forked from mirrors/linux
8e04944f0e
syzbot is catching so many bugs triggered by commit 9ee332d99e
("sget(): handle failures of register_shrinker()"). That commit expected
that calling kill_sb() from deactivate_locked_super() without successful
fill_super() is safe, but the reality was different; some callers assign
attributes which are needed for kill_sb() after sget() succeeds.
For example, [1] is a report where sb->s_mode (which seems to be either
FMODE_READ | FMODE_EXCL | FMODE_WRITE or FMODE_READ | FMODE_EXCL) is not
assigned unless sget() succeeds. But it does not worth complicate sget()
so that register_shrinker() failure path can safely call
kill_block_super() via kill_sb(). Making alloc_super() fail if memory
allocation for register_shrinker() failed is much simpler. Let's avoid
calling deactivate_locked_super() from sget_userns() by preallocating
memory for the shrinker and making register_shrinker() in sget_userns()
never fail.
[1] https://syzkaller.appspot.com/bug?id=588996a25a2587be2e3a54e8646728fb9cae44e7
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reported-by: syzbot <syzbot+5a170e19c963a2e0df79@syzkaller.appspotmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
83 lines
2.8 KiB
C
83 lines
2.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_SHRINKER_H
|
|
#define _LINUX_SHRINKER_H
|
|
|
|
/*
|
|
* This struct is used to pass information from page reclaim to the shrinkers.
|
|
* We consolidate the values for easier extention later.
|
|
*
|
|
* The 'gfpmask' refers to the allocation we are currently trying to
|
|
* fulfil.
|
|
*/
|
|
struct shrink_control {
|
|
gfp_t gfp_mask;
|
|
|
|
/*
|
|
* How many objects scan_objects should scan and try to reclaim.
|
|
* This is reset before every call, so it is safe for callees
|
|
* to modify.
|
|
*/
|
|
unsigned long nr_to_scan;
|
|
|
|
/*
|
|
* How many objects did scan_objects process?
|
|
* This defaults to nr_to_scan before every call, but the callee
|
|
* should track its actual progress.
|
|
*/
|
|
unsigned long nr_scanned;
|
|
|
|
/* current node being shrunk (for NUMA aware shrinkers) */
|
|
int nid;
|
|
|
|
/* current memcg being shrunk (for memcg aware shrinkers) */
|
|
struct mem_cgroup *memcg;
|
|
};
|
|
|
|
#define SHRINK_STOP (~0UL)
|
|
/*
|
|
* A callback you can register to apply pressure to ageable caches.
|
|
*
|
|
* @count_objects should return the number of freeable items in the cache. If
|
|
* there are no objects to free or the number of freeable items cannot be
|
|
* determined, it should return 0. No deadlock checks should be done during the
|
|
* count callback - the shrinker relies on aggregating scan counts that couldn't
|
|
* be executed due to potential deadlocks to be run at a later call when the
|
|
* deadlock condition is no longer pending.
|
|
*
|
|
* @scan_objects will only be called if @count_objects returned a non-zero
|
|
* value for the number of freeable objects. The callout should scan the cache
|
|
* and attempt to free items from the cache. It should then return the number
|
|
* of objects freed during the scan, or SHRINK_STOP if progress cannot be made
|
|
* due to potential deadlocks. If SHRINK_STOP is returned, then no further
|
|
* attempts to call the @scan_objects will be made from the current reclaim
|
|
* context.
|
|
*
|
|
* @flags determine the shrinker abilities, like numa awareness
|
|
*/
|
|
struct shrinker {
|
|
unsigned long (*count_objects)(struct shrinker *,
|
|
struct shrink_control *sc);
|
|
unsigned long (*scan_objects)(struct shrinker *,
|
|
struct shrink_control *sc);
|
|
|
|
int seeks; /* seeks to recreate an obj */
|
|
long batch; /* reclaim batch size, 0 = default */
|
|
unsigned long flags;
|
|
|
|
/* These are for internal use */
|
|
struct list_head list;
|
|
/* objs pending delete, per node */
|
|
atomic_long_t *nr_deferred;
|
|
};
|
|
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
|
|
|
|
/* Flags */
|
|
#define SHRINKER_NUMA_AWARE (1 << 0)
|
|
#define SHRINKER_MEMCG_AWARE (1 << 1)
|
|
|
|
extern int prealloc_shrinker(struct shrinker *shrinker);
|
|
extern void register_shrinker_prepared(struct shrinker *shrinker);
|
|
extern int register_shrinker(struct shrinker *shrinker);
|
|
extern void unregister_shrinker(struct shrinker *shrinker);
|
|
extern void free_prealloced_shrinker(struct shrinker *shrinker);
|
|
#endif
|