Merge tag 'for-5.12/drivers-2021-02-17' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - Remove the skd driver. It's been EOL for a long time (Damien)

 - NVMe pull requests
      - fix multipath handling of ->queue_rq errors (Chao Leng)
      - nvmet cleanups (Chaitanya Kulkarni)
      - add a quirk for buggy Amazon controller (Filippo Sironi)
      - avoid devm allocations in nvme-hwmon that don't interact well
        with fabrics (Hannes Reinecke)
      - sysfs cleanups (Jiapeng Chong)
      - fix nr_zones for multipath (Keith Busch)
      - nvme-tcp crash fix for no-data commands (Sagi Grimberg)
      - nvmet-tcp fixes (Sagi Grimberg)
      - add a missing __rcu annotation (Christoph)
      - failed reconnect fixes (Chao Leng)
      - various tracing improvements (Michal Krakowiak, Johannes
        Thumshirn)
      - switch the nvmet-fc assoc_list to use RCU protection (Leonid
        Ravich)
      - resync the status codes with the latest spec (Max Gurtovoy)
      - minor nvme-tcp improvements (Sagi Grimberg)
      - various cleanups (Rikard Falkeborn, Minwoo Im, Chaitanya
        Kulkarni, Israel Rukshin)

 - Floppy O_NDELAY fix (Denis)

 - MD pull request
      - raid5 chunk_sectors fix (Guoqing)

 - Use lore links (Kees)

 - Use DEFINE_SHOW_ATTRIBUTE for nbd (Liao)

 - loop lock scaling (Pavel)

 - mtip32xx PCI fixes (Bjorn)

 - bcache fixes (Kai, Dongdong)

 - Misc fixes (Tian, Yang, Guoqing, Joe, Andy)

* tag 'for-5.12/drivers-2021-02-17' of git://git.kernel.dk/linux-block: (64 commits)
  lightnvm: pblk: Replace guid_copy() with export_guid()/import_guid()
  lightnvm: fix unnecessary NULL check warnings
  nvme-tcp: fix crash triggered with a dataless request submission
  block: Replace lkml.org links with lore
  nbd: Convert to DEFINE_SHOW_ATTRIBUTE
  nvme: add 48-bit DMA address quirk for Amazon NVMe controllers
  nvme-hwmon: rework to avoid devm allocation
  nvmet: remove else at the end of the function
  nvmet: add nvmet_req_subsys() helper
  nvmet: use min of device_path and disk len
  nvmet: use invalid cmd opcode helper
  nvmet: use invalid cmd opcode helper
  nvmet: add helper to report invalid opcode
  nvmet: remove extra variable in id-ns handler
  nvmet: make nvmet_find_namespace() req based
  nvmet: return uniform error for invalid ns
  nvmet: set status to 0 in case for invalid nsid
  nvmet-fc: add a missing __rcu annotation to nvmet_fc_tgt_assoc.queues
  nvme-multipath: set nr_zones for zoned namespaces
  nvmet-tcp: fix potential race of tcp socket closing accept_work
  ...

9 files changed, 132 insertions, 13 deletions

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 1d57f48307e6..848dd4db1659 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -373,6 +373,7 @@ struct cached_dev {
 	unsigned int		partial_stripes_expensive:1;
 	unsigned int		writeback_metadata:1;
 	unsigned int		writeback_running:1;
+	unsigned int		writeback_consider_fragment:1;
 	unsigned char		writeback_percent;
 	unsigned int		writeback_delay;
 
@@ -385,6 +386,9 @@ struct cached_dev {
 	unsigned int		writeback_rate_update_seconds;
 	unsigned int		writeback_rate_i_term_inverse;
 	unsigned int		writeback_rate_p_term_inverse;
+	unsigned int		writeback_rate_fp_term_low;
+	unsigned int		writeback_rate_fp_term_mid;
+	unsigned int		writeback_rate_fp_term_high;
 	unsigned int		writeback_rate_minimum;
 
 	enum stop_on_failure	stop_when_cache_set_failed;
@@ -1001,6 +1005,7 @@ void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent);
 
 extern struct workqueue_struct *bcache_wq;
 extern struct workqueue_struct *bch_journal_wq;
+extern struct workqueue_struct *bch_flush_wq;
 extern struct mutex bch_register_lock;
 extern struct list_head bch_cache_sets;
 
@@ -1042,5 +1047,7 @@ void bch_debug_exit(void);
 void bch_debug_init(void);
 void bch_request_exit(void);
 int bch_request_init(void);
+void bch_btree_exit(void);
+int bch_btree_init(void);
 
