1 files changed, 55 insertions, 28 deletions

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 864c08d08a35..28a05ba47060 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -28,6 +28,7 @@
 #include "compression.h"
 #include "delalloc-space.h"
 #include "reflink.h"
+#include "subpage.h"
 
 static struct kmem_cache *btrfs_inode_defrag_cachep;
 /*
@@ -482,6 +483,7 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages,
 	start_pos = round_down(pos, fs_info->sectorsize);
 	num_bytes = round_up(write_bytes + pos - start_pos,
 			     fs_info->sectorsize);
+	ASSERT(num_bytes <= U32_MAX);
 
 	end_of_last_block = start_pos + num_bytes - 1;
 
@@ -500,9 +502,10 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages,
 
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = pages[i];
-		SetPageUptodate(p);
+
+		btrfs_page_clamp_set_uptodate(fs_info, p, start_pos, num_bytes);
 		ClearPageChecked(p);
-		set_page_dirty(p);
+		btrfs_page_clamp_set_dirty(fs_info, p, start_pos, num_bytes);
 	}
 
 	/*
@@ -1094,7 +1097,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 	int del_nr = 0;
 	int del_slot = 0;
 	int recow;
-	int ret;
+	int ret = 0;
 	u64 ino = btrfs_ino(inode);
 
 	path = btrfs_alloc_path();
@@ -1315,7 +1318,7 @@ again:
 	}
 out:
 	btrfs_free_path(path);
-	return 0;
+	return ret;
 }
 
 /*
@@ -2067,6 +2070,30 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
 	return ret;
 }
 
+static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
+{
+	struct btrfs_inode *inode = BTRFS_I(ctx->inode);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+
+	if (btrfs_inode_in_log(inode, fs_info->generation) &&
+	    list_empty(&ctx->ordered_extents))
+		return true;
+
+	/*
+	 * If we are doing a fast fsync we can not bail out if the inode's
+	 * last_trans is <= then the last committed transaction, because we only
+	 * update the last_trans of the inode during ordered extent completion,
+	 * and for a fast fsync we don't wait for that, we only wait for the
+	 * writeback to complete.
+	 */
+	if (inode->last_trans <= fs_info->last_trans_committed &&
+	    (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) ||
+	     list_empty(&ctx->ordered_extents)))
+		return true;
+
+	return false;
+}
+
 /*
  * fsync call for both files and directories.  This logs the inode into
  * the tree log instead of forcing full commits whenever possible.
@@ -2185,17 +2212,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	atomic_inc(&root->log_batch);
 
-	/*
-	 * If we are doing a fast fsync we can not bail out if the inode's
-	 * last_trans is <= then the last committed transaction, because we only
-	 * update the last_trans of the inode during ordered extent completion,
-	 * and for a fast fsync we don't wait for that, we only wait for the
-	 * writeback to complete.
-	 */
 	smp_mb();
-	if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) ||
-	    (BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed &&
-	     (full_sync || list_empty(&ctx.ordered_extents)))) {
+	if (skip_inode_logging(&ctx)) {
 		/*
 		 * We've had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
@@ -2468,6 +2486,17 @@ static int btrfs_punch_hole_lock_range(struct inode *inode,
 				       const u64 lockend,
 				       struct extent_state **cached_state)
 {
+	/*
+	 * For subpage case, if the range is not at page boundary, we could
+	 * have pages at the leading/tailing part of the range.
+	 * This could lead to dead loop since filemap_range_has_page()
+	 * will always return true.
+	 * So here we need to do extra page alignment for
+	 * filemap_range_has_page().
+	 */
+	const u64 page_lockstart = round_up(lockstart, PAGE_SIZE);
+	const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1;
+
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
 		int ret;
@@ -2488,7 +2517,7 @@ static int btrfs_punch_hole_lock_range(struct inode *inode,
 		    (ordered->file_offset + ordered->num_bytes <= lockstart ||
 		     ordered->file_offset > lockend)) &&
 		     !filemap_range_has_page(inode->i_mapping,
-					     lockstart, lockend)) {
+					     page_lockstart, page_lockend)) {
 			if (ordered)
 				btrfs_put_ordered_extent(ordered);
 			break;
@@ -3019,22 +3048,20 @@ struct falloc_range {
  */
 static int add_falloc_range(struct list_head *head, u64 start, u64 len)
 {
-	struct falloc_range *prev = NULL;
 	struct falloc_range *range = NULL;
 
-	if (list_empty(head))
-		goto insert;
-
-	/*
-	 * As fallocate iterate by bytenr order, we only need to check
-	 * the last range.
-	 */
-	prev = list_entry(head->prev, struct falloc_range, list);
-	if (prev->start + prev->len == start) {
-		prev->len += len;
-		return 0;
+	if (!list_empty(head)) {
+		/*
+		 * As fallocate iterates by bytenr order, we only need to check
+		 * the last range.
+		 */
+		range = list_last_entry(head, struct falloc_range, list);
+		if (range->start + range->len == start) {
+			range->len += len;
+			return 0;
+		}
 	}
-insert:
+
 	range = kmalloc(sizeof(*range), GFP_KERNEL);
 	if (!range)
 		return -ENOMEM;