[v3,00/13] scsi: qla2xxx: Bug fixes
mbox series

Message ID 20191125165702.1013-1-r.bolshakov@yadro.com
Headers show
Series
  • scsi: qla2xxx: Bug fixes
Related show

Message

Roman Bolshakov Nov. 25, 2019, 4:56 p.m. UTC
Hi Martin,

The patch series contains fixes for qla2xxx and solves two visible
issues:
  - Target port in N2N topology doesn't perform login if it has higher
    WWPN than initiator
  - ABORT TASK TMF leads to crash if it's received shortly after ACL of
    an initiator is deleted and there's active I/O from the initiator

It also contains reliability improvements and cleanups.

Changes since v2 (https://patchwork.kernel.org/cover/11254937/):
- Target is allowed to perform PLOGI only if it detects N2N mode;
- Dropped patches to improve ABTS handling for ports that are not
  currently logged in. They will go into a separate patch series.
Changes since v1 (https://patchwork.kernel.org/cover/11141979/):
- Fixes target port in N2N mode were added (patches 5-11);
- Target port makes explicit LOGO on session teardown in the patch made
  by Quinn. Together with patch 1, it helps to immediately turn
  fc_remote_port to the Blocked stated on client side and avoids visibly
  stuck session;
- The last three patches address violation of FCP specification with
  regards to handling of ABTS-LS from ports that are not currently
  logged in.

Thank you,
Roman

Quinn Tran (1):
  scsi: qla2xxx: Use explicit LOGO in target mode

Roman Bolshakov (12):
  scsi: qla2xxx: Ignore NULL pointer in tcm_qla2xxx_free_mcmd
  scsi: qla2xxx: Initialize free_work before flushing it
  scsi: qla2xxx: Drop superfluous INIT_WORK of del_work
  scsi: qla2xxx: Change discovery state before PLOGI
  scsi: qla2xxx: Allow PLOGI in target mode
  scsi: qla2xxx: Don't call qlt_async_event twice
  scsi: qla2xxx: Fix PLOGI payload and ELS IOCB dump length
  scsi: qla2xxx: Configure local loop for N2N target
  scsi: qla2xxx: Send Notify ACK after N2N PLOGI
  scsi: qla2xxx: Don't defer relogin unconditonally
  scsi: qla2xxx: Ignore PORT UPDATE after N2N PLOGI
  scsi: qla2xxx: Add debug dump of LOGO payload and ELS IOCB

 drivers/scsi/qla2xxx/qla_def.h     |  1 +
 drivers/scsi/qla2xxx/qla_init.c    | 21 ++++++++++----------
 drivers/scsi/qla2xxx/qla_iocb.c    | 31 ++++++++++++++++++++++++------
 drivers/scsi/qla2xxx/qla_isr.c     |  4 ----
 drivers/scsi/qla2xxx/qla_mbx.c     |  3 ++-
 drivers/scsi/qla2xxx/qla_target.c  |  4 ++--
 drivers/scsi/qla2xxx/tcm_qla2xxx.c |  3 +++
 7 files changed, 43 insertions(+), 24 deletions(-)

Comments

Bart Van Assche Nov. 26, 2019, 8:56 p.m. UTC | #1
On 11/25/19 8:56 AM, Roman Bolshakov wrote:
> The patch series contains fixes for qla2xxx and solves two visible
> issues: [ ... ]

As explained in Documentation/process/2.Process.rst, please post patches 
outside the merge window.

Thanks,

Bart.
Roman Bolshakov Nov. 27, 2019, 5:24 p.m. UTC | #2
On Tue, Nov 26, 2019 at 12:56:51PM -0800, Bart Van Assche wrote:
> On 11/25/19 8:56 AM, Roman Bolshakov wrote:
> > The patch series contains fixes for qla2xxx and solves two visible
> > issues: [ ... ]
> 
> As explained in Documentation/process/2.Process.rst, please post patches
> outside the merge window.
> 
> Thanks,
> 
> Bart.

Hi Bart,

Thank you for the reference. Could you please assess if my understanding
of the document is correct:
	The fixes might go into 5.5-rc2 after the release of rc1 which
	closes the merge window.

	No patches except critical for -rc1 should be posted when the
	merge window is opened.

Best regards,
Roman
Bart Van Assche Nov. 27, 2019, 5:34 p.m. UTC | #3
On 11/27/19 9:24 AM, Roman Bolshakov wrote:
> On Tue, Nov 26, 2019 at 12:56:51PM -0800, Bart Van Assche wrote:
>> On 11/25/19 8:56 AM, Roman Bolshakov wrote:
>>> The patch series contains fixes for qla2xxx and solves two visible
>>> issues: [ ... ]
>>
>> As explained in Documentation/process/2.Process.rst, please post patches
>> outside the merge window.
> 
> Thank you for the reference. Could you please assess if my understanding
> of the document is correct:
> 	The fixes might go into 5.5-rc2 after the release of rc1 which
> 	closes the merge window.
> 
> 	No patches except critical for -rc1 should be posted when the
> 	merge window is opened.

Hi Roman,

During the merge window many maintainers and core contributors are busy 
with identifying and addressing regressions introduced during the merge 
window. I think that is why the merge window is not the best time to 
post patches and why that text was added to the kernel documentation.

What happens with patches posted during the merge window depends on the 
maintainer (Martin Petersen). Sometimes patches posted during the merge 
window are ignored. Sometimes such patches are queued after the merge 
window has closed. Sometimes contributors are asked after the merge 
window has closed to rebase their patch series, to retest it and to 
repost it. The latter makes sense because the changes accepted during 
the merge window (e.g. core kernel API changes) may require matching 
changes in a patch series. You may want to ask Martin directly which 
approach he prefers after the merge window has closed.

Bart.
Martin K. Petersen Nov. 28, 2019, 12:18 p.m. UTC | #4
Bart,

> What happens with patches posted during the merge window depends on
> the maintainer (Martin Petersen). Sometimes patches posted during the
> merge window are ignored. Sometimes such patches are queued after the
> merge window has closed. Sometimes contributors are asked after the
> merge window has closed to rebase their patch series, to retest it and
> to repost it.

Bug fixes are OK at any time, as far as I'm concerned. Although this
series is a bit big to deal with given that we're now in the merge
window.

As a rule of thumb, I won't look closely at anything resembling new
feature series until -rc1 is out.
Martin K. Petersen Dec. 9, 2019, 11:36 p.m. UTC | #5
Roman,

> The patch series contains fixes for qla2xxx and solves two visible
> issues:
>   - Target port in N2N topology doesn't perform login if it has higher
>     WWPN than initiator
>   - ABORT TASK TMF leads to crash if it's received shortly after ACL of
>     an initiator is deleted and there's active I/O from the initiator

I was concerned about the churn in this series but the actual code
changes are mostly simple and to the point.

Applied to 5.5/scsi-fixes with a couple of checkpatch tweaks. Thanks!