static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
{
struct inode *inode = file_inode(file);
struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
int is_dir = S_ISDIR(inode->i_mode);
u32 attr, oldattr;
struct iattr ia;
int err;
err = get_user(attr, user_attr);
if (err)
goto out;
err = mnt_want_write_file(file);
if (err)
goto out;
inode_lock(inode);
/*
* ATTR_VOLUME and ATTR_DIR cannot be changed; this also
* prevents the user from turning us into a VFAT
* longname entry. Also, we obviously can't set
* any of the NTFS attributes in the high 24 bits.
*/
attr &= 0xff & ~(ATTR_VOLUME | ATTR_DIR);
/* Merge in ATTR_VOLUME and ATTR_DIR */
attr |= (MSDOS_I(inode)->i_attrs & ATTR_VOLUME) |
(is_dir ? ATTR_DIR : 0);
oldattr = fat_make_attrs(inode);
/* Equivalent to a chmod() */
ia.ia_valid = ATTR_MODE | ATTR_CTIME;
ia.ia_ctime = current_time(inode);
if (is_dir)
ia.ia_mode = fat_make_mode(sbi, attr, S_IRWXUGO);
else {
ia.ia_mode = fat_make_mode(sbi, attr,
S_IRUGO | S_IWUGO | (inode->i_mode & S_IXUGO));
}
/* The root directory has no attributes */
if (inode->i_ino == MSDOS_ROOT_INO && attr != ATTR_DIR) {
err = -EINVAL;
goto out_unlock_inode;
}
if (sbi->options.sys_immutable &&
((attr | oldattr) & ATTR_SYS) &&
!capable(CAP_LINUX_IMMUTABLE)) {
err = -EPERM;
goto out_unlock_inode;
}
/*
* The security check is questionable... We single
* out the RO attribute for checking by the security
* module, just because it maps to a file mode.
*/
err = security_inode_setattr(file->f_path.dentry, &ia);
if (err)
goto out_unlock_inode;
/* This MUST be done before doing anything irreversible... */
err = fat_setattr(file->f_path.dentry, &ia);
if (err)
goto out_unlock_inode;
fsnotify_change(file->f_path.dentry, ia.ia_valid);
if (sbi->options.sys_immutable) {
if (attr & ATTR_SYS)
inode->i_flags |= S_IMMUTABLE;
else
inode->i_flags &= ~S_IMMUTABLE;
}
fat_save_attrs(inode, attr);
mark_inode_dirty(inode);
out_unlock_inode:
inode_unlock(inode);
mnt_drop_write_file(file);
out:
return err;
}
int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len)
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
__u64 logical = 0, phys = 0, size = 0;
__u32 flags = 0;
loff_t isize;
sector_t blkoff, end_blkoff;
sector_t delalloc_blkoff;
unsigned long delalloc_blklen;
unsigned int blkbits = inode->i_blkbits;
int ret, n;
ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
if (ret)
return ret;
inode_lock(inode);
isize = i_size_read(inode);
blkoff = start >> blkbits;
end_blkoff = (start + len - 1) >> blkbits;
delalloc_blklen = nilfs_find_uncommitted_extent(inode, blkoff,
&delalloc_blkoff);
do {
__u64 blkphy;
unsigned int maxblocks;
if (delalloc_blklen && blkoff == delalloc_blkoff) {
if (size) {
/* End of the current extent */
ret = fiemap_fill_next_extent(
fieinfo, logical, phys, size, flags);
if (ret)
break;
}
if (blkoff > end_blkoff)
break;
flags = FIEMAP_EXTENT_MERGED | FIEMAP_EXTENT_DELALLOC;
logical = blkoff << blkbits;
phys = 0;
size = delalloc_blklen << blkbits;
blkoff = delalloc_blkoff + delalloc_blklen;
delalloc_blklen = nilfs_find_uncommitted_extent(
inode, blkoff, &delalloc_blkoff);
continue;
}
/*
* Limit the number of blocks that we look up so as
* not to get into the next delayed allocation extent.
*/
maxblocks = INT_MAX;
if (delalloc_blklen)
maxblocks = min_t(sector_t, delalloc_blkoff - blkoff,
maxblocks);
blkphy = 0;
down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
n = nilfs_bmap_lookup_contig(
NILFS_I(inode)->i_bmap, blkoff, &blkphy, maxblocks);
up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
if (n < 0) {
int past_eof;
if (unlikely(n != -ENOENT))
break; /* error */
/* HOLE */
blkoff++;
past_eof = ((blkoff << blkbits) >= isize);
if (size) {
/* End of the current extent */
if (past_eof)
flags |= FIEMAP_EXTENT_LAST;
ret = fiemap_fill_next_extent(
fieinfo, logical, phys, size, flags);
if (ret)
break;
size = 0;
}
if (blkoff > end_blkoff || past_eof)
break;
} else {
if (size) {
if (phys && blkphy << blkbits == phys + size) {
/* The current extent goes on */
size += n << blkbits;
} else {
/* Terminate the current extent */
ret = fiemap_fill_next_extent(
fieinfo, logical, phys, size,
flags);
if (ret || blkoff > end_blkoff)
break;
/* Start another extent */
flags = FIEMAP_EXTENT_MERGED;
logical = blkoff << blkbits;
phys = blkphy << blkbits;
size = n << blkbits;
}
} else {
/* Start a new extent */
flags = FIEMAP_EXTENT_MERGED;
logical = blkoff << blkbits;
phys = blkphy << blkbits;
size = n << blkbits;
}
blkoff += n;
}
cond_resched();
} while (true);
/* If ret is 1 then we just hit the end of the extent array */
if (ret == 1)
ret = 0;
inode_unlock(inode);
return ret;
}
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t ino = inode->i_ino;
int ret = 0;
bool need_cp = false;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
if (unlikely(f2fs_readonly(inode->i_sb)))
return 0;
trace_f2fs_sync_file_enter(inode);
/* if fdatasync is triggered, let's do in-place-update */
if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
set_inode_flag(fi, FI_NEED_IPU);
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
clear_inode_flag(fi, FI_NEED_IPU);
if (ret) {
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
return ret;
}
/* if the inode is dirty, let's recover all the time */
if (!datasync) {
f2fs_write_inode(inode, NULL);
goto go_write;
}
/*
* if there is no written data, don't waste time to write recovery info.
*/
if (!is_inode_flag_set(fi, FI_APPEND_WRITE) &&
!exist_written_data(sbi, ino, APPEND_INO)) {
/* it may call write_inode just prior to fsync */
if (need_inode_page_update(sbi, ino))
goto go_write;
if (is_inode_flag_set(fi, FI_UPDATE_WRITE) ||
exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
}
go_write:
/*
* Both of fdatasync() and fsync() are able to be recovered from
* sudden-power-off.
*/
down_read(&fi->i_sem);
need_cp = need_do_checkpoint(inode);
up_read(&fi->i_sem);
if (need_cp) {
/* all the dirty node pages should be flushed for POR */
ret = f2fs_sync_fs(inode->i_sb, 1);
/*
* We've secured consistency through sync_fs. Following pino
* will be used only for fsynced inodes after checkpoint.
*/
try_to_fix_pino(inode);
clear_inode_flag(fi, FI_APPEND_WRITE);
clear_inode_flag(fi, FI_UPDATE_WRITE);
goto out;
}
sync_nodes:
sync_node_pages(sbi, ino, &wbc);
/* if cp_error was enabled, we should avoid infinite loop */
if (unlikely(f2fs_cp_error(sbi))) {
ret = -EIO;
goto out;
}
if (need_inode_block_update(sbi, ino)) {
mark_inode_dirty_sync(inode);
f2fs_write_inode(inode, NULL);
goto sync_nodes;
}
ret = wait_on_node_pages_writeback(sbi, ino);
if (ret)
goto out;
/* once recovery info is written, don't need to tack this */
remove_ino_entry(sbi, ino, APPEND_INO);
clear_inode_flag(fi, FI_APPEND_WRITE);
flush_out:
remove_ino_entry(sbi, ino, UPDATE_INO);
clear_inode_flag(fi, FI_UPDATE_WRITE);
ret = f2fs_issue_flush(sbi);
f2fs_update_time(sbi, REQ_TIME);
out:
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
f2fs_trace_ios(NULL, 1);
return ret;
}
static pgoff_t __get_first_dirty_index(struct address_space *mapping,
pgoff_t pgofs, int whence)
{
struct pagevec pvec;
int nr_pages;
if (whence != SEEK_DATA)
return 0;
/* find first dirty page index */
pagevec_init(&pvec, 0);
nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
PAGECACHE_TAG_DIRTY, 1);
pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX;
pagevec_release(&pvec);
return pgofs;
}
static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
int whence)
{
switch (whence) {
case SEEK_DATA:
if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
(blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
return true;
break;
case SEEK_HOLE:
if (blkaddr == NULL_ADDR)
return true;
break;
}
return false;
}
static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes = inode->i_sb->s_maxbytes;
struct dnode_of_data dn;
pgoff_t pgofs, end_offset, dirty;
loff_t data_ofs = offset;
loff_t isize;
int err = 0;
inode_lock(inode);
isize = i_size_read(inode);
if (offset >= isize)
goto fail;
/* handle inline data case */
if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
if (whence == SEEK_HOLE)
data_ofs = isize;
goto found;
}
pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);
dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
if (err && err != -ENOENT) {
goto fail;
} else if (err == -ENOENT) {
/* direct node does not exists */
if (whence == SEEK_DATA) {
pgofs = get_next_page_offset(&dn, pgofs);
continue;
} else {
goto found;
}
}
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
/* find data/hole in dnode block */
for (; dn.ofs_in_node < end_offset;
dn.ofs_in_node++, pgofs++,
data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
block_t blkaddr;
blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
if (__found_offset(blkaddr, dirty, pgofs, whence)) {
f2fs_put_dnode(&dn);
goto found;
}
}
f2fs_put_dnode(&dn);
}
if (whence == SEEK_DATA)
goto fail;
found:
if (whence == SEEK_HOLE && data_ofs > isize)
data_ofs = isize;
inode_unlock(inode);
return vfs_setpos(file, data_ofs, maxbytes);
fail:
inode_unlock(inode);
return -ENXIO;
}
static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes = inode->i_sb->s_maxbytes;
switch (whence) {
case SEEK_SET:
case SEEK_CUR:
case SEEK_END:
return generic_file_llseek_size(file, offset, whence,
maxbytes, i_size_read(inode));
case SEEK_DATA:
case SEEK_HOLE:
if (offset < 0)
return -ENXIO;
return f2fs_seek_block(file, offset, whence);
}
return -EINVAL;
}
static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file_inode(file);
int err;
if (f2fs_encrypted_inode(inode)) {
err = fscrypt_get_encryption_info(inode);
if (err)
return 0;
if (!f2fs_encrypted_inode(inode))
return -ENOKEY;
}
/* we don't need to use inline_data strictly */
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
file_accessed(file);
vma->vm_ops = &f2fs_file_vm_ops;
return 0;
}
static int f2fs_file_open(struct inode *inode, struct file *filp)
{
int ret = generic_file_open(inode, filp);
struct inode *dir = filp->f_path.dentry->d_parent->d_inode;
if (!ret && f2fs_encrypted_inode(inode)) {
ret = fscrypt_get_encryption_info(inode);
if (ret)
return -EACCES;
if (!fscrypt_has_encryption_key(inode))
return -ENOKEY;
}
if (f2fs_encrypted_inode(dir) &&
!fscrypt_has_permitted_context(dir, inode))
return -EPERM;
return ret;
}
long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct ext2_inode_info *ei = EXT2_I(inode);
unsigned int flags;
unsigned short rsv_window_size;
int ret;
ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case EXT2_IOC_GETFLAGS:
flags = ei->i_flags & EXT2_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT2_IOC_SETFLAGS: {
unsigned int oldflags;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
if (!inode_owner_or_capable(inode)) {
ret = -EACCES;
goto setflags_out;
}
if (get_user(flags, (int __user *) arg)) {
ret = -EFAULT;
goto setflags_out;
}
flags = ext2_mask_flags(inode->i_mode, flags);
inode_lock(inode);
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode)) {
inode_unlock(inode);
ret = -EPERM;
goto setflags_out;
}
oldflags = ei->i_flags;
/*
* The IMMUTABLE and APPEND_ONLY flags can only be changed by
* the relevant capability.
*
* This test looks nicer. Thanks to Pauline Middelink
*/
if ((flags ^ oldflags) & (EXT2_APPEND_FL | EXT2_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE)) {
inode_unlock(inode);
ret = -EPERM;
goto setflags_out;
}
}
flags = flags & EXT2_FL_USER_MODIFIABLE;
flags |= oldflags & ~EXT2_FL_USER_MODIFIABLE;
ei->i_flags = flags;
ext2_set_inode_flags(inode);
inode->i_ctime = current_time(inode);
inode_unlock(inode);
mark_inode_dirty(inode);
setflags_out:
mnt_drop_write_file(filp);
return ret;
}
case EXT2_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *) arg);
case EXT2_IOC_SETVERSION: {
__u32 generation;
if (!inode_owner_or_capable(inode))
return -EPERM;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
if (get_user(generation, (int __user *) arg)) {
ret = -EFAULT;
goto setversion_out;
}
inode_lock(inode);
inode->i_ctime = current_time(inode);
inode->i_generation = generation;
inode_unlock(inode);
mark_inode_dirty(inode);
setversion_out:
mnt_drop_write_file(filp);
return ret;
}
case EXT2_IOC_GETRSVSZ:
if (test_opt(inode->i_sb, RESERVATION)
&& S_ISREG(inode->i_mode)
&& ei->i_block_alloc_info) {
rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size;
return put_user(rsv_window_size, (int __user *)arg);
}
return -ENOTTY;
case EXT2_IOC_SETRSVSZ: {
if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
return -ENOTTY;
if (!inode_owner_or_capable(inode))
return -EACCES;
if (get_user(rsv_window_size, (int __user *)arg))
return -EFAULT;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
if (rsv_window_size > EXT2_MAX_RESERVE_BLOCKS)
rsv_window_size = EXT2_MAX_RESERVE_BLOCKS;
/*
* need to allocate reservation structure for this inode
* before set the window size
*/
/*
* XXX What lock should protect the rsv_goal_size?
* Accessed in ext2_get_block only. ext3 uses i_truncate.
*/
mutex_lock(&ei->truncate_mutex);
if (!ei->i_block_alloc_info)
ext2_init_block_alloc_info(inode);
if (ei->i_block_alloc_info){
struct ext2_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
rsv->rsv_goal_size = rsv_window_size;
}
mutex_unlock(&ei->truncate_mutex);
mnt_drop_write_file(filp);
return 0;
}
default:
return -ENOTTY;
}
}
static void unlock_dir(struct dentry *dir)
{
inode_unlock(d_inode(dir));
dput(dir);
}
static int nfs42_clone_file_range(struct file *src_file, loff_t src_off,
struct file *dst_file, loff_t dst_off, u64 count)
{
struct inode *dst_inode = file_inode(dst_file);
struct nfs_server *server = NFS_SERVER(dst_inode);
struct inode *src_inode = file_inode(src_file);
unsigned int bs = server->clone_blksize;
bool same_inode = false;
int ret;
/* check alignment w.r.t. clone_blksize */
ret = -EINVAL;
if (bs) {
if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs))
goto out;
if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count))
goto out;
}
if (src_inode == dst_inode)
same_inode = true;
/* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
if (same_inode) {
inode_lock(src_inode);
} else if (dst_inode < src_inode) {
inode_lock_nested(dst_inode, I_MUTEX_PARENT);
inode_lock_nested(src_inode, I_MUTEX_CHILD);
} else {
inode_lock_nested(src_inode, I_MUTEX_PARENT);
inode_lock_nested(dst_inode, I_MUTEX_CHILD);
}
/* flush all pending writes on both src and dst so that server
* has the latest data */
ret = nfs_sync_inode(src_inode);
if (ret)
goto out_unlock;
ret = nfs_sync_inode(dst_inode);
if (ret)
goto out_unlock;
ret = nfs42_proc_clone(src_file, dst_file, src_off, dst_off, count);
/* truncate inode page cache of the dst range so that future reads can fetch
* new data from server */
if (!ret)
truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1);
out_unlock:
if (same_inode) {
inode_unlock(src_inode);
} else if (dst_inode < src_inode) {
inode_unlock(src_inode);
inode_unlock(dst_inode);
} else {
inode_unlock(dst_inode);
inode_unlock(src_inode);
}
out:
return ret;
}
/*
* reiserfs_unpack
* Function try to convert tail from direct item into indirect.
* It set up nopack attribute in the REISERFS_I(inode)->nopack
*/
int reiserfs_unpack(struct inode *inode, struct file *filp)
{
int retval = 0;
int index;
struct page *page;
struct address_space *mapping;
unsigned long write_from;
unsigned long blocksize = inode->i_sb->s_blocksize;
if (inode->i_size == 0) {
REISERFS_I(inode)->i_flags |= i_nopack_mask;
return 0;
}
/* ioctl already done */
if (REISERFS_I(inode)->i_flags & i_nopack_mask) {
return 0;
}
/* we need to make sure nobody is changing the file size beneath us */
{
int depth = reiserfs_write_unlock_nested(inode->i_sb);
inode_lock(inode);
reiserfs_write_lock_nested(inode->i_sb, depth);
}
reiserfs_write_lock(inode->i_sb);
write_from = inode->i_size & (blocksize - 1);
/* if we are on a block boundary, we are already unpacked. */
if (write_from == 0) {
REISERFS_I(inode)->i_flags |= i_nopack_mask;
goto out;
}
/*
* we unpack by finding the page with the tail, and calling
* __reiserfs_write_begin on that page. This will force a
* reiserfs_get_block to unpack the tail for us.
*/
index = inode->i_size >> PAGE_SHIFT;
mapping = inode->i_mapping;
page = grab_cache_page(mapping, index);
retval = -ENOMEM;
if (!page) {
goto out;
}
retval = __reiserfs_write_begin(page, write_from, 0);
if (retval)
goto out_unlock;
/* conversion can change page contents, must flush */
flush_dcache_page(page);
retval = reiserfs_commit_write(NULL, page, write_from, write_from);
REISERFS_I(inode)->i_flags |= i_nopack_mask;
out_unlock:
unlock_page(page);
put_page(page);
out:
inode_unlock(inode);
reiserfs_write_unlock(inode->i_sb);
return retval;
}
int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *uarg)
{
int err, e;
unsigned char dmsg;
struct au_mvd_args *args;
struct inode *inode;
inode = d_inode(dentry);
err = -EPERM;
if (unlikely(!capable(CAP_SYS_ADMIN)))
goto out;
err = -ENOMEM;
args = kmalloc(sizeof(*args), GFP_NOFS);
if (unlikely(!args))
goto out;
err = copy_from_user(&args->mvdown, uarg, sizeof(args->mvdown));
if (!err)
err = !access_ok(VERIFY_WRITE, uarg, sizeof(*uarg));
if (unlikely(err)) {
err = -EFAULT;
AuTraceErr(err);
goto out_free;
}
AuDbg("flags 0x%x\n", args->mvdown.flags);
args->mvdown.flags &= ~(AUFS_MVDOWN_ROLOWER_R | AUFS_MVDOWN_ROUPPER_R);
args->mvdown.au_errno = 0;
args->dentry = dentry;
args->inode = inode;
args->sb = dentry->d_sb;
err = -ENOENT;
dmsg = !!(args->mvdown.flags & AUFS_MVDOWN_DMSG);
args->parent = dget_parent(dentry);
args->dir = d_inode(args->parent);
inode_lock_nested(args->dir, I_MUTEX_PARENT);
dput(args->parent);
if (unlikely(args->parent != dentry->d_parent)) {
AU_MVD_PR(dmsg, "parent dir is moved\n");
goto out_dir;
}
inode_lock_nested(inode, I_MUTEX_CHILD);
err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_NOPLMW);
if (unlikely(err))
goto out_inode;
di_write_lock_parent(args->parent);
err = au_mvd_args(dmsg, args);
if (unlikely(err))
goto out_parent;
err = au_do_mvdown(dmsg, args);
if (unlikely(err))
goto out_parent;
au_cpup_attr_timesizes(args->dir);
au_cpup_attr_timesizes(inode);
if (!(args->mvdown.flags & AUFS_MVDOWN_KUPPER))
au_cpup_igen(inode, au_h_iptr(inode, args->mvd_bdst));
/* au_digen_dec(dentry); */
out_parent:
di_write_unlock(args->parent);
aufs_read_unlock(dentry, AuLock_DW);
out_inode:
inode_unlock(inode);
out_dir:
inode_unlock(args->dir);
out_free:
e = copy_to_user(uarg, &args->mvdown, sizeof(args->mvdown));
if (unlikely(e))
err = -EFAULT;
kfree(args);
out:
AuTraceErr(err);
return err;
}
/*
* Extend the filesystem to the new number of clusters specified. This entry
* point is only used to extend the current filesystem to the end of the last
* existing group.
