Merge tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:
 "Pretty quiet round for this release. This contains:

   - Add support for zoned storage to ublk (Andreas, Ming)

   - Series improving performance for drivers that mark themselves as
     needing a blocking context for issue (Bart)

   - Cleanup the flush logic (Chengming)

   - sed opal keyring support (Greg)

   - Fixes and improvements to the integrity support (Jinyoung)

   - Add some exports for bcachefs that we can hopefully delete again in
     the future (Kent)

   - deadline throttling fix (Zhiguo)

   - Series allowing building the kernel without buffer_head support
     (Christoph)

   - Sanitize the bio page adding flow (Christoph)

   - Write back cache fixes (Christoph)

   - MD updates via Song:
      - Fix perf regression for raid0 large sequential writes (Jan)
      - Fix split bio iostat for raid0 (David)
      - Various raid1 fixes (Heinz, Xueshi)
      - raid6test build fixes (WANG)
      - Deprecate bitmap file support (Christoph)
      - Fix deadlock with md sync thread (Yu)
      - Refactor md io accounting (Yu)
      - Various non-urgent fixes (Li, Yu, Jack)

   - Various fixes and cleanups (Arnd, Azeem, Chengming, Damien, Li,
     Ming, Nitesh, Ruan, Tejun, Thomas, Xu)"

* tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux: (113 commits)
  block: use strscpy() to instead of strncpy()
  block: sed-opal: keyring support for SED keys
  block: sed-opal: Implement IOC_OPAL_REVERT_LSP
  block: sed-opal: Implement IOC_OPAL_DISCOVERY
  blk-mq: prealloc tags when increase tagset nr_hw_queues
  blk-mq: delete redundant tagset map update when fallback
  blk-mq: fix tags leak when shrink nr_hw_queues
  ublk: zoned: support REQ_OP_ZONE_RESET_ALL
  md: raid0: account for split bio in iostat accounting
  md/raid0: Fix performance regression for large sequential writes
  md/raid0: Factor out helper for mapping and submitting a bio
  md raid1: allow writebehind to work on any leg device set WriteMostly
  md/raid1: hold the barrier until handle_read_error() finishes
  md/raid1: free the r1bio before waiting for blocked rdev
  md/raid1: call free_r1bio() before allow_barrier() in raid_end_bio_io()
  blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init
  drivers/rnbd: restore sysfs interface to rnbd-client
  md/raid5-cache: fix null-ptr-deref for r5l_flush_stripe_to_raid()
  raid6: test: only check for Altivec if building on powerpc hosts
  raid6: test: make sure all intermediate and artifact files are .gitignored
  ...

3 files changed, 340 insertions, 29 deletions

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 42e0159bb258..df1cd0f718b8 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -2334,6 +2334,7 @@ static struct genl_family nbd_genl_family __ro_after_init = {
 	.mcgrps		= nbd_mcast_grps,
 	.n_mcgrps	= ARRAY_SIZE(nbd_mcast_grps),
 };
+MODULE_ALIAS_GENL_FAMILY(NBD_GENL_FAMILY_NAME);
 
 static int populate_nbd_status(struct nbd_device *nbd, struct sk_buff *reply)
 {
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index dc43a63b3469..c2bc85826358 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -1277,7 +1277,7 @@ static struct macio_driver swim3_driver =
 };
 
 
-int swim3_init(void)
+static int swim3_init(void)
 {
 	macio_register_driver(&swim3_driver);
 	return 0;
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 21d2e71c5514..630ddfe6657b 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -56,16 +56,21 @@
 		| UBLK_F_USER_RECOVERY_REISSUE \
 		| UBLK_F_UNPRIVILEGED_DEV \
 		| UBLK_F_CMD_IOCTL_ENCODE \
-		| UBLK_F_USER_COPY)
+		| UBLK_F_USER_COPY \
+		| UBLK_F_ZONED)
 
 /* All UBLK_PARAM_TYPE_* should be included here */
-#define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \
-		UBLK_PARAM_TYPE_DISCARD | UBLK_PARAM_TYPE_DEVT)
+#define UBLK_PARAM_TYPE_ALL                                \
+	(UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD | \
+	 UBLK_PARAM_TYPE_DEVT | UBLK_PARAM_TYPE_ZONED)
 
 struct ublk_rq_data {
 	struct llist_node node;
 
 	struct kref ref;
+	__u64 sector;
+	__u32 operation;
+	__u32 nr_zones;
 };
 
 struct ublk_uring_cmd_pdu {
@@ -185,6 +190,266 @@ struct ublk_params_header {
 	__u32	types;
 };
 
