diff options
Diffstat (limited to 'drivers/block/zram')
-rw-r--r-- | drivers/block/zram/Kconfig | 3 | ||||
-rw-r--r-- | drivers/block/zram/zcomp.c | 11 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.c | 165 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.h | 15 |
4 files changed, 85 insertions, 109 deletions
diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index 668c6bf2554d..d4100b0c083e 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 config ZRAM tristate "Compressed RAM block device support" - depends on BLOCK && SYSFS && ZSMALLOC && CRYPTO + depends on BLOCK && SYSFS && MMU depends on CRYPTO_LZO || CRYPTO_ZSTD || CRYPTO_LZ4 || CRYPTO_LZ4HC || CRYPTO_842 + select ZSMALLOC help Creates virtual block devices called /dev/zramX (X = 0, 1, ...). Pages written to these disks are compressed and stored in memory diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index 052aa3f65514..0916de952e09 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -63,12 +63,6 @@ static int zcomp_strm_init(struct zcomp_strm *zstrm, struct zcomp *comp) bool zcomp_available_algorithm(const char *comp) { - int i; - - i = sysfs_match_string(backends, comp); - if (i >= 0) - return true; - /* * Crypto does not ignore a trailing new line symbol, * so make sure you don't supply a string containing @@ -217,6 +211,11 @@ struct zcomp *zcomp_create(const char *compress) struct zcomp *comp; int error; + /* + * Crypto API will execute /sbin/modprobe if the compression module + * is not loaded yet. We must do it here, otherwise we are about to + * call /sbin/modprobe under CPU hot-plug lock. + */ if (!zcomp_available_algorithm(compress)) return ERR_PTR(-EINVAL); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 25071126995b..966aab902d19 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -22,7 +22,6 @@ #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> @@ -53,7 +52,6 @@ static unsigned int num_devices = 1; static size_t huge_class_size; static const struct block_device_operations zram_devops; -static const struct block_device_operations zram_wb_devops; static void zram_free_page(struct zram *zram, size_t index); static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, @@ -328,8 +326,8 @@ static ssize_t idle_store(struct device *dev, 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. + * If it did not parse as 'all' try to treat it as an integer + * when we have memory tracking enabled. */ u64 age_sec; @@ -344,7 +342,10 @@ static ssize_t idle_store(struct device *dev, if (!init_done(zram)) goto out_unlock; - /* A cutoff_time of 0 marks everything as idle, this is the "all" behavior */ + /* + * A cutoff_time of 0 marks everything as idle, this is the + * "all" behavior. + */ mark_idle(zram, cutoff_time); rv = len; @@ -498,7 +499,7 @@ static ssize_t backing_dev_store(struct device *dev, goto out; } - strlcpy(file_name, buf, PATH_MAX); + strscpy(file_name, buf, PATH_MAX); /* ignore trailing newline */ sz = strlen(file_name); if (sz > 0 && file_name[sz - 1] == '\n') @@ -542,17 +543,6 @@ static ssize_t backing_dev_store(struct device *dev, zram->backing_dev = backing_dev; zram->bitmap = bitmap; zram->nr_pages = nr_pages; - /* - * With writeback feature, zram does asynchronous IO so it's no longer - * synchronous device so let's remove synchronous io flag. Othewise, - * upper layer(e.g., swap) could wait IO completion rather than - * (submit and return), which will cause system sluggish. - * Furthermore, when the IO function returns(e.g., swap_readpage), - * upper layer expects IO was done so it could deallocate the page - * freely but in fact, IO is going on so finally could cause - * use-after-free when the IO is really done. - */ - zram->disk->fops = &zram_wb_devops; up_write(&zram->init_lock); pr_info("setup backing device %s\n", file_name); @@ -617,24 +607,21 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, { struct bio *bio; - bio = bio_alloc(GFP_NOIO, 1); + 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); - 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; + if (!parent) bio->bi_end_io = zram_page_end_io; - } else { - bio->bi_opf = parent->bi_opf; + else bio_chain(bio, parent); - } submit_bio(bio); return 1; @@ -643,8 +630,8 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, #define PAGE_WB_SIG "page_index=" #define PAGE_WRITEBACK 0 -#define HUGE_WRITEBACK 1 -#define IDLE_WRITEBACK 2 +#define HUGE_WRITEBACK (1<<0) +#define IDLE_WRITEBACK (1<<1) static ssize_t writeback_store(struct device *dev, @@ -664,6 +651,8 @@ static ssize_t writeback_store(struct device *dev, 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 (strncmp(buf, PAGE_WB_SIG, sizeof(PAGE_WB_SIG) - 1)) return -EINVAL; @@ -725,10 +714,10 @@ static ssize_t writeback_store(struct device *dev, zram_test_flag(zram, index, ZRAM_UNDER_WB)) goto next; - if (mode == IDLE_WRITEBACK && + if (mode & IDLE_WRITEBACK && !zram_test_flag(zram, index, ZRAM_IDLE)) goto next; - if (mode == HUGE_WRITEBACK && + if (mode & HUGE_WRITEBACK && !zram_test_flag(zram, index, ZRAM_HUGE)) goto next; /* @@ -747,10 +736,9 @@ static ssize_t writeback_store(struct device *dev, continue; } - bio_init(&bio, &bio_vec, 1); - bio_set_dev(&bio, zram->bdev); + bio_init(&bio, zram->bdev, &bio_vec, 1, + REQ_OP_WRITE | REQ_SYNC); bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9); - bio.bi_opf = REQ_OP_WRITE | REQ_SYNC; bio_add_page(&bio, bvec.bv_page, bvec.bv_len, bvec.bv_offset); @@ -1032,7 +1020,7 @@ static ssize_t comp_algorithm_store(struct device *dev, char compressor[ARRAY_SIZE(zram->compressor)]; size_t sz; - strlcpy(compressor, buf, sizeof(compressor)); + strscpy(compressor, buf, sizeof(compressor)); /* ignore trailing newline */ sz = strlen(compressor); if (sz > 0 && compressor[sz - 1] == '\n') @@ -1268,6 +1256,9 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, struct bio_vec bvec; zram_slot_unlock(zram, index); + /* A null bio means rw_page was used, we must fallback to bio */ + if (!bio) + return -EOPNOTSUPP; bvec.bv_page = page; bvec.bv_len = PAGE_SIZE; @@ -1336,12 +1327,10 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, 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); + memcpy_to_bvec(bvec, src + offset); kunmap_atomic(src); - kunmap_atomic(dst); } out: if (is_partial_io(bvec)) @@ -1355,7 +1344,7 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, { int ret = 0; unsigned long alloced_pages; - unsigned long handle = 0; + unsigned long handle = -ENOMEM; unsigned int comp_len = 0; void *src, *dst, *mem; struct zcomp_strm *zstrm; @@ -1401,21 +1390,31 @@ compress_again: * if we have a 'non-null' handle here then we are coming * from the slow path and handle has already been allocated. */ - if (!handle) + if (IS_ERR((void *)handle)) handle = zs_malloc(zram->mem_pool, comp_len, __GFP_KSWAPD_RECLAIM | __GFP_NOWARN | __GFP_HIGHMEM | __GFP_MOVABLE); - if (!handle) { + if (IS_ERR((void *)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) + if (IS_ERR((void *)handle)) + return PTR_ERR((void *)handle); + + if (comp_len != PAGE_SIZE) goto compress_again; - return -ENOMEM; + /* + * 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->comp); } alloced_pages = zs_get_total_pages(zram->mem_pool); @@ -1472,7 +1471,6 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, { int ret; struct page *page = NULL; - void *src; struct bio_vec vec; vec = *bvec; @@ -1490,11 +1488,9 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, if (ret) goto out; - src = kmap_atomic(bvec->bv_page); dst = kmap_atomic(page); - memcpy(dst + offset, src + bvec->bv_offset, bvec->bv_len); + memcpy_from_bvec(dst + offset, bvec); kunmap_atomic(dst); - kunmap_atomic(src); vec.bv_page = page; vec.bv_len = PAGE_SIZE; @@ -1552,7 +1548,7 @@ static void zram_bio_discard(struct zram *zram, u32 index, * Returns 1 if IO request was successfully submitted. */ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, - int offset, unsigned int op, struct bio *bio) + int offset, enum req_op op, struct bio *bio) { int ret; @@ -1660,7 +1656,7 @@ static void zram_slot_free_notify(struct block_device *bdev, } static int zram_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, unsigned int op) + struct page *page, enum req_op op) { int offset, ret; u32 index; @@ -1685,9 +1681,10 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, bv.bv_len = PAGE_SIZE; bv.bv_offset = 0; - start_time = disk_start_io_acct(bdev->bd_disk, SECTORS_PER_PAGE, op); + start_time = bdev_start_io_acct(bdev->bd_disk->part0, + SECTORS_PER_PAGE, op, jiffies); ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL); - disk_end_io_acct(bdev->bd_disk, op, start_time); + bdev_end_io_acct(bdev->bd_disk->part0, op, start_time); out: /* * If I/O fails, just return error(ie, non-zero) without @@ -1715,9 +1712,6 @@ out: static void zram_reset_device(struct zram *zram) { - struct zcomp *comp; - u64 disksize; - down_write(&zram->init_lock); zram->limit_pages = 0; @@ -1727,17 +1721,15 @@ static void zram_reset_device(struct zram *zram) return; } - comp = zram->comp; - disksize = zram->disksize; - zram->disksize = 0; - 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, disksize); + zram_meta_free(zram, zram->disksize); + zram->disksize = 0; memset(&zram->stats, 0, sizeof(zram->stats)); - zcomp_destroy(comp); + zcomp_destroy(zram->comp); + zram->comp = NULL; reset_bdev(zram); up_write(&zram->init_lock); @@ -1796,7 +1788,7 @@ static ssize_t reset_store(struct device *dev, int ret; unsigned short do_reset; struct zram *zram; - struct block_device *bdev; + struct gendisk *disk; ret = kstrtou16(buf, 10, &do_reset); if (ret) @@ -1806,26 +1798,26 @@ static ssize_t reset_store(struct device *dev, return -EINVAL; zram = dev_to_zram(dev); - bdev = zram->disk->part0; + disk = zram->disk; - mutex_lock(&bdev->bd_disk->open_mutex); + mutex_lock(&disk->open_mutex); /* Do not reset an active device or claimed device */ - if (bdev->bd_openers || zram->claim) { - mutex_unlock(&bdev->bd_disk->open_mutex); + 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(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); /* Make sure all the pending I/O are finished */ - sync_blockdev(bdev); + sync_blockdev(disk->part0); zram_reset_device(zram); - mutex_lock(&bdev->bd_disk->open_mutex); + mutex_lock(&disk->open_mutex); zram->claim = false; - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); return len; } @@ -1853,15 +1845,6 @@ static const struct block_device_operations zram_devops = { .owner = THIS_MODULE }; -#ifdef CONFIG_ZRAM_WRITEBACK -static const struct block_device_operations zram_wb_devops = { - .open = zram_open, - .submit_bio = zram_submit_bio, - .swap_slot_free_notify = zram_slot_free_notify, - .owner = THIS_MODULE -}; -#endif - static DEVICE_ATTR_WO(compact); static DEVICE_ATTR_RW(disksize); static DEVICE_ATTR_RO(initstate); @@ -1903,14 +1886,7 @@ static struct attribute *zram_disk_attrs[] = { 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, -}; +ATTRIBUTE_GROUPS(zram_disk); /* * Allocate and initialize new zram device. the function returns @@ -1947,6 +1923,7 @@ static int zram_add(void) 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); @@ -1968,7 +1945,6 @@ static int zram_add(void) 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); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, zram->disk->queue); /* * zram_bio_discard() will clear all logical blocks if logical block @@ -1982,18 +1958,18 @@ static int zram_add(void) 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_attr_groups); + ret = device_add_disk(NULL, zram->disk, zram_disk_groups); if (ret) goto out_cleanup_disk; - strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor)); + strscpy(zram->compressor, default_compressor, sizeof(zram->compressor)); zram_debugfs_register(zram); pr_info("Added device: %s\n", zram->disk->disk_name); return device_id; out_cleanup_disk: - blk_cleanup_disk(zram->disk); + put_disk(zram->disk); out_free_idr: idr_remove(&zram_index_idr, device_id); out_free_dev: @@ -2003,19 +1979,18 @@ out_free_dev: static int zram_remove(struct zram *zram) { - struct block_device *bdev = zram->disk->part0; bool claimed; - mutex_lock(&bdev->bd_disk->open_mutex); - if (bdev->bd_openers) { - mutex_unlock(&bdev->bd_disk->open_mutex); + 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(&bdev->bd_disk->open_mutex); + mutex_unlock(&zram->disk->open_mutex); zram_debugfs_unregister(zram); @@ -2027,7 +2002,7 @@ static int zram_remove(struct zram *zram) ; } else { /* Make sure all the pending I/O are finished */ - sync_blockdev(bdev); + sync_blockdev(zram->disk->part0); zram_reset_device(zram); } @@ -2045,7 +2020,7 @@ static int zram_remove(struct zram *zram) */ zram_reset_device(zram); - blk_cleanup_disk(zram->disk); + put_disk(zram->disk); kfree(zram); return 0; } @@ -2139,6 +2114,8 @@ 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) diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 80c3b43b4828..a2bda53020fd 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -30,16 +30,15 @@ /* - * The lower ZRAM_FLAG_SHIFT bits of table.flags is for - * object size (excluding header), the higher bits is for - * zram_pageflags. + * ZRAM is mainly used for memory efficiency so we want to keep memory + * footprint small and thus squeeze size and zram pageflags into a flags + * member. The lower ZRAM_FLAG_SHIFT bits is for object size (excluding + * header), which cannot be larger than PAGE_SIZE (requiring PAGE_SHIFT + * bits), the higher bits are for zram_pageflags. * - * zram is mainly used for memory efficiency so we want to keep memory - * footprint small so we can squeeze size and flags into a field. - * The lower ZRAM_FLAG_SHIFT bits is for object size (excluding header), - * the higher bits is for zram_pageflags. + * We use BUILD_BUG_ON() to make sure that zram pageflags don't overflow. */ -#define ZRAM_FLAG_SHIFT 24 +#define ZRAM_FLAG_SHIFT (PAGE_SHIFT + 1) /* Flags for zram pages (table[page_no].flags) */ enum zram_pageflags { |