/*
* Check whether the dentry is still valid
*
* If the entry validity timeout has expired and the dentry is
* positive, try to redo the lookup. If the lookup results in a
* different inode, then let the VFS invalidate the dentry and redo
* the lookup once more. If the lookup results in the same inode,
* then refresh the attributes, timeouts and mark the dentry valid.
*/
static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
{
struct _inode *inode = d_get_inode(entry);
if (inode && is_bad_inode(inode))
return 0;
else if (fuse_dentry_time(entry) < get_jiffies_64()) {
int err;
struct fuse_entry_out outarg;
struct fuse_conn *fc;
struct fuse_req *req;
struct fuse_req *forget_req;
struct dentry *parent;
/* For negative dentries, always do a fresh lookup */
if (!inode)
return 0;
fc = get_fuse_conn(inode);
req = fuse_get_req(fc);
if (IS_ERR(req))
return 0;
forget_req = fuse_get_req(fc);
if (IS_ERR(forget_req)) {
fuse_put_request(fc, req);
return 0;
}
parent = dget_parent(entry);
fuse_lookup_init(req, d_get_inode(parent), entry, &outarg);
request_send(fc, req);
dput(parent);
err = req->out.h.error;
fuse_put_request(fc, req);
/* Zero nodeid is same as -ENOENT */
if (!err && !outarg.nodeid)
err = -ENOENT;
if (!err) {
struct fuse_inode *fi = _get_fuse_inode(inode);
if (outarg.nodeid != _get_node_id(inode)) {
fuse_send_forget(fc, forget_req,
outarg.nodeid, 1);
return 0;
}
spin_lock(&fc->lock);
fi->nlookup ++;
spin_unlock(&fc->lock);
}
fuse_put_request(fc, forget_req);
if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
return 0;
fuse_change_attributes(inode, &outarg.attr);
fuse_change_timeout(entry, &outarg);
}
return 1;
}
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
int error;
int block;
struct _inode * inode = d_get_inode(file_get_dentry(filp));
int __user *p = (int __user *)arg;
switch (cmd) {
case FIBMAP:
{
struct address_space *mapping = filp->f_mapping;
int res;
/* do we support this mess? */
if (!mapping->a_ops->bmap)
return -EINVAL;
if (!capable(CAP_SYS_RAWIO))
return -EPERM;
if ((error = get_user(block, p)) != 0)
return error;
lock_kernel();
res = mapping->a_ops->bmap(mapping, block);
unlock_kernel();
return put_user(res, p);
}
case FIGETBSZ:
return put_user(inode->i_sb->s_blocksize, p);
case FIONREAD:
return put_user(i_size_read(inode) - tx_cache_get_file_ro(filp)->f_pos, p);
}
return do_ioctl(filp, cmd, arg);
}
asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
mode_t mode)
{
struct nameidata nd;
struct _inode * inode;
int error;
struct iattr newattrs;
error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd);
if (error)
goto out;
inode = d_get_inode(nd.dentry);
error = -EROFS;
if (IS_RDONLY(inode))
goto dput_and_out;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto dput_and_out;
imutex_lock(parent(inode));
if (mode == (mode_t) -1)
mode = inode->i_mode;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
error = notify_change(nd.dentry, &newattrs);
imutex_unlock(parent(inode));
dput_and_out:
path_release(&nd);
out:
return error;
}
static int fuse_link(struct dentry *entry, struct _inode *newdir,
struct dentry *newent)
{
int err;
struct fuse_link_in inarg;
struct _inode *inode = d_get_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
memset(&inarg, 0, sizeof(inarg));
inarg.oldnodeid = _get_node_id(inode);
req->in.h.opcode = FUSE_LINK;
req->in.numargs = 2;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
req->in.args[1].size = newent->d_name.len + 1;
req->in.args[1].value = newent->d_name.name;
err = create_new_entry(fc, req, newdir, newent, inode->i_mode);
/* Contrary to "normal" filesystems it can happen that link
makes two "logical" inodes point to the same "physical"
inode. We invalidate the attributes of the old one, so it
will reflect changes in the backing inode (link count,
etc.)
