Merge branch 'for-4.15/block' of git://git.kernel.dk/linux-block

Pull core block layer updates from Jens Axboe:
 "This is the main pull request for block storage for 4.15-rc1.

  Nothing out of the ordinary in here, and no API changes or anything
  like that. Just various new features for drivers, core changes, etc.
  In particular, this pull request contains:

   - A patch series from Bart, closing the whole on blk/scsi-mq queue
     quescing.

   - A series from Christoph, building towards hidden gendisks (for
     multipath) and ability to move bio chains around.

   - NVMe
        - Support for native multipath for NVMe (Christoph).
        - Userspace notifications for AENs (Keith).
        - Command side-effects support (Keith).
        - SGL support (Chaitanya Kulkarni)
        - FC fixes and improvements (James Smart)
        - Lots of fixes and tweaks (Various)

   - bcache
        - New maintainer (Michael Lyle)
        - Writeback control improvements (Michael)
        - Various fixes (Coly, Elena, Eric, Liang, et al)

   - lightnvm updates, mostly centered around the pblk interface
     (Javier, Hans, and Rakesh).

   - Removal of unused bio/bvec kmap atomic interfaces (me, Christoph)

   - Writeback series that fix the much discussed hundreds of millions
     of sync-all units. This goes all the way, as discussed previously
     (me).

   - Fix for missing wakeup on writeback timer adjustments (Yafang
     Shao).

   - Fix laptop mode on blk-mq (me).

   - {mq,name} tupple lookup for IO schedulers, allowing us to have
     alias names. This means you can use 'deadline' on both !mq and on
     mq (where it's called mq-deadline). (me).

   - blktrace race fix, oopsing on sg load (me).

   - blk-mq optimizations (me).

   - Obscure waitqueue race fix for kyber (Omar).

   - NBD fixes (Josef).

   - Disable writeback throttling by default on bfq, like we do on cfq
     (Luca Miccio).

   - Series from Ming that enable us to treat flush requests on blk-mq
     like any other request. This is a really nice cleanup.

   - Series from Ming that improves merging on blk-mq with schedulers,
     getting us closer to flipping the switch on scsi-mq again.

   - BFQ updates (Paolo).

   - blk-mq atomic flags memory ordering fixes (Peter Z).

   - Loop cgroup support (Shaohua).

   - Lots of minor fixes from lots of different folks, both for core and
     driver code"

* 'for-4.15/block' of git://git.kernel.dk/linux-block: (294 commits)
  nvme: fix visibility of "uuid" ns attribute
  blk-mq: fixup some comment typos and lengths
  ide: ide-atapi: fix compile error with defining macro DEBUG
  blk-mq: improve tag waiting setup for non-shared tags
  brd: remove unused brd_mutex
  blk-mq: only run the hardware queue if IO is pending
  block: avoid null pointer dereference on null disk
  fs: guard_bio_eod() needs to consider partitions
  xtensa/simdisk: fix compile error
  nvme: expose subsys attribute to sysfs
  nvme: create 'slaves' and 'holders' entries for hidden controllers
  block: create 'slaves' and 'holders' entries for hidden gendisks
  nvme: also expose the namespace identification sysfs files for mpath nodes
  nvme: implement multipath access to nvme subsystems
  nvme: track shared namespaces
  nvme: introduce a nvme_ns_ids structure
  nvme: track subsystems
  block, nvme: Introduce blk_mq_req_flags_t
  block, scsi: Make SCSI quiesce and resume work reliably
  block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag
  ...

12 files changed, 201 insertions, 111 deletions

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 08035634795c..a27d85232ce1 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -407,7 +407,8 @@ long bch_bucket_alloc(struct cache *ca, unsigned reserve, bool wait)
 
 	finish_wait(&ca->set->bucket_wait, &w);
 out:
-	wake_up_process(ca->alloc_thread);
+	if (ca->alloc_thread)
+		wake_up_process(ca->alloc_thread);
 
 	trace_bcache_alloc(ca, reserve);
 
@@ -442,6 +443,11 @@ out:
 		b->prio = INITIAL_PRIO;
 	}
 
+	if (ca->set->avail_nbuckets > 0) {
+		ca->set->avail_nbuckets--;
+		bch_update_bucket_in_use(ca->set, &ca->set->gc_stats);
+	}
+
 	return r;
 }
 
