diff mbox series

[5.4,31/85] btrfs: allow btrfs_truncate_block() to fallback to nocow for data space reservation

Message ID 20201012132634.353480633@linuxfoundation.org
State New
Headers show
Series None | expand

Commit Message

Greg Kroah-Hartman Oct. 12, 2020, 1:26 p.m. UTC 
From: Qu Wenruo <wqu@suse.com>

commit 6d4572a9d71d5fc2affee0258d8582d39859188c upstream.

[BUG]
When the data space is exhausted, even if the inode has NOCOW attribute,
we will still refuse to truncate unaligned range due to ENOSPC.

The following script can reproduce it pretty easily:
  #!/bin/bash

  dev=/dev/test/test
  mnt=/mnt/btrfs

  umount $dev &> /dev/null
  umount $mnt &> /dev/null

  mkfs.btrfs -f $dev -b 1G
  mount -o nospace_cache $dev $mnt
  touch $mnt/foobar
  chattr +C $mnt/foobar

  xfs_io -f -c "pwrite -b 4k 0 4k" $mnt/foobar > /dev/null
  xfs_io -f -c "pwrite -b 4k 0 1G" $mnt/padding &> /dev/null
  sync

  xfs_io -c "fpunch 0 2k" $mnt/foobar
  umount $mnt

Currently this will fail at the fpunch part.

[CAUSE]
Because btrfs_truncate_block() always reserves space without checking
the NOCOW attribute.

Since the writeback path follows NOCOW bit, we only need to bother the
space reservation code in btrfs_truncate_block().

[FIX]
Make btrfs_truncate_block() follow btrfs_buffered_write() to try to
reserve data space first, and fall back to NOCOW check only when we
don't have enough space.

Such always-try-reserve is an optimization introduced in
btrfs_buffered_write(), to avoid expensive btrfs_check_can_nocow() call.

This patch will export check_can_nocow() as btrfs_check_can_nocow(), and
use it in btrfs_truncate_block() to fix the problem.

Reported-by: Martin Doucha <martin.doucha@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/btrfs/ctree.h |    2 ++
 fs/btrfs/file.c  |    9 +++++----
 fs/btrfs/inode.c |   44 +++++++++++++++++++++++++++++++++++++-------
 3 files changed, 44 insertions(+), 11 deletions(-)
diff mbox series

Patch

--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2956,6 +2956,8 @@  int btrfs_fdatawrite_range(struct inode
 loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in,
 			      struct file *file_out, loff_t pos_out,
 			      loff_t len, unsigned int remap_flags);
+int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos,
+			  size_t *write_bytes);
 
 /* tree-defrag.c */
 int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1546,8 +1546,8 @@  lock_and_cleanup_extent_if_need(struct b
 	return ret;
 }
 
-static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
-				    size_t *write_bytes)
+int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos,
+			  size_t *write_bytes)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_root *root = inode->root;
@@ -1647,7 +1647,7 @@  static noinline ssize_t btrfs_buffered_w
 		if (ret < 0) {
 			if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
 						      BTRFS_INODE_PREALLOC)) &&
-			    check_can_nocow(BTRFS_I(inode), pos,
+			    btrfs_check_can_nocow(BTRFS_I(inode), pos,
 					&write_bytes) > 0) {
 				/*
 				 * For nodata cow case, no need to reserve
@@ -1927,7 +1927,8 @@  static ssize_t btrfs_file_write_iter(str
 		 */
 		if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
 					      BTRFS_INODE_PREALLOC)) ||
-		    check_can_nocow(BTRFS_I(inode), pos, &nocow_bytes) <= 0) {
+		    btrfs_check_can_nocow(BTRFS_I(inode), pos,
+					  &nocow_bytes) <= 0) {
 			inode_unlock(inode);
 			return -EAGAIN;
 		}
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5133,11 +5133,13 @@  int btrfs_truncate_block(struct inode *i
 	struct extent_state *cached_state = NULL;
 	struct extent_changeset *data_reserved = NULL;
 	char *kaddr;
+	bool only_release_metadata = false;
 	u32 blocksize = fs_info->sectorsize;
 	pgoff_t index = from >> PAGE_SHIFT;
 	unsigned offset = from & (blocksize - 1);
 	struct page *page;
 	gfp_t mask = btrfs_alloc_write_mask(mapping);
+	size_t write_bytes = blocksize;
 	int ret = 0;
 	u64 block_start;
 	u64 block_end;
@@ -5149,11 +5151,27 @@  int btrfs_truncate_block(struct inode *i
 	block_start = round_down(from, blocksize);
 	block_end = block_start + blocksize - 1;
 
-	ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
-					   block_start, blocksize);
-	if (ret)
-		goto out;
 
+	ret = btrfs_check_data_free_space(inode, &data_reserved, block_start,
+					  blocksize);
+	if (ret < 0) {
+		if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+					      BTRFS_INODE_PREALLOC)) &&
+		    btrfs_check_can_nocow(BTRFS_I(inode), block_start,
+					  &write_bytes) > 0) {
+			/* For nocow case, no need to reserve data space */
+			only_release_metadata = true;
+		} else {
+			goto out;
+		}
+	}
+	ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), blocksize);
+	if (ret < 0) {
+		if (!only_release_metadata)
+			btrfs_free_reserved_data_space(inode, data_reserved,
+					block_start, blocksize);
+		goto out;
+	}
 again:
 	page = find_or_create_page(mapping, index, mask);
 	if (!page) {
@@ -5222,14 +5240,26 @@  again:
 	set_page_dirty(page);
 	unlock_extent_cached(io_tree, block_start, block_end, &cached_state);
 
+	if (only_release_metadata)
+		set_extent_bit(&BTRFS_I(inode)->io_tree, block_start,
+				block_end, EXTENT_NORESERVE, NULL, NULL,
+				GFP_NOFS);
+
 out_unlock:
-	if (ret)
-		btrfs_delalloc_release_space(inode, data_reserved, block_start,
-					     blocksize, true);
+	if (ret) {
+		if (only_release_metadata)
+			btrfs_delalloc_release_metadata(BTRFS_I(inode),
+					blocksize, true);
+		else
+			btrfs_delalloc_release_space(inode, data_reserved,
+					block_start, blocksize, true);
+	}
 	btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
 	unlock_page(page);
 	put_page(page);
 out:
+	if (only_release_metadata)
+		btrfs_end_write_no_snapshotting(BTRFS_I(inode)->root);
 	extent_changeset_free(data_reserved);
 	return ret;
 }