Merge tag 'for-linus-20180210' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A few fixes to round off the merge window on the block side:

   - a set of bcache fixes by way of Michael Lyle, from the usual bcache
     suspects.

   - add a simple-to-hook-into function for bpf EIO error injection.

   - fix blk-wbt that mischarectized flushes as reads. Improve the logic
     so that flushes and writes are accounted as writes, and only reads
     as reads. From me.

   - fix requeue crash in BFQ, from Paolo"

* tag 'for-linus-20180210' of git://git.kernel.dk/linux-block:
  block, bfq: add requeue-request hook
  bcache: fix for data collapse after re-attaching an attached device
  bcache: return attach error when no cache set exist
  bcache: set writeback_rate_update_seconds in range [1, 60] seconds
  bcache: fix for allocator and register thread race
  bcache: set error_limit correctly
  bcache: properly set task state in bch_writeback_thread()
  bcache: fix high CPU occupancy during journal
  bcache: add journal statistic
  block: Add should_fail_bio() for bpf error injection
  blk-wbt: account flush requests correctly

9 files changed, 111 insertions, 36 deletions

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 6cc6c0f9c3a9..458e1d38577d 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -287,8 +287,10 @@ do {									\
 			break;						\
 									\
 		mutex_unlock(&(ca)->set->bucket_lock);			\
-		if (kthread_should_stop())				\
+		if (kthread_should_stop()) {				\
+			set_current_state(TASK_RUNNING);		\
 			return 0;					\
+		}							\
 									\
 		schedule();						\
 		mutex_lock(&(ca)->set->bucket_lock);			\
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 5e2d4e80198e..12e5197f186c 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -658,10 +658,15 @@ struct cache_set {
 	atomic_long_t		writeback_keys_done;
 	atomic_long_t		writeback_keys_failed;
 
+	atomic_long_t		reclaim;
+	atomic_long_t		flush_write;
+	atomic_long_t		retry_flush_write;
+
 	enum			{
 		ON_ERROR_UNREGISTER,
 		ON_ERROR_PANIC,
 	}			on_error;
+#define DEFAULT_IO_ERROR_LIMIT 8
 	unsigned		error_limit;
 	unsigned		error_decay;
 
@@ -675,6 +680,8 @@ struct cache_set {
 
 #define BUCKET_HASH_BITS	12
 	struct hlist_head	bucket_hash[1 << BUCKET_HASH_BITS];
+
+	DECLARE_HEAP(struct btree *, flush_btree);
 };
 
 struct bbio {
@@ -917,7 +924,7 @@ void bcache_write_super(struct cache_set *);
 
 int bch_flash_dev_create(struct cache_set *c, uint64_t size);
 
-int bch_cached_dev_attach(struct cached_dev *, struct cache_set *);
+int bch_cached_dev_attach(struct cached_dev *, struct cache_set *, uint8_t *);
 void bch_cached_dev_detach(struct cached_dev *);
 void bch_cached_dev_run(struct cached_dev *);
 void bcache_device_stop(struct bcache_device *);
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index bf3a48aa9a9a..fad9fe8817eb 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1869,14 +1869,17 @@ void bch_initial_gc_finish(struct cache_set *c)
 	 */
 	for_each_cache(ca, c, i) {
 		for_each_bucket(b, ca) {
-			if (fifo_full(&ca->free[RESERVE_PRIO]))
+			if (fifo_full(&ca->free[RESERVE_PRIO]) &&
+			    fifo_full(&ca->free[RESERVE_BTREE]))
 				break;
 
 			if (bch_can_invalidate_bucket(ca, b) &&
 			    !GC_MARK(b)) {
 				__bch_invalidate_one_bucket(ca, b);
-				fifo_push(&ca->free[RESERVE_PRIO],
-					  b - ca->buckets);
+				if (!fifo_push(&ca->free[RESERVE_PRIO],
+				   b - ca->buckets))
+					fifo_push(&ca->free[RESERVE_BTREE],
+						  b - ca->buckets);
 			}
 		}
 	}
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index a87165c1d8e5..1b736b860739 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -368,6 +368,12 @@ err:
 }
 
 /* Journalling */
+#define journal_max_cmp(l, r) \
+	(fifo_idx(&c->journal.pin, btree_current_write(l)->journal) < \
+	 fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
+#define journal_min_cmp(l, r) \
+	(fifo_idx(&c->journal.pin, btree_current_write(l)->journal) > \
+	 fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
 
 static void btree_flush_write(struct cache_set *c)
 {
@@ -375,28 +381,41 @@ 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;
-	unsigned i;
+	struct btree *b;
+	int i;
+
+	atomic_long_inc(&c->flush_write);
+
 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;
+	spin_lock(&c->journal.lock);
+	if (heap_empty(&c->flush_btree)) {
+		for_each_cached_btree(b, c, i)
+			if (btree_current_write(b)->journal) {
+				if (!heap_full(&c->flush_btree))
+					heap_add(&c->flush_btree, b,
+						 journal_max_cmp);
+				else if (journal_max_cmp(b,
+					 heap_peek(&c->flush_btree))) {
+					c->flush_btree.data[0] = b;
+					heap_sift(&c->flush_btree, 0,
+						  journal_max_cmp);
+				}
 			}
-		}
 
