From d8dad2588addd1d861ce19e7df3b702330f0c7e3 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Mon, 4 Apr 2022 11:58:06 +0900
Subject: [PATCH 1/5] exfat: fix referencing wrong parent directory information
after renaming
During renaming, the parent directory information maybe
updated. But the file/directory still references to the
old parent directory information.
This bug will cause 2 problems.
(1) The renamed file can not be written.
[10768.175172] exFAT-fs (sda1): error, failed to bmap (inode : 7afd50e4 iblock : 0, err : -5)
[10768.184285] exFAT-fs (sda1): Filesystem has been set read-only
ash: write error: Input/output error
(2) Some dentries of the renamed file/directory are not set
to deleted after removing the file/directory.
exfat_update_parent_info() is a workaround for the wrong parent
directory information being used after renaming. Now that bug is
fixed, this is no longer needed, so remove it.
Fixes: 5f2aa075070c ("exfat: add inode operations")
Cc: stable@vger.kernel.org # v5.7+
Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Andy Wu <Andy.Wu@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Daniel Palmer <daniel.palmer@sony.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
fs/exfat/namei.c | 27 +--------------------------
1 file changed, 1 insertion(+), 26 deletions(-)
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index a02a04a993bf..76acc3721951 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -1080,6 +1080,7 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir,
exfat_remove_entries(inode, p_dir, oldentry, 0,
num_old_entries);
+ ei->dir = *p_dir;
ei->entry = newentry;
} else {
if (exfat_get_entry_type(epold) == TYPE_FILE) {
@@ -1167,28 +1168,6 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir,
return 0;
}
-static void exfat_update_parent_info(struct exfat_inode_info *ei,
- struct inode *parent_inode)
-{
- struct exfat_sb_info *sbi = EXFAT_SB(parent_inode->i_sb);
- struct exfat_inode_info *parent_ei = EXFAT_I(parent_inode);
- loff_t parent_isize = i_size_read(parent_inode);
-
- /*
- * the problem that struct exfat_inode_info caches wrong parent info.
- *
- * because of flag-mismatch of ei->dir,
- * there is abnormal traversing cluster chain.
- */
- if (unlikely(parent_ei->flags != ei->dir.flags ||
- parent_isize != EXFAT_CLU_TO_B(ei->dir.size, sbi) ||
- parent_ei->start_clu != ei->dir.dir)) {
- exfat_chain_set(&ei->dir, parent_ei->start_clu,
- EXFAT_B_TO_CLU_ROUND_UP(parent_isize, sbi),
- parent_ei->flags);
- }
-}
-
/* rename or move a old file into a new file */
static int __exfat_rename(struct inode *old_parent_inode,
struct exfat_inode_info *ei, struct inode *new_parent_inode,
@@ -1219,8 +1198,6 @@ static int __exfat_rename(struct inode *old_parent_inode,
return -ENOENT;
}
- exfat_update_parent_info(ei, old_parent_inode);
-
exfat_chain_dup(&olddir, &ei->dir);
dentry = ei->entry;
@@ -1241,8 +1218,6 @@ static int __exfat_rename(struct inode *old_parent_inode,
goto out;
}
- exfat_update_parent_info(new_ei, new_parent_inode);
-
p_dir = &(new_ei->dir);
new_entry = new_ei->entry;
ep = exfat_get_dentry(sb, p_dir, new_entry, &new_bh);
From 9b002894b4c252169abc26720452bf3746114b20 Mon Sep 17 00:00:00 2001
From: Chung-Chiang Cheng <cccheng@synology.com>
Date: Wed, 6 Apr 2022 17:55:52 +0800
Subject: [PATCH 2/5] exfat: introduce mount option 'sys_tz'
EXFAT_TZ_VALID bit in {create,modify,access}_tz is corresponding to
OffsetValid field in exfat specification [1]. When this bit isn't
set, timestamps should be treated as having the same UTC offset as
the current local time.
Currently, there is an option 'time_offset' for users to specify the
UTC offset for this issue. This patch introduces a new mount option
'sys_tz' to use system timezone as time offset.
