From: Arun Easi <aeasi@xxxxxxxxxxx>
System crash was seen when I/O was run against a NVME target and when I/O
aborts were occurring.
Crash stack is:
-- relevant crash stack --
BUG: kernel NULL pointer dereference, address: 0000000000000010
:
#6 [ffffae1f8666bdd0] page_fault at ffffffffa740122e
[exception RIP: qla_nvme_abort_work+339]
RIP: ffffffffc0f592e3 RSP: ffffae1f8666be80 RFLAGS: 00010297
RAX: 0000000000000000 RBX: ffff9b581fc8af80 RCX: ffffffffc0f83bd0
RDX: 0000000000000001 RSI: ffff9b5839c6c7c8 RDI: 0000000008000000
RBP: ffff9b6832f85000 R8: ffffffffc0f68160 R9: ffffffffc0f70652
R10: ffffae1f862ffdc8 R11: 0000000000000300 R12: 000000000000010d
R13: 0000000000000000 R14: ffff9b5839cea000 R15: 0ffff9b583fab170
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
#7 [ffffae1f8666be98] process_one_work at ffffffffa6aba184
#8 [ffffae1f8666bed8] worker_thread at ffffffffa6aba39d
#9 [ffffae1f8666bf10] kthread at ffffffffa6ac06ed
The crash was due to a stale SRB structure access after it was aborted.
Fixed the issue by removing stale access.
Fixes: 2cabf10dbbe38 (“scsi: qla2xxx: Fix hang on NVMe command timeouts ”)
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Arun Easi <aeasi@xxxxxxxxxxx>
Signed-off-by: Nilesh Javali <njavali@xxxxxxxxxxx>
Reviewed-by: Himanshu Madhani <himanshu.madhani@xxxxxxxxxx>
---
drivers/scsi/qla2xxx/qla_nvme.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 1c5da2dbd6f9..877b2b625020 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -228,6 +228,8 @@ static void qla_nvme_abort_work(struct work_struct *work)
fc_port_t *fcport = sp->fcport;
struct qla_hw_data *ha = fcport->vha->hw;
int rval, abts_done_called = 1;
+ bool io_wait_for_abort_done;
+ uint32_t handle;
ql_dbg(ql_dbg_io, fcport->vha, 0xffff,
"%s called for sp=%p, hndl=%x on fcport=%p desc=%p deleted=%d\n",
@@ -244,12 +246,20 @@ static void qla_nvme_abort_work(struct work_struct *work)
goto out;
}
+ /*
+ * sp may not be valid after abort_command if return code is either
+ * SUCCESS or ERR_FROM_FW codes, so cache the value here.
+ */
+ io_wait_for_abort_done = ql2xabts_wait_nvme &&
+ QLA_ABTS_WAIT_ENABLED(sp);
+ handle = sp->handle;
+
rval = ha->isp_ops->abort_command(sp);
ql_dbg(ql_dbg_io, fcport->vha, 0x212b,
"%s: %s command for sp=%p, handle=%x on fcport=%p rval=%x\n",
__func__, (rval != QLA_SUCCESS) ? "Failed to abort" : "Aborted",
- sp, sp->handle, fcport, rval);
+ sp, handle, fcport, rval);
/*
* If async tmf is enabled, the abort callback is called only on
@@ -264,7 +274,7 @@ static void qla_nvme_abort_work(struct work_struct *work)
* are waited until ABTS complete. This kref is decreased
* at qla24xx_abort_sp_done function.
*/
- if (abts_done_called && ql2xabts_wait_nvme && QLA_ABTS_WAIT_ENABLED(sp))
+ if (abts_done_called && io_wait_for_abort_done)
return;
out:
/* kref_get was done before work was schedule. */
--
2.19.0.rc0
