Merge tag 'bpf-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:
 "For this merge window we're splitting BPF pull request into three for
  higher visibility: main changes, res_spin_lock, try_alloc_pages.

  These are the main BPF changes:

   - Add DFA-based live registers analysis to improve verification of
     programs with loops (Eduard Zingerman)

   - Introduce load_acquire and store_release BPF instructions and add
     x86, arm64 JIT support (Peilin Ye)

   - Fix loop detection logic in the verifier (Eduard Zingerman)

   - Drop unnecesary lock in bpf_map_inc_not_zero() (Eric Dumazet)

   - Add kfunc for populating cpumask bits (Emil Tsalapatis)

   - Convert various shell based tests to selftests/bpf/test_progs
     format (Bastien Curutchet)

   - Allow passing referenced kptrs into struct_ops callbacks (Amery
     Hung)

   - Add a flag to LSM bpf hook to facilitate bpf program signing
     (Blaise Boscaccy)

   - Track arena arguments in kfuncs (Ihor Solodrai)

   - Add copy_remote_vm_str() helper for reading strings from remote VM
     and bpf_copy_from_user_task_str() kfunc (Jordan Rome)

   - Add support for timed may_goto instruction (Kumar Kartikeya
     Dwivedi)

   - Allow bpf_get_netns_cookie() int cgroup_skb programs (Mahe Tardy)

   - Reduce bpf_cgrp_storage_busy false positives when accessing cgroup
     local storage (Martin KaFai Lau)

   - Introduce bpf_dynptr_copy() kfunc (Mykyta Yatsenko)

   - Allow retrieving BTF data with BTF token (Mykyta Yatsenko)

   - Add BPF kfuncs to set and get xattrs with 'security.bpf.' prefix
     (Song Liu)

   - Reject attaching programs to noreturn functions (Yafang Shao)

   - Introduce pre-order traversal of cgroup bpf programs (Yonghong
     Song)"

* tag 'bpf-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (186 commits)
  selftests/bpf: Add selftests for load-acquire/store-release when register number is invalid
  bpf: Fix out-of-bounds read in check_atomic_load/store()
  libbpf: Add namespace for errstr making it libbpf_errstr
  bpf: Add struct_ops context information to struct bpf_prog_aux
  selftests/bpf: Sanitize pointer prior fclose()
  selftests/bpf: Migrate test_xdp_vlan.sh into test_progs
  selftests/bpf: test_xdp_vlan: Rename BPF sections
  bpf: clarify a misleading verifier error message
  selftests/bpf: Add selftest for attaching fexit to __noreturn functions
  bpf: Reject attaching fexit/fmod_ret to __noreturn functions
  bpf: Only fails the busy counter check in bpf_cgrp_storage_get if it creates storage
  bpf: Make perf_event_read_output accessible in all program types.
  bpftool: Using the right format specifiers
  bpftool: Add -Wformat-signedness flag to detect format errors
  selftests/bpf: Test freplace from user namespace
  libbpf: Pass BPF token from find_prog_btf_id to BPF_BTF_GET_FD_BY_ID
  bpf: Return prog btf_id without capable check
  bpf: BPF token support for BPF_BTF_GET_FD_BY_ID
  bpf, x86: Fix objtool warning for timed may_goto
  bpf: Check map->record at the beginning of check_and_free_fields()
  ...

16 files changed, 1606 insertions, 458 deletions

diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 095a9554e1de..647b709d7d77 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -577,8 +577,8 @@ __bpf_kfunc void bpf_arena_free_pages(void *p__map, void *ptr__ign, u32 page_cnt
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(arena_kfuncs)
-BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE)
-BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE | KF_ARENA_RET | KF_ARENA_ARG2)
+BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE | KF_ARENA_ARG2)
 BTF_KFUNCS_END(arena_kfuncs)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {
diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c
index 54ff2a85d4c0..148da8f7ff36 100644
--- a/kernel/bpf/bpf_cgrp_storage.c
+++ b/kernel/bpf/bpf_cgrp_storage.c
@@ -161,6 +161,7 @@ BPF_CALL_5(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup,
 	   void *, value, u64, flags, gfp_t, gfp_flags)
 {
 	struct bpf_local_storage_data *sdata;
+	bool nobusy;
 
 	WARN_ON_ONCE(!bpf_rcu_lock_held());
 	if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
@@ -169,21 +170,21 @@ BPF_CALL_5(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup,
 	if (!cgroup)
 		return (unsigned long)NULL;
 
-	if (!bpf_cgrp_storage_trylock())
-		return (unsigned long)NULL;
+	nobusy = bpf_cgrp_storage_trylock();
 
-	sdata = cgroup_storage_lookup(cgroup, map, true);
+	sdata = cgroup_storage_lookup(cgroup, map, nobusy);
 	if (sdata)
 		goto unlock;
 
