linux/drivers/block/zram/zram_drv.h

125 lines
3.4 KiB
C
Raw Normal View History

/*
* Compressed RAM block device
*
* Copyright (C) 2008, 2009, 2010 Nitin Gupta
* 2012, 2013 Minchan Kim
*
* 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
*
*/
#ifndef _ZRAM_DRV_H_
#define _ZRAM_DRV_H_
#include <linux/spinlock.h>
#include <linux/mutex.h>
zsmalloc: move it under mm This patch moves zsmalloc under mm directory. Before that, description will explain why we have needed custom allocator. Zsmalloc is a new slab-based memory allocator for storing compressed pages. It is designed for low fragmentation and high allocation success rate on large object, but <= PAGE_SIZE allocations. zsmalloc differs from the kernel slab allocator in two primary ways to achieve these design goals. zsmalloc never requires high order page allocations to back slabs, or "size classes" in zsmalloc terms. Instead it allows multiple single-order pages to be stitched together into a "zspage" which backs the slab. This allows for higher allocation success rate under memory pressure. Also, zsmalloc allows objects to span page boundaries within the zspage. This allows for lower fragmentation than could be had with the kernel slab allocator for objects between PAGE_SIZE/2 and PAGE_SIZE. With the kernel slab allocator, if a page compresses to 60% of it original size, the memory savings gained through compression is lost in fragmentation because another object of the same size can't be stored in the leftover space. This ability to span pages results in zsmalloc allocations not being directly addressable by the user. The user is given an non-dereferencable handle in response to an allocation request. That handle must be mapped, using zs_map_object(), which returns a pointer to the mapped region that can be used. The mapping is necessary since the object data may reside in two different noncontigious pages. The zsmalloc fulfills the allocation needs for zram perfectly [sjenning@linux.vnet.ibm.com: borrow Seth's quote] Signed-off-by: Minchan Kim <minchan@kernel.org> Acked-by: Nitin Gupta <ngupta@vflare.org> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Hugh Dickins <hughd@google.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Pekka Enberg <penberg@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-30 23:45:50 +00:00
#include <linux/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;
};
zram: don't grab mutex in zram_slot_free_noity [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>
2013-08-12 06:13:56 +00:00
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 */
zram: don't grab mutex in zram_slot_free_noity [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>
2013-08-12 06:13:56 +00:00
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 */
zram: don't grab mutex in zram_slot_free_noity [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>
2013-08-12 06:13:56 +00:00
spinlock_t slot_free_lock;
struct zram_stats stats;
};
#endif