Merge branch 'bpf-sleepable'

Alexei Starovoitov says:

====================
v2->v3:
- switched to minimal allowlist approach. Essentially that means that syscall
  entry, few btrfs allow_error_inject functions, should_fail_bio(), and two LSM
  hooks: file_mprotect and bprm_committed_creds are the only hooks that allow
  attaching of sleepable BPF programs. When comprehensive analysis of LSM hooks
  will be done this allowlist will be extended.
- added patch 1 that fixes prototypes of two mm functions to reliably work with
  error injection. It's also necessary for resolve_btfids tool to recognize
  these two funcs, but that's secondary.

v1->v2:
- split fmod_ret fix into separate patch
- added denylist

v1:
This patch set introduces the minimal viable support for sleepable bpf programs.
In this patch only fentry/fexit/fmod_ret and lsm progs can be sleepable.
Only array and pre-allocated hash and lru maps allowed.

Here is 'perf report' difference of sleepable vs non-sleepable:
   3.86%  bench     [k] __srcu_read_unlock
   3.22%  bench     [k] __srcu_read_lock
   0.92%  bench     [k] bpf_prog_740d4210cdcd99a3_bench_trigger_fentry_sleep
   0.50%  bench     [k] bpf_trampoline_10297
   0.26%  bench     [k] __bpf_prog_exit_sleepable
   0.21%  bench     [k] __bpf_prog_enter_sleepable
vs
   0.88%  bench     [k] bpf_prog_740d4210cdcd99a3_bench_trigger_fentry
   0.84%  bench     [k] bpf_trampoline_10297
   0.13%  bench     [k] __bpf_prog_enter
   0.12%  bench     [k] __bpf_prog_exit
vs
   0.79%  bench     [k] bpf_prog_740d4210cdcd99a3_bench_trigger_fentry_sleep
   0.72%  bench     [k] bpf_trampoline_10381
   0.31%  bench     [k] __bpf_prog_exit_sleepable
   0.29%  bench     [k] __bpf_prog_enter_sleepable

Sleepable vs non-sleepable program invocation overhead is only marginally higher
due to rcu_trace. srcu approach is much slower.
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

arch/x86/net/bpf_jit_comp.c

@@ -1379,10 +1379,15 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	u8 *prog = *pprog;
 	int cnt = 0;
 
-	if (emit_call(&prog, __bpf_prog_enter, prog))
-		return -EINVAL;
-	/* remember prog start time returned by __bpf_prog_enter */
-	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
+	if (p->aux->sleepable) {
+		if (emit_call(&prog, __bpf_prog_enter_sleepable, prog))
+			return -EINVAL;
+	} else {
+		if (emit_call(&prog, __bpf_prog_enter, prog))
+			return -EINVAL;
+		/* remember prog start time returned by __bpf_prog_enter */
+		emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
+	}
 
 	/* arg1: lea rdi, [rbp - stack_size] */
 	EMIT4(0x48, 0x8D, 0x7D, -stack_size);
@@ -1402,13 +1407,18 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	if (mod_ret)
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 
-	/* arg1: mov rdi, progs[i] */
-	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32,
-		       (u32) (long) p);
-	/* arg2: mov rsi, rbx <- start time in nsec */
-	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
-	if (emit_call(&prog, __bpf_prog_exit, prog))
-		return -EINVAL;
+	if (p->aux->sleepable) {
+		if (emit_call(&prog, __bpf_prog_exit_sleepable, prog))
+			return -EINVAL;
+	} else {
+		/* arg1: mov rdi, progs[i] */
+		emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32,
+			       (u32) (long) p);
+		/* arg2: mov rsi, rbx <- start time in nsec */
+		emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
+		if (emit_call(&prog, __bpf_prog_exit, prog))
+			return -EINVAL;
+	}
 
 	*pprog = prog;
 	return 0;

include/linux/bpf.h

@@ -539,6 +539,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 /* these two functions are called from generated trampoline */
 u64 notrace __bpf_prog_enter(void);
 void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
+void notrace __bpf_prog_enter_sleepable(void);
+void notrace __bpf_prog_exit_sleepable(void);
 
 struct bpf_ksym {
 	unsigned long		 start;
@@ -734,6 +736,7 @@ struct bpf_prog_aux {
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
 	bool func_proto_unreliable;
+	bool sleepable;
 	enum bpf_tramp_prog_type trampoline_prog_type;
 	struct bpf_trampoline *trampoline;
 	struct hlist_node tramp_hlist;
@@ -1781,6 +1784,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
+extern const struct bpf_func_proto bpf_copy_from_user_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);

include/uapi/linux/bpf.h

@@ -346,6 +346,14 @@ enum bpf_link_type {
 /* The verifier internal test flag. Behavior is undefined */
 #define BPF_F_TEST_STATE_FREQ	(1U << 3)
 
