e92aaf1b8a
Before this commit, VolumeDirty will be cleared first in writeback if 'dirsync' or 'sync' is not enabled. If the power is suddenly cut off after cleaning VolumeDirty but other updates are not written, the exFAT filesystem will not be able to detect the power failure in the next mount. And VolumeDirty will be set again but not cleared when updating the parent directory. It means that BootSector will be written at least once in each write-back, which will shorten the life of the device. Reviewed-by: Andy Wu <Andy.Wu@sony.com> Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com> Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com> Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
503 lines
13 KiB
C
503 lines
13 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* Copyright (C) 2012-2013 Samsung Electronics Co., Ltd.
|
|
*/
|
|
|
|
#include <linux/version.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/buffer_head.h>
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 11, 0)
|
|
#include <linux/cred.h>
|
|
#endif
|
|
#include <linux/compat.h>
|
|
#include <linux/blkdev.h>
|
|
|
|
#include "exfat_raw.h"
|
|
#include "exfat_fs.h"
|
|
|
|
static int exfat_cont_expand(struct inode *inode, loff_t size)
|
|
{
|
|
struct address_space *mapping = inode->i_mapping;
|
|
loff_t start = i_size_read(inode), count = size - i_size_read(inode);
|
|
int err, err2;
|
|
|
|
err = generic_cont_expand_simple(inode, size);
|
|
if (err)
|
|
return err;
|
|
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0)
|
|
inode->i_ctime = inode->i_mtime = current_time(inode);
|
|
#else
|
|
inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
|
|
#endif
|
|
mark_inode_dirty(inode);
|
|
|
|
if (!IS_SYNC(inode))
|
|
return 0;
|
|
|
|
err = filemap_fdatawrite_range(mapping, start, start + count - 1);
|
|
err2 = sync_mapping_buffers(mapping);
|
|
if (!err)
|
|
err = err2;
|
|
err2 = write_inode_now(inode, 1);
|
|
if (!err)
|
|
err = err2;
|
|
if (err)
|
|
return err;
|
|
|
|
return filemap_fdatawait_range(mapping, start, start + count - 1);
|
|
}
|
|
|
|
static bool exfat_allow_set_time(struct exfat_sb_info *sbi, struct inode *inode)
|
|
{
|
|
mode_t allow_utime = sbi->options.allow_utime;
|
|
|
|
if (!uid_eq(current_fsuid(), inode->i_uid)) {
|
|
if (in_group_p(inode->i_gid))
|
|
allow_utime >>= 3;
|
|
if (allow_utime & MAY_WRITE)
|
|
return true;
|
|
}
|
|
|
|
/* use a default check */
|
|
return false;
|
|
}
|
|
|
|
static int exfat_sanitize_mode(const struct exfat_sb_info *sbi,
|
|
struct inode *inode, umode_t *mode_ptr)
|
|
{
|
|
mode_t i_mode, mask, perm;
|
|
|
|
i_mode = inode->i_mode;
|
|
|
|
mask = (S_ISREG(i_mode) || S_ISLNK(i_mode)) ?
|
|
sbi->options.fs_fmask : sbi->options.fs_dmask;
|
|
perm = *mode_ptr & ~(S_IFMT | mask);
|
|
|
|
/* Of the r and x bits, all (subject to umask) must be present.*/
|
|
if ((perm & 0555) != (i_mode & 0555))
|
|
return -EPERM;
|
|
|
|
if (exfat_mode_can_hold_ro(inode)) {
|
|
/*
|
|
* Of the w bits, either all (subject to umask) or none must
|
|
* be present.
|
|
*/
|
|
if ((perm & 0222) && ((perm & 0222) != (0222 & ~mask)))
|
|
return -EPERM;
|
|
} else {
|
|
/*
|
|
* If exfat_mode_can_hold_ro(inode) is false, can't change
|
|
* w bits.
