btrfs: get zone information of zoned block devices

If a zoned block device is found, get its zone information (number of
zones and zone size).  To avoid costly run-time zone report
commands to test the device zones type during block allocation, attach
the seq_zones bitmap to the device structure to indicate if a zone is
sequential or accept random writes. Also it attaches the empty_zones
bitmap to indicate if a zone is empty or not.

This patch also introduces the helper function btrfs_dev_is_sequential()
to test if the zone storing a block is a sequential write required zone
and btrfs_dev_is_empty_zone() to test if the zone is a empty zone.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/Makefile

@@ -16,6 +16,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
 btrfs-$(CONFIG_BTRFS_FS_REF_VERIFY) += ref-verify.o
+btrfs-$(CONFIG_BLK_DEV_ZONED) += zoned.o
 
 btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \
 	tests/extent-buffer-tests.o tests/btrfs-tests.o \

fs/btrfs/dev-replace.c

@@ -21,6 +21,7 @@
 #include "rcu-string.h"
 #include "dev-replace.h"
 #include "sysfs.h"
+#include "zoned.h"
 
 /*
  * Device replace overview
@@ -313,6 +314,10 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
 	device->fs_devices = fs_info->fs_devices;
 
+	ret = btrfs_get_dev_zone_info(device);
+	if (ret)
+		goto error;
+
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	list_add(&device->dev_list, &fs_info->fs_devices->devices);
 	fs_info->fs_devices->num_devices++;

fs/btrfs/super.c

@@ -2513,6 +2513,11 @@ static void __init btrfs_print_mod_info(void)
 #endif
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 			", ref-verify=on"
+#endif
+#ifdef CONFIG_BLK_DEV_ZONED
+			", zoned=yes"
+#else
+			", zoned=no"
 #endif
 			;
 	pr_info("Btrfs loaded, crc32c=%s%s\n", crc32c_impl(), options);

fs/btrfs/volumes.c

@@ -31,6 +31,7 @@
 #include "space-info.h"
 #include "block-group.h"
 #include "discard.h"
+#include "zoned.h"
 
 const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID10] = {
@@ -374,6 +375,7 @@ void btrfs_free_device(struct btrfs_device *device)
 	rcu_string_free(device->name);
 	extent_io_tree_release(&device->alloc_state);
 	bio_put(device->flush_bio);
+	btrfs_destroy_dev_zone_info(device);
 	kfree(device);
 }
 
@@ -667,6 +669,10 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	device->mode = flags;
 
+	ret = btrfs_get_dev_zone_info(device);
+	if (ret != 0)
+		goto error_free_page;
+
 	fs_devices->open_devices++;
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
 	    device->devid != BTRFS_DEV_REPLACE_DEVID) {
@@ -1137,6 +1143,7 @@ static void btrfs_close_one_device(struct btrfs_device *device)
 		device->bdev = NULL;
 	}
 	clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
+	btrfs_destroy_dev_zone_info(device);
 
 	device->fs_info = NULL;
 	atomic_set(&device->dev_stats_ccnt, 0);
@@ -2541,10 +2548,17 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	}
 	rcu_assign_pointer(device->name, name);
 
+	device->fs_info = fs_info;
+	device->bdev = bdev;
+
+	ret = btrfs_get_dev_zone_info(device);
+	if (ret)
+		goto error_free_device;
+
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
-		goto error_free_device;
+		goto error_free_zone;
 	}
 
 	q = bdev_get_queue(bdev);
@@ -2557,8 +2571,6 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 					 fs_info->sectorsize);
 	device->disk_total_bytes = device->total_bytes;
 	device->commit_total_bytes = device->total_bytes;
-	device->fs_info = fs_info;
-	device->bdev = bdev;
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
 	device->mode = FMODE_EXCL;
@@ -2705,6 +2717,8 @@ error_trans:
 		sb->s_flags |= SB_RDONLY;
 	if (trans)
 		btrfs_end_transaction(trans);
+error_free_zone:
+	btrfs_destroy_dev_zone_info(device);
 error_free_device:
 	btrfs_free_device(device);
 error:

fs/btrfs/volumes.h

@@ -52,6 +52,8 @@ struct btrfs_io_geometry {
 #define BTRFS_DEV_STATE_FLUSH_SENT	(4)
 #define BTRFS_DEV_STATE_NO_READA	(5)
 
+struct btrfs_zoned_device_info;
+
 struct btrfs_device {
 	struct list_head dev_list; /* device_list_mutex */
 	struct list_head dev_alloc_list; /* chunk mutex */
@@ -65,6 +67,8 @@ struct btrfs_device {
 
 	struct block_device *bdev;
 
+	struct btrfs_zoned_device_info *zone_info;
+
 	/* the mode sent to blkdev_get */
 	fmode_t mode;
 

fs/btrfs/zoned.c

@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include "ctree.h"
+#include "volumes.h"
+#include "zoned.h"
+#include "rcu-string.h"
+
+/* Maximum number of zones to report per blkdev_report_zones() call */
+#define BTRFS_REPORT_NR_ZONES   4096
+
+static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
+{
+	struct blk_zone *zones = data;
+
+	memcpy(&zones[idx], zone, sizeof(*zone));
+
+	return 0;
+}
+
+static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos,
+			       struct blk_zone *zones, unsigned int *nr_zones)
+{
+	int ret;
+
+	if (!*nr_zones)
+		return 0;
+
+	ret = blkdev_report_zones(device->bdev, pos >> SECTOR_SHIFT, *nr_zones,
+				  copy_zone_info_cb, zones);
+	if (ret < 0) {
+		btrfs_err_in_rcu(device->fs_info,
+				 "zoned: failed to read zone %llu on %s (devid %llu)",
+				 pos, rcu_str_deref(device->name),
+				 device->devid);
+		return ret;
+	}
+	*nr_zones = ret;
+	if (!ret)
+		return -EIO;
+
+	return 0;
+}
+
+int btrfs_get_dev_zone_info(struct btrfs_device *device)
+{
+	struct btrfs_zoned_device_info *zone_info = NULL;
+	struct block_device *bdev = device->bdev;
+	sector_t nr_sectors;
+	sector_t sector = 0;
+	struct blk_zone *zones = NULL;
+	unsigned int i, nreported = 0, nr_zones;
+	unsigned int zone_sectors;
+	int ret;
+
+	if (!bdev_is_zoned(bdev))
+		return 0;
+
+	if (device->zone_info)
+		return 0;
+
+	zone_info = kzalloc(sizeof(*zone_info), GFP_KERNEL);
+	if (!zone_info)
+		return -ENOMEM;
+
+	nr_sectors = bdev->bd_part->nr_sects;
+	zone_sectors = bdev_zone_sectors(bdev);
+	/* Check if it's power of 2 (see is_power_of_2) */
+	ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
+	zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
+	zone_info->zone_size_shift = ilog2(zone_info->zone_size);
+	zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors);
+	if (!IS_ALIGNED(nr_sectors, zone_sectors))
+		zone_info->nr_zones++;
+
+	zone_info->seq_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
+	if (!zone_info->seq_zones) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	zone_info->empty_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
+	if (!zone_info->empty_zones) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	zones = kcalloc(BTRFS_REPORT_NR_ZONES, sizeof(struct blk_zone), GFP_KERNEL);
+	if (!zones) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/* Get zones type */
+	while (sector < nr_sectors) {
+		nr_zones = BTRFS_REPORT_NR_ZONES;
+		ret = btrfs_get_dev_zones(device, sector << SECTOR_SHIFT, zones,
+					  &nr_zones);
+		if (ret)
+			goto out;
+
+		for (i = 0; i < nr_zones; i++) {
+			if (zones[i].type == BLK_ZONE_TYPE_SEQWRITE_REQ)
+				__set_bit(nreported, zone_info->seq_zones);
+			if (zones[i].cond == BLK_ZONE_COND_EMPTY)
+				__set_bit(nreported, zone_info->empty_zones);
+			nreported++;
+		}
+		sector = zones[nr_zones - 1].start + zones[nr_zones - 1].len;
+	}
+
+	if (nreported != zone_info->nr_zones) {
+		btrfs_err_in_rcu(device->fs_info,
+				 "inconsistent number of zones on %s (%u/%u)",
+				 rcu_str_deref(device->name), nreported,
+				 zone_info->nr_zones);
+		ret = -EIO;
+		goto out;
+	}
+
+	kfree(zones);
+
+	device->zone_info = zone_info;
+
+	/* device->fs_info is not safe to use for printing messages */
+	btrfs_info_in_rcu(NULL,
+			"host-%s zoned block device %s, %u zones of %llu bytes",
+			bdev_zoned_model(bdev) == BLK_ZONED_HM ? "managed" : "aware",
+			rcu_str_deref(device->name), zone_info->nr_zones,
+			zone_info->zone_size);
+
+	return 0;
+
+out:
+	kfree(zones);
+	bitmap_free(zone_info->empty_zones);
+	bitmap_free(zone_info->seq_zones);
+	kfree(zone_info);
+
+	return ret;
+}
+
+void btrfs_destroy_dev_zone_info(struct btrfs_device *device)
+{
+	struct btrfs_zoned_device_info *zone_info = device->zone_info;
+
+	if (!zone_info)
+		return;
+
+	bitmap_free(zone_info->seq_zones);
+	bitmap_free(zone_info->empty_zones);
+	kfree(zone_info);
+	device->zone_info = NULL;
+}
+
+int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
+		       struct blk_zone *zone)
+{
+	unsigned int nr_zones = 1;
+	int ret;
+
+	ret = btrfs_get_dev_zones(device, pos, zone, &nr_zones);
+	if (ret != 0 || !nr_zones)
+		return ret ? ret : -EIO;
+
+	return 0;
+}

