Commit 08bc3276 authored by Alex Estrin's avatar Alex Estrin Committed by Doug Ledford
Browse files

IB/ipoib: fix for rare multicast join race condition

A narrow window for race condition still exist between
multicast join thread and *dev_flush workers.
A kernel crash caused by prolong erratic link state changes
was observed (most likely a faulty cabling):

[167275.656270] BUG: unable to handle kernel NULL pointer dereference at
[167275.665973] IP: [<ffffffffa05f8f2e>] ipoib_mcast_join+0xae/0x1d0 [ib_ipoib]
[167275.674443] PGD 0
[167275.677373] Oops: 0000 [#1] SMP
[167275.977530] Call Trace:
[167275.982225]  [<ffffffffa05f92f0>] ? ipoib_mcast_free+0x200/0x200 [ib_ipoib]
[167275.992024]  [<ffffffffa05fa1b7>] ipoib_mcast_join_task+0x2a7/0x490
[167276.002149]  [<ffffffff8109d5fb>] process_one_work+0x17b/0x470
[167276.010754]  [<ffffffff8109e3cb>] worker_thread+0x11b/0x400
[167276.019088]  [<ffffffff8109e2b0>] ? rescuer_thread+0x400/0x400
[167276.027737]  [<ffffffff810a5aef>] kthread+0xcf/0xe0
Here was a hit spot:
ipoib_mcast_join() {
      rec.qkey      = priv->broadcast->mcmember.qkey;
Proposed patch should prevent multicast join task to continue
if link state change is detected.
Signed-off-by: default avatarAlex Estrin <>

Changes from v4:
- as suggested by Doug Ledford, optimized spinlock usage,
i.e. ipoib_mcast_join() is called with lock held.
Changes from v3:
- sync with priv->lock before flag check.
Chages from v2:
- Move check for OPER_UP flag state to mcast_join() to
ensure no event worker is in progress.
- minor style fixes.
Changes from v1:
- No need to lock again if error detected.
Signed-off-by: default avatarDoug Ledford <>
parent ee50aeac
......@@ -456,7 +456,10 @@ out_locked:
return status;
static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
* Caller must hold 'priv->lock'
static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ib_sa_multicast *multicast;
......@@ -466,6 +469,10 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
ib_sa_comp_mask comp_mask;
int ret = 0;
if (!priv->broadcast ||
!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
return -EINVAL;
ipoib_dbg_mcast(priv, "joining MGID %pI6\n", mcast->mcmember.mgid.raw);
rec.mgid = mcast->mcmember.mgid;
......@@ -525,20 +532,23 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
rec.join_state = 4;
multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
&rec, comp_mask, GFP_KERNEL,
ipoib_mcast_join_complete, mcast);
if (IS_ERR(multicast)) {
ret = PTR_ERR(multicast);
ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret);
/* Requeue this join task with a backoff delay */
__ipoib_mcast_schedule_join_thread(priv, mcast, 1);
clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
return 0;
void ipoib_mcast_join_task(struct work_struct *work)
......@@ -620,9 +630,10 @@ void ipoib_mcast_join_task(struct work_struct *work)
/* Found the next unjoined group */
set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
ipoib_mcast_join(dev, mcast);
if (ipoib_mcast_join(dev, mcast)) {
} else if (!delay_until ||
time_before(mcast->delay_until, delay_until))
delay_until = mcast->delay_until;
......@@ -641,10 +652,9 @@ out:
if (mcast) {
set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
ipoib_mcast_join(dev, mcast);
if (mcast)
ipoib_mcast_join(dev, mcast);
int ipoib_mcast_start_thread(struct net_device *dev)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment