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>

7 files changed, 145 insertions, 14 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index d851ebbcf302..e046fb7d17cd 100644
--- a/kernel/bpf/arraymap.c
+++ b/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"
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index ad80f45774e7..fe0e06284d33 100644
--- a/kernel/bpf/hashtab.c
+++ b/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;
 
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index be43ab3e619f..5cc7425ee476 100644
--- a/kernel/bpf/helpers.c
+++ b/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;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b86b1155b748..4108ef3b828b 100644
--- a/kernel/bpf/syscall.c
+++ b/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)
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 9be85aa4ec5f..c2b76545153c 100644
--- a/kernel/bpf/trampoline.c
+++ b/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,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6f5a9f51cc03..3ebfdb7bd427 100644
--- a/kernel/bpf/verifier.c
+++ b/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;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d973d891f2e2..b2a5380eb187 100644
--- a/kernel/trace/bpf_trace.c
+++ b/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;
 	}