Skip to main content

Browse the archive

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 
Revert "kmemleak: allow to coexist with fault injection"
 
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-mq-tag.h 
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef INT_BLK_MQ_TAG_H
#define INT_BLK_MQ_TAG_H

#include "blk-mq.h"

/*
 * Tag address space map.
 */
struct blk_mq_tags {
	unsigned int nr_tags;
	unsigned int nr_reserved_tags;

	atomic_t active_queues;

	struct sbitmap_queue bitmap_tags;
	struct sbitmap_queue breserved_tags;

	struct request **rqs;
	struct request **static_rqs;
	struct list_head page_list;
};


extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy);
extern void blk_mq_free_tags(struct blk_mq_tags *tags);

extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
			   struct blk_mq_ctx *ctx, unsigned int tag);
extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
					struct blk_mq_tags **tags,
					unsigned int depth, bool can_grow);
extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
		void *priv);

static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt,
						 struct blk_mq_hw_ctx *hctx)
{
	if (!hctx)
		return &bt->ws[0];
	return sbq_wait_ptr(bt, &hctx->wait_index);
}

enum {
	BLK_MQ_TAG_FAIL		= -1U,
	BLK_MQ_TAG_MIN		= 1,
	BLK_MQ_TAG_MAX		= BLK_MQ_TAG_FAIL - 1,
};

extern bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *);
extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);

static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
{
	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
		return false;

	return __blk_mq_tag_busy(hctx);
}

static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
{
	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
		return;

	__blk_mq_tag_idle(hctx);
}

/*
 * This helper should only be used for flush request to share tag
 * with the request cloned from, and both the two requests can't be
 * in flight at the same time. The caller has to make sure the tag
 * can't be freed.
 */
static inline void blk_mq_tag_set_rq(struct blk_mq_hw_ctx *hctx,
		unsigned int tag, struct request *rq)
{
	hctx->tags->rqs[tag] = rq;
}

static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags,
					  unsigned int tag)
{
	return tag < tags->nr_reserved_tags;
}

#endif
back to top