*/
int ocfs2_group_extend(struct inode * inode, int new_clusters)
{
int ret;
handle_t *handle;
struct buffer_head *main_bm_bh = NULL;
struct buffer_head *group_bh = NULL;
struct inode *main_bm_inode = NULL;
struct ocfs2_dinode *fe = NULL;
struct ocfs2_group_desc *group = NULL;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
u16 cl_bpc;
u32 first_new_cluster;
u64 lgd_blkno;
if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
return -EROFS;
if (new_clusters < 0)
return -EINVAL;
else if (new_clusters == 0)
return 0;
main_bm_inode = ocfs2_get_system_file_inode(osb,
GLOBAL_BITMAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT);
if (!main_bm_inode) {
ret = -EINVAL;
mlog_errno(ret);
goto out;
}
inode_lock(main_bm_inode);
ret = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 1);
if (ret < 0) {
mlog_errno(ret);
goto out_mutex;
}
fe = (struct ocfs2_dinode *)main_bm_bh->b_data;
/* main_bm_bh is validated by inode read inside ocfs2_inode_lock(),
* so any corruption is a code bug. */
BUG_ON(!OCFS2_IS_VALID_DINODE(fe));
if (le16_to_cpu(fe->id2.i_chain.cl_cpg) !=
ocfs2_group_bitmap_size(osb->sb, 0,
osb->s_feature_incompat) * 8) {
mlog(ML_ERROR, "The disk is too old and small. "
"Force to do offline resize.");
ret = -EINVAL;
goto out_unlock;
}
first_new_cluster = le32_to_cpu(fe->i_clusters);
lgd_blkno = ocfs2_which_cluster_group(main_bm_inode,
first_new_cluster - 1);
ret = ocfs2_read_group_descriptor(main_bm_inode, fe, lgd_blkno,
&group_bh);
if (ret < 0) {
mlog_errno(ret);
goto out_unlock;
}
group = (struct ocfs2_group_desc *)group_bh->b_data;
cl_bpc = le16_to_cpu(fe->id2.i_chain.cl_bpc);
if (le16_to_cpu(group->bg_bits) / cl_bpc + new_clusters >
le16_to_cpu(fe->id2.i_chain.cl_cpg)) {
ret = -EINVAL;
goto out_unlock;
}
trace_ocfs2_group_extend(
(unsigned long long)le64_to_cpu(group->bg_blkno), new_clusters);
handle = ocfs2_start_trans(osb, OCFS2_GROUP_EXTEND_CREDITS);
if (IS_ERR(handle)) {
mlog_errno(PTR_ERR(handle));
ret = -EINVAL;
goto out_unlock;
}
/* update the last group descriptor and inode. */
ret = ocfs2_update_last_group_and_inode(handle, main_bm_inode,
main_bm_bh, group_bh,
first_new_cluster,
new_clusters);
if (ret) {
mlog_errno(ret);
goto out_commit;
}
ocfs2_update_super_and_backups(main_bm_inode, new_clusters);
out_commit:
ocfs2_commit_trans(osb, handle);
out_unlock:
brelse(group_bh);
brelse(main_bm_bh);
ocfs2_inode_unlock(main_bm_inode, 1);
out_mutex:
inode_unlock(main_bm_inode);
iput(main_bm_inode);
out:
return ret;
}
/* Add a new group descriptor to global_bitmap. */
int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input)
{
int ret;
handle_t *handle;
struct buffer_head *main_bm_bh = NULL;
struct inode *main_bm_inode = NULL;
struct ocfs2_dinode *fe = NULL;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct buffer_head *group_bh = NULL;
struct ocfs2_group_desc *group = NULL;
struct ocfs2_chain_list *cl;
struct ocfs2_chain_rec *cr;
u16 cl_bpc;
u64 bg_ptr;
if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
return -EROFS;
main_bm_inode = ocfs2_get_system_file_inode(osb,
GLOBAL_BITMAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT);
if (!main_bm_inode) {
ret = -EINVAL;
mlog_errno(ret);
goto out;
}
inode_lock(main_bm_inode);
ret = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 1);
if (ret < 0) {
mlog_errno(ret);
goto out_mutex;
}
fe = (struct ocfs2_dinode *)main_bm_bh->b_data;
if (le16_to_cpu(fe->id2.i_chain.cl_cpg) !=
ocfs2_group_bitmap_size(osb->sb, 0,
osb->s_feature_incompat) * 8) {
mlog(ML_ERROR, "The disk is too old and small."
" Force to do offline resize.");
ret = -EINVAL;
goto out_unlock;
}
ret = ocfs2_read_blocks_sync(osb, input->group, 1, &group_bh);
if (ret < 0) {
mlog(ML_ERROR, "Can't read the group descriptor # %llu "
"from the device.", (unsigned long long)input->group);
goto out_unlock;
}
ocfs2_set_new_buffer_uptodate(INODE_CACHE(inode), group_bh);
ret = ocfs2_verify_group_and_input(main_bm_inode, fe, input, group_bh);
if (ret) {
mlog_errno(ret);
goto out_free_group_bh;
}
trace_ocfs2_group_add((unsigned long long)input->group,
input->chain, input->clusters, input->frees);
handle = ocfs2_start_trans(osb, OCFS2_GROUP_ADD_CREDITS);
if (IS_ERR(handle)) {
mlog_errno(PTR_ERR(handle));
ret = -EINVAL;
goto out_free_group_bh;
}
cl_bpc = le16_to_cpu(fe->id2.i_chain.cl_bpc);
cl = &fe->id2.i_chain;
cr = &cl->cl_recs[input->chain];
ret = ocfs2_journal_access_gd(handle, INODE_CACHE(main_bm_inode),
group_bh, OCFS2_JOURNAL_ACCESS_WRITE);
if (ret < 0) {
mlog_errno(ret);
goto out_commit;
}
group = (struct ocfs2_group_desc *)group_bh->b_data;
bg_ptr = le64_to_cpu(group->bg_next_group);
group->bg_next_group = cr->c_blkno;
ocfs2_journal_dirty(handle, group_bh);
ret = ocfs2_journal_access_di(handle, INODE_CACHE(main_bm_inode),
main_bm_bh, OCFS2_JOURNAL_ACCESS_WRITE);
if (ret < 0) {
group->bg_next_group = cpu_to_le64(bg_ptr);
mlog_errno(ret);
goto out_commit;
}
if (input->chain == le16_to_cpu(cl->cl_next_free_rec)) {
le16_add_cpu(&cl->cl_next_free_rec, 1);
memset(cr, 0, sizeof(struct ocfs2_chain_rec));
}
cr->c_blkno = cpu_to_le64(input->group);
le32_add_cpu(&cr->c_total, input->clusters * cl_bpc);
le32_add_cpu(&cr->c_free, input->frees * cl_bpc);
le32_add_cpu(&fe->id1.bitmap1.i_total, input->clusters *cl_bpc);
le32_add_cpu(&fe->id1.bitmap1.i_used,
(input->clusters - input->frees) * cl_bpc);
le32_add_cpu(&fe->i_clusters, input->clusters);
ocfs2_journal_dirty(handle, main_bm_bh);
spin_lock(&OCFS2_I(main_bm_inode)->ip_lock);
OCFS2_I(main_bm_inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
le64_add_cpu(&fe->i_size, (u64)input->clusters << osb->s_clustersize_bits);
spin_unlock(&OCFS2_I(main_bm_inode)->ip_lock);
i_size_write(main_bm_inode, le64_to_cpu(fe->i_size));
ocfs2_update_super_and_backups(main_bm_inode, input->clusters);
out_commit:
ocfs2_commit_trans(osb, handle);
out_free_group_bh:
brelse(group_bh);
out_unlock:
brelse(main_bm_bh);
ocfs2_inode_unlock(main_bm_inode, 1);
out_mutex:
inode_unlock(main_bm_inode);
iput(main_bm_inode);
out:
return ret;
}
static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
struct kstat *stat, const char *link,
struct dentry *hardlink)
{
struct dentry *workdir = ovl_workdir(dentry);
struct inode *wdir = workdir->d_inode;
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct dentry *upper;
struct dentry *newdentry;
int err;
if (WARN_ON(!workdir))
return -EROFS;
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
newdentry = ovl_lookup_temp(workdir, dentry);
err = PTR_ERR(newdentry);
if (IS_ERR(newdentry))
goto out_unlock;
upper = lookup_one_len(dentry->d_name.name, upperdir,
dentry->d_name.len);
err = PTR_ERR(upper);
if (IS_ERR(upper))
goto out_dput;
err = ovl_create_real(wdir, newdentry, stat, link, hardlink, true);
if (err)
goto out_dput2;
/*
* mode could have been mutilated due to umask (e.g. sgid directory)
*/
if (!hardlink &&
!S_ISLNK(stat->mode) && newdentry->d_inode->i_mode != stat->mode) {
struct iattr attr = {
.ia_valid = ATTR_MODE,
.ia_mode = stat->mode,
};
