blob: 0798d6aacedd3fa5512d016f07c7448954a88b20 [file] [log] [blame]
/*
* 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/genhd.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/cpuhotplug.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 = "lzo";
/* Module params (documentation at end) */
static unsigned int num_devices = 1;
static void zram_free_page(struct zram *zram, size_t index);
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 int zram_test_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
return zram->table[index].value & BIT(flag);
}
static void zram_set_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
zram->table[index].value |= BIT(flag);
}
static void zram_clear_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
zram->table[index].value &= ~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].value & (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].value >> ZRAM_FLAG_SHIFT;
zram->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
}
#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 void zram_revalidate_disk(struct zram *zram)
{
revalidate_disk(zram->disk);
/* revalidate_disk reset the BDI_CAP_STABLE_WRITES so set again */
zram->disk->queue->backing_dev_info->capabilities |=
BDI_CAP_STABLE_WRITES;
}
/*
* 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 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 old_max, cur_max;
old_max = atomic_long_read(&zram->stats.max_used_pages);
do {
cur_max = old_max;
if (pages > cur_max)
old_max = atomic_long_cmpxchg(
&zram->stats.max_used_pages, cur_max, pages);
} while (old_max != cur_max);
}
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 int pos;
unsigned long *page;
unsigned long val;
page = (unsigned long *)ptr;
val = page[0];
for (pos = 1; pos < PAGE_SIZE / sizeof(*page); 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;
}
#ifdef CONFIG_ZRAM_WRITEBACK
static bool zram_wb_enabled(struct zram *zram)
{
return zram->backing_dev;
}
static void reset_bdev(struct zram *zram)
{
struct block_device *bdev;
if (!zram_wb_enabled(zram))
return;
bdev = zram->bdev;
if (zram->old_block_size)
set_blocksize(bdev, zram->old_block_size);
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->old_block_size = 0;
zram->bdev = NULL;
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, old_block_size = 0;
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;
}
strlcpy(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 = bdgrab(I_BDEV(inode));
err = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram);
if (err < 0) {
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;
}
old_block_size = block_size(bdev);
err = set_blocksize(bdev, PAGE_SIZE);
if (err)
goto out;
reset_bdev(zram);
spin_lock_init(&zram->bitmap_lock);
zram->old_block_size = old_block_size;
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:
if (bitmap)
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 get_entry_bdev(struct zram *zram)
{
unsigned long entry;
spin_lock(&zram->bitmap_lock);
/* skip 0 bit to confuse zram.handle = 0 */
entry = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1);
if (entry == zram->nr_pages) {
spin_unlock(&zram->bitmap_lock);
return 0;
}
set_bit(entry, zram->bitmap);
spin_unlock(&zram->bitmap_lock);
return entry;
}
static void put_entry_bdev(struct zram *zram, unsigned long entry)
{
int was_set;
spin_lock(&zram->bitmap_lock);
was_set = test_and_clear_bit(entry, zram->bitmap);
spin_unlock(&zram->bitmap_lock);
WARN_ON_ONCE(!was_set);
}
void zram_page_end_io(struct bio *bio)
{
struct page *page = bio->bi_io_vec[0].bv_page;
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(GFP_ATOMIC, 1);
if (!bio)
return -ENOMEM;
bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
bio_set_dev(bio, zram->bdev);
if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) {
bio_put(bio);
return -EIO;
}
if (!parent) {
bio->bi_opf = REQ_OP_READ;
bio->bi_end_io = zram_page_end_io;
} else {
bio->bi_opf = parent->bi_opf;
bio_chain(bio, parent);
}
submit_bio(bio);
return 1;
}
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 ->make_request_fn to be active at a time
* so if we use chained IO with parent IO in same context,
* it's a deadlock. To avoid, it, it uses 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)
{
if (sync)
return read_from_bdev_sync(zram, bvec, entry, parent);
else
return read_from_bdev_async(zram, bvec, entry, parent);
}
static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
u32 index, struct bio *parent,
unsigned long *pentry)
{
struct bio *bio;
