Btrfs: Subpagesize-blocksize: Get rid of whole page I/O.

index a389820..c98dfd8 100644
@@ -1951,14 +1951,23 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
  * helper function to set a given page up to date if all the
  * extents in the tree for that page are up to date
  */
-static void check_page_uptodate(struct extent_io_tree *tree, struct page *page)
+static void check_page_uptodate(struct extent_io_tree *tree, struct page *page,
+				struct extent_state *cached)
 {
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_CACHE_SIZE - 1;
-	if (test_range_bit(tree, start, end, EXTENT_UPTODATE, 1, NULL))
+	if (test_range_bit(tree, start, end, EXTENT_UPTODATE, 1, cached))
 		SetPageUptodate(page);
 }
 
+static int page_read_complete(struct extent_io_tree *tree, struct page *page)
+{
+	u64 start = page_offset(page);
+	u64 end = start + PAGE_CACHE_SIZE - 1;
+
+	return !test_range_bit(tree, start, end, EXTENT_READ_IO, 0, NULL);
+}
+
 /*
  * When IO fails, either with EIO or csum verification fails, we
  * try other mirrors that might have a good copy of the data.  This

@@ -2275,7 +2284,9 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	 *	a) deliver good data to the caller
 	 *	b) correct the bad sectors on disk
 	 */
-	if (failed_bio->bi_vcnt > 1) {
+	if ((failed_bio->bi_vcnt > 1)
+		|| (failed_bio->bi_io_vec->bv_len
+			> BTRFS_I(inode)->root->sectorsize)) {
 		/*
 		 * to fulfill b), we need to know the exact failing sectors, as
 		 * we don't want to rewrite any more than the failed ones. thus,

@@ -2422,18 +2433,6 @@ static void end_bio_extent_writepage(struct bio *bio, int err)
 	bio_put(bio);
 }
 
-static void
-endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len,
-			      int uptodate)
-{
-	struct extent_state *cached = NULL;
-	u64 end = start + len - 1;
-
-	if (uptodate && tree->track_uptodate)
-		set_extent_uptodate(tree, start, end, &cached, GFP_ATOMIC);
-	unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
-}
-
 /*
  * after a readpage IO is done, we need to:
  * clear the uptodate bits on error

@@ -2450,14 +2449,15 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 	struct bio_vec *bvec;
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+	struct extent_state *cached = NULL;
 	struct extent_io_tree *tree;
+	unsigned long flags;
 	u64 offset = 0;
 	u64 start;
 	u64 end;
-	u64 len;
-	u64 extent_start = 0;
-	u64 extent_len = 0;
+	int nr_sectors;
 	int mirror;
+	int unlock;
 	int ret;
 	int i;
 

@@ -2467,54 +2467,31 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 		struct inode *inode = page->mapping->host;
+		struct btrfs_root *root = BTRFS_I(inode)->root;
 
 		pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
 			 "mirror=%lu\n", (u64)bio->bi_iter.bi_sector, err,
 			 io_bio->mirror_num);
 		tree = &BTRFS_I(inode)->io_tree;
 
-		/* We always issue full-page reads, but if some block
-		 * in a page fails to read, blk_update_request() will
-		 * advance bv_offset and adjust bv_len to compensate.
-		 * Print a warning for nonzero offsets, and an error
-		 * if they don't add up to a full page.  */
-		if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) {
-			if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
-				btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
-				   "partial page read in btrfs with offset %u and length %u",
-					bvec->bv_offset, bvec->bv_len);
-			else
-				btrfs_info(BTRFS_I(page->mapping->host)->root->fs_info,
-				   "incomplete page read in btrfs with offset %u and "
-				   "length %u",
-					bvec->bv_offset, bvec->bv_len);
-		}
-
-		start = page_offset(page);
-		end = start + bvec->bv_offset + bvec->bv_len - 1;
-		len = bvec->bv_len;
-
+		start = page_offset(page) + bvec->bv_offset;
+		end = start + bvec->bv_len - 1;
+		nr_sectors = bvec->bv_len >> inode->i_sb->s_blocksize_bits;
 		mirror = io_bio->mirror_num;
-		if (likely(uptodate && tree->ops &&
-			   tree->ops->readpage_end_io_hook)) {
+
+next_block:
+		if (likely(uptodate)) {
 			ret = tree->ops->readpage_end_io_hook(io_bio, offset,
-							      page, start, end,
-							      mirror);
+							page, start,
+							start + root->sectorsize - 1,
+							mirror);
 			if (ret)
 				uptodate = 0;
 			else
 				clean_io_failure(start, page);
 		}
 
-		if (likely(uptodate))
-			goto readpage_ok;
-
-		if (tree->ops && tree->ops->readpage_io_failed_hook) {
-			ret = tree->ops->readpage_io_failed_hook(page, mirror);
-			if (!ret && !err &&
-			    test_bit(BIO_UPTODATE, &bio->bi_flags))
-				uptodate = 1;
-		} else {
+		if (!uptodate) {
 			/*
 			 * The generic bio_readpage_error handles errors the
 			 * following way: If possible, new read requests are

@@ -2525,60 +2502,64 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 			 * can't handle the error it will return -EIO and we
 			 * remain responsible for that page.
 			 */
-			ret = bio_readpage_error(bio, offset, page, start, end,
-						 mirror);
+			ret = bio_readpage_error(bio, offset, page,
+						start, start + root->sectorsize - 1,
+						mirror);
 			if (ret == 0) {
-				uptodate =
-					test_bit(BIO_UPTODATE, &bio->bi_flags);
+				uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 				if (err)
 					uptodate = 0;
-				continue;
+				offset += root->sectorsize;
+				if (--nr_sectors) {
+					start += root->sectorsize;
+					goto next_block;
+				} else {
+					continue;
+				}
 			}
 		}
-readpage_ok:
-		if (likely(uptodate)) {
-			loff_t i_size = i_size_read(inode);
-			pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
-			unsigned offset;
-
-			/* Zero out the end if this page straddles i_size */
-			offset = i_size & (PAGE_CACHE_SIZE-1);
-			if (page->index == end_index && offset)
-				zero_user_segment(page, offset, PAGE_CACHE_SIZE);
-			SetPageUptodate(page);
+
+		if (uptodate) {
+			set_extent_uptodate(tree, start,
+					start + root->sectorsize - 1,
+					&cached, GFP_ATOMIC);
+			check_page_uptodate(tree, page, cached);
 		} else {
 			ClearPageUptodate(page);
 			SetPageError(page);
 		}
-		unlock_page(page);
-		offset += len;
-
-		if (unlikely(!uptodate)) {
-			if (extent_len) {
-				endio_readpage_release_extent(tree,
-							      extent_start,
-							      extent_len, 1);
-				extent_start = 0;
-				extent_len = 0;
-			}
-			endio_readpage_release_extent(tree, start,
-						      end - start + 1, 0);
-		} else if (!extent_len) {
-			extent_start = start;
-			extent_len = end + 1 - start;
-		} else if (extent_start + extent_len == start) {
-			extent_len += end + 1 - start;
-		} else {
-			endio_readpage_release_extent(tree, extent_start,
-						      extent_len, uptodate);
-			extent_start = start;
-			extent_len = end + 1 - start;
+
+		offset += root->sectorsize;
+
+		if (--nr_sectors) {
+			clear_extent_bit(tree, start, start + root->sectorsize - 1,
+				EXTENT_READ_IO, 0, 0, &cached, GFP_ATOMIC);
+			clear_extent_bit(tree, start, start + root->sectorsize - 1,
+					EXTENT_LOCKED, 1, 0, &cached, GFP_ATOMIC);
+			start += root->sectorsize;
+			goto next_block;
 		}
+
+		WARN_ON(!PagePrivate(page));
+
+		local_irq_save(flags);
+		bit_spin_lock(EXTENT_PAGE_UPTODATE_LOCK, &page->private);
+
+		clear_extent_bit(tree, start, start + root->sectorsize - 1,
+				EXTENT_READ_IO, 0, 0, &cached, GFP_ATOMIC);
+
+		unlock = page_read_complete(tree, page);
+
+		bit_spin_unlock(EXTENT_PAGE_UPTODATE_LOCK, &page->private);
+		local_irq_restore(flags);
+
+		clear_extent_bit(tree, start, start + root->sectorsize - 1,
+				EXTENT_LOCKED, 1, 0, &cached, GFP_ATOMIC);
+
+		if (unlock)
+			unlock_page(page);
 	}
 