inode_lock(newdentry->d_inode);
err = notify_change(newdentry, &attr, NULL);
inode_unlock(newdentry->d_inode);
if (err)
goto out_cleanup;
}
if (!hardlink && S_ISDIR(stat->mode)) {
err = ovl_set_opaque(newdentry);
if (err)
goto out_cleanup;
err = ovl_do_rename(wdir, newdentry, udir, upper,
RENAME_EXCHANGE);
if (err)
goto out_cleanup;
ovl_cleanup(wdir, upper);
} else {
err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
if (err)
goto out_cleanup;
}
ovl_instantiate(dentry, inode, newdentry, !!hardlink);
newdentry = NULL;
out_dput2:
dput(upper);
out_dput:
dput(newdentry);
out_unlock:
unlock_rename(workdir, upperdir);
out:
return err;
out_cleanup:
ovl_cleanup(wdir, newdentry);
goto out_dput2;
}
static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
struct kstat *stat, const char *link,
struct dentry *hardlink)
{
int err;
const struct cred *old_cred;
struct cred *override_cred;
err = ovl_copy_up(dentry->d_parent);
if (err)
return err;
old_cred = ovl_override_creds(dentry->d_sb);
err = -ENOMEM;
override_cred = prepare_creds();
if (override_cred) {
override_cred->fsuid = inode->i_uid;
override_cred->fsgid = inode->i_gid;
put_cred(override_creds(override_cred));
put_cred(override_cred);
if (!ovl_dentry_is_opaque(dentry))
err = ovl_create_upper(dentry, inode, stat, link,
hardlink);
else
err = ovl_create_over_whiteout(dentry, inode, stat,
link, hardlink);
}
revert_creds(old_cred);
if (!err) {
struct inode *realinode = d_inode(ovl_dentry_upper(dentry));
WARN_ON(inode->i_mode != realinode->i_mode);
WARN_ON(!uid_eq(inode->i_uid, realinode->i_uid));
WARN_ON(!gid_eq(inode->i_gid, realinode->i_gid));
}
return err;
}
static struct dentry *ovl_clear_empty(struct dentry *dentry,
struct list_head *list)
{
struct dentry *workdir = ovl_workdir(dentry);
struct inode *wdir = workdir->d_inode;
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct path upperpath;
struct dentry *upper;
struct dentry *opaquedir;
struct kstat stat;
int err;
if (WARN_ON(!workdir))
return ERR_PTR(-EROFS);
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
ovl_path_upper(dentry, &upperpath);
err = vfs_getattr(&upperpath, &stat);
if (err)
goto out_unlock;
err = -ESTALE;
if (!S_ISDIR(stat.mode))
goto out_unlock;
upper = upperpath.dentry;
if (upper->d_parent->d_inode != udir)
goto out_unlock;
opaquedir = ovl_lookup_temp(workdir, dentry);
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir))
goto out_unlock;
err = ovl_create_real(wdir, opaquedir, &stat, NULL, NULL, true);
if (err)
goto out_dput;
err = ovl_copy_xattr(upper, opaquedir);
if (err)
goto out_cleanup;
err = ovl_set_opaque(opaquedir);
if (err)
goto out_cleanup;
inode_lock(opaquedir->d_inode);
err = ovl_set_attr(opaquedir, &stat);
inode_unlock(opaquedir->d_inode);
if (err)
goto out_cleanup;
err = ovl_do_rename(wdir, opaquedir, udir, upper, RENAME_EXCHANGE);
if (err)
goto out_cleanup;
ovl_cleanup_whiteouts(upper, list);
ovl_cleanup(wdir, upper);
unlock_rename(workdir, upperdir);
/* dentry's upper doesn't match now, get rid of it */
d_drop(dentry);
return opaquedir;
out_cleanup:
ovl_cleanup(wdir, opaquedir);
out_dput:
dput(opaquedir);
out_unlock:
unlock_rename(workdir, upperdir);
out:
return ERR_PTR(err);
}
int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
u64 child_nodeid, struct qstr *name)
{
int err = -ENOTDIR;
struct inode *parent;
struct dentry *dir;
struct dentry *entry;
parent = ilookup5(sb, parent_nodeid, fuse_inode_eq, &parent_nodeid);
if (!parent)
return -ENOENT;
inode_lock(parent);
if (!S_ISDIR(parent->i_mode))
goto unlock;
err = -ENOENT;
dir = d_find_alias(parent);
if (!dir)
goto unlock;
entry = d_lookup(dir, name);
dput(dir);
if (!entry)
goto unlock;
fuse_invalidate_attr(parent);
fuse_invalidate_entry(entry);
if (child_nodeid != 0 && d_really_is_positive(entry)) {
inode_lock(d_inode(entry));
if (get_node_id(d_inode(entry)) != child_nodeid) {
err = -ENOENT;
goto badentry;
}
if (d_mountpoint(entry)) {
err = -EBUSY;
goto badentry;
}
if (d_is_dir(entry)) {
shrink_dcache_parent(entry);
if (!simple_empty(entry)) {
err = -ENOTEMPTY;
goto badentry;
}
d_inode(entry)->i_flags |= S_DEAD;
}
dont_mount(entry);
clear_nlink(d_inode(entry));
err = 0;
badentry:
inode_unlock(d_inode(entry));
if (!err)
d_delete(entry);
} else {
err = 0;
}
dput(entry);
unlock:
inode_unlock(parent);
iput(parent);
return err;
}
static int ocfs2_remove_inode(struct inode *inode,
struct buffer_head *di_bh,
struct inode *orphan_dir_inode,
struct buffer_head *orphan_dir_bh)
{
int status;
struct inode *inode_alloc_inode = NULL;
struct buffer_head *inode_alloc_bh = NULL;
handle_t *handle;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
inode_alloc_inode =
ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE,
le16_to_cpu(di->i_suballoc_slot));
if (!inode_alloc_inode) {
status = -ENOENT;
mlog_errno(status);
goto bail;
}
inode_lock(inode_alloc_inode);
status = ocfs2_inode_lock(inode_alloc_inode, &inode_alloc_bh, 1);
if (status < 0) {
inode_unlock(inode_alloc_inode);
mlog_errno(status);
goto bail;
}
handle = ocfs2_start_trans(osb, OCFS2_DELETE_INODE_CREDITS +
ocfs2_quota_trans_credits(inode->i_sb));
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
mlog_errno(status);
goto bail_unlock;
}
if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode,
orphan_dir_bh, false);
if (status < 0) {
mlog_errno(status);
goto bail_commit;
}
}
/* set the inodes dtime */
status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
mlog_errno(status);
goto bail_commit;
}
di->i_dtime = cpu_to_le64(ktime_get_real_seconds());
di->i_flags &= cpu_to_le32(~(OCFS2_VALID_FL | OCFS2_ORPHANED_FL));
ocfs2_journal_dirty(handle, di_bh);
ocfs2_remove_from_cache(INODE_CACHE(inode), di_bh);
dquot_free_inode(inode);
status = ocfs2_free_dinode(handle, inode_alloc_inode,
inode_alloc_bh, di);
if (status < 0)
mlog_errno(status);
bail_commit:
ocfs2_commit_trans(osb, handle);
bail_unlock:
ocfs2_inode_unlock(inode_alloc_inode, 1);
inode_unlock(inode_alloc_inode);
brelse(inode_alloc_bh);
bail:
iput(inode_alloc_inode);
return status;
}
long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct jfs_inode_info *jfs_inode = JFS_IP(inode);
unsigned int flags;
switch (cmd) {
case JFS_IOC_GETFLAGS:
jfs_get_inode_flags(jfs_inode);
flags = jfs_inode->mode2 & JFS_FL_USER_VISIBLE;
flags = jfs_map_ext2(flags, 0);
return put_user(flags, (int __user *) arg);
case JFS_IOC_SETFLAGS: {
unsigned int oldflags;
int err;
err = mnt_want_write_file(filp);
if (err)
return err;
if (!inode_owner_or_capable(inode)) {
err = -EACCES;
goto setflags_out;
}
if (get_user(flags, (int __user *) arg)) {
err = -EFAULT;
goto setflags_out;
}
flags = jfs_map_ext2(flags, 1);
if (!S_ISDIR(inode->i_mode))
flags &= ~JFS_DIRSYNC_FL;
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode)) {
err = -EPERM;
goto setflags_out;
}
/* Lock against other parallel changes of flags */
inode_lock(inode);
jfs_get_inode_flags(jfs_inode);
oldflags = jfs_inode->mode2;
/*
* The IMMUTABLE and APPEND_ONLY flags can only be changed by
* the relevant capability.