+static inline unsigned int ublk_req_build_flags(struct request *req);
+static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq,
+						   int tag);
+
+static inline bool ublk_dev_is_user_copy(const struct ublk_device *ub)
+{
+	return ub->dev_info.flags & UBLK_F_USER_COPY;
+}
+
+static inline bool ublk_dev_is_zoned(const struct ublk_device *ub)
+{
+	return ub->dev_info.flags & UBLK_F_ZONED;
+}
+
+static inline bool ublk_queue_is_zoned(struct ublk_queue *ubq)
+{
+	return ubq->flags & UBLK_F_ZONED;
+}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+
+static int ublk_get_nr_zones(const struct ublk_device *ub)
+{
+	const struct ublk_param_basic *p = &ub->params.basic;
+
+	/* Zone size is a power of 2 */
+	return p->dev_sectors >> ilog2(p->chunk_sectors);
+}
+
+static int ublk_revalidate_disk_zones(struct ublk_device *ub)
+{
+	return blk_revalidate_disk_zones(ub->ub_disk, NULL);
+}
+
+static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
+{
+	const struct ublk_param_zoned *p = &ub->params.zoned;
+	int nr_zones;
+
+	if (!ublk_dev_is_zoned(ub))
+		return -EINVAL;
+
+	if (!p->max_zone_append_sectors)
+		return -EINVAL;
+
+	nr_zones = ublk_get_nr_zones(ub);
+
+	if (p->max_active_zones > nr_zones)
+		return -EINVAL;
+
+	if (p->max_open_zones > nr_zones)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
+{
+	const struct ublk_param_zoned *p = &ub->params.zoned;
+
+	disk_set_zoned(ub->ub_disk, BLK_ZONED_HM);
+	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
+	blk_queue_required_elevator_features(ub->ub_disk->queue,
+					     ELEVATOR_F_ZBD_SEQ_WRITE);
+	disk_set_max_active_zones(ub->ub_disk, p->max_active_zones);
+	disk_set_max_open_zones(ub->ub_disk, p->max_open_zones);
+	blk_queue_max_zone_append_sectors(ub->ub_disk->queue, p->max_zone_append_sectors);
+
+	ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
+
+	return 0;
+}
+
+/* Based on virtblk_alloc_report_buffer */
+static void *ublk_alloc_report_buffer(struct ublk_device *ublk,
+				      unsigned int nr_zones, size_t *buflen)
+{
+	struct request_queue *q = ublk->ub_disk->queue;
+	size_t bufsize;
+	void *buf;
+
+	nr_zones = min_t(unsigned int, nr_zones,
+			 ublk->ub_disk->nr_zones);
+
+	bufsize = nr_zones * sizeof(struct blk_zone);
+	bufsize =
+		min_t(size_t, bufsize, queue_max_hw_sectors(q) << SECTOR_SHIFT);
+
+	while (bufsize >= sizeof(struct blk_zone)) {
+		buf = kvmalloc(bufsize, GFP_KERNEL | __GFP_NORETRY);
+		if (buf) {
+			*buflen = bufsize;
+			return buf;
+		}
+		bufsize >>= 1;
+	}
+
+	*buflen = 0;
+	return NULL;
+}
+
+static int ublk_report_zones(struct gendisk *disk, sector_t sector,
+		      unsigned int nr_zones, report_zones_cb cb, void *data)
+{
+	struct ublk_device *ub = disk->private_data;
+	unsigned int zone_size_sectors = disk->queue->limits.chunk_sectors;
+	unsigned int first_zone = sector >> ilog2(zone_size_sectors);
+	unsigned int done_zones = 0;
+	unsigned int max_zones_per_request;
+	int ret;
+	struct blk_zone *buffer;
+	size_t buffer_length;
+
+	nr_zones = min_t(unsigned int, ub->ub_disk->nr_zones - first_zone,
+			 nr_zones);
+
+	buffer = ublk_alloc_report_buffer(ub, nr_zones, &buffer_length);
+	if (!buffer)
+		return -ENOMEM;
+
+	max_zones_per_request = buffer_length / sizeof(struct blk_zone);
+
+	while (done_zones < nr_zones) {
+		unsigned int remaining_zones = nr_zones - done_zones;
+		unsigned int zones_in_request =
+			min_t(unsigned int, remaining_zones, max_zones_per_request);
+		struct request *req;
+		struct ublk_rq_data *pdu;
+		blk_status_t status;
+
+		memset(buffer, 0, buffer_length);
+
+		req = blk_mq_alloc_request(disk->queue, REQ_OP_DRV_IN, 0);
+		if (IS_ERR(req)) {
+			ret = PTR_ERR(req);
+			goto out;
+		}
+
+		pdu = blk_mq_rq_to_pdu(req);
+		pdu->operation = UBLK_IO_OP_REPORT_ZONES;
+		pdu->sector = sector;
+		pdu->nr_zones = zones_in_request;
+
+		ret = blk_rq_map_kern(disk->queue, req, buffer, buffer_length,
+					GFP_KERNEL);
+		if (ret) {
+			blk_mq_free_request(req);
+			goto out;
+		}
+
+		status = blk_execute_rq(req, 0);
+		ret = blk_status_to_errno(status);
+		blk_mq_free_request(req);
+		if (ret)
+			goto out;
+
+		for (unsigned int i = 0; i < zones_in_request; i++) {
+			struct blk_zone *zone = buffer + i;
+
+			/* A zero length zone means no more zones in this response */
+			if (!zone->len)
+				break;
+
+			ret = cb(zone, i, data);
+			if (ret)
+				goto out;
+
+			done_zones++;
+			sector += zone_size_sectors;
+
+		}
+	}
+
+	ret = done_zones;
+
+out:
+	kvfree(buffer);
+	return ret;
+}
+
+static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq,
+					 struct request *req)
+{
+	struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag);
+	struct ublk_io *io = &ubq->ios[req->tag];
+	struct ublk_rq_data *pdu = blk_mq_rq_to_pdu(req);
+	u32 ublk_op;
+
+	switch (req_op(req)) {
+	case REQ_OP_ZONE_OPEN:
+		ublk_op = UBLK_IO_OP_ZONE_OPEN;
+		break;
+	case REQ_OP_ZONE_CLOSE:
+		ublk_op = UBLK_IO_OP_ZONE_CLOSE;
+		break;
+	case REQ_OP_ZONE_FINISH:
+		ublk_op = UBLK_IO_OP_ZONE_FINISH;
+		break;
+	case REQ_OP_ZONE_RESET:
+		ublk_op = UBLK_IO_OP_ZONE_RESET;
+		break;
+	case REQ_OP_ZONE_APPEND:
+		ublk_op = UBLK_IO_OP_ZONE_APPEND;
+		break;
+	case REQ_OP_ZONE_RESET_ALL:
+		ublk_op = UBLK_IO_OP_ZONE_RESET_ALL;
+		break;
+	case REQ_OP_DRV_IN:
+		ublk_op = pdu->operation;
+		switch (ublk_op) {
+		case UBLK_IO_OP_REPORT_ZONES:
+			iod->op_flags = ublk_op | ublk_req_build_flags(req);
+			iod->nr_zones = pdu->nr_zones;
+			iod->start_sector = pdu->sector;
+			return BLK_STS_OK;
+		default:
+			return BLK_STS_IOERR;
+		}
+	case REQ_OP_DRV_OUT:
+		/* We do not support drv_out */
+		return BLK_STS_NOTSUPP;
+	default:
+		return BLK_STS_IOERR;
+	}
+
+	iod->op_flags = ublk_op | ublk_req_build_flags(req);
+	iod->nr_sectors = blk_rq_sectors(req);
+	iod->start_sector = blk_rq_pos(req);
+	iod->addr = io->addr;
+
+	return BLK_STS_OK;
+}
+
+#else
+
+#define ublk_report_zones (NULL)
+
+static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ublk_revalidate_disk_zones(struct ublk_device *ub)
+{
+	return 0;
+}
+
+static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq,
+					 struct request *req)
+{
+	return BLK_STS_NOTSUPP;
+}
+
+#endif
+
 static inline void __ublk_complete_rq(struct request *req);
 static void ublk_complete_rq(struct kref *ref);
 
@@ -281,6 +546,9 @@ static int ublk_validate_params(const struct ublk_device *ub)
 
 		if (p->max_sectors > (ub->dev_info.max_io_buf_bytes >> 9))
 			return -EINVAL;
+
+		if (ublk_dev_is_zoned(ub) && !p->chunk_sectors)
+			return -EINVAL;
 	} else
 		return -EINVAL;
 
@@ -299,6 +567,11 @@ static int ublk_validate_params(const struct ublk_device *ub)
 	if (ub->params.types & UBLK_PARAM_TYPE_DEVT)
 		return -EINVAL;
 
+	if (ub->params.types & UBLK_PARAM_TYPE_ZONED)
+		return ublk_dev_param_zoned_validate(ub);
+	else if (ublk_dev_is_zoned(ub))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -312,6 +585,9 @@ static int ublk_apply_params(struct ublk_device *ub)
 	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD)
 		ublk_dev_param_discard_apply(ub);
 
+	if (ub->params.types & UBLK_PARAM_TYPE_ZONED)
+		return ublk_dev_param_zoned_apply(ub);
+
 	return 0;
 }
 
@@ -482,6 +758,7 @@ static const struct block_device_operations ub_fops = {
 	.owner =	THIS_MODULE,
 	.open =		ublk_open,
 	.free_disk =	ublk_free_disk,
+	.report_zones =	ublk_report_zones,
 };
 
 #define UBLK_MAX_PIN_PAGES	32
@@ -596,7 +873,8 @@ static inline bool ublk_need_map_req(const struct request *req)
 
 static inline bool ublk_need_unmap_req(const struct request *req)
 {
-	return ublk_rq_has_data(req) && req_op(req) == REQ_OP_READ;
+	return ublk_rq_has_data(req) &&
+	       (req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_DRV_IN);
 }
 
 static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req,
@@ -680,8 +958,13 @@ static blk_status_t ublk_setup_iod(struct ublk_queue *ubq, struct request *req)
 {
 	struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag);
 	struct ublk_io *io = &ubq->ios[req->tag];
+	enum req_op op = req_op(req);
 	u32 ublk_op;
 
+	if (!ublk_queue_is_zoned(ubq) &&
+	    (op_is_zone_mgmt(op) || op == REQ_OP_ZONE_APPEND))
+		return BLK_STS_IOERR;
+
 	switch (req_op(req)) {
 	case REQ_OP_READ:
 		ublk_op = UBLK_IO_OP_READ;
@@ -699,6 +982,8 @@ static blk_status_t ublk_setup_iod(struct ublk_queue *ubq, struct request *req)
 		ublk_op = UBLK_IO_OP_WRITE_ZEROES;
 		break;
 	default:
+		if (ublk_queue_is_zoned(ubq))
+			return ublk_setup_iod_zoned(ubq, req);
 		return BLK_STS_IOERR;
 	}
 
@@ -751,7 +1036,8 @@ static inline void __ublk_complete_rq(struct request *req)
 	 *
 	 * Both the two needn't unmap.
 	 */
-	if (req_op(req) != REQ_OP_READ && req_op(req) != REQ_OP_WRITE)
+	if (req_op(req) != REQ_OP_READ && req_op(req) != REQ_OP_WRITE &&
+	    req_op(req) != REQ_OP_DRV_IN)
 		goto exit;
 
 	/* for READ request, writing data in iod->addr to rq buffers */
@@ -1114,8 +1400,13 @@ static void ublk_commit_completion(struct ublk_device *ub,
 
 	/* find the io request and complete */
 	req = blk_mq_tag_to_rq(ub->tag_set.tags[qid], tag);
+	if (WARN_ON_ONCE(unlikely(!req)))
+		return;
 
-	if (req && likely(!blk_should_fake_timeout(req->q)))
+	if (req_op(req) == REQ_OP_ZONE_APPEND)
+		req->__sector = ub_cmd->zone_append_lba;
+
+	if (likely(!blk_should_fake_timeout(req->q)))
 		ublk_put_req_ref(ubq, req);
 }
 
@@ -1414,11 +1705,6 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			^ (_IOC_NR(cmd_op) == UBLK_IO_NEED_GET_DATA))
 		goto out;
 
-	if (ublk_support_user_copy(ubq) && ub_cmd->addr) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	ret = ublk_check_cmd_op(cmd_op);
 	if (ret)
 		goto out;
@@ -1445,6 +1731,10 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			 */
 			if (!ub_cmd->addr && !ublk_need_get_data(ubq))
 				goto out;
+		} else if (ub_cmd->addr) {
+			/* User copy requires addr to be unset */
+			ret = -EINVAL;
+			goto out;
 		}
 
 		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
@@ -1464,7 +1754,15 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			if (!ub_cmd->addr && (!ublk_need_get_data(ubq) ||
 						req_op(req) == REQ_OP_READ))
 				goto out;
+		} else if (req_op(req) != REQ_OP_ZONE_APPEND && ub_cmd->addr) {
+			/*
+			 * User copy requires addr to be unset when command is
+			 * not zone append
+			 */
+			ret = -EINVAL;
+			goto out;
 		}
+
 		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
 		ublk_commit_completion(ub, ub_cmd);
 		break;
@@ -1537,11 +1835,14 @@ static inline bool ublk_check_ubuf_dir(const struct request *req,
 		int ubuf_dir)
 {
 	/* copy ubuf to request pages */
-	if (req_op(req) == REQ_OP_READ && ubuf_dir == ITER_SOURCE)
+	if ((req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_DRV_IN) &&
+	    ubuf_dir == ITER_SOURCE)
 		return true;
 
 	/* copy request pages to ubuf */
-	if (req_op(req) == REQ_OP_WRITE && ubuf_dir == ITER_DEST)
+	if ((req_op(req) == REQ_OP_WRITE ||
+	     req_op(req) == REQ_OP_ZONE_APPEND) &&
+	    ubuf_dir == ITER_DEST)
 		return true;
 
 	return false;
@@ -1881,17 +2182,24 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 
 	get_device(&ub->cdev_dev);
 	ub->dev_info.state = UBLK_S_DEV_LIVE;
+
+	if (ublk_dev_is_zoned(ub)) {
+		ret = ublk_revalidate_disk_zones(ub);
+		if (ret)
+			goto out_put_cdev;
+	}
+
 	ret = add_disk(disk);
+	if (ret)
+		goto out_put_cdev;
+
+	set_bit(UB_STATE_USED, &ub->state);
+
+out_put_cdev:
 	if (ret) {
-		/*
-		 * Has to drop the reference since ->free_disk won't be
-		 * called in case of add_disk failure.
-		 */
 		ub->dev_info.state = UBLK_S_DEV_DEAD;
 		ublk_put_device(ub);
-		goto out_put_disk;
 	}
-	set_bit(UB_STATE_USED, &ub->state);
 out_put_disk:
 	if (ret)
 		put_disk(disk);
@@ -2038,9 +2346,16 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 		UBLK_F_URING_CMD_COMP_IN_TASK;
 
 	/* GET_DATA isn't needed any more with USER_COPY */
-	if (ub->dev_info.flags & UBLK_F_USER_COPY)
+	if (ublk_dev_is_user_copy(ub))
 		ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA;
 
+	/* Zoned storage support requires user copy feature */
+	if (ublk_dev_is_zoned(ub) &&
+	    (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || !ublk_dev_is_user_copy(ub))) {
+		ret = -EINVAL;
+		goto out_free_dev_number;
+	}
+
 	/* We are not ready to support zero copy */
 	ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY;
 
@@ -2433,14 +2748,9 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub,
 	if (header->len < header->dev_path_len)
 		return -EINVAL;
 
-	dev_path = kmalloc(header->dev_path_len + 1, GFP_KERNEL);
-	if (!dev_path)
-		return -ENOMEM;
-
-	ret = -EFAULT;
-	if (copy_from_user(dev_path, argp, header->dev_path_len))
-		goto exit;
-	dev_path[header->dev_path_len] = 0;
+	dev_path = memdup_user_nul(argp, header->dev_path_len);
+	if (IS_ERR(dev_path))
+		return PTR_ERR(dev_path);
 
 	ret = -EINVAL;
 	switch (_IOC_NR(cmd->cmd_op)) {