block: Implement support for zoned block devices

Implement zoned block device zone information reporting and reset.
Zone information are reported as struct blk_zone. This implementation
does not differentiate between host-aware and host-managed device
models and is valid for both. Two functions are provided:
blkdev_report_zones for discovering the zone configuration of a
zoned block device, and blkdev_reset_zones for resetting the write
pointer of sequential zones. The helper function blk_queue_zone_size
and bdev_zone_size are also provided for, as the name suggest,
obtaining the zone size (in 512B sectors) of the zones of the device.

Signed-off-by: Hannes Reinecke <hare@suse.de>

[Damien: * Removed the zone cache
         * Implement report zones operation based on earlier proposal
           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: Shaun Tancheff <shaun.tancheff@seagate.com>
Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

3 files changed, 135 insertions, 0 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f19e16bb43d1..252043f7cd2c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,7 @@
 #include <linux/rcupdate.h>
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
+#include <linux/blkzoned.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -302,6 +303,21 @@ struct queue_limits {
 	enum blk_zoned_model	zoned;
 };
 
+#ifdef CONFIG_BLK_DEV_ZONED
+
+struct blk_zone_report_hdr {
+	unsigned int	nr_zones;
+	u8		padding[60];
+};
+
+extern int blkdev_report_zones(struct block_device *bdev,
+			       sector_t sector, struct blk_zone *zones,
+			       unsigned int *nr_zones, gfp_t gfp_mask);
+extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors,
+			      sector_t nr_sectors, gfp_t gfp_mask);
+
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 struct request_queue {
 	/*
 	 * Together with queue_head for cacheline sharing
@@ -654,6 +670,11 @@ static inline bool blk_queue_is_zoned(struct request_queue *q)
 	}
 }
 
+static inline unsigned int blk_queue_zone_size(struct request_queue *q)
+{
+	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
+}
+
 /*
  * We regard a request as sync, if either a read or a sync write
  */
@@ -1401,6 +1422,16 @@ static inline bool bdev_is_zoned(struct block_device *bdev)
 	return false;
 }
 
