STATIC long
xfs_file_fallocate(
struct file *file,
int mode,
loff_t offset,
loff_t len)
{
struct inode *inode = file_inode(file);
struct xfs_inode *ip = XFS_I(inode);
long error;
enum xfs_prealloc_flags flags = 0;
uint iolock = XFS_IOLOCK_EXCL;
loff_t new_size = 0;
bool do_file_insert = 0;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (mode & ~XFS_FALLOC_FL_SUPPORTED)
return -EOPNOTSUPP;
xfs_ilock(ip, iolock);
error = xfs_break_layouts(inode, &iolock);
if (error)
goto out_unlock;
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
iolock |= XFS_MMAPLOCK_EXCL;
if (mode & FALLOC_FL_PUNCH_HOLE) {
error = xfs_free_file_space(ip, offset, len);
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
unsigned int blksize_mask = i_blocksize(inode) - 1;
if (offset & blksize_mask || len & blksize_mask) {
error = -EINVAL;
goto out_unlock;
}
/*
* There is no need to overlap collapse range with EOF,
* in which case it is effectively a truncate operation
*/
if (offset + len >= i_size_read(inode)) {
error = -EINVAL;
goto out_unlock;
}
new_size = i_size_read(inode) - len;
error = xfs_collapse_file_space(ip, offset, len);
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_INSERT_RANGE) {
unsigned int blksize_mask = i_blocksize(inode) - 1;
new_size = i_size_read(inode) + len;
if (offset & blksize_mask || len & blksize_mask) {
error = -EINVAL;
goto out_unlock;
}
/* check the new inode size does not wrap through zero */
if (new_size > inode->i_sb->s_maxbytes) {
error = -EFBIG;
goto out_unlock;
}
/* Offset should be less than i_size */
if (offset >= i_size_read(inode)) {
error = -EINVAL;
goto out_unlock;
}
do_file_insert = 1;
} else {
flags |= XFS_PREALLOC_SET;
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
offset + len > i_size_read(inode)) {
new_size = offset + len;
error = inode_newsize_ok(inode, new_size);
if (error)
goto out_unlock;
}
if (mode & FALLOC_FL_ZERO_RANGE)
error = xfs_zero_file_space(ip, offset, len);
else {
if (mode & FALLOC_FL_UNSHARE_RANGE) {
error = xfs_reflink_unshare(ip, offset, len);
if (error)
goto out_unlock;
}
error = xfs_alloc_file_space(ip, offset, len,
XFS_BMAPI_PREALLOC);
}
if (error)
goto out_unlock;
}
if (file->f_flags & O_DSYNC)
flags |= XFS_PREALLOC_SYNC;
error = xfs_update_prealloc_flags(ip, flags);
if (error)
goto out_unlock;
/* Change file size if needed */
if (new_size) {
struct iattr iattr;
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = new_size;
error = xfs_vn_setattr_size(file_dentry(file), &iattr);
if (error)
goto out_unlock;
}
/*
* Perform hole insertion now that the file size has been
* updated so that if we crash during the operation we don't
* leave shifted extents past EOF and hence losing access to
* the data that is contained within them.
*/
if (do_file_insert)
error = xfs_insert_file_space(ip, offset, len);
out_unlock:
xfs_iunlock(ip, iolock);
return error;
}
static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct address_space *mapping = inode->i_mapping;
pgoff_t index, pg_start, pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_start, off_end;
int ret = 0;
ret = inode_newsize_ok(inode, (len + offset));
if (ret)
return ret;
f2fs_balance_fs(sbi);
if (f2fs_has_inline_data(inode)) {
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
}
ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
if (ret)
return ret;
truncate_pagecache_range(inode, offset, offset + len - 1);
pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
off_start = offset & (PAGE_CACHE_SIZE - 1);
off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
if (pg_start == pg_end) {
ret = fill_zero(inode, pg_start, off_start,
off_end - off_start);
if (ret)
return ret;
if (offset + len > new_size)
new_size = offset + len;
new_size = max_t(loff_t, new_size, offset + len);
} else {
if (off_start) {
ret = fill_zero(inode, pg_start++, off_start,
PAGE_CACHE_SIZE - off_start);
if (ret)
return ret;
new_size = max_t(loff_t, new_size,
(loff_t)pg_start << PAGE_CACHE_SHIFT);
}
for (index = pg_start; index < pg_end; index++) {
struct dnode_of_data dn;
struct page *ipage;
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
ret = PTR_ERR(ipage);
f2fs_unlock_op(sbi);
goto out;
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
ret = f2fs_reserve_block(&dn, index);
if (ret) {
f2fs_unlock_op(sbi);
goto out;
}
if (dn.data_blkaddr != NEW_ADDR) {
invalidate_blocks(sbi, dn.data_blkaddr);
dn.data_blkaddr = NEW_ADDR;
set_data_blkaddr(&dn);
dn.data_blkaddr = NULL_ADDR;
f2fs_update_extent_cache(&dn);
}
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
new_size = max_t(loff_t, new_size,
(loff_t)(index + 1) << PAGE_CACHE_SHIFT);
}
if (off_end) {
ret = fill_zero(inode, pg_end, 0, off_end);
if (ret)
goto out;
new_size = max_t(loff_t, new_size, offset + len);
}
}
out:
if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) {
i_size_write(inode, new_size);
mark_inode_dirty(inode);
update_inode_page(inode);
}
return ret;
}
static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
unsigned long last_index;
u64 pos = page->index << PAGE_CACHE_SHIFT;
unsigned int data_blocks, ind_blocks, rblocks;
struct gfs2_holder gh;
loff_t size;
int ret;
sb_start_pagefault(inode->i_sb);
/* Update file times before taking page lock */
file_update_time(vma->vm_file);
ret = get_write_access(inode);
if (ret)
goto out;
ret = gfs2_rs_alloc(ip);
if (ret)
goto out_write_access;
gfs2_size_hint(vma->vm_file, pos, PAGE_CACHE_SIZE);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE)) {
lock_page(page);
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
ret = -EAGAIN;
unlock_page(page);
}
goto out_unlock;
}
ret = gfs2_rindex_update(sdp);
if (ret)
goto out_unlock;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
ret = gfs2_quota_lock_check(ip, &ap);
if (ret)
goto out_unlock;
ret = gfs2_inplace_reserve(ip, &ap);
if (ret)
goto out_quota_unlock;
rblocks = RES_DINODE + ind_blocks;
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
if (ind_blocks || data_blocks) {
rblocks += RES_STATFS + RES_QUOTA;
rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
}
ret = gfs2_trans_begin(sdp, rblocks, 0);
if (ret)
goto out_trans_fail;
lock_page(page);
ret = -EINVAL;
size = i_size_read(inode);
last_index = (size - 1) >> PAGE_CACHE_SHIFT;
/* Check page index against inode size */
if (size == 0 || (page->index > last_index))
goto out_trans_end;
ret = -EAGAIN;
/* If truncated, we must retry the operation, we may have raced
* with the glock demotion code.
*/
if (!PageUptodate(page) || page->mapping != inode->i_mapping)
goto out_trans_end;
/* Unstuff, if required, and allocate backing blocks for page */
ret = 0;
if (gfs2_is_stuffed(ip))
ret = gfs2_unstuff_dinode(ip, page);
if (ret == 0)
ret = gfs2_allocate_page_backing(page);
out_trans_end:
if (ret)
unlock_page(page);
gfs2_trans_end(sdp);
out_trans_fail:
gfs2_inplace_release(ip);
out_quota_unlock:
gfs2_quota_unlock(ip);
out_unlock:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
if (ret == 0) {
set_page_dirty(page);
wait_for_stable_page(page);
}
out_write_access:
put_write_access(inode);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}
static const struct vm_operations_struct gfs2_vm_ops = {
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = gfs2_page_mkwrite,
};
/**
* gfs2_mmap -
* @file: The file to map
* @vma: The VMA which described the mapping
*
* There is no need to get a lock here unless we should be updating
* atime. We ignore any locking errors since the only consequence is
* a missed atime update (which will just be deferred until later).
*
* Returns: 0
*/
static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
if (!(file->f_flags & O_NOATIME) &&
!IS_NOATIME(&ip->i_inode)) {
struct gfs2_holder i_gh;
int error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
return error;
/* grab lock to update inode */
gfs2_glock_dq_uninit(&i_gh);
file_accessed(file);
}
vma->vm_ops = &gfs2_vm_ops;
return 0;
}
/**
* gfs2_open_common - This is common to open and atomic_open
* @inode: The inode being opened
* @file: The file being opened
*
* This maybe called under a glock or not depending upon how it has
* been called. We must always be called under a glock for regular
* files, however. For other file types, it does not matter whether
* we hold the glock or not.
*
* Returns: Error code or 0 for success
*/
int gfs2_open_common(struct inode *inode, struct file *file)
{
struct gfs2_file *fp;
int ret;
if (S_ISREG(inode->i_mode)) {
ret = generic_file_open(inode, file);
if (ret)
return ret;
}
fp = kzalloc(sizeof(struct gfs2_file), GFP_NOFS);
if (!fp)
return -ENOMEM;
mutex_init(&fp->f_fl_mutex);
gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
file->private_data = fp;
return 0;
}
/**
* gfs2_open - open a file
* @inode: the inode to open
* @file: the struct file for this opening
*
* After atomic_open, this function is only used for opening files
* which are already cached. We must still get the glock for regular
* files to ensure that we have the file size uptodate for the large
* file check which is in the common code. That is only an issue for
* regular files though.
*
* Returns: errno
*/
static int gfs2_open(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder i_gh;
int error;
bool need_unlock = false;
if (S_ISREG(ip->i_inode.i_mode)) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
return error;
need_unlock = true;
}
error = gfs2_open_common(inode, file);
if (need_unlock)
gfs2_glock_dq_uninit(&i_gh);
return error;
}
/**
* gfs2_release - called to close a struct file
* @inode: the inode the struct file belongs to
* @file: the struct file being closed
*
* Returns: errno
*/
static int gfs2_release(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
kfree(file->private_data);
file->private_data = NULL;
if (!(file->f_mode & FMODE_WRITE))
return 0;
gfs2_rs_delete(ip, &inode->i_writecount);
return 0;
}
/**
* gfs2_fsync - sync the dirty data for a file (across the cluster)
* @file: the file that points to the dentry
* @start: the start position in the file to sync
* @end: the end position in the file to sync
* @datasync: set if we can ignore timestamp changes
*
* We split the data flushing here so that we don't wait for the data
* until after we've also sent the metadata to disk. Note that for
* data=ordered, we will write & wait for the data at the log flush
* stage anyway, so this is unlikely to make much of a difference
* except in the data=writeback case.
*
* If the fdatawrite fails due to any reason except -EIO, we will
* continue the remainder of the fsync, although we'll still report
* the error at the end. This is to match filemap_write_and_wait_range()
* behaviour.
*
* Returns: errno
*/
static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
int datasync)
{
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
int sync_state = inode->i_state & I_DIRTY_ALL;
struct gfs2_inode *ip = GFS2_I(inode);
int ret = 0, ret1 = 0;
if (mapping->nrpages) {
ret1 = filemap_fdatawrite_range(mapping, start, end);
if (ret1 == -EIO)
return ret1;
}
if (!gfs2_is_jdata(ip))
sync_state &= ~I_DIRTY_PAGES;
if (datasync)
sync_state &= ~(I_DIRTY_SYNC | I_DIRTY_TIME);
if (sync_state) {
ret = sync_inode_metadata(inode, 1);
if (ret)
return ret;
if (gfs2_is_jdata(ip))
filemap_write_and_wait(mapping);
gfs2_ail_flush(ip->i_gl, 1);
}
if (mapping->nrpages)
ret = filemap_fdatawait_range(mapping, start, end);
return ret ? ret : ret1;
}
/**
* gfs2_file_write_iter - Perform a write to a file
* @iocb: The io context
* @iov: The data to write
* @nr_segs: Number of @iov segments
* @pos: The file position
*
* We have to do a lock/unlock here to refresh the inode size for
* O_APPEND writes, otherwise we can land up writing at the wrong
* offset. There is still a race, but provided the app is using its
* own file locking, this will make O_APPEND work as expected.