*/
if (!err || err == -EINTR)
fuse_invalidate_attr(inode);
return err;
}
int do_truncate(struct _dentry *dentry, loff_t length, unsigned int time_attrs,
struct file *filp)
{
int err;
struct iattr newattrs;
struct inode *inode;
/* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */
if (length < 0)
return -EINVAL;
newattrs.ia_size = length;
newattrs.ia_valid = ATTR_SIZE | time_attrs;
if (filp) {
newattrs.ia_file = filp;
newattrs.ia_valid |= ATTR_FILE;
}
/* Remove suid/sgid on truncate too */
newattrs.ia_valid |= should_remove_suid(dentry);
inode = parent(d_get_inode(dentry));
imutex_lock(inode);
err = notify_change(dentry, &newattrs);
imutex_unlock(inode);
return err;
}
static int fuse_unlink(struct _inode *dir, struct dentry *entry)
{
int err;
struct fuse_conn *fc = get_fuse_conn(dir);
struct fuse_req *req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
req->in.h.opcode = FUSE_UNLINK;
req->in.h.nodeid = _get_node_id(dir);
req->in.numargs = 1;
req->in.args[0].size = entry->d_name.len + 1;
req->in.args[0].value = entry->d_name.name;
request_send(fc, req);
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err) {
struct _inode *inode = d_get_inode(entry);
/* Set nlink to zero so the inode can be cleared, if
the inode does have more links this will be
discovered at the next lookup/getattr */
clear_nlink(inode);
fuse_invalidate_attr(inode);
fuse_invalidate_attr(dir);
fuse_invalidate_entry_cache(entry);
} else if (err == -EINTR)
fuse_invalidate_entry(entry);
return err;
}
static char *read_link(struct dentry *dentry)
{
struct _inode *inode = d_get_inode(dentry);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req = fuse_get_req(fc);
char *link;
if (IS_ERR(req))
return ERR_PTR(PTR_ERR(req));
link = (char *) __get_free_page(GFP_KERNEL);
if (!link) {
link = ERR_PTR(-ENOMEM);
goto out;
}
req->in.h.opcode = FUSE_READLINK;
req->in.h.nodeid = _get_node_id(inode);
req->out.argvar = 1;
req->out.numargs = 1;
req->out.args[0].size = PAGE_SIZE - 1;
req->out.args[0].value = link;
request_send(fc, req);
if (req->out.h.error) {
free_page((unsigned long) link);
link = ERR_PTR(req->out.h.error);
} else
link[req->out.args[0].size] = '\0';
out:
fuse_put_request(fc, req);
fuse_invalidate_attr(inode); /* atime changed */
return link;
}
static int chown_common(struct _dentry * dentry, uid_t user, gid_t group)
{
struct _inode * inode;
int error;
struct iattr newattrs;
error = -ENOENT;
if (!(inode = d_get_inode(dentry))) {
printk(KERN_ERR "chown_common: NULL inode\n");
goto out;
}
error = -EROFS;
if (IS_RDONLY(inode))
goto out;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out;
newattrs.ia_valid = ATTR_CTIME;
if (user != (uid_t) -1) {
newattrs.ia_valid |= ATTR_UID;
newattrs.ia_uid = user;
}
if (group != (gid_t) -1) {
newattrs.ia_valid |= ATTR_GID;
newattrs.ia_gid = group;
}
if (!S_ISDIR(inode->i_mode))
newattrs.ia_valid |= ATTR_KILL_SUID|ATTR_KILL_SGID;
imutex_lock(parent(inode));
error = notify_change(dentry, &newattrs);
imutex_unlock(parent(inode));
out:
return error;
}
static int fuse_removexattr(struct dentry *entry, const char *name)
{
struct _inode *inode = d_get_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
int err;
if (fc->no_removexattr)
return -EOPNOTSUPP;
req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
req->in.h.opcode = FUSE_REMOVEXATTR;
req->in.h.nodeid = _get_node_id(inode);
req->in.numargs = 1;
req->in.args[0].size = strlen(name) + 1;
req->in.args[0].value = name;
request_send(fc, req);
err = req->out.h.error;
fuse_put_request(fc, req);
if (err == -ENOSYS) {
fc->no_removexattr = 1;
err = -EOPNOTSUPP;
}
return err;
}
static long do_sys_truncate(const char __user * path, loff_t length)
{
struct nameidata nd;
struct _inode * inode;
int error;
error = -EINVAL;
if (length < 0) /* sorry, but loff_t says... */
goto out;
error = user_path_walk(path, &nd);
if (error)
goto out;
inode = d_get_inode(nd.dentry);
/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
error = -EISDIR;
if (S_ISDIR(inode->i_mode))
goto dput_and_out;
error = -EINVAL;
if (!S_ISREG(inode->i_mode))
goto dput_and_out;
error = vfs_permission(inode, &nd, MAY_WRITE);
if (error)
goto dput_and_out;
error = -EROFS;
if (IS_RDONLY(inode))
goto dput_and_out;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto dput_and_out;
/*
* Make sure that there are no leases.