+static inline unsigned int bdev_zone_size(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return blk_queue_zone_size(q);
+
+	return 0;
+}
+
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 6965d0909554..b2166f283da9 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -70,6 +70,7 @@ header-y += bfs_fs.h
 header-y += binfmts.h
 header-y += blkpg.h
 header-y += blktrace_api.h
+header-y += blkzoned.h
 header-y += bpf_common.h
 header-y += bpf_perf_event.h
 header-y += bpf.h
diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
new file mode 100644
index 000000000000..a3817214b0e0
--- /dev/null
+++ b/include/uapi/linux/blkzoned.h
@@ -0,0 +1,103 @@
+/*
+ * Zoned block devices handling.
+ *
+ * Copyright (C) 2015 Seagate Technology PLC
+ *
+ * Written by: Shaun Tancheff <shaun.tancheff@seagate.com>
+ *
+ * Modified by: Damien Le Moal <damien.lemoal@hgst.com>
+ * Copyright (C) 2016 Western Digital
+ *
+ * This file is licensed under  the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#ifndef _UAPI_BLKZONED_H
+#define _UAPI_BLKZONED_H
+
+#include <linux/types.h>
+
+/**
+ * enum blk_zone_type - Types of zones allowed in a zoned device.
+ *
+ * @BLK_ZONE_TYPE_CONVENTIONAL: The zone has no write pointer and can be writen
+ *                              randomly. Zone reset has no effect on the zone.
+ * @BLK_ZONE_TYPE_SEQWRITE_REQ: The zone must be written sequentially
+ * @BLK_ZONE_TYPE_SEQWRITE_PREF: The zone can be written non-sequentially
+ *
+ * Any other value not defined is reserved and must be considered as invalid.
+ */
+enum blk_zone_type {
+	BLK_ZONE_TYPE_CONVENTIONAL	= 0x1,
+	BLK_ZONE_TYPE_SEQWRITE_REQ	= 0x2,
+	BLK_ZONE_TYPE_SEQWRITE_PREF	= 0x3,
+};
+
+/**
+ * enum blk_zone_cond - Condition [state] of a zone in a zoned device.
+ *
+ * @BLK_ZONE_COND_NOT_WP: The zone has no write pointer, it is conventional.
+ * @BLK_ZONE_COND_EMPTY: The zone is empty.
+ * @BLK_ZONE_COND_IMP_OPEN: The zone is open, but not explicitly opened.
+ * @BLK_ZONE_COND_EXP_OPEN: The zones was explicitly opened by an
+ *                          OPEN ZONE command.
+ * @BLK_ZONE_COND_CLOSED: The zone was [explicitly] closed after writing.
+ * @BLK_ZONE_COND_FULL: The zone is marked as full, possibly by a zone
+ *                      FINISH ZONE command.
+ * @BLK_ZONE_COND_READONLY: The zone is read-only.
+ * @BLK_ZONE_COND_OFFLINE: The zone is offline (sectors cannot be read/written).
+ *
+ * The Zone Condition state machine in the ZBC/ZAC standards maps the above
+ * deinitions as:
+ *   - ZC1: Empty         | BLK_ZONE_EMPTY
+ *   - ZC2: Implicit Open | BLK_ZONE_COND_IMP_OPEN
+ *   - ZC3: Explicit Open | BLK_ZONE_COND_EXP_OPEN
+ *   - ZC4: Closed        | BLK_ZONE_CLOSED
+ *   - ZC5: Full          | BLK_ZONE_FULL
+ *   - ZC6: Read Only     | BLK_ZONE_READONLY
+ *   - ZC7: Offline       | BLK_ZONE_OFFLINE
+ *
+ * Conditions 0x5 to 0xC are reserved by the current ZBC/ZAC spec and should
+ * be considered invalid.
+ */
+enum blk_zone_cond {
+	BLK_ZONE_COND_NOT_WP	= 0x0,
+	BLK_ZONE_COND_EMPTY	= 0x1,
+	BLK_ZONE_COND_IMP_OPEN	= 0x2,
+	BLK_ZONE_COND_EXP_OPEN	= 0x3,
+	BLK_ZONE_COND_CLOSED	= 0x4,
+	BLK_ZONE_COND_READONLY	= 0xD,
+	BLK_ZONE_COND_FULL	= 0xE,
+	BLK_ZONE_COND_OFFLINE	= 0xF,
+};
+
+/**
+ * struct blk_zone - Zone descriptor for BLKREPORTZONE ioctl.
+ *
+ * @start: Zone start in 512 B sector units
+ * @len: Zone length in 512 B sector units
+ * @wp: Zone write pointer location in 512 B sector units
+ * @type: see enum blk_zone_type for possible values
+ * @cond: see enum blk_zone_cond for possible values
+ * @non_seq: Flag indicating that the zone is using non-sequential resources
+ *           (for host-aware zoned block devices only).
+ * @reset: Flag indicating that a zone reset is recommended.
+ * @reserved: Padding to 64 B to match the ZBC/ZAC defined zone descriptor size.
+ *
+ * start, len and wp use the regular 512 B sector unit, regardless of the
+ * device logical block size. The overall structure size is 64 B to match the
+ * ZBC/ZAC defined zone descriptor and allow support for future additional
+ * zone information.
+ */
+struct blk_zone {
+	__u64	start;		/* Zone start sector */
+	__u64	len;		/* Zone length in number of sectors */
+	__u64	wp;		/* Zone write pointer position */
+	__u8	type;		/* Zone type */
+	__u8	cond;		/* Zone condition */
+	__u8	non_seq;	/* Non-sequential write resources active */
+	__u8	reset;		/* Reset write pointer recommended */
+	__u8	reserved[36];
+};
+
+#endif /* _UAPI_BLKZONED_H */