Merge tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull request via Keith:
      - Various cleanups all around (Irvin, Chaitanya, Christophe)
      - Better struct packing (Christophe JAILLET)
      - Reduce controller error logs for optional commands (Keith)
      - Support for >=64KiB block sizes (Daniel Gomez)
      - Fabrics fixes and code organization (Max, Chaitanya, Daniel
        Wagner)

 - bcache updates via Coly:
      - Fix a race at init time (Mingzhe Zou)
      - Misc fixes and cleanups (Andrea, Thomas, Zheng, Ye)

 - use page pinning in the block layer for dio (David)

 - convert old block dio code to page pinning (David, Christoph)

 - cleanups for pktcdvd (Andy)

 - cleanups for rnbd (Guoqing)

 - use the unchecked __bio_add_page() for the initial single page
   additions (Johannes)

 - fix overflows in the Amiga partition handling code (Michael)

 - improve mq-deadline zoned device support (Bart)

 - keep passthrough requests out of the IO schedulers (Christoph, Ming)

 - improve support for flush requests, making them less special to deal
   with (Christoph)

 - add bdev holder ops and shutdown methods (Christoph)

 - fix the name_to_dev_t() situation and use cases (Christoph)

 - decouple the block open flags from fmode_t (Christoph)

 - ublk updates and cleanups, including adding user copy support (Ming)

 - BFQ sanity checking (Bart)

 - convert brd from radix to xarray (Pankaj)

 - constify various structures (Thomas, Ivan)

 - more fine grained persistent reservation ioctl capability checks
   (Jingbo)

 - misc fixes and cleanups (Arnd, Azeem, Demi, Ed, Hengqi, Hou, Jan,
   Jordy, Li, Min, Yu, Zhong, Waiman)

* tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux: (266 commits)
  scsi/sg: don't grab scsi host module reference
  ext4: Fix warning in blkdev_put()
  block: don't return -EINVAL for not found names in devt_from_devname
  cdrom: Fix spectre-v1 gadget
  block: Improve kernel-doc headers
  blk-mq: don't insert passthrough request into sw queue
  bsg: make bsg_class a static const structure
  ublk: make ublk_chr_class a static const structure
  aoe: make aoe_class a static const structure
  block/rnbd: make all 'class' structures const
  block: fix the exclusive open mask in disk_scan_partitions
  block: add overflow checks for Amiga partition support
  block: change all __u32 annotations to __be32 in affs_hardblocks.h
  block: fix signed int overflow in Amiga partition support
  block: add capacity validation in bdev_add_partition()
  block: fine-granular CAP_SYS_ADMIN for Persistent Reservation
  block: disallow Persistent Reservation on partitions
  reiserfs: fix blkdev_put() warning from release_journal_dev()
  block: fix wrong mode for blkdev_get_by_dev() from disk_scan_partitions()
  block: document the holder argument to blkdev_get_by_path
  ...

4 files changed, 49 insertions, 34 deletions

diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index 4cd37ec45762..be106dc20ff3 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -209,40 +209,34 @@ static void block2mtd_free_device(struct block2mtd_dev *dev)
 	if (dev->blkdev) {
 		invalidate_mapping_pages(dev->blkdev->bd_inode->i_mapping,
 					0, -1);
-		blkdev_put(dev->blkdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+		blkdev_put(dev->blkdev, NULL);
 	}
 
 	kfree(dev);
 }
 
-
-static struct block2mtd_dev *add_device(char *devname, int erase_size,
-		char *label, int timeout)
+/*
+ * This function is marked __ref because it calls the __init marked
+ * early_lookup_bdev when called from the early boot code.
+ */
+static struct block_device __ref *mdtblock_early_get_bdev(const char *devname,
+		blk_mode_t mode, int timeout, struct block2mtd_dev *dev)
 {
+	struct block_device *bdev = ERR_PTR(-ENODEV);
 #ifndef MODULE
 	int i;
-#endif
-	const fmode_t mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL;
-	struct block_device *bdev;
-	struct block2mtd_dev *dev;
-	char *name;
 
-	if (!devname)
-		return NULL;
-
-	dev = kzalloc(sizeof(struct block2mtd_dev), GFP_KERNEL);
-	if (!dev)
-		return NULL;
-
-	/* Get a handle on the device */
-	bdev = blkdev_get_by_path(devname, mode, dev);
+	/*
+	 * We can't use early_lookup_bdev from a running system.
+	 */
+	if (system_state >= SYSTEM_RUNNING)
+		return bdev;
 