@@ -449,6 +455,11 @@ void __bch_bucket_free(struct cache *ca, struct bucket *b)
 {
 	SET_GC_MARK(b, 0);
 	SET_GC_SECTORS_USED(b, 0);
+
+	if (ca->set->avail_nbuckets < ca->set->nbuckets) {
+		ca->set->avail_nbuckets++;
+		bch_update_bucket_in_use(ca->set, &ca->set->gc_stats);
+	}
 }
 
 void bch_bucket_free(struct cache_set *c, struct bkey *k)
@@ -601,7 +612,7 @@ bool bch_alloc_sectors(struct cache_set *c, struct bkey *k, unsigned sectors,
 
 	/*
 	 * 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
+	 * second time we call pick_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))
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index abd31e847f96..843877e017e1 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -185,6 +185,7 @@
 #include <linux/mutex.h>
 #include <linux/rbtree.h>
 #include <linux/rwsem.h>
+#include <linux/refcount.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
@@ -266,9 +267,6 @@ struct bcache_device {
 	atomic_t		*stripe_sectors_dirty;
 	unsigned long		*full_dirty_stripes;
 
-	unsigned long		sectors_dirty_last;
-	long			sectors_dirty_derivative;
-
 	struct bio_set		*bio_split;
 
 	unsigned		data_csum:1;
@@ -300,7 +298,7 @@ struct cached_dev {
 	struct semaphore	sb_write_mutex;
 
 	/* Refcount on the cache set. Always nonzero when we're caching. */
-	atomic_t		count;
+	refcount_t		count;
 	struct work_struct	detach;
 
 	/*
@@ -363,12 +361,14 @@ struct cached_dev {
 
 	uint64_t		writeback_rate_target;
 	int64_t			writeback_rate_proportional;
-	int64_t			writeback_rate_derivative;
-	int64_t			writeback_rate_change;
+	int64_t			writeback_rate_integral;
+	int64_t			writeback_rate_integral_scaled;
+	int32_t			writeback_rate_change;
 
 	unsigned		writeback_rate_update_seconds;
-	unsigned		writeback_rate_d_term;
+	unsigned		writeback_rate_i_term_inverse;
 	unsigned		writeback_rate_p_term_inverse;
+	unsigned		writeback_rate_minimum;
 };
 
 enum alloc_reserve {
@@ -582,6 +582,7 @@ struct cache_set {
 	uint8_t			need_gc;
 	struct gc_stat		gc_stats;
 	size_t			nbuckets;
+	size_t			avail_nbuckets;
 
 	struct task_struct	*gc_thread;
 	/* Where in the btree gc currently is */
@@ -807,13 +808,13 @@ do {									\
 
 static inline void cached_dev_put(struct cached_dev *dc)
 {
-	if (atomic_dec_and_test(&dc->count))
+	if (refcount_dec_and_test(&dc->count))
 		schedule_work(&dc->detach);
 }
 
 static inline bool cached_dev_get(struct cached_dev *dc)
 {
-	if (!atomic_inc_not_zero(&dc->count))
+	if (!refcount_inc_not_zero(&dc->count))
 		return false;
 
 	/* Paired with the mb in cached_dev_attach */
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 658c54b3b07a..11c5503d31dc 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1241,6 +1241,11 @@ void bch_initial_mark_key(struct cache_set *c, int level, struct bkey *k)
 	__bch_btree_mark_key(c, level, k);
 }
 
+void bch_update_bucket_in_use(struct cache_set *c, struct gc_stat *stats)
+{
+	stats->in_use = (c->nbuckets - c->avail_nbuckets) * 100 / c->nbuckets;
+}
+
 static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc)
 {
 	uint8_t stale = 0;
@@ -1652,9 +1657,8 @@ static void btree_gc_start(struct cache_set *c)
 	mutex_unlock(&c->bucket_lock);
 }
 
-static size_t bch_btree_gc_finish(struct cache_set *c)
+static void bch_btree_gc_finish(struct cache_set *c)
 {
-	size_t available = 0;
 	struct bucket *b;
 	struct cache *ca;
 	unsigned i;
@@ -1691,6 +1695,7 @@ static size_t bch_btree_gc_finish(struct cache_set *c)
 	}
 	rcu_read_unlock();
 
+	c->avail_nbuckets = 0;
 	for_each_cache(ca, c, i) {
 		uint64_t *i;
 
@@ -1712,18 +1717,16 @@ static size_t bch_btree_gc_finish(struct cache_set *c)
 			BUG_ON(!GC_MARK(b) && GC_SECTORS_USED(b));
 
 			if (!GC_MARK(b) || GC_MARK(b) == GC_MARK_RECLAIMABLE)
-				available++;
+				c->avail_nbuckets++;
 		}
 	}
 
 	mutex_unlock(&c->bucket_lock);
-	return available;
 }
 
 static void bch_btree_gc(struct cache_set *c)
 {
 	int ret;
-	unsigned long available;
 	struct gc_stat stats;
 	struct closure writes;
 	struct btree_op op;
@@ -1746,14 +1749,14 @@ static void bch_btree_gc(struct cache_set *c)
 			pr_warn("gc failed!");
 	} while (ret);
 
-	available = bch_btree_gc_finish(c);
+	bch_btree_gc_finish(c);
 	wake_up_allocators(c);
 
 	bch_time_stats_update(&c->btree_gc_time, start_time);
 
 	stats.key_bytes *= sizeof(uint64_t);
 	stats.data	<<= 9;
-	stats.in_use	= (c->nbuckets - available) * 100 / c->nbuckets;
+	bch_update_bucket_in_use(c, &stats);
 	memcpy(&c->gc_stats, &stats, sizeof(struct gc_stat));
 
 	trace_bcache_gc_end(c);
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index 42204d61bc95..d211e2c25b6b 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -306,5 +306,5 @@ void bch_keybuf_del(struct keybuf *, struct keybuf_key *);
 struct keybuf_key *bch_keybuf_next(struct keybuf *);
 struct keybuf_key *bch_keybuf_next_rescan(struct cache_set *, struct keybuf *,
 					  struct bkey *, keybuf_pred_fn *);
-
+void bch_update_bucket_in_use(struct cache_set *c, struct gc_stat *stats);
 #endif
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 965907ce1e20..ccfbea6f9f6b 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -252,6 +252,12 @@ static inline void set_closure_fn(struct closure *cl, closure_fn *fn,
 static inline void closure_queue(struct closure *cl)
 {
 	struct workqueue_struct *wq = cl->wq;
+	/**
+	 * Changes made to closure, work_struct, or a couple of other structs
+	 * may cause work.func not pointing to the right location.
+	 */
+	BUILD_BUG_ON(offsetof(struct closure, fn)
+		     != offsetof(struct work_struct, func));
 	if (wq) {
 		INIT_WORK(&cl->work, cl->work.func);
 		BUG_ON(!queue_work(wq, &cl->work));
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 3475d6628e21..3a7aed7282b2 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -27,12 +27,12 @@ struct kmem_cache *bch_search_cache;
 
 static void bch_data_insert_start(struct closure *);
 
-static unsigned cache_mode(struct cached_dev *dc, struct bio *bio)
+static unsigned cache_mode(struct cached_dev *dc)
 {
 	return BDEV_CACHE_MODE(&dc->sb);
 }
 
-static bool verify(struct cached_dev *dc, struct bio *bio)
+static bool verify(struct cached_dev *dc)
 {
 	return dc->verify;
 }
@@ -370,7 +370,7 @@ static struct hlist_head *iohash(struct cached_dev *dc, uint64_t k)
 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 mode = cache_mode(dc);
 	unsigned sectors, congested = bch_get_congested(c);
 	struct task_struct *task = current;
 	struct io *i;
@@ -385,6 +385,14 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 	     op_is_write(bio_op(bio))))
 		goto skip;
 
+	/*
+	 * Flag for bypass if the IO is for read-ahead or background,
+	 * unless the read-ahead request is for metadata (eg, for gfs2).
+	 */
+	if (bio->bi_opf & (REQ_RAHEAD|REQ_BACKGROUND) &&
+	    !(bio->bi_opf & REQ_META))
+		goto skip;
+
 	if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
 	    bio_sectors(bio) & (c->sb.block_size - 1)) {
 		pr_debug("skipping unaligned io");
@@ -463,6 +471,7 @@ struct search {
 	unsigned		recoverable:1;
 	unsigned		write:1;
 	unsigned		read_dirty_data:1;
+	unsigned		cache_missed:1;
 
 	unsigned long		start_time;
 
@@ -649,6 +658,7 @@ static inline struct search *search_alloc(struct bio *bio,
 
 	s->orig_bio		= bio;
 	s->cache_miss		= NULL;
+	s->cache_missed		= 0;
 	s->d			= d;
 	s->recoverable		= 1;
 	s->write		= op_is_write(bio_op(bio));
@@ -698,8 +708,16 @@ 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 cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
-	if (s->recoverable) {
+	/*
+	 * If cache device is dirty (dc->has_dirty is non-zero), then
+	 * recovery a failed read request from cached device may get a
+	 * stale data back. So read failure recovery is only permitted
+	 * when cache device is clean.
+	 */
+	if (s->recoverable &&
+	    (dc && !atomic_read(&dc->has_dirty))) {
 		/* Retry from the backing device: */
 		trace_bcache_read_retry(s->orig_bio);
 
