1 files changed, 154 insertions, 62 deletions

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index eb742c07e7a4..1f2b99cb55ea 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -40,6 +40,7 @@
 #include "tree-log.h"
 #include "locking.h"
 #include "volumes.h"
+#include "qgroup.h"
 
 static struct kmem_cache *btrfs_inode_defrag_cachep;
 /*
@@ -447,7 +448,7 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 		write_bytes -= copied;
 		total_copied += copied;
 
-		/* Return to btrfs_file_aio_write to fault page */
+		/* Return to btrfs_file_write_iter to fault page */
 		if (unlikely(copied == 0))
 			break;
 
@@ -470,11 +471,12 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages)
 	for (i = 0; i < num_pages; i++) {
 		/* page checked is some magic around finding pages that
 		 * have been modified without going through btrfs_set_page_dirty
-		 * clear it here
+		 * clear it here. There should be no need to mark the pages
+		 * accessed as prepare_pages should have marked them accessed
+		 * in prepare_pages via find_or_create_page()
 		 */
 		ClearPageChecked(pages[i]);
 		unlock_page(pages[i]);
-		mark_page_accessed(pages[i]);
 		page_cache_release(pages[i]);
 	}
 }
@@ -714,7 +716,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	int recow;
 	int ret;
 	int modify_tree = -1;
-	int update_refs = (root->ref_cows || root == root->fs_info->tree_root);
+	int update_refs;
 	int found = 0;
 	int leafs_visited = 0;
 
@@ -724,6 +726,8 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent)
 		modify_tree = 0;
 
+	update_refs = (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+		       root == root->fs_info->tree_root);
 	while (1) {
 		recow = 0;
 		ret = btrfs_lookup_file_extent(trans, root, path, ino,
@@ -780,6 +784,18 @@ next_slot:
 			extent_end = search_start;
 		}
 
+		/*
+		 * Don't skip extent items representing 0 byte lengths. They
+		 * used to be created (bug) if while punching holes we hit
+		 * -ENOSPC condition. So if we find one here, just ensure we
+		 * delete it, otherwise we would insert a new file extent item
+		 * with the same key (offset) as that 0 bytes length file
+		 * extent item in the call to setup_items_for_insert() later
+		 * in this function.
+		 */
+		if (extent_end == key.offset && extent_end >= search_start)
+			goto delete_extent_item;
+
 		if (extent_end <= search_start) {
 			path->slots[0]++;
 			goto next_slot;
@@ -800,7 +816,7 @@ next_slot:
 		if (start > key.offset && end < extent_end) {
 			BUG_ON(del_nr > 0);
 			if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
-				ret = -EINVAL;
+				ret = -EOPNOTSUPP;
 				break;
 			}
 
@@ -835,7 +851,7 @@ next_slot:
 						disk_bytenr, num_bytes, 0,
 						root->root_key.objectid,
 						new_key.objectid,
-						start - extent_offset, 0);
+						start - extent_offset, 1);
 				BUG_ON(ret); /* -ENOMEM */
 			}
 			key.offset = start;
@@ -846,7 +862,7 @@ next_slot:
 		 */
 		if (start <= key.offset && end < extent_end) {
 			if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
-				ret = -EINVAL;
+				ret = -EOPNOTSUPP;
 				break;
 			}
 
@@ -872,7 +888,7 @@ next_slot:
 		if (start > key.offset && end >= extent_end) {
 			BUG_ON(del_nr > 0);
 			if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
-				ret = -EINVAL;
+				ret = -EOPNOTSUPP;
 				break;
 			}
 
@@ -893,6 +909,7 @@ next_slot:
 		 *    | ------ extent ------ |
 		 */
 		if (start <= key.offset && end >= extent_end) {
+delete_extent_item:
 			if (del_nr == 0) {
 				del_slot = path->slots[0];
 				del_nr = 1;
@@ -1191,7 +1208,7 @@ again:
 
 		ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
 					   root->root_key.objectid,
-					   ino, orig_offset, 0);
+					   ino, orig_offset, 1);
 		BUG_ON(ret); /* -ENOMEM */
 
 		if (split == start) {
@@ -1658,27 +1675,22 @@ again:
 }
 
 static ssize_t __btrfs_direct_write(struct kiocb *iocb,
-				    const struct iovec *iov,
-				    unsigned long nr_segs, loff_t pos,
-				    size_t count, size_t ocount)
+				    struct iov_iter *from,
+				    loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
-	struct iov_iter i;
 	ssize_t written;
 	ssize_t written_buffered;
 	loff_t endbyte;
 	int err;
 
-	written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
-					    count, ocount);
+	written = generic_file_direct_write(iocb, from, pos);
 
-	if (written < 0 || written == count)
+	if (written < 0 || !iov_iter_count(from))
 		return written;
 
 	pos += written;
-	count -= written;
-	iov_iter_init(&i, iov, nr_segs, count, written);
-	written_buffered = __btrfs_buffered_write(file, &i, pos);
+	written_buffered = __btrfs_buffered_write(file, from, pos);
 	if (written_buffered < 0) {
 		err = written_buffered;
 		goto out;
@@ -1713,9 +1725,8 @@ static void update_time_for_write(struct inode *inode)
 		inode_inc_iversion(inode);
 }
 