 #endif /* _BCACHE_H */
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 67a2c47f4201..94d38e8a59b3 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -712,8 +712,10 @@ void bch_bset_build_written_tree(struct btree_keys *b)
 	for (j = inorder_next(0, t->size);
 	     j;
 	     j = inorder_next(j, t->size)) {
-		while (bkey_to_cacheline(t, k) < cacheline)
-			prev = k, k = bkey_next(k);
+		while (bkey_to_cacheline(t, k) < cacheline) {
+			prev = k;
+			k = bkey_next(k);
+		}
 
 		t->prev[j] = bkey_u64s(prev);
 		t->tree[j].m = bkey_to_cacheline_offset(t, cacheline++, k);
@@ -901,8 +903,10 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	status = BTREE_INSERT_STATUS_INSERT;
 
 	while (m != bset_bkey_last(i) &&
-	       bkey_cmp(k, b->ops->is_extents ? &START_KEY(m) : m) > 0)
-		prev = m, m = bkey_next(m);
+	       bkey_cmp(k, b->ops->is_extents ? &START_KEY(m) : m) > 0) {
+		prev = m;
+		m = bkey_next(m);
+	}
 
 	/* prev is in the tree, if we merge we're done */
 	status = BTREE_INSERT_STATUS_BACK_MERGE;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 910df242c83d..fe6dce125aba 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -99,6 +99,8 @@
 #define PTR_HASH(c, k)							\
 	(((k)->ptr[0] >> c->bucket_bits) | PTR_GEN(k, 0))
 
+static struct workqueue_struct *btree_io_wq;
+
 #define insert_lock(s, b)	((b)->level <= (s)->lock)
 
 
@@ -308,7 +310,7 @@ static void __btree_node_write_done(struct closure *cl)
 	btree_complete_write(b, w);
 
 	if (btree_node_dirty(b))
-		schedule_delayed_work(&b->work, 30 * HZ);
+		queue_delayed_work(btree_io_wq, &b->work, 30 * HZ);
 
 	closure_return_with_destructor(cl, btree_node_write_unlock);
 }
@@ -481,7 +483,7 @@ static void bch_btree_leaf_dirty(struct btree *b, atomic_t *journal_ref)
 	BUG_ON(!i->keys);
 
 	if (!btree_node_dirty(b))
-		schedule_delayed_work(&b->work, 30 * HZ);
+		queue_delayed_work(btree_io_wq, &b->work, 30 * HZ);
 
 	set_btree_node_dirty(b);
 
@@ -2764,3 +2766,18 @@ void bch_keybuf_init(struct keybuf *buf)
 	spin_lock_init(&buf->lock);
 	array_allocator_init(&buf->freelist);
 }
+
+void bch_btree_exit(void)
+{
+	if (btree_io_wq)
+		destroy_workqueue(btree_io_wq);
+}
+
+int __init bch_btree_init(void)
+{
+	btree_io_wq = alloc_workqueue("bch_btree_io", WQ_MEM_RECLAIM, 0);
+	if (!btree_io_wq)
+		return -ENOMEM;
+
+	return 0;
+}
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index aefbdb7e003b..c6613e817333 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -932,8 +932,8 @@ atomic_t *bch_journal(struct cache_set *c,
 		journal_try_write(c);
 	} else if (!w->dirty) {
 		w->dirty = true;
-		schedule_delayed_work(&c->journal.work,
-				      msecs_to_jiffies(c->journal_delay_ms));
+		queue_delayed_work(bch_flush_wq, &c->journal.work,
+				   msecs_to_jiffies(c->journal_delay_ms));
 		spin_unlock(&c->journal.lock);
 	} else {
 		spin_unlock(&c->journal.lock);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 193fe7652329..71691f32959b 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -49,6 +49,7 @@ static int bcache_major;
 static DEFINE_IDA(bcache_device_idx);
 static wait_queue_head_t unregister_wait;
 struct workqueue_struct *bcache_wq;
+struct workqueue_struct *bch_flush_wq;
 struct workqueue_struct *bch_journal_wq;
 
 
@@ -2517,7 +2518,7 @@ out:
 	module_put(THIS_MODULE);
 }
 
-static void register_device_aync(struct async_reg_args *args)
+static void register_device_async(struct async_reg_args *args)
 {
 	if (SB_IS_BDEV(args->sb))
 		INIT_DELAYED_WORK(&args->reg_work, register_bdev_worker);
@@ -2611,7 +2612,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 		args->sb	= sb;
 		args->sb_disk	= sb_disk;
 		args->bdev	= bdev;
-		register_device_aync(args);
+		register_device_async(args);
 		/* No wait and returns to user space */
 		goto async_done;
 	}
@@ -2821,6 +2822,9 @@ static void bcache_exit(void)
 		destroy_workqueue(bcache_wq);
 	if (bch_journal_wq)
 		destroy_workqueue(bch_journal_wq);
+	if (bch_flush_wq)
+		destroy_workqueue(bch_flush_wq);
+	bch_btree_exit();
 
 	if (bcache_major)
 		unregister_blkdev(bcache_major, "bcache");
@@ -2876,10 +2880,26 @@ static int __init bcache_init(void)
 		return bcache_major;
 	}
 
+	if (bch_btree_init())
+		goto err;
+
 	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
 	if (!bcache_wq)
 		goto err;
 
+	/*
+	 * Let's not make this `WQ_MEM_RECLAIM` for the following reasons:
+	 *
+	 * 1. It used `system_wq` before which also does no memory reclaim.
+	 * 2. With `WQ_MEM_RECLAIM` desktop stalls, increased boot times, and
+	 *    reduced throughput can be observed.
+	 *
+	 * We still want to user our own queue to not congest the `system_wq`.
+	 */
+	bch_flush_wq = alloc_workqueue("bch_flush", 0, 0);
+	if (!bch_flush_wq)
+		goto err;
+
 	bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0);
 	if (!bch_journal_wq)
 		goto err;
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 00a520c03f41..cc89f3156d1a 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -117,10 +117,14 @@ rw_attribute(writeback_running);
 rw_attribute(writeback_percent);
 rw_attribute(writeback_delay);
 rw_attribute(writeback_rate);
+rw_attribute(writeback_consider_fragment);
 
 rw_attribute(writeback_rate_update_seconds);
 rw_attribute(writeback_rate_i_term_inverse);
 rw_attribute(writeback_rate_p_term_inverse);
+rw_attribute(writeback_rate_fp_term_low);
+rw_attribute(writeback_rate_fp_term_mid);
+rw_attribute(writeback_rate_fp_term_high);
 rw_attribute(writeback_rate_minimum);
 read_attribute(writeback_rate_debug);
 
@@ -195,6 +199,7 @@ SHOW(__bch_cached_dev)
 	var_printf(bypass_torture_test,	"%i");
 	var_printf(writeback_metadata,	"%i");
 	var_printf(writeback_running,	"%i");
+	var_printf(writeback_consider_fragment,	"%i");
 	var_print(writeback_delay);
 	var_print(writeback_percent);
 	sysfs_hprint(writeback_rate,
@@ -205,6 +210,9 @@ SHOW(__bch_cached_dev)
 	var_print(writeback_rate_update_seconds);
 	var_print(writeback_rate_i_term_inverse);
 	var_print(writeback_rate_p_term_inverse);
+	var_print(writeback_rate_fp_term_low);
+	var_print(writeback_rate_fp_term_mid);
+	var_print(writeback_rate_fp_term_high);
 	var_print(writeback_rate_minimum);
 
 	if (attr == &sysfs_writeback_rate_debug) {
@@ -303,6 +311,7 @@ STORE(__cached_dev)
 	sysfs_strtoul_bool(bypass_torture_test, dc->bypass_torture_test);
 	sysfs_strtoul_bool(writeback_metadata, dc->writeback_metadata);
 	sysfs_strtoul_bool(writeback_running, dc->writeback_running);
+	sysfs_strtoul_bool(writeback_consider_fragment, dc->writeback_consider_fragment);
 	sysfs_strtoul_clamp(writeback_delay, dc->writeback_delay, 0, UINT_MAX);
 
 	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent,
@@ -331,6 +340,16 @@ STORE(__cached_dev)
 	sysfs_strtoul_clamp(writeback_rate_p_term_inverse,
 			    dc->writeback_rate_p_term_inverse,
 			    1, UINT_MAX);
+	sysfs_strtoul_clamp(writeback_rate_fp_term_low,
+			    dc->writeback_rate_fp_term_low,
+			    1, dc->writeback_rate_fp_term_mid - 1);
+	sysfs_strtoul_clamp(writeback_rate_fp_term_mid,
+			    dc->writeback_rate_fp_term_mid,
+			    dc->writeback_rate_fp_term_low + 1,
+			    dc->writeback_rate_fp_term_high - 1);
+	sysfs_strtoul_clamp(writeback_rate_fp_term_high,
+			    dc->writeback_rate_fp_term_high,
+			    dc->writeback_rate_fp_term_mid + 1, UINT_MAX);
 	sysfs_strtoul_clamp(writeback_rate_minimum,
 			    dc->writeback_rate_minimum,
 			    1, UINT_MAX);
@@ -499,9 +518,13 @@ static struct attribute *bch_cached_dev_files[] = {
 	&sysfs_writeback_delay,
 	&sysfs_writeback_percent,
 	&sysfs_writeback_rate,
+	&sysfs_writeback_consider_fragment,
 	&sysfs_writeback_rate_update_seconds,
 	&sysfs_writeback_rate_i_term_inverse,
 	&sysfs_writeback_rate_p_term_inverse,
+	&sysfs_writeback_rate_fp_term_low,
+	&sysfs_writeback_rate_fp_term_mid,
+	&sysfs_writeback_rate_fp_term_high,
 	&sysfs_writeback_rate_minimum,
 	&sysfs_writeback_rate_debug,
 	&sysfs_io_errors,
@@ -1071,8 +1094,10 @@ SHOW(__bch_cache)
 			--n;
 
 		while (cached < p + n &&
-		       *cached == BTREE_PRIO)
-			cached++, n--;
+		       *cached == BTREE_PRIO) {
+			cached++;
+			n--;
+		}
 
 		for (i = 0; i < n; i++)
 			sum += INITIAL_PRIO - cached[i];
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index a129e4d2707c..82d4e0880a99 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -88,6 +88,44 @@ static void __update_writeback_rate(struct cached_dev *dc)
 	int64_t integral_scaled;
 	uint32_t new_rate;
 
+	/*
+	 * We need to consider the number of dirty buckets as well
+	 * when calculating the proportional_scaled, Otherwise we might
+	 * have an unreasonable small writeback rate at a highly fragmented situation
+	 * when very few dirty sectors consumed a lot dirty buckets, the
+	 * worst case is when dirty buckets reached cutoff_writeback_sync and
+	 * dirty data is still not even reached to writeback percent, so the rate
+	 * still will be at the minimum value, which will cause the write
+	 * stuck at a non-writeback mode.
+	 */
+	struct cache_set *c = dc->disk.c;
+
+	int64_t dirty_buckets = c->nbuckets - c->avail_nbuckets;
+
+	if (dc->writeback_consider_fragment &&
+		c->gc_stats.in_use > BCH_WRITEBACK_FRAGMENT_THRESHOLD_LOW && dirty > 0) {
+		int64_t fragment =
+			div_s64((dirty_buckets *  c->cache->sb.bucket_size), dirty);
+		int64_t fp_term;
+		int64_t fps;
+
+		if (c->gc_stats.in_use <= BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID) {
+			fp_term = dc->writeback_rate_fp_term_low *
+			(c->gc_stats.in_use - BCH_WRITEBACK_FRAGMENT_THRESHOLD_LOW);
+		} else if (c->gc_stats.in_use <= BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH) {
+			fp_term = dc->writeback_rate_fp_term_mid *
+			(c->gc_stats.in_use - BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID);
+		} else {
+			fp_term = dc->writeback_rate_fp_term_high *
+			(c->gc_stats.in_use - BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH);
+		}
+		fps = div_s64(dirty, dirty_buckets) * fp_term;
+		if (fragment > 3 && fps > proportional_scaled) {
+			/* Only overrite the p when fragment > 3 */
+			proportional_scaled = fps;
+		}
+	}
+
 	if ((error < 0 && dc->writeback_rate_integral > 0) ||
 	    (error > 0 && time_before64(local_clock(),
 			 dc->writeback_rate.next + NSEC_PER_MSEC))) {
@@ -977,6 +1015,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 
 	dc->writeback_metadata		= true;
 	dc->writeback_running		= false;
+	dc->writeback_consider_fragment = true;
 	dc->writeback_percent		= 10;
 	dc->writeback_delay		= 30;
 	atomic_long_set(&dc->writeback_rate.rate, 1024);
@@ -984,6 +1023,9 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 
 	dc->writeback_rate_update_seconds = WRITEBACK_RATE_UPDATE_SECS_DEFAULT;
 	dc->writeback_rate_p_term_inverse = 40;
+	dc->writeback_rate_fp_term_low = 1;
+	dc->writeback_rate_fp_term_mid = 10;
+	dc->writeback_rate_fp_term_high = 1000;
 	dc->writeback_rate_i_term_inverse = 10000;
 
 	WARN_ON(test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags));
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 3f1230e22de0..02b2f9df73f6 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -16,6 +16,10 @@
 
 #define BCH_AUTO_GC_DIRTY_THRESHOLD	50
 
+#define BCH_WRITEBACK_FRAGMENT_THRESHOLD_LOW 50
+#define BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID 57
+#define BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH 64
+
 #define BCH_DIRTY_INIT_THRD_MAX	64
 /*
  * 14 (16384ths) is chosen here as something that each backing device
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index a348b2adf2a9..5d57a5bd171f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7643,7 +7643,7 @@ static int raid5_run(struct mddev *mddev)
 	}
 
 	/* device size must be a multiple of chunk size */
-	mddev->dev_sectors &= ~(mddev->chunk_sectors - 1);
+	mddev->dev_sectors &= ~((sector_t)mddev->chunk_sectors - 1);
 	mddev->resync_max_sectors = mddev->dev_sectors;
 
 	if (mddev->degraded > dirty_parity_disks &&