From: Kui-Feng Lee <kuifeng@meta.com>
To: <bpf@vger.kernel.org>, <ast@kernel.org>, <martin.lau@linux.dev>,
<song@kernel.org>, <kernel-team@meta.com>, <andrii@kernel.org>,
<sdf@google.com>
Cc: Kui-Feng Lee <kuifeng@meta.com>
Subject: [PATCH bpf-next v6 5/8] bpf: Update the struct_ops of a bpf_link.
Date: Thu, 9 Mar 2023 20:38:10 -0800 [thread overview]
Message-ID: <20230310043812.3087672-6-kuifeng@meta.com> (raw)
In-Reply-To: <20230310043812.3087672-1-kuifeng@meta.com>
By improving the BPF_LINK_UPDATE command of bpf(), it should allow you
to conveniently switch between different struct_ops on a single
bpf_link. This would enable smoother transitions from one struct_ops
to another.
The struct_ops maps passing along with BPF_LINK_UPDATE should have the
BPF_F_LINK flag.
Signed-off-by: Kui-Feng Lee <kuifeng@meta.com>
---
include/linux/bpf.h | 1 +
include/uapi/linux/bpf.h | 8 +++++--
kernel/bpf/bpf_struct_ops.c | 40 ++++++++++++++++++++++++++++++++++
kernel/bpf/syscall.c | 20 +++++++++++++++++
tools/include/uapi/linux/bpf.h | 8 +++++--
5 files changed, 73 insertions(+), 4 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 38f0c8ff726f..c3ef680cafd9 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1469,6 +1469,7 @@ struct bpf_link_ops {
void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq);
int (*fill_link_info)(const struct bpf_link *link,
struct bpf_link_info *info);
+ int (*update_map)(struct bpf_link *link, struct bpf_map *new_map);
};
struct bpf_tramp_link {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index dedd948de6a2..1539a7bdb83e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1555,8 +1555,12 @@ union bpf_attr {
struct { /* struct used by BPF_LINK_UPDATE command */
__u32 link_fd; /* link fd */
- /* new program fd to update link with */
- __u32 new_prog_fd;
+ union {
+ /* new program fd to update link with */
+ __u32 new_prog_fd;
+ /* new struct_ops map fd to update link with */
+ __u32 new_map_fd;
+ };
__u32 flags; /* extra flags */
/* expected link's program fd; is specified only if
* BPF_F_REPLACE flag is set in flags */
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 888d6aefc31a..70202c85f8d9 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -64,6 +64,8 @@ struct bpf_struct_ops_link {
struct bpf_map __rcu *map;
};
+static DEFINE_MUTEX(update_mutex);
+
#define VALUE_PREFIX "bpf_struct_ops_"
#define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1)
@@ -793,10 +795,48 @@ static int bpf_struct_ops_map_link_fill_link_info(const struct bpf_link *link,
return 0;
}
+static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map *new_map)
+{
+ struct bpf_struct_ops_map *st_map, *old_st_map;
+ struct bpf_struct_ops_link *st_link;
+ struct bpf_map *old_map;
+ int err = 0;
+
+ st_link = container_of(link, struct bpf_struct_ops_link, link);
+ st_map = container_of(new_map, struct bpf_struct_ops_map, map);
+
+ if (!bpf_struct_ops_valid_to_reg(new_map))
+ return -EINVAL;
+
+ mutex_lock(&update_mutex);
+
+ old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
+ old_st_map = container_of(old_map, struct bpf_struct_ops_map, map);
+ /* The new and old struct_ops must be the same type. */
+ if (st_map->st_ops != old_st_map->st_ops) {
+ err = -EINVAL;
+ goto err_out;
+ }
+
+ err = st_map->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data);
+ if (err)
+ goto err_out;
+
+ bpf_map_inc(new_map);
+ rcu_assign_pointer(st_link->map, new_map);
+ bpf_map_put(old_map);
+
+err_out:
+ mutex_unlock(&update_mutex);
+
+ return err;
+}
+
static const struct bpf_link_ops bpf_struct_ops_map_lops = {
