[SCSI] sd: limit the scope of the async probe domain
sd injects and synchronizes probe work on the global kernel-wide domain.
This runs into conflict with PM that wants to perform resume actions in
async context:
[ 494.237079] INFO: task kworker/u:3:554 blocked for more than 120 seconds.
[ 494.294396] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 494.360809] kworker/u:3 D 0000000000000000 0 554 2 0x00000000
[ 494.420739] ffff88012e4d3af0 0000000000000046 ffff88013200c160 ffff88012e4d3fd8
[ 494.484392] ffff88012e4d3fd8 0000000000012500 ffff8801394ea0b0 ffff88013200c160
[ 494.548038] ffff88012e4d3ae0 00000000000001e3 ffffffff81a249e0 ffff8801321c5398
[ 494.611685] Call Trace:
[ 494.632649] [<ffffffff8149dd25>] schedule+0x5a/0x5c
[ 494.674687] [<ffffffff8104b968>] async_synchronize_cookie_domain+0xb6/0x112
[ 494.734177] [<ffffffff810461ff>] ? __init_waitqueue_head+0x50/0x50
[ 494.787134] [<ffffffff8131a224>] ? scsi_remove_target+0x48/0x48
[ 494.837900] [<ffffffff8104b9d9>] async_synchronize_cookie+0x15/0x17
[ 494.891567] [<ffffffff8104ba49>] async_synchronize_full+0x54/0x70 <-- here we wait for async contexts to complete
[ 494.943783] [<ffffffff8104b9f5>] ? async_synchronize_full_domain+0x1a/0x1a
[ 495.002547] [<ffffffffa00114b1>] sd_remove+0x2c/0xa2 [sd_mod]
[ 495.051861] [<ffffffff812fe94f>] __device_release_driver+0x86/0xcf
[ 495.104807] [<ffffffff812fe9bd>] device_release_driver+0x25/0x32 <-- here we take device_lock()
[ 853.511341] INFO: task kworker/u:4:549 blocked for more than 120 seconds.
[ 853.568693] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 853.635119] kworker/u:4 D ffff88013097b5d0 0 549 2 0x00000000
[ 853.695129] ffff880132773c40 0000000000000046 ffff880130790000 ffff880132773fd8
[ 853.758990] ffff880132773fd8 0000000000012500 ffff88013288a0b0 ffff880130790000
[ 853.822796] 0000000000000246 0000000000000040 ffff88013097b5c8 ffff880130790000
[ 853.886633] Call Trace:
[ 853.907631] [<ffffffff8149dd25>] schedule+0x5a/0x5c
[ 853.949670] [<ffffffff8149cc44>] __mutex_lock_common+0x220/0x351
[ 854.001225] [<ffffffff81304bd7>] ? device_resume+0x58/0x1c4
[ 854.049082] [<ffffffff81304bd7>] ? device_resume+0x58/0x1c4
[ 854.097011] [<ffffffff8149ce48>] mutex_lock_nested+0x2f/0x36 <-- here we wait for device_lock()
[ 854.145591] [<ffffffff81304bd7>] device_resume+0x58/0x1c4
[ 854.192066] [<ffffffff81304d61>] async_resume+0x1e/0x45
[ 854.237019] [<ffffffff8104bc93>] async_run_entry_fn+0xc6/0x173 <-- ...while running in async context
Provide a 'scsi_sd_probe_domain' so that async probe actions actions can
be flushed without regard for the state of PM, and allow for the resume
path to handle devices that have transitioned from SDEV_QUIESCE to
SDEV_DEL prior to resume.
Acked-by: Alan Stern <stern@rowland.harvard.edu>
[alan: uplevel scsi_sd_probe_domain, clarify scsi_device_resume]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
[jejb: remove unneeded config guards in include file]
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 07322ec..61c82a3 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -90,6 +90,12 @@
EXPORT_SYMBOL(scsi_logging_level);
#endif
+#if IS_ENABLED(CONFIG_PM) || IS_ENABLED(CONFIG_BLK_DEV_SD)
+/* sd and scsi_pm need to coordinate flushing async actions */
+LIST_HEAD(scsi_sd_probe_domain);
+EXPORT_SYMBOL(scsi_sd_probe_domain);
+#endif
+
/* NB: These are exposed through /proc/scsi/scsi and form part of the ABI.
* You may not alter any existing entry (although adding new ones is
* encouraged once assigned by ANSI/INCITS T10
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index ead6405..dbe4392 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2348,10 +2348,14 @@
*
* Must be called with user context, may sleep.
*/
-void
-scsi_device_resume(struct scsi_device *sdev)
+void scsi_device_resume(struct scsi_device *sdev)
{
- if(scsi_device_set_state(sdev, SDEV_RUNNING))
+ /* check if the device state was mutated prior to resume, and if
+ * so assume the state is being managed elsewhere (for example
+ * device deleted during suspend)
+ */
+ if (sdev->sdev_state != SDEV_QUIESCE ||
+ scsi_device_set_state(sdev, SDEV_RUNNING))
return;
scsi_run_queue(sdev->request_queue);
}
diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c
index c467064..f661a41 100644
--- a/drivers/scsi/scsi_pm.c
+++ b/drivers/scsi/scsi_pm.c
@@ -97,7 +97,7 @@
{
if (scsi_is_sdev_device(dev)) {
/* sd probing uses async_schedule. Wait until it finishes. */
- async_synchronize_full();
+ async_synchronize_full_domain(&scsi_sd_probe_domain);
} else if (scsi_is_host_device(dev)) {
/* Wait until async scanning is finished */
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index be4fa6d..07ce3f5 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -163,6 +163,8 @@
static inline void scsi_autopm_put_host(struct Scsi_Host *h) {}
#endif /* CONFIG_PM_RUNTIME */
+extern struct list_head scsi_sd_probe_domain;
+
/*
* internal scsi timeout functions: for use by mid-layer and transport
* classes.
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 5ba5c2a..6f0a4c6 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -65,6 +65,7 @@
#include <scsi/scsicam.h>
#include "sd.h"
+#include "scsi_priv.h"
#include "scsi_logging.h"
MODULE_AUTHOR("Eric Youngdale");
@@ -2722,7 +2723,7 @@
dev_set_drvdata(dev, sdkp);
get_device(&sdkp->dev); /* prevent release before async_schedule */
- async_schedule(sd_probe_async, sdkp);
+ async_schedule_domain(sd_probe_async, sdkp, &scsi_sd_probe_domain);
return 0;
@@ -2756,7 +2757,7 @@
sdkp = dev_get_drvdata(dev);
scsi_autopm_get_device(sdkp->device);
- async_synchronize_full();
+ async_synchronize_full_domain(&scsi_sd_probe_domain);
blk_queue_prep_rq(sdkp->device->request_queue, scsi_prep_fn);
blk_queue_unprep_rq(sdkp->device->request_queue, NULL);
device_del(&sdkp->dev);