*/
if ((oldflags & JFS_IMMUTABLE_FL) ||
((flags ^ oldflags) &
(JFS_APPEND_FL | JFS_IMMUTABLE_FL))) {
if (!capable(CAP_LINUX_IMMUTABLE)) {
inode_unlock(inode);
err = -EPERM;
goto setflags_out;
}
}
flags = flags & JFS_FL_USER_MODIFIABLE;
flags |= oldflags & ~JFS_FL_USER_MODIFIABLE;
jfs_inode->mode2 = flags;
jfs_set_inode_flags(inode);
inode_unlock(inode);
inode->i_ctime = current_time(inode);
mark_inode_dirty(inode);
setflags_out:
mnt_drop_write_file(filp);
return err;
}
case FITRIM:
{
struct super_block *sb = inode->i_sb;
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
s64 ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q)) {
jfs_warn("FITRIM not supported on device");
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 = jfs_ioc_trim(inode, &range);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
default:
return -ENOTTY;
}
}
static int ocfs2_wipe_inode(struct inode *inode,
struct buffer_head *di_bh)
{
int status, orphaned_slot = -1;
struct inode *orphan_dir_inode = NULL;
struct buffer_head *orphan_dir_bh = NULL;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
orphaned_slot = le16_to_cpu(di->i_orphaned_slot);
status = ocfs2_check_orphan_recovery_state(osb, orphaned_slot);
if (status)
return status;
orphan_dir_inode = ocfs2_get_system_file_inode(osb,
ORPHAN_DIR_SYSTEM_INODE,
orphaned_slot);
if (!orphan_dir_inode) {
status = -ENOENT;
mlog_errno(status);
goto bail;
}
/* Lock the orphan dir. The lock will be held for the entire
* delete_inode operation. We do this now to avoid races with
* recovery completion on other nodes. */
inode_lock(orphan_dir_inode);
status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
if (status < 0) {
inode_unlock(orphan_dir_inode);
mlog_errno(status);
goto bail;
}
}
/* we do this while holding the orphan dir lock because we
* don't want recovery being run from another node to try an
* inode delete underneath us -- this will result in two nodes
* truncating the same file! */
status = ocfs2_truncate_for_delete(osb, inode, di_bh);
if (status < 0) {
mlog_errno(status);
goto bail_unlock_dir;
}
/* Remove any dir index tree */
if (S_ISDIR(inode->i_mode)) {
status = ocfs2_dx_dir_truncate(inode, di_bh);
if (status) {
mlog_errno(status);
goto bail_unlock_dir;
}
}
/*Free extended attribute resources associated with this inode.*/
status = ocfs2_xattr_remove(inode, di_bh);
if (status < 0) {
mlog_errno(status);
goto bail_unlock_dir;
}
status = ocfs2_remove_refcount_tree(inode, di_bh);
if (status < 0) {
mlog_errno(status);
goto bail_unlock_dir;
}
status = ocfs2_remove_inode(inode, di_bh, orphan_dir_inode,
orphan_dir_bh);
if (status < 0)
mlog_errno(status);
bail_unlock_dir:
if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)
return status;
ocfs2_inode_unlock(orphan_dir_inode, 1);
inode_unlock(orphan_dir_inode);
brelse(orphan_dir_bh);
bail:
iput(orphan_dir_inode);
ocfs2_signal_wipe_completion(osb, orphaned_slot);
return status;
}
static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
int err, rc;
handle_t *handle;
kprojid_t kprojid;
struct ext4_iloc iloc;
struct ext4_inode *raw_inode;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_PROJECT)) {
if (projid != EXT4_DEF_PROJID)
return -EOPNOTSUPP;
else
return 0;
}
if (EXT4_INODE_SIZE(sb) <= EXT4_GOOD_OLD_INODE_SIZE)
return -EOPNOTSUPP;
kprojid = make_kprojid(&init_user_ns, (projid_t)projid);
if (projid_eq(kprojid, EXT4_I(inode)->i_projid))
return 0;
err = mnt_want_write_file(filp);
if (err)
return err;
err = -EPERM;
inode_lock(inode);
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode))
goto out_unlock;
err = ext4_get_inode_loc(inode, &iloc);
if (err)
goto out_unlock;
raw_inode = ext4_raw_inode(&iloc);
if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) {
err = -EOVERFLOW;
brelse(iloc.bh);
goto out_unlock;
}
brelse(iloc.bh);
dquot_initialize(inode);
handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
EXT4_QUOTA_INIT_BLOCKS(sb) +
EXT4_QUOTA_DEL_BLOCKS(sb) + 3);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto out_unlock;
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto out_stop;
if (sb_has_quota_limits_enabled(sb, PRJQUOTA)) {
struct dquot *transfer_to[MAXQUOTAS] = { };
transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
if (transfer_to[PRJQUOTA]) {
err = __dquot_transfer(inode, transfer_to);
dqput(transfer_to[PRJQUOTA]);
if (err)
goto out_dirty;
}
}
EXT4_I(inode)->i_projid = kprojid;
inode->i_ctime = ext4_current_time(inode);
out_dirty:
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
out_stop:
ext4_journal_stop(handle);
out_unlock:
inode_unlock(inode);
mnt_drop_write_file(filp);
return err;
}
static int process_measurement(struct file *file, const struct cred *cred,
u32 secid, char *buf, loff_t size, int mask,
enum ima_hooks func, int opened)
{
struct inode *inode = file_inode(file);
struct integrity_iint_cache *iint = NULL;
struct ima_template_desc *template_desc;
char *pathbuf = NULL;
char filename[NAME_MAX];
const char *pathname = NULL;
int rc = 0, action, must_appraise = 0;
int pcr = CONFIG_IMA_MEASURE_PCR_IDX;
struct evm_ima_xattr_data *xattr_value = NULL;
int xattr_len = 0;
bool violation_check;
enum hash_algo hash_algo;
if (!ima_policy_flag || !S_ISREG(inode->i_mode))
return 0;
/* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action
* bitmask based on the appraise/audit/measurement policy.
* Included is the appraise submask.
*/
action = ima_get_action(inode, cred, secid, mask, func, &pcr);
violation_check = ((func == FILE_CHECK || func == MMAP_CHECK) &&
(ima_policy_flag & IMA_MEASURE));
if (!action && !violation_check)
return 0;
must_appraise = action & IMA_APPRAISE;
/* Is the appraise rule hook specific? */
if (action & IMA_FILE_APPRAISE)
func = FILE_CHECK;
inode_lock(inode);
if (action) {
iint = integrity_inode_get(inode);
if (!iint)
rc = -ENOMEM;
}
if (!rc && violation_check)
ima_rdwr_violation_check(file, iint, action & IMA_MEASURE,
&pathbuf, &pathname, filename);
inode_unlock(inode);
if (rc)
goto out;
if (!action)
goto out;
mutex_lock(&iint->mutex);
if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags))
/* reset appraisal flags if ima_inode_post_setattr was called */
iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED |
IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK |
IMA_ACTION_FLAGS);
/*
* Re-evaulate the file if either the xattr has changed or the
* kernel has no way of detecting file change on the filesystem.
* (Limited to privileged mounted filesystems.)
*/
if (test_and_clear_bit(IMA_CHANGE_XATTR, &iint->atomic_flags) ||
((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) &&
!(inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) &&
!(action & IMA_FAIL_UNVERIFIABLE_SIGS))) {
iint->flags &= ~IMA_DONE_MASK;
iint->measured_pcrs = 0;
}
/* Determine if already appraised/measured based on bitmask
* (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED,
* IMA_AUDIT, IMA_AUDITED)
*/
iint->flags |= action;
action &= IMA_DO_MASK;
action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1);
/* If target pcr is already measured, unset IMA_MEASURE action */
if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr)))
action ^= IMA_MEASURE;
/* HASH sets the digital signature and update flags, nothing else */
if ((action & IMA_HASH) &&
!(test_bit(IMA_DIGSIG, &iint->atomic_flags))) {
xattr_len = ima_read_xattr(file_dentry(file), &xattr_value);
if ((xattr_value && xattr_len > 2) &&
(xattr_value->type == EVM_IMA_XATTR_DIGSIG))
set_bit(IMA_DIGSIG, &iint->atomic_flags);
iint->flags |= IMA_HASHED;
action ^= IMA_HASH;
set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags);
}
/* Nothing to do, just return existing appraised status */
if (!action) {
if (must_appraise)
rc = ima_get_cache_status(iint, func);
goto out_locked;
}
template_desc = ima_template_desc_current();
if ((action & IMA_APPRAISE_SUBMASK) ||
strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0)
/* read 'security.ima' */
xattr_len = ima_read_xattr(file_dentry(file), &xattr_value);
hash_algo = ima_get_hash_algo(xattr_value, xattr_len);
rc = ima_collect_measurement(iint, file, buf, size, hash_algo);
if (rc != 0 && rc != -EBADF && rc != -EINVAL)
goto out_locked;
if (!pathbuf) /* ima_rdwr_violation possibly pre-fetched */
pathname = ima_d_path(&file->f_path, &pathbuf, filename);
if (action & IMA_MEASURE)
ima_store_measurement(iint, file, pathname,
xattr_value, xattr_len, pcr);
if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) {
inode_lock(inode);
rc = ima_appraise_measurement(func, iint, file, pathname,
xattr_value, xattr_len, opened);
inode_unlock(inode);
}
if (action & IMA_AUDIT)
ima_audit_measurement(iint, pathname);
if ((file->f_flags & O_DIRECT) && (iint->flags & IMA_PERMIT_DIRECTIO))
rc = 0;
out_locked:
if ((mask & MAY_WRITE) && test_bit(IMA_DIGSIG, &iint->atomic_flags) &&
!(iint->flags & IMA_NEW_FILE))
rc = -EACCES;
mutex_unlock(&iint->mutex);
kfree(xattr_value);
out:
if (pathbuf)
__putname(pathbuf);
if (must_appraise) {
if (rc && (ima_appraise & IMA_APPRAISE_ENFORCE))
return -EACCES;
if (file->f_mode & FMODE_WRITE)
set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags);
}
return 0;
}
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case EXT4_IOC_GETFLAGS:
ext4_get_inode_flags(ei);
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT4_IOC_SETFLAGS: {
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
return -EFAULT;
err = mnt_want_write_file(filp);
if (err)
return err;
flags = ext4_mask_flags(inode->i_mode, flags);
inode_lock(inode);
err = ext4_ioctl_setflags(inode, flags);
inode_unlock(inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GETVERSION:
case EXT4_IOC_GETVERSION_OLD:
return put_user(inode->i_generation, (int __user *) arg);
case EXT4_IOC_SETVERSION:
case EXT4_IOC_SETVERSION_OLD: {
handle_t *handle;
struct ext4_iloc iloc;
__u32 generation;
int err;
if (!inode_owner_or_capable(inode))
return -EPERM;
if (ext4_has_metadata_csum(inode->i_sb)) {
ext4_warning(sb, "Setting inode version is not "
"supported with metadata_csum enabled.");
return -ENOTTY;
}
err = mnt_want_write_file(filp);
if (err)
return err;
if (get_user(generation, (int __user *) arg)) {
err = -EFAULT;
goto setversion_out;
}
inode_lock(inode);
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto unlock_out;
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err == 0) {
inode->i_ctime = ext4_current_time(inode);
inode->i_generation = generation;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
}
ext4_journal_stop(handle);
unlock_out:
inode_unlock(inode);
setversion_out:
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (get_user(n_blocks_count, (__u32 __user *)arg)) {
err = -EFAULT;
goto group_extend_out;
}
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_extend_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_extend_out;
err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
group_extend_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
struct fd donor;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&me,
(struct move_extent __user *)arg, sizeof(me)))
return -EFAULT;
me.moved_len = 0;
donor = fdget(me.donor_fd);
if (!donor.file)
return -EBADF;
if (!(donor.file->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto mext_out;
}
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with bigalloc");
err = -EOPNOTSUPP;
goto mext_out;
}
err = mnt_want_write_file(filp);
if (err)
goto mext_out;
err = ext4_move_extents(filp, donor.file, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write_file(filp);
if (copy_to_user((struct move_extent __user *)arg,
&me, sizeof(me)))
err = -EFAULT;
mext_out:
fdput(donor);
return err;
}
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
sizeof(input))) {
err = -EFAULT;
goto group_add_out;
}
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_add_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_add_out;
err = ext4_group_add(sb, &input);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
if (!err && ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, input.group);
group_add_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MIGRATE:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
/*
* inode_mutex prevent write and truncate on the file.
* Read still goes through. We take i_data_sem in
* ext4_ext_swap_inode_data before we switch the
* inode format to prevent read.
*/
inode_lock((inode));
err = ext4_ext_migrate(inode);
inode_unlock((inode));
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
err = ext4_alloc_da_blocks(inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_SWAP_BOOT:
{
int err;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
err = mnt_want_write_file(filp);
if (err)
return err;
err = swap_inode_boot_loader(sb, inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_RESIZE_FS: {
ext4_fsblk_t n_blocks_count;
int err = 0, err2 = 0;
ext4_group_t o_group = EXT4_SB(sb)->s_groups_count;
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not (yet) supported with bigalloc");
return -EOPNOTSUPP;
}
if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
sizeof(__u64))) {
return -EFAULT;
}
err = ext4_resize_begin(sb);
if (err)
return err;
err = mnt_want_write_file(filp);
if (err)
goto resizefs_out;
err = ext4_resize_fs(sb, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
if (!err && (o_group > EXT4_SB(sb)->s_groups_count) &&
ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, o_group);
resizefs_out:
ext4_resize_end(sb);
return err;
}
case FITRIM:
{
struct request_queue *q = bdev_get_queue(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((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = ext4_trim_fs(sb, &range);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
case EXT4_IOC_PRECACHE_EXTENTS:
return ext4_ext_precache(inode);
case EXT4_IOC_SET_ENCRYPTION_POLICY: {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
struct ext4_encryption_policy policy;
int err = 0;
if (copy_from_user(&policy,
(struct ext4_encryption_policy __user *)arg,
sizeof(policy))) {
err = -EFAULT;
goto encryption_policy_out;
}
err = ext4_process_policy(&policy, inode);
encryption_policy_out:
return err;
#else
return -EOPNOTSUPP;
#endif
}
case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
int err, err2;
struct ext4_sb_info *sbi = EXT4_SB(sb);
handle_t *handle;
if (!ext4_sb_has_crypto(sb))
return -EOPNOTSUPP;
if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
err = mnt_want_write_file(filp);
if (err)
return err;
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto pwsalt_err_exit;
}
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto pwsalt_err_journal;
generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
err = ext4_handle_dirty_metadata(handle, NULL,
sbi->s_sbh);
pwsalt_err_journal:
err2 = ext4_journal_stop(handle);
if (err2 && !err)
err = err2;
pwsalt_err_exit:
mnt_drop_write_file(filp);
if (err)
return err;
}
if (copy_to_user((void __user *) arg,
sbi->s_es->s_encrypt_pw_salt, 16))
return -EFAULT;
return 0;
}
case EXT4_IOC_GET_ENCRYPTION_POLICY: {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
struct ext4_encryption_policy policy;
int err = 0;
if (!ext4_encrypted_inode(inode))
return -ENOENT;
err = ext4_get_policy(inode, &policy);
if (err)
return err;
if (copy_to_user((void __user *)arg, &policy, sizeof(policy)))
return -EFAULT;
return 0;
#else
return -EOPNOTSUPP;
#endif
}
case EXT4_IOC_FSGETXATTR:
{
struct fsxattr fa;
memset(&fa, 0, sizeof(struct fsxattr));
ext4_get_inode_flags(ei);
fa.fsx_xflags = ext4_iflags_to_xflags(ei->i_flags & EXT4_FL_USER_VISIBLE);
if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_RO_COMPAT_PROJECT)) {
fa.fsx_projid = (__u32)from_kprojid(&init_user_ns,
EXT4_I(inode)->i_projid);
}
if (copy_to_user((struct fsxattr __user *)arg,
&fa, sizeof(fa)))
return -EFAULT;
return 0;
}
case EXT4_IOC_FSSETXATTR:
{
struct fsxattr fa;
int err;
if (copy_from_user(&fa, (struct fsxattr __user *)arg,
sizeof(fa)))
return -EFAULT;
/* Make sure caller has proper permission */
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
flags = ext4_xflags_to_iflags(fa.fsx_xflags);
flags = ext4_mask_flags(inode->i_mode, flags);
inode_lock(inode);
flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) |
(flags & EXT4_FL_XFLAG_VISIBLE);
err = ext4_ioctl_setflags(inode, flags);
inode_unlock(inode);
mnt_drop_write_file(filp);
if (err)
return err;
err = ext4_ioctl_setproject(filp, fa.fsx_projid);
if (err)
return err;
return 0;
}
default:
return -ENOTTY;
}
}
static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
struct nfs_lock_context *lock, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(filep);
struct nfs_server *server = NFS_SERVER(inode);
struct nfs42_falloc_args args = {
.falloc_fh = NFS_FH(inode),
.falloc_offset = offset,
.falloc_length = len,
.falloc_bitmask = server->cache_consistency_bitmask,
};
struct nfs42_falloc_res res = {
.falloc_server = server,
};
int status;
msg->rpc_argp = &args;
msg->rpc_resp = &res;
status = nfs4_set_rw_stateid(&args.falloc_stateid, lock->open_context,
lock, FMODE_WRITE);
if (status)
return status;
res.falloc_fattr = nfs_alloc_fattr();
if (!res.falloc_fattr)
return -ENOMEM;
status = nfs4_call_sync(server->client, server, msg,
&args.seq_args, &res.seq_res, 0);
if (status == 0)
status = nfs_post_op_update_inode(inode, res.falloc_fattr);
kfree(res.falloc_fattr);
return status;
}
static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
loff_t offset, loff_t len)
{
struct nfs_server *server = NFS_SERVER(file_inode(filep));
struct nfs4_exception exception = { };
struct nfs_lock_context *lock;
int err;
lock = nfs_get_lock_context(nfs_file_open_context(filep));
if (IS_ERR(lock))
return PTR_ERR(lock);
exception.inode = file_inode(filep);
exception.state = lock->open_context->state;
do {
err = _nfs42_proc_fallocate(msg, filep, lock, offset, len);
if (err == -ENOTSUPP) {
err = -EOPNOTSUPP;
break;
}
err = nfs4_handle_exception(server, err, &exception);
} while (exception.retry);
nfs_put_lock_context(lock);
return err;
}
int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
{
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE],
};
struct inode *inode = file_inode(filep);
int err;
if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE))
return -EOPNOTSUPP;
inode_lock(inode);
err = nfs42_proc_fallocate(&msg, filep, offset, len);
if (err == -EOPNOTSUPP)
NFS_SERVER(inode)->caps &= ~NFS_CAP_ALLOCATE;
inode_unlock(inode);
return err;
}
int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
{
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DEALLOCATE],
};
struct inode *inode = file_inode(filep);
int err;
if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE))
return -EOPNOTSUPP;
inode_lock(inode);
err = nfs_sync_inode(inode);
if (err)
goto out_unlock;
err = nfs42_proc_fallocate(&msg, filep, offset, len);
if (err == 0)
truncate_pagecache_range(inode, offset, (offset + len) -1);
if (err == -EOPNOTSUPP)
NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
out_unlock:
inode_unlock(inode);
return err;
}
static ssize_t _nfs42_proc_copy(struct file *src, loff_t pos_src,
struct nfs_lock_context *src_lock,
struct file *dst, loff_t pos_dst,
struct nfs_lock_context *dst_lock,
size_t count)
{
struct nfs42_copy_args args = {
.src_fh = NFS_FH(file_inode(src)),
.src_pos = pos_src,
.dst_fh = NFS_FH(file_inode(dst)),
.dst_pos = pos_dst,
.count = count,
};
struct nfs42_copy_res res;
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY],
.rpc_argp = &args,
.rpc_resp = &res,
};
struct inode *dst_inode = file_inode(dst);
struct nfs_server *server = NFS_SERVER(dst_inode);
int status;
status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context,
src_lock, FMODE_READ);
if (status)
return status;
status = nfs_filemap_write_and_wait_range(file_inode(src)->i_mapping,
pos_src, pos_src + (loff_t)count - 1);
if (status)
return status;
status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
dst_lock, FMODE_WRITE);
if (status)
return status;
status = nfs_sync_inode(dst_inode);
if (status)
return status;
status = nfs4_call_sync(server->client, server, &msg,
&args.seq_args, &res.seq_res, 0);
if (status == -ENOTSUPP)
server->caps &= ~NFS_CAP_COPY;
if (status)
return status;
if (res.write_res.verifier.committed != NFS_FILE_SYNC) {
status = nfs_commit_file(dst, &res.write_res.verifier.verifier);
if (status)
return status;
}
truncate_pagecache_range(dst_inode, pos_dst,
pos_dst + res.write_res.count);
return res.write_res.count;
}
ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
struct file *dst, loff_t pos_dst,
size_t count)
{
struct nfs_server *server = NFS_SERVER(file_inode(dst));
struct nfs_lock_context *src_lock;
struct nfs_lock_context *dst_lock;
struct nfs4_exception src_exception = { };
struct nfs4_exception dst_exception = { };
ssize_t err, err2;
if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY))
return -EOPNOTSUPP;
src_lock = nfs_get_lock_context(nfs_file_open_context(src));
if (IS_ERR(src_lock))
return PTR_ERR(src_lock);
src_exception.inode = file_inode(src);
src_exception.state = src_lock->open_context->state;
dst_lock = nfs_get_lock_context(nfs_file_open_context(dst));
if (IS_ERR(dst_lock)) {
err = PTR_ERR(dst_lock);
goto out_put_src_lock;
}
dst_exception.inode = file_inode(dst);
dst_exception.state = dst_lock->open_context->state;
do {
inode_lock(file_inode(dst));
err = _nfs42_proc_copy(src, pos_src, src_lock,
dst, pos_dst, dst_lock, count);
inode_unlock(file_inode(dst));
if (err == -ENOTSUPP) {
err = -EOPNOTSUPP;
break;
}
err2 = nfs4_handle_exception(server, err, &src_exception);
err = nfs4_handle_exception(server, err, &dst_exception);
if (!err)
err = err2;
} while (src_exception.retry || dst_exception.retry);
nfs_put_lock_context(dst_lock);
out_put_src_lock:
nfs_put_lock_context(src_lock);
return err;
}
static loff_t _nfs42_proc_llseek(struct file *filep,
struct nfs_lock_context *lock, loff_t offset, int whence)
{
struct inode *inode = file_inode(filep);
struct nfs42_seek_args args = {
.sa_fh = NFS_FH(inode),
.sa_offset = offset,
.sa_what = (whence == SEEK_HOLE) ?
