Linux-BTRFS Archive on lore.kernel.org
 help / color / Atom feed
From: Naohiro Aota <naohiro.aota@wdc.com>
To: linux-btrfs@vger.kernel.org, David Sterba <dsterba@suse.com>
Cc: "Chris Mason" <clm@fb.com>, "Josef Bacik" <josef@toxicpanda.com>,
	"Qu Wenruo" <wqu@suse.com>, "Nikolay Borisov" <nborisov@suse.com>,
	linux-kernel@vger.kernel.org, "Hannes Reinecke" <hare@suse.com>,
	linux-fsdevel@vger.kernel.org,
	"Damien Le Moal" <damien.lemoal@wdc.com>,
	"Matias Bjørling" <mb@lightnvm.io>,
	"Johannes Thumshirn" <jthumshirn@suse.de>,
	"Bart Van Assche" <bvanassche@acm.org>,
	"Naohiro Aota" <naohiro.aota@wdc.com>
Subject: [PATCH 02/19] btrfs: Get zone information of zoned block devices
Date: Fri,  7 Jun 2019 22:10:08 +0900
Message-ID: <20190607131025.31996-3-naohiro.aota@wdc.com> (raw)
In-Reply-To: <20190607131025.31996-1-naohiro.aota@wdc.com>

If a zoned block device is found, get its zone information (number of zones
and zone size) using the new helper function btrfs_get_dev_zonetypes().  To
avoid costly run-time zone report commands to test the device zones type
during block allocation, attach the seqzones bitmap to the device structure
to indicate if a zone is sequential or accept random writes.

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.

Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
 fs/btrfs/volumes.c | 143 +++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/volumes.h |  33 +++++++++++
 2 files changed, 176 insertions(+)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1c2a6e4b39da..b673178718e3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -786,6 +786,135 @@ static int btrfs_free_stale_devices(const char *path,
 	return ret;
 }
 
+static int __btrfs_get_dev_zones(struct btrfs_device *device, u64 pos,
+				 struct blk_zone **zones,
+				 unsigned int *nr_zones, gfp_t gfp_mask)
+{
+	struct blk_zone *z = *zones;
+	int ret;
+
+	if (!z) {
+		z = kcalloc(*nr_zones, sizeof(struct blk_zone), GFP_KERNEL);
+		if (!z)
+			return -ENOMEM;
+	}
+
+	ret = blkdev_report_zones(device->bdev, pos >> SECTOR_SHIFT,
+				  z, nr_zones, gfp_mask);
+	if (ret != 0) {
+		btrfs_err(device->fs_info, "Get zone at %llu failed %d\n",
+			  pos, ret);
+		return ret;
+	}
+
+	*zones = z;
+
+	return 0;
+}
+
+static void btrfs_destroy_dev_zonetypes(struct btrfs_device *device)
+{
+	kfree(device->seq_zones);
+	kfree(device->empty_zones);
+	device->seq_zones = NULL;
+	device->empty_zones = NULL;
+	device->nr_zones = 0;
+	device->zone_size = 0;
+	device->zone_size_shift = 0;
+}
+
+int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
+		       struct blk_zone *zone, gfp_t gfp_mask)
+{
+	unsigned int nr_zones = 1;
+	int ret;
+
+	ret = __btrfs_get_dev_zones(device, pos, &zone, &nr_zones, gfp_mask);
+	if (ret != 0 || !nr_zones)
+		return ret ? ret : -EIO;
+
+	return 0;
+}
+
+int btrfs_get_dev_zonetypes(struct btrfs_device *device)
+{
+	struct block_device *bdev = device->bdev;
+	sector_t nr_sectors = bdev->bd_part->nr_sects;
+	sector_t sector = 0;
+	struct blk_zone *zones = NULL;
+	unsigned int i, n = 0, nr_zones;
+	int ret;
+
+	device->zone_size = 0;
+	device->zone_size_shift = 0;
+	device->nr_zones = 0;
+	device->seq_zones = NULL;
+	device->empty_zones = NULL;
+
+	if (!bdev_is_zoned(bdev))
+		return 0;
+
+	device->zone_size = (u64)bdev_zone_sectors(bdev) << SECTOR_SHIFT;
+	device->zone_size_shift = ilog2(device->zone_size);
+	device->nr_zones = nr_sectors >> ilog2(bdev_zone_sectors(bdev));
+	if (nr_sectors & (bdev_zone_sectors(bdev) - 1))
+		device->nr_zones++;
+
+	device->seq_zones = kcalloc(BITS_TO_LONGS(device->nr_zones),
+				    sizeof(*device->seq_zones), GFP_KERNEL);
+	if (!device->seq_zones)
+		return -ENOMEM;
+
+	device->empty_zones = kcalloc(BITS_TO_LONGS(device->nr_zones),
+				      sizeof(*device->empty_zones), GFP_KERNEL);
+	if (!device->empty_zones)
+		return -ENOMEM;
+
+#define BTRFS_REPORT_NR_ZONES   4096
+
+	/* 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, GFP_KERNEL);
+		if (ret != 0 || !nr_zones) {
+			if (!ret)
+				ret = -EIO;
+			goto out;
+		}
+
+		for (i = 0; i < nr_zones; i++) {
+			if (zones[i].type == BLK_ZONE_TYPE_SEQWRITE_REQ)
+				set_bit(n, device->seq_zones);
+			if (zones[i].cond == BLK_ZONE_COND_EMPTY)
+				set_bit(n, device->empty_zones);
+			sector = zones[i].start + zones[i].len;
+			n++;
+		}
+	}
+
+	if (n != device->nr_zones) {
+		btrfs_err(device->fs_info,
+			  "Inconsistent number of zones (%u / %u)\n", n,
+			  device->nr_zones);
+		ret = -EIO;
+		goto out;
+	}
+
+	btrfs_info(device->fs_info,
+		   "host-%s zoned block device, %u zones of %llu sectors\n",
+		   bdev_zoned_model(bdev) == BLK_ZONED_HM ? "managed" : "aware",
+		   device->nr_zones, device->zone_size >> SECTOR_SHIFT);
+
+out:
+	kfree(zones);
+
+	if (ret)
+		btrfs_destroy_dev_zonetypes(device);
+
+	return ret;
+}
+
 static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 			struct btrfs_device *device, fmode_t flags,
 			void *holder)
@@ -842,6 +971,11 @@ 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;
 
+	/* Get zone type information of zoned block devices */
+	ret = btrfs_get_dev_zonetypes(device);
+	if (ret != 0)
+		goto error_brelse;
+
 	fs_devices->open_devices++;
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
 	    device->devid != BTRFS_DEV_REPLACE_DEVID) {
@@ -1243,6 +1377,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 	}
 
 	blkdev_put(device->bdev, device->mode);
+	btrfs_destroy_dev_zonetypes(device);
 }
 
 static void btrfs_close_one_device(struct btrfs_device *device)
@@ -2664,6 +2799,13 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	mutex_unlock(&fs_info->chunk_mutex);
 	mutex_unlock(&fs_devices->device_list_mutex);
 
+	/* Get zone type information of zoned block devices */
+	ret = btrfs_get_dev_zonetypes(device);
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto error_sysfs;
+	}
+
 	if (seeding_dev) {
 		mutex_lock(&fs_info->chunk_mutex);
 		ret = init_first_rw_device(trans);
@@ -2729,6 +2871,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	return ret;
 
 error_sysfs:
+	btrfs_destroy_dev_zonetypes(device);
 	btrfs_sysfs_rm_device_link(fs_devices, device);
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	mutex_lock(&fs_info->chunk_mutex);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index b8a0e8d0672d..1599641e216c 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -62,6 +62,16 @@ struct btrfs_device {
 
 	struct block_device *bdev;
 
+	/*
+	 * 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;
+
 	/* the mode sent to blkdev_get */
 	fmode_t mode;
 
@@ -476,6 +486,28 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset);
 struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
 				       u64 logical, u64 length);
+int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
+		       struct blk_zone *zone, gfp_t gfp_mask);
+
+static inline int btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
+{
+	unsigned int zno = pos >> device->zone_size_shift;
+
+	if (!device->seq_zones)
+		return 1;
+
+	return test_bit(zno, device->seq_zones);
+}
+
+static inline int btrfs_dev_is_empty_zone(struct btrfs_device *device, u64 pos)
+{
+	unsigned int zno = pos >> device->zone_size_shift;
+
+	if (!device->empty_zones)
+		return 0;
+
+	return test_bit(zno, device->empty_zones);
+}
 
 static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
 				      int index)
@@ -568,5 +600,6 @@ bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 
 int btrfs_bg_type_to_factor(u64 flags);
 int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info);
+int btrfs_get_dev_zonetypes(struct btrfs_device *device);
 
 #endif
-- 
2.21.0


  parent reply index

Thread overview: 79+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-07 13:10 [PATCH v2 00/19] btrfs zoned block device support Naohiro Aota
2019-06-07 13:10 ` [PATCH 01/19] btrfs: introduce HMZONED feature flag Naohiro Aota
2019-06-07 13:10 ` Naohiro Aota [this message]
2019-06-13 13:58   ` [PATCH 02/19] btrfs: Get zone information of zoned block devices Josef Bacik
2019-06-18  6:04     ` Naohiro Aota
2019-06-13 13:58   ` Josef Bacik
2019-06-17 18:57   ` David Sterba
2019-06-18  6:42     ` Naohiro Aota
2019-06-27 15:11       ` David Sterba
2019-06-07 13:10 ` [PATCH 03/19] btrfs: Check and enable HMZONED mode Naohiro Aota
2019-06-13 13:57   ` Josef Bacik
2019-06-18  6:43     ` Naohiro Aota
2019-06-07 13:10 ` [PATCH 04/19] btrfs: disable fallocate in " Naohiro Aota
2019-06-07 13:10 ` [PATCH 05/19] btrfs: disable direct IO " Naohiro Aota
2019-06-13 14:00   ` Josef Bacik
2019-06-18  8:17     ` Naohiro Aota
2019-06-07 13:10 ` [PATCH 06/19] btrfs: align dev extent allocation to zone boundary Naohiro Aota
2019-06-07 13:10 ` [PATCH 07/19] btrfs: do sequential extent allocation in HMZONED mode Naohiro Aota
2019-06-13 14:07   ` Josef Bacik
2019-06-18  8:28     ` Naohiro Aota
2019-06-18 13:37       ` Josef Bacik
2019-06-17 22:30   ` David Sterba
2019-06-18  8:49     ` Naohiro Aota
2019-06-27 15:28       ` David Sterba
2019-06-07 13:10 ` [PATCH 08/19] btrfs: make unmirroed BGs readonly only if we have at least one writable BG Naohiro Aota
2019-06-13 14:09   ` Josef Bacik
2019-06-18  7:42     ` Naohiro Aota
2019-06-18 13:35       ` Josef Bacik
2019-06-07 13:10 ` [PATCH 09/19] btrfs: limit super block locations in HMZONED mode Naohiro Aota
2019-06-13 14:12   ` Josef Bacik
2019-06-18  8:51     ` Naohiro Aota
2019-06-17 22:53   ` David Sterba
2019-06-18  9:01     ` Naohiro Aota
2019-06-27 15:35       ` David Sterba
2019-06-28  3:55   ` Anand Jain
2019-06-28  6:39     ` Naohiro Aota
2019-06-28  6:52       ` Anand Jain
2019-06-07 13:10 ` [PATCH 10/19] btrfs: rename btrfs_map_bio() Naohiro Aota
2019-06-07 13:10 ` [PATCH 11/19] btrfs: introduce submit buffer Naohiro Aota
2019-06-13 14:14   ` Josef Bacik
2019-06-17  3:16     ` Damien Le Moal
2019-06-18  0:00       ` David Sterba
2019-06-18  4:04         ` Damien Le Moal
2019-06-18 13:33       ` Josef Bacik
