mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 08:19:28 +00:00
![Minchan Kim](/assets/img/avatar_default.png)
[1] introduced down_write in zram_slot_free_notify to prevent race
between zram_slot_free_notify and zram_bvec_[read|write]. The race
could happen if somebody who has right permission to open swap device
is reading swap device while it is used by swap in parallel.
However, zram_slot_free_notify is called with holding spin_lock of
swap layer so we shouldn't avoid holing mutex. Otherwise, lockdep
warns it.
This patch adds new list to handle free slot and workqueue
so zram_slot_free_notify just registers slot index to be freed and
registers the request to workqueue. If workqueue is expired,
it holds mutex_lock so there is no problem any more.
If any I/O is issued, zram handles pending slot-free request
caused by zram_slot_free_notify right before handling issued
request because workqueue wouldn't be expired yet so zram I/O
request handling function can miss it.
Lastly, when zram is reset, flush_work could handle all of pending
free request so we shouldn't have memory leak.
NOTE: If zram_slot_free_notify's kmalloc with GFP_ATOMIC would be
failed, the slot will be freed when next write I/O write the slot.
[1] [57ab0485
, zram: use zram->lock to protect zram_free_page()
in swap free notify path]
* from v2
* refactoring
* from v1
* totally redesign
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: stable@vger.kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
125 lines
3.4 KiB
C
125 lines
3.4 KiB
C
/*
|
|
* Compressed RAM block device
|
|
*
|
|
* Copyright (C) 2008, 2009, 2010 Nitin Gupta
|
|
*
|
|
* This code is released using a dual license strategy: BSD/GPL
|
|
* You can choose the licence that better fits your requirements.
|
|
*
|
|
* Released under the terms of 3-clause BSD License
|
|
* Released under the terms of GNU General Public License Version 2.0
|
|
*
|
|
* Project home: http://compcache.googlecode.com
|
|
*/
|
|
|
|
#ifndef _ZRAM_DRV_H_
|
|
#define _ZRAM_DRV_H_
|
|
|
|
#include <linux/spinlock.h>
|
|
#include <linux/mutex.h>
|
|
|
|
#include "../zsmalloc/zsmalloc.h"
|
|
|
|
/*
|
|
* Some arbitrary value. This is just to catch
|
|
* invalid value for num_devices module parameter.
|
|
*/
|
|
static const unsigned max_num_devices = 32;
|
|
|
|
/*-- Configurable parameters */
|
|
|
|
/*
|
|
* Pages that compress to size greater than this are stored
|
|
* uncompressed in memory.
|
|
*/
|
|
static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
|
|
|
|
/*
|
|
* NOTE: max_zpage_size must be less than or equal to:
|
|
* ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
|
|
* always return failure.
|
|
*/
|
|
|
|
/*-- End of configurable params */
|
|
|
|
#define SECTOR_SHIFT 9
|
|
#define SECTOR_SIZE (1 << SECTOR_SHIFT)
|
|
#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
|
|
#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
|
|
#define ZRAM_LOGICAL_BLOCK_SHIFT 12
|
|
#define ZRAM_LOGICAL_BLOCK_SIZE (1 << ZRAM_LOGICAL_BLOCK_SHIFT)
|
|
#define ZRAM_SECTOR_PER_LOGICAL_BLOCK \
|
|
(1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
|
|
|
|
/* Flags for zram pages (table[page_no].flags) */
|
|
enum zram_pageflags {
|
|
/* Page consists entirely of zeros */
|
|
ZRAM_ZERO,
|
|
|
|
__NR_ZRAM_PAGEFLAGS,
|
|
};
|
|
|
|
/*-- Data structures */
|
|
|
|
/* Allocated for each disk page */
|
|
struct table {
|
|
unsigned long handle;
|
|
u16 size; /* object size (excluding header) */
|
|
u8 count; /* object ref count (not yet used) */
|
|
u8 flags;
|
|
} __aligned(4);
|
|
|
|
/*
|
|
* All 64bit fields should only be manipulated by 64bit atomic accessors.
|
|
* All modifications to 32bit counter should be protected by zram->lock.
|
|
*/
|
|
struct zram_stats {
|
|
atomic64_t compr_size; /* compressed size of pages stored */
|
|
atomic64_t num_reads; /* failed + successful */
|
|
atomic64_t num_writes; /* --do-- */
|
|
atomic64_t failed_reads; /* should NEVER! happen */
|
|
atomic64_t failed_writes; /* can happen when memory is too low */
|
|
atomic64_t invalid_io; /* non-page-aligned I/O requests */
|
|
atomic64_t notify_free; /* no. of swap slot free notifications */
|
|
u32 pages_zero; /* no. of zero filled pages */
|
|
u32 pages_stored; /* no. of pages currently stored */
|
|
u32 good_compress; /* % of pages with compression ratio<=50% */
|
|
u32 bad_compress; /* % of pages with compression ratio>=75% */
|
|
};
|
|
|
|
struct zram_meta {
|
|
void *compress_workmem;
|
|
void *compress_buffer;
|
|
struct table *table;
|
|
struct zs_pool *mem_pool;
|
|
};
|
|
|
|
struct zram_slot_free {
|
|
unsigned long index;
|
|
struct zram_slot_free *next;
|
|
};
|
|
|
|
struct zram {
|
|
struct zram_meta *meta;
|
|
struct rw_semaphore lock; /* protect compression buffers, table,
|
|
* 32bit stat counters against concurrent
|
|
* notifications, reads and writes */
|
|
|
|
struct work_struct free_work; /* handle pending free request */
|
|
struct zram_slot_free *slot_free_rq; /* list head of free request */
|
|
|
|
struct request_queue *queue;
|
|
struct gendisk *disk;
|
|
int init_done;
|
|
/* Prevent concurrent execution of device init, reset and R/W request */
|
|
struct rw_semaphore init_lock;
|
|
/*
|
|
* This is the limit on amount of *uncompressed* worth of data
|
|
* we can store in a disk.
|
|
*/
|
|
u64 disksize; /* bytes */
|
|
spinlock_t slot_free_lock;
|
|
|
|
struct zram_stats stats;
|
|
};
|
|
#endif
|