summaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/mptcp_diag.c2
-rw-r--r--net/mptcp/pm_netlink.c4
-rw-r--r--net/mptcp/protocol.c57
-rw-r--r--net/mptcp/protocol.h2
-rw-r--r--net/mptcp/subflow.c2
-rw-r--r--net/mptcp/syncookies.c13
-rw-r--r--net/mptcp/token.c11
-rw-r--r--net/mptcp/token_test.c14
8 files changed, 37 insertions, 68 deletions
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index f48eb6315bbb..292374fb0779 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -36,7 +36,7 @@ static int mptcp_diag_dump_one(struct netlink_callback *cb,
struct sock *sk;
net = sock_net(in_skb->sk);
- msk = mptcp_token_get_sock(req->id.idiag_cookie[0]);
+ msk = mptcp_token_get_sock(net, req->id.idiag_cookie[0]);
if (!msk)
goto out_nosk;
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index c4f9a5ce3815..050eea231528 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1718,9 +1718,7 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
list_for_each_entry(entry, &pernet->local_addr_list, list) {
if (addresses_equal(&entry->addr, &addr.addr, true)) {
- ret = mptcp_nl_addr_backup(net, &entry->addr, bkup);
- if (ret)
- return ret;
+ mptcp_nl_addr_backup(net, &entry->addr, bkup);
if (bkup)
entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index dbcebf56798f..d073b2111382 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -528,7 +528,6 @@ static bool mptcp_check_data_fin(struct sock *sk)
sk->sk_shutdown |= RCV_SHUTDOWN;
smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
- set_bit(MPTCP_DATA_READY, &msk->flags);
switch (sk->sk_state) {
case TCP_ESTABLISHED:
@@ -742,10 +741,9 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
- if (move_skbs_to_msk(msk, ssk)) {
- set_bit(MPTCP_DATA_READY, &msk->flags);
+ if (move_skbs_to_msk(msk, ssk))
sk->sk_data_ready(sk);
- }
+
mptcp_data_unlock(sk);
}
@@ -847,7 +845,6 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
sk->sk_shutdown |= RCV_SHUTDOWN;
smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
- set_bit(MPTCP_DATA_READY, &msk->flags);
sk->sk_data_ready(sk);
}
@@ -1759,21 +1756,6 @@ out:
return copied ? : ret;
}
-static void mptcp_wait_data(struct sock *sk, long *timeo)
-{
- DEFINE_WAIT_FUNC(wait, woken_wake_function);
- struct mptcp_sock *msk = mptcp_sk(sk);
-
- add_wait_queue(sk_sleep(sk), &wait);
- sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-
- sk_wait_event(sk, timeo,
- test_bit(MPTCP_DATA_READY, &msk->flags), &wait);
-
- sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- remove_wait_queue(sk_sleep(sk), &wait);
-}
-
static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
struct msghdr *msg,
size_t len, int flags,
@@ -2077,19 +2059,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
}
pr_debug("block timeout %ld", timeo);
- mptcp_wait_data(sk, &timeo);
- }
-
- if (skb_queue_empty_lockless(&sk->sk_receive_queue) &&
- skb_queue_empty(&msk->receive_queue)) {
- /* entire backlog drained, clear DATA_READY. */
- clear_bit(MPTCP_DATA_READY, &msk->flags);
-
- /* .. race-breaker: ssk might have gotten new data
- * after last __mptcp_move_skbs() returned false.
