter);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
new file mode 100644
index 000000000000..65f93bb03f0f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+
+#define IPV6_SEQ_DGRAM_HEADER				\
+	"  sl  "					\
+	"local_address                         "	\
+	"remote_address                        "	\
+	"st tx_queue rx_queue tr tm->when retrnsmt"	\
+	"   uid  timeout inode ref pointer drops\n"
+
+static long sock_i_ino(const struct sock *sk)
+{
+	const struct socket *sk_socket = sk->sk_socket;
+	const struct inode *inode;
+	unsigned long ino;
+
+	if (!sk_socket)
+		return 0;
+
+	inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode;
+	bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino);
+	return ino;
+}
+
+SEC("iter/udp")
+int dump_udp6(struct bpf_iter__udp *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct udp_sock *udp_sk = ctx->udp_sk;
+	const struct in6_addr *dest, *src;
+	struct udp6_sock *udp6_sk;
+	struct inet_sock *inet;
+	__u16 srcp, destp;
+	__u32 seq_num;
+	int rqueue;
+
+	if (udp_sk == (void *)0)
+		return 0;
+
+	seq_num = ctx->meta->seq_num;
+	if (seq_num == 0)
+		BPF_SEQ_PRINTF(seq, IPV6_SEQ_DGRAM_HEADER);
+
+	udp6_sk = bpf_skc_to_udp6_sock(udp_sk);
+	if (udp6_sk == (void *)0)
+		return 0;
+
+	inet = &udp_sk->inet;
+	srcp = bpf_ntohs(inet->inet_sport);
+	destp = bpf_ntohs(inet->inet_dport);
+	rqueue = inet->sk.sk_rmem_alloc.counter - udp_sk->forward_deficit;
+	dest  = &inet->sk.sk_v6_daddr;
+	src   = &inet->sk.sk_v6_rcv_saddr;
+
+	BPF_SEQ_PRINTF(seq, "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ",
+		       ctx->bucket,
+		       src->s6_addr32[0], src->s6_addr32[1],
+		       src->s6_addr32[2], src->s6_addr32[3], srcp,
+		       dest->s6_addr32[0], dest->s6_addr32[1],
+		       dest->s6_addr32[2], dest->s6_addr32[3], destp);
+
+	BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n",
+		       inet->sk.sk_state,
+		       inet->sk.sk_wmem_alloc.refs.counter - 1,
+		       rqueue,
+		       0, 0L, 0, ctx->uid, 0,
+		       sock_i_ino(&inet->sk),
+		       inet->sk.sk_refcnt.refs.counter, udp_sk,
+		       inet->sk.sk_drops.counter);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
new file mode 100644
index 000000000000..01378911252b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_TRACING_NET_H__
+#define __BPF_TRACING_NET_H__
+
+#define AF_INET			2
+#define AF_INET6		10
+
+#define ICSK_TIME_RETRANS	1
+#define ICSK_TIME_PROBE0	3
+#define ICSK_TIME_LOSS_PROBE	5
+#define ICSK_TIME_REO_TIMEOUT	6
+
+#define IFNAMSIZ		16
+
+#define RTF_GATEWAY		0x0002
+
+#define TCP_INFINITE_SSTHRESH	0x7fffffff
+#define TCP_PINGPONG_THRESH	3
+
+#define fib_nh_dev		nh_common.nhc_dev
+#define fib_nh_gw_family	nh_common.nhc_gw_family
+#define fib_nh_gw6		nh_common.nhc_gw.ipv6
+
+#define inet_daddr		sk.__sk_common.skc_daddr
+#define inet_rcv_saddr		sk.__sk_common.skc_rcv_saddr
+#define inet_dport		sk.__sk_common.skc_dport
+
+#define ir_loc_addr		req.__req_common.skc_rcv_saddr
+#define ir_num			req.__req_common.skc_num
+#define ir_rmt_addr		req.__req_common.skc_daddr
+#define ir_rmt_port		req.__req_common.skc_dport
+#define ir_v6_rmt_addr		req.__req_common.skc_v6_daddr
+#define ir_v6_loc_addr		req.__req_common.skc_v6_rcv_saddr
+
+#define sk_family		__sk_common.skc_family
+#define sk_rmem_alloc		sk_backlog.rmem_alloc
+#define sk_refcnt		__sk_common.skc_refcnt
+#define sk_state		__sk_common.skc_state
+#define sk_v6_daddr		__sk_common.skc_v6_daddr
+#define sk_v6_rcv_saddr		__sk_common.skc_v6_rcv_saddr
+
+#define s6_addr32		in6_u.u6_addr32
+
+#define tw_daddr		__tw_common.skc_daddr
+#define tw_rcv_saddr		__tw_common.skc_rcv_saddr
+#define tw_dport		__tw_common.skc_dport
+#define tw_refcnt		__tw_common.skc_refcnt
+#define tw_v6_daddr		__tw_common.skc_v6_daddr
+#define tw_v6_rcv_saddr		__tw_common.skc_v6_rcv_saddr
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/btf_data.c b/tools/testing/selftests/bpf/progs/btf_data.c
new file mode 100644
index 000000000000..baa525275bde
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf_data.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+struct S {
+	int	a;
+	int	b;
+	int	c;
+};
+
+union U {
+	int	a;
+	int	b;
+	int	c;
+};
+
+struct S1 {
+	int	a;
+	int	b;
+	int	c;
+};
+
+union U1 {
+	int	a;
+	int	b;
+	int	c;
+};
+
+typedef int T;
+typedef int S;
+typedef int U;
+typedef int T1;
+typedef int S1;
+typedef int U1;
+
+struct root_struct {
+	S		m_1;
+	T		m_2;
+	U		m_3;
+	S1		m_4;
+	T1		m_5;
+	U1		m_6;
+	struct S	m_7;
+	struct S1	m_8;
+	union  U	m_9;
+	union  U1	m_10;
+};
+
+int func(struct root_struct *root)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi.h b/tools/testing/selftests/bpf/progs/cg_storage_multi.h
new file mode 100644
index 000000000000..a0778fe7857a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cg_storage_multi.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __PROGS_CG_STORAGE_MULTI_H
+#define __PROGS_CG_STORAGE_MULTI_H
+
+#include <asm/types.h>
+
+struct cgroup_value {
+	__u32 egress_pkts;
+	__u32 ingress_pkts;
+};
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c
new file mode 100644
index 000000000000..44ad46b33539
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <errno.h>
+#include <linux/bpf.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <bpf/bpf_helpers.h>
+
+#include "progs/cg_storage_multi.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, struct cgroup_value);
+} cgroup_storage SEC(".maps");
+
+__u32 invocations = 0;
+
+SEC("cgroup_skb/egress")
+int egress(struct __sk_buff *skb)
+{
+	struct cgroup_value *ptr_cg_storage =
+		bpf_get_local_storage(&cgroup_storage, 0);
+
+	__sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1);
+	__sync_fetch_and_add(&invocations, 1);
+
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c
new file mode 100644
index 000000000000..a25373002055
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <errno.h>
+#include <linux/bpf.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <bpf/bpf_helpers.h>
+
+#include "progs/cg_storage_multi.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, struct cgroup_value);
+} cgroup_storage SEC(".maps");
+
+__u32 invocations = 0;
+
+SEC("cgroup_skb/egress/1")
+int egress1(struct __sk_buff *skb)
+{
+	struct cgroup_value *ptr_cg_storage =
+		bpf_get_local_storage(&cgroup_storage, 0);
+
+	__sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1);
+	__sync_fetch_and_add(&invocations, 1);
+
+	return 1;
+}
+
+SEC("cgroup_skb/egress/2")
+int egress2(struct __sk_buff *skb)
+{
+	struct cgroup_value *ptr_cg_storage =
+		bpf_get_local_storage(&cgroup_storage, 0);
+
+	__sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1);
+	__sync_fetch_and_add(&invocations, 1);
+
+	return 1;
+}
+
+SEC("cgroup_skb/ingress")
+int ingress(struct __sk_buff *skb)
+{
+	struct cgroup_value *ptr_cg_storage =
+		bpf_get_local_storage(&cgroup_storage, 0);
+
+	__sync_fetch_and_add(&ptr_cg_storage->ingress_pkts, 1);
+	__sync_fetch_and_add(&invocations, 1);
+
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c
new file mode 100644
index 000000000000..a149f33bc533
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <errno.h>
+#include <linux/bpf.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <bpf/bpf_helpers.h>
+
+#include "progs/cg_storage_multi.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, __u64);
+	__type(value, struct cgroup_value);
+} cgroup_storage SEC(".maps");
+
+__u32 invocations = 0;
+
+SEC("cgroup_skb/egress/1")
+int egress1(struct __sk_buff *skb)
+{
+	struct cgroup_value *ptr_cg_storage =
+		bpf_get_local_storage(&cgroup_storage, 0);
+
+	__sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1);
+	__sync_fetch_and_add(&invocations, 1);
+
+	return 1;
+}
+
+SEC("cgroup_skb/egress/2")
+int egress2(struct __sk_buff *skb)
+{
+	struct cgroup_value *ptr_cg_storage =
+		bpf_get_local_storage(&cgroup_storage, 0);
+
+	__sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1);
+	__sync_fetch_and_add(&invocations, 1);
+
+	return 1;
+}
+
+SEC("cgroup_skb/ingress")
+int ingress(struct __sk_buff *skb)
+{
+	struct cgroup_value *ptr_cg_storage =
+		bpf_get_local_storage(&cgroup_storage, 0);
+
+	__sync_fetch_and_add(&ptr_cg_storage->ingress_pkts, 1);
+	__sync_fetch_and_add(&invocations, 1);
+
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index 1ab2c5eba86c..b1b2773c0b9d 100644
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -104,6 +104,30 @@ static __inline int bind_to_device(struct bpf_sock_addr *ctx)
 	return 0;
 }
 
+static __inline int set_keepalive(struct bpf_sock_addr *ctx)
+{
+	int zero = 0, one = 1;
+
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &one, sizeof(one)))
+		return 1;
+	if (ctx->type == SOCK_STREAM) {
+		if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPIDLE, &one, sizeof(one)))
+			return 1;
+		if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPINTVL, &one, sizeof(one)))
+			return 1;
+		if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPCNT, &one, sizeof(one)))
+			return 1;
+		if (bpf_setsockopt(ctx, SOL_TCP, TCP_SYNCNT, &one, sizeof(one)))
+			return 1;
+		if (bpf_setsockopt(ctx, SOL_TCP, TCP_USER_TIMEOUT, &one, sizeof(one)))
+			return 1;
+	}
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &zero, sizeof(zero)))
+		return 1;
+
+	return 0;
+}
+
 SEC("cgroup/connect4")
 int connect_v4_prog(struct bpf_sock_addr *ctx)
 {
@@ -121,6 +145,9 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
 	if (bind_to_device(ctx))
 		return 0;
 
+	if (set_keepalive(ctx))
+		return 0;
+
 	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
 		return 0;
 	else if (ctx->type == SOCK_STREAM)
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index 34d84717c946..69139ed66216 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -1,5 +1,10 @@
 #include <stdint.h>
 #include <stdbool.h>
+
+void preserce_ptr_sz_fn(long x) {}
+
+#define __bpf_aligned __attribute__((aligned(8)))
+
 /*
  * KERNEL
  */
@@ -444,51 +449,51 @@ struct core_reloc_primitives {
 	char a;
 	int b;
 	enum core_reloc_primitives_enum c;
-	void *d;
-	int (*f)(const char *);
+	void *d __bpf_aligned;
+	int (*f)(const char *) __bpf_aligned;
 };
 
 struct core_reloc_primitives___diff_enum_def {
 	char a;
 	int b;
-	void *d;
-	int (*f)(const char *);
+	void *d __bpf_aligned;
+	int (*f)(const char *) __bpf_aligned;
 	enum {
 		X = 100,
 		Y = 200,
-	} c; /* inline enum def with differing set of values */
+	} c __bpf_aligned; /* inline enum def with differing set of values */
 };
 
 struct core_reloc_primitives___diff_func_proto {
-	void (*f)(int); /* incompatible function prototype */
-	void *d;
-	enum core_reloc_primitives_enum c;
+	void (*f)(int) __bpf_aligned; /* incompatible function prototype */
+	void *d __bpf_aligned;
+	enum core_reloc_primitives_enum c __bpf_aligned;
 	int b;
 	char a;
 };
 
 struct core_reloc_primitives___diff_ptr_type {
-	const char * const d; /* different pointee type + modifiers */
-	char a;
+	const char * const d __bpf_aligned; /* different pointee type + modifiers */
+	char a __bpf_aligned;
 	int b;
 	enum core_reloc_primitives_enum c;
-	int (*f)(const char *);
+	int (*f)(const char *) __bpf_aligned;
 };
 
 struct core_reloc_primitives___err_non_enum {
 	char a[1];
 	int b;
 	int c; /* int instead of enum */
-	void *d;
-	int (*f)(const char *);
+	void *d __bpf_aligned;
+	int (*f)(const char *) __bpf_aligned;
 };
 
 struct core_reloc_primitives___err_non_int {
 	char a[1];
-	int *b; /* ptr instead of int */
-	enum core_reloc_primitives_enum c;
-	void *d;
-	int (*f)(const char *);
+	int *b __bpf_aligned; /* ptr instead of int */
+	enum core_reloc_primitives_enum c __bpf_aligned;
+	void *d __bpf_aligned;
+	int (*f)(const char *) __bpf_aligned;
 };
 
 struct core_reloc_primitives___err_non_ptr {
@@ -496,7 +501,7 @@ struct core_reloc_primitives___err_non_ptr {
 	int b;
 	enum core_reloc_primitives_enum c;
 	int d; /* int instead of ptr */
-	int (*f)(const char *);
+	int (*f)(const char *) __bpf_aligned;
 };
 
 /*
@@ -507,7 +512,7 @@ struct core_reloc_mods_output {
 };
 
 typedef const int int_t;
-typedef const char *char_ptr_t;
+typedef const char *char_ptr_t __bpf_aligned;
 typedef const int arr_t[7];
 
 struct core_reloc_mods_substruct {
@@ -523,9 +528,9 @@ typedef struct {
 struct core_reloc_mods {
 	int a;
 	int_t b;
-	char *c;
+	char *c __bpf_aligned;
 	char_ptr_t d;
-	int e[3];
+	int e[3] __bpf_aligned;
 	arr_t f;
 	struct core_reloc_mods_substruct g;
 	core_reloc_mods_substruct_t h;
@@ -535,9 +540,9 @@ struct core_reloc_mods {
 struct core_reloc_mods___mod_swap {
 	int b;
 	int_t a;
-	char *d;
+	char *d __bpf_aligned;
 	char_ptr_t c;
-	int f[3];
+	int f[3] __bpf_aligned;
 	arr_t e;
 	struct {
 		int y;
@@ -555,7 +560,7 @@ typedef arr1_t arr2_t;
 typedef arr2_t arr3_t;
 typedef arr3_t arr4_t;
 
-typedef const char * const volatile fancy_char_ptr_t;
+typedef const char * const volatile fancy_char_ptr_t __bpf_aligned;
 
 typedef core_reloc_mods_substruct_t core_reloc_mods_substruct_tt;
 
@@ -567,7 +572,7 @@ struct core_reloc_mods___typedefs {
 	arr4_t e;
 	fancy_char_ptr_t d;
 	fancy_char_ptr_t c;
-	int3_t b;
+	int3_t b __bpf_aligned;
 	int3_t a;
 };
 
@@ -739,19 +744,19 @@ struct core_reloc_bitfields___bit_sz_change {
 	int8_t		sb4: 1;		/*  4 ->  1 */
 	int32_t		sb20: 30;	/* 20 -> 30 */
 	/* non-bitfields */
-	uint16_t	u32;		/* 32 -> 16 */
-	int64_t		s32;		/* 32 -> 64 */
+	uint16_t	u32;			/* 32 -> 16 */
+	int64_t		s32 __bpf_aligned;	/* 32 -> 64 */
 };
 
 /* turn bitfield into non-bitfield and vice versa */
 struct core_reloc_bitfields___bitfield_vs_int {
 	uint64_t	ub1;		/*  3 -> 64 non-bitfield */
 	uint8_t		ub2;		/* 20 ->  8 non-bitfield */
-	int64_t		ub7;		/*  7 -> 64 non-bitfield signed */
-	int64_t		sb4;		/*  4 -> 64 non-bitfield signed */
-	uint64_t	sb20;		/* 20 -> 16 non-bitfield unsigned */
-	int32_t		u32: 20;	/* 32 non-bitfield -> 20 bitfield */
-	uint64_t	s32: 60;	/* 32 non-bitfield -> 60 bitfield */
+	int64_t		ub7 __bpf_aligned;	/*  7 -> 64 non-bitfield signed */
+	int64_t		sb4 __bpf_aligned;	/*  4 -> 64 non-bitfield signed */
+	uint64_t	sb20 __bpf_aligned;	/* 20 -> 16 non-bitfield unsigned */
+	int32_t		u32: 20;		/* 32 non-bitfield -> 20 bitfield */
+	uint64_t	s32: 60 __bpf_aligned;	/* 32 non-bitfield -> 60 bitfield */
 };
 
 struct core_reloc_bitfields___just_big_enough {
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
new file mode 100644
index 000000000000..473665cac67e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -0,0 +1,686 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define LOOP_BOUND 0xf
+#define MAX_ENTRIES 8
+#define HALF_ENTRIES (MAX_ENTRIES >> 1)
+
+_Static_assert(MAX_ENTRIES < LOOP_BOUND, "MAX_ENTRIES must be < LOOP_BOUND");
+
+enum bpf_map_type g_map_type = BPF_MAP_TYPE_UNSPEC;
+__u32 g_line = 0;
+
+#define VERIFY_TYPE(type, func) ({	\
+	g_map_type = type;		\
+	if (!func())			\
+		return 0;		\
+})
+
+
+#define VERIFY(expr) ({		\
+	g_line = __LINE__;	\
+	if (!(expr))		\
+		return 0;	\
+})
+
+struct bpf_map_memory {
+	__u32 pages;
+} __attribute__((preserve_access_index));
+
+struct bpf_map {
+	enum bpf_map_type map_type;
+	__u32 key_size;
+	__u32 value_size;
+	__u32 max_entries;
+	__u32 id;
+	struct bpf_map_memory memory;
+} __attribute__((preserve_access_index));
+
+static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size,
+				       __u32 value_size, __u32 max_entries)
+{
+	VERIFY(map->map_type == g_map_type);
+	VERIFY(map->key_size == key_size);
+	VERIFY(map->value_size == value_size);
+	VERIFY(map->max_entries == max_entries);
+	VERIFY(map->id > 0);
+	VERIFY(map->memory.pages > 0);
+
+	return 1;
+}
+
+static inline int check_bpf_map_ptr(struct bpf_map *indirect,
+				    struct bpf_map *direct)
+{
+	VERIFY(indirect->map_type == direct->map_type);
+	VERIFY(indirect->key_size == direct->key_size);
+	VERIFY(indirect->value_size == direct->value_size);
+	VERIFY(indirect->max_entries == direct->max_entries);
+	VERIFY(indirect->id == direct->id);
+	VERIFY(indirect->memory.pages == direct->memory.pages);
+
+	return 1;
+}
+
+static inline int check(struct bpf_map *indirect, struct bpf_map *direct,
+			__u32 key_size, __u32 value_size, __u32 max_entries)
+{
+	VERIFY(check_bpf_map_ptr(indirect, direct));
+	VERIFY(check_bpf_map_fields(indirect, key_size, value_size,
+				    max_entries));
+	return 1;
+}
+
+static inline int check_default(struct bpf_map *indirect,
+				struct bpf_map *direct)
+{
+	VERIFY(check(indirect, direct, sizeof(__u32), sizeof(__u32),
+		     MAX_ENTRIES));
+	return 1;
+}
+
+typedef struct {
+	int counter;
+} atomic_t;
+
+struct bpf_htab {
+	struct bpf_map map;
+	atomic_t count;
+	__u32 n_buckets;
+	__u32 elem_size;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC); /* to test bpf_htab.count */
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_hash SEC(".maps");
+
+static inline int check_hash(void)
+{
+	struct bpf_htab *hash = (struct bpf_htab *)&m_hash;
+	struct bpf_map *map = (struct bpf_map *)&m_hash;
+	int i;
+
+	VERIFY(check_default(&hash->map, map));
+
+	VERIFY(hash->n_buckets == MAX_ENTRIES);
+	VERIFY(hash->elem_size == 64);
+
+	VERIFY(hash->count.counter == 0);
+	for (i = 0; i < HALF_ENTRIES; ++i) {
+		const __u32 key = i;
+		const __u32 val = 1;
+
+		if (bpf_map_update_elem(hash, &key, &val, 0))
+			return 0;
+	}
+	VERIFY(hash->count.counter == HALF_ENTRIES);
+
+	return 1;
+}
+
+struct bpf_array {
+	struct bpf_map map;
+	__u32 elem_size;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_array SEC(".maps");
+
+static inline int check_array(void)
+{
+	struct bpf_array *array = (struct bpf_array *)&m_array;
+	struct bpf_map *map = (struct bpf_map *)&m_array;
+	int i, n_lookups = 0, n_keys = 0;
+
+	VERIFY(check_default(&array->map, map));
+
+	VERIFY(array->elem_size == 8);
+
+	for (i = 0; i < array->map.max_entries && i < LOOP_BOUND; ++i) {
+		const __u32 key = i;
+		__u32 *val = bpf_map_lookup_elem(array, &key);
+
+		++n_lookups;
+		if (val)
+			++n_keys;
+	}
+
+	VERIFY(n_lookups == MAX_ENTRIES);
+	VERIFY(n_keys == MAX_ENTRIES);
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_prog_array SEC(".maps");
+
+static inline int check_prog_array(void)
+{
+	struct bpf_array *prog_array = (struct bpf_array *)&m_prog_array;
+	struct bpf_map *map = (struct bpf_map *)&m_prog_array;
+
+	VERIFY(check_default(&prog_array->map, map));
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_perf_event_array SEC(".maps");
+
+static inline int check_perf_event_array(void)
+{
+	struct bpf_array *perf_event_array = (struct bpf_array *)&m_perf_event_array;
+	struct bpf_map *map = (struct bpf_map *)&m_perf_event_array;
+
+	VERIFY(check_default(&perf_event_array->map, map));
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_percpu_hash SEC(".maps");
+
+static inline int check_percpu_hash(void)
+{
+	struct bpf_htab *percpu_hash = (struct bpf_htab *)&m_percpu_hash;
+	struct bpf_map *map = (struct bpf_map *)&m_percpu_hash;
+
+	VERIFY(check_default(&percpu_hash->map, map));
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_percpu_array SEC(".maps");
+
+static inline int check_percpu_array(void)
+{
+	struct bpf_array *percpu_array = (struct bpf_array *)&m_percpu_array;
+	struct bpf_map *map = (struct bpf_map *)&m_percpu_array;
+
+	VERIFY(check_default(&percpu_array->map, map));
+
+	return 1;
+}
+
+struct bpf_stack_map {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u64);
+} m_stack_trace SEC(".maps");
+
+static inline int check_stack_trace(void)
+{
+	struct bpf_stack_map *stack_trace =
+		(struct bpf_stack_map *)&m_stack_trace;
+	struct bpf_map *map = (struct bpf_map *)&m_stack_trace;
+
+	VERIFY(check(&stack_trace->map, map, sizeof(__u32), sizeof(__u64),
+		     MAX_ENTRIES));
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_ARRAY);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_cgroup_array SEC(".maps");
+
+static inline int check_cgroup_array(void)
+{
+	struct bpf_array *cgroup_array = (struct bpf_array *)&m_cgroup_array;
+	struct bpf_map *map = (struct bpf_map *)&m_cgroup_array;
+
+	VERIFY(check_default(&cgroup_array->map, map));
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_lru_hash SEC(".maps");
+
+static inline int check_lru_hash(void)
+{
+	struct bpf_htab *lru_hash = (struct bpf_htab *)&m_lru_hash;
+	struct bpf_map *map = (struct bpf_map *)&m_lru_hash;
+
+	VERIFY(check_default(&lru_hash->map, map));
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_PERCPU_HASH);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_lru_percpu_hash SEC(".maps");
+
+static inline int check_lru_percpu_hash(void)
+{
+	struct bpf_htab *lru_percpu_hash = (struct bpf_htab *)&m_lru_percpu_hash;
+	struct bpf_map *map = (struct bpf_map *)&m_lru_percpu_hash;
+
+	VERIFY(check_default(&lru_percpu_hash->map, map));
+
+	return 1;
+}
+
+struct lpm_trie {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct lpm_key {
+	struct bpf_lpm_trie_key trie_key;
+	__u32 data;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LPM_TRIE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, struct lpm_key);
+	__type(value, __u32);
+} m_lpm_trie SEC(".maps");
+
+static inline int check_lpm_trie(void)
+{
+	struct lpm_trie *lpm_trie = (struct lpm_trie *)&m_lpm_trie;
+	struct bpf_map *map = (struct bpf_map *)&m_lpm_trie;
+
+	VERIFY(check(&lpm_trie->map, map, sizeof(struct lpm_key), sizeof(__u32),
+		     MAX_ENTRIES));
+
+	return 1;
+}
+
+struct inner_map {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} inner_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+	__array(values, struct {
+		__uint(type, BPF_MAP_TYPE_ARRAY);
+		__uint(max_entries, 1);
+		__type(key, __u32);
+		__type(value, __u32);
+	});
+} m_array_of_maps SEC(".maps") = {
+	.values = { (void *)&inner_map, 0, 0, 0, 0, 0, 0, 0, 0 },
+};
+
+static inline int check_array_of_maps(void)
+{
+	struct bpf_array *array_of_maps = (struct bpf_array *)&m_array_of_maps;
+	struct bpf_map *map = (struct bpf_map *)&m_array_of_maps;
+
+	VERIFY(check_default(&array_of_maps->map, map));
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+	__array(values, struct inner_map);
+} m_hash_of_maps SEC(".maps") = {
+	.values = {
+		[2] = &inner_map,
+	},
+};
+
+static inline int check_hash_of_maps(void)
+{
+	struct bpf_htab *hash_of_maps = (struct bpf_htab *)&m_hash_of_maps;
+	struct bpf_map *map = (struct bpf_map *)&m_hash_of_maps;
+
+	VERIFY(check_default(&hash_of_maps->map, map));
+
+	return 1;
+}
+
+struct bpf_dtab {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_devmap SEC(".maps");
+
+static inline int check_devmap(void)
+{
+	struct bpf_dtab *devmap = (struct bpf_dtab *)&m_devmap;
+	struct bpf_map *map = (struct bpf_map *)&m_devmap;
+
+	VERIFY(check_default(&devmap->map, map));
+
+	return 1;
+}
+
+struct bpf_stab {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_sockmap SEC(".maps");
+
+static inline int check_sockmap(void)
+{
+	struct bpf_stab *sockmap = (struct bpf_stab *)&m_sockmap;
+	struct bpf_map *map = (struct bpf_map *)&m_sockmap;
+
+	VERIFY(check_default(&sockmap->map, map));
+
+	return 1;
+}
+
+struct bpf_cpu_map {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CPUMAP);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_cpumap SEC(".maps");
+
+static inline int check_cpumap(void)
+{
+	struct bpf_cpu_map *cpumap = (struct bpf_cpu_map *)&m_cpumap;
+	struct bpf_map *map = (struct bpf_map *)&m_cpumap;
+
+	VERIFY(check_default(&cpumap->map, map));
+
+	return 1;
+}
+
+struct xsk_map {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_xskmap SEC(".maps");
+
+static inline int check_xskmap(void)
+{
+	struct xsk_map *xskmap = (struct xsk_map *)&m_xskmap;
+	struct bpf_map *map = (struct bpf_map *)&m_xskmap;
+
+	VERIFY(check_default(&xskmap->map, map));
+
+	return 1;
+}
+
+struct bpf_shtab {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKHASH);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_sockhash SEC(".maps");
+
+static inline int check_sockhash(void)
+{
+	struct bpf_shtab *sockhash = (struct bpf_shtab *)&m_sockhash;
+	struct bpf_map *map = (struct bpf_map *)&m_sockhash;
+
+	VERIFY(check_default(&sockhash->map, map));
+
+	return 1;
+}
+
+struct bpf_cgroup_storage_map {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, __u32);
+} m_cgroup_storage SEC(".maps");
+
+static inline int check_cgroup_storage(void)
+{
+	struct bpf_cgroup_storage_map *cgroup_storage =
+		(struct bpf_cgroup_storage_map *)&m_cgroup_storage;
+	struct bpf_map *map = (struct bpf_map *)&m_cgroup_storage;
+
+	VERIFY(check(&cgroup_storage->map, map,
+		     sizeof(struct bpf_cgroup_storage_key), sizeof(__u32), 0));
+
+	return 1;
+}
+
+struct reuseport_array {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_reuseport_sockarray SEC(".maps");
+
+static inline int check_reuseport_sockarray(void)
+{
+	struct reuseport_array *reuseport_sockarray =
+		(struct reuseport_array *)&m_reuseport_sockarray;
+	struct bpf_map *map = (struct bpf_map *)&m_reuseport_sockarray;
+
+	VERIFY(check_default(&reuseport_sockarray->map, map));
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, __u32);
+} m_percpu_cgroup_storage SEC(".maps");
+
+static inline int check_percpu_cgroup_storage(void)
+{
+	struct bpf_cgroup_storage_map *percpu_cgroup_storage =
+		(struct bpf_cgroup_storage_map *)&m_percpu_cgroup_storage;
+	struct bpf_map *map = (struct bpf_map *)&m_percpu_cgroup_storage;
+
+	VERIFY(check(&percpu_cgroup_storage->map, map,
+		     sizeof(struct bpf_cgroup_storage_key), sizeof(__u32), 0));
+
+	return 1;
+}
+
+struct bpf_queue_stack {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_QUEUE);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(value, __u32);
+} m_queue SEC(".maps");
+
+static inline int check_queue(void)
+{
+	struct bpf_queue_stack *queue = (struct bpf_queue_stack *)&m_queue;
+	struct bpf_map *map = (struct bpf_map *)&m_queue;
+
+	VERIFY(check(&queue->map, map, 0, sizeof(__u32), MAX_ENTRIES));
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(value, __u32);
+} m_stack SEC(".maps");
+
+static inline int check_stack(void)
+{
+	struct bpf_queue_stack *stack = (struct bpf_queue_stack *)&m_stack;
+	struct bpf_map *map = (struct bpf_map *)&m_stack;
+
+	VERIFY(check(&stack->map, map, 0, sizeof(__u32), MAX_ENTRIES));
+
+	return 1;
+}
+
+struct bpf_sk_storage_map {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_sk_storage SEC(".maps");
+
+static inline int check_sk_storage(void)
+{
+	struct bpf_sk_storage_map *sk_storage =
+		(struct bpf_sk_storage_map *)&m_sk_storage;
+	struct bpf_map *map = (struct bpf_map *)&m_sk_storage;
+
+	VERIFY(check(&sk_storage->map, map, sizeof(__u32), sizeof(__u32), 0));
+
+	return 1;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+	__uint(max_entries, MAX_ENTRIES);
+	__type(key, __u32);
+	__type(value, __u32);
+} m_devmap_hash SEC(".maps");
+
+static inline int check_devmap_hash(void)
+{
+	struct bpf_dtab *devmap_hash = (struct bpf_dtab *)&m_devmap_hash;
+	struct bpf_map *map = (struct bpf_map *)&m_devmap_hash;
+
+	VERIFY(check_default(&devmap_hash->map, map));
+
+	return 1;
+}
+
+struct bpf_ringbuf_map {
+	struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 1 << 12);
+} m_ringbuf SEC(".maps");
+
+static inline int check_ringbuf(void)
+{
+	struct bpf_ringbuf_map *ringbuf = (struct bpf_ringbuf_map *)&m_ringbuf;
+	struct bpf_map *map = (struct bpf_map *)&m_ringbuf;
+
+	VERIFY(check(&ringbuf->map, map, 0, 0, 1 << 12));
+
+	return 1;
+}
+
+SEC("cgroup_skb/egress")
+int cg_skb(void *ctx)
+{
+	VERIFY_TYPE(BPF_MAP_TYPE_HASH, check_hash);
+	VERIFY_TYPE(BPF_MAP_TYPE_ARRAY, check_array);
+	VERIFY_TYPE(BPF_MAP_TYPE_PROG_ARRAY, check_prog_array);
+	VERIFY_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, check_perf_event_array);
+	VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_HASH, check_percpu_hash);
+	VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, check_percpu_array);
+	VERIFY_TYPE(BPF_MAP_TYPE_STACK_TRACE, check_stack_trace);
+	VERIFY_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, check_cgroup_array);
+	VERIFY_TYPE(BPF_MAP_TYPE_LRU_HASH, check_lru_hash);
+	VERIFY_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, check_lru_percpu_hash);
+	VERIFY_TYPE(BPF_MAP_TYPE_LPM_TRIE, check_lpm_trie);
+	VERIFY_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, check_array_of_maps);
+	VERIFY_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, check_hash_of_maps);
+	VERIFY_TYPE(BPF_MAP_TYPE_DEVMAP, check_devmap);
+	VERIFY_TYPE(BPF_MAP_TYPE_SOCKMAP, check_sockmap);
+	VERIFY_TYPE(BPF_MAP_TYPE_CPUMAP, check_cpumap);
+	VERIFY_TYPE(BPF_MAP_TYPE_XSKMAP, check_xskmap);
+	VERIFY_TYPE(BPF_MAP_TYPE_SOCKHASH, check_sockhash);
+	VERIFY_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, check_cgroup_storage);
+	VERIFY_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+		    check_reuseport_sockarray);
+	VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+		    check_percpu_cgroup_storage);
+	VERIFY_TYPE(BPF_MAP_TYPE_QUEUE, check_queue);
+	VERIFY_TYPE(BPF_MAP_TYPE_STACK, check_stack);
+	VERIFY_TYPE(BPF_MAP_TYPE_SK_STORAGE, check_sk_storage);
+	VERIFY_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, check_devmap_hash);
+	VERIFY_TYPE(BPF_MAP_TYPE_RINGBUF, check_ringbuf);
+
+	return 1;
+}
+
+__u32 _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c
new file mode 100644
index 000000000000..25467d13c356
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+#ifndef PERF_MAX_STACK_DEPTH
+#define PERF_MAX_STACK_DEPTH         127
+#endif
+
+typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH];
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, 16384);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(stack_trace_t));
+} stackmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, stack_trace_t);
+} stackdata_map SEC(".maps");
+
+long stackid_kernel = 1;
+long stackid_user = 1;
+long stack_kernel = 1;
+long stack_user = 1;
+
+SEC("perf_event")
+int oncpu(void *ctx)
+{
+	stack_trace_t *trace;
+	__u32 key = 0;
+	long val;
+
+	val = bpf_get_stackid(ctx, &stackmap, 0);
+	if (val > 0)
+		stackid_kernel = 2;
+	val = bpf_get_stackid(ctx, &stackmap, BPF_F_USER_STACK);
+	if (val > 0)
+		stackid_user = 2;
+
+	trace = bpf_map_lookup_elem(&stackdata_map, &key);
+	if (!trace)
+		return 0;
+
+	val = bpf_get_stack(ctx, trace, sizeof(stack_trace_t), 0);
+	if (val > 0)
+		stack_kernel = 2;
+
+	val = bpf_get_stack(ctx, trace, sizeof(stack_trace_t), BPF_F_USER_STACK);
+	if (val > 0)
+		stack_user = 2;
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_autoload.c b/tools/testing/selftests/bpf/progs/test_autoload.c
new file mode 100644
index 000000000000..62c8cdec6d5d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_autoload.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+bool prog1_called = false;
+bool prog2_called = false;
+bool prog3_called = false;
+
+SEC("raw_tp/sys_enter")
+int prog1(const void *ctx)
+{
+	prog1_called = true;
+	return 0;
+}
+
+SEC("raw_tp/sys_exit")
+int prog2(const void *ctx)
+{
+	prog2_called = true;
+	return 0;
+}
+
+struct fake_kernel_struct {
+	int whatever;
+} __attribute__((preserve_access_index));
+
+SEC("fentry/unexisting-kprobe-will-fail-if-loaded")
+int prog3(const void *ctx)
+{
+	struct fake_kernel_struct *fake = (void *)ctx;
+	fake->whatever = 123;
+	prog3_called = true;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_retro.c b/tools/testing/selftests/bpf/progs/test_core_retro.c
new file mode 100644
index 000000000000..20861ec2f674
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_core_retro.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+struct task_struct {
+	int tgid;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} exp_tgid_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} results SEC(".maps");
+
+SEC("tp/raw_syscalls/sys_enter")
+int handle_sys_enter(void *ctx)
+{
+	struct task_struct *task = (void *)bpf_get_current_task();
+	int tgid = BPF_CORE_READ(task, tgid);
+	int zero = 0;
+	int real_tgid = bpf_get_current_pid_tgid() >> 32;
+	int *exp_tgid = bpf_map_lookup_elem(&exp_tgid_map, &zero);
+
+	/* only pass through sys_enters from test process */
+	if (!exp_tgid || *exp_tgid != real_tgid)
+		return 0;
+
+	bpf_map_update_elem(&results, &zero, &tgid, 0);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_endian.c b/tools/testing/selftests/bpf/progs/test_endian.c
new file mode 100644
index 000000000000..ddb687c5d125
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_endian.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define IN16 0x1234
+#define IN32 0x12345678U
+#define IN64 0x123456789abcdef0ULL
+
+__u16 in16 = 0;
+__u32 in32 = 0;
+__u64 in64 = 0;
+
+__u16 out16 = 0;
+__u32 out32 = 0;
+__u64 out64 = 0;
+
+__u16 const16 = 0;
+__u32 const32 = 0;
+__u64 const64 = 0;
+
+SEC("raw_tp/sys_enter")
+int sys_enter(const void *ctx)
+{
+	out16 = __builtin_bswap16(in16);
+	out32 = __builtin_bswap32(in32);
+	out64 = __builtin_bswap64(in64);
+	const16 = ___bpf_swab16(IN16);
+	const32 = ___bpf_swab32(IN32);
+	const64 = ___bpf_swab64(IN64);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
index 29817a703984..b6a6eb279e54 100644
--- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
@@ -57,8 +57,9 @@ struct {
 SEC("raw_tracepoint/sys_enter")
 int bpf_prog1(void *ctx)
 {
-	int max_len, max_buildid_len, usize, ksize, total_size;
+	int max_len, max_buildid_len, total_size;
 	struct stack_trace_t *data;
+	long usize, ksize;
 	void *raw_data;
 	__u32 key = 0;
 
diff --git a/tools/testing/selftests/bpf/progs/test_ksyms.c b/tools/testing/selftests/bpf/progs/test_ksyms.c
new file mode 100644
index 000000000000..6c9cbb5a3bdf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ksyms.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__u64 out__bpf_link_fops = -1;
+__u64 out__bpf_link_fops1 = -1;
+__u64 out__btf_size = -1;
+__u64 out__per_cpu_start = -1;
+
+extern const void bpf_link_fops __ksym;
+extern const void __start_BTF __ksym;
+extern const void __stop_BTF __ksym;
+extern const void __per_cpu_start __ksym;
+/* non-existing symbol, weak, default to zero */
+extern const void bpf_link_fops1 __ksym __weak;
+
+SEC("raw_tp/sys_enter")
+int handler(const void *ctx)
+{
+	out__bpf_link_fops = (__u64)&bpf_link_fops;
+	out__btf_size = (__u64)(&__stop_BTF - &__start_BTF);
+	out__per_cpu_start = (__u64)&__per_cpu_start;
+
+	out__bpf_link_fops1 = (__u64)&bpf_link_fops1;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
index ad59c4c9aba8..8207a2dc2f9d 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -12,8 +12,8 @@ struct {
 	__uint(value_size, sizeof(int));
 } perf_buf_map SEC(".maps");
 
-SEC("kprobe/sys_nanosleep")
-int BPF_KPROBE(handle_sys_nanosleep_entry)
+SEC("tp/raw_syscalls/sys_enter")
+int handle_sys_enter(void *ctx)
 {
 	int cpu = bpf_get_smp_processor_id();
 
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
new file mode 100644
index 000000000000..bbf8296f4d66
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
@@ -0,0 +1,641 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+// Copyright (c) 2020 Cloudflare
+
+#include <errno.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+#define IP4(a, b, c, d)					\
+	bpf_htonl((((__u32)(a) & 0xffU) << 24) |	\
+		  (((__u32)(b) & 0xffU) << 16) |	\
+		  (((__u32)(c) & 0xffU) <<  8) |	\
+		  (((__u32)(d) & 0xffU) <<  0))
+#define IP6(aaaa, bbbb, cccc, dddd)			\
+	{ bpf_htonl(aaaa), bpf_htonl(bbbb), bpf_htonl(cccc), bpf_htonl(dddd) }
+
+#define MAX_SOCKS 32
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, MAX_SOCKS);
+	__type(key, __u32);
+	__type(value, __u64);
+} redir_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, int);
+	__type(value, int);
+} run_map SEC(".maps");
+
+enum {
+	PROG1 = 0,
+	PROG2,
+};
+
+enum {
+	SERVER_A = 0,
+	SERVER_B,
+};
+
+/* Addressable key/value constants for convenience */
+static const int KEY_PROG1 = PROG1;
+static const int KEY_PROG2 = PROG2;
+static const int PROG_DONE = 1;
+
+static const __u32 KEY_SERVER_A = SERVER_A;
+static const __u32 KEY_SERVER_B = SERVER_B;
+
+static const __u16 DST_PORT = 7007; /* Host byte order */
+static const __u32 DST_IP4 = IP4(127, 0, 0, 1);
+static const __u32 DST_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000001);
+
+SEC("sk_lookup/lookup_pass")
+int lookup_pass(struct bpf_sk_lookup *ctx)
+{
+	return SK_PASS;
+}
+
+SEC("sk_lookup/lookup_drop")
+int lookup_drop(struct bpf_sk_lookup *ctx)
+{
+	return SK_DROP;
+}
+
+SEC("sk_reuseport/reuse_pass")
+int reuseport_pass(struct sk_reuseport_md *ctx)
+{
+	return SK_PASS;
+}
+
+SEC("sk_reuseport/reuse_drop")
+int reuseport_drop(struct sk_reuseport_md *ctx)
+{
+	return SK_DROP;
+}
+
+/* Redirect packets destined for port DST_PORT to socket at redir_map[0]. */
+SEC("sk_lookup/redir_port")
+int redir_port(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk;
+	int err;
+
+	if (ctx->local_port != DST_PORT)
+		return SK_PASS;
+
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A);
+	if (!sk)
+		return SK_PASS;
+
+	err = bpf_sk_assign(ctx, sk, 0);
+	bpf_sk_release(sk);
+	return err ? SK_DROP : SK_PASS;
+}
+
+/* Redirect packets destined for DST_IP4 address to socket at redir_map[0]. */
+SEC("sk_lookup/redir_ip4")
+int redir_ip4(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk;
+	int err;
+
+	if (ctx->family != AF_INET)
+		return SK_PASS;
+	if (ctx->local_port != DST_PORT)
+		return SK_PASS;
+	if (ctx->local_ip4 != DST_IP4)
+		return SK_PASS;
+
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A);
+	if (!sk)
+		return SK_PASS;
+
+	err = bpf_sk_assign(ctx, sk, 0);
+	bpf_sk_release(sk);
+	return err ? SK_DROP : SK_PASS;
+}
+
+/* Redirect packets destined for DST_IP6 address to socket at redir_map[0]. */
+SEC("sk_lookup/redir_ip6")
+int redir_ip6(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk;
+	int err;
+
+	if (ctx->family != AF_INET6)
+		return SK_PASS;
+	if (ctx->local_port != DST_PORT)
+		return SK_PASS;
+	if (ctx->local_ip6[0] != DST_IP6[0] ||
+	    ctx->local_ip6[1] != DST_IP6[1] ||
+	    ctx->local_ip6[2] != DST_IP6[2] ||
+	    ctx->local_ip6[3] != DST_IP6[3])
+		return SK_PASS;
+
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A);
+	if (!sk)
+		return SK_PASS;
+
+	err = bpf_sk_assign(ctx, sk, 0);
+	bpf_sk_release(sk);
+	return err ? SK_DROP : SK_PASS;
+}
+
+SEC("sk_lookup/select_sock_a")
+int select_sock_a(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk;
+	int err;
+
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A);
+	if (!sk)
+		return SK_PASS;
+
+	err = bpf_sk_assign(ctx, sk, 0);
+	bpf_sk_release(sk);
+	return err ? SK_DROP : SK_PASS;
+}
+
+SEC("sk_lookup/select_sock_a_no_reuseport")
+int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk;
+	int err;
+
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A);
+	if (!sk)
+		return SK_DROP;
+
+	err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_NO_REUSEPORT);
+	bpf_sk_release(sk);
+	return err ? SK_DROP : SK_PASS;
+}
+
+SEC("sk_reuseport/select_sock_b")
+int select_sock_b(struct sk_reuseport_md *ctx)
+{
+	__u32 key = KEY_SERVER_B;
+	int err;
+
+	err = bpf_sk_select_reuseport(ctx, &redir_map, &key, 0);
+	return err ? SK_DROP : SK_PASS;
+}
+
+/* Check that bpf_sk_assign() returns -EEXIST if socket already selected. */
+SEC("sk_lookup/sk_assign_eexist")
+int sk_assign_eexist(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk;
+	int err, ret;
+
+	ret = SK_DROP;
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B);
+	if (!sk)
+		goto out;
+	err = bpf_sk_assign(ctx, sk, 0);
+	if (err)
+		goto out;
+	bpf_sk_release(sk);
+
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A);
+	if (!sk)
+		goto out;
+	err = bpf_sk_assign(ctx, sk, 0);
+	if (err != -EEXIST) {
+		bpf_printk("sk_assign returned %d, expected %d\n",
+			   err, -EEXIST);
+		goto out;
+	}
+
+	ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */
+out:
+	if (sk)
+		bpf_sk_release(sk);
+	return ret;
+}
+
+/* Check that bpf_sk_assign(BPF_SK_LOOKUP_F_REPLACE) can override selection. */
+SEC("sk_lookup/sk_assign_replace_flag")
+int sk_assign_replace_flag(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk;
+	int err, ret;
+
+	ret = SK_DROP;
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A);
+	if (!sk)
+		goto out;
+	err = bpf_sk_assign(ctx, sk, 0);
+	if (err)
+		goto out;
+	bpf_sk_release(sk);
+
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B);
+	if (!sk)
+		goto out;
+	err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE);
+	if (err) {
+		bpf_printk("sk_assign returned %d, expected 0\n", err);
+		goto out;
+	}
+
+	ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */
+out:
+	if (sk)
+		bpf_sk_release(sk);
+	return ret;
+}
+
+/* Check that bpf_sk_assign(sk=NULL) is accepted. */
+SEC("sk_lookup/sk_assign_null")
+int sk_assign_null(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk = NULL;
+	int err, ret;
+
+	ret = SK_DROP;
+
+	err = bpf_sk_assign(ctx, NULL, 0);
+	if (err) {
+		bpf_printk("sk_assign returned %d, expected 0\n", err);
+		goto out;
+	}
+
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B);
+	if (!sk)
+		goto out;
+	err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE);
+	if (err) {
+		bpf_printk("sk_assign returned %d, expected 0\n", err);
+		goto out;
+	}
+
+	if (ctx->sk != sk)
+		goto out;
+	err = bpf_sk_assign(ctx, NULL, 0);
+	if (err != -EEXIST)
+		goto out;
+	err = bpf_sk_assign(ctx, NULL, BPF_SK_LOOKUP_F_REPLACE);
+	if (err)
+		goto out;
+	err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE);
+	if (err)
+		goto out;
+
+	ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */
+out:
+	if (sk)
+		bpf_sk_release(sk);
+	return ret;
+}
+
+/* Check that selected sk is accessible through context. */
+SEC("sk_lookup/access_ctx_sk")
+int access_ctx_sk(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk1 = NULL, *sk2 = NULL;
+	int err, ret;
+
+	ret = SK_DROP;
+
+	/* Try accessing unassigned (NULL) ctx->sk field */
+	if (ctx->sk && ctx->sk->family != AF_INET)
+		goto out;
+
+	/* Assign a value to ctx->sk */
+	sk1 = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A);
+	if (!sk1)
+		goto out;
+	err = bpf_sk_assign(ctx, sk1, 0);
+	if (err)
+		goto out;
+	if (ctx->sk != sk1)
+		goto out;
+
+	/* Access ctx->sk fields */
+	if (ctx->sk->family != AF_INET ||
+	    ctx->sk->type != SOCK_STREAM ||
+	    ctx->sk->state != BPF_TCP_LISTEN)
+		goto out;
+
+	/* Reset selection */
+	err = bpf_sk_assign(ctx, NULL, BPF_SK_LOOKUP_F_REPLACE);
+	if (err)
+		goto out;
+	if (ctx->sk)
+		goto out;
+
+	/* Assign another socket */
+	sk2 = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B);
+	if (!sk2)
+		goto out;
+	err = bpf_sk_assign(ctx, sk2, BPF_SK_LOOKUP_F_REPLACE);
+	if (err)
+		goto out;
+	if (ctx->sk != sk2)
+		goto out;
+
+	/* Access reassigned ctx->sk fields */
+	if (ctx->sk->family != AF_INET ||
+	    ctx->sk->type != SOCK_STREAM ||
+	    ctx->sk->state != BPF_TCP_LISTEN)
+		goto out;
+
+	ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */
+out:
+	if (sk1)
+		bpf_sk_release(sk1);
+	if (sk2)
+		bpf_sk_release(sk2);
+	return ret;
+}
+
+/* Check narrow loads from ctx fields that support them.
+ *
+ * Narrow loads of size >= target field size from a non-zero offset
+ * are not covered because they give bogus results, that is the
+ * verifier ignores the offset.
+ */
+SEC("sk_lookup/ctx_narrow_access")
+int ctx_narrow_access(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk;
+	int err, family;
+	__u16 *half;
+	__u8 *byte;
+	bool v4;
+
+	v4 = (ctx->family == AF_INET);
+
+	/* Narrow loads from family field */
+	byte = (__u8 *)&ctx->family;
+	half = (__u16 *)&ctx->family;
+	if (byte[0] != (v4 ? AF_INET : AF_INET6) ||
+	    byte[1] != 0 || byte[2] != 0 || byte[3] != 0)
+		return SK_DROP;
+	if (half[0] != (v4 ? AF_INET : AF_INET6))
+		return SK_DROP;
+
+	byte = (__u8 *)&ctx->protocol;
+	if (byte[0] != IPPROTO_TCP ||
+	    byte[1] != 0 || byte[2] != 0 || byte[3] != 0)
+		return SK_DROP;
+	half = (__u16 *)&ctx->protocol;
+	if (half[0] != IPPROTO_TCP)
+		return SK_DROP;
+
+	/* Narrow loads from remote_port field. Expect non-0 value. */
+	byte = (__u8 *)&ctx->remote_port;
+	if (byte[0] == 0 && byte[1] == 0 && byte[2] == 0 && byte[3] == 0)
+		return SK_DROP;
+	half = (__u16 *)&ctx->remote_port;
+	if (half[0] == 0)
+		return SK_DROP;
+
+	/* Narrow loads from local_port field. Expect DST_PORT. */
+	byte = (__u8 *)&ctx->local_port;
+	if (byte[0] != ((DST_PORT >> 0) & 0xff) ||
+	    byte[1] != ((DST_PORT >> 8) & 0xff) ||
+	    byte[2] != 0 || byte[3] != 0)
+		return SK_DROP;
+	half = (__u16 *)&ctx->local_port;
+	if (half[0] != DST_PORT)
+		return SK_DROP;
+
+	/* Narrow loads from IPv4 fields */
+	if (v4) {
+		/* Expect non-0.0.0.0 in remote_ip4 */
+		byte = (__u8 *)&ctx->remote_ip4;
+		if (byte[0] == 0 && byte[1] == 0 &&
+		    byte[2] == 0 && byte[3] == 0)
+			return SK_DROP;
+		half = (__u16 *)&ctx->remote_ip4;
+		if (half[0] == 0 && half[1] == 0)
+			return SK_DROP;
+
+		/* Expect DST_IP4 in local_ip4 */
+		byte = (__u8 *)&ctx->local_ip4;
+		if (byte[0] != ((DST_IP4 >>  0) & 0xff) ||
+		    byte[1] != ((DST_IP4 >>  8) & 0xff) ||
+		    byte[2] != ((DST_IP4 >> 16) & 0xff) ||
+		    byte[3] != ((DST_IP4 >> 24) & 0xff))
+			return SK_DROP;
+		half = (__u16 *)&ctx->local_ip4;
+		if (half[0] != ((DST_IP4 >>  0) & 0xffff) ||
+		    half[1] != ((DST_IP4 >> 16) & 0xffff))
+			return SK_DROP;
+	} else {
+		/* Expect 0.0.0.0 IPs when family != AF_INET */
+		byte = (__u8 *)&ctx->remote_ip4;
+		if (byte[0] != 0 || byte[1] != 0 &&
+		    byte[2] != 0 || byte[3] != 0)
+			return SK_DROP;
+		half = (__u16 *)&ctx->remote_ip4;
+		if (half[0] != 0 || half[1] != 0)
+			return SK_DROP;
+
+		byte = (__u8 *)&ctx->local_ip4;
+		if (byte[0] != 0 || byte[1] != 0 &&
+		    byte[2] != 0 || byte[3] != 0)
+			return SK_DROP;
+		half = (__u16 *)&ctx->local_ip4;
+		if (half[0] != 0 || half[1] != 0)
+			return SK_DROP;
+	}
+
+	/* Narrow loads from IPv6 fields */
+	if (!v4) {
+		/* Expenct non-:: IP in remote_ip6 */
+		byte = (__u8 *)&ctx->remote_ip6;
+		if (byte[0] == 0 && byte[1] == 0 &&
+		    byte[2] == 0 && byte[3] == 0 &&
+		    byte[4] == 0 && byte[5] == 0 &&
+		    byte[6] == 0 && byte[7] == 0 &&
+		    byte[8] == 0 && byte[9] == 0 &&
+		    byte[10] == 0 && byte[11] == 0 &&
+		    byte[12] == 0 && byte[13] == 0 &&
+		    byte[14] == 0 && byte[15] == 0)
+			return SK_DROP;
+		half = (__u16 *)&ctx->remote_ip6;
+		if (half[0] == 0 && half[1] == 0 &&
+		    half[2] == 0 && half[3] == 0 &&
+		    half[4] == 0 && half[5] == 0 &&
+		    half[6] == 0 && half[7] == 0)
+			return SK_DROP;
+
+		/* Expect DST_IP6 in local_ip6 */
+		byte = (__u8 *)&ctx->local_ip6;
+		if (byte[0] != ((DST_IP6[0] >>  0) & 0xff) ||
+		    byte[1] != ((DST_IP6[0] >>  8) & 0xff) ||
+		    byte[2] != ((DST_IP6[0] >> 16) & 0xff) ||
+		    byte[3] != ((DST_IP6[0] >> 24) & 0xff) ||
+		    byte[4] != ((DST_IP6[1] >>  0) & 0xff) ||
+		    byte[5] != ((DST_IP6[1] >>  8) & 0xff) ||
+		    byte[6] != ((DST_IP6[1] >> 16) & 0xff) ||
+		    byte[7] != ((DST_IP6[1] >> 24) & 0xff) ||
+		    byte[8] != ((DST_IP6[2] >>  0) & 0xff) ||
+		    byte[9] != ((DST_IP6[2] >>  8) & 0xff) ||
+		    byte[10] != ((DST_IP6[2] >> 16) & 0xff) ||
+		    byte[11] != ((DST_IP6[2] >> 24) & 0xff) ||
+		    byte[12] != ((DST_IP6[3] >>  0) & 0xff) ||
+		    byte[13] != ((DST_IP6[3] >>  8) & 0xff) ||
+		    byte[14] != ((DST_IP6[3] >> 16) & 0xff) ||
+		    byte[15] != ((DST_IP6[3] >> 24) & 0xff))
+			return SK_DROP;
+		half = (__u16 *)&ctx->local_ip6;
+		if (half[0] != ((DST_IP6[0] >>  0) & 0xffff) ||
+		    half[1] != ((DST_IP6[0] >> 16) & 0xffff) ||
+		    half[2] != ((DST_IP6[1] >>  0) & 0xffff) ||
+		    half[3] != ((DST_IP6[1] >> 16) & 0xffff) ||
+		    half[4] != ((DST_IP6[2] >>  0) & 0xffff) ||
+		    half[5] != ((DST_IP6[2] >> 16) & 0xffff) ||
+		    half[6] != ((DST_IP6[3] >>  0) & 0xffff) ||
+		    half[7] != ((DST_IP6[3] >> 16) & 0xffff))
+			return SK_DROP;
+	} else {
+		/* Expect :: IPs when family != AF_INET6 */
+		byte = (__u8 *)&ctx->remote_ip6;
+		if (byte[0] != 0 || byte[1] != 0 ||
+		    byte[2] != 0 || byte[3] != 0 ||
+		    byte[4] != 0 || byte[5] != 0 ||
+		    byte[6] != 0 || byte[7] != 0 ||
+		    byte[8] != 0 || byte[9] != 0 ||
+		    byte[10] != 0 || byte[11] != 0 ||
+		    byte[12] != 0 || byte[13] != 0 ||
+		    byte[14] != 0 || byte[15] != 0)
+			return SK_DROP;
+		half = (__u16 *)&ctx->remote_ip6;
+		if (half[0] != 0 || half[1] != 0 ||
+		    half[2] != 0 || half[3] != 0 ||
+		    half[4] != 0 || half[5] != 0 ||
+		    half[6] != 0 || half[7] != 0)
+			return SK_DROP;
+
+		byte = (__u8 *)&ctx->local_ip6;
+		if (byte[0] != 0 || byte[1] != 0 ||
+		    byte[2] != 0 || byte[3] != 0 ||
+		    byte[4] != 0 || byte[5] != 0 ||
+		    byte[6] != 0 || byte[7] != 0 ||
+		    byte[8] != 0 || byte[9] != 0 ||
+		    byte[10] != 0 || byte[11] != 0 ||
+		    byte[12] != 0 || byte[13] != 0 ||
+		    byte[14] != 0 || byte[15] != 0)
+			return SK_DROP;
+		half = (__u16 *)&ctx->local_ip6;
+		if (half[0] != 0 || half[1] != 0 ||
+		    half[2] != 0 || half[3] != 0 ||
+		    half[4] != 0 || half[5] != 0 ||
+		    half[6] != 0 || half[7] != 0)
+			return SK_DROP;
+	}
+
+	/* Success, redirect to KEY_SERVER_B */
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B);
+	if (sk) {
+		bpf_sk_assign(ctx, sk, 0);
+		bpf_sk_release(sk);
+	}
+	return SK_PASS;
+}
+
+/* Check that sk_assign rejects SERVER_A socket with -ESOCKNOSUPPORT */
+SEC("sk_lookup/sk_assign_esocknosupport")
+int sk_assign_esocknosupport(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk;
+	int err, ret;
+
+	ret = SK_DROP;
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A);
+	if (!sk)
+		goto out;
+
+	err = bpf_sk_assign(ctx, sk, 0);
+	if (err != -ESOCKTNOSUPPORT) {
+		bpf_printk("sk_assign returned %d, expected %d\n",
+			   err, -ESOCKTNOSUPPORT);
+		goto out;
+	}
+
+	ret = SK_PASS; /* Success, pass to regular lookup */
+out:
+	if (sk)
+		bpf_sk_release(sk);
+	return ret;
+}
+
+SEC("sk_lookup/multi_prog_pass1")
+int multi_prog_pass1(struct bpf_sk_lookup *ctx)
+{
+	bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY);
+	return SK_PASS;
+}
+
+SEC("sk_lookup/multi_prog_pass2")
+int multi_prog_pass2(struct bpf_sk_lookup *ctx)
+{
+	bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY);
+	return SK_PASS;
+}
+
+SEC("sk_lookup/multi_prog_drop1")
+int multi_prog_drop1(struct bpf_sk_lookup *ctx)
+{
+	bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY);
+	return SK_DROP;
+}
+
+SEC("sk_lookup/multi_prog_drop2")
+int multi_prog_drop2(struct bpf_sk_lookup *ctx)
+{
+	bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY);
+	return SK_DROP;
+}
+
+static __always_inline int select_server_a(struct bpf_sk_lookup *ctx)
+{
+	struct bpf_sock *sk;
+	int err;
+
+	sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A);
+	if (!sk)
+		return SK_DROP;
+
+	err = bpf_sk_assign(ctx, sk, 0);
+	bpf_sk_release(sk);
+	if (err)
+		return SK_DROP;
+
+	return SK_PASS;
+}
+
+SEC("sk_lookup/multi_prog_redir1")
+int multi_prog_redir1(struct bpf_sk_lookup *ctx)
+{
+	int ret;
+
+	ret = select_server_a(ctx);
+	bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY);
+	return SK_PASS;
+}
+
+SEC("sk_lookup/multi_prog_redir2")
+int multi_prog_redir2(struct bpf_sk_lookup *ctx)
+{
+	int ret;
+
+	ret = select_server_a(ctx);
+	bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY);
+	return SK_PASS;
+}
+
+char _license[] SEC("license") = "Dual BSD/GPL";
+__u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c
index 77ae86f44db5..374ccef704e1 100644
--- a/tools/testing/selftests/bpf/progs/test_skeleton.c
+++ b/tools/testing/selftests/bpf/progs/test_skeleton.c
@@ -20,7 +20,9 @@ long long in4 __attribute__((aligned(64))) = 0;
 struct s in5 = {};
 
 /* .rodata section */
-const volatile int in6 = 0;
+const volatile struct {
+	const int in6;
+} in = {};
 
 /* .data section */
 int out1 = -1;
@@ -46,7 +48,7 @@ int handler(const void *ctx)
 	out3 = in3;
 	out4 = in4;
 	out5 = in5;
-	out6 = in6;
+	out6 = in.in6;
 
 	bpf_syscall = CONFIG_BPF_SYSCALL;
 	kern_ver = LINUX_KERNEL_VERSION;
diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index 1f1966e86e9f..3e6912e4df3d 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@@ -54,6 +54,7 @@ SEC("sockops")
 int bpf_testcb(struct bpf_sock_ops *skops)
 {
 	char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)];
+	struct bpf_sock_ops *reuse = skops;
 	struct tcphdr *thdr;
 	int good_call_rv = 0;
 	int bad_call_rv = 0;
@@ -62,6 +63,46 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 	int v = 0;
 	int op;
 
+	/* Test reading fields in bpf_sock_ops using single register */
+	asm volatile (
+		"%[reuse] = *(u32 *)(%[reuse] +96)"
+		: [reuse] "+r"(reuse)
+		:);
+
+	asm volatile (
+		"%[op] = *(u32 *)(%[skops] +96)"
+		: [op] "+r"(op)
+		: [skops] "r"(skops)
+		:);
+
+	asm volatile (
+		"r9 = %[skops];\n"
+		"r8 = *(u32 *)(r9 +164);\n"
+		"*(u32 *)(r9 +164) = r8;\n"
+		:: [skops] "r"(skops)
+		: "r9", "r8");
+
+	asm volatile (
+		"r1 = %[skops];\n"
+		"r1 = *(u64 *)(r1 +184);\n"
+		"if r1 == 0 goto +1;\n"
+		"r1 = *(u32 *)(r1 +4);\n"
+		:: [skops] "r"(skops):"r1");
+
+	asm volatile (
+		"r9 = %[skops];\n"
+		"r9 = *(u64 *)(r9 +184);\n"
+		"if r9 == 0 goto +1;\n"
+		"r9 = *(u32 *)(r9 +4);\n"
+		:: [skops] "r"(skops):"r9");
+
+	asm volatile (
+		"r1 = %[skops];\n"
+		"r2 = *(u64 *)(r1 +184);\n"
+		"if r2 == 0 goto +1;\n"
+		"r2 = *(u32 *)(r2 +4);\n"
+		:: [skops] "r"(skops):"r1", "r2");
+
 	op = (int) skops->op;
 
 	update_event_map(op);
diff --git a/tools/testing/selftests/bpf/progs/test_varlen.c b/tools/testing/selftests/bpf/progs/test_varlen.c
new file mode 100644
index 000000000000..913acdffd90f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_varlen.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#define MAX_LEN 256
+
+char buf_in1[MAX_LEN] = {};
+char buf_in2[MAX_LEN] = {};
+
+int test_pid = 0;
+bool capture = false;
+
+/* .bss */
+__u64 payload1_len1 = 0;
+__u64 payload1_len2 = 0;
+__u64 total1 = 0;
+char payload1[MAX_LEN + MAX_LEN] = {};
+
+/* .data */
+int payload2_len1 = -1;
+int payload2_len2 = -1;
+int total2 = -1;
+char payload2[MAX_LEN + MAX_LEN] = { 1 };
+
+int payload3_len1 = -1;
+int payload3_len2 = -1;
+int total3= -1;
+char payload3[MAX_LEN + MAX_LEN] = { 1 };
+
+int payload4_len1 = -1;
+int payload4_len2 = -1;
+int total4= -1;
+char payload4[MAX_LEN + MAX_LEN] = { 1 };
+
+SEC("raw_tp/sys_enter")
+int handler64_unsigned(void *regs)
+{
+	int pid = bpf_get_current_pid_tgid() >> 32;
+	void *payload = payload1;
+	u64 len;
+
+	/* ignore irrelevant invocations */
+	if (test_pid != pid || !capture)
+		return 0;
+
+	len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]);
+	if (len <= MAX_LEN) {
+		payload += len;
+		payload1_len1 = len;
+	}
+
+	len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]);
+	if (len <= MAX_LEN) {
+		payload += len;
+		payload1_len2 = len;
+	}
+
+	total1 = payload - (void *)payload1;
+
+	return 0;
+}
+
+SEC("raw_tp/sys_exit")
+int handler64_signed(void *regs)
+{
+	int pid = bpf_get_current_pid_tgid() >> 32;
+	void *payload = payload3;
+	long len;
+
+	/* ignore irrelevant invocations */
+	if (test_pid != pid || !capture)
+		return 0;
+
+	len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]);
+	if (len >= 0) {
+		payload += len;
+		payload3_len1 = len;
+	}
+	len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]);
+	if (len >= 0) {
+		payload += len;
+		payload3_len2 = len;
+	}
+	total3 = payload - (void *)payload3;
+
+	return 0;
+}
+
+SEC("tp/raw_syscalls/sys_enter")
+int handler32_unsigned(void *regs)
+{
+	int pid = bpf_get_current_pid_tgid() >> 32;
+	void *payload = payload2;
+	u32 len;
+
+	/* ignore irrelevant invocations */
+	if (test_pid != pid || !capture)
+		return 0;
+
+	len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]);
+	if (len <= MAX_LEN) {
+		payload += len;
+		payload2_len1 = len;
+	}
+
+	len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]);
+	if (len <= MAX_LEN) {
+		payload += len;
+		payload2_len2 = len;
+	}
+
+	total2 = payload - (void *)payload2;
+
+	return 0;
+}
+
+SEC("tp/raw_syscalls/sys_exit")
+int handler32_signed(void *regs)
+{
+	int pid = bpf_get_current_pid_tgid() >> 32;
+	void *payload = payload4;
+	int len;
+
+	/* ignore irrelevant invocations */
+	if (test_pid != pid || !capture)
+		return 0;
+
+	len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]);
+	if (len >= 0) {
+		payload += len;
+		payload4_len1 = len;
+	}
+	len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]);
+	if (len >= 0) {
+		payload += len;
+		payload4_len2 = len;
+	}
+	total4 = payload - (void *)payload4;
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_exit_getpid")
+int handler_exit(void *regs)
+{
+	long bla;
+
+	if (bpf_probe_read_kernel(&bla, sizeof(bla), 0))
+		return 1;
+	else
+		return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c
index 5611b564d3b1..29fa09d6a6c6 100644
--- a/tools/testing/selftests/bpf/progs/test_vmlinux.c
+++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c
@@ -63,20 +63,20 @@ int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id)
 	return 0;
 }
 
-SEC("kprobe/hrtimer_nanosleep")
-int BPF_KPROBE(handle__kprobe,
-	       ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid)
+SEC("kprobe/hrtimer_start_range_ns")
+int BPF_KPROBE(handle__kprobe, struct hrtimer *timer, ktime_t tim, u64 delta_ns,
+	       const enum hrtimer_mode mode)
 {
-	if (rqtp == MY_TV_NSEC)
+	if (tim == MY_TV_NSEC)
 		kprobe_called = true;
 	return 0;
 }
 
-SEC("fentry/hrtimer_nanosleep")
-int BPF_PROG(handle__fentry,
-	     ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid)
+SEC("fentry/hrtimer_start_range_ns")
+int BPF_PROG(handle__fentry, struct hrtimer *timer, ktime_t tim, u64 delta_ns,
+	     const enum hrtimer_mode mode)
 {
-	if (rqtp == MY_TV_NSEC)
+	if (tim == MY_TV_NSEC)
 		fentry_called = true;
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c
new file mode 100644
index 000000000000..eb93ea95d1d8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+SEC("xdp/handler")
+int xdp_handler(struct xdp_md *xdp)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
new file mode 100644
index 000000000000..59ee4f182ff8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define IFINDEX_LO	1
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CPUMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_cpumap_val));
+	__uint(max_entries, 4);
+} cpu_map SEC(".maps");
+
+SEC("xdp_redir")
+int xdp_redir_prog(struct xdp_md *ctx)
+{
+	return bpf_redirect_map(&cpu_map, 1, 0);
+}
+
+SEC("xdp_dummy")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+SEC("xdp_cpumap/dummy_cm")
+int xdp_dummy_cm(struct xdp_md *ctx)
+{
+	if (ctx->ingress_ifindex == IFINDEX_LO)
+		return XDP_DROP;
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c
new file mode 100644
index 000000000000..8ca7f399b670
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/trace_printk.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020, Oracle and/or its affiliates.
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int trace_printk_ret = 0;
+int trace_printk_ran = 0;
+
+SEC("tp/raw_syscalls/sys_enter")
+int sys_enter(void *ctx)
+{
+	static const char fmt[] = "testing,testing %d\n";
+
+	trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt),
+					    ++trace_printk_ran);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/udp_limit.c b/tools/testing/selftests/bpf/progs/udp_limit.c
new file mode 100644
index 000000000000..165e3c2dd9a3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/udp_limit.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <sys/socket.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+int invocations = 0, in_use = 0;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} sk_map SEC(".maps");
+
+SEC("cgroup/sock_create")
+int sock(struct bpf_sock *ctx)
+{
+	int *sk_storage;
+	__u32 key;
+
+	if (ctx->type != SOCK_DGRAM)
+		return 1;
+
+	sk_storage = bpf_sk_storage_get(&sk_map, ctx, 0,
+					BPF_SK_STORAGE_GET_F_CREATE);
+	if (!sk_storage)
+		return 0;
+	*sk_storage = 0xdeadbeef;
+
+	__sync_fetch_and_add(&invocations, 1);
+
+	if (in_use > 0) {
+		/* BPF_CGROUP_INET_SOCK_RELEASE is _not_ called
+		 * when we return an error from the BPF
+		 * program!
+		 */
+		return 0;
+	}
+
+	__sync_fetch_and_add(&in_use, 1);
+	return 1;
+}
+
+SEC("cgroup/sock_release")
+int sock_release(struct bpf_sock *ctx)
+{
+	int *sk_storage;
+	__u32 key;
+
+	if (ctx->type != SOCK_DGRAM)
+		return 1;
+
+	sk_storage = bpf_sk_storage_get(&sk_map, ctx, 0, 0);
+	if (!sk_storage || *sk_storage != 0xdeadbeef)
+		return 0;
+
+	__sync_fetch_and_add(&invocations, 1);
+	__sync_fetch_and_add(&in_use, -1);
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/settings b/tools/testing/selftests/bpf/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/bpf/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py
index a53ed58528d6..bfff82be3fc1 100755
--- a/tools/testing/selftests/bpf/tcp_client.py
+++ b/tools/testing/selftests/bpf/tcp_client.py
@@ -34,7 +34,7 @@ serverPort = int(sys.argv[1])
 # create active socket
 sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
 try:
-    sock.connect(('localhost', serverPort))
+    sock.connect(('::1', serverPort))
 except socket.error as e:
     sys.exit(1)
 
diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py
index 0ca60d193bed..42ab8882f00f 100755
--- a/tools/testing/selftests/bpf/tcp_server.py
+++ b/tools/testing/selftests/bpf/tcp_server.py
@@ -38,7 +38,7 @@ serverSocket = None
 # create passive socket
 serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
 
