Merge branch 'topic/error' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator into regulator-fixed

1 files changed, 252 insertions, 154 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3cd57825c75f..66a755150056 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -20,6 +20,7 @@
 #include "locking.h"
 #include "rcu-string.h"
 #include "backref.h"
+#include "transaction.h"
 
 static struct kmem_cache *extent_state_cache;
 static struct kmem_cache *extent_buffer_cache;
@@ -74,8 +75,7 @@ void btrfs_leak_debug_check(void)
 
 	while (!list_empty(&buffers)) {
 		eb = list_entry(buffers.next, struct extent_buffer, leak_list);
-		printk(KERN_ERR "BTRFS: buffer leak start %llu len %lu "
-		       "refs %d\n",
+		pr_err("BTRFS: buffer leak start %llu len %lu refs %d\n",
 		       eb->start, eb->len, atomic_read(&eb->refs));
 		list_del(&eb->leak_list);
 		kmem_cache_free(extent_buffer_cache, eb);
@@ -163,13 +163,13 @@ int __init extent_io_init(void)
 {
 	extent_state_cache = kmem_cache_create("btrfs_extent_state",
 			sizeof(struct extent_state), 0,
-			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+			SLAB_MEM_SPREAD, NULL);
 	if (!extent_state_cache)
 		return -ENOMEM;
 
 	extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
 			sizeof(struct extent_buffer), 0,
-			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+			SLAB_MEM_SPREAD, NULL);
 	if (!extent_buffer_cache)
 		goto free_state_cache;
 
@@ -460,8 +460,7 @@ static int insert_state(struct extent_io_tree *tree,
 	if (node) {
 		struct extent_state *found;
 		found = rb_entry(node, struct extent_state, rb_node);
-		printk(KERN_ERR "BTRFS: found node %llu %llu on insert of "
-		       "%llu %llu\n",
+		pr_err("BTRFS: found node %llu %llu on insert of %llu %llu\n",
 		       found->start, found->end, start, end);
 		return -EEXIST;
 	}
@@ -572,9 +571,8 @@ alloc_extent_state_atomic(struct extent_state *prealloc)
 
 static void extent_io_tree_panic(struct extent_io_tree *tree, int err)
 {
-	btrfs_panic(tree_fs_info(tree), err, "Locking error: "
-		    "Extent tree was modified by another "
-		    "thread while locked.");
+	btrfs_panic(tree_fs_info(tree), err,
+		    "Locking error: Extent tree was modified by another thread while locked.");
 }
 
 /*
@@ -1729,7 +1727,7 @@ out_failed:
 }
 
 void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
-				 struct page *locked_page,
+				 u64 delalloc_end, struct page *locked_page,
 				 unsigned clear_bits,
 				 unsigned long page_ops)
 {
@@ -2025,9 +2023,16 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	bio->bi_iter.bi_size = 0;
 	map_length = length;
 
+	/*
+	 * Avoid races with device replace and make sure our bbio has devices
+	 * associated to its stripes that don't go away while we are doing the
+	 * read repair operation.
+	 */
+	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_block(fs_info, WRITE, logical,
 			      &map_length, &bbio, mirror_num);
 	if (ret) {
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		return -EIO;
 	}
@@ -2037,14 +2042,17 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	dev = bbio->stripes[mirror_num-1].dev;
 	btrfs_put_bbio(bbio);
 	if (!dev || !dev->bdev || !dev->writeable) {
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		return -EIO;
 	}
 	bio->bi_bdev = dev->bdev;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_SYNC);
 	bio_add_page(bio, page, length, pg_offset);
 
-	if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
+	if (btrfsic_submit_bio_wait(bio)) {
 		/* try to remap that extent elsewhere? */
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
 		return -EIO;
@@ -2054,6 +2062,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
 				  btrfs_ino(inode), start,
 				  rcu_str_deref(dev->name), sector);
+	btrfs_bio_counter_dec(fs_info);
 	bio_put(bio);
 	return 0;
 }
@@ -2111,8 +2120,9 @@ int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 
 	if (failrec->in_validation) {
 		/* there was no real error, just free the record */
-		pr_debug("clean_io_failure: freeing dummy error at %llu\n",
-			 failrec->start);
+		btrfs_debug(fs_info,
+			"clean_io_failure: freeing dummy error at %llu",
+			failrec->start);
 		goto out;
 	}
 	if (fs_info->sb->s_flags & MS_RDONLY)
@@ -2178,6 +2188,7 @@ void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end)
 int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 		struct io_failure_record **failrec_ret)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct io_failure_record *failrec;
 	struct extent_map *em;
 	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
@@ -2225,8 +2236,9 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 						 em->compress_type);
 		}
 
