From: Gang Yan <gang.yan@linux.dev>
To: mptcp@lists.linux.dev
Cc: Gang Yan <yangang@kylinos.cn>, Tao Cui <cuitao@kylinos.cn>
Subject: [PATCH mptcp-next 1/3] mptcp: sched: change scheduler sysctl atomically
Date: Mon, 17 Aug 2026 09:24:50 +0800 [thread overview]
Message-ID: <20260817012452.7519-2-gang.yan@linux.dev> (raw)
In-Reply-To: <20260817012452.7519-1-gang.yan@linux.dev>
From: Gang Yan <yangang@kylinos.cn>
The per-netns scheduler name is stored as an inline char[] buffer and
updated via strscpy() from the sysctl handler. A concurrent reader (e.g.
mptcp_init_sock() resolving the default scheduler) can observe a
half-written name, which is also flagged by KCSAN. READ_ONCE() does not
help here as it cannot read a multi-byte string atomically.
Following the tcp_congestion_control() model, store a pointer to the
immutable struct mptcp_sched_ops instead of the name string:
- mptcp_set_scheduler() now looks the ops up, takes a module reference,
and atomically swaps the pernet pointer with xchg(), releasing the
previous reference;
- mptcp_get_scheduler() copies the ops name out under rcu_read_lock();
- the default reference is taken in mptcp_pernet_set_defaults() and
released in mptcp_net_exit(), mirroring tcp_sk_init()/tcp_sk_exit().
A pointer store is a single atomic word, so readers always observe a
consistent value.
Assisted-by: Claude:GLM5.2
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/626
Co-developed-by: Tao Cui <cuitao@kylinos.cn>
Signed-off-by: Tao Cui <cuitao@kylinos.cn>
Signed-off-by: Gang Yan <yangang@kylinos.cn>
---
net/mptcp/ctrl.c | 50 +++++++++++++++++++++++++++++++++-----------
net/mptcp/protocol.c | 5 +++--
net/mptcp/protocol.h | 3 ++-
net/mptcp/sched.c | 2 +-
4 files changed, 44 insertions(+), 16 deletions(-)
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 63c5747f0f63..85e9d3e996db 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -39,7 +39,7 @@ struct mptcp_pernet {
u8 allow_join_initial_addr_port;
u8 pm_type;
u8 add_addr_v6_port_drop_ts;
- char scheduler[MPTCP_SCHED_NAME_MAX];
+ struct mptcp_sched_ops __rcu *scheduler;
char path_manager[MPTCP_PM_NAME_MAX];
};
@@ -90,9 +90,14 @@ const char *mptcp_get_path_manager(const struct net *net)
return mptcp_get_pernet(net)->path_manager;
}
-const char *mptcp_get_scheduler(const struct net *net)
+void mptcp_get_scheduler(const struct net *net, char *name)
{
- return mptcp_get_pernet(net)->scheduler;
+ struct mptcp_sched_ops *sched;
+
+ rcu_read_lock();
+ sched = rcu_dereference(mptcp_get_pernet(net)->scheduler);
+ strscpy(name, sched ? sched->name : "default", MPTCP_SCHED_NAME_MAX);
+ rcu_read_unlock();
}
unsigned int mptcp_add_addr_v6_port_drop_ts(const struct net *net)
@@ -112,23 +117,33 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
pernet->allow_join_initial_addr_port = 1;
pernet->stale_loss_cnt = 4;
pernet->pm_type = MPTCP_PM_TYPE_KERNEL;
- strscpy(pernet->scheduler, "default", sizeof(pernet->scheduler));
+
+ if (bpf_try_module_get(&mptcp_sched_default, mptcp_sched_default.owner))
+ RCU_INIT_POINTER(pernet->scheduler, &mptcp_sched_default);
+
strscpy(pernet->path_manager, "kernel", sizeof(pernet->path_manager));
pernet->add_addr_v6_port_drop_ts = 1;
}
#ifdef CONFIG_SYSCTL
-static int mptcp_set_scheduler(char *scheduler, const char *name)
+static int mptcp_set_scheduler(struct mptcp_pernet *pernet, const char *name)
{
- struct mptcp_sched_ops *sched;
+ struct mptcp_sched_ops *sched, *prev;
int ret = 0;
rcu_read_lock();
sched = mptcp_sched_find(name);
- if (sched)
- strscpy(scheduler, name, MPTCP_SCHED_NAME_MAX);
- else
+ if (sched) {
+ if (bpf_try_module_get(sched, sched->owner)) {
+ prev = xchg(&pernet->scheduler, sched);
+ if (prev)
+ bpf_module_put(prev, prev->owner);
+ } else {
+ ret = -EBUSY;
+ }
+ } else {
ret = -ENOENT;
+ }
rcu_read_unlock();
return ret;
@@ -137,7 +152,10 @@ static int mptcp_set_scheduler(char *scheduler, const char *name)
static int proc_scheduler(const struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