|
|
*/
|
|
if ((perm & 0222) != (0222 & ~mask))
|
|
return -EPERM;
|
|
}
|
|
|
|
*mode_ptr &= S_IFMT | perm;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* resize the file length */
|
|
int __exfat_truncate(struct inode *inode, loff_t new_size)
|
|
{
|
|
unsigned int num_clusters_new, num_clusters_phys;
|
|
unsigned int last_clu = EXFAT_FREE_CLUSTER;
|
|
struct exfat_chain clu;
|
|
struct super_block *sb = inode->i_sb;
|
|
struct exfat_sb_info *sbi = EXFAT_SB(sb);
|
|
struct exfat_inode_info *ei = EXFAT_I(inode);
|
|
int evict = (ei->dir.dir == DIR_DELETED) ? 1 : 0;
|
|
|
|
/* check if the given file ID is opened */
|
|
if (ei->type != TYPE_FILE && ei->type != TYPE_DIR)
|
|
return -EPERM;
|
|
|
|
exfat_set_volume_dirty(sb);
|
|
|
|
num_clusters_new = EXFAT_B_TO_CLU_ROUND_UP(i_size_read(inode), sbi);
|
|
num_clusters_phys = EXFAT_B_TO_CLU_ROUND_UP(ei->i_size_ondisk, sbi);
|
|
|
|
exfat_chain_set(&clu, ei->start_clu, num_clusters_phys, ei->flags);
|
|
|
|
if (new_size > 0) {
|
|
/*
|
|
* Truncate FAT chain num_clusters after the first cluster
|
|
* num_clusters = min(new, phys);
|
|
*/
|
|
unsigned int num_clusters =
|
|
min(num_clusters_new, num_clusters_phys);
|
|
|
|
/*
|
|
* Follow FAT chain
|
|
* (defensive coding - works fine even with corrupted FAT table
|
|
*/
|
|
if (clu.flags == ALLOC_NO_FAT_CHAIN) {
|
|
clu.dir += num_clusters;
|
|
clu.size -= num_clusters;
|
|
} else {
|
|
while (num_clusters > 0) {
|
|
last_clu = clu.dir;
|
|
if (exfat_get_next_cluster(sb, &(clu.dir)))
|
|
return -EIO;
|
|
|
|
num_clusters--;
|
|
clu.size--;
|
|
}
|
|
}
|
|
} else {
|
|
ei->flags = ALLOC_NO_FAT_CHAIN;
|
|
ei->start_clu = EXFAT_EOF_CLUSTER;
|
|
}
|
|
|
|
i_size_write(inode, new_size);
|
|
|
|
if (ei->type == TYPE_FILE)
|
|
ei->attr |= ATTR_ARCHIVE;
|
|
|
|
/* update the directory entry */
|
|
if (!evict) {
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 19, 0)
|
|
struct timespec64 ts;
|
|
#else
|
|
struct timespec ts;
|
|
#endif
|
|
struct exfat_dentry *ep, *ep2;
|
|
struct exfat_entry_set_cache *es;
|
|
int err;
|
|
|
|
es = exfat_get_dentry_set(sb, &(ei->dir), ei->entry,
|
|
ES_ALL_ENTRIES);
|
|
if (!es)
|
|
return -EIO;
|
|
ep = exfat_get_dentry_cached(es, 0);
|
|
ep2 = exfat_get_dentry_cached(es, 1);
|
|
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0)
|
|
ts = current_time(inode);
|
|
#else
|
|
ts = CURRENT_TIME_SEC;
|
|
#endif
|
|
exfat_set_entry_time(sbi, &ts,
|
|
&ep->dentry.file.modify_tz,
|
|
&ep->dentry.file.modify_time,
|
|
&ep->dentry.file.modify_date,
|
|
&ep->dentry.file.modify_time_cs);
|
|
ep->dentry.file.attr = cpu_to_le16(ei->attr);
|
|
|
|
/* File size should be zero if there is no cluster allocated */
|
|
if (ei->start_clu == EXFAT_EOF_CLUSTER) {
|
|
ep2->dentry.stream.valid_size = 0;
|
|
ep2->dentry.stream.size = 0;
|
|
} else {
|
|
ep2->dentry.stream.valid_size = cpu_to_le64(new_size);
|
|