-		pr_debug("Get IO Failure Record: (new) logical=%llu, start=%llu, len=%llu\n",
-			 logical, start, failrec->len);
+		btrfs_debug(fs_info,
+			"Get IO Failure Record: (new) logical=%llu, start=%llu, len=%llu",
+			logical, start, failrec->len);
 
 		failrec->logical = logical;
 		free_extent_map(em);
@@ -2244,9 +2256,10 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 			return ret;
 		}
 	} else {
-		pr_debug("Get IO Failure Record: (found) logical=%llu, start=%llu, len=%llu, validation=%d\n",
-			 failrec->logical, failrec->start, failrec->len,
-			 failrec->in_validation);
+		btrfs_debug(fs_info,
+			"Get IO Failure Record: (found) logical=%llu, start=%llu, len=%llu, validation=%d",
+			failrec->logical, failrec->start, failrec->len,
+			failrec->in_validation);
 		/*
 		 * when data can be on disk more than twice, add to failrec here
 		 * (e.g. with a list for failed_mirror) to make
@@ -2262,18 +2275,19 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 			   struct io_failure_record *failrec, int failed_mirror)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	int num_copies;
 
-	num_copies = btrfs_num_copies(BTRFS_I(inode)->root->fs_info,
-				      failrec->logical, failrec->len);
+	num_copies = btrfs_num_copies(fs_info, failrec->logical, failrec->len);
 	if (num_copies == 1) {
 		/*
 		 * we only have a single copy of the data, so don't bother with
 		 * all the retry and error correction code that follows. no
 		 * matter what the error is, it is very likely to persist.
 		 */
-		pr_debug("Check Repairable: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d\n",
-			 num_copies, failrec->this_mirror, failed_mirror);
+		btrfs_debug(fs_info,
+			"Check Repairable: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d",
+			num_copies, failrec->this_mirror, failed_mirror);
 		return 0;
 	}
 
@@ -2312,8 +2326,9 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 	}
 
 	if (failrec->this_mirror > num_copies) {
-		pr_debug("Check Repairable: (fail) num_copies=%d, next_mirror %d, failed_mirror %d\n",
-			 num_copies, failrec->this_mirror, failed_mirror);
+		btrfs_debug(fs_info,
+			"Check Repairable: (fail) num_copies=%d, next_mirror %d, failed_mirror %d",
+			num_copies, failrec->this_mirror, failed_mirror);
 		return 0;
 	}
 
@@ -2376,7 +2391,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	int read_mode;
 	int ret;
 
-	BUG_ON(failed_bio->bi_rw & REQ_WRITE);
+	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
 
 	ret = btrfs_get_io_failure_record(inode, start, end, &failrec);
 	if (ret)
@@ -2402,12 +2417,13 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 		free_io_failure(inode, failrec);
 		return -EIO;
 	}
+	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
 
-	pr_debug("Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d\n",
-		 read_mode, failrec->this_mirror, failrec->in_validation);
+	btrfs_debug(btrfs_sb(inode->i_sb),
+		"Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d",
+		read_mode, failrec->this_mirror, failrec->in_validation);
 
-	ret = tree->ops->submit_bio_hook(inode, read_mode, bio,
-					 failrec->this_mirror,
+	ret = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror,
 					 failrec->bio_flags, 0);
 	if (ret) {
 		free_io_failure(inode, failrec);
@@ -2473,8 +2489,7 @@ static void end_bio_extent_writepage(struct bio *bio)
 					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",
+				   "incomplete page write in btrfs with offset %u and length %u",
 					bvec->bv_offset, bvec->bv_len);
 		}
 
@@ -2530,10 +2545,12 @@ static void end_bio_extent_readpage(struct bio *bio)
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 		struct inode *inode = page->mapping->host;
+		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 
-		pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
-			 "mirror=%u\n", (u64)bio->bi_iter.bi_sector,
-			 bio->bi_error, io_bio->mirror_num);
+		btrfs_debug(fs_info,
+			"end_bio_extent_readpage: bi_sector=%llu, err=%d, mirror=%u",
+			(u64)bio->bi_iter.bi_sector, bio->bi_error,
+			io_bio->mirror_num);
 		tree = &BTRFS_I(inode)->io_tree;
 
 		/* We always issue full-page reads, but if some block
@@ -2543,13 +2560,12 @@ static void end_bio_extent_readpage(struct bio *bio)
 		 * if they don't add up to a full page.  */
 		if (bvec->bv_offset || bvec->bv_len != PAGE_SIZE) {
 			if (bvec->bv_offset + bvec->bv_len != PAGE_SIZE)
-				btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
-				   "partial page read in btrfs with offset %u and length %u",
+				btrfs_err(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",
+				btrfs_info(fs_info,
+					"incomplete page read in btrfs with offset %u and length %u",
 					bvec->bv_offset, bvec->bv_len);
 		}
 
@@ -2686,12 +2702,6 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask)
 		btrfs_bio->csum = NULL;
 		btrfs_bio->csum_allocated = NULL;
 		btrfs_bio->end_io = NULL;
-
-#ifdef CONFIG_BLK_CGROUP
-		/* FIXME, put this into bio_clone_bioset */
-		if (bio->bi_css)
-			bio_associate_blkcg(new, bio->bi_css);
-#endif
 	}
 	return new;
 }
@@ -2713,8 +2723,8 @@ struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 }
 
 
-static int __must_check submit_one_bio(int rw, struct bio *bio,
-				       int mirror_num, unsigned long bio_flags)
+static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
+				       unsigned long bio_flags)
 {
 	int ret = 0;
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
@@ -2725,33 +2735,31 @@ static int __must_check submit_one_bio(int rw, struct bio *bio,
 	start = page_offset(page) + bvec->bv_offset;
 
 	bio->bi_private = NULL;
-
 	bio_get(bio);
 
 	if (tree->ops && tree->ops->submit_bio_hook)
-		ret = tree->ops->submit_bio_hook(page->mapping->host, rw, bio,
+		ret = tree->ops->submit_bio_hook(page->mapping->host, bio,
 					   mirror_num, bio_flags, start);
 	else
-		btrfsic_submit_bio(rw, bio);
+		btrfsic_submit_bio(bio);
 
 	bio_put(bio);
 	return ret;
 }
 
-static int merge_bio(int rw, struct extent_io_tree *tree, struct page *page,
+static int merge_bio(struct extent_io_tree *tree, struct page *page,
 		     unsigned long offset, size_t size, struct bio *bio,
 		     unsigned long bio_flags)
 {
 	int ret = 0;
 	if (tree->ops && tree->ops->merge_bio_hook)
-		ret = tree->ops->merge_bio_hook(rw, page, offset, size, bio,
+		ret = tree->ops->merge_bio_hook(page, offset, size, bio,
 						bio_flags);
-	BUG_ON(ret < 0);
 	return ret;
 
 }
 
-static int submit_extent_page(int rw, struct extent_io_tree *tree,
+static int submit_extent_page(int op, int op_flags, struct extent_io_tree *tree,
 			      struct writeback_control *wbc,
 			      struct page *page, sector_t sector,
 			      size_t size, unsigned long offset,
@@ -2779,10 +2787,9 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 
 		if (prev_bio_flags != bio_flags || !contig ||
 		    force_bio_submit ||
-		    merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) ||
+		    merge_bio(tree, page, offset, page_size, bio, bio_flags) ||
 		    bio_add_page(bio, page, page_size, offset) < page_size) {
-			ret = submit_one_bio(rw, bio, mirror_num,
-					     prev_bio_flags);
+			ret = submit_one_bio(bio, mirror_num, prev_bio_flags);
 			if (ret < 0) {
 				*bio_ret = NULL;
 				return ret;
@@ -2803,6 +2810,7 @@ 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;
+	bio_set_op_attrs(bio, op, op_flags);
 	if (wbc) {
 		wbc_init_bio(wbc, bio);
 		wbc_account_io(wbc, page, page_size);
@@ -2811,7 +2819,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 	if (bio_ret)
 		*bio_ret = bio;
 	else
-		ret = submit_one_bio(rw, bio, mirror_num, bio_flags);
+		ret = submit_one_bio(bio, mirror_num, bio_flags);
 
 	return ret;
 }
@@ -2869,13 +2877,14 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
  * into the tree that are removed when the IO is done (by the end_io
  * handlers)
  * XXX JDM: This needs looking at to ensure proper page locking
+ * return 0 on success, otherwise return error
  */
 static int __do_readpage(struct extent_io_tree *tree,
 			 struct page *page,
 			 get_extent_t *get_extent,
 			 struct extent_map **em_cached,
 			 struct bio **bio, int mirror_num,
-			 unsigned long *bio_flags, int rw,
+			 unsigned long *bio_flags, int read_flags,
 			 u64 *prev_em_start)
 {
 	struct inode *inode = page->mapping->host;
@@ -2890,7 +2899,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 	sector_t sector;
 	struct extent_map *em;
 	struct block_device *bdev;
-	int ret;
+	int ret = 0;
 	int nr = 0;
 	size_t pg_offset = 0;
 	size_t iosize;
@@ -3058,8 +3067,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 		}
 
 		pnr -= page->index;
-		ret = submit_extent_page(rw, tree, NULL, page,
-					 sector, disk_io_size, pg_offset,
+		ret = submit_extent_page(REQ_OP_READ, read_flags, tree, NULL,
+					 page, sector, disk_io_size, pg_offset,
 					 bdev, bio, pnr,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
@@ -3071,6 +3080,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 		} else {
 			SetPageError(page);
 			unlock_extent(tree, cur, cur + iosize - 1);
+			goto out;
 		}
 		cur = cur + iosize;
 		pg_offset += iosize;
@@ -3081,7 +3091,7 @@ out:
 			SetPageUptodate(page);
 		unlock_page(page);
 	}
-	return 0;
+	return ret;
 }
 
 static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
@@ -3090,7 +3100,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 					     get_extent_t *get_extent,
 					     struct extent_map **em_cached,
 					     struct bio **bio, int mirror_num,
-					     unsigned long *bio_flags, int rw,
+					     unsigned long *bio_flags,
 					     u64 *prev_em_start)
 {
 	struct inode *inode;
@@ -3111,7 +3121,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 
 	for (index = 0; index < nr_pages; index++) {
 		__do_readpage(tree, pages[index], get_extent, em_cached, bio,
-			      mirror_num, bio_flags, rw, prev_em_start);
+			      mirror_num, bio_flags, 0, prev_em_start);
 		put_page(pages[index]);
 	}
 }
@@ -3121,7 +3131,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
 			       int nr_pages, get_extent_t *get_extent,
 			       struct extent_map **em_cached,
 			       struct bio **bio, int mirror_num,
-			       unsigned long *bio_flags, int rw,
+			       unsigned long *bio_flags,
 			       u64 *prev_em_start)
 {
 	u64 start = 0;
@@ -3143,7 +3153,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
 						  index - first_index, start,
 						  end, get_extent, em_cached,
 						  bio, mirror_num, bio_flags,
-						  rw, prev_em_start);
+						  prev_em_start);
 			start = page_start;
 			end = start + PAGE_SIZE - 1;
 			first_index = index;
@@ -3154,7 +3164,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
 		__do_contiguous_readpages(tree, &pages[first_index],
 					  index - first_index, start,
 					  end, get_extent, em_cached, bio,
-					  mirror_num, bio_flags, rw,
+					  mirror_num, bio_flags,
 					  prev_em_start);
 }
 
@@ -3162,7 +3172,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 				   struct page *page,
 				   get_extent_t *get_extent,
 				   struct bio **bio, int mirror_num,
-				   unsigned long *bio_flags, int rw)
+				   unsigned long *bio_flags, int read_flags)
 {
 	struct inode *inode = page->mapping->host;
 	struct btrfs_ordered_extent *ordered;
@@ -3182,7 +3192,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 	}
 
 	ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num,
-			    bio_flags, rw, NULL);
+			    bio_flags, read_flags, NULL);
 	return ret;
 }
 
@@ -3194,9 +3204,9 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	int ret;
 
 	ret = __extent_read_full_page(tree, page, get_extent, &bio, mirror_num,
-				      &bio_flags, READ);
+				      &bio_flags, 0);
 	if (bio)
-		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
+		ret = submit_one_bio(bio, mirror_num, bio_flags);
 	return ret;
 }
 
@@ -3430,8 +3440,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 			       page->index, cur, end);
 		}
 
-		ret = submit_extent_page(write_flags, tree, wbc, page,
-					 sector, iosize, pg_offset,
+		ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc,
+					 page, sector, iosize, pg_offset,
 					 bdev, &epd->bio, max_nr,
 					 end_bio_extent_writepage,
 					 0, 0, 0, false);
@@ -3470,13 +3480,11 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	size_t pg_offset = 0;
 	loff_t i_size = i_size_read(inode);
 	unsigned long end_index = i_size >> PAGE_SHIFT;
-	int write_flags;
+	int write_flags = 0;
 	unsigned long nr_written = 0;
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		write_flags = WRITE_SYNC;
-	else
-		write_flags = WRITE;
 
 	trace___extent_writepage(page, inode, wbc);
 
@@ -3621,7 +3629,6 @@ static void end_extent_buffer_writeback(struct extent_buffer *eb)
 static void set_btree_ioerr(struct page *page)
 {
 	struct extent_buffer *eb = (struct extent_buffer *)page->private;
-	struct btrfs_inode *btree_ino = BTRFS_I(eb->fs_info->btree_inode);
 
