From 2dd7e7bc02829eded71be2342a93dc035f5223f9 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 9 Sep 2022 15:59:55 +0900 Subject: [PATCH] btrfs: zoned: wait for extent buffer IOs before finishing a zone Before sending REQ_OP_ZONE_FINISH to a zone, we need to ensure that ongoing IOs already finished. Or, we will see a "Zone Is Full" error for the IOs, as the ZONE_FINISH command makes the zone full. We ensure that with btrfs_wait_block_group_reservations() and btrfs_wait_ordered_roots() for a data block group. And, for a metadata block group, the comparison of alloc_offset vs meta_write_pointer mostly ensures IOs for the allocated region already sent. However, there still can be a little time frame where the IOs are sent but not yet completed. Introduce wait_eb_writebacks() to ensure such IOs are completed for a metadata block group. It walks the buffer_radix to find extent buffers in the block group and calls wait_on_extent_buffer_writeback() on them. Fixes: afba2bc036b0 ("btrfs: zoned: implement active zone tracking") CC: stable@vger.kernel.org # 5.19+ Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 40 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 38 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 62e7007a7e46..73c6929f7be6 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1918,10 +1918,44 @@ out_unlock: return ret; } +static void wait_eb_writebacks(struct btrfs_block_group *block_group) +{ + struct btrfs_fs_info *fs_info = block_group->fs_info; + const u64 end = block_group->start + block_group->length; + struct radix_tree_iter iter; + struct extent_buffer *eb; + void __rcu **slot; + + rcu_read_lock(); + radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, + block_group->start >> fs_info->sectorsize_bits) { + eb = radix_tree_deref_slot(slot); + if (!eb) + continue; + if (radix_tree_deref_retry(eb)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + if (eb->start < block_group->start) + continue; + if (eb->start >= end) + break; + + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); + wait_on_extent_buffer_writeback(eb); + rcu_read_lock(); + } + rcu_read_unlock(); +} + static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct map_lookup *map; + const bool is_metadata = (block_group->flags & + (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)); int ret = 0; int i; @@ -1932,8 +1966,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ } /* Check if we have unwritten allocated space */ - if ((block_group->flags & - (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)) && + if (is_metadata && block_group->start + block_group->alloc_offset > block_group->meta_write_pointer) { spin_unlock(&block_group->lock); return -EAGAIN; @@ -1958,6 +1991,9 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ /* No need to wait for NOCOW writers. Zoned mode does not allow that */ btrfs_wait_ordered_roots(fs_info, U64_MAX, block_group->start, block_group->length); + /* Wait for extent buffers to be written. */ + if (is_metadata) + wait_eb_writebacks(block_group); spin_lock(&block_group->lock);