diff options
Diffstat (limited to 'drivers/md')
64 files changed, 6132 insertions, 3834 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 30b426e..f2ccbc3 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -297,6 +297,17 @@ config DM_MIRROR Allow volume managers to mirror logical volumes, also needed for live data migration tools such as 'pvmove'. +config DM_LOG_USERSPACE + tristate "Mirror userspace logging" + depends on DM_MIRROR && NET + select CONNECTOR + ---help--- + The userspace logging module provides a mechanism for + relaying the dm-dirty-log API to userspace. Log designs + which are more suited to userspace implementation (e.g. + shared storage logs) or experimental logs can be implemented + by leveraging this framework. + config DM_RAID tristate "RAID 1/4/5/6/10 target" depends on BLK_DEV_DM @@ -323,17 +334,6 @@ config DM_RAID RAID-5, RAID-6 distributes the syndromes across the drives in one of the available parity distribution methods. -config DM_LOG_USERSPACE - tristate "Mirror userspace logging" - depends on DM_MIRROR && NET - select CONNECTOR - ---help--- - The userspace logging module provides a mechanism for - relaying the dm-dirty-log API to userspace. Log designs - which are more suited to userspace implementation (e.g. - shared storage logs) or experimental logs can be implemented - by leveraging this framework. - config DM_ZERO tristate "Zero target" depends on BLK_DEV_DM diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 5ef78ef..2acc43f 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -3,7 +3,7 @@ # dm-mod-y += dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \ - dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o + dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o dm-stats.o dm-multipath-y += dm-path-selector.o dm-mpath.o dm-snapshot-y += dm-snap.o dm-exception-store.o dm-snap-transient.o \ dm-snap-persistent.o diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig index f950c9d..2638417 100644 --- a/drivers/md/bcache/Kconfig +++ b/drivers/md/bcache/Kconfig @@ -13,15 +13,8 @@ config BCACHE_DEBUG ---help--- Don't select this option unless you're a developer - Enables extra debugging tools (primarily a fuzz tester) - -config BCACHE_EDEBUG - bool "Extended runtime checks" - depends on BCACHE - ---help--- - Don't select this option unless you're a developer - - Enables extra runtime checks which significantly affect performance + Enables extra debugging tools, allows expensive runtime checks to be + turned on. config BCACHE_CLOSURES_DEBUG bool "Debug closures" diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index e45f557..2b46bf1 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -63,13 +63,12 @@ #include "bcache.h" #include "btree.h" +#include <linux/blkdev.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/random.h> #include <trace/events/bcache.h> -#define MAX_IN_FLIGHT_DISCARDS 8U - /* Bucket heap / gen */ uint8_t bch_inc_gen(struct cache *ca, struct bucket *b) @@ -121,75 +120,6 @@ void bch_rescale_priorities(struct cache_set *c, int sectors) mutex_unlock(&c->bucket_lock); } -/* Discard/TRIM */ - -struct discard { - struct list_head list; - struct work_struct work; - struct cache *ca; - long bucket; - - struct bio bio; - struct bio_vec bv; -}; - -static void discard_finish(struct work_struct *w) -{ - struct discard *d = container_of(w, struct discard, work); - struct cache *ca = d->ca; - char buf[BDEVNAME_SIZE]; - - if (!test_bit(BIO_UPTODATE, &d->bio.bi_flags)) { - pr_notice("discard error on %s, disabling", - bdevname(ca->bdev, buf)); - d->ca->discard = 0; - } - - mutex_lock(&ca->set->bucket_lock); - - fifo_push(&ca->free, d->bucket); - list_add(&d->list, &ca->discards); - atomic_dec(&ca->discards_in_flight); - - mutex_unlock(&ca->set->bucket_lock); - - closure_wake_up(&ca->set->bucket_wait); - wake_up_process(ca->alloc_thread); - - closure_put(&ca->set->cl); -} - -static void discard_endio(struct bio *bio, int error) -{ - struct discard *d = container_of(bio, struct discard, bio); - schedule_work(&d->work); -} - -static void do_discard(struct cache *ca, long bucket) -{ - struct discard *d = list_first_entry(&ca->discards, - struct discard, list); - - list_del(&d->list); - d->bucket = bucket; - - atomic_inc(&ca->discards_in_flight); - closure_get(&ca->set->cl); - - bio_init(&d->bio); - - d->bio.bi_sector = bucket_to_sector(ca->set, d->bucket); - d->bio.bi_bdev = ca->bdev; - d->bio.bi_rw = REQ_WRITE|REQ_DISCARD; - d->bio.bi_max_vecs = 1; - d->bio.bi_io_vec = d->bio.bi_inline_vecs; - d->bio.bi_size = bucket_bytes(ca); - d->bio.bi_end_io = discard_endio; - bio_set_prio(&d->bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)); - - submit_bio(0, &d->bio); -} - /* Allocation */ static inline bool can_inc_bucket_gen(struct bucket *b) @@ -280,7 +210,7 @@ static void invalidate_buckets_lru(struct cache *ca) * multiple times when it can't do anything */ ca->invalidate_needs_gc = 1; - bch_queue_gc(ca->set); + wake_up_gc(ca->set); return; } @@ -305,7 +235,7 @@ static void invalidate_buckets_fifo(struct cache *ca) if (++checked >= ca->sb.nbuckets) { ca->invalidate_needs_gc = 1; - bch_queue_gc(ca->set); + wake_up_gc(ca->set); return; } } @@ -330,7 +260,7 @@ static void invalidate_buckets_random(struct cache *ca) if (++checked >= ca->sb.nbuckets / 2) { ca->invalidate_needs_gc = 1; - bch_queue_gc(ca->set); + wake_up_gc(ca->set); return; } } @@ -398,16 +328,18 @@ static int bch_allocator_thread(void *arg) else break; - allocator_wait(ca, (int) fifo_free(&ca->free) > - atomic_read(&ca->discards_in_flight)); - if (ca->discard) { - allocator_wait(ca, !list_empty(&ca->discards)); - do_discard(ca, bucket); - } else { - fifo_push(&ca->free, bucket); - closure_wake_up(&ca->set->bucket_wait); + mutex_unlock(&ca->set->bucket_lock); + blkdev_issue_discard(ca->bdev, + bucket_to_sector(ca->set, bucket), + ca->sb.block_size, GFP_KERNEL, 0); + mutex_lock(&ca->set->bucket_lock); } + + allocator_wait(ca, !fifo_full(&ca->free)); + + fifo_push(&ca->free, bucket); + wake_up(&ca->set->bucket_wait); } /* @@ -433,16 +365,40 @@ static int bch_allocator_thread(void *arg) } } -long bch_bucket_alloc(struct cache *ca, unsigned watermark, struct closure *cl) +long bch_bucket_alloc(struct cache *ca, unsigned watermark, bool wait) { - long r = -1; -again: + DEFINE_WAIT(w); + struct bucket *b; + long r; + + /* fastpath */ + if (fifo_used(&ca->free) > ca->watermark[watermark]) { + fifo_pop(&ca->free, r); + goto out; + } + + if (!wait) + return -1; + + while (1) { + if (fifo_used(&ca->free) > ca->watermark[watermark]) { + fifo_pop(&ca->free, r); + break; + } + + prepare_to_wait(&ca->set->bucket_wait, &w, + TASK_UNINTERRUPTIBLE); + + mutex_unlock(&ca->set->bucket_lock); + schedule(); + mutex_lock(&ca->set->bucket_lock); + } + + finish_wait(&ca->set->bucket_wait, &w); +out: wake_up_process(ca->alloc_thread); - if (fifo_used(&ca->free) > ca->watermark[watermark] && - fifo_pop(&ca->free, r)) { - struct bucket *b = ca->buckets + r; -#ifdef CONFIG_BCACHE_EDEBUG + if (expensive_debug_checks(ca->set)) { size_t iter; long i; @@ -455,36 +411,23 @@ again: BUG_ON(i == r); fifo_for_each(i, &ca->unused, iter) BUG_ON(i == r); -#endif - BUG_ON(atomic_read(&b->pin) != 1); - - SET_GC_SECTORS_USED(b, ca->sb.bucket_size); - - if (watermark <= WATERMARK_METADATA) { - SET_GC_MARK(b, GC_MARK_METADATA); - b->prio = BTREE_PRIO; - } else { - SET_GC_MARK(b, GC_MARK_RECLAIMABLE); - b->prio = INITIAL_PRIO; - } - - return r; } - trace_bcache_alloc_fail(ca); + b = ca->buckets + r; - if (cl) { - closure_wait(&ca->set->bucket_wait, cl); + BUG_ON(atomic_read(&b->pin) != 1); - if (closure_blocking(cl)) { - mutex_unlock(&ca->set->bucket_lock); - closure_sync(cl); - mutex_lock(&ca->set->bucket_lock); - goto again; - } + SET_GC_SECTORS_USED(b, ca->sb.bucket_size); + + if (watermark <= WATERMARK_METADATA) { + SET_GC_MARK(b, GC_MARK_METADATA); + b->prio = BTREE_PRIO; + } else { + SET_GC_MARK(b, GC_MARK_RECLAIMABLE); + b->prio = INITIAL_PRIO; } - return -1; + return r; } void bch_bucket_free(struct cache_set *c, struct bkey *k) @@ -501,7 +444,7 @@ void bch_bucket_free(struct cache_set *c, struct bkey *k) } int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark, - struct bkey *k, int n, struct closure *cl) + struct bkey *k, int n, bool wait) { int i; @@ -514,7 +457,7 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark, for (i = 0; i < n; i++) { struct cache *ca = c->cache_by_alloc[i]; - long b = bch_bucket_alloc(ca, watermark, cl); + long b = bch_bucket_alloc(ca, watermark, wait); if (b == -1) goto err; @@ -529,22 +472,202 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark, return 0; err: bch_bucket_free(c, k); - __bkey_put(c, k); + bkey_put(c, k); return -1; } int bch_bucket_alloc_set(struct cache_set *c, unsigned watermark, - struct bkey *k, int n, struct closure *cl) + struct bkey *k, int n, bool wait) { int ret; mutex_lock(&c->bucket_lock); - ret = __bch_bucket_alloc_set(c, watermark, k, n, cl); + ret = __bch_bucket_alloc_set(c, watermark, k, n, wait); mutex_unlock(&c->bucket_lock); return ret; } +/* Sector allocator */ + +struct open_bucket { + struct list_head list; + unsigned last_write_point; + unsigned sectors_free; + BKEY_PADDED(key); +}; + +/* + * We keep multiple buckets open for writes, and try to segregate different + * write streams for better cache utilization: first we look for a bucket where + * the last write to it was sequential with the current write, and failing that + * we look for a bucket that was last used by the same task. + * + * The ideas is if you've got multiple tasks pulling data into the cache at the + * same time, you'll get better cache utilization if you try to segregate their + * data and preserve locality. + * + * For example, say you've starting Firefox at the same time you're copying a + * bunch of files. Firefox will likely end up being fairly hot and stay in the + * cache awhile, but the data you copied might not be; if you wrote all that + * data to the same buckets it'd get invalidated at the same time. + * + * Both of those tasks will be doing fairly random IO so we can't rely on + * detecting sequential IO to segregate their data, but going off of the task + * should be a sane heuristic. + */ +static struct open_bucket *pick_data_bucket(struct cache_set *c, + const struct bkey *search, + unsigned write_point, + struct bkey *alloc) +{ + struct open_bucket *ret, *ret_task = NULL; + + list_for_each_entry_reverse(ret, &c->data_buckets, list) + if (!bkey_cmp(&ret->key, search)) + goto found; + else if (ret->last_write_point == write_point) + ret_task = ret; + + ret = ret_task ?: list_first_entry(&c->data_buckets, + struct open_bucket, list); +found: + if (!ret->sectors_free && KEY_PTRS(alloc)) { + ret->sectors_free = c->sb.bucket_size; + bkey_copy(&ret->key, alloc); + bkey_init(alloc); + } + + if (!ret->sectors_free) + ret = NULL; + + return ret; +} + +/* + * Allocates some space in the cache to write to, and k to point to the newly + * allocated space, and updates KEY_SIZE(k) and KEY_OFFSET(k) (to point to the + * end of the newly allocated space). + * + * May allocate fewer sectors than @sectors, KEY_SIZE(k) indicates how many + * sectors were actually allocated. + * + * If s->writeback is true, will not fail. + */ +bool bch_alloc_sectors(struct cache_set *c, struct bkey *k, unsigned sectors, + unsigned write_point, unsigned write_prio, bool wait) +{ + struct open_bucket *b; + BKEY_PADDED(key) alloc; + unsigned i; + + /* + * We might have to allocate a new bucket, which we can't do with a + * spinlock held. So if we have to allocate, we drop the lock, allocate + * and then retry. KEY_PTRS() indicates whether alloc points to + * allocated bucket(s). + */ + + bkey_init(&alloc.key); + spin_lock(&c->data_bucket_lock); + + while (!(b = pick_data_bucket(c, k, write_point, &alloc.key))) { + unsigned watermark = write_prio + ? WATERMARK_MOVINGGC + : WATERMARK_NONE; + + spin_unlock(&c->data_bucket_lock); + + if (bch_bucket_alloc_set(c, watermark, &alloc.key, 1, wait)) + return false; + + spin_lock(&c->data_bucket_lock); + } + + /* + * If we had to allocate, we might race and not need to allocate the + * second time we call find_data_bucket(). If we allocated a bucket but + * didn't use it, drop the refcount bch_bucket_alloc_set() took: + */ + if (KEY_PTRS(&alloc.key)) + bkey_put(c, &alloc.key); + + for (i = 0; i < KEY_PTRS(&b->key); i++) + EBUG_ON(ptr_stale(c, &b->key, i)); + + /* Set up the pointer to the space we're allocating: */ + + for (i = 0; i < KEY_PTRS(&b->key); i++) + k->ptr[i] = b->key.ptr[i]; + + sectors = min(sectors, b->sectors_free); + + SET_KEY_OFFSET(k, KEY_OFFSET(k) + sectors); + SET_KEY_SIZE(k, sectors); + SET_KEY_PTRS(k, KEY_PTRS(&b->key)); + + /* + * Move b to the end of the lru, and keep track of what this bucket was + * last used for: + */ + list_move_tail(&b->list, &c->data_buckets); + bkey_copy_key(&b->key, k); + b->last_write_point = write_point; + + b->sectors_free -= sectors; + + for (i = 0; i < KEY_PTRS(&b->key); i++) { + SET_PTR_OFFSET(&b->key, i, PTR_OFFSET(&b->key, i) + sectors); + + atomic_long_add(sectors, + &PTR_CACHE(c, &b->key, i)->sectors_written); + } + + if (b->sectors_free < c->sb.block_size) + b->sectors_free = 0; + + /* + * k takes refcounts on the buckets it points to until it's inserted + * into the btree, but if we're done with this bucket we just transfer + * get_data_bucket()'s refcount. + */ + if (b->sectors_free) + for (i = 0; i < KEY_PTRS(&b->key); i++) + atomic_inc(&PTR_BUCKET(c, &b->key, i)->pin); + + spin_unlock(&c->data_bucket_lock); + return true; +} + /* Init */ +void bch_open_buckets_free(struct cache_set *c) +{ + struct open_bucket *b; + + while (!list_empty(&c->data_buckets)) { + b = list_first_entry(&c->data_buckets, + struct open_bucket, list); + list_del(&b->list); + kfree(b); + } +} + +int bch_open_buckets_alloc(struct cache_set *c) +{ + int i; + + spin_lock_init(&c->data_bucket_lock); + + for (i = 0; i < 6; i++) { + struct open_bucket *b = kzalloc(sizeof(*b), GFP_KERNEL); + if (!b) + return -ENOMEM; + + list_add(&b->list, &c->data_buckets); + } + + return 0; +} + int bch_cache_allocator_start(struct cache *ca) { struct task_struct *k = kthread_run(bch_allocator_thread, @@ -556,22 +679,8 @@ int bch_cache_allocator_start(struct cache *ca) return 0; } -void bch_cache_allocator_exit(struct cache *ca) -{ - struct discard *d; - - while (!list_empty(&ca->discards)) { - d = list_first_entry(&ca->discards, struct discard, list); - cancel_work_sync(&d->work); - list_del(&d->list); - kfree(d); - } -} - int bch_cache_allocator_init(struct cache *ca) { - unsigned i; - /* * Reserve: * Prio/gen writes first @@ -589,15 +698,5 @@ int bch_cache_allocator_init(struct cache *ca) ca->watermark[WATERMARK_NONE] = ca->free.size / 2 + ca->watermark[WATERMARK_MOVINGGC]; - for (i = 0; i < MAX_IN_FLIGHT_DISCARDS; i++) { - struct discard *d = kzalloc(sizeof(*d), GFP_KERNEL); - if (!d) - return -ENOMEM; - - d->ca = ca; - INIT_WORK(&d->work, discard_finish); - list_add(&d->list, &ca->discards); - } - return 0; } diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index b39f6f0..4beb55a 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -177,6 +177,7 @@ #define pr_fmt(fmt) "bcache: %s() " fmt "\n", __func__ +#include <linux/bcache.h> #include <linux/bio.h> #include <linux/kobject.h> #include <linux/list.h> @@ -210,168 +211,6 @@ BITMASK(GC_MARK, struct bucket, gc_mark, 0, 2); #define GC_MARK_METADATA 2 BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 14); -struct bkey { - uint64_t high; - uint64_t low; - uint64_t ptr[]; -}; - -/* Enough for a key with 6 pointers */ -#define BKEY_PAD 8 - -#define BKEY_PADDED(key) \ - union { struct bkey key; uint64_t key ## _pad[BKEY_PAD]; } - -/* Version 0: Cache device - * Version 1: Backing device - * Version 2: Seed pointer into btree node checksum - * Version 3: Cache device with new UUID format - * Version 4: Backing device with data offset - */ -#define BCACHE_SB_VERSION_CDEV 0 -#define BCACHE_SB_VERSION_BDEV 1 -#define BCACHE_SB_VERSION_CDEV_WITH_UUID 3 -#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET 4 -#define BCACHE_SB_MAX_VERSION 4 - -#define SB_SECTOR 8 -#define SB_SIZE 4096 -#define SB_LABEL_SIZE 32 -#define SB_JOURNAL_BUCKETS 256U -/* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */ -#define MAX_CACHES_PER_SET 8 - -#define BDEV_DATA_START_DEFAULT 16 /* sectors */ - -struct cache_sb { - uint64_t csum; - uint64_t offset; /* sector where this sb was written */ - uint64_t version; - - uint8_t magic[16]; - - uint8_t uuid[16]; - union { - uint8_t set_uuid[16]; - uint64_t set_magic; - }; - uint8_t label[SB_LABEL_SIZE]; - - uint64_t flags; - uint64_t seq; - uint64_t pad[8]; - - union { - struct { - /* Cache devices */ - uint64_t nbuckets; /* device size */ - - uint16_t block_size; /* sectors */ - uint16_t bucket_size; /* sectors */ - - uint16_t nr_in_set; - uint16_t nr_this_dev; - }; - struct { - /* Backing devices */ - uint64_t data_offset; - - /* - * block_size from the cache device section is still used by - * backing devices, so don't add anything here until we fix - * things to not need it for backing devices anymore - */ - }; - }; - - uint32_t last_mount; /* time_t */ - - uint16_t first_bucket; - union { - uint16_t njournal_buckets; - uint16_t keys; - }; - uint64_t d[SB_JOURNAL_BUCKETS]; /* journal buckets */ -}; - -BITMASK(CACHE_SYNC, struct cache_sb, flags, 0, 1); -BITMASK(CACHE_DISCARD, struct cache_sb, flags, 1, 1); -BITMASK(CACHE_REPLACEMENT, struct cache_sb, flags, 2, 3); -#define CACHE_REPLACEMENT_LRU 0U -#define CACHE_REPLACEMENT_FIFO 1U -#define CACHE_REPLACEMENT_RANDOM 2U - -BITMASK(BDEV_CACHE_MODE, struct cache_sb, flags, 0, 4); -#define CACHE_MODE_WRITETHROUGH 0U -#define CACHE_MODE_WRITEBACK 1U -#define CACHE_MODE_WRITEAROUND 2U -#define CACHE_MODE_NONE 3U -BITMASK(BDEV_STATE, struct cache_sb, flags, 61, 2); -#define BDEV_STATE_NONE 0U -#define BDEV_STATE_CLEAN 1U -#define BDEV_STATE_DIRTY 2U -#define BDEV_STATE_STALE 3U - -/* Version 1: Seed pointer into btree node checksum - */ -#define BCACHE_BSET_VERSION 1 - -/* - * This is the on disk format for btree nodes - a btree node on disk is a list - * of these; within each set the keys are sorted - */ -struct bset { - uint64_t csum; - uint64_t magic; - uint64_t seq; - uint32_t version; - uint32_t keys; - - union { - struct bkey start[0]; - uint64_t d[0]; - }; -}; - -/* - * On disk format for priorities and gens - see super.c near prio_write() for - * more. - */ -struct prio_set { - uint64_t csum; - uint64_t magic; - uint64_t seq; - uint32_t version; - uint32_t pad; - - uint64_t next_bucket; - - struct bucket_disk { - uint16_t prio; - uint8_t gen; - } __attribute((packed)) data[]; -}; - -struct uuid_entry { - union { - struct { - uint8_t uuid[16]; - uint8_t label[32]; - uint32_t first_reg; - uint32_t last_reg; - uint32_t invalidated; - - uint32_t flags; - /* Size of flash only volumes */ - uint64_t sectors; - }; - - uint8_t pad[128]; - }; -}; - -BITMASK(UUID_FLASH_ONLY, struct uuid_entry, flags, 0, 1); - #include "journal.h" #include "stats.h" struct search; @@ -384,8 +223,6 @@ struct keybuf_key { void *private; }; -typedef bool (keybuf_pred_fn)(struct keybuf *, struct bkey *); - struct keybuf { struct bkey last_scanned; spinlock_t lock; @@ -400,7 +237,7 @@ struct keybuf { struct rb_root keys; -#define KEYBUF_NR 100 +#define KEYBUF_NR 500 DECLARE_ARRAY_ALLOCATOR(struct keybuf_key, freelist, KEYBUF_NR); }; @@ -429,16 +266,15 @@ struct bcache_device { struct gendisk *disk; - /* If nonzero, we're closing */ - atomic_t closing; - - /* If nonzero, we're detaching/unregistering from cache set */ - atomic_t detaching; - int flush_done; + unsigned long flags; +#define BCACHE_DEV_CLOSING 0 +#define BCACHE_DEV_DETACHING 1 +#define BCACHE_DEV_UNLINK_DONE 2 - uint64_t nr_stripes; - unsigned stripe_size_bits; + unsigned nr_stripes; + unsigned stripe_size; atomic_t *stripe_sectors_dirty; + unsigned long *full_dirty_stripes; unsigned long sectors_dirty_last; long sectors_dirty_derivative; @@ -498,7 +334,7 @@ struct cached_dev { */ atomic_t has_dirty; - struct ratelimit writeback_rate; + struct bch_ratelimit writeback_rate; struct delayed_work writeback_rate_update; /* @@ -507,10 +343,9 @@ struct cached_dev { */ sector_t last_read; - /* Number of writeback bios in flight */ - atomic_t in_flight; - struct closure_with_timer writeback; - struct closure_waitlist writeback_wait; + /* Limit number of writeback bios in flight */ + struct semaphore in_flight; + struct task_struct *writeback_thread; struct keybuf writeback_keys; @@ -528,8 +363,8 @@ struct cached_dev { unsigned sequential_cutoff; unsigned readahead; - unsigned sequential_merge:1; unsigned verify:1; + unsigned bypass_torture_test:1; unsigned partial_stripes_expensive:1; unsigned writeback_metadata:1; @@ -621,15 +456,6 @@ struct cache { bool discard; /* Get rid of? */ - /* - * We preallocate structs for issuing discards to buckets, and keep them - * on this list when they're not in use; do_discard() issues discards - * whenever there's work to do and is called by free_some_buckets() and - * when a discard finishes. - */ - atomic_t discards_in_flight; - struct list_head discards; - struct journal_device journal; /* The rest of this all shows up in sysfs */ @@ -650,7 +476,6 @@ struct gc_stat { size_t nkeys; uint64_t data; /* sectors */ - uint64_t dirty; /* sectors */ unsigned in_use; /* percent */ }; @@ -745,8 +570,8 @@ struct cache_set { * basically a lock for this that we can wait on asynchronously. The * btree_root() macro releases the lock when it returns. */ - struct closure *try_harder; - struct closure_waitlist try_wait; + struct task_struct *try_harder; + wait_queue_head_t try_wait; uint64_t try_harder_start; /* @@ -760,7 +585,7 @@ struct cache_set { * written. */ atomic_t prio_blocked; - struct closure_waitlist bucket_wait; + wait_queue_head_t bucket_wait; /* * For any bio we don't skip we subtract the number of sectors from @@ -783,7 +608,7 @@ struct cache_set { struct gc_stat gc_stats; size_t nbuckets; - struct closure_with_waitlist gc; + struct task_struct *gc_thread; /* Where in the btree gc currently is */ struct bkey gc_done; @@ -796,11 +621,10 @@ struct cache_set { /* Counts how many sectors bio_insert has added to the cache */ atomic_t sectors_to_gc; - struct closure moving_gc; - struct closure_waitlist moving_gc_wait; + wait_queue_head_t moving_gc_wait; struct keybuf moving_gc_keys; /* Number of moving GC bios in flight */ - atomic_t in_flight; + struct semaphore moving_in_flight; struct btree *root; @@ -842,22 +666,27 @@ struct cache_set { unsigned congested_read_threshold_us; unsigned congested_write_threshold_us; - spinlock_t sort_time_lock; struct time_stats sort_time; struct time_stats btree_gc_time; struct time_stats btree_split_time; - spinlock_t btree_read_time_lock; struct time_stats btree_read_time; struct time_stats try_harder_time; atomic_long_t cache_read_races; atomic_long_t writeback_keys_done; atomic_long_t writeback_keys_failed; + + enum { + ON_ERROR_UNREGISTER, + ON_ERROR_PANIC, + } on_error; unsigned error_limit; unsigned error_decay; + unsigned short journal_delay_ms; unsigned verify:1; unsigned key_merging_disabled:1; + unsigned expensive_debug_checks:1; unsigned gc_always_rewrite:1; unsigned shrinker_disabled:1; unsigned copy_gc_enabled:1; @@ -866,21 +695,6 @@ struct cache_set { struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS]; }; -static inline bool key_merging_disabled(struct cache_set *c) -{ -#ifdef CONFIG_BCACHE_DEBUG - return c->key_merging_disabled; -#else - return 0; -#endif -} - -static inline bool SB_IS_BDEV(const struct cache_sb *sb) -{ - return sb->version == BCACHE_SB_VERSION_BDEV - || sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET; -} - struct bbio { unsigned submit_time_us; union { @@ -934,59 +748,6 @@ static inline unsigned local_clock_us(void) #define prio_buckets(c) \ DIV_ROUND_UP((size_t) (c)->sb.nbuckets, prios_per_bucket(c)) -#define JSET_MAGIC 0x245235c1a3625032ULL -#define PSET_MAGIC 0x6750e15f87337f91ULL -#define BSET_MAGIC 0x90135c78b99e07f5ULL - -#define jset_magic(c) ((c)->sb.set_magic ^ JSET_MAGIC) -#define pset_magic(c) ((c)->sb.set_magic ^ PSET_MAGIC) -#define bset_magic(c) ((c)->sb.set_magic ^ BSET_MAGIC) - -/* Bkey fields: all units are in sectors */ - -#define KEY_FIELD(name, field, offset, size) \ - BITMASK(name, struct bkey, field, offset, size) - -#define PTR_FIELD(name, offset, size) \ - static inline uint64_t name(const struct bkey *k, unsigned i) \ - { return (k->ptr[i] >> offset) & ~(((uint64_t) ~0) << size); } \ - \ - static inline void SET_##name(struct bkey *k, unsigned i, uint64_t v)\ - { \ - k->ptr[i] &= ~(~((uint64_t) ~0 << size) << offset); \ - k->ptr[i] |= v << offset; \ - } - -KEY_FIELD(KEY_PTRS, high, 60, 3) -KEY_FIELD(HEADER_SIZE, high, 58, 2) -KEY_FIELD(KEY_CSUM, high, 56, 2) -KEY_FIELD(KEY_PINNED, high, 55, 1) -KEY_FIELD(KEY_DIRTY, high, 36, 1) - -KEY_FIELD(KEY_SIZE, high, 20, 16) -KEY_FIELD(KEY_INODE, high, 0, 20) - -/* Next time I change the on disk format, KEY_OFFSET() won't be 64 bits */ - -static inline uint64_t KEY_OFFSET(const struct bkey *k) -{ - return k->low; -} - -static inline void SET_KEY_OFFSET(struct bkey *k, uint64_t v) -{ - k->low = v; -} - -PTR_FIELD(PTR_DEV, 51, 12) -PTR_FIELD(PTR_OFFSET, 8, 43) -PTR_FIELD(PTR_GEN, 0, 8) - -#define PTR_CHECK_DEV ((1 << 12) - 1) - -#define PTR(gen, offset, dev) \ - ((((uint64_t) dev) << 51) | ((uint64_t) offset) << 8 | gen) - static inline size_t sector_to_bucket(struct cache_set *c, sector_t s) { return s >> c->bucket_bits; @@ -1025,27 +786,11 @@ static inline struct bucket *PTR_BUCKET(struct cache_set *c, /* Btree key macros */ -/* - * The high bit being set is a relic from when we used it to do binary - * searches - it told you where a key started. It's not used anymore, - * and can probably be safely dropped. - */ -#define KEY(dev, sector, len) \ -((struct bkey) { \ - .high = (1ULL << 63) | ((uint64_t) (len) << 20) | (dev), \ - .low = (sector) \ -}) - static inline void bkey_init(struct bkey *k) { - *k = KEY(0, 0, 0); + *k = ZERO_KEY; } -#define KEY_START(k) (KEY_OFFSET(k) - KEY_SIZE(k)) -#define START_KEY(k) KEY(KEY_INODE(k), KEY_START(k), 0) -#define MAX_KEY KEY(~(~0 << 20), ((uint64_t) ~0) >> 1, 0) -#define ZERO_KEY KEY(0, 0, 0) - /* * This is used for various on disk data structures - cache_sb, prio_set, bset, * jset: The checksum is _always_ the first 8 bytes of these structs @@ -1095,14 +840,6 @@ do { \ for (b = (ca)->buckets + (ca)->sb.first_bucket; \ b < (ca)->buckets + (ca)->sb.nbuckets; b++) -static inline void __bkey_put(struct cache_set *c, struct bkey *k) -{ - unsigned i; - - for (i = 0; i < KEY_PTRS(k); i++) - atomic_dec_bug(&PTR_BUCKET(c, k, i)->pin); -} - static inline void cached_dev_put(struct cached_dev *dc) { if (atomic_dec_and_test(&dc->count)) @@ -1174,13 +911,15 @@ uint8_t bch_inc_gen(struct cache *, struct bucket *); void bch_rescale_priorities(struct cache_set *, int); bool bch_bucket_add_unused(struct cache *, struct bucket *); -long bch_bucket_alloc(struct cache *, unsigned, struct closure *); +long bch_bucket_alloc(struct cache *, unsigned, bool); void bch_bucket_free(struct cache_set *, struct bkey *); int __bch_bucket_alloc_set(struct cache_set *, unsigned, - struct bkey *, int, struct closure *); + struct bkey *, int, bool); int bch_bucket_alloc_set(struct cache_set *, unsigned, - struct bkey *, int, struct closure *); + struct bkey *, int, bool); +bool bch_alloc_sectors(struct cache_set *, struct bkey *, unsigned, + unsigned, unsigned, bool); __printf(2, 3) bool bch_cache_set_error(struct cache_set *, const char *, ...); @@ -1188,7 +927,7 @@ bool bch_cache_set_error(struct cache_set *, const char *, ...); void bch_prio_write(struct cache *); void bch_write_bdev_super(struct cached_dev *, struct closure *); -extern struct workqueue_struct *bcache_wq, *bch_gc_wq; +extern struct workqueue_struct *bcache_wq; extern const char * const bch_cache_modes[]; extern struct mutex bch_register_lock; extern struct list_head bch_cache_sets; @@ -1221,15 +960,14 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *); void bch_btree_cache_free(struct cache_set *); int bch_btree_cache_alloc(struct cache_set *); void bch_moving_init_cache_set(struct cache_set *); +int bch_open_buckets_alloc(struct cache_set *); +void bch_open_buckets_free(struct cache_set *); int bch_cache_allocator_start(struct cache *ca); -void bch_cache_allocator_exit(struct cache *ca); int bch_cache_allocator_init(struct cache *ca); void bch_debug_exit(void); int bch_debug_init(struct kobject *); -void bch_writeback_exit(void); -int bch_writeback_init(void); void bch_request_exit(void); int bch_request_init(void); void bch_btree_exit(void); diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 8010eed..7d388b8 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -14,22 +14,12 @@ /* Keylists */ -void bch_keylist_copy(struct keylist *dest, struct keylist *src) -{ - *dest = *src; - - if (src->list == src->d) { - size_t n = (uint64_t *) src->top - src->d; - dest->top = (struct bkey *) &dest->d[n]; - dest->list = dest->d; - } -} - int bch_keylist_realloc(struct keylist *l, int nptrs, struct cache_set *c) { - unsigned oldsize = (uint64_t *) l->top - l->list; - unsigned newsize = oldsize + 2 + nptrs; - uint64_t *new; + size_t oldsize = bch_keylist_nkeys(l); + size_t newsize = oldsize + 2 + nptrs; + uint64_t *old_keys = l->keys_p == l->inline_keys ? NULL : l->keys_p; + uint64_t *new_keys; /* The journalling code doesn't handle the case where the keys to insert * is bigger than an empty write: If we just return -ENOMEM here, @@ -45,24 +35,23 @@ int bch_keylist_realloc(struct keylist *l, int nptrs, struct cache_set *c) roundup_pow_of_two(oldsize) == newsize) return 0; - new = krealloc(l->list == l->d ? NULL : l->list, - sizeof(uint64_t) * newsize, GFP_NOIO); + new_keys = krealloc(old_keys, sizeof(uint64_t) * newsize, GFP_NOIO); - if (!new) + if (!new_keys) return -ENOMEM; - if (l->list == l->d) - memcpy(new, l->list, sizeof(uint64_t) * KEYLIST_INLINE); + if (!old_keys) + memcpy(new_keys, l->inline_keys, sizeof(uint64_t) * oldsize); - l->list = new; - l->top = (struct bkey *) (&l->list[oldsize]); + l->keys_p = new_keys; + l->top_p = new_keys + oldsize; return 0; } struct bkey *bch_keylist_pop(struct keylist *l) { - struct bkey *k = l->bottom; + struct bkey *k = l->keys; if (k == l->top) return NULL; @@ -73,21 +62,20 @@ struct bkey *bch_keylist_pop(struct keylist *l) return l->top = k; } -/* Pointer validation */ - -bool __bch_ptr_invalid(struct cache_set *c, int level, const struct bkey *k) +void bch_keylist_pop_front(struct keylist *l) { - unsigned i; - char buf[80]; + l->top_p -= bkey_u64s(l->keys); - if (level && (!KEY_PTRS(k) || !KEY_SIZE(k) || KEY_DIRTY(k))) - goto bad; + memmove(l->keys, + bkey_next(l->keys), + bch_keylist_bytes(l)); +} - if (!level && KEY_SIZE(k) > KEY_OFFSET(k)) - goto bad; +/* Pointer validation */ - if (!KEY_SIZE(k)) - return true; +static bool __ptr_invalid(struct cache_set *c, const struct bkey *k) +{ + unsigned i; for (i = 0; i < KEY_PTRS(k); i++) if (ptr_available(c, k, i)) { @@ -98,13 +86,83 @@ bool __bch_ptr_invalid(struct cache_set *c, int level, const struct bkey *k) if (KEY_SIZE(k) + r > c->sb.bucket_size || bucket < ca->sb.first_bucket || bucket >= ca->sb.nbuckets) - goto bad; + return true; } return false; +} + +bool bch_btree_ptr_invalid(struct cache_set *c, const struct bkey *k) +{ + char buf[80]; + + if (!KEY_PTRS(k) || !KEY_SIZE(k) || KEY_DIRTY(k)) + goto bad; + + if (__ptr_invalid(c, k)) + goto bad; + + return false; +bad: + bch_bkey_to_text(buf, sizeof(buf), k); + cache_bug(c, "spotted btree ptr %s: %s", buf, bch_ptr_status(c, k)); + return true; +} + +bool bch_extent_ptr_invalid(struct cache_set *c, const struct bkey *k) +{ + char buf[80]; + + if (!KEY_SIZE(k)) + return true; + + if (KEY_SIZE(k) > KEY_OFFSET(k)) + goto bad; + + if (__ptr_invalid(c, k)) + goto bad; + + return false; bad: bch_bkey_to_text(buf, sizeof(buf), k); - cache_bug(c, "spotted bad key %s: %s", buf, bch_ptr_status(c, k)); + cache_bug(c, "spotted extent %s: %s", buf, bch_ptr_status(c, k)); + return true; +} + +static bool ptr_bad_expensive_checks(struct btree *b, const struct bkey *k, + unsigned ptr) +{ + struct bucket *g = PTR_BUCKET(b->c, k, ptr); + char buf[80]; + + if (mutex_trylock(&b->c->bucket_lock)) { + if (b->level) { + if (KEY_DIRTY(k) || + g->prio != BTREE_PRIO || + (b->c->gc_mark_valid && + GC_MARK(g) != GC_MARK_METADATA)) + goto err; + + } else { + if (g->prio == BTREE_PRIO) + goto err; + + if (KEY_DIRTY(k) && + b->c->gc_mark_valid && + GC_MARK(g) != GC_MARK_DIRTY) + goto err; + } + mutex_unlock(&b->c->bucket_lock); + } + + return false; +err: + mutex_unlock(&b->c->bucket_lock); + bch_bkey_to_text(buf, sizeof(buf), k); + btree_bug(b, +"inconsistent pointer %s: bucket %zu pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i", + buf, PTR_BUCKET_NR(b->c, k, ptr), atomic_read(&g->pin), + g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen); return true; } @@ -118,64 +176,29 @@ bool bch_ptr_bad(struct btree *b, const struct bkey *k) bch_ptr_invalid(b, k)) return true; - if (KEY_PTRS(k) && PTR_DEV(k, 0) == PTR_CHECK_DEV) - return true; + for (i = 0; i < KEY_PTRS(k); i++) { + if (!ptr_available(b->c, k, i)) + return true; - for (i = 0; i < KEY_PTRS(k); i++) - if (ptr_available(b->c, k, i)) { - g = PTR_BUCKET(b->c, k, i); - stale = ptr_stale(b->c, k, i); + g = PTR_BUCKET(b->c, k, i); + stale = ptr_stale(b->c, k, i); - btree_bug_on(stale > 96, b, - "key too stale: %i, need_gc %u", - stale, b->c->need_gc); + btree_bug_on(stale > 96, b, + "key too stale: %i, need_gc %u", + stale, b->c->need_gc); - btree_bug_on(stale && KEY_DIRTY(k) && KEY_SIZE(k), - b, "stale dirty pointer"); + btree_bug_on(stale && KEY_DIRTY(k) && KEY_SIZE(k), + b, "stale dirty pointer"); - if (stale) - return true; + if (stale) + return true; -#ifdef CONFIG_BCACHE_EDEBUG - if (!mutex_trylock(&b->c->bucket_lock)) - continue; - - if (b->level) { - if (KEY_DIRTY(k) || - g->prio != BTREE_PRIO || - (b->c->gc_mark_valid && - GC_MARK(g) != GC_MARK_METADATA)) - goto bug; - - } else { - if (g->prio == BTREE_PRIO) - goto bug; - - if (KEY_DIRTY(k) && - b->c->gc_mark_valid && - GC_MARK(g) != GC_MARK_DIRTY) - goto bug; - } - mutex_unlock(&b->c->bucket_lock); -#endif - } + if (expensive_debug_checks(b->c) && + ptr_bad_expensive_checks(b, k, i)) + return true; + } return false; -#ifdef CONFIG_BCACHE_EDEBUG -bug: - mutex_unlock(&b->c->bucket_lock); - - { - char buf[80]; - - bch_bkey_to_text(buf, sizeof(buf), k); - btree_bug(b, -"inconsistent pointer %s: bucket %zu pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i", - buf, PTR_BUCKET_NR(b->c, k, i), atomic_read(&g->pin), - g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen); - } - return true; -#endif } /* Key/pointer manipulation */ @@ -458,16 +481,8 @@ static struct bkey *table_to_bkey(struct bset_tree *t, unsigned cacheline) static inline uint64_t shrd128(uint64_t high, uint64_t low, uint8_t shift) { -#ifdef CONFIG_X86_64 - asm("shrd %[shift],%[high],%[low]" - : [low] "+Rm" (low) - : [high] "R" (high), - [shift] "ci" (shift) - : "cc"); -#else low >>= shift; low |= (high << 1) << (63U - shift); -#endif return low; } @@ -686,7 +701,7 @@ void bch_bset_init_next(struct btree *b) } else get_random_bytes(&i->seq, sizeof(uint64_t)); - i->magic = bset_magic(b->c); + i->magic = bset_magic(&b->c->sb); i->version = 0; i->keys = 0; @@ -824,16 +839,16 @@ struct bkey *__bch_bset_search(struct btree *b, struct bset_tree *t, } else i = bset_search_write_set(b, t, search); -#ifdef CONFIG_BCACHE_EDEBUG - BUG_ON(bset_written(b, t) && - i.l != t->data->start && - bkey_cmp(tree_to_prev_bkey(t, - inorder_to_tree(bkey_to_cacheline(t, i.l), t)), - search) > 0); + if (expensive_debug_checks(b->c)) { + BUG_ON(bset_written(b, t) && + i.l != t->data->start && + bkey_cmp(tree_to_prev_bkey(t, + inorder_to_tree(bkey_to_cacheline(t, i.l), t)), + search) > 0); - BUG_ON(i.r != end(t->data) && - bkey_cmp(i.r, search) <= 0); -#endif + BUG_ON(i.r != end(t->data) && + bkey_cmp(i.r, search) <= 0); + } while (likely(i.l != i.r) && bkey_cmp(i.l, search) <= 0) @@ -844,6 +859,13 @@ struct bkey *__bch_bset_search(struct btree *b, struct bset_tree *t, /* Btree iterator */ +/* + * Returns true if l > r - unless l == r, in which case returns true if l is + * older than r. + * + * Necessary for btree_sort_fixup() - if there are multiple keys that compare + * equal in different sets, we have to process them newest to oldest. + */ static inline bool btree_iter_cmp(struct btree_iter_set l, struct btree_iter_set r) { @@ -867,12 +889,16 @@ void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, } struct bkey *__bch_btree_iter_init(struct btree *b, struct btree_iter *iter, - struct bkey *search, struct bset_tree *start) + struct bkey *search, struct bset_tree *start) { struct bkey *ret = NULL; iter->size = ARRAY_SIZE(iter->data); iter->used = 0; +#ifdef CONFIG_BCACHE_DEBUG + iter->b = b; +#endif + for (; start <= &b->sets[b->nsets]; start++) { ret = bch_bset_search(b, start, search); bch_btree_iter_push(iter, ret, end(start->data)); @@ -887,6 +913,8 @@ struct bkey *bch_btree_iter_next(struct btree_iter *iter) struct bkey *ret = NULL; if (!btree_iter_end(iter)) { + bch_btree_iter_next_check(iter); + ret = iter->data->k; iter->data->k = bkey_next(iter->data->k); @@ -916,38 +944,47 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter, return ret; } -struct bkey *bch_next_recurse_key(struct btree *b, struct bkey *search) +/* Mergesort */ + +static void sort_key_next(struct btree_iter *iter, + struct btree_iter_set *i) { - struct btree_iter iter; + i->k = bkey_next(i->k); - bch_btree_iter_init(b, &iter, search); - return bch_btree_iter_next_filter(&iter, b, bch_ptr_bad); + if (i->k == i->end) + *i = iter->data[--iter->used]; } -/* Mergesort */ - static void btree_sort_fixup(struct btree_iter *iter) { while (iter->used > 1) { struct btree_iter_set *top = iter->data, *i = top + 1; - struct bkey *k; if (iter->used > 2 && btree_iter_cmp(i[0], i[1])) i++; - for (k = i->k; - k != i->end && bkey_cmp(top->k, &START_KEY(k)) > 0; - k = bkey_next(k)) - if (top->k > i->k) - __bch_cut_front(top->k, k); - else if (KEY_SIZE(k)) - bch_cut_back(&START_KEY(k), top->k); - - if (top->k < i->k || k == i->k) + if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0) break; - heap_sift(iter, i - top, btree_iter_cmp); + if (!KEY_SIZE(i->k)) { + sort_key_next(iter, i); + heap_sift(iter, i - top, btree_iter_cmp); + continue; + } + + if (top->k > i->k) { + if (bkey_cmp(top->k, i->k) >= 0) + sort_key_next(iter, i); + else + bch_cut_front(top->k, i->k); + + heap_sift(iter, i - top, btree_iter_cmp); + } else { + /* can't happen because of comparison func */ + BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k))); + bch_cut_back(&START_KEY(i->k), top->k); + } } } @@ -981,7 +1018,6 @@ static void btree_mergesort(struct btree *b, struct bset *out, out->keys = last ? (uint64_t *) bkey_next(last) - out->d : 0; pr_debug("sorted %i keys", out->keys); - bch_check_key_order(b, out); } static void __btree_sort(struct btree *b, struct btree_iter *iter, @@ -1012,7 +1048,7 @@ static void __btree_sort(struct btree *b, struct btree_iter *iter, * memcpy() */ - out->magic = bset_magic(b->c); + out->magic = bset_magic(&b->c->sb); out->seq = b->sets[0].data->seq; out->version = b->sets[0].data->version; swap(out, b->sets[0].data); @@ -1033,24 +1069,21 @@ static void __btree_sort(struct btree *b, struct btree_iter *iter, if (b->written) bset_build_written_tree(b); - if (!start) { - spin_lock(&b->c->sort_time_lock); + if (!start) bch_time_stats_update(&b->c->sort_time, start_time); - spin_unlock(&b->c->sort_time_lock); - } } void bch_btree_sort_partial(struct btree *b, unsigned start) { - size_t oldsize = 0, order = b->page_order, keys = 0; + size_t order = b->page_order, keys = 0; struct btree_iter iter; + int oldsize = bch_count_data(b); + __bch_btree_iter_init(b, &iter, NULL, &b->sets[start]); BUG_ON(b->sets[b->nsets].data == write_block(b) && (b->sets[b->nsets].size || b->nsets)); - if (b->written) - oldsize = bch_count_data(b); if (start) { unsigned i; @@ -1066,7 +1099,7 @@ void bch_btree_sort_partial(struct btree *b, unsigned start) __btree_sort(b, &iter, start, order, false); - EBUG_ON(b->written && bch_count_data(b) != oldsize); + EBUG_ON(b->written && oldsize >= 0 && bch_count_data(b) != oldsize); } void bch_btree_sort_and_fix_extents(struct btree *b, struct btree_iter *iter) @@ -1084,9 +1117,7 @@ void bch_btree_sort_into(struct btree *b, struct btree *new) btree_mergesort(b, new->sets->data, &iter, false, true); - spin_lock(&b->c->sort_time_lock); bch_time_stats_update(&b->c->sort_time, start_time); - spin_unlock(&b->c->sort_time_lock); bkey_copy_key(&new->key, &b->key); new->sets->size = 0; @@ -1131,16 +1162,16 @@ out: /* Sysfs stuff */ struct bset_stats { + struct btree_op op; size_t nodes; size_t sets_written, sets_unwritten; size_t bytes_written, bytes_unwritten; size_t floats, failed; }; -static int bch_btree_bset_stats(struct btree *b, struct btree_op *op, - struct bset_stats *stats) +static int btree_bset_stats(struct btree_op *op, struct btree *b) { - struct bkey *k; + struct bset_stats *stats = container_of(op, struct bset_stats, op); unsigned i; stats->nodes++; @@ -1165,30 +1196,19 @@ static int bch_btree_bset_stats(struct btree *b, struct btree_op *op, } } - if (b->level) { - struct btree_iter iter; - - for_each_key_filter(b, k, &iter, bch_ptr_bad) { - int ret = btree(bset_stats, k, b, op, stats); - if (ret) - return ret; - } - } - - return 0; + return MAP_CONTINUE; } int bch_bset_print_stats(struct cache_set *c, char *buf) { - struct btree_op op; struct bset_stats t; int ret; - bch_btree_op_init_stack(&op); memset(&t, 0, sizeof(struct bset_stats)); + bch_btree_op_init(&t.op, -1); - ret = btree_root(bset_stats, c, &op, &t); - if (ret) + ret = bch_btree_map_nodes(&t.op, c, &ZERO_KEY, btree_bset_stats); + if (ret < 0) return ret; return snprintf(buf, PAGE_SIZE, diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index ae115a2..1d3c24f 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -148,6 +148,9 @@ struct btree_iter { size_t size, used; +#ifdef CONFIG_BCACHE_DEBUG + struct btree *b; +#endif struct btree_iter_set { struct bkey *k, *end; } data[MAX_BSETS]; @@ -193,54 +196,26 @@ static __always_inline int64_t bkey_cmp(const struct bkey *l, : (int64_t) KEY_OFFSET(l) - (int64_t) KEY_OFFSET(r); } -static inline size_t bkey_u64s(const struct bkey *k) -{ - BUG_ON(KEY_CSUM(k) > 1); - return 2 + KEY_PTRS(k) + (KEY_CSUM(k) ? 1 : 0); -} - -static inline size_t bkey_bytes(const struct bkey *k) -{ - return bkey_u64s(k) * sizeof(uint64_t); -} - -static inline void bkey_copy(struct bkey *dest, const struct bkey *src) -{ - memcpy(dest, src, bkey_bytes(src)); -} - -static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src) -{ - if (!src) - src = &KEY(0, 0, 0); - - SET_KEY_INODE(dest, KEY_INODE(src)); - SET_KEY_OFFSET(dest, KEY_OFFSET(src)); -} - -static inline struct bkey *bkey_next(const struct bkey *k) -{ - uint64_t *d = (void *) k; - return (struct bkey *) (d + bkey_u64s(k)); -} - /* Keylists */ struct keylist { - struct bkey *top; union { - uint64_t *list; - struct bkey *bottom; + struct bkey *keys; + uint64_t *keys_p; + }; + union { + struct bkey *top; + uint64_t *top_p; }; /* Enough room for btree_split's keys without realloc */ #define KEYLIST_INLINE 16 - uint64_t d[KEYLIST_INLINE]; + uint64_t inline_keys[KEYLIST_INLINE]; }; static inline void bch_keylist_init(struct keylist *l) { - l->top = (void *) (l->list = l->d); + l->top_p = l->keys_p = l->inline_keys; } static inline void bch_keylist_push(struct keylist *l) @@ -256,17 +231,32 @@ static inline void bch_keylist_add(struct keylist *l, struct bkey *k) static inline bool bch_keylist_empty(struct keylist *l) { - return l->top == (void *) l->list; + return l->top == l->keys; +} + +static inline void bch_keylist_reset(struct keylist *l) +{ + l->top = l->keys; } static inline void bch_keylist_free(struct keylist *l) { - if (l->list != l->d) - kfree(l->list); + if (l->keys_p != l->inline_keys) + kfree(l->keys_p); +} + +static inline size_t bch_keylist_nkeys(struct keylist *l) +{ + return l->top_p - l->keys_p; +} + +static inline size_t bch_keylist_bytes(struct keylist *l) +{ + return bch_keylist_nkeys(l) * sizeof(uint64_t); } -void bch_keylist_copy(struct keylist *, struct keylist *); struct bkey *bch_keylist_pop(struct keylist *); +void bch_keylist_pop_front(struct keylist *); int bch_keylist_realloc(struct keylist *, int, struct cache_set *); void bch_bkey_copy_single_ptr(struct bkey *, const struct bkey *, @@ -287,7 +277,9 @@ static inline bool bch_cut_back(const struct bkey *where, struct bkey *k) } const char *bch_ptr_status(struct cache_set *, const struct bkey *); -bool __bch_ptr_invalid(struct cache_set *, int level, const struct bkey *); +bool bch_btree_ptr_invalid(struct cache_set *, const struct bkey *); +bool bch_extent_ptr_invalid(struct cache_set *, const struct bkey *); + bool bch_ptr_bad(struct btree *, const struct bkey *); static inline uint8_t gen_after(uint8_t a, uint8_t b) @@ -311,7 +303,6 @@ static inline bool ptr_available(struct cache_set *c, const struct bkey *k, typedef bool (*ptr_filter_fn)(struct btree *, const struct bkey *); -struct bkey *bch_next_recurse_key(struct btree *, struct bkey *); struct bkey *bch_btree_iter_next(struct btree_iter *); struct bkey *bch_btree_iter_next_filter(struct btree_iter *, struct btree *, ptr_filter_fn); @@ -361,12 +352,30 @@ void bch_bset_fix_lookup_table(struct btree *, struct bkey *); struct bkey *__bch_bset_search(struct btree *, struct bset_tree *, const struct bkey *); +/* + * Returns the first key that is strictly greater than search + */ static inline struct bkey *bch_bset_search(struct btree *b, struct bset_tree *t, const struct bkey *search) { return search ? __bch_bset_search(b, t, search) : t->data->start; } +#define PRECEDING_KEY(_k) \ +({ \ + struct bkey *_ret = NULL; \ + \ + if (KEY_INODE(_k) || KEY_OFFSET(_k)) { \ + _ret = &KEY(KEY_INODE(_k), KEY_OFFSET(_k), 0); \ + \ + if (!_ret->low) \ + _ret->high--; \ + _ret->low--; \ + } \ + \ + _ret; \ +}) + bool bch_bkey_try_merge(struct btree *, struct bkey *, struct bkey *); void bch_btree_sort_lazy(struct btree *); void bch_btree_sort_into(struct btree *, struct btree *); diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index ee37288..5e2765a 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -23,12 +23,13 @@ #include "bcache.h" #include "btree.h" #include "debug.h" -#include "request.h" #include "writeback.h" #include <linux/slab.h> #include <linux/bitops.h> +#include <linux/freezer.h> #include <linux/hash.h> +#include <linux/kthread.h> #include <linux/prefetch.h> #include <linux/random.h> #include <linux/rcupdate.h> @@ -88,15 +89,13 @@ * Test module load/unload */ -static const char * const op_types[] = { - "insert", "replace" +enum { + BTREE_INSERT_STATUS_INSERT, + BTREE_INSERT_STATUS_BACK_MERGE, + BTREE_INSERT_STATUS_OVERWROTE, + BTREE_INSERT_STATUS_FRONT_MERGE, }; -static const char *op_type(struct btree_op *op) -{ - return op_types[op->type]; -} - #define MAX_NEED_GC 64 #define MAX_SAVE_PRIO 72 @@ -105,23 +104,89 @@ static const char *op_type(struct btree_op *op) #define PTR_HASH(c, k) \ (((k)->ptr[0] >> c->bucket_bits) | PTR_GEN(k, 0)) -struct workqueue_struct *bch_gc_wq; static struct workqueue_struct *btree_io_wq; -void bch_btree_op_init_stack(struct btree_op *op) +static inline bool should_split(struct btree *b) { - memset(op, 0, sizeof(struct btree_op)); - closure_init_stack(&op->cl); - op->lock = -1; - bch_keylist_init(&op->keys); + struct bset *i = write_block(b); + return b->written >= btree_blocks(b) || + (b->written + __set_blocks(i, i->keys + 15, b->c) + > btree_blocks(b)); } +#define insert_lock(s, b) ((b)->level <= (s)->lock) + +/* + * These macros are for recursing down the btree - they handle the details of + * locking and looking up nodes in the cache for you. They're best treated as + * mere syntax when reading code that uses them. + * + * op->lock determines whether we take a read or a write lock at a given depth. + * If you've got a read lock and find that you need a write lock (i.e. you're + * going to have to split), set op->lock and return -EINTR; btree_root() will + * call you again and you'll have the correct lock. + */ + +/** + * btree - recurse down the btree on a specified key + * @fn: function to call, which will be passed the child node + * @key: key to recurse on + * @b: parent btree node + * @op: pointer to struct btree_op + */ +#define btree(fn, key, b, op, ...) \ +({ \ + int _r, l = (b)->level - 1; \ + bool _w = l <= (op)->lock; \ + struct btree *_child = bch_btree_node_get((b)->c, key, l, _w); \ + if (!IS_ERR(_child)) { \ + _child->parent = (b); \ + _r = bch_btree_ ## fn(_child, op, ##__VA_ARGS__); \ + rw_unlock(_w, _child); \ + } else \ + _r = PTR_ERR(_child); \ + _r; \ +}) + +/** + * btree_root - call a function on the root of the btree + * @fn: function to call, which will be passed the child node + * @c: cache set + * @op: pointer to struct btree_op + */ +#define btree_root(fn, c, op, ...) \ +({ \ + int _r = -EINTR; \ + do { \ + struct btree *_b = (c)->root; \ + bool _w = insert_lock(op, _b); \ + rw_lock(_w, _b, _b->level); \ + if (_b == (c)->root && \ + _w == insert_lock(op, _b)) { \ + _b->parent = NULL; \ + _r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__); \ + } \ + rw_unlock(_w, _b); \ + bch_cannibalize_unlock(c); \ + if (_r == -ENOSPC) { \ + wait_event((c)->try_wait, \ + !