-	if (extent_len)
-		endio_readpage_release_extent(tree, extent_start, extent_len,
-					      uptodate);
 	if (io_bio->end_io)
 		io_bio->end_io(io_bio, err);
 	bio_put(bio);

@@ -2799,6 +2780,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 			 unsigned long *bio_flags, int rw)
 {
 	struct inode *inode = page->mapping->host;
+	struct extent_state *cached = NULL;
 	u64 start = page_offset(page);
 	u64 page_end = start + PAGE_CACHE_SIZE - 1;
 	u64 end;

@@ -2918,7 +2900,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 		/* the get_extent function already copied into the page */
 		if (test_range_bit(tree, cur, cur_end,
 				   EXTENT_UPTODATE, 1, NULL)) {
-			check_page_uptodate(tree, page);
+			check_page_uptodate(tree, page, NULL);
 			if (!parent_locked)
 				unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;

@@ -2938,6 +2920,10 @@ static int __do_readpage(struct extent_io_tree *tree,
 		}
 
 		pnr -= page->index;
+
+		set_extent_bit(tree, cur, cur + iosize - 1, EXTENT_READ_IO,
+			NULL, &cached, GFP_NOFS);
+
 		ret = submit_extent_page(rw, tree, page,
 					 sector, disk_io_size, pg_offset,
 					 bdev, bio, pnr,

@@ -2949,8 +2935,12 @@ static int __do_readpage(struct extent_io_tree *tree,
 			*bio_flags = this_bio_flag;
 		} else {
 			SetPageError(page);
+			clear_extent_bit(tree, cur, cur + iosize - 1,
+					EXTENT_READ_IO, 0, 0, &cached,
+					GFP_NOFS);
 			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+				unlock_extent_cached(tree, cur, cur + iosize - 1,
+						&cached, GFP_NOFS);
 		}
 		cur = cur + iosize;
 		pg_offset += iosize;

index ccc264e..4d019c0 100644
@@ -20,6 +20,7 @@
 #define EXTENT_NEED_WAIT (1 << 13)
 #define EXTENT_DAMAGED (1 << 14)
 #define EXTENT_NORESERVE (1 << 15)
+#define EXTENT_READ_IO (1 << 16)
 #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
 #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
 

@@ -56,8 +57,8 @@
  * page->private values.  Every page that is controlled by the extent
  * map has page->private set to one.
  */
-#define EXTENT_PAGE_PRIVATE 1
-#define EXTENT_PAGE_PRIVATE_FIRST_PAGE 3
+#define EXTENT_PAGE_PRIVATE		(1 << 0)
+#define EXTENT_PAGE_UPTODATE_LOCK	(1 << 1)
 
 struct extent_state;
 struct btrfs_root;

index c98dfd8..57db008 100644
@@ -1300,6 +1300,20 @@ int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
 				cached_state, mask);
 }
 
+static int set_extent_writeback(struct extent_io_tree *tree, u64 start, u64 end,
+				struct extent_state **cached_state, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end, EXTENT_WRITEBACK, NULL,
+			cached_state, mask);
+}
+
+static int clear_extent_writeback(struct extent_io_tree *tree, u64 start, u64 end,
+				struct extent_state **cached_state, gfp_t mask)
+{
+	return clear_extent_bit(tree, start, end, EXTENT_WRITEBACK, 1, 0,
+				cached_state, mask);
+}
+
 /*
  * either insert or lock state struct between start and end use mask to tell
  * us if waiting is desired.

@@ -1406,6 +1420,7 @@ static int set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
 		page_cache_release(page);
 		index++;
 	}
+	set_extent_writeback(tree, start, end, NULL, GFP_NOFS);
 	return 0;
 }
 

@@ -2403,31 +2418,23 @@ static void end_bio_extent_writepage(struct bio *bio, int err)
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
+		struct inode *inode = page->mapping->host;
+		struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
+		u64 page_start, page_end;
 
-		/* We always issue full-page reads, but if some block
-		 * in a page fails to read, blk_update_request() will
-		 * advance bv_offset and adjust bv_len to compensate.
-		 * Print a warning for nonzero offsets, and an error
-		 * if they don't add up to a full page.  */
-		if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) {
-			if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
-				btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
-				   "partial page write in btrfs with offset %u and length %u",
-					bvec->bv_offset, bvec->bv_len);
-			else
-				btrfs_info(BTRFS_I(page->mapping->host)->root->fs_info,
-				   "incomplete page write in btrfs with offset %u and "
-				   "length %u",
-					bvec->bv_offset, bvec->bv_len);
-		}
-
-		start = page_offset(page);
-		end = start + bvec->bv_offset + bvec->bv_len - 1;
+		start = page_offset(page) + bvec->bv_offset;
+		end = start + bvec->bv_len - 1;
 
 		if (end_extent_writepage(page, err, start, end))
 			continue;
 
-		end_page_writeback(page);
+		clear_extent_writeback(tree, start, end, NULL, GFP_ATOMIC);
+
+		page_start = page_offset(page);
+		page_end = page_offset(page) + PAGE_CACHE_SIZE - 1;
+		if (!test_range_bit(tree, page_start, page_end,
+					EXTENT_WRITEBACK, 0, NULL))
+			end_page_writeback(page);
 	}
 
 	bio_put(bio);

index 7309832..2ffb4df 100644
@@ -2823,22 +2823,44 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ordered_extent *ordered_extent = NULL;
 	struct btrfs_workqueue *workers;
+	u64 ordered_start, ordered_end;
+	int done;
 
 	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
 
 	ClearPagePrivate2(page);
-	if (!btrfs_dec_test_ordered_pending(inode, &ordered_extent, start,
-					    end - start + 1, uptodate))
-		return 0;
+loop:
+	ordered_extent = btrfs_lookup_ordered_range(inode, start,
+						end - start + 1);
+	if (!ordered_extent)
+		goto out;
 
-	btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
+	ordered_start = max_t(u64, start, ordered_extent->file_offset);
+	ordered_end = min_t(u64, end,
+			ordered_extent->file_offset + ordered_extent->len - 1);
 
-	if (btrfs_is_free_space_inode(inode))
-		workers = root->fs_info->endio_freespace_worker;
-	else
-		workers = root->fs_info->endio_write_workers;
-	btrfs_queue_work(workers, &ordered_extent->work);
+	done = btrfs_dec_test_ordered_pending(inode, &ordered_extent,
+					ordered_start,
+					ordered_end - ordered_start + 1,
+					uptodate);
+	if (done) {
+		btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
+
+		if (btrfs_is_free_space_inode(inode))
+			workers = root->fs_info->endio_freespace_worker;
+		else
+			workers = root->fs_info->endio_write_workers;
 
+		btrfs_queue_work(workers, &ordered_extent->work);
+	}
+
+	btrfs_put_ordered_extent(ordered_extent);
+
+	start = ordered_end + 1;
+
+	if (start < end)
+		goto loop;
+out:
 	return 0;
 }
 

index d3afac2..444819d 100644
@@ -1366,18 +1366,21 @@ fail:
 static noinline int
 lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 				size_t num_pages, loff_t pos,
+				size_t write_bytes,
 				u64 *lockstart, u64 *lockend,
 				struct extent_state **cached_state)
 {
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	u64 start_pos;
 	u64 last_pos;
 	int i;
 	int ret = 0;
 
-	start_pos = pos & ~((u64)PAGE_CACHE_SIZE - 1);
-	last_pos = start_pos + ((u64)num_pages << PAGE_CACHE_SHIFT) - 1;
+       start_pos = pos & ~((u64)root->sectorsize - 1);
+       last_pos = start_pos
+               + ALIGN(pos + write_bytes - start_pos, root->sectorsize) - 1;
 
-	if (start_pos < inode->i_size) {
+       if (start_pos < inode->i_size) {
 		struct btrfs_ordered_extent *ordered;
 		lock_extent_bits(&BTRFS_I(inode)->io_tree,
 				 start_pos, last_pos, 0, cached_state);