ep2->dentry.stream.size = ep2->dentry.stream.valid_size;
|
|
}
|
|
|
|
if (new_size == 0) {
|
|
/* Any directory can not be truncated to zero */
|
|
WARN_ON(ei->type != TYPE_FILE);
|
|
|
|
ep2->dentry.stream.flags = ALLOC_FAT_CHAIN;
|
|
ep2->dentry.stream.start_clu = EXFAT_FREE_CLUSTER;
|
|
}
|
|
|
|
exfat_update_dir_chksum_with_entry_set(es);
|
|
err = exfat_free_dentry_set(es, inode_needs_sync(inode));
|
|
if (err)
|
|
return err;
|
|
}
|
|
|
|
/* cut off from the FAT chain */
|
|
if (ei->flags == ALLOC_FAT_CHAIN && last_clu != EXFAT_FREE_CLUSTER &&
|
|
last_clu != EXFAT_EOF_CLUSTER) {
|
|
if (exfat_ent_set(sb, last_clu, EXFAT_EOF_CLUSTER))
|
|
return -EIO;
|
|
}
|
|
|
|
/* invalidate cache and free the clusters */
|
|
/* clear exfat cache */
|
|
exfat_cache_inval_inode(inode);
|
|
|
|
/* hint information */
|
|
ei->hint_bmap.off = EXFAT_EOF_CLUSTER;
|
|
ei->hint_bmap.clu = EXFAT_EOF_CLUSTER;
|
|
|
|
/* hint_stat will be used if this is directory. */
|
|
ei->hint_stat.eidx = 0;
|
|
ei->hint_stat.clu = ei->start_clu;
|
|
ei->hint_femp.eidx = EXFAT_HINT_NONE;
|
|
|
|
/* free the clusters */
|
|
if (exfat_free_cluster(inode, &clu))
|
|
return -EIO;
|
|
|
|
return 0;
|
|
}
|
|
|
|
void exfat_truncate(struct inode *inode, loff_t size)
|
|
{
|
|
struct super_block *sb = inode->i_sb;
|
|
struct exfat_sb_info *sbi = EXFAT_SB(sb);
|
|
struct exfat_inode_info *ei = EXFAT_I(inode);
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 4, 0)
|
|
unsigned int blocksize = i_blocksize(inode);
|
|
#else
|
|
unsigned int blocksize = 1 << inode->i_blkbits;
|
|
#endif
|
|
loff_t aligned_size;
|
|
int err;
|
|
|
|
mutex_lock(&sbi->s_lock);
|
|
if (ei->start_clu == 0) {
|
|
/*
|
|
* Empty start_clu != ~0 (not allocated)
|
|
*/
|
|
exfat_fs_error(sb, "tried to truncate zeroed cluster.");
|
|
goto write_size;
|
|
}
|
|
|
|
err = __exfat_truncate(inode, i_size_read(inode));
|
|
if (err)
|
|
goto write_size;
|
|
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0)
|
|
inode->i_ctime = inode->i_mtime = current_time(inode);
|
|
#else
|
|
inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
|
|
#endif
|
|
if (IS_DIRSYNC(inode))
|
|
exfat_sync_inode(inode);
|
|
else
|
|
mark_inode_dirty(inode);
|
|
|
|
inode->i_blocks = ((i_size_read(inode) + (sbi->cluster_size - 1)) &
|
|
~((loff_t)sbi->cluster_size - 1)) >> inode->i_blkbits;
|
|
write_size:
|
|
aligned_size = i_size_read(inode);
|
|
if (aligned_size & (blocksize - 1)) {
|
|
aligned_size |= (blocksize - 1);
|
|
aligned_size++;
|
|
}
|
|
|
|
if (ei->i_size_ondisk > i_size_read(inode))
|
|
ei->i_size_ondisk = aligned_size;
|
|
|
|
if (ei->i_size_aligned > i_size_read(inode))
|
|
ei->i_size_aligned = aligned_size;
|
|
mutex_unlock(&sbi->s_lock);
|
|
}
|
|
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 12, 0)
|
|
int exfat_getattr(struct user_namespace *mnt_uerns, const struct path *path,
|
|
struct kstat *stat, unsigned int request_mask,
|