 	/* only allocate new storage, when the cgroup is refcounted */
 	if (!percpu_ref_is_dying(&cgroup->self.refcnt) &&
-	    (flags & BPF_LOCAL_STORAGE_GET_F_CREATE))
+	    (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) && nobusy)
 		sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map,
 						 value, BPF_NOEXIST, false, gfp_flags);
 
 unlock:
-	bpf_cgrp_storage_unlock();
+	if (nobusy)
+		bpf_cgrp_storage_unlock();
 	return IS_ERR_OR_NULL(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data;
 }
 
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 106735145948..380e9a7cac75 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -335,7 +335,7 @@ static void cache_btf_id(struct bpf_iter_target_info *tinfo,
 	tinfo->btf_id = prog->aux->attach_btf_id;
 }
 
-bool bpf_iter_prog_supported(struct bpf_prog *prog)
+int bpf_iter_prog_supported(struct bpf_prog *prog)
 {
 	const char *attach_fname = prog->aux->attach_func_name;
 	struct bpf_iter_target_info *tinfo = NULL, *iter;
@@ -344,7 +344,7 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog)
 	int prefix_len = strlen(prefix);
 
 	if (strncmp(attach_fname, prefix, prefix_len))
-		return false;
+		return -EINVAL;
 
 	mutex_lock(&targets_mutex);
 	list_for_each_entry(iter, &targets, list) {
@@ -360,12 +360,11 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog)
 	}
 	mutex_unlock(&targets_mutex);
 
-	if (tinfo) {
-		prog->aux->ctx_arg_info_size = tinfo->reg_info->ctx_arg_info_size;
-		prog->aux->ctx_arg_info = tinfo->reg_info->ctx_arg_info;
-	}
+	if (!tinfo)
+		return -EINVAL;
 
-	return tinfo != NULL;
+	return bpf_prog_ctx_arg_info_init(prog, tinfo->reg_info->ctx_arg_info,
+					  tinfo->reg_info->ctx_arg_info_size);
 }
 
 const struct bpf_func_proto *
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 967492b65185..0a59df1c550a 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -316,7 +316,9 @@ BTF_ID(func, bpf_lsm_inode_getxattr)
 BTF_ID(func, bpf_lsm_inode_mknod)
 BTF_ID(func, bpf_lsm_inode_need_killpriv)
 BTF_ID(func, bpf_lsm_inode_post_setxattr)
+BTF_ID(func, bpf_lsm_inode_post_removexattr)
 BTF_ID(func, bpf_lsm_inode_readlink)
+BTF_ID(func, bpf_lsm_inode_removexattr)
 BTF_ID(func, bpf_lsm_inode_rename)
 BTF_ID(func, bpf_lsm_inode_rmdir)
 BTF_ID(func, bpf_lsm_inode_setattr)
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 040fb1cd840b..db13ee70d94d 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -146,39 +146,7 @@ void bpf_struct_ops_image_free(void *image)
 }
 
 #define MAYBE_NULL_SUFFIX "__nullable"
-#define MAX_STUB_NAME 128
-
-/* Return the type info of a stub function, if it exists.
- *
- * The name of a stub function is made up of the name of the struct_ops and
- * the name of the function pointer member, separated by "__". For example,
- * if the struct_ops type is named "foo_ops" and the function pointer
- * member is named "bar", the stub function name would be "foo_ops__bar".
- */
-static const struct btf_type *
-find_stub_func_proto(const struct btf *btf, const char *st_op_name,
-		     const char *member_name)
-{
-	char stub_func_name[MAX_STUB_NAME];
-	const struct btf_type *func_type;
-	s32 btf_id;
-	int cp;
-
-	cp = snprintf(stub_func_name, MAX_STUB_NAME, "%s__%s",
-		      st_op_name, member_name);
-	if (cp >= MAX_STUB_NAME) {
-		pr_warn("Stub function name too long\n");
-		return NULL;
-	}
-	btf_id = btf_find_by_name_kind(btf, stub_func_name, BTF_KIND_FUNC);
-	if (btf_id < 0)
-		return NULL;
-	func_type = btf_type_by_id(btf, btf_id);
-	if (!func_type)
-		return NULL;
-
-	return btf_type_by_id(btf, func_type->type); /* FUNC_PROTO */
-}
+#define REFCOUNTED_SUFFIX "__ref"
 