-try: serverSocket.bind(('localhost', 0))
+try: serverSocket.bind(('::1', 0))
 except socket.error as msg:
     print('bind fails: ' + str(msg))
 
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 305fae8f80a9..c75fc6447186 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -3883,7 +3883,7 @@ static int test_big_btf_info(unsigned int test_num)
 	info_garbage.garbage = 0;
 	err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len);
 	if (CHECK(err || info_len != sizeof(*info),
-		  "err:%d errno:%d info_len:%u sizeof(*info):%lu",
+		  "err:%d errno:%d info_len:%u sizeof(*info):%zu",
 		  err, errno, info_len, sizeof(*info))) {
 		err = -1;
 		goto done;
@@ -4094,7 +4094,7 @@ static int do_test_get_info(unsigned int test_num)
 	if (CHECK(err || !info.id || info_len != sizeof(info) ||
 		  info.btf_size != raw_btf_size ||
 		  (ret = memcmp(raw_btf, user_btf, expected_nbytes)),
-		  "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%lu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d",
+		  "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%zu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d",
 		  err, errno, info.id, info_len, sizeof(info),
 		  raw_btf_size, info.btf_size, expected_nbytes, ret)) {
 		err = -1;
@@ -4730,7 +4730,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind,
 
 		nexpected_line = snprintf(expected_line, line_size,
 					  "%s%u: {%u,0,%d,0x%x,0x%x,0x%x,"
-					  "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s,"
+					  "{%llu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s,"
 					  "%u,0x%x,[[%d,%d],[%d,%d]]}\n",
 					  percpu_map ? "\tcpu" : "",
 					  percpu_map ? cpu : next_key,
@@ -4738,7 +4738,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind,
 					  v->unused_bits2a,
 					  v->bits28,
 					  v->unused_bits2b,
-					  v->ui64,
+					  (__u64)v->ui64,
 					  v->ui8a[0], v->ui8a[1],
 					  v->ui8a[2], v->ui8a[3],
 					  v->ui8a[4], v->ui8a[5],
diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
index 655729004391..d946252a25bb 100644
--- a/tools/testing/selftests/bpf/test_cgroup_storage.c
+++ b/tools/testing/selftests/bpf/test_cgroup_storage.c
@@ -74,22 +74,7 @@ int main(int argc, char **argv)
 		goto out;
 	}
 
-	if (setup_cgroup_environment()) {
-		printf("Failed to setup cgroup environment\n");
-		goto err;
-	}
-
-	/* Create a cgroup, get fd, and join it */
-	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
-	if (cgroup_fd < 0) {
-		printf("Failed to create test cgroup\n");
-		goto err;
-	}
-
-	if (join_cgroup(TEST_CGROUP)) {
-		printf("Failed to join cgroup\n");
-		goto err;
-	}
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
 
 	/* Attach the bpf program */
 	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c
index d850fb9076b5..804dddd97d4c 100644
--- a/tools/testing/selftests/bpf/test_dev_cgroup.c
+++ b/tools/testing/selftests/bpf/test_dev_cgroup.c
@@ -33,21 +33,10 @@ int main(int argc, char **argv)
 		goto out;
 	}
 
-	if (setup_cgroup_environment()) {
-		printf("Failed to load DEV_CGROUP program\n");
-		goto err;
-	}
-
-	/* Create a cgroup, get fd, and join it */
-	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
 	if (cgroup_fd < 0) {
 		printf("Failed to create test cgroup\n");
-		goto err;
-	}
-
-	if (join_cgroup(TEST_CGROUP)) {
-		printf("Failed to join cgroup\n");
-		goto err;
+		goto out;
 	}
 
 	/* Attach bpf program */
diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh
index 9df0d2ac45f8..4f6444bcd53f 100755
--- a/tools/testing/selftests/bpf/test_kmod.sh
+++ b/tools/testing/selftests/bpf/test_kmod.sh
@@ -10,7 +10,13 @@ if [ "$(id -u)" != "0" ]; then
 	exit $ksft_skip
 fi
 
-SRC_TREE=../../../../
+if [ "$building_out_of_srctree" ]; then
+	# We are in linux-build/kselftest/bpf
+	OUTPUT=../../
+else
+	# We are in linux/tools/testing/selftests/bpf
+	OUTPUT=../../../../
+fi
 
 test_run()
 {
@@ -19,8 +25,8 @@ test_run()
 
 	echo "[ JIT enabled:$1 hardened:$2 ]"
 	dmesg -C
-	if [ -f ${SRC_TREE}/lib/test_bpf.ko ]; then
-		insmod ${SRC_TREE}/lib/test_bpf.ko 2> /dev/null
+	if [ -f ${OUTPUT}/lib/test_bpf.ko ]; then
+		insmod ${OUTPUT}/lib/test_bpf.ko 2> /dev/null
 		if [ $? -ne 0 ]; then
 			rc=1
 		fi
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
index 785eabf2a593..5620919fde9e 100755
--- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh
+++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
@@ -140,7 +140,7 @@ ip netns exec ns6 sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null
 ip netns exec ns6 nc -l -6 -u -d 7330 > $TMP_FILE &
 ip netns exec ns1 bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330"
 sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment
-kill -INT $!
+kill -TERM $!
 
 if [[ $(< $TMP_FILE) != "foobar" ]]; then
 	exit 1
diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c
index c1da5404454a..a7b9a69f4fd5 100644
--- a/tools/testing/selftests/bpf/test_netcnt.c
+++ b/tools/testing/selftests/bpf/test_netcnt.c
@@ -58,22 +58,9 @@ int main(int argc, char **argv)
 		goto out;
 	}
 
-	if (setup_cgroup_environment()) {
-		printf("Failed to load bpf program\n");
-		goto err;
-	}
-
-	/* Create a cgroup, get fd, and join it */
-	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
-	if (cgroup_fd < 0) {
-		printf("Failed to create test cgroup\n");
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
+	if (cgroup_fd < 0)
 		goto err;
-	}
-
-	if (join_cgroup(TEST_CGROUP)) {
-		printf("Failed to join cgroup\n");
-		goto err;
-	}
 
 	/* Attach bpf program */
 	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
@@ -82,9 +69,9 @@ int main(int argc, char **argv)
 	}
 
 	if (system("which ping6 &>/dev/null") == 0)
-		assert(!system("ping6 localhost -c 10000 -f -q > /dev/null"));
+		assert(!system("ping6 ::1 -c 10000 -f -q > /dev/null"));
 	else
-		assert(!system("ping -6 localhost -c 10000 -f -q > /dev/null"));
+		assert(!system("ping -6 ::1 -c 10000 -f -q > /dev/null"));
 
 	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL,
 			   &prog_cnt)) {
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 8294ae3ffb3c..43c9cda199b8 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -318,6 +318,9 @@ class DebugfsDir:
                 continue
 
             if os.path.isfile(p):
+                # We need to init trap_flow_action_cookie before read it
+                if f == "trap_flow_action_cookie":
+                    cmd('echo deadbeef > %s/%s' % (path, f))
                 _, out = cmd('cat %s/%s' % (path, f))
                 dfs[f] = out.strip()
             elif os.path.isdir(p):
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 54fa5fa688ce..b1e4dadacd9b 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -12,6 +12,9 @@
 #include <string.h>
 #include <execinfo.h> /* backtrace */
 
+#define EXIT_NO_TEST		2
+#define EXIT_ERR_SETUP_INFRA	3
+
 /* defined in test_progs.h */
 struct test_env env = {};
 
@@ -111,13 +114,31 @@ static void reset_affinity() {
 	if (err < 0) {
 		stdio_restore();
 		fprintf(stderr, "Failed to reset process affinity: %d!\n", err);
-		exit(-1);
+		exit(EXIT_ERR_SETUP_INFRA);
 	}
 	err = pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
 	if (err < 0) {
 		stdio_restore();
 		fprintf(stderr, "Failed to reset thread affinity: %d!\n", err);
-		exit(-1);
+		exit(EXIT_ERR_SETUP_INFRA);
+	}
+}
+
+static void save_netns(void)
+{
+	env.saved_netns_fd = open("/proc/self/ns/net", O_RDONLY);
+	if (env.saved_netns_fd == -1) {
+		perror("open(/proc/self/ns/net)");
+		exit(EXIT_ERR_SETUP_INFRA);
+	}
+}
+
+static void restore_netns(void)
+{
+	if (setns(env.saved_netns_fd, CLONE_NEWNET) == -1) {
+		stdio_restore();
+		perror("setns(CLONE_NEWNS)");
+		exit(EXIT_ERR_SETUP_INFRA);
 	}
 }
 
@@ -138,8 +159,6 @@ void test__end_subtest()
 	       test->test_num, test->subtest_num,
 	       test->subtest_name, sub_error_cnt ? "FAIL" : "OK");
 
-	reset_affinity();
-
 	free(test->subtest_name);
 	test->subtest_name = NULL;
 }
@@ -366,6 +385,8 @@ enum ARG_KEYS {
 	ARG_TEST_NAME_BLACKLIST = 'b',
 	ARG_VERIFIER_STATS = 's',
 	ARG_VERBOSE = 'v',
+	ARG_GET_TEST_CNT = 'c',
+	ARG_LIST_TEST_NAMES = 'l',
 };
 
 static const struct argp_option opts[] = {
@@ -379,6 +400,10 @@ static const struct argp_option opts[] = {
 	  "Output verifier statistics", },
 	{ "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL,
 	  "Verbose output (use -vv or -vvv for progressively verbose output)" },
+	{ "count", ARG_GET_TEST_CNT, NULL, 0,
+	  "Get number of selected top-level tests " },
+	{ "list", ARG_LIST_TEST_NAMES, NULL, 0,
+	  "List test names that would run (without running them) " },
 	{},
 };
 
@@ -511,6 +536,12 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 			}
 		}
 		break;
+	case ARG_GET_TEST_CNT:
+		env->get_test_cnt = true;
+		break;
+	case ARG_LIST_TEST_NAMES:
+		env->list_test_names = true;
+		break;
 	case ARGP_KEY_ARG:
 		argp_usage(state);
 		break;
@@ -643,6 +674,7 @@ int main(int argc, char **argv)
 		return -1;
 	}
 
+	save_netns();
 	stdio_hijack();
 	for (i = 0; i < prog_test_cnt; i++) {
 		struct prog_test_def *test = &prog_test_defs[i];
@@ -654,6 +686,17 @@ int main(int argc, char **argv)
 				test->test_num, test->test_name))
 			continue;
 
+		if (env.get_test_cnt) {
+			env.succ_cnt++;
+			continue;
+		}
+
+		if (env.list_test_names) {
+			fprintf(env.stdout, "%s\n", test->test_name);
+			env.succ_cnt++;
+			continue;
+		}
+
 		test->run_test();
 		/* ensure last sub-test is finalized properly */
 		if (test->subtest_name)
@@ -673,19 +716,34 @@ int main(int argc, char **argv)
 			test->error_cnt ? "FAIL" : "OK");
 
 		reset_affinity();
+		restore_netns();
 		if (test->need_cgroup_cleanup)
 			cleanup_cgroup_environment();
 	}
 	stdio_restore();
+
+	if (env.get_test_cnt) {
+		printf("%d\n", env.succ_cnt);
+		goto out;
+	}
+
+	if (env.list_test_names)
+		goto out;
+
 	fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
 		env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
 
+out:
 	free_str_set(&env.test_selector.blacklist);
 	free_str_set(&env.test_selector.whitelist);
 	free(env.test_selector.num_set);
 	free_str_set(&env.subtest_selector.blacklist);
 	free_str_set(&env.subtest_selector.whitelist);
 	free(env.subtest_selector.num_set);
+	close(env.saved_netns_fd);
+
+	if (env.succ_cnt + env.fail_cnt + env.skip_cnt == 0)
+		return EXIT_NO_TEST;
 
 	return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
 }
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index f4503c926aca..dbb820dde138 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -66,6 +66,8 @@ struct test_env {
 	enum verbosity verbosity;
 
 	bool jit_enabled;
+	bool get_test_cnt;
+	bool list_test_names;
 
 	struct prog_test_def *test;
 	FILE *stdout;
@@ -78,6 +80,8 @@ struct test_env {
 	int sub_succ_cnt; /* successful sub-tests */
 	int fail_cnt; /* total failed tests + sub-tests */
 	int skip_cnt; /* skipped tests */
+
+	int saved_netns_fd;
 };
 
 extern struct test_env env;
@@ -131,6 +135,11 @@ static inline __u64 ptr_to_u64(const void *ptr)
 	return (__u64) (unsigned long) ptr;
 }
 
+static inline void *u64_to_ptr(__u64 ptr)
+{
+	return (void *) (unsigned long) ptr;
+}
+
 int bpf_find_map(const char *test, struct bpf_object *obj, const char *name);
 int compare_map_keys(int map1_fd, int map2_fd);
 int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
index 356351c0ac28..4a64306728ab 100644
--- a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
+++ b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
@@ -160,16 +160,10 @@ int main(int argc, char **argv)
 		exit(EXIT_FAILURE);
 	}
 
-	if (setup_cgroup_environment())
-		goto err;
-
-	cgfd = create_and_get_cgroup(CGROUP_PATH);
+	cgfd = cgroup_setup_and_join(CGROUP_PATH);
 	if (cgfd < 0)
 		goto err;
 
-	if (join_cgroup(CGROUP_PATH))
-		goto err;
-
 	if (send_packet(argv[1]))
 		goto err;
 
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
index 52bf14955797..9613f7538840 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -464,16 +464,10 @@ int main(int argc, char **argv)
 	int cgfd = -1;
 	int err = 0;
 
-	if (setup_cgroup_environment())
-		goto err;
-
-	cgfd = create_and_get_cgroup(CG_PATH);
+	cgfd = cgroup_setup_and_join(CG_PATH);
 	if (cgfd < 0)
 		goto err;
 
-	if (join_cgroup(CG_PATH))
-		goto err;
-
 	if (run_tests(cgfd))
 		goto err;
 
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index 0358814c67dc..b8c72c1d9cf7 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -1638,16 +1638,10 @@ int main(int argc, char **argv)
 		exit(err);
 	}
 
-	if (setup_cgroup_environment())
-		goto err;
-
-	cgfd = create_and_get_cgroup(CG_PATH);
+	cgfd = cgroup_setup_and_join(CG_PATH);
 	if (cgfd < 0)
 		goto err;
 
-	if (join_cgroup(CG_PATH))
-		goto err;
-
 	if (run_tests(cgfd))
 		goto err;
 
diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c
index f0fc103261a4..6c9f269c396d 100644
--- a/tools/testing/selftests/bpf/test_sock_fields.c
+++ b/tools/testing/selftests/bpf/test_sock_fields.c
@@ -421,19 +421,11 @@ int main(int argc, char **argv)
 	struct bpf_object *obj;
 	struct bpf_map *map;
 
-	err = setup_cgroup_environment();
-	CHECK(err, "setup_cgroup_environment()", "err:%d errno:%d",
-	      err, errno);
-
-	atexit(cleanup_cgroup_environment);
-
 	/* Create a cgroup, get fd, and join it */
-	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
-	CHECK(cgroup_fd == -1, "create_and_get_cgroup()",
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
+	CHECK(cgroup_fd < 0, "cgroup_setup_and_join()",
 	      "cgroup_fd:%d errno:%d", cgroup_fd, errno);
-
-	err = join_cgroup(TEST_CGROUP);
-	CHECK(err, "join_cgroup", "err:%d errno:%d", err, errno);
+	atexit(cleanup_cgroup_environment);
 
 	err = bpf_prog_load_xattr(&attr, &obj, &egress_fd);
 	CHECK(err, "bpf_prog_load_xattr()", "err:%d", err);
diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c
index 15653b0e26eb..154a8fd2a48d 100644
--- a/tools/testing/selftests/bpf/test_socket_cookie.c
+++ b/tools/testing/selftests/bpf/test_socket_cookie.c
@@ -191,16 +191,10 @@ int main(int argc, char **argv)
 	int cgfd = -1;
 	int err = 0;
 
-	if (setup_cgroup_environment())
-		goto err;
-
-	cgfd = create_and_get_cgroup(CG_PATH);
+	cgfd = cgroup_setup_and_join(CG_PATH);
 	if (cgfd < 0)
 		goto err;
 
-	if (join_cgroup(CG_PATH))
-		goto err;
-
 	if (run_test(cgfd))
 		goto err;
 
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 78789b27e573..9b6fb00dc7a0 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1963,23 +1963,9 @@ int main(int argc, char **argv)
 	}
 
 	if (!cg_fd) {
-		if (setup_cgroup_environment()) {
-			fprintf(stderr, "ERROR: cgroup env failed\n");
-			return -EINVAL;
-		}
-
-		cg_fd = create_and_get_cgroup(CG_PATH);
-		if (cg_fd < 0) {
-			fprintf(stderr,
-				"ERROR: (%i) open cg path failed: %s\n",
-				cg_fd, strerror(errno));
+		cg_fd = cgroup_setup_and_join(CG_PATH);
+		if (cg_fd < 0)
 			return cg_fd;
-		}
-
-		if (join_cgroup(CG_PATH)) {
-			fprintf(stderr, "ERROR: failed to join cgroup\n");
-			return -EINVAL;
-		}
 		cg_created = 1;
 	}
 
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c
index d196e2a4a6e0..a20a919244c0 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/test_sysctl.c
@@ -1619,16 +1619,10 @@ int main(int argc, char **argv)
 	int cgfd = -1;
 	int err = 0;
 
-	if (setup_cgroup_environment())
-		goto err;
-
-	cgfd = create_and_get_cgroup(CG_PATH);
+	cgfd = cgroup_setup_and_join(CG_PATH);
 	if (cgfd < 0)
 		goto err;
 
-	if (join_cgroup(CG_PATH))
-		goto err;
-
 	if (run_tests(cgfd))
 		goto err;
 
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index 3ae127620463..74a9e49988b6 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -102,16 +102,10 @@ int main(int argc, char **argv)
 	__u32 key = 0;
 	int rv;
 
-	if (setup_cgroup_environment())
-		goto err;
-
-	cg_fd = create_and_get_cgroup(cg_path);
+	cg_fd = cgroup_setup_and_join(cg_path);
 	if (cg_fd < 0)
 		goto err;
 
-	if (join_cgroup(cg_path))
-		goto err;
-
 	if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
 		printf("FAILED: load_bpf_file failed for: %s\n", file);
 		goto err;
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c
index f9765ddf0761..73da7fe8c152 100644
--- a/tools/testing/selftests/bpf/test_tcpnotify_user.c
+++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c
@@ -86,16 +86,10 @@ int main(int argc, char **argv)
 	CPU_SET(0, &cpuset);
 	pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
 
-	if (setup_cgroup_environment())
-		goto err;
-
-	cg_fd = create_and_get_cgroup(cg_path);
+	cg_fd = cgroup_setup_and_join(cg_path);
 	if (cg_fd < 0)
 		goto err;
 
-	if (join_cgroup(cg_path))
-		goto err;
-
 	if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
 		printf("FAILED: load_bpf_file failed for: %s\n", file);
 		goto err;
@@ -130,17 +124,24 @@ int main(int argc, char **argv)
 	sprintf(test_script,
 		"iptables -A INPUT -p tcp --dport %d -j DROP",
 		TESTPORT);
-	system(test_script);
+	if (system(test_script)) {
+		printf("FAILED: execute command: %s, err %d\n", test_script, -errno);
+		goto err;
+	}
 
 	sprintf(test_script,
 		"nc 127.0.0.1 %d < /etc/passwd > /dev/null 2>&1 ",
 		TESTPORT);
-	system(test_script);
+	if (system(test_script))
+		printf("execute command: %s, err %d\n", test_script, -errno);
 
 	sprintf(test_script,
 		"iptables -D INPUT -p tcp --dport %d -j DROP",
 		TESTPORT);
-	system(test_script);
+	if (system(test_script)) {
+		printf("FAILED: execute command: %s, err %d\n", test_script, -errno);
+		goto err;
+	}
 
 	rv = bpf_map_lookup_elem(bpf_map__fd(global_map), &key, &g);
 	if (rv != 0) {
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh
index c4b17e08d431..dd80f0c84afb 100755
--- a/tools/testing/selftests/bpf/test_xdp_redirect.sh
+++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh
@@ -10,52 +10,72 @@
 #     | xdp forwarding |
 #     ------------------
 
-cleanup()
+ret=0
+
+setup()
 {
-	if [ "$?" = "0" ]; then
-		echo "selftests: test_xdp_redirect [PASS]";
-	else
-		echo "selftests: test_xdp_redirect [FAILED]";
-	fi
 
-	set +e
+	local xdpmode=$1
+
+	ip netns add ns1
+	ip netns add ns2
+
+	ip link add veth1 index 111 type veth peer name veth11 netns ns1
+	ip link add veth2 index 222 type veth peer name veth22 netns ns2
+
+	ip link set veth1 up
+	ip link set veth2 up
+	ip -n ns1 link set dev veth11 up
+	ip -n ns2 link set dev veth22 up
+
+	ip -n ns1 addr add 10.1.1.11/24 dev veth11
+	ip -n ns2 addr add 10.1.1.22/24 dev veth22
+}
+
+cleanup()
+{
 	ip link del veth1 2> /dev/null
 	ip link del veth2 2> /dev/null
 	ip netns del ns1 2> /dev/null
 	ip netns del ns2 2> /dev/null
 }
 
-ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null
-if [ $? -ne 0 ];then
-	echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support"
-	exit 0
-fi
-set -e
-
-ip netns add ns1
-ip netns add ns2
+test_xdp_redirect()
+{
+	local xdpmode=$1
 
-trap cleanup 0 2 3 6 9
+	setup
 
-ip link add veth1 index 111 type veth peer name veth11
-ip link add veth2 index 222 type veth peer name veth22
+	ip link set dev veth1 $xdpmode off &> /dev/null
+	if [ $? -ne 0 ];then
+		echo "selftests: test_xdp_redirect $xdpmode [SKIP]"
+		return 0
+	fi
 
-ip link set veth11 netns ns1
-ip link set veth22 netns ns2
+	ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null
+	ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null
+	ip link set dev veth1 $xdpmode obj test_xdp_redirect.o sec redirect_to_222 &> /dev/null
+	ip link set dev veth2 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null
 
-ip link set veth1 up
-ip link set veth2 up
+	ip netns exec ns1 ping -c 1 10.1.1.22 &> /dev/null
+	local ret1=$?
+	ip netns exec ns2 ping -c 1 10.1.1.11 &> /dev/null
+	local ret2=$?
 
-ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth11
-ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth22
+	if [ $ret1 -eq 0 -a $ret2 -eq 0 ]; then
+		echo "selftests: test_xdp_redirect $xdpmode [PASS]";
+	else
+		ret=1
+		echo "selftests: test_xdp_redirect $xdpmode [FAILED]";
+	fi
 
-ip netns exec ns1 ip link set dev veth11 up
-ip netns exec ns2 ip link set dev veth22 up
+	cleanup
+}
 
-ip link set dev veth1 xdpgeneric obj test_xdp_redirect.o sec redirect_to_222
-ip link set dev veth2 xdpgeneric obj test_xdp_redirect.o sec redirect_to_111
+set -e
+trap cleanup 2 3 6 9
 
-ip netns exec ns1 ping -c 1 10.1.1.22
-ip netns exec ns2 ping -c 1 10.1.1.11
+test_xdp_redirect xdpgeneric
+test_xdp_redirect xdpdrv
 
-exit 0
+exit $ret
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index 0af6337a8962..800d503e5cb4 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -64,3 +64,17 @@ int parse_num_list(const char *s, bool **num_set, int *num_set_len)
 
 	return 0;
 }
+
+__u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info)
+{
+	__u32 info_len = sizeof(*info);
+	int err;
+
+	memset(info, 0, sizeof(*info));
+	err = bpf_obj_get_info_by_fd(bpf_link__fd(link), info, &info_len);
+	if (err) {
+		printf("failed to get link info: %d\n", -errno);
+		return 0;
+	}
+	return info->prog_id;
+}
diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h
index 923b51762759..d4f8e749611b 100644
--- a/tools/testing/selftests/bpf/testing_helpers.h
+++ b/tools/testing/selftests/bpf/testing_helpers.h
@@ -1,5 +1,8 @@
 /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 /* Copyright (C) 2020 Facebook, Inc. */
 #include <stdbool.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 
 int parse_num_list(const char *s, bool **set, int *set_len);
+__u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info);
diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
new file mode 100644
index 000000000000..2ad5f974451c
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
@@ -0,0 +1,492 @@
+{
+	"valid 1,2,4,8-byte reads from bpf_sk_lookup",
+	.insns = {
+		/* 1-byte read from family field */
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, family)),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, family) + 1),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, family) + 2),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, family) + 3),
+		/* 2-byte read from family field */
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, family)),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, family) + 2),
+		/* 4-byte read from family field */
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, family)),
+
+		/* 1-byte read from protocol field */
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, protocol)),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, protocol) + 1),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, protocol) + 2),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, protocol) + 3),
+		/* 2-byte read from protocol field */
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, protocol)),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, protocol) + 2),
+		/* 4-byte read from protocol field */
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, protocol)),
+
+		/* 1-byte read from remote_ip4 field */
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip4)),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip4) + 1),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip4) + 2),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip4) + 3),
+		/* 2-byte read from remote_ip4 field */
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip4)),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip4) + 2),
+		/* 4-byte read from remote_ip4 field */
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip4)),
+
+		/* 1-byte read from remote_ip6 field */
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6)),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 1),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 2),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 3),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 4),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 5),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 6),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 7),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 8),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 9),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 10),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 11),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 12),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 13),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 14),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 15),
+		/* 2-byte read from remote_ip6 field */
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6)),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 2),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 4),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 6),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 8),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 10),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 12),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 14),
+		/* 4-byte read from remote_ip6 field */
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 4),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 8),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6) + 12),
+
+		/* 1-byte read from remote_port field */
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_port)),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_port) + 1),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_port) + 2),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_port) + 3),
+		/* 2-byte read from remote_port field */
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_port)),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_port) + 2),
+		/* 4-byte read from remote_port field */
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_port)),
+
+		/* 1-byte read from local_ip4 field */
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip4)),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip4) + 1),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip4) + 2),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip4) + 3),
+		/* 2-byte read from local_ip4 field */
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip4)),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip4) + 2),
+		/* 4-byte read from local_ip4 field */
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip4)),
+
+		/* 1-byte read from local_ip6 field */
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6)),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 1),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 2),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 3),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 4),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 5),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 6),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 7),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 8),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 9),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 10),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 11),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 12),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 13),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 14),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 15),
+		/* 2-byte read from local_ip6 field */
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6)),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 2),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 4),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 6),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 8),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 10),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 12),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 14),
+		/* 4-byte read from local_ip6 field */
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 4),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 8),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6) + 12),
+
+		/* 1-byte read from local_port field */
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_port)),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_port) + 1),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_port) + 2),
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_port) + 3),
+		/* 2-byte read from local_port field */
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_port)),
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_port) + 2),
+		/* 4-byte read from local_port field */
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_port)),
+
+		/* 8-byte read from sk field */
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, sk)),
+
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+/* invalid 8-byte reads from a 4-byte fields in bpf_sk_lookup */
+{
+	"invalid 8-byte read from bpf_sk_lookup family field",
+	.insns = {
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, family)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 8-byte read from bpf_sk_lookup protocol field",
+	.insns = {
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, protocol)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 8-byte read from bpf_sk_lookup remote_ip4 field",
+	.insns = {
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip4)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 8-byte read from bpf_sk_lookup remote_ip6 field",
+	.insns = {
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_ip6)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 8-byte read from bpf_sk_lookup remote_port field",
+	.insns = {
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, remote_port)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 8-byte read from bpf_sk_lookup local_ip4 field",
+	.insns = {
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip4)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 8-byte read from bpf_sk_lookup local_ip6 field",
+	.insns = {
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_ip6)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 8-byte read from bpf_sk_lookup local_port field",
+	.insns = {
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, local_port)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+/* invalid 1,2,4-byte reads from 8-byte fields in bpf_sk_lookup */
+{
+	"invalid 4-byte read from bpf_sk_lookup sk field",
+	.insns = {
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, sk)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 2-byte read from bpf_sk_lookup sk field",
+	.insns = {
+		BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, sk)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 1-byte read from bpf_sk_lookup sk field",
+	.insns = {
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+			    offsetof(struct bpf_sk_lookup, sk)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+/* out of bounds and unaligned reads from bpf_sk_lookup */
+{
+	"invalid 4-byte read past end of bpf_sk_lookup",
+	.insns = {
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+			    sizeof(struct bpf_sk_lookup)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 4-byte unaligned read from bpf_sk_lookup at odd offset",
+	.insns = {
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 1),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 4-byte unaligned read from bpf_sk_lookup at even offset",
+	.insns = {
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 2),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+/* in-bound and out-of-bound writes to bpf_sk_lookup */
+{
+	"invalid 8-byte write to bpf_sk_lookup",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U),
+		BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 4-byte write to bpf_sk_lookup",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U),
+		BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 2-byte write to bpf_sk_lookup",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U),
+		BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, 0),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 1-byte write to bpf_sk_lookup",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U),
+		BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
+{
+	"invalid 4-byte write past end of bpf_sk_lookup",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U),
+		BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+			    sizeof(struct bpf_sk_lookup)),
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid bpf_context access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+},
diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c
index 99f8f582c02b..c5e805980409 100644
--- a/tools/testing/selftests/bpf/verifier/event_output.c
+++ b/tools/testing/selftests/bpf/verifier/event_output.c
@@ -112,6 +112,7 @@
 	"perfevent for cgroup sockopt",
 	.insns =  { __PERF_EVENT_INSNS__ },
 	.prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT,
+	.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 	.fixup_map_event_output = { 4 },
 	.result = ACCEPT,
 	.retval = 1,
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c
new file mode 100644
index 000000000000..b52209db8250
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/map_ptr.c
@@ -0,0 +1,62 @@
+{
+	"bpf_map_ptr: read with negative offset rejected",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN",
+	.result = REJECT,
+	.errstr = "R1 is bpf_array invalid negative access: off=-8",
+},
+{
+	"bpf_map_ptr: write rejected",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 3 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN",
+	.result = REJECT,
+	.errstr = "only read from bpf_array is supported",
+},
+{
+	"bpf_map_ptr: read non-existent field rejected",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_6, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, 1),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN",
+	.result = REJECT,
+	.errstr = "cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4",
+},
+{
+	"bpf_map_ptr: read ops field accepted",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_6, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN",
+	.result = ACCEPT,
+	.retval = 1,
+},
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c b/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c
index cd26ee6b7b1d..1f2b8c4cb26d 100644
--- a/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c
+++ b/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c
@@ -56,7 +56,7 @@
 	.fixup_map_in_map = { 16 },
 	.fixup_map_array_48b = { 13 },
 	.result = REJECT,
-	.errstr = "R0 invalid mem access 'map_ptr'",
+	.errstr = "only read from bpf_array is supported",
 },
 {
 	"cond: two branches returning different map pointers for lookup (tail, tail)",
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index 97ee658e1242..ed4e76b24649 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -836,3 +836,41 @@
 	.errstr = "R0 invalid mem access 'inv'",
 	.errstr_unpriv = "R0 pointer -= pointer prohibited",
 },
+{
+	"32bit pkt_ptr -= scalar",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 40),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_8, 2),
+	BPF_ALU32_REG(BPF_MOV, BPF_REG_4, BPF_REG_7),
+	BPF_ALU32_REG(BPF_SUB, BPF_REG_6, BPF_REG_4),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"32bit scalar -= pkt_ptr",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 40),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_8, 2),
+	BPF_ALU32_REG(BPF_MOV, BPF_REG_4, BPF_REG_6),
+	BPF_ALU32_REG(BPF_SUB, BPF_REG_4, BPF_REG_7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
index b3ead29c6089..2cf6f10ab7c4 100644
--- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c
+++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
@@ -47,7 +47,7 @@ void child(int cpu)
 	_exit(0);
 }
 
-bool run_test(int cpu)
+int run_test(int cpu)
 {
 	int status;
 	pid_t pid = fork();
@@ -55,7 +55,7 @@ bool run_test(int cpu)
 
 	if (pid < 0) {
 		ksft_print_msg("fork() failed: %s\n", strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 	if (pid == 0)
 		child(cpu);
@@ -63,67 +63,68 @@ bool run_test(int cpu)
 	wpid = waitpid(pid, &status, __WALL);
 	if (wpid != pid) {
 		ksft_print_msg("waitpid() failed: %s\n", strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 	if (!WIFSTOPPED(status)) {
 		ksft_print_msg("child did not stop: %s\n", strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 	if (WSTOPSIG(status) != SIGSTOP) {
 		ksft_print_msg("child did not stop with SIGSTOP: %s\n",
 			strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 
 	if (ptrace(PTRACE_SINGLESTEP, pid, NULL, NULL) < 0) {
 		if (errno == EIO) {
-			ksft_exit_skip(
+			ksft_print_msg(
 				"ptrace(PTRACE_SINGLESTEP) not supported on this architecture: %s\n",
 				strerror(errno));
+			return KSFT_SKIP;
 		}
 		ksft_print_msg("ptrace(PTRACE_SINGLESTEP) failed: %s\n",
 			strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 
 	wpid = waitpid(pid, &status, __WALL);
 	if (wpid != pid) {
 		ksft_print_msg("waitpid() failed: $s\n", strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 	if (WIFEXITED(status)) {
 		ksft_print_msg("child did not single-step: %s\n",
 			strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 	if (!WIFSTOPPED(status)) {
 		ksft_print_msg("child did not stop: %s\n", strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 	if (WSTOPSIG(status) != SIGTRAP) {
 		ksft_print_msg("child did not stop with SIGTRAP: %s\n",
 			strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 
 	if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) {
 		ksft_print_msg("ptrace(PTRACE_CONT) failed: %s\n",
 			strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 
 	wpid = waitpid(pid, &status, __WALL);
 	if (wpid != pid) {
 		ksft_print_msg("waitpid() failed: %s\n", strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 	if (!WIFEXITED(status)) {
 		ksft_print_msg("child did not exit after PTRACE_CONT: %s\n",
 			strerror(errno));
-		return false;
+		return KSFT_FAIL;
 	}
 
-	return true;
+	return KSFT_PASS;
 }
 
 void suspend(void)
@@ -183,32 +184,38 @@ int main(int argc, char **argv)
 		}
 	}
 
+	err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus);
+	if (err < 0)
+		ksft_exit_fail_msg("sched_getaffinity() failed\n");
+
 	for (cpu = 0; cpu < CPU_SETSIZE; cpu++) {
 		if (!CPU_ISSET(cpu, &available_cpus))
 			continue;
 		tests++;
 	}
-	ksft_set_plan(tests);
 
 	if (do_suspend)
 		suspend();
 
-	err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus);
-	if (err < 0)
-		ksft_exit_fail_msg("sched_getaffinity() failed\n");
-
+	ksft_set_plan(tests);
 	for (cpu = 0; cpu < CPU_SETSIZE; cpu++) {
-		bool test_success;
+		int test_success;
 
 		if (!CPU_ISSET(cpu, &available_cpus))
 			continue;
 
 		test_success = run_test(cpu);
-		if (test_success) {
+		switch (test_success) {
+		case KSFT_PASS:
 			ksft_test_result_pass("CPU %d\n", cpu);
-		} else {
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("CPU %d\n", cpu);
+			break;
+		case KSFT_FAIL:
 			ksft_test_result_fail("CPU %d\n", cpu);
 			succeeded = false;
+			break;
 		}
 	}
 
diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
index aa6de65b0838..84cfcabea838 100644
--- a/tools/testing/selftests/cgroup/.gitignore
+++ b/tools/testing/selftests/cgroup/.gitignore
@@ -2,3 +2,4 @@
 test_memcontrol
 test_core
 test_freezer
+test_kmem
\ No newline at end of file
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 967f268fde74..f027d933595b 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -6,11 +6,13 @@ all:
 TEST_FILES     := with_stress.sh
 TEST_PROGS     := test_stress.sh
 TEST_GEN_PROGS = test_memcontrol
+TEST_GEN_PROGS += test_kmem
 TEST_GEN_PROGS += test_core
 TEST_GEN_PROGS += test_freezer
 
 include ../lib.mk
 
 $(OUTPUT)/test_memcontrol: cgroup_util.c ../clone3/clone3_selftests.h
+$(OUTPUT)/test_kmem: cgroup_util.c ../clone3/clone3_selftests.h
 $(OUTPUT)/test_core: cgroup_util.c ../clone3/clone3_selftests.h
 $(OUTPUT)/test_freezer: cgroup_util.c ../clone3/clone3_selftests.h
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 8a637ca7d73a..05853b0b8831 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -106,7 +106,7 @@ int cg_read_strcmp(const char *cgroup, const char *control,
 
 	/* Handle the case of comparing against empty string */
 	if (!expected)
-		size = 32;
+		return -1;
 	else
 		size = strlen(expected) + 1;
 
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
new file mode 100644
index 000000000000..0941aa16157e
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -0,0 +1,450 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/wait.h>
+#include <errno.h>
+#include <sys/sysinfo.h>
+#include <pthread.h>
+
+#include "../kselftest.h"
+#include "cgroup_util.h"
+
+
+/*
+ * Memory cgroup charging and vmstat data aggregation is performed using
+ * percpu batches 32 pages big (look at MEMCG_CHARGE_BATCH). So the maximum
+ * discrepancy between charge and vmstat entries is number of cpus multiplied
+ * by 32 pages multiplied by 2.
+ */
+#define MAX_VMSTAT_ERROR (4096 * 32 * 2 * get_nprocs())
+
+
+static int alloc_dcache(const char *cgroup, void *arg)
+{
+	unsigned long i;
+	struct stat st;
+	char buf[128];
+
+	for (i = 0; i < (unsigned long)arg; i++) {
+		snprintf(buf, sizeof(buf),
+			"/something-non-existent-with-a-long-name-%64lu-%d",
+			 i, getpid());
+		stat(buf, &st);
+	}
+
+	return 0;
+}
+
+/*
+ * This test allocates 100000 of negative dentries with long names.
+ * Then it checks that "slab" in memory.stat is larger than 1M.
+ * Then it sets memory.high to 1M and checks that at least 1/2
+ * of slab memory has been reclaimed.
+ */
+static int test_kmem_basic(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg = NULL;
+	long slab0, slab1, current;
+
+	cg = cg_name(root, "kmem_basic_test");
+	if (!cg)
+		goto cleanup;
+
+	if (cg_create(cg))
+		goto cleanup;
+
+	if (cg_run(cg, alloc_dcache, (void *)100000))
+		goto cleanup;
+
+	slab0 = cg_read_key_long(cg, "memory.stat", "slab ");
+	if (slab0 < (1 << 20))
+		goto cleanup;
+
+	cg_write(cg, "memory.high", "1M");
+	slab1 = cg_read_key_long(cg, "memory.stat", "slab ");
+	if (slab1 <= 0)
+		goto cleanup;
+
+	current = cg_read_long(cg, "memory.current");
+	if (current <= 0)
+		goto cleanup;
+
+	if (slab1 < slab0 / 2 && current < slab0 / 2)
+		ret = KSFT_PASS;
+cleanup:
+	cg_destroy(cg);
+	free(cg);
+
+	return ret;
+}
+
+static void *alloc_kmem_fn(void *arg)
+{
+	alloc_dcache(NULL, (void *)100);
+	return NULL;
+}
+
+static int alloc_kmem_smp(const char *cgroup, void *arg)
+{
+	int nr_threads = 2 * get_nprocs();
+	pthread_t *tinfo;
+	unsigned long i;
+	int ret = -1;
+
+	tinfo = calloc(nr_threads, sizeof(pthread_t));
+	if (tinfo == NULL)
+		return -1;
+
+	for (i = 0; i < nr_threads; i++) {
+		if (pthread_create(&tinfo[i], NULL, &alloc_kmem_fn,
+				   (void *)i)) {
+			free(tinfo);
+			return -1;
+		}
+	}
+
+	for (i = 0; i < nr_threads; i++) {
+		ret = pthread_join(tinfo[i], NULL);
+		if (ret)
+			break;
+	}
+
+	free(tinfo);
+	return ret;
+}
+
+static int cg_run_in_subcgroups(const char *parent,
+				int (*fn)(const char *cgroup, void *arg),
+				void *arg, int times)
+{
+	char *child;
+	int i;
+
+	for (i = 0; i < times; i++) {
+		child = cg_name_indexed(parent, "child", i);
+		if (!child)
+			return -1;
+
+		if (cg_create(child)) {
+			cg_destroy(child);
+			free(child);
+			return -1;
+		}
+
+		if (cg_run(child, fn, NULL)) {
+			cg_destroy(child);
+			free(child);
+			return -1;
+		}
+
+		cg_destroy(child);
+		free(child);
+	}
+
+	return 0;
+}
+
+/*
+ * The test creates and destroys a large number of cgroups. In each cgroup it
+ * allocates some slab memory (mostly negative dentries) using 2 * NR_CPUS
+ * threads. Then it checks the sanity of numbers on the parent level:
+ * the total size of the cgroups should be roughly equal to
+ * anon + file + slab + kernel_stack.
+ */
+static int test_kmem_memcg_deletion(const char *root)
+{
+	long current, slab, anon, file, kernel_stack, sum;
+	int ret = KSFT_FAIL;
+	char *parent;
+
+	parent = cg_name(root, "kmem_memcg_deletion_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_run_in_subcgroups(parent, alloc_kmem_smp, NULL, 100))
+		goto cleanup;
+
+	current = cg_read_long(parent, "memory.current");
+	slab = cg_read_key_long(parent, "memory.stat", "slab ");
+	anon = cg_read_key_long(parent, "memory.stat", "anon ");
+	file = cg_read_key_long(parent, "memory.stat", "file ");
+	kernel_stack = cg_read_key_long(parent, "memory.stat", "kernel_stack ");
+	if (current < 0 || slab < 0 || anon < 0 || file < 0 ||
+	    kernel_stack < 0)
+		goto cleanup;
+
+	sum = slab + anon + file + kernel_stack;
+	if (abs(sum - current) < MAX_VMSTAT_ERROR) {
+		ret = KSFT_PASS;
+	} else {
+		printf("memory.current = %ld\n", current);
+		printf("slab + anon + file + kernel_stack = %ld\n", sum);
+		printf("slab = %ld\n", slab);
+		printf("anon = %ld\n", anon);
+		printf("file = %ld\n", file);
+		printf("kernel_stack = %ld\n", kernel_stack);
+	}
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * The test reads the entire /proc/kpagecgroup. If the operation went
+ * successfully (and the kernel didn't panic), the test is treated as passed.
+ */
+static int test_kmem_proc_kpagecgroup(const char *root)
+{
+	unsigned long buf[128];
+	int ret = KSFT_FAIL;
+	ssize_t len;
+	int fd;
+
+	fd = open("/proc/kpagecgroup", O_RDONLY);
+	if (fd < 0)
+		return ret;
+
+	do {
+		len = read(fd, buf, sizeof(buf));
+	} while (len > 0);
+
+	if (len == 0)
+		ret = KSFT_PASS;
+
+	close(fd);
+	return ret;
+}
+
+static void *pthread_wait_fn(void *arg)
+{
+	sleep(100);
+	return NULL;
+}
+
+static int spawn_1000_threads(const char *cgroup, void *arg)
+{
+	int nr_threads = 1000;
+	pthread_t *tinfo;
+	unsigned long i;
+	long stack;
+	int ret = -1;
+
+	tinfo = calloc(nr_threads, sizeof(pthread_t));
+	if (tinfo == NULL)
+		return -1;
+
+	for (i = 0; i < nr_threads; i++) {
+		if (pthread_create(&tinfo[i], NULL, &pthread_wait_fn,
+				   (void *)i)) {
+			free(tinfo);
+			return(-1);
+		}
+	}
+
+	stack = cg_read_key_long(cgroup, "memory.stat", "kernel_stack ");
+	if (stack >= 4096 * 1000)
+		ret = 0;
+
+	free(tinfo);
+	return ret;
+}
+
+/*
+ * The test spawns a process, which spawns 1000 threads. Then it checks
+ * that memory.stat's kernel_stack is at least 1000 pages large.
+ */
+static int test_kmem_kernel_stacks(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg = NULL;
+
+	cg = cg_name(root, "kmem_kernel_stacks_test");
+	if (!cg)
+		goto cleanup;
+
+	if (cg_create(cg))
+		goto cleanup;
+
+	if (cg_run(cg, spawn_1000_threads, NULL))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+cleanup:
+	cg_destroy(cg);
+	free(cg);
+
+	return ret;
+}
+
+/*
+ * This test sequentionally creates 30 child cgroups, allocates some
+ * kernel memory in each of them, and deletes them. Then it checks
+ * that the number of dying cgroups on the parent level is 0.
+ */
+static int test_kmem_dead_cgroups(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent;
+	long dead;
+	int i;
+
+	parent = cg_name(root, "kmem_dead_cgroups_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_run_in_subcgroups(parent, alloc_dcache, (void *)100, 30))
+		goto cleanup;
+
+	for (i = 0; i < 5; i++) {
+		dead = cg_read_key_long(parent, "cgroup.stat",
+					"nr_dying_descendants ");
+		if (dead == 0) {
+			ret = KSFT_PASS;
+			break;
+		}
+		/*
+		 * Reclaiming cgroups might take some time,
+		 * let's wait a bit and repeat.
+		 */
+		sleep(1);
+	}
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * This test creates a sub-tree with 1000 memory cgroups.
+ * Then it checks that the memory.current on the parent level
+ * is greater than 0 and approximates matches the percpu value
+ * from memory.stat.
+ */
+static int test_percpu_basic(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent, *child;
+	long current, percpu;
+	int i;
+
+	parent = cg_name(root, "percpu_basic_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	for (i = 0; i < 1000; i++) {
+		child = cg_name_indexed(parent, "child", i);
+		if (!child)
+			return -1;
+
+		if (cg_create(child))
+			goto cleanup_children;
+
+		free(child);
+	}
+
+	current = cg_read_long(parent, "memory.current");
+	percpu = cg_read_key_long(parent, "memory.stat", "percpu ");
+
+	if (current > 0 && percpu > 0 && abs(current - percpu) <
+	    MAX_VMSTAT_ERROR)
+		ret = KSFT_PASS;
+	else
+		printf("memory.current %ld\npercpu %ld\n",
+		       current, percpu);
+
+cleanup_children:
+	for (i = 0; i < 1000; i++) {
+		child = cg_name_indexed(parent, "child", i);
+		cg_destroy(child);
+		free(child);
+	}
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+#define T(x) { x, #x }
+struct kmem_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_kmem_basic),
+	T(test_kmem_memcg_deletion),
+	T(test_kmem_proc_kpagecgroup),
+	T(test_kmem_kernel_stacks),
+	T(test_kmem_dead_cgroups),
+	T(test_percpu_basic),
+};
+#undef T
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int i, ret = EXIT_SUCCESS;
+
+	if (cg_find_unified_root(root, sizeof(root)))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	/*
+	 * Check that memory controller is available:
+	 * memory is listed in cgroup.controllers
+	 */
+	if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+		ksft_exit_skip("memory controller isn't available\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
+		if (cg_write(root, "cgroup.subtree_control", "+memory"))
+			ksft_exit_skip("Failed to set memory controller\n");
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ret = EXIT_FAILURE;
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	return ret;
+}
diff --git a/tools/testing/selftests/clone3/.gitignore b/tools/testing/selftests/clone3/.gitignore
index a81085742d40..83c0f6246055 100644
--- a/tools/testing/selftests/clone3/.gitignore
+++ b/tools/testing/selftests/clone3/.gitignore
@@ -2,3 +2,4 @@
 clone3
 clone3_clear_sighand
 clone3_set_tid
+clone3_cap_checkpoint_restore
diff --git a/tools/testing/selftests/clone3/Makefile b/tools/testing/selftests/clone3/Makefile
index cf976c732906..ef7564cb7abe 100644
--- a/tools/testing/selftests/clone3/Makefile
+++ b/tools/testing/selftests/clone3/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -g -I../../../../usr/include/
+LDLIBS += -lcap
 
-TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid
+TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid \
+	clone3_cap_checkpoint_restore
 
 include ../lib.mk
diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c
index f14c269a5a18..b7e6dec36173 100644
--- a/tools/testing/selftests/clone3/clone3.c
+++ b/tools/testing/selftests/clone3/clone3.c
@@ -131,9 +131,9 @@ int main(int argc, char *argv[])
 
 	uid_t uid = getuid();
 
-	test_clone3_supported();
 	ksft_print_header();
 	ksft_set_plan(17);
+	test_clone3_supported();
 
 	/* Just a simple clone3() should return 0.*/
 	test_clone3(0, 0, 0, CLONE3_ARGS_NO_TEST);
diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
new file mode 100644
index 000000000000..9562425aa0a9
--- /dev/null
+++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Based on Christian Brauner's clone3() example.
+ * These tests are assuming to be running in the host's
+ * PID namespace.
+ */
+
+/* capabilities related code based on selftests/bpf/test_verifier.c */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/capability.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sched.h>
+
+#include "../kselftest_harness.h"
+#include "clone3_selftests.h"
+
+#ifndef MAX_PID_NS_LEVEL
+#define MAX_PID_NS_LEVEL 32
+#endif
+
+static void child_exit(int ret)
+{
+	fflush(stdout);
+	fflush(stderr);
+	_exit(ret);
+}
+
+static int call_clone3_set_tid(struct __test_metadata *_metadata,
+			       pid_t *set_tid, size_t set_tid_size)
+{
+	int status;
+	pid_t pid = -1;
+
+	struct clone_args args = {
+		.exit_signal = SIGCHLD,
+		.set_tid = ptr_to_u64(set_tid),
+		.set_tid_size = set_tid_size,
+	};
+
+	pid = sys_clone3(&args, sizeof(struct clone_args));
+	if (pid < 0) {
+		TH_LOG("%s - Failed to create new process", strerror(errno));
+		return -errno;
+	}
+
+	if (pid == 0) {
+		int ret;
+		char tmp = 0;
+
+		TH_LOG("I am the child, my PID is %d (expected %d)", getpid(), set_tid[0]);
+
+		if (set_tid[0] != getpid())
+			child_exit(EXIT_FAILURE);
+		child_exit(EXIT_SUCCESS);
+	}
+
+	TH_LOG("I am the parent (%d). My child's pid is %d", getpid(), pid);
+
+	if (waitpid(pid, &status, 0) < 0) {
+		TH_LOG("Child returned %s", strerror(errno));
+		return -errno;
+	}
+
+	if (!WIFEXITED(status))
+		return -1;
+
+	return WEXITSTATUS(status);
+}
+
+static int test_clone3_set_tid(struct __test_metadata *_metadata,
+			       pid_t *set_tid, size_t set_tid_size)
+{
+	int ret;
+
+	TH_LOG("[%d] Trying clone3() with CLONE_SET_TID to %d", getpid(), set_tid[0]);
+	ret = call_clone3_set_tid(_metadata, set_tid, set_tid_size);
+	TH_LOG("[%d] clone3() with CLONE_SET_TID %d says:%d", getpid(), set_tid[0], ret);
+	return ret;
+}
+
+struct libcap {
+	struct __user_cap_header_struct hdr;
+	struct __user_cap_data_struct data[2];
+};
+
+static int set_capability(void)
+{
+	cap_value_t cap_values[] = { CAP_SETUID, CAP_SETGID };
+	struct libcap *cap;
+	int ret = -1;
+	cap_t caps;
+
+	caps = cap_get_proc();
+	if (!caps) {
+		perror("cap_get_proc");
+		return -1;
+	}
+
+	/* Drop all capabilities */
+	if (cap_clear(caps)) {
+		perror("cap_clear");
+		goto out;
+	}
+
+	cap_set_flag(caps, CAP_EFFECTIVE, 2, cap_values, CAP_SET);
+	cap_set_flag(caps, CAP_PERMITTED, 2, cap_values, CAP_SET);
+
+	cap = (struct libcap *) caps;
+
+	/* 40 -> CAP_CHECKPOINT_RESTORE */
+	cap->data[1].effective |= 1 << (40 - 32);
+	cap->data[1].permitted |= 1 << (40 - 32);
+
+	if (cap_set_proc(caps)) {
+		perror("cap_set_proc");
+		goto out;
+	}
+	ret = 0;
+out:
+	if (cap_free(caps))
+		perror("cap_free");
+	return ret;
+}
+
+TEST(clone3_cap_checkpoint_restore)
+{
+	pid_t pid;
+	int status;
+	int ret = 0;
+	pid_t set_tid[1];
+
+	test_clone3_supported();
+
+	EXPECT_EQ(getuid(), 0)
+		XFAIL(return, "Skipping all tests as non-root\n");
+
+	memset(&set_tid, 0, sizeof(set_tid));
+
+	/* Find the current active PID */
+	pid = fork();
+	if (pid == 0) {
+		TH_LOG("Child has PID %d", getpid());
+		child_exit(EXIT_SUCCESS);
+	}
+	ASSERT_GT(waitpid(pid, &status, 0), 0)
+		TH_LOG("Waiting for child %d failed", pid);
+
+	/* After the child has finished, its PID should be free. */
+	set_tid[0] = pid;
+
+	ASSERT_EQ(set_capability(), 0)
+		TH_LOG("Could not set CAP_CHECKPOINT_RESTORE");
+
+	ASSERT_EQ(prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0), 0);
+
+	EXPECT_EQ(setgid(65534), 0)
+		TH_LOG("Failed to setgid(65534)");
+	ASSERT_EQ(setuid(65534), 0);
+
+	set_tid[0] = pid;
+	/* This would fail without CAP_CHECKPOINT_RESTORE */
+	ASSERT_EQ(test_clone3_set_tid(_metadata, set_tid, 1), -EPERM);
+	ASSERT_EQ(set_capability(), 0)
+		TH_LOG("Could not set CAP_CHECKPOINT_RESTORE");
+	/* This should work as we have CAP_CHECKPOINT_RESTORE as non-root */
+	ASSERT_EQ(test_clone3_set_tid(_metadata, set_tid, 1), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/clone3/clone3_clear_sighand.c b/tools/testing/selftests/clone3/clone3_clear_sighand.c
index 9e1af8aa7698..db5fc9c5edcf 100644
--- a/tools/testing/selftests/clone3/clone3_clear_sighand.c
+++ b/tools/testing/selftests/clone3/clone3_clear_sighand.c
@@ -119,9 +119,8 @@ static void test_clone3_clear_sighand(void)
 int main(int argc, char **argv)
 {
 	ksft_print_header();
-	test_clone3_supported();
-
 	ksft_set_plan(1);
+	test_clone3_supported();
 
 	test_clone3_clear_sighand();
 
diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c
index 25beb22f35b5..5831c1082d6d 100644
--- a/tools/testing/selftests/clone3/clone3_set_tid.c
+++ b/tools/testing/selftests/clone3/clone3_set_tid.c
@@ -157,8 +157,8 @@ int main(int argc, char *argv[])
 	pid_t set_tid[MAX_PID_NS_LEVEL * 2];
 
 	ksft_print_header();
-	test_clone3_supported();
 	ksft_set_plan(29);
+	test_clone3_supported();
 
 	if (pipe(pipe_1) < 0 || pipe(pipe_2) < 0)
 		ksft_exit_fail_msg("pipe() failed\n");
diff --git a/tools/testing/selftests/core/.gitignore b/tools/testing/selftests/core/.gitignore
new file mode 100644
index 000000000000..6e6712ce5817
--- /dev/null
+++ b/tools/testing/selftests/core/.gitignore
@@ -0,0 +1 @@
+close_range_test
diff --git a/tools/testing/selftests/core/Makefile b/tools/testing/selftests/core/Makefile
new file mode 100644
index 000000000000..f6f2d6f473c6
--- /dev/null
+++ b/tools/testing/selftests/core/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+CFLAGS += -g -I../../../../usr/include/
+
+TEST_GEN_PROGS := close_range_test
+
+include ../lib.mk
+
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
new file mode 100644
index 000000000000..c99b98b0d461
--- /dev/null
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+#include "../clone3/clone3_selftests.h"
+
+#ifndef __NR_close_range
+#define __NR_close_range -1
+#endif
+
+#ifndef CLOSE_RANGE_UNSHARE
+#define CLOSE_RANGE_UNSHARE	(1U << 1)
+#endif
+
+static inline int sys_close_range(unsigned int fd, unsigned int max_fd,
+				  unsigned int flags)
+{
+	return syscall(__NR_close_range, fd, max_fd, flags);
+}
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+TEST(close_range)
+{
+	int i, ret;
+	int open_fds[101];
+
+	for (i = 0; i < ARRAY_SIZE(open_fds); i++) {
+		int fd;
+
+		fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+		ASSERT_GE(fd, 0) {
+			if (errno == ENOENT)
+				XFAIL(return, "Skipping test since /dev/null does not exist");
+		}
+
+		open_fds[i] = fd;
+	}
+
+	EXPECT_EQ(-1, sys_close_range(open_fds[0], open_fds[100], -1)) {
+		if (errno == ENOSYS)
+			XFAIL(return, "close_range() syscall not supported");
+	}
+
+	EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0));
+
+	for (i = 0; i <= 50; i++)
+		EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL));
+
+	for (i = 51; i <= 100; i++)
+		EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1);
+
+	/* create a couple of gaps */
+	close(57);
+	close(78);
+	close(81);
+	close(82);
+	close(84);
+	close(90);
+
+	EXPECT_EQ(0, sys_close_range(open_fds[51], open_fds[92], 0));
+
+	for (i = 51; i <= 92; i++)
+		EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL));
+
+	for (i = 93; i <= 100; i++)
+		EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1);
+
+	/* test that the kernel caps and still closes all fds */
+	EXPECT_EQ(0, sys_close_range(open_fds[93], open_fds[99], 0));
+
+	for (i = 93; i <= 99; i++)
+		EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL));
+
+	EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1);
+
+	EXPECT_EQ(0, sys_close_range(open_fds[100], open_fds[100], 0));
+
+	EXPECT_EQ(-1, fcntl(open_fds[100], F_GETFL));
+}
+
+TEST(close_range_unshare)
+{
+	int i, ret, status;
+	pid_t pid;
+	int open_fds[101];
+	struct clone_args args = {
+		.flags = CLONE_FILES,
+		.exit_signal = SIGCHLD,
+	};
+
+	for (i = 0; i < ARRAY_SIZE(open_fds); i++) {
+		int fd;
+
+		fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+		ASSERT_GE(fd, 0) {
+			if (errno == ENOENT)
+				XFAIL(return, "Skipping test since /dev/null does not exist");
+		}
+
+		open_fds[i] = fd;
+	}
+
+	pid = sys_clone3(&args, sizeof(args));
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		ret = sys_close_range(open_fds[0], open_fds[50],
+				      CLOSE_RANGE_UNSHARE);
+		if (ret)
+			exit(EXIT_FAILURE);
+
+		for (i = 0; i <= 50; i++)
+			if (fcntl(open_fds[i], F_GETFL) != -1)
+				exit(EXIT_FAILURE);
+
+		for (i = 51; i <= 100; i++)
+			if (fcntl(open_fds[i], F_GETFL) == -1)
+				exit(EXIT_FAILURE);
+
+		/* create a couple of gaps */
+		close(57);
+		close(78);
+		close(81);
+		close(82);
+		close(84);
+		close(90);
+
+		ret = sys_close_range(open_fds[51], open_fds[92],
+				      CLOSE_RANGE_UNSHARE);
+		if (ret)
+			exit(EXIT_FAILURE);
+
+		for (i = 51; i <= 92; i++)
+			if (fcntl(open_fds[i], F_GETFL) != -1)
+				exit(EXIT_FAILURE);
+
+		for (i = 93; i <= 100; i++)
+			if (fcntl(open_fds[i], F_GETFL) == -1)
+				exit(EXIT_FAILURE);
+
+		/* test that the kernel caps and still closes all fds */
+		ret = sys_close_range(open_fds[93], open_fds[99],
+				      CLOSE_RANGE_UNSHARE);
+		if (ret)
+			exit(EXIT_FAILURE);
+
+		for (i = 93; i <= 99; i++)
+			if (fcntl(open_fds[i], F_GETFL) != -1)
+				exit(EXIT_FAILURE);
+
+		if (fcntl(open_fds[100], F_GETFL) == -1)
+			exit(EXIT_FAILURE);
+
+		ret = sys_close_range(open_fds[100], open_fds[100],
+				      CLOSE_RANGE_UNSHARE);
+		if (ret)
+			exit(EXIT_FAILURE);
+
+		if (fcntl(open_fds[100], F_GETFL) != -1)
+			exit(EXIT_FAILURE);
+
+		exit(EXIT_SUCCESS);
+	}
+
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
+TEST(close_range_unshare_capped)
+{
+	int i, ret, status;
+	pid_t pid;
+	int open_fds[101];
+	struct clone_args args = {
+		.flags = CLONE_FILES,
+		.exit_signal = SIGCHLD,
+	};
+
+	for (i = 0; i < ARRAY_SIZE(open_fds); i++) {
+		int fd;
+
+		fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+		ASSERT_GE(fd, 0) {
+			if (errno == ENOENT)
+				XFAIL(return, "Skipping test since /dev/null does not exist");
+		}
+
+		open_fds[i] = fd;
+	}
+
+	pid = sys_clone3(&args, sizeof(args));
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		ret = sys_close_range(open_fds[0], UINT_MAX,
+				      CLOSE_RANGE_UNSHARE);
+		if (ret)
+			exit(EXIT_FAILURE);
+
+		for (i = 0; i <= 100; i++)
+			if (fcntl(open_fds[i], F_GETFL) != -1)
+				exit(EXIT_FAILURE);
+
+		exit(EXIT_SUCCESS);
+	}
+
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index 0d347d48c112..517297a14ecf 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -121,6 +121,7 @@ h1_destroy()
 h2_create()
 {
 	host_create $h2 2
+	tc qdisc add dev $h2 clsact
 
 	# Some of the tests in this suite use multicast traffic. As this traffic
 	# enters BR2_10 resp. BR2_11, it is flooded to all other ports. Thus
@@ -141,6 +142,7 @@ h2_create()
 h2_destroy()
 {
 	ethtool -s $h2 autoneg on
+	tc qdisc del dev $h2 clsact
 	host_destroy $h2
 }
 
@@ -336,6 +338,17 @@ get_qdisc_npackets()
 		qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .packets
 }
 
+send_packets()
+{
+	local vlan=$1; shift
+	local proto=$1; shift
+	local pkts=$1; shift
+
+	$MZ $h2.$vlan -p 8000 -a own -b $h3_mac \
+	    -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \
+	    -t $proto -q -c $pkts "$@"
+}
+
 # This sends traffic in an attempt to build a backlog of $size. Returns 0 on
 # success. After 10 failed attempts it bails out and returns 1. It dumps the
 # backlog size to stdout.
@@ -364,9 +377,7 @@ build_backlog()
 			return 1
 		fi
 
-		$MZ $h2.$vlan -p 8000 -a own -b $h3_mac \
-		    -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \
-		    -t $proto -q -c $pkts "$@"
+		send_packets $vlan $proto $pkts "$@"
 	done
 }
 
@@ -531,3 +542,115 @@ do_mc_backlog_test()
 
 	log_test "TC $((vlan - 10)): Qdisc reports MC backlog"
 }
+
+do_drop_test()
+{
+	local vlan=$1; shift
+	local limit=$1; shift
+	local trigger=$1; shift
+	local subtest=$1; shift
+	local fetch_counter=$1; shift
+	local backlog
+	local base
+	local now
+	local pct
+
+	RET=0
+
+	start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) $h3_mac
+
+	# Create a bit of a backlog and observe no mirroring due to drops.
+	qevent_rule_install_$subtest
+	base=$($fetch_counter)
+
+	build_backlog $vlan $((2 * limit / 3)) udp >/dev/null
+
+	busywait 1100 until_counter_is ">= $((base + 1))" $fetch_counter >/dev/null
+	check_fail $? "Spurious packets observed without buffer pressure"
+
+	# Push to the queue until it's at the limit. The configured limit is
+	# rounded by the qdisc and then by the driver, so this is the best we
+	# can do to get to the real limit of the system.
+	build_backlog $vlan $((3 * limit / 2)) udp >/dev/null
+
+	base=$($fetch_counter)
+	send_packets $vlan udp 11
+
+	now=$(busywait 1100 until_counter_is ">= $((base + 10))" $fetch_counter)
+	check_err $? "Dropped packets not observed: 11 expected, $((now - base)) seen"
+
+	# When no extra traffic is injected, there should be no mirroring.
+	busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null
+	check_fail $? "Spurious packets observed"
+
+	# When the rule is uninstalled, there should be no mirroring.
+	qevent_rule_uninstall_$subtest
+	send_packets $vlan udp 11
+	busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null
+	check_fail $? "Spurious packets observed after uninstall"
+
+	log_test "TC $((vlan - 10)): ${trigger}ped packets $subtest'd"
+
+	stop_traffic
+	sleep 1
+}
+
+qevent_rule_install_mirror()
+{
+	tc filter add block 10 pref 1234 handle 102 matchall skip_sw \
+	   action mirred egress mirror dev $swp2 hw_stats disabled
+}
+
+qevent_rule_uninstall_mirror()
+{
+	tc filter del block 10 pref 1234 handle 102 matchall
+}
+
+qevent_counter_fetch_mirror()
+{
+	tc_rule_handle_stats_get "dev $h2 ingress" 101
+}
+
+do_drop_mirror_test()
+{
+	local vlan=$1; shift
+	local limit=$1; shift
+	local qevent_name=$1; shift
+
+	tc filter add dev $h2 ingress pref 1 handle 101 prot ip \
+	   flower skip_sw ip_proto udp \
+	   action drop
+
+	do_drop_test "$vlan" "$limit" "$qevent_name" mirror \
+		     qevent_counter_fetch_mirror
+
+	tc filter del dev $h2 ingress pref 1 handle 101 flower
+}
+
+qevent_rule_install_trap()
+{
+	tc filter add block 10 pref 1234 handle 102 matchall skip_sw \
+	   action trap hw_stats disabled
+}
+
+qevent_rule_uninstall_trap()
+{
+	tc filter del block 10 pref 1234 handle 102 matchall
+}
+
+qevent_counter_fetch_trap()
+{
+	local trap_name=$1; shift
+
+	devlink_trap_rx_packets_get "$trap_name"
+}
+
+do_drop_trap_test()
+{
+	local vlan=$1; shift
+	local limit=$1; shift
+	local trap_name=$1; shift
+
+	do_drop_test "$vlan" "$limit" "$trap_name" trap \
+		     "qevent_counter_fetch_trap $trap_name"
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
index 1c36c576613b..3f007c5f8361 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
@@ -7,6 +7,8 @@ ALL_TESTS="
 	ecn_nodrop_test
 	red_test
 	mc_backlog_test
+	red_mirror_test
+	red_trap_test
 "
 : ${QDISC:=ets}
 source sch_red_core.sh
@@ -83,6 +85,26 @@ mc_backlog_test()
 	uninstall_qdisc
 }
 
+red_mirror_test()
+{
+	install_qdisc qevent early_drop block 10
+
+	do_drop_mirror_test 10 $BACKLOG1 early_drop
+	do_drop_mirror_test 11 $BACKLOG2 early_drop
+
+	uninstall_qdisc
+}
+
+red_trap_test()
+{
+	install_qdisc qevent early_drop block 10
+
+	do_drop_trap_test 10 $BACKLOG1 early_drop
+	do_drop_trap_test 11 $BACKLOG2 early_drop
+
+	uninstall_qdisc
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
index 558667ea11ec..ede9c38d3eff 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
@@ -7,6 +7,7 @@ ALL_TESTS="
 	ecn_nodrop_test
 	red_test
 	mc_backlog_test
+	red_mirror_test
 "
 source sch_red_core.sh
 
@@ -57,6 +58,13 @@ mc_backlog_test()
 	uninstall_qdisc
 }
 
+red_mirror_test()
+{
+	install_qdisc qevent early_drop block 10
+	do_drop_mirror_test 10 $BACKLOG
+	uninstall_qdisc
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
index fd583a171db7..d7cf33a3f18d 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
@@ -28,7 +28,7 @@ cleanup()
 
 trap cleanup EXIT
 
-ALL_TESTS="router tc_flower mirror_gre"
+ALL_TESTS="router tc_flower mirror_gre tc_police"
 for current_test in ${TESTS:-$ALL_TESTS}; do
 	source ${current_test}_scale.sh
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_police_scale.sh
new file mode 100644
index 000000000000..e79ac0dad1f4
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_police_scale.sh
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../tc_police_scale.sh
+
+tc_police_get_target()
+{
+	local should_fail=$1; shift
+	local target
+
+	target=$(devlink_resource_size_get global_policers single_rate_policers)
+
+	if ((! should_fail)); then
+		echo $target
+	else
+		echo $((target + 1))
+	fi
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index 43ba1b438f6d..43f662401bc3 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -22,7 +22,7 @@ cleanup()
 devlink_sp_read_kvd_defaults
 trap cleanup EXIT
 
