1 files changed, 146 insertions, 35 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 41b718cfea40..c9a3036c23bf 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -42,6 +42,7 @@
 #include "discard.h"
 #include "space-info.h"
 #include "zoned.h"
+#include "subpage.h"
 
 #define BTRFS_SUPER_FLAG_SUPP	(BTRFS_HEADER_FLAG_WRITTEN |\
 				 BTRFS_HEADER_FLAG_RELOC |\
@@ -440,6 +441,74 @@ static int btree_read_extent_buffer_pages(struct extent_buffer *eb,
 	return ret;
 }
 
+static int csum_one_extent_buffer(struct extent_buffer *eb)
+{
+	struct btrfs_fs_info *fs_info = eb->fs_info;
+	u8 result[BTRFS_CSUM_SIZE];
+	int ret;
+
+	ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid,
+				    offsetof(struct btrfs_header, fsid),
+				    BTRFS_FSID_SIZE) == 0);
+	csum_tree_block(eb, result);
+
+	if (btrfs_header_level(eb))
+		ret = btrfs_check_node(eb);
+	else
+		ret = btrfs_check_leaf_full(eb);
+
+	if (ret < 0) {
+		btrfs_print_tree(eb, 0);
+		btrfs_err(fs_info,
+			"block=%llu write time tree block corruption detected",
+			eb->start);
+		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+		return ret;
+	}
+	write_extent_buffer(eb, result, 0, fs_info->csum_size);
+
+	return 0;
+}
+
+/* Checksum all dirty extent buffers in one bio_vec */
+static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info,
+				      struct bio_vec *bvec)
+{
+	struct page *page = bvec->bv_page;
+	u64 bvec_start = page_offset(page) + bvec->bv_offset;
+	u64 cur;
+	int ret = 0;
+
+	for (cur = bvec_start; cur < bvec_start + bvec->bv_len;
+	     cur += fs_info->nodesize) {
+		struct extent_buffer *eb;
+		bool uptodate;
+
+		eb = find_extent_buffer(fs_info, cur);
+		uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur,
+						       fs_info->nodesize);
+
+		/* A dirty eb shouldn't disappear from buffer_radix */
+		if (WARN_ON(!eb))
+			return -EUCLEAN;
+
+		if (WARN_ON(cur != btrfs_header_bytenr(eb))) {
+			free_extent_buffer(eb);
+			return -EUCLEAN;
+		}
+		if (WARN_ON(!uptodate)) {
+			free_extent_buffer(eb);
+			return -EUCLEAN;
+		}
+
+		ret = csum_one_extent_buffer(eb);
+		free_extent_buffer(eb);
+		if (ret < 0)
+			return ret;
+	}
+	return ret;
+}
+
 /*
  * Checksum a dirty tree block before IO.  This has extra checks to make sure
  * we only fill in the checksum field in the first page of a multi-page block.
@@ -450,9 +519,10 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec
 	struct page *page = bvec->bv_page;
 	u64 start = page_offset(page);
 	u64 found_start;
-	u8 result[BTRFS_CSUM_SIZE];
 	struct extent_buffer *eb;
-	int ret;
+
+	if (fs_info->sectorsize < PAGE_SIZE)
+		return csum_dirty_subpage_buffers(fs_info, bvec);
 
 	eb = (struct extent_buffer *)page->private;
 	if (page != eb->pages[0])
@@ -474,28 +544,7 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec
 	if (WARN_ON(!PageUptodate(page)))
 		return -EUCLEAN;
 
-	ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid,
-				    offsetof(struct btrfs_header, fsid),
-				    BTRFS_FSID_SIZE) == 0);
-
-	csum_tree_block(eb, result);
-
-	if (btrfs_header_level(eb))
-		ret = btrfs_check_node(eb);
-	else
-		ret = btrfs_check_leaf_full(eb);
-
-	if (ret < 0) {
-		btrfs_print_tree(eb, 0);
-		btrfs_err(fs_info,
-		"block=%llu write time tree block corruption detected",
-			  eb->start);
-		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
-		return ret;
-	}
-	write_extent_buffer(eb, result, 0, fs_info->csum_size);
-
-	return 0;
+	return csum_one_extent_buffer(eb);
 }
 
 static int check_tree_block_fsid(struct extent_buffer *eb)
@@ -992,14 +1041,48 @@ static void btree_invalidatepage(struct page *page, unsigned int offset,
 static int btree_set_page_dirty(struct page *page)
 {
 #ifdef DEBUG
+	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	struct btrfs_subpage *subpage;
 	struct extent_buffer *eb;
+	int cur_bit = 0;
+	u64 page_start = page_offset(page);
+
+	if (fs_info->sectorsize == PAGE_SIZE) {
+		BUG_ON(!PagePrivate(page));
+		eb = (struct extent_buffer *)page->private;
+		BUG_ON(!eb);
+		BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+		BUG_ON(!atomic_read(&eb->refs));
+		btrfs_assert_tree_locked(eb);
+		return __set_page_dirty_nobuffers(page);
+	}
+	ASSERT(PagePrivate(page) && page->private);
+	subpage = (struct btrfs_subpage *)page->private;
+
+	ASSERT(subpage->dirty_bitmap);
+	while (cur_bit < BTRFS_SUBPAGE_BITMAP_SIZE) {
+		unsigned long flags;
+		u64 cur;
+		u16 tmp = (1 << cur_bit);
+
+		spin_lock_irqsave(&subpage->lock, flags);
+		if (!(tmp & subpage->dirty_bitmap)) {
+			spin_unlock_irqrestore(&subpage->lock, flags);
+			cur_bit++;
+			continue;
+		}
+		spin_unlock_irqrestore(&subpage->lock, flags);
+		cur = page_start + cur_bit * fs_info->sectorsize;
 
