1 files changed, 166 insertions, 121 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2776112dbdf8..f688fab55251 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -396,15 +396,14 @@ again:
 	/* then test to make sure it is all still delalloc */
 	ret = test_range_bit(tree, delalloc_start, delalloc_end,
 			     EXTENT_DELALLOC, cached_state);
+
+	unlock_extent(tree, delalloc_start, delalloc_end, &cached_state);
 	if (!ret) {
-		unlock_extent(tree, delalloc_start, delalloc_end,
-			      &cached_state);
 		__unlock_for_delalloc(inode, locked_page,
 			      delalloc_start, delalloc_end);
 		cond_resched();
 		goto again;
 	}
-	free_extent_state(cached_state);
 	*start = delalloc_start;
 	*end = delalloc_end;
 out_failed:
@@ -413,9 +412,10 @@ out_failed:
 
 void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 				  struct page *locked_page,
+				  struct extent_state **cached,
 				  u32 clear_bits, unsigned long page_ops)
 {
-	clear_extent_bit(&inode->io_tree, start, end, clear_bits, NULL);
+	clear_extent_bit(&inode->io_tree, start, end, clear_bits, cached);
 
 	__process_pages_contig(inode->vfs_inode.i_mapping, locked_page,
 			       start, end, page_ops);
@@ -667,6 +667,37 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
 }
 
 /*
+ * Populate every free slot in a provided array with folios.
+ *
+ * @nr_folios:   number of folios to allocate
+ * @folio_array: the array to fill with folios; any existing non-NULL entries in
+ *		 the array will be skipped
+ * @extra_gfp:	 the extra GFP flags for the allocation
+ *
+ * Return: 0        if all folios were able to be allocated;
+ *         -ENOMEM  otherwise, the partially allocated folios would be freed and
+ *                  the array slots zeroed
+ */
+int btrfs_alloc_folio_array(unsigned int nr_folios, struct folio **folio_array,
+			    gfp_t extra_gfp)
+{
+	for (int i = 0; i < nr_folios; i++) {
+		if (folio_array[i])
+			continue;
+		folio_array[i] = folio_alloc(GFP_NOFS | extra_gfp, 0);
+		if (!folio_array[i])
+			goto error;
+	}
+	return 0;
+error:
+	for (int i = 0; i < nr_folios; i++) {
+		if (folio_array[i])
+			folio_put(folio_array[i]);
+	}
+	return -ENOMEM;
+}
+
+/*
  * Populate every free slot in a provided array with pages.
  *
  * @nr_pages:   number of pages to allocate
@@ -1571,7 +1602,7 @@ static void set_btree_ioerr(struct extent_buffer *eb)
 	 * can be no longer dirty nor marked anymore for writeback (if a
 	 * subsequent modification to the extent buffer didn't happen before the
 	 * transaction commit), which makes filemap_fdata[write|wait]_range not
-	 * able to find the pages tagged with SetPageError at transaction
+	 * able to find the pages which contain errors at transaction
 	 * commit time. So if this happens we must abort the transaction,
 	 * otherwise we commit a super block with btree roots that point to
 	 * btree nodes/leafs whose content on disk is invalid - either garbage
@@ -2246,8 +2277,7 @@ next_page:
 	submit_write_bio(&bio_ctrl, found_error ? ret : 0);
 }
 
-int extent_writepages(struct address_space *mapping,
-		      struct writeback_control *wbc)
+int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
 	int ret = 0;
@@ -2267,7 +2297,7 @@ int extent_writepages(struct address_space *mapping,
 	return ret;
 }
 
-void extent_readahead(struct readahead_control *rac)
+void btrfs_readahead(struct readahead_control *rac)
 {
 	struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD };
 	struct page *pagepool[16];
@@ -2325,19 +2355,20 @@ int extent_invalidate_folio(struct extent_io_tree *tree,
  * are locked or under IO and drops the related state bits if it is safe
  * to drop the page.
  */
-static int try_release_extent_state(struct extent_io_tree *tree,
+static bool try_release_extent_state(struct extent_io_tree *tree,
 				    struct page *page, gfp_t mask)
 {
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
-	int ret = 1;
+	bool ret;
 
 	if (test_range_bit_exists(tree, start, end, EXTENT_LOCKED)) {
-		ret = 0;
+		ret = false;
 	} else {
 		u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM |
 				   EXTENT_DELALLOC_NEW | EXTENT_CTLBITS |
 				   EXTENT_QGROUP_RESERVED);
+		int ret2;
 
