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>,
	Nikolay Borisov <nborisov@suse.com>,
	Damien Le Moal <damien.lemoal@wdc.com>,
	Matias Bjorling <Matias.Bjorling@wdc.com>,
	Johannes Thumshirn <jthumshirn@suse.de>,
	Hannes Reinecke <hare@suse.com>,
	linux-fsdevel@vger.kernel.org,
	Naohiro Aota <naohiro.aota@wdc.com>
Subject: [PATCH v3 02/27] btrfs: Get zone information of zoned block devices
Date: Thu,  8 Aug 2019 18:30:13 +0900
Message-ID: <20190808093038.4163421-3-naohiro.aota@wdc.com> (raw)
In-Reply-To: <20190808093038.4163421-1-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 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.

Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
 fs/btrfs/Makefile  |   2 +-
 fs/btrfs/hmzoned.c | 162 +++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/hmzoned.h |  79 ++++++++++++++++++++++
 fs/btrfs/volumes.c |  18 ++++-
 fs/btrfs/volumes.h |   4 ++
 5 files changed, 262 insertions(+), 3 deletions(-)
 create mode 100644 fs/btrfs/hmzoned.c
 create mode 100644 fs/btrfs/hmzoned.h

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 76a843198bcb..8d93abb31074 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -11,7 +11,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
 	   reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
 	   uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \
-	   block-rsv.o delalloc-space.o
+	   block-rsv.o delalloc-space.o hmzoned.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
diff --git a/fs/btrfs/hmzoned.c b/fs/btrfs/hmzoned.c
new file mode 100644
index 000000000000..bfd04792dd62
--- /dev/null
+++ b/fs/btrfs/hmzoned.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ * Authors:
+ *	Naohiro Aota	<naohiro.aota@wdc.com>
+ *	Damien Le Moal	<damien.lemoal@wdc.com>
+ */
+
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include "ctree.h"
+#include "volumes.h"
+#include "hmzoned.h"
+#include "rcu-string.h"
+
+/* Maximum number of zones to report per blkdev_report_zones() call */
+#define BTRFS_REPORT_NR_ZONES   4096
+
+static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos,
+			       struct blk_zone **zones_ret,
+			       unsigned int *nr_zones, gfp_t gfp_mask)
+{
+	struct blk_zone *zones = *zones_ret;
+	int ret;
+
+	if (!zones) {
+		zones = kcalloc(*nr_zones, sizeof(struct blk_zone), GFP_KERNEL);
+		if (!zones)
+			return -ENOMEM;
+	}
+
+	ret = blkdev_report_zones(device->bdev, pos >> SECTOR_SHIFT,
+				  zones, nr_zones, gfp_mask);
+	if (ret != 0) {
+		btrfs_err_in_rcu(device->fs_info,
+				 "get zone at %llu on %s failed %d", pos,
+				 rcu_str_deref(device->name), ret);
+		return ret;
+	}
+	if (!*nr_zones)
+		return -EIO;
+
+	*zones_ret = zones;
+
+	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 = bdev->bd_part->nr_sects;
+	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;
+
+	zone_info = kzalloc(sizeof(*zone_info), GFP_KERNEL);
+	if (!zone_info)
+		return -ENOMEM;
+
+	zone_sectors = bdev_zone_sectors(bdev);
+	ASSERT(is_power_of_2(zone_sectors));
+	zone_info->zone_size = (u64)zone_sectors << SECTOR_SHIFT;
+	zone_info->zone_size_shift = ilog2(zone_info->zone_size);
+	zone_info->nr_zones = nr_sectors >> ilog2(bdev_zone_sectors(bdev));
+	if (nr_sectors & (bdev_zone_sectors(bdev) - 1))
+		zone_info->nr_zones++;
+
+	zone_info->seq_zones = kcalloc(BITS_TO_LONGS(zone_info->nr_zones),
+				       sizeof(*zone_info->seq_zones),
+				       GFP_KERNEL);
+	if (!zone_info->seq_zones) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	zone_info->empty_zones = kcalloc(BITS_TO_LONGS(zone_info->nr_zones),
+					 sizeof(*zone_info->empty_zones),
+					 GFP_KERNEL);
+	if (!zone_info->empty_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, GFP_KERNEL);
+		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;
+	}
+
+	device->zone_info = zone_info;
+
+	btrfs_info_in_rcu(
+		device->fs_info,
+		"host-%s zoned block device %s, %u zones of %llu sectors",
+		bdev_zoned_model(bdev) == BLK_ZONED_HM ? "managed" : "aware",
+		rcu_str_deref(device->name), zone_info->nr_zones,
+		zone_info->zone_size >> SECTOR_SHIFT);
+
+out:
+	kfree(zones);
+
+	if (ret) {
+		kfree(zone_info->seq_zones);
+		kfree(zone_info->empty_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;
+
+	kfree(zone_info->seq_zones);
+	kfree(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, 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;
+}
diff --git a/fs/btrfs/hmzoned.h b/fs/btrfs/hmzoned.h
new file mode 100644
index 000000000000..ffc70842135e
--- /dev/null
+++ b/fs/btrfs/hmzoned.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ * Authors:
+ *	Naohiro Aota	<naohiro.aota@wdc.com>
+ *	Damien Le Moal	<damien.lemoal@wdc.com>
+ */
+
+#ifndef BTRFS_HMZONED_H
+#define BTRFS_HMZONED_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;
+};
+
+int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
+		       struct blk_zone *zone, gfp_t gfp_mask);
+int btrfs_get_dev_zone_info(struct btrfs_device *device);
+void btrfs_destroy_dev_zone_info(struct btrfs_device *device);
+
+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
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d74b74ca07af..8e5a894e7bde 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -29,6 +29,7 @@
 #include "sysfs.h"
 #include "tree-checker.h"
 #include "space-info.h"
+#include "hmzoned.h"
 