-ALL_TESTS="router tc_flower mirror_gre"
+ALL_TESTS="router tc_flower mirror_gre tc_police"
 for current_test in ${TESTS:-$ALL_TESTS}; do
 	source ${current_test}_scale.sh
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_police_scale.sh
new file mode 100644
index 000000000000..e79ac0dad1f4
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_police_scale.sh
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../tc_police_scale.sh
+
+tc_police_get_target()
+{
+	local should_fail=$1; shift
+	local target
+
+	target=$(devlink_resource_size_get global_policers single_rate_policers)
+
+	if ((! should_fail)); then
+		echo $target
+	else
+		echo $((target + 1))
+	fi
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_occ.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_occ.sh
new file mode 100755
index 000000000000..448b75c1545a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_occ.sh
@@ -0,0 +1,108 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that policers shared by different tc filters are correctly reference
+# counted by observing policers' occupancy via devlink-resource.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	tc_police_occ_test
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1
+}
+
+switch_create()
+{
+	simple_if_init $swp1
+	tc qdisc add dev $swp1 clsact
+}
+
+switch_destroy()
+{
+	tc qdisc del dev $swp1 clsact
+	simple_if_fini $swp1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	vrf_prepare
+
+	h1_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+tc_police_occ_get()
+{
+	devlink_resource_occ_get global_policers single_rate_policers
+}
+
+tc_police_occ_test()
+{
+	RET=0
+
+	local occ=$(tc_police_occ_get)
+
+	tc filter add dev $swp1 ingress pref 1 handle 101 proto ip \
+		flower skip_sw \
+		action police rate 100mbit burst 100k conform-exceed drop/ok
+	(( occ + 1 == $(tc_police_occ_get) ))
+	check_err $? "Got occupancy $(tc_police_occ_get), expected $((occ + 1))"
+
+	tc filter del dev $swp1 ingress pref 1 handle 101 flower
+	(( occ == $(tc_police_occ_get) ))
+	check_err $? "Got occupancy $(tc_police_occ_get), expected $occ"
+
+	tc filter add dev $swp1 ingress pref 1 handle 101 proto ip \
+		flower skip_sw \
+		action police rate 100mbit burst 100k conform-exceed drop/ok \
+		index 10
+	tc filter add dev $swp1 ingress pref 2 handle 102 proto ip \
+		flower skip_sw action police index 10
+
+	(( occ + 1 == $(tc_police_occ_get) ))
+	check_err $? "Got occupancy $(tc_police_occ_get), expected $((occ + 1))"
+
+	tc filter del dev $swp1 ingress pref 2 handle 102 flower
+	(( occ + 1 == $(tc_police_occ_get) ))
+	check_err $? "Got occupancy $(tc_police_occ_get), expected $((occ + 1))"
+
+	tc filter del dev $swp1 ingress pref 1 handle 101 flower
+	(( occ == $(tc_police_occ_get) ))
+	check_err $? "Got occupancy $(tc_police_occ_get), expected $occ"
+
+	log_test "tc police occupancy"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
new file mode 100644
index 000000000000..4b96561c462f
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
@@ -0,0 +1,92 @@
+# SPDX-License-Identifier: GPL-2.0
+
+TC_POLICE_NUM_NETIFS=2
+
+tc_police_h1_create()
+{
+	simple_if_init $h1
+}
+
+tc_police_h1_destroy()
+{
+	simple_if_fini $h1
+}
+
+tc_police_switch_create()
+{
+	simple_if_init $swp1
+	tc qdisc add dev $swp1 clsact
+}
+
+tc_police_switch_destroy()
+{
+	tc qdisc del dev $swp1 clsact
+	simple_if_fini $swp1
+}
+
+tc_police_rules_create()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	TC_POLICE_BATCH_FILE="$(mktemp)"
+
+	for ((i = 0; i < count; ++i)); do
+		cat >> $TC_POLICE_BATCH_FILE <<-EOF
+			filter add dev $swp1 ingress \
+				prot ip \
+				flower skip_sw \
+				action police rate 10mbit burst 100k \
+				conform-exceed drop/ok
+		EOF
+	done
+
+	tc -b $TC_POLICE_BATCH_FILE
+	check_err_fail $should_fail $? "Rule insertion"
+}
+
+__tc_police_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	tc_police_rules_create $count $should_fail
+
+	offload_count=$(tc filter show dev $swp1 ingress | grep in_hw | wc -l)
+	((offload_count == count))
+	check_err_fail $should_fail $? "tc police offload count"
+}
+
+tc_police_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	if ! tc_offload_check $TC_POLICE_NUM_NETIFS; then
+		check_err 1 "Could not test offloaded functionality"
+		return
+	fi
+
+	__tc_police_test $count $should_fail
+}
+
+tc_police_setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	vrf_prepare
+
+	tc_police_h1_create
+	tc_police_switch_create
+}
+
+tc_police_cleanup()
+{
+	pre_cleanup
+
+	tc_police_switch_destroy
+	tc_police_h1_destroy
+
+	vrf_cleanup
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
index 9241250c5921..553cb9fad508 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
@@ -11,6 +11,8 @@ ALL_TESTS="
 	matchall_mirror_behind_flower_ingress_test
 	matchall_sample_behind_flower_ingress_test
 	matchall_mirror_behind_flower_egress_test
+	police_limits_test
+	multi_police_test
 "
 NUM_NETIFS=2
 
@@ -287,6 +289,80 @@ matchall_mirror_behind_flower_egress_test()
 	matchall_behind_flower_egress_test "mirror" "mirred egress mirror dev $swp2"
 }
 
+police_limits_test()
+{
+	RET=0
+
+	tc qdisc add dev $swp1 clsact
+
+	tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
+		flower skip_sw \
+		action police rate 0.5kbit burst 1m conform-exceed drop/ok
+	check_fail $? "Incorrect success to add police action with too low rate"
+
+	tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
+		flower skip_sw \
+		action police rate 2.5tbit burst 1g conform-exceed drop/ok
+	check_fail $? "Incorrect success to add police action with too high rate"
+
+	tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
+		flower skip_sw \
+		action police rate 1.5kbit burst 1m conform-exceed drop/ok
+	check_err $? "Failed to add police action with low rate"
+
+	tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+
+	tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
+		flower skip_sw \
+		action police rate 1.9tbit burst 1g conform-exceed drop/ok
+	check_err $? "Failed to add police action with high rate"
+
+	tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+
+	tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
+		flower skip_sw \
+		action police rate 1.5kbit burst 512b conform-exceed drop/ok
+	check_fail $? "Incorrect success to add police action with too low burst size"
+
+	tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
+		flower skip_sw \
+		action police rate 1.5kbit burst 2k conform-exceed drop/ok
+	check_err $? "Failed to add police action with low burst size"
+
+	tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+
+	tc qdisc del dev $swp1 clsact
+
+	log_test "police rate and burst limits"
+}
+
+multi_police_test()
+{
+	RET=0
+
+	# It is forbidden in mlxsw driver to have multiple police
+	# actions in a single rule.
+
+	tc qdisc add dev $swp1 clsact
+
+	tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 \
+		flower skip_sw \
+		action police rate 100mbit burst 100k conform-exceed drop/ok
+	check_err $? "Failed to add rule with single police action"
+
+	tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+
+	tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 \
+		flower skip_sw \
+		action police rate 100mbit burst 100k conform-exceed drop/pipe \
+		action police rate 200mbit burst 200k conform-exceed drop/ok
+	check_fail $? "Incorrect success to add rule with two police actions"
+
+	tc qdisc del dev $swp1 clsact
+
+	log_test "multi police"
+}
+
 setup_prepare()
 {
 	swp1=${NETIFS[p1]}
diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
new file mode 100644
index 000000000000..ba1d53b9f815
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
@@ -0,0 +1,786 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+VNI_GEN=$RANDOM
+NSIM_ID=$((RANDOM % 1024))
+NSIM_DEV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_ID
+NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID
+NSIM_NETDEV=
+HAS_ETHTOOL=
+EXIT_STATUS=0
+num_cases=0
+num_errors=0
+
+clean_up_devs=( )
+
+function err_cnt {
+    echo "ERROR:" $@
+    EXIT_STATUS=1
+    ((num_errors++))
+    ((num_cases++))
+}
+
+function pass_cnt {
+    ((num_cases++))
+}
+
+function cleanup_tuns {
+    for dev in "${clean_up_devs[@]}"; do
+	[ -e /sys/class/net/$dev ] && ip link del dev $dev
+    done
+    clean_up_devs=( )
+}
+
+function cleanup_nsim {
+    if [ -e $NSIM_DEV_SYS ]; then
+	echo $NSIM_ID > /sys/bus/netdevsim/del_device
+    fi
+}
+
+function cleanup {
+    cleanup_tuns
+    cleanup_nsim
+}
+
+trap cleanup EXIT
+
+function new_vxlan {
+    local dev=$1
+    local dstport=$2
+    local lower=$3
+    local ipver=$4
+    local flags=$5
+
+    local group ipfl
+
+    [ "$ipver" != '6' ] && group=239.1.1.1 || group=fff1::1
+    [ "$ipver" != '6' ] || ipfl="-6"
+
+    [[ ! "$flags" =~ "external" ]] && flags="$flags id $((VNI_GEN++))"
+
+    ip $ipfl link add $dev type vxlan \
+       group $group \
+       dev $lower \
+       dstport $dstport \
+       $flags
+
+    ip link set dev $dev up
+
+    clean_up_devs=("${clean_up_devs[@]}" $dev)
+
+    check_tables
+}
+
+function new_geneve {
+    local dev=$1
+    local dstport=$2
+    local ipver=$3
+    local flags=$4
+
+    local group ipfl
+
+    [ "$ipver" != '6' ] && remote=1.1.1.2 || group=::2
+    [ "$ipver" != '6' ] || ipfl="-6"
+
+    [[ ! "$flags" =~ "external" ]] && flags="$flags vni $((VNI_GEN++))"
+
+    ip $ipfl link add $dev type geneve \
+       remote $remote  \
+       dstport $dstport \
+       $flags
+
+    ip link set dev $dev up
+
+    clean_up_devs=("${clean_up_devs[@]}" $dev)
+
+    check_tables
+}
+
+function del_dev {
+    local dev=$1
+
+    ip link del dev $dev
+    check_tables
+}
+
+# Helpers for netdevsim port/type encoding
+function mke {
+    local port=$1
+    local type=$2
+
+    echo $((port << 16 | type))
+}
+
+function pre {
+    local val=$1
+
+    echo -e "port: $((val >> 16))\ttype: $((val & 0xffff))"
+}
+
+function pre_ethtool {
+    local val=$1
+    local port=$((val >> 16))
+    local type=$((val & 0xffff))
+
+    case $type in
+	1)
+	    type_name="vxlan"
+	    ;;
+	2)
+	    type_name="geneve"
+	    ;;
+	4)
+	    type_name="vxlan-gpe"
+	    ;;
+	*)
+	    type_name="bit X"
+	    ;;
+    esac
+
+    echo "port $port, $type_name"
+}
+
+function check_table {
+    local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1
+    local -n expected=$2
+    local last=$3
+
+    read -a have < $path
+
+    if [ ${#expected[@]} -ne ${#have[@]} ]; then
+	echo "check_table: BAD NUMBER OF ITEMS"
+	return 0
+    fi
+
+    for i in "${!expected[@]}"; do
+	if [ -n "$HAS_ETHTOOL" -a ${expected[i]} -ne 0 ]; then
+	    pp_expected=`pre_ethtool ${expected[i]}`
+	    ethtool --show-tunnels $NSIM_NETDEV | grep "$pp_expected" >/dev/null
+	    if [ $? -ne 0 -a $last -ne 0 ]; then
+		err_cnt "ethtool table $1 on port $port: $pfx - $msg"
+		echo "       check_table: ethtool does not contain '$pp_expected'"
+		ethtool --show-tunnels $NSIM_NETDEV
+		return 0
+
+	    fi
+	fi
+
+	if [ ${expected[i]} != ${have[i]} ]; then
+	    if [ $last -ne 0 ]; then
+		err_cnt "table $1 on port $port: $pfx - $msg"
+		echo "       check_table: wrong entry $i"
+		echo "       expected: `pre ${expected[i]}`"
+		echo "       have:     `pre ${have[i]}`"
+		return 0
+	    fi
+	    return 1
+	fi
+    done
+
+    pass_cnt
+    return 0
+}
+
+function check_tables {
+    # Need retries in case we have workqueue making the changes
+    local retries=10
+
+    while ! check_table 0 exp0 $((retries == 0)); do
+	sleep 0.02
+	((retries--))
+    done
+    while ! check_table 1 exp1 $((retries == 0)); do
+	sleep 0.02
+	((retries--))
+    done
+}
+
+function print_table {
+    local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1
+    read -a have < $path
+
+    tree $NSIM_DEV_DFS/
+
+    echo "Port $port table $1:"
+
+    for i in "${!have[@]}"; do
+	echo "    `pre ${have[i]}`"
+    done
+
+}
+
+function print_tables {
+    print_table 0
+    print_table 1
+}
+
+function get_netdev_name {
+    local -n old=$1
+
+    new=$(ls /sys/class/net)
+
+    for netdev in $new; do
+	for check in $old; do
+            [ $netdev == $check ] && break
+	done
+
+	if [ $netdev != $check ]; then
+	    echo $netdev
+	    break
+	fi
+    done
+}
+
+###
+### Code start
+###
+
+# Probe ethtool support
+ethtool -h | grep show-tunnels 2>&1 >/dev/null && HAS_ETHTOOL=y
+
+modprobe netdevsim
+
+# Basic test
+pfx="basic"
+
+for port in 0 1; do
+    old_netdevs=$(ls /sys/class/net)
+    if [ $port -eq 0 ]; then
+	echo $NSIM_ID > /sys/bus/netdevsim/new_device
+    else
+	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
+	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
+	echo 1 > $NSIM_DEV_SYS/new_port
+    fi
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
+
+    msg="new NIC device created"
+    exp0=( 0 0 0 0 )
+    exp1=( 0 0 0 0 )
+    check_tables
+
+    msg="VxLAN v4 devices"
+    exp0=( `mke 4789 1` 0 0 0 )
+    new_vxlan vxlan0 4789 $NSIM_NETDEV
+    new_vxlan vxlan1 4789 $NSIM_NETDEV
+
+    msg="VxLAN v4 devices go down"
+    exp0=( 0 0 0 0 )
+    ifconfig vxlan1 down
+    ifconfig vxlan0 down
+    check_tables
+
+    msg="VxLAN v6 devices"
+    exp0=( `mke 4789 1` 0 0 0 )
+    new_vxlan vxlanA 4789 $NSIM_NETDEV 6
+
+    for ifc in vxlan0 vxlan1; do
+	ifconfig $ifc up
+    done
+
+    new_vxlan vxlanB 4789 $NSIM_NETDEV 6
+
+    msg="another VxLAN v6 devices"
+    exp0=( `mke 4789 1` `mke 4790 1` 0 0 )
+    new_vxlan vxlanC 4790 $NSIM_NETDEV 6
+
+    msg="Geneve device"
+    exp1=( `mke 6081 2` 0 0 0 )
+    new_geneve gnv0 6081
+
+    msg="NIC device goes down"
+    ifconfig $NSIM_NETDEV down
+    if [ $port -eq 1 ]; then
+	exp0=( 0 0 0 0 )
+	exp1=( 0 0 0 0 )
+    fi
+    check_tables
+    msg="NIC device goes up again"
+    ifconfig $NSIM_NETDEV up
+    exp0=( `mke 4789 1` `mke 4790 1` 0 0 )
+    exp1=( `mke 6081 2` 0 0 0 )
+    check_tables
+
+    cleanup_tuns
+
+    msg="tunnels destroyed"
+    exp0=( 0 0 0 0 )
+    exp1=( 0 0 0 0 )
+    check_tables
+
+    modprobe -r geneve
+    modprobe -r vxlan
+    modprobe -r udp_tunnel
+
+    check_tables
+done
+
+modprobe -r netdevsim
+
+# Module tests
+pfx="module tests"
+
+if modinfo netdevsim | grep udp_tunnel >/dev/null; then
+    err_cnt "netdevsim depends on udp_tunnel"
+else
+    pass_cnt
+fi
+
+modprobe netdevsim
+
+old_netdevs=$(ls /sys/class/net)
+port=0
+echo $NSIM_ID > /sys/bus/netdevsim/new_device
+echo 0 > $NSIM_DEV_SYS/del_port
+echo 1000 > $NSIM_DEV_DFS/udp_ports_sleep
+echo 0 > $NSIM_DEV_SYS/new_port
+NSIM_NETDEV=`get_netdev_name old_netdevs`
+
+msg="create VxLANs"
+exp0=( 0 0 0 0 ) # sleep is longer than out wait
+new_vxlan vxlan0 10000 $NSIM_NETDEV
+
+modprobe -r vxlan
+modprobe -r udp_tunnel
+
+msg="remove tunnels"
+exp0=( 0 0 0 0 )
+check_tables
+
+msg="create VxLANs"
+exp0=( 0 0 0 0 ) # sleep is longer than out wait
+new_vxlan vxlan0 10000 $NSIM_NETDEV
+
+exp0=( 0 0 0 0 )
+
+modprobe -r netdevsim
+modprobe netdevsim
+
+# Overflow the table
+
+function overflow_table0 {
+    local pfx=$1
+
+    msg="create VxLANs 1/5"
+    exp0=( `mke 10000 1` 0 0 0 )
+    new_vxlan vxlan0 10000 $NSIM_NETDEV
+
+    msg="create VxLANs 2/5"
+    exp0=( `mke 10000 1` `mke 10001 1` 0 0 )
+    new_vxlan vxlan1 10001 $NSIM_NETDEV
+
+    msg="create VxLANs 3/5"
+    exp0=( `mke 10000 1` `mke 10001 1` `mke 10002 1` 0 )
+    new_vxlan vxlan2 10002 $NSIM_NETDEV
+
+    msg="create VxLANs 4/5"
+    exp0=( `mke 10000 1` `mke 10001 1` `mke 10002 1` `mke 10003 1` )
+    new_vxlan vxlan3 10003 $NSIM_NETDEV
+
+    msg="create VxLANs 5/5"
+    new_vxlan vxlan4 10004 $NSIM_NETDEV
+}
+
+function overflow_table1 {
+    local pfx=$1
+
+    msg="create GENEVE 1/5"
+    exp1=( `mke 20000 2` 0 0 0 )
+    new_geneve gnv0 20000
+
+    msg="create GENEVE 2/5"
+    exp1=( `mke 20000 2` `mke 20001 2` 0 0 )
+    new_geneve gnv1 20001
+
+    msg="create GENEVE 3/5"
+    exp1=( `mke 20000 2` `mke 20001 2` `mke 20002 2` 0 )
+    new_geneve gnv2 20002
+
+    msg="create GENEVE 4/5"
+    exp1=( `mke 20000 2` `mke 20001 2` `mke 20002 2` `mke 20003 2` )
+    new_geneve gnv3 20003
+
+    msg="create GENEVE 5/5"
+    new_geneve gnv4 20004
+}
+
+echo $NSIM_ID > /sys/bus/netdevsim/new_device
+echo 0 > $NSIM_DEV_SYS/del_port
+
+for port in 0 1; do
+    if [ $port -ne 0 ]; then
+	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
+	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
+    fi
+
+    echo $port > $NSIM_DEV_SYS/new_port
+    ifconfig $NSIM_NETDEV up
+
+    overflow_table0 "overflow NIC table"
+    overflow_table1 "overflow NIC table"
+
+    msg="replace VxLAN in overflow table"
+    exp0=( `mke 10000 1` `mke 10004 1` `mke 10002 1` `mke 10003 1` )
+    del_dev vxlan1
+
+    msg="vacate VxLAN in overflow table"
+    exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` )
+    del_dev vxlan2
+
+    msg="replace GENEVE in overflow table"
+    exp1=( `mke 20000 2` `mke 20004 2` `mke 20002 2` `mke 20003 2` )
+    del_dev gnv1
+
+    msg="vacate GENEVE in overflow table"
+    exp1=( `mke 20000 2` `mke 20004 2` 0 `mke 20003 2` )
+    del_dev gnv2
+
+    msg="table sharing - share"
+    exp1=( `mke 20000 2` `mke 20004 2` `mke 30001 4` `mke 20003 2` )
+    new_vxlan vxlanG0 30001 $NSIM_NETDEV 4 "gpe external"
+
+    msg="table sharing - overflow"
+    new_vxlan vxlanG1 30002 $NSIM_NETDEV 4 "gpe external"
+    msg="table sharing - overflow v6"
+    new_vxlan vxlanG2 30002 $NSIM_NETDEV 6 "gpe external"
+
+    exp1=( `mke 20000 2` `mke 30002 4` `mke 30001 4` `mke 20003 2` )
+    del_dev gnv4
+
+    msg="destroy NIC"
+    echo $port > $NSIM_DEV_SYS/del_port
+
+    cleanup_tuns
+    exp0=( 0 0 0 0 )
+    exp1=( 0 0 0 0 )
+done
+
+cleanup_nsim
+
+# Sync all
+pfx="sync all"
+
+echo $NSIM_ID > /sys/bus/netdevsim/new_device
+echo 0 > $NSIM_DEV_SYS/del_port
+echo 1 > $NSIM_DEV_DFS/udp_ports_sync_all
+
+for port in 0 1; do
+    if [ $port -ne 0 ]; then
+	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
+	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
+    fi
+
+    echo $port > $NSIM_DEV_SYS/new_port
+    ifconfig $NSIM_NETDEV up
+
+    overflow_table0 "overflow NIC table"
+    overflow_table1 "overflow NIC table"
+
+    msg="replace VxLAN in overflow table"
+    exp0=( `mke 10000 1` `mke 10004 1` `mke 10002 1` `mke 10003 1` )
+    del_dev vxlan1
+
+    msg="vacate VxLAN in overflow table"
+    exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` )
+    del_dev vxlan2
+
+    msg="replace GENEVE in overflow table"
+    exp1=( `mke 20000 2` `mke 20004 2` `mke 20002 2` `mke 20003 2` )
+    del_dev gnv1
+
+    msg="vacate GENEVE in overflow table"
+    exp1=( `mke 20000 2` `mke 20004 2` 0 `mke 20003 2` )
+    del_dev gnv2
+
+    msg="table sharing - share"
+    exp1=( `mke 20000 2` `mke 20004 2` `mke 30001 4` `mke 20003 2` )
+    new_vxlan vxlanG0 30001 $NSIM_NETDEV 4 "gpe external"
+
+    msg="table sharing - overflow"
+    new_vxlan vxlanG1 30002 $NSIM_NETDEV 4 "gpe external"
+    msg="table sharing - overflow v6"
+    new_vxlan vxlanG2 30002 $NSIM_NETDEV 6 "gpe external"
+
+    exp1=( `mke 20000 2` `mke 30002 4` `mke 30001 4` `mke 20003 2` )
+    del_dev gnv4
+
+    msg="destroy NIC"
+    echo $port > $NSIM_DEV_SYS/del_port
+
+    cleanup_tuns
+    exp0=( 0 0 0 0 )
+    exp1=( 0 0 0 0 )
+done
+
+cleanup_nsim
+
+# Destroy full NIC
+pfx="destroy full"
+
+echo $NSIM_ID > /sys/bus/netdevsim/new_device
+echo 0 > $NSIM_DEV_SYS/del_port
+
+for port in 0 1; do
+    if [ $port -ne 0 ]; then
+	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
+	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
+    fi
+
+    echo $port > $NSIM_DEV_SYS/new_port
+    ifconfig $NSIM_NETDEV up
+
+    overflow_table0 "destroy NIC"
+    overflow_table1 "destroy NIC"
+
+    msg="destroy NIC"
+    echo $port > $NSIM_DEV_SYS/del_port
+
+    cleanup_tuns
+    exp0=( 0 0 0 0 )
+    exp1=( 0 0 0 0 )
+done
+
+cleanup_nsim
+
+# IPv4 only
+pfx="IPv4 only"
+
+echo $NSIM_ID > /sys/bus/netdevsim/new_device
+echo 0 > $NSIM_DEV_SYS/del_port
+echo 1 > $NSIM_DEV_DFS/udp_ports_ipv4_only
+
+for port in 0 1; do
+    if [ $port -ne 0 ]; then
+	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
+	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
+    fi
+
+    echo $port > $NSIM_DEV_SYS/new_port
+    ifconfig $NSIM_NETDEV up
+
+    msg="create VxLANs v6"
+    new_vxlan vxlanA0 10000 $NSIM_NETDEV 6
+
+    msg="create VxLANs v6"
+    new_vxlan vxlanA1 10000 $NSIM_NETDEV 6
+
+    ip link set dev vxlanA0 down
+    ip link set dev vxlanA0 up
+    check_tables
+
+    msg="create VxLANs v4"
+    exp0=( `mke 10000 1` 0 0 0 )
+    new_vxlan vxlan0 10000 $NSIM_NETDEV
+
+    msg="down VxLANs v4"
+    exp0=( 0 0 0 0 )
+    ip link set dev vxlan0 down
+    check_tables
+
+    msg="up VxLANs v4"
+    exp0=( `mke 10000 1` 0 0 0 )
+    ip link set dev vxlan0 up
+    check_tables
+
+    msg="destroy VxLANs v4"
+    exp0=( 0 0 0 0 )
+    del_dev vxlan0
+
+    msg="recreate VxLANs v4"
+    exp0=( `mke 10000 1` 0 0 0 )
+    new_vxlan vxlan0 10000 $NSIM_NETDEV
+
+    del_dev vxlanA0
+    del_dev vxlanA1
+
+    msg="destroy NIC"
+    echo $port > $NSIM_DEV_SYS/del_port
+
+    cleanup_tuns
+    exp0=( 0 0 0 0 )
+    exp1=( 0 0 0 0 )
+done
+
+cleanup_nsim
+
+# Failures
+pfx="error injection"
+
+echo $NSIM_ID > /sys/bus/netdevsim/new_device
+echo 0 > $NSIM_DEV_SYS/del_port
+
+for port in 0 1; do
+    if [ $port -ne 0 ]; then
+	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
+	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
+    fi
+
+    echo $port > $NSIM_DEV_SYS/new_port
+    ifconfig $NSIM_NETDEV up
+
+    echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error
+
+    msg="1 - create VxLANs v6"
+    exp0=( 0 0 0 0 )
+    new_vxlan vxlanA0 10000 $NSIM_NETDEV 6
+
+    msg="1 - create VxLANs v4"
+    exp0=( `mke 10000 1` 0 0 0 )
+    new_vxlan vxlan0 10000 $NSIM_NETDEV
+
+    msg="1 - remove VxLANs v4"
+    del_dev vxlan0
+
+    msg="1 - remove VxLANs v6"
+    exp0=( 0 0 0 0 )
+    del_dev vxlanA0
+
+    msg="2 - create GENEVE"
+    exp1=( `mke 20000 2` 0 0 0 )
+    new_geneve gnv0 20000
+
+    msg="2 - destroy GENEVE"
+    echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error
+    exp1=( `mke 20000 2` 0 0 0 )
+    del_dev gnv0
+
+    msg="2 - create second GENEVE"
+    exp1=( 0 `mke 20001 2` 0 0 )
+    new_geneve gnv0 20001
+
+    msg="destroy NIC"
+    echo $port > $NSIM_DEV_SYS/del_port
+
+    cleanup_tuns
+    exp0=( 0 0 0 0 )
+    exp1=( 0 0 0 0 )
+done
+
+cleanup_nsim
+
+# netdev flags
+pfx="netdev flags"
+
+echo $NSIM_ID > /sys/bus/netdevsim/new_device
+echo 0 > $NSIM_DEV_SYS/del_port
+
+for port in 0 1; do
+    if [ $port -ne 0 ]; then
+	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
+	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
+    fi
+
+    echo $port > $NSIM_DEV_SYS/new_port
+    ifconfig $NSIM_NETDEV up
+
+    msg="create VxLANs v6"
+    exp0=( `mke 10000 1` 0 0 0 )
+    new_vxlan vxlanA0 10000 $NSIM_NETDEV 6
+
+    msg="create VxLANs v4"
+    new_vxlan vxlan0 10000 $NSIM_NETDEV
+
+    msg="turn off"
+    exp0=( 0 0 0 0 )
+    ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload off
+    check_tables
+
+    msg="turn on"
+    exp0=( `mke 10000 1` 0 0 0 )
+    ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload on
+    check_tables
+
+    msg="remove both"
+    del_dev vxlanA0
+    exp0=( 0 0 0 0 )
+    del_dev vxlan0
+    check_tables
+
+    ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload off
+
+    msg="create VxLANs v4 - off"
+    exp0=( 0 0 0 0 )
+    new_vxlan vxlan0 10000 $NSIM_NETDEV
+
+    msg="created off - turn on"
+    exp0=( `mke 10000 1` 0 0 0 )
+    ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload on
+    check_tables
+
+    msg="destroy NIC"
+    echo $port > $NSIM_DEV_SYS/del_port
+
+    cleanup_tuns
+    exp0=( 0 0 0 0 )
+    exp1=( 0 0 0 0 )
+done
+
+cleanup_nsim
+
+# device initiated reset
+pfx="reset notification"
+
+echo $NSIM_ID > /sys/bus/netdevsim/new_device
+echo 0 > $NSIM_DEV_SYS/del_port
+
+for port in 0 1; do
+    if [ $port -ne 0 ]; then
+	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
+	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
+    fi
+
+    echo $port > $NSIM_DEV_SYS/new_port
+    ifconfig $NSIM_NETDEV up
+
+    msg="create VxLANs v6"
+    exp0=( `mke 10000 1` 0 0 0 )
+    new_vxlan vxlanA0 10000 $NSIM_NETDEV 6
+
+    msg="create VxLANs v4"
+    new_vxlan vxlan0 10000 $NSIM_NETDEV
+
+    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+    check_tables
+
+    msg="NIC device goes down"
+    ifconfig $NSIM_NETDEV down
+    if [ $port -eq 1 ]; then
+	exp0=( 0 0 0 0 )
+	exp1=( 0 0 0 0 )
+    fi
+    check_tables
+
+    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+    check_tables
+
+    msg="NIC device goes up again"
+    ifconfig $NSIM_NETDEV up
+    exp0=( `mke 10000 1` 0 0 0 )
+    check_tables
+
+    msg="remove both"
+    del_dev vxlanA0
+    exp0=( 0 0 0 0 )
+    del_dev vxlan0
+    check_tables
+
+    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+    check_tables
+
+    msg="destroy NIC"
+    echo $port > $NSIM_DEV_SYS/del_port
+
+    cleanup_tuns
+    exp0=( 0 0 0 0 )
+    exp1=( 0 0 0 0 )
+done
+
+modprobe -r netdevsim
+
+if [ $num_errors -eq 0 ]; then
+    echo "PASSED all $num_cases checks"
+else
+    echo "FAILED $num_errors/$num_cases checks"
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore
index 94b02a18f230..344a99c6da1b 100644
--- a/tools/testing/selftests/exec/.gitignore
+++ b/tools/testing/selftests/exec/.gitignore
@@ -10,3 +10,4 @@ execveat.denatured
 /recursion-depth
 xxxxxxxx*
 pipe
+S_I*.test
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index 4453b8f8def3..0a13b110c1e6 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -3,7 +3,7 @@ CFLAGS = -Wall
 CFLAGS += -Wno-nonnull
 CFLAGS += -D_GNU_SOURCE
 
-TEST_PROGS := binfmt_script
+TEST_PROGS := binfmt_script non-regular
 TEST_GEN_PROGS := execveat
 TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir pipe
 # Makefile is a run-time dependency, since it's accessed by the execveat test
@@ -11,7 +11,8 @@ TEST_FILES := Makefile
 
 TEST_GEN_PROGS += recursion-depth
 
-EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx*
+EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx*	\
+	       $(OUTPUT)/S_I*.test
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/exec/non-regular.c b/tools/testing/selftests/exec/non-regular.c
new file mode 100644
index 000000000000..cd3a34aca93e
--- /dev/null
+++ b/tools/testing/selftests/exec/non-regular.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/sysmacros.h>
+#include <sys/types.h>
+
+#include "../kselftest_harness.h"
+
+/* Remove a file, ignoring the result if it didn't exist. */
+void rm(struct __test_metadata *_metadata, const char *pathname,
+	int is_dir)
+{
+	int rc;
+
+	if (is_dir)
+		rc = rmdir(pathname);
+	else
+		rc = unlink(pathname);
+
+	if (rc < 0) {
+		ASSERT_EQ(errno, ENOENT) {
+			TH_LOG("Not ENOENT: %s", pathname);
+		}
+	} else {
+		ASSERT_EQ(rc, 0) {
+			TH_LOG("Failed to remove: %s", pathname);
+		}
+	}
+}
+
+FIXTURE(file) {
+	char *pathname;
+	int is_dir;
+};
+
+FIXTURE_VARIANT(file)
+{
+	const char *name;
+	int expected;
+	int is_dir;
+	void (*setup)(struct __test_metadata *_metadata,
+		      FIXTURE_DATA(file) *self,
+		      const FIXTURE_VARIANT(file) *variant);
+	int major, minor, mode; /* for mknod() */
+};
+
+void setup_link(struct __test_metadata *_metadata,
+		FIXTURE_DATA(file) *self,
+		const FIXTURE_VARIANT(file) *variant)
+{
+	const char * const paths[] = {
+		"/bin/true",
+		"/usr/bin/true",
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(paths); i++) {
+		if (access(paths[i], X_OK) == 0) {
+			ASSERT_EQ(symlink(paths[i], self->pathname), 0);
+			return;
+		}
+	}
+	ASSERT_EQ(1, 0) {
+		TH_LOG("Could not find viable 'true' binary");
+	}
+}
+
+FIXTURE_VARIANT_ADD(file, S_IFLNK)
+{
+	.name = "S_IFLNK",
+	.expected = ELOOP,
+	.setup = setup_link,
+};
+
+void setup_dir(struct __test_metadata *_metadata,
+	       FIXTURE_DATA(file) *self,
+	       const FIXTURE_VARIANT(file) *variant)
+{
+	ASSERT_EQ(mkdir(self->pathname, 0755), 0);
+}
+
+FIXTURE_VARIANT_ADD(file, S_IFDIR)
+{
+	.name = "S_IFDIR",
+	.is_dir = 1,
+	.expected = EACCES,
+	.setup = setup_dir,
+};
+
+void setup_node(struct __test_metadata *_metadata,
+		FIXTURE_DATA(file) *self,
+		const FIXTURE_VARIANT(file) *variant)
+{
+	dev_t dev;
+	int rc;
+
+	dev = makedev(variant->major, variant->minor);
+	rc = mknod(self->pathname, 0755 | variant->mode, dev);
+	ASSERT_EQ(rc, 0) {
+		if (errno == EPERM)
+			SKIP(return, "Please run as root; cannot mknod(%s)",
+				variant->name);
+	}
+}
+
+FIXTURE_VARIANT_ADD(file, S_IFBLK)
+{
+	.name = "S_IFBLK",
+	.expected = EACCES,
+	.setup = setup_node,
+	/* /dev/loop0 */
+	.major = 7,
+	.minor = 0,
+	.mode = S_IFBLK,
+};
+
+FIXTURE_VARIANT_ADD(file, S_IFCHR)
+{
+	.name = "S_IFCHR",
+	.expected = EACCES,
+	.setup = setup_node,
+	/* /dev/zero */
+	.major = 1,
+	.minor = 5,
+	.mode = S_IFCHR,
+};
+
+void setup_fifo(struct __test_metadata *_metadata,
+		FIXTURE_DATA(file) *self,
+		const FIXTURE_VARIANT(file) *variant)
+{
+	ASSERT_EQ(mkfifo(self->pathname, 0755), 0);
+}
+
+FIXTURE_VARIANT_ADD(file, S_IFIFO)
+{
+	.name = "S_IFIFO",
+	.expected = EACCES,
+	.setup = setup_fifo,
+};
+
+FIXTURE_SETUP(file)
+{
+	ASSERT_GT(asprintf(&self->pathname, "%s.test", variant->name), 6);
+	self->is_dir = variant->is_dir;
+
+	rm(_metadata, self->pathname, variant->is_dir);
+	variant->setup(_metadata, self, variant);
+}
+
+FIXTURE_TEARDOWN(file)
+{
+	rm(_metadata, self->pathname, self->is_dir);
+}
+
+TEST_F(file, exec_errno)
+{
+	char * const argv[2] = { (char * const)self->pathname, NULL };
+
+	EXPECT_LT(execv(argv[0], argv), 0);
+	EXPECT_EQ(errno, variant->expected);
+}
+
+/* S_IFSOCK */
+FIXTURE(sock)
+{
+	int fd;
+};
+
+FIXTURE_SETUP(sock)
+{
+	self->fd = socket(AF_INET, SOCK_STREAM, 0);
+	ASSERT_GE(self->fd, 0);
+}
+
+FIXTURE_TEARDOWN(sock)
+{
+	if (self->fd >= 0)
+		ASSERT_EQ(close(self->fd), 0);
+}
+
+TEST_F(sock, exec_errno)
+{
+	char * const argv[2] = { " magic socket ", NULL };
+	char * const envp[1] = { NULL };
+
+	EXPECT_LT(fexecve(self->fd, argv, envp), 0);
+	EXPECT_EQ(errno, EACCES);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
index 8a6b507e34a8..1d27f52c61e6 100644
--- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
+++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
@@ -21,7 +21,6 @@
 #include <linux/android/binder.h>
 #include <linux/android/binderfs.h>
 
-#include "../../kselftest.h"
 #include "../../kselftest_harness.h"
 
 #define DEFAULT_THREADS 4
@@ -37,37 +36,26 @@
 		fd = -EBADF;        \
 	}
 
-#define log_exit(format, ...)                                                  \
-	({                                                                     \
-		fprintf(stderr, format "\n", ##__VA_ARGS__);                   \
-		exit(EXIT_FAILURE);                                            \
-	})
-
-static void change_mountns(void)
+static void change_mountns(struct __test_metadata *_metadata)
 {
 	int ret;
 
 	ret = unshare(CLONE_NEWNS);
-	if (ret < 0)
-		ksft_exit_fail_msg("%s - Failed to unshare mount namespace\n",
-				   strerror(errno));
+	ASSERT_EQ(ret, 0) {
+		TH_LOG("%s - Failed to unshare mount namespace",
+			strerror(errno));
+	}
 
 	ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0);
-	if (ret < 0)
-		ksft_exit_fail_msg("%s - Failed to mount / as private\n",
-				   strerror(errno));
-}
-
-static void rmdir_protect_errno(const char *dir)
-{
-	int saved_errno = errno;
-	(void)rmdir(dir);
-	errno = saved_errno;
+	ASSERT_EQ(ret, 0) {
+		TH_LOG("%s - Failed to mount / as private",
+			strerror(errno));
+	}
 }
 
-static int __do_binderfs_test(void)
+static int __do_binderfs_test(struct __test_metadata *_metadata)
 {
-	int fd, ret, saved_errno;
+	int fd, ret, saved_errno, result = 1;
 	size_t len;
 	ssize_t wret;
 	struct binderfs_device device = { 0 };
@@ -75,113 +63,107 @@ static int __do_binderfs_test(void)
 	char binderfs_mntpt[] = P_tmpdir "/binderfs_XXXXXX",
 		device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME];
 
-	change_mountns();
+	change_mountns(_metadata);
 
-	if (!mkdtemp(binderfs_mntpt))
-		ksft_exit_fail_msg(
-			"%s - Failed to create binderfs mountpoint\n",
+	EXPECT_NE(mkdtemp(binderfs_mntpt), NULL) {
+		TH_LOG("%s - Failed to create binderfs mountpoint",
 			strerror(errno));
+		goto out;
+	}
 
 	ret = mount(NULL, binderfs_mntpt, "binder", 0, 0);
-	if (ret < 0) {
-		if (errno != ENODEV)
-			ksft_exit_fail_msg("%s - Failed to mount binderfs\n",
-					   strerror(errno));
-
-		rmdir_protect_errno(binderfs_mntpt);
-		return 1;
+	EXPECT_EQ(ret, 0) {
+		if (errno == ENODEV)
+			XFAIL(goto out, "binderfs missing");
+		TH_LOG("%s - Failed to mount binderfs", strerror(errno));
+		goto rmdir;
 	}
 
-	/* binderfs mount test passed */
-	ksft_inc_pass_cnt();
+	/* success: binderfs mounted */
 
 	memcpy(device.name, "my-binder", strlen("my-binder"));
 
 	snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt);
 	fd = open(device_path, O_RDONLY | O_CLOEXEC);
-	if (fd < 0)
-		ksft_exit_fail_msg(
-			"%s - Failed to open binder-control device\n",
+	EXPECT_GE(fd, 0) {
+		TH_LOG("%s - Failed to open binder-control device",
 			strerror(errno));
+		goto umount;
+	}
 
 	ret = ioctl(fd, BINDER_CTL_ADD, &device);
 	saved_errno = errno;
 	close(fd);
 	errno = saved_errno;
-	if (ret < 0) {
-		rmdir_protect_errno(binderfs_mntpt);
-		ksft_exit_fail_msg(
-			"%s - Failed to allocate new binder device\n",
+	EXPECT_GE(ret, 0) {
+		TH_LOG("%s - Failed to allocate new binder device",
 			strerror(errno));
+		goto umount;
 	}
 
-	ksft_print_msg(
-		"Allocated new binder device with major %d, minor %d, and name %s\n",
+	TH_LOG("Allocated new binder device with major %d, minor %d, and name %s",
 		device.major, device.minor, device.name);
 
-	/* binder device allocation test passed */
-	ksft_inc_pass_cnt();
+	/* success: binder device allocation */
 
 	snprintf(device_path, sizeof(device_path), "%s/my-binder", binderfs_mntpt);
 	fd = open(device_path, O_CLOEXEC | O_RDONLY);
-	if (fd < 0) {
-		rmdir_protect_errno(binderfs_mntpt);
-		ksft_exit_fail_msg("%s - Failed to open my-binder device\n",
-				   strerror(errno));
+	EXPECT_GE(fd, 0) {
+		TH_LOG("%s - Failed to open my-binder device",
+			strerror(errno));
+		goto umount;
 	}
 
 	ret = ioctl(fd, BINDER_VERSION, &version);
 	saved_errno = errno;
 	close(fd);
 	errno = saved_errno;
-	if (ret < 0) {
-		rmdir_protect_errno(binderfs_mntpt);
-		ksft_exit_fail_msg(
-			"%s - Failed to open perform BINDER_VERSION request\n",
+	EXPECT_GE(ret, 0) {
+		TH_LOG("%s - Failed to open perform BINDER_VERSION request",
 			strerror(errno));
+		goto umount;
 	}
 
-	ksft_print_msg("Detected binder version: %d\n",
-		       version.protocol_version);
+	TH_LOG("Detected binder version: %d", version.protocol_version);
 
-	/* binder transaction with binderfs binder device passed */
-	ksft_inc_pass_cnt();
+	/* success: binder transaction with binderfs binder device */
 
 	ret = unlink(device_path);
-	if (ret < 0) {
-		rmdir_protect_errno(binderfs_mntpt);
-		ksft_exit_fail_msg("%s - Failed to delete binder device\n",
-				   strerror(errno));
+	EXPECT_EQ(ret, 0) {
+		TH_LOG("%s - Failed to delete binder device",
+			strerror(errno));
+		goto umount;
 	}
 
-	/* binder device removal passed */
-	ksft_inc_pass_cnt();
+	/* success: binder device removal */
 
 	snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt);
 	ret = unlink(device_path);
-	if (!ret) {
-		rmdir_protect_errno(binderfs_mntpt);
-		ksft_exit_fail_msg("Managed to delete binder-control device\n");
-	} else if (errno != EPERM) {
-		rmdir_protect_errno(binderfs_mntpt);
-		ksft_exit_fail_msg(
-			"%s - Failed to delete binder-control device but exited with unexpected error code\n",
+	EXPECT_NE(ret, 0) {
+		TH_LOG("Managed to delete binder-control device");
+		goto umount;
+	}
+	EXPECT_EQ(errno, EPERM) {
+		TH_LOG("%s - Failed to delete binder-control device but exited with unexpected error code",
 			strerror(errno));
+		goto umount;
 	}
 
-	/* binder-control device removal failed as expected */
-	ksft_inc_xfail_cnt();
+	/* success: binder-control device removal failed as expected */
+	result = 0;
 
-on_error:
+umount:
 	ret = umount2(binderfs_mntpt, MNT_DETACH);
-	rmdir_protect_errno(binderfs_mntpt);
-	if (ret < 0)
-		ksft_exit_fail_msg("%s - Failed to unmount binderfs\n",
-				   strerror(errno));
-
-	/* binderfs unmount test passed */
-	ksft_inc_pass_cnt();
-	return 0;
+	EXPECT_EQ(ret, 0) {
+		TH_LOG("%s - Failed to unmount binderfs", strerror(errno));
+	}
+rmdir:
+	ret = rmdir(binderfs_mntpt);
+	EXPECT_EQ(ret, 0) {
+		TH_LOG("%s - Failed to rmdir binderfs mount", strerror(errno));
+	}
+out:
+	return result;
 }
 
 static int wait_for_pid(pid_t pid)
@@ -291,7 +273,7 @@ static int write_id_mapping(enum idmap_type type, pid_t pid, const char *buf,
 	return 0;
 }
 
-static void change_userns(int syncfds[2])
+static void change_userns(struct __test_metadata *_metadata, int syncfds[2])
 {
 	int ret;
 	char buf;
@@ -299,25 +281,29 @@ static void change_userns(int syncfds[2])
 	close_prot_errno_disarm(syncfds[1]);
 
 	ret = unshare(CLONE_NEWUSER);
-	if (ret < 0)
-		ksft_exit_fail_msg("%s - Failed to unshare user namespace\n",
-				   strerror(errno));
+	ASSERT_EQ(ret, 0) {
+		TH_LOG("%s - Failed to unshare user namespace",
+			strerror(errno));
+	}
 
 	ret = write_nointr(syncfds[0], "1", 1);
-	if (ret != 1)
-		ksft_exit_fail_msg("write_nointr() failed\n");
+	ASSERT_EQ(ret, 1) {
+		TH_LOG("write_nointr() failed");
+	}
 
 	ret = read_nointr(syncfds[0], &buf, 1);
-	if (ret != 1)
-		ksft_exit_fail_msg("read_nointr() failed\n");
+	ASSERT_EQ(ret, 1) {
+		TH_LOG("read_nointr() failed");
+	}
 
 	close_prot_errno_disarm(syncfds[0]);
 
-	if (setid_userns_root())
-		ksft_exit_fail_msg("setid_userns_root() failed");
+	ASSERT_EQ(setid_userns_root(), 0) {
+		TH_LOG("setid_userns_root() failed");
+	}
 }
 
-static void change_idmaps(int syncfds[2], pid_t pid)
+static void change_idmaps(struct __test_metadata *_metadata, int syncfds[2], pid_t pid)
 {
 	int ret;
 	char buf;
@@ -326,35 +312,42 @@ static void change_idmaps(int syncfds[2], pid_t pid)
 	close_prot_errno_disarm(syncfds[0]);
 
 	ret = read_nointr(syncfds[1], &buf, 1);
-	if (ret != 1)
-		ksft_exit_fail_msg("read_nointr() failed\n");
+	ASSERT_EQ(ret, 1) {
+		TH_LOG("read_nointr() failed");
+	}
 
 	snprintf(id_map, sizeof(id_map), "0 %d 1\n", getuid());
 	ret = write_id_mapping(UID_MAP, pid, id_map, strlen(id_map));
-	if (ret)
-		ksft_exit_fail_msg("write_id_mapping(UID_MAP) failed");
+	ASSERT_EQ(ret, 0) {
+		TH_LOG("write_id_mapping(UID_MAP) failed");
+	}
 
 	snprintf(id_map, sizeof(id_map), "0 %d 1\n", getgid());
 	ret = write_id_mapping(GID_MAP, pid, id_map, strlen(id_map));
-	if (ret)
-		ksft_exit_fail_msg("write_id_mapping(GID_MAP) failed");
+	ASSERT_EQ(ret, 0) {
+		TH_LOG("write_id_mapping(GID_MAP) failed");
+	}
 
 	ret = write_nointr(syncfds[1], "1", 1);
-	if (ret != 1)
-		ksft_exit_fail_msg("write_nointr() failed");
+	ASSERT_EQ(ret, 1) {
+		TH_LOG("write_nointr() failed");
+	}
 
 	close_prot_errno_disarm(syncfds[1]);
 }
 
+struct __test_metadata *_thread_metadata;
 static void *binder_version_thread(void *data)
 {
+	struct __test_metadata *_metadata = _thread_metadata;
 	int fd = PTR_TO_INT(data);
 	struct binder_version version = { 0 };
 	int ret;
 
 	ret = ioctl(fd, BINDER_VERSION, &version);
 	if (ret < 0)
-		ksft_print_msg("%s - Failed to open perform BINDER_VERSION request\n", strerror(errno));
+		TH_LOG("%s - Failed to open perform BINDER_VERSION request\n",
+			strerror(errno));
 
 	pthread_exit(data);
 }
@@ -377,68 +370,79 @@ TEST(binderfs_stress)
 		device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME];
 
 	ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds);
-	if (ret < 0)
-		ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno));
+	ASSERT_EQ(ret, 0) {
+		TH_LOG("%s - Failed to create socket pair", strerror(errno));
+	}
 
 	pid = fork();
-	if (pid < 0) {
+	ASSERT_GE(pid, 0) {
+		TH_LOG("%s - Failed to fork", strerror(errno));
 		close_prot_errno_disarm(syncfds[0]);
 		close_prot_errno_disarm(syncfds[1]);
-		ksft_exit_fail_msg("%s - Failed to fork", strerror(errno));
 	}
 
 	if (pid == 0) {
 		int i, j, k, nthreads;
 		pthread_attr_t attr;
 		pthread_t threads[DEFAULT_THREADS];
-		change_userns(syncfds);
-		change_mountns();
+		change_userns(_metadata, syncfds);
+		change_mountns(_metadata);
 
-		if (!mkdtemp(binderfs_mntpt))
-			log_exit("%s - Failed to create binderfs mountpoint\n",
-				 strerror(errno));
+		ASSERT_NE(mkdtemp(binderfs_mntpt), NULL) {
+			TH_LOG("%s - Failed to create binderfs mountpoint",
+				strerror(errno));
+		}
 
 		ret = mount(NULL, binderfs_mntpt, "binder", 0, 0);
-		if (ret < 0)
-			log_exit("%s - Failed to mount binderfs\n", strerror(errno));
+		ASSERT_EQ(ret, 0) {
+			TH_LOG("%s - Failed to mount binderfs", strerror(errno));
+		}
 
 		for (int i = 0; i < ARRAY_SIZE(fds); i++) {
 
 			snprintf(device_path, sizeof(device_path),
 				 "%s/binder-control", binderfs_mntpt);
 			fd = open(device_path, O_RDONLY | O_CLOEXEC);
-			if (fd < 0)
-				log_exit("%s - Failed to open binder-control device\n", strerror(errno));
+			ASSERT_GE(fd, 0) {
+				TH_LOG("%s - Failed to open binder-control device",
+					strerror(errno));
+			}
 
 			memset(&device, 0, sizeof(device));
 			snprintf(device.name, sizeof(device.name), "%d", i);
 			ret = ioctl(fd, BINDER_CTL_ADD, &device);
 			close_prot_errno_disarm(fd);
-			if (ret < 0)
-				log_exit("%s - Failed to allocate new binder device\n", strerror(errno));
+			ASSERT_EQ(ret, 0) {
+				TH_LOG("%s - Failed to allocate new binder device",
+					strerror(errno));
+			}
 
 			snprintf(device_path, sizeof(device_path), "%s/%d",
 				 binderfs_mntpt, i);
 			fds[i] = open(device_path, O_RDONLY | O_CLOEXEC);
-			if (fds[i] < 0)
-				log_exit("%s - Failed to open binder device\n", strerror(errno));
+			ASSERT_GE(fds[i], 0) {
+				TH_LOG("%s - Failed to open binder device", strerror(errno));
+			}
 		}
 
 		ret = umount2(binderfs_mntpt, MNT_DETACH);
-		rmdir_protect_errno(binderfs_mntpt);
-		if (ret < 0)
-			log_exit("%s - Failed to unmount binderfs\n", strerror(errno));
+		ASSERT_EQ(ret, 0) {
+			TH_LOG("%s - Failed to unmount binderfs", strerror(errno));
+			rmdir(binderfs_mntpt);
+		}
 
 		nthreads = get_nprocs_conf();
 		if (nthreads > DEFAULT_THREADS)
 			nthreads = DEFAULT_THREADS;
 
+		_thread_metadata = _metadata;
 		pthread_attr_init(&attr);
 		for (k = 0; k < ARRAY_SIZE(fds); k++) {
 			for (i = 0; i < nthreads; i++) {
 				ret = pthread_create(&threads[i], &attr, binder_version_thread, INT_TO_PTR(fds[k]));
 				if (ret) {
-					ksft_print_msg("%s - Failed to create thread %d\n", strerror(errno), i);
+					TH_LOG("%s - Failed to create thread %d",
+						strerror(errno), i);
 					break;
 				}
 			}
@@ -448,7 +452,8 @@ TEST(binderfs_stress)
 
 				ret = pthread_join(threads[j], &fdptr);
 				if (ret)
-					ksft_print_msg("%s - Failed to join thread %d for fd %d\n", strerror(errno), j, PTR_TO_INT(fdptr));
+					TH_LOG("%s - Failed to join thread %d for fd %d",
+						strerror(errno), j, PTR_TO_INT(fdptr));
 			}
 		}
 		pthread_attr_destroy(&attr);
@@ -459,11 +464,12 @@ TEST(binderfs_stress)
 		exit(EXIT_SUCCESS);
 	}
 
-	change_idmaps(syncfds, pid);
+	change_idmaps(_metadata, syncfds, pid);
 
 	ret = wait_for_pid(pid);
-	if (ret)
-		ksft_exit_fail_msg("wait_for_pid() failed");
+	ASSERT_EQ(ret, 0) {
+		TH_LOG("wait_for_pid() failed");
+	}
 }
 
 TEST(binderfs_test_privileged)
@@ -471,7 +477,7 @@ TEST(binderfs_test_privileged)
 	if (geteuid() != 0)
 		XFAIL(return, "Tests are not run as root. Skipping privileged tests");
 
-	if (__do_binderfs_test() == 1)
+	if (__do_binderfs_test(_metadata))
 		XFAIL(return, "The Android binderfs filesystem is not available");
 }
 
@@ -482,31 +488,33 @@ TEST(binderfs_test_unprivileged)
 	pid_t pid;
 
 	ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds);
-	if (ret < 0)
-		ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno));
+	ASSERT_EQ(ret, 0) {
+		TH_LOG("%s - Failed to create socket pair", strerror(errno));
+	}
 
 	pid = fork();
-	if (pid < 0) {
+	ASSERT_GE(pid, 0) {
 		close_prot_errno_disarm(syncfds[0]);
 		close_prot_errno_disarm(syncfds[1]);
-		ksft_exit_fail_msg("%s - Failed to fork", strerror(errno));
+		TH_LOG("%s - Failed to fork", strerror(errno));
 	}
 
 	if (pid == 0) {
-		change_userns(syncfds);
-		if (__do_binderfs_test() == 1)
+		change_userns(_metadata, syncfds);
+		if (__do_binderfs_test(_metadata))
 			exit(2);
 		exit(EXIT_SUCCESS);
 	}
 
-	change_idmaps(syncfds, pid);
+	change_idmaps(_metadata, syncfds, pid);
 
 	ret = wait_for_pid(pid);
 	if (ret) {
 		if (ret == 2)
 			XFAIL(return, "The Android binderfs filesystem is not available");
-		else
-			ksft_exit_fail_msg("wait_for_pid() failed");
+		ASSERT_EQ(ret, 0) {
+			TH_LOG("wait_for_pid() failed");
+		}
 	}
 }
 
diff --git a/tools/testing/selftests/firmware/settings b/tools/testing/selftests/firmware/settings
new file mode 100644
index 000000000000..085e664ee093
--- /dev/null
+++ b/tools/testing/selftests/firmware/settings
@@ -0,0 +1,8 @@
+# The async firmware timeout is set to 1 second (but ends up being effectively
+# 2 seconds). There are 3 test configs, each done with and without firmware
+# present, each with 2 "nowait" functions tested 5 times. Expected time for a
+# normal execution should be 2 * 3 * 2 * 2 * 5 = 120 seconds for those alone.
+# Additionally, fw_fallback may take 5 seconds for internal timeouts in each
+# of the 3 configs, so at least another 15 seconds are needed. Add another
+# 10 seconds for each testing config: 120 + 15 + 30
+timeout=165
diff --git a/tools/testing/selftests/fpu/.gitignore b/tools/testing/selftests/fpu/.gitignore
new file mode 100644
index 000000000000..d6d12ac1d9c3
--- /dev/null
+++ b/tools/testing/selftests/fpu/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0+
+test_fpu
diff --git a/tools/testing/selftests/fpu/Makefile b/tools/testing/selftests/fpu/Makefile
new file mode 100644
index 000000000000..ea62c176ede7
--- /dev/null
+++ b/tools/testing/selftests/fpu/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0+
+
+LDLIBS := -lm
+
+TEST_GEN_PROGS := test_fpu
+
+TEST_PROGS := run_test_fpu.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/fpu/run_test_fpu.sh b/tools/testing/selftests/fpu/run_test_fpu.sh
new file mode 100755
index 000000000000..d77be93ec139
--- /dev/null
+++ b/tools/testing/selftests/fpu/run_test_fpu.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Load kernel module for FPU tests
+
+uid=$(id -u)
+if [ $uid -ne 0 ]; then
+	echo "$0: Must be run as root"
+	exit 1
+fi
+
+if ! which modprobe > /dev/null 2>&1; then
+	echo "$0: You need modprobe installed"
+        exit 4
+fi
+
+if ! modinfo test_fpu > /dev/null 2>&1; then
+	echo "$0: You must have the following enabled in your kernel:"
+	echo "CONFIG_TEST_FPU=m"
+	exit 4
+fi
+
+NR_CPUS=$(getconf _NPROCESSORS_ONLN)
+if [ ! $NR_CPUS ]; then
+	NR_CPUS=1
+fi
+
+modprobe test_fpu
+
+if [ ! -e /sys/kernel/debug/selftest_helpers/test_fpu ]; then
+	mount -t debugfs none /sys/kernel/debug
+
+	if [ ! -e /sys/kernel/debug/selftest_helpers/test_fpu ]; then
+		echo "$0: Error mounting debugfs"
+		exit 4
+	fi
+fi
+
+echo "Running 1000 iterations on all CPUs... "
+for i in $(seq 1 1000); do
+	for c in $(seq 1 $NR_CPUS); do
+		./test_fpu &
+	done
+done
+
+rmmod test_fpu
diff --git a/tools/testing/selftests/fpu/test_fpu.c b/tools/testing/selftests/fpu/test_fpu.c
new file mode 100644
index 000000000000..200238522a9d
--- /dev/null
+++ b/tools/testing/selftests/fpu/test_fpu.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* This testcase operates with the test_fpu kernel driver.
+ * It modifies the FPU control register in user mode and calls the kernel
+ * module to perform floating point operations in the kernel. The control
+ * register value should be independent between kernel and user mode.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <fenv.h>
+#include <unistd.h>
+#include <fcntl.h>
+
+const char *test_fpu_path = "/sys/kernel/debug/selftest_helpers/test_fpu";
+
+int main(void)
+{
+	char dummy[1];
+	int fd = open(test_fpu_path, O_RDONLY);
+
+	if (fd < 0) {
+		printf("[SKIP]\tcan't access %s: %s\n",
+		       test_fpu_path, strerror(errno));
+		return 0;
+	}
+
+	if (read(fd, dummy, 1) < 0) {
+		printf("[FAIL]\taccess with default rounding mode failed\n");
+		return 1;
+	}
+
+	fesetround(FE_DOWNWARD);
+	if (read(fd, dummy, 1) < 0) {
+		printf("[FAIL]\taccess with downward rounding mode failed\n");
+		return 2;
+	}
+	if (fegetround() != FE_DOWNWARD) {
+		printf("[FAIL]\tusermode rounding mode clobbered\n");
+		return 3;
+	}
+
+	/* Note: the tests up to this point are quite safe and will only return
+	 * an error. But the exception mask setting can cause misbehaving kernel
+	 * to crash.
+	 */
+	feclearexcept(FE_ALL_EXCEPT);
+	feenableexcept(FE_ALL_EXCEPT);
+	if (read(fd, dummy, 1) < 0) {
+		printf("[FAIL]\taccess with fpu exceptions unmasked failed\n");
+		return 4;
+	}
+	if (fegetexcept() != FE_ALL_EXCEPT) {
+		printf("[FAIL]\tusermode fpu exception mask clobbered\n");
+		return 5;
+	}
+
+	printf("[OK]\ttest_fpu\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh
index c82aa77958e5..afd42387e8b2 100755
--- a/tools/testing/selftests/kmod/kmod.sh
+++ b/tools/testing/selftests/kmod/kmod.sh
@@ -130,7 +130,7 @@ test_reqs()
 	if [[ $KMOD_VERSION  -le 19 ]]; then
 		echo "$0: You need at least kmod 20" >&2
 		echo "kmod <= 19 is buggy, for details see:" >&2
-		echo "http://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2
+		echo "https://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2
 		exit $ksft_skip
 	fi
 
@@ -343,7 +343,7 @@ kmod_test_0001_driver()
 
 	kmod_defaults_driver
 	config_num_threads 1
-	printf '\000' >"$DIR"/config_test_driver
+	printf $NAME >"$DIR"/config_test_driver
 	config_trigger ${FUNCNAME[0]}
 	config_expect_result ${FUNCNAME[0]} MODULE_NOT_FOUND
 }
@@ -354,7 +354,7 @@ kmod_test_0001_fs()
 
 	kmod_defaults_fs
 	config_num_threads 1
-	printf '\000' >"$DIR"/config_test_fs
+	printf $NAME >"$DIR"/config_test_fs
 	config_trigger ${FUNCNAME[0]}
 	config_expect_result ${FUNCNAME[0]} -EINVAL
 }
diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index 862eee734553..8d50483fe204 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -1,11 +1,43 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * kselftest.h:	kselftest framework return codes to include from
- *		selftests.
+ * kselftest.h:	low-level kselftest framework to include from
+ *		selftest programs. When possible, please use
+ *		kselftest_harness.h instead.
  *
  * Copyright (c) 2014 Shuah Khan <shuahkh@osg.samsung.com>
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
  *
+ * Using this API consists of first counting how many tests your code
+ * has to run, and then starting up the reporting:
+ *
+ *     ksft_print_header();
+ *     ksft_set_plan(total_number_of_tests);
+ *
+ * For each test, report any progress, debugging, etc with:
+ *
+ *     ksft_print_msg(fmt, ...);
+ *
+ * and finally report the pass/fail/skip/xfail state of the test with one of:
+ *
+ *     ksft_test_result(condition, fmt, ...);
+ *     ksft_test_result_pass(fmt, ...);
+ *     ksft_test_result_fail(fmt, ...);
+ *     ksft_test_result_skip(fmt, ...);
+ *     ksft_test_result_xfail(fmt, ...);
+ *     ksft_test_result_error(fmt, ...);
+ *
+ * When all tests are finished, clean up and exit the program with one of:
+ *
+ *    ksft_exit(condition);
+ *    ksft_exit_pass();
+ *    ksft_exit_fail();
+ *
+ * If the program wants to report details on why the entire program has
+ * failed, it can instead exit with a message (this is usually done when
+ * the program is aborting before finishing all tests):
+ *
+ *    ksft_exit_fail_msg(fmt, ...);
+ *
  */
 #ifndef __KSELFTEST_H
 #define __KSELFTEST_H
@@ -74,7 +106,7 @@ static inline void ksft_print_cnts(void)
 	if (ksft_plan != ksft_test_num())
 		printf("# Planned tests != run tests (%u != %u)\n",
 			ksft_plan, ksft_test_num());
-	printf("# Pass %d Fail %d Xfail %d Xpass %d Skip %d Error %d\n",
+	printf("# Totals: pass:%d fail:%d xfail:%d xpass:%d skip:%d error:%d\n",
 		ksft_cnt.ksft_pass, ksft_cnt.ksft_fail,
 		ksft_cnt.ksft_xfail, ksft_cnt.ksft_xpass,
 		ksft_cnt.ksft_xskip, ksft_cnt.ksft_error);
@@ -120,6 +152,32 @@ static inline void ksft_test_result_fail(const char *msg, ...)
 	va_end(args);
 }
 
+/**
+ * ksft_test_result() - Report test success based on truth of condition
+ *
+ * @condition: if true, report test success, otherwise failure.
+ */
+#define ksft_test_result(condition, fmt, ...) do {	\
+	if (!!(condition))				\
+		ksft_test_result_pass(fmt, ##__VA_ARGS__);\
+	else						\
+		ksft_test_result_fail(fmt, ##__VA_ARGS__);\
+	} while (0)
+
+static inline void ksft_test_result_xfail(const char *msg, ...)
+{
+	int saved_errno = errno;
+	va_list args;
+
+	ksft_cnt.ksft_xfail++;
+
+	va_start(args, msg);
+	printf("ok %d # XFAIL ", ksft_test_num());
+	errno = saved_errno;
+	vprintf(msg, args);
+	va_end(args);
+}
+
 static inline void ksft_test_result_skip(const char *msg, ...)
 {
 	int saved_errno = errno;
@@ -128,12 +186,13 @@ static inline void ksft_test_result_skip(const char *msg, ...)
 	ksft_cnt.ksft_xskip++;
 
 	va_start(args, msg);
-	printf("not ok %d # SKIP ", ksft_test_num());
+	printf("ok %d # SKIP ", ksft_test_num());
 	errno = saved_errno;
 	vprintf(msg, args);
 	va_end(args);
 }
 
+/* TODO: how does "error" differ from "fail" or "skip"? */
 static inline void ksft_test_result_error(const char *msg, ...)
 {
 	int saved_errno = errno;
@@ -156,11 +215,22 @@ static inline int ksft_exit_pass(void)
 
 static inline int ksft_exit_fail(void)
 {
-	printf("Bail out!\n");
 	ksft_print_cnts();
 	exit(KSFT_FAIL);
 }
 
+/**
+ * ksft_exit() - Exit selftest based on truth of condition
+ *
+ * @condition: if true, exit self test with success, otherwise fail.
+ */
+#define ksft_exit(condition) do {	\
+	if (!!(condition))		\
+		ksft_exit_pass();	\
+	else				\
+		ksft_exit_fail();	\
+	} while (0)
+
 static inline int ksft_exit_fail_msg(const char *msg, ...)
 {
 	int saved_errno = errno;
@@ -190,18 +260,30 @@ static inline int ksft_exit_xpass(void)
 
 static inline int ksft_exit_skip(const char *msg, ...)
 {
-	if (msg) {
-		int saved_errno = errno;
-		va_list args;
+	int saved_errno = errno;
+	va_list args;
+
+	va_start(args, msg);
 
-		va_start(args, msg);
-		printf("not ok %d # SKIP ", 1 + ksft_test_num());
+	/*
+	 * FIXME: several tests misuse ksft_exit_skip so produce
+	 * something sensible if some tests have already been run
+	 * or a plan has been printed.  Those tests should use
+	 * ksft_test_result_skip or ksft_exit_fail_msg instead.
+	 */
+	if (ksft_plan || ksft_test_num()) {
+		ksft_cnt.ksft_xskip++;
+		printf("ok %d # SKIP ", 1 + ksft_test_num());
+	} else {
+		printf("1..0 # SKIP ");
+	}
+	if (msg) {
 		errno = saved_errno;
 		vprintf(msg, args);
 		va_end(args);
-	} else {
-		ksft_print_cnts();
 	}
+	if (ksft_test_num())
+		ksft_print_cnts();
 	exit(KSFT_SKIP);
 }
 
diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index 676b3a8b114d..cc9c846585f0 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -53,6 +53,10 @@ run_one()
 	settings="$BASE_DIR/$DIR/settings"
 	if [ -r "$settings" ] ; then
 		while read line ; do
+			# Skip comments.
+			if echo "$line" | grep -q '^#'; then
+				continue
+			fi
 			field=$(echo "$line" | cut -d= -f1)
 			value=$(echo "$line" | cut -d= -f2-)
 			eval "kselftest_$field"="$value"
@@ -77,10 +81,10 @@ run_one()
 		echo "ok $test_num $TEST_HDR_MSG") ||
 		(rc=$?;	\
 		if [ $rc -eq $skip_rc ]; then	\
-			echo "not ok $test_num $TEST_HDR_MSG # SKIP"
+			echo "ok $test_num $TEST_HDR_MSG # SKIP"
 		elif [ $rc -eq $timeout_rc ]; then \
 			echo "#"
-			echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT"
+			echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT $kselftest_timeout seconds"
 		else
 			echo "not ok $test_num $TEST_HDR_MSG # exit=$rc"
 		fi)
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index c9f03ef93338..4f78e4805633 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -50,7 +50,9 @@
 #ifndef __KSELFTEST_HARNESS_H
 #define __KSELFTEST_HARNESS_H
 
+#ifndef _GNU_SOURCE
 #define _GNU_SOURCE
+#endif
 #include <asm/types.h>
 #include <errno.h>
 #include <stdbool.h>
@@ -58,10 +60,13 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <unistd.h>
 
+#include "kselftest.h"
+
 #define TEST_TIMEOUT_DEFAULT 30
 
 /* Utilities exposed to the test definitions */
@@ -104,26 +109,28 @@
 
 /* Unconditional logger for internal use. */
 #define __TH_LOG(fmt, ...) \
-		fprintf(TH_LOG_STREAM, "%s:%d:%s:" fmt "\n", \
+		fprintf(TH_LOG_STREAM, "# %s:%d:%s:" fmt "\n", \
 			__FILE__, __LINE__, _metadata->name, ##__VA_ARGS__)
 