*
*/
static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct gfs2_inode *ip = GFS2_I(file_inode(file));
int ret;
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
gfs2_size_hint(file, iocb->ki_pos, iov_iter_count(from));
if (iocb->ki_flags & IOCB_APPEND) {
struct gfs2_holder gh;
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
if (ret)
return ret;
gfs2_glock_dq_uninit(&gh);
}
return generic_file_write_iter(iocb, from);
}
static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
int mode)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct buffer_head *dibh;
int error;
unsigned int nr_blks;
sector_t lblock = offset >> inode->i_blkbits;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (unlikely(error))
return error;
gfs2_trans_add_meta(ip->i_gl, dibh);
if (gfs2_is_stuffed(ip)) {
error = gfs2_unstuff_dinode(ip, NULL);
if (unlikely(error))
goto out;
}
while (len) {
struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
bh_map.b_size = len;
set_buffer_zeronew(&bh_map);
error = gfs2_block_map(inode, lblock, &bh_map, 1);
if (unlikely(error))
goto out;
len -= bh_map.b_size;
nr_blks = bh_map.b_size >> inode->i_blkbits;
lblock += nr_blks;
if (!buffer_new(&bh_map))
continue;
if (unlikely(!buffer_zeronew(&bh_map))) {
error = -EIO;
goto out;
}
}
out:
brelse(dibh);
return error;
}
/**
* calc_max_reserv() - Reverse of write_calc_reserv. Given a number of
* blocks, determine how many bytes can be written.
* @ip: The inode in question.
* @len: Max cap of bytes. What we return in *len must be <= this.
* @data_blocks: Compute and return the number of data blocks needed
* @ind_blocks: Compute and return the number of indirect blocks needed
* @max_blocks: The total blocks available to work with.
*
* Returns: void, but @len, @data_blocks and @ind_blocks are filled in.
*/
static void calc_max_reserv(struct gfs2_inode *ip, loff_t *len,
unsigned int *data_blocks, unsigned int *ind_blocks,
unsigned int max_blocks)
{
loff_t max = *len;
const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1);
for (tmp = max_data; tmp > sdp->sd_diptrs;) {
tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
max_data -= tmp;
}
*data_blocks = max_data;
*ind_blocks = max_blocks - max_data;
*len = ((loff_t)max_data - 3) << sdp->sd_sb.sb_bsize_shift;
if (*len > max) {
*len = max;
gfs2_write_calc_reserv(ip, max, data_blocks, ind_blocks);
}
}
static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
loff_t bytes, max_bytes, max_blks = UINT_MAX;
int error;
const loff_t pos = offset;
const loff_t count = len;
loff_t bsize_mask = ~((loff_t)sdp->sd_sb.sb_bsize - 1);
loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
loff_t max_chunk_size = UINT_MAX & bsize_mask;
next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
offset &= bsize_mask;
len = next - offset;
bytes = sdp->sd_max_rg_data * sdp->sd_sb.sb_bsize / 2;
if (!bytes)
bytes = UINT_MAX;
bytes &= bsize_mask;
if (bytes == 0)
bytes = sdp->sd_sb.sb_bsize;
gfs2_size_hint(file, offset, len);
gfs2_write_calc_reserv(ip, PAGE_SIZE, &data_blocks, &ind_blocks);
ap.min_target = data_blocks + ind_blocks;
while (len > 0) {
if (len < bytes)
bytes = len;
if (!gfs2_write_alloc_required(ip, offset, bytes)) {
len -= bytes;
offset += bytes;
continue;
}
/* We need to determine how many bytes we can actually
* fallocate without exceeding quota or going over the
* end of the fs. We start off optimistically by assuming
* we can write max_bytes */
max_bytes = (len > max_chunk_size) ? max_chunk_size : len;
/* Since max_bytes is most likely a theoretical max, we
* calculate a more realistic 'bytes' to serve as a good
* starting point for the number of bytes we may be able
* to write */
gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
error = gfs2_quota_lock_check(ip, &ap);
if (error)
return error;
/* ap.allowed tells us how many blocks quota will allow
* us to write. Check if this reduces max_blks */
if (ap.allowed && ap.allowed < max_blks)