 	SetPageError(page);
 	if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))
@@ -3667,13 +3674,13 @@ static void set_btree_ioerr(struct page *page)
 	 */
 	switch (eb->log_index) {
 	case -1:
-		set_bit(BTRFS_INODE_BTREE_ERR, &btree_ino->runtime_flags);
+		set_bit(BTRFS_FS_BTREE_ERR, &eb->fs_info->flags);
 		break;
 	case 0:
-		set_bit(BTRFS_INODE_BTREE_LOG1_ERR, &btree_ino->runtime_flags);
+		set_bit(BTRFS_FS_LOG1_ERR, &eb->fs_info->flags);
 		break;
 	case 1:
-		set_bit(BTRFS_INODE_BTREE_LOG2_ERR, &btree_ino->runtime_flags);
+		set_bit(BTRFS_FS_LOG2_ERR, &eb->fs_info->flags);
 		break;
 	default:
 		BUG(); /* unexpected, logic error */
@@ -3718,9 +3725,11 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	struct block_device *bdev = fs_info->fs_devices->latest_bdev;
 	struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
 	u64 offset = eb->start;
+	u32 nritems;
 	unsigned long i, num_pages;
 	unsigned long bio_flags = 0;
-	int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
+	unsigned long start, end;
+	int write_flags = (epd->sync_io ? WRITE_SYNC : 0) | REQ_META;
 	int ret = 0;
 
 	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
@@ -3729,14 +3738,32 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	if (btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID)
 		bio_flags = EXTENT_BIO_TREE_LOG;
 
+	/* set btree blocks beyond nritems with 0 to avoid stale content. */
+	nritems = btrfs_header_nritems(eb);
+	if (btrfs_header_level(eb) > 0) {
+		end = btrfs_node_key_ptr_offset(nritems);
+
+		memset_extent_buffer(eb, 0, end, eb->len - end);
+	} else {
+		/*
+		 * leaf:
+		 * header 0 1 2 .. N ... data_N .. data_2 data_1 data_0
+		 */
+		start = btrfs_item_nr_offset(nritems);
+		end = btrfs_leaf_data(eb) +
+		      leaf_data_end(fs_info->tree_root, eb);
+		memset_extent_buffer(eb, 0, start, end - start);
+	}
+
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = eb->pages[i];
 
 		clear_page_dirty_for_io(p);
 		set_page_writeback(p);
-		ret = submit_extent_page(rw, tree, wbc, p, offset >> 9,
-					 PAGE_SIZE, 0, bdev, &epd->bio,
-					 -1, end_bio_extent_buffer_writepage,
+		ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc,
+					 p, offset >> 9, PAGE_SIZE, 0, bdev,
+					 &epd->bio, -1,
+					 end_bio_extent_buffer_writepage,
 					 0, epd->bio_flags, bio_flags, false);
 		epd->bio_flags = bio_flags;
 		if (ret) {
@@ -4046,13 +4073,12 @@ retry:
 static void flush_epd_write_bio(struct extent_page_data *epd)
 {
 	if (epd->bio) {
-		int rw = WRITE;
 		int ret;
 
-		if (epd->sync_io)
-			rw = WRITE_SYNC;
+		bio_set_op_attrs(epd->bio, REQ_OP_WRITE,
+				 epd->sync_io ? WRITE_SYNC : 0);
 
-		ret = submit_one_bio(rw, epd->bio, 0, epd->bio_flags);
+		ret = submit_one_bio(epd->bio, 0, epd->bio_flags);
 		BUG_ON(ret < 0); /* -ENOMEM */
 		epd->bio = NULL;
 	}
@@ -4170,7 +4196,8 @@ int extent_readpages(struct extent_io_tree *tree,
 		prefetchw(&page->flags);
 		list_del(&page->lru);
 		if (add_to_page_cache_lru(page, mapping,
-					page->index, GFP_NOFS)) {
+					page->index,
+					readahead_gfp_mask(mapping))) {
 			put_page(page);
 			continue;
 		}
@@ -4179,19 +4206,19 @@ int extent_readpages(struct extent_io_tree *tree,
 		if (nr < ARRAY_SIZE(pagepool))
 			continue;
 		__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
-				   &bio, 0, &bio_flags, READ, &prev_em_start);
+				   &bio, 0, &bio_flags, &prev_em_start);
 		nr = 0;
 	}
 	if (nr)
 		__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
-				   &bio, 0, &bio_flags, READ, &prev_em_start);
+				   &bio, 0, &bio_flags, &prev_em_start);
 
 	if (em_cached)
 		free_extent_map(em_cached);
 
 	BUG_ON(!list_empty(pages));
 	if (bio)
-		return submit_one_bio(READ, bio, 0, bio_flags);
+		return submit_one_bio(bio, 0, bio_flags);
 	return 0;
 }
 
@@ -4483,21 +4510,36 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			flags |= (FIEMAP_EXTENT_DELALLOC |
 				  FIEMAP_EXTENT_UNKNOWN);
 		} else if (fieinfo->fi_extents_max) {
+			struct btrfs_trans_handle *trans;
+
 			u64 bytenr = em->block_start -
 				(em->start - em->orig_start);
 
 			disko = em->block_start + offset_in_extent;
 
 			/*
+			 * We need a trans handle to get delayed refs
+			 */
+			trans = btrfs_join_transaction(root);
+			/*
+			 * It's OK if we can't start a trans we can still check
+			 * from commit_root
+			 */
+			if (IS_ERR(trans))
+				trans = NULL;
+
+			/*
 			 * As btrfs supports shared space, this information
 			 * can be exported to userspace tools via
 			 * flag FIEMAP_EXTENT_SHARED.  If fi_extents_max == 0
 			 * then we're just getting a count and we can skip the
 			 * lookup stuff.
 			 */
-			ret = btrfs_check_shared(NULL, root->fs_info,
+			ret = btrfs_check_shared(trans, root->fs_info,
 						 root->objectid,
 						 btrfs_ino(inode), bytenr);
+			if (trans)
+				btrfs_end_transaction(trans, root);
 			if (ret < 0)
 				goto out_free;
 			if (ret)
@@ -4718,16 +4760,16 @@ err:
 }
 
 struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
-						u64 start)
+						u64 start, u32 nodesize)
 {
 	unsigned long len;
 
 	if (!fs_info) {
 		/*
 		 * Called only from tests that don't always have a fs_info
-		 * available, but we know that nodesize is 4096
+		 * available
 		 */
-		len = 4096;
+		len = nodesize;
 	} else {
 		len = fs_info->tree_root->nodesize;
 	}
@@ -4823,7 +4865,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
-					       u64 start)
+					u64 start, u32 nodesize)
 {
 	struct extent_buffer *eb, *exists = NULL;
 	int ret;
@@ -4831,7 +4873,7 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
 	eb = find_extent_buffer(fs_info, start);
 	if (eb)
 		return eb;
-	eb = alloc_dummy_extent_buffer(fs_info, start);
+	eb = alloc_dummy_extent_buffer(fs_info, start, nodesize);
 	if (!eb)
 		return NULL;
 	eb->fs_info = fs_info;
@@ -4882,18 +4924,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	int uptodate = 1;
 	int ret;
 
+	if (!IS_ALIGNED(start, fs_info->tree_root->sectorsize)) {
+		btrfs_err(fs_info, "bad tree block start %llu", start);
+		return ERR_PTR(-EINVAL);
+	}
+
 	eb = find_extent_buffer(fs_info, start);
 	if (eb)
 		return eb;
 
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; i < num_pages; i++, index++) {
 		p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
-		if (!p)
+		if (!p) {
+			exists = ERR_PTR(-ENOMEM);
 			goto free_eb;
+		}
 
 		spin_lock(&mapping->private_lock);
 		if (PagePrivate(p)) {
@@ -4938,8 +4987,10 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 		set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 again:
 	ret = radix_tree_preload(GFP_NOFS);
-	if (ret)
+	if (ret) {
+		exists = ERR_PTR(ret);
 		goto free_eb;
+	}
 
 	spin_lock(&fs_info->buffer_lock);
 	ret = radix_tree_insert(&fs_info->buffer_radix,
@@ -5160,11 +5211,10 @@ int extent_buffer_uptodate(struct extent_buffer *eb)
 }
 
 int read_extent_buffer_pages(struct extent_io_tree *tree,
-			     struct extent_buffer *eb, u64 start, int wait,
+			     struct extent_buffer *eb, int wait,
 			     get_extent_t *get_extent, int mirror_num)
 {
 	unsigned long i;
-	unsigned long start_i;
 	struct page *page;
 	int err;
 	int ret = 0;
@@ -5178,16 +5228,8 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
 		return 0;
 
