Merge tag 'for-6.15/block-20250322' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - Fixes for integrity handling

 - NVMe pull request via Keith:
      - Secure concatenation for TCP transport (Hannes)
      - Multipath sysfs visibility (Nilay)
      - Various cleanups (Qasim, Baruch, Wang, Chen, Mike, Damien, Li)
      - Correct use of 64-bit BARs for pci-epf target (Niklas)
      - Socket fix for selinux when used in containers (Peijie)

 - MD pull request via Yu:
      - fix recovery can preempt resync (Li Nan)
      - fix md-bitmap IO limit (Su Yue)
      - fix raid10 discard with REQ_NOWAIT (Xiao Ni)
      - fix raid1 memory leak (Zheng Qixing)
      - fix mddev uaf (Yu Kuai)
      - fix raid1,raid10 IO flags (Yu Kuai)
      - some refactor and cleanup (Yu Kuai)

 - Series cleaning up and fixing bugs in the bad block handling code

 - Improve support for write failure simulation in null_blk

 - Various lock ordering fixes

 - Fixes for locking for debugfs attributes

 - Various ublk related fixes and improvements

 - Cleanups for blk-rq-qos wait handling

 - blk-throttle fixes

 - Fixes for loop dio and sync handling

 - Fixes and cleanups for the auto-PI code

 - Block side support for hardware encryption keys in blk-crypto

 - Various cleanups and fixes

* tag 'for-6.15/block-20250322' of git://git.kernel.dk/linux: (105 commits)
  nvmet: replace max(a, min(b, c)) by clamp(val, lo, hi)
  nvme-tcp: fix selinux denied when calling sock_sendmsg
  nvmet: pci-epf: Always configure BAR0 as 64-bit
  nvmet: Remove duplicate uuid_copy
  nvme: zns: Simplify nvme_zone_parse_entry()
  nvmet: pci-epf: Remove redundant 'flush_workqueue()' calls
  nvmet-fc: Remove unused functions
  nvme-pci: remove stale comment
  nvme-fc: Utilise min3() to simplify queue count calculation
  nvme-multipath: Add visibility for queue-depth io-policy
  nvme-multipath: Add visibility for numa io-policy
  nvme-multipath: Add visibility for round-robin io-policy
  nvmet: add tls_concat and tls_key debugfs entries
  nvmet-tcp: support secure channel concatenation
  nvmet: Add 'sq' argument to alloc_ctrl_args
  nvme-fabrics: reset admin connection for secure concatenation
  nvme-tcp: request secure channel concatenation
  nvme-keyring: add nvme_tls_psk_refresh()
  nvme: add nvme_auth_derive_tls_psk()
  nvme: add nvme_auth_generate_digest()
  ...

3 files changed, 135 insertions, 68 deletions

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index da1ecbf988b8..3bb9cee0a9b5 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -473,6 +473,8 @@ NULLB_DEVICE_ATTR(shared_tags, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL);
 NULLB_DEVICE_ATTR(fua, bool, NULL);
 NULLB_DEVICE_ATTR(rotational, bool, NULL);
+NULLB_DEVICE_ATTR(badblocks_once, bool, NULL);
+NULLB_DEVICE_ATTR(badblocks_partial_io, bool, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -559,14 +561,14 @@ static ssize_t nullb_device_badblocks_store(struct config_item *item,
 		goto out;
 	/* enable badblocks */
 	cmpxchg(&t_dev->badblocks.shift, -1, 0);
-	if (buf[0] == '+')
-		ret = badblocks_set(&t_dev->badblocks, start,
-			end - start + 1, 1);
-	else
-		ret = badblocks_clear(&t_dev->badblocks, start,
-			end - start + 1);
-	if (ret == 0)
+	if (buf[0] == '+') {
+		if (badblocks_set(&t_dev->badblocks, start,
+				  end - start + 1, 1))
+			ret = count;
+	} else if (badblocks_clear(&t_dev->badblocks, start,
+				   end - start + 1)) {
 		ret = count;
+	}
 out:
 	kfree(orig);
 	return ret;
@@ -592,41 +594,43 @@ static ssize_t nullb_device_zone_offline_store(struct config_item *item,
 CONFIGFS_ATTR_WO(nullb_device_, zone_offline);
 
 static struct configfs_attribute *nullb_device_attrs[] = {
-	&nullb_device_attr_size,
+	&nullb_device_attr_badblocks,
+	&nullb_device_attr_badblocks_once,
+	&nullb_device_attr_badblocks_partial_io,
+	&nullb_device_attr_blocking,
+	&nullb_device_attr_blocksize,
+	&nullb_device_attr_cache_size,
 	&nullb_device_attr_completion_nsec,
-	&nullb_device_attr_submit_queues,
-	&nullb_device_attr_poll_queues,
+	&nullb_device_attr_discard,
+	&nullb_device_attr_fua,
 	&nullb_device_attr_home_node,
-	&nullb_device_attr_queue_mode,
-	&nullb_device_attr_blocksize,
-	&nullb_device_attr_max_sectors,
-	&nullb_device_attr_irqmode,
 	&nullb_device_attr_hw_queue_depth,
 	&nullb_device_attr_index,
-	&nullb_device_attr_blocking,
-	&nullb_device_attr_use_per_node_hctx,
-	&nullb_device_attr_power,
-	&nullb_device_attr_memory_backed,
-	&nullb_device_attr_discard,
+	&nullb_device_attr_irqmode,
+	&nullb_device_attr_max_sectors,
 	&nullb_device_attr_mbps,
-	&nullb_device_attr_cache_size,
-	&nullb_device_attr_badblocks,
-	&nullb_device_attr_zoned,
-	&nullb_device_attr_zone_size,
+	&nullb_device_attr_memory_backed,
+	&nullb_device_attr_no_sched,
+	&nullb_device_attr_poll_queues,
+	&nullb_device_attr_power,
+	&nullb_device_attr_queue_mode,
+	&nullb_device_attr_rotational,
+	&nullb_device_attr_shared_tag_bitmap,
+	&nullb_device_attr_shared_tags,
+	&nullb_device_attr_size,
+	&nullb_device_attr_submit_queues,
+	&nullb_device_attr_use_per_node_hctx,
+	&nullb_device_attr_virt_boundary,
+	&nullb_device_attr_zone_append_max_sectors,
 	&nullb_device_attr_zone_capacity,
-	&nullb_device_attr_zone_nr_conv,
-	&nullb_device_attr_zone_max_open,
+	&nullb_device_attr_zone_full,
 	&nullb_device_attr_zone_max_active,
-	&nullb_device_attr_zone_append_max_sectors,
-	&nullb_device_attr_zone_readonly,
+	&nullb_device_attr_zone_max_open,
+	&nullb_device_attr_zone_nr_conv,
 	&nullb_device_attr_zone_offline,
-	&nullb_device_attr_zone_full,
-	&nullb_device_attr_virt_boundary,
-	&nullb_device_attr_no_sched,
-	&nullb_device_attr_shared_tags,
-	&nullb_device_attr_shared_tag_bitmap,
-	&nullb_device_attr_fua,
-	&nullb_device_attr_rotational,
+	&nullb_device_attr_zone_readonly,
+	&nullb_device_attr_zone_size,
+	&nullb_device_attr_zoned,
 	NULL,
 };
 
@@ -704,16 +708,28 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
-	return snprintf(page, PAGE_SIZE,
-			"badblocks,blocking,blocksize,cache_size,fua,"
-			"completion_nsec,discard,home_node,hw_queue_depth,"
-			"irqmode,max_sectors,mbps,memory_backed,no_sched,"
-			"poll_queues,power,queue_mode,shared_tag_bitmap,"
-			"shared_tags,size,submit_queues,use_per_node_hctx,"
-			"virt_boundary,zoned,zone_capacity,zone_max_active,"
-			"zone_max_open,zone_nr_conv,zone_offline,zone_readonly,"
-			"zone_size,zone_append_max_sectors,zone_full,"
-			"rotational\n");
+
+	struct configfs_attribute **entry;
+	char delimiter = ',';
+	size_t left = PAGE_SIZE;
+	size_t written = 0;
+	int ret;
+
+	for (entry = &nullb_device_attrs[0]; *entry && left > 0; entry++) {
+		if (!*(entry + 1))
+			delimiter = '\n';
+		ret = snprintf(page + written, left, "%s%c", (*entry)->ca_name,
+			       delimiter);
+		if (ret >= left) {
+			WARN_ONCE(1, "Too many null_blk features to print\n");
+			memzero_explicit(page, PAGE_SIZE);
+			return -ENOBUFS;
+		}
+		left -= ret;
+		written += ret;
+	}
+
+	return written;
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -1249,25 +1265,37 @@ static int null_transfer(struct nullb *nullb, struct page *page,
 	return err;
 }
 
-static blk_status_t null_handle_rq(struct nullb_cmd *cmd)
+/*
+ * Transfer data for the given request. The transfer size is capped with the
+ * nr_sectors argument.
+ */
+static blk_status_t null_handle_data_transfer(struct nullb_cmd *cmd,
+					      sector_t nr_sectors)
 {
 	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct nullb *nullb = cmd->nq->dev->nullb;
 	int err = 0;
 	unsigned int len;
 	sector_t sector = blk_rq_pos(rq);
+	unsigned int max_bytes = nr_sectors << SECTOR_SHIFT;
+	unsigned int transferred_bytes = 0;
 	struct req_iterator iter;
 	struct bio_vec bvec;
 
 	spin_lock_irq(&nullb->lock);
 	rq_for_each_segment(bvec, rq, iter) {
 		len = bvec.bv_len;
+		if (transferred_bytes + len > max_bytes)
+			len = max_bytes - transferred_bytes;
 		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
 				     op_is_write(req_op(rq)), sector,
 				     rq->cmd_flags & REQ_FUA);
 		if (err)
 			break;
 		sector += len >> SECTOR_SHIFT;
+		transferred_bytes += len;
+		if (transferred_bytes >= max_bytes)
+			break;
 	}
 	spin_unlock_irq(&nullb->lock);
 
@@ -1295,31 +1323,51 @@ static inline blk_status_t null_handle_throttled(struct nullb_cmd *cmd)
 	return sts;
 }
 
-static inline blk_status_t null_handle_badblocks(struct nullb_cmd *cmd,
-						 sector_t sector,
-						 sector_t nr_sectors)
+/*
+ * Check if the command should fail for the badblocks. If so, return
+ * BLK_STS_IOERR and return number of partial I/O sectors to be written or read,
+ * which may be less than the requested number of sectors.
+ *
+ * @cmd:        The command to handle.
+ * @sector:     The start sector for I/O.
+ * @nr_sectors: Specifies number of sectors to write or read, and returns the
+ *              number of sectors to be written or read.
+ */
+blk_status_t null_handle_badblocks(struct nullb_cmd *cmd, sector_t sector,
+				   unsigned int *nr_sectors)
 {
 	struct badblocks *bb = &cmd->nq->dev->badblocks;
-	sector_t first_bad;
-	int bad_sectors;
+	struct nullb_device *dev = cmd->nq->dev;
+	unsigned int block_sectors = dev->blocksize >> SECTOR_SHIFT;
+	sector_t first_bad, bad_sectors;
+	unsigned int partial_io_sectors = 0;
 
-	if (badblocks_check(bb, sector, nr_sectors, &first_bad, &bad_sectors))
-		return BLK_STS_IOERR;
+	if (!badblocks_check(bb, sector, *nr_sectors, &first_bad, &bad_sectors))
+		return BLK_STS_OK;
 
-	return BLK_STS_OK;
+	if (cmd->nq->dev->badblocks_once)
+		badblocks_clear(bb, first_bad, bad_sectors);
+
+	if (cmd->nq->dev->badblocks_partial_io) {
+		if (!IS_ALIGNED(first_bad, block_sectors))
+			first_bad = ALIGN_DOWN(first_bad, block_sectors);
+		if (sector < first_bad)
+			partial_io_sectors = first_bad - sector;
+	}
+	*nr_sectors = partial_io_sectors;
+
+	return BLK_STS_IOERR;
 }
 
-static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd,
-						     enum req_op op,
-						     sector_t sector,
-						     sector_t nr_sectors)
+blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd, enum req_op op,
+				       sector_t sector, sector_t nr_sectors)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 
 	if (op == REQ_OP_DISCARD)
 		return null_handle_discard(dev, sector, nr_sectors);
 
-	return null_handle_rq(cmd);
+	return null_handle_data_transfer(cmd, nr_sectors);
 }
 
 static void nullb_zero_read_cmd_buffer(struct nullb_cmd *cmd)
@@ -1366,18 +1414,19 @@ blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op,
 			      sector_t sector, unsigned int nr_sectors)
 {
 	struct nullb_device *dev = cmd->nq->dev;
+	blk_status_t badblocks_ret = BLK_STS_OK;
 	blk_status_t ret;
 
-	if (dev->badblocks.shift != -1) {
-		ret = null_handle_badblocks(cmd, sector, nr_sectors);
+	if (dev->badblocks.shift != -1)
+		badblocks_ret = null_handle_badblocks(cmd, sector, &nr_sectors);
+
+	if (dev->memory_backed && nr_sectors) {
+		ret = null_handle_memory_backed(cmd, op, sector, nr_sectors);
 		if (ret != BLK_STS_OK)
 			return ret;
 	}
 
-	if (dev->memory_backed)
-		return null_handle_memory_backed(cmd, op, sector, nr_sectors);
-
-	return BLK_STS_OK;
+	return badblocks_ret;
 }
 
 static void null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 6f9fe6171087..7bb6128dbaaf 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -63,6 +63,8 @@ struct nullb_device {
 	unsigned long flags; /* device flags */
 	unsigned int curr_cache;
 	struct badblocks badblocks;
+	bool badblocks_once;
+	bool badblocks_partial_io;
 
 	unsigned int nr_zones;
 	unsigned int nr_zones_imp_open;
@@ -131,6 +133,10 @@ blk_status_t null_handle_discard(struct nullb_device *dev, sector_t sector,
 				 sector_t nr_sectors);
 blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op,
 			      sector_t sector, unsigned int nr_sectors);
+blk_status_t null_handle_badblocks(struct nullb_cmd *cmd, sector_t sector,
+				   unsigned int *nr_sectors);
+blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd, enum req_op op,
+				       sector_t sector, sector_t nr_sectors);
 
 #ifdef CONFIG_BLK_DEV_ZONED
 int null_init_zoned_dev(struct nullb_device *dev, struct queue_limits *lim);
diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 0d5f9bf95229..4e5728f45989 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -353,6 +353,7 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	struct nullb_device *dev = cmd->nq->dev;
 	unsigned int zno = null_zone_no(dev, sector);
 	struct nullb_zone *zone = &dev->zones[zno];
+	blk_status_t badblocks_ret = BLK_STS_OK;
 	blk_status_t ret;
 
 	trace_nullb_zone_op(cmd, zno, zone->cond);
@@ -412,9 +413,20 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 		zone->cond = BLK_ZONE_COND_IMP_OPEN;
 	}
 
-	ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
-	if (ret != BLK_STS_OK)
-		goto unlock_zone;
+	if (dev->badblocks.shift != -1) {
+		badblocks_ret = null_handle_badblocks(cmd, sector, &nr_sectors);
+		if (badblocks_ret != BLK_STS_OK && !nr_sectors) {
+			ret = badblocks_ret;
+			goto unlock_zone;
+		}
+	}
+
+	if (dev->memory_backed) {
+		ret = null_handle_memory_backed(cmd, REQ_OP_WRITE, sector,
+						nr_sectors);
+		if (ret != BLK_STS_OK)
+			goto unlock_zone;
+	}
 
 	zone->wp += nr_sectors;
 	if (zone->wp == zone->start + zone->capacity) {
@@ -429,7 +441,7 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 		zone->cond = BLK_ZONE_COND_FULL;
 	}
 
-	ret = BLK_STS_OK;
+	ret = badblocks_ret;
 
 unlock_zone:
 	null_unlock_zone(dev, zone);