Merge tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Improve the type checking of request flags (Bart)

 - Ensure queue mapping for a single queues always picks the right queue
   (Bart)

 - Sanitize the io priority handling (Jan)

 - rq-qos race fix (Jinke)

 - Reserved tags handling improvements (John)

 - Separate memory alignment from file/disk offset aligment for O_DIRECT
   (Keith)

 - Add new ublk driver, userspace block driver using io_uring for
   communication with the userspace backend (Ming)

 - Use try_cmpxchg() to cleanup the code in various spots (Uros)

 - Finally remove bdevname() (Christoph)

 - Clean up the zoned device handling (Christoph)

 - Clean up independent access range support (Christoph)

 - Clean up and improve block sysfs handling (Christoph)

 - Clean up and improve teardown of block devices.

   This turns the usual two step process into something that is simpler
   to implement and handle in block drivers (Christoph)

 - Clean up chunk size handling (Christoph)

 - Misc cleanups and fixes (Bart, Bo, Dan, GuoYong, Jason, Keith, Liu,
   Ming, Sebastian, Yang, Ying)

* tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block: (178 commits)
  ublk_drv: fix double shift bug
  ublk_drv: make sure that correct flags(features) returned to userspace
  ublk_drv: fix error handling of ublk_add_dev
  ublk_drv: fix lockdep warning
  block: remove __blk_get_queue
  block: call blk_mq_exit_queue from disk_release for never added disks
  blk-mq: fix error handling in __blk_mq_alloc_disk
  ublk: defer disk allocation
  ublk: rewrite ublk_ctrl_get_queue_affinity to not rely on hctx->cpumask
  ublk: fold __ublk_create_dev into ublk_ctrl_add_dev
  ublk: cleanup ublk_ctrl_uring_cmd
  ublk: simplify ublk_ch_open and ublk_ch_release
  ublk: remove the empty open and release block device operations
  ublk: remove UBLK_IO_F_PREFLUSH
  ublk: add a MAINTAINERS entry
  block: don't allow the same type rq_qos add more than once
  mmc: fix disk/queue leak in case of adding disk failure
  ublk_drv: fix an IS_ERR() vs NULL check
  ublk: remove UBLK_IO_F_INTEGRITY
  ublk_drv: remove unneeded semicolon
  ...

4 files changed, 41 insertions, 46 deletions

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 35d40a67204c..304ed2be1b83 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -638,7 +638,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
 			   !buffer_new(bh) &&
 			   ocfs2_should_read_blk(inode, page, block_start) &&
 			   (block_start < from || block_end > to)) {
-			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+			ll_rw_block(REQ_OP_READ, 1, &bh);
 			*wait_bh++=bh;
 		}
 
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index e7758778abef..196638a22b48 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -64,7 +64,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 
 	get_bh(bh); /* for end_buffer_write_sync() */
 	bh->b_end_io = end_buffer_write_sync;
-	submit_bh(REQ_OP_WRITE, 0, bh);
+	submit_bh(REQ_OP_WRITE, bh);
 
 	wait_on_buffer(bh);
 
@@ -147,7 +147,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 
 		get_bh(bh); /* for end_buffer_read_sync() */
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(REQ_OP_READ, 0, bh);
+		submit_bh(REQ_OP_READ, bh);
 	}
 
 read_failure:
@@ -328,7 +328,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 			if (validate)
 				set_buffer_needs_validate(bh);
 			bh->b_end_io = end_buffer_read_sync;
-			submit_bh(REQ_OP_READ, 0, bh);
+			submit_bh(REQ_OP_READ, bh);
 			continue;
 		}
 	}
@@ -449,7 +449,7 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
 	get_bh(bh); /* for end_buffer_write_sync() */
 	bh->b_end_io = end_buffer_write_sync;
 	ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &di->i_check);
-	submit_bh(REQ_OP_WRITE, 0, bh);
+	submit_bh(REQ_OP_WRITE, bh);
 
 	wait_on_buffer(bh);
 
