summaryrefslogtreecommitdiffstats
path: root/drivers
diff options
context:
space:
mode:
authorMike Marciniszyn <mike.marciniszyn@qlogic.com>2011-11-21 08:43:54 -0500
committerRoland Dreier <roland@purestorage.com>2011-11-29 13:20:02 -0800
commit3874397c0bdec3c21ce071711cd105165179b8eb (patch)
treed4ad5784650fff68d798d38af6c0533f25b4ed78 /drivers
parent1ea6b8f48918282bdca0b32a34095504ee65bab5 (diff)
downloadlinux-stable-3874397c0bdec3c21ce071711cd105165179b8eb.tar.gz
linux-stable-3874397c0bdec3c21ce071711cd105165179b8eb.tar.bz2
linux-stable-3874397c0bdec3c21ce071711cd105165179b8eb.zip
IB/ipoib: Prevent hung task or softlockup processing multicast response
This following can occur with ipoib when processing a multicast reponse: BUG: soft lockup - CPU#0 stuck for 67s! [ib_mad1:982] Modules linked in: ... CPU 0: Modules linked in: ... Pid: 982, comm: ib_mad1 Not tainted 2.6.32-131.0.15.el6.x86_64 #1 ProLiant DL160 G5 RIP: 0010:[<ffffffff814ddb27>] [<ffffffff814ddb27>] _spin_unlock_irqrestore+0x17/0x20 RSP: 0018:ffff8802119ed860 EFLAGS: 00000246 0000000000000004 RBX: ffff8802119ed860 RCX: 000000000000a299 RDX: ffff88021086c700 RSI: 0000000000000246 RDI: 0000000000000246 RBP: ffffffff8100bc8e R08: ffff880210ac229c R09: 0000000000000000 R10: ffff88021278aab8 R11: 0000000000000000 R12: ffff8802119ed860 R13: ffffffff8100be6e R14: 0000000000000001 R15: 0000000000000003 FS: 0000000000000000(0000) GS:ffff880028200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 00000000006d4840 CR3: 0000000209aa5000 CR4: 00000000000406f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Call Trace: [<ffffffffa032c247>] ? ipoib_mcast_send+0x157/0x480 [ib_ipoib] [<ffffffff8100bc8e>] ? apic_timer_interrupt+0xe/0x20 [<ffffffff8100bc8e>] ? apic_timer_interrupt+0xe/0x20 [<ffffffffa03283d4>] ? ipoib_path_lookup+0x124/0x2d0 [ib_ipoib] [<ffffffffa03286fc>] ? ipoib_start_xmit+0x17c/0x430 [ib_ipoib] [<ffffffff8141e758>] ? dev_hard_start_xmit+0x2c8/0x3f0 [<ffffffff81439d0a>] ? sch_direct_xmit+0x15a/0x1c0 [<ffffffff81423098>] ? dev_queue_xmit+0x388/0x4d0 [<ffffffffa032d6b7>] ? ipoib_mcast_join_finish+0x2c7/0x510 [ib_ipoib] [<ffffffffa032dab8>] ? ipoib_mcast_sendonly_join_complete+0x1b8/0x1f0 [ib_ipoib] [<ffffffffa02a0946>] ? mcast_work_handler+0x1a6/0x710 [ib_sa] [<ffffffffa015f01e>] ? ib_send_mad+0xfe/0x3c0 [ib_mad] [<ffffffffa00f6c93>] ? ib_get_cached_lmc+0xa3/0xb0 [ib_core] [<ffffffffa02a0f9b>] ? join_handler+0xeb/0x200 [ib_sa] [<ffffffffa029e4fc>] ? ib_sa_mcmember_rec_callback+0x5c/0xa0 [ib_sa] [<ffffffffa029e79c>] ? recv_handler+0x3c/0x70 [ib_sa] [<ffffffffa01603a4>] ? ib_mad_completion_handler+0x844/0x9d0 [ib_mad] [<ffffffffa015fb60>] ? ib_mad_completion_handler+0x0/0x9d0 [ib_mad] [<ffffffff81088830>] ? worker_thread+0x170/0x2a0 [<ffffffff8108e160>] ? autoremove_wake_function+0x0/0x40 [<ffffffff810886c0>] ? worker_thread+0x0/0x2a0 [<ffffffff8108ddf6>] ? kthread+0x96/0xa0 [<ffffffff8100c1ca>] ? child_rip+0xa/0x20 Coinciding with stack trace is the following message: ib0: ib_address_create failed The code below in ipoib_mcast_join_finish() will note the above failure in the address handle but otherwise continue: ah = ipoib_create_ah(dev, priv->pd, &av); if (!ah) { ipoib_warn(priv, "ib_address_create failed\n"); } else { The while loop at the bottom of ipoib_mcast_join_finish() will attempt to send queued multicast packets in mcast->pkt_queue and eventually end up in ipoib_mcast_send(): if (!mcast->ah) { if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) skb_queue_tail(&mcast->pkt_queue, skb); else { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } My read is that the code will requeue the packet and return to the ipoib_mcast_join_finish() while loop and the stage is set for the "hung" task diagnostic as the while loop never sees a non-NULL ah, and will do nothing to resolve. There are GFP_ATOMIC allocates in the provider routines, so this is possible and should be dealt with. The test that induced the failure is associated with a host SM on the same server during a shutdown. This patch causes ipoib_mcast_join_finish() to exit with an error which will flush the queued mcast packets. Nothing is done to unwind the QP attached state so that subsequent sends from above will retry the join. Reviewed-by: Ram Vepa <ram.vepa@qlogic.com> Reviewed-by: Gary Leshner <gary.leshner@qlogic.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@qlogic.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_ib.c13
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_main.c2
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_multicast.c7
3 files changed, 14 insertions, 8 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 0ef9af94997d..4115be54ba3b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -57,21 +57,24 @@ struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
struct ib_pd *pd, struct ib_ah_attr *attr)
{
struct ipoib_ah *ah;
+ struct ib_ah *vah;
ah = kmalloc(sizeof *ah, GFP_KERNEL);
if (!ah)
- return NULL;
+ return ERR_PTR(-ENOMEM);
ah->dev = dev;
ah->last_send = 0;
kref_init(&ah->ref);
- ah->ah = ib_create_ah(pd, attr);
- if (IS_ERR(ah->ah)) {
+ vah = ib_create_ah(pd, attr);
+ if (IS_ERR(vah)) {
kfree(ah);
- ah = NULL;
- } else
+ ah = (struct ipoib_ah *)vah;
+ } else {
+ ah->ah = vah;
ipoib_dbg(netdev_priv(dev), "Created ah %p\n", ah->ah);
+ }
return ah;
}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 7567b6000230..37c46c66b0f2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -432,7 +432,7 @@ static void path_rec_completion(int status,
spin_lock_irqsave(&priv->lock, flags);
- if (ah) {
+ if (!IS_ERR_OR_NULL(ah)) {
path->pathrec = *pathrec;
old_ah = path->ah;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 1b7a97686356..30ca8f069a17 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -240,8 +240,11 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
av.grh.dgid = mcast->mcmember.mgid;
ah = ipoib_create_ah(dev, priv->pd, &av);
- if (!ah) {
- ipoib_warn(priv, "ib_address_create failed\n");
+ if (IS_ERR(ah)) {
+ ipoib_warn(priv, "ib_address_create failed %ld\n",
+ -PTR_ERR(ah));
+ /* use original error */
+ return PTR_ERR(ah);
} else {
spin_lock_irq(&priv->lock);
mcast->ah = ah;