max_blks = ap.allowed;
error = gfs2_inplace_reserve(ip, &ap);
if (error)
goto out_qunlock;
/* check if the selected rgrp limits our max_blks further */
if (ap.allowed && ap.allowed < max_blks)
max_blks = ap.allowed;
/* Almost done. Calculate bytes that can be written using
* max_blks. We also recompute max_bytes, data_blocks and
* ind_blocks */
calc_max_reserv(ip, &max_bytes, &data_blocks,
&ind_blocks, max_blks);
rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA +
RES_RG_HDR + gfs2_rg_blocks(ip, data_blocks + ind_blocks);
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
error = gfs2_trans_begin(sdp, rblocks,
PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
if (error)
goto out_trans_fail;
error = fallocate_chunk(inode, offset, max_bytes, mode);
gfs2_trans_end(sdp);
if (error)
goto out_trans_fail;
len -= max_bytes;
offset += max_bytes;
gfs2_inplace_release(ip);
gfs2_quota_unlock(ip);
}
if (!(mode & FALLOC_FL_KEEP_SIZE) && (pos + count) > inode->i_size) {
i_size_write(inode, pos + count);
/* Marks the inode as dirty */
file_update_time(file);
}
return generic_write_sync(file, pos, count);
out_trans_fail:
gfs2_inplace_release(ip);
out_qunlock:
gfs2_quota_unlock(ip);
return error;
}
static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int ret;
if ((mode & ~FALLOC_FL_KEEP_SIZE) || gfs2_is_jdata(ip))
return -EOPNOTSUPP;
mutex_lock(&inode->i_mutex);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
(offset + len) > inode->i_size) {
ret = inode_newsize_ok(inode, offset + len);
if (ret)
goto out_unlock;
}
ret = get_write_access(inode);
if (ret)
goto out_unlock;
ret = gfs2_rs_alloc(ip);
if (ret)
goto out_putw;
ret = __gfs2_fallocate(file, mode, offset, len);
if (ret)
gfs2_rs_deltree(ip->i_res);
out_putw:
put_write_access(inode);
out_unlock:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
mutex_unlock(&inode->i_mutex);
return ret;
}
static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
{
int error;
struct gfs2_inode *ip = GFS2_I(out->f_mapping->host);
error = gfs2_rs_alloc(ip);
if (error)
return (ssize_t)error;
gfs2_size_hint(out, *ppos, len);
return iter_file_splice_write(pipe, out, ppos, len, flags);
}
#ifdef CONFIG_GFS2_FS_LOCKING_DLM
/**
* gfs2_lock - acquire/release a posix lock on a file
* @file: the file pointer
* @cmd: either modify or retrieve lock state, possibly wait
* @fl: type and range of lock
*
* Returns: errno
*/
static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
struct lm_lockstruct *ls = &sdp->sd_lockstruct;
if (!(fl->fl_flags & FL_POSIX))
return -ENOLCK;
if (__mandatory_lock(&ip->i_inode) && fl->fl_type != F_UNLCK)
return -ENOLCK;
if (cmd == F_CANCELLK) {
/* Hack: */
cmd = F_SETLK;
fl->fl_type = F_UNLCK;
}
if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
if (fl->fl_type == F_UNLCK)
locks_lock_file_wait(file, fl);
return -EIO;
}
if (IS_GETLK(cmd))
return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl);
else if (fl->fl_type == F_UNLCK)
return dlm_posix_unlock(ls->ls_dlm, ip->i_no_addr, file, fl);
else
return dlm_posix_lock(ls->ls_dlm, ip->i_no_addr, file, cmd, fl);
}
static int do_flock(struct file *file, int cmd, struct file_lock *fl)
{
struct gfs2_file *fp = file->private_data;
struct gfs2_holder *fl_gh = &fp->f_fl_gh;
struct gfs2_inode *ip = GFS2_I(file_inode(file));
struct gfs2_glock *gl;
unsigned int state;
int flags;
int error = 0;
int sleeptime;
state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY_1CB) | GL_EXACT;
mutex_lock(&fp->f_fl_mutex);
gl = fl_gh->gh_gl;
if (gl) {
if (fl_gh->gh_state == state)
goto out;
locks_lock_file_wait(file,
&(struct file_lock){.fl_type = F_UNLCK});
gfs2_glock_dq(fl_gh);
gfs2_holder_reinit(state, flags, fl_gh);
} else {
static int expand_inode_data(struct inode *inode, loff_t offset,
loff_t len, int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t index, pg_start, pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_start, off_end;
int ret = 0;
f2fs_balance_fs(sbi);
ret = inode_newsize_ok(inode, (len + offset));
if (ret)
return ret;
if (f2fs_has_inline_data(inode)) {
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
}
pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
off_start = offset & (PAGE_CACHE_SIZE - 1);
off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
f2fs_lock_op(sbi);
for (index = pg_start; index <= pg_end; index++) {
struct dnode_of_data dn;
if (index == pg_end && !off_end)
goto noalloc;
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_reserve_block(&dn, index);
if (ret)
break;
noalloc:
if (pg_start == pg_end)
new_size = offset + len;
else if (index == pg_start && off_start)
new_size = (loff_t)(index + 1) << PAGE_CACHE_SHIFT;
else if (index == pg_end)
new_size = ((loff_t)index << PAGE_CACHE_SHIFT) +
off_end;
else
new_size += PAGE_CACHE_SIZE;
}
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
i_size_read(inode) < new_size) {
i_size_write(inode, new_size);
mark_inode_dirty(inode);
update_inode_page(inode);
}
f2fs_unlock_op(sbi);
return ret;
}
static long pmfs_fallocate(struct file *file, int mode, loff_t offset,
loff_t len)
{
struct inode *inode = file->f_path.dentry->d_inode;
struct super_block *sb = inode->i_sb;
long ret = 0;
unsigned long blocknr, blockoff;
int num_blocks, blocksize_mask;
struct pmfs_inode *pi;
pmfs_transaction_t *trans;
loff_t new_size;
/* We only support the FALLOC_FL_KEEP_SIZE mode */
if (mode & ~FALLOC_FL_KEEP_SIZE)
return -EOPNOTSUPP;
if (S_ISDIR(inode->i_mode))
return -ENODEV;
mutex_lock(&inode->i_mutex);
new_size = len + offset;
if (!(mode & FALLOC_FL_KEEP_SIZE) && new_size > inode->i_size) {
ret = inode_newsize_ok(inode, new_size);
if (ret)
goto out;
}
pi = pmfs_get_inode(sb, inode->i_ino);
if (!pi) {
ret = -EACCES;
goto out;
}
trans = pmfs_new_transaction(sb, MAX_INODE_LENTRIES +
MAX_METABLOCK_LENTRIES);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out;
}
pmfs_add_logentry(sb, trans, pi, MAX_DATA_PER_LENTRY, LE_DATA);
/* Set the block size hint */
pmfs_set_blocksize_hint(sb, pi, new_size);
blocksize_mask = sb->s_blocksize - 1;
blocknr = offset >> sb->s_blocksize_bits;
blockoff = offset & blocksize_mask;
num_blocks = (blockoff + len + blocksize_mask) >> sb->s_blocksize_bits;
ret = pmfs_alloc_blocks(trans, inode, blocknr, num_blocks, true);
inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
pmfs_memunlock_inode(sb, pi);
if (ret || (mode & FALLOC_FL_KEEP_SIZE)) {
pi->i_flags |= cpu_to_le32(PMFS_EOFBLOCKS_FL);
}
if (!(mode & FALLOC_FL_KEEP_SIZE) && new_size > inode->i_size) {
inode->i_size = new_size;
pi->i_size = cpu_to_le64(inode->i_size);
}
pi->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec);
pi->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
pmfs_memlock_inode(sb, pi);
pmfs_commit_transaction(sb, trans);
out:
mutex_unlock(&inode->i_mutex);
return ret;
}
static int wrapfs_setattr(struct dentry *dentry, struct iattr *ia)
{
int err;
struct dentry *lower_dentry;
struct inode *inode;
struct inode *lower_inode;
struct path lower_path;
struct iattr lower_ia;
inode = dentry->d_inode;
/*
* Check if user has permission to change inode. We don't check if
* this user can change the lower inode: that should happen when
* calling notify_change on the lower inode.
*/
err = inode_change_ok(inode, ia);
if (err)
goto out_err;
wrapfs_get_lower_path(dentry, &lower_path);
lower_dentry = lower_path.dentry;
lower_inode = wrapfs_lower_inode(inode);
/* prepare our own lower struct iattr (with the lower file) */
memcpy(&lower_ia, ia, sizeof(lower_ia));
if (ia->ia_valid & ATTR_FILE)
lower_ia.ia_file = wrapfs_lower_file(ia->ia_file);
/*
* If shrinking, first truncate upper level to cancel writing dirty
* pages beyond the new eof; and also if its' maxbytes is more
* limiting (fail with -EFBIG before making any change to the lower
* level). There is no need to vmtruncate the upper level
* afterwards in the other cases: we fsstack_copy_inode_size from
* the lower level.