fs/btrfs/zoned.h

@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_ZONED_H
+#define BTRFS_ZONED_H
+
+#include <linux/types.h>
+
+struct btrfs_zoned_device_info {
+	/*
+	 * Number of zones, zone size and types of zones if bdev is a
+	 * zoned block device.
+	 */
+	u64 zone_size;
+	u8  zone_size_shift;
+	u32 nr_zones;
+	unsigned long *seq_zones;
+	unsigned long *empty_zones;
+};
+
+#ifdef CONFIG_BLK_DEV_ZONED
+int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
+		       struct blk_zone *zone);
+int btrfs_get_dev_zone_info(struct btrfs_device *device);
+void btrfs_destroy_dev_zone_info(struct btrfs_device *device);
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
+				     struct blk_zone *zone)
+{
+	return 0;
+}
+
+static inline int btrfs_get_dev_zone_info(struct btrfs_device *device)
+{
+	return 0;
+}
+
+static inline void btrfs_destroy_dev_zone_info(struct btrfs_device *device) { }
+
+#endif
+
+static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
+{
+	struct btrfs_zoned_device_info *zone_info = device->zone_info;
+
+	if (!zone_info)
+		return false;
+
+	return test_bit(pos >> zone_info->zone_size_shift, zone_info->seq_zones);
+}
+
+static inline bool btrfs_dev_is_empty_zone(struct btrfs_device *device, u64 pos)
+{
+	struct btrfs_zoned_device_info *zone_info = device->zone_info;
+
+	if (!zone_info)
+		return true;
+
+	return test_bit(pos >> zone_info->zone_size_shift, zone_info->empty_zones);
+}
+
+static inline void btrfs_dev_set_empty_zone_bit(struct btrfs_device *device,
+						u64 pos, bool set)
+{
+	struct btrfs_zoned_device_info *zone_info = device->zone_info;
+	unsigned int zno;
+
+	if (!zone_info)
+		return;
+
+	zno = pos >> zone_info->zone_size_shift;
+	if (set)
+		set_bit(zno, zone_info->empty_zones);
+	else
+		clear_bit(zno, zone_info->empty_zones);
+}
+
+static inline void btrfs_dev_set_zone_empty(struct btrfs_device *device, u64 pos)
+{
+	btrfs_dev_set_empty_zone_bit(device, pos, true);
+}
+
+static inline void btrfs_dev_clear_zone_empty(struct btrfs_device *device, u64 pos)
+{
+	btrfs_dev_set_empty_zone_bit(device, pos, false);
+}
+
+#endif