[PATCH 3.13.y-ckt 54/57] net: call rcu_read_lock early in process_backlog

From: Kamal Mostafa
Date: Tue Sep 22 2015 - 13:51:33 EST


3.13.11-ckt27 -stable review patch. If anyone has any objections, please let me know.

------------------

From: Julian Anastasov <ja@xxxxxx>

commit 2c17d27c36dcce2b6bf689f41a46b9e909877c21 upstream.

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@xxxxxxxxxxxx>
Cc: Stephen Hemminger <stephen@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Julian Anastasov <ja@xxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
[ luis: backported to 3.16: used davem's backport to 3.18 ]
Signed-off-by: Luis Henriques <luis.henriques@xxxxxxxxxxxxx>
Signed-off-by: Kamal Mostafa <kamal@xxxxxxxxxxxxx>
---
net/core/dev.c | 29 ++++++++++++++---------------
1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 870b9ec..6c97f06 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3534,8 +3534,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)

pt_prev = NULL;

- rcu_read_lock();
-
another_round:
skb->skb_iif = skb->dev->ifindex;

@@ -3545,7 +3543,7 @@ 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
@@ -3570,7 +3568,7 @@ skip_taps:
#ifdef CONFIG_NET_CLS_ACT
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
- goto unlock;
+ goto out;
ncls:
#endif

@@ -3585,7 +3583,7 @@ 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);
@@ -3597,7 +3595,7 @@ 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:
@@ -3649,8 +3647,6 @@ drop:
ret = NET_RX_DROP;
}

-unlock:
- rcu_read_unlock();
out:
return ret;
}
@@ -3697,29 +3693,30 @@ static int __netif_receive_skb(struct sk_buff *skb)
*/
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);

@@ -4130,8 +4127,10 @@ static int process_backlog(struct napi_struct *napi, int quota)
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) {
--
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/