[v3,01/13] scsi: qla2xxx: Ignore NULL pointer in tcm_qla2xxx_free_mcmd
diff mbox series

Message ID 20191125165702.1013-2-r.bolshakov@yadro.com
State Accepted
Commit f2c9ee54a56995a293efef290657d8a1d80e14ab
Headers show
  • scsi: qla2xxx: Bug fixes
Related show

Commit Message

Roman Bolshakov Nov. 25, 2019, 4:56 p.m. UTC
If ABTS cannot be completed in target mode, the driver attempts to free
related management command and crashes:

  NIP [d000000019181ee8] tcm_qla2xxx_free_mcmd+0x40/0x80 [tcm_qla2xxx]
  LR [d00000001dc1e6f8] qlt_response_pkt+0x190/0xa10 [qla2xxx]
  Call Trace:
  [c000003fff27bb50] [c000003fff27bc10] 0xc000003fff27bc10 (unreliable)
  [c000003fff27bb70] [d00000001dc1e6f8] qlt_response_pkt+0x190/0xa10 [qla2xxx]
  [c000003fff27bc10] [d00000001dbc2be0] qla24xx_process_response_queue+0x5d8/0xbd0 [qla2xxx]
  [c000003fff27bd50] [d00000001dbc632c] qla24xx_msix_rsp_q+0x64/0x150 [qla2xxx]
  [c000003fff27bde0] [c000000000187200] __handle_irq_event_percpu+0x90/0x310
  [c000003fff27bea0] [c0000000001874b8] handle_irq_event_percpu+0x38/0x90
  [c000003fff27bee0] [c000000000187574] handle_irq_event+0x64/0xb0
  [c000003fff27bf10] [c00000000018cd38] handle_fasteoi_irq+0xe8/0x280
  [c000003fff27bf40] [c000000000185ccc] generic_handle_irq+0x4c/0x70
  [c000003fff27bf60] [c000000000016cec] __do_irq+0x7c/0x1d0
  [c000003fff27bf90] [c00000000002a530] call_do_irq+0x14/0x24
  [c00000207d2cba90] [c000000000016edc] do_IRQ+0x9c/0x130
  [c00000207d2cbae0] [c000000000008bf4] hardware_interrupt_common+0x114/0x120
  --- interrupt: 501 at arch_local_irq_restore+0x74/0x90
      LR = arch_local_irq_restore+0x74/0x90
  [c00000207d2cbdd0] [c0000000001c64fc] tick_broadcast_oneshot_control+0x4c/0x60 (unreliable)
  [c00000207d2cbdf0] [c0000000007ac840] cpuidle_enter_state+0xf0/0x450
  [c00000207d2cbe50] [c00000000016b81c] call_cpuidle+0x4c/0x90
  [c00000207d2cbe70] [c00000000016bc30] do_idle+0x2b0/0x330
  [c00000207d2cbec0] [c00000000016beec] cpu_startup_entry+0x3c/0x50
  [c00000207d2cbef0] [c00000000004a06c] start_secondary+0x63c/0x670
  [c00000207d2cbf90] [c00000000000aa6c] start_secondary_prolog+0x10/0x14

The crash can be triggered by ACL deletion when there's active I/O.

During ACL deletion, qla2xxx performs implicit LOGO that's invisible for
the initiator. Only the driver and firmware are aware of the logout.
Therefore the initiator continues to send SCSI commands and the target
always responds with SAM STATUS BUSY as it can't find the session.

The command times out after a while and initiator invokes ABORT TASK TMF
for the command. The TMF is mapped to ABTS-LS in FCP. The target can't
find session for S_ID originating ABTS-LS so it never allocates mcmd.
And since N_Port handle was deleted after LOGO, it is no longer valid
and ABTS Response IOCB is returned from firmware with status 31. Then
free_mcmd is invoked on NULL pointer and the kernel crashes.

[ 7734.578642] qla2xxx [0000:00:0c.0]-e837:6: ABTS_RECV_24XX: instance 0
[ 7734.578644] qla2xxx [0000:00:0c.0]-f811:6: qla_target(0): task abort (s_id=1:2:0, tag=1209504, param=0)
[ 7734.578645] find_sess_by_s_id: 0x010200
[ 7734.578645] Unable to locate s_id: 0x010200
[ 7734.578646] qla2xxx [0000:00:0c.0]-f812:6: qla_target(0): task abort for non-existent session
[ 7734.578648] qla2xxx [0000:00:0c.0]-e806:6: Sending task mgmt ABTS response (ha=c0000000d5819000, atio=c0000000d3fd4700, status=4
[ 7734.578730] qla2xxx [0000:00:0c.0]-e838:6: ABTS_RESP_24XX: compl_status 31
[ 7734.578732] qla2xxx [0000:00:0c.0]-e863:6: qla_target(0): ABTS_RESP_24XX failed 31 (subcode 19:a)
[ 7734.578740] Unable to handle kernel paging request for data at address 0x00000200

Fixes: 6b0431d6fa20b ("scsi: qla2xxx: Fix out of order Termination and ABTS response")
Cc: Quinn Tran <qutran@marvell.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Thomas Abraham <tabraham@suse.com>
Cc: stable@vger.kernel.org
Acked-by: Himanshu Madhani <hmadhani@marvell.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
 drivers/scsi/qla2xxx/tcm_qla2xxx.c | 2 ++
 1 file changed, 2 insertions(+)


Bart Van Assche Nov. 26, 2019, 8:55 p.m. UTC | #1
On 11/25/19 8:56 AM, Roman Bolshakov wrote:
> If ABTS cannot be completed in target mode, the driver attempts to free [ ... ]

Reviewed-by: Bart Van Assche <bvanassche@acm.org>

diff mbox series

diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 042a24314edc..bab2073c1f72 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -246,6 +246,8 @@  static void tcm_qla2xxx_complete_mcmd(struct work_struct *work)
 static void tcm_qla2xxx_free_mcmd(struct qla_tgt_mgmt_cmd *mcmd)
+	if (!mcmd)
+		return;
 	INIT_WORK(&mcmd->free_work, tcm_qla2xxx_complete_mcmd);
 	queue_work(tcm_qla2xxx_free_wq, &mcmd->free_work);