- */
- if (unlikely(__mptcp_move_skbs(msk)))
- set_bit(MPTCP_DATA_READY, &msk->flags);
+ sk_wait_data(sk, &timeo, NULL);
}
out_err:
@@ -2098,9 +2068,9 @@ out_err:
tcp_recv_timestamp(msg, sk, &tss);
}
- pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d",
- msk, test_bit(MPTCP_DATA_READY, &msk->flags),
- skb_queue_empty_lockless(&sk->sk_receive_queue), copied);
+ pr_debug("msk=%p rx queue empty=%d:%d copied=%d",
+ msk, skb_queue_empty_lockless(&sk->sk_receive_queue),
+ skb_queue_empty(&msk->receive_queue), copied);
if (!(flags & MSG_PEEK))
mptcp_rcv_space_adjust(msk, copied);
@@ -2368,7 +2338,6 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
inet_sk_state_store(sk, TCP_CLOSE);
sk->sk_shutdown = SHUTDOWN_MASK;
smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
- set_bit(MPTCP_DATA_READY, &msk->flags);
set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
mptcp_close_wake_up(sk);
@@ -2735,7 +2704,7 @@ cleanup:
inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- bool slow = lock_sock_fast(ssk);
+ bool slow = lock_sock_fast_nested(ssk);
sock_orphan(ssk);
unlock_sock_fast(ssk, slow);
@@ -3385,8 +3354,14 @@ unlock_fail:
static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
{
- return test_bit(MPTCP_DATA_READY, &msk->flags) ? EPOLLIN | EPOLLRDNORM :
- 0;
+ /* Concurrent splices from sk_receive_queue into receive_queue will
+ * always show at least one non-empty queue when checked in this order.
+ */
+ if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) &&
+ skb_queue_empty_lockless(&msk->receive_queue))
+ return 0;
+
+ return EPOLLIN | EPOLLRDNORM;
}
static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
@@ -3421,7 +3396,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
state = inet_sk_state_load(sk);
pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
if (state == TCP_LISTEN)
- return mptcp_check_readable(msk);
+ return test_bit(MPTCP_DATA_READY, &msk->flags) ? EPOLLIN | EPOLLRDNORM : 0;
if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
mask |= mptcp_check_readable(msk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d3e6fd1615f1..dc984676c5eb 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -709,7 +709,7 @@ int mptcp_token_new_connect(struct sock *sk);
void mptcp_token_accept(struct mptcp_subflow_request_sock *r,
struct mptcp_sock *msk);
bool mptcp_token_exists(u32 token);
-struct mptcp_sock *mptcp_token_get_sock(u32 token);
+struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token);
struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot,
long *s_num);
void mptcp_token_destroy(struct mptcp_sock *msk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 1de7ce883c37..6172f380dfb7 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -86,7 +86,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
struct mptcp_sock *msk;
int local_id;
- msk = mptcp_token_get_sock(subflow_req->token);
+ msk = mptcp_token_get_sock(sock_net(req_to_sk(req)), subflow_req->token);
if (!msk) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN);
return NULL;
diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c
index 37127781aee9..7f22526346a7 100644
--- a/net/mptcp/syncookies.c
+++ b/net/mptcp/syncookies.c
@@ -108,18 +108,12 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl
e->valid = 0;
- msk = mptcp_token_get_sock(e->token);
+ msk = mptcp_token_get_sock(net, e->token);
if (!msk) {
spin_unlock_bh(&join_entry_locks[i]);
return false;
}
- /* If this fails, the token got re-used in the mean time by another
- * mptcp socket in a different netns, i.e. entry is outdated.
- */
- if (!net_eq(sock_net((struct sock *)msk), net))
- goto err_put;
-
subflow_req->remote_nonce = e->remote_nonce;
subflow_req->local_nonce = e->local_nonce;
subflow_req->backup = e->backup;
@@ -128,11 +122,6 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl
subflow_req->msk = msk;
spin_unlock_bh(&join_entry_locks[i]);
return true;
-
-err_put:
- spin_unlock_bh(&join_entry_locks[i]);
- sock_put((struct sock *)msk);
- return false;
}
void __init mptcp_join_cookie_init(void)
diff --git a/net/mptcp/token.c b/net/mptcp/token.c
index a98e554b034f..e581b341c5be 100644
--- a/net/mptcp/token.c
+++ b/net/mptcp/token.c
@@ -231,6 +231,7 @@ found:
/**
* mptcp_token_get_sock - retrieve mptcp connection sock using its token
+ * @net: restrict to this namespace
* @token: token of the mptcp connection to retrieve
*
* This function returns the mptcp connection structure with the given token.