 /* Prepare argument info for every nullable argument of a member of a
  * struct_ops type.
@@ -203,27 +171,44 @@ find_stub_func_proto(const struct btf *btf, const char *st_op_name,
 static int prepare_arg_info(struct btf *btf,
 			    const char *st_ops_name,
 			    const char *member_name,
-			    const struct btf_type *func_proto,
+			    const struct btf_type *func_proto, void *stub_func_addr,
 			    struct bpf_struct_ops_arg_info *arg_info)
 {
 	const struct btf_type *stub_func_proto, *pointed_type;
+	bool is_nullable = false, is_refcounted = false;
 	const struct btf_param *stub_args, *args;
 	struct bpf_ctx_arg_aux *info, *info_buf;
 	u32 nargs, arg_no, info_cnt = 0;
+	char ksym[KSYM_SYMBOL_LEN];
+	const char *stub_fname;
+	const char *suffix;
+	s32 stub_func_id;
 	u32 arg_btf_id;
 	int offset;
 
-	stub_func_proto = find_stub_func_proto(btf, st_ops_name, member_name);
-	if (!stub_func_proto)
-		return 0;
+	stub_fname = kallsyms_lookup((unsigned long)stub_func_addr, NULL, NULL, NULL, ksym);
+	if (!stub_fname) {
+		pr_warn("Cannot find the stub function name for the %s in struct %s\n",
+			member_name, st_ops_name);
+		return -ENOENT;
+	}
+
+	stub_func_id = btf_find_by_name_kind(btf, stub_fname, BTF_KIND_FUNC);
+	if (stub_func_id < 0) {
+		pr_warn("Cannot find the stub function %s in btf\n", stub_fname);
+		return -ENOENT;
+	}
+
+	stub_func_proto = btf_type_by_id(btf, stub_func_id);
+	stub_func_proto = btf_type_by_id(btf, stub_func_proto->type);
 
 	/* Check if the number of arguments of the stub function is the same
 	 * as the number of arguments of the function pointer.
 	 */
 	nargs = btf_type_vlen(func_proto);
 	if (nargs != btf_type_vlen(stub_func_proto)) {
-		pr_warn("the number of arguments of the stub function %s__%s does not match the number of arguments of the member %s of struct %s\n",
-			st_ops_name, member_name, member_name, st_ops_name);
+		pr_warn("the number of arguments of the stub function %s does not match the number of arguments of the member %s of struct %s\n",
+			stub_fname, member_name, st_ops_name);
 		return -EINVAL;
 	}
 
@@ -241,10 +226,18 @@ static int prepare_arg_info(struct btf *btf,
 	info = info_buf;
 	for (arg_no = 0; arg_no < nargs; arg_no++) {
 		/* Skip arguments that is not suffixed with
-		 * "__nullable".
+		 * "__nullable or __ref".
 		 */
-		if (!btf_param_match_suffix(btf, &stub_args[arg_no],
-					    MAYBE_NULL_SUFFIX))
+		is_nullable = btf_param_match_suffix(btf, &stub_args[arg_no],
+						     MAYBE_NULL_SUFFIX);
+		is_refcounted = btf_param_match_suffix(btf, &stub_args[arg_no],
+						       REFCOUNTED_SUFFIX);
+
+		if (is_nullable)
+			suffix = MAYBE_NULL_SUFFIX;
+		else if (is_refcounted)
+			suffix = REFCOUNTED_SUFFIX;
+		else
 			continue;
 
 		/* Should be a pointer to struct */
@@ -253,30 +246,34 @@ static int prepare_arg_info(struct btf *btf,
 						    &arg_btf_id);
 		if (!pointed_type ||
 		    !btf_type_is_struct(pointed_type)) {
-			pr_warn("stub function %s__%s has %s tagging to an unsupported type\n",
-				st_ops_name, member_name, MAYBE_NULL_SUFFIX);
+			pr_warn("stub function %s has %s tagging to an unsupported type\n",
+				stub_fname, suffix);
 			goto err_out;
 		}
 
 		offset = btf_ctx_arg_offset(btf, func_proto, arg_no);
 		if (offset < 0) {
-			pr_warn("stub function %s__%s has an invalid trampoline ctx offset for arg#%u\n",
-				st_ops_name, member_name, arg_no);
+			pr_warn("stub function %s has an invalid trampoline ctx offset for arg#%u\n",
+				stub_fname, arg_no);
 			goto err_out;
 		}
 
 		if (args[arg_no].type != stub_args[arg_no].type) {
-			pr_warn("arg#%u type in stub function %s__%s does not match with its original func_proto\n",
-				arg_no, st_ops_name, member_name);
+			pr_warn("arg#%u type in stub function %s does not match with its original func_proto\n",
+				arg_no, stub_fname);
 			goto err_out;
 		}
 
