Merge tag 'for-6.4/block-2023-04-21' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - drbd patches, bringing us closer to unifying the out-of-tree version
   and the in tree one (Andreas, Christoph)

 - support for auto-quiesce for the s390 dasd driver (Stefan)

 - MD pull request via Song:
      - md/bitmap: Optimal last page size (Jon Derrick)
      - Various raid10 fixes (Yu Kuai, Li Nan)
      - md: add error_handlers for raid0 and linear (Mariusz Tkaczyk)

 - NVMe pull request via Christoph:
      - Drop redundant pci_enable_pcie_error_reporting (Bjorn Helgaas)
      - Validate nvmet module parameters (Chaitanya Kulkarni)
      - Fence TCP socket on receive error (Chris Leech)
      - Fix async event trace event (Keith Busch)
      - Minor cleanups (Chaitanya Kulkarni, zhenwei pi)
      - Fix and cleanup nvmet Identify handling (Damien Le Moal,
        Christoph Hellwig)
      - Fix double blk_mq_complete_request race in the timeout handler
        (Lei Yin)
      - Fix irq locking in nvme-fcloop (Ming Lei)
      - Remove queue mapping helper for rdma devices (Sagi Grimberg)

 - use structured request attribute checks for nbd (Jakub)

 - fix blk-crypto race conditions between keyslot management (Eric)

 - add sed-opal support for reading read locking range attributes
   (Ondrej)

 - make fault injection configurable for null_blk (Akinobu)

 - clean up the request insertion API (Christoph)

 - clean up the queue running API (Christoph)

 - blkg config helper cleanups (Tejun)

 - lazy init support for blk-iolatency (Tejun)

 - various fixes and tweaks to ublk (Ming)

 - remove hybrid polling. It hasn't really been useful since we got
   async polled IO support, and these days we don't support sync polled
   IO at all (Keith)

 - misc fixes, cleanups, improvements (Zhong, Ondrej, Colin, Chengming,
   Chaitanya, me)

* tag 'for-6.4/block-2023-04-21' of git://git.kernel.dk/linux: (118 commits)
  nbd: fix incomplete validation of ioctl arg
  ublk: don't return 0 in case of any failure
  sed-opal: geometry feature reporting command
  null_blk: Always check queue mode setting from configfs
  block: ublk: switch to ioctl command encoding
  blk-mq: fix the blk_mq_add_to_requeue_list call in blk_kick_flush
  block, bfq: Fix division by zero error on zero wsum
  fault-inject: fix build error when FAULT_INJECTION_CONFIGFS=y and CONFIGFS_FS=m
  block: store bdev->bd_disk->fops->submit_bio state in bdev
  block: re-arrange the struct block_device fields for better layout
  md/raid5: remove unused working_disks variable
  md/raid10: don't call bio_start_io_acct twice for bio which experienced read error
  md/raid10: fix memleak of md thread
  md/raid10: fix memleak for 'conf->bio_split'
  md/raid10: fix leak of 'r10bio->remaining' for recovery
  md/raid10: don't BUG_ON() in raise_barrier()
  md: fix soft lockup in status_resync
  md: add error_handlers for raid0 and linear
  md: Use optimal I/O size for last bitmap page
  md: Fix types in sb writer
  ...

1 files changed, 76 insertions, 57 deletions

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 604c1a13c76e..afbef182820b 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -53,7 +53,8 @@
 		| UBLK_F_NEED_GET_DATA \
 		| UBLK_F_USER_RECOVERY \
 		| UBLK_F_USER_RECOVERY_REISSUE \
-		| UBLK_F_UNPRIVILEGED_DEV)
+		| UBLK_F_UNPRIVILEGED_DEV \
+		| UBLK_F_CMD_IOCTL_ENCODE)
 
