1 files changed, 77 insertions, 55 deletions
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 91419ef79b00..df731c0ebec7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -455,7 +455,7 @@ again:
 
 	/*
 	 * skip compression for a small file range(<=blocksize) that
-	 * isn't an inline extent, since it dosen't save disk space at all.
+	 * isn't an inline extent, since it doesn't save disk space at all.
 	 */
 	if (total_compressed <= blocksize &&
 	   (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
@@ -1823,7 +1823,7 @@ static void btrfs_clear_bit_hook(struct inode *inode,
  * extent_io.c merge_bio_hook, this must check the chunk tree to make sure
  * we don't create bios that span stripes or chunks
  */
-int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
+int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 			 size_t size, struct bio *bio,
 			 unsigned long bio_flags)
 {
@@ -1838,7 +1838,7 @@ int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
 
 	length = bio->bi_iter.bi_size;
 	map_length = length;
-	ret = btrfs_map_block(root->fs_info, rw, logical,
+	ret = btrfs_map_block(root->fs_info, bio_op(bio), logical,
 			      &map_length, NULL, 0);
 	/* Will always return 0 with map_multi == NULL */
 	BUG_ON(ret < 0);
@@ -1855,9 +1855,8 @@ int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static int __btrfs_submit_bio_start(struct inode *inode, int rw,
-				    struct bio *bio, int mirror_num,
-				    unsigned long bio_flags,
+static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
+				    int mirror_num, unsigned long bio_flags,
 				    u64 bio_offset)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -1876,14 +1875,14 @@ static int __btrfs_submit_bio_start(struct inode *inode, int rw,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static int __btrfs_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
+static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio,
 			  int mirror_num, unsigned long bio_flags,
 			  u64 bio_offset)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
-	ret = btrfs_map_bio(root, rw, bio, mirror_num, 1);
+	ret = btrfs_map_bio(root, bio, mirror_num, 1);
 	if (ret) {
 		bio->bi_error = ret;
 		bio_endio(bio);
@@ -1895,7 +1894,7 @@ static int __btrfs_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
  * extent_io.c submission hook. This does the right thing for csum calculation
  * on write, or reading the csums from the tree before a read
  */
-static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
+static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
 			  int mirror_num, unsigned long bio_flags,
 			  u64 bio_offset)
 {
@@ -1910,7 +1909,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 	if (btrfs_is_free_space_inode(inode))
 		metadata = BTRFS_WQ_ENDIO_FREE_SPACE;
 
-	if (!(rw & REQ_WRITE)) {
+	if (bio_op(bio) != REQ_OP_WRITE) {
 		ret = btrfs_bio_wq_end_io(root->fs_info, bio, metadata);
 		if (ret)
 			goto out;
@@ -1932,7 +1931,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 			goto mapit;
 		/* we're doing a write, do the async checksumming */
 		ret = btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info,
-				   inode, rw, bio, mirror_num,
+				   inode, bio, mirror_num,
 				   bio_flags, bio_offset,
 				   __btrfs_submit_bio_start,
 				   __btrfs_submit_bio_done);
@@ -1944,7 +1943,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 	}
 
 mapit:
-	ret = btrfs_map_bio(root, rw, bio, mirror_num, 0);
+	ret = btrfs_map_bio(root, bio, mirror_num, 0);
 
 out:
 	if (ret < 0) {
@@ -1978,7 +1977,7 @@ int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 {
 	WARN_ON((end & (PAGE_SIZE - 1)) == 0);
 	return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
-				   cached_state, GFP_NOFS);
+				   cached_state);
 }
 
 /* see btrfs_writepage_start_hook for details on why this is required */
@@ -3119,8 +3118,7 @@ static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 
 	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID &&
 	    test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) {
-		clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM,
-				  GFP_NOFS);
+		clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM);
 		return 0;
 	}
 
@@ -3272,7 +3270,16 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 	/* grab metadata reservation from transaction handle */
 	if (reserve) {
 		ret = btrfs_orphan_reserve_metadata(trans, inode);
-		BUG_ON(ret); /* -ENOSPC in reservation; Logic error? JDM */
+		ASSERT(!ret);
+		if (ret) {
+			atomic_dec(&root->orphan_inodes);
+			clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
+				  &BTRFS_I(inode)->runtime_flags);
+			if (insert)
+				clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
+					  &BTRFS_I(inode)->runtime_flags);
+			return ret;
+		}
 	}
 