 		/* Fill the information of the new argument */
-		info->reg_type =
-			PTR_TRUSTED | PTR_TO_BTF_ID | PTR_MAYBE_NULL;
 		info->btf_id = arg_btf_id;
 		info->btf = btf;
 		info->offset = offset;
+		if (is_nullable) {
+			info->reg_type = PTR_TRUSTED | PTR_TO_BTF_ID | PTR_MAYBE_NULL;
+		} else if (is_refcounted) {
+			info->reg_type = PTR_TRUSTED | PTR_TO_BTF_ID;
+			info->refcounted = true;
+		}
 
 		info++;
 		info_cnt++;
@@ -324,6 +321,13 @@ static bool is_module_member(const struct btf *btf, u32 id)
 	return !strcmp(btf_name_by_offset(btf, t->name_off), "module");
 }
 
+int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff)
+{
+	void *func_ptr = *(void **)(st_ops->cfi_stubs + moff);
+
+	return func_ptr ? 0 : -ENOTSUPP;
+}
+
 int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc,
 			     struct btf *btf,
 			     struct bpf_verifier_log *log)
@@ -386,8 +390,11 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc,
 	st_ops_desc->value_type = btf_type_by_id(btf, value_id);
 
 	for_each_member(i, t, member) {
-		const struct btf_type *func_proto;
+		const struct btf_type *func_proto, *ret_type;
+		void **stub_func_addr;
+		u32 moff;
 
+		moff = __btf_member_bit_offset(t, member) / 8;
 		mname = btf_name_by_offset(btf, member->name_off);
 		if (!*mname) {
 			pr_warn("anon member in struct %s is not supported\n",
@@ -413,9 +420,23 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc,
 		func_proto = btf_type_resolve_func_ptr(btf,
 						       member->type,
 						       NULL);
-		if (!func_proto)
+
+		/* The member is not a function pointer or
+		 * the function pointer is not supported.
+		 */
+		if (!func_proto || bpf_struct_ops_supported(st_ops, moff))
 			continue;
 
+		if (func_proto->type) {
+			ret_type = btf_type_resolve_ptr(btf, func_proto->type, NULL);
+			if (ret_type && !__btf_type_is_struct(ret_type)) {
+				pr_warn("func ptr %s in struct %s returns non-struct pointer, which is not supported\n",
+					mname, st_ops->name);
+				err = -EOPNOTSUPP;
+				goto errout;
+			}
+		}
+
 		if (btf_distill_func_proto(log, btf,
 					   func_proto, mname,
 					   &st_ops->func_models[i])) {
@@ -425,8 +446,9 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc,
 			goto errout;
 		}
 
+		stub_func_addr = *(void **)(st_ops->cfi_stubs + moff);
 		err = prepare_arg_info(btf, st_ops->name, mname,
-				       func_proto,
+				       func_proto, stub_func_addr,
 				       arg_info + i);
 		if (err)
 			goto errout;
@@ -1152,13 +1174,6 @@ void bpf_struct_ops_put(const void *kdata)
 	bpf_map_put(&st_map->map);
 }
 
-int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff)
-{
-	void *func_ptr = *(void **)(st_ops->cfi_stubs + moff);
-
-	return func_ptr ? 0 : -ENOTSUPP;
-}
-
 static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map)
 {
 	struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index eacb701bc2be..91ce49b7ae28 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -606,6 +606,7 @@ s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p)
 	spin_unlock_bh(&btf_idr_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(bpf_find_btf_id);
 
 const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
 					       u32 id, u32 *res_id)
@@ -2575,7 +2576,7 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	if (btf_type_kflag(t)) {
+	if (btf_type_kflag(t) && !btf_type_is_type_tag(t)) {
 		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
 		return -EINVAL;
 	}
@@ -3332,6 +3333,8 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
 			 u32 off, int sz, struct btf_field_info *info, u32 field_mask)
 {
 	enum btf_field_type type;
+	const char *tag_value;
+	bool is_type_tag;
 	u32 res_id;
 
