From: Christoph Hellwig hch@lst.de

commit 2aba0d19f4d8c8929b4b3b94a9cfde2aa20e6ee2 upstream

Add a helper to check the max supported sectors for zone append based on the block_device instead of having to poke into the block layer internal request_queue.

Signed-off-by: Christoph Hellwig hch@lst.de Acked-by: Damien Le Moal damien.lemoal@opensource.wdc.com Reviewed-by: Martin K. Petersen martin.petersen@oracle.com Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Reviewed-by: Chaitanya Kulkarni kch@nvidia.com Link: https://lore.kernel.org/r/20220415045258.199825-16-hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk --- drivers/nvme/target/zns.c | 3 +-- fs/zonefs/super.c | 3 +-- include/linux/blkdev.h | 6 ++++++ 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index 46bc30fe85d2..235553337fb2 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -34,8 +34,7 @@ static int validate_conv_zones_cb(struct blk_zone *z,

bool nvmet_bdev_zns_enable(struct nvmet_ns *ns) { - struct request_queue *q = ns->bdev->bd_disk->queue; - u8 zasl = nvmet_zasl(queue_max_zone_append_sectors(q)); + u8 zasl = nvmet_zasl(bdev_max_zone_append_sectors(ns->bdev)); struct gendisk *bd_disk = ns->bdev->bd_disk; int ret;

diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index ecf564d150b3..f8feaed0b54d 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -723,13 +723,12 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(iocb->ki_filp); struct zonefs_inode_info *zi = ZONEFS_I(inode); struct block_device *bdev = inode->i_sb->s_bdev; - unsigned int max; + unsigned int max = bdev_max_zone_append_sectors(bdev); struct bio *bio; ssize_t size; int nr_pages; ssize_t ret;

- max = queue_max_zone_append_sectors(bdev_get_queue(bdev)); max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize); iov_iter_truncate(from, max);

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8863b4a378af..2f4ba6e345d5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1387,6 +1387,12 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu return min(l->max_zone_append_sectors, l->max_sectors); }

+static inline unsigned int +bdev_max_zone_append_sectors(struct block_device *bdev) +{ + return queue_max_zone_append_sectors(bdev_get_queue(bdev)); +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512;

commit c2ae7b772ef4e86c5ddf3fd47bf59045ae96a414 upstream

This patch is basically a revert of commit 5a80d1c6a270 ("btrfs: zoned: remove max_zone_append_size logic"), but without unnecessary ASSERT and check. The max_zone_append_size will be used as a hint to estimate the number of extents to cover delalloc/writeback region in the later commits.

The size of a ZONE APPEND bio is also limited by queue_max_segments(), so this commit considers it to calculate max_zone_append_size. Technically, a bio can be larger than queue_max_segments() * PAGE_SIZE if the pages are contiguous. But, it is safe to consider "queue_max_segments() * PAGE_SIZE" as an upper limit of an extent size to calculate the number of extents needed to write data.

Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Signed-off-by: Naohiro Aota naohiro.aota@wdc.com Signed-off-by: David Sterba dsterba@suse.com --- fs/btrfs/ctree.h | 2 ++ fs/btrfs/zoned.c | 17 +++++++++++++++++ fs/btrfs/zoned.h | 1 + 3 files changed, 20 insertions(+)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index d1838de0b39c..099c30477cf2 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1017,6 +1017,8 @@ struct btrfs_fs_info { u64 zoned; };

+ /* Max size to emit ZONE_APPEND write command */ + u64 max_zone_append_size; struct mutex zoned_meta_io_lock; spinlock_t treelog_bg_lock; u64 treelog_bg; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index fc791f7c7142..bfbceb94c4e2 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -386,6 +386,16 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) nr_sectors = bdev_nr_sectors(bdev); zone_info->zone_size_shift = ilog2(zone_info->zone_size); zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors); + /* + * We limit max_zone_append_size also by max_segments * + * PAGE_SIZE. Technically, we can have multiple pages per segment. But, + * since btrfs adds the pages one by one to a bio, and btrfs cannot + * increase the metadata reservation even if it increases the number of + * extents, it is safe to stick with the limit. + */ + zone_info->max_zone_append_size = + min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT, + (u64)bdev_max_segments(bdev) << PAGE_SHIFT); if (!IS_ALIGNED(nr_sectors, zone_sectors)) zone_info->nr_zones++;

@@ -570,6 +580,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) u64 zoned_devices = 0; u64 nr_devices = 0; u64 zone_size = 0; + u64 max_zone_append_size = 0; const bool incompat_zoned = btrfs_fs_incompat(fs_info, ZONED); int ret = 0;

@@ -605,6 +616,11 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) ret = -EINVAL; goto out; } + if (!max_zone_append_size || + (zone_info->max_zone_append_size && + zone_info->max_zone_append_size < max_zone_append_size)) + max_zone_append_size = + zone_info->max_zone_append_size; } nr_devices++; } @@ -654,6 +670,7 @@ 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;

/* diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 574490ea2cc8..1ef493fcd504 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -23,6 +23,7 @@ struct btrfs_zoned_device_info { */ u64 zone_size; u8 zone_size_shift; + u64 max_zone_append_size; u32 nr_zones; unsigned long *seq_zones; unsigned long *empty_zones;

commit 7d7672bc5d1038c745716c397d892d21e29de71c upstream

If count_max_extents() uses BTRFS_MAX_EXTENT_SIZE to calculate the number of extents needed, btrfs release the metadata reservation too much on its way to write out the data.

