Merge tag 'for-5.5/drivers-20191121' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Here are the main block driver updates for 5.5. Nothing major in here,
  mostly just fixes. This contains:

   - a set of bcache changes via Coly

   - MD changes from Song

   - loop unmap write-zeroes fix (Darrick)

   - spelling fixes (Geert)

   - zoned additions cleanups to null_blk/dm (Ajay)

   - allow null_blk online submit queue changes (Bart)

   - NVMe changes via Keith, nothing major here either"

* tag 'for-5.5/drivers-20191121' of git://git.kernel.dk/linux-block: (56 commits)
  Revert "bcache: fix fifo index swapping condition in journal_pin_cmp()"
  drivers/md/raid5-ppl.c: use the new spelling of RWH_WRITE_LIFE_NOT_SET
  drivers/md/raid5.c: use the new spelling of RWH_WRITE_LIFE_NOT_SET
  bcache: don't export symbols
  bcache: remove the extra cflags for request.o
  bcache: at least try to shrink 1 node in bch_mca_scan()
  bcache: add idle_max_writeback_rate sysfs interface
  bcache: add code comments in bch_btree_leaf_dirty()
  bcache: fix deadlock in bcache_allocator
  bcache: add code comment bch_keylist_pop() and bch_keylist_pop_front()
  bcache: deleted code comments for dead code in bch_data_insert_keys()
  bcache: add more accurate error messages in read_super()
  bcache: fix static checker warning in bcache_device_free()
  bcache: fix a lost wake-up problem caused by mca_cannibalize_lock
  bcache: fix fifo index swapping condition in journal_pin_cmp()
  md/raid10: prevent access of uninitialized resync_pages offset
  md: avoid invalid memory access for array sb->dev_roles
  md/raid1: avoid soft lockup under high load
  null_blk: add zone open, close, and finish support
  dm: add zone open, close and finish support
  ...

drivers/block/loop.c

@@ -417,18 +417,20 @@ static int lo_read_transfer(struct loop_device *lo, struct request *rq,
 	return ret;
 }
 
-static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos)
+static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
+			int mode)
 {
 	/*
-	 * We use punch hole to reclaim the free space used by the
-	 * image a.k.a. discard. However we do not support discard if
-	 * encryption is enabled, because it may give an attacker
-	 * useful information.
+	 * We use fallocate to manipulate the space mappings used by the image
+	 * a.k.a. discard/zerorange. However we do not support this if
+	 * encryption is enabled, because it may give an attacker useful
+	 * information.
 	 */
 	struct file *file = lo->lo_backing_file;
-	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	int ret;
 
+	mode |= FALLOC_FL_KEEP_SIZE;
+
 	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
 		ret = -EOPNOTSUPP;
 		goto out;
@@ -596,9 +598,17 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	switch (req_op(rq)) {
 	case REQ_OP_FLUSH:
 		return lo_req_flush(lo, rq);
-	case REQ_OP_DISCARD:
 	case REQ_OP_WRITE_ZEROES:
-		return lo_discard(lo, rq, pos);
+		/*
+		 * If the caller doesn't want deallocation, call zeroout to
+		 * write zeroes the range.  Otherwise, punch them out.
+		 */
+		return lo_fallocate(lo, rq, pos,
+			(rq->cmd_flags & REQ_NOUNMAP) ?
+				FALLOC_FL_ZERO_RANGE :
+				FALLOC_FL_PUNCH_HOLE);
+	case REQ_OP_DISCARD:
+		return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
 	case REQ_OP_WRITE:
 		if (lo->transfer)
 			return lo_write_transfer(lo, rq, pos);

drivers/block/mtip32xx/mtip32xx.c

@@ -129,7 +129,7 @@ struct mtip_compat_ide_task_request_s {
 /*
  * This function check_for_surprise_removal is called
  * while card is removed from the system and it will
- * read the vendor id from the configration space
+ * read the vendor id from the configuration space
  *
  * @pdev Pointer to the pci_dev structure.
  *

drivers/block/null_blk.h

@@ -96,6 +96,8 @@ int null_zone_report(struct gendisk *disk, sector_t sector,
 blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
 				enum req_opf op, sector_t sector,
 				sector_t nr_sectors);
+size_t null_zone_valid_read_len(struct nullb *nullb,
+				sector_t sector, unsigned int len);
 #else
 static inline int null_zone_init(struct nullb_device *dev)
 {
@@ -115,5 +117,11 @@ static inline blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
 {
 	return BLK_STS_NOTSUPP;
 }
+static inline size_t null_zone_valid_read_len(struct nullb *nullb,
+					      sector_t sector,
+					      unsigned int len)
+{
+	return len;
+}
 #endif /* CONFIG_BLK_DEV_ZONED */
 #endif /* __NULL_BLK_H */

drivers/block/null_blk_main.c

@@ -227,7 +227,7 @@ static ssize_t nullb_device_uint_attr_store(unsigned int *val,
 	int result;
 
 	result = kstrtouint(page, 0, &tmp);
-	if (result)
+	if (result < 0)
 		return result;
 
 	*val = tmp;
@@ -241,7 +241,7 @@ static ssize_t nullb_device_ulong_attr_store(unsigned long *val,
 	unsigned long tmp;
 
 	result = kstrtoul(page, 0, &tmp);
-	if (result)
+	if (result < 0)
 		return result;
 
 	*val = tmp;
@@ -255,15 +255,15 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page,
 	int result;
 
 	result = kstrtobool(page,  &tmp);
-	if (result)
+	if (result < 0)
 		return result;
 
 	*val = tmp;
 	return count;
 }
 
 /* The following macro should only be used with TYPE = {uint, ulong, bool}. */
-#define NULLB_DEVICE_ATTR(NAME, TYPE)						\
+#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY)					\
 static ssize_t									\
 nullb_device_##NAME##_show(struct config_item *item, char *page)		\
 {										\
@@ -274,31 +274,57 @@ static ssize_t									\
 nullb_device_##NAME##_store(struct config_item *item, const char *page,		\
 			    size_t count)					\
 {										\
-	if (test_bit(NULLB_DEV_FL_CONFIGURED, &to_nullb_device(item)->flags))	\
-		return -EBUSY;							\
-	return nullb_device_##TYPE##_attr_store(				\
-			&to_nullb_device(item)->NAME, page, count);		\
+	int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY;	\
+	struct nullb_device *dev = to_nullb_device(item);			\
+	TYPE new_value;								\
+	int ret;								\
+										\
+	ret = nullb_device_##TYPE##_attr_store(&new_value, page, count);	\
+	if (ret < 0)								\
+		return ret;							\
+	if (apply_fn)								\
+		ret = apply_fn(dev, new_value);					\
+	else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) 		\
+		ret = -EBUSY;							\
+	if (ret < 0)								\
+		return ret;							\
+	dev->NAME = new_value;							\
+	return count;								\
 }										\
 CONFIGFS_ATTR(nullb_device_, NAME);
 
-NULLB_DEVICE_ATTR(size, ulong);
-NULLB_DEVICE_ATTR(completion_nsec, ulong);
-NULLB_DEVICE_ATTR(submit_queues, uint);
-NULLB_DEVICE_ATTR(home_node, uint);
-NULLB_DEVICE_ATTR(queue_mode, uint);
-NULLB_DEVICE_ATTR(blocksize, uint);
-NULLB_DEVICE_ATTR(irqmode, uint);
-NULLB_DEVICE_ATTR(hw_queue_depth, uint);
-NULLB_DEVICE_ATTR(index, uint);
-NULLB_DEVICE_ATTR(blocking, bool);
-NULLB_DEVICE_ATTR(use_per_node_hctx, bool);
-NULLB_DEVICE_ATTR(memory_backed, bool);
-NULLB_DEVICE_ATTR(discard, bool);
-NULLB_DEVICE_ATTR(mbps, uint);
-NULLB_DEVICE_ATTR(cache_size, ulong);
-NULLB_DEVICE_ATTR(zoned, bool);
-NULLB_DEVICE_ATTR(zone_size, ulong);
-NULLB_DEVICE_ATTR(zone_nr_conv, uint);
+static int nullb_apply_submit_queues(struct nullb_device *dev,
+				     unsigned int submit_queues)
+{
+	struct nullb *nullb = dev->nullb;
+	struct blk_mq_tag_set *set;
+
+	if (!nullb)
+		return 0;
+
+	set = nullb->tag_set;
+	blk_mq_update_nr_hw_queues(set, submit_queues);
+	return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM;
+}
+
+NULLB_DEVICE_ATTR(size, ulong, NULL);
+NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL);
+NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues);
+NULLB_DEVICE_ATTR(home_node, uint, NULL);
+NULLB_DEVICE_ATTR(queue_mode, uint, NULL);
+NULLB_DEVICE_ATTR(blocksize, uint, NULL);
+NULLB_DEVICE_ATTR(irqmode, uint, NULL);
+NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL);
+NULLB_DEVICE_ATTR(index, uint, NULL);
+NULLB_DEVICE_ATTR(blocking, bool, NULL);
+NULLB_DEVICE_ATTR(use_per_node_hctx, bool, NULL);
+NULLB_DEVICE_ATTR(memory_backed, bool, NULL);
+NULLB_DEVICE_ATTR(discard, bool, NULL);
+NULLB_DEVICE_ATTR(mbps, uint, NULL);
+NULLB_DEVICE_ATTR(cache_size, ulong, NULL);
+NULLB_DEVICE_ATTR(zoned, bool, NULL);
+NULLB_DEVICE_ATTR(zone_size, ulong, NULL);
+NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -996,6 +1022,16 @@ static int copy_from_nullb(struct nullb *nullb, struct page *dest,
 	return 0;
 }
 
+static void nullb_fill_pattern(struct nullb *nullb, struct page *page,
+			       unsigned int len, unsigned int off)
+{
+	void *dst;
+
+	dst = kmap_atomic(page);
+	memset(dst + off, 0xFF, len);
+	kunmap_atomic(dst);
+}
+
 static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n)
 {
 	size_t temp;
@@ -1036,10 +1072,24 @@ static int null_transfer(struct nullb *nullb, struct page *page,
 	unsigned int len, unsigned int off, bool is_write, sector_t sector,
 	bool is_fua)
 {
+	struct nullb_device *dev = nullb->dev;
+	unsigned int valid_len = len;
 	int err = 0;
 
 	if (!is_write) {
-		err = copy_from_nullb(nullb, page, off, sector, len);
+		if (dev->zoned)
+			valid_len = null_zone_valid_read_len(nullb,
+				sector, len);
+
+		if (valid_len) {
+			err = copy_from_nullb(nullb, page, off,
+				sector, valid_len);
+			off += valid_len;
+			len -= valid_len;
+		}
+
+		if (len)
+			nullb_fill_pattern(nullb, page, len, off);
 		flush_dcache_page(page);
 	} else {
 		flush_dcache_page(page);

drivers/block/null_blk_zoned.c

@@ -84,6 +84,24 @@ int null_zone_report(struct gendisk *disk, sector_t sector,
 	return 0;
 }
 
+size_t null_zone_valid_read_len(struct nullb *nullb,
+				sector_t sector, unsigned int len)
+{
+	struct nullb_device *dev = nullb->dev;
+	struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
+	unsigned int nr_sectors = len >> SECTOR_SHIFT;
+
+	/* Read must be below the write pointer position */
+	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL ||
+	    sector + nr_sectors <= zone->wp)
+		return len;
+
+	if (sector > zone->wp)
+		return 0;
+
+	return (zone->wp - sector) << SECTOR_SHIFT;
+}
+
 static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 		     unsigned int nr_sectors)
 {
@@ -118,14 +136,14 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	return BLK_STS_OK;
 }
 
-static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
+static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
+				   sector_t sector)
 {
 	struct nullb_device *dev = cmd->nq->dev;
-	unsigned int zno = null_zone_no(dev, sector);
-	struct blk_zone *zone = &dev->zones[zno];
+	struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
 	size_t i;
 
-	switch (req_op(cmd->rq)) {
+	switch (op) {
 	case REQ_OP_ZONE_RESET_ALL:
 		for (i = 0; i < dev->nr_zones; i++) {
 			if (zone[i].type == BLK_ZONE_TYPE_CONVENTIONAL)
@@ -141,6 +159,29 @@ static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
 		zone->cond = BLK_ZONE_COND_EMPTY;
 		zone->wp = zone->start;
 		break;
+	case REQ_OP_ZONE_OPEN:
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			return BLK_STS_IOERR;
+		if (zone->cond == BLK_ZONE_COND_FULL)
+			return BLK_STS_IOERR;
+
+		zone->cond = BLK_ZONE_COND_EXP_OPEN;
+		break;
+	case REQ_OP_ZONE_CLOSE:
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			return BLK_STS_IOERR;
+		if (zone->cond == BLK_ZONE_COND_FULL)
+			return BLK_STS_IOERR;
+
+		zone->cond = BLK_ZONE_COND_CLOSED;
+		break;
+	case REQ_OP_ZONE_FINISH:
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			return BLK_STS_IOERR;
+
+		zone->cond = BLK_ZONE_COND_FULL;
+		zone->wp = zone->start + zone->len;
+		break;
 	default:
 		return BLK_STS_NOTSUPP;
 	}
@@ -155,7 +196,10 @@ blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op,
 		return null_zone_write(cmd, sector, nr_sectors);
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_RESET_ALL:
-		return null_zone_reset(cmd, sector);
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
+		return null_zone_mgmt(cmd, op, sector);
 	default:
 		return BLK_STS_OK;
 	}

drivers/md/bcache/Makefile

@@ -5,5 +5,3 @@ obj-$(CONFIG_BCACHE)	+= bcache.o
 bcache-y		:= alloc.o bset.o btree.o closure.o debug.o extents.o\
 	io.o journal.o movinggc.o request.o stats.o super.o sysfs.o trace.o\
 	util.o writeback.o
-
-CFLAGS_request.o	+= -Iblock

drivers/md/bcache/alloc.c

@@ -377,7 +377,10 @@ static int bch_allocator_thread(void *arg)
 			if (!fifo_full(&ca->free_inc))
 				goto retry_invalidate;
 
-			bch_prio_write(ca);
+			if (bch_prio_write(ca, false) < 0) {
+				ca->invalidate_needs_gc = 1;
+				wake_up_gc(ca->set);
+			}
 		}
 	}
 out:

drivers/md/bcache/bcache.h

@@ -582,6 +582,7 @@ struct cache_set {
 	 */
 	wait_queue_head_t	btree_cache_wait;
 	struct task_struct	*btree_cache_alloc_lock;
+	spinlock_t		btree_cannibalize_lock;
 
 	/*
 	 * When we free a btree node, we increment the gen of the bucket the
@@ -723,6 +724,7 @@ struct cache_set {
 	unsigned int		gc_always_rewrite:1;
 	unsigned int		shrinker_disabled:1;
 	unsigned int		copy_gc_enabled:1;
+	unsigned int		idle_max_writeback_rate_enabled:1;
 
 #define BUCKET_HASH_BITS	12
 	struct hlist_head	bucket_hash[1 << BUCKET_HASH_BITS];
@@ -977,7 +979,7 @@ bool bch_cached_dev_error(struct cached_dev *dc);
 __printf(2, 3)
 bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...);
 
-void bch_prio_write(struct cache *ca);
+int bch_prio_write(struct cache *ca, bool wait);
 void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent);
 
 extern struct workqueue_struct *bcache_wq;