 		/*
 		 * At this point we can safely clear everything except the
@@ -2345,15 +2376,15 @@ static int try_release_extent_state(struct extent_io_tree *tree,
 		 * The delalloc new bit will be cleared by ordered extent
 		 * completion.
 		 */
-		ret = __clear_extent_bit(tree, start, end, clear_bits, NULL, NULL);
+		ret2 = __clear_extent_bit(tree, start, end, clear_bits, NULL, NULL);
 
 		/* if clear_extent_bit failed for enomem reasons,
 		 * we can't allow the release to continue.
 		 */
-		if (ret < 0)
-			ret = 0;
+		if (ret2 < 0)
+			ret = false;
 		else
-			ret = 1;
+			ret = true;
 	}
 	return ret;
 }
@@ -2363,84 +2394,80 @@ static int try_release_extent_state(struct extent_io_tree *tree,
  * in the range corresponding to the page, both state records and extent
  * map records are removed
  */
-int try_release_extent_mapping(struct page *page, gfp_t mask)
+bool try_release_extent_mapping(struct page *page, gfp_t mask)
 {
-	struct extent_map *em;
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
-	struct btrfs_inode *btrfs_inode = page_to_inode(page);
-	struct extent_io_tree *tree = &btrfs_inode->io_tree;
-	struct extent_map_tree *map = &btrfs_inode->extent_tree;
-
-	if (gfpflags_allow_blocking(mask) &&
-	    page->mapping->host->i_size > SZ_16M) {
-		u64 len;
-		while (start <= end) {
-			struct btrfs_fs_info *fs_info;
-			u64 cur_gen;
-
-			len = end - start + 1;
-			write_lock(&map->lock);
-			em = lookup_extent_mapping(map, start, len);
-			if (!em) {
-				write_unlock(&map->lock);
-				break;
-			}
-			if ((em->flags & EXTENT_FLAG_PINNED) ||
-			    em->start != start) {
-				write_unlock(&map->lock);
-				free_extent_map(em);
-				break;
-			}
-			if (test_range_bit_exists(tree, em->start,
-						  extent_map_end(em) - 1,
-						  EXTENT_LOCKED))
-				goto next;
-			/*
-			 * If it's not in the list of modified extents, used
-			 * by a fast fsync, we can remove it. If it's being
-			 * logged we can safely remove it since fsync took an
-			 * extra reference on the em.
-			 */
-			if (list_empty(&em->list) ||
-			    (em->flags & EXTENT_FLAG_LOGGING))
-				goto remove_em;
-			/*
-			 * If it's in the list of modified extents, remove it
-			 * only if its generation is older then the current one,
-			 * in which case we don't need it for a fast fsync.
-			 * Otherwise don't remove it, we could be racing with an
-			 * ongoing fast fsync that could miss the new extent.
-			 */
-			fs_info = btrfs_inode->root->fs_info;
-			spin_lock(&fs_info->trans_lock);
-			cur_gen = fs_info->generation;
-			spin_unlock(&fs_info->trans_lock);
-			if (em->generation >= cur_gen)
-				goto next;
-remove_em:
-			/*
-			 * We only remove extent maps that are not in the list of
-			 * modified extents or that are in the list but with a
-			 * generation lower then the current generation, so there
-			 * is no need to set the full fsync flag on the inode (it
-			 * hurts the fsync performance for workloads with a data
-			 * size that exceeds or is close to the system's memory).
-			 */
-			remove_extent_mapping(map, em);
-			/* once for the rb tree */
+	struct btrfs_inode *inode = page_to_inode(page);
+	struct extent_io_tree *io_tree = &inode->io_tree;
+
+	while (start <= end) {
+		const u64 cur_gen = btrfs_get_fs_generation(inode->root->fs_info);
+		const u64 len = end - start + 1;
+		struct extent_map_tree *extent_tree = &inode->extent_tree;
+		struct extent_map *em;
+
+		write_lock(&extent_tree->lock);
+		em = lookup_extent_mapping(extent_tree, start, len);
+		if (!em) {
+			write_unlock(&extent_tree->lock);
+			break;
+		}
+		if ((em->flags & EXTENT_FLAG_PINNED) || em->start != start) {
+			write_unlock(&extent_tree->lock);
 			free_extent_map(em);
+			break;
+		}
+		if (test_range_bit_exists(io_tree, em->start,
+					  extent_map_end(em) - 1, EXTENT_LOCKED))
+			goto next;
+		/*
+		 * If it's not in the list of modified extents, used by a fast
+		 * fsync, we can remove it. If it's being logged we can safely
+		 * remove it since fsync took an extra reference on the em.
+		 */
+		if (list_empty(&em->list) || (em->flags & EXTENT_FLAG_LOGGING))
+			goto remove_em;
+		/*
+		 * If it's in the list of modified extents, remove it only if
+		 * its generation is older then the current one, in which case
+		 * we don't need it for a fast fsync. Otherwise don't remove it,
+		 * we could be racing with an ongoing fast fsync that could miss
+		 * the new extent.
+		 */
+		if (em->generation >= cur_gen)
+			goto next;
+remove_em:
+		/*
+		 * We only remove extent maps that are not in the list of
+		 * modified extents or that are in the list but with a
+		 * generation lower then the current generation, so there is no
+		 * need to set the full fsync flag on the inode (it hurts the
+		 * fsync performance for workloads with a data size that exceeds
+		 * or is close to the system's memory).
+		 */
+		remove_extent_mapping(inode, em);
+		/* Once for the inode's extent map tree. */
+		free_extent_map(em);
 next:
-			start = extent_map_end(em);
-			write_unlock(&map->lock);
+		start = extent_map_end(em);
+		write_unlock(&extent_tree->lock);
 