 /* All UBLK_PARAM_TYPE_* should be included here */
 #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \
@@ -298,9 +299,7 @@ static inline bool ublk_can_use_task_work(const struct ublk_queue *ubq)
 
 static inline bool ublk_need_get_data(const struct ublk_queue *ubq)
 {
-	if (ubq->flags & UBLK_F_NEED_GET_DATA)
-		return true;
-	return false;
+	return ubq->flags & UBLK_F_NEED_GET_DATA;
 }
 
 static struct ublk_device *ublk_get_device(struct ublk_device *ub)
@@ -349,25 +348,19 @@ static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id)
 static inline bool ublk_queue_can_use_recovery_reissue(
 		struct ublk_queue *ubq)
 {
-	if ((ubq->flags & UBLK_F_USER_RECOVERY) &&
-			(ubq->flags & UBLK_F_USER_RECOVERY_REISSUE))
-		return true;
-	return false;
+	return (ubq->flags & UBLK_F_USER_RECOVERY) &&
+			(ubq->flags & UBLK_F_USER_RECOVERY_REISSUE);
 }
 
 static inline bool ublk_queue_can_use_recovery(
 		struct ublk_queue *ubq)
 {
-	if (ubq->flags & UBLK_F_USER_RECOVERY)
-		return true;
-	return false;
+	return ubq->flags & UBLK_F_USER_RECOVERY;
 }
 
 static inline bool ublk_can_use_recovery(struct ublk_device *ub)
 {
-	if (ub->dev_info.flags & UBLK_F_USER_RECOVERY)
-		return true;
-	return false;
+	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
 }
 
 static void ublk_free_disk(struct gendisk *disk)
@@ -428,10 +421,9 @@ static const struct block_device_operations ub_fops = {
 #define UBLK_MAX_PIN_PAGES	32
 
 struct ublk_map_data {
-	const struct ublk_queue *ubq;
 	const struct request *rq;
-	const struct ublk_io *io;
-	unsigned max_bytes;
+	unsigned long	ubuf;
+	unsigned int	len;
 };
 
 struct ublk_io_iter {
@@ -488,18 +480,17 @@ static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data,
 	return done;
 }
 
-static inline int ublk_copy_user_pages(struct ublk_map_data *data,
-		bool to_vm)
+static int ublk_copy_user_pages(struct ublk_map_data *data, bool to_vm)
 {
 	const unsigned int gup_flags = to_vm ? FOLL_WRITE : 0;
-	const unsigned long start_vm = data->io->addr;
+	const unsigned long start_vm = data->ubuf;
 	unsigned int done = 0;
 	struct ublk_io_iter iter = {
 		.pg_off	= start_vm & (PAGE_SIZE - 1),
 		.bio	= data->rq->bio,
 		.iter	= data->rq->bio->bi_iter,
 	};
-	const unsigned int nr_pages = round_up(data->max_bytes +
+	const unsigned int nr_pages = round_up(data->len +
 			(start_vm & (PAGE_SIZE - 1)), PAGE_SIZE) >> PAGE_SHIFT;
 
 	while (done < nr_pages) {
@@ -512,42 +503,49 @@ static inline int ublk_copy_user_pages(struct ublk_map_data *data,
 				iter.pages);
 		if (iter.nr_pages <= 0)
 			return done == 0 ? iter.nr_pages : done;
-		len = ublk_copy_io_pages(&iter, data->max_bytes, to_vm);
+		len = ublk_copy_io_pages(&iter, data->len, to_vm);
 		for (i = 0; i < iter.nr_pages; i++) {
 			if (to_vm)
 				set_page_dirty(iter.pages[i]);
 			put_page(iter.pages[i]);
 		}
-		data->max_bytes -= len;
+		data->len -= len;
 		done += iter.nr_pages;
 	}
 