- char (*scheduler)[MPTCP_SCHED_NAME_MAX] = ctl->data;
+ struct mptcp_pernet *pernet = container_of(ctl->data,
+ struct mptcp_pernet,
+ scheduler);
+ struct mptcp_sched_ops *sched;
char val[MPTCP_SCHED_NAME_MAX];
struct ctl_table tbl = {
.data = val,
@@ -145,11 +163,14 @@ static int proc_scheduler(const struct ctl_table *ctl, int write,
};
int ret;
- strscpy(val, *scheduler, MPTCP_SCHED_NAME_MAX);
+ rcu_read_lock();
+ sched = rcu_dereference(pernet->scheduler);
+ strscpy(val, sched ? sched->name : "default", MPTCP_SCHED_NAME_MAX);
+ rcu_read_unlock();
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0)
- ret = mptcp_set_scheduler(*scheduler, val);
+ ret = mptcp_set_scheduler(pernet, val);
return ret;
}
@@ -573,8 +594,13 @@ static int __net_init mptcp_net_init(struct net *net)
static void __net_exit mptcp_net_exit(struct net *net)
{
struct mptcp_pernet *pernet = mptcp_get_pernet(net);
+ struct mptcp_sched_ops *sched;
mptcp_pernet_del_table(pernet);
+
+ sched = rcu_dereference_protected(pernet->scheduler, true);
+ if (sched)
+ bpf_module_put(sched, sched->owner);
}
static struct pernet_operations mptcp_pernet_ops = {
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index f879b1061f2d..9d84dd803802 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3260,6 +3260,7 @@ static void mptcp_ca_reset(struct sock *sk)
static int mptcp_init_sock(struct sock *sk)
{
struct net *net = sock_net(sk);
+ char sched_name[MPTCP_SCHED_NAME_MAX];
int ret;
__mptcp_init_sock(sk);
@@ -3271,8 +3272,8 @@ static int mptcp_init_sock(struct sock *sk)
return -ENOMEM;
rcu_read_lock();
- ret = mptcp_init_sched(mptcp_sk(sk),
- mptcp_sched_find(mptcp_get_scheduler(net)));
+ mptcp_get_scheduler(net, sched_name);
+ ret = mptcp_init_sched(mptcp_sk(sk), mptcp_sched_find(sched_name));
rcu_read_unlock();
if (ret)
return ret;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 7e168e450fb0..af79b3450ab7 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -803,7 +803,7 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net);
unsigned int mptcp_close_timeout(const struct sock *sk);
int mptcp_get_pm_type(const struct net *net);
const char *mptcp_get_path_manager(const struct net *net);
-const char *mptcp_get_scheduler(const struct net *net);
+void mptcp_get_scheduler(const struct net *net, char *name);
unsigned int mptcp_add_addr_v6_port_drop_ts(const struct net *net);
void mptcp_active_disable(struct sock *sk);
@@ -1155,6 +1155,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
/* the default path manager, used in mptcp_pm_unregister */
extern struct mptcp_pm_ops mptcp_pm_kernel;
+extern struct mptcp_sched_ops mptcp_sched_default;
struct mptcp_pm_ops *mptcp_pm_find(const char *name);
int mptcp_pm_register(struct mptcp_pm_ops *pm_ops);
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 1e59072d478c..0d13ee46ffdf 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -40,7 +40,7 @@ static int mptcp_sched_default_get_retrans(struct mptcp_sock *msk)
return 0;
}
-static struct mptcp_sched_ops mptcp_sched_default = {
+struct mptcp_sched_ops mptcp_sched_default = {
.get_send = mptcp_sched_default_get_send,
.get_retrans = mptcp_sched_default_get_retrans,
.name = "default",
--
2.43.0
next prev parent reply other threads:[~2026-08-17 1:25 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-17 1:24 [PATCH mptcp-next 0/3] mptcp: avoid data-races around the sysctls Gang Yan
2026-08-17 1:24 ` Gang Yan [this message]
2026-08-17 1:24 ` [PATCH mptcp-next 2/3] mptcp: pm: change path_manager sysctl atomically Gang Yan
2026-08-17 1:24 ` [PATCH mptcp-next 3/3] mptcp: use READ_ONCE() over sysctls Gang Yan
2026-08-17 2:31 ` [PATCH mptcp-next 0/3] mptcp: avoid data-races around the sysctls MPTCP CI
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=20260817012452.7519-2-gang.yan@linux.dev \
--to=gang.yan@linux.dev \
--cc=cuitao@kylinos.cn \
--cc=mptcp@lists.linux.dev \
--cc=yangang@kylinos.cn \
/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