Adding upstream version 6.8.9.upstream/6.8.9

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

151 files changed, 8290 insertions, 1062 deletions

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 9c27b67bc7..fd15017ed3 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -18,7 +18,7 @@ else
 GENDIR := $(abspath ../../../../include/generated)
 endif
 GENHDR := $(GENDIR)/autoconf.h
-HOSTPKG_CONFIG := pkg-config
+PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
 
 ifneq ($(wildcard $(GENHDR)),)
   GENFLAGS := -DHAVE_GENHDR
@@ -29,13 +29,17 @@ SAN_CFLAGS	?=
 SAN_LDFLAGS	?= $(SAN_CFLAGS)
 RELEASE		?=
 OPT_FLAGS	?= $(if $(RELEASE),-O2,-O0)
+
+LIBELF_CFLAGS	:= $(shell $(PKG_CONFIG) libelf --cflags 2>/dev/null)
+LIBELF_LIBS	:= $(shell $(PKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
+
 CFLAGS += -g $(OPT_FLAGS) -rdynamic					\
 	  -Wall -Werror 						\
-	  $(GENFLAGS) $(SAN_CFLAGS)					\
+	  $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS)			\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
 	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)
 LDFLAGS += $(SAN_LDFLAGS)
-LDLIBS += -lelf -lz -lrt -lpthread
+LDLIBS += $(LIBELF_LIBS) -lz -lrt -lpthread
 
 ifneq ($(LLVM),)
 # Silence some warnings when compiled with clang
@@ -219,9 +223,9 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r
 
 $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c
 	$(call msg,SIGN-FILE,,$@)
-	$(Q)$(CC) $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) \
+	$(Q)$(CC) $(shell $(PKG_CONFIG) --cflags libcrypto 2> /dev/null) \
 		  $< -o $@ \
-		  $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto)
+		  $(shell $(PKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto)
 
 $(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch])
 	$(call msg,MOD,,$@)
@@ -379,6 +383,7 @@ CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN)	\
 	     -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR)			\
 	     -I$(abspath $(OUTPUT)/../usr/include)
+# TODO: enable me -Wsign-compare
 
 CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
 	       -Wno-compare-distinct-pointer-types
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index cb9b95702a..9af79c7a9b 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -77,7 +77,7 @@ In case of linker errors when running selftests, try using static linking:
 
 .. code-block:: console
 
-  $ LDLIBS=-static vmtest.sh
+  $ LDLIBS=-static PKG_CONFIG='pkg-config --static' vmtest.sh
 
 .. note:: Some distros may not support static linking.
 
diff --git a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
index 9146d3f414..926ee82214 100644
--- a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
+++ b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
@@ -335,6 +335,7 @@ static void htab_mem_report_final(struct bench_res res[], int res_cnt)
 	       " peak memory usage %7.2lfMiB\n",
 	       loop_mean, loop_stddev, mem_mean, mem_stddev, peak_mem / 1048576.0);
 
+	close(ctx.fd);
 	cleanup_cgroup_environment();
 }
 
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 1386baf9ae..f44875f8b3 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -254,173 +254,97 @@ extern void bpf_throw(u64 cookie) __ksym;
 		}									\
 	 })
 
-/* Description
- *	Assert that a conditional expression is true.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert(cond) if (!(cond)) bpf_throw(0);
-
-/* Description
- *	Assert that a conditional expression is true.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_with(cond, value) if (!(cond)) bpf_throw(value);
-
-/* Description
- *	Assert that LHS is equal to RHS. This statement updates the known value
- *	of LHS during verification. Note that RHS must be a constant value, and
- *	must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_eq(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, ==, RHS, 0, true);			\
-	})
-
-/* Description
- *	Assert that LHS is equal to RHS. This statement updates the known value
- *	of LHS during verification. Note that RHS must be a constant value, and
- *	must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_eq_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, ==, RHS, value, true);		\
-	})
-
-/* Description
- *	Assert that LHS is less than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_lt(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <, RHS, 0, false);			\
-	})
-
-/* Description
- *	Assert that LHS is less than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_lt_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <, RHS, value, false);		\
-	})
+#define __cmp_cannot_be_signed(x) \
+	__builtin_strcmp(#x, "==") == 0 || __builtin_strcmp(#x, "!=") == 0 || \
+	__builtin_strcmp(#x, "&") == 0
 
-/* Description
- *	Assert that LHS is greater than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_gt(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >, RHS, 0, false);			\
-	})
+#define __is_signed_type(type) (((type)(-1)) < (type)1)
 
-/* Description
- *	Assert that LHS is greater than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
+#define __bpf_cmp(LHS, OP, SIGN, PRED, RHS, DEFAULT)						\
+	({											\
+		__label__ l_true;								\
+		bool ret = DEFAULT;								\
+		asm volatile goto("if %[lhs] " SIGN #OP " %[rhs] goto %l[l_true]"		\
+				  :: [lhs] "r"((short)LHS), [rhs] PRED (RHS) :: l_true);	\
+		ret = !DEFAULT;									\
+l_true:												\
+		ret;										\
+       })
+
+/* C type conversions coupled with comparison operator are tricky.
+ * Make sure BPF program is compiled with -Wsign-compare then
+ * __lhs OP __rhs below will catch the mistake.
+ * Be aware that we check only __lhs to figure out the sign of compare.
  */
-#define bpf_assert_gt_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >, RHS, value, false);		\
-	})
+#define _bpf_cmp(LHS, OP, RHS, NOFLIP)								\
+	({											\
+		typeof(LHS) __lhs = (LHS);							\
+		typeof(RHS) __rhs = (RHS);							\
+		bool ret;									\
+		_Static_assert(sizeof(&(LHS)), "1st argument must be an lvalue expression");	\
+		(void)(__lhs OP __rhs);								\
+		if (__cmp_cannot_be_signed(OP) || !__is_signed_type(typeof(__lhs))) {		\
+			if (sizeof(__rhs) == 8)							\
+				ret = __bpf_cmp(__lhs, OP, "", "r", __rhs, NOFLIP);		\
+			else									\
+				ret = __bpf_cmp(__lhs, OP, "", "i", __rhs, NOFLIP);		\
+		} else {									\
+			if (sizeof(__rhs) == 8)							\
+				ret = __bpf_cmp(__lhs, OP, "s", "r", __rhs, NOFLIP);		\
+			else									\
+				ret = __bpf_cmp(__lhs, OP, "s", "i", __rhs, NOFLIP);		\
+		}										\
+		ret;										\
+       })
+
+#ifndef bpf_cmp_unlikely
+#define bpf_cmp_unlikely(LHS, OP, RHS) _bpf_cmp(LHS, OP, RHS, true)
+#endif
 
-/* Description
- *	Assert that LHS is less than or equal to RHS. This statement updates the
- *	known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_le(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <=, RHS, 0, false);		\
-	})
+#ifndef bpf_cmp_likely
+#define bpf_cmp_likely(LHS, OP, RHS)								\
+	({											\
+		bool ret;									\
+		if (__builtin_strcmp(#OP, "==") == 0)						\
+			ret = _bpf_cmp(LHS, !=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "!=") == 0)					\
+			ret = _bpf_cmp(LHS, ==, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "<=") == 0)					\
+			ret = _bpf_cmp(LHS, >, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "<") == 0)					\
+			ret = _bpf_cmp(LHS, >=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, ">") == 0)					\
+			ret = _bpf_cmp(LHS, <=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, ">=") == 0)					\
+			ret = _bpf_cmp(LHS, <, RHS, false);					\
+		else										\
+			(void) "bug";								\
+		ret;										\
+       })
+#endif
 
-/* Description
- *	Assert that LHS is less than or equal to RHS. This statement updates the
- *	known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_le_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <=, RHS, value, false);		\
-	})
+#ifndef bpf_nop_mov
+#define bpf_nop_mov(var) \
+	asm volatile("%[reg]=%[reg]"::[reg]"r"((short)var))
+#endif
 
 /* Description
- *	Assert that LHS is greater than or equal to RHS. This statement updates
- *	the known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
+ *	Assert that a conditional expression is true.
  * Returns
  *	Void.
  * Throws
  *	An exception with the value zero when the assertion fails.
  */
-#define bpf_assert_ge(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >=, RHS, 0, false);		\
-	})
+#define bpf_assert(cond) if (!(cond)) bpf_throw(0);
 
 /* Description
- *	Assert that LHS is greater than or equal to RHS. This statement updates
- *	the known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
+ *	Assert that a conditional expression is true.
  * Returns
  *	Void.
  * Throws
  *	An exception with the specified value when the assertion fails.
  */
-#define bpf_assert_ge_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >=, RHS, value, false);		\
-	})
+#define bpf_assert_with(cond, value) if (!(cond)) bpf_throw(value);
 
 /* Description
  *	Assert that LHS is in the range [BEG, END] (inclusive of both). This
diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index 5ca68ff0b5..b4e78c1eb3 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -55,4 +55,14 @@ void *bpf_cast_to_kern_ctx(void *) __ksym;
 
 void *bpf_rdonly_cast(void *obj, __u32 btf_id) __ksym;
 
+extern int bpf_get_file_xattr(struct file *file, const char *name,
+			      struct bpf_dynptr *value_ptr) __ksym;
+extern int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *digest_ptr) __ksym;
+
+extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
+extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
+extern void bpf_key_put(struct bpf_key *key) __ksym;
+extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
+				      struct bpf_dynptr *sig_ptr,
+				      struct bpf_key *trusted_keyring) __ksym;
 #endif
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 10b5f42e65..19be9c63d5 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -45,9 +45,12 @@
 #define format_parent_cgroup_path(buf, path) \
 	format_cgroup_path_pid(buf, path, getppid())
 
-#define format_classid_path(buf)				\
-	snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH,	\
-		 CGROUP_WORK_DIR)
+#define format_classid_path_pid(buf, pid)				\
+	snprintf(buf, sizeof(buf), "%s%s%d", NETCLS_MOUNT_PATH,	\
+		 CGROUP_WORK_DIR, pid)
+
+#define format_classid_path(buf)	\
+	format_classid_path_pid(buf, getpid())
 
 static __thread bool cgroup_workdir_mounted;
 
@@ -419,26 +422,23 @@ int create_and_get_cgroup(const char *relative_path)
 }
 
 /**
- * get_cgroup_id() - Get cgroup id for a particular cgroup path
- * @relative_path: The cgroup path, relative to the workdir, to join
+ * get_cgroup_id_from_path - Get cgroup id for a particular cgroup path
+ * @cgroup_workdir: The absolute cgroup path
  *
  * On success, it returns the cgroup id. On failure it returns 0,
  * which is an invalid cgroup id.
  * If there is a failure, it prints the error to stderr.
  */
-unsigned long long get_cgroup_id(const char *relative_path)
+unsigned long long get_cgroup_id_from_path(const char *cgroup_workdir)
 {
 	int dirfd, err, flags, mount_id, fhsize;
 	union {
 		unsigned long long cgid;
 		unsigned char raw_bytes[8];
 	} id;
-	char cgroup_workdir[PATH_MAX + 1];
 	struct file_handle *fhp, *fhp2;
 	unsigned long long ret = 0;
 
-	format_cgroup_path(cgroup_workdir, relative_path);
-
 	dirfd = AT_FDCWD;
 	flags = 0;
 	fhsize = sizeof(*fhp);
@@ -474,6 +474,14 @@ free_mem:
 	return ret;
 }
 
+unsigned long long get_cgroup_id(const char *relative_path)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_workdir, relative_path);
+	return get_cgroup_id_from_path(cgroup_workdir);
+}
+
 int cgroup_setup_and_join(const char *path) {
 	int cg_fd;
 
@@ -551,15 +559,16 @@ int setup_classid_environment(void)
 
 /**
  * set_classid() - Set a cgroupv1 net_cls classid
- * @id: the numeric classid
  *
- * Writes the passed classid into the cgroup work dir's net_cls.classid
+ * Writes the classid into the cgroup work dir's net_cls.classid
  * file in order to later on trigger socket tagging.
  *
+ * We leverage the current pid as the classid, ensuring unique identification.
+ *
  * On success, it returns 0, otherwise on failure it returns 1. If there
  * is a failure, it prints the error to stderr.
  */
-int set_classid(unsigned int id)
+int set_classid(void)
 {
 	char cgroup_workdir[PATH_MAX - 42];
 	char cgroup_classid_path[PATH_MAX + 1];
@@ -575,7 +584,7 @@ int set_classid(unsigned int id)
 		return 1;
 	}
 
-	if (dprintf(fd, "%u\n", id) < 0) {
+	if (dprintf(fd, "%u\n", getpid()) < 0) {
 		log_err("Setting cgroup classid");
 		rc = 1;
 	}
@@ -617,3 +626,82 @@ void cleanup_classid_environment(void)
 	join_cgroup_from_top(NETCLS_MOUNT_PATH);
 	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
 }
+
+/**
+ * get_classid_cgroup_id - Get the cgroup id of a net_cls cgroup
+ */
+unsigned long long get_classid_cgroup_id(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+	return get_cgroup_id_from_path(cgroup_workdir);
+}
+
+/**
+ * get_cgroup1_hierarchy_id - Retrieves the ID of a cgroup1 hierarchy from the cgroup1 subsys name.
+ * @subsys_name: The cgroup1 subsys name, which can be retrieved from /proc/self/cgroup. It can be
+ * a named cgroup like "name=systemd", a controller name like "net_cls", or multi-contollers like
+ * "net_cls,net_prio".
+ */
+int get_cgroup1_hierarchy_id(const char *subsys_name)
+{
+	char *c, *c2, *c3, *c4;
+	bool found = false;
+	char line[1024];
+	FILE *file;
+	int i, id;
+
+	if (!subsys_name)
+		return -1;
+
+	file = fopen("/proc/self/cgroup", "r");
+	if (!file) {
+		log_err("fopen /proc/self/cgroup");
+		return -1;
+	}
+
+	while (fgets(line, 1024, file)) {
+		i = 0;
+		for (c = strtok_r(line, ":", &c2); c && i < 2; c = strtok_r(NULL, ":", &c2)) {
+			if (i == 0) {
+				id = strtol(c, NULL, 10);
+			} else if (i == 1) {
+				if (!strcmp(c, subsys_name)) {
+					found = true;
+					break;
+				}
+
+				/* Multiple subsystems may share one single mount point */
+				for (c3 = strtok_r(c, ",", &c4); c3;
+				     c3 = strtok_r(NULL, ",", &c4)) {
+					if (!strcmp(c, subsys_name)) {
+						found = true;
+						break;
+					}
+				}
+			}
+			i++;
+		}
+		if (found)
+			break;
+	}
+	fclose(file);
+	return found ? id : -1;
+}
+
+/**
+ * open_classid() - Open a cgroupv1 net_cls classid
+ *
+ * This function expects the cgroup work dir to be already created, as we
+ * open it here.
+ *
+ * On success, it returns the file descriptor. On failure it returns -1.
+ */
+int open_classid(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+	return open(cgroup_workdir, O_RDONLY);
+}
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index 5c2cb9c8b5..502845160d 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -20,6 +20,7 @@ int get_root_cgroup(void);
 int create_and_get_cgroup(const char *relative_path);
 void remove_cgroup(const char *relative_path);
 unsigned long long get_cgroup_id(const char *relative_path);
+int get_cgroup1_hierarchy_id(const char *subsys_name);
 
 int join_cgroup(const char *relative_path);
 int join_root_cgroup(void);
@@ -29,8 +30,10 @@ int setup_cgroup_environment(void);
 void cleanup_cgroup_environment(void);
 
 /* cgroupv1 related */
-int set_classid(unsigned int id);
+int set_classid(void);
 int join_classid(void);
+unsigned long long get_classid_cgroup_id(void);
+int open_classid(void);
 
 int setup_classid_environment(void);
 void cleanup_classid_environment(void);
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 3ec5927ec3..c125c441ab 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -23,6 +23,7 @@ CONFIG_FPROBE=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_FUNCTION_ERROR_INJECTION=y
 CONFIG_FUNCTION_TRACER=y
+CONFIG_FS_VERITY=y
 CONFIG_GENEVE=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
@@ -82,7 +83,7 @@ CONFIG_SECURITY=y
 CONFIG_SECURITYFS=y
 CONFIG_TEST_BPF=m
 CONFIG_USERFAULTFD=y
+CONFIG_VSOCKETS=y
 CONFIG_VXLAN=y
 CONFIG_XDP_SOCKETS=y
 CONFIG_XFRM_INTERFACE=y
-CONFIG_VSOCKETS=y
diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64
index 2538214948..3720b76115 100644
--- a/tools/testing/selftests/bpf/config.aarch64
+++ b/tools/testing/selftests/bpf/config.aarch64
@@ -1,4 +1,3 @@
-CONFIG_9P_FS=y
 CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y
 CONFIG_ARM_SMMU_V3=y
@@ -12,7 +11,6 @@ CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BONDING=y
-CONFIG_BPFILTER=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_BPF_PRELOAD_UMD=y
@@ -37,6 +35,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
 CONFIG_DEBUG_INFO_BTF=y
 CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_DEBUG_INFO_REDUCED=n
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_NOTIFIERS=y
@@ -46,7 +45,6 @@ CONFIG_DEBUG_SG=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_DEVTMPFS=y
-CONFIG_DRM_VIRTIO_GPU=y
 CONFIG_DRM=y
 CONFIG_DUMMY=y
 CONFIG_EXPERT=y
@@ -67,7 +65,6 @@ CONFIG_HAVE_KRETPROBES=y
 CONFIG_HEADERS_INSTALL=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_HUGETLBFS=y
-CONFIG_HW_RANDOM_VIRTIO=y
 CONFIG_HW_RANDOM=y
 CONFIG_HZ_100=y
 CONFIG_IDLE_PAGE_TRACKING=y
@@ -99,8 +96,6 @@ CONFIG_MEMCG=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_NAMESPACES=y
-CONFIG_NET_9P_VIRTIO=y
-CONFIG_NET_9P=y
 CONFIG_NET_ACT_BPF=y
 CONFIG_NET_ACT_GACT=y
 CONFIG_NETDEVICES=y
@@ -140,7 +135,6 @@ CONFIG_SCHED_TRACER=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SCAN_ASYNC=y
-CONFIG_SCSI_VIRTIO=y
 CONFIG_SCSI=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
@@ -167,16 +161,6 @@ CONFIG_UPROBES=y
 CONFIG_USELIB=y
 CONFIG_USER_NS=y
 CONFIG_VETH=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_VIRTIO_CONSOLE=y
-CONFIG_VIRTIO_FS=y
-CONFIG_VIRTIO_INPUT=y
-CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
-CONFIG_VIRTIO_MMIO=y
-CONFIG_VIRTIO_NET=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_VSOCKETS_COMMON=y
 CONFIG_VLAN_8021Q=y
 CONFIG_VSOCKETS=y
 CONFIG_VSOCKETS_LOOPBACK=y
diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x
index 2ba92167be..706931a8c2 100644
--- a/tools/testing/selftests/bpf/config.s390x
+++ b/tools/testing/selftests/bpf/config.s390x
@@ -1,4 +1,3 @@
-CONFIG_9P_FS=y
 CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y
 CONFIG_AUDIT=y
 CONFIG_BLK_CGROUP=y
@@ -10,7 +9,6 @@ CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-CONFIG_BPFILTER=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_FREEZER=y
@@ -84,8 +82,6 @@ CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_NAMESPACES=y
 CONFIG_NET=y
-CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
 CONFIG_NET_ACT_BPF=y
 CONFIG_NET_ACT_GACT=y
 CONFIG_NET_KEY=y
@@ -114,7 +110,6 @@ CONFIG_SAMPLE_SECCOMP=y
 CONFIG_SAMPLES=y
 CONFIG_SCHED_TRACER=y
 CONFIG_SCSI=y
-CONFIG_SCSI_VIRTIO=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_STACK_TRACER=y
 CONFIG_STATIC_KEYS_SELFTEST=y
@@ -136,11 +131,6 @@ CONFIG_UPROBES=y
 CONFIG_USELIB=y
 CONFIG_USER_NS=y
 CONFIG_VETH=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_VIRTIO_NET=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_VSOCKETS_COMMON=y
 CONFIG_VLAN_8021Q=y
 CONFIG_VSOCKETS=y
 CONFIG_VSOCKETS_LOOPBACK=y
diff --git a/tools/testing/selftests/bpf/config.vm b/tools/testing/selftests/bpf/config.vm
new file mode 100644
index 0000000000..a9746ca787
--- /dev/null
+++ b/tools/testing/selftests/bpf/config.vm
@@ -0,0 +1,12 @@
+CONFIG_9P_FS=y
+CONFIG_9P_FS_POSIX_ACL=y
+CONFIG_9P_FS_SECURITY=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_NET_9P=y
+CONFIG_NET_9P_VIRTIO=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO_NET=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_VSOCKETS_COMMON=y
diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64
index 49a29dbc19..5680befae8 100644
--- a/tools/testing/selftests/bpf/config.x86_64
+++ b/tools/testing/selftests/bpf/config.x86_64
@@ -1,6 +1,3 @@
-CONFIG_9P_FS=y
-CONFIG_9P_FS_POSIX_ACL=y
-CONFIG_9P_FS_SECURITY=y
 CONFIG_AGP=y
 CONFIG_AGP_AMD64=y
 CONFIG_AGP_INTEL=y
@@ -22,7 +19,6 @@ CONFIG_BOOTTIME_TRACING=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-CONFIG_BPFILTER=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_CFS_BANDWIDTH=y
@@ -45,7 +41,6 @@ CONFIG_CPU_IDLE_GOV_LADDER=y
 CONFIG_CPUSETS=y
 CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_BLAKE2B=y
-CONFIG_CRYPTO_DEV_VIRTIO=y
 CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_XXHASH=y
 CONFIG_DCB=y
@@ -144,8 +139,6 @@ CONFIG_MEMORY_FAILURE=y
 CONFIG_MINIX_SUBPARTITION=y
 CONFIG_NAMESPACES=y
 CONFIG_NET=y
-CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
 CONFIG_NET_ACT_BPF=y
 CONFIG_NET_CLS_CGROUP=y
 CONFIG_NET_EMATCH=y
@@ -227,12 +220,6 @@ CONFIG_USER_NS=y
 CONFIG_VALIDATE_FS_PARSER=y
 CONFIG_VETH=y
 CONFIG_VIRT_DRIVERS=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_VIRTIO_CONSOLE=y
-CONFIG_VIRTIO_NET=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_VSOCKETS_COMMON=y
 CONFIG_VLAN_8021Q=y
 CONFIG_VSOCKETS=y
 CONFIG_VSOCKETS_LOOPBACK=y
diff --git a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
index 8bf497a984..2ea3640881 100644
--- a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
+++ b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
@@ -131,10 +131,17 @@ static bool is_lru(__u32 map_type)
 	       map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
 }
 
+static bool is_percpu(__u32 map_type)
+{
+	return map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	       map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
 struct upsert_opts {
 	__u32 map_type;
 	int map_fd;
 	__u32 n;
+	bool retry_for_nomem;
 };
 
 static int create_small_hash(void)
@@ -148,19 +155,38 @@ static int create_small_hash(void)
 	return map_fd;
 }
 
+static bool retry_for_nomem_fn(int err)
+{
+	return err == ENOMEM;
+}
+
 static void *patch_map_thread(void *arg)
 {
+	/* 8KB is enough for 1024 CPUs. And it is shared between N_THREADS. */
+	static __u8 blob[8 << 10];
 	struct upsert_opts *opts = arg;
+	void *val_ptr;
 	int val;
 	int ret;
 	int i;
 
 	for (i = 0; i < opts->n; i++) {
-		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
+		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
 			val = create_small_hash();
-		else
+			val_ptr = &val;
+		} else if (is_percpu(opts->map_type)) {
+			val_ptr = blob;
+		} else {
 			val = rand();
-		ret = bpf_map_update_elem(opts->map_fd, &i, &val, 0);
+			val_ptr = &val;
+		}
+
+		/* 2 seconds may be enough ? */
+		if (opts->retry_for_nomem)
+			ret = map_update_retriable(opts->map_fd, &i, val_ptr, 0,
+						   40, retry_for_nomem_fn);
+		else
+			ret = bpf_map_update_elem(opts->map_fd, &i, val_ptr, 0);
 		CHECK(ret < 0, "bpf_map_update_elem", "key=%d error: %s\n", i, strerror(errno));
 
 		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
@@ -281,6 +307,13 @@ static void __test(int map_fd)
 	else
 		opts.n /= 2;
 
+	/* per-cpu bpf memory allocator may not be able to allocate per-cpu
+	 * pointer successfully and it can not refill free llist timely, and
+	 * bpf_map_update_elem() will return -ENOMEM. so just retry to mitigate
+	 * the problem temporarily.
+	 */
+	opts.retry_for_nomem = is_percpu(opts.map_type) && (info.map_flags & BPF_F_NO_PREALLOC);
+
 	/*
 	 * Upsert keys [0, n) under some competition: with random values from
 	 * N_THREADS threads. Check values, then delete all elements and check
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 34f1200a78..94b9be24e3 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -71,4 +71,47 @@ struct nstoken;
  */
 struct nstoken *open_netns(const char *name);
 void close_netns(struct nstoken *token);
+
+static __u16 csum_fold(__u32 csum)
+{
+	csum = (csum & 0xffff) + (csum >> 16);
+	csum = (csum & 0xffff) + (csum >> 16);
+
+	return (__u16)~csum;
+}
+
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+					__u32 len, __u8 proto,
+					__wsum csum)
+{
+	__u64 s = csum;
+
+	s += (__u32)saddr;
+	s += (__u32)daddr;
+	s += htons(proto + len);
+	s = (s & 0xffffffff) + (s >> 32);
+	s = (s & 0xffffffff) + (s >> 32);
+
+	return csum_fold((__u32)s);
+}
+
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+					__u32 len, __u8 proto,
+					__wsum csum)
+{
+	__u64 s = csum;
+	int i;
+
+	for (i = 0; i < 4; i++)
+		s += (__u32)saddr->s6_addr32[i];
+	for (i = 0; i < 4; i++)
+		s += (__u32)daddr->s6_addr32[i];
+	s += htons(proto + len);
+	s = (s & 0xffffffff) + (s >> 32);
+	s = (s & 0xffffffff) + (s >> 32);
+
+	return csum_fold((__u32)s);
+}
+
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 465c1c3a3d..4ebd0da898 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -40,7 +40,7 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R1", "ctx()"},
 			{0, "R10", "fp0"},
 			{0, "R3_w", "2"},
 			{1, "R3_w", "4"},
@@ -68,7 +68,7 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R1", "ctx()"},
 			{0, "R10", "fp0"},
 			{0, "R3_w", "1"},
 			{1, "R3_w", "2"},
@@ -97,7 +97,7 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R1", "ctx()"},
 			{0, "R10", "fp0"},
 			{0, "R3_w", "4"},
 			{1, "R3_w", "8"},
@@ -119,7 +119,7 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R1", "ctx()"},
 			{0, "R10", "fp0"},
 			{0, "R3_w", "7"},
 			{1, "R3_w", "7"},
@@ -162,13 +162,13 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{6, "R0_w", "pkt(off=8,r=8,imm=0)"},
+			{6, "R0_w", "pkt(off=8,r=8)"},
 			{6, "R3_w", "var_off=(0x0; 0xff)"},
 			{7, "R3_w", "var_off=(0x0; 0x1fe)"},
 			{8, "R3_w", "var_off=(0x0; 0x3fc)"},
 			{9, "R3_w", "var_off=(0x0; 0x7f8)"},
 			{10, "R3_w", "var_off=(0x0; 0xff0)"},
-			{12, "R3_w", "pkt_end(off=0,imm=0)"},
+			{12, "R3_w", "pkt_end()"},
 			{17, "R4_w", "var_off=(0x0; 0xff)"},
 			{18, "R4_w", "var_off=(0x0; 0x1fe0)"},
 			{19, "R4_w", "var_off=(0x0; 0xff0)"},
@@ -235,11 +235,11 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{2, "R5_w", "pkt(off=0,r=0,imm=0)"},
-			{4, "R5_w", "pkt(off=14,r=0,imm=0)"},
-			{5, "R4_w", "pkt(off=14,r=0,imm=0)"},
-			{9, "R2", "pkt(off=0,r=18,imm=0)"},
-			{10, "R5", "pkt(off=14,r=18,imm=0)"},
+			{2, "R5_w", "pkt(r=0)"},
+			{4, "R5_w", "pkt(off=14,r=0)"},
+			{5, "R4_w", "pkt(off=14,r=0)"},
+			{9, "R2", "pkt(r=18)"},
+			{10, "R5", "pkt(off=14,r=18)"},
 			{10, "R4_w", "var_off=(0x0; 0xff)"},
 			{13, "R4_w", "var_off=(0x0; 0xffff)"},
 			{14, "R4_w", "var_off=(0x0; 0xffff)"},
@@ -299,7 +299,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{6, "R2_w", "pkt(r=8)"},
 			{7, "R6_w", "var_off=(0x0; 0x3fc)"},
 			/* Offset is added to packet pointer R5, resulting in
 			 * known fixed offset, and variable offset from R6.
@@ -337,7 +337,7 @@ static struct bpf_align_test tests[] = {
 			/* Constant offset is added to R5 packet pointer,
 			 * resulting in reg->off value of 14.
 			 */
-			{26, "R5_w", "pkt(off=14,r=8,"},
+			{26, "R5_w", "pkt(off=14,r=8)"},
 			/* Variable offset is added to R5, resulting in a
 			 * variable offset of (4n). See comment for insn #18
 			 * for R4 = R5 trick.
@@ -397,7 +397,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{6, "R2_w", "pkt(r=8)"},
 			{7, "R6_w", "var_off=(0x0; 0x3fc)"},
 			/* Adding 14 makes R6 be (4n+2) */
 			{8, "R6_w", "var_off=(0x2; 0x7fc)"},
@@ -459,7 +459,7 @@ static struct bpf_align_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = REJECT,
 		.matches = {
-			{3, "R5_w", "pkt_end(off=0,imm=0)"},
+			{3, "R5_w", "pkt_end()"},
 			/* (ptr - ptr) << 2 == unknown, (4n) */
 			{5, "R5_w", "var_off=(0x0; 0xfffffffffffffffc)"},
 			/* (4n) + 14 == (4n+2).  We blow our bounds, because
@@ -513,7 +513,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{6, "R2_w", "pkt(r=8)"},
 			{8, "R6_w", "var_off=(0x0; 0x3fc)"},
 			/* Adding 14 makes R6 be (4n+2) */
 			{9, "R6_w", "var_off=(0x2; 0x7fc)"},
@@ -566,7 +566,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{6, "R2_w", "pkt(r=8)"},
 			{9, "R6_w", "var_off=(0x0; 0x3c)"},
 			/* Adding 14 makes R6 be (4n+2) */
 			{10, "R6_w", "var_off=(0x2; 0x7c)"},
@@ -659,14 +659,14 @@ static int do_test_single(struct bpf_align_test *test)
 			/* Check the next line as well in case the previous line
 			 * did not have a corresponding bpf insn. Example:
 			 * func#0 @0
-			 * 0: R1=ctx(off=0,imm=0) R10=fp0
+			 * 0: R1=ctx() R10=fp0
 			 * 0: (b7) r3 = 2                 ; R3_w=2
 			 *
 			 * Sometimes it's actually two lines below, e.g. when
 			 * searching for "6: R3_w=scalar(umax=255,var_off=(0x0; 0xff))":
-			 *   from 4 to 6: R0_w=pkt(off=8,r=8,imm=0) R1=ctx(off=0,imm=0) R2_w=pkt(off=0,r=8,imm=0) R3_w=pkt_end(off=0,imm=0) R10=fp0
-			 *   6: R0_w=pkt(off=8,r=8,imm=0) R1=ctx(off=0,imm=0) R2_w=pkt(off=0,r=8,imm=0) R3_w=pkt_end(off=0,imm=0) R10=fp0
-			 *   6: (71) r3 = *(u8 *)(r2 +0)           ; R2_w=pkt(off=0,r=8,imm=0) R3_w=scalar(umax=255,var_off=(0x0; 0xff))
+			 *   from 4 to 6: R0_w=pkt(off=8,r=8) R1=ctx() R2_w=pkt(r=8) R3_w=pkt_end() R10=fp0
+			 *   6: R0_w=pkt(off=8,r=8) R1=ctx() R2_w=pkt(r=8) R3_w=pkt_end() R10=fp0
+			 *   6: (71) r3 = *(u8 *)(r2 +0)           ; R2_w=pkt(r=8) R3_w=scalar(umax=255,var_off=(0x0; 0xff))
 			 */
 			while (!(p = strstr(line_ptr, m.reg)) || !strstr(p, m.match)) {
 				cur_line = -1;
diff --git a/tools/testing/selftests/bpf/prog_tests/bind_perm.c b/tools/testing/selftests/bpf/prog_tests/bind_perm.c
index a1766a298b..f7cd129cb8 100644
--- a/tools/testing/selftests/bpf/prog_tests/bind_perm.c
+++ b/tools/testing/selftests/bpf/prog_tests/bind_perm.c
@@ -9,8 +9,6 @@
 #include "cap_helpers.h"
 #include "bind_perm.skel.h"
 
-static int duration;
-
 static int create_netns(void)
 {
 	if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns"))
@@ -27,7 +25,7 @@ void try_bind(int family, int port, int expected_errno)
 	int fd = -1;
 
 	fd = socket(family, SOCK_STREAM, 0);
-	if (CHECK(fd < 0, "fd", "errno %d", errno))
+	if (!ASSERT_GE(fd, 0, "socket"))
 		goto close_socket;
 
 	if (family == AF_INET) {
@@ -60,7 +58,7 @@ void test_bind_perm(void)
 		return;
 
 	cgroup_fd = test__join_cgroup("/bind_perm");
-	if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno))
+	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
 	skel = bind_perm__open_and_load();
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 2cacc8fa96..618af9dfae 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -34,8 +34,6 @@
 #include "bpf_iter_ksym.skel.h"
 #include "bpf_iter_sockmap.skel.h"
 
-static int duration;
-
 static void test_btf_id_or_null(void)
 {
 	struct bpf_iter_test_kern3 *skel;
@@ -64,7 +62,7 @@ static void do_dummy_read_opts(struct bpf_program *prog, struct bpf_iter_attach_
 	/* not check contents, but ensure read() ends without error */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	CHECK(len < 0, "read", "read failed: %s\n", strerror(errno));
+	ASSERT_GE(len, 0, "read");
 
 	close(iter_fd);
 
@@ -415,7 +413,7 @@ static int do_btf_read(struct bpf_iter_task_btf *skel)
 		goto free_link;
 	}
 
-	if (CHECK(err < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(err, 0, "read"))
 		goto free_link;
 
 	ASSERT_HAS_SUBSTR(taskbuf, "(struct task_struct)",
@@ -528,11 +526,11 @@ static int do_read_with_fd(int iter_fd, const char *expected,
 	start = 0;
 	while ((len = read(iter_fd, buf + start, read_buf_len)) > 0) {
 		start += len;
-		if (CHECK(start >= 16, "read", "read len %d\n", len))
+		if (!ASSERT_LT(start, 16, "read"))
 			return -1;
 		read_buf_len = read_one_char ? 1 : 16 - start;
 	}
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		return -1;
 
 	if (!ASSERT_STREQ(buf, expected, "read"))
@@ -573,8 +571,7 @@ static int do_read(const char *path, const char *expected)
 	int err, iter_fd;
 
 	iter_fd = open(path, O_RDONLY);
-	if (CHECK(iter_fd < 0, "open", "open %s failed: %s\n",
-		  path, strerror(errno)))
+	if (!ASSERT_GE(iter_fd, 0, "open"))
 		return -1;
 
 	err = do_read_with_fd(iter_fd, expected, false);
@@ -602,7 +599,7 @@ static void test_file_iter(void)
 	unlink(path);
 
 	err = bpf_link__pin(link, path);
-	if (CHECK(err, "pin_iter", "pin_iter to %s failed: %d\n", path, err))
+	if (!ASSERT_OK(err, "pin_iter"))
 		goto free_link;
 
 	err = do_read(path, "abcd");
@@ -653,12 +650,10 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 	 * overflow and needs restart.
 	 */
 	map1_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL);
-	if (CHECK(map1_fd < 0, "bpf_map_create",
-		  "map_creation failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(map1_fd, 0, "bpf_map_create"))
 		goto out;
 	map2_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL);
-	if (CHECK(map2_fd < 0, "bpf_map_create",
-		  "map_creation failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(map2_fd, 0, "bpf_map_create"))
 		goto free_map1;
 
 	/* bpf_seq_printf kernel buffer is 8 pages, so one map
@@ -687,14 +682,12 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 	/* setup filtering map_id in bpf program */
 	map_info_len = sizeof(map_info);
 	err = bpf_map_get_info_by_fd(map1_fd, &map_info, &map_info_len);
-	if (CHECK(err, "get_map_info", "get map info failed: %s\n",
-		  strerror(errno)))
+	if (!ASSERT_OK(err, "get_map_info"))
 		goto free_map2;
 	skel->bss->map1_id = map_info.id;
 
 	err = bpf_map_get_info_by_fd(map2_fd, &map_info, &map_info_len);
-	if (CHECK(err, "get_map_info", "get map info failed: %s\n",
-		  strerror(errno)))
+	if (!ASSERT_OK(err, "get_map_info"))
 		goto free_map2;
 	skel->bss->map2_id = map_info.id;
 
@@ -707,7 +700,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 		goto free_link;
 
 	buf = malloc(expected_read_len);
-	if (!buf)
+	if (!ASSERT_OK_PTR(buf, "malloc"))
 		goto close_iter;
 
 	/* do read */
@@ -716,16 +709,14 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 		while ((len = read(iter_fd, buf, expected_read_len)) > 0)
 			total_read_len += len;
 
-		CHECK(len != -1 || errno != E2BIG, "read",
-		      "expected ret -1, errno E2BIG, but get ret %d, error %s\n",
-			  len, strerror(errno));
+		ASSERT_EQ(len, -1, "read");
+		ASSERT_EQ(errno, E2BIG, "read");
 		goto free_buf;
 	} else if (!ret1) {
 		while ((len = read(iter_fd, buf, expected_read_len)) > 0)
 			total_read_len += len;
 
-		if (CHECK(len < 0, "read", "read failed: %s\n",
-			  strerror(errno)))
+		if (!ASSERT_GE(len, 0, "read"))
 			goto free_buf;
 	} else {
 		do {
@@ -734,8 +725,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 				total_read_len += len;
 		} while (len > 0 || len == -EAGAIN);
 
-		if (CHECK(len < 0, "read", "read failed: %s\n",
-			  strerror(errno)))
+		if (!ASSERT_GE(len, 0, "read"))
 			goto free_buf;
 	}
 
@@ -838,7 +828,7 @@ static void test_bpf_hash_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
@@ -880,6 +870,8 @@ static void test_bpf_percpu_hash_map(void)
 
 	skel->rodata->num_cpus = bpf_num_possible_cpus();
 	val = malloc(8 * bpf_num_possible_cpus());
+	if (!ASSERT_OK_PTR(val, "malloc"))
+		goto out;
 
 	err = bpf_iter_bpf_percpu_hash_map__load(skel);
 	if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_percpu_hash_map__load"))
@@ -919,7 +911,7 @@ static void test_bpf_percpu_hash_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
@@ -985,17 +977,14 @@ static void test_bpf_array_map(void)
 	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)))
+	if (!ASSERT_GE(len, 0, "read"))
 		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))
+	if (!ASSERT_EQ(res_first_key, 0, "bpf_seq_write") ||
+			!ASSERT_EQ(res_first_val, first_val, "bpf_seq_write"))
 		goto close_iter;
 
 	if (!ASSERT_EQ(skel->bss->key_sum, expected_key, "key_sum"))
@@ -1059,6 +1048,8 @@ static void test_bpf_percpu_array_map(void)
 
 	skel->rodata->num_cpus = bpf_num_possible_cpus();
 	val = malloc(8 * bpf_num_possible_cpus());
+	if (!ASSERT_OK_PTR(val, "malloc"))
+		goto out;
 
 	err = bpf_iter_bpf_percpu_array_map__load(skel);
 	if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_percpu_array_map__load"))
@@ -1094,7 +1085,7 @@ static void test_bpf_percpu_array_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
@@ -1133,6 +1124,7 @@ static void test_bpf_sk_storage_delete(void)
 	sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
 	if (!ASSERT_GE(sock_fd, 0, "socket"))
 		goto out;
+
 	err = bpf_map_update_elem(map_fd, &sock_fd, &val, BPF_NOEXIST);
 	if (!ASSERT_OK(err, "map_update"))
 		goto out;
@@ -1153,14 +1145,19 @@ static void test_bpf_sk_storage_delete(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
 	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
-	if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
-		  "map value wasn't deleted (err=%d, errno=%d)\n", err, errno))
-		goto close_iter;
+
+	 /* Note: The following assertions serve to ensure
+	  * the value was deleted. It does so by asserting
+	  * that bpf_map_lookup_elem has failed. This might
+	  * seem counterintuitive at first.
+	  */
+	ASSERT_ERR(err, "bpf_map_lookup_elem");
+	ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem");
 
 close_iter:
 	close(iter_fd);
@@ -1205,17 +1202,15 @@ static void test_bpf_sk_storage_get(void)
 	do_dummy_read(skel->progs.fill_socket_owner);
 
 	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
-	if (CHECK(err || val != getpid(), "bpf_map_lookup_elem",
-	    "map value wasn't set correctly (expected %d, got %d, err=%d)\n",
-	    getpid(), val, err))
+	if (!ASSERT_OK(err, "bpf_map_lookup_elem") ||
+			!ASSERT_EQ(val, getpid(), "bpf_map_lookup_elem"))
 		goto close_socket;
 
 	do_dummy_read(skel->progs.negate_socket_local_storage);
 
 	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
-	CHECK(err || val != -getpid(), "bpf_map_lookup_elem",
-	      "map value wasn't set correctly (expected %d, got %d, err=%d)\n",
-	      -getpid(), val, err);
+	ASSERT_OK(err, "bpf_map_lookup_elem");
+	ASSERT_EQ(val, -getpid(), "bpf_map_lookup_elem");
 
 close_socket:
 	close(sock_fd);
@@ -1292,7 +1287,7 @@ static void test_bpf_sk_storage_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
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 675b90b152..f09d6ac2ef 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -25,7 +25,7 @@ void serial_test_bpf_obj_id(void)
 	 */
 	__u32 map_ids[nr_iters + 1];
 	char jited_insns[128], xlated_insns[128], zeros[128], tp_name[128];
-	__u32 i, next_id, info_len, nr_id_found, duration = 0;
+	__u32 i, next_id, info_len, nr_id_found;
 	struct timespec real_time_ts, boot_time_ts;
 	int err = 0;
 	__u64 array_value;
@@ -33,16 +33,16 @@ void serial_test_bpf_obj_id(void)
 	time_t now, load_time;
 
 	err = bpf_prog_get_fd_by_id(0);
-	CHECK(err >= 0 || errno != ENOENT,
-	      "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno);
+	ASSERT_LT(err, 0, "bpf_prog_get_fd_by_id");
+	ASSERT_EQ(errno, ENOENT, "bpf_prog_get_fd_by_id");
 
 	err = bpf_map_get_fd_by_id(0);
-	CHECK(err >= 0 || errno != ENOENT,
-	      "get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno);
+	ASSERT_LT(err, 0, "bpf_map_get_fd_by_id");
+	ASSERT_EQ(errno, ENOENT, "bpf_map_get_fd_by_id");
 
 	err = bpf_link_get_fd_by_id(0);
-	CHECK(err >= 0 || errno != ENOENT,
-	      "get-fd-by-notexist-link-id", "err %d errno %d\n", err, errno);
+	ASSERT_LT(err, 0, "bpf_map_get_fd_by_id");
+	ASSERT_EQ(errno, ENOENT, "bpf_map_get_fd_by_id");
 
 	/* Check bpf_map_get_info_by_fd() */
 	bzero(zeros, sizeof(zeros));
@@ -53,25 +53,26 @@ void serial_test_bpf_obj_id(void)
 		/* test_obj_id.o is a dumb prog. It should never fail
 		 * to load.
 		 */
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "bpf_prog_test_load"))
 			continue;
 
 		/* Insert a magic value to the map */
 		map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
-		if (CHECK_FAIL(map_fds[i] < 0))
+		if (!ASSERT_GE(map_fds[i], 0, "bpf_find_map"))
 			goto done;
+
 		err = bpf_map_update_elem(map_fds[i], &array_key,
 					  &array_magic_value, 0);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
 			goto done;
 
-		prog = bpf_object__find_program_by_name(objs[i],
-							"test_obj_id");
-		if (CHECK_FAIL(!prog))
+		prog = bpf_object__find_program_by_name(objs[i], "test_obj_id");
+		if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
 			goto done;
+
 		links[i] = bpf_program__attach(prog);
 		err = libbpf_get_error(links[i]);
-		if (CHECK(err, "prog_attach", "prog #%d, err %d\n", i, err)) {
+		if (!ASSERT_OK(err, "bpf_program__attach")) {
 			links[i] = NULL;
 			goto done;
 		}
@@ -81,24 +82,14 @@ void serial_test_bpf_obj_id(void)
 		bzero(&map_infos[i], info_len);
 		err = bpf_map_get_info_by_fd(map_fds[i], &map_infos[i],
 					     &info_len);
-		if (CHECK(err ||
-			  map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
-			  map_infos[i].key_size != sizeof(__u32) ||
-			  map_infos[i].value_size != sizeof(__u64) ||
-			  map_infos[i].max_entries != 1 ||
-			  map_infos[i].map_flags != 0 ||
-			  info_len != sizeof(struct bpf_map_info) ||
-			  strcmp((char *)map_infos[i].name, expected_map_name),
-			  "get-map-info(fd)",
-			  "err %d errno %d type %d(%d) info_len %u(%zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
-			  err, errno,
-			  map_infos[i].type, BPF_MAP_TYPE_ARRAY,
-			  info_len, sizeof(struct bpf_map_info),
-			  map_infos[i].key_size,
-			  map_infos[i].value_size,
-			  map_infos[i].max_entries,
-			  map_infos[i].map_flags,
-			  map_infos[i].name, expected_map_name))
+		if (!ASSERT_OK(err, "bpf_map_get_info_by_fd") ||
+				!ASSERT_EQ(map_infos[i].type, BPF_MAP_TYPE_ARRAY, "map_type") ||
+				!ASSERT_EQ(map_infos[i].key_size, sizeof(__u32), "key_size") ||
+				!ASSERT_EQ(map_infos[i].value_size, sizeof(__u64), "value_size") ||
+				!ASSERT_EQ(map_infos[i].max_entries, 1, "max_entries") ||
+				!ASSERT_EQ(map_infos[i].map_flags, 0, "map_flags") ||
+				!ASSERT_EQ(info_len, sizeof(struct bpf_map_info), "map_info_len") ||
+				!ASSERT_STREQ((char *)map_infos[i].name, expected_map_name, "map_name"))
 			goto done;
 
 		/* Check getting prog info */
@@ -112,48 +103,34 @@ void serial_test_bpf_obj_id(void)
 		prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
 		prog_infos[i].map_ids = ptr_to_u64(map_ids + i);
 		prog_infos[i].nr_map_ids = 2;
+
 		err = clock_gettime(CLOCK_REALTIME, &real_time_ts);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "clock_gettime"))
 			goto done;
+
 		err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "clock_gettime"))
 			goto done;
+
 		err = bpf_prog_get_info_by_fd(prog_fds[i], &prog_infos[i],
 					      &info_len);
 		load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec)
 			+ (prog_infos[i].load_time / nsec_per_sec);
-		if (CHECK(err ||
-			  prog_infos[i].type != BPF_PROG_TYPE_RAW_TRACEPOINT ||
-			  info_len != sizeof(struct bpf_prog_info) ||
-			  (env.jit_enabled && !prog_infos[i].jited_prog_len) ||
-			  (env.jit_enabled &&
-			   !memcmp(jited_insns, zeros, sizeof(zeros))) ||
-			  !prog_infos[i].xlated_prog_len ||
-			  !memcmp(xlated_insns, zeros, sizeof(zeros)) ||
-			  load_time < now - 60 || load_time > now + 60 ||
-			  prog_infos[i].created_by_uid != my_uid ||
-			  prog_infos[i].nr_map_ids != 1 ||
-			  *(int *)(long)prog_infos[i].map_ids != map_infos[i].id ||
-			  strcmp((char *)prog_infos[i].name, expected_prog_name),
-			  "get-prog-info(fd)",
-			  "err %d errno %d i %d type %d(%d) info_len %u(%zu) "
-			  "jit_enabled %d jited_prog_len %u xlated_prog_len %u "
-			  "jited_prog %d xlated_prog %d load_time %lu(%lu) "
-			  "uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) "
-			  "name %s(%s)\n",
-			  err, errno, i,
-			  prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
-			  info_len, sizeof(struct bpf_prog_info),
-			  env.jit_enabled,
-			  prog_infos[i].jited_prog_len,
-			  prog_infos[i].xlated_prog_len,
-			  !!memcmp(jited_insns, zeros, sizeof(zeros)),
-			  !!memcmp(xlated_insns, zeros, sizeof(zeros)),
-			  load_time, now,
-			  prog_infos[i].created_by_uid, my_uid,
-			  prog_infos[i].nr_map_ids, 1,
-			  *(int *)(long)prog_infos[i].map_ids, map_infos[i].id,
-			  prog_infos[i].name, expected_prog_name))
+
+		if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd") ||
+				!ASSERT_EQ(prog_infos[i].type, BPF_PROG_TYPE_RAW_TRACEPOINT, "prog_type") ||
+				!ASSERT_EQ(info_len, sizeof(struct bpf_prog_info), "prog_info_len") ||
+				!ASSERT_FALSE((env.jit_enabled && !prog_infos[i].jited_prog_len), "jited_prog_len") ||
+				!ASSERT_FALSE((env.jit_enabled && !memcmp(jited_insns, zeros, sizeof(zeros))),
+					"jited_insns") ||
+				!ASSERT_NEQ(prog_infos[i].xlated_prog_len, 0, "xlated_prog_len") ||
+				!ASSERT_NEQ(memcmp(xlated_insns, zeros, sizeof(zeros)), 0, "xlated_insns") ||
+				!ASSERT_GE(load_time, (now - 60), "load_time") ||
+				!ASSERT_LE(load_time, (now + 60), "load_time") ||
+				!ASSERT_EQ(prog_infos[i].created_by_uid, my_uid, "created_by_uid") ||
+				!ASSERT_EQ(prog_infos[i].nr_map_ids, 1, "nr_map_ids") ||
+				!ASSERT_EQ(*(int *)(long)prog_infos[i].map_ids, map_infos[i].id, "map_ids") ||
+				!ASSERT_STREQ((char *)prog_infos[i].name, expected_prog_name, "prog_name"))
 			goto done;
 
 		/* Check getting link info */
@@ -163,25 +140,12 @@ void serial_test_bpf_obj_id(void)
 		link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name);
 		err = bpf_link_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 != 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)",
-			  "err %d errno %d info_len %u(%zu) type %d(%d) id %d "
-			  "prog_id %d (%d) tp_name %s(%s)\n",
-			  err, errno,
-			  info_len, sizeof(struct bpf_link_info),
-			  link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT,
-			  link_infos[i].id,
-			  link_infos[i].prog_id, prog_infos[i].id,
-			  (const char *)u64_to_ptr(link_infos[i].raw_tracepoint.tp_name),
-			  "sys_enter"))
+		if (!ASSERT_OK(err, "bpf_link_get_info_by_fd") ||
+				!ASSERT_EQ(link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT, "link_type") ||
+				!ASSERT_EQ(link_infos[i].prog_id, prog_infos[i].id, "prog_id") ||
+				!ASSERT_EQ(link_infos[i].raw_tracepoint.tp_name, ptr_to_u64(&tp_name), "&tp_name") ||
+				!ASSERT_STREQ(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), "sys_enter", "tp_name"))
 			goto done;
-
 	}
 
 	/* Check bpf_prog_get_next_id() */
@@ -190,7 +154,7 @@ void serial_test_bpf_obj_id(void)
 	while (!bpf_prog_get_next_id(next_id, &next_id)) {
 		struct bpf_prog_info prog_info = {};
 		__u32 saved_map_id;
-		int prog_fd;
+		int prog_fd, cmp_res;
 
 		info_len = sizeof(prog_info);
 
@@ -198,9 +162,7 @@ void serial_test_bpf_obj_id(void)
 		if (prog_fd < 0 && errno == ENOENT)
 			/* The bpf_prog is in the dead row */
 			continue;
-		if (CHECK(prog_fd < 0, "get-prog-fd(next_id)",
-			  "prog_fd %d next_id %d errno %d\n",
-			  prog_fd, next_id, errno))
+		if (!ASSERT_GE(prog_fd, 0, "bpf_prog_get_fd_by_id"))
 			break;
 
 		for (i = 0; i < nr_iters; i++)
@@ -218,9 +180,8 @@ void serial_test_bpf_obj_id(void)
 		 */
 		prog_info.nr_map_ids = 1;
 		err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len);
-		if (CHECK(!err || errno != EFAULT,
-			  "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)",
-			  err, errno, EFAULT))
+		if (!ASSERT_ERR(err, "bpf_prog_get_info_by_fd") ||
+				!ASSERT_EQ(errno, EFAULT, "bpf_prog_get_info_by_fd"))
 			break;
 		bzero(&prog_info, sizeof(prog_info));
 		info_len = sizeof(prog_info);
@@ -231,27 +192,22 @@ void serial_test_bpf_obj_id(void)
 		err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len);
 		prog_infos[i].jited_prog_insns = 0;
 		prog_infos[i].xlated_prog_insns = 0;
-		CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
-		      memcmp(&prog_info, &prog_infos[i], info_len) ||
-		      *(int *)(long)prog_info.map_ids != saved_map_id,
-		      "get-prog-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%zu) memcmp %d map_id %u(%u)\n",
-		      err, errno, info_len, sizeof(struct bpf_prog_info),
-		      memcmp(&prog_info, &prog_infos[i], info_len),
-		      *(int *)(long)prog_info.map_ids, saved_map_id);
+		cmp_res = memcmp(&prog_info, &prog_infos[i], info_len);
+
+		ASSERT_OK(err, "bpf_prog_get_info_by_fd");
+		ASSERT_EQ(info_len, sizeof(struct bpf_prog_info), "prog_info_len");
+		ASSERT_OK(cmp_res, "memcmp");
+		ASSERT_EQ(*(int *)(long)prog_info.map_ids, saved_map_id, "map_id");
 		close(prog_fd);
 	}
-	CHECK(nr_id_found != nr_iters,
-	      "check total prog id found by get_next_id",
-	      "nr_id_found %u(%u)\n",
-	      nr_id_found, nr_iters);
+	ASSERT_EQ(nr_id_found, nr_iters, "prog_nr_id_found");
 
