mptcp: drop __mptcp_fastopen_gen_msk_ackseq()

[ Upstream commit f03afb3aeb9d81f6c5ab728a61a040012923e3b3 ]

When we will move the whole RX path under the msk socket lock, updating
the already queued skb for passive fastopen socket at 3rd ack time will
be extremely painful and race prone

The map_seq for already enqueued skbs is used only to allow correct
coalescing with later data; preventing collapsing to the first skb of
a fastopen connect we can completely remove the
__mptcp_fastopen_gen_msk_ackseq() helper.

Before dropping this helper, a new item had to be added to the
mptcp_skb_cb structure. Because this item will be frequently tested in
the fast path -- almost on every packet -- and because there is free
space there, a single byte is used instead of a bitfield. This micro
optimisation slightly reduces the number of CPU operations to do the
associated check.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250218-net-next-mptcp-rx-path-refactor-v1-2-4a47d90d7998@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 6254a16d6f0c ("mptcp: fix rx timestamp corruption on fastopen")
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index a29ff901df7588dec24e330ddd77a4aeb1462b68..7777f5a2d14379853fcd13c4b57c5569be05a2e4 100644 (file)
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -40,13 +40,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
        tp->copied_seq += skb->len;
        subflow->ssn_offset += skb->len;
 
-       /* initialize a dummy sequence number, we will update it at MPC
-        * completion, if needed
-        */
+       /* Only the sequence delta is relevant */
        MPTCP_SKB_CB(skb)->map_seq = -skb->len;
        MPTCP_SKB_CB(skb)->end_seq = 0;
        MPTCP_SKB_CB(skb)->offset = 0;
        MPTCP_SKB_CB(skb)->has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
+       MPTCP_SKB_CB(skb)->cant_coalesce = 1;
 
        mptcp_data_lock(sk);
 
@@ -58,22 +57,3 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 
        mptcp_data_unlock(sk);
 }
-
-void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
-                                    const struct mptcp_options_received *mp_opt)
-{
-       struct sock *sk = (struct sock *)msk;
-       struct sk_buff *skb;
-
-       skb = skb_peek_tail(&sk->sk_receive_queue);
-       if (skb) {
-               WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
-               pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx\n", sk,
-                        MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq,
-                        MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq);
-               MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq;
-               MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq;
-       }
-
-       pr_debug("msk=%p ack_seq=%llx\n", msk, msk->ack_seq);
-}

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 71995d00696eabaa4f31ee0f1f1911e11a526245..aed6c04c7de67cb33245ec72ff4de18abcdb7ace 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -139,7 +139,8 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
        bool fragstolen;
        int delta;
 
-       if (MPTCP_SKB_CB(from)->offset ||
+       if (unlikely(MPTCP_SKB_CB(to)->cant_coalesce) ||
+           MPTCP_SKB_CB(from)->offset ||
            ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) ||
            !skb_try_coalesce(to, from, &fragstolen, &delta))
                return false;
@@ -370,6 +371,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
        MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len;
        MPTCP_SKB_CB(skb)->offset = offset;
        MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp;
+       MPTCP_SKB_CB(skb)->cant_coalesce = 0;
 
        if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
                /* in sequence */

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index fbb3897c9c2c2b377ccaba9864ea4817853af356..2a33452715597ad7a1f4b1532686b5c1b5c7709e 100644 (file)
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -129,7 +129,8 @@ struct mptcp_skb_cb {
        u64 map_seq;
        u64 end_seq;
        u32 offset;
-       u8  has_rxtstamp:1;
+       u8  has_rxtstamp;
+       u8  cant_coalesce;
 };
 
 #define MPTCP_SKB_CB(__skb)    ((struct mptcp_skb_cb *)&((__skb)->cb[0]))
@@ -988,8 +989,6 @@ void mptcp_event_pm_listener(const struct sock *ssk,
                             enum mptcp_event_type event);
 bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);
 
-void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
-                                    const struct mptcp_options_received *mp_opt);
 void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,
                                              struct request_sock *req);
 

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 49be98ffd1de7a7d34cb0c9a3d9d5da37b0343f5..f2fc735d8b618379e181357595b31c82e3239dcf 100644 (file)
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -778,9 +778,6 @@ void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
        subflow_set_remote_key(msk, subflow, mp_opt);
        subflow->fully_established = 1;
        WRITE_ONCE(msk->fully_established, true);
-
-       if (subflow->is_mptfo)
-               __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
 }
 
 static struct sock *subflow_syn_recv_sock(const struct sock *sk,