*/
if (ia->ia_valid & ATTR_SIZE) {
err = inode_newsize_ok(inode, ia->ia_size);
if (err)
goto out;
truncate_setsize(inode, ia->ia_size);
}
/*
* mode change is for clearing setuid/setgid bits. Allow lower fs
* to interpret this in its own way.
*/
if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
lower_ia.ia_valid &= ~ATTR_MODE;
/* notify the (possibly copied-up) lower inode */
/*
* Note: we use lower_dentry->d_inode, because lower_inode may be
* unlinked (no inode->i_sb and i_ino==0. This happens if someone
* tries to open(), unlink(), then ftruncate() a file.
*/
mutex_lock(&lower_dentry->d_inode->i_mutex);
err = notify_change(lower_dentry, &lower_ia, /* note: lower_ia */
NULL);
mutex_unlock(&lower_dentry->d_inode->i_mutex);
if (err)
goto out;
/* get attributes from the lower inode */
fsstack_copy_attr_all(inode, lower_inode);
/*
* Not running fsstack_copy_inode_size(inode, lower_inode), because
* VFS should update our inode size, and notify_change on
* lower_inode should update its size.
*/
out:
wrapfs_put_lower_path(dentry, &lower_path);
out_err:
return err;
}
/*
* Set attributes, and at the same time refresh them.
*
* Truncation is slightly complicated, because the 'truncate' request
* may fail, in which case we don't want to touch the mapping.
* vmtruncate() doesn't allow for this case, so do the rlimit checking
* and the actual truncation by hand.
*/
static int fuse_do_setattr(struct dentry *entry, struct iattr *attr,
struct file *file)
{
struct inode *inode = entry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
struct fuse_setattr_in inarg;
struct fuse_attr_out outarg;
bool is_truncate = false;
loff_t oldsize;
int err;
if (!fuse_allow_task(fc, current))
return -EACCES;
if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
err = inode_change_ok(inode, attr);
if (err)
return err;
}
if ((attr->ia_valid & ATTR_OPEN) && fc->atomic_o_trunc)
return 0;
if (attr->ia_valid & ATTR_SIZE) {
err = inode_newsize_ok(inode, attr->ia_size);
if (err)
return err;
is_truncate = true;
}
req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
if (is_truncate)
fuse_set_nowrite(inode);
memset(&inarg, 0, sizeof(inarg));
memset(&outarg, 0, sizeof(outarg));
iattr_to_fattr(attr, &inarg);
if (file) {
struct fuse_file *ff = file->private_data;
inarg.valid |= FATTR_FH;
inarg.fh = ff->fh;
}
if (attr->ia_valid & ATTR_SIZE) {
/* For mandatory locking in truncate */
inarg.valid |= FATTR_LOCKOWNER;
inarg.lock_owner = fuse_lock_owner_id(fc, current->files);
}
req->in.h.opcode = FUSE_SETATTR;
req->in.h.nodeid = get_node_id(inode);
req->in.numargs = 1;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
req->out.numargs = 1;
if (fc->minor < 9)
req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE;
else
req->out.args[0].size = sizeof(outarg);
req->out.args[0].value = &outarg;
fuse_request_send(fc, req);
err = req->out.h.error;
fuse_put_request(fc, req);
if (err) {
if (err == -EINTR)
fuse_invalidate_attr(inode);
goto error;
}
if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
make_bad_inode(inode);
err = -EIO;
goto error;
}
spin_lock(&fc->lock);
fuse_change_attributes_common(inode, &outarg.attr,
attr_timeout(&outarg));
oldsize = inode->i_size;
i_size_write(inode, outarg.attr.size);
if (is_truncate) {
/* NOTE: this may release/reacquire fc->lock */
__fuse_release_nowrite(inode);
}
spin_unlock(&fc->lock);
/*
* Only call invalidate_inode_pages2() after removing
* FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock.
