mirrors/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2024-09-12 21:57:43 +00:00
Code Issues Releases Wiki Activity

scsi: libsas: Don't always drain event workqueue for HA resume

Browse source 
For the hisi_sas driver, if a directly attached disk is removed during
suspend, a hang will occur in the resume process:

The background is that in commit 16fd4a7c59 ("scsi: hisi_sas: Add device
link between SCSI devices and hisi_hba"), it is ensured that the HBA device
cannot be runtime suspended when any SCSI device associated is active.

Other drivers which use libsas don't worry about this as none support
runtime suspend.

The mentioned hang occurs when an disk is removed during suspend. In the
removal process - from PHYE_RESUME_TIMEOUT event processing - we call into
scsi_remove_device(), which is being processed in the HA event workqueue.
Here we wait for all suppliers of the SCSI device to resume, which includes
the HBA device (from the above commit). However the HBA device cannot
resume, as it is waiting for the PHYE_RESUME_TIMEOUT to be processed (from
calling sas_resume_ha() -> sas_drain_work()). This is the deadlock.

There does not appear to be any need for the sas_drain_work() to be called
at all in sas_resume_ha() as it is not syncing against anything, so allow
LLDDs to avoid this by providing a variant of sas_resume_ha() which does
"sync", i.e. doesn't drain the event workqueue.

Link: https://lore.kernel.org/r/1639999298-244569-2-git-send-email-chenxiang66@hisilicon.com
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This commit is contained in:
John Garry 2021-12-20 19:21:24 +08:00 committed by Martin K. Petersen
parent 4be6181fea
commit fbefe22811
3 changed files with 25 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
View file

@ -4950,7 +4950,15 @@ static int _resume_v3_hw(struct device *device)
return rc;
}
phys_init_v3_hw(hisi_hba);
sas_resume_ha(sha);
/*
* If a directly-attached disk is removed during suspend, a deadlock
* may occur, as the PHYE_RESUME_TIMEOUT processing will require the
* hisi_hba->device to be active, which can only happen when resume
* completes. So don't wait for the HA event workqueue to drain upon
* resume.
*/
sas_resume_ha_no_sync(sha);
clear_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags);
return 0;

17
drivers/scsi/libsas/sas_init.c
View file

@ -387,7 +387,7 @@ static int phys_suspended(struct sas_ha_struct *ha)
return rc;
}
void sas_resume_ha(struct sas_ha_struct *ha)
static void _sas_resume_ha(struct sas_ha_struct *ha, bool drain)
{
const unsigned long tmo = msecs_to_jiffies(25000);
int i;
@ -417,10 +417,23 @@ void sas_resume_ha(struct sas_ha_struct *ha)
* flush out disks that did not return
*/
scsi_unblock_requests(ha->core.shost);
sas_drain_work(ha);
if (drain)
sas_drain_work(ha);
}
void sas_resume_ha(struct sas_ha_struct *ha)
{
_sas_resume_ha(ha, true);
}
EXPORT_SYMBOL(sas_resume_ha);
/* A no-sync variant, which does not call sas_drain_ha(). */
void sas_resume_ha_no_sync(struct sas_ha_struct *ha)
{
_sas_resume_ha(ha, false);
}
EXPORT_SYMBOL(sas_resume_ha_no_sync);
void sas_suspend_ha(struct sas_ha_struct *ha)
{
int i;

1
include/scsi/libsas.h
View file

@ -660,6 +660,7 @@ extern int sas_register_ha(struct sas_ha_struct *);
extern int sas_unregister_ha(struct sas_ha_struct *);
extern void sas_prep_resume_ha(struct sas_ha_struct *sas_ha);
extern void sas_resume_ha(struct sas_ha_struct *sas_ha);
extern void sas_resume_ha_no_sync(struct sas_ha_struct *sas_ha);
extern void sas_suspend_ha(struct sas_ha_struct *sas_ha);
int sas_set_phy_speed(struct sas_phy *phy, struct sas_phy_linkrates *rates);