@@ -1494,6 +1497,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 
 	while (iov_iter_count(i) > 0) {
 		size_t offset = pos & (PAGE_CACHE_SIZE - 1);
+		size_t sector_offset;
 		size_t write_bytes = min(iov_iter_count(i),
 					 nrptrs * (size_t)PAGE_CACHE_SIZE -
 					 offset);

@@ -1514,7 +1518,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			break;
 		}
 
-		reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+		sector_offset = pos & (root->sectorsize - 1);
+		reserve_bytes = ALIGN(write_bytes + sector_offset, root->sectorsize);
+
 		ret = btrfs_check_data_free_space(inode, reserve_bytes);
 		if (ret == -ENOSPC &&
 		    (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |

@@ -1529,7 +1535,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 				num_pages = (write_bytes + offset +
 					     PAGE_CACHE_SIZE - 1) >>
 					PAGE_CACHE_SHIFT;
-				reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+
+				reserve_bytes = ALIGN(write_bytes + sector_offset,
+						root->sectorsize);
 				ret = 0;
 			} else {
 				ret = -ENOSPC;

@@ -1564,8 +1572,8 @@ again:
 			break;
 
 		ret = lock_and_cleanup_extent_if_need(inode, pages, num_pages,
-						      pos, &lockstart, &lockend,
-						      &cached_state);
+						pos, write_bytes, &lockstart, &lockend,
+						&cached_state);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				goto again;

@@ -1602,9 +1610,9 @@ again:
 		 * we still have an outstanding extent for the chunk we actually
 		 * managed to copy.
 		 */
-		if (num_pages > dirty_pages) {
-			release_bytes = (num_pages - dirty_pages) <<
-				PAGE_CACHE_SHIFT;
+		if (write_bytes > copied) {
+			release_bytes = (write_bytes - copied)
+				& ~((u64)root->sectorsize - 1);
 			if (copied > 0) {
 				spin_lock(&BTRFS_I(inode)->lock);
 				BTRFS_I(inode)->outstanding_extents++;

@@ -1618,7 +1626,7 @@ again:
 							     release_bytes);
 		}
 
-		release_bytes = dirty_pages << PAGE_CACHE_SHIFT;
+		release_bytes = ALIGN(copied + sector_offset, root->sectorsize);
 
 		if (copied > 0)
 			ret = btrfs_dirty_pages(root, inode, pages,

@@ -1640,7 +1648,7 @@ again:
 		if (only_release_metadata && copied > 0) {
 			u64 lockstart = round_down(pos, root->sectorsize);
 			u64 lockend = lockstart +
-				(dirty_pages << PAGE_CACHE_SHIFT) - 1;
+				ALIGN(copied, root->sectorsize) - 1;
 
 			set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
 				       lockend, EXTENT_NORESERVE, NULL,

index 54a201d..1d3d5d6 100644
@@ -1305,7 +1305,7 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
 		if (eb != eb_in) {
-			atomic_inc(&eb->refs);
+			atomic_inc(&eb_head(eb)->refs);
 			btrfs_tree_read_lock(eb);
 			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
 		}

index 44ee5d2..693b541 100644
@@ -169,7 +169,7 @@ struct extent_buffer *btrfs_root_node(struct btrfs_root *root)
 		 * the inc_not_zero dance and if it doesn't work then
 		 * synchronize_rcu and try again.
 		 */
-		if (atomic_inc_not_zero(&eb->refs)) {
+		if (atomic_inc_not_zero(&eb_head(eb)->refs)) {
 			rcu_read_unlock();
 			break;
 		}

index 8e29b61..5b7b7ca 100644
@@ -2215,14 +2215,16 @@ static inline void btrfs_set_token_##name(struct extent_buffer *eb,	\
 #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits)		\
 static inline u##bits btrfs_##name(struct extent_buffer *eb)		\
 {									\
-	type *p = page_address(eb->pages[0]);				\
+	type *p = page_address(eb_head(eb)->pages[0]) +			\
+				(eb->start & (PAGE_CACHE_SIZE -1));	\
 	u##bits res = le##bits##_to_cpu(p->member);			\
 	return res;							\
 }									\
 static inline void btrfs_set_##name(struct extent_buffer *eb,		\
 				    u##bits val)			\
 {									\
-	type *p = page_address(eb->pages[0]);				\
+	type *p = page_address(eb_head(eb)->pages[0]) +			\
+				(eb->start & (PAGE_CACHE_SIZE -1));	\
 	p->member = cpu_to_le##bits(val);				\
 }
 

123 lines not on this page · raw message

index 102ed31..fbcad82 100644
@@ -6209,7 +6209,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 
-		WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
+		WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->ebflags));
 
 		btrfs_add_free_space(cache, buf->start, buf->len);
 		btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0);

@@ -6226,7 +6226,7 @@ out:
 	 * Deleting the buffer, clear the corrupt flag since it doesn't matter
 	 * anymore.
 	 */
-	clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
+	clear_bit(EXTENT_BUFFER_CORRUPT, &buf->ebflags);
 	btrfs_put_block_group(cache);
 }
 

@@ -7212,7 +7212,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
 	clean_tree_block(trans, root, buf);
-	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
+	clear_bit(EXTENT_BUFFER_STALE, &buf->ebflags);
 
 	btrfs_set_lock_blocking(buf);
 	btrfs_set_buffer_uptodate(buf);

704 lines not on this page · raw message

87 lines not on this page · raw message

index 6cb82f6..99bafcb 100644
@@ -6060,7 +6060,7 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	 * to silence the warning eg. on PowerPC 64.
 	 */
 	if (PAGE_CACHE_SIZE > BTRFS_SUPER_INFO_SIZE)
-		SetPageUptodate(sb->pages[0]);
+		SetPageUptodate(eb_head(sb)->pages[0]);
 
 	write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE);
 	array_size = btrfs_super_sys_array_size(super_copy);

index 4ee4e30..2dc966e 100644
@@ -697,7 +697,7 @@ TRACE_EVENT(btrfs_cow_block,
 	TP_fast_assign(
 		__entry->root_objectid	= root->root_key.objectid;
 		__entry->buf_start	= buf->start;
-		__entry->refs		= atomic_read(&buf->refs);
+		__entry->refs		= atomic_read(&eb_head(buf)->refs);
 		__entry->cow_start	= cow->start;
 		__entry->buf_level	= btrfs_header_level(buf);
 		__entry->cow_level	= btrfs_header_level(cow);

index 3a79833..20168e6 100644
@@ -431,7 +431,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 	int mirror_num = 0;
 	int failed_mirror = 0;
 
-	clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
+	clear_bit(EXTENT_BUFFER_CORRUPT, &eb->ebflags);
 	io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
 	while (1) {
 		ret = read_extent_buffer_pages(io_tree, eb, start,

@@ -450,7 +450,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 		 * there is no reason to read the other copies, they won't be
 		 * any less wrong.
 		 */
-		if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
+		if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->ebflags))
 			break;
 
 		num_copies = btrfs_num_copies(root->fs_info,

@@ -582,12 +582,13 @@ static noinline int check_leaf(struct btrfs_root *root,
 	return 0;
 }
 
-static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
-				      u64 phy_offset, struct page *page,
-				      u64 start, u64 end, int mirror)
+int verify_extent_buffer_read(struct btrfs_io_bio *io_bio,
+			struct page *page,
+			u64 start, u64 end, int mirror)
 {
 	u64 found_start;
 	int found_level;
+	struct extent_buffer_head *ebh;
 	struct extent_buffer *eb;
 	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
 	int ret = 0;

@@ -597,18 +598,26 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 		goto out;
 
 	eb = (struct extent_buffer *)page->private;
+	do {
+		if ((eb->start <= start) && (eb->start + eb->len - 1 > start))
+			break;
+	} while ((eb = eb->eb_next) != NULL);
+
+	BUG_ON(!eb);
+
+	ebh = eb_head(eb);
 
 	/* the pending IO might have been the only thing that kept this buffer
 	 * in memory.  Make sure we have a ref for all this other checks
 	 */
 	extent_buffer_get(eb);
 
-	reads_done = atomic_dec_and_test(&eb->io_pages);
+	reads_done = atomic_dec_and_test(&ebh->io_bvecs);
 	if (!reads_done)
 		goto err;
 
 	eb->read_mirror = mirror;
-	if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
+	if (test_bit(EXTENT_BUFFER_IOERR, &eb->ebflags)) {
 		ret = -EIO;
 		goto err;
 	}