 /**
- * XFAIL(statement, fmt, ...)
+ * SKIP(statement, fmt, ...)
  *
- * @statement: statement to run after reporting XFAIL
+ * @statement: statement to run after reporting SKIP
  * @fmt: format string
  * @...: optional arguments
  *
- * This forces a "pass" after reporting a failure with an XFAIL prefix,
+ * This forces a "pass" after reporting why something is being skipped
  * and runs "statement", which is usually "return" or "goto skip".
  */
-#define XFAIL(statement, fmt, ...) do { \
+#define SKIP(statement, fmt, ...) do { \
+	snprintf(_metadata->results->reason, \
+		 sizeof(_metadata->results->reason), fmt, ##__VA_ARGS__); \
 	if (TH_LOG_ENABLED) { \
-		fprintf(TH_LOG_STREAM, "[  XFAIL!  ] " fmt "\n", \
-			##__VA_ARGS__); \
+		fprintf(TH_LOG_STREAM, "#      SKIP     %s\n", \
+			_metadata->results->reason); \
 	} \
-	/* TODO: find a way to pass xfail to test runner process. */ \
 	_metadata->passed = 1; \
+	_metadata->skip = 1; \
 	_metadata->trigger = 0; \
 	statement; \
 } while (0)
@@ -195,8 +202,9 @@
  *
  * .. code-block:: c
  *
- *     FIXTURE_DATA(datatype name)
+ *     FIXTURE_DATA(datatype_name)
  *
+ * Almost always, you want just FIXTURE() instead (see below).
  * This call may be used when the type of the fixture data
  * is needed.  In general, this should not be needed unless
  * the *self* is being passed to a helper directly.
@@ -211,7 +219,7 @@
  *
  * .. code-block:: c
  *
- *     FIXTURE(datatype name) {
+ *     FIXTURE(fixture_name) {
  *       type property1;
  *       ...
  *     };
@@ -238,7 +246,7 @@
  *
  * .. code-block:: c
  *
- *     FIXTURE_SETUP(fixture name) { implementation }
+ *     FIXTURE_SETUP(fixture_name) { implementation }
  *
  * Populates the required "setup" function for a fixture.  An instance of the
  * datatype defined with FIXTURE_DATA() will be exposed as *self* for the
@@ -264,7 +272,7 @@
  *
  * .. code-block:: c
  *
- *     FIXTURE_TEARDOWN(fixture name) { implementation }
+ *     FIXTURE_TEARDOWN(fixture_name) { implementation }
  *
  * Populates the required "teardown" function for a fixture.  An instance of the
  * datatype defined with FIXTURE_DATA() will be exposed as *self* for the
@@ -285,7 +293,7 @@
  *
  * .. code-block:: c
  *
- *     FIXTURE_VARIANT(datatype name) {
+ *     FIXTURE_VARIANT(fixture_name) {
  *       type property1;
  *       ...
  *     };
@@ -305,8 +313,8 @@
  *
  * .. code-block:: c
  *
- *     FIXTURE_ADD(datatype name) {
- *       .property1 = val1;
+ *     FIXTURE_VARIANT_ADD(fixture_name, variant_name) {
+ *       .property1 = val1,
  *       ...
  *     };
  *
@@ -672,20 +680,53 @@
 			__bail(_assert, _metadata->no_print, _metadata->step))
 
 #define __INC_STEP(_metadata) \
-	if (_metadata->passed && _metadata->step < 255) \
+	/* Keep "step" below 255 (which is used for "SKIP" reporting). */	\
+	if (_metadata->passed && _metadata->step < 253) \
 		_metadata->step++;
 
+#define is_signed_type(var)       (!!(((__typeof__(var))(-1)) < (__typeof__(var))1))
+
 #define __EXPECT(_expected, _expected_str, _seen, _seen_str, _t, _assert) do { \
 	/* Avoid multiple evaluation of the cases */ \
 	__typeof__(_expected) __exp = (_expected); \
 	__typeof__(_seen) __seen = (_seen); \
 	if (_assert) __INC_STEP(_metadata); \
 	if (!(__exp _t __seen)) { \
-		unsigned long long __exp_print = (uintptr_t)__exp; \
-		unsigned long long __seen_print = (uintptr_t)__seen; \
-		__TH_LOG("Expected %s (%llu) %s %s (%llu)", \
-			 _expected_str, __exp_print, #_t, \
-			 _seen_str, __seen_print); \
+		/* Report with actual signedness to avoid weird output. */ \
+		switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \
+		case 0: { \
+			unsigned long long __exp_print = (uintptr_t)__exp; \
+			unsigned long long __seen_print = (uintptr_t)__seen; \
+			__TH_LOG("Expected %s (%llu) %s %s (%llu)", \
+				 _expected_str, __exp_print, #_t, \
+				 _seen_str, __seen_print); \
+			break; \
+			} \
+		case 1: { \
+			unsigned long long __exp_print = (uintptr_t)__exp; \
+			long long __seen_print = (intptr_t)__seen; \
+			__TH_LOG("Expected %s (%llu) %s %s (%lld)", \
+				 _expected_str, __exp_print, #_t, \
+				 _seen_str, __seen_print); \
+			break; \
+			} \
+		case 2: { \
+			long long __exp_print = (intptr_t)__exp; \
+			unsigned long long __seen_print = (uintptr_t)__seen; \
+			__TH_LOG("Expected %s (%lld) %s %s (%llu)", \
+				 _expected_str, __exp_print, #_t, \
+				 _seen_str, __seen_print); \
+			break; \
+			} \
+		case 3: { \
+			long long __exp_print = (intptr_t)__exp; \
+			long long __seen_print = (intptr_t)__seen; \
+			__TH_LOG("Expected %s (%lld) %s %s (%lld)", \
+				 _expected_str, __exp_print, #_t, \
+				 _seen_str, __seen_print); \
+			break; \
+			} \
+		} \
 		_metadata->passed = 0; \
 		/* Ensure the optional handler is triggered */ \
 		_metadata->trigger = 1; \
@@ -726,6 +767,10 @@
 	} \
 }
 
+struct __test_results {
+	char reason[1024];	/* Reason for test result */
+};
+
 struct __test_metadata;
 struct __fixture_variant_metadata;
 
@@ -773,11 +818,13 @@ struct __test_metadata {
 	struct __fixture_metadata *fixture;
 	int termsig;
 	int passed;
+	int skip;	/* did SKIP get used? */
 	int trigger; /* extra handler after the evaluation */
 	int timeout;	/* seconds to wait for test timeout */
 	bool timed_out;	/* did this test timeout instead of exiting? */
 	__u8 step;
 	bool no_print; /* manual trigger when TH_LOG_STREAM is not available */
+	struct __test_results *results;
 	struct __test_metadata *prev, *next;
 };
 
@@ -813,12 +860,12 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext)
 	/* Sanity check handler execution environment. */
 	if (!t) {
 		fprintf(TH_LOG_STREAM,
-			"no active test in SIGALRM handler!?\n");
+			"# no active test in SIGALRM handler!?\n");
 		abort();
 	}
 	if (sig != SIGALRM || sig != info->si_signo) {
 		fprintf(TH_LOG_STREAM,
-			"%s: SIGALRM handler caught signal %d!?\n",
+			"# %s: SIGALRM handler caught signal %d!?\n",
 			t->name, sig != SIGALRM ? sig : info->si_signo);
 		abort();
 	}
@@ -839,7 +886,7 @@ void __wait_for_test(struct __test_metadata *t)
 	if (sigaction(SIGALRM, &action, &saved_action)) {
 		t->passed = 0;
 		fprintf(TH_LOG_STREAM,
-			"%s: unable to install SIGALRM handler\n",
+			"# %s: unable to install SIGALRM handler\n",
 			t->name);
 		return;
 	}
@@ -851,7 +898,7 @@ void __wait_for_test(struct __test_metadata *t)
 	if (sigaction(SIGALRM, &saved_action, NULL)) {
 		t->passed = 0;
 		fprintf(TH_LOG_STREAM,
-			"%s: unable to uninstall SIGALRM handler\n",
+			"# %s: unable to uninstall SIGALRM handler\n",
 			t->name);
 		return;
 	}
@@ -860,39 +907,51 @@ void __wait_for_test(struct __test_metadata *t)
 	if (t->timed_out) {
 		t->passed = 0;
 		fprintf(TH_LOG_STREAM,
-			"%s: Test terminated by timeout\n", t->name);
+			"# %s: Test terminated by timeout\n", t->name);
 	} else if (WIFEXITED(status)) {
-		t->passed = t->termsig == -1 ? !WEXITSTATUS(status) : 0;
 		if (t->termsig != -1) {
+			t->passed = 0;
 			fprintf(TH_LOG_STREAM,
-				"%s: Test exited normally "
-				"instead of by signal (code: %d)\n",
-				t->name,
-				WEXITSTATUS(status));
-		} else if (!t->passed) {
-			fprintf(TH_LOG_STREAM,
-				"%s: Test failed at step #%d\n",
+				"# %s: Test exited normally instead of by signal (code: %d)\n",
 				t->name,
 				WEXITSTATUS(status));
+		} else {
+			switch (WEXITSTATUS(status)) {
+			/* Success */
+			case 0:
+				t->passed = 1;
+				break;
+			/* SKIP */
+			case 255:
+				t->passed = 1;
+				t->skip = 1;
+				break;
+			/* Other failure, assume step report. */
+			default:
+				t->passed = 0;
+				fprintf(TH_LOG_STREAM,
+					"# %s: Test failed at step #%d\n",
+					t->name,
+					WEXITSTATUS(status));
+			}
 		}
 	} else if (WIFSIGNALED(status)) {
 		t->passed = 0;
 		if (WTERMSIG(status) == SIGABRT) {
 			fprintf(TH_LOG_STREAM,
-				"%s: Test terminated by assertion\n",
+				"# %s: Test terminated by assertion\n",
 				t->name);
 		} else if (WTERMSIG(status) == t->termsig) {
 			t->passed = 1;
 		} else {
 			fprintf(TH_LOG_STREAM,
-				"%s: Test terminated unexpectedly "
-				"by signal %d\n",
+				"# %s: Test terminated unexpectedly by signal %d\n",
 				t->name,
 				WTERMSIG(status));
 		}
 	} else {
 		fprintf(TH_LOG_STREAM,
-			"%s: Test ended in some other way [%u]\n",
+			"# %s: Test ended in some other way [%u]\n",
 			t->name,
 			status);
 	}
@@ -904,25 +963,39 @@ void __run_test(struct __fixture_metadata *f,
 {
 	/* reset test struct */
 	t->passed = 1;
+	t->skip = 0;
 	t->trigger = 0;
 	t->step = 0;
 	t->no_print = 0;
+	memset(t->results->reason, 0, sizeof(t->results->reason));
 
-	printf("[ RUN      ] %s%s%s.%s\n",
+	ksft_print_msg(" RUN           %s%s%s.%s ...\n",
 	       f->name, variant->name[0] ? "." : "", variant->name, t->name);
 	t->pid = fork();
 	if (t->pid < 0) {
-		printf("ERROR SPAWNING TEST CHILD\n");
+		ksft_print_msg("ERROR SPAWNING TEST CHILD\n");
 		t->passed = 0;
 	} else if (t->pid == 0) {
 		t->fn(t, variant);
-		/* return the step that failed or 0 */
-		_exit(t->passed ? 0 : t->step);
+		if (t->skip)
+			_exit(255);
+		/* Pass is exit 0 */
+		if (t->passed)
+			_exit(0);
+		/* Something else happened, report the step. */
+		_exit(t->step);
 	} else {
 		__wait_for_test(t);
 	}
-	printf("[     %4s ] %s%s%s.%s\n", (t->passed ? "OK" : "FAIL"),
+	ksft_print_msg("         %4s  %s%s%s.%s\n", t->passed ? "OK" : "FAIL",
 	       f->name, variant->name[0] ? "." : "", variant->name, t->name);
+
+	if (t->skip)
+		ksft_test_result_skip("%s\n", t->results->reason[0] ?
+					t->results->reason : "unknown");
+	else
+		ksft_test_result(t->passed, "%s%s%s.%s\n",
+			f->name, variant->name[0] ? "." : "", variant->name, t->name);
 }
 
 static int test_harness_run(int __attribute__((unused)) argc,
@@ -931,6 +1004,7 @@ static int test_harness_run(int __attribute__((unused)) argc,
 	struct __fixture_variant_metadata no_variant = { .name = "", };
 	struct __fixture_variant_metadata *v;
 	struct __fixture_metadata *f;
+	struct __test_results *results;
 	struct __test_metadata *t;
 	int ret = 0;
 	unsigned int case_count = 0, test_count = 0;
@@ -945,14 +1019,20 @@ static int test_harness_run(int __attribute__((unused)) argc,
 		}
 	}
 
-	/* TODO(wad) add optional arguments similar to gtest. */
-	printf("[==========] Running %u tests from %u test cases.\n",
+	results = mmap(NULL, sizeof(*results), PROT_READ | PROT_WRITE,
+		       MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+
+	ksft_print_header();
+	ksft_set_plan(test_count);
+	ksft_print_msg("Starting %u tests from %u test cases.\n",
 	       test_count, case_count);
 	for (f = __fixture_list; f; f = f->next) {
 		for (v = f->variant ?: &no_variant; v; v = v->next) {
 			for (t = f->tests; t; t = t->next) {
 				count++;
+				t->results = results;
 				__run_test(f, v, t);
+				t->results = NULL;
 				if (t->passed)
 					pass_count++;
 				else
@@ -960,9 +1040,14 @@ static int test_harness_run(int __attribute__((unused)) argc,
 			}
 		}
 	}
-	printf("[==========] %u / %u tests passed.\n", pass_count, count);
-	printf("[  %s  ]\n", (ret ? "FAILED" : "PASSED"));
-	return ret;
+	munmap(results, sizeof(*results));
+
+	ksft_print_msg("%s: %u / %u tests passed.\n", ret ? "FAILED" : "PASSED",
+			pass_count, count);
+	ksft_exit(ret == 0);
+
+	/* unreachable */
+	return KSFT_FAIL;
 }
 
 static void __attribute__((constructor)) __constructor_order_first(void)
diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c
index 8162c58a1234..b8d14f9db5f9 100644
--- a/tools/testing/selftests/kvm/x86_64/debug_regs.c
+++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c
@@ -40,11 +40,11 @@ static void guest_code(void)
 
 	/* Single step test, covers 2 basic instructions and 2 emulated */
 	asm volatile("ss_start: "
-		     "xor %%rax,%%rax\n\t"
+		     "xor %%eax,%%eax\n\t"
 		     "cpuid\n\t"
 		     "movl $0x1a0,%%ecx\n\t"
 		     "rdmsr\n\t"
-		     : : : "rax", "ecx");
+		     : : : "eax", "ebx", "ecx", "edx");
 
 	/* DR6.BD test */
 	asm volatile("bd_start: mov %%dr0, %%rax" : : : "rax");
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
index 54cdefdfb49d..d59f3eb67c8f 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
@@ -76,10 +76,8 @@ void set_default_state(struct kvm_nested_state *state)
 void set_default_vmx_state(struct kvm_nested_state *state, int size)
 {
 	memset(state, 0, size);
-	state->flags = KVM_STATE_NESTED_GUEST_MODE  |
-			KVM_STATE_NESTED_RUN_PENDING;
 	if (have_evmcs)
-		state->flags |= KVM_STATE_NESTED_EVMCS;
+		state->flags = KVM_STATE_NESTED_EVMCS;
 	state->format = 0;
 	state->size = size;
 	state->hdr.vmx.vmxon_pa = 0x1000;
@@ -148,6 +146,11 @@ void test_vmx_nested_state(struct kvm_vm *vm)
 	state->hdr.vmx.smm.flags = 1;
 	test_nested_state_expect_einval(vm, state);
 
+	/* Invalid flags are rejected. */
+	set_default_vmx_state(state, state_sz);
+	state->hdr.vmx.flags = ~0;
+	test_nested_state_expect_einval(vm, state);
+
 	/* It is invalid to have vmxon_pa == -1ull and vmcs_pa != -1ull. */
 	set_default_vmx_state(state, state_sz);
 	state->hdr.vmx.vmxon_pa = -1ull;
@@ -185,20 +188,41 @@ void test_vmx_nested_state(struct kvm_vm *vm)
 	state->hdr.vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE;
 	test_nested_state_expect_einval(vm, state);
 
-	/* Size must be large enough to fit kvm_nested_state and vmcs12. */
+	/*
+	 * Size must be large enough to fit kvm_nested_state and vmcs12
+	 * if VMCS12 physical address is set
+	 */
 	set_default_vmx_state(state, state_sz);
 	state->size = sizeof(*state);
+	state->flags = 0;
+	test_nested_state_expect_einval(vm, state);
+
+	set_default_vmx_state(state, state_sz);
+	state->size = sizeof(*state);
+	state->flags = 0;
+	state->hdr.vmx.vmcs12_pa = -1;
 	test_nested_state(vm, state);
 
-	/* vmxon_pa cannot be the same address as vmcs_pa. */
+	/*
+	 * KVM_SET_NESTED_STATE succeeds with invalid VMCS
+	 * contents but L2 not running.
+	 */
 	set_default_vmx_state(state, state_sz);
-	state->hdr.vmx.vmxon_pa = 0;
-	state->hdr.vmx.vmcs12_pa = 0;
+	state->flags = 0;
+	test_nested_state(vm, state);
+
+	/* Invalid flags are rejected, even if no VMCS loaded. */
+	set_default_vmx_state(state, state_sz);
+	state->size = sizeof(*state);
+	state->flags = 0;
+	state->hdr.vmx.vmcs12_pa = -1;
+	state->hdr.vmx.flags = ~0;
 	test_nested_state_expect_einval(vm, state);
 
-	/* The revision id for vmcs12 must be VMCS12_REVISION. */
+	/* vmxon_pa cannot be the same address as vmcs_pa. */
 	set_default_vmx_state(state, state_sz);
-	set_revision_id_for_vmcs12(state, 0);
+	state->hdr.vmx.vmxon_pa = 0;
+	state->hdr.vmx.vmcs12_pa = 0;
 	test_nested_state_expect_einval(vm, state);
 
 	/*
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index b0556c752443..7a17ea815736 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -59,9 +59,8 @@ else
 all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
 endif
 
-.ONESHELL:
 define RUN_TESTS
-	@BASE_DIR="$(selfdir)";			\
+	BASE_DIR="$(selfdir)";			\
 	. $(selfdir)/kselftest/runner.sh;	\
 	if [ "X$(summary)" != "X" ]; then       \
 		per_test_logging=1;		\
@@ -71,22 +70,21 @@ endef
 
 run_tests: all
 ifdef building_out_of_srctree
-	@if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then
-		@rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT)
+	@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \
+		rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \
 	fi
-	@if [ "X$(TEST_PROGS)" != "X" ]; then
-		$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS))
-	else
-		$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS))
+	@if [ "X$(TEST_PROGS)" != "X" ]; then \
+		$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) ; \
+	else \
+		$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)); \
 	fi
 else
-	$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
+	@$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
 endif
 
 define INSTALL_SINGLE_RULE
 	$(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH))
-	$(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
-	$(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
+	$(if $(INSTALL_LIST),rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
 endef
 
 define INSTALL_RULE
diff --git a/tools/testing/selftests/livepatch/README b/tools/testing/selftests/livepatch/README
index 621d325425c2..0942dd5826f8 100644
--- a/tools/testing/selftests/livepatch/README
+++ b/tools/testing/selftests/livepatch/README
@@ -6,8 +6,8 @@ This is a small set of sanity tests for the kernel livepatching.
 
 The test suite loads and unloads several test kernel modules to verify
 livepatch behavior.  Debug information is logged to the kernel's message
-buffer and parsed for expected messages.  (Note: the tests will clear
-the message buffer between individual tests.)
+buffer and parsed for expected messages.  (Note: the tests will compare
+the message buffer for only the duration of each individual test.)
 
 
 Config
@@ -35,9 +35,9 @@ Adding tests
 ------------
 
 See the common functions.sh file for the existing collection of utility
-functions, most importantly setup_config() and check_result().  The
-latter function greps the kernel's ring buffer for "livepatch:" and
-"test_klp" strings, so tests be sure to include one of those strings for
-result comparison.  Other utility functions include general module
-loading and livepatch loading helpers (waiting for patch transitions,
-sysfs entries, etc.)
+functions, most importantly setup_config(), start_test() and
+check_result().  The latter function greps the kernel's ring buffer for
+"livepatch:" and "test_klp" strings, so tests be sure to include one of
+those strings for result comparison.  Other utility functions include
+general module loading and livepatch loading helpers (waiting for patch
+transitions, sysfs entries, etc.)
diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh
index 2aab9791791d..1aba83c87ad3 100644
--- a/tools/testing/selftests/livepatch/functions.sh
+++ b/tools/testing/selftests/livepatch/functions.sh
@@ -41,6 +41,17 @@ function die() {
 	exit 1
 }
 
+# save existing dmesg so we can detect new content
+function save_dmesg() {
+	SAVED_DMESG=$(mktemp --tmpdir -t klp-dmesg-XXXXXX)
+	dmesg > "$SAVED_DMESG"
+}
+
+# cleanup temporary dmesg file from save_dmesg()
+function cleanup_dmesg_file() {
+	rm -f "$SAVED_DMESG"
+}
+
 function push_config() {
 	DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \
 			awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}')
@@ -64,10 +75,16 @@ function set_dynamic_debug() {
 }
 
 function set_ftrace_enabled() {
-	result=$(sysctl kernel.ftrace_enabled="$1" 2>&1 | paste --serial --delimiters=' ')
+	result=$(sysctl -q kernel.ftrace_enabled="$1" 2>&1 && \
+		 sysctl kernel.ftrace_enabled 2>&1)
 	echo "livepatch: $result" > /dev/kmsg
 }
 
+function cleanup() {
+	pop_config
+	cleanup_dmesg_file
+}
+
 # setup_config - save the current config and set a script exit trap that
 #		 restores the original config.  Setup the dynamic debug
 #		 for verbose livepatching output and turn on
@@ -77,7 +94,7 @@ function setup_config() {
 	push_config
 	set_dynamic_debug
 	set_ftrace_enabled 1
-	trap pop_config EXIT INT TERM HUP
+	trap cleanup EXIT INT TERM HUP
 }
 
 # loop_until(cmd) - loop a command until it is successful or $MAX_RETRIES,
@@ -243,13 +260,28 @@ function set_pre_patch_ret {
 		die "failed to set pre_patch_ret parameter for $mod module"
 }
 
+function start_test {
+	local test="$1"
+
+	save_dmesg
+	echo -n "TEST: $test ... "
+	log "===== TEST: $test ====="
+}
+
 # check_result() - verify dmesg output
 #	TODO - better filter, out of order msgs, etc?
 function check_result {
 	local expect="$*"
 	local result
 
-	result=$(dmesg | grep -v 'tainting' | grep -e 'livepatch:' -e 'test_klp' | sed 's/^\[[ 0-9.]*\] //')
+	# Note: when comparing dmesg output, the kernel log timestamps
+	# help differentiate repeated testing runs.  Remove them with a
+	# post-comparison sed filter.
+
+	result=$(dmesg | comm -13 "$SAVED_DMESG" - | \
+		 grep -e 'livepatch:' -e 'test_klp' | \
+		 grep -v '\(tainting\|taints\) kernel' | \
+		 sed 's/^\[[ 0-9.]*\] //')
 
 	if [[ "$expect" == "$result" ]] ; then
 		echo "ok"
@@ -257,4 +289,6 @@ function check_result {
 		echo -e "not ok\n\n$(diff -upr --label expected --label result <(echo "$expect") <(echo "$result"))\n"
 		die "livepatch kselftest(s) failed"
 	fi
+
+	cleanup_dmesg_file
 }
diff --git a/tools/testing/selftests/livepatch/test-callbacks.sh b/tools/testing/selftests/livepatch/test-callbacks.sh
index a35289b13c9c..90b26dbb2626 100755
--- a/tools/testing/selftests/livepatch/test-callbacks.sh
+++ b/tools/testing/selftests/livepatch/test-callbacks.sh
@@ -12,8 +12,6 @@ MOD_TARGET_BUSY=test_klp_callbacks_busy
 setup_config
 
 
-# TEST: target module before livepatch
-#
 # Test a combination of loading a kernel module and a livepatch that
 # patches a function in the first module.  Load the target module
 # before the livepatch module.  Unload them in the same order.
@@ -28,8 +26,7 @@ setup_config
 #   unpatching transition starts.  klp_objects are reverted, post-patch
 #   callbacks execute and the transition completes.
 
-echo -n "TEST: target module before livepatch ... "
-dmesg -C
+start_test "target module before livepatch"
 
 load_mod $MOD_TARGET
 load_lp $MOD_LIVEPATCH
@@ -63,8 +60,6 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 $MOD_TARGET: ${MOD_TARGET}_exit"
 
 
-# TEST: module_coming notifier
-#
 # This test is similar to the previous test, but (un)load the livepatch
 # module before the target kernel module.  This tests the livepatch
 # core's module_coming handler.
@@ -78,8 +73,7 @@ $MOD_TARGET: ${MOD_TARGET}_exit"
 # - On livepatch disable, all currently loaded klp_objects' (vmlinux and
 #   $MOD_TARGET) pre/post-unpatch callbacks are executed.
 
-echo -n "TEST: module_coming notifier ... "
-dmesg -C
+start_test "module_coming notifier"
 
 load_lp $MOD_LIVEPATCH
 load_mod $MOD_TARGET
@@ -114,8 +108,6 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 $MOD_TARGET: ${MOD_TARGET}_exit"
 
 
-# TEST: module_going notifier
-#
 # Test loading the livepatch after a targeted kernel module, then unload
 # the kernel module before disabling the livepatch.  This tests the
 # livepatch core's module_going handler.
@@ -129,8 +121,7 @@ $MOD_TARGET: ${MOD_TARGET}_exit"
 # - When the livepatch is disabled, pre and post-unpatch callbacks are
 #   run for the remaining klp_object, vmlinux.
 
-echo -n "TEST: module_going notifier ... "
-dmesg -C
+start_test "module_going notifier"
 
 load_mod $MOD_TARGET
 load_lp $MOD_LIVEPATCH
@@ -165,8 +156,6 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 % rmmod $MOD_LIVEPATCH"
 
 
-# TEST: module_coming and module_going notifiers
-#
 # This test is similar to the previous test, however the livepatch is
 # loaded first.  This tests the livepatch core's module_coming and
 # module_going handlers.
@@ -180,8 +169,7 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 #   from the $MOD_TARGET klp_object.  As such, only pre and
 #   post-unpatch callbacks are executed when this occurs.
 
-echo -n "TEST: module_coming and module_going notifiers ... "
-dmesg -C
+start_test "module_coming and module_going notifiers"
 
 load_lp $MOD_LIVEPATCH
 load_mod $MOD_TARGET
@@ -217,8 +205,6 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 % rmmod $MOD_LIVEPATCH"
 
 
-# TEST: target module not present
-#
 # A simple test of loading a livepatch without one of its patch target
 # klp_objects ever loaded ($MOD_TARGET).
 #
@@ -227,8 +213,7 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 # - As expected, only pre/post-(un)patch handlers are executed for
 #   vmlinux.
 
-echo -n "TEST: target module not present ... "
-dmesg -C
+start_test "target module not present"
 
 load_lp $MOD_LIVEPATCH
 disable_lp $MOD_LIVEPATCH
@@ -252,8 +237,6 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 % rmmod $MOD_LIVEPATCH"
 
 
-# TEST: pre-patch callback -ENODEV
-#
 # Test a scenario where a vmlinux pre-patch callback returns a non-zero
 # status (ie, failure).
 #
@@ -265,8 +248,7 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 #   The result is that the insmod command refuses to load the livepatch
 #   module.
 
-echo -n "TEST: pre-patch callback -ENODEV ... "
-dmesg -C
+start_test "pre-patch callback -ENODEV"
 
 load_mod $MOD_TARGET
 load_failing_mod $MOD_LIVEPATCH pre_patch_ret=-19
@@ -288,8 +270,6 @@ modprobe: ERROR: could not insert '$MOD_LIVEPATCH': No such device
 $MOD_TARGET: ${MOD_TARGET}_exit"
 
 
-# TEST: module_coming + pre-patch callback -ENODEV
-#
 # Similar to the previous test, setup a livepatch such that its vmlinux
 # pre-patch callback returns success.  However, when a targeted kernel
 # module is later loaded, have the livepatch return a failing status
@@ -307,8 +287,7 @@ $MOD_TARGET: ${MOD_TARGET}_exit"
 #
 # - Pre/post-unpatch callbacks are run for the vmlinux klp_object.
 
-echo -n "TEST: module_coming + pre-patch callback -ENODEV ... "
-dmesg -C
+start_test "module_coming + pre-patch callback -ENODEV"
 
 load_lp $MOD_LIVEPATCH
 set_pre_patch_ret $MOD_LIVEPATCH -19
@@ -341,8 +320,6 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 % rmmod $MOD_LIVEPATCH"
 
 
-# TEST: multiple target modules
-#
 # Test loading multiple targeted kernel modules.  This test-case is
 # mainly for comparing with the next test-case.
 #
@@ -353,12 +330,9 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 #   module.  Post-patch callbacks are executed and the transition
 #   completes quickly.
 
-echo -n "TEST: multiple target modules ... "
-dmesg -C
+start_test "multiple target modules"
 
-load_mod $MOD_TARGET_BUSY sleep_secs=0
-# give $MOD_TARGET_BUSY::busymod_work_func() a chance to run
-sleep 5
+load_mod $MOD_TARGET_BUSY block_transition=N
 load_lp $MOD_LIVEPATCH
 load_mod $MOD_TARGET
 unload_mod $MOD_TARGET
@@ -366,9 +340,9 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 unload_mod $MOD_TARGET_BUSY
 
-check_result "% modprobe $MOD_TARGET_BUSY sleep_secs=0
+check_result "% modprobe $MOD_TARGET_BUSY block_transition=N
 $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_init
-$MOD_TARGET_BUSY: busymod_work_func, sleeping 0 seconds ...
+$MOD_TARGET_BUSY: busymod_work_func enter
 $MOD_TARGET_BUSY: busymod_work_func exit
 % modprobe $MOD_LIVEPATCH
 livepatch: enabling patch '$MOD_LIVEPATCH'
@@ -404,11 +378,8 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_exit"
 
 
-
-# TEST: busy target module
-#
 # A similar test as the previous one, but force the "busy" kernel module
-# to do longer work.
+# to block the livepatch transition.
 #
 # The livepatching core will refuse to patch a task that is currently
 # executing a to-be-patched function -- the consistency model stalls the
@@ -417,8 +388,7 @@ $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_exit"
 # function for a long time.  Meanwhile, load and unload other target
 # kernel modules while the livepatch transition is in progress.
 #
-# - Load the "busy" kernel module, this time make it do 10 seconds worth
-#   of work.
+# - Load the "busy" kernel module, this time make its work function loop
 #
 # - Meanwhile, the livepatch is loaded.  Notice that the patch
 #   transition does not complete as the targeted "busy" module is
@@ -435,23 +405,25 @@ $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_exit"
 #   klp_object's post-patch callbacks executed, the remaining
 #   klp_object's pre-unpatch callbacks are skipped.
 
-echo -n "TEST: busy target module ... "
-dmesg -C
+start_test "busy target module"
 
-load_mod $MOD_TARGET_BUSY sleep_secs=10
+load_mod $MOD_TARGET_BUSY block_transition=Y
 load_lp_nowait $MOD_LIVEPATCH
-# Don't wait for transition, load $MOD_TARGET while the transition
-# is still stalled in $MOD_TARGET_BUSY::busymod_work_func()
-sleep 5
+
+# Wait until the livepatch reports in-transition state, i.e. that it's
+# stalled on $MOD_TARGET_BUSY::busymod_work_func()
+loop_until 'grep -q '^1$' /sys/kernel/livepatch/$MOD_LIVEPATCH/transition' ||
+	die "failed to stall transition"
+
 load_mod $MOD_TARGET
 unload_mod $MOD_TARGET
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 unload_mod $MOD_TARGET_BUSY
 
-check_result "% modprobe $MOD_TARGET_BUSY sleep_secs=10
+check_result "% modprobe $MOD_TARGET_BUSY block_transition=Y
 $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_init
-$MOD_TARGET_BUSY: busymod_work_func, sleeping 10 seconds ...
+$MOD_TARGET_BUSY: busymod_work_func enter
 % modprobe $MOD_LIVEPATCH
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
@@ -479,8 +451,6 @@ $MOD_TARGET_BUSY: busymod_work_func exit
 $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_exit"
 
 
-# TEST: multiple livepatches
-#
 # Test loading multiple livepatches.  This test-case is mainly for comparing
 # with the next test-case.
 #
@@ -488,8 +458,7 @@ $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_exit"
 #   execute as each patch progresses through its (un)patching
 #   transition.
 
-echo -n "TEST: multiple livepatches ... "
-dmesg -C
+start_test "multiple livepatches"
 
 load_lp $MOD_LIVEPATCH
 load_lp $MOD_LIVEPATCH2
@@ -532,8 +501,6 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 % rmmod $MOD_LIVEPATCH"
 
 
-# TEST: atomic replace
-#
 # Load multiple livepatches, but the second as an 'atomic-replace'
 # patch.  When the latter loads, the original livepatch should be
 # disabled and *none* of its pre/post-unpatch callbacks executed.  On
@@ -548,8 +515,7 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 # - Once the atomic replace module is loaded, only its pre and post
 #   unpatch callbacks are executed.
 
-echo -n "TEST: atomic replace ... "
-dmesg -C
+start_test "atomic replace"
 
 load_lp $MOD_LIVEPATCH
 load_lp $MOD_LIVEPATCH2 replace=1
diff --git a/tools/testing/selftests/livepatch/test-ftrace.sh b/tools/testing/selftests/livepatch/test-ftrace.sh
index e2a76887f40a..552e165512f4 100755
--- a/tools/testing/selftests/livepatch/test-ftrace.sh
+++ b/tools/testing/selftests/livepatch/test-ftrace.sh
@@ -9,13 +9,11 @@ MOD_LIVEPATCH=test_klp_livepatch
 setup_config
 
 
-# TEST: livepatch interaction with ftrace_enabled sysctl
 # - turn ftrace_enabled OFF and verify livepatches can't load
 # - turn ftrace_enabled ON and verify livepatch can load
 # - verify that ftrace_enabled can't be turned OFF while a livepatch is loaded
 
-echo -n "TEST: livepatch interaction with ftrace_enabled sysctl ... "
-dmesg -C
+start_test "livepatch interaction with ftrace_enabled sysctl"
 
 set_ftrace_enabled 0
 load_failing_mod $MOD_LIVEPATCH
@@ -53,7 +51,7 @@ livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 livepatch: '$MOD_LIVEPATCH': patching complete
-livepatch: sysctl: setting key \"kernel.ftrace_enabled\": Device or resource busy kernel.ftrace_enabled = 0
+livepatch: sysctl: setting key \"kernel.ftrace_enabled\": Device or resource busy
 % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled
 livepatch: '$MOD_LIVEPATCH': initializing unpatching transition
 livepatch: '$MOD_LIVEPATCH': starting unpatching transition
diff --git a/tools/testing/selftests/livepatch/test-livepatch.sh b/tools/testing/selftests/livepatch/test-livepatch.sh
index 493e3df415a1..5fe79ac34be1 100755
--- a/tools/testing/selftests/livepatch/test-livepatch.sh
+++ b/tools/testing/selftests/livepatch/test-livepatch.sh
@@ -10,13 +10,11 @@ MOD_REPLACE=test_klp_atomic_replace
 setup_config
 
 
-# TEST: basic function patching
 # - load a livepatch that modifies the output from /proc/cmdline and
 #   verify correct behavior
 # - unload the livepatch and make sure the patch was removed
 
-echo -n "TEST: basic function patching ... "
-dmesg -C
+start_test "basic function patching"
 
 load_lp $MOD_LIVEPATCH
 
@@ -47,15 +45,13 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 % rmmod $MOD_LIVEPATCH"
 
 
-# TEST: multiple livepatches
 # - load a livepatch that modifies the output from /proc/cmdline and
 #   verify correct behavior
 # - load another livepatch and verify that both livepatches are active
 # - unload the second livepatch and verify that the first is still active
 # - unload the first livepatch and verify none are active
 
-echo -n "TEST: multiple livepatches ... "
-dmesg -C
+start_test "multiple livepatches"
 
 load_lp $MOD_LIVEPATCH
 
@@ -109,7 +105,6 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 % rmmod $MOD_LIVEPATCH"
 
 
-# TEST: atomic replace livepatch
 # - load a livepatch that modifies the output from /proc/cmdline and
 #   verify correct behavior
 # - load an atomic replace livepatch and verify that only the second is active
@@ -117,8 +112,7 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 #   is still active
 # - remove the atomic replace livepatch and verify that none are active
 
-echo -n "TEST: atomic replace livepatch ... "
-dmesg -C
+start_test "atomic replace livepatch"
 
 load_lp $MOD_LIVEPATCH
 
diff --git a/tools/testing/selftests/livepatch/test-shadow-vars.sh b/tools/testing/selftests/livepatch/test-shadow-vars.sh
index 1aae73299114..e04cb354f56b 100755
--- a/tools/testing/selftests/livepatch/test-shadow-vars.sh
+++ b/tools/testing/selftests/livepatch/test-shadow-vars.sh
@@ -9,52 +9,71 @@ MOD_TEST=test_klp_shadow_vars
 setup_config
 
 
-# TEST: basic shadow variable API
 # - load a module that exercises the shadow variable API
 
-echo -n "TEST: basic shadow variable API ... "
-dmesg -C
+start_test "basic shadow variable API"
 
 load_mod $MOD_TEST
 unload_mod $MOD_TEST
 
 check_result "% modprobe $MOD_TEST
-$MOD_TEST: klp_shadow_get(obj=PTR5, id=0x1234) = PTR0
+$MOD_TEST: klp_shadow_get(obj=PTR1, id=0x1234) = PTR0
 $MOD_TEST:   got expected NULL result
-$MOD_TEST: shadow_ctor: PTR6 -> PTR1
-$MOD_TEST: klp_shadow_alloc(obj=PTR5, id=0x1234, size=8, gfp_flags=GFP_KERNEL), ctor=PTR7, ctor_data=PTR1 = PTR6
-$MOD_TEST: shadow_ctor: PTR8 -> PTR2
-$MOD_TEST: klp_shadow_alloc(obj=PTR9, id=0x1234, size=8, gfp_flags=GFP_KERNEL), ctor=PTR7, ctor_data=PTR2 = PTR8
-$MOD_TEST: shadow_ctor: PTR10 -> PTR3
-$MOD_TEST: klp_shadow_alloc(obj=PTR5, id=0x1235, size=8, gfp_flags=GFP_KERNEL), ctor=PTR7, ctor_data=PTR3 = PTR10
-$MOD_TEST: klp_shadow_get(obj=PTR5, id=0x1234) = PTR6
-$MOD_TEST:   got expected PTR6 -> PTR1 result
+$MOD_TEST: shadow_ctor: PTR3 -> PTR2
+$MOD_TEST: klp_shadow_get_or_alloc(obj=PTR1, id=0x1234, size=8, gfp_flags=GFP_KERNEL), ctor=PTR4, ctor_data=PTR2 = PTR3
+$MOD_TEST: shadow_ctor: PTR6 -> PTR5
+$MOD_TEST: klp_shadow_alloc(obj=PTR1, id=0x1235, size=8, gfp_flags=GFP_KERNEL), ctor=PTR4, ctor_data=PTR5 = PTR6
+$MOD_TEST: shadow_ctor: PTR8 -> PTR7
+$MOD_TEST: klp_shadow_alloc(obj=PTR9, id=0x1234, size=8, gfp_flags=GFP_KERNEL), ctor=PTR4, ctor_data=PTR7 = PTR8
+$MOD_TEST: shadow_ctor: PTR11 -> PTR10
+$MOD_TEST: klp_shadow_alloc(obj=PTR9, id=0x1235, size=8, gfp_flags=GFP_KERNEL), ctor=PTR4, ctor_data=PTR10 = PTR11
+$MOD_TEST: shadow_ctor: PTR13 -> PTR12
+$MOD_TEST: klp_shadow_get_or_alloc(obj=PTR14, id=0x1234, size=8, gfp_flags=GFP_KERNEL), ctor=PTR4, ctor_data=PTR12 = PTR13
+$MOD_TEST: shadow_ctor: PTR16 -> PTR15
+$MOD_TEST: klp_shadow_alloc(obj=PTR14, id=0x1235, size=8, gfp_flags=GFP_KERNEL), ctor=PTR4, ctor_data=PTR15 = PTR16
+$MOD_TEST: klp_shadow_get(obj=PTR1, id=0x1234) = PTR3
+$MOD_TEST:   got expected PTR3 -> PTR2 result
+$MOD_TEST: klp_shadow_get(obj=PTR1, id=0x1235) = PTR6
+$MOD_TEST:   got expected PTR6 -> PTR5 result
 $MOD_TEST: klp_shadow_get(obj=PTR9, id=0x1234) = PTR8
-$MOD_TEST:   got expected PTR8 -> PTR2 result
-$MOD_TEST: klp_shadow_get(obj=PTR5, id=0x1235) = PTR10
-$MOD_TEST:   got expected PTR10 -> PTR3 result
-$MOD_TEST: shadow_ctor: PTR11 -> PTR4
-$MOD_TEST: klp_shadow_get_or_alloc(obj=PTR12, id=0x1234, size=8, gfp_flags=GFP_KERNEL), ctor=PTR7, ctor_data=PTR4 = PTR11
-$MOD_TEST: klp_shadow_get_or_alloc(obj=PTR12, id=0x1234, size=8, gfp_flags=GFP_KERNEL), ctor=PTR7, ctor_data=PTR4 = PTR11
-$MOD_TEST:   got expected PTR11 -> PTR4 result
-$MOD_TEST: shadow_dtor(obj=PTR5, shadow_data=PTR6)
-$MOD_TEST: klp_shadow_free(obj=PTR5, id=0x1234, dtor=PTR13)
-$MOD_TEST: klp_shadow_get(obj=PTR5, id=0x1234) = PTR0
+$MOD_TEST:   got expected PTR8 -> PTR7 result
+$MOD_TEST: klp_shadow_get(obj=PTR9, id=0x1235) = PTR11
+$MOD_TEST:   got expected PTR11 -> PTR10 result
+$MOD_TEST: klp_shadow_get(obj=PTR14, id=0x1234) = PTR13
+$MOD_TEST:   got expected PTR13 -> PTR12 result
+$MOD_TEST: klp_shadow_get(obj=PTR14, id=0x1235) = PTR16
+$MOD_TEST:   got expected PTR16 -> PTR15 result
+$MOD_TEST: klp_shadow_get_or_alloc(obj=PTR1, id=0x1234, size=8, gfp_flags=GFP_KERNEL), ctor=PTR4, ctor_data=PTR2 = PTR3
+$MOD_TEST:   got expected PTR3 -> PTR2 result
+$MOD_TEST: klp_shadow_get_or_alloc(obj=PTR9, id=0x1234, size=8, gfp_flags=GFP_KERNEL), ctor=PTR4, ctor_data=PTR7 = PTR8
+$MOD_TEST:   got expected PTR8 -> PTR7 result
+$MOD_TEST: klp_shadow_get_or_alloc(obj=PTR14, id=0x1234, size=8, gfp_flags=GFP_KERNEL), ctor=PTR4, ctor_data=PTR12 = PTR13
+$MOD_TEST:   got expected PTR13 -> PTR12 result
+$MOD_TEST: shadow_dtor(obj=PTR1, shadow_data=PTR3)
+$MOD_TEST: klp_shadow_free(obj=PTR1, id=0x1234, dtor=PTR17)
+$MOD_TEST: klp_shadow_get(obj=PTR1, id=0x1234) = PTR0
 $MOD_TEST:   got expected NULL result
 $MOD_TEST: shadow_dtor(obj=PTR9, shadow_data=PTR8)
-$MOD_TEST: klp_shadow_free(obj=PTR9, id=0x1234, dtor=PTR13)
+$MOD_TEST: klp_shadow_free(obj=PTR9, id=0x1234, dtor=PTR17)
 $MOD_TEST: klp_shadow_get(obj=PTR9, id=0x1234) = PTR0
 $MOD_TEST:   got expected NULL result
-$MOD_TEST: shadow_dtor(obj=PTR12, shadow_data=PTR11)
-$MOD_TEST: klp_shadow_free(obj=PTR12, id=0x1234, dtor=PTR13)
-$MOD_TEST: klp_shadow_get(obj=PTR12, id=0x1234) = PTR0
+$MOD_TEST: shadow_dtor(obj=PTR14, shadow_data=PTR13)
+$MOD_TEST: klp_shadow_free(obj=PTR14, id=0x1234, dtor=PTR17)
+$MOD_TEST: klp_shadow_get(obj=PTR14, id=0x1234) = PTR0
 $MOD_TEST:   got expected NULL result
-$MOD_TEST: klp_shadow_get(obj=PTR5, id=0x1235) = PTR10
-$MOD_TEST:   got expected PTR10 -> PTR3 result
-$MOD_TEST: shadow_dtor(obj=PTR5, shadow_data=PTR10)
-$MOD_TEST: klp_shadow_free_all(id=0x1235, dtor=PTR13)
-$MOD_TEST: klp_shadow_get(obj=PTR5, id=0x1234) = PTR0
-$MOD_TEST:   shadow_get() got expected NULL result
-% rmmod test_klp_shadow_vars"
+$MOD_TEST: klp_shadow_get(obj=PTR1, id=0x1235) = PTR6
+$MOD_TEST:   got expected PTR6 -> PTR5 result
+$MOD_TEST: klp_shadow_get(obj=PTR9, id=0x1235) = PTR11
+$MOD_TEST:   got expected PTR11 -> PTR10 result
+$MOD_TEST: klp_shadow_get(obj=PTR14, id=0x1235) = PTR16
+$MOD_TEST:   got expected PTR16 -> PTR15 result
+$MOD_TEST: klp_shadow_free_all(id=0x1235, dtor=PTR0)
+$MOD_TEST: klp_shadow_get(obj=PTR1, id=0x1235) = PTR0
+$MOD_TEST:   got expected NULL result
+$MOD_TEST: klp_shadow_get(obj=PTR9, id=0x1235) = PTR0
+$MOD_TEST:   got expected NULL result
+$MOD_TEST: klp_shadow_get(obj=PTR14, id=0x1235) = PTR0
+$MOD_TEST:   got expected NULL result
+% rmmod $MOD_TEST"
 
 exit 0
diff --git a/tools/testing/selftests/livepatch/test-state.sh b/tools/testing/selftests/livepatch/test-state.sh
index a08212708115..38656721c958 100755
--- a/tools/testing/selftests/livepatch/test-state.sh
+++ b/tools/testing/selftests/livepatch/test-state.sh
@@ -10,10 +10,10 @@ MOD_LIVEPATCH3=test_klp_state3
 
 setup_config
 
-# TEST: Loading and removing a module that modifies the system state
 
-echo -n "TEST: system state modification ... "
-dmesg -C
+# Load and remove a module that modifies the system state
+
+start_test "system state modification"
 
 load_lp $MOD_LIVEPATCH
 disable_lp $MOD_LIVEPATCH
@@ -41,10 +41,9 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete
 % rmmod $MOD_LIVEPATCH"
 
 
-# TEST: Take over system state change by a cumulative patch
+# Take over system state change by a cumulative patch
 
-echo -n "TEST: taking over system state modification ... "
-dmesg -C
+start_test "taking over system state modification"
 
 load_lp $MOD_LIVEPATCH
 load_lp $MOD_LIVEPATCH2
@@ -85,10 +84,9 @@ livepatch: '$MOD_LIVEPATCH2': unpatching complete
 % rmmod $MOD_LIVEPATCH2"
 
 
-# TEST: Take over system state change by a cumulative patch
+# Take over system state change by a cumulative patch
 
-echo -n "TEST: compatible cumulative livepatches ... "
-dmesg -C
+start_test "compatible cumulative livepatches"
 
 load_lp $MOD_LIVEPATCH2
 load_lp $MOD_LIVEPATCH3
@@ -142,10 +140,9 @@ livepatch: '$MOD_LIVEPATCH2': unpatching complete
 % rmmod $MOD_LIVEPATCH3"
 
 
-# TEST: Failure caused by incompatible cumulative livepatches
+# Failure caused by incompatible cumulative livepatches
 
-echo -n "TEST: incompatible cumulative livepatches ... "
-dmesg -C
+start_test "incompatible cumulative livepatches"
 
 load_lp $MOD_LIVEPATCH2
 load_failing_mod $MOD_LIVEPATCH
diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh
index ee64ff8df8f4..8383eb89d88a 100755
--- a/tools/testing/selftests/lkdtm/run.sh
+++ b/tools/testing/selftests/lkdtm/run.sh
@@ -8,6 +8,7 @@
 #
 set -e
 TRIGGER=/sys/kernel/debug/provoke-crash/DIRECT
+CLEAR_ONCE=/sys/kernel/debug/clear_warn_once
 KSELFTEST_SKIP_TEST=4
 
 # Verify we have LKDTM available in the kernel.
@@ -67,6 +68,11 @@ cleanup() {
 }
 trap cleanup EXIT
 
+# Reset WARN_ONCE counters so we trip it each time this runs.
+if [ -w $CLEAR_ONCE ] ; then
+	echo 1 > $CLEAR_ONCE
+fi
+
 # Save existing dmesg so we can detect new content below
 dmesg > "$DMESG"
 
diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt
index 92ca32143ae5..9d266e79c6a2 100644
--- a/tools/testing/selftests/lkdtm/tests.txt
+++ b/tools/testing/selftests/lkdtm/tests.txt
@@ -14,6 +14,7 @@ STACK_GUARD_PAGE_LEADING
 STACK_GUARD_PAGE_TRAILING
 UNSET_SMEP CR4 bits went missing
 DOUBLE_FAULT
+CORRUPT_PAC
 UNALIGNED_LOAD_STORE_WRITE
 #OVERWRITE_ALLOCATION Corrupts memory on failure
 #WRITE_AFTER_FREE Corrupts memory on failure
diff --git a/tools/testing/selftests/mincore/.gitignore b/tools/testing/selftests/mincore/.gitignore
new file mode 100644
index 000000000000..15c4dfc2df00
--- /dev/null
+++ b/tools/testing/selftests/mincore/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0+
+mincore_selftest
diff --git a/tools/testing/selftests/mincore/Makefile b/tools/testing/selftests/mincore/Makefile
new file mode 100644
index 000000000000..38c7db1e8926
--- /dev/null
+++ b/tools/testing/selftests/mincore/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0+
+
+CFLAGS += -Wall
+
+TEST_GEN_PROGS := mincore_selftest
+include ../lib.mk
diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c
new file mode 100644
index 000000000000..5a1e85ff5d32
--- /dev/null
+++ b/tools/testing/selftests/mincore/mincore_selftest.c
@@ -0,0 +1,361 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * kselftest suite for mincore().
+ *
+ * Copyright (C) 2020 Collabora, Ltd.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <string.h>
+#include <fcntl.h>
+#include <string.h>
+
+#include "../kselftest.h"
+#include "../kselftest_harness.h"
+
+/* Default test file size: 4MB */
+#define MB (1UL << 20)
+#define FILE_SIZE (4 * MB)
+
+
+/*
+ * Tests the user interface. This test triggers most of the documented
+ * error conditions in mincore().
+ */
+TEST(basic_interface)
+{
+	int retval;
+	int page_size;
+	unsigned char vec[1];
+	char *addr;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	/* Query a 0 byte sized range */
+	retval = mincore(0, 0, vec);
+	EXPECT_EQ(0, retval);
+
+	/* Addresses in the specified range are invalid or unmapped */
+	errno = 0;
+	retval = mincore(NULL, page_size, vec);
+	EXPECT_EQ(-1, retval);
+	EXPECT_EQ(ENOMEM, errno);
+
+	errno = 0;
+	addr = mmap(NULL, page_size, PROT_READ | PROT_WRITE,
+		MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(MAP_FAILED, addr) {
+		TH_LOG("mmap error: %s", strerror(errno));
+	}
+
+	/* <addr> argument is not page-aligned */
+	errno = 0;
+	retval = mincore(addr + 1, page_size, vec);
+	EXPECT_EQ(-1, retval);
+	EXPECT_EQ(EINVAL, errno);
+
+	/* <length> argument is too large */
+	errno = 0;
+	retval = mincore(addr, -1, vec);
+	EXPECT_EQ(-1, retval);
+	EXPECT_EQ(ENOMEM, errno);
+
+	/* <vec> argument points to an illegal address */
+	errno = 0;
+	retval = mincore(addr, page_size, NULL);
+	EXPECT_EQ(-1, retval);
+	EXPECT_EQ(EFAULT, errno);
+	munmap(addr, page_size);
+}
+
+
+/*
+ * Test mincore() behavior on a private anonymous page mapping.
+ * Check that the page is not loaded into memory right after the mapping
+ * but after accessing it (on-demand allocation).
+ * Then free the page and check that it's not memory-resident.
+ */
+TEST(check_anonymous_locked_pages)
+{
+	unsigned char vec[1];
+	char *addr;
+	int retval;
+	int page_size;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	/* Map one page and check it's not memory-resident */
+	errno = 0;
+	addr = mmap(NULL, page_size, PROT_READ | PROT_WRITE,
+			MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(MAP_FAILED, addr) {
+		TH_LOG("mmap error: %s", strerror(errno));
+	}
+	retval = mincore(addr, page_size, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(0, vec[0]) {
+		TH_LOG("Page found in memory before use");
+	}
+
+	/* Touch the page and check again. It should now be in memory */
+	addr[0] = 1;
+	mlock(addr, page_size);
+	retval = mincore(addr, page_size, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(1, vec[0]) {
+		TH_LOG("Page not found in memory after use");
+	}
+
+	/*
+	 * It shouldn't be memory-resident after unlocking it and
+	 * marking it as unneeded.
+	 */
+	munlock(addr, page_size);
+	madvise(addr, page_size, MADV_DONTNEED);
+	retval = mincore(addr, page_size, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(0, vec[0]) {
+		TH_LOG("Page in memory after being zapped");
+	}
+	munmap(addr, page_size);
+}
+
+
+/*
+ * Check mincore() behavior on huge pages.
+ * This test will be skipped if the mapping fails (ie. if there are no
+ * huge pages available).
+ *
+ * Make sure the system has at least one free huge page, check
+ * "HugePages_Free" in /proc/meminfo.
+ * Increment /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages if
+ * needed.
+ */
+TEST(check_huge_pages)
+{
+	unsigned char vec[1];
+	char *addr;
+	int retval;
+	int page_size;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	errno = 0;
+	addr = mmap(NULL, page_size, PROT_READ | PROT_WRITE,
+		MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
+		-1, 0);
+	if (addr == MAP_FAILED) {
+		if (errno == ENOMEM)
+			SKIP(return, "No huge pages available.");
+		else
+			TH_LOG("mmap error: %s", strerror(errno));
+	}
+	retval = mincore(addr, page_size, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(0, vec[0]) {
+		TH_LOG("Page found in memory before use");
+	}
+
+	addr[0] = 1;
+	mlock(addr, page_size);
+	retval = mincore(addr, page_size, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(1, vec[0]) {
+		TH_LOG("Page not found in memory after use");
+	}
+
+	munlock(addr, page_size);
+	munmap(addr, page_size);
+}
+
+
+/*
+ * Test mincore() behavior on a file-backed page.
+ * No pages should be loaded into memory right after the mapping. Then,
+ * accessing any address in the mapping range should load the page
+ * containing the address and a number of subsequent pages (readahead).
+ *
+ * The actual readahead settings depend on the test environment, so we
+ * can't make a lot of assumptions about that. This test covers the most
+ * general cases.
+ */
+TEST(check_file_mmap)
+{
+	unsigned char *vec;
+	int vec_size;
+	char *addr;
+	int retval;
+	int page_size;
+	int fd;
+	int i;
+	int ra_pages = 0;
+
+	page_size = sysconf(_SC_PAGESIZE);
+	vec_size = FILE_SIZE / page_size;
+	if (FILE_SIZE % page_size)
+		vec_size++;
+
+	vec = calloc(vec_size, sizeof(unsigned char));
+	ASSERT_NE(NULL, vec) {
+		TH_LOG("Can't allocate array");
+	}
+
+	errno = 0;
+	fd = open(".", O_TMPFILE | O_RDWR, 0600);
+	ASSERT_NE(-1, fd) {
+		TH_LOG("Can't create temporary file: %s",
+			strerror(errno));
+	}
+	errno = 0;
+	retval = fallocate(fd, 0, 0, FILE_SIZE);
+	ASSERT_EQ(0, retval) {
+		TH_LOG("Error allocating space for the temporary file: %s",
+			strerror(errno));
+	}
+
+	/*
+	 * Map the whole file, the pages shouldn't be fetched yet.
+	 */
+	errno = 0;
+	addr = mmap(NULL, FILE_SIZE, PROT_READ | PROT_WRITE,
+			MAP_SHARED, fd, 0);
+	ASSERT_NE(MAP_FAILED, addr) {
+		TH_LOG("mmap error: %s", strerror(errno));
+	}
+	retval = mincore(addr, FILE_SIZE, vec);
+	ASSERT_EQ(0, retval);
+	for (i = 0; i < vec_size; i++) {
+		ASSERT_EQ(0, vec[i]) {
+			TH_LOG("Unexpected page in memory");
+		}
+	}
+
+	/*
+	 * Touch a page in the middle of the mapping. We expect the next
+	 * few pages (the readahead window) to be populated too.
+	 */
+	addr[FILE_SIZE / 2] = 1;
+	retval = mincore(addr, FILE_SIZE, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(1, vec[FILE_SIZE / 2 / page_size]) {
+		TH_LOG("Page not found in memory after use");
+	}
+
+	i = FILE_SIZE / 2 / page_size + 1;
+	while (i < vec_size && vec[i]) {
+		ra_pages++;
+		i++;
+	}
+	EXPECT_GT(ra_pages, 0) {
+		TH_LOG("No read-ahead pages found in memory");
+	}
+
+	EXPECT_LT(i, vec_size) {
+		TH_LOG("Read-ahead pages reached the end of the file");
+	}
+	/*
+	 * End of the readahead window. The rest of the pages shouldn't
+	 * be in memory.
+	 */
+	if (i < vec_size) {
+		while (i < vec_size && !vec[i])
+			i++;
+		EXPECT_EQ(vec_size, i) {
+			TH_LOG("Unexpected page in memory beyond readahead window");
+		}
+	}
+
+	munmap(addr, FILE_SIZE);
+	close(fd);
+	free(vec);
+}
+
+
+/*
+ * Test mincore() behavior on a page backed by a tmpfs file.  This test
+ * performs the same steps as the previous one. However, we don't expect
+ * any readahead in this case.
+ */
+TEST(check_tmpfs_mmap)
+{
+	unsigned char *vec;
+	int vec_size;
+	char *addr;
+	int retval;
+	int page_size;
+	int fd;
+	int i;
+	int ra_pages = 0;
+
+	page_size = sysconf(_SC_PAGESIZE);
+	vec_size = FILE_SIZE / page_size;
+	if (FILE_SIZE % page_size)
+		vec_size++;
+
+	vec = calloc(vec_size, sizeof(unsigned char));
+	ASSERT_NE(NULL, vec) {
+		TH_LOG("Can't allocate array");
+	}
+
+	errno = 0;
+	fd = open("/dev/shm", O_TMPFILE | O_RDWR, 0600);
+	ASSERT_NE(-1, fd) {
+		TH_LOG("Can't create temporary file: %s",
+			strerror(errno));
+	}
+	errno = 0;
+	retval = fallocate(fd, 0, 0, FILE_SIZE);
+	ASSERT_EQ(0, retval) {
+		TH_LOG("Error allocating space for the temporary file: %s",
+			strerror(errno));
+	}
+
+	/*
+	 * Map the whole file, the pages shouldn't be fetched yet.
+	 */
+	errno = 0;
+	addr = mmap(NULL, FILE_SIZE, PROT_READ | PROT_WRITE,
+			MAP_SHARED, fd, 0);
+	ASSERT_NE(MAP_FAILED, addr) {
+		TH_LOG("mmap error: %s", strerror(errno));
+	}
+	retval = mincore(addr, FILE_SIZE, vec);
+	ASSERT_EQ(0, retval);
+	for (i = 0; i < vec_size; i++) {
+		ASSERT_EQ(0, vec[i]) {
+			TH_LOG("Unexpected page in memory");
+		}
+	}
+
+	/*
+	 * Touch a page in the middle of the mapping. We expect only
+	 * that page to be fetched into memory.
+	 */
+	addr[FILE_SIZE / 2] = 1;
+	retval = mincore(addr, FILE_SIZE, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(1, vec[FILE_SIZE / 2 / page_size]) {
+		TH_LOG("Page not found in memory after use");
+	}
+
+	i = FILE_SIZE / 2 / page_size + 1;
+	while (i < vec_size && vec[i]) {
+		ra_pages++;
+		i++;
+	}
+	ASSERT_EQ(ra_pages, 0) {
+		TH_LOG("Read-ahead pages found in memory");
+	}
+
+	munmap(addr, FILE_SIZE);
+	close(fd);
+	free(vec);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 895ec992b2f1..9491bbaa0831 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -17,6 +17,8 @@ TEST_PROGS += route_localnet.sh
 TEST_PROGS += reuseaddr_ports_exhausted.sh
 TEST_PROGS += txtimestamp.sh
 TEST_PROGS += vrf-xfrm-tests.sh
+TEST_PROGS += rxtimestamp.sh
+TEST_PROGS += devlink_port_split.py
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py
new file mode 100755
index 000000000000..58bb7e9b88ce
--- /dev/null
+++ b/tools/testing/selftests/net/devlink_port_split.py
@@ -0,0 +1,277 @@
+#!/usr/bin/python3
+# SPDX-License-Identifier: GPL-2.0
+
+from subprocess import PIPE, Popen
+import json
+import time
+import argparse
+import collections
+import sys
+
+#
+# Test port split configuration using devlink-port lanes attribute.
+# The test is skipped in case the attribute is not available.
+#
+# First, check that all the ports with 1 lane fail to split.
+# Second, check that all the ports with more than 1 lane can be split
+# to all valid configurations (e.g., split to 2, split to 4 etc.)
+#
+
+
+Port = collections.namedtuple('Port', 'bus_info name')
+
+
+def run_command(cmd, should_fail=False):
+    """
+    Run a command in subprocess.
+    Return: Tuple of (stdout, stderr).
+    """
+
+    p = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True)
+    stdout, stderr = p.communicate()
+    stdout, stderr = stdout.decode(), stderr.decode()
+
+    if stderr != "" and not should_fail:
+        print("Error sending command: %s" % cmd)
+        print(stdout)
+        print(stderr)
+    return stdout, stderr
+
+
+class devlink_ports(object):
+    """
+    Class that holds information on the devlink ports, required to the tests;
+    if_names: A list of interfaces in the devlink ports.
+    """
+
+    def get_if_names(dev):
+        """
+        Get a list of physical devlink ports.
+        Return: Array of tuples (bus_info/port, if_name).
+        """
+
+        arr = []
+
+        cmd = "devlink -j port show"
+        stdout, stderr = run_command(cmd)
+        assert stderr == ""
+        ports = json.loads(stdout)['port']
+
+        for port in ports:
+            if dev in port:
+                if ports[port]['flavour'] == 'physical':
+                    arr.append(Port(bus_info=port, name=ports[port]['netdev']))
+
+        return arr
+
+    def __init__(self, dev):
+        self.if_names = devlink_ports.get_if_names(dev)
+
+
+def get_max_lanes(port):
+    """
+    Get the $port's maximum number of lanes.
+    Return: number of lanes, e.g. 1, 2, 4 and 8.
+    """
+
+    cmd = "devlink -j port show %s" % port
+    stdout, stderr = run_command(cmd)
+    assert stderr == ""
+    values = list(json.loads(stdout)['port'].values())[0]
+
+    if 'lanes' in values:
+        lanes = values['lanes']
+    else:
+        lanes = 0
+    return lanes
+
+
+def get_split_ability(port):
+    """
+    Get the $port split ability.
+    Return: split ability, true or false.
+    """
+
+    cmd = "devlink -j port show %s" % port.name
+    stdout, stderr = run_command(cmd)
+    assert stderr == ""
+    values = list(json.loads(stdout)['port'].values())[0]
+
+    return values['splittable']
+
+
+def split(k, port, should_fail=False):
+    """
+    Split $port into $k ports.
+    If should_fail == True, the split should fail. Otherwise, should pass.
+    Return: Array of sub ports after splitting.
+            If the $port wasn't split, the array will be empty.
+    """
+
+    cmd = "devlink port split %s count %s" % (port.bus_info, k)
+    stdout, stderr = run_command(cmd, should_fail=should_fail)
+
+    if should_fail:
+        if not test(stderr != "", "%s is unsplittable" % port.name):
+            print("split an unsplittable port %s" % port.name)
+            return create_split_group(port, k)
+    else:
+        if stderr == "":
+            return create_split_group(port, k)
+        print("didn't split a splittable port %s" % port.name)
+
+    return []
+
+
+def unsplit(port):
+    """
+    Unsplit $port.
+    """
+
+    cmd = "devlink port unsplit %s" % port
+    stdout, stderr = run_command(cmd)
+    test(stderr == "", "Unsplit port %s" % port)
+
+
+def exists(port, dev):
+    """
+    Check if $port exists in the devlink ports.
+    Return: True is so, False otherwise.
+    """
+
+    return any(dev_port.name == port
+               for dev_port in devlink_ports.get_if_names(dev))
+
+
+def exists_and_lanes(ports, lanes, dev):
+    """
+    Check if every port in the list $ports exists in the devlink ports and has
+    $lanes number of lanes after splitting.
+    Return: True if both are True, False otherwise.
+    """
+
+    for port in ports:
+        max_lanes = get_max_lanes(port)
+        if not exists(port, dev):
+            print("port %s doesn't exist in devlink ports" % port)
+            return False
+        if max_lanes != lanes:
+            print("port %s has %d lanes, but %s were expected"
+                  % (port, lanes, max_lanes))
+            return False
+    return True
+
+
+def test(cond, msg):
+    """
+    Check $cond and print a message accordingly.
+    Return: True is pass, False otherwise.
+    """
+
+    if cond:
+        print("TEST: %-60s [ OK ]" % msg)
+    else:
+        print("TEST: %-60s [FAIL]" % msg)
+
+    return cond
+
+
+def create_split_group(port, k):
+    """
+    Create the split group for $port.
+    Return: Array with $k elements, which are the split port group.
+    """
+
+    return list(port.name + "s" + str(i) for i in range(k))
+
+
+def split_unsplittable_port(port, k):
+    """
+    Test that splitting of unsplittable port fails.
+    """
+
+    # split to max
+    new_split_group = split(k, port, should_fail=True)
+
+    if new_split_group != []:
+        unsplit(port.bus_info)
+
+
+def split_splittable_port(port, k, lanes, dev):
+    """
+    Test that splitting of splittable port passes correctly.
+    """
+
+    new_split_group = split(k, port)
+
+    # Once the split command ends, it takes some time to the sub ifaces'
+    # to get their names. Use udevadm to continue only when all current udev
+    # events are handled.
+    cmd = "udevadm settle"
+    stdout, stderr = run_command(cmd)
+    assert stderr == ""
+
+    if new_split_group != []:
+        test(exists_and_lanes(new_split_group, lanes/k, dev),
+             "split port %s into %s" % (port.name, k))
+
+    unsplit(port.bus_info)
+
+
+def make_parser():
+    parser = argparse.ArgumentParser(description='A test for port splitting.')
+    parser.add_argument('--dev',
+                        help='The devlink handle of the device under test. ' +
+                             'The default is the first registered devlink ' +
+                             'handle.')
+
+    return parser
+
+
+def main(cmdline=None):
+    parser = make_parser()
+    args = parser.parse_args(cmdline)
+
+    dev = args.dev
+    if not dev:
+        cmd = "devlink -j dev show"
+        stdout, stderr = run_command(cmd)
+        assert stderr == ""
+
+        devs = json.loads(stdout)['dev']
+        dev = list(devs.keys())[0]
+
+    cmd = "devlink dev show %s" % dev
+    stdout, stderr = run_command(cmd)
+    if stderr != "":
+        print("devlink device %s can not be found" % dev)
+        sys.exit(1)
+
+    ports = devlink_ports(dev)
+
+    for port in ports.if_names:
+        max_lanes = get_max_lanes(port.name)
+
+        # If max lanes is 0, do not test port splitting at all
+        if max_lanes == 0:
+            continue
+
+        # If 1 lane, shouldn't be able to split
+        elif max_lanes == 1:
+            test(not get_split_ability(port),
+                 "%s should not be able to split" % port.name)
+            split_unsplittable_port(port, max_lanes)
+
+        # Else, splitting should pass and all the split ports should exist.
+        else:
+            lane = max_lanes
+            test(get_split_ability(port),
+                 "%s should be able to split" % port.name)
+            while lane > 1:
+                split_splittable_port(port, lane, max_lanes, dev)
+
+                lane //= 2
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
index f0e6be4c09e9..75fe24bcb9cd 100644
--- a/tools/testing/selftests/net/forwarding/devlink_lib.sh
+++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
@@ -98,6 +98,11 @@ devlink_resource_size_set()
 	check_err $? "Failed setting path $path to size $size"
 }
 
+devlink_resource_occ_get()
+{
+	devlink_resource_get "$@" | jq '.["occ"]'
+}
+
 devlink_reload()
 {
 	local still_pending
diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh
index eb8e2a23bbb4..dbb9fcf759e0 100755
--- a/tools/testing/selftests/net/forwarding/ethtool.sh
+++ b/tools/testing/selftests/net/forwarding/ethtool.sh
@@ -50,23 +50,6 @@ cleanup()
 	h1_destroy
 }
 