 	/* Check bpf_map_get_next_id() */
 	nr_id_found = 0;
 	next_id = 0;
 	while (!bpf_map_get_next_id(next_id, &next_id)) {
 		struct bpf_map_info map_info = {};
-		int map_fd;
+		int map_fd, cmp_res;
 
 		info_len = sizeof(map_info);
 
@@ -259,9 +215,7 @@ void serial_test_bpf_obj_id(void)
 		if (map_fd < 0 && errno == ENOENT)
 			/* The bpf_map is in the dead row */
 			continue;
-		if (CHECK(map_fd < 0, "get-map-fd(next_id)",
-			  "map_fd %d next_id %u errno %d\n",
-			  map_fd, next_id, errno))
+		if (!ASSERT_GE(map_fd, 0, "bpf_map_get_fd_by_id"))
 			break;
 
 		for (i = 0; i < nr_iters; i++)
@@ -274,25 +228,19 @@ void serial_test_bpf_obj_id(void)
 		nr_id_found++;
 
 		err = bpf_map_lookup_elem(map_fd, &array_key, &array_value);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
 			goto done;
 
 		err = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len);
-		CHECK(err || info_len != sizeof(struct bpf_map_info) ||
-		      memcmp(&map_info, &map_infos[i], info_len) ||
-		      array_value != array_magic_value,
-		      "check get-map-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%zu) memcmp %d array_value %llu(%llu)\n",
-		      err, errno, info_len, sizeof(struct bpf_map_info),
-		      memcmp(&map_info, &map_infos[i], info_len),
-		      array_value, array_magic_value);
+		cmp_res = memcmp(&map_info, &map_infos[i], info_len);
+		ASSERT_OK(err, "bpf_map_get_info_by_fd");
+		ASSERT_EQ(info_len, sizeof(struct bpf_map_info), "info_len");
+		ASSERT_OK(cmp_res, "memcmp");
+		ASSERT_EQ(array_value, array_magic_value, "array_value");
 
 		close(map_fd);
 	}
-	CHECK(nr_id_found != nr_iters,
-	      "check total map id found by get_next_id",
-	      "nr_id_found %u(%u)\n",
-	      nr_id_found, nr_iters);
+	ASSERT_EQ(nr_id_found, nr_iters, "map_nr_id_found");
 
 	/* Check bpf_link_get_next_id() */
 	nr_id_found = 0;
@@ -308,9 +256,7 @@ void serial_test_bpf_obj_id(void)
 		if (link_fd < 0 && errno == ENOENT)
 			/* The bpf_link is in the dead row */
 			continue;
-		if (CHECK(link_fd < 0, "get-link-fd(next_id)",
-			  "link_fd %d next_id %u errno %d\n",
-			  link_fd, next_id, errno))
+		if (!ASSERT_GE(link_fd, 0, "bpf_link_get_fd_by_id"))
 			break;
 
 		for (i = 0; i < nr_iters; i++)
@@ -325,17 +271,13 @@ void serial_test_bpf_obj_id(void)
 		err = bpf_link_get_info_by_fd(link_fd, &link_info, &info_len);
 		cmp_res = memcmp(&link_info, &link_infos[i],
 				offsetof(struct bpf_link_info, raw_tracepoint));
-		CHECK(err || info_len != sizeof(link_info) || cmp_res,
-		      "check get-link-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%zu) memcmp %d\n",
-		      err, errno, info_len, sizeof(struct bpf_link_info),
-		      cmp_res);
+		ASSERT_OK(err, "bpf_link_get_info_by_fd");
+		ASSERT_EQ(info_len, sizeof(link_info), "info_len");
+		ASSERT_OK(cmp_res, "memcmp");
 
 		close(link_fd);
 	}
-	CHECK(nr_id_found != nr_iters,
-	      "check total link id found by get_next_id",
-	      "nr_id_found %u(%u)\n", nr_id_found, nr_iters);
+	ASSERT_EQ(nr_id_found, nr_iters, "link_nr_id_found");
 
 done:
 	for (i = 0; i < nr_iters; i++) {
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 4aabeaa525..a88e6e07e4 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -20,15 +20,14 @@
 
 static const unsigned int total_bytes = 10 * 1024 * 1024;
 static int expected_stg = 0xeB9F;
-static int stop, duration;
+static int stop;
 
 static int settcpca(int fd, const char *tcp_ca)
 {
 	int err;
 
 	err = setsockopt(fd, IPPROTO_TCP, TCP_CONGESTION, tcp_ca, strlen(tcp_ca));
-	if (CHECK(err == -1, "setsockopt(fd, TCP_CONGESTION)", "errno:%d\n",
-		  errno))
+	if (!ASSERT_NEQ(err, -1, "setsockopt"))
 		return -1;
 
 	return 0;
@@ -65,8 +64,7 @@ static void *server(void *arg)
 		bytes += nr_sent;
 	}
 
-	CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n",
-	      bytes, total_bytes, nr_sent, errno);
+	ASSERT_EQ(bytes, total_bytes, "send");
 
 done:
 	if (fd >= 0)
@@ -92,10 +90,11 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 	WRITE_ONCE(stop, 0);
 
 	lfd = socket(AF_INET6, SOCK_STREAM, 0);
-	if (CHECK(lfd == -1, "socket", "errno:%d\n", errno))
+	if (!ASSERT_NEQ(lfd, -1, "socket"))
 		return;
+
 	fd = socket(AF_INET6, SOCK_STREAM, 0);
-	if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) {
+	if (!ASSERT_NEQ(fd, -1, "socket")) {
 		close(lfd);
 		return;
 	}
@@ -108,26 +107,27 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 	sa6.sin6_family = AF_INET6;
 	sa6.sin6_addr = in6addr_loopback;
 	err = bind(lfd, (struct sockaddr *)&sa6, addrlen);
-	if (CHECK(err == -1, "bind", "errno:%d\n", errno))
+	if (!ASSERT_NEQ(err, -1, "bind"))
 		goto done;
+
 	err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen);
-	if (CHECK(err == -1, "getsockname", "errno:%d\n", errno))
+	if (!ASSERT_NEQ(err, -1, "getsockname"))
 		goto done;
+
 	err = listen(lfd, 1);
-	if (CHECK(err == -1, "listen", "errno:%d\n", errno))
+	if (!ASSERT_NEQ(err, -1, "listen"))
 		goto done;
 
 	if (sk_stg_map) {
 		err = bpf_map_update_elem(bpf_map__fd(sk_stg_map), &fd,
 					  &expected_stg, BPF_NOEXIST);
-		if (CHECK(err, "bpf_map_update_elem(sk_stg_map)",
-			  "err:%d errno:%d\n", err, errno))
+		if (!ASSERT_OK(err, "bpf_map_update_elem(sk_stg_map)"))
 			goto done;
 	}
 
 	/* connect to server */
 	err = connect(fd, (struct sockaddr *)&sa6, addrlen);
-	if (CHECK(err == -1, "connect", "errno:%d\n", errno))
+	if (!ASSERT_NEQ(err, -1, "connect"))
 		goto done;
 
 	if (sk_stg_map) {
@@ -135,14 +135,13 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 
 		err = bpf_map_lookup_elem(bpf_map__fd(sk_stg_map), &fd,
 					  &tmp_stg);
-		if (CHECK(!err || errno != ENOENT,
-			  "bpf_map_lookup_elem(sk_stg_map)",
-			  "err:%d errno:%d\n", err, errno))
+		if (!ASSERT_ERR(err, "bpf_map_lookup_elem(sk_stg_map)") ||
+				!ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem(sk_stg_map)"))
 			goto done;
 	}
 
 	err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
-	if (CHECK(err != 0, "pthread_create", "err:%d errno:%d\n", err, errno))
+	if (!ASSERT_OK(err, "pthread_create"))
 		goto done;
 
 	/* recv total_bytes */
@@ -156,13 +155,12 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 		bytes += nr_recv;
 	}
 
-	CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n",
-	      bytes, total_bytes, nr_recv, errno);
+	ASSERT_EQ(bytes, total_bytes, "recv");
 
 	WRITE_ONCE(stop, 1);
 	pthread_join(srv_thread, &thread_ret);
-	CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld",
-	      PTR_ERR(thread_ret));
+	ASSERT_OK(IS_ERR(thread_ret), "thread_ret");
+
 done:
 	close(lfd);
 	close(fd);
@@ -174,7 +172,7 @@ static void test_cubic(void)
 	struct bpf_link *link;
 
 	cubic_skel = bpf_cubic__open_and_load();
-	if (CHECK(!cubic_skel, "bpf_cubic__open_and_load", "failed\n"))
+	if (!ASSERT_OK_PTR(cubic_skel, "bpf_cubic__open_and_load"))
 		return;
 
 	link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic);
@@ -197,7 +195,7 @@ static void test_dctcp(void)
 	struct bpf_link *link;
 
 	dctcp_skel = bpf_dctcp__open_and_load();
-	if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n"))
+	if (!ASSERT_OK_PTR(dctcp_skel, "bpf_dctcp__open_and_load"))
 		return;
 
 	link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
@@ -207,9 +205,7 @@ static void test_dctcp(void)
 	}
 
 	do_test("bpf_dctcp", dctcp_skel->maps.sk_stg_map);
-	CHECK(dctcp_skel->bss->stg_result != expected_stg,
-	      "Unexpected stg_result", "stg_result (%x) != expected_stg (%x)\n",
-	      dctcp_skel->bss->stg_result, expected_stg);
+	ASSERT_EQ(dctcp_skel->bss->stg_result, expected_stg, "stg_result");
 
 	bpf_link__destroy(link);
 	bpf_dctcp__destroy(dctcp_skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 731c343897..e770912fc1 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -35,7 +35,7 @@ static int check_load(const char *file, enum bpf_prog_type type)
 	}
 
 	bpf_program__set_type(prog, type);
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
+	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS);
 	bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags);
 
 	err = bpf_object__load(obj);
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
new file mode 100644
index 0000000000..74d6d7546f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include <sys/types.h>
+#include <unistd.h>
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "test_cgroup1_hierarchy.skel.h"
+
+static void bpf_cgroup1(struct test_cgroup1_hierarchy *skel)
+{
+	struct bpf_link *lsm_link, *fentry_link;
+	int err;
+
+	/* Attach LSM prog first */
+	lsm_link = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(lsm_link, "lsm_attach"))
+		return;
+
+	/* LSM prog will be triggered when attaching fentry */
+	fentry_link = bpf_program__attach_trace(skel->progs.fentry_run);
+	ASSERT_NULL(fentry_link, "fentry_attach_fail");
+
+	err = bpf_link__destroy(lsm_link);
+	ASSERT_OK(err, "destroy_lsm");
+}
+
+static void bpf_cgroup1_sleepable(struct test_cgroup1_hierarchy *skel)
+{
+	struct bpf_link *lsm_link, *fentry_link;
+	int err;
+
+	/* Attach LSM prog first */
+	lsm_link = bpf_program__attach_lsm(skel->progs.lsm_s_run);
+	if (!ASSERT_OK_PTR(lsm_link, "lsm_attach"))
+		return;
+
+	/* LSM prog will be triggered when attaching fentry */
+	fentry_link = bpf_program__attach_trace(skel->progs.fentry_run);
+	ASSERT_NULL(fentry_link, "fentry_attach_fail");
+
+	err = bpf_link__destroy(lsm_link);
+	ASSERT_OK(err, "destroy_lsm");
+}
+
+static void bpf_cgroup1_invalid_id(struct test_cgroup1_hierarchy *skel)
+{
+	struct bpf_link *lsm_link, *fentry_link;
+	int err;
+
+	/* Attach LSM prog first */
+	lsm_link = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(lsm_link, "lsm_attach"))
+		return;
+
+	/* LSM prog will be triggered when attaching fentry */
+	fentry_link = bpf_program__attach_trace(skel->progs.fentry_run);
+	if (!ASSERT_OK_PTR(fentry_link, "fentry_attach_success"))
+		goto cleanup;
+
+	err = bpf_link__destroy(fentry_link);
+	ASSERT_OK(err, "destroy_lsm");
+
+cleanup:
+	err = bpf_link__destroy(lsm_link);
+	ASSERT_OK(err, "destroy_fentry");
+}
+
+void test_cgroup1_hierarchy(void)
+{
+	struct test_cgroup1_hierarchy *skel;
+	__u64 current_cgid;
+	int hid, err;
+
+	skel = test_cgroup1_hierarchy__open();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	skel->bss->target_pid = getpid();
+
+	err = bpf_program__set_attach_target(skel->progs.fentry_run, 0, "bpf_fentry_test1");
+	if (!ASSERT_OK(err, "fentry_set_target"))
+		goto destroy;
+
+	err = test_cgroup1_hierarchy__load(skel);
+	if (!ASSERT_OK(err, "load"))
+		goto destroy;
+
+	/* Setup cgroup1 hierarchy */
+	err = setup_classid_environment();
+	if (!ASSERT_OK(err, "setup_classid_environment"))
+		goto destroy;
+
+	err = join_classid();
+	if (!ASSERT_OK(err, "join_cgroup1"))
+		goto cleanup;
+
+	current_cgid = get_classid_cgroup_id();
+	if (!ASSERT_GE(current_cgid, 0, "cgroup1 id"))
+		goto cleanup;
+
+	hid = get_cgroup1_hierarchy_id("net_cls");
+	if (!ASSERT_GE(hid, 0, "cgroup1 id"))
+		goto cleanup;
+	skel->bss->target_hid = hid;
+
+	if (test__start_subtest("test_cgroup1_hierarchy")) {
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1(skel);
+	}
+
+	if (test__start_subtest("test_root_cgid")) {
+		skel->bss->target_ancestor_cgid = 1;
+		skel->bss->target_ancestor_level = 0;
+		bpf_cgroup1(skel);
+	}
+
+	if (test__start_subtest("test_invalid_level")) {
+		skel->bss->target_ancestor_cgid = 1;
+		skel->bss->target_ancestor_level = 1;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_cgid")) {
+		skel->bss->target_ancestor_cgid = 0;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_hid")) {
+		skel->bss->target_ancestor_cgid = 1;
+		skel->bss->target_ancestor_level = 0;
+		skel->bss->target_hid = -1;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_cgrp_name")) {
+		skel->bss->target_hid = get_cgroup1_hierarchy_id("net_cl");
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_cgrp_name2")) {
+		skel->bss->target_hid = get_cgroup1_hierarchy_id("net_cls,");
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_sleepable_prog")) {
+		skel->bss->target_hid = hid;
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1_sleepable(skel);
+	}
+
+cleanup:
+	cleanup_classid_environment();
+destroy:
+	test_cgroup1_hierarchy__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
index 9026b42914..addf720428 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
@@ -71,7 +71,7 @@ void test_cgroup_v1v2(void)
 	}
 	ASSERT_OK(run_test(cgroup_fd, server_fd, false), "cgroup-v2-only");
 	setup_classid_environment();
-	set_classid(42);
+	set_classid();
 	ASSERT_OK(run_test(cgroup_fd, server_fd, true), "cgroup-v1v2");
 	cleanup_classid_environment();
 	close(server_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
index 63e776f417..7477615720 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
@@ -19,6 +19,21 @@ struct socket_cookie {
 	__u64 cookie_value;
 };
 
+static bool is_cgroup1;
+static int target_hid;
+
+#define CGROUP_MODE_SET(skel)			\
+{						\
+	skel->bss->is_cgroup1 = is_cgroup1;	\
+	skel->bss->target_hid = target_hid;	\
+}
+
+static void cgroup_mode_value_init(bool cgroup, int hid)
+{
+	is_cgroup1 = cgroup;
+	target_hid = hid;
+}
+
 static void test_tp_btf(int cgroup_fd)
 {
 	struct cgrp_ls_tp_btf *skel;
@@ -29,6 +44,8 @@ static void test_tp_btf(int cgroup_fd)
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	/* populate a value in map_b */
 	err = bpf_map_update_elem(bpf_map__fd(skel->maps.map_b), &cgroup_fd, &val1, BPF_ANY);
 	if (!ASSERT_OK(err, "map_update_elem"))
@@ -130,6 +147,8 @@ static void test_recursion(int cgroup_fd)
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	err = cgrp_ls_recursion__attach(skel);
 	if (!ASSERT_OK(err, "skel_attach"))
 		goto out;
@@ -165,6 +184,8 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	bpf_program__set_autoload(skel->progs.cgroup_iter, true);
 	err = cgrp_ls_sleepable__load(skel);
 	if (!ASSERT_OK(err, "skel_load"))
@@ -202,6 +223,7 @@ static void test_yes_rcu_lock(__u64 cgroup_id)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
+	CGROUP_MODE_SET(skel);
 	skel->bss->target_pid = syscall(SYS_gettid);
 
 	bpf_program__set_autoload(skel->progs.yes_rcu_lock, true);
@@ -229,6 +251,8 @@ static void test_no_rcu_lock(void)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	bpf_program__set_autoload(skel->progs.no_rcu_lock, true);
 	err = cgrp_ls_sleepable__load(skel);
 	ASSERT_ERR(err, "skel_load");
@@ -236,7 +260,25 @@ static void test_no_rcu_lock(void)
 	cgrp_ls_sleepable__destroy(skel);
 }
 
-void test_cgrp_local_storage(void)
+static void test_cgrp1_no_rcu_lock(void)
+{
+	struct cgrp_ls_sleepable *skel;
+	int err;
+
+	skel = cgrp_ls_sleepable__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	CGROUP_MODE_SET(skel);
+
+	bpf_program__set_autoload(skel->progs.cgrp1_no_rcu_lock, true);
+	err = cgrp_ls_sleepable__load(skel);
+	ASSERT_OK(err, "skel_load");
+
+	cgrp_ls_sleepable__destroy(skel);
+}
+
+static void cgrp2_local_storage(void)
 {
 	__u64 cgroup_id;
 	int cgroup_fd;
@@ -245,6 +287,8 @@ void test_cgrp_local_storage(void)
 	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /cgrp_local_storage"))
 		return;
 
+	cgroup_mode_value_init(0, -1);
+
 	cgroup_id = get_cgroup_id("/cgrp_local_storage");
 	if (test__start_subtest("tp_btf"))
 		test_tp_btf(cgroup_fd);
@@ -263,3 +307,55 @@ void test_cgrp_local_storage(void)
 
 	close(cgroup_fd);
 }
+
+static void cgrp1_local_storage(void)
+{
+	int cgrp1_fd, cgrp1_hid, cgrp1_id, err;
+
+	/* Setup cgroup1 hierarchy */
+	err = setup_classid_environment();
+	if (!ASSERT_OK(err, "setup_classid_environment"))
+		return;
+
+	err = join_classid();
+	if (!ASSERT_OK(err, "join_cgroup1"))
+		goto cleanup;
+
+	cgrp1_fd = open_classid();
+	if (!ASSERT_GE(cgrp1_fd, 0, "cgroup1 fd"))
+		goto cleanup;
+
+	cgrp1_id = get_classid_cgroup_id();
+	if (!ASSERT_GE(cgrp1_id, 0, "cgroup1 id"))
+		goto close_fd;
+
+	cgrp1_hid = get_cgroup1_hierarchy_id("net_cls");
+	if (!ASSERT_GE(cgrp1_hid, 0, "cgroup1 hid"))
+		goto close_fd;
+
+	cgroup_mode_value_init(1, cgrp1_hid);
+
+	if (test__start_subtest("cgrp1_tp_btf"))
+		test_tp_btf(cgrp1_fd);
+	if (test__start_subtest("cgrp1_recursion"))
+		test_recursion(cgrp1_fd);
+	if (test__start_subtest("cgrp1_negative"))
+		test_negative();
+	if (test__start_subtest("cgrp1_iter_sleepable"))
+		test_cgroup_iter_sleepable(cgrp1_fd, cgrp1_id);
+	if (test__start_subtest("cgrp1_yes_rcu_lock"))
+		test_yes_rcu_lock(cgrp1_id);
+	if (test__start_subtest("cgrp1_no_rcu_lock"))
+		test_cgrp1_no_rcu_lock();
+
+close_fd:
+	close(cgrp1_fd);
+cleanup:
+	cleanup_classid_environment();
+}
+
+void test_cgrp_local_storage(void)
+{
+	cgrp2_local_storage();
+	cgrp1_local_storage();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c
index 756ea8b590..c2e886399e 100644
--- a/tools/testing/selftests/bpf/prog_tests/cpumask.c
+++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c
@@ -18,6 +18,7 @@ static const char * const cpumask_success_testcases[] = {
 	"test_insert_leave",
 	"test_insert_remove_release",
 	"test_global_mask_rcu",
+	"test_cpumask_weight",
 };
 
 static void verify_success(const char *prog_name)
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index 8ec73fdfcd..f29fc789c1 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -348,7 +348,8 @@ static void test_func_sockmap_update(void)
 }
 
 static void test_obj_load_failure_common(const char *obj_file,
-					 const char *target_obj_file)
+					 const char *target_obj_file,
+					 const char *exp_msg)
 {
 	/*
 	 * standalone test that asserts failure to load freplace prog
@@ -356,6 +357,7 @@ static void test_obj_load_failure_common(const char *obj_file,
 	 */
 	struct bpf_object *obj = NULL, *pkt_obj;
 	struct bpf_program *prog;
+	char log_buf[64 * 1024];
 	int err, pkt_fd;
 	__u32 duration = 0;
 
@@ -374,11 +376,21 @@ static void test_obj_load_failure_common(const char *obj_file,
 	err = bpf_program__set_attach_target(prog, pkt_fd, NULL);
 	ASSERT_OK(err, "set_attach_target");
 
+	log_buf[0] = '\0';
+	if (exp_msg)
+		bpf_program__set_log_buf(prog, log_buf, sizeof(log_buf));
+	if (env.verbosity > VERBOSE_NONE)
+		bpf_program__set_log_level(prog, 2);
+
 	/* It should fail to load the program */
 	err = bpf_object__load(obj);
+	if (env.verbosity > VERBOSE_NONE && exp_msg) /* we overtook log */
+		printf("VERIFIER LOG:\n================\n%s\n================\n", log_buf);
 	if (CHECK(!err, "bpf_obj_load should fail", "err %d\n", err))
 		goto close_prog;
 
+	if (exp_msg)
+		ASSERT_HAS_SUBSTR(log_buf, exp_msg, "fail_msg");
 close_prog:
 	bpf_object__close(obj);
 	bpf_object__close(pkt_obj);
@@ -388,14 +400,24 @@ static void test_func_replace_return_code(void)
 {
 	/* test invalid return code in the replaced program */
 	test_obj_load_failure_common("./freplace_connect_v4_prog.bpf.o",
-				     "./connect4_prog.bpf.o");
+				     "./connect4_prog.bpf.o", NULL);
 }
 
 static void test_func_map_prog_compatibility(void)
 {
 	/* test with spin lock map value in the replaced program */
 	test_obj_load_failure_common("./freplace_attach_probe.bpf.o",
-				     "./test_attach_probe.bpf.o");
+				     "./test_attach_probe.bpf.o", NULL);
+}
+
+static void test_func_replace_unreliable(void)
+{
+	/* freplace'ing unreliable main prog should fail with error
+	 * "Cannot replace static functions"
+	 */
+	test_obj_load_failure_common("freplace_unreliable_prog.bpf.o",
+				     "./verifier_btf_unreliable_prog.bpf.o",
+				     "Cannot replace static functions");
 }
 
 static void test_func_replace_global_func(void)
@@ -563,6 +585,8 @@ void serial_test_fexit_bpf2bpf(void)
 		test_func_replace_return_code();
 	if (test__start_subtest("func_map_prog_compatibility"))
 		test_func_map_prog_compatibility();
+	if (test__start_subtest("func_replace_unreliable"))
+		test_func_replace_unreliable();
 	if (test__start_subtest("func_replace_multi"))
 		test_func_replace_multi();
 	if (test__start_subtest("fmod_ret_freplace"))
diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
index 97142a4db3..d4b1901f78 100644
--- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -7,6 +7,7 @@
 #include <test_progs.h>
 #include "trace_helpers.h"
 #include "test_fill_link_info.skel.h"
+#include "bpf/libbpf_internal.h"
 
 #define TP_CAT "sched"
 #define TP_NAME "sched_switch"
@@ -140,14 +141,14 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
 		.retprobe = type == BPF_PERF_EVENT_KRETPROBE,
 	);
 	ssize_t entry_offset = 0;
+	struct bpf_link *link;
 	int link_fd, err;
 
-	skel->links.kprobe_run = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run,
-								 KPROBE_FUNC, &opts);
-	if (!ASSERT_OK_PTR(skel->links.kprobe_run, "attach_kprobe"))
+	link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run, KPROBE_FUNC, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_kprobe"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.kprobe_run);
+	link_fd = bpf_link__fd(link);
 	if (!invalid) {
 		/* See also arch_adjust_kprobe_addr(). */
 		if (skel->kconfig->CONFIG_X86_KERNEL_IBT)
@@ -157,39 +158,41 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
 	} else {
 		kprobe_fill_invalid_user_buffer(link_fd);
 	}
-	bpf_link__detach(skel->links.kprobe_run);
+	bpf_link__destroy(link);
 }
 
 static void test_tp_fill_link_info(struct test_fill_link_info *skel)
 {
+	struct bpf_link *link;
 	int link_fd, err;
 
-	skel->links.tp_run = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME);
-	if (!ASSERT_OK_PTR(skel->links.tp_run, "attach_tp"))
+	link = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME);
+	if (!ASSERT_OK_PTR(link, "attach_tp"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.tp_run);
+	link_fd = bpf_link__fd(link);
 	err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_TRACEPOINT, 0, 0, 0);
 	ASSERT_OK(err, "verify_perf_link_info");
-	bpf_link__detach(skel->links.tp_run);
+	bpf_link__destroy(link);
 }
 
 static void test_uprobe_fill_link_info(struct test_fill_link_info *skel,
 				       enum bpf_perf_event_type type)
 {
+	struct bpf_link *link;
 	int link_fd, err;
 
-	skel->links.uprobe_run = bpf_program__attach_uprobe(skel->progs.uprobe_run,
-							    type == BPF_PERF_EVENT_URETPROBE,
-							    0, /* self pid */
-							    UPROBE_FILE, uprobe_offset);
-	if (!ASSERT_OK_PTR(skel->links.uprobe_run, "attach_uprobe"))
+	link = bpf_program__attach_uprobe(skel->progs.uprobe_run,
+					  type == BPF_PERF_EVENT_URETPROBE,
+					  0, /* self pid */
+					  UPROBE_FILE, uprobe_offset);
+	if (!ASSERT_OK_PTR(link, "attach_uprobe"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.uprobe_run);
+	link_fd = bpf_link__fd(link);
 	err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, 0);
 	ASSERT_OK(err, "verify_perf_link_info");
-	bpf_link__detach(skel->links.uprobe_run);
+	bpf_link__destroy(link);
 }
 
 static int verify_kmulti_link_info(int fd, bool retprobe)
@@ -278,24 +281,214 @@ static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel,
 					     bool retprobe, bool invalid)
 {
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	struct bpf_link *link;
 	int link_fd, err;
 
 	opts.syms = kmulti_syms;
 	opts.cnt = KMULTI_CNT;
 	opts.retprobe = retprobe;
-	skel->links.kmulti_run = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run,
-								       NULL, &opts);
-	if (!ASSERT_OK_PTR(skel->links.kmulti_run, "attach_kprobe_multi"))
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run, NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_kprobe_multi"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.kmulti_run);
+	link_fd = bpf_link__fd(link);
 	if (!invalid) {
 		err = verify_kmulti_link_info(link_fd, retprobe);
 		ASSERT_OK(err, "verify_kmulti_link_info");
 	} else {
 		verify_kmulti_invalid_user_buffer(link_fd);
 	}
-	bpf_link__detach(skel->links.kmulti_run);
+	bpf_link__destroy(link);
+}
+
+#define SEC(name) __attribute__((section(name), used))
+
+static short uprobe_link_info_sema_1 SEC(".probes");
+static short uprobe_link_info_sema_2 SEC(".probes");
+static short uprobe_link_info_sema_3 SEC(".probes");
+
+noinline void uprobe_link_info_func_1(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_1++;
+}
+
+noinline void uprobe_link_info_func_2(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_2++;
+}
+
+noinline void uprobe_link_info_func_3(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_3++;
+}
+
+static int
+verify_umulti_link_info(int fd, bool retprobe, __u64 *offsets,
+			__u64 *cookies, __u64 *ref_ctr_offsets)
+{
+	char path[PATH_MAX], path_buf[PATH_MAX];
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	__u64 ref_ctr_offsets_buf[3];
+	__u64 offsets_buf[3];
+	__u64 cookies_buf[3];
+	int i, err, bit;
+	__u32 count = 0;
+
+	memset(path, 0, sizeof(path));
+	err = readlink("/proc/self/exe", path, sizeof(path));
+	if (!ASSERT_NEQ(err, -1, "readlink"))
+		return -1;
+
+	for (bit = 0; bit < 8; bit++) {
+		memset(&info, 0, sizeof(info));
+		info.uprobe_multi.path = ptr_to_u64(path_buf);
+		info.uprobe_multi.path_size = sizeof(path_buf);
+		info.uprobe_multi.count = count;
+
+		if (bit & 0x1)
+			info.uprobe_multi.offsets = ptr_to_u64(offsets_buf);
+		if (bit & 0x2)
+			info.uprobe_multi.cookies = ptr_to_u64(cookies_buf);
+		if (bit & 0x4)
+			info.uprobe_multi.ref_ctr_offsets = ptr_to_u64(ref_ctr_offsets_buf);
+
+		err = bpf_link_get_info_by_fd(fd, &info, &len);
+		if (!ASSERT_OK(err, "bpf_link_get_info_by_fd"))
+			return -1;
+
+		if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_UPROBE_MULTI, "info.type"))
+			return -1;
+
+		ASSERT_EQ(info.uprobe_multi.pid, getpid(), "info.uprobe_multi.pid");
+		ASSERT_EQ(info.uprobe_multi.count, 3, "info.uprobe_multi.count");
+		ASSERT_EQ(info.uprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN,
+			  retprobe, "info.uprobe_multi.flags.retprobe");
+		ASSERT_EQ(info.uprobe_multi.path_size, strlen(path) + 1, "info.uprobe_multi.path_size");
+		ASSERT_STREQ(path_buf, path, "info.uprobe_multi.path");
+
+		for (i = 0; i < info.uprobe_multi.count; i++) {
+			if (info.uprobe_multi.offsets)
+				ASSERT_EQ(offsets_buf[i], offsets[i], "info.uprobe_multi.offsets");
+			if (info.uprobe_multi.cookies)
+				ASSERT_EQ(cookies_buf[i], cookies[i], "info.uprobe_multi.cookies");
+			if (info.uprobe_multi.ref_ctr_offsets) {
+				ASSERT_EQ(ref_ctr_offsets_buf[i], ref_ctr_offsets[i],
+					  "info.uprobe_multi.ref_ctr_offsets");
+			}
+		}
+		count = count ?: info.uprobe_multi.count;
+	}
+
+	return 0;
+}
+
+static void verify_umulti_invalid_user_buffer(int fd)
+{
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	__u64 buf[3];
+	int err;
+
+	/* upath_size defined, not path */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path_size = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "failed_upath_size");
+
+	/* path defined, but small */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path = ptr_to_u64(buf);
+	info.uprobe_multi.path_size = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_LT(err, 0, "failed_upath_small");
+
+	/* path has wrong pointer */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path_size = PATH_MAX;
+	info.uprobe_multi.path = 123;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "failed_bad_path_ptr");
+
+	/* count zero, with offsets */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = ptr_to_u64(buf);
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "failed_count");
+
+	/* offsets not big enough */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = ptr_to_u64(buf);
+	info.uprobe_multi.count = 2;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -ENOSPC, "failed_small_count");
+
+	/* offsets has wrong pointer */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = 123;
+	info.uprobe_multi.count = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "failed_wrong_offsets");
+}
+
+static void test_uprobe_multi_fill_link_info(struct test_fill_link_info *skel,
+					     bool retprobe, bool invalid)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+		.retprobe = retprobe,
+	);
+	const char *syms[3] = {
+		"uprobe_link_info_func_1",
+		"uprobe_link_info_func_2",
+		"uprobe_link_info_func_3",
+	};
+	__u64 cookies[3] = {
+		0xdead,
+		0xbeef,
+		0xcafe,
+	};
+	const char *sema[3] = {
+		"uprobe_link_info_sema_1",
+		"uprobe_link_info_sema_2",
+		"uprobe_link_info_sema_3",
+	};
+	__u64 *offsets = NULL, *ref_ctr_offsets;
+	struct bpf_link *link;
+	int link_fd, err;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 3, sema,
+				       (unsigned long **) &ref_ctr_offsets, STT_OBJECT);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_object"))
+		return;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 3, syms,
+				       (unsigned long **) &offsets, STT_FUNC);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_func"))
+		goto out;
+
+	opts.syms = syms;
+	opts.cookies = &cookies[0];
+	opts.ref_ctr_offsets = (unsigned long *) &ref_ctr_offsets[0];
+	opts.cnt = ARRAY_SIZE(syms);
+
+	link = bpf_program__attach_uprobe_multi(skel->progs.umulti_run, 0,
+						"/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto out;
+
+	link_fd = bpf_link__fd(link);
+	if (invalid)
+		verify_umulti_invalid_user_buffer(link_fd);
+	else
+		verify_umulti_link_info(link_fd, retprobe, offsets, cookies, ref_ctr_offsets);
+
+	bpf_link__destroy(link);
+out:
+	free(ref_ctr_offsets);
+	free(offsets);
 }
 
 void test_fill_link_info(void)
@@ -337,6 +530,13 @@ void test_fill_link_info(void)
 	if (test__start_subtest("kprobe_multi_invalid_ubuff"))
 		test_kprobe_multi_fill_link_info(skel, true, true);
 
+	if (test__start_subtest("uprobe_multi_link_info"))
+		test_uprobe_multi_fill_link_info(skel, false, false);
+	if (test__start_subtest("uretprobe_multi_link_info"))
+		test_uprobe_multi_fill_link_info(skel, true, false);
+	if (test__start_subtest("uprobe_multi_invalid"))
+		test_uprobe_multi_fill_link_info(skel, false, true);
+
 cleanup:
 	test_fill_link_info__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
new file mode 100644
index 0000000000..37056ba738
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/xattr.h>
+#include <linux/fsverity.h>
+#include <unistd.h>
+#include <test_progs.h>
+#include "test_get_xattr.skel.h"
+#include "test_fsverity.skel.h"
+
+static const char testfile[] = "/tmp/test_progs_fs_kfuncs";
+
+static void test_xattr(void)
+{
+	struct test_get_xattr *skel = NULL;
+	int fd = -1, err;
+
+	fd = open(testfile, O_CREAT | O_RDONLY, 0644);
+	if (!ASSERT_GE(fd, 0, "create_file"))
+		return;
+
+	close(fd);
+	fd = -1;
+
+	err = setxattr(testfile, "user.kfuncs", "hello", sizeof("hello"), 0);
+	if (err && errno == EOPNOTSUPP) {
+		printf("%s:SKIP:local fs doesn't support xattr (%d)\n"
+		       "To run this test, make sure /tmp filesystem supports xattr.\n",
+		       __func__, errno);
+		test__skip();
+		goto out;
+	}
+
+	if (!ASSERT_OK(err, "setxattr"))
+		goto out;
+
+	skel = test_get_xattr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_get_xattr__open_and_load"))
+		goto out;
+
+	skel->bss->monitored_pid = getpid();
+	err = test_get_xattr__attach(skel);
+
+	if (!ASSERT_OK(err, "test_get_xattr__attach"))
+		goto out;
+
+	fd = open(testfile, O_RDONLY, 0644);
+	if (!ASSERT_GE(fd, 0, "open_file"))
+		goto out;
+
+	ASSERT_EQ(skel->bss->found_xattr, 1, "found_xattr");
+
+out:
+	close(fd);
+	test_get_xattr__destroy(skel);
+	remove(testfile);
+}
+
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
+static void test_fsverity(void)
+{
+	struct fsverity_enable_arg arg = {0};
+	struct test_fsverity *skel = NULL;
+	struct fsverity_digest *d;
+	int fd, err;
+	char buffer[4096];
+
+	fd = open(testfile, O_CREAT | O_RDWR, 0644);
+	if (!ASSERT_GE(fd, 0, "create_file"))
+		return;
+
+	/* Write random buffer, so the file is not empty */
+	err = write(fd, buffer, 4096);
+	if (!ASSERT_EQ(err, 4096, "write_file"))
+		goto out;
+	close(fd);
+
+	/* Reopen read-only, otherwise FS_IOC_ENABLE_VERITY will fail */
+	fd = open(testfile, O_RDONLY, 0644);
+	if (!ASSERT_GE(fd, 0, "open_file1"))
+		return;
+
+	/* Enable fsverity for the file.
+	 * If the file system doesn't support verity, this will fail. Skip
+	 * the test in such case.
+	 */
+	arg.version = 1;
+	arg.hash_algorithm = FS_VERITY_HASH_ALG_SHA256;
+	arg.block_size = 4096;
+	err = ioctl(fd, FS_IOC_ENABLE_VERITY, &arg);
+	if (err) {
+		printf("%s:SKIP:local fs doesn't support fsverity (%d)\n"
+		       "To run this test, try enable CONFIG_FS_VERITY and enable FSVerity for the filesystem.\n",
+		       __func__, errno);
+		test__skip();
+		goto out;
+	}
+
+	skel = test_fsverity__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_fsverity__open_and_load"))
+		goto out;
+
+	/* Get fsverity_digest from ioctl */
+	d = (struct fsverity_digest *)skel->bss->expected_digest;
+	d->digest_algorithm = FS_VERITY_HASH_ALG_SHA256;
+	d->digest_size = SHA256_DIGEST_SIZE;
+	err = ioctl(fd, FS_IOC_MEASURE_VERITY, skel->bss->expected_digest);
+	if (!ASSERT_OK(err, "ioctl_FS_IOC_MEASURE_VERITY"))
+		goto out;
+
+	skel->bss->monitored_pid = getpid();
+	err = test_fsverity__attach(skel);
+	if (!ASSERT_OK(err, "test_fsverity__attach"))
+		goto out;
+
+	/* Reopen the file to trigger the program */
+	close(fd);
+	fd = open(testfile, O_RDONLY);
+	if (!ASSERT_GE(fd, 0, "open_file2"))
+		goto out;
+
+	ASSERT_EQ(skel->bss->got_fsverity, 1, "got_fsverity");
+	ASSERT_EQ(skel->bss->digest_matches, 1, "digest_matches");
+out:
+	close(fd);
+	test_fsverity__destroy(skel);
+	remove(testfile);
+}
+
+void test_fs_kfuncs(void)
+{
+	if (test__start_subtest("xattr"))
+		test_xattr();
+
+	if (test__start_subtest("fsverity"))
+		test_fsverity();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c b/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c
new file mode 100644
index 0000000000..65309894b2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "verifier_global_subprogs.skel.h"
+#include "freplace_dead_global_func.skel.h"
+
+void test_global_func_dead_code(void)
+{
+	struct verifier_global_subprogs *tgt_skel = NULL;
+	struct freplace_dead_global_func *skel = NULL;
+	char log_buf[4096];
+	int err, tgt_fd;
+
+	/* first, try to load target with good global subprog */
+	tgt_skel = verifier_global_subprogs__open();
+	if (!ASSERT_OK_PTR(tgt_skel, "tgt_skel_good_open"))
+		return;
+
+	bpf_program__set_autoload(tgt_skel->progs.chained_global_func_calls_success, true);
+
+	err = verifier_global_subprogs__load(tgt_skel);
+	if (!ASSERT_OK(err, "tgt_skel_good_load"))
+		goto out;
+
+	tgt_fd = bpf_program__fd(tgt_skel->progs.chained_global_func_calls_success);
+
+	/* Attach to good non-eliminated subprog */
+	skel = freplace_dead_global_func__open();
+	if (!ASSERT_OK_PTR(skel, "skel_good_open"))
+		goto out;
+
+	err = bpf_program__set_attach_target(skel->progs.freplace_prog, tgt_fd, "global_good");
+	ASSERT_OK(err, "attach_target_good");
+
+	err = freplace_dead_global_func__load(skel);
+	if (!ASSERT_OK(err, "skel_good_load"))
+		goto out;
+
+	freplace_dead_global_func__destroy(skel);
+
+	/* Try attaching to dead code-eliminated subprog */
+	skel = freplace_dead_global_func__open();
+	if (!ASSERT_OK_PTR(skel, "skel_dead_open"))
+		goto out;
+
+	bpf_program__set_log_buf(skel->progs.freplace_prog, log_buf, sizeof(log_buf));
+	err = bpf_program__set_attach_target(skel->progs.freplace_prog, tgt_fd, "global_dead");
+	ASSERT_OK(err, "attach_target_dead");
+
+	err = freplace_dead_global_func__load(skel);
+	if (!ASSERT_ERR(err, "skel_dead_load"))
+		goto out;
+
+	ASSERT_HAS_SUBSTR(log_buf, "Subprog global_dead doesn't exist", "dead_subprog_missing_msg");
+
+out:
+	verifier_global_subprogs__destroy(tgt_skel);
+	freplace_dead_global_func__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index bf84d4a1d9..3c440370c1 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -193,6 +193,7 @@ static void subtest_task_iters(void)
 	ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt");
 	ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt");
 	ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt");
+	ASSERT_EQ(skel->bss->invalid_cnt, 0, "invalid_cnt");
 	pthread_mutex_unlock(&do_nothing_mutex);
 	for (int i = 0; i < thread_num; i++)
 		ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join");
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 4041cfa670..05000810e2 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -222,6 +222,7 @@ static void test_attach_api_fails(void)
 		"bpf_fentry_test2",
 	};
 	__u64 cookies[2];
+	int saved_error;
 
 	addrs[0] = ksym_get_addr("bpf_fentry_test1");
 	addrs[1] = ksym_get_addr("bpf_fentry_test2");
@@ -238,10 +239,11 @@ static void test_attach_api_fails(void)
 	/* fail_1 - pattern and opts NULL */
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     NULL, NULL);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_1"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_1_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_1_error"))
 		goto cleanup;
 
 	/* fail_2 - both addrs and syms set */
@@ -252,10 +254,11 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     NULL, &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_2"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_2_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_2_error"))
 		goto cleanup;
 
 	/* fail_3 - pattern and addrs set */
@@ -266,10 +269,11 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     "ksys_*", &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_3"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_3_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_3_error"))
 		goto cleanup;
 
 	/* fail_4 - pattern and cnt set */
@@ -280,10 +284,11 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     "ksys_*", &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_4"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_4_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_4_error"))
 		goto cleanup;
 
 	/* fail_5 - pattern and cookies */
@@ -294,10 +299,26 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     "ksys_*", &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_5"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_5_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_5_error"))
+		goto cleanup;
+
+	/* fail_6 - abnormal cnt */
+	opts.addrs = (const unsigned long *) addrs;
+	opts.syms = NULL;
+	opts.cnt = INT_MAX;
+	opts.cookies = NULL;
+
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
+						     NULL, &opts);
+	saved_error = -errno;
+	if (!ASSERT_ERR_PTR(link, "fail_6"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(saved_error, -E2BIG, "fail_6_error"))
 		goto cleanup;
 
 cleanup:
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
index c440ea3311..eb34d612d6 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -87,7 +87,7 @@ static void test_libbpf_bpf_link_type_str(void)
 		const char *link_type_str;
 		char buf[256];
 
-		if (link_type == MAX_BPF_LINK_TYPE)
+		if (link_type == __MAX_BPF_LINK_TYPE)
 			continue;
 
 		link_type_name = btf__str_by_offset(btf, e->name_off);
diff --git a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
index b25b870f87..827e713f6c 100644
--- a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
+++ b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
@@ -48,6 +48,27 @@ static void test_local_kptr_stash_plain(void)
 	local_kptr_stash__destroy(skel);
 }
 
+static void test_local_kptr_stash_local_with_root(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct local_kptr_stash *skel;
+	int ret;
+
+	skel = local_kptr_stash__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_local_with_root), &opts);
+	ASSERT_OK(ret, "local_kptr_stash_add_local_with_root run");
+	ASSERT_OK(opts.retval, "local_kptr_stash_add_local_with_root retval");
+
+	local_kptr_stash__destroy(skel);
+}
+
 static void test_local_kptr_stash_unstash(void)
 {
 	LIBBPF_OPTS(bpf_test_run_opts, opts,
@@ -73,6 +94,37 @@ static void test_local_kptr_stash_unstash(void)
 	local_kptr_stash__destroy(skel);
 }
 
