[PATCH v3 7/7] blk-zoned: implement ioctls

[PATCH v3 7/7] blk-zoned: implement ioctls

[Shaun Tancheff]

Adds the new BLKREPORTZONE and BLKRESETZONE ioctls for respectively
obtaining the zone configuration of a zoned block device and resetting
the write pointer of sequential zones of a zoned block device.

The BLKREPORTZONE ioctl maps directly to a single call of the function
blkdev_report_zones. The zone information result is passed as an array
of struct blk_zone identical to the structure used internally for
processing the REQ_OP_ZONE_REPORT operation.  The BLKRESETZONE ioctl
maps to a single call of the blkdev_reset_zones function.

Signed-off-by: Shaun Tancheff <shaun.tancheff@seagate.com>
Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com>
---
Changes since v2:
 - Changed kzalloc() to kcalloc() per Christoph
 - Added ioctl specific bits to uapi as blkzoned.h is now added in an earlier
   patch.

 block/blk-zoned.c             | 93 +++++++++++++++++++++++++++++++++++++++++++
 block/ioctl.c                 |  4 ++
 include/linux/blkdev.h        | 22 ++++++++++
 include/uapi/linux/blkzoned.h | 40 +++++++++++++++++++
 include/uapi/linux/fs.h       |  4 ++
 5 files changed, 163 insertions(+)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index bc4159d..91f7347 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -240,3 +240,96 @@ int blkdev_reset_zones(struct block_device *bdev,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blkdev_reset_zones);
+
+/**
+ * BLKREPORTZONE ioctl processing.
+ * Called from blkdev_ioctl.
+ */
+int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
+			      unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct request_queue *q;
+	struct blk_zone_report rep;
+	struct blk_zone *zones;
+	int ret;
+
+	if (!argp)
+		return -EINVAL;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -ENOTTY;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report)))
+		return -EFAULT;
+
+	if (!rep.nr_zones)
+		return -EINVAL;
+
+	zones = kcalloc(rep.nr_zones, sizeof(struct blk_zone), GFP_KERNEL);
+	if (!zones)
+		return -ENOMEM;
+
+	ret = blkdev_report_zones(bdev, rep.sector,
+				  zones, &rep.nr_zones,
+				  GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (rep.nr_zones) {
+		if (copy_to_user(argp + sizeof(struct blk_zone_report), zones,
+				 sizeof(struct blk_zone) * rep.nr_zones))
+			ret = -EFAULT;
+	}
+
+ out:
+	kfree(zones);
+
+	return ret;
+}
+
+/**
+ * BLKRESETZONE ioctl processing.
+ * Called from blkdev_ioctl.
+ */
+int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
+			     unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct request_queue *q;
+	struct blk_zone_range zrange;
+
+	if (!argp)
+		return -EINVAL;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -ENOTTY;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (!(mode & FMODE_WRITE))
+		return -EBADF;
+
+	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
+		return -EFAULT;
+
+	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
+				  GFP_KERNEL);
+}
diff --git a/block/ioctl.c b/block/ioctl.c
index ed2397f..448f78a 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -513,6 +513,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 				BLKDEV_DISCARD_SECURE);
 	case BLKZEROOUT:
 		return blk_ioctl_zeroout(bdev, mode, arg);
+	case BLKREPORTZONE:
+		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
+	case BLKRESETZONE:
+		return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg);
 	case HDIO_GETGEO:
 		return blkdev_getgeo(bdev, argp);
 	case BLKRAGET:
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6316972..0a75285 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -315,6 +315,28 @@ extern int blkdev_report_zones(struct block_device *,
 				unsigned int *, gfp_t);
 extern int blkdev_reset_zones(struct block_device *, sector_t,
 				sector_t, gfp_t);
+
+extern int blkdev_report_zones_ioctl(struct block_device *, fmode_t,
+				     unsigned int, unsigned long);
+extern int blkdev_reset_zones_ioctl(struct block_device *, fmode_t,
+				    unsigned int, unsigned long);
+
+#else /* CONFIG_BLK_DEV_ZONED */
+
+static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
+					    fmode_t mode, unsigned int cmd,
+					    unsigned long arg)
+{
+	return -ENOTTY;
+}
+
+static inline int blkdev_reset_zones_ioctl(struct block_device *bdev,
+					   fmode_t mode, unsigned int cmd,
+					   unsigned long arg)
+{
+	return -ENOTTY;
+}
+
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 struct request_queue {
diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
index a381721..40d1d7b 100644
--- a/include/uapi/linux/blkzoned.h
+++ b/include/uapi/linux/blkzoned.h
@@ -16,6 +16,7 @@
 #define _UAPI_BLKZONED_H
 
