mirror of
https://github.com/torvalds/linux.git
synced 2024-11-23 12:42:02 +00:00
6e1fcab00a
John Garry reported a deadlock that occurs when trying to access a
runtime-suspended SATA device. For obscure reasons, the rescan procedure
causes the link to be hard-reset, which disconnects the device.
The rescan tries to carry out a runtime resume when accessing the device.
scsi_rescan_device() holds the SCSI device lock and won't release it until
it can put commands onto the device's block queue. This can't happen until
the queue is successfully runtime-resumed or the device is unregistered.
But the runtime resume fails because the device is disconnected, and
__scsi_remove_device() can't do the unregistration because it can't get the
device lock.
The best way to resolve this deadlock appears to be to allow the block
queue to start running again even after an unsuccessful runtime resume.
The idea is that the driver or the SCSI error handler will need to be able
to use the queue to resolve the runtime resume failure.
This patch removes the err argument to blk_post_runtime_resume() and makes
the routine act as though the resume was successful always. This fixes the
deadlock.
Link: https://lore.kernel.org/r/1639999298-244569-4-git-send-email-chenxiang66@hisilicon.com
Fixes: e27829dc92
("scsi: serialize ->rescan against ->remove")
Reported-and-tested-by: John Garry <john.garry@huawei.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
217 lines
6.6 KiB
C
217 lines
6.6 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
#include <linux/blk-mq.h>
|
|
#include <linux/blk-pm.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/pm_runtime.h>
|
|
#include "blk-mq.h"
|
|
#include "blk-mq-tag.h"
|
|
|
|
/**
|
|
* blk_pm_runtime_init - Block layer runtime PM initialization routine
|
|
* @q: the queue of the device
|
|
* @dev: the device the queue belongs to
|
|
*
|
|
* Description:
|
|
* Initialize runtime-PM-related fields for @q and start auto suspend for
|
|
* @dev. Drivers that want to take advantage of request-based runtime PM
|
|
* should call this function after @dev has been initialized, and its
|
|
* request queue @q has been allocated, and runtime PM for it can not happen
|
|
* yet(either due to disabled/forbidden or its usage_count > 0). In most
|
|
* cases, driver should call this function before any I/O has taken place.
|
|
*
|
|
* This function takes care of setting up using auto suspend for the device,
|
|
* the autosuspend delay is set to -1 to make runtime suspend impossible
|
|
* until an updated value is either set by user or by driver. Drivers do
|
|
* not need to touch other autosuspend settings.
|
|
*
|
|
* The block layer runtime PM is request based, so only works for drivers
|
|
* that use request as their IO unit instead of those directly use bio's.
|
|
*/
|
|
void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
|
|
{
|
|
q->dev = dev;
|
|
q->rpm_status = RPM_ACTIVE;
|
|
pm_runtime_set_autosuspend_delay(q->dev, -1);
|
|
pm_runtime_use_autosuspend(q->dev);
|
|
}
|
|
EXPORT_SYMBOL(blk_pm_runtime_init);
|
|
|
|
/**
|
|
* blk_pre_runtime_suspend - Pre runtime suspend check
|
|
* @q: the queue of the device
|
|
*
|
|
* Description:
|
|
* This function will check if runtime suspend is allowed for the device
|
|
* by examining if there are any requests pending in the queue. If there
|
|
* are requests pending, the device can not be runtime suspended; otherwise,
|
|
* the queue's status will be updated to SUSPENDING and the driver can
|
|
* proceed to suspend the device.
|
|
*
|
|
* For the not allowed case, we mark last busy for the device so that
|
|
* runtime PM core will try to autosuspend it some time later.
|
|
*
|
|
* This function should be called near the start of the device's
|
|
* runtime_suspend callback.
|
|
*
|
|
* Return:
|
|
* 0 - OK to runtime suspend the device
|
|
* -EBUSY - Device should not be runtime suspended
|
|
*/
|
|
int blk_pre_runtime_suspend(struct request_queue *q)
|
|
{
|
|
int ret = 0;
|
|
|
|
if (!q->dev)
|
|
return ret;
|
|
|
|
WARN_ON_ONCE(q->rpm_status != RPM_ACTIVE);
|
|
|
|
spin_lock_irq(&q->queue_lock);
|
|
q->rpm_status = RPM_SUSPENDING;
|
|
spin_unlock_irq(&q->queue_lock);
|
|
|
|
/*
|
|
* Increase the pm_only counter before checking whether any
|
|
* non-PM blk_queue_enter() calls are in progress to avoid that any
|
|
* new non-PM blk_queue_enter() calls succeed before the pm_only
|
|
* counter is decreased again.
|
|
*/
|
|
blk_set_pm_only(q);
|
|
ret = -EBUSY;
|
|
/* Switch q_usage_counter from per-cpu to atomic mode. */
|
|
blk_freeze_queue_start(q);
|
|
/*
|
|
* Wait until atomic mode has been reached. Since that
|
|
* involves calling call_rcu(), it is guaranteed that later
|
|
* blk_queue_enter() calls see the pm-only state. See also
|
|
* http://lwn.net/Articles/573497/.
|
|
*/
|
|
percpu_ref_switch_to_atomic_sync(&q->q_usage_counter);
|
|
if (percpu_ref_is_zero(&q->q_usage_counter))
|
|
ret = 0;
|
|
/* Switch q_usage_counter back to per-cpu mode. */
|
|
blk_mq_unfreeze_queue(q);
|
|
|
|
if (ret < 0) {
|
|
spin_lock_irq(&q->queue_lock);
|
|
q->rpm_status = RPM_ACTIVE;
|
|
pm_runtime_mark_last_busy(q->dev);
|
|
spin_unlock_irq(&q->queue_lock);
|
|
|
|
blk_clear_pm_only(q);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(blk_pre_runtime_suspend);
|
|
|
|
/**
|
|
* blk_post_runtime_suspend - Post runtime suspend processing
|
|
* @q: the queue of the device
|
|
* @err: return value of the device's runtime_suspend function
|
|
*
|
|
* Description:
|
|
* Update the queue's runtime status according to the return value of the
|
|
* device's runtime suspend function and mark last busy for the device so
|
|
* that PM core will try to auto suspend the device at a later time.
|
|
*
|
|
* This function should be called near the end of the device's
|
|
* runtime_suspend callback.
|
|
*/
|
|
void blk_post_runtime_suspend(struct request_queue *q, int err)
|
|
{
|
|
if (!q->dev)
|
|
return;
|
|
|
|
spin_lock_irq(&q->queue_lock);
|
|
if (!err) {
|
|
q->rpm_status = RPM_SUSPENDED;
|
|
} else {
|
|
q->rpm_status = RPM_ACTIVE;
|
|
pm_runtime_mark_last_busy(q->dev);
|
|
}
|
|
spin_unlock_irq(&q->queue_lock);
|
|
|
|
if (err)
|
|
blk_clear_pm_only(q);
|
|
}
|
|
EXPORT_SYMBOL(blk_post_runtime_suspend);
|
|
|
|
/**
|
|
* blk_pre_runtime_resume - Pre runtime resume processing
|
|
* @q: the queue of the device
|
|
*
|
|
* Description:
|
|
* Update the queue's runtime status to RESUMING in preparation for the
|
|
* runtime resume of the device.
|
|
*
|
|
* This function should be called near the start of the device's
|
|
* runtime_resume callback.
|
|
*/
|
|
void blk_pre_runtime_resume(struct request_queue *q)
|
|
{
|
|
if (!q->dev)
|
|
return;
|
|
|
|
spin_lock_irq(&q->queue_lock);
|
|
q->rpm_status = RPM_RESUMING;
|
|
spin_unlock_irq(&q->queue_lock);
|
|
}
|
|
EXPORT_SYMBOL(blk_pre_runtime_resume);
|
|
|
|
/**
|
|
* blk_post_runtime_resume - Post runtime resume processing
|
|
* @q: the queue of the device
|
|
*
|
|
* Description:
|
|
* For historical reasons, this routine merely calls blk_set_runtime_active()
|
|
* to do the real work of restarting the queue. It does this regardless of
|
|
* whether the device's runtime-resume succeeded; even if it failed the
|
|
* driver or error handler will need to communicate with the device.
|
|
*
|
|
* This function should be called near the end of the device's
|
|
* runtime_resume callback.
|
|
*/
|
|
void blk_post_runtime_resume(struct request_queue *q)
|
|
{
|
|
blk_set_runtime_active(q);
|
|
}
|
|
EXPORT_SYMBOL(blk_post_runtime_resume);
|
|
|
|
/**
|
|
* blk_set_runtime_active - Force runtime status of the queue to be active
|
|
* @q: the queue of the device
|
|
*
|
|
* If the device is left runtime suspended during system suspend the resume
|
|
* hook typically resumes the device and corrects runtime status
|
|
* accordingly. However, that does not affect the queue runtime PM status
|
|
* which is still "suspended". This prevents processing requests from the
|
|
* queue.
|
|
*
|
|
* This function can be used in driver's resume hook to correct queue
|
|
* runtime PM status and re-enable peeking requests from the queue. It
|
|
* should be called before first request is added to the queue.
|
|
*
|
|
* This function is also called by blk_post_runtime_resume() for
|
|
* runtime resumes. It does everything necessary to restart the queue.
|
|
*/
|
|
void blk_set_runtime_active(struct request_queue *q)
|
|
{
|
|
int old_status;
|
|
|
|
if (!q->dev)
|
|
return;
|
|
|
|
spin_lock_irq(&q->queue_lock);
|
|
old_status = q->rpm_status;
|
|
q->rpm_status = RPM_ACTIVE;
|
|
pm_runtime_mark_last_busy(q->dev);
|
|
pm_request_autosuspend(q->dev);
|
|
spin_unlock_irq(&q->queue_lock);
|
|
|
|
if (old_status != RPM_ACTIVE)
|
|
blk_clear_pm_only(q);
|
|
}
|
|
EXPORT_SYMBOL(blk_set_runtime_active);
|