@@ -238,7 +239,7 @@ found:
*
* returns NULL if no connection with the given token value exists.
*/
-struct mptcp_sock *mptcp_token_get_sock(u32 token)
+struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token)
{
struct hlist_nulls_node *pos;
struct token_bucket *bucket;
@@ -251,11 +252,15 @@ struct mptcp_sock *mptcp_token_get_sock(u32 token)
again:
sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) {
msk = mptcp_sk(sk);
- if (READ_ONCE(msk->token) != token)
+ if (READ_ONCE(msk->token) != token ||
+ !net_eq(sock_net(sk), net))
continue;
+
if (!refcount_inc_not_zero(&sk->sk_refcnt))
goto not_found;
- if (READ_ONCE(msk->token) != token) {
+
+ if (READ_ONCE(msk->token) != token ||
+ !net_eq(sock_net(sk), net)) {
sock_put(sk);
goto again;
}
diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c
index e1bd6f0a0676..5d984bec1cd8 100644
--- a/net/mptcp/token_test.c
+++ b/net/mptcp/token_test.c
@@ -11,6 +11,7 @@ static struct mptcp_subflow_request_sock *build_req_sock(struct kunit *test)
GFP_USER);
KUNIT_EXPECT_NOT_ERR_OR_NULL(test, req);
mptcp_token_init_request((struct request_sock *)req);
+ sock_net_set((struct sock *)req, &init_net);
return req;
}
@@ -22,7 +23,7 @@ static void mptcp_token_test_req_basic(struct kunit *test)
KUNIT_ASSERT_EQ(test, 0,
mptcp_token_new_request((struct request_sock *)req));
KUNIT_EXPECT_NE(test, 0, (int)req->token);
- KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(req->token));
+ KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, req->token));
/* cleanup */
mptcp_token_destroy_request((struct request_sock *)req);
@@ -55,6 +56,7 @@ static struct mptcp_sock *build_msk(struct kunit *test)
msk = kunit_kzalloc(test, sizeof(struct mptcp_sock), GFP_USER);
KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk);
refcount_set(&((struct sock *)msk)->sk_refcnt, 1);
+ sock_net_set((struct sock *)msk, &init_net);
return msk;
}
@@ -74,11 +76,11 @@ static void mptcp_token_test_msk_basic(struct kunit *test)
mptcp_token_new_connect((struct sock *)icsk));
KUNIT_EXPECT_NE(test, 0, (int)ctx->token);
KUNIT_EXPECT_EQ(test, ctx->token, msk->token);
- KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(ctx->token));
+ KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, ctx->token));
KUNIT_EXPECT_EQ(test, 2, (int)refcount_read(&sk->sk_refcnt));
mptcp_token_destroy(msk);
- KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(ctx->token));
+ KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, ctx->token));
}
static void mptcp_token_test_accept(struct kunit *test)
@@ -90,11 +92,11 @@ static void mptcp_token_test_accept(struct kunit *test)
mptcp_token_new_request((struct request_sock *)req));
msk->token = req->token;
mptcp_token_accept(req, msk);
- KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token));
+ KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token));
/* this is now a no-op */
mptcp_token_destroy_request((struct request_sock *)req);
- KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token));
+ KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token));
/* cleanup */
mptcp_token_destroy(msk);
@@ -116,7 +118,7 @@ static void mptcp_token_test_destroyed(struct kunit *test)
/* simulate race on removal */
refcount_set(&sk->sk_refcnt, 0);
- KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(msk->token));
+ KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, msk->token));
/* cleanup */
mptcp_token_destroy(msk);
generated by cgit v1.2.3 (git 2.25.1) at 2025-03-26 09:11:02 +0000