-different_speeds_get()
-{
-	local dev1=$1; shift
-	local dev2=$1; shift
-	local with_mode=$1; shift
-	local adver=$1; shift
-
-	local -a speeds_arr
-
-	speeds_arr=($(common_speeds_get $dev1 $dev2 $with_mode $adver))
-	if [[ ${#speeds_arr[@]} < 2 ]]; then
-		check_err 1 "cannot check different speeds. There are not enough speeds"
-	fi
-
-	echo ${speeds_arr[0]} ${speeds_arr[1]}
-}
-
 same_speeds_autoneg_off()
 {
 	# Check that when each of the reported speeds is forced, the links come
@@ -252,8 +235,6 @@ check_highest_speed_is_chosen()
 	fi
 
 	local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1))
-	# Remove the first speed, h1 does not advertise this speed.
-	unset speeds_arr[0]
 
 	max_speed=${speeds_arr[0]}
 	for current in ${speeds_arr[@]}; do
diff --git a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh
new file mode 100755
index 000000000000..4b42dfd4efd1
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh
@@ -0,0 +1,102 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	autoneg
+	autoneg_force_mode
+	no_cable
+"
+
+NUM_NETIFS=2
+source lib.sh
+source ethtool_lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+	swp3=$NETIF_NO_CABLE
+}
+
+ethtool_extended_state_check()
+{
+	local dev=$1; shift
+	local expected_ext_state=$1; shift
+	local expected_ext_substate=${1:-""}; shift
+
+	local ext_state=$(ethtool $dev | grep "Link detected" \
+		| cut -d "(" -f2 | cut -d ")" -f1)
+	local ext_substate=$(echo $ext_state | cut -sd "," -f2 \
+		| sed -e 's/^[[:space:]]*//')
+	ext_state=$(echo $ext_state | cut -d "," -f1)
+
+	[[ $ext_state == $expected_ext_state ]]
+	check_err $? "Expected \"$expected_ext_state\", got \"$ext_state\""
+
+	[[ $ext_substate == $expected_ext_substate ]]
+	check_err $? "Expected \"$expected_ext_substate\", got \"$ext_substate\""
+}
+
+autoneg()
+{
+	RET=0
+
+	ip link set dev $swp1 up
+
+	sleep 4
+	ethtool_extended_state_check $swp1 "Autoneg" "No partner detected"
+
+	log_test "Autoneg, No partner detected"
+
+	ip link set dev $swp1 down
+}
+
+autoneg_force_mode()
+{
+	RET=0
+
+	ip link set dev $swp1 up
+	ip link set dev $swp2 up
+
+	local -a speeds_arr=($(different_speeds_get $swp1 $swp2 0 0))
+	local speed1=${speeds_arr[0]}
+	local speed2=${speeds_arr[1]}
+
+	ethtool_set $swp1 speed $speed1 autoneg off
+	ethtool_set $swp2 speed $speed2 autoneg off
+
+	sleep 4
+	ethtool_extended_state_check $swp1 "Autoneg" \
+		"No partner detected during force mode"
+
+	ethtool_extended_state_check $swp2 "Autoneg" \
+		"No partner detected during force mode"
+
+	log_test "Autoneg, No partner detected during force mode"
+
+	ethtool -s $swp2 autoneg on
+	ethtool -s $swp1 autoneg on
+
+	ip link set dev $swp2 down
+	ip link set dev $swp1 down
+}
+
+no_cable()
+{
+	RET=0
+
+	ip link set dev $swp3 up
+
+	sleep 1
+	ethtool_extended_state_check $swp3 "No cable"
+
+	log_test "No cable"
+
+	ip link set dev $swp3 down
+}
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/ethtool_lib.sh b/tools/testing/selftests/net/forwarding/ethtool_lib.sh
index 925d229a59d8..9188e624dec0 100644
--- a/tools/testing/selftests/net/forwarding/ethtool_lib.sh
+++ b/tools/testing/selftests/net/forwarding/ethtool_lib.sh
@@ -67,3 +67,20 @@ common_speeds_get()
 		<(printf '%s\n' "${dev1_speeds[@]}" | sort -u) \
 		<(printf '%s\n' "${dev2_speeds[@]}" | sort -u)
 }
+
+different_speeds_get()
+{
+	local dev1=$1; shift
+	local dev2=$1; shift
+	local with_mode=$1; shift
+	local adver=$1; shift
+
+	local -a speeds_arr
+
+	speeds_arr=($(common_speeds_get $dev1 $dev2 $with_mode $adver))
+	if [[ ${#speeds_arr[@]} < 2 ]]; then
+		check_err 1 "cannot check different speeds. There are not enough speeds"
+	fi
+
+	echo ${speeds_arr[0]} ${speeds_arr[1]}
+}
diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample
index e2adb533c8fc..b802c14d2950 100644
--- a/tools/testing/selftests/net/forwarding/forwarding.config.sample
+++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample
@@ -14,6 +14,9 @@ NETIFS[p6]=veth5
 NETIFS[p7]=veth6
 NETIFS[p8]=veth7
 
+# Port that does not have a cable connected.
+NETIF_NO_CABLE=eth8
+
 ##############################################################################
 # Defines
 
diff --git a/tools/testing/selftests/net/forwarding/pedit_l4port.sh b/tools/testing/selftests/net/forwarding/pedit_l4port.sh
new file mode 100755
index 000000000000..5f20d289ee43
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/pedit_l4port.sh
@@ -0,0 +1,198 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test sends traffic from H1 to H2. Either on ingress of $swp1, or on egress of $swp2, the
+# traffic is acted upon by a pedit action. An ingress filter installed on $h2 verifies that the
+# packet looks like expected.
+#
+# +----------------------+                             +----------------------+
+# | H1                   |                             |                   H2 |
+# |    + $h1             |                             |            $h2 +     |
+# |    | 192.0.2.1/28    |                             |   192.0.2.2/28 |     |
+# +----|-----------------+                             +----------------|-----+
+#      |                                                                |
+# +----|----------------------------------------------------------------|-----+
+# | SW |                                                                |     |
+# |  +-|----------------------------------------------------------------|-+   |
+# |  | + $swp1                       BR                           $swp2 + |   |
+# |  +--------------------------------------------------------------------+   |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	test_udp_sport
+	test_udp_dport
+	test_tcp_sport
+	test_tcp_dport
+"
+
+NUM_NETIFS=4
+source lib.sh
+source tc_common.sh
+
+: ${HIT_TIMEOUT:=2000} # ms
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64
+	tc qdisc add dev $h2 clsact
+}
+
+h2_destroy()
+{
+	tc qdisc del dev $h2 clsact
+	simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64
+}
+
+switch_create()
+{
+	ip link add name br1 up type bridge vlan_filtering 1
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+	ip link set dev $swp2 master br1
+	ip link set dev $swp2 up
+
+	tc qdisc add dev $swp1 clsact
+	tc qdisc add dev $swp2 clsact
+}
+
+switch_destroy()
+{
+	tc qdisc del dev $swp2 clsact
+	tc qdisc del dev $swp1 clsact
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 nomaster
+	ip link del dev br1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	h2mac=$(mac_get $h2)
+
+	vrf_prepare
+	h1_create
+	h2_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.2
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:1::2
+}
+
+do_test_pedit_l4port_one()
+{
+	local pedit_locus=$1; shift
+	local pedit_prot=$1; shift
+	local pedit_action=$1; shift
+	local match_prot=$1; shift
+	local match_flower=$1; shift
+	local mz_flags=$1; shift
+	local saddr=$1; shift
+	local daddr=$1; shift
+
+	tc filter add $pedit_locus handle 101 pref 1 \
+	   flower action pedit ex munge $pedit_action
+	tc filter add dev $h2 ingress handle 101 pref 1 prot $match_prot \
+	   flower skip_hw $match_flower action pass
+
+	RET=0
+
+	$MZ $mz_flags $h1 -c 10 -d 20msec -p 100 \
+	    -a own -b $h2mac -q -t $pedit_prot sp=54321,dp=12345
+
+	local pkts
+	pkts=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= 10" \
+			tc_rule_handle_stats_get "dev $h2 ingress" 101)
+	check_err $? "Expected to get 10 packets, but got $pkts."
+
+	pkts=$(tc_rule_handle_stats_get "$pedit_locus" 101)
+	((pkts >= 10))
+	check_err $? "Expected to get 10 packets on pedit rule, but got $pkts."
+
+	log_test "$pedit_locus pedit $pedit_action"
+
+	tc filter del dev $h2 ingress pref 1
+	tc filter del $pedit_locus pref 1
+}
+
+do_test_pedit_l4port()
+{
+	local locus=$1; shift
+	local prot=$1; shift
+	local pedit_port=$1; shift
+	local flower_port=$1; shift
+	local port
+
+	for port in 1 11111 65535; do
+		do_test_pedit_l4port_one "$locus" "$prot"			\
+					 "$prot $pedit_port set $port"		\
+					 ip "ip_proto $prot $flower_port $port"	\
+					 "-A 192.0.2.1 -B 192.0.2.2"
+	done
+}
+
+test_udp_sport()
+{
+	do_test_pedit_l4port "dev $swp1 ingress" udp sport src_port
+	do_test_pedit_l4port "dev $swp2 egress"  udp sport src_port
+}
+
+test_udp_dport()
+{
+	do_test_pedit_l4port "dev $swp1 ingress" udp dport dst_port
+	do_test_pedit_l4port "dev $swp2 egress"  udp dport dst_port
+}
+
+test_tcp_sport()
+{
+	do_test_pedit_l4port "dev $swp1 ingress" tcp sport src_port
+	do_test_pedit_l4port "dev $swp2 egress"  tcp sport src_port
+}
+
+test_tcp_dport()
+{
+	do_test_pedit_l4port "dev $swp1 ingress" tcp dport dst_port
+	do_test_pedit_l4port "dev $swp2 egress"  tcp dport dst_port
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/sch_red.sh b/tools/testing/selftests/net/forwarding/sch_red.sh
new file mode 100755
index 000000000000..e714bae473fb
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/sch_red.sh
@@ -0,0 +1,492 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# This test sends one stream of traffic from H1 through a TBF shaper, to a RED
+# within TBF shaper on $swp3. The two shapers have the same configuration, and
+# thus the resulting stream should fill all available bandwidth on the latter
+# shaper. A second stream is sent from H2 also via $swp3, and used to inject
+# additional traffic. Since all available bandwidth is taken, this traffic has
+# to go to backlog.
+#
+# +--------------------------+                     +--------------------------+
+# | H1                       |                     | H2                       |
+# |     + $h1                |                     |     + $h2                |
+# |     | 192.0.2.1/28       |                     |     | 192.0.2.2/28       |
+# |     | TBF 10Mbps         |                     |     |                    |
+# +-----|--------------------+                     +-----|--------------------+
+#       |                                                |
+# +-----|------------------------------------------------|--------------------+
+# | SW  |                                                |                    |
+# |  +--|------------------------------------------------|----------------+   |
+# |  |  + $swp1                                          + $swp2          |   |
+# |  |                               BR                                   |   |
+# |  |                                                                    |   |
+# |  |                                + $swp3                             |   |
+# |  |                                | TBF 10Mbps / RED                  |   |
+# |  +--------------------------------|-----------------------------------+   |
+# |                                   |                                       |
+# +-----------------------------------|---------------------------------------+
+#                                     |
+#                               +-----|--------------------+
+#			        | H3  |                    |
+#			        |     + $h1                |
+#			        |       192.0.2.3/28       |
+#			        |                          |
+#			        +--------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ecn_test
+	ecn_nodrop_test
+	red_test
+	red_qevent_test
+	ecn_qevent_test
+"
+
+NUM_NETIFS=6
+CHECK_TC="yes"
+source lib.sh
+
+BACKLOG=30000
+PKTSZ=1400
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28
+	mtu_set $h1 10000
+	tc qdisc replace dev $h1 root handle 1: tbf \
+	   rate 10Mbit burst 10K limit 1M
+}
+
+h1_destroy()
+{
+	tc qdisc del dev $h1 root
+	mtu_restore $h1
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/28
+	mtu_set $h2 10000
+}
+
+h2_destroy()
+{
+	mtu_restore $h2
+	simple_if_fini $h2 192.0.2.2/28
+}
+
+h3_create()
+{
+	simple_if_init $h3 192.0.2.3/28
+	mtu_set $h3 10000
+}
+
+h3_destroy()
+{
+	mtu_restore $h3
+	simple_if_fini $h3 192.0.2.3/28
+}
+
+switch_create()
+{
+	ip link add dev br up type bridge
+	ip link set dev $swp1 up master br
+	ip link set dev $swp2 up master br
+	ip link set dev $swp3 up master br
+
+	mtu_set $swp1 10000
+	mtu_set $swp2 10000
+	mtu_set $swp3 10000
+
+	tc qdisc replace dev $swp3 root handle 1: tbf \
+	   rate 10Mbit burst 10K limit 1M
+	ip link add name _drop_test up type dummy
+}
+
+switch_destroy()
+{
+	ip link del dev _drop_test
+	tc qdisc del dev $swp3 root
+
+	mtu_restore $h3
+	mtu_restore $h2
+	mtu_restore $h1
+
+	ip link set dev $swp3 down nomaster
+	ip link set dev $swp2 down nomaster
+	ip link set dev $swp1 down nomaster
+	ip link del dev br
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	h2=${NETIFS[p3]}
+	swp2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	h3_mac=$(mac_get $h3)
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	h3_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h3_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.3 " from host 1"
+	ping_test $h2 192.0.2.3 " from host 2"
+}
+
+get_qdisc_backlog()
+{
+	qdisc_stats_get $swp3 11: .backlog
+}
+
+get_nmarked()
+{
+	qdisc_stats_get $swp3 11: .marked
+}
+
+get_qdisc_npackets()
+{
+	qdisc_stats_get $swp3 11: .packets
+}
+
+get_nmirrored()
+{
+	link_stats_get _drop_test tx packets
+}
+
+send_packets()
+{
+	local proto=$1; shift
+	local pkts=$1; shift
+
+	$MZ $h2 -p $PKTSZ -a own -b $h3_mac -A 192.0.2.2 -B 192.0.2.3 -t $proto -q -c $pkts "$@"
+}
+
+# This sends traffic in an attempt to build a backlog of $size. Returns 0 on
+# success. After 10 failed attempts it bails out and returns 1. It dumps the
+# backlog size to stdout.
+build_backlog()
+{
+	local size=$1; shift
+	local proto=$1; shift
+
+	local i=0
+
+	while :; do
+		local cur=$(get_qdisc_backlog)
+		local diff=$((size - cur))
+		local pkts=$(((diff + PKTSZ - 1) / PKTSZ))
+
+		if ((cur >= size)); then
+			echo $cur
+			return 0
+		elif ((i++ > 10)); then
+			echo $cur
+			return 1
+		fi
+
+		send_packets $proto $pkts "$@"
+		sleep 1
+	done
+}
+
+check_marking()
+{
+	local cond=$1; shift
+
+	local npackets_0=$(get_qdisc_npackets)
+	local nmarked_0=$(get_nmarked)
+	sleep 5
+	local npackets_1=$(get_qdisc_npackets)
+	local nmarked_1=$(get_nmarked)
+
+	local nmarked_d=$((nmarked_1 - nmarked_0))
+	local npackets_d=$((npackets_1 - npackets_0))
+	local pct=$((100 * nmarked_d / npackets_d))
+
+	echo $pct
+	((pct $cond))
+}
+
+check_mirroring()
+{
+	local cond=$1; shift
+
+	local npackets_0=$(get_qdisc_npackets)
+	local nmirrored_0=$(get_nmirrored)
+	sleep 5
+	local npackets_1=$(get_qdisc_npackets)
+	local nmirrored_1=$(get_nmirrored)
+
+	local nmirrored_d=$((nmirrored_1 - nmirrored_0))
+	local npackets_d=$((npackets_1 - npackets_0))
+	local pct=$((100 * nmirrored_d / npackets_d))
+
+	echo $pct
+	((pct $cond))
+}
+
+ecn_test_common()
+{
+	local name=$1; shift
+	local limit=$1; shift
+	local backlog
+	local pct
+
+	# Build the below-the-limit backlog using UDP. We could use TCP just
+	# fine, but this way we get a proof that UDP is accepted when queue
+	# length is below the limit. The main stream is using TCP, and if the
+	# limit is misconfigured, we would see this traffic being ECN marked.
+	RET=0
+	backlog=$(build_backlog $((2 * limit / 3)) udp)
+	check_err $? "Could not build the requested backlog"
+	pct=$(check_marking "== 0")
+	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
+	log_test "$name backlog < limit"
+
+	# Now push TCP, because non-TCP traffic would be early-dropped after the
+	# backlog crosses the limit, and we want to make sure that the backlog
+	# is above the limit.
+	RET=0
+	backlog=$(build_backlog $((3 * limit / 2)) tcp tos=0x01)
+	check_err $? "Could not build the requested backlog"
+	pct=$(check_marking ">= 95")
+	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95."
+	log_test "$name backlog > limit"
+}
+
+do_ecn_test()
+{
+	local limit=$1; shift
+	local name=ECN
+
+	$MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \
+		-a own -b $h3_mac -t tcp -q tos=0x01 &
+	sleep 1
+
+	ecn_test_common "$name" $limit
+
+	# Up there we saw that UDP gets accepted when backlog is below the
+	# limit. Now that it is above, it should all get dropped, and backlog
+	# building should fail.
+	RET=0
+	build_backlog $((2 * limit)) udp >/dev/null
+	check_fail $? "UDP traffic went into backlog instead of being early-dropped"
+	log_test "$name backlog > limit: UDP early-dropped"
+
+	stop_traffic
+	sleep 1
+}
+
+do_ecn_nodrop_test()
+{
+	local limit=$1; shift
+	local name="ECN nodrop"
+
+	$MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \
+		-a own -b $h3_mac -t tcp -q tos=0x01 &
+	sleep 1
+
+	ecn_test_common "$name" $limit
+
+	# Up there we saw that UDP gets accepted when backlog is below the
+	# limit. Now that it is above, in nodrop mode, make sure it goes to
+	# backlog as well.
+	RET=0
+	build_backlog $((2 * limit)) udp >/dev/null
+	check_err $? "UDP traffic was early-dropped instead of getting into backlog"
+	log_test "$name backlog > limit: UDP not dropped"
+
+	stop_traffic
+	sleep 1
+}
+
+do_red_test()
+{
+	local limit=$1; shift
+	local backlog
+	local pct
+
+	# Use ECN-capable TCP to verify there's no marking even though the queue
+	# is above limit.
+	$MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \
+		-a own -b $h3_mac -t tcp -q tos=0x01 &
+
+	# Pushing below the queue limit should work.
+	RET=0
+	backlog=$(build_backlog $((2 * limit / 3)) tcp tos=0x01)
+	check_err $? "Could not build the requested backlog"
+	pct=$(check_marking "== 0")
+	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
+	log_test "RED backlog < limit"
+
+	# Pushing above should not.
+	RET=0
+	backlog=$(build_backlog $((3 * limit / 2)) tcp tos=0x01)
+	check_fail $? "Traffic went into backlog instead of being early-dropped"
+	pct=$(check_marking "== 0")
+	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
+	log_test "RED backlog > limit"
+
+	stop_traffic
+	sleep 1
+}
+
+do_red_qevent_test()
+{
+	local limit=$1; shift
+	local backlog
+	local base
+	local now
+	local pct
+
+	RET=0
+
+	$MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \
+		-a own -b $h3_mac -t udp -q &
+	sleep 1
+
+	tc filter add block 10 pref 1234 handle 102 matchall skip_hw \
+	   action mirred egress mirror dev _drop_test
+
+	# Push to the queue until it's at the limit. The configured limit is
+	# rounded by the qdisc, so this is the best we can do to get to the real
+	# limit.
+	build_backlog $((3 * limit / 2)) udp >/dev/null
+
+	base=$(get_nmirrored)
+	send_packets udp 100
+	sleep 1
+	now=$(get_nmirrored)
+	((now >= base + 100))
+	check_err $? "Dropped packets not observed: 100 expected, $((now - base)) seen"
+
+	tc filter del block 10 pref 1234 handle 102 matchall
+
+	base=$(get_nmirrored)
+	send_packets udp 100
+	sleep 1
+	now=$(get_nmirrored)
+	((now == base))
+	check_err $? "Dropped packets still observed: 0 expected, $((now - base)) seen"
+
+	log_test "RED early_dropped packets mirrored"
+
+	stop_traffic
+	sleep 1
+}
+
+do_ecn_qevent_test()
+{
+	local limit=$1; shift
+	local name=ECN
+
+	RET=0
+
+	$MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \
+		-a own -b $h3_mac -t tcp -q tos=0x01 &
+	sleep 1
+
+	tc filter add block 10 pref 1234 handle 102 matchall skip_hw \
+	   action mirred egress mirror dev _drop_test
+
+	backlog=$(build_backlog $((2 * limit / 3)) tcp tos=0x01)
+	check_err $? "Could not build the requested backlog"
+	pct=$(check_mirroring "== 0")
+	check_err $? "backlog $backlog / $limit Got $pct% mirrored packets, expected == 0."
+
+	backlog=$(build_backlog $((3 * limit / 2)) tcp tos=0x01)
+	check_err $? "Could not build the requested backlog"
+	pct=$(check_mirroring ">= 95")
+	check_err $? "backlog $backlog / $limit Got $pct% mirrored packets, expected >= 95."
+
+	tc filter del block 10 pref 1234 handle 102 matchall
+
+	log_test "ECN marked packets mirrored"
+
+	stop_traffic
+	sleep 1
+}
+
+install_qdisc()
+{
+	local -a args=("$@")
+
+	tc qdisc replace dev $swp3 parent 1:1 handle 11: red \
+	   limit 1M avpkt $PKTSZ probability 1 \
+	   min $BACKLOG max $((BACKLOG + 1)) burst 38 "${args[@]}"
+	sleep 1
+}
+
+uninstall_qdisc()
+{
+	tc qdisc del dev $swp3 parent 1:1
+}
+
+ecn_test()
+{
+	install_qdisc ecn
+	do_ecn_test $BACKLOG
+	uninstall_qdisc
+}
+
+ecn_nodrop_test()
+{
+	install_qdisc ecn nodrop
+	do_ecn_nodrop_test $BACKLOG
+	uninstall_qdisc
+}
+
+red_test()
+{
+	install_qdisc
+	do_red_test $BACKLOG
+	uninstall_qdisc
+}
+
+red_qevent_test()
+{
+	install_qdisc qevent early_drop block 10
+	do_red_qevent_test $BACKLOG
+	uninstall_qdisc
+}
+
+ecn_qevent_test()
+{
+	install_qdisc ecn qevent mark block 10
+	do_ecn_qevent_test $BACKLOG
+	uninstall_qdisc
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh
new file mode 100755
index 000000000000..160f9cccdfb7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/tc_police.sh
@@ -0,0 +1,333 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test tc-police action.
+#
+# +---------------------------------+
+# | H1 (vrf)                        |
+# |    + $h1                        |
+# |    | 192.0.2.1/24               |
+# |    |                            |
+# |    |  default via 192.0.2.2     |
+# +----|----------------------------+
+#      |
+# +----|----------------------------------------------------------------------+
+# | SW |                                                                      |
+# |    + $rp1                                                                 |
+# |        192.0.2.2/24                                                       |
+# |                                                                           |
+# |        198.51.100.2/24                           203.0.113.2/24           |
+# |    + $rp2                                    + $rp3                       |
+# |    |                                         |                            |
+# +----|-----------------------------------------|----------------------------+
+#      |                                         |
+# +----|----------------------------+       +----|----------------------------+
+# |    |  default via 198.51.100.2  |       |    |  default via 203.0.113.2   |
+# |    |                            |       |    |                            |
+# |    | 198.51.100.1/24            |       |    | 203.0.113.1/24             |
+# |    + $h2                        |       |    + $h3                        |
+# | H2 (vrf)                        |       | H3 (vrf)                        |
+# +---------------------------------+       +---------------------------------+
+
+ALL_TESTS="
+	police_rx_test
+	police_tx_test
+	police_shared_test
+	police_rx_mirror_test
+	police_tx_mirror_test
+"
+NUM_NETIFS=6
+source tc_common.sh
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/24
+
+	ip -4 route add default vrf v$h1 nexthop via 192.0.2.2
+}
+
+h1_destroy()
+{
+	ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
+
+	simple_if_fini $h1 192.0.2.1/24
+}
+
+h2_create()
+{
+	simple_if_init $h2 198.51.100.1/24
+
+	ip -4 route add default vrf v$h2 nexthop via 198.51.100.2
+
+	tc qdisc add dev $h2 clsact
+}
+
+h2_destroy()
+{
+	tc qdisc del dev $h2 clsact
+
+	ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
+
+	simple_if_fini $h2 198.51.100.1/24
+}
+
+h3_create()
+{
+	simple_if_init $h3 203.0.113.1/24
+
+	ip -4 route add default vrf v$h3 nexthop via 203.0.113.2
+
+	tc qdisc add dev $h3 clsact
+}
+
+h3_destroy()
+{
+	tc qdisc del dev $h3 clsact
+
+	ip -4 route del default vrf v$h3 nexthop via 203.0.113.2
+
+	simple_if_fini $h3 203.0.113.1/24
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	ip link set dev $rp2 up
+	ip link set dev $rp3 up
+
+	__addr_add_del $rp1 add 192.0.2.2/24
+	__addr_add_del $rp2 add 198.51.100.2/24
+	__addr_add_del $rp3 add 203.0.113.2/24
+
+	tc qdisc add dev $rp1 clsact
+	tc qdisc add dev $rp2 clsact
+}
+
+router_destroy()
+{
+	tc qdisc del dev $rp2 clsact
+	tc qdisc del dev $rp1 clsact
+
+	__addr_add_del $rp3 del 203.0.113.2/24
+	__addr_add_del $rp2 del 198.51.100.2/24
+	__addr_add_del $rp1 del 192.0.2.2/24
+
+	ip link set dev $rp3 down
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
+}
+
+police_common_test()
+{
+	local test_name=$1; shift
+
+	RET=0
+
+	# Rule to measure bandwidth on ingress of $h2
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+		action drop
+
+	mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \
+		-t udp sp=12345,dp=54321 -p 1000 -c 0 -q &
+
+	local t0=$(tc_rule_stats_get $h2 1 ingress .bytes)
+	sleep 10
+	local t1=$(tc_rule_stats_get $h2 1 ingress .bytes)
+
+	local er=$((80 * 1000 * 1000))
+	local nr=$(rate $t0 $t1 10)
+	local nr_pct=$((100 * (nr - er) / er))
+	((-10 <= nr_pct && nr_pct <= 10))
+	check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%."
+
+	log_test "$test_name"
+
+	{ kill %% && wait %%; } 2>/dev/null
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+}
+
+police_rx_test()
+{
+	# Rule to police traffic destined to $h2 on ingress of $rp1
+	tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+		action police rate 80mbit burst 16k conform-exceed drop/ok
+
+	police_common_test "police on rx"
+
+	tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower
+}
+
+police_tx_test()
+{
+	# Rule to police traffic destined to $h2 on egress of $rp2
+	tc filter add dev $rp2 egress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+		action police rate 80mbit burst 16k conform-exceed drop/ok
+
+	police_common_test "police on tx"
+
+	tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+}
+
+police_shared_common_test()
+{
+	local dport=$1; shift
+	local test_name=$1; shift
+
+	RET=0
+
+	mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \
+		-t udp sp=12345,dp=$dport -p 1000 -c 0 -q &
+
+	local t0=$(tc_rule_stats_get $h2 1 ingress .bytes)
+	sleep 10
+	local t1=$(tc_rule_stats_get $h2 1 ingress .bytes)
+
+	local er=$((80 * 1000 * 1000))
+	local nr=$(rate $t0 $t1 10)
+	local nr_pct=$((100 * (nr - er) / er))
+	((-10 <= nr_pct && nr_pct <= 10))
+	check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%."
+
+	log_test "$test_name"
+
+	{ kill %% && wait %%; } 2>/dev/null
+}
+
+police_shared_test()
+{
+	# Rule to measure bandwidth on ingress of $h2
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp src_port 12345 \
+		action drop
+
+	# Rule to police traffic destined to $h2 on ingress of $rp1
+	tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+		action police rate 80mbit burst 16k conform-exceed drop/ok \
+		index 10
+
+	# Rule to police a different flow destined to $h2 on egress of $rp2
+	# using same policer
+	tc filter add dev $rp2 egress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 22222 \
+		action police index 10
+
+	police_shared_common_test 54321 "police with shared policer - rx"
+
+	police_shared_common_test 22222 "police with shared policer - tx"
+
+	tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+	tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+}
+
+police_mirror_common_test()
+{
+	local pol_if=$1; shift
+	local dir=$1; shift
+	local test_name=$1; shift
+
+	RET=0
+
+	# Rule to measure bandwidth on ingress of $h2
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+		action drop
+
+	# Rule to measure bandwidth of mirrored traffic on ingress of $h3
+	tc filter add dev $h3 ingress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+		action drop
+
+	# Rule to police traffic destined to $h2 and mirror to $h3
+	tc filter add dev $pol_if $dir protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+		action police rate 80mbit burst 16k conform-exceed drop/pipe \
+		action mirred egress mirror dev $rp3
+
+	mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \
+		-t udp sp=12345,dp=54321 -p 1000 -c 0 -q &
+
+	local t0=$(tc_rule_stats_get $h2 1 ingress .bytes)
+	sleep 10
+	local t1=$(tc_rule_stats_get $h2 1 ingress .bytes)
+
+	local er=$((80 * 1000 * 1000))
+	local nr=$(rate $t0 $t1 10)
+	local nr_pct=$((100 * (nr - er) / er))
+	((-10 <= nr_pct && nr_pct <= 10))
+	check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%."
+
+	local t0=$(tc_rule_stats_get $h3 1 ingress .bytes)
+	sleep 10
+	local t1=$(tc_rule_stats_get $h3 1 ingress .bytes)
+
+	local er=$((80 * 1000 * 1000))
+	local nr=$(rate $t0 $t1 10)
+	local nr_pct=$((100 * (nr - er) / er))
+	((-10 <= nr_pct && nr_pct <= 10))
+	check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%."
+
+	log_test "$test_name"
+
+	{ kill %% && wait %%; } 2>/dev/null
+	tc filter del dev $pol_if $dir protocol ip pref 1 handle 101 flower
+	tc filter del dev $h3 ingress protocol ip pref 1 handle 101 flower
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+}
+
+police_rx_mirror_test()
+{
+	police_mirror_common_test $rp1 ingress "police rx and mirror"
+}
+
+police_tx_mirror_test()
+{
+	police_mirror_common_test $rp2 egress "police tx and mirror"
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	forwarding_enable
+
+	h1_create
+	h2_create
+	h3_create
+	router_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	router_destroy
+	h3_destroy
+	h2_destroy
+	h1_destroy
+
+	forwarding_restore
+	vrf_cleanup
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh
index 18c5de53558a..bf361f30d6ef 100755
--- a/tools/testing/selftests/net/icmp_redirect.sh
+++ b/tools/testing/selftests/net/icmp_redirect.sh
@@ -180,6 +180,8 @@ setup()
 			;;
 		r[12]) ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
 		       ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1
+		       ip netns exec $ns sysctl -q -w net.ipv4.conf.default.rp_filter=0
+		       ip netns exec $ns sysctl -q -w net.ipv4.conf.all.rp_filter=0
 
 		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
 		       ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index f50976ee7d44..aa254aefc2c3 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -5,7 +5,7 @@ KSFT_KHDR_INSTALL := 1
 
 CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g  -I$(top_srcdir)/usr/include
 
-TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh
+TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh
 
 TEST_GEN_FILES = mptcp_connect pm_nl_ctl
 
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index 2499824d9e1c..8df5cb8f71ff 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -1,4 +1,6 @@
 CONFIG_MPTCP=y
 CONFIG_MPTCP_IPV6=y
+CONFIG_INET_DIAG=m
+CONFIG_INET_MPTCP_DIAG=m
 CONFIG_VETH=y
 CONFIG_NET_SCH_NETEM=m
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
new file mode 100755
index 000000000000..39edce4f541c
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -0,0 +1,121 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+ns="ns1-$rndh"
+ksft_skip=4
+test_cnt=1
+ret=0
+pids=()
+
+flush_pids()
+{
+	# mptcp_connect in join mode will sleep a bit before completing,
+	# give it some time
+	sleep 1.1
+
+	for pid in ${pids[@]}; do
+		[ -d /proc/$pid ] && kill -SIGUSR1 $pid >/dev/null 2>&1
+	done
+	pids=()
+}
+
+cleanup()
+{
+	ip netns del $ns
+	for pid in ${pids[@]}; do
+		[ -d /proc/$pid ] && kill -9 $pid >/dev/null 2>&1
+	done
+}
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+ss -h | grep -q MPTCP
+if [ $? -ne 0 ];then
+	echo "SKIP: ss tool does not support MPTCP"
+	exit $ksft_skip
+fi
+
+__chk_nr()
+{
+	local condition="$1"
+	local expected=$2
+	local msg nr
+
+	shift 2
+	msg=$*
+	nr=$(ss -inmHMN $ns | $condition)
+
+	printf "%-50s" "$msg"
+	if [ $nr != $expected ]; then
+		echo "[ fail ] expected $expected found $nr"
+		ret=$test_cnt
+	else
+		echo "[  ok  ]"
+	fi
+	test_cnt=$((test_cnt+1))
+}
+
+chk_msk_nr()
+{
+	__chk_nr "grep -c token:" $*
+}
+
+chk_msk_fallback_nr()
+{
+		__chk_nr "grep -c fallback" $*
+}
+
+chk_msk_remote_key_nr()
+{
+		__chk_nr "grep -c remote_key" $*
+}
+
+
+trap cleanup EXIT
+ip netns add $ns
+ip -n $ns link set dev lo up
+
+echo "a" | ip netns exec $ns ./mptcp_connect -p 10000 -l 0.0.0.0 -t 100 >/dev/null &
+sleep 0.1
+pids[0]=$!
+chk_msk_nr 0 "no msk on netns creation"
+
+echo "b" | ip netns exec $ns ./mptcp_connect -p 10000 127.0.0.1 -j -t 100 >/dev/null &
+sleep 0.1
+pids[1]=$!
+chk_msk_nr 2 "after MPC handshake "
+chk_msk_remote_key_nr 2 "....chk remote_key"
+chk_msk_fallback_nr 0 "....chk no fallback"
+flush_pids
+
+
+echo "a" | ip netns exec $ns ./mptcp_connect -p 10001 -s TCP -l 0.0.0.0 -t 100 >/dev/null &
+pids[0]=$!
+sleep 0.1
+echo "b" | ip netns exec $ns ./mptcp_connect -p 10001 127.0.0.1 -j -t 100 >/dev/null &
+pids[1]=$!
+sleep 0.1
+chk_msk_fallback_nr 1 "check fallback"
+flush_pids
+
+NR_CLIENTS=100
+for I in `seq 1 $NR_CLIENTS`; do
+	echo "a" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) -l 0.0.0.0 -t 100 -w 10 >/dev/null  &
+	pids[$((I*2))]=$!
+done
+sleep 0.1
+
+for I in `seq 1 $NR_CLIENTS`; do
+	echo "b" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) 127.0.0.1 -t 100 -w 10 >/dev/null &
+	pids[$((I*2 + 1))]=$!
+done
+sleep 1.5
+
+chk_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
+flush_pids
+
+exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index cedee5b952ba..090620c3e10c 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -11,6 +11,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <strings.h>
+#include <signal.h>
 #include <unistd.h>
 
 #include <sys/poll.h>
@@ -36,6 +37,7 @@ extern int optind;
 
 static int  poll_timeout = 10 * 1000;
 static bool listen_mode;
+static bool quit;
 
 enum cfg_mode {
 	CFG_MODE_POLL,
@@ -52,11 +54,12 @@ static int pf = AF_INET;
 static int cfg_sndbuf;
 static int cfg_rcvbuf;
 static bool cfg_join;
+static int cfg_wait;
 
 static void die_usage(void)
 {
 	fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]"
-		"[-l] connect_address\n");
+		"[-l] [-w sec] connect_address\n");
 	fprintf(stderr, "\t-6 use ipv6\n");
 	fprintf(stderr, "\t-t num -- set poll timeout to num\n");
 	fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n");
@@ -65,9 +68,15 @@ static void die_usage(void)
 	fprintf(stderr, "\t-m [MPTCP|TCP] -- use tcp or mptcp sockets\n");
 	fprintf(stderr, "\t-s [mmap|poll] -- use poll (default) or mmap\n");
 	fprintf(stderr, "\t-u -- check mptcp ulp\n");
+	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
 	exit(1);
 }
 
+static void handle_signal(int nr)
+{
+	quit = true;
+}
+
 static const char *getxinfo_strerr(int err)
 {
 	if (err == EAI_SYSTEM)
@@ -397,10 +406,11 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd)
 
 				/* ... but we still receive.
 				 * Close our write side, ev. give some time
-				 * for address notification
+				 * for address notification and/or checking
+				 * the current status
 				 */
-				if (cfg_join)
-					usleep(400000);
+				if (cfg_wait)
+					usleep(cfg_wait);
 				shutdown(peerfd, SHUT_WR);
 			} else {
 				if (errno == EINTR)
@@ -419,7 +429,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd)
 
 	/* leave some time for late join/announce */
 	if (cfg_join)
-		usleep(400000);
+		usleep(cfg_wait);
 
 	close(peerfd);
 	return 0;
@@ -812,11 +822,12 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jlp:s:hut:m:S:R:")) != -1) {
+	while ((c = getopt(argc, argv, "6jlp:s:hut:m:S:R:w:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
 			cfg_mode = CFG_MODE_POLL;
+			cfg_wait = 400000;
 			break;
 		case 'l':
 			listen_mode = true;
@@ -850,6 +861,9 @@ static void parse_opts(int argc, char **argv)
 		case 'R':
 			cfg_rcvbuf = parse_int(optarg);
 			break;
+		case 'w':
+			cfg_wait = atoi(optarg)*1000000;
+			break;
 		}
 	}
 
@@ -865,6 +879,7 @@ int main(int argc, char *argv[])
 {
 	init_rng();
 
+	signal(SIGUSR1, handle_signal);
 	parse_opts(argc, argv);
 
 	if (tcpulp_audit)
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index acf02e156d20..57d75b7f6220 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -3,7 +3,7 @@
 
 time_start=$(date +%s)
 
-optstring="S:R:d:e:l:r:h4cm:"
+optstring="S:R:d:e:l:r:h4cm:f:t"
 ret=0
 sin=""
 sout=""
@@ -21,6 +21,8 @@ testmode=""
 sndbuf=0
 rcvbuf=0
 options_log=true
+do_tcp=0
+filesize=0
 
 if [ $tc_loss -eq 100 ];then
 	tc_loss=1%
@@ -40,9 +42,11 @@ usage() {
 	echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)"
 	echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)"
 	echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
+	echo -e "\t-f: size of file to transfer in bytes (default random)"
 	echo -e "\t-S: set sndbuf value (default: use kernel default)"
 	echo -e "\t-R: set rcvbuf value (default: use kernel default)"
 	echo -e "\t-m: test mode (poll, sendfile; default: poll)"
+	echo -e "\t-t: also run tests with TCP (use twice to non-fallback tcp)"
 }
 
 while getopts "$optstring" option;do
@@ -94,6 +98,12 @@ while getopts "$optstring" option;do
 	"m")
 		testmode="$OPTARG"
 		;;
+	"f")
+		filesize="$OPTARG"
+		;;
+	"t")
+		do_tcp=$((do_tcp+1))
+		;;
 	"?")
 		usage $0
 		exit 1
@@ -186,6 +196,9 @@ ip -net "$ns4" link set ns4eth3 up
 ip -net "$ns4" route add default via 10.0.3.2
 ip -net "$ns4" route add default via dead:beef:3::2
 
+# use TCP syn cookies, even if no flooding was detected.
+ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2
+
 set_ethtool_flags() {
 	local ns="$1"
 	local dev="$2"
@@ -385,14 +398,23 @@ do_transfer()
 			capuser="-Z $SUDO_USER"
 		fi
 
-		local capfile="${listener_ns}-${connector_ns}-${cl_proto}-${srv_proto}-${connect_addr}.pcap"
+		local capfile="${rndh}-${connector_ns:0:3}-${listener_ns:0:3}-${cl_proto}-${srv_proto}-${connect_addr}-${port}"
+		local capopt="-i any -s 65535 -B 32768 ${capuser}"
+
+		ip netns exec ${listener_ns}  tcpdump ${capopt} -w "${capfile}-listener.pcap"  >> "${capout}" 2>&1 &
+		local cappid_listener=$!
 
-		ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 &
-		local cappid=$!
+		ip netns exec ${connector_ns} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 &
+		local cappid_connector=$!
 
 		sleep 1
 	fi
 
+	local stat_synrx_last_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableSYNRX | while read a count c rest ;do  echo $count;done)
+	local stat_ackrx_last_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableACKRX | while read a count c rest ;do  echo $count;done)
+	local stat_cookietx_last=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesSent | while read a count c rest ;do  echo $count;done)
+	local stat_cookierx_last=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesRecv | while read a count c rest ;do  echo $count;done)
+
 	ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" &
 	local spid=$!
 
@@ -413,7 +435,8 @@ do_transfer()
 
 	if $capture; then
 		sleep 1
-		kill $cappid
+		kill ${cappid_listener}
+		kill ${cappid_connector}
 	fi
 
 	local duration
@@ -435,6 +458,45 @@ do_transfer()
 	check_transfer $cin $sout "file received by server"
 	rets=$?
 
+	local stat_synrx_now_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableSYNRX  | while read a count c rest ;do  echo $count;done)
+	local stat_ackrx_now_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableACKRX  | while read a count c rest ;do  echo $count;done)
+
+	local stat_cookietx_now=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesSent | while read a count c rest ;do  echo $count;done)
+	local stat_cookierx_now=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesRecv | while read a count c rest ;do  echo $count;done)
+
+	expect_synrx=$((stat_synrx_last_l))
+	expect_ackrx=$((stat_ackrx_last_l))
+
+	cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies)
+	cookies=${cookies##*=}
+
+	if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then
+		expect_synrx=$((stat_synrx_last_l+1))
+		expect_ackrx=$((stat_ackrx_last_l+1))
+	fi
+	if [ $cookies -eq 2 ];then
+		if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then
+			echo "${listener_ns} CookieSent: ${cl_proto} -> ${srv_proto}: did not advance"
+		fi
+		if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then
+			echo "${listener_ns} CookieRecv: ${cl_proto} -> ${srv_proto}: did not advance"
+		fi
+	else
+		if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then
+			echo "${listener_ns} CookieSent: ${cl_proto} -> ${srv_proto}: changed"
+		fi
+		if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then
+			echo "${listener_ns} CookieRecv: ${cl_proto} -> ${srv_proto}: changed"
+		fi
+	fi
+
+	if [ $expect_synrx -ne $stat_synrx_now_l ] ;then
+		echo "${listener_ns} SYNRX: ${cl_proto} -> ${srv_proto}: expect ${expect_synrx}, got ${stat_synrx_now_l}"
+	fi
+	if [ $expect_ackrx -ne $stat_ackrx_now_l ] ;then
+		echo "${listener_ns} ACKRX: ${cl_proto} -> ${srv_proto}: expect ${expect_synrx}, got ${stat_synrx_now_l}"
+	fi
+
 	if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
 		echo "$duration [ OK ]"
 		cat "$capout"
@@ -449,20 +511,25 @@ make_file()
 {
 	local name=$1
 	local who=$2
+	local SIZE=$filesize
+	local ksize
+	local rem
 
-	local SIZE TSIZE
-	SIZE=$((RANDOM % (1024 * 8)))
-	TSIZE=$((SIZE * 1024))
+	if [ $SIZE -eq 0 ]; then
+		local MAXSIZE=$((1024 * 1024 * 8))
+		local MINSIZE=$((1024 * 256))
 
-	dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null
+		SIZE=$(((RANDOM * RANDOM + MINSIZE) % MAXSIZE))
+	fi
 
-	SIZE=$((RANDOM % 1024))
-	SIZE=$((SIZE + 128))
-	TSIZE=$((TSIZE + SIZE))
-	dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null
+	ksize=$((SIZE / 1024))
+	rem=$((SIZE - (ksize * 1024)))
+
+	dd if=/dev/urandom of="$name" bs=1024 count=$ksize 2> /dev/null
+	dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$rem 2> /dev/null
 	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
 
-	echo "Created $name (size $TSIZE) containing data sent by $who"
+	echo "Created $name (size $(du -b "$name")) containing data sent by $who"
 }
 
 run_tests_lo()
@@ -497,9 +564,11 @@ run_tests_lo()
 		return 1
 	fi
 
-	# don't bother testing fallback tcp except for loopback case.
-	if [ ${listener_ns} != ${connector_ns} ]; then
-		return 0
+	if [ $do_tcp -eq 0 ]; then
+		# don't bother testing fallback tcp except for loopback case.
+		if [ ${listener_ns} != ${connector_ns} ]; then
+			return 0
+		fi
 	fi
 
 	do_transfer ${listener_ns} ${connector_ns} MPTCP TCP ${connect_addr} ${local_addr}
@@ -516,6 +585,15 @@ run_tests_lo()
 		return 1
 	fi
 
+	if [ $do_tcp -gt 1 ] ;then
+		do_transfer ${listener_ns} ${connector_ns} TCP TCP ${connect_addr} ${local_addr}
+		lret=$?
+		if [ $lret -ne 0 ]; then
+			ret=$lret
+			return 1
+		fi
+	fi
+
 	return 0
 }
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index dd42c2f692d0..f39c1129ce5f 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -72,6 +72,15 @@ reset()
 	init
 }
 
+reset_with_cookies()
+{
+	reset
+
+	for netns in "$ns1" "$ns2";do
+		ip netns exec $netns sysctl -q net.ipv4.tcp_syncookies=2
+	done
+}
+
 for arg in "$@"; do
 	if [ "$arg" = "-c" ]; then
 		capture=1
@@ -138,7 +147,7 @@ do_transfer()
 			capuser="-Z $SUDO_USER"
 		fi
 
-		capfile="mp_join-${listener_ns}.pcap"
+		capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}")
 
 		echo "Capturing traffic for test $TEST_COUNT into $capfile"
 		ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 &
@@ -227,7 +236,7 @@ chk_join_nr()
 	local count
 	local dump_stats
 
-	printf "%-36s %s" "$msg" "syn"
+	printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn"
 	count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'`
 	[ -z "$count" ] && count=0
 	if [ "$count" != "$syn_nr" ]; then
@@ -354,4 +363,57 @@ ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
 run_tests $ns1 $ns2 10.0.1.1
 chk_join_nr "multiple subflows and signal" 3 3 3
 
+# single subflow, syncookies
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "single subflow with syn cookies" 1 1 1
+
+# multiple subflows with syn cookies
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "multiple subflows with syn cookies" 2 2 2
+
+# multiple subflows limited by server
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "subflows limited by server w cookies" 2 2 1
+
+# test signal address with cookies
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "signal address with syn cookies" 1 1 1
+
+# test cookie with subflow and signal
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl limits 1 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "subflow and signal w cookies" 2 2 2
+
+# accept and use add_addr with additional subflows
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl limits 0 3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 3
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "subflows and signal w. cookies" 3 3 3
+
 exit $ret
diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index 4b02933cab8a..bdc03a2097e8 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -125,9 +125,8 @@ static int do_setcpu(int cpu)
 	CPU_ZERO(&mask);
 	CPU_SET(cpu, &mask);
 	if (sched_setaffinity(0, sizeof(mask), &mask))
-		error(1, 0, "setaffinity %d", cpu);
-
-	if (cfg_verbose)
+		fprintf(stderr, "cpu: unable to pin, may increase variance.\n");
+	else if (cfg_verbose)
 		fprintf(stderr, "cpu: %u\n", cpu);
 
 	return 0;
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 77c09cd339c3..6bbf69a28e12 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -59,6 +59,45 @@
 #	Same as pmtu_ipv6_vxlan6_exception, but using a GENEVE tunnel instead of
 #	VXLAN
 #
+# - pmtu_ipv{4,6}_br_vxlan{4,6}_exception
+#	Set up three namespaces, A, B, and C, with routing between A and B over
+#	R1. R2 is unused in these tests. A has a veth connection to C, and is
+#	connected to B via a VXLAN endpoint, which is directly bridged to C.
+#	MTU on the B-R1 link is lower than other MTUs.
+#
+#	Check that both C and A are able to communicate with B over the VXLAN
+#	tunnel, and that PMTU exceptions with the correct values are created.
+#
+#	                  segment a_r1    segment b_r1            b_r1: 4000
+#	                .--------------R1--------------.    everything
+#	   C---veth     A                               B         else: 5000
+#	        ' bridge                                |
+#	            '---- - - - - - VXLAN - - - - - - - '
+#
+# - pmtu_ipv{4,6}_br_geneve{4,6}_exception
+#	Same as pmtu_ipv{4,6}_br_vxlan{4,6}_exception, with a GENEVE tunnel
+#	instead.
+#
+# - pmtu_ipv{4,6}_ovs_vxlan{4,6}_exception
+#	Set up two namespaces, B, and C, with routing between the init namespace
+#	and B over R1. A and R2 are unused in these tests. The init namespace
+#	has a veth connection to C, and is connected to B via a VXLAN endpoint,
+#	which is handled by Open vSwitch and bridged to C. MTU on the B-R1 link
+#	is lower than other MTUs.
+#
+#	Check that C is able to communicate with B over the VXLAN tunnel, and
+#	that PMTU exceptions with the correct values are created.
+#
+#	                  segment a_r1    segment b_r1            b_r1: 4000
+#	                .--------------R1--------------.    everything
+#	   C---veth    init                             B         else: 5000
+#	        '- ovs                                  |
+#	            '---- - - - - - VXLAN - - - - - - - '
+#
+# - pmtu_ipv{4,6}_ovs_geneve{4,6}_exception
+#	Same as pmtu_ipv{4,6}_ovs_vxlan{4,6}_exception, with a GENEVE tunnel
+#	instead.
+#
 # - pmtu_ipv{4,6}_fou{4,6}_exception
 #	Same as pmtu_ipv4_vxlan4, but using a direct IPv4/IPv6 encapsulation
 #	(FoU) over IPv4/IPv6, instead of VXLAN
@@ -147,6 +186,22 @@ tests="
 	pmtu_ipv6_geneve4_exception	IPv6 over geneve4: PMTU exceptions	1
 	pmtu_ipv4_geneve6_exception	IPv4 over geneve6: PMTU exceptions	1
 	pmtu_ipv6_geneve6_exception	IPv6 over geneve6: PMTU exceptions	1
+	pmtu_ipv4_br_vxlan4_exception	IPv4, bridged vxlan4: PMTU exceptions	1
+	pmtu_ipv6_br_vxlan4_exception	IPv6, bridged vxlan4: PMTU exceptions	1
+	pmtu_ipv4_br_vxlan6_exception	IPv4, bridged vxlan6: PMTU exceptions	1
+	pmtu_ipv6_br_vxlan6_exception	IPv6, bridged vxlan6: PMTU exceptions	1
+	pmtu_ipv4_br_geneve4_exception	IPv4, bridged geneve4: PMTU exceptions	1
+	pmtu_ipv6_br_geneve4_exception	IPv6, bridged geneve4: PMTU exceptions	1
+	pmtu_ipv4_br_geneve6_exception	IPv4, bridged geneve6: PMTU exceptions	1
+	pmtu_ipv6_br_geneve6_exception	IPv6, bridged geneve6: PMTU exceptions	1
+	pmtu_ipv4_ovs_vxlan4_exception	IPv4, OVS vxlan4: PMTU exceptions	1
+	pmtu_ipv6_ovs_vxlan4_exception	IPv6, OVS vxlan4: PMTU exceptions	1
+	pmtu_ipv4_ovs_vxlan6_exception	IPv4, OVS vxlan6: PMTU exceptions	1
+	pmtu_ipv6_ovs_vxlan6_exception	IPv6, OVS vxlan6: PMTU exceptions	1
+	pmtu_ipv4_ovs_geneve4_exception	IPv4, OVS geneve4: PMTU exceptions	1
+	pmtu_ipv6_ovs_geneve4_exception	IPv6, OVS geneve4: PMTU exceptions	1
+	pmtu_ipv4_ovs_geneve6_exception	IPv4, OVS geneve6: PMTU exceptions	1
+	pmtu_ipv6_ovs_geneve6_exception	IPv6, OVS geneve6: PMTU exceptions	1
 	pmtu_ipv4_fou4_exception	IPv4 over fou4: PMTU exceptions		1
 	pmtu_ipv6_fou4_exception	IPv6 over fou4: PMTU exceptions		1
 	pmtu_ipv4_fou6_exception	IPv4 over fou6: PMTU exceptions		1
@@ -173,10 +228,12 @@ tests="
 
 NS_A="ns-A"
 NS_B="ns-B"
+NS_C="ns-C"
 NS_R1="ns-R1"
 NS_R2="ns-R2"
 ns_a="ip netns exec ${NS_A}"
 ns_b="ip netns exec ${NS_B}"
+ns_c="ip netns exec ${NS_C}"
 ns_r1="ip netns exec ${NS_R1}"
 ns_r2="ip netns exec ${NS_R2}"
 
@@ -239,9 +296,11 @@ routes_nh="
 
 veth4_a_addr="192.168.1.1"
 veth4_b_addr="192.168.1.2"
+veth4_c_addr="192.168.2.10"
 veth4_mask="24"
 veth6_a_addr="fd00:1::a"
 veth6_b_addr="fd00:1::b"
+veth6_c_addr="fd00:2::c"
 veth6_mask="64"
 
 tunnel4_a_addr="192.168.2.1"
@@ -428,7 +487,7 @@ setup_ip6ip6() {
 }
 
 setup_namespaces() {
-	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+	for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do
 		ip netns add ${n} || return 1
 
 		# Disable DAD, so that we don't have to wait to use the
@@ -484,6 +543,7 @@ setup_vxlan_or_geneve() {
 	a_addr="${2}"
 	b_addr="${3}"
 	opts="${4}"
+	br_if_a="${5}"
 
 	if [ "${type}" = "vxlan" ]; then
 		opts="${opts} ttl 64 dstport 4789"
@@ -497,10 +557,16 @@ setup_vxlan_or_geneve() {
 	run_cmd ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1
 	run_cmd ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts}
 
-	run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a
-	run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b
+	if [ -n "${br_if_a}" ]; then
+		run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${br_if_a}
+		run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${br_if_a}
+		run_cmd ${ns_a} ip link set ${type}_a master ${br_if_a}
+	else
+		run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a
+		run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a
+	fi
 
-	run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a
+	run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b
 	run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b
 
 	run_cmd ${ns_a} ip link set ${type}_a up
@@ -516,11 +582,27 @@ setup_vxlan4() {
 }
 
 setup_geneve6() {
-	setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
+	setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ""
 }
 
 setup_vxlan6() {
-	setup_vxlan_or_geneve vxlan  ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
+	setup_vxlan_or_geneve vxlan  ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ""
+}
+
+setup_bridged_geneve4() {
+	setup_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1  ${prefix4}.${b_r1}.1  "df set" "br0"
+}
+
+setup_bridged_vxlan4() {
+	setup_vxlan_or_geneve vxlan  ${prefix4}.${a_r1}.1  ${prefix4}.${b_r1}.1  "df set" "br0"
+}
+
+setup_bridged_geneve6() {
+	setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "" "br0"
+}
+
+setup_bridged_vxlan6() {
+	setup_vxlan_or_geneve vxlan  ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "" "br0"
 }
 
 setup_xfrm() {
@@ -630,6 +712,80 @@ setup_routing() {
 	return 0
 }
 
+setup_bridge() {
+	run_cmd ${ns_a} ip link add br0 type bridge || return 2
+	run_cmd ${ns_a} ip link set br0 up
+
+	run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C
+	run_cmd ${ns_c} ip link set veth_A-C netns ns-A
+
+	run_cmd ${ns_a} ip link set veth_A-C up
+	run_cmd ${ns_c} ip link set veth_C-A up
+	run_cmd ${ns_c} ip addr add ${veth4_c_addr}/${veth4_mask} dev veth_C-A
+	run_cmd ${ns_c} ip addr add ${veth6_c_addr}/${veth6_mask} dev veth_C-A
+	run_cmd ${ns_a} ip link set veth_A-C master br0
+}
+
+setup_ovs_vxlan_or_geneve() {
+	type="${1}"
+	a_addr="${2}"
+	b_addr="${3}"
+
+	if [ "${type}" = "vxlan" ]; then
+		opts="${opts} ttl 64 dstport 4789"
+		opts_b="local ${b_addr}"
+	fi
+
+	run_cmd ovs-vsctl add-port ovs_br0 ${type}_a -- \
+		set interface ${type}_a type=${type} \
+		options:remote_ip=${b_addr} options:key=1 options:csum=true || return 1
+
+	run_cmd ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts} || return 1
+
+	run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b
+	run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b
+
+	run_cmd ${ns_b} ip link set ${type}_b up
+}
+
+setup_ovs_geneve4() {
+	setup_ovs_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1  ${prefix4}.${b_r1}.1
+}
+
+setup_ovs_vxlan4() {
+	setup_ovs_vxlan_or_geneve vxlan  ${prefix4}.${a_r1}.1  ${prefix4}.${b_r1}.1
+}
+
+setup_ovs_geneve6() {
+	setup_ovs_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
+}
+
+setup_ovs_vxlan6() {
+	setup_ovs_vxlan_or_geneve vxlan  ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
+}
+
+setup_ovs_bridge() {
+	run_cmd ovs-vsctl add-br ovs_br0 || return 2
+	run_cmd ip link set ovs_br0 up
+
+	run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C
+	run_cmd ${ns_c} ip link set veth_A-C netns 1
+
+	run_cmd         ip link set veth_A-C up
+	run_cmd ${ns_c} ip link set veth_C-A up
+	run_cmd ${ns_c} ip addr add ${veth4_c_addr}/${veth4_mask} dev veth_C-A
+	run_cmd ${ns_c} ip addr add ${veth6_c_addr}/${veth6_mask} dev veth_C-A
+	run_cmd ovs-vsctl add-port ovs_br0 veth_A-C
+
+	# Move veth_A-R1 to init
+	run_cmd ${ns_a} ip link set veth_A-R1 netns 1
+	run_cmd ip addr add ${prefix4}.${a_r1}.1/${veth4_mask} dev veth_A-R1
+	run_cmd ip addr add ${prefix6}:${a_r1}::1/${veth6_mask} dev veth_A-R1
+	run_cmd ip link set veth_A-R1 up
+	run_cmd ip route add ${prefix4}.${b_r1}.1 via ${prefix4}.${a_r1}.2
+	run_cmd ip route add ${prefix6}:${b_r1}::1 via ${prefix6}:${a_r1}::2
+}
+
 setup() {
 	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip
 
@@ -657,9 +813,14 @@ cleanup() {
 	done
 	tcpdump_pids=
 
-	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+	for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do
 		ip netns del ${n} 2> /dev/null
 	done
+
+	ip link del veth_A-C			2>/dev/null
+	ip link del veth_A-R1			2>/dev/null
+	ovs-vsctl --if-exists del-port vxlan_a	2>/dev/null
+	ovs-vsctl --if-exists del-br ovs_br0	2>/dev/null
 }
 
 mtu() {
@@ -892,6 +1053,177 @@ test_pmtu_ipv6_geneve6_exception() {
 	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 6
 }
 
+test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() {
+	type=${1}
+	family=${2}
+	outer_family=${3}
+	ll_mtu=4000
+
+	if [ ${outer_family} -eq 4 ]; then
+		setup namespaces routing bridge bridged_${type}4 || return 2
+		#                      IPv4 header   UDP header   VXLAN/GENEVE header   Ethernet header
+		exp_mtu=$((${ll_mtu} - 20          - 8          - 8                   - 14))
+	else
+		setup namespaces routing bridge bridged_${type}6 || return 2
+		#                      IPv6 header   UDP header   VXLAN/GENEVE header   Ethernet header
+		exp_mtu=$((${ll_mtu} - 40          - 8          - 8                   - 14))
+	fi
+
+	trace "${ns_a}" ${type}_a    "${ns_b}"  ${type}_b \
+	      "${ns_a}" veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_b}" veth_B-R1    "${ns_r1}" veth_R1-B \
+	      "${ns_a}" br0          "${ns_a}"  veth-A-C  \
+	      "${ns_c}" veth_C-A
+
+	if [ ${family} -eq 4 ]; then
+		ping=ping
+		dst=${tunnel4_b_addr}
+	else
+		ping=${ping6}
+		dst=${tunnel6_b_addr}
+	fi
+
+	# Create route exception by exceeding link layer MTU
+	mtu "${ns_a}"  veth_A-R1 $((${ll_mtu} + 1000))
+	mtu "${ns_a}"  br0       $((${ll_mtu} + 1000))
+	mtu "${ns_a}"  veth_A-C  $((${ll_mtu} + 1000))
+	mtu "${ns_c}"  veth_C-A  $((${ll_mtu} + 1000))
+	mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+	mtu "${ns_b}"  veth_B-R1 ${ll_mtu}
+	mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+	mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000))
+	mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000))
+
+	run_cmd ${ns_c} ${ping} -q -M want -i 0.1 -c 10 -s $((${ll_mtu} + 500)) ${dst} || return 1
+	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1  -s $((${ll_mtu} + 500)) ${dst} || return 1
+
+	# Check that exceptions were created
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})"
+	check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on bridged ${type} interface"
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
+	check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on locally bridged ${type} interface"
+}
+
+test_pmtu_ipv4_br_vxlan4_exception() {
+	test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan  4 4
+}
+
+test_pmtu_ipv6_br_vxlan4_exception() {
+	test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan  6 4
+}
+
+test_pmtu_ipv4_br_geneve4_exception() {
+	test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 4 4
+}
+
+test_pmtu_ipv6_br_geneve4_exception() {
+	test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 6 4
+}
+
+test_pmtu_ipv4_br_vxlan6_exception() {
+	test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan  4 6
+}
+
+test_pmtu_ipv6_br_vxlan6_exception() {
+	test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan  6 6
+}
+
+test_pmtu_ipv4_br_geneve6_exception() {
+	test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 4 6
+}
+
+test_pmtu_ipv6_br_geneve6_exception() {
+	test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 6 6
+}
+
+test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception() {
+	type=${1}
+	family=${2}
+	outer_family=${3}
+	ll_mtu=4000
+
+	if [ ${outer_family} -eq 4 ]; then
+		setup namespaces routing ovs_bridge ovs_${type}4 || return 2
+		#                      IPv4 header   UDP header   VXLAN/GENEVE header   Ethernet header
+		exp_mtu=$((${ll_mtu} - 20          - 8          - 8                   - 14))
+	else
+		setup namespaces routing ovs_bridge ovs_${type}6 || return 2
+		#                      IPv6 header   UDP header   VXLAN/GENEVE header   Ethernet header
+		exp_mtu=$((${ll_mtu} - 40          - 8          - 8                   - 14))
+	fi
+
+	if [ "${type}" = "vxlan" ]; then
+		tun_a="vxlan_sys_4789"
+	elif [ "${type}" = "geneve" ]; then
+		tun_a="genev_sys_6081"
+	fi
+
+	trace ""        "${tun_a}"  "${ns_b}"  ${type}_b \
+	      ""        veth_A-R1   "${ns_r1}" veth_R1-A \
+	      "${ns_b}" veth_B-R1   "${ns_r1}" veth_R1-B \
+	      ""        ovs_br0     ""         veth-A-C  \
+	      "${ns_c}" veth_C-A
+
+	if [ ${family} -eq 4 ]; then
+		ping=ping
+		dst=${tunnel4_b_addr}
+	else
+		ping=${ping6}
+		dst=${tunnel6_b_addr}
+	fi
+
+	# Create route exception by exceeding link layer MTU
+	mtu ""         veth_A-R1 $((${ll_mtu} + 1000))
+	mtu ""         ovs_br0   $((${ll_mtu} + 1000))
+	mtu ""         veth_A-C  $((${ll_mtu} + 1000))
+	mtu "${ns_c}"  veth_C-A  $((${ll_mtu} + 1000))
+	mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+	mtu "${ns_b}"  veth_B-R1 ${ll_mtu}
+	mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+	mtu ""        ${tun_a}  $((${ll_mtu} + 1000))
+	mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000))
+
+	run_cmd ${ns_c} ${ping} -q -M want -i 0.1 -c 20 -s $((${ll_mtu} + 500)) ${dst} || return 1
+
+	# Check that exceptions were created
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})"
+	check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on Open vSwitch ${type} interface"
+}
+
+test_pmtu_ipv4_ovs_vxlan4_exception() {
+	test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan  4 4
+}
+
+test_pmtu_ipv6_ovs_vxlan4_exception() {
+	test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan  6 4
+}
+
+test_pmtu_ipv4_ovs_geneve4_exception() {
+	test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 4 4
+}
+
+test_pmtu_ipv6_ovs_geneve4_exception() {
+	test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 6 4
+}
+
+test_pmtu_ipv4_ovs_vxlan6_exception() {
+	test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan  4 6
+}
+
+test_pmtu_ipv6_ovs_vxlan6_exception() {
+	test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan  6 6
+}
+
+test_pmtu_ipv4_ovs_geneve6_exception() {
+	test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 4 6
+}
+
+test_pmtu_ipv6_ovs_geneve6_exception() {
+	test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 6 6
+}
+
 test_pmtu_ipvX_over_fouY_or_gueY() {
 	inner_family=${1}
 	outer_family=${2}
diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c
index 8c8c7d79c38d..2c522f7a0aec 100644
--- a/tools/testing/selftests/net/psock_fanout.c
+++ b/tools/testing/selftests/net/psock_fanout.c
@@ -350,7 +350,8 @@ static int test_datapath(uint16_t typeflags, int port_off,
 	int fds[2], fds_udp[2][2], ret;
 
 	fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n",
-		typeflags, PORT_BASE, PORT_BASE + port_off);
+		typeflags, (uint16_t)PORT_BASE,
+		(uint16_t)(PORT_BASE + port_off));
 
 	fds[0] = sock_fanout_open(typeflags, 0);
 	fds[1] = sock_fanout_open(typeflags, 0);
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index bdbf4b3125b6..7c38a909f8b8 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -5,7 +5,6 @@
 # set -e
 
 devdummy="test-dummy0"
-ret=0
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
@@ -66,7 +65,7 @@ kci_test_bridge()
 	devbr="test-br0"
 	vlandev="testbr-vlan1"
 
-	ret=0
+	local ret=0
 	ip link add name "$devbr" type bridge
 	check_err $?
 
