This is a note to let you know that I've just added the patch titled
RDMA/cm: add timeout to cm_destroy_id wait
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
rdma-cm-add-timeout-to-cm_destroy_id-wait.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit fb817b89a010fa08bcbc617f31b7e05e9e2284ed
Author: Manjunath Patil <manjunath.b.patil@xxxxxxxxxx>
Date: Fri Mar 8 22:33:23 2024 -0800
RDMA/cm: add timeout to cm_destroy_id wait
[ Upstream commit 96d9cbe2f2ff7abde021bac75eafaceabe9a51fa ]
Add timeout to cm_destroy_id, so that userspace can trigger any data
collection that would help in analyzing the cause of delay in destroying
the cm_id.
New noinline function helps dtrace/ebpf programs to hook on to it.
Existing functionality isn't changed except triggering a probe-able new
function at every timeout interval.
We have seen cases where CM messages stuck with MAD layer (either due to
software bug or faulty HCA), leading to cm_id getting stuck in the
following call stack. This patch helps in resolving such issues faster.
kernel: ... INFO: task XXXX:56778 blocked for more than 120 seconds.
...
Call Trace:
__schedule+0x2bc/0x895
schedule+0x36/0x7c
schedule_timeout+0x1f6/0x31f
? __slab_free+0x19c/0x2ba
wait_for_completion+0x12b/0x18a
? wake_up_q+0x80/0x73
cm_destroy_id+0x345/0x610 [ib_cm]
ib_destroy_cm_id+0x10/0x20 [ib_cm]
rdma_destroy_id+0xa8/0x300 [rdma_cm]
ucma_destroy_id+0x13e/0x190 [rdma_ucm]
ucma_write+0xe0/0x160 [rdma_ucm]
__vfs_write+0x3a/0x16d
vfs_write+0xb2/0x1a1
? syscall_trace_enter+0x1ce/0x2b8
SyS_write+0x5c/0xd3
do_syscall_64+0x79/0x1b9
entry_SYSCALL_64_after_hwframe+0x16d/0x0
Signed-off-by: Manjunath Patil <manjunath.b.patil@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20240309063323.458102-1-manjunath.b.patil@xxxxxxxxxx
Signed-off-by: Leon Romanovsky <leon@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 680c3ac8cd4c0..504e1adf1997a 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -34,6 +34,7 @@ MODULE_AUTHOR("Sean Hefty");
MODULE_DESCRIPTION("InfiniBand CM");
MODULE_LICENSE("Dual BSD/GPL");
+#define CM_DESTROY_ID_WAIT_TIMEOUT 10000 /* msecs */
static const char * const ibcm_rej_reason_strs[] = {
[IB_CM_REJ_NO_QP] = "no QP",
[IB_CM_REJ_NO_EEC] = "no EEC",
@@ -1032,10 +1033,20 @@ static void cm_reset_to_idle(struct cm_id_private *cm_id_priv)
}
}
+static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id)
+{
+ struct cm_id_private *cm_id_priv;
+
+ cm_id_priv = container_of(cm_id, struct cm_id_private, id);
+ pr_err("%s: cm_id=%p timed out. state=%d refcnt=%d\n", __func__,
+ cm_id, cm_id->state, refcount_read(&cm_id_priv->refcount));
+}
+
static void cm_destroy_id(struct ib_cm_id *cm_id, int err)
{
struct cm_id_private *cm_id_priv;
struct cm_work *work;
+ int ret;
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
spin_lock_irq(&cm_id_priv->lock);
@@ -1142,7 +1153,14 @@ static void cm_destroy_id(struct ib_cm_id *cm_id, int err)
xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id));
cm_deref_id(cm_id_priv);
- wait_for_completion(&cm_id_priv->comp);
+ do {
+ ret = wait_for_completion_timeout(&cm_id_priv->comp,
+ msecs_to_jiffies(
+ CM_DESTROY_ID_WAIT_TIMEOUT));
+ if (!ret) /* timeout happened */
+ cm_destroy_id_wait_timeout(cm_id);
+ } while (!ret);
+
while ((work = cm_dequeue_work(cm_id_priv)) != NULL)
cm_free_work(work);
