add a ZONE_RESET_ALL uring cmd

add a ZONE_RESET_ALL uring cmd

[Christoph Hellwig]

Hi Jens,

this series adds a new ZONE_RESET_ALL uring cmd, and cleans up the discard
support a little bit in preparation for that.

This command is useful to speed up workloads that need to initialize a
large number (or even a small > 1 number) of disks.

Diffstat:
 block/ioctl.c               |   58 ++++++++++++++++++++++++++++++++++----------
 include/uapi/linux/blkdev.h |    1 
 2 files changed, 46 insertions(+), 13 deletions(-)

[PATCH 1/2] block: remove most blkdev_cmd_discard arguments

[Christoph Hellwig]

All other arguments can be derived from cmd, so do that to simplify the
calling convention.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/ioctl.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/block/ioctl.c b/block/ioctl.c
index 3d4ea1537457..af2a897f13f9 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -887,14 +887,13 @@ static void bio_cmd_bio_end_io(struct bio *bio)
 	bio_put(bio);
 }
 
-static int blkdev_cmd_discard(struct io_uring_cmd *cmd,
-			      struct block_device *bdev,
-			      uint64_t start, uint64_t len, bool nowait)
+static int blkdev_cmd_discard(struct io_uring_cmd *cmd)
 {
 	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
-	gfp_t gfp = nowait ? GFP_NOWAIT : GFP_KERNEL;
-	sector_t sector = start >> SECTOR_SHIFT;
-	sector_t nr_sects = len >> SECTOR_SHIFT;
+	struct block_device *bdev = I_BDEV(cmd->file->f_mapping->host);
+	gfp_t gfp = bic->nowait ? GFP_NOWAIT : GFP_KERNEL;
+	sector_t sector = bic->start >> SECTOR_SHIFT;
+	sector_t nr_sects = bic->len >> SECTOR_SHIFT;
 	struct bio *prev = NULL, *bio;
 	int err;
 
@@ -904,12 +903,12 @@ static int blkdev_cmd_discard(struct io_uring_cmd *cmd,
 		return -EBADF;
 	if (bdev_read_only(bdev))
 		return -EPERM;
-	err = blk_validate_byte_range(bdev, start, len);
+	err = blk_validate_byte_range(bdev, bic->start, bic->len);
 	if (err)
 		return err;
 
-	err = filemap_invalidate_pages(bdev->bd_mapping, start,
-					start + len - 1, nowait);
+	err = filemap_invalidate_pages(bdev->bd_mapping, bic->start,
+				       bic->start + bic->len - 1, bic->nowait);
 	if (err)
 		return err;
 
@@ -917,7 +916,7 @@ static int blkdev_cmd_discard(struct io_uring_cmd *cmd,
 		bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects, gfp);
 		if (!bio)
 			break;
-		if (nowait) {
+		if (bic->nowait) {
 			/*
 			 * Don't allow multi-bio non-blocking submissions as
 			 * subsequent bios may fail but we won't get a direct
@@ -946,7 +945,6 @@ static int blkdev_cmd_discard(struct io_uring_cmd *cmd,
 
 int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 {
-	struct block_device *bdev = I_BDEV(cmd->file->f_mapping->host);
 	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
 	u32 cmd_op = cmd->cmd_op;
 
@@ -967,8 +965,7 @@ int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 
 	switch (cmd_op) {
 	case BLOCK_URING_CMD_DISCARD:
-		return blkdev_cmd_discard(cmd, bdev, bic->start, bic->len,
-					  bic->nowait);
+		return blkdev_cmd_discard(cmd);
 	}
 	return -EINVAL;
 }
-- 
2.53.0

[PATCH 2/2] block: implement async io_uring zone reset all

[Christoph Hellwig]

