diff options
| author | Manjunath Patil <manjunath.b.patil@oracle.com> | 2024-03-08 22:33:23 -0800 |
|---|---|---|
| committer | Leon Romanovsky <leon@kernel.org> | 2024-03-10 13:17:54 +0200 |
| commit | 96d9cbe2f2ff7abde021bac75eafaceabe9a51fa (patch) | |
| tree | 06f5ce1c681da5d07cdbd2f0e22dbdb8b5c4067d | |
| parent | 2d5c00815778ec4f4e0a84e405e3e157b7815db1 (diff) | |
RDMA/cm: add timeout to cm_destroy_id wait
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@oracle.com>
Link: https://lore.kernel.org/r/20240309063323.458102-1-manjunath.b.patil@oracle.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
| -rw-r--r-- | drivers/infiniband/core/cm.c | 20 |
1 files changed, 19 insertions, 1 deletions
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index ff58058aeadc..bf0df6ee4f78 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", @@ -1025,10 +1026,20 @@ 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); @@ -1135,7 +1146,14 @@ retest: 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); |