 	return done;
 }
 
+static inline bool ublk_need_map_req(const struct request *req)
+{
+	return ublk_rq_has_data(req) && req_op(req) == REQ_OP_WRITE;
+}
+
+static inline bool ublk_need_unmap_req(const struct request *req)
+{
+	return ublk_rq_has_data(req) && req_op(req) == REQ_OP_READ;
+}
+
 static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req,
 		struct ublk_io *io)
 {
 	const unsigned int rq_bytes = blk_rq_bytes(req);
+
 	/*
 	 * no zero copy, we delay copy WRITE request data into ublksrv
 	 * context and the big benefit is that pinning pages in current
 	 * context is pretty fast, see ublk_pin_user_pages
 	 */
-	if (req_op(req) != REQ_OP_WRITE && req_op(req) != REQ_OP_FLUSH)
-		return rq_bytes;
-
-	if (ublk_rq_has_data(req)) {
+	if (ublk_need_map_req(req)) {
 		struct ublk_map_data data = {
-			.ubq	=	ubq,
 			.rq	=	req,
-			.io	=	io,
-			.max_bytes =	rq_bytes,
+			.ubuf	=	io->addr,
+			.len	=	rq_bytes,
 		};
 
 		ublk_copy_user_pages(&data, true);
 
-		return rq_bytes - data.max_bytes;
+		return rq_bytes - data.len;
 	}
 	return rq_bytes;
 }
@@ -558,19 +556,18 @@ static int ublk_unmap_io(const struct ublk_queue *ubq,
 {
 	const unsigned int rq_bytes = blk_rq_bytes(req);
 
-	if (req_op(req) == REQ_OP_READ && ublk_rq_has_data(req)) {
+	if (ublk_need_unmap_req(req)) {
 		struct ublk_map_data data = {
-			.ubq	=	ubq,
 			.rq	=	req,
-			.io	=	io,
-			.max_bytes =	io->res,
+			.ubuf	=	io->addr,
+			.len	=	io->res,
 		};
 
 		WARN_ON_ONCE(io->res > rq_bytes);
 
 		ublk_copy_user_pages(&data, false);
 
-		return io->res - data.max_bytes;
+		return io->res - data.len;
 	}
 	return rq_bytes;
 }
@@ -655,14 +652,15 @@ static void ublk_complete_rq(struct request *req)
 	struct ublk_queue *ubq = req->mq_hctx->driver_data;
 	struct ublk_io *io = &ubq->ios[req->tag];
 	unsigned int unmapped_bytes;
+	blk_status_t res = BLK_STS_OK;
 
 	/* failed read IO if nothing is read */
 	if (!io->res && req_op(req) == REQ_OP_READ)
 		io->res = -EIO;
 
 	if (io->res < 0) {
-		blk_mq_end_request(req, errno_to_blk_status(io->res));
-		return;
+		res = errno_to_blk_status(io->res);
+		goto exit;
 	}
 
 	/*
@@ -671,10 +669,8 @@ static 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) {
-		blk_mq_end_request(req, BLK_STS_OK);
-		return;
-	}
+	if (req_op(req) != REQ_OP_READ && req_op(req) != REQ_OP_WRITE)
+		goto exit;
 
 	/* for READ request, writing data in iod->addr to rq buffers */
 	unmapped_bytes = ublk_unmap_io(ubq, req, io);
@@ -691,6 +687,10 @@ static void ublk_complete_rq(struct request *req)
 		blk_mq_requeue_request(req, true);
 	else
 		__blk_mq_end_request(req, BLK_STS_OK);
+
+	return;
+exit:
+	blk_mq_end_request(req, res);
 }
 
 /*
@@ -771,9 +771,7 @@ static inline void __ublk_rq_task_work(struct request *req,
 		return;
 	}
 
-	if (ublk_need_get_data(ubq) &&
-			(req_op(req) == REQ_OP_WRITE ||
-			req_op(req) == REQ_OP_FLUSH)) {
+	if (ublk_need_get_data(ubq) && ublk_need_map_req(req)) {
 		/*
 		 * We have not handled UBLK_IO_NEED_GET_DATA command yet,
 		 * so immepdately pass UBLK_IO_RES_NEED_GET_DATA to ublksrv
@@ -1261,6 +1259,19 @@ static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id,
 	ublk_queue_cmd(ubq, req);
 }
 
+static inline int ublk_check_cmd_op(u32 cmd_op)
+{
+	u32 ioc_type = _IOC_TYPE(cmd_op);
+
+	if (IS_ENABLED(CONFIG_BLKDEV_UBLK_LEGACY_OPCODES) && ioc_type != 'u')
+		return -EOPNOTSUPP;
+
+	if (ioc_type != 'u' && ioc_type != 0)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			       unsigned int issue_flags,
 			       struct ublksrv_io_cmd *ub_cmd)
@@ -1303,10 +1314,15 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 	 * iff the driver have set the UBLK_IO_FLAG_NEED_GET_DATA.
 	 */
 	if ((!!(io->flags & UBLK_IO_FLAG_NEED_GET_DATA))
-			^ (cmd_op == UBLK_IO_NEED_GET_DATA))
+			^ (_IOC_NR(cmd_op) == UBLK_IO_NEED_GET_DATA))
+		goto out;
+
+	ret = ublk_check_cmd_op(cmd_op);
+	if (ret)
 		goto out;
 
-	switch (cmd_op) {
+	ret = -EINVAL;
+	switch (_IOC_NR(cmd_op)) {
 	case UBLK_IO_FETCH_REQ:
 		/* UBLK_IO_FETCH_REQ is only allowed before queue is setup */
 		if (ublk_queue_ready(ubq)) {
@@ -1770,6 +1786,8 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 	if (!IS_BUILTIN(CONFIG_BLK_DEV_UBLK))
 		ub->dev_info.flags |= UBLK_F_URING_CMD_COMP_IN_TASK;
 
+	ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE;
+
 	/* We are not ready to support zero copy */
 	ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY;
 
@@ -2128,7 +2146,7 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub,
 		 * know if the specified device is created as unprivileged
 		 * mode.
 		 */
-		if (cmd->cmd_op != UBLK_CMD_GET_DEV_INFO2)
+		if (_IOC_NR(cmd->cmd_op) != UBLK_CMD_GET_DEV_INFO2)
 			return 0;
 	}
 
@@ -2154,7 +2172,7 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub,
 	dev_path[header->dev_path_len] = 0;
 
 	ret = -EINVAL;
-	switch (cmd->cmd_op) {
+	switch (_IOC_NR(cmd->cmd_op)) {
 	case UBLK_CMD_GET_DEV_INFO:
 	case UBLK_CMD_GET_DEV_INFO2:
 	case UBLK_CMD_GET_QUEUE_AFFINITY:
@@ -2193,6 +2211,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 {
 	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
 	struct ublk_device *ub = NULL;
+	u32 cmd_op = cmd->cmd_op;
 	int ret = -EINVAL;
 
 	if (issue_flags & IO_URING_F_NONBLOCK)
@@ -2203,22 +2222,22 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 	if (!(issue_flags & IO_URING_F_SQE128))
 		goto out;
 
-	if (cmd->cmd_op != UBLK_CMD_ADD_DEV) {
+	ret = ublk_check_cmd_op(cmd_op);
+	if (ret)
+		goto out;
+
+	if (_IOC_NR(cmd_op) != UBLK_CMD_ADD_DEV) {
 		ret = -ENODEV;
 		ub = ublk_get_device_from_id(header->dev_id);
 		if (!ub)
 			goto out;
 
 		ret = ublk_ctrl_uring_cmd_permission(ub, cmd);
-	} else {
-		/* ADD_DEV permission check is done in command handler */
-		ret = 0;
+		if (ret)
+			goto put_dev;
 	}
 
-	if (ret)
-		goto put_dev;
-
-	switch (cmd->cmd_op) {
+	switch (_IOC_NR(cmd_op)) {
 	case UBLK_CMD_START_DEV:
 		ret = ublk_ctrl_start_dev(ub, cmd);
 		break;