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

index fbe501d..fa28545 100644
@@ -1943,15 +1943,29 @@ 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);
 }
 
 /*
+ * helper function to unlock a page if all the extents in the tree
+ * for that page are unlocked
+ */
+static void check_page_locked(struct extent_io_tree *tree, struct page *page)
+{
+	u64 start = page_offset(page);
+	u64 end = start + PAGE_CACHE_SIZE - 1;
+
+	if (!test_range_bit(tree, start, end, EXTENT_LOCKED, 0, NULL)) {
+		unlock_page(page);
+	}
+}
+
  * When IO fails, either with EIO or csum verification fails, we
  * try other mirrors that might have a good copy of the data.  This
  * io_failure_record is used to record state as we go through all the

@@ -2173,6 +2187,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	struct bio *bio;
 	struct btrfs_io_bio *btrfs_failed_bio;
 	struct btrfs_io_bio *btrfs_bio;
+	int nr_sectors;
 	int num_copies;
 	int ret;
 	int read_mode;

@@ -2267,7 +2282,8 @@ 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) {
+	nr_sectors = btrfs_io_bio(failed_bio)->len >> inode->i_sb->s_blocksize_bits;
+	if (nr_sectors > 1) {
 		/*
 		 * 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,

@@ -2314,6 +2330,8 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	bio->bi_sector = failrec->logical >> 9;
 	bio->bi_bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
 	bio->bi_size = 0;
+	btrfs_io_bio(bio)->start_offset = start;
+	btrfs_io_bio(bio)->len = end - start + 1;
 
 	btrfs_failed_bio = btrfs_io_bio(failed_bio);
 	if (btrfs_failed_bio->csum) {

@@ -2414,18 +2432,6 @@ 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

@@ -2440,76 +2446,50 @@ endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len,
 static void end_bio_extent_readpage(struct bio *bio, int err)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1;
-	struct bio_vec *bvec = bio->bi_io_vec;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+	struct bio_vec *bvec = bio->bi_io_vec;
+	struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1;
+	struct address_space *mapping;
+	struct extent_state *cached = NULL;
 	struct extent_io_tree *tree;
-	u64 offset = 0;
+	struct btrfs_root *root;
+	struct inode *inode;
+	struct page *page;
 	u64 start;
-	u64 end;
+	u64 offset = 0;
 	u64 len;
-	u64 extent_start = 0;
-	u64 extent_len = 0;
+	int nr_sectors;
 	int mirror;
 	int ret;
 
-	if (err)
-		uptodate = 0;
+	mapping = bio->bi_io_vec->bv_page->mapping;
+	inode = mapping->host;
+	root = BTRFS_I(inode)->root;
+	tree = &BTRFS_I(inode)->io_tree;
 
-	do {
-		struct page *page = bvec->bv_page;
-		struct inode *inode = page->mapping->host;
-
-		pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
-			 "mirror=%lu\n", (u64)bio->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 = btrfs_io_bio(bio)->start_offset;
+	len = btrfs_io_bio(bio)->len;
+	mirror = io_bio->mirror_num;
 
-		start = page_offset(page);
-		end = start + bvec->bv_offset + bvec->bv_len - 1;
-		len = bvec->bv_len;
+	nr_sectors = len >> inode->i_sb->s_blocksize_bits;
+	BUG_ON(!nr_sectors);
 
-		if (++bvec <= bvec_end)
-			prefetchw(&bvec->bv_page->flags);
+	do {
+		BUG_ON(bvec > bvec_end);
+		page = bvec->bv_page;
 
-		mirror = io_bio->mirror_num;
-		if (likely(uptodate && tree->ops &&
-			   tree->ops->readpage_end_io_hook)) {
+		if (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

@@ -2520,63 +2500,38 @@ 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;
+				goto next_block;
 			}
 		}
-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;
-		}
-	} while (bvec <= bvec_end);
 
-	if (extent_len)
-		endio_readpage_release_extent(tree, extent_start, extent_len,
-					      uptodate);
+		unlock_extent(tree, start, start + root->sectorsize - 1);
+		check_page_locked(tree, page);
+next_block:
+		offset += root->sectorsize;
+		start += root->sectorsize;
+		if ((page_offset(page) + PAGE_CACHE_SIZE) == start)
+			++bvec;
+	} while (--nr_sectors);
+
 	if (io_bio->end_io)
 		io_bio->end_io(io_bio, err);
-	bio_put(bio);
 }
 
 /*

@@ -2700,6 +2655,18 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 		else
 			contig = bio_end_sector(bio) == sector;
 
+		if (contig) {
+			/*
+			 * Check whether we are contig if file offsets.
+			 * We should mostly be for readpage/readpages
+			 * We need to do this because we use btrfs_io_bio
+			 * start_offset and len to unlock in endio routines.
+			 */
+			if ((page_offset(page) + offset) !=
+					(btrfs_io_bio(bio)->start_offset +
+					 btrfs_io_bio(bio)->len))
+				contig = 0;
+		}
 		if (prev_bio_flags != bio_flags || !contig ||
 		    merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) ||
 		    bio_add_page(bio, page, page_size, offset) < page_size) {

@@ -2709,6 +2676,11 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 				return ret;
 			bio = NULL;
 		} else {
+			/*
+			 * update btrfs_io_bio len. So that we can unlock
+			 * correctly in end_io callback.
+			 */
+			btrfs_io_bio(bio)->len += page_size;
 			return 0;
 		}
 	}

@@ -2724,6 +2696,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 	bio_add_page(bio, page, page_size, offset);
 	bio->bi_end_io = end_io_func;
 	bio->bi_private = tree;
+	btrfs_io_bio(bio)->start_offset = page_offset(page) + offset;
+	btrfs_io_bio(bio)->len = page_size;
 
 	if (bio_ret)
 		*bio_ret = bio;

@@ -2914,7 +2888,7 @@ 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;

index 80754f9..fb2dbdc 100644
@@ -173,6 +173,9 @@ struct btrfs_io_bio {
 	u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
 	u8 *csum_allocated;
 	btrfs_io_bio_end_io_t *end_io;
+	/* Track file offset range operated on by the bio.*/
+	u64 start_offset;
+	u64 len;
 	struct bio bio;
 };
 

index fa28545..20d8bdc 100644
@@ -1293,6 +1293,20 @@ 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.

@@ -1399,6 +1413,7 @@ 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;
 }
 

@@ -1966,6 +1981,16 @@ static void check_page_locked(struct extent_io_tree *tree, struct page *page)
 	}
 }
 
+static void check_page_writeback(struct extent_io_tree *tree, struct page *page)
+{
+	u64 start = page_offset(page);
+	u64 end = start + PAGE_CACHE_SIZE - 1;
+
+	if (!test_range_bit(tree, start, end, EXTENT_WRITEBACK, 0, NULL))
+		end_page_writeback(page);
+}
+
+/*
  * When IO fails, either with EIO or csum verification fails, we
  * try other mirrors that might have a good copy of the data.  This
  * io_failure_record is used to record state as we go through all the

@@ -2359,27 +2384,69 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 }
 
 /* lots and lots of room for performance fixes in the end_bio funcs */
-
-int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
+void end_extents_write(struct inode *inode, int err, u64 start, u64 end)
 {
+	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 	int uptodate = (err == 0);
-	struct extent_io_tree *tree;
+	pgoff_t index, end_index;
+	u64 page_start, page_end;
+	struct page *page;
 	int ret;
 
-	tree = &BTRFS_I(page->mapping->host)->io_tree;
+	index = start >> PAGE_CACHE_SHIFT;
+	end_index = end >> PAGE_CACHE_SHIFT;
 
-	if (tree->ops && tree->ops->writepage_end_io_hook) {
-		ret = tree->ops->writepage_end_io_hook(page, start,
-					       end, NULL, uptodate);
-		if (ret)
-			uptodate = 0;
+	page_start = start;
+
+	while (index <= end_index) {
+		page = find_get_page(inode->i_mapping, index);
+		BUG_ON(!page);
+
+		page_end = min_t(u64, end, page_offset(page) + PAGE_CACHE_SIZE - 1);
+
+		if (tree->ops && tree->ops->writepage_end_io_hook) {
+			ret = tree->ops->writepage_end_io_hook(page,
+							page_start, page_end,
+							NULL, uptodate);
+			if (ret)
+				uptodate = 0;
+		}
+
+		page_start = page_end + 1;
+
+		++index;
+
+		if (!uptodate) {
+			ClearPageUptodate(page);
+			SetPageError(page);
+		}
+
+		page_cache_release(page);
 	}
+}
+
+static void clear_extent_and_page_writeback(struct address_space *mapping,
+					struct extent_io_tree *tree,
+					struct btrfs_io_bio *io_bio)
+{
+	struct page *page;
+	pgoff_t index;
+	u64 offset, len;
 
-	if (!uptodate) {
-		ClearPageUptodate(page);
-		SetPageError(page);
+	offset	= io_bio->start_offset;
+	len	= io_bio->len;
+
+	clear_extent_writeback(tree, offset, offset + len - 1, NULL,
+			GFP_ATOMIC);
+
+	index = offset >> PAGE_CACHE_SHIFT;
+	while (offset < io_bio->start_offset + len) {
+		page = find_get_page(mapping, index);
+		check_page_writeback(tree, page);
+		page_cache_release(page);
+		index++;
+		offset += page_offset(page) + PAGE_CACHE_SIZE - offset;
 	}
-	return 0;
 }
 
 /*

@@ -2393,41 +2460,14 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
  */
 static void end_bio_extent_writepage(struct bio *bio, int err)
 {
-	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-	u64 start;
-	u64 end;
-
-	do {
-		struct page *page = bvec->bv_page;
-
-		/* 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;
-
-		if (--bvec >= bio->bi_io_vec)
-			prefetchw(&bvec->bv_page->flags);
+	struct address_space *mapping =  bio->bi_io_vec->bv_page->mapping;
+	struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree;
+	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
 
-		if (end_extent_writepage(page, err, start, end))
-			continue;
+	end_extents_write(mapping->host, err, io_bio->start_offset,
+			io_bio->start_offset + io_bio->len - 1);
 
-		end_page_writeback(page);
-	} while (bvec >= bio->bi_io_vec);
+	clear_extent_and_page_writeback(mapping, tree, io_bio);
 
 	bio_put(bio);
 }

@@ -3091,6 +3131,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	u64 last_byte = i_size_read(inode);
 	u64 block_start;
 	u64 iosize;
+	u64 unlock_start = start;
 	sector_t sector;
 	struct extent_state *cached_state = NULL;
 	struct extent_map *em;

@@ -3173,6 +3214,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 			/* File system has been set read-only */
 			if (ret) {
 				SetPageError(page);
+				unlock_start = page_end + 1;
 				goto done;
 			}
 			/*

@@ -3208,10 +3250,14 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 			goto done_unlocked;
 		}
 	}
+
+	lock_extent(tree, start, page_end);
+
 	if (tree->ops && tree->ops->writepage_start_hook) {
 		ret = tree->ops->writepage_start_hook(page, start,
 						      page_end);
 		if (ret) {
+			unlock_extent(tree, start, page_end);
 			/* Fixup worker will requeue */
 			if (ret == -EBUSY)
 				wbc->pages_skipped++;

@@ -3232,9 +3278,11 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 
 	end = page_end;
 	if (last_byte <= start) {
+		unlock_extent(tree, start, page_end);
 		if (tree->ops && tree->ops->writepage_end_io_hook)
 			tree->ops->writepage_end_io_hook(page, start,
 							 page_end, NULL, 1);
+		unlock_start = page_end + 1;
 		goto done;
 	}
 

