| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1357883793-15199-1-git-send-email-gaowanlong@cn.fujitsu.com>
Date: Fri, 11 Jan 2013 13:56:32 +0800
From: Wanlong Gao <gaowanlong@...fujitsu.com>
To: linux-kernel@...r.kernel.org
Cc: Rusty Russell <rusty@...tcorp.com.au>,
"Michael S. Tsirkin" <mst@...hat.com>,
Jason Wang <jasowang@...hat.com>,
Eric Dumazet <erdnetdev@...il.com>,
virtualization@...ts.linux-foundation.org, netdev@...r.kernel.org,
Wanlong Gao <gaowanlong@...fujitsu.com>
Subject: [PATCH V4 1/2] virtio-net: fix the set affinity bug when CPU IDs are not consecutive
As Michael mentioned, set affinity and select queue will not work very
well when CPU IDs are not consecutive, this can happen with hot unplug.
Fix this bug by traversal the online CPUs, and create a per cpu variable
to find the mapping from CPU to the preferable virtual-queue.
Cc: Rusty Russell <rusty@...tcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@...hat.com>
Cc: Jason Wang <jasowang@...hat.com>
Cc: Eric Dumazet <erdnetdev@...il.com>
Cc: virtualization@...ts.linux-foundation.org
Cc: netdev@...r.kernel.org
Signed-off-by: Wanlong Gao <gaowanlong@...fujitsu.com>
---
V3->V4:
move vq_index into virtnet_info (Jason)
change the mapping value when not setting affinity (Jason)
address the comments about select_queue (Rusty)
Not Addressed yet:
race between select_queue and set_channels need discuss more
but not the same problem with this (Rusty)
drivers/net/virtio_net.c | 53 ++++++++++++++++++++++++++++++++++++++----------
1 file changed, 42 insertions(+), 11 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index a6fcf15..ca17a58 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -123,6 +123,9 @@ struct virtnet_info {
/* Does the affinity hint is set for virtqueues? */
bool affinity_hint_set;
+
+ /* Per-cpu variable to show the mapping from CPU to virtqueue */
+ int __percpu *vq_index;
};
struct skb_vnet_hdr {
@@ -1016,6 +1019,7 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev, u16 vid)
static void virtnet_set_affinity(struct virtnet_info *vi, bool set)
{
int i;
+ int cpu;
/* In multiqueue mode, when the number of cpu is equal to the number of
* queue pairs, we let the queue pairs to be private to one cpu by
@@ -1029,16 +1033,29 @@ static void virtnet_set_affinity(struct virtnet_info *vi, bool set)
return;
}
- for (i = 0; i < vi->max_queue_pairs; i++) {
- int cpu = set ? i : -1;
- virtqueue_set_affinity(vi->rq[i].vq, cpu);
- virtqueue_set_affinity(vi->sq[i].vq, cpu);
- }
+ if (set) {
+ i = 0;
+ for_each_online_cpu(cpu) {
+ virtqueue_set_affinity(vi->rq[i].vq, cpu);
+ virtqueue_set_affinity(vi->sq[i].vq, cpu);
+ *per_cpu_ptr(vi->vq_index, cpu) = i;
+ i++;
+ }
- if (set)
vi->affinity_hint_set = true;
- else
+ } else {
+ for(i = 0; i < vi->max_queue_pairs; i++) {
+ virtqueue_set_affinity(vi->rq[i].vq, -1);
+ virtqueue_set_affinity(vi->sq[i].vq, -1);
+ }
+
+ i = 0;
+ for_each_online_cpu(cpu)
+ *per_cpu_ptr(vi->vq_index, cpu) =
+ ++i % vi->curr_queue_pairs;
+
vi->affinity_hint_set = false;
+ }
}
static void virtnet_get_ringparam(struct net_device *dev,
@@ -1127,12 +1144,19 @@ static int virtnet_change_mtu(struct net_device *dev, int new_mtu)
/* To avoid contending a lock hold by a vcpu who would exit to host, select the
* txq based on the processor id.
- * TODO: handle cpu hotplug.
*/
static u16 virtnet_select_queue(struct net_device *dev, struct sk_buff *skb)
{
- int txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) :
- smp_processor_id();
+ int txq;
+ struct virtnet_info *vi = netdev_priv(dev);
+
+ if (skb_rx_queue_recorded(skb)) {
+ txq = skb_get_rx_queue(skb);
+ } else {
+ txq = *__this_cpu_ptr(vi->vq_index);
+ if (txq == -1)
+ txq = 0;
+ }
while (unlikely(txq >= dev->real_num_tx_queues))
txq -= dev->real_num_tx_queues;
@@ -1453,6 +1477,10 @@ static int virtnet_probe(struct virtio_device *vdev)
if (vi->stats == NULL)
goto free;
+ vi->vq_index = alloc_percpu(int);
+ if (vi->vq_index == NULL)
+ goto free_stats;
+
mutex_init(&vi->config_lock);
vi->config_enable = true;
INIT_WORK(&vi->config_work, virtnet_config_changed_work);
@@ -1476,7 +1504,7 @@ static int virtnet_probe(struct virtio_device *vdev)
/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
err = init_vqs(vi);
if (err)
- goto free_stats;
+ goto free_index;
netif_set_real_num_tx_queues(dev, 1);
netif_set_real_num_rx_queues(dev, 1);
@@ -1520,6 +1548,8 @@ free_recv_bufs:
free_vqs:
cancel_delayed_work_sync(&vi->refill);
virtnet_del_vqs(vi);
+free_index:
+ free_percpu(vi->vq_index);
free_stats:
free_percpu(vi->stats);
free:
@@ -1554,6 +1584,7 @@ static void virtnet_remove(struct virtio_device *vdev)
flush_work(&vi->config_work);
+ free_percpu(vi->vq_index);
free_percpu(vi->stats);
free_netdev(vi->dev);
}
--
1.8.1
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists