UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/drivers/block/zram/zram_drv.c

2561 lines
61 KiB
C
Raw Blame 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
*
*/
#define KMSG_COMPONENT "zram"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/device.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/string.h>
#include <linux/vmalloc.h>
#include <linux/err.h>
#include <linux/idr.h>
#include <linux/sysfs.h>
#include <linux/debugfs.h>
#include <linux/cpuhotplug.h>
#include <linux/part_stat.h>
#include "zram_drv.h"
static DEFINE_IDR(zram_index_idr);
/* idr index must be protected */
static DEFINE_MUTEX(zram_index_mutex);
static int zram_major;
static const char *default_compressor = CONFIG_ZRAM_DEF_COMP;
/* Module params (documentation at end) */
static unsigned int num_devices = 1;
/*
* Pages that compress to sizes equals or greater than this are stored
* uncompressed in memory.
*/
static size_t huge_class_size;
static const struct block_device_operations zram_devops;
static void zram_free_page(struct zram *zram, size_t index);
static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
u32 index, int offset, struct bio *bio);
static int zram_slot_trylock(struct zram *zram, u32 index)
{
return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].flags);
}
static void zram_slot_lock(struct zram *zram, u32 index)
{
bit_spin_lock(ZRAM_LOCK, &zram->table[index].flags);
}
static void zram_slot_unlock(struct zram *zram, u32 index)
{
bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags);
}
static inline bool init_done(struct zram *zram)
{
return zram->disksize;
}
static inline struct zram *dev_to_zram(struct device *dev)
{
return (struct zram *)dev_to_disk(dev)->private_data;
}
static unsigned long zram_get_handle(struct zram *zram, u32 index)
{
return zram->table[index].handle;
}
static void zram_set_handle(struct zram *zram, u32 index, unsigned long handle)
{
zram->table[index].handle = handle;
}
/* flag operations require table entry bit_spin_lock() being held */
static bool zram_test_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
return zram->table[index].flags & BIT(flag);
}
static void zram_set_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
zram->table[index].flags |= BIT(flag);
}
static void zram_clear_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
zram->table[index].flags &= ~BIT(flag);
}
static inline void zram_set_element(struct zram *zram, u32 index,
unsigned long element)
{
zram->table[index].element = element;
}
static unsigned long zram_get_element(struct zram *zram, u32 index)
{
return zram->table[index].element;
}
static size_t zram_get_obj_size(struct zram *zram, u32 index)
{
return zram->table[index].flags & (BIT(ZRAM_FLAG_SHIFT) - 1);
}
static void zram_set_obj_size(struct zram *zram,
u32 index, size_t size)
{
unsigned long flags = zram->table[index].flags >> ZRAM_FLAG_SHIFT;
zram->table[index].flags = (flags << ZRAM_FLAG_SHIFT) | size;
}
static inline bool zram_allocated(struct zram *zram, u32 index)
{
return zram_get_obj_size(zram, index) ||
zram_test_flag(zram, index, ZRAM_SAME) ||
zram_test_flag(zram, index, ZRAM_WB);
}
#if PAGE_SIZE != 4096
static inline bool is_partial_io(struct bio_vec *bvec)
{
return bvec->bv_len != PAGE_SIZE;
}
#else
static inline bool is_partial_io(struct bio_vec *bvec)
{
return false;
}
#endif
static inline void zram_set_priority(struct zram *zram, u32 index, u32 prio)
{
prio &= ZRAM_COMP_PRIORITY_MASK;
/*
* Clear previous priority value first, in case if we recompress
* further an already recompressed page
*/
zram->table[index].flags &= ~(ZRAM_COMP_PRIORITY_MASK <<
ZRAM_COMP_PRIORITY_BIT1);
zram->table[index].flags |= (prio << ZRAM_COMP_PRIORITY_BIT1);
}
static inline u32 zram_get_priority(struct zram *zram, u32 index)
{
u32 prio = zram->table[index].flags >> ZRAM_COMP_PRIORITY_BIT1;
return prio & ZRAM_COMP_PRIORITY_MASK;
}
/*
* Check if request is within bounds and aligned on zram logical blocks.
*/
static inline bool valid_io_request(struct zram *zram,
sector_t start, unsigned int size)
{
u64 end, bound;
/* unaligned request */
if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
return false;
if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
return false;
end = start + (size >> SECTOR_SHIFT);
bound = zram->disksize >> SECTOR_SHIFT;
/* out of range */
if (unlikely(start >= bound || end > bound || start > end))
return false;
/* I/O request is valid */
return true;
}
static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
{
*index += (*offset + bvec->bv_len) / PAGE_SIZE;
*offset = (*offset + bvec->bv_len) % PAGE_SIZE;
}
static inline void update_used_max(struct zram *zram,
const unsigned long pages)
{
unsigned long cur_max = atomic_long_read(&zram->stats.max_used_pages);
do {
if (cur_max >= pages)
return;
} while (!atomic_long_try_cmpxchg(&zram->stats.max_used_pages,
&cur_max, pages));
}
static inline void zram_fill_page(void *ptr, unsigned long len,
unsigned long value)
{
WARN_ON_ONCE(!IS_ALIGNED(len, sizeof(unsigned long)));
memset_l(ptr, value, len / sizeof(unsigned long));
}
static bool page_same_filled(void *ptr, unsigned long *element)
{
unsigned long *page;
unsigned long val;
unsigned int pos, last_pos = PAGE_SIZE / sizeof(*page) - 1;
page = (unsigned long *)ptr;
val = page[0];
if (val != page[last_pos])
return false;
for (pos = 1; pos < last_pos; pos++) {
if (val != page[pos])
return false;
}
*element = val;
return true;
}
static ssize_t initstate_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
u32 val;
struct zram *zram = dev_to_zram(dev);
down_read(&zram->init_lock);
val = init_done(zram);
up_read(&zram->init_lock);
return scnprintf(buf, PAGE_SIZE, "%u\n", val);
}
static ssize_t disksize_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct zram *zram = dev_to_zram(dev);
return scnprintf(buf, PAGE_SIZE, "%llu\n", zram->disksize);
}
static ssize_t mem_limit_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
u64 limit;
char *tmp;
struct zram *zram = dev_to_zram(dev);
limit = memparse(buf, &tmp);
if (buf == tmp) /* no chars parsed, invalid input */
return -EINVAL;
down_write(&zram->init_lock);
zram->limit_pages = PAGE_ALIGN(limit) >> PAGE_SHIFT;
up_write(&zram->init_lock);
return len;
}
static ssize_t mem_used_max_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
int err;
unsigned long val;
struct zram *zram = dev_to_zram(dev);
err = kstrtoul(buf, 10, &val);
if (err || val != 0)
return -EINVAL;
down_read(&zram->init_lock);
if (init_done(zram)) {
atomic_long_set(&zram->stats.max_used_pages,
zs_get_total_pages(zram->mem_pool));
}
up_read(&zram->init_lock);
return len;
}
/*
* Mark all pages which are older than or equal to cutoff as IDLE.
* Callers should hold the zram init lock in read mode
*/
static void mark_idle(struct zram *zram, ktime_t cutoff)
{
int is_idle = 1;
unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
int index;
for (index = 0; index < nr_pages; index++) {
/*
* Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race.
* See the comment in writeback_store.
*/
zram_slot_lock(zram, index);
if (zram_allocated(zram, index) &&
!zram_test_flag(zram, index, ZRAM_UNDER_WB)) {
#ifdef CONFIG_ZRAM_MEMORY_TRACKING
is_idle = !cutoff || ktime_after(cutoff, zram->table[index].ac_time);
#endif
if (is_idle)
zram_set_flag(zram, index, ZRAM_IDLE);
}
zram_slot_unlock(zram, index);
}
}
static ssize_t idle_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct zram *zram = dev_to_zram(dev);
ktime_t cutoff_time = 0;
ssize_t rv = -EINVAL;
if (!sysfs_streq(buf, "all")) {
/*
* If it did not parse as 'all' try to treat it as an integer
* when we have memory tracking enabled.
*/
u64 age_sec;
if (IS_ENABLED(CONFIG_ZRAM_MEMORY_TRACKING) && !kstrtoull(buf, 0, &age_sec))
cutoff_time = ktime_sub(ktime_get_boottime(),
ns_to_ktime(age_sec * NSEC_PER_SEC));
else
goto out;
}
down_read(&zram->init_lock);
if (!init_done(zram))
goto out_unlock;
/*
* A cutoff_time of 0 marks everything as idle, this is the
* "all" behavior.
*/
mark_idle(zram, cutoff_time);
rv = len;
out_unlock:
up_read(&zram->init_lock);
out:
return rv;
}
#ifdef CONFIG_ZRAM_WRITEBACK
static ssize_t writeback_limit_enable_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct zram *zram = dev_to_zram(dev);
u64 val;
ssize_t ret = -EINVAL;
if (kstrtoull(buf, 10, &val))
return ret;
down_read(&zram->init_lock);
spin_lock(&zram->wb_limit_lock);
zram->wb_limit_enable = val;
spin_unlock(&zram->wb_limit_lock);
up_read(&zram->init_lock);
ret = len;
return ret;
}
static ssize_t writeback_limit_enable_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
bool val;
struct zram *zram = dev_to_zram(dev);
down_read(&zram->init_lock);
spin_lock(&zram->wb_limit_lock);
val = zram->wb_limit_enable;
spin_unlock(&zram->wb_limit_lock);
up_read(&zram->init_lock);
return scnprintf(buf, PAGE_SIZE, "%d\n", val);
}
static ssize_t writeback_limit_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct zram *zram = dev_to_zram(dev);
u64 val;
ssize_t ret = -EINVAL;
if (kstrtoull(buf, 10, &val))
return ret;
down_read(&zram->init_lock);
spin_lock(&zram->wb_limit_lock);
zram->bd_wb_limit = val;
spin_unlock(&zram->wb_limit_lock);
up_read(&zram->init_lock);
ret = len;
return ret;
}
static ssize_t writeback_limit_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
u64 val;
struct zram *zram = dev_to_zram(dev);
down_read(&zram->init_lock);
spin_lock(&zram->wb_limit_lock);
val = zram->bd_wb_limit;
spin_unlock(&zram->wb_limit_lock);
up_read(&zram->init_lock);
return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
}
static void reset_bdev(struct zram *zram)
{
struct block_device *bdev;
if (!zram->backing_dev)
return;
bdev = zram->bdev;
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
/* hope filp_close flush all of IO */
filp_close(zram->backing_dev, NULL);
zram->backing_dev = NULL;
zram->bdev = NULL;
zram->disk->fops = &zram_devops;
kvfree(zram->bitmap);
zram->bitmap = NULL;
}
static ssize_t backing_dev_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct file *file;
struct zram *zram = dev_to_zram(dev);
char *p;
ssize_t ret;
down_read(&zram->init_lock);
file = zram->backing_dev;
if (!file) {
memcpy(buf, "none\n", 5);
up_read(&zram->init_lock);
return 5;
}
p = file_path(file, buf, PAGE_SIZE - 1);
if (IS_ERR(p)) {
ret = PTR_ERR(p);
goto out;
}
ret = strlen(p);
memmove(buf, p, ret);
buf[ret++] = '\n';
out:
up_read(&zram->init_lock);
return ret;
}
static ssize_t backing_dev_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
char *file_name;
size_t sz;
struct file *backing_dev = NULL;
struct inode *inode;
struct address_space *mapping;
unsigned int bitmap_sz;
unsigned long nr_pages, *bitmap = NULL;
struct block_device *bdev = NULL;
int err;
struct zram *zram = dev_to_zram(dev);
file_name = kmalloc(PATH_MAX, GFP_KERNEL);
if (!file_name)
return -ENOMEM;
down_write(&zram->init_lock);
if (init_done(zram)) {
pr_info("Can't setup backing device for initialized device\n");
err = -EBUSY;
goto out;
}
strscpy(file_name, buf, PATH_MAX);
/* ignore trailing newline */
sz = strlen(file_name);
if (sz > 0 && file_name[sz - 1] == '\n')
file_name[sz - 1] = 0x00;
backing_dev = filp_open(file_name, O_RDWR|O_LARGEFILE, 0);
if (IS_ERR(backing_dev)) {
err = PTR_ERR(backing_dev);
backing_dev = NULL;
goto out;
}
mapping = backing_dev->f_mapping;
inode = mapping->host;
/* Support only block device in this moment */
if (!S_ISBLK(inode->i_mode)) {
err = -ENOTBLK;
goto out;
}
bdev = blkdev_get_by_dev(inode->i_rdev,
FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram);
if (IS_ERR(bdev)) {
err = PTR_ERR(bdev);
bdev = NULL;
goto out;
}
nr_pages = i_size_read(inode) >> PAGE_SHIFT;
bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long);
bitmap = kvzalloc(bitmap_sz, GFP_KERNEL);
if (!bitmap) {
err = -ENOMEM;
goto out;
}
reset_bdev(zram);
zram->bdev = bdev;
zram->backing_dev = backing_dev;
zram->bitmap = bitmap;
zram->nr_pages = nr_pages;
up_write(&zram->init_lock);
pr_info("setup backing device %s\n", file_name);
kfree(file_name);
return len;
out:
kvfree(bitmap);
if (bdev)
blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
if (backing_dev)
filp_close(backing_dev, NULL);
up_write(&zram->init_lock);
kfree(file_name);
return err;
}
static unsigned long alloc_block_bdev(struct zram *zram)
{
unsigned long blk_idx = 1;
retry:
/* skip 0 bit to confuse zram.handle = 0 */
blk_idx = find_next_zero_bit(zram->bitmap, zram->nr_pages, blk_idx);
if (blk_idx == zram->nr_pages)
return 0;
if (test_and_set_bit(blk_idx, zram->bitmap))
goto retry;
atomic64_inc(&zram->stats.bd_count);
return blk_idx;
}
static void free_block_bdev(struct zram *zram, unsigned long blk_idx)
{
int was_set;
was_set = test_and_clear_bit(blk_idx, zram->bitmap);
WARN_ON_ONCE(!was_set);
atomic64_dec(&zram->stats.bd_count);
}
static void zram_page_end_io(struct bio *bio)
{
struct page *page = bio_first_page_all(bio);
page_endio(page, op_is_write(bio_op(bio)),
blk_status_to_errno(bio->bi_status));
bio_put(bio);
}
/*
* Returns 1 if the submission is successful.
*/
static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
unsigned long entry, struct bio *parent)
{
struct bio *bio;
bio = bio_alloc(zram->bdev, 1, parent ? parent->bi_opf : REQ_OP_READ,
GFP_NOIO);
if (!bio)
return -ENOMEM;
bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) {
bio_put(bio);
return -EIO;
}
if (!parent)
bio->bi_end_io = zram_page_end_io;
else
bio_chain(bio, parent);
submit_bio(bio);
return 1;
}
#define PAGE_WB_SIG "page_index="
#define PAGE_WRITEBACK 0
#define HUGE_WRITEBACK (1<<0)
#define IDLE_WRITEBACK (1<<1)
#define INCOMPRESSIBLE_WRITEBACK (1<<2)
static ssize_t writeback_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct zram *zram = dev_to_zram(dev);
unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
unsigned long index = 0;
struct bio bio;
struct bio_vec bio_vec;
struct page *page;
ssize_t ret = len;
int mode, err;
unsigned long blk_idx = 0;
if (sysfs_streq(buf, "idle"))
mode = IDLE_WRITEBACK;
else if (sysfs_streq(buf, "huge"))
mode = HUGE_WRITEBACK;
else if (sysfs_streq(buf, "huge_idle"))
mode = IDLE_WRITEBACK | HUGE_WRITEBACK;
else if (sysfs_streq(buf, "incompressible"))
mode = INCOMPRESSIBLE_WRITEBACK;
else {
if (strncmp(buf, PAGE_WB_SIG, sizeof(PAGE_WB_SIG) - 1))
return -EINVAL;
if (kstrtol(buf + sizeof(PAGE_WB_SIG) - 1, 10, &index) ||
index >= nr_pages)
return -EINVAL;
nr_pages = 1;
mode = PAGE_WRITEBACK;
}
down_read(&zram->init_lock);
if (!init_done(zram)) {
ret = -EINVAL;
goto release_init_lock;
}
if (!zram->backing_dev) {
ret = -ENODEV;
goto release_init_lock;
}
page = alloc_page(GFP_KERNEL);
if (!page) {
ret = -ENOMEM;
goto release_init_lock;
}
for (; nr_pages != 0; index++, nr_pages--) {
struct bio_vec bvec;
bvec_set_page(&bvec, page, PAGE_SIZE, 0);
spin_lock(&zram->wb_limit_lock);
if (zram->wb_limit_enable && !zram->bd_wb_limit) {
spin_unlock(&zram->wb_limit_lock);
ret = -EIO;
break;
}
spin_unlock(&zram->wb_limit_lock);
if (!blk_idx) {
blk_idx = alloc_block_bdev(zram);
if (!blk_idx) {
ret = -ENOSPC;
break;
}
}
zram_slot_lock(zram, index);
if (!zram_allocated(zram, index))
goto next;
if (zram_test_flag(zram, index, ZRAM_WB) ||
zram_test_flag(zram, index, ZRAM_SAME) ||
zram_test_flag(zram, index, ZRAM_UNDER_WB))
goto next;
if (mode & IDLE_WRITEBACK &&
!zram_test_flag(zram, index, ZRAM_IDLE))
goto next;
if (mode & HUGE_WRITEBACK &&
!zram_test_flag(zram, index, ZRAM_HUGE))
goto next;
if (mode & INCOMPRESSIBLE_WRITEBACK &&
!zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE))
goto next;
/*
* Clearing ZRAM_UNDER_WB is duty of caller.
* IOW, zram_free_page never clear it.
*/
zram_set_flag(zram, index, ZRAM_UNDER_WB);
/* Need for hugepage writeback racing */
zram_set_flag(zram, index, ZRAM_IDLE);
zram_slot_unlock(zram, index);
if (zram_bvec_read(zram, &bvec, index, 0, NULL)) {
zram_slot_lock(zram, index);
zram_clear_flag(zram, index, ZRAM_UNDER_WB);
zram_clear_flag(zram, index, ZRAM_IDLE);
zram_slot_unlock(zram, index);
continue;
}
bio_init(&bio, zram->bdev, &bio_vec, 1,
REQ_OP_WRITE | REQ_SYNC);
bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9);
bio_add_page(&bio, bvec.bv_page, bvec.bv_len,
bvec.bv_offset);
/*
* XXX: A single page IO would be inefficient for write
* but it would be not bad as starter.
*/
err = submit_bio_wait(&bio);
if (err) {
zram_slot_lock(zram, index);
zram_clear_flag(zram, index, ZRAM_UNDER_WB);
zram_clear_flag(zram, index, ZRAM_IDLE);
zram_slot_unlock(zram, index);
/*
* BIO errors are not fatal, we continue and simply
* attempt to writeback the remaining objects (pages).
* At the same time we need to signal user-space that
* some writes (at least one, but also could be all of
* them) were not successful and we do so by returning
* the most recent BIO error.
*/
ret = err;
continue;
}
atomic64_inc(&zram->stats.bd_writes);
/*
* We released zram_slot_lock so need to check if the slot was
* changed. If there is freeing for the slot, we can catch it
* easily by zram_allocated.
* A subtle case is the slot is freed/reallocated/marked as
* ZRAM_IDLE again. To close the race, idle_store doesn't
* mark ZRAM_IDLE once it found the slot was ZRAM_UNDER_WB.
* Thus, we could close the race by checking ZRAM_IDLE bit.
*/
zram_slot_lock(zram, index);
if (!zram_allocated(zram, index) ||
!zram_test_flag(zram, index, ZRAM_IDLE)) {
zram_clear_flag(zram, index, ZRAM_UNDER_WB);
zram_clear_flag(zram, index, ZRAM_IDLE);
goto next;
}
zram_free_page(zram, index);
zram_clear_flag(zram, index, ZRAM_UNDER_WB);
zram_set_flag(zram, index, ZRAM_WB);
zram_set_element(zram, index, blk_idx);
blk_idx = 0;
atomic64_inc(&zram->stats.pages_stored);
spin_lock(&zram->wb_limit_lock);
if (zram->wb_limit_enable && zram->bd_wb_limit > 0)
zram->bd_wb_limit -= 1UL << (PAGE_SHIFT - 12);
spin_unlock(&zram->wb_limit_lock);
next:
zram_slot_unlock(zram, index);
}
if (blk_idx)
free_block_bdev(zram, blk_idx);
__free_page(page);
release_init_lock:
up_read(&zram->init_lock);
return ret;
}
struct zram_work {
struct work_struct work;
struct zram *zram;
unsigned long entry;
struct bio *bio;
struct bio_vec bvec;
};
#if PAGE_SIZE != 4096
static void zram_sync_read(struct work_struct *work)
{
struct zram_work *zw = container_of(work, struct zram_work, work);
struct zram *zram = zw->zram;
unsigned long entry = zw->entry;
struct bio *bio = zw->bio;
read_from_bdev_async(zram, &zw->bvec, entry, bio);
}
/*
* Block layer want one ->submit_bio to be active at a time, so if we use
* chained IO with parent IO in same context, it's a deadlock. To avoid that,
* use a worker thread context.
*/
static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
unsigned long entry, struct bio *bio)
{
struct zram_work work;
work.bvec = *bvec;
work.zram = zram;
work.entry = entry;
work.bio = bio;
INIT_WORK_ONSTACK(&work.work, zram_sync_read);
queue_work(system_unbound_wq, &work.work);
flush_work(&work.work);
destroy_work_on_stack(&work.work);
return 1;
}
#else
static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
unsigned long entry, struct bio *bio)
{
WARN_ON(1);
return -EIO;
}
#endif
static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
unsigned long entry, struct bio *parent, bool sync)
{
atomic64_inc(&zram->stats.bd_reads);
if (sync)
return read_from_bdev_sync(zram, bvec, entry, parent);
else
return read_from_bdev_async(zram, bvec, entry, parent);
}
#else
static inline void reset_bdev(struct zram *zram) {};
static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
unsigned long entry, struct bio *parent, bool sync)
{
return -EIO;
}
static void free_block_bdev(struct zram *zram, unsigned long blk_idx) {};
#endif
#ifdef CONFIG_ZRAM_MEMORY_TRACKING
static struct dentry *zram_debugfs_root;
static void zram_debugfs_create(void)
{
zram_debugfs_root = debugfs_create_dir("zram", NULL);
}
static void zram_debugfs_destroy(void)
{
debugfs_remove_recursive(zram_debugfs_root);
}
static void zram_accessed(struct zram *zram, u32 index)
{
zram_clear_flag(zram, index, ZRAM_IDLE);
zram->table[index].ac_time = ktime_get_boottime();
}
static ssize_t read_block_state(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
char *kbuf;
ssize_t index, written = 0;
struct zram *zram = file->private_data;
unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
struct timespec64 ts;
kbuf = kvmalloc(count, GFP_KERNEL);
if (!kbuf)
return -ENOMEM;
down_read(&zram->init_lock);
if (!init_done(zram)) {
up_read(&zram->init_lock);
kvfree(kbuf);
return -EINVAL;
}
for (index = *ppos; index < nr_pages; index++) {
int copied;
zram_slot_lock(zram, index);
if (!zram_allocated(zram, index))
goto next;
ts = ktime_to_timespec64(zram->table[index].ac_time);
copied = snprintf(kbuf + written, count,
"%12zd %12lld.%06lu %c%c%c%c%c%c\n",
index, (s64)ts.tv_sec,
ts.tv_nsec / NSEC_PER_USEC,
zram_test_flag(zram, index, ZRAM_SAME) ? 's' : '.',
zram_test_flag(zram, index, ZRAM_WB) ? 'w' : '.',
zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.',
zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.',
zram_get_priority(zram, index) ? 'r' : '.',
zram_test_flag(zram, index,
ZRAM_INCOMPRESSIBLE) ? 'n' : '.');
if (count <= copied) {
zram_slot_unlock(zram, index);
break;
}
written += copied;
count -= copied;
next:
zram_slot_unlock(zram, index);
*ppos += 1;
}
up_read(&zram->init_lock);
if (copy_to_user(buf, kbuf, written))
written = -EFAULT;
kvfree(kbuf);
return written;
}
static const struct file_operations proc_zram_block_state_op = {
.open = simple_open,
.read = read_block_state,
.llseek = default_llseek,
};
static void zram_debugfs_register(struct zram *zram)
{
if (!zram_debugfs_root)
return;
zram->debugfs_dir = debugfs_create_dir(zram->disk->disk_name,
zram_debugfs_root);
debugfs_create_file("block_state", 0400, zram->debugfs_dir,
zram, &proc_zram_block_state_op);
}
static void zram_debugfs_unregister(struct zram *zram)
{
debugfs_remove_recursive(zram->debugfs_dir);
}
#else
static void zram_debugfs_create(void) {};
static void zram_debugfs_destroy(void) {};
static void zram_accessed(struct zram *zram, u32 index)
{
zram_clear_flag(zram, index, ZRAM_IDLE);
};
static void zram_debugfs_register(struct zram *zram) {};
static void zram_debugfs_unregister(struct zram *zram) {};
#endif
/*
* We switched to per-cpu streams and this attr is not needed anymore.
* However, we will keep it around for some time, because:
* a) we may revert per-cpu streams in the future
* b) it's visible to user space and we need to follow our 2 years
* retirement rule; but we already have a number of 'soon to be
* altered' attrs, so max_comp_streams need to wait for the next
* layoff cycle.
*/
static ssize_t max_comp_streams_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
return scnprintf(buf, PAGE_SIZE, "%d\n", num_online_cpus());
}
static ssize_t max_comp_streams_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
return len;
}
static void comp_algorithm_set(struct zram *zram, u32 prio, const char *alg)
{
/* Do not free statically defined compression algorithms */
if (zram->comp_algs[prio] != default_compressor)
kfree(zram->comp_algs[prio]);
zram->comp_algs[prio] = alg;
}
static ssize_t __comp_algorithm_show(struct zram *zram, u32 prio, char *buf)
{
ssize_t sz;
down_read(&zram->init_lock);
sz = zcomp_available_show(zram->comp_algs[prio], buf);
up_read(&zram->init_lock);
return sz;
}
static int __comp_algorithm_store(struct zram *zram, u32 prio, const char *buf)
{
char *compressor;
size_t sz;
sz = strlen(buf);
if (sz >= CRYPTO_MAX_ALG_NAME)
return -E2BIG;
compressor = kstrdup(buf, GFP_KERNEL);
if (!compressor)
return -ENOMEM;
/* ignore trailing newline */
if (sz > 0 && compressor[sz - 1] == '\n')
compressor[sz - 1] = 0x00;
if (!zcomp_available_algorithm(compressor)) {
kfree(compressor);
return -EINVAL;
}
down_write(&zram->init_lock);
if (init_done(zram)) {
up_write(&zram->init_lock);
kfree(compressor);
pr_info("Can't change algorithm for initialized device\n");
return -EBUSY;
}
comp_algorithm_set(zram, prio, compressor);
up_write(&zram->init_lock);
return 0;
}
static ssize_t comp_algorithm_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct zram *zram = dev_to_zram(dev);
return __comp_algorithm_show(zram, ZRAM_PRIMARY_COMP, buf);
}
static ssize_t comp_algorithm_store(struct device *dev,
struct device_attribute *attr,
const char *buf,
size_t len)
{
struct zram *zram = dev_to_zram(dev);
int ret;
ret = __comp_algorithm_store(zram, ZRAM_PRIMARY_COMP, buf);
return ret ? ret : len;
}
#ifdef CONFIG_ZRAM_MULTI_COMP
static ssize_t recomp_algorithm_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct zram *zram = dev_to_zram(dev);
ssize_t sz = 0;
u32 prio;
for (prio = ZRAM_SECONDARY_COMP; prio < ZRAM_MAX_COMPS; prio++) {
if (!zram->comp_algs[prio])
continue;
sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2, "#%d: ", prio);
sz += __comp_algorithm_show(zram, prio, buf + sz);
}
return sz;
}
static ssize_t recomp_algorithm_store(struct device *dev,
struct device_attribute *attr,
const char *buf,
size_t len)
{
struct zram *zram = dev_to_zram(dev);
int prio = ZRAM_SECONDARY_COMP;
char *args, *param, *val;
char *alg = NULL;
int ret;
args = skip_spaces(buf);
while (*args) {
args = next_arg(args, &param, &val);
if (!val || !*val)
return -EINVAL;
if (!strcmp(param, "algo")) {
alg = val;
continue;
}
if (!strcmp(param, "priority")) {
ret = kstrtoint(val, 10, &prio);
if (ret)
return ret;
continue;
}
}
if (!alg)
return -EINVAL;
if (prio < ZRAM_SECONDARY_COMP || prio >= ZRAM_MAX_COMPS)
return -EINVAL;
ret = __comp_algorithm_store(zram, prio, alg);
return ret ? ret : len;
}
#endif
static ssize_t compact_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct zram *zram = dev_to_zram(dev);
down_read(&zram->init_lock);
if (!init_done(zram)) {
up_read(&zram->init_lock);
return -EINVAL;
}
zs_compact(zram->mem_pool);
up_read(&zram->init_lock);
return len;
}
static ssize_t io_stat_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct zram *zram = dev_to_zram(dev);
ssize_t ret;
down_read(&zram->init_lock);
ret = scnprintf(buf, PAGE_SIZE,
"%8llu %8llu %8llu %8llu\n",
(u64)atomic64_read(&zram->stats.failed_reads),
(u64)atomic64_read(&zram->stats.failed_writes),
(u64)atomic64_read(&zram->stats.invalid_io),
(u64)atomic64_read(&zram->stats.notify_free));
up_read(&zram->init_lock);
return ret;
}
static ssize_t mm_stat_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct zram *zram = dev_to_zram(dev);
struct zs_pool_stats pool_stats;
u64 orig_size, mem_used = 0;
long max_used;
ssize_t ret;
memset(&pool_stats, 0x00, sizeof(struct zs_pool_stats));
down_read(&zram->init_lock);
if (init_done(zram)) {
mem_used = zs_get_total_pages(zram->mem_pool);
zs_pool_stats(zram->mem_pool, &pool_stats);
}
orig_size = atomic64_read(&zram->stats.pages_stored);
max_used = atomic_long_read(&zram->stats.max_used_pages);
ret = scnprintf(buf, PAGE_SIZE,
"%8llu %8llu %8llu %8lu %8ld %8llu %8lu %8llu %8llu\n",
orig_size << PAGE_SHIFT,
(u64)atomic64_read(&zram->stats.compr_data_size),
mem_used << PAGE_SHIFT,
zram->limit_pages << PAGE_SHIFT,
max_used << PAGE_SHIFT,
(u64)atomic64_read(&zram->stats.same_pages),
atomic_long_read(&pool_stats.pages_compacted),
(u64)atomic64_read(&zram->stats.huge_pages),
(u64)atomic64_read(&zram->stats.huge_pages_since));
up_read(&zram->init_lock);
return ret;
}
#ifdef CONFIG_ZRAM_WRITEBACK
#define FOUR_K(x) ((x) * (1 << (PAGE_SHIFT - 12)))
static ssize_t bd_stat_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct zram *zram = dev_to_zram(dev);
ssize_t ret;
down_read(&zram->init_lock);
ret = scnprintf(buf, PAGE_SIZE,
"%8llu %8llu %8llu\n",
FOUR_K((u64)atomic64_read(&zram->stats.bd_count)),
FOUR_K((u64)atomic64_read(&zram->stats.bd_reads)),
FOUR_K((u64)atomic64_read(&zram->stats.bd_writes)));
up_read(&zram->init_lock);
return ret;
}
#endif
static ssize_t debug_stat_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
int version = 1;
struct zram *zram = dev_to_zram(dev);
ssize_t ret;
down_read(&zram->init_lock);
ret = scnprintf(buf, PAGE_SIZE,
"version: %d\n%8llu %8llu\n",
version,
(u64)atomic64_read(&zram->stats.writestall),
(u64)atomic64_read(&zram->stats.miss_free));
up_read(&zram->init_lock);
return ret;
}
static DEVICE_ATTR_RO(io_stat);
static DEVICE_ATTR_RO(mm_stat);
#ifdef CONFIG_ZRAM_WRITEBACK
static DEVICE_ATTR_RO(bd_stat);
#endif
static DEVICE_ATTR_RO(debug_stat);
static void zram_meta_free(struct zram *zram, u64 disksize)
{
size_t num_pages = disksize >> PAGE_SHIFT;
size_t index;
/* Free all pages that are still in this zram device */
for (index = 0; index < num_pages; index++)
zram_free_page(zram, index);
zs_destroy_pool(zram->mem_pool);
vfree(zram->table);
}
static bool zram_meta_alloc(struct zram *zram, u64 disksize)
{
size_t num_pages;
num_pages = disksize >> PAGE_SHIFT;
zram->table = vzalloc(array_size(num_pages, sizeof(*zram->table)));
if (!zram->table)
return false;
zram->mem_pool = zs_create_pool(zram->disk->disk_name);
if (!zram->mem_pool) {
vfree(zram->table);
return false;
}
if (!huge_class_size)
huge_class_size = zs_huge_class_size(zram->mem_pool);
return true;
}
/*
* To protect concurrent access to the same index entry,
* caller should hold this table index entry's bit_spinlock to
* indicate this index entry is accessing.
*/
static void zram_free_page(struct zram *zram, size_t index)
{
unsigned long handle;
#ifdef CONFIG_ZRAM_MEMORY_TRACKING
zram->table[index].ac_time = 0;
#endif
if (zram_test_flag(zram, index, ZRAM_IDLE))
zram_clear_flag(zram, index, ZRAM_IDLE);
if (zram_test_flag(zram, index, ZRAM_HUGE)) {
zram_clear_flag(zram, index, ZRAM_HUGE);
atomic64_dec(&zram->stats.huge_pages);
}
if (zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE))
zram_clear_flag(zram, index, ZRAM_INCOMPRESSIBLE);
zram_set_priority(zram, index, 0);
if (zram_test_flag(zram, index, ZRAM_WB)) {
zram_clear_flag(zram, index, ZRAM_WB);
free_block_bdev(zram, zram_get_element(zram, index));
goto out;
}
/*
* No memory is allocated for same element filled pages.
* Simply clear same page flag.
*/
if (zram_test_flag(zram, index, ZRAM_SAME)) {
zram_clear_flag(zram, index, ZRAM_SAME);
atomic64_dec(&zram->stats.same_pages);
goto out;
}
handle = zram_get_handle(zram, index);
if (!handle)
return;
zs_free(zram->mem_pool, handle);
atomic64_sub(zram_get_obj_size(zram, index),
&zram->stats.compr_data_size);
out:
atomic64_dec(&zram->stats.pages_stored);
zram_set_handle(zram, index, 0);
zram_set_obj_size(zram, index, 0);
WARN_ON_ONCE(zram->table[index].flags &
~(1UL << ZRAM_LOCK | 1UL << ZRAM_UNDER_WB));
}
/*
* Reads a page from the writeback devices. Corresponding ZRAM slot
* should be unlocked.
*/
static int zram_bvec_read_from_bdev(struct zram *zram, struct page *page,
u32 index, struct bio *bio, bool partial_io)
{
struct bio_vec bvec;
bvec_set_page(&bvec, page, PAGE_SIZE, 0);
return read_from_bdev(zram, &bvec, zram_get_element(zram, index), bio,
partial_io);
}
/*
* Reads (decompresses if needed) a page from zspool (zsmalloc).
* Corresponding ZRAM slot should be locked.
*/
static int zram_read_from_zspool(struct zram *zram, struct page *page,
u32 index)
{
struct zcomp_strm *zstrm;
unsigned long handle;
unsigned int size;
void *src, *dst;
u32 prio;
int ret;
handle = zram_get_handle(zram, index);
if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) {
unsigned long value;
void *mem;
value = handle ? zram_get_element(zram, index) : 0;
mem = kmap_atomic(page);
zram_fill_page(mem, PAGE_SIZE, value);
kunmap_atomic(mem);
return 0;
}
size = zram_get_obj_size(zram, index);
if (size != PAGE_SIZE) {
prio = zram_get_priority(zram, index);
zstrm = zcomp_stream_get(zram->comps[prio]);
}
src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
if (size == PAGE_SIZE) {
dst = kmap_atomic(page);
memcpy(dst, src, PAGE_SIZE);
kunmap_atomic(dst);
ret = 0;
} else {
dst = kmap_atomic(page);
ret = zcomp_decompress(zstrm, src, size, dst);
kunmap_atomic(dst);
zcomp_stream_put(zram->comps[prio]);
}
zs_unmap_object(zram->mem_pool, handle);
return ret;
}
static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
struct bio *bio, bool partial_io)
{
int ret;
zram_slot_lock(zram, index);
if (!zram_test_flag(zram, index, ZRAM_WB)) {
/* Slot should be locked through out the function call */
ret = zram_read_from_zspool(zram, page, index);
zram_slot_unlock(zram, index);
} else {
/* Slot should be unlocked before the function call */
zram_slot_unlock(zram, index);
ret = zram_bvec_read_from_bdev(zram, page, index, bio,
partial_io);
}
/* Should NEVER happen. Return bio error if it does. */
if (WARN_ON(ret < 0))
pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
return ret;
}
static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
u32 index, int offset, struct bio *bio)
{
int ret;
struct page *page;
page = bvec->bv_page;
if (is_partial_io(bvec)) {
/* Use a temporary buffer to decompress the page */
page = alloc_page(GFP_NOIO|__GFP_HIGHMEM);
if (!page)
return -ENOMEM;
}
ret = __zram_bvec_read(zram, page, index, bio, is_partial_io(bvec));
if (unlikely(ret))
goto out;
if (is_partial_io(bvec)) {
void *src = kmap_atomic(page);
memcpy_to_bvec(bvec, src + offset);
kunmap_atomic(src);
}
out:
if (is_partial_io(bvec))
__free_page(page);
return ret;
}
static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
u32 index, struct bio *bio)
{
int ret = 0;
unsigned long alloced_pages;
unsigned long handle = -ENOMEM;
unsigned int comp_len = 0;
void *src, *dst, *mem;
struct zcomp_strm *zstrm;
struct page *page = bvec->bv_page;
unsigned long element = 0;
enum zram_pageflags flags = 0;
mem = kmap_atomic(page);
if (page_same_filled(mem, &element)) {
kunmap_atomic(mem);
/* Free memory associated with this sector now. */
flags = ZRAM_SAME;
atomic64_inc(&zram->stats.same_pages);
goto out;
}
kunmap_atomic(mem);
compress_again:
zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]);
src = kmap_atomic(page);
ret = zcomp_compress(zstrm, src, &comp_len);
kunmap_atomic(src);
if (unlikely(ret)) {
zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
pr_err("Compression failed! err=%d\n", ret);
zs_free(zram->mem_pool, handle);
return ret;
}
if (comp_len >= huge_class_size)
comp_len = PAGE_SIZE;
/*
* handle allocation has 2 paths:
* a) fast path is executed with preemption disabled (for
* per-cpu streams) and has __GFP_DIRECT_RECLAIM bit clear,
* since we can't sleep;
* b) slow path enables preemption and attempts to allocate
* the page with __GFP_DIRECT_RECLAIM bit set. we have to
* put per-cpu compression stream and, thus, to re-do
* the compression once handle is allocated.
*
* if we have a 'non-null' handle here then we are coming
* from the slow path and handle has already been allocated.
*/
if (IS_ERR_VALUE(handle))
handle = zs_malloc(zram->mem_pool, comp_len,
__GFP_KSWAPD_RECLAIM |
__GFP_NOWARN |
__GFP_HIGHMEM |
__GFP_MOVABLE);
if (IS_ERR_VALUE(handle)) {
zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
atomic64_inc(&zram->stats.writestall);
handle = zs_malloc(zram->mem_pool, comp_len,
GFP_NOIO | __GFP_HIGHMEM |
__GFP_MOVABLE);
if (IS_ERR_VALUE(handle))
return PTR_ERR((void *)handle);
if (comp_len != PAGE_SIZE)
goto compress_again;
/*
* If the page is not compressible, you need to acquire the
* lock and execute the code below. The zcomp_stream_get()
* call is needed to disable the cpu hotplug and grab the
* zstrm buffer back. It is necessary that the dereferencing
* of the zstrm variable below occurs correctly.
*/
zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]);
}
alloced_pages = zs_get_total_pages(zram->mem_pool);
update_used_max(zram, alloced_pages);
if (zram->limit_pages && alloced_pages > zram->limit_pages) {
zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
zs_free(zram->mem_pool, handle);
return -ENOMEM;
}
dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO);
src = zstrm->buffer;
if (comp_len == PAGE_SIZE)
src = kmap_atomic(page);
memcpy(dst, src, comp_len);
if (comp_len == PAGE_SIZE)
kunmap_atomic(src);
zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
zs_unmap_object(zram->mem_pool, handle);
atomic64_add(comp_len, &zram->stats.compr_data_size);
out:
/*
* Free memory associated with this sector
* before overwriting unused sectors.
*/
zram_slot_lock(zram, index);
zram_free_page(zram, index);
if (comp_len == PAGE_SIZE) {
zram_set_flag(zram, index, ZRAM_HUGE);
atomic64_inc(&zram->stats.huge_pages);
atomic64_inc(&zram->stats.huge_pages_since);
}
if (flags) {
zram_set_flag(zram, index, flags);
zram_set_element(zram, index, element);
} else {
zram_set_handle(zram, index, handle);
zram_set_obj_size(zram, index, comp_len);
}
zram_slot_unlock(zram, index);
/* Update stats */
atomic64_inc(&zram->stats.pages_stored);
return ret;
}
static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
u32 index, int offset, struct bio *bio)
{
int ret;
struct page *page = NULL;
struct bio_vec vec;
vec = *bvec;
if (is_partial_io(bvec)) {
void *dst;
/*
* This is a partial IO. We need to read the full page
* before to write the changes.
*/
page = alloc_page(GFP_NOIO|__GFP_HIGHMEM);
if (!page)
return -ENOMEM;
ret = __zram_bvec_read(zram, page, index, bio, true);
if (ret)
goto out;
dst = kmap_atomic(page);
memcpy_from_bvec(dst + offset, bvec);
kunmap_atomic(dst);
bvec_set_page(&vec, page, PAGE_SIZE, 0);
}
ret = __zram_bvec_write(zram, &vec, index, bio);
out:
if (is_partial_io(bvec))
__free_page(page);
return ret;
}
#ifdef CONFIG_ZRAM_MULTI_COMP
/*
* This function will decompress (unless it's ZRAM_HUGE) the page and then
* attempt to compress it using provided compression algorithm priority
* (which is potentially more effective).
*
* Corresponding ZRAM slot should be locked.
*/
static int zram_recompress(struct zram *zram, u32 index, struct page *page,
u32 threshold, u32 prio, u32 prio_max)
{
struct zcomp_strm *zstrm = NULL;
unsigned long handle_old;
unsigned long handle_new;
unsigned int comp_len_old;
unsigned int comp_len_new;
unsigned int class_index_old;
unsigned int class_index_new;
u32 num_recomps = 0;
void *src, *dst;
int ret;
handle_old = zram_get_handle(zram, index);
if (!handle_old)
return -EINVAL;
comp_len_old = zram_get_obj_size(zram, index);
/*
* Do not recompress objects that are already "small enough".
*/
if (comp_len_old < threshold)
return 0;
ret = zram_read_from_zspool(zram, page, index);
if (ret)
return ret;
class_index_old = zs_lookup_class_index(zram->mem_pool, comp_len_old);
/*
* Iterate the secondary comp algorithms list (in order of priority)
* and try to recompress the page.
*/
for (; prio < prio_max; prio++) {
if (!zram->comps[prio])
continue;
/*
* Skip if the object is already re-compressed with a higher
* priority algorithm (or same algorithm).
*/
if (prio <= zram_get_priority(zram, index))
continue;
num_recomps++;
zstrm = zcomp_stream_get(zram->comps[prio]);
src = kmap_atomic(page);
ret = zcomp_compress(zstrm, src, &comp_len_new);
kunmap_atomic(src);
if (ret) {
zcomp_stream_put(zram->comps[prio]);
return ret;
}
class_index_new = zs_lookup_class_index(zram->mem_pool,
comp_len_new);
/* Continue until we make progress */
if (class_index_new >= class_index_old ||
(threshold && comp_len_new >= threshold)) {
zcomp_stream_put(zram->comps[prio]);
continue;
}
/* Recompression was successful so break out */
break;
}
/*
* We did not try to recompress, e.g. when we have only one
* secondary algorithm and the page is already recompressed
* using that algorithm
*/
if (!zstrm)
return 0;
if (class_index_new >= class_index_old) {
/*
* Secondary algorithms failed to re-compress the page
* in a way that would save memory, mark the object as
* incompressible so that we will not try to compress
* it again.
*
* We need to make sure that all secondary algorithms have
* failed, so we test if the number of recompressions matches
* the number of active secondary algorithms.
*/
if (num_recomps == zram->num_active_comps - 1)
zram_set_flag(zram, index, ZRAM_INCOMPRESSIBLE);
return 0;
}
/* Successful recompression but above threshold */
if (threshold && comp_len_new >= threshold)
return 0;
/*
* No direct reclaim (slow path) for handle allocation and no
* re-compression attempt (unlike in __zram_bvec_write()) since
* we already have stored that object in zsmalloc. If we cannot
* alloc memory for recompressed object then we bail out and
* simply keep the old (existing) object in zsmalloc.
*/
handle_new = zs_malloc(zram->mem_pool, comp_len_new,
__GFP_KSWAPD_RECLAIM |
__GFP_NOWARN |
__GFP_HIGHMEM |
__GFP_MOVABLE);
if (IS_ERR_VALUE(handle_new)) {
zcomp_stream_put(zram->comps[prio]);
return PTR_ERR((void *)handle_new);
}
dst = zs_map_object(zram->mem_pool, handle_new, ZS_MM_WO);
memcpy(dst, zstrm->buffer, comp_len_new);
zcomp_stream_put(zram->comps[prio]);
zs_unmap_object(zram->mem_pool, handle_new);
zram_free_page(zram, index);
zram_set_handle(zram, index, handle_new);
zram_set_obj_size(zram, index, comp_len_new);
zram_set_priority(zram, index, prio);
atomic64_add(comp_len_new, &zram->stats.compr_data_size);
atomic64_inc(&zram->stats.pages_stored);
return 0;
}
#define RECOMPRESS_IDLE (1 << 0)
#define RECOMPRESS_HUGE (1 << 1)
static ssize_t recompress_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t len)
{
u32 prio = ZRAM_SECONDARY_COMP, prio_max = ZRAM_MAX_COMPS;
struct zram *zram = dev_to_zram(dev);
unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
char *args, *param, *val, *algo = NULL;
u32 mode = 0, threshold = 0;
unsigned long index;
struct page *page;
ssize_t ret;
args = skip_spaces(buf);
while (*args) {
args = next_arg(args, &param, &val);
if (!val || !*val)
return -EINVAL;
if (!strcmp(param, "type")) {
if (!strcmp(val, "idle"))
mode = RECOMPRESS_IDLE;
if (!strcmp(val, "huge"))
mode = RECOMPRESS_HUGE;
if (!strcmp(val, "huge_idle"))
mode = RECOMPRESS_IDLE | RECOMPRESS_HUGE;
continue;
}
if (!strcmp(param, "threshold")) {
/*
* We will re-compress only idle objects equal or
* greater in size than watermark.
*/
ret = kstrtouint(val, 10, &threshold);
if (ret)
return ret;
continue;
}
if (!strcmp(param, "algo")) {
algo = val;
continue;
}
}
if (threshold >= PAGE_SIZE)
return -EINVAL;
down_read(&zram->init_lock);
if (!init_done(zram)) {
ret = -EINVAL;
goto release_init_lock;
}
if (algo) {
bool found = false;
for (; prio < ZRAM_MAX_COMPS; prio++) {
if (!zram->comp_algs[prio])
continue;
if (!strcmp(zram->comp_algs[prio], algo)) {
prio_max = min(prio + 1, ZRAM_MAX_COMPS);
found = true;
break;
}
}
if (!found) {
ret = -EINVAL;
goto release_init_lock;
}
}
page = alloc_page(GFP_KERNEL);
if (!page) {
ret = -ENOMEM;
goto release_init_lock;
}
ret = len;
for (index = 0; index < nr_pages; index++) {
int err = 0;
zram_slot_lock(zram, index);
if (!zram_allocated(zram, index))
goto next;
if (mode & RECOMPRESS_IDLE &&
!zram_test_flag(zram, index, ZRAM_IDLE))
goto next;
if (mode & RECOMPRESS_HUGE &&
!zram_test_flag(zram, index, ZRAM_HUGE))
goto next;
if (zram_test_flag(zram, index, ZRAM_WB) ||
zram_test_flag(zram, index, ZRAM_UNDER_WB) ||
zram_test_flag(zram, index, ZRAM_SAME) ||
zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE))
goto next;
err = zram_recompress(zram, index, page, threshold,
prio, prio_max);
next:
zram_slot_unlock(zram, index);
if (err) {
ret = err;
break;
}
cond_resched();
}
__free_page(page);
release_init_lock:
up_read(&zram->init_lock);
return ret;
}
#endif
/*
* zram_bio_discard - handler on discard request
* @index: physical block index in PAGE_SIZE units
* @offset: byte offset within physical block
*/
static void zram_bio_discard(struct zram *zram, u32 index,
int offset, struct bio *bio)
{
size_t n = bio->bi_iter.bi_size;
/*
* zram manages data in physical block size units. Because logical block
* size isn't identical with physical block size on some arch, we
* could get a discard request pointing to a specific offset within a
* certain physical block. Although we can handle this request by
* reading that physiclal block and decompressing and partially zeroing
* and re-compressing and then re-storing it, this isn't reasonable
* because our intent with a discard request is to save memory. So
* skipping this logical block is appropriate here.
*/
if (offset) {
if (n <= (PAGE_SIZE - offset))
return;
n -= (PAGE_SIZE - offset);
index++;
}
while (n >= PAGE_SIZE) {
zram_slot_lock(zram, index);
zram_free_page(zram, index);
zram_slot_unlock(zram, index);
atomic64_inc(&zram->stats.notify_free);
index++;
n -= PAGE_SIZE;
}
}
/*
* Returns errno if it has some problem. Otherwise return 0 or 1.
* Returns 0 if IO request was done synchronously
* Returns 1 if IO request was successfully submitted.
*/
static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
int offset, enum req_op op, struct bio *bio)
{
int ret;
if (!op_is_write(op)) {
ret = zram_bvec_read(zram, bvec, index, offset, bio);
flush_dcache_page(bvec->bv_page);
} else {
ret = zram_bvec_write(zram, bvec, index, offset, bio);
}
zram_slot_lock(zram, index);
zram_accessed(zram, index);
zram_slot_unlock(zram, index);
if (unlikely(ret < 0)) {
if (!op_is_write(op))
atomic64_inc(&zram->stats.failed_reads);
else
atomic64_inc(&zram->stats.failed_writes);
}
return ret;
}
static void __zram_make_request(struct zram *zram, struct bio *bio)
{
int offset;
u32 index;
struct bio_vec bvec;
struct bvec_iter iter;
unsigned long start_time;
index = bio->bi_iter.bi_sector >> SECTORS_PER_PAGE_SHIFT;
offset = (bio->bi_iter.bi_sector &
(SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
switch (bio_op(bio)) {
case REQ_OP_DISCARD:
case REQ_OP_WRITE_ZEROES:
zram_bio_discard(zram, index, offset, bio);
bio_endio(bio);
return;
default:
break;
}
start_time = bio_start_io_acct(bio);
bio_for_each_segment(bvec, bio, iter) {
struct bio_vec bv = bvec;
unsigned int unwritten = bvec.bv_len;
do {
bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
unwritten);
if (zram_bvec_rw(zram, &bv, index, offset,
bio_op(bio), bio) < 0) {
bio->bi_status = BLK_STS_IOERR;
break;
}
bv.bv_offset += bv.bv_len;
unwritten -= bv.bv_len;
update_position(&index, &offset, &bv);
} while (unwritten);
}
bio_end_io_acct(bio, start_time);
bio_endio(bio);
}
/*
* Handler function for all zram I/O requests.
*/
static void zram_submit_bio(struct bio *bio)
{
struct zram *zram = bio->bi_bdev->bd_disk->private_data;
if (!valid_io_request(zram, bio->bi_iter.bi_sector,
bio->bi_iter.bi_size)) {
atomic64_inc(&zram->stats.invalid_io);
bio_io_error(bio);
return;
}
__zram_make_request(zram, bio);
}
static void zram_slot_free_notify(struct block_device *bdev,
unsigned long index)
{
struct zram *zram;
zram = bdev->bd_disk->private_data;
atomic64_inc(&zram->stats.notify_free);
if (!zram_slot_trylock(zram, index)) {
atomic64_inc(&zram->stats.miss_free);
return;
}
zram_free_page(zram, index);
zram_slot_unlock(zram, index);
}
static void zram_destroy_comps(struct zram *zram)
{
u32 prio;
for (prio = 0; prio < ZRAM_MAX_COMPS; prio++) {
struct zcomp *comp = zram->comps[prio];
zram->comps[prio] = NULL;
if (!comp)
continue;
zcomp_destroy(comp);
zram->num_active_comps--;
}
}
static void zram_reset_device(struct zram *zram)
{
down_write(&zram->init_lock);
zram->limit_pages = 0;
if (!init_done(zram)) {
up_write(&zram->init_lock);
return;
}
set_capacity_and_notify(zram->disk, 0);
part_stat_set_all(zram->disk->part0, 0);
/* I/O operation under all of CPU are done so let's free */
zram_meta_free(zram, zram->disksize);
zram->disksize = 0;
zram_destroy_comps(zram);
memset(&zram->stats, 0, sizeof(zram->stats));
reset_bdev(zram);
comp_algorithm_set(zram, ZRAM_PRIMARY_COMP, default_compressor);
up_write(&zram->init_lock);
}
static ssize_t disksize_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
u64 disksize;
struct zcomp *comp;
struct zram *zram = dev_to_zram(dev);
int err;
u32 prio;
disksize = memparse(buf, NULL);
if (!disksize)
return -EINVAL;
down_write(&zram->init_lock);
if (init_done(zram)) {
pr_info("Cannot change disksize for initialized device\n");
err = -EBUSY;
goto out_unlock;
}
disksize = PAGE_ALIGN(disksize);
if (!zram_meta_alloc(zram, disksize)) {
err = -ENOMEM;
goto out_unlock;
}
for (prio = 0; prio < ZRAM_MAX_COMPS; prio++) {
if (!zram->comp_algs[prio])
continue;
comp = zcomp_create(zram->comp_algs[prio]);
if (IS_ERR(comp)) {
pr_err("Cannot initialise %s compressing backend\n",
zram->comp_algs[prio]);
err = PTR_ERR(comp);
goto out_free_comps;
}
zram->comps[prio] = comp;
zram->num_active_comps++;
}
zram->disksize = disksize;
set_capacity_and_notify(zram->disk, zram->disksize >> SECTOR_SHIFT);
up_write(&zram->init_lock);
return len;
out_free_comps:
zram_destroy_comps(zram);
zram_meta_free(zram, disksize);
out_unlock:
up_write(&zram->init_lock);
return err;
}
static ssize_t reset_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
int ret;
unsigned short do_reset;
struct zram *zram;
struct gendisk *disk;
ret = kstrtou16(buf, 10, &do_reset);
if (ret)
return ret;
if (!do_reset)
return -EINVAL;
zram = dev_to_zram(dev);
disk = zram->disk;
mutex_lock(&disk->open_mutex);
/* Do not reset an active device or claimed device */
if (disk_openers(disk) || zram->claim) {
mutex_unlock(&disk->open_mutex);
return -EBUSY;
}
/* From now on, anyone can't open /dev/zram[0-9] */
zram->claim = true;
mutex_unlock(&disk->open_mutex);
/* Make sure all the pending I/O are finished */
sync_blockdev(disk->part0);
zram_reset_device(zram);
mutex_lock(&disk->open_mutex);
zram->claim = false;
mutex_unlock(&disk->open_mutex);
return len;
}
static int zram_open(struct block_device *bdev, fmode_t mode)
{
int ret = 0;
struct zram *zram;
WARN_ON(!mutex_is_locked(&bdev->bd_disk->open_mutex));
zram = bdev->bd_disk->private_data;
/* zram was claimed to reset so open request fails */
if (zram->claim)
ret = -EBUSY;
return ret;
}
static const struct block_device_operations zram_devops = {
.open = zram_open,
.submit_bio = zram_submit_bio,
.swap_slot_free_notify = zram_slot_free_notify,
.owner = THIS_MODULE
};
static DEVICE_ATTR_WO(compact);
static DEVICE_ATTR_RW(disksize);
static DEVICE_ATTR_RO(initstate);
static DEVICE_ATTR_WO(reset);
static DEVICE_ATTR_WO(mem_limit);
static DEVICE_ATTR_WO(mem_used_max);
static DEVICE_ATTR_WO(idle);
static DEVICE_ATTR_RW(max_comp_streams);
static DEVICE_ATTR_RW(comp_algorithm);
#ifdef CONFIG_ZRAM_WRITEBACK
static DEVICE_ATTR_RW(backing_dev);
static DEVICE_ATTR_WO(writeback);
static DEVICE_ATTR_RW(writeback_limit);
static DEVICE_ATTR_RW(writeback_limit_enable);
#endif
#ifdef CONFIG_ZRAM_MULTI_COMP
static DEVICE_ATTR_RW(recomp_algorithm);
static DEVICE_ATTR_WO(recompress);
#endif
static struct attribute *zram_disk_attrs[] = {
&dev_attr_disksize.attr,
&dev_attr_initstate.attr,
&dev_attr_reset.attr,
&dev_attr_compact.attr,
&dev_attr_mem_limit.attr,
&dev_attr_mem_used_max.attr,
&dev_attr_idle.attr,
&dev_attr_max_comp_streams.attr,
&dev_attr_comp_algorithm.attr,
#ifdef CONFIG_ZRAM_WRITEBACK
&dev_attr_backing_dev.attr,
&dev_attr_writeback.attr,
&dev_attr_writeback_limit.attr,
&dev_attr_writeback_limit_enable.attr,
#endif
&dev_attr_io_stat.attr,
&dev_attr_mm_stat.attr,
#ifdef CONFIG_ZRAM_WRITEBACK
&dev_attr_bd_stat.attr,
#endif
&dev_attr_debug_stat.attr,
#ifdef CONFIG_ZRAM_MULTI_COMP
&dev_attr_recomp_algorithm.attr,
&dev_attr_recompress.attr,
#endif
NULL,
};
ATTRIBUTE_GROUPS(zram_disk);
/*
* Allocate and initialize new zram device. the function returns
* '>= 0' device_id upon success, and negative value otherwise.
