From 123aaf774f70ba48fb9ab064b6ce75a9b64d7b85 Mon Sep 17 00:00:00 2001
From: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Date: Wed, 19 Aug 2020 10:34:48 +0900
Subject: [PATCH 1/3] f2fs: Fix type of section block count variables
Commit da52f8ade40b ("f2fs: get the right gc victim section when section
has several segments") added code to count blocks of each section using
variables with type 'unsigned short', which has 2 bytes size in many
systems. However, the counts can be larger than the 2 bytes range and
type conversion results in wrong values. Especially when the f2fs
sections have blocks as many as USHRT_MAX + 1, the count is handled as 0.
This triggers eternal loop in init_dirty_segmap() at mount system call.
Fix this by changing the type of the variables to block_t.
Fixes: da52f8ade40b ("f2fs: get the right gc victim section when section has several segments")
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
fs/f2fs/segment.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index a65d357f89a9..e247a5ef3713 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -799,7 +799,7 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
if (__is_large_section(sbi)) {
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
- unsigned short valid_blocks =
+ block_t valid_blocks =
get_valid_blocks(sbi, segno, true);
f2fs_bug_on(sbi, unlikely(!valid_blocks ||
@@ -815,7 +815,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
enum dirty_type dirty_type)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned short valid_blocks;
+ block_t valid_blocks;
if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type]))
dirty_i->nr_dirty[dirty_type]--;
@@ -4316,8 +4316,8 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int segno = 0, offset = 0, secno;
- unsigned short valid_blocks;
- unsigned short blks_per_sec = BLKS_PER_SEC(sbi);
+ block_t valid_blocks;
+ block_t blks_per_sec = BLKS_PER_SEC(sbi);
while (1) {
/* find dirty segment based on free segmap */
From e2cab031ba7b5003cd12185b3ef38f1a75e3dae8 Mon Sep 17 00:00:00 2001
From: Sahitya Tummala <stummala@codeaurora.org>
Date: Tue, 18 Aug 2020 15:40:14 +0530
Subject: [PATCH 2/3] f2fs: fix indefinite loop scanning for free nid
If the sbi->ckpt->next_free_nid is not NAT block aligned and if there
are free nids in that NAT block between the start of the block and
next_free_nid, then those free nids will not be scanned in scan_nat_page().
This results into mismatch between nm_i->available_nids and the sum of
nm_i->free_nid_count of all NAT blocks scanned. And nm_i->available_nids
will always be greater than the sum of free nids in all the blocks.
Under this condition, if we use all the currently scanned free nids,
then it will loop forever in f2fs_alloc_nid() as nm_i->available_nids
is still not zero but nm_i->free_nid_count of that partially scanned
NAT block is zero.
Fix this to align the nm_i->next_scan_nid to the first nid of the
corresponding NAT block.
Signed-off-by: Sahitya Tummala <stummala@codeaurora.org>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
fs/f2fs/node.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 3ad7bdbda5ca..cb1b5b61a1da 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -2373,6 +2373,9 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
if (unlikely(nid >= nm_i->max_nid))
nid = 0;
+ if (unlikely(nid % NAT_ENTRY_PER_BLOCK))
+ nid = NAT_BLOCK_OFFSET(nid) * NAT_ENTRY_PER_BLOCK;
+
/* Enough entries */
if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
return 0;
From 20d0a107fb35f37578b919f62bd474d6d358d579 Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Wed, 19 Aug 2020 16:07:31 -0400
Subject: [PATCH 3/3] f2fs: Return EOF on unaligned end of file DIO read
Reading past end of file returns EOF for aligned reads but -EINVAL for
unaligned reads on f2fs. While documentation is not strict about this
corner case, most filesystem returns EOF on this case, like iomap
filesystems. This patch consolidates the behavior for f2fs, by making
it return EOF(0).
it can be verified by a read loop on a file that does a partial read
before EOF (A file that doesn't end at an aligned address). The
following code fails on an unaligned file on f2fs, but not on
btrfs, ext4, and xfs.
while (done < total) {
ssize_t delta = pread(fd, buf + done, total - done, off + done);
if (!delta)
break;
...
}
It is arguable whether filesystems should actually return EOF or
-EINVAL, but since iomap filesystems support it, and so does the
original DIO code, it seems reasonable to consolidate on that.
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
fs/f2fs/data.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ed2bca0fce92..73683e58a08d 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3550,6 +3550,9 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
unsigned long align = offset | iov_iter_alignment(iter);
struct block_device *bdev = inode->i_sb->s_bdev;
+ if (iov_iter_rw(iter) == READ && offset >= i_size_read(inode))
+ return 1;
+
if (align & blocksize_mask) {
if (bdev)
blkbits = blksize_bits(bdev_logical_block_size(bdev));