+/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will
+ * restrict map and helper usage for such programs. Sleepable BPF programs can
+ * only be attached to hooks where kernel execution context allows sleeping.
+ * Such programs are allowed to use helpers that may sleep like
+ * bpf_copy_from_user().
+ */
+#define BPF_F_SLEEPABLE		(1U << 4)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * two extensions:
  *
@@ -3561,6 +3569,13 @@ union bpf_attr {
  *		On success, the strictly positive length of the string,
  *		including the trailing NUL character. On error, a negative
  *		value.
+ *
+ * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
+ * 	Description
+ * 		Read *size* bytes from user space address *user_ptr* and store
+ * 		the data in *dst*. This is a wrapper of copy_from_user().
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3711,6 +3726,7 @@ union bpf_attr {
 	FN(inode_storage_get),		\
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
+	FN(copy_from_user),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

init/Kconfig

@@ -1691,6 +1691,7 @@ config BPF_SYSCALL
 	bool "Enable bpf() system call"
 	select BPF
 	select IRQ_WORK
+	select TASKS_TRACE_RCU
 	default n
 	help
 	  Enable the bpf() system call that allows to manipulate eBPF

kernel/bpf/arraymap.c

@@ -10,6 +10,7 @@
 #include <linux/filter.h>
 #include <linux/perf_event.h>
 #include <uapi/linux/btf.h>
+#include <linux/rcupdate_trace.h>
 
 #include "map_in_map.h"
 

kernel/bpf/hashtab.c

@@ -9,6 +9,7 @@
 #include <linux/rculist_nulls.h>
 #include <linux/random.h>
 #include <uapi/linux/btf.h>
+#include <linux/rcupdate_trace.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
 #include "map_in_map.h"
@@ -577,8 +578,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 	struct htab_elem *l;
 	u32 hash, key_size;
 
-	/* Must be called with rcu_read_lock. */
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 
@@ -941,7 +941,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* unknown flags */
 		return -EINVAL;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 
@@ -1032,7 +1032,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* unknown flags */
 		return -EINVAL;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 
@@ -1220,7 +1220,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 	u32 hash, key_size;
 	int ret = -ENOENT;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 
@@ -1252,7 +1252,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 	u32 hash, key_size;
 	int ret = -ENOENT;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 

kernel/bpf/helpers.c

@@ -601,6 +601,28 @@ const struct bpf_func_proto bpf_event_output_data_proto =  {
 	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
 };
 
+BPF_CALL_3(bpf_copy_from_user, void *, dst, u32, size,
+	   const void __user *, user_ptr)
+{
+	int ret = copy_from_user(dst, user_ptr, size);
+
+	if (unlikely(ret)) {
+		memset(dst, 0, size);
+		ret = -EFAULT;
+	}
+
+	return ret;
+}
+
+const struct bpf_func_proto bpf_copy_from_user_proto = {
+	.func		= bpf_copy_from_user,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;

kernel/bpf/syscall.c

@@ -29,6 +29,7 @@
 #include <linux/bpf_lsm.h>
 #include <linux/poll.h>
 #include <linux/bpf-netns.h>
+#include <linux/rcupdate_trace.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -1731,10 +1732,14 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
 	btf_put(prog->aux->btf);
 	bpf_prog_free_linfo(prog);
 
-	if (deferred)
-		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
-	else
+	if (deferred) {
+		if (prog->aux->sleepable)
+			call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu);
+		else
+			call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
+	} else {
 		__bpf_prog_put_rcu(&prog->aux->rcu);
+	}
 }
 
 static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
@@ -2104,6 +2109,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT |
 				 BPF_F_ANY_ALIGNMENT |
 				 BPF_F_TEST_STATE_FREQ |
+				 BPF_F_SLEEPABLE |
 				 BPF_F_TEST_RND_HI32))
 		return -EINVAL;
 
