Revision df9576def004d2cd5beedc00cb6e8901427634b9 authored by Yang Shi on 03 August 2019, 04:48:37 UTC, committed by Linus Torvalds on 03 August 2019, 14:02:00 UTC
When running ltp's oom test with kmemleak enabled, the below warning was
triggerred since kernel detects __GFP_NOFAIL & ~__GFP_DIRECT_RECLAIM is
passed in:

  WARNING: CPU: 105 PID: 2138 at mm/page_alloc.c:4608 __alloc_pages_nodemask+0x1c31/0x1d50
  Modules linked in: loop dax_pmem dax_pmem_core ip_tables x_tables xfs virtio_net net_failover virtio_blk failover ata_generic virtio_pci virtio_ring virtio libata
  CPU: 105 PID: 2138 Comm: oom01 Not tainted 5.2.0-next-20190710+ #7
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.2-0-g5f4c7b1-prebuilt.qemu-project.org 04/01/2014
  RIP: 0010:__alloc_pages_nodemask+0x1c31/0x1d50
  ...
   kmemleak_alloc+0x4e/0xb0
   kmem_cache_alloc+0x2a7/0x3e0
   mempool_alloc_slab+0x2d/0x40
   mempool_alloc+0x118/0x2b0
   bio_alloc_bioset+0x19d/0x350
   get_swap_bio+0x80/0x230
   __swap_writepage+0x5ff/0xb20

The mempool_alloc_slab() clears __GFP_DIRECT_RECLAIM, however kmemleak
has __GFP_NOFAIL set all the time due to d9570ee3bd1d4f2 ("kmemleak:
allow to coexist with fault injection").  But, it doesn't make any sense
to have __GFP_NOFAIL and ~__GFP_DIRECT_RECLAIM specified at the same
time.

According to the discussion on the mailing list, the commit should be
reverted for short term solution.  Catalin Marinas would follow up with
a better solution for longer term.

The failure rate of kmemleak metadata allocation may increase in some
circumstances, but this should be expected side effect.

Link: http://lkml.kernel.org/r/1563299431-111710-1-git-send-email-yang.shi@linux.alibaba.com
Fixes: d9570ee3bd1d4f2 ("kmemleak: allow to coexist with fault injection")
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Suggested-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 68d8681
Raw File
blk-pm.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);

	/*
	 * 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);

	spin_lock_irq(&q->queue_lock);
	if (ret < 0)
		pm_runtime_mark_last_busy(q->dev);
	else
		q->rpm_status = RPM_SUSPENDING;
	spin_unlock_irq(&q->queue_lock);

	if (ret)
		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
 * @err: return value of the device's runtime_resume function
 *
 * Description:
 *    Update the queue's runtime status according to the return value of the
 *    device's runtime_resume function. If it is successfully resumed, process
 *    the requests that are queued into the device's queue when it is resuming
 *    and then mark last busy and initiate autosuspend for it.
 *
 *    This function should be called near the end of the device's
 *    runtime_resume callback.
 */
void blk_post_runtime_resume(struct request_queue *q, int err)
{
	if (!q->dev)
		return;

	spin_lock_irq(&q->queue_lock);
	if (!err) {
		q->rpm_status = RPM_ACTIVE;
		pm_runtime_mark_last_busy(q->dev);
		pm_request_autosuspend(q->dev);
	} else {
		q->rpm_status = RPM_SUSPENDED;
	}
	spin_unlock_irq(&q->queue_lock);

	if (!err)
		blk_clear_pm_only(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.
 */
void blk_set_runtime_active(struct request_queue *q)
{
	spin_lock_irq(&q->queue_lock);
	q->rpm_status = RPM_ACTIVE;
	pm_runtime_mark_last_busy(q->dev);
	pm_request_autosuspend(q->dev);
	spin_unlock_irq(&q->queue_lock);
}
EXPORT_SYMBOL(blk_set_runtime_active);
back to top