2019-06-19 10:32         ` Damien Le Moal
2019-06-07 13:10 ` [PATCH 12/19] btrfs: expire submit buffer on timeout Naohiro Aota
2019-06-13 14:15   ` Josef Bacik
2019-06-17  3:19     ` Damien Le Moal
2019-06-07 13:10 ` [PATCH 13/19] btrfs: avoid sync IO prioritization on checksum in HMZONED mode Naohiro Aota
2019-06-13 14:17   ` Josef Bacik
2019-06-07 13:10 ` [PATCH 14/19] btrfs: redirty released extent buffers in sequential BGs Naohiro Aota
2019-06-13 14:24   ` Josef Bacik
2019-06-18  9:09     ` Naohiro Aota
2019-06-07 13:10 ` [PATCH 15/19] btrfs: reset zones of unused block groups Naohiro Aota
2019-06-07 13:10 ` [PATCH 16/19] btrfs: wait existing extents before truncating Naohiro Aota
2019-06-13 14:25   ` Josef Bacik
2019-06-07 13:10 ` [PATCH 17/19] btrfs: shrink delayed allocation size in HMZONED mode Naohiro Aota
2019-06-13 14:27   ` Josef Bacik
2019-06-07 13:10 ` [PATCH 18/19] btrfs: support dev-replace " Naohiro Aota
2019-06-13 14:33   ` Josef Bacik
2019-06-18  9:14     ` Naohiro Aota
2019-06-07 13:10 ` [PATCH 19/19] btrfs: enable to mount HMZONED incompat flag Naohiro Aota
2019-06-07 13:17 ` [PATCH 01/12] btrfs-progs: build: Check zoned block device support Naohiro Aota
2019-06-07 13:17   ` [PATCH 02/12] btrfs-progs: utils: Introduce queue_param Naohiro Aota
2019-06-07 13:17   ` [PATCH 03/12] btrfs-progs: add new HMZONED feature flag Naohiro Aota
2019-06-07 13:17   ` [PATCH 04/12] btrfs-progs: Introduce zone block device helper functions Naohiro Aota
2019-06-07 13:17   ` [PATCH 05/12] btrfs-progs: load and check zone information Naohiro Aota
2019-06-07 13:17   ` [PATCH 06/12] btrfs-progs: avoid writing super block to sequential zones Naohiro Aota
2019-06-07 13:17   ` [PATCH 07/12] btrfs-progs: support discarding zoned device Naohiro Aota
2019-06-07 13:17   ` [PATCH 08/12] btrfs-progs: volume: align chunk allocation to zones Naohiro Aota
2019-06-07 13:17   ` [PATCH 09/12] btrfs-progs: do sequential allocation Naohiro Aota
2019-06-07 13:17   ` [PATCH 10/12] btrfs-progs: mkfs: Zoned block device support Naohiro Aota
2019-06-07 13:17   ` [PATCH 11/12] btrfs-progs: device-add: support HMZONED device Naohiro Aota
2019-06-07 13:17   ` [PATCH 12/12] btrfs-progs: introduce support for dev-place " Naohiro Aota
2019-06-12 17:51 ` [PATCH v2 00/19] btrfs zoned block device support David Sterba
2019-06-13  4:59   ` Naohiro Aota
2019-06-13 13:46     ` David Sterba
2019-06-14  2:07       ` Naohiro Aota
2019-06-17  2:44       ` Damien Le Moal

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190607131025.31996-3-naohiro.aota@wdc.com \
    --to=naohiro.aota@wdc.com \
    --cc=bvanassche@acm.org \
    --cc=clm@fb.com \
    --cc=damien.lemoal@wdc.com \
    --cc=dsterba@suse.com \
    --cc=hare@suse.com \
    --cc=josef@toxicpanda.com \
    --cc=jthumshirn@suse.de \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mb@lightnvm.io \
    --cc=nborisov@suse.com \
    --cc=wqu@suse.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-BTRFS Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-btrfs/0 linux-btrfs/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-btrfs linux-btrfs/ https://lore.kernel.org/linux-btrfs \
		linux-btrfs@vger.kernel.org linux-btrfs@archiver.kernel.org
	public-inbox-index linux-btrfs


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-btrfs


AGPL code for this site: git clone https://public-inbox.org/ public-inbox