-	if (start) {
-		WARN_ON(start < eb->start);
-		start_i = (start >> PAGE_SHIFT) -
-			(eb->start >> PAGE_SHIFT);
-	} else {
-		start_i = 0;
-	}
-
 	num_pages = num_extent_pages(eb->start, eb->len);
-	for (i = start_i; i < num_pages; i++) {
+	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		if (wait == WAIT_NONE) {
 			if (!trylock_page(page))
@@ -5196,38 +5238,62 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 			lock_page(page);
 		}
 		locked_pages++;
+	}
+	/*
+	 * We need to firstly lock all pages to make sure that
+	 * the uptodate bit of our pages won't be affected by
+	 * clear_extent_buffer_uptodate().
+	 */
+	for (i = 0; i < num_pages; i++) {
+		page = eb->pages[i];
 		if (!PageUptodate(page)) {
 			num_reads++;
 			all_uptodate = 0;
 		}
 	}
+
 	if (all_uptodate) {
-		if (start_i == 0)
-			set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+		set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 		goto unlock_exit;
 	}
 
 	clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = 0;
 	atomic_set(&eb->io_pages, num_reads);
-	for (i = start_i; i < num_pages; i++) {
+	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
+
 		if (!PageUptodate(page)) {
+			if (ret) {
+				atomic_dec(&eb->io_pages);
+				unlock_page(page);
+				continue;
+			}
+
 			ClearPageError(page);
 			err = __extent_read_full_page(tree, page,
 						      get_extent, &bio,
 						      mirror_num, &bio_flags,
-						      READ | REQ_META);
-			if (err)
+						      REQ_META);
+			if (err) {
 				ret = err;
+				/*
+				 * We use &bio in above __extent_read_full_page,
+				 * so we ensure that if it returns error, the
+				 * current page fails to add itself to bio and
+				 * it's been unlocked.
+				 *
+				 * We must dec io_pages by ourselves.
+				 */
+				atomic_dec(&eb->io_pages);
+			}
 		} else {
 			unlock_page(page);
 		}
 	}
 
 	if (bio) {
-		err = submit_one_bio(READ | REQ_META, bio, mirror_num,
-				     bio_flags);
+		err = submit_one_bio(bio, mirror_num, bio_flags);
 		if (err)
 			return err;
 	}
@@ -5235,7 +5301,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	if (ret || wait != WAIT_COMPLETE)
 		return ret;
 
-	for (i = start_i; i < num_pages; i++) {
+	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		wait_on_page_locked(page);
 		if (!PageUptodate(page))
@@ -5245,12 +5311,10 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	return ret;
 
 unlock_exit:
-	i = start_i;
 	while (locked_pages > 0) {
-		page = eb->pages[i];
-		i++;
-		unlock_page(page);
 		locked_pages--;
+		page = eb->pages[locked_pages];
+		unlock_page(page);
 	}
 	return ret;
 }
@@ -5323,6 +5387,11 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
 	return ret;
 }
 
+/*
+ * return 0 if the item is found within a page.
+ * return 1 if the item spans two pages.
+ * return -EINVAL otherwise.
+ */
 int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 			       unsigned long min_len, char **map,
 			       unsigned long *map_start,
@@ -5337,7 +5406,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 		PAGE_SHIFT;
 
 	if (i != end_i)
-		return -EINVAL;
+		return 1;
 
 	if (i == 0) {
 		offset = start_offset;
@@ -5348,8 +5417,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 	}
 
 	if (start + min_len > eb->len) {
-		WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, "
-		       "wanted %lu %lu\n",
+		WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
 		       eb->start, eb->len, start, min_len);
 		return -EINVAL;
 	}
@@ -5490,17 +5558,45 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
 	}
 }
 
-/*
- * The extent buffer bitmap operations are done with byte granularity because
- * bitmap items are not guaranteed to be aligned to a word and therefore a
- * single word in a bitmap may straddle two pages in the extent buffer.
- */
-#define BIT_BYTE(nr) ((nr) / BITS_PER_BYTE)
-#define BYTE_MASK ((1 << BITS_PER_BYTE) - 1)
-#define BITMAP_FIRST_BYTE_MASK(start) \
-	((BYTE_MASK << ((start) & (BITS_PER_BYTE - 1))) & BYTE_MASK)
-#define BITMAP_LAST_BYTE_MASK(nbits) \
-	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
+void le_bitmap_set(u8 *map, unsigned int start, int len)
+{
+	u8 *p = map + BIT_BYTE(start);
+	const unsigned int size = start + len;
+	int bits_to_set = BITS_PER_BYTE - (start % BITS_PER_BYTE);
+	u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(start);
+
+	while (len - bits_to_set >= 0) {
+		*p |= mask_to_set;
+		len -= bits_to_set;
+		bits_to_set = BITS_PER_BYTE;
+		mask_to_set = ~(u8)0;
+		p++;
+	}
+	if (len) {
+		mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
+		*p |= mask_to_set;
+	}
+}
+
+void le_bitmap_clear(u8 *map, unsigned int start, int len)
+{
+	u8 *p = map + BIT_BYTE(start);
+	const unsigned int size = start + len;
+	int bits_to_clear = BITS_PER_BYTE - (start % BITS_PER_BYTE);
+	u8 mask_to_clear = BITMAP_FIRST_BYTE_MASK(start);
+
+	while (len - bits_to_clear >= 0) {
+		*p &= ~mask_to_clear;
+		len -= bits_to_clear;
+		bits_to_clear = BITS_PER_BYTE;
+		mask_to_clear = ~(u8)0;
+		p++;
+	}
+	if (len) {
+		mask_to_clear &= BITMAP_LAST_BYTE_MASK(size);
+		*p &= ~mask_to_clear;
+	}
+}
 
