| Message ID | 20191125165702.1013-1-r.bolshakov@yadro.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | scsi: qla2xxx: Bug fixes | expand |
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.
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
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.
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.
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!
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(-)