Add a new BLOCK_URING_CMD_ZONE_RESET_ALL uring cmd to reset all zones
for a given block device.  This can be used by storage systems or
file system mkfs tools to initialize multiple devices in parallel.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/ioctl.c               | 35 +++++++++++++++++++++++++++++++++++
 include/uapi/linux/blkdev.h |  1 +
 2 files changed, 36 insertions(+)

diff --git a/block/ioctl.c b/block/ioctl.c
index af2a897f13f9..a6bdf7dd1fc1 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -14,6 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/io_uring/cmd.h>
 #include <linux/blk-integrity.h>
+#include <trace/events/block.h>
 #include <uapi/linux/blkdev.h>
 #include "blk.h"
 #include "blk-crypto-internal.h"
@@ -943,6 +944,38 @@ static int blkdev_cmd_discard(struct io_uring_cmd *cmd)
 	return -EIOCBQUEUED;
 }
 
+static int blkdev_cmd_zone_reset_all(struct io_uring_cmd *cmd)
+{
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+	struct block_device *bdev = I_BDEV(cmd->file->f_mapping->host);
+	struct bio *bio;
+	int err;
+
+	if (!(file_to_blk_mode(cmd->file) & BLK_OPEN_WRITE))
+		return -EBADF;
+	if (bdev_read_only(bdev))
+		return -EPERM;
+	if (!bdev_is_zoned(bdev))
+		return -EOPNOTSUPP;
+	if (bic->start || bic->len)
+		return -EINVAL;
+
+	err = filemap_invalidate_pages(bdev->bd_mapping, 0,
+				bdev_nr_bytes(bdev) - 1, bic->nowait);
+	if (err)
+		return err;
+
+	bio = bio_alloc(bdev, 0, REQ_OP_ZONE_RESET_ALL,
+			bic->nowait ? GFP_NOWAIT : GFP_KERNEL);
+	if (!bio)
+		return -EAGAIN;
+	trace_blkdev_zone_mgmt(bio, 0);
+	bio->bi_private = cmd;
+	bio->bi_end_io = bio_cmd_bio_end_io;
+	submit_bio(bio);
+	return -EIOCBQUEUED;
+}
+
 int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 {
 	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
@@ -966,6 +999,8 @@ int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 	switch (cmd_op) {
 	case BLOCK_URING_CMD_DISCARD:
 		return blkdev_cmd_discard(cmd);
+	case BLOCK_URING_CMD_ZONE_RESET_ALL:
+		return blkdev_cmd_zone_reset_all(cmd);
 	}
 	return -EINVAL;
 }
diff --git a/include/uapi/linux/blkdev.h b/include/uapi/linux/blkdev.h
index 66373cd1a83a..57b0bbd04e2b 100644
--- a/include/uapi/linux/blkdev.h
+++ b/include/uapi/linux/blkdev.h
@@ -10,5 +10,6 @@
  * It's a different number space from ioctl(), reuse the block's code 0x12.
  */
 #define BLOCK_URING_CMD_DISCARD			_IO(0x12, 0)
+#define BLOCK_URING_CMD_ZONE_RESET_ALL		_IO(0x12, 1)
 
 #endif
-- 
2.53.0

Re: [PATCH 1/2] block: remove most blkdev_cmd_discard arguments

[Damien Le Moal]

On 7/15/26 15:37, Christoph Hellwig wrote:
> All other arguments can be derived from cmd, so do that to simplify the
> calling convention.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Looks good to me.

Reviewed-by: Damien Le Moal <dlemoal@kernel.org>

-- 
Damien Le Moal
Western Digital Research

Re: [PATCH 2/2] block: implement async io_uring zone reset all

[Damien Le Moal]

On 7/15/26 15:37, Christoph Hellwig wrote:
> Add a new BLOCK_URING_CMD_ZONE_RESET_ALL uring cmd to reset all zones
> for a given block device.  This can be used by storage systems or
> file system mkfs tools to initialize multiple devices in parallel.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Looks good to me.

Reviewed-by: Damien Le Moal <dlemoal@kernel.org>

-- 
Damien Le Moal
Western Digital Research