Link: [1] https://docs.microsoft.com/en-us/windows/win32/fileio/exfat-specification#74102-offsetvalid-field
Signed-off-by: Chung-Chiang Cheng <cccheng@synology.com>
Acked-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
fs/exfat/exfat_fs.h | 1 +
fs/exfat/misc.c | 10 ++++++++--
fs/exfat/super.c | 9 ++++++++-
3 files changed, 17 insertions(+), 3 deletions(-)
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index c6800b880920..82e507413291 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -203,6 +203,7 @@ struct exfat_mount_options {
/* on error: continue, panic, remount-ro */
enum exfat_error_mode errors;
unsigned utf8:1, /* Use of UTF-8 character set */
+ sys_tz:1, /* Use local timezone */
discard:1, /* Issue discard requests on deletions */
keep_last_dots:1; /* Keep trailing periods in paths */
int time_offset; /* Offset of timestamps from UTC (in minutes) */
diff --git a/fs/exfat/misc.c b/fs/exfat/misc.c
index d5bd8e6d9741..9380e0188b55 100644
--- a/fs/exfat/misc.c
+++ b/fs/exfat/misc.c
@@ -74,6 +74,13 @@ static void exfat_adjust_tz(struct timespec64 *ts, u8 tz_off)
ts->tv_sec += TIMEZONE_SEC(0x80 - tz_off);
}
+static inline int exfat_tz_offset(struct exfat_sb_info *sbi)
+{
+ if (sbi->options.sys_tz)
+ return -sys_tz.tz_minuteswest;
+ return sbi->options.time_offset;
+}
+
/* Convert a EXFAT time/date pair to a UNIX date (seconds since 1 1 70). */
void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts,
u8 tz, __le16 time, __le16 date, u8 time_cs)
@@ -96,8 +103,7 @@ void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts,
/* Adjust timezone to UTC0. */
exfat_adjust_tz(ts, tz & ~EXFAT_TZ_VALID);
else
- /* Convert from local time to UTC using time_offset. */
- ts->tv_sec -= sbi->options.time_offset * SECS_PER_MIN;
+ ts->tv_sec -= exfat_tz_offset(sbi) * SECS_PER_MIN;
}
/* Convert linear UNIX date to a EXFAT time/date pair. */
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index 8ca21e7917d1..3e0f67b2103e 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -170,7 +170,9 @@ static int exfat_show_options(struct seq_file *m, struct dentry *root)
seq_puts(m, ",discard");
if (opts->keep_last_dots)
seq_puts(m, ",keep_last_dots");
- if (opts->time_offset)
+ if (opts->sys_tz)
+ seq_puts(m, ",sys_tz");
+ else if (opts->time_offset)
seq_printf(m, ",time_offset=%d", opts->time_offset);
return 0;
}
@@ -214,6 +216,7 @@ enum {
Opt_errors,
Opt_discard,
Opt_keep_last_dots,
+ Opt_sys_tz,
Opt_time_offset,
/* Deprecated options */
@@ -241,6 +244,7 @@ static const struct fs_parameter_spec exfat_parameters[] = {
fsparam_enum("errors", Opt_errors, exfat_param_enums),
fsparam_flag("discard", Opt_discard),
fsparam_flag("keep_last_dots", Opt_keep_last_dots),
+ fsparam_flag("sys_tz", Opt_sys_tz),
fsparam_s32("time_offset", Opt_time_offset),
__fsparam(NULL, "utf8", Opt_utf8, fs_param_deprecated,
NULL),
@@ -298,6 +302,9 @@ static int exfat_parse_param(struct fs_context *fc, struct fs_parameter *param)
case Opt_keep_last_dots:
opts->keep_last_dots = 1;
break;
+ case Opt_sys_tz:
+ opts->sys_tz = 1;
+ break;
case Opt_time_offset:
/*
* Make the limit 24 just in case someone invents something
From 97d6fb1b48f5e6f6d58028593defe8a23641b0b4 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Tue, 12 Apr 2022 12:23:10 +0900
Subject: [PATCH 3/5] block: add sync_blockdev_range()
sync_blockdev_range() is to support syncing multiple sectors
with as few block device requests as possible, it is helpful
to make the block device to give full play to its performance.
Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Suggested-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Andy Wu <Andy.Wu@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Acked-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
block/bdev.c | 7 +++++++
include/linux/blkdev.h | 1 +
2 files changed, 8 insertions(+)
diff --git a/block/bdev.c b/block/bdev.c
index 13de871fa816..8b549b071bd6 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -200,6 +200,13 @@ int sync_blockdev(struct block_device *bdev)
}
EXPORT_SYMBOL(sync_blockdev);
+int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend)
+{
+ return filemap_write_and_wait_range(bdev->bd_inode->i_mapping,
+ lstart, lend);
+}
+EXPORT_SYMBOL(sync_blockdev_range);
+
/*
* Write out and wait upon all dirty data associated with this
* device. Filesystem data as well as the underlying block
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 60d016138997..331cc6918ee9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1547,6 +1547,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
#ifdef CONFIG_BLOCK
void invalidate_bdev(struct block_device *bdev);
int sync_blockdev(struct block_device *bdev);
+int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
int sync_blockdev_nowait(struct block_device *bdev);
void sync_bdevs(bool wait);
void printk_all_partitions(void);
From 1b6138385499507147e8f654840f4c39afe6adbf Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Tue, 12 Apr 2022 12:26:47 +0900
Subject: [PATCH 4/5] exfat: reduce block requests when zeroing a cluster
If 'dirsync' is enabled, when zeroing a cluster, submitting
sector by sector will generate many block requests, will
cause the block device to not fully perform its performance.
This commit makes the sectors in a cluster to be submitted in
once, it will reduce the number of block requests. This will
make the block device to give full play to its performance.
Test create 1000 directories on SD card with:
$ time (for ((i=0;i<1000;i++)); do mkdir dir${i}; done)
Performance has been improved by more than 73% on imx6q-sabrelite.
Cluster size Before After Improvement
64 KBytes 3m34.036s 0m56.052s 73.8%
128 KBytes 6m2.644s 1m13.354s 79.8%
256 KBytes 11m22.202s 1m39.451s 85.4%
imx6q-sabrelite:
- CPU: 792 MHz x4
- Memory: 1GB DDR3
- SD Card: SanDisk 8GB Class 4
Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Andy Wu <Andy.Wu@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
fs/exfat/fatent.c | 41 +++++++++++++++++------------------------
1 file changed, 17 insertions(+), 24 deletions(-)
diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c
index a3464e56a7e1..04e1126ce971 100644
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -6,6 +6,7 @@
#include <linux/slab.h>
#include <asm/unaligned.h>
#include <linux/buffer_head.h>
+#include <linux/blkdev.h>
#include "exfat_raw.h"
#include "exfat_fs.h"
@@ -274,10 +275,9 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu)
{
struct super_block *sb = dir->i_sb;
struct exfat_sb_info *sbi = EXFAT_SB(sb);
- struct buffer_head *bhs[MAX_BUF_PER_PAGE];
- int nr_bhs = MAX_BUF_PER_PAGE;
+ struct buffer_head *bh;
sector_t blknr, last_blknr;
- int err, i, n;
+ int i;
blknr = exfat_cluster_to_sector(sbi, clu);
last_blknr = blknr + sbi->sect_per_clus;
@@ -291,30 +291,23 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu)
}
/* Zeroing the unused blocks on this cluster */
- while (blknr < last_blknr) {
- for (n = 0; n < nr_bhs && blknr < last_blknr; n++, blknr++) {
- bhs[n] = sb_getblk(sb, blknr);
- if (!bhs[n]) {
- err = -ENOMEM;
- goto release_bhs;
- }
- memset(bhs[n]->b_data, 0, sb->s_blocksize);
- }
+ for (i = blknr; i < last_blknr; i++) {
+ bh = sb_getblk(sb, i);
+ if (!bh)
+ return -ENOMEM;
- err = exfat_update_bhs(bhs, n, IS_DIRSYNC(dir));
- if (err)
- goto release_bhs;
-
- for (i = 0; i < n; i++)
- brelse(bhs[i]);
+ memset(bh->b_data, 0, sb->s_blocksize);
+ set_buffer_uptodate(bh);
+ mark_buffer_dirty(bh);
+ brelse(bh);
}
- return 0;
-release_bhs:
- exfat_err(sb, "failed zeroed sect %llu\n", (unsigned long long)blknr);
- for (i = 0; i < n; i++)
- bforget(bhs[i]);
- return err;
+ if (IS_DIRSYNC(dir))
+ return sync_blockdev_range(sb->s_bdev,
+ EXFAT_BLK_TO_B(blknr, sb),
+ EXFAT_BLK_TO_B(last_blknr, sb) - 1);
+
+ return 0;
}
int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
From 64ba4b15e5c045f8b746c6da5fc9be9a6b00b61d Mon Sep 17 00:00:00 2001
From: Tadeusz Struk <tadeusz.struk@linaro.org>
Date: Tue, 17 May 2022 08:13:08 +0900
Subject: [PATCH 5/5] exfat: check if cluster num is valid
Syzbot reported slab-out-of-bounds read in exfat_clear_bitmap.
This was triggered by reproducer calling truncute with size 0,
which causes the following trace:
BUG: KASAN: slab-out-of-bounds in exfat_clear_bitmap+0x147/0x490 fs/exfat/balloc.c:174
Read of size 8 at addr ffff888115aa9508 by task syz-executor251/365
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack_lvl+0x1e2/0x24b lib/dump_stack.c:118
print_address_description+0x81/0x3c0 mm/kasan/report.c:233
__kasan_report mm/kasan/report.c:419 [inline]
kasan_report+0x1a4/0x1f0 mm/kasan/report.c:436
__asan_report_load8_noabort+0x14/0x20 mm/kasan/report_generic.c:309
exfat_clear_bitmap+0x147/0x490 fs/exfat/balloc.c:174
exfat_free_cluster+0x25a/0x4a0 fs/exfat/fatent.c:181
__exfat_truncate+0x99e/0xe00 fs/exfat/file.c:217
exfat_truncate+0x11b/0x4f0 fs/exfat/file.c:243
exfat_setattr+0xa03/0xd40 fs/exfat/file.c:339
notify_change+0xb76/0xe10 fs/attr.c:336
do_truncate+0x1ea/0x2d0 fs/open.c:65
Move the is_valid_cluster() helper from fatent.c to a common
header to make it reusable in other *.c files. And add is_valid_cluster()
to validate if cluster number is within valid range in exfat_clear_bitmap()
and exfat_set_bitmap().
Link: https://syzkaller.appspot.com/bug?id=50381fc73821ecae743b8cf24b4c9a04776f767c
Reported-by: syzbot+a4087e40b9c13aad7892@syzkaller.appspotmail.com
Fixes: 1e49a94cf707 ("exfat: add bitmap operations")
Cc: stable@vger.kernel.org # v5.7+
Signed-off-by: Tadeusz Struk <tadeusz.struk@linaro.org>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
fs/exfat/balloc.c | 8 ++++++--
fs/exfat/exfat_fs.h | 6 ++++++
fs/exfat/fatent.c | 6 ------
3 files changed, 12 insertions(+), 8 deletions(-)
diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c
index 03f142307174..9f42f25fab92 100644
--- a/fs/exfat/balloc.c
+++ b/fs/exfat/balloc.c
@@ -148,7 +148,9 @@ int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync)
struct super_block *sb = inode->i_sb;
struct exfat_sb_info *sbi = EXFAT_SB(sb);
- WARN_ON(clu < EXFAT_FIRST_CLUSTER);
+ if (!is_valid_cluster(sbi, clu))
+ return -EINVAL;
+
ent_idx = CLUSTER_TO_BITMAP_ENT(clu);
i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx);
b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx);
@@ -166,7 +168,9 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
struct exfat_sb_info *sbi = EXFAT_SB(sb);
struct exfat_mount_options *opts = &sbi->options;
- WARN_ON(clu < EXFAT_FIRST_CLUSTER);
+ if (!is_valid_cluster(sbi, clu))
+ return;
+
ent_idx = CLUSTER_TO_BITMAP_ENT(clu);
i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx);
b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx);
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 82e507413291..4a7a2308eb72 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -382,6 +382,12 @@ static inline int exfat_sector_to_cluster(struct exfat_sb_info *sbi,
EXFAT_RESERVED_CLUSTERS;
}
+static inline bool is_valid_cluster(struct exfat_sb_info *sbi,
+ unsigned int clus)
+{
+ return clus >= EXFAT_FIRST_CLUSTER && clus < sbi->num_clusters;
+}
+
/* super.c */
int exfat_set_volume_dirty(struct super_block *sb);
int exfat_clear_volume_dirty(struct super_block *sb);
diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c
index 04e1126ce971..9de6a6b844c9 100644
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -82,12 +82,6 @@ int exfat_ent_set(struct super_block *sb, unsigned int loc,
return 0;
}
-static inline bool is_valid_cluster(struct exfat_sb_info *sbi,
- unsigned int clus)
-{
- return clus >= EXFAT_FIRST_CLUSTER && clus < sbi->num_clusters;
-}
-
int exfat_ent_get(struct super_block *sb, unsigned int loc,
unsigned int *content)
{