 	/* Permit modifiers on the pointer itself */
@@ -3341,19 +3344,20 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
 	if (!btf_type_is_ptr(t))
 		return BTF_FIELD_IGNORE;
 	t = btf_type_by_id(btf, t->type);
-
-	if (!btf_type_is_type_tag(t))
+	is_type_tag = btf_type_is_type_tag(t) && !btf_type_kflag(t);
+	if (!is_type_tag)
 		return BTF_FIELD_IGNORE;
 	/* Reject extra tags */
 	if (btf_type_is_type_tag(btf_type_by_id(btf, t->type)))
 		return -EINVAL;
-	if (!strcmp("kptr_untrusted", __btf_name_by_offset(btf, t->name_off)))
+	tag_value = __btf_name_by_offset(btf, t->name_off);
+	if (!strcmp("kptr_untrusted", tag_value))
 		type = BPF_KPTR_UNREF;
-	else if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off)))
+	else if (!strcmp("kptr", tag_value))
 		type = BPF_KPTR_REF;
-	else if (!strcmp("percpu_kptr", __btf_name_by_offset(btf, t->name_off)))
+	else if (!strcmp("percpu_kptr", tag_value))
 		type = BPF_KPTR_PERCPU;
-	else if (!strcmp("uptr", __btf_name_by_offset(btf, t->name_off)))
+	else if (!strcmp("uptr", tag_value))
 		type = BPF_UPTR;
 	else
 		return -EINVAL;
@@ -4944,11 +4948,6 @@ static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	if (btf_type_kflag(t)) {
-		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
-		return -EINVAL;
-	}
-
 	component_idx = btf_type_decl_tag(t)->component_idx;
 	if (component_idx < -1) {
 		btf_verifier_log_type(env, t, "Invalid component_idx");
@@ -6507,6 +6506,8 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = {
 	/* rxrpc */
 	{ "rxrpc_recvdata", 0x1 },
 	{ "rxrpc_resend", 0x10 },
+	{ "rxrpc_tq", 0x10 },
+	{ "rxrpc_client", 0x1 },
 	/* skb */
 	{"kfree_skb", 0x1000},
 	/* sunrpc */
@@ -6529,6 +6530,103 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = {
 	{ "mr_integ_alloc", 0x2000 },
 	/* bpf_testmod */
 	{ "bpf_testmod_test_read", 0x0 },
+	/* amdgpu */
+	{ "amdgpu_vm_bo_map", 0x1 },
+	{ "amdgpu_vm_bo_unmap", 0x1 },
+	/* netfs */
+	{ "netfs_folioq", 0x1 },
+	/* xfs from xfs_defer_pending_class */
+	{ "xfs_defer_create_intent", 0x1 },
+	{ "xfs_defer_cancel_list", 0x1 },
+	{ "xfs_defer_pending_finish", 0x1 },
+	{ "xfs_defer_pending_abort", 0x1 },
+	{ "xfs_defer_relog_intent", 0x1 },
+	{ "xfs_defer_isolate_paused", 0x1 },
+	{ "xfs_defer_item_pause", 0x1 },
+	{ "xfs_defer_item_unpause", 0x1 },
+	/* xfs from xfs_defer_pending_item_class */
+	{ "xfs_defer_add_item", 0x1 },
+	{ "xfs_defer_cancel_item", 0x1 },
+	{ "xfs_defer_finish_item", 0x1 },
+	/* xfs from xfs_icwalk_class */
+	{ "xfs_ioc_free_eofblocks", 0x10 },
+	{ "xfs_blockgc_free_space", 0x10 },
+	/* xfs from xfs_btree_cur_class */
+	{ "xfs_btree_updkeys", 0x100 },
+	{ "xfs_btree_overlapped_query_range", 0x100 },
+	/* xfs from xfs_imap_class*/
+	{ "xfs_map_blocks_found", 0x10000 },
+	{ "xfs_map_blocks_alloc", 0x10000 },
+	{ "xfs_iomap_alloc", 0x1000 },
+	{ "xfs_iomap_found", 0x1000 },
+	/* xfs from xfs_fs_class */
+	{ "xfs_inodegc_flush", 0x1 },
+	{ "xfs_inodegc_push", 0x1 },
+	{ "xfs_inodegc_start", 0x1 },
+	{ "xfs_inodegc_stop", 0x1 },
+	{ "xfs_inodegc_queue", 0x1 },
+	{ "xfs_inodegc_throttle", 0x1 },
+	{ "xfs_fs_sync_fs", 0x1 },
+	{ "xfs_blockgc_start", 0x1 },
+	{ "xfs_blockgc_stop", 0x1 },
+	{ "xfs_blockgc_worker", 0x1 },
+	{ "xfs_blockgc_flush_all", 0x1 },
+	/* xfs_scrub */
+	{ "xchk_nlinks_live_update", 0x10 },
+	/* xfs_scrub from xchk_metapath_class */
+	{ "xchk_metapath_lookup", 0x100 },
+	/* nfsd */
+	{ "nfsd_dirent", 0x1 },
+	{ "nfsd_file_acquire", 0x1001 },
+	{ "nfsd_file_insert_err", 0x1 },
+	{ "nfsd_file_cons_err", 0x1 },
+	/* nfs4 */
+	{ "nfs4_setup_sequence", 0x1 },
+	{ "pnfs_update_layout", 0x10000 },
+	{ "nfs4_inode_callback_event", 0x200 },
+	{ "nfs4_inode_stateid_callback_event", 0x200 },
+	/* nfs from pnfs_layout_event */
+	{ "pnfs_mds_fallback_pg_init_read", 0x10000 },
+	{ "pnfs_mds_fallback_pg_init_write", 0x10000 },
+	{ "pnfs_mds_fallback_pg_get_mirror_count", 0x10000 },
+	{ "pnfs_mds_fallback_read_done", 0x10000 },
+	{ "pnfs_mds_fallback_write_done", 0x10000 },
+	{ "pnfs_mds_fallback_read_pagelist", 0x10000 },
+	{ "pnfs_mds_fallback_write_pagelist", 0x10000 },
+	/* coda */
+	{ "coda_dec_pic_run", 0x10 },
+	{ "coda_dec_pic_done", 0x10 },
+	/* cfg80211 */
+	{ "cfg80211_scan_done", 0x11 },
+	{ "rdev_set_coalesce", 0x10 },
+	{ "cfg80211_report_wowlan_wakeup", 0x100 },
+	{ "cfg80211_inform_bss_frame", 0x100 },
+	{ "cfg80211_michael_mic_failure", 0x10000 },
+	/* cfg80211 from wiphy_work_event */
+	{ "wiphy_work_queue", 0x10 },
+	{ "wiphy_work_run", 0x10 },
+	{ "wiphy_work_cancel", 0x10 },
+	{ "wiphy_work_flush", 0x10 },
+	/* hugetlbfs */
+	{ "hugetlbfs_alloc_inode", 0x10 },
+	/* spufs */
+	{ "spufs_context", 0x10 },
+	/* kvm_hv */
+	{ "kvm_page_fault_enter", 0x100 },
+	/* dpu */
+	{ "dpu_crtc_setup_mixer", 0x100 },
+	/* binder */
+	{ "binder_transaction", 0x100 },
+	/* bcachefs */
+	{ "btree_path_free", 0x100 },
+	/* hfi1_tx */
+	{ "hfi1_sdma_progress", 0x1000 },
+	/* iptfs */
+	{ "iptfs_ingress_postq_event", 0x1000 },
+	/* neigh */
+	{ "neigh_update", 0x10 },
+	/* snd_firewire_lib */
+	{ "amdtp_packet", 0x100 },
 };
 