-			/* once for us */
-			free_extent_map(em);
+		/* Once for us, for the lookup_extent_mapping() reference. */
+		free_extent_map(em);
+
+		if (need_resched()) {
+			/*
+			 * If we need to resched but we can't block just exit
+			 * and leave any remaining extent maps.
+			 */
+			if (!gfpflags_allow_blocking(mask))
+				break;
 
-			cond_resched(); /* Allow large-extent preemption. */
+			cond_resched();
 		}
 	}
-	return try_release_extent_state(tree, page, mask);
+	return try_release_extent_state(io_tree, page, mask);
 }
 
 struct btrfs_fiemap_entry {
@@ -2773,13 +2800,19 @@ static int fiemap_next_leaf_item(struct btrfs_inode *inode, struct btrfs_path *p
 		goto out;
 	}
 
-	/* See the comment at fiemap_search_slot() about why we clone. */
-	copy_extent_buffer_full(clone, path->nodes[0]);
 	/*
 	 * Important to preserve the start field, for the optimizations when
 	 * checking if extents are shared (see extent_fiemap()).
+	 *
+	 * We must set ->start before calling copy_extent_buffer_full().  If we
+	 * are on sub-pagesize blocksize, we use ->start to determine the offset
+	 * into the folio where our eb exists, and if we update ->start after
+	 * the fact then any subsequent reads of the eb may read from a
+	 * different offset in the folio than where we originally copied into.
 	 */
 	clone->start = path->nodes[0]->start;
+	/* See the comment at fiemap_search_slot() about why we clone. */
+	copy_extent_buffer_full(clone, path->nodes[0]);
 
 	slot = path->slots[0];
 	btrfs_release_path(path);
@@ -3656,6 +3689,8 @@ static struct extent_buffer *grab_extent_buffer(
 	struct folio *folio = page_folio(page);
 	struct extent_buffer *exists;
 
+	lockdep_assert_held(&page->mapping->i_private_lock);
+
 	/*
 	 * For subpage case, we completely rely on radix tree to ensure we
 	 * don't try to insert two ebs for the same bytenr.  So here we always
@@ -3723,13 +3758,14 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start)
  * The caller needs to free the existing folios and retry using the same order.
  */
 static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i,
+				      struct btrfs_subpage *prealloc,
 				      struct extent_buffer **found_eb_ret)
 {
 
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	const unsigned long index = eb->start >> PAGE_SHIFT;
-	struct folio *existing_folio;
+	struct folio *existing_folio = NULL;
 	int ret;
 
 	ASSERT(found_eb_ret);
@@ -3741,12 +3777,14 @@ retry:
 	ret = filemap_add_folio(mapping, eb->folios[i], index + i,
 				GFP_NOFS | __GFP_NOFAIL);
 	if (!ret)
-		return 0;
+		goto finish;
 
 	existing_folio = filemap_lock_folio(mapping, index + i);
 	/* The page cache only exists for a very short time, just retry. */
-	if (IS_ERR(existing_folio))
+	if (IS_ERR(existing_folio)) {
+		existing_folio = NULL;
 		goto retry;
+	}
 
 	/* For now, we should only have single-page folios for btree inode. */
 	ASSERT(folio_nr_pages(existing_folio) == 1);
@@ -3757,14 +3795,13 @@ retry:
 		return -EAGAIN;
 	}
 