+static void test_refcount_acquire_without_unstash(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct local_kptr_stash *skel;
+	int ret;
+
+	skel = local_kptr_stash__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.refcount_acquire_without_unstash),
+				     &opts);
+	ASSERT_OK(ret, "refcount_acquire_without_unstash run");
+	ASSERT_EQ(opts.retval, 2, "refcount_acquire_without_unstash retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_refcounted_node), &opts);
+	ASSERT_OK(ret, "stash_refcounted_node run");
+	ASSERT_OK(opts.retval, "stash_refcounted_node retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.refcount_acquire_without_unstash),
+				     &opts);
+	ASSERT_OK(ret, "refcount_acquire_without_unstash (2) run");
+	ASSERT_EQ(opts.retval, 42, "refcount_acquire_without_unstash (2) retval");
+
+	local_kptr_stash__destroy(skel);
+}
+
 static void test_local_kptr_stash_fail(void)
 {
 	RUN_TESTS(local_kptr_stash_fail);
@@ -84,8 +136,12 @@ void test_local_kptr_stash(void)
 		test_local_kptr_stash_simple();
 	if (test__start_subtest("local_kptr_stash_plain"))
 		test_local_kptr_stash_plain();
+	if (test__start_subtest("local_kptr_stash_local_with_root"))
+		test_local_kptr_stash_local_with_root();
 	if (test__start_subtest("local_kptr_stash_unstash"))
 		test_local_kptr_stash_unstash();
+	if (test__start_subtest("refcount_acquire_without_unstash"))
+		test_refcount_acquire_without_unstash();
 	if (test__start_subtest("local_kptr_stash_fail"))
 		test_local_kptr_stash_fail();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c
index fe9a23e65e..0f7ea4d7d9 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_buf.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c
@@ -78,7 +78,7 @@ static void obj_load_log_buf(void)
 	ASSERT_OK_PTR(strstr(libbpf_log_buf, "prog 'bad_prog': BPF program load failed"),
 		      "libbpf_log_not_empty");
 	ASSERT_OK_PTR(strstr(obj_log_buf, "DATASEC license"), "obj_log_not_empty");
-	ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"),
+	ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx() R10=fp0"),
 		      "good_log_verbose");
 	ASSERT_OK_PTR(strstr(bad_log_buf, "invalid access to map value, value_size=16 off=16000 size=4"),
 		      "bad_log_not_empty");
@@ -175,7 +175,7 @@ static void bpf_prog_load_log_buf(void)
 	opts.log_level = 2;
 	fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL",
 			   good_prog_insns, good_prog_insn_cnt, &opts);
-	ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"), "good_log_2");
+	ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx() R10=fp0"), "good_log_2");
 	ASSERT_GE(fd, 0, "good_fd2");
 	if (fd >= 0)
 		close(fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/log_fixup.c b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
index effd78b2a6..7a3fa2ff56 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_fixup.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
@@ -169,9 +169,9 @@ void test_log_fixup(void)
 	if (test__start_subtest("bad_core_relo_trunc_none"))
 		bad_core_relo(0, TRUNC_NONE /* full buf */);
 	if (test__start_subtest("bad_core_relo_trunc_partial"))
-		bad_core_relo(300, TRUNC_PARTIAL /* truncate original log a bit */);
+		bad_core_relo(280, TRUNC_PARTIAL /* truncate original log a bit */);
 	if (test__start_subtest("bad_core_relo_trunc_full"))
-		bad_core_relo(210, TRUNC_FULL  /* truncate also libbpf's message patch */);
+		bad_core_relo(220, TRUNC_FULL  /* truncate also libbpf's message patch */);
 	if (test__start_subtest("bad_core_relo_subprog"))
 		bad_core_relo_subprog();
 	if (test__start_subtest("missing_map"))
diff --git a/tools/testing/selftests/bpf/prog_tests/map_btf.c b/tools/testing/selftests/bpf/prog_tests/map_btf.c
new file mode 100644
index 0000000000..2c4ef60375
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_btf.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <test_progs.h>
+
+#include "normal_map_btf.skel.h"
+#include "map_in_map_btf.skel.h"
+
+static void do_test_normal_map_btf(void)
+{
+	struct normal_map_btf *skel;
+	int i, err, new_fd = -1;
+	int map_fd_arr[64];
+
+	skel = normal_map_btf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load"))
+		return;
+
+	err = normal_map_btf__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out;
+
+	skel->bss->pid = getpid();
+	usleep(1);
+	ASSERT_TRUE(skel->bss->done, "done");
+
+	/* Use percpu_array to slow bpf_map_free_deferred() down.
+	 * The memory allocation may fail, so doesn't check the returned fd.
+	 */
+	for (i = 0; i < ARRAY_SIZE(map_fd_arr); i++)
+		map_fd_arr[i] = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, NULL, 4, 4, 256, NULL);
+
+	/* Close array fd later */
+	new_fd = dup(bpf_map__fd(skel->maps.array));
+out:
+	normal_map_btf__destroy(skel);
+	if (new_fd < 0)
+		return;
+	/* Use kern_sync_rcu() to wait for the start of the free of the bpf
+	 * program and use an assumed delay to wait for the release of the map
+	 * btf which is held by other maps (e.g, bss). After that, array map
+	 * holds the last reference of map btf.
+	 */
+	kern_sync_rcu();
+	usleep(4000);
+	/* Spawn multiple kworkers to delay the invocation of
+	 * bpf_map_free_deferred() for array map.
+	 */
+	for (i = 0; i < ARRAY_SIZE(map_fd_arr); i++) {
+		if (map_fd_arr[i] < 0)
+			continue;
+		close(map_fd_arr[i]);
+	}
+	close(new_fd);
+}
+
+static void do_test_map_in_map_btf(void)
+{
+	int err, zero = 0, new_fd = -1;
+	struct map_in_map_btf *skel;
+
+	skel = map_in_map_btf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load"))
+		return;
+
+	err = map_in_map_btf__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out;
+
+	skel->bss->pid = getpid();
+	usleep(1);
+	ASSERT_TRUE(skel->bss->done, "done");
+
+	/* Close inner_array fd later */
+	new_fd = dup(bpf_map__fd(skel->maps.inner_array));
+	/* Defer the free of inner_array */
+	err = bpf_map__delete_elem(skel->maps.outer_array, &zero, sizeof(zero), 0);
+	ASSERT_OK(err, "delete inner map");
+out:
+	map_in_map_btf__destroy(skel);
+	if (new_fd < 0)
+		return;
+	/* Use kern_sync_rcu() to wait for the start of the free of the bpf
+	 * program and use an assumed delay to wait for the free of the outer
+	 * map and the release of map btf. After that, inner map holds the last
+	 * reference of map btf.
+	 */
+	kern_sync_rcu();
+	usleep(10000);
+	close(new_fd);
+}
+
+void test_map_btf(void)
+{
+	if (test__start_subtest("array_btf"))
+		do_test_normal_map_btf();
+	if (test__start_subtest("inner_array_btf"))
+		do_test_map_in_map_btf();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/map_in_map.c b/tools/testing/selftests/bpf/prog_tests/map_in_map.c
new file mode 100644
index 0000000000..d2a10eb4e5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_in_map.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "access_map_in_map.skel.h"
+
+struct thread_ctx {
+	pthread_barrier_t barrier;
+	int outer_map_fd;
+	int start, abort;
+	int loop, err;
+};
+
+static int wait_for_start_or_abort(struct thread_ctx *ctx)
+{
+	while (!ctx->start && !ctx->abort)
+		usleep(1);
+	return ctx->abort ? -1 : 0;
+}
+
+static void *update_map_fn(void *data)
+{
+	struct thread_ctx *ctx = data;
+	int loop = ctx->loop, err = 0;
+
+	if (wait_for_start_or_abort(ctx) < 0)
+		return NULL;
+	pthread_barrier_wait(&ctx->barrier);
+
+	while (loop-- > 0) {
+		int fd, zero = 0;
+
+		fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL);
+		if (fd < 0) {
+			err |= 1;
+			pthread_barrier_wait(&ctx->barrier);
+			continue;
+		}
+
+		/* Remove the old inner map */
+		if (bpf_map_update_elem(ctx->outer_map_fd, &zero, &fd, 0) < 0)
+			err |= 2;
+		close(fd);
+		pthread_barrier_wait(&ctx->barrier);
+	}
+
+	ctx->err = err;
+
+	return NULL;
+}
+
+static void *access_map_fn(void *data)
+{
+	struct thread_ctx *ctx = data;
+	int loop = ctx->loop;
+
+	if (wait_for_start_or_abort(ctx) < 0)
+		return NULL;
+	pthread_barrier_wait(&ctx->barrier);
+
+	while (loop-- > 0) {
+		/* Access the old inner map */
+		syscall(SYS_getpgid);
+		pthread_barrier_wait(&ctx->barrier);
+	}
+
+	return NULL;
+}
+
+static void test_map_in_map_access(const char *prog_name, const char *map_name)
+{
+	struct access_map_in_map *skel;
+	struct bpf_map *outer_map;
+	struct bpf_program *prog;
+	struct thread_ctx ctx;
+	pthread_t tid[2];
+	int err;
+
+	skel = access_map_in_map__open();
+	if (!ASSERT_OK_PTR(skel, "access_map_in_map open"))
+		return;
+
+	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+	if (!ASSERT_OK_PTR(prog, "find program"))
+		goto out;
+	bpf_program__set_autoload(prog, true);
+
+	outer_map = bpf_object__find_map_by_name(skel->obj, map_name);
+	if (!ASSERT_OK_PTR(outer_map, "find map"))
+		goto out;
+
+	err = access_map_in_map__load(skel);
+	if (!ASSERT_OK(err, "access_map_in_map load"))
+		goto out;
+
+	err = access_map_in_map__attach(skel);
+	if (!ASSERT_OK(err, "access_map_in_map attach"))
+		goto out;
+
+	skel->bss->tgid = getpid();
+
+	memset(&ctx, 0, sizeof(ctx));
+	pthread_barrier_init(&ctx.barrier, NULL, 2);
+	ctx.outer_map_fd = bpf_map__fd(outer_map);
+	ctx.loop = 4;
+
+	err = pthread_create(&tid[0], NULL, update_map_fn, &ctx);
+	if (!ASSERT_OK(err, "close_thread"))
+		goto out;
+
+	err = pthread_create(&tid[1], NULL, access_map_fn, &ctx);
+	if (!ASSERT_OK(err, "read_thread")) {
+		ctx.abort = 1;
+		pthread_join(tid[0], NULL);
+		goto out;
+	}
+
+	ctx.start = 1;
+	pthread_join(tid[0], NULL);
+	pthread_join(tid[1], NULL);
+
+	ASSERT_OK(ctx.err, "err");
+out:
+	access_map_in_map__destroy(skel);
+}
+
+void test_map_in_map(void)
+{
+	if (test__start_subtest("acc_map_in_array"))
+		test_map_in_map_access("access_map_in_array", "outer_array_map");
+	if (test__start_subtest("sleepable_acc_map_in_array"))
+		test_map_in_map_access("sleepable_access_map_in_array", "outer_array_map");
+	if (test__start_subtest("acc_map_in_htab"))
+		test_map_in_map_access("access_map_in_htab", "outer_htab_map");
+	if (test__start_subtest("sleepable_acc_map_in_htab"))
+		test_map_in_map_access("sleepable_access_map_in_htab", "outer_htab_map");
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
new file mode 100644
index 0000000000..3405923fe4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include "test_progs.h"
+#include "read_vsyscall.skel.h"
+
+#if defined(__x86_64__)
+/* For VSYSCALL_ADDR */
+#include <asm/vsyscall.h>
+#else
+/* To prevent build failure on non-x86 arch */
+#define VSYSCALL_ADDR 0UL
+#endif
+
+struct read_ret_desc {
+	const char *name;
+	int ret;
+} all_read[] = {
+	{ .name = "probe_read_kernel", .ret = -ERANGE },
+	{ .name = "probe_read_kernel_str", .ret = -ERANGE },
+	{ .name = "probe_read", .ret = -ERANGE },
+	{ .name = "probe_read_str", .ret = -ERANGE },
+	{ .name = "probe_read_user", .ret = -EFAULT },
+	{ .name = "probe_read_user_str", .ret = -EFAULT },
+	{ .name = "copy_from_user", .ret = -EFAULT },
+	{ .name = "copy_from_user_task", .ret = -EFAULT },
+};
+
+void test_read_vsyscall(void)
+{
+	struct read_vsyscall *skel;
+	unsigned int i;
+	int err;
+
+#if !defined(__x86_64__)
+	test__skip();
+	return;
+#endif
+	skel = read_vsyscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "read_vsyscall open_load"))
+		return;
+
+	skel->bss->target_pid = getpid();
+	err = read_vsyscall__attach(skel);
+	if (!ASSERT_EQ(err, 0, "read_vsyscall attach"))
+		goto out;
+
+	/* userspace may don't have vsyscall page due to LEGACY_VSYSCALL_NONE,
+	 * but it doesn't affect the returned error codes.
+	 */
+	skel->bss->user_ptr = (void *)VSYSCALL_ADDR;
+	usleep(1);
+
+	for (i = 0; i < ARRAY_SIZE(all_read); i++)
+		ASSERT_EQ(skel->bss->read_ret[i], all_read[i].ret, all_read[i].name);
+out:
+	read_vsyscall__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/recursive_attach.c b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
new file mode 100644
index 0000000000..8100509e56
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <test_progs.h>
+#include "fentry_recursive.skel.h"
+#include "fentry_recursive_target.skel.h"
+#include <bpf/btf.h>
+#include "bpf/libbpf_internal.h"
+
+/* Test recursive attachment of tracing progs with more than one nesting level
+ * is not possible. Create a chain of attachment, verify that the last prog
+ * will fail. Depending on the arguments, following cases are tested:
+ *
+ * - Recursive loading of tracing progs, without attaching (attach = false,
+ *   detach = false). The chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       load fentry2 -> fentry1 (fail)
+ *
+ * - Recursive attach of tracing progs (attach = true, detach = false). The
+ *   chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       attach fentry1 -> target
+ *       load fentry2 -> fentry1 (fail)
+ *
+ * - Recursive attach and detach of tracing progs (attach = true, detach =
+ *   true). This validates that attach_tracing_prog flag will be set throughout
+ *   the whole lifecycle of an fentry prog, independently from whether it's
+ *   detached. The chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       attach fentry1 -> target
+ *       detach fentry1
+ *       load fentry2 -> fentry1 (fail)
+ */
+static void test_recursive_fentry_chain(bool attach, bool detach)
+{
+	struct fentry_recursive_target *target_skel = NULL;
+	struct fentry_recursive *tracing_chain[2] = {};
+	struct bpf_program *prog;
+	int prev_fd, err;
+
+	target_skel = fentry_recursive_target__open_and_load();
+	if (!ASSERT_OK_PTR(target_skel, "fentry_recursive_target__open_and_load"))
+		return;
+
+	/* Create an attachment chain with two fentry progs */
+	for (int i = 0; i < 2; i++) {
+		tracing_chain[i] = fentry_recursive__open();
+		if (!ASSERT_OK_PTR(tracing_chain[i], "fentry_recursive__open"))
+			goto close_prog;
+
+		/* The first prog in the chain is going to be attached to the target
+		 * fentry program, the second one to the previous in the chain.
+		 */
+		prog = tracing_chain[i]->progs.recursive_attach;
+		if (i == 0) {
+			prev_fd = bpf_program__fd(target_skel->progs.test1);
+			err = bpf_program__set_attach_target(prog, prev_fd, "test1");
+		} else {
+			prev_fd = bpf_program__fd(tracing_chain[i-1]->progs.recursive_attach);
+			err = bpf_program__set_attach_target(prog, prev_fd, "recursive_attach");
+		}
+
+		if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+			goto close_prog;
+
+		err = fentry_recursive__load(tracing_chain[i]);
+		/* The first attach should succeed, the second fail */
+		if (i == 0) {
+			if (!ASSERT_OK(err, "fentry_recursive__load"))
+				goto close_prog;
+
+			if (attach) {
+				err = fentry_recursive__attach(tracing_chain[i]);
+				if (!ASSERT_OK(err, "fentry_recursive__attach"))
+					goto close_prog;
+			}
+
+			if (detach) {
+				/* Flag attach_tracing_prog should still be set, preventing
+				 * attachment of the following prog.
+				 */
+				fentry_recursive__detach(tracing_chain[i]);
+			}
+		} else {
+			if (!ASSERT_ERR(err, "fentry_recursive__load"))
+				goto close_prog;
+		}
+	}
+
+close_prog:
+	fentry_recursive_target__destroy(target_skel);
+	for (int i = 0; i < 2; i++) {
+		fentry_recursive__destroy(tracing_chain[i]);
+	}
+}
+
+void test_recursive_fentry(void)
+{
+	if (test__start_subtest("attach"))
+		test_recursive_fentry_chain(true, false);
+	if (test__start_subtest("load"))
+		test_recursive_fentry_chain(false, false);
+	if (test__start_subtest("detach"))
+		test_recursive_fentry_chain(true, true);
+}
+
+/* Test that a tracing prog reattachment (when we land in
+ * "prog->aux->dst_trampoline and tgt_prog is NULL" branch in
+ * bpf_tracing_prog_attach) does not lead to a crash due to missing attach_btf
+ */
+void test_fentry_attach_btf_presence(void)
+{
+	struct fentry_recursive_target *target_skel = NULL;
+	struct fentry_recursive *tracing_skel = NULL;
+	struct bpf_program *prog;
+	int err, link_fd, tgt_prog_fd;
+
+	target_skel = fentry_recursive_target__open_and_load();
+	if (!ASSERT_OK_PTR(target_skel, "fentry_recursive_target__open_and_load"))
+		goto close_prog;
+
+	tracing_skel = fentry_recursive__open();
+	if (!ASSERT_OK_PTR(tracing_skel, "fentry_recursive__open"))
+		goto close_prog;
+
+	prog = tracing_skel->progs.recursive_attach;
+	tgt_prog_fd = bpf_program__fd(target_skel->progs.fentry_target);
+	err = bpf_program__set_attach_target(prog, tgt_prog_fd, "fentry_target");
+	if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+		goto close_prog;
+
+	err = fentry_recursive__load(tracing_skel);
+	if (!ASSERT_OK(err, "fentry_recursive__load"))
+		goto close_prog;
+
+	tgt_prog_fd = bpf_program__fd(tracing_skel->progs.recursive_attach);
+	link_fd = bpf_link_create(tgt_prog_fd, 0, BPF_TRACE_FENTRY, NULL);
+	if (!ASSERT_GE(link_fd, 0, "link_fd"))
+		goto close_prog;
+
+	fentry_recursive__detach(tracing_skel);
+
+	err = fentry_recursive__attach(tracing_skel);
+	ASSERT_ERR(err, "fentry_recursive__attach");
+
+close_prog:
+	fentry_recursive_target__destroy(target_skel);
+	fentry_recursive__destroy(tracing_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
new file mode 100644
index 0000000000..820d0bcfc4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -0,0 +1,2131 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#define _GNU_SOURCE
+#include <limits.h>
+#include <test_progs.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+
+/* =================================
+ * SHORT AND CONSISTENT NUMBER TYPES
+ * =================================
+ */
+#define U64_MAX ((u64)UINT64_MAX)
+#define U32_MAX ((u32)UINT_MAX)
+#define U16_MAX ((u32)UINT_MAX)
+#define S64_MIN ((s64)INT64_MIN)
+#define S64_MAX ((s64)INT64_MAX)
+#define S32_MIN ((s32)INT_MIN)
+#define S32_MAX ((s32)INT_MAX)
+#define S16_MIN ((s16)0x80000000)
+#define S16_MAX ((s16)0x7fffffff)
+
+typedef unsigned long long ___u64;
+typedef unsigned int ___u32;
+typedef long long ___s64;
+typedef int ___s32;
+
+/* avoid conflicts with already defined types in kernel headers */
+#define u64 ___u64
+#define u32 ___u32
+#define s64 ___s64
+#define s32 ___s32
+
+/* ==================================
+ * STRING BUF ABSTRACTION AND HELPERS
+ * ==================================
+ */
+struct strbuf {
+	size_t buf_sz;
+	int pos;
+	char buf[0];
+};
+
+#define DEFINE_STRBUF(name, N)						\
+	struct { struct strbuf buf; char data[(N)]; } ___##name;	\
+	struct strbuf *name = (___##name.buf.buf_sz = (N), ___##name.buf.pos = 0, &___##name.buf)
+
+__printf(2, 3)
+static inline void snappendf(struct strbuf *s, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	s->pos += vsnprintf(s->buf + s->pos,
+			    s->pos < s->buf_sz ? s->buf_sz - s->pos : 0,
+			    fmt, args);
+	va_end(args);
+}
+
+/* ==================================
+ * GENERIC NUMBER TYPE AND OPERATIONS
+ * ==================================
+ */
+enum num_t { U64, first_t = U64, U32, S64, S32, last_t = S32 };
+
+static __always_inline u64 min_t(enum num_t t, u64 x, u64 y)
+{
+	switch (t) {
+	case U64: return (u64)x < (u64)y ? (u64)x : (u64)y;
+	case U32: return (u32)x < (u32)y ? (u32)x : (u32)y;
+	case S64: return (s64)x < (s64)y ? (s64)x : (s64)y;
+	case S32: return (s32)x < (s32)y ? (s32)x : (s32)y;
+	default: printf("min_t!\n"); exit(1);
+	}
+}
+
+static __always_inline u64 max_t(enum num_t t, u64 x, u64 y)
+{
+	switch (t) {
+	case U64: return (u64)x > (u64)y ? (u64)x : (u64)y;
+	case U32: return (u32)x > (u32)y ? (u32)x : (u32)y;
+	case S64: return (s64)x > (s64)y ? (s64)x : (s64)y;
+	case S32: return (s32)x > (s32)y ? (u32)(s32)x : (u32)(s32)y;
+	default: printf("max_t!\n"); exit(1);
+	}
+}
+
+static __always_inline u64 cast_t(enum num_t t, u64 x)
+{
+	switch (t) {
+	case U64: return (u64)x;
+	case U32: return (u32)x;
+	case S64: return (s64)x;
+	case S32: return (u32)(s32)x;
+	default: printf("cast_t!\n"); exit(1);
+	}
+}
+
+static const char *t_str(enum num_t t)
+{
+	switch (t) {
+	case U64: return "u64";
+	case U32: return "u32";
+	case S64: return "s64";
+	case S32: return "s32";
+	default: printf("t_str!\n"); exit(1);
+	}
+}
+
+static enum num_t t_is_32(enum num_t t)
+{
+	switch (t) {
+	case U64: return false;
+	case U32: return true;
+	case S64: return false;
+	case S32: return true;
+	default: printf("t_is_32!\n"); exit(1);
+	}
+}
+
+static enum num_t t_signed(enum num_t t)
+{
+	switch (t) {
+	case U64: return S64;
+	case U32: return S32;
+	case S64: return S64;
+	case S32: return S32;
+	default: printf("t_signed!\n"); exit(1);
+	}
+}
+
+static enum num_t t_unsigned(enum num_t t)
+{
+	switch (t) {
+	case U64: return U64;
+	case U32: return U32;
+	case S64: return U64;
+	case S32: return U32;
+	default: printf("t_unsigned!\n"); exit(1);
+	}
+}
+
+#define UNUM_MAX_DECIMAL U16_MAX
+#define SNUM_MAX_DECIMAL S16_MAX
+#define SNUM_MIN_DECIMAL S16_MIN
+
+static bool num_is_small(enum num_t t, u64 x)
+{
+	switch (t) {
+	case U64: return (u64)x <= UNUM_MAX_DECIMAL;
+	case U32: return (u32)x <= UNUM_MAX_DECIMAL;
+	case S64: return (s64)x >= SNUM_MIN_DECIMAL && (s64)x <= SNUM_MAX_DECIMAL;
+	case S32: return (s32)x >= SNUM_MIN_DECIMAL && (s32)x <= SNUM_MAX_DECIMAL;
+	default: printf("num_is_small!\n"); exit(1);
+	}
+}
+
+static void snprintf_num(enum num_t t, struct strbuf *sb, u64 x)
+{
+	bool is_small = num_is_small(t, x);
+
+	if (is_small) {
+		switch (t) {
+		case U64: return snappendf(sb, "%llu", (u64)x);
+		case U32: return snappendf(sb, "%u", (u32)x);
+		case S64: return snappendf(sb, "%lld", (s64)x);
+		case S32: return snappendf(sb, "%d", (s32)x);
+		default: printf("snprintf_num!\n"); exit(1);
+		}
+	} else {
+		switch (t) {
+		case U64:
+			if (x == U64_MAX)
+				return snappendf(sb, "U64_MAX");
+			else if (x >= U64_MAX - 256)
+				return snappendf(sb, "U64_MAX-%llu", U64_MAX - x);
+			else
+				return snappendf(sb, "%#llx", (u64)x);
+		case U32:
+			if ((u32)x == U32_MAX)
+				return snappendf(sb, "U32_MAX");
+			else if ((u32)x >= U32_MAX - 256)
+				return snappendf(sb, "U32_MAX-%u", U32_MAX - (u32)x);
+			else
+				return snappendf(sb, "%#x", (u32)x);
+		case S64:
+			if ((s64)x == S64_MAX)
+				return snappendf(sb, "S64_MAX");
+			else if ((s64)x >= S64_MAX - 256)
+				return snappendf(sb, "S64_MAX-%lld", S64_MAX - (s64)x);
+			else if ((s64)x == S64_MIN)
+				return snappendf(sb, "S64_MIN");
+			else if ((s64)x <= S64_MIN + 256)
+				return snappendf(sb, "S64_MIN+%lld", (s64)x - S64_MIN);
+			else
+				return snappendf(sb, "%#llx", (s64)x);
+		case S32:
+			if ((s32)x == S32_MAX)
+				return snappendf(sb, "S32_MAX");
+			else if ((s32)x >= S32_MAX - 256)
+				return snappendf(sb, "S32_MAX-%d", S32_MAX - (s32)x);
+			else if ((s32)x == S32_MIN)
+				return snappendf(sb, "S32_MIN");
+			else if ((s32)x <= S32_MIN + 256)
+				return snappendf(sb, "S32_MIN+%d", (s32)x - S32_MIN);
+			else
+				return snappendf(sb, "%#x", (s32)x);
+		default: printf("snprintf_num!\n"); exit(1);
+		}
+	}
+}
+
+/* ===================================
+ * GENERIC RANGE STRUCT AND OPERATIONS
+ * ===================================
+ */
+struct range {
+	u64 a, b;
+};
+
+static void snprintf_range(enum num_t t, struct strbuf *sb, struct range x)
+{
+	if (x.a == x.b)
+		return snprintf_num(t, sb, x.a);
+
+	snappendf(sb, "[");
+	snprintf_num(t, sb, x.a);
+	snappendf(sb, "; ");
+	snprintf_num(t, sb, x.b);
+	snappendf(sb, "]");
+}
+
+static void print_range(enum num_t t, struct range x, const char *sfx)
+{
+	DEFINE_STRBUF(sb, 128);
+
+	snprintf_range(t, sb, x);
+	printf("%s%s", sb->buf, sfx);
+}
+
+static const struct range unkn[] = {
+	[U64] = { 0, U64_MAX },
+	[U32] = { 0, U32_MAX },
+	[S64] = { (u64)S64_MIN, (u64)S64_MAX },
+	[S32] = { (u64)(u32)S32_MIN, (u64)(u32)S32_MAX },
+};
+
+static struct range unkn_subreg(enum num_t t)
+{
+	switch (t) {
+	case U64: return unkn[U32];
+	case U32: return unkn[U32];
+	case S64: return unkn[U32];
+	case S32: return unkn[S32];
+	default: printf("unkn_subreg!\n"); exit(1);
+	}
+}
+
+static struct range range(enum num_t t, u64 a, u64 b)
+{
+	switch (t) {
+	case U64: return (struct range){ (u64)a, (u64)b };
+	case U32: return (struct range){ (u32)a, (u32)b };
+	case S64: return (struct range){ (s64)a, (s64)b };
+	case S32: return (struct range){ (u32)(s32)a, (u32)(s32)b };
+	default: printf("range!\n"); exit(1);
+	}
+}
+
+static __always_inline u32 sign64(u64 x) { return (x >> 63) & 1; }
+static __always_inline u32 sign32(u64 x) { return ((u32)x >> 31) & 1; }
+static __always_inline u32 upper32(u64 x) { return (u32)(x >> 32); }
+static __always_inline u64 swap_low32(u64 x, u32 y) { return (x & 0xffffffff00000000ULL) | y; }
+
+static bool range_eq(struct range x, struct range y)
+{
+	return x.a == y.a && x.b == y.b;
+}
+
+static struct range range_cast_to_s32(struct range x)
+{
+	u64 a = x.a, b = x.b;
+
+	/* if upper 32 bits are constant, lower 32 bits should form a proper
+	 * s32 range to be correct
+	 */
+	if (upper32(a) == upper32(b) && (s32)a <= (s32)b)
+		return range(S32, a, b);
+
+	/* Special case where upper bits form a small sequence of two
+	 * sequential numbers (in 32-bit unsigned space, so 0xffffffff to
+	 * 0x00000000 is also valid), while lower bits form a proper s32 range
+	 * going from negative numbers to positive numbers.
+	 *
+	 * E.g.: [0xfffffff0ffffff00; 0xfffffff100000010]. Iterating
+	 * over full 64-bit numbers range will form a proper [-16, 16]
+	 * ([0xffffff00; 0x00000010]) range in its lower 32 bits.
+	 */
+	if (upper32(a) + 1 == upper32(b) && (s32)a < 0 && (s32)b >= 0)
+		return range(S32, a, b);
+
+	/* otherwise we can't derive much meaningful information */
+	return unkn[S32];
+}
+
+static struct range range_cast_u64(enum num_t to_t, struct range x)
+{
+	u64 a = (u64)x.a, b = (u64)x.b;
+
+	switch (to_t) {
+	case U64:
+		return x;
+	case U32:
+		if (upper32(a) != upper32(b))
+			return unkn[U32];
+		return range(U32, a, b);
+	case S64:
+		if (sign64(a) != sign64(b))
+			return unkn[S64];
+		return range(S64, a, b);
+	case S32:
+		return range_cast_to_s32(x);
+	default: printf("range_cast_u64!\n"); exit(1);
+	}
+}
+
+static struct range range_cast_s64(enum num_t to_t, struct range x)
+{
+	s64 a = (s64)x.a, b = (s64)x.b;
+
+	switch (to_t) {
+	case U64:
+		/* equivalent to (s64)a <= (s64)b check */
+		if (sign64(a) != sign64(b))
+			return unkn[U64];
+		return range(U64, a, b);
+	case U32:
+		if (upper32(a) != upper32(b) || sign32(a) != sign32(b))
+			return unkn[U32];
+		return range(U32, a, b);
+	case S64:
+		return x;
+	case S32:
+		return range_cast_to_s32(x);
+	default: printf("range_cast_s64!\n"); exit(1);
+	}
+}
+
+static struct range range_cast_u32(enum num_t to_t, struct range x)
+{
+	u32 a = (u32)x.a, b = (u32)x.b;
+
+	switch (to_t) {
+	case U64:
+	case S64:
+		/* u32 is always a valid zero-extended u64/s64 */
+		return range(to_t, a, b);
+	case U32:
+		return x;
+	case S32:
+		return range_cast_to_s32(range(U32, a, b));
+	default: printf("range_cast_u32!\n"); exit(1);
+	}
+}
+
+static struct range range_cast_s32(enum num_t to_t, struct range x)
+{
+	s32 a = (s32)x.a, b = (s32)x.b;
+
+	switch (to_t) {
+	case U64:
+	case U32:
+	case S64:
+		if (sign32(a) != sign32(b))
+			return unkn[to_t];
+		return range(to_t, a, b);
+	case S32:
+		return x;
+	default: printf("range_cast_s32!\n"); exit(1);
+	}
+}
+
+/* Reinterpret range in *from_t* domain as a range in *to_t* domain preserving
+ * all possible information. Worst case, it will be unknown range within
+ * *to_t* domain, if nothing more specific can be guaranteed during the
+ * conversion
+ */
+static struct range range_cast(enum num_t from_t, enum num_t to_t, struct range from)
+{
+	switch (from_t) {
+	case U64: return range_cast_u64(to_t, from);
+	case U32: return range_cast_u32(to_t, from);
+	case S64: return range_cast_s64(to_t, from);
+	case S32: return range_cast_s32(to_t, from);
+	default: printf("range_cast!\n"); exit(1);
+	}
+}
+
+static bool is_valid_num(enum num_t t, u64 x)
+{
+	switch (t) {
+	case U64: return true;
+	case U32: return upper32(x) == 0;
+	case S64: return true;
+	case S32: return upper32(x) == 0;
+	default: printf("is_valid_num!\n"); exit(1);
+	}
+}
+
+static bool is_valid_range(enum num_t t, struct range x)
+{
+	if (!is_valid_num(t, x.a) || !is_valid_num(t, x.b))
+		return false;
+
+	switch (t) {
+	case U64: return (u64)x.a <= (u64)x.b;
+	case U32: return (u32)x.a <= (u32)x.b;
+	case S64: return (s64)x.a <= (s64)x.b;
+	case S32: return (s32)x.a <= (s32)x.b;
+	default: printf("is_valid_range!\n"); exit(1);
+	}
+}
+
+static struct range range_improve(enum num_t t, struct range old, struct range new)
+{
+	return range(t, max_t(t, old.a, new.a), min_t(t, old.b, new.b));
+}
+
+static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, struct range y)
+{
+	struct range y_cast;
+
+	y_cast = range_cast(y_t, x_t, y);
+
+	/* the case when new range knowledge, *y*, is a 32-bit subregister
+	 * range, while previous range knowledge, *x*, is a full register
+	 * 64-bit range, needs special treatment to take into account upper 32
+	 * bits of full register range
+	 */
+	if (t_is_32(y_t) && !t_is_32(x_t)) {
+		struct range x_swap;
+
+		/* some combinations of upper 32 bits and sign bit can lead to
+		 * invalid ranges, in such cases it's easier to detect them
+		 * after cast/swap than try to enumerate all the conditions
+		 * under which transformation and knowledge transfer is valid
+		 */
+		x_swap = range(x_t, swap_low32(x.a, y_cast.a), swap_low32(x.b, y_cast.b));
+		if (!is_valid_range(x_t, x_swap))
+			return x;
+		return range_improve(x_t, x, x_swap);
+	}
+
+	/* otherwise, plain range cast and intersection works */
+	return range_improve(x_t, x, y_cast);
+}
+
+/* =======================
+ * GENERIC CONDITIONAL OPS
+ * =======================
+ */
+enum op { OP_LT, OP_LE, OP_GT, OP_GE, OP_EQ, OP_NE, first_op = OP_LT, last_op = OP_NE };
+
+static enum op complement_op(enum op op)
+{
+	switch (op) {
+	case OP_LT: return OP_GE;
+	case OP_LE: return OP_GT;
+	case OP_GT: return OP_LE;
+	case OP_GE: return OP_LT;
+	case OP_EQ: return OP_NE;
+	case OP_NE: return OP_EQ;
+	default: printf("complement_op!\n"); exit(1);
+	}
+}
+
+static const char *op_str(enum op op)
+{
+	switch (op) {
+	case OP_LT: return "<";
+	case OP_LE: return "<=";
+	case OP_GT: return ">";
+	case OP_GE: return ">=";
+	case OP_EQ: return "==";
+	case OP_NE: return "!=";
+	default: printf("op_str!\n"); exit(1);
+	}
+}
+
+/* Can register with range [x.a, x.b] *EVER* satisfy
+ * OP (<, <=, >, >=, ==, !=) relation to
+ * a regsiter with range [y.a, y.b]
+ * _in *num_t* domain_
+ */
+static bool range_canbe_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+#define range_canbe(T) do {									\
+	switch (op) {										\
+	case OP_LT: return (T)x.a < (T)y.b;							\
+	case OP_LE: return (T)x.a <= (T)y.b;							\
+	case OP_GT: return (T)x.b > (T)y.a;							\
+	case OP_GE: return (T)x.b >= (T)y.a;							\
+	case OP_EQ: return (T)max_t(t, x.a, y.a) <= (T)min_t(t, x.b, y.b);			\
+	case OP_NE: return !((T)x.a == (T)x.b && (T)y.a == (T)y.b && (T)x.a == (T)y.a);		\
+	default: printf("range_canbe op %d\n", op); exit(1);					\
+	}											\
+} while (0)
+
+	switch (t) {
+	case U64: { range_canbe(u64); }
+	case U32: { range_canbe(u32); }
+	case S64: { range_canbe(s64); }
+	case S32: { range_canbe(s32); }
+	default: printf("range_canbe!\n"); exit(1);
+	}
+#undef range_canbe
+}
+
+/* Does register with range [x.a, x.b] *ALWAYS* satisfy
+ * OP (<, <=, >, >=, ==, !=) relation to
+ * a regsiter with range [y.a, y.b]
+ * _in *num_t* domain_
+ */
+static bool range_always_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+	/* always op <=> ! canbe complement(op) */
+	return !range_canbe_op(t, x, y, complement_op(op));
+}
+
+/* Does register with range [x.a, x.b] *NEVER* satisfy
+ * OP (<, <=, >, >=, ==, !=) relation to
+ * a regsiter with range [y.a, y.b]
+ * _in *num_t* domain_
+ */
+static bool range_never_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+	return !range_canbe_op(t, x, y, op);
+}
+
+/* similar to verifier's is_branch_taken():
+ *    1 - always taken;
+ *    0 - never taken,
+ *   -1 - unsure.
+ */
+static int range_branch_taken_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+	if (range_always_op(t, x, y, op))
+		return 1;
+	if (range_never_op(t, x, y, op))
+		return 0;
+	return -1;
+}
+
+/* What would be the new estimates for register x and y ranges assuming truthful
+ * OP comparison between them. I.e., (x OP y == true) => x <- newx, y <- newy.
+ *
+ * We assume "interesting" cases where ranges overlap. Cases where it's
+ * obvious that (x OP y) is either always true or false should be filtered with
+ * range_never and range_always checks.
+ */
+static void range_cond(enum num_t t, struct range x, struct range y,
+		       enum op op, struct range *newx, struct range *newy)
+{
+	if (!range_canbe_op(t, x, y, op)) {
+		/* nothing to adjust, can't happen, return original values */
+		*newx = x;
+		*newy = y;
+		return;
+	}
+	switch (op) {
+	case OP_LT:
+		*newx = range(t, x.a, min_t(t, x.b, y.b - 1));
+		*newy = range(t, max_t(t, x.a + 1, y.a), y.b);
+		break;
+	case OP_LE:
+		*newx = range(t, x.a, min_t(t, x.b, y.b));
+		*newy = range(t, max_t(t, x.a, y.a), y.b);
+		break;
+	case OP_GT:
+		*newx = range(t, max_t(t, x.a, y.a + 1), x.b);
+		*newy = range(t, y.a, min_t(t, x.b - 1, y.b));
+		break;
+	case OP_GE:
+		*newx = range(t, max_t(t, x.a, y.a), x.b);
+		*newy = range(t, y.a, min_t(t, x.b, y.b));
+		break;
+	case OP_EQ:
+		*newx = range(t, max_t(t, x.a, y.a), min_t(t, x.b, y.b));
+		*newy = range(t, max_t(t, x.a, y.a), min_t(t, x.b, y.b));
+		break;
+	case OP_NE:
+		/* below logic is supported by the verifier now */
+		if (x.a == x.b && x.a == y.a) {
+			/* X is a constant matching left side of Y */
+			*newx = range(t, x.a, x.b);
+			*newy = range(t, y.a + 1, y.b);
+		} else if (x.a == x.b && x.b == y.b) {
+			/* X is a constant matching rigth side of Y */
+			*newx = range(t, x.a, x.b);
+			*newy = range(t, y.a, y.b - 1);
+		} else if (y.a == y.b && x.a == y.a) {
+			/* Y is a constant matching left side of X */
+			*newx = range(t, x.a + 1, x.b);
+			*newy = range(t, y.a, y.b);
+		} else if (y.a == y.b && x.b == y.b) {
+			/* Y is a constant matching rigth side of X */
+			*newx = range(t, x.a, x.b - 1);
+			*newy = range(t, y.a, y.b);
+		} else {
+			/* generic case, can't derive more information */
+			*newx = range(t, x.a, x.b);
+			*newy = range(t, y.a, y.b);
+		}
+
+		break;
+	default:
+		break;
+	}
+}
+
+/* =======================
+ * REGISTER STATE HANDLING
+ * =======================
+ */
+struct reg_state {
+	struct range r[4]; /* indexed by enum num_t: U64, U32, S64, S32 */
+	bool valid;
+};
+
+static void print_reg_state(struct reg_state *r, const char *sfx)
+{
+	DEFINE_STRBUF(sb, 512);
+	enum num_t t;
+	int cnt = 0;
+
+	if (!r->valid) {
+		printf("<not found>%s", sfx);
+		return;
+	}
+
+	snappendf(sb, "scalar(");
+	for (t = first_t; t <= last_t; t++) {
+		snappendf(sb, "%s%s=", cnt++ ? "," : "", t_str(t));
+		snprintf_range(t, sb, r->r[t]);
+	}
+	snappendf(sb, ")");
+
+	printf("%s%s", sb->buf, sfx);
+}
+
+static void print_refinement(enum num_t s_t, struct range src,
+			     enum num_t d_t, struct range old, struct range new,
+			     const char *ctx)
+{
+	printf("REFINING (%s) (%s)SRC=", ctx, t_str(s_t));
+	print_range(s_t, src, "");
+	printf(" (%s)DST_OLD=", t_str(d_t));
+	print_range(d_t, old, "");
+	printf(" (%s)DST_NEW=", t_str(d_t));
+	print_range(d_t, new, "\n");
+}
+
+static void reg_state_refine(struct reg_state *r, enum num_t t, struct range x, const char *ctx)
+{
+	enum num_t d_t, s_t;
+	struct range old;
+	bool keep_going = false;
+
+again:
+	/* try to derive new knowledge from just learned range x of type t */
+	for (d_t = first_t; d_t <= last_t; d_t++) {
+		old = r->r[d_t];
+		r->r[d_t] = range_refine(d_t, r->r[d_t], t, x);
+		if (!range_eq(r->r[d_t], old)) {
+			keep_going = true;
+			if (env.verbosity >= VERBOSE_VERY)
+				print_refinement(t, x, d_t, old, r->r[d_t], ctx);
+		}
+	}
+
+	/* now see if we can derive anything new from updated reg_state's ranges */
+	for (s_t = first_t; s_t <= last_t; s_t++) {
+		for (d_t = first_t; d_t <= last_t; d_t++) {
+			old = r->r[d_t];
+			r->r[d_t] = range_refine(d_t, r->r[d_t], s_t, r->r[s_t]);
+			if (!range_eq(r->r[d_t], old)) {
+				keep_going = true;
+				if (env.verbosity >= VERBOSE_VERY)
+					print_refinement(s_t, r->r[s_t], d_t, old, r->r[d_t], ctx);
+			}
+		}
+	}
+
+	/* keep refining until we converge */
+	if (keep_going) {
+		keep_going = false;
+		goto again;
+	}
+}
+
+static void reg_state_set_const(struct reg_state *rs, enum num_t t, u64 val)
+{
+	enum num_t tt;
+
+	rs->valid = true;
+	for (tt = first_t; tt <= last_t; tt++)
+		rs->r[tt] = tt == t ? range(t, val, val) : unkn[tt];
+
+	reg_state_refine(rs, t, rs->r[t], "CONST");
+}
+
+static void reg_state_cond(enum num_t t, struct reg_state *x, struct reg_state *y, enum op op,
+			   struct reg_state *newx, struct reg_state *newy, const char *ctx)
+{
+	char buf[32];
+	enum num_t ts[2];
+	struct reg_state xx = *x, yy = *y;
+	int i, t_cnt;
+	struct range z1, z2;
+
+	if (op == OP_EQ || op == OP_NE) {
+		/* OP_EQ and OP_NE are sign-agnostic, so we need to process
+		 * both signed and unsigned domains at the same time
+		 */
+		ts[0] = t_unsigned(t);
+		ts[1] = t_signed(t);
+		t_cnt = 2;
+	} else {
+		ts[0] = t;
+		t_cnt = 1;
+	}
+
+	for (i = 0; i < t_cnt; i++) {
+		t = ts[i];
+		z1 = x->r[t];
+		z2 = y->r[t];
+
+		range_cond(t, z1, z2, op, &z1, &z2);
+
+		if (newx) {
+			snprintf(buf, sizeof(buf), "%s R1", ctx);
+			reg_state_refine(&xx, t, z1, buf);
+		}
+		if (newy) {
+			snprintf(buf, sizeof(buf), "%s R2", ctx);
+			reg_state_refine(&yy, t, z2, buf);
+		}
+	}
+
+	if (newx)
+		*newx = xx;
+	if (newy)
+		*newy = yy;
+}
+
+static int reg_state_branch_taken_op(enum num_t t, struct reg_state *x, struct reg_state *y,
+				     enum op op)
+{
+	if (op == OP_EQ || op == OP_NE) {
+		/* OP_EQ and OP_NE are sign-agnostic */
+		enum num_t tu = t_unsigned(t);
+		enum num_t ts = t_signed(t);
+		int br_u, br_s, br;
+
+		br_u = range_branch_taken_op(tu, x->r[tu], y->r[tu], op);
+		br_s = range_branch_taken_op(ts, x->r[ts], y->r[ts], op);
+
+		if (br_u >= 0 && br_s >= 0 && br_u != br_s)
+			ASSERT_FALSE(true, "branch taken inconsistency!\n");
+
+		/* if 64-bit ranges are indecisive, use 32-bit subranges to
+		 * eliminate always/never taken branches, if possible
+		 */
+		if (br_u == -1 && (t == U64 || t == S64)) {
+			br = range_branch_taken_op(U32, x->r[U32], y->r[U32], op);
+			/* we can only reject for OP_EQ, never take branch
+			 * based on lower 32 bits
+			 */
+			if (op == OP_EQ && br == 0)
+				return 0;
+			/* for OP_NEQ we can be conclusive only if lower 32 bits
+			 * differ and thus inequality branch is always taken
+			 */
+			if (op == OP_NE && br == 1)
+				return 1;
+
+			br = range_branch_taken_op(S32, x->r[S32], y->r[S32], op);
+			if (op == OP_EQ && br == 0)
+				return 0;
+			if (op == OP_NE && br == 1)
+				return 1;
+		}
+
+		return br_u >= 0 ? br_u : br_s;
+	}
+	return range_branch_taken_op(t, x->r[t], y->r[t], op);
+}
+
+/* =====================================
+ * BPF PROGS GENERATION AND VERIFICATION
+ * =====================================
+ */
+struct case_spec {
+	/* whether to init full register (r1) or sub-register (w1) */
+	bool init_subregs;
+	/* whether to establish initial value range on full register (r1) or
+	 * sub-register (w1)
+	 */
+	bool setup_subregs;
+	/* whether to establish initial value range using signed or unsigned
+	 * comparisons (i.e., initialize umin/umax or smin/smax directly)
+	 */
+	bool setup_signed;
+	/* whether to perform comparison on full registers or sub-registers */
+	bool compare_subregs;
+	/* whether to perform comparison using signed or unsigned operations */
+	bool compare_signed;
+};
+
+/* Generate test BPF program based on provided test ranges, operation, and
+ * specifications about register bitness and signedness.
+ */
+static int load_range_cmp_prog(struct range x, struct range y, enum op op,
+			       int branch_taken, struct case_spec spec,
+			       char *log_buf, size_t log_sz,
+			       int *false_pos, int *true_pos)
+{
+#define emit(insn) ({							\
+	struct bpf_insn __insns[] = { insn };				\
+	int __i;							\
+	for (__i = 0; __i < ARRAY_SIZE(__insns); __i++)			\
+		insns[cur_pos + __i] = __insns[__i];			\
+	cur_pos += __i;							\
+})
+#define JMP_TO(target) (target - cur_pos - 1)
+	int cur_pos = 0, exit_pos, fd, op_code;
+	struct bpf_insn insns[64];
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_level = 2,
+		.log_buf = log_buf,
+		.log_size = log_sz,
+		.prog_flags = BPF_F_TEST_REG_INVARIANTS,
+	);
+
+	/* ; skip exit block below
+	 * goto +2;
+	 */
+	emit(BPF_JMP_A(2));
+	exit_pos = cur_pos;
+	/* ; exit block for all the preparatory conditionals
+	 * out:
+	 * r0 = 0;
+	 * exit;
+	 */
+	emit(BPF_MOV64_IMM(BPF_REG_0, 0));
+	emit(BPF_EXIT_INSN());
+	/*
+	 * ; assign r6/w6 and r7/w7 unpredictable u64/u32 value
+	 * call bpf_get_current_pid_tgid;
+	 * r6 = r0;               | w6 = w0;
+	 * call bpf_get_current_pid_tgid;
+	 * r7 = r0;               | w7 = w0;
+	 */
+	emit(BPF_EMIT_CALL(BPF_FUNC_get_current_pid_tgid));
+	if (spec.init_subregs)
+		emit(BPF_MOV32_REG(BPF_REG_6, BPF_REG_0));
+	else
+		emit(BPF_MOV64_REG(BPF_REG_6, BPF_REG_0));
+	emit(BPF_EMIT_CALL(BPF_FUNC_get_current_pid_tgid));
+	if (spec.init_subregs)
+		emit(BPF_MOV32_REG(BPF_REG_7, BPF_REG_0));
+	else
+		emit(BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+	/* ; setup initial r6/w6 possible value range ([x.a, x.b])
+	 * r1 = %[x.a] ll;        | w1 = %[x.a];
+	 * r2 = %[x.b] ll;        | w2 = %[x.b];
+	 * if r6 < r1 goto out;   | if w6 < w1 goto out;
+	 * if r6 > r2 goto out;   | if w6 > w2 goto out;
+	 */
+	if (spec.setup_subregs) {
+		emit(BPF_MOV32_IMM(BPF_REG_1, (s32)x.a));
+		emit(BPF_MOV32_IMM(BPF_REG_2, (s32)x.b));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				   BPF_REG_6, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				   BPF_REG_6, BPF_REG_2, JMP_TO(exit_pos)));
+	} else {
+		emit(BPF_LD_IMM64(BPF_REG_1, x.a));
+		emit(BPF_LD_IMM64(BPF_REG_2, x.b));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				 BPF_REG_6, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				 BPF_REG_6, BPF_REG_2, JMP_TO(exit_pos)));
+	}
+	/* ; setup initial r7/w7 possible value range ([y.a, y.b])
+	 * r1 = %[y.a] ll;        | w1 = %[y.a];
+	 * r2 = %[y.b] ll;        | w2 = %[y.b];
+	 * if r7 < r1 goto out;   | if w7 < w1 goto out;
+	 * if r7 > r2 goto out;   | if w7 > w2 goto out;
+	 */
+	if (spec.setup_subregs) {
+		emit(BPF_MOV32_IMM(BPF_REG_1, (s32)y.a));
+		emit(BPF_MOV32_IMM(BPF_REG_2, (s32)y.b));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				   BPF_REG_7, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				   BPF_REG_7, BPF_REG_2, JMP_TO(exit_pos)));
+	} else {
+		emit(BPF_LD_IMM64(BPF_REG_1, y.a));
+		emit(BPF_LD_IMM64(BPF_REG_2, y.b));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				 BPF_REG_7, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				 BPF_REG_7, BPF_REG_2, JMP_TO(exit_pos)));
+	}
+	/* ; range test instruction
+	 * if r6 <op> r7 goto +3; | if w6 <op> w7 goto +3;
+	 */
+	switch (op) {
+	case OP_LT: op_code = spec.compare_signed ? BPF_JSLT : BPF_JLT; break;
+	case OP_LE: op_code = spec.compare_signed ? BPF_JSLE : BPF_JLE; break;
+	case OP_GT: op_code = spec.compare_signed ? BPF_JSGT : BPF_JGT; break;
+	case OP_GE: op_code = spec.compare_signed ? BPF_JSGE : BPF_JGE; break;
+	case OP_EQ: op_code = BPF_JEQ; break;
+	case OP_NE: op_code = BPF_JNE; break;
+	default:
+		printf("unrecognized op %d\n", op);
+		return -ENOTSUP;
+	}
+	/* ; BEFORE conditional, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably
+	 * ; this is used for debugging, as verifier doesn't always print
+	 * ; registers states as of condition jump instruction (e.g., when
+	 * ; precision marking happens)
+	 * r0 = r6;               | w0 = w6;
+	 * r0 = r7;               | w0 = w7;
+	 */
+	if (spec.compare_subregs) {
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7));
+	} else {
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	}
+	if (spec.compare_subregs)
+		emit(BPF_JMP32_REG(op_code, BPF_REG_6, BPF_REG_7, 3));
+	else
+		emit(BPF_JMP_REG(op_code, BPF_REG_6, BPF_REG_7, 3));
+	/* ; FALSE branch, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably
+	 * r0 = r6;               | w0 = w6;
+	 * r0 = r7;               | w0 = w7;
+	 * exit;
+	 */
+	*false_pos = cur_pos;
+	if (spec.compare_subregs) {
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7));
+	} else {
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	}
+	if (branch_taken == 1) /* false branch is never taken */
+		emit(BPF_EMIT_CALL(0xDEAD)); /* poison this branch */
+	else
+		emit(BPF_EXIT_INSN());
+	/* ; TRUE branch, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably
+	 * r0 = r6;               | w0 = w6;
+	 * r0 = r7;               | w0 = w7;
+	 * exit;
+	 */
+	*true_pos = cur_pos;
+	if (spec.compare_subregs) {
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7));
+	} else {
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	}
+	if (branch_taken == 0) /* true branch is never taken */
+		emit(BPF_EMIT_CALL(0xDEAD)); /* poison this branch */
+	emit(BPF_EXIT_INSN()); /* last instruction has to be exit */
+
+	fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT, "reg_bounds_test",
+			   "GPL", insns, cur_pos, &opts);
+	if (fd < 0)
+		return fd;
+
+	close(fd);
+	return 0;
+#undef emit
+#undef JMP_TO
+}
+
+#define str_has_pfx(str, pfx) (strncmp(str, pfx, strlen(pfx)) == 0)
+
+/* Parse register state from verifier log.
+ * `s` should point to the start of "Rx = ..." substring in the verifier log.
+ */
+static int parse_reg_state(const char *s, struct reg_state *reg)
+{
+	/* There are two generic forms for SCALAR register:
+	 * - known constant: R6_rwD=P%lld
+	 * - range: R6_rwD=scalar(id=1,...), where "..." is a comma-separated
+	 *   list of optional range specifiers:
+	 *     - umin=%llu, if missing, assumed 0;
+	 *     - umax=%llu, if missing, assumed U64_MAX;
+	 *     - smin=%lld, if missing, assumed S64_MIN;
+	 *     - smax=%lld, if missing, assummed S64_MAX;
+	 *     - umin32=%d, if missing, assumed 0;
+	 *     - umax32=%d, if missing, assumed U32_MAX;
+	 *     - smin32=%d, if missing, assumed S32_MIN;
+	 *     - smax32=%d, if missing, assummed S32_MAX;
+	 *     - var_off=(%#llx; %#llx), tnum part, we don't care about it.
+	 *
+	 * If some of the values are equal, they will be grouped (but min/max
+	 * are not mixed together, and similarly negative values are not
+	 * grouped with non-negative ones). E.g.:
+	 *
+	 *   R6_w=Pscalar(smin=smin32=0, smax=umax=umax32=1000)
+	 *
+	 * _rwD part is optional (and any of the letters can be missing).
+	 * P (precision mark) is optional as well.
+	 *
+	 * Anything inside scalar() is optional, including id, of course.
+	 */
+	struct {
+		const char *pfx;
+		u64 *dst, def;
+		bool is_32, is_set;
+	} *f, fields[8] = {
+		{"smin=", &reg->r[S64].a, S64_MIN},
+		{"smax=", &reg->r[S64].b, S64_MAX},
+		{"umin=", &reg->r[U64].a, 0},
+		{"umax=", &reg->r[U64].b, U64_MAX},
+		{"smin32=", &reg->r[S32].a, (u32)S32_MIN, true},
+		{"smax32=", &reg->r[S32].b, (u32)S32_MAX, true},
+		{"umin32=", &reg->r[U32].a, 0,            true},
+		{"umax32=", &reg->r[U32].b, U32_MAX,      true},
+	};
+	const char *p;
+	int i;
+
+	p = strchr(s, '=');
+	if (!p)
+		return -EINVAL;
+	p++;
+	if (*p == 'P')
+		p++;
+
+	if (!str_has_pfx(p, "scalar(")) {
+		long long sval;
+		enum num_t t;
+
+		if (p[0] == '0' && p[1] == 'x') {
+			if (sscanf(p, "%llx", &sval) != 1)
+				return -EINVAL;
+		} else {
+			if (sscanf(p, "%lld", &sval) != 1)
+				return -EINVAL;
+		}
+
+		reg->valid = true;
+		for (t = first_t; t <= last_t; t++) {
+			reg->r[t] = range(t, sval, sval);
+		}
+		return 0;
+	}
+
+	p += sizeof("scalar");
+	while (p) {
+		int midxs[ARRAY_SIZE(fields)], mcnt = 0;
+		u64 val;
+
+		for (i = 0; i < ARRAY_SIZE(fields); i++) {
+			f = &fields[i];
+			if (!str_has_pfx(p, f->pfx))
+				continue;
+			midxs[mcnt++] = i;
+			p += strlen(f->pfx);
+		}
+
+		if (mcnt) {
+			/* populate all matched fields */
+			if (p[0] == '0' && p[1] == 'x') {
+				if (sscanf(p, "%llx", &val) != 1)
+					return -EINVAL;
+			} else {
+				if (sscanf(p, "%lld", &val) != 1)
+					return -EINVAL;
+			}
+
+			for (i = 0; i < mcnt; i++) {
+				f = &fields[midxs[i]];
+				f->is_set = true;
+				*f->dst = f->is_32 ? (u64)(u32)val : val;
+			}
+		} else if (str_has_pfx(p, "var_off")) {
+			/* skip "var_off=(0x0; 0x3f)" part completely */
+			p = strchr(p, ')');
+			if (!p)
+				return -EINVAL;
+			p++;
+		}
+
+		p = strpbrk(p, ",)");
+		if (*p == ')')
+			break;
+		if (p)
+			p++;
+	}
+
+	reg->valid = true;
+
+	for (i = 0; i < ARRAY_SIZE(fields); i++) {
+		f = &fields[i];
+		if (!f->is_set)
+			*f->dst = f->def;
+	}
+
+	return 0;
+}
+
+
+/* Parse all register states (TRUE/FALSE branches and DST/SRC registers)
+ * out of the verifier log for a corresponding test case BPF program.
+ */
+static int parse_range_cmp_log(const char *log_buf, struct case_spec spec,
+			       int false_pos, int true_pos,
+			       struct reg_state *false1_reg, struct reg_state *false2_reg,
+			       struct reg_state *true1_reg, struct reg_state *true2_reg)
+{
+	struct {
+		int insn_idx;
+		int reg_idx;
+		const char *reg_upper;
+		struct reg_state *state;
+	} specs[] = {
+		{false_pos,     6, "R6=", false1_reg},
+		{false_pos + 1, 7, "R7=", false2_reg},
+		{true_pos,      6, "R6=", true1_reg},
+		{true_pos + 1,  7, "R7=", true2_reg},
+	};
+	char buf[32];
+	const char *p = log_buf, *q;
+	int i, err;
+
+	for (i = 0; i < 4; i++) {
+		sprintf(buf, "%d: (%s) %s = %s%d", specs[i].insn_idx,
+			spec.compare_subregs ? "bc" : "bf",
+			spec.compare_subregs ? "w0" : "r0",
+			spec.compare_subregs ? "w" : "r", specs[i].reg_idx);
+
+		q = strstr(p, buf);
+		if (!q) {
+			*specs[i].state = (struct reg_state){.valid = false};
+			continue;
+		}
+		p = strstr(q, specs[i].reg_upper);
+		if (!p)
+			return -EINVAL;
+		err = parse_reg_state(p, specs[i].state);
+		if (err)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+/* Validate ranges match, and print details if they don't */
+static bool assert_range_eq(enum num_t t, struct range x, struct range y,
+			    const char *ctx1, const char *ctx2)
+{
+	DEFINE_STRBUF(sb, 512);
+
+	if (range_eq(x, y))
+		return true;
+
+	snappendf(sb, "MISMATCH %s.%s: ", ctx1, ctx2);
+	snprintf_range(t, sb, x);
+	snappendf(sb, " != ");
+	snprintf_range(t, sb, y);
+
+	printf("%s\n", sb->buf);
+
+	return false;
+}
+
+/* Validate that register states match, and print details if they don't */
+static bool assert_reg_state_eq(struct reg_state *r, struct reg_state *e, const char *ctx)
+{
+	bool ok = true;
+	enum num_t t;
+
+	if (r->valid != e->valid) {
+		printf("MISMATCH %s: actual %s != expected %s\n", ctx,
+		       r->valid ? "<valid>" : "<invalid>",
+		       e->valid ? "<valid>" : "<invalid>");
+		return false;
+	}
+
+	if (!r->valid)
+		return true;
+
+	for (t = first_t; t <= last_t; t++) {
+		if (!assert_range_eq(t, r->r[t], e->r[t], ctx, t_str(t)))
+			ok = false;
+	}
+
+	return ok;
+}
+
+/* Printf verifier log, filtering out irrelevant noise */
+static void print_verifier_log(const char *buf)
+{
+	const char *p;
+
+	while (buf[0]) {
+		p = strchrnul(buf, '\n');
+
+		/* filter out irrelevant precision backtracking logs */
+		if (str_has_pfx(buf, "mark_precise: "))
+			goto skip_line;
+
+		printf("%.*s\n", (int)(p - buf), buf);
+
+skip_line:
+		buf = *p == '\0' ? p : p + 1;
+	}
+}
+
+/* Simulate provided test case purely with our own range-based logic.
+ * This is done to set up expectations for verifier's branch_taken logic and
+ * verifier's register states in the verifier log.
+ */
+static void sim_case(enum num_t init_t, enum num_t cond_t,
+		     struct range x, struct range y, enum op op,
+		     struct reg_state *fr1, struct reg_state *fr2,
+		     struct reg_state *tr1, struct reg_state *tr2,
+		     int *branch_taken)
+{
+	const u64 A = x.a;
+	const u64 B = x.b;
+	const u64 C = y.a;
+	const u64 D = y.b;
+	struct reg_state rc;
+	enum op rev_op = complement_op(op);
+	enum num_t t;
+
+	fr1->valid = fr2->valid = true;
+	tr1->valid = tr2->valid = true;
+	for (t = first_t; t <= last_t; t++) {
+		/* if we are initializing using 32-bit subregisters,
+		 * full registers get upper 32 bits zeroed automatically
+		 */
+		struct range z = t_is_32(init_t) ? unkn_subreg(t) : unkn[t];
+
+		fr1->r[t] = fr2->r[t] = tr1->r[t] = tr2->r[t] = z;
+	}
+
+	/* step 1: r1 >= A, r2 >= C */
+	reg_state_set_const(&rc, init_t, A);
+	reg_state_cond(init_t, fr1, &rc, OP_GE, fr1, NULL, "r1>=A");
+	reg_state_set_const(&rc, init_t, C);
+	reg_state_cond(init_t, fr2, &rc, OP_GE, fr2, NULL, "r2>=C");
+	*tr1 = *fr1;
+	*tr2 = *fr2;
+	if (env.verbosity >= VERBOSE_VERY) {
+		printf("STEP1 (%s) R1: ", t_str(init_t)); print_reg_state(fr1, "\n");
+		printf("STEP1 (%s) R2: ", t_str(init_t)); print_reg_state(fr2, "\n");
+	}
+
+	/* step 2: r1 <= B, r2 <= D */
+	reg_state_set_const(&rc, init_t, B);
+	reg_state_cond(init_t, fr1, &rc, OP_LE, fr1, NULL, "r1<=B");
+	reg_state_set_const(&rc, init_t, D);
+	reg_state_cond(init_t, fr2, &rc, OP_LE, fr2, NULL, "r2<=D");
+	*tr1 = *fr1;
+	*tr2 = *fr2;
+	if (env.verbosity >= VERBOSE_VERY) {
+		printf("STEP2 (%s) R1: ", t_str(init_t)); print_reg_state(fr1, "\n");
+		printf("STEP2 (%s) R2: ", t_str(init_t)); print_reg_state(fr2, "\n");
+	}
+
+	/* step 3: r1 <op> r2 */
+	*branch_taken = reg_state_branch_taken_op(cond_t, fr1, fr2, op);
+	fr1->valid = fr2->valid = false;
+	tr1->valid = tr2->valid = false;
+	if (*branch_taken != 1) { /* FALSE is possible */
+		fr1->valid = fr2->valid = true;
+		reg_state_cond(cond_t, fr1, fr2, rev_op, fr1, fr2, "FALSE");
+	}
+	if (*branch_taken != 0) { /* TRUE is possible */
+		tr1->valid = tr2->valid = true;
+		reg_state_cond(cond_t, tr1, tr2, op, tr1, tr2, "TRUE");
+	}
+	if (env.verbosity >= VERBOSE_VERY) {
+		printf("STEP3 (%s) FALSE R1:", t_str(cond_t)); print_reg_state(fr1, "\n");
+		printf("STEP3 (%s) FALSE R2:", t_str(cond_t)); print_reg_state(fr2, "\n");
+		printf("STEP3 (%s) TRUE  R1:", t_str(cond_t)); print_reg_state(tr1, "\n");
+		printf("STEP3 (%s) TRUE  R2:", t_str(cond_t)); print_reg_state(tr2, "\n");
+	}
+}
+
+/* ===============================
+ * HIGH-LEVEL TEST CASE VALIDATION
+ * ===============================
+ */
+static u32 upper_seeds[] = {
+	0,
+	1,
+	U32_MAX,
+	U32_MAX - 1,
+	S32_MAX,
+	(u32)S32_MIN,
+};
+
+static u32 lower_seeds[] = {
+	0,
+	1,
+	2, (u32)-2,
+	255, (u32)-255,
+	UINT_MAX,
+	UINT_MAX - 1,
+	INT_MAX,
+	(u32)INT_MIN,
+};
+
+struct ctx {
+	int val_cnt, subval_cnt, range_cnt, subrange_cnt;
+	u64 uvals[ARRAY_SIZE(upper_seeds) * ARRAY_SIZE(lower_seeds)];
+	s64 svals[ARRAY_SIZE(upper_seeds) * ARRAY_SIZE(lower_seeds)];
+	u32 usubvals[ARRAY_SIZE(lower_seeds)];
+	s32 ssubvals[ARRAY_SIZE(lower_seeds)];
+	struct range *uranges, *sranges;
+	struct range *usubranges, *ssubranges;
+	int max_failure_cnt, cur_failure_cnt;
+	int total_case_cnt, case_cnt;
+	int rand_case_cnt;
+	unsigned rand_seed;
+	__u64 start_ns;
+	char progress_ctx[64];
+};
+
+static void cleanup_ctx(struct ctx *ctx)
+{
+	free(ctx->uranges);
+	free(ctx->sranges);
+	free(ctx->usubranges);
+	free(ctx->ssubranges);
+}
+
+struct subtest_case {
+	enum num_t init_t;
+	enum num_t cond_t;
+	struct range x;
+	struct range y;
+	enum op op;
+};
+
+static void subtest_case_str(struct strbuf *sb, struct subtest_case *t, bool use_op)
+{
+	snappendf(sb, "(%s)", t_str(t->init_t));
+	snprintf_range(t->init_t, sb, t->x);
+	snappendf(sb, " (%s)%s ", t_str(t->cond_t), use_op ? op_str(t->op) : "<op>");
+	snprintf_range(t->init_t, sb, t->y);
+}
+
+/* Generate and validate test case based on specific combination of setup
+ * register ranges (including their expected num_t domain), and conditional
+ * operation to perform (including num_t domain in which it has to be
+ * performed)
+ */
+static int verify_case_op(enum num_t init_t, enum num_t cond_t,
+			  struct range x, struct range y, enum op op)
+{
+	char log_buf[256 * 1024];
+	size_t log_sz = sizeof(log_buf);
+	int err, false_pos = 0, true_pos = 0, branch_taken;
+	struct reg_state fr1, fr2, tr1, tr2;
+	struct reg_state fe1, fe2, te1, te2;
+	bool failed = false;
+	struct case_spec spec = {
+		.init_subregs = (init_t == U32 || init_t == S32),
+		.setup_subregs = (init_t == U32 || init_t == S32),
+		.setup_signed = (init_t == S64 || init_t == S32),
+		.compare_subregs = (cond_t == U32 || cond_t == S32),
+		.compare_signed = (cond_t == S64 || cond_t == S32),
+	};
+
+	log_buf[0] = '\0';
+
+	sim_case(init_t, cond_t, x, y, op, &fe1, &fe2, &te1, &te2, &branch_taken);
+
+	err = load_range_cmp_prog(x, y, op, branch_taken, spec,
+				  log_buf, log_sz, &false_pos, &true_pos);
+	if (err) {
+		ASSERT_OK(err, "load_range_cmp_prog");
+		failed = true;
+	}
+
+	err = parse_range_cmp_log(log_buf, spec, false_pos, true_pos,
+				  &fr1, &fr2, &tr1, &tr2);
+	if (err) {
+		ASSERT_OK(err, "parse_range_cmp_log");
+		failed = true;
+	}
+
+	if (!assert_reg_state_eq(&fr1, &fe1, "false_reg1") ||
+	    !assert_reg_state_eq(&fr2, &fe2, "false_reg2") ||
+	    !assert_reg_state_eq(&tr1, &te1, "true_reg1") ||
+	    !assert_reg_state_eq(&tr2, &te2, "true_reg2")) {
+		failed = true;
+	}
+
+	if (failed || env.verbosity >= VERBOSE_NORMAL) {
+		if (failed || env.verbosity >= VERBOSE_VERY) {
+			printf("VERIFIER LOG:\n========================\n");
+			print_verifier_log(log_buf);
+			printf("=====================\n");
+		}
+		printf("ACTUAL   FALSE1: "); print_reg_state(&fr1, "\n");
+		printf("EXPECTED FALSE1: "); print_reg_state(&fe1, "\n");
+		printf("ACTUAL   FALSE2: "); print_reg_state(&fr2, "\n");
+		printf("EXPECTED FALSE2: "); print_reg_state(&fe2, "\n");
+		printf("ACTUAL   TRUE1:  "); print_reg_state(&tr1, "\n");
+		printf("EXPECTED TRUE1:  "); print_reg_state(&te1, "\n");
+		printf("ACTUAL   TRUE2:  "); print_reg_state(&tr2, "\n");
+		printf("EXPECTED TRUE2:  "); print_reg_state(&te2, "\n");
+
+		return failed ? -EINVAL : 0;
+	}
+
+	return 0;
+}
+
+/* Given setup ranges and number types, go over all supported operations,
+ * generating individual subtest for each allowed combination
+ */
+static int verify_case_opt(struct ctx *ctx, enum num_t init_t, enum num_t cond_t,
+			   struct range x, struct range y, bool is_subtest)
+{
+	DEFINE_STRBUF(sb, 256);
+	int err;
+	struct subtest_case sub = {
+		.init_t = init_t,
+		.cond_t = cond_t,
+		.x = x,
+		.y = y,
+	};
+
+	sb->pos = 0; /* reset position in strbuf */
+	subtest_case_str(sb, &sub, false /* ignore op */);
+	if (is_subtest && !test__start_subtest(sb->buf))
+		return 0;
+
+	for (sub.op = first_op; sub.op <= last_op; sub.op++) {
+		sb->pos = 0; /* reset position in strbuf */
+		subtest_case_str(sb, &sub, true /* print op */);
+
+		if (env.verbosity >= VERBOSE_NORMAL) /* this speeds up debugging */
+			printf("TEST CASE: %s\n", sb->buf);
+
+		err = verify_case_op(init_t, cond_t, x, y, sub.op);
+		if (err || env.verbosity >= VERBOSE_NORMAL)
+			ASSERT_OK(err, sb->buf);
+		if (err) {
+			ctx->cur_failure_cnt++;
+			if (ctx->cur_failure_cnt > ctx->max_failure_cnt)
+				return err;
+			return 0; /* keep testing other cases */
+		}
+		ctx->case_cnt++;
+		if ((ctx->case_cnt % 10000) == 0) {
+			double progress = (ctx->case_cnt + 0.0) / ctx->total_case_cnt;
+			u64 elapsed_ns = get_time_ns() - ctx->start_ns;
+			double remain_ns = elapsed_ns / progress * (1 - progress);
+
+			fprintf(env.stderr, "PROGRESS (%s): %d/%d (%.2lf%%), "
+					    "elapsed %llu mins (%.2lf hrs), "
+					    "ETA %.0lf mins (%.2lf hrs)\n",
+				ctx->progress_ctx,
+				ctx->case_cnt, ctx->total_case_cnt, 100.0 * progress,
+				elapsed_ns / 1000000000 / 60,
+				elapsed_ns / 1000000000.0 / 3600,
+				remain_ns / 1000000000.0 / 60,
+				remain_ns / 1000000000.0 / 3600);
+		}
+	}
+
+	return 0;
+}
+
+static int verify_case(struct ctx *ctx, enum num_t init_t, enum num_t cond_t,
+		       struct range x, struct range y)
+{
+	return verify_case_opt(ctx, init_t, cond_t, x, y, true /* is_subtest */);
+}
+
+/* ================================
+ * GENERATED CASES FROM SEED VALUES
+ * ================================
+ */
+static int u64_cmp(const void *p1, const void *p2)
+{
+	u64 x1 = *(const u64 *)p1, x2 = *(const u64 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+static int u32_cmp(const void *p1, const void *p2)
+{
+	u32 x1 = *(const u32 *)p1, x2 = *(const u32 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+static int s64_cmp(const void *p1, const void *p2)
+{
+	s64 x1 = *(const s64 *)p1, x2 = *(const s64 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+static int s32_cmp(const void *p1, const void *p2)
+{
+	s32 x1 = *(const s32 *)p1, x2 = *(const s32 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+/* Generate valid unique constants from seeds, both signed and unsigned */
+static void gen_vals(struct ctx *ctx)
+{
+	int i, j, cnt = 0;
+
+	for (i = 0; i < ARRAY_SIZE(upper_seeds); i++) {
+		for (j = 0; j < ARRAY_SIZE(lower_seeds); j++) {
+			ctx->uvals[cnt++] = (((u64)upper_seeds[i]) << 32) | lower_seeds[j];
+		}
+	}
+
+	/* sort and compact uvals (i.e., it's `sort | uniq`) */
+	qsort(ctx->uvals, cnt, sizeof(*ctx->uvals), u64_cmp);
+	for (i = 1, j = 0; i < cnt; i++) {
+		if (ctx->uvals[j] == ctx->uvals[i])
+			continue;
+		j++;
+		ctx->uvals[j] = ctx->uvals[i];
+	}
+	ctx->val_cnt = j + 1;
+
+	/* we have exactly the same number of s64 values, they are just in
+	 * a different order than u64s, so just sort them differently
+	 */
+	for (i = 0; i < ctx->val_cnt; i++)
+		ctx->svals[i] = ctx->uvals[i];
+	qsort(ctx->svals, ctx->val_cnt, sizeof(*ctx->svals), s64_cmp);
+
+	if (env.verbosity >= VERBOSE_SUPER) {
+		DEFINE_STRBUF(sb1, 256);
+		DEFINE_STRBUF(sb2, 256);
+
+		for (i = 0; i < ctx->val_cnt; i++) {
+			sb1->pos = sb2->pos = 0;
+			snprintf_num(U64, sb1, ctx->uvals[i]);
+			snprintf_num(S64, sb2, ctx->svals[i]);
+			printf("SEED #%d: u64=%-20s s64=%-20s\n", i, sb1->buf, sb2->buf);
+		}
+	}
+
+	/* 32-bit values are generated separately */
+	cnt = 0;
+	for (i = 0; i < ARRAY_SIZE(lower_seeds); i++) {
+		ctx->usubvals[cnt++] = lower_seeds[i];
+	}
+
+	/* sort and compact usubvals (i.e., it's `sort | uniq`) */
+	qsort(ctx->usubvals, cnt, sizeof(*ctx->usubvals), u32_cmp);
+	for (i = 1, j = 0; i < cnt; i++) {
+		if (ctx->usubvals[j] == ctx->usubvals[i])
+			continue;
+		j++;
+		ctx->usubvals[j] = ctx->usubvals[i];
+	}
+	ctx->subval_cnt = j + 1;
+
+	for (i = 0; i < ctx->subval_cnt; i++)
+		ctx->ssubvals[i] = ctx->usubvals[i];
+	qsort(ctx->ssubvals, ctx->subval_cnt, sizeof(*ctx->ssubvals), s32_cmp);
+
+	if (env.verbosity >= VERBOSE_SUPER) {
+		DEFINE_STRBUF(sb1, 256);
+		DEFINE_STRBUF(sb2, 256);
+
+		for (i = 0; i < ctx->subval_cnt; i++) {
+			sb1->pos = sb2->pos = 0;
+			snprintf_num(U32, sb1, ctx->usubvals[i]);
+			snprintf_num(S32, sb2, ctx->ssubvals[i]);
+			printf("SUBSEED #%d: u32=%-10s s32=%-10s\n", i, sb1->buf, sb2->buf);
+		}
+	}
+}
+
+/* Generate valid ranges from upper/lower seeds */
+static int gen_ranges(struct ctx *ctx)
+{
+	int i, j, cnt = 0;
+
+	for (i = 0; i < ctx->val_cnt; i++) {
+		for (j = i; j < ctx->val_cnt; j++) {
+			if (env.verbosity >= VERBOSE_SUPER) {
+				DEFINE_STRBUF(sb1, 256);
+				DEFINE_STRBUF(sb2, 256);
+
+				sb1->pos = sb2->pos = 0;
+				snprintf_range(U64, sb1, range(U64, ctx->uvals[i], ctx->uvals[j]));
+				snprintf_range(S64, sb2, range(S64, ctx->svals[i], ctx->svals[j]));
+				printf("RANGE #%d: u64=%-40s s64=%-40s\n", cnt, sb1->buf, sb2->buf);
+			}
+			cnt++;
+		}
+	}
+	ctx->range_cnt = cnt;
+
+	ctx->uranges = calloc(ctx->range_cnt, sizeof(*ctx->uranges));
+	if (!ASSERT_OK_PTR(ctx->uranges, "uranges_calloc"))
+		return -EINVAL;
+	ctx->sranges = calloc(ctx->range_cnt, sizeof(*ctx->sranges));
+	if (!ASSERT_OK_PTR(ctx->sranges, "sranges_calloc"))
+		return -EINVAL;
+
+	cnt = 0;
+	for (i = 0; i < ctx->val_cnt; i++) {
+		for (j = i; j < ctx->val_cnt; j++) {
+			ctx->uranges[cnt] = range(U64, ctx->uvals[i], ctx->uvals[j]);
+			ctx->sranges[cnt] = range(S64, ctx->svals[i], ctx->svals[j]);
+			cnt++;
+		}
+	}
+
+	cnt = 0;
+	for (i = 0; i < ctx->subval_cnt; i++) {
+		for (j = i; j < ctx->subval_cnt; j++) {
+			if (env.verbosity >= VERBOSE_SUPER) {
+				DEFINE_STRBUF(sb1, 256);
+				DEFINE_STRBUF(sb2, 256);
+
+				sb1->pos = sb2->pos = 0;
+				snprintf_range(U32, sb1, range(U32, ctx->usubvals[i], ctx->usubvals[j]));
+				snprintf_range(S32, sb2, range(S32, ctx->ssubvals[i], ctx->ssubvals[j]));
+				printf("SUBRANGE #%d: u32=%-20s s32=%-20s\n", cnt, sb1->buf, sb2->buf);
+			}
+			cnt++;
+		}
+	}
+	ctx->subrange_cnt = cnt;
+
+	ctx->usubranges = calloc(ctx->subrange_cnt, sizeof(*ctx->usubranges));
+	if (!ASSERT_OK_PTR(ctx->usubranges, "usubranges_calloc"))
+		return -EINVAL;
+	ctx->ssubranges = calloc(ctx->subrange_cnt, sizeof(*ctx->ssubranges));
+	if (!ASSERT_OK_PTR(ctx->ssubranges, "ssubranges_calloc"))
+		return -EINVAL;
+
+	cnt = 0;
+	for (i = 0; i < ctx->subval_cnt; i++) {
+		for (j = i; j < ctx->subval_cnt; j++) {
+			ctx->usubranges[cnt] = range(U32, ctx->usubvals[i], ctx->usubvals[j]);
+			ctx->ssubranges[cnt] = range(S32, ctx->ssubvals[i], ctx->ssubvals[j]);
+			cnt++;
+		}
+	}
+
+	return 0;
+}
+
+static int parse_env_vars(struct ctx *ctx)
+{
+	const char *s;
+
+	if ((s = getenv("REG_BOUNDS_MAX_FAILURE_CNT"))) {
+		errno = 0;
+		ctx->max_failure_cnt = strtol(s, NULL, 10);
+		if (errno || ctx->max_failure_cnt < 0) {
+			ASSERT_OK(-errno, "REG_BOUNDS_MAX_FAILURE_CNT");
+			return -EINVAL;
+		}
+	}
+
+	if ((s = getenv("REG_BOUNDS_RAND_CASE_CNT"))) {
+		errno = 0;
+		ctx->rand_case_cnt = strtol(s, NULL, 10);
+		if (errno || ctx->rand_case_cnt < 0) {
+			ASSERT_OK(-errno, "REG_BOUNDS_RAND_CASE_CNT");
+			return -EINVAL;
+		}
+	}
+
+	if ((s = getenv("REG_BOUNDS_RAND_SEED"))) {
+		errno = 0;
+		ctx->rand_seed = strtoul(s, NULL, 10);
+		if (errno) {
+			ASSERT_OK(-errno, "REG_BOUNDS_RAND_SEED");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int prepare_gen_tests(struct ctx *ctx)
+{
+	const char *s;
+	int err;
+
+	if (!(s = getenv("SLOW_TESTS")) || strcmp(s, "1") != 0) {
+		test__skip();
+		return -ENOTSUP;
+	}
+
+	err = parse_env_vars(ctx);
+	if (err)
+		return err;
+
+	gen_vals(ctx);
+	err = gen_ranges(ctx);
+	if (err) {
+		ASSERT_OK(err, "gen_ranges");
+		return err;
+	}
+
+	return 0;
+}
+
+/* Go over generated constants and ranges and validate various supported
+ * combinations of them
+ */
+static void validate_gen_range_vs_const_64(enum num_t init_t, enum num_t cond_t)
+{
+	struct ctx ctx;
+	struct range rconst;
+	const struct range *ranges;
+	const u64 *vals;
+	int i, j;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	if (prepare_gen_tests(&ctx))
+		goto cleanup;
+
+	ranges = init_t == U64 ? ctx.uranges : ctx.sranges;
+	vals = init_t == U64 ? ctx.uvals : (const u64 *)ctx.svals;
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.range_cnt * ctx.val_cnt);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "RANGE x CONST, %s -> %s",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < ctx.val_cnt; i++) {
+		for (j = 0; j < ctx.range_cnt; j++) {
+			rconst = range(init_t, vals[i], vals[i]);
+
+			/* (u64|s64)(<range> x <const>) */
+			if (verify_case(&ctx, init_t, cond_t, ranges[j], rconst))
+				goto cleanup;
+			/* (u64|s64)(<const> x <range>) */
+			if (verify_case(&ctx, init_t, cond_t, rconst, ranges[j]))
+				goto cleanup;
+		}
+	}
+
+cleanup:
+	cleanup_ctx(&ctx);
+}
+
+static void validate_gen_range_vs_const_32(enum num_t init_t, enum num_t cond_t)
+{
+	struct ctx ctx;
+	struct range rconst;
+	const struct range *ranges;
+	const u32 *vals;
+	int i, j;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	if (prepare_gen_tests(&ctx))
+		goto cleanup;
+
+	ranges = init_t == U32 ? ctx.usubranges : ctx.ssubranges;
+	vals = init_t == U32 ? ctx.usubvals : (const u32 *)ctx.ssubvals;
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.subrange_cnt * ctx.subval_cnt);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "RANGE x CONST, %s -> %s",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < ctx.subval_cnt; i++) {
+		for (j = 0; j < ctx.subrange_cnt; j++) {
+			rconst = range(init_t, vals[i], vals[i]);
+
+			/* (u32|s32)(<range> x <const>) */
+			if (verify_case(&ctx, init_t, cond_t, ranges[j], rconst))
+				goto cleanup;
+			/* (u32|s32)(<const> x <range>) */
+			if (verify_case(&ctx, init_t, cond_t, rconst, ranges[j]))
+				goto cleanup;
+		}
+	}
+
+cleanup:
+	cleanup_ctx(&ctx);
+}
+
+static void validate_gen_range_vs_range(enum num_t init_t, enum num_t cond_t)
+{
+	struct ctx ctx;
+	const struct range *ranges;
+	int i, j, rcnt;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	if (prepare_gen_tests(&ctx))
+		goto cleanup;
+
+	switch (init_t)
+	{
+	case U64:
+		ranges = ctx.uranges;
+		rcnt = ctx.range_cnt;
+		break;
+	case U32:
+		ranges = ctx.usubranges;
+		rcnt = ctx.subrange_cnt;
+		break;
+	case S64:
+		ranges = ctx.sranges;
+		rcnt = ctx.range_cnt;
+		break;
+	case S32:
+		ranges = ctx.ssubranges;
+		rcnt = ctx.subrange_cnt;
+		break;
+	default:
+		printf("validate_gen_range_vs_range!\n");
+		exit(1);
+	}
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * rcnt * (rcnt + 1) / 2);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "RANGE x RANGE, %s -> %s",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < rcnt; i++) {
+		for (j = i; j < rcnt; j++) {
+			/* (<range> x <range>) */
+			if (verify_case(&ctx, init_t, cond_t, ranges[i], ranges[j]))
+				goto cleanup;
+			if (verify_case(&ctx, init_t, cond_t, ranges[j], ranges[i]))
+				goto cleanup;
+		}
+	}
+
+cleanup:
+	cleanup_ctx(&ctx);
+}
+
+/* Go over thousands of test cases generated from initial seed values.
+ * Given this take a long time, guard this begind SLOW_TESTS=1 envvar. If
+ * envvar is not set, this test is skipped during test_progs testing.
+ *
+ * We split this up into smaller subsets based on initialization and
+ * conditiona numeric domains to get an easy parallelization with test_progs'
+ * -j argument.
+ */
+
+/* RANGE x CONST, U64 initial range */
+void test_reg_bounds_gen_consts_u64_u64(void) { validate_gen_range_vs_const_64(U64, U64); }
+void test_reg_bounds_gen_consts_u64_s64(void) { validate_gen_range_vs_const_64(U64, S64); }
+void test_reg_bounds_gen_consts_u64_u32(void) { validate_gen_range_vs_const_64(U64, U32); }
+void test_reg_bounds_gen_consts_u64_s32(void) { validate_gen_range_vs_const_64(U64, S32); }
+/* RANGE x CONST, S64 initial range */
+void test_reg_bounds_gen_consts_s64_u64(void) { validate_gen_range_vs_const_64(S64, U64); }
+void test_reg_bounds_gen_consts_s64_s64(void) { validate_gen_range_vs_const_64(S64, S64); }
+void test_reg_bounds_gen_consts_s64_u32(void) { validate_gen_range_vs_const_64(S64, U32); }
+void test_reg_bounds_gen_consts_s64_s32(void) { validate_gen_range_vs_const_64(S64, S32); }
+/* RANGE x CONST, U32 initial range */
+void test_reg_bounds_gen_consts_u32_u64(void) { validate_gen_range_vs_const_32(U32, U64); }
+void test_reg_bounds_gen_consts_u32_s64(void) { validate_gen_range_vs_const_32(U32, S64); }
+void test_reg_bounds_gen_consts_u32_u32(void) { validate_gen_range_vs_const_32(U32, U32); }
+void test_reg_bounds_gen_consts_u32_s32(void) { validate_gen_range_vs_const_32(U32, S32); }
+/* RANGE x CONST, S32 initial range */
+void test_reg_bounds_gen_consts_s32_u64(void) { validate_gen_range_vs_const_32(S32, U64); }
+void test_reg_bounds_gen_consts_s32_s64(void) { validate_gen_range_vs_const_32(S32, S64); }
+void test_reg_bounds_gen_consts_s32_u32(void) { validate_gen_range_vs_const_32(S32, U32); }
+void test_reg_bounds_gen_consts_s32_s32(void) { validate_gen_range_vs_const_32(S32, S32); }
+
+/* RANGE x RANGE, U64 initial range */
+void test_reg_bounds_gen_ranges_u64_u64(void) { validate_gen_range_vs_range(U64, U64); }
+void test_reg_bounds_gen_ranges_u64_s64(void) { validate_gen_range_vs_range(U64, S64); }
+void test_reg_bounds_gen_ranges_u64_u32(void) { validate_gen_range_vs_range(U64, U32); }
+void test_reg_bounds_gen_ranges_u64_s32(void) { validate_gen_range_vs_range(U64, S32); }
+/* RANGE x RANGE, S64 initial range */
+void test_reg_bounds_gen_ranges_s64_u64(void) { validate_gen_range_vs_range(S64, U64); }
+void test_reg_bounds_gen_ranges_s64_s64(void) { validate_gen_range_vs_range(S64, S64); }
+void test_reg_bounds_gen_ranges_s64_u32(void) { validate_gen_range_vs_range(S64, U32); }
+void test_reg_bounds_gen_ranges_s64_s32(void) { validate_gen_range_vs_range(S64, S32); }
+/* RANGE x RANGE, U32 initial range */
+void test_reg_bounds_gen_ranges_u32_u64(void) { validate_gen_range_vs_range(U32, U64); }
+void test_reg_bounds_gen_ranges_u32_s64(void) { validate_gen_range_vs_range(U32, S64); }
+void test_reg_bounds_gen_ranges_u32_u32(void) { validate_gen_range_vs_range(U32, U32); }
+void test_reg_bounds_gen_ranges_u32_s32(void) { validate_gen_range_vs_range(U32, S32); }
+/* RANGE x RANGE, S32 initial range */
+void test_reg_bounds_gen_ranges_s32_u64(void) { validate_gen_range_vs_range(S32, U64); }
+void test_reg_bounds_gen_ranges_s32_s64(void) { validate_gen_range_vs_range(S32, S64); }
+void test_reg_bounds_gen_ranges_s32_u32(void) { validate_gen_range_vs_range(S32, U32); }
+void test_reg_bounds_gen_ranges_s32_s32(void) { validate_gen_range_vs_range(S32, S32); }
+
+#define DEFAULT_RAND_CASE_CNT 100
+
+#define RAND_21BIT_MASK ((1 << 22) - 1)
+
+static u64 rand_u64()
+{
+	/* RAND_MAX is guaranteed to be at least 1<<15, but in practice it
+	 * seems to be 1<<31, so we need to call it thrice to get full u64;
+	 * we'll use rougly equal split: 22 + 21 + 21 bits
+	 */
+	return ((u64)random() << 42) |
+	       (((u64)random() & RAND_21BIT_MASK) << 21) |
+	       (random() & RAND_21BIT_MASK);
+}
+
+static u64 rand_const(enum num_t t)
+{
+	return cast_t(t, rand_u64());
+}
+
+static struct range rand_range(enum num_t t)
+{
+	u64 x = rand_const(t), y = rand_const(t);
+
+	return range(t, min_t(t, x, y), max_t(t, x, y));
+}
+
+static void validate_rand_ranges(enum num_t init_t, enum num_t cond_t, bool const_range)
+{
+	struct ctx ctx;
+	struct range range1, range2;
+	int err, i;
+	u64 t;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	err = parse_env_vars(&ctx);
+	if (err) {
+		ASSERT_OK(err, "parse_env_vars");
+		return;
+	}
+
+	if (ctx.rand_case_cnt == 0)
+		ctx.rand_case_cnt = DEFAULT_RAND_CASE_CNT;
+	if (ctx.rand_seed == 0)
+		ctx.rand_seed = (unsigned)get_time_ns();
+
+	srandom(ctx.rand_seed);
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.rand_case_cnt);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "[RANDOM SEED %u] RANGE x %s, %s -> %s",
+		 ctx.rand_seed, const_range ? "CONST" : "RANGE",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < ctx.rand_case_cnt; i++) {
+		range1 = rand_range(init_t);
+		if (const_range) {
+			t = rand_const(init_t);
+			range2 = range(init_t, t, t);
+		} else {
+			range2 = rand_range(init_t);
+		}
+
+		/* <range1> x <range2> */
+		if (verify_case_opt(&ctx, init_t, cond_t, range1, range2, false /* !is_subtest */))
+			goto cleanup;
+		/* <range2> x <range1> */
+		if (verify_case_opt(&ctx, init_t, cond_t, range2, range1, false /* !is_subtest */))
+			goto cleanup;
+	}
+
+cleanup:
+	/* make sure we report random seed for reproducing */
+	ASSERT_TRUE(true, ctx.progress_ctx);
+	cleanup_ctx(&ctx);
+}
+
+/* [RANDOM] RANGE x CONST, U64 initial range */
+void test_reg_bounds_rand_consts_u64_u64(void) { validate_rand_ranges(U64, U64, true /* const */); }
+void test_reg_bounds_rand_consts_u64_s64(void) { validate_rand_ranges(U64, S64, true /* const */); }
+void test_reg_bounds_rand_consts_u64_u32(void) { validate_rand_ranges(U64, U32, true /* const */); }
+void test_reg_bounds_rand_consts_u64_s32(void) { validate_rand_ranges(U64, S32, true /* const */); }
+/* [RANDOM] RANGE x CONST, S64 initial range */
+void test_reg_bounds_rand_consts_s64_u64(void) { validate_rand_ranges(S64, U64, true /* const */); }
+void test_reg_bounds_rand_consts_s64_s64(void) { validate_rand_ranges(S64, S64, true /* const */); }
+void test_reg_bounds_rand_consts_s64_u32(void) { validate_rand_ranges(S64, U32, true /* const */); }
+void test_reg_bounds_rand_consts_s64_s32(void) { validate_rand_ranges(S64, S32, true /* const */); }
+/* [RANDOM] RANGE x CONST, U32 initial range */
+void test_reg_bounds_rand_consts_u32_u64(void) { validate_rand_ranges(U32, U64, true /* const */); }
+void test_reg_bounds_rand_consts_u32_s64(void) { validate_rand_ranges(U32, S64, true /* const */); }
+void test_reg_bounds_rand_consts_u32_u32(void) { validate_rand_ranges(U32, U32, true /* const */); }
+void test_reg_bounds_rand_consts_u32_s32(void) { validate_rand_ranges(U32, S32, true /* const */); }
+/* [RANDOM] RANGE x CONST, S32 initial range */
+void test_reg_bounds_rand_consts_s32_u64(void) { validate_rand_ranges(S32, U64, true /* const */); }
+void test_reg_bounds_rand_consts_s32_s64(void) { validate_rand_ranges(S32, S64, true /* const */); }
+void test_reg_bounds_rand_consts_s32_u32(void) { validate_rand_ranges(S32, U32, true /* const */); }
+void test_reg_bounds_rand_consts_s32_s32(void) { validate_rand_ranges(S32, S32, true /* const */); }
+
+/* [RANDOM] RANGE x RANGE, U64 initial range */
+void test_reg_bounds_rand_ranges_u64_u64(void) { validate_rand_ranges(U64, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_u64_s64(void) { validate_rand_ranges(U64, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_u64_u32(void) { validate_rand_ranges(U64, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_u64_s32(void) { validate_rand_ranges(U64, S32, false /* range */); }
+/* [RANDOM] RANGE x RANGE, S64 initial range */
+void test_reg_bounds_rand_ranges_s64_u64(void) { validate_rand_ranges(S64, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_s64_s64(void) { validate_rand_ranges(S64, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_s64_u32(void) { validate_rand_ranges(S64, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_s64_s32(void) { validate_rand_ranges(S64, S32, false /* range */); }
+/* [RANDOM] RANGE x RANGE, U32 initial range */
+void test_reg_bounds_rand_ranges_u32_u64(void) { validate_rand_ranges(U32, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_u32_s64(void) { validate_rand_ranges(U32, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_u32_u32(void) { validate_rand_ranges(U32, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_u32_s32(void) { validate_rand_ranges(U32, S32, false /* range */); }
+/* [RANDOM] RANGE x RANGE, S32 initial range */
+void test_reg_bounds_rand_ranges_s32_u64(void) { validate_rand_ranges(S32, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_s32_s64(void) { validate_rand_ranges(S32, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_s32_u32(void) { validate_rand_ranges(S32, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_s32_s32(void) { validate_rand_ranges(S32, S32, false /* range */); }
+
+/* A set of hard-coded "interesting" cases to validate as part of normal
+ * test_progs test runs
+ */
+static struct subtest_case crafted_cases[] = {
+	{U64, U64, {0, 0xffffffff}, {0, 0}},
+	{U64, U64, {0, 0x80000000}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x100000100ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x180000000ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x1ffffff00ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x1ffffff01ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x1fffffffeULL}, {0, 0}},
+	{U64, U64, {0x100000001ULL, 0x1000000ffULL}, {0, 0}},
+
+	/* single point overlap, interesting BPF_EQ and BPF_NE interactions */
+	{U64, U64, {0, 1}, {1, 0x80000000}},
+	{U64, S64, {0, 1}, {1, 0x80000000}},
+	{U64, U32, {0, 1}, {1, 0x80000000}},
+	{U64, S32, {0, 1}, {1, 0x80000000}},
+
+	{U64, S64, {0, 0xffffffff00000000ULL}, {0, 0}},
+	{U64, S64, {0x7fffffffffffffffULL, 0xffffffff00000000ULL}, {0, 0}},
+	{U64, S64, {0x7fffffff00000001ULL, 0xffffffff00000000ULL}, {0, 0}},
+	{U64, S64, {0, 0xffffffffULL}, {1, 1}},
+	{U64, S64, {0, 0xffffffffULL}, {0x7fffffff, 0x7fffffff}},
+
+	{U64, U32, {0, 0x100000000}, {0, 0}},
+	{U64, U32, {0xfffffffe, 0x100000000}, {0x80000000, 0x80000000}},
+
+	{U64, S32, {0, 0xffffffff00000000ULL}, {0, 0}},
+	/* these are tricky cases where lower 32 bits allow to tighten 64
+	 * bit boundaries based on tightened lower 32 bit boundaries
+	 */
+	{U64, S32, {0, 0x0ffffffffULL}, {0, 0}},
+	{U64, S32, {0, 0x100000000ULL}, {0, 0}},
+	{U64, S32, {0, 0x100000001ULL}, {0, 0}},
+	{U64, S32, {0, 0x180000000ULL}, {0, 0}},
+	{U64, S32, {0, 0x17fffffffULL}, {0, 0}},
+	{U64, S32, {0, 0x180000001ULL}, {0, 0}},
+
+	/* verifier knows about [-1, 0] range for s32 for this case already */
+	{S64, S64, {0xffffffffffffffffULL, 0}, {0xffffffff00000000ULL, 0xffffffff00000000ULL}},
+	/* but didn't know about these cases initially */
+	{U64, U64, {0xffffffff, 0x100000000ULL}, {0, 0}}, /* s32: [-1, 0] */
+	{U64, U64, {0xffffffff, 0x100000001ULL}, {0, 0}}, /* s32: [-1, 1] */
+
+	/* longer convergence case: learning from u64 -> s64 -> u64 -> u32,
+	 * arriving at u32: [1, U32_MAX] (instead of more pessimistic [0, U32_MAX])
+	 */
+	{S64, U64, {0xffffffff00000001ULL, 0}, {0xffffffff00000000ULL, 0xffffffff00000000ULL}},
+
+	{U32, U32, {1, U32_MAX}, {0, 0}},
+
+	{U32, S32, {0, U32_MAX}, {U32_MAX, U32_MAX}},
+
+	{S32, U64, {(u32)S32_MIN, (u32)S32_MIN}, {(u32)(s32)-255, 0}},
+	{S32, S64, {(u32)S32_MIN, (u32)(s32)-255}, {(u32)(s32)-2, 0}},
+	{S32, S64, {0, 1}, {(u32)S32_MIN, (u32)S32_MIN}},
+	{S32, U32, {(u32)S32_MIN, (u32)S32_MIN}, {(u32)S32_MIN, (u32)S32_MIN}},
+
+	/* edge overlap testings for BPF_NE */
+	{U64, U64, {0, U64_MAX}, {U64_MAX, U64_MAX}},
+	{U64, U64, {0, U64_MAX}, {0, 0}},
+	{S64, U64, {S64_MIN, 0}, {S64_MIN, S64_MIN}},
+	{S64, U64, {S64_MIN, 0}, {0, 0}},
+	{S64, U64, {S64_MIN, S64_MAX}, {S64_MAX, S64_MAX}},
+	{U32, U32, {0, U32_MAX}, {0, 0}},
+	{U32, U32, {0, U32_MAX}, {U32_MAX, U32_MAX}},
+	{S32, U32, {(u32)S32_MIN, 0}, {0, 0}},
+	{S32, U32, {(u32)S32_MIN, 0}, {(u32)S32_MIN, (u32)S32_MIN}},
+	{S32, U32, {(u32)S32_MIN, S32_MAX}, {S32_MAX, S32_MAX}},
+};
+
+/* Go over crafted hard-coded cases. This is fast, so we do it as part of
+ * normal test_progs run.
+ */
+void test_reg_bounds_crafted(void)
+{
+	struct ctx ctx;
+	int i;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	for (i = 0; i < ARRAY_SIZE(crafted_cases); i++) {
+		struct subtest_case *c = &crafted_cases[i];
+
+		verify_case(&ctx, c->init_t, c->cond_t, c->x, c->y);
+		verify_case(&ctx, c->init_t, c->cond_t, c->y, c->x);
+	}
+
+	cleanup_ctx(&ctx);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
new file mode 100644
index 0000000000..0c365f36c7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2024 Meta
+
+#include <test_progs.h>
+#include "network_helpers.h"
+#include "sock_iter_batch.skel.h"
+
+#define TEST_NS "sock_iter_batch_netns"
+
+static const int nr_soreuse = 4;
+
+static void do_test(int sock_type, bool onebyone)
+{
+	int err, i, nread, to_read, total_read, iter_fd = -1;
+	int first_idx, second_idx, indices[nr_soreuse];
+	struct bpf_link *link = NULL;
+	struct sock_iter_batch *skel;
+	int *fds[2] = {};
+
+	skel = sock_iter_batch__open();
+	if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open"))
+		return;
+
+	/* Prepare 2 buckets of sockets in the kernel hashtable */
+	for (i = 0; i < ARRAY_SIZE(fds); i++) {
+		int local_port;
+
+		fds[i] = start_reuseport_server(AF_INET6, sock_type, "::1", 0, 0,
+						nr_soreuse);
+		if (!ASSERT_OK_PTR(fds[i], "start_reuseport_server"))
+			goto done;
+		local_port = get_socket_local_port(*fds[i]);
+		if (!ASSERT_GE(local_port, 0, "get_socket_local_port"))
+			goto done;
+		skel->rodata->ports[i] = ntohs(local_port);
+	}
+
+	err = sock_iter_batch__load(skel);
+	if (!ASSERT_OK(err, "sock_iter_batch__load"))
+		goto done;
+
+	link = bpf_program__attach_iter(sock_type == SOCK_STREAM ?
+					skel->progs.iter_tcp_soreuse :
+					skel->progs.iter_udp_soreuse,
+					NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto done;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create"))
+		goto done;
+
+	/* Test reading a bucket (either from fds[0] or fds[1]).
+	 * Only read "nr_soreuse - 1" number of sockets
+	 * from a bucket and leave one socket out from
+	 * that bucket on purpose.
+	 */
+	to_read = (nr_soreuse - 1) * sizeof(*indices);
+	total_read = 0;
+	first_idx = -1;
+	do {
+		nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
+		if (nread <= 0 || nread % sizeof(*indices))
+			break;
+		total_read += nread;
+
+		if (first_idx == -1)
+			first_idx = indices[0];
+		for (i = 0; i < nread / sizeof(*indices); i++)
+			ASSERT_EQ(indices[i], first_idx, "first_idx");
+	} while (total_read < to_read);
+	ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread");
+	ASSERT_EQ(total_read, to_read, "total_read");
+
+	free_fds(fds[first_idx], nr_soreuse);
+	fds[first_idx] = NULL;
+
+	/* Read the "whole" second bucket */
+	to_read = nr_soreuse * sizeof(*indices);
+	total_read = 0;
+	second_idx = !first_idx;
+	do {
+		nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
+		if (nread <= 0 || nread % sizeof(*indices))
+			break;
+		total_read += nread;
+
+		for (i = 0; i < nread / sizeof(*indices); i++)
+			ASSERT_EQ(indices[i], second_idx, "second_idx");
+	} while (total_read <= to_read);
+	ASSERT_EQ(nread, 0, "nread");
+	/* Both so_reuseport ports should be in different buckets, so
+	 * total_read must equal to the expected to_read.
+	 *
+	 * For a very unlikely case, both ports collide at the same bucket,
+	 * the bucket offset (i.e. 3) will be skipped and it cannot
+	 * expect the to_read number of bytes.
+	 */
+	if (skel->bss->bucket[0] != skel->bss->bucket[1])
+		ASSERT_EQ(total_read, to_read, "total_read");
+
+done:
+	for (i = 0; i < ARRAY_SIZE(fds); i++)
+		free_fds(fds[i], nr_soreuse);
+	if (iter_fd < 0)
+		close(iter_fd);
+	bpf_link__destroy(link);
+	sock_iter_batch__destroy(skel);
+}
+
+void test_sock_iter_batch(void)
+{
+	struct nstoken *nstoken = NULL;
+
+	SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null");
+	SYS(done, "ip netns add %s", TEST_NS);
+	SYS(done, "ip -net %s link set dev lo up", TEST_NS);
+
+	nstoken = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto done;
+
+	if (test__start_subtest("tcp")) {
+		do_test(SOCK_STREAM, true);
+		do_test(SOCK_STREAM, false);
+	}
+	if (test__start_subtest("udp")) {
+		do_test(SOCK_DGRAM, true);
+		do_test(SOCK_DGRAM, false);
+	}
+	close_netns(nstoken);
+
+done:
+	SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 7c2241fae1..77e26ecffa 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -555,6 +555,213 @@ static void test_sockmap_unconnected_unix(void)
 	close(dgram);
 }
 