 #include <linux/types.h>
+#include <linux/ioctl.h>
 
 /**
  * enum blk_zone_type - Types of zones allowed in a zoned device.
@@ -100,4 +101,43 @@ struct blk_zone {
 	__u8	reserved[36];
 };
 
+/**
+ * struct blk_zone_report - BLKREPORTZONE ioctl request/reply
+ *
+ * @sector: starting sector of report
+ * @nr_zones: IN maximum / OUT actual
+ * @reserved: padding to 16 byte alignment
+ * @zones: Space to hold @nr_zones @zones entries on reply.
+ *
+ * The array of at most @nr_zones must follow this structure in memory.
+ */
+struct blk_zone_report {
+	__u64		sector;
+	__u32		nr_zones;
+	__u8		reserved[4];
+	struct blk_zone zones[0];
+} __packed;
+
+/**
+ * struct blk_zone_range - BLKRESETZONE ioctl request
+ * @sector: starting sector of the first zone to issue reset write pointer
+ * @nr_sectors: Total number of sectors of 1 or more zones to reset
+ */
+struct blk_zone_range {
+	__u64		sector;
+	__u64		nr_sectors;
+};
+
+/**
+ * Zoned block device ioctl's:
+ *
+ * @BLKREPORTZONE: Get zone information. Takes a zone report as argument.
+ *                 The zone report will start from the zone containing the
+ *                 sector specified in the report request structure.
+ * @BLKRESETZONE: Reset the write pointer of the zones in the specified
+ *                sector range. The sector range must be zone aligned.
+ */
+#define BLKREPORTZONE	_IOWR(0x12, 130, struct blk_zone_report)
+#define BLKRESETZONE	_IOW(0x12, 131, struct blk_zone_range)
+
 #endif /* _UAPI_BLKZONED_H */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 3b00f7c..e0fc7f0 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -222,6 +222,10 @@ struct fsxattr {
 #define BLKSECDISCARD _IO(0x12,125)
 #define BLKROTATIONAL _IO(0x12,126)
 #define BLKZEROOUT _IO(0x12,127)
+/*
+ * A jump here: 130-131 are reserved for zoned block devices
+ * (see uapi/linux/blkzoned.h)
+ */
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
-- 
2.9.3

Re: [PATCH v3 7/7] blk-zoned: implement ioctls

[Christoph Hellwig]

Damien, can you do a repost of the whole series with the
header reshuffled included?  Except for that and the trivial
kcalloc bit the series looks fine to me:

Reviewed-by: Christoph Hellwig <hch@lst.de>

[PATCH v3 0/7] ZBC / Zoned block device support

[Damien Le Moal]

This series introduces support for zoned block devices. It integrates
earlier submissions by Hannes Reinecke and Shaun Tancheff. Compared to the
previous series version, the code was significantly simplified by limiting
support to zoned devices satisfying the following conditions:
1) All zones of the device are the same size, with the exception of an
   eventual last smaller runt zone.
2) For host-managed disks, reads must be unrestricted (read commands do not
   fail due to zone or write pointer alignement constraints).
Zoned disks that do not satisfy these 2 conditions are ignored.

These 2 conditions allowed dropping the zone information cache implemented
in the previous version. This simplifies the code and also reduces the memory
consumption at run time. Support for zoned devices now only require one bit
per zone (less than 8KB in total). This bit field is used to write-lock
zones and prevent the concurrent execution of multiple write commands in
the same zone. This avoids write ordering problems at dispatch time, for
both the simple queue and scsi-mq settings.

The new operations introduced to suport zone manipulation was reduced to
only the two main ZBC/ZAC defined commands: REPORT ZONES (REQ_OP_ZONE_REPORT)
and RESET WRITE POINTER (REQ_OP_ZONE_RESET). This brings the total number of
operations defined to 8, which fits in the 3 bits (REQ_OP_BITS) reserved for
operation code in bio->bi_opf and req->cmd_flags.

Most of the ZBC specific code is kept out of sd.c and implemented in the
new file sd_zbc.c. Similarly, at the block layer, most of the zoned block
device code is implemented in the new blk-zoned.c.

For host-managed zoned block devices, the sequential write constraint of
write pointer zones is exposed to the user. Users of the disk (applications,
file systems or device mappers) must sequentially write to zones. This means
that for raw block device accesses from applications, buffered writes are
unreliable and direct I/Os must be used (or buffered writes with O_SYNC).

Access to zone manipulation operations is also provided to applications
through a set of new ioctls. This allows applications operating on raw
block devices (e.g. mkfs.xxx) to discover a device zone layout and
manipulate zone state.

Changes from v2:
* Use kcalloc to allocate zone information array for ioctl
* Use kcalloc to allocate zone information array for ioctl
* Export GPL the functions blkdev_report_zones and blkdev_reset_zones
* Shuffled uapi definitions from patch 7 into patch 5

Damien Le Moal (1):
  block: Add 'zoned' queue limit

Hannes Reinecke (4):
  blk-sysfs: Add 'chunk_sectors' to sysfs attributes
  block: update chunk_sectors in blk_stack_limits()
  block: Implement support for zoned block devices
  sd: Implement support for ZBC devices

Shaun Tancheff (2):
  block: Define zoned block device operations
  blk-zoned: implement ioctls

 block/Kconfig                 |   8 +
 block/Makefile                |   1 +
 block/blk-core.c              |   4 +
 block/blk-settings.c          |   5 +
 block/blk-sysfs.c             |  29 +++
 block/blk-zoned.c             | 350 +++++++++++++++++++++++++
 block/ioctl.c                 |   4 +
 drivers/scsi/Makefile         |   1 +
 drivers/scsi/sd.c             |  97 ++++++-
 drivers/scsi/sd.h             |  67 +++++
 drivers/scsi/sd_zbc.c         | 586 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/blk_types.h     |   2 +
 include/linux/blkdev.h        |  99 +++++++
 include/scsi/scsi_proto.h     |  17 ++
 include/uapi/linux/Kbuild     |   1 +
 include/uapi/linux/blkzoned.h | 143 +++++++++++
 include/uapi/linux/fs.h       |   4 +
 17 files changed, 1404 insertions(+), 14 deletions(-)
 create mode 100644 block/blk-zoned.c
 create mode 100644 drivers/scsi/sd_zbc.c
 create mode 100644 include/uapi/linux/blkzoned.h

-- 
2.7.4

[PATCH v3 7/7] blk-zoned: implement ioctls

[Damien Le Moal]

From: Shaun Tancheff <shaun@tancheff.com>

Adds the new BLKREPORTZONE and BLKRESETZONE ioctls for respectively
obtaining the zone configuration of a zoned block device and resetting
the write pointer of sequential zones of a zoned block device.

The BLKREPORTZONE ioctl maps directly to a single call of the function
blkdev_report_zones. The zone information result is passed as an array
of struct blk_zone identical to the structure used internally for
processing the REQ_OP_ZONE_REPORT operation.  The BLKRESETZONE ioctl
maps to a single call of the blkdev_reset_zones function.

Signed-off-by: Shaun Tancheff <shaun.tancheff@seagate.com>
Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com>
---
 block/blk-zoned.c             | 93 +++++++++++++++++++++++++++++++++++++++++++
 block/ioctl.c                 |  4 ++
 include/linux/blkdev.h        | 22 ++++++++++
 include/uapi/linux/blkzoned.h | 40 +++++++++++++++++++
 include/uapi/linux/fs.h       |  4 ++
 5 files changed, 163 insertions(+)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 7ebfc86..d354bea 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -255,3 +255,96 @@ int blkdev_reset_zones(struct block_device *bdev,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blkdev_reset_zones);
+
+/**
+ * BLKREPORTZONE ioctl processing.
+ * Called from blkdev_ioctl.
+ */
+int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
+			      unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct request_queue *q;
+	struct blk_zone_report rep;
+	struct blk_zone *zones;
+	int ret;
+
+	if (!argp)
+		return -EINVAL;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -ENOTTY;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report)))
+		return -EFAULT;
+
+	if (!rep.nr_zones)
+		return -EINVAL;
+
+	zones = kcalloc(rep.nr_zones, sizeof(struct blk_zone), GFP_KERNEL);
+	if (!zones)
+		return -ENOMEM;
+
+	ret = blkdev_report_zones(bdev, rep.sector,
+				  zones, &rep.nr_zones,
+				  GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (rep.nr_zones) {
+		if (copy_to_user(argp + sizeof(struct blk_zone_report), zones,
+				 sizeof(struct blk_zone) * rep.nr_zones))
+			ret = -EFAULT;
+	}
+
+ out:
+	kfree(zones);
+
+	return ret;
+}
+
+/**
+ * BLKRESETZONE ioctl processing.
+ * Called from blkdev_ioctl.
+ */
+int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
+			     unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct request_queue *q;
+	struct blk_zone_range zrange;
+
+	if (!argp)
+		return -EINVAL;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -ENOTTY;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (!(mode & FMODE_WRITE))
+		return -EBADF;
+
+	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
+		return -EFAULT;
+
+	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
+				  GFP_KERNEL);
+}
diff --git a/block/ioctl.c b/block/ioctl.c
index ed2397f..448f78a 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -513,6 +513,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 				BLKDEV_DISCARD_SECURE);
 	case BLKZEROOUT:
 		return blk_ioctl_zeroout(bdev, mode, arg);
+	case BLKREPORTZONE:
+		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
+	case BLKRESETZONE:
+		return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg);
 	case HDIO_GETGEO:
 		return blkdev_getgeo(bdev, argp);
 	case BLKRAGET:
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6316972..0a75285 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -315,6 +315,28 @@ extern int blkdev_report_zones(struct block_device *,
 				unsigned int *, gfp_t);
 extern int blkdev_reset_zones(struct block_device *, sector_t,
 				sector_t, gfp_t);
+
+extern int blkdev_report_zones_ioctl(struct block_device *, fmode_t,
+				     unsigned int, unsigned long);
+extern int blkdev_reset_zones_ioctl(struct block_device *, fmode_t,
+				    unsigned int, unsigned long);
+
+#else /* CONFIG_BLK_DEV_ZONED */
+
+static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
+					    fmode_t mode, unsigned int cmd,
+					    unsigned long arg)
+{
+	return -ENOTTY;
+}
+
+static inline int blkdev_reset_zones_ioctl(struct block_device *bdev,
+					   fmode_t mode, unsigned int cmd,
+					   unsigned long arg)
+{
+	return -ENOTTY;
+}
+
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 struct request_queue {
diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
index a381721..40d1d7b 100644
--- a/include/uapi/linux/blkzoned.h
+++ b/include/uapi/linux/blkzoned.h
@@ -16,6 +16,7 @@
 #define _UAPI_BLKZONED_H
 