-	BUG_ON(!PagePrivate(page));
-	eb = (struct extent_buffer *)page->private;
-	BUG_ON(!eb);
-	BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
-	BUG_ON(!atomic_read(&eb->refs));
-	btrfs_assert_tree_locked(eb);
+		eb = find_extent_buffer(fs_info, cur);
+		ASSERT(eb);
+		ASSERT(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+		ASSERT(atomic_read(&eb->refs));
+		btrfs_assert_tree_locked(eb);
+		free_extent_buffer(eb);
+
+		cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits);
+	}
 #endif
 	return __set_page_dirty_nobuffers(page);
 }
@@ -1807,14 +1890,21 @@ static int cleaner_kthread(void *arg)
 		btrfs_run_defrag_inodes(fs_info);
 
 		/*
-		 * Acquires fs_info->delete_unused_bgs_mutex to avoid racing
+		 * Acquires fs_info->reclaim_bgs_lock to avoid racing
 		 * with relocation (btrfs_relocate_chunk) and relocation
 		 * acquires fs_info->cleaner_mutex (btrfs_relocate_block_group)
-		 * after acquiring fs_info->delete_unused_bgs_mutex. So we
+		 * after acquiring fs_info->reclaim_bgs_lock. So we
 		 * can't hold, nor need to, fs_info->cleaner_mutex when deleting
 		 * unused block groups.
 		 */
 		btrfs_delete_unused_bgs(fs_info);
+
+		/*
+		 * Reclaim block groups in the reclaim_bgs list after we deleted
+		 * all unused block_groups. This possibly gives us some more free
+		 * space.
+		 */
+		btrfs_reclaim_bgs(fs_info);
 sleep:
 		clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
 		if (kthread_should_park())
@@ -2387,8 +2477,9 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	} else {
 		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
 		fs_info->dev_root = root;
-		btrfs_init_devices_late(fs_info);
 	}
+	/* Initialize fs_info for all devices in any case */
+	btrfs_init_devices_late(fs_info);
 
 	/* If IGNOREDATACSUMS is set don't bother reading the csum root. */
 	if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
@@ -2792,7 +2883,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	spin_lock_init(&fs_info->treelog_bg_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);
 	mutex_init(&fs_info->unused_bg_unpin_mutex);
-	mutex_init(&fs_info->delete_unused_bgs_mutex);
+	mutex_init(&fs_info->reclaim_bgs_lock);
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
 	mutex_init(&fs_info->zoned_meta_io_lock);
@@ -2802,6 +2893,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&fs_info->space_info);
 	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
 	INIT_LIST_HEAD(&fs_info->unused_bgs);
+	INIT_LIST_HEAD(&fs_info->reclaim_bgs);
 #ifdef CONFIG_BTRFS_DEBUG
 	INIT_LIST_HEAD(&fs_info->allocated_roots);
 	INIT_LIST_HEAD(&fs_info->allocated_ebs);
@@ -2890,6 +2982,9 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	fs_info->swapfile_pins = RB_ROOT;
 
 	fs_info->send_in_progress = 0;
+
+	fs_info->bg_reclaim_threshold = BTRFS_DEFAULT_RECLAIM_THRESH;
+	INIT_WORK(&fs_info->reclaim_bgs_work, btrfs_reclaim_bgs_work);
 }
 
 static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block *sb)
@@ -3009,6 +3104,21 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 		}
 	}
 
+	/*
+	 * btrfs_find_orphan_roots() is responsible for finding all the dead
+	 * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
+	 * them into the fs_info->fs_roots_radix tree. This must be done before
+	 * calling btrfs_orphan_cleanup() on the tree root. If we don't do it
+	 * first, then btrfs_orphan_cleanup() will delete a dead root's orphan
+	 * item before the root's tree is deleted - this means that if we unmount
+	 * or crash before the deletion completes, on the next mount we will not
+	 * delete what remains of the tree because the orphan item does not
+	 * exists anymore, which is what tells us we have a pending deletion.
+	 */
+	ret = btrfs_find_orphan_roots(fs_info);
+	if (ret)
+		goto out;
+
 	ret = btrfs_cleanup_fs_roots(fs_info);
 	if (ret)
 		goto out;
@@ -3068,7 +3178,6 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 		}
 	}
 
-	ret = btrfs_find_orphan_roots(fs_info);
 out:
 	return ret;
 }
@@ -4234,6 +4343,8 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	cancel_work_sync(&fs_info->async_data_reclaim_work);
 	cancel_work_sync(&fs_info->preempt_reclaim_work);
 
+	cancel_work_sync(&fs_info->reclaim_bgs_work);
+
 	/* Cancel or finish ongoing discard work */
 	btrfs_discard_cleanup(fs_info);