+static void test_sockmap_many_socket(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map, entry = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+	for (entry--; entry >= 0; entry--) {
+		err = bpf_map_delete_elem(map, &entry);
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+	}
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_many_maps(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map[2], entry = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map[0] = bpf_map__fd(skel->maps.sock_map_rx);
+	map[1] = bpf_map__fd(skel->maps.sock_map_tx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+	for (entry--; entry >= 0; entry--) {
+		err = bpf_map_delete_elem(map[1], &entry);
+		entry--;
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+		err = bpf_map_delete_elem(map[0], &entry);
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+	}
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_same_sock(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map, zero = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+
+	err = bpf_map_delete_elem(map, &zero);
+	ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -597,7 +804,12 @@ void test_sockmap_basic(void)
 		test_sockmap_skb_verdict_fionread(false);
 	if (test__start_subtest("sockmap skb_verdict msg_f_peek"))
 		test_sockmap_skb_verdict_peek();
-
 	if (test__start_subtest("sockmap unconnected af_unix"))
 		test_sockmap_unconnected_unix();
+	if (test__start_subtest("sockmap one socket to many map entries"))
+		test_sockmap_many_socket();
+	if (test__start_subtest("sockmap one socket to many maps"))
+		test_sockmap_many_maps();
+	if (test__start_subtest("sockmap same socket replace"))
+		test_sockmap_same_sock();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
index f29c08d93b..18d451be57 100644
--- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
@@ -13,22 +13,22 @@ static struct {
 	const char *err_msg;
 } spin_lock_fail_tests[] = {
 	{ "lock_id_kptr_preserve",
-	  "5: (bf) r1 = r0                       ; R0_w=ptr_foo(id=2,ref_obj_id=2,off=0,imm=0) "
-	  "R1_w=ptr_foo(id=2,ref_obj_id=2,off=0,imm=0) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n"
+	  "5: (bf) r1 = r0                       ; R0_w=ptr_foo(id=2,ref_obj_id=2) "
+	  "R1_w=ptr_foo(id=2,ref_obj_id=2) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=ptr_ expected=percpu_ptr_" },
 	{ "lock_id_global_zero",
-	  "; R1_w=map_value(off=0,ks=4,vs=4,imm=0)\n2: (85) call bpf_this_cpu_ptr#154\n"
+	  "; R1_w=map_value(map=.data.A,ks=4,vs=4)\n2: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_mapval_preserve",
 	  "[0-9]\\+: (bf) r1 = r0                       ;"
-	  " R0_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)"
-	  " R1_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)\n"
+	  " R0_w=map_value(id=1,map=array_map,ks=4,vs=8)"
+	  " R1_w=map_value(id=1,map=array_map,ks=4,vs=8)\n"
 	  "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_innermapval_preserve",
 	  "[0-9]\\+: (bf) r1 = r0                      ;"
-	  " R0=map_value(id=2,off=0,ks=4,vs=8,imm=0)"
-	  " R1_w=map_value(id=2,off=0,ks=4,vs=8,imm=0)\n"
+	  " R0=map_value(id=2,ks=4,vs=8)"
+	  " R1_w=map_value(id=2,ks=4,vs=8)\n"
 	  "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_mismatch_kptr_kptr", "bpf_spin_unlock of different lock" },
diff --git a/tools/testing/selftests/bpf/prog_tests/syscall.c b/tools/testing/selftests/bpf/prog_tests/syscall.c
index f4d4000115..0be8301c0f 100644
--- a/tools/testing/selftests/bpf/prog_tests/syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/syscall.c
@@ -12,7 +12,7 @@ struct args {
 	int btf_fd;
 };
 
-void test_syscall(void)
+static void test_syscall_load_prog(void)
 {
 	static char verifier_log[8192];
 	struct args ctx = {
@@ -32,7 +32,7 @@ void test_syscall(void)
 	if (!ASSERT_OK_PTR(skel, "skel_load"))
 		goto cleanup;
 
-	prog_fd = bpf_program__fd(skel->progs.bpf_prog);
+	prog_fd = bpf_program__fd(skel->progs.load_prog);
 	err = bpf_prog_test_run_opts(prog_fd, &tattr);
 	ASSERT_EQ(err, 0, "err");
 	ASSERT_EQ(tattr.retval, 1, "retval");
@@ -53,3 +53,29 @@ cleanup:
 	if (ctx.btf_fd > 0)
 		close(ctx.btf_fd);
 }
+
+static void test_syscall_update_outer_map(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct syscall *skel;
+	int err, prog_fd;
+
+	skel = syscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.update_outer_map);
+	err = bpf_prog_test_run_opts(prog_fd, &opts);
+	ASSERT_EQ(err, 0, "err");
+	ASSERT_EQ(opts.retval, 1, "retval");
+cleanup:
+	syscall__destroy(skel);
+}
+
+void test_syscall(void)
+{
+	if (test__start_subtest("load_prog"))
+		test_syscall_load_prog();
+	if (test__start_subtest("update_outer_map"))
+		test_syscall_update_outer_map();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
index d3491a84b3..ccae0b31ac 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
@@ -14,7 +14,8 @@ static void do_bpf_ma_test(const char *name)
 	struct test_bpf_ma *skel;
 	struct bpf_program *prog;
 	struct btf *btf;
-	int i, err;
+	int i, err, id;
+	char tname[32];
 
 	skel = test_bpf_ma__open();
 	if (!ASSERT_OK_PTR(skel, "open"))
@@ -25,16 +26,21 @@ static void do_bpf_ma_test(const char *name)
 		goto out;
 
 	for (i = 0; i < ARRAY_SIZE(skel->rodata->data_sizes); i++) {
-		char name[32];
-		int id;
-
-		snprintf(name, sizeof(name), "bin_data_%u", skel->rodata->data_sizes[i]);
-		id = btf__find_by_name_kind(btf, name, BTF_KIND_STRUCT);
-		if (!ASSERT_GT(id, 0, "bin_data"))
+		snprintf(tname, sizeof(tname), "bin_data_%u", skel->rodata->data_sizes[i]);
+		id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+		if (!ASSERT_GT(id, 0, tname))
 			goto out;
 		skel->rodata->data_btf_ids[i] = id;
 	}
 
+	for (i = 0; i < ARRAY_SIZE(skel->rodata->percpu_data_sizes); i++) {
+		snprintf(tname, sizeof(tname), "percpu_bin_data_%u", skel->rodata->percpu_data_sizes[i]);
+		id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+		if (!ASSERT_GT(id, 0, tname))
+			goto out;
+		skel->rodata->percpu_data_btf_ids[i] = id;
+	}
+
 	prog = bpf_object__find_program_by_name(skel->obj, name);
 	if (!ASSERT_OK_PTR(prog, "invalid prog name"))
 		goto out;
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 e0879df386..e905cbaf6b 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -20,6 +20,122 @@
 #include "test_global_func17.skel.h"
 #include "test_global_func_ctx_args.skel.h"
 
+#include "bpf/libbpf_internal.h"
+#include "btf_helpers.h"
+
+static void check_ctx_arg_type(const struct btf *btf, const struct btf_param *p)
+{
+	const struct btf_type *t;
+	const char *s;
+
+	t = btf__type_by_id(btf, p->type);
+	if (!ASSERT_EQ(btf_kind(t), BTF_KIND_PTR, "ptr_t"))
+		return;
+
+	s = btf_type_raw_dump(btf, t->type);
+	if (!ASSERT_HAS_SUBSTR(s, "STRUCT 'bpf_perf_event_data' size=0 vlen=0",
+			       "ctx_struct_t"))
+		return;
+}
+
+static void subtest_ctx_arg_rewrite(void)
+{
+	struct test_global_func_ctx_args *skel = NULL;
+	struct bpf_prog_info info;
+	char func_info_buf[1024] __attribute__((aligned(8)));
+	struct bpf_func_info_min *rec;
+	struct btf *btf = NULL;
+	__u32 info_len = sizeof(info);
+	int err, fd, i;
+	struct btf *kern_btf = NULL;
+
+	kern_btf = btf__load_vmlinux_btf();
+	if (!ASSERT_OK_PTR(kern_btf, "kern_btf_load"))
+		return;
+
+	/* simple detection of kernel native arg:ctx tag support */
+	if (btf__find_by_name_kind(kern_btf, "bpf_subprog_arg_info", BTF_KIND_STRUCT) > 0) {
+		test__skip();
+		btf__free(kern_btf);
+		return;
+	}
+	btf__free(kern_btf);
+
+	skel = test_global_func_ctx_args__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.arg_tag_ctx_perf, true);
+
+	err = test_global_func_ctx_args__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto out;
+
+	memset(&info, 0, sizeof(info));
+	info.func_info = ptr_to_u64(&func_info_buf);
+	info.nr_func_info = 3;
+	info.func_info_rec_size = sizeof(struct bpf_func_info_min);
+
+	fd = bpf_program__fd(skel->progs.arg_tag_ctx_perf);
+	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(err, "prog_info"))
+		goto out;
+
+	if (!ASSERT_EQ(info.nr_func_info, 3, "nr_func_info"))
+		goto out;
+
+	btf = btf__load_from_kernel_by_id(info.btf_id);
+	if (!ASSERT_OK_PTR(btf, "obj_kern_btf"))
+		goto out;
+
+	rec = (struct bpf_func_info_min *)func_info_buf;
+	for (i = 0; i < info.nr_func_info; i++, rec = (void *)rec + info.func_info_rec_size) {
+		const struct btf_type *fn_t, *proto_t;
+		const char *name;
+
+		if (rec->insn_off == 0)
+			continue; /* main prog, skip */
+
+		fn_t = btf__type_by_id(btf, rec->type_id);
+		if (!ASSERT_OK_PTR(fn_t, "fn_type"))
+			goto out;
+		if (!ASSERT_EQ(btf_kind(fn_t), BTF_KIND_FUNC, "fn_type_kind"))
+			goto out;
+		proto_t = btf__type_by_id(btf, fn_t->type);
+		if (!ASSERT_OK_PTR(proto_t, "proto_type"))
+			goto out;
+
+		name = btf__name_by_offset(btf, fn_t->name_off);
+		if (strcmp(name, "subprog_ctx_tag") == 0) {
+			/* int subprog_ctx_tag(void *ctx __arg_ctx) */
+			if (!ASSERT_EQ(btf_vlen(proto_t), 1, "arg_cnt"))
+				goto out;
+
+			/* arg 0 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[0]);
+		} else if (strcmp(name, "subprog_multi_ctx_tags") == 0) {
+			/* int subprog_multi_ctx_tags(void *ctx1 __arg_ctx,
+			 *			      struct my_struct *mem,
+			 *			      void *ctx2 __arg_ctx)
+			 */
+			if (!ASSERT_EQ(btf_vlen(proto_t), 3, "arg_cnt"))
+				goto out;
+
+			/* arg 0 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[0]);
+			/* arg 2 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[2]);
+		} else {
+			ASSERT_FAIL("unexpected subprog %s", name);
+			goto out;
+		}
+	}
+
+out:
+	btf__free(btf);
+	test_global_func_ctx_args__destroy(skel);
+}
+
 void test_test_global_funcs(void)
 {
 	RUN_TESTS(test_global_func1);
@@ -40,4 +156,7 @@ void test_test_global_funcs(void)
 	RUN_TESTS(test_global_func16);
 	RUN_TESTS(test_global_func17);
 	RUN_TESTS(test_global_func_ctx_args);
+
+	if (test__start_subtest("ctx_arg_rewrite"))
+		subtest_ctx_arg_rewrite();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
index d149ab9879..2b3c6dd662 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
@@ -50,6 +50,7 @@
  */
 
 #include <arpa/inet.h>
+#include <linux/if_link.h>
 #include <linux/if_tun.h>
 #include <linux/limits.h>
 #include <linux/sysctl.h>
@@ -92,6 +93,11 @@
 #define IPIP_TUNL_DEV0 "ipip00"
 #define IPIP_TUNL_DEV1 "ipip11"
 
+#define XFRM_AUTH "0x1111111111111111111111111111111111111111"
+#define XFRM_ENC "0x22222222222222222222222222222222"
+#define XFRM_SPI_IN_TO_OUT 0x1
+#define XFRM_SPI_OUT_TO_IN 0x2
+
 #define PING_ARGS "-i 0.01 -c 3 -w 10 -q"
 
 static int config_device(void)
@@ -264,6 +270,92 @@ static void delete_ipip_tunnel(void)
 	SYS_NOFAIL("ip fou del port 5555 2> /dev/null");
 }
 