@@ -2159,6 +2165,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	}
 
 	prog->aux->offload_requested = !!attr->prog_ifindex;
+	prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
 
 	err = security_bpf_prog_alloc(prog->aux);
 	if (err)

kernel/bpf/trampoline.c

@@ -7,6 +7,8 @@
 #include <linux/rbtree_latch.h>
 #include <linux/perf_event.h>
 #include <linux/btf.h>
+#include <linux/rcupdate_trace.h>
+#include <linux/rcupdate_wait.h>
 
 /* dummy _ops. The verifier will operate on target program's ops. */
 const struct bpf_verifier_ops bpf_extension_verifier_ops = {
@@ -210,9 +212,12 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 	 * updates to trampoline would change the code from underneath the
 	 * preempted task. Hence wait for tasks to voluntarily schedule or go
 	 * to userspace.
+	 * The same trampoline can hold both sleepable and non-sleepable progs.
+	 * synchronize_rcu_tasks_trace() is needed to make sure all sleepable
+	 * programs finish executing.
+	 * Wait for these two grace periods together.
 	 */
-
-	synchronize_rcu_tasks();
+	synchronize_rcu_mult(call_rcu_tasks, call_rcu_tasks_trace);
 
 	err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2,
 					  &tr->func.model, flags, tprogs,
@@ -344,7 +349,14 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
 	if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT])))
 		goto out;
 	bpf_image_ksym_del(&tr->ksym);
-	/* wait for tasks to get out of trampoline before freeing it */
+	/* This code will be executed when all bpf progs (both sleepable and
+	 * non-sleepable) went through
+	 * bpf_prog_put()->call_rcu[_tasks_trace]()->bpf_prog_free_deferred().
+	 * Hence no need for another synchronize_rcu_tasks_trace() here,
+	 * but synchronize_rcu_tasks() is still needed, since trampoline
+	 * may not have had any sleepable programs and we need to wait
+	 * for tasks to get out of trampoline code before freeing it.
+	 */
 	synchronize_rcu_tasks();
 	bpf_jit_free_exec(tr->image);
 	hlist_del(&tr->hlist);
@@ -394,6 +406,16 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
 	rcu_read_unlock();
 }
 
+void notrace __bpf_prog_enter_sleepable(void)
+{
+	rcu_read_lock_trace();
+}
+
+void notrace __bpf_prog_exit_sleepable(void)
+{
+	rcu_read_unlock_trace();
+}
+
 int __weak
 arch_prepare_bpf_trampoline(void *image, void *image_end,
 			    const struct btf_func_model *m, u32 flags,

kernel/bpf/verifier.c

@@ -21,6 +21,7 @@
 #include <linux/ctype.h>
 #include <linux/error-injection.h>
 #include <linux/bpf_lsm.h>
+#include <linux/btf_ids.h>
 
 #include "disasm.h"
 
@@ -9367,6 +9368,23 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (prog->aux->sleepable)
+		switch (map->map_type) {
+		case BPF_MAP_TYPE_HASH:
+		case BPF_MAP_TYPE_LRU_HASH:
+		case BPF_MAP_TYPE_ARRAY:
+			if (!is_preallocated_map(map)) {
+				verbose(env,
+					"Sleepable programs can only use preallocated hash maps\n");
+				return -EINVAL;
+			}
+			break;
+		default:
+			verbose(env,
+				"Sleepable programs can only use array and hash maps\n");
+			return -EINVAL;
+		}
+
 	return 0;
 }
 
@@ -10985,6 +11003,36 @@ static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr)
 	return -EINVAL;
 }
 
+/* non exhaustive list of sleepable bpf_lsm_*() functions */
+BTF_SET_START(btf_sleepable_lsm_hooks)
+#ifdef CONFIG_BPF_LSM
+BTF_ID(func, bpf_lsm_file_mprotect)
+BTF_ID(func, bpf_lsm_bprm_committed_creds)
+#endif
+BTF_SET_END(btf_sleepable_lsm_hooks)
+
+static int check_sleepable_lsm_hook(u32 btf_id)
+{
+	return btf_id_set_contains(&btf_sleepable_lsm_hooks, btf_id);
+}
+
+/* list of non-sleepable functions that are otherwise on
+ * ALLOW_ERROR_INJECTION list
+ */
+BTF_SET_START(btf_non_sleepable_error_inject)
+/* Three functions below can be called from sleepable and non-sleepable context.
+ * Assume non-sleepable from bpf safety point of view.
+ */
+BTF_ID(func, __add_to_page_cache_locked)
+BTF_ID(func, should_fail_alloc_page)
+BTF_ID(func, should_failslab)
+BTF_SET_END(btf_non_sleepable_error_inject)
+
+static int check_non_sleepable_error_inject(u32 btf_id)
+{
+	return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id);
+}
+
 static int check_attach_btf_id(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog;
@@ -11002,6 +11050,12 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	long addr;
 	u64 key;
 
+	if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
+	    prog->type != BPF_PROG_TYPE_LSM) {
+		verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
+		return -EINVAL;
+	}
+
 	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
 		return check_struct_ops_btf_id(env);
 
@@ -11210,13 +11264,36 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			}
 		}
 
-		if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
+		if (prog->aux->sleepable) {
+			ret = -EINVAL;
+			switch (prog->type) {
+			case BPF_PROG_TYPE_TRACING:
+				/* fentry/fexit/fmod_ret progs can be sleepable only if they are
+				 * attached to ALLOW_ERROR_INJECTION and are not in denylist.
+				 */
+				if (!check_non_sleepable_error_inject(btf_id) &&
+				    within_error_injection_list(addr))
+					ret = 0;
+				break;
+			case BPF_PROG_TYPE_LSM:
+				/* LSM progs check that they are attached to bpf_lsm_*() funcs.
+				 * Only some of them are sleepable.
+				 */
+				if (check_sleepable_lsm_hook(btf_id))
+					ret = 0;
+				break;
+			default:
+				break;
+			}
+			if (ret)
+				verbose(env, "%s is not sleepable\n",
+					prog->aux->attach_func_name);
+		} else if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
 			ret = check_attach_modify_return(prog, addr);
 			if (ret)
 				verbose(env, "%s() is not modifiable\n",
 					prog->aux->attach_func_name);
 		}
-
 		if (ret)
 			goto out;
 		tr->func.addr = (void *)addr;

kernel/trace/bpf_trace.c

@@ -1228,6 +1228,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_jiffies64_proto;
 	case BPF_FUNC_get_task_stack:
 		return &bpf_get_task_stack_proto;
+	case BPF_FUNC_copy_from_user:
+		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
 	default:
 		return NULL;
 	}

mm/filemap.c

@@ -827,10 +827,10 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
-static int __add_to_page_cache_locked(struct page *page,
-				      struct address_space *mapping,
-				      pgoff_t offset, gfp_t gfp_mask,
-				      void **shadowp)
+noinline int __add_to_page_cache_locked(struct page *page,
+					struct address_space *mapping,
+					pgoff_t offset, gfp_t gfp_mask,
+					void **shadowp)
 {
 	XA_STATE(xas, &mapping->i_pages, offset);
 	int huge = PageHuge(page);

mm/page_alloc.c

@@ -3477,7 +3477,7 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 
 #endif /* CONFIG_FAIL_PAGE_ALLOC */
 
-static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 {
 	return __should_fail_alloc_page(gfp_mask, order);
 }

tools/include/uapi/linux/bpf.h

@@ -346,6 +346,14 @@ enum bpf_link_type {
 /* The verifier internal test flag. Behavior is undefined */
 #define BPF_F_TEST_STATE_FREQ	(1U << 3)
 
+/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will
+ * restrict map and helper usage for such programs. Sleepable BPF programs can
+ * only be attached to hooks where kernel execution context allows sleeping.
+ * Such programs are allowed to use helpers that may sleep like
+ * bpf_copy_from_user().
+ */
+#define BPF_F_SLEEPABLE		(1U << 4)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * two extensions:
  *
@@ -3561,6 +3569,13 @@ union bpf_attr {
  *		On success, the strictly positive length of the string,
  *		including the trailing NUL character. On error, a negative
  *		value.
+ *
+ * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
+ * 	Description
+ * 		Read *size* bytes from user space address *user_ptr* and store
+ * 		the data in *dst*. This is a wrapper of copy_from_user().
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3711,6 +3726,7 @@ union bpf_attr {
 	FN(inode_storage_get),		\
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
+	FN(copy_from_user),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

tools/lib/bpf/libbpf.c

@@ -208,6 +208,7 @@ struct bpf_sec_def {
 	bool is_exp_attach_type_optional;
 	bool is_attachable;
 	bool is_attach_btf;
+	bool is_sleepable;
 	attach_fn_t attach_fn;
 };
 
@@ -6291,6 +6292,8 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 			/* couldn't guess, but user might manually specify */
 			continue;
 
+		if (prog->sec_def->is_sleepable)
+			prog->prog_flags |= BPF_F_SLEEPABLE;
 		bpf_program__set_type(prog, prog->sec_def->prog_type);
 		bpf_program__set_expected_attach_type(prog,
 				prog->sec_def->expected_attach_type);
@@ -7559,6 +7562,21 @@ static const struct bpf_sec_def section_defs[] = {
 		.expected_attach_type = BPF_TRACE_FEXIT,
 		.is_attach_btf = true,
 		.attach_fn = attach_trace),
+	SEC_DEF("fentry.s/", TRACING,
+		.expected_attach_type = BPF_TRACE_FENTRY,
+		.is_attach_btf = true,
+		.is_sleepable = true,
+		.attach_fn = attach_trace),
+	SEC_DEF("fmod_ret.s/", TRACING,
+		.expected_attach_type = BPF_MODIFY_RETURN,
+		.is_attach_btf = true,
+		.is_sleepable = true,
+		.attach_fn = attach_trace),
+	SEC_DEF("fexit.s/", TRACING,
+		.expected_attach_type = BPF_TRACE_FEXIT,
+		.is_attach_btf = true,
+		.is_sleepable = true,
+		.attach_fn = attach_trace),
 	SEC_DEF("freplace/", EXT,
 		.is_attach_btf = true,
 		.attach_fn = attach_trace),
@@ -7566,6 +7584,11 @@ static const struct bpf_sec_def section_defs[] = {
 		.is_attach_btf = true,
 		.expected_attach_type = BPF_LSM_MAC,
 		.attach_fn = attach_lsm),
+	SEC_DEF("lsm.s/", LSM,
+		.is_attach_btf = true,
+		.is_sleepable = true,
+		.expected_attach_type = BPF_LSM_MAC,
+		.attach_fn = attach_lsm),
 	SEC_DEF("iter/", TRACING,
 		.expected_attach_type = BPF_TRACE_ITER,
 		.is_attach_btf = true,
@@ -8288,7 +8311,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 
 		prog->prog_ifindex = attr->ifindex;
 		prog->log_level = attr->log_level;
-		prog->prog_flags = attr->prog_flags;
+		prog->prog_flags |= attr->prog_flags;
 		if (!first_prog)
 			first_prog = prog;
 	}

tools/testing/selftests/bpf/bench.c

@@ -317,6 +317,7 @@ extern const struct bench bench_trig_tp;
 extern const struct bench bench_trig_rawtp;
 extern const struct bench bench_trig_kprobe;
 extern const struct bench bench_trig_fentry;
+extern const struct bench bench_trig_fentry_sleep;
 extern const struct bench bench_trig_fmodret;
 extern const struct bench bench_rb_libbpf;
 extern const struct bench bench_rb_custom;
@@ -338,6 +339,7 @@ static const struct bench *benchs[] = {
 	&bench_trig_rawtp,
 	&bench_trig_kprobe,
 	&bench_trig_fentry,
+	&bench_trig_fentry_sleep,
 	&bench_trig_fmodret,
 	&bench_rb_libbpf,
 	&bench_rb_custom,

tools/testing/selftests/bpf/benchs/bench_trigger.c

@@ -90,6 +90,12 @@ static void trigger_fentry_setup()
 	attach_bpf(ctx.skel->progs.bench_trigger_fentry);
 }
 
+static void trigger_fentry_sleep_setup()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_fentry_sleep);
+}
+
 static void trigger_fmodret_setup()
 {
 	setup_ctx();
@@ -155,6 +161,17 @@ const struct bench bench_trig_fentry = {
 	.report_final = hits_drops_report_final,
 };
 
+const struct bench bench_trig_fentry_sleep = {
+	.name = "trig-fentry-sleep",
+	.validate = trigger_validate,
+	.setup = trigger_fentry_sleep_setup,
+	.producer_thread = trigger_producer,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
 const struct bench bench_trig_fmodret = {
 	.name = "trig-fmodret",
 	.validate = trigger_validate,

tools/testing/selftests/bpf/prog_tests/test_lsm.c

@@ -10,6 +10,7 @@
 #include <unistd.h>
 #include <malloc.h>
 #include <stdlib.h>
+#include <unistd.h>
 
