Merge branch 'mptcp-rx-path-refactor'

Matthieu Baerts says:

====================
mptcp: rx path refactor

Paolo worked on this RX path refactor for these two main reasons:

- Currently, the MPTCP RX path introduces quite a bit of 'exceptional'
  accounting/locking processing WRT to plain TCP, adding up to the
  implementation complexity in a miserable way.

- The performance gap WRT plain TCP for single subflow connections is
  quite measurable.

The present refactor addresses both the above items: most of the
additional complexity is dropped, and single stream performances
increase measurably, from 55Gbps to 71Gbps in Paolo's loopback test.
As a reference, plain TCP was around 84Gbps on the same host.

The above comes to a price: the patch are invasive, even in subtle ways.

Note: patch 5/7 removes the sk_forward_alloc_get() helper, which caused
some trivial modifications in different places in the net tree: sockets,
IPv4, sched. That's why a few more people have been Cc here. Feel free
to only look at this patch 5/7.
====================

Link: https://patch.msgid.link/20250218-net-next-mptcp-rx-path-refactor-v1-0-4a47d90d7998@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 7 insertions, 15 deletions

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 37226cdd9e37..ca65f8bff632 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -124,12 +124,14 @@
 #define MPTCP_FLUSH_JOIN_LIST	5
 #define MPTCP_SYNC_STATE	6
 #define MPTCP_SYNC_SNDBUF	7
+#define MPTCP_DEQUEUE		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]))
@@ -279,7 +281,6 @@ struct mptcp_sock {
 	u64		rcv_data_fin_seq;
 	u64		bytes_retrans;
 	u64		bytes_consumed;
-	int		rmem_fwd_alloc;
 	int		snd_burst;
 	int		old_wspace;
 	u64		recovery_snd_nxt;	/* in recovery mode accept up to this seq;
@@ -294,7 +295,6 @@ struct mptcp_sock {
 	u32		last_ack_recv;
 	unsigned long	timer_ival;
 	u32		token;
-	int		rmem_released;
 	unsigned long	flags;
 	unsigned long	cb_flags;
 	bool		recovery;		/* closing subflow write queue reinjected */
@@ -324,7 +324,6 @@ struct mptcp_sock {
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
-	struct sk_buff_head receive_queue;
 	struct list_head conn_list;
 	struct list_head rtx_queue;
 	struct mptcp_data_frag *first_pending;
@@ -355,6 +354,8 @@ struct mptcp_sock {
 	list_for_each_entry(__subflow, &((__msk)->conn_list), node)
 #define mptcp_for_each_subflow_safe(__msk, __subflow, __tmp)			\
 	list_for_each_entry_safe(__subflow, __tmp, &((__msk)->conn_list), node)
+#define mptcp_next_subflow(__msk, __subflow)				\
+	list_next_entry_circular(__subflow, &((__msk)->conn_list), node)
 
 extern struct genl_family mptcp_genl_family;
 
@@ -381,14 +382,6 @@ static inline void msk_owned_by_me(const struct mptcp_sock *msk)
 #define mptcp_sk(ptr) container_of_const(ptr, struct mptcp_sock, sk.icsk_inet.sk)
 #endif
 
-/* the msk socket don't use the backlog, also account for the bulk
- * free memory
- */
-static inline int __mptcp_rmem(const struct sock *sk)
-{
-	return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released);
-}
-
 static inline int mptcp_win_from_space(const struct sock *sk, int space)
 {
 	return __tcp_win_from_space(mptcp_sk(sk)->scaling_ratio, space);
@@ -401,7 +394,8 @@ static inline int mptcp_space_from_win(const struct sock *sk, int win)
 
 static inline int __mptcp_space(const struct sock *sk)
 {
-	return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
+	return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) -
+				    sk_rmem_alloc_get(sk));
 }
 
 static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
@@ -1059,8 +1053,6 @@ 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,