diff options
Diffstat (limited to 'drivers/block/zram/zram_drv.c')
-rw-r--r-- | drivers/block/zram/zram_drv.c | 1386 |
1 files changed, 935 insertions, 451 deletions
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 6772e0c654fa..54c57103715f 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -33,6 +33,7 @@ #include <linux/debugfs.h> #include <linux/cpuhotplug.h> #include <linux/part_stat.h> +#include <linux/kernel_read_file.h> #include "zram_drv.h" @@ -43,6 +44,8 @@ static DEFINE_MUTEX(zram_index_mutex); static int zram_major; static const char *default_compressor = CONFIG_ZRAM_DEF_COMP; +#define ZRAM_MAX_ALGO_NAME_SZ 128 + /* Module params (documentation at end) */ static unsigned int num_devices = 1; /* @@ -54,22 +57,59 @@ 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_read_page(struct zram *zram, struct page *page, u32 index, - struct bio *parent); +static int zram_read_from_zspool(struct zram *zram, struct page *page, + u32 index); + +#define slot_dep_map(zram, index) (&(zram)->table[(index)].dep_map) + +static void zram_slot_lock_init(struct zram *zram, u32 index) +{ + static struct lock_class_key __key; + + lockdep_init_map(slot_dep_map(zram, index), "zram->table[index].lock", + &__key, 0); +} -static int zram_slot_trylock(struct zram *zram, u32 index) +/* + * entry locking rules: + * + * 1) Lock is exclusive + * + * 2) lock() function can sleep waiting for the lock + * + * 3) Lock owner can sleep + * + * 4) Use TRY lock variant when in atomic context + * - must check return value and handle locking failers + */ +static __must_check bool zram_slot_trylock(struct zram *zram, u32 index) { - return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].flags); + unsigned long *lock = &zram->table[index].flags; + + if (!test_and_set_bit_lock(ZRAM_ENTRY_LOCK, lock)) { + mutex_acquire(slot_dep_map(zram, index), 0, 1, _RET_IP_); + lock_acquired(slot_dep_map(zram, index), _RET_IP_); + return true; + } + + return false; } static void zram_slot_lock(struct zram *zram, u32 index) { - bit_spin_lock(ZRAM_LOCK, &zram->table[index].flags); + unsigned long *lock = &zram->table[index].flags; + + mutex_acquire(slot_dep_map(zram, index), 0, 0, _RET_IP_); + wait_on_bit_lock(lock, ZRAM_ENTRY_LOCK, TASK_UNINTERRUPTIBLE); + lock_acquired(slot_dep_map(zram, index), _RET_IP_); } static void zram_slot_unlock(struct zram *zram, u32 index) { - bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags); + unsigned long *lock = &zram->table[index].flags; + + mutex_release(slot_dep_map(zram, index), _RET_IP_); + clear_and_wake_up_bit(ZRAM_ENTRY_LOCK, lock); } static inline bool init_done(struct zram *zram) @@ -92,7 +132,6 @@ 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) { @@ -111,17 +150,6 @@ static void zram_clear_flag(struct zram *zram, u32 index, 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); @@ -142,6 +170,27 @@ static inline bool zram_allocated(struct zram *zram, u32 index) zram_test_flag(zram, index, ZRAM_WB); } +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 bool zram_can_store_page(struct zram *zram) +{ + unsigned long alloced_pages; + + alloced_pages = zs_get_total_pages(zram->mem_pool); + update_used_max(zram, alloced_pages); + + return !zram->limit_pages || alloced_pages <= zram->limit_pages; +} + #if PAGE_SIZE != 4096 static inline bool is_partial_io(struct bio_vec *bvec) { @@ -177,22 +226,113 @@ static inline u32 zram_get_priority(struct zram *zram, u32 index) static void zram_accessed(struct zram *zram, u32 index) { zram_clear_flag(zram, index, ZRAM_IDLE); + zram_clear_flag(zram, index, ZRAM_PP_SLOT); #ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME zram->table[index].ac_time = ktime_get_boottime(); #endif } -static inline void update_used_max(struct zram *zram, - const unsigned long pages) +#if defined CONFIG_ZRAM_WRITEBACK || defined CONFIG_ZRAM_MULTI_COMP +struct zram_pp_slot { + unsigned long index; + struct list_head entry; +}; + +/* + * A post-processing bucket is, essentially, a size class, this defines + * the range (in bytes) of pp-slots sizes in particular bucket. + */ +#define PP_BUCKET_SIZE_RANGE 64 +#define NUM_PP_BUCKETS ((PAGE_SIZE / PP_BUCKET_SIZE_RANGE) + 1) + +struct zram_pp_ctl { + struct list_head pp_buckets[NUM_PP_BUCKETS]; +}; + +static struct zram_pp_ctl *init_pp_ctl(void) { - unsigned long cur_max = atomic_long_read(&zram->stats.max_used_pages); + struct zram_pp_ctl *ctl; + u32 idx; - do { - if (cur_max >= pages) - return; - } while (!atomic_long_try_cmpxchg(&zram->stats.max_used_pages, - &cur_max, pages)); + ctl = kmalloc(sizeof(*ctl), GFP_KERNEL); + if (!ctl) + return NULL; + + for (idx = 0; idx < NUM_PP_BUCKETS; idx++) + INIT_LIST_HEAD(&ctl->pp_buckets[idx]); + return ctl; +} + +static void release_pp_slot(struct zram *zram, struct zram_pp_slot *pps) +{ + list_del_init(&pps->entry); + + zram_slot_lock(zram, pps->index); + zram_clear_flag(zram, pps->index, ZRAM_PP_SLOT); + zram_slot_unlock(zram, pps->index); + + kfree(pps); +} + +static void release_pp_ctl(struct zram *zram, struct zram_pp_ctl *ctl) +{ + u32 idx; + + if (!ctl) + return; + + for (idx = 0; idx < NUM_PP_BUCKETS; idx++) { + while (!list_empty(&ctl->pp_buckets[idx])) { + struct zram_pp_slot *pps; + + pps = list_first_entry(&ctl->pp_buckets[idx], + struct zram_pp_slot, + entry); + release_pp_slot(zram, pps); + } + } + + kfree(ctl); +} + +static bool place_pp_slot(struct zram *zram, struct zram_pp_ctl *ctl, + u32 index) +{ + struct zram_pp_slot *pps; + u32 bid; + + pps = kmalloc(sizeof(*pps), GFP_NOIO | __GFP_NOWARN); + if (!pps) + return false; + + INIT_LIST_HEAD(&pps->entry); + pps->index = index; + + bid = zram_get_obj_size(zram, pps->index) / PP_BUCKET_SIZE_RANGE; + list_add(&pps->entry, &ctl->pp_buckets[bid]); + + zram_set_flag(zram, pps->index, ZRAM_PP_SLOT); + return true; +} + +static struct zram_pp_slot *select_pp_slot(struct zram_pp_ctl *ctl) +{ + struct zram_pp_slot *pps = NULL; + s32 idx = NUM_PP_BUCKETS - 1; + + /* The higher the bucket id the more optimal slot post-processing is */ + while (idx >= 0) { + pps = list_first_entry_or_null(&ctl->pp_buckets[idx], + struct zram_pp_slot, + entry); + if (pps) + break; + + idx--; + } + return pps; } +#endif static inline void zram_fill_page(void *ptr, unsigned long len, unsigned long value) @@ -295,19 +435,28 @@ static void mark_idle(struct zram *zram, ktime_t cutoff) 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. + * Do not mark ZRAM_SAME slots as ZRAM_IDLE, because no + * post-processing (recompress, writeback) happens to the + * ZRAM_SAME slot. + * + * And ZRAM_WB slots simply cannot be ZRAM_IDLE. */ zram_slot_lock(zram, index); - if (zram_allocated(zram, index) && - !zram_test_flag(zram, index, ZRAM_UNDER_WB)) { + if (!zram_allocated(zram, index) || + zram_test_flag(zram, index, ZRAM_WB) || + zram_test_flag(zram, index, ZRAM_SAME)) { + zram_slot_unlock(zram, index); + continue; + } + #ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME - is_idle = !cutoff || ktime_after(cutoff, - zram->table[index].ac_time); + is_idle = !cutoff || + ktime_after(cutoff, zram->table[index].ac_time); #endif - if (is_idle) - zram_set_flag(zram, index, ZRAM_IDLE); - } + if (is_idle) + zram_set_flag(zram, index, ZRAM_IDLE); + else + zram_clear_flag(zram, index, ZRAM_IDLE); zram_slot_unlock(zram, index); } } @@ -426,11 +575,10 @@ static void reset_bdev(struct zram *zram) if (!zram->backing_dev) return; - bdev_release(zram->bdev_handle); /* hope filp_close flush all of IO */ filp_close(zram->backing_dev, NULL); zram->backing_dev = NULL; - zram->bdev_handle = NULL; + zram->bdev = NULL; zram->disk->fops = &zram_devops; kvfree(zram->bitmap); zram->bitmap = NULL; @@ -473,10 +621,8 @@ static ssize_t backing_dev_store(struct device *dev, 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 bdev_handle *bdev_handle = NULL; int err; struct zram *zram = dev_to_zram(dev); @@ -497,15 +643,14 @@ static ssize_t backing_dev_store(struct device *dev, if (sz > 0 && file_name[sz - 1] == '\n') file_name[sz - 1] = 0x00; - backing_dev = filp_open(file_name, O_RDWR|O_LARGEFILE, 0); + backing_dev = filp_open(file_name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(backing_dev)) { err = PTR_ERR(backing_dev); backing_dev = NULL; goto out; } - mapping = backing_dev->f_mapping; - inode = mapping->host; + inode = backing_dev->f_mapping->host; /* Support only block device in this moment */ if (!S_ISBLK(inode->i_mode)) { @@ -513,15 +658,13 @@ static ssize_t backing_dev_store(struct device *dev, goto out; } - bdev_handle = bdev_open_by_dev(inode->i_rdev, - BLK_OPEN_READ | BLK_OPEN_WRITE, zram, NULL); - if (IS_ERR(bdev_handle)) { - err = PTR_ERR(bdev_handle); - bdev_handle = NULL; + nr_pages = i_size_read(inode) >> PAGE_SHIFT; + /* Refuse to use zero sized device (also prevents self reference) */ + if (!nr_pages) { + err = -EINVAL; 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) { @@ -531,7 +674,7 @@ static ssize_t backing_dev_store(struct device *dev, reset_bdev(zram); - zram->bdev_handle = bdev_handle; + zram->bdev = I_BDEV(inode); zram->backing_dev = backing_dev; zram->bitmap = bitmap; zram->nr_pages = nr_pages; @@ -544,9 +687,6 @@ static ssize_t backing_dev_store(struct device *dev, out: kvfree(bitmap); - if (bdev_handle) - bdev_release(bdev_handle); - if (backing_dev) filp_close(backing_dev, NULL); @@ -587,71 +727,28 @@ static void read_from_bdev_async(struct zram *zram, struct page *page, { struct bio *bio; - bio = bio_alloc(zram->bdev_handle->bdev, 1, parent->bi_opf, GFP_NOIO); + bio = bio_alloc(zram->bdev, 1, parent->bi_opf, GFP_NOIO); bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); __bio_add_page(bio, page, PAGE_SIZE, 0); bio_chain(bio, parent); submit_bio(bio); } -#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) +static int zram_writeback_slots(struct zram *zram, struct zram_pp_ctl *ctl) { - 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; - } + struct page *page = NULL; + struct zram_pp_slot *pps; + struct bio_vec bio_vec; + struct bio bio; + int ret = 0, err; + u32 index; page = alloc_page(GFP_KERNEL); - if (!page) { - ret = -ENOMEM; - goto release_init_lock; - } + if (!page) + return -ENOMEM; - for (; nr_pages != 0; index++, nr_pages--) { + while ((pps = select_pp_slot(ctl))) { spin_lock(&zram->wb_limit_lock); if (zram->wb_limit_enable && !zram->bd_wb_limit) { spin_unlock(&zram->wb_limit_lock); @@ -668,42 +765,21 @@ static ssize_t writeback_store(struct device *dev, } } + index = pps->index; 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. + * scan_slots() sets ZRAM_PP_SLOT and relases slot lock, so + * slots can change in the meantime. If slots are accessed or + * freed they lose ZRAM_PP_SLOT flag and hence we don't + * post-process them. */ - zram_set_flag(zram, index, ZRAM_UNDER_WB); - /* Need for hugepage writeback racing */ - zram_set_flag(zram, index, ZRAM_IDLE); + if (!zram_test_flag(zram, index, ZRAM_PP_SLOT)) + goto next; + if (zram_read_from_zspool(zram, page, index)) + goto next; zram_slot_unlock(zram, index); - if (zram_read_page(zram, page, index, 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_handle->bdev, &bio_vec, 1, + 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, page, PAGE_SIZE, 0); @@ -714,10 +790,7 @@ static ssize_t writeback_store(struct device *dev, */ 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); + release_pp_slot(zram, pps); /* * BIO errors are not fatal, we continue and simply * attempt to writeback the remaining objects (pages). @@ -731,27 +804,21 @@ static ssize_t writeback_store(struct device *dev, } atomic64_inc(&zram->stats.bd_writes); + zram_slot_lock(zram, index); /* - * 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. + * Same as above, we release slot lock during writeback so + * slot can change under us: slot_free() or slot_free() and + * reallocation (zram_write_page()). In both cases slot loses + * ZRAM_PP_SLOT flag. No concurrent post-processing can set + * ZRAM_PP_SLOT on such slots until current post-processing + * finishes. */ - 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); + if (!zram_test_flag(zram, index, ZRAM_PP_SLOT)) 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); + zram_set_handle(zram, index, blk_idx); blk_idx = 0; atomic64_inc(&zram->stats.pages_stored); spin_lock(&zram->wb_limit_lock); @@ -760,12 +827,224 @@ static ssize_t writeback_store(struct device *dev, spin_unlock(&zram->wb_limit_lock); next: zram_slot_unlock(zram, index); + release_pp_slot(zram, pps); + + cond_resched(); } if (blk_idx) free_block_bdev(zram, blk_idx); - __free_page(page); + if (page) + __free_page(page); + + return ret; +} + +#define PAGE_WRITEBACK 0 +#define HUGE_WRITEBACK (1 << 0) +#define IDLE_WRITEBACK (1 << 1) +#define INCOMPRESSIBLE_WRITEBACK (1 << 2) + +static int parse_page_index(char *val, unsigned long nr_pages, + unsigned long *lo, unsigned long *hi) +{ + int ret; + + ret = kstrtoul(val, 10, lo); + if (ret) + return ret; + if (*lo >= nr_pages) + return -ERANGE; + *hi = *lo + 1; + return 0; +} + +static int parse_page_indexes(char *val, unsigned long nr_pages, + unsigned long *lo, unsigned long *hi) +{ + char *delim; + int ret; + + delim = strchr(val, '-'); + if (!delim) + return -EINVAL; + + *delim = 0x00; + ret = kstrtoul(val, 10, lo); + if (ret) + return ret; + if (*lo >= nr_pages) + return -ERANGE; + + ret = kstrtoul(delim + 1, 10, hi); + if (ret) + return ret; + if (*hi >= nr_pages || *lo > *hi) + return -ERANGE; + *hi += 1; + return 0; +} + +static int parse_mode(char *val, u32 *mode) +{ + *mode = 0; + + if (!strcmp(val, "idle")) + *mode = IDLE_WRITEBACK; + if (!strcmp(val, "huge")) + *mode = HUGE_WRITEBACK; + if (!strcmp(val, "huge_idle")) + *mode = IDLE_WRITEBACK | HUGE_WRITEBACK; + if (!strcmp(val, "incompressible")) + *mode = INCOMPRESSIBLE_WRITEBACK; + + if (*mode == 0) + return -EINVAL; + return 0; +} + +static int scan_slots_for_writeback(struct zram *zram, u32 mode, + unsigned long lo, unsigned long hi, + struct zram_pp_ctl *ctl) +{ + u32 index = lo; + + while (index < hi) { + bool ok = true; + + 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)) + 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; + + ok = place_pp_slot(zram, ctl, index); +next: + zram_slot_unlock(zram, index); + if (!ok) + break; + index++; + } + + return 0; +} + +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); + u64 nr_pages = zram->disksize >> PAGE_SHIFT; + unsigned long lo = 0, hi = nr_pages; + struct zram_pp_ctl *ctl = NULL; + char *args, *param, *val; + ssize_t ret = len; + int err, mode = 0; + + down_read(&zram->init_lock); + if (!init_done(zram)) { + up_read(&zram->init_lock); + return -EINVAL; + } + + /* Do not permit concurrent post-processing actions. */ + if (atomic_xchg(&zram->pp_in_progress, 1)) { + up_read(&zram->init_lock); + return -EAGAIN; + } + + if (!zram->backing_dev) { + ret = -ENODEV; + goto release_init_lock; + } + + ctl = init_pp_ctl(); + if (!ctl) { + ret = -ENOMEM; + goto release_init_lock; + } + + args = skip_spaces(buf); + while (*args) { + args = next_arg(args, ¶m, &val); + + /* + * Workaround to support the old writeback interface. + * + * The old writeback interface has a minor inconsistency and + * requires key=value only for page_index parameter, while the + * writeback mode is a valueless parameter. + * + * This is not the case anymore and now all parameters are + * required to have values, however, we need to support the + * legacy writeback interface format so we check if we can + * recognize a valueless parameter as the (legacy) writeback + * mode. + */ + if (!val || !*val) { + err = parse_mode(param, &mode); + if (err) { + ret = err; + goto release_init_lock; + } + + scan_slots_for_writeback(zram, mode, lo, hi, ctl); + break; + } + + if (!strcmp(param, "type")) { + err = parse_mode(val, &mode); + if (err) { + ret = err; + goto release_init_lock; + } + + scan_slots_for_writeback(zram, mode, lo, hi, ctl); + break; + } + + if (!strcmp(param, "page_index")) { + err = parse_page_index(val, nr_pages, &lo, &hi); + if (err) { + ret = err; + goto release_init_lock; + } + + scan_slots_for_writeback(zram, mode, lo, hi, ctl); + continue; + } + + if (!strcmp(param, "page_indexes")) { + err = parse_page_indexes(val, nr_pages, &lo, &hi); + if (err) { + ret = err; + goto release_init_lock; + } + + scan_slots_for_writeback(zram, mode, lo, hi, ctl); + continue; + } + } + + err = zram_writeback_slots(zram, ctl); + if (err) + ret = err; + release_init_lock: + release_pp_ctl(zram, ctl); + atomic_set(&zram->pp_in_progress, 0); up_read(&zram->init_lock); return ret; @@ -785,7 +1064,7 @@ static void zram_sync_read(struct work_struct *work) struct bio_vec bv; struct bio bio; - bio_init(&bio, zw->zram->bdev_handle->bdev, &bv, 1, REQ_OP_READ); + bio_init(&bio, zw->zram->bdev, &bv, 1, REQ_OP_READ); bio.bi_iter.bi_sector = zw->entry * (PAGE_SIZE >> 9); __bio_add_page(&bio, zw->page, PAGE_SIZE, 0); zw->error = submit_bio_wait(&bio); @@ -937,27 +1216,6 @@ 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 */ @@ -984,7 +1242,7 @@ static int __comp_algorithm_store(struct zram *zram, u32 prio, const char *buf) size_t sz; sz = strlen(buf); - if (sz >= CRYPTO_MAX_ALG_NAME) + if (sz >= ZRAM_MAX_ALGO_NAME_SZ) return -E2BIG; compressor = kstrdup(buf, GFP_KERNEL); @@ -1013,6 +1271,116 @@ static int __comp_algorithm_store(struct zram *zram, u32 prio, const char *buf) return 0; } +static void comp_params_reset(struct zram *zram, u32 prio) +{ + struct zcomp_params *params = &zram->params[prio]; + + vfree(params->dict); + params->level = ZCOMP_PARAM_NOT_SET; + params->deflate.winbits = ZCOMP_PARAM_NOT_SET; + params->dict_sz = 0; + params->dict = NULL; +} + +static int comp_params_store(struct zram *zram, u32 prio, s32 level, + const char *dict_path, + struct deflate_params *deflate_params) +{ + ssize_t sz = 0; + + comp_params_reset(zram, prio); + + if (dict_path) { + sz = kernel_read_file_from_path(dict_path, 0, + &zram->params[prio].dict, + INT_MAX, + NULL, + READING_POLICY); + if (sz < 0) + return -EINVAL; + } + + zram->params[prio].dict_sz = sz; + zram->params[prio].level = level; + zram->params[prio].deflate.winbits = deflate_params->winbits; + return 0; +} + +static ssize_t algorithm_params_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t len) +{ + s32 prio = ZRAM_PRIMARY_COMP, level = ZCOMP_PARAM_NOT_SET; + char *args, *param, *val, *algo = NULL, *dict_path = NULL; + struct deflate_params deflate_params; + struct zram *zram = dev_to_zram(dev); + int ret; + + deflate_params.winbits = ZCOMP_PARAM_NOT_SET; + + args = skip_spaces(buf); + while (*args) { + args = next_arg(args, ¶m, &val); + + if (!val || !*val) + return -EINVAL; + + if (!strcmp(param, "priority")) { + ret = kstrtoint(val, 10, &prio); + if (ret) + return ret; + continue; + } + + if (!strcmp(param, "level")) { + ret = kstrtoint(val, 10, &level); + if (ret) + return ret; + continue; + } + + if (!strcmp(param, "algo")) { + algo = val; + continue; + } + + if (!strcmp(param, "dict")) { + dict_path = val; + continue; + } + + if (!strcmp(param, "deflate.winbits")) { + ret = kstrtoint(val, 10, &deflate_params.winbits); + if (ret) + return ret; + continue; + } + } + + /* Lookup priority by algorithm name */ + if (algo) { + s32 p; + + prio = -EINVAL; + for (p = ZRAM_PRIMARY_COMP; p < ZRAM_MAX_COMPS; p++) { + if (!zram->comp_algs[p]) + continue; + + if (!strcmp(zram->comp_algs[p], algo)) { + prio = p; + break; + } + } + } + + if (prio < ZRAM_PRIMARY_COMP || prio >= ZRAM_MAX_COMPS) + return -EINVAL; + + ret = comp_params_store(zram, prio, level, dict_path, &deflate_params); + return ret ? ret : len; +} + static ssize_t comp_algorithm_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -1195,9 +1563,8 @@ static ssize_t debug_stat_show(struct device *dev, down_read(&zram->init_lock); ret = scnprintf(buf, PAGE_SIZE, - "version: %d\n%8llu %8llu\n", + "version: %d\n0 %8llu\n", version, - (u64)atomic64_read(&zram->stats.writestall), (u64)atomic64_read(&zram->stats.miss_free)); up_read(&zram->init_lock); @@ -1216,17 +1583,21 @@ static void zram_meta_free(struct zram *zram, u64 disksize) size_t num_pages = disksize >> PAGE_SHIFT; size_t index; + if (!zram->table) + return; + /* 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); + zram->table = NULL; } static bool zram_meta_alloc(struct zram *zram, u64 disksize) { - size_t num_pages; + size_t num_pages, index; num_pages = disksize >> PAGE_SHIFT; zram->table = vzalloc(array_size(num_pages, sizeof(*zram->table))); @@ -1236,19 +1607,19 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) zram->mem_pool = zs_create_pool(zram->disk->disk_name); if (!zram->mem_pool) { vfree(zram->table); + zram->table = NULL; return false; } if (!huge_class_size) huge_class_size = zs_huge_class_size(zram->mem_pool); + + for (index = 0; index < num_pages; index++) + zram_slot_lock_init(zram, index); + 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; @@ -1256,22 +1627,20 @@ static void zram_free_page(struct zram *zram, size_t index) #ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME zram->table[index].ac_time = 0; #endif - if (zram_test_flag(zram, index, ZRAM_IDLE)) - zram_clear_flag(zram, index, ZRAM_IDLE); + + zram_clear_flag(zram, index, ZRAM_IDLE); + zram_clear_flag(zram, index, ZRAM_INCOMPRESSIBLE); + zram_clear_flag(zram, index, ZRAM_PP_SLOT); + zram_set_priority(zram, index, 0); 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)); + free_block_bdev(zram, zram_get_handle(zram, index)); goto out; } @@ -1292,64 +1661,80 @@ static void zram_free_page(struct zram *zram, size_t index) zs_free(zram->mem_pool, handle); atomic64_sub(zram_get_obj_size(zram, index), - &zram->stats.compr_data_size); + &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 (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, +static int read_same_filled_page(struct zram *zram, struct page *page, u32 index) { + void *mem; + + mem = kmap_local_page(page); + zram_fill_page(mem, PAGE_SIZE, zram_get_handle(zram, index)); + kunmap_local(mem); + return 0; +} + +static int read_incompressible_page(struct zram *zram, struct page *page, + u32 index) +{ + unsigned long handle; + void *src, *dst; + + handle = zram_get_handle(zram, index); + src = zs_obj_read_begin(zram->mem_pool, handle, NULL); + dst = kmap_local_page(page); + copy_page(dst, src); + kunmap_local(dst); + zs_obj_read_end(zram->mem_pool, handle, src); + + return 0; +} + +static int read_compressed_page(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; + int ret, prio; 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_local_page(page); - zram_fill_page(mem, PAGE_SIZE, value); - kunmap_local(mem); - return 0; - } - size = zram_get_obj_size(zram, index); + prio = zram_get_priority(zram, index); - if (size != PAGE_SIZE) { - prio = zram_get_priority(zram, index); - zstrm = zcomp_stream_get(zram->comps[prio]); - } + zstrm = zcomp_stream_get(zram->comps[prio]); + src = zs_obj_read_begin(zram->mem_pool, handle, zstrm->local_copy); + dst = kmap_local_page(page); + ret = zcomp_decompress(zram->comps[prio], zstrm, src, size, dst); + kunmap_local(dst); + zs_obj_read_end(zram->mem_pool, handle, src); + zcomp_stream_put(zstrm); - src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); - if (size == PAGE_SIZE) { - dst = kmap_local_page(page); - memcpy(dst, src, PAGE_SIZE); - kunmap_local(dst); - ret = 0; - } else { - dst = kmap_local_page(page); - ret = zcomp_decompress(zstrm, src, size, dst); - kunmap_local(dst); - zcomp_stream_put(zram->comps[prio]); - } - zs_unmap_object(zram->mem_pool, handle); return ret; } +/* + * 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) +{ + if (zram_test_flag(zram, index, ZRAM_SAME) || + !zram_get_handle(zram, index)) + return read_same_filled_page(zram, page, index); + + if (!zram_test_flag(zram, index, ZRAM_HUGE)) + return read_compressed_page(zram, page, index); + else + return read_incompressible_page(zram, page, index); +} + static int zram_read_page(struct zram *zram, struct page *page, u32 index, struct bio *parent) { @@ -1367,7 +1752,7 @@ static int zram_read_page(struct zram *zram, struct page *page, u32 index, */ zram_slot_unlock(zram, index); - ret = read_from_bdev(zram, page, zram_get_element(zram, index), + ret = read_from_bdev(zram, page, zram_get_handle(zram, index), parent); } @@ -1405,128 +1790,124 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, return zram_read_page(zram, bvec->bv_page, index, bio); } +static int write_same_filled_page(struct zram *zram, unsigned long fill, + u32 index) +{ + zram_slot_lock(zram, index); + zram_set_flag(zram, index, ZRAM_SAME); + zram_set_handle(zram, index, fill); + zram_slot_unlock(zram, index); + + atomic64_inc(&zram->stats.same_pages); + atomic64_inc(&zram->stats.pages_stored); + + return 0; +} + +static int write_incompressible_page(struct zram *zram, struct page *page, + u32 index) +{ + unsigned long handle; + void *src; + + /* + * This function is called from preemptible context so we don't need + * to do optimistic and fallback to pessimistic handle allocation, + * like we do for compressible pages. + */ + handle = zs_malloc(zram->mem_pool, PAGE_SIZE, + GFP_NOIO | __GFP_NOWARN | + __GFP_HIGHMEM | __GFP_MOVABLE, page_to_nid(page)); + if (IS_ERR_VALUE(handle)) + return PTR_ERR((void *)handle); + + if (!zram_can_store_page(zram)) { + zs_free(zram->mem_pool, handle); + return -ENOMEM; + } + + src = kmap_local_page(page); + zs_obj_write(zram->mem_pool, handle, src, PAGE_SIZE); + kunmap_local(src); + + zram_slot_lock(zram, index); + zram_set_flag(zram, index, ZRAM_HUGE); + zram_set_handle(zram, index, handle); + zram_set_obj_size(zram, index, PAGE_SIZE); + zram_slot_unlock(zram, index); + + atomic64_add(PAGE_SIZE, &zram->stats.compr_data_size); + atomic64_inc(&zram->stats.huge_pages); + atomic64_inc(&zram->stats.huge_pages_since); + atomic64_inc(&zram->stats.pages_stored); + + return 0; +} + static int zram_write_page(struct zram *zram, struct page *page, u32 index) { int ret = 0; - unsigned long alloced_pages; - unsigned long handle = -ENOMEM; - unsigned int comp_len = 0; - void *src, *dst, *mem; + unsigned long handle; + unsigned int comp_len; + void *mem; struct zcomp_strm *zstrm; - unsigned long element = 0; - enum zram_pageflags flags = 0; + unsigned long element; + bool same_filled; + + /* First, free memory allocated to this slot (if any) */ + zram_slot_lock(zram, index); + zram_free_page(zram, index); + zram_slot_unlock(zram, index); mem = kmap_local_page(page); - if (page_same_filled(mem, &element)) { - kunmap_local(mem); - /* Free memory associated with this sector now. */ - flags = ZRAM_SAME; - atomic64_inc(&zram->stats.same_pages); - goto out; - } + same_filled = page_same_filled(mem, &element); kunmap_local(mem); + if (same_filled) + return write_same_filled_page(zram, element, index); -compress_again: zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]); - src = kmap_local_page(page); - ret = zcomp_compress(zstrm, src, &comp_len); - kunmap_local(src); + mem = kmap_local_page(page); + ret = zcomp_compress(zram->comps[ZRAM_PRIMARY_COMP], zstrm, + mem, &comp_len); + kunmap_local(mem); if (unlikely(ret)) { - zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]); + zcomp_stream_put(zstrm); 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]); + if (comp_len >= huge_class_size) { + zcomp_stream_put(zstrm); + return write_incompressible_page(zram, page, index); } - alloced_pages = zs_get_total_pages(zram->mem_pool); - update_used_max(zram, alloced_pages); + handle = zs_malloc(zram->mem_pool, comp_len, + GFP_NOIO | __GFP_NOWARN | + __GFP_HIGHMEM | __GFP_MOVABLE, page_to_nid(page)); + if (IS_ERR_VALUE(handle)) { + zcomp_stream_put(zstrm); + return PTR_ERR((void *)handle); + } - if (zram->limit_pages && alloced_pages > zram->limit_pages) { - zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]); + if (!zram_can_store_page(zram)) { + zcomp_stream_put(zstrm); 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_local_page(page); - memcpy(dst, src, comp_len); - if (comp_len == PAGE_SIZE) - kunmap_local(src); + zs_obj_write(zram->mem_pool, handle, zstrm->buffer, comp_len); + zcomp_stream_put(zstrm); - 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_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); + atomic64_add(comp_len, &zram->stats.compr_data_size); + return ret; } @@ -1560,6 +1941,49 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, } #ifdef CONFIG_ZRAM_MULTI_COMP +#define RECOMPRESS_IDLE (1 << 0) +#define RECOMPRESS_HUGE (1 << 1) + +static int scan_slots_for_recompress(struct zram *zram, u32 mode, u32 prio_max, + struct zram_pp_ctl *ctl) +{ + unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; + unsigned long index; + + for (index = 0; index < nr_pages; index++) { + bool ok = true; + + 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_SAME) || + zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE)) + goto next; + + /* Already compressed with same of higher priority */ + if (zram_get_priority(zram, index) + 1 >= prio_max) + goto next; + + ok = place_pp_slot(zram, ctl, index); +next: + zram_slot_unlock(zram, index); + if (!ok) + break; + } + + return 0; +} + /* * This function will decompress (unless it's ZRAM_HUGE) the page and then * attempt to compress it using provided compression algorithm priority @@ -1567,8 +1991,9 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, * * 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) +static int recompress_slot(struct zram *zram, u32 index, struct page *page, + u64 *num_recomp_pages, u32 threshold, u32 prio, + u32 prio_max) { struct zcomp_strm *zstrm = NULL; unsigned long handle_old; @@ -1577,9 +2002,8 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, unsigned int comp_len_new; unsigned int class_index_old; unsigned int class_index_new; - u32 num_recomps = 0; - void *src, *dst; - int ret; + void *src; + int ret = 0; handle_old = zram_get_handle(zram, index); if (!handle_old) @@ -1596,7 +2020,24 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, if (ret) return ret; + /* + * We touched this entry so mark it as non-IDLE. This makes sure that + * we don't preserve IDLE flag and don't incorrectly pick this entry + * for different post-processing type (e.g. writeback). + */ + zram_clear_flag(zram, index, ZRAM_IDLE); + class_index_old = zs_lookup_class_index(zram->mem_pool, comp_len_old); + + prio = max(prio, zram_get_priority(zram, index) + 1); + /* + * Recompression slots scan should not select slots that are + * already compressed with a higher priority algorithm, but + * just in case + */ + if (prio >= prio_max) + return 0; + /* * Iterate the secondary comp algorithms list (in order of priority) * and try to recompress the page. @@ -1605,22 +2046,16 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, 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_local_page(page); - ret = zcomp_compress(zstrm, src, &comp_len_new); + ret = zcomp_compress(zram->comps[prio], zstrm, + src, &comp_len_new); kunmap_local(src); if (ret) { - zcomp_stream_put(zram->comps[prio]); - return ret; + zcomp_stream_put(zstrm); + zstrm = NULL; + break; } class_index_new = zs_lookup_class_index(zram->mem_pool, @@ -1629,7 +2064,8 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, /* Continue until we make progress */ if (class_index_new >= class_index_old || (threshold && comp_len_new >= threshold)) { - zcomp_stream_put(zram->comps[prio]); + zcomp_stream_put(zstrm); + zstrm = NULL; continue; } @@ -1638,55 +2074,52 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, } /* - * We did not try to recompress, e.g. when we have only one - * secondary algorithm and the page is already recompressed - * using that algorithm + * Decrement the limit (if set) on pages we can recompress, even + * when current recompression was unsuccessful or did not compress + * the page below the threshold, because we still spent resources + * on it. */ - if (!zstrm) - return 0; + if (*num_recomp_pages) + *num_recomp_pages -= 1; + + /* Compression error */ + if (ret) + return ret; - if (class_index_new >= class_index_old) { + if (!zstrm) { /* * 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. + * in a way that would save memory. * - * 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. + * Mark the object incompressible if the max-priority + * algorithm couldn't re-compress it. */ - if (num_recomps == zram->num_active_comps - 1) - zram_set_flag(zram, index, ZRAM_INCOMPRESSIBLE); + if (prio < zram->num_active_comps) + return 0; + 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_write_bvec()) 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. + * We are holding per-CPU stream mutex and entry lock so better + * avoid direct reclaim. Allocation error is not fatal since + * we still have the old object in the mem_pool. + * + * XXX: technically, the node we really want here is the node that holds + * the original compressed data. But that would require us to modify + * zsmalloc API to return this information. For now, we will make do with + * the node of the page allocated for recompression. */ handle_new = zs_malloc(zram->mem_pool, comp_len_new, - __GFP_KSWAPD_RECLAIM | - __GFP_NOWARN | - __GFP_HIGHMEM | - __GFP_MOVABLE); + GFP_NOIO | __GFP_NOWARN | + __GFP_HIGHMEM | __GFP_MOVABLE, page_to_nid(page)); if (IS_ERR_VALUE(handle_new)) { - zcomp_stream_put(zram->comps[prio]); + zcomp_stream_put(zstrm); 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); + zs_obj_write(zram->mem_pool, handle_new, zstrm->buffer, comp_len_new); + zcomp_stream_put(zstrm); zram_free_page(zram, index); zram_set_handle(zram, index, handle_new); @@ -1699,22 +2132,23 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, 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; + u64 num_recomp_pages = ULLONG_MAX; + struct zram_pp_ctl *ctl = NULL; + struct zram_pp_slot *pps; u32 mode = 0, threshold = 0; - unsigned long index; - struct page *page; + u32 prio, prio_max; + struct page *page = NULL; ssize_t ret; + prio = ZRAM_SECONDARY_COMP; + prio_max = zram->num_active_comps; + args = skip_spaces(buf); while (*args) { args = next_arg(args, ¶m, &val); @@ -1732,6 +2166,17 @@ static ssize_t recompress_store(struct device *dev, continue; } + if (!strcmp(param, "max_pages")) { + /* + * Limit the number of entries (pages) we attempt to + * recompress. + */ + ret = kstrtoull(val, 10, &num_recomp_pages); + if (ret) + return ret; + continue; + } + if (!strcmp(param, "threshold")) { /* * We will re-compress only idle objects equal or @@ -1747,6 +2192,18 @@ static ssize_t recompress_store(struct device *dev, algo = val; continue; } + + if (!strcmp(param, "priority")) { + ret = kstrtouint(val, 10, &prio); + if (ret) + return ret; + + if (prio == ZRAM_PRIMARY_COMP) + prio = ZRAM_SECONDARY_COMP; + + prio_max = prio + 1; + continue; + } } if (threshold >= huge_class_size) @@ -1758,6 +2215,12 @@ static ssize_t recompress_store(struct device *dev, goto release_init_lock; } + /* Do not permit concurrent post-processing actions. */ + if (atomic_xchg(&zram->pp_in_progress, 1)) { + up_read(&zram->init_lock); + return -EAGAIN; + } + if (algo) { bool found = false; @@ -1766,7 +2229,7 @@ static ssize_t recompress_store(struct device *dev, continue; if (!strcmp(zram->comp_algs[prio], algo)) { - prio_max = min(prio + 1, ZRAM_MAX_COMPS); + prio_max = prio + 1; found = true; break; } @@ -1778,39 +2241,44 @@ static ssize_t recompress_store(struct device *dev, } } + prio_max = min(prio_max, (u32)zram->num_active_comps); + if (prio >= prio_max) { + 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); + ctl = init_pp_ctl(); + if (!ctl) { + ret = -ENOMEM; + goto release_init_lock; + } - if (!zram_allocated(zram, index)) - goto next; + scan_slots_for_recompress(zram, mode, prio_max, ctl); - if (mode & RECOMPRESS_IDLE && - !zram_test_flag(zram, index, ZRAM_IDLE)) - goto next; + ret = len; + while ((pps = select_pp_slot(ctl))) { + int