.dealloc = bpf_struct_ops_map_link_dealloc,
.show_fdinfo = bpf_struct_ops_map_link_show_fdinfo,
.fill_link_info = bpf_struct_ops_map_link_fill_link_info,
+ .update_map = bpf_struct_ops_map_link_update,
};
int bpf_struct_ops_link_create(union bpf_attr *attr)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8d473af5ff42..f2602787dc43 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4660,6 +4660,21 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
return ret;
}
+static int link_update_map(struct bpf_link *link, union bpf_attr *attr)
+{
+ struct bpf_map *new_map;
+ int ret = 0;
+
+ new_map = bpf_map_get(attr->link_update.new_map_fd);
+ if (IS_ERR(new_map))
+ return -EINVAL;
+
+ ret = link->ops->update_map(link, new_map);
+
+ bpf_map_put(new_map);
+ return ret;
+}
+
#define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd
static int link_update(union bpf_attr *attr)
@@ -4680,6 +4695,11 @@ static int link_update(union bpf_attr *attr)
if (IS_ERR(link))
return PTR_ERR(link);
+ if (link->ops->update_map) {
+ ret = link_update_map(link, attr);
+ goto out_put_link;
+ }
+
new_prog = bpf_prog_get(attr->link_update.new_prog_fd);
if (IS_ERR(new_prog)) {
ret = PTR_ERR(new_prog);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e75a3f66e9db..c53c685231a9 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1555,8 +1555,12 @@ union bpf_attr {
struct { /* struct used by BPF_LINK_UPDATE command */
__u32 link_fd; /* link fd */
- /* new program fd to update link with */
- __u32 new_prog_fd;
+ union {
+ /* new program fd to update link with */
+ __u32 new_prog_fd;
+ /* new struct_ops map fd to update link with */
+ __u32 new_map_fd;
+ };
__u32 flags; /* extra flags */
/* expected link's program fd; is specified only if
* BPF_F_REPLACE flag is set in flags */
--
2.34.1
next prev parent reply other threads:[~2023-03-10 4:39 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-10 4:38 [PATCH bpf-next v6 0/8] Transit between BPF TCP congestion controls Kui-Feng Lee
2023-03-10 4:38 ` [PATCH bpf-next v6 1/8] bpf: Retire the struct_ops map kvalue->refcnt Kui-Feng Lee
2023-03-14 6:05 ` Martin KaFai Lau
2023-03-10 4:38 ` [PATCH bpf-next v6 2/8] net: Update an existing TCP congestion control algorithm Kui-Feng Lee
2023-03-10 16:47 ` Stephen Hemminger
2023-03-13 15:46 ` Kui-Feng Lee
2023-03-13 16:43 ` Kui-Feng Lee
2023-03-14 0:28 ` Martin KaFai Lau
2023-03-14 4:31 ` Kui-Feng Lee
2023-03-10 4:38 ` [PATCH bpf-next v6 3/8] bpf: Create links for BPF struct_ops maps Kui-Feng Lee
2023-03-14 1:42 ` Martin KaFai Lau
2023-03-16 0:21 ` Kui-Feng Lee
2023-03-10 4:38 ` [PATCH bpf-next v6 4/8] libbpf: Create a bpf_link in bpf_map__attach_struct_ops() Kui-Feng Lee
2023-03-10 4:38 ` Kui-Feng Lee [this message]
2023-03-10 4:38 ` [PATCH bpf-next v6 6/8] libbpf: Update a bpf_link with another struct_ops Kui-Feng Lee
2023-03-10 4:38 ` [PATCH bpf-next v6 7/8] libbpf: Use .struct_ops.link section to indicate a struct_ops with a link Kui-Feng Lee
2023-03-10 4:38 ` [PATCH bpf-next v6 8/8] selftests/bpf: Test switching TCP Congestion Control algorithms Kui-Feng Lee
2023-03-14 5:04 ` Martin KaFai Lau
2023-03-10 16:28 ` [PATCH bpf-next v6 0/8] Transit between BPF TCP congestion controls Kui-Feng Lee
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=20230310043812.3087672-6-kuifeng@meta.com \
--to=kuifeng@meta.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=kernel-team@meta.com \
--cc=martin.lau@linux.dev \
--cc=sdf@google.com \
--cc=song@kernel.org \
/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