+static int add_xfrm_tunnel(void)
+{
+	/* at_ns0 namespace
+	 * at_ns0 -> root
+	 */
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm state add src %s dst %s proto esp "
+			"spi %d reqid 1 mode tunnel replay-window 42 "
+			"auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s",
+	    IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm policy add src %s/32 dst %s/32 dir out "
+			"tmpl src %s dst %s proto esp reqid 1 "
+			"mode tunnel",
+	    IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+	/* root -> at_ns0 */
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm state add src %s dst %s proto esp "
+			"spi %d reqid 2 mode tunnel "
+			"auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s",
+	    IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm policy add src %s/32 dst %s/32 dir in "
+			"tmpl src %s dst %s proto esp reqid 2 "
+			"mode tunnel",
+	    IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0, IP4_ADDR1_VETH1, IP4_ADDR_VETH0);
+
+	/* address & route */
+	SYS(fail, "ip netns exec at_ns0 ip addr add dev veth0 %s/32",
+	    IP4_ADDR_TUNL_DEV0);
+	SYS(fail, "ip netns exec at_ns0 ip route add %s dev veth0 via %s src %s",
+	    IP4_ADDR_TUNL_DEV1, IP4_ADDR1_VETH1, IP4_ADDR_TUNL_DEV0);
+
+	/* root namespace
+	 * at_ns0 -> root
+	 */
+	SYS(fail,
+	    "ip xfrm state add src %s dst %s proto esp "
+		    "spi %d reqid 1 mode tunnel replay-window 42 "
+		    "auth-trunc 'hmac(sha1)' %s 96  enc 'cbc(aes)' %s",
+	    IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip xfrm policy add src %s/32 dst %s/32 dir in "
+		    "tmpl src %s dst %s proto esp reqid 1 "
+		    "mode tunnel",
+	    IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+	/* root -> at_ns0 */
+	SYS(fail,
+	    "ip xfrm state add src %s dst %s proto esp "
+		    "spi %d reqid 2 mode tunnel "
+		    "auth-trunc 'hmac(sha1)' %s 96  enc 'cbc(aes)' %s",
+	    IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip xfrm policy add src %s/32 dst %s/32 dir out "
+		    "tmpl src %s dst %s proto esp reqid 2 "
+		    "mode tunnel",
+	    IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0, IP4_ADDR1_VETH1, IP4_ADDR_VETH0);
+
+	/* address & route */
+	SYS(fail, "ip addr add dev veth1 %s/32", IP4_ADDR_TUNL_DEV1);
+	SYS(fail, "ip route add %s dev veth1 via %s src %s",
+	    IP4_ADDR_TUNL_DEV0, IP4_ADDR_VETH0, IP4_ADDR_TUNL_DEV1);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void delete_xfrm_tunnel(void)
+{
+	SYS_NOFAIL("ip xfrm policy delete dir out src %s/32 dst %s/32 2> /dev/null",
+		   IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0);
+	SYS_NOFAIL("ip xfrm policy delete dir in src %s/32 dst %s/32 2> /dev/null",
+		   IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1);
+	SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d 2> /dev/null",
+		   IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT);
+	SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d 2> /dev/null",
+		   IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN);
+}
+
 static int test_ping(int family, const char *addr)
 {
 	SYS(fail, "%s %s %s > /dev/null", ping_command(family), PING_ARGS, addr);
@@ -532,25 +624,85 @@ done:
 		test_tunnel_kern__destroy(skel);
 }
 
+static void test_xfrm_tunnel(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
+			    .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
+	struct test_tunnel_kern *skel = NULL;
+	struct nstoken *nstoken;
+	int xdp_prog_fd;
+	int tc_prog_fd;
+	int ifindex;
+	int err;
+
+	err = add_xfrm_tunnel();
+	if (!ASSERT_OK(err, "add_xfrm_tunnel"))
+		return;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		goto done;
+
+	ifindex = if_nametoindex("veth1");
+	if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
+		goto done;
+
+	/* attach tc prog to tunnel dev */
+	tc_hook.ifindex = ifindex;
+	tc_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state);
+	if (!ASSERT_GE(tc_prog_fd, 0, "bpf_program__fd"))
+		goto done;
+	if (attach_tc_prog(&tc_hook, tc_prog_fd, -1))
+		goto done;
+
+	/* attach xdp prog to tunnel dev */
+	xdp_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state_xdp);
+	if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__fd"))
+		goto done;
+	err = bpf_xdp_attach(ifindex, xdp_prog_fd, XDP_FLAGS_REPLACE, &opts);
+	if (!ASSERT_OK(err, "bpf_xdp_attach"))
+		goto done;
+
+	/* ping from at_ns0 namespace test */
+	nstoken = open_netns("at_ns0");
+	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1);
+	close_netns(nstoken);
+	if (!ASSERT_OK(err, "test_ping"))
+		goto done;
+
+	if (!ASSERT_EQ(skel->bss->xfrm_reqid, 1, "req_id"))
+		goto done;
+	if (!ASSERT_EQ(skel->bss->xfrm_spi, XFRM_SPI_IN_TO_OUT, "spi"))
+		goto done;
+	if (!ASSERT_EQ(skel->bss->xfrm_remote_ip, 0xac100164, "remote_ip"))
+		goto done;
+	if (!ASSERT_EQ(skel->bss->xfrm_replay_window, 42, "replay_window"))
+		goto done;
+
+done:
+	delete_xfrm_tunnel();
+	if (skel)
+		test_tunnel_kern__destroy(skel);
+}
+
 #define RUN_TEST(name, ...)						\
 	({								\
 		if (test__start_subtest(#name)) {			\
+			config_device();				\
 			test_ ## name(__VA_ARGS__);			\
+			cleanup();					\
 		}							\
 	})
 
 static void *test_tunnel_run_tests(void *arg)
 {
-	cleanup();
-	config_device();
-
 	RUN_TEST(vxlan_tunnel);
 	RUN_TEST(ip6vxlan_tunnel);
 	RUN_TEST(ipip_tunnel, NONE);
 	RUN_TEST(ipip_tunnel, FOU);
 	RUN_TEST(ipip_tunnel, GUE);
-
-	cleanup();
+	RUN_TEST(xfrm_tunnel);
 
 	return NULL;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index 760ad96b4b..d66687f1ee 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -4,10 +4,29 @@
 #include "timer.skel.h"
 #include "timer_failure.skel.h"
 
+#define NUM_THR 8
+
+static void *spin_lock_thread(void *arg)
+{
+	int i, err, prog_fd = *(int *)arg;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	for (i = 0; i < 10000; i++) {
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+		if (!ASSERT_OK(err, "test_run_opts err") ||
+		    !ASSERT_OK(topts.retval, "test_run_opts retval"))
+			break;
+	}
+
+	pthread_exit(arg);
+}
+
 static int timer(struct timer *timer_skel)
 {
-	int err, prog_fd;
+	int i, err, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	pthread_t thread_id[NUM_THR];
+	void *ret;
 
 	err = timer__attach(timer_skel);
 	if (!ASSERT_OK(err, "timer_attach"))
@@ -43,6 +62,20 @@ static int timer(struct timer *timer_skel)
 	/* check that code paths completed */
 	ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok");
 
+	prog_fd = bpf_program__fd(timer_skel->progs.race);
+	for (i = 0; i < NUM_THR; i++) {
+		err = pthread_create(&thread_id[i], NULL,
+				     &spin_lock_thread, &prog_fd);
+		if (!ASSERT_OK(err, "pthread_create"))
+			break;
+	}
+
+	while (i) {
+		err = pthread_join(thread_id[--i], &ret);
+		if (ASSERT_OK(err, "pthread_join"))
+			ASSERT_EQ(ret, (void *)&prog_fd, "pthread_join");
+	}
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index cd051d3901..8269cdee33 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -234,6 +234,177 @@ static void test_attach_api_syms(void)
 	test_attach_api("/proc/self/exe", NULL, &opts);
 }
 
+static void test_attach_api_fails(void)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, opts);
+	const char *path = "/proc/self/exe";
+	struct uprobe_multi *skel = NULL;
+	int prog_fd, link_fd = -1;
+	unsigned long offset = 0;
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.uprobe_extra);
+
+	/* abnormal cnt */
+	opts.uprobe_multi.path = path;
+	opts.uprobe_multi.offsets = &offset;
+	opts.uprobe_multi.cnt = INT_MAX;
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -E2BIG, "big cnt"))
+		goto cleanup;
+
+	/* cnt is 0 */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "cnt_is_zero"))
+		goto cleanup;
+
+	/* negative offset */
+	offset = -1;
+	opts.uprobe_multi.path = path;
+	opts.uprobe_multi.offsets = (unsigned long *) &offset;
+	opts.uprobe_multi.cnt = 1;
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "offset_is_negative"))
+		goto cleanup;
+
+	/* offsets is NULL */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "offsets_is_null"))
+		goto cleanup;
+
+	/* wrong offsets pointer */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) 1,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "offsets_is_wrong"))
+		goto cleanup;
+
+	/* path is NULL */
+	offset = 1;
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "path_is_null"))
+		goto cleanup;
+
+	/* wrong path pointer  */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = (const char *) 1,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "path_is_wrong"))
+		goto cleanup;
+
+	/* wrong path type */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = "/",
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EBADF, "path_is_wrong_type"))
+		goto cleanup;
+
+	/* wrong cookies pointer */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cookies = (__u64 *) 1ULL,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "cookies_is_wrong"))
+		goto cleanup;
+
+	/* wrong ref_ctr_offsets pointer */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cookies = (__u64 *) &offset,
+		.uprobe_multi.ref_ctr_offsets = (unsigned long *) 1,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "ref_ctr_offsets_is_wrong"))
+		goto cleanup;
+
+	/* wrong flags */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.flags = 1 << 31,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "wrong_flags"))
+		goto cleanup;
+
+	/* wrong pid */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+		.uprobe_multi.pid = -2,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong");
+
+cleanup:
+	if (link_fd >= 0)
+		close(link_fd);
+	uprobe_multi__destroy(skel);
+}
+
 static void __test_link_api(struct child *child)
 {
 	int prog_fd, link1_fd = -1, link2_fd = -1, link3_fd = -1, link4_fd = -1;
@@ -249,7 +420,7 @@ static void __test_link_api(struct child *child)
 	int link_extra_fd = -1;
 	int err;
 
-	err = elf_resolve_syms_offsets(path, 3, syms, (unsigned long **) &offsets);
+	err = elf_resolve_syms_offsets(path, 3, syms, (unsigned long **) &offsets, STT_FUNC);
 	if (!ASSERT_OK(err, "elf_resolve_syms_offsets"))
 		return;
 
@@ -311,7 +482,7 @@ cleanup:
 	free(offsets);
 }
 
-void test_link_api(void)
+static void test_link_api(void)
 {
 	struct child *child;
 
@@ -412,4 +583,6 @@ void test_uprobe_multi_test(void)
 		test_bench_attach_uprobe();
 	if (test__start_subtest("bench_usdt"))
 		test_bench_attach_usdt();
+	if (test__start_subtest("attach_api_fails"))
+		test_attach_api_fails();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 5cfa7a6316..d62c5bf00e 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -6,6 +6,7 @@
 #include "verifier_and.skel.h"
 #include "verifier_array_access.skel.h"
 #include "verifier_basic_stack.skel.h"
+#include "verifier_bitfield_write.skel.h"
 #include "verifier_bounds.skel.h"
 #include "verifier_bounds_deduction.skel.h"
 #include "verifier_bounds_deduction_non_const.skel.h"
@@ -13,6 +14,7 @@
 #include "verifier_bpf_get_stack.skel.h"
 #include "verifier_bswap.skel.h"
 #include "verifier_btf_ctx_access.skel.h"
+#include "verifier_btf_unreliable_prog.skel.h"
 #include "verifier_cfg.skel.h"
 #include "verifier_cgroup_inv_retcode.skel.h"
 #include "verifier_cgroup_skb.skel.h"
@@ -25,6 +27,7 @@
 #include "verifier_direct_stack_access_wraparound.skel.h"
 #include "verifier_div0.skel.h"
 #include "verifier_div_overflow.skel.h"
+#include "verifier_global_subprogs.skel.h"
 #include "verifier_gotol.skel.h"
 #include "verifier_helper_access_var_len.skel.h"
 #include "verifier_helper_packet_access.skel.h"
@@ -115,6 +118,7 @@ static void run_tests_aux(const char *skel_name,
 
 void test_verifier_and(void)                  { RUN(verifier_and); }
 void test_verifier_basic_stack(void)          { RUN(verifier_basic_stack); }
+void test_verifier_bitfield_write(void)       { RUN(verifier_bitfield_write); }
 void test_verifier_bounds(void)               { RUN(verifier_bounds); }
 void test_verifier_bounds_deduction(void)     { RUN(verifier_bounds_deduction); }
 void test_verifier_bounds_deduction_non_const(void)     { RUN(verifier_bounds_deduction_non_const); }
@@ -122,6 +126,7 @@ void test_verifier_bounds_mix_sign_unsign(void) { RUN(verifier_bounds_mix_sign_u
 void test_verifier_bpf_get_stack(void)        { RUN(verifier_bpf_get_stack); }
 void test_verifier_bswap(void)                { RUN(verifier_bswap); }
 void test_verifier_btf_ctx_access(void)       { RUN(verifier_btf_ctx_access); }
+void test_verifier_btf_unreliable_prog(void)  { RUN(verifier_btf_unreliable_prog); }
 void test_verifier_cfg(void)                  { RUN(verifier_cfg); }
 void test_verifier_cgroup_inv_retcode(void)   { RUN(verifier_cgroup_inv_retcode); }
 void test_verifier_cgroup_skb(void)           { RUN(verifier_cgroup_skb); }
@@ -134,6 +139,7 @@ void test_verifier_direct_packet_access(void) { RUN(verifier_direct_packet_acces
 void test_verifier_direct_stack_access_wraparound(void) { RUN(verifier_direct_stack_access_wraparound); }
 void test_verifier_div0(void)                 { RUN(verifier_div0); }
 void test_verifier_div_overflow(void)         { RUN(verifier_div_overflow); }
+void test_verifier_global_subprogs(void)      { RUN(verifier_global_subprogs); }
 void test_verifier_gotol(void)                { RUN(verifier_gotol); }
 void test_verifier_helper_access_var_len(void) { RUN(verifier_helper_access_var_len); }
 void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_access); }
diff --git a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
index dd7f2bc700..ab0f02faa8 100644
--- a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
@@ -16,9 +16,12 @@
 #include <sys/wait.h>
 #include <sys/mman.h>
 #include <linux/keyctl.h>
+#include <sys/xattr.h>
+#include <linux/fsverity.h>
 #include <test_progs.h>
 
 #include "test_verify_pkcs7_sig.skel.h"
+#include "test_sig_in_xattr.skel.h"
 
 #define MAX_DATA_SIZE (1024 * 1024)
 #define MAX_SIG_SIZE 1024
@@ -26,6 +29,10 @@
 #define VERIFY_USE_SECONDARY_KEYRING (1UL)
 #define VERIFY_USE_PLATFORM_KEYRING  (2UL)
 
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
 /* In stripped ARM and x86-64 modules, ~ is surprisingly rare. */
 #define MODULE_SIG_STRING "~Module signature appended~\n"
 
@@ -254,7 +261,7 @@ out:
 	return ret;
 }
 
-void test_verify_pkcs7_sig(void)
+static void test_verify_pkcs7_sig_from_map(void)
 {
 	libbpf_print_fn_t old_print_cb;
 	char tmp_dir_template[] = "/tmp/verify_sigXXXXXX";
@@ -400,3 +407,159 @@ close_prog:
 	skel->bss->monitored_pid = 0;
 	test_verify_pkcs7_sig__destroy(skel);
 }
+
+static int get_signature_size(const char *sig_path)
+{
+	struct stat st;
+
+	if (stat(sig_path, &st) == -1)
+		return -1;
+
+	return st.st_size;
+}
+
+static int add_signature_to_xattr(const char *data_path, const char *sig_path)
+{
+	char sig[MAX_SIG_SIZE] = {0};
+	int fd, size, ret;
+
+	if (sig_path) {
+		fd = open(sig_path, O_RDONLY);
+		if (fd < 0)
+			return -1;
+
+		size = read(fd, sig, MAX_SIG_SIZE);
+		close(fd);
+		if (size <= 0)
+			return -1;
+	} else {
+		/* no sig_path, just write 32 bytes of zeros */
+		size = 32;
+	}
+	ret = setxattr(data_path, "user.sig", sig, size, 0);
+	if (!ASSERT_OK(ret, "setxattr"))
+		return -1;
+
+	return 0;
+}
+
+static int test_open_file(struct test_sig_in_xattr *skel, char *data_path,
+			  pid_t pid, bool should_success, char *name)
+{
+	int ret;
+
+	skel->bss->monitored_pid = pid;
+	ret = open(data_path, O_RDONLY);
+	close(ret);
+	skel->bss->monitored_pid = 0;
+
+	if (should_success) {
+		if (!ASSERT_GE(ret, 0, name))
+			return -1;
+	} else {
+		if (!ASSERT_LT(ret, 0, name))
+			return -1;
+	}
+	return 0;
+}
+
+static void test_pkcs7_sig_fsverity(void)
+{
+	char data_path[PATH_MAX];
+	char sig_path[PATH_MAX];
+	char tmp_dir_template[] = "/tmp/verify_sigXXXXXX";
+	char *tmp_dir;
+	struct test_sig_in_xattr *skel = NULL;
+	pid_t pid;
+	int ret;
+
+	tmp_dir = mkdtemp(tmp_dir_template);
+	if (!ASSERT_OK_PTR(tmp_dir, "mkdtemp"))
+		return;
+
+	snprintf(data_path, PATH_MAX, "%s/data-file", tmp_dir);
+	snprintf(sig_path, PATH_MAX, "%s/sig-file", tmp_dir);
+
+	ret = _run_setup_process(tmp_dir, "setup");
+	if (!ASSERT_OK(ret, "_run_setup_process"))
+		goto out;
+
+	ret = _run_setup_process(tmp_dir, "fsverity-create-sign");
+
+	if (ret) {
+		printf("%s: SKIP: fsverity [sign|enable] doesn't work.\n"
+		       "To run this test, try enable CONFIG_FS_VERITY and enable FSVerity for the filesystem.\n",
+		       __func__);
+		test__skip();
+		goto out;
+	}
+
+	skel = test_sig_in_xattr__open();
+	if (!ASSERT_OK_PTR(skel, "test_sig_in_xattr__open"))
+		goto out;
+	ret = get_signature_size(sig_path);
+	if (!ASSERT_GT(ret, 0, "get_signature_size"))
+		goto out;
+	skel->bss->sig_size = ret;
+	skel->bss->user_keyring_serial = syscall(__NR_request_key, "keyring",
+						 "ebpf_testing_keyring", NULL,
+						 KEY_SPEC_SESSION_KEYRING);
+	memcpy(skel->bss->digest, "FSVerity", 8);
+
+	ret = test_sig_in_xattr__load(skel);
+	if (!ASSERT_OK(ret, "test_sig_in_xattr__load"))
+		goto out;
+
+	ret = test_sig_in_xattr__attach(skel);
+	if (!ASSERT_OK(ret, "test_sig_in_xattr__attach"))
+		goto out;
+
+	pid = getpid();
+
+	/* Case 1: fsverity is not enabled, open should succeed */
+	if (test_open_file(skel, data_path, pid, true, "open_1"))
+		goto out;
+
+	/* Case 2: fsverity is enabled, xattr is missing, open should
+	 * fail
+	 */
+	ret = _run_setup_process(tmp_dir, "fsverity-enable");
+	if (!ASSERT_OK(ret, "fsverity-enable"))
+		goto out;
+	if (test_open_file(skel, data_path, pid, false, "open_2"))
+		goto out;
+
+	/* Case 3: fsverity is enabled, xattr has valid signature, open
+	 * should succeed
+	 */
+	ret = add_signature_to_xattr(data_path, sig_path);
+	if (!ASSERT_OK(ret, "add_signature_to_xattr_1"))
+		goto out;
+
+	if (test_open_file(skel, data_path, pid, true, "open_3"))
+		goto out;
+
+	/* Case 4: fsverity is enabled, xattr has invalid signature, open
+	 * should fail
+	 */
+	ret = add_signature_to_xattr(data_path, NULL);
+	if (!ASSERT_OK(ret, "add_signature_to_xattr_2"))
+		goto out;
+	test_open_file(skel, data_path, pid, false, "open_4");
+
+out:
+	_run_setup_process(tmp_dir, "cleanup");
+	if (!skel)
+		return;
+
+	skel->bss->monitored_pid = 0;
+	test_sig_in_xattr__destroy(skel);
+}
+
+void test_verify_pkcs7_sig(void)
+{
+	if (test__start_subtest("pkcs7_sig_from_map"))
+		test_verify_pkcs7_sig_from_map();
+	if (test__start_subtest("pkcs7_sig_fsverity"))
+		test_pkcs7_sig_fsverity();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/vmlinux.c b/tools/testing/selftests/bpf/prog_tests/vmlinux.c
index 72310cfc64..6fb2217d94 100644
--- a/tools/testing/selftests/bpf/prog_tests/vmlinux.c
+++ b/tools/testing/selftests/bpf/prog_tests/vmlinux.c
@@ -16,27 +16,27 @@ static void nsleep()
 
 void test_vmlinux(void)
 {
-	int duration = 0, err;
+	int err;
 	struct test_vmlinux* skel;
 	struct test_vmlinux__bss *bss;
 
 	skel = test_vmlinux__open_and_load();
-	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+	if (!ASSERT_OK_PTR(skel, "test_vmlinux__open_and_load"))
 		return;
 	bss = skel->bss;
 
 	err = test_vmlinux__attach(skel);
-	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "test_vmlinux__attach"))
 		goto cleanup;
 
 	/* trigger everything */
 	nsleep();
 
-	CHECK(!bss->tp_called, "tp", "not called\n");
-	CHECK(!bss->raw_tp_called, "raw_tp", "not called\n");
-	CHECK(!bss->tp_btf_called, "tp_btf", "not called\n");
-	CHECK(!bss->kprobe_called, "kprobe", "not called\n");
-	CHECK(!bss->fentry_called, "fentry", "not called\n");
+	ASSERT_TRUE(bss->tp_called, "tp");
+	ASSERT_TRUE(bss->raw_tp_called, "raw_tp");
+	ASSERT_TRUE(bss->tp_btf_called, "tp_btf");
+	ASSERT_TRUE(bss->kprobe_called, "kprobe");
+	ASSERT_TRUE(bss->fentry_called, "fentry");
 
 cleanup:
 	test_vmlinux__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
index ab4952b9fb..e6a783c7f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
@@ -77,8 +77,8 @@ void test_xdp_context_test_run(void)
 	test_xdp_context_error(prog_fd, opts, 4, sizeof(__u32), sizeof(data),
 			       0, 0, 0);
 
-	/* Meta data must be 32 bytes or smaller */
-	test_xdp_context_error(prog_fd, opts, 0, 36, sizeof(data), 0, 0, 0);
+	/* Meta data must be 255 bytes or smaller */
+	test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0);
 
 	/* Total size of data must match data_end - data_meta */
 	test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index 4439ba9392..05edcf32f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -20,7 +20,7 @@
 
 #define UDP_PAYLOAD_BYTES 4
 
-#define AF_XDP_SOURCE_PORT 1234
+#define UDP_SOURCE_PORT 1234
 #define AF_XDP_CONSUMER_PORT 8080
 
 #define UMEM_NUM 16
@@ -33,6 +33,18 @@
 #define RX_ADDR "10.0.0.2"
 #define PREFIX_LEN "8"
 #define FAMILY AF_INET
+#define TX_NETNS_NAME "xdp_metadata_tx"
+#define RX_NETNS_NAME "xdp_metadata_rx"
+#define TX_MAC "00:00:00:00:00:01"
+#define RX_MAC "00:00:00:00:00:02"
+
+#define VLAN_ID 59
+#define VLAN_PROTO "802.1Q"
+#define VLAN_PID htons(ETH_P_8021Q)
+#define TX_NAME_VLAN TX_NAME "." TO_STR(VLAN_ID)
+
+#define XDP_RSS_TYPE_L4 BIT(3)
+#define VLAN_VID_MASK 0xfff
 
 struct xsk {
 	void *umem_area;
@@ -56,7 +68,8 @@ static int open_xsk(int ifindex, struct xsk *xsk)
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
-		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG,
+		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG | XDP_UMEM_TX_SW_CSUM,
+		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
 	};
 	__u32 idx;
 	u64 addr;
@@ -138,6 +151,7 @@ static void ip_csum(struct iphdr *iph)
 
 static int generate_packet(struct xsk *xsk, __u16 dst_port)
 {
+	struct xsk_tx_metadata *meta;
 	struct xdp_desc *tx_desc;
 	struct udphdr *udph;
 	struct ethhdr *eth;
@@ -151,10 +165,14 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 		return -1;
 
 	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
-	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE;
+	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE + sizeof(struct xsk_tx_metadata);
 	printf("%p: tx_desc[%u]->addr=%llx\n", xsk, idx, tx_desc->addr);
 	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
 
+	meta = data - sizeof(struct xsk_tx_metadata);
+	memset(meta, 0, sizeof(*meta));
+	meta->flags = XDP_TXMD_FLAGS_TIMESTAMP;
+
 	eth = data;
 	iph = (void *)(eth + 1);
 	udph = (void *)(iph + 1);
@@ -175,14 +193,20 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 	ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)");
 	ip_csum(iph);
 
-	udph->source = htons(AF_XDP_SOURCE_PORT);
+	udph->source = htons(UDP_SOURCE_PORT);
 	udph->dest = htons(dst_port);
 	udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES);
-	udph->check = 0;
+	udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+					 ntohs(udph->len), IPPROTO_UDP, 0);
 
 	memset(udph + 1, 0xAA, UDP_PAYLOAD_BYTES);
 
+	meta->flags |= XDP_TXMD_FLAGS_CHECKSUM;
+	meta->request.csum_start = sizeof(*eth) + sizeof(*iph);
+	meta->request.csum_offset = offsetof(struct udphdr, check);
+
 	tx_desc->len = sizeof(*eth) + sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES;
+	tx_desc->options |= XDP_TX_METADATA;
 	xsk_ring_prod__submit(&xsk->tx, 1);
 
 	ret = sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
@@ -192,15 +216,47 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 	return 0;
 }
 
+static int generate_packet_inet(void)
+{
+	char udp_payload[UDP_PAYLOAD_BYTES];
+	struct sockaddr_in rx_addr;
+	int sock_fd, err = 0;
+
+	/* Build a packet */
+	memset(udp_payload, 0xAA, UDP_PAYLOAD_BYTES);
+	rx_addr.sin_addr.s_addr = inet_addr(RX_ADDR);
+	rx_addr.sin_family = AF_INET;
+	rx_addr.sin_port = htons(AF_XDP_CONSUMER_PORT);
+
+	sock_fd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
+	if (!ASSERT_GE(sock_fd, 0, "socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP)"))
+		return sock_fd;
+
+	err = sendto(sock_fd, udp_payload, UDP_PAYLOAD_BYTES, MSG_DONTWAIT,
+		     (void *)&rx_addr, sizeof(rx_addr));
+	ASSERT_GE(err, 0, "sendto");
+
+	close(sock_fd);
+	return err;
+}
+
 static void complete_tx(struct xsk *xsk)
 {
-	__u32 idx;
+	struct xsk_tx_metadata *meta;
 	__u64 addr;
+	void *data;
+	__u32 idx;
 
 	if (ASSERT_EQ(xsk_ring_cons__peek(&xsk->comp, 1, &idx), 1, "xsk_ring_cons__peek")) {
 		addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
 
 		printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr);
+
+		data = xsk_umem__get_data(xsk->umem_area, addr);
+		meta = data - sizeof(struct xsk_tx_metadata);
+
+		ASSERT_NEQ(meta->completion.tx_timestamp, 0, "tx_timestamp");
+
 		xsk_ring_cons__release(&xsk->comp, 1);
 	}
 }
@@ -216,11 +272,12 @@ static void refill_rx(struct xsk *xsk, __u64 addr)
 	}
 }
 
-static int verify_xsk_metadata(struct xsk *xsk)
+static int verify_xsk_metadata(struct xsk *xsk, bool sent_from_af_xdp)
 {
 	const struct xdp_desc *rx_desc;
 	struct pollfd fds = {};
 	struct xdp_meta *meta;
+	struct udphdr *udph;
 	struct ethhdr *eth;
 	struct iphdr *iph;
 	__u64 comp_addr;
@@ -257,6 +314,7 @@ static int verify_xsk_metadata(struct xsk *xsk)
 	ASSERT_EQ(eth->h_proto, htons(ETH_P_IP), "eth->h_proto");
 	iph = (void *)(eth + 1);
 	ASSERT_EQ((int)iph->version, 4, "iph->version");
+	udph = (void *)(iph + 1);
 
 	/* custom metadata */
 
@@ -268,14 +326,42 @@ static int verify_xsk_metadata(struct xsk *xsk)
 	if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
 		return -1;
 
+	if (!sent_from_af_xdp) {
+		if (!ASSERT_NEQ(meta->rx_hash_type & XDP_RSS_TYPE_L4, 0, "rx_hash_type"))
+			return -1;
+
+		if (!ASSERT_EQ(meta->rx_vlan_tci & VLAN_VID_MASK, VLAN_ID, "rx_vlan_tci"))
+			return -1;
+
+		if (!ASSERT_EQ(meta->rx_vlan_proto, VLAN_PID, "rx_vlan_proto"))
+			return -1;
+		goto done;
+	}
+
 	ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type");
 
+	/* checksum offload */
+	ASSERT_EQ(udph->check, htons(0x721c), "csum");
+
+done:
 	xsk_ring_cons__release(&xsk->rx, 1);
 	refill_rx(xsk, comp_addr);
 
 	return 0;
 }
 
+static void switch_ns_to_rx(struct nstoken **tok)
+{
+	close_netns(*tok);
+	*tok = open_netns(RX_NETNS_NAME);
+}
+
+static void switch_ns_to_tx(struct nstoken **tok)
+{
+	close_netns(*tok);
+	*tok = open_netns(TX_NETNS_NAME);
+}
+
 void test_xdp_metadata(void)
 {
 	struct xdp_metadata2 *bpf_obj2 = NULL;
@@ -293,27 +379,35 @@ void test_xdp_metadata(void)
 	int sock_fd;
 	int ret;
 
-	/* Setup new networking namespace, with a veth pair. */
+	/* Setup new networking namespaces, with a veth pair. */
+	SYS(out, "ip netns add " TX_NETNS_NAME);
+	SYS(out, "ip netns add " RX_NETNS_NAME);
 
-	SYS(out, "ip netns add xdp_metadata");
-	tok = open_netns("xdp_metadata");
+	tok = open_netns(TX_NETNS_NAME);
 	SYS(out, "ip link add numtxqueues 1 numrxqueues 1 " TX_NAME
 	    " type veth peer " RX_NAME " numtxqueues 1 numrxqueues 1");
-	SYS(out, "ip link set dev " TX_NAME " address 00:00:00:00:00:01");
-	SYS(out, "ip link set dev " RX_NAME " address 00:00:00:00:00:02");
+	SYS(out, "ip link set " RX_NAME " netns " RX_NETNS_NAME);
+
+	SYS(out, "ip link set dev " TX_NAME " address " TX_MAC);
 	SYS(out, "ip link set dev " TX_NAME " up");
+
+	SYS(out, "ip link add link " TX_NAME " " TX_NAME_VLAN
+		 " type vlan proto " VLAN_PROTO " id " TO_STR(VLAN_ID));
+	SYS(out, "ip link set dev " TX_NAME_VLAN " up");
+	SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME_VLAN);
+
+	/* Avoid ARP calls */
+	SYS(out, "ip -4 neigh add " RX_ADDR " lladdr " RX_MAC " dev " TX_NAME_VLAN);
+
+	switch_ns_to_rx(&tok);
+
+	SYS(out, "ip link set dev " RX_NAME " address " RX_MAC);
 	SYS(out, "ip link set dev " RX_NAME " up");
-	SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME);
 	SYS(out, "ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME);
 
 	rx_ifindex = if_nametoindex(RX_NAME);
-	tx_ifindex = if_nametoindex(TX_NAME);
 
-	/* Setup separate AF_XDP for TX and RX interfaces. */
-
-	ret = open_xsk(tx_ifindex, &tx_xsk);
-	if (!ASSERT_OK(ret, "open_xsk(TX_NAME)"))
-		goto out;
+	/* Setup separate AF_XDP for RX interface. */
 
 	ret = open_xsk(rx_ifindex, &rx_xsk);
 	if (!ASSERT_OK(ret, "open_xsk(RX_NAME)"))
@@ -354,18 +448,38 @@ void test_xdp_metadata(void)
 	if (!ASSERT_GE(ret, 0, "bpf_map_update_elem"))
 		goto out;
 
-	/* Send packet destined to RX AF_XDP socket. */
+	switch_ns_to_tx(&tok);
+
+	/* Setup separate AF_XDP for TX interface nad send packet to the RX socket. */
+	tx_ifindex = if_nametoindex(TX_NAME);
+	ret = open_xsk(tx_ifindex, &tx_xsk);
+	if (!ASSERT_OK(ret, "open_xsk(TX_NAME)"))
+		goto out;
+
 	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
 		       "generate AF_XDP_CONSUMER_PORT"))
 		goto out;
 
-	/* Verify AF_XDP RX packet has proper metadata. */
-	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk), 0,
+	switch_ns_to_rx(&tok);
+
+	/* Verify packet sent from AF_XDP has proper metadata. */
+	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, true), 0,
 		       "verify_xsk_metadata"))
 		goto out;
 
+	switch_ns_to_tx(&tok);
 	complete_tx(&tx_xsk);
 
+	/* Now check metadata of packet, generated with network stack */
+	if (!ASSERT_GE(generate_packet_inet(), 0, "generate UDP packet"))
+		goto out;
+
+	switch_ns_to_rx(&tok);
+
+	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, false), 0,
+		       "verify_xsk_metadata"))
+		goto out;
+
 	/* Make sure freplace correctly picks up original bound device
 	 * and doesn't crash.
 	 */
@@ -383,11 +497,15 @@ void test_xdp_metadata(void)
 	if (!ASSERT_OK(xdp_metadata2__attach(bpf_obj2), "attach freplace"))
 		goto out;
 
+	switch_ns_to_tx(&tok);
+
 	/* Send packet to trigger . */
 	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
 		       "generate freplace packet"))
 		goto out;
 
+	switch_ns_to_rx(&tok);
+
 	while (!retries--) {
 		if (bpf_obj2->bss->called)
 			break;
@@ -402,5 +520,6 @@ out:
 	xdp_metadata__destroy(bpf_obj);
 	if (tok)
 		close_netns(tok);
-	SYS_NOFAIL("ip netns del xdp_metadata");
+	SYS_NOFAIL("ip netns del " RX_NETNS_NAME);
+	SYS_NOFAIL("ip netns del " TX_NETNS_NAME);
 }
diff --git a/tools/testing/selftests/bpf/progs/access_map_in_map.c b/tools/testing/selftests/bpf/progs/access_map_in_map.c
new file mode 100644
index 0000000000..1126871c2e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/access_map_in_map.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <linux/bpf.h>
+#include <time.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+struct inner_map_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+} inner_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct inner_map_type);
+} outer_array_map SEC(".maps") = {
+	.values = {
+		[0] = &inner_map,
+	},
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct inner_map_type);
+} outer_htab_map SEC(".maps") = {
+	.values = {
+		[0] = &inner_map,
+	},
+};
+
+char _license[] SEC("license") = "GPL";
+
+int tgid = 0;
+
+static int acc_map_in_map(void *outer_map)
+{
+	int i, key, value = 0xdeadbeef;
+	void *inner_map;
+
+	if ((bpf_get_current_pid_tgid() >> 32) != tgid)
+		return 0;
+
+	/* Find nonexistent inner map */
+	key = 1;
+	inner_map = bpf_map_lookup_elem(outer_map, &key);
+	if (inner_map)
+		return 0;
+
+	/* Find the old inner map */
+	key = 0;
+	inner_map = bpf_map_lookup_elem(outer_map, &key);
+	if (!inner_map)
+		return 0;
+
+	/* Wait for the old inner map to be replaced */
+	for (i = 0; i < 2048; i++)
+		bpf_map_update_elem(inner_map, &key, &value, 0);
+
+	return 0;
+}
+
+SEC("?kprobe/" SYS_PREFIX "sys_getpgid")
+int access_map_in_array(void *ctx)
+{
+	return acc_map_in_map(&outer_array_map);
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int sleepable_access_map_in_array(void *ctx)
+{
+	return acc_map_in_map(&outer_array_map);
+}
+
+SEC("?kprobe/" SYS_PREFIX "sys_getpgid")
+int access_map_in_htab(void *ctx)
+{
+	return acc_map_in_map(&outer_htab_map);
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int sleepable_access_map_in_htab(void *ctx)
+{
+	return acc_map_in_map(&outer_htab_map);
+}
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
index feaaa2b89c..5014a17d6c 100644
--- 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
@@ -20,7 +20,7 @@ struct {
 } hashmap1 SEC(".maps");
 
 /* will set before prog run */
-volatile const __u32 num_cpus = 0;
+volatile const __s32 num_cpus = 0;
 
 /* will collect results during prog run */
 __u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
index dd923dc637..423b39e60b 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
@@ -35,7 +35,7 @@ SEC("iter/task_vma") int proc_maps(struct bpf_iter__task_vma *ctx)
 		return 0;
 
 	file = vma->vm_file;
-	if (task->tgid != pid) {
+	if (task->tgid != (pid_t)pid) {
 		if (one_task)
 			one_task_error = 1;
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
index 96131b9a1c..6cbb3393f2 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
@@ -22,7 +22,7 @@ int dump_task(struct bpf_iter__task *ctx)
 		return 0;
 	}
 
-	if (task->pid != tid)
+	if (task->pid != (pid_t)tid)
 		num_unknown_tid++;
 	else
 		num_known_tid++;
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 400fdf8d62..dbf61c44ac 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
@@ -45,7 +45,7 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 	}
 
 	/* fill seq_file buffer */
-	for (i = 0; i < print_len; i++)
+	for (i = 0; i < (int)print_len; i++)
 		bpf_seq_write(seq, &seq_num, sizeof(seq_num));
 
 	return ret;
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 799fff4995..2fd59970c4 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -71,6 +71,7 @@
 #define __retval_unpriv(val)	__attribute__((btf_decl_tag("comment:test_retval_unpriv="#val)))
 #define __auxiliary		__attribute__((btf_decl_tag("comment:test_auxiliary")))
 #define __auxiliary_unpriv	__attribute__((btf_decl_tag("comment:test_auxiliary_unpriv")))
+#define __btf_path(path)	__attribute__((btf_decl_tag("comment:test_btf_path=" path)))
 
 /* Convenience macro for use with 'asm volatile' blocks */
 #define __naked __attribute__((naked))
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index 0b793a1027..e8bd4b7b5e 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -26,6 +26,7 @@
 #define IPV6_AUTOFLOWLABEL	70
 
 #define TC_ACT_UNSPEC		(-1)
+#define TC_ACT_OK		0
 #define TC_ACT_SHOT		2
 
 #define SOL_TCP			6
@@ -71,6 +72,8 @@
 #define inet_rcv_saddr		sk.__sk_common.skc_rcv_saddr
 #define inet_dport		sk.__sk_common.skc_dport
 
+#define udp_portaddr_hash	inet.sk.__sk_common.skc_u16hashes[1]
+
 #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
@@ -84,6 +87,7 @@
 #define sk_rmem_alloc		sk_backlog.rmem_alloc
 #define sk_refcnt		__sk_common.skc_refcnt
 #define sk_state		__sk_common.skc_state
+#define sk_net			__sk_common.skc_net
 #define sk_v6_daddr		__sk_common.skc_v6_daddr
 #define sk_v6_rcv_saddr		__sk_common.skc_v6_rcv_saddr
 #define sk_flags		__sk_common.skc_flags
diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
index b7fa8804e1..45a0e9f492 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
@@ -11,7 +11,7 @@
 __u32 invocations = 0;
 __u32 assertion_error = 0;
 __u32 retval_value = 0;
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 SEC("cgroup/setsockopt")
 int get_retval(struct bpf_sockopt *ctx)
diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
index 0fa564a5cc..9fe9c4a4e8 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
@@ -78,7 +78,7 @@ int BPF_PROG(cgrp_kfunc_acquire_fp, struct cgroup *cgrp, const char *path)
 }
 
 SEC("kretprobe/cgroup_destroy_locked")
-__failure __msg("reg type unsupported for arg#0 function")
+__failure __msg("calling kernel function bpf_cgroup_acquire is not allowed")
 int BPF_PROG(cgrp_kfunc_acquire_unsafe_kretprobe, struct cgroup *cgrp)
 {
 	struct cgroup *acquired;
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
index a043d8fefd..610c2427fd 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
@@ -21,50 +21,100 @@ struct {
 	__type(value, long);
 } map_b SEC(".maps");
 
+int target_hid = 0;
+bool is_cgroup1 = 0;
+
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+
+static void __on_lookup(struct cgroup *cgrp)
+{
+	bpf_cgrp_storage_delete(&map_a, cgrp);
+	bpf_cgrp_storage_delete(&map_b, cgrp);
+}
+
 SEC("fentry/bpf_local_storage_lookup")
 int BPF_PROG(on_lookup)
 {
 	struct task_struct *task = bpf_get_current_task_btf();
+	struct cgroup *cgrp;
+
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
 
-	bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp);
-	bpf_cgrp_storage_delete(&map_b, task->cgroups->dfl_cgrp);
+		__on_lookup(cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_lookup(task->cgroups->dfl_cgrp);
 	return 0;
 }
 
-SEC("fentry/bpf_local_storage_update")
-int BPF_PROG(on_update)
+static void __on_update(struct cgroup *cgrp)
 {
-	struct task_struct *task = bpf_get_current_task_btf();
 	long *ptr;
 
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr += 1;
 
-	ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_b, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr += 1;
+}
 
+SEC("fentry/bpf_local_storage_update")
+int BPF_PROG(on_update)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct cgroup *cgrp;
+
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_update(cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_update(task->cgroups->dfl_cgrp);
 	return 0;
 }
 
-SEC("tp_btf/sys_enter")
-int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+static void __on_enter(struct pt_regs *regs, long id, struct cgroup *cgrp)
 {
-	struct task_struct *task;
 	long *ptr;
 
-	task = bpf_get_current_task_btf();
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr = 200;
 
-	ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_b, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr = 100;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct cgroup *cgrp;
+
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_enter(regs, id, cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_enter(regs, id, task->cgroups->dfl_cgrp);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
index 4c7844e1db..5e282c16ea 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
@@ -15,9 +15,13 @@ struct {
 	__type(value, long);
 } map_a SEC(".maps");
 
-__u32 target_pid;
+__s32 target_pid;
 __u64 cgroup_id;
+int target_hid;
+bool is_cgroup1;
 
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
 void bpf_rcu_read_lock(void) __ksym;
 void bpf_rcu_read_unlock(void) __ksym;
 
@@ -37,23 +41,50 @@ int cgroup_iter(struct bpf_iter__cgroup *ctx)
 	return 0;
 }
 
+static void __no_rcu_lock(struct cgroup *cgrp)
+{
+	long *ptr;
+
+	/* Note that trace rcu is held in sleepable prog, so we can use
+	 * bpf_cgrp_storage_get() in sleepable prog.
+	 */
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (ptr)
+		cgroup_id = cgrp->kn->id;
+}
+
 SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
-int no_rcu_lock(void *ctx)
+int cgrp1_no_rcu_lock(void *ctx)
 {
 	struct task_struct *task;
 	struct cgroup *cgrp;
-	long *ptr;
+
+	task = bpf_get_current_task_btf();
+	if (task->pid != target_pid)
+		return 0;
+
+	/* bpf_task_get_cgroup1 can work in sleepable prog */
+	cgrp = bpf_task_get_cgroup1(task, target_hid);
+	if (!cgrp)
+		return 0;
+
+	__no_rcu_lock(cgrp);
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int no_rcu_lock(void *ctx)
+{
+	struct task_struct *task;
 
 	task = bpf_get_current_task_btf();
 	if (task->pid != target_pid)
 		return 0;
 
 	/* task->cgroups is untrusted in sleepable prog outside of RCU CS */
-	cgrp = task->cgroups->dfl_cgrp;
-	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (ptr)
-		cgroup_id = cgrp->kn->id;
+	__no_rcu_lock(task->cgroups->dfl_cgrp);
 	return 0;
 }
 
@@ -68,6 +99,22 @@ int yes_rcu_lock(void *ctx)
 	if (task->pid != target_pid)
 		return 0;
 
+	if (is_cgroup1) {
+		bpf_rcu_read_lock();
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp) {
+			bpf_rcu_read_unlock();
+			return 0;
+		}
+
+		ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
+		if (ptr)
+			cgroup_id = cgrp->kn->id;
+		bpf_cgroup_release(cgrp);
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+
 	bpf_rcu_read_lock();
 	cgrp = task->cgroups->dfl_cgrp;
 	/* cgrp is trusted under RCU CS */
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c
index 9ebb8e2fe5..1c348f000f 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c
@@ -27,62 +27,100 @@ pid_t target_pid = 0;
 int mismatch_cnt = 0;
 int enter_cnt = 0;
 int exit_cnt = 0;
+int target_hid = 0;
+bool is_cgroup1 = 0;
 
-SEC("tp_btf/sys_enter")
-int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+
+static void __on_enter(struct pt_regs *regs, long id, struct cgroup *cgrp)
 {
-	struct task_struct *task;
 	long *ptr;
 	int err;
 
-	task = bpf_get_current_task_btf();
-	if (task->pid != target_pid)
-		return 0;
-
 	/* populate value 0 */
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!ptr)
-		return 0;
+		return;
 
 	/* delete value 0 */
-	err = bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp);
+	err = bpf_cgrp_storage_delete(&map_a, cgrp);
 	if (err)
-		return 0;
+		return;
 
 	/* value is not available */
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, 0);
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, 0);
 	if (ptr)
-		return 0;
+		return;
 
 	/* re-populate the value */
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!ptr)
-		return 0;
+		return;
 	__sync_fetch_and_add(&enter_cnt, 1);
 	*ptr = MAGIC_VALUE + enter_cnt;
-
-	return 0;
 }
 
-SEC("tp_btf/sys_exit")
-int BPF_PROG(on_exit, struct pt_regs *regs, long id)
+SEC("tp_btf/sys_enter")
+int BPF_PROG(on_enter, struct pt_regs *regs, long id)
 {
 	struct task_struct *task;
-	long *ptr;
+	struct cgroup *cgrp;
 
 	task = bpf_get_current_task_btf();
 	if (task->pid != target_pid)
 		return 0;
 
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_enter(regs, id, cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_enter(regs, id, task->cgroups->dfl_cgrp);
+	return 0;
+}
+
+static void __on_exit(struct pt_regs *regs, long id, struct cgroup *cgrp)
+{
+	long *ptr;
+
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!ptr)
-		return 0;
+		return;
 
 	__sync_fetch_and_add(&exit_cnt, 1);
 	if (*ptr != MAGIC_VALUE + exit_cnt)
 		__sync_fetch_and_add(&mismatch_cnt, 1);
+}
+
+SEC("tp_btf/sys_exit")
+int BPF_PROG(on_exit, struct pt_regs *regs, long id)
+{
+	struct task_struct *task;
+	struct cgroup *cgrp;
+
+	task = bpf_get_current_task_btf();
+	if (task->pid != target_pid)
+		return 0;
+
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_exit(regs, id, cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_exit(regs, id, task->cgroups->dfl_cgrp);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h
index b15c588ace..0cd4aebb97 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_common.h
+++ b/tools/testing/selftests/bpf/progs/cpumask_common.h
@@ -54,6 +54,7 @@ bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym;
 void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym;
 u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym;
 u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym;
 
 void bpf_rcu_read_lock(void) __ksym;
 void bpf_rcu_read_unlock(void) __ksym;
diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c
index 674a63424d..7a1e64c6c0 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_success.c
+++ b/tools/testing/selftests/bpf/progs/cpumask_success.c
@@ -332,7 +332,7 @@ SEC("tp_btf/task_newtask")
 int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags)
 {
 	struct bpf_cpumask *mask1, *mask2, *dst1, *dst2;
-	u32 cpu;
+	int cpu;
 
 	if (!is_test_task())
 		return 0;
@@ -461,6 +461,49 @@ int BPF_PROG(test_global_mask_rcu, struct task_struct *task, u64 clone_flags)
 }
 
 SEC("tp_btf/task_newtask")
+int BPF_PROG(test_cpumask_weight, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local;
+
+	if (!is_test_task())
+		return 0;
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	if (bpf_cpumask_weight(cast(local)) != 0) {
+		err = 3;
+		goto out;
+	}
+
+	bpf_cpumask_set_cpu(0, local);
+	if (bpf_cpumask_weight(cast(local)) != 1) {
+		err = 4;
+		goto out;
+	}
+
+	/*
+	 * Make sure that adding additional CPUs changes the weight. Test to
+	 * see whether the CPU was set to account for running on UP machines.
+	 */
+	bpf_cpumask_set_cpu(1, local);
+	if (bpf_cpumask_test_cpu(1, cast(local)) && bpf_cpumask_weight(cast(local)) != 2) {
+		err = 5;
+		goto out;
+	}
+
+	bpf_cpumask_clear(local);
+	if (bpf_cpumask_weight(cast(local)) != 0) {
+		err = 6;
+		goto out;
+	}
+out:
+	bpf_cpumask_release(local);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
 __success
 int BPF_PROG(test_refcount_null_tracking, struct task_struct *task, u64 clone_flags)
 {
diff --git a/tools/testing/selftests/bpf/progs/exceptions.c b/tools/testing/selftests/bpf/progs/exceptions.c
index 2811ee842b..f09cd14d8e 100644
--- a/tools/testing/selftests/bpf/progs/exceptions.c
+++ b/tools/testing/selftests/bpf/progs/exceptions.c
@@ -210,7 +210,7 @@ __noinline int assert_zero_gfunc(u64 c)
 {
 	volatile u64 cookie = c;
 
-	bpf_assert_eq(cookie, 0);
+	bpf_assert(bpf_cmp_unlikely(cookie, ==, 0));
 	return 0;
 }
 
@@ -218,7 +218,7 @@ __noinline int assert_neg_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_lt(cookie, 0);
+	bpf_assert(bpf_cmp_unlikely(cookie, <, 0));
 	return 0;
 }
 
@@ -226,7 +226,7 @@ __noinline int assert_pos_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_gt(cookie, 0);
+	bpf_assert(bpf_cmp_unlikely(cookie, >, 0));
 	return 0;
 }
 
@@ -234,7 +234,7 @@ __noinline int assert_negeq_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_le(cookie, -1);
+	bpf_assert(bpf_cmp_unlikely(cookie, <=, -1));
 	return 0;
 }
 
@@ -242,7 +242,7 @@ __noinline int assert_poseq_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_ge(cookie, 1);
+	bpf_assert(bpf_cmp_unlikely(cookie, >=, 1));
 	return 0;
 }
 
@@ -258,7 +258,7 @@ __noinline int assert_zero_gfunc_with(u64 c)
 {
 	volatile u64 cookie = c;
 
-	bpf_assert_eq_with(cookie, 0, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, ==, 0), cookie + 100);
 	return 0;
 }
 
@@ -266,7 +266,7 @@ __noinline int assert_neg_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_lt_with(cookie, 0, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, <, 0), cookie + 100);
 	return 0;
 }
 
@@ -274,7 +274,7 @@ __noinline int assert_pos_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_gt_with(cookie, 0, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, >, 0), cookie + 100);
 	return 0;
 }
 
@@ -282,7 +282,7 @@ __noinline int assert_negeq_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_le_with(cookie, -1, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, <=, -1), cookie + 100);
 	return 0;
 }
 
@@ -290,7 +290,7 @@ __noinline int assert_poseq_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_ge_with(cookie, 1, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, >=, 1), cookie + 100);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c
index e1e5c54a6a..5e0a1ca96d 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_assert.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c
@@ -11,55 +11,55 @@
 #define check_assert(type, op, name, value)				\
 	SEC("?tc")							\
 	__log_level(2) __failure					\
-	int check_assert_##op##_##name(void *ctx)			\
+	int check_assert_##name(void *ctx)				\
 	{								\
 		type num = bpf_ktime_get_ns();				\
-		bpf_assert_##op(num, value);				\
+		bpf_assert(bpf_cmp_unlikely(num, op, value));		\
 		return *(u64 *)num;					\
 	}
 
-__msg(": R0_w=-2147483648 R10=fp0")
-check_assert(s64, eq, int_min, INT_MIN);
-__msg(": R0_w=2147483647 R10=fp0")
-check_assert(s64, eq, int_max, INT_MAX);
-__msg(": R0_w=0 R10=fp0")
-check_assert(s64, eq, zero, 0);
-__msg(": R0_w=-9223372036854775808 R1_w=-9223372036854775808 R10=fp0")
-check_assert(s64, eq, llong_min, LLONG_MIN);
-__msg(": R0_w=9223372036854775807 R1_w=9223372036854775807 R10=fp0")
-check_assert(s64, eq, llong_max, LLONG_MAX);
-
-__msg(": R0_w=scalar(smax=2147483646) R10=fp0")
-check_assert(s64, lt, pos, INT_MAX);
-__msg(": R0_w=scalar(smax=-1,umin=9223372036854775808,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
-check_assert(s64, lt, zero, 0);
-__msg(": R0_w=scalar(smax=-2147483649,umin=9223372036854775808,umax=18446744071562067967,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
-check_assert(s64, lt, neg, INT_MIN);
-
-__msg(": R0_w=scalar(smax=2147483647) R10=fp0")
-check_assert(s64, le, pos, INT_MAX);
-__msg(": R0_w=scalar(smax=0) R10=fp0")
-check_assert(s64, le, zero, 0);
-__msg(": R0_w=scalar(smax=-2147483648,umin=9223372036854775808,umax=18446744071562067968,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
-check_assert(s64, le, neg, INT_MIN);
-
-__msg(": R0_w=scalar(smin=umin=2147483648,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
-check_assert(s64, gt, pos, INT_MAX);
-__msg(": R0_w=scalar(smin=umin=1,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
-check_assert(s64, gt, zero, 0);
-__msg(": R0_w=scalar(smin=-2147483647) R10=fp0")
-check_assert(s64, gt, neg, INT_MIN);
-
-__msg(": R0_w=scalar(smin=umin=2147483647,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
-check_assert(s64, ge, pos, INT_MAX);
-__msg(": R0_w=scalar(smin=0,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0")
-check_assert(s64, ge, zero, 0);
-__msg(": R0_w=scalar(smin=-2147483648) R10=fp0")
-check_assert(s64, ge, neg, INT_MIN);
+__msg(": R0_w=0xffffffff80000000")
+check_assert(s64, ==, eq_int_min, INT_MIN);
+__msg(": R0_w=0x7fffffff")
+check_assert(s64, ==, eq_int_max, INT_MAX);
+__msg(": R0_w=0")
+check_assert(s64, ==, eq_zero, 0);
+__msg(": R0_w=0x8000000000000000 R1_w=0x8000000000000000")
+check_assert(s64, ==, eq_llong_min, LLONG_MIN);
+__msg(": R0_w=0x7fffffffffffffff R1_w=0x7fffffffffffffff")
+check_assert(s64, ==, eq_llong_max, LLONG_MAX);
+
+__msg(": R0_w=scalar(id=1,smax=0x7ffffffe)")
+check_assert(s64, <, lt_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+check_assert(s64, <, lt_zero, 0);
+__msg(": R0_w=scalar(id=1,smax=0xffffffff7fffffff")
+check_assert(s64, <, lt_neg, INT_MIN);
+
+__msg(": R0_w=scalar(id=1,smax=0x7fffffff)")
+check_assert(s64, <=, le_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smax=0)")
+check_assert(s64, <=, le_zero, 0);
+__msg(": R0_w=scalar(id=1,smax=0xffffffff80000000")
+check_assert(s64, <=, le_neg, INT_MIN);
+
+__msg(": R0_w=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >, gt_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >, gt_zero, 0);
+__msg(": R0_w=scalar(id=1,smin=0xffffffff80000001")
+check_assert(s64, >, gt_neg, INT_MIN);
+
+__msg(": R0_w=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >=, ge_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >=, ge_zero, 0);
+__msg(": R0_w=scalar(id=1,smin=0xffffffff80000000")
+check_assert(s64, >=, ge_neg, INT_MIN);
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R0=0 R1=ctx(off=0,imm=0) R2=scalar(smin=smin32=-2147483646,smax=smax32=2147483645) R10=fp0")
+__msg(": R0=0 R1=ctx() R2=scalar(smin=0xffffffff80000002,smax=smax32=0x7ffffffd,smin32=0x80000002) R10=fp0")
 int check_assert_range_s64(struct __sk_buff *ctx)
 {
 	struct bpf_sock *sk = ctx->sk;
@@ -75,7 +75,7 @@ int check_assert_range_s64(struct __sk_buff *ctx)
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R1=ctx(off=0,imm=0) R2=scalar(smin=umin=smin32=umin32=4096,smax=umax=smax32=umax32=8192,var_off=(0x0; 0x3fff))")
+__msg(": R1=ctx() R2=scalar(smin=umin=smin32=umin32=4096,smax=umax=smax32=umax32=8192,var_off=(0x0; 0x3fff))")
 int check_assert_range_u64(struct __sk_buff *ctx)
 {
 	u64 num = ctx->len;
@@ -86,7 +86,7 @@ int check_assert_range_u64(struct __sk_buff *ctx)
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R0=0 R1=ctx(off=0,imm=0) R2=4096 R10=fp0")
+__msg(": R0=0 R1=ctx() R2=4096 R10=fp0")
 int check_assert_single_range_s64(struct __sk_buff *ctx)
 {
 	struct bpf_sock *sk = ctx->sk;
@@ -103,7 +103,7 @@ int check_assert_single_range_s64(struct __sk_buff *ctx)
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R1=ctx(off=0,imm=0) R2=4096 R10=fp0")
+__msg(": R1=ctx() R2=4096 R10=fp0")
 int check_assert_single_range_u64(struct __sk_buff *ctx)
 {
 	u64 num = ctx->len;
@@ -114,7 +114,7 @@ int check_assert_single_range_u64(struct __sk_buff *ctx)
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R1=pkt(off=64,r=64,imm=0) R2=pkt_end(off=0,imm=0) R6=pkt(off=0,r=64,imm=0) R10=fp0")
+__msg(": R1=pkt(off=64,r=64) R2=pkt_end() R6=pkt(r=64) R10=fp0")
 int check_assert_generic(struct __sk_buff *ctx)
 {
 	u8 *data_end = (void *)(long)ctx->data_end;
@@ -125,7 +125,7 @@ int check_assert_generic(struct __sk_buff *ctx)
 }
 
 SEC("?fentry/bpf_check")
-__failure __msg("At program exit the register R0 has value (0x40; 0x0)")
+__failure __msg("At program exit the register R1 has smin=64 smax=64")
 int check_assert_with_return(void *ctx)
 {
 	bpf_assert_with(!ctx, 64);
diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c
index 8c0ef27422..9cceb65211 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_fail.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c
@@ -308,7 +308,7 @@ int reject_set_exception_cb_bad_ret1(void *ctx)
 }
 
 SEC("?fentry/bpf_check")
-__failure __msg("At program exit the register R0 has value (0x40; 0x0) should")
+__failure __msg("At program exit the register R1 has smin=64 smax=64 should")
 int reject_set_exception_cb_bad_ret2(void *ctx)
 {
 	bpf_throw(64);
diff --git a/tools/testing/selftests/bpf/progs/fentry_recursive.c b/tools/testing/selftests/bpf/progs/fentry_recursive.c
new file mode 100644
index 0000000000..2c9fb5ac42
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_recursive.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* Dummy fentry bpf prog for testing fentry attachment chains */
+SEC("fentry/XXX")
+int BPF_PROG(recursive_attach, int a)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/fentry_recursive_target.c b/tools/testing/selftests/bpf/progs/fentry_recursive_target.c
new file mode 100644
index 0000000000..267c876d0a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_recursive_target.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* Dummy fentry bpf prog for testing fentry attachment chains. It's going to be
+ * a start of the chain.
+ */
+SEC("fentry/bpf_testmod_fentry_test1")
+int BPF_PROG(test1, int a)
+{
+	return 0;
+}
+
+/* Dummy bpf prog for testing attach_btf presence when attaching an fentry
+ * program.
+ */
+SEC("raw_tp/sys_enter")
+int BPF_PROG(fentry_target, struct pt_regs *regs, long id)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c b/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c
new file mode 100644
index 0000000000..e6a75f86ca
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("freplace")
+int freplace_prog(void)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c b/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c
new file mode 100644
index 0000000000..624078abf3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+SEC("freplace/btf_unreliable_kprobe")
+/* context type is what BPF verifier expects for kprobe context, but target
+ * program has `stuct whatever *ctx` argument, so freplace operation will be
+ * rejected with the following message:
+ *
+ * arg0 replace_btf_unreliable_kprobe(struct pt_regs *) doesn't match btf_unreliable_kprobe(struct whatever *)
+ */
+int replace_btf_unreliable_kprobe(bpf_user_pt_regs_t *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 844d968c27..fe971992e6 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -6,7 +6,7 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#define ARRAY_SIZE(x) (int)(sizeof(x) / sizeof((x)[0]))
 
 static volatile int zero = 0;
 
@@ -676,7 +676,7 @@ static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n)
 
 	while ((t = bpf_iter_num_next(it))) {
 		i = *t;
-		if (i >= n)
+		if ((__u32)i >= n)
 			break;
 		sum += arr[i];
 	}
@@ -1411,4 +1411,26 @@ __naked int checkpoint_states_deletion(void)
 	);
 }
 
+struct {
+	int data[32];
+	int n;
+} loop_data;
+
+SEC("raw_tp")
+__success
+int iter_arr_with_actual_elem_count(const void *ctx)
+{
+	int i, n = loop_data.n, sum = 0;
+
+	if (n > ARRAY_SIZE(loop_data.data))
+		return 0;
+
+	bpf_for(i, 0, n) {
+		/* no rechecking of i against ARRAY_SIZE(loop_data.n) */
+		sum += loop_data.data[i];
+	}
+
+	return sum;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c
index c9b4055cd4..e4d53e40ff 100644
--- a/tools/testing/selftests/bpf/progs/iters_task.c
+++ b/tools/testing/selftests/bpf/progs/iters_task.c
@@ -10,7 +10,7 @@
 char _license[] SEC("license") = "GPL";
 
 pid_t target_pid;
-int procs_cnt, threads_cnt, proc_threads_cnt;
+int procs_cnt, threads_cnt, proc_threads_cnt, invalid_cnt;
 
 void bpf_rcu_read_lock(void) __ksym;
 void bpf_rcu_read_unlock(void) __ksym;
@@ -26,6 +26,16 @@ int iter_task_for_each_sleep(void *ctx)
 	procs_cnt = threads_cnt = proc_threads_cnt = 0;
 
 	bpf_rcu_read_lock();
+	bpf_for_each(task, pos, NULL, ~0U) {
+		/* Below instructions shouldn't be executed for invalid flags */
+		invalid_cnt++;
+	}
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_PROC_THREADS) {
+		/* Below instructions shouldn't be executed for invalid task__nullable */
+		invalid_cnt++;
+	}
+
 	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS)
 		if (pos->pid == target_pid)
 			procs_cnt++;
diff --git a/tools/testing/selftests/bpf/progs/iters_task_vma.c b/tools/testing/selftests/bpf/progs/iters_task_vma.c
index e085a51d15..dc0c3691dc 100644
--- a/tools/testing/selftests/bpf/progs/iters_task_vma.c
+++ b/tools/testing/selftests/bpf/progs/iters_task_vma.c
@@ -28,9 +28,8 @@ int iter_task_vma_for_each(const void *ctx)
 		return 0;
 
 	bpf_for_each(task_vma, vma, task, 0) {
-		if (seen >= 1000)
+		if (bpf_cmp_unlikely(seen, >=, 1000))
 			break;
-		barrier_var(seen);
 
 		vm_ranges[seen].vm_start = vma->vm_start;
 		vm_ranges[seen].vm_end = vma->vm_end;
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs1.c b/tools/testing/selftests/bpf/progs/linked_funcs1.c
index c4b49ceea9..cc79dddac1 100644
--- a/tools/testing/selftests/bpf/progs/linked_funcs1.c
+++ b/tools/testing/selftests/bpf/progs/linked_funcs1.c
@@ -8,7 +8,7 @@
 #include "bpf_misc.h"
 
 /* weak and shared between two files */
-const volatile int my_tid __weak;
+const volatile __u32 my_tid __weak;
 long syscall_id __weak;
 
 int output_val1;
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs2.c b/tools/testing/selftests/bpf/progs/linked_funcs2.c
index 013ff0645f..942cc5526d 100644
--- a/tools/testing/selftests/bpf/progs/linked_funcs2.c
+++ b/tools/testing/selftests/bpf/progs/linked_funcs2.c
@@ -68,7 +68,7 @@ int BPF_PROG(handler2, struct pt_regs *regs, long id)
 {
 	static volatile int whatever;
 
-	if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id)
+	if (my_tid != (s32)bpf_get_current_pid_tgid() || id != syscall_id)
 		return 0;
 
 	/* make sure we have CO-RE relocations in main program */
diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c
index 84d1777a9e..26205ca806 100644
--- a/tools/testing/selftests/bpf/progs/linked_list.c
+++ b/tools/testing/selftests/bpf/progs/linked_list.c
@@ -6,7 +6,7 @@
 #include "bpf_experimental.h"
 
 #ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#define ARRAY_SIZE(x) (int)(sizeof(x) / sizeof((x)[0]))
 #endif
 
 #include "linked_list.h"
diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c
index b567a666d2..75043ffc5d 100644
--- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c
+++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c
@@ -14,16 +14,41 @@ struct node_data {
 	struct bpf_rb_node node;
 };
 
+struct refcounted_node {
+	long data;
+	struct bpf_rb_node rb_node;
+	struct bpf_refcount refcount;
+};
+
+struct stash {
+	struct bpf_spin_lock l;
+	struct refcounted_node __kptr *stashed;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct stash);
+	__uint(max_entries, 10);
+} refcounted_node_stash SEC(".maps");
+
 struct plain_local {
 	long key;
 	long data;
 };
 
+struct local_with_root {
+	long key;
+	struct bpf_spin_lock l;
+	struct bpf_rb_root r __contains(node_data, node);
+};
+
 struct map_value {
 	struct prog_test_ref_kfunc *not_kptr;
 	struct prog_test_ref_kfunc __kptr *val;
 	struct node_data __kptr *node;
 	struct plain_local __kptr *plain;
+	struct local_with_root __kptr *local_root;
 };
 
 /* This is necessary so that LLVM generates BTF for node_data struct
@@ -38,6 +63,7 @@ struct map_value {
  * Had to do the same w/ bpf_kfunc_call_test_release below
  */
 struct node_data *just_here_because_btf_bug;
+struct refcounted_node *just_here_because_btf_bug2;
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -46,6 +72,17 @@ struct {
 	__uint(max_entries, 2);
 } some_nodes SEC(".maps");
 
+static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = container_of(a, struct node_data, node);
+	node_b = container_of(b, struct node_data, node);
+
+	return node_a->key < node_b->key;
+}
+
 static int create_and_stash(int idx, int val)
 {
 	struct map_value *mapval;
@@ -95,6 +132,41 @@ long stash_plain(void *ctx)
 }
 
 SEC("tc")
+long stash_local_with_root(void *ctx)
+{
+	struct local_with_root *res;
+	struct map_value *mapval;
+	struct node_data *n;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	res = bpf_obj_new(typeof(*res));
+	if (!res)
+		return 2;
+	res->key = 41;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n) {
+		bpf_obj_drop(res);
+		return 3;
+	}
+
+	bpf_spin_lock(&res->l);
+	bpf_rbtree_add(&res->r, &n->node, less);
+	bpf_spin_unlock(&res->l);
+
+	res = bpf_kptr_xchg(&mapval->local_root, res);
+	if (res) {
+		bpf_obj_drop(res);
+		return 4;
+	}
+	return 0;
+}
+
+SEC("tc")
 long unstash_rb_node(void *ctx)
 {
 	struct map_value *mapval;
@@ -132,4 +204,56 @@ long stash_test_ref_kfunc(void *ctx)
 	return 0;
 }
 
+SEC("tc")
+long refcount_acquire_without_unstash(void *ctx)
+{
+	struct refcounted_node *p;
+	struct stash *s;
+	int ret = 0;
+
+	s = bpf_map_lookup_elem(&refcounted_node_stash, &ret);
+	if (!s)
+		return 1;
+
+	if (!s->stashed)
+		/* refcount_acquire failure is expected when no refcounted_node
+		 * has been stashed before this program executes
+		 */
+		return 2;
+
+	p = bpf_refcount_acquire(s->stashed);
+	if (!p)
+		return 3;
+
+	ret = s->stashed ? s->stashed->data : -1;
+	bpf_obj_drop(p);
+	return ret;
+}
+
+/* Helper for refcount_acquire_without_unstash test */
+SEC("tc")
+long stash_refcounted_node(void *ctx)
+{
+	struct refcounted_node *p;
+	struct stash *s;
+	int key = 0;
+
+	s = bpf_map_lookup_elem(&refcounted_node_stash, &key);
+	if (!s)
+		return 1;
+
+	p = bpf_obj_new(typeof(*p));
+	if (!p)
+		return 2;
+	p->data = 42;
+
+	p = bpf_kptr_xchg(&s->stashed, p);
+	if (p) {
+		bpf_obj_drop(p);
+		return 3;
+	}
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index bc8ea56671..e5e3a8b8dd 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -13,7 +13,7 @@ char _license[] SEC("license") = "GPL";
 
 #define DUMMY_STORAGE_VALUE 0xdeadbeef
 
-int monitored_pid = 0;
+__u32 monitored_pid = 0;
 int inode_storage_result = -1;
 int sk_storage_result = -1;
 int task_storage_result = -1;
diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c
index fadfdd9870..0c13b74099 100644
--- a/tools/testing/selftests/bpf/progs/lsm.c
+++ b/tools/testing/selftests/bpf/progs/lsm.c
@@ -92,7 +92,7 @@ int BPF_PROG(test_int_hook, struct vm_area_struct *vma,
 	if (ret != 0)
 		return ret;
 
-	__u32 pid = bpf_get_current_pid_tgid() >> 32;
+	__s32 pid = bpf_get_current_pid_tgid() >> 32;
 	int is_stack = 0;
 
 	is_stack = (vma->vm_start <= vma->vm_mm->start_stack &&
diff --git a/tools/testing/selftests/bpf/progs/map_in_map_btf.c b/tools/testing/selftests/bpf/progs/map_in_map_btf.c
new file mode 100644
index 0000000000..7a1336d7b1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_in_map_btf.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct node_data {
+	__u64 data;
+	struct bpf_list_node node;
+};
+
+struct map_value {
+	struct bpf_list_head head __contains(node_data, node);
+	struct bpf_spin_lock lock;
+};
+
+struct inner_array_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} inner_array SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+	__array(values, struct inner_array_type);
+} outer_array SEC(".maps") = {
+	.values = {
+		[0] = &inner_array,
+	},
+};
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+bool done = false;
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int add_to_list_in_inner_array(void *ctx)
+{
+	struct map_value *value;
+	struct node_data *new;
+	struct bpf_map *map;
+	int zero = 0;
+
+	if (done || (u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	map = bpf_map_lookup_elem(&outer_array, &zero);
+	if (!map)
+		return 0;
+
+	value = bpf_map_lookup_elem(map, &zero);
+	if (!value)
+		return 0;
+
+	new = bpf_obj_new(typeof(*new));
+	if (!new)
+		return 0;
+
+	bpf_spin_lock(&value->lock);
+	bpf_list_push_back(&value->head, &new->node);
+	bpf_spin_unlock(&value->lock);
+	done = true;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/normal_map_btf.c b/tools/testing/selftests/bpf/progs/normal_map_btf.c
new file mode 100644
index 0000000000..a45c929955
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/normal_map_btf.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct node_data {
+	__u64 data;
+	struct bpf_list_node node;
+};
+
+struct map_value {
+	struct bpf_list_head head __contains(node_data, node);
+	struct bpf_spin_lock lock;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} array SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+bool done = false;
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int add_to_list_in_array(void *ctx)
+{
+	struct map_value *value;
+	struct node_data *new;
+	int zero = 0;
+
+	if (done || (int)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	value = bpf_map_lookup_elem(&array, &zero);
+	if (!value)
+		return 0;
+
+	new = bpf_obj_new(typeof(*new));
+	if (!new)
+		return 0;
+
+	bpf_spin_lock(&value->lock);
+	bpf_list_push_back(&value->head, &new->node);
+	bpf_spin_unlock(&value->lock);
+	done = true;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
index 1a891d30f1..f2b8eb2ff7 100644
--- a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
@@ -17,6 +17,10 @@ struct val_with_rb_root_t {
 	struct bpf_spin_lock lock;
 };
 
+struct val_600b_t {
+	char b[600];
+};
+
 struct elem {
 	long sum;
 	struct val_t __percpu_kptr *pc;
@@ -161,4 +165,18 @@ int BPF_PROG(test_array_map_7)
 	return 0;
 }
 
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("bpf_percpu_obj_new type size (600) is greater than 512")
+int BPF_PROG(test_array_map_8)
+{
+	struct val_600b_t __percpu_kptr *p;
+
+	p = bpf_percpu_obj_new(struct val_600b_t);
+	if (!p)
+		return 0;
+
+	bpf_percpu_obj_drop(p);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 897061930c..de3b6e4e4d 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -7,6 +7,7 @@
 
 #include "profiler.h"
 #include "err.h"
+#include "bpf_experimental.h"
 
 #ifndef NULL
 #define NULL 0
@@ -132,7 +133,7 @@ struct {
 } disallowed_exec_inodes SEC(".maps");
 
 #ifndef ARRAY_SIZE
-#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
+#define ARRAY_SIZE(arr) (int)(sizeof(arr) / sizeof(arr[0]))
 #endif
 
 static INLINE bool IS_ERR(const void* ptr)
@@ -221,8 +222,7 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node,
 			return payload;
 		if (cgroup_node == cgroup_root_node)
 			*root_pos = payload - payload_start;
-		if (filepart_length <= MAX_PATH) {
-			barrier_var(filepart_length);
+		if (bpf_cmp_likely(filepart_length, <=, MAX_PATH)) {
 			payload += filepart_length;
 		}
 		cgroup_node = BPF_CORE_READ(cgroup_node, parent);
@@ -305,9 +305,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 	size_t cgroup_root_length =
 		bpf_probe_read_kernel_str(payload, MAX_PATH,
 					  BPF_CORE_READ(root_kernfs, name));
-	barrier_var(cgroup_root_length);
-	if (cgroup_root_length <= MAX_PATH) {
-		barrier_var(cgroup_root_length);
+	if (bpf_cmp_likely(cgroup_root_length, <=, MAX_PATH)) {
 		cgroup_data->cgroup_root_length = cgroup_root_length;
 		payload += cgroup_root_length;
 	}
@@ -315,9 +313,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 	size_t cgroup_proc_length =
 		bpf_probe_read_kernel_str(payload, MAX_PATH,
 					  BPF_CORE_READ(proc_kernfs, name));
-	barrier_var(cgroup_proc_length);
-	if (cgroup_proc_length <= MAX_PATH) {
-		barrier_var(cgroup_proc_length);
+	if (bpf_cmp_likely(cgroup_proc_length, <=, MAX_PATH)) {
 		cgroup_data->cgroup_proc_length = cgroup_proc_length;
 		payload += cgroup_proc_length;
 	}
@@ -347,9 +343,7 @@ static INLINE void* populate_var_metadata(struct var_metadata_t* metadata,
 	metadata->comm_length = 0;
 
 	size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm);
-	barrier_var(comm_length);
-	if (comm_length <= TASK_COMM_LEN) {
-		barrier_var(comm_length);
+	if (bpf_cmp_likely(comm_length, <=, TASK_COMM_LEN)) {
 		metadata->comm_length = comm_length;
 		payload += comm_length;
 	}
@@ -494,10 +488,9 @@ read_absolute_file_path_from_dentry(struct dentry* filp_dentry, void* payload)
 		filepart_length =
 			bpf_probe_read_kernel_str(payload, MAX_PATH,
 						  BPF_CORE_READ(filp_dentry, d_name.name));
-		barrier_var(filepart_length);
-		if (filepart_length > MAX_PATH)
+		bpf_nop_mov(filepart_length);
+		if (bpf_cmp_unlikely(filepart_length, >, MAX_PATH))
 			break;
-		barrier_var(filepart_length);
 		payload += filepart_length;
 		length += filepart_length;
 
@@ -579,9 +572,7 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write,
 
 	size_t sysctl_val_length = bpf_probe_read_kernel_str(payload,
 							     CTL_MAXNAME, buf);
-	barrier_var(sysctl_val_length);
-	if (sysctl_val_length <= CTL_MAXNAME) {
-		barrier_var(sysctl_val_length);
+	if (bpf_cmp_likely(sysctl_val_length, <=, CTL_MAXNAME)) {
 		sysctl_data->sysctl_val_length = sysctl_val_length;
 		payload += sysctl_val_length;
 	}
@@ -590,9 +581,7 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write,
 		bpf_probe_read_kernel_str(payload, MAX_PATH,
 					  BPF_CORE_READ(filp, f_path.dentry,
 							d_name.name));
-	barrier_var(sysctl_path_length);
-	if (sysctl_path_length <= MAX_PATH) {
-		barrier_var(sysctl_path_length);
+	if (bpf_cmp_likely(sysctl_path_length, <=, MAX_PATH)) {
 		sysctl_data->sysctl_path_length = sysctl_path_length;
 		payload += sysctl_path_length;
 	}
@@ -645,7 +634,7 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 	for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) {
 		struct var_kill_data_t* past_kill_data = &arr_struct->array[i];
 
-		if (past_kill_data != NULL && past_kill_data->kill_target_pid == tpid) {
+		if (past_kill_data != NULL && past_kill_data->kill_target_pid == (pid_t)tpid) {
 			bpf_probe_read_kernel(kill_data, sizeof(*past_kill_data),
 					      past_kill_data);
 			void* payload = kill_data->payload;
@@ -658,9 +647,7 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 			kill_data->kill_target_cgroup_proc_length = 0;
 
 			size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm);
-			barrier_var(comm_length);
-			if (comm_length <= TASK_COMM_LEN) {
-				barrier_var(comm_length);
+			if (bpf_cmp_likely(comm_length, <=, TASK_COMM_LEN)) {
 				kill_data->kill_target_name_length = comm_length;
 				payload += comm_length;
 			}
@@ -669,9 +656,7 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 				bpf_probe_read_kernel_str(payload,
 							  KILL_TARGET_LEN,
 							  BPF_CORE_READ(proc_kernfs, name));
-			barrier_var(cgroup_proc_length);
-			if (cgroup_proc_length <= KILL_TARGET_LEN) {
-				barrier_var(cgroup_proc_length);
+			if (bpf_cmp_likely(cgroup_proc_length, <=, KILL_TARGET_LEN)) {
 				kill_data->kill_target_cgroup_proc_length = cgroup_proc_length;
 				payload += cgroup_proc_length;
 			}
@@ -731,9 +716,7 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx)
 	const char* filename = BPF_CORE_READ(bprm, filename);
 	size_t bin_path_length =
 		bpf_probe_read_kernel_str(payload, MAX_FILENAME_LEN, filename);
-	barrier_var(bin_path_length);
-	if (bin_path_length <= MAX_FILENAME_LEN) {
-		barrier_var(bin_path_length);
+	if (bpf_cmp_likely(bin_path_length, <=, MAX_FILENAME_LEN)) {
 		proc_exec_data->bin_path_length = bin_path_length;
 		payload += bin_path_length;
 	}
@@ -743,8 +726,7 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx)
 	unsigned int cmdline_length = probe_read_lim(payload, arg_start,
 						     arg_end - arg_start, MAX_ARGS_LEN);
 
-	if (cmdline_length <= MAX_ARGS_LEN) {
-		barrier_var(cmdline_length);
+	if (bpf_cmp_likely(cmdline_length, <=, MAX_ARGS_LEN)) {
 		proc_exec_data->cmdline_length = cmdline_length;
 		payload += cmdline_length;
 	}
@@ -821,9 +803,7 @@ int kprobe_ret__do_filp_open(struct pt_regs* ctx)
 	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);
 
 	size_t len = read_absolute_file_path_from_dentry(filp_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
@@ -876,17 +856,13 @@ int BPF_KPROBE(kprobe__vfs_link,
 	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);
 
 	size_t len = read_absolute_file_path_from_dentry(old_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->src_filepath_length = len;
 	}
 
 	len = read_absolute_file_path_from_dentry(new_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
@@ -936,16 +912,12 @@ int BPF_KPROBE(kprobe__vfs_symlink, struct inode* dir, struct dentry* dentry,
 
 	size_t len = bpf_probe_read_kernel_str(payload, MAX_FILEPATH_LENGTH,
 					       oldname);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->src_filepath_length = len;
 	}
 	len = read_absolute_file_path_from_dentry(dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c
new file mode 100644
index 0000000000..986f96687a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/read_vsyscall.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+int target_pid = 0;
+void *user_ptr = 0;
+int read_ret[8];
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int do_probe_read(void *ctx)
+{
+	char buf[8];
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	read_ret[0] = bpf_probe_read_kernel(buf, sizeof(buf), user_ptr);
+	read_ret[1] = bpf_probe_read_kernel_str(buf, sizeof(buf), user_ptr);
+	read_ret[2] = bpf_probe_read(buf, sizeof(buf), user_ptr);
+	read_ret[3] = bpf_probe_read_str(buf, sizeof(buf), user_ptr);
+	read_ret[4] = bpf_probe_read_user(buf, sizeof(buf), user_ptr);
+	read_ret[5] = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr);
+
+	return 0;
+}
+
+SEC("fentry.s/" SYS_PREFIX "sys_nanosleep")
+int do_copy_from_user(void *ctx)
+{
+	char buf[8];
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	read_ret[6] = bpf_copy_from_user(buf, sizeof(buf), user_ptr);
+	read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr,
+					      bpf_get_current_task_btf(), 0);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
index 1ef07f6ee5..1553b9c16a 100644
--- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
@@ -54,6 +54,25 @@ long rbtree_refcounted_node_ref_escapes(void *ctx)
 }
 
 SEC("?tc")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+long refcount_acquire_maybe_null(void *ctx)
+{
+	struct node_acquire *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	/* Intentionally not testing !n
+	 * it's MAYBE_NULL for refcount_acquire
+	 */
+	m = bpf_refcount_acquire(n);
+	if (m)
+		bpf_obj_drop(m);
+	if (n)
+		bpf_obj_drop(n);
+
+	return 0;
+}
+
+SEC("?tc")
 __failure __msg("Unreleased reference id=3 alloc_insn=9")
 long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
new file mode 100644
index 0000000000..ffbbfe1fa1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2024 Meta
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+#include "bpf_kfuncs.h"
+
+#define ATTR __always_inline
+#include "test_jhash.h"
+
+static bool ipv6_addr_loopback(const struct in6_addr *a)
+{
+	return (a->s6_addr32[0] | a->s6_addr32[1] |
+		a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0;
+}
+
+volatile const __u16 ports[2];
+unsigned int bucket[2];
+
+SEC("iter/tcp")
+int iter_tcp_soreuse(struct bpf_iter__tcp *ctx)
+{
+	struct sock *sk = (struct sock *)ctx->sk_common;
+	struct inet_hashinfo *hinfo;
+	unsigned int hash;
+	struct net *net;
+	int idx;
+
+	if (!sk)
+		return 0;
+
+	sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock));
+	if (sk->sk_family != AF_INET6 ||
+	    sk->sk_state != TCP_LISTEN ||
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
+		return 0;
+
+	if (sk->sk_num == ports[0])
+		idx = 0;
+	else if (sk->sk_num == ports[1])
+		idx = 1;
+	else
+		return 0;
+
+	/* bucket selection as in inet_lhash2_bucket_sk() */
+	net = sk->sk_net.net;
+	hash = jhash2(sk->sk_v6_rcv_saddr.s6_addr32, 4, net->hash_mix);
+	hash ^= sk->sk_num;
+	hinfo = net->ipv4.tcp_death_row.hashinfo;
+	bucket[idx] = hash & hinfo->lhash2_mask;
+	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+
+	return 0;
+}
+
+#define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk)
+
+SEC("iter/udp")
+int iter_udp_soreuse(struct bpf_iter__udp *ctx)
+{
+	struct sock *sk = (struct sock *)ctx->udp_sk;
+	struct udp_table *udptable;
+	int idx;
+
+	if (!sk)
+		return 0;
+
+	sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock));
+	if (sk->sk_family != AF_INET6 ||
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
+		return 0;
+
+	if (sk->sk_num == ports[0])
+		idx = 0;
+	else if (sk->sk_num == ports[1])
+		idx = 1;
+	else
+		return 0;
+
+	/* bucket selection as in udp_hashslot2() */
+	udptable = sk->sk_net.net->ipv4.udp_table;
+	bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask;
+	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
index c8f59caa46..a3434b8409 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
@@ -9,7 +9,7 @@ char _license[] SEC("license") = "GPL";
 #define CUSTOM_INHERIT2			1
 #define CUSTOM_LISTENER			2
 
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 struct sockopt_inherit {
 	__u8 val;
diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c
index 96f29fce05..db67278e12 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c
@@ -5,7 +5,7 @@
 
 char _license[] SEC("license") = "GPL";
 
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 SEC("cgroup/getsockopt")
 int _getsockopt_child(struct bpf_sockopt *ctx)
diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
index dbe235ede7..83753b00a5 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
@@ -9,7 +9,7 @@
 
 char _license[] SEC("license") = "GPL";
 
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 SEC("cgroup/setsockopt")
 int sockopt_qos_to_cc(struct bpf_sockopt *ctx)
diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c
index e550f72896..3d3cafdebe 100644
--- a/tools/testing/selftests/bpf/progs/syscall.c
+++ b/tools/testing/selftests/bpf/progs/syscall.c
@@ -6,9 +6,15 @@
 #include <bpf/bpf_tracing.h>
 #include <../../../tools/include/linux/filter.h>
 #include <linux/btf.h>
+#include <string.h>
+#include <errno.h>
 
 char _license[] SEC("license") = "GPL";
 
+struct bpf_map {
+	int id;
+}  __attribute__((preserve_access_index));
+
 struct args {
 	__u64 log_buf;
 	__u32 log_size;
@@ -27,6 +33,37 @@ struct args {
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
 	BTF_INT_ENC(encoding, bits_offset, bits)
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, union bpf_attr);
+	__uint(max_entries, 1);
+} bpf_attr_array SEC(".maps");
+
+struct inner_map_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+} inner_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct inner_map_type);
+} outer_array_map SEC(".maps") = {
+	.values = {
+		[0] = &inner_map,
+	},
+};
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
 static int btf_load(void)
 {
 	struct btf_blob {
@@ -58,7 +95,7 @@ static int btf_load(void)
 }
 
 SEC("syscall")
-int bpf_prog(struct args *ctx)
+int load_prog(struct args *ctx)
 {
 	static char license[] = "GPL";
 	static struct bpf_insn insns[] = {
@@ -94,8 +131,8 @@ int bpf_prog(struct args *ctx)
 	map_create_attr.max_entries = ctx->max_entries;
 	map_create_attr.btf_fd = ret;
 
-	prog_load_attr.license = (long) license;
-	prog_load_attr.insns = (long) insns;
+	prog_load_attr.license = ptr_to_u64(license);
+	prog_load_attr.insns = ptr_to_u64(insns);
 	prog_load_attr.log_buf = ctx->log_buf;
 	prog_load_attr.log_size = ctx->log_size;
 	prog_load_attr.log_level = 1;
@@ -107,8 +144,8 @@ int bpf_prog(struct args *ctx)
 	insns[3].imm = ret;
 
 	map_update_attr.map_fd = ret;
-	map_update_attr.key = (long) &key;
-	map_update_attr.value = (long) &value;
+	map_update_attr.key = ptr_to_u64(&key);
+	map_update_attr.value = ptr_to_u64(&value);
 	ret = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, &map_update_attr, sizeof(map_update_attr));
 	if (ret < 0)
 		return ret;
@@ -119,3 +156,52 @@ int bpf_prog(struct args *ctx)
 	ctx->prog_fd = ret;
 	return 1;
 }
+
+SEC("syscall")
+int update_outer_map(void *ctx)
+{
+	int zero = 0, ret = 0, outer_fd = -1, inner_fd = -1, err;
+	const int attr_sz = sizeof(union bpf_attr);
+	union bpf_attr *attr;
+
+	attr = bpf_map_lookup_elem((struct bpf_map *)&bpf_attr_array, &zero);
+	if (!attr)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_id = ((struct bpf_map *)&outer_array_map)->id;
+	outer_fd = bpf_sys_bpf(BPF_MAP_GET_FD_BY_ID, attr, attr_sz);
+	if (outer_fd < 0)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_type = BPF_MAP_TYPE_ARRAY;
+	attr->key_size = 4;
+	attr->value_size = 4;
+	attr->max_entries = 1;
+	inner_fd = bpf_sys_bpf(BPF_MAP_CREATE, attr, attr_sz);
+	if (inner_fd < 0)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_fd = outer_fd;
+	attr->key = ptr_to_u64(&zero);
+	attr->value = ptr_to_u64(&inner_fd);
+	err = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, attr, attr_sz);
+	if (err)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_fd = outer_fd;
+	attr->key = ptr_to_u64(&zero);
+	err = bpf_sys_bpf(BPF_MAP_DELETE_ELEM, attr, attr_sz);
+	if (err)
+		goto out;
+	ret = 1;
+out:
+	if (inner_fd >= 0)
+		bpf_sys_close(inner_fd);
+	if (outer_fd >= 0)
+		bpf_sys_close(outer_fd);
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
index dcdea31270..ad88a3796d 100644
--- a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
+++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
@@ -248,7 +248,7 @@ int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 cl
 }
 
 SEC("lsm/task_free")
-__failure __msg("reg type unsupported for arg#0 function")
+__failure __msg("R1 must be a rcu pointer")
 int BPF_PROG(task_kfunc_from_lsm_task_free, struct task_struct *task)
 {
 	struct task_struct *acquired;
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
index b685a4aba6..3494ca30fa 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_ma.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
@@ -17,20 +17,23 @@ struct generic_map_value {
 
 char _license[] SEC("license") = "GPL";
 
-const unsigned int data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096};
+const unsigned int data_sizes[] = {16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096};
 const volatile unsigned int data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
 
+const unsigned int percpu_data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512};
+const volatile unsigned int percpu_data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
+
 int err = 0;
-int pid = 0;
+u32 pid = 0;
 
 #define DEFINE_ARRAY_WITH_KPTR(_size) \
 	struct bin_data_##_size { \
 		char data[_size - sizeof(void *)]; \
 	}; \
+	/* See Commit 5d8d6634ccc, force btf generation for type bin_data_##_size */	\
+	struct bin_data_##_size *__bin_data_##_size; \
 	struct map_value_##_size { \
 		struct bin_data_##_size __kptr * data; \
-		/* To emit BTF info for bin_data_xx */ \
-		struct bin_data_##_size not_used; \
 	}; \
 	struct { \
 		__uint(type, BPF_MAP_TYPE_ARRAY); \
@@ -40,8 +43,12 @@ int pid = 0;
 	} array_##_size SEC(".maps")
 
 #define DEFINE_ARRAY_WITH_PERCPU_KPTR(_size) \
+	struct percpu_bin_data_##_size { \
+		char data[_size]; \
+	}; \
+	struct percpu_bin_data_##_size *__percpu_bin_data_##_size; \
 	struct map_value_percpu_##_size { \
-		struct bin_data_##_size __percpu_kptr * data; \
+		struct percpu_bin_data_##_size __percpu_kptr * data; \
 	}; \
 	struct { \
 		__uint(type, BPF_MAP_TYPE_ARRAY); \
@@ -114,7 +121,7 @@ static __always_inline void batch_percpu_alloc(struct bpf_map *map, unsigned int
 			return;
 		}
 		/* per-cpu allocator may not be able to refill in time */
-		new = bpf_percpu_obj_new_impl(data_btf_ids[idx], NULL);
+		new = bpf_percpu_obj_new_impl(percpu_data_btf_ids[idx], NULL);
 		if (!new)
 			continue;
 
@@ -166,7 +173,7 @@ static __always_inline void batch_percpu_free(struct bpf_map *map, unsigned int
 		batch_percpu_free((struct bpf_map *)(&array_percpu_##size), batch, idx); \
 	} while (0)
 
-DEFINE_ARRAY_WITH_KPTR(8);
+/* kptr doesn't support bin_data_8 which is a zero-sized array */
 DEFINE_ARRAY_WITH_KPTR(16);
 DEFINE_ARRAY_WITH_KPTR(32);
 DEFINE_ARRAY_WITH_KPTR(64);
@@ -179,7 +186,7 @@ DEFINE_ARRAY_WITH_KPTR(1024);
 DEFINE_ARRAY_WITH_KPTR(2048);
 DEFINE_ARRAY_WITH_KPTR(4096);
 
-/* per-cpu kptr doesn't support bin_data_8 which is a zero-sized array */
+DEFINE_ARRAY_WITH_PERCPU_KPTR(8);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(16);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(32);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(64);
@@ -188,9 +195,6 @@ DEFINE_ARRAY_WITH_PERCPU_KPTR(128);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(192);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(256);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(512);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(1024);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(2048);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(4096);
 
 SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
 int test_batch_alloc_free(void *ctx)
@@ -198,21 +202,20 @@ int test_batch_alloc_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 8-bytes objects in batch to trigger refilling,
-	 * then free 128 8-bytes objects in batch to trigger freeing.
+	/* Alloc 128 16-bytes objects in batch to trigger refilling,
+	 * then free 128 16-bytes objects in batch to trigger freeing.
 	 */
-	CALL_BATCH_ALLOC_FREE(8, 128, 0);
-	CALL_BATCH_ALLOC_FREE(16, 128, 1);
-	CALL_BATCH_ALLOC_FREE(32, 128, 2);
-	CALL_BATCH_ALLOC_FREE(64, 128, 3);
-	CALL_BATCH_ALLOC_FREE(96, 128, 4);
-	CALL_BATCH_ALLOC_FREE(128, 128, 5);
-	CALL_BATCH_ALLOC_FREE(192, 128, 6);
-	CALL_BATCH_ALLOC_FREE(256, 128, 7);
-	CALL_BATCH_ALLOC_FREE(512, 64, 8);
-	CALL_BATCH_ALLOC_FREE(1024, 32, 9);
-	CALL_BATCH_ALLOC_FREE(2048, 16, 10);
-	CALL_BATCH_ALLOC_FREE(4096, 8, 11);
+	CALL_BATCH_ALLOC_FREE(16, 128, 0);
+	CALL_BATCH_ALLOC_FREE(32, 128, 1);
+	CALL_BATCH_ALLOC_FREE(64, 128, 2);
+	CALL_BATCH_ALLOC_FREE(96, 128, 3);
+	CALL_BATCH_ALLOC_FREE(128, 128, 4);
+	CALL_BATCH_ALLOC_FREE(192, 128, 5);
+	CALL_BATCH_ALLOC_FREE(256, 128, 6);
+	CALL_BATCH_ALLOC_FREE(512, 64, 7);
+	CALL_BATCH_ALLOC_FREE(1024, 32, 8);
+	CALL_BATCH_ALLOC_FREE(2048, 16, 9);
+	CALL_BATCH_ALLOC_FREE(4096, 8, 10);
 
 	return 0;
 }
@@ -223,21 +226,20 @@ int test_free_through_map_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 8-bytes objects in batch to trigger refilling,
+	/* Alloc 128 16-bytes objects in batch to trigger refilling,
 	 * then free these objects through map free.
 	 */
-	CALL_BATCH_ALLOC(8, 128, 0);
-	CALL_BATCH_ALLOC(16, 128, 1);
-	CALL_BATCH_ALLOC(32, 128, 2);
-	CALL_BATCH_ALLOC(64, 128, 3);
-	CALL_BATCH_ALLOC(96, 128, 4);
-	CALL_BATCH_ALLOC(128, 128, 5);
-	CALL_BATCH_ALLOC(192, 128, 6);
-	CALL_BATCH_ALLOC(256, 128, 7);
-	CALL_BATCH_ALLOC(512, 64, 8);
-	CALL_BATCH_ALLOC(1024, 32, 9);
-	CALL_BATCH_ALLOC(2048, 16, 10);
-	CALL_BATCH_ALLOC(4096, 8, 11);
+	CALL_BATCH_ALLOC(16, 128, 0);
+	CALL_BATCH_ALLOC(32, 128, 1);
+	CALL_BATCH_ALLOC(64, 128, 2);
+	CALL_BATCH_ALLOC(96, 128, 3);
+	CALL_BATCH_ALLOC(128, 128, 4);
+	CALL_BATCH_ALLOC(192, 128, 5);
+	CALL_BATCH_ALLOC(256, 128, 6);
+	CALL_BATCH_ALLOC(512, 64, 7);
+	CALL_BATCH_ALLOC(1024, 32, 8);
+	CALL_BATCH_ALLOC(2048, 16, 9);
+	CALL_BATCH_ALLOC(4096, 8, 10);
 
 	return 0;
 }
@@ -248,9 +250,10 @@ int test_batch_percpu_alloc_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling,
-	 * then free 128 16-bytes per-cpu objects in batch to trigger freeing.
+	/* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling,
+	 * then free 128 8-bytes per-cpu objects in batch to trigger freeing.
 	 */
+	CALL_BATCH_PERCPU_ALLOC_FREE(8, 128, 0);
 	CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 1);
 	CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 2);
 	CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 3);
@@ -259,9 +262,6 @@ int test_batch_percpu_alloc_free(void *ctx)
 	CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 6);
 	CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 7);
 	CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 8);
-	CALL_BATCH_PERCPU_ALLOC_FREE(1024, 32, 9);
-	CALL_BATCH_PERCPU_ALLOC_FREE(2048, 16, 10);
-	CALL_BATCH_PERCPU_ALLOC_FREE(4096, 8, 11);
 
 	return 0;
 }
@@ -272,9 +272,10 @@ int test_percpu_free_through_map_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling,
+	/* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling,
 	 * then free these object through map free.
 	 */
+	CALL_BATCH_PERCPU_ALLOC(8, 128, 0);
 	CALL_BATCH_PERCPU_ALLOC(16, 128, 1);
 	CALL_BATCH_PERCPU_ALLOC(32, 128, 2);
 	CALL_BATCH_PERCPU_ALLOC(64, 128, 3);
@@ -283,9 +284,6 @@ int test_percpu_free_through_map_free(void *ctx)
 	CALL_BATCH_PERCPU_ALLOC(192, 128, 6);
 	CALL_BATCH_PERCPU_ALLOC(256, 128, 7);
 	CALL_BATCH_PERCPU_ALLOC(512, 64, 8);
-	CALL_BATCH_PERCPU_ALLOC(1024, 32, 9);
-	CALL_BATCH_PERCPU_ALLOC(2048, 16, 10);
-	CALL_BATCH_PERCPU_ALLOC(4096, 8, 11);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
new file mode 100644
index 0000000000..44628865fe
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+__u32 target_ancestor_level;
+__u64 target_ancestor_cgid;
+int target_pid, target_hid;
+
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+
+static int bpf_link_create_verify(int cmd)
+{
+	struct cgroup *cgrp, *ancestor;
+	struct task_struct *task;
+	int ret = 0;
+
+	if (cmd != BPF_LINK_CREATE)
+		return 0;
+
+	task = bpf_get_current_task_btf();
+
+	/* Then it can run in parallel with others */
+	if (task->pid != target_pid)
+		return 0;
+
+	cgrp = bpf_task_get_cgroup1(task, target_hid);
+	if (!cgrp)
+		return 0;
+
+	/* Refuse it if its cgid or its ancestor's cgid is the target cgid */
+	if (cgrp->kn->id == target_ancestor_cgid)
+		ret = -1;
+
+	ancestor = bpf_cgroup_ancestor(cgrp, target_ancestor_level);
+	if (!ancestor)
+		goto out;
+
+	if (ancestor->kn->id == target_ancestor_cgid)
+		ret = -1;
+	bpf_cgroup_release(ancestor);
+
+out:
+	bpf_cgroup_release(cgrp);
+	return ret;
+}
+
+SEC("lsm/bpf")
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
+{
+	return bpf_link_create_verify(cmd);
+}
+
+SEC("lsm.s/bpf")
+int BPF_PROG(lsm_s_run, int cmd, union bpf_attr *attr, unsigned int size)
+{
+	return bpf_link_create_verify(cmd);
+}
+
+SEC("fentry")
+int BPF_PROG(fentry_run)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
index a17dd83eae..ee4a601dcb 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
@@ -53,7 +53,7 @@ int test_core_kernel(void *ctx)
 	struct task_struct *task = (void *)bpf_get_current_task();
 	struct core_reloc_kernel_output *out = (void *)&data.out;
 	uint64_t pid_tgid = bpf_get_current_pid_tgid();
-	uint32_t real_tgid = (uint32_t)pid_tgid;
+	int32_t real_tgid = (int32_t)pid_tgid;
 	int pid, tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
index f59f175c7b..bcb31ff92d 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
@@ -43,8 +43,8 @@ int BPF_PROG(test_core_module_probed,
 #if __has_builtin(__builtin_preserve_enum_value)
 	struct core_reloc_module_output *out = (void *)&data.out;
 	__u64 pid_tgid = bpf_get_current_pid_tgid();
-	__u32 real_tgid = (__u32)(pid_tgid >> 32);
-	__u32 real_pid = (__u32)pid_tgid;
+	__s32 real_tgid = (__s32)(pid_tgid >> 32);
+	__s32 real_pid = (__s32)pid_tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
 		return 0;
@@ -77,8 +77,8 @@ int BPF_PROG(test_core_module_direct,
 #if __has_builtin(__builtin_preserve_enum_value)
 	struct core_reloc_module_output *out = (void *)&data.out;
 	__u64 pid_tgid = bpf_get_current_pid_tgid();
-	__u32 real_tgid = (__u32)(pid_tgid >> 32);
-	__u32 real_pid = (__u32)pid_tgid;
+	__s32 real_tgid = (__s32)(pid_tgid >> 32);
+	__s32 real_pid = (__s32)pid_tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
index 564f402d56..69509f8bb6 100644
--- a/tools/testing/selftests/bpf/progs/test_fill_link_info.c
+++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
@@ -39,4 +39,10 @@ int BPF_PROG(kmulti_run)
 	return 0;
 }
 
+SEC("uprobe.multi")
+int BPF_PROG(umulti_run)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_fsverity.c b/tools/testing/selftests/bpf/progs/test_fsverity.c
new file mode 100644
index 0000000000..9e0f73e818
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_fsverity.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
+#define SIZEOF_STRUCT_FSVERITY_DIGEST 4  /* sizeof(struct fsverity_digest) */
+
+char expected_digest[SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE];
+char digest[SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE];
+__u32 monitored_pid;
+__u32 got_fsverity;
+__u32 digest_matches;
+
+SEC("lsm.s/file_open")
+int BPF_PROG(test_file_open, struct file *f)
+{
+	struct bpf_dynptr digest_ptr;
+	__u32 pid;
+	int ret;
+	int i;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	bpf_dynptr_from_mem(digest, sizeof(digest), 0, &digest_ptr);
+	ret = bpf_get_fsverity_digest(f, &digest_ptr);
+	if (ret < 0)
+		return 0;
+	got_fsverity = 1;
+
+	for (i = 0; i < (int)sizeof(digest); i++) {
+		if (digest[i] != expected_digest[i])
+			return 0;
+	}
+
+	digest_matches = 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_get_xattr.c b/tools/testing/selftests/bpf/progs/test_get_xattr.c
new file mode 100644
index 0000000000..7eb2a4e5a3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_get_xattr.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u32 monitored_pid;
+__u32 found_xattr;
+
+static const char expected_value[] = "hello";
+char value[32];
+
+SEC("lsm.s/file_open")
+int BPF_PROG(test_file_open, struct file *f)
+{
+	struct bpf_dynptr value_ptr;
+	__u32 pid;
+	int ret;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	bpf_dynptr_from_mem(value, sizeof(value), 0, &value_ptr);
+
+	ret = bpf_get_file_xattr(f, "user.kfuncs", &value_ptr);
+	if (ret != sizeof(expected_value))
+		return 0;
+	if (bpf_strncmp(value, ret, expected_value))
+		return 0;
+	found_xattr = 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func12.c b/tools/testing/selftests/bpf/progs/test_global_func12.c
index 7f159d83c6..6e03d42519 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func12.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func12.c
@@ -19,5 +19,7 @@ int global_func12(struct __sk_buff *skb)
 {
 	const struct S s = {.x = skb->len };
 
-	return foo(&s);
+	foo(&s);
+
+	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_func15.c b/tools/testing/selftests/bpf/progs/test_global_func15.c
index b512d6a6c7..b4e089d698 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func15.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func15.c
@@ -13,7 +13,7 @@ __noinline int foo(unsigned int *v)
 }
 
 SEC("cgroup_skb/ingress")
-__failure __msg("At program exit the register R0 has value")
+__failure __msg("At program exit the register R0 has ")
 int global_func15(struct __sk_buff *skb)
 {
 	unsigned int v = 1;
@@ -22,3 +22,35 @@ int global_func15(struct __sk_buff *skb)
 
 	return v;
 }
+
+SEC("cgroup_skb/ingress")
+__log_level(2) __flag(BPF_F_TEST_STATE_FREQ)
+__failure
+/* check that fallthrough code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before 2: (b7) r0 = 1")
+/* check that branch code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before 0: (85) call bpf_get_prandom_u32#7")
+__msg("At program exit the register R0 has ")
+__naked int global_func15_tricky_pruning(void)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 s> 1000 goto 1f;"
+		"r0 = 1;"
+	"1:"
+		"goto +0;" /* checkpoint */
+		/* cgroup_skb/ingress program is expected to return [0, 1]
+		 * values, so branch above makes sure that in a fallthrough
+		 * case we have a valid 1 stored in R0 register, but in
+		 * a branch case we assign some random value to R0.  So if
+		 * there is something wrong with precision tracking for R0 at
+		 * program exit, we might erronenously prune branch case,
+		 * because R0 in fallthrough case is imprecise (and thus any
+		 * value is valid from POV of verifier is_state_equal() logic)
+		 */
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_common
+	);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c
index cc55aedaf8..257c0569ff 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func5.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func5.c
@@ -26,7 +26,7 @@ int f3(int val, struct __sk_buff *skb)
 }
 
 SEC("tc")
-__failure __msg("expected pointer to ctx, but got PTR")
+__failure __msg("expects pointer to ctx")
 int global_func5(struct __sk_buff *skb)
 {
 	return f1(skb) + f2(2, skb) + f3(3, skb);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
index 7faa8eef05..9a06e5eb1f 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
@@ -102,3 +102,52 @@ int perf_event_ctx(void *ctx)
 {
 	return perf_event_ctx_subprog(ctx);
 }
+
+/* this global subprog can be now called from many types of entry progs, each
+ * with different context type
+ */
+__weak int subprog_ctx_tag(void *ctx __arg_ctx)
+{
+	return bpf_get_stack(ctx, stack, sizeof(stack), 0);
+}
+
+struct my_struct { int x; };
+
+__weak int subprog_multi_ctx_tags(void *ctx1 __arg_ctx,
+				  struct my_struct *mem,
+				  void *ctx2 __arg_ctx)
+{
+	if (!mem)
+		return 0;
+
+	return bpf_get_stack(ctx1, stack, sizeof(stack), 0) +
+	       mem->x +
+	       bpf_get_stack(ctx2, stack, sizeof(stack), 0);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
+
+SEC("?perf_event")
+__success __log_level(2)
+int arg_tag_ctx_perf(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
+
+SEC("?kprobe")
+__success __log_level(2)
+int arg_tag_ctx_kprobe(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h
index c300734d26..ef53559bbb 100644
--- a/tools/testing/selftests/bpf/progs/test_jhash.h
+++ b/tools/testing/selftests/bpf/progs/test_jhash.h
@@ -69,3 +69,34 @@ u32 jhash(const void *key, u32 length, u32 initval)
 
 	return c;
 }
+
+static __always_inline u32 jhash2(const u32 *k, u32 length, u32 initval)
+{
+	u32 a, b, c;
+
+	/* Set up the internal state */
+	a = b = c = JHASH_INITVAL + (length<<2) + initval;
+
+	/* Handle most of the key */
+	while (length > 3) {
+		a += k[0];
+		b += k[1];
+		c += k[2];
+		__jhash_mix(a, b, c);
+		length -= 3;
+		k += 3;
+	}
+
+	/* Handle the last 3 u32's */
+	switch (length) {
+	case 3: c += k[2];
+	case 2: b += k[1];
+	case 1: a += k[0];
+		__jhash_final(a, b, c);
+		break;
+	case 0:	/* Nothing left to add */
+		break;
+	}
+
+	return c;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
new file mode 100644
index 0000000000..2f0eb1334d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
+#define MAX_SIG_SIZE 1024
+
+/* By default, "fsverity sign" signs a file with fsverity_formatted_digest
+ * of the file. fsverity_formatted_digest on the kernel side is only used
+ * with CONFIG_FS_VERITY_BUILTIN_SIGNATURES. However, BPF LSM doesn't not
+ * require CONFIG_FS_VERITY_BUILTIN_SIGNATURES, so vmlinux.h may not have
+ * fsverity_formatted_digest. In this test, we intentionally avoid using
+ * fsverity_formatted_digest.
+ *
+ * Luckily, fsverity_formatted_digest is simply 8-byte magic followed by
+ * fsverity_digest. We use a char array of size fsverity_formatted_digest
+ * plus SHA256_DIGEST_SIZE. The magic part of it is filled by user space,
+ * and the rest of it is filled by bpf_get_fsverity_digest.
+ *
+ * Note that, generating signatures based on fsverity_formatted_digest is
+ * the design choice of this selftest (and "fsverity sign"). With BPF
+ * LSM, we have the flexibility to generate signature based on other data
+ * sets, for example, fsverity_digest or only the digest[] part of it.
+ */
+#define MAGIC_SIZE 8
+#define SIZEOF_STRUCT_FSVERITY_DIGEST 4  /* sizeof(struct fsverity_digest) */
+char digest[MAGIC_SIZE + SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE];
+
+__u32 monitored_pid;
+char sig[MAX_SIG_SIZE];
+__u32 sig_size;
+__u32 user_keyring_serial;
+
+SEC("lsm.s/file_open")
+int BPF_PROG(test_file_open, struct file *f)
+{
+	struct bpf_dynptr digest_ptr, sig_ptr;
+	struct bpf_key *trusted_keyring;
+	__u32 pid;
+	int ret;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	/* digest_ptr points to fsverity_digest */
+	bpf_dynptr_from_mem(digest + MAGIC_SIZE, sizeof(digest) - MAGIC_SIZE, 0, &digest_ptr);
+
+	ret = bpf_get_fsverity_digest(f, &digest_ptr);
+	/* No verity, allow access */
+	if (ret < 0)
+		return 0;
+
+	/* Move digest_ptr to fsverity_formatted_digest */
+	bpf_dynptr_from_mem(digest, sizeof(digest), 0, &digest_ptr);
+
+	/* Read signature from xattr */
+	bpf_dynptr_from_mem(sig, sizeof(sig), 0, &sig_ptr);
+	ret = bpf_get_file_xattr(f, "user.sig", &sig_ptr);
+	/* No signature, reject access */
+	if (ret < 0)
+		return -EPERM;
+
+	trusted_keyring = bpf_lookup_user_key(user_keyring_serial, 0);
+	if (!trusted_keyring)
+		return -ENOENT;
+
+	/* Verify signature */
+	ret = bpf_verify_pkcs7_signature(&digest_ptr, &sig_ptr, trusted_keyring);
+
+	bpf_key_put(trusted_keyring);
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
index eacda9fe07..4cfa42aa94 100644
--- a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
+++ b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
@@ -29,7 +29,7 @@ int BPF_PROG(unix_listen, struct socket *sock, int backlog)
 	len = unix_sk->addr->len - sizeof(short);
 	path[0] = '@';
 	for (i = 1; i < len; i++) {
-		if (i >= sizeof(struct sockaddr_un))
+		if (i >= (int)sizeof(struct sockaddr_un))
 			break;
 
 		path[i] = unix_sk->addr->name->sun_path[i];
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index f66af753bb..3e436e6f73 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -6,66 +6,34 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
-#include <stddef.h>
-#include <string.h>
-#include <arpa/inet.h>
-#include <linux/bpf.h>
-#include <linux/if_ether.h>
-#include <linux/if_packet.h>
-#include <linux/if_tunnel.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/icmp.h>
-#include <linux/types.h>
-#include <linux/socket.h>
-#include <linux/pkt_cls.h>
-#include <linux/erspan.h>
-#include <linux/udp.h>
+#include "vmlinux.h"
+#include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include "bpf_kfuncs.h"
+#include "bpf_tracing_net.h"
 
 #define log_err(__ret) bpf_printk("ERROR line:%d ret:%d\n", __LINE__, __ret)
 
-#define VXLAN_UDP_PORT 4789
+#define VXLAN_UDP_PORT		4789
+#define ETH_P_IP		0x0800
+#define PACKET_HOST		0
+#define TUNNEL_CSUM		bpf_htons(0x01)
+#define TUNNEL_KEY		bpf_htons(0x04)
 
 /* Only IPv4 address assigned to veth1.
  * 172.16.1.200
  */
 #define ASSIGNED_ADDR_VETH1 0xac1001c8
 
-struct geneve_opt {
-	__be16	opt_class;
-	__u8	type;
-	__u8	length:5;
-	__u8	r3:1;
-	__u8	r2:1;
-	__u8	r1:1;
-	__u8	opt_data[8]; /* hard-coded to 8 byte */
-};
-
-struct vxlanhdr {
-	__be32 vx_flags;
-	__be32 vx_vni;
-} __attribute__((packed));
-
-struct vxlan_metadata {
-	__u32     gbp;
-};
-
-struct bpf_fou_encap {
-	__be16 sport;
-	__be16 dport;
-};
-
-enum bpf_fou_encap_type {
-	FOU_BPF_ENCAP_FOU,
-	FOU_BPF_ENCAP_GUE,
-};
-
 int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx,
 			  struct bpf_fou_encap *encap, int type) __ksym;
 int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
 			  struct bpf_fou_encap *encap) __ksym;
+struct xfrm_state *
+bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts,
+		       u32 opts__sz) __ksym;
+void bpf_xdp_xfrm_state_release(struct xfrm_state *x) __ksym;
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -205,9 +173,9 @@ int erspan_set_tunnel(struct __sk_buff *skb)
 	__u8 hwid = 7;
 
 	md.version = 2;
-	md.u.md2.dir = direction;
-	md.u.md2.hwid = hwid & 0xf;
-	md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction);
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf));
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3);
 #endif
 
 	ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
@@ -246,8 +214,9 @@ int erspan_get_tunnel(struct __sk_buff *skb)
 	bpf_printk("\tindex %x\n", index);
 #else
 	bpf_printk("\tdirection %d hwid %x timestamp %u\n",
-		   md.u.md2.dir,
-		   (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, dir),
+		   (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) +
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, hwid),
 		   bpf_ntohl(md.u.md2.timestamp));
 #endif
 
@@ -284,9 +253,9 @@ int ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
 	__u8 hwid = 17;
 
 	md.version = 2;
-	md.u.md2.dir = direction;
-	md.u.md2.hwid = hwid & 0xf;
-	md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction);
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf));
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3);
 #endif
 
 	ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
@@ -326,8 +295,9 @@ int ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
 	bpf_printk("\tindex %x\n", index);
 #else
 	bpf_printk("\tdirection %d hwid %x timestamp %u\n",
-		   md.u.md2.dir,
-		   (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, dir),
+		   (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) +
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, hwid),
 		   bpf_ntohl(md.u.md2.timestamp));
 #endif
 
@@ -963,6 +933,10 @@ int ip6ip6_get_tunnel(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
+volatile int xfrm_reqid = 0;
+volatile int xfrm_spi = 0;
+volatile int xfrm_remote_ip = 0;
+
 SEC("tc")
 int xfrm_get_state(struct __sk_buff *skb)
 {
@@ -973,10 +947,58 @@ int xfrm_get_state(struct __sk_buff *skb)
 	if (ret < 0)
 		return TC_ACT_OK;
 
-	bpf_printk("reqid %d spi 0x%x remote ip 0x%x\n",
-		   x.reqid, bpf_ntohl(x.spi),
-		   bpf_ntohl(x.remote_ipv4));
+	xfrm_reqid = x.reqid;
+	xfrm_spi = bpf_ntohl(x.spi);
+	xfrm_remote_ip = bpf_ntohl(x.remote_ipv4);
+
 	return TC_ACT_OK;
 }
 
+volatile int xfrm_replay_window = 0;
+
+SEC("xdp")
+int xfrm_get_state_xdp(struct xdp_md *xdp)
+{
+	struct bpf_xfrm_state_opts opts = {};
+	struct xfrm_state *x = NULL;
+	struct ip_esp_hdr *esph;
+	struct bpf_dynptr ptr;
+	u8 esph_buf[8] = {};
+	u8 iph_buf[20] = {};
+	struct iphdr *iph;
+	u32 off;
+
+	if (bpf_dynptr_from_xdp(xdp, 0, &ptr))
+		goto out;
+
+	off = sizeof(struct ethhdr);
+	iph = bpf_dynptr_slice(&ptr, off, iph_buf, sizeof(iph_buf));
+	if (!iph || iph->protocol != IPPROTO_ESP)
+		goto out;
+
+	off += sizeof(struct iphdr);
+	esph = bpf_dynptr_slice(&ptr, off, esph_buf, sizeof(esph_buf));
+	if (!esph)
+		goto out;
+
+	opts.netns_id = BPF_F_CURRENT_NETNS;
+	opts.daddr.a4 = iph->daddr;
+	opts.spi = esph->spi;
+	opts.proto = IPPROTO_ESP;
+	opts.family = AF_INET;
+
+	x = bpf_xdp_get_xfrm_state(xdp, &opts, sizeof(opts));
+	if (!x)
+		goto out;
+
+	if (!x->replay_esn)
+		goto out;
+
+	xfrm_replay_window = x->replay_esn->replay_window;
+out:
+	if (x)
+		bpf_xdp_xfrm_state_release(x);
+	return XDP_PASS;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
index 7748cc23de..f42e9f3831 100644
--- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
@@ -10,17 +10,11 @@
 #include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
 
 #define MAX_DATA_SIZE (1024 * 1024)
 #define MAX_SIG_SIZE 1024
 
-extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
-extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
-extern void bpf_key_put(struct bpf_key *key) __ksym;
-extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
-				      struct bpf_dynptr *sig_ptr,
-				      struct bpf_key *trusted_keyring) __ksym;
-
 __u32 monitored_pid;
 __u32 user_keyring_serial;
 __u64 system_keyring_id;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
index 5baaafed0d..3abf068b84 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
@@ -38,7 +38,7 @@ int xdp_redirect(struct xdp_md *xdp)
 	if (payload + 1 > data_end)
 		return XDP_ABORTED;
 
-	if (xdp->ingress_ifindex != ifindex_in)
+	if (xdp->ingress_ifindex != (__u32)ifindex_in)
 		return XDP_ABORTED;
 
 	if (metadata + 1 > data)
diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c
index 8b946c8188..f615da97df 100644
--- a/tools/testing/selftests/bpf/progs/timer.c
+++ b/tools/testing/selftests/bpf/progs/timer.c
@@ -51,7 +51,8 @@ struct {
 	__uint(max_entries, 1);
 	__type(key, int);
 	__type(value, struct elem);
-} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps");
+} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps"),
+	race_array SEC(".maps");
 
 __u64 bss_data;
 __u64 abs_data;
@@ -390,3 +391,34 @@ int BPF_PROG2(test5, int, a)
 
 	return 0;
 }
+
+static int race_timer_callback(void *race_array, int *race_key, struct bpf_timer *timer)
+{
+	bpf_timer_start(timer, 1000000, 0);
+	return 0;
+}
+
+SEC("syscall")
+int race(void *ctx)
+{
+	struct bpf_timer *timer;
+	int err, race_key = 0;
+	struct elem init;
+
+	__builtin_memset(&init, 0, sizeof(struct elem));
+	bpf_map_update_elem(&race_array, &race_key, &init, BPF_ANY);
+
+	timer = bpf_map_lookup_elem(&race_array, &race_key);
+	if (!timer)
+		return 1;
+
+	err = bpf_timer_init(timer, &race_array, CLOCK_MONOTONIC);
+	if (err && err != -EBUSY)
+		return 1;
+
+	bpf_timer_set_callback(timer, race_timer_callback);
+	bpf_timer_start(timer, 0, 0);
+	bpf_timer_cancel(timer);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_failure.c b/tools/testing/selftests/bpf/progs/timer_failure.c
index 226d33b5a0..0996c2486f 100644
--- a/tools/testing/selftests/bpf/progs/timer_failure.c
+++ b/tools/testing/selftests/bpf/progs/timer_failure.c
@@ -21,17 +21,38 @@ struct {
 	__type(value, struct elem);
 } timer_map SEC(".maps");
 
-static int timer_cb_ret1(void *map, int *key, struct bpf_timer *timer)
+__naked __noinline __used
+static unsigned long timer_cb_ret_bad()
 {
-	if (bpf_get_smp_processor_id() % 2)
-		return 1;
-	else
-		return 0;
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 s> 1000 goto 1f;"
+		"r0 = 0;"
+	"1:"
+		"goto +0;" /* checkpoint */
+		/* async callback is expected to return 0, so branch above
+		 * skipping r0 = 0; should lead to a failure, but if exit
+		 * instruction doesn't enforce r0's precision, this callback
+		 * will be successfully verified
+		 */
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_common
+	);
 }
 
 SEC("fentry/bpf_fentry_test1")
-__failure __msg("should have been in (0x0; 0x0)")
-int BPF_PROG2(test_ret_1, int, a)
+__log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure
+/* check that fallthrough code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before")
+__msg(": (85) call bpf_get_prandom_u32#7") /* anchor message */
+/* check that branch code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before ") __msg(": (85) call bpf_get_prandom_u32#7")
+__msg("should have been in [0, 0]")
+long BPF_PROG2(test_bad_ret, int, a)
 {
 	int key = 0;
 	struct bpf_timer *timer;
@@ -39,7 +60,7 @@ int BPF_PROG2(test_ret_1, int, a)
 	timer = bpf_map_lookup_elem(&timer_map, &key);
 	if (timer) {
 		bpf_timer_init(timer, &timer_map, CLOCK_BOOTTIME);
-		bpf_timer_set_callback(timer, timer_cb_ret1);
+		bpf_timer_set_callback(timer, timer_cb_ret_bad);
 		bpf_timer_start(timer, 1000, 0);
 	}
 
diff --git a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c
index 03ee946c6b..11ab25c42c 100644
--- a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c
+++ b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c
@@ -184,7 +184,7 @@ invalid_drain_callback_return(struct bpf_dynptr *dynptr, void *context)
  * not be able to write to that pointer.
  */
 SEC("?raw_tp")
-__failure __msg("At callback return the register R0 has value")
+__failure __msg("At callback return the register R0 has ")
 int user_ringbuf_callback_invalid_return(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, invalid_drain_callback_return, NULL, 0);
diff --git a/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c b/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c
new file mode 100644
index 0000000000..623f130a31
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <stdint.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+#include "bpf_misc.h"
+
+struct core_reloc_bitfields {
+	/* unsigned bitfields */
+	uint8_t		ub1: 1;
+	uint8_t		ub2: 2;
+	uint32_t	ub7: 7;
+	/* signed bitfields */
+	int8_t		sb4: 4;
+	int32_t		sb20: 20;
+	/* non-bitfields */
+	uint32_t	u32;
+	int32_t		s32;
+} __attribute__((preserve_access_index));
+
+SEC("tc")
+__description("single CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(3)
+int single_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 3);
+	return BPF_CORE_READ_BITFIELD(&bitfields, ub2);
+}
+
+SEC("tc")
+__description("multiple CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(0x3FD)
+int multiple_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+	uint8_t ub2;
+	int8_t sb4;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 1);
+	BPF_CORE_WRITE_BITFIELD(&bitfields, sb4, -1);
+
+	ub2 = BPF_CORE_READ_BITFIELD(&bitfields, ub2);
+	sb4 = BPF_CORE_READ_BITFIELD(&bitfields, sb4);
+
+	return (((uint8_t)sb4) << 2) | ub2;
+}
+
+SEC("tc")
+__description("adjacent CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(7)
+int adjacent_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+	uint8_t ub1, ub2;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub1, 1);
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 3);
+
+	ub1 = BPF_CORE_READ_BITFIELD(&bitfields, ub1);
+	ub2 = BPF_CORE_READ_BITFIELD(&bitfields, ub2);
+
+	return (ub2 << 1) | ub1;
+}
+
+SEC("tc")
+__description("multibyte CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(0x21)
+int multibyte_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+	uint32_t ub7;
+	uint8_t ub1;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub1, 1);
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub7, 16);
+
+	ub1 = BPF_CORE_READ_BITFIELD(&bitfields, ub1);
+	ub7 = BPF_CORE_READ_BITFIELD(&bitfields, ub7);
+
+	return (ub7 << 1) | ub1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index c5588a14fe..960998f163 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -965,6 +965,7 @@ l0_%=:	r0 = 0;						\
 SEC("xdp")
 __description("bound check with JMP_JSLT for crossing 64-bit signed boundary")
 __success __retval(0)
+__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */
 __naked void crossing_64_bit_signed_boundary_2(void)
 {
 	asm volatile ("					\
@@ -1046,6 +1047,7 @@ l0_%=:	r0 = 0;						\
 SEC("xdp")
 __description("bound check with JMP32_JSLT for crossing 32-bit signed boundary")
 __success __retval(0)
+__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */
 __naked void crossing_32_bit_signed_boundary_2(void)
 {
 	asm volatile ("					\
@@ -1073,4 +1075,66 @@ l0_%=:	r0 = 0;						\
 	: __clobber_all);
 }
 
+SEC("tc")
+__description("bounds check with JMP_NE for reg edge")
+__success __retval(0)
+__naked void reg_not_equal_const(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	call %[bpf_get_prandom_u32];			\
+	r4 = r0;					\
+	r4 &= 7;					\
+	if r4 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r1 = r6;					\
+	r2 = 0;						\
+	r3 = r10;					\
+	r3 += -8;					\
+	r5 = 0;						\
+	/* The 4th argument of bpf_skb_store_bytes is defined as \
+	 * ARG_CONST_SIZE, so 0 is not allowed. The 'r4 != 0' \
+	 * is providing us this exclusion of zero from initial \
+	 * [0, 7] range.				\
+	 */						\
+	call %[bpf_skb_store_bytes];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("bounds check with JMP_EQ for reg edge")
+__success __retval(0)
+__naked void reg_equal_const(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	call %[bpf_get_prandom_u32];			\
+	r4 = r0;					\
+	r4 &= 7;					\
+	if r4 == 0 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = 0;						\
+	r3 = r10;					\
+	r3 += -8;					\
+	r5 = 0;						\
+	/* Just the same as what we do in reg_not_equal_const() */ \
+	call %[bpf_skb_store_bytes];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c b/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c
new file mode 100644
index 0000000000..36e033a2e0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+
+struct whatever {};
+
+SEC("kprobe")
+__success __log_level(2)
+/* context type is wrong, making it impossible to freplace this program */
+int btf_unreliable_kprobe(struct whatever *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c
index d6c4a7f3f7..6e0f349f8f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c
+++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c
@@ -7,7 +7,7 @@
 
 SEC("cgroup/sock")
 __description("bpf_exit with invalid return code. test1")
-__failure __msg("R0 has value (0x0; 0xffffffff)")
+__failure __msg("smin=0 smax=4294967295 should have been in [0, 1]")
 __naked void with_invalid_return_code_test1(void)
 {
 	asm volatile ("					\
@@ -30,7 +30,7 @@ __naked void with_invalid_return_code_test2(void)
 
 SEC("cgroup/sock")
 __description("bpf_exit with invalid return code. test3")
-__failure __msg("R0 has value (0x0; 0x3)")
+__failure __msg("smin=0 smax=3 should have been in [0, 1]")
 __naked void with_invalid_return_code_test3(void)
 {
 	asm volatile ("					\
@@ -53,7 +53,7 @@ __naked void with_invalid_return_code_test4(void)
 
 SEC("cgroup/sock")
 __description("bpf_exit with invalid return code. test5")
-__failure __msg("R0 has value (0x2; 0x0)")
+__failure __msg("smin=2 smax=2 should have been in [0, 1]")
 __naked void with_invalid_return_code_test5(void)
 {
 	asm volatile ("					\
@@ -75,7 +75,7 @@ __naked void with_invalid_return_code_test6(void)
 
 SEC("cgroup/sock")
 __description("bpf_exit with invalid return code. test7")
-__failure __msg("R0 has unknown scalar value")
+__failure __msg("R0 has unknown scalar value should have been in [0, 1]")
 __naked void with_invalid_return_code_test7(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
index 99a23dea82..be95570ab3 100644
--- a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
@@ -411,7 +411,7 @@ l0_%=:	r0 = 0;						\
 
 SEC("tc")
 __description("direct packet access: test17 (pruning, alignment)")
-__failure __msg("misaligned packet access off 2+(0x0; 0x0)+15+-4 size 4")
+__failure __msg("misaligned packet access off 2+0+15+-4 size 4")
 __flag(BPF_F_STRICT_ALIGNMENT)
 __naked void packet_access_test17_pruning_alignment(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
new file mode 100644
index 0000000000..67dddd9418
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
@@ -0,0 +1,350 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "xdp_metadata.h"
+#include "bpf_kfuncs.h"
+
+int arr[1];
+int unkn_idx;
+const volatile bool call_dead_subprog = false;
+
+__noinline long global_bad(void)
+{
+	return arr[unkn_idx]; /* BOOM */
+}
+
+__noinline long global_good(void)
+{
+	return arr[0];
+}
+
+__noinline long global_calls_bad(void)
+{
+	return global_good() + global_bad() /* does BOOM indirectly */;
+}
+
+__noinline long global_calls_good_only(void)
+{
+	return global_good();
+}
+
+__noinline long global_dead(void)
+{
+	return arr[0] * 2;
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+/* main prog is validated completely first */
+__msg("('global_calls_good_only') is global and assumed valid.")
+/* eventually global_good() is transitively validated as well */
+__msg("Validating global_good() func")
+__msg("('global_good') is safe for any args that match its prototype")
+int chained_global_func_calls_success(void)
+{
+	int sum = 0;
+
+	if (call_dead_subprog)
+		sum += global_dead();
+	return global_calls_good_only() + sum;
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+/* main prog validated successfully first */
+__msg("('global_calls_bad') is global and assumed valid.")
+/* eventually we validate global_bad() and fail */
+__msg("Validating global_bad() func")
+__msg("math between map_value pointer and register") /* BOOM */
+int chained_global_func_calls_bad(void)
+{
+	return global_calls_bad();
+}
+
+/* do out of bounds access forcing verifier to fail verification if this
+ * global func is called
+ */
+__noinline int global_unsupp(const int *mem)
+{
+	if (!mem)
+		return 0;
+	return mem[100]; /* BOOM */
+}
+
+const volatile bool skip_unsupp_global = true;
+
+SEC("?raw_tp")
+__success
+int guarded_unsupp_global_called(void)
+{
+	if (!skip_unsupp_global)
+		return global_unsupp(NULL);
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__msg("Func#1 ('global_unsupp') is global and assumed valid.")
+__msg("Validating global_unsupp() func#1...")
+__msg("value is outside of the allowed memory range")
+int unguarded_unsupp_global_called(void)
+{
+	int x = 0;
+
+	return global_unsupp(&x);
+}
+
+long stack[128];
+
+__weak int subprog_nullable_ptr_bad(int *p)
+{
+	return (*p) * 2; /* bad, missing null check */
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__msg("invalid mem access 'mem_or_null'")
+int arg_tag_nullable_ptr_fail(void *ctx)
+{
+	int x = 42;
+
+	return subprog_nullable_ptr_bad(&x);
+}
+
+__noinline __weak int subprog_nonnull_ptr_good(int *p1 __arg_nonnull, int *p2 __arg_nonnull)
+{
+	return (*p1) * (*p2); /* good, no need for NULL checks */
+}
+
+int x = 47;
+
+SEC("?raw_tp")
+__success __log_level(2)
+int arg_tag_nonnull_ptr_good(void *ctx)
+{
+	int y = 74;
+
+	return subprog_nonnull_ptr_good(&x, &y);
+}
+
+/* this global subprog can be now called from many types of entry progs, each
+ * with different context type
+ */
+__weak int subprog_ctx_tag(void *ctx __arg_ctx)
+{
+	return bpf_get_stack(ctx, stack, sizeof(stack), 0);
+}
+
+__weak int raw_tp_canonical(struct bpf_raw_tracepoint_args *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int raw_tp_u64_array(u64 *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+SEC("?raw_tp.w")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp_writable(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+SEC("?tp_btf/sys_enter")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp_btf(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+struct whatever { };
+
+__weak int tp_whatever(struct whatever *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?tp")
+__success __log_level(2)
+int arg_tag_ctx_tp(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + tp_whatever(ctx);
+}
+
+__weak int kprobe_subprog_pt_regs(struct pt_regs *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int kprobe_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?kprobe")
+__success __log_level(2)
+int arg_tag_ctx_kprobe(void *ctx)
+{
+	return subprog_ctx_tag(ctx) +
+	       kprobe_subprog_pt_regs(ctx) +
+	       kprobe_subprog_typedef(ctx);
+}
+
+__weak int perf_subprog_regs(
+#if defined(bpf_target_riscv)
+	struct user_regs_struct *ctx __arg_ctx
+#elif defined(bpf_target_s390)
+	/* user_pt_regs typedef is anonymous struct, so only `void *` works */
+	void *ctx __arg_ctx
+#elif defined(bpf_target_loongarch) || defined(bpf_target_arm64) || defined(bpf_target_powerpc)
+	struct user_pt_regs *ctx __arg_ctx
+#else
+	struct pt_regs *ctx __arg_ctx
+#endif
+)
+{
+	return 0;
+}
+
+__weak int perf_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int perf_subprog_canonical(struct bpf_perf_event_data *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?perf_event")
+__success __log_level(2)
+int arg_tag_ctx_perf(void *ctx)
+{
+	return subprog_ctx_tag(ctx) +
+	       perf_subprog_regs(ctx) +
+	       perf_subprog_typedef(ctx) +
+	       perf_subprog_canonical(ctx);
+}
+
+__weak int iter_subprog_void(void *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int iter_subprog_typed(struct bpf_iter__task *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?iter/task")
+__success __log_level(2)
+int arg_tag_ctx_iter_task(struct bpf_iter__task *ctx)
+{
+	return (iter_subprog_void(ctx) + iter_subprog_typed(ctx)) & 1;
+}
+
+__weak int tracing_subprog_void(void *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int tracing_subprog_u64(u64 *ctx __arg_ctx)
+{
+	return 0;
+}
+
+int acc;
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fentry)
+{
+	acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	return 0;
+}
+
+SEC("?fexit/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fexit)
+{
+	acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	return 0;
+}
+
+SEC("?fmod_ret/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fmod_ret)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC("?lsm/bpf")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_lsm)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC("?struct_ops/test_1")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_struct_ops)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC(".struct_ops")
+struct bpf_dummy_ops dummy_1 = {
+	.test_1 = (void *)arg_tag_ctx_struct_ops,
+};
+
+SEC("?syscall")
+__success __log_level(2)
+int arg_tag_ctx_syscall(void *ctx)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx) + tp_whatever(ctx);
+}
+
+__weak int subprog_dynptr(struct bpf_dynptr *dptr)
+{
+	long *d, t, buf[1] = {};
+
+	d = bpf_dynptr_data(dptr, 0, sizeof(long));
+	if (!d)
+		return 0;
+
+	t = *d + 1;
+
+	d = bpf_dynptr_slice(dptr, 0, &buf, sizeof(long));
+	if (!d)
+		return t;
+
+	t = *d + 2;
+
+	return t;
+}
+
+SEC("?xdp")
+__success __log_level(2)
+int arg_tag_dynptr(struct xdp_md *ctx)
+{
+	struct bpf_dynptr dptr;
+
+	bpf_dynptr_from_xdp(ctx, 0, &dptr);
+
+	return subprog_dynptr(&dptr);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index d1edbcff9a..05a329ee45 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -33,6 +33,25 @@ l3_%=:							\
 	: __clobber_all);
 }
 
+SEC("socket")
+__description("gotol, large_imm")
+__success __failure_unpriv __retval(40000)
+__naked void gotol_large_imm(void)
+{
+	asm volatile ("					\
+	gotol 1f;					\
+0:							\
+	r0 = 0;						\
+	.rept 40000;					\
+	r0 += 1;					\
+	.endr;						\
+	exit;						\
+1:	gotol 0b;					\
+"	:
+	:
+	: __clobber_all);
+}
+
 #else
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
index 692216c0ad..886498b5e6 100644
--- a/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
@@ -89,9 +89,14 @@ l0_%=:	exit;						\
 	: __clobber_all);
 }
 
+/* Call a function taking a pointer and a size which doesn't allow the size to
+ * be zero (i.e. bpf_trace_printk() declares the second argument to be
+ * ARG_CONST_SIZE, not ARG_CONST_SIZE_OR_ZERO). We attempt to pass zero for the
+ * size and expect to fail.
+ */
 SEC("tracepoint")
 __description("helper access to map: empty range")
-__failure __msg("invalid access to map value, value_size=48 off=0 size=0")
+__failure __msg("R2 invalid zero-sized read: u64=[0,0]")
 __naked void access_to_map_empty_range(void)
 {
 	asm volatile ("					\
@@ -113,6 +118,38 @@ l0_%=:	exit;						\
 	: __clobber_all);
 }
 
+/* Like the test above, but this time the size register is not known to be zero;
+ * its lower-bound is zero though, which is still unacceptable.
+ */
+SEC("tracepoint")
+__description("helper access to map: possibly-empty ange")
+__failure __msg("R2 invalid zero-sized read: u64=[0,4]")
+__naked void access_to_map_possibly_empty_range(void)
+{
+	asm volatile ("                                         \
+	r2 = r10;                                               \
+	r2 += -8;                                               \
+	r1 = 0;                                                 \
+	*(u64*)(r2 + 0) = r1;                                   \
+	r1 = %[map_hash_48b] ll;                                \
+	call %[bpf_map_lookup_elem];                            \
+	if r0 == 0 goto l0_%=;                                  \
+	r1 = r0;                                                \
+	/* Read an unknown value */                             \
+	r7 = *(u64*)(r0 + 0);                                   \
+	/* Make it small and positive, to avoid other errors */ \
+	r7 &= 4;                                                \
+	r2 = 0;                                                 \
+	r2 += r7;                                               \
+	call %[bpf_trace_printk];                               \
+l0_%=:	exit;                                               \
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_trace_printk),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
 SEC("tracepoint")
 __description("helper access to map: out-of-bound range")
 __failure __msg("invalid access to map value, value_size=48 off=0 size=56")
@@ -221,7 +258,7 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("helper access to adjusted map (via const imm): empty range")
-__failure __msg("invalid access to map value, value_size=48 off=4 size=0")
+__failure __msg("R2 invalid zero-sized read")
 __naked void via_const_imm_empty_range(void)
 {
 	asm volatile ("					\
@@ -386,7 +423,7 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("helper access to adjusted map (via const reg): empty range")
-__failure __msg("R1 min value is outside of the allowed memory range")
+__failure __msg("R2 invalid zero-sized read")
 __naked void via_const_reg_empty_range(void)
 {
 	asm volatile ("					\
@@ -556,7 +593,7 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("helper access to adjusted map (via variable): empty range")
-__failure __msg("R1 min value is outside of the allowed memory range")
+__failure __msg("R2 invalid zero-sized read")
 __naked void map_via_variable_empty_range(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
index 589e8270de..9fc3fae5cd 100644
--- a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
+++ b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
@@ -68,7 +68,7 @@ __naked void ptr_to_long_half_uninitialized(void)
 
 SEC("cgroup/sysctl")
 __description("ARG_PTR_TO_LONG misaligned")
-__failure __msg("misaligned stack access off (0x0; 0x0)+-20+0 size 8")
+__failure __msg("misaligned stack access off 0+-20+0 size 8")
 __naked void arg_ptr_to_long_misaligned(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
index 5905e036e0..a955a63582 100644
--- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -239,4 +239,74 @@ int bpf_loop_iter_limit_nested(void *unused)
 	return 1000 * a + b + c;
 }
 
+struct iter_limit_bug_ctx {
+	__u64 a;
+	__u64 b;
+	__u64 c;
+};
+
+static __naked void iter_limit_bug_cb(void)
+{
+	/* This is the same as C code below, but written
+	 * in assembly to control which branches are fall-through.
+	 *
+	 *   switch (bpf_get_prandom_u32()) {
+	 *   case 1:  ctx->a = 42; break;
+	 *   case 2:  ctx->b = 42; break;
+	 *   default: ctx->c = 42; break;
+	 *   }
+	 */
+	asm volatile (
+	"r9 = r2;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = r0;"
+	"r2 = 42;"
+	"r0 = 0;"
+	"if r1 == 0x1 goto 1f;"
+	"if r1 == 0x2 goto 2f;"
+	"*(u64 *)(r9 + 16) = r2;"
+	"exit;"
+	"1: *(u64 *)(r9 + 0) = r2;"
+	"exit;"
+	"2: *(u64 *)(r9 + 8) = r2;"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all
+	);
+}
+
+SEC("tc")
+__failure
+__flag(BPF_F_TEST_STATE_FREQ)
+int iter_limit_bug(struct __sk_buff *skb)
+{
+	struct iter_limit_bug_ctx ctx = { 7, 7, 7 };
+
+	bpf_loop(2, iter_limit_bug_cb, &ctx, 0);
+
+	/* This is the same as C code below,
+	 * written in assembly to guarantee checks order.
+	 *
+	 *   if (ctx.a == 42 && ctx.b == 42 && ctx.c == 7)
+	 *     asm volatile("r1 /= 0;":::"r1");
+	 */
+	asm volatile (
+	"r1 = *(u64 *)%[ctx_a];"
+	"if r1 != 42 goto 1f;"
+	"r1 = *(u64 *)%[ctx_b];"
+	"if r1 != 42 goto 1f;"
+	"r1 = *(u64 *)%[ctx_c];"
+	"if r1 != 7 goto 1f;"
+	"r1 /= 0;"
+	"1:"
+	:
+	: [ctx_a]"m"(ctx.a),
+	  [ctx_b]"m"(ctx.b),
+	  [ctx_c]"m"(ctx.c)
+	: "r1"
+	);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c
index 353ae6da00..e1ffa5d32f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c
+++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c
@@ -39,7 +39,7 @@ __naked void with_valid_return_code_test3(void)
 
 SEC("netfilter")
 __description("bpf_exit with invalid return code. test4")
-__failure __msg("R0 has value (0x2; 0x0)")
+__failure __msg("R0 has smin=2 smax=2 should have been in [0, 1]")
 __naked void with_invalid_return_code_test4(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
index f67390224a..7cc83acac7 100644
--- a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
+++ b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
@@ -64,7 +64,7 @@ __naked void load_bytes_negative_len_2(void)
 
 SEC("tc")
 __description("raw_stack: skb_load_bytes, zero len")
-__failure __msg("invalid zero-sized read")
+__failure __msg("R4 invalid zero-sized read: u64=[0,0]")
 __naked void skb_load_bytes_zero_len(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
index 6115520154..39fe3372e0 100644
--- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
+++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
+#include <../../../tools/include/linux/filter.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_RINGBUF);
@@ -450,4 +451,290 @@ l0_%=:	r1 >>= 16;					\
 	: __clobber_all);
 }
 
+SEC("raw_tp")
+__log_level(2)
+__success
+__msg("fp-8=0m??mmmm")
+__msg("fp-16=00mm??mm")
+__msg("fp-24=00mm???m")
+__naked void spill_subregs_preserve_stack_zero(void)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+
+		/* 32-bit subreg spill with ZERO, MISC, and INVALID */
+		".8byte %[fp1_u8_st_zero];"   /* ZERO, LLVM-18+: *(u8 *)(r10 -1) = 0; */
+		"*(u8 *)(r10 -2) = r0;"       /* MISC */
+		/* fp-3 and fp-4 stay INVALID */
+		"*(u32 *)(r10 -8) = r0;"
+
+		/* 16-bit subreg spill with ZERO, MISC, and INVALID */
+		".8byte %[fp10_u16_st_zero];" /* ZERO, LLVM-18+: *(u16 *)(r10 -10) = 0; */
+		"*(u16 *)(r10 -12) = r0;"     /* MISC */
+		/* fp-13 and fp-14 stay INVALID */
+		"*(u16 *)(r10 -16) = r0;"
+
+		/* 8-bit subreg spill with ZERO, MISC, and INVALID */
+		".8byte %[fp18_u16_st_zero];" /* ZERO, LLVM-18+: *(u16 *)(r18 -10) = 0; */
+		"*(u16 *)(r10 -20) = r0;"     /* MISC */
+		/* fp-21, fp-22, and fp-23 stay INVALID */
+		"*(u8 *)(r10 -24) = r0;"
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm_insn(fp1_u8_st_zero, BPF_ST_MEM(BPF_B, BPF_REG_FP, -1, 0)),
+	  __imm_insn(fp10_u16_st_zero, BPF_ST_MEM(BPF_H, BPF_REG_FP, -10, 0)),
+	  __imm_insn(fp18_u16_st_zero, BPF_ST_MEM(BPF_H, BPF_REG_FP, -18, 0))
+	: __clobber_all);
+}
+
+char single_byte_buf[1] SEC(".data.single_byte_buf");
+
+SEC("raw_tp")
+__log_level(2)
+__success
+/* make sure fp-8 is all STACK_ZERO */
+__msg("2: (7a) *(u64 *)(r10 -8) = 0          ; R10=fp0 fp-8_w=00000000")
+/* but fp-16 is spilled IMPRECISE zero const reg */
+__msg("4: (7b) *(u64 *)(r10 -16) = r0        ; R0_w=0 R10=fp0 fp-16_w=0")
+/* validate that assigning R2 from STACK_ZERO doesn't mark register
+ * precise immediately; if necessary, it will be marked precise later
+ */
+__msg("6: (71) r2 = *(u8 *)(r10 -1)          ; R2_w=0 R10=fp0 fp-8_w=00000000")
+/* similarly, when R2 is assigned from spilled register, it is initially
+ * imprecise, but will be marked precise later once it is used in precise context
+ */
+__msg("10: (71) r2 = *(u8 *)(r10 -9)         ; R2_w=0 R10=fp0 fp-16_w=0")
+__msg("11: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 11 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 10: (71) r2 = *(u8 *)(r10 -9)")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 8: (73) *(u8 *)(r1 +0) = r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 7: (0f) r1 += r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 6: (71) r2 = *(u8 *)(r10 -1)")
+__msg("mark_precise: frame0: regs= stack=-16 before 5: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 4: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 3: (b7) r0 = 0")
+__naked void partial_stack_load_preserves_zeros(void)
+{
+	asm volatile (
+		/* fp-8 is all STACK_ZERO */
+		".8byte %[fp8_st_zero];" /* LLVM-18+: *(u64 *)(r10 -8) = 0; */
+
+		/* fp-16 is const zero register */
+		"r0 = 0;"
+		"*(u64 *)(r10 -16) = r0;"
+
+		/* load single U8 from non-aligned STACK_ZERO slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u8 *)(r10 -1);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U8 from non-aligned ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u8 *)(r10 -9);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U16 from non-aligned STACK_ZERO slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u16 *)(r10 -2);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U16 from non-aligned ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u16 *)(r10 -10);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from non-aligned STACK_ZERO slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u32 *)(r10 -4);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from non-aligned ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u32 *)(r10 -12);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* for completeness, load U64 from STACK_ZERO slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u64 *)(r10 -8);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* for completeness, load U64 from ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u64 *)(r10 -16);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(single_byte_buf),
+	  __imm_insn(fp8_st_zero, BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0))
+	: __clobber_common);
+}
+
+char two_byte_buf[2] SEC(".data.two_byte_buf");
+
+SEC("raw_tp")
+__log_level(2) __flag(BPF_F_TEST_STATE_FREQ)
+__success
+/* make sure fp-8 is IMPRECISE fake register spill */
+__msg("3: (7a) *(u64 *)(r10 -8) = 1          ; R10=fp0 fp-8_w=1")
+/* and fp-16 is spilled IMPRECISE const reg */
+__msg("5: (7b) *(u64 *)(r10 -16) = r0        ; R0_w=1 R10=fp0 fp-16_w=1")
+/* validate load from fp-8, which was initialized using BPF_ST_MEM */
+__msg("8: (79) r2 = *(u64 *)(r10 -8)         ; R2_w=1 R10=fp0 fp-8=1")
+__msg("9: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 8: (79) r2 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6")
+/* note, fp-8 is precise, fp-16 is not yet precise, we'll get there */
+__msg("mark_precise: frame0: parent state regs= stack=-8:  R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_rw=P1 fp-16_w=1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (7a) *(u64 *)(r10 -8) = 1")
+__msg("10: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+/* validate load from fp-16, which was initialized using BPF_STX_MEM */
+__msg("12: (79) r2 = *(u64 *)(r10 -16)       ; R2_w=1 R10=fp0 fp-16=1")
+__msg("13: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 12: (79) r2 = *(u64 *)(r10 -16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 11: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 10: (73) *(u8 *)(r1 +0) = r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 8: (79) r2 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6")
+/* now both fp-8 and fp-16 are precise, very good */
+__msg("mark_precise: frame0: parent state regs= stack=-16:  R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_rw=P1 fp-16_rw=P1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-16 before 5: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1")
+__msg("14: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+__naked void stack_load_preserves_const_precision(void)
+{
+	asm volatile (
+		/* establish checkpoint with state that has no stack slots;
+		 * if we bubble up to this state without finding desired stack
+		 * slot, then it's a bug and should be caught
+		 */
+		"goto +0;"
+
+		/* fp-8 is const 1 *fake* register */
+		".8byte %[fp8_st_one];" /* LLVM-18+: *(u64 *)(r10 -8) = 1; */
+
+		/* fp-16 is const 1 register */
+		"r0 = 1;"
+		"*(u64 *)(r10 -16) = r0;"
+
+		/* force checkpoint to check precision marks preserved in parent states */
+		"goto +0;"
+
+		/* load single U64 from aligned FAKE_REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u64 *)(r10 -8);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U64 from aligned REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u64 *)(r10 -16);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(two_byte_buf),
+	  __imm_insn(fp8_st_one, BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 1))
+	: __clobber_common);
+}
+
+SEC("raw_tp")
+__log_level(2) __flag(BPF_F_TEST_STATE_FREQ)
+__success
+/* make sure fp-8 is 32-bit FAKE subregister spill */
+__msg("3: (62) *(u32 *)(r10 -8) = 1          ; R10=fp0 fp-8=????1")
+/* but fp-16 is spilled IMPRECISE zero const reg */
+__msg("5: (63) *(u32 *)(r10 -16) = r0        ; R0_w=1 R10=fp0 fp-16=????1")
+/* validate load from fp-8, which was initialized using BPF_ST_MEM */
+__msg("8: (61) r2 = *(u32 *)(r10 -8)         ; R2_w=1 R10=fp0 fp-8=????1")
+__msg("9: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 8: (61) r2 = *(u32 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6")
+__msg("mark_precise: frame0: parent state regs= stack=-8:  R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_r=????P1 fp-16=????1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-8 before 5: (63) *(u32 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (62) *(u32 *)(r10 -8) = 1")
+__msg("10: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+/* validate load from fp-16, which was initialized using BPF_STX_MEM */
+__msg("12: (61) r2 = *(u32 *)(r10 -16)       ; R2_w=1 R10=fp0 fp-16=????1")
+__msg("13: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 12: (61) r2 = *(u32 *)(r10 -16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 11: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 10: (73) *(u8 *)(r1 +0) = r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 8: (61) r2 = *(u32 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6")
+__msg("mark_precise: frame0: parent state regs= stack=-16:  R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_r=????P1 fp-16_r=????P1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-16 before 5: (63) *(u32 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1")
+__msg("14: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+__naked void stack_load_preserves_const_precision_subreg(void)
+{
+	asm volatile (
+		/* establish checkpoint with state that has no stack slots;
+		 * if we bubble up to this state without finding desired stack
+		 * slot, then it's a bug and should be caught
+		 */
+		"goto +0;"
+
+		/* fp-8 is const 1 *fake* SUB-register */
+		".8byte %[fp8_st_one];" /* LLVM-18+: *(u32 *)(r10 -8) = 1; */
+
+		/* fp-16 is const 1 SUB-register */
+		"r0 = 1;"
+		"*(u32 *)(r10 -16) = r0;"
+
+		/* force checkpoint to check precision marks preserved in parent states */
+		"goto +0;"
+
+		/* load single U32 from aligned FAKE_REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u32 *)(r10 -8);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from aligned REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u32 *)(r10 -16);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(two_byte_buf),
+	  __imm_insn(fp8_st_one, BPF_ST_MEM(BPF_W, BPF_REG_FP, -8, 1)) /* 32-bit spill */
+	: __clobber_common);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
index e0f77e3e78..417c61cd4b 100644
--- a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
+++ b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
@@ -37,7 +37,7 @@ __naked void ptr_to_stack_store_load(void)
 
 SEC("socket")
 __description("PTR_TO_STACK store/load - bad alignment on off")
-__failure __msg("misaligned stack access off (0x0; 0x0)+-8+2 size 8")
+__failure __msg("misaligned stack access off 0+-8+2 size 8")
 __failure_unpriv
 __naked void load_bad_alignment_on_off(void)
 {
@@ -53,7 +53,7 @@ __naked void load_bad_alignment_on_off(void)
 
 SEC("socket")
 __description("PTR_TO_STACK store/load - bad alignment on reg")
-__failure __msg("misaligned stack access off (0x0; 0x0)+-10+8 size 8")
+__failure __msg("misaligned stack access off 0+-10+8 size 8")
 __failure_unpriv
 __naked void load_bad_alignment_on_reg(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
index f61d623b1c..6f5d19665c 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -117,6 +117,56 @@ __naked int global_subprog_result_precise(void)
 	);
 }
 
+__naked __noinline __used
+static unsigned long loop_callback_bad()
+{
+	/* bpf_loop() callback that can return values outside of [0, 1] range */
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 s> 1000 goto 1f;"
+		"r0 = 0;"
+	"1:"
+		"goto +0;" /* checkpoint */
+		/* bpf_loop() expects [0, 1] values, so branch above skipping
+		 * r0 = 0; should lead to a failure, but if exit instruction
+		 * doesn't enforce r0's precision, this callback will be
+		 * successfully verified
+		 */
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_common
+	);
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+/* check that fallthrough code path marks r0 as precise */
+__msg("mark_precise: frame1: regs=r0 stack= before 11: (b7) r0 = 0")
+/* check that we have branch code path doing its own validation */
+__msg("from 10 to 12: frame1: R0=scalar(smin=umin=1001")
+/* check that branch code path marks r0 as precise, before failing */
+__msg("mark_precise: frame1: regs=r0 stack= before 9: (85) call bpf_get_prandom_u32#7")
+__msg("At callback return the register R0 has smin=1001 should have been in [0, 1]")
+__naked int callback_precise_return_fail(void)
+{
+	asm volatile (
+		"r1 = 1;"			/* nr_loops */
+		"r2 = %[loop_callback_bad];"	/* callback_fn */
+		"r3 = 0;"			/* callback_ctx */
+		"r4 = 0;"			/* flags */
+		"call %[bpf_loop];"
+
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm_ptr(loop_callback_bad),
+		  __imm(bpf_loop)
+		: __clobber_common
+	);
+}
+
 SEC("?raw_tp")
 __success __log_level(2)
 /* First simulated path does not include callback body,
@@ -370,12 +420,10 @@ __naked int parent_stack_slot_precise(void)
 SEC("?raw_tp")
 __success __log_level(2)
 __msg("9: (0f) r1 += r6")
-__msg("mark_precise: frame0: last_idx 9 first_idx 6")
+__msg("mark_precise: frame0: last_idx 9 first_idx 0")
 __msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4")
 __msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)")
-__msg("mark_precise: frame0: parent state regs= stack=-8:")
-__msg("mark_precise: frame0: last_idx 5 first_idx 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6")
 __msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6")
@@ -541,11 +589,24 @@ static __u64 subprog_spill_reg_precise(void)
 
 SEC("?raw_tp")
 __success __log_level(2)
-/* precision backtracking can't currently handle stack access not through r10,
- * so we won't be able to mark stack slot fp-8 as precise, and so will
- * fallback to forcing all as precise
- */
-__msg("mark_precise: frame0: falling back to forcing all scalars precise")
+__msg("10: (0f) r1 += r7")
+__msg("mark_precise: frame0: last_idx 10 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r7 stack= before 9: (bf) r1 = r8")
+__msg("mark_precise: frame0: regs=r7 stack= before 8: (27) r7 *= 4")
+__msg("mark_precise: frame0: regs=r7 stack= before 7: (79) r7 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: parent state regs= stack=-8:  R0_w=2 R6_w=1 R8_rw=map_value(map=.data.vals,ks=4,vs=16) R10=fp0 fp-8_rw=P1")
+__msg("mark_precise: frame0: last_idx 18 first_idx 0 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 17: (0f) r0 += r2")
+__msg("mark_precise: frame1: regs= stack= before 16: (79) r2 = *(u64 *)(r1 +0)")
+__msg("mark_precise: frame1: regs= stack= before 15: (79) r0 = *(u64 *)(r10 -16)")
+__msg("mark_precise: frame1: regs= stack= before 14: (7b) *(u64 *)(r10 -16) = r2")
+__msg("mark_precise: frame1: regs= stack= before 13: (7b) *(u64 *)(r1 +0) = r2")
+__msg("mark_precise: frame1: regs=r2 stack= before 6: (85) call pc+6")
+__msg("mark_precise: frame0: regs=r2 stack= before 5: (bf) r2 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 4: (07) r1 += -8")
+__msg("mark_precise: frame0: regs=r6 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 1")
 __naked int subprog_spill_into_parent_stack_slot_precise(void)
 {
 	asm volatile (
@@ -580,14 +641,68 @@ __naked int subprog_spill_into_parent_stack_slot_precise(void)
 	);
 }
 
-__naked __noinline __used
-static __u64 subprog_with_checkpoint(void)
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("17: (0f) r1 += r0")
+__msg("mark_precise: frame0: last_idx 17 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 16: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r0 stack= before 15: (27) r0 *= 4")
+__msg("mark_precise: frame0: regs=r0 stack= before 14: (79) r0 = *(u64 *)(r10 -16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 13: (7b) *(u64 *)(r7 -8) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 12: (79) r0 = *(u64 *)(r8 +16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 11: (7b) *(u64 *)(r8 +16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 10: (79) r0 = *(u64 *)(r7 -8)")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 8: (07) r8 += -32")
+__msg("mark_precise: frame0: regs=r0 stack= before 7: (bf) r8 = r10")
+__msg("mark_precise: frame0: regs=r0 stack= before 6: (07) r7 += -8")
+__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r7 = r10")
+__msg("mark_precise: frame0: regs=r0 stack= before 21: (95) exit")
+__msg("mark_precise: frame1: regs=r0 stack= before 20: (bf) r0 = r1")
+__msg("mark_precise: frame1: regs=r1 stack= before 4: (85) call pc+15")
+__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 1")
+__naked int stack_slot_aliases_precision(void)
 {
 	asm volatile (
-		"r0 = 0;"
-		/* guaranteed checkpoint if BPF_F_TEST_STATE_FREQ is used */
-		"goto +0;"
+		"r6 = 1;"
+		/* pass r6 through r1 into subprog to get it back as r0;
+		 * this whole chain will have to be marked as precise later
+		 */
+		"r1 = r6;"
+		"call identity_subprog;"
+		/* let's setup two registers that are aliased to r10 */
+		"r7 = r10;"
+		"r7 += -8;"			/* r7 = r10 - 8 */
+		"r8 = r10;"
+		"r8 += -32;"			/* r8 = r10 - 32 */
+		/* now spill subprog's return value (a r6 -> r1 -> r0 chain)
+		 * a few times through different stack pointer regs, making
+		 * sure to use r10, r7, and r8 both in LDX and STX insns, and
+		 * *importantly* also using a combination of const var_off and
+		 * insn->off to validate that we record final stack slot
+		 * correctly, instead of relying on just insn->off derivation,
+		 * which is only valid for r10-based stack offset
+		 */
+		"*(u64 *)(r10 - 16) = r0;"
+		"r0 = *(u64 *)(r7 - 8);"	/* r7 - 8 == r10 - 16 */
+		"*(u64 *)(r8 + 16) = r0;"	/* r8 + 16 = r10 - 16 */
+		"r0 = *(u64 *)(r8 + 16);"
+		"*(u64 *)(r7 - 8) = r0;"
+		"r0 = *(u64 *)(r10 - 16);"
+		/* get ready to use r0 as an index into array to force precision */
+		"r0 *= 4;"
+		"r1 = %[vals];"
+		/* here r0->r1->r6 chain is forced to be precise and has to be
+		 * propagated back to the beginning, including through the
+		 * subprog call and all the stack spills and loads
+		 */
+		"r1 += r0;"
+		"r0 = *(u32 *)(r1 + 0);"
 		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common, "r6"
 	);
 }
 
diff --git a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
index 71814a7532..a9ab37d3b9 100644
--- a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
+++ b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
@@ -146,4 +146,23 @@ l0_%=:	exit;						\
 	: __clobber_all);
 }
 
+SEC("flow_dissector")
+__description("flow_keys illegal alu op with variable offset")
+__failure __msg("R7 pointer arithmetic on flow_keys prohibited")
+__naked void flow_keys_illegal_variable_offset_alu(void)
+{
+	asm volatile("					\
+	r6 = r1;					\
+	r7 = *(u64*)(r6 + %[flow_keys_off]);		\
+	r8 = 8;						\
+	r8 /= 1;					\
+	r8 &= 8;					\
+	r7 += r8;					\
+	r0 = *(u64*)(r7 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(flow_keys_off, offsetof(struct __sk_buff, flow_keys))
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_var_off.c b/tools/testing/selftests/bpf/progs/verifier_var_off.c
index d1f23c1a7c..c810f4f6f4 100644
--- a/tools/testing/selftests/bpf/progs/verifier_var_off.c
+++ b/tools/testing/selftests/bpf/progs/verifier_var_off.c
@@ -263,6 +263,35 @@ __naked void access_max_out_of_bound(void)
 	: __clobber_all);
 }
 
