Netdev List
 help / color / mirror / Atom feed
From: Martin KaFai Lau <martin.lau@linux.dev>
To: bpf@vger.kernel.org
Cc: 'Alexei Starovoitov ' <ast@kernel.org>,
	'Andrii Nakryiko ' <andrii@kernel.org>,
	'Daniel Borkmann ' <daniel@iogearbox.net>,
	'Shakeel Butt ' <shakeel.butt@linux.dev>,
	'Roman Gushchin ' <roman.gushchin@linux.dev>,
	'Amery Hung ' <ameryhung@gmail.com>,
	netdev@vger.kernel.org
Subject: [RFC PATCH bpf-next 01/12] bpf: Remove __rcu tagging in st_link->map
Date: Tue, 19 May 2026 14:58:08 -0700	[thread overview]
Message-ID: <20260519215841.2984970-2-martin.lau@linux.dev> (raw)
In-Reply-To: <20260519215841.2984970-1-martin.lau@linux.dev>

From: Martin KaFai Lau <martin.lau@kernel.org>

st_link->map is always written under update_mutex. The paths that read
st_link->map with rcu_read_lock() are not in the fast path, so they can
simply take update_mutex instead. Remove the __rcu annotation and replace
all RCU accessors with direct pointer reads under update_mutex. Use
READ_ONCE() in bpf_struct_ops_map_link_poll() which reads the pointer
without holding update_mutex.

It is a simplification change.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/bpf_struct_ops.c | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 521cb9d7e8c7..08791180d71d 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -57,7 +57,7 @@ struct bpf_struct_ops_map {
 
 struct bpf_struct_ops_link {
 	struct bpf_link link;
-	struct bpf_map __rcu *map;
+	struct bpf_map *map;
 	wait_queue_head_t wait_hup;
 };
 
@@ -1220,8 +1220,7 @@ static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link)
 	struct bpf_struct_ops_map *st_map;
 
 	st_link = container_of(link, struct bpf_struct_ops_link, link);
-	st_map = (struct bpf_struct_ops_map *)
-		rcu_dereference_protected(st_link->map, true);
+	st_map = (struct bpf_struct_ops_map *)st_link->map;
 	if (st_map) {
 		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, link);
 		bpf_map_put(&st_map->map);
@@ -1236,11 +1235,11 @@ static void bpf_struct_ops_map_link_show_fdinfo(const struct bpf_link *link,
 	struct bpf_map *map;
 
 	st_link = container_of(link, struct bpf_struct_ops_link, link);
-	rcu_read_lock();
-	map = rcu_dereference(st_link->map);
+	mutex_lock(&update_mutex);
+	map = st_link->map;
 	if (map)
 		seq_printf(seq, "map_id:\t%d\n", map->id);
-	rcu_read_unlock();
+	mutex_unlock(&update_mutex);
 }
 
 static int bpf_struct_ops_map_link_fill_link_info(const struct bpf_link *link,
@@ -1250,11 +1249,11 @@ static int bpf_struct_ops_map_link_fill_link_info(const struct bpf_link *link,
 	struct bpf_map *map;
 
 	st_link = container_of(link, struct bpf_struct_ops_link, link);
-	rcu_read_lock();
-	map = rcu_dereference(st_link->map);
+	mutex_lock(&update_mutex);
+	map = st_link->map;
 	if (map)
 		info->struct_ops.map_id = map->id;
-	rcu_read_unlock();
+	mutex_unlock(&update_mutex);
 	return 0;
 }
 
@@ -1277,7 +1276,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 
 	mutex_lock(&update_mutex);
 
-	old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
+	old_map = st_link->map;
 	if (!old_map) {
 		err = -ENOLINK;
 		goto err_out;
@@ -1299,7 +1298,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 		goto err_out;
 
 	bpf_map_inc(new_map);
-	rcu_assign_pointer(st_link->map, new_map);
+	WRITE_ONCE(st_link->map, new_map);
 	bpf_map_put(old_map);
 
 err_out:
@@ -1316,7 +1315,7 @@ static int bpf_struct_ops_map_link_detach(struct bpf_link *link)
 
 	mutex_lock(&update_mutex);
 
-	map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
+	map = st_link->map;
 	if (!map) {
 		mutex_unlock(&update_mutex);
 		return 0;
@@ -1325,7 +1324,7 @@ static int bpf_struct_ops_map_link_detach(struct bpf_link *link)
 
 	st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, link);
 
-	RCU_INIT_POINTER(st_link->map, NULL);
+	WRITE_ONCE(st_link->map, NULL);
 	/* Pair with bpf_map_get() in bpf_struct_ops_link_create() or
 	 * bpf_map_inc() in bpf_struct_ops_map_link_update().
 	 */
@@ -1345,7 +1344,7 @@ static __poll_t bpf_struct_ops_map_link_poll(struct file *file,
 
 	poll_wait(file, &st_link->wait_hup, pts);
 
-	return rcu_access_pointer(st_link->map) ? 0 : EPOLLHUP;
+	return READ_ONCE(st_link->map) ? 0 : EPOLLHUP;
 }
 
 static const struct bpf_link_ops bpf_struct_ops_map_lops = {
@@ -1401,7 +1400,7 @@ int bpf_struct_ops_link_create(union bpf_attr *attr)
 		link = NULL;
 		goto err_out;
 	}
-	RCU_INIT_POINTER(link->map, map);
+	link->map = map;
 	mutex_unlock(&update_mutex);
 
 	return bpf_link_settle(&link_primer);
-- 
2.53.0-Meta


  reply	other threads:[~2026-05-19 21:59 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-19 21:58 [RFC PATCH bpf-next 00/12] bpf: A common way to attach struct_ops to a cgroup Martin KaFai Lau
2026-05-19 21:58 ` Martin KaFai Lau [this message]
2026-05-19 21:58 ` [RFC PATCH bpf-next 02/12] bpf: Make struct_ops tasks_rcu grace period optional Martin KaFai Lau
2026-05-19 21:58 ` [RFC PATCH bpf-next 03/12] bpf: Add bpf_struct_ops accessor helpers Martin KaFai Lau
2026-05-19 21:58 ` [RFC PATCH bpf-next 04/12] bpf: Remove unnecessary prog_list_prog() check Martin KaFai Lau
2026-05-19 21:58 ` [RFC PATCH bpf-next 05/12] bpf: Replace prog_list_prog() check with direct pl->prog and pl->link check Martin KaFai Lau
2026-05-19 21:58 ` [RFC PATCH bpf-next 06/12] bpf: Add prog_list_init_item(), prog_list_replace_item(), and prog_list_id() Martin KaFai Lau
2026-05-19 21:58 ` [RFC PATCH bpf-next 07/12] bpf: Move LSM trampoline unlink into bpf_cgroup_link_auto_detach() Martin KaFai Lau
2026-05-19 21:58 ` [RFC PATCH bpf-next 08/12] bpf: Add a few bpf_cgroup_array_* helper functions Martin KaFai Lau
2026-05-19 21:58 ` [RFC PATCH bpf-next 09/12] bpf: Add infrastructure to support attaching struct_ops to cgroups Martin KaFai Lau
2026-05-19 21:58 ` [RFC PATCH bpf-next 10/12] bpf: tcp: Support selected sock_ops callbacks as struct_ops Martin KaFai Lau
2026-05-19 21:58 ` [RFC PATCH bpf-next 11/12] libbpf: Support attaching struct_ops to a cgroup Martin KaFai Lau
2026-05-19 21:58 ` [RFC PATCH bpf-next 12/12] selftests/bpf: Test " Martin KaFai Lau

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260519215841.2984970-2-martin.lau@linux.dev \
    --to=martin.lau@linux.dev \
    --cc=ameryhung@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=netdev@vger.kernel.org \
    --cc=roman.gushchin@linux.dev \
    --cc=shakeel.butt@linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox