mptcp: use get_retrans wrapper

This patch adds the multiple subflows support for __mptcp_retrans(). Use
get_retrans() wrapper instead of mptcp_subflow_get_retrans() in it.

Check the subflow scheduled flags to test which subflow or subflows are
picked by the scheduler, use them to send data.

Move msk_owned_by_me() and fallback checks into get_retrans() wrapper
from mptcp_subflow_get_retrans().

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-9-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 77e94ee..61590ff 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2233,11 +2233,6 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
        struct mptcp_subflow_context *subflow;
        int min_stale_count = INT_MAX;
 
-       msk_owned_by_me(msk);
-
-       if (__mptcp_check_fallback(msk))
-               return NULL;
-
        mptcp_for_each_subflow(msk, subflow) {
                struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
@@ -2515,16 +2510,17 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 static void __mptcp_retrans(struct sock *sk)
 {
        struct mptcp_sock *msk = mptcp_sk(sk);
+       struct mptcp_subflow_context *subflow;
        struct mptcp_sendmsg_info info = {};
        struct mptcp_data_frag *dfrag;
-       size_t copied = 0;
        struct sock *ssk;
-       int ret;
+       int ret, err;
+       u16 len = 0;
 
        mptcp_clean_una_wakeup(sk);
 
        /* first check ssk: need to kick "stale" logic */
-       ssk = mptcp_subflow_get_retrans(msk);
+       err = mptcp_sched_get_retrans(msk);
        dfrag = mptcp_rtx_head(sk);
        if (!dfrag) {
                if (mptcp_data_fin_enabled(msk)) {
@@ -2543,32 +2539,45 @@ static void __mptcp_retrans(struct sock *sk)
                goto reset_timer;
        }
 
-       if (!ssk)
+       if (err)
                goto reset_timer;
 
-       lock_sock(ssk);
+       mptcp_for_each_subflow(msk, subflow) {
+               if (READ_ONCE(subflow->scheduled)) {
+                       u16 copied = 0;
 
-       /* limit retransmission to the bytes already sent on some subflows */
-       info.sent = 0;
-       info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
-       while (info.sent < info.limit) {
-               ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
-               if (ret <= 0)
-                       break;
+                       mptcp_subflow_set_scheduled(subflow, false);
 
-               MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
-               copied += ret;
-               info.sent += ret;
-       }
-       if (copied) {
-               dfrag->already_sent = max(dfrag->already_sent, info.sent);
-               msk->bytes_retrans += copied;
-               tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
-                        info.size_goal);
-               WRITE_ONCE(msk->allow_infinite_fallback, false);
+                       ssk = mptcp_subflow_tcp_sock(subflow);
+
+                       lock_sock(ssk);
+
+                       /* limit retransmission to the bytes already sent on some subflows */
+                       info.sent = 0;
+                       info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len :
+                                                                   dfrag->already_sent;
+                       while (info.sent < info.limit) {
+                               ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+                               if (ret <= 0)
+                                       break;
+
+                               MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
+                               copied += ret;
+                               info.sent += ret;
+                       }
+                       if (copied) {
+                               len = max(copied, len);
+                               tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+                                        info.size_goal);
+                               WRITE_ONCE(msk->allow_infinite_fallback, false);
+                       }
+
+                       release_sock(ssk);
+               }
        }
 
-       release_sock(ssk);
+       msk->bytes_retrans += len;
+       dfrag->already_sent = max(dfrag->already_sent, len);
 
 reset_timer:
        mptcp_check_and_set_pending(sk);

diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 078b5d4..cac1cc1 100644 (file)
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -136,6 +136,12 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
        struct mptcp_subflow_context *subflow;
        struct mptcp_sched_data data;
 
+       msk_owned_by_me(msk);
+
+       /* the following check is moved out of mptcp_subflow_get_retrans */
+       if (__mptcp_check_fallback(msk))
+               return -EINVAL;
+
        mptcp_for_each_subflow(msk, subflow) {
                if (READ_ONCE(subflow->scheduled))
                        return 0;