 	/* insert an orphan item to track this unlinked/truncated file */
@@ -3722,7 +3729,7 @@ cache_index:
 	 * and doesn't have an inode ref with the name "bar" anymore.
 	 *
 	 * Setting last_unlink_trans to last_trans is a pessimistic approach,
-	 * but it guarantees correctness at the expense of ocassional full
+	 * but it guarantees correctness at the expense of occasional full
 	 * transaction commits on fsync if our inode is a directory, or if our
 	 * inode is not a directory, logging its parent unnecessarily.
 	 */
@@ -4550,6 +4557,7 @@ delete:
 			BUG_ON(ret);
 			if (btrfs_should_throttle_delayed_refs(trans, root))
 				btrfs_async_run_delayed_refs(root,
+							     trans->transid,
 					trans->delayed_ref_updates * 2, 0);
 			if (be_nice) {
 				if (truncate_space_check(trans, root,
@@ -4978,7 +4986,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		 * be instantly completed which will give us extents that need
 		 * to be truncated.  If we fail to get an orphan inode down we
 		 * could have left over extents that were never meant to live,
-		 * so we need to garuntee from this point on that everything
+		 * so we need to guarantee from this point on that everything
 		 * will be consistent.
 		 */
 		ret = btrfs_orphan_add(trans, inode);
@@ -5248,7 +5256,7 @@ void btrfs_evict_inode(struct inode *inode)
 		}
 
 		/*
-		 * We can't just steal from the global reserve, we need tomake
+		 * We can't just steal from the global reserve, we need to make
 		 * sure there is room to do it, if not we need to commit and try
 		 * again.
 		 */
@@ -5749,6 +5757,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	int name_len;
 	int is_curr = 0;	/* ctx->pos points to the current index? */
 	bool emitted;
+	bool put = false;
 
 	/* FIXME, use a real flag for deciding about the key type */
 	if (root->fs_info->tree_root == root)
@@ -5766,7 +5775,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		INIT_LIST_HEAD(&ins_list);
 		INIT_LIST_HEAD(&del_list);
-		btrfs_get_delayed_items(inode, &ins_list, &del_list);
+		put = btrfs_readdir_get_delayed_items(inode, &ins_list,
+						      &del_list);
 	}
 
 	key.type = key_type;
@@ -5913,8 +5923,8 @@ next:
 nopos:
 	ret = 0;
 err:
-	if (key_type == BTRFS_DIR_INDEX_KEY)
-		btrfs_put_delayed_items(&ins_list, &del_list);
+	if (put)
+		btrfs_readdir_put_delayed_items(inode, &ins_list, &del_list);
 	btrfs_free_path(path);
 	return ret;
 }
@@ -6980,7 +6990,18 @@ insert:
 		 * existing will always be non-NULL, since there must be
 		 * extent causing the -EEXIST.
 		 */
-		if (start >= extent_map_end(existing) ||
+		if (existing->start == em->start &&
+		    extent_map_end(existing) == extent_map_end(em) &&
+		    em->block_start == existing->block_start) {
+			/*
+			 * these two extents are the same, it happens
+			 * with inlines especially
+			 */
+			free_extent_map(em);
+			em = existing;
+			err = 0;
+
+		} else if (start >= extent_map_end(existing) ||
 		    start <= existing->start) {
 			/*
 			 * The existing extent map is the one nearest to
@@ -7433,7 +7454,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 				 cached_state);
 		/*
 		 * We're concerned with the entire range that we're going to be
-		 * doing DIO to, so we need to make sure theres no ordered
+		 * doing DIO to, so we need to make sure there's no ordered
 		 * extents in this range.
 		 */
 		ordered = btrfs_lookup_ordered_range(inode, lockstart,
@@ -7595,7 +7616,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	if (current->journal_info) {
 		/*
 		 * Need to pull our outstanding extents and set journal_info to NULL so
-		 * that anything that needs to check if there's a transction doesn't get
+		 * that anything that needs to check if there's a transaction doesn't get
 		 * confused.
 		 */
 		dio_data = current->journal_info;
@@ -7628,7 +7649,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	 * decompress it, so there will be buffering required no matter what we
 	 * do, so go ahead and fallback to buffered.
 	 *
-	 * We return -ENOTBLK because thats what makes DIO go ahead and go back
+	 * We return -ENOTBLK because that's what makes DIO go ahead and go back
 	 * to buffered IO.  Don't blame me, this is the price we pay for using
 	 * the generic code.
 	 */
@@ -7768,12 +7789,12 @@ err:
 }
 