*/
error = break_lease(parent(inode), FMODE_WRITE);
if (error)
goto dput_and_out;
error = get_write_access(parent(inode));
if (error)
goto dput_and_out;
error = locks_verify_truncate(parent(inode), NULL, length);
if (!error) {
DQUOT_INIT(inode);
error = do_truncate(nd.dentry, length, 0, NULL);
}
put_write_access(parent(inode));
dput_and_out:
path_release(&nd);
out:
return error;
}
static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
struct kstat *stat)
{
struct _inode *inode = d_get_inode(entry);
int err = fuse_revalidate(entry);
if (!err)
generic_fillattr(inode, stat);
return err;
}
/*
* Check whether the inode attributes are still valid
*
* If the attribute validity timeout has expired, then fetch the fresh
* attributes with a 'getattr' request
*
* I'm not sure why cached attributes are never returned for the root
* inode, this is probably being too cautious.
*/
static int fuse_revalidate(struct dentry *entry)
{
struct _inode *inode = d_get_inode(entry);
struct fuse_inode *fi = get_fuse_inode(parent(inode));
struct fuse_conn *fc = get_fuse_conn(inode);
if (!fuse_allow_task(fc, current))
return -EACCES;
if (_get_node_id(inode) != FUSE_ROOT_ID &&
fi->i_time >= get_jiffies_64())
return 0;
return fuse_do_getattr(inode);
}
static ssize_t fuse_getxattr(struct dentry *entry, const char *name,
void *value, size_t size)
{
struct _inode *inode = d_get_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
struct fuse_getxattr_in inarg;
struct fuse_getxattr_out outarg;
ssize_t ret;
if (fc->no_getxattr)
return -EOPNOTSUPP;
req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
memset(&inarg, 0, sizeof(inarg));
inarg.size = size;
req->in.h.opcode = FUSE_GETXATTR;
req->in.h.nodeid = _get_node_id(inode);
req->in.numargs = 2;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
req->in.args[1].size = strlen(name) + 1;
req->in.args[1].value = name;
/* This is really two different operations rolled into one */
req->out.numargs = 1;
if (size) {
req->out.argvar = 1;
req->out.args[0].size = size;
req->out.args[0].value = value;
} else {
req->out.args[0].size = sizeof(outarg);
req->out.args[0].value = &outarg;
}
request_send(fc, req);
ret = req->out.h.error;
if (!ret)
ret = size ? req->out.args[0].size : outarg.size;
else {
if (ret == -ENOSYS) {
fc->no_getxattr = 1;
ret = -EOPNOTSUPP;
}
}
fuse_put_request(fc, req);
return ret;
}
static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct _inode * inode;
struct _dentry *dentry;
struct file * file;
struct _file * _file;
int error;
error = -EINVAL;
if (length < 0)
goto out;
error = -EBADF;
file = fget(fd);
if (!file)
goto out;
_file = tx_cache_get_file_ro(file);
/* explicitly opened as large or we are on 64-bit box */
if (_file->f_flags & O_LARGEFILE)
small = 0;
dentry = f_get_dentry(_file);
inode = d_get_inode(dentry);
error = -EINVAL;
if (!S_ISREG(inode->i_mode) || !(_file->f_mode & FMODE_WRITE))
goto out_putf;
error = -EINVAL;
/* Cannot ftruncate over 2^31 bytes without large file support */
if (small && length > MAX_NON_LFS)
goto out_putf;
error = -EPERM;
if (IS_APPEND(inode))
goto out_putf;
error = locks_verify_truncate(parent(inode), file, length);
if (!error)
error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file);
out_putf:
fput(file);
out:
return error;
}
static int acct_on(char *name)
{
struct file *file;
struct _file *_file;
int error;
/* Difference from BSD - they don't do O_APPEND */
file = filp_open(name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
if (IS_ERR(file))
return PTR_ERR(file);
_file = tx_cache_get_file(file);
if (!S_ISREG(d_get_inode(f_get_dentry_ro(_file))->i_mode)) {
filp_close(file, NULL);
return -EACCES;
}
if (!file->f_op->write) {
filp_close(file, NULL);
return -EIO;
}
error = security_acct(file);
if (error) {
filp_close(file, NULL);
return error;
}
spin_lock(&acct_globals.lock);
mnt_pin(_file->f_path.mnt);
acct_file_reopen(file);
spin_unlock(&acct_globals.lock);
mntput(_file->f_path.mnt); /* it's pinned, now give up active reference */
return 0;
}
static int fuse_setxattr(struct dentry *entry, const char *name,
const void *value, size_t size, int flags)
{
struct _inode *inode = d_get_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
struct fuse_setxattr_in inarg;
int err;
if (fc->no_setxattr)
return -EOPNOTSUPP;