-	if (fs_info->nodesize < PAGE_SIZE) {
-		/*
-		 * We're going to reuse the existing page, can drop our page
-		 * and subpage structure now.
-		 */
+finish:
+	spin_lock(&mapping->i_private_lock);
+	if (existing_folio && fs_info->nodesize < PAGE_SIZE) {
+		/* We're going to reuse the existing page, can drop our folio now. */
 		__free_page(folio_page(eb->folios[i], 0));
 		eb->folios[i] = existing_folio;
-	} else {
+	} else if (existing_folio) {
 		struct extent_buffer *existing_eb;
 
 		existing_eb = grab_extent_buffer(fs_info,
@@ -3772,6 +3809,7 @@ retry:
 		if (existing_eb) {
 			/* The extent buffer still exists, we can use it directly. */
 			*found_eb_ret = existing_eb;
+			spin_unlock(&mapping->i_private_lock);
 			folio_unlock(existing_folio);
 			folio_put(existing_folio);
 			return 1;
@@ -3780,6 +3818,22 @@ retry:
 		__free_page(folio_page(eb->folios[i], 0));
 		eb->folios[i] = existing_folio;
 	}
+	eb->folio_size = folio_size(eb->folios[i]);
+	eb->folio_shift = folio_shift(eb->folios[i]);
+	/* Should not fail, as we have preallocated the memory. */
+	ret = attach_extent_buffer_folio(eb, eb->folios[i], prealloc);
+	ASSERT(!ret);
+	/*
+	 * To inform we have an extra eb under allocation, so that
+	 * detach_extent_buffer_page() won't release the folio private when the
+	 * eb hasn't been inserted into radix tree yet.
+	 *
+	 * The ref will be decreased when the eb releases the page, in
+	 * detach_extent_buffer_page().  Thus needs no special handling in the
+	 * error path.
+	 */
+	btrfs_folio_inc_eb_refs(fs_info, eb->folios[i]);
+	spin_unlock(&mapping->i_private_lock);
 	return 0;
 }
 
@@ -3791,7 +3845,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	int attached = 0;
 	struct extent_buffer *eb;
 	struct extent_buffer *existing_eb = NULL;
-	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	struct btrfs_subpage *prealloc = NULL;
 	u64 lockdep_owner = owner_root;
 	bool page_contig = true;
@@ -3857,7 +3910,7 @@ reallocate:
 	for (int i = 0; i < num_folios; i++) {
 		struct folio *folio;
 
-		ret = attach_eb_folio_to_filemap(eb, i, &existing_eb);
+		ret = attach_eb_folio_to_filemap(eb, i, prealloc, &existing_eb);
 		if (ret > 0) {
 			ASSERT(existing_eb);
 			goto out;
@@ -3894,24 +3947,6 @@ reallocate:
 		 * and free the allocated page.
 		 */
 		folio = eb->folios[i];
-		eb->folio_size = folio_size(folio);
-		eb->folio_shift = folio_shift(folio);
-		spin_lock(&mapping->i_private_lock);
-		/* Should not fail, as we have preallocated the memory */
-		ret = attach_extent_buffer_folio(eb, folio, prealloc);
-		ASSERT(!ret);
-		/*
-		 * To inform we have extra eb under allocation, so that
-		 * detach_extent_buffer_page() won't release the folio private
-		 * when the eb hasn't yet been inserted into radix tree.
-		 *
-		 * The ref will be decreased when the eb released the page, in
-		 * detach_extent_buffer_page().
-		 * Thus needs no special handling in error path.
-		 */
-		btrfs_folio_inc_eb_refs(fs_info, folio);
-		spin_unlock(&mapping->i_private_lock);
-
 		WARN_ON(btrfs_folio_test_dirty(fs_info, folio, eb->start, eb->len));
 
 		/*
@@ -4261,6 +4296,13 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb)
 	}
 }
 
+static void clear_extent_buffer_reading(struct extent_buffer *eb)
+{
+	clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
+	smp_mb__after_atomic();
+	wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+}
+
 static void end_bbio_meta_read(struct btrfs_bio *bbio)
 {
 	struct extent_buffer *eb = bbio->private;
@@ -4269,6 +4311,13 @@ static void end_bbio_meta_read(struct btrfs_bio *bbio)
 	struct folio_iter fi;
 	u32 bio_offset = 0;
 
+	/*
+	 * If the extent buffer is marked UPTODATE before the read operation
+	 * completes, other calls to read_extent_buffer_pages() will return
+	 * early without waiting for the read to finish, causing data races.
+	 */
+	WARN_ON(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags));
+
 	eb->read_mirror = bbio->mirror_num;
 
 	if (uptodate &&
@@ -4295,9 +4344,7 @@ static void end_bbio_meta_read(struct btrfs_bio *bbio)
 		bio_offset += len;
 	}
 
-	clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
-	smp_mb__after_atomic();
-	wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+	clear_extent_buffer_reading(eb);
 	free_extent_buffer(eb);
 
 	bio_put(&bbio->bio);
@@ -4331,9 +4378,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 	 * will now be set, and we shouldn't read it in again.
 	 */
 	if (unlikely(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))) {
-		clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
-		smp_mb__after_atomic();
-		wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+		clear_extent_buffer_reading(eb);
 		return 0;
 	}