(c)->try_harder); \ + _r = -EINTR; \ + } \ + } while (_r == -EINTR); \ + \ + _r; \ +}) + /* Btree key manipulation */ -static void bkey_put(struct cache_set *c, struct bkey *k, int level) +void bkey_put(struct cache_set *c, struct bkey *k) { - if ((level && KEY_OFFSET(k)) || !level) - __bkey_put(c, k); + unsigned i; + + for (i = 0; i < KEY_PTRS(k); i++) + if (ptr_available(c, k, i)) + atomic_dec_bug(&PTR_BUCKET(c, k, i)->pin); } /* Btree IO */ @@ -145,6 +210,10 @@ static void bch_btree_node_read_done(struct btree *b) iter->size = b->c->sb.bucket_size / b->c->sb.block_size; iter->used = 0; +#ifdef CONFIG_BCACHE_DEBUG + iter->b = b; +#endif + if (!i->seq) goto err; @@ -160,7 +229,7 @@ static void bch_btree_node_read_done(struct btree *b) goto err; err = "bad magic"; - if (i->magic != bset_magic(b->c)) + if (i->magic != bset_magic(&b->c->sb)) goto err; err = "bad checksum"; @@ -248,14 +317,11 @@ void bch_btree_node_read(struct btree *b) goto err; bch_btree_node_read_done(b); - - spin_lock(&b->c->btree_read_time_lock); bch_time_stats_update(&b->c->btree_read_time, start_time); - spin_unlock(&b->c->btree_read_time_lock); return; err: - bch_cache_set_error(b->c, "io error reading bucket %lu", + bch_cache_set_error(b->c, "io error reading bucket %zu", PTR_BUCKET_NR(b->c, &b->key, 0)); } @@ -327,7 +393,7 @@ static void do_btree_node_write(struct btree *b) b->bio = bch_bbio_alloc(b->c); b->bio->bi_end_io = btree_node_write_endio; - b->bio->bi_private = &b->io.cl; + b->bio->bi_private = cl; b->bio->bi_rw = REQ_META|WRITE_SYNC|REQ_FUA; b->bio->bi_size = set_blocks(i, b->c) * block_bytes(b->c); bch_bio_map(b->bio, i); @@ -383,7 +449,7 @@ void bch_btree_node_write(struct btree *b, struct closure *parent) BUG_ON(b->written >= btree_blocks(b)); BUG_ON(b->written && !i->keys); BUG_ON(b->sets->data->seq != i->seq); - bch_check_key_order(b, i); + bch_check_keys(b, "writing"); cancel_delayed_work(&b->work); @@ -405,6 +471,15 @@ void bch_btree_node_write(struct btree *b, struct closure *parent) bch_bset_init_next(b); } +static void bch_btree_node_write_sync(struct btree *b) +{ + struct closure cl; + + closure_init_stack(&cl); + bch_btree_node_write(b, &cl); + closure_sync(&cl); +} + static void btree_node_write_work(struct work_struct *w) { struct btree *b = container_of(to_delayed_work(w), struct btree, work); @@ -416,7 +491,7 @@ static void btree_node_write_work(struct work_struct *w) rw_unlock(true, b); } -static void bch_btree_leaf_dirty(struct btree *b, struct btree_op *op) +static void bch_btree_leaf_dirty(struct btree *b, atomic_t *journal_ref) { struct bset *i = b->sets[b->nsets].data; struct btree_write *w = btree_current_write(b); @@ -429,15 +504,15 @@ static void bch_btree_leaf_dirty(struct btree *b, struct btree_op *op) set_btree_node_dirty(b); - if (op && op->journal) { + if (journal_ref) { if (w->journal && - journal_pin_cmp(b->c, w, op)) { + journal_pin_cmp(b->c, w->journal, journal_ref)) { atomic_dec_bug(w->journal); w->journal = NULL; } if (!w->journal) { - w->journal = op->journal; + w->journal = journal_ref; atomic_inc(w->journal); } } @@ -566,58 +641,52 @@ static struct btree *mca_bucket_alloc(struct cache_set *c, return b; } -static int mca_reap(struct btree *b, struct closure *cl, unsigned min_order) +static int mca_reap(struct btree *b, unsigned min_order, bool flush) { + struct closure cl; + + closure_init_stack(&cl); lockdep_assert_held(&b->c->bucket_lock); if (!down_write_trylock(&b->lock)) return -ENOMEM; - if (b->page_order < min_order) { + BUG_ON(btree_node_dirty(b) && !b->sets[0].data); + + if (b->page_order < min_order || + (!flush && + (btree_node_dirty(b) || + atomic_read(&b->io.cl.remaining) != -1))) { rw_unlock(true, b); return -ENOMEM; } - BUG_ON(btree_node_dirty(b) && !b->sets[0].data); - - if (cl && btree_node_dirty(b)) - bch_btree_node_write(b, NULL); + if (btree_node_dirty(b)) + bch_btree_node_write_sync(b); - if (cl) - closure_wait_event_async(&b->io.wait, cl, - atomic_read(&b->io.cl.remaining) == -1); - - if (btree_node_dirty(b) || - !closure_is_unlocked(&b->io.cl) || - work_pending(&b->work.work)) { - rw_unlock(true, b); - return -EAGAIN; - } + /* wait for any in flight btree write */ + closure_wait_event(&b->io.wait, &cl, + atomic_read(&b->io.cl.remaining) == -1); return 0; } -static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long bch_mca_scan(struct shrinker *shrink, + struct shrink_control *sc) { struct cache_set *c = container_of(shrink, struct cache_set, shrink); struct btree *b, *t; unsigned long i, nr = sc->nr_to_scan; + unsigned long freed = 0; if (c->shrinker_disabled) - return 0; + return SHRINK_STOP; if (c->try_harder) - return 0; - - /* - * If nr == 0, we're supposed to return the number of items we have - * cached. Not allowed to return -1. - */ - if (!nr) - return mca_can_free(c) * c->btree_pages; + return SHRINK_STOP; /* Return -1 if we can't do anything right now */ - if (sc->gfp_mask & __GFP_WAIT) + if (sc->gfp_mask & __GFP_IO) mutex_lock(&c->bucket_lock); else if (!mutex_trylock(&c->bucket_lock)) return -1; @@ -634,14 +703,14 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc) i = 0; list_for_each_entry_safe(b, t, &c->btree_cache_freeable, list) { - if (!nr) + if (freed >= nr) break; if (++i > 3 && - !mca_reap(b, NULL, 0)) { + !mca_reap(b, 0, false)) { mca_data_free(b); rw_unlock(true, b); - --nr; + freed++; } } @@ -652,23 +721,36 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc) if (list_empty(&c->btree_cache)) goto out; - for (i = 0; nr && i < c->bucket_cache_used; i++) { + for (i = 0; (nr--) && i < c->bucket_cache_used; i++) { b = list_first_entry(&c->btree_cache, struct btree, list); list_rotate_left(&c->btree_cache); if (!b->accessed && - !mca_reap(b, NULL, 0)) { + !mca_reap(b, 0, false)) { mca_bucket_free(b); mca_data_free(b); rw_unlock(true, b); - --nr; + freed++; } else b->accessed = 0; } out: - nr = mca_can_free(c) * c->btree_pages; mutex_unlock(&c->bucket_lock); - return nr; + return freed; +} + +static unsigned long bch_mca_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct cache_set *c = container_of(shrink, struct cache_set, shrink); + + if (c->shrinker_disabled) + return 0; + + if (c->try_harder) + return 0; + + return mca_can_free(c) * c->btree_pages; } void bch_btree_cache_free(struct cache_set *c) @@ -715,12 +797,9 @@ int bch_btree_cache_alloc(struct cache_set *c) { unsigned i; - /* XXX: doesn't check for errors */ - - closure_init_unlocked(&c->gc); - for (i = 0; i < mca_reserve(c); i++) - mca_bucket_alloc(c, &ZERO_KEY, GFP_KERNEL); + if (!mca_bucket_alloc(c, &ZERO_KEY, GFP_KERNEL)) + return -ENOMEM; list_splice_init(&c->btree_cache, &c->btree_cache_freeable); @@ -737,7 +816,8 @@ int bch_btree_cache_alloc(struct cache_set *c) c->verify_data = NULL; #endif - c->shrink.shrink = bch_mca_shrink; + c->shrink.count_objects = bch_mca_count; + c->shrink.scan_objects = bch_mca_scan; c->shrink.seeks = 4; c->shrink.batch = c->btree_pages * 2; register_shrinker(&c->shrink); @@ -766,52 +846,27 @@ out: return b; } -static struct btree *mca_cannibalize(struct cache_set *c, struct bkey *k, - int level, struct closure *cl) +static struct btree *mca_cannibalize(struct cache_set *c, struct bkey *k) { - int ret = -ENOMEM; - struct btree *i; + struct btree *b; trace_bcache_btree_cache_cannibalize(c); - if (!cl) - return ERR_PTR(-ENOMEM); - - /* - * Trying to free up some memory - i.e. reuse some btree nodes - may - * require initiating IO to flush the dirty part of the node. If we're - * running under generic_make_request(), that IO will never finish and - * we would deadlock. Returning -EAGAIN causes the cache lookup code to - * punt to workqueue and retry. - */ - if (current->bio_list) - return ERR_PTR(-EAGAIN); + if (!c->try_harder) { + c->try_harder = current; + c->try_harder_start = local_clock(); + } else if (c->try_harder != current) + return ERR_PTR(-ENOSPC); - if (c->try_harder && c->try_harder != cl) { - closure_wait_event_async(&c->try_wait, cl, !c->try_harder); - return ERR_PTR(-EAGAIN); - } - - c->try_harder = cl; - c->try_harder_start = local_clock(); -retry: - list_for_each_entry_reverse(i, &c->btree_cache, list) { - int r = mca_reap(i, cl, btree_order(k)); - if (!r) - return i; - if (r != -ENOMEM) - ret = r; - } + list_for_each_entry_reverse(b, &c->btree_cache, list) + if (!mca_reap(b, btree_order(k), false)) + return b; - if (ret == -EAGAIN && - closure_blocking(cl)) { - mutex_unlock(&c->bucket_lock); - closure_sync(cl); - mutex_lock(&c->bucket_lock); - goto retry; - } + list_for_each_entry_reverse(b, &c->btree_cache, list) + if (!mca_reap(b, btree_order(k), true)) + return b; - return ERR_PTR(ret); + return ERR_PTR(-ENOMEM); } /* @@ -820,20 +875,21 @@ retry: * cannibalize_bucket() will take. This means every time we unlock the root of * the btree, we need to release this lock if we have it held. */ -void bch_cannibalize_unlock(struct cache_set *c, struct closure *cl) +static void bch_cannibalize_unlock(struct cache_set *c) { - if (c->try_harder == cl) { + if (c->try_harder == current) { bch_time_stats_update(&c->try_harder_time, c->try_harder_start); c->try_harder = NULL; - __closure_wake_up(&c->try_wait); + wake_up(&c->try_wait); } } -static struct btree *mca_alloc(struct cache_set *c, struct bkey *k, - int level, struct closure *cl) +static struct btree *mca_alloc(struct cache_set *c, struct bkey *k, int level) { struct btree *b; + BUG_ON(current->bio_list); + lockdep_assert_held(&c->bucket_lock); if (mca_find(c, k)) @@ -843,14 +899,14 @@ static struct btree *mca_alloc(struct cache_set *c, struct bkey *k, * the list. Check if there's any freed nodes there: */ list_for_each_entry(b, &c->btree_cache_freeable, list) - if (!mca_reap(b, NULL, btree_order(k))) + if (!mca_reap(b, btree_order(k), false)) goto out; /* We never free struct btree itself, just the memory that holds the on * disk node. Check the freed list before allocating a new one: */ list_for_each_entry(b, &c->btree_cache_freed, list) - if (!mca_reap(b, NULL, 0)) { + if (!mca_reap(b, 0, false)) { mca_data_alloc(b, k, __GFP_NOWARN|GFP_NOIO); if (!b->sets[0].data) goto err; @@ -875,6 +931,7 @@ out: lock_set_subclass(&b->lock.dep_map, level + 1, _THIS_IP_); b->level = level; + b->parent = (void *) ~0UL; mca_reinit(b); @@ -883,7 +940,7 @@ err: if (b) rw_unlock(true, b); - b = mca_cannibalize(c, k, level, cl); + b = mca_cannibalize(c, k); if (!IS_ERR(b)) goto out; @@ -894,17 +951,15 @@ err: * bch_btree_node_get - find a btree node in the cache and lock it, reading it * in from disk if necessary. * - * If IO is necessary, it uses the closure embedded in struct btree_op to wait; - * if that closure is in non blocking mode, will return -EAGAIN. + * If IO is necessary and running under generic_make_request, returns -EAGAIN. * * The btree node will have either a read or a write lock held, depending on * level and op->lock. */ struct btree *bch_btree_node_get(struct cache_set *c, struct bkey *k, - int level, struct btree_op *op) + int level, bool write) { int i = 0; - bool write = level <= op->lock; struct btree *b; BUG_ON(level < 0); @@ -916,7 +971,7 @@ retry: return ERR_PTR(-EAGAIN); mutex_lock(&c->bucket_lock); - b = mca_alloc(c, k, level, &op->cl); + b = mca_alloc(c, k, level); mutex_unlock(&c->bucket_lock); if (!b) @@ -962,7 +1017,7 @@ static void btree_node_prefetch(struct cache_set *c, struct bkey *k, int level) struct btree *b; mutex_lock(&c->bucket_lock); - b = mca_alloc(c, k, level, NULL); + b = mca_alloc(c, k, level); mutex_unlock(&c->bucket_lock); if (!IS_ERR_OR_NULL(b)) { @@ -973,17 +1028,12 @@ static void btree_node_prefetch(struct cache_set *c, struct bkey *k, int level) /* Btree alloc */ -static void btree_node_free(struct btree *b, struct btree_op *op) +static void btree_node_free(struct btree *b) { unsigned i; trace_bcache_btree_node_free(b); - /* - * The BUG_ON() in btree_node_get() implies that we must have a write - * lock on parent to free or even invalidate a node - */ - BUG_ON(op->lock <= b->level); BUG_ON(b == b->c->root); if (btree_node_dirty(b)) @@ -1006,27 +1056,26 @@ static void btree_node_free(struct btree *b, struct btree_op *op) mutex_unlock(&b->c->bucket_lock); } -struct btree *bch_btree_node_alloc(struct cache_set *c, int level, - struct closure *cl) +struct btree *bch_btree_node_alloc(struct cache_set *c, int level, bool wait) { BKEY_PADDED(key) k; struct btree *b = ERR_PTR(-EAGAIN); mutex_lock(&c->bucket_lock); retry: - if (__bch_bucket_alloc_set(c, WATERMARK_METADATA, &k.key, 1, cl)) + if (__bch_bucket_alloc_set(c, WATERMARK_METADATA, &k.key, 1, wait)) goto err; + bkey_put(c, &k.key); SET_KEY_SIZE(&k.key, c->btree_pages * PAGE_SECTORS); - b = mca_alloc(c, &k.key, level, cl); + b = mca_alloc(c, &k.key, level); if (IS_ERR(b)) goto err_free; if (!b) { cache_bug(c, "Tried to allocate bucket that was in btree cache"); - __bkey_put(c, &k.key); goto retry; } @@ -1039,7 +1088,6 @@ retry: return b; err_free: bch_bucket_free(c, &k.key); - __bkey_put(c, &k.key); err: mutex_unlock(&c->bucket_lock); @@ -1047,16 +1095,31 @@ err: return b; } -static struct btree *btree_node_alloc_replacement(struct btree *b, - struct closure *cl) +static struct btree *btree_node_alloc_replacement(struct btree *b, bool wait) { - struct btree *n = bch_btree_node_alloc(b->c, b->level, cl); + struct btree *n = bch_btree_node_alloc(b->c, b->level, wait); if (!IS_ERR_OR_NULL(n)) bch_btree_sort_into(b, n); return n; } +static void make_btree_freeing_key(struct btree *b, struct bkey *k) +{ + unsigned i; + + bkey_copy(k, &b->key); + bkey_copy_key(k, &ZERO_KEY); + + for (i = 0; i < KEY_PTRS(k); i++) { + uint8_t g = PTR_BUCKET(b->c, k, i)->gen + 1; + + SET_PTR_GEN(k, i, g); + } + + atomic_inc(&b->c->prio_blocked); +} + /* Garbage collection */ uint8_t __bch_btree_mark_key(struct cache_set *c, int level, struct bkey *k) @@ -1110,12 +1173,10 @@ uint8_t __bch_btree_mark_key(struct cache_set *c, int level, struct bkey *k) #define btree_mark_key(b, k) __bch_btree_mark_key(b->c, b->level, k) -static int btree_gc_mark_node(struct btree *b, unsigned *keys, - struct gc_stat *gc) +static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc) { uint8_t stale = 0; - unsigned last_dev = -1; - struct bcache_device *d = NULL; + unsigned keys = 0, good_keys = 0; struct bkey *k; struct btree_iter iter; struct bset_tree *t; @@ -1123,27 +1184,17 @@ static int btree_gc_mark_node(struct btree *b, unsigned *keys, gc->nodes++; for_each_key_filter(b, k, &iter, bch_ptr_invalid) { - if (last_dev != KEY_INODE(k)) { - last_dev = KEY_INODE(k); - - d = KEY_INODE(k) < b->c->nr_uuids - ? b->c->devices[last_dev] - : NULL; - } - stale = max(stale, btree_mark_key(b, k)); + keys++; if (bch_ptr_bad(b, k)) continue; - *keys += bkey_u64s(k); - gc->key_bytes += bkey_u64s(k); gc->nkeys++; + good_keys++; gc->data += KEY_SIZE(k); - if (KEY_DIRTY(k)) - gc->dirty += KEY_SIZE(k); } for (t = b->sets; t <= &b->sets[b->nsets]; t++) @@ -1152,78 +1203,74 @@ static int btree_gc_mark_node(struct btree *b, unsigned *keys, bkey_cmp(&b->key, &t->end) < 0, b, "found short btree key in gc"); - return stale; -} - -static struct btree *btree_gc_alloc(struct btree *b, struct bkey *k, - struct btree_op *op) -{ - /* - * We block priorities from being written for the duration of garbage - * collection, so we can't sleep in btree_alloc() -> - * bch_bucket_alloc_set(), or we'd risk deadlock - so we don't pass it - * our closure. - */ - struct btree *n = btree_node_alloc_replacement(b, NULL); - - if (!IS_ERR_OR_NULL(n)) { - swap(b, n); - __bkey_put(b->c, &b->key); + if (b->c->gc_always_rewrite) + return true; - memcpy(k->ptr, b->key.ptr, - sizeof(uint64_t) * KEY_PTRS(&b->key)); + if (stale > 10) + return true; - btree_node_free(n, op); - up_write(&n->lock); - } + if ((keys - good_keys) * 2 > keys) + return true; - return b; + return false; } -/* - * Leaving this at 2 until we've got incremental garbage collection done; it - * could be higher (and has been tested with 4) except that garbage collection - * could take much longer, adversely affecting latency. - */ -#define GC_MERGE_NODES 2U +#define GC_MERGE_NODES 4U struct gc_merge_info { struct btree *b; - struct bkey *k; unsigned keys; }; -static void btree_gc_coalesce(struct btree *b, struct btree_op *op, - struct gc_stat *gc, struct gc_merge_info *r) +static int bch_btree_insert_node(struct btree *, struct btree_op *, + struct keylist *, atomic_t *, struct bkey *); + +static int btree_gc_coalesce(struct btree *b, struct btree_op *op, + struct keylist *keylist, struct gc_stat *gc, + struct gc_merge_info *r) { - unsigned nodes = 0, keys = 0, blocks; - int i; + unsigned i, nodes = 0, keys = 0, blocks; + struct btree *new_nodes[GC_MERGE_NODES]; + struct closure cl; + struct bkey *k; + + memset(new_nodes, 0, sizeof(new_nodes)); + closure_init_stack(&cl); - while (nodes < GC_MERGE_NODES && r[nodes].b) + while (nodes < GC_MERGE_NODES && !IS_ERR_OR_NULL(r[nodes].b)) keys += r[nodes++].keys; blocks = btree_default_blocks(b->c) * 2 / 3; if (nodes < 2 || __set_blocks(b->sets[0].data, keys, b->c) > blocks * (nodes - 1)) - return; - - for (i = nodes - 1; i >= 0; --i) { - if (r[i].b->written) - r[i].b = btree_gc_alloc(r[i].b, r[i].k, op); + return 0; - if (r[i].b->written) - return; + for (i = 0; i < nodes; i++) { + new_nodes[i] = btree_node_alloc_replacement(r[i].b, false); + if (IS_ERR_OR_NULL(new_nodes[i])) + goto out_nocoalesce; } for (i = nodes - 1; i > 0; --i) { - struct bset *n1 = r[i].b->sets->data; - struct bset *n2 = r[i - 1].b->sets->data; + struct bset *n1 = new_nodes[i]->sets->data; + struct bset *n2 = new_nodes[i - 1]->sets->data; struct bkey *k, *last = NULL; keys = 0; - if (i == 1) { + if (i > 1) { + for (k = n2->start; + k < end(n2); + k = bkey_next(k)) { + if (__set_blocks(n1, n1->keys + keys + + bkey_u64s(k), b->c) > blocks) + break; + + last = k; + keys += bkey_u64s(k); + } + } else { /* * Last node we're not getting rid of - we're getting * rid of the node at r[0]. Have to try and fit all of @@ -1232,37 +1279,27 @@ static void btree_gc_coalesce(struct btree *b, struct btree_op *op, * length keys (shouldn't be possible in practice, * though) */ - if (__set_blocks(n1, n1->keys + r->keys, - b->c) > btree_blocks(r[i].b)) - return; + if (__set_blocks(n1, n1->keys + n2->keys, + b->c) > btree_blocks(new_nodes[i])) + goto out_nocoalesce; keys = n2->keys; + /* Take the key of the node we're getting rid of */ last = &r->b->key; - } else - for (k = n2->start; - k < end(n2); - k = bkey_next(k)) { - if (__set_blocks(n1, n1->keys + keys + - bkey_u64s(k), b->c) > blocks) - break; - - last = k; - keys += bkey_u64s(k); - } + } BUG_ON(__set_blocks(n1, n1->keys + keys, - b->c) > btree_blocks(r[i].b)); + b->c) > btree_blocks(new_nodes[i])); - if (last) { - bkey_copy_key(&r[i].b->key, last); - bkey_copy_key(r[i].k, last); - } + if (last) + bkey_copy_key(&new_nodes[i]->key, last); memcpy(end(n1), n2->start, (void *) node(n2, keys) - (void *) n2->start); n1->keys += keys; + r[i].keys = n1->keys; memmove(n2->start, node(n2, keys), @@ -1270,95 +1307,176 @@ static void btree_gc_coalesce(struct btree *b, struct btree_op *op, n2->keys -= keys; - r[i].keys = n1->keys; - r[i - 1].keys = n2->keys; + if (bch_keylist_realloc(keylist, + KEY_PTRS(&new_nodes[i]->key), b->c)) + goto out_nocoalesce; + + bch_btree_node_write(new_nodes[i], &cl); + bch_keylist_add(keylist, &new_nodes[i]->key); } - btree_node_free(r->b, op); - up_write(&r->b->lock); + for (i = 0; i < nodes; i++) { + if (bch_keylist_realloc(keylist, KEY_PTRS(&r[i].b->key), b->c)) + goto out_nocoalesce; - trace_bcache_btree_gc_coalesce(nodes); + make_btree_freeing_key(r[i].b, keylist->top); + bch_keylist_push(keylist); + } + + /* We emptied out this node */ + BUG_ON(new_nodes[0]->sets->data->keys); + btree_node_free(new_nodes[0]); + rw_unlock(true, new_nodes[0]); + + closure_sync(&cl); + + for (i = 0; i < nodes; i++) { + btree_node_free(r[i].b); + rw_unlock(true, r[i].b); + r[i].b = new_nodes[i]; + } + + bch_btree_insert_node(b, op, keylist, NULL, NULL); + BUG_ON(!bch_keylist_empty(keylist)); + + memmove(r, r + 1, sizeof(r[0]) * (nodes - 1)); + r[nodes - 1].b = ERR_PTR(-EINTR); + + trace_bcache_btree_gc_coalesce(nodes); gc->nodes--; - nodes--; - memmove(&r[0], &r[1], sizeof(struct gc_merge_info) * nodes); - memset(&r[nodes], 0, sizeof(struct gc_merge_info)); + /* Invalidated our iterator */ + return -EINTR; + +out_nocoalesce: + closure_sync(&cl); + + while ((k = bch_keylist_pop(keylist))) + if (!bkey_cmp(k, &ZERO_KEY)) + atomic_dec(&b->c->prio_blocked); + + for (i = 0; i < nodes; i++) + if (!IS_ERR_OR_NULL(new_nodes[i])) { + btree_node_free(new_nodes[i]); + rw_unlock(true, new_nodes[i]); + } + return 0; } -static int btree_gc_recurse(struct btree *b, struct btree_op *op, - struct closure *writes, struct gc_stat *gc) +static unsigned btree_gc_count_keys(struct btree *b) { - void write(struct btree *r) - { - if (!r->written) - bch_btree_node_write(r, &op->cl); - else if (btree_node_dirty(r)) - bch_btree_node_write(r, writes); + struct bkey *k; + struct btree_iter iter; + unsigned ret = 0; - up_write(&r->lock); - } + for_each_key_filter(b, k, &iter, bch_ptr_bad) + ret += bkey_u64s(k); - int ret = 0, stale; + return ret; +} + +static int btree_gc_recurse(struct btree *b, struct btree_op *op, + struct closure *writes, struct gc_stat *gc) +{ unsigned i; + int ret = 0; + bool should_rewrite; + struct btree *n; + struct bkey *k; + struct keylist keys; + struct btree_iter iter; struct gc_merge_info r[GC_MERGE_NODES]; + struct gc_merge_info *last = r + GC_MERGE_NODES - 1; - memset(r, 0, sizeof(r)); + bch_keylist_init(&keys); + bch_btree_iter_init(b, &iter, &b->c->gc_done); - while ((r->k = bch_next_recurse_key(b, &b->c->gc_done))) { - r->b = bch_btree_node_get(b->c, r->k, b->level - 1, op); + for (i = 0; i < GC_MERGE_NODES; i++) + r[i].b = ERR_PTR(-EINTR); - if (IS_ERR(r->b)) { - ret = PTR_ERR(r->b); - break; + while (1) { + k = bch_btree_iter_next_filter(&iter, b, bch_ptr_bad); + if (k) { + r->b = bch_btree_node_get(b->c, k, b->level - 1, true); + if (IS_ERR(r->b)) { + ret = PTR_ERR(r->b); + break; + } + + r->keys = btree_gc_count_keys(r->b); + + ret = btree_gc_coalesce(b, op, &keys, gc, r); + if (ret) + break; } - r->keys = 0; - stale = btree_gc_mark_node(r->b, &r->keys, gc); + if (!last->b) + break; - if (!b->written && - (r->b->level || stale > 10 || - b->c->gc_always_rewrite)) - r->b = btree_gc_alloc(r->b, r->k, op); + if (!IS_ERR(last->b)) { + should_rewrite = btree_gc_mark_node(last->b, gc); + if (should_rewrite) { + n = btree_node_alloc_replacement(last->b, + false); - if (r->b->level) - ret = btree_gc_recurse(r->b, op, writes, gc); + if (!IS_ERR_OR_NULL(n)) { + bch_btree_node_write_sync(n); + bch_keylist_add(&keys, &n->key); - if (ret) { - write(r->b); - break; - } + make_btree_freeing_key(last->b, + keys.top); + bch_keylist_push(&keys); - bkey_copy_key(&b->c->gc_done, r->k); + btree_node_free(last->b); - if (!b->written) - btree_gc_coalesce(b, op, gc, r); + bch_btree_insert_node(b, op, &keys, + NULL, NULL); + BUG_ON(!bch_keylist_empty(&keys)); - if (r[GC_MERGE_NODES - 1].b) - write(r[GC_MERGE_NODES - 1].b); + rw_unlock(true, last->b); + last->b = n; - memmove(&r[1], &r[0], - sizeof(struct gc_merge_info) * (GC_MERGE_NODES - 1)); + /* Invalidated our iterator */ + ret = -EINTR; + break; + } + } + + if (last->b->level) { + ret = btree_gc_recurse(last->b, op, writes, gc); + if (ret) + break; + } + + bkey_copy_key(&b->c->gc_done, &last->b->key); + + /* + * Must flush leaf nodes before gc ends, since replace + * operations aren't journalled + */ + if (btree_node_dirty(last->b)) + bch_btree_node_write(last->b, writes); + rw_unlock(true, last->b); + } + + memmove(r + 1, r, sizeof(r[0]) * (GC_MERGE_NODES - 1)); + r->b = NULL; - /* When we've got incremental GC working, we'll want to do - * if (should_resched()) - * return -EAGAIN; - */ - cond_resched(); -#if 0 if (need_resched()) { ret = -EAGAIN; break; } -#endif } - for (i = 1; i < GC_MERGE_NODES && r[i].b; i++) - write(r[i].b); + for (i = 0; i < GC_MERGE_NODES; i++) + if (!IS_ERR_OR_NULL(r[i].b)) { + if (btree_node_dirty(r[i].b)) + bch_btree_node_write(r[i].b, writes); + rw_unlock(true, r[i].b); + } - /* Might have freed some children, must remove their keys */ - if (!b->written) - bch_btree_sort(b); + bch_keylist_free(&keys); return ret; } @@ -1367,29 +1485,31 @@ static int bch_btree_gc_root(struct btree *b, struct btree_op *op, struct closure *writes, struct gc_stat *gc) { struct btree *n = NULL; - unsigned keys = 0; - int ret = 0, stale = btree_gc_mark_node(b, &keys, gc); - - if (b->level || stale > 10) - n = btree_node_alloc_replacement(b, NULL); + int ret = 0; + bool should_rewrite; - if (!IS_ERR_OR_NULL(n)) - swap(b, n); + should_rewrite = btree_gc_mark_node(b, gc); + if (should_rewrite) { + n = btree_node_alloc_replacement(b, false); - if (b->level) - ret = btree_gc_recurse(b, op, writes, gc); + if (!IS_ERR_OR_NULL(n)) { + bch_btree_node_write_sync(n); + bch_btree_set_root(n); + btree_node_free(b); + rw_unlock(true, n); - if (!b->written || btree_node_dirty(b)) { - bch_btree_node_write(b, n ? &op->cl : NULL); + return -EINTR; + } } - if (!IS_ERR_OR_NULL(n)) { - closure_sync(&op->cl); - bch_btree_set_root(b); - btree_node_free(n, op); - rw_unlock(true, b); + if (b->level) { + ret = btree_gc_recurse(b, op, writes, gc); + if (ret) + return ret; } + bkey_copy_key(&b->c->gc_done, &b->key); + return ret; } @@ -1470,9 +1590,8 @@ size_t bch_btree_gc_finish(struct cache_set *c) return available; } -static void bch_btree_gc(struct closure *cl) +static void bch_btree_gc(struct cache_set *c) { - struct cache_set *c = container_of(cl, struct cache_set, gc.cl); int ret; unsigned long available; struct gc_stat stats; @@ -1484,47 +1603,73 @@ static void bch_btree_gc(struct closure *cl) memset(&stats, 0, sizeof(struct gc_stat)); closure_init_stack(&writes); - bch_btree_op_init_stack(&op); - op.lock = SHRT_MAX; + bch_btree_op_init(&op, SHRT_MAX); btree_gc_start(c); - atomic_inc(&c->prio_blocked); - - ret = btree_root(gc_root, c, &op, &writes, &stats); - closure_sync(&op.cl); - closure_sync(&writes); - - if (ret) { - pr_warn("gc failed!"); - continue_at(cl, bch_btree_gc, bch_gc_wq); - } + do { + ret = btree_root(gc_root, c, &op, &writes, &stats); + closure_sync(&writes); - /* Possibly wait for new UUIDs or whatever to hit disk */ - bch_journal_meta(c, &op.cl); - closure_sync(&op.cl); + if (ret && ret != -EAGAIN) + pr_warn("gc failed!"); + } while (ret); available = bch_btree_gc_finish(c); - - atomic_dec(&c->prio_blocked); wake_up_allocators(c); bch_time_stats_update(&c->btree_gc_time, start_time); stats.key_bytes *= sizeof(uint64_t); - stats.dirty <<= 9; stats.data <<= 9; stats.in_use = (c->nbuckets - available) * 100 / c->nbuckets; memcpy(&c->gc_stats, &stats, sizeof(struct gc_stat)); trace_bcache_gc_end(c); - continue_at(cl, bch_moving_gc, bch_gc_wq); + bch_moving_gc(c); +} + +static int bch_gc_thread(void *arg) +{ + struct cache_set *c = arg; + struct cache *ca; + unsigned i; + + while (1) { +again: + bch_btree_gc(c); + + set_current_state(TASK_INTERRUPTIBLE); + if (kthread_should_stop()) + break; + + mutex_lock(&c->bucket_lock); + + for_each_cache(ca, c, i) + if (ca->invalidate_needs_gc) { + mutex_unlock(&c->bucket_lock); + set_current_state(TASK_RUNNING); + goto again; + } + + mutex_unlock(&c->bucket_lock); + + try_to_freeze(); + schedule(); + } + + return 0; } -void bch_queue_gc(struct cache_set *c) +int bch_gc_thread_start(struct cache_set *c) { - closure_trylock_call(&c->gc.cl, bch_btree_gc, bch_gc_wq, &c->cl); + c->gc_thread = kthread_create(bch_gc_thread, c, "bcache_gc"); + if (IS_ERR(c->gc_thread)) + return PTR_ERR(c->gc_thread); + + set_task_state(c->gc_thread, TASK_INTERRUPTIBLE); + return 0; } /* Initial partial gc */ @@ -1532,9 +1677,9 @@ void bch_queue_gc(struct cache_set *c) static int bch_btree_check_recurse(struct btree *b, struct btree_op *op, unsigned long **seen) { - int ret; + int ret = 0; unsigned i; - struct bkey *k; + struct bkey *k, *p = NULL; struct bucket *g; struct btree_iter iter; @@ -1561,31 +1706,32 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op, } if (b->level) { - k = bch_next_recurse_key(b, &ZERO_KEY); + bch_btree_iter_init(b, &iter, NULL); - while (k) { - struct bkey *p = bch_next_recurse_key(b, k); - if (p) - btree_node_prefetch(b->c, p, b->level - 1); + do { + k = bch_btree_iter_next_filter(&iter, b, bch_ptr_bad); + if (k) + btree_node_prefetch(b->c, k, b->level - 1); - ret = btree(check_recurse, k, b, op, seen); - if (ret) - return ret; + if (p) + ret = btree(check_recurse, p, b, op, seen); - k = p; - } + p = k; + } while (p && !ret); } return 0; } -int bch_btree_check(struct cache_set *c, struct btree_op *op) +int bch_btree_check(struct cache_set *c) { int ret = -ENOMEM; unsigned i; unsigned long *seen[MAX_CACHES_PER_SET]; + struct btree_op op; memset(seen, 0, sizeof(seen)); + bch_btree_op_init(&op, SHRT_MAX); for (i = 0; c->cache[i]; i++) { size_t n = DIV_ROUND_UP(c->cache[i]->sb.nbuckets, 8); @@ -1597,7 +1743,7 @@ int bch_btree_check(struct cache_set *c, struct btree_op *op) memset(seen[i], 0xFF, n); } - ret = btree_root(check_recurse, c, op, seen); + ret = btree_root(check_recurse, c, &op, seen); err: for (i = 0; i < MAX_CACHES_PER_SET; i++) kfree(seen[i]); @@ -1619,10 +1765,9 @@ static void shift_keys(struct btree *b, struct bkey *where, struct bkey *insert) bch_bset_fix_lookup_table(b, where); } -static bool fix_overlapping_extents(struct btree *b, - struct bkey *insert, +static bool fix_overlapping_extents(struct btree *b, struct bkey *insert, struct btree_iter *iter, - struct btree_op *op) + struct bkey *replace_key) { void subtract_dirty(struct bkey *k, uint64_t offset, int sectors) { @@ -1650,39 +1795,38 @@ static bool fix_overlapping_extents(struct btree *b, * We might overlap with 0 size extents; we can't skip these * because if they're in the set we're inserting to we have to * adjust them so they don't overlap with the key we're - * inserting. But we don't want to check them for BTREE_REPLACE + * inserting. But we don't want to check them for replace * operations. */ - if (op->type == BTREE_REPLACE && - KEY_SIZE(k)) { + if (replace_key && KEY_SIZE(k)) { /* * k might have been split since we inserted/found the * key we're replacing */ unsigned i; uint64_t offset = KEY_START(k) - - KEY_START(&op->replace); + KEY_START(replace_key); /* But it must be a subset of the replace key */ - if (KEY_START(k) < KEY_START(&op->replace) || - KEY_OFFSET(k) > KEY_OFFSET(&op->replace)) + if (KEY_START(k) < KEY_START(replace_key) || + KEY_OFFSET(k) > KEY_OFFSET(replace_key)) goto check_failed; /* We didn't find a key that we were supposed to */ if (KEY_START(k) > KEY_START(insert) + sectors_found) goto check_failed; - if (KEY_PTRS(&op->replace) != KEY_PTRS(k)) + if (KEY_PTRS(replace_key) != KEY_PTRS(k)) goto check_failed; /* skip past gen */ offset <<= 8; - BUG_ON(!KEY_PTRS(&op->replace)); + BUG_ON(!KEY_PTRS(replace_key)); - for (i = 0; i < KEY_PTRS(&op->replace); i++) - if (k->ptr[i] != op->replace.ptr[i] + offset) + for (i = 0; i < KEY_PTRS(replace_key); i++) + if (k->ptr[i] != replace_key->ptr[i] + offset) goto check_failed; sectors_found = KEY_OFFSET(k) - KEY_START(insert); @@ -1733,6 +1877,9 @@ static bool fix_overlapping_extents(struct btree *b, if (bkey_cmp(insert, k) < 0) { bch_cut_front(insert, k); } else { + if (bkey_cmp(&START_KEY(insert), &START_KEY(k)) > 0) + old_offset = KEY_START(insert); + if (bkey_written(b, k) && bkey_cmp(&START_KEY(insert), &START_KEY(k)) <= 0) { /* @@ -1750,9 +1897,8 @@ static bool fix_overlapping_extents(struct btree *b, } check_failed: - if (op->type == BTREE_REPLACE) { + if (replace_key) { if (!sectors_found) { - op->insert_collision = true; return true; } else if (sectors_found < KEY_SIZE(insert)) { SET_KEY_OFFSET(insert, KEY_OFFSET(insert) - @@ -1765,7 +1911,7 @@ check_failed: } static bool btree_insert_key(struct btree *b, struct btree_op *op, - struct bkey *k) + struct bkey *k, struct bkey *replace_key) { struct bset *i = b->sets[b->nsets].data; struct bkey *m, *prev; @@ -1777,22 +1923,23 @@ static bool btree_insert_key(struct btree *b, struct btree_op *op, if (!b->level) { struct btree_iter iter; - struct bkey search = KEY(KEY_INODE(k), KEY_START(k), 0); /* * bset_search() returns the first key that is strictly greater * than the search key - but for back merging, we want to find - * the first key that is greater than or equal to KEY_START(k) - - * unless KEY_START(k) is 0. + * the previous key. */ - if (KEY_OFFSET(&search)) - SET_KEY_OFFSET(&search, KEY_OFFSET(&search) - 1); - prev = NULL; - m = bch_btree_iter_init(b, &iter, &search); + m = bch_btree_iter_init(b, &iter, PRECEDING_KEY(&START_KEY(k))); - if (fix_overlapping_extents(b, k, &iter, op)) + if (fix_overlapping_extents(b, k, &iter, replace_key)) { + op->insert_collision = true; return false; + } + + if (KEY_DIRTY(k)) + bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k), + KEY_START(k), KEY_SIZE(k)); while (m != end(i) && bkey_cmp(k, &START_KEY(m)) > 0) @@ -1816,84 +1963,80 @@ static bool btree_insert_key(struct btree *b, struct btree_op *op, if (m != end(i) && bch_bkey_try_merge(b, k, m)) goto copy; - } else + } else { + BUG_ON(replace_key); m = bch_bset_search(b, &b->sets[b->nsets], k); + } insert: shift_keys(b, m, k); copy: bkey_copy(m, k); merged: - if (KEY_DIRTY(k)) - bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k), - KEY_START(k), KEY_SIZE(k)); - - bch_check_keys(b, "%u for %s", status, op_type(op)); + bch_check_keys(b, "%u for %s", status, + replace_key ? "replace" : "insert"); if (b->level && !KEY_OFFSET(k)) btree_current_write(b)->prio_blocked++; - trace_bcache_btree_insert_key(b, k, op->type, status); + trace_bcache_btree_insert_key(b, k, replace_key != NULL, status); return true; } -static bool bch_btree_insert_keys(struct btree *b, struct btree_op *op) +static bool bch_btree_insert_keys(struct btree *b, struct btree_op *op, + struct keylist *insert_keys, + struct bkey *replace_key) { bool ret = false; - struct bkey *k; - unsigned oldsize = bch_count_data(b); + int oldsize = bch_count_data(b); - while ((k = bch_keylist_pop(&op->keys))) { - bkey_put(b->c, k, b->level); - ret |= btree_insert_key(b, op, k); - } + while (!bch_keylist_empty(insert_keys)) { + struct bset *i = write_block(b); + struct bkey *k = insert_keys->keys; - BUG_ON(bch_count_data(b) < oldsize); - return ret; -} - -bool bch_btree_insert_check_key(struct btree *b, struct btree_op *op, - struct bio *bio) -{ - bool ret = false; - uint64_t btree_ptr = b->key.ptr[0]; - unsigned long seq = b->seq; - BKEY_PADDED(k) tmp; - - rw_unlock(false, b); - rw_lock(true, b, b->level); + if (b->written + __set_blocks(i, i->keys + bkey_u64s(k), b->c) + > btree_blocks(b)) + break; - if (b->key.ptr[0] != btree_ptr || - b->seq != seq + 1 || - should_split(b)) - goto out; + if (bkey_cmp(k, &b->key) <= 0) { + if (!b->level) + bkey_put(b->c, k); - op->replace = KEY(op->inode, bio_end_sector(bio), bio_sectors(bio)); + ret |= btree_insert_key(b, op, k, replace_key); + bch_keylist_pop_front(insert_keys); + } else if (bkey_cmp(&START_KEY(k), &b->key) < 0) { + BKEY_PADDED(key) temp; + bkey_copy(&temp.key, insert_keys->keys); - SET_KEY_PTRS(&op->replace, 1); - get_random_bytes(&op->replace.ptr[0], sizeof(uint64_t)); + bch_cut_back(&b->key, &temp.key); + bch_cut_front(&b->key, insert_keys->keys); - SET_PTR_DEV(&op->replace, 0, PTR_CHECK_DEV); + ret |= btree_insert_key(b, op, &temp.key, replace_key); + break; + } else { + break; + } + } - bkey_copy(&tmp.k, &op->replace); + BUG_ON(!bch_keylist_empty(insert_keys) && b->level); - BUG_ON(op->type != BTREE_INSERT); - BUG_ON(!btree_insert_key(b, op, &tmp.k)); - ret = true; -out: - downgrade_write(&b->lock); + BUG_ON(bch_count_data(b) < oldsize); return ret; } -static int btree_split(struct btree *b, struct btree_op *op) +static int btree_split(struct btree *b, struct btree_op *op, + struct keylist *insert_keys, + struct bkey *replace_key) { - bool split, root = b == b->c->root; + bool split; struct btree *n1, *n2 = NULL, *n3 = NULL; uint64_t start_time = local_clock(); + struct closure cl; + struct keylist parent_keys; - if (b->level) - set_closure_blocking(&op->cl); + closure_init_stack(&cl); + bch_keylist_init(&parent_keys); - n1 = btree_node_alloc_replacement(b, &op->cl); + n1 = btree_node_alloc_replacement(b, true); if (IS_ERR(n1)) goto err; @@ -1904,19 +2047,20 @@ static int btree_split(struct btree *b, struct btree_op *op) trace_bcache_btree_node_split(b, n1->sets[0].data->keys); - n2 = bch_btree_node_alloc(b->c, b->level, &op->cl); + n2 = bch_btree_node_alloc(b->c, b->level, true); if (IS_ERR(n2)) goto err_free1; - if (root) { - n3 = bch_btree_node_alloc(b->c, b->level + 1, &op->cl); + if (!b->parent) { + n3 = bch_btree_node_alloc(b->c, b->level + 1, true); if (IS_ERR(n3)) goto err_free2; } - bch_btree_insert_keys(n1, op); + bch_btree_insert_keys(n1, op, insert_keys, replace_key); - /* Has to be a linear search because we don't have an auxiliary + /* + * Has to be a linear search because we don't have an auxiliary * search tree yet */ @@ -1935,60 +2079,57 @@ static int btree_split(struct btree *b, struct btree_op *op) bkey_copy_key(&n2->key, &b->key); - bch_keylist_add(&op->keys, &n2->key); - bch_btree_node_write(n2, &op->cl); + bch_keylist_add(&parent_keys, &n2->key); + bch_btree_node_write(n2, &cl); rw_unlock(true, n2); } else { trace_bcache_btree_node_compact(b, n1->sets[0].data->keys); - bch_btree_insert_keys(n1, op); + bch_btree_insert_keys(n1, op, insert_keys, replace_key); } - bch_keylist_add(&op->keys, &n1->key); - bch_btree_node_write(n1, &op->cl); + bch_keylist_add(&parent_keys, &n1->key); + bch_btree_node_write(n1, &cl); if (n3) { + /* Depth increases, make a new root */ bkey_copy_key(&n3->key, &MAX_KEY); - bch_btree_insert_keys(n3, op); - bch_btree_node_write(n3, &op->cl); + bch_btree_insert_keys(n3, op, &parent_keys, NULL); + bch_btree_node_write(n3, &cl); - closure_sync(&op->cl); + closure_sync(&cl); bch_btree_set_root(n3); rw_unlock(true, n3); - } else if (root) { - op->keys.top = op->keys.bottom; - closure_sync(&op->cl); - bch_btree_set_root(n1); - } else { - unsigned i; - bkey_copy(op->keys.top, &b->key); - bkey_copy_key(op->keys.top, &ZERO_KEY); + btree_node_free(b); + } else if (!b->parent) { + /* Root filled up but didn't need to be split */ + closure_sync(&cl); + bch_btree_set_root(n1); - for (i = 0; i < KEY_PTRS(&b->key); i++) { - uint8_t g = PTR_BUCKET(b->c, &b->key, i)->gen + 1; + btree_node_free(b); + } else { + /* Split a non root node */ + closure_sync(&cl); + make_btree_freeing_key(b, parent_keys.top); + bch_keylist_push(&parent_keys); - SET_PTR_GEN(op->keys.top, i, g); - } + btree_node_free(b); - bch_keylist_push(&op->keys); - closure_sync(&op->cl); - atomic_inc(&b->c->prio_blocked); + bch_btree_insert_node(b->parent, op, &parent_keys, NULL, NULL); + BUG_ON(!bch_keylist_empty(&parent_keys)); } rw_unlock(true, n1); - btree_node_free(b, op); bch_time_stats_update(&b->c->btree_split_time, start_time); return 0; err_free2: - __bkey_put(n2->c, &n2->key); - btree_node_free(n2, op); + btree_node_free(n2); rw_unlock(true, n2); err_free1: - __bkey_put(n1->c, &n1->key); - btree_node_free(n1, op); + btree_node_free(n1); rw_unlock(true, n1); err: if (n3 == ERR_PTR(-EAGAIN) || @@ -2000,116 +2141,126 @@ err: return -ENOMEM; } -static int bch_btree_insert_recurse(struct btree *b, struct btree_op *op, - struct keylist *stack_keys) +static int bch_btree_insert_node(struct btree *b, struct btree_op *op, + struct keylist *insert_keys, + atomic_t *journal_ref, + struct bkey *replace_key) { - if (b->level) { - int ret; - struct bkey *insert = op->keys.bottom; - struct bkey *k = bch_next_recurse_key(b, &START_KEY(insert)); + BUG_ON(b->level && replace_key); - if (!k) { - btree_bug(b, "no key to recurse on at level %i/%i", - b->level, b->c->root->level); - - op->keys.top = op->keys.bottom; - return -EIO; + if (should_split(b)) { + if (current->bio_list) { + op->lock = b->c->root->level + 1; + return -EAGAIN; + } else if (op->lock <= b->c->root->level) { + op->lock = b->c->root->level + 1; + return -EINTR; + } else { + /* Invalidated all iterators */ + return btree_split(b, op, insert_keys, replace_key) ?: + -EINTR; } + } else { + BUG_ON(write_block(b) != b->sets[b->nsets].data); - if (bkey_cmp(insert, k) > 0) { - unsigned i; - - if (op->type == BTREE_REPLACE) { - __bkey_put(b->c, insert); - op->keys.top = op->keys.bottom; - op->insert_collision = true; - return 0; - } + if (bch_btree_insert_keys(b, op, insert_keys, replace_key)) { + if (!b->level) + bch_btree_leaf_dirty(b, journal_ref); + else + bch_btree_node_write_sync(b); + } - for (i = 0; i < KEY_PTRS(insert); i++) - atomic_inc(&PTR_BUCKET(b->c, insert, i)->pin); + return 0; + } +} - bkey_copy(stack_keys->top, insert); +int bch_btree_insert_check_key(struct btree *b, struct btree_op *op, + struct bkey *check_key) +{ + int ret = -EINTR; + uint64_t btree_ptr = b->key.ptr[0]; + unsigned long seq = b->seq; + struct keylist insert; + bool upgrade = op->lock == -1; - bch_cut_back(k, insert); - bch_cut_front(k, stack_keys->top); + bch_keylist_init(&insert); - bch_keylist_push(stack_keys); - } + if (upgrade) { + rw_unlock(false, b); + rw_lock(true, b, b->level); - ret = btree(insert_recurse, k, b, op, stack_keys); - if (ret) - return ret; + if (b->key.ptr[0] != btree_ptr || + b->seq != seq + 1) + goto out; } - if (!bch_keylist_empty(&op->keys)) { - if (should_split(b)) { - if (op->lock <= b->c->root->level) { - BUG_ON(b->level); - op->lock = b->c->root->level + 1; - return -EINTR; - } - return btree_split(b, op); - } + SET_KEY_PTRS(check_key, 1); + get_random_bytes(&check_key->ptr[0], sizeof(uint64_t)); - BUG_ON(write_block(b) != b->sets[b->nsets].data); + SET_PTR_DEV(check_key, 0, PTR_CHECK_DEV); - if (bch_btree_insert_keys(b, op)) { - if (!b->level) - bch_btree_leaf_dirty(b, op); - else - bch_btree_node_write(b, &op->cl); - } - } + bch_keylist_add(&insert, check_key); - return 0; + ret = bch_btree_insert_node(b, op, &insert, NULL, NULL); + + BUG_ON(!ret && !bch_keylist_empty(&insert)); +out: + if (upgrade) + downgrade_write(&b->lock); + return ret; } -int bch_btree_insert(struct btree_op *op, struct cache_set *c) +struct btree_insert_op { + struct btree_op op; + struct keylist *keys; + atomic_t *journal_ref; + struct bkey *replace_key; +}; + +int btree_insert_fn(struct btree_op *b_op, struct btree *b) { - int ret = 0; - struct keylist stack_keys; + struct btree_insert_op *op = container_of(b_op, + struct btree_insert_op, op); - /* - * Don't want to block with the btree locked unless we have to, - * otherwise we get deadlocks with try_harder and between split/gc - */ - clear_closure_blocking(&op->cl); - - BUG_ON(bch_keylist_empty(&op->keys)); - bch_keylist_copy(&stack_keys, &op->keys); - bch_keylist_init(&op->keys); - - while (!bch_keylist_empty(&stack_keys) || - !bch_keylist_empty(&op->keys)) { - if (bch_keylist_empty(&op->keys)) { - bch_keylist_add(&op->keys, - bch_keylist_pop(&stack_keys)); - op->lock = 0; - } + int ret = bch_btree_insert_node(b, &op->op, op->keys, + op->journal_ref, op->replace_key); + if (ret && !bch_keylist_empty(op->keys)) + return ret; + else + return MAP_DONE; +} - ret = btree_root(insert_recurse, c, op, &stack_keys); +int bch_btree_insert(struct cache_set *c, struct keylist *keys, + atomic_t *journal_ref, struct bkey *replace_key) +{ + struct btree_insert_op op; + int ret = 0; - if (ret == -EAGAIN) { - ret = 0; - closure_sync(&op->cl); - } else if (ret) { - struct bkey *k; + BUG_ON(current->bio_list); + BUG_ON(bch_keylist_empty(keys)); + + bch_btree_op_init(&op.op, 0); + op.keys = keys; + op.journal_ref = journal_ref; + op.replace_key = replace_key; + + while (!ret && !bch_keylist_empty(keys)) { + op.op.lock = 0; + ret = bch_btree_map_leaf_nodes(&op.op, c, + &START_KEY(keys->keys), + btree_insert_fn); + } - pr_err("error %i trying to insert key for %s", - ret, op_type(op)); + if (ret) { + struct bkey *k; - while ((k = bch_keylist_pop(&stack_keys) ?: - bch_keylist_pop(&op->keys))) - bkey_put(c, k, 0); - } - } + pr_err("error %i", ret); - bch_keylist_free(&stack_keys); + while ((k = bch_keylist_pop(keys))) + bkey_put(c, k); + } else if (op.op.insert_collision) + ret = -ESRCH; - if (op->journal) - atomic_dec_bug(op->journal); - op->journal = NULL; return ret; } @@ -2132,132 +2283,81 @@ void bch_btree_set_root(struct btree *b) mutex_unlock(&b->c->bucket_lock); b->c->root = b; - __bkey_put(b->c, &b->key); bch_journal_meta(b->c, &cl); closure_sync(&cl); } -/* Cache lookup */ +/* Map across nodes or keys */ -static int submit_partial_cache_miss(struct btree *b, struct btree_op *op, - struct bkey *k) +static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op, + struct bkey *from, + btree_map_nodes_fn *fn, int flags) { - struct search *s = container_of(op, struct search, op); - struct bio *bio = &s->bio.bio; - int ret = 0; + int ret = MAP_CONTINUE; - while (!ret && - !op->lookup_done) { - unsigned sectors = INT_MAX; + if (b->level) { + struct bkey *k; + struct btree_iter iter; - if (KEY_INODE(k) == op->inode) { - if (KEY_START(k) <= bio->bi_sector) - break; + bch_btree_iter_init(b, &iter, from); - sectors = min_t(uint64_t, sectors, - KEY_START(k) - bio->bi_sector); - } + while ((k = bch_btree_iter_next_filter(&iter, b, + bch_ptr_bad))) { + ret = btree(map_nodes_recurse, k, b, + op, from, fn, flags); + from = NULL; - ret = s->d->cache_miss(b, s, bio, sectors); + if (ret != MAP_CONTINUE) + return ret; + } } + if (!b->level || flags == MAP_ALL_NODES) + ret = fn(op, b); + return ret; } -/* - * Read from a single key, handling the initial cache miss if the key starts in - * the middle of the bio - */ -static int submit_partial_cache_hit(struct btree *b, struct btree_op *op, - struct bkey *k) +int __bch_btree_map_nodes(struct btree_op *op, struct cache_set *c, + struct bkey *from, btree_map_nodes_fn *fn, int flags) { - struct search *s = container_of(op, struct search, op); - struct bio *bio = &s->bio.bio; - unsigned ptr; - struct bio *n; - - int ret = submit_partial_cache_miss(b, op, k); - if (ret || op->lookup_done) - return ret; - - /* XXX: figure out best pointer - for multiple cache devices */ - ptr = 0; - - PTR_BUCKET(b->c, k, ptr)->prio = INITIAL_PRIO; - - while (!op->lookup_done && - KEY_INODE(k) == op->inode && - bio->bi_sector < KEY_OFFSET(k)) { - struct bkey *bio_key; - sector_t sector = PTR_OFFSET(k, ptr) + - (bio->bi_sector - KEY_START(k)); - unsigned sectors = min_t(uint64_t, INT_MAX, - KEY_OFFSET(k) - bio->bi_sector); - - n = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split); - if (n == bio) - op->lookup_done = true; - - bio_key = &container_of(n, struct bbio, bio)->key; - - /* - * The bucket we're reading from might be reused while our bio - * is in flight, and we could then end up reading the wrong - * data. - * - * We guard against this by checking (in cache_read_endio()) if - * the pointer is stale again; if so, we treat it as an error - * and reread from the backing device (but we don't pass that - * error up anywhere). - */ - - bch_bkey_copy_single_ptr(bio_key, k, ptr); - SET_PTR_OFFSET(bio_key, 0, sector); - - n->bi_end_io = bch_cache_read_endio; - n->bi_private = &s->cl; - - __bch_submit_bbio(n, b->c); - } - - return 0; + return btree_root(map_nodes_recurse, c, op, from, fn, flags); } -int bch_btree_search_recurse(struct btree *b, struct btree_op *op) +static int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op, + struct bkey *from, btree_map_keys_fn *fn, + int flags) { - struct search *s = container_of(op, struct search, op); - struct bio *bio = &s->bio.bio; - - int ret = 0; + int ret = MAP_CONTINUE; struct bkey *k; struct btree_iter iter; - bch_btree_iter_init(b, &iter, &KEY(op->inode, bio->bi_sector, 0)); - do { - k = bch_btree_iter_next_filter(&iter, b, bch_ptr_bad); - if (!k) { - /* - * b->key would be exactly what we want, except that - * pointers to btree nodes have nonzero size - we - * wouldn't go far enough - */ + bch_btree_iter_init(b, &iter, from); - ret = submit_partial_cache_miss(b, op, - &KEY(KEY_INODE(&b->key), - KEY_OFFSET(&b->key), 0)); - break; - } + while ((k = bch_btree_iter_next_filter(&iter, b, bch_ptr_bad))) { + ret = !b->level + ? fn(op, b, k) + : btree(map_keys_recurse, k, b, op, from, fn, flags); + from = NULL; + + if (ret != MAP_CONTINUE) + return ret; + } - ret = b->level - ? btree(search_recurse, k, b, op) - : submit_partial_cache_hit(b, op, k); - } while (!ret && - !op->lookup_done); + if (!b->level && (flags & MAP_END_KEY)) + ret = fn(op, b, &KEY(KEY_INODE(&b->key), + KEY_OFFSET(&b->key), 0)); return ret; } +int bch_btree_map_keys(struct btree_op *op, struct cache_set *c, + struct bkey *from, btree_map_keys_fn *fn, int flags) +{ + return btree_root(map_keys_recurse, c, op, from, fn, flags); +} + /* Keybuf code */ static inline int keybuf_cmp(struct keybuf_key *l, struct keybuf_key *r) @@ -2276,80 +2376,79 @@ static inline int keybuf_nonoverlapping_cmp(struct keybuf_key *l, return clamp_t(int64_t, bkey_cmp(&l->key, &r->key), -1, 1); } -static int bch_btree_refill_keybuf(struct btree *b, struct btree_op *op, - struct keybuf *buf, struct bkey *end, - keybuf_pred_fn *pred) -{ - struct btree_iter iter; - bch_btree_iter_init(b, &iter, &buf->last_scanned); - - while (!array_freelist_empty(&buf->freelist)) { - struct bkey *k = bch_btree_iter_next_filter(&iter, b, - bch_ptr_bad); +struct refill { + struct btree_op op; + unsigned nr_found; + struct keybuf *buf; + struct bkey *end; + keybuf_pred_fn *pred; +}; - if (!b->level) { - if (!k) { - buf->last_scanned = b->key; - break; - } +static int refill_keybuf_fn(struct btree_op *op, struct btree *b, + struct bkey *k) +{ + struct refill *refill = container_of(op, struct refill, op); + struct keybuf *buf = refill->buf; + int ret = MAP_CONTINUE; - buf->last_scanned = *k; - if (bkey_cmp(&buf->last_scanned, end) >= 0) - break; + if (bkey_cmp(k, refill->end) >= 0) { + ret = MAP_DONE; + goto out; + } - if (pred(buf, k)) { - struct keybuf_key *w; + if (!KEY_SIZE(k)) /* end key */ + goto out; - spin_lock(&buf->lock); + if (refill->pred(buf, k)) { + struct keybuf_key *w; - w = array_alloc(&buf->freelist); + spin_lock(&buf->lock); - w->private = NULL; - bkey_copy(&w->key, k); + w = array_alloc(&buf->freelist); + if (!w) { + spin_unlock(&buf->lock); + return MAP_DONE; + } - if (RB_INSERT(&buf->keys, w, node, keybuf_cmp)) - array_free(&buf->freelist, w); + w->private = NULL; + bkey_copy(&w->key, k); - spin_unlock(&buf->lock); - } - } else { - if (!k) - break; - - btree(refill_keybuf, k, b, op, buf, end, pred); - /* - * Might get an error here, but can't really do anything - * and it'll get logged elsewhere. Just read what we - * can. - */ + if (RB_INSERT(&buf->keys, w, node, keybuf_cmp)) + array_free(&buf->freelist, w); + else + refill->nr_found++; - if (bkey_cmp(&buf->last_scanned, end) >= 0) - break; + if (array_freelist_empty(&buf->freelist)) + ret = MAP_DONE; - cond_resched(); - } + spin_unlock(&buf->lock); } - - return 0; +out: + buf->last_scanned = *k; + return ret; } void bch_refill_keybuf(struct cache_set *c, struct keybuf *buf, struct bkey *end, keybuf_pred_fn *pred) { struct bkey start = buf->last_scanned; - struct btree_op op; - bch_btree_op_init_stack(&op); + struct refill refill; cond_resched(); - btree_root(refill_keybuf, c, &op, buf, end, pred); - closure_sync(&op.cl); + bch_btree_op_init(&refill.op, -1); + refill.nr_found = 0; + refill.buf = buf; + refill.end = end; + refill.pred = pred; + + bch_btree_map_keys(&refill.op, c, &buf->last_scanned, + refill_keybuf_fn, MAP_END_KEY); - pr_debug("found %s keys from %llu:%llu to %llu:%llu", - RB_EMPTY_ROOT(&buf->keys) ? "no" : - array_freelist_empty(&buf->freelist) ? "some" : "a few", - KEY_INODE(&start), KEY_OFFSET(&start), - KEY_INODE(&buf->last_scanned), KEY_OFFSET(&buf->last_scanned)); + trace_bcache_keyscan(refill.nr_found, + KEY_INODE(&start), KEY_OFFSET(&start), + KEY_INODE(&buf->last_scanned), + KEY_OFFSET(&buf->last_scanned)); spin_lock(&buf->lock); @@ -2427,9 +2526,9 @@ struct keybuf_key *bch_keybuf_next(struct keybuf *buf) } struct keybuf_key *bch_keybuf_next_rescan(struct cache_set *c, - struct keybuf *buf, - struct bkey *end, - keybuf_pred_fn *pred) + struct keybuf *buf, + struct bkey *end, + keybuf_pred_fn *pred) { struct keybuf_key *ret; @@ -2462,14 +2561,12 @@ void bch_btree_exit(void) { if (btree_io_wq) destroy_workqueue(btree_io_wq); - if (bch_gc_wq) - destroy_workqueue(bch_gc_wq); } int __init bch_btree_init(void) { - if (!(bch_gc_wq = create_singlethread_workqueue("bch_btree_gc")) || - !(btree_io_wq = create_singlethread_workqueue("bch_btree_io"))) + btree_io_wq = create_singlethread_workqueue("bch_btree_io"); + if (!btree_io_wq) return -ENOMEM; return 0; diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 3333d37..767e755 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -125,6 +125,7 @@ struct btree { unsigned long seq; struct rw_semaphore lock; struct cache_set *c; + struct btree *parent; unsigned long flags; uint16_t written; /* would be nice to kill */ @@ -200,12 +201,7 @@ static inline bool bkey_written(struct btree *b, struct bkey *k) static inline void set_gc_sectors(struct cache_set *c) { - atomic_set(&c->sectors_to_gc, c->sb.bucket_size * c->nbuckets / 8); -} - -static inline bool bch_ptr_invalid(struct btree *b, const struct bkey *k) -{ - return __bch_ptr_invalid(b->c, b->level, k); + atomic_set(&c->sectors_to_gc, c->sb.bucket_size * c->nbuckets / 16); } static inline struct bkey *bch_btree_iter_init(struct btree *b, @@ -215,6 +211,16 @@ static inline struct bkey *bch_btree_iter_init(struct btree *b, return __bch_btree_iter_init(b, iter, search, b->sets); } +static inline bool bch_ptr_invalid(struct btree *b, const struct bkey *k) +{ + if (b->level) + return bch_btree_ptr_invalid(b->c, k); + else + return bch_extent_ptr_invalid(b->c, k); +} + +void bkey_put(struct cache_set *c, struct bkey *k); + /* Looping macros */ #define for_each_cached_btree(b, c, iter) \ @@ -234,51 +240,17 @@ static inline struct bkey *bch_btree_iter_init(struct btree *b, /* Recursing down the btree */ struct btree_op { - struct closure cl; - struct cache_set *c; - - /* Journal entry we have a refcount on */ - atomic_t *journal; - - /* Bio to be inserted into the cache */ - struct bio *cache_bio; - - unsigned inode; - - uint16_t write_prio; - /* Btree level at which we start taking write locks */ short lock; - /* Btree insertion type */ - enum { - BTREE_INSERT, - BTREE_REPLACE - } type:8; - - unsigned csum:1; - unsigned skip:1; - unsigned flush_journal:1; - - unsigned insert_data_done:1; - unsigned lookup_done:1; unsigned insert_collision:1; - - /* Anything after this point won't get zeroed in do_bio_hook() */ - - /* Keys to be inserted */ - struct keylist keys; - BKEY_PADDED(replace); }; -enum { - BTREE_INSERT_STATUS_INSERT, - BTREE_INSERT_STATUS_BACK_MERGE, - BTREE_INSERT_STATUS_OVERWROTE, - BTREE_INSERT_STATUS_FRONT_MERGE, -}; - -void bch_btree_op_init_stack(struct btree_op *); +static inline void bch_btree_op_init(struct btree_op *op, int write_lock_level) +{ + memset(op, 0, sizeof(struct btree_op)); + op->lock = write_lock_level; +} static inline void rw_lock(bool w, struct btree *b, int level) { @@ -290,108 +262,71 @@ static inline void rw_lock(bool w, struct btree *b, int level) static inline void rw_unlock(bool w, struct btree *b) { -#ifdef CONFIG_BCACHE_EDEBUG - unsigned i; - - if (w && b->key.ptr[0]) - for (i = 0; i <= b->nsets; i++) - bch_check_key_order(b, b->sets[i].data); -#endif - if (w) b->seq++; (w ? up_write : up_read)(&b->lock); } -#define insert_lock(s, b) ((b)->level <= (s)->lock) +void bch_btree_node_read(struct btree *); +void bch_btree_node_write(struct btree *, struct closure *); -/* - * These macros are for recursing down the btree - they handle the details of - * locking and looking up nodes in the cache for you. They're best treated as - * mere syntax when reading code that uses them. - * - * op->lock determines whether we take a read or a write lock at a given depth. - * If you've got a read lock and find that you need a write lock (i.e. you're - * going to have to split), set op->lock and return -EINTR; btree_root() will - * call you again and you'll have the correct lock. - */ +void bch_btree_set_root(struct btree *); +struct btree *bch_btree_node_alloc(struct cache_set *, int, bool); +struct btree *bch_btree_node_get(struct cache_set *, struct bkey *, int, bool); -/** - * btree - recurse down the btree on a specified key - * @fn: function to call, which will be passed the child node - * @key: key to recurse on - * @b: parent btree node - * @op: pointer to struct btree_op - */ -#define btree(fn, key, b, op, ...) \ -({ \ - int _r, l = (b)->level - 1; \ - bool _w = l <= (op)->lock; \ - struct btree *_b = bch_btree_node_get((b)->c, key, l, op); \ - if (!IS_ERR(_b)) { \ - _r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__); \ - rw_unlock(_w, _b); \ - } else \ - _r = PTR_ERR(_b); \ - _r; \ -}) - -/** - * btree_root - call a function on the root of the btree - * @fn: function to call, which will be passed the child node - * @c: cache set - * @op: pointer to struct btree_op - */ -#define btree_root(fn, c, op, ...) \ -({ \ - int _r = -EINTR; \ - do { \ - struct btree *_b = (c)->root; \ - bool _w = insert_lock(op, _b); \ - rw_lock(_w, _b, _b->level); \ - if (_b == (c)->root && \ - _w == insert_lock(op, _b)) \ - _r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__); \ - rw_unlock(_w, _b); \ - bch_cannibalize_unlock(c, &(op)->cl); \ - } while (_r == -EINTR); \ - \ - _r; \ -}) +int bch_btree_insert_check_key(struct btree *, struct btree_op *, + struct bkey *); +int bch_btree_insert(struct cache_set *, struct keylist *, + atomic_t *, struct bkey *); + +int bch_gc_thread_start(struct cache_set *); +size_t bch_btree_gc_finish(struct cache_set *); +void bch_moving_gc(struct cache_set *); +int bch_btree_check(struct cache_set *); +uint8_t __bch_btree_mark_key(struct cache_set *, int, struct bkey *); -static inline bool should_split(struct btree *b) +static inline void wake_up_gc(struct cache_set *c) { - struct bset *i = write_block(b); - return b->written >= btree_blocks(b) || - (i->seq == b->sets[0].data->seq && - b->written + __set_blocks(i, i->keys + 15, b->c) - > btree_blocks(b)); + if (c->gc_thread) + wake_up_process(c->gc_thread); } -void bch_btree_node_read(struct btree *); -void bch_btree_node_write(struct btree *, struct closure *); +#define MAP_DONE 0 +#define MAP_CONTINUE 1 -void bch_cannibalize_unlock(struct cache_set *, struct closure *); -void bch_btree_set_root(struct btree *); -struct btree *bch_btree_node_alloc(struct cache_set *, int, struct closure *); -struct btree *bch_btree_node_get(struct cache_set *, struct bkey *, - int, struct btree_op *); +#define MAP_ALL_NODES 0 +#define MAP_LEAF_NODES 1 -bool bch_btree_insert_check_key(struct btree *, struct btree_op *, - struct bio *); -int bch_btree_insert(struct btree_op *, struct cache_set *); +#define MAP_END_KEY 1 -int bch_btree_search_recurse(struct btree *, struct btree_op *); +typedef int (btree_map_nodes_fn)(struct btree_op *, struct btree *); +int __bch_btree_map_nodes(struct btree_op *, struct cache_set *, + struct bkey *, btree_map_nodes_fn *, int); -void bch_queue_gc(struct cache_set *); -size_t bch_btree_gc_finish(struct cache_set *); -void bch_moving_gc(struct closure *); -int bch_btree_check(struct cache_set *, struct btree_op *); -uint8_t __bch_btree_mark_key(struct cache_set *, int, struct bkey *); +static inline int bch_btree_map_nodes(struct btree_op *op, struct cache_set *c, + struct bkey *from, btree_map_nodes_fn *fn) +{ + return __bch_btree_map_nodes(op, c, from, fn, MAP_ALL_NODES); +} + +static inline int bch_btree_map_leaf_nodes(struct btree_op *op, + struct cache_set *c, + struct bkey *from, + btree_map_nodes_fn *fn) +{ + return __bch_btree_map_nodes(op, c, from, fn, MAP_LEAF_NODES); +} + +typedef int (btree_map_keys_fn)(struct btree_op *, struct btree *, + struct bkey *); +int bch_btree_map_keys(struct btree_op *, struct cache_set *, + struct bkey *, btree_map_keys_fn *, int); + +typedef bool (keybuf_pred_fn)(struct keybuf *, struct bkey *); void bch_keybuf_init(struct keybuf *); -void bch_refill_keybuf(struct cache_set *, struct keybuf *, struct bkey *, - keybuf_pred_fn *); +void bch_refill_keybuf(struct cache_set *, struct keybuf *, + struct bkey *, keybuf_pred_fn *); bool bch_keybuf_check_overlapping(struct keybuf *, struct bkey *, struct bkey *); void bch_keybuf_del(struct keybuf *, struct keybuf_key *); diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c index 9aba201..dfff241 100644 --- a/drivers/md/bcache/closure.c +++ b/drivers/md/bcache/closure.c @@ -11,17 +11,6 @@ #include "closure.h" -void closure_queue(struct closure *cl) -{ - struct workqueue_struct *wq = cl->wq; - if (wq) { - INIT_WORK(&cl->work, cl->work.func); - BUG_ON(!queue_work(wq, &cl->work)); - } else - cl->fn(cl); -} -EXPORT_SYMBOL_GPL(closure_queue); - #define CL_FIELD(type, field) \ case TYPE_ ## type: \ return &container_of(cl, struct type, cl)->field @@ -30,17 +19,6 @@ static struct closure_waitlist *closure_waitlist(struct closure *cl) { switch (cl->type) { CL_FIELD(closure_with_waitlist, wait); - CL_FIELD(closure_with_waitlist_and_timer, wait); - default: - return NULL; - } -} - -static struct timer_list *closure_timer(struct closure *cl) -{ - switch (cl->type) { - CL_FIELD(closure_with_timer, timer); - CL_FIELD(closure_with_waitlist_and_timer, timer); default: return NULL; } @@ -51,7 +29,7 @@ static inline void closure_put_after_sub(struct closure *cl, int flags) int r = flags & CLOSURE_REMAINING_MASK; BUG_ON(flags & CLOSURE_GUARD_MASK); - BUG_ON(!r && (flags & ~(CLOSURE_DESTRUCTOR|CLOSURE_BLOCKING))); + BUG_ON(!r && (flags & ~CLOSURE_DESTRUCTOR)); /* Must deliver precisely one wakeup */ if (r == 1 && (flags & CLOSURE_SLEEPING)) @@ -59,7 +37,6 @@ static inline void closure_put_after_sub(struct closure *cl, int flags) if (!r) { if (cl->fn && !(flags & CLOSURE_DESTRUCTOR)) { - /* CLOSURE_BLOCKING might be set - clear it */ atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); closure_queue(cl); @@ -90,13 +67,13 @@ void closure_sub(struct closure *cl, int v) { closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining)); } -EXPORT_SYMBOL_GPL(closure_sub); +EXPORT_SYMBOL(closure_sub); void closure_put(struct closure *cl) { closure_put_after_sub(cl, atomic_dec_return(&cl->remaining)); } -EXPORT_SYMBOL_GPL(closure_put); +EXPORT_SYMBOL(closure_put); static void set_waiting(struct closure *cl, unsigned long f) { @@ -133,7 +110,7 @@ void __closure_wake_up(struct closure_waitlist *wait_list) closure_sub(cl, CLOSURE_WAITING + 1); } } -EXPORT_SYMBOL_GPL(__closure_wake_up); +EXPORT_SYMBOL(__closure_wake_up); bool closure_wait(struct closure_waitlist *list, struct closure *cl) { @@ -146,7 +123,7 @@ bool closure_wait(struct closure_waitlist *list, struct closure *cl) return true; } -EXPORT_SYMBOL_GPL(closure_wait); +EXPORT_SYMBOL(closure_wait); /** * closure_sync() - sleep until a closure a closure has nothing left to wait on @@ -169,7 +146,7 @@ void closure_sync(struct closure *cl) __closure_end_sleep(cl); } -EXPORT_SYMBOL_GPL(closure_sync); +EXPORT_SYMBOL(closure_sync); /** * closure_trylock() - try to acquire the closure, without waiting @@ -183,17 +160,17 @@ bool closure_trylock(struct closure *cl, struct closure *parent) CLOSURE_REMAINING_INITIALIZER) != -1) return false; - closure_set_ret_ip(cl); - smp_mb(); + cl->parent = parent; if (parent) closure_get(parent); + closure_set_ret_ip(cl); closure_debug_create(cl); return true; } -EXPORT_SYMBOL_GPL(closure_trylock); +EXPORT_SYMBOL(closure_trylock); void __closure_lock(struct closure *cl, struct closure *parent, struct closure_waitlist *wait_list) @@ -205,57 +182,11 @@ void __closure_lock(struct closure *cl, struct closure *parent, if (closure_trylock(cl, parent)) return; - closure_wait_event_sync(wait_list, &wait, - atomic_read(&cl->remaining) == -1); + closure_wait_event(wait_list, &wait, + atomic_read(&cl->remaining) == -1); } } -EXPORT_SYMBOL_GPL(__closure_lock); - -static void closure_delay_timer_fn(unsigned long data) -{ - struct closure *cl = (struct closure *) data; - closure_sub(cl, CLOSURE_TIMER + 1); -} - -void do_closure_timer_init(struct closure *cl) -{ - struct timer_list *timer = closure_timer(cl); - - init_timer(timer); - timer->data = (unsigned long) cl; - timer->function = closure_delay_timer_fn; -} -EXPORT_SYMBOL_GPL(do_closure_timer_init); - -bool __closure_delay(struct closure *cl, unsigned long delay, - struct timer_list *timer) -{ - if (atomic_read(&cl->remaining) & CLOSURE_TIMER) - return false; - - BUG_ON(timer_pending(timer)); - - timer->expires = jiffies + delay; - - atomic_add(CLOSURE_TIMER + 1, &cl->remaining); - add_timer(timer); - return true; -} -EXPORT_SYMBOL_GPL(__closure_delay); - -void __closure_flush(struct closure *cl, struct timer_list *timer) -{ - if (del_timer(timer)) - closure_sub(cl, CLOSURE_TIMER + 1); -} -EXPORT_SYMBOL_GPL(__closure_flush); - -void __closure_flush_sync(struct closure *cl, struct timer_list *timer) -{ - if (del_timer_sync(timer)) - closure_sub(cl, CLOSURE_TIMER + 1); -} -EXPORT_SYMBOL_GPL(__closure_flush_sync); +EXPORT_SYMBOL(__closure_lock); #ifdef CONFIG_BCACHE_CLOSURES_DEBUG @@ -273,7 +204,7 @@ void closure_debug_create(struct closure *cl) list_add(&cl->all, &closure_list); spin_unlock_irqrestore(&closure_list_lock, flags); } -EXPORT_SYMBOL_GPL(closure_debug_create); +EXPORT_SYMBOL(closure_debug_create); void closure_debug_destroy(struct closure *cl) { @@ -286,7 +217,7 @@ void closure_debug_destroy(struct closure *cl) list_del(&cl->all); spin_unlock_irqrestore(&closure_list_lock, flags); } -EXPORT_SYMBOL_GPL(closure_debug_destroy); +EXPORT_SYMBOL(closure_debug_destroy); static struct dentry *debug; @@ -304,14 +235,12 @@ static int debug_seq_show(struct seq_file *f, void *data) cl, (void *) cl->ip, cl->fn, cl->parent, r & CLOSURE_REMAINING_MASK); - seq_printf(f, "%s%s%s%s%s%s\n", + seq_printf(f, "%s%s%s%s\n", test_bit(WORK_STRUCT_PENDING, work_data_bits(&cl->work)) ? "Q" : "", r & CLOSURE_RUNNING ? "R" : "", - r & CLOSURE_BLOCKING ? "B" : "", r & CLOSURE_STACK ? "S" : "", - r & CLOSURE_SLEEPING ? "Sl" : "", - r & CLOSURE_TIMER ? "T" : ""); + r & CLOSURE_SLEEPING ? "Sl" : ""); if (r & CLOSURE_WAITING) seq_printf(f, " W %pF\n", diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h index 0003992..9762f1b 100644 --- a/drivers/md/bcache/closure.h +++ b/drivers/md/bcache/closure.h @@ -155,21 +155,6 @@ * delayed_work embeds a work item and a timer_list. The important thing is, use * it exactly like you would a regular closure and closure_put() will magically * handle everything for you. - * - * We've got closures that embed timers, too. They're called, appropriately - * enough: - * struct closure_with_timer; - * - * This gives you access to closure_delay(). It takes a refcount for a specified - * number of jiffies - you could then call closure_sync() (for a slightly - * convoluted version of msleep()) or continue_at() - which gives you the same - * effect as using a delayed work item, except you can reuse the work_struct - * already embedded in struct closure. - * - * Lastly, there's struct closure_with_waitlist_and_timer. It does what you - * probably expect, if you happen to need the features of both. (You don't - * really want to know how all this is implemented, but if I've done my job - * right you shouldn't have to care). */ struct closure; @@ -182,16 +167,11 @@ struct closure_waitlist { enum closure_type { TYPE_closure = 0, TYPE_closure_with_waitlist = 1, - TYPE_closure_with_timer = 2, - TYPE_closure_with_waitlist_and_timer = 3, - MAX_CLOSURE_TYPE = 3, + MAX_CLOSURE_TYPE = 1, }; enum closure_state { /* - * CLOSURE_BLOCKING: Causes closure_wait_event() to block, instead of - * waiting asynchronously - * * CLOSURE_WAITING: Set iff the closure is on a waitlist. Must be set by * the thread that owns the closure, and cleared by the thread that's * waking up the closure. @@ -200,10 +180,6 @@ enum closure_state { * - indicates that cl->task is valid and closure_put() may wake it up. * Only set or cleared by the thread that owns the closure. * - * CLOSURE_TIMER: Analagous to CLOSURE_WAITING, indicates that a closure - * has an outstanding timer. Must be set by the thread that owns the - * closure, and cleared by the timer function when the timer goes off. - * * The rest are for debugging and don't affect behaviour: * * CLOSURE_RUNNING: Set when a closure is running (i.e. by @@ -218,19 +194,17 @@ enum closure_state { * closure with this flag set */ - CLOSURE_BITS_START = (1 << 19), - CLOSURE_DESTRUCTOR = (1 << 19), - CLOSURE_BLOCKING = (1 << 21), - CLOSURE_WAITING = (1 << 23), - CLOSURE_SLEEPING = (1 << 25), - CLOSURE_TIMER = (1 << 27), + CLOSURE_BITS_START = (1 << 23), + CLOSURE_DESTRUCTOR = (1 << 23), + CLOSURE_WAITING = (1 << 25), + CLOSURE_SLEEPING = (1 << 27), CLOSURE_RUNNING = (1 << 29), CLOSURE_STACK = (1 << 31), }; #define CLOSURE_GUARD_MASK \ - ((CLOSURE_DESTRUCTOR|CLOSURE_BLOCKING|CLOSURE_WAITING| \ - CLOSURE_SLEEPING|CLOSURE_TIMER|CLOSURE_RUNNING|CLOSURE_STACK) << 1) + ((CLOSURE_DESTRUCTOR|CLOSURE_WAITING|CLOSURE_SLEEPING| \ + CLOSURE_RUNNING|CLOSURE_STACK) << 1) #define CLOSURE_REMAINING_MASK (CLOSURE_BITS_START - 1) #define CLOSURE_REMAINING_INITIALIZER (1|CLOSURE_RUNNING) @@ -268,17 +242,6 @@ struct closure_with_waitlist { struct closure_waitlist wait; }; -struct closure_with_timer { - struct closure cl; - struct timer_list timer; -}; - -struct closure_with_waitlist_and_timer { - struct closure cl; - struct closure_waitlist wait; - struct timer_list timer; -}; - extern unsigned invalid_closure_type(void); #define __CLOSURE_TYPE(cl, _t) \ @@ -289,14 +252,11 @@ extern unsigned invalid_closure_type(void); ( \ __CLOSURE_TYPE(cl, closure) \ __CLOSURE_TYPE(cl, closure_with_waitlist) \ - __CLOSURE_TYPE(cl, closure_with_timer) \ - __CLOSURE_TYPE(cl, closure_with_waitlist_and_timer) \ invalid_closure_type() \ ) void closure_sub(struct closure *cl, int v); void closure_put(struct closure *cl); -void closure_queue(struct closure *cl); void __closure_wake_up(struct closure_waitlist *list); bool closure_wait(struct closure_waitlist *list, struct closure *cl); void closure_sync(struct closure *cl); @@ -305,12 +265,6 @@ bool closure_trylock(struct closure *cl, struct closure *parent); void __closure_lock(struct closure *cl, struct closure *parent, struct closure_waitlist *wait_list); -void do_closure_timer_init(struct closure *cl); -bool __closure_delay(struct closure *cl, unsigned long delay, - struct timer_list *timer); -void __closure_flush(struct closure *cl, struct timer_list *timer); -void __closure_flush_sync(struct closure *cl, struct timer_list *timer); - #ifdef CONFIG_BCACHE_CLOSURES_DEBUG void closure_debug_init(void); @@ -354,11 +308,6 @@ static inline void closure_set_stopped(struct closure *cl) atomic_sub(CLOSURE_RUNNING, &cl->remaining); } -static inline bool closure_is_stopped(struct closure *cl) -{ - return !(atomic_read(&cl->remaining) & CLOSURE_RUNNING); -} - static inline bool closure_is_unlocked(struct closure *cl) { return atomic_read(&cl->remaining) == -1; @@ -367,14 +316,6 @@ static inline bool closure_is_unlocked(struct closure *cl) static inline void do_closure_init(struct closure *cl, struct closure *parent, bool running) { - switch (cl->type) { - case TYPE_closure_with_timer: - case TYPE_closure_with_waitlist_and_timer: - do_closure_timer_init(cl); - default: - break; - } - cl->parent = parent; if (parent) closure_get(parent); @@ -429,8 +370,7 @@ do { \ static inline void closure_init_stack(struct closure *cl) { memset(cl, 0, sizeof(struct closure)); - atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER| - CLOSURE_BLOCKING|CLOSURE_STACK); + atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER|CLOSURE_STACK); } /** @@ -461,24 +401,6 @@ do { \ #define closure_lock(cl, parent) \ __closure_lock(__to_internal_closure(cl), parent, &(cl)->wait) -/** - * closure_delay() - delay some number of jiffies - * @cl: the closure that will sleep - * @delay: the delay in jiffies - * - * Takes a refcount on @cl which will be released after @delay jiffies; this may - * be used to have a function run after a delay with continue_at(), or - * closure_sync() may be used for a convoluted version of msleep(). - */ -#define closure_delay(cl, delay) \ - __closure_delay(__to_internal_closure(cl), delay, &(cl)->timer) - -#define closure_flush(cl) \ - __closure_flush(__to_internal_closure(cl), &(cl)->timer) - -#define closure_flush_sync(cl) \ - __closure_flush_sync(__to_internal_closure(cl), &(cl)->timer) - static inline void __closure_end_sleep(struct closure *cl) { __set_current_state(TASK_RUNNING); @@ -498,40 +420,6 @@ static inline void __closure_start_sleep(struct closure *cl) } /** - * closure_blocking() - returns true if the closure is in blocking mode. - * - * If a closure is in blocking mode, closure_wait_event() will sleep until the - * condition is true instead of waiting asynchronously. - */ -static inline bool closure_blocking(struct closure *cl) -{ - return atomic_read(&cl->remaining) & CLOSURE_BLOCKING; -} - -/** - * set_closure_blocking() - put a closure in blocking mode. - * - * If a closure is in blocking mode, closure_wait_event() will sleep until the - * condition is true instead of waiting asynchronously. - * - * Not thread safe - can only be called by the thread running the closure. - */ -static inline void set_closure_blocking(struct closure *cl) -{ - if (!closure_blocking(cl)) - atomic_add(CLOSURE_BLOCKING, &cl->remaining); -} - -/* - * Not thread safe - can only be called by the thread running the closure. - */ -static inline void clear_closure_blocking(struct closure *cl) -{ - if (closure_blocking(cl)) - atomic_sub(CLOSURE_BLOCKING, &cl->remaining); -} - -/** * closure_wake_up() - wake up all closures on a wait list. */ static inline void closure_wake_up(struct closure_waitlist *list) @@ -561,63 +449,36 @@ static inline void closure_wake_up(struct closure_waitlist *list) * refcount on our closure. If this was a stack allocated closure, that would be * bad. */ -#define __closure_wait_event(list, cl, condition, _block) \ +#define closure_wait_event(list, cl, condition) \ ({ \ - bool block = _block; \ typeof(condition) ret; \ \ while (1) { \ ret = (condition); \ if (ret) { \ __closure_wake_up(list); \ - if (block) \ - closure_sync(cl); \ - \ + closure_sync(cl); \ break; \ } \ \ - if (block) \ - __closure_start_sleep(cl); \ - \ - if (!closure_wait(list, cl)) { \ - if (!block) \ - break; \ + __closure_start_sleep(cl); \ \ + if (!closure_wait(list, cl)) \ schedule(); \ - } \ } \ \ ret; \ }) -/** - * closure_wait_event() - wait on a condition, synchronously or asynchronously. - * @list: the wait list to wait on - * @cl: the closure that is doing the waiting - * @condition: a C expression for the event to wait for - * - * If the closure is in blocking mode, sleeps until the @condition evaluates to - * true - exactly like wait_event(). - * - * If the closure is not in blocking mode, waits asynchronously; if the - * condition is currently false the @cl is put onto @list and returns. @list - * owns a refcount on @cl; closure_sync() or continue_at() may be used later to - * wait for another thread to wake up @list, which drops the refcount on @cl. - * - * Returns the value of @condition; @cl will be on @list iff @condition was - * false. - * - * closure_wake_up(@list) must be called after changing any variable that could - * cause @condition to become true. - */ -#define closure_wait_event(list, cl, condition) \ - __closure_wait_event(list, cl, condition, closure_blocking(cl)) - -#define closure_wait_event_async(list, cl, condition) \ - __closure_wait_event(list, cl, condition, false) - -#define closure_wait_event_sync(list, cl, condition) \ - __closure_wait_event(list, cl, condition, true) +static inline void closure_queue(struct closure *cl) +{ + struct workqueue_struct *wq = cl->wq; + if (wq) { + INIT_WORK(&cl->work, cl->work.func); + BUG_ON(!queue_work(wq, &cl->work)); + } else + cl->fn(cl); +} static inline void set_closure_fn(struct closure *cl, closure_fn *fn, struct workqueue_struct *wq) @@ -642,7 +503,7 @@ do { \ #define continue_at_nobarrier(_cl, _fn, _wq) \ do { \ set_closure_fn(_cl, _fn, _wq); \ - closure_queue(cl); \ + closure_queue(_cl); \ return; \ } while (0) diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c index 88e6411..264fcfb 100644 --- a/drivers/md/bcache/debug.c +++ b/drivers/md/bcache/debug.c @@ -8,7 +8,6 @@ #include "bcache.h" #include "btree.h" #include "debug.h" -#include "request.h" #include <linux/console.h> #include <linux/debugfs.h> @@ -77,29 +76,17 @@ int bch_bkey_to_text(char *buf, size_t size, const struct bkey *k) return out - buf; } -int bch_btree_to_text(char *buf, size_t size, const struct btree *b) -{ - return scnprintf(buf, size, "%zu level %i/%i", - PTR_BUCKET_NR(b->c, &b->key, 0), - b->level, b->c->root ? b->c->root->level : -1); -} - -#if defined(CONFIG_BCACHE_DEBUG) || defined(CONFIG_BCACHE_EDEBUG) - -static bool skipped_backwards(struct btree *b, struct bkey *k) -{ - return bkey_cmp(k, (!b->level) - ? &START_KEY(bkey_next(k)) - : bkey_next(k)) > 0; -} +#ifdef CONFIG_BCACHE_DEBUG static void dump_bset(struct btree *b, struct bset *i) { - struct bkey *k; + struct bkey *k, *next; unsigned j; char buf[80]; - for (k = i->start; k < end(i); k = bkey_next(k)) { + for (k = i->start; k < end(i); k = next) { + next = bkey_next(k); + bch_bkey_to_text(buf, sizeof(buf), k); printk(KERN_ERR "block %zu key %zi/%u: %s", index(i, b), (uint64_t *) k - i->d, i->keys, buf); @@ -115,15 +102,21 @@ static void dump_bset(struct btree *b, struct bset *i) printk(" %s\n", bch_ptr_status(b->c, k)); - if (bkey_next(k) < end(i) && - skipped_backwards(b, k)) + if (next < end(i) && + bkey_cmp(k, !b->level ? &START_KEY(next) : next) > 0) printk(KERN_ERR "Key skipped backwards\n"); } } -#endif +static void bch_dump_bucket(struct btree *b) +{ + unsigned i; -#ifdef CONFIG_BCACHE_DEBUG + console_lock(); + for (i = 0; i <= b->nsets; i++) + dump_bset(b, b->sets[i].data); + console_unlock(); +} void bch_btree_verify(struct btree *b, struct bset *new) { @@ -176,66 +169,44 @@ void bch_btree_verify(struct btree *b, struct bset *new) mutex_unlock(&b->c->verify_lock); } -static void data_verify_endio(struct bio *bio, int error) -{ - struct closure *cl = bio->bi_private; - closure_put(cl); -} - -void bch_data_verify(struct search *s) +void bch_data_verify(struct cached_dev *dc, struct bio *bio) { char name[BDEVNAME_SIZE]; - struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); - struct closure *cl = &s->cl; struct bio *check; struct bio_vec *bv; int i; - if (!s->unaligned_bvec) - bio_for_each_segment(bv, s->orig_bio, i) - bv->bv_offset = 0, bv->bv_len = PAGE_SIZE; - - check = bio_clone(s->orig_bio, GFP_NOIO); + check = bio_clone(bio, GFP_NOIO); if (!check) return; if (bio_alloc_pages(check, GFP_NOIO)) goto out_put; - check->bi_rw = READ_SYNC; - check->bi_private = cl; - check->bi_end_io = data_verify_endio; - - closure_bio_submit(check, cl, &dc->disk); - closure_sync(cl); + submit_bio_wait(READ_SYNC, check); - bio_for_each_segment(bv, s->orig_bio, i) { - void *p1 = kmap(bv->bv_page); - void *p2 = kmap(check->bi_io_vec[i].bv_page); + bio_for_each_segment(bv, bio, i) { + void *p1 = kmap_atomic(bv->bv_page); + void *p2 = page_address(check->bi_io_vec[i].bv_page); - if (memcmp(p1 + bv->bv_offset, - p2 + bv->bv_offset, - bv->bv_len)) - printk(KERN_ERR - "bcache (%s): verify failed at sector %llu\n", - bdevname(dc->bdev, name), - (uint64_t) s->orig_bio->bi_sector); + cache_set_err_on(memcmp(p1 + bv->bv_offset, + p2 + bv->bv_offset, + bv->bv_len), + dc->disk.c, + "verify failed at dev %s sector %llu", + bdevname(dc->bdev, name), + (uint64_t) bio->bi_sector); - kunmap(bv->bv_page); - kunmap(check->bi_io_vec[i].bv_page); + kunmap_atomic(p1); } - __bio_for_each_segment(bv, check, i, 0) + bio_for_each_segment_all(bv, check, i) __free_page(bv->bv_page); out_put: bio_put(check); } -#endif - -#ifdef CONFIG_BCACHE_EDEBUG - -unsigned bch_count_data(struct btree *b) +int __bch_count_data(struct btree *b) { unsigned ret = 0; struct btree_iter iter; @@ -247,72 +218,60 @@ unsigned bch_count_data(struct btree *b) return ret; } -static void vdump_bucket_and_panic(struct btree *b, const char *fmt, - va_list args) -{ - unsigned i; - char buf[80]; - - console_lock(); - - for (i = 0; i <= b->nsets; i++) - dump_bset(b, b->sets[i].data); - - vprintk(fmt, args); - - console_unlock(); - - bch_btree_to_text(buf, sizeof(buf), b); - panic("at %s\n", buf); -} - -void bch_check_key_order_msg(struct btree *b, struct bset *i, - const char *fmt, ...) -{ - struct bkey *k; - - if (!i->keys) - return; - - for (k = i->start; bkey_next(k) < end(i); k = bkey_next(k)) - if (skipped_backwards(b, k)) { - va_list args; - va_start(args, fmt); - - vdump_bucket_and_panic(b, fmt, args); - va_end(args); - } -} - -void bch_check_keys(struct btree *b, const char *fmt, ...) +void __bch_check_keys(struct btree *b, const char *fmt, ...) { va_list args; struct bkey *k, *p = NULL; struct btree_iter iter; - - if (b->level) - return; + const char *err; for_each_key(b, k, &iter) { - if (p && bkey_cmp(&START_KEY(p), &START_KEY(k)) > 0) { - printk(KERN_ERR "Keys out of order:\n"); - goto bug; - } - - if (bch_ptr_invalid(b, k)) - continue; - - if (p && bkey_cmp(p, &START_KEY(k)) > 0) { - printk(KERN_ERR "Overlapping keys:\n"); - goto bug; + if (!b->level) { + err = "Keys out of order"; + if (p && bkey_cmp(&START_KEY(p), &START_KEY(k)) > 0) + goto bug; + + if (bch_ptr_invalid(b, k)) + continue; + + err = "Overlapping keys"; + if (p && bkey_cmp(p, &START_KEY(k)) > 0) + goto bug; + } else { + if (bch_ptr_bad(b, k)) + continue; + + err = "Duplicate keys"; + if (p && !bkey_cmp(p, k)) + goto bug; } p = k; } + + err = "Key larger than btree node key"; + if (p && bkey_cmp(p, &b->key) > 0) + goto bug; + return; bug: + bch_dump_bucket(b); + va_start(args, fmt); - vdump_bucket_and_panic(b, fmt, args); + vprintk(fmt, args); va_end(args); + + panic("bcache error: %s:\n", err); +} + +void bch_btree_iter_next_check(struct btree_iter *iter) +{ + struct bkey *k = iter->data->k, *next = bkey_next(k); + + if (next < iter->data->end && + bkey_cmp(k, iter->b->level ? next : &START_KEY(next)) > 0) { + bch_dump_bucket(iter->b); + panic("Key skipped backwards\n"); + } } #endif diff --git a/drivers/md/bcache/debug.h b/drivers/md/bcache/debug.h index 1c39b5a..2ede60e 100644 --- a/drivers/md/bcache/debug.h +++ b/drivers/md/bcache/debug.h @@ -4,40 +4,44 @@ /* Btree/bkey debug printing */ int bch_bkey_to_text(char *buf, size_t size, const struct bkey *k); -int bch_btree_to_text(char *buf, size_t size, const struct btree *b); - -#ifdef CONFIG_BCACHE_EDEBUG - -unsigned bch_count_data(struct btree *); -void bch_check_key_order_msg(struct btree *, struct bset *, const char *, ...); -void bch_check_keys(struct btree *, const char *, ...); - -#define bch_check_key_order(b, i) \ - bch_check_key_order_msg(b, i, "keys out of order") -#define EBUG_ON(cond) BUG_ON(cond) - -#else /* EDEBUG */ - -#define bch_count_data(b) 0 -#define bch_check_key_order(b, i) do {} while (0) -#define bch_check_key_order_msg(b, i, ...) do {} while (0) -#define bch_check_keys(b, ...) do {} while (0) -#define EBUG_ON(cond) do {} while (0) - -#endif #ifdef CONFIG_BCACHE_DEBUG void bch_btree_verify(struct btree *, struct bset *); -void bch_data_verify(struct search *); +void bch_data_verify(struct cached_dev *, struct bio *); +int __bch_count_data(struct btree *); +void __bch_check_keys(struct btree *, const char *, ...); +void bch_btree_iter_next_check(struct btree_iter *); + +#define EBUG_ON(cond) BUG_ON(cond) +#define expensive_debug_checks(c) ((c)->expensive_debug_checks) +#define key_merging_disabled(c) ((c)->key_merging_disabled) +#define bypass_torture_test(d) ((d)->bypass_torture_test) #else /* DEBUG */ static inline void bch_btree_verify(struct btree *b, struct bset *i) {} -static inline void bch_data_verify(struct search *s) {}; +static inline void bch_data_verify(struct cached_dev *dc, struct bio *bio) {} +static inline int __bch_count_data(struct btree *b) { return -1; } +static inline void __bch_check_keys(struct btree *b, const char *fmt, ...) {} +static inline void bch_btree_iter_next_check(struct btree_iter *iter) {} + +#define EBUG_ON(cond) do { if (cond); } while (0) +#define expensive_debug_checks(c) 0 +#define key_merging_disabled(c) 0 +#define bypass_torture_test(d) 0 #endif +#define bch_count_data(b) \ + (expensive_debug_checks((b)->c) ? __bch_count_data(b) : -1) + +#define bch_check_keys(b, ...) \ +do { \ + if (expensive_debug_checks((b)->c)) \ + __bch_check_keys(b, __VA_ARGS__); \ +} while (0) + #ifdef CONFIG_DEBUG_FS void bch_debug_init_cache_set(struct cache_set *); #else diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index ba95ab8..ecdaa67 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -7,7 +7,6 @@ #include "bcache.h" #include "btree.h" #include "debug.h" -#include "request.h" #include <trace/events/bcache.h> @@ -31,17 +30,20 @@ static void journal_read_endio(struct bio *bio, int error) } static int journal_read_bucket(struct cache *ca, struct list_head *list, - struct btree_op *op, unsigned bucket_index) + unsigned bucket_index) { struct journal_device *ja = &ca->journal; struct bio *bio = &ja->bio; struct journal_replay *i; struct jset *j, *data = ca->set->journal.w[0].data; + struct closure cl; unsigned len, left, offset = 0; int ret = 0; sector_t bucket = bucket_to_sector(ca->set, ca->sb.d[bucket_index]); + closure_init_stack(&cl); + pr_debug("reading %llu", (uint64_t) bucket); while (offset < ca->sb.bucket_size) { @@ -55,11 +57,11 @@ reread: left = ca->sb.bucket_size - offset; bio->bi_size = len << 9; bio->bi_end_io = journal_read_endio; - bio->bi_private = &op->cl; + bio->bi_private = &cl; bch_bio_map(bio, data); - closure_bio_submit(bio, &op->cl, ca); - closure_sync(&op->cl); + closure_bio_submit(bio, &cl, ca); + closure_sync(&cl); /* This function could be simpler now since we no longer write * journal entries that overlap bucket boundaries; this means @@ -72,7 +74,7 @@ reread: left = ca->sb.bucket_size - offset; struct list_head *where; size_t blocks, bytes = set_bytes(j); - if (j->magic != jset_magic(ca->set)) + if (j->magic != jset_magic(&ca->sb)) return ret; if (bytes > left << 9) @@ -129,12 +131,11 @@ next_set: return ret; } -int bch_journal_read(struct cache_set *c, struct list_head *list, - struct btree_op *op) +int bch_journal_read(struct cache_set *c, struct list_head *list) { #define read_bucket(b) \ ({ \ - int ret = journal_read_bucket(ca, list, op, b); \ + int ret = journal_read_bucket(ca, list, b); \ __set_bit(b, bitmap); \ if (ret < 0) \ return ret; \ @@ -153,7 +154,8 @@ int bch_journal_read(struct cache_set *c, struct list_head *list, bitmap_zero(bitmap, SB_JOURNAL_BUCKETS); pr_debug("%u journal buckets", ca->sb.njournal_buckets); - /* Read journal buckets ordered by golden ratio hash to quickly + /* + * Read journal buckets ordered by golden ratio hash to quickly * find a sequence of buckets with valid journal entries */ for (i = 0; i < ca->sb.njournal_buckets; i++) { @@ -166,18 +168,20 @@ int bch_journal_read(struct cache_set *c, struct list_head *list, goto bsearch; } - /* If that fails, check all the buckets we haven't checked + /* + * If that fails, check all the buckets we haven't checked * already */ pr_debug("falling back to linear search"); - for (l = 0; l < ca->sb.njournal_buckets; l++) { - if (test_bit(l, bitmap)) - continue; - + for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets); + l < ca->sb.njournal_buckets; + l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets, l + 1)) if (read_bucket(l)) goto bsearch; - } + + if (list_empty(list)) + continue; bsearch: /* Binary search */ m = r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1); @@ -197,10 +201,12 @@ bsearch: r = m; } - /* Read buckets in reverse order until we stop finding more + /* + * Read buckets in reverse order until we stop finding more * journal entries */ - pr_debug("finishing up"); + pr_debug("finishing up: m %u njournal_buckets %u", + m, ca->sb.njournal_buckets); l = m; while (1) { @@ -228,9 +234,10 @@ bsearch: } } - c->journal.seq = list_entry(list->prev, - struct journal_replay, - list)->j.seq; + if (!list_empty(list)) + c->journal.seq = list_entry(list->prev, + struct journal_replay, + list)->j.seq; return 0; #undef read_bucket @@ -286,8 +293,7 @@ void bch_journal_mark(struct cache_set *c, struct list_head *list) } } -int bch_journal_replay(struct cache_set *s, struct list_head *list, - struct btree_op *op) +int bch_journal_replay(struct cache_set *s, struct list_head *list) { int ret = 0, keys = 0, entries = 0; struct bkey *k; @@ -295,31 +301,30 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list, list_entry(list->prev, struct journal_replay, list); uint64_t start = i->j.last_seq, end = i->j.seq, n = start; + struct keylist keylist; + + bch_keylist_init(&keylist); list_for_each_entry(i, list, list) { BUG_ON(i->pin && atomic_read(i->pin) != 1); - if (n != i->j.seq) - pr_err( - "journal entries %llu-%llu missing! (replaying %llu-%llu)\n", - n, i->j.seq - 1, start, end); + cache_set_err_on(n != i->j.seq, s, +"bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)", + n, i->j.seq - 1, start, end); for (k = i->j.start; k < end(&i->j); k = bkey_next(k)) { trace_bcache_journal_replay_key(k); - bkey_copy(op->keys.top, k); - bch_keylist_push(&op->keys); - - op->journal = i->pin; - atomic_inc(op->journal); + bkey_copy(keylist.top, k); + bch_keylist_push(&keylist); - ret = bch_btree_insert(op, s); + ret = bch_btree_insert(s, &keylist, i->pin, NULL); if (ret) goto err; - BUG_ON(!bch_keylist_empty(&op->keys)); + BUG_ON(!bch_keylist_empty(&keylist)); keys++; cond_resched(); @@ -333,14 +338,13 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list, pr_info("journal replay done, %i keys in %i entries, seq %llu", keys, entries, end); - +err: while (!list_empty(list)) { i = list_first_entry(list, struct journal_replay, list); list_del(&i->list); kfree(i); } -err: - closure_sync(&op->cl); + return ret; } @@ -352,48 +356,35 @@ static void btree_flush_write(struct cache_set *c) * Try to find the btree node with that references the oldest journal * entry, best is our current candidate and is locked if non NULL: */ - struct btree *b, *best = NULL; - unsigned iter; + struct btree *b, *best; + unsigned i; +retry: + best = NULL; + + for_each_cached_btree(b, c, i) + if (btree_current_write(b)->journal) { + if (!best) + best = b; + else if (journal_pin_cmp(c, + btree_current_write(best)->journal, + btree_current_write(b)->journal)) { + best = b; + } + } - for_each_cached_btree(b, c, iter) { - if (!down_write_trylock(&b->lock)) - continue; + b = best; + if (b) { + rw_lock(true, b, b->level); - if (!btree_node_dirty(b) || - !btree_current_write(b)->journal) { + if (!btree_current_write(b)->journal) { rw_unlock(true, b); - continue; + /* We raced */ + goto retry; } - if (!best) - best = b; - else if (journal_pin_cmp(c, - btree_current_write(best), - btree_current_write(b))) { - rw_unlock(true, best); - best = b; - } else - rw_unlock(true, b); + bch_btree_node_write(b, NULL); + rw_unlock(true, b); } - - if (best) - goto out; - - /* We can't find the best btree node, just pick the first */ - list_for_each_entry(b, &c->btree_cache, list) - if (!b->level && btree_node_dirty(b)) { - best = b; - rw_lock(true, best, best->level); - goto found; - } - -out: - if (!best) - return; -found: - if (btree_node_dirty(best)) - bch_btree_node_write(best, NULL); - rw_unlock(true, best); } #define last_seq(j) ((j)->seq - fifo_used(&(j)->pin) + 1) @@ -428,7 +419,7 @@ static void do_journal_discard(struct cache *ca) return; } - switch (atomic_read(&ja->discard_in_flight) == DISCARD_IN_FLIGHT) { + switch (atomic_read(&ja->discard_in_flight)) { case DISCARD_IN_FLIGHT: return; @@ -489,7 +480,7 @@ static void journal_reclaim(struct cache_set *c) do_journal_discard(ca); if (c->journal.blocks_free) - return; + goto out; /* * Allocate: @@ -515,7 +506,7 @@ static void journal_reclaim(struct cache_set *c) if (n) c->journal.blocks_free = c->sb.bucket_size >> c->block_bits; - +out: if (!journal_full(&c->journal)) __closure_wake_up(&c->journal.wait); } @@ -548,32 +539,26 @@ static void journal_write_endio(struct bio *bio, int error) struct journal_write *w = bio->bi_private; cache_set_err_on(error, w->c, "journal io error"); - closure_put(&w->c->journal.io.cl); + closure_put(&w->c->journal.io); } static void journal_write(struct closure *); static void journal_write_done(struct closure *cl) { - struct journal *j = container_of(cl, struct journal, io.cl); - struct cache_set *c = container_of(j, struct cache_set, journal); - + struct journal *j = container_of(cl, struct journal, io); struct journal_write *w = (j->cur == j->w) ? &j->w[1] : &j->w[0]; __closure_wake_up(&w->wait); - - if (c->journal_delay_ms) - closure_delay(&j->io, msecs_to_jiffies(c->journal_delay_ms)); - - continue_at(cl, journal_write, system_wq); + continue_at_nobarrier(cl, journal_write, system_wq); } static void journal_write_unlocked(struct closure *cl) __releases(c->journal.lock) { - struct cache_set *c = container_of(cl, struct cache_set, journal.io.cl); + struct cache_set *c = container_of(cl, struct cache_set, journal.io); struct cache *ca; struct journal_write *w = c->journal.cur; struct bkey *k = &c->journal.key; @@ -611,7 +596,7 @@ static void journal_write_unlocked(struct closure *cl) for_each_cache(ca, c, i) w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0]; - w->data->magic = jset_magic(c); + w->data->magic = jset_magic(&c->sb); w->data->version = BCACHE_JSET_VERSION; w->data->last_seq = last_seq(&c->journal); w->data->csum = csum_set(w->data); @@ -654,120 +639,134 @@ static void journal_write_unlocked(struct closure *cl) static void journal_write(struct closure *cl) { - struct cache_set *c = container_of(cl, struct cache_set, journal.io.cl); + struct cache_set *c = container_of(cl, struct cache_set, journal.io); spin_lock(&c->journal.lock); journal_write_unlocked(cl); } -static void __journal_try_write(struct cache_set *c, bool noflush) +static void journal_try_write(struct cache_set *c) __releases(c->journal.lock) { - struct closure *cl = &c->journal.io.cl; + struct closure *cl = &c->journal.io; + struct journal_write *w = c->journal.cur; - if (!closure_trylock(cl, &c->cl)) - spin_unlock(&c->journal.lock); - else if (noflush && journal_full(&c->journal)) { - spin_unlock(&c->journal.lock); - continue_at(cl, journal_write, system_wq); - } else + w->need_write = true; + + if (closure_trylock(cl, &c->cl)) journal_write_unlocked(cl); + else + spin_unlock(&c->journal.lock); } -#define journal_try_write(c) __journal_try_write(c, false) - -void bch_journal_meta(struct cache_set *c, struct closure *cl) +static struct journal_write *journal_wait_for_write(struct cache_set *c, + unsigned nkeys) { - struct journal_write *w; + size_t sectors; + struct closure cl; - if (CACHE_SYNC(&c->sb)) { - spin_lock(&c->journal.lock); + closure_init_stack(&cl); + + spin_lock(&c->journal.lock); + + while (1) { + struct journal_write *w = c->journal.cur; + + sectors = __set_blocks(w->data, w->data->keys + nkeys, + c) * c->sb.block_size; - w = c->journal.cur; - w->need_write = true; + if (sectors <= min_t(size_t, + c->journal.blocks_free * c->sb.block_size, + PAGE_SECTORS << JSET_BITS)) + return w; - if (cl) - BUG_ON(!closure_wait(&w->wait, cl)); + /* XXX: tracepoint */ + if (!journal_full(&c->journal)) { + trace_bcache_journal_entry_full(c); + + /* + * XXX: If we were inserting so many keys that they + * won't fit in an _empty_ journal write, we'll + * deadlock. For now, handle this in + * bch_keylist_realloc() - but something to think about. + */ + BUG_ON(!w->data->keys); + + closure_wait(&w->wait, &cl); + journal_try_write(c); /* unlocks */ + } else { + trace_bcache_journal_full(c); + + closure_wait(&c->journal.wait, &cl); + journal_reclaim(c); + spin_unlock(&c->journal.lock); + + btree_flush_write(c); + } - __journal_try_write(c, true); + closure_sync(&cl); + spin_lock(&c->journal.lock); } } +static void journal_write_work(struct work_struct *work) +{ + struct cache_set *c = container_of(to_delayed_work(work), + struct cache_set, + journal.work); + spin_lock(&c->journal.lock); + journal_try_write(c); +} + /* * Entry point to the journalling code - bio_insert() and btree_invalidate() * pass bch_journal() a list of keys to be journalled, and then * bch_journal() hands those same keys off to btree_insert_async() */ -void bch_journal(struct closure *cl) +atomic_t *bch_journal(struct cache_set *c, + struct keylist *keys, + struct closure *parent) { - struct btree_op *op = container_of(cl, struct btree_op, cl); - struct cache_set *c = op->c; struct journal_write *w; - size_t b, n = ((uint64_t *) op->keys.top) - op->keys.list; + atomic_t *ret; - if (op->type != BTREE_INSERT || - !CACHE_SYNC(&c->sb)) - goto out; + if (!CACHE_SYNC(&c->sb)) + return NULL; - /* - * If we're looping because we errored, might already be waiting on - * another journal write: - */ - while (atomic_read(&cl->parent->remaining) & CLOSURE_WAITING) - closure_sync(cl->parent); - - spin_lock(&c->journal.lock); + w = journal_wait_for_write(c, bch_keylist_nkeys(keys)); - if (journal_full(&c->journal)) { - trace_bcache_journal_full(c); + memcpy(end(w->data), keys->keys, bch_keylist_bytes(keys)); + w->data->keys += bch_keylist_nkeys(keys); - closure_wait(&c->journal.wait, cl); + ret = &fifo_back(&c->journal.pin); + atomic_inc(ret); - journal_reclaim(c); + if (parent) { + closure_wait(&w->wait, parent); + journal_try_write(c); + } else if (!w->need_write) { + schedule_delayed_work(&c->journal.work, + msecs_to_jiffies(c->journal_delay_ms)); + spin_unlock(&c->journal.lock); + } else { spin_unlock(&c->journal.lock); - - btree_flush_write(c); - continue_at(cl, bch_journal, bcache_wq); } - w = c->journal.cur; - w->need_write = true; - b = __set_blocks(w->data, w->data->keys + n, c); - - if (b * c->sb.block_size > PAGE_SECTORS << JSET_BITS || - b > c->journal.blocks_free) { - trace_bcache_journal_entry_full(c); - - /* - * XXX: If we were inserting so many keys that they won't fit in - * an _empty_ journal write, we'll deadlock. For now, handle - * this in bch_keylist_realloc() - but something to think about. - */ - BUG_ON(!w->data->keys); - - BUG_ON(!closure_wait(&w->wait, cl)); - closure_flush(&c->journal.io); - - journal_try_write(c); - continue_at(cl, bch_journal, bcache_wq); - } - - memcpy(end(w->data), op->keys.list, n * sizeof(uint64_t)); - w->data->keys += n; + return ret; +} - op->journal = &fifo_back(&c->journal.pin); - atomic_inc(op->journal); +void bch_journal_meta(struct cache_set *c, struct closure *cl) +{ + struct keylist keys; + atomic_t *ref; - if (op->flush_journal) { - closure_flush(&c->journal.io); - closure_wait(&w->wait, cl->parent); - } + bch_keylist_init(&keys); - journal_try_write(c); -out: - bch_btree_insert_async(cl); + ref = bch_journal(c, &keys, cl); + if (ref) + atomic_dec_bug(ref); } void bch_journal_free(struct cache_set *c) @@ -783,6 +782,7 @@ int bch_journal_alloc(struct cache_set *c) closure_init_unlocked(&j->io); spin_lock_init(&j->lock); + INIT_DELAYED_WORK(&j->work, journal_write_work); c->journal_delay_ms = 100; diff --git a/drivers/md/bcache/journal.h b/drivers/md/bcache/journal.h index 3d78512..a6472fd 100644 --- a/drivers/md/bcache/journal.h +++ b/drivers/md/bcache/journal.h @@ -75,43 +75,6 @@ * nodes that are pinning the oldest journal entries first. */ -#define BCACHE_JSET_VERSION_UUIDv1 1 -/* Always latest UUID format */ -#define BCACHE_JSET_VERSION_UUID 1 -#define BCACHE_JSET_VERSION 1 - -/* - * On disk format for a journal entry: - * seq is monotonically increasing; every journal entry has its own unique - * sequence number. - * - * last_seq is the oldest journal entry that still has keys the btree hasn't - * flushed to disk yet. - * - * version is for on disk format changes. - */ -struct jset { - uint64_t csum; - uint64_t magic; - uint64_t seq; - uint32_t version; - uint32_t keys; - - uint64_t last_seq; - - BKEY_PADDED(uuid_bucket); - BKEY_PADDED(btree_root); - uint16_t btree_level; - uint16_t pad[3]; - - uint64_t prio_bucket[MAX_CACHES_PER_SET]; - - union { - struct bkey start[0]; - uint64_t d[0]; - }; -}; - /* * Only used for holding the journal entries we read in btree_journal_read() * during cache_registration @@ -140,7 +103,8 @@ struct journal { spinlock_t lock; /* used when waiting because the journal was full */ struct closure_waitlist wait; - struct closure_with_timer io; + struct closure io; + struct delayed_work work; /* Number of blocks free in the bucket(s) we're currently writing to */ unsigned blocks_free; @@ -188,8 +152,7 @@ struct journal_device { }; #define journal_pin_cmp(c, l, r) \ - (fifo_idx(&(c)->journal.pin, (l)->journal) > \ - fifo_idx(&(c)->journal.pin, (r)->journal)) + (fifo_idx(&(c)->journal.pin, (l)) > fifo_idx(&(c)->journal.pin, (r))) #define JOURNAL_PIN 20000 @@ -199,15 +162,14 @@ struct journal_device { struct closure; struct cache_set; struct btree_op; +struct keylist; -void bch_journal(struct closure *); +atomic_t *bch_journal(struct cache_set *, struct keylist *, struct closure *); void bch_journal_next(struct journal *); void bch_journal_mark(struct cache_set *, struct list_head *); void bch_journal_meta(struct cache_set *, struct closure *); -int bch_journal_read(struct cache_set *, struct list_head *, - struct btree_op *); -int bch_journal_replay(struct cache_set *, struct list_head *, - struct btree_op *); +int bch_journal_read(struct cache_set *, struct list_head *); +int bch_journal_replay(struct cache_set *, struct list_head *); void bch_journal_free(struct cache_set *); int bch_journal_alloc(struct cache_set *); diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c index 1a3b4f4..7c1275e 100644 --- a/drivers/md/bcache/movinggc.c +++ b/drivers/md/bcache/movinggc.c @@ -12,8 +12,9 @@ #include <trace/events/bcache.h> struct moving_io { + struct closure cl; struct keybuf_key *w; - struct search s; + struct data_insert_op op; struct bbio bio; }; @@ -38,13 +39,13 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k) static void moving_io_destructor(struct closure *cl) { - struct moving_io *io = container_of(cl, struct moving_io, s.cl); + struct moving_io *io = container_of(cl, struct moving_io, cl); kfree(io); } static void write_moving_finish(struct closure *cl) { - struct moving_io *io = container_of(cl, struct moving_io, s.cl); + struct moving_io *io = container_of(cl, struct moving_io, cl); struct bio *bio = &io->bio.bio; struct bio_vec *bv; int i; @@ -52,13 +53,12 @@ static void write_moving_finish(struct closure *cl) bio_for_each_segment_all(bv, bio, i) __free_page(bv->bv_page); - if (io->s.op.insert_collision) + if (io->op.replace_collision) trace_bcache_gc_copy_collision(&io->w->key); - bch_keybuf_del(&io->s.op.c->moving_gc_keys, io->w); + bch_keybuf_del(&io->op.c->moving_gc_keys, io->w); - atomic_dec_bug(&io->s.op.c->in_flight); - closure_wake_up(&io->s.op.c->moving_gc_wait); + up(&io->op.c->moving_in_flight); closure_return_with_destructor(cl, moving_io_destructor); } @@ -66,12 +66,12 @@ static void write_moving_finish(struct closure *cl) static void read_moving_endio(struct bio *bio, int error) { struct moving_io *io = container_of(bio->bi_private, - struct moving_io, s.cl); + struct moving_io, cl); if (error) - io->s.error = error; + io->op.error = error; - bch_bbio_endio(io->s.op.c, bio, error, "reading data to move"); + bch_bbio_endio(io->op.c, bio, error, "reading data to move"); } static void moving_init(struct moving_io *io) @@ -85,54 +85,53 @@ static void moving_init(struct moving_io *io) bio->bi_size = KEY_SIZE(&io->w->key) << 9; bio->bi_max_vecs = DIV_ROUND_UP(KEY_SIZE(&io->w->key), PAGE_SECTORS); - bio->bi_private = &io->s.cl; + bio->bi_private = &io->cl; bio->bi_io_vec = bio->bi_inline_vecs; bch_bio_map(bio, NULL); } static void write_moving(struct closure *cl) { - struct search *s = container_of(cl, struct search, cl); - struct moving_io *io = container_of(s, struct moving_io, s); + struct moving_io *io = container_of(cl, struct moving_io, cl); + struct data_insert_op *op = &io->op; - if (!s->error) { + if (!op->error) { moving_init(io); - io->bio.bio.bi_sector = KEY_START(&io->w->key); - s->op.lock = -1; - s->op.write_prio = 1; - s->op.cache_bio = &io->bio.bio; + io->bio.bio.bi_sector = KEY_START(&io->w->key); + op->write_prio = 1; + op->bio = &io->bio.bio; - s->writeback = KEY_DIRTY(&io->w->key); - s->op.csum = KEY_CSUM(&io->w->key); + op->writeback = KEY_DIRTY(&io->w->key); + op->csum = KEY_CSUM(&io->w->key); - s->op.type = BTREE_REPLACE; - bkey_copy(&s->op.replace, &io->w->key); + bkey_copy(&op->replace_key, &io->w->key); + op->replace = true; - closure_init(&s->op.cl, cl); - bch_insert_data(&s->op.cl); + closure_call(&op->cl, bch_data_insert, NULL, cl); } - continue_at(cl, write_moving_finish, NULL); + continue_at(cl, write_moving_finish, system_wq); } static void read_moving_submit(struct closure *cl) { - struct search *s = container_of(cl, struct search, cl); - struct moving_io *io = container_of(s, struct moving_io, s); + struct moving_io *io = container_of(cl, struct moving_io, cl); struct bio *bio = &io->bio.bio; - bch_submit_bbio(bio, s->op.c, &io->w->key, 0); + bch_submit_bbio(bio, io->op.c, &io->w->key, 0); - continue_at(cl, write_moving, bch_gc_wq); + continue_at(cl, write_moving, system_wq); } -static void read_moving(struct closure *cl) +static void read_moving(struct cache_set *c) { - struct cache_set *c = container_of(cl, struct cache_set, moving_gc); struct keybuf_key *w; struct moving_io *io; struct bio *bio; + struct closure cl; + + closure_init_stack(&cl); /* XXX: if we error, background writeback could stall indefinitely */ @@ -150,8 +149,8 @@ static void read_moving(struct closure *cl) w->private = io; io->w = w; - io->s.op.inode = KEY_INODE(&w->key); - io->s.op.c = c; + io->op.inode = KEY_INODE(&w->key); + io->op.c = c; moving_init(io); bio = &io->bio.bio; @@ -164,13 +163,8 @@ static void read_moving(struct closure *cl) trace_bcache_gc_copy(&w->key); - closure_call(&io->s.cl, read_moving_submit, NULL, &c->gc.cl); - - if (atomic_inc_return(&c->in_flight) >= 64) { - closure_wait_event(&c->moving_gc_wait, cl, - atomic_read(&c->in_flight) < 64); - continue_at(cl, read_moving, bch_gc_wq); - } + down(&c->moving_in_flight); + closure_call(&io->cl, read_moving_submit, NULL, &cl); } if (0) { @@ -180,7 +174,7 @@ err: if (!IS_ERR_OR_NULL(w->private)) bch_keybuf_del(&c->moving_gc_keys, w); } - closure_return(cl); + closure_sync(&cl); } static bool bucket_cmp(struct bucket *l, struct bucket *r) @@ -193,15 +187,14 @@ static unsigned bucket_heap_top(struct cache *ca) return GC_SECTORS_USED(heap_peek(&ca->heap)); } -void bch_moving_gc(struct closure *cl) +void bch_moving_gc(struct cache_set *c) { - struct cache_set *c = container_of(cl, struct cache_set, gc.cl); struct cache *ca; struct bucket *b; unsigned i; if (!c->copy_gc_enabled) - closure_return(cl); + return; mutex_lock(&c->bucket_lock); @@ -242,13 +235,11 @@ void bch_moving_gc(struct closure *cl) c->moving_gc_keys.last_scanned = ZERO_KEY; - closure_init(&c->moving_gc, cl); - read_moving(&c->moving_gc); - - closure_return(cl); + read_moving(c); } void bch_moving_init_cache_set(struct cache_set *c) { bch_keybuf_init(&c->moving_gc_keys); + sema_init(&c->moving_in_flight, 64); } diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 786a1a4..fbcc851 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -25,7 +25,7 @@ struct kmem_cache *bch_search_cache; -static void check_should_skip(struct cached_dev *, struct search *); +static void bch_data_insert_start(struct closure *); /* Cgroup interface */ @@ -213,221 +213,79 @@ static void bio_csum(struct bio *bio, struct bkey *k) /* Insert data into cache */ -static void bio_invalidate(struct closure *cl) +static void bch_data_insert_keys(struct closure *cl) { - struct btree_op *op = container_of(cl, struct btree_op, cl); - struct bio *bio = op->cache_bio; - - pr_debug("invalidating %i sectors from %llu", - bio_sectors(bio), (uint64_t) bio->bi_sector); - - while (bio_sectors(bio)) { - unsigned len = min(bio_sectors(bio), 1U << 14); - - if (bch_keylist_realloc(&op->keys, 0, op->c)) - goto out; - - bio->bi_sector += len; - bio->bi_size -= len << 9; - - bch_keylist_add(&op->keys, - &KEY(op->inode, bio->bi_sector, len)); - } - - op->insert_data_done = true; - bio_put(bio); -out: - continue_at(cl, bch_journal, bcache_wq); -} - -struct open_bucket { - struct list_head list; - struct task_struct *last; - unsigned sectors_free; - BKEY_PADDED(key); -}; - -void bch_open_buckets_free(struct cache_set *c) -{ - struct open_bucket *b; - - while (!list_empty(&c->data_buckets)) { - b = list_first_entry(&c->data_buckets, - struct open_bucket, list); - list_del(&b->list); - kfree(b); - } -} - -int bch_open_buckets_alloc(struct cache_set *c) -{ - int i; - - spin_lock_init(&c->data_bucket_lock); - - for (i = 0; i < 6; i++) { - struct open_bucket *b = kzalloc(sizeof(*b), GFP_KERNEL); - if (!b) - return -ENOMEM; - - list_add(&b->list, &c->data_buckets); - } - - return 0; -} - -/* - * We keep multiple buckets open for writes, and try to segregate different - * write streams for better cache utilization: first we look for a bucket where - * the last write to it was sequential with the current write, and failing that - * we look for a bucket that was last used by the same task. - * - * The ideas is if you've got multiple tasks pulling data into the cache at the - * same time, you'll get better cache utilization if you try to segregate their - * data and preserve locality. - * - * For example, say you've starting Firefox at the same time you're copying a - * bunch of files. Firefox will likely end up being fairly hot and stay in the - * cache awhile, but the data you copied might not be; if you wrote all that - * data to the same buckets it'd get invalidated at the same time. - * - * Both of those tasks will be doing fairly random IO so we can't rely on - * detecting sequential IO to segregate their data, but going off of the task - * should be a sane heuristic. - */ -static struct open_bucket *pick_data_bucket(struct cache_set *c, - const struct bkey *search, - struct task_struct *task, - struct bkey *alloc) -{ - struct open_bucket *ret, *ret_task = NULL; - - list_for_each_entry_reverse(ret, &c->data_buckets, list) - if (!bkey_cmp(&ret->key, search)) - goto found; - else if (ret->last == task) - ret_task = ret; - - ret = ret_task ?: list_first_entry(&c->data_buckets, - struct open_bucket, list); -found: - if (!ret->sectors_free && KEY_PTRS(alloc)) { - ret->sectors_free = c->sb.bucket_size; - bkey_copy(&ret->key, alloc); - bkey_init(alloc); - } - - if (!ret->sectors_free) - ret = NULL; - - return ret; -} - -/* - * Allocates some space in the cache to write to, and k to point to the newly - * allocated space, and updates KEY_SIZE(k) and KEY_OFFSET(k) (to point to the - * end of the newly allocated space). - * - * May allocate fewer sectors than @sectors, KEY_SIZE(k) indicates how many - * sectors were actually allocated. - * - * If s->writeback is true, will not fail. - */ -static bool bch_alloc_sectors(struct bkey *k, unsigned sectors, - struct search *s) -{ - struct cache_set *c = s->op.c; - struct open_bucket *b; - BKEY_PADDED(key) alloc; - struct closure cl, *w = NULL; - unsigned i; - - if (s->writeback) { - closure_init_stack(&cl); - w = &cl; - } + struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); + atomic_t *journal_ref = NULL; + struct bkey *replace_key = op->replace ? &op->replace_key : NULL; + int ret; /* - * We might have to allocate a new bucket, which we can't do with a - * spinlock held. So if we have to allocate, we drop the lock, allocate - * and then retry. KEY_PTRS() indicates whether alloc points to - * allocated bucket(s). + * If we're looping, might already be waiting on + * another journal write - can't wait on more than one journal write at + * a time + * + * XXX: this looks wrong */ +#if 0 + while (atomic_read(&s->cl.remaining) & CLOSURE_WAITING) + closure_sync(&s->cl); +#endif - bkey_init(&alloc.key); - spin_lock(&c->data_bucket_lock); - - while (!