diff mbox series

[net] tcp: consistently disable header prediction for mptcp

Message ID 7f941e06e6434902ea4a0a572392f65cd2745447.1625053058.git.pabeni@redhat.com (mailing list archive)
State Accepted
Commit 71158bb1f2d2da61385c58fc1114e1a1c19984ba
Delegated to: Netdev Maintainers
Headers show
Series [net] tcp: consistently disable header prediction for mptcp | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for net
netdev/subject_prefix success Link
netdev/cc_maintainers success CCed 7 of 7 maintainers
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 1091 this patch: 1091
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 10 lines checked
netdev/build_allmodconfig_warn success Errors and warnings before: 1093 this patch: 1093
netdev/header_inline success Link

Commit Message

Paolo Abeni June 30, 2021, 11:42 a.m. UTC
The MPTCP receive path is hooked only into the TCP slow-path.
The DSS presence allows plain MPTCP traffic to hit that
consistently.

Since commit e1ff9e82e2ea ("net: mptcp: improve fallback to TCP"),
when an MPTCP socket falls back to TCP, it can hit the TCP receive
fast-path, and delay or stop triggering the event notification.

Address the issue explicitly disabling the header prediction
for MPTCP sockets.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/200
Fixes: e1ff9e82e2ea ("net: mptcp: improve fallback to TCP")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
Notes:
- I'm unable to disable header prediction consistently for MPTCP
  sockets touching only MPTCP code
- possible alternatives could be:
  - hook MPTCP in the TCP fastpath, too
  - try to pull again commit 45f119bf936b ("tcp: remove header prediction")
    avoiding the regression noded in 31770e34e43d ("tcp: Revert "tcp: remove
    header prediction"")
  I choose this option as the hopefully less invasive one.
---
 include/net/tcp.h | 4 ++++
 1 file changed, 4 insertions(+)

Comments

Eric Dumazet June 30, 2021, 1:20 p.m. UTC | #1
On 6/30/21 1:42 PM, Paolo Abeni wrote:
> The MPTCP receive path is hooked only into the TCP slow-path.
> The DSS presence allows plain MPTCP traffic to hit that
> consistently.
> 
> Since commit e1ff9e82e2ea ("net: mptcp: improve fallback to TCP"),
> when an MPTCP socket falls back to TCP, it can hit the TCP receive
> fast-path, and delay or stop triggering the event notification.
> 
> Address the issue explicitly disabling the header prediction
> for MPTCP sockets.
> 
> Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/200
> Fixes: e1ff9e82e2ea ("net: mptcp: improve fallback to TCP")
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---

SGTM, thanks.

Reviewed-by: Eric Dumazet <edumazet@google.com>
patchwork-bot+netdevbpf@kernel.org July 1, 2021, 8:36 p.m. UTC | #2
Hello:

This patch was applied to netdev/net.git (refs/heads/master):

On Wed, 30 Jun 2021 13:42:13 +0200 you wrote:
> The MPTCP receive path is hooked only into the TCP slow-path.
> The DSS presence allows plain MPTCP traffic to hit that
> consistently.
> 
> Since commit e1ff9e82e2ea ("net: mptcp: improve fallback to TCP"),
> when an MPTCP socket falls back to TCP, it can hit the TCP receive
> fast-path, and delay or stop triggering the event notification.
> 
> [...]

Here is the summary with links:
  - [net] tcp: consistently disable header prediction for mptcp
    https://git.kernel.org/netdev/net/c/71158bb1f2d2

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
diff mbox series

Patch

diff --git a/include/net/tcp.h b/include/net/tcp.h
index d05193cb0d99..b42b3e6731ed 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -682,6 +682,10 @@  static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
 
 static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
 {
+	/* mptcp hooks are only on the slow path */
+	if (sk_is_mptcp((struct sock *)tp))
+		return;
+
 	tp->pred_flags = htonl((tp->tcp_header_len << 26) |
 			       ntohl(TCP_FLAG_ACK) |
 			       snd_wnd);