@@ -650,7 +659,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	 * return -EIO.
 	 */
 	if (found_level == 0 && check_leaf(root, eb)) {
-		set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
+		set_bit(EXTENT_BUFFER_CORRUPT, &eb->ebflags);
 		ret = -EIO;
 	}
 

@@ -658,7 +667,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 		set_extent_buffer_uptodate(eb);
 err:
 	if (reads_done &&
-	    test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
+	    test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->ebflags))
 		btree_readahead_hook(root, eb, eb->start, ret);
 
 	if (ret) {

@@ -667,7 +676,7 @@ err:
 		 * again, we have to make sure it has something
 		 * to decrement
 		 */
-		atomic_inc(&eb->io_pages);
+		atomic_inc(&eb_head(eb)->io_bvecs);
 		clear_extent_buffer_uptodate(eb);
 	}
 	free_extent_buffer(eb);

@@ -675,20 +684,6 @@ out:
 	return ret;
 }
 
-static int btree_io_failed_hook(struct page *page, int failed_mirror)
-{
-	struct extent_buffer *eb;
-	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
-
-	eb = (struct extent_buffer *)page->private;
-	set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
-	eb->read_mirror = failed_mirror;
-	atomic_dec(&eb->io_pages);
-	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
-		btree_readahead_hook(root, eb, eb->start, -EIO);
-	return -EIO;	/* we fixed nothing */
-}
-
 static void end_workqueue_bio(struct bio *bio, int err)
 {
 	struct end_io_wq *end_io_wq = bio->bi_private;

@@ -4156,8 +4151,6 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 }
 
 static struct extent_io_ops btree_extent_io_ops = {
-	.readpage_end_io_hook = btree_readpage_end_io_hook,
-	.readpage_io_failed_hook = btree_io_failed_hook,
 	.submit_bio_hook = btree_submit_bio_hook,
 	/* note we're sharing with inode.c for the merge bio hook */
 	.merge_bio_hook = btrfs_merge_bio_hook,

index 23ce3ce..482ed21 100644
@@ -111,6 +111,9 @@ static inline void btrfs_put_fs_root(struct btrfs_root *root)
 		kfree(root);
 }
 
+int verify_extent_buffer_read(struct btrfs_io_bio *io_bio,
+			struct page *page,
+			u64 start, u64 end, int mirror);
 void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
 int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
 			  int atomic);

181 lines not on this page · raw message

index 20168e6..6c6e8bb 100644
@@ -484,17 +484,23 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 
 static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
 {
-	u64 start = page_offset(page);
-	u64 found_start;
 	struct extent_buffer *eb;
+	u64 found_start;
 
 	eb = (struct extent_buffer *)page->private;
-	if (page != eb->pages[0])
+	if (page != eb_head(eb)->pages[0])
 		return 0;
-	found_start = btrfs_header_bytenr(eb);
-	if (WARN_ON(found_start != start || !PageUptodate(page)))
-		return 0;
-	csum_tree_block(root, eb, 0);
+	do {
+		if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags))
+			continue;
+		if (WARN_ON(!test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags)))
+			continue;
+		found_start = btrfs_header_bytenr(eb);
+		if (WARN_ON(found_start != eb->start))
+			return 0;
+		csum_tree_block(root, eb, 0);
+	} while ((eb = eb->eb_next) != NULL);
+
 	return 0;
 }
 

422 lines not on this page · raw message

index 6c6e8bb..2f3caaf 100644
@@ -2634,12 +2634,6 @@ int open_ctree(struct super_block *sb,
 		goto fail_sb_buffer;
 	}
 
-	if (sectorsize != PAGE_SIZE) {
-		printk(KERN_WARNING "BTRFS: Incompatible sector size(%lu) "
-		       "found on %s\n", (unsigned long)sectorsize, sb->s_id);
-		goto fail_sb_buffer;
-	}
-
 	mutex_lock(&fs_info->chunk_mutex);
 	ret = btrfs_read_sys_array(tree_root);
 	mutex_unlock(&fs_info->chunk_mutex);

index 54c84da..000418a 100644
@@ -172,6 +172,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	u64 item_start_offset = 0;
 	u64 item_last_offset = 0;
 	u64 disk_bytenr;
+	u64 page_bytes_left;
 	u32 diff;
 	int nblocks;
 	int bio_index = 0;

@@ -220,6 +221,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
 	if (dio)
 		offset = logical_offset;
+
+	page_bytes_left = bvec->bv_len;
 	while (bio_index < bio->bi_vcnt) {
 		if (!dio)
 			offset = page_offset(bvec->bv_page) + bvec->bv_offset;

@@ -243,7 +246,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 				if (BTRFS_I(inode)->root->root_key.objectid ==
 				    BTRFS_DATA_RELOC_TREE_OBJECTID) {
 					set_extent_bits(io_tree, offset,
-						offset + bvec->bv_len - 1,
+						offset + root->sectorsize - 1,
 						EXTENT_NODATASUM, GFP_NOFS);
 				} else {
 					btrfs_info(BTRFS_I(inode)->root->fs_info,

@@ -281,11 +284,17 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 found:
 		csum += count * csum_size;
 		nblocks -= count;
-		bio_index += count;
+
 		while (count--) {
-			disk_bytenr += bvec->bv_len;
-			offset += bvec->bv_len;
-			bvec++;
+			disk_bytenr += root->sectorsize;
+			offset += root->sectorsize;
+			page_bytes_left -= root->sectorsize;
+			if (!page_bytes_left) {
+				bio_index++;
+				bvec++;
+				page_bytes_left = bvec->bv_len;
+			}
+
 		}
 	}
 	btrfs_free_path(path);

@@ -442,6 +451,8 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 	struct bio_vec *bvec = bio->bi_io_vec;
 	int bio_index = 0;
 	int index;
+	int nr_sectors;
+	int i;
 	unsigned long total_bytes = 0;
 	unsigned long this_sum_bytes = 0;
 	u64 offset;

@@ -469,41 +480,51 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		if (!contig)
 			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
 
-		if (offset >= ordered->file_offset + ordered->len ||
-		    offset < ordered->file_offset) {
-			unsigned long bytes_left;
-			sums->len = this_sum_bytes;
-			this_sum_bytes = 0;
-			btrfs_add_ordered_sum(inode, ordered, sums);
-			btrfs_put_ordered_extent(ordered);
+		data = kmap_atomic(bvec->bv_page);
 
-			bytes_left = bio->bi_iter.bi_size - total_bytes;
 
-			sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
-				       GFP_NOFS);
-			BUG_ON(!sums); /* -ENOMEM */
-			sums->len = bytes_left;
-			ordered = btrfs_lookup_ordered_extent(inode, offset);
-			BUG_ON(!ordered); /* Logic error */
-			sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
-				       total_bytes;
-			index = 0;
+		nr_sectors = (bvec->bv_len + root->sectorsize - 1)
+			>> root->fs_info->sb->s_blocksize_bits;
+
+
+		for (i = 0; i < nr_sectors; i++) {
+			if (offset >= ordered->file_offset + ordered->len ||
+				offset < ordered->file_offset) {
+				unsigned long bytes_left;
+				sums->len = this_sum_bytes;
+				this_sum_bytes = 0;
+				btrfs_add_ordered_sum(inode, ordered, sums);
+				btrfs_put_ordered_extent(ordered);
+
+				bytes_left = bio->bi_iter.bi_size - total_bytes;
+
+				sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
+					GFP_NOFS);
+				BUG_ON(!sums); /* -ENOMEM */
+				sums->len = bytes_left;
+				ordered = btrfs_lookup_ordered_extent(inode, offset);
+				BUG_ON(!ordered); /* Logic error */
+				sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
+					total_bytes;
+				index = 0;
+			}
+
+			sums->sums[index] = ~(u32)0;
+			sums->sums[index]
+				= btrfs_csum_data(data + bvec->bv_offset + (i * root->sectorsize),
+						sums->sums[index],
+						root->sectorsize);
+			btrfs_csum_final(sums->sums[index],
+					(char *)(sums->sums + index));
+			index++;
+			offset += root->sectorsize;
+			this_sum_bytes += root->sectorsize;
+			total_bytes += root->sectorsize;
 		}
 