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index ea0e70c0fce0..b13d344d40b6 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -235,8 +235,6 @@ struct o2hb_region {
 	 * (hr_steady_iterations == 0) within hr_unsteady_iterations */
 	atomic_t		hr_unsteady_iterations;
 
-	char			hr_dev_name[BDEVNAME_SIZE];
-
 	unsigned int		hr_timeout_ms;
 
 	/* randomized as the region goes up and down so that a node
@@ -287,8 +285,8 @@ static void o2hb_write_timeout(struct work_struct *work)
 		container_of(work, struct o2hb_region,
 			     hr_write_timeout_work.work);
 
-	mlog(ML_ERROR, "Heartbeat write timeout to device %s after %u "
-	     "milliseconds\n", reg->hr_dev_name,
+	mlog(ML_ERROR, "Heartbeat write timeout to device %pg after %u "
+	     "milliseconds\n", reg->hr_bdev,
 	     jiffies_to_msecs(jiffies - reg->hr_last_timeout_start));
 
 	if (o2hb_global_heartbeat_active()) {
@@ -383,9 +381,9 @@ static void o2hb_nego_timeout(struct work_struct *work)
 
 	if (master_node == o2nm_this_node()) {
 		if (!test_bit(master_node, reg->hr_nego_node_bitmap)) {
-			printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s).\n",
+			printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg).\n",
 				o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000,
-				config_item_name(&reg->hr_item), reg->hr_dev_name);
+				config_item_name(&reg->hr_item), reg->hr_bdev);
 			set_bit(master_node, reg->hr_nego_node_bitmap);
 		}
 		if (memcmp(reg->hr_nego_node_bitmap, live_node_bitmap,
@@ -399,8 +397,8 @@ static void o2hb_nego_timeout(struct work_struct *work)
 			return;
 		}
 
-		printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%s) is down.\n",
-			config_item_name(&reg->hr_item), reg->hr_dev_name);
+		printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%pg) is down.\n",
+			config_item_name(&reg->hr_item), reg->hr_bdev);
 		/* approve negotiate timeout request. */
 		o2hb_arm_timeout(reg);
 
@@ -419,9 +417,9 @@ static void o2hb_nego_timeout(struct work_struct *work)
 		}
 	} else {
 		/* negotiate timeout with master node. */
-		printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s), negotiate timeout with node %d.\n",
+		printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg), negotiate timeout with node %d.\n",
 			o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, config_item_name(&reg->hr_item),
-			reg->hr_dev_name, master_node);
+			reg->hr_bdev, master_node);
 		ret = o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG,
 				master_node);
 		if (ret)
@@ -437,8 +435,8 @@ static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data,
 	struct o2hb_nego_msg *nego_msg;
 
 	nego_msg = (struct o2hb_nego_msg *)msg->buf;
-	printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%s).\n",
-		nego_msg->node_num, config_item_name(&reg->hr_item), reg->hr_dev_name);
+	printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%pg).\n",
+		nego_msg->node_num, config_item_name(&reg->hr_item), reg->hr_bdev);
 	if (nego_msg->node_num < O2NM_MAX_NODES)
 		set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap);
 	else
@@ -452,8 +450,8 @@ static int o2hb_nego_approve_handler(struct o2net_msg *msg, u32 len, void *data,
 {
 	struct o2hb_region *reg = data;
 
-	printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%s).\n",
-		config_item_name(&reg->hr_item), reg->hr_dev_name);
+	printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%pg).\n",
+		config_item_name(&reg->hr_item), reg->hr_bdev);
 	o2hb_arm_timeout(reg);
 	return 0;
 }
@@ -503,8 +501,7 @@ static void o2hb_bio_end_io(struct bio *bio)
 static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 				      struct o2hb_bio_wait_ctxt *wc,
 				      unsigned int *current_slot,
-				      unsigned int max_slots, int op,
-				      int op_flags)
+				      unsigned int max_slots, blk_opf_t opf)
 {
 	int len, current_page;
 	unsigned int vec_len, vec_start;
@@ -518,7 +515,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 	 * GFP_KERNEL that the local node can get fenced. It would be
 	 * nicest if we could pre-allocate these bios and avoid this
 	 * all together. */
-	bio = bio_alloc(reg->hr_bdev, 16, op | op_flags, GFP_ATOMIC);
+	bio = bio_alloc(reg->hr_bdev, 16, opf, GFP_ATOMIC);
 	if (!bio) {
 		mlog(ML_ERROR, "Could not alloc slots BIO!\n");
 		bio = ERR_PTR(-ENOMEM);
@@ -566,7 +563,7 @@ static int o2hb_read_slots(struct o2hb_region *reg,
 