+/* Similar to the test above, but this time check the special case of a
+ * zero-sized stack access. We used to have a bug causing crashes for zero-sized
+ * out-of-bounds accesses.
+ */
+SEC("socket")
+__description("indirect variable-offset stack access, zero-sized, max out of bound")
+__failure __msg("invalid variable-offset indirect access to stack R1")
+__naked void zero_sized_access_max_out_of_bound(void)
+{
+	asm volatile ("                      \
+	r0 = 0;                              \
+	/* Fill some stack */                \
+	*(u64*)(r10 - 16) = r0;              \
+	*(u64*)(r10 - 8) = r0;               \
+	/* Get an unknown value */           \
+	r1 = *(u32*)(r1 + 0);                \
+	r1 &= 63;                            \
+	r1 += -16;                           \
+	/* r1 is now anywhere in [-16,48) */ \
+	r1 += r10;                           \
+	r2 = 0;                              \
+	r3 = 0;                              \
+	call %[bpf_probe_read_kernel];       \
+	exit;                                \
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
 SEC("lwt_in")
 __description("indirect variable-offset stack access, min out of bound")
 __failure __msg("invalid variable-offset indirect access to stack R2")
diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
index f6d1cc9ad8..330ece2eab 100644
--- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -20,21 +20,32 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
 					 __u64 *timestamp) __ksym;
 extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
 				    enum xdp_rss_hash_type *rss_type) __ksym;
+extern int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					__be16 *vlan_proto,
+					__u16 *vlan_tci) __ksym;
 
 SEC("xdp.frags")
 int rx(struct xdp_md *ctx)
 {
 	void *data, *data_meta, *data_end;
 	struct ipv6hdr *ip6h = NULL;
-	struct ethhdr *eth = NULL;
 	struct udphdr *udp = NULL;
 	struct iphdr *iph = NULL;
 	struct xdp_meta *meta;
+	struct ethhdr *eth;
 	int err;
 
 	data = (void *)(long)ctx->data;
 	data_end = (void *)(long)ctx->data_end;
 	eth = data;
+
+	if (eth + 1 < data_end && (eth->h_proto == bpf_htons(ETH_P_8021AD) ||
+				   eth->h_proto == bpf_htons(ETH_P_8021Q)))
+		eth = (void *)eth + sizeof(struct vlan_hdr);
+
+	if (eth + 1 < data_end && eth->h_proto == bpf_htons(ETH_P_8021Q))
+		eth = (void *)eth + sizeof(struct vlan_hdr);
+
 	if (eth + 1 < data_end) {
 		if (eth->h_proto == bpf_htons(ETH_P_IP)) {
 			iph = (void *)(eth + 1);
@@ -76,15 +87,28 @@ int rx(struct xdp_md *ctx)
 		return XDP_PASS;
 	}
 
+	meta->hint_valid = 0;
+
+	meta->xdp_timestamp = bpf_ktime_get_tai_ns();
 	err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp);
-	if (!err)
-		meta->xdp_timestamp = bpf_ktime_get_tai_ns();
+	if (err)
+		meta->rx_timestamp_err = err;
 	else
-		meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */
+		meta->hint_valid |= XDP_META_FIELD_TS;
 
-	err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);
-	if (err < 0)
-		meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */
+	err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash,
+				       &meta->rx_hash_type);
+	if (err)
+		meta->rx_hash_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_RSS;
+
+	err = bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto,
+					   &meta->rx_vlan_tci);
+	if (err)
+		meta->rx_vlan_tag_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_VLAN_TAG;
 
 	__sync_add_and_fetch(&pkts_redir, 1);
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c
index d151d406a1..31ca229bb3 100644
--- a/tools/testing/selftests/bpf/progs/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c
@@ -23,15 +23,47 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
 					 __u64 *timestamp) __ksym;
 extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
 				    enum xdp_rss_hash_type *rss_type) __ksym;
+extern int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					__be16 *vlan_proto,
+					__u16 *vlan_tci) __ksym;
 
 SEC("xdp")
 int rx(struct xdp_md *ctx)
 {
-	void *data, *data_meta;
+	void *data, *data_meta, *data_end;
+	struct ipv6hdr *ip6h = NULL;
+	struct ethhdr *eth = NULL;
+	struct udphdr *udp = NULL;
+	struct iphdr *iph = NULL;
 	struct xdp_meta *meta;
 	u64 timestamp = -1;
 	int ret;
 
+	data = (void *)(long)ctx->data;
+	data_end = (void *)(long)ctx->data_end;
+	eth = data;
+	if (eth + 1 < data_end) {
+		if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+			iph = (void *)(eth + 1);
+			if (iph + 1 < data_end && iph->protocol == IPPROTO_UDP)
+				udp = (void *)(iph + 1);
+		}
+		if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+			ip6h = (void *)(eth + 1);
+			if (ip6h + 1 < data_end && ip6h->nexthdr == IPPROTO_UDP)
+				udp = (void *)(ip6h + 1);
+		}
+		if (udp && udp + 1 > data_end)
+			udp = NULL;
+	}
+
+	if (!udp)
+		return XDP_PASS;
+
+	/* Forwarding UDP:8080 to AF_XDP */
+	if (udp->dest != bpf_htons(8080))
+		return XDP_PASS;
+
 	/* Reserve enough for all custom metadata. */
 
 	ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta));
@@ -57,6 +89,8 @@ int rx(struct xdp_md *ctx)
 		meta->rx_timestamp = 1;
 
 	bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);
+	bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto,
+				     &meta->rx_vlan_tci);
 
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
 }
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 37ffa57f28..f013910212 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -12,7 +12,7 @@
 #define str_has_pfx(str, pfx) \
 	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
 
-#define TEST_LOADER_LOG_BUF_SZ 1048576
+#define TEST_LOADER_LOG_BUF_SZ 2097152
 
 #define TEST_TAG_EXPECT_FAILURE "comment:test_expect_failure"
 #define TEST_TAG_EXPECT_SUCCESS "comment:test_expect_success"
@@ -27,6 +27,7 @@
 #define TEST_TAG_RETVAL_PFX_UNPRIV "comment:test_retval_unpriv="
 #define TEST_TAG_AUXILIARY "comment:test_auxiliary"
 #define TEST_TAG_AUXILIARY_UNPRIV "comment:test_auxiliary_unpriv"
+#define TEST_BTF_PATH "comment:test_btf_path="
 
 /* Warning: duplicated in bpf_misc.h */
 #define POINTER_VALUE	0xcafe4all
@@ -58,6 +59,7 @@ struct test_spec {
 	const char *prog_name;
 	struct test_subspec priv;
 	struct test_subspec unpriv;
+	const char *btf_custom_path;
 	int log_level;
 	int prog_flags;
 	int mode_mask;
@@ -153,6 +155,14 @@ static int parse_retval(const char *str, int *val, const char *name)
 	return parse_int(str, val, name);
 }
 
+static void update_flags(int *flags, int flag, bool clear)
+{
+	if (clear)
+		*flags &= ~flag;
+	else
+		*flags |= flag;
+}
+
 /* Uses btf_decl_tag attributes to describe the expected test
  * behavior, see bpf_misc.h for detailed description of each attribute
  * and attribute combinations.
@@ -171,6 +181,7 @@ static int parse_test_spec(struct test_loader *tester,
 	memset(spec, 0, sizeof(*spec));
 
 	spec->prog_name = bpf_program__name(prog);
+	spec->prog_flags = BPF_F_TEST_REG_INVARIANTS; /* by default be strict */
 
 	btf = bpf_object__btf(obj);
 	if (!btf) {
@@ -187,7 +198,8 @@ static int parse_test_spec(struct test_loader *tester,
 	for (i = 1; i < btf__type_cnt(btf); i++) {
 		const char *s, *val, *msg;
 		const struct btf_type *t;
-		int tmp;
+		bool clear;
+		int flags;
 
 		t = btf__type_by_id(btf, i);
 		if (!btf_is_decl_tag(t))
@@ -253,24 +265,33 @@ static int parse_test_spec(struct test_loader *tester,
 				goto cleanup;
 		} else if (str_has_pfx(s, TEST_TAG_PROG_FLAGS_PFX)) {
 			val = s + sizeof(TEST_TAG_PROG_FLAGS_PFX) - 1;
+
+			clear = val[0] == '!';
+			if (clear)
+				val++;
+
 			if (strcmp(val, "BPF_F_STRICT_ALIGNMENT") == 0) {
-				spec->prog_flags |= BPF_F_STRICT_ALIGNMENT;
+				update_flags(&spec->prog_flags, BPF_F_STRICT_ALIGNMENT, clear);
 			} else if (strcmp(val, "BPF_F_ANY_ALIGNMENT") == 0) {
-				spec->prog_flags |= BPF_F_ANY_ALIGNMENT;
+				update_flags(&spec->prog_flags, BPF_F_ANY_ALIGNMENT, clear);
 			} else if (strcmp(val, "BPF_F_TEST_RND_HI32") == 0) {
-				spec->prog_flags |= BPF_F_TEST_RND_HI32;
+				update_flags(&spec->prog_flags, BPF_F_TEST_RND_HI32, clear);
 			} else if (strcmp(val, "BPF_F_TEST_STATE_FREQ") == 0) {
-				spec->prog_flags |= BPF_F_TEST_STATE_FREQ;
+				update_flags(&spec->prog_flags, BPF_F_TEST_STATE_FREQ, clear);
 			} else if (strcmp(val, "BPF_F_SLEEPABLE") == 0) {
-				spec->prog_flags |= BPF_F_SLEEPABLE;
+				update_flags(&spec->prog_flags, BPF_F_SLEEPABLE, clear);
 			} else if (strcmp(val, "BPF_F_XDP_HAS_FRAGS") == 0) {
-				spec->prog_flags |= BPF_F_XDP_HAS_FRAGS;
+				update_flags(&spec->prog_flags, BPF_F_XDP_HAS_FRAGS, clear);
+			} else if (strcmp(val, "BPF_F_TEST_REG_INVARIANTS") == 0) {
+				update_flags(&spec->prog_flags, BPF_F_TEST_REG_INVARIANTS, clear);
 			} else /* assume numeric value */ {
-				err = parse_int(val, &tmp, "test prog flags");
+				err = parse_int(val, &flags, "test prog flags");
 				if (err)
 					goto cleanup;
-				spec->prog_flags |= tmp;
+				update_flags(&spec->prog_flags, flags, clear);
 			}
+		} else if (str_has_pfx(s, TEST_BTF_PATH)) {
+			spec->btf_custom_path = s + sizeof(TEST_BTF_PATH) - 1;
 		}
 	}
 
@@ -561,6 +582,9 @@ void run_subtest(struct test_loader *tester,
 		}
 	}
 
+	/* Implicitly reset to NULL if next test case doesn't specify */
+	open_opts->btf_custom_path = spec->btf_custom_path;
+
 	tobj = bpf_object__open_mem(obj_bytes, obj_byte_cnt, open_opts);
 	if (!ASSERT_OK_PTR(tobj, "obj_open_mem")) /* shouldn't happen */
 		goto subtest_cleanup;
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index e0dd101c9f..dfbab214f4 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1400,13 +1400,18 @@ static void test_map_stress(void)
 #define MAX_DELAY_US 50000
 #define MIN_DELAY_RANGE_US 5000
 
-static int map_update_retriable(int map_fd, const void *key, const void *value,
-				int flags, int attempts)
+static bool retry_for_again_or_busy(int err)
+{
+	return (err == EAGAIN || err == EBUSY);
+}
+
+int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts,
+			 retry_for_error_fn need_retry)
 {
 	int delay = rand() % MIN_DELAY_RANGE_US;
 
 	while (bpf_map_update_elem(map_fd, key, value, flags)) {
-		if (!attempts || (errno != EAGAIN && errno != EBUSY))
+		if (!attempts || !need_retry(errno))
 			return -errno;
 
 		if (delay <= MAX_DELAY_US / 2)
@@ -1449,11 +1454,13 @@ static void test_update_delete(unsigned int fn, void *data)
 		key = value = i;
 
 		if (do_update) {
-			err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES);
+			err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES,
+						   retry_for_again_or_busy);
 			if (err)
 				printf("error %d %d\n", err, errno);
 			assert(err == 0);
-			err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES);
+			err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES,
+						   retry_for_again_or_busy);
 			if (err)
 				printf("error %d %d\n", err, errno);
 			assert(err == 0);
diff --git a/tools/testing/selftests/bpf/test_maps.h b/tools/testing/selftests/bpf/test_maps.h
index f6fbca7617..e4ac704a53 100644
--- a/tools/testing/selftests/bpf/test_maps.h
+++ b/tools/testing/selftests/bpf/test_maps.h
@@ -4,6 +4,7 @@
 
 #include <stdio.h>
 #include <stdlib.h>
+#include <stdbool.h>
 
 #define CHECK(condition, tag, format...) ({				\
 	int __ret = !!(condition);					\
@@ -16,4 +17,8 @@
 
 extern int skips;
 
+typedef bool (*retry_for_error_fn)(int err);
+int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts,
+			 retry_for_error_fn need_retry);
+
 #endif
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 40cba8d368..6157f884d0 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -169,12 +169,14 @@ def bpftool(args, JSON=True, ns="", fail=True, include_stderr=False):
     return tool("bpftool", args, {"json":"-p"}, JSON=JSON, ns=ns,
                 fail=fail, include_stderr=include_stderr)
 
-def bpftool_prog_list(expected=None, ns=""):
+def bpftool_prog_list(expected=None, ns="", exclude_orphaned=True):
     _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
     # Remove the base progs
     for p in base_progs:
         if p in progs:
             progs.remove(p)
+    if exclude_orphaned:
+        progs = [ p for p in progs if not p['orphaned'] ]
     if expected is not None:
         if len(progs) != expected:
             fail(True, "%d BPF programs loaded, expected %d" %
@@ -612,11 +614,9 @@ def pin_map(file_name, idx=0, expected=1):
 
 def check_dev_info_removed(prog_file=None, map_file=None):
     bpftool_prog_list(expected=0)
+    bpftool_prog_list(expected=1, exclude_orphaned=False)
     ret, err = bpftool("prog show pin %s" % (prog_file), fail=False)
-    fail(ret == 0, "Showing prog with removed device did not fail")
-    fail(err["error"].find("No such device") == -1,
-         "Showing prog with removed device expected ENODEV, error is %s" %
-         (err["error"]))
+    fail(ret != 0, "failed to show prog with removed device")
 
     bpftool_map_list(expected=0)
     ret, err = bpftool("map show pin %s" % (map_file), fail=False)
@@ -1395,10 +1395,7 @@ try:
 
     start_test("Test multi-dev ASIC cross-dev destruction - orphaned...")
     ret, out = bpftool("prog show %s" % (progB), fail=False)
-    fail(ret == 0, "got information about orphaned program")
-    fail("error" not in out, "no error reported for get info on orphaned")
-    fail(out["error"] != "can't get prog info: No such device",
-         "wrong error for get info on orphaned")
+    fail(ret != 0, "couldn't get information about orphaned program")
 
     print("%s: OK" % (os.path.basename(__file__)))
 
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index 2c89674fc6..b0068a9d2c 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -679,7 +679,7 @@ static int load_path(const struct sock_addr_test *test, const char *path)
 
 	bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR);
 	bpf_program__set_expected_attach_type(prog, test->expected_attach_type);
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
+	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS);
 
 	err = bpf_object__load(obj);
 	if (err) {
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh
index 2dec7dbf29..d9661b9988 100755
--- a/tools/testing/selftests/bpf/test_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tunnel.sh
@@ -517,90 +517,6 @@ test_ip6ip6()
         echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
 }
 
-setup_xfrm_tunnel()
-{
-	auth=0x$(printf '1%.0s' {1..40})
-	enc=0x$(printf '2%.0s' {1..32})
-	spi_in_to_out=0x1
-	spi_out_to_in=0x2
-	# at_ns0 namespace
-	# at_ns0 -> root
-	ip netns exec at_ns0 \
-		ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
-			spi $spi_in_to_out reqid 1 mode tunnel \
-			auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
-	ip netns exec at_ns0 \
-		ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \
-		tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
-		mode tunnel
-	# root -> at_ns0
-	ip netns exec at_ns0 \
-		ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
-			spi $spi_out_to_in reqid 2 mode tunnel \
-			auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
-	ip netns exec at_ns0 \
-		ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \
-		tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
-		mode tunnel
-	# address & route
-	ip netns exec at_ns0 \
-		ip addr add dev veth0 10.1.1.100/32
-	ip netns exec at_ns0 \
-		ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \
-			src 10.1.1.100
-
-	# root namespace
-	# at_ns0 -> root
-	ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
-		spi $spi_in_to_out reqid 1 mode tunnel \
-		auth-trunc 'hmac(sha1)' $auth 96  enc 'cbc(aes)' $enc
-	ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \
-		tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
-		mode tunnel
-	# root -> at_ns0
-	ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
-		spi $spi_out_to_in reqid 2 mode tunnel \
-		auth-trunc 'hmac(sha1)' $auth 96  enc 'cbc(aes)' $enc
-	ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \
-		tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
-		mode tunnel
-	# address & route
-	ip addr add dev veth1 10.1.1.200/32
-	ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200
-}
-
-test_xfrm_tunnel()
-{
-	if [[ -e /sys/kernel/tracing/trace ]]; then
-		TRACE=/sys/kernel/tracing/trace
-	else
-		TRACE=/sys/kernel/debug/tracing/trace
-	fi
-	config_device
-	> ${TRACE}
-	setup_xfrm_tunnel
-	mkdir -p ${BPF_PIN_TUNNEL_DIR}
-	bpftool prog loadall ${BPF_FILE} ${BPF_PIN_TUNNEL_DIR}
-	tc qdisc add dev veth1 clsact
-	tc filter add dev veth1 proto ip ingress bpf da object-pinned \
-		${BPF_PIN_TUNNEL_DIR}/xfrm_get_state
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	sleep 1
-	grep "reqid 1" ${TRACE}
-	check_err $?
-	grep "spi 0x1" ${TRACE}
-	check_err $?
-	grep "remote ip 0xac100164" ${TRACE}
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-		echo -e ${RED}"FAIL: xfrm tunnel"${NC}
-		return 1
-	fi
-	echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
-}
-
 attach_bpf()
 {
 	DEV=$1
@@ -630,10 +546,6 @@ cleanup()
 	ip link del ip6geneve11 2> /dev/null
 	ip link del erspan11 2> /dev/null
 	ip link del ip6erspan11 2> /dev/null
-	ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null
-	ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null
-	ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null
-	ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null
 }
 
 cleanup_exit()
@@ -716,10 +628,6 @@ bpf_tunnel_test()
 	test_ip6ip6
 	errors=$(( $errors + $? ))
 
-	echo "Testing IPSec tunnel..."
-	test_xfrm_tunnel
-	errors=$(( $errors + $? ))
-
 	return $errors
 }
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 98107e0452..f36e41435b 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1588,7 +1588,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	if (fixup_skips != skips)
 		return;
 
-	pflags = BPF_F_TEST_RND_HI32;
+	pflags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS;
 	if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
 		pflags |= BPF_F_STRICT_ALIGNMENT;
 	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index 8d994884c7..d2458c1b16 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -276,7 +276,7 @@ int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
 	if (type != BPF_PROG_TYPE_UNSPEC && bpf_program__type(prog) != type)
 		bpf_program__set_type(prog, type);
 
-	flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32;
+	flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS;
 	bpf_program__set_flags(prog, flags);
 
 	err = bpf_object__load(obj);
@@ -299,7 +299,7 @@ int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 {
 	LIBBPF_OPTS(bpf_prog_load_opts, opts,
 		.kern_version = kern_version,
-		.prog_flags = BPF_F_TEST_RND_HI32,
+		.prog_flags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS,
 		.log_level = extra_prog_load_log_flags,
 		.log_buf = log_buf,
 		.log_size = log_buf_sz,
diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h
index 5b7a551367..35284faff4 100644
--- a/tools/testing/selftests/bpf/testing_helpers.h
+++ b/tools/testing/selftests/bpf/testing_helpers.h
@@ -9,6 +9,9 @@
 #include <bpf/libbpf.h>
 #include <time.h>
 
+#define __TO_STR(x) #x
+#define TO_STR(x) __TO_STR(x)
+
 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);
 int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 0d84dd1f38..8a2ff81d83 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -140,10 +140,11 @@
 	.result = REJECT,
 },
 {
-	"precise: ST insn causing spi > allocated_stack",
+	"precise: ST zero to stack insn is supported",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0),
+	/* not a register spill, so we stop precision propagation for R4 here */
 	BPF_ST_MEM(BPF_DW, BPF_REG_3, -8, 0),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
 	BPF_MOV64_IMM(BPF_REG_0, -1),
@@ -157,11 +158,11 @@
 	mark_precise: frame0: last_idx 4 first_idx 2\
 	mark_precise: frame0: regs=r4 stack= before 4\
 	mark_precise: frame0: regs=r4 stack= before 3\
-	mark_precise: frame0: regs= stack=-8 before 2\
-	mark_precise: frame0: falling back to forcing all scalars precise\
-	force_precise: frame0: forcing r0 to be precise\
 	mark_precise: frame0: last_idx 5 first_idx 5\
-	mark_precise: frame0: parent state regs= stack=:",
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 4 first_idx 2\
+	mark_precise: frame0: regs=r0 stack= before 4\
+	5: R0=-1 R4=0",
 	.result = VERBOSE_ACCEPT,
 	.retval = -1,
 },
@@ -169,6 +170,8 @@
 	"precise: STX insn causing spi > allocated_stack",
 	.insns = {
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	/* make later reg spill more interesting by having somewhat known scalar */
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xff),
 	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0),
 	BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, -8),
@@ -179,18 +182,21 @@
 	},
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = BPF_F_TEST_STATE_FREQ,
-	.errstr = "mark_precise: frame0: last_idx 6 first_idx 6\
+	.errstr = "mark_precise: frame0: last_idx 7 first_idx 7\
 	mark_precise: frame0: parent state regs=r4 stack=:\
-	mark_precise: frame0: last_idx 5 first_idx 3\
-	mark_precise: frame0: regs=r4 stack= before 5\
-	mark_precise: frame0: regs=r4 stack= before 4\
-	mark_precise: frame0: regs= stack=-8 before 3\
-	mark_precise: frame0: falling back to forcing all scalars precise\
-	force_precise: frame0: forcing r0 to be precise\
-	force_precise: frame0: forcing r0 to be precise\
-	force_precise: frame0: forcing r0 to be precise\
-	force_precise: frame0: forcing r0 to be precise\
-	mark_precise: frame0: last_idx 6 first_idx 6\
+	mark_precise: frame0: last_idx 6 first_idx 4\
+	mark_precise: frame0: regs=r4 stack= before 6: (b7) r0 = -1\
+	mark_precise: frame0: regs=r4 stack= before 5: (79) r4 = *(u64 *)(r10 -8)\
+	mark_precise: frame0: regs= stack=-8 before 4: (7b) *(u64 *)(r3 -8) = r0\
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 3 first_idx 3\
+	mark_precise: frame0: regs=r0 stack= before 3: (55) if r3 != 0x7b goto pc+0\
+	mark_precise: frame0: regs=r0 stack= before 2: (bf) r3 = r10\
+	mark_precise: frame0: regs=r0 stack= before 1: (57) r0 &= 255\
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 0 first_idx 0\
+	mark_precise: frame0: regs=r0 stack= before 0: (85) call bpf_get_prandom_u32#7\
+	mark_precise: frame0: last_idx 7 first_idx 7\
 	mark_precise: frame0: parent state regs= stack=:",
 	.result = VERBOSE_ACCEPT,
 	.retval = -1,
diff --git a/tools/testing/selftests/bpf/verify_sig_setup.sh b/tools/testing/selftests/bpf/verify_sig_setup.sh
index ba08922b4a..f2cac42298 100755
--- a/tools/testing/selftests/bpf/verify_sig_setup.sh
+++ b/tools/testing/selftests/bpf/verify_sig_setup.sh
@@ -60,6 +60,27 @@ cleanup() {
 	rm -rf ${tmp_dir}
 }
 
+fsverity_create_sign_file() {
+	local tmp_dir="$1"
+
+	data_file=${tmp_dir}/data-file
+	sig_file=${tmp_dir}/sig-file
+	dd if=/dev/urandom of=$data_file bs=1 count=12345 2> /dev/null
+	fsverity sign --key ${tmp_dir}/signing_key.pem $data_file $sig_file
+
+	# We do not want to enable fsverity on $data_file yet. Try whether
+	# the file system support fsverity on a different file.
+	touch ${tmp_dir}/tmp-file
+	fsverity enable ${tmp_dir}/tmp-file
+}
+
+fsverity_enable_file() {
+	local tmp_dir="$1"
+
+	data_file=${tmp_dir}/data-file
+	fsverity enable $data_file
+}
+
 catch()
 {
 	local exit_code="$1"
@@ -86,6 +107,10 @@ main()
 		setup "${tmp_dir}"
 	elif [[ "${action}" == "cleanup" ]]; then
 		cleanup "${tmp_dir}"
+	elif [[ "${action}" == "fsverity-create-sign" ]]; then
+		fsverity_create_sign_file "${tmp_dir}"
+	elif [[ "${action}" == "fsverity-enable" ]]; then
+		fsverity_enable_file "${tmp_dir}"
 	else
 		echo "Unknown action: ${action}"
 		exit 1
diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index 0ad98b6a8e..244d4996e0 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -18,6 +18,7 @@
 #include <libelf.h>
 #include <gelf.h>
 #include <float.h>
+#include <math.h>
 
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
@@ -99,6 +100,7 @@ struct stat_specs {
 	enum stat_id ids[ALL_STATS_CNT];
 	enum stat_variant variants[ALL_STATS_CNT];
 	bool asc[ALL_STATS_CNT];
+	bool abs[ALL_STATS_CNT];
 	int lens[ALL_STATS_CNT * 3]; /* 3x for comparison mode */
 };
 
@@ -133,6 +135,7 @@ struct filter {
 	int stat_id;
 	enum stat_variant stat_var;
 	long value;
+	bool abs;
 };
 
 static struct env {
@@ -142,10 +145,12 @@ static struct env {
 	bool debug;
 	bool quiet;
 	bool force_checkpoints;
+	bool force_reg_invariants;
 	enum resfmt out_fmt;
 	bool show_version;
 	bool comparison_mode;
 	bool replay_mode;
+	int top_n;
 
 	int log_level;
 	int log_size;
@@ -210,8 +215,7 @@ static const struct argp_option opts[] = {
 	{ "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode)" },
 	{ "log-fixed", OPT_LOG_FIXED, NULL, 0, "Disable verifier log rotation" },
 	{ "log-size", OPT_LOG_SIZE, "BYTES", 0, "Customize verifier log size (default to 16MB)" },
-	{ "test-states", 't', NULL, 0,
-	  "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" },
+	{ "top-n", 'n', "N", 0, "Emit only up to first N results." },
 	{ "quiet", 'q', NULL, 0, "Quiet mode" },
 	{ "emit", 'e', "SPEC", 0, "Specify stats to be emitted" },
 	{ "sort", 's', "SPEC", 0, "Specify sort order" },
@@ -219,6 +223,10 @@ static const struct argp_option opts[] = {
 	{ "compare", 'C', NULL, 0, "Comparison mode" },
 	{ "replay", 'R', NULL, 0, "Replay mode" },
 	{ "filter", 'f', "FILTER", 0, "Filter expressions (or @filename for file with expressions)." },
+	{ "test-states", 't', NULL, 0,
+	  "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" },
+	{ "test-reg-invariants", 'r', NULL, 0,
+	  "Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" },
 	{},
 };
 
@@ -290,6 +298,16 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	case 't':
 		env.force_checkpoints = true;
 		break;
+	case 'r':
+		env.force_reg_invariants = true;
+		break;
+	case 'n':
+		errno = 0;
+		env.top_n = strtol(arg, NULL, 10);
+		if (errno) {
+			fprintf(stderr, "invalid top N specifier: %s\n", arg);
+			argp_usage(state);
+		}
 	case 'C':
 		env.comparison_mode = true;
 		break;
@@ -455,7 +473,8 @@ static struct {
 	{ OP_EQ, "=" },
 };
 
-static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_variant *var);
+static bool parse_stat_id_var(const char *name, size_t len, int *id,
+			      enum stat_variant *var, bool *is_abs);
 
 static int append_filter(struct filter **filters, int *cnt, const char *str)
 {
@@ -488,13 +507,14 @@ static int append_filter(struct filter **filters, int *cnt, const char *str)
 		long val;
 		const char *end = str;
 		const char *op_str;
+		bool is_abs;
 
 		op_str = operators[i].op_str;
 		p = strstr(str, op_str);
 		if (!p)
 			continue;
 
-		if (!parse_stat_id_var(str, p - str, &id, &var)) {
+		if (!parse_stat_id_var(str, p - str, &id, &var, &is_abs)) {
 			fprintf(stderr, "Unrecognized stat name in '%s'!\n", str);
 			return -EINVAL;
 		}
@@ -533,6 +553,7 @@ static int append_filter(struct filter **filters, int *cnt, const char *str)
 		f->stat_id = id;
 		f->stat_var = var;
 		f->op = operators[i].op_kind;
+		f->abs = true;
 		f->value = val;
 
 		*cnt += 1;
@@ -657,7 +678,8 @@ static struct stat_def {
 	[MARK_READ_MAX_LEN] = { "Max mark read length", {"max_mark_read_len", "mark_read"}, },
 };
 
-static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_variant *var)
+static bool parse_stat_id_var(const char *name, size_t len, int *id,
+			      enum stat_variant *var, bool *is_abs)
 {
 	static const char *var_sfxs[] = {
 		[VARIANT_A] = "_a",
@@ -667,6 +689,14 @@ static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_v
 	};
 	int i, j, k;
 
+	/* |<stat>| means we take absolute value of given stat */
+	*is_abs = false;
+	if (len > 2 && name[0] == '|' && name[len - 1] == '|') {
+		*is_abs = true;
+		name += 1;
+		len -= 2;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(stat_defs); i++) {
 		struct stat_def *def = &stat_defs[i];
 		size_t alias_len, sfx_len;
@@ -722,7 +752,7 @@ static bool is_desc_sym(char c)
 static int parse_stat(const char *stat_name, struct stat_specs *specs)
 {
 	int id;
-	bool has_order = false, is_asc = false;
+	bool has_order = false, is_asc = false, is_abs = false;
 	size_t len = strlen(stat_name);
 	enum stat_variant var;
 
@@ -737,7 +767,7 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs)
 		len -= 1;
 	}
 
-	if (!parse_stat_id_var(stat_name, len, &id, &var)) {
+	if (!parse_stat_id_var(stat_name, len, &id, &var, &is_abs)) {
 		fprintf(stderr, "Unrecognized stat name '%s'\n", stat_name);
 		return -ESRCH;
 	}
@@ -745,6 +775,7 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs)
 	specs->ids[specs->spec_cnt] = id;
 	specs->variants[specs->spec_cnt] = var;
 	specs->asc[specs->spec_cnt] = has_order ? is_asc : stat_defs[id].asc_by_default;
+	specs->abs[specs->spec_cnt] = is_abs;
 	specs->spec_cnt++;
 
 	return 0;
@@ -997,6 +1028,8 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
 
 	if (env.force_checkpoints)
 		bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_STATE_FREQ);
+	if (env.force_reg_invariants)
+		bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_REG_INVARIANTS);
 
 	err = bpf_object__load(obj);
 	env.progs_processed++;
@@ -1103,7 +1136,7 @@ cleanup:
 }
 
 static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2,
-		    enum stat_id id, bool asc)
+		    enum stat_id id, bool asc, bool abs)
 {
 	int cmp = 0;
 
@@ -1124,6 +1157,11 @@ static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2,
 		long v1 = s1->stats[id];
 		long v2 = s2->stats[id];
 
+		if (abs) {
+			v1 = v1 < 0 ? -v1 : v1;
+			v2 = v2 < 0 ? -v2 : v2;
+		}
+
 		if (v1 != v2)
 			cmp = v1 < v2 ? -1 : 1;
 		break;
@@ -1142,7 +1180,8 @@ static int cmp_prog_stats(const void *v1, const void *v2)
 	int i, cmp;
 
 	for (i = 0; i < env.sort_spec.spec_cnt; i++) {
-		cmp = cmp_stat(s1, s2, env.sort_spec.ids[i], env.sort_spec.asc[i]);
+		cmp = cmp_stat(s1, s2, env.sort_spec.ids[i],
+			       env.sort_spec.asc[i], env.sort_spec.abs[i]);
 		if (cmp != 0)
 			return cmp;
 	}
@@ -1211,7 +1250,8 @@ static void fetch_join_stat_value(const struct verif_stats_join *s,
 
 static int cmp_join_stat(const struct verif_stats_join *s1,
 			 const struct verif_stats_join *s2,
-			 enum stat_id id, enum stat_variant var, bool asc)
+			 enum stat_id id, enum stat_variant var,
+			 bool asc, bool abs)
 {
 	const char *str1 = NULL, *str2 = NULL;
 	double v1 = 0.0, v2 = 0.0;
@@ -1220,6 +1260,11 @@ static int cmp_join_stat(const struct verif_stats_join *s1,
 	fetch_join_stat_value(s1, id, var, &str1, &v1);
 	fetch_join_stat_value(s2, id, var, &str2, &v2);
 
+	if (abs) {
+		v1 = fabs(v1);
+		v2 = fabs(v2);
+	}
+
 	if (str1)
 		cmp = strcmp(str1, str2);
 	else if (v1 != v2)
@@ -1237,7 +1282,8 @@ static int cmp_join_stats(const void *v1, const void *v2)
 		cmp = cmp_join_stat(s1, s2,
 				    env.sort_spec.ids[i],
 				    env.sort_spec.variants[i],
-				    env.sort_spec.asc[i]);
+				    env.sort_spec.asc[i],
+				    env.sort_spec.abs[i]);
 		if (cmp != 0)
 			return cmp;
 	}
@@ -1720,6 +1766,9 @@ static bool is_join_stat_filter_matched(struct filter *f, const struct verif_sta
 
 	fetch_join_stat_value(stats, f->stat_id, f->stat_var, &str, &value);
 
+	if (f->abs)
+		value = fabs(value);
+
 	switch (f->op) {
 	case OP_EQ: return value > f->value - eps && value < f->value + eps;
 	case OP_NEQ: return value < f->value - eps || value > f->value + eps;
@@ -1766,7 +1815,7 @@ static int handle_comparison_mode(void)
 	struct stat_specs base_specs = {}, comp_specs = {};
 	struct stat_specs tmp_sort_spec;
 	enum resfmt cur_fmt;
-	int err, i, j, last_idx;
+	int err, i, j, last_idx, cnt;
 
 	if (env.filename_cnt != 2) {
 		fprintf(stderr, "Comparison mode expects exactly two input CSV files!\n\n");
@@ -1879,7 +1928,7 @@ static int handle_comparison_mode(void)
 		env.join_stat_cnt += 1;
 	}
 
-	/* now sort joined results accorsing to sort spec */
+	/* now sort joined results according to sort spec */
 	qsort(env.join_stats, env.join_stat_cnt, sizeof(*env.join_stats), cmp_join_stats);
 
 	/* for human-readable table output we need to do extra pass to
@@ -1896,16 +1945,22 @@ one_more_time:
 	output_comp_headers(cur_fmt);
 
 	last_idx = -1;
+	cnt = 0;
 	for (i = 0; i < env.join_stat_cnt; i++) {
 		const struct verif_stats_join *join = &env.join_stats[i];
 
 		if (!should_output_join_stats(join))
 			continue;
 
+		if (env.top_n && cnt >= env.top_n)
+			break;
+
 		if (cur_fmt == RESFMT_TABLE_CALCLEN)
 			last_idx = i;
 
 		output_comp_stats(join, cur_fmt, i == last_idx);
+
+		cnt++;
 	}
 
 	if (cur_fmt == RESFMT_TABLE_CALCLEN) {
@@ -1920,6 +1975,9 @@ static bool is_stat_filter_matched(struct filter *f, const struct verif_stats *s
 {
 	long value = stats->stats[f->stat_id];
 
+	if (f->abs)
+		value = value < 0 ? -value : value;
+
 	switch (f->op) {
 	case OP_EQ: return value == f->value;
 	case OP_NEQ: return value != f->value;
@@ -1964,7 +2022,7 @@ static bool should_output_stats(const struct verif_stats *stats)
 static void output_prog_stats(void)
 {
 	const struct verif_stats *stats;
-	int i, last_stat_idx = 0;
+	int i, last_stat_idx = 0, cnt = 0;
 
 	if (env.out_fmt == RESFMT_TABLE) {
 		/* calculate column widths */
@@ -1984,7 +2042,10 @@ static void output_prog_stats(void)
 		stats = &env.prog_stats[i];
 		if (!should_output_stats(stats))
 			continue;
+		if (env.top_n && cnt >= env.top_n)
+			break;
 		output_stats(stats, env.out_fmt, i == last_stat_idx);
+		cnt++;
 	}
 }
 
diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 6850345280..65d14f3bbe 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -36,7 +36,9 @@ DEFAULT_COMMAND="./test_progs"
 MOUNT_DIR="mnt"
 ROOTFS_IMAGE="root.img"
 OUTPUT_DIR="$HOME/.bpf_selftests"
-KCONFIG_REL_PATHS=("tools/testing/selftests/bpf/config" "tools/testing/selftests/bpf/config.${ARCH}")
+KCONFIG_REL_PATHS=("tools/testing/selftests/bpf/config"
+	"tools/testing/selftests/bpf/config.vm"
+	"tools/testing/selftests/bpf/config.${ARCH}")
 INDEX_URL="https://raw.githubusercontent.com/libbpf/ci/master/INDEX"
 NUM_COMPILE_JOBS="$(nproc)"
 LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")"
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index c5e7937d7f..878d68db03 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -10,7 +10,9 @@
  *   - rx_hash
  *
  * TX:
- * - TBD
+ * - UDP 9091 packets trigger TX reply
+ * - TX HW timestamp is requested and reported back upon completion
+ * - TX checksum is requested
  */
 
 #include <test_progs.h>
@@ -19,20 +21,26 @@
 #include "xsk.h"
 
 #include <error.h>
+#include <linux/kernel.h>
+#include <linux/bits.h>
+#include <linux/bitfield.h>
 #include <linux/errqueue.h>
 #include <linux/if_link.h>
 #include <linux/net_tstamp.h>
 #include <linux/udp.h>
 #include <linux/sockios.h>
+#include <linux/if_xdp.h>
 #include <sys/mman.h>
 #include <net/if.h>
 #include <ctype.h>
 #include <poll.h>
 #include <time.h>
+#include <unistd.h>
+#include <libgen.h>
 
 #include "xdp_metadata.h"
 
-#define UMEM_NUM 16
+#define UMEM_NUM 256
 #define UMEM_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE
 #define UMEM_SIZE (UMEM_FRAME_SIZE * UMEM_NUM)
 #define XDP_FLAGS (XDP_FLAGS_DRV_MODE | XDP_FLAGS_REPLACE)
@@ -48,11 +56,14 @@ struct xsk {
 };
 
 struct xdp_hw_metadata *bpf_obj;
-__u16 bind_flags = XDP_COPY;
+__u16 bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY;
 struct xsk *rx_xsk;
 const char *ifname;
 int ifindex;
 int rxq;
+bool skip_tx;
+__u64 last_hw_rx_timestamp;
+__u64 last_xdp_rx_timestamp;
 
 void test__fail(void) { /* for network_helpers.c */ }
 
@@ -68,7 +79,8 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
-		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG,
+		.flags = XSK_UMEM__DEFAULT_FLAGS,
+		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
 	};
 	__u32 idx = 0;
 	u64 addr;
@@ -110,7 +122,7 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
 	for (i = 0; i < UMEM_NUM / 2; i++) {
 		addr = (UMEM_NUM / 2 + i) * UMEM_FRAME_SIZE;
 		printf("%p: rx_desc[%d] -> %lx\n", xsk, i, addr);
-		*xsk_ring_prod__fill_addr(&xsk->fill, i) = addr;
+		*xsk_ring_prod__fill_addr(&xsk->fill, idx + i) = addr;
 	}
 	xsk_ring_prod__submit(&xsk->fill, ret);
 
@@ -131,12 +143,22 @@ static void refill_rx(struct xsk *xsk, __u64 addr)
 	__u32 idx;
 
 	if (xsk_ring_prod__reserve(&xsk->fill, 1, &idx) == 1) {
-		printf("%p: complete idx=%u addr=%llx\n", xsk, idx, addr);
+		printf("%p: complete rx idx=%u addr=%llx\n", xsk, idx, addr);
 		*xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr;
 		xsk_ring_prod__submit(&xsk->fill, 1);
 	}
 }
 
+static int kick_tx(struct xsk *xsk)
+{
+	return sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
+}
+
+static int kick_rx(struct xsk *xsk)
+{
+	return recvfrom(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, NULL);
+}
+
 #define NANOSEC_PER_SEC 1000000000 /* 10^9 */
 static __u64 gettime(clockid_t clock_id)
 {
@@ -152,37 +174,64 @@ static __u64 gettime(clockid_t clock_id)
 	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
 }
 
+static void print_tstamp_delta(const char *name, const char *refname,
+			       __u64 tstamp, __u64 reference)
+{
+	__s64 delta = (__s64)reference - (__s64)tstamp;
+
+	printf("%s:   %llu (sec:%0.4f) delta to %s sec:%0.4f (%0.3f usec)\n",
+	       name, tstamp, (double)tstamp / NANOSEC_PER_SEC, refname,
+	       (double)delta / NANOSEC_PER_SEC,
+	       (double)delta / 1000);
+}
+
+#define VLAN_PRIO_MASK		GENMASK(15, 13) /* Priority Code Point */
+#define VLAN_DEI_MASK		GENMASK(12, 12) /* Drop Eligible Indicator */
+#define VLAN_VID_MASK		GENMASK(11, 0)	/* VLAN Identifier */
+static void print_vlan_tci(__u16 tag)
+{
+	__u16 vlan_id = FIELD_GET(VLAN_VID_MASK, tag);
+	__u8 pcp = FIELD_GET(VLAN_PRIO_MASK, tag);
+	bool dei = FIELD_GET(VLAN_DEI_MASK, tag);
+
+	printf("PCP=%u, DEI=%d, VID=0x%X\n", pcp, dei, vlan_id);
+}
+
 static void verify_xdp_metadata(void *data, clockid_t clock_id)
 {
 	struct xdp_meta *meta;
 
 	meta = data - sizeof(*meta);
 
-	if (meta->rx_hash_err < 0)
-		printf("No rx_hash err=%d\n", meta->rx_hash_err);
-	else
+	if (meta->hint_valid & XDP_META_FIELD_RSS)
 		printf("rx_hash: 0x%X with RSS type:0x%X\n",
 		       meta->rx_hash, meta->rx_hash_type);
+	else
+		printf("No rx_hash, err=%d\n", meta->rx_hash_err);
+
+	if (meta->hint_valid & XDP_META_FIELD_TS) {
+		__u64 ref_tstamp = gettime(clock_id);
 
-	printf("rx_timestamp:  %llu (sec:%0.4f)\n", meta->rx_timestamp,
-	       (double)meta->rx_timestamp / NANOSEC_PER_SEC);
-	if (meta->rx_timestamp) {
-		__u64 usr_clock = gettime(clock_id);
-		__u64 xdp_clock = meta->xdp_timestamp;
-		__s64 delta_X = xdp_clock - meta->rx_timestamp;
-		__s64 delta_X2U = usr_clock - xdp_clock;
-
-		printf("XDP RX-time:   %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n",
-		       xdp_clock, (double)xdp_clock / NANOSEC_PER_SEC,
-		       (double)delta_X / NANOSEC_PER_SEC,
-		       (double)delta_X / 1000);
-
-		printf("AF_XDP time:   %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n",
-		       usr_clock, (double)usr_clock / NANOSEC_PER_SEC,
-		       (double)delta_X2U / NANOSEC_PER_SEC,
-		       (double)delta_X2U / 1000);
+		/* store received timestamps to calculate a delta at tx */
+		last_hw_rx_timestamp = meta->rx_timestamp;
+		last_xdp_rx_timestamp = meta->xdp_timestamp;
+
+		print_tstamp_delta("HW RX-time", "User RX-time",
+				   meta->rx_timestamp, ref_tstamp);
+		print_tstamp_delta("XDP RX-time", "User RX-time",
+				   meta->xdp_timestamp, ref_tstamp);
+	} else {
+		printf("No rx_timestamp, err=%d\n", meta->rx_timestamp_err);
 	}
 
+	if (meta->hint_valid & XDP_META_FIELD_VLAN_TAG) {
+		printf("rx_vlan_proto: 0x%X\n", ntohs(meta->rx_vlan_proto));
+		printf("rx_vlan_tci: ");
+		print_vlan_tci(meta->rx_vlan_tci);
+	} else {
+		printf("No rx_vlan_tci or rx_vlan_proto, err=%d\n",
+		       meta->rx_vlan_tag_err);
+	}
 }
 
 static void verify_skb_metadata(int fd)
@@ -230,6 +279,129 @@ static void verify_skb_metadata(int fd)
 	printf("skb hwtstamp is not found!\n");
 }
 
+static bool complete_tx(struct xsk *xsk, clockid_t clock_id)
+{
+	struct xsk_tx_metadata *meta;
+	__u64 addr;
+	void *data;
+	__u32 idx;
+
+	if (!xsk_ring_cons__peek(&xsk->comp, 1, &idx))
+		return false;
+
+	addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
+	data = xsk_umem__get_data(xsk->umem_area, addr);
+	meta = data - sizeof(struct xsk_tx_metadata);
+
+	printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr);
+
+	if (meta->completion.tx_timestamp) {
+		__u64 ref_tstamp = gettime(clock_id);
+
+		print_tstamp_delta("HW TX-complete-time", "User TX-complete-time",
+				   meta->completion.tx_timestamp, ref_tstamp);
+		print_tstamp_delta("XDP RX-time", "User TX-complete-time",
+				   last_xdp_rx_timestamp, ref_tstamp);
+		print_tstamp_delta("HW RX-time", "HW TX-complete-time",
+				   last_hw_rx_timestamp, meta->completion.tx_timestamp);
+	} else {
+		printf("No tx_timestamp\n");
+	}
+
+	xsk_ring_cons__release(&xsk->comp, 1);
+
+	return true;
+}
+
+#define swap(a, b, len) do { \
+	for (int i = 0; i < len; i++) { \
+		__u8 tmp = ((__u8 *)a)[i]; \
+		((__u8 *)a)[i] = ((__u8 *)b)[i]; \
+		((__u8 *)b)[i] = tmp; \
+	} \
+} while (0)
+
+static void ping_pong(struct xsk *xsk, void *rx_packet, clockid_t clock_id)
+{
+	struct xsk_tx_metadata *meta;
+	struct ipv6hdr *ip6h = NULL;
+	struct iphdr *iph = NULL;
+	struct xdp_desc *tx_desc;
+	struct udphdr *udph;
+	struct ethhdr *eth;
+	__sum16 want_csum;
+	void *data;
+	__u32 idx;
+	int ret;
+	int len;
+
+	ret = xsk_ring_prod__reserve(&xsk->tx, 1, &idx);
+	if (ret != 1) {
+		printf("%p: failed to reserve tx slot\n", xsk);
+		return;
+	}
+
+	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
+	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE + sizeof(struct xsk_tx_metadata);
+	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
+
+	meta = data - sizeof(struct xsk_tx_metadata);
+	memset(meta, 0, sizeof(*meta));
+	meta->flags = XDP_TXMD_FLAGS_TIMESTAMP;
+
+	eth = rx_packet;
+
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		iph = (void *)(eth + 1);
+		udph = (void *)(iph + 1);
+	} else if (eth->h_proto == htons(ETH_P_IPV6)) {
+		ip6h = (void *)(eth + 1);
+		udph = (void *)(ip6h + 1);
+	} else {
+		printf("%p: failed to detect IP version for ping pong %04x\n", xsk, eth->h_proto);
+		xsk_ring_prod__cancel(&xsk->tx, 1);
+		return;
+	}
+
+	len = ETH_HLEN;
+	if (ip6h)
+		len += sizeof(*ip6h) + ntohs(ip6h->payload_len);
+	if (iph)
+		len += ntohs(iph->tot_len);
+
+	swap(eth->h_dest, eth->h_source, ETH_ALEN);
+	if (iph)
+		swap(&iph->saddr, &iph->daddr, 4);
+	else
+		swap(&ip6h->saddr, &ip6h->daddr, 16);
+	swap(&udph->source, &udph->dest, 2);
+
+	want_csum = udph->check;
+	if (ip6h)
+		udph->check = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+					       ntohs(udph->len), IPPROTO_UDP, 0);
+	else
+		udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+						 ntohs(udph->len), IPPROTO_UDP, 0);
+
+	meta->flags |= XDP_TXMD_FLAGS_CHECKSUM;
+	if (iph)
+		meta->request.csum_start = sizeof(*eth) + sizeof(*iph);
+	else
+		meta->request.csum_start = sizeof(*eth) + sizeof(*ip6h);
+	meta->request.csum_offset = offsetof(struct udphdr, check);
+
+	printf("%p: ping-pong with csum=%04x (want %04x) csum_start=%d csum_offset=%d\n",
+	       xsk, ntohs(udph->check), ntohs(want_csum),
+	       meta->request.csum_start, meta->request.csum_offset);
+
+	memcpy(data, rx_packet, len); /* don't share umem chunk for simplicity */
+	tx_desc->options |= XDP_TX_METADATA;
+	tx_desc->len = len;
+
+	xsk_ring_prod__submit(&xsk->tx, 1);
+}
+
 static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id)
 {
 	const struct xdp_desc *rx_desc;
@@ -252,6 +424,13 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 
 	while (true) {
 		errno = 0;
+
+		for (i = 0; i < rxq; i++) {
+			ret = kick_rx(&rx_xsk[i]);
+			if (ret)
+				printf("kick_rx ret=%d\n", ret);
+		}
+
 		ret = poll(fds, rxq + 1, 1000);
 		printf("poll: %d (%d) skip=%llu fail=%llu redir=%llu\n",
 		       ret, errno, bpf_obj->bss->pkts_skip,
@@ -288,6 +467,22 @@ peek:
 				verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr),
 						    clock_id);
 				first_seg = false;
+
+				if (!skip_tx) {
+					/* mirror first chunk back */
+					ping_pong(xsk, xsk_umem__get_data(xsk->umem_area, addr),
+						  clock_id);
+
+					ret = kick_tx(xsk);
+					if (ret)
+						printf("kick_tx ret=%d\n", ret);
+
+					for (int j = 0; j < 500; j++) {
+						if (complete_tx(xsk, clock_id))
+							break;
+						usleep(10*1000);
+					}
+				}
 			}
 
 			xsk_ring_cons__release(&xsk->rx, 1);
@@ -420,8 +615,10 @@ static void print_usage(void)
 {
 	const char *usage =
 		"Usage: xdp_hw_metadata [OPTIONS] [IFNAME]\n"
-		"  -m    Enable multi-buffer XDP for larger MTU\n"
+		"  -c    Run in copy mode (zerocopy is default)\n"
 		"  -h    Display this help and exit\n\n"
+		"  -m    Enable multi-buffer XDP for larger MTU\n"
+		"  -r    Don't generate AF_XDP reply (rx metadata only)\n"
 		"Generate test packets on the other machine with:\n"
 		"  echo -n xdp | nc -u -q1 <dst_ip> 9091\n";
 
@@ -432,14 +629,22 @@ static void read_args(int argc, char *argv[])
 {
 	int opt;
 
-	while ((opt = getopt(argc, argv, "mh")) != -1) {
+	while ((opt = getopt(argc, argv, "chmr")) != -1) {
 		switch (opt) {
-		case 'm':
-			bind_flags |= XDP_USE_SG;
+		case 'c':
+			bind_flags &= ~XDP_USE_NEED_WAKEUP;
+			bind_flags &= ~XDP_ZEROCOPY;
+			bind_flags |= XDP_COPY;
 			break;
 		case 'h':
 			print_usage();
 			exit(0);
+		case 'm':
+			bind_flags |= XDP_USE_SG;
+			break;
+		case 'r':
+			skip_tx = true;
+			break;
 		case '?':
 			if (isprint(optopt))
 				fprintf(stderr, "Unknown option: -%c\n", optopt);
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
index 938a729bd3..87318ad111 100644
--- a/tools/testing/selftests/bpf/xdp_metadata.h
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -9,12 +9,44 @@
 #define ETH_P_IPV6 0x86DD
 #endif
 
+#ifndef ETH_P_8021Q
+#define ETH_P_8021Q 0x8100
+#endif
+
+#ifndef ETH_P_8021AD
+#define ETH_P_8021AD 0x88A8
+#endif
+
+#ifndef BIT
+#define BIT(nr)			(1 << (nr))
+#endif
+
+/* Non-existent checksum status */
+#define XDP_CHECKSUM_MAGIC	BIT(2)
+
+enum xdp_meta_field {
+	XDP_META_FIELD_TS	= BIT(0),
+	XDP_META_FIELD_RSS	= BIT(1),
+	XDP_META_FIELD_VLAN_TAG	= BIT(2),
+};
+
 struct xdp_meta {
-	__u64 rx_timestamp;
+	union {
+		__u64 rx_timestamp;
+		__s32 rx_timestamp_err;
+	};
 	__u64 xdp_timestamp;
 	__u32 rx_hash;
 	union {
 		__u32 rx_hash_type;
 		__s32 rx_hash_err;
 	};
+	union {
+		struct {
+			__be16 rx_vlan_proto;
+			__u16 rx_vlan_tci;
+		};
+		__s32 rx_vlan_tag_err;
+	};
+	enum xdp_meta_field hint_valid;
 };
diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c
index e574711eeb..25d568abf0 100644
--- a/tools/testing/selftests/bpf/xsk.c
+++ b/tools/testing/selftests/bpf/xsk.c
@@ -115,6 +115,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
 		cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 		cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
 		cfg->flags = XSK_UMEM__DEFAULT_FLAGS;
+		cfg->tx_metadata_len = 0;
 		return;
 	}
 
@@ -123,6 +124,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
 	cfg->frame_size = usr_cfg->frame_size;
 	cfg->frame_headroom = usr_cfg->frame_headroom;
 	cfg->flags = usr_cfg->flags;
+	cfg->tx_metadata_len = usr_cfg->tx_metadata_len;
 }
 
 static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
@@ -252,6 +254,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area,
 	mr.chunk_size = umem->config.frame_size;
 	mr.headroom = umem->config.frame_headroom;
 	mr.flags = umem->config.flags;
+	mr.tx_metadata_len = umem->config.tx_metadata_len;
 
 	err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr));
 	if (err) {
diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h
index 771570bc37..93c2cc413c 100644
--- a/tools/testing/selftests/bpf/xsk.h
+++ b/tools/testing/selftests/bpf/xsk.h
@@ -200,6 +200,7 @@ struct xsk_umem_config {
 	__u32 frame_size;
 	__u32 frame_headroom;
 	__u32 flags;
+	__u32 tx_metadata_len;
 };
 
 int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags);