Merge tag 'block-5.10-2020-10-30' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - null_blk zone fixes (Damien, Kanchan)

 - NVMe pull request from Christoph:
       - improve zone revalidation (Keith Busch)
       - gracefully handle zero length messages in nvme-rdma (zhenwei pi)
       - nvme-fc error handling fixes (James Smart)
       - nvmet tracing NULL pointer dereference fix (Chaitanya Kulkarni)"

 - xsysace platform fixes (Andy)

 - scatterlist type cleanup (David)

 - blk-cgroup memory fixes (Gabriel)

 - nbd block size update fix (Ming)

 - Flush completion state fix (Ming)

 - bio_add_hw_page() iteration fix (Naohiro)

* tag 'block-5.10-2020-10-30' of git://git.kernel.dk/linux-block:
  blk-mq: mark flush request as IDLE in flush_end_io()
  lib/scatterlist: use consistent sg_copy_buffer() return type
  xsysace: use platform_get_resource() and platform_get_irq_optional()
  null_blk: Fix locking in zoned mode
  null_blk: Fix zone reset all tracing
  nbd: don't update block size after device is started
  block: advance iov_iter on bio_add_hw_page failure
  null_blk: synchronization fix for zoned device
  nvmet: fix a NULL pointer dereference when tracing the flush command
  nvme-fc: remove nvme_fc_terminate_io()
  nvme-fc: eliminate terminate_io use by nvme_fc_error_recovery
  nvme-fc: remove err_work work item
  nvme-fc: track error_recovery while connecting
  nvme-rdma: handle unexpected nvme completion data length
  nvme: ignore zone validate errors on subsequent scans
  blk-cgroup: Pre-allocate tree node on blkg_conf_prep
  blk-cgroup: Fix memleak on error path

Author: torvalds

block/bio.c

@@ -1044,6 +1044,7 @@ static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
 	ssize_t size, left;
 	unsigned len, i;
 	size_t offset;
+	int ret = 0;
 
 	if (WARN_ON_ONCE(!max_append_sectors))
 		return 0;
@@ -1066,15 +1067,17 @@ static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
 
 		len = min_t(size_t, PAGE_SIZE - offset, left);
 		if (bio_add_hw_page(q, bio, page, len, offset,
-				max_append_sectors, &same_page) != len)
-			return -EINVAL;
+				max_append_sectors, &same_page) != len) {
+			ret = -EINVAL;
+			break;
+		}
 		if (same_page)
 			put_page(page);
 		offset = 0;
 	}
 
-	iov_iter_advance(iter, size);
-	return 0;
+	iov_iter_advance(iter, size - left);
+	return ret;
 }
 
 /**

block/blk-cgroup.c

@@ -657,13 +657,20 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 			goto fail;
 		}
 
+		if (radix_tree_preload(GFP_KERNEL)) {
+			blkg_free(new_blkg);
+			ret = -ENOMEM;
+			goto fail;
+		}
+
 		rcu_read_lock();
 		spin_lock_irq(&q->queue_lock);
 
 		blkg = blkg_lookup_check(pos, pol, q);
 		if (IS_ERR(blkg)) {
 			ret = PTR_ERR(blkg);
-			goto fail_unlock;
+			blkg_free(new_blkg);
+			goto fail_preloaded;
 		}
 
 		if (blkg) {
@@ -672,10 +679,12 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 			blkg = blkg_create(pos, q, new_blkg);
 			if (IS_ERR(blkg)) {
 				ret = PTR_ERR(blkg);
-				goto fail_unlock;
+				goto fail_preloaded;
 			}
 		}
 
+		radix_tree_preload_end();
+
 		if (pos == blkcg)
 			goto success;
 	}
@@ -685,6 +694,8 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	ctx->body = input;
 	return 0;
 
+fail_preloaded:
+	radix_tree_preload_end();
 fail_unlock:
 	spin_unlock_irq(&q->queue_lock);
 	rcu_read_unlock();

block/blk-flush.c

@@ -225,6 +225,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	/* release the tag's ownership to the req cloned from */
 	spin_lock_irqsave(&fq->mq_flush_lock, flags);
 
+	WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE);
 	if (!refcount_dec_and_test(&flush_rq->ref)) {
 		fq->rq_status = error;
 		spin_unlock_irqrestore(&fq->mq_flush_lock, flags);

drivers/block/nbd.c

@@ -296,7 +296,7 @@ static void nbd_size_clear(struct nbd_device *nbd)
 	}
 }
 
-static void nbd_size_update(struct nbd_device *nbd)
+static void nbd_size_update(struct nbd_device *nbd, bool start)
 {
 	struct nbd_config *config = nbd->config;
 	struct block_device *bdev = bdget_disk(nbd->disk, 0);
@@ -313,7 +313,8 @@ static void nbd_size_update(struct nbd_device *nbd)
 	if (bdev) {
 		if (bdev->bd_disk) {
 			bd_set_nr_sectors(bdev, nr_sectors);
-			set_blocksize(bdev, config->blksize);
+			if (start)
+				set_blocksize(bdev, config->blksize);
 		} else
 			set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
 		bdput(bdev);
@@ -328,7 +329,7 @@ static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize,
 	config->blksize = blocksize;
 	config->bytesize = blocksize * nr_blocks;
 	if (nbd->task_recv != NULL)
-		nbd_size_update(nbd);
+		nbd_size_update(nbd, false);
 }
 
 static void nbd_complete_rq(struct request *req)
@@ -1308,7 +1309,7 @@ static int nbd_start_device(struct nbd_device *nbd)
 		args->index = i;
 		queue_work(nbd->recv_workq, &args->work);
 	}
-	nbd_size_update(nbd);
+	nbd_size_update(nbd, true);
 	return error;
 }
 

drivers/block/null_blk.h

@@ -47,6 +47,8 @@ struct nullb_device {
 	unsigned int nr_zones_closed;
 	struct blk_zone *zones;
 	sector_t zone_size_sects;
+	spinlock_t zone_dev_lock;
+	unsigned long *zone_locks;
 
 	unsigned long size; /* device size in MB */
 	unsigned long completion_nsec; /* time in ns to complete a request */

drivers/block/null_blk_zoned.c

@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/vmalloc.h>
+#include <linux/bitmap.h>
 #include "null_blk.h"
 
 #define CREATE_TRACE_POINTS
@@ -45,6 +46,13 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 	if (!dev->zones)
 		return -ENOMEM;
 
+	spin_lock_init(&dev->zone_dev_lock);
+	dev->zone_locks = bitmap_zalloc(dev->nr_zones, GFP_KERNEL);
+	if (!dev->zone_locks) {
+		kvfree(dev->zones);
+		return -ENOMEM;
+	}
+
 	if (dev->zone_nr_conv >= dev->nr_zones) {
 		dev->zone_nr_conv = dev->nr_zones - 1;
 		pr_info("changed the number of conventional zones to %u",
@@ -123,15 +131,26 @@ int null_register_zoned_dev(struct nullb *nullb)
 
 void null_free_zoned_dev(struct nullb_device *dev)
 {
+	bitmap_free(dev->zone_locks);
 	kvfree(dev->zones);
 }
 
+static inline void null_lock_zone(struct nullb_device *dev, unsigned int zno)
+{
+	wait_on_bit_lock_io(dev->zone_locks, zno, TASK_UNINTERRUPTIBLE);
+}
+
+static inline void null_unlock_zone(struct nullb_device *dev, unsigned int zno)
+{
+	clear_and_wake_up_bit(zno, dev->zone_locks);
+}
+
 int null_report_zones(struct gendisk *disk, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data)
 {
 	struct nullb *nullb = disk->private_data;
 	struct nullb_device *dev = nullb->dev;
-	unsigned int first_zone, i;
+	unsigned int first_zone, i, zno;
 	struct blk_zone zone;
 	int error;
 
@@ -142,15 +161,18 @@ int null_report_zones(struct gendisk *disk, sector_t sector,
 	nr_zones = min(nr_zones, dev->nr_zones - first_zone);
 	trace_nullb_report_zones(nullb, nr_zones);
 
-	for (i = 0; i < nr_zones; i++) {
+	zno = first_zone;
+	for (i = 0; i < nr_zones; i++, zno++) {
 		/*
 		 * Stacked DM target drivers will remap the zone information by
 		 * modifying the zone information passed to the report callback.
 		 * So use a local copy to avoid corruption of the device zone
 		 * array.
 		 */
-		memcpy(&zone, &dev->zones[first_zone + i],
-		       sizeof(struct blk_zone));
+		null_lock_zone(dev, zno);
+		memcpy(&zone, &dev->zones[zno], sizeof(struct blk_zone));
+		null_unlock_zone(dev, zno);
+
 		error = cb(&zone, i, data);
 		if (error)
 			return error;
@@ -159,6 +181,10 @@ int null_report_zones(struct gendisk *disk, sector_t sector,
 	return nr_zones;
 }
 
+/*
+ * This is called in the case of memory backing from null_process_cmd()
+ * with the target zone already locked.
+ */
 size_t null_zone_valid_read_len(struct nullb *nullb,
 				sector_t sector, unsigned int len)
 {
@@ -295,22 +321,27 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
 
+	null_lock_zone(dev, zno);
+	spin_lock(&dev->zone_dev_lock);
+
 	switch (zone->cond) {
 	case BLK_ZONE_COND_FULL:
 		/* Cannot write to a full zone */
-		return BLK_STS_IOERR;
+		ret = BLK_STS_IOERR;
+		goto unlock;
 	case BLK_ZONE_COND_EMPTY:
 	case BLK_ZONE_COND_CLOSED:
 		ret = null_check_zone_resources(dev, zone);
 		if (ret != BLK_STS_OK)
-			return ret;
+			goto unlock;
 		break;
 	case BLK_ZONE_COND_IMP_OPEN:
 	case BLK_ZONE_COND_EXP_OPEN:
 		break;
 	default:
 		/* Invalid zone condition */
-		return BLK_STS_IOERR;
+		ret = BLK_STS_IOERR;
+		goto unlock;
 	}
 
 	/*
@@ -326,11 +357,14 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 		else
 			cmd->rq->__sector = sector;
 	} else if (sector != zone->wp) {
-		return BLK_STS_IOERR;
+		ret = BLK_STS_IOERR;
+		goto unlock;
 	}
 
-	if (zone->wp + nr_sectors > zone->start + zone->capacity)
-		return BLK_STS_IOERR;
+	if (zone->wp + nr_sectors > zone->start + zone->capacity) {
+		ret = BLK_STS_IOERR;
+		goto unlock;
+	}
 
 	if (zone->cond == BLK_ZONE_COND_CLOSED) {
 		dev->nr_zones_closed--;
@@ -341,9 +375,11 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
 		zone->cond = BLK_ZONE_COND_IMP_OPEN;
 
+	spin_unlock(&dev->zone_dev_lock);
 	ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
+	spin_lock(&dev->zone_dev_lock);
 	if (ret != BLK_STS_OK)
-		return ret;
+		goto unlock;
 
 	zone->wp += nr_sectors;
 	if (zone->wp == zone->start + zone->capacity) {
@@ -353,7 +389,13 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 			dev->nr_zones_imp_open--;
 		zone->cond = BLK_ZONE_COND_FULL;
 	}
-	return BLK_STS_OK;
+	ret = BLK_STS_OK;
+
+unlock:
+	spin_unlock(&dev->zone_dev_lock);
+	null_unlock_zone(dev, zno);
+
+	return ret;
 }
 
 static blk_status_t null_open_zone(struct nullb_device *dev, struct blk_zone *zone)
@@ -464,16 +506,33 @@ 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 zone_no = null_zone_no(dev, sector);
-	struct blk_zone *zone = &dev->zones[zone_no];
-	blk_status_t ret = BLK_STS_OK;
+	unsigned int zone_no;
+	struct blk_zone *zone;
+	blk_status_t ret;
 	size_t i;
 
+	if (op == REQ_OP_ZONE_RESET_ALL) {
+		for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
+			null_lock_zone(dev, i);
+			zone = &dev->zones[i];
+			if (zone->cond != BLK_ZONE_COND_EMPTY) {
+				spin_lock(&dev->zone_dev_lock);
+				null_reset_zone(dev, zone);
+				spin_unlock(&dev->zone_dev_lock);
+				trace_nullb_zone_op(cmd, i, zone->cond);
+			}
+			null_unlock_zone(dev, i);
+		}
+		return BLK_STS_OK;
+	}
+
+	zone_no = null_zone_no(dev, sector);
+	zone = &dev->zones[zone_no];
+
+	null_lock_zone(dev, zone_no);
+	spin_lock(&dev->zone_dev_lock);
+
 	switch (op) {
-	case REQ_OP_ZONE_RESET_ALL:
-		for (i = dev->zone_nr_conv; i < dev->nr_zones; i++)
-			null_reset_zone(dev, &dev->zones[i]);
-		break;
 	case REQ_OP_ZONE_RESET:
 		ret = null_reset_zone(dev, zone);
 		break;
@@ -487,30 +546,46 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
 		ret = null_finish_zone(dev, zone);
 		break;
 	default:
-		return BLK_STS_NOTSUPP;
+		ret = BLK_STS_NOTSUPP;
+		break;
 	}
 
+	spin_unlock(&dev->zone_dev_lock);
+
 	if (ret == BLK_STS_OK)
 		trace_nullb_zone_op(cmd, zone_no, zone->cond);
 
+	null_unlock_zone(dev, zone_no);
+
 	return ret;
 }
 
 blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_opf op,
 				    sector_t sector, sector_t nr_sectors)
 {
+	struct nullb_device *dev = cmd->nq->dev;
+	unsigned int zno = null_zone_no(dev, sector);
+	blk_status_t sts;
+
 	switch (op) {
 	case REQ_OP_WRITE:
-		return null_zone_write(cmd, sector, nr_sectors, false);
+		sts = null_zone_write(cmd, sector, nr_sectors, false);
+		break;
 	case REQ_OP_ZONE_APPEND:
-		return null_zone_write(cmd, sector, nr_sectors, true);
+		sts = null_zone_write(cmd, sector, nr_sectors, true);
+		break;
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_RESET_ALL:
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
 	case REQ_OP_ZONE_FINISH:
-		return null_zone_mgmt(cmd, op, sector);
+		sts = null_zone_mgmt(cmd, op, sector);
+		break;
 	default:
-		return null_process_cmd(cmd, op, sector, nr_sectors);
+		null_lock_zone(dev, zno);
+		sts = null_process_cmd(cmd, op, sector, nr_sectors);
+		null_unlock_zone(dev, zno);
 	}
+
+	return sts;
 }