mptcp: preserve MSG_EOR semantics in sendmsg path

Extend MPTCP's sendmsg handling to recognize and honor the MSG_EOR flag,
which marks the end of a record for application-level message boundaries.

Data fragments tagged with MSG_EOR are explicitly marked in the
mptcp_data_frag structure and skb context to prevent unintended
coalescing with subsequent data chunks. This ensures the intent of
applications using MSG_EOR is preserved across MPTCP subflows,
maintaining consistent message segmentation behavior.

Signed-off-by: Gang Yan <yangang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260403-net-next-mptcp-msg_eor-misc-v1-2-b0b33bea3fed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 79315e575d074b346dccbdc4f6c5d015e82bcd41..e21e416cd19afae90ca0f300c179874f2ea0bfc0 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1005,7 +1005,8 @@ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
                                       const struct page_frag *pfrag,
                                       const struct mptcp_data_frag *df)
 {
-       return df && pfrag->page == df->page &&
+       return df && !df->eor &&
+               pfrag->page == df->page &&
                pfrag->size - pfrag->offset > 0 &&
                pfrag->offset == (df->offset + df->data_len) &&
                df->data_seq + df->data_len == msk->write_seq;
@@ -1147,6 +1148,7 @@ mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag,
        dfrag->offset = offset + sizeof(struct mptcp_data_frag);
        dfrag->already_sent = 0;
        dfrag->page = pfrag->page;
+       dfrag->eor = 0;
 
        return dfrag;
 }
@@ -1408,6 +1410,13 @@ out:
                mptcp_update_infinite_map(msk, ssk, mpext);
        trace_mptcp_sendmsg_frag(mpext);
        mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
+
+       /* if this is the last chunk of a dfrag with MSG_EOR set,
+        * mark the skb to prevent coalescing with subsequent data.
+        */
+       if (dfrag->eor && info->sent + copy >= dfrag->data_len)
+               TCP_SKB_CB(skb)->eor = 1;
+
        return copy;
 }
 
@@ -1868,7 +1877,8 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
        long timeo;
 
        /* silently ignore everything else */
-       msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_FASTOPEN;
+       msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
+                         MSG_FASTOPEN | MSG_EOR;
 
        lock_sock(sk);
 
@@ -1975,8 +1985,16 @@ wait_for_memory:
                        goto do_error;
        }
 
-       if (copied)
+       if (copied) {
+               /* mark the last dfrag with EOR if MSG_EOR was set */
+               if (msg->msg_flags & MSG_EOR) {
+                       struct mptcp_data_frag *dfrag = mptcp_pending_tail(sk);
+
+                       if (dfrag)
+                               dfrag->eor = 1;
+               }
                __mptcp_push_pending(sk, msg->msg_flags);
+       }
 
 out:
        release_sock(sk);

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 02031007100b2c61551235640daaa3eadd9f193b..1208f317ac3330db1d67453c98cdd39745c7914b 100644 (file)
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -264,7 +264,7 @@ struct mptcp_data_frag {
        u16 data_len;
        u16 offset;
        u8 overhead;
-       u8 __unused;
+       u8 eor;                 /* currently using 1 bit */
        u16 already_sent;
        struct page *page;
 };