 const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID10] = {
@@ -342,6 +343,7 @@ 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);
 }
 
@@ -847,6 +849,11 @@ 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_zone_info(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) {
@@ -2598,6 +2605,14 @@ 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;
+
+	/* Get zone type information of zoned block devices */
+	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);
@@ -2614,8 +2629,6 @@ 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;
@@ -2756,6 +2769,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		sb->s_flags |= SB_RDONLY;
 	if (trans)
 		btrfs_end_transaction(trans);
+	btrfs_destroy_dev_zone_info(device);
 error_free_device:
 	btrfs_free_device(device);
 error:
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 7f6aa1816409..5da1f354db93 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -57,6 +57,8 @@ struct btrfs_io_geometry {
 #define BTRFS_DEV_STATE_REPLACE_TGT	(3)
 #define BTRFS_DEV_STATE_FLUSH_SENT	(4)
 
+struct btrfs_zoned_device_info;
+
 struct btrfs_device {
 	struct list_head dev_list; /* device_list_mutex */
 	struct list_head dev_alloc_list; /* chunk mutex */
@@ -77,6 +79,8 @@ struct btrfs_device {
 
 	struct block_device *bdev;
 
+	struct btrfs_zoned_device_info *zone_info;
+
 	/* the mode sent to blkdev_get */
 	fmode_t mode;
 
-- 
2.22.0


  parent reply index

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-08  9:30 [PATCH v3 00/27] btrfs zoned block device support Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 01/27] btrfs: introduce HMZONED feature flag Naohiro Aota
2019-08-16  4:49   ` Anand Jain
2019-08-08  9:30 ` Naohiro Aota [this message]
2019-08-16  4:44   ` [PATCH v3 02/27] btrfs: Get zone information of zoned block devices Anand Jain
2019-08-16 14:19     ` Damien Le Moal
2019-08-16 23:47       ` Anand Jain
2019-08-16 23:55         ` Damien Le Moal
2019-08-08  9:30 ` [PATCH v3 03/27] btrfs: Check and enable HMZONED mode Naohiro Aota
2019-08-16  5:46   ` Anand Jain
2019-08-16 14:23     ` Damien Le Moal
2019-08-16 23:56       ` Anand Jain
2019-08-17  0:05         ` Damien Le Moal
2019-08-20  5:07         ` Naohiro Aota
2019-08-20 13:05           ` David Sterba
2019-08-08  9:30 ` [PATCH v3 04/27] btrfs: disallow RAID5/6 in " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 05/27] btrfs: disallow space_cache " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 06/27] btrfs: disallow NODATACOW " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 07/27] btrfs: disable tree-log " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 08/27] btrfs: disable fallocate " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 09/27] btrfs: align device extent allocation to zone boundary Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 10/27] btrfs: do sequential extent allocation in HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 11/27] btrfs: make unmirroed BGs readonly only if we have at least one writable BG Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 12/27] btrfs: ensure metadata space available on/after degraded mount in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 13/27] btrfs: reset zones of unused block groups Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 14/27] btrfs: limit super block locations in HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 15/27] btrfs: redirty released extent buffers in sequential BGs Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 16/27] btrfs: serialize data allocation and submit IOs Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 17/27] btrfs: implement atomic compressed IO submission Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 18/27] btrfs: support direct write IO in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 19/27] btrfs: serialize meta IOs on HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 20/27] btrfs: wait existing extents before truncating Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 21/27] btrfs: avoid async checksum/submit on HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 22/27] btrfs: disallow mixed-bg in " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 23/27] btrfs: disallow inode_cache " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 24/27] btrfs: support dev-replace " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 25/27] btrfs: enable relocation " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 26/27] btrfs: relocate block group to repair IO failure in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 27/27] btrfs: enable to mount HMZONED incompat flag Naohiro Aota

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=20190808093038.4163421-3-naohiro.aota@wdc.com \
    --to=naohiro.aota@wdc.com \
    --cc=Matias.Bjorling@wdc.com \
    --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=nborisov@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