 /*
  * eb_bitmap_offset() - calculate the page and offset of the byte containing the
@@ -5544,7 +5640,7 @@ static inline void eb_bitmap_offset(struct extent_buffer *eb,
 int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
 			   unsigned long nr)
 {
-	char *kaddr;
+	u8 *kaddr;
 	struct page *page;
 	unsigned long i;
 	size_t offset;
@@ -5566,13 +5662,13 @@ int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
 void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
 			      unsigned long pos, unsigned long len)
 {
-	char *kaddr;
+	u8 *kaddr;
 	struct page *page;
 	unsigned long i;
 	size_t offset;
 	const unsigned int size = pos + len;
 	int bits_to_set = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
-	unsigned int mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
+	u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
 
 	eb_bitmap_offset(eb, start, pos, &i, &offset);
 	page = eb->pages[i];
@@ -5583,7 +5679,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
 		kaddr[offset] |= mask_to_set;
 		len -= bits_to_set;
 		bits_to_set = BITS_PER_BYTE;
-		mask_to_set = ~0U;
+		mask_to_set = ~(u8)0;
 		if (++offset >= PAGE_SIZE && len > 0) {
 			offset = 0;
 			page = eb->pages[++i];
@@ -5608,13 +5704,13 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
 void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
 				unsigned long pos, unsigned long len)
 {
-	char *kaddr;
+	u8 *kaddr;
 	struct page *page;
 	unsigned long i;
 	size_t offset;
 	const unsigned int size = pos + len;
 	int bits_to_clear = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
-	unsigned int mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
+	u8 mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
 
 	eb_bitmap_offset(eb, start, pos, &i, &offset);
 	page = eb->pages[i];
@@ -5625,7 +5721,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
 		kaddr[offset] &= ~mask_to_clear;
 		len -= bits_to_clear;
 		bits_to_clear = BITS_PER_BYTE;
-		mask_to_clear = ~0U;
+		mask_to_clear = ~(u8)0;
 		if (++offset >= PAGE_SIZE && len > 0) {
 			offset = 0;
 			page = eb->pages[++i];
@@ -5679,14 +5775,14 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 
 	if (src_offset + len > dst->len) {
 		btrfs_err(dst->fs_info,
-			"memmove bogus src_offset %lu move "
-		       "len %lu dst len %lu", src_offset, len, dst->len);
+			"memmove bogus src_offset %lu move len %lu dst len %lu",
+			 src_offset, len, dst->len);
 		BUG_ON(1);
 	}
 	if (dst_offset + len > dst->len) {
 		btrfs_err(dst->fs_info,
-			"memmove bogus dst_offset %lu move "
-		       "len %lu dst len %lu", dst_offset, len, dst->len);
+			"memmove bogus dst_offset %lu move len %lu dst len %lu",
+			 dst_offset, len, dst->len);
 		BUG_ON(1);
 	}
 
@@ -5726,13 +5822,15 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 	unsigned long src_i;
 
 	if (src_offset + len > dst->len) {
-		btrfs_err(dst->fs_info, "memmove bogus src_offset %lu move "
-		       "len %lu len %lu", src_offset, len, dst->len);
+		btrfs_err(dst->fs_info,
+			  "memmove bogus src_offset %lu move len %lu len %lu",
+			  src_offset, len, dst->len);
 		BUG_ON(1);
 	}
 	if (dst_offset + len > dst->len) {
-		btrfs_err(dst->fs_info, "memmove bogus dst_offset %lu move "
-		       "len %lu len %lu", dst_offset, len, dst->len);
+		btrfs_err(dst->fs_info,
+			  "memmove bogus dst_offset %lu move len %lu len %lu",
+			  dst_offset, len, dst->len);
 		BUG_ON(1);
 	}
 	if (dst_offset < src_offset) {