unsigned long entry;
bio = bio_alloc(GFP_ATOMIC, 1);
if (!bio)
return -ENOMEM;
entry = get_entry_bdev(zram);
if (!entry) {
bio_put(bio);
return -ENOSPC;
}
bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
bio_set_dev(bio, zram->bdev);
if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len,
bvec->bv_offset)) {
bio_put(bio);
put_entry_bdev(zram, entry);
return -EIO;
}
if (!parent) {
bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
bio->bi_end_io = zram_page_end_io;
} else {
bio->bi_opf = parent->bi_opf;
bio_chain(bio, parent);
}
submit_bio(bio);
*pentry = entry;
return 0;
}
static void zram_wb_clear(struct zram *zram, u32 index)
{
unsigned long entry;
zram_clear_flag(zram, index, ZRAM_WB);
entry = zram_get_element(zram, index);
zram_set_element(zram, index, 0);
put_entry_bdev(zram, entry);
}
#else
static bool zram_wb_enabled(struct zram *zram) { return false; }
static inline void reset_bdev(struct zram *zram) {};
static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
u32 index, struct bio *parent,
unsigned long *pentry)
{
return -EIO;
}
static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
unsigned long entry, struct bio *parent, bool sync)
{
return -EIO;
}
static void zram_wb_clear(struct zram *zram, u32 index) {}
#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 ssize_t comp_algorithm_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
size_t sz;
struct zram *zram = dev_to_zram(dev);
down_read(&zram->init_lock);
sz = zcomp_available_show(zram->compressor, buf);
up_read(&zram->init_lock);
return sz;
}
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);
char compressor[ARRAY_SIZE(zram->compressor)];
size_t sz;
strlcpy(compressor, buf, sizeof(compressor));
/* ignore trailing newline */
sz = strlen(compressor);
if (sz > 0 && compressor[sz - 1] == '\n')
compressor[sz - 1] = 0x00;
if (!zcomp_available_algorithm(compressor))
return -EINVAL;
down_write(&zram->init_lock);
if (init_done(zram)) {
up_write(&zram->init_lock);
pr_info("Can't change algorithm for initialized device\n");
return -EBUSY;
}
strcpy(zram->compressor, compressor);
up_write(&zram->init_lock);
return len;
}
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\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));
up_read(&zram->init_lock);
return ret;
}
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\n",
version,
(u64)atomic64_read(&zram->stats.writestall));
up_read(&zram->init_lock);
return ret;
}
static DEVICE_ATTR_RO(io_stat);
static DEVICE_ATTR_RO(mm_stat);
static DEVICE_ATTR_RO(debug_stat);
static void zram_slot_lock(struct zram *zram, u32 index)
{
bit_spin_lock(ZRAM_ACCESS, &zram->table[index].value);
}
static void zram_slot_unlock(struct zram *zram, u32 index)
{
bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value);
}
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(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;
}
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;
if (zram_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) {
zram_wb_clear(zram, index);
atomic64_dec(&zram->stats.pages_stored);
return;
}
/*
* 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);
zram_set_element(zram, index, 0);
atomic64_dec(&zram->stats.same_pages);
atomic64_dec(&zram->stats.pages_stored);
return;
}
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);
atomic64_dec(&zram->stats.pages_stored);
zram_set_handle(zram, index, 0);
zram_set_obj_size(zram, index, 0);
}
static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
struct bio *bio, bool partial_io)
{
int ret;
unsigned long handle;
unsigned int size;
void *src, *dst;
if (zram_wb_enabled(zram)) {
zram_slot_lock(zram, index);
if (zram_test_flag(zram, index, ZRAM_WB)) {
struct bio_vec bvec;
zram_slot_unlock(zram, index);
bvec.bv_page = page;
bvec.bv_len = PAGE_SIZE;
bvec.bv_offset = 0;
return read_from_bdev(zram, &bvec,
zram_get_element(zram, index),
bio, partial_io);
}
zram_slot_unlock(zram, index);
}
zram_slot_lock(zram, index);
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);
zram_slot_unlock(zram, index);
return 0;
}
size = zram_get_obj_size(zram, index);
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 {
struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
dst = kmap_atomic(page);
ret = zcomp_decompress(zstrm, src, size, dst);
kunmap_atomic(dst);
zcomp_stream_put(zram->comp);
}
zs_unmap_object(zram->mem_pool, handle);
zram_slot_unlock(zram, index);
/* Should NEVER happen. Return bio error if it does. */
if (unlikely(ret))
