Apply to the MPTCP auto-tuning the same improvements introduced for the
TCP protocol by the merge commit 2da35e4b4df9 ("Merge branch
'tcp-receive-side-improvements'").
The main difference is that TCP subflow and the main MPTCP socket need
to account separately for OoO: MPTCP does not care for TCP-level OoO
and vice versa.
The above additionally allow dropping the msk receive buffer update at
receive time, as the latter only intended to cope with subflow receive
buffer increase due to OoO packets.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
net/mptcp/protocol.c | 95 +++++++++++++++++++++-----------------------
net/mptcp/protocol.h | 4 +-
2 files changed, 47 insertions(+), 52 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index c51aede20779d..671c51cb9539c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -178,6 +178,33 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
return mptcp_try_coalesce((struct sock *)msk, to, from);
}
+static bool mptcp_rcvbuf_grow(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ int rcvwin, rcvbuf;
+
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) ||
+ (sk->sk_userlocks & SOCK_RCVBUF_LOCK))
+ return false;
+
+ rcvwin = ((u64)msk->rcvq_space.space << 1);
+
+ if (!RB_EMPTY_ROOT(&msk->out_of_order_queue))
+ rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq;
+
+ rcvbuf = min_t(u64, mptcp_space_from_win(sk, rcvwin),
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
+
+ if (rcvbuf > sk->sk_rcvbuf) {
+ u32 window_clamp;
+
+ window_clamp = mptcp_win_from_space(sk, rcvbuf);
+ WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+ return true;
+ }
+ return false;
+}
+
/* "inspired" by tcp_data_queue_ofo(), main differences:
* - use mptcp seqs
* - don't cope with sacks
@@ -291,6 +318,9 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
end:
skb_condense(skb);
skb_set_owner_r(skb, sk);
+ /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */
+ if (sk->sk_socket)
+ mptcp_rcvbuf_grow(sk);
}
static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
@@ -770,18 +800,10 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
return moved;
}
-static void __mptcp_rcvbuf_update(struct sock *sk, struct sock *ssk)
-{
- if (unlikely(ssk->sk_rcvbuf > sk->sk_rcvbuf))
- WRITE_ONCE(sk->sk_rcvbuf, ssk->sk_rcvbuf);
-}
-
static void __mptcp_data_ready(struct sock *sk, struct sock *ssk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- __mptcp_rcvbuf_update(sk, ssk);
-
/* Wake-up the reader only for in-sequence data */
if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk))
sk->sk_data_ready(sk);
@@ -1984,48 +2006,26 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
if (msk->rcvq_space.copied <= msk->rcvq_space.space)
goto new_measure;
- if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
- !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
- u64 rcvwin, grow;
- int rcvbuf;
-
- rcvwin = ((u64)msk->rcvq_space.copied << 1) + 16 * advmss;
-
- grow = rcvwin * (msk->rcvq_space.copied - msk->rcvq_space.space);
-
- do_div(grow, msk->rcvq_space.space);
- rcvwin += (grow << 1);
-
- rcvbuf = min_t(u64, mptcp_space_from_win(sk, rcvwin),
- READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
-
- if (rcvbuf > sk->sk_rcvbuf) {
- u32 window_clamp;
-
- window_clamp = mptcp_win_from_space(sk, rcvbuf);
- WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+ msk->rcvq_space.space = msk->rcvq_space.copied;
+ if (mptcp_rcvbuf_grow(sk)) {
- /* Make subflows follow along. If we do not do this, we
- * get drops at subflow level if skbs can't be moved to
- * the mptcp rx queue fast enough (announced rcv_win can
- * exceed ssk->sk_rcvbuf).
- */
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *ssk;
- bool slow;
+ /* Make subflows follow along. If we do not do this, we
+ * get drops at subflow level if skbs can't be moved to
+ * the mptcp rx queue fast enough (announced rcv_win can
+ * exceed ssk->sk_rcvbuf).