 static inline int submit_dio_repair_bio(struct inode *inode, struct bio *bio,
-					int rw, int mirror_num)
+					int mirror_num)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
-	BUG_ON(rw & REQ_WRITE);
+	BUG_ON(bio_op(bio) == REQ_OP_WRITE);
 
 	bio_get(bio);
 
@@ -7782,7 +7803,7 @@ static inline int submit_dio_repair_bio(struct inode *inode, struct bio *bio,
 	if (ret)
 		goto err;
 
-	ret = btrfs_map_bio(root, rw, bio, mirror_num, 0);
+	ret = btrfs_map_bio(root, bio, mirror_num, 0);
 err:
 	bio_put(bio);
 	return ret;
@@ -7833,7 +7854,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	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)
@@ -7861,13 +7882,13 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 		free_io_failure(inode, failrec);
 		return -EIO;
 	}
+	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
 
 	btrfs_debug(BTRFS_I(inode)->root->fs_info,
 		    "Repair DIO Read Error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d\n",
 		    read_mode, failrec->this_mirror, failrec->in_validation);
 
-	ret = submit_dio_repair_bio(inode, bio, read_mode,
-				    failrec->this_mirror);
+	ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror);
 	if (ret) {
 		free_io_failure(inode, failrec);
 		bio_put(bio);
@@ -8157,7 +8178,7 @@ static void btrfs_endio_direct_write(struct bio *bio)
 	bio_put(bio);
 }
 
-static int __btrfs_submit_bio_start_direct_io(struct inode *inode, int rw,
+static int __btrfs_submit_bio_start_direct_io(struct inode *inode,
 				    struct bio *bio, int mirror_num,
 				    unsigned long bio_flags, u64 offset)
 {
@@ -8175,8 +8196,8 @@ static void btrfs_end_dio_bio(struct bio *bio)
 
 	if (err)
 		btrfs_warn(BTRFS_I(dip->inode)->root->fs_info,
-			   "direct IO failed ino %llu rw %lu sector %#Lx len %u err no %d",
-			   btrfs_ino(dip->inode), bio->bi_rw,
+			   "direct IO failed ino %llu rw %d,%u sector %#Lx len %u err no %d",
+			   btrfs_ino(dip->inode), bio_op(bio), bio->bi_rw,
 			   (unsigned long long)bio->bi_iter.bi_sector,
 			   bio->bi_iter.bi_size, err);
 
@@ -8250,11 +8271,11 @@ static inline int btrfs_lookup_and_bind_dio_csum(struct btrfs_root *root,
 }
 
 static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
-					 int rw, u64 file_offset, int skip_sum,
+					 u64 file_offset, int skip_sum,
 					 int async_submit)
 {
 	struct btrfs_dio_private *dip = bio->bi_private;
-	int write = rw & REQ_WRITE;
+	bool write = bio_op(bio) == REQ_OP_WRITE;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
@@ -8275,8 +8296,7 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 
 	if (write && async_submit) {
 		ret = btrfs_wq_submit_bio(root->fs_info,
-				   inode, rw, bio, 0, 0,
-				   file_offset,
+				   inode, bio, 0, 0, file_offset,
 				   __btrfs_submit_bio_start_direct_io,
 				   __btrfs_submit_bio_done);
 		goto err;
@@ -8295,13 +8315,13 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 			goto err;
 	}
 map:
-	ret = btrfs_map_bio(root, rw, bio, 0, async_submit);
+	ret = btrfs_map_bio(root, bio, 0, async_submit);
 err:
 	bio_put(bio);
 	return ret;
 }
 
-static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
+static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 				    int skip_sum)
 {
 	struct inode *inode = dip->inode;
@@ -8320,8 +8340,8 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	int i;
 
 	map_length = orig_bio->bi_iter.bi_size;
-	ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
-			      &map_length, NULL, 0);
+	ret = btrfs_map_block(root->fs_info, bio_op(orig_bio),
+			      start_sector << 9, &map_length, NULL, 0);
 	if (ret)
 		return -EIO;
 