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
@@ -6679,6 +6777,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 			info->reg_type = ctx_arg_info->reg_type;
 			info->btf = ctx_arg_info->btf ? : btf_vmlinux;
 			info->btf_id = ctx_arg_info->btf_id;
+			info->ref_obj_id = ctx_arg_info->ref_obj_id;
 			return true;
 		}
 	}
@@ -6745,7 +6844,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	info->btf_id = t->type;
 	t = btf_type_by_id(btf, t->type);
 
-	if (btf_type_is_type_tag(t)) {
+	if (btf_type_is_type_tag(t) && !btf_type_kflag(t)) {
 		tag_value = __btf_name_by_offset(btf, t->name_off);
 		if (strcmp(tag_value, "user") == 0)
 			info->reg_type |= MEM_USER;
@@ -7004,7 +7103,7 @@ error:
 
 			/* check type tag */
 			t = btf_type_by_id(btf, mtype->type);
-			if (btf_type_is_type_tag(t)) {
+			if (btf_type_is_type_tag(t) && !btf_type_kflag(t)) {
 				tag_value = __btf_name_by_offset(btf, t->name_off);
 				/* check __user tag */
 				if (strcmp(tag_value, "user") == 0)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 46e5db65dbc8..84f58f3d028a 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -369,7 +369,7 @@ static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl)
 /* count number of elements in the list.
  * it's slow but the list cannot be long
  */
-static u32 prog_list_length(struct hlist_head *head)
+static u32 prog_list_length(struct hlist_head *head, int *preorder_cnt)
 {
 	struct bpf_prog_list *pl;
 	u32 cnt = 0;
@@ -377,6 +377,8 @@ static u32 prog_list_length(struct hlist_head *head)
 	hlist_for_each_entry(pl, head, node) {
 		if (!prog_list_prog(pl))
 			continue;
+		if (preorder_cnt && (pl->flags & BPF_F_PREORDER))
+			(*preorder_cnt)++;
 		cnt++;
 	}
 	return cnt;
@@ -400,7 +402,7 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp,
 
 		if (flags & BPF_F_ALLOW_MULTI)
 			return true;
-		cnt = prog_list_length(&p->bpf.progs[atype]);
+		cnt = prog_list_length(&p->bpf.progs[atype], NULL);
 		WARN_ON_ONCE(cnt > 1);
 		if (cnt == 1)
 			return !!(flags & BPF_F_ALLOW_OVERRIDE);
@@ -423,12 +425,12 @@ static int compute_effective_progs(struct cgroup *cgrp,
 	struct bpf_prog_array *progs;
 	struct bpf_prog_list *pl;
 	struct cgroup *p = cgrp;
-	int cnt = 0;
+	int i, j, cnt = 0, preorder_cnt = 0, fstart, bstart, init_bstart;
 