-static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
-				    const struct iovec *iov,
-				    unsigned long nr_segs, loff_t pos)
+static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
+				    struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
@@ -1724,18 +1735,12 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	u64 end_pos;
 	ssize_t num_written = 0;
 	ssize_t err = 0;
-	size_t count, ocount;
+	size_t count = iov_iter_count(from);
 	bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host);
+	loff_t pos = iocb->ki_pos;
 
 	mutex_lock(&inode->i_mutex);
 
-	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
-	if (err) {
-		mutex_unlock(&inode->i_mutex);
-		goto out;
-	}
-	count = ocount;
-
 	current->backing_dev_info = inode->i_mapping->backing_dev_info;
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err) {
@@ -1748,6 +1753,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		goto out;
 	}
 
+	iov_iter_truncate(from, count);
+
 	err = file_remove_suid(file);
 	if (err) {
 		mutex_unlock(&inode->i_mutex);
@@ -1777,7 +1784,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	start_pos = round_down(pos, root->sectorsize);
 	if (start_pos > i_size_read(inode)) {
 		/* Expand hole size to cover write data, preventing empty gap */
-		end_pos = round_up(pos + iov->iov_len, root->sectorsize);
+		end_pos = round_up(pos + count, root->sectorsize);
 		err = btrfs_cont_expand(inode, i_size_read(inode), end_pos);
 		if (err) {
 			mutex_unlock(&inode->i_mutex);
@@ -1789,14 +1796,9 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		atomic_inc(&BTRFS_I(inode)->sync_writers);
 
 	if (unlikely(file->f_flags & O_DIRECT)) {
-		num_written = __btrfs_direct_write(iocb, iov, nr_segs,
-						   pos, count, ocount);
+		num_written = __btrfs_direct_write(iocb, from, pos);
 	} else {
-		struct iov_iter i;
-
-		iov_iter_init(&i, iov, nr_segs, count, num_written);
-
-		num_written = __btrfs_buffered_write(file, &i, pos);
+		num_written = __btrfs_buffered_write(file, from, pos);
 		if (num_written > 0)
 			iocb->ki_pos = pos + num_written;
 	}
@@ -2009,8 +2011,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		if (!full_sync) {
 			ret = btrfs_wait_ordered_range(inode, start,
 						       end - start + 1);
-			if (ret)
+			if (ret) {
+				btrfs_end_transaction(trans, root);
 				goto out;
+			}
 		}
 		ret = btrfs_commit_transaction(trans, root);
 	} else {
@@ -2168,6 +2172,37 @@ out:
 	return 0;
 }
 
+/*
+ * Find a hole extent on given inode and change start/len to the end of hole
+ * extent.(hole/vacuum extent whose em->start <= start &&
+ *	   em->start + em->len > start)
+ * When a hole extent is found, return 1 and modify start/len.
+ */
+static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len)
+{
+	struct extent_map *em;
+	int ret = 0;
+
+	em = btrfs_get_extent(inode, NULL, 0, *start, *len, 0);
+	if (IS_ERR_OR_NULL(em)) {
+		if (!em)
+			ret = -ENOMEM;
+		else
+			ret = PTR_ERR(em);
+		return ret;
+	}
+
+	/* Hole or vacuum extent(only exists in no-hole mode) */
+	if (em->block_start == EXTENT_MAP_HOLE) {
+		ret = 1;
+		*len = em->start + em->len > *start + *len ?
+		       0 : *start + *len - em->start - em->len;
+		*start = em->start + em->len;
+	}
+	free_extent_map(em);
+	return ret;
+}
+
 static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -2175,25 +2210,42 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	struct btrfs_path *path;
 	struct btrfs_block_rsv *rsv;
 	struct btrfs_trans_handle *trans;
-	u64 lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
-	u64 lockend = round_down(offset + len,
-				 BTRFS_I(inode)->root->sectorsize) - 1;
-	u64 cur_offset = lockstart;
+	u64 lockstart;
+	u64 lockend;
+	u64 tail_start;
+	u64 tail_len;
+	u64 orig_start = offset;
+	u64 cur_offset;
 	u64 min_size = btrfs_calc_trunc_metadata_size(root, 1);
 	u64 drop_end;
 	int ret = 0;
 	int err = 0;
 	int rsv_count;
-	bool same_page = ((offset >> PAGE_CACHE_SHIFT) ==
-			  ((offset + len - 1) >> PAGE_CACHE_SHIFT));
+	bool same_page;
 	bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
-	u64 ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
+	u64 ino_size;
 
 	ret = btrfs_wait_ordered_range(inode, offset, len);
 	if (ret)
 		return ret;
 