@@ -740,7 +758,7 @@ static void cached_dev_read_done(struct closure *cl)
 		s->cache_miss = NULL;
 	}
 
-	if (verify(dc, &s->bio.bio) && s->recoverable && !s->read_dirty_data)
+	if (verify(dc) && s->recoverable && !s->read_dirty_data)
 		bch_data_verify(dc, s->orig_bio);
 
 	bio_complete(s);
@@ -760,12 +778,12 @@ static void cached_dev_read_done_bh(struct closure *cl)
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	bch_mark_cache_accounting(s->iop.c, s->d,
-				  !s->cache_miss, s->iop.bypass);
+				  !s->cache_missed, s->iop.bypass);
 	trace_bcache_read(s->orig_bio, !s->cache_miss, s->iop.bypass);
 
 	if (s->iop.status)
 		continue_at_nobarrier(cl, cached_dev_read_error, bcache_wq);
-	else if (s->iop.bio || verify(dc, &s->bio.bio))
+	else if (s->iop.bio || verify(dc))
 		continue_at_nobarrier(cl, cached_dev_read_done, bcache_wq);
 	else
 		continue_at_nobarrier(cl, cached_dev_bio_complete, NULL);
@@ -779,6 +797,8 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 	struct bio *miss, *cache_bio;
 
+	s->cache_missed = 1;
+
 	if (s->cache_miss || s->iop.bypass) {
 		miss = bio_next_split(bio, sectors, GFP_NOIO, s->d->bio_split);
 		ret = miss == bio ? MAP_DONE : MAP_CONTINUE;
@@ -892,7 +912,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 		s->iop.bypass = true;
 
 	if (should_writeback(dc, s->orig_bio,
-			     cache_mode(dc, bio),
+			     cache_mode(dc),
 			     s->iop.bypass)) {
 		s->iop.bypass = false;
 		s->iop.writeback = true;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index fc0a31b13ac4..b4d28928dec5 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -53,12 +53,15 @@ LIST_HEAD(bch_cache_sets);
 static LIST_HEAD(uncached_devices);
 
 static int bcache_major;
-static DEFINE_IDA(bcache_minor);
+static DEFINE_IDA(bcache_device_idx);
 static wait_queue_head_t unregister_wait;
 struct workqueue_struct *bcache_wq;
 
 #define BTREE_MAX_PAGES		(256 * 1024 / PAGE_SIZE)
-#define BCACHE_MINORS		16 /* partition support */
+/* limitation of partitions number on single bcache device */
+#define BCACHE_MINORS		128
+/* limitation of bcache devices number on single system */
+#define BCACHE_DEVICE_IDX_MAX	((1U << MINORBITS)/BCACHE_MINORS)
 
 /* Superblock */
 
@@ -721,6 +724,16 @@ static void bcache_device_attach(struct bcache_device *d, struct cache_set *c,
 	closure_get(&c->caching);
 }
 
+static inline int first_minor_to_idx(int first_minor)
+{
+	return (first_minor/BCACHE_MINORS);
+}
+
+static inline int idx_to_first_minor(int idx)
+{
+	return (idx * BCACHE_MINORS);
+}
+
 static void bcache_device_free(struct bcache_device *d)
 {
 	lockdep_assert_held(&bch_register_lock);
@@ -734,7 +747,8 @@ static void bcache_device_free(struct bcache_device *d)
 	if (d->disk && d->disk->queue)
 		blk_cleanup_queue(d->disk->queue);
 	if (d->disk) {
-		ida_simple_remove(&bcache_minor, d->disk->first_minor);
+		ida_simple_remove(&bcache_device_idx,
+				  first_minor_to_idx(d->disk->first_minor));
 		put_disk(d->disk);
 	}
 
@@ -751,7 +765,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 {
 	struct request_queue *q;
 	size_t n;
-	int minor;
+	int idx;
 
 	if (!d->stripe_size)
 		d->stripe_size = 1 << 31;
@@ -776,25 +790,24 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	if (!d->full_dirty_stripes)
 		return -ENOMEM;
 
