From a813aea1343de5a075f047fd573eeaf686af71ac Mon Sep 17 00:00:00 2001 From: Jack Wang Date: Thu, 21 Mar 2024 10:27:59 +0800 Subject: [PATCH 1/2] RDMA/IPoIB: Fix error code return in ipoib_mcast_join stable inclusion from stable-v4.19.307 commit c6d9287ebe4ed77ea34fa450a5d70f4984824181 bugzilla: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=c6d9287ebe4ed77ea34fa450a5d70f4984824181 -------------------------------- [ Upstream commit 753fff78f430704548f45eda52d6d55371a52c0f ] Return the error code in case of ib_sa_join_multicast fail. Signed-off-by: Jack Wang Link: https://lore.kernel.org/r/20231121130316.126364-2-jinpu.wang@ionos.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin Signed-off-by: Yu Liao --- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index b9e9562f5034..805df1fcba84 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -558,6 +558,7 @@ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) spin_unlock_irq(&priv->lock); complete(&mcast->done); spin_lock_irq(&priv->lock); + return ret; } return 0; } -- Gitee From c383aeb1353cf351608406f827f7131a50398bdc Mon Sep 17 00:00:00 2001 From: Daniel Vacek Date: Thu, 21 Mar 2024 10:28:00 +0800 Subject: [PATCH 2/2] IB/ipoib: Fix mcast list locking stable inclusion from stable-v4.19.307 commit 4c8922ae8eb8dcc1e4b7d1059d97a8334288d825 category: bugfix bugzilla: NA CVE: CVE-2023-52587 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=4c8922ae8eb8dcc1e4b7d1059d97a8334288d825 -------------------------------- [ 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" --- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 805df1fcba84..de82fb0cb1d5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -543,21 +543,17 @@ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) /* SM supports sendonly-fullmember, otherwise fallback to full-member */ 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; -- Gitee