@@ -113,7 +112,7 @@ kci_test_gre()
 	rem=10.42.42.1
 	loc=10.0.0.1
 
-	ret=0
+	local ret=0
 	ip tunnel add $gredev mode gre remote $rem local $loc ttl 1
 	check_err $?
 	ip link set $gredev up
@@ -149,7 +148,7 @@ kci_test_gre()
 kci_test_tc()
 {
 	dev=lo
-	ret=0
+	local ret=0
 
 	tc qdisc add dev "$dev" root handle 1: htb
 	check_err $?
@@ -184,7 +183,7 @@ kci_test_tc()
 
 kci_test_polrouting()
 {
-	ret=0
+	local ret=0
 	ip rule add fwmark 1 lookup 100
 	check_err $?
 	ip route add local 0.0.0.0/0 dev lo table 100
@@ -207,7 +206,7 @@ kci_test_route_get()
 {
 	local hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy)
 
-	ret=0
+	local ret=0
 
 	ip route get 127.0.0.1 > /dev/null
 	check_err $?
@@ -290,7 +289,7 @@ kci_test_promote_secondaries()
 
 kci_test_addrlabel()
 {
-	ret=0
+	local ret=0
 
 	ip addrlabel add prefix dead::/64 dev lo label 1
 	check_err $?
@@ -330,7 +329,7 @@ kci_test_addrlabel()
 
 kci_test_ifalias()
 {
-	ret=0
+	local ret=0
 	namewant=$(uuidgen)
 	syspathname="/sys/class/net/$devdummy/ifalias"
 
@@ -385,7 +384,7 @@ kci_test_ifalias()
 kci_test_vrf()
 {
 	vrfname="test-vrf"
-	ret=0
+	local ret=0
 
 	ip link show type vrf 2>/dev/null
 	if [ $? -ne 0 ]; then
@@ -425,7 +424,7 @@ kci_test_vrf()
 
 kci_test_encap_vxlan()
 {
-	ret=0
+	local ret=0
 	vxlan="test-vxlan0"
 	vlan="test-vlan0"
 	testns="$1"
@@ -511,7 +510,7 @@ kci_test_encap_vxlan()
 
 kci_test_encap_fou()
 {
-	ret=0
+	local ret=0
 	name="test-fou"
 	testns="$1"
 
@@ -548,7 +547,7 @@ kci_test_encap_fou()
 kci_test_encap()
 {
 	testns="testns"
-	ret=0
+	local ret=0
 
 	ip netns add "$testns"
 	if [ $? -ne 0 ]; then
@@ -565,15 +564,18 @@ kci_test_encap()
 	check_err $?
 
 	kci_test_encap_vxlan "$testns"
+	check_err $?
 	kci_test_encap_fou "$testns"
+	check_err $?
 
 	ip netns del "$testns"
+	return $ret
 }
 
 kci_test_macsec()
 {
 	msname="test_macsec0"
-	ret=0
+	local ret=0
 
 	ip macsec help 2>&1 | grep -q "^Usage: ip macsec"
 	if [ $? -ne 0 ]; then
@@ -631,7 +633,7 @@ kci_test_macsec()
 #-------------------------------------------------------------------
 kci_test_ipsec()
 {
-	ret=0
+	local ret=0
 	algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
 	srcip=192.168.123.1
 	dstip=192.168.123.2
@@ -731,7 +733,7 @@ kci_test_ipsec()
 #-------------------------------------------------------------------
 kci_test_ipsec_offload()
 {
-	ret=0
+	local ret=0
 	algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
 	srcip=192.168.123.3
 	dstip=192.168.123.4
@@ -841,7 +843,7 @@ kci_test_gretap()
 {
 	testns="testns"
 	DEV_NS=gretap00
-	ret=0
+	local ret=0
 
 	ip netns add "$testns"
 	if [ $? -ne 0 ]; then
@@ -891,7 +893,7 @@ kci_test_ip6gretap()
 {
 	testns="testns"
 	DEV_NS=ip6gretap00
-	ret=0
+	local ret=0
 
 	ip netns add "$testns"
 	if [ $? -ne 0 ]; then
@@ -941,7 +943,7 @@ kci_test_erspan()
 {
 	testns="testns"
 	DEV_NS=erspan00
-	ret=0
+	local ret=0
 
 	ip link help erspan 2>&1 | grep -q "^Usage:"
 	if [ $? -ne 0 ];then
@@ -1006,7 +1008,7 @@ kci_test_ip6erspan()
 {
 	testns="testns"
 	DEV_NS=ip6erspan00
-	ret=0
+	local ret=0
 
 	ip link help ip6erspan 2>&1 | grep -q "^Usage:"
 	if [ $? -ne 0 ];then
@@ -1077,7 +1079,7 @@ kci_test_fdb_get()
 	test_mac=de:ad:be:ef:13:37
 	localip="10.0.2.2"
 	dstip="10.0.2.3"
-	ret=0
+	local ret=0
 
 	bridge fdb help 2>&1 |grep -q 'bridge fdb get'
 	if [ $? -ne 0 ];then
@@ -1125,7 +1127,7 @@ kci_test_neigh_get()
 	dstmac=de:ad:be:ef:13:37
 	dstip=10.0.2.4
 	dstip6=dead::2
-	ret=0
+	local ret=0
 
 	ip neigh help 2>&1 |grep -q 'ip neigh get'
 	if [ $? -ne 0 ];then
@@ -1175,6 +1177,7 @@ kci_test_neigh_get()
 
 kci_test_rtnl()
 {
+	local ret=0
 	kci_add_dummy
 	if [ $ret -ne 0 ];then
 		echo "FAIL: cannot add dummy interface"
@@ -1182,27 +1185,48 @@ kci_test_rtnl()
 	fi
 
 	kci_test_polrouting
+	check_err $?
 	kci_test_route_get
+	check_err $?
 	kci_test_addrlft
+	check_err $?
 	kci_test_promote_secondaries
+	check_err $?
 	kci_test_tc
+	check_err $?
 	kci_test_gre
+	check_err $?
 	kci_test_gretap
+	check_err $?
 	kci_test_ip6gretap
+	check_err $?
 	kci_test_erspan
+	check_err $?
 	kci_test_ip6erspan
+	check_err $?
 	kci_test_bridge
+	check_err $?
 	kci_test_addrlabel
+	check_err $?
 	kci_test_ifalias
+	check_err $?
 	kci_test_vrf
+	check_err $?
 	kci_test_encap
+	check_err $?
 	kci_test_macsec
+	check_err $?
 	kci_test_ipsec
+	check_err $?
 	kci_test_ipsec_offload
+	check_err $?
 	kci_test_fdb_get
+	check_err $?
 	kci_test_neigh_get
+	check_err $?
 
 	kci_del_dummy
+	return $ret
 }
 
 #check for needed privileges
@@ -1221,4 +1245,4 @@ done
 
 kci_test_rtnl
 
-exit $ret
+exit $?
diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c
index 422e7761254d..e4613ce4ed69 100644
--- a/tools/testing/selftests/net/rxtimestamp.c
+++ b/tools/testing/selftests/net/rxtimestamp.c
@@ -44,6 +44,7 @@ struct test_case {
 	struct options sockopt;
 	struct tstamps expected;
 	bool enabled;
+	bool warn_on_fail;
 };
 
 struct sof_flag {
@@ -67,44 +68,44 @@ static struct socket_type socket_types[] = {
 static struct test_case test_cases[] = {
 	{ {}, {} },
 	{
-		{ so_timestamp: 1 },
-		{ tstamp: true }
+		{ .so_timestamp = 1 },
+		{ .tstamp = true }
 	},
 	{
-		{ so_timestampns: 1 },
-		{ tstampns: true }
+		{ .so_timestampns = 1 },
+		{ .tstampns = true }
 	},
 	{
-		{ so_timestamp: 1, so_timestampns: 1 },
-		{ tstampns: true }
+		{ .so_timestamp = 1, .so_timestampns = 1 },
+		{ .tstampns = true }
 	},
 	{
-		{ so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE },
+		{ .so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE },
 		{}
 	},
 	{
 		/* Loopback device does not support hw timestamps. */
-		{ so_timestamping: SOF_TIMESTAMPING_RX_HARDWARE },
+		{ .so_timestamping = SOF_TIMESTAMPING_RX_HARDWARE },
 		{}
 	},
 	{
-		{ so_timestamping: SOF_TIMESTAMPING_SOFTWARE },
-		{}
+		{ .so_timestamping = SOF_TIMESTAMPING_SOFTWARE },
+		.warn_on_fail = true
 	},
 	{
-		{ so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE
+		{ .so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE
 			| SOF_TIMESTAMPING_RX_HARDWARE },
 		{}
 	},
 	{
-		{ so_timestamping: SOF_TIMESTAMPING_SOFTWARE
+		{ .so_timestamping = SOF_TIMESTAMPING_SOFTWARE
 			| SOF_TIMESTAMPING_RX_SOFTWARE },
-		{ swtstamp: true }
+		{ .swtstamp = true }
 	},
 	{
-		{ so_timestamp: 1, so_timestamping: SOF_TIMESTAMPING_SOFTWARE
+		{ .so_timestamp = 1, .so_timestamping = SOF_TIMESTAMPING_SOFTWARE
 			| SOF_TIMESTAMPING_RX_SOFTWARE },
-		{ tstamp: true, swtstamp: true }
+		{ .tstamp = true, .swtstamp = true }
 	},
 };
 
@@ -115,6 +116,9 @@ static struct option long_options[] = {
 	{ "tcp", no_argument, 0, 't' },
 	{ "udp", no_argument, 0, 'u' },
 	{ "ip", no_argument, 0, 'i' },
+	{ "strict", no_argument, 0, 'S' },
+	{ "ipv4", no_argument, 0, '4' },
+	{ "ipv6", no_argument, 0, '6' },
 	{ NULL, 0, NULL, 0 },
 };
 
@@ -270,37 +274,55 @@ void config_so_flags(int rcv, struct options o)
 		error(1, errno, "Failed to set SO_TIMESTAMPING");
 }
 
-bool run_test_case(struct socket_type s, struct test_case t)
+bool run_test_case(struct socket_type *s, int test_num, char ip_version,
+		   bool strict)
 {
-	int port = (s.type == SOCK_RAW) ? 0 : next_port++;
+	union {
+		struct sockaddr_in6 addr6;
+		struct sockaddr_in addr4;
+		struct sockaddr addr_un;
+	} addr;
 	int read_size = op_size;
-	struct sockaddr_in addr;
+	int src, dst, rcv, port;
+	socklen_t addr_size;
 	bool failed = false;
-	int src, dst, rcv;
 
-	src = socket(AF_INET, s.type, s.protocol);
+	port = (s->type == SOCK_RAW) ? 0 : next_port++;
+	memset(&addr, 0, sizeof(addr));
+	if (ip_version == '4') {
+		addr.addr4.sin_family = AF_INET;
+		addr.addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+		addr.addr4.sin_port = htons(port);
+		addr_size = sizeof(addr.addr4);
+		if (s->type == SOCK_RAW)
+			read_size += 20;  /* for IPv4 header */
+	} else {
+		addr.addr6.sin6_family = AF_INET6;
+		addr.addr6.sin6_addr = in6addr_loopback;
+		addr.addr6.sin6_port = htons(port);
+		addr_size = sizeof(addr.addr6);
+	}
+	printf("Starting testcase %d over ipv%c...\n", test_num, ip_version);
+	src = socket(addr.addr_un.sa_family, s->type,
+		     s->protocol);
 	if (src < 0)
 		error(1, errno, "Failed to open src socket");
 
-	dst = socket(AF_INET, s.type, s.protocol);
+	dst = socket(addr.addr_un.sa_family, s->type,
+		     s->protocol);
 	if (dst < 0)
 		error(1, errno, "Failed to open dst socket");
 
-	memset(&addr, 0, sizeof(addr));
-	addr.sin_family = AF_INET;
-	addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
-	addr.sin_port = htons(port);
-
-	if (bind(dst, (struct sockaddr *)&addr, sizeof(addr)) < 0)
+	if (bind(dst, &addr.addr_un, addr_size) < 0)
 		error(1, errno, "Failed to bind to port %d", port);
 
-	if (s.type == SOCK_STREAM && (listen(dst, 1) < 0))
+	if (s->type == SOCK_STREAM && (listen(dst, 1) < 0))
 		error(1, errno, "Failed to listen");
 
-	if (connect(src, (struct sockaddr *)&addr, sizeof(addr)) < 0)
+	if (connect(src, &addr.addr_un, addr_size) < 0)
 		error(1, errno, "Failed to connect");
 
-	if (s.type == SOCK_STREAM) {
+	if (s->type == SOCK_STREAM) {
 		rcv = accept(dst, NULL, NULL);
 		if (rcv < 0)
 			error(1, errno, "Failed to accept");
@@ -309,17 +331,22 @@ bool run_test_case(struct socket_type s, struct test_case t)
 		rcv = dst;
 	}
 
-	config_so_flags(rcv, t.sockopt);
+	config_so_flags(rcv, test_cases[test_num].sockopt);
 	usleep(20000); /* setsockopt for SO_TIMESTAMPING is asynchronous */
 	do_send(src);
 
-	if (s.type == SOCK_RAW)
-		read_size += 20;  /* for IP header */
-	failed = do_recv(rcv, read_size, t.expected);
+	failed = do_recv(rcv, read_size, test_cases[test_num].expected);
 
 	close(rcv);
 	close(src);
 
+	if (failed) {
+		printf("FAILURE in testcase %d over ipv%c ", test_num,
+		       ip_version);
+		print_test_case(&test_cases[test_num]);
+		if (!strict && test_cases[test_num].warn_on_fail)
+			failed = false;
+	}
 	return failed;
 }
 
@@ -327,10 +354,12 @@ int main(int argc, char **argv)
 {
 	bool all_protocols = true;
 	bool all_tests = true;
+	bool cfg_ipv4 = false;
+	bool cfg_ipv6 = false;
+	bool strict = false;
 	int arg_index = 0;
 	int failures = 0;
-	int s, t;
-	char opt;
+	int s, t, opt;
 
 	while ((opt = getopt_long(argc, argv, "", long_options,
 				  &arg_index)) != -1) {
@@ -363,6 +392,15 @@ int main(int argc, char **argv)
 			all_protocols = false;
 			socket_types[0].enabled = true;
 			break;
+		case 'S':
+			strict = true;
+			break;
+		case '4':
+			cfg_ipv4 = true;
+			break;
+		case '6':
+			cfg_ipv6 = true;
+			break;
 		default:
 			error(1, 0, "Failed to parse parameters.");
 		}
@@ -376,13 +414,14 @@ int main(int argc, char **argv)
 		for (t = 0; t < ARRAY_SIZE(test_cases); t++) {
 			if (!all_tests && !test_cases[t].enabled)
 				continue;
-
-			printf("Starting testcase %d...\n", t);
-			if (run_test_case(socket_types[s], test_cases[t])) {
-				failures++;
-				printf("FAILURE in test case ");
-				print_test_case(&test_cases[t]);
-			}
+			if (cfg_ipv4 || !cfg_ipv6)
+				if (run_test_case(&socket_types[s], t, '4',
+						  strict))
+					failures++;
+			if (cfg_ipv6 || !cfg_ipv4)
+				if (run_test_case(&socket_types[s], t, '6',
+						  strict))
+					failures++;
 		}
 	}
 	if (!failures)
diff --git a/tools/testing/selftests/net/rxtimestamp.sh b/tools/testing/selftests/net/rxtimestamp.sh
new file mode 100755
index 000000000000..91631e88bf46
--- /dev/null
+++ b/tools/testing/selftests/net/rxtimestamp.sh
@@ -0,0 +1,4 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+./in_netns.sh ./rxtimestamp $@
diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c
index ceaad78e9667..3155fbbf644b 100644
--- a/tools/testing/selftests/net/so_txtime.c
+++ b/tools/testing/selftests/net/so_txtime.c
@@ -121,7 +121,7 @@ static bool do_recv_one(int fdr, struct timed_send *ts)
 	if (rbuf[0] != ts->data)
 		error(1, 0, "payload mismatch. expected %c", ts->data);
 
-	if (labs(tstop - texpect) > cfg_variance_us)
+	if (llabs(tstop - texpect) > cfg_variance_us)
 		error(1, 0, "exceeds variance (%d us)", cfg_variance_us);
 
 	return false;
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 4555f88252ba..a61b7b3da549 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -344,7 +344,7 @@ int main(int argc, char *argv[])
 {
 	struct sockaddr_storage listenaddr, addr;
 	unsigned int max_pacing_rate = 0;
-	size_t total = 0;
+	uint64_t total = 0;
 	char *host = NULL;
 	int fd, c, on = 1;
 	char *buffer;
@@ -473,12 +473,12 @@ int main(int argc, char *argv[])
 		zflg = 0;
 	}
 	while (total < FILE_SZ) {
-		ssize_t wr = FILE_SZ - total;
+		int64_t wr = FILE_SZ - total;
 
 		if (wr > chunk_size)
 			wr = chunk_size;
 		/* Note : we just want to fill the pipe with 0 bytes */
-		wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0);
+		wr = send(fd, buffer, (size_t)wr, zflg ? MSG_ZEROCOPY : 0);
 		if (wr <= 0)
 			break;
 		total += wr;
diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c
index 011b0da6b033..490a8cca708a 100644
--- a/tools/testing/selftests/net/txtimestamp.c
+++ b/tools/testing/selftests/net/txtimestamp.c
@@ -64,6 +64,7 @@ static int cfg_payload_len = 10;
 static int cfg_poll_timeout = 100;
 static int cfg_delay_snd;
 static int cfg_delay_ack;
+static int cfg_delay_tolerance_usec = 500;
 static bool cfg_show_payload;
 static bool cfg_do_pktinfo;
 static bool cfg_busy_poll;
@@ -152,11 +153,12 @@ static void validate_key(int tskey, int tstype)
 
 static void validate_timestamp(struct timespec *cur, int min_delay)
 {
-	int max_delay = min_delay + 500 /* processing time upper bound */;
 	int64_t cur64, start64;
+	int max_delay;
 
 	cur64 = timespec_to_us64(cur);
 	start64 = timespec_to_us64(&ts_usr);
+	max_delay = min_delay + cfg_delay_tolerance_usec;
 
 	if (cur64 < start64 + min_delay || cur64 > start64 + max_delay) {
 		fprintf(stderr, "ERROR: %lu us expected between %d and %d\n",
@@ -683,6 +685,7 @@ static void __attribute__((noreturn)) usage(const char *filepath)
 			"  -r:   use raw\n"
 			"  -R:   use raw (IP_HDRINCL)\n"
 			"  -S N: usec to sleep before reading error queue\n"
+			"  -t N: tolerance (usec) for timestamp validation\n"
 			"  -u:   use udp\n"
 			"  -v:   validate SND delay (usec)\n"
 			"  -V:   validate ACK delay (usec)\n"
@@ -697,7 +700,7 @@ static void parse_opt(int argc, char **argv)
 	int c;
 
 	while ((c = getopt(argc, argv,
-				"46bc:CeEFhIl:LnNp:PrRS:uv:V:x")) != -1) {
+				"46bc:CeEFhIl:LnNp:PrRS:t:uv:V:x")) != -1) {
 		switch (c) {
 		case '4':
 			do_ipv6 = 0;
@@ -760,6 +763,9 @@ static void parse_opt(int argc, char **argv)
 		case 'S':
 			cfg_sleep_usec = strtoul(optarg, NULL, 10);
 			break;
+		case 't':
+			cfg_delay_tolerance_usec = strtoul(optarg, NULL, 10);
+			break;
 		case 'u':
 			proto_count++;
 			cfg_proto = SOCK_DGRAM;
diff --git a/tools/testing/selftests/net/vrf_strict_mode_test.sh b/tools/testing/selftests/net/vrf_strict_mode_test.sh
new file mode 100755
index 000000000000..18b982d611de
--- /dev/null
+++ b/tools/testing/selftests/net/vrf_strict_mode_test.sh
@@ -0,0 +1,396 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test is designed for testing the new VRF strict_mode functionality.
+
+ret=0
+
+# identifies the "init" network namespace which is often called root network
+# namespace.
+INIT_NETNS_NAME="init"
+
+PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+
+log_test()
+{
+	local rc=$1
+	local expected=$2
+	local msg="$3"
+
+	if [ ${rc} -eq ${expected} ]; then
+		nsuccess=$((nsuccess+1))
+		printf "\n    TEST: %-60s  [ OK ]\n" "${msg}"
+	else
+		ret=1
+		nfail=$((nfail+1))
+		printf "\n    TEST: %-60s  [FAIL]\n" "${msg}"
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+			echo
+			echo "hit enter to continue, 'q' to quit"
+			read a
+			[ "$a" = "q" ] && exit 1
+		fi
+	fi
+}
+
+print_log_test_results()
+{
+	if [ "$TESTS" != "none" ]; then
+		printf "\nTests passed: %3d\n" ${nsuccess}
+		printf "Tests failed: %3d\n"   ${nfail}
+	fi
+}
+
+log_section()
+{
+	echo
+	echo "################################################################################"
+	echo "TEST SECTION: $*"
+	echo "################################################################################"
+}
+
+ip_expand_args()
+{
+	local nsname=$1
+	local nsarg=""
+
+	if [ "${nsname}" != "${INIT_NETNS_NAME}" ]; then
+		nsarg="-netns ${nsname}"
+	fi
+
+	echo "${nsarg}"
+}
+
+vrf_count()
+{
+	local nsname=$1
+	local nsarg="$(ip_expand_args ${nsname})"
+
+	ip ${nsarg} -o link show type vrf | wc -l
+}
+
+count_vrf_by_table_id()
+{
+	local nsname=$1
+	local tableid=$2
+	local nsarg="$(ip_expand_args ${nsname})"
+
+	ip ${nsarg} -d -o link show type vrf | grep "table ${tableid}" | wc -l
+}
+
+add_vrf()
+{
+	local nsname=$1
+	local vrfname=$2
+	local vrftable=$3
+	local nsarg="$(ip_expand_args ${nsname})"
+
+	ip ${nsarg} link add ${vrfname} type vrf table ${vrftable} &>/dev/null
+}
+
+add_vrf_and_check()
+{
+	local nsname=$1
+	local vrfname=$2
+	local vrftable=$3
+	local cnt
+	local rc
+
+	add_vrf ${nsname} ${vrfname} ${vrftable}; rc=$?
+
+	cnt=$(count_vrf_by_table_id ${nsname} ${vrftable})
+
+	log_test ${rc} 0 "${nsname}: add vrf ${vrfname}, ${cnt} vrfs for table ${vrftable}"
+}
+
+add_vrf_and_check_fail()
+{
+	local nsname=$1
+	local vrfname=$2
+	local vrftable=$3
+	local cnt
+	local rc
+
+	add_vrf ${nsname} ${vrfname} ${vrftable}; rc=$?
+
+	cnt=$(count_vrf_by_table_id ${nsname} ${vrftable})
+
+	log_test ${rc} 2 "${nsname}: CANNOT add vrf ${vrfname}, ${cnt} vrfs for table ${vrftable}"
+}
+
+del_vrf_and_check()
+{
+	local nsname=$1
+	local vrfname=$2
+	local nsarg="$(ip_expand_args ${nsname})"
+
+	ip ${nsarg} link del ${vrfname}
+	log_test $? 0 "${nsname}: remove vrf ${vrfname}"
+}
+
+config_vrf_and_check()
+{
+	local nsname=$1
+	local addr=$2
+	local vrfname=$3
+	local nsarg="$(ip_expand_args ${nsname})"
+
+	ip ${nsarg} link set dev ${vrfname} up && \
+		ip ${nsarg} addr add ${addr} dev ${vrfname}
+	log_test $? 0 "${nsname}: vrf ${vrfname} up, addr ${addr}"
+}
+
+read_strict_mode()
+{
+	local nsname=$1
+	local rval
+	local rc=0
+	local nsexec=""
+
+	if [ "${nsname}" != "${INIT_NETNS_NAME}" ]; then
+		# a custom network namespace is provided
+		nsexec="ip netns exec ${nsname}"
+	fi
+
+	rval="$(${nsexec} bash -c "cat /proc/sys/net/vrf/strict_mode" | \
+		grep -E "^[0-1]$")" &> /dev/null
+	if [ $? -ne 0 ]; then
+		# set errors
+		rval=255
+		rc=1
+	fi
+
+	# on success, rval can be only 0 or 1; on error, rval is equal to 255
+	echo ${rval}
+	return ${rc}
+}
+
+read_strict_mode_compare_and_check()
+{
+	local nsname=$1
+	local expected=$2
+	local res
+
+	res="$(read_strict_mode ${nsname})"
+	log_test ${res} ${expected} "${nsname}: check strict_mode=${res}"
+}
+
+set_strict_mode()
+{
+	local nsname=$1
+	local val=$2
+	local nsexec=""
+
+	if [ "${nsname}" != "${INIT_NETNS_NAME}" ]; then
+		# a custom network namespace is provided
+		nsexec="ip netns exec ${nsname}"
+	fi
+
+	${nsexec} bash -c "echo ${val} >/proc/sys/net/vrf/strict_mode" &>/dev/null
+}
+
+enable_strict_mode()
+{
+	local nsname=$1
+
+	set_strict_mode ${nsname} 1
+}
+
+disable_strict_mode()
+{
+	local nsname=$1
+
+	set_strict_mode ${nsname} 0
+}
+
+disable_strict_mode_and_check()
+{
+	local nsname=$1
+
+	disable_strict_mode ${nsname}
+	log_test $? 0 "${nsname}: disable strict_mode (=0)"
+}
+
+enable_strict_mode_and_check()
+{
+	local nsname=$1
+
+	enable_strict_mode ${nsname}
+	log_test $? 0 "${nsname}: enable strict_mode (=1)"
+}
+
+enable_strict_mode_and_check_fail()
+{
+	local nsname=$1
+
+	enable_strict_mode ${nsname}
+	log_test $? 1 "${nsname}: CANNOT enable strict_mode"
+}
+
+strict_mode_check_default()
+{
+	local nsname=$1
+	local strictmode
+	local vrfcnt
+
+	vrfcnt=$(vrf_count ${nsname})
+	strictmode=$(read_strict_mode ${nsname})
+	log_test ${strictmode} 0 "${nsname}: strict_mode=0 by default, ${vrfcnt} vrfs"
+}
+
+setup()
+{
+	modprobe vrf
+
+	ip netns add testns
+	ip netns exec testns ip link set lo up
+}
+
+cleanup()
+{
+	ip netns del testns 2>/dev/null
+
+	ip link del vrf100 2>/dev/null
+	ip link del vrf101 2>/dev/null
+	ip link del vrf102 2>/dev/null
+
+	echo 0 >/proc/sys/net/vrf/strict_mode 2>/dev/null
+}
+
+vrf_strict_mode_tests_init()
+{
+	vrf_strict_mode_check_support init
+
+	strict_mode_check_default init
+
+	add_vrf_and_check init vrf100 100
+	config_vrf_and_check init 172.16.100.1/24 vrf100
+
+	enable_strict_mode_and_check init
+
+	add_vrf_and_check_fail init vrf101 100
+
+	disable_strict_mode_and_check init
+
+	add_vrf_and_check init vrf101 100
+	config_vrf_and_check init 172.16.101.1/24 vrf101
+
+	enable_strict_mode_and_check_fail init
+
+	del_vrf_and_check init vrf101
+
+	enable_strict_mode_and_check init
+
+	add_vrf_and_check init vrf102 102
+	config_vrf_and_check init 172.16.102.1/24 vrf102
+
+	# the strict_modle is enabled in the init
+}
+
+vrf_strict_mode_tests_testns()
+{
+	vrf_strict_mode_check_support testns
+
+	strict_mode_check_default testns
+
+	enable_strict_mode_and_check testns
+
+	add_vrf_and_check testns vrf100 100
+	config_vrf_and_check testns 10.0.100.1/24 vrf100
+
+	add_vrf_and_check_fail testns vrf101 100
+
+	add_vrf_and_check_fail testns vrf102 100
+
+	add_vrf_and_check testns vrf200 200
+
+	disable_strict_mode_and_check testns
+
+	add_vrf_and_check testns vrf101 100
+
+	add_vrf_and_check testns vrf102 100
+
+	#the strict_mode is disabled in the testns
+}
+
+vrf_strict_mode_tests_mix()
+{
+	read_strict_mode_compare_and_check init 1
+
+	read_strict_mode_compare_and_check testns 0
+
+	del_vrf_and_check testns vrf101
+
+	del_vrf_and_check testns vrf102
+
+	disable_strict_mode_and_check init
+
+	enable_strict_mode_and_check testns
+
+	enable_strict_mode_and_check init
+	enable_strict_mode_and_check init
+
+	disable_strict_mode_and_check testns
+	disable_strict_mode_and_check testns
+
+	read_strict_mode_compare_and_check init 1
+
+	read_strict_mode_compare_and_check testns 0
+}
+
+vrf_strict_mode_tests()
+{
+	log_section "VRF strict_mode test on init network namespace"
+	vrf_strict_mode_tests_init
+
+	log_section "VRF strict_mode test on testns network namespace"
+	vrf_strict_mode_tests_testns
+
+	log_section "VRF strict_mode test mixing init and testns network namespaces"
+	vrf_strict_mode_tests_mix
+}
+
+vrf_strict_mode_check_support()
+{
+	local nsname=$1
+	local output
+	local rc
+
+	output="$(lsmod | grep '^vrf' | awk '{print $1}')"
+	if [ -z "${output}" ]; then
+		modinfo vrf || return $?
+	fi
+
+	# we do not care about the value of the strict_mode; we only check if
+	# the strict_mode parameter is available or not.
+	read_strict_mode ${nsname} &>/dev/null; rc=$?
+	log_test ${rc} 0 "${nsname}: net.vrf.strict_mode is available"
+
+	return ${rc}
+}
+
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit 0
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+	echo "SKIP: Could not run test without ip tool"
+	exit 0
+fi
+
+modprobe vrf &>/dev/null
+if [ ! -e /proc/sys/net/vrf/strict_mode ]; then
+	echo "SKIP: vrf sysctl does not exist"
+	exit 0
+fi
+
+cleanup &> /dev/null
+
+setup
+vrf_strict_mode_tests
+cleanup
+
+print_log_test_results
+
+exit $ret
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index a179f0dca8ce..a374e10ef506 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -4,7 +4,7 @@
 TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
 	conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
 	nft_concat_range.sh nft_conntrack_helper.sh \
-	nft_queue.sh
+	nft_queue.sh nft_meta.sh
 
 LDLIBS = -lmnl
 TEST_GEN_FILES =  nf-queue
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index d3e0809ab368..a47d1d832210 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -2,13 +2,18 @@
 # SPDX-License-Identifier: GPL-2.0
 #
 # This tests basic flowtable functionality.
-# Creates following topology:
+# Creates following default topology:
 #
 # Originator (MTU 9000) <-Router1-> MTU 1500 <-Router2-> Responder (MTU 2000)
 # Router1 is the one doing flow offloading, Router2 has no special
 # purpose other than having a link that is smaller than either Originator
 # and responder, i.e. TCPMSS announced values are too large and will still
 # result in fragmentation and/or PMTU discovery.
+#
+# You can check with different Orgininator/Link/Responder MTU eg:
+# sh nft_flowtable.sh -o1000 -l500 -r100
+#
+
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
@@ -21,29 +26,18 @@ ns2out=""
 
 log_netns=$(sysctl -n net.netfilter.nf_log_all_netns)
 
-nft --version > /dev/null 2>&1
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not run test without nft tool"
-	exit $ksft_skip
-fi
-
-ip -Version > /dev/null 2>&1
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not run test without ip tool"
-	exit $ksft_skip
-fi
-
-which nc > /dev/null 2>&1
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not run test without nc (netcat)"
-	exit $ksft_skip
-fi
+checktool (){
+	$1 > /dev/null 2>&1
+	if [ $? -ne 0 ];then
+		echo "SKIP: Could not $2"
+		exit $ksft_skip
+	fi
+}
 
-ip netns add nsr1
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not create net namespace"
-	exit $ksft_skip
-fi
+checktool "nft --version" "run test without nft tool"
+checktool "ip -Version" "run test without ip tool"
+checktool "which nc" "run test without nc (netcat)"
+checktool "ip netns add nsr1" "create net namespace"
 
 ip netns add ns1
 ip netns add ns2
@@ -89,11 +83,24 @@ ip -net nsr2 addr add dead:2::1/64 dev veth1
 # ns2 is going via nsr2 with a smaller mtu, so that TCPMSS announced by both peers
 # is NOT the lowest link mtu.
 
-ip -net nsr1 link set veth0 mtu 9000
-ip -net ns1 link set eth0 mtu 9000
+omtu=9000
+lmtu=1500
+rmtu=2000
+
+while getopts "o:l:r:" o
+do
+	case $o in
+		o) omtu=$OPTARG;;
+		l) lmtu=$OPTARG;;
+		r) rmtu=$OPTARG;;
+	esac
+done
+
+ip -net nsr1 link set veth0 mtu $omtu
+ip -net ns1 link set eth0 mtu $omtu
 
-ip -net nsr2 link set veth1 mtu 2000
-ip -net ns2 link set eth0 mtu 2000
+ip -net nsr2 link set veth1 mtu $rmtu
+ip -net ns2 link set eth0 mtu $rmtu
 
 # transfer-net between nsr1 and nsr2.
 # these addresses are not used for connections.
@@ -147,7 +154,7 @@ table inet filter {
       # as PMTUd is off.
       # This rule is deleted for the last test, when we expect PMTUd
       # to kick in and ensure all packets meet mtu requirements.
-      meta length gt 1500 accept comment something-to-grep-for
+      meta length gt $lmtu accept comment something-to-grep-for
 
       # next line blocks connection w.o. working offload.
       # we only do this for reverse dir, because we expect packets to
@@ -243,8 +250,14 @@ test_tcp_forwarding_ip()
 
 	sleep 3
 
-	kill $lpid
-	kill $cpid
+	if ps -p $lpid > /dev/null;then
+		kill $lpid
+	fi
+
+	if ps -p $cpid > /dev/null;then
+		kill $cpid
+	fi
+
 	wait
 
 	check_transfer "$ns1in" "$ns2out" "ns1 -> ns2"
diff --git a/tools/testing/selftests/netfilter/nft_meta.sh b/tools/testing/selftests/netfilter/nft_meta.sh
new file mode 100755
index 000000000000..d250b84dd5bc
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_meta.sh
@@ -0,0 +1,124 @@
+#!/bin/bash
+
+# check iif/iifname/oifgroup/iiftype match.
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+sfx=$(mktemp -u "XXXXXXXX")
+ns0="ns0-$sfx"
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+cleanup()
+{
+	ip netns del "$ns0"
+}
+
+ip netns add "$ns0"
+ip -net "$ns0" link set lo up
+ip -net "$ns0" addr add 127.0.0.1 dev lo
+
+trap cleanup EXIT
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table inet filter {
+	counter iifcount {}
+	counter iifnamecount {}
+	counter iifgroupcount {}
+	counter iiftypecount {}
+	counter infproto4count {}
+	counter il4protocounter {}
+	counter imarkcounter {}
+
+	counter oifcount {}
+	counter oifnamecount {}
+	counter oifgroupcount {}
+	counter oiftypecount {}
+	counter onfproto4count {}
+	counter ol4protocounter {}
+	counter oskuidcounter {}
+	counter oskgidcounter {}
+	counter omarkcounter {}
+
+	chain input {
+		type filter hook input priority 0; policy accept;
+
+		meta iif lo counter name "iifcount"
+		meta iifname "lo" counter name "iifnamecount"
+		meta iifgroup "default" counter name "iifgroupcount"
+		meta iiftype "loopback" counter name "iiftypecount"
+		meta nfproto ipv4 counter name "infproto4count"
+		meta l4proto icmp counter name "il4protocounter"
+		meta mark 42 counter name "imarkcounter"
+	}
+
+	chain output {
+		type filter hook output priority 0; policy accept;
+		meta oif lo counter name "oifcount" counter
+		meta oifname "lo" counter name "oifnamecount"
+		meta oifgroup "default" counter name "oifgroupcount"
+		meta oiftype "loopback" counter name "oiftypecount"
+		meta nfproto ipv4 counter name "onfproto4count"
+		meta l4proto icmp counter name "ol4protocounter"
+		meta skuid 0 counter name "oskuidcounter"
+		meta skgid 0 counter name "oskgidcounter"
+		meta mark 42 counter name "omarkcounter"
+	}
+}
+EOF
+
+if [ $? -ne 0 ]; then
+	echo "SKIP: Could not add test ruleset"
+	exit $ksft_skip
+fi
+
+ret=0
+
+check_one_counter()
+{
+	local cname="$1"
+	local want="packets $2"
+	local verbose="$3"
+
+	cnt=$(ip netns exec "$ns0" nft list counter inet filter $cname | grep -q "$want")
+	if [ $? -ne 0 ];then
+		echo "FAIL: $cname, want \"$want\", got"
+		ret=1
+		ip netns exec "$ns0" nft list counter inet filter $counter
+	fi
+}
+
+check_lo_counters()
+{
+	local want="$1"
+	local verbose="$2"
+	local counter
+
+	for counter in iifcount iifnamecount iifgroupcount iiftypecount infproto4count \
+		       oifcount oifnamecount oifgroupcount oiftypecount onfproto4count \
+		       il4protocounter \
+		       ol4protocounter \
+	     ; do
+		check_one_counter "$counter" "$want" "$verbose"
+	done
+}
+
+check_lo_counters "0" false
+ip netns exec "$ns0" ping -q -c 1 127.0.0.1 -m 42 > /dev/null
+
+check_lo_counters "2" true
+
+check_one_counter oskuidcounter "1" true
+check_one_counter oskgidcounter "1" true
+check_one_counter imarkcounter "1" true
+check_one_counter omarkcounter "1" true
+
+if [ $ret -eq 0 ];then
+	echo "OK: nftables meta iif/oif counters at expected values"
+fi
+
+exit $ret
diff --git a/tools/testing/selftests/pid_namespace/regression_enomem.c b/tools/testing/selftests/pid_namespace/regression_enomem.c
index 73d532556d17..7d84097ad45c 100644
--- a/tools/testing/selftests/pid_namespace/regression_enomem.c
+++ b/tools/testing/selftests/pid_namespace/regression_enomem.c
@@ -11,7 +11,6 @@
 #include <syscall.h>
 #include <sys/wait.h>
 
-#include "../kselftest.h"
 #include "../kselftest_harness.h"
 #include "../pidfd/pidfd.h"
 
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index 8d728eda783d..a2c80914e3dc 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -22,6 +22,10 @@
 #define P_PIDFD 3
 #endif
 
+#ifndef CLONE_NEWTIME
+#define CLONE_NEWTIME 0x00000080
+#endif
+
 #ifndef CLONE_PIDFD
 #define CLONE_PIDFD 0x00001000
 #endif
diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
index 84b65ecccb04..7758c98be015 100644
--- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
@@ -18,7 +18,6 @@
 #include <linux/kcmp.h>
 
 #include "pidfd.h"
-#include "../kselftest.h"
 #include "../kselftest_harness.h"
 
 /*
diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c
index 9418108eae13..7dca1aa4672d 100644
--- a/tools/testing/selftests/pidfd/pidfd_setns_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c
@@ -20,7 +20,6 @@
 
 #include "pidfd.h"
 #include "../clone3/clone3_selftests.h"
-#include "../kselftest.h"
 #include "../kselftest_harness.h"
 
 enum {
@@ -32,6 +31,7 @@ enum {
 	PIDFD_NS_NET,
 	PIDFD_NS_CGROUP,
 	PIDFD_NS_PIDCLD,
+	PIDFD_NS_TIME,
 	PIDFD_NS_MAX
 };
 
@@ -47,6 +47,7 @@ const struct ns_info {
 	[PIDFD_NS_NET]    = { "net",              CLONE_NEWNET,    },
 	[PIDFD_NS_CGROUP] = { "cgroup",           CLONE_NEWCGROUP, },
 	[PIDFD_NS_PIDCLD] = { "pid_for_children", 0,               },
+	[PIDFD_NS_TIME]	  = { "time",             CLONE_NEWTIME,   },
 };
 
 FIXTURE(current_nsset)
@@ -83,9 +84,49 @@ pid_t create_child(int *pidfd, unsigned flags)
 	return sys_clone3(&args, sizeof(struct clone_args));
 }
 
+static bool switch_timens(void)
+{
+	int fd, ret;
+
+	if (unshare(CLONE_NEWTIME))
+		return false;
+
+	fd = open("/proc/self/ns/time_for_children", O_RDONLY | O_CLOEXEC);
+	if (fd < 0)
+		return false;
+
+	ret = setns(fd, CLONE_NEWTIME);
+	close(fd);
+	return ret == 0;
+}
+
+static ssize_t read_nointr(int fd, void *buf, size_t count)
+{
+	ssize_t ret;
+
+	do {
+		ret = read(fd, buf, count);
+	} while (ret < 0 && errno == EINTR);
+
+	return ret;
+}
+
+static ssize_t write_nointr(int fd, const void *buf, size_t count)
+{
+	ssize_t ret;
+
+	do {
+		ret = write(fd, buf, count);
+	} while (ret < 0 && errno == EINTR);
+
+	return ret;
+}
+
 FIXTURE_SETUP(current_nsset)
 {
 	int i, proc_fd, ret;
+	int ipc_sockets[2];
+	char c;
 
 	for (i = 0; i < PIDFD_NS_MAX; i++) {
 		self->nsfds[i]		= -EBADF;
@@ -130,6 +171,9 @@ FIXTURE_SETUP(current_nsset)
 		TH_LOG("%m - Failed to open pidfd for process %d", self->pid);
 	}
 
+	ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	EXPECT_EQ(ret, 0);
+
 	/* Create tasks that will be stopped. */
 	self->child_pid1 = create_child(&self->child_pidfd1,
 					CLONE_NEWUSER | CLONE_NEWNS |
@@ -139,10 +183,27 @@ FIXTURE_SETUP(current_nsset)
 	EXPECT_GE(self->child_pid1, 0);
 
 	if (self->child_pid1 == 0) {
+		close(ipc_sockets[0]);
+
+		if (!switch_timens())
+			_exit(EXIT_FAILURE);
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			_exit(EXIT_FAILURE);
+
+		close(ipc_sockets[1]);
+
 		pause();
 		_exit(EXIT_SUCCESS);
 	}
 
+	close(ipc_sockets[1]);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	close(ipc_sockets[0]);
+
+	ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	EXPECT_EQ(ret, 0);
+
 	self->child_pid2 = create_child(&self->child_pidfd2,
 					CLONE_NEWUSER | CLONE_NEWNS |
 					CLONE_NEWCGROUP | CLONE_NEWIPC |
@@ -151,10 +212,24 @@ FIXTURE_SETUP(current_nsset)
 	EXPECT_GE(self->child_pid2, 0);
 
 	if (self->child_pid2 == 0) {
+		close(ipc_sockets[0]);
+
+		if (!switch_timens())
+			_exit(EXIT_FAILURE);
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			_exit(EXIT_FAILURE);
+
+		close(ipc_sockets[1]);
+
 		pause();
 		_exit(EXIT_SUCCESS);
 	}
 
+	close(ipc_sockets[1]);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	close(ipc_sockets[0]);
+
 	for (i = 0; i < PIDFD_NS_MAX; i++) {
 		char p[100];
 
diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c
index 7aff2d3b42c0..c585aaa2acd8 100644
--- a/tools/testing/selftests/pidfd/pidfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_test.c
@@ -8,6 +8,7 @@
 #include <sched.h>
 #include <signal.h>
 #include <stdio.h>
+#include <stdbool.h>
 #include <stdlib.h>
 #include <string.h>
 #include <syscall.h>
@@ -27,6 +28,8 @@
 
 #define MAX_EVENTS 5
 
+static bool have_pidfd_send_signal;
+
 static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *))
 {
 	size_t stack_size = 1024;
@@ -56,6 +59,13 @@ static int test_pidfd_send_signal_simple_success(void)
 	int pidfd, ret;
 	const char *test_name = "pidfd_send_signal send SIGUSR1";
 
+	if (!have_pidfd_send_signal) {
+		ksft_test_result_skip(
+			"%s test: pidfd_send_signal() syscall not supported\n",
+			test_name);
+		return 0;
+	}
+
 	pidfd = open("/proc/self", O_DIRECTORY | O_CLOEXEC);
 	if (pidfd < 0)
 		ksft_exit_fail_msg(
@@ -86,6 +96,13 @@ static int test_pidfd_send_signal_exited_fail(void)
 	pid_t pid;
 	const char *test_name = "pidfd_send_signal signal exited process";
 
+	if (!have_pidfd_send_signal) {
+		ksft_test_result_skip(
+			"%s test: pidfd_send_signal() syscall not supported\n",
+			test_name);
+		return 0;
+	}
+
 	pid = fork();
 	if (pid < 0)
 		ksft_exit_fail_msg("%s test: Failed to create new process\n",
@@ -137,16 +154,34 @@ static int test_pidfd_send_signal_recycled_pid_fail(void)
 	pid_t pid1;
 	const char *test_name = "pidfd_send_signal signal recycled pid";
 
+	if (!have_pidfd_send_signal) {
+		ksft_test_result_skip(
+			"%s test: pidfd_send_signal() syscall not supported\n",
+			test_name);
+		return 0;
+	}
+
 	ret = unshare(CLONE_NEWPID);
-	if (ret < 0)
+	if (ret < 0) {
+		if (errno == EPERM) {
+			ksft_test_result_skip("%s test: Unsharing pid namespace not permitted\n",
+					      test_name);
+			return 0;
+		}
 		ksft_exit_fail_msg("%s test: Failed to unshare pid namespace\n",
 				   test_name);
+	}
 
 	ret = unshare(CLONE_NEWNS);
-	if (ret < 0)
-		ksft_exit_fail_msg(
-			"%s test: Failed to unshare mount namespace\n",
-			test_name);
+	if (ret < 0) {
+		if (errno == EPERM) {
+			ksft_test_result_skip("%s test: Unsharing mount namespace not permitted\n",
+					      test_name);
+			return 0;
+		}
+		ksft_exit_fail_msg("%s test: Failed to unshare mount namespace\n",
+				   test_name);
+	}
 
 	ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0);
 	if (ret < 0)
@@ -325,15 +360,17 @@ static int test_pidfd_send_signal_syscall_support(void)
 
 	ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0);
 	if (ret < 0) {
-		if (errno == ENOSYS)
-			ksft_exit_skip(
+		if (errno == ENOSYS) {
+			ksft_test_result_skip(
 				"%s test: pidfd_send_signal() syscall not supported\n",
 				test_name);
-
+			return 0;
+		}
 		ksft_exit_fail_msg("%s test: Failed to send signal\n",
 				   test_name);
 	}
 
+	have_pidfd_send_signal = true;
 	close(pidfd);
 	ksft_test_result_pass(
 		"%s test: pidfd_send_signal() syscall is supported. Tests can be executed\n",
@@ -521,7 +558,7 @@ static void test_pidfd_poll_leader_exit(int use_waitpid)
 int main(int argc, char **argv)
 {
 	ksft_print_header();
-	ksft_set_plan(4);
+	ksft_set_plan(8);
 
 	test_pidfd_poll_exec(0);
 	test_pidfd_poll_exec(1);
diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
index 0453c50c949c..55ef15184057 100644
--- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c
+++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
@@ -9,7 +9,17 @@
  * This selftest exercises the powerpc alignment fault handler.
  *
  * We create two sets of source and destination buffers, one in regular memory,
- * the other cache-inhibited (we use /dev/fb0 for this).
+ * the other cache-inhibited (by default we use /dev/fb0 for this, but an
+ * alterative path for cache-inhibited memory may be provided).
+ *
+ * One way to get cache-inhibited memory is to use the "mem" kernel parameter
+ * to limit the kernel to less memory than actually exists.  Addresses above
+ * the limit may still be accessed but will be treated as cache-inhibited. For
+ * example, if there is actually 4GB of memory and the parameter "mem=3GB" is
+ * used, memory from address 0xC0000000 onwards is treated as cache-inhibited.
+ * To access this region /dev/mem is used. The kernel should be configured
+ * without CONFIG_STRICT_DEVMEM. In this case use:
+ *         ./alignment_handler /dev/mem 0xc0000000
  *
  * We initialise the source buffers, then use whichever set of load/store
  * instructions is under test to copy bytes from the source buffers to the
@@ -48,11 +58,14 @@
 #include <asm/cputable.h>
 
 #include "utils.h"
+#include "instructions.h"
 
 int bufsize;
 int debug;
 int testing;
 volatile int gotsig;
+char *cipath = "/dev/fb0";
+long cioffset;
 
 void sighandler(int sig, siginfo_t *info, void *ctx)
 {
@@ -84,6 +97,17 @@ void sighandler(int sig, siginfo_t *info, void *ctx)
 	}							\
 	rc |= do_test(#name, test_##name)
 
+#define TESTP(name, ld_op, st_op, ld_reg, st_reg)		\
+	void test_##name(char *s, char *d)			\
+	{							\
+		asm volatile(					\
+			ld_op(ld_reg, %0, 0, 0)			\
+			st_op(st_reg, %1, 0, 0)			\
+			:: "r"(s), "r"(d), "r"(0)		\
+			: "memory", "vs0", "vs32", "r31");	\
+	}							\
+	rc |= do_test(#name, test_##name)
+
 #define LOAD_VSX_XFORM_TEST(op) TEST(op, op, stxvd2x, XFORM, 32, 32)
 #define STORE_VSX_XFORM_TEST(op) TEST(op, lxvd2x, op, XFORM, 32, 32)
 #define LOAD_VSX_DFORM_TEST(op) TEST(op, op, stxv, DFORM, 32, 32)
@@ -103,6 +127,17 @@ void sighandler(int sig, siginfo_t *info, void *ctx)
 #define LOAD_FLOAT_XFORM_TEST(op)  TEST(op, op, stfdx, XFORM, 0, 0)
 #define STORE_FLOAT_XFORM_TEST(op) TEST(op, lfdx, op, XFORM, 0, 0)
 
+#define LOAD_MLS_PREFIX_TEST(op) TESTP(op, op, PSTD, 31, 31)
+#define STORE_MLS_PREFIX_TEST(op) TESTP(op, PLD, op, 31, 31)
+
+#define LOAD_8LS_PREFIX_TEST(op) TESTP(op, op, PSTD, 31, 31)
+#define STORE_8LS_PREFIX_TEST(op) TESTP(op, PLD, op, 31, 31)
+
+#define LOAD_FLOAT_MLS_PREFIX_TEST(op) TESTP(op, op, PSTFD, 0, 0)
+#define STORE_FLOAT_MLS_PREFIX_TEST(op) TESTP(op, PLFD, op, 0, 0)
+
+#define LOAD_VSX_8LS_PREFIX_TEST(op, tail) TESTP(op, op, PSTXV ## tail, 0, 32)
+#define STORE_VSX_8LS_PREFIX_TEST(op, tail) TESTP(op, PLXV ## tail, op, 32, 0)
 
 /* FIXME: Unimplemented tests: */
 // STORE_DFORM_TEST(stq)   /* FIXME: need two registers for quad */
@@ -195,17 +230,18 @@ int do_test(char *test_name, void (*test_func)(char *, char *))
 
 	printf("\tDoing %s:\t", test_name);
 
-	fd = open("/dev/fb0", O_RDWR);
+	fd = open(cipath, O_RDWR);
 	if (fd < 0) {
 		printf("\n");
-		perror("Can't open /dev/fb0 now?");
+		perror("Can't open ci file now?");
 		return 1;
 	}
 
-	ci0 = mmap(NULL, bufsize, PROT_WRITE, MAP_SHARED,
-		   fd, 0x0);
-	ci1 = mmap(NULL, bufsize, PROT_WRITE, MAP_SHARED,
-		   fd, bufsize);
+	ci0 = mmap(NULL, bufsize, PROT_WRITE | PROT_READ, MAP_SHARED,
+		   fd, cioffset);
+	ci1 = mmap(NULL, bufsize, PROT_WRITE | PROT_READ, MAP_SHARED,
+		   fd, cioffset + bufsize);
+
 	if ((ci0 == MAP_FAILED) || (ci1 == MAP_FAILED)) {
 		printf("\n");
 		perror("mmap failed");
@@ -270,11 +306,11 @@ int do_test(char *test_name, void (*test_func)(char *, char *))
 	return rc;
 }
 
-static bool can_open_fb0(void)
+static bool can_open_cifile(void)
 {
 	int fd;
 
-	fd = open("/dev/fb0", O_RDWR);
+	fd = open(cipath, O_RDWR);
 	if (fd < 0)
 		return false;
 
@@ -286,7 +322,7 @@ int test_alignment_handler_vsx_206(void)
 {
 	int rc = 0;
 
-	SKIP_IF(!can_open_fb0());
+	SKIP_IF(!can_open_cifile());
 	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
 
 	printf("VSX: 2.06B\n");
@@ -304,7 +340,7 @@ int test_alignment_handler_vsx_207(void)
 {
 	int rc = 0;
 
-	SKIP_IF(!can_open_fb0());
+	SKIP_IF(!can_open_cifile());
 	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07));
 
 	printf("VSX: 2.07B\n");
@@ -320,7 +356,7 @@ int test_alignment_handler_vsx_300(void)
 {
 	int rc = 0;
 
-	SKIP_IF(!can_open_fb0());
+	SKIP_IF(!can_open_cifile());
 
 	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00));
 	printf("VSX: 3.00B\n");
@@ -348,11 +384,30 @@ int test_alignment_handler_vsx_300(void)
 	return rc;
 }
 
+int test_alignment_handler_vsx_prefix(void)
+{
+	int rc = 0;
+
+	SKIP_IF(!can_open_cifile());
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1));
+
+	printf("VSX: PREFIX\n");
+	LOAD_VSX_8LS_PREFIX_TEST(PLXSD, 0);
+	LOAD_VSX_8LS_PREFIX_TEST(PLXSSP, 0);
+	LOAD_VSX_8LS_PREFIX_TEST(PLXV0, 0);
+	LOAD_VSX_8LS_PREFIX_TEST(PLXV1, 1);
+	STORE_VSX_8LS_PREFIX_TEST(PSTXSD, 0);
+	STORE_VSX_8LS_PREFIX_TEST(PSTXSSP, 0);
+	STORE_VSX_8LS_PREFIX_TEST(PSTXV0, 0);
+	STORE_VSX_8LS_PREFIX_TEST(PSTXV1, 1);
+	return rc;
+}
+
 int test_alignment_handler_integer(void)
 {
 	int rc = 0;
 
-	SKIP_IF(!can_open_fb0());
+	SKIP_IF(!can_open_cifile());
 
 	printf("Integer\n");
 	LOAD_DFORM_TEST(lbz);
@@ -408,7 +463,7 @@ int test_alignment_handler_integer_206(void)
 {
 	int rc = 0;
 
-	SKIP_IF(!can_open_fb0());
+	SKIP_IF(!can_open_cifile());
 	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
 
 	printf("Integer: 2.06\n");
@@ -419,11 +474,32 @@ int test_alignment_handler_integer_206(void)
 	return rc;
 }
 
+int test_alignment_handler_integer_prefix(void)
+{
+	int rc = 0;
+
+	SKIP_IF(!can_open_cifile());
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1));
+
+	printf("Integer: PREFIX\n");
+	LOAD_MLS_PREFIX_TEST(PLBZ);
+	LOAD_MLS_PREFIX_TEST(PLHZ);
+	LOAD_MLS_PREFIX_TEST(PLHA);
+	LOAD_MLS_PREFIX_TEST(PLWZ);
+	LOAD_8LS_PREFIX_TEST(PLWA);
+	LOAD_8LS_PREFIX_TEST(PLD);
+	STORE_MLS_PREFIX_TEST(PSTB);
+	STORE_MLS_PREFIX_TEST(PSTH);
+	STORE_MLS_PREFIX_TEST(PSTW);
+	STORE_8LS_PREFIX_TEST(PSTD);
+	return rc;
+}
+
 int test_alignment_handler_vmx(void)
 {
 	int rc = 0;
 
-	SKIP_IF(!can_open_fb0());
+	SKIP_IF(!can_open_cifile());
 	SKIP_IF(!have_hwcap(PPC_FEATURE_HAS_ALTIVEC));
 
 	printf("VMX\n");
@@ -451,7 +527,7 @@ int test_alignment_handler_fp(void)
 {
 	int rc = 0;
 
-	SKIP_IF(!can_open_fb0());
+	SKIP_IF(!can_open_cifile());
 
 	printf("Floating point\n");
 	LOAD_FLOAT_DFORM_TEST(lfd);
@@ -479,7 +555,7 @@ int test_alignment_handler_fp_205(void)
 {
 	int rc = 0;
 
-	SKIP_IF(!can_open_fb0());
+	SKIP_IF(!can_open_cifile());
 	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_05));
 
 	printf("Floating point: 2.05\n");
@@ -497,7 +573,7 @@ int test_alignment_handler_fp_206(void)
 {
 	int rc = 0;
 
-	SKIP_IF(!can_open_fb0());
+	SKIP_IF(!can_open_cifile());
 	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
 
 	printf("Floating point: 2.06\n");
@@ -507,13 +583,32 @@ int test_alignment_handler_fp_206(void)
 	return rc;
 }
 
+
+int test_alignment_handler_fp_prefix(void)
+{
+	int rc = 0;
+
+	SKIP_IF(!can_open_cifile());
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1));
+
+	printf("Floating point: PREFIX\n");
+	LOAD_FLOAT_DFORM_TEST(lfs);
+	LOAD_FLOAT_MLS_PREFIX_TEST(PLFS);
+	LOAD_FLOAT_MLS_PREFIX_TEST(PLFD);
+	STORE_FLOAT_MLS_PREFIX_TEST(PSTFS);
+	STORE_FLOAT_MLS_PREFIX_TEST(PSTFD);
+	return rc;
+}
+
 void usage(char *prog)
 {
-	printf("Usage: %s [options]\n", prog);
+	printf("Usage: %s [options] [path [offset]]\n", prog);
 	printf("  -d	Enable debug error output\n");
 	printf("\n");
-	printf("This test requires a POWER8 or POWER9 CPU and a usable ");
-	printf("framebuffer at /dev/fb0.\n");
+	printf("This test requires a POWER8, POWER9 or POWER10 CPU ");
+	printf("and either a usable framebuffer at /dev/fb0 or ");
+	printf("the path to usable cache inhibited memory and optional ");
+	printf("offset to be provided\n");
 }
 
 int main(int argc, char *argv[])
@@ -533,6 +628,13 @@ int main(int argc, char *argv[])
 			exit(1);
 		}
 	}
+	argc -= optind;
+	argv += optind;
+
+	if (argc > 0)
+		cipath = argv[0];
+	if (argc > 1)
+		cioffset = strtol(argv[1], 0, 0x10);
 
 	bufsize = getpagesize();
 
@@ -552,10 +654,14 @@ int main(int argc, char *argv[])
 			   "test_alignment_handler_vsx_207");
 	rc |= test_harness(test_alignment_handler_vsx_300,
 			   "test_alignment_handler_vsx_300");
+	rc |= test_harness(test_alignment_handler_vsx_prefix,
+			   "test_alignment_handler_vsx_prefix");
 	rc |= test_harness(test_alignment_handler_integer,
 			   "test_alignment_handler_integer");
 	rc |= test_harness(test_alignment_handler_integer_206,
 			   "test_alignment_handler_integer_206");
+	rc |= test_harness(test_alignment_handler_integer_prefix,
+			   "test_alignment_handler_integer_prefix");
 	rc |= test_harness(test_alignment_handler_vmx,
 			   "test_alignment_handler_vmx");
 	rc |= test_harness(test_alignment_handler_fp,
@@ -564,5 +670,7 @@ int main(int argc, char *argv[])
 			   "test_alignment_handler_fp_205");
 	rc |= test_harness(test_alignment_handler_fp_206,
 			   "test_alignment_handler_fp_206");
+	rc |= test_harness(test_alignment_handler_fp_prefix,
+			   "test_alignment_handler_fp_prefix");
 	return rc;
 }
diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
index a2e8c9da7fa5..d50cc05df495 100644
--- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c
+++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
@@ -19,6 +19,7 @@
 #include <limits.h>
 #include <sys/time.h>
 #include <sys/syscall.h>
+#include <sys/sysinfo.h>
 #include <sys/types.h>
 #include <sys/shm.h>
 #include <linux/futex.h>
@@ -104,8 +105,9 @@ static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 
 static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 {
-	int pid;
-	cpu_set_t cpuset;
+	int pid, ncpus;
+	cpu_set_t *cpuset;
+	size_t size;
 
 	pid = fork();
 	if (pid == -1) {
@@ -116,14 +118,23 @@ static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 	if (pid)
 		return;
 
-	CPU_ZERO(&cpuset);
-	CPU_SET(cpu, &cpuset);
+	ncpus = get_nprocs();
+	size = CPU_ALLOC_SIZE(ncpus);
+	cpuset = CPU_ALLOC(ncpus);
+	if (!cpuset) {
+		perror("malloc");
+		exit(1);
+	}
+	CPU_ZERO_S(size, cpuset);
+	CPU_SET_S(cpu, size, cpuset);
 
-	if (sched_setaffinity(0, sizeof(cpuset), &cpuset)) {
+	if (sched_setaffinity(0, size, cpuset)) {
 		perror("sched_setaffinity");
+		CPU_FREE(cpuset);
 		exit(1);
 	}
 
+	CPU_FREE(cpuset);
 	fn(arg);
 
 	exit(0);
diff --git a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
index f52ed92b53e7..00dc32c0ed75 100755
--- a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
+++ b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
@@ -5,12 +5,17 @@ pe_ok() {
 	local dev="$1"
 	local path="/sys/bus/pci/devices/$dev/eeh_pe_state"
 
-	if ! [ -e "$path" ] ; then
+	# if a driver doesn't support the error handling callbacks then the
+	# device is recovered by removing and re-probing it. This causes the
+	# sysfs directory to disappear so read the PE state once and squash
+	# any potential error messages
+	local eeh_state="$(cat $path 2>/dev/null)"
+	if [ -z "$eeh_state" ]; then
 		return 1;
 	fi
 
-	local fw_state="$(cut -d' ' -f1 < $path)"
-	local sw_state="$(cut -d' ' -f2 < $path)"
+	local fw_state="$(echo $eeh_state | cut -d' ' -f1)"
+	local sw_state="$(echo $eeh_state | cut -d' ' -f2)"
 
 	# If EEH_PE_ISOLATED or EEH_PE_RECOVERING are set then the PE is in an
 	# error state or being recovered. Either way, not ok.
diff --git a/tools/testing/selftests/powerpc/include/instructions.h b/tools/testing/selftests/powerpc/include/instructions.h
index f36061eb6f0f..4efa6314bd96 100644
--- a/tools/testing/selftests/powerpc/include/instructions.h
+++ b/tools/testing/selftests/powerpc/include/instructions.h
@@ -66,4 +66,81 @@ static inline int paste_last(void *i)
 #define PPC_INST_PASTE                 __PASTE(0, 0, 0, 0)
 #define PPC_INST_PASTE_LAST            __PASTE(0, 0, 1, 1)
 
+/* This defines the prefixed load/store instructions */
+#ifdef __ASSEMBLY__
+#  define stringify_in_c(...)	__VA_ARGS__
+#else
+#  define __stringify_in_c(...)	#__VA_ARGS__
+#  define stringify_in_c(...)	__stringify_in_c(__VA_ARGS__) " "
+#endif
+
+#define __PPC_RA(a)	(((a) & 0x1f) << 16)
+#define __PPC_RS(s)	(((s) & 0x1f) << 21)
+#define __PPC_RT(t)	__PPC_RS(t)
+#define __PPC_PREFIX_R(r)	(((r) & 0x1) << 20)
+
+#define PPC_PREFIX_MLS			0x06000000
+#define PPC_PREFIX_8LS			0x04000000
+
+#define PPC_INST_LBZ			0x88000000
+#define PPC_INST_LHZ			0xa0000000
+#define PPC_INST_LHA			0xa8000000
+#define PPC_INST_LWZ			0x80000000
+#define PPC_INST_STB			0x98000000
+#define PPC_INST_STH			0xb0000000
+#define PPC_INST_STW			0x90000000
+#define PPC_INST_STD			0xf8000000
+#define PPC_INST_LFS			0xc0000000
+#define PPC_INST_LFD			0xc8000000
+#define PPC_INST_STFS			0xd0000000
+#define PPC_INST_STFD			0xd8000000
+
+#define PREFIX_MLS(instr, t, a, r, d)	stringify_in_c(.balign 64, , 4;)		\
+					stringify_in_c(.long PPC_PREFIX_MLS |		\
+						       __PPC_PREFIX_R(r) |		\
+						       (((d) >> 16) & 0x3ffff);)	\
+					stringify_in_c(.long (instr)  |			\
+						       __PPC_RT(t) |			\
+						       __PPC_RA(a) |			\
+						       ((d) & 0xffff);\n)
+
+#define PREFIX_8LS(instr, t, a, r, d)	stringify_in_c(.balign 64, , 4;)		\
+					stringify_in_c(.long PPC_PREFIX_8LS |		\
+						       __PPC_PREFIX_R(r) |		\
+						       (((d) >> 16) & 0x3ffff);)	\
+					stringify_in_c(.long (instr)  |			\
+						       __PPC_RT(t) |			\
+						       __PPC_RA(a) |			\
+						       ((d) & 0xffff);\n)
+
+/* Prefixed Integer Load/Store instructions */
+#define PLBZ(t, a, r, d)		PREFIX_MLS(PPC_INST_LBZ, t, a, r, d)
+#define PLHZ(t, a, r, d)		PREFIX_MLS(PPC_INST_LHZ, t, a, r, d)
+#define PLHA(t, a, r, d)		PREFIX_MLS(PPC_INST_LHA, t, a, r, d)
+#define PLWZ(t, a, r, d)		PREFIX_MLS(PPC_INST_LWZ, t, a, r, d)
+#define PLWA(t, a, r, d)		PREFIX_8LS(0xa4000000, t, a, r, d)
+#define PLD(t, a, r, d)			PREFIX_8LS(0xe4000000, t, a, r, d)
+#define PLQ(t, a, r, d)			PREFIX_8LS(0xe0000000, t, a, r, d)
+#define PSTB(s, a, r, d)		PREFIX_MLS(PPC_INST_STB, s, a, r, d)
+#define PSTH(s, a, r, d)		PREFIX_MLS(PPC_INST_STH, s, a, r, d)
+#define PSTW(s, a, r, d)		PREFIX_MLS(PPC_INST_STW, s, a, r, d)
+#define PSTD(s, a, r, d)		PREFIX_8LS(0xf4000000, s, a, r, d)
+#define PSTQ(s, a, r, d)		PREFIX_8LS(0xf0000000, s, a, r, d)
+
+/* Prefixed Floating-Point Load/Store Instructions */
+#define PLFS(frt, a, r, d)		PREFIX_MLS(PPC_INST_LFS, frt, a, r, d)
+#define PLFD(frt, a, r, d)		PREFIX_MLS(PPC_INST_LFD, frt, a, r, d)
+#define PSTFS(frs, a, r, d)		PREFIX_MLS(PPC_INST_STFS, frs, a, r, d)
+#define PSTFD(frs, a, r, d)		PREFIX_MLS(PPC_INST_STFD, frs, a, r, d)
+
+/* Prefixed VSX Load/Store Instructions */
+#define PLXSD(vrt, a, r, d)		PREFIX_8LS(0xa8000000, vrt, a, r, d)
+#define PLXSSP(vrt, a, r, d)		PREFIX_8LS(0xac000000, vrt, a, r, d)
+#define PLXV0(s, a, r, d)		PREFIX_8LS(0xc8000000, s, a, r, d)
+#define PLXV1(s, a, r, d)		PREFIX_8LS(0xcc000000, s, a, r, d)
+#define PSTXSD(vrs, a, r, d)		PREFIX_8LS(0xb8000000, vrs, a, r, d)
+#define PSTXSSP(vrs, a, r, d)		PREFIX_8LS(0xbc000000, vrs, a, r, d)
+#define PSTXV0(s, a, r, d)		PREFIX_8LS(0xd8000000, s, a, r, d)
+#define PSTXV1(s, a, r, d)		PREFIX_8LS(0xdc000000, s, a, r, d)
+
 #endif /* _SELFTESTS_POWERPC_INSTRUCTIONS_H */
diff --git a/tools/testing/selftests/powerpc/include/pkeys.h b/tools/testing/selftests/powerpc/include/pkeys.h
new file mode 100644
index 000000000000..3312cb1b058d
--- /dev/null
+++ b/tools/testing/selftests/powerpc/include/pkeys.h
@@ -0,0 +1,136 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2020, Sandipan Das, IBM Corp.
+ */
+
+#ifndef _SELFTESTS_POWERPC_PKEYS_H
+#define _SELFTESTS_POWERPC_PKEYS_H
+
+#include <sys/mman.h>
+
+#include "reg.h"
+#include "utils.h"
+
+/*
+ * Older versions of libc use the Intel-specific access rights.
+ * Hence, override the definitions as they might be incorrect.
+ */
+#undef PKEY_DISABLE_ACCESS
+#define PKEY_DISABLE_ACCESS	0x3
+
+#undef PKEY_DISABLE_WRITE
+#define PKEY_DISABLE_WRITE	0x2
+
+#undef PKEY_DISABLE_EXECUTE
+#define PKEY_DISABLE_EXECUTE	0x4
+
+/* Older versions of libc do not not define this */
+#ifndef SEGV_PKUERR
+#define SEGV_PKUERR	4
+#endif
+
+#define SI_PKEY_OFFSET	0x20
+
+#define __NR_pkey_mprotect	386
+#define __NR_pkey_alloc		384
+#define __NR_pkey_free		385
+
+#define PKEY_BITS_PER_PKEY	2
+#define NR_PKEYS		32
+#define PKEY_BITS_MASK		((1UL << PKEY_BITS_PER_PKEY) - 1)
+
+inline unsigned long pkeyreg_get(void)
+{
+	return mfspr(SPRN_AMR);
+}
+
+inline void pkeyreg_set(unsigned long amr)
+{
+	set_amr(amr);
+}
+
+void pkey_set_rights(int pkey, unsigned long rights)
+{
+	unsigned long amr, shift;
+
+	shift = (NR_PKEYS - pkey - 1) * PKEY_BITS_PER_PKEY;
+	amr = pkeyreg_get();
+	amr &= ~(PKEY_BITS_MASK << shift);
+	amr |= (rights & PKEY_BITS_MASK) << shift;
+	pkeyreg_set(amr);
+}
+
+int sys_pkey_mprotect(void *addr, size_t len, int prot, int pkey)
+{
+	return syscall(__NR_pkey_mprotect, addr, len, prot, pkey);
+}
+
+int sys_pkey_alloc(unsigned long flags, unsigned long rights)
+{
+	return syscall(__NR_pkey_alloc, flags, rights);
+}
+
+int sys_pkey_free(int pkey)
+{
+	return syscall(__NR_pkey_free, pkey);
+}
+
+int pkeys_unsupported(void)
+{
+	bool hash_mmu = false;
+	int pkey;
+
+	/* Protection keys are currently supported on Hash MMU only */
+	FAIL_IF(using_hash_mmu(&hash_mmu));
+	SKIP_IF(!hash_mmu);
+
+	/* Check if the system call is supported */
+	pkey = sys_pkey_alloc(0, 0);
+	SKIP_IF(pkey < 0);
+	sys_pkey_free(pkey);
+
+	return 0;
+}
+
+int siginfo_pkey(siginfo_t *si)
+{
+	/*
+	 * In older versions of libc, siginfo_t does not have si_pkey as
+	 * a member.
+	 */
+#ifdef si_pkey
+	return si->si_pkey;
+#else
+	return *((int *)(((char *) si) + SI_PKEY_OFFSET));
+#endif
+}
+
+#define pkey_rights(r) ({						\
+	static char buf[4] = "rwx";					\
+	unsigned int amr_bits;						\
+	if ((r) & PKEY_DISABLE_EXECUTE)					\
+		buf[2] = '-';						\
+	amr_bits = (r) & PKEY_BITS_MASK;				\
+	if (amr_bits & PKEY_DISABLE_WRITE)				\
+		buf[1] = '-';						\
+	if (amr_bits & PKEY_DISABLE_ACCESS & ~PKEY_DISABLE_WRITE)	\
+		buf[0] = '-';						\
+	buf;								\
+})
+
+unsigned long next_pkey_rights(unsigned long rights)
+{
+	if (rights == PKEY_DISABLE_ACCESS)
+		return PKEY_DISABLE_EXECUTE;
+	else if (rights == (PKEY_DISABLE_ACCESS | PKEY_DISABLE_EXECUTE))
+		return 0;
+
+	if ((rights & PKEY_BITS_MASK) == 0)
+		rights |= PKEY_DISABLE_WRITE;
+	else if ((rights & PKEY_BITS_MASK) == PKEY_DISABLE_WRITE)
+		rights |= PKEY_DISABLE_ACCESS;
+
+	return rights;
+}
+
+#endif /* _SELFTESTS_POWERPC_PKEYS_H */
diff --git a/tools/testing/selftests/powerpc/include/reg.h b/tools/testing/selftests/powerpc/include/reg.h
index 022c5076b2c5..c0f2742a3a59 100644
--- a/tools/testing/selftests/powerpc/include/reg.h
+++ b/tools/testing/selftests/powerpc/include/reg.h
@@ -57,6 +57,12 @@
 #define SPRN_PPR       896	/* Program Priority Register */
 #define SPRN_AMR       13	/* Authority Mask Register - problem state */
 
+#define set_amr(v)	asm volatile("isync;" \
+				     "mtspr " __stringify(SPRN_AMR) ",%0;" \
+				     "isync" : \
+				    : "r" ((unsigned long)(v)) \
+				    : "memory")
+
 /* TEXASR register bits */
 #define TEXASR_FC	0xFE00000000000000
 #define TEXASR_FP	0x0100000000000000
diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index e089a0c30d9a..71d2924f5b8b 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -42,6 +42,16 @@ int perf_event_enable(int fd);
 int perf_event_disable(int fd);
 int perf_event_reset(int fd);
 
+#if !defined(__GLIBC_PREREQ) || !__GLIBC_PREREQ(2, 30)
+#include <unistd.h>
+#include <sys/syscall.h>
+
+static inline pid_t gettid(void)
+{
+	return syscall(SYS_gettid);
+}
+#endif
+
 static inline bool have_hwcap(unsigned long ftr)
 {
 	return ((unsigned long)get_auxv_entry(AT_HWCAP) & ftr) == ftr;
@@ -60,6 +70,7 @@ static inline bool have_hwcap2(unsigned long ftr2)
 #endif
 
 bool is_ppc64le(void);
+int using_hash_mmu(bool *using_hash);
 
 /* Yes, this is evil */
 #define FAIL_IF(x)						\
@@ -71,6 +82,15 @@ do {								\
 	}							\
 } while (0)
 
+#define FAIL_IF_EXIT(x)						\
+do {								\
+	if ((x)) {						\
+		fprintf(stderr,					\
+		"[FAIL] Test FAILED on line %d\n", __LINE__);	\
+		_exit(1);					\
+	}							\
+} while (0)
+
 /* The test harness uses this, yes it's gross */
 #define MAGIC_SKIP_RETURN_VALUE	99
 
@@ -96,11 +116,20 @@ do {								\
 #define _str(s) #s
 #define str(s) _str(s)
 
+#define sigsafe_err(msg)	({ \
+		ssize_t nbytes __attribute__((unused)); \
+		nbytes = write(STDERR_FILENO, msg, strlen(msg)); })
+
 /* POWER9 feature */
 #ifndef PPC_FEATURE2_ARCH_3_00
 #define PPC_FEATURE2_ARCH_3_00 0x00800000
 #endif
 
+/* POWER10 feature */
+#ifndef PPC_FEATURE2_ARCH_3_1
+#define PPC_FEATURE2_ARCH_3_1 0x00040000
+#endif
+
 #if defined(__powerpc64__)
 #define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.gp_regs[PT_NIP]
 #define UCONTEXT_MSR(UC)	(UC)->uc_mcontext.gp_regs[PT_MSR]
diff --git a/tools/testing/selftests/powerpc/math/.gitignore b/tools/testing/selftests/powerpc/math/.gitignore
index e31ca6f453ed..d0c23b2e4b60 100644
--- a/tools/testing/selftests/powerpc/math/.gitignore
+++ b/tools/testing/selftests/powerpc/math/.gitignore
@@ -6,3 +6,4 @@ vmx_preempt
 fpu_signal
 vmx_signal
 vsx_preempt
+fpu_denormal
diff --git a/tools/testing/selftests/powerpc/math/Makefile b/tools/testing/selftests/powerpc/math/Makefile
index 11a10d7a2bbd..fcc91c205984 100644
--- a/tools/testing/selftests/powerpc/math/Makefile
+++ b/tools/testing/selftests/powerpc/math/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_GEN_PROGS := fpu_syscall fpu_preempt fpu_signal vmx_syscall vmx_preempt vmx_signal vsx_preempt
+TEST_GEN_PROGS := fpu_syscall fpu_preempt fpu_signal fpu_denormal vmx_syscall vmx_preempt vmx_signal vsx_preempt
 
 top_srcdir = ../../../../..
 include ../../lib.mk
@@ -11,9 +11,9 @@ $(OUTPUT)/fpu_syscall: fpu_asm.S
 $(OUTPUT)/fpu_preempt: fpu_asm.S
 $(OUTPUT)/fpu_signal:  fpu_asm.S
 