@@ -8341,6 +8361,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	if (!bio)
 		return -ENOMEM;
 
+	bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_rw);
 	bio->bi_private = dip;
 	bio->bi_end_io = btrfs_end_dio_bio;
 	btrfs_io_bio(bio)->logical = file_offset;
@@ -8360,7 +8381,7 @@ next_block:
 			 * before we're done setting it up
 			 */
 			atomic_inc(&dip->pending_bios);
-			ret = __btrfs_submit_dio_bio(bio, inode, rw,
+			ret = __btrfs_submit_dio_bio(bio, inode,
 						     file_offset, skip_sum,
 						     async_submit);
 			if (ret) {
@@ -8378,12 +8399,13 @@ next_block:
 						  start_sector, GFP_NOFS);
 			if (!bio)
 				goto out_err;
+			bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_rw);
 			bio->bi_private = dip;
 			bio->bi_end_io = btrfs_end_dio_bio;
 			btrfs_io_bio(bio)->logical = file_offset;
 
 			map_length = orig_bio->bi_iter.bi_size;
-			ret = btrfs_map_block(root->fs_info, rw,
+			ret = btrfs_map_block(root->fs_info, bio_op(orig_bio),
 					      start_sector << 9,
 					      &map_length, NULL, 0);
 			if (ret) {
@@ -8403,7 +8425,7 @@ next_block:
 	}
 
 submit:
-	ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum,
+	ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
 				     async_submit);
 	if (!ret)
 		return 0;
@@ -8423,14 +8445,14 @@ out_err:
 	return 0;
 }
 
-static void btrfs_submit_direct(int rw, struct bio *dio_bio,
-				struct inode *inode, loff_t file_offset)
+static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
+				loff_t file_offset)
 {
 	struct btrfs_dio_private *dip = NULL;
 	struct bio *io_bio = NULL;
 	struct btrfs_io_bio *btrfs_bio;
 	int skip_sum;
-	int write = rw & REQ_WRITE;
+	bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
 	int ret = 0;
 
 	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
@@ -8481,7 +8503,7 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
 			dio_data->unsubmitted_oe_range_end;
 	}
 
-	ret = btrfs_submit_direct_hook(rw, dip, skip_sum);
+	ret = btrfs_submit_direct_hook(dip, skip_sum);
 	if (!ret)
 		return;
 
@@ -9041,7 +9063,7 @@ static int btrfs_truncate(struct inode *inode)
 		return ret;
 
 	/*
-	 * Yes ladies and gentelment, this is indeed ugly.  The fact is we have
+	 * Yes ladies and gentlemen, this is indeed ugly.  The fact is we have
 	 * 3 things going on here
 	 *
 	 * 1) We need to reserve space for our orphan item and the space to
@@ -9055,15 +9077,15 @@ static int btrfs_truncate(struct inode *inode)
 	 * space reserved in case it uses space during the truncate (thank you
 	 * very much snapshotting).
 	 *
-	 * And we need these to all be seperate.  The fact is we can use alot of
+	 * And we need these to all be separate.  The fact is we can use a lot of
 	 * space doing the truncate, and we have no earthly idea how much space
-	 * we will use, so we need the truncate reservation to be seperate so it
+	 * we will use, so we need the truncate reservation to be separate so it
 	 * doesn't end up using space reserved for updating the inode or
 	 * removing the orphan item.  We also need to be able to stop the
 	 * transaction and start a new one, which means we need to be able to
 	 * update the inode several times, and we have no idea of knowing how
 	 * many times that will be, so we can't just reserve 1 item for the
-	 * entirety of the opration, so that has to be done seperately as well.
+	 * entirety of the operation, so that has to be done separately as well.
 	 * Then there is the orphan item, which does indeed need to be held on
 	 * to for the whole operation, and we need nobody to touch this reserved
 	 * space except the orphan code.
@@ -10515,7 +10537,7 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = {
 static const struct file_operations btrfs_dir_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
-	.iterate	= btrfs_real_readdir,
+	.iterate_shared	= btrfs_real_readdir,
 	.unlocked_ioctl	= btrfs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= btrfs_compat_ioctl,