aboutsummaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/pm_userspace.c6
-rw-r--r--net/mptcp/protocol.c71
-rw-r--r--net/mptcp/protocol.h35
-rw-r--r--net/mptcp/subflow.c10
4 files changed, 57 insertions, 65 deletions
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index b5a8aa4c1ebd..d042d32beb4d 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -307,12 +307,6 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info)
goto create_err;
}
- if (addr_l.id == 0) {
- NL_SET_ERR_MSG_ATTR(info->extack, laddr, "missing local addr id");
- err = -EINVAL;
- goto create_err;
- }
-
err = mptcp_pm_parse_addr(raddr, info, &addr_r);
if (err < 0) {
NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr");
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e252539b1e19..886ab689a8ae 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1298,7 +1298,7 @@ alloc_skb:
if (copy == 0) {
u64 snd_una = READ_ONCE(msk->snd_una);
- if (snd_una != msk->snd_nxt) {
+ if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) {
tcp_remove_empty_skb(ssk);
return 0;
}
@@ -1306,11 +1306,6 @@ alloc_skb:
zero_window_probe = true;
data_seq = snd_una - 1;
copy = 1;
-
- /* all mptcp-level data is acked, no skbs should be present into the
- * ssk write queue
- */
- WARN_ON_ONCE(reuse_skb);
}
copy = min_t(size_t, copy, info->limit - info->sent);
@@ -1339,7 +1334,6 @@ alloc_skb:
if (reuse_skb) {
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
mpext->data_len += copy;
- WARN_ON_ONCE(zero_window_probe);
goto out;
}
@@ -2354,6 +2348,26 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
#define MPTCP_CF_PUSH BIT(1)
#define MPTCP_CF_FASTCLOSE BIT(2)
+/* be sure to send a reset only if the caller asked for it, also
+ * clean completely the subflow status when the subflow reaches
+ * TCP_CLOSE state
+ */
+static void __mptcp_subflow_disconnect(struct sock *ssk,
+ struct mptcp_subflow_context *subflow,
+ unsigned int flags)
+{
+ if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+ (flags & MPTCP_CF_FASTCLOSE)) {
+ /* The MPTCP code never wait on the subflow sockets, TCP-level
+ * disconnect should never fail
+ */
+ WARN_ON_ONCE(tcp_disconnect(ssk, 0));
+ mptcp_subflow_ctx_reset(subflow);
+ } else {
+ tcp_shutdown(ssk, SEND_SHUTDOWN);
+ }
+}
+
/* subflow sockets can be either outgoing (connect) or incoming
* (accept).
*
@@ -2391,7 +2405,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) {
- /* be sure to force the tcp_disconnect() path,
+ /* be sure to force the tcp_close path
* to generate the egress reset
*/
ssk->sk_lingertime = 0;
@@ -2401,11 +2415,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
if (!dispose_it) {
- /* The MPTCP code never wait on the subflow sockets, TCP-level
- * disconnect should never fail
- */
- WARN_ON_ONCE(tcp_disconnect(ssk, 0));
- mptcp_subflow_ctx_reset(subflow);
+ __mptcp_subflow_disconnect(ssk, subflow, flags);
release_sock(ssk);
goto out;
@@ -3098,12 +3108,6 @@ static int mptcp_disconnect(struct sock *sk, int flags)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- /* Deny disconnect if other threads are blocked in sk_wait_event()
- * or inet_wait_for_connect().
- */
- if (sk->sk_wait_pending)
- return -EBUSY;
-
/* We are on the fastopen error path. We can't call straight into the
* subflows cleanup code due to lock nesting (we are already under
* msk->firstsocket lock).
@@ -3173,7 +3177,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk);
#endif
- nsk->sk_wait_pending = 0;
__mptcp_init_sock(nsk);
msk = mptcp_sk(nsk);
@@ -3425,24 +3428,21 @@ static void schedule_3rdack_retransmission(struct sock *ssk)
sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout);
}
-void mptcp_subflow_process_delegated(struct sock *ssk)
+void mptcp_subflow_process_delegated(struct sock *ssk, long status)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct sock *sk = subflow->conn;
- if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
+ if (status & BIT(MPTCP_DELEGATE_SEND)) {
mptcp_data_lock(sk);
if (!sock_owned_by_user(sk))
__mptcp_subflow_push_pending(sk, ssk, true);
else
__set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags);
mptcp_data_unlock(sk);
- mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND);
}
- if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) {
+ if (status & BIT(MPTCP_DELEGATE_ACK))
schedule_3rdack_retransmission(ssk);
- mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK);
- }
}
static int mptcp_hash(struct sock *sk)
@@ -3968,14 +3968,17 @@ static int mptcp_napi_poll(struct napi_struct *napi, int budget)
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bh_lock_sock_nested(ssk);
- if (!sock_owned_by_user(ssk) &&
- mptcp_subflow_has_delegated_action(subflow))
- mptcp_subflow_process_delegated(ssk);
- /* ... elsewhere tcp_release_cb_override already processed
- * the action or will do at next release_sock().