req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
memset(&inarg, 0, sizeof(inarg));
inarg.size = size;
inarg.flags = flags;
req->in.h.opcode = FUSE_SETXATTR;
req->in.h.nodeid = _get_node_id(inode);
req->in.numargs = 3;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
req->in.args[1].size = strlen(name) + 1;
req->in.args[1].value = name;
req->in.args[2].size = size;
req->in.args[2].value = value;
request_send(fc, req);
err = req->out.h.error;
fuse_put_request(fc, req);
if (err == -ENOSYS) {
fc->no_setxattr = 1;
err = -EOPNOTSUPP;
}
return err;
}
static int fuse_rmdir(struct _inode *dir, struct dentry *entry)
{
int err;
struct fuse_conn *fc = get_fuse_conn(dir);
struct fuse_req *req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
req->in.h.opcode = FUSE_RMDIR;
req->in.h.nodeid = _get_node_id(dir);
req->in.numargs = 1;
req->in.args[0].size = entry->d_name.len + 1;
req->in.args[0].value = entry->d_name.name;
request_send(fc, req);
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err) {
clear_nlink(d_get_inode(entry));
fuse_invalidate_attr(dir);
fuse_invalidate_entry_cache(entry);
} else if (err == -EINTR)
fuse_invalidate_entry(entry);
return err;
}
asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
{
struct _inode * inode;
struct _dentry * dentry;
struct file * file;
int err = -EBADF;
struct iattr newattrs;
file = fget(fd);
if (!file)
goto out;
dentry = file_get_dentry(file);
inode = d_get_inode(dentry);
audit_inode(NULL, inode);
err = -EROFS;
if (IS_RDONLY(inode))
goto out_putf;
err = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out_putf;
imutex_lock(parent(inode));
if (mode == (mode_t) -1)
mode = inode->i_mode;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
err = notify_change(dentry, &newattrs);
imutex_unlock(parent(inode));
out_putf:
fput(file);
out:
return err;
}
static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir)
{
int err;
size_t nbytes;
struct page *page;
struct _inode *inode = d_get_inode(file_get_dentry(file));
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
if (is_bad_inode(inode))
return -EIO;
req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
page = alloc_page(GFP_KERNEL);
if (!page) {
fuse_put_request(fc, req);
return -ENOMEM;
}
req->num_pages = 1;
req->pages[0] = page;
fuse_read_fill(req, file, parent(inode), file->f_pos, PAGE_SIZE, FUSE_READDIR);
request_send(fc, req);
nbytes = req->out.args[0].size;
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err)
err = parse_dirfile(page_address(page), nbytes, file, dstbuf,
filldir);
__free_page(page);
fuse_invalidate_attr(inode); /* atime changed */
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_setattr(struct dentry *entry, struct iattr *attr)
{
struct _inode *inode = d_get_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = _get_fuse_inode(inode);
struct fuse_req *req;
struct fuse_setattr_in inarg;
struct fuse_attr_out outarg;
int err;
int is_truncate = 0;
if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
err = inode_change_ok(inode, attr);
if (err)
return err;
}
if (attr->ia_valid & ATTR_SIZE) {
unsigned long limit;
is_truncate = 1;
if (IS_SWAPFILE(inode))
return -ETXTBSY;
limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
if (limit != RLIM_INFINITY && attr->ia_size > (loff_t) limit) {
send_sig(SIGXFSZ, current, 0);
return -EFBIG;
}
}
req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
memset(&inarg, 0, sizeof(inarg));
iattr_to_fattr(attr, &inarg);
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;
req->out.args[0].size = sizeof(outarg);
req->out.args[0].value = &outarg;
request_send(fc, req);
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err) {
if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
make_bad_inode(inode);
err = -EIO;
} else {
if (is_truncate)
fuse_vmtruncate(inode, outarg.attr.size);
fuse_change_attributes(inode, &outarg.attr);
fi->i_time = time_to_jiffies(outarg.attr_valid,
outarg.attr_valid_nsec);
}
} else if (err == -EINTR)
fuse_invalidate_attr(inode);
return err;
}
static struct file *__dentry_open(struct _dentry *dentry, struct vfsmount *mnt,
int flags, struct file *f,
int (*open)(struct _inode *, struct file *))
{
struct _inode *inode;
int error;
struct super_block *sb;
struct _file *_f = tx_cache_get_file(f);
_f->f_flags = flags;