-		data = kmap_atomic(bvec->bv_page);
-		sums->sums[index] = ~(u32)0;
-		sums->sums[index] = btrfs_csum_data(data + bvec->bv_offset,
-						    sums->sums[index],
-						    bvec->bv_len);
 		kunmap_atomic(data);
-		btrfs_csum_final(sums->sums[index],
-				 (char *)(sums->sums + index));
 
 		bio_index++;
-		index++;
-		total_bytes += bvec->bv_len;
-		this_sum_bytes += bvec->bv_len;
-		offset += bvec->bv_len;
 		bvec++;
 	}
 	this_sum_bytes = 0;

72 lines not on this page · raw message

index bbb5e980..ceaf137 100644
@@ -3212,18 +3212,18 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 				 int write_flags, int *nr_ret)
 {
 	struct extent_io_tree *tree = epd->tree;
+	struct btrfs_ordered_extent *ordered;
 	u64 start = page_offset(page);
 	u64 page_end = start + PAGE_CACHE_SIZE - 1;
 	u64 end;
 	u64 cur = start;
 	u64 extent_offset;
-	u64 block_start;
+	u64 extent_end;
 	u64 iosize;
 	sector_t sector;
 	struct extent_state *cached_state = NULL;
-	struct extent_map *em;
 	struct block_device *bdev;
-	size_t pg_offset = 0;
+	size_t pg_offset;
 	size_t blocksize;
 	int ret = 0;
 	int nr = 0;

@@ -3263,59 +3263,46 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 	blocksize = inode->i_sb->s_blocksize;
 
 	while (cur <= end) {
-		u64 em_end;
 		if (cur >= i_size) {
 			if (tree->ops && tree->ops->writepage_end_io_hook)
 				tree->ops->writepage_end_io_hook(page, cur,
 							 page_end, NULL, 1);
 			break;
 		}
-		em = epd->get_extent(inode, page, pg_offset, cur,
-				     end - cur + 1, 1);
-		if (IS_ERR_OR_NULL(em)) {
-			SetPageError(page);
-			ret = PTR_ERR_OR_ZERO(em);
-			break;
-		}
 
-		extent_offset = cur - em->start;
-		em_end = extent_map_end(em);
-		BUG_ON(em_end <= cur);
+		ordered = btrfs_lookup_ordered_extent(inode, cur);
+		if (!ordered) {
+			cur += blocksize;
+			continue;
+ 		}
+
+		pg_offset = cur & (PAGE_CACHE_SIZE - 1);
+
+		extent_offset = cur - ordered->file_offset;
+		extent_end = ordered->file_offset + ordered->len;
+		extent_end = (extent_end < ordered->file_offset) ? -1 : extent_end;
+		BUG_ON(extent_end <= cur);
 		BUG_ON(end < cur);
-		iosize = min(em_end - cur, end - cur + 1);
+		iosize = min(extent_end - cur, end - cur + 1);
 		iosize = ALIGN(iosize, blocksize);
-		sector = (em->block_start + extent_offset) >> 9;
-		bdev = em->bdev;
-		block_start = em->block_start;
-		compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-		free_extent_map(em);
-		em = NULL;
+
+		sector = (ordered->start + extent_offset) >> 9;
+		bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
+		compressed = test_bit(BTRFS_ORDERED_COMPRESSED, &ordered->flags);
+		btrfs_put_ordered_extent(ordered);
+		ordered = NULL;
 
 		/*
 		 * compressed and inline extents are written through other
 		 * paths in the FS
 		 */
-		if (compressed || block_start == EXTENT_MAP_HOLE ||
-		    block_start == EXTENT_MAP_INLINE) {
-			/*
-			 * end_io notification does not happen here for
-			 * compressed extents
-			 */
-			if (!compressed && tree->ops &&
-			    tree->ops->writepage_end_io_hook)
-				tree->ops->writepage_end_io_hook(page, cur,
-							 cur + iosize - 1,
-							 NULL, 1);
-			else if (compressed) {
-				/* we don't want to end_page_writeback on
-				 * a compressed extent.  this happens
-				 * elsewhere
-				 */
-				nr++;
-			}
-
+		if (compressed) {
+			/* we don't want to end_page_writeback on
+			 * a compressed extent.  this happens
+			 * elsewhere
+ 			 */
+			nr++;
 			cur += iosize;
-			pg_offset += iosize;
 			continue;
 		}
 

@@ -3346,7 +3333,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 				SetPageError(page);
 		}
 		cur = cur + iosize;
-		pg_offset += iosize;
 		nr++;
 	}
 done:

@@ -3374,7 +3360,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	u64 page_end = start + PAGE_CACHE_SIZE - 1;
 	int ret;
 	int nr = 0;
-	size_t pg_offset = 0;
+	size_t pg_offset;
 	loff_t i_size = i_size_read(inode);
 	unsigned long end_index = i_size >> PAGE_CACHE_SHIFT;
 	int write_flags;

@@ -3409,8 +3395,6 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 		flush_dcache_page(page);
 	}
 
-	pg_offset = 0;
-
 	set_page_extent_mapped(page);
 
 	ret = writepage_delalloc(inode, page, wbc, epd, start, &nr_written);

index 5b7b7ca..59779dc 100644
@@ -3815,7 +3815,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct inode *dir, u64 objectid,
 			const char *name, int name_len);
-int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
+int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 			int front);
 int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,

93 lines not on this page · raw message

123 lines not on this page · raw message

index 7ad7d0f..23ce9ff 100644
@@ -7812,26 +7812,23 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	loff_t size;
 	int ret;
 	int reserved = 0;
+	u64 delalloc_size;
 	u64 page_start;
 	u64 page_end;
 
 	sb_start_pagefault(inode->i_sb);
-	ret  = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
-	if (!ret) {
-		ret = file_update_time(vma->vm_file);
-		reserved = 1;
-	}
+
+	ret = file_update_time(vma->vm_file);
 	if (ret) {
 		if (ret == -ENOMEM)
 			ret = VM_FAULT_OOM;
 		else /* -ENOSPC, -EIO, etc */
 			ret = VM_FAULT_SIGBUS;
-		if (reserved)
-			goto out;
-		goto out_noreserve;
+		goto out;
 	}
 
 	ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
+
 again:
 	lock_page(page);
 	size = i_size_read(inode);

@@ -7862,6 +7859,19 @@ again:
 		goto again;
 	}
 
+	if (page->index == ((size - 1) >> PAGE_CACHE_SHIFT))
+		delalloc_size = round_up(size - page_start, root->sectorsize);
+	else
+		delalloc_size = PAGE_CACHE_SIZE;
+
+	ret = btrfs_delalloc_reserve_space(inode, delalloc_size);
+	if (ret) {
+		/* -ENOSPC */
+		ret = VM_FAULT_SIGBUS;
+		goto out_unlock;
+	}
+	reserved = 1;
+
 	/*
 	 * XXX - page_mkwrite gets called every time the page is dirtied, even
 	 * if it was already dirty, so for space accounting reasons we need to

@@ -7874,7 +7884,8 @@ again:
 			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
 			  0, 0, &cached_state, GFP_NOFS);
 
-	ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
+	ret = btrfs_set_extent_delalloc(inode, page_start,
+					page_start + delalloc_size - 1,
 					&cached_state);
 	if (ret) {
 		unlock_extent_cached(io_tree, page_start, page_end,

@@ -7913,8 +7924,8 @@ out_unlock:
 	}
 	unlock_page(page);
 out:
-	btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
-out_noreserve:
+	if (reserved)
+		btrfs_delalloc_release_space(inode, delalloc_size);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 }

index ceaf137..3f6bec2 100644
@@ -3053,7 +3053,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 
 	while (1) {
 		lock_extent(tree, start, end);
-		ordered = btrfs_lookup_ordered_extent(inode, start);
+		ordered = btrfs_lookup_ordered_range(inode, start,
+						PAGE_CACHE_SIZE);
 		if (!ordered)
 			break;
 		unlock_extent(tree, start, end);

index 23ce9ff..91c5580 100644
@@ -1821,7 +1821,7 @@ again:
 	if (PagePrivate2(page))
 		goto out;
 