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 *dst = kmap_atomic(bvec->bv_page);
void *src = kmap_atomic(page);
memcpy(dst + bvec->bv_offset, src + offset, bvec->bv_len);
kunmap_atomic(src);
kunmap_atomic(dst);
}
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 = 0;
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;
bool allow_wb = true;
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->comp);
src = kmap_atomic(page);
ret = zcomp_compress(zstrm, src, &comp_len);
kunmap_atomic(src);
if (unlikely(ret)) {
zcomp_stream_put(zram->comp);
pr_err("Compression failed! err=%d\n", ret);
zs_free(zram->mem_pool, handle);
return ret;
}
if (unlikely(comp_len > max_zpage_size)) {
if (zram_wb_enabled(zram) && allow_wb) {
zcomp_stream_put(zram->comp);
ret = write_to_bdev(zram, bvec, index, bio, &element);
if (!ret) {
flags = ZRAM_WB;
ret = 1;
goto out;
}
allow_wb = false;
goto compress_again;
}
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 (!handle)
handle = zs_malloc(zram->mem_pool, comp_len,
__GFP_KSWAPD_RECLAIM |
__GFP_NOWARN |
__GFP_HIGHMEM |
__GFP_MOVABLE);
if (!handle) {
zcomp_stream_put(zram->comp);
atomic64_inc(&zram->stats.writestall);
handle = zs_malloc(zram->mem_pool, comp_len,
GFP_NOIO | __GFP_HIGHMEM |
__GFP_MOVABLE);
if (handle)
goto compress_again;
return -ENOMEM;
}
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->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->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 (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;
void *src;
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;
src = kmap_atomic(bvec->bv_page);
dst = kmap_atomic(page);
memcpy(dst + offset, src + bvec->bv_offset, bvec->bv_len);
kunmap_atomic(dst);
kunmap_atomic(src);
vec.bv_page = page;
vec.bv_len = PAGE_SIZE;
vec.bv_offset = 0;
}
ret = __zram_bvec_write(zram, &vec, index, bio);
out:
if (is_partial_io(bvec))
__free_page(page);
return ret;
}
/*
* 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, bool is_write, struct bio *bio)
{
unsigned long start_time = jiffies;
int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
struct request_queue *q = zram->disk->queue;
int ret;
generic_start_io_acct(q, rw_acct, bvec->bv_len >> SECTOR_SHIFT,
&zram->disk->part0);
if (!is_write) {
atomic64_inc(&zram->stats.num_reads);
ret = zram_bvec_read(zram, bvec, index, offset, bio);
flush_dcache_page(bvec->bv_page);
} else {
atomic64_inc(&zram->stats.num_writes);
ret = zram_bvec_write(zram, bvec, index, offset, bio);
}
generic_end_io_acct(q, rw_acct, &zram->disk->part0, start_time);
if (unlikely(ret < 0)) {
if (!is_write)
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;
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;
}
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,
op_is_write(bio_op(bio)), bio) < 0)
goto out;
bv.bv_offset += bv.bv_len;
unwritten -= bv.bv_len;
update_position(&index, &offset, &bv);
} while (unwritten);
}
bio_endio(bio);
return;
out:
bio_io_error(bio);
}
/*
* Handler function for all zram I/O requests.
*/
static blk_qc_t zram_make_request(struct request_queue *queue, struct bio *bio)
{
struct zram *zram = queue->queuedata;
if (!valid_io_request(zram, bio->bi_iter.bi_sector,
bio->bi_iter.bi_size)) {
atomic64_inc(&zram->stats.invalid_io);
goto error;
}
__zram_make_request(zram, bio);
return BLK_QC_T_NONE;
error:
bio_io_error(bio);
return BLK_QC_T_NONE;
}
static void zram_slot_free_notify(struct block_device *bdev,
unsigned long index)
{
struct zram *zram;
zram = bdev->bd_disk->private_data;
zram_slot_lock(zram, index);
zram_free_page(zram, index);
zram_slot_unlock(zram, index);
atomic64_inc(&zram->stats.notify_free);
}
static int zram_rw_page(struct block_device *bdev, sector_t sector,
struct page *page, bool is_write)
{
int offset, ret;
u32 index;
struct zram *zram;
struct bio_vec bv;
if (PageTransHuge(page))
return -ENOTSUPP;
zram = bdev->bd_disk->private_data;
if (!valid_io_request(zram, sector, PAGE_SIZE)) {
atomic64_inc(&zram->stats.invalid_io);
ret = -EINVAL;
goto out;
}
index = sector >> SECTORS_PER_PAGE_SHIFT;
offset = (sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
bv.bv_page = page;
bv.bv_len = PAGE_SIZE;
bv.bv_offset = 0;
ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL);
out:
/*
* If I/O fails, just return error(ie, non-zero) without
* calling page_endio.
* It causes resubmit the I/O with bio request by upper functions
* of rw_page(e.g., swap_readpage, __swap_writepage) and
* bio->bi_end_io does things to handle the error
* (e.g., SetPageError, set_page_dirty and extra works).