-$(OUTPUT)/vmx_syscall: vmx_asm.S
-$(OUTPUT)/vmx_preempt: vmx_asm.S
-$(OUTPUT)/vmx_signal: vmx_asm.S
+$(OUTPUT)/vmx_syscall: vmx_asm.S ../utils.c
+$(OUTPUT)/vmx_preempt: vmx_asm.S ../utils.c
+$(OUTPUT)/vmx_signal: vmx_asm.S ../utils.c
 
 $(OUTPUT)/vsx_preempt: CFLAGS += -mvsx
-$(OUTPUT)/vsx_preempt: vsx_asm.S
+$(OUTPUT)/vsx_preempt: vsx_asm.S ../utils.c
diff --git a/tools/testing/selftests/powerpc/math/fpu_denormal.c b/tools/testing/selftests/powerpc/math/fpu_denormal.c
new file mode 100644
index 000000000000..5f96682abaa8
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/fpu_denormal.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright IBM Corp. 2020
+ *
+ * This test attempts to cause a FP denormal exception on POWER8 CPUs. Unfortunately
+ * if the denormal handler is not configured or working properly, this can cause a bad
+ * crash in kernel mode when the kernel tries to save FP registers when the process
+ * exits.
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "utils.h"
+
+static int test_denormal_fpu(void)
+{
+	unsigned int m32;
+	unsigned long m64;
+	volatile float f;
+	volatile double d;
+
+	/* try to induce lfs <denormal> ; stfd */
+
+	m32 = 0x00715fcf; /* random denormal */
+	memcpy((float *)&f, &m32, sizeof(f));
+	d = f;
+	memcpy(&m64, (double *)&d, sizeof(d));
+
+	FAIL_IF((long)(m64 != 0x380c57f3c0000000)); /* renormalised value */
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_denormal_fpu, "fpu_denormal");
+}
diff --git a/tools/testing/selftests/powerpc/math/vmx_preempt.c b/tools/testing/selftests/powerpc/math/vmx_preempt.c
index 2e059f154e77..6761d6ce30ec 100644
--- a/tools/testing/selftests/powerpc/math/vmx_preempt.c
+++ b/tools/testing/selftests/powerpc/math/vmx_preempt.c
@@ -57,6 +57,9 @@ int test_preempt_vmx(void)
 	int i, rc, threads;
 	pthread_t *tids;
 
+	// vcmpequd used in vmx_asm.S is v2.07
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07));
+
 	threads = sysconf(_SC_NPROCESSORS_ONLN) * THREAD_FACTOR;
 	tids = malloc(threads * sizeof(pthread_t));
 	FAIL_IF(!tids);
diff --git a/tools/testing/selftests/powerpc/math/vmx_signal.c b/tools/testing/selftests/powerpc/math/vmx_signal.c
index 785a48e0976f..b340a5c4e79d 100644
--- a/tools/testing/selftests/powerpc/math/vmx_signal.c
+++ b/tools/testing/selftests/powerpc/math/vmx_signal.c
@@ -96,6 +96,9 @@ int test_signal_vmx(void)
 	void *rc_p;
 	pthread_t *tids;
 
+	// vcmpequd used in vmx_asm.S is v2.07
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07));
+
 	threads = sysconf(_SC_NPROCESSORS_ONLN) * THREAD_FACTOR;
 	tids = malloc(threads * sizeof(pthread_t));
 	FAIL_IF(!tids);
diff --git a/tools/testing/selftests/powerpc/math/vmx_syscall.c b/tools/testing/selftests/powerpc/math/vmx_syscall.c
index 9ee293cc868e..03c78dfe3444 100644
--- a/tools/testing/selftests/powerpc/math/vmx_syscall.c
+++ b/tools/testing/selftests/powerpc/math/vmx_syscall.c
@@ -49,9 +49,14 @@ int test_vmx_syscall(void)
 	 * Setup an environment with much context switching
 	 */
 	pid_t pid2;
-	pid_t pid = fork();
+	pid_t pid;
 	int ret;
 	int child_ret;
+
+	// vcmpequd used in vmx_asm.S is v2.07
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07));
+
+	pid = fork();
 	FAIL_IF(pid == -1);
 
 	pid2 = fork();
diff --git a/tools/testing/selftests/powerpc/math/vsx_preempt.c b/tools/testing/selftests/powerpc/math/vsx_preempt.c
index 63de9c6e2cd3..d1601bb889d4 100644
--- a/tools/testing/selftests/powerpc/math/vsx_preempt.c
+++ b/tools/testing/selftests/powerpc/math/vsx_preempt.c
@@ -92,6 +92,8 @@ int test_preempt_vsx(void)
 	int i, rc, threads;
 	pthread_t *tids;
 
+	SKIP_IF(!have_hwcap(PPC_FEATURE_HAS_VSX));
+
 	threads = sysconf(_SC_NPROCESSORS_ONLN) * THREAD_FACTOR;
 	tids = malloc(threads * sizeof(pthread_t));
 	FAIL_IF(!tids);
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 2ca523255b1b..91c775c23c66 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -2,9 +2,12 @@
 hugetlb_vs_thp_test
 subpage_prot
 tempfile
-prot_sao
 segv_errors
 wild_bctr
 large_vm_fork_separation
 bad_accesses
 tlbie_test
+pkey_exec_prot
+pkey_siginfo
+stack_expansion_ldst
+stack_expansion_signal
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index b9103c4bb414..250ce172e0da 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -2,23 +2,31 @@
 noarg:
 	$(MAKE) -C ../
 
-TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \
-		  large_vm_fork_separation bad_accesses
+TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot segv_errors wild_bctr \
+		  large_vm_fork_separation bad_accesses pkey_exec_prot \
+		  pkey_siginfo stack_expansion_signal stack_expansion_ldst
+
 TEST_GEN_PROGS_EXTENDED := tlbie_test
 TEST_GEN_FILES := tempfile
 
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-$(TEST_GEN_PROGS): ../harness.c
-
-$(OUTPUT)/prot_sao: ../utils.c
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
 
 $(OUTPUT)/wild_bctr: CFLAGS += -m64
 $(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64
 $(OUTPUT)/bad_accesses: CFLAGS += -m64
+$(OUTPUT)/pkey_exec_prot: CFLAGS += -m64
+$(OUTPUT)/pkey_siginfo: CFLAGS += -m64
+
+$(OUTPUT)/stack_expansion_signal: ../utils.c ../pmu/lib.c
+
+$(OUTPUT)/stack_expansion_ldst: CFLAGS += -fno-stack-protector
+$(OUTPUT)/stack_expansion_ldst: ../utils.c
 
 $(OUTPUT)/tempfile:
 	dd if=/dev/zero of=$@ bs=64k count=1
 
 $(OUTPUT)/tlbie_test: LDLIBS += -lpthread
+$(OUTPUT)/pkey_siginfo: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/powerpc/mm/bad_accesses.c b/tools/testing/selftests/powerpc/mm/bad_accesses.c
index adc465f499ef..a864ed7e2008 100644
--- a/tools/testing/selftests/powerpc/mm/bad_accesses.c
+++ b/tools/testing/selftests/powerpc/mm/bad_accesses.c
@@ -64,34 +64,6 @@ int bad_access(char *p, bool write)
 	return 0;
 }
 
-static int using_hash_mmu(bool *using_hash)
-{
-	char line[128];
-	FILE *f;
-	int rc;
-
-	f = fopen("/proc/cpuinfo", "r");
-	FAIL_IF(!f);
-
-	rc = 0;
-	while (fgets(line, sizeof(line), f) != NULL) {
-		if (strcmp(line, "MMU		: Hash\n") == 0) {
-			*using_hash = true;
-			goto out;
-		}
-
-		if (strcmp(line, "MMU		: Radix\n") == 0) {
-			*using_hash = false;
-			goto out;
-		}
-	}
-
-	rc = -1;
-out:
-	fclose(f);
-	return rc;
-}
-
 static int test(void)
 {
 	unsigned long i, j, addr, region_shift, page_shift, page_size;
diff --git a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
new file mode 100644
index 000000000000..9e5c7f3f498a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
@@ -0,0 +1,294 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Copyright 2020, Sandipan Das, IBM Corp.
+ *
+ * Test if applying execute protection on pages using memory
+ * protection keys works as expected.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+
+#include <unistd.h>
+
+#include "pkeys.h"
+
+#define PPC_INST_NOP	0x60000000
+#define PPC_INST_TRAP	0x7fe00008
+#define PPC_INST_BLR	0x4e800020
+
+static volatile sig_atomic_t fault_pkey, fault_code, fault_type;
+static volatile sig_atomic_t remaining_faults;
+static volatile unsigned int *fault_addr;
+static unsigned long pgsize, numinsns;
+static unsigned int *insns;
+
+static void trap_handler(int signum, siginfo_t *sinfo, void *ctx)
+{
+	/* Check if this fault originated from the expected address */
+	if (sinfo->si_addr != (void *) fault_addr)
+		sigsafe_err("got a fault for an unexpected address\n");
+
+	_exit(1);
+}
+
+static void segv_handler(int signum, siginfo_t *sinfo, void *ctx)
+{
+	int signal_pkey;
+
+	signal_pkey = siginfo_pkey(sinfo);
+	fault_code = sinfo->si_code;
+
+	/* Check if this fault originated from the expected address */
+	if (sinfo->si_addr != (void *) fault_addr) {
+		sigsafe_err("got a fault for an unexpected address\n");
+		_exit(1);
+	}
+
+	/* Check if too many faults have occurred for a single test case */
+	if (!remaining_faults) {
+		sigsafe_err("got too many faults for the same address\n");
+		_exit(1);
+	}
+
+
+	/* Restore permissions in order to continue */
+	switch (fault_code) {
+	case SEGV_ACCERR:
+		if (mprotect(insns, pgsize, PROT_READ | PROT_WRITE)) {
+			sigsafe_err("failed to set access permissions\n");
+			_exit(1);
+		}
+		break;
+	case SEGV_PKUERR:
+		if (signal_pkey != fault_pkey) {
+			sigsafe_err("got a fault for an unexpected pkey\n");
+			_exit(1);
+		}
+
+		switch (fault_type) {
+		case PKEY_DISABLE_ACCESS:
+			pkey_set_rights(fault_pkey, 0);
+			break;
+		case PKEY_DISABLE_EXECUTE:
+			/*
+			 * Reassociate the exec-only pkey with the region
+			 * to be able to continue. Unlike AMR, we cannot
+			 * set IAMR directly from userspace to restore the
+			 * permissions.
+			 */
+			if (mprotect(insns, pgsize, PROT_EXEC)) {
+				sigsafe_err("failed to set execute permissions\n");
+				_exit(1);
+			}
+			break;
+		default:
+			sigsafe_err("got a fault with an unexpected type\n");
+			_exit(1);
+		}
+		break;
+	default:
+		sigsafe_err("got a fault with an unexpected code\n");
+		_exit(1);
+	}
+
+	remaining_faults--;
+}
+
+static int test(void)
+{
+	struct sigaction segv_act, trap_act;
+	unsigned long rights;
+	int pkey, ret, i;
+
+	ret = pkeys_unsupported();
+	if (ret)
+		return ret;
+
+	/* Setup SIGSEGV handler */
+	segv_act.sa_handler = 0;
+	segv_act.sa_sigaction = segv_handler;
+	FAIL_IF(sigprocmask(SIG_SETMASK, 0, &segv_act.sa_mask) != 0);
+	segv_act.sa_flags = SA_SIGINFO;
+	segv_act.sa_restorer = 0;
+	FAIL_IF(sigaction(SIGSEGV, &segv_act, NULL) != 0);
+
+	/* Setup SIGTRAP handler */
+	trap_act.sa_handler = 0;
+	trap_act.sa_sigaction = trap_handler;
+	FAIL_IF(sigprocmask(SIG_SETMASK, 0, &trap_act.sa_mask) != 0);
+	trap_act.sa_flags = SA_SIGINFO;
+	trap_act.sa_restorer = 0;
+	FAIL_IF(sigaction(SIGTRAP, &trap_act, NULL) != 0);
+
+	/* Setup executable region */
+	pgsize = getpagesize();
+	numinsns = pgsize / sizeof(unsigned int);
+	insns = (unsigned int *) mmap(NULL, pgsize, PROT_READ | PROT_WRITE,
+				      MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	FAIL_IF(insns == MAP_FAILED);
+
+	/* Write the instruction words */
+	for (i = 1; i < numinsns - 1; i++)
+		insns[i] = PPC_INST_NOP;
+
+	/*
+	 * Set the first instruction as an unconditional trap. If
+	 * the last write to this address succeeds, this should
+	 * get overwritten by a no-op.
+	 */
+	insns[0] = PPC_INST_TRAP;
+
+	/*
+	 * Later, to jump to the executable region, we use a branch
+	 * and link instruction (bctrl) which sets the return address
+	 * automatically in LR. Use that to return back.
+	 */
+	insns[numinsns - 1] = PPC_INST_BLR;
+
+	/* Allocate a pkey that restricts execution */
+	rights = PKEY_DISABLE_EXECUTE;
+	pkey = sys_pkey_alloc(0, rights);
+	FAIL_IF(pkey < 0);
+
+	/*
+	 * Pick the first instruction's address from the executable
+	 * region.
+	 */
+	fault_addr = insns;
+
+	/* The following two cases will avoid SEGV_PKUERR */
+	fault_type = -1;
+	fault_pkey = -1;
+
+	/*
+	 * Read an instruction word from the address when AMR bits
+	 * are not set i.e. the pkey permits both read and write
+	 * access.
+	 *
+	 * This should not generate a fault as having PROT_EXEC
+	 * implies PROT_READ on GNU systems. The pkey currently
+	 * restricts execution only based on the IAMR bits. The
+	 * AMR bits are cleared.
+	 */
+	remaining_faults = 0;
+	FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+	printf("read from %p, pkey permissions are %s\n", fault_addr,
+	       pkey_rights(rights));
+	i = *fault_addr;
+	FAIL_IF(remaining_faults != 0);
+
+	/*
+	 * Write an instruction word to the address when AMR bits
+	 * are not set i.e. the pkey permits both read and write
+	 * access.
+	 *
+	 * This should generate an access fault as having just
+	 * PROT_EXEC also restricts writes. The pkey currently
+	 * restricts execution only based on the IAMR bits. The
+	 * AMR bits are cleared.
+	 */
+	remaining_faults = 1;
+	FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+	printf("write to %p, pkey permissions are %s\n", fault_addr,
+	       pkey_rights(rights));
+	*fault_addr = PPC_INST_TRAP;
+	FAIL_IF(remaining_faults != 0 || fault_code != SEGV_ACCERR);
+
+	/* The following three cases will generate SEGV_PKUERR */
+	rights |= PKEY_DISABLE_ACCESS;
+	fault_type = PKEY_DISABLE_ACCESS;
+	fault_pkey = pkey;
+
+	/*
+	 * Read an instruction word from the address when AMR bits
+	 * are set i.e. the pkey permits neither read nor write
+	 * access.
+	 *
+	 * This should generate a pkey fault based on AMR bits only
+	 * as having PROT_EXEC implicitly allows reads.
+	 */
+	remaining_faults = 1;
+	FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+	pkey_set_rights(pkey, rights);
+	printf("read from %p, pkey permissions are %s\n", fault_addr,
+	       pkey_rights(rights));
+	i = *fault_addr;
+	FAIL_IF(remaining_faults != 0 || fault_code != SEGV_PKUERR);
+
+	/*
+	 * Write an instruction word to the address when AMR bits
+	 * are set i.e. the pkey permits neither read nor write
+	 * access.
+	 *
+	 * This should generate two faults. First, a pkey fault
+	 * based on AMR bits and then an access fault since
+	 * PROT_EXEC does not allow writes.
+	 */
+	remaining_faults = 2;
+	FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+	pkey_set_rights(pkey, rights);
+	printf("write to %p, pkey permissions are %s\n", fault_addr,
+	       pkey_rights(rights));
+	*fault_addr = PPC_INST_NOP;
+	FAIL_IF(remaining_faults != 0 || fault_code != SEGV_ACCERR);
+
+	/* Free the current pkey */
+	sys_pkey_free(pkey);
+
+	rights = 0;
+	do {
+		/*
+		 * Allocate pkeys with all valid combinations of read,
+		 * write and execute restrictions.
+		 */
+		pkey = sys_pkey_alloc(0, rights);
+		FAIL_IF(pkey < 0);
+
+		/*
+		 * Jump to the executable region. AMR bits may or may not
+		 * be set but they should not affect execution.
+		 *
+		 * This should generate pkey faults based on IAMR bits which
+		 * may be set to restrict execution.
+		 *
+		 * The first iteration also checks if the overwrite of the
+		 * first instruction word from a trap to a no-op succeeded.
+		 */
+		fault_pkey = pkey;
+		fault_type = -1;
+		remaining_faults = 0;
+		if (rights & PKEY_DISABLE_EXECUTE) {
+			fault_type = PKEY_DISABLE_EXECUTE;
+			remaining_faults = 1;
+		}
+
+		FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+		printf("execute at %p, pkey permissions are %s\n", fault_addr,
+		       pkey_rights(rights));
+		asm volatile("mtctr	%0; bctrl" : : "r"(insns));
+		FAIL_IF(remaining_faults != 0);
+		if (rights & PKEY_DISABLE_EXECUTE)
+			FAIL_IF(fault_code != SEGV_PKUERR);
+
+		/* Free the current pkey */
+		sys_pkey_free(pkey);
+
+		/* Find next valid combination of pkey rights */
+		rights = next_pkey_rights(rights);
+	} while (rights);
+
+	/* Cleanup */
+	munmap((void *) insns, pgsize);
+
+	return 0;
+}
+
+int main(void)
+{
+	test_harness(test, "pkey_exec_prot");
+}
diff --git a/tools/testing/selftests/powerpc/mm/pkey_siginfo.c b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c
new file mode 100644
index 000000000000..4f815d7c1214
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020, Sandipan Das, IBM Corp.
+ *
+ * Test if the signal information reports the correct memory protection
+ * key upon getting a key access violation fault for a page that was
+ * attempted to be protected by two different keys from two competing
+ * threads at the same time.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+
+#include <unistd.h>
+#include <pthread.h>
+#include <sys/mman.h>
+
+#include "pkeys.h"
+
+#define PPC_INST_NOP	0x60000000
+#define PPC_INST_BLR	0x4e800020
+#define PROT_RWX	(PROT_READ | PROT_WRITE | PROT_EXEC)
+
+#define NUM_ITERATIONS	1000000
+
+static volatile sig_atomic_t perm_pkey, rest_pkey;
+static volatile sig_atomic_t rights, fault_count;
+static volatile unsigned int *volatile fault_addr;
+static pthread_barrier_t iteration_barrier;
+
+static void segv_handler(int signum, siginfo_t *sinfo, void *ctx)
+{
+	void *pgstart;
+	size_t pgsize;
+	int pkey;
+
+	pkey = siginfo_pkey(sinfo);
+
+	/* Check if this fault originated from a pkey access violation */
+	if (sinfo->si_code != SEGV_PKUERR) {
+		sigsafe_err("got a fault for an unexpected reason\n");
+		_exit(1);
+	}
+
+	/* Check if this fault originated from the expected address */
+	if (sinfo->si_addr != (void *) fault_addr) {
+		sigsafe_err("got a fault for an unexpected address\n");
+		_exit(1);
+	}
+
+	/* Check if this fault originated from the restrictive pkey */
+	if (pkey != rest_pkey) {
+		sigsafe_err("got a fault for an unexpected pkey\n");
+		_exit(1);
+	}
+
+	/* Check if too many faults have occurred for the same iteration */
+	if (fault_count > 0) {
+		sigsafe_err("got too many faults for the same address\n");
+		_exit(1);
+	}
+
+	pgsize = getpagesize();
+	pgstart = (void *) ((unsigned long) fault_addr & ~(pgsize - 1));
+
+	/*
+	 * If the current fault occurred due to lack of execute rights,
+	 * reassociate the page with the exec-only pkey since execute
+	 * rights cannot be changed directly for the faulting pkey as
+	 * IAMR is inaccessible from userspace.
+	 *
+	 * Otherwise, if the current fault occurred due to lack of
+	 * read-write rights, change the AMR permission bits for the
+	 * pkey.
+	 *
+	 * This will let the test continue.
+	 */
+	if (rights == PKEY_DISABLE_EXECUTE &&
+	    mprotect(pgstart, pgsize, PROT_EXEC))
+		_exit(1);
+	else
+		pkey_set_rights(pkey, 0);
+
+	fault_count++;
+}
+
+struct region {
+	unsigned long rights;
+	unsigned int *base;
+	size_t size;
+};
+
+static void *protect(void *p)
+{
+	unsigned long rights;
+	unsigned int *base;
+	size_t size;
+	int tid, i;
+
+	tid = gettid();
+	base = ((struct region *) p)->base;
+	size = ((struct region *) p)->size;
+	FAIL_IF_EXIT(!base);
+
+	/* No read, write and execute restrictions */
+	rights = 0;
+
+	printf("tid %d, pkey permissions are %s\n", tid, pkey_rights(rights));
+
+	/* Allocate the permissive pkey */
+	perm_pkey = sys_pkey_alloc(0, rights);
+	FAIL_IF_EXIT(perm_pkey < 0);
+
+	/*
+	 * Repeatedly try to protect the common region with a permissive
+	 * pkey
+	 */
+	for (i = 0; i < NUM_ITERATIONS; i++) {
+		/*
+		 * Wait until the other thread has finished allocating the
+		 * restrictive pkey or until the next iteration has begun
+		 */
+		pthread_barrier_wait(&iteration_barrier);
+
+		/* Try to associate the permissive pkey with the region */
+		FAIL_IF_EXIT(sys_pkey_mprotect(base, size, PROT_RWX,
+					       perm_pkey));
+	}
+
+	/* Free the permissive pkey */
+	sys_pkey_free(perm_pkey);
+
+	return NULL;
+}
+
+static void *protect_access(void *p)
+{
+	size_t size, numinsns;
+	unsigned int *base;
+	int tid, i;
+
+	tid = gettid();
+	base = ((struct region *) p)->base;
+	size = ((struct region *) p)->size;
+	rights = ((struct region *) p)->rights;
+	numinsns = size / sizeof(base[0]);
+	FAIL_IF_EXIT(!base);
+
+	/* Allocate the restrictive pkey */
+	rest_pkey = sys_pkey_alloc(0, rights);
+	FAIL_IF_EXIT(rest_pkey < 0);
+
+	printf("tid %d, pkey permissions are %s\n", tid, pkey_rights(rights));
+	printf("tid %d, %s randomly in range [%p, %p]\n", tid,
+	       (rights == PKEY_DISABLE_EXECUTE) ? "execute" :
+	       (rights == PKEY_DISABLE_WRITE)  ? "write" : "read",
+	       base, base + numinsns);
+
+	/*
+	 * Repeatedly try to protect the common region with a restrictive
+	 * pkey and read, write or execute from it
+	 */
+	for (i = 0; i < NUM_ITERATIONS; i++) {
+		/*
+		 * Wait until the other thread has finished allocating the
+		 * permissive pkey or until the next iteration has begun
+		 */
+		pthread_barrier_wait(&iteration_barrier);
+
+		/* Try to associate the restrictive pkey with the region */
+		FAIL_IF_EXIT(sys_pkey_mprotect(base, size, PROT_RWX,
+					       rest_pkey));
+
+		/* Choose a random instruction word address from the region */
+		fault_addr = base + (rand() % numinsns);
+		fault_count = 0;
+
+		switch (rights) {
+		/* Read protection test */
+		case PKEY_DISABLE_ACCESS:
+			/*
+			 * Read an instruction word from the region and
+			 * verify if it has not been overwritten to
+			 * something unexpected
+			 */
+			FAIL_IF_EXIT(*fault_addr != PPC_INST_NOP &&
+				     *fault_addr != PPC_INST_BLR);
+			break;
+
+		/* Write protection test */
+		case PKEY_DISABLE_WRITE:
+			/*
+			 * Write an instruction word to the region and
+			 * verify if the overwrite has succeeded
+			 */
+			*fault_addr = PPC_INST_BLR;
+			FAIL_IF_EXIT(*fault_addr != PPC_INST_BLR);
+			break;
+
+		/* Execute protection test */
+		case PKEY_DISABLE_EXECUTE:
+			/* Jump to the region and execute instructions */
+			asm volatile(
+				"mtctr	%0; bctrl"
+				: : "r"(fault_addr) : "ctr", "lr");
+			break;
+		}
+
+		/*
+		 * Restore the restrictions originally imposed by the
+		 * restrictive pkey as the signal handler would have
+		 * cleared out the corresponding AMR bits
+		 */
+		pkey_set_rights(rest_pkey, rights);
+	}
+
+	/* Free restrictive pkey */
+	sys_pkey_free(rest_pkey);
+
+	return NULL;
+}
+
+static void reset_pkeys(unsigned long rights)
+{
+	int pkeys[NR_PKEYS], i;
+
+	/* Exhaustively allocate all available pkeys */
+	for (i = 0; i < NR_PKEYS; i++)
+		pkeys[i] = sys_pkey_alloc(0, rights);
+
+	/* Free all allocated pkeys */
+	for (i = 0; i < NR_PKEYS; i++)
+		sys_pkey_free(pkeys[i]);
+}
+
+static int test(void)
+{
+	pthread_t prot_thread, pacc_thread;
+	struct sigaction act;
+	pthread_attr_t attr;
+	size_t numinsns;
+	struct region r;
+	int ret, i;
+
+	srand(time(NULL));
+	ret = pkeys_unsupported();
+	if (ret)
+		return ret;
+
+	/* Allocate the region */
+	r.size = getpagesize();
+	r.base = mmap(NULL, r.size, PROT_RWX,
+		      MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	FAIL_IF(r.base == MAP_FAILED);
+
+	/*
+	 * Fill the region with no-ops with a branch at the end
+	 * for returning to the caller
+	 */
+	numinsns = r.size / sizeof(r.base[0]);
+	for (i = 0; i < numinsns - 1; i++)
+		r.base[i] = PPC_INST_NOP;
+	r.base[i] = PPC_INST_BLR;
+
+	/* Setup SIGSEGV handler */
+	act.sa_handler = 0;
+	act.sa_sigaction = segv_handler;
+	FAIL_IF(sigprocmask(SIG_SETMASK, 0, &act.sa_mask) != 0);
+	act.sa_flags = SA_SIGINFO;
+	act.sa_restorer = 0;
+	FAIL_IF(sigaction(SIGSEGV, &act, NULL) != 0);
+
+	/*
+	 * For these tests, the parent process should clear all bits of
+	 * AMR and IAMR, i.e. impose no restrictions, for all available
+	 * pkeys. This will be the base for the initial AMR and IAMR
+	 * values for all the test thread pairs.
+	 *
+	 * If the AMR and IAMR bits of all available pkeys are cleared
+	 * before running the tests and a fault is generated when
+	 * attempting to read, write or execute instructions from a
+	 * pkey protected region, the pkey responsible for this must be
+	 * the one from the protect-and-access thread since the other
+	 * one is fully permissive. Despite that, if the pkey reported
+	 * by siginfo is not the restrictive pkey, then there must be a
+	 * kernel bug.
+	 */
+	reset_pkeys(0);
+
+	/* Setup barrier for protect and protect-and-access threads */
+	FAIL_IF(pthread_attr_init(&attr) != 0);
+	FAIL_IF(pthread_barrier_init(&iteration_barrier, NULL, 2) != 0);
+
+	/* Setup and start protect and protect-and-read threads */
+	puts("starting thread pair (protect, protect-and-read)");
+	r.rights = PKEY_DISABLE_ACCESS;
+	FAIL_IF(pthread_create(&prot_thread, &attr, &protect, &r) != 0);
+	FAIL_IF(pthread_create(&pacc_thread, &attr, &protect_access, &r) != 0);
+	FAIL_IF(pthread_join(prot_thread, NULL) != 0);
+	FAIL_IF(pthread_join(pacc_thread, NULL) != 0);
+
+	/* Setup and start protect and protect-and-write threads */
+	puts("starting thread pair (protect, protect-and-write)");
+	r.rights = PKEY_DISABLE_WRITE;
+	FAIL_IF(pthread_create(&prot_thread, &attr, &protect, &r) != 0);
+	FAIL_IF(pthread_create(&pacc_thread, &attr, &protect_access, &r) != 0);
+	FAIL_IF(pthread_join(prot_thread, NULL) != 0);
+	FAIL_IF(pthread_join(pacc_thread, NULL) != 0);
+
+	/* Setup and start protect and protect-and-execute threads */
+	puts("starting thread pair (protect, protect-and-execute)");
+	r.rights = PKEY_DISABLE_EXECUTE;
+	FAIL_IF(pthread_create(&prot_thread, &attr, &protect, &r) != 0);
+	FAIL_IF(pthread_create(&pacc_thread, &attr, &protect_access, &r) != 0);
+	FAIL_IF(pthread_join(prot_thread, NULL) != 0);
+	FAIL_IF(pthread_join(pacc_thread, NULL) != 0);
+
+	/* Cleanup */
+	FAIL_IF(pthread_attr_destroy(&attr) != 0);
+	FAIL_IF(pthread_barrier_destroy(&iteration_barrier) != 0);
+	munmap(r.base, r.size);
+
+	return 0;
+}
+
+int main(void)
+{
+	test_harness(test, "pkey_siginfo");
+}
diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c
deleted file mode 100644
index e2eed65b7735..000000000000
--- a/tools/testing/selftests/powerpc/mm/prot_sao.c
+++ /dev/null
@@ -1,42 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright 2016, Michael Ellerman, IBM Corp.
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/mman.h>
-
-#include <asm/cputable.h>
-
-#include "utils.h"
-
-#define SIZE (64 * 1024)
-
-int test_prot_sao(void)
-{
-	char *p;
-
-	/* 2.06 or later should support SAO */
-	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
-
-	/*
-	 * Ensure we can ask for PROT_SAO.
-	 * We can't really verify that it does the right thing, but at least we
-	 * confirm the kernel will accept it.
-	 */
-	p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO,
-		 MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
-	FAIL_IF(p == MAP_FAILED);
-
-	/* Write to the mapping, to at least cause a fault */
-	memset(p, 0xaa, SIZE);
-
-	return 0;
-}
-
-int main(void)
-{
-	return test_harness(test_prot_sao, "prot-sao");
-}
diff --git a/tools/testing/selftests/powerpc/mm/stack_expansion_ldst.c b/tools/testing/selftests/powerpc/mm/stack_expansion_ldst.c
new file mode 100644
index 000000000000..ed9143990888
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/stack_expansion_ldst.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that loads/stores expand the stack segment, or trigger a SEGV, in
+ * various conditions.
+ *
+ * Based on test code by Tom Lane.
+ */
+
+#undef NDEBUG
+#include <assert.h>
+
+#include <err.h>
+#include <errno.h>
+#include <stdio.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#define _KB (1024)
+#define _MB (1024 * 1024)
+
+volatile char *stack_top_ptr;
+volatile unsigned long stack_top_sp;
+volatile char c;
+
+enum access_type {
+	LOAD,
+	STORE,
+};
+
+/*
+ * Consume stack until the stack pointer is below @target_sp, then do an access
+ * (load or store) at offset @delta from either the base of the stack or the
+ * current stack pointer.
+ */
+__attribute__ ((noinline))
+int consume_stack(unsigned long target_sp, unsigned long stack_high, int delta, enum access_type type)
+{
+	unsigned long target;
+	char stack_cur;
+
+	if ((unsigned long)&stack_cur > target_sp)
+		return consume_stack(target_sp, stack_high, delta, type);
+	else {
+		// We don't really need this, but without it GCC might not
+		// generate a recursive call above.
+		stack_top_ptr = &stack_cur;
+
+#ifdef __powerpc__
+		asm volatile ("mr %[sp], %%r1" : [sp] "=r" (stack_top_sp));
+#else
+		asm volatile ("mov %%rsp, %[sp]" : [sp] "=r" (stack_top_sp));
+#endif
+		target = stack_high - delta + 1;
+		volatile char *p = (char *)target;
+
+		if (type == STORE)
+			*p = c;
+		else
+			c = *p;
+
+		// Do something to prevent the stack frame being popped prior to
+		// our access above.
+		getpid();
+	}
+
+	return 0;
+}
+
+static int search_proc_maps(char *needle, unsigned long *low, unsigned long *high)
+{
+	unsigned long start, end;
+	static char buf[4096];
+	char name[128];
+	FILE *f;
+	int rc;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!f) {
+		perror("fopen");
+		return -1;
+	}
+
+	while (fgets(buf, sizeof(buf), f)) {
+		rc = sscanf(buf, "%lx-%lx %*c%*c%*c%*c %*x %*d:%*d %*d %127s\n",
+			    &start, &end, name);
+		if (rc == 2)
+			continue;
+
+		if (rc != 3) {
+			printf("sscanf errored\n");
+			rc = -1;
+			break;
+		}
+
+		if (strstr(name, needle)) {
+			*low = start;
+			*high = end - 1;
+			rc = 0;
+			break;
+		}
+	}
+
+	fclose(f);
+
+	return rc;
+}
+
+int child(unsigned int stack_used, int delta, enum access_type type)
+{
+	unsigned long low, stack_high;
+
+	assert(search_proc_maps("[stack]", &low, &stack_high) == 0);
+
+	assert(consume_stack(stack_high - stack_used, stack_high, delta, type) == 0);
+
+	printf("Access OK: %s delta %-7d used size 0x%06x stack high 0x%lx top_ptr %p top sp 0x%lx actual used 0x%lx\n",
+	       type == LOAD ? "load" : "store", delta, stack_used, stack_high,
+	       stack_top_ptr, stack_top_sp, stack_high - stack_top_sp + 1);
+
+	return 0;
+}
+
+static int test_one(unsigned int stack_used, int delta, enum access_type type)
+{
+	pid_t pid;
+	int rc;
+
+	pid = fork();
+	if (pid == 0)
+		exit(child(stack_used, delta, type));
+
+	assert(waitpid(pid, &rc, 0) != -1);
+
+	if (WIFEXITED(rc) && WEXITSTATUS(rc) == 0)
+		return 0;
+
+	// We don't expect a non-zero exit that's not a signal
+	assert(!WIFEXITED(rc));
+
+	printf("Faulted:   %s delta %-7d used size 0x%06x signal %d\n",
+	       type == LOAD ? "load" : "store", delta, stack_used,
+	       WTERMSIG(rc));
+
+	return 1;
+}
+
+// This is fairly arbitrary but is well below any of the targets below,
+// so that the delta between the stack pointer and the target is large.
+#define DEFAULT_SIZE	(32 * _KB)
+
+static void test_one_type(enum access_type type, unsigned long page_size, unsigned long rlim_cur)
+{
+	unsigned long delta;
+
+	// We should be able to access anywhere within the rlimit
+	for (delta = page_size; delta <= rlim_cur; delta += page_size)
+		assert(test_one(DEFAULT_SIZE, delta, type) == 0);
+
+	assert(test_one(DEFAULT_SIZE, rlim_cur, type) == 0);
+
+	// But if we go past the rlimit it should fail
+	assert(test_one(DEFAULT_SIZE, rlim_cur + 1, type) != 0);
+}
+
+static int test(void)
+{
+	unsigned long page_size;
+	struct rlimit rlimit;
+
+	page_size = getpagesize();
+	getrlimit(RLIMIT_STACK, &rlimit);
+	printf("Stack rlimit is 0x%lx\n", rlimit.rlim_cur);
+
+	printf("Testing loads ...\n");
+	test_one_type(LOAD, page_size, rlimit.rlim_cur);
+	printf("Testing stores ...\n");
+	test_one_type(STORE, page_size, rlimit.rlim_cur);
+
+	printf("All OK\n");
+
+	return 0;
+}
+
+#ifdef __powerpc__
+#include "utils.h"
+
+int main(void)
+{
+	return test_harness(test, "stack_expansion_ldst");
+}
+#else
+int main(void)
+{
+	return test();
+}
+#endif
diff --git a/tools/testing/selftests/powerpc/mm/stack_expansion_signal.c b/tools/testing/selftests/powerpc/mm/stack_expansion_signal.c
new file mode 100644
index 000000000000..c8b32a29e274
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/stack_expansion_signal.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that signal delivery is able to expand the stack segment without
+ * triggering a SEGV.
+ *
+ * Based on test code by Tom Lane.
+ */
+
+#include <err.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "../pmu/lib.h"
+#include "utils.h"
+
+#define _KB (1024)
+#define _MB (1024 * 1024)
+
+static char *stack_base_ptr;
+static char *stack_top_ptr;
+
+static volatile sig_atomic_t sig_occurred = 0;
+
+static void sigusr1_handler(int signal_arg)
+{
+	sig_occurred = 1;
+}
+
+static int consume_stack(unsigned int stack_size, union pipe write_pipe)
+{
+	char stack_cur;
+
+	if ((stack_base_ptr - &stack_cur) < stack_size)
+		return consume_stack(stack_size, write_pipe);
+	else {
+		stack_top_ptr = &stack_cur;
+
+		FAIL_IF(notify_parent(write_pipe));
+
+		while (!sig_occurred)
+			barrier();
+	}
+
+	return 0;
+}
+
+static int child(unsigned int stack_size, union pipe write_pipe)
+{
+	struct sigaction act;
+	char stack_base;
+
+	act.sa_handler = sigusr1_handler;
+	sigemptyset(&act.sa_mask);
+	act.sa_flags = 0;
+	if (sigaction(SIGUSR1, &act, NULL) < 0)
+		err(1, "sigaction");
+
+	stack_base_ptr = (char *) (((size_t) &stack_base + 65535) & ~65535UL);
+
+	FAIL_IF(consume_stack(stack_size, write_pipe));
+
+	printf("size 0x%06x: OK, stack base %p top %p (%zx used)\n",
+		stack_size, stack_base_ptr, stack_top_ptr,
+		stack_base_ptr - stack_top_ptr);
+
+	return 0;
+}
+
+static int test_one_size(unsigned int stack_size)
+{
+	union pipe read_pipe, write_pipe;
+	pid_t pid;
+
+	FAIL_IF(pipe(read_pipe.fds) == -1);
+	FAIL_IF(pipe(write_pipe.fds) == -1);
+
+	pid = fork();
+	if (pid == 0) {
+		close(read_pipe.read_fd);
+		close(write_pipe.write_fd);
+		exit(child(stack_size, read_pipe));
+	}
+
+	close(read_pipe.write_fd);
+	close(write_pipe.read_fd);
+	FAIL_IF(sync_with_child(read_pipe, write_pipe));
+
+	kill(pid, SIGUSR1);
+
+	FAIL_IF(wait_for_child(pid));
+
+	close(read_pipe.read_fd);
+	close(write_pipe.write_fd);
+
+	return 0;
+}
+
+int test(void)
+{
+	unsigned int i, size;
+
+	// Test with used stack from 1MB - 64K to 1MB + 64K
+	// Increment by 64 to get more coverage of odd sizes
+	for (i = 0; i < (128 * _KB); i += 64) {
+		size = i + (1 * _MB) - (64 * _KB);
+		FAIL_IF(test_one_size(size));
+	}
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test, "stack_expansion_signal");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c b/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c
index 7b4ac4537702..2980abca31e0 100644
--- a/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c
+++ b/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c
@@ -9,6 +9,7 @@
 #include <stdbool.h>
 #include <string.h>
 #include <sys/prctl.h>
+#include <asm/cputable.h>
 
 #include "event.h"
 #include "utils.h"
@@ -104,6 +105,9 @@ static int test_body(void)
 	struct event events[3];
 	u64 overhead;
 
+	// The STCX_FAIL event we use works on Power8 or later
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07));
+
 	setup_event(&events[0], PERF_COUNT_HW_INSTRUCTIONS, PERF_TYPE_HARDWARE, "instructions");
 	setup_event(&events[1], PERF_COUNT_HW_CPU_CYCLES, PERF_TYPE_HARDWARE, "cycles");
 	setup_event(&events[2], PM_STCX_FAIL, PERF_TYPE_RAW, "stcx_fail");
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index a2d7b0e3dca9..a26ac122c759 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -91,8 +91,6 @@ int back_to_back_ebbs(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index bc893813483e..bb9f587fa76e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -42,8 +42,6 @@ int cycles(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index dcd351d20328..9ae795ce314e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -99,8 +99,6 @@ int cycles_with_freeze(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	printf("EBBs while frozen %d\n", ebbs_while_frozen);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index 94c99c12c0f2..4b45a2e70f62 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -71,8 +71,6 @@ int cycles_with_mmcr2(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index dfbc5c3ad52d..21537d6eb6b7 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -396,8 +396,6 @@ int ebb_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index ca2f7d729155..b208bf6ad58d 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -38,8 +38,6 @@ static int victim_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	FAIL_IF(ebb_state.stats.ebb_count == 0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index ac3e6e182614..ba2681a12cc7 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -75,7 +75,6 @@ static int test_body(void)
 	ebb_freeze_pmcs();
 	ebb_global_disable();
 
-	count_pmc(4, sample_period);
 	mtspr(SPRN_PMC4, 0xdead);
 
 	dump_summary_ebb_state();
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index b8242e9d97d2..791d37ba327b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -70,13 +70,6 @@ int multi_counter(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-	count_pmc(2, sample_period);
-	count_pmc(3, sample_period);
-	count_pmc(4, sample_period);
-	count_pmc(5, sample_period);
-	count_pmc(6, sample_period);
-
 	dump_ebb_state();
 
 	for (i = 0; i < 6; i++)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index a05c0e18ded6..9b0f70d59702 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -61,8 +61,6 @@ static int cycles_child(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_summary_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index 153ebc92234f..2904c741e04e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -82,8 +82,6 @@ static int test_body(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	if (mmcr0_mismatch)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index eadad75ed7e6..b29f8ba22d1e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -76,8 +76,6 @@ int pmc56_overflow(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(2, sample_period);
-
 	dump_ebb_state();
 
 	printf("PMC5/6 overflow %d\n", pmc56_overflowed);
diff --git a/tools/testing/selftests/powerpc/pmu/lib.h b/tools/testing/selftests/powerpc/pmu/lib.h
index fa12e7d0b4d3..bf1bec013bbb 100644
--- a/tools/testing/selftests/powerpc/pmu/lib.h
+++ b/tools/testing/selftests/powerpc/pmu/lib.h
@@ -6,6 +6,7 @@
 #ifndef __SELFTESTS_POWERPC_PMU_LIB_H
 #define __SELFTESTS_POWERPC_PMU_LIB_H
 
+#include <stdbool.h>
 #include <stdio.h>
 #include <stdint.h>
 #include <string.h>
diff --git a/tools/testing/selftests/powerpc/pmu/per_event_excludes.c b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c
index 2756fe2efdc5..2d37942bf72b 100644
--- a/tools/testing/selftests/powerpc/pmu/per_event_excludes.c
+++ b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c
@@ -12,6 +12,8 @@
 #include <string.h>
 #include <sys/prctl.h>
 
+#include <asm/cputable.h>
+
 #include "event.h"
 #include "lib.h"
 #include "utils.h"
@@ -23,12 +25,9 @@
 static int per_event_excludes(void)
 {
 	struct event *e, events[4];
-	char *platform;
 	int i;
 
-	platform = (char *)get_auxv_entry(AT_BASE_PLATFORM);
-	FAIL_IF(!platform);
-	SKIP_IF(strcmp(platform, "power8") != 0);
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07));
 
 	/*
 	 * We need to create the events disabled, otherwise the running/enabled
diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c
index d5c64fee032d..bbc05ffc5860 100644
--- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c
@@ -150,7 +150,7 @@ static int child(struct shared_info *info)
 	printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n",
 	       user_write, info->amr, pkey1, pkey2, pkey3);
 
-	mtspr(SPRN_AMR, info->amr);
+	set_amr(info->amr);
 
 	/*
 	 * We won't use pkey3. This tests whether the kernel restores the UAMOR
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
index bdbbbe8431e0..bc454f899124 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
@@ -44,7 +44,7 @@ struct shared_info {
 	unsigned long amr2;
 
 	/* AMR value that ptrace should refuse to write to the child. */
-	unsigned long amr3;
+	unsigned long invalid_amr;
 
 	/* IAMR value the parent expects to read from the child. */
 	unsigned long expected_iamr;
@@ -57,8 +57,8 @@ struct shared_info {
 	 * (even though they're valid ones) because userspace doesn't have
 	 * access to those registers.
 	 */
-	unsigned long new_iamr;
-	unsigned long new_uamor;
+	unsigned long invalid_iamr;
+	unsigned long invalid_uamor;
 };
 
 static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights)
@@ -66,11 +66,6 @@ static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights)
 	return syscall(__NR_pkey_alloc, flags, init_access_rights);
 }
 
-static int sys_pkey_free(int pkey)
-{
-	return syscall(__NR_pkey_free, pkey);
-}
-
 static int child(struct shared_info *info)
 {
 	unsigned long reg;
@@ -100,33 +95,37 @@ static int child(struct shared_info *info)
 
 	info->amr1 |= 3ul << pkeyshift(pkey1);
 	info->amr2 |= 3ul << pkeyshift(pkey2);
-	info->amr3 |= info->amr2 | 3ul << pkeyshift(pkey3);
+	/*
+	 * invalid amr value where we try to force write
+	 * things which are deined by a uamor setting.
+	 */
+	info->invalid_amr = info->amr2 | (~0x0UL & ~info->expected_uamor);
 
+	/*
+	 * if PKEY_DISABLE_EXECUTE succeeded we should update the expected_iamr
+	 */
 	if (disable_execute)
 		info->expected_iamr |= 1ul << pkeyshift(pkey1);
 	else
 		info->expected_iamr &= ~(1ul << pkeyshift(pkey1));
 
-	info->expected_iamr &= ~(1ul << pkeyshift(pkey2) | 1ul << pkeyshift(pkey3));
-
-	info->expected_uamor |= 3ul << pkeyshift(pkey1) |
-				3ul << pkeyshift(pkey2);
-	info->new_iamr |= 1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2);
-	info->new_uamor |= 3ul << pkeyshift(pkey1);
+	/*
+	 * We allocated pkey2 and pkey 3 above. Clear the IAMR bits.
+	 */
+	info->expected_iamr &= ~(1ul << pkeyshift(pkey2));
+	info->expected_iamr &= ~(1ul << pkeyshift(pkey3));
 
 	/*
-	 * We won't use pkey3. We just want a plausible but invalid key to test
-	 * whether ptrace will let us write to AMR bits we are not supposed to.
-	 *
-	 * This also tests whether the kernel restores the UAMOR permissions
-	 * after a key is freed.
+	 * Create an IAMR value different from expected value.
+	 * Kernel will reject an IAMR and UAMOR change.
 	 */
-	sys_pkey_free(pkey3);
+	info->invalid_iamr = info->expected_iamr | (1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2));
+	info->invalid_uamor = info->expected_uamor & ~(0x3ul << pkeyshift(pkey1));
 
 	printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n",
 	       user_write, info->amr1, pkey1, pkey2, pkey3);
 
-	mtspr(SPRN_AMR, info->amr1);
+	set_amr(info->amr1);
 
 	/* Wait for parent to read our AMR value and write a new one. */
 	ret = prod_parent(&info->child_sync);
@@ -196,9 +195,9 @@ static int parent(struct shared_info *info, pid_t pid)
 	PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync);
 	PARENT_FAIL_IF(ret, &info->child_sync);
 
-	info->amr1 = info->amr2 = info->amr3 = regs[0];
-	info->expected_iamr = info->new_iamr = regs[1];
-	info->expected_uamor = info->new_uamor = regs[2];
+	info->amr1 = info->amr2 = regs[0];
+	info->expected_iamr = regs[1];
+	info->expected_uamor = regs[2];
 
 	/* Wake up child so that it can set itself up. */
 	ret = prod_child(&info->child_sync);
@@ -234,10 +233,10 @@ static int parent(struct shared_info *info, pid_t pid)
 		return ret;
 
 	/* Write invalid AMR value in child. */
-	ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->amr3, 1);
+	ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->invalid_amr, 1);
 	PARENT_FAIL_IF(ret, &info->child_sync);
 
-	printf("%-30s AMR: %016lx\n", ptrace_write_running, info->amr3);
+	printf("%-30s AMR: %016lx\n", ptrace_write_running, info->invalid_amr);
 
 	/* Wake up child so that it can verify it didn't change. */
 	ret = prod_child(&info->child_sync);
@@ -249,7 +248,7 @@ static int parent(struct shared_info *info, pid_t pid)
 
 	/* Try to write to IAMR. */
 	regs[0] = info->amr1;
-	regs[1] = info->new_iamr;
+	regs[1] = info->invalid_iamr;
 	ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 2);
 	PARENT_FAIL_IF(!ret, &info->child_sync);
 
@@ -257,7 +256,7 @@ static int parent(struct shared_info *info, pid_t pid)
 	       ptrace_write_running, regs[0], regs[1]);
 
 	/* Try to write to IAMR and UAMOR. */
-	regs[2] = info->new_uamor;
+	regs[2] = info->invalid_uamor;
 	ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 3);
 	PARENT_FAIL_IF(!ret, &info->child_sync);
 
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tar.c
index 58cb1a860cc9..4436ca9d3caf 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tar.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tar.c
@@ -78,6 +78,9 @@ int ptrace_tar(void)
 	pid_t pid;
 	int ret, status;
 
+	// TAR was added in v2.07
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07));
+
 	shm_id = shmget(IPC_PRIVATE, sizeof(int) * 3, 0777|IPC_CREAT);
 	pid = fork();
 	if (pid < 0) {
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-vsx.c
index c4fe0e893306..cb9875f764ca 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-vsx.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-vsx.c
@@ -61,6 +61,8 @@ int ptrace_vsx(void)
 	pid_t pid;
 	int ret, status, i;
 
+	SKIP_IF(!have_hwcap(PPC_FEATURE_HAS_VSX));
+
 	shm_id = shmget(IPC_PRIVATE, sizeof(int) * 2, 0777|IPC_CREAT);
 
 	for (i = 0; i < VEC_MAX; i++)
diff --git a/tools/testing/selftests/powerpc/security/spectre_v2.c b/tools/testing/selftests/powerpc/security/spectre_v2.c
index 8c6b982af2a8..c8d82b784102 100644
--- a/tools/testing/selftests/powerpc/security/spectre_v2.c
+++ b/tools/testing/selftests/powerpc/security/spectre_v2.c
@@ -183,6 +183,16 @@ int spectre_v2_test(void)
 		if (miss_percent > 15) {
 			printf("Branch misses > 15%% unexpected in this configuration!\n");
 			printf("Possible mis-match between reported & actual mitigation\n");
+			/*
+			 * Such a mismatch may be caused by a guest system
+			 * reporting as vulnerable when the host is mitigated.
+			 * Return skip code to avoid detecting this as an error.
+			 * We are not vulnerable and reporting otherwise, so
+			 * missing such a mismatch is safe.
+			 */
+			if (state == VULNERABLE)
+				return 4;
+
 			return 1;
 		}
 		break;
diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
index 7fc0623d85c3..9c39f55a58ff 100644
--- a/tools/testing/selftests/powerpc/stringloops/Makefile
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -8,7 +8,7 @@ build_32bit = $(shell if ($(CC) $(CFLAGS) -m32 -o /dev/null memcmp.c >/dev/null
 
 TEST_GEN_PROGS := memcmp_64 strlen
 
-$(OUTPUT)/memcmp_64: memcmp.c
+$(OUTPUT)/memcmp_64: memcmp.c ../utils.c
 $(OUTPUT)/memcmp_64: CFLAGS += -m64 -maltivec
 
 ifeq ($(build_32bit),1)
diff --git a/tools/testing/selftests/powerpc/stringloops/memcmp.c b/tools/testing/selftests/powerpc/stringloops/memcmp.c
index b1fa7546957f..979df3d98368 100644
--- a/tools/testing/selftests/powerpc/stringloops/memcmp.c
+++ b/tools/testing/selftests/powerpc/stringloops/memcmp.c
@@ -2,7 +2,9 @@
 #include <malloc.h>
 #include <stdlib.h>
 #include <string.h>
+#include <sys/mman.h>
 #include <time.h>
+#include <asm/cputable.h>
 #include "utils.h"
 
 #define SIZE 256
@@ -13,6 +15,9 @@
 #define LARGE_MAX_OFFSET 32
 #define LARGE_SIZE_START 4096
 
+/* This is big enough to fit LARGE_SIZE and works on 4K & 64K kernels */
+#define MAP_SIZE (64 * 1024)
+
 #define MAX_OFFSET_DIFF_S1_S2 48
 
 int vmx_count;
@@ -68,25 +73,25 @@ static void test_one(char *s1, char *s2, unsigned long max_offset,
 
 static int testcase(bool islarge)
 {
-	char *s1;
-	char *s2;
-	unsigned long i;
-
-	unsigned long comp_size = (islarge ? LARGE_SIZE : SIZE);
-	unsigned long alloc_size = comp_size + MAX_OFFSET_DIFF_S1_S2;
-	int iterations = islarge ? LARGE_ITERATIONS : ITERATIONS;
-
-	s1 = memalign(128, alloc_size);
-	if (!s1) {
-		perror("memalign");
-		exit(1);
-	}
+	unsigned long i, comp_size, alloc_size;
+	char *p, *s1, *s2;
+	int iterations;
 
-	s2 = memalign(128, alloc_size);
-	if (!s2) {
-		perror("memalign");
-		exit(1);
-	}
+	comp_size = (islarge ? LARGE_SIZE : SIZE);
+	alloc_size = comp_size + MAX_OFFSET_DIFF_S1_S2;
+	iterations = islarge ? LARGE_ITERATIONS : ITERATIONS;
+
+	p = mmap(NULL, 4 * MAP_SIZE, PROT_READ | PROT_WRITE,
+		 MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	FAIL_IF(p == MAP_FAILED);
+
+	/* Put s1/s2 at the end of a page */
+	s1 = p + MAP_SIZE - alloc_size;
+	s2 = p + 3 * MAP_SIZE - alloc_size;
+
+	/* And unmap the subsequent page to force a fault if we overread */
+	munmap(p + MAP_SIZE, MAP_SIZE);
+	munmap(p + 3 * MAP_SIZE, MAP_SIZE);
 
 	srandom(time(0));
 
@@ -147,6 +152,11 @@ static int testcase(bool islarge)
 
 static int testcases(void)
 {
+#ifdef __powerpc64__
+	// vcmpequd used in memcmp_64.S is v2.07
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07));
+#endif
+
 	testcase(0);
 	testcase(1);
 	return 0;
diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c
index 5ee0e98c4896..18b6a773d5c7 100644
--- a/tools/testing/selftests/powerpc/utils.c
+++ b/tools/testing/selftests/powerpc/utils.c
@@ -16,6 +16,7 @@
 #include <string.h>
 #include <sys/ioctl.h>
 #include <sys/stat.h>
+#include <sys/sysinfo.h>
 #include <sys/types.h>
 #include <sys/utsname.h>
 #include <unistd.h>
@@ -88,28 +89,40 @@ void *get_auxv_entry(int type)
 
 int pick_online_cpu(void)
 {
-	cpu_set_t mask;
-	int cpu;
+	int ncpus, cpu = -1;
+	cpu_set_t *mask;
+	size_t size;
+
+	ncpus = get_nprocs_conf();
+	size = CPU_ALLOC_SIZE(ncpus);
+	mask = CPU_ALLOC(ncpus);
+	if (!mask) {
+		perror("malloc");
+		return -1;
+	}
 
-	CPU_ZERO(&mask);
+	CPU_ZERO_S(size, mask);
 
-	if (sched_getaffinity(0, sizeof(mask), &mask)) {
+	if (sched_getaffinity(0, size, mask)) {
 		perror("sched_getaffinity");
-		return -1;
+		goto done;
 	}
 
 	/* We prefer a primary thread, but skip 0 */
-	for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8)
-		if (CPU_ISSET(cpu, &mask))
-			return cpu;
+	for (cpu = 8; cpu < ncpus; cpu += 8)
+		if (CPU_ISSET_S(cpu, size, mask))
+			goto done;
 
 	/* Search for anything, but in reverse */
-	for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--)
-		if (CPU_ISSET(cpu, &mask))
-			return cpu;
+	for (cpu = ncpus - 1; cpu >= 0; cpu--)
+		if (CPU_ISSET_S(cpu, size, mask))
+			goto done;
 
 	printf("No cpus in affinity mask?!\n");
-	return -1;
+
+done:
+	CPU_FREE(mask);
+	return cpu;
 }
 
 bool is_ppc64le(void)
@@ -293,3 +306,31 @@ void set_dscr(unsigned long val)
 
 	asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
 }
+
+int using_hash_mmu(bool *using_hash)
+{
+	char line[128];
+	FILE *f;
+	int rc;
+
+	f = fopen("/proc/cpuinfo", "r");
+	FAIL_IF(!f);
+
+	rc = 0;
+	while (fgets(line, sizeof(line), f) != NULL) {
+		if (strcmp(line, "MMU		: Hash\n") == 0) {
+			*using_hash = true;
+			goto out;
+		}
+
+		if (strcmp(line, "MMU		: Radix\n") == 0) {
+			*using_hash = false;
+			goto out;
+		}
+	}
+
+	rc = -1;
+out:
+	fclose(f);
+	return rc;
+}
diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c
index da7a9dda9490..f7911aaeb007 100644
--- a/tools/testing/selftests/ptp/testptp.c
+++ b/tools/testing/selftests/ptp/testptp.c
@@ -35,6 +35,8 @@
 #define CLOCK_INVALID -1
 #endif
 
+#define NSEC_PER_SEC 1000000000LL
+
 /* clock_adjtime is not available in GLIBC < 2.14 */
 #if !__GLIBC_PREREQ(2, 14)
 #include <sys/syscall.h>
@@ -132,6 +134,8 @@ static void usage(char *progname)
 		"            1 - external time stamp\n"
 		"            2 - periodic output\n"
 		" -p val     enable output with a period of 'val' nanoseconds\n"
+		" -H val     set output phase to 'val' nanoseconds (requires -p)\n"
+		" -w val     set output pulse width to 'val' nanoseconds (requires -p)\n"
 		" -P val     enable or disable (val=1|0) the system clock PPS\n"
 		" -s         set the ptp clock time from the system time\n"
 		" -S         set the system time from the ptp clock time\n"
@@ -169,7 +173,6 @@ int main(int argc, char *argv[])
 	int list_pins = 0;
 	int pct_offset = 0;
 	int n_samples = 0;
-	int perout = -1;
 	int pin_index = -1, pin_func;
 	int pps = -1;
 	int seconds = 0;
@@ -177,10 +180,13 @@ int main(int argc, char *argv[])
 
 	int64_t t1, t2, tp;
 	int64_t interval, offset;
+	int64_t perout_phase = -1;
+	int64_t pulsewidth = -1;
+	int64_t perout = -1;
 
 	progname = strrchr(argv[0], '/');
 	progname = progname ? 1+progname : argv[0];
-	while (EOF != (c = getopt(argc, argv, "cd:e:f:ghi:k:lL:p:P:sSt:T:z"))) {
+	while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:p:P:sSt:T:w:z"))) {
 		switch (c) {
 		case 'c':
 			capabilities = 1;
@@ -197,6 +203,9 @@ int main(int argc, char *argv[])
 		case 'g':
 			gettime = 1;
 			break;
+		case 'H':
+			perout_phase = atoll(optarg);
+			break;
 		case 'i':
 			index = atoi(optarg);
 			break;
@@ -215,7 +224,7 @@ int main(int argc, char *argv[])
 			}
 			break;
 		case 'p':
-			perout = atoi(optarg);
+			perout = atoll(optarg);
 			break;
 		case 'P':
 			pps = atoi(optarg);
@@ -233,6 +242,9 @@ int main(int argc, char *argv[])
 			settime = 3;
 			seconds = atoi(optarg);
 			break;
+		case 'w':
+			pulsewidth = atoi(optarg);
+			break;
 		case 'z':
 			flagtest = 1;
 			break;
@@ -391,6 +403,16 @@ int main(int argc, char *argv[])
 		}
 	}
 
+	if (pulsewidth >= 0 && perout < 0) {
+		puts("-w can only be specified together with -p");
+		return -1;
+	}
+
+	if (perout_phase >= 0 && perout < 0) {
+		puts("-H can only be specified together with -p");
+		return -1;
+	}
+
 	if (perout >= 0) {
 		if (clock_gettime(clkid, &ts)) {
 			perror("clock_gettime");
@@ -398,11 +420,24 @@ int main(int argc, char *argv[])
 		}
 		memset(&perout_request, 0, sizeof(perout_request));
 		perout_request.index = index;
-		perout_request.start.sec = ts.tv_sec + 2;
-		perout_request.start.nsec = 0;
-		perout_request.period.sec = 0;
-		perout_request.period.nsec = perout;
-		if (ioctl(fd, PTP_PEROUT_REQUEST, &perout_request)) {
+		perout_request.period.sec = perout / NSEC_PER_SEC;
+		perout_request.period.nsec = perout % NSEC_PER_SEC;
+		perout_request.flags = 0;
+		if (pulsewidth >= 0) {
+			perout_request.flags |= PTP_PEROUT_DUTY_CYCLE;
+			perout_request.on.sec = pulsewidth / NSEC_PER_SEC;
+			perout_request.on.nsec = pulsewidth % NSEC_PER_SEC;
+		}
+		if (perout_phase >= 0) {
+			perout_request.flags |= PTP_PEROUT_PHASE;
+			perout_request.phase.sec = perout_phase / NSEC_PER_SEC;
+			perout_request.phase.nsec = perout_phase % NSEC_PER_SEC;
+		} else {
+			perout_request.start.sec = ts.tv_sec + 2;
+			perout_request.start.nsec = 0;
+		}
+
+		if (ioctl(fd, PTP_PEROUT_REQUEST2, &perout_request)) {
 			perror("PTP_PEROUT_REQUEST");
 		} else {
 			puts("periodic output request okay");
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 93e80a42249a..d6e5ce084b1c 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -32,11 +32,11 @@ if test -z "$TORTURE_TRUST_MAKE"
 then
 	make clean > $resdir/Make.clean 2>&1
 fi
-make $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1
+make $TORTURE_KMAKE_ARG $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1
 mv .config .config.sav
 sh $T/upd.sh < .config.sav > .config
 cp .config .config.new
-yes '' | make oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err
+yes '' | make $TORTURE_KMAKE_ARG oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err
 
 # verify new config matches specification.
 configcheck.sh .config $c
diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh
new file mode 100755
index 000000000000..0e4c0b2eb7f0
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh
@@ -0,0 +1,16 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Scan standard input for error messages, dumping any found to standard
+# output.
+#
+# Usage: console-badness.sh
+#
+# Copyright (C) 2020 Facebook, Inc.
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' |
+grep -v 'ODEBUG: ' |
+grep -v 'This means that this is a DEBUG kernel and it is' |
+grep -v 'Warning: unable to open an initial console'
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 12810229fddc..51f3464b96d3 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -215,9 +215,6 @@ identify_qemu_args () {
 		then
 			echo -device spapr-vlan,netdev=net0,mac=$TORTURE_QEMU_MAC
 			echo -netdev bridge,br=br0,id=net0
-		elif test -n "$TORTURE_QEMU_INTERACTIVE"
-		then
-			echo -net nic -net user
 		fi
 		;;
 	esac
@@ -234,7 +231,7 @@ identify_qemu_args () {
 # Returns the number of virtual CPUs available to the aggregate of the
 # guest OSes.
 identify_qemu_vcpus () {
-	lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://'
+	lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' -e 's/[ 	]*//g'
 }
 
 # print_bug
@@ -275,3 +272,21 @@ specify_qemu_cpus () {
 		esac
 	fi
 }
+
+# specify_qemu_net qemu-args
+#
+# Appends a string containing "-net none" to qemu-args, unless the incoming
+# qemu-args already contains "-smp" or unless the TORTURE_QEMU_INTERACTIVE
+# environment variable is set, in which case the string that is be added is
+# instead "-net nic -net user".
+specify_qemu_net () {
+	if echo $1 | grep -q -e -net
+	then
+		echo $1
+	elif test -n "$TORTURE_QEMU_INTERACTIVE"
+	then
+		echo $1 -net nic -net user
+	else
+		echo $1 -net none
+	fi
+}
diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh
index 30cb5b27d32e..188b864bc4bf 100755
--- a/tools/testing/selftests/rcutorture/bin/jitter.sh
+++ b/tools/testing/selftests/rcutorture/bin/jitter.sh
@@ -46,6 +46,12 @@ do
 		exit 0;
 	fi
 
+	# Check for stop request.
+	if test -f "$TORTURE_STOPFILE"
+	then
+		exit 1;
+	fi
+
 	# Set affinity to randomly selected online CPU
 	if cpus=`grep 1 /sys/devices/system/cpu/*/online 2>&1 |
 		 sed -e 's,/[^/]*$,,' -e 's/^[^0-9]*//'`
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 18d6518504ee..115e1822b26f 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -9,6 +9,12 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
+if test -f "$TORTURE_STOPFILE"
+then
+	echo "kvm-build.sh early exit due to run STOP request"
+	exit 1
+fi
+
 config_template=${1}
 if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template"
 then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
new file mode 100755
index 000000000000..6e65c134e5f1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
@@ -0,0 +1,108 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Run a group of kvm.sh tests on the specified commits.  This currently
+# unconditionally does three-minute runs on each scenario in CFLIST,
+# taking advantage of all available CPUs and trusting the "make" utility.
+# In the short term, adjustments can be made by editing this script and
+# CFLIST.  If some adjustments appear to have ongoing value, this script
+# might grow some command-line arguments.
+#
+# Usage: kvm-check-branches.sh commit1 commit2..commit3 commit4 ...
+#
+# This script considers its arguments one at a time.  If more elaborate
+# specification of commits is needed, please use "git rev-list" to
+# produce something that this simple script can understand.  The reason
+# for retaining the simplicity is that it allows the user to more easily
+# see which commit came from which branch.
+#
+# This script creates a yyyy.mm.dd-hh.mm.ss-group entry in the "res"
+# directory.  The calls to kvm.sh create the usual entries, but this script
+# moves them under the yyyy.mm.dd-hh.mm.ss-group entry, each in its own
+# directory numbered in run order, that is, "0001", "0002", and so on.
+# For successful runs, the large build artifacts are removed.  Doing this
+# reduces the disk space required by about two orders of magnitude for
+# successful runs.
+#
+# Copyright (C) Facebook, 2020
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+if ! git status > /dev/null 2>&1
+then
+	echo '!!!' This script needs to run in a git archive. 1>&2
+	echo '!!!' Giving up. 1>&2
+	exit 1
+fi
+
+# Remember where we started so that we can get back and the end.
+curcommit="`git status | head -1 | awk '{ print $NF }'`"
+
+nfail=0
+ntry=0
+resdir="tools/testing/selftests/rcutorture/res"
+ds="`date +%Y.%m.%d-%H.%M.%S`-group"
+if ! test -e $resdir
+then
+	mkdir $resdir || :
+fi
+mkdir $resdir/$ds
+echo Results directory: $resdir/$ds
+
+KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
+PATH=${KVM}/bin:$PATH; export PATH
+. functions.sh
+cpus="`identify_qemu_vcpus`"
+echo Using up to $cpus CPUs.
+
+# Each pass through this loop does one command-line argument.
+for gitbr in $@
+do
+	echo ' --- git branch ' $gitbr
+
+	# Each pass through this loop tests one commit.
+	for i in `git rev-list "$gitbr"`
+	do
+		ntry=`expr $ntry + 1`
+		idir=`awk -v ntry="$ntry" 'END { printf "%04d", ntry; }' < /dev/null`
+		echo ' --- commit ' $i from branch $gitbr
+		date
+		mkdir $resdir/$ds/$idir
+		echo $gitbr > $resdir/$ds/$idir/gitbr
+		echo $i >> $resdir/$ds/$idir/gitbr
+
+		# Test the specified commit.
+		git checkout $i > $resdir/$ds/$idir/git-checkout.out 2>&1
+		echo git checkout return code: $? "(Commit $ntry: $i)"
+		kvm.sh --cpus $cpus --duration 3 --trust-make > $resdir/$ds/$idir/kvm.sh.out 2>&1
+		ret=$?
+		echo kvm.sh return code $ret for commit $i from branch $gitbr
+
+		# Move the build products to their resting place.
+		runresdir="`grep -m 1 '^Results directory:' < $resdir/$ds/$idir/kvm.sh.out | sed -e 's/^Results directory://'`"
+		mv $runresdir $resdir/$ds/$idir
+		rrd="`echo $runresdir | sed -e 's,^.*/,,'`"
+		echo Run results: $resdir/$ds/$idir/$rrd
+		if test "$ret" -ne 0
+		then
+			# Failure, so leave all evidence intact.
+			nfail=`expr $nfail + 1`
+		else
+			# Success, so remove large files to save about 1GB.
+			( cd $resdir/$ds/$idir/$rrd; rm -f */vmlinux */bzImage */System.map */Module.symvers )
+		fi
+	done
+done
+date
+
+# Go back to the original commit.
+git checkout "$curcommit"
+
+if test $nfail -ne 0
+then
+	echo '!!! ' $nfail failures in $ntry 'runs!!!'
+	exit 1
+else
+	echo No failures in $ntry runs.
+	exit 0
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh
new file mode 100755
index 000000000000..35a463dddffe
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh
@@ -0,0 +1,71 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Analyze a given results directory for refscale performance measurements.
+#
+# Usage: kvm-recheck-refscale.sh resdir
+#
+# Copyright (C) IBM Corporation, 2016
+#
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
+
+i="$1"
+if test -d "$i" -a -r "$i"
+then
+	:
+else
+	echo Unreadable results directory: $i
+	exit 1
+fi
+PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
+. functions.sh
+
+configfile=`echo $i | sed -e 's/^.*\///'`
+
+sed -e 's/^\[[^]]*]//' < $i/console.log | tr -d '\015' |
+awk -v configfile="$configfile" '
+/^[ 	]*Runs	Time\(ns\) *$/ {
+	if (dataphase + 0 == 0) {
+		dataphase = 1;
+		# print configfile, $0;
+	}
+	next;
+}
+
+/[^ 	]*[0-9][0-9]*	[0-9][0-9]*\.[0-9][0-9]*$/ {
+	if (dataphase == 1) {
+		# print $0;
+		readertimes[++n] = $2;
+		sum += $2;
+	}
+	next;
+}
+
+{
+	if (dataphase == 1)
+		dataphase == 2;
+	next;
+}
+
+END {
+	print configfile " results:";
+	newNR = asort(readertimes);
+	if (newNR <= 0) {
+		print "No refscale records found???"
+		exit;
+	}
+	medianidx = int(newNR / 2);
+	if (newNR == medianidx * 2)
+		medianvalue = (readertimes[medianidx - 1] + readertimes[medianidx]) / 2;
+	else
+		medianvalue = readertimes[medianidx];
+	points = "Points:";
+	for (i = 1; i <= newNR; i++)
+		points = points " " readertimes[i];
+	print points;
+	print "Average reader duration: " sum / newNR " nanoseconds";
+	print "Minimum reader duration: " readertimes[1];
+	print "Median reader duration: " medianvalue;
+	print "Maximum reader duration: " readertimes[newNR];
+	print "Computed from refscale printk output.";
+}'
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 736f04749b90..840a4679a0d7 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -31,6 +31,7 @@ do
 			head -1 $resdir/log
 		fi
 		TORTURE_SUITE="`cat $i/../TORTURE_SUITE`"
+		configfile=`echo $i | sed -e 's,^.*/,,'`
 		rm -f $i/console.log.*.diags
 		kvm-recheck-${TORTURE_SUITE}.sh $i
 		if test -f "$i/qemu-retval" && test "`cat $i/qemu-retval`" -ne 0 && test "`cat $i/qemu-retval`" -ne 137
@@ -43,7 +44,8 @@ do
 			then
 				echo QEMU killed
 			fi
-			configcheck.sh $i/.config $i/ConfigFragment
+			configcheck.sh $i/.config $i/ConfigFragment > $T 2>&1
+			cat $T
 			if test -r $i/Make.oldconfig.err
 			then
 				cat $i/Make.oldconfig.err
@@ -55,15 +57,15 @@ do
 				cat $i/Warnings
 			fi
 		else
-			if test -f "$i/qemu-cmd"
-			then
-				print_bug qemu failed
-				echo "   $i"
-			elif test -f "$i/buildonly"
+			if test -f "$i/buildonly"
 			then
 				echo Build-only run, no boot/test
 				configcheck.sh $i/.config $i/ConfigFragment
 				parse-build.sh $i/Make.out $configfile
+			elif test -f "$i/qemu-cmd"
+			then
+				print_bug qemu failed
+				echo "   $i"
 			else
 				print_bug Build failed
 				echo "   $i"
@@ -72,7 +74,11 @@ do
 	done
 	if test -f "$rd/kcsan.sum"
 	then
-		if test -s "$rd/kcsan.sum"
+		if grep -q CONFIG_KCSAN=y $T
+		then
+			echo "Compiler or architecture does not support KCSAN!"
+			echo Did you forget to switch your compiler with '--kmake-arg CC=<cc-that-supports-kcsan>'?
+		elif test -s "$rd/kcsan.sum"
 		then
 			echo KCSAN summary in $rd/kcsan.sum
 		else
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 6ff611c630d1..e07779a62634 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -124,7 +124,6 @@ seconds=$4
 qemu_args=$5
 boot_args=$6
 