 	/* count number of effective programs by walking parents */
 	do {
 		if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
-			cnt += prog_list_length(&p->bpf.progs[atype]);
+			cnt += prog_list_length(&p->bpf.progs[atype], &preorder_cnt);
 		p = cgroup_parent(p);
 	} while (p);
 
@@ -439,20 +441,34 @@ static int compute_effective_progs(struct cgroup *cgrp,
 	/* populate the array with effective progs */
 	cnt = 0;
 	p = cgrp;
+	fstart = preorder_cnt;
+	bstart = preorder_cnt - 1;
 	do {
 		if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
 			continue;
 
+		init_bstart = bstart;
 		hlist_for_each_entry(pl, &p->bpf.progs[atype], node) {
 			if (!prog_list_prog(pl))
 				continue;
 
-			item = &progs->items[cnt];
+			if (pl->flags & BPF_F_PREORDER) {
+				item = &progs->items[bstart];
+				bstart--;
+			} else {
+				item = &progs->items[fstart];
+				fstart++;
+			}
 			item->prog = prog_list_prog(pl);
 			bpf_cgroup_storages_assign(item->cgroup_storage,
 						   pl->storage);
 			cnt++;
 		}
+
+		/* reverse pre-ordering progs at this cgroup level */
+		for (i = bstart + 1, j = init_bstart; i < j; i++, j--)
+			swap(progs->items[i], progs->items[j]);
+
 	} while ((p = cgroup_parent(p)));
 
 	*array = progs;
@@ -663,7 +679,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
 		 */
 		return -EPERM;
 
-	if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
+	if (prog_list_length(progs, NULL) >= BPF_CGROUP_MAX_PROGS)
 		return -E2BIG;
 
 	pl = find_attach_entry(progs, prog, link, replace_prog,
@@ -698,6 +714,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
 
 	pl->prog = prog;
 	pl->link = link;
+	pl->flags = flags;
 	bpf_cgroup_storages_assign(pl->storage, storage);
 	cgrp->bpf.flags[atype] = saved_flags;
 
@@ -1073,7 +1090,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 							      lockdep_is_held(&cgroup_mutex));
 			total_cnt += bpf_prog_array_length(effective);
 		} else {
-			total_cnt += prog_list_length(&cgrp->bpf.progs[atype]);
+			total_cnt += prog_list_length(&cgrp->bpf.progs[atype], NULL);
 		}
 	}
 
@@ -1105,7 +1122,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 			u32 id;
 
 			progs = &cgrp->bpf.progs[atype];
-			cnt = min_t(int, prog_list_length(progs), total_cnt);
+			cnt = min_t(int, prog_list_length(progs, NULL), total_cnt);
 			i = 0;
 			hlist_for_each_entry(pl, progs, node) {
 				prog = prog_list_prog(pl);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index da729cbbaeb9..ba6b6118cf50 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1663,14 +1663,17 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 	INSN_3(JMP, JSET, K),			\
 	INSN_2(JMP, JA),			\
 	INSN_2(JMP32, JA),			\
+	/* Atomic operations. */		\
+	INSN_3(STX, ATOMIC, B),			\
+	INSN_3(STX, ATOMIC, H),			\
+	INSN_3(STX, ATOMIC, W),			\
+	INSN_3(STX, ATOMIC, DW),		\
 	/* Store instructions. */		\
 	/*   Register based. */			\
 	INSN_3(STX, MEM,  B),			\
 	INSN_3(STX, MEM,  H),			\
 	INSN_3(STX, MEM,  W),			\
 	INSN_3(STX, MEM,  DW),			\
-	INSN_3(STX, ATOMIC, W),			\
-	INSN_3(STX, ATOMIC, DW),		\
 	/*   Immediate based. */		\
 	INSN_3(ST, MEM, B),			\
 	INSN_3(ST, MEM, H),			\
@@ -2152,24 +2155,33 @@ out:
 			if (BPF_SIZE(insn->code) == BPF_W)		\
 				atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \
 					     (DST + insn->off));	\
-			else						\
+			else if (BPF_SIZE(insn->code) == BPF_DW)	\
 				atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \
 					       (DST + insn->off));	\
+			else						\
+				goto default_label;			\
 			break;						\
 		case BOP | BPF_FETCH:					\
 			if (BPF_SIZE(insn->code) == BPF_W)		\
 				SRC = (u32) atomic_fetch_##KOP(		\
 					(u32) SRC,			\
 					(atomic_t *)(unsigned long) (DST + insn->off)); \
-			else						\
+			else if (BPF_SIZE(insn->code) == BPF_DW)	\
 				SRC = (u64) atomic64_fetch_##KOP(	\
 					(u64) SRC,			\
 					(atomic64_t *)(unsigned long) (DST + insn->off)); \
+			else						\
+				goto default_label;			\
 			break;
 