 #include <linux/types.h>
+#include <linux/ioctl.h>
 
 /**
  * enum blk_zone_type - Types of zones allowed in a zoned device.
@@ -100,4 +101,43 @@ struct blk_zone {
 	__u8	reserved[36];
 };
 
+/**
+ * struct blk_zone_report - BLKREPORTZONE ioctl request/reply
+ *
+ * @sector: starting sector of report
+ * @nr_zones: IN maximum / OUT actual
+ * @reserved: padding to 16 byte alignment
+ * @zones: Space to hold @nr_zones @zones entries on reply.
+ *
+ * The array of at most @nr_zones must follow this structure in memory.
+ */
+struct blk_zone_report {
+	__u64		sector;
+	__u32		nr_zones;
+	__u8		reserved[4];
+	struct blk_zone zones[0];
+} __packed;
+
+/**
+ * struct blk_zone_range - BLKRESETZONE ioctl request
+ * @sector: starting sector of the first zone to issue reset write pointer
+ * @nr_sectors: Total number of sectors of 1 or more zones to reset
+ */
+struct blk_zone_range {
+	__u64		sector;
+	__u64		nr_sectors;
+};
+
+/**
+ * Zoned block device ioctl's:
+ *
+ * @BLKREPORTZONE: Get zone information. Takes a zone report as argument.
+ *                 The zone report will start from the zone containing the
+ *                 sector specified in the report request structure.
+ * @BLKRESETZONE: Reset the write pointer of the zones in the specified
+ *                sector range. The sector range must be zone aligned.
+ */
+#define BLKREPORTZONE	_IOWR(0x12, 130, struct blk_zone_report)
+#define BLKRESETZONE	_IOW(0x12, 131, struct blk_zone_range)
+
 #endif /* _UAPI_BLKZONED_H */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 3b00f7c..e0fc7f0 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -222,6 +222,10 @@ struct fsxattr {
 #define BLKSECDISCARD _IO(0x12,125)
 #define BLKROTATIONAL _IO(0x12,126)
 #define BLKZEROOUT _IO(0x12,127)
+/*
+ * A jump here: 130-131 are reserved for zoned block devices
+ * (see uapi/linux/blkzoned.h)
+ */
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
-- 
2.7.4

Re: [PATCH v3 7/7] blk-zoned: implement ioctls

[Martin K. Petersen]

>>>>> "Damien" == Damien Le Moal <damien.lemoal@hgst.com> writes:

Damien> Adds the new BLKREPORTZONE and BLKRESETZONE ioctls for
Damien> respectively obtaining the zone configuration of a zoned block
Damien> device and resetting the write pointer of sequential zones of a
Damien> zoned block device.

Damien> The BLKREPORTZONE ioctl maps directly to a single call of the
Damien> function blkdev_report_zones. The zone information result is
Damien> passed as an array of struct blk_zone identical to the structure
Damien> used internally for processing the REQ_OP_ZONE_REPORT operation.
Damien> The BLKRESETZONE ioctl maps to a single call of the
Damien> blkdev_reset_zones function.

Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>

-- 
Martin K. Petersen	Oracle Linux Engineering