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+	ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_CACHE_SIZE);
 	if (ordered) {
 		unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
 				     page_end, &cached_state, GFP_NOFS);

@@ -7724,7 +7724,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 
 	if (!inode_evicting)
 		lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+	ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_CACHE_SIZE);
 	if (ordered) {
 		/*
 		 * IO on this page will never be started, so we need

@@ -7849,7 +7849,7 @@ again:
 	 * we can't set the delalloc bits if there are pending ordered
 	 * extents.  Drop our locks and wait for them to finish
 	 */
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+	ordered = btrfs_lookup_ordered_range(inode, page_start, page_end);
 	if (ordered) {
 		unlock_extent_cached(io_tree, page_start, page_end,
 				     &cached_state, GFP_NOFS);

index 3f6bec2..51ab453 100644
@@ -1774,15 +1774,22 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 			if (page_ops & PAGE_SET_PRIVATE2)
 				SetPagePrivate2(pages[i]);
 
+			if (page_ops & PAGE_SET_ERROR)
+				SetPageError(pages[i]);
+
 			if (pages[i] == locked_page) {
 				page_cache_release(pages[i]);
 				continue;
 			}
-			if (page_ops & PAGE_CLEAR_DIRTY)
+
+			if ((page_ops & PAGE_CLEAR_DIRTY)
+				&& !PagePrivate2(pages[i]))
 				clear_page_dirty_for_io(pages[i]);
-			if (page_ops & PAGE_SET_WRITEBACK)
+			if ((page_ops & PAGE_SET_WRITEBACK)
+				&& !PagePrivate2(pages[i]))
 				set_page_writeback(pages[i]);
-			if (page_ops & PAGE_END_WRITEBACK)
+			if ((page_ops & PAGE_END_WRITEBACK)
+				&& !PagePrivate2(pages[i]))
 				end_page_writeback(pages[i]);
 			if (page_ops & PAGE_UNLOCK)
 				unlock_page(pages[i]);

@@ -2398,7 +2405,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 			uptodate = 0;
 	}
 
-	if (!uptodate) {
+	if (!uptodate || PageError(page)) {
 		ClearPageUptodate(page);
 		SetPageError(page);
 		ret = ret < 0 ? ret : -EIO;

@@ -3149,7 +3156,6 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode,
 					       nr_written);
 		/* File system has been set read-only */
 		if (ret) {
-			SetPageError(page);
 			/* fill_delalloc should be return < 0 for error
 			 * but just in case, we use > 0 here meaning the
 			 * IO is started, so we don't want to return > 0

@@ -3358,7 +3364,6 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	struct inode *inode = page->mapping->host;
 	struct extent_page_data *epd = data;
 	u64 start = page_offset(page);
-	u64 page_end = start + PAGE_CACHE_SIZE - 1;
 	int ret;
 	int nr = 0;
 	size_t pg_offset;

@@ -3401,7 +3406,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	ret = writepage_delalloc(inode, page, wbc, epd, start, &nr_written);
 	if (ret == 1)
 		goto done_unlocked;
-	if (ret)
+	if (ret && !PagePrivate2(page))
 		goto done;
 
 	ret = __extent_writepage_io(inode, page, wbc, epd,

@@ -3415,10 +3420,7 @@ done:
 		set_page_writeback(page);
 		end_page_writeback(page);
 	}
-	if (PageError(page)) {
-		ret = ret < 0 ? ret : -EIO;
-		end_extent_writepage(page, ret, start, page_end);
-	}
+
 	unlock_page(page);
 	return ret;
 

index 39e14fc..264dfd4 100644
@@ -52,6 +52,7 @@
 #define PAGE_SET_WRITEBACK	(1 << 2)
 #define PAGE_END_WRITEBACK	(1 << 3)
 #define PAGE_SET_PRIVATE2	(1 << 4)
+#define PAGE_SET_ERROR		(1 << 5)
 
 /*
  * page->private values.  Every page that is controlled by the extent

index 91c5580..4ed78dd 100644
@@ -880,6 +880,8 @@ static noinline int cow_file_range(struct inode *inode,
 	struct btrfs_key ins;
 	struct extent_map *em;
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct btrfs_ordered_extent *ordered;
+	unsigned long page_ops, extent_ops;
 	int ret = 0;
 
 	if (btrfs_is_free_space_inode(inode)) {

@@ -924,8 +926,6 @@ static noinline int cow_file_range(struct inode *inode,
 	btrfs_drop_extent_cache(inode, start, start + num_bytes - 1, 0);
 
 	while (disk_num_bytes > 0) {
-		unsigned long op;
-
 		cur_alloc_size = disk_num_bytes;
 		ret = btrfs_reserve_extent(root, cur_alloc_size,
 					   root->sectorsize, 0, alloc_hint,

@@ -971,14 +971,14 @@ static noinline int cow_file_range(struct inode *inode,
 		ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
 					       ram_size, cur_alloc_size, 0);
 		if (ret)
-			goto out_reserve;
+			goto out_remove_extent_map;
 
 		if (root->root_key.objectid ==
 		    BTRFS_DATA_RELOC_TREE_OBJECTID) {
 			ret = btrfs_reloc_clone_csums(inode, start,
 						      cur_alloc_size);
 			if (ret)
-				goto out_reserve;
+				goto out_remove_ordered_extent;
 		}
 
 		if (disk_num_bytes < cur_alloc_size)

@@ -991,13 +991,12 @@ static noinline int cow_file_range(struct inode *inode,
 		 * Do set the Private2 bit so we know this page was properly
 		 * setup for writepage
 		 */
-		op = unlock ? PAGE_UNLOCK : 0;
-		op |= PAGE_SET_PRIVATE2;
-
+		page_ops = unlock ? PAGE_UNLOCK : 0;
+		page_ops |= PAGE_SET_PRIVATE2;
+		extent_ops = EXTENT_LOCKED | EXTENT_DELALLOC;
 		extent_clear_unlock_delalloc(inode, start,
-					     start + ram_size - 1, locked_page,
-					     EXTENT_LOCKED | EXTENT_DELALLOC,
-					     op);
+					start + ram_size - 1, locked_page,
+					extent_ops, page_ops);
 		disk_num_bytes -= cur_alloc_size;
 		num_bytes -= cur_alloc_size;
 		alloc_hint = ins.objectid + ins.offset;

@@ -1006,14 +1005,26 @@ static noinline int cow_file_range(struct inode *inode,
 out:
 	return ret;
 
+out_remove_ordered_extent:
+	ordered = btrfs_lookup_ordered_extent(inode, ins.objectid);
+	BUG_ON(!ordered);
+	btrfs_remove_ordered_extent(inode, ordered);
+
+out_remove_extent_map:
+	btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0);
+
 out_reserve:
 	btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
+
 out_unlock:
+	page_ops = unlock ? PAGE_UNLOCK : 0;
+	page_ops |= PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK
+		| PAGE_SET_ERROR;
+	extent_ops = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING
+		| EXTENT_DEFRAG;
+
 	extent_clear_unlock_delalloc(inode, start, end, locked_page,
-				     EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
-				     EXTENT_DELALLOC | EXTENT_DEFRAG,
-				     PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
-				     PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK);
+				extent_ops, page_ops);
 	goto out;
 }
 

index 51ab453..f9172aa 100644
@@ -4302,11 +4302,10 @@ int extent_invalidatepage(struct extent_io_tree *tree,
  * to drop the page.
  */
 static int try_release_extent_state(struct extent_map_tree *map,
-				    struct extent_io_tree *tree,
-				    struct page *page, gfp_t mask)
+				struct extent_io_tree *tree,
+				struct page *page, u64 start, u64 end,
+				gfp_t mask)
 {
-	u64 start = page_offset(page);
-	u64 end = start + PAGE_CACHE_SIZE - 1;
 	int ret = 1;
 
 	if (test_range_bit(tree, start, end,

@@ -4340,12 +4339,12 @@ static int try_release_extent_state(struct extent_map_tree *map,
  * map records are removed
  */
 int try_release_extent_mapping(struct extent_map_tree *map,
-			       struct extent_io_tree *tree, struct page *page,
-			       gfp_t mask)
+			struct extent_io_tree *tree, struct page *page,
+			u64 start, u64 end, gfp_t mask)
 {
 	struct extent_map *em;
-	u64 start = page_offset(page);
-	u64 end = start + PAGE_CACHE_SIZE - 1;
+	u64 orig_start = start;
+	u64 orig_end = end;
 
 	if ((mask & __GFP_WAIT) &&
 	    page->mapping->host->i_size > 16 * 1024 * 1024) {