Now that BTRFS_MAX_EXTENT_SIZE is replaced with fs_info->max_extent_size, convert count_max_extents() to use it instead, and fix the calculation of the metadata reservation.

CC: stable@vger.kernel.org # 5.12+ Fixes: d8e3fb106f39 ("btrfs: zoned: use ZONE_APPEND write for zoned mode") Signed-off-by: Naohiro Aota naohiro.aota@wdc.com Signed-off-by: David Sterba dsterba@suse.com --- fs/btrfs/ctree.h | 21 +++++++++++++-------- fs/btrfs/delalloc-space.c | 6 +++--- fs/btrfs/inode.c | 16 ++++++++-------- 3 files changed, 24 insertions(+), 19 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index e751eb1b5514..1831135fef1a 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -105,14 +105,6 @@ struct btrfs_ref; #define BTRFS_STAT_CURR 0 #define BTRFS_STAT_PREV 1

-/* - * Count how many BTRFS_MAX_EXTENT_SIZE cover the @size - */ -static inline u32 count_max_extents(u64 size) -{ - return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE); -} - static inline unsigned long btrfs_chunk_item_size(int num_stripes) { BUG_ON(num_stripes == 0); @@ -3878,6 +3870,19 @@ static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info) return fs_info->zoned != 0; }

+/* + * Count how many fs_info->max_extent_size cover the @size + */ +static inline u32 count_max_extents(struct btrfs_fs_info *fs_info, u64 size) +{ +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS + if (!fs_info) + return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE); +#endif + + return div_u64(size + fs_info->max_extent_size - 1, fs_info->max_extent_size); +} + static inline bool btrfs_is_data_reloc_root(const struct btrfs_root *root) { return root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID; diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 40c4d6ba3fb9..b934429c2435 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -273,7 +273,7 @@ static void calc_inode_reservations(struct btrfs_fs_info *fs_info, u64 num_bytes, u64 *meta_reserve, u64 *qgroup_reserve) { - u64 nr_extents = count_max_extents(num_bytes); + u64 nr_extents = count_max_extents(fs_info, num_bytes); u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes); u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);

@@ -347,7 +347,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) * needs to free the reservation we just made. */ spin_lock(&inode->lock); - nr_extents = count_max_extents(num_bytes); + nr_extents = count_max_extents(fs_info, num_bytes); btrfs_mod_outstanding_extents(inode, nr_extents); inode->csum_bytes += num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); @@ -410,7 +410,7 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes) unsigned num_extents;

spin_lock(&inode->lock); - num_extents = count_max_extents(num_bytes); + num_extents = count_max_extents(fs_info, num_bytes); btrfs_mod_outstanding_extents(inode, -num_extents); btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 91417cdbf70d..ac6ba984973c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2049,10 +2049,10 @@ void btrfs_split_delalloc_extent(struct inode *inode, * applies here, just in reverse. */ new_size = orig->end - split + 1; - num_extents = count_max_extents(new_size); + num_extents = count_max_extents(fs_info, new_size); new_size = split - orig->start; - num_extents += count_max_extents(new_size); - if (count_max_extents(size) >= num_extents) + num_extents += count_max_extents(fs_info, new_size); + if (count_max_extents(fs_info, size) >= num_extents) return; }

@@ -2109,10 +2109,10 @@ void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new, * this case. */ old_size = other->end - other->start + 1; - num_extents = count_max_extents(old_size); + num_extents = count_max_extents(fs_info, old_size); old_size = new->end - new->start + 1; - num_extents += count_max_extents(old_size); - if (count_max_extents(new_size) >= num_extents) + num_extents += count_max_extents(fs_info, old_size); + if (count_max_extents(fs_info, new_size) >= num_extents) return;

spin_lock(&BTRFS_I(inode)->lock); @@ -2191,7 +2191,7 @@ void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state, if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) { struct btrfs_root *root = BTRFS_I(inode)->root; u64 len = state->end + 1 - state->start; - u32 num_extents = count_max_extents(len); + u32 num_extents = count_max_extents(fs_info, len); bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode));

spin_lock(&BTRFS_I(inode)->lock); @@ -2233,7 +2233,7 @@ void btrfs_clear_delalloc_extent(struct inode *vfs_inode, struct btrfs_inode *inode = BTRFS_I(vfs_inode); struct btrfs_fs_info *fs_info = btrfs_sb(vfs_inode->i_sb); u64 len = state->end + 1 - state->start; - u32 num_extents = count_max_extents(len); + u32 num_extents = count_max_extents(fs_info, len);

if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG)) { spin_lock(&inode->lock);