For several target drivers (e.g. ib_srpt and ib_isert) sleeping inside
transport_generic_free_cmd() causes RDMA completion processing to stall.
Hence only sleep inside this function if the (iSCSI) target driver
requires this.
This patch avoids that messages similar to the following appear in the
kernel log:
INFO: task kworker/u25:0:1013 blocked for more than 480 seconds.
Tainted: G W 4.10.0-rc7-dbg+ #3
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kworker/u25:0 D 0 1013 2 0x00000000
Workqueue: ib-comp-wq ib_cq_poll_work [ib_core]
Call Trace:
__schedule+0x2da/0xb00
schedule+0x38/0x90
schedule_timeout+0x2fe/0x640
wait_for_completion+0xfe/0x160
transport_generic_free_cmd+0x2e/0x80 [target_core_mod]
srpt_send_done+0x59/0x9f [ib_srpt]
__ib_process_cq+0x4b/0xd0 [ib_core]
ib_cq_poll_work+0x1b/0x60 [ib_core]
process_one_work+0x208/0x6a0
worker_thread+0x49/0x4a0
kthread+0x107/0x140
ret_from_fork+0x2e/0x40
Signed-off-by: Bart Van Assche <bart.vanassche@xxxxxxxxxxx>
Cc: Hannes Reinecke <hare@xxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Andy Grover <agrover@xxxxxxxxxx>
Cc: David Disseldorp <ddiss@xxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
---
drivers/target/target_core_transport.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 37f57357d4a0..df1ceb2dd110 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2553,7 +2553,8 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
*/
if (aborted) {
pr_debug("Detected CMD_T_ABORTED for ITT: %llu\n", cmd->tag);
- wait_for_completion(&cmd->cmd_wait_comp);
+ if (wait_for_tasks)
+ wait_for_completion(&cmd->cmd_wait_comp);
cmd->se_tfo->release_cmd(cmd);
ret = 1;
}
--
2.12.2