(b = pick_data_bucket(c, k, s->task, &alloc.key))) { - unsigned watermark = s->op.write_prio - ? WATERMARK_MOVINGGC - : WATERMARK_NONE; - - spin_unlock(&c->data_bucket_lock); - - if (bch_bucket_alloc_set(c, watermark, &alloc.key, 1, w)) - return false; + if (!op->replace) + journal_ref = bch_journal(op->c, &op->insert_keys, + op->flush_journal ? cl : NULL); - spin_lock(&c->data_bucket_lock); + ret = bch_btree_insert(op->c, &op->insert_keys, + journal_ref, replace_key); + if (ret == -ESRCH) { + op->replace_collision = true; + } else if (ret) { + op->error = -ENOMEM; + op->insert_data_done = true; } - /* - * If we had to allocate, we might race and not need to allocate the - * second time we call find_data_bucket(). If we allocated a bucket but - * didn't use it, drop the refcount bch_bucket_alloc_set() took: - */ - if (KEY_PTRS(&alloc.key)) - __bkey_put(c, &alloc.key); - - for (i = 0; i < KEY_PTRS(&b->key); i++) - EBUG_ON(ptr_stale(c, &b->key, i)); + if (journal_ref) + atomic_dec_bug(journal_ref); - /* Set up the pointer to the space we're allocating: */ + if (!op->insert_data_done) + continue_at(cl, bch_data_insert_start, bcache_wq); - for (i = 0; i < KEY_PTRS(&b->key); i++) - k->ptr[i] = b->key.ptr[i]; + bch_keylist_free(&op->insert_keys); + closure_return(cl); +} - sectors = min(sectors, b->sectors_free); +static void bch_data_invalidate(struct closure *cl) +{ + struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); + struct bio *bio = op->bio; - SET_KEY_OFFSET(k, KEY_OFFSET(k) + sectors); - SET_KEY_SIZE(k, sectors); - SET_KEY_PTRS(k, KEY_PTRS(&b->key)); + pr_debug("invalidating %i sectors from %llu", + bio_sectors(bio), (uint64_t) bio->bi_sector); - /* - * Move b to the end of the lru, and keep track of what this bucket was - * last used for: - */ - list_move_tail(&b->list, &c->data_buckets); - bkey_copy_key(&b->key, k); - b->last = s->task; + while (bio_sectors(bio)) { + unsigned sectors = min(bio_sectors(bio), + 1U << (KEY_SIZE_BITS - 1)); - b->sectors_free -= sectors; + if (bch_keylist_realloc(&op->insert_keys, 0, op->c)) + goto out; - for (i = 0; i < KEY_PTRS(&b->key); i++) { - SET_PTR_OFFSET(&b->key, i, PTR_OFFSET(&b->key, i) + sectors); + bio->bi_sector += sectors; + bio->bi_size -= sectors << 9; - atomic_long_add(sectors, - &PTR_CACHE(c, &b->key, i)->sectors_written); + bch_keylist_add(&op->insert_keys, + &KEY(op->inode, bio->bi_sector, sectors)); } - if (b->sectors_free < c->sb.block_size) - b->sectors_free = 0; - - /* - * k takes refcounts on the buckets it points to until it's inserted - * into the btree, but if we're done with this bucket we just transfer - * get_data_bucket()'s refcount. - */ - if (b->sectors_free) - for (i = 0; i < KEY_PTRS(&b->key); i++) - atomic_inc(&PTR_BUCKET(c, &b->key, i)->pin); - - spin_unlock(&c->data_bucket_lock); - return true; + op->insert_data_done = true; + bio_put(bio); +out: + continue_at(cl, bch_data_insert_keys, bcache_wq); } -static void bch_insert_data_error(struct closure *cl) +static void bch_data_insert_error(struct closure *cl) { - struct btree_op *op = container_of(cl, struct btree_op, cl); + struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); /* * Our data write just errored, which means we've got a bunch of keys to @@ -438,35 +296,34 @@ static void bch_insert_data_error(struct closure *cl) * from the keys we'll accomplish just that. */ - struct bkey *src = op->keys.bottom, *dst = op->keys.bottom; + struct bkey *src = op->insert_keys.keys, *dst = op->insert_keys.keys; - while (src != op->keys.top) { + while (src != op->insert_keys.top) { struct bkey *n = bkey_next(src); SET_KEY_PTRS(src, 0); - bkey_copy(dst, src); + memmove(dst, src, bkey_bytes(src)); dst = bkey_next(dst); src = n; } - op->keys.top = dst; + op->insert_keys.top = dst; - bch_journal(cl); + bch_data_insert_keys(cl); } -static void bch_insert_data_endio(struct bio *bio, int error) +static void bch_data_insert_endio(struct bio *bio, int error) { struct closure *cl = bio->bi_private; - struct btree_op *op = container_of(cl, struct btree_op, cl); - struct search *s = container_of(op, struct search, op); + struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); if (error) { /* TODO: We could try to recover from this. */ - if (s->writeback) - s->error = error; - else if (s->write) - set_closure_fn(cl, bch_insert_data_error, bcache_wq); + if (op->writeback) + op->error = error; + else if (!op->replace) + set_closure_fn(cl, bch_data_insert_error, bcache_wq); else set_closure_fn(cl, NULL, NULL); } @@ -474,18 +331,17 @@ static void bch_insert_data_endio(struct bio *bio, int error) bch_bbio_endio(op->c, bio, error, "writing data to cache"); } -static void bch_insert_data_loop(struct closure *cl) +static void bch_data_insert_start(struct closure *cl) { - struct btree_op *op = container_of(cl, struct btree_op, cl); - struct search *s = container_of(op, struct search, op); - struct bio *bio = op->cache_bio, *n; + struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); + struct bio *bio = op->bio, *n; - if (op->skip) - return bio_invalidate(cl); + if (op->bypass) + return bch_data_invalidate(cl); if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) { set_gc_sectors(op->c); - bch_queue_gc(op->c); + wake_up_gc(op->c); } /* @@ -497,29 +353,30 @@ static void bch_insert_data_loop(struct closure *cl) do { unsigned i; struct bkey *k; - struct bio_set *split = s->d - ? s->d->bio_split : op->c->bio_split; + struct bio_set *split = op->c->bio_split; /* 1 for the device pointer and 1 for the chksum */ - if (bch_keylist_realloc(&op->keys, + if (bch_keylist_realloc(&op->insert_keys, 1 + (op->csum ? 1 : 0), op->c)) - continue_at(cl, bch_journal, bcache_wq); + continue_at(cl, bch_data_insert_keys, bcache_wq); - k = op->keys.top; + k = op->insert_keys.top; bkey_init(k); SET_KEY_INODE(k, op->inode); SET_KEY_OFFSET(k, bio->bi_sector); - if (!bch_alloc_sectors(k, bio_sectors(bio), s)) + if (!bch_alloc_sectors(op->c, k, bio_sectors(bio), + op->write_point, op->write_prio, + op->writeback)) goto err; n = bch_bio_split(bio, KEY_SIZE(k), GFP_NOIO, split); - n->bi_end_io = bch_insert_data_endio; + n->bi_end_io = bch_data_insert_endio; n->bi_private = cl; - if (s->writeback) { + if (op->writeback) { SET_KEY_DIRTY(k, true); for (i = 0; i < KEY_PTRS(k); i++) @@ -532,17 +389,17 @@ static void bch_insert_data_loop(struct closure *cl) bio_csum(n, k); trace_bcache_cache_insert(k); - bch_keylist_push(&op->keys); + bch_keylist_push(&op->insert_keys); n->bi_rw |= REQ_WRITE; bch_submit_bbio(n, op->c, k, 0); } while (n != bio); op->insert_data_done = true; - continue_at(cl, bch_journal, bcache_wq); + continue_at(cl, bch_data_insert_keys, bcache_wq); err: /* bch_alloc_sectors() blocks if s->writeback = true */ - BUG_ON(s->writeback); + BUG_ON(op->writeback); /* * But if it's not a writeback write we'd rather just bail out if @@ -550,15 +407,15 @@ err: * we might be starving btree writes for gc or something. */ - if (s->write) { + if (!op->replace) { /* * Writethrough write: We can't complete the write until we've * updated the index. But we don't want to delay the write while * we wait for buckets to be freed up, so just invalidate the * rest of the write. */ - op->skip = true; - return bio_invalidate(cl); + op->bypass = true; + return bch_data_invalidate(cl); } else { /* * From a cache miss, we can just insert the keys for the data @@ -567,15 +424,15 @@ err: op->insert_data_done = true; bio_put(bio); - if (!bch_keylist_empty(&op->keys)) - continue_at(cl, bch_journal, bcache_wq); + if (!bch_keylist_empty(&op->insert_keys)) + continue_at(cl, bch_data_insert_keys, bcache_wq); else closure_return(cl); } } /** - * bch_insert_data - stick some data in the cache + * bch_data_insert - stick some data in the cache * * This is the starting point for any data to end up in a cache device; it could * be from a normal write, or a writeback write, or a write to a flash only @@ -587,56 +444,179 @@ err: * data is written it calls bch_journal, and after the keys have been added to * the next journal write they're inserted into the btree. * - * It inserts the data in op->cache_bio; bi_sector is used for the key offset, + * It inserts the data in s->cache_bio; bi_sector is used for the key offset, * and op->inode is used for the key inode. * - * If op->skip is true, instead of inserting the data it invalidates the region - * of the cache represented by op->cache_bio and op->inode. + * If s->bypass is true, instead of inserting the data it invalidates the + * region of the cache represented by s->cache_bio and op->inode. */ -void bch_insert_data(struct closure *cl) +void bch_data_insert(struct closure *cl) { - struct btree_op *op = container_of(cl, struct btree_op, cl); + struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); + + trace_bcache_write(op->bio, op->writeback, op->bypass); - bch_keylist_init(&op->keys); - bio_get(op->cache_bio); - bch_insert_data_loop(cl); + bch_keylist_init(&op->insert_keys); + bio_get(op->bio); + bch_data_insert_start(cl); } -void bch_btree_insert_async(struct closure *cl) +/* Congested? */ + +unsigned bch_get_congested(struct cache_set *c) { - struct btree_op *op = container_of(cl, struct btree_op, cl); - struct search *s = container_of(op, struct search, op); + int i; + long rand; - if (bch_btree_insert(op, op->c)) { - s->error = -ENOMEM; - op->insert_data_done = true; - } + if (!c->congested_read_threshold_us && + !c->congested_write_threshold_us) + return 0; + + i = (local_clock_us() - c->congested_last_us) / 1024; + if (i < 0) + return 0; + + i += atomic_read(&c->congested); + if (i >= 0) + return 0; + + i += CONGESTED_MAX; + + if (i > 0) + i = fract_exp_two(i, 6); - if (op->insert_data_done) { - bch_keylist_free(&op->keys); - closure_return(cl); - } else - continue_at(cl, bch_insert_data_loop, bcache_wq); + rand = get_random_int(); + i -= bitmap_weight(&rand, BITS_PER_LONG); + + return i > 0 ? i : 1; } -/* Common code for the make_request functions */ +static void add_sequential(struct task_struct *t) +{ + ewma_add(t->sequential_io_avg, + t->sequential_io, 8, 0); -static void request_endio(struct bio *bio, int error) + t->sequential_io = 0; +} + +static struct hlist_head *iohash(struct cached_dev *dc, uint64_t k) { - struct closure *cl = bio->bi_private; + return &dc->io_hash[hash_64(k, RECENT_IO_BITS)]; +} - if (error) { - struct search *s = container_of(cl, struct search, cl); - s->error = error; - /* Only cache read errors are recoverable */ - s->recoverable = false; +static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) +{ + struct cache_set *c = dc->disk.c; + unsigned mode = cache_mode(dc, bio); + unsigned sectors, congested = bch_get_congested(c); + struct task_struct *task = current; + struct io *i; + + if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) || + c->gc_stats.in_use > CUTOFF_CACHE_ADD || + (bio->bi_rw & REQ_DISCARD)) + goto skip; + + if (mode == CACHE_MODE_NONE || + (mode == CACHE_MODE_WRITEAROUND && + (bio->bi_rw & REQ_WRITE))) + goto skip; + + if (bio->bi_sector & (c->sb.block_size - 1) || + bio_sectors(bio) & (c->sb.block_size - 1)) { + pr_debug("skipping unaligned io"); + goto skip; } - bio_put(bio); - closure_put(cl); + if (bypass_torture_test(dc)) { + if ((get_random_int() & 3) == 3) + goto skip; + else + goto rescale; + } + + if (!congested && !dc->sequential_cutoff) + goto rescale; + + if (!congested && + mode == CACHE_MODE_WRITEBACK && + (bio->bi_rw & REQ_WRITE) && + (bio->bi_rw & REQ_SYNC)) + goto rescale; + + spin_lock(&dc->io_lock); + + hlist_for_each_entry(i, iohash(dc, bio->bi_sector), hash) + if (i->last == bio->bi_sector && + time_before(jiffies, i->jiffies)) + goto found; + + i = list_first_entry(&dc->io_lru, struct io, lru); + + add_sequential(task); + i->sequential = 0; +found: + if (i->sequential + bio->bi_size > i->sequential) + i->sequential += bio->bi_size; + + i->last = bio_end_sector(bio); + i->jiffies = jiffies + msecs_to_jiffies(5000); + task->sequential_io = i->sequential; + + hlist_del(&i->hash); + hlist_add_head(&i->hash, iohash(dc, i->last)); + list_move_tail(&i->lru, &dc->io_lru); + + spin_unlock(&dc->io_lock); + + sectors = max(task->sequential_io, + task->sequential_io_avg) >> 9; + + if (dc->sequential_cutoff && + sectors >= dc->sequential_cutoff >> 9) { + trace_bcache_bypass_sequential(bio); + goto skip; + } + + if (congested && sectors >= congested) { + trace_bcache_bypass_congested(bio); + goto skip; + } + +rescale: + bch_rescale_priorities(c, bio_sectors(bio)); + return false; +skip: + bch_mark_sectors_bypassed(c, dc, bio_sectors(bio)); + return true; } -void bch_cache_read_endio(struct bio *bio, int error) +/* Cache lookup */ + +struct search { + /* Stack frame for bio_complete */ + struct closure cl; + + struct bcache_device *d; + + struct bbio bio; + struct bio *orig_bio; + struct bio *cache_miss; + + unsigned insert_bio_sectors; + + unsigned recoverable:1; + unsigned unaligned_bvec:1; + unsigned write:1; + unsigned read_dirty_data:1; + + unsigned long start_time; + + struct btree_op op; + struct data_insert_op iop; +}; + +static void bch_cache_read_endio(struct bio *bio, int error) { struct bbio *b = container_of(bio, struct bbio, bio); struct closure *cl = bio->bi_private; @@ -650,13 +630,113 @@ void bch_cache_read_endio(struct bio *bio, int error) */ if (error) - s->error = error; - else if (ptr_stale(s->op.c, &b->key, 0)) { - atomic_long_inc(&s->op.c->cache_read_races); - s->error = -EINTR; + s->iop.error = error; + else if (ptr_stale(s->iop.c, &b->key, 0)) { + atomic_long_inc(&s->iop.c->cache_read_races); + s->iop.error = -EINTR; } - bch_bbio_endio(s->op.c, bio, error, "reading from cache"); + bch_bbio_endio(s->iop.c, bio, error, "reading from cache"); +} + +/* + * Read from a single key, handling the initial cache miss if the key starts in + * the middle of the bio + */ +static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k) +{ + struct search *s = container_of(op, struct search, op); + struct bio *n, *bio = &s->bio.bio; + struct bkey *bio_key; + unsigned ptr; + + if (bkey_cmp(k, &KEY(s->iop.inode, bio->bi_sector, 0)) <= 0) + return MAP_CONTINUE; + + if (KEY_INODE(k) != s->iop.inode || + KEY_START(k) > bio->bi_sector) { + unsigned bio_sectors = bio_sectors(bio); + unsigned sectors = KEY_INODE(k) == s->iop.inode + ? min_t(uint64_t, INT_MAX, + KEY_START(k) - bio->bi_sector) + : INT_MAX; + + int ret = s->d->cache_miss(b, s, bio, sectors); + if (ret != MAP_CONTINUE) + return ret; + + /* if this was a complete miss we shouldn't get here */ + BUG_ON(bio_sectors <= sectors); + } + + if (!KEY_SIZE(k)) + return MAP_CONTINUE; + + /* XXX: figure out best pointer - for multiple cache devices */ + ptr = 0; + + PTR_BUCKET(b->c, k, ptr)->prio = INITIAL_PRIO; + + if (KEY_DIRTY(k)) + s->read_dirty_data = true; + + n = bch_bio_split(bio, min_t(uint64_t, INT_MAX, + KEY_OFFSET(k) - bio->bi_sector), + GFP_NOIO, s->d->bio_split); + + bio_key = &container_of(n, struct bbio, bio)->key; + bch_bkey_copy_single_ptr(bio_key, k, ptr); + + bch_cut_front(&KEY(s->iop.inode, n->bi_sector, 0), bio_key); + bch_cut_back(&KEY(s->iop.inode, bio_end_sector(n), 0), bio_key); + + n->bi_end_io = bch_cache_read_endio; + n->bi_private = &s->cl; + + /* + * The bucket we're reading from might be reused while our bio + * is in flight, and we could then end up reading the wrong + * data. + * + * We guard against this by checking (in cache_read_endio()) if + * the pointer is stale again; if so, we treat it as an error + * and reread from the backing device (but we don't pass that + * error up anywhere). + */ + + __bch_submit_bbio(n, b->c); + return n == bio ? MAP_DONE : MAP_CONTINUE; +} + +static void cache_lookup(struct closure *cl) +{ + struct search *s = container_of(cl, struct search, iop.cl); + struct bio *bio = &s->bio.bio; + + int ret = bch_btree_map_keys(&s->op, s->iop.c, + &KEY(s->iop.inode, bio->bi_sector, 0), + cache_lookup_fn, MAP_END_KEY); + if (ret == -EAGAIN) + continue_at(cl, cache_lookup, bcache_wq); + + closure_return(cl); +} + +/* Common code for the make_request functions */ + +static void request_endio(struct bio *bio, int error) +{ + struct closure *cl = bio->bi_private; + + if (error) { + struct search *s = container_of(cl, struct search, cl); + s->iop.error = error; + /* Only cache read errors are recoverable */ + s->recoverable = false; + } + + bio_put(bio); + closure_put(cl); } static void bio_complete(struct search *s) @@ -670,8 +750,8 @@ static void bio_complete(struct search *s) part_stat_add(cpu, &s->d->disk->part0, ticks[rw], duration); part_stat_unlock(); - trace_bcache_request_end(s, s->orig_bio); - bio_endio(s->orig_bio, s->error); + trace_bcache_request_end(s->d, s->orig_bio); + bio_endio(s->orig_bio, s->iop.error); s->orig_bio = NULL; } } @@ -691,8 +771,8 @@ static void search_free(struct closure *cl) struct search *s = container_of(cl, struct search, cl); bio_complete(s); - if (s->op.cache_bio) - bio_put(s->op.cache_bio); + if (s->iop.bio) + bio_put(s->iop.bio); if (s->unaligned_bvec) mempool_free(s->bio.bio.bi_io_vec, s->d->unaligned_bvec); @@ -703,21 +783,22 @@ static void search_free(struct closure *cl) static struct search *search_alloc(struct bio *bio, struct bcache_device *d) { + struct search *s; struct bio_vec *bv; - struct search *s = mempool_alloc(d->c->search, GFP_NOIO); - memset(s, 0, offsetof(struct search, op.keys)); + + s = mempool_alloc(d->c->search, GFP_NOIO); + memset(s, 0, offsetof(struct search, iop.insert_keys)); __closure_init(&s->cl, NULL); - s->op.inode = d->id; - s->op.c = d->c; + s->iop.inode = d->id; + s->iop.c = d->c; s->d = d; s->op.lock = -1; - s->task = current; + s->iop.write_point = hash_long((unsigned long) current, 16); s->orig_bio = bio; s->write = (bio->bi_rw & REQ_WRITE) != 0; - s->op.flush_journal = (bio->bi_rw & (REQ_FLUSH|REQ_FUA)) != 0; - s->op.skip = (bio->bi_rw & REQ_DISCARD) != 0; + s->iop.flush_journal = (bio->bi_rw & (REQ_FLUSH|REQ_FUA)) != 0; s->recoverable = 1; s->start_time = jiffies; do_bio_hook(s); @@ -734,18 +815,6 @@ static struct search *search_alloc(struct bio *bio, struct bcache_device *d) return s; } -static void btree_read_async(struct closure *cl) -{ - struct btree_op *op = container_of(cl, struct btree_op, cl); - - int ret = btree_root(search_recurse, op->c, op); - - if (ret == -EAGAIN) - continue_at(cl, btree_read_async, bcache_wq); - - closure_return(cl); -} - /* Cached devices */ static void cached_dev_bio_complete(struct closure *cl) @@ -759,27 +828,28 @@ static void cached_dev_bio_complete(struct closure *cl) /* Process reads */ -static void cached_dev_read_complete(struct closure *cl) +static void cached_dev_cache_miss_done(struct closure *cl) { struct search *s = container_of(cl, struct search, cl); - if (s->op.insert_collision) - bch_mark_cache_miss_collision(s); + if (s->iop.replace_collision) + bch_mark_cache_miss_collision(s->iop.c, s->d); - if (s->op.cache_bio) { + if (s->iop.bio) { int i; struct bio_vec *bv; - __bio_for_each_segment(bv, s->op.cache_bio, i, 0) + bio_for_each_segment_all(bv, s->iop.bio, i) __free_page(bv->bv_page); } cached_dev_bio_complete(cl); } -static void request_read_error(struct closure *cl) +static void cached_dev_read_error(struct closure *cl) { struct search *s = container_of(cl, struct search, cl); + struct bio *bio = &s->bio.bio; struct bio_vec *bv; int i; @@ -787,7 +857,7 @@ static void request_read_error(struct closure *cl) /* Retry from the backing device: */ trace_bcache_read_retry(s->orig_bio); - s->error = 0; + s->iop.error = 0; bv = s->bio.bio.bi_io_vec; do_bio_hook(s); s->bio.bio.bi_io_vec = bv; @@ -803,146 +873,148 @@ static void request_read_error(struct closure *cl) /* XXX: invalidate cache */ - closure_bio_submit(&s->bio.bio, &s->cl, s->d); + closure_bio_submit(bio, cl, s->d); } - continue_at(cl, cached_dev_read_complete, NULL); + continue_at(cl, cached_dev_cache_miss_done, NULL); } -static void request_read_done(struct closure *cl) +static void cached_dev_read_done(struct closure *cl) { struct search *s = container_of(cl, struct search, cl); struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); /* - * s->cache_bio != NULL implies that we had a cache miss; cache_bio now - * contains data ready to be inserted into the cache. + * We had a cache miss; cache_bio now contains data ready to be inserted + * into the cache. * * First, we copy the data we just read from cache_bio's bounce buffers * to the buffers the original bio pointed to: */ - if (s->op.cache_bio) { - bio_reset(s->op.cache_bio); - s->op.cache_bio->bi_sector = s->cache_miss->bi_sector; - s->op.cache_bio->bi_bdev = s->cache_miss->bi_bdev; - s->op.cache_bio->bi_size = s->cache_bio_sectors << 9; - bch_bio_map(s->op.cache_bio, NULL); + if (s->iop.bio) { + bio_reset(s->iop.bio); + s->iop.bio->bi_sector = s->cache_miss->bi_sector; + s->iop.bio->bi_bdev = s->cache_miss->bi_bdev; + s->iop.bio->bi_size = s->insert_bio_sectors << 9; + bch_bio_map(s->iop.bio, NULL); - bio_copy_data(s->cache_miss, s->op.cache_bio); + bio_copy_data(s->cache_miss, s->iop.bio); bio_put(s->cache_miss); s->cache_miss = NULL; } - if (verify(dc, &s->bio.bio) && s->recoverable) - bch_data_verify(s); + if (verify(dc, &s->bio.bio) && s->recoverable && + !s->unaligned_bvec && !s->read_dirty_data) + bch_data_verify(dc, s->orig_bio); bio_complete(s); - if (s->op.cache_bio && - !test_bit(CACHE_SET_STOPPING, &s->op.c->flags)) { - s->op.type = BTREE_REPLACE; - closure_call(&s->op.cl, bch_insert_data, NULL, cl); + if (s->iop.bio && + !test_bit(CACHE_SET_STOPPING, &s->iop.c->flags)) { + BUG_ON(!s->iop.replace); + closure_call(&s->iop.cl, bch_data_insert, NULL, cl); } - continue_at(cl, cached_dev_read_complete, NULL); + continue_at(cl, cached_dev_cache_miss_done, NULL); } -static void request_read_done_bh(struct closure *cl) +static void cached_dev_read_done_bh(struct closure *cl) { struct search *s = container_of(cl, struct search, cl); struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); - bch_mark_cache_accounting(s, !s->cache_miss, s->op.skip); - trace_bcache_read(s->orig_bio, !s->cache_miss, s->op.skip); + bch_mark_cache_accounting(s->iop.c, s->d, + !s->cache_miss, s->iop.bypass); + trace_bcache_read(s->orig_bio, !s->cache_miss, s->iop.bypass); - if (s->error) - continue_at_nobarrier(cl, request_read_error, bcache_wq); - else if (s->op.cache_bio || verify(dc, &s->bio.bio)) - continue_at_nobarrier(cl, request_read_done, bcache_wq); + if (s->iop.error) + continue_at_nobarrier(cl, cached_dev_read_error, bcache_wq); + else if (s->iop.bio || verify(dc, &s->bio.bio)) + continue_at_nobarrier(cl, cached_dev_read_done, bcache_wq); else - continue_at_nobarrier(cl, cached_dev_read_complete, NULL); + continue_at_nobarrier(cl, cached_dev_bio_complete, NULL); } static int cached_dev_cache_miss(struct btree *b, struct search *s, struct bio *bio, unsigned sectors) { - int ret = 0; - unsigned reada; + int ret = MAP_CONTINUE; + unsigned reada = 0; struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); - struct bio *miss; + struct bio *miss, *cache_bio; - miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split); - if (miss == bio) - s->op.lookup_done = true; - - miss->bi_end_io = request_endio; - miss->bi_private = &s->cl; - - if (s->cache_miss || s->op.skip) + if (s->cache_miss || s->iop.bypass) { + miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split); + ret = miss == bio ? MAP_DONE : MAP_CONTINUE; goto out_submit; - - if (miss != bio || - (bio->bi_rw & REQ_RAHEAD) || - (bio->bi_rw & REQ_META) || - s->op.c->gc_stats.in_use >= CUTOFF_CACHE_READA) - reada = 0; - else { - reada = min(dc->readahead >> 9, - sectors - bio_sectors(miss)); - - if (bio_end_sector(miss) + reada > bdev_sectors(miss->bi_bdev)) - reada = bdev_sectors(miss->bi_bdev) - - bio_end_sector(miss); } - s->cache_bio_sectors = bio_sectors(miss) + reada; - s->op.cache_bio = bio_alloc_bioset(GFP_NOWAIT, - DIV_ROUND_UP(s->cache_bio_sectors, PAGE_SECTORS), - dc->disk.bio_split); + if (!(bio->bi_rw & REQ_RAHEAD) && + !(bio->bi_rw & REQ_META) && + s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA) + reada = min_t(sector_t, dc->readahead >> 9, + bdev_sectors(bio->bi_bdev) - bio_end_sector(bio)); - if (!s->op.cache_bio) - goto out_submit; + s->insert_bio_sectors = min(sectors, bio_sectors(bio) + reada); - s->op.cache_bio->bi_sector = miss->bi_sector; - s->op.cache_bio->bi_bdev = miss->bi_bdev; - s->op.cache_bio->bi_size = s->cache_bio_sectors << 9; + s->iop.replace_key = KEY(s->iop.inode, + bio->bi_sector + s->insert_bio_sectors, + s->insert_bio_sectors); - s->op.cache_bio->bi_end_io = request_endio; - s->op.cache_bio->bi_private = &s->cl; + ret = bch_btree_insert_check_key(b, &s->op, &s->iop.replace_key); + if (ret) + return ret; + + s->iop.replace = true; + + miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split); /* btree_search_recurse()'s btree iterator is no good anymore */ - ret = -EINTR; - if (!bch_btree_insert_check_key(b, &s->op, s->op.cache_bio)) - goto out_put; + ret = miss == bio ? MAP_DONE : -EINTR; - bch_bio_map(s->op.cache_bio, NULL); - if (bio_alloc_pages(s->op.cache_bio, __GFP_NOWARN|GFP_NOIO)) + cache_bio = bio_alloc_bioset(GFP_NOWAIT, + DIV_ROUND_UP(s->insert_bio_sectors, PAGE_SECTORS), + dc->disk.bio_split); + if (!cache_bio) + goto out_submit; + + cache_bio->bi_sector = miss->bi_sector; + cache_bio->bi_bdev = miss->bi_bdev; + cache_bio->bi_size = s->insert_bio_sectors << 9; + + cache_bio->bi_end_io = request_endio; + cache_bio->bi_private = &s->cl; + + bch_bio_map(cache_bio, NULL); + if (bio_alloc_pages(cache_bio, __GFP_NOWARN|GFP_NOIO)) goto out_put; - s->cache_miss = miss; - bio_get(s->op.cache_bio); + if (reada) + bch_mark_cache_readahead(s->iop.c, s->d); - closure_bio_submit(s->op.cache_bio, &s->cl, s->d); + s->cache_miss = miss; + s->iop.bio = cache_bio; + bio_get(cache_bio); + closure_bio_submit(cache_bio, &s->cl, s->d); return ret; out_put: - bio_put(s->op.cache_bio); - s->op.cache_bio = NULL; + bio_put(cache_bio); out_submit: + miss->bi_end_io = request_endio; + miss->bi_private = &s->cl; closure_bio_submit(miss, &s->cl, s->d); return ret; } -static void request_read(struct cached_dev *dc, struct search *s) +static void cached_dev_read(struct cached_dev *dc, struct search *s) { struct closure *cl = &s->cl; - check_should_skip(dc, s); - closure_call(&s->op.cl, btree_read_async, NULL, cl); - - continue_at(cl, request_read_done_bh, NULL); + closure_call(&s->iop.cl, cache_lookup, NULL, cl); + continue_at(cl, cached_dev_read_done_bh, NULL); } /* Process writes */ @@ -956,88 +1028,85 @@ static void cached_dev_write_complete(struct closure *cl) cached_dev_bio_complete(cl); } -static void request_write(struct cached_dev *dc, struct search *s) +static void cached_dev_write(struct cached_dev *dc, struct search *s) { struct closure *cl = &s->cl; struct bio *bio = &s->bio.bio; - struct bkey start, end; - start = KEY(dc->disk.id, bio->bi_sector, 0); - end = KEY(dc->disk.id, bio_end_sector(bio), 0); + struct bkey start = KEY(dc->disk.id, bio->bi_sector, 0); + struct bkey end = KEY(dc->disk.id, bio_end_sector(bio), 0); - bch_keybuf_check_overlapping(&s->op.c->moving_gc_keys, &start, &end); + bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys, &start, &end); - check_should_skip(dc, s); down_read_non_owner(&dc->writeback_lock); - if (bch_keybuf_check_overlapping(&dc->writeback_keys, &start, &end)) { - s->op.skip = false; - s->writeback = true; + /* + * We overlap with some dirty data undergoing background + * writeback, force this write to writeback + */ + s->iop.bypass = false; + s->iop.writeback = true; } + /* + * Discards aren't _required_ to do anything, so skipping if + * check_overlapping returned true is ok + * + * But check_overlapping drops dirty keys for which io hasn't started, + * so we still want to call it. + */ if (bio->bi_rw & REQ_DISCARD) - goto skip; + s->iop.bypass = true; if (should_writeback(dc, s->orig_bio, cache_mode(dc, bio), - s->op.skip)) { - s->op.skip = false; - s->writeback = true; + s->iop.bypass)) { + s->iop.bypass = false; + s->iop.writeback = true; } - if (s->op.skip) - goto skip; - - trace_bcache_write(s->orig_bio, s->writeback, s->op.skip); + if (s->iop.bypass) { + s->iop.bio = s->orig_bio; + bio_get(s->iop.bio); - if (!s->writeback) { - s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO, - dc->disk.bio_split); - - closure_bio_submit(bio, cl, s->d); - } else { + if (!(bio->bi_rw & REQ_DISCARD) || + blk_queue_discard(bdev_get_queue(dc->bdev))) + closure_bio_submit(bio, cl, s->d); + } else if (s->iop.writeback) { bch_writeback_add(dc); + s->iop.bio = bio; - if (s->op.flush_journal) { + if (bio->bi_rw & REQ_FLUSH) { /* Also need to send a flush to the backing device */ - s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO, - dc->disk.bio_split); + struct bio *flush = bio_alloc_bioset(GFP_NOIO, 0, + dc->disk.bio_split); - bio->bi_size = 0; - bio->bi_vcnt = 0; - closure_bio_submit(bio, cl, s->d); - } else { - s->op.cache_bio = bio; + flush->bi_rw = WRITE_FLUSH; + flush->bi_bdev = bio->bi_bdev; + flush->bi_end_io = request_endio; + flush->bi_private = cl; + + closure_bio_submit(flush, cl, s->d); } - } -out: - closure_call(&s->op.cl, bch_insert_data, NULL, cl); - continue_at(cl, cached_dev_write_complete, NULL); -skip: - s->op.skip = true; - s->op.cache_bio = s->orig_bio; - bio_get(s->op.cache_bio); + } else { + s->iop.bio = bio_clone_bioset(bio, GFP_NOIO, + dc->disk.bio_split); - if ((bio->bi_rw & REQ_DISCARD) && - !blk_queue_discard(bdev_get_queue(dc->bdev))) - goto out; + closure_bio_submit(bio, cl, s->d); + } - closure_bio_submit(bio, cl, s->d); - goto out; + closure_call(&s->iop.cl, bch_data_insert, NULL, cl); + continue_at(cl, cached_dev_write_complete, NULL); } -static void request_nodata(struct cached_dev *dc, struct search *s) +static void cached_dev_nodata(struct closure *cl) { - struct closure *cl = &s->cl; + struct search *s = container_of(cl, struct search, cl); struct bio *bio = &s->bio.bio; - if (bio->bi_rw & REQ_DISCARD) { - request_write(dc, s); - return; - } - - if (s->op.flush_journal) - bch_journal_meta(s->op.c, cl); + if (s->iop.flush_journal) + bch_journal_meta(s->iop.c, cl); + /* If it's a flush, we send the flush to the backing device too */ closure_bio_submit(bio, cl, s->d); continue_at(cl, cached_dev_bio_complete, NULL); @@ -1045,134 +1114,6 @@ static void request_nodata(struct cached_dev *dc, struct search *s) /* Cached devices - read & write stuff */ -unsigned bch_get_congested(struct cache_set *c) -{ - int i; - long rand; - - if (!c->congested_read_threshold_us && - !c->congested_write_threshold_us) - return 0; - - i = (local_clock_us() - c->congested_last_us) / 1024; - if (i < 0) - return 0; - - i += atomic_read(&c->congested); - if (i >= 0) - return 0; - - i += CONGESTED_MAX; - - if (i > 0) - i = fract_exp_two(i, 6); - - rand = get_random_int(); - i -= bitmap_weight(&rand, BITS_PER_LONG); - - return i > 0 ? i : 1; -} - -static void add_sequential(struct task_struct *t) -{ - ewma_add(t->sequential_io_avg, - t->sequential_io, 8, 0); - - t->sequential_io = 0; -} - -static struct hlist_head *iohash(struct cached_dev *dc, uint64_t k) -{ - return &dc->io_hash[hash_64(k, RECENT_IO_BITS)]; -} - -static void check_should_skip(struct cached_dev *dc, struct search *s) -{ - struct cache_set *c = s->op.c; - struct bio *bio = &s->bio.bio; - unsigned mode = cache_mode(dc, bio); - unsigned sectors, congested = bch_get_congested(c); - - if (atomic_read(&dc->disk.detaching) || - c->gc_stats.in_use > CUTOFF_CACHE_ADD || - (bio->bi_rw & REQ_DISCARD)) - goto skip; - - if (mode == CACHE_MODE_NONE || - (mode == CACHE_MODE_WRITEAROUND && - (bio->bi_rw & REQ_WRITE))) - goto skip; - - if (bio->bi_sector & (c->sb.block_size - 1) || - bio_sectors(bio) & (c->sb.block_size - 1)) { - pr_debug("skipping unaligned io"); - goto skip; - } - - if (!congested && !dc->sequential_cutoff) - goto rescale; - - if (!congested && - mode == CACHE_MODE_WRITEBACK && - (bio->bi_rw & REQ_WRITE) && - (bio->bi_rw & REQ_SYNC)) - goto rescale; - - if (dc->sequential_merge) { - struct io *i; - - spin_lock(&dc->io_lock); - - hlist_for_each_entry(i, iohash(dc, bio->bi_sector), hash) - if (i->last == bio->bi_sector && - time_before(jiffies, i->jiffies)) - goto found; - - i = list_first_entry(&dc->io_lru, struct io, lru); - - add_sequential(s->task); - i->sequential = 0; -found: - if (i->sequential + bio->bi_size > i->sequential) - i->sequential += bio->bi_size; - - i->last = bio_end_sector(bio); - i->jiffies = jiffies + msecs_to_jiffies(5000); - s->task->sequential_io = i->sequential; - - hlist_del(&i->hash); - hlist_add_head(&i->hash, iohash(dc, i->last)); - list_move_tail(&i->lru, &dc->io_lru); - - spin_unlock(&dc->io_lock); - } else { - s->task->sequential_io = bio->bi_size; - - add_sequential(s->task); - } - - sectors = max(s->task->sequential_io, - s->task->sequential_io_avg) >> 9; - - if (dc->sequential_cutoff && - sectors >= dc->sequential_cutoff >> 9) { - trace_bcache_bypass_sequential(s->orig_bio); - goto skip; - } - - if (congested && sectors >= congested) { - trace_bcache_bypass_congested(s->orig_bio); - goto skip; - } - -rescale: - bch_rescale_priorities(c, bio_sectors(bio)); - return; -skip: - bch_mark_sectors_bypassed(s, bio_sectors(bio)); - s->op.skip = true; -} - static void cached_dev_make_request(struct request_queue *q, struct bio *bio) { struct search *s; @@ -1190,14 +1131,24 @@ static void cached_dev_make_request(struct request_queue *q, struct bio *bio) if (cached_dev_get(dc)) { s = search_alloc(bio, d); - trace_bcache_request_start(s, bio); + trace_bcache_request_start(s->d, bio); + + if (!bio->bi_size) { + /* + * can't call bch_journal_meta from under + * generic_make_request + */ + continue_at_nobarrier(&s->cl, + cached_dev_nodata, + bcache_wq); + } else { + s->iop.bypass = check_should_bypass(dc, bio); - if (!bio_has_data(bio)) - request_nodata(dc, s); - else if (rw) - request_write(dc, s); - else - request_read(dc, s); + if (rw) + cached_dev_write(dc, s); + else + cached_dev_read(dc, s); + } } else { if ((bio->bi_rw & REQ_DISCARD) && !blk_queue_discard(bdev_get_queue(dc->bdev))) @@ -1272,9 +1223,19 @@ static int flash_dev_cache_miss(struct btree *b, struct search *s, bio_advance(bio, min(sectors << 9, bio->bi_size)); if (!bio->bi_size) - s->op.lookup_done = true; + return MAP_DONE; - return 0; + return MAP_CONTINUE; +} + +static void flash_dev_nodata(struct closure *cl) +{ + struct search *s = container_of(cl, struct search, cl); + + if (s->iop.flush_journal) + bch_journal_meta(s->iop.c, cl); + + continue_at(cl, search_free, NULL); } static void flash_dev_make_request(struct request_queue *q, struct bio *bio) @@ -1293,23 +1254,28 @@ static void flash_dev_make_request(struct request_queue *q, struct bio *bio) cl = &s->cl; bio = &s->bio.bio; - trace_bcache_request_start(s, bio); + trace_bcache_request_start(s->d, bio); - if (bio_has_data(bio) && !rw) { - closure_call(&s->op.cl, btree_read_async, NULL, cl); - } else if (bio_has_data(bio) || s->op.skip) { - bch_keybuf_check_overlapping(&s->op.c->moving_gc_keys, + if (!bio->bi_size) { + /* + * can't call bch_journal_meta from under + * generic_make_request + */ + continue_at_nobarrier(&s->cl, + flash_dev_nodata, + bcache_wq); + } else if (rw) { + bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys, &KEY(d->id, bio->bi_sector, 0), &KEY(d->id, bio_end_sector(bio), 0)); - s->writeback = true; - s->op.cache_bio = bio; + s->iop.bypass = (bio->bi_rw & REQ_DISCARD) != 0; + s->iop.writeback = true; + s->iop.bio = bio; - closure_call(&s->op.cl, bch_insert_data, NULL, cl); + closure_call(&s->iop.cl, bch_data_insert, NULL, cl); } else { - /* No data - probably a cache flush */ - if (s->op.flush_journal) - bch_journal_meta(s->op.c, cl); + closure_call(&s->iop.cl, cache_lookup, NULL, cl); } continue_at(cl, search_free, NULL); diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index 57dc478..2cd65bf 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -3,40 +3,33 @@ #include <linux/cgroup.h> -struct search { - /* Stack frame for bio_complete */ +struct data_insert_op { struct closure cl; + struct cache_set *c; + struct bio *bio; - struct bcache_device *d; - struct task_struct *task; - - struct bbio bio; - struct bio *orig_bio; - struct bio *cache_miss; - unsigned cache_bio_sectors; - - unsigned recoverable:1; - unsigned unaligned_bvec:1; + unsigned inode; + uint16_t write_point; + uint16_t write_prio; + short error; - unsigned write:1; + unsigned bypass:1; unsigned writeback:1; + unsigned flush_journal:1; + unsigned csum:1; - /* IO error returned to s->bio */ - short error; - unsigned long start_time; + unsigned replace:1; + unsigned replace_collision:1; + + unsigned insert_data_done:1; - /* Anything past op->keys won't get zeroed in do_bio_hook */ - struct btree_op op; + /* Anything past this point won't get zeroed in search_alloc() */ + struct keylist insert_keys; + BKEY_PADDED(replace_key); }; -void bch_cache_read_endio(struct bio *, int); unsigned bch_get_congested(struct cache_set *); -void bch_insert_data(struct closure *cl); -void bch_btree_insert_async(struct closure *); -void bch_cache_read_endio(struct bio *, int); - -void bch_open_buckets_free(struct cache_set *); -int bch_open_buckets_alloc(struct cache_set *); +void bch_data_insert(struct closure *cl); void bch_cached_dev_request_init(struct cached_dev *dc); void bch_flash_dev_request_init(struct bcache_device *d); diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c index b8730e7..84d0782 100644 --- a/drivers/md/bcache/stats.c +++ b/drivers/md/bcache/stats.c @@ -7,7 +7,6 @@ #include "bcache.h" #include "stats.h" #include "btree.h" -#include "request.h" #include "sysfs.h" /* @@ -196,35 +195,36 @@ static void mark_cache_stats(struct cache_stat_collector *stats, atomic_inc(&stats->cache_bypass_misses); } -void bch_mark_cache_accounting(struct search *s, bool hit, bool bypass) +void bch_mark_cache_accounting(struct cache_set *c, struct bcache_device *d, + bool hit, bool bypass) { - struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); + struct cached_dev *dc = container_of(d, struct cached_dev, disk); mark_cache_stats(&dc->accounting.collector, hit, bypass); - mark_cache_stats(&s->op.c->accounting.collector, hit, bypass); + mark_cache_stats(&c->accounting.collector, hit, bypass); #ifdef CONFIG_CGROUP_BCACHE mark_cache_stats(&(bch_bio_to_cgroup(s->orig_bio)->stats), hit, bypass); #endif } -void bch_mark_cache_readahead(struct search *s) +void bch_mark_cache_readahead(struct cache_set *c, struct bcache_device *d) { - struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); + struct cached_dev *dc = container_of(d, struct cached_dev, disk); atomic_inc(&dc->accounting.collector.cache_readaheads); - atomic_inc(&s->op.c->accounting.collector.cache_readaheads); + atomic_inc(&c->accounting.collector.cache_readaheads); } -void bch_mark_cache_miss_collision(struct search *s) +void bch_mark_cache_miss_collision(struct cache_set *c, struct bcache_device *d) { - struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); + struct cached_dev *dc = container_of(d, struct cached_dev, disk); atomic_inc(&dc->accounting.collector.cache_miss_collisions); - atomic_inc(&s->op.c->accounting.collector.cache_miss_collisions); + atomic_inc(&c->accounting.collector.cache_miss_collisions); } -void bch_mark_sectors_bypassed(struct search *s, int sectors) +void bch_mark_sectors_bypassed(struct cache_set *c, struct cached_dev *dc, + int sectors) { - struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); atomic_add(sectors, &dc->accounting.collector.sectors_bypassed); - atomic_add(sectors, &s->op.c->accounting.collector.sectors_bypassed); + atomic_add(sectors, &c->accounting.collector.sectors_bypassed); } void bch_cache_accounting_init(struct cache_accounting *acc, diff --git a/drivers/md/bcache/stats.h b/drivers/md/bcache/stats.h index c7c7a8f..adbff14 100644 --- a/drivers/md/bcache/stats.h +++ b/drivers/md/bcache/stats.h @@ -38,7 +38,9 @@ struct cache_accounting { struct cache_stats day; }; -struct search; +struct cache_set; +struct cached_dev; +struct bcache_device; void bch_cache_accounting_init(struct cache_accounting *acc, struct closure *parent); @@ -50,9 +52,10 @@ void bch_cache_accounting_clear(struct cache_accounting *acc); void bch_cache_accounting_destroy(struct cache_accounting *acc); -void bch_mark_cache_accounting(struct search *s, bool hit, bool bypass); -void bch_mark_cache_readahead(struct search *s); -void bch_mark_cache_miss_collision(struct search *s); -void bch_mark_sectors_bypassed(struct search *s, int sectors); +void bch_mark_cache_accounting(struct cache_set *, struct bcache_device *, + bool, bool); +void bch_mark_cache_readahead(struct cache_set *, struct bcache_device *); +void bch_mark_cache_miss_collision(struct cache_set *, struct bcache_device *); +void bch_mark_sectors_bypassed(struct cache_set *, struct cached_dev *, int); #endif /* _BCACHE_STATS_H_ */ diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 547c4c5..dec15cd 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -16,6 +16,7 @@ #include <linux/buffer_head.h> #include <linux/debugfs.h> #include <linux/genhd.h> +#include <linux/idr.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/random.h> @@ -45,21 +46,13 @@ const char * const bch_cache_modes[] = { NULL }; -struct uuid_entry_v0 { - uint8_t uuid[16]; - uint8_t label[32]; - uint32_t first_reg; - uint32_t last_reg; - uint32_t invalidated; - uint32_t pad; -}; - static struct kobject *bcache_kobj; struct mutex bch_register_lock; LIST_HEAD(bch_cache_sets); static LIST_HEAD(uncached_devices); -static int bcache_major, bcache_minor; +static int bcache_major; +static DEFINE_IDA(bcache_minor); static wait_queue_head_t unregister_wait; struct workqueue_struct *bcache_wq; @@ -382,7 +375,7 @@ static char *uuid_read(struct cache_set *c, struct jset *j, struct closure *cl) { struct bkey *k = &j->uuid_bucket; - if (__bch_ptr_invalid(c, 1, k)) + if (bch_btree_ptr_invalid(c, k)) return "bad uuid pointer"; bkey_copy(&c->uuid_bucket, k); @@ -427,7 +420,7 @@ static int __uuid_write(struct cache_set *c) lockdep_assert_held(&bch_register_lock); - if (bch_bucket_alloc_set(c, WATERMARK_METADATA, &k.key, 1, &cl)) + if (bch_bucket_alloc_set(c, WATERMARK_METADATA, &k.key, 1, true)) return 1; SET_KEY_SIZE(&k.key, c->sb.bucket_size); @@ -435,7 +428,7 @@ static int __uuid_write(struct cache_set *c) closure_sync(&cl); bkey_copy(&c->uuid_bucket, &k.key); - __bkey_put(c, &k.key); + bkey_put(c, &k.key); return 0; } @@ -562,10 +555,10 @@ void bch_prio_write(struct cache *ca) } p->next_bucket = ca->prio_buckets[i + 1]; - p->magic = pset_magic(ca); + p->magic = pset_magic(&ca->sb); p->csum = bch_crc64(&p->magic, bucket_bytes(ca) - 8); - bucket = bch_bucket_alloc(ca, WATERMARK_PRIO, &cl); + bucket = bch_bucket_alloc(ca, WATERMARK_PRIO, true); BUG_ON(bucket == -1); mutex_unlock(&ca->set->bucket_lock); @@ -613,7 +606,7 @@ static void prio_read(struct cache *ca, uint64_t bucket) if (p->csum != bch_crc64(&p->magic, bucket_bytes(ca) - 8)) pr_warn("bad csum reading priorities"); - if (p->magic != pset_magic(ca)) + if (p->magic != pset_magic(&ca->sb)) pr_warn("bad magic reading priorities"); bucket = p->next_bucket; @@ -630,7 +623,7 @@ static void prio_read(struct cache *ca, uint64_t bucket) static int open_dev(struct block_device *b, fmode_t mode) { struct bcache_device *d = b->bd_disk->private_data; - if (atomic_read(&d->closing)) + if (test_bit(BCACHE_DEV_CLOSING, &d->flags)) return -ENXIO; closure_get(&d->cl); @@ -659,20 +652,24 @@ static const struct block_device_operations bcache_ops = { void bcache_device_stop(struct bcache_device *d) { - if (!atomic_xchg(&d->closing, 1)) + if (!test_and_set_bit(BCACHE_DEV_CLOSING, &d->flags)) closure_queue(&d->cl); } static void bcache_device_unlink(struct bcache_device *d) { - unsigned i; - struct cache *ca; + lockdep_assert_held(&bch_register_lock); - sysfs_remove_link(&d->c->kobj, d->name); - sysfs_remove_link(&d->kobj, "cache"); + if (d->c && !test_and_set_bit(BCACHE_DEV_UNLINK_DONE, &d->flags)) { + unsigned i; + struct cache *ca; - for_each_cache(ca, d->c, i) - bd_unlink_disk_holder(ca->bdev, d->disk); + sysfs_remove_link(&d->c->kobj, d->name); + sysfs_remove_link(&d->kobj, "cache"); + + for_each_cache(ca, d->c, i) + bd_unlink_disk_holder(ca->bdev, d->disk); + } } static void bcache_device_link(struct bcache_device *d, struct cache_set *c, @@ -696,19 +693,16 @@ static void bcache_device_detach(struct bcache_device *d) { lockdep_assert_held(&bch_register_lock); - if (atomic_read(&d->detaching)) { + if (test_bit(BCACHE_DEV_DETACHING, &d->flags)) { struct uuid_entry *u = d->c->uuids + d->id; SET_UUID_FLASH_ONLY(u, 0); memcpy(u->uuid, invalid_uuid, 16); u->invalidated = cpu_to_le32(get_seconds()); bch_uuid_write(d->c); - - atomic_set(&d->detaching, 0); } - if (!d->flush_done) - bcache_device_unlink(d); + bcache_device_unlink(d); d->c->devices[d->id] = NULL; closure_put(&d->c->caching); @@ -739,14 +733,20 @@ static void bcache_device_free(struct bcache_device *d) del_gendisk(d->disk); if (d->disk && d->disk->queue) blk_cleanup_queue(d->disk->queue); - if (d->disk) + if (d->disk) { + ida_simple_remove(&bcache_minor, d->disk->first_minor); put_disk(d->disk); + } bio_split_pool_free(&d->bio_split_hook); if (d->unaligned_bvec) mempool_destroy(d->unaligned_bvec); if (d->bio_split) bioset_free(d->bio_split); + if (is_vmalloc_addr(d->full_dirty_stripes)) + vfree(d->full_dirty_stripes); + else + kfree(d->full_dirty_stripes); if (is_vmalloc_addr(d->stripe_sectors_dirty)) vfree(d->stripe_sectors_dirty); else @@ -760,15 +760,19 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, { struct request_queue *q; size_t n; + int minor; - if (!d->stripe_size_bits) - d->stripe_size_bits = 31; + if (!d->stripe_size) + d->stripe_size = 1 << 31; - d->nr_stripes = round_up(sectors, 1 << d->stripe_size_bits) >> - d->stripe_size_bits; + d->nr_stripes = DIV_ROUND_UP_ULL(sectors, d->stripe_size); - if (!d->nr_stripes || d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) + if (!d->nr_stripes || + d->nr_stripes > INT_MAX || + d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) { + pr_err("nr_stripes too large"); return -ENOMEM; + } n = d->nr_stripes * sizeof(atomic_t); d->stripe_sectors_dirty = n < PAGE_SIZE << 6 @@ -777,22 +781,38 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, if (!d->stripe_sectors_dirty) return -ENOMEM; + n = BITS_TO_LONGS(d->nr_stripes) * sizeof(unsigned long); + d->full_dirty_stripes = n < PAGE_SIZE << 6 + ? kzalloc(n, GFP_KERNEL) + : vzalloc(n); + if (!d->full_dirty_stripes) + return -ENOMEM; + + minor = ida_simple_get(&bcache_minor, 0, MINORMASK + 1, GFP_KERNEL); + if (minor < 0) + return minor; + if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) || !(d->unaligned_bvec = mempool_create_kmalloc_pool(1, sizeof(struct bio_vec) * BIO_MAX_PAGES)) || bio_split_pool_init(&d->bio_split_hook) || - !(d->disk = alloc_disk(1)) || - !(q = blk_alloc_queue(GFP_KERNEL))) + !