diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-12-28 16:55:46 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-12-28 16:55:46 -0800 |
commit | f346b0becb1bc62e45495f9cdbae3eef35d0b635 (patch) | |
tree | ae79f3dfb8e031da51d38f0f095f89d7d23f3643 /drivers/block | |
parent | 00d59fde8532b2d42e80909d2e58678755e04da9 (diff) | |
parent | 0f4991e8fd48987ae476a92cdee6bfec4aff31b8 (diff) | |
download | linux-f346b0becb1bc62e45495f9cdbae3eef35d0b635.tar.bz2 |
Merge branch 'akpm' (patches from Andrew)
Merge misc updates from Andrew Morton:
- large KASAN update to use arm's "software tag-based mode"
- a few misc things
- sh updates
- ocfs2 updates
- just about all of MM
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (167 commits)
kernel/fork.c: mark 'stack_vm_area' with __maybe_unused
memcg, oom: notify on oom killer invocation from the charge path
mm, swap: fix swapoff with KSM pages
include/linux/gfp.h: fix typo
mm/hmm: fix memremap.h, move dev_page_fault_t callback to hmm
hugetlbfs: Use i_mmap_rwsem to fix page fault/truncate race
hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization
memory_hotplug: add missing newlines to debugging output
mm: remove __hugepage_set_anon_rmap()
include/linux/vmstat.h: remove unused page state adjustment macro
mm/page_alloc.c: allow error injection
mm: migrate: drop unused argument of migrate_page_move_mapping()
blkdev: avoid migration stalls for blkdev pages
mm: migrate: provide buffer_migrate_page_norefs()
mm: migrate: move migrate_page_lock_buffers()
mm: migrate: lock buffers before migrate_page_move_mapping()
mm: migration: factor out code to compute expected number of page references
mm, page_alloc: enable pcpu_drain with zone capability
kmemleak: add config to select auto scan
mm/page_alloc.c: don't call kasan_free_pages() at deferred mem init
...
Diffstat (limited to 'drivers/block')
-rw-r--r-- | drivers/block/zram/Kconfig | 5 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.c | 502 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.h | 19 |
3 files changed, 372 insertions, 154 deletions
diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index fcd055457364..1ffc64770643 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -15,7 +15,7 @@ config ZRAM See Documentation/blockdev/zram.txt for more information. config ZRAM_WRITEBACK - bool "Write back incompressible page to backing device" + bool "Write back incompressible or idle page to backing device" depends on ZRAM help With incompressible page, there is no memory saving to keep it @@ -23,6 +23,9 @@ config ZRAM_WRITEBACK For this feature, admin should set up backing device via /sys/block/zramX/backing_dev. + With /sys/block/zramX/{idle,writeback}, application could ask + idle page's writeback to the backing device to save in memory. + See Documentation/blockdev/zram.txt for more information. config ZRAM_MEMORY_TRACKING diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 4879595200e1..33c5cc879f24 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -52,15 +52,23 @@ static unsigned int num_devices = 1; static size_t huge_class_size; 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].value); + 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].value); + bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags); } static inline bool init_done(struct zram *zram) @@ -68,13 +76,6 @@ static inline bool init_done(struct zram *zram) return zram->disksize; } -static inline bool zram_allocated(struct zram *zram, u32 index) -{ - - return (zram->table[index].value >> (ZRAM_FLAG_SHIFT + 1)) || - zram->table[index].handle; -} - static inline struct zram *dev_to_zram(struct device *dev) { return (struct zram *)dev_to_disk(dev)->private_data; @@ -94,19 +95,19 @@ static void zram_set_handle(struct zram *zram, u32 index, unsigned long handle) static bool zram_test_flag(struct zram *zram, u32 index, enum zram_pageflags flag) { - return zram->table[index].value & BIT(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].value |= BIT(flag); + zram->table[index].flags |= BIT(flag); } static void zram_clear_flag(struct zram *zram, u32 index, enum zram_pageflags flag) { - zram->table[index].value &= ~BIT(flag); + zram->table[index].flags &= ~BIT(flag); } static inline void zram_set_element(struct zram *zram, u32 index, @@ -122,15 +123,22 @@ static unsigned long zram_get_element(struct zram *zram, u32 index) static size_t zram_get_obj_size(struct zram *zram, u32 index) { - return zram->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1); + 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].value >> ZRAM_FLAG_SHIFT; + unsigned long flags = zram->table[index].flags >> ZRAM_FLAG_SHIFT; - zram->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size; + 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 @@ -276,17 +284,90 @@ static ssize_t mem_used_max_store(struct device *dev, return len; } +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); + unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; + int index; + char mode_buf[8]; + ssize_t sz; + + sz = strscpy(mode_buf, buf, sizeof(mode_buf)); + if (sz <= 0) + return -EINVAL; + + /* ignore trailing new line */ + if (mode_buf[sz - 1] == '\n') + mode_buf[sz - 1] = 0x00; + + if (strcmp(mode_buf, "all")) + return -EINVAL; + + down_read(&zram->init_lock); + if (!init_done(zram)) { + up_read(&zram->init_lock); + return -EINVAL; + } + + 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)) + goto next; + zram_set_flag(zram, index, ZRAM_IDLE); +next: + zram_slot_unlock(zram, index); + } + + up_read(&zram->init_lock); + + return len; +} + #ifdef CONFIG_ZRAM_WRITEBACK -static bool zram_wb_enabled(struct zram *zram) +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); + atomic64_set(&zram->stats.bd_wb_limit, val); + if (val == 0) + zram->stop_writeback = false; + up_read(&zram->init_lock); + ret = len; + + return ret; +} + +static ssize_t writeback_limit_show(struct device *dev, + struct device_attribute *attr, char *buf) { - return zram->backing_dev; + u64 val; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + val = atomic64_read(&zram->stats.bd_wb_limit); + 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_wb_enabled(zram)) + if (!zram->backing_dev) return; bdev = zram->bdev; @@ -313,7 +394,7 @@ static ssize_t backing_dev_show(struct device *dev, ssize_t ret; down_read(&zram->init_lock); - if (!zram_wb_enabled(zram)) { + if (!zram->backing_dev) { memcpy(buf, "none\n", 5); up_read(&zram->init_lock); return 5; @@ -382,8 +463,10 @@ static ssize_t backing_dev_store(struct device *dev, bdev = bdgrab(I_BDEV(inode)); err = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram); - if (err < 0) + if (err < 0) { + bdev = NULL; goto out; + } nr_pages = i_size_read(inode) >> PAGE_SHIFT; bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long); @@ -399,7 +482,6 @@ static ssize_t backing_dev_store(struct device *dev, goto out; reset_bdev(zram); - spin_lock_init(&zram->bitmap_lock); zram->old_block_size = old_block_size; zram->bdev = bdev; @@ -441,32 +523,29 @@ out: return err; } -static unsigned long get_entry_bdev(struct zram *zram) +static unsigned long alloc_block_bdev(struct zram *zram) { - unsigned long entry; - - spin_lock(&zram->bitmap_lock); + unsigned long blk_idx = 1; +retry: /* 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); + blk_idx = find_next_zero_bit(zram->bitmap, zram->nr_pages, blk_idx); + if (blk_idx == zram->nr_pages) return 0; - } - set_bit(entry, zram->bitmap); - spin_unlock(&zram->bitmap_lock); + if (test_and_set_bit(blk_idx, zram->bitmap)) + goto retry; - return entry; + atomic64_inc(&zram->stats.bd_count); + return blk_idx; } -static void put_entry_bdev(struct zram *zram, unsigned long entry) +static void free_block_bdev(struct zram *zram, unsigned long blk_idx) { int was_set; - spin_lock(&zram->bitmap_lock); - was_set = test_and_clear_bit(entry, zram->bitmap); - spin_unlock(&zram->bitmap_lock); + 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) @@ -509,6 +588,169 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, return 1; } +#define HUGE_WRITEBACK 0x1 +#define IDLE_WRITEBACK 0x2 + +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; + struct bio bio; + struct bio_vec bio_vec; + struct page *page; + ssize_t ret, sz; + char mode_buf[8]; + unsigned long mode = -1UL; + unsigned long blk_idx = 0; + + sz = strscpy(mode_buf, buf, sizeof(mode_buf)); + if (sz <= 0) + return -EINVAL; + + /* ignore trailing newline */ + if (mode_buf[sz - 1] == '\n') + mode_buf[sz - 1] = 0x00; + + if (!strcmp(mode_buf, "idle")) + mode = IDLE_WRITEBACK; + else if (!strcmp(mode_buf, "huge")) + mode = HUGE_WRITEBACK; + + if (mode == -1UL) + return -EINVAL; + + 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 (index = 0; index < nr_pages; index++) { + struct bio_vec bvec; + + bvec.bv_page = page; + bvec.bv_len = PAGE_SIZE; + bvec.bv_offset = 0; + + if (zram->stop_writeback) { + ret = -EIO; + break; + } + + 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)) && + (mode & HUGE_WRITEBACK && + !zram_test_flag(zram, index, ZRAM_HUGE))) + 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, &bio_vec, 1); + bio_set_dev(&bio, zram->bdev); + 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); + /* + * XXX: A single page IO would be inefficient for write + * but it would be not bad as starter. + */ + ret = submit_bio_wait(&bio); + if (ret) { + 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; + } + + 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); + if (atomic64_add_unless(&zram->stats.bd_wb_limit, + -1 << (PAGE_SHIFT - 12), 0)) { + if (atomic64_read(&zram->stats.bd_wb_limit) == 0) + zram->stop_writeback = true; + } +next: + zram_slot_unlock(zram, index); + } + + if (blk_idx) + free_block_bdev(zram, blk_idx); + ret = len; + __free_page(page); +release_init_lock: + up_read(&zram->init_lock); + + return ret; +} + struct zram_work { struct work_struct work; struct zram *zram; @@ -561,79 +803,21 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, 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); } - -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) {} + +static void free_block_bdev(struct zram *zram, unsigned long blk_idx) {}; #endif #ifdef CONFIG_ZRAM_MEMORY_TRACKING @@ -652,14 +836,10 @@ static void zram_debugfs_destroy(void) 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 void zram_reset_access(struct zram *zram, u32 index) -{ - zram->table[index].ac_time = 0; -} - static ssize_t read_block_state(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -689,12 +869,13 @@ static ssize_t read_block_state(struct file *file, char __user *buf, ts = ktime_to_timespec64(zram->table[index].ac_time); copied = snprintf(kbuf + written, count, - "%12zd %12lld.%06lu %c%c%c\n", + "%12zd %12lld.%06lu %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_HUGE) ? 'h' : '.', + zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.'); if (count < copied) { zram_slot_unlock(zram, index); @@ -739,8 +920,10 @@ static void zram_debugfs_unregister(struct zram *zram) #else static void zram_debugfs_create(void) {}; static void zram_debugfs_destroy(void) {}; -static void zram_accessed(struct zram *zram, u32 index) {}; -static void zram_reset_access(struct zram *zram, u32 index) {}; +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 @@ -877,6 +1060,26 @@ static ssize_t mm_stat_show(struct device *dev, 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) { @@ -886,9 +1089,10 @@ static ssize_t debug_stat_show(struct device *dev, down_read(&zram->init_lock); ret = scnprintf(buf, PAGE_SIZE, - "version: %d\n%8llu\n", + "version: %d\n%8llu %8llu\n", version, - (u64)atomic64_read(&zram->stats.writestall)); + (u64)atomic64_read(&zram->stats.writestall), + (u64)atomic64_read(&zram->stats.miss_free)); up_read(&zram->init_lock); return ret; @@ -896,6 +1100,9 @@ static ssize_t debug_stat_show(struct device *dev, 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) @@ -940,17 +1147,21 @@ static void zram_free_page(struct zram *zram, size_t index) { unsigned long handle; - zram_reset_access(zram, index); +#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_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) { - zram_wb_clear(zram, index); - atomic64_dec(&zram->stats.pages_stored); - return; + 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; } /* @@ -959,10 +1170,8 @@ static void zram_free_page(struct zram *zram, size_t index) */ 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; + goto out; } handle = zram_get_handle(zram, index); @@ -973,10 +1182,12 @@ static void zram_free_page(struct zram *zram, size_t index) 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)); } static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, @@ -987,24 +1198,20 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, 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); + zram_slot_lock(zram, index); + if (zram_test_flag(zram, index, ZRAM_WB)) { + struct bio_vec bvec; - 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); + + 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_lock(zram, index); handle = zram_get_handle(zram, index); if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) { unsigned long value; @@ -1089,7 +1296,6 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, 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)) { @@ -1114,21 +1320,8 @@ compress_again: return ret; } - if (unlikely(comp_len >= huge_class_size)) { + if (comp_len >= huge_class_size) comp_len = PAGE_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; - } - } - /* * handle allocation has 2 paths: * a) fast path is executed with preemption disabled (for @@ -1400,10 +1593,14 @@ static void zram_slot_free_notify(struct block_device *bdev, zram = bdev->bd_disk->private_data; - zram_slot_lock(zram, index); + 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); - atomic64_inc(&zram->stats.notify_free); } static int zram_rw_page(struct block_device *bdev, sector_t sector, @@ -1608,10 +1805,13 @@ 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); #endif static struct attribute *zram_disk_attrs[] = { @@ -1621,13 +1821,19 @@ static struct attribute *zram_disk_attrs[] = { &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, #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, NULL, }; diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 72c8584b6dff..4bd3afd15e83 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -30,7 +30,7 @@ /* - * The lower ZRAM_FLAG_SHIFT bits of table.value is for + * The lower ZRAM_FLAG_SHIFT bits of table.flags is for * object size (excluding header), the higher bits is for * zram_pageflags. * @@ -41,13 +41,15 @@ */ #define ZRAM_FLAG_SHIFT 24 -/* Flags for zram pages (table[page_no].value) */ +/* Flags for zram pages (table[page_no].flags) */ enum zram_pageflags { /* zram slot is locked */ ZRAM_LOCK = ZRAM_FLAG_SHIFT, ZRAM_SAME, /* Page consists the same element */ ZRAM_WB, /* page is stored on backing_device */ + ZRAM_UNDER_WB, /* page is under writeback */ ZRAM_HUGE, /* Incompressible page */ + ZRAM_IDLE, /* not accessed page since last idle marking */ __NR_ZRAM_PAGEFLAGS, }; @@ -60,7 +62,7 @@ struct zram_table_entry { unsigned long handle; unsigned long element; }; - unsigned long value; + unsigned long flags; #ifdef CONFIG_ZRAM_MEMORY_TRACKING ktime_t ac_time; #endif @@ -79,6 +81,13 @@ struct zram_stats { atomic64_t pages_stored; /* no. of pages currently stored */ atomic_long_t max_used_pages; /* no. of maximum pages stored */ atomic64_t writestall; /* no. of write slow paths */ + atomic64_t miss_free; /* no. of missed free */ +#ifdef CONFIG_ZRAM_WRITEBACK + atomic64_t bd_count; /* no. of pages in backing device */ + atomic64_t bd_reads; /* no. of reads from backing device */ + atomic64_t bd_writes; /* no. of writes from backing device */ + atomic64_t bd_wb_limit; /* writeback limit of backing device */ +#endif }; struct zram { @@ -104,13 +113,13 @@ struct zram { * zram is claimed so open request will be failed */ bool claim; /* Protected by bdev->bd_mutex */ -#ifdef CONFIG_ZRAM_WRITEBACK struct file *backing_dev; + bool stop_writeback; +#ifdef CONFIG_ZRAM_WRITEBACK struct block_device *bdev; unsigned int old_block_size; unsigned long *bitmap; unsigned long nr_pages; - spinlock_t bitmap_lock; #endif #ifdef CONFIG_ZRAM_MEMORY_TRACKING struct dentry *debugfs_dir; |