Merge tag 'for-6.8/block-2024-01-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:
 "Pretty quiet round this time around. This contains:

   - NVMe updates via Keith:
        - nvme fabrics spec updates (Guixin, Max)
        - nvme target udpates (Guixin, Evan)
        - nvme attribute refactoring (Daniel)
        - nvme-fc numa fix (Keith)

   - MD updates via Song:
        - Fix/Cleanup RCU usage from conf->disks[i].rdev (Yu Kuai)
        - Fix raid5 hang issue (Junxiao Bi)
        - Add Yu Kuai as Reviewer of the md subsystem
        - Remove deprecated flavors (Song Liu)
        - raid1 read error check support (Li Nan)
        - Better handle events off-by-1 case (Alex Lyakas)

   - Efficiency improvements for passthrough (Kundan)

   - Support for mapping integrity data directly (Keith)

   - Zoned write fix (Damien)

   - rnbd fixes (Kees, Santosh, Supriti)

   - Default to a sane discard size granularity (Christoph)

   - Make the default max transfer size naming less confusing
     (Christoph)

   - Remove support for deprecated host aware zoned model (Christoph)

   - Misc fixes (me, Li, Matthew, Min, Ming, Randy, liyouhong, Daniel,
     Bart, Christoph)"

* tag 'for-6.8/block-2024-01-08' of git://git.kernel.dk/linux: (78 commits)
  block: Treat sequential write preferred zone type as invalid
  block: remove disk_clear_zoned
  sd: remove the !ZBC && blk_queue_is_zoned case in sd_read_block_characteristics
  drivers/block/xen-blkback/common.h: Fix spelling typo in comment
  blk-cgroup: fix rcu lockdep warning in blkg_lookup()
  blk-cgroup: don't use removal safe list iterators
  block: floor the discard granularity to the physical block size
  mtd_blkdevs: use the default discard granularity
  bcache: use the default discard granularity
  zram: use the default discard granularity
  null_blk: use the default discard granularity
  nbd: use the default discard granularity
  ubd: use the default discard granularity
  block: default the discard granularity to sector size
  bcache: discard_granularity should not be smaller than a sector
  block: remove two comments in bio_split_discard
  block: rename and document BLK_DEF_MAX_SECTORS
  loop: don't abuse BLK_DEF_MAX_SECTORS
  aoe: don't abuse BLK_DEF_MAX_SECTORS
  null_blk: don't cap max_hw_sectors to BLK_DEF_MAX_SECTORS
  ...

1 files changed, 33 insertions, 172 deletions

diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 4939ed35638f..093e46f16e6c 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -97,58 +97,6 @@ static void __user *nvme_to_user_ptr(uintptr_t ptrval)
 	return (void __user *)ptrval;
 }
 
-static void *nvme_add_user_metadata(struct request *req, void __user *ubuf,
-		unsigned len, u32 seed)
-{
-	struct bio_integrity_payload *bip;
-	int ret = -ENOMEM;
-	void *buf;
-	struct bio *bio = req->bio;
-
-	buf = kmalloc(len, GFP_KERNEL);
-	if (!buf)
-		goto out;
-
-	if (req_op(req) == REQ_OP_DRV_OUT) {
-		ret = -EFAULT;
-		if (copy_from_user(buf, ubuf, len))
-			goto out_free_meta;
-	} else {
-		memset(buf, 0, len);
-	}
-
-	bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
-	if (IS_ERR(bip)) {
-		ret = PTR_ERR(bip);
-		goto out_free_meta;
-	}
-
-	bip->bip_iter.bi_sector = seed;
-	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
-			offset_in_page(buf));
-	if (ret != len) {
-		ret = -ENOMEM;
-		goto out_free_meta;
-	}
-
-	req->cmd_flags |= REQ_INTEGRITY;
-	return buf;
-out_free_meta:
-	kfree(buf);
-out:
-	return ERR_PTR(ret);
-}
-
-static int nvme_finish_user_metadata(struct request *req, void __user *ubuf,
-		void *meta, unsigned len, int ret)
-{
-	if (!ret && req_op(req) == REQ_OP_DRV_IN &&
-	    copy_to_user(ubuf, meta, len))
-		ret = -EFAULT;
-	kfree(meta);
-	return ret;
-}
-
 static struct request *nvme_alloc_user_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_opf_t rq_flags,
 		blk_mq_req_flags_t blk_flags)
@@ -165,14 +113,12 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
 
 static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, void **metap, struct io_uring_cmd *ioucmd,
-		unsigned int flags)
+		u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags)
 {
 	struct request_queue *q = req->q;
 	struct nvme_ns *ns = q->queuedata;
 	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
 	struct bio *bio = NULL;
-	void *meta = NULL;
 	int ret;
 
 	if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
@@ -194,18 +140,17 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 
 	if (ret)
 		goto out;
+
 	bio = req->bio;
-	if (bdev)
+	if (bdev) {
 		bio_set_dev(bio, bdev);
-
-	if (bdev && meta_buffer && meta_len) {
-		meta = nvme_add_user_metadata(req, meta_buffer, meta_len,
-				meta_seed);
-		if (IS_ERR(meta)) {
-			ret = PTR_ERR(meta);
-			goto out_unmap;
+		if (meta_buffer && meta_len) {
+			ret = bio_integrity_map_user(bio, meta_buffer, meta_len,
+						     meta_seed);
+			if (ret)
+				goto out_unmap;
+			req->cmd_flags |= REQ_INTEGRITY;
 		}
-		*metap = meta;
 	}
 
 	return ret;
@@ -226,7 +171,6 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	struct nvme_ns *ns = q->queuedata;
 	struct nvme_ctrl *ctrl;
 	struct request *req;
-	void *meta = NULL;
 	struct bio *bio;
 	u32 effects;
 	int ret;
@@ -238,7 +182,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	req->timeout = timeout;
 	if (ubuffer && bufflen) {
 		ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer,
-				meta_len, meta_seed, &meta, NULL, flags);
+				meta_len, meta_seed, NULL, flags);
 		if (ret)
 			return ret;
 	}
@@ -250,9 +194,6 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	ret = nvme_execute_rq(req, false);
 	if (result)
 		*result = le64_to_cpu(nvme_req(req)->result.u64);
-	if (meta)
-		ret = nvme_finish_user_metadata(req, meta_buffer, meta,
-						meta_len, ret);
 	if (bio)
 		blk_rq_unmap_user(bio);
 	blk_mq_free_request(req);
@@ -284,10 +225,10 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		return -EINVAL;
 	}
 
-	length = (io.nblocks + 1) << ns->lba_shift;
+	length = (io.nblocks + 1) << ns->head->lba_shift;
 
 	if ((io.control & NVME_RW_PRINFO_PRACT) &&
-	    ns->ms == sizeof(struct t10_pi_tuple)) {
+	    ns->head->ms == sizeof(struct t10_pi_tuple)) {
 		/*
 		 * Protection information is stripped/inserted by the
 		 * controller.
@@ -297,11 +238,11 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		meta_len = 0;
 		metadata = NULL;
 	} else {
-		meta_len = (io.nblocks + 1) * ns->ms;
+		meta_len = (io.nblocks + 1) * ns->head->ms;
 		metadata = nvme_to_user_ptr(io.metadata);
 	}
 
-	if (ns->features & NVME_NS_EXT_LBAS) {
+	if (ns->head->features & NVME_NS_EXT_LBAS) {
 		length += meta_len;
 		meta_len = 0;
 	} else if (meta_len) {
@@ -447,19 +388,10 @@ struct nvme_uring_data {
  * Expect build errors if this grows larger than that.
  */
 struct nvme_uring_cmd_pdu {
-	union {
-		struct bio *bio;
-		struct request *req;
-	};
-	u32 meta_len;
-	u32 nvme_status;
-	union {
-		struct {
-			void *meta; /* kernel-resident buffer */
-			void __user *meta_buffer;
-		};
-		u64 result;
-	} u;
+	struct request *req;
+	struct bio *bio;
+	u64 result;
+	int status;
 };
 
 static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
@@ -468,31 +400,6 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
 	return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu;
 }
 
-static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd,
-				    unsigned issue_flags)
-{
-	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
-	struct request *req = pdu->req;
-	int status;
-	u64 result;
-
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
-		status = -EINTR;
-	else
-		status = nvme_req(req)->status;
-
-	result = le64_to_cpu(nvme_req(req)->result.u64);
-
-	if (pdu->meta_len)
-		status = nvme_finish_user_metadata(req, pdu->u.meta_buffer,
-					pdu->u.meta, pdu->meta_len, status);
-	if (req->bio)
-		blk_rq_unmap_user(req->bio);
-	blk_mq_free_request(req);
-
-	io_uring_cmd_done(ioucmd, status, result, issue_flags);
-}
-
 static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
 			       unsigned issue_flags)
 {
@@ -500,8 +407,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
 
 	if (pdu->bio)
 		blk_rq_unmap_user(pdu->bio);
-
-	io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result, issue_flags);
+	io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags);
 }
 
 static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
@@ -510,53 +416,24 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	struct io_uring_cmd *ioucmd = req->end_io_data;
 	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
 
-	req->bio = pdu->bio;
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED) {
-		pdu->nvme_status = -EINTR;
-	} else {
-		pdu->nvme_status = nvme_req(req)->status;
-		if (!pdu->nvme_status)
-			pdu->nvme_status = blk_status_to_errno(err);
-	}
-	pdu->u.result = le64_to_cpu(nvme_req(req)->result.u64);
+	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+		pdu->status = -EINTR;
+	else
+		pdu->status = nvme_req(req)->status;
+	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
 	 * For iopoll, complete it directly.
 	 * Otherwise, move the completion to task work.
 	 */
-	if (blk_rq_is_poll(req)) {
-		WRITE_ONCE(ioucmd->cookie, NULL);
+	if (blk_rq_is_poll(req))
 		nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
-	} else {
+	else
 		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
-	}
 
 	return RQ_END_IO_FREE;
 }
 
-static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req,
-						     blk_status_t err)
-{
-	struct io_uring_cmd *ioucmd = req->end_io_data;
-	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
-
-	req->bio = pdu->bio;
-	pdu->req = req;
-
-	/*
-	 * For iopoll, complete it directly.
-	 * Otherwise, move the completion to task work.
-	 */
-	if (blk_rq_is_poll(req)) {
-		WRITE_ONCE(ioucmd->cookie, NULL);
-		nvme_uring_task_meta_cb(ioucmd, IO_URING_F_UNLOCKED);
-	} else {
-		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_meta_cb);
-	}
-
-	return RQ_END_IO_NONE;
-}
-
 static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		struct io_uring_cmd *ioucmd, unsigned int issue_flags, bool vec)
 {
@@ -568,7 +445,6 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	struct request *req;
 	blk_opf_t rq_flags = REQ_ALLOC_CACHE;
 	blk_mq_req_flags_t blk_flags = 0;
-	void *meta = NULL;
 	int ret;
 
 	c.common.opcode = READ_ONCE(cmd->opcode);
@@ -616,27 +492,16 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	if (d.addr && d.data_len) {
 		ret = nvme_map_user_request(req, d.addr,
 			d.data_len, nvme_to_user_ptr(d.metadata),
-			d.metadata_len, 0, &meta, ioucmd, vec);
+			d.metadata_len, 0, ioucmd, vec);
 		if (ret)
 			return ret;
 	}
 
-	if (blk_rq_is_poll(req)) {
-		ioucmd->flags |= IORING_URING_CMD_POLLED;
-		WRITE_ONCE(ioucmd->cookie, req);
-	}
-
 	/* to free bio on completion, as req->bio will be null at that time */
 	pdu->bio = req->bio;
-	pdu->meta_len = d.metadata_len;
+	pdu->req = req;
 	req->end_io_data = ioucmd;
-	if (pdu->meta_len) {
-		pdu->u.meta = meta;
-		pdu->u.meta_buffer = nvme_to_user_ptr(d.metadata);
-		req->end_io = nvme_uring_cmd_end_io_meta;
-	} else {
-		req->end_io = nvme_uring_cmd_end_io;
-	}
+	req->end_io = nvme_uring_cmd_end_io;
 	blk_execute_rq_nowait(req, false);
 	return -EIOCBQUEUED;
 }
@@ -787,16 +652,12 @@ int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd,
 				 struct io_comp_batch *iob,
 				 unsigned int poll_flags)
 {
-	struct request *req;
-	int ret = 0;
-
-	if (!(ioucmd->flags & IORING_URING_CMD_POLLED))
-		return 0;
+	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
+	struct request *req = pdu->req;
 
-	req = READ_ONCE(ioucmd->cookie);
 	if (req && blk_rq_is_poll(req))
-		ret = blk_rq_poll(req, iob, poll_flags);
-	return ret;
+		return blk_rq_poll(req, iob, poll_flags);
+	return 0;
 }
 #ifdef CONFIG_NVME_MULTIPATH
 static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,