mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2025-02-17 01:17:23 +07:00
08eee69fcf
Admin could reset zram during I/O operation going on so we have used zram->init_lock as read-side lock in I/O path to prevent sudden zram meta freeing. However, the init_lock is really troublesome. We can't do call zram_meta_alloc under init_lock due to lockdep splat because zram_rw_page is one of the function under reclaim path and hold it as read_lock while other places in process context hold it as write_lock. So, we have used allocation out of the lock to avoid lockdep warn but it's not good for readability and fainally, I met another lockdep splat between init_lock and cpu_hotplug from kmem_cache_destroy during working zsmalloc compaction. :( Yes, the ideal is to remove horrible init_lock of zram in rw path. This patch removes it in rw path and instead, add atomic refcount for meta lifetime management and completion to free meta in process context. It's important to free meta in process context because some of resource destruction needs mutex lock, which could be held if we releases the resource in reclaim context so it's deadlock, again. As a bonus, we could remove init_done check in rw path because zram_meta_get will do a role for it, instead. Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Ganesh Mahendran <opensource.ganesh@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
126 lines
3.4 KiB
C
126 lines
3.4 KiB
C
/*
|
|
* 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/zsmalloc.h>
|
|
|
|
#include "zcomp.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 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))
|
|
|
|
|
|
/*
|
|
* The lower ZRAM_FLAG_SHIFT bits of table.value is for
|
|
* object size (excluding header), the higher bits is for
|
|
* zram_pageflags.
|
|
*
|
|
* zram is mainly used for memory efficiency so we want to keep memory
|
|
* footprint small so we can squeeze size and flags into a field.
|
|
* The lower ZRAM_FLAG_SHIFT bits is for object size (excluding header),
|
|
* the higher bits is for zram_pageflags.
|
|
*/
|
|
#define ZRAM_FLAG_SHIFT 24
|
|
|
|
/* Flags for zram pages (table[page_no].value) */
|
|
enum zram_pageflags {
|
|
/* Page consists entirely of zeros */
|
|
ZRAM_ZERO = ZRAM_FLAG_SHIFT,
|
|
ZRAM_ACCESS, /* page is now accessed */
|
|
|
|
__NR_ZRAM_PAGEFLAGS,
|
|
};
|
|
|
|
/*-- Data structures */
|
|
|
|
/* Allocated for each disk page */
|
|
struct zram_table_entry {
|
|
unsigned long handle;
|
|
unsigned long value;
|
|
};
|
|
|
|
struct zram_stats {
|
|
atomic64_t compr_data_size; /* compressed size of pages stored */
|
|
atomic64_t num_reads; /* failed + successful */
|
|
atomic64_t num_writes; /* --do-- */
|
|
atomic64_t failed_reads; /* can happen when memory is too low */
|
|
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 */
|
|
atomic64_t zero_pages; /* no. of zero filled pages */
|
|
atomic64_t pages_stored; /* no. of pages currently stored */
|
|
atomic_long_t max_used_pages; /* no. of maximum pages stored */
|
|
};
|
|
|
|
struct zram_meta {
|
|
struct zram_table_entry *table;
|
|
struct zs_pool *mem_pool;
|
|
};
|
|
|
|
struct zram {
|
|
struct zram_meta *meta;
|
|
struct zcomp *comp;
|
|
struct request_queue *queue;
|
|
struct gendisk *disk;
|
|
/* Prevent concurrent execution of device init */
|
|
struct rw_semaphore init_lock;
|
|
/*
|
|
* the number of pages zram can consume for storing compressed data
|
|
*/
|
|
unsigned long limit_pages;
|
|
int max_comp_streams;
|
|
|
|
struct zram_stats stats;
|
|
atomic_t refcount; /* refcount for zram_meta */
|
|
/* wait all IO under all of cpu are done */
|
|
wait_queue_head_t io_done;
|
|
/*
|
|
* This is the limit on amount of *uncompressed* worth of data
|
|
* we can store in a disk.
|
|
*/
|
|
u64 disksize; /* bytes */
|
|
char compressor[10];
|
|
};
|
|
#endif
|