@@ -3242,9 +3290,11 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 
 	while (cur <= end) {
 		if (cur >= last_byte) {
+			unlock_extent(tree, unlock_start, page_end);
 			if (tree->ops && tree->ops->writepage_end_io_hook)
 				tree->ops->writepage_end_io_hook(page, cur,
 							 page_end, NULL, 1);
+			unlock_start = page_end + 1;
 			break;
 		}
 		em = epd->get_extent(inode, page, pg_offset, cur,

@@ -3272,6 +3322,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 		 */
 		if (compressed || block_start == EXTENT_MAP_HOLE ||
 		    block_start == EXTENT_MAP_INLINE) {
+			unlock_extent(tree, unlock_start, cur + iosize - 1);
 			/*
 			 * end_io notification does not happen here for
 			 * compressed extents

@@ -3291,6 +3342,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 
 			cur += iosize;
 			pg_offset += iosize;
+			unlock_start = cur;
 			continue;
 		}
 		/* leave this out until we have a page_mkwrite call */

@@ -3337,6 +3389,9 @@ done:
 		set_page_writeback(page);
 		end_page_writeback(page);
 	}
+	if (unlock_start <= page_end)
+		unlock_extent(tree, unlock_start, page_end);
+
 	unlock_page(page);
 
 done_unlocked:

index 58b27e5..42d0b74 100644
@@ -341,7 +341,7 @@ struct btrfs_fs_info;
 int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
 			u64 length, u64 logical, struct page *page,
 			int mirror_num);
-int end_extent_writepage(struct page *page, int err, u64 start, u64 end);
+void end_extents_write(struct inode *inode, int err, u64 start, u64 end);
 int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
 			 int mirror_num);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS

64 lines not on this page · raw message

index 006af2f..541e227 100644
@@ -1339,18 +1339,21 @@ 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);

@@ -1468,6 +1471,7 @@ 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);

@@ -1488,7 +1492,9 @@ 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 |

@@ -1503,7 +1509,9 @@ 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;

@@ -1536,8 +1544,8 @@ 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;

@@ -1574,9 +1582,9 @@ 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++;

@@ -1590,7 +1598,7 @@ 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,

@@ -1609,7 +1617,7 @@ 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 a88da72..603ae44 100644
@@ -1272,7 +1272,7 @@ 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 cbd3a7d..0d4ad91 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 dac6653..901ada2 100644
@@ -2138,14 +2138,16 @@ 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 32312e0..232d0a3 100644
@@ -5984,7 +5984,7 @@ 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);

@@ -6001,7 +6001,7 @@ 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);
 }
 

@@ -6887,7 +6887,7 @@ 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

86 lines not on this page · raw message

index 07629e9..1ec359b 100644
@@ -5936,7 +5936,7 @@ 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 3176cdc..5b79ac2 100644
@@ -695,7 +695,7 @@ 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 bda2157..b2c4e9d 100644
@@ -413,7 +413,7 @@ 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,

@@ -432,7 +432,7 @@ 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,

@@ -564,12 +564,13 @@ 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;

@@ -579,18 +580,26 @@ 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;
 	}

@@ -632,7 +641,7 @@ 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;
 	}
 

@@ -640,7 +649,7 @@ 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) {

@@ -649,7 +658,7 @@ 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);

@@ -657,20 +666,6 @@ 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;

@@ -4109,8 +4104,6 @@ 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 53059df..678a09b 100644
@@ -110,6 +110,9 @@ 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);

190 lines not on this page · raw message

index b2c4e9d..28a45f6 100644
@@ -466,17 +466,23 @@ 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;
 }
 

406 lines not on this page · raw message

index 28a45f6..3bb7072 100644
@@ -2599,12 +2599,6 @@ 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 9d84658..16deb87 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_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;
+
 		while (count--) {
-			disk_bytenr += bvec->bv_len;
-			offset += bvec->bv_len;
-			bio_index++;
-			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;

@@ -468,41 +479,49 @@ 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_size - total_bytes;
+		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_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_sector << 9) +
+					total_bytes;
+				index = 0;
+			}
 
-			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_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;