*/
if (unlikely(ret < 0))
return ret;
switch (ret) {
case 0:
page_endio(page, is_write, 0);
break;
case 1:
ret = 0;
break;
default:
WARN_ON(1);
}
return ret;
}
static void zram_reset_device(struct zram *zram)
{
struct zcomp *comp;
u64 disksize;
down_write(&zram->init_lock);
zram->limit_pages = 0;
if (!init_done(zram)) {
up_write(&zram->init_lock);
return;
}
comp = zram->comp;
disksize = zram->disksize;
zram->disksize = 0;
set_capacity(zram->disk, 0);
part_stat_set_all(&zram->disk->part0, 0);
up_write(&zram->init_lock);
/* I/O operation under all of CPU are done so let's free */
zram_meta_free(zram, disksize);
memset(&zram->stats, 0, sizeof(zram->stats));
zcomp_destroy(comp);
reset_bdev(zram);
}
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;
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;
}
comp = zcomp_create(zram->compressor);
if (IS_ERR(comp)) {
pr_err("Cannot initialise %s compressing backend\n",
zram->compressor);
err = PTR_ERR(comp);
goto out_free_meta;
}
zram->comp = comp;
zram->disksize = disksize;
set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
zram_revalidate_disk(zram);
up_write(&zram->init_lock);
return len;
out_free_meta:
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 block_device *bdev;
ret = kstrtou16(buf, 10, &do_reset);
if (ret)
return ret;
if (!do_reset)
return -EINVAL;
zram = dev_to_zram(dev);
bdev = bdget_disk(zram->disk, 0);
if (!bdev)
return -ENOMEM;
mutex_lock(&bdev->bd_mutex);
/* Do not reset an active device or claimed device */
if (bdev->bd_openers || zram->claim) {
mutex_unlock(&bdev->bd_mutex);
bdput(bdev);
return -EBUSY;
}
/* From now on, anyone can't open /dev/zram[0-9] */
zram->claim = true;
mutex_unlock(&bdev->bd_mutex);
/* Make sure all the pending I/O are finished */
fsync_bdev(bdev);
zram_reset_device(zram);
zram_revalidate_disk(zram);
bdput(bdev);
mutex_lock(&bdev->bd_mutex);
zram->claim = false;
mutex_unlock(&bdev->bd_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_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,
.swap_slot_free_notify = zram_slot_free_notify,
.rw_page = zram_rw_page,
.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_RW(max_comp_streams);
static DEVICE_ATTR_RW(comp_algorithm);
#ifdef CONFIG_ZRAM_WRITEBACK
static DEVICE_ATTR_RW(backing_dev);
#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_max_comp_streams.attr,
&dev_attr_comp_algorithm.attr,
#ifdef CONFIG_ZRAM_WRITEBACK
&dev_attr_backing_dev.attr,
#endif
&dev_attr_io_stat.attr,
&dev_attr_mm_stat.attr,
&dev_attr_debug_stat.attr,
NULL,
};
static const struct attribute_group zram_disk_attr_group = {
.attrs = zram_disk_attrs,
};
static const struct attribute_group *zram_disk_attr_groups[] = {
&zram_disk_attr_group,
NULL,
};
/*
* 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;
struct request_queue *queue;
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);
queue = blk_alloc_queue(GFP_KERNEL);
if (!queue) {
pr_err("Error allocating disk queue for device %d\n",
device_id);
ret = -ENOMEM;
goto out_free_idr;
}
blk_queue_make_request(queue, zram_make_request);
/* gendisk structure */
zram->disk = alloc_disk(1);
if (!zram->disk) {
pr_err("Error allocating disk structure for device %d\n",
device_id);
ret = -ENOMEM;
goto out_free_queue;
}
zram->disk->major = zram_major;
zram->disk->first_minor = device_id;
zram->disk->fops = &zram_devops;
zram->disk->queue = queue;
zram->disk->queue->queuedata = zram;
zram->disk->private_data = zram;
snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
/* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
set_capacity(zram->disk, 0);
/* zram devices sort of resembles non-rotational disks */
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
queue_flag_clear_unlocked(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);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
/*
* 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);
disk_to_dev(zram->disk)->groups = zram_disk_attr_groups;
add_disk(zram->disk);
strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
pr_info("Added device: %s\n", zram->disk->disk_name);
return device_id;
out_free_queue:
blk_cleanup_queue(queue);
out_free_idr:
idr_remove(&zram_index_idr, device_id);
out_free_dev:
kfree(zram);
return ret;
}
static int zram_remove(struct zram *zram)
{
struct block_device *bdev;
bdev = bdget_disk(zram->disk, 0);
if (!bdev)
return -ENOMEM;
mutex_lock(&bdev->bd_mutex);
if (bdev->bd_openers || zram->claim) {
mutex_unlock(&bdev->bd_mutex);
bdput(bdev);
return -EBUSY;
}
zram->claim = true;
mutex_unlock(&bdev->bd_mutex);
/* Make sure all the pending I/O are finished */
fsync_bdev(bdev);
zram_reset_device(zram);
bdput(bdev);
pr_info("Removed device: %s\n", zram->disk->disk_name);
blk_cleanup_queue(zram->disk->queue);
del_gendisk(zram->disk);
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)
{
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);
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;
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_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");