blk-zoned: implement ioctls

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>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

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);
+}

block/ioctl.c

@@ -519,6 +519,10 @@ 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:

include/linux/blkdev.h

@@ -316,6 +316,27 @@ extern int blkdev_report_zones(struct block_device *bdev,
 extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors,
 			      sector_t nr_sectors, gfp_t gfp_mask);
 
+extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
+				     unsigned int cmd, unsigned long arg);
+extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
+				    unsigned int cmd, unsigned long arg);
+
+#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 {

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 */

include/uapi/linux/fs.h

@@ -225,6 +225,10 @@ 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 */