NFS4_CONTENT_HOLE : NFS4_CONTENT_DATA,
};
struct nfs42_seek_res res;
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SEEK],
.rpc_argp = &args,
.rpc_resp = &res,
};
struct nfs_server *server = NFS_SERVER(inode);
int status;
if (!nfs_server_capable(inode, NFS_CAP_SEEK))
return -ENOTSUPP;
status = nfs4_set_rw_stateid(&args.sa_stateid, lock->open_context,
lock, FMODE_READ);
if (status)
return status;
status = nfs_filemap_write_and_wait_range(inode->i_mapping,
offset, LLONG_MAX);
if (status)
return status;
status = nfs4_call_sync(server->client, server, &msg,
&args.seq_args, &res.seq_res, 0);
if (status == -ENOTSUPP)
server->caps &= ~NFS_CAP_SEEK;
if (status)
return status;
return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
}
loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
{
struct nfs_server *server = NFS_SERVER(file_inode(filep));
struct nfs4_exception exception = { };
struct nfs_lock_context *lock;
loff_t err;
lock = nfs_get_lock_context(nfs_file_open_context(filep));
if (IS_ERR(lock))
return PTR_ERR(lock);
exception.inode = file_inode(filep);
exception.state = lock->open_context->state;
do {
err = _nfs42_proc_llseek(filep, lock, offset, whence);
if (err >= 0)
break;
if (err == -ENOTSUPP) {
err = -EOPNOTSUPP;
break;
}
err = nfs4_handle_exception(server, err, &exception);
} while (exception.retry);
nfs_put_lock_context(lock);
return err;
}
static void
nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata)
{
struct nfs42_layoutstat_data *data = calldata;
struct inode *inode = data->inode;
struct nfs_server *server = NFS_SERVER(inode);
struct pnfs_layout_hdr *lo;
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
if (!pnfs_layout_is_valid(lo)) {
spin_unlock(&inode->i_lock);
rpc_exit(task, 0);
return;
}
nfs4_stateid_copy(&data->args.stateid, &lo->plh_stateid);
spin_unlock(&inode->i_lock);
nfs41_setup_sequence(nfs4_get_session(server), &data->args.seq_args,
&data->res.seq_res, task);
}
static void
nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
{
struct nfs42_layoutstat_data *data = calldata;
struct inode *inode = data->inode;
struct pnfs_layout_hdr *lo;
if (!nfs4_sequence_done(task, &data->res.seq_res))
return;
switch (task->tk_status) {
case 0:
break;
case -NFS4ERR_EXPIRED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_BAD_STATEID:
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
if (pnfs_layout_is_valid(lo) &&
nfs4_stateid_match(&data->args.stateid,
&lo->plh_stateid)) {
LIST_HEAD(head);
/*
* Mark the bad layout state as invalid, then retry
* with the current stateid.
*/
pnfs_mark_layout_stateid_invalid(lo, &head);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
} else
spin_unlock(&inode->i_lock);
break;
case -NFS4ERR_OLD_STATEID:
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
if (pnfs_layout_is_valid(lo) &&
nfs4_stateid_match_other(&data->args.stateid,
&lo->plh_stateid)) {
/* Do we need to delay before resending? */
if (!nfs4_stateid_is_newer(&lo->plh_stateid,
&data->args.stateid))
rpc_delay(task, HZ);
rpc_restart_call_prepare(task);
}
spin_unlock(&inode->i_lock);
break;
case -ENOTSUPP:
case -EOPNOTSUPP:
NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS;
}
dprintk("%s server returns %d\n", __func__, task->tk_status);
}
static void
nfs42_layoutstat_release(void *calldata)
{
struct nfs42_layoutstat_data *data = calldata;
struct nfs_server *nfss = NFS_SERVER(data->args.inode);
if (nfss->pnfs_curr_ld->cleanup_layoutstats)
nfss->pnfs_curr_ld->cleanup_layoutstats(data);
pnfs_put_layout_hdr(NFS_I(data->args.inode)->layout);
smp_mb__before_atomic();
clear_bit(NFS_INO_LAYOUTSTATS, &NFS_I(data->args.inode)->flags);
smp_mb__after_atomic();
nfs_iput_and_deactive(data->inode);
kfree(data->args.devinfo);
kfree(data);
}
static const struct rpc_call_ops nfs42_layoutstat_ops = {
.rpc_call_prepare = nfs42_layoutstat_prepare,
.rpc_call_done = nfs42_layoutstat_done,
.rpc_release = nfs42_layoutstat_release,
};
int nfs42_proc_layoutstats_generic(struct nfs_server *server,
struct nfs42_layoutstat_data *data)
{
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTSTATS],
.rpc_argp = &data->args,
.rpc_resp = &data->res,
};
struct rpc_task_setup task_setup = {
.rpc_client = server->client,
.rpc_message = &msg,
.callback_ops = &nfs42_layoutstat_ops,
.callback_data = data,
.flags = RPC_TASK_ASYNC,
};
struct rpc_task *task;
data->inode = nfs_igrab_and_active(data->args.inode);
if (!data->inode) {
nfs42_layoutstat_release(data);
return -EAGAIN;
}
nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
task = rpc_run_task(&task_setup);
if (IS_ERR(task))
return PTR_ERR(task);
rpc_put_task(task);
return 0;
}
static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
struct file *dst_f, struct nfs_lock_context *src_lock,
struct nfs_lock_context *dst_lock, loff_t src_offset,
loff_t dst_offset, loff_t count)
{
struct inode *src_inode = file_inode(src_f);
struct inode *dst_inode = file_inode(dst_f);
struct nfs_server *server = NFS_SERVER(dst_inode);
struct nfs42_clone_args args = {
.src_fh = NFS_FH(src_inode),
.dst_fh = NFS_FH(dst_inode),
.src_offset = src_offset,
.dst_offset = dst_offset,
.count = count,
.dst_bitmask = server->cache_consistency_bitmask,
};
struct nfs42_clone_res res = {
.server = server,
};
int status;
msg->rpc_argp = &args;
msg->rpc_resp = &res;
status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context,
src_lock, FMODE_READ);
if (status)
return status;
status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
dst_lock, FMODE_WRITE);
if (status)
return status;
res.dst_fattr = nfs_alloc_fattr();
if (!res.dst_fattr)
return -ENOMEM;
status = nfs4_call_sync(server->client, server, msg,
&args.seq_args, &res.seq_res, 0);
if (status == 0)
status = nfs_post_op_update_inode(dst_inode, res.dst_fattr);
kfree(res.dst_fattr);
return status;
}
int nfs42_proc_clone(struct file *src_f, struct file *dst_f,
loff_t src_offset, loff_t dst_offset, loff_t count)
{
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLONE],
};
struct inode *inode = file_inode(src_f);
struct nfs_server *server = NFS_SERVER(file_inode(src_f));
struct nfs_lock_context *src_lock;
struct nfs_lock_context *dst_lock;
struct nfs4_exception src_exception = { };
struct nfs4_exception dst_exception = { };
int err, err2;
if (!nfs_server_capable(inode, NFS_CAP_CLONE))
return -EOPNOTSUPP;
src_lock = nfs_get_lock_context(nfs_file_open_context(src_f));
if (IS_ERR(src_lock))
return PTR_ERR(src_lock);
src_exception.inode = file_inode(src_f);
src_exception.state = src_lock->open_context->state;
dst_lock = nfs_get_lock_context(nfs_file_open_context(dst_f));
if (IS_ERR(dst_lock)) {
err = PTR_ERR(dst_lock);
goto out_put_src_lock;
}
dst_exception.inode = file_inode(dst_f);
dst_exception.state = dst_lock->open_context->state;
do {
err = _nfs42_proc_clone(&msg, src_f, dst_f, src_lock, dst_lock,
src_offset, dst_offset, count);
if (err == -ENOTSUPP || err == -EOPNOTSUPP) {
NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE;
err = -EOPNOTSUPP;
break;
}
err2 = nfs4_handle_exception(server, err, &src_exception);
err = nfs4_handle_exception(server, err, &dst_exception);
if (!err)
err = err2;
} while (src_exception.retry || dst_exception.retry);
nfs_put_lock_context(dst_lock);
out_put_src_lock:
nfs_put_lock_context(src_lock);
return err;
}
static int process_measurement(struct file *file, char *buf, loff_t size,
int mask, enum ima_hooks func, int opened)
{
struct inode *inode = file_inode(file);
struct integrity_iint_cache *iint = NULL;
struct ima_template_desc *template_desc;
char *pathbuf = NULL;
const char *pathname = NULL;
int rc = -ENOMEM, action, must_appraise;
int pcr = CONFIG_IMA_MEASURE_PCR_IDX;
struct evm_ima_xattr_data *xattr_value = NULL;
int xattr_len = 0;
bool violation_check;
enum hash_algo hash_algo;
if (!ima_policy_flag || !S_ISREG(inode->i_mode))
return 0;
/* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action
* bitmask based on the appraise/audit/measurement policy.