-	b = best;
+		for (i = c->flush_btree.used / 2 - 1; i >= 0; --i)
+			heap_sift(&c->flush_btree, i, journal_min_cmp);
+	}
+
+	b = NULL;
+	heap_pop(&c->flush_btree, b, journal_min_cmp);
+	spin_unlock(&c->journal.lock);
+
 	if (b) {
 		mutex_lock(&b->write_lock);
 		if (!btree_current_write(b)->journal) {
 			mutex_unlock(&b->write_lock);
 			/* We raced */
+			atomic_long_inc(&c->retry_flush_write);
 			goto retry;
 		}
 
@@ -476,6 +495,8 @@ static void journal_reclaim(struct cache_set *c)
 	unsigned iter, n = 0;
 	atomic_t p;
 
+	atomic_long_inc(&c->reclaim);
+
 	while (!atomic_read(&fifo_front(&c->journal.pin)))
 		fifo_pop(&c->journal.pin, p);
 
@@ -819,7 +840,8 @@ int bch_journal_alloc(struct cache_set *c)
 	j->w[0].c = c;
 	j->w[1].c = c;
 
-	if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
+	if (!(init_heap(&c->flush_btree, 128, GFP_KERNEL)) ||
+	    !(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
 	    !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) ||
 	    !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)))
 		return -ENOMEM;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 133b81225ea9..312895788036 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -957,7 +957,8 @@ void bch_cached_dev_detach(struct cached_dev *dc)
 	cached_dev_put(dc);
 }
 
-int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
+int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
+			  uint8_t *set_uuid)
 {
 	uint32_t rtime = cpu_to_le32(get_seconds());
 	struct uuid_entry *u;
@@ -965,7 +966,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 
 	bdevname(dc->bdev, buf);
 
-	if (memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16))
+	if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) ||
+	    (!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)))
 		return -ENOENT;
 
 	if (dc->disk.c) {
@@ -1194,7 +1196,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 
 	list_add(&dc->list, &uncached_devices);
 	list_for_each_entry(c, &bch_cache_sets, list)
-		bch_cached_dev_attach(dc, c);
+		bch_cached_dev_attach(dc, c, NULL);
 
 	if (BDEV_STATE(&dc->sb) == BDEV_STATE_NONE ||
 	    BDEV_STATE(&dc->sb) == BDEV_STATE_STALE)
@@ -1553,7 +1555,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 
 	c->congested_read_threshold_us	= 2000;
 	c->congested_write_threshold_us	= 20000;
-	c->error_limit	= 8 << IO_ERROR_SHIFT;
+	c->error_limit	= DEFAULT_IO_ERROR_LIMIT;
 
 	return c;
 err:
@@ -1716,7 +1718,7 @@ static void run_cache_set(struct cache_set *c)
 	bcache_write_super(c);
 
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
-		bch_cached_dev_attach(dc, c);
+		bch_cached_dev_attach(dc, c, NULL);
 
 	flash_devs_run(c);
 
@@ -1833,6 +1835,7 @@ void bch_cache_release(struct kobject *kobj)
 static int cache_alloc(struct cache *ca)
 {
 	size_t free;
+	size_t btree_buckets;
 	struct bucket *b;
 
 	__module_get(THIS_MODULE);
@@ -1840,9 +1843,19 @@ static int cache_alloc(struct cache *ca)
 
 	bio_init(&ca->journal.bio, ca->journal.bio.bi_inline_vecs, 8);
 
+	/*
+	 * when ca->sb.njournal_buckets is not zero, journal exists,
+	 * and in bch_journal_replay(), tree node may split,
+	 * so bucket of RESERVE_BTREE type is needed,
+	 * the worst situation is all journal buckets are valid journal,
+	 * and all the keys need to replay,
+	 * so the number of  RESERVE_BTREE type buckets should be as much
+	 * as journal buckets
+	 */
+	btree_buckets = ca->sb.njournal_buckets ?: 8;
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
 
-	if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
+	if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets, GFP_KERNEL) ||
 	    !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index b4184092c727..78cd7bd50fdd 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -65,6 +65,9 @@ read_attribute(bset_tree_stats);
 
 read_attribute(state);
 read_attribute(cache_read_races);
+read_attribute(reclaim);
+read_attribute(flush_write);
+read_attribute(retry_flush_write);
 read_attribute(writeback_keys_done);
 read_attribute(writeback_keys_failed);
 read_attribute(io_errors);
@@ -195,7 +198,7 @@ STORE(__cached_dev)
 {
 	struct cached_dev *dc = container_of(kobj, struct cached_dev,
 					     disk.kobj);
-	ssize_t v = size;
+	ssize_t v;
 	struct cache_set *c;
 	struct kobj_uevent_env *env;
 