-cd $KVM
 kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null`
 if test -z "$TORTURE_BUILDONLY"
 then
@@ -141,6 +140,7 @@ then
 	cpu_count=$TORTURE_ALLOTED_CPUS
 fi
 qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`"
+qemu_args="`specify_qemu_net "$qemu_args"`"
 
 # Generate architecture-specific and interaction-specific qemu arguments
 qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$resdir/console.log"`"
@@ -152,6 +152,7 @@ qemu_append="`identify_qemu_append "$QEMU"`"
 boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
 # Generate kernel-version-specific boot parameters
 boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`"
+echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
 
 if test -n "$TORTURE_BUILDONLY"
 then
@@ -159,9 +160,16 @@ then
 	touch $resdir/buildonly
 	exit 0
 fi
+
+# Decorate qemu-cmd with redirection, backgrounding, and PID capture
+sed -e 's/$/ 2>\&1 \&/' < $resdir/qemu-cmd > $T/qemu-cmd
+echo 'echo $! > $resdir/qemu_pid' >> $T/qemu-cmd
+
+# In case qemu refuses to run...
 echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log
-echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
-( $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append "$qemu_append $boot_args" > $resdir/qemu-output 2>&1 & echo $! > $resdir/qemu_pid; wait `cat  $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) &
+
+# Attempt to run qemu
+( . $T/qemu-cmd; wait `cat  $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) &
 commandcompleted=0
 sleep 10 # Give qemu's pid a chance to reach the file
 if test -s "$resdir/qemu_pid"
@@ -181,7 +189,7 @@ do
 	kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
 	if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1
 	then
-		if test $kruntime -ge $seconds
+		if test $kruntime -ge $seconds -o -f "$TORTURE_STOPFILE"
 		then
 			break;
 		fi
@@ -210,10 +218,19 @@ then
 fi
 if test $commandcompleted -eq 0 -a -n "$qemu_pid"
 then
-	echo Grace period for qemu job at pid $qemu_pid
+	if ! test -f "$TORTURE_STOPFILE"
+	then
+		echo Grace period for qemu job at pid $qemu_pid
+	fi
 	oldline="`tail $resdir/console.log`"
 	while :
 	do
+		if test -f "$TORTURE_STOPFILE"
+		then
+			echo "PID $qemu_pid killed due to run STOP request" >> $resdir/Warnings 2>&1
+			kill -KILL $qemu_pid
+			break
+		fi
 		kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
 		if kill -0 $qemu_pid > /dev/null 2>&1
 		then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-transform.sh b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh
new file mode 100755
index 000000000000..c45a953ef393
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh
@@ -0,0 +1,51 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Transform a qemu-cmd file to allow reuse.
+#
+# Usage: kvm-transform.sh bzImage console.log < qemu-cmd-in > qemu-cmd-out
+#
+#	bzImage: Kernel and initrd from the same prior kvm.sh run.
+#	console.log: File into which to place console output.
+#
+# The original qemu-cmd file is provided on standard input.
+# The transformed qemu-cmd file is on standard output.
+# The transformation assumes that the qemu command is confined to a
+# single line.  It also assumes no whitespace in filenames.
+#
+# Copyright (C) 2020 Facebook, Inc.
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+image="$1"
+if test -z "$image"
+then
+	echo Need kernel image file.
+	exit 1
+fi
+consolelog="$2"
+if test -z "$consolelog"
+then
+	echo "Need console log file name."
+	exit 1
+fi
+
+awk -v image="$image" -v consolelog="$consolelog" '
+{
+	line = "";
+	for (i = 1; i <= NF; i++) {
+		if (line == "")
+			line = $i;
+		else
+			line = line " " $i;
+		if ($i == "-serial") {
+			i++;
+			line = line " file:" consolelog;
+		}
+		if ($i == "-kernel") {
+			i++;
+			line = line " " image;
+		}
+	}
+	print line;
+}'
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index c279cf9cb010..e655983b7429 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -73,6 +73,10 @@ usage () {
 while test $# -gt 0
 do
 	case "$1" in
+	--allcpus)
+		cpus=$TORTURE_ALLOTED_CPUS
+		max_cpus=$TORTURE_ALLOTED_CPUS
+		;;
 	--bootargs|--bootarg)
 		checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--'
 		TORTURE_BOOTARGS="$2"
@@ -180,13 +184,14 @@ do
 		shift
 		;;
 	--torture)
-		checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\)$' '^--'
+		checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\|refscale\)$' '^--'
 		TORTURE_SUITE=$2
 		shift
-		if test "$TORTURE_SUITE" = rcuperf
+		if test "$TORTURE_SUITE" = rcuperf || test "$TORTURE_SUITE" = refscale
 		then
-			# If you really want jitter for rcuperf, specify
-			# it after specifying rcuperf.  (But why?)
+			# If you really want jitter for refscale or
+			# rcuperf, specify it after specifying the rcuperf
+			# or the refscale.  (But why jitter in these cases?)
 			jitter=0
 		fi
 		;;
@@ -333,6 +338,8 @@ then
 	mkdir -p "$resdir" || :
 fi
 mkdir $resdir/$ds
+TORTURE_RESDIR="$resdir/$ds"; export TORTURE_RESDIR
+TORTURE_STOPFILE="$resdir/$ds/STOP"; export TORTURE_STOPFILE
 echo Results directory: $resdir/$ds
 echo $scriptname $args
 touch $resdir/$ds/log
@@ -497,3 +504,7 @@ fi
 # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier
 # Function-graph tracing: ftrace=function_graph ftrace_graph_filter=sched_setaffinity,migration_cpu_stop
 # Also --kconfig "CONFIG_FUNCTION_TRACER=y CONFIG_FUNCTION_GRAPH_TRACER=y"
+# Control buffer size: --bootargs trace_buf_size=3k
+# Get trace-buffer dumps on all oopses: --bootargs ftrace_dump_on_oops
+# Ditto, but dump only the oopsing CPU: --bootargs ftrace_dump_on_oops=orig_cpu
+# Heavy-handed way to also dump on warnings: --bootargs panic_on_warn
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 4bf62d7b1cbc..71a9f43a3918 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -33,8 +33,8 @@ then
 fi
 cat /dev/null > $file.diags
 
-# Check for proper termination, except that rcuperf runs don't indicate this.
-if test "$TORTURE_SUITE" != rcuperf
+# Check for proper termination, except for rcuperf and refscale.
+if test "$TORTURE_SUITE" != rcuperf && test "$TORTURE_SUITE" != refscale
 then
 	# check for abject failure
 
@@ -44,11 +44,23 @@ then
 		tail -1 |
 		awk '
 		{
-			for (i=NF-8;i<=NF;i++)
+			normalexit = 1;
+			for (i=NF-8;i<=NF;i++) {
+				if (i <= 0 || i !~ /^[0-9]*$/) {
+					bangstring = $0;
+					gsub(/^\[[^]]*] /, "", bangstring);
+					print bangstring;
+					normalexit = 0;
+					exit 0;
+				}
 				sum+=$i;
+			}
 		}
-		END { print sum }'`
-		print_bug $title FAILURE, $nerrs instances
+		END {
+			if (normalexit)
+				print sum " instances"
+		}'`
+		print_bug $title FAILURE, $nerrs
 		exit
 	fi
 
@@ -104,10 +116,7 @@ then
 	fi
 fi | tee -a $file.diags
 
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file |
-grep -v 'ODEBUG: ' |
-grep -v 'This means that this is a DEBUG kernel and it is' |
-grep -v 'Warning: unable to open an initial console' > $T.diags
+console-badness.sh < $file > $T.diags
 if test -s $T.diags
 then
 	print_warning "Assertion failure in $file $title"
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFLIST b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST
new file mode 100644
index 000000000000..4d62eb4a39f9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST
@@ -0,0 +1,2 @@
+NOPREEMPT
+PREEMPT
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon
new file mode 100644
index 000000000000..a98b58b54bb1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon
@@ -0,0 +1,2 @@
+CONFIG_RCU_REF_SCALE_TEST=y
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
new file mode 100644
index 000000000000..1cd25b7314e3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
@@ -0,0 +1,18 @@
+CONFIG_SMP=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_PREEMPT_RCU=n
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_LOCKING=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT
new file mode 100644
index 000000000000..d10bc694f42c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT
@@ -0,0 +1,18 @@
+CONFIG_SMP=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_LOCKING=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh
new file mode 100644
index 000000000000..321e82641287
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh
@@ -0,0 +1,16 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Torture-suite-dependent shell functions for the rest of the scripts.
+#
+# Copyright (C) IBM Corporation, 2015
+#
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
+
+# per_version_boot_params bootparam-string config-file seconds
+#
+# Adds per-version torture-module parameters to kernels supporting them.
+per_version_boot_params () {
+	echo $1 refscale.shutdown=1 \
+		refscale.verbose=1
+}
diff --git a/tools/testing/selftests/seccomp/config b/tools/testing/selftests/seccomp/config
index db1e11b08c8a..64c19d8eba79 100644
--- a/tools/testing/selftests/seccomp/config
+++ b/tools/testing/selftests/seccomp/config
@@ -1,2 +1,3 @@
 CONFIG_SECCOMP=y
 CONFIG_SECCOMP_FILTER=y
+CONFIG_USER_NS=y
diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c
index 5838c8697ec3..91f5a89cadac 100644
--- a/tools/testing/selftests/seccomp/seccomp_benchmark.c
+++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c
@@ -18,9 +18,9 @@
 
 unsigned long long timing(clockid_t clk_id, unsigned long long samples)
 {
-	pid_t pid, ret;
-	unsigned long long i;
 	struct timespec start, finish;
+	unsigned long long i;
+	pid_t pid, ret;
 
 	pid = getpid();
 	assert(clock_gettime(clk_id, &start) == 0);
@@ -31,30 +31,43 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples)
 	assert(clock_gettime(clk_id, &finish) == 0);
 
 	i = finish.tv_sec - start.tv_sec;
-	i *= 1000000000;
+	i *= 1000000000ULL;
 	i += finish.tv_nsec - start.tv_nsec;
 
-	printf("%lu.%09lu - %lu.%09lu = %llu\n",
+	printf("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n",
 		finish.tv_sec, finish.tv_nsec,
 		start.tv_sec, start.tv_nsec,
-		i);
+		i, (double)i / 1000000000.0);
 
 	return i;
 }
 
 unsigned long long calibrate(void)
 {
-	unsigned long long i;
-
-	printf("Calibrating reasonable sample size...\n");
+	struct timespec start, finish;
+	unsigned long long i, samples, step = 9973;
+	pid_t pid, ret;
+	int seconds = 15;
 
-	for (i = 5; ; i++) {
-		unsigned long long samples = 1 << i;
+	printf("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds);
 
-		/* Find something that takes more than 5 seconds to run. */
-		if (timing(CLOCK_REALTIME, samples) / 1000000000ULL > 5)
-			return samples;
-	}
+	samples = 0;
+	pid = getpid();
+	assert(clock_gettime(CLOCK_MONOTONIC, &start) == 0);
+	do {
+		for (i = 0; i < step; i++) {
+			ret = syscall(__NR_getpid);
+			assert(pid == ret);
+		}
+		assert(clock_gettime(CLOCK_MONOTONIC, &finish) == 0);
+
+		samples += step;
+		i = finish.tv_sec - start.tv_sec;
+		i *= 1000000000ULL;
+		i += finish.tv_nsec - start.tv_nsec;
+	} while (i < 1000000000ULL);
+
+	return samples * seconds;
 }
 
 int main(int argc, char *argv[])
@@ -68,32 +81,55 @@ int main(int argc, char *argv[])
 	};
 	long ret;
 	unsigned long long samples;
-	unsigned long long native, filtered;
+	unsigned long long native, filter1, filter2;
+
+	printf("Current BPF sysctl settings:\n");
+	system("sysctl net.core.bpf_jit_enable");
+	system("sysctl net.core.bpf_jit_harden");
 
 	if (argc > 1)
 		samples = strtoull(argv[1], NULL, 0);
 	else
 		samples = calibrate();
 
-	printf("Benchmarking %llu samples...\n", samples);
+	printf("Benchmarking %llu syscalls...\n", samples);
 
+	/* Native call */
 	native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
 	printf("getpid native: %llu ns\n", native);
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	assert(ret == 0);
 
+	/* One filter */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
 	assert(ret == 0);
 
-	filtered = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW: %llu ns\n", filtered);
+	filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+	printf("getpid RET_ALLOW 1 filter: %llu ns\n", filter1);
+
+	if (filter1 == native)
+		printf("No overhead measured!? Try running again with more samples.\n");
+
+	/* Two filters */
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	assert(ret == 0);
+
+	filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+	printf("getpid RET_ALLOW 2 filters: %llu ns\n", filter2);
+
+	/* Calculations */
+	printf("Estimated total seccomp overhead for 1 filter: %llu ns\n",
+		filter1 - native);
+
+	printf("Estimated total seccomp overhead for 2 filters: %llu ns\n",
+		filter2 - native);
 
-	printf("Estimated seccomp overhead per syscall: %llu ns\n",
-		filtered - native);
+	printf("Estimated seccomp per-filter overhead: %llu ns\n",
+		filter2 - filter1);
 
-	if (filtered == native)
-		printf("Trying running again with more samples.\n");
+	printf("Estimated seccomp entry overhead: %llu ns\n",
+		filter1 - native - (filter2 - filter1));
 
 	return 0;
 }
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 252140a52553..7a6d40286a42 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -45,12 +45,19 @@
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <linux/kcmp.h>
+#include <sys/resource.h>
 
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <poll.h>
 
 #include "../kselftest_harness.h"
+#include "../clone3/clone3_selftests.h"
+
+/* Attempt to de-conflict with the selftests tree. */
+#ifndef SKIP
+#define SKIP(s, ...)	XFAIL(s, ##__VA_ARGS__)
+#endif
 
 #ifndef PR_SET_PTRACER
 # define PR_SET_PTRACER 0x59616d61
@@ -116,12 +123,18 @@ struct seccomp_data {
 #  define __NR_seccomp 277
 # elif defined(__riscv)
 #  define __NR_seccomp 277
+# elif defined(__csky__)
+#  define __NR_seccomp 277
 # elif defined(__hppa__)
 #  define __NR_seccomp 338
 # elif defined(__powerpc__)
 #  define __NR_seccomp 358
 # elif defined(__s390__)
 #  define __NR_seccomp 348
+# elif defined(__xtensa__)
+#  define __NR_seccomp 337
+# elif defined(__sh__)
+#  define __NR_seccomp 372
 # else
 #  warning "seccomp syscall number unknown for this architecture"
 #  define __NR_seccomp 0xffff
@@ -167,7 +180,9 @@ struct seccomp_metadata {
 
 #ifndef SECCOMP_FILTER_FLAG_NEW_LISTENER
 #define SECCOMP_FILTER_FLAG_NEW_LISTENER	(1UL << 3)
+#endif
 
+#ifndef SECCOMP_RET_USER_NOTIF
 #define SECCOMP_RET_USER_NOTIF 0x7fc00000U
 
 #define SECCOMP_IOC_MAGIC		'!'
@@ -180,7 +195,7 @@ struct seccomp_metadata {
 #define SECCOMP_IOCTL_NOTIF_RECV	SECCOMP_IOWR(0, struct seccomp_notif)
 #define SECCOMP_IOCTL_NOTIF_SEND	SECCOMP_IOWR(1,	\
 						struct seccomp_notif_resp)
-#define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOR(2, __u64)
+#define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOW(2, __u64)
 
 struct seccomp_notif {
 	__u64 id;
@@ -203,6 +218,39 @@ struct seccomp_notif_sizes {
 };
 #endif
 
+#ifndef SECCOMP_IOCTL_NOTIF_ADDFD
+/* On success, the return value is the remote process's added fd number */
+#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOW(3,	\
+						struct seccomp_notif_addfd)
+
+/* valid flags for seccomp_notif_addfd */
+#define SECCOMP_ADDFD_FLAG_SETFD	(1UL << 0) /* Specify remote fd */
+
+struct seccomp_notif_addfd {
+	__u64 id;
+	__u32 flags;
+	__u32 srcfd;
+	__u32 newfd;
+	__u32 newfd_flags;
+};
+#endif
+
+struct seccomp_notif_addfd_small {
+	__u64 id;
+	char weird[4];
+};
+#define SECCOMP_IOCTL_NOTIF_ADDFD_SMALL	\
+	SECCOMP_IOW(3, struct seccomp_notif_addfd_small)
+
+struct seccomp_notif_addfd_big {
+	union {
+		struct seccomp_notif_addfd addfd;
+		char buf[sizeof(struct seccomp_notif_addfd) + 8];
+	};
+};
+#define SECCOMP_IOCTL_NOTIF_ADDFD_BIG	\
+	SECCOMP_IOWR(3, struct seccomp_notif_addfd_big)
+
 #ifndef PTRACE_EVENTMSG_SYSCALL_ENTRY
 #define PTRACE_EVENTMSG_SYSCALL_ENTRY	1
 #define PTRACE_EVENTMSG_SYSCALL_EXIT	2
@@ -236,6 +284,40 @@ int seccomp(unsigned int op, unsigned int flags, void *args)
 #define SIBLING_EXIT_FAILURE	0xbadface
 #define SIBLING_EXIT_NEWPRIVS	0xbadfeed
 
+static int __filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2)
+{
+#ifdef __NR_kcmp
+	errno = 0;
+	return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2);
+#else
+	errno = ENOSYS;
+	return -1;
+#endif
+}
+
+/* Have TH_LOG report actual location filecmp() is used. */
+#define filecmp(pid1, pid2, fd1, fd2)	({		\
+	int _ret;					\
+							\
+	_ret = __filecmp(pid1, pid2, fd1, fd2);		\
+	if (_ret != 0) {				\
+		if (_ret < 0 && errno == ENOSYS) {	\
+			TH_LOG("kcmp() syscall missing (test is less accurate)");\
+			_ret = 0;			\
+		}					\
+	}						\
+	_ret; })
+
+TEST(kcmp)
+{
+	int ret;
+
+	ret = __filecmp(getpid(), getpid(), 1, 1);
+	EXPECT_EQ(ret, 0);
+	if (ret != 0 && errno == ENOSYS)
+		SKIP(return, "Kernel does not support kcmp() (missing CONFIG_CHECKPOINT_RESTORE?)");
+}
+
 TEST(mode_strict_support)
 {
 	long ret;
@@ -1470,6 +1552,7 @@ pid_t setup_trace_fixture(struct __test_metadata *_metadata,
 
 	return tracer_pid;
 }
+
 void teardown_trace_fixture(struct __test_metadata *_metadata,
 			    pid_t tracer)
 {
@@ -1603,6 +1686,14 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 # define ARCH_REGS	struct user_regs_struct
 # define SYSCALL_NUM	a7
 # define SYSCALL_RET	a0
+#elif defined(__csky__)
+# define ARCH_REGS	struct pt_regs
+#if defined(__CSKYABIV2__)
+# define SYSCALL_NUM	regs[3]
+#else
+# define SYSCALL_NUM	regs[9]
+#endif
+# define SYSCALL_RET	a0
 #elif defined(__hppa__)
 # define ARCH_REGS	struct user_regs_struct
 # define SYSCALL_NUM	gr[20]
@@ -1622,6 +1713,18 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 # define SYSCALL_SYSCALL_NUM regs[4]
 # define SYSCALL_RET	regs[2]
 # define SYSCALL_NUM_RET_SHARE_REG
+#elif defined(__xtensa__)
+# define ARCH_REGS	struct user_pt_regs
+# define SYSCALL_NUM	syscall
+/*
+ * On xtensa syscall return value is in the register
+ * a2 of the current window which is not fixed.
+ */
+#define SYSCALL_RET(reg) a[(reg).windowbase * 4 + 2]
+#elif defined(__sh__)
+# define ARCH_REGS	struct pt_regs
+# define SYSCALL_NUM	gpr[3]
+# define SYSCALL_RET	gpr[0]
 #else
 # error "Do not know how to find your architecture's registers and syscalls"
 #endif
@@ -1693,7 +1796,8 @@ void change_syscall(struct __test_metadata *_metadata,
 	EXPECT_EQ(0, ret) {}
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__powerpc__) || \
-	defined(__s390__) || defined(__hppa__) || defined(__riscv)
+	defined(__s390__) || defined(__hppa__) || defined(__riscv) || \
+	defined(__xtensa__) || defined(__csky__) || defined(__sh__)
 	{
 		regs.SYSCALL_NUM = syscall;
 	}
@@ -1736,6 +1840,9 @@ void change_syscall(struct __test_metadata *_metadata,
 	if (syscall == -1)
 #ifdef SYSCALL_NUM_RET_SHARE_REG
 		TH_LOG("Can't modify syscall return on this architecture");
+
+#elif defined(__xtensa__)
+		regs.SYSCALL_RET(regs) = result;
 #else
 		regs.SYSCALL_RET = result;
 #endif
@@ -1750,7 +1857,7 @@ void change_syscall(struct __test_metadata *_metadata,
 	EXPECT_EQ(0, ret);
 }
 
-void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee,
+void tracer_seccomp(struct __test_metadata *_metadata, pid_t tracee,
 		    int status, void *args)
 {
 	int ret;
@@ -1827,6 +1934,24 @@ FIXTURE(TRACE_syscall) {
 	pid_t tracer, mytid, mypid, parent;
 };
 
+FIXTURE_VARIANT(TRACE_syscall) {
+	/*
+	 * All of the SECCOMP_RET_TRACE behaviors can be tested with either
+	 * SECCOMP_RET_TRACE+PTRACE_CONT or plain ptrace()+PTRACE_SYSCALL.
+	 * This indicates if we should use SECCOMP_RET_TRACE (false), or
+	 * ptrace (true).
+	 */
+	bool use_ptrace;
+};
+
+FIXTURE_VARIANT_ADD(TRACE_syscall, ptrace) {
+	.use_ptrace = true,
+};
+
+FIXTURE_VARIANT_ADD(TRACE_syscall, seccomp) {
+	.use_ptrace = false,
+};
+
 FIXTURE_SETUP(TRACE_syscall)
 {
 	struct sock_filter filter[] = {
@@ -1842,12 +1967,11 @@ FIXTURE_SETUP(TRACE_syscall)
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
 	};
-
-	memset(&self->prog, 0, sizeof(self->prog));
-	self->prog.filter = malloc(sizeof(filter));
-	ASSERT_NE(NULL, self->prog.filter);
-	memcpy(self->prog.filter, filter, sizeof(filter));
-	self->prog.len = (unsigned short)ARRAY_SIZE(filter);
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+	long ret;
 
 	/* Prepare some testable syscall results. */
 	self->mytid = syscall(__NR_gettid);
@@ -1865,60 +1989,48 @@ FIXTURE_SETUP(TRACE_syscall)
 	ASSERT_NE(self->parent, self->mypid);
 
 	/* Launch tracer. */
-	self->tracer = setup_trace_fixture(_metadata, tracer_syscall, NULL,
-					   false);
-}
+	self->tracer = setup_trace_fixture(_metadata,
+					   variant->use_ptrace ? tracer_ptrace
+							       : tracer_seccomp,
+					   NULL, variant->use_ptrace);
 
-FIXTURE_TEARDOWN(TRACE_syscall)
-{
-	teardown_trace_fixture(_metadata, self->tracer);
-	if (self->prog.filter)
-		free(self->prog.filter);
-}
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
 
-TEST_F(TRACE_syscall, ptrace_syscall_redirected)
-{
-	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
-	teardown_trace_fixture(_metadata, self->tracer);
-	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
-					   true);
+	if (variant->use_ptrace)
+		return;
 
-	/* Tracer will redirect getpid to getppid. */
-	EXPECT_NE(self->mypid, syscall(__NR_getpid));
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
+	ASSERT_EQ(0, ret);
 }
 
-TEST_F(TRACE_syscall, ptrace_syscall_errno)
+FIXTURE_TEARDOWN(TRACE_syscall)
 {
-	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
 	teardown_trace_fixture(_metadata, self->tracer);
-	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
-					   true);
-
-	/* Tracer should skip the open syscall, resulting in ESRCH. */
-	EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat));
 }
 
-TEST_F(TRACE_syscall, ptrace_syscall_faked)
+TEST(negative_ENOSYS)
 {
-	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
-	teardown_trace_fixture(_metadata, self->tracer);
-	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
-					   true);
+	/*
+	 * There should be no difference between an "internal" skip
+	 * and userspace asking for syscall "-1".
+	 */
+	errno = 0;
+	EXPECT_EQ(-1, syscall(-1));
+	EXPECT_EQ(errno, ENOSYS);
+	/* And no difference for "still not valid but not -1". */
+	errno = 0;
+	EXPECT_EQ(-1, syscall(-101));
+	EXPECT_EQ(errno, ENOSYS);
+}
 
-	/* Tracer should skip the gettid syscall, resulting fake pid. */
-	EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid));
+TEST_F(TRACE_syscall, negative_ENOSYS)
+{
+	negative_ENOSYS(_metadata);
 }
 
 TEST_F(TRACE_syscall, syscall_allowed)
 {
-	long ret;
-
-	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
-	ASSERT_EQ(0, ret);
-
 	/* getppid works as expected (no changes). */
 	EXPECT_EQ(self->parent, syscall(__NR_getppid));
 	EXPECT_NE(self->mypid, syscall(__NR_getppid));
@@ -1926,14 +2038,6 @@ TEST_F(TRACE_syscall, syscall_allowed)
 
 TEST_F(TRACE_syscall, syscall_redirected)
 {
-	long ret;
-
-	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
-	ASSERT_EQ(0, ret);
-
 	/* getpid has been redirected to getppid as expected. */
 	EXPECT_EQ(self->parent, syscall(__NR_getpid));
 	EXPECT_NE(self->mypid, syscall(__NR_getpid));
@@ -1941,33 +2045,17 @@ TEST_F(TRACE_syscall, syscall_redirected)
 
 TEST_F(TRACE_syscall, syscall_errno)
 {
-	long ret;
-
-	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	/* openat has been skipped and an errno return. */
+	/* Tracer should skip the open syscall, resulting in ESRCH. */
 	EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat));
 }
 
 TEST_F(TRACE_syscall, syscall_faked)
 {
-	long ret;
-
-	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	/* gettid has been skipped and an altered return value stored. */
+	/* Tracer skips the gettid syscall and store altered return value. */
 	EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid));
 }
 
-TEST_F(TRACE_syscall, skip_after_RET_TRACE)
+TEST_F(TRACE_syscall, skip_after)
 {
 	struct sock_filter filter[] = {
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
@@ -1982,14 +2070,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE)
 	};
 	long ret;
 
-	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	/* Install fixture filter. */
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	/* Install "errno on getppid" filter. */
+	/* Install additional "errno on getppid" filter. */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
 	ASSERT_EQ(0, ret);
 
@@ -1999,69 +2080,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE)
 	EXPECT_EQ(EPERM, errno);
 }
 
-TEST_F_SIGNAL(TRACE_syscall, kill_after_RET_TRACE, SIGSYS)
-{
-	struct sock_filter filter[] = {
-		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-			offsetof(struct seccomp_data, nr)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-	};
-	struct sock_fprog prog = {
-		.len = (unsigned short)ARRAY_SIZE(filter),
-		.filter = filter,
-	};
-	long ret;
-
-	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	/* Install fixture filter. */
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	/* Install "death on getppid" filter. */
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	/* Tracer will redirect getpid to getppid, and we should die. */
-	EXPECT_NE(self->mypid, syscall(__NR_getpid));
-}
-
-TEST_F(TRACE_syscall, skip_after_ptrace)
-{
-	struct sock_filter filter[] = {
-		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-			offsetof(struct seccomp_data, nr)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-	};
-	struct sock_fprog prog = {
-		.len = (unsigned short)ARRAY_SIZE(filter),
-		.filter = filter,
-	};
-	long ret;
-
-	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
-	teardown_trace_fixture(_metadata, self->tracer);
-	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
-					   true);
-
-	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	/* Install "errno on getppid" filter. */
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	/* Tracer will redirect getpid to getppid, and we should see EPERM. */
-	EXPECT_EQ(-1, syscall(__NR_getpid));
-	EXPECT_EQ(EPERM, errno);
-}
-
-TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS)
+TEST_F_SIGNAL(TRACE_syscall, kill_after, SIGSYS)
 {
 	struct sock_filter filter[] = {
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
@@ -2076,15 +2095,7 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS)
 	};
 	long ret;
 
-	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
-	teardown_trace_fixture(_metadata, self->tracer);
-	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
-					   true);
-
-	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
-	ASSERT_EQ(0, ret);
-
-	/* Install "death on getppid" filter. */
+	/* Install additional "death on getppid" filter. */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
 	ASSERT_EQ(0, ret);
 
@@ -3069,7 +3080,7 @@ TEST(get_metadata)
 
 	/* Only real root can get metadata. */
 	if (geteuid()) {
-		XFAIL(return, "get_metadata requires real root");
+		SKIP(return, "get_metadata requires real root");
 		return;
 	}
 
@@ -3112,7 +3123,7 @@ TEST(get_metadata)
 	ret = ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md);
 	EXPECT_EQ(sizeof(md), ret) {
 		if (errno == EINVAL)
-			XFAIL(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)");
+			SKIP(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)");
 	}
 
 	EXPECT_EQ(md.flags, SECCOMP_FILTER_FLAG_LOG);
@@ -3128,7 +3139,7 @@ skip:
 	ASSERT_EQ(0, kill(pid, SIGKILL));
 }
 
-static int user_trap_syscall(int nr, unsigned int flags)
+static int user_notif_syscall(int nr, unsigned int flags)
 {
 	struct sock_filter filter[] = {
 		BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
@@ -3174,7 +3185,7 @@ TEST(user_notification_basic)
 
 	/* Check that we get -ENOSYS with no listener attached */
 	if (pid == 0) {
-		if (user_trap_syscall(__NR_getppid, 0) < 0)
+		if (user_notif_syscall(__NR_getppid, 0) < 0)
 			exit(1);
 		ret = syscall(__NR_getppid);
 		exit(ret >= 0 || errno != ENOSYS);
@@ -3191,13 +3202,13 @@ TEST(user_notification_basic)
 	EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0);
 
 	/* Check that the basic notification machinery works */
-	listener = user_trap_syscall(__NR_getppid,
-				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	/* Installing a second listener in the chain should EBUSY */
-	EXPECT_EQ(user_trap_syscall(__NR_getppid,
-				    SECCOMP_FILTER_FLAG_NEW_LISTENER),
+	EXPECT_EQ(user_notif_syscall(__NR_getppid,
+				     SECCOMP_FILTER_FLAG_NEW_LISTENER),
 		  -1);
 	EXPECT_EQ(errno, EBUSY);
 
@@ -3258,15 +3269,20 @@ TEST(user_notification_with_tsync)
 	int ret;
 	unsigned int flags;
 
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
 	/* these were exclusive */
 	flags = SECCOMP_FILTER_FLAG_NEW_LISTENER |
 		SECCOMP_FILTER_FLAG_TSYNC;
-	ASSERT_EQ(-1, user_trap_syscall(__NR_getppid, flags));
+	ASSERT_EQ(-1, user_notif_syscall(__NR_getppid, flags));
 	ASSERT_EQ(EINVAL, errno);
 
 	/* but now they're not */
 	flags |= SECCOMP_FILTER_FLAG_TSYNC_ESRCH;
-	ret = user_trap_syscall(__NR_getppid, flags);
+	ret = user_notif_syscall(__NR_getppid, flags);
 	close(ret);
 	ASSERT_LE(0, ret);
 }
@@ -3284,8 +3300,8 @@ TEST(user_notification_kill_in_middle)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	listener = user_trap_syscall(__NR_getppid,
-				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	/*
@@ -3338,8 +3354,8 @@ TEST(user_notification_signal)
 
 	ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0);
 
-	listener = user_trap_syscall(__NR_gettid,
-				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_notif_syscall(__NR_gettid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	pid = fork();
@@ -3408,8 +3424,8 @@ TEST(user_notification_closed_listener)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	listener = user_trap_syscall(__NR_getppid,
-				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	/*
@@ -3440,10 +3456,13 @@ TEST(user_notification_child_pid_ns)
 	struct seccomp_notif req = {};
 	struct seccomp_notif_resp resp = {};
 
-	ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0);
+	ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0) {
+		if (errno == EINVAL)
+			SKIP(return, "kernel missing CLONE_NEWUSER support");
+	};
 
-	listener = user_trap_syscall(__NR_getppid,
-				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	pid = fork();
@@ -3482,8 +3501,8 @@ TEST(user_notification_sibling_pid_ns)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	listener = user_trap_syscall(__NR_getppid,
-				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	pid = fork();
@@ -3505,7 +3524,10 @@ TEST(user_notification_sibling_pid_ns)
 	}
 
 	/* Create the sibling ns, and sibling in it. */
-	ASSERT_EQ(unshare(CLONE_NEWPID), 0);
+	ASSERT_EQ(unshare(CLONE_NEWPID), 0) {
+		if (errno == EPERM)
+			SKIP(return, "CLONE_NEWPID requires CAP_SYS_ADMIN");
+	}
 	ASSERT_EQ(errno, 0);
 
 	pid2 = fork();
@@ -3547,8 +3569,8 @@ TEST(user_notification_fault_recv)
 
 	ASSERT_EQ(unshare(CLONE_NEWUSER), 0);
 
-	listener = user_trap_syscall(__NR_getppid,
-				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	pid = fork();
@@ -3585,16 +3607,6 @@ TEST(seccomp_get_notif_sizes)
 	EXPECT_EQ(sizes.seccomp_notif_resp, sizeof(struct seccomp_notif_resp));
 }
 
-static int filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2)
-{
-#ifdef __NR_kcmp
-	return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2);
-#else
-	errno = ENOSYS;
-	return -1;
-#endif
-}
-
 TEST(user_notification_continue)
 {
 	pid_t pid;
@@ -3609,7 +3621,7 @@ TEST(user_notification_continue)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	listener = user_trap_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_notif_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	pid = fork();
@@ -3619,20 +3631,14 @@ TEST(user_notification_continue)
 		int dup_fd, pipe_fds[2];
 		pid_t self;
 
-		ret = pipe(pipe_fds);
-		if (ret < 0)
-			exit(1);
+		ASSERT_GE(pipe(pipe_fds), 0);
 
 		dup_fd = dup(pipe_fds[0]);
-		if (dup_fd < 0)
-			exit(1);
+		ASSERT_GE(dup_fd, 0);
+		EXPECT_NE(pipe_fds[0], dup_fd);
 
 		self = getpid();
-
-		ret = filecmp(self, self, pipe_fds[0], dup_fd);
-		if (ret)
-			exit(2);
-
+		ASSERT_EQ(filecmp(self, self, pipe_fds[0], dup_fd), 0);
 		exit(0);
 	}
 
@@ -3673,7 +3679,7 @@ TEST(user_notification_continue)
 	resp.val = 0;
 	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0) {
 		if (errno == EINVAL)
-			XFAIL(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE");
+			SKIP(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE");
 	}
 
 skip:
@@ -3681,15 +3687,342 @@ skip:
 	EXPECT_EQ(true, WIFEXITED(status));
 	EXPECT_EQ(0, WEXITSTATUS(status)) {
 		if (WEXITSTATUS(status) == 2) {
-			XFAIL(return, "Kernel does not support kcmp() syscall");
+			SKIP(return, "Kernel does not support kcmp() syscall");
 			return;
 		}
 	}
 }
 
+TEST(user_notification_filter_empty)
+{
+	pid_t pid;
+	long ret;
+	int status;
+	struct pollfd pollfd;
+	struct clone_args args = {
+		.flags = CLONE_FILES,
+		.exit_signal = SIGCHLD,
+	};
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	pid = sys_clone3(&args, sizeof(args));
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		int listener;
+
+		listener = user_notif_syscall(__NR_mknod, SECCOMP_FILTER_FLAG_NEW_LISTENER);
+		if (listener < 0)
+			_exit(EXIT_FAILURE);
+
+		if (dup2(listener, 200) != 200)
+			_exit(EXIT_FAILURE);
+
+		close(listener);
+
+		_exit(EXIT_SUCCESS);
+	}
+
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+
+	/*
+	 * The seccomp filter has become unused so we should be notified once
+	 * the kernel gets around to cleaning up task struct.
+	 */
+	pollfd.fd = 200;
+	pollfd.events = POLLHUP;
+
+	EXPECT_GT(poll(&pollfd, 1, 2000), 0);
+	EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0);
+}
+
+static void *do_thread(void *data)
+{
+	return NULL;
+}
+
+TEST(user_notification_filter_empty_threaded)
+{
+	pid_t pid;
+	long ret;
+	int status;
+	struct pollfd pollfd;
+	struct clone_args args = {
+		.flags = CLONE_FILES,
+		.exit_signal = SIGCHLD,
+	};
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	pid = sys_clone3(&args, sizeof(args));
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		pid_t pid1, pid2;
+		int listener, status;
+		pthread_t thread;
+
+		listener = user_notif_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER);
+		if (listener < 0)
+			_exit(EXIT_FAILURE);
+
+		if (dup2(listener, 200) != 200)
+			_exit(EXIT_FAILURE);
+
+		close(listener);
+
+		pid1 = fork();
+		if (pid1 < 0)
+			_exit(EXIT_FAILURE);
+
+		if (pid1 == 0)
+			_exit(EXIT_SUCCESS);
+
+		pid2 = fork();
+		if (pid2 < 0)
+			_exit(EXIT_FAILURE);
+
+		if (pid2 == 0)
+			_exit(EXIT_SUCCESS);
+
+		if (pthread_create(&thread, NULL, do_thread, NULL) ||
+		    pthread_join(thread, NULL))
+			_exit(EXIT_FAILURE);
+
+		if (pthread_create(&thread, NULL, do_thread, NULL) ||
+		    pthread_join(thread, NULL))
+			_exit(EXIT_FAILURE);
+
+		if (waitpid(pid1, &status, 0) != pid1 || !WIFEXITED(status) ||
+		    WEXITSTATUS(status))
+			_exit(EXIT_FAILURE);
+
+		if (waitpid(pid2, &status, 0) != pid2 || !WIFEXITED(status) ||
+		    WEXITSTATUS(status))
+			_exit(EXIT_FAILURE);
+
+		exit(EXIT_SUCCESS);
+	}
+
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+
+	/*
+	 * The seccomp filter has become unused so we should be notified once
+	 * the kernel gets around to cleaning up task struct.
+	 */
+	pollfd.fd = 200;
+	pollfd.events = POLLHUP;
+
+	EXPECT_GT(poll(&pollfd, 1, 2000), 0);
+	EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0);
+}
+
+TEST(user_notification_addfd)
+{
+	pid_t pid;
+	long ret;
+	int status, listener, memfd, fd;
+	struct seccomp_notif_addfd addfd = {};
+	struct seccomp_notif_addfd_small small = {};
+	struct seccomp_notif_addfd_big big = {};
+	struct seccomp_notif req = {};
+	struct seccomp_notif_resp resp = {};
+	/* 100 ms */
+	struct timespec delay = { .tv_nsec = 100000000 };
+
+	memfd = memfd_create("test", 0);
+	ASSERT_GE(memfd, 0);
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	/* Check that the basic notification machinery works */
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	ASSERT_GE(listener, 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		if (syscall(__NR_getppid) != USER_NOTIF_MAGIC)
+			exit(1);
+		exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);
+	}
+
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+
+	addfd.srcfd = memfd;
+	addfd.newfd = 0;
+	addfd.id = req.id;
+	addfd.flags = 0x0;
+
+	/* Verify bad newfd_flags cannot be set */
+	addfd.newfd_flags = ~O_CLOEXEC;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EINVAL);
+	addfd.newfd_flags = O_CLOEXEC;
+
+	/* Verify bad flags cannot be set */
+	addfd.flags = 0xff;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EINVAL);
+	addfd.flags = 0;
+
+	/* Verify that remote_fd cannot be set without setting flags */
+	addfd.newfd = 1;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EINVAL);
+	addfd.newfd = 0;
+
+	/* Verify small size cannot be set */
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_SMALL, &small), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* Verify we can't send bits filled in unknown buffer area */
+	memset(&big, 0xAA, sizeof(big));
+	big.addfd = addfd;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big), -1);
+	EXPECT_EQ(errno, E2BIG);
+
+
+	/* Verify we can set an arbitrary remote fd */
+	fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd);
+	/*
+	 * The child has fds 0(stdin), 1(stdout), 2(stderr), 3(memfd),
+	 * 4(listener), so the newly allocated fd should be 5.
+	 */
+	EXPECT_EQ(fd, 5);
+	EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0);
+
+	/* Verify we can set an arbitrary remote fd with large size */
+	memset(&big, 0x0, sizeof(big));
+	big.addfd = addfd;
+	fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big);
+	EXPECT_EQ(fd, 6);
+
+	/* Verify we can set a specific remote fd */
+	addfd.newfd = 42;
+	addfd.flags = SECCOMP_ADDFD_FLAG_SETFD;
+	fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd);
+	EXPECT_EQ(fd, 42);
+	EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0);
+
+	/* Resume syscall */
+	resp.id = req.id;
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+	/*
+	 * This sets the ID of the ADD FD to the last request plus 1. The
+	 * notification ID increments 1 per notification.
+	 */
+	addfd.id = req.id + 1;
+
+	/* This spins until the underlying notification is generated */
+	while (ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd) != -1 &&
+	       errno != -EINPROGRESS)
+		nanosleep(&delay, NULL);
+
+	memset(&req, 0, sizeof(req));
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+	ASSERT_EQ(addfd.id, req.id);
+
+	resp.id = req.id;
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+	/* Wait for child to finish. */
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+
+	close(memfd);
+}
+
+TEST(user_notification_addfd_rlimit)
+{
+	pid_t pid;
+	long ret;
+	int status, listener, memfd;
+	struct seccomp_notif_addfd addfd = {};
+	struct seccomp_notif req = {};
+	struct seccomp_notif_resp resp = {};
+	const struct rlimit lim = {
+		.rlim_cur	= 0,
+		.rlim_max	= 0,
+	};
+
+	memfd = memfd_create("test", 0);
+	ASSERT_GE(memfd, 0);
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	/* Check that the basic notification machinery works */
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	ASSERT_GE(listener, 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0)
+		exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);
+
+
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+
+	ASSERT_EQ(prlimit(pid, RLIMIT_NOFILE, &lim, NULL), 0);
+
+	addfd.srcfd = memfd;
+	addfd.newfd_flags = O_CLOEXEC;
+	addfd.newfd = 0;
+	addfd.id = req.id;
+	addfd.flags = 0;
+
+	/* Should probably spot check /proc/sys/fs/file-nr */
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EMFILE);
+
+	addfd.newfd = 100;
+	addfd.flags = SECCOMP_ADDFD_FLAG_SETFD;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EBADF);
+
+	resp.id = req.id;
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+	/* Wait for child to finish. */
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+
+	close(memfd);
+}
+
 /*
  * TODO:
- * - add microbenchmarks
  * - expand NNP testing
  * - better arch-specific TRACE and TRAP handlers.
  * - endianness checking when appropriate
@@ -3697,7 +4030,6 @@ skip:
  * - arch value testing (x86 modes especially)
  * - verify that FILTER_FLAG_LOG filters generate log messages
  * - verify that RET_LOG generates log messages
- * - ...
  */
 
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/seccomp/settings b/tools/testing/selftests/seccomp/settings
new file mode 100644
index 000000000000..ba4d85f74cd6
--- /dev/null
+++ b/tools/testing/selftests/seccomp/settings
@@ -0,0 +1 @@
+timeout=90
diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c
index ad0f8df2ca0a..8934a3766d20 100644
--- a/tools/testing/selftests/sigaltstack/sas.c
+++ b/tools/testing/selftests/sigaltstack/sas.c
@@ -71,7 +71,7 @@ void my_usr1(int sig, siginfo_t *si, void *u)
 	swapcontext(&sc, &uc);
 	ksft_print_msg("%s\n", p->msg);
 	if (!p->flag) {
-		ksft_exit_skip("[RUN]\tAborting\n");
+		ksft_exit_fail_msg("[RUN]\tAborting\n");
 		exit(EXIT_FAILURE);
 	}
 }
@@ -144,7 +144,7 @@ int main(void)
 	err = sigaltstack(&stk, NULL);
 	if (err) {
 		if (errno == EINVAL) {
-			ksft_exit_skip(
+			ksft_test_result_skip(
 				"[NOTE]\tThe running kernel doesn't support SS_AUTODISARM\n");
 			/*
 			 * If test cases for the !SS_AUTODISARM variant were
diff --git a/tools/testing/selftests/splice/.gitignore b/tools/testing/selftests/splice/.gitignore
index d5a2da428752..be8266f5d04c 100644
--- a/tools/testing/selftests/splice/.gitignore
+++ b/tools/testing/selftests/splice/.gitignore
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 default_file_splice_read
+splice_read
diff --git a/tools/testing/selftests/splice/Makefile b/tools/testing/selftests/splice/Makefile
index e519b159b60d..541cd826d5a5 100644
--- a/tools/testing/selftests/splice/Makefile
+++ b/tools/testing/selftests/splice/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := default_file_splice_read.sh
-TEST_GEN_PROGS_EXTENDED := default_file_splice_read
+TEST_PROGS := default_file_splice_read.sh short_splice_read.sh
+TEST_GEN_PROGS_EXTENDED := default_file_splice_read splice_read
 
 include ../lib.mk
diff --git a/tools/testing/selftests/splice/config b/tools/testing/selftests/splice/config
new file mode 100644
index 000000000000..058c928368b8
--- /dev/null
+++ b/tools/testing/selftests/splice/config
@@ -0,0 +1 @@
+CONFIG_TEST_LKM=m
diff --git a/tools/testing/selftests/splice/settings b/tools/testing/selftests/splice/settings
new file mode 100644
index 000000000000..89cedfc0d12b
--- /dev/null
+++ b/tools/testing/selftests/splice/settings
@@ -0,0 +1 @@
+timeout=5
diff --git a/tools/testing/selftests/splice/short_splice_read.sh b/tools/testing/selftests/splice/short_splice_read.sh
new file mode 100755
index 000000000000..7810d3589d9a
--- /dev/null
+++ b/tools/testing/selftests/splice/short_splice_read.sh
@@ -0,0 +1,56 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+set -e
+
+ret=0
+
+do_splice()
+{
+	filename="$1"
+	bytes="$2"
+	expected="$3"
+
+	out=$(./splice_read "$filename" "$bytes" | cat)
+	if [ "$out" = "$expected" ] ; then
+		echo "ok: $filename $bytes"
+	else
+		echo "FAIL: $filename $bytes"
+		ret=1
+	fi
+}
+
+test_splice()
+{
+	filename="$1"
+
+	full=$(cat "$filename")
+	two=$(echo "$full" | grep -m1 . | cut -c-2)
+
+	# Make sure full splice has the same contents as a standard read.
+	do_splice "$filename" 4096 "$full"
+
+	# Make sure a partial splice see the first two characters.
+	do_splice "$filename" 2 "$two"
+}
+
+# proc_single_open(), seq_read()
+test_splice /proc/$$/limits
+# special open, seq_read()
+test_splice /proc/$$/comm
+
+# proc_handler, proc_dointvec_minmax
+test_splice /proc/sys/fs/nr_open
+# proc_handler, proc_dostring
+test_splice /proc/sys/kernel/modprobe
+# proc_handler, special read
+test_splice /proc/sys/kernel/version
+
+if ! [ -d /sys/module/test_module/sections ] ; then
+	modprobe test_module
+fi
+# kernfs, attr
+test_splice /sys/module/test_module/coresize
+# kernfs, binattr
+test_splice /sys/module/test_module/sections/.init.text
+
+exit $ret
diff --git a/tools/testing/selftests/splice/splice_read.c b/tools/testing/selftests/splice/splice_read.c
new file mode 100644
index 000000000000..46dae6a25cfb
--- /dev/null
+++ b/tools/testing/selftests/splice/splice_read.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+int main(int argc, char *argv[])
+{
+	int fd;
+	size_t size;
+	ssize_t spliced;
+
+	if (argc < 2) {
+		fprintf(stderr, "Usage: %s INPUT [BYTES]\n", argv[0]);
+		return EXIT_FAILURE;
+	}
+
+	fd = open(argv[1], O_RDONLY);
+	if (fd < 0) {
+		perror(argv[1]);
+		return EXIT_FAILURE;
+	}
+
+	if (argc == 3)
+		size = atol(argv[2]);
+	else {
+		struct stat statbuf;
+
+		if (fstat(fd, &statbuf) < 0) {
+			perror(argv[1]);
+			return EXIT_FAILURE;
+		}
+
+		if (statbuf.st_size > INT_MAX) {
+			fprintf(stderr, "%s: Too big\n", argv[1]);
+			return EXIT_FAILURE;
+		}
+
+		size = statbuf.st_size;
+	}
+
+	/* splice(2) file to stdout. */
+	spliced = splice(fd, NULL, STDOUT_FILENO, NULL,
+		      size, SPLICE_F_MOVE);
+	if (spliced < 0) {
+		perror("splice");
+		return EXIT_FAILURE;
+	}
+
+	close(fd);
+	return EXIT_SUCCESS;
+}
diff --git a/tools/testing/selftests/sync/sync_test.c b/tools/testing/selftests/sync/sync_test.c
index 3824b66f41a0..414a617db993 100644
--- a/tools/testing/selftests/sync/sync_test.c
+++ b/tools/testing/selftests/sync/sync_test.c
@@ -86,9 +86,9 @@ int main(void)
 	int err;
 
 	ksft_print_header();
-	ksft_set_plan(3 + 7);
 
 	sync_api_supported();
+	ksft_set_plan(3 + 7);
 
 	ksft_print_msg("[RUN]\tTesting sync framework\n");
 
diff --git a/tools/testing/selftests/tc-testing/bpf/Makefile b/tools/testing/selftests/tc-testing/Makefile
index be5a5e542804..91fee5c43274 100644
--- a/tools/testing/selftests/tc-testing/bpf/Makefile
+++ b/tools/testing/selftests/tc-testing/Makefile
@@ -1,11 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 
-APIDIR := ../../../../include/uapi
+top_srcdir = $(abspath ../../../..)
+APIDIR := $(top_scrdir)/include/uapi
 TEST_GEN_FILES = action.o
 
-top_srcdir = ../../../../..
 KSFT_KHDR_INSTALL := 1
-include ../../lib.mk
+include ../lib.mk
 
 CLANG ?= clang
 LLC   ?= llc
@@ -28,3 +28,6 @@ $(OUTPUT)/%.o: %.c
 	$(CLANG) $(CLANG_FLAGS) \
 		 -O2 -target bpf -emit-llvm -c $< -o - |      \
 	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
+
+TEST_PROGS += ./tdc.sh
+TEST_FILES := tdc*.py Tdc*.py plugins plugin-lib tc-tests
diff --git a/tools/testing/selftests/tc-testing/bpf/action.c b/tools/testing/selftests/tc-testing/action.c
index c32b99b80e19..c32b99b80e19 100644
--- a/tools/testing/selftests/tc-testing/bpf/action.c
+++ b/tools/testing/selftests/tc-testing/action.c
diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh
new file mode 100755
index 000000000000..7fe38c76db44
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tdc.sh
@@ -0,0 +1,5 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+./tdc.py -c actions --nobuildebpf
+./tdc.py -c qdisc
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index 080709cc4297..cd4a27ee1466 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -24,7 +24,7 @@ NAMES = {
           # Name of the namespace to use
           'NS': 'tcut',
           # Directory containing eBPF test programs
-          'EBPFDIR': './bpf'
+          'EBPFDIR': './'
         }
 
 
diff --git a/tools/testing/selftests/uevent/uevent_filtering.c b/tools/testing/selftests/uevent/uevent_filtering.c
index f83391aa42cf..5cebfb356345 100644
--- a/tools/testing/selftests/uevent/uevent_filtering.c
+++ b/tools/testing/selftests/uevent/uevent_filtering.c
@@ -19,7 +19,6 @@
 #include <sys/wait.h>
 #include <unistd.h>
 
-#include "../kselftest.h"
 #include "../kselftest_harness.h"
 
 #define __DEV_FULL "/sys/devices/virtual/mem/full/uevent"
diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
index 79db22604019..93fc5cadce61 100644
--- a/tools/testing/selftests/vm/hmm-tests.c
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -881,8 +881,9 @@ TEST_F(hmm, migrate)
 }
 
 /*
- * Migrate anonymous memory to device private memory and fault it back to system
- * memory.
+ * Migrate anonymous memory to device private memory and fault some of it back
+ * to system memory, then try migrating the resulting mix of system and device
+ * private memory to the device.
  */
 TEST_F(hmm, migrate_fault)
 {
@@ -924,14 +925,58 @@ TEST_F(hmm, migrate_fault)
 	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
 		ASSERT_EQ(ptr[i], i);
 
-	/* Fault pages back to system memory and check them. */
-	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+	/* Fault half the pages back to system memory and check them. */
+	for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	/* Migrate memory to the device again. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device read. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
 		ASSERT_EQ(ptr[i], i);
 
 	hmm_buffer_free(buffer);
 }
 
 /*
+ * Migrate anonymous shared memory to device private memory.
+ */
+TEST_F(hmm, migrate_shared)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_SHARED | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Migrate memory to device. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ASSERT_EQ(ret, -ENOENT);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
  * Try to migrate various memory types to device private memory.
  */
 TEST_F(hmm2, migrate_mixed)
@@ -1292,6 +1337,82 @@ TEST_F(hmm2, snapshot)
 }
 
 /*
+ * Test the hmm_range_fault() HMM_PFN_PMD flag for large pages that
+ * should be mapped by a large page table entry.
+ */
+TEST_F(hmm, compound)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	int *ptr;
+	unsigned char *m;
+	int ret;
+	long pagesizes[4];
+	int n, idx;
+	unsigned long i;
+
+	/* Skip test if we can't allocate a hugetlbfs page. */
+
+	n = gethugepagesizes(pagesizes, 4);
+	if (n <= 0)
+		return;
+	for (idx = 0; --n > 0; ) {
+		if (pagesizes[n] < pagesizes[idx])
+			idx = n;
+	}
+	size = ALIGN(TWOMEG, pagesizes[idx]);
+	npages = size >> self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->ptr = get_hugepage_region(size, GHR_STRICT);
+	if (buffer->ptr == NULL) {
+		free(buffer);
+		return;
+	}
+
+	buffer->size = size;
+	buffer->mirror = malloc(npages);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	/* Initialize the pages the device will snapshot in buffer->ptr. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Simulate a device snapshotting CPU pagetables. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device saw. */
+	m = buffer->mirror;
+	for (i = 0; i < npages; ++i)
+		ASSERT_EQ(m[i], HMM_DMIRROR_PROT_WRITE |
+				HMM_DMIRROR_PROT_PMD);
+
+	/* Make the region read-only. */
+	ret = mprotect(buffer->ptr, size, PROT_READ);
+	ASSERT_EQ(ret, 0);
+
+	/* Simulate a device snapshotting CPU pagetables. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device saw. */
+	m = buffer->mirror;
+	for (i = 0; i < npages; ++i)
+		ASSERT_EQ(m[i], HMM_DMIRROR_PROT_READ |
+				HMM_DMIRROR_PROT_PMD);
+
+	free_hugepage_region(buffer->ptr);
+	buffer->ptr = NULL;
+	hmm_buffer_free(buffer);
+}
+
+/*
  * Test two devices reading the same memory (double mapped).
  */
 TEST_F(hmm2, double_map)
diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c
index fc19addcb5c8..fdbb602ecf32 100644
--- a/tools/testing/selftests/vm/protection_keys.c
+++ b/tools/testing/selftests/vm/protection_keys.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Tests Memory Protection Keys (see Documentation/vm/protection-keys.txt)
+ * Tests Memory Protection Keys (see Documentation/core-api/protection-keys.rst)
  *
  * There are examples in here of:
  *  * how to set protection keys on memory
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index d2796ea98c5a..6703c7906b71 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -13,7 +13,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie)
 TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
 			check_initial_reg_state sigreturn iopl ioperm \
 			test_vdso test_vsyscall mov_ss_trap \
-			syscall_arg_fault
+			syscall_arg_fault fsgsbase_restore
 TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 15a329da59fa..998319553523 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -285,7 +285,8 @@ static unsigned short load_gs(void)
 		/* 32-bit set_thread_area */
 		long ret;
 		asm volatile ("int $0x80"
-			      : "=a" (ret) : "a" (243), "b" (low_desc)
+			      : "=a" (ret), "+m" (*low_desc)
+			      : "a" (243), "b" (low_desc)
 			      : "r8", "r9", "r10", "r11");
 		memcpy(&desc, low_desc, sizeof(desc));
 		munmap(low_desc, sizeof(desc));
@@ -489,11 +490,28 @@ static void test_ptrace_write_gsbase(void)
 		 * selector value is changed or not by the GSBASE write in
 		 * a ptracer.
 		 */
-		if (gs == 0 && base == 0xFF) {
-			printf("[OK]\tGS was reset as expected\n");
-		} else {
+		if (gs != *shared_scratch) {
 			nerrs++;
-			printf("[FAIL]\tGS=0x%lx, GSBASE=0x%lx (should be 0, 0xFF)\n", gs, base);
+			printf("[FAIL]\tGS changed to %lx\n", gs);
+
+			/*
+			 * On older kernels, poking a nonzero value into the
+			 * base would zero the selector.  On newer kernels,
+			 * this behavior has changed -- poking the base
+			 * changes only the base and, if FSGSBASE is not
+			 * available, this may have no effect once the tracee
+			 * is resumed.
+			 */
+			if (gs == 0)
+				printf("\tNote: this is expected behavior on older kernels.\n");
+		} else if (have_fsgsbase && (base != 0xFF)) {
+			nerrs++;
+			printf("[FAIL]\tGSBASE changed to %lx\n", base);
+		} else {
+			printf("[OK]\tGS remained 0x%hx", *shared_scratch);
+			if (have_fsgsbase)
+				printf(" and GSBASE changed to 0xFF");
+			printf("\n");
 		}
 	}
 
diff --git a/tools/testing/selftests/x86/fsgsbase_restore.c b/tools/testing/selftests/x86/fsgsbase_restore.c
new file mode 100644
index 000000000000..6fffadc51579
--- /dev/null
+++ b/tools/testing/selftests/x86/fsgsbase_restore.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * fsgsbase_restore.c, test ptrace vs fsgsbase
+ * Copyright (c) 2020 Andy Lutomirski
+ *
+ * This test case simulates a tracer redirecting tracee execution to
+ * a function and then restoring tracee state using PTRACE_GETREGS and
+ * PTRACE_SETREGS.  This is similar to what gdb does when doing
+ * 'p func()'.  The catch is that this test has the called function
+ * modify a segment register.  This makes sure that ptrace correctly
+ * restores segment state when using PTRACE_SETREGS.
+ *
+ * This is not part of fsgsbase.c, because that test is 64-bit only.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <err.h>
+#include <sys/user.h>
+#include <asm/prctl.h>
+#include <sys/prctl.h>
+#include <asm/ldt.h>
+#include <sys/mman.h>
+#include <stddef.h>
+#include <sys/ptrace.h>
+#include <sys/wait.h>
+#include <stdint.h>
+
+#define EXPECTED_VALUE 0x1337f00d
+
+#ifdef __x86_64__
+# define SEG "%gs"
+#else
+# define SEG "%fs"
+#endif
+
+static unsigned int dereference_seg_base(void)
+{
+	int ret;
+	asm volatile ("mov %" SEG ":(0), %0" : "=rm" (ret));
+	return ret;
+}
+
+static void init_seg(void)
+{
+	unsigned int *target = mmap(
+		NULL, sizeof(unsigned int),
+		PROT_READ | PROT_WRITE,
+		MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0);
+	if (target == MAP_FAILED)
+		err(1, "mmap");
+
+	*target = EXPECTED_VALUE;
+
+	printf("\tsegment base address = 0x%lx\n", (unsigned long)target);
+
+	struct user_desc desc = {
+		.entry_number    = 0,
+		.base_addr       = (unsigned int)(uintptr_t)target,
+		.limit           = sizeof(unsigned int) - 1,
+		.seg_32bit       = 1,
+		.contents        = 0, /* Data, grow-up */
+		.read_exec_only  = 0,
+		.limit_in_pages  = 0,
+		.seg_not_present = 0,
+		.useable         = 0
+	};
+	if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) == 0) {
+		printf("\tusing LDT slot 0\n");
+		asm volatile ("mov %0, %" SEG :: "rm" ((unsigned short)0x7));
+	} else {
+		/* No modify_ldt for us (configured out, perhaps) */
+
+		struct user_desc *low_desc = mmap(
+			NULL, sizeof(desc),
+			PROT_READ | PROT_WRITE,
+			MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0);
+		memcpy(low_desc, &desc, sizeof(desc));
+
+		low_desc->entry_number = -1;
+
+		/* 32-bit set_thread_area */
+		long ret;
+		asm volatile ("int $0x80"
+			      : "=a" (ret), "+m" (*low_desc)
+			      : "a" (243), "b" (low_desc)
+#ifdef __x86_64__
+			      : "r8", "r9", "r10", "r11"
+#endif
+			);
+		memcpy(&desc, low_desc, sizeof(desc));
+		munmap(low_desc, sizeof(desc));
+
+		if (ret != 0) {
+			printf("[NOTE]\tcould not create a segment -- can't test anything\n");
+			exit(0);
+		}
+		printf("\tusing GDT slot %d\n", desc.entry_number);
+
+		unsigned short sel = (unsigned short)((desc.entry_number << 3) | 0x3);
+		asm volatile ("mov %0, %" SEG :: "rm" (sel));
+	}
+}
+
+static void tracee_zap_segment(void)
+{
+	/*
+	 * The tracer will redirect execution here.  This is meant to
+	 * work like gdb's 'p func()' feature.  The tricky bit is that
+	 * we modify a segment register in order to make sure that ptrace
+	 * can correctly restore segment registers.
+	 */
+	printf("\tTracee: in tracee_zap_segment()\n");
+
+	/*
+	 * Write a nonzero selector with base zero to the segment register.
+	 * Using a null selector would defeat the test on AMD pre-Zen2
+	 * CPUs, as such CPUs don't clear the base when loading a null
+	 * selector.
+	 */
+	unsigned short sel;
+	asm volatile ("mov %%ss, %0\n\t"
+		      "mov %0, %" SEG
+		      : "=rm" (sel));
+
+	pid_t pid = getpid(), tid = syscall(SYS_gettid);
+
+	printf("\tTracee is going back to sleep\n");
+	syscall(SYS_tgkill, pid, tid, SIGSTOP);
+
+	/* Should not get here. */
+	while (true) {
+		printf("[FAIL]\tTracee hit unreachable code\n");
+		pause();
+	}
+}
+
+int main()
+{
+	printf("\tSetting up a segment\n");
+	init_seg();
+
+	unsigned int val = dereference_seg_base();
+	if (val != EXPECTED_VALUE) {
+		printf("[FAIL]\tseg[0] == %x; should be %x\n", val, EXPECTED_VALUE);
+		return 1;
+	}
+	printf("[OK]\tThe segment points to the right place.\n");
+
+	pid_t chld = fork();
+	if (chld < 0)
+		err(1, "fork");
+
+	if (chld == 0) {
+		prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0, 0);
+
+		if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0)
+			err(1, "PTRACE_TRACEME");
+
+		pid_t pid = getpid(), tid = syscall(SYS_gettid);
+
+		printf("\tTracee will take a nap until signaled\n");
+		syscall(SYS_tgkill, pid, tid, SIGSTOP);
+
+		printf("\tTracee was resumed.  Will re-check segment.\n");
+
+		val = dereference_seg_base();
+		if (val != EXPECTED_VALUE) {
+			printf("[FAIL]\tseg[0] == %x; should be %x\n", val, EXPECTED_VALUE);
+			exit(1);
+		}
+
+		printf("[OK]\tThe segment points to the right place.\n");
+		exit(0);
+	}
+
+	int status;
+
+	/* Wait for SIGSTOP. */
+	if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status))
+		err(1, "waitpid");
+
+	struct user_regs_struct regs;
+
+	if (ptrace(PTRACE_GETREGS, chld, NULL, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+#ifdef __x86_64__
+	printf("\tChild GS=0x%lx, GSBASE=0x%lx\n", (unsigned long)regs.gs, (unsigned long)regs.gs_base);
+#else
+	printf("\tChild FS=0x%lx\n", (unsigned long)regs.xfs);
+#endif
+
+	struct user_regs_struct regs2 = regs;
+#ifdef __x86_64__
+	regs2.rip = (unsigned long)tracee_zap_segment;
+	regs2.rsp -= 128;	/* Don't clobber the redzone. */
+#else
+	regs2.eip = (unsigned long)tracee_zap_segment;
+#endif
+
+	printf("\tTracer: redirecting tracee to tracee_zap_segment()\n");
+	if (ptrace(PTRACE_SETREGS, chld, NULL, &regs2) != 0)
+		err(1, "PTRACE_GETREGS");
+	if (ptrace(PTRACE_CONT, chld, NULL, NULL) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	/* Wait for SIGSTOP. */
+	if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status))
+		err(1, "waitpid");
+
+	printf("\tTracer: restoring tracee state\n");
+	if (ptrace(PTRACE_SETREGS, chld, NULL, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+	if (ptrace(PTRACE_DETACH, chld, NULL, NULL) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	/* Wait for SIGSTOP. */
+	if (waitpid(chld, &status, 0) != chld)
+		err(1, "waitpid");
+
+	if (WIFSIGNALED(status)) {
+		printf("[FAIL]\tTracee crashed\n");
+		return 1;
+	}
+
+	if (!WIFEXITED(status)) {
+		printf("[FAIL]\tTracee stopped for an unexpected reason: %d\n", status);
+		return 1;
+	}
+
+	int exitcode = WEXITSTATUS(status);
+	if (exitcode != 0) {
+		printf("[FAIL]\tTracee reported failure\n");
+		return 1;
+	}
+
+	printf("[OK]\tAll is well.\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c
index 5b7abebbcbb9..bff474b5efc6 100644
--- a/tools/testing/selftests/x86/syscall_arg_fault.c
+++ b/tools/testing/selftests/x86/syscall_arg_fault.c
@@ -53,6 +53,7 @@ static void sigsegv_or_sigbus(int sig, siginfo_t *info, void *ctx_void)
 	if (ax != -EFAULT && ax != -ENOSYS) {
 		printf("[FAIL]\tAX had the wrong value: 0x%lx\n",
 		       (unsigned long)ax);
+		printf("\tIP = 0x%lx\n", (unsigned long)ctx->uc_mcontext.gregs[REG_IP]);
 		n_errs++;
 	} else {
 		printf("[OK]\tSeems okay\n");
@@ -207,5 +208,30 @@ int main()
 	}
 	set_eflags(get_eflags() & ~X86_EFLAGS_TF);
 
+#ifdef __x86_64__
+	printf("[RUN]\tSYSENTER with TF, invalid state, and GSBASE < 0\n");
+
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		sigtrap_consecutive_syscalls = 0;
+
+		asm volatile ("wrgsbase %%rax\n\t"
+			      :: "a" (0xffffffffffff0000UL));
+
+		set_eflags(get_eflags() | X86_EFLAGS_TF);
+		asm volatile (
+			"movl $-1, %%eax\n\t"
+			"movl $-1, %%ebx\n\t"
+			"movl $-1, %%ecx\n\t"
+			"movl $-1, %%edx\n\t"
+			"movl $-1, %%esi\n\t"
+			"movl $-1, %%edi\n\t"
+			"movl $-1, %%ebp\n\t"
+			"movl $-1, %%esp\n\t"
+			"sysenter"
+			: : : "memory", "flags");
+	}
+	set_eflags(get_eflags() & ~X86_EFLAGS_TF);
+#endif
+
 	return 0;
 }