err = 0; - if (mode & RECOMPRESS_HUGE && - !zram_test_flag(zram, index, ZRAM_HUGE)) - goto next; + if (!num_recomp_pages) + break; - 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)) + zram_slot_lock(zram, pps->index); + if (!zram_test_flag(zram, pps->index, ZRAM_PP_SLOT)) goto next; - err = zram_recompress(zram, index, page, threshold, + err = recompress_slot(zram, pps->index, page, + &num_recomp_pages, threshold, prio, prio_max); next: - zram_slot_unlock(zram, index); + zram_slot_unlock(zram, pps->index); + release_pp_slot(zram, pps); + if (err) { ret = err; break; @@ -1819,9 +2287,11 @@ next: cond_resched(); } - __free_page(page); - release_init_lock: + if (page) + __free_page(page); + release_pp_ctl(zram, ctl); + atomic_set(&zram->pp_in_progress, 0); up_read(&zram->init_lock); return ret; } @@ -1966,11 +2436,20 @@ static void zram_slot_free_notify(struct block_device *bdev, zram_slot_unlock(zram, index); } +static void zram_comp_params_reset(struct zram *zram) +{ + u32 prio; + + for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) { + comp_params_reset(zram, prio); + } +} + static void zram_destroy_comps(struct zram *zram) { u32 prio; - for (prio = 0; prio < ZRAM_MAX_COMPS; prio++) { + for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) { struct zcomp *comp = zram->comps[prio]; zram->comps[prio] = NULL; @@ -1979,6 +2458,15 @@ static void zram_destroy_comps(struct zram *zram) zcomp_destroy(comp); zram->num_active_comps--; } + + for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) { + /* Do not free statically defined compression algorithms */ + if (zram->comp_algs[prio] != default_compressor) + kfree(zram->comp_algs[prio]); + zram->comp_algs[prio] = NULL; + } + + zram_comp_params_reset(zram); } static void zram_reset_device(struct zram *zram) @@ -1987,11 +2475,6 @@ static void zram_reset_device(struct zram *zram) 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); @@ -2000,6 +2483,7 @@ static void zram_reset_device(struct zram *zram) zram->disksize = 0; zram_destroy_comps(zram); memset(&zram->stats, 0, sizeof(zram->stats)); + atomic_set(&zram->pp_in_progress, 0); reset_bdev(zram); comp_algorithm_set(zram, ZRAM_PRIMARY_COMP, default_compressor); @@ -2032,11 +2516,12 @@ static ssize_t disksize_store(struct device *dev, goto out_unlock; } - for (prio = 0; prio < ZRAM_MAX_COMPS; prio++) { + for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) { if (!zram->comp_algs[prio]) continue; - comp = zcomp_create(zram->comp_algs[prio]); + comp = zcomp_create(zram->comp_algs[prio], + &zram->params[prio]); if (IS_ERR(comp)) { pr_err("Cannot initialise %s compressing backend\n", zram->comp_algs[prio]); @@ -2127,7 +2612,6 @@ 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); @@ -2139,6 +2623,7 @@ static DEVICE_ATTR_RW(writeback_limit_enable); static DEVICE_ATTR_RW(recomp_algorithm); static DEVICE_ATTR_WO(recompress); #endif +static DEVICE_ATTR_WO(algorithm_params); static struct attribute *zram_disk_attrs[] = { &dev_attr_disksize.attr, @@ -2148,7 +2633,6 @@ static struct attribute *zram_disk_attrs[] = { &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, @@ -2166,6 +2650,7 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_recomp_algorithm.attr, &dev_attr_recompress.attr, #endif + &dev_attr_algorithm_params.attr, NULL, }; @@ -2177,6 +2662,30 @@ ATTRIBUTE_GROUPS(zram_disk); */ static int zram_add(void) { + struct queue_limits lim = { + .logical_block_size = ZRAM_LOGICAL_BLOCK_SIZE, + /* + * To ensure that we always get PAGE_SIZE aligned and + * n*PAGE_SIZED sized I/O requests. + */ + .physical_block_size = PAGE_SIZE, + .io_min = PAGE_SIZE, + .io_opt = PAGE_SIZE, + .max_hw_discard_sectors = 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 + .max_write_zeroes_sectors = UINT_MAX, +#endif + .features = BLK_FEAT_STABLE_WRITES | + BLK_FEAT_SYNCHRONOUS, + }; struct zram *zram; int ret, device_id; @@ -2195,11 +2704,11 @@ static int zram_add(void) #endif /* gendisk structure */ - zram->disk = blk_alloc_disk(NUMA_NO_NODE); - if (!zram->disk) { + zram->disk = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(zram->disk)) { pr_err("Error allocating disk structure for device %d\n", device_id); - ret = -ENOMEM; + ret = PTR_ERR(zram->disk); goto out_free_idr; } @@ -2210,42 +2719,16 @@ static int zram_add(void) zram->disk->fops = &zram_devops; zram->disk->private_data = zram; snprintf(zram->disk->disk_name, 16, "zram%d", device_id); + atomic_set(&zram->pp_in_progress, 0); + zram_comp_params_reset(zram); + comp_algorithm_set(zram, ZRAM_PRIMARY_COMP, default_compressor); /* 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); - - /* - * 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); - 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; @@ -2394,9 +2877,10 @@ static void destroy_devices(void) static int __init zram_init(void) { + struct zram_table_entry zram_te; int ret; - BUILD_BUG_ON(__NR_ZRAM_PAGEFLAGS > BITS_PER_LONG); + BUILD_BUG_ON(__NR_ZRAM_PAGEFLAGS > sizeof(zram_te.flags) * 8); ret = cpuhp_setup_state_multi(CPUHP_ZCOMP_PREPARE, "block/zram:prepare", zcomp_cpu_up_prepare, zcomp_cpu_dead); |