-#ifndef MODULE
 	/*
 	 * We might not have the root device mounted at this point.
 	 * Try to resolve the device name by other means.
 	 */
-	for (i = 0; IS_ERR(bdev) && i <= timeout; i++) {
+	for (i = 0; i <= timeout; i++) {
 		dev_t devt;
 
 		if (i)
@@ -254,13 +248,35 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size,
 			msleep(1000);
 		wait_for_device_probe();
 
-		devt = name_to_dev_t(devname);
-		if (!devt)
-			continue;
-		bdev = blkdev_get_by_dev(devt, mode, dev);
+		if (!early_lookup_bdev(devname, &devt)) {
+			bdev = blkdev_get_by_dev(devt, mode, dev, NULL);
+			if (!IS_ERR(bdev))
+				break;
+		}
 	}
 #endif
+	return bdev;
+}
 
+static struct block2mtd_dev *add_device(char *devname, int erase_size,
+		char *label, int timeout)
+{
+	const blk_mode_t mode = BLK_OPEN_READ | BLK_OPEN_WRITE;
+	struct block_device *bdev;
+	struct block2mtd_dev *dev;
+	char *name;
+
+	if (!devname)
+		return NULL;
+
+	dev = kzalloc(sizeof(struct block2mtd_dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	/* Get a handle on the device */
+	bdev = blkdev_get_by_path(devname, mode, dev, NULL);
+	if (IS_ERR(bdev))
+		bdev = mdtblock_early_get_bdev(devname, mode, timeout, dev);
 	if (IS_ERR(bdev)) {
 		pr_err("error: cannot open device %s\n", devname);
 		goto err_free_block2mtd;
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 60b222799871..ff18636e0889 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -182,9 +182,9 @@ static blk_status_t mtd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
-static int blktrans_open(struct block_device *bdev, fmode_t mode)
+static int blktrans_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct mtd_blktrans_dev *dev = bdev->bd_disk->private_data;
+	struct mtd_blktrans_dev *dev = disk->private_data;
 	int ret = 0;
 
 	kref_get(&dev->ref);
@@ -208,7 +208,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode)
 	ret = __get_mtd_device(dev->mtd);
 	if (ret)
 		goto error_release;
-	dev->file_mode = mode;
+	dev->writable = mode & BLK_OPEN_WRITE;
 
 unlock:
 	dev->open++;
@@ -225,7 +225,7 @@ error_put:
 	return ret;
 }
 
-static void blktrans_release(struct gendisk *disk, fmode_t mode)
+static void blktrans_release(struct gendisk *disk)
 {
 	struct mtd_blktrans_dev *dev = disk->private_data;
 
diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c
index a0a1194dc1d9..fa476fb4dffb 100644
--- a/drivers/mtd/mtdblock.c
+++ b/drivers/mtd/mtdblock.c
@@ -294,7 +294,7 @@ static void mtdblock_release(struct mtd_blktrans_dev *mbd)
 		 * It was the last usage. Free the cache, but only sync if
 		 * opened for writing.
 		 */
-		if (mbd->file_mode & FMODE_WRITE)
+		if (mbd->writable)
 			mtd_sync(mbd->mtd);
 		vfree(mtdblk->cache_data);
 	}
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index 3711d7f74600..437c5b83ffe5 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -227,9 +227,9 @@ static blk_status_t ubiblock_read(struct request *req)
 	return BLK_STS_OK;
 }
 
-static int ubiblock_open(struct block_device *bdev, fmode_t mode)
+static int ubiblock_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct ubiblock *dev = bdev->bd_disk->private_data;
+	struct ubiblock *dev = disk->private_data;
 	int ret;
 
 	mutex_lock(&dev->dev_mutex);
@@ -246,11 +246,10 @@ static int ubiblock_open(struct block_device *bdev, fmode_t mode)
 	 * It's just a paranoid check, as write requests will get rejected
 	 * in any case.
 	 */
-	if (mode & FMODE_WRITE) {
+	if (mode & BLK_OPEN_WRITE) {
 		ret = -EROFS;
 		goto out_unlock;
 	}
-
 	dev->desc = ubi_open_volume(dev->ubi_num, dev->vol_id, UBI_READONLY);
 	if (IS_ERR(dev->desc)) {
 		dev_err(disk_to_dev(dev->gd), "failed to open ubi volume %d_%d",
@@ -270,7 +269,7 @@ out_unlock:
 	return ret;
 }
 
-static void ubiblock_release(struct gendisk *gd, fmode_t mode)
+static void ubiblock_release(struct gendisk *gd)
 {
 	struct ubiblock *dev = gd->private_data;