summary | shortlog | log | commit | commitdiff | tree
raw | patch | inline | side by side (parent: 2095ab2)
raw | patch | inline | side by side (parent: 2095ab2)
author | Julian Anastasov <ja@ssi.bg> | |
Thu, 9 Jul 2015 06:59:10 +0000 (09:59 +0300) | ||
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | |
Thu, 1 Oct 2015 09:36:20 +0000 (11:36 +0200) |
[ 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 <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
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 <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
net/core/dev.c | patch | blob | history |
diff --git a/net/core/dev.c b/net/core/dev.c
index 1fe07b2c5cec25173ce0beb96c0f84dd01ae43c2..ae3260fc133da5b95f8ae264667c5f73b9d3a095 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
pt_prev = NULL;
- rcu_read_lock();
-
another_round:
skb->skb_iif = skb->dev->ifindex;
skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
skb = skb_vlan_untag(skb);
if (unlikely(!skb))
- goto unlock;
+ goto out;
}
#ifdef CONFIG_NET_CLS_ACT
#ifdef CONFIG_NET_CLS_ACT
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
- goto unlock;
+ goto out;
ncls:
#endif
if (vlan_do_receive(&skb))
goto another_round;
else if (unlikely(!skb))
- goto unlock;
+ goto out;
}
rx_handler = rcu_dereference(skb->dev->rx_handler);
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:
ret = NET_RX_DROP;
}
-unlock:
- rcu_read_unlock();
out:
return ret;
}
static int netif_receive_skb_internal(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;
}
/**
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) {