@@ -215,7 +218,9 @@ STORE(__cached_dev)
 	sysfs_strtoul_clamp(writeback_rate,
 			    dc->writeback_rate.rate, 1, INT_MAX);
 
-	d_strtoul_nonzero(writeback_rate_update_seconds);
+	sysfs_strtoul_clamp(writeback_rate_update_seconds,
+			    dc->writeback_rate_update_seconds,
+			    1, WRITEBACK_RATE_UPDATE_SECS_MAX);
 	d_strtoul(writeback_rate_i_term_inverse);
 	d_strtoul_nonzero(writeback_rate_p_term_inverse);
 
@@ -267,17 +272,20 @@ STORE(__cached_dev)
 	}
 
 	if (attr == &sysfs_attach) {
-		if (bch_parse_uuid(buf, dc->sb.set_uuid) < 16)
+		uint8_t		set_uuid[16];
+
+		if (bch_parse_uuid(buf, set_uuid) < 16)
 			return -EINVAL;
 
+		v = -ENOENT;
 		list_for_each_entry(c, &bch_cache_sets, list) {
-			v = bch_cached_dev_attach(dc, c);
+			v = bch_cached_dev_attach(dc, c, set_uuid);
 			if (!v)
 				return size;
 		}
 
 		pr_err("Can't attach %s: cache set not found", buf);
-		size = v;
+		return v;
 	}
 
 	if (attr == &sysfs_detach && dc->disk.c)
@@ -545,6 +553,15 @@ SHOW(__bch_cache_set)
 	sysfs_print(cache_read_races,
 		    atomic_long_read(&c->cache_read_races));
 
+	sysfs_print(reclaim,
+		    atomic_long_read(&c->reclaim));
+
+	sysfs_print(flush_write,
+		    atomic_long_read(&c->flush_write));
+
+	sysfs_print(retry_flush_write,
+		    atomic_long_read(&c->retry_flush_write));
+
 	sysfs_print(writeback_keys_done,
 		    atomic_long_read(&c->writeback_keys_done));
 	sysfs_print(writeback_keys_failed,
@@ -556,7 +573,7 @@ SHOW(__bch_cache_set)
 
 	/* 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);
+	sysfs_print(io_error_limit,	c->error_limit);
 
 	sysfs_hprint(congested,
 		     ((uint64_t) bch_get_congested(c)) << 9);
@@ -656,7 +673,7 @@ STORE(__bch_cache_set)
 	}
 
 	if (attr == &sysfs_io_error_limit)
-		c->error_limit = strtoul_or_return(buf) << IO_ERROR_SHIFT;
+		c->error_limit = strtoul_or_return(buf);
 
 	/* See count_io_errors() for why 88 */
 	if (attr == &sysfs_io_error_halflife)
@@ -731,6 +748,9 @@ static struct attribute *bch_cache_set_internal_files[] = {
 
 	&sysfs_bset_tree_stats,
 	&sysfs_cache_read_races,
+	&sysfs_reclaim,
+	&sysfs_flush_write,
+	&sysfs_retry_flush_write,
 	&sysfs_writeback_keys_done,
 	&sysfs_writeback_keys_failed,
 
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 4df4c5c1cab2..a6763db7f061 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -112,6 +112,8 @@ do {									\
 
 #define heap_full(h)	((h)->used == (h)->size)
 
+#define heap_empty(h)	((h)->used == 0)
+
 #define DECLARE_FIFO(type, name)					\
 	struct {							\
 		size_t front, back, size, mask;				\
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 51306a19ab03..f1d2fc15abcc 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -564,18 +564,21 @@ static int bch_writeback_thread(void *arg)
 
 	while (!kthread_should_stop()) {
 		down_write(&dc->writeback_lock);
+		set_current_state(TASK_INTERRUPTIBLE);
 		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())
+			if (kthread_should_stop()) {
+				set_current_state(TASK_RUNNING);
 				return 0;
+			}
 
 			schedule();
 			continue;
 		}
+		set_current_state(TASK_RUNNING);
 
 		searched_full_index = refill_dirty(dc);
 
@@ -652,7 +655,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 	dc->writeback_rate.rate		= 1024;
 	dc->writeback_rate_minimum	= 8;
 
-	dc->writeback_rate_update_seconds = 5;
+	dc->writeback_rate_update_seconds = WRITEBACK_RATE_UPDATE_SECS_DEFAULT;
 	dc->writeback_rate_p_term_inverse = 40;
 	dc->writeback_rate_i_term_inverse = 10000;
 
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 66f1c527fa24..587b25599856 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -8,6 +8,9 @@
 #define MAX_WRITEBACKS_IN_PASS  5
 #define MAX_WRITESIZE_IN_PASS   5000	/* *512b */
 
+#define WRITEBACK_RATE_UPDATE_SECS_MAX		60
+#define WRITEBACK_RATE_UPDATE_SECS_DEFAULT	5
+
 /*
  * 14 (16384ths) is chosen here as something that each backing device
  * should be a reasonable fraction of the share, and not to blow up