btrfs: zoned: implement zoned chunk allocator

Implement a zoned chunk and device extent allocator. One device zone
becomes a device extent so that a zone reset affects only this device
extent and does not change the state of blocks in the neighbor device
extents.

To implement the allocator, we need to extend the following functions for
a zoned filesystem.

- init_alloc_chunk_ctl
- dev_extent_search_start
- dev_extent_hole_check
- decide_stripe_size

init_alloc_chunk_ctl_zoned() is mostly the same as regular one. It always
set the stripe_size to the zone size and aligns the parameters to the zone
size.

dev_extent_search_start() only aligns the start offset to zone boundaries.
We don't care about the first 1MB like in regular filesystem because we
anyway reserve the first two zones for superblock logging.

dev_extent_hole_check_zoned() checks if zones in given hole are either
conventional or empty sequential zones. Also, it skips zones reserved for
superblock logging.

With the change to the hole, the new hole may now contain pending extents.
So, in this case, loop again to check that.

Finally, decide_stripe_size_zoned() should shrink the number of devices
instead of stripe size because we need to honor stripe_size == zone_size.

Reviewed-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.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>

1 files changed, 141 insertions, 0 deletions

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 6699f626a86e..69fd0d078b9b 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1,11 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <linux/bitops.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include "ctree.h"
 #include "volumes.h"
 #include "zoned.h"
 #include "rcu-string.h"
+#include "disk-io.h"
 
 /* Maximum number of zones to report per blkdev_report_zones() call */
 #define BTRFS_REPORT_NR_ZONES   4096
@@ -559,6 +561,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 
 	fs_info->zone_size = zone_size;
 	fs_info->max_zone_append_size = max_zone_append_size;
+	fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED;
 
 	/*
 	 * Check mount options here, because we might change fs_info->zoned
@@ -779,3 +782,141 @@ int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
 				sb_zone << zone_sectors_shift,
 				zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS);
 }
+
+/**
+ * btrfs_find_allocatable_zones - find allocatable zones within a given region
+ *
+ * @device:	the device to allocate a region on
+ * @hole_start: the position of the hole to allocate the region
+ * @num_bytes:	size of wanted region
+ * @hole_end:	the end of the hole
+ * @return:	position of allocatable zones
+ *
+ * Allocatable region should not contain any superblock locations.
+ */
+u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start,
+				 u64 hole_end, u64 num_bytes)
+{
+	struct btrfs_zoned_device_info *zinfo = device->zone_info;
+	const u8 shift = zinfo->zone_size_shift;
+	u64 nzones = num_bytes >> shift;
+	u64 pos = hole_start;
+	u64 begin, end;
+	bool have_sb;
+	int i;
+
+	ASSERT(IS_ALIGNED(hole_start, zinfo->zone_size));
+	ASSERT(IS_ALIGNED(num_bytes, zinfo->zone_size));
+
+	while (pos < hole_end) {
+		begin = pos >> shift;
+		end = begin + nzones;
+
+		if (end > zinfo->nr_zones)
+			return hole_end;
+
+		/* Check if zones in the region are all empty */
+		if (btrfs_dev_is_sequential(device, pos) &&
+		    find_next_zero_bit(zinfo->empty_zones, end, begin) != end) {
+			pos += zinfo->zone_size;
+			continue;
+		}
+
+		have_sb = false;
+		for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
+			u32 sb_zone;
+			u64 sb_pos;
+
+			sb_zone = sb_zone_number(shift, i);
+			if (!(end <= sb_zone ||
+			      sb_zone + BTRFS_NR_SB_LOG_ZONES <= begin)) {
+				have_sb = true;
+				pos = ((u64)sb_zone + BTRFS_NR_SB_LOG_ZONES) << shift;
+				break;
+			}
+
+			/* We also need to exclude regular superblock positions */
+			sb_pos = btrfs_sb_offset(i);
+			if (!(pos + num_bytes <= sb_pos ||
+			      sb_pos + BTRFS_SUPER_INFO_SIZE <= pos)) {
+				have_sb = true;
+				pos = ALIGN(sb_pos + BTRFS_SUPER_INFO_SIZE,
+					    zinfo->zone_size);
+				break;
+			}
+		}
+		if (!have_sb)
+			break;
+	}
+
+	return pos;
+}
+
+int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
+			    u64 length, u64 *bytes)
+{
+	int ret;
+
+	*bytes = 0;
+	ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_RESET,
+			       physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT,
+			       GFP_NOFS);
+	if (ret)
+		return ret;
+
+	*bytes = length;
+	while (length) {
+		btrfs_dev_set_zone_empty(device, physical);
+		physical += device->zone_info->zone_size;
+		length -= device->zone_info->zone_size;
+	}
+
+	return 0;
+}
+
+int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size)
+{
+	struct btrfs_zoned_device_info *zinfo = device->zone_info;
+	const u8 shift = zinfo->zone_size_shift;
+	unsigned long begin = start >> shift;
+	unsigned long end = (start + size) >> shift;
+	u64 pos;
+	int ret;
+
+	ASSERT(IS_ALIGNED(start, zinfo->zone_size));
+	ASSERT(IS_ALIGNED(size, zinfo->zone_size));
+
+	if (end > zinfo->nr_zones)
+		return -ERANGE;
+
+	/* All the zones are conventional */
+	if (find_next_bit(zinfo->seq_zones, begin, end) == end)
+		return 0;
+
+	/* All the zones are sequential and empty */
+	if (find_next_zero_bit(zinfo->seq_zones, begin, end) == end &&
+	    find_next_zero_bit(zinfo->empty_zones, begin, end) == end)
+		return 0;
+
+	for (pos = start; pos < start + size; pos += zinfo->zone_size) {
+		u64 reset_bytes;
+
+		if (!btrfs_dev_is_sequential(device, pos) ||
+		    btrfs_dev_is_empty_zone(device, pos))
+			continue;
+
+		/* Free regions should be empty */
+		btrfs_warn_in_rcu(
+			device->fs_info,
+		"zoned: resetting device %s (devid %llu) zone %llu for allocation",
+			rcu_str_deref(device->name), device->devid, pos >> shift);
+		WARN_ON_ONCE(1);
+
+		ret = btrfs_reset_device_zone(device, pos, zinfo->zone_size,
+					      &reset_bytes);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}