 	STX_ATOMIC_DW:
 	STX_ATOMIC_W:
+	STX_ATOMIC_H:
+	STX_ATOMIC_B:
 		switch (IMM) {
+		/* Atomic read-modify-write instructions support only W and DW
+		 * size modifiers.
+		 */
 		ATOMIC_ALU_OP(BPF_ADD, add)
 		ATOMIC_ALU_OP(BPF_AND, and)
 		ATOMIC_ALU_OP(BPF_OR, or)
@@ -2181,20 +2193,63 @@ out:
 				SRC = (u32) atomic_xchg(
 					(atomic_t *)(unsigned long) (DST + insn->off),
 					(u32) SRC);
-			else
+			else if (BPF_SIZE(insn->code) == BPF_DW)
 				SRC = (u64) atomic64_xchg(
 					(atomic64_t *)(unsigned long) (DST + insn->off),
 					(u64) SRC);
+			else
+				goto default_label;
 			break;
 		case BPF_CMPXCHG:
 			if (BPF_SIZE(insn->code) == BPF_W)
 				BPF_R0 = (u32) atomic_cmpxchg(
 					(atomic_t *)(unsigned long) (DST + insn->off),
 					(u32) BPF_R0, (u32) SRC);
-			else
+			else if (BPF_SIZE(insn->code) == BPF_DW)
 				BPF_R0 = (u64) atomic64_cmpxchg(
 					(atomic64_t *)(unsigned long) (DST + insn->off),
 					(u64) BPF_R0, (u64) SRC);
+			else
+				goto default_label;
+			break;
+		/* Atomic load and store instructions support all size
+		 * modifiers.
+		 */
+		case BPF_LOAD_ACQ:
+			switch (BPF_SIZE(insn->code)) {
+#define LOAD_ACQUIRE(SIZEOP, SIZE)				\
+			case BPF_##SIZEOP:			\
+				DST = (SIZE)smp_load_acquire(	\
+					(SIZE *)(unsigned long)(SRC + insn->off));	\
+				break;
+			LOAD_ACQUIRE(B,   u8)
+			LOAD_ACQUIRE(H,  u16)
+			LOAD_ACQUIRE(W,  u32)
+#ifdef CONFIG_64BIT
+			LOAD_ACQUIRE(DW, u64)
+#endif
+#undef LOAD_ACQUIRE
+			default:
+				goto default_label;
+			}
+			break;
+		case BPF_STORE_REL:
+			switch (BPF_SIZE(insn->code)) {
+#define STORE_RELEASE(SIZEOP, SIZE)			\
+			case BPF_##SIZEOP:		\
+				smp_store_release(	\
+					(SIZE *)(unsigned long)(DST + insn->off), (SIZE)SRC);	\
+				break;
+			STORE_RELEASE(B,   u8)
+			STORE_RELEASE(H,  u16)
+			STORE_RELEASE(W,  u32)
+#ifdef CONFIG_64BIT
+			STORE_RELEASE(DW, u64)
+#endif
+#undef STORE_RELEASE
+			default:
+				goto default_label;
+			}
 			break;
 
 		default:
@@ -2290,17 +2345,18 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
 	insn->code = BPF_JMP | BPF_CALL_ARGS;
 }
 #endif
-#else
+#endif
+
 static unsigned int __bpf_prog_ret0_warn(const void *ctx,
 					 const struct bpf_insn *insn)
 {
 	/* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
-	 * is not working properly, so warn about it!
+	 * is not working properly, or interpreter is being used when
+	 * prog->jit_requested is not 0, so warn about it!
 	 */
 	WARN_ON_ONCE(1);
 	return 0;
 }
-#endif
 
 bool bpf_prog_map_compatible(struct bpf_map *map,
 			     const struct bpf_prog *fp)
@@ -2380,8 +2436,18 @@ static void bpf_prog_select_func(struct bpf_prog *fp)
 {
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+	u32 idx = (round_up(stack_depth, 32) / 32) - 1;
 
-	fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+	/* may_goto may cause stack size > 512, leading to idx out-of-bounds.
+	 * But for non-JITed programs, we don't need bpf_func, so no bounds
+	 * check needed.
+	 */
+	if (!fp->jit_requested &&
+	    !WARN_ON_ONCE(idx >= ARRAY_SIZE(interpreters))) {
+		fp->bpf_func = interpreters[idx];
+	} else {
+		fp->bpf_func = __bpf_prog_ret0_warn;
+	}
 #else
 	fp->bpf_func = __bpf_prog_ret0_warn;
 #endif
@@ -2906,6 +2972,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void)
 	return NULL;
 }