]> git.ipfire.org Git - thirdparty/kernel/stable.git/commit
net: rps: fix cpu unplug
authorEric Dumazet <edumazet@google.com>
Fri, 16 Jan 2015 01:04:22 +0000 (17:04 -0800)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Fri, 27 Feb 2015 01:50:10 +0000 (17:50 -0800)
commit64d76f569ae7f966b9e5fa26fd6d822df8d2f96f
treea338a68d94f878462736859ec851a788ec289525
parentada98740b7198b58cd7882c49dfbd4d3047b911e
net: rps: fix cpu unplug

[ Upstream commit ac64da0b83d82abe62f78b3d0e21cca31aea24fa ]

softnet_data.input_pkt_queue is protected by a spinlock that
we must hold when transferring packets from victim queue to an active
one. This is because other cpus could still be trying to enqueue packets
into victim queue.

A second problem is that when we transfert the NAPI poll_list from
victim to current cpu, we absolutely need to special case the percpu
backlog, because we do not want to add complex locking to protect
process_queue : Only owner cpu is allowed to manipulate it, unless cpu
is offline.

Based on initial patch from Prasad Sodagudi & Subash Abhinov
Kasiviswanathan.

This version is better because we do not slow down packet processing,
only make migration safer.

Reported-by: Prasad Sodagudi <psodagud@codeaurora.org>
Reported-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
net/core/dev.c