*/
static int zram_add(void)
{
struct zram *zram;
int ret, device_id;
zram = kzalloc(sizeof(struct zram), GFP_KERNEL);
if (!zram)
return -ENOMEM;
ret = idr_alloc(&zram_index_idr, zram, 0, 0, GFP_KERNEL);
if (ret < 0)
goto out_free_dev;
device_id = ret;
init_rwsem(&zram->init_lock);
#ifdef CONFIG_ZRAM_WRITEBACK
spin_lock_init(&zram->wb_limit_lock);
#endif
/* gendisk structure */
zram->disk = blk_alloc_disk(NUMA_NO_NODE);
if (!zram->disk) {
pr_err("Error allocating disk structure for device %d\n",
device_id);
ret = -ENOMEM;
goto out_free_idr;
}
zram->disk->major = zram_major;
zram->disk->first_minor = device_id;
zram->disk->minors = 1;
zram->disk->flags |= GENHD_FL_NO_PART;
zram->disk->fops = &zram_devops;
zram->disk->private_data = zram;
snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
/* Actual capacity set using sysfs (/sys/block/zram<id>/disksize */
set_capacity(zram->disk, 0);
/* zram devices sort of resembles non-rotational disks */
blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue);
blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue);
blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue);
/*
* To ensure that we always get PAGE_SIZE aligned
* and n*PAGE_SIZED sized I/O requests.
*/
blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
blk_queue_logical_block_size(zram->disk->queue,
ZRAM_LOGICAL_BLOCK_SIZE);
blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
/*
* zram_bio_discard() will clear all logical blocks if logical block
* size is identical with physical block size(PAGE_SIZE). But if it is
* different, we will skip discarding some parts of logical blocks in
* the part of the request range which isn't aligned to physical block
* size. So we can't ensure that all discarded logical blocks are
* zeroed.
*/
if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
ret = device_add_disk(NULL, zram->disk, zram_disk_groups);
if (ret)
goto out_cleanup_disk;
comp_algorithm_set(zram, ZRAM_PRIMARY_COMP, default_compressor);
zram_debugfs_register(zram);
pr_info("Added device: %s\n", zram->disk->disk_name);
return device_id;
out_cleanup_disk:
put_disk(zram->disk);
out_free_idr:
idr_remove(&zram_index_idr, device_id);
out_free_dev:
kfree(zram);
return ret;
}
static int zram_remove(struct zram *zram)
{
bool claimed;
mutex_lock(&zram->disk->open_mutex);
if (disk_openers(zram->disk)) {
mutex_unlock(&zram->disk->open_mutex);
return -EBUSY;
}
claimed = zram->claim;
if (!claimed)
zram->claim = true;
mutex_unlock(&zram->disk->open_mutex);
zram_debugfs_unregister(zram);
if (claimed) {
/*
* If we were claimed by reset_store(), del_gendisk() will
* wait until reset_store() is done, so nothing need to do.
*/
;
} else {
/* Make sure all the pending I/O are finished */
sync_blockdev(zram->disk->part0);
zram_reset_device(zram);
}
pr_info("Removed device: %s\n", zram->disk->disk_name);
del_gendisk(zram->disk);
/* del_gendisk drains pending reset_store */
WARN_ON_ONCE(claimed && zram->claim);
/*
* disksize_store() may be called in between zram_reset_device()
* and del_gendisk(), so run the last reset to avoid leaking
* anything allocated with disksize_store()
*/
zram_reset_device(zram);
put_disk(zram->disk);
kfree(zram);
return 0;
}
/* zram-control sysfs attributes */
/*
* NOTE: hot_add attribute is not the usual read-only sysfs attribute. In a
* sense that reading from this file does alter the state of your system -- it
* creates a new un-initialized zram device and returns back this device's
* device_id (or an error code if it fails to create a new device).
*/
static ssize_t hot_add_show(struct class *class,
struct class_attribute *attr,
char *buf)
{
int ret;
mutex_lock(&zram_index_mutex);
ret = zram_add();
mutex_unlock(&zram_index_mutex);
if (ret < 0)
return ret;
return scnprintf(buf, PAGE_SIZE, "%d\n", ret);
}
static struct class_attribute class_attr_hot_add =
__ATTR(hot_add, 0400, hot_add_show, NULL);
static ssize_t hot_remove_store(struct class *class,
struct class_attribute *attr,
const char *buf,
size_t count)
{
struct zram *zram;
int ret, dev_id;
/* dev_id is gendisk->first_minor, which is `int' */
ret = kstrtoint(buf, 10, &dev_id);
if (ret)
return ret;
if (dev_id < 0)
return -EINVAL;
mutex_lock(&zram_index_mutex);
zram = idr_find(&zram_index_idr, dev_id);
if (zram) {
ret = zram_remove(zram);
if (!ret)
idr_remove(&zram_index_idr, dev_id);
} else {
ret = -ENODEV;
}
mutex_unlock(&zram_index_mutex);
return ret ? ret : count;
}
static CLASS_ATTR_WO(hot_remove);
static struct attribute *zram_control_class_attrs[] = {
&class_attr_hot_add.attr,
&class_attr_hot_remove.attr,
NULL,
};
ATTRIBUTE_GROUPS(zram_control_class);
static struct class zram_control_class = {
.name = "zram-control",
.owner = THIS_MODULE,
.class_groups = zram_control_class_groups,
};
static int zram_remove_cb(int id, void *ptr, void *data)
{
WARN_ON_ONCE(zram_remove(ptr));
return 0;
}
static void destroy_devices(void)
{
class_unregister(&zram_control_class);
idr_for_each(&zram_index_idr, &zram_remove_cb, NULL);
zram_debugfs_destroy();
idr_destroy(&zram_index_idr);
unregister_blkdev(zram_major, "zram");
cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
}
static int __init zram_init(void)
{
int ret;
BUILD_BUG_ON(__NR_ZRAM_PAGEFLAGS > BITS_PER_LONG);
ret = cpuhp_setup_state_multi(CPUHP_ZCOMP_PREPARE, "block/zram:prepare",
zcomp_cpu_up_prepare, zcomp_cpu_dead);
if (ret < 0)
return ret;
ret = class_register(&zram_control_class);
if (ret) {
pr_err("Unable to register zram-control class\n");
cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
return ret;
}
zram_debugfs_create();
zram_major = register_blkdev(0, "zram");
if (zram_major <= 0) {
pr_err("Unable to get major number\n");
class_unregister(&zram_control_class);
cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
return -EBUSY;
}
while (num_devices != 0) {
mutex_lock(&zram_index_mutex);
ret = zram_add();
mutex_unlock(&zram_index_mutex);
if (ret < 0)
goto out_error;
num_devices--;
}
return 0;
out_error:
destroy_devices();
return ret;
}
static void __exit zram_exit(void)
{
destroy_devices();
}
module_init(zram_init);
module_exit(zram_exit);
module_param(num_devices, uint, 0);
MODULE_PARM_DESC(num_devices, "Number of pre-created zram devices");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
MODULE_DESCRIPTION("Compressed RAM Block Device");
Reference in New Issue View Git Blame Copy Permalink