-	minor = ida_simple_get(&bcache_minor, 0, MINORMASK + 1, GFP_KERNEL);
-	if (minor < 0)
-		return minor;
-
-	minor *= BCACHE_MINORS;
+	idx = ida_simple_get(&bcache_device_idx, 0,
+				BCACHE_DEVICE_IDX_MAX, GFP_KERNEL);
+	if (idx < 0)
+		return idx;
 
 	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio),
 					   BIOSET_NEED_BVECS |
 					   BIOSET_NEED_RESCUER)) ||
 	    !(d->disk = alloc_disk(BCACHE_MINORS))) {
-		ida_simple_remove(&bcache_minor, minor);
+		ida_simple_remove(&bcache_device_idx, idx);
 		return -ENOMEM;
 	}
 
 	set_capacity(d->disk, sectors);
-	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", minor);
+	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
 
 	d->disk->major		= bcache_major;
-	d->disk->first_minor	= minor;
+	d->disk->first_minor	= idx_to_first_minor(idx);
 	d->disk->fops		= &bcache_ops;
 	d->disk->private_data	= d;
 
@@ -889,7 +902,7 @@ static void cached_dev_detach_finish(struct work_struct *w)
 	closure_init_stack(&cl);
 
 	BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags));
-	BUG_ON(atomic_read(&dc->count));
+	BUG_ON(refcount_read(&dc->count));
 
 	mutex_lock(&bch_register_lock);
 
@@ -1016,7 +1029,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 	 * dc->c must be set before dc->count != 0 - paired with the mb in
 	 * cached_dev_get()
 	 */
-	atomic_set(&dc->count, 1);
+	refcount_set(&dc->count, 1);
 
 	/* Block writeback thread, but spawn it */
 	down_write(&dc->writeback_lock);
@@ -1028,7 +1041,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 	if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
 		bch_sectors_dirty_init(&dc->disk);
 		atomic_set(&dc->has_dirty, 1);
-		atomic_inc(&dc->count);
+		refcount_inc(&dc->count);
 		bch_writeback_queue(dc);
 	}
 
@@ -1129,9 +1142,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned block_size)
 	if (ret)
 		return ret;
 
-	set_capacity(dc->disk.disk,
-		     dc->bdev->bd_part->nr_sects - dc->sb.data_offset);
-
 	dc->disk.disk->queue->backing_dev_info->ra_pages =
 		max(dc->disk.disk->queue->backing_dev_info->ra_pages,
 		    q->backing_dev_info->ra_pages);
@@ -2085,6 +2095,7 @@ static void bcache_exit(void)
 	if (bcache_major)
 		unregister_blkdev(bcache_major, "bcache");
 	unregister_reboot_notifier(&reboot);
+	mutex_destroy(&bch_register_lock);
 }
 
 static int __init bcache_init(void)
@@ -2103,14 +2114,15 @@ static int __init bcache_init(void)
 	bcache_major = register_blkdev(0, "bcache");
 	if (bcache_major < 0) {
 		unregister_reboot_notifier(&reboot);
+		mutex_destroy(&bch_register_lock);
 		return bcache_major;
 	}
 
 	if (!(bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0)) ||
 	    !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
-	    sysfs_create_files(bcache_kobj, files) ||
 	    bch_request_init() ||
-	    bch_debug_init(bcache_kobj))
+	    bch_debug_init(bcache_kobj) ||
+	    sysfs_create_files(bcache_kobj, files))
 		goto err;
 
 	return 0;
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 234b2f5b286d..b4184092c727 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -82,8 +82,9 @@ rw_attribute(writeback_delay);
 rw_attribute(writeback_rate);
 
 rw_attribute(writeback_rate_update_seconds);
-rw_attribute(writeback_rate_d_term);
+rw_attribute(writeback_rate_i_term_inverse);
 rw_attribute(writeback_rate_p_term_inverse);
+rw_attribute(writeback_rate_minimum);
 read_attribute(writeback_rate_debug);
 
 read_attribute(stripe_size);
@@ -131,15 +132,16 @@ SHOW(__bch_cached_dev)
 	sysfs_hprint(writeback_rate,	dc->writeback_rate.rate << 9);
 
 	var_print(writeback_rate_update_seconds);
-	var_print(writeback_rate_d_term);
+	var_print(writeback_rate_i_term_inverse);
 	var_print(writeback_rate_p_term_inverse);
+	var_print(writeback_rate_minimum);
 
 	if (attr == &sysfs_writeback_rate_debug) {
 		char rate[20];
 		char dirty[20];
 		char target[20];
 		char proportional[20];
-		char derivative[20];
+		char integral[20];
 		char change[20];
 		s64 next_io;
 
@@ -147,7 +149,7 @@ SHOW(__bch_cached_dev)
 		bch_hprint(dirty,	bcache_dev_sectors_dirty(&dc->disk) << 9);
 		bch_hprint(target,	dc->writeback_rate_target << 9);
 		bch_hprint(proportional,dc->writeback_rate_proportional << 9);
-		bch_hprint(derivative,	dc->writeback_rate_derivative << 9);
+		bch_hprint(integral,	dc->writeback_rate_integral_scaled << 9);
 		bch_hprint(change,	dc->writeback_rate_change << 9);
 
 		next_io = div64_s64(dc->writeback_rate.next - local_clock(),
@@ -158,11 +160,11 @@ SHOW(__bch_cached_dev)
 			       "dirty:\t\t%s\n"
 			       "target:\t\t%s\n"
 			       "proportional:\t%s\n"
-			       "derivative:\t%s\n"
+			       "integral:\t%s\n"
 			       "change:\t\t%s/sec\n"
 			       "next io:\t%llims\n",
 			       rate, dirty, target, proportional,
-			       derivative, change, next_io);
+			       integral, change, next_io);
 	}
 
 	sysfs_hprint(dirty_data,
@@ -214,7 +216,7 @@ STORE(__cached_dev)
 			    dc->writeback_rate.rate, 1, INT_MAX);
 
 	d_strtoul_nonzero(writeback_rate_update_seconds);
-	d_strtoul(writeback_rate_d_term);
+	d_strtoul(writeback_rate_i_term_inverse);
 	d_strtoul_nonzero(writeback_rate_p_term_inverse);
 
 	d_strtoi_h(sequential_cutoff);
@@ -320,7 +322,7 @@ static struct attribute *bch_cached_dev_files[] = {
 	&sysfs_writeback_percent,
 	&sysfs_writeback_rate,
 	&sysfs_writeback_rate_update_seconds,
-	&sysfs_writeback_rate_d_term,
+	&sysfs_writeback_rate_i_term_inverse,
 	&sysfs_writeback_rate_p_term_inverse,
 	&sysfs_writeback_rate_debug,
 	&sysfs_dirty_data,
@@ -746,6 +748,11 @@ static struct attribute *bch_cache_set_internal_files[] = {
 };
 KTYPE(bch_cache_set_internal);
 
+static int __bch_cache_cmp(const void *l, const void *r)
+{
+	return *((uint16_t *)r) - *((uint16_t *)l);
+}
+
 SHOW(__bch_cache)
 {
 	struct cache *ca = container_of(kobj, struct cache, kobj);
@@ -770,9 +777,6 @@ SHOW(__bch_cache)
 					       CACHE_REPLACEMENT(&ca->sb));
 
 	if (attr == &sysfs_priority_stats) {
-		int cmp(const void *l, const void *r)
-		{	return *((uint16_t *) r) - *((uint16_t *) l); }
-
 		struct bucket *b;
 		size_t n = ca->sb.nbuckets, i;
 		size_t unused = 0, available = 0, dirty = 0, meta = 0;
@@ -801,7 +805,7 @@ SHOW(__bch_cache)
 			p[i] = ca->buckets[i].prio;
 		mutex_unlock(&ca->set->bucket_lock);
 
-		sort(p, n, sizeof(uint16_t), cmp, NULL);
+		sort(p, n, sizeof(uint16_t), __bch_cache_cmp, NULL);
 
 		while (n &&
 		       !cached[n - 1])
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index 176d3c2ef5f5..e548b8b51322 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -232,8 +232,14 @@ uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
 
 	d->next += div_u64(done * NSEC_PER_SEC, d->rate);
 
-	if (time_before64(now + NSEC_PER_SEC, d->next))
-		d->next = now + NSEC_PER_SEC;
+	/* Bound the time.  Don't let us fall further than 2 seconds behind
+	 * (this prevents unnecessary backlog that would make it impossible
+	 * to catch up).  If we're ahead of the desired writeback rate,
+	 * don't let us sleep more than 2.5 seconds (so we can notice/respond
+	 * if the control system tells us to speed up!).
+	 */
+	if (time_before64(now + NSEC_PER_SEC * 5LLU / 2LLU, d->next))
+		d->next = now + NSEC_PER_SEC * 5LLU / 2LLU;
 
 	if (time_after64(now - NSEC_PER_SEC * 2, d->next))
 		d->next = now - NSEC_PER_SEC * 2;
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index f54b58282f77..ed5e8a412eb8 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -442,10 +442,10 @@ struct bch_ratelimit {
 	uint64_t		next;
 
