diff mbox series

[net-next,2/7] mptcp: drop __mptcp_fastopen_gen_msk_ackseq()

Message ID 20250218-net-next-mptcp-rx-path-refactor-v1-2-4a47d90d7998@kernel.org (mailing list archive)
State Accepted
Commit f03afb3aeb9d81f6c5ab728a61a040012923e3b3
Delegated to: Netdev Maintainers
Headers show
Series mptcp: rx path refactor | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 9 of 9 maintainers
netdev/build_clang success Errors and warnings before: 1 this patch: 1
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 3 this patch: 3
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 60 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2025-02-19--06-00 (tests: 891)

Commit Message

Matthieu Baerts Feb. 18, 2025, 6:36 p.m. UTC 
From: Paolo Abeni <pabeni@redhat.com>

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>
---
 net/mptcp/fastopen.c | 24 ++----------------------
 net/mptcp/protocol.c |  4 +++-
 net/mptcp/protocol.h |  5 ++---
 net/mptcp/subflow.c  |  3 ---
 4 files changed, 7 insertions(+), 29 deletions(-)
diff mbox series

Patch

diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index a29ff901df7588dec24e330ddd77a4aeb1462b68..7777f5a2d14379853fcd13c4b57c5569be05a2e4 100644
--- 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 6bd81904747066d8f2c1043dd81b372925f18cbb..55f9698f3c22f1dc423a7605c7b00bfda162b54c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -135,7 +135,8 @@  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;
@@ -366,6 +367,7 @@  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 37226cdd9e3717c4f8cf0d4c879a0feaaa91d459..3c3e9b185ae35d92b5a2daae994a4a9e76f9cc84 100644
--- 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]))
@@ -1059,8 +1060,6 @@  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);
 int mptcp_nl_fill_addr(struct sk_buff *skb,
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 2926bdf88e42c5f2db6875b00b4eca2dbf49dba2..d2caffa56bdd98f5fd9ef07fdcb3610ea186b848 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -802,9 +802,6 @@  void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
 	subflow_set_remote_key(msk, subflow, mp_opt);
 	WRITE_ONCE(subflow->fully_established, true);
 	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,