@@ -4379,7 +4378,9 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 			free_extent_map(em);
 		}
 	}
-	return try_release_extent_state(map, tree, page, mask);
+	return try_release_extent_state(map, tree, page,
+					orig_start, orig_end,
+					mask);
 }
 
 /*

index 264dfd4..15bb2a7 100644
@@ -209,8 +209,9 @@ typedef struct extent_map *(get_extent_t)(struct inode *inode,
 void extent_io_tree_init(struct extent_io_tree *tree,
 			 struct address_space *mapping);
 int try_release_extent_mapping(struct extent_map_tree *map,
-			       struct extent_io_tree *tree, struct page *page,
-			       gfp_t mask);
+			struct extent_io_tree *tree, struct page *page,
+			u64 start, u64 end,
+			gfp_t mask);
 int try_release_extent_buffer(struct page *page);
 int lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,

415 lines not on this page · raw message

index 963895c..4d9832f 100644
@@ -189,12 +189,25 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	struct btrfs_ordered_inode_tree *tree;
 	struct rb_node *node;
 	struct btrfs_ordered_extent *entry;
+	u64 nr_longs;
 
 	tree = &BTRFS_I(inode)->ordered_tree;
 	entry = kmem_cache_zalloc(btrfs_ordered_extent_cache, GFP_NOFS);
 	if (!entry)
 		return -ENOMEM;
 
+	nr_longs = BITS_TO_LONGS(len >> inode->i_sb->s_blocksize_bits);
+	if (nr_longs == 1) {
+		entry->blocks_done = &entry->blocks_bitmap;
+	} else {
+		entry->blocks_done = kzalloc(nr_longs * sizeof(unsigned long),
+					GFP_NOFS);
+		if (!entry->blocks_done) {
+			kmem_cache_free(btrfs_ordered_extent_cache, entry);
+			return -ENOMEM;
+		}
+	}
+
 	entry->file_offset = file_offset;
 	entry->start = start;
 	entry->len = len;

@@ -541,6 +554,10 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 			list_del(&sum->list);
 			kfree(sum);
 		}
+
+		if (entry->blocks_done != &entry->blocks_bitmap)
+			kfree(entry->blocks_done);
+
 		kmem_cache_free(btrfs_ordered_extent_cache, entry);
 	}
 }

index d81a274..7de3b1e 100644
@@ -135,6 +135,10 @@ struct btrfs_ordered_extent {
 	struct completion completion;
 	struct btrfs_work flush_work;
 	struct list_head work_list;
+
+	/* bitmap to track the blocks that have been written to disk */
+	unsigned long *blocks_done;
+	unsigned long blocks_bitmap;
 };
 
 /*

index 43527fd..50497bf 100644
@@ -278,6 +278,4 @@ static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
 		  &BTRFS_I(inode)->runtime_flags);
 }
 
-bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end);
-
 #endif

index b1e0d27..3707515 100644
@@ -2314,7 +2314,9 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		if ((!ordered ||
 		    (ordered->file_offset + ordered->len <= lockstart ||
 		     ordered->file_offset > lockend)) &&
-		     !btrfs_page_exists_in_range(inode, lockstart, lockend)) {
+		     !test_range_bit(&BTRFS_I(inode)->io_tree, lockstart,
+				     lockend, EXTENT_UPTODATE, 0,
+				     cached_state)) {
 			if (ordered)
 				btrfs_put_ordered_extent(ordered);
 			break;

89 lines not on this page · raw message

index f9172aa..bc4dd46 100644
@@ -3227,6 +3227,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 	u64 extent_offset;
 	u64 extent_end;
 	u64 iosize;
+	u64 blk, nr_blks;
+	u64 blk_submitted;
 	sector_t sector;
 	struct extent_state *cached_state = NULL;
 	struct block_device *bdev;

@@ -3293,11 +3295,26 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 		iosize = min(extent_end - cur, end - cur + 1);
 		iosize = ALIGN(iosize, blocksize);
 
+		blk = extent_offset >> inode->i_sb->s_blocksize_bits;
+		nr_blks = iosize >> inode->i_sb->s_blocksize_bits;
+
+		blk_submitted = find_next_bit(ordered->blocks_submitted,
+					ordered->len >> inode->i_sb->s_blocksize_bits,
+					blk);
+		if (blk_submitted < blk + nr_blks) {
+			if (blk_submitted == blk) {
+				cur += blocksize;
+				btrfs_put_ordered_extent(ordered);
+				continue;
+			}
+			iosize = (blk_submitted - blk)
+				<< inode->i_sb->s_blocksize_bits;
+			nr_blks = iosize >> inode->i_sb->s_blocksize_bits;
+		}
+
 		sector = (ordered->start + extent_offset) >> 9;
 		bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
 		compressed = test_bit(BTRFS_ORDERED_COMPRESSED, &ordered->flags);
-		btrfs_put_ordered_extent(ordered);
-		ordered = NULL;
 
 		/*
 		 * compressed and inline extents are written through other

@@ -3310,6 +3327,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
  			 */
 			nr++;
 			cur += iosize;
+			btrfs_put_ordered_extent(ordered);
 			continue;
 		}
 

@@ -3324,6 +3342,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 		} else {
 			unsigned long max_nr = (i_size >> PAGE_CACHE_SHIFT) + 1;
 
+			bitmap_set(ordered->blocks_submitted, blk, nr_blks);
+			btrfs_put_ordered_extent(ordered);
 			set_range_writeback(tree, cur, cur + iosize - 1);
 			if (!PageWriteback(page)) {
 				btrfs_err(BTRFS_I(inode)->root->fs_info,

index 4d9832f..59b2544 100644
@@ -199,13 +199,15 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	nr_longs = BITS_TO_LONGS(len >> inode->i_sb->s_blocksize_bits);
 	if (nr_longs == 1) {
 		entry->blocks_done = &entry->blocks_bitmap;
+		entry->blocks_submitted = &entry->blocks_submitted_bitmap;
 	} else {
-		entry->blocks_done = kzalloc(nr_longs * sizeof(unsigned long),
+		entry->blocks_done = kzalloc(2 * nr_longs * sizeof(unsigned long),
 					GFP_NOFS);
 		if (!entry->blocks_done) {
 			kmem_cache_free(btrfs_ordered_extent_cache, entry);
 			return -ENOMEM;
 		}
+		entry->blocks_submitted = entry->blocks_done + nr_longs;
 	}
 
 	entry->file_offset = file_offset;

index 7de3b1e..851914c 100644
@@ -139,6 +139,10 @@ struct btrfs_ordered_extent {
 	/* bitmap to track the blocks that have been written to disk */
 	unsigned long *blocks_done;
 	unsigned long blocks_bitmap;
+
+	/* bitmap to track the blocks that have been submitted for write i/o */
+	unsigned long *blocks_submitted;
+	unsigned long blocks_submitted_bitmap;
 };
 
 /*

index 693b541..75129da 100644
@@ -1543,6 +1543,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		    struct extent_buffer *parent, int parent_slot,
 		    struct extent_buffer **cow_ret)
 {
+	struct extent_buffer_head *ebh = eb_head(buf);
 	u64 search_start;
 	int ret;
 

@@ -1556,6 +1557,13 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		       trans->transid, root->fs_info->generation);
 
 	if (!should_cow_block(trans, root, buf)) {
+		if (test_bit(EXTENT_BUFFER_HEAD_WRITEBACK, &ebh->bflags)) {
+			if (parent)
+				btrfs_set_lock_blocking(parent);
+			btrfs_set_lock_blocking(buf);
+			wait_on_bit(&ebh->bflags, EXTENT_BUFFER_HEAD_WRITEBACK,
+				eb_wait, TASK_UNINTERRUPTIBLE);
+		}
 		*cow_ret = buf;
 		return 0;
 	}

@@ -2687,6 +2695,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *root, struct btrfs_key *key, struct btrfs_path *p, int
 		      ins_len, int cow)
 {
+	struct extent_buffer_head *ebh;
 	struct extent_buffer *b;
 	int slot;
 	int ret;

@@ -2789,8 +2798,17 @@ again:
 			 * then we don't want to set the path blocking,
 			 * so we test it here
 			 */
-			if (!should_cow_block(trans, root, b))
+			if (!should_cow_block(trans, root, b)) {
+				ebh = eb_head(b);
+				if (test_bit(EXTENT_BUFFER_HEAD_WRITEBACK,
+						&ebh->bflags)) {
+					btrfs_set_path_blocking(p);
+					wait_on_bit(&ebh->bflags,
+						EXTENT_BUFFER_HEAD_WRITEBACK,
+						eb_wait, TASK_UNINTERRUPTIBLE);
+				}
 				goto cow_done;
+			}
 
 			btrfs_set_path_blocking(p);
 

index fbcad82..fb5cc46 100644
@@ -7203,14 +7203,26 @@ static struct extent_buffer *
 btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		      u64 bytenr, u32 blocksize, int level)
 {
+	struct extent_buffer_head *ebh;
 	struct extent_buffer *buf;
 
 	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
+
+	ebh = eb_head(buf);
 	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
+
+	if (test_bit(EXTENT_BUFFER_HEAD_WRITEBACK,
+			&ebh->bflags)) {
+		btrfs_set_lock_blocking(buf);
+		wait_on_bit(&ebh->bflags,
+			EXTENT_BUFFER_HEAD_WRITEBACK,
+			eb_wait, TASK_UNINTERRUPTIBLE);
+	}
+
 	clean_tree_block(trans, root, buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->ebflags);
 

316 lines not on this page · raw message

index 15bb2a7..6e952fb 100644
@@ -45,6 +45,7 @@
 #define EXTENT_BUFFER_IOERR 8
 #define EXTENT_BUFFER_DUMMY 9
 #define EXTENT_BUFFER_IN_TREE 10
+#define EXTENT_BUFFER_HEAD_WRITEBACK 11
 
 /* these are flags for extent_clear_unlock_delalloc */
 #define PAGE_UNLOCK		(1 << 0)

@@ -302,6 +303,7 @@ void free_extent_buffer_stale(struct extent_buffer *eb);
 int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     struct extent_buffer *eb, u64 start, int wait,
 			     get_extent_t *get_extent, int mirror_num);
+int eb_wait(void *word);
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
 
 static inline unsigned long num_extent_pages(u64 start, u64 len)

index 75129da..8344f49 100644
@@ -314,7 +314,7 @@ struct tree_mod_root {
 
 struct tree_mod_elem {
 	struct rb_node node;
-	u64 index;		/* shifted logical */
+	u64 logical;
 	u64 seq;
 	enum mod_log_op op;
 

@@ -438,11 +438,11 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 
 /*
  * key order of the log:
- *       index -> sequence
+ *       node/leaf start address -> sequence
  *
- * the index is the shifted logical of the *new* root node for root replace
- * operations, or the shifted logical of the affected block for all other
- * operations.
+ * The 'start address' is the logical address of the *new* root node
+ * for root replace operations, or the logical address of the affected
+ * block for all other operations.
  *
  * Note: must be called with write lock (tree_mod_log_write_lock).
  */

@@ -463,9 +463,9 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
 	while (*new) {
 		cur = container_of(*new, struct tree_mod_elem, node);
 		parent = *new;
-		if (cur->index < tm->index)
+		if (cur->logical < tm->logical)
 			new = &((*new)->rb_left);
-		else if (cur->index > tm->index)
+		else if (cur->logical > tm->logical)
 			new = &((*new)->rb_right);
 		else if (cur->seq < tm->seq)
 			new = &((*new)->rb_left);

@@ -526,7 +526,7 @@ alloc_tree_mod_elem(struct extent_buffer *eb, int slot,
 	if (!tm)
 		return NULL;
 
-	tm->index = eb->start >> PAGE_CACHE_SHIFT;
+	tm->logical = eb->start;
 	if (op != MOD_LOG_KEY_ADD) {
 		btrfs_node_key(eb, &tm->key, slot);
 		tm->blockptr = btrfs_node_blockptr(eb, slot);

@@ -591,7 +591,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
 		goto free_tms;
 	}
 
-	tm->index = eb->start >> PAGE_CACHE_SHIFT;
+	tm->logical = eb->start;
 	tm->slot = src_slot;
 	tm->move.dst_slot = dst_slot;
 	tm->move.nr_items = nr_items;

@@ -702,7 +702,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 		goto free_tms;
 	}
 
-	tm->index = new_root->start >> PAGE_CACHE_SHIFT;
+	tm->logical = new_root->start;
 	tm->old_root.logical = old_root->start;
 	tm->old_root.level = btrfs_header_level(old_root);
 	tm->generation = btrfs_header_generation(old_root);

@@ -742,16 +742,15 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
 	struct rb_node *node;
 	struct tree_mod_elem *cur = NULL;
 	struct tree_mod_elem *found = NULL;
-	u64 index = start >> PAGE_CACHE_SHIFT;
 
 	tree_mod_log_read_lock(fs_info);
 	tm_root = &fs_info->tree_mod_log;
 	node = tm_root->rb_node;
 	while (node) {
 		cur = container_of(node, struct tree_mod_elem, node);
-		if (cur->index < index) {
+		if (cur->logical < start) {
 			node = node->rb_left;
-		} else if (cur->index > index) {
+		} else if (cur->logical > start) {
 			node = node->rb_right;
 		} else if (cur->seq < min_seq) {
 			node = node->rb_left;

@@ -1232,9 +1231,10 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info,
 		return NULL;
 
 	/*
-	 * the very last operation that's logged for a root is the replacement
-	 * operation (if it is replaced at all). this has the index of the *new*
-	 * root, making it the very first operation that's logged for this root.
+	 * the very last operation that's logged for a root is the
+	 * replacement operation (if it is replaced at all). this has
+	 * the logical address of the *new* root, making it the very
+	 * first operation that's logged for this root.
 	 */
 	while (1) {
 		tm = tree_mod_log_search_oldest(fs_info, root_logical,

@@ -1338,7 +1338,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 		if (!next)
 			break;
 		tm = container_of(next, struct tree_mod_elem, node);
-		if (tm->index != first_tm->index)
+		if (tm->logical != first_tm->logical)
 			break;
 	}
 	tree_mod_log_read_unlock(fs_info);

index b236417..0f59c6c 100644
@@ -7346,9 +7346,11 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	u64 file_offset = dip->logical_offset;
 	u64 submit_len = 0;
 	u64 map_length;
-	int nr_pages = 0;
+	u32 blocksize = root->sectorsize;
 	int ret = 0;
 	int async_submit = 0;
+	int nr_sectors;
+	int i;
 
 	map_length = orig_bio->bi_iter.bi_size;
 	ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,

@@ -7378,9 +7380,12 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	atomic_inc(&dip->pending_bios);
 
 	while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
-		if (unlikely(map_length < submit_len + bvec->bv_len ||
-		    bio_add_page(bio, bvec->bv_page, bvec->bv_len,
-				 bvec->bv_offset) < bvec->bv_len)) {
+		nr_sectors = bvec->bv_len >> inode->i_sb->s_blocksize_bits;
+		i = 0;
+next_block:
+		if (unlikely(map_length < submit_len + blocksize ||
+		    bio_add_page(bio, bvec->bv_page, blocksize,
+			    bvec->bv_offset + (i * blocksize)) < blocksize)) {
 			/*
 			 * inc the count before we submit the bio so
 			 * we know the end IO handler won't happen before

@@ -7401,7 +7406,6 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 			file_offset += submit_len;
 
 			submit_len = 0;
-			nr_pages = 0;
 
 			bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev,
 						  start_sector, GFP_NOFS);

@@ -7418,9 +7422,14 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 				bio_put(bio);
 				goto out_err;
 			}
+
+			goto next_block;
 		} else {
-			submit_len += bvec->bv_len;
-			nr_pages++;
+			submit_len += blocksize;
+			if (--nr_sectors) {
+				i++;
+				goto next_block;
+			}
 			bvec++;
 		}
 	}