* Included is the appraise submask.
*/
action = ima_get_action(inode, mask, func, &pcr);
violation_check = ((func == FILE_CHECK || func == MMAP_CHECK) &&
(ima_policy_flag & IMA_MEASURE));
if (!action && !violation_check)
return 0;
must_appraise = action & IMA_APPRAISE;
/* Is the appraise rule hook specific? */
if (action & IMA_FILE_APPRAISE)
func = FILE_CHECK;
inode_lock(inode);
if (action) {
iint = integrity_inode_get(inode);
if (!iint)
goto out;
}
if (violation_check) {
ima_rdwr_violation_check(file, iint, action & IMA_MEASURE,
&pathbuf, &pathname);
if (!action) {
rc = 0;
goto out_free;
}
}
/* Determine if already appraised/measured based on bitmask
* (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED,
* IMA_AUDIT, IMA_AUDITED)
*/
iint->flags |= action;
action &= IMA_DO_MASK;
action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1);
/* If target pcr is already measured, unset IMA_MEASURE action */
if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr)))
action ^= IMA_MEASURE;
/* Nothing to do, just return existing appraised status */
if (!action) {
if (must_appraise)
rc = ima_get_cache_status(iint, func);
goto out_digsig;
}
template_desc = ima_template_desc_current();
if ((action & IMA_APPRAISE_SUBMASK) ||
strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0)
/* read 'security.ima' */
xattr_len = ima_read_xattr(file_dentry(file), &xattr_value);
hash_algo = ima_get_hash_algo(xattr_value, xattr_len);
rc = ima_collect_measurement(iint, file, buf, size, hash_algo);
if (rc != 0) {
if (file->f_flags & O_DIRECT)
rc = (iint->flags & IMA_PERMIT_DIRECTIO) ? 0 : -EACCES;
goto out_digsig;
}
if (!pathname) /* ima_rdwr_violation possibly pre-fetched */
pathname = ima_d_path(&file->f_path, &pathbuf);
if (action & IMA_MEASURE)
ima_store_measurement(iint, file, pathname,
xattr_value, xattr_len, pcr);
if (action & IMA_APPRAISE_SUBMASK)
rc = ima_appraise_measurement(func, iint, file, pathname,
xattr_value, xattr_len, opened);
if (action & IMA_AUDIT)
ima_audit_measurement(iint, pathname);
out_digsig:
if ((mask & MAY_WRITE) && (iint->flags & IMA_DIGSIG) &&
!(iint->flags & IMA_NEW_FILE))
rc = -EACCES;
kfree(xattr_value);
out_free:
if (pathbuf)
__putname(pathbuf);
out:
inode_unlock(inode);
if ((rc && must_appraise) && (ima_appraise & IMA_APPRAISE_ENFORCE))
return -EACCES;
return 0;
}
/**
* securityfs_create_file - create a file in the securityfs filesystem
*
* @name: a pointer to a string containing the name of the file to create.
* @mode: the permission that the file should have
* @parent: a pointer to the parent dentry for this file. This should be a
* directory dentry if set. If this parameter is %NULL, then the
* file will be created in the root of the securityfs filesystem.
* @data: a pointer to something that the caller will want to get to later
* on. The inode.i_private pointer will point to this value on
* the open() call.
* @fops: a pointer to a struct file_operations that should be used for
* this file.
*
* This is the basic "create a file" function for securityfs. It allows for a
* wide range of flexibility in creating a file, or a directory (if you
* want to create a directory, the securityfs_create_dir() function is
* recommended to be used instead).
*
* This function returns a pointer to a dentry if it succeeds. This
* pointer must be passed to the securityfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
* you are responsible here). If an error occurs, the function will return
* the error value (via ERR_PTR).
*
* If securityfs is not enabled in the kernel, the value %-ENODEV is
* returned.
*/
struct dentry *securityfs_create_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
const struct file_operations *fops)
{
struct dentry *dentry;
int is_dir = S_ISDIR(mode);
struct inode *dir, *inode;
int error;
if (!is_dir) {
BUG_ON(!fops);
mode = (mode & S_IALLUGO) | S_IFREG;
}
pr_debug("securityfs: creating file '%s'\n",name);
error = simple_pin_fs(&fs_type, &mount, &mount_count);
if (error)
return ERR_PTR(error);
if (!parent)
parent = mount->mnt_root;
dir = d_inode(parent);
inode_lock(dir);
dentry = lookup_one_len(name, parent, strlen(name));
if (IS_ERR(dentry))
goto out;
if (d_really_is_positive(dentry)) {
error = -EEXIST;
goto out1;
}
inode = new_inode(dir->i_sb);
if (!inode) {
error = -ENOMEM;
goto out1;
}
inode->i_ino = get_next_ino();
inode->i_mode = mode;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_private = data;
if (is_dir) {
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
inc_nlink(inode);
inc_nlink(dir);
} else {
inode->i_fop = fops;
}
d_instantiate(dentry, inode);
dget(dentry);
inode_unlock(dir);
return dentry;
out1:
dput(dentry);
dentry = ERR_PTR(error);
out:
inode_unlock(dir);
simple_release_fs(&mount, &mount_count);
return dentry;
}
static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
struct file *filp,
struct f2fs_defragment *range)
{
struct inode *inode = file_inode(filp);
struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
struct extent_info ei;
pgoff_t pg_start, pg_end;
unsigned int blk_per_seg = sbi->blocks_per_seg;
unsigned int total = 0, sec_num;
unsigned int pages_per_sec = sbi->segs_per_sec * blk_per_seg;
block_t blk_end = 0;
bool fragmented = false;
int err;
/* if in-place-update policy is enabled, don't waste time here */
if (need_inplace_update(inode))
return -EINVAL;
pg_start = range->start >> PAGE_CACHE_SHIFT;
pg_end = (range->start + range->len) >> PAGE_CACHE_SHIFT;
f2fs_balance_fs(sbi, true);
inode_lock(inode);
/* writeback all dirty pages in the range */
err = filemap_write_and_wait_range(inode->i_mapping, range->start,
range->start + range->len - 1);
if (err)
goto out;
/*
* lookup mapping info in extent cache, skip defragmenting if physical
* block addresses are continuous.
*/
if (f2fs_lookup_extent_cache(inode, pg_start, &ei)) {
if (ei.fofs + ei.len >= pg_end)
goto out;
}
map.m_lblk = pg_start;
/*
* lookup mapping info in dnode page cache, skip defragmenting if all
* physical block addresses are continuous even if there are hole(s)
* in logical blocks.
*/
while (map.m_lblk < pg_end) {
map.m_len = pg_end - map.m_lblk;
err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
if (err)
goto out;
if (!(map.m_flags & F2FS_MAP_FLAGS)) {
map.m_lblk++;
continue;
}
if (blk_end && blk_end != map.m_pblk) {
fragmented = true;
break;
}
blk_end = map.m_pblk + map.m_len;
map.m_lblk += map.m_len;
}
if (!fragmented)
goto out;
map.m_lblk = pg_start;
map.m_len = pg_end - pg_start;
sec_num = (map.m_len + pages_per_sec - 1) / pages_per_sec;
/*
* make sure there are enough free section for LFS allocation, this can
* avoid defragment running in SSR mode when free section are allocated
* intensively
*/
if (has_not_enough_free_secs(sbi, sec_num)) {
err = -EAGAIN;
goto out;
}
while (map.m_lblk < pg_end) {
pgoff_t idx;
int cnt = 0;
do_map:
map.m_len = pg_end - map.m_lblk;
err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
if (err)
goto clear_out;
if (!(map.m_flags & F2FS_MAP_FLAGS)) {
map.m_lblk++;
continue;
}
set_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
idx = map.m_lblk;
while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) {
struct page *page;
page = get_lock_data_page(inode, idx, true);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto clear_out;
}
set_page_dirty(page);
f2fs_put_page(page, 1);
idx++;
cnt++;
total++;
}
map.m_lblk = idx;
if (idx < pg_end && cnt < blk_per_seg)
goto do_map;
clear_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
err = filemap_fdatawrite(inode->i_mapping);
if (err)
goto out;
}
clear_out:
clear_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
out:
inode_unlock(inode);
if (!err)
range->len = (u64)total << PAGE_CACHE_SHIFT;
return err;
}