|
unsigned int query_flags)
|
|
#else
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 11, 0)
|
|
int exfat_getattr(const struct path *path, struct kstat *stat,
|
|
unsigned int request_mask, unsigned int query_flags)
|
|
#else
|
|
int exfat_getattr(struct vfsmount *mnt, struct dentry *dentry,
|
|
struct kstat *stat)
|
|
#endif
|
|
#endif
|
|
{
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 11, 0)
|
|
struct inode *inode = d_backing_inode(path->dentry);
|
|
struct exfat_inode_info *ei = EXFAT_I(inode);
|
|
#else
|
|
struct inode *inode = d_inode(dentry);
|
|
#endif
|
|
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 12, 0)
|
|
generic_fillattr(&init_user_ns, inode, stat);
|
|
#else
|
|
generic_fillattr(inode, stat);
|
|
#endif
|
|
exfat_truncate_atime(&stat->atime);
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 11, 0)
|
|
stat->result_mask |= STATX_BTIME;
|
|
stat->btime.tv_sec = ei->i_crtime.tv_sec;
|
|
stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
|
|
#endif
|
|
stat->blksize = EXFAT_SB(inode->i_sb)->cluster_size;
|
|
return 0;
|
|
}
|
|
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 12, 0)
|
|
int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
|
|
struct iattr *attr)
|
|
#else
|
|
int exfat_setattr(struct dentry *dentry, struct iattr *attr)
|
|
#endif
|
|
{
|
|
struct exfat_sb_info *sbi = EXFAT_SB(dentry->d_sb);
|
|
struct inode *inode = dentry->d_inode;
|
|
unsigned int ia_valid;
|
|
int error;
|
|
|
|
if ((attr->ia_valid & ATTR_SIZE) &&
|
|
attr->ia_size > i_size_read(inode)) {
|
|
error = exfat_cont_expand(inode, attr->ia_size);
|
|
if (error || attr->ia_valid == ATTR_SIZE)
|
|
return error;
|
|
attr->ia_valid &= ~ATTR_SIZE;
|
|
}
|
|
|
|
/* Check for setting the inode time. */
|
|
ia_valid = attr->ia_valid;
|
|
if ((ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) &&
|
|
exfat_allow_set_time(sbi, inode)) {
|
|
attr->ia_valid &= ~(ATTR_MTIME_SET | ATTR_ATIME_SET |
|
|
ATTR_TIMES_SET);
|
|
}
|
|
|
|
#if ((LINUX_VERSION_CODE < KERNEL_VERSION(4, 2, 0)) && \
|
|
(LINUX_VERSION_CODE >= KERNEL_VERSION(4, 1, 37))) || \
|
|
(LINUX_VERSION_CODE >= KERNEL_VERSION(4, 9, 0))
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 12, 0)
|
|
error = setattr_prepare(&init_user_ns, dentry, attr);
|
|
#else
|
|
error = setattr_prepare(dentry, attr);
|
|
#endif
|
|
#else
|
|
error = inode_change_ok(inode, attr);
|
|
#endif
|
|
attr->ia_valid = ia_valid;
|
|
if (error)
|
|
goto out;
|
|
|
|
if (((attr->ia_valid & ATTR_UID) &&
|
|
!uid_eq(attr->ia_uid, sbi->options.fs_uid)) ||
|
|
((attr->ia_valid & ATTR_GID) &&
|
|
!gid_eq(attr->ia_gid, sbi->options.fs_gid)) ||
|
|
((attr->ia_valid & ATTR_MODE) &&
|
|
(attr->ia_mode & ~(S_IFREG | S_IFLNK | S_IFDIR | 0777)))) {
|
|
error = -EPERM;
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* We don't return -EPERM here. Yes, strange, but this is too
|
|
* old behavior.
