diff mbox series

[06/21] btrfs: wait ordered range before locking during truncate

Message ID e9629218282f3e016517f1280b48c5d194fd7c40.1677793433.git.rgoldwyn@suse.com (mailing list archive)
State New, archived
Headers show
Series Lock extents before pages | expand

Commit Message

Goldwyn Rodrigues March 2, 2023, 10:24 p.m. UTC 
From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Check if truncate needs to wait for ordered range before calling
btrfs_truncate(). Instead of performing it in btrfs_truncate(), perform
the wait before the call.

Remove the no longer needed variable to perform writeback in
btrfs_truncate().

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
---
 fs/btrfs/inode.c | 18 +++++-------------
 1 file changed, 5 insertions(+), 13 deletions(-)

Comments

Christoph Hellwig March 7, 2023, 5:03 p.m. UTC | #1 
So, one thing I've been wondering about for a while is why btrfs even
does all these explicit waits for ordered extents.  The ordered_extent
is effectively a mechanism to describe a range of I/O.

So why can't we use the nornal mechanisms to wait for I/O, that is the
completion of writeback for buffered I/O (i.e. filemap_fdatawait*)
and inode_dio_wait for direct I/O?  I've been wanting to look deeper
into this for a while, so this might be a good time to bring it up.
diff mbox series

Patch

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2c96c39975e0..02307789b0a8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -109,7 +109,7 @@  static const struct file_operations btrfs_dir_file_operations;
 static struct kmem_cache *btrfs_inode_cachep;
 
 static int btrfs_setsize(struct inode *inode, struct iattr *attr);
-static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback);
+static int btrfs_truncate(struct btrfs_inode *inode);
 static noinline int cow_file_range(struct btrfs_inode *inode,
 				   struct page *locked_page,
 				   u64 start, u64 end, int *page_started,
@@ -5084,7 +5084,7 @@  static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 	} else {
 		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 
-		if (btrfs_is_zoned(fs_info)) {
+		if (btrfs_is_zoned(fs_info) || (newsize < oldsize)) {
 			ret = btrfs_wait_ordered_range(inode,
 					ALIGN(newsize, fs_info->sectorsize),
 					(u64)-1);
@@ -5105,7 +5105,8 @@  static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 
 		inode_dio_wait(inode);
 
-		ret = btrfs_truncate(BTRFS_I(inode), newsize == oldsize);
+		ret = btrfs_truncate(BTRFS_I(inode));
+
 		if (ret && inode->i_nlink) {
 			int err;
 
@@ -8241,7 +8242,7 @@  vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
 	return ret;
 }
 
-static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback)
+static int btrfs_truncate(struct btrfs_inode *inode)
 {
 	struct btrfs_truncate_control control = {
 		.inode = inode,
@@ -8254,17 +8255,8 @@  static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback)
 	struct btrfs_block_rsv *rsv;
 	int ret;
 	struct btrfs_trans_handle *trans;
-	u64 mask = fs_info->sectorsize - 1;
 	u64 min_size = btrfs_calc_metadata_size(fs_info, 1);
 
-	if (!skip_writeback) {
-		ret = btrfs_wait_ordered_range(&inode->vfs_inode,
-					       inode->vfs_inode.i_size & (~mask),
-					       (u64)-1);
-		if (ret)
-			return ret;
-	}
-
 	/*
 	 * Yes ladies and gentlemen, this is indeed ugly.  We have a couple of
 	 * things going on here: