From: Florian Westphal <fw at strlen.de>
To: mptcp at lists.01.org
Subject: [MPTCP] [PATCH v3 3/6] mptcp: add rmem queue accounting
Date: Thu, 20 Feb 2020 15:34:22 +0100 [thread overview]
Message-ID: <20200220143426.28626-4-fw@strlen.de> (raw)
In-Reply-To: 20200220143426.28626-1-fw@strlen.de
[-- Attachment #1: Type: text/plain, Size: 2017 bytes --]
If userspace never drains the receive buffers we must stop draining
the subflow socket(s) at some point.
This adds the needed rmem accouting for this.
If the threshold is reached, we stop draining the subflows.
Signed-off-by: Florian Westphal <fw(a)strlen.de>
---
net/mptcp/protocol.c | 16 +++++++++++++++-
1 file changed, 15 insertions(+), 1 deletion(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 85d7f73ca804..ac81283d5ec3 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -172,6 +172,10 @@ void mptcp_data_ready(struct sock *sk)
if (test_and_set_bit(MPTCP_WORK_DATA_READY, &msk->flags))
return;
+ /* don't schedule if mptcp sk is (still) over limit */
+ if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf))
+ return;
+
sock_hold(sk);
if (!schedule_work(&msk->rtx_work))
sock_put(sk);
@@ -699,7 +703,7 @@ static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
struct sock *sk = (struct sock *)msk;
__skb_unlink(skb, &ssk->sk_receive_queue);
- skb_orphan(skb);
+ skb_set_owner_r(skb, sk);
__skb_queue_tail(&sk->sk_receive_queue, skb);
msk->ack_seq += copy_len;
@@ -717,6 +721,7 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
struct sock *ssk;
bool more_data_avail;
struct tcp_sock *tp;
+ int rcvbuf;
ssk = mptcp_subflow_recv_lookup(msk);
if (!ssk)
@@ -726,6 +731,10 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
lock_sock(ssk);
+ rcvbuf = max(ssk->sk_rcvbuf, sk->sk_rcvbuf);
+ if (rcvbuf > sk->sk_rcvbuf)
+ sk->sk_rcvbuf = rcvbuf;
+
tp = tcp_sk(ssk);
do {
u32 map_remaining, offset;
@@ -741,6 +750,11 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
if (!skb)
break;
+ if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
+ done = true;
+ break;
+ }
+
offset = seq - TCP_SKB_CB(skb)->seq;
fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
if (fin) {
--
2.24.1
next reply other threads:[~2020-02-20 14:34 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-20 14:34 Florian Westphal [this message]
-- strict thread matches above, loose matches on Subject: below --
2020-02-18 12:21 [MPTCP] [PATCH v3 3/6] mptcp: add rmem queue accounting Florian Westphal
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200220143426.28626-4-fw@strlen.de \
--to=unknown@example.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.