3.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: Julian Anastasov <j...@ssi.bg>
[ Upstream commit 2c17d27c36dcce2b6bf689f41a46b9e909877c21 ]
Incoming packet should be either in backlog queue or
in RCU read-side section. Otherwise, the final sequence of
flush_backlog() and synchronize_net() may miss packets
that can run without device reference:
CPU 1 CPU 2
skb->dev: no reference
process_backlog:__skb_dequeue
process_backlog:local_irq_enable
on_each_cpu for
flush_backlog => IPI(hardirq): flush_backlog
- packet not found in backlog
CPU delayed ...
synchronize_net
- no ongoing RCU
read-side sections
netdev_run_todo,
rcu_barrier: no
ongoing callbacks
__netif_receive_skb_core:rcu_read_lock
- too late
free dev
process packet for freed dev
Fixes: 6e583ce5242f ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebied...@xmission.com>
Cc: Stephen Hemminger <step...@networkplumber.org>
Signed-off-by: Julian Anastasov <j...@ssi.bg>
Signed-off-by: David S. Miller <da...@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>
---
net/core/dev.c | 29 ++++++++++++++---------------
1 file changed, 14 insertions(+), 15 deletions(-)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3443,8 +3443,6 @@ static int __netif_receive_skb_core(stru
pt_prev = NULL;
- rcu_read_lock();
-
another_round:
skb->skb_iif = skb->dev->ifindex;
@@ -3454,7 +3452,7 @@ another_round:
skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
skb = vlan_untag(skb);
if (unlikely(!skb))
- goto unlock;
+ goto out;
}
#ifdef CONFIG_NET_CLS_ACT
@@ -3479,7 +3477,7 @@ skip_taps:
#ifdef CONFIG_NET_CLS_ACT
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
- goto unlock;
+ goto out;
ncls:
#endif
@@ -3494,7 +3492,7 @@ ncls:
if (vlan_do_receive(&skb))
goto another_round;
else if (unlikely(!skb))
- goto unlock;
+ goto out;
}
rx_handler = rcu_dereference(skb->dev->rx_handler);
@@ -3506,7 +3504,7 @@ ncls:
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
ret = NET_RX_SUCCESS;
- goto unlock;
+ goto out;
case RX_HANDLER_ANOTHER:
goto another_round;
case RX_HANDLER_EXACT:
@@ -3558,8 +3556,6 @@ drop:
ret = NET_RX_DROP;
}
-unlock:
- rcu_read_unlock();
out:
return ret;
}
@@ -3606,29 +3602,30 @@ static int __netif_receive_skb(struct sk
*/
int netif_receive_skb(struct sk_buff *skb)
{
+ int ret;
+
net_timestamp_check(netdev_tstamp_prequeue, skb);
if (skb_defer_rx_timestamp(skb))
return NET_RX_SUCCESS;
+ rcu_read_lock();
+
#ifdef CONFIG_RPS
if (static_key_false(&rps_needed)) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
- int cpu, ret;
-
- rcu_read_lock();
-
- cpu = get_rps_cpu(skb->dev, skb, &rflow);
+ int cpu = get_rps_cpu(skb->dev, skb, &rflow);
if (cpu >= 0) {
ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
rcu_read_unlock();
return ret;
}
- rcu_read_unlock();
}
#endif
- return __netif_receive_skb(skb);
+ ret = __netif_receive_skb(skb);
+ rcu_read_unlock();
+ return ret;
}
EXPORT_SYMBOL(netif_receive_skb);
@@ -4038,8 +4035,10 @@ static int process_backlog(struct napi_s
unsigned int qlen;
while ((skb = __skb_dequeue(&sd->process_queue))) {
+ rcu_read_lock();
local_irq_enable();
__netif_receive_skb(skb);
+ rcu_read_unlock();
local_irq_disable();
input_queue_head_incr(sd);
if (++work >= quota) {
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