- * In both case must dequeue the subflow here - on the same
- * CPU that scheduled it.
- */
+ if (!sock_owned_by_user(ssk)) {
+ mptcp_subflow_process_delegated(ssk, xchg(&subflow->delegated_status, 0));
+ } else {
+ /* tcp_release_cb_override already processed
+ * the action or will do at next release_sock().
+ * In both case must dequeue the subflow here - on the same
+ * CPU that scheduled it.
+ */
+ smp_wmb();
+ clear_bit(MPTCP_DELEGATE_SCHEDULED, &subflow->delegated_status);
+ }
bh_unlock_sock(ssk);
sock_put(ssk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index ed61d6850cce..3612545fa62e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -444,9 +444,11 @@ struct mptcp_delegated_action {
DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
-#define MPTCP_DELEGATE_SEND 0
-#define MPTCP_DELEGATE_ACK 1
+#define MPTCP_DELEGATE_SCHEDULED 0
+#define MPTCP_DELEGATE_SEND 1
+#define MPTCP_DELEGATE_ACK 2
+#define MPTCP_DELEGATE_ACTIONS_MASK (~BIT(MPTCP_DELEGATE_SCHEDULED))
/* MPTCP subflow context */
struct mptcp_subflow_context {
struct list_head node;/* conn_list of subflows */
@@ -564,23 +566,24 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
return subflow->map_seq + mptcp_subflow_get_map_offset(subflow);
}
-void mptcp_subflow_process_delegated(struct sock *ssk);
+void mptcp_subflow_process_delegated(struct sock *ssk, long actions);
static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action)
{
+ long old, set_bits = BIT(MPTCP_DELEGATE_SCHEDULED) | BIT(action);
struct mptcp_delegated_action *delegated;
bool schedule;
/* the caller held the subflow bh socket lock */
lockdep_assert_in_softirq();
- /* The implied barrier pairs with mptcp_subflow_delegated_done(), and
- * ensures the below list check sees list updates done prior to status
- * bit changes
+ /* The implied barrier pairs with tcp_release_cb_override()
+ * mptcp_napi_poll(), and ensures the below list check sees list
+ * updates done prior to delegated status bits changes
*/
- if (!test_and_set_bit(action, &subflow->delegated_status)) {
- /* still on delegated list from previous scheduling */
- if (!list_empty(&subflow->delegated_node))
+ old = set_mask_bits(&subflow->delegated_status, 0, set_bits);
+ if (!(old & BIT(MPTCP_DELEGATE_SCHEDULED))) {
+ if (WARN_ON_ONCE(!list_empty(&subflow->delegated_node)))
return;
delegated = this_cpu_ptr(&mptcp_delegated_actions);
@@ -605,20 +608,6 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated)
return ret;
}
-static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow)
-{
- return !!READ_ONCE(subflow->delegated_status);
-}
-
-static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action)
-{
- /* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before
- * touching the status bit
- */
- smp_wmb();
- clear_bit(action, &subflow->delegated_status);
-}
-
int mptcp_is_enabled(const struct net *net);
unsigned int mptcp_get_add_addr_timeout(const struct net *net);
int mptcp_is_checksum_enabled(const struct net *net);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 918c1a235790..9c1f8d1d63d2 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1956,9 +1956,15 @@ static void subflow_ulp_clone(const struct request_sock *req,
static void tcp_release_cb_override(struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ long status;
- if (mptcp_subflow_has_delegated_action(subflow))
- mptcp_subflow_process_delegated(ssk);
+ /* process and clear all the pending actions, but leave the subflow into
+ * the napi queue. To respect locking, only the same CPU that originated
+ * the action can touch the list. mptcp_napi_poll will take care of it.
+ */
+ status = set_mask_bits(&subflow->delegated_status, MPTCP_DELEGATE_ACTIONS_MASK, 0);
+ if (status)
+ mptcp_subflow_process_delegated(ssk, status);
tcp_release_cb(ssk);
}
Powered by cgit, Gruvboxed by Blaster4385.