 	/*
-	 * Rate at which we want to do work, in units per nanosecond
+	 * Rate at which we want to do work, in units per second
 	 * The units here correspond to the units passed to bch_next_delay()
 	 */
-	unsigned		rate;
+	uint32_t		rate;
 };
 
 static inline void bch_ratelimit_reset(struct bch_ratelimit *d)
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 70454f2ad2fa..56a37884ca8b 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -26,48 +26,63 @@ static void __update_writeback_rate(struct cached_dev *dc)
 				bcache_flash_devs_sectors_dirty(c);
 	uint64_t cache_dirty_target =
 		div_u64(cache_sectors * dc->writeback_percent, 100);
-
 	int64_t target = div64_u64(cache_dirty_target * bdev_sectors(dc->bdev),
 				   c->cached_dev_sectors);
 
-	/* PD controller */
-
+	/*
+	 * PI controller:
+	 * Figures out the amount that should be written per second.
+	 *
+	 * First, the error (number of sectors that are dirty beyond our
+	 * target) is calculated.  The error is accumulated (numerically
+	 * integrated).
+	 *
+	 * Then, the proportional value and integral value are scaled
+	 * based on configured values.  These are stored as inverses to
+	 * avoid fixed point math and to make configuration easy-- e.g.
+	 * the default value of 40 for writeback_rate_p_term_inverse
+	 * attempts to write at a rate that would retire all the dirty
+	 * blocks in 40 seconds.
+	 *
+	 * The writeback_rate_i_inverse value of 10000 means that 1/10000th
+	 * of the error is accumulated in the integral term per second.
+	 * This acts as a slow, long-term average that is not subject to
+	 * variations in usage like the p term.
+	 */
 	int64_t dirty = bcache_dev_sectors_dirty(&dc->disk);
-	int64_t derivative = dirty - dc->disk.sectors_dirty_last;
-	int64_t proportional = dirty - target;
-	int64_t change;
-
-	dc->disk.sectors_dirty_last = dirty;
-
-	/* Scale to sectors per second */
-
-	proportional *= dc->writeback_rate_update_seconds;
-	proportional = div_s64(proportional, dc->writeback_rate_p_term_inverse);
-
-	derivative = div_s64(derivative, dc->writeback_rate_update_seconds);
-
-	derivative = ewma_add(dc->disk.sectors_dirty_derivative, derivative,
-			      (dc->writeback_rate_d_term /
-			       dc->writeback_rate_update_seconds) ?: 1, 0);
-
-	derivative *= dc->writeback_rate_d_term;
-	derivative = div_s64(derivative, dc->writeback_rate_p_term_inverse);
-
-	change = proportional + derivative;
+	int64_t error = dirty - target;
+	int64_t proportional_scaled =
+		div_s64(error, dc->writeback_rate_p_term_inverse);
+	int64_t integral_scaled;
+	uint32_t new_rate;
+
+	if ((error < 0 && dc->writeback_rate_integral > 0) ||
+	    (error > 0 && time_before64(local_clock(),
+			 dc->writeback_rate.next + NSEC_PER_MSEC))) {
+		/*
+		 * Only decrease the integral term if it's more than
+		 * zero.  Only increase the integral term if the device
+		 * is keeping up.  (Don't wind up the integral
+		 * ineffectively in either case).
+		 *
+		 * It's necessary to scale this by
+		 * writeback_rate_update_seconds to keep the integral
+		 * term dimensioned properly.
+		 */
+		dc->writeback_rate_integral += error *
+			dc->writeback_rate_update_seconds;
+	}
 
-	/* Don't increase writeback rate if the device isn't keeping up */
-	if (change > 0 &&
-	    time_after64(local_clock(),
-			 dc->writeback_rate.next + NSEC_PER_MSEC))
-		change = 0;
+	integral_scaled = div_s64(dc->writeback_rate_integral,
+			dc->writeback_rate_i_term_inverse);
 
-	dc->writeback_rate.rate =
-		clamp_t(int64_t, (int64_t) dc->writeback_rate.rate + change,
-			1, NSEC_PER_MSEC);
+	new_rate = clamp_t(int32_t, (proportional_scaled + integral_scaled),
+			dc->writeback_rate_minimum, NSEC_PER_SEC);
 
