diff options
| author | Bart Van Assche | 2013-12-11 17:06:14 +0100 |
|---|---|---|
| committer | Roland Dreier | 2014-01-21 10:46:17 -0800 |
| commit | 93079162bf0ed2934c7b0c3ee93ba894df8fb3cd (patch) | |
| tree | 3250899980a35531d4a38dcf2d899df8bef5ad37 /include/scsi | |
| parent | 18cc4e02508e3f1fadf81f697837567431ee5a9c (diff) | |
scsi_transport_srp: Fix a race condition
The rport timers must be stopped before the SRP initiator destroys the
resources associated with the SCSI host. This is necessary because
otherwise the callback functions invoked from the SRP transport layer
could trigger a use-after-free. Stopping the rport timers before
invoking scsi_remove_host() can trigger long delays in the SCSI error
handler if a transport layer failure occurs while scsi_remove_host()
is in progress. Hence move the code for stopping the rport timers from
srp_rport_release() into a new function and invoke that function after
scsi_remove_host() has finished. This patch fixes the following
sporadic kernel crash:
kernel BUG at include/asm-generic/dma-mapping-common.h:64!
invalid opcode: 0000 [#1] SMP
RIP: 0010:[<ffffffffa03b20b1>] [<ffffffffa03b20b1>] srp_unmap_data+0x121/0x130 [ib_srp]
Call Trace:
[<ffffffffa03b20fc>] srp_free_req+0x3c/0x80 [ib_srp]
[<ffffffffa03b2188>] srp_finish_req+0x48/0x70 [ib_srp]
[<ffffffffa03b21fb>] srp_terminate_io+0x4b/0x60 [ib_srp]
[<ffffffffa03a6fb5>] __rport_fail_io_fast+0x75/0x80 [scsi_transport_srp]
[<ffffffffa03a7438>] rport_fast_io_fail_timedout+0x88/0xc0 [scsi_transport_srp]
[<ffffffff8108b370>] worker_thread+0x170/0x2a0
[<ffffffff81090876>] kthread+0x96/0xa0
[<ffffffff8100c0ca>] child_rip+0xa/0x20
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Diffstat (limited to 'include/scsi')
| -rw-r--r-- | include/scsi/scsi_transport_srp.h | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h index 4ebf6913b7b2..f24e763fa430 100644 --- a/include/scsi/scsi_transport_srp.h +++ b/include/scsi/scsi_transport_srp.h @@ -19,7 +19,7 @@ struct srp_rport_identifiers { * @SRP_RPORT_BLOCKED: Transport layer not operational; fast I/O fail timer * is running and I/O has been blocked. * @SRP_RPORT_FAIL_FAST: Fast I/O fail timer has expired; fail I/O fast. - * @SRP_RPORT_LOST: Device loss timer has expired; port is being removed. + * @SRP_RPORT_LOST: Port is being removed. */ enum srp_rport_state { SRP_RPORT_RUNNING, @@ -48,7 +48,6 @@ struct srp_rport { struct mutex mutex; enum srp_rport_state state; - bool deleted; int reconnect_delay; int failed_reconnects; struct delayed_work reconnect_work; @@ -101,6 +100,7 @@ extern int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo, extern int srp_reconnect_rport(struct srp_rport *rport); extern void srp_start_tl_fail_timers(struct srp_rport *rport); extern void srp_remove_host(struct Scsi_Host *); +extern void srp_stop_rport_timers(struct srp_rport *rport); /** * srp_chkready() - evaluate the transport layer state before I/O |