|
|
*/
|
|
if (attr->ia_valid & ATTR_MODE) {
|
|
if (exfat_sanitize_mode(sbi, inode, &attr->ia_mode) < 0)
|
|
attr->ia_valid &= ~ATTR_MODE;
|
|
}
|
|
|
|
if (attr->ia_valid & ATTR_SIZE) {
|
|
error = exfat_block_truncate_page(inode, attr->ia_size);
|
|
if (error)
|
|
goto out;
|
|
|
|
down_write(&EXFAT_I(inode)->truncate_lock);
|
|
truncate_setsize(inode, attr->ia_size);
|
|
exfat_truncate(inode, attr->ia_size);
|
|
up_write(&EXFAT_I(inode)->truncate_lock);
|
|
}
|
|
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 12, 0)
|
|
setattr_copy(&init_user_ns, inode, attr);
|
|
#else
|
|
setattr_copy(inode, attr);
|
|
#endif
|
|
exfat_truncate_atime(&inode->i_atime);
|
|
mark_inode_dirty(inode);
|
|
|
|
out:
|
|
return error;
|
|
}
|
|
|
|
static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg)
|
|
{
|
|
struct request_queue *q = bdev_get_queue(inode->i_sb->s_bdev);
|
|
struct fstrim_range range;
|
|
int ret = 0;
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
if (!blk_queue_discard(q))
|
|
return -EOPNOTSUPP;
|
|
|
|
if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range)))
|
|
return -EFAULT;
|
|
|
|
range.minlen = max_t(unsigned int, range.minlen,
|
|
q->limits.discard_granularity);
|
|
|
|
ret = exfat_trim_fs(inode, &range);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range)))
|
|
return -EFAULT;
|
|
|
|
return 0;
|
|
}
|
|
|
|
long exfat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
|
|
{
|
|
struct inode *inode = file_inode(filp);
|
|
|
|
switch (cmd) {
|
|
case FITRIM:
|
|
return exfat_ioctl_fitrim(inode, arg);
|
|
default:
|
|
return -ENOTTY;
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
long exfat_compat_ioctl(struct file *filp, unsigned int cmd,
|
|
unsigned long arg)
|
|
{
|
|
return exfat_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
|
|
}
|
|
#endif
|
|
|
|
int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
|
|
{
|
|
struct inode *inode = filp->f_mapping->host;
|
|
int err;
|
|
|
|
err = __generic_file_fsync(filp, start, end, datasync);
|
|
if (err)
|
|
return err;
|
|
|
|
err = sync_blockdev(inode->i_sb->s_bdev);
|
|
if (err)
|
|
return err;
|
|
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 12, 0)
|
|
return blkdev_issue_flush(inode->i_sb->s_bdev);
|
|
#else
|
|
#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 8, 0)
|
|
return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
|
|
#else
|
|
return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
|
|
#endif
|
|
#endif
|
|
}
|
|
|
|
const struct file_operations exfat_file_operations = {
|
|
.llseek = generic_file_llseek,
|
|
.read_iter = generic_file_read_iter,
|
|
.write_iter = generic_file_write_iter,
|
|
.unlocked_ioctl = exfat_ioctl,
|
|
#ifdef CONFIG_COMPAT
|
|
.compat_ioctl = exfat_compat_ioctl,
|
|
#endif
|
|
.mmap = generic_file_mmap,
|
|
.fsync = exfat_file_fsync,
|
|
.splice_read = generic_file_splice_read,
|
|
.splice_write = iter_file_splice_write,
|
|
};
|
|
|
|
const struct inode_operations exfat_file_inode_operations = {
|
|
.setattr = exfat_setattr,
|
|
.getattr = exfat_getattr,
|
|
};
|