(d->disk = alloc_disk(1))) { + ida_simple_remove(&bcache_minor, minor); return -ENOMEM; + } set_capacity(d->disk, sectors); - snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", bcache_minor); + snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", minor); d->disk->major = bcache_major; - d->disk->first_minor = bcache_minor++; + d->disk->first_minor = minor; d->disk->fops = &bcache_ops; d->disk->private_data = d; + q = blk_alloc_queue(GFP_KERNEL); + if (!q) + return -ENOMEM; + blk_queue_make_request(q, NULL); d->disk->queue = q; q->queuedata = d; @@ -874,7 +894,7 @@ static void cached_dev_detach_finish(struct work_struct *w) struct closure cl; closure_init_stack(&cl); - BUG_ON(!atomic_read(&dc->disk.detaching)); + BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)); BUG_ON(atomic_read(&dc->count)); mutex_lock(&bch_register_lock); @@ -888,6 +908,8 @@ static void cached_dev_detach_finish(struct work_struct *w) bcache_device_detach(&dc->disk); list_move(&dc->list, &uncached_devices); + clear_bit(BCACHE_DEV_DETACHING, &dc->disk.flags); + mutex_unlock(&bch_register_lock); pr_info("Caching disabled for %s", bdevname(dc->bdev, buf)); @@ -900,10 +922,10 @@ void bch_cached_dev_detach(struct cached_dev *dc) { lockdep_assert_held(&bch_register_lock); - if (atomic_read(&dc->disk.closing)) + if (test_bit(BCACHE_DEV_CLOSING, &dc->disk.flags)) return; - if (atomic_xchg(&dc->disk.detaching, 1)) + if (test_and_set_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)) return; /* @@ -1030,6 +1052,7 @@ static void cached_dev_free(struct closure *cl) struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl); cancel_delayed_work_sync(&dc->writeback_rate_update); + kthread_stop(dc->writeback_thread); mutex_lock(&bch_register_lock); @@ -1058,11 +1081,7 @@ static void cached_dev_flush(struct closure *cl) struct bcache_device *d = &dc->disk; mutex_lock(&bch_register_lock); - d->flush_done = 1; - - if (d->c) - bcache_device_unlink(d); - + bcache_device_unlink(d); mutex_unlock(&bch_register_lock); bch_cache_accounting_destroy(&dc->accounting); @@ -1088,7 +1107,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned block_size) spin_lock_init(&dc->io_lock); bch_cache_accounting_init(&dc->accounting, &dc->disk.cl); - dc->sequential_merge = true; dc->sequential_cutoff = 4 << 20; for (io = dc->io; io < dc->io + RECENT_IO; io++) { @@ -1260,7 +1278,8 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...) { va_list args; - if (test_bit(CACHE_SET_STOPPING, &c->flags)) + if (c->on_error != ON_ERROR_PANIC && + test_bit(CACHE_SET_STOPPING, &c->flags)) return false; /* XXX: we can be called from atomic context @@ -1275,6 +1294,9 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...) printk(", disabling caching\n"); + if (c->on_error == ON_ERROR_PANIC) + panic("panic forced after error\n"); + bch_cache_set_unregister(c); return true; } @@ -1339,6 +1361,9 @@ static void cache_set_flush(struct closure *cl) kobject_put(&c->internal); kobject_del(&c->kobj); + if (c->gc_thread) + kthread_stop(c->gc_thread); + if (!IS_ERR_OR_NULL(c->root)) list_add(&c->root->list, &c->btree_cache); @@ -1433,12 +1458,19 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) c->sort_crit_factor = int_sqrt(c->btree_pages); - mutex_init(&c->bucket_lock); - mutex_init(&c->sort_lock); - spin_lock_init(&c->sort_time_lock); closure_init_unlocked(&c->sb_write); + mutex_init(&c->bucket_lock); + init_waitqueue_head(&c->try_wait); + init_waitqueue_head(&c->bucket_wait); closure_init_unlocked(&c->uuid_write); - spin_lock_init(&c->btree_read_time_lock); + mutex_init(&c->sort_lock); + + spin_lock_init(&c->sort_time.lock); + spin_lock_init(&c->btree_gc_time.lock); + spin_lock_init(&c->btree_split_time.lock); + spin_lock_init(&c->btree_read_time.lock); + spin_lock_init(&c->try_harder_time.lock); + bch_moving_init_cache_set(c); INIT_LIST_HEAD(&c->list); @@ -1483,11 +1515,10 @@ static void run_cache_set(struct cache_set *c) const char *err = "cannot allocate memory"; struct cached_dev *dc, *t; struct cache *ca; + struct closure cl; unsigned i; - struct btree_op op; - bch_btree_op_init_stack(&op); - op.lock = SHRT_MAX; + closure_init_stack(&cl); for_each_cache(ca, c, i) c->nbuckets += ca->sb.nbuckets; @@ -1498,7 +1529,7 @@ static void run_cache_set(struct cache_set *c) struct jset *j; err = "cannot allocate memory for journal"; - if (bch_journal_read(c, &journal, &op)) + if (bch_journal_read(c, &journal)) goto err; pr_debug("btree_journal_read() done"); @@ -1522,23 +1553,23 @@ static void run_cache_set(struct cache_set *c) k = &j->btree_root; err = "bad btree root"; - if (__bch_ptr_invalid(c, j->btree_level + 1, k)) + if (bch_btree_ptr_invalid(c, k)) goto err; err = "error reading btree root"; - c->root = bch_btree_node_get(c, k, j->btree_level, &op); + c->root = bch_btree_node_get(c, k, j->btree_level, true); if (IS_ERR_OR_NULL(c->root)) goto err; list_del_init(&c->root->list); rw_unlock(true, c->root); - err = uuid_read(c, j, &op.cl); + err = uuid_read(c, j, &cl); if (err) goto err; err = "error in recovery"; - if (bch_btree_check(c, &op)) + if (bch_btree_check(c)) goto err; bch_journal_mark(c, &journal); @@ -1570,11 +1601,9 @@ static void run_cache_set(struct cache_set *c) if (j->version < BCACHE_JSET_VERSION_UUID) __uuid_write(c); - bch_journal_replay(c, &journal, &op); + bch_journal_replay(c, &journal); } else { pr_notice("invalidating existing data"); - /* Don't want invalidate_buckets() to queue a gc yet */ - closure_lock(&c->gc, NULL); for_each_cache(ca, c, i) { unsigned j; @@ -1600,15 +1629,15 @@ static void run_cache_set(struct cache_set *c) err = "cannot allocate new UUID bucket"; if (__uuid_write(c)) - goto err_unlock_gc; + goto err; err = "cannot allocate new btree root"; - c->root = bch_btree_node_alloc(c, 0, &op.cl); + c->root = bch_btree_node_alloc(c, 0, true); if (IS_ERR_OR_NULL(c->root)) - goto err_unlock_gc; + goto err; bkey_copy_key(&c->root->key, &MAX_KEY); - bch_btree_node_write(c->root, &op.cl); + bch_btree_node_write(c->root, &cl); bch_btree_set_root(c->root); rw_unlock(true, c->root); @@ -1621,14 +1650,14 @@ static void run_cache_set(struct cache_set *c) SET_CACHE_SYNC(&c->sb, true); bch_journal_next(&c->journal); - bch_journal_meta(c, &op.cl); - - /* Unlock */ - closure_set_stopped(&c->gc.cl); - closure_put(&c->gc.cl); + bch_journal_meta(c, &cl); } - closure_sync(&op.cl); + err = "error starting gc thread"; + if (bch_gc_thread_start(c)) + goto err; + + closure_sync(&cl); c->sb.last_mount = get_seconds(); bcache_write_super(c); @@ -1638,13 +1667,10 @@ static void run_cache_set(struct cache_set *c) flash_devs_run(c); return; -err_unlock_gc: - closure_set_stopped(&c->gc.cl); - closure_put(&c->gc.cl); err: - closure_sync(&op.cl); + closure_sync(&cl); /* XXX: test this, it's broken */ - bch_cache_set_error(c, err); + bch_cache_set_error(c, "%s", err); } static bool can_attach_cache(struct cache *ca, struct cache_set *c) @@ -1725,8 +1751,6 @@ void bch_cache_release(struct kobject *kobj) if (ca->set) ca->set->cache[ca->sb.nr_this_dev] = NULL; - bch_cache_allocator_exit(ca); - bio_split_pool_free(&ca->bio_split_hook); free_pages((unsigned long) ca->disk_buckets, ilog2(bucket_pages(ca))); @@ -1758,8 +1782,6 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca) __module_get(THIS_MODULE); kobject_init(&ca->kobj, &bch_cache_ktype); - INIT_LIST_HEAD(&ca->discards); - bio_init(&ca->journal.bio); ca->journal.bio.bi_max_vecs = 8; ca->journal.bio.bi_io_vec = ca->journal.bio.bi_inline_vecs; @@ -2006,7 +2028,6 @@ static struct notifier_block reboot = { static void bcache_exit(void) { bch_debug_exit(); - bch_writeback_exit(); bch_request_exit(); bch_btree_exit(); if (bcache_kobj) @@ -2039,7 +2060,6 @@ static int __init bcache_init(void) sysfs_create_files(bcache_kobj, files) || bch_btree_init() || bch_request_init() || - bch_writeback_init() || bch_debug_init(bcache_kobj)) goto err; diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 12a2c28..80d4c2b 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -21,6 +21,12 @@ static const char * const cache_replacement_policies[] = { NULL }; +static const char * const error_actions[] = { + "unregister", + "panic", + NULL +}; + write_attribute(attach); write_attribute(detach); write_attribute(unregister); @@ -66,7 +72,6 @@ rw_attribute(congested_read_threshold_us); rw_attribute(congested_write_threshold_us); rw_attribute(sequential_cutoff); -rw_attribute(sequential_merge); rw_attribute(data_csum); rw_attribute(cache_mode); rw_attribute(writeback_metadata); @@ -90,11 +95,14 @@ rw_attribute(discard); rw_attribute(running); rw_attribute(label); rw_attribute(readahead); +rw_attribute(errors); rw_attribute(io_error_limit); rw_attribute(io_error_halflife); rw_attribute(verify); +rw_attribute(bypass_torture_test); rw_attribute(key_merging_disabled); rw_attribute(gc_always_rewrite); +rw_attribute(expensive_debug_checks); rw_attribute(freelist_percent); rw_attribute(cache_replacement_policy); rw_attribute(btree_shrinker_disabled); @@ -116,6 +124,7 @@ SHOW(__bch_cached_dev) sysfs_printf(data_csum, "%i", dc->disk.data_csum); var_printf(verify, "%i"); + var_printf(bypass_torture_test, "%i"); var_printf(writeback_metadata, "%i"); var_printf(writeback_running, "%i"); var_print(writeback_delay); @@ -150,10 +159,9 @@ SHOW(__bch_cached_dev) sysfs_hprint(dirty_data, bcache_dev_sectors_dirty(&dc->disk) << 9); - sysfs_hprint(stripe_size, (1 << dc->disk.stripe_size_bits) << 9); + sysfs_hprint(stripe_size, dc->disk.stripe_size << 9); var_printf(partial_stripes_expensive, "%u"); - var_printf(sequential_merge, "%i"); var_hprint(sequential_cutoff); var_hprint(readahead); @@ -185,6 +193,7 @@ STORE(__cached_dev) sysfs_strtoul(data_csum, dc->disk.data_csum); d_strtoul(verify); + d_strtoul(bypass_torture_test); d_strtoul(writeback_metadata); d_strtoul(writeback_running); d_strtoul(writeback_delay); @@ -199,7 +208,6 @@ STORE(__cached_dev) dc->writeback_rate_p_term_inverse, 1, INT_MAX); d_strtoul(writeback_rate_d_smooth); - d_strtoul(sequential_merge); d_strtoi_h(sequential_cutoff); d_strtoi_h(readahead); @@ -223,8 +231,13 @@ STORE(__cached_dev) } if (attr == &sysfs_label) { - /* note: endlines are preserved */ - memcpy(dc->sb.label, buf, SB_LABEL_SIZE); + if (size > SB_LABEL_SIZE) + return -EINVAL; + memcpy(dc->sb.label, buf, size); + if (size < SB_LABEL_SIZE) + dc->sb.label[size] = '\0'; + if (size && dc->sb.label[size - 1] == '\n') + dc->sb.label[size - 1] = '\0'; bch_write_bdev_super(dc, NULL); if (dc->disk.c) { memcpy(dc->disk.c->uuids[dc->disk.id].label, @@ -306,7 +319,6 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_stripe_size, &sysfs_partial_stripes_expensive, &sysfs_sequential_cutoff, - &sysfs_sequential_merge, &sysfs_clear_stats, &sysfs_running, &sysfs_state, @@ -314,6 +326,7 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_readahead, #ifdef CONFIG_BCACHE_DEBUG &sysfs_verify, + &sysfs_bypass_torture_test, #endif NULL }; @@ -361,7 +374,7 @@ STORE(__bch_flash_dev) } if (attr == &sysfs_unregister) { - atomic_set(&d->detaching, 1); + set_bit(BCACHE_DEV_DETACHING, &d->flags); bcache_device_stop(d); } @@ -476,7 +489,6 @@ lock_root: sysfs_print(btree_used_percent, btree_used(c)); sysfs_print(btree_nodes, c->gc_stats.nodes); - sysfs_hprint(dirty_data, c->gc_stats.dirty); sysfs_hprint(average_key_size, average_key_size(c)); sysfs_print(cache_read_races, @@ -487,6 +499,10 @@ lock_root: sysfs_print(writeback_keys_failed, atomic_long_read(&c->writeback_keys_failed)); + if (attr == &sysfs_errors) + return bch_snprint_string_list(buf, PAGE_SIZE, error_actions, + c->on_error); + /* See count_io_errors for why 88 */ sysfs_print(io_error_halflife, c->error_decay * 88); sysfs_print(io_error_limit, c->error_limit >> IO_ERROR_SHIFT); @@ -501,6 +517,8 @@ lock_root: sysfs_print(active_journal_entries, fifo_used(&c->journal.pin)); sysfs_printf(verify, "%i", c->verify); sysfs_printf(key_merging_disabled, "%i", c->key_merging_disabled); + sysfs_printf(expensive_debug_checks, + "%i", c->expensive_debug_checks); sysfs_printf(gc_always_rewrite, "%i", c->gc_always_rewrite); sysfs_printf(btree_shrinker_disabled, "%i", c->shrinker_disabled); sysfs_printf(copy_gc_enabled, "%i", c->copy_gc_enabled); @@ -550,13 +568,13 @@ STORE(__bch_cache_set) } if (attr == &sysfs_trigger_gc) - bch_queue_gc(c); + wake_up_gc(c); if (attr == &sysfs_prune_cache) { struct shrink_control sc; sc.gfp_mask = GFP_KERNEL; sc.nr_to_scan = strtoul_or_return(buf); - c->shrink.shrink(&c->shrink, &sc); + c->shrink.scan_objects(&c->shrink, &sc); } sysfs_strtoul(congested_read_threshold_us, @@ -564,6 +582,15 @@ STORE(__bch_cache_set) sysfs_strtoul(congested_write_threshold_us, c->congested_write_threshold_us); + if (attr == &sysfs_errors) { + ssize_t v = bch_read_string_list(buf, error_actions); + + if (v < 0) + return v; + + c->on_error = v; + } + if (attr == &sysfs_io_error_limit) c->error_limit = strtoul_or_return(buf) << IO_ERROR_SHIFT; @@ -574,6 +601,7 @@ STORE(__bch_cache_set) sysfs_strtoul(journal_delay_ms, c->journal_delay_ms); sysfs_strtoul(verify, c->verify); sysfs_strtoul(key_merging_disabled, c->key_merging_disabled); + sysfs_strtoul(expensive_debug_checks, c->expensive_debug_checks); sysfs_strtoul(gc_always_rewrite, c->gc_always_rewrite); sysfs_strtoul(btree_shrinker_disabled, c->shrinker_disabled); sysfs_strtoul(copy_gc_enabled, c->copy_gc_enabled); @@ -613,8 +641,8 @@ static struct attribute *bch_cache_set_files[] = { &sysfs_cache_available_percent, &sysfs_average_key_size, - &sysfs_dirty_data, + &sysfs_errors, &sysfs_io_error_limit, &sysfs_io_error_halflife, &sysfs_congested, @@ -648,6 +676,7 @@ static struct attribute *bch_cache_set_internal_files[] = { #ifdef CONFIG_BCACHE_DEBUG &sysfs_verify, &sysfs_key_merging_disabled, + &sysfs_expensive_debug_checks, #endif &sysfs_gc_always_rewrite, &sysfs_btree_shrinker_disabled, diff --git a/drivers/md/bcache/trace.c b/drivers/md/bcache/trace.c index f7b6c19..adbc3df 100644 --- a/drivers/md/bcache/trace.c +++ b/drivers/md/bcache/trace.c @@ -1,6 +1,5 @@ #include "bcache.h" #include "btree.h" -#include "request.h" #include <linux/blktrace_api.h> #include <linux/module.h> diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index 98eb811..462214e 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -168,10 +168,14 @@ int bch_parse_uuid(const char *s, char *uuid) void bch_time_stats_update(struct time_stats *stats, uint64_t start_time) { - uint64_t now = local_clock(); - uint64_t duration = time_after64(now, start_time) + uint64_t now, duration, last; + + spin_lock(&stats->lock); + + now = local_clock(); + duration = time_after64(now, start_time) ? now - start_time : 0; - uint64_t last = time_after64(now, stats->last) + last = time_after64(now, stats->last) ? now - stats->last : 0; stats->max_duration = max(stats->max_duration, duration); @@ -188,9 +192,20 @@ void bch_time_stats_update(struct time_stats *stats, uint64_t start_time) } stats->last = now ?: 1; + + spin_unlock(&stats->lock); } -unsigned bch_next_delay(struct ratelimit *d, uint64_t done) +/** + * bch_next_delay() - increment @d by the amount of work done, and return how + * long to delay until the next time to do some work. + * + * @d - the struct bch_ratelimit to update + * @done - the amount of work done, in arbitrary units + * + * Returns the amount of time to delay by, in jiffies + */ +uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done) { uint64_t now = local_clock(); diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 1ae2a73..362c4b3 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -15,28 +15,18 @@ struct closure; -#ifdef CONFIG_BCACHE_EDEBUG +#ifdef CONFIG_BCACHE_DEBUG #define atomic_dec_bug(v) BUG_ON(atomic_dec_return(v) < 0) #define atomic_inc_bug(v, i) BUG_ON(atomic_inc_return(v) <= i) -#else /* EDEBUG */ +#else /* DEBUG */ #define atomic_dec_bug(v) atomic_dec(v) #define atomic_inc_bug(v, i) atomic_inc(v) #endif -#define BITMASK(name, type, field, offset, size) \ -static inline uint64_t name(const type *k) \ -{ return (k->field >> offset) & ~(((uint64_t) ~0) << size); } \ - \ -static inline void SET_##name(type *k, uint64_t v) \ -{ \ - k->field &= ~(~((uint64_t) ~0 << size) << offset); \ - k->field |= v << offset; \ -} - #define DECLARE_HEAP(type, name) \ struct { \ size_t size, used; \ @@ -388,6 +378,7 @@ ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[ ssize_t bch_read_string_list(const char *buf, const char * const list[]); struct time_stats { + spinlock_t lock; /* * all fields are in nanoseconds, averages are ewmas stored left shifted * by 8 @@ -450,17 +441,23 @@ read_attribute(name ## _last_ ## frequency_units) (ewma) >> factor; \ }) -struct ratelimit { +struct bch_ratelimit { + /* Next time we want to do some work, in nanoseconds */ uint64_t next; + + /* + * Rate at which we want to do work, in units per nanosecond + * The units here correspond to the units passed to bch_next_delay() + */ unsigned rate; }; -static inline void ratelimit_reset(struct ratelimit *d) +static inline void bch_ratelimit_reset(struct bch_ratelimit *d) { d->next = local_clock(); } -unsigned bch_next_delay(struct ratelimit *d, uint64_t done); +uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done); #define __DIV_SAFE(n, d, zero) \ ({ \ diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 22cbff5..99053b1 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -11,18 +11,11 @@ #include "debug.h" #include "writeback.h" +#include <linux/delay.h> +#include <linux/freezer.h> +#include <linux/kthread.h> #include <trace/events/bcache.h> -static struct workqueue_struct *dirty_wq; - -static void read_dirty(struct closure *); - -struct dirty_io { - struct closure cl; - struct cached_dev *dc; - struct bio bio; -}; - /* Rate limiting */ static void __update_writeback_rate(struct cached_dev *dc) @@ -72,9 +65,6 @@ out: dc->writeback_rate_derivative = derivative; dc->writeback_rate_change = change; dc->writeback_rate_target = target; - - schedule_delayed_work(&dc->writeback_rate_update, - dc->writeback_rate_update_seconds * HZ); } static void update_writeback_rate(struct work_struct *work) @@ -90,48 +80,29 @@ static void update_writeback_rate(struct work_struct *work) __update_writeback_rate(dc); up_read(&dc->writeback_lock); + + schedule_delayed_work(&dc->writeback_rate_update, + dc->writeback_rate_update_seconds * HZ); } static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors) { - if (atomic_read(&dc->disk.detaching) || + uint64_t ret; + + if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) || !dc->writeback_percent) return 0; - return bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL); -} - -/* Background writeback */ + ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL); -static bool dirty_pred(struct keybuf *buf, struct bkey *k) -{ - return KEY_DIRTY(k); + return min_t(uint64_t, ret, HZ); } -static bool dirty_full_stripe_pred(struct keybuf *buf, struct bkey *k) -{ - uint64_t stripe; - unsigned nr_sectors = KEY_SIZE(k); - struct cached_dev *dc = container_of(buf, struct cached_dev, - writeback_keys); - unsigned stripe_size = 1 << dc->disk.stripe_size_bits; - - if (!KEY_DIRTY(k)) - return false; - - stripe = KEY_START(k) >> dc->disk.stripe_size_bits; - while (1) { - if (atomic_read(dc->disk.stripe_sectors_dirty + stripe) != - stripe_size) - return false; - - if (nr_sectors <= stripe_size) - return true; - - nr_sectors -= stripe_size; - stripe++; - } -} +struct dirty_io { + struct closure cl; + struct cached_dev *dc; + struct bio bio; +}; static void dirty_init(struct keybuf_key *w) { @@ -149,131 +120,6 @@ static void dirty_init(struct keybuf_key *w) bch_bio_map(bio, NULL); } -static void refill_dirty(struct closure *cl) -{ - struct cached_dev *dc = container_of(cl, struct cached_dev, - writeback.cl); - struct keybuf *buf = &dc->writeback_keys; - bool searched_from_start = false; - struct bkey end = MAX_KEY; - SET_KEY_INODE(&end, dc->disk.id); - - if (!atomic_read(&dc->disk.detaching) && - !dc->writeback_running) - closure_return(cl); - - down_write(&dc->writeback_lock); - - if (!atomic_read(&dc->has_dirty)) { - SET_BDEV_STATE(&dc->sb, BDEV_STATE_CLEAN); - bch_write_bdev_super(dc, NULL); - - up_write(&dc->writeback_lock); - closure_return(cl); - } - - if (bkey_cmp(&buf->last_scanned, &end) >= 0) { - buf->last_scanned = KEY(dc->disk.id, 0, 0); - searched_from_start = true; - } - - if (dc->partial_stripes_expensive) { - uint64_t i; - - for (i = 0; i < dc->disk.nr_stripes; i++) - if (atomic_read(dc->disk.stripe_sectors_dirty + i) == - 1 << dc->disk.stripe_size_bits) - goto full_stripes; - - goto normal_refill; -full_stripes: - bch_refill_keybuf(dc->disk.c, buf, &end, - dirty_full_stripe_pred); - } else { -normal_refill: - bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred); - } - - if (bkey_cmp(&buf->last_scanned, &end) >= 0 && searched_from_start) { - /* Searched the entire btree - delay awhile */ - - if (RB_EMPTY_ROOT(&buf->keys)) { - atomic_set(&dc->has_dirty, 0); - cached_dev_put(dc); - } - - if (!atomic_read(&dc->disk.detaching)) - closure_delay(&dc->writeback, dc->writeback_delay * HZ); - } - - up_write(&dc->writeback_lock); - - ratelimit_reset(&dc->writeback_rate); - - /* Punt to workqueue only so we don't recurse and blow the stack */ - continue_at(cl, read_dirty, dirty_wq); -} - -void bch_writeback_queue(struct cached_dev *dc) -{ - if (closure_trylock(&dc->writeback.cl, &dc->disk.cl)) { - if (!atomic_read(&dc->disk.detaching)) - closure_delay(&dc->writeback, dc->writeback_delay * HZ); - - continue_at(&dc->writeback.cl, refill_dirty, dirty_wq); - } -} - -void bch_writeback_add(struct cached_dev *dc) -{ - if (!atomic_read(&dc->has_dirty) && - !atomic_xchg(&dc->has_dirty, 1)) { - atomic_inc(&dc->count); - - if (BDEV_STATE(&dc->sb) != BDEV_STATE_DIRTY) { - SET_BDEV_STATE(&dc->sb, BDEV_STATE_DIRTY); - /* XXX: should do this synchronously */ - bch_write_bdev_super(dc, NULL); - } - - bch_writeback_queue(dc); - - if (dc->writeback_percent) - schedule_delayed_work(&dc->writeback_rate_update, - dc->writeback_rate_update_seconds * HZ); - } -} - -void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode, - uint64_t offset, int nr_sectors) -{ - struct bcache_device *d = c->devices[inode]; - unsigned stripe_size, stripe_offset; - uint64_t stripe; - - if (!d) - return; - - stripe_size = 1 << d->stripe_size_bits; - stripe = offset >> d->stripe_size_bits; - stripe_offset = offset & (stripe_size - 1); - - while (nr_sectors) { - int s = min_t(unsigned, abs(nr_sectors), - stripe_size - stripe_offset); - - if (nr_sectors < 0) - s = -s; - - atomic_add(s, d->stripe_sectors_dirty + stripe); - nr_sectors -= s; - stripe_offset = 0; - stripe++; - } -} - -/* Background writeback - IO loop */ - static void dirty_io_destructor(struct closure *cl) { struct dirty_io *io = container_of(cl, struct dirty_io, cl); @@ -293,34 +139,31 @@ static void write_dirty_finish(struct closure *cl) /* This is kind of a dumb way of signalling errors. */ if (KEY_DIRTY(&w->key)) { + int ret; unsigned i; - struct btree_op op; - bch_btree_op_init_stack(&op); + struct keylist keys; - op.type = BTREE_REPLACE; - bkey_copy(&op.replace, &w->key); + bch_keylist_init(&keys); - SET_KEY_DIRTY(&w->key, false); - bch_keylist_add(&op.keys, &w->key); + bkey_copy(keys.top, &w->key); + SET_KEY_DIRTY(keys.top, false); + bch_keylist_push(&keys); for (i = 0; i < KEY_PTRS(&w->key); i++) atomic_inc(&PTR_BUCKET(dc->disk.c, &w->key, i)->pin); - bch_btree_insert(&op, dc->disk.c); - closure_sync(&op.cl); + ret = bch_btree_insert(dc->disk.c, &keys, NULL, &w->key); - if (op.insert_collision) + if (ret) trace_bcache_writeback_collision(&w->key); - atomic_long_inc(op.insert_collision + atomic_long_inc(ret ? &dc->disk.c->writeback_keys_failed : &dc->disk.c->writeback_keys_done); } bch_keybuf_del(&dc->writeback_keys, w); - atomic_dec_bug(&dc->in_flight); - - closure_wake_up(&dc->writeback_wait); + up(&dc->in_flight); closure_return_with_destructor(cl, dirty_io_destructor); } @@ -349,7 +192,7 @@ static void write_dirty(struct closure *cl) closure_bio_submit(&io->bio, cl, &io->dc->disk); - continue_at(cl, write_dirty_finish, dirty_wq); + continue_at(cl, write_dirty_finish, system_wq); } static void read_dirty_endio(struct bio *bio, int error) @@ -369,37 +212,36 @@ static void read_dirty_submit(struct closure *cl) closure_bio_submit(&io->bio, cl, &io->dc->disk); - continue_at(cl, write_dirty, dirty_wq); + continue_at(cl, write_dirty, system_wq); } -static void read_dirty(struct closure *cl) +static void read_dirty(struct cached_dev *dc) { - struct cached_dev *dc = container_of(cl, struct cached_dev, - writeback.cl); - unsigned delay = writeback_delay(dc, 0); + unsigned delay = 0; struct keybuf_key *w; struct dirty_io *io; + struct closure cl; + + closure_init_stack(&cl); /* * XXX: if we error, background writeback just spins. Should use some * mempools. */ - while (1) { + while (!kthread_should_stop()) { + try_to_freeze(); + w = bch_keybuf_next(&dc->writeback_keys); if (!w) break; BUG_ON(ptr_stale(dc->disk.c, &w->key, 0)); - if (delay > 0 && - (KEY_START(&w->key) != dc->last_read || - jiffies_to_msecs(delay) > 50)) { - w->private = NULL; - - closure_delay(&dc->writeback, delay); - continue_at(cl, read_dirty, dirty_wq); - } + if (KEY_START(&w->key) != dc->last_read || + jiffies_to_msecs(delay) > 50) + while (!kthread_should_stop() && delay) + delay = schedule_timeout_interruptible(delay); dc->last_read = KEY_OFFSET(&w->key); @@ -424,15 +266,10 @@ static void read_dirty(struct closure *cl) trace_bcache_writeback(&w->key); - closure_call(&io->cl, read_dirty_submit, NULL, &dc->disk.cl); + down(&dc->in_flight); + closure_call(&io->cl, read_dirty_submit, NULL, &cl); delay = writeback_delay(dc, KEY_SIZE(&w->key)); - - atomic_inc(&dc->in_flight); - - if (!closure_wait_event(&dc->writeback_wait, cl, - atomic_read(&dc->in_flight) < 64)) - continue_at(cl, read_dirty, dirty_wq); } if (0) { @@ -442,51 +279,209 @@ err: bch_keybuf_del(&dc->writeback_keys, w); } - refill_dirty(cl); + /* + * Wait for outstanding writeback IOs to finish (and keybuf slots to be + * freed) before refilling again + */ + closure_sync(&cl); } -/* Init */ +/* Scan for dirty data */ + +void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode, + uint64_t offset, int nr_sectors) +{ + struct bcache_device *d = c->devices[inode]; + unsigned stripe_offset, stripe, sectors_dirty; + + if (!d) + return; + + stripe = offset_to_stripe(d, offset); + stripe_offset = offset & (d->stripe_size - 1); + + while (nr_sectors) { + int s = min_t(unsigned, abs(nr_sectors), + d->stripe_size - stripe_offset); + + if (nr_sectors < 0) + s = -s; + + if (stripe >= d->nr_stripes) + return; + + sectors_dirty = atomic_add_return(s, + d->stripe_sectors_dirty + stripe); + if (sectors_dirty == d->stripe_size) + set_bit(stripe, d->full_dirty_stripes); + else + clear_bit(stripe, d->full_dirty_stripes); -static int bch_btree_sectors_dirty_init(struct btree *b, struct btree_op *op, - struct cached_dev *dc) + nr_sectors -= s; + stripe_offset = 0; + stripe++; + } +} + +static bool dirty_pred(struct keybuf *buf, struct bkey *k) { - struct bkey *k; - struct btree_iter iter; - - bch_btree_iter_init(b, &iter, &KEY(dc->disk.id, 0, 0)); - while ((k = bch_btree_iter_next_filter(&iter, b, bch_ptr_bad))) - if (!b->level) { - if (KEY_INODE(k) > dc->disk.id) - break; - - if (KEY_DIRTY(k)) - bcache_dev_sectors_dirty_add(b->c, dc->disk.id, - KEY_START(k), - KEY_SIZE(k)); - } else { - btree(sectors_dirty_init, k, b, op, dc); - if (KEY_INODE(k) > dc->disk.id) - break; - - cond_resched(); + return KEY_DIRTY(k); +} + +static void refill_full_stripes(struct cached_dev *dc) +{ + struct keybuf *buf = &dc->writeback_keys; + unsigned start_stripe, stripe, next_stripe; + bool wrapped = false; + + stripe = offset_to_stripe(&dc->disk, KEY_OFFSET(&buf->last_scanned)); + + if (stripe >= dc->disk.nr_stripes) + stripe = 0; + + start_stripe = stripe; + + while (1) { + stripe = find_next_bit(dc->disk.full_dirty_stripes, + dc->disk.nr_stripes, stripe); + + if (stripe == dc->disk.nr_stripes) + goto next; + + next_stripe = find_next_zero_bit(dc->disk.full_dirty_stripes, + dc->disk.nr_stripes, stripe); + + buf->last_scanned = KEY(dc->disk.id, + stripe * dc->disk.stripe_size, 0); + + bch_refill_keybuf(dc->disk.c, buf, + &KEY(dc->disk.id, + next_stripe * dc->disk.stripe_size, 0), + dirty_pred); + + if (array_freelist_empty(&buf->freelist)) + return; + + stripe = next_stripe; +next: + if (wrapped && stripe > start_stripe) + return; + + if (stripe == dc->disk.nr_stripes) { + stripe = 0; + wrapped = true; } + } +} + +static bool refill_dirty(struct cached_dev *dc) +{ + struct keybuf *buf = &dc->writeback_keys; + struct bkey end = KEY(dc->disk.id, MAX_KEY_OFFSET, 0); + bool searched_from_start = false; + + if (dc->partial_stripes_expensive) { + refill_full_stripes(dc); + if (array_freelist_empty(&buf->freelist)) + return false; + } + + if (bkey_cmp(&buf->last_scanned, &end) >= 0) { + buf->last_scanned = KEY(dc->disk.id, 0, 0); + searched_from_start = true; + } + + bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred); + + return bkey_cmp(&buf->last_scanned, &end) >= 0 && searched_from_start; +} + +static int bch_writeback_thread(void *arg) +{ + struct cached_dev *dc = arg; + bool searched_full_index; + + while (!kthread_should_stop()) { + down_write(&dc->writeback_lock); + if (!atomic_read(&dc->has_dirty) || + (!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) && + !dc->writeback_running)) { + up_write(&dc->writeback_lock); + set_current_state(TASK_INTERRUPTIBLE); + + if (kthread_should_stop()) + return 0; + + try_to_freeze(); + schedule(); + continue; + } + + searched_full_index = refill_dirty(dc); + + if (searched_full_index && + RB_EMPTY_ROOT(&dc->writeback_keys.keys)) { + atomic_set(&dc->has_dirty, 0); + cached_dev_put(dc); + SET_BDEV_STATE(&dc->sb, BDEV_STATE_CLEAN); + bch_write_bdev_super(dc, NULL); + } + + up_write(&dc->writeback_lock); + + bch_ratelimit_reset(&dc->writeback_rate); + read_dirty(dc); + + if (searched_full_index) { + unsigned delay = dc->writeback_delay * HZ; + + while (delay && + !kthread_should_stop() && + !test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)) + delay = schedule_timeout_interruptible(delay); + } + } return 0; } +/* Init */ + +struct sectors_dirty_init { + struct btree_op op; + unsigned inode; +}; + +static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b, + struct bkey *k) +{ + struct sectors_dirty_init *op = container_of(_op, + struct sectors_dirty_init, op); + if (KEY_INODE(k) > op->inode) + return MAP_DONE; + + if (KEY_DIRTY(k)) + bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k), + KEY_START(k), KEY_SIZE(k)); + + return MAP_CONTINUE; +} + void bch_sectors_dirty_init(struct cached_dev *dc) { - struct btree_op op; + struct sectors_dirty_init op; + + bch_btree_op_init(&op.op, -1); + op.inode = dc->disk.id; - bch_btree_op_init_stack(&op); - btree_root(sectors_dirty_init, dc->disk.c, &op, dc); + bch_btree_map_keys(&op.op, dc->disk.c, &KEY(op.inode, 0, 0), + sectors_dirty_init_fn, 0); } -void bch_cached_dev_writeback_init(struct cached_dev *dc) +int bch_cached_dev_writeback_init(struct cached_dev *dc) { - closure_init_unlocked(&dc->writeback); + sema_init(&dc->in_flight, 64); init_rwsem(&dc->writeback_lock); - bch_keybuf_init(&dc->writeback_keys); dc->writeback_metadata = true; @@ -500,22 +495,16 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc) dc->writeback_rate_p_term_inverse = 64; dc->writeback_rate_d_smooth = 8; + dc->writeback_thread = kthread_create(bch_writeback_thread, dc, + "bcache_writeback"); + if (IS_ERR(dc->writeback_thread)) + return PTR_ERR(dc->writeback_thread); + + set_task_state(dc->writeback_thread, TASK_INTERRUPTIBLE); + INIT_DELAYED_WORK(&dc->writeback_rate_update, update_writeback_rate); schedule_delayed_work(&dc->writeback_rate_update, dc->writeback_rate_update_seconds * HZ); -} - -void bch_writeback_exit(void) -{ - if (dirty_wq) - destroy_workqueue(dirty_wq); -} - -int __init bch_writeback_init(void) -{ - dirty_wq = create_singlethread_workqueue("bcache_writeback"); - if (!dirty_wq) - return -ENOMEM; return 0; } diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index c91f61b..c9ddcf4 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -14,20 +14,27 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d) return ret; } -static inline bool bcache_dev_stripe_dirty(struct bcache_device *d, +static inline unsigned offset_to_stripe(struct bcache_device *d, + uint64_t offset) +{ + do_div(offset, d->stripe_size); + return offset; +} + +static inline bool bcache_dev_stripe_dirty(struct cached_dev *dc, uint64_t offset, unsigned nr_sectors) { - uint64_t stripe = offset >> d->stripe_size_bits; + unsigned stripe = offset_to_stripe(&dc->disk, offset); while (1) { - if (atomic_read(d->stripe_sectors_dirty + stripe)) + if (atomic_read(dc->disk.stripe_sectors_dirty + stripe)) return true; - if (nr_sectors <= 1 << d->stripe_size_bits) + if (nr_sectors <= dc->disk.stripe_size) return false; - nr_sectors -= 1 << d->stripe_size_bits; + nr_sectors -= dc->disk.stripe_size; stripe++; } } @@ -38,12 +45,12 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio, unsigned in_use = dc->disk.c->gc_stats.in_use; if (cache_mode != CACHE_MODE_WRITEBACK || - atomic_read(&dc->disk.detaching) || + test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) || in_use > CUTOFF_WRITEBACK_SYNC) return false; if (dc->partial_stripes_expensive && - bcache_dev_stripe_dirty(&dc->disk, bio->bi_sector, + bcache_dev_stripe_dirty(dc, bio->bi_sector, bio_sectors(bio))) return true; @@ -54,11 +61,30 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio, in_use <= CUTOFF_WRITEBACK; } +static inline void bch_writeback_queue(struct cached_dev *dc) +{ + wake_up_process(dc->writeback_thread); +} + +static inline void bch_writeback_add(struct cached_dev *dc) +{ + if (!atomic_read(&dc->has_dirty) && + !atomic_xchg(&dc->has_dirty, 1)) { + atomic_inc(&dc->count); + + if (BDEV_STATE(&dc->sb) != BDEV_STATE_DIRTY) { + SET_BDEV_STATE(&dc->sb, BDEV_STATE_DIRTY); + /* XXX: should do this synchronously */ + bch_write_bdev_super(dc, NULL); + } + + bch_writeback_queue(dc); + } +} + void bcache_dev_sectors_dirty_add(struct cache_set *, unsigned, uint64_t, int); -void bch_writeback_queue(struct cached_dev *); -void bch_writeback_add(struct cached_dev *); void bch_sectors_dirty_init(struct cached_dev *dc); -void bch_cached_dev_writeback_init(struct cached_dev *); +int bch_cached_dev_writeback_init(struct cached_dev *); #endif diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index a7fd821..12dc29b 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1654,9 +1654,9 @@ int bitmap_create(struct mddev *mddev) bitmap->mddev = mddev; if (mddev->kobj.sd) - bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap"); + bm = sysfs_get_dirent(mddev->kobj.sd, "bitmap"); if (bm) { - bitmap->sysfs_can_clear = sysfs_get_dirent(bm, NULL, "can_clear"); + bitmap->sysfs_can_clear = sysfs_get_dirent(bm, "can_clear"); sysfs_put(bm); } else bitmap->sysfs_can_clear = NULL; diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 5227e07..173cbb2 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1425,62 +1425,75 @@ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp, unsigned long max_jiffies) { if (jiffies - b->last_accessed < max_jiffies) - return 1; + return 0; if (!(gfp & __GFP_IO)) { if (test_bit(B_READING, &b->state) || test_bit(B_WRITING, &b->state) || test_bit(B_DIRTY, &b->state)) - return 1; + return 0; } if (b->hold_count) - return 1; + return 0; __make_buffer_clean(b); __unlink_buffer(b); __free_buffer_wake(b); - return 0; + return 1; } -static void __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, - struct shrink_control *sc) +static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, + gfp_t gfp_mask) { int l; struct dm_buffer *b, *tmp; + long freed = 0; for (l = 0; l < LIST_SIZE; l++) { - list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) - if (!__cleanup_old_buffer(b, sc->gfp_mask, 0) && - !--nr_to_scan) - return; + list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) { + freed += __cleanup_old_buffer(b, gfp_mask, 0); + if (!--nr_to_scan) + break; + } dm_bufio_cond_resched(); } + return freed; } -static int shrink(struct shrinker *shrinker, struct shrink_control *sc) +static unsigned long +dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - struct dm_bufio_client *c = - container_of(shrinker, struct dm_bufio_client, shrinker); - unsigned long r; - unsigned long nr_to_scan = sc->nr_to_scan; + struct dm_bufio_client *c; + unsigned long freed; + c = container_of(shrink, struct dm_bufio_client, shrinker); if (sc->gfp_mask & __GFP_IO) dm_bufio_lock(c); else if (!dm_bufio_trylock(c)) - return !nr_to_scan ? 0 : -1; + return SHRINK_STOP; - if (nr_to_scan) - __scan(c, nr_to_scan, sc); + freed = __scan(c, sc->nr_to_scan, sc->gfp_mask); + dm_bufio_unlock(c); + return freed; +} - r = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY]; - if (r > INT_MAX) - r = INT_MAX; +static unsigned long +dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + struct dm_bufio_client *c; + unsigned long count; - dm_bufio_unlock(c); + c = container_of(shrink, struct dm_bufio_client, shrinker); + if (sc->gfp_mask & __GFP_IO) + dm_bufio_lock(c); + else if (!dm_bufio_trylock(c)) + return 0; - return r; + count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY]; + dm_bufio_unlock(c); + return count; } /* @@ -1582,7 +1595,8 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign __cache_size_refresh(); mutex_unlock(&dm_bufio_clients_lock); - c->shrinker.shrink = shrink; + c->shrinker.count_objects = dm_bufio_shrink_count; + c->shrinker.scan_objects = dm_bufio_shrink_scan; c->shrinker.seeks = 1; c->shrinker.batch = 0; register_shrinker(&c->shrinker); @@ -1669,7 +1683,7 @@ static void cleanup_old_buffers(void) struct dm_buffer *b; b = list_entry(c->lru[LIST_CLEAN].prev, struct dm_buffer, lru_list); - if (__cleanup_old_buffer(b, 0, max_age * HZ)) + if (!__cleanup_old_buffer(b, 0, max_age * HZ)) break; dm_bufio_cond_resched(); } diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 1af7255..9ef0752 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -20,7 +20,13 @@ #define CACHE_SUPERBLOCK_MAGIC 06142003 #define CACHE_SUPERBLOCK_LOCATION 0 -#define CACHE_VERSION 1 + +/* + * defines a range of metadata versions that this module can handle. + */ +#define MIN_CACHE_VERSION 1 +#define MAX_CACHE_VERSION 1 + #define CACHE_METADATA_CACHE_SIZE 64 /* @@ -134,6 +140,18 @@ static void sb_prepare_for_write(struct dm_block_validator *v, SUPERBLOCK_CSUM_XOR)); } +static int check_metadata_version(struct cache_disk_superblock *disk_super) +{ + uint32_t metadata_version = le32_to_cpu(disk_super->version); + if (metadata_version < MIN_CACHE_VERSION || metadata_version > MAX_CACHE_VERSION) { + DMERR("Cache metadata version %u found, but only versions between %u and %u supported.", + metadata_version, MIN_CACHE_VERSION, MAX_CACHE_VERSION); + return -EINVAL; + } + + return 0; +} + static int sb_check(struct dm_block_validator *v, struct dm_block *b, size_t sb_block_size) @@ -164,7 +182,7 @@ static int sb_check(struct dm_block_validator *v, return -EILSEQ; } - return 0; + return check_metadata_version(disk_super); } static struct dm_block_validator sb_validator = { @@ -198,7 +216,7 @@ static int superblock_lock(struct dm_cache_metadata *cmd, /*----------------------------------------------------------------*/ -static int __superblock_all_zeroes(struct dm_block_manager *bm, int *result) +static int __superblock_all_zeroes(struct dm_block_manager *bm, bool *result) { int r; unsigned i; @@ -214,10 +232,10 @@ static int __superblock_all_zeroes(struct dm_block_manager *bm, int *result) return r; data_le = dm_block_data(b); - *result = 1; + *result = true; for (i = 0; i < sb_block_size; i++) { if (data_le[i] != zero) { - *result = 0; + *result = false; break; } } @@ -270,7 +288,7 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd) disk_super->flags = 0; memset(disk_super->uuid, 0, sizeof(disk_super->uuid)); disk_super->magic = cpu_to_le64(CACHE_SUPERBLOCK_MAGIC); - disk_super->version = cpu_to_le32(CACHE_VERSION); + disk_super->version = cpu_to_le32(MAX_CACHE_VERSION); memset(disk_super->policy_name, 0, sizeof(disk_super->policy_name)); memset(disk_super->policy_version, 0, sizeof(disk_super->policy_version)); disk_super->policy_hint_size = 0; @@ -411,7 +429,8 @@ bad: static int __open_or_format_metadata(struct dm_cache_metadata *cmd, bool format_device) { - int r, unformatted; + int r; + bool unformatted = false; r = __superblock_all_zeroes(cmd->bm, &unformatted); if (r) @@ -666,19 +685,85 @@ void dm_cache_metadata_close(struct dm_cache_metadata *cmd) kfree(cmd); } +/* + * Checks that the given cache block is either unmapped or clean. + */ +static int block_unmapped_or_clean(struct dm_cache_metadata *cmd, dm_cblock_t b, + bool *result) +{ + int r; + __le64 value; + dm_oblock_t ob; + unsigned flags; + + r = dm_array_get_value(&cmd->info, cmd->root, from_cblock(b), &value); + if (r) { + DMERR("block_unmapped_or_clean failed"); + return r; + } + + unpack_value(value, &ob, &flags); + *result = !((flags & M_VALID) && (flags & M_DIRTY)); + + return 0; +} + +static int blocks_are_unmapped_or_clean(struct dm_cache_metadata *cmd, + dm_cblock_t begin, dm_cblock_t end, + bool *result) +{ + int r; + *result = true; + + while (begin != end) { + r = block_unmapped_or_clean(cmd, begin, result); + if (r) + return r; + + if (!*result) { + DMERR("cache block %llu is dirty", + (unsigned long long) from_cblock(begin)); + return 0; + } + + begin = to_cblock(from_cblock(begin) + 1); + } + + return 0; +} + int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size) { int r; + bool clean; __le64 null_mapping = pack_value(0, 0); down_write(&cmd->root_lock); __dm_bless_for_disk(&null_mapping); + + if (from_cblock(new_cache_size) < from_cblock(cmd->cache_blocks)) { + r = blocks_are_unmapped_or_clean(cmd, new_cache_size, cmd->cache_blocks, &clean); + if (r) { + __dm_unbless_for_disk(&null_mapping); + goto out; + } + + if (!clean) { + DMERR("unable to shrink cache due to dirty blocks"); + r = -EINVAL; + __dm_unbless_for_disk(&null_mapping); + goto out; + } + } + r = dm_array_resize(&cmd->info, cmd->root, from_cblock(cmd->cache_blocks), from_cblock(new_cache_size), &null_mapping, &cmd->root); if (!r) cmd->cache_blocks = new_cache_size; cmd->changed = true; + +out: up_write(&cmd->root_lock); return r; @@ -1182,3 +1267,8 @@ int dm_cache_save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock, return r; } + +int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result) +{ + return blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result); +} diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h index f45cef2..cd906f1 100644 --- a/drivers/md/dm-cache-metadata.h +++ b/drivers/md/dm-cache-metadata.h @@ -137,6 +137,11 @@ int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy * int dm_cache_save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock, uint32_t hint); +/* + * Query method. Are all the blocks in the cache clean? + */ +int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result); + /*----------------------------------------------------------------*/ #endif /* DM_CACHE_METADATA_H */ diff --git a/drivers/md/dm-cache-policy-internal.h b/drivers/md/dm-cache-policy-internal.h index 0928abd..2256a1f 100644 --- a/drivers/md/dm-cache-policy-internal.h +++ b/drivers/md/dm-cache-policy-internal.h @@ -61,7 +61,12 @@ static inline int policy_writeback_work(struct dm_cache_policy *p, static inline void policy_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock) { - return p->remove_mapping(p, oblock); + p->remove_mapping(p, oblock); +} + +static inline int policy_remove_cblock(struct dm_cache_policy *p, dm_cblock_t cblock) +{ + return p->remove_cblock(p, cblock); } static inline void policy_force_mapping(struct dm_cache_policy *p, diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c index 4296155..416b7b7 100644 --- a/drivers/md/dm-cache-policy-mq.c +++ b/drivers/md/dm-cache-policy-mq.c @@ -26,19 +26,6 @@ static unsigned next_power(unsigned n, unsigned min) /*----------------------------------------------------------------*/ -static unsigned long *alloc_bitset(unsigned nr_entries) -{ - size_t s = sizeof(unsigned long) * dm_div_up(nr_entries, BITS_PER_LONG); - return vzalloc(s); -} - -static void free_bitset(unsigned long *bits) -{ - vfree(bits); -} - -/*----------------------------------------------------------------*/ - /* * Large, sequential ios are probably better left on the origin device since * spindles tend to have good bandwidth. @@ -151,6 +138,21 @@ static void queue_init(struct queue *q) } /* + * Checks to see if the queue is empty. + * FIXME: reduce cpu usage. + */ +static bool queue_empty(struct queue *q) +{ + unsigned i; + + for (i = 0; i < NR_QUEUE_LEVELS; i++) + if (!list_empty(q->qs + i)) + return false; + + return true; +} + +/* * Insert an entry to the back of the given level. */ static void queue_push(struct queue *q, unsigned level, struct list_head *elt) @@ -218,17 +220,116 @@ struct entry { struct hlist_node hlist; struct list_head list; dm_oblock_t oblock; - dm_cblock_t cblock; /* valid iff in_cache */ /* * FIXME: pack these better */ - bool in_cache:1; + bool dirty:1; unsigned hit_count; unsigned generation; unsigned tick; }; +/* + * Rather than storing the cblock in an entry, we allocate all entries in + * an array, and infer the cblock from the entry position. + * + * Free entries are linked together into a list. + */ +struct entry_pool { + struct entry *entries, *entries_end; + struct list_head free; + unsigned nr_allocated; +}; + +static int epool_init(struct entry_pool *ep, unsigned nr_entries) +{ + unsigned i; + + ep->entries = vzalloc(sizeof(struct entry) * nr_entries); + if (!ep->entries) + return -ENOMEM; + + ep->entries_end = ep->entries + nr_entries; + + INIT_LIST_HEAD(&ep->free); + for (i = 0; i < nr_entries; i++) + list_add(&ep->entries[i].list, &ep->free); + + ep->nr_allocated = 0; + + return 0; +} + +static void epool_exit(struct entry_pool *ep) +{ + vfree(ep->entries); +} + +static struct entry *alloc_entry(struct entry_pool *ep) +{ + struct entry *e; + + if (list_empty(&ep->free)) + return NULL; + + e = list_entry(list_pop(&ep->free), struct entry, list); + INIT_LIST_HEAD(&e->list); + INIT_HLIST_NODE(&e->hlist); + ep->nr_allocated++; + + return e; +} + +/* + * This assumes the cblock hasn't already been allocated. + */ +static struct entry *alloc_particular_entry(struct entry_pool *ep, dm_cblock_t cblock) +{ + struct entry *e = ep->entries + from_cblock(cblock); + list_del(&e->list); + + INIT_LIST_HEAD(&e->list); + INIT_HLIST_NODE(&e->hlist); + ep->nr_allocated++; + + return e; +} + +static void free_entry(struct entry_pool *ep, struct entry *e) +{ + BUG_ON(!ep->nr_allocated); + ep->nr_allocated--; + INIT_HLIST_NODE(&e->hlist); + list_add(&e->list, &ep->free); +} + +/* + * Returns NULL if the entry is free. + */ +static struct entry *epool_find(struct entry_pool *ep, dm_cblock_t cblock) +{ + struct entry *e = ep->entries + from_cblock(cblock); + return !hlist_unhashed(&e->hlist) ? e : NULL; +} + +static bool epool_empty(struct entry_pool *ep) +{ + return list_empty(&ep->free); +} + +static bool in_pool(struct entry_pool *ep, struct entry *e) +{ + return e >= ep->entries && e < ep->entries_end; +} + +static dm_cblock_t infer_cblock(struct entry_pool *ep, struct entry *e) +{ + return to_cblock(e - ep->entries); +} + +/*----------------------------------------------------------------*/ + struct mq_policy { struct dm_cache_policy policy; @@ -238,13 +339,22 @@ struct mq_policy { struct io_tracker tracker; /* - * We maintain two queues of entries. The cache proper contains - * the currently active mappings. Whereas the pre_cache tracks - * blocks that are being hit frequently and potential candidates - * for promotion to the cache. + * Entries come from two pools, one of pre-cache entries, and one + * for the cache proper. + */ + struct entry_pool pre_cache_pool; + struct entry_pool cache_pool; + + /* + * We maintain three queues of entries. The cache proper, + * consisting of a clean and dirty queue, contains the currently + * active mappings. Whereas the pre_cache tracks blocks that + * are being hit frequently and potential candidates for promotion + * to the cache. */ struct queue pre_cache; - struct queue cache; + struct queue cache_clean; + struct queue cache_dirty; /* * Keeps track of time, incremented by the core. We use this to @@ -282,25 +392,6 @@ struct mq_policy { unsigned promote_threshold; /* - * We need cache_size entries for the cache, and choose to have - * cache_size entries for the pre_cache too. One motivation for - * using the same size is to make the hit counts directly - * comparable between pre_cache and cache. - */ - unsigned nr_entries; - unsigned nr_entries_allocated; - struct list_head free; - - /* - * Cache blocks may be unallocated. We store this info in a - * bitset. - */ - unsigned long *allocation_bitset; - unsigned nr_cblocks_allocated; - unsigned find_free_nr_words; - unsigned find_free_last_word; - - /* * The hash table allows us to quickly find an entry by origin * block. Both pre_cache and cache entries are in here. */ @@ -310,49 +401,6 @@ struct mq_policy { }; /*----------------------------------------------------------------*/ -/* Free/alloc mq cache entry structures. */ -static void takeout_queue(struct list_head *lh, struct queue *q) -{ - unsigned level; - - for (level = 0; level < NR_QUEUE_LEVELS; level++) - list_splice(q->qs + level, lh); -} - -static void free_entries(struct mq_policy *mq) -{ - struct entry *e, *tmp; - - takeout_queue(&mq->free, &mq->pre_cache); - takeout_queue(&mq->free, &mq->cache); - - list_for_each_entry_safe(e, tmp, &mq->free, list) - kmem_cache_free(mq_entry_cache, e); -} - -static int alloc_entries(struct mq_policy *mq, unsigned elts) -{ - unsigned u = mq->nr_entries; - - INIT_LIST_HEAD(&mq->free); - mq->nr_entries_allocated = 0; - - while (u--) { - struct entry *e = kmem_cache_zalloc(mq_entry_cache, GFP_KERNEL); - - if (!e) { - free_entries(mq); - return -ENOMEM; - } - - - list_add(&e->list, &mq->free); - } - - return 0; -} - -/*----------------------------------------------------------------*/ /* * Simple hash table implementation. Should replace with the standard hash @@ -388,96 +436,14 @@ static void hash_remove(struct entry *e) /*----------------------------------------------------------------*/ -/* - * Allocates a new entry structure. The memory is allocated in one lump, - * so we just handing it out here. Returns NULL if all entries have - * already been allocated. Cannot fail otherwise. - */ -static struct entry *alloc_entry(struct mq_policy *mq) -{ - struct entry *e; - - if (mq->nr_entries_allocated >= mq->nr_entries) { - BUG_ON(!list_empty(&mq->free)); - return NULL; - } - - e = list_entry(list_pop(&mq->free), struct entry, list); - INIT_LIST_HEAD(&e->list); - INIT_HLIST_NODE(&e->hlist); - - mq->nr_entries_allocated++; - return e; -} - -/*----------------------------------------------------------------*/ - -/* - * Mark cache blocks allocated or not in the bitset. - */ -static void alloc_cblock(struct mq_policy *mq, dm_cblock_t cblock) -{ - BUG_ON(from_cblock(cblock) > from_cblock(mq->cache_size)); - BUG_ON(test_bit(from_cblock(cblock), mq->allocation_bitset)); - - set_bit(from_cblock(cblock), mq->allocation_bitset); - mq->nr_cblocks_allocated++; -} - -static void free_cblock(struct mq_policy *mq, dm_cblock_t cblock) -{ - BUG_ON(from_cblock(cblock) > from_cblock(mq->cache_size)); - BUG_ON(!test_bit(from_cblock(cblock), mq->allocation_bitset)); - - clear_bit(from_cblock(cblock), mq->allocation_bitset); - mq->nr_cblocks_allocated--; -} - static bool any_free_cblocks(struct mq_policy *mq) { - return mq->nr_cblocks_allocated < from_cblock(mq->cache_size); + return !epool_empty(&mq->cache_pool); } -/* - * Fills result out with a cache block that isn't in use, or return - * -ENOSPC. This does _not_ mark the cblock as allocated, the caller is - * reponsible for that. - */ -static int __find_free_cblock(struct mq_policy *mq, unsigned begin, unsigned end, - dm_cblock_t *result, unsigned *last_word) +static bool any_clean_cblocks(struct mq_policy *mq) { - int r = -ENOSPC; - unsigned w; - - for (w = begin; w < end; w++) { - /* - * ffz is undefined if no zero exists - */ - if (mq->allocation_bitset[w] != ~0UL) { - *last_word = w; - *result = to_cblock((w * BITS_PER_LONG) + ffz(mq->allocation_bitset[w])); - if (from_cblock(*result) < from_cblock(mq->cache_size)) - r = 0; - - break; - } - } - - return r; -} - -static int find_free_cblock(struct mq_policy *mq, dm_cblock_t *result) -{ - int r; - - if (!any_free_cblocks(mq)) - return -ENOSPC; - - r = __find_free_cblock(mq, mq->find_free_last_word, mq->find_free_nr_words, result, &mq->find_free_last_word); - if (r == -ENOSPC && mq->find_free_last_word) - r = __find_free_cblock(mq, 0, mq->find_free_last_word, result, &mq->find_free_last_word); - - return r; + return !queue_empty(&mq->cache_clean); } /*----------------------------------------------------------------*/ @@ -496,33 +462,35 @@ static unsigned queue_level(struct entry *e) return min((unsigned) ilog2(e->hit_count), NR_QUEUE_LEVELS - 1u); } +static bool in_cache(struct mq_policy *mq, struct entry *e) +{ + return in_pool(&mq->cache_pool, e); +} + /* * Inserts the entry into the pre_cache or the cache. Ensures the cache - * block is marked as allocated if necc. Inserts into the hash table. Sets the - * tick which records when the entry was last moved about. + * block is marked as allocated if necc. Inserts into the hash table. + * Sets the tick which records when the entry was last moved about. */ static void push(struct mq_policy *mq, struct entry *e) { e->tick = mq->tick; hash_insert(mq, e); - if (e->in_cache) { - alloc_cblock(mq, e->cblock); - queue_push(&mq->cache, queue_level(e), &e->list); - } else + if (in_cache(mq, e)) + queue_push(e->dirty ? &mq->cache_dirty : &mq->cache_clean, + queue_level(e), &e->list); + else queue_push(&mq->pre_cache, queue_level(e), &e->list); } /* * Removes an entry from pre_cache or cache. Removes from the hash table. - * Frees off the cache block if necc. */ static void del(struct mq_policy *mq, struct entry *e) { queue_remove(&e->list); hash_remove(e); - if (e->in_cache) - free_cblock(mq, e->cblock); } /* @@ -531,14 +499,14 @@ static void del(struct mq_policy *mq, struct entry *e) */ static struct entry *pop(struct mq_policy *mq, struct queue *q) { - struct entry *e = container_of(queue_pop(q), struct entry, list); + struct entry *e; + struct list_head *h = queue_pop(q); - if (e) { - hash_remove(e); + if (!h) + return NULL; - if (e->in_cache) - free_cblock(mq, e->cblock); - } + e = container_of(h, struct entry, list); + hash_remove(e); return e; } @@ -556,7 +524,8 @@ static bool updated_this_tick(struct mq_policy *mq, struct entry *e) * of the entries. * * At the moment the threshold is taken by averaging the hit counts of some - * of the entries in the cache (the first 20 entries of the first level). + * of the entries in the cache (the first 20 entries across all levels in + * ascending order, giving preference to the clean entries at each level). * * We can be much cleverer than this though. For example, each promotion * could bump up the threshold helping to prevent churn. Much more to do @@ -571,14 +540,21 @@ static void check_generation(struct mq_policy *mq) struct list_head *head; struct entry *e; - if ((mq->hit_count >= mq->generation_period) && - (mq->nr_cblocks_allocated == from_cblock(mq->cache_size))) { - + if ((mq->hit_count >= mq->generation_period) && (epool_empty(&mq->cache_pool))) { mq->hit_count = 0; mq->generation++; for (level = 0; level < NR_QUEUE_LEVELS && count < MAX_TO_AVERAGE; level++) { - head = mq->cache.qs + level; + head = mq->cache_clean.qs + level; + list_for_each_entry(e, head, list) { + nr++; + total += e->hit_count; + + if (++count >= MAX_TO_AVERAGE) + break; + } + + head = mq->cache_dirty.qs + level; list_for_each_entry(e, head, list) { nr++; total += e->hit_count; @@ -631,19 +607,30 @@ static void requeue_and_update_tick(struct mq_policy *mq, struct entry *e) * - set the hit count to a hard coded value other than 1, eg, is it better * if it goes in at level 2? */ -static dm_cblock_t demote_cblock(struct mq_policy *mq, dm_oblock_t *oblock) +static int demote_cblock(struct mq_policy *mq, dm_oblock_t *oblock) { - dm_cblock_t result; - struct entry *demoted = pop(mq, &mq->cache); + struct entry *demoted = pop(mq, &mq->cache_clean); + + if (!demoted) + /* + * We could get a block from mq->cache_dirty, but that + * would add extra latency to the triggering bio as it + * waits for the writeback. Better to not promote this + * time and hope there's a clean block next time this block + * is hit. + */ + return -ENOSPC; - BUG_ON(!demoted); - result = demoted->cblock; *oblock = demoted->oblock; - demoted->in_cache = false; - demoted->hit_count = 1; - push(mq, demoted); + free_entry(&mq->cache_pool, demoted); + + /* + * We used to put the demoted block into the pre-cache, but I think + * it's simpler to just let it work it's way up from zero again. + * Stops blocks flickering in and out of the cache. + */ - return result; + return 0; } /* @@ -662,17 +649,18 @@ static dm_cblock_t demote_cblock(struct mq_policy *mq, dm_oblock_t *oblock) static unsigned adjusted_promote_threshold(struct mq_policy *mq, bool discarded_oblock, int data_dir) { - if (discarded_oblock && any_free_cblocks(mq) && data_dir == WRITE) + if (data_dir == READ) + return mq->promote_threshold + READ_PROMOTE_THRESHOLD; + + if (discarded_oblock && (any_free_cblocks(mq) || any_clean_cblocks(mq))) { /* * We don't need to do any copying at all, so give this a - * very low threshold. In practice this only triggers - * during initial population after a format. + * very low threshold. */ return DISCARDED_PROMOTE_THRESHOLD; + } - return data_dir == READ ? - (mq->promote_threshold + READ_PROMOTE_THRESHOLD) : - (mq->promote_threshold + WRITE_PROMOTE_THRESHOLD); + return mq->promote_threshold + WRITE_PROMOTE_THRESHOLD; } static bool should_promote(struct mq_policy *mq, struct entry *e, @@ -688,34 +676,49 @@ static int cache_entry_found(struct mq_policy *mq, { requeue_and_update_tick(mq, e); - if (e->in_cache) { + if (in_cache(mq, e)) { result->op = POLICY_HIT; - result->cblock = e->cblock; + result->cblock = infer_cblock(&mq->cache_pool, e); } return 0; } /* - * Moves and entry from the pre_cache to the cache. The main work is + * Moves an entry from the pre_cache to the cache. The main work is * finding which cache block to use. */ static int pre_cache_to_cache(struct mq_policy *mq, struct entry *e, struct policy_result *result) { - dm_cblock_t cblock; + int r; + struct entry *new_e; - if (find_free_cblock(mq, &cblock) == -ENOSPC) { + /* Ensure there's a free cblock in the cache */ + if (epool_empty(&mq->cache_pool)) { result->op = POLICY_REPLACE; - cblock = demote_cblock(mq, &result->old_oblock); + r = demote_cblock(mq, &result->old_oblock); + if (r) { + result->op = POLICY_MISS; + return 0; + } } else result->op = POLICY_NEW; - result->cblock = e->cblock = cblock; + new_e = alloc_entry(&mq->cache_pool); + BUG_ON(!new_e); + + new_e->oblock = e->oblock; + new_e->dirty = false; + new_e->hit_count = e->hit_count; + new_e->generation = e->generation; + new_e->tick = e->tick; del(mq, e); - e->in_cache = true; - push(mq, e); + free_entry(&mq->pre_cache_pool, e); + push(mq, new_e); + + result->cblock = infer_cblock(&mq->cache_pool, new_e); return 0; } @@ -743,7 +746,7 @@ static int pre_cache_entry_found(struct mq_policy *mq, struct entry *e, static void insert_in_pre_cache(struct mq_policy *mq, dm_oblock_t oblock) { - struct entry *e = alloc_entry(mq); + struct entry *e = alloc_entry(&mq->pre_cache_pool); if (!e) /* @@ -757,7 +760,7 @@ static void insert_in_pre_cache(struct mq_policy *mq, return; } - e->in_cache = false; + e->dirty = false; e->oblock = oblock; e->hit_count = 1; e->generation = mq->generation; @@ -767,30 +770,36 @@ static void insert_in_pre_cache(struct mq_policy *mq, static void insert_in_cache(struct mq_policy *mq, dm_oblock_t oblock, struct policy_result *result) { + int r; struct entry *e; - dm_cblock_t cblock; - if (find_free_cblock(mq, &cblock) == -ENOSPC) { - result->op = POLICY_MISS; - insert_in_pre_cache(mq, oblock); - return; - } + if (epool_empty(&mq->cache_pool)) { + result->op = POLICY_REPLACE; + r = demote_cblock(mq, &result->old_oblock); + if (unlikely(r)) { + result->op = POLICY_MISS; + insert_in_pre_cache(mq, oblock); + return; + } - e = alloc_entry(mq); - if (unlikely(!e)) { - result->op = POLICY_MISS; - return; + /* + * This will always succeed, since we've just demoted. + */ + e = alloc_entry(&mq->cache_pool); + BUG_ON(!e); + + } else { + e = alloc_entry(&mq->cache_pool); + result->op = POLICY_NEW; } e->oblock = oblock; - e->cblock = cblock; - e->in_cache = true; + e->dirty = false; e->hit_count = 1; e->generation = mq->generation; push(mq, e); - result->op = POLICY_NEW; - result->cblock = e->cblock; + result->cblock = infer_cblock(&mq->cache_pool, e); } static int no_entry_found(struct mq_policy *mq, dm_oblock_t oblock, @@ -821,13 +830,16 @@ static int map(struct mq_policy *mq, dm_oblock_t oblock, int r = 0; struct entry *e = hash_lookup(mq, oblock); - if (e && e->in_cache) + if (e && in_cache(mq, e)) r = cache_entry_found(mq, e, result); + else if (iot_pattern(&mq->tracker) == PATTERN_SEQUENTIAL) result->op = POLICY_MISS; + else if (e) r = pre_cache_entry_found(mq, e, can_migrate, discarded_oblock, data_dir, result); + else r = no_entry_found(mq, oblock, can_migrate, discarded_oblock, data_dir, result); @@ -854,9 +866,9 @@ static void mq_destroy(struct dm_cache_policy *p) { struct mq_policy *mq = to_mq_policy(p); - free_bitset(mq->allocation_bitset); kfree(mq->table); - free_entries(mq); + epool_exit(&mq->cache_pool); + epool_exit(&mq->pre_cache_pool); kfree(mq); } @@ -904,8 +916,8 @@ static int mq_lookup(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t return -EWOULDBLOCK; e = hash_lookup(mq, oblock); - if (e && e->in_cache) { - *cblock = e->cblock; + if (e && in_cache(mq, e)) { + *cblock = infer_cblock(&mq->cache_pool, e); r = 0; } else r = -ENOENT; @@ -915,6 +927,36 @@ static int mq_lookup(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t return r; } +static void __mq_set_clear_dirty(struct mq_policy *mq, dm_oblock_t oblock, bool set) +{ + struct entry *e; + + e = hash_lookup(mq, oblock); + BUG_ON(!e || !in_cache(mq, e)); + + del(mq, e); + e->dirty = set; + push(mq, e); +} + +static void mq_set_dirty(struct dm_cache_policy *p, dm_oblock_t oblock) +{ + struct mq_policy *mq = to_mq_policy(p); + + mutex_lock(&mq->lock); + __mq_set_clear_dirty(mq, oblock, true); + mutex_unlock(&mq->lock); +} + +static void mq_clear_dirty(struct dm_cache_policy *p, dm_oblock_t oblock) +{ + struct mq_policy *mq = to_mq_policy(p); + + mutex_lock(&mq->lock); + __mq_set_clear_dirty(mq, oblock, false); + mutex_unlock(&mq->lock); +} + static int mq_load_mapping(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t cblock, uint32_t hint, bool hint_valid) @@ -922,13 +964,9 @@ static int mq_load_mapping(struct dm_cache_policy *p, struct mq_policy *mq = to_mq_policy(p); struct entry *e; - e = alloc_entry(mq); - if (!e) - return -ENOMEM; - - e->cblock = cblock; + e = alloc_particular_entry(&mq->cache_pool, cblock); e->oblock = oblock; - e->in_cache = true; + e->dirty = false; /* this gets corrected in a minute */ e->hit_count = hint_valid ? hint : 1; e->generation = mq->generation; push(mq, e); @@ -936,57 +974,126 @@ static int mq_load_mapping(struct dm_cache_policy *p, return 0; } +static int mq_save_hints(struct mq_policy *mq, struct queue *q, + policy_walk_fn fn, void *context) +{ + int r; + unsigned level; + struct entry *e; + + for (level = 0; level < NR_QUEUE_LEVELS; level++) + list_for_each_entry(e, q->qs + level, list) { + r = fn(context, infer_cblock(&mq->cache_pool, e), + e->oblock, e->hit_count); + if (r) + return r; + } + + return 0; +} + static int mq_walk_mappings(struct dm_cache_policy *p, policy_walk_fn fn, void *context) { struct mq_policy *mq = to_mq_policy(p); int r = 0; - struct entry *e; - unsigned level; mutex_lock(&mq->lock); - for (level = 0; level < NR_QUEUE_LEVELS; level++) - list_for_each_entry(e, &mq->cache.qs[level], list) { - r = fn(context, e->cblock, e->oblock, e->hit_count); - if (r) - goto out; - } + r = mq_save_hints(mq, &mq->cache_clean, fn, context); + if (!r) + r = mq_save_hints(mq, &mq->cache_dirty, fn, context); -out: mutex_unlock(&mq->lock); return r; } +static void __remove_mapping(struct mq_policy *mq, dm_oblock_t oblock) +{ + struct entry *e; + + e = hash_lookup(mq, oblock); + BUG_ON(!e || !in_cache(mq, e)); + + del(mq, e); + free_entry(&mq->cache_pool, e); +} + static void mq_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock) { struct mq_policy *mq = to_mq_policy(p); - struct entry *e; mutex_lock(&mq->lock); + __remove_mapping(mq, oblock); + mutex_unlock(&mq->lock); +} - e = hash_lookup(mq, oblock); +static int __remove_cblock(struct mq_policy *mq, dm_cblock_t cblock) +{ + struct entry *e = epool_find(&mq->cache_pool, cblock); - BUG_ON(!e || !e->in_cache); + if (!e) + return -ENODATA; del(mq, e); - e->in_cache = false; - push(mq, e); + free_entry(&mq->cache_pool, e); + return 0; +} + +static int mq_remove_cblock(struct dm_cache_policy *p, dm_cblock_t cblock) +{ + int r; + struct mq_policy *mq = to_mq_policy(p); + + mutex_lock(&mq->lock); + r = __remove_cblock(mq, cblock); mutex_unlock(&mq->lock); + + return r; } -static void force_mapping(struct mq_policy *mq, - dm_oblock_t current_oblock, dm_oblock_t new_oblock) +static int __mq_writeback_work(struct mq_policy *mq, dm_oblock_t *oblock, + dm_cblock_t *cblock) { - struct entry *e = hash_lookup(mq, current_oblock); + struct entry *e = pop(mq, &mq->cache_dirty); - BUG_ON(!e || !e->in_cache); + if (!e) + return -ENODATA; - del(mq, e); - e->oblock = new_oblock; + *oblock = e->oblock; + *cblock = infer_cblock(&mq->cache_pool, e); + e->dirty = false; push(mq, e); + + return 0; +} + +static int mq_writeback_work(struct dm_cache_policy *p, dm_oblock_t *oblock, + dm_cblock_t *cblock) +{ + int r; + struct mq_policy *mq = to_mq_policy(p); + + mutex_lock(&mq->lock); + r = __mq_writeback_work(mq, oblock, cblock); + mutex_unlock(&mq->lock); + + return r; +} + +static void __force_mapping(struct mq_policy *mq, + dm_oblock_t current_oblock, dm_oblock_t new_oblock) +{ + struct entry *e = hash_lookup(mq, current_oblock); + + if (e && in_cache(mq, e)) { + del(mq, e); + e->oblock = new_oblock; + e->dirty = true; + push(mq, e); + } } static void mq_force_mapping(struct dm_cache_policy *p, @@ -995,16 +1102,20 @@ static void mq_force_mapping(struct dm_cache_policy *p, struct mq_policy *mq = to_mq_policy(p); mutex_lock(&mq->lock); - force_mapping(mq, current_oblock, new_oblock); + __force_mapping(mq, current_oblock, new_oblock); mutex_unlock(&mq->lock); } static dm_cblock_t mq_residency(struct dm_cache_policy *p) { + dm_cblock_t r; struct mq_policy *mq = to_mq_policy(p); - /* FIXME: lock mutex, not sure we can block here */ - return to_cblock(mq->nr_cblocks_allocated); + mutex_lock(&mq->lock); + r = to_cblock(mq->cache_pool.nr_allocated); + mutex_unlock(&mq->lock); + + return r; } static void mq_tick(struct dm_cache_policy *p) @@ -1057,10 +1168,13 @@ static void init_policy_functions(struct mq_policy *mq) mq->policy.destroy = mq_destroy; mq->policy.map = mq_map; mq->policy.lookup = mq_lookup; + mq->policy.set_dirty = mq_set_dirty; + mq->policy.clear_dirty = mq_clear_dirty; mq->policy.load_mapping = mq_load_mapping; mq->policy.walk_mappings = mq_walk_mappings; mq->policy.remove_mapping = mq_remove_mapping; - mq->policy.writeback_work = NULL; + mq->policy.remove_cblock = mq_remove_cblock; + mq->policy.writeback_work = mq_writeback_work; mq->policy.force_mapping = mq_force_mapping; mq->policy.residency = mq_residency; mq->policy.tick = mq_tick; @@ -1072,7 +1186,6 @@ static struct dm_cache_policy *mq_create(dm_cblock_t cache_size, sector_t origin_size, sector_t cache_block_size) { - int r; struct mq_policy *mq = kzalloc(sizeof(*mq), GFP_KERNEL); if (!mq) @@ -1080,8 +1193,18 @@ static struct dm_cache_policy *mq_create(dm_cblock_t cache_size, init_policy_functions(mq); iot_init(&mq->tracker, SEQUENTIAL_THRESHOLD_DEFAULT, RANDOM_THRESHOLD_DEFAULT); - mq->cache_size = cache_size; + + if (epool_init(&mq->pre_cache_pool, from_cblock(cache_size))) { + DMERR("couldn't initialize pool of pre-cache entries"); + goto bad_pre_cache_init; + } + + if (epool_init(&mq->cache_pool, from_cblock(cache_size))) { + DMERR("couldn't initialize pool of cache entries"); + goto bad_cache_init; + } + mq->tick_protected = 0; mq->tick = 0; mq->hit_count = 0; @@ -1089,20 +1212,12 @@ static struct dm_cache_policy *mq_create(dm_cblock_t cache_size, mq->promote_threshold = 0; mutex_init(&mq->lock); spin_lock_init(&mq->tick_lock); - mq->find_free_nr_words = dm_div_up(from_cblock(mq->cache_size), BITS_PER_LONG); - mq->find_free_last_word = 0; queue_init(&mq->pre_cache); - queue_init(&mq->cache); - mq->generation_period = max((unsigned) from_cblock(cache_size), 1024U); + queue_init(&mq->cache_clean); + queue_init(&mq->cache_dirty); - mq->nr_entries = 2 * from_cblock(cache_size); - r = alloc_entries(mq, mq->nr_entries); - if (r) - goto bad_cache_alloc; - - mq->nr_entries_allocated = 0; - mq->nr_cblocks_allocated = 0; + mq->generation_period = max((unsigned) from_cblock(cache_size), 1024U); mq->nr_buckets = next_power(from_cblock(cache_size) / 2, 16); mq->hash_bits = ffs(mq->nr_buckets) - 1; @@ -1110,17 +1225,13 @@ static struct dm_cache_policy *mq_create(dm_cblock_t cache_size, if (!mq->table) goto bad_alloc_table; - mq->allocation_bitset = alloc_bitset(from_cblock(cache_size)); - if (!mq->allocation_bitset) - goto bad_alloc_bitset; - return &mq->policy; -bad_alloc_bitset: - kfree(mq->table); bad_alloc_table: - free_entries(mq); -bad_cache_alloc: + epool_exit(&mq->cache_pool); +bad_cache_init: + epool_exit(&mq->pre_cache_pool); +bad_pre_cache_init: kfree(mq); return NULL; @@ -1130,7 +1241,7 @@ bad_cache_alloc: static struct dm_cache_policy_type mq_policy_type = { .name = "mq", - .version = {1, 0, 0}, + .version = {1, 1, 0}, .hint_size = 4, .owner = THIS_MODULE, .create = mq_create @@ -1138,7 +1249,7 @@ static struct dm_cache_policy_type mq_policy_type = { static struct dm_cache_policy_type default_policy_type = { .name = "default", - .version = {1, 0, 0}, + .version = {1, 1, 0}, .hint_size = 4, .owner = THIS_MODULE, .create = mq_create diff --git a/drivers/md/dm-cache-policy.c b/drivers/md/dm-cache-policy.c index 21c03c5..d800579 100644 --- a/drivers/md/dm-cache-policy.c +++ b/drivers/md/dm-cache-policy.c @@ -119,13 +119,13 @@ struct dm_cache_policy *dm_cache_policy_create(const char *name, type = get_policy(name); if (!type) { DMWARN("unknown policy type"); - return NULL; + return ERR_PTR(-EINVAL); } p = type->create(cache_size, origin_size, cache_block_size); if (!p) { put_policy(type); - return NULL; + return ERR_PTR(-ENOMEM); } p->private = type; diff --git a/drivers/md/dm-cache-policy.h b/drivers/md/dm-cache-policy.h index 33369ca..052c00a 100644 --- a/drivers/md/dm-cache-policy.h +++ b/drivers/md/dm-cache-policy.h @@ -135,9 +135,6 @@ struct dm_cache_policy { */ int (*lookup)(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock); - /* - * oblock must be a mapped block. Must not block. - */ void (*set_dirty)(struct dm_cache_policy *p, dm_oblock_t oblock); void (*clear_dirty)(struct dm_cache_policy *p, dm_oblock_t oblock); @@ -159,8 +156,24 @@ struct dm_cache_policy { void (*force_mapping)(struct dm_cache_policy *p, dm_oblock_t current_oblock, dm_oblock_t new_oblock); - int (*writeback_work)(struct dm_cache_policy *p, dm_oblock_t *oblock, dm_cblock_t *cblock); + /* + * This is called via the invalidate_cblocks message. It is + * possible the particular cblock has already been removed due to a + * write io in passthrough mode. In which case this should return + * -ENODATA. + */ + int (*remove_cblock)(struct dm_cache_policy *p, dm_cblock_t cblock); + /* + * Provide a dirty block to be written back by the core target. + * + * Returns: + * + * 0 and @cblock,@oblock: block to write back provided + * + * -ENODATA: no dirty blocks available + */ + int (*writeback_work)(struct dm_cache_policy *p, dm_oblock_t *oblock, dm_cblock_t *cblock); /* * How full is the cache? diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 0df3ec0..9efcf10 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -61,27 +61,80 @@ static void free_bitset(unsigned long *bits) /*----------------------------------------------------------------*/ +/* + * There are a couple of places where we let a bio run, but want to do some + * work before calling its endio function. We do this by temporarily + * changing the endio fn. + */ +struct dm_hook_info { + bio_end_io_t *bi_end_io; + void *bi_private; +}; + +static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio, + bio_end_io_t *bi_end_io, void *bi_private) +{ + h->bi_end_io = bio->bi_end_io; + h->bi_private = bio->bi_private; + + bio->bi_end_io = bi_end_io; + bio->bi_private = bi_private; +} + +static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio) +{ + bio->bi_end_io = h->bi_end_io; + bio->bi_private = h->bi_private; +} + +/*----------------------------------------------------------------*/ + #define PRISON_CELLS 1024 #define MIGRATION_POOL_SIZE 128 #define COMMIT_PERIOD HZ #define MIGRATION_COUNT_WINDOW 10 /* - * The block size of the device holding cache data must be >= 32KB + * The block size of the device holding cache data must be + * between 32KB and 1GB. */ #define DATA_DEV_BLOCK_SIZE_MIN_SECTORS (32 * 1024 >> SECTOR_SHIFT) +#define DATA_DEV_BLOCK_SIZE_MAX_SECTORS (1024 * 1024 * 1024 >> SECTOR_SHIFT) /* * FIXME: the cache is read/write for the time being. */ -enum cache_mode { +enum cache_metadata_mode { CM_WRITE, /* metadata may be changed */ CM_READ_ONLY, /* metadata may not be changed */ }; +enum cache_io_mode { + /* + * Data is written to cached blocks only. These blocks are marked + * dirty. If you lose the cache device you will lose data. + * Potential performance increase for both reads and writes. + */ + CM_IO_WRITEBACK, + + /* + * Data is written to both cache and origin. Blocks are never + * dirty. Potential performance benfit for reads only. + */ + CM_IO_WRITETHROUGH, + + /* + * A degraded mode useful for various cache coherency situations + * (eg, rolling back snapshots). Reads and writes always go to the + * origin. If a write goes to a cached oblock, then the cache + * block is invalidated. + */ + CM_IO_PASSTHROUGH +}; + struct cache_features { - enum cache_mode mode; - bool write_through:1; + enum cache_metadata_mode mode; + enum cache_io_mode io_mode; }; struct cache_stats { @@ -97,10 +150,31 @@ struct cache_stats { atomic_t discard_count; }; +/* + * Defines a range of cblocks, begin to (end - 1) are in the range. end is + * the one-past-the-end value. + */ +struct cblock_range { + dm_cblock_t begin; + dm_cblock_t end; +}; + +struct invalidation_request { + struct list_head list; + struct cblock_range *cblocks; + + atomic_t complete; + int err; + + wait_queue_head_t result_wait; +}; + struct cache { struct dm_target *ti; struct dm_target_callbacks callbacks; + struct dm_cache_metadata *cmd; + /* * Metadata is written to this device. */ @@ -117,11 +191,6 @@ struct cache { struct dm_dev *cache_dev; /* - * Cache features such as write-through. - */ - struct cache_features features; - - /* * Size of the origin device in _complete_ blocks and native sectors. */ dm_oblock_t origin_blocks; @@ -138,8 +207,6 @@ struct cache { uint32_t sectors_per_block; int sectors_per_block_shift; - struct dm_cache_metadata *cmd; - spinlock_t lock; struct bio_list deferred_bios; struct bio_list deferred_flush_bios; @@ -148,8 +215,12 @@ struct cache { struct list_head completed_migrations; struct list_head need_commit_migrations; sector_t migration_threshold; - atomic_t nr_migrations; wait_queue_head_t migration_wait; + atomic_t nr_migrations; + + wait_queue_head_t quiescing_wait; + atomic_t quiescing; + atomic_t quiescing_ack; /* * cache_size entries, dirty if set @@ -160,9 +231,16 @@ struct cache { /* * origin_blocks entries, discarded if set. */ - uint32_t discard_block_size; /* a power of 2 times sectors per block */ dm_dblock_t discard_nr_blocks; unsigned long *discard_bitset; + uint32_t discard_block_size; /* a power of 2 times sectors per block */ + + /* + * Rather than reconstructing the table line for the status we just + * save it and regurgitate. + */ + unsigned nr_ctr_args; + const char **ctr_args; struct dm_kcopyd_client *copier; struct workqueue_struct *wq; @@ -182,19 +260,23 @@ struct cache { bool need_tick_bio:1; bool sized:1; - bool quiescing:1; + bool invalidate:1; bool commit_requested:1; bool loaded_mappings:1; bool loaded_discards:1; + /* + * Cache features such as write-through. + */ + struct cache_features features; + struct cache_stats stats; /* - * Rather than reconstructing the table line for the status we just - * save it and regurgitate. + * Invalidation fields. */ - unsigned nr_ctr_args; - const char **ctr_args; + spinlock_t invalidation_lock; + struct list_head invalidation_requests; }; struct per_bio_data { @@ -209,7 +291,7 @@ struct per_bio_data { */ struct cache *cache; dm_cblock_t cblock; - bio_end_io_t *saved_bi_end_io; + struct dm_hook_info hook_info; struct dm_bio_details bio_details; }; @@ -226,6 +308,8 @@ struct dm_cache_migration { bool writeback:1; bool demote:1; bool promote:1; + bool requeue_holder:1; + bool invalidate:1; struct dm_bio_prison_cell *old_ocell; struct dm_bio_prison_cell *new_ocell; @@ -531,9 +615,24 @@ static void save_stats(struct cache *cache) #define PB_DATA_SIZE_WB (offsetof(struct per_bio_data, cache)) #define PB_DATA_SIZE_WT (sizeof(struct per_bio_data)) +static bool writethrough_mode(struct cache_features *f) +{ + return f->io_mode == CM_IO_WRITETHROUGH; +} + +static bool writeback_mode(struct cache_features *f) +{ + return f->io_mode == CM_IO_WRITEBACK; +} + +static bool passthrough_mode(struct cache_features *f) +{ + return f->io_mode == CM_IO_PASSTHROUGH; +} + static size_t get_per_bio_data_size(struct cache *cache) { - return cache->features.write_through ? PB_DATA_SIZE_WT : PB_DATA_SIZE_WB; + return writethrough_mode(&cache->features) ? PB_DATA_SIZE_WT : PB_DATA_SIZE_WB; } static struct per_bio_data *get_per_bio_data(struct bio *bio, size_t data_size) @@ -603,6 +702,7 @@ static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, static void remap_to_cache_dirty(struct cache *cache, struct bio *bio, dm_oblock_t oblock, dm_cblock_t cblock) { + check_if_tick_bio_needed(cache, bio); remap_to_cache(cache, bio, cblock); if (bio_data_dir(bio) == WRITE) { set_dirty(cache, oblock, cblock); @@ -660,7 +760,8 @@ static void defer_writethrough_bio(struct cache *cache, struct bio *bio) static void writethrough_endio(struct bio *bio, int err) { struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT); - bio->bi_end_io = pb->saved_bi_end_io; + + dm_unhook_bio(&pb->hook_info, bio); if (err) { bio_endio(bio, err); @@ -691,9 +792,8 @@ static void remap_to_origin_then_cache(struct cache *cache, struct bio *bio, pb->cache = cache; pb->cblock = cblock; - pb->saved_bi_end_io = bio->bi_end_io; + dm_hook_bio(&pb->hook_info, bio, writethrough_endio, NULL); dm_bio_record(&pb->bio_details, bio); - bio->bi_end_io = writethrough_endio; remap_to_origin_clear_discard(pb->cache, bio, oblock); } @@ -746,8 +846,9 @@ static void cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell, static void cleanup_migration(struct dm_cache_migration *mg) { - dec_nr_migrations(mg->cache); + struct cache *cache = mg->cache; free_migration(mg); + dec_nr_migrations(cache); } static void migration_failure(struct dm_cache_migration *mg) @@ -763,13 +864,13 @@ static void migration_failure(struct dm_cache_migration *mg) DMWARN_LIMIT("demotion failed; couldn't copy block"); policy_force_mapping(cache->policy, mg->new_oblock, mg->old_oblock); - cell_defer(cache, mg->old_ocell, mg->promote ? 0 : 1); + cell_defer(cache, mg->old_ocell, mg->promote ? false : true); if (mg->promote) - cell_defer(cache, mg->new_ocell, 1); + cell_defer(cache, mg->new_ocell, true); } else { DMWARN_LIMIT("promotion failed; couldn't copy block"); policy_remove_mapping(cache->policy, mg->new_oblock); - cell_defer(cache, mg->new_ocell, 1); + cell_defer(cache, mg->new_ocell, true); } cleanup_migration(mg); @@ -821,7 +922,7 @@ static void migration_success_post_commit(struct dm_cache_migration *mg) return; } else if (mg->demote) { - cell_defer(cache, mg->old_ocell, mg->promote ? 0 : 1); + cell_defer(cache, mg->old_ocell, mg->promote ? false : true); if (mg->promote) { mg->demote = false; @@ -830,11 +931,19 @@ static void migration_success_post_commit(struct dm_cache_migration *mg) list_add_tail(&mg->list, &cache->quiesced_migrations); spin_unlock_irqrestore(&cache->lock, flags); - } else + } else { + if (mg->invalidate) + policy_remove_mapping(cache->policy, mg->old_oblock); cleanup_migration(mg); + } } else { - cell_defer(cache, mg->new_ocell, true); + if (mg->requeue_holder) + cell_defer(cache, mg->new_ocell, true); + else { + bio_endio(mg->new_ocell->holder, 0); + cell_defer(cache, mg->new_ocell, false); + } clear_dirty(cache, mg->new_oblock, mg->cblock); cleanup_migration(mg); } @@ -879,8 +988,46 @@ static void issue_copy_real(struct dm_cache_migration *mg) r = dm_kcopyd_copy(cache->copier, &o_region, 1, &c_region, 0, copy_complete, mg); } - if (r < 0) + if (r < 0) { + DMERR_LIMIT("issuing migration failed"); migration_failure(mg); + } +} + +static void overwrite_endio(struct bio *bio, int err) +{ + struct dm_cache_migration *mg = bio->bi_private; + struct cache *cache = mg->cache; + size_t pb_data_size = get_per_bio_data_size(cache); + struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); + unsigned long flags; + + if (err) + mg->err = true; + + spin_lock_irqsave(&cache->lock, flags); + list_add_tail(&mg->list, &cache->completed_migrations); + dm_unhook_bio(&pb->hook_info, bio); + mg->requeue_holder = false; + spin_unlock_irqrestore(&cache->lock, flags); + + wake_worker(cache); +} + +static void issue_overwrite(struct dm_cache_migration *mg, struct bio *bio) +{ + size_t pb_data_size = get_per_bio_data_size(mg->cache); + struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); + + dm_hook_bio(&pb->hook_info, bio, overwrite_endio, mg); + remap_to_cache_dirty(mg->cache, bio, mg->new_oblock, mg->cblock); + generic_make_request(bio); +} + +static bool bio_writes_complete_block(struct cache *cache, struct bio *bio) +{ + return (bio_data_dir(bio) == WRITE) && + (bio->bi_size == (cache->sectors_per_block << SECTOR_SHIFT)); } static void avoid_copy(struct dm_cache_migration *mg) @@ -897,9 +1044,17 @@ static void issue_copy(struct dm_cache_migration *mg) if (mg->writeback || mg->demote) avoid = !is_dirty(cache, mg->cblock) || is_discarded_oblock(cache, mg->old_oblock); - else + else { + struct bio *bio = mg->new_ocell->holder; + avoid = is_discarded_oblock(cache, mg->new_oblock); + if (!avoid && bio_writes_complete_block(cache, bio)) { + issue_overwrite(mg, bio); + return; + } + } + avoid ? avoid_copy(mg) : issue_copy_real(mg); } @@ -989,6 +1144,8 @@ static void promote(struct cache *cache, struct prealloc *structs, mg->writeback = false; mg->demote = false; mg->promote = true; + mg->requeue_holder = true; + mg->invalidate = false; mg->cache = cache; mg->new_oblock = oblock; mg->cblock = cblock; @@ -1010,6 +1167,8 @@ static void writeback(struct cache *cache, struct prealloc *structs, mg->writeback = true; mg->demote = false; mg->promote = false; + mg->requeue_holder = true; + mg->invalidate = false; mg->cache = cache; mg->old_oblock = oblock; mg->cblock = cblock; @@ -1033,6 +1192,8 @@ static void demote_then_promote(struct cache *cache, struct prealloc *structs, mg->writeback = false; mg->demote = true; mg->promote = true; + mg->requeue_holder = true; + mg->invalidate = false; mg->cache = cache; mg->old_oblock = old_oblock; mg->new_oblock = new_oblock; @@ -1045,6 +1206,33 @@ static void demote_then_promote(struct cache *cache, struct prealloc *structs, quiesce_migration(mg); } +/* + * Invalidate a cache entry. No writeback occurs; any changes in the cache + * block are thrown away. + */ +static void invalidate(struct cache *cache, struct prealloc *structs, + dm_oblock_t oblock, dm_cblock_t cblock, + struct dm_bio_prison_cell *cell) +{ + struct dm_cache_migration *mg = prealloc_get_migration(structs); + + mg->err = false; + mg->writeback = false; + mg->demote = true; + mg->promote = false; + mg->requeue_holder = true; + mg->invalidate = true; + mg->cache = cache; + mg->old_oblock = oblock; + mg->cblock = cblock; + mg->old_ocell = cell; + mg->new_ocell = NULL; + mg->start_jiffies = jiffies; + + inc_nr_migrations(cache); + quiesce_migration(mg); +} + /*---------------------------------------------------------------- * bio processing *--------------------------------------------------------------*/ @@ -1107,13 +1295,6 @@ static bool spare_migration_bandwidth(struct cache *cache) return current_volume < cache->migration_threshold; } -static bool is_writethrough_io(struct cache *cache, struct bio *bio, - dm_cblock_t cblock) -{ - return bio_data_dir(bio) == WRITE && - cache->features.write_through && !is_dirty(cache, cblock); -} - static void inc_hit_counter(struct cache *cache, struct bio *bio) { atomic_inc(bio_data_dir(bio) == READ ? @@ -1126,6 +1307,15 @@ static void inc_miss_counter(struct cache *cache, struct bio *bio) &cache->stats.read_miss : &cache->stats.write_miss); } +static void issue_cache_bio(struct cache *cache, struct bio *bio, + struct per_bio_data *pb, + dm_oblock_t oblock, dm_cblock_t cblock) +{ + pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); + remap_to_cache_dirty(cache, bio, oblock, cblock); + issue(cache, bio); +} + static void process_bio(struct cache *cache, struct prealloc *structs, struct bio *bio) { @@ -1137,7 +1327,8 @@ static void process_bio(struct cache *cache, struct prealloc *structs, size_t pb_data_size = get_per_bio_data_size(cache); struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); bool discarded_block = is_discarded_oblock(cache, block); - bool can_migrate = discarded_block || spare_migration_bandwidth(cache); + bool passthrough = passthrough_mode(&cache->features); + bool can_migrate = !passthrough && (discarded_block || spare_migration_bandwidth(cache)); /* * Check to see if that block is currently migrating. @@ -1158,15 +1349,39 @@ static void process_bio(struct cache *cache, struct prealloc *structs, switch (lookup_result.op) { case POLICY_HIT: - inc_hit_counter(cache, bio); - pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); + if (passthrough) { + inc_miss_counter(cache, bio); - if (is_writethrough_io(cache, bio, lookup_result.cblock)) - remap_to_origin_then_cache(cache, bio, block, lookup_result.cblock); - else - remap_to_cache_dirty(cache, bio, block, lookup_result.cblock); + /* + * Passthrough always maps to the origin, + * invalidating any cache blocks that are written + * to. + */ + + if (bio_data_dir(bio) == WRITE) { + atomic_inc(&cache->stats.demotion); + invalidate(cache, structs, block, lookup_result.cblock, new_ocell); + release_cell = false; + + } else { + /* FIXME: factor out issue_origin() */ + pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); + remap_to_origin_clear_discard(cache, bio, block); + issue(cache, bio); + } + } else { + inc_hit_counter(cache, bio); + + if (bio_data_dir(bio) == WRITE && + writethrough_mode(&cache->features) && + !is_dirty(cache, lookup_result.cblock)) { + pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); + remap_to_origin_then_cache(cache, bio, block, lookup_result.cblock); + issue(cache, bio); + } else + issue_cache_bio(cache, bio, pb, block, lookup_result.cblock); + } - issue(cache, bio); break; case POLICY_MISS: @@ -1225,15 +1440,17 @@ static int need_commit_due_to_time(struct cache *cache) static int commit_if_needed(struct cache *cache) { - if (dm_cache_changed_this_transaction(cache->cmd) && - (cache->commit_requested || need_commit_due_to_time(cache))) { + int r = 0; + + if ((cache->commit_requested || need_commit_due_to_time(cache)) && + dm_cache_changed_this_transaction(cache->cmd)) { atomic_inc(&cache->stats.commit_count); - cache->last_commit_jiffies = jiffies; cache->commit_requested = false; - return dm_cache_commit(cache->cmd, false); + r = dm_cache_commit(cache->cmd, false); + cache->last_commit_jiffies = jiffies; } - return 0; + return r; } static void process_deferred_bios(struct cache *cache) @@ -1342,36 +1559,88 @@ static void writeback_some_dirty_blocks(struct cache *cache) } /*---------------------------------------------------------------- - * Main worker loop + * Invalidations. + * Dropping something from the cache *without* writing back. *--------------------------------------------------------------*/ -static void start_quiescing(struct cache *cache) + +static void process_invalidation_request(struct cache *cache, struct invalidation_request *req) { - unsigned long flags; + int r = 0; + uint64_t begin = from_cblock(req->cblocks->begin); + uint64_t end = from_cblock(req->cblocks->end); - spin_lock_irqsave(&cache->lock, flags); - cache->quiescing = 1; - spin_unlock_irqrestore(&cache->lock, flags); + while (begin != end) { + r = policy_remove_cblock(cache->policy, to_cblock(begin)); + if (!r) { + r = dm_cache_remove_mapping(cache->cmd, to_cblock(begin)); + if (r) + break; + + } else if (r == -ENODATA) { + /* harmless, already unmapped */ + r = 0; + + } else { + DMERR("policy_remove_cblock failed"); + break; + } + + begin++; + } + + cache->commit_requested = true; + + req->err = r; + atomic_set(&req->complete, 1); + + wake_up(&req->result_wait); } -static void stop_quiescing(struct cache *cache) +static void process_invalidation_requests(struct cache *cache) { - unsigned long flags; + struct list_head list; + struct invalidation_request *req, *tmp; - spin_lock_irqsave(&cache->lock, flags); - cache->quiescing = 0; - spin_unlock_irqrestore(&cache->lock, flags); + INIT_LIST_HEAD(&list); + spin_lock(&cache->invalidation_lock); + list_splice_init(&cache->invalidation_requests, &list); + spin_unlock(&cache->invalidation_lock); + + list_for_each_entry_safe (req, tmp, &list, list) + process_invalidation_request(cache, req); } +/*---------------------------------------------------------------- + * Main worker loop + *--------------------------------------------------------------*/ static bool is_quiescing(struct cache *cache) { - int r; - unsigned long flags; + return atomic_read(&cache->quiescing); +} - spin_lock_irqsave(&cache->lock, flags); - r = cache->quiescing; - spin_unlock_irqrestore(&cache->lock, flags); +static void ack_quiescing(struct cache *cache) +{ + if (is_quiescing(cache)) { + atomic_inc(&cache->quiescing_ack); + wake_up(&cache->quiescing_wait); + } +} - return r; +static void wait_for_quiescing_ack(struct cache *cache) +{ + wait_event(cache->quiescing_wait, atomic_read(&cache->quiescing_ack)); +} + +static void start_quiescing(struct cache *cache) +{ + atomic_inc(&cache->quiescing); + wait_for_quiescing_ack(cache); +} + +static void stop_quiescing(struct cache *cache) +{ + atomic_set(&cache->quiescing, 0); + atomic_set(&cache->quiescing_ack, 0); } static void wait_for_migrations(struct cache *cache) @@ -1410,7 +1679,8 @@ static int more_work(struct cache *cache) !bio_list_empty(&cache->deferred_writethrough_bios) || !list_empty(&cache->quiesced_migrations) || !list_empty(&cache->completed_migrations) || - !list_empty(&cache->need_commit_migrations); + !list_empty(&cache->need_commit_migrations) || + cache->invalidate; } static void do_worker(struct work_struct *ws) @@ -1418,16 +1688,16 @@ static void do_worker(struct work_struct *ws) struct cache *cache = container_of(ws, struct cache, worker); do { - if (!is_quiescing(cache)) + if (!is_quiescing(cache)) { + writeback_some_dirty_blocks(cache); + process_deferred_writethrough_bios(cache); process_deferred_bios(cache); + process_invalidation_requests(cache); + } process_migrations(cache, &cache->quiesced_migrations, issue_copy); process_migrations(cache, &cache->completed_migrations, complete_migration); - writeback_some_dirty_blocks(cache); - - process_deferred_writethrough_bios(cache); - if (commit_if_needed(cache)) { process_deferred_flush_bios(cache, false); @@ -1440,6 +1710,9 @@ static void do_worker(struct work_struct *ws) process_migrations(cache, &cache->need_commit_migrations, migration_success_post_commit); } + + ack_quiescing(cache); + } while (more_work(cache)); } @@ -1687,24 +1960,25 @@ static int parse_origin_dev(struct cache_args *ca, struct dm_arg_set *as, static int parse_block_size(struct cache_args *ca, struct dm_arg_set *as, char **error) { - unsigned long tmp; + unsigned long block_size; if (!at_least_one_arg(as, error)) return -EINVAL; - if (kstrtoul(dm_shift_arg(as), 10, &tmp) || !tmp || - tmp < DATA_DEV_BLOCK_SIZE_MIN_SECTORS || - tmp & (DATA_DEV_BLOCK_SIZE_MIN_SECTORS - 1)) { + if (kstrtoul(dm_shift_arg(as), 10, &block_size) || !block_size || + block_size < DATA_DEV_BLOCK_SIZE_MIN_SECTORS || + block_size > DATA_DEV_BLOCK_SIZE_MAX_SECTORS || + block_size & (DATA_DEV_BLOCK_SIZE_MIN_SECTORS - 1)) { *error = "Invalid data block size"; return -EINVAL; } - if (tmp > ca->cache_sectors) { + if (block_size > ca->cache_sectors) { *error = "Data block size is larger than the cache device"; return -EINVAL; } - ca->block_size = tmp; + ca->block_size = block_size; return 0; } @@ -1712,7 +1986,7 @@ static int parse_block_size(struct cache_args *ca, struct dm_arg_set *as, static void init_features(struct cache_features *cf) { cf->mode = CM_WRITE; - cf->write_through = false; + cf->io_mode = CM_IO_WRITEBACK; } static int parse_features(struct cache_args *ca, struct dm_arg_set *as, @@ -1737,10 +2011,13 @@ static int parse_features(struct cache_args *ca, struct dm_arg_set *as, arg = dm_shift_arg(as); if (!strcasecmp(arg, "writeback")) - cf->write_through = false; + cf->io_mode = CM_IO_WRITEBACK; else if (!strcasecmp(arg, "writethrough")) - cf->write_through = true; + cf->io_mode = CM_IO_WRITETHROUGH; + + else if (!strcasecmp(arg, "passthrough")) + cf->io_mode = CM_IO_PASSTHROUGH; else { *error = "Unrecognised cache feature requested"; @@ -1869,14 +2146,15 @@ static int set_config_values(struct cache *cache, int argc, const char **argv) static int create_cache_policy(struct cache *cache, struct cache_args *ca, char **error) { - cache->policy = dm_cache_policy_create(ca->policy_name, - cache->cache_size, - cache->origin_sectors, - cache->sectors_per_block); - if (!cache->policy) { + struct dm_cache_policy *p = dm_cache_policy_create(ca->policy_name, + cache->cache_size, + cache->origin_sectors, + cache->sectors_per_block); + if (IS_ERR(p)) { *error = "Error creating cache's policy"; - return -ENOMEM; + return PTR_ERR(p); } + cache->policy = p; return 0; } @@ -1992,6 +2270,22 @@ static int cache_create(struct cache_args *ca, struct cache **result) } cache->cmd = cmd; + if (passthrough_mode(&cache->features)) { + bool all_clean; + + r = dm_cache_metadata_all_clean(cache->cmd, &all_clean); + if (r) { + *error = "dm_cache_metadata_all_clean() failed"; + goto bad; + } + + if (!all_clean) { + *error = "Cannot enter passthrough mode unless all blocks are clean"; + r = -EINVAL; + goto bad; + } + } + spin_lock_init(&cache->lock); bio_list_init(&cache->deferred_bios); bio_list_init(&cache->deferred_flush_bios); @@ -2002,6 +2296,10 @@ static int cache_create(struct cache_args *ca, struct cache **result) atomic_set(&cache->nr_migrations, 0); init_waitqueue_head(&cache->migration_wait); + init_waitqueue_head(&cache->quiescing_wait); + atomic_set(&cache->quiescing, 0); + atomic_set(&cache->quiescing_ack, 0); + r = -ENOMEM; cache->nr_dirty = 0; cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size)); @@ -2061,7 +2359,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) cache->need_tick_bio = true; cache->sized = false; - cache->quiescing = false; + cache->invalidate = false; cache->commit_requested = false; cache->loaded_mappings = false; cache->loaded_discards = false; @@ -2075,6 +2373,9 @@ static int cache_create(struct cache_args *ca, struct cache **result) atomic_set(&cache->stats.commit_count, 0); atomic_set(&cache->stats.discard_count, 0); + spin_lock_init(&cache->invalidation_lock); + INIT_LIST_HEAD(&cache->invalidation_requests); + *result = cache; return 0; @@ -2204,17 +2505,37 @@ static int cache_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } + r = DM_MAPIO_REMAPPED; switch (lookup_result.op) { case POLICY_HIT: - inc_hit_counter(cache, bio); - pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); + if (passthrough_mode(&cache->features)) { + if (bio_data_dir(bio) == WRITE) { + /* + * We need to invalidate this block, so + * defer for the worker thread. + */ + cell_defer(cache, cell, true); + r = DM_MAPIO_SUBMITTED; + + } else { + pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); + inc_miss_counter(cache, bio); + remap_to_origin_clear_discard(cache, bio, block); + + cell_defer(cache, cell, false); + } - if (is_writethrough_io(cache, bio, lookup_result.cblock)) - remap_to_origin_then_cache(cache, bio, block, lookup_result.cblock); - else - remap_to_cache_dirty(cache, bio, block, lookup_result.cblock); + } else { + inc_hit_counter(cache, bio); - cell_defer(cache, cell, false); + if (bio_data_dir(bio) == WRITE && writethrough_mode(&cache->features) && + !is_dirty(cache, lookup_result.cblock)) + remap_to_origin_then_cache(cache, bio, block, lookup_result.cblock); + else + remap_to_cache_dirty(cache, bio, block, lookup_result.cblock); + + cell_defer(cache, cell, false); + } break; case POLICY_MISS: @@ -2239,10 +2560,10 @@ static int cache_map(struct dm_target *ti, struct bio *bio) DMERR_LIMIT("%s: erroring bio: unknown policy op: %u", __func__, (unsigned) lookup_result.op); bio_io_error(bio); - return DM_MAPIO_SUBMITTED; + r = DM_MAPIO_SUBMITTED; } - return DM_MAPIO_REMAPPED; + return r; } static int cache_end_io(struct dm_target *ti, struct bio *bio, int error) @@ -2403,26 +2724,71 @@ static int load_discard(void *context, sector_t discard_block_size, return 0; } +static dm_cblock_t get_cache_dev_size(struct cache *cache) +{ + sector_t size = get_dev_size(cache->cache_dev); + (void) sector_div(size, cache->sectors_per_block); + return to_cblock(size); +} + +static bool can_resize(struct cache *cache, dm_cblock_t new_size) +{ + if (from_cblock(new_size) > from_cblock(cache->cache_size)) + return true; + + /* + * We can't drop a dirty block when shrinking the cache. + */ + while (from_cblock(new_size) < from_cblock(cache->cache_size)) { + new_size = to_cblock(from_cblock(new_size) + 1); + if (is_dirty(cache, new_size)) { + DMERR("unable to shrink cache; cache block %llu is dirty", + (unsigned long long) from_cblock(new_size)); + return false; + } + } + + return true; +} + +static int resize_cache_dev(struct cache *cache, dm_cblock_t new_size) +{ + int r; + + r = dm_cache_resize(cache->cmd, cache->cache_size); + if (r) { + DMERR("could not resize cache metadata"); + return r; + } + + cache->cache_size = new_size; + + return 0; +} + static int cache_preresume(struct dm_target *ti) { int r = 0; struct cache *cache = ti->private; - sector_t actual_cache_size = get_dev_size(cache->cache_dev); - (void) sector_div(actual_cache_size, cache->sectors_per_block); + dm_cblock_t csize = get_cache_dev_size(cache); /* * Check to see if the cache has resized. */ - if (from_cblock(cache->cache_size) != actual_cache_size || !cache->sized) { - cache->cache_size = to_cblock(actual_cache_size); - - r = dm_cache_resize(cache->cmd, cache->cache_size); - if (r) { - DMERR("could not resize cache metadata"); + if (!cache->sized) { + r = resize_cache_dev(cache, csize); + if (r) return r; - } cache->sized = true; + + } else if (csize != cache->cache_size) { + if (!can_resize(cache, csize)) + return -EINVAL; + + r = resize_cache_dev(cache, csize); + if (r) + return r; } if (!cache->loaded_mappings) { @@ -2515,10 +2881,19 @@ static void cache_status(struct dm_target *ti, status_type_t type, (unsigned long long) from_cblock(residency), cache->nr_dirty); - if (cache->features.write_through) + if (writethrough_mode(&cache->features)) DMEMIT("1 writethrough "); - else - DMEMIT("0 "); + + else if (passthrough_mode(&cache->features)) + DMEMIT("1 passthrough "); + + else if (writeback_mode(&cache->features)) + DMEMIT("1 writeback "); + + else { + DMERR("internal error: unknown io mode: %d", (int) cache->features.io_mode); + goto err; + } DMEMIT("2 migration_threshold %llu ", (unsigned long long) cache->migration_threshold); if (sz < maxlen) { @@ -2550,7 +2925,128 @@ err: } /* - * Supports <key> <value>. + * A cache block range can take two forms: + * + * i) A single cblock, eg. '3456' + * ii) A begin and end cblock with dots between, eg. 123-234 + */ +static int parse_cblock_range(struct cache *cache, const char *str, + struct cblock_range *result) +{ + char dummy; + uint64_t b, e; + int r; + + /* + * Try and parse form (ii) first. + */ + r = sscanf(str, "%llu-%llu%c", &b, &e, &dummy); + if (r < 0) + return r; + + if (r == 2) { + result->begin = to_cblock(b); + result->end = to_cblock(e); + return 0; + } + + /* + * That didn't work, try form (i). + */ + r = sscanf(str, "%llu%c", &b, &dummy); + if (r < 0) + return r; + + if (r == 1) { + result->begin = to_cblock(b); + result->end = to_cblock(from_cblock(result->begin) + 1u); + return 0; + } + + DMERR("invalid cblock range '%s'", str); + return -EINVAL; +} + +static int validate_cblock_range(struct cache *cache, struct cblock_range *range) +{ + uint64_t b = from_cblock(range->begin); + uint64_t e = from_cblock(range->end); + uint64_t n = from_cblock(cache->cache_size); + + if (b >= n) { + DMERR("begin cblock out of range: %llu >= %llu", b, n); + return -EINVAL; + } + + if (e > n) { + DMERR("end cblock out of range: %llu > %llu", e, n); + return -EINVAL; + } + + if (b >= e) { + DMERR("invalid cblock range: %llu >= %llu", b, e); + return -EINVAL; + } + + return 0; +} + +static int request_invalidation(struct cache *cache, struct cblock_range *range) +{ + struct invalidation_request req; + + INIT_LIST_HEAD(&req.list); + req.cblocks = range; + atomic_set(&req.complete, 0); + req.err = 0; + init_waitqueue_head(&req.result_wait); + + spin_lock(&cache->invalidation_lock); + list_add(&req.list, &cache->invalidation_requests); + spin_unlock(&cache->invalidation_lock); + wake_worker(cache); + + wait_event(req.result_wait, atomic_read(&req.complete)); + return req.err; +} + +static int process_invalidate_cblocks_message(struct cache *cache, unsigned count, + const char **cblock_ranges) +{ + int r = 0; + unsigned i; + struct cblock_range range; + + if (!passthrough_mode(&cache->features)) { + DMERR("cache has to be in passthrough mode for invalidation"); + return -EPERM; + } + + for (i = 0; i < count; i++) { + r = parse_cblock_range(cache, cblock_ranges[i], &range); + if (r) + break; + + r = validate_cblock_range(cache, &range); + if (r) + break; + + /* + * Pass begin and end origin blocks to the worker and wake it. + */ + r = request_invalidation(cache, &range); + if (r) + break; + } + + return r; +} + +/* + * Supports + * "<key> <value>" + * and + * "invalidate_cblocks [(<begin>)|(<begin>-<end>)]* * * The key migration_threshold is supported by the cache target core. */ @@ -2558,6 +3054,12 @@ static int cache_message(struct dm_target *ti, unsigned argc, char **argv) { struct cache *cache = ti->private; + if (!argc) + return -EINVAL; + + if (!strcasecmp(argv[0], "invalidate_cblocks")) + return process_invalidate_cblocks_message(cache, argc - 1, (const char **) argv + 1); + if (argc != 2) return -EINVAL; @@ -2609,9 +3111,17 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits) static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct cache *cache = ti->private; + uint64_t io_opt_sectors = limits->io_opt >> SECTOR_SHIFT; - blk_limits_io_min(limits, 0); - blk_limits_io_opt(limits, cache->sectors_per_block << SECTOR_SHIFT); + /* + * If the system-determined stacked limits are compatible with the + * cache's blocksize (io_opt is a factor) do not override them. + */ + if (io_opt_sectors < cache->sectors_per_block || + do_div(io_opt_sectors, cache->sectors_per_block)) { + blk_limits_io_min(limits, 0); + blk_limits_io_opt(limits, cache->sectors_per_block << SECTOR_SHIFT); + } set_discard_limits(cache, limits); } @@ -2619,7 +3129,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type cache_target = { .name = "cache", - .version = {1, 1, 1}, + .version = {1, 2, 0}, .module = THIS_MODULE, .ctr = cache_ctr, .dtr = cache_dtr, diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 6d2d41a..81b0fa6 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -2,6 +2,7 @@ * Copyright (C) 2003 Christophe Saout <christophe@saout.de> * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org> * Copyright (C) 2006-2009 Red Hat, Inc. All rights reserved. + * Copyright (C) 2013 Milan Broz <gmazyland@gmail.com> * * This file is released under the GPL. */ @@ -98,6 +99,13 @@ struct iv_lmk_private { u8 *seed; }; +#define TCW_WHITENING_SIZE 16 +struct iv_tcw_private { + struct crypto_shash *crc32_tfm; + u8 *iv_seed; + u8 *whitening; +}; + /* * Crypt: maps a linear range of a block device * and encrypts / decrypts at the same time. @@ -139,6 +147,7 @@ struct crypt_config { struct iv_essiv_private essiv; struct iv_benbi_private benbi; struct iv_lmk_private lmk; + struct iv_tcw_private tcw; } iv_gen_private; sector_t iv_offset; unsigned int iv_size; @@ -171,7 +180,8 @@ struct crypt_config { unsigned long flags; unsigned int key_size; - unsigned int key_parts; + unsigned int key_parts; /* independent parts in key buffer */ + unsigned int key_extra_size; /* additional keys length */ u8 key[0]; }; @@ -230,6 +240,16 @@ static struct crypto_ablkcipher *any_tfm(struct crypt_config *cc) * version 3: the same as version 2 with additional IV seed * (it uses 65 keys, last key is used as IV seed) * + * tcw: Compatible implementation of the block chaining mode used + * by the TrueCrypt device encryption system (prior to version 4.1). + * For more info see: http://www.truecrypt.org + * It operates on full 512 byte sectors and uses CBC + * with an IV derived from initial key and the sector number. + * In addition, whitening value is applied on every sector, whitening + * is calculated from initial key, sector number and mixed using CRC32. + * Note that this encryption scheme is vulnerable to watermarking attacks + * and should be used for old compatible containers access only. + * * plumb: unimplemented, see: * http://article.gmane.org/gmane.linux.kernel.device-mapper.dm-crypt/454 */ @@ -530,7 +550,7 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, char ctx[crypto_shash_descsize(lmk->hash_tfm)]; } sdesc; struct md5_state md5state; - u32 buf[4]; + __le32 buf[4]; int i, r; sdesc.desc.tfm = lmk->hash_tfm; @@ -608,6 +628,153 @@ static int crypt_iv_lmk_post(struct crypt_config *cc, u8 *iv, return r; } +static void crypt_iv_tcw_dtr(struct crypt_config *cc) +{ + struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw; + + kzfree(tcw->iv_seed); + tcw->iv_seed = NULL; + kzfree(tcw->whitening); + tcw->whitening = NULL; + + if (tcw->crc32_tfm && !IS_ERR(tcw->crc32_tfm)) + crypto_free_shash(tcw->crc32_tfm); + tcw->crc32_tfm = NULL; +} + +static int crypt_iv_tcw_ctr(struct crypt_config *cc, struct dm_target *ti, + const char *opts) +{ + struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw; + + if (cc->key_size <= (cc->iv_size + TCW_WHITENING_SIZE)) { + ti->error = "Wrong key size for TCW"; + return -EINVAL; + } + + tcw->crc32_tfm = crypto_alloc_shash("crc32", 0, 0); + if (IS_ERR(tcw->crc32_tfm)) { + ti->error = "Error initializing CRC32 in TCW"; + return PTR_ERR(tcw->crc32_tfm); + } + + tcw->iv_seed = kzalloc(cc->iv_size, GFP_KERNEL); + tcw->whitening = kzalloc(TCW_WHITENING_SIZE, GFP_KERNEL); + if (!tcw->iv_seed || !tcw->whitening) { + crypt_iv_tcw_dtr(cc); + ti->error = "Error allocating seed storage in TCW"; + return -ENOMEM; + } + + return 0; +} + +static int crypt_iv_tcw_init(struct crypt_config *cc) +{ + struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw; + int key_offset = cc->key_size - cc->iv_size - TCW_WHITENING_SIZE; + + memcpy(tcw->iv_seed, &cc->key[key_offset], cc->iv_size); + memcpy(tcw->whitening, &cc->key[key_offset + cc->iv_size], + TCW_WHITENING_SIZE); + + return 0; +} + +static int crypt_iv_tcw_wipe(struct crypt_config *cc) +{ + struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw; + + memset(tcw->iv_seed, 0, cc->iv_size); + memset(tcw->whitening, 0, TCW_WHITENING_SIZE); + + return 0; +} + +static int crypt_iv_tcw_whitening(struct crypt_config *cc, + struct dm_crypt_request *dmreq, + u8 *data) +{ + struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw; + u64 sector = cpu_to_le64((u64)dmreq->iv_sector); + u8 buf[TCW_WHITENING_SIZE]; + struct { + struct shash_desc desc; + char ctx[crypto_shash_descsize(tcw->crc32_tfm)]; + } sdesc; + int i, r; + + /* xor whitening with sector number */ + memcpy(buf, tcw->whitening, TCW_WHITENING_SIZE); + crypto_xor(buf, (u8 *)§or, 8); + crypto_xor(&buf[8], (u8 *)§or, 8); + + /* calculate crc32 for every 32bit part and xor it */ + sdesc.desc.tfm = tcw->crc32_tfm; + sdesc.desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP; + for (i = 0; i < 4; i++) { + r = crypto_shash_init(&sdesc.desc); + if (r) + goto out; + r = crypto_shash_update(&sdesc.desc, &buf[i * 4], 4); + if (r) + goto out; + r = crypto_shash_final(&sdesc.desc, &buf[i * 4]); + if (r) + goto out; + } + crypto_xor(&buf[0], &buf[12], 4); + crypto_xor(&buf[4], &buf[8], 4); + + /* apply whitening (8 bytes) to whole sector */ + for (i = 0; i < ((1 << SECTOR_SHIFT) / 8); i++) + crypto_xor(data + i * 8, buf, 8); +out: + memset(buf, 0, sizeof(buf)); + return r; +} + +static int crypt_iv_tcw_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) +{ + struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw; + u64 sector = cpu_to_le64((u64)dmreq->iv_sector); + u8 *src; + int r = 0; + + /* Remove whitening from ciphertext */ + if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) { + src = kmap_atomic(sg_page(&dmreq->sg_in)); + r = crypt_iv_tcw_whitening(cc, dmreq, src + dmreq->sg_in.offset); + kunmap_atomic(src); + } + + /* Calculate IV */ + memcpy(iv, tcw->iv_seed, cc->iv_size); + crypto_xor(iv, (u8 *)§or, 8); + if (cc->iv_size > 8) + crypto_xor(&iv[8], (u8 *)§or, cc->iv_size - 8); + + return r; +} + +static int crypt_iv_tcw_post(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) +{ + u8 *dst; + int r; + + if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) + return 0; + + /* Apply whitening on ciphertext */ + dst = kmap_atomic(sg_page(&dmreq->sg_out)); + r = crypt_iv_tcw_whitening(cc, dmreq, dst + dmreq->sg_out.offset); + kunmap_atomic(dst); + + return r; +} + static struct crypt_iv_operations crypt_iv_plain_ops = { .generator = crypt_iv_plain_gen }; @@ -643,6 +810,15 @@ static struct crypt_iv_operations crypt_iv_lmk_ops = { .post = crypt_iv_lmk_post }; +static struct crypt_iv_operations crypt_iv_tcw_ops = { + .ctr = crypt_iv_tcw_ctr, + .dtr = crypt_iv_tcw_dtr, + .init = crypt_iv_tcw_init, + .wipe = crypt_iv_tcw_wipe, + .generator = crypt_iv_tcw_gen, + .post = crypt_iv_tcw_post +}; + static void crypt_convert_init(struct crypt_config *cc, struct convert_context *ctx, struct bio *bio_out, struct bio *bio_in, @@ -774,7 +950,7 @@ static int crypt_convert(struct crypt_config *cc, /* async */ case -EBUSY: wait_for_completion(&ctx->restart); - INIT_COMPLETION(ctx->restart); + reinit_completion(&ctx->restart); /* fall through*/ case -EINPROGRESS: this_cc->req = NULL; @@ -1274,9 +1450,12 @@ static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode) static int crypt_setkey_allcpus(struct crypt_config *cc) { - unsigned subkey_size = cc->key_size >> ilog2(cc->tfms_count); + unsigned subkey_size; int err = 0, i, r; + /* Ignore extra keys (which are used for IV etc) */ + subkey_size = (cc->key_size - cc->key_extra_size) >> ilog2(cc->tfms_count); + for (i = 0; i < cc->tfms_count; i++) { r = crypto_ablkcipher_setkey(cc->tfms[i], cc->key + (i * subkey_size), @@ -1409,6 +1588,7 @@ static int crypt_ctr_cipher(struct dm_target *ti, return -EINVAL; } cc->key_parts = cc->tfms_count; + cc->key_extra_size = 0; cc->cipher = kstrdup(cipher, GFP_KERNEL); if (!cc->cipher) @@ -1460,13 +1640,6 @@ static int crypt_ctr_cipher(struct dm_target *ti, goto bad; } - /* Initialize and set key */ - ret = crypt_set_key(cc, key); - if (ret < 0) { - ti->error = "Error decoding and setting key"; - goto bad; - } - /* Initialize IV */ cc->iv_size = crypto_ablkcipher_ivsize(any_tfm(cc)); if (cc->iv_size) @@ -1493,18 +1666,33 @@ static int crypt_ctr_cipher(struct dm_target *ti, cc->iv_gen_ops = &crypt_iv_null_ops; else if (strcmp(ivmode, "lmk") == 0) { cc->iv_gen_ops = &crypt_iv_lmk_ops; - /* Version 2 and 3 is recognised according + /* + * Version 2 and 3 is recognised according * to length of provided multi-key string. * If present (version 3), last key is used as IV seed. + * All keys (including IV seed) are always the same size. */ - if (cc->key_size % cc->key_parts) + if (cc->key_size % cc->key_parts) { cc->key_parts++; + cc->key_extra_size = cc->key_size / cc->key_parts; + } + } else if (strcmp(ivmode, "tcw") == 0) { + cc->iv_gen_ops = &crypt_iv_tcw_ops; + cc->key_parts += 2; /* IV + whitening */ + cc->key_extra_size = cc->iv_size + TCW_WHITENING_SIZE; } else { ret = -EINVAL; ti->error = "Invalid IV mode"; goto bad; } + /* Initialize and set key */ + ret = crypt_set_key(cc, key); + if (ret < 0) { + ti->error = "Error decoding and setting key"; + goto bad; + } + /* Allocate IV */ if (cc->iv_gen_ops && cc->iv_gen_ops->ctr) { ret = cc->iv_gen_ops->ctr(cc, ti, ivopts); @@ -1645,20 +1833,14 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } ret = -ENOMEM; - cc->io_queue = alloc_workqueue("kcryptd_io", - WQ_NON_REENTRANT| - WQ_MEM_RECLAIM, - 1); + cc->io_queue = alloc_workqueue("kcryptd_io", WQ_MEM_RECLAIM, 1); if (!cc->io_queue) { ti->error = "Couldn't create kcryptd io queue"; goto bad; } cc->crypt_queue = alloc_workqueue("kcryptd", - WQ_NON_REENTRANT| - WQ_CPU_INTENSIVE| - WQ_MEM_RECLAIM, - 1); + WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1); if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; goto bad; @@ -1823,7 +2005,7 @@ static int crypt_iterate_devices(struct dm_target *ti, static struct target_type crypt_target = { .name = "crypt", - .version = {1, 12, 1}, + .version = {1, 13, 0}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index ea49834..2a20986 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -19,8 +19,6 @@ #define DM_MSG_PREFIX "io" #define DM_IO_MAX_REGIONS BITS_PER_LONG -#define MIN_IOS 16 -#define MIN_BIOS 16 struct dm_io_client { mempool_t *pool; @@ -50,16 +48,17 @@ static struct kmem_cache *_dm_io_cache; struct dm_io_client *dm_io_client_create(void) { struct dm_io_client *client; + unsigned min_ios = dm_get_reserved_bio_based_ios(); client = kmalloc(sizeof(*client), GFP_KERNEL); if (!client) return ERR_PTR(-ENOMEM); - client->pool = mempool_create_slab_pool(MIN_IOS, _dm_io_cache); + client->pool = mempool_create_slab_pool(min_ios, _dm_io_cache); if (!client->pool) goto bad; - client->bios = bioset_create(MIN_BIOS, 0); + client->bios = bioset_create(min_ios, 0); if (!client->bios) goto bad; diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index f1b7586..5152142 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -57,7 +57,7 @@ struct vers_iter { static struct list_head _name_buckets[NUM_BUCKETS]; static struct list_head _uuid_buckets[NUM_BUCKETS]; -static void dm_hash_remove_all(int keep_open_devices); +static void dm_hash_remove_all(bool keep_open_devices, bool mark_deferred, bool only_deferred); /* * Guards access to both hash tables. @@ -86,7 +86,7 @@ static int dm_hash_init(void) static void dm_hash_exit(void) { - dm_hash_remove_all(0); + dm_hash_remove_all(false, false, false); } /*----------------------------------------------------------------- @@ -276,7 +276,7 @@ static struct dm_table *__hash_remove(struct hash_cell *hc) return table; } -static void dm_hash_remove_all(int keep_open_devices) +static void dm_hash_remove_all(bool keep_open_devices, bool mark_deferred, bool only_deferred) { int i, dev_skipped; struct hash_cell *hc; @@ -293,7 +293,8 @@ retry: md = hc->md; dm_get(md); - if (keep_open_devices && dm_lock_for_deletion(md)) { + if (keep_open_devices && + dm_lock_for_deletion(md, mark_deferred, only_deferred)) { dm_put(md); dev_skipped++; continue; @@ -450,6 +451,11 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param, return md; } +void dm_deferred_remove(void) +{ + dm_hash_remove_all(true, false, true); +} + /*----------------------------------------------------------------- * Implementation of the ioctl commands *---------------------------------------------------------------*/ @@ -461,7 +467,7 @@ typedef int (*ioctl_fn)(struct dm_ioctl *param, size_t param_size); static int remove_all(struct dm_ioctl *param, size_t param_size) { - dm_hash_remove_all(1); + dm_hash_remove_all(true, !!