 #include "lsm.skel.h"
 
@@ -55,6 +56,7 @@ void test_test_lsm(void)
 {
 	struct lsm *skel = NULL;
 	int err, duration = 0;
+	int buf = 1234;
 
 	skel = lsm__open_and_load();
 	if (CHECK(!skel, "skel_load", "lsm skeleton failed\n"))
@@ -81,6 +83,13 @@ void test_test_lsm(void)
 	CHECK(skel->bss->mprotect_count != 1, "mprotect_count",
 	      "mprotect_count = %d\n", skel->bss->mprotect_count);
 
+	syscall(__NR_setdomainname, &buf, -2L);
+	syscall(__NR_setdomainname, 0, -3L);
+	syscall(__NR_setdomainname, ~0L, -4L);
+
+	CHECK(skel->bss->copy_test != 3, "copy_test",
+	      "copy_test = %d\n", skel->bss->copy_test);
+
 close_prog:
 	lsm__destroy(skel);
 }

tools/testing/selftests/bpf/progs/lsm.c

@@ -9,16 +9,41 @@
 #include <bpf/bpf_tracing.h>
 #include  <errno.h>
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} array SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} hash SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} lru_hash SEC(".maps");
+
 char _license[] SEC("license") = "GPL";
 
 int monitored_pid = 0;
 int mprotect_count = 0;
 int bprm_count = 0;
 
-SEC("lsm/file_mprotect")
+SEC("lsm.s/file_mprotect")
 int BPF_PROG(test_int_hook, struct vm_area_struct *vma,
 	     unsigned long reqprot, unsigned long prot, int ret)
 {
+	char args[64];
+	__u32 key = 0;
+	__u64 *value;
+
 	if (ret != 0)
 		return ret;
 
@@ -28,6 +53,18 @@ int BPF_PROG(test_int_hook, struct vm_area_struct *vma,
 	is_stack = (vma->vm_start <= vma->vm_mm->start_stack &&
 		    vma->vm_end >= vma->vm_mm->start_stack);
 
+	bpf_copy_from_user(args, sizeof(args), (void *)vma->vm_mm->arg_start);
+
+	value = bpf_map_lookup_elem(&array, &key);
+	if (value)
+		*value = 0;
+	value = bpf_map_lookup_elem(&hash, &key);
+	if (value)
+		*value = 0;
+	value = bpf_map_lookup_elem(&lru_hash, &key);
+	if (value)
+		*value = 0;
+
 	if (is_stack && monitored_pid == pid) {
 		mprotect_count++;
 		ret = -EPERM;
@@ -36,7 +73,7 @@ int BPF_PROG(test_int_hook, struct vm_area_struct *vma,
 	return ret;
 }
 
-SEC("lsm/bprm_committed_creds")
+SEC("lsm.s/bprm_committed_creds")
 int BPF_PROG(test_void_hook, struct linux_binprm *bprm)
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
@@ -46,3 +83,28 @@ int BPF_PROG(test_void_hook, struct linux_binprm *bprm)
 
 	return 0;
 }
+SEC("lsm/task_free") /* lsm/ is ok, lsm.s/ fails */
+int BPF_PROG(test_task_free, struct task_struct *task)
+{
+	return 0;
+}
+
+int copy_test = 0;
+
+SEC("fentry.s/__x64_sys_setdomainname")
+int BPF_PROG(test_sys_setdomainname, struct pt_regs *regs)
+{
+	void *ptr = (void *)PT_REGS_PARM1(regs);
+	int len = PT_REGS_PARM2(regs);
+	int buf = 0;
+	long ret;
+
+	ret = bpf_copy_from_user(&buf, sizeof(buf), ptr);
+	if (len == -2 && ret == 0 && buf == 1234)
+		copy_test++;
+	if (len == -3 && ret == -EFAULT)
+		copy_test++;
+	if (len == -4 && ret == -EFAULT)
+		copy_test++;
+	return 0;
+}

tools/testing/selftests/bpf/progs/trigger_bench.c

@@ -39,6 +39,13 @@ int bench_trigger_fentry(void *ctx)
 	return 0;
 }
 
+SEC("fentry.s/__x64_sys_getpgid")
+int bench_trigger_fentry_sleep(void *ctx)
+{
+	__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
 SEC("fmod_ret/__x64_sys_getpgid")
 int bench_trigger_fmodret(void *ctx)
 {