+ */
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk;
+ bool slow;
- ssk = mptcp_subflow_tcp_sock(subflow);
- slow = lock_sock_fast(ssk);
- WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf);
- WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp);
- if (tcp_can_send_ack(ssk))
- tcp_cleanup_rbuf(ssk, 1);
- unlock_sock_fast(ssk, slow);
- }
+ ssk = mptcp_subflow_tcp_sock(subflow);
+ slow = lock_sock_fast(ssk);
+ tcp_sk(ssk)->rcvq_space.space = msk->rcvq_space.copied;
+ tcp_rcvbuf_grow(ssk);
+ unlock_sock_fast(ssk, slow);
}
}
- msk->rcvq_space.space = msk->rcvq_space.copied;
new_measure:
msk->rcvq_space.copied = 0;
msk->rcvq_space.time = mstamp;
@@ -2054,11 +2054,6 @@ static bool __mptcp_move_skbs(struct sock *sk)
if (list_empty(&msk->conn_list))
return false;
- /* verify we can move any data from the subflow, eventually updating */
- if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK))
- mptcp_for_each_subflow(msk, subflow)
- __mptcp_rcvbuf_update(sk, subflow->tcp_sock);
-
subflow = list_first_entry(&msk->conn_list,
struct mptcp_subflow_context, node);
for (;;) {
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a1787a1344ac1..128baea5b496e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -341,8 +341,8 @@ struct mptcp_sock {
struct mptcp_pm_data pm;
struct mptcp_sched_ops *sched;
struct {
- u32 space; /* bytes copied in last measurement window */
- u32 copied; /* bytes copied in this measurement window */
+ int space; /* bytes copied in last measurement window */
+ int copied; /* bytes copied in this measurement window */
u64 time; /* start time of measurement window */
u64 rtt_us; /* last maximum rtt of subflows */
} rcvq_space;
--
2.51.0Hi Paolo,
kernel test robot noticed the following build warnings:
[auto build test WARNING on mptcp/export-net]
[also build test WARNING on linus/master v6.17-rc6 next-20250916]
[cannot apply to next-20250916 mptcp/export]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Paolo-Abeni/mptcp-leverage-skb-deferral-free/20250917-003012
base: https://github.com/multipath-tcp/mptcp_net-next.git export-net
patch link: https://lore.kernel.org/r/d3f96328a76e6fffcb871e8542c526ea99135ea5.1758039775.git.pabeni%40redhat.com
patch subject: [MPTCP next 03/12] mptcp: rcvbuf auto-tuning improvement
config: arc-nsimosci_hs_smp_defconfig (https://download.01.org/0day-ci/archive/20250917/202509171856.1KhVdgmP-lkp@intel.com/config)
compiler: arc-linux-gcc (GCC) 15.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250917/202509171856.1KhVdgmP-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202509171856.1KhVdgmP-lkp@intel.com/
All warnings (new ones prefixed by >>):
net/mptcp/protocol.c: In function 'mptcp_rcvbuf_grow':
>> net/mptcp/protocol.c:199:21: warning: variable 'window_clamp' set but not used [-Wunused-but-set-variable]
199 | u32 window_clamp;
| ^~~~~~~~~~~~
vim +/window_clamp +199 net/mptcp/protocol.c
180
181 static bool mptcp_rcvbuf_grow(struct sock *sk)
182 {
183 struct mptcp_sock *msk = mptcp_sk(sk);
184 int rcvwin, rcvbuf;
185
186 if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) ||
187 (sk->sk_userlocks & SOCK_RCVBUF_LOCK))
188 return false;
189
190 rcvwin = ((u64)msk->rcvq_space.space << 1);
191
192 if (!RB_EMPTY_ROOT(&msk->out_of_order_queue))
193 rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq;
194
195 rcvbuf = min_t(u64, mptcp_space_from_win(sk, rcvwin),
196 READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
197
198 if (rcvbuf > sk->sk_rcvbuf) {
> 199 u32 window_clamp;
200
201 window_clamp = mptcp_win_from_space(sk, rcvbuf);
202 WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
203 return true;
204 }
205 return false;
206 }
207
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
© 2016 - 2025 Red Hat, Inc.