_f->f_mode = ((flags+1) & O_ACCMODE) | FMODE_LSEEK |
FMODE_PREAD | FMODE_PWRITE;
inode = d_get_inode(dentry);
sb = inode->i_sb;
if (_f->f_mode & FMODE_WRITE) {
error = get_write_access(parent(inode));
if (error)
goto cleanup_file;
}
f->f_mapping = inode->i_mapping;
_f->f_path.dentry = parent(dentry);
_f->f_path.mnt = mnt;
_f->f_pos = 0;
f->f_op = fops_get(inode->i_fop);
file_move(f, &sb->s_files);
if (!open && f->f_op)
open = f->f_op->open;
if (open) {
error = open(inode, f);
if (error)
goto cleanup_all;
}
_f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
file_ra_state_init(&f->f_ra,
tx_cache_get_inode(f->f_mapping->host)->i_mapping);
/* NB: we're sure to have correct a_ops only after f_op->open */
if (_f->f_flags & O_DIRECT) {
if (!f->f_mapping->a_ops ||
((!f->f_mapping->a_ops->direct_IO) &&
(!f->f_mapping->a_ops->get_xip_page))) {
fput(f);
f = ERR_PTR(-EINVAL);
}
}
return f;
cleanup_all:
fops_put(f->f_op);
if (_f->f_mode & FMODE_WRITE)
put_write_access(parent(inode));
file_kill(f);
_f->f_path.dentry = NULL;
_f->f_path.mnt = NULL;
cleanup_file:
/* Avoid issues if we recycle this object */
if(live_transaction())
early_release(&f->xobj, 1);
put_filp(f);
dput(parent(dentry));
mntput(mnt);
return ERR_PTR(error);
}
/*
* sys_sync_file_range() permits finely controlled syncing over a segment of
* a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is
* zero then sys_sync_file_range() will operate from offset out to EOF.
*
* The flag bits are:
*
* SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range
* before performing the write.
*
* SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
* range which are not presently under writeback.
*
* SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range
* after performing the write.
*
* Useful combinations of the flag bits are:
*
* SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages
* in the range which were dirty on entry to sys_sync_file_range() are placed
* under writeout. This is a start-write-for-data-integrity operation.
*
* SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which
* are not presently under writeout. This is an asynchronous flush-to-disk
* operation. Not suitable for data integrity operations.
*
* SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for
* completion of writeout of all pages in the range. This will be used after an
* earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait
* for that operation to complete and to return the result.
*
* SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER:
* a traditional sync() operation. This is a write-for-data-integrity operation
* which will ensure that all pages in the range which were dirty on entry to
* sys_sync_file_range() are committed to disk.
*
*
* SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any
* I/O errors or ENOSPC conditions and will return those to the caller, after
* clearing the EIO and ENOSPC flags in the address_space.
*
* It should be noted that none of these operations write out the file's
* metadata. So unless the application is strictly performing overwrites of
* already-instantiated disk blocks, there are no guarantees here that the data
* will be available after a crash.
*/
asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
unsigned int flags)
{
int ret;
struct file *file;
loff_t endbyte; /* inclusive */
int fput_needed;
umode_t i_mode;
ret = -EINVAL;
if (flags & ~VALID_FLAGS)
goto out;
endbyte = offset + nbytes;
if ((s64)offset < 0)
goto out;
if ((s64)endbyte < 0)
goto out;
if (endbyte < offset)
goto out;
if (sizeof(pgoff_t) == 4) {
if (offset >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
/*
* The range starts outside a 32 bit machine's
* pagecache addressing capabilities. Let it "succeed"
*/
ret = 0;
goto out;
}
if (endbyte >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
/*
* Out to EOF
*/
nbytes = 0;
}
}
if (nbytes == 0)
endbyte = LLONG_MAX;
else
endbyte--; /* inclusive */
ret = -EBADF;
file = fget_light(fd, &fput_needed);
if (!file)
goto out;
i_mode = d_get_inode(file_get_dentry(file))->i_mode;
ret = -ESPIPE;
if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
!S_ISLNK(i_mode))
goto out_put;
ret = do_sync_mapping_range(file->f_mapping, offset, endbyte, flags);
out_put:
fput_light(file, fput_needed);
out:
return ret;
}
