diff options
author | Daniel Vacek <neelx@redhat.com> | 2023-12-12 11:07:45 +0300 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2024-02-05 23:12:56 +0300 |
commit | 5108a2dc2db5630fb6cd58b8be80a0c134bc310a (patch) | |
tree | fed1c76c44926b09f1eed76b8dc6ea6e46b87b18 /drivers/infiniband | |
parent | fe80290b2ad1bfe1ac14c300e9db3d29eda874e0 (diff) | |
download | linux-5108a2dc2db5630fb6cd58b8be80a0c134bc310a.tar.xz |
IB/ipoib: Fix mcast list locking
[ Upstream commit 4f973e211b3b1c6d36f7c6a19239d258856749f9 ]
Releasing the `priv->lock` while iterating the `priv->multicast_list` in
`ipoib_mcast_join_task()` opens a window for `ipoib_mcast_dev_flush()` to
remove the items while in the middle of iteration. If the mcast is removed
while the lock was dropped, the for loop spins forever resulting in a hard
lockup (as was reported on RHEL 4.18.0-372.75.1.el8_6 kernel):
Task A (kworker/u72:2 below) | Task B (kworker/u72:0 below)
-----------------------------------+-----------------------------------
ipoib_mcast_join_task(work) | ipoib_ib_dev_flush_light(work)
spin_lock_irq(&priv->lock) | __ipoib_ib_dev_flush(priv, ...)
list_for_each_entry(mcast, | ipoib_mcast_dev_flush(dev = priv->dev)
&priv->multicast_list, list) |
ipoib_mcast_join(dev, mcast) |
spin_unlock_irq(&priv->lock) |
| spin_lock_irqsave(&priv->lock, flags)
| list_for_each_entry_safe(mcast, tmcast,
| &priv->multicast_list, list)
| list_del(&mcast->list);
| list_add_tail(&mcast->list, &remove_list)
| spin_unlock_irqrestore(&priv->lock, flags)
spin_lock_irq(&priv->lock) |
| ipoib_mcast_remove_list(&remove_list)
(Here, `mcast` is no longer on the | list_for_each_entry_safe(mcast, tmcast,
`priv->multicast_list` and we keep | remove_list, list)
spinning on the `remove_list` of | >>> wait_for_completion(&mcast->done)
the other thread which is blocked |
and the list is still valid on |
it's stack.)
Fix this by keeping the lock held and changing to GFP_ATOMIC to prevent
eventual sleeps.
Unfortunately we could not reproduce the lockup and confirm this fix but
based on the code review I think this fix should address such lockups.
crash> bc 31
PID: 747 TASK: ff1c6a1a007e8000 CPU: 31 COMMAND: "kworker/u72:2"
--
[exception RIP: ipoib_mcast_join_task+0x1b1]
RIP: ffffffffc0944ac1 RSP: ff646f199a8c7e00 RFLAGS: 00000002
RAX: 0000000000000000 RBX: ff1c6a1a04dc82f8 RCX: 0000000000000000
work (&priv->mcast_task{,.work})
RDX: ff1c6a192d60ac68 RSI: 0000000000000286 RDI: ff1c6a1a04dc8000
&mcast->list
RBP: ff646f199a8c7e90 R8: ff1c699980019420 R9: ff1c6a1920c9a000
R10: ff646f199a8c7e00 R11: ff1c6a191a7d9800 R12: ff1c6a192d60ac00
mcast
R13: ff1c6a1d82200000 R14: ff1c6a1a04dc8000 R15: ff1c6a1a04dc82d8
dev priv (&priv->lock) &priv->multicast_list (aka head)
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'drivers/infiniband')
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 6 |
1 files changed, 1 insertions, 5 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 9e6967a40042..319d4288eddd 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -531,21 +531,17 @@ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) rec.join_state = SENDONLY_FULLMEMBER_JOIN; } - spin_unlock_irq(&priv->lock); multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port, - &rec, comp_mask, GFP_KERNEL, + &rec, comp_mask, GFP_ATOMIC, ipoib_mcast_join_complete, mcast); - spin_lock_irq(&priv->lock); 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); - spin_unlock_irq(&priv->lock); complete(&mcast->done); - spin_lock_irq(&priv->lock); return ret; } return 0; |