diff mbox series

[V5,1/1] block: reject I/O for same fd if block size changed

Message ID 20210113143432.426-2-minwoo.im.dev@gmail.com (mailing list archive)
State New, archived
Headers show
Series block: fix I/O errors in BLKRRPART | expand

Commit Message

Minwoo Im Jan. 13, 2021, 2:34 p.m. UTC 
This patch fixes I/O errors during BLKRRPART ioctl() behavior right
after format operation that changed logical block size of the block
device with a same file descriptor opened.

This issue can be easily reproduced with a single format command in case
of NVMe (logical block size 512B to 4096B).

	nvme format /dev/nvme0n1 --lbaf=1 --force

This is because the application, nvme-cli format subcommand issues an
admin command followed by BLKRRPART ioctl to re-read partition
information without closing the file descriptor.  If file descriptor
stays opened, __blkdev_get() will not be invoked at all even logical
block size has been changed.

It will cause I/O errors with invalid Read operations during the
BLKRRPART ioctl due to i_blkbits mismatch. The invalid operations in
BLKRRPART happens with under-flowed Number of LBA(NLB) values
0xffff(65535) because i_blkbits is still set to 9 even the logical block
size has been updated to 4096.  The BLKRRPART will lead buffer_head to
hold 512B data which is less than the logical lock size of the block
device.

The root cause, which is because i_blkbits of inode of the block device
is not updated, can be solved easily by re-opening file descriptor
again from application.  But, that's just for application's business
and kernel should reject invalid Read operations during the BLKRRPART
ioctl.

This patch rejects I/O from the path of add_partitions() to avoid
issuing invalid Read operations to device.  It sets a flag to
request_queue in blk_queue_logical_block_size to minimize caller-side
updates.

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 block/blk-settings.c    |  3 +++
 block/partitions/core.c | 12 ++++++++++++
 fs/block_dev.c          |  8 ++++++++
 include/linux/blkdev.h  |  1 +
 4 files changed, 24 insertions(+)
diff mbox series

Patch

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 43990b1d148b..48a6fc7bb5f5 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -329,6 +329,9 @@  void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
 {
 	struct queue_limits *limits = &q->limits;
 
+	if (limits->logical_block_size != size)
+		blk_queue_flag_set(QUEUE_FLAG_LBSZ_CHANGED, q);
+
 	limits->logical_block_size = size;
 
 	if (limits->physical_block_size < size)
diff --git a/block/partitions/core.c b/block/partitions/core.c
index e7d776db803b..6f175ea18ff3 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -612,12 +612,24 @@  static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
 
 int blk_add_partitions(struct gendisk *disk, struct block_device *bdev)
 {
+	struct request_queue *q = bdev_get_queue(bdev);
 	struct parsed_partitions *state;
 	int ret = -EAGAIN, p, highest;
 
 	if (!disk_part_scan_enabled(disk))
 		return 0;
 
+	/*
+	 * Reject to check partition information if block size has been changed
+	 * in the runtime.  If block size of a block device has been changed,
+	 * the file descriptor should be opened agian to update the blkbits.
+	 */
+	if (test_bit(QUEUE_FLAG_LBSZ_CHANGED, &q->queue_flags)) {
+		pr_warn("%s: rejecting checking partition. fd should be opened again.\n",
+				disk->disk_name);
+		return -EBADFD;
+	}
+
 	state = check_partition(disk, bdev);
 	if (!state)
 		return 0;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 3b8963e228a1..db5b0b75f0be 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -130,7 +130,15 @@  EXPORT_SYMBOL(truncate_bdev_range);
 
 static void set_init_blocksize(struct block_device *bdev)
 {
+	struct request_queue *q = bdev_get_queue(bdev);
+
 	bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev));
+
+	/*
+	 * Allow I/O commands for this block device.  We can say that this
+	 * block device has proper blkbits updated.
+	 */
+	blk_queue_flag_clear(QUEUE_FLAG_LBSZ_CHANGED, q);
 }
 
 int set_blocksize(struct block_device *bdev, int size)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 070de09425ad..6d0542434be6 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -625,6 +625,7 @@  struct request_queue {
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
 #define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
 #define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
+#define QUEUE_FLAG_LBSZ_CHANGED	30	/* logical block size changed */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP) |		\