This is a note to let you know that I've just added the patch titled
net: rps: fix cpu unplug
to the 3.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
net-rps-fix-cpu-unplug.patch
and it can be found in the queue-3.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.
>From foo@baz Thu Feb 12 09:26:20 HKT 2015
From: Eric Dumazet <eduma...@google.com>
Date: Thu, 15 Jan 2015 17:04:22 -0800
Subject: net: rps: fix cpu unplug
From: Eric Dumazet <eduma...@google.com>
[ 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 <psoda...@codeaurora.org>
Reported-by: Subash Abhinov Kasiviswanathan <subas...@codeaurora.org>
Signed-off-by: Eric Dumazet <eduma...@google.com>
Cc: Tom Herbert <therb...@google.com>
Signed-off-by: David S. Miller <da...@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>
---
net/core/dev.c | 20 +++++++++++++++-----
1 file changed, 15 insertions(+), 5 deletions(-)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6015,10 +6015,20 @@ static int dev_cpu_callback(struct notif
oldsd->output_queue = NULL;
oldsd->output_queue_tailp = &oldsd->output_queue;
}
- /* Append NAPI poll list from offline CPU. */
- if (!list_empty(&oldsd->poll_list)) {
- list_splice_init(&oldsd->poll_list, &sd->poll_list);
- raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ /* Append NAPI poll list from offline CPU, with one exception :
+ * process_backlog() must be called by cpu owning percpu backlog.
+ * We properly handle process_queue & input_pkt_queue later.
+ */
+ while (!list_empty(&oldsd->poll_list)) {
+ struct napi_struct *napi = list_first_entry(&oldsd->poll_list,
+ struct napi_struct,
+ poll_list);
+
+ list_del_init(&napi->poll_list);
+ if (napi->poll == process_backlog)
+ napi->state = 0;
+ else
+ ____napi_schedule(sd, napi);
}
raise_softirq_irqoff(NET_TX_SOFTIRQ);
@@ -6029,7 +6039,7 @@ static int dev_cpu_callback(struct notif
netif_rx(skb);
input_queue_head_incr(oldsd);
}
- while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
+ while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx(skb);
input_queue_head_incr(oldsd);
}
Patches currently in stable-queue which might be from eduma...@google.com are
queue-3.10/tcp-ipv4-initialize-unicast_sock-sk_pacing_rate.patch
queue-3.10/ip-zero-sockaddr-returned-on-error-queue.patch
queue-3.10/ping-fix-race-in-free-in-receive-path.patch
queue-3.10/net-rps-fix-cpu-unplug.patch
queue-3.10/netxen-fix-netxen_nic_poll-logic.patch
queue-3.10/ipv4-tcp-get-rid-of-ugly-unicast_sock.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
