diff options
| author | Shlomo Pongratz <shlomop@mellanox.com> | 2013-02-04 15:29:10 +0000 |
|---|---|---|
| committer | Roland Dreier <roland@purestorage.com> | 2013-02-05 09:35:06 -0800 |
| commit | 7e5a90c25f89128c096dbdb0e5451962438b1e05 (patch) | |
| tree | 0f7547c36c7d7ab5ed33a2922c18e452b1b627c7 | |
| parent | 949db153b6466c6f7cad5a427ecea94985927311 (diff) | |
| download | lwn-7e5a90c25f89128c096dbdb0e5451962438b1e05.tar.gz lwn-7e5a90c25f89128c096dbdb0e5451962438b1e05.zip | |
IPoIB: Fix crash due to skb double destruct
After commit b13912bbb4a2 ("IPoIB: Call skb_dst_drop() once skb is
enqueued for sending"), using connected mode and running multithreaded
iperf for long time, ie
iperf -c <IP> -P 16 -t 3600
results in a crash.
After the above-mentioned patch, the driver is calling skb_orphan() and
skb_dst_drop() after calling post_send() in ipoib_cm.c::ipoib_cm_send()
(also in ipoib_ib.c::ipoib_send())
The problem with this is, as is written in a comment in both routines,
"it's entirely possible that the completion handler will run before we
execute anything after the post_send()." This leads to running the
skb cleanup routines simultaneously in two different contexts.
The solution is to always perform the skb_orphan() and skb_dst_drop()
before queueing the send work request. If an error occurs, then it
will be no different than the regular case where dev_free_skb_any() in
the completion path, which is assumed to be after these two routines.
Signed-off-by: Shlomo Pongratz <shlomop@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_cm.c | 6 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_ib.c | 6 |
2 files changed, 6 insertions, 6 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 03103d2bd641..67b0c1d23678 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -741,6 +741,9 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ tx_req->mapping = addr; + skb_orphan(skb); + skb_dst_drop(skb); + rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1), addr, skb->len); if (unlikely(rc)) { @@ -752,9 +755,6 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ dev->trans_start = jiffies; ++tx->tx_head; - skb_orphan(skb); - skb_dst_drop(skb); - if (++priv->tx_outstanding == ipoib_sendq_size) { ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n", tx->qp->qp_num); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index a1bca70e20aa..2cfa76f5d99e 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -600,6 +600,9 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, netif_stop_queue(dev); } + skb_orphan(skb); + skb_dst_drop(skb); + rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1), address->ah, qpn, tx_req, phead, hlen); if (unlikely(rc)) { @@ -615,9 +618,6 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, address->last_send = priv->tx_head; ++priv->tx_head; - - skb_orphan(skb); - skb_dst_drop(skb); } if (unlikely(priv->tx_outstanding > MAX_SEND_CQE)) |