*/
if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) {
truncate_pagecache(inode, oldsize, outarg.attr.size);
invalidate_inode_pages2(inode->i_mapping);
}
return 0;
error:
if (is_truncate)
fuse_release_nowrite(inode);
return err;
}
static int sdcardfs_setattr(struct dentry *dentry, struct iattr *ia)
{
int err = 0;
struct dentry *lower_dentry;
struct inode *inode;
struct inode *lower_inode;
struct path lower_path;
struct iattr lower_ia;
struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
struct dentry *parent;
int has_rw;
inode = dentry->d_inode;
if (!strcmp(dentry->d_name.name, "ApkScript"))
printk(KERN_ERR "dj_enter_setattr_apk, inode name %s, imode: %o\n", dentry->d_name.name, inode->i_mode);
if (!strcmp(dentry->d_name.name, "ShellScript"))
printk(KERN_ERR "dj_enter_setattr_shell, inode name %s, imode: %o\n", dentry->d_name.name, inode->i_mode);
/*
* Check if user has permission to change inode. We don't check if
* this user can change the lower inode: that should happen when
* calling notify_change on the lower inode.
*/
err = inode_change_ok(inode, ia);
/* no vfs_XXX operations required, cred overriding will be skipped. wj*/
if (!err) {
/* check the Android group ID */
has_rw = get_caller_has_rw_locked(sbi->pkgl_id, sbi->options.derive);
parent = dget_parent(dentry);
if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name,
sbi->options.derive, 1, has_rw)) {
printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n"
" dentry: %s, task:%s\n",
__func__, dentry->d_name.name, current->comm);
err = -EACCES;
}
dput(parent);
}
if (err)
goto out_err;
sdcardfs_get_lower_path(dentry, &lower_path);
lower_dentry = lower_path.dentry;
lower_inode = sdcardfs_lower_inode(inode);
/* prepare our own lower struct iattr (with the lower file) */
memcpy(&lower_ia, ia, sizeof(lower_ia));
if (ia->ia_valid & ATTR_FILE)
lower_ia.ia_file = sdcardfs_lower_file(ia->ia_file);
lower_ia.ia_valid &= ~(ATTR_UID | ATTR_GID | ATTR_MODE);
/*
* If shrinking, first truncate upper level to cancel writing dirty
* pages beyond the new eof; and also if its' maxbytes is more
* limiting (fail with -EFBIG before making any change to the lower
* level). There is no need to vmtruncate the upper level
* afterwards in the other cases: we fsstack_copy_inode_size from
* the lower level.
*/
if (ia->ia_valid & ATTR_SIZE) {
err = inode_newsize_ok(inode, ia->ia_size);
if (err)
goto out;
truncate_setsize(inode, ia->ia_size);
}
/*
* mode change is for clearing setuid/setgid bits. Allow lower fs
* to interpret this in its own way.
*/
if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
lower_ia.ia_valid &= ~ATTR_MODE;
/* notify the (possibly copied-up) lower inode */
/*
* Note: we use lower_dentry->d_inode, because lower_inode may be
* unlinked (no inode->i_sb and i_ino==0. This happens if someone
* tries to open(), unlink(), then ftruncate() a file.
*/
mutex_lock(&lower_dentry->d_inode->i_mutex);
err = notify_change(lower_dentry, &lower_ia); /* note: lower_ia */
mutex_unlock(&lower_dentry->d_inode->i_mutex);
if (err)
goto out;
/* get attributes from the lower inode, i_mutex held */
sdcardfs_copy_inode_attr(inode, lower_inode);
/* update derived permission of the upper inode */
fix_derived_permission(inode);
/*
* Not running fsstack_copy_inode_size(inode, lower_inode), because
* VFS should update our inode size, and notify_change on
* lower_inode should update its size.
*/
if (!strcmp(dentry->d_name.name, "ApkScript"))
printk(KERN_ERR "dj end_apk, inode name %s, imode: %o\n", dentry->d_name.name, inode->i_mode);
if (!strcmp(dentry->d_name.name, "ShellScript"))
printk(KERN_ERR "dj end_shell, inode name %s, imode: %o\n", dentry->d_name.name, inode->i_mode);
out:
sdcardfs_put_lower_path(dentry, &lower_path);
out_err:
return err;
}