 	while(current_slot < max_slots) {
 		bio = o2hb_setup_one_bio(reg, &wc, &current_slot, max_slots,
-					 REQ_OP_READ, 0);
+					 REQ_OP_READ);
 		if (IS_ERR(bio)) {
 			status = PTR_ERR(bio);
 			mlog_errno(status);
@@ -598,8 +595,8 @@ static int o2hb_issue_node_write(struct o2hb_region *reg,
 
 	slot = o2nm_this_node();
 
-	bio = o2hb_setup_one_bio(reg, write_wc, &slot, slot+1, REQ_OP_WRITE,
-				 REQ_SYNC);
+	bio = o2hb_setup_one_bio(reg, write_wc, &slot, slot+1,
+				 REQ_OP_WRITE | REQ_SYNC);
 	if (IS_ERR(bio)) {
 		status = PTR_ERR(bio);
 		mlog_errno(status);
@@ -689,8 +686,8 @@ static int o2hb_check_own_slot(struct o2hb_region *reg)
 	else
 		errstr = ERRSTR3;
 
-	mlog(ML_ERROR, "%s (%s): expected(%u:0x%llx, 0x%llx), "
-	     "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg->hr_dev_name,
+	mlog(ML_ERROR, "%s (%pg): expected(%u:0x%llx, 0x%llx), "
+	     "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg->hr_bdev,
 	     slot->ds_node_num, (unsigned long long)slot->ds_last_generation,
 	     (unsigned long long)slot->ds_last_time, hb_block->hb_node,
 	     (unsigned long long)le64_to_cpu(hb_block->hb_generation),
@@ -863,8 +860,8 @@ static void o2hb_set_quorum_device(struct o2hb_region *reg)
 		   sizeof(o2hb_live_node_bitmap)))
 		goto unlock;
 
-	printk(KERN_NOTICE "o2hb: Region %s (%s) is now a quorum device\n",
-	       config_item_name(&reg->hr_item), reg->hr_dev_name);
+	printk(KERN_NOTICE "o2hb: Region %s (%pg) is now a quorum device\n",
+	       config_item_name(&reg->hr_item), reg->hr_bdev);
 
 	set_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
 
@@ -922,8 +919,8 @@ static int o2hb_check_slot(struct o2hb_region *reg,
 		/* The node is live but pushed out a bad crc. We
 		 * consider it a transient miss but don't populate any
 		 * other values as they may be junk. */
-		mlog(ML_ERROR, "Node %d has written a bad crc to %s\n",
-		     slot->ds_node_num, reg->hr_dev_name);
+		mlog(ML_ERROR, "Node %d has written a bad crc to %pg\n",
+		     slot->ds_node_num, reg->hr_bdev);
 		o2hb_dump_slot(hb_block);
 