 	mutex_lock(&inode->i_mutex);
+	ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
+	ret = find_first_non_hole(inode, &offset, &len);
+	if (ret < 0)
+		goto out_only_mutex;
+	if (ret && !len) {
+		/* Already in a large hole */
+		ret = 0;
+		goto out_only_mutex;
+	}
+
+	lockstart = round_up(offset , BTRFS_I(inode)->root->sectorsize);
+	lockend = round_down(offset + len,
+			     BTRFS_I(inode)->root->sectorsize) - 1;
+	same_page = ((offset >> PAGE_CACHE_SHIFT) ==
+		    ((offset + len - 1) >> PAGE_CACHE_SHIFT));
+
 	/*
 	 * We needn't truncate any page which is beyond the end of the file
 	 * because we are sure there is no data there.
@@ -2205,8 +2257,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	if (same_page && len < PAGE_CACHE_SIZE) {
 		if (offset < ino_size)
 			ret = btrfs_truncate_page(inode, offset, len, 0);
-		mutex_unlock(&inode->i_mutex);
-		return ret;
+		goto out_only_mutex;
 	}
 
 	/* zero back part of the first page */
@@ -2218,12 +2269,39 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		}
 	}
 
-	/* zero the front end of the last page */
-	if (offset + len < ino_size) {
-		ret = btrfs_truncate_page(inode, offset + len, 0, 1);
-		if (ret) {
-			mutex_unlock(&inode->i_mutex);
-			return ret;
+	/* Check the aligned pages after the first unaligned page,
+	 * if offset != orig_start, which means the first unaligned page
+	 * including serveral following pages are already in holes,
+	 * the extra check can be skipped */
+	if (offset == orig_start) {
+		/* after truncate page, check hole again */
+		len = offset + len - lockstart;
+		offset = lockstart;
+		ret = find_first_non_hole(inode, &offset, &len);
+		if (ret < 0)
+			goto out_only_mutex;
+		if (ret && !len) {
+			ret = 0;
+			goto out_only_mutex;
+		}
+		lockstart = offset;
+	}
+
+	/* Check the tail unaligned part is in a hole */
+	tail_start = lockend + 1;
+	tail_len = offset + len - tail_start;
+	if (tail_len) {
+		ret = find_first_non_hole(inode, &tail_start, &tail_len);
+		if (unlikely(ret < 0))
+			goto out_only_mutex;
+		if (!ret) {
+			/* zero the front end of the last page */
+			if (tail_start + tail_len < ino_size) {
+				ret = btrfs_truncate_page(inode,
+						tail_start + tail_len, 0, 1);
+				if (ret)
+					goto out_only_mutex;
+				}
 		}
 	}
 
@@ -2249,9 +2327,7 @@ 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)) &&
-		     !test_range_bit(&BTRFS_I(inode)->io_tree, lockstart,
-				     lockend, EXTENT_UPTODATE, 0,
-				     cached_state)) {
+		     !btrfs_page_exists_in_range(inode, lockstart, lockend)) {
 			if (ordered)
 				btrfs_put_ordered_extent(ordered);
 			break;
@@ -2299,6 +2375,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	BUG_ON(ret);
 	trans->block_rsv = rsv;
 
+	cur_offset = lockstart;
+	len = lockend - cur_offset;
 	while (cur_offset < lockend) {
 		ret = __btrfs_drop_extents(trans, root, inode, path,
 					   cur_offset, lockend + 1,
@@ -2339,6 +2417,14 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 					      rsv, min_size);
 		BUG_ON(ret);	/* shouldn't happen */
 		trans->block_rsv = rsv;
+
+		ret = find_first_non_hole(inode, &cur_offset, &len);
+		if (unlikely(ret < 0))
+			break;
+		if (ret && !len) {
+			ret = 0;
+			break;
+		}
 	}
 
 	if (ret) {
@@ -2347,7 +2433,12 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	}
 
 	trans->block_rsv = &root->fs_info->trans_block_rsv;
-	if (cur_offset < ino_size) {
+	/*
+	 * Don't insert file hole extent item if it's for a range beyond eof
+	 * (because it's useless) or if it represents a 0 bytes range (when
+	 * cur_offset == drop_end).
+	 */
+	if (cur_offset < ino_size && cur_offset < drop_end) {
 		ret = fill_holes(trans, inode, path, cur_offset, drop_end);
 		if (ret) {
 			err = ret;
@@ -2372,6 +2463,7 @@ out_free:
 out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state, GFP_NOFS);
+out_only_mutex:
 	mutex_unlock(&inode->i_mutex);
 	if (ret && !err)
 		err = ret;
@@ -2633,11 +2725,11 @@ out:
 
 const struct file_operations btrfs_file_operations = {
 	.llseek		= btrfs_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read       = generic_file_aio_read,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter      = generic_file_read_iter,
 	.splice_read	= generic_file_splice_read,
-	.aio_write	= btrfs_file_aio_write,
+	.write_iter	= btrfs_file_write_iter,
 	.mmap		= btrfs_file_mmap,
 	.open		= generic_file_open,
 	.release	= btrfs_release_file,