(param->flags & DM_DEFERRED_REMOVE), false); param->data_size = 0; return 0; } @@ -683,6 +689,9 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param) if (dm_suspended_md(md)) param->flags |= DM_SUSPEND_FLAG; + if (dm_test_deferred_remove_flag(md)) + param->flags |= DM_DEFERRED_REMOVE; + param->dev = huge_encode_dev(disk_devt(disk)); /* @@ -832,8 +841,13 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size) /* * Ensure the device is not open and nothing further can open it. */ - r = dm_lock_for_deletion(md); + r = dm_lock_for_deletion(md, !!(param->flags & DM_DEFERRED_REMOVE), false); if (r) { + if (r == -EBUSY && param->flags & DM_DEFERRED_REMOVE) { + up_write(&_hash_lock); + dm_put(md); + return 0; + } DMDEBUG_LIMIT("unable to remove open device %s", hc->name); up_write(&_hash_lock); dm_put(md); @@ -848,6 +862,8 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size) dm_table_destroy(t); } + param->flags &= ~DM_DEFERRED_REMOVE; + if (!dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr)) param->flags |= DM_UEVENT_GENERATED_FLAG; @@ -877,7 +893,7 @@ static int dev_rename(struct dm_ioctl *param, size_t param_size) unsigned change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0; if (new_data < param->data || - invalid_str(new_data, (void *) param + param_size) || + invalid_str(new_data, (void *) param + param_size) || !*new_data || strlen(new_data) > (change_uuid ? DM_UUID_LEN - 1 : DM_NAME_LEN - 1)) { DMWARN("Invalid new mapped device name or uuid string supplied."); return -EINVAL; @@ -1262,44 +1278,37 @@ static int table_load(struct dm_ioctl *param, size_t param_size) r = dm_table_create(&t, get_mode(param), param->target_count, md); if (r) - goto out; + goto err; + /* Protect md->type and md->queue against concurrent table loads. */ + dm_lock_md_type(md); r = populate_table(t, param, param_size); - if (r) { - dm_table_destroy(t); - goto out; - } + if (r) + goto err_unlock_md_type; immutable_target_type = dm_get_immutable_target_type(md); if (immutable_target_type && (immutable_target_type != dm_table_get_immutable_target_type(t))) { DMWARN("can't replace immutable target type %s", immutable_target_type->name); - dm_table_destroy(t); r = -EINVAL; - goto out; + goto err_unlock_md_type; } - /* Protect md->type and md->queue against concurrent table loads. */ - dm_lock_md_type(md); if (dm_get_md_type(md) == DM_TYPE_NONE) /* Initial table load: acquire type of table. */ dm_set_md_type(md, dm_table_get_type(t)); else if (dm_get_md_type(md) != dm_table_get_type(t)) { DMWARN("can't change device type after initial table load."); - dm_table_destroy(t); - dm_unlock_md_type(md); r = -EINVAL; - goto out; + goto err_unlock_md_type; } /* setup md->queue to reflect md's type (may block) */ r = dm_setup_md_queue(md); if (r) { DMWARN("unable to set up device queue for new table."); - dm_table_destroy(t); - dm_unlock_md_type(md); - goto out; + goto err_unlock_md_type; } dm_unlock_md_type(md); @@ -1309,9 +1318,8 @@ static int table_load(struct dm_ioctl *param, size_t param_size) if (!hc || hc->md != md) { DMWARN("device has been removed from the dev hash table."); up_write(&_hash_lock); - dm_table_destroy(t); r = -ENXIO; - goto out; + goto err_destroy_table; } if (hc->new_map) @@ -1322,7 +1330,6 @@ static int table_load(struct dm_ioctl *param, size_t param_size) param->flags |= DM_INACTIVE_PRESENT_FLAG; __dev_status(md, param); -out: if (old_map) { dm_sync_table(md); dm_table_destroy(old_map); @@ -1330,6 +1337,15 @@ out: dm_put(md); + return 0; + +err_unlock_md_type: + dm_unlock_md_type(md); +err_destroy_table: + dm_table_destroy(t); +err: + dm_put(md); + return r; } @@ -1455,20 +1471,34 @@ static int table_status(struct dm_ioctl *param, size_t param_size) return 0; } -static bool buffer_test_overflow(char *result, unsigned maxlen) -{ - return !maxlen || strlen(result) + 1 >= maxlen; -} - /* - * Process device-mapper dependent messages. + * Process device-mapper dependent messages. Messages prefixed with '@' + * are processed by the DM core. All others are delivered to the target. * Returns a number <= 1 if message was processed by device mapper. * Returns 2 if message should be delivered to the target. */ static int message_for_md(struct mapped_device *md, unsigned argc, char **argv, char *result, unsigned maxlen) { - return 2; + int r; + + if (**argv != '@') + return 2; /* no '@' prefix, deliver to target */ + + if (!strcasecmp(argv[0], "@cancel_deferred_remove")) { + if (argc != 1) { + DMERR("Invalid arguments for @cancel_deferred_remove"); + return -EINVAL; + } + return dm_cancel_deferred_remove(md); + } + + r = dm_stats_message(md, argc, argv, result, maxlen); + if (r < 2) + return r; + + DMERR("Unsupported message sent to DM core: %s", argv[0]); + return -EINVAL; } /* @@ -1542,7 +1572,7 @@ static int target_message(struct dm_ioctl *param, size_t param_size) if (r == 1) { param->flags |= DM_DATA_OUT_FLAG; - if (buffer_test_overflow(result, maxlen)) + if (dm_message_test_buffer_overflow(result, maxlen)) param->flags |= DM_BUFFER_FULL_FLAG; else param->data_size = param->data_start + strlen(result) + 1; diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index d581fe5..3a7cade 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -833,8 +833,7 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro goto bad_slab; INIT_WORK(&kc->kcopyd_work, do_work); - kc->kcopyd_wq = alloc_workqueue("kcopyd", - WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0); + kc->kcopyd_wq = alloc_workqueue("kcopyd", WQ_MEM_RECLAIM, 0); if (!kc->kcopyd_wq) goto bad_workqueue; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index b759a12..6eb9dc9 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -7,6 +7,7 @@ #include <linux/device-mapper.h> +#include "dm.h" #include "dm-path-selector.h" #include "dm-uevent.h" @@ -86,6 +87,7 @@ struct multipath { unsigned queue_if_no_path:1; /* Queue I/O if last path fails? */ unsigned saved_queue_if_no_path:1; /* Saved state during suspension */ unsigned retain_attached_hw_handler:1; /* If there's already a hw_handler present, don't change it. */ + unsigned pg_init_disabled:1; /* pg_init is not currently allowed */ unsigned pg_init_retries; /* Number of times to retry pg_init */ unsigned pg_init_count; /* Number of times pg_init called */ @@ -116,8 +118,6 @@ struct dm_mpath_io { typedef int (*action_fn) (struct pgpath *pgpath); -#define MIN_IOS 256 /* Mempool size */ - static struct kmem_cache *_mpio_cache; static struct workqueue_struct *kmultipathd, *kmpath_handlerd; @@ -190,6 +190,7 @@ static void free_priority_group(struct priority_group *pg, static struct multipath *alloc_multipath(struct dm_target *ti) { struct multipath *m; + unsigned min_ios = dm_get_reserved_rq_based_ios(); m = kzalloc(sizeof(*m), GFP_KERNEL); if (m) { @@ -202,7 +203,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti) INIT_WORK(&m->trigger_event, trigger_event); init_waitqueue_head(&m->pg_init_wait); mutex_init(&m->work_mutex); - m->mpio_pool = mempool_create_slab_pool(MIN_IOS, _mpio_cache); + m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache); if (!m->mpio_pool) { kfree(m); return NULL; @@ -390,13 +391,16 @@ static int map_io(struct multipath *m, struct request *clone, if (was_queued) m->queue_size--; - if ((pgpath && m->queue_io) || - (!pgpath && m->queue_if_no_path)) { + if (m->pg_init_required) { + if (!m->pg_init_in_progress) + queue_work(kmultipathd, &m->process_queued_ios); + r = DM_MAPIO_REQUEUE; + } else if ((pgpath && m->queue_io) || + (!pgpath && m->queue_if_no_path)) { /* Queue for the daemon to resubmit */ list_add_tail(&clone->queuelist, &m->queued_ios); m->queue_size++; - if ((m->pg_init_required && !m->pg_init_in_progress) || - !m->queue_io) + if (!m->queue_io) queue_work(kmultipathd, &m->process_queued_ios); pgpath = NULL; r = DM_MAPIO_SUBMITTED; @@ -497,7 +501,8 @@ static void process_queued_ios(struct work_struct *work) (!pgpath && !m->queue_if_no_path)) must_queue = 0; - if (m->pg_init_required && !m->pg_init_in_progress && pgpath) + if (m->pg_init_required && !m->pg_init_in_progress && pgpath && + !m->pg_init_disabled) __pg_init_all_paths(m); spin_unlock_irqrestore(&m->lock, flags); @@ -942,10 +947,20 @@ static void multipath_wait_for_pg_init_completion(struct multipath *m) static void flush_multipath_work(struct multipath *m) { + unsigned long flags; + + spin_lock_irqsave(&m->lock, flags); + m->pg_init_disabled = 1; + spin_unlock_irqrestore(&m->lock, flags); + flush_workqueue(kmpath_handlerd); multipath_wait_for_pg_init_completion(m); flush_workqueue(kmultipathd); flush_work(&m->trigger_event); + + spin_lock_irqsave(&m->lock, flags); + m->pg_init_disabled = 0; + spin_unlock_irqrestore(&m->lock, flags); } static void multipath_dtr(struct dm_target *ti) @@ -1164,7 +1179,7 @@ static int pg_init_limit_reached(struct multipath *m, struct pgpath *pgpath) spin_lock_irqsave(&m->lock, flags); - if (m->pg_init_count <= m->pg_init_retries) + if (m->pg_init_count <= m->pg_init_retries && !m->pg_init_disabled) m->pg_init_required = 1; else limit_reached = 1; @@ -1268,6 +1283,7 @@ static int noretry_error(int error) case -EREMOTEIO: case -EILSEQ: case -ENODATA: + case -ENOSPC: return 1; } @@ -1298,8 +1314,17 @@ static int do_end_io(struct multipath *m, struct request *clone, if (!error && !clone->errors) return 0; /* I/O complete */ - if (noretry_error(error)) + if (noretry_error(error)) { + if ((clone->cmd_flags & REQ_WRITE_SAME) && + !clone->q->limits.max_write_same_sectors) { + struct queue_limits *limits; + + /* device doesn't really support WRITE SAME, disable it */ + limits = dm_get_queue_limits(dm_table_get_md(m->ti->table)); + limits->max_write_same_sectors = 0; + } return error; + } if (mpio->pgpath) fail_path(mpio->pgpath); @@ -1655,6 +1680,11 @@ static int multipath_busy(struct dm_target *ti) spin_lock_irqsave(&m->lock, flags); + /* pg_init in progress, requeue until done */ + if (m->pg_init_in_progress) { + busy = 1; + goto out; + } /* Guess which priority_group will be used at next mapping time */ if (unlikely(!m->current_pgpath && m->next_pg)) pg = m->next_pg; @@ -1704,7 +1734,7 @@ out: *---------------------------------------------------------------*/ static struct target_type multipath_target = { .name = "multipath", - .version = {1, 5, 1}, + .version = {1, 6, 0}, .module = THIS_MODULE, .ctr = multipath_ctr, .dtr = multipath_dtr, diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 699b5be..9584443 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1080,8 +1080,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->per_bio_data_size = sizeof(struct dm_raid1_bio_record); ti->discard_zeroes_data_unsupported = true; - ms->kmirrord_wq = alloc_workqueue("kmirrord", - WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0); + ms->kmirrord_wq = alloc_workqueue("kmirrord", WQ_MEM_RECLAIM, 0); if (!ms->kmirrord_wq) { DMERR("couldn't start kmirrord"); r = -ENOMEM; diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 3ac4156..2d2b1b7 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -256,7 +256,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw, */ INIT_WORK_ONSTACK(&req.work, do_metadata); queue_work(ps->metadata_wq, &req.work); - flush_work(&req.work); + flush_workqueue(ps->metadata_wq); return req.result; } @@ -269,6 +269,14 @@ static chunk_t area_location(struct pstore *ps, chunk_t area) return NUM_SNAPSHOT_HDR_CHUNKS + ((ps->exceptions_per_area + 1) * area); } +static void skip_metadata(struct pstore *ps) +{ + uint32_t stride = ps->exceptions_per_area + 1; + chunk_t next_free = ps->next_free; + if (sector_div(next_free, stride) == NUM_SNAPSHOT_HDR_CHUNKS) + ps->next_free++; +} + /* * Read or write a metadata area. Remembering to skip the first * chunk which holds the header. @@ -502,6 +510,8 @@ static int read_exceptions(struct pstore *ps, ps->current_area--; + skip_metadata(ps); + return 0; } @@ -616,8 +626,6 @@ static int persistent_prepare_exception(struct dm_exception_store *store, struct dm_exception *e) { struct pstore *ps = get_info(store); - uint32_t stride; - chunk_t next_free; sector_t size = get_dev_size(dm_snap_cow(store->snap)->bdev); /* Is there enough room ? */ @@ -630,10 +638,8 @@ static int persistent_prepare_exception(struct dm_exception_store *store, * Move onto the next free pending, making sure to take * into account the location of the metadata chunks. */ - stride = (ps->exceptions_per_area + 1); - next_free = ++ps->next_free; - if (sector_div(next_free, stride) == 1) - ps->next_free++; + ps->next_free++; + skip_metadata(ps); atomic_inc(&ps->pending_count); return 0; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index c434e5a..aec57d7 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -725,17 +725,16 @@ static int calc_max_buckets(void) */ static int init_hash_tables(struct dm_snapshot *s) { - sector_t hash_size, cow_dev_size, origin_dev_size, max_buckets; + sector_t hash_size, cow_dev_size, max_buckets; /* * Calculate based on the size of the original volume or * the COW volume... */ cow_dev_size = get_dev_size(s->cow->bdev); - origin_dev_size = get_dev_size(s->origin->bdev); max_buckets = calc_max_buckets(); - hash_size = min(origin_dev_size, cow_dev_size) >> s->store->chunk_shift; + hash_size = cow_dev_size >> s->store->chunk_shift; hash_size = min(hash_size, max_buckets); if (hash_size < 64) diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c new file mode 100644 index 0000000..3d404c1 --- /dev/null +++ b/drivers/md/dm-stats.c @@ -0,0 +1,980 @@ +#include <linux/errno.h> +#include <linux/numa.h> +#include <linux/slab.h> +#include <linux/rculist.h> +#include <linux/threads.h> +#include <linux/preempt.h> +#include <linux/irqflags.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/device-mapper.h> + +#include "dm.h" +#include "dm-stats.h" + +#define DM_MSG_PREFIX "stats" + +static int dm_stat_need_rcu_barrier; + +/* + * Using 64-bit values to avoid overflow (which is a + * problem that block/genhd.c's IO accounting has). + */ +struct dm_stat_percpu { + unsigned long long sectors[2]; + unsigned long long ios[2]; + unsigned long long merges[2]; + unsigned long long ticks[2]; + unsigned long long io_ticks[2]; + unsigned long long io_ticks_total; + unsigned long long time_in_queue; +}; + +struct dm_stat_shared { + atomic_t in_flight[2]; + unsigned long stamp; + struct dm_stat_percpu tmp; +}; + +struct dm_stat { + struct list_head list_entry; + int id; + size_t n_entries; + sector_t start; + sector_t end; + sector_t step; + const char *program_id; + const char *aux_data; + struct rcu_head rcu_head; + size_t shared_alloc_size; + size_t percpu_alloc_size; + struct dm_stat_percpu *stat_percpu[NR_CPUS]; + struct dm_stat_shared stat_shared[0]; +}; + +struct dm_stats_last_position { + sector_t last_sector; + unsigned last_rw; +}; + +/* + * A typo on the command line could possibly make the kernel run out of memory + * and crash. To prevent the crash we account all used memory. We fail if we + * exhaust 1/4 of all memory or 1/2 of vmalloc space. + */ +#define DM_STATS_MEMORY_FACTOR 4 +#define DM_STATS_VMALLOC_FACTOR 2 + +static DEFINE_SPINLOCK(shared_memory_lock); + +static unsigned long shared_memory_amount; + +static bool __check_shared_memory(size_t alloc_size) +{ + size_t a; + + a = shared_memory_amount + alloc_size; + if (a < shared_memory_amount) + return false; + if (a >> PAGE_SHIFT > totalram_pages / DM_STATS_MEMORY_FACTOR) + return false; +#ifdef CONFIG_MMU + if (a > (VMALLOC_END - VMALLOC_START) / DM_STATS_VMALLOC_FACTOR) + return false; +#endif + return true; +} + +static bool check_shared_memory(size_t alloc_size) +{ + bool ret; + + spin_lock_irq(&shared_memory_lock); + + ret = __check_shared_memory(alloc_size); + + spin_unlock_irq(&shared_memory_lock); + + return ret; +} + +static bool claim_shared_memory(size_t alloc_size) +{ + spin_lock_irq(&shared_memory_lock); + + if (!__check_shared_memory(alloc_size)) { + spin_unlock_irq(&shared_memory_lock); + return false; + } + + shared_memory_amount += alloc_size; + + spin_unlock_irq(&shared_memory_lock); + + return true; +} + +static void free_shared_memory(size_t alloc_size) +{ + unsigned long flags; + + spin_lock_irqsave(&shared_memory_lock, flags); + + if (WARN_ON_ONCE(shared_memory_amount < alloc_size)) { + spin_unlock_irqrestore(&shared_memory_lock, flags); + DMCRIT("Memory usage accounting bug."); + return; + } + + shared_memory_amount -= alloc_size; + + spin_unlock_irqrestore(&shared_memory_lock, flags); +} + +static void *dm_kvzalloc(size_t alloc_size, int node) +{ + void *p; + + if (!claim_shared_memory(alloc_size)) + return NULL; + + if (alloc_size <= KMALLOC_MAX_SIZE) { + p = kzalloc_node(alloc_size, GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN, node); + if (p) + return p; + } + p = vzalloc_node(alloc_size, node); + if (p) + return p; + + free_shared_memory(alloc_size); + + return NULL; +} + +static void dm_kvfree(void *ptr, size_t alloc_size) +{ + if (!ptr) + return; + + free_shared_memory(alloc_size); + + if (is_vmalloc_addr(ptr)) + vfree(ptr); + else + kfree(ptr); +} + +static void dm_stat_free(struct rcu_head *head) +{ + int cpu; + struct dm_stat *s = container_of(head, struct dm_stat, rcu_head); + + kfree(s->program_id); + kfree(s->aux_data); + for_each_possible_cpu(cpu) + dm_kvfree(s->stat_percpu[cpu], s->percpu_alloc_size); + dm_kvfree(s, s->shared_alloc_size); +} + +static int dm_stat_in_flight(struct dm_stat_shared *shared) +{ + return atomic_read(&shared->in_flight[READ]) + + atomic_read(&shared->in_flight[WRITE]); +} + +void dm_stats_init(struct dm_stats *stats) +{ + int cpu; + struct dm_stats_last_position *last; + + mutex_init(&stats->mutex); + INIT_LIST_HEAD(&stats->list); + stats->last = alloc_percpu(struct dm_stats_last_position); + for_each_possible_cpu(cpu) { + last = per_cpu_ptr(stats->last, cpu); + last->last_sector = (sector_t)ULLONG_MAX; + last->last_rw = UINT_MAX; + } +} + +void dm_stats_cleanup(struct dm_stats *stats) +{ + size_t ni; + struct dm_stat *s; + struct dm_stat_shared *shared; + + while (!list_empty(&stats->list)) { + s = container_of(stats->list.next, struct dm_stat, list_entry); + list_del(&s->list_entry); + for (ni = 0; ni < s->n_entries; ni++) { + shared = &s->stat_shared[ni]; + if (WARN_ON(dm_stat_in_flight(shared))) { + DMCRIT("leaked in-flight counter at index %lu " + "(start %llu, end %llu, step %llu): reads %d, writes %d", + (unsigned long)ni, + (unsigned long long)s->start, + (unsigned long long)s->end, + (unsigned long long)s->step, + atomic_read(&shared->in_flight[READ]), + atomic_read(&shared->in_flight[WRITE])); + } + } + dm_stat_free(&s->rcu_head); + } + free_percpu(stats->last); +} + +static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end, + sector_t step, const char *program_id, const char *aux_data, + void (*suspend_callback)(struct mapped_device *), + void (*resume_callback)(struct mapped_device *), + struct mapped_device *md) +{ + struct list_head *l; + struct dm_stat *s, *tmp_s; + sector_t n_entries; + size_t ni; + size_t shared_alloc_size; + size_t percpu_alloc_size; + struct dm_stat_percpu *p; + int cpu; + int ret_id; + int r; + + if (end < start || !step) + return -EINVAL; + + n_entries = end - start; + if (dm_sector_div64(n_entries, step)) + n_entries++; + + if (n_entries != (size_t)n_entries || !(size_t)(n_entries + 1)) + return -EOVERFLOW; + + shared_alloc_size = sizeof(struct dm_stat) + (size_t)n_entries * sizeof(struct dm_stat_shared); + if ((shared_alloc_size - sizeof(struct dm_stat)) / sizeof(struct dm_stat_shared) != n_entries) + return -EOVERFLOW; + + percpu_alloc_size = (size_t)n_entries * sizeof(struct dm_stat_percpu); + if (percpu_alloc_size / sizeof(struct dm_stat_percpu) != n_entries) + return -EOVERFLOW; + + if (!check_shared_memory(shared_alloc_size + num_possible_cpus() * percpu_alloc_size)) + return -ENOMEM; + + s = dm_kvzalloc(shared_alloc_size, NUMA_NO_NODE); + if (!s) + return -ENOMEM; + + s->n_entries = n_entries; + s->start = start; + s->end = end; + s->step = step; + s->shared_alloc_size = shared_alloc_size; + s->percpu_alloc_size = percpu_alloc_size; + + s->program_id = kstrdup(program_id, GFP_KERNEL); + if (!s->program_id) { + r = -ENOMEM; + goto out; + } + s->aux_data = kstrdup(aux_data, GFP_KERNEL); + if (!s->aux_data) { + r = -ENOMEM; + goto out; + } + + for (ni = 0; ni < n_entries; ni++) { + atomic_set(&s->stat_shared[ni].in_flight[READ], 0); + atomic_set(&s->stat_shared[ni].in_flight[WRITE], 0); + } + + for_each_possible_cpu(cpu) { + p = dm_kvzalloc(percpu_alloc_size, cpu_to_node(cpu)); + if (!p) { + r = -ENOMEM; + goto out; + } + s->stat_percpu[cpu] = p; + } + + /* + * Suspend/resume to make sure there is no i/o in flight, + * so that newly created statistics will be exact. + * + * (note: we couldn't suspend earlier because we must not + * allocate memory while suspended) + */ + suspend_callback(md); + + mutex_lock(&stats->mutex); + s->id = 0; + list_for_each(l, &stats->list) { + tmp_s = container_of(l, struct dm_stat, list_entry); + if (WARN_ON(tmp_s->id < s->id)) { + r = -EINVAL; + goto out_unlock_resume; + } + if (tmp_s->id > s->id) + break; + if (unlikely(s->id == INT_MAX)) { + r = -ENFILE; + goto out_unlock_resume; + } + s->id++; + } + ret_id = s->id; + list_add_tail_rcu(&s->list_entry, l); + mutex_unlock(&stats->mutex); + + resume_callback(md); + + return ret_id; + +out_unlock_resume: + mutex_unlock(&stats->mutex); + resume_callback(md); +out: + dm_stat_free(&s->rcu_head); + return r; +} + +static struct dm_stat *__dm_stats_find(struct dm_stats *stats, int id) +{ + struct dm_stat *s; + + list_for_each_entry(s, &stats->list, list_entry) { + if (s->id > id) + break; + if (s->id == id) + return s; + } + + return NULL; +} + +static int dm_stats_delete(struct dm_stats *stats, int id) +{ + struct dm_stat *s; + int cpu; + + mutex_lock(&stats->mutex); + + s = __dm_stats_find(stats, id); + if (!s) { + mutex_unlock(&stats->mutex); + return -ENOENT; + } + + list_del_rcu(&s->list_entry); + mutex_unlock(&stats->mutex); + + /* + * vfree can't be called from RCU callback + */ + for_each_possible_cpu(cpu) + if (is_vmalloc_addr(s->stat_percpu)) + goto do_sync_free; + if (is_vmalloc_addr(s)) { +do_sync_free: + synchronize_rcu_expedited(); + dm_stat_free(&s->rcu_head); + } else { + ACCESS_ONCE(dm_stat_need_rcu_barrier) = 1; + call_rcu(&s->rcu_head, dm_stat_free); + } + return 0; +} + +static int dm_stats_list(struct dm_stats *stats, const char *program, + char *result, unsigned maxlen) +{ + struct dm_stat *s; + sector_t len; + unsigned sz = 0; + + /* + * Output format: + * <region_id>: <start_sector>+<length> <step> <program_id> <aux_data> + */ + + mutex_lock(&stats->mutex); + list_for_each_entry(s, &stats->list, list_entry) { + if (!program || !strcmp(program, s->program_id)) { + len = s->end - s->start; + DMEMIT("%d: %llu+%llu %llu %s %s\n", s->id, + (unsigned long long)s->start, + (unsigned long long)len, + (unsigned long long)s->step, + s->program_id, + s->aux_data); + } + } + mutex_unlock(&stats->mutex); + + return 1; +} + +static void dm_stat_round(struct dm_stat_shared *shared, struct dm_stat_percpu *p) +{ + /* + * This is racy, but so is part_round_stats_single. + */ + unsigned long now = jiffies; + unsigned in_flight_read; + unsigned in_flight_write; + unsigned long difference = now - shared->stamp; + + if (!difference) + return; + in_flight_read = (unsigned)atomic_read(&shared->in_flight[READ]); + in_flight_write = (unsigned)atomic_read(&shared->in_flight[WRITE]); + if (in_flight_read) + p->io_ticks[READ] += difference; + if (in_flight_write) + p->io_ticks[WRITE] += difference; + if (in_flight_read + in_flight_write) { + p->io_ticks_total += difference; + p->time_in_queue += (in_flight_read + in_flight_write) * difference; + } + shared->stamp = now; +} + +static void dm_stat_for_entry(struct dm_stat *s, size_t entry, + unsigned long bi_rw, sector_t len, bool merged, + bool end, unsigned long duration) +{ + unsigned long idx = bi_rw & REQ_WRITE; + struct dm_stat_shared *shared = &s->stat_shared[entry]; + struct dm_stat_percpu *p; + + /* + * For strict correctness we should use local_irq_save/restore + * instead of preempt_disable/enable. + * + * preempt_disable/enable is racy if the driver finishes bios + * from non-interrupt context as well as from interrupt context + * or from more different interrupts. + * + * On 64-bit architectures the race only results in not counting some + * events, so it is acceptable. On 32-bit architectures the race could + * cause the counter going off by 2^32, so we need to do proper locking + * there. + * + * part_stat_lock()/part_stat_unlock() have this race too. + */ +#if BITS_PER_LONG == 32 + unsigned long flags; + local_irq_save(flags); +#else + preempt_disable(); +#endif + p = &s->stat_percpu[smp_processor_id()][entry]; + + if (!end) { + dm_stat_round(shared, p); + atomic_inc(&shared->in_flight[idx]); + } else { + dm_stat_round(shared, p); + atomic_dec(&shared->in_flight[idx]); + p->sectors[idx] += len; + p->ios[idx] += 1; + p->merges[idx] += merged; + p->ticks[idx] += duration; + } + +#if BITS_PER_LONG == 32 + local_irq_restore(flags); +#else + preempt_enable(); +#endif +} + +static void __dm_stat_bio(struct dm_stat *s, unsigned long bi_rw, + sector_t bi_sector, sector_t end_sector, + bool end, unsigned long duration, + struct dm_stats_aux *stats_aux) +{ + sector_t rel_sector, offset, todo, fragment_len; + size_t entry; + + if (end_sector <= s->start || bi_sector >= s->end) + return; + if (unlikely(bi_sector < s->start)) { + rel_sector = 0; + todo = end_sector - s->start; + } else { + rel_sector = bi_sector - s->start; + todo = end_sector - bi_sector; + } + if (unlikely(end_sector > s->end)) + todo -= (end_sector - s->end); + + offset = dm_sector_div64(rel_sector, s->step); + entry = rel_sector; + do { + if (WARN_ON_ONCE(entry >= s->n_entries)) { + DMCRIT("Invalid area access in region id %d", s->id); + return; + } + fragment_len = todo; + if (fragment_len > s->step - offset) + fragment_len = s->step - offset; + dm_stat_for_entry(s, entry, bi_rw, fragment_len, + stats_aux->merged, end, duration); + todo -= fragment_len; + entry++; + offset = 0; + } while (unlikely(todo != 0)); +} + +void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw, + sector_t bi_sector, unsigned bi_sectors, bool end, + unsigned long duration, struct dm_stats_aux *stats_aux) +{ + struct dm_stat *s; + sector_t end_sector; + struct dm_stats_last_position *last; + + if (unlikely(!bi_sectors)) + return; + + end_sector = bi_sector + bi_sectors; + + if (!end) { + /* + * A race condition can at worst result in the merged flag being + * misrepresented, so we don't have to disable preemption here. + */ + last = __this_cpu_ptr(stats->last); + stats_aux->merged = + (bi_sector == (ACCESS_ONCE(last->last_sector) && + ((bi_rw & (REQ_WRITE | REQ_DISCARD)) == + (ACCESS_ONCE(last->last_rw) & (REQ_WRITE | REQ_DISCARD))) + )); + ACCESS_ONCE(last->last_sector) = end_sector; + ACCESS_ONCE(last->last_rw) = bi_rw; + } + + rcu_read_lock(); + + list_for_each_entry_rcu(s, &stats->list, list_entry) + __dm_stat_bio(s, bi_rw, bi_sector, end_sector, end, duration, stats_aux); + + rcu_read_unlock(); +} + +static void __dm_stat_init_temporary_percpu_totals(struct dm_stat_shared *shared, + struct dm_stat *s, size_t x) +{ + int cpu; + struct dm_stat_percpu *p; + + local_irq_disable(); + p = &s->stat_percpu[smp_processor_id()][x]; + dm_stat_round(shared, p); + local_irq_enable(); + + memset(&shared->tmp, 0, sizeof(shared->tmp)); + for_each_possible_cpu(cpu) { + p = &s->stat_percpu[cpu][x]; + shared->tmp.sectors[READ] += ACCESS_ONCE(p->sectors[READ]); + shared->tmp.sectors[WRITE] += ACCESS_ONCE(p->sectors[WRITE]); + shared->tmp.ios[READ] += ACCESS_ONCE(p->ios[READ]); + shared->tmp.ios[WRITE] += ACCESS_ONCE(p->ios[WRITE]); + shared->tmp.merges[READ] += ACCESS_ONCE(p->merges[READ]); + shared->tmp.merges[WRITE] += ACCESS_ONCE(p->merges[WRITE]); + shared->tmp.ticks[READ] += ACCESS_ONCE(p->ticks[READ]); + shared->tmp.ticks[WRITE] += ACCESS_ONCE(p->ticks[WRITE]); + shared->tmp.io_ticks[READ] += ACCESS_ONCE(p->io_ticks[READ]); + shared->tmp.io_ticks[WRITE] += ACCESS_ONCE(p->io_ticks[WRITE]); + shared->tmp.io_ticks_total += ACCESS_ONCE(p->io_ticks_total); + shared->tmp.time_in_queue += ACCESS_ONCE(p->time_in_queue); + } +} + +static void __dm_stat_clear(struct dm_stat *s, size_t idx_start, size_t idx_end, + bool init_tmp_percpu_totals) +{ + size_t x; + struct dm_stat_shared *shared; + struct dm_stat_percpu *p; + + for (x = idx_start; x < idx_end; x++) { + shared = &s->stat_shared[x]; + if (init_tmp_percpu_totals) + __dm_stat_init_temporary_percpu_totals(shared, s, x); + local_irq_disable(); + p = &s->stat_percpu[smp_processor_id()][x]; + p->sectors[READ] -= shared->tmp.sectors[READ]; + p->sectors[WRITE] -= shared->tmp.sectors[WRITE]; + p->ios[READ] -= shared->tmp.ios[READ]; + p->ios[WRITE] -= shared->tmp.ios[WRITE]; + p->merges[READ] -= shared->tmp.merges[READ]; + p->merges[WRITE] -= shared->tmp.merges[WRITE]; + p->ticks[READ] -= shared->tmp.ticks[READ]; + p->ticks[WRITE] -= shared->tmp.ticks[WRITE]; + p->io_ticks[READ] -= shared->tmp.io_ticks[READ]; + p->io_ticks[WRITE] -= shared->tmp.io_ticks[WRITE]; + p->io_ticks_total -= shared->tmp.io_ticks_total; + p->time_in_queue -= shared->tmp.time_in_queue; + local_irq_enable(); + } +} + +static int dm_stats_clear(struct dm_stats *stats, int id) +{ + struct dm_stat *s; + + mutex_lock(&stats->mutex); + + s = __dm_stats_find(stats, id); + if (!s) { + mutex_unlock(&stats->mutex); + return -ENOENT; + } + + __dm_stat_clear(s, 0, s->n_entries, true); + + mutex_unlock(&stats->mutex); + + return 1; +} + +/* + * This is like jiffies_to_msec, but works for 64-bit values. + */ +static unsigned long long dm_jiffies_to_msec64(unsigned long long j) +{ + unsigned long long result = 0; + unsigned mult; + + if (j) + result = jiffies_to_msecs(j & 0x3fffff); + if (j >= 1 << 22) { + mult = jiffies_to_msecs(1 << 22); + result += (unsigned long long)mult * (unsigned long long)jiffies_to_msecs((j >> 22) & 0x3fffff); + } + if (j >= 1ULL << 44) + result += (unsigned long long)mult * (unsigned long long)mult * (unsigned long long)jiffies_to_msecs(j >> 44); + + return result; +} + +static int dm_stats_print(struct dm_stats *stats, int id, + size_t idx_start, size_t idx_len, + bool clear, char *result, unsigned maxlen) +{ + unsigned sz = 0; + struct dm_stat *s; + size_t x; + sector_t start, end, step; + size_t idx_end; + struct dm_stat_shared *shared; + + /* + * Output format: + * <start_sector>+<length> counters + */ + + mutex_lock(&stats->mutex); + + s = __dm_stats_find(stats, id); + if (!s) { + mutex_unlock(&stats->mutex); + return -ENOENT; + } + + idx_end = idx_start + idx_len; + if (idx_end < idx_start || + idx_end > s->n_entries) + idx_end = s->n_entries; + + if (idx_start > idx_end) + idx_start = idx_end; + + step = s->step; + start = s->start + (step * idx_start); + + for (x = idx_start; x < idx_end; x++, start = end) { + shared = &s->stat_shared[x]; + end = start + step; + if (unlikely(end > s->end)) + end = s->end; + + __dm_stat_init_temporary_percpu_totals(shared, s, x); + + DMEMIT("%llu+%llu %llu %llu %llu %llu %llu %llu %llu %llu %d %llu %llu %llu %llu\n", + (unsigned long long)start, + (unsigned long long)step, + shared->tmp.ios[READ], + shared->tmp.merges[READ], + shared->tmp.sectors[READ], + dm_jiffies_to_msec64(shared->tmp.ticks[READ]), + shared->tmp.ios[WRITE], + shared->tmp.merges[WRITE], + shared->tmp.sectors[WRITE], + dm_jiffies_to_msec64(shared->tmp.ticks[WRITE]), + dm_stat_in_flight(shared), + dm_jiffies_to_msec64(shared->tmp.io_ticks_total), + dm_jiffies_to_msec64(shared->tmp.time_in_queue), + dm_jiffies_to_msec64(shared->tmp.io_ticks[READ]), + dm_jiffies_to_msec64(shared->tmp.io_ticks[WRITE])); + + if (unlikely(sz + 1 >= maxlen)) + goto buffer_overflow; + } + + if (clear) + __dm_stat_clear(s, idx_start, idx_end, false); + +buffer_overflow: + mutex_unlock(&stats->mutex); + + return 1; +} + +static int dm_stats_set_aux(struct dm_stats *stats, int id, const char *aux_data) +{ + struct dm_stat *s; + const char *new_aux_data; + + mutex_lock(&stats->mutex); + + s = __dm_stats_find(stats, id); + if (!s) { + mutex_unlock(&stats->mutex); + return -ENOENT; + } + + new_aux_data = kstrdup(aux_data, GFP_KERNEL); + if (!new_aux_data) { + mutex_unlock(&stats->mutex); + return -ENOMEM; + } + + kfree(s->aux_data); + s->aux_data = new_aux_data; + + mutex_unlock(&stats->mutex); + + return 0; +} + +static int message_stats_create(struct mapped_device *md, + unsigned argc, char **argv, + char *result, unsigned maxlen) +{ + int id; + char dummy; + unsigned long long start, end, len, step; + unsigned divisor; + const char *program_id, *aux_data; + + /* + * Input format: + * <range> <step> [<program_id> [<aux_data>]] + */ + + if (argc < 3 || argc > 5) + return -EINVAL; + + if (!strcmp(argv[1], "-")) { + start = 0; + len = dm_get_size(md); + if (!len) + len = 1; + } else if (sscanf(argv[1], "%llu+%llu%c", &start, &len, &dummy) != 2 || + start != (sector_t)start || len != (sector_t)len) + return -EINVAL; + + end = start + len; + if (start >= end) + return -EINVAL; + + if (sscanf(argv[2], "/%u%c", &divisor, &dummy) == 1) { + step = end - start; + if (do_div(step, divisor)) + step++; + if (!step) + step = 1; + } else if (sscanf(argv[2], "%llu%c", &step, &dummy) != 1 || + step != (sector_t)step || !step) + return -EINVAL; + + program_id = "-"; + aux_data = "-"; + + if (argc > 3) + program_id = argv[3]; + + if (argc > 4) + aux_data = argv[4]; + + /* + * If a buffer overflow happens after we created the region, + * it's too late (the userspace would retry with a larger + * buffer, but the region id that caused the overflow is already + * leaked). So we must detect buffer overflow in advance. + */ + snprintf(result, maxlen, "%d", INT_MAX); + if (dm_message_test_buffer_overflow(result, maxlen)) + return 1; + + id = dm_stats_create(dm_get_stats(md), start, end, step, program_id, aux_data, + dm_internal_suspend, dm_internal_resume, md); + if (id < 0) + return id; + + snprintf(result, maxlen, "%d", id); + + return 1; +} + +static int message_stats_delete(struct mapped_device *md, + unsigned argc, char **argv) +{ + int id; + char dummy; + + if (argc != 2) + return -EINVAL; + + if (sscanf(argv[1], "%d%c", &id, &dummy) != 1 || id < 0) + return -EINVAL; + + return dm_stats_delete(dm_get_stats(md), id); +} + +static int message_stats_clear(struct mapped_device *md, + unsigned argc, char **argv) +{ + int id; + char dummy; + + if (argc != 2) + return -EINVAL; + + if (sscanf(argv[1], "%d%c", &id, &dummy) != 1 || id < 0) + return -EINVAL; + + return dm_stats_clear(dm_get_stats(md), id); +} + +static int message_stats_list(struct mapped_device *md, + unsigned argc, char **argv, + char *result, unsigned maxlen) +{ + int r; + const char *program = NULL; + + if (argc < 1 || argc > 2) + return -EINVAL; + + if (argc > 1) { + program = kstrdup(argv[1], GFP_KERNEL); + if (!program) + return -ENOMEM; + } + + r = dm_stats_list(dm_get_stats(md), program, result, maxlen); + + kfree(program); + + return r; +} + +static int message_stats_print(struct mapped_device *md, + unsigned argc, char **argv, bool clear, + char *result, unsigned maxlen) +{ + int id; + char dummy; + unsigned long idx_start = 0, idx_len = ULONG_MAX; + + if (argc != 2 && argc != 4) + return -EINVAL; + + if (sscanf(argv[1], "%d%c", &id, &dummy) != 1 || id < 0) + return -EINVAL; + + if (argc > 3) { + if (strcmp(argv[2], "-") && + sscanf(argv[2], "%lu%c", &idx_start, &dummy) != 1) + return -EINVAL; + if (strcmp(argv[3], "-") && + sscanf(argv[3], "%lu%c", &idx_len, &dummy) != 1) + return -EINVAL; + } + + return dm_stats_print(dm_get_stats(md), id, idx_start, idx_len, clear, + result, maxlen); +} + +static int message_stats_set_aux(struct mapped_device *md, + unsigned argc, char **argv) +{ + int id; + char dummy; + + if (argc != 3) + return -EINVAL; + + if (sscanf(argv[1], "%d%c", &id, &dummy) != 1 || id < 0) + return -EINVAL; + + return dm_stats_set_aux(dm_get_stats(md), id, argv[2]); +} + +int dm_stats_message(struct mapped_device *md, unsigned argc, char **argv, + char *result, unsigned maxlen) +{ + int r; + + if (dm_request_based(md)) { + DMWARN("Statistics are only supported for bio-based devices"); + return -EOPNOTSUPP; + } + + /* All messages here must start with '@' */ + if (!strcasecmp(argv[0], "@stats_create")) + r = message_stats_create(md, argc, argv, result, maxlen); + else if (!strcasecmp(argv[0], "@stats_delete")) + r = message_stats_delete(md, argc, argv); + else if (!strcasecmp(argv[0], "@stats_clear")) + r = message_stats_clear(md, argc, argv); + else if (!strcasecmp(argv[0], "@stats_list")) + r = message_stats_list(md, argc, argv, result, maxlen); + else if (!strcasecmp(argv[0], "@stats_print")) + r = message_stats_print(md, argc, argv, false, result, maxlen); + else if (!strcasecmp(argv[0], "@stats_print_clear")) + r = message_stats_print(md, argc, argv, true, result, maxlen); + else if (!strcasecmp(argv[0], "@stats_set_aux")) + r = message_stats_set_aux(md, argc, argv); + else + return 2; /* this wasn't a stats message */ + + if (r == -EINVAL) + DMWARN("Invalid parameters for message %s", argv[0]); + + return r; +} + +int __init dm_statistics_init(void) +{ + dm_stat_need_rcu_barrier = 0; + return 0; +} + +void dm_statistics_exit(void) +{ + if (dm_stat_need_rcu_barrier) + rcu_barrier(); + if (WARN_ON(shared_memory_amount)) + DMCRIT("shared_memory_amount leaked: %lu", shared_memory_amount); +} + +module_param_named(stats_current_allocated_bytes, shared_memory_amount, ulong, S_IRUGO); +MODULE_PARM_DESC(stats_current_allocated_bytes, "Memory currently used by statistics"); diff --git a/drivers/md/dm-stats.h b/drivers/md/dm-stats.h new file mode 100644 index 0000000..e7c4984 --- /dev/null +++ b/drivers/md/dm-stats.h @@ -0,0 +1,40 @@ +#ifndef DM_STATS_H +#define DM_STATS_H + +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/list.h> + +int dm_statistics_init(void); +void dm_statistics_exit(void); + +struct dm_stats { + struct mutex mutex; + struct list_head list; /* list of struct dm_stat */ + struct dm_stats_last_position __percpu *last; + sector_t last_sector; + unsigned last_rw; +}; + +struct dm_stats_aux { + bool merged; +}; + +void dm_stats_init(struct dm_stats *st); +void dm_stats_cleanup(struct dm_stats *st); + +struct mapped_device; + +int dm_stats_message(struct mapped_device *md, unsigned argc, char **argv, + char *result, unsigned maxlen); + +void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw, + sector_t bi_sector, unsigned bi_sectors, bool end, + unsigned long duration, struct dm_stats_aux *aux); + +static inline bool dm_stats_used(struct dm_stats *st) +{ + return !list_empty(&st->list); +} + +#endif diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index d907ca6..73c1712 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -4,6 +4,7 @@ * This file is released under the GPL. */ +#include "dm.h" #include <linux/device-mapper.h> #include <linux/module.h> diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index f221812..465f08c 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -545,14 +545,28 @@ static int adjoin(struct dm_table *table, struct dm_target *ti) /* * Used to dynamically allocate the arg array. + * + * We do first allocation with GFP_NOIO because dm-mpath and dm-thin must + * process messages even if some device is suspended. These messages have a + * small fixed number of arguments. + * + * On the other hand, dm-switch needs to process bulk data using messages and + * excessive use of GFP_NOIO could cause trouble. */ static char **realloc_argv(unsigned *array_size, char **old_argv) { char **argv; unsigned new_size; + gfp_t gfp; - new_size = *array_size ? *array_size * 2 : 64; - argv = kmalloc(new_size * sizeof(*argv), GFP_KERNEL); + if (*array_size) { + new_size = *array_size * 2; + gfp = GFP_KERNEL; + } else { + new_size = 8; + gfp = GFP_NOIO; + } + argv = kmalloc(new_size * sizeof(*argv), gfp); if (argv) { memcpy(argv, old_argv, *array_size * sizeof(*argv)); *array_size = new_size; @@ -860,14 +874,17 @@ EXPORT_SYMBOL(dm_consume_args); static int dm_table_set_type(struct dm_table *t) { unsigned i; - unsigned bio_based = 0, request_based = 0; + unsigned bio_based = 0, request_based = 0, hybrid = 0; struct dm_target *tgt; struct dm_dev_internal *dd; struct list_head *devices; + unsigned live_md_type; for (i = 0; i < t->num_targets; i++) { tgt = t->targets + i; - if (dm_target_request_based(tgt)) + if (dm_target_hybrid(tgt)) + hybrid = 1; + else if (dm_target_request_based(tgt)) request_based = 1; else bio_based = 1; @@ -879,6 +896,19 @@ static int dm_table_set_type(struct dm_table *t) } } + if (hybrid && !bio_based && !request_based) { + /* + * The targets can work either way. + * Determine the type from the live device. + * Default to bio-based if device is new. + */ + live_md_type = dm_get_md_type(t->md); + if (live_md_type == DM_TYPE_REQUEST_BASED) + request_based = 1; + else + bio_based = 1; + } + if (bio_based) { /* We must use this table as bio-based */ t->type = DM_TYPE_BIO_BASED; @@ -1532,8 +1562,11 @@ int dm_table_resume_targets(struct dm_table *t) continue; r = ti->type->preresume(ti); - if (r) + if (r) { + DMERR("%s: %s: preresume failed, error = %d", + dm_device_name(t->md), ti->type->name, r); return r; + } } for (i = 0; i < t->num_targets; i++) { diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c index 37ba5db..242e3ce 100644 --- a/drivers/md/dm-target.c +++ b/drivers/md/dm-target.c @@ -131,12 +131,19 @@ static int io_err_map(struct dm_target *tt, struct bio *bio) return -EIO; } +static int io_err_map_rq(struct dm_target *ti, struct request *clone, + union map_info *map_context) +{ + return -EIO; +} + static struct target_type error_target = { .name = "error", - .version = {1, 1, 0}, + .version = {1, 2, 0}, .ctr = io_err_ctr, .dtr = io_err_dtr, .map = io_err_map, + .map_rq = io_err_map_rq, }; int __init dm_target_init(void) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 88f2f80..2c0cf51 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -887,7 +887,8 @@ static int commit(struct pool *pool) r = dm_pool_commit_metadata(pool->pmd); if (r) - DMERR_LIMIT("commit failed: error = %d", r); + DMERR_LIMIT("%s: commit failed: error = %d", + dm_device_name(pool->pool_md), r); return r; } @@ -917,6 +918,13 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result) unsigned long flags; struct pool *pool = tc->pool; + /* + * Once no_free_space is set we must not allow allocation to succeed. + * Otherwise it is difficult to explain, debug, test and support. + */ + if (pool->no_free_space) + return -ENOSPC; + r = dm_pool_get_free_block_count(pool->pmd, &free_blocks); if (r) return r; @@ -931,31 +939,30 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result) } if (!free_blocks) { - if (pool->no_free_space) - return -ENOSPC; - else { - /* - * Try to commit to see if that will free up some - * more space. - */ - (void) commit_or_fallback(pool); + /* + * Try to commit to see if that will free up some + * more space. + */ + (void) commit_or_fallback(pool); - r = dm_pool_get_free_block_count(pool->pmd, &free_blocks); - if (r) - return r; + r = dm_pool_get_free_block_count(pool->pmd, &free_blocks); + if (r) + return r; - /* - * If we still have no space we set a flag to avoid - * doing all this checking and return -ENOSPC. - */ - if (!free_blocks) { - DMWARN("%s: no free space available.", - dm_device_name(pool->pool_md)); - spin_lock_irqsave(&pool->lock, flags); - pool->no_free_space = 1; - spin_unlock_irqrestore(&pool->lock, flags); - return -ENOSPC; - } + /* + * If we still have no space we set a flag to avoid + * doing all this checking and return -ENOSPC. This + * flag serves as a latch that disallows allocations from + * this pool until the admin takes action (e.g. resize or + * table reload). + */ + if (!free_blocks) { + DMWARN("%s: no free space available.", + dm_device_name(pool->pool_md)); + spin_lock_irqsave(&pool->lock, flags); + pool->no_free_space = 1; + spin_unlock_irqrestore(&pool->lock, flags); + return -ENOSPC; } } @@ -1085,6 +1092,7 @@ static void break_sharing(struct thin_c *tc, struct bio *bio, dm_block_t block, { int r; dm_block_t data_block; + struct pool *pool = tc->pool; r = alloc_data_block(tc, &data_block); switch (r) { @@ -1094,13 +1102,14 @@ static void break_sharing(struct thin_c *tc, struct bio *bio, dm_block_t block, break; case -ENOSPC: - no_space(tc->pool, cell); + no_space(pool, cell); break; default: DMERR_LIMIT("%s: alloc_data_block() failed: error = %d", __func__, r); - cell_error(tc->pool, cell); + set_pool_mode(pool, PM_READ_ONLY); + cell_error(pool, cell); break; } } @@ -1386,7 +1395,8 @@ static void set_pool_mode(struct pool *pool, enum pool_mode mode) switch (mode) { case PM_FAIL: - DMERR("switching pool to failure mode"); + DMERR("%s: switching pool to failure mode", + dm_device_name(pool->pool_md)); pool->process_bio = process_bio_fail; pool->process_discard = process_bio_fail; pool->process_prepared_mapping = process_prepared_mapping_fail; @@ -1394,10 +1404,12 @@ static void set_pool_mode(struct pool *pool, enum pool_mode mode) break; case PM_READ_ONLY: - DMERR("switching pool to read-only mode"); + DMERR("%s: switching pool to read-only mode", + dm_device_name(pool->pool_md)); r = dm_pool_abort_metadata(pool->pmd); if (r) { - DMERR("aborting transaction failed"); + DMERR("%s: aborting transaction failed", + dm_device_name(pool->pool_md)); set_pool_mode(pool, PM_FAIL); } else { dm_pool_metadata_read_only(pool->pmd); @@ -2083,6 +2095,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) * them down to the data device. The thin device's discard * processing will cause mappings to be removed from the btree. */ + ti->discard_zeroes_data_unsupported = true; if (pf.discard_enabled && pf.discard_passdown) { ti->num_discard_bios = 1; @@ -2092,7 +2105,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) * thin devices' discard limits consistent). */ ti->discards_supported = true; - ti->discard_zeroes_data_unsupported = true; } ti->private = pt; @@ -2156,19 +2168,22 @@ static int maybe_resize_data_dev(struct dm_target *ti, bool *need_commit) r = dm_pool_get_data_dev_size(pool->pmd, &sb_data_size); if (r) { - DMERR("failed to retrieve data device size"); + DMERR("%s: failed to retrieve data device size", + dm_device_name(pool->pool_md)); return r; } if (data_size < sb_data_size) { - DMERR("pool target (%llu blocks) too small: expected %llu", + DMERR("%s: pool target (%llu blocks) too small: expected %llu", + dm_device_name(pool->pool_md), (unsigned long long)data_size, sb_data_size); return -EINVAL; } else if (data_size > sb_data_size) { r = dm_pool_resize_data_dev(pool->pmd, data_size); if (r) { - DMERR("failed to resize data device"); + DMERR("%s: failed to resize data device", + dm_device_name(pool->pool_md)); set_pool_mode(pool, PM_READ_ONLY); return r; } @@ -2192,19 +2207,22 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit) r = dm_pool_get_metadata_dev_size(pool->pmd, &sb_metadata_dev_size); if (r) { - DMERR("failed to retrieve data device size"); + DMERR("%s: failed to retrieve metadata device size", + dm_device_name(pool->pool_md)); return r; } if (metadata_dev_size < sb_metadata_dev_size) { - DMERR("metadata device (%llu blocks) too small: expected %llu", + DMERR("%s: metadata device (%llu blocks) too small: expected %llu", + dm_device_name(pool->pool_md), metadata_dev_size, sb_metadata_dev_size); return -EINVAL; } else if (metadata_dev_size > sb_metadata_dev_size) { r = dm_pool_resize_metadata_dev(pool->pmd, metadata_dev_size); if (r) { - DMERR("failed to resize metadata device"); + DMERR("%s: failed to resize metadata device", + dm_device_name(pool->pool_md)); return r; } @@ -2530,37 +2548,43 @@ static void pool_status(struct dm_target *ti, status_type_t type, r = dm_pool_get_metadata_transaction_id(pool->pmd, &transaction_id); if (r) { - DMERR("dm_pool_get_metadata_transaction_id returned %d", r); + DMERR("%s: dm_pool_get_metadata_transaction_id returned %d", + dm_device_name(pool->pool_md), r); goto err; } r = dm_pool_get_free_metadata_block_count(pool->pmd, &nr_free_blocks_metadata); if (r) { - DMERR("dm_pool_get_free_metadata_block_count returned %d", r); + DMERR("%s: dm_pool_get_free_metadata_block_count returned %d", + dm_device_name(pool->pool_md), r); goto err; } r = dm_pool_get_metadata_dev_size(pool->pmd, &nr_blocks_metadata); if (r) { - DMERR("dm_pool_get_metadata_dev_size returned %d", r); + DMERR("%s: dm_pool_get_metadata_dev_size returned %d", + dm_device_name(pool->pool_md), r); goto err; } r = dm_pool_get_free_block_count(pool->pmd, &nr_free_blocks_data); if (r) { - DMERR("dm_pool_get_free_block_count returned %d", r); + DMERR("%s: dm_pool_get_free_block_count returned %d", + dm_device_name(pool->pool_md), r); goto err; } r = dm_pool_get_data_dev_size(pool->pmd, &nr_blocks_data); if (r) { - DMERR("dm_pool_get_data_dev_size returned %d", r); + DMERR("%s: dm_pool_get_data_dev_size returned %d", + dm_device_name(pool->pool_md), r); goto err; } r = dm_pool_get_metadata_snap(pool->pmd, &held_root); if (r) { - DMERR("dm_pool_get_metadata_snap returned %d", r); + DMERR("%s: dm_pool_get_metadata_snap returned %d", + dm_device_name(pool->pool_md), r); goto err; } @@ -2648,17 +2672,33 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct pool_c *pt = ti->private; struct pool *pool = pt->pool; + uint64_t io_opt_sectors = limits->io_opt >> SECTOR_SHIFT; - blk_limits_io_min(limits, 0); - blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT); + /* + * If the system-determined stacked limits are compatible with the + * pool's blocksize (io_opt is a factor) do not override them. + */ + if (io_opt_sectors < pool->sectors_per_block || + do_div(io_opt_sectors, pool->sectors_per_block)) { + blk_limits_io_min(limits, 0); + blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT); + } /* * pt->adjusted_pf is a staging area for the actual features to use. * They get transferred to the live pool in bind_control_target() * called from pool_preresume(). */ - if (!pt->adjusted_pf.discard_enabled) + if (!pt->adjusted_pf.discard_enabled) { + /* + * Must explicitly disallow stacking discard limits otherwise the + * block layer will stack them if pool's data device has support. + * QUEUE_FLAG_DISCARD wouldn't be set but there is no way for the + * user to see that, so make sure to set all discard limits to 0. + */ + limits->discard_granularity = 0; return; + } disable_passdown_if_not_supported(pt); @@ -2669,7 +2709,7 @@ static struct target_type pool_target = { .name = "thin-pool", .features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE | DM_TARGET_IMMUTABLE, - .version = {1, 8, 0}, + .version = {1, 9, 0}, .module = THIS_MODULE, .ctr = pool_ctr, .dtr = pool_dtr, @@ -2794,10 +2834,10 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->per_bio_data_size = sizeof(struct dm_thin_endio_hook); /* In case the pool supports discards, pass them on. */ + ti->discard_zeroes_data_unsupported = true; if (tc->pool->pf.discard_enabled) { ti->discards_supported = true; ti->num_discard_bios = 1; - ti->discard_zeroes_data_unsupported = true; /* Discard bios must be split on a block boundary */ ti->split_discard_bios = true; } @@ -2956,7 +2996,7 @@ static int thin_iterate_devices(struct dm_target *ti, static struct target_type thin_target = { .name = "thin", - .version = {1, 8, 0}, + .version = {1, 9, 0}, .module = THIS_MODULE, .ctr = thin_ctr, .dtr = thin_dtr, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 9e39d2b..0704c52 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -49,6 +49,11 @@ static unsigned int _major = 0; static DEFINE_IDR(_minor_idr); static DEFINE_SPINLOCK(_minor_lock); + +static void do_deferred_remove(struct work_struct *w); + +static DECLARE_WORK(deferred_remove_work, do_deferred_remove); + /* * For bio-based dm. * One of these is allocated per bio. @@ -60,6 +65,7 @@ struct dm_io { struct bio *bio; unsigned long start_time; spinlock_t endio_lock; + struct dm_stats_aux stats_aux; }; /* @@ -115,6 +121,7 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo); #define DMF_DELETING 4 #define DMF_NOFLUSH_SUSPENDING 5 #define DMF_MERGE_IS_OPTIONAL 6 +#define DMF_DEFERRED_REMOVE 7 /* * A dummy definition to make RCU happy. @@ -198,6 +205,8 @@ struct mapped_device { /* zero-length flush that will be cloned and submitted to targets */ struct bio flush_bio; + + struct dm_stats stats; }; /* @@ -208,10 +217,55 @@ struct dm_md_mempools { struct bio_set *bs; }; -#define MIN_IOS 256 +#define RESERVED_BIO_BASED_IOS 16 +#define RESERVED_REQUEST_BASED_IOS 256 +#define RESERVED_MAX_IOS 1024 static struct kmem_cache *_io_cache; static struct kmem_cache *_rq_tio_cache; +/* + * Bio-based DM's mempools' reserved IOs set by the user. + */ +static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS; + +/* + * Request-based DM's mempools' reserved IOs set by the user. + */ +static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS; + +static unsigned __dm_get_reserved_ios(unsigned *reserved_ios, + unsigned def, unsigned max) +{ + unsigned ios = ACCESS_ONCE(*reserved_ios); + unsigned modified_ios = 0; + + if (!ios) + modified_ios = def; + else if (ios > max) + modified_ios = max; + + if (modified_ios) { + (void)cmpxchg(reserved_ios, ios, modified_ios); + ios = modified_ios; + } + + return ios; +} + +unsigned dm_get_reserved_bio_based_ios(void) +{ + return __dm_get_reserved_ios(&reserved_bio_based_ios, + RESERVED_BIO_BASED_IOS, RESERVED_MAX_IOS); +} +EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios); + +unsigned dm_get_reserved_rq_based_ios(void) +{ + return __dm_get_reserved_ios(&reserved_rq_based_ios, + RESERVED_REQUEST_BASED_IOS, RESERVED_MAX_IOS); +} +EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios); + static int __init local_init(void) { int r = -ENOMEM; @@ -251,6 +305,8 @@ out_free_io_cache: static void local_exit(void) { + flush_scheduled_work(); + kmem_cache_destroy(_rq_tio_cache); kmem_cache_destroy(_io_cache); unregister_blkdev(_major, _name); @@ -269,6 +325,7 @@ static int (*_inits[])(void) __initdata = { dm_io_init, dm_kcopyd_init, dm_interface_init, + dm_statistics_init, }; static void (*_exits[])(void) = { @@ -279,6 +336,7 @@ static void (*_exits[])(void) = { dm_io_exit, dm_kcopyd_exit, dm_interface_exit, + dm_statistics_exit, }; static int __init dm_init(void) @@ -354,7 +412,10 @@ static void dm_blk_close(struct gendisk *disk, fmode_t mode) spin_lock(&_minor_lock); - atomic_dec(&md->open_count); + if (atomic_dec_and_test(&md->open_count) && + (test_bit(DMF_DEFERRED_REMOVE, &md->flags))) + schedule_work(&deferred_remove_work); + dm_put(md); spin_unlock(&_minor_lock); @@ -368,14 +429,18 @@ int dm_open_count(struct mapped_device *md) /* * Guarantees nothing is using the device before it's deleted. */ -int dm_lock_for_deletion(struct mapped_device *md) +int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred) { int r = 0; spin_lock(&_minor_lock); - if (dm_open_count(md)) + if (dm_open_count(md)) { r = -EBUSY; + if (mark_deferred) + set_bit(DMF_DEFERRED_REMOVE, &md->flags); + } else if (only_deferred && !test_bit(DMF_DEFERRED_REMOVE, &md->flags)) + r = -EEXIST; else set_bit(DMF_DELETING, &md->flags); @@ -384,6 +449,37 @@ int dm_lock_for_deletion(struct mapped_device *md) return r; } +int dm_cancel_deferred_remove(struct mapped_device *md) +{ + int r = 0; + + spin_lock(&_minor_lock); + + if (test_bit(DMF_DELETING, &md->flags)) + r = -EBUSY; + else + clear_bit(DMF_DEFERRED_REMOVE, &md->flags); + + spin_unlock(&_minor_lock); + + return r; +} + +static void do_deferred_remove(struct work_struct *w) +{ + dm_deferred_remove(); +} + +sector_t dm_get_size(struct mapped_device *md) +{ + return get_capacity(md->disk); +} + +struct dm_stats *dm_get_stats(struct mapped_device *md) +{ + return &md->stats; +} + static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) { struct mapped_device *md = bdev->bd_disk->private_data; @@ -466,8 +562,9 @@ static int md_in_flight(struct mapped_device *md) static void start_io_acct(struct dm_io *io) { struct mapped_device *md = io->md; + struct bio *bio = io->bio; int cpu; - int rw = bio_data_dir(io->bio); + int rw = bio_data_dir(bio); io->start_time = jiffies; @@ -476,6 +573,10 @@ static void start_io_acct(struct dm_io *io) part_stat_unlock(); atomic_set(&dm_disk(md)->part0.in_flight[rw], atomic_inc_return(&md->pending[rw])); + + if (unlikely(dm_stats_used(&md->stats))) + dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_sector, + bio_sectors(bio), false, 0, &io->stats_aux); } static void end_io_acct(struct dm_io *io) @@ -491,6 +592,10 @@ static void end_io_acct(struct dm_io *io) part_stat_add(cpu, &dm_disk(md)->part0, ticks[rw], duration); part_stat_unlock(); + if (unlikely(dm_stats_used(&md->stats))) + dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_sector, + bio_sectors(bio), true, duration, &io->stats_aux); + /* * After this is decremented the bio must not be touched if it is * a flush. @@ -1519,7 +1624,7 @@ static void _dm_request(struct request_queue *q, struct bio *bio) return; } -static int dm_request_based(struct mapped_device *md) +int dm_request_based(struct mapped_device *md) { return blk_queue_stackable(md->queue); } @@ -1946,8 +2051,7 @@ static struct mapped_device *alloc_dev(int minor) add_disk(md->disk); format_dev_t(md->name, MKDEV(_major, minor)); - md->wq = alloc_workqueue("kdmflush", - WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0); + md->wq = alloc_workqueue("kdmflush", WQ_MEM_RECLAIM, 0); if (!md->wq) goto bad_thread; @@ -1959,6 +2063,8 @@ static struct mapped_device *alloc_dev(int minor) md->flush_bio.bi_bdev = md->bdev; md->flush_bio.bi_rw = WRITE_FLUSH; + dm_stats_init(&md->stats); + /* Populate the mapping, nobody knows we exist yet */ spin_lock(&_minor_lock); old_md = idr_replace(&_minor_idr, md, minor); @@ -2010,6 +2116,7 @@ static void free_dev(struct mapped_device *md) put_disk(md->disk); blk_cleanup_queue(md->queue); + dm_stats_cleanup(&md->stats); module_put(THIS_MODULE); kfree(md); } @@ -2151,7 +2258,7 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, /* * Wipe any geometry if the size of the table changed. */ - if (size != get_capacity(md->disk)) + if (size != dm_get_size(md)) memset(&md->geometry, 0, sizeof(md->geometry)); __set_size(md, size); @@ -2236,11 +2343,13 @@ void dm_unlock_md_type(struct mapped_device *md) void dm_set_md_type(struct mapped_device *md, unsigned type) { + BUG_ON(!mutex_is_locked(&md->type_lock)); md->type = type; } unsigned dm_get_md_type(struct mapped_device *md) { + BUG_ON(!mutex_is_locked(&md->type_lock)); return md->type; } @@ -2250,6 +2359,17 @@ struct target_type *dm_get_immutable_target_type(struct mapped_device *md) } /* + * The queue_limits are only valid as long as you have a reference + * count on 'md'. + */ +struct queue_limits *dm_get_queue_limits(struct mapped_device *md) +{ + BUG_ON(!atomic_read(&md->holders)); + return &md->queue->limits; +} +EXPORT_SYMBOL_GPL(dm_get_queue_limits); + +/* * Fully initialize a request-based queue (->elevator, ->request_fn, etc). */ static int dm_init_request_based_queue(struct mapped_device *md) @@ -2695,6 +2815,38 @@ out: return r; } +/* + * Internal suspend/resume works like userspace-driven suspend. It waits + * until all bios finish and prevents issuing new bios to the target drivers. + * It may be used only from the kernel. + * + * Internal suspend holds md->suspend_lock, which prevents interaction with + * userspace-driven suspend. + */ + +void dm_internal_suspend(struct mapped_device *md) +{ + mutex_lock(&md->suspend_lock); + if (dm_suspended_md(md)) + return; + + set_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags); + synchronize_srcu(&md->io_barrier); + flush_workqueue(md->wq); + dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE); +} + +void dm_internal_resume(struct mapped_device *md) +{ + if (dm_suspended_md(md)) + goto done; + + dm_queue_flush(md); + +done: + mutex_unlock(&md->suspend_lock); +} + /*----------------------------------------------------------------- * Event notification. *---------------------------------------------------------------*/ @@ -2778,6 +2930,11 @@ int dm_suspended_md(struct mapped_device *md) return test_bit(DMF_SUSPENDED, &md->flags); } +int dm_test_deferred_remove_flag(struct mapped_device *md) +{ + return test_bit(DMF_DEFERRED_REMOVE, &md->flags); +} + int dm_suspended(struct dm_target *ti) { return dm_suspended_md(dm_table_get_md(ti->table)); @@ -2802,18 +2959,18 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u if (type == DM_TYPE_BIO_BASED) { cachep = _io_cache; - pool_size = 16; + pool_size = dm_get_reserved_bio_based_ios(); front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone); } else if (type == DM_TYPE_REQUEST_BASED) { cachep = _rq_tio_cache; - pool_size = MIN_IOS; + pool_size = dm_get_reserved_rq_based_ios(); front_pad = offsetof(struct dm_rq_clone_bio_info, clone); /* per_bio_data_size is not used. See __bind_mempools(). */ WARN_ON(per_bio_data_size != 0); } else goto out; - pools->io_pool = mempool_create_slab_pool(MIN_IOS, cachep); + pools->io_pool = mempool_create_slab_pool(pool_size, cachep); if (!pools->io_pool) goto out; @@ -2864,6 +3021,13 @@ module_exit(dm_exit); module_param(major, uint, 0); MODULE_PARM_DESC(major, "The major number of the device mapper"); + +module_param(reserved_bio_based_ios, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools"); + +module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools"); + MODULE_DESCRIPTION(DM_NAME " driver"); MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 45b97da..c57ba55 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -16,6 +16,8 @@ #include <linux/blkdev.h> #include <linux/hdreg.h> +#include "dm-stats.h" + /* * Suspend feature flags */ @@ -89,10 +91,21 @@ int dm_setup_md_queue(struct mapped_device *md); #define dm_target_is_valid(t) ((t)->table) /* + * To check whether the target type is bio-based or not (request-based). + */ +#define dm_target_bio_based(t) ((t)->type->map != NULL) + +/* * To check whether the target type is request-based or not (bio-based). */ #define dm_target_request_based(t) ((t)->type->map_rq != NULL) +/* + * To check whether the target type is a hybrid (capable of being + * either request-based or bio-based). + */ +#define dm_target_hybrid(t) (dm_target_bio_based(t) && dm_target_request_based(t)) + /*----------------------------------------------------------------- * A registry of target types. *---------------------------------------------------------------*/ @@ -116,6 +129,16 @@ int dm_deleting_md(struct mapped_device *md); int dm_suspended_md(struct mapped_device *md); /* + * Test if the device is scheduled for deferred remove. + */ +int dm_test_deferred_remove_flag(struct mapped_device *md); + +/* + * Try to remove devices marked for deferred removal. + */ +void dm_deferred_remove(void); + +/* * The device-mapper can be driven through one of two interfaces; * ioctl or filesystem, depending which patch you have applied. */ @@ -145,11 +168,18 @@ void dm_stripe_exit(void); void dm_destroy(struct mapped_device *md); void dm_destroy_immediate(struct mapped_device *md); int dm_open_count(struct mapped_device *md); -int dm_lock_for_deletion(struct mapped_device *md); +int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred); +int dm_cancel_deferred_remove(struct mapped_device *md); +int dm_request_based(struct mapped_device *md); +sector_t dm_get_size(struct mapped_device *md); +struct dm_stats *dm_get_stats(struct mapped_device *md); int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, unsigned cookie); +void dm_internal_suspend(struct mapped_device *md); +void dm_internal_resume(struct mapped_device *md); + int dm_io_init(void); void dm_io_exit(void); @@ -162,4 +192,15 @@ void dm_kcopyd_exit(void); struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, unsigned per_bio_data_size); void dm_free_md_mempools(struct dm_md_mempools *pools); +/* + * Helpers that are used by DM core + */ +unsigned dm_get_reserved_bio_based_ios(void); +unsigned dm_get_reserved_rq_based_ios(void); + +static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen) +{ + return !maxlen || strlen(result) + 1 >= maxlen; +} + #endif diff --git a/drivers/md/md.c b/drivers/md/md.c index 9f13e13..8766eab 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -183,46 +183,6 @@ struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask, } EXPORT_SYMBOL_GPL(bio_clone_mddev); -void md_trim_bio(struct bio *bio, int offset, int size) -{ - /* 'bio' is a cloned bio which we need to trim to match - * the given offset and size. - * This requires adjusting bi_sector, bi_size, and bi_io_vec - */ - int i; - struct bio_vec *bvec; - int sofar = 0; - - size <<= 9; - if (offset == 0 && size == bio->bi_size) - return; - - clear_bit(BIO_SEG_VALID, &bio->bi_flags); - - bio_advance(bio, offset << 9); - - bio->bi_size = size; - - /* avoid any complications with bi_idx being non-zero*/ - if (bio->bi_idx) { - memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx, - (bio->bi_vcnt - bio->bi_idx) * sizeof(struct bio_vec)); - bio->bi_vcnt -= bio->bi_idx; - bio->bi_idx = 0; - } - /* Make sure vcnt and last bv are not too big */ - bio_for_each_segment(bvec, bio, i) { - if (sofar + bvec->bv_len > size) - bvec->bv_len = size - sofar; - if (bvec->bv_len == 0) { - bio->bi_vcnt = i; - break; - } - sofar += bvec->bv_len; - } -} -EXPORT_SYMBOL_GPL(md_trim_bio); - /* * We have a system wide 'event count' that is incremented * on any 'interesting' event, and readers of /proc/mdstat @@ -1180,7 +1140,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev) mddev->bitmap_info.offset = mddev->bitmap_info.default_offset; mddev->bitmap_info.space = - mddev->bitmap_info.space; + mddev->bitmap_info.default_space; } } else if (mddev->pers == NULL) { @@ -3429,7 +3389,7 @@ safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len) mddev->safemode_delay = (msec*HZ)/1000; if (mddev->safemode_delay == 0) mddev->safemode_delay = 1; - if (mddev->safemode_delay < old_delay) + if (mddev->safemode_delay < old_delay || old_delay == 0) md_safemode_timeout((unsigned long)mddev); } return len; @@ -3555,7 +3515,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len) printk(KERN_WARNING "md: cannot register extra attributes for %s\n", mdname(mddev)); - mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, NULL, "sync_action"); + mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action"); } if (mddev->pers->sync_request != NULL && pers->sync_request == NULL) { @@ -5144,7 +5104,7 @@ int md_run(struct mddev *mddev) set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - if (mddev->flags) + if (mddev->flags & MD_UPDATE_SB_FLAGS) md_update_sb(mddev, 0); md_new_event(mddev); @@ -5289,7 +5249,7 @@ static void __md_stop_writes(struct mddev *mddev) md_super_wait(mddev); if (mddev->ro == 0 && - (!mddev->in_sync || mddev->flags)) { + (!mddev->in_sync || (mddev->flags & MD_UPDATE_SB_FLAGS))) { /* mark array as shutdown cleanly */ mddev->in_sync = 1; md_update_sb(mddev, 1); @@ -5337,8 +5297,14 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) err = -EBUSY; goto out; } - if (bdev) - sync_blockdev(bdev); + if (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags)) { + /* Someone opened the device since we flushed it + * so page cache could be dirty and it is too late + * to flush. So abort + */ + mutex_unlock(&mddev->open_mutex); + return -EBUSY; + } if (mddev->pers) { __md_stop_writes(mddev); @@ -5373,14 +5339,14 @@ static int do_md_stop(struct mddev * mddev, int mode, mutex_unlock(&mddev->open_mutex); return -EBUSY; } - if (bdev) - /* It is possible IO was issued on some other - * open file which was closed before we took ->open_mutex. - * As that was not the last close __blkdev_put will not - * have called sync_blockdev, so we must. + if (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags)) { + /* Someone opened the device since we flushed it + * so page cache could be dirty and it is too late + * to flush. So abort */ - sync_blockdev(bdev); - + mutex_unlock(&mddev->open_mutex); + return -EBUSY; + } if (mddev->pers) { if (mddev->ro) set_disk_ro(disk, 0); @@ -5628,10 +5594,7 @@ static int get_bitmap_file(struct mddev * mddev, void __user * arg) char *ptr, *buf = NULL; int err = -ENOMEM; - if (md_allow_write(mddev)) - file = kmalloc(sizeof(*file), GFP_NOIO); - else - file = kmalloc(sizeof(*file), GFP_KERNEL); + file = kmalloc(sizeof(*file), GFP_NOIO); if (!file) goto out; @@ -6420,6 +6383,20 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, !test_bit(MD_RECOVERY_NEEDED, &mddev->flags), msecs_to_jiffies(5000)); + if (cmd == STOP_ARRAY || cmd == STOP_ARRAY_RO) { + /* Need to flush page cache, and ensure no-one else opens + * and writes + */ + mutex_lock(&mddev->open_mutex); + if (atomic_read(&mddev->openers) > 1) { + mutex_unlock(&mddev->open_mutex); + err = -EBUSY; + goto abort; + } + set_bit(MD_STILL_CLOSED, &mddev->flags); + mutex_unlock(&mddev->open_mutex); + sync_blockdev(bdev); + } err = mddev_lock(mddev); if (err) { printk(KERN_INFO @@ -6673,6 +6650,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) err = 0; atomic_inc(&mddev->openers); + clear_bit(MD_STILL_CLOSED, &mddev->flags); mutex_unlock(&mddev->open_mutex); check_disk_change(bdev); @@ -7817,7 +7795,7 @@ void md_check_recovery(struct mddev *mddev) sysfs_notify_dirent_safe(mddev->sysfs_state); } - if (mddev->flags) + if (mddev->flags & MD_UPDATE_SB_FLAGS) md_update_sb(mddev, 0); if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && @@ -8093,6 +8071,7 @@ static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors, u64 *p; int lo, hi; int rv = 1; + unsigned long flags; if (bb->shift < 0) /* badblocks are disabled */ @@ -8107,7 +8086,7 @@ static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors, sectors = next - s; } - write_seqlock_irq(&bb->lock); + write_seqlock_irqsave(&bb->lock, flags); p = bb->page; lo = 0; @@ -8223,7 +8202,7 @@ static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors, bb->changed = 1; if (!acknowledged) bb->unacked_exist = 1; - write_sequnlock_irq(&bb->lock); + write_sequnlock_irqrestore(&bb->lock, flags); return rv; } diff --git a/drivers/md/md.h b/drivers/md/md.h index 20f02c0..2f5cc8a 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -204,12 +204,16 @@ struct mddev { struct md_personality *pers; dev_t unit; int md_minor; - struct list_head disks; + struct list_head disks; unsigned long flags; #define MD_CHANGE_DEVS 0 /* Some device status has changed */ #define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */ #define MD_CHANGE_PENDING 2 /* switch from 'clean' to 'active' in progress */ +#define MD_UPDATE_SB_FLAGS (1 | 2 | 4) /* If these are set, md_update_sb needed */ #define MD_ARRAY_FIRST_USE 3 /* First use of array, needs initialization */ +#define MD_STILL_CLOSED 4 /* If set, then array has not been opened since + * md_ioctl checked on it. + */ int suspended; atomic_t active_io; @@ -218,7 +222,7 @@ struct mddev { * are happening, so run/ * takeover/stop are not safe */ - int ready; /* See when safe to pass + int ready; /* See when safe to pass * IO requests down */ struct gendisk *gendisk; @@ -497,7 +501,7 @@ extern struct attribute_group md_bitmap_group; static inline struct sysfs_dirent *sysfs_get_dirent_safe(struct sysfs_dirent *sd, char *name) { if (sd) - return sysfs_get_dirent(sd, NULL, name); + return sysfs_get_dirent(sd, name); return sd; } static inline void sysfs_notify_dirent_safe(struct sysfs_dirent *sd) @@ -613,7 +617,6 @@ extern struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask, struct mddev *mddev); extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, struct mddev *mddev); -extern void md_trim_bio(struct bio *bio, int offset, int size); extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule); static inline int mddev_check_plugged(struct mddev *mddev) diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c index 172147e..af96e24 100644 --- a/drivers/md/persistent-data/dm-array.c +++ b/drivers/md/persistent-data/dm-array.c @@ -509,15 +509,18 @@ static int grow_add_tail_block(struct resize *resize) static int grow_needs_more_blocks(struct resize *resize) { int r; + unsigned old_nr_blocks = resize->old_nr_full_blocks; if (resize->old_nr_entries_in_last_block > 0) { + old_nr_blocks++; + r = grow_extend_tail_block(resize, resize->max_entries); if (r) return r; } r = insert_full_ablocks(resize->info, resize->size_of_block, - resize->old_nr_full_blocks, + old_nr_blocks, resize->new_nr_full_blocks, resize->max_entries, resize->value, &resize->root); diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index 81b5138..a7e8bf2 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -615,6 +615,11 @@ int dm_bm_flush_and_unlock(struct dm_block_manager *bm, } EXPORT_SYMBOL_GPL(dm_bm_flush_and_unlock); +void dm_bm_prefetch(struct dm_block_manager *bm, dm_block_t b) +{ + dm_bufio_prefetch(bm->bufio, b, 1); +} + void dm_bm_set_read_only(struct dm_block_manager *bm) { bm->read_only = true; diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h index be5bff6..9a82083 100644 --- a/drivers/md/persistent-data/dm-block-manager.h +++ b/drivers/md/persistent-data/dm-block-manager.h @@ -108,6 +108,11 @@ int dm_bm_unlock(struct dm_block *b); int dm_bm_flush_and_unlock(struct dm_block_manager *bm, struct dm_block *superblock); + /* + * Request data be prefetched into the cache. + */ +void dm_bm_prefetch(struct dm_block_manager *bm, dm_block_t b); + /* * Switches the bm to a read only mode. Once read-only mode * has been entered the following functions will return -EPERM. diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 3586542..468e371 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -161,6 +161,7 @@ struct frame { }; struct del_stack { + struct dm_btree_info *info; struct dm_transaction_manager *tm; int top; struct frame spine[MAX_SPINE_DEPTH]; @@ -183,6 +184,20 @@ static int unprocessed_frames(struct del_stack *s) return s->top >= 0; } +static void prefetch_children(struct del_stack *s, struct frame *f) +{ + unsigned i; + struct dm_block_manager *bm = dm_tm_get_bm(s->tm); + + for (i = 0; i < f->nr_children; i++) + dm_bm_prefetch(bm, value64(f->n, i)); +} + +static bool is_internal_level(struct dm_btree_info *info, struct frame *f) +{ + return f->level < (info->levels - 1); +} + static int push_frame(struct del_stack *s, dm_block_t b, unsigned level) { int r; @@ -205,6 +220,7 @@ static int push_frame(struct del_stack *s, dm_block_t b, unsigned level) dm_tm_dec(s->tm, b); else { + uint32_t flags; struct frame *f = s->spine + ++s->top; r = dm_tm_read_lock(s->tm, b, &btree_node_validator, &f->b); @@ -217,6 +233,10 @@ static int push_frame(struct del_stack *s, dm_block_t b, unsigned level) f->level = level; f->nr_children = le32_to_cpu(f->n->header.nr_entries); f->current_child = 0; + + flags = le32_to_cpu(f->n->header.flags); + if (flags & INTERNAL_NODE || is_internal_level(s->info, f)) + prefetch_children(s, f); } return 0; @@ -230,11 +250,6 @@ static void pop_frame(struct del_stack *s) dm_tm_unlock(s->tm, f->b); } -static bool is_internal_level(struct dm_btree_info *info, struct frame *f) -{ - return f->level < (info->levels - 1); -} - int dm_btree_del(struct dm_btree_info *info, dm_block_t root) { int r; @@ -243,6 +258,7 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root) s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) return -ENOMEM; + s->info = info; s->tm = info->tm; s->top = -1; @@ -287,7 +303,7 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root) info->value_type.dec(info->value_type.context, value_ptr(f->n, i)); } - f->current_child = f->nr_children; + pop_frame(s); } } diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c index 3e7a88d..6058569 100644 --- a/drivers/md/persistent-data/dm-space-map-common.c +++ b/drivers/md/persistent-data/dm-space-map-common.c @@ -292,16 +292,11 @@ int sm_ll_lookup_bitmap(struct ll_disk *ll, dm_block_t b, uint32_t *result) return dm_tm_unlock(ll->tm, blk); } -int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result) +static int sm_ll_lookup_big_ref_count(struct ll_disk *ll, dm_block_t b, + uint32_t *result) { __le32 le_rc; - int r = sm_ll_lookup_bitmap(ll, b, result); - - if (r) - return r; - - if (*result != 3) - return r; + int r; r = dm_btree_lookup(&ll->ref_count_info, ll->ref_count_root, &b, &le_rc); if (r < 0) @@ -312,6 +307,19 @@ int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result) return r; } +int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result) +{ + int r = sm_ll_lookup_bitmap(ll, b, result); + + if (r) + return r; + + if (*result != 3) + return r; + + return sm_ll_lookup_big_ref_count(ll, b, result); +} + int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin, dm_block_t end, dm_block_t *result) { @@ -372,11 +380,12 @@ int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin, return -ENOSPC; } -int sm_ll_insert(struct ll_disk *ll, dm_block_t b, - uint32_t ref_count, enum allocation_event *ev) +static int sm_ll_mutate(struct ll_disk *ll, dm_block_t b, + uint32_t (*mutator)(void *context, uint32_t old), + void *context, enum allocation_event *ev) { int r; - uint32_t bit, old; + uint32_t bit, old, ref_count; struct dm_block *nb; dm_block_t index = b; struct disk_index_entry ie_disk; @@ -399,6 +408,14 @@ int sm_ll_insert(struct ll_disk *ll, dm_block_t b, bm_le = dm_bitmap_data(nb); old = sm_lookup_bitmap(bm_le, bit); + if (old > 2) { + r = sm_ll_lookup_big_ref_count(ll, b, &old); + if (r < 0) + return r; + } + + ref_count = mutator(context, old); + if (ref_count <= 2) { sm_set_bitmap(bm_le, bit, ref_count); @@ -448,31 +465,35 @@ int sm_ll_insert(struct ll_disk *ll, dm_block_t b, return ll->save_ie(ll, index, &ie_disk); } -int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev) +static uint32_t set_ref_count(void *context, uint32_t old) { - int r; - uint32_t rc; - - r = sm_ll_lookup(ll, b, &rc); - if (r) - return r; + return *((uint32_t *) context); +} - return sm_ll_insert(ll, b, rc + 1, ev); +int sm_ll_insert(struct ll_disk *ll, dm_block_t b, + uint32_t ref_count, enum allocation_event *ev) +{ + return sm_ll_mutate(ll, b, set_ref_count, &ref_count, ev); } -int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev) +static uint32_t inc_ref_count(void *context, uint32_t old) { - int r; - uint32_t rc; + return old + 1; +} - r = sm_ll_lookup(ll, b, &rc); - if (r) - return r; +int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev) +{ + return sm_ll_mutate(ll, b, inc_ref_count, NULL, ev); +} - if (!rc) - return -EINVAL; +static uint32_t dec_ref_count(void *context, uint32_t old) +{ + return old - 1; +} - return sm_ll_insert(ll, b, rc - 1, ev); +int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev) +{ + return sm_ll_mutate(ll, b, dec_ref_count, NULL, ev); } int sm_ll_commit(struct ll_disk *ll) diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c index e735a6d..cfbf961 100644 --- a/drivers/md/persistent-data/dm-space-map-disk.c +++ b/drivers/md/persistent-data/dm-space-map-disk.c @@ -140,26 +140,10 @@ static int sm_disk_inc_block(struct dm_space_map *sm, dm_block_t b) static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b) { - int r; - uint32_t old_count; enum allocation_event ev; struct sm_disk *smd = container_of(sm, struct sm_disk, sm); - r = sm_ll_dec(&smd->ll, b, &ev); - if (!r && (ev == SM_FREE)) { - /* - * It's only free if it's also free in the last - * transaction. - */ - r = sm_ll_lookup(&smd->old_ll, b, &old_count); - if (r) - return r; - - if (!old_count) - smd->nr_allocated_this_transaction--; - } - - return r; + return sm_ll_dec(&smd->ll, b, &ev); } static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index d60412c..af6681b1 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1097,8 +1097,8 @@ read_again: r1_bio->read_disk = rdisk; read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); - md_trim_bio(read_bio, r1_bio->sector - bio->bi_sector, - max_sectors); + bio_trim(read_bio, r1_bio->sector - bio->bi_sector, + max_sectors); r1_bio->bios[rdisk] = read_bio; @@ -1266,7 +1266,7 @@ read_again: continue; mbio = bio_clone_mddev(bio, GFP_NOIO, mddev); - md_trim_bio(mbio, r1_bio->sector - bio->bi_sector, max_sectors); + bio_trim(mbio, r1_bio->sector - bio->bi_sector, max_sectors); if (first_clone) { /* do behind I/O ? @@ -1479,6 +1479,7 @@ static int raid1_spare_active(struct mddev *mddev) } } if (rdev + && rdev->recovery_offset == MaxSector && !test_bit(Faulty, &rdev->flags) && !test_and_set_bit(In_sync, &rdev->flags)) { count++; @@ -2125,7 +2126,7 @@ static int narrow_write_error(struct r1bio *r1_bio, int i) wbio->bi_sector = r1_bio->sector; wbio->bi_size = r1_bio->sectors << 9; - md_trim_bio(wbio, sector - r1_bio->sector, sectors); + bio_trim(wbio, sector - r1_bio->sector, sectors); wbio->bi_sector += rdev->data_offset; wbio->bi_bdev = rdev->bdev; if (submit_bio_wait(WRITE, wbio) == 0) @@ -2240,7 +2241,7 @@ read_more: } r1_bio->read_disk = disk; bio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev); - md_trim_bio(bio, r1_bio->sector - bio->bi_sector, max_sectors); + bio_trim(bio, r1_bio->sector - bio->bi_sector, max_sectors); r1_bio->bios[r1_bio->read_disk] = bio; rdev = conf->mirrors[disk].rdev; printk_ratelimited(KERN_ERR diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index df7b0a0..7c3508a 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1302,8 +1302,8 @@ read_again: slot = r10_bio->read_slot; read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); - md_trim_bio(read_bio, r10_bio->sector - bio->bi_sector, - max_sectors); + bio_trim(read_bio, r10_bio->sector - bio->bi_sector, + max_sectors); r10_bio->devs[slot].bio = read_bio; r10_bio->devs[slot].rdev = rdev; @@ -1510,8 +1510,8 @@ retry_write: if (r10_bio->devs[i].bio) { struct md_rdev *rdev = conf->mirrors[d].rdev; mbio = bio_clone_mddev(bio, GFP_NOIO, mddev); - md_trim_bio(mbio, r10_bio->sector - bio->bi_sector, - max_sectors); + bio_trim(mbio, r10_bio->sector - bio->bi_sector, + max_sectors); r10_bio->devs[i].bio = mbio; mbio->bi_sector = (r10_bio->devs[i].addr+ @@ -1553,8 +1553,8 @@ retry_write: rdev = conf->mirrors[d].rdev; } mbio = bio_clone_mddev(bio, GFP_NOIO, mddev); - md_trim_bio(mbio, r10_bio->sector - bio->bi_sector, - max_sectors); + bio_trim(mbio, r10_bio->sector - bio->bi_sector, + max_sectors); r10_bio->devs[i].repl_bio = mbio; mbio->bi_sector = (r10_bio->devs[i].addr + @@ -1782,6 +1782,7 @@ static int raid10_spare_active(struct mddev *mddev) } sysfs_notify_dirent_safe(tmp->replacement->sysfs_state); } else if (tmp->rdev + && tmp->rdev->recovery_offset == MaxSector && !test_bit(Faulty, &tmp->rdev->flags) && !test_and_set_bit(In_sync, &tmp->rdev->flags)) { count++; @@ -2613,7 +2614,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i) sectors = sect_to_write; /* Write at 'sector' for 'sectors' */ wbio = bio_clone_mddev(bio, GFP_NOIO, mddev); - md_trim_bio(wbio, sector - bio->bi_sector, sectors); + bio_trim(wbio, sector - bio->bi_sector, sectors); wbio->bi_sector = (r10_bio->devs[i].addr+ choose_data_offset(r10_bio, rdev) + (sector - r10_bio->sector)); @@ -2686,9 +2687,7 @@ read_more: (unsigned long long)r10_bio->sector); bio = bio_clone_mddev(r10_bio->master_bio, GFP_NOIO, mddev); - md_trim_bio(bio, - r10_bio->sector - bio->bi_sector, - max_sectors); + bio_trim(bio, r10_bio->sector - bio->bi_sector, max_sectors); r10_bio->devs[slot].bio = bio; r10_bio->devs[slot].rdev = rdev; bio->bi_sector = r10_bio->devs[slot].addr diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 78ea443..7f0e17a 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -53,6 +53,7 @@ #include <linux/cpu.h> #include <linux/slab.h> #include <linux/ratelimit.h> +#include <linux/nodemask.h> #include <trace/events/block.h> #include "md.h" @@ -60,6 +61,10 @@ #include "raid0.h" #include "bitmap.h" +#define cpu_to_group(cpu) cpu_to_node(cpu) +#define ANY_GROUP NUMA_NO_NODE + +static struct workqueue_struct *raid5_wq; /* * Stripe cache */ @@ -72,6 +77,7 @@ #define BYPASS_THRESHOLD 1 #define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head)) #define HASH_MASK (NR_HASH - 1) +#define MAX_STRIPE_BATCH 8 static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect) { @@ -200,6 +206,49 @@ static int stripe_operations_active(struct stripe_head *sh) test_bit(STRIPE_COMPUTE_RUN, &sh->state); } +static void raid5_wakeup_stripe_thread(struct stripe_head *sh) +{ + struct r5conf *conf = sh->raid_conf; + struct r5worker_group *group; + int thread_cnt; + int i, cpu = sh->cpu; + + if (!cpu_online(cpu)) { + cpu = cpumask_any(cpu_online_mask); + sh->cpu = cpu; + } + + if (list_empty(&sh->lru)) { + struct r5worker_group *group; + group = conf->worker_groups + cpu_to_group(cpu); + list_add_tail(&sh->lru, &group->handle_list); + group->stripes_cnt++; + sh->group = group; + } + + if (conf->worker_cnt_per_group == 0) { + md_wakeup_thread(conf->mddev->thread); + return; + } + + group = conf->worker_groups + cpu_to_group(sh->cpu); + + group->workers[0].working = true; + /* at least one worker should run to avoid race */ + queue_work_on(sh->cpu, raid5_wq, &group->workers[0].work); + + thread_cnt = group->stripes_cnt / MAX_STRIPE_BATCH - 1; + /* wakeup more workers */ + for (i = 1; i < conf->worker_cnt_per_group && thread_cnt > 0; i++) { + if (group->workers[i].working == false) { + group->workers[i].working = true; + queue_work_on(sh->cpu, raid5_wq, + &group->workers[i].work); + thread_cnt--; + } + } +} + static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh) { BUG_ON(!list_empty(&sh->lru)); @@ -214,7 +263,12 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh) else { clear_bit(STRIPE_DELAYED, &sh->state); clear_bit(STRIPE_BIT_DELAY, &sh->state); - list_add_tail(&sh->lru, &conf->handle_list); + if (conf->worker_cnt_per_group == 0) { + list_add_tail(&sh->lru, &conf->handle_list); + } else { + raid5_wakeup_stripe_thread(sh); + return; + } } md_wakeup_thread(conf->mddev->thread); } else { @@ -239,12 +293,48 @@ static void __release_stripe(struct r5conf *conf, struct stripe_head *sh) do_release_stripe(conf, sh); } +/* should hold conf->device_lock already */ +static int release_stripe_list(struct r5conf *conf) +{ + struct stripe_head *sh; + int count = 0; + struct llist_node *head; + + head = llist_del_all(&conf->released_stripes); + head = llist_reverse_order(head); + while (head) { + sh = llist_entry(head, struct stripe_head, release_list); + head = llist_next(head); + /* sh could be readded after STRIPE_ON_RELEASE_LIST is cleard */ + smp_mb(); + clear_bit(STRIPE_ON_RELEASE_LIST, &sh->state); + /* + * Don't worry the bit is set here, because if the bit is set + * again, the count is always > 1. This is true for + * STRIPE_ON_UNPLUG_LIST bit too. + */ + __release_stripe(conf, sh); + count++; + } + + return count; +} + static void release_stripe(struct stripe_head *sh) { struct r5conf *conf = sh->raid_conf; unsigned long flags; + bool wakeup; + if (test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state)) + goto slow_path; + wakeup = llist_add(&sh->release_list, &conf->released_stripes); + if (wakeup) + md_wakeup_thread(conf->mddev->thread); + return; +slow_path: local_irq_save(flags); + /* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */ if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) { do_release_stripe(conf, sh); spin_unlock(&conf->device_lock); @@ -359,6 +449,7 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int previous) raid5_build_block(sh, i, previous); } insert_hash(conf, sh); + sh->cpu = smp_processor_id(); } static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, @@ -491,7 +582,8 @@ get_active_stripe(struct r5conf *conf, sector_t sector, if (atomic_read(&sh->count)) { BUG_ON(!list_empty(&sh->lru) && !test_bit(STRIPE_EXPANDING, &sh->state) - && !test_bit(STRIPE_ON_UNPLUG_LIST, &sh->state)); + && !test_bit(STRIPE_ON_UNPLUG_LIST, &sh->state) + && !test_bit(STRIPE_ON_RELEASE_LIST, &sh->state)); } else { if (!test_bit(STRIPE_HANDLE, &sh->state)) atomic_inc(&conf->active_stripes); @@ -499,6 +591,10 @@ get_active_stripe(struct r5conf *conf, sector_t sector, !test_bit(STRIPE_EXPANDING, &sh->state)) BUG(); list_del_init(&sh->lru); + if (sh->group) { + sh->group->stripes_cnt--; + sh->group = NULL; + } } } } while (sh == NULL); @@ -668,6 +764,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) bi->bi_io_vec[0].bv_len = STRIPE_SIZE; bi->bi_io_vec[0].bv_offset = 0; bi->bi_size = STRIPE_SIZE; + /* + * If this is discard request, set bi_vcnt 0. We don't + * want to confuse SCSI because SCSI will replace payload + */ + if (rw & REQ_DISCARD) + bi->bi_vcnt = 0; if (rrdev) set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags); @@ -706,6 +808,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) rbi->bi_io_vec[0].bv_len = STRIPE_SIZE; rbi->bi_io_vec[0].bv_offset = 0; rbi->bi_size = STRIPE_SIZE; + /* + * If this is discard request, set bi_vcnt 0. We don't + * want to confuse SCSI because SCSI will replace payload + */ + if (rw & REQ_DISCARD) + rbi->bi_vcnt = 0; if (conf->mddev->gendisk) trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev), rbi, disk_devt(conf->mddev->gendisk), @@ -2800,6 +2908,14 @@ static void handle_stripe_clean_event(struct r5conf *conf, } /* now that discard is done we can proceed with any sync */ clear_bit(STRIPE_DISCARD, &sh->state); + /* + * SCSI discard will change some bio fields and the stripe has + * no updated data, so remove it from hash list and the stripe + * will be reinitialized + */ + spin_lock_irq(&conf->device_lock); + remove_hash(sh); + spin_unlock_irq(&conf->device_lock); if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) set_bit(STRIPE_HANDLE, &sh->state); @@ -3779,6 +3895,7 @@ static void raid5_activate_delayed(struct r5conf *conf) if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); list_add_tail(&sh->lru, &conf->hold_list); + raid5_wakeup_stripe_thread(sh); } } } @@ -4058,18 +4175,35 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) * head of the hold_list has changed, i.e. the head was promoted to the * handle_list. */ -static struct stripe_head *__get_priority_stripe(struct r5conf *conf) +static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group) { - struct stripe_head *sh; + struct stripe_head *sh = NULL, *tmp; + struct list_head *handle_list = NULL; + struct r5worker_group *wg = NULL; + + if (conf->worker_cnt_per_group == 0) { + handle_list = &conf->handle_list; + } else if (group != ANY_GROUP) { + handle_list = &conf->worker_groups[group].handle_list; + wg = &conf->worker_groups[group]; + } else { + int i; + for (i = 0; i < conf->group_cnt; i++) { + handle_list = &conf->worker_groups[i].handle_list; + wg = &conf->worker_groups[i]; + if (!list_empty(handle_list)) + break; + } + } pr_debug("%s: handle: %s hold: %s full_writes: %d bypass_count: %d\n", __func__, - list_empty(&conf->handle_list) ? "empty" : "busy", + list_empty(handle_list) ? "empty" : "busy", list_empty(&conf->hold_list) ? "empty" : "busy", atomic_read(&conf->pending_full_writes), conf->bypass_count); - if (!list_empty(&conf->handle_list)) { - sh = list_entry(conf->handle_list.next, typeof(*sh), lru); + if (!list_empty(handle_list)) { + sh = list_entry(handle_list->next, typeof(*sh), lru); if (list_empty(&conf->hold_list)) conf->bypass_count = 0; @@ -4087,14 +4221,32 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf) ((conf->bypass_threshold && conf->bypass_count > conf->bypass_threshold) || atomic_read(&conf->pending_full_writes) == 0)) { - sh = list_entry(conf->hold_list.next, - typeof(*sh), lru); - conf->bypass_count -= conf->bypass_threshold; - if (conf->bypass_count < 0) - conf->bypass_count = 0; - } else + + list_for_each_entry(tmp, &conf->hold_list, lru) { + if (conf->worker_cnt_per_group == 0 || + group == ANY_GROUP || + !cpu_online(tmp->cpu) || + cpu_to_group(tmp->cpu) == group) { + sh = tmp; + break; + } + } + + if (sh) { + conf->bypass_count -= conf->bypass_threshold; + if (conf->bypass_count < 0) + conf->bypass_count = 0; + } + wg = NULL; + } + + if (!sh) return NULL; + if (wg) { + wg->stripes_cnt--; + sh->group = NULL; + } list_del_init(&sh->lru); atomic_inc(&sh->count); BUG_ON(atomic_read(&sh->count) != 1); @@ -4127,6 +4279,10 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule) */ smp_mb__before_clear_bit(); clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state); + /* + * STRIPE_ON_RELEASE_LIST could be set here. In that + * case, the count is always > 1 here + */ __release_stripe(conf, sh); cnt++; } @@ -4286,8 +4442,10 @@ static void make_request(struct mddev *mddev, struct bio * bi) for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) { DEFINE_WAIT(w); int previous; + int seq; retry: + seq = read_seqcount_begin(&conf->gen_lock); previous = 0; prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); if (unlikely(conf->reshape_progress != MaxSector)) { @@ -4320,7 +4478,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) previous, &dd_idx, NULL); pr_debug("raid456: make_request, sector %llu logical %llu\n", - (unsigned long long)new_sector, + (unsigned long long)new_sector, (unsigned long long)logical_sector); sh = get_active_stripe(conf, new_sector, previous, @@ -4349,6 +4507,13 @@ static void make_request(struct mddev *mddev, struct bio * bi) goto retry; } } + if (read_seqcount_retry(&conf->gen_lock, seq)) { + /* Might have got the wrong stripe_head + * by accident + */ + release_stripe(sh); + goto retry; + } if (rw == WRITE && logical_sector >= mddev->suspend_lo && @@ -4788,14 +4953,14 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio) return handled; } -#define MAX_STRIPE_BATCH 8 -static int handle_active_stripes(struct r5conf *conf) +static int handle_active_stripes(struct r5conf *conf, int group, + struct r5worker *worker) { struct stripe_head *batch[MAX_STRIPE_BATCH], *sh; int i, batch_size = 0; while (batch_size < MAX_STRIPE_BATCH && - (sh = __get_priority_stripe(conf)) != NULL) + (sh = __get_priority_stripe(conf, group)) != NULL) batch[batch_size++] = sh; if (batch_size == 0) @@ -4813,6 +4978,39 @@ static int handle_active_stripes(struct r5conf *conf) return batch_size; } +static void raid5_do_work(struct work_struct *work) +{ + struct r5worker *worker = container_of(work, struct r5worker, work); + struct r5worker_group *group = worker->group; + struct r5conf *conf = group->conf; + int group_id = group - conf->worker_groups; + int handled; + struct blk_plug plug; + + pr_debug("+++ raid5worker active\n"); + + blk_start_plug(&plug); + handled = 0; + spin_lock_irq(&conf->device_lock); + while (1) { + int batch_size, released; + + released = release_stripe_list(conf); + + batch_size = handle_active_stripes(conf, group_id, worker); + worker->working = false; + if (!batch_size && !released) + break; + handled += batch_size; + } + pr_debug("%d stripes handled\n", handled); + + spin_unlock_irq(&conf->device_lock); + blk_finish_plug(&plug); + + pr_debug("--- raid5worker inactive\n"); +} + /* * This is our raid5 kernel thread. * @@ -4836,7 +5034,9 @@ static void raid5d(struct md_thread *thread) spin_lock_irq(&conf->device_lock); while (1) { struct bio *bio; - int batch_size; + int batch_size, released; + + released = release_stripe_list(conf); if ( !list_empty(&conf->bitmap_list)) { @@ -4860,8 +5060,8 @@ static void raid5d(struct md_thread *thread) handled++; } - batch_size = handle_active_stripes(conf); - if (!batch_size) + batch_size = handle_active_stripes(conf, ANY_GROUP, NULL); + if (!batch_size && !released) break; handled += batch_size; @@ -4989,10 +5189,70 @@ stripe_cache_active_show(struct mddev *mddev, char *page) static struct md_sysfs_entry raid5_stripecache_active = __ATTR_RO(stripe_cache_active); +static ssize_t +raid5_show_group_thread_cnt(struct mddev *mddev, char *page) +{ + struct r5conf *conf = mddev->private; + if (conf) + return sprintf(page, "%d\n", conf->worker_cnt_per_group); + else + return 0; +} + +static int alloc_thread_groups(struct r5conf *conf, int cnt); +static ssize_t +raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) +{ + struct r5conf *conf = mddev->private; + unsigned long new; + int err; + struct r5worker_group *old_groups; + int old_group_cnt; + + if (len >= PAGE_SIZE) + return -EINVAL; + if (!conf) + return -ENODEV; + + if (kstrtoul(page, 10, &new)) + return -EINVAL; + + if (new == conf->worker_cnt_per_group) + return len; + + mddev_suspend(mddev); + + old_groups = conf->worker_groups; + old_group_cnt = conf->worker_cnt_per_group; + + conf->worker_groups = NULL; + err = alloc_thread_groups(conf, new); + if (err) { + conf->worker_groups = old_groups; + conf->worker_cnt_per_group = old_group_cnt; + } else { + if (old_groups) + kfree(old_groups[0].workers); + kfree(old_groups); + } + + mddev_resume(mddev); + + if (err) + return err; + return len; +} + +static struct md_sysfs_entry +raid5_group_thread_cnt = __ATTR(group_thread_cnt, S_IRUGO | S_IWUSR, + raid5_show_group_thread_cnt, + raid5_store_group_thread_cnt); + static struct attribute *raid5_attrs[] = { &raid5_stripecache_size.attr, &raid5_stripecache_active.attr, &raid5_preread_bypass_threshold.attr, + &raid5_group_thread_cnt.attr, NULL, }; static struct attribute_group raid5_attrs_group = { @@ -5000,6 +5260,54 @@ static struct attribute_group raid5_attrs_group = { .attrs = raid5_attrs, }; +static int alloc_thread_groups(struct r5conf *conf, int cnt) +{ + int i, j; + ssize_t size; + struct r5worker *workers; + + conf->worker_cnt_per_group = cnt; + if (cnt == 0) { + conf->worker_groups = NULL; + return 0; + } + conf->group_cnt = num_possible_nodes(); + size = sizeof(struct r5worker) * cnt; + workers = kzalloc(size * conf->group_cnt, GFP_NOIO); + conf->worker_groups = kzalloc(sizeof(struct r5worker_group) * + conf->group_cnt, GFP_NOIO); + if (!conf->worker_groups || !workers) { + kfree(workers); + kfree(conf->worker_groups); + conf->worker_groups = NULL; + return -ENOMEM; + } + + for (i = 0; i < conf->group_cnt; i++) { + struct r5worker_group *group; + + group = &conf->worker_groups[i]; + INIT_LIST_HEAD(&group->handle_list); + group->conf = conf; + group->workers = workers + i * cnt; + + for (j = 0; j < cnt; j++) { + group->workers[j].group = group; + INIT_WORK(&group->workers[j].work, raid5_do_work); + } + } + + return 0; +} + +static void free_thread_groups(struct r5conf *conf) +{ + if (conf->worker_groups) + kfree(conf->worker_groups[0].workers); + kfree(conf->worker_groups); + conf->worker_groups = NULL; +} + static sector_t raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks) { @@ -5040,6 +5348,7 @@ static void raid5_free_percpu(struct r5conf *conf) static void free_conf(struct r5conf *conf) { + free_thread_groups(conf); shrink_stripes(conf); raid5_free_percpu(conf); kfree(conf->disks); @@ -5168,7 +5477,11 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf = kzalloc(sizeof(struct r5conf), GFP_KERNEL); if (conf == NULL) goto abort; + /* Don't enable multi-threading by default*/ + if (alloc_thread_groups(conf, 0)) + goto abort; spin_lock_init(&conf->device_lock); + seqcount_init(&conf->gen_lock); init_waitqueue_head(&conf->wait_for_stripe); init_waitqueue_head(&conf->wait_for_overlap); INIT_LIST_HEAD(&conf->handle_list); @@ -5176,6 +5489,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) INIT_LIST_HEAD(&conf->delayed_list); INIT_LIST_HEAD(&conf->bitmap_list); INIT_LIST_HEAD(&conf->inactive_list); + init_llist_head(&conf->released_stripes); atomic_set(&conf->active_stripes, 0); atomic_set(&conf->preread_active_stripes, 0); atomic_set(&conf->active_aligned_reads, 0); @@ -5980,6 +6294,7 @@ static int raid5_start_reshape(struct mddev *mddev) atomic_set(&conf->reshape_stripes, 0); spin_lock_irq(&conf->device_lock); + write_seqcount_begin(&conf->gen_lock); conf->previous_raid_disks = conf->raid_disks; conf->raid_disks += mddev->delta_disks; conf->prev_chunk_sectors = conf->chunk_sectors; @@ -5996,8 +6311,16 @@ static int raid5_start_reshape(struct mddev *mddev) else conf->reshape_progress = 0; conf->reshape_safe = conf->reshape_progress; + write_seqcount_end(&conf->gen_lock); spin_unlock_irq(&conf->device_lock); + /* Now make sure any requests that proceeded on the assumption + * the reshape wasn't running - like Discard or Read - have + * completed. + */ + mddev_suspend(mddev); + mddev_resume(mddev); + /* Add some new drives, as many as will fit. * We know there are enough to make the newly sized array work. * Don't add devices if we are reducing the number of @@ -6472,6 +6795,10 @@ static struct md_personality raid4_personality = static int __init raid5_init(void) { + raid5_wq = alloc_workqueue("raid5wq", + WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE|WQ_SYSFS, 0); + if (!raid5_wq) + return -ENOMEM; register_md_personality(&raid6_personality); register_md_personality(&raid5_personality); register_md_personality(&raid4_personality); @@ -6483,6 +6810,7 @@ static void raid5_exit(void) unregister_md_personality(&raid6_personality); unregister_md_personality(&raid5_personality); unregister_md_personality(&raid4_personality); + destroy_workqueue(raid5_wq); } module_init(raid5_init); diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 5c9797c..b42e6b4 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -197,6 +197,7 @@ enum reconstruct_states { struct stripe_head { struct hlist_node hash; struct list_head lru; /* inactive_list or handle_list */ + struct llist_node release_list; struct r5conf *raid_conf; short generation; /* increments with every * reshape */ @@ -211,6 +212,8 @@ struct stripe_head { enum check_states check_state; enum reconstruct_states reconstruct_state; spinlock_t stripe_lock; + int cpu; + struct r5worker_group *group; /** * struct stripe_operations * @target - STRIPE_OP_COMPUTE_BLK target @@ -321,6 +324,7 @@ enum { STRIPE_OPS_REQ_PENDING, STRIPE_ON_UNPLUG_LIST, STRIPE_DISCARD, + STRIPE_ON_RELEASE_LIST, }; /* @@ -363,6 +367,19 @@ struct disk_info { struct md_rdev *rdev, *replacement; }; +struct r5worker { + struct work_struct work; + struct r5worker_group *group; + bool working; +}; + +struct r5worker_group { + struct list_head handle_list; + struct r5conf *conf; + struct r5worker *workers; + int stripes_cnt; +}; + struct r5conf { struct hlist_head *stripe_hashtbl; struct mddev *mddev; @@ -386,6 +403,7 @@ struct r5conf { int prev_chunk_sectors; int prev_algo; short generation; /* increments with every reshape */ + seqcount_t gen_lock; /* lock against generation changes */ unsigned long reshape_checkpoint; /* Time we last updated * metadata */ long long min_offset_diff; /* minimum difference between @@ -445,6 +463,7 @@ struct r5conf { */ atomic_t active_stripes; struct list_head inactive_list; + struct llist_head released_stripes; wait_queue_head_t wait_for_stripe; wait_queue_head_t wait_for_overlap; int inactive_blocked; /* release of inactive stripes blocked, @@ -458,6 +477,9 @@ struct r5conf { * the new thread here until we fully activate the array. */ struct md_thread *thread; + struct r5worker_group *worker_groups; + int group_cnt; + int worker_cnt_per_group; }; /* |