 		slot->ds_equal_samples++;
@@ -1002,11 +999,11 @@ fire_callbacks:
 		slot_dead_ms = le32_to_cpu(hb_block->hb_dead_ms);
 		if (slot_dead_ms && slot_dead_ms != dead_ms) {
 			/* TODO: Perhaps we can fail the region here. */
-			mlog(ML_ERROR, "Node %d on device %s has a dead count "
+			mlog(ML_ERROR, "Node %d on device %pg has a dead count "
 			     "of %u ms, but our count is %u ms.\n"
 			     "Please double check your configuration values "
 			     "for 'O2CB_HEARTBEAT_THRESHOLD'\n",
-			     slot->ds_node_num, reg->hr_dev_name, slot_dead_ms,
+			     slot->ds_node_num, reg->hr_bdev, slot_dead_ms,
 			     dead_ms);
 		}
 		goto out;
@@ -1145,8 +1142,8 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
 		/* Do not re-arm the write timeout on I/O error - we
 		 * can't be sure that the new block ever made it to
 		 * disk */
-		mlog(ML_ERROR, "Write error %d on device \"%s\"\n",
-		     write_wc.wc_error, reg->hr_dev_name);
+		mlog(ML_ERROR, "Write error %d on device \"%pg\"\n",
+		     write_wc.wc_error, reg->hr_bdev);
 		ret = write_wc.wc_error;
 		goto bail;
 	}
@@ -1170,9 +1167,9 @@ bail:
 	if (atomic_read(&reg->hr_steady_iterations) != 0) {
 		if (atomic_dec_and_test(&reg->hr_unsteady_iterations)) {
 			printk(KERN_NOTICE "o2hb: Unable to stabilize "
-			       "heartbeat on region %s (%s)\n",
+			       "heartbeat on region %s (%pg)\n",
 			       config_item_name(&reg->hr_item),
-			       reg->hr_dev_name);
+			       reg->hr_bdev);
 			atomic_set(&reg->hr_steady_iterations, 0);
 			reg->hr_aborted_start = 1;
 			wake_up(&o2hb_steady_queue);
@@ -1494,7 +1491,7 @@ static void o2hb_region_release(struct config_item *item)
 	struct page *page;
 	struct o2hb_region *reg = to_o2hb_region(item);
 
-	mlog(ML_HEARTBEAT, "hb region release (%s)\n", reg->hr_dev_name);
+	mlog(ML_HEARTBEAT, "hb region release (%pg)\n", reg->hr_bdev);
 
 	kfree(reg->hr_tmp_block);
 
@@ -1641,7 +1638,7 @@ static ssize_t o2hb_region_dev_show(struct config_item *item, char *page)
 	unsigned int ret = 0;
 
 	if (to_o2hb_region(item)->hr_bdev)
-		ret = sprintf(page, "%s\n", to_o2hb_region(item)->hr_dev_name);
+		ret = sprintf(page, "%pg\n", to_o2hb_region(item)->hr_bdev);
 
 	return ret;
 }
@@ -1798,8 +1795,6 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 		goto out2;
 	}
 
-	bdevname(reg->hr_bdev, reg->hr_dev_name);
-
 	sectsize = bdev_logical_block_size(reg->hr_bdev);
 	if (sectsize != reg->hr_block_bytes) {
 		mlog(ML_ERROR,
@@ -1895,8 +1890,8 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 		ret = -EIO;
 
 	if (hb_task && o2hb_global_heartbeat_active())
-		printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%s)\n",
-		       config_item_name(&reg->hr_item), reg->hr_dev_name);
+		printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%pg)\n",
+		       config_item_name(&reg->hr_item), reg->hr_bdev);
 
 out3:
 	if (ret < 0) {
@@ -2088,10 +2083,10 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group,
 			quorum_region = 1;
 		clear_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
 		spin_unlock(&o2hb_live_lock);
-		printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%s)\n",
+		printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%pg)\n",
 		       ((atomic_read(&reg->hr_steady_iterations) == 0) ?
 			"stopped" : "start aborted"), config_item_name(item),
-		       reg->hr_dev_name);
+		       reg->hr_bdev);
 	}
 
 	/*
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 438be028935d..013a727bd7c8 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1764,7 +1764,7 @@ static int ocfs2_get_sector(struct super_block *sb,
 	if (!buffer_dirty(*bh))
 		clear_buffer_uptodate(*bh);
 	unlock_buffer(*bh);
-	ll_rw_block(REQ_OP_READ, 0, 1, bh);
+	ll_rw_block(REQ_OP_READ, 1, bh);
 	wait_on_buffer(*bh);
 	if (!buffer_uptodate(*bh)) {
 		mlog_errno(-EIO);