-	dc->writeback_rate_proportional = proportional;
-	dc->writeback_rate_derivative = derivative;
-	dc->writeback_rate_change = change;
+	dc->writeback_rate_proportional = proportional_scaled;
+	dc->writeback_rate_integral_scaled = integral_scaled;
+	dc->writeback_rate_change = new_rate - dc->writeback_rate.rate;
+	dc->writeback_rate.rate = new_rate;
 	dc->writeback_rate_target = target;
 }
 
@@ -180,13 +195,21 @@ static void write_dirty(struct closure *cl)
 	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
 	struct keybuf_key *w = io->bio.bi_private;
 
-	dirty_init(w);
-	bio_set_op_attrs(&io->bio, REQ_OP_WRITE, 0);
-	io->bio.bi_iter.bi_sector = KEY_START(&w->key);
-	bio_set_dev(&io->bio, io->dc->bdev);
-	io->bio.bi_end_io	= dirty_endio;
+	/*
+	 * IO errors are signalled using the dirty bit on the key.
+	 * If we failed to read, we should not attempt to write to the
+	 * backing device.  Instead, immediately go to write_dirty_finish
+	 * to clean up.
+	 */
+	if (KEY_DIRTY(&w->key)) {
+		dirty_init(w);
+		bio_set_op_attrs(&io->bio, REQ_OP_WRITE, 0);
+		io->bio.bi_iter.bi_sector = KEY_START(&w->key);
+		bio_set_dev(&io->bio, io->dc->bdev);
+		io->bio.bi_end_io	= dirty_endio;
 
-	closure_bio_submit(&io->bio, cl);
+		closure_bio_submit(&io->bio, cl);
+	}
 
 	continue_at(cl, write_dirty_finish, io->dc->writeback_write_wq);
 }
@@ -418,6 +441,8 @@ static int bch_writeback_thread(void *arg)
 	struct cached_dev *dc = arg;
 	bool searched_full_index;
 
+	bch_ratelimit_reset(&dc->writeback_rate);
+
 	while (!kthread_should_stop()) {
 		down_write(&dc->writeback_lock);
 		if (!atomic_read(&dc->has_dirty) ||
@@ -445,7 +470,6 @@ static int bch_writeback_thread(void *arg)
 
 		up_write(&dc->writeback_lock);
 
-		bch_ratelimit_reset(&dc->writeback_rate);
 		read_dirty(dc);
 
 		if (searched_full_index) {
@@ -455,6 +479,8 @@ static int bch_writeback_thread(void *arg)
 			       !kthread_should_stop() &&
 			       !test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags))
 				delay = schedule_timeout_interruptible(delay);
+
+			bch_ratelimit_reset(&dc->writeback_rate);
 		}
 	}
 
@@ -492,8 +518,6 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 
 	bch_btree_map_keys(&op.op, d->c, &KEY(op.inode, 0, 0),
 			   sectors_dirty_init_fn, 0);
-
-	d->sectors_dirty_last = bcache_dev_sectors_dirty(d);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
@@ -507,10 +531,11 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 	dc->writeback_percent		= 10;
 	dc->writeback_delay		= 30;
 	dc->writeback_rate.rate		= 1024;
+	dc->writeback_rate_minimum	= 8;
 
 	dc->writeback_rate_update_seconds = 5;
-	dc->writeback_rate_d_term	= 30;
-	dc->writeback_rate_p_term_inverse = 6000;
+	dc->writeback_rate_p_term_inverse = 40;
+	dc->writeback_rate_i_term_inverse = 10000;
 
 	INIT_DELAYED_WORK(&dc->writeback_rate_update, update_writeback_rate);
 }
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 151544740148..a9e3ffb4b03c 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -77,7 +77,9 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
 	if (would_skip)
 		return false;
 
-	return op_is_sync(bio->bi_opf) || in_use <= CUTOFF_WRITEBACK;
+	return (op_is_sync(bio->bi_opf) ||
+		bio->bi_opf & (REQ_META|REQ_PRIO) ||
+		in_use <= CUTOFF_WRITEBACK);
 }
 
 static inline void bch_writeback_queue(struct cached_dev *dc)
@@ -90,7 +92,7 @@ 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);
+		refcount_inc(&dc->count);
 
 		if (BDEV_STATE(&dc->sb) != BDEV_STATE_DIRTY) {
 			SET_BDEV_STATE(&dc->sb, BDEV_STATE_DIRTY);