static inline long do_sys_truncate(const char * 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 = nd.dentry->d_inode;
/* 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 = permission(inode,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 = get_lease(inode, FMODE_WRITE);
if (error)
goto dput_and_out;
error = get_write_access(inode);
if (error)
goto dput_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error)
{
DQUOT_INIT(inode);
error = do_truncate(nd.dentry, length);
}
put_write_access(inode);
dput_and_out:
path_release(&nd);
out:
return error;
}
int sys_truncate(char *path, loff_t length)
{
struct inode *inode;
register struct inode *inodep;
int error;
error = namei(path, &inode, NOT_DIR, MAY_WRITE);
inodep = inode;
if (error)
return error;
if (IS_RDONLY(inodep)) {
iput(inodep);
return -EROFS;
}
#ifdef BLOAT_FS
error = get_write_access(inodep);
if (error) {
iput(inodep);
return error;
}
#endif
error = do_truncate(inodep, length);
put_write_access(inodep);
iput(inodep);
return error;
}
struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags)
{
struct file * f;
struct inode *inode;
int error;
error = -ENFILE;
f = get_empty_filp();
if (!f)
goto cleanup_dentry;
f->f_flags = flags;
f->f_mode = ((flags+1) & O_ACCMODE) | FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
inode = dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
error = get_write_access(inode);
if (error)
goto cleanup_file;
}
f->f_mapping = inode->i_mapping;
f->f_dentry = dentry;
f->f_vfsmnt = mnt;
f->f_pos = 0;
f->f_op = fops_get(inode->i_fop);
file_move(f, &inode->i_sb->s_files);
if (f->f_op && f->f_op->open) {
error = f->f_op->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, 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) {
fput(f);
f = ERR_PTR(-EINVAL);
}
}
return f;
cleanup_all:
fops_put(f->f_op);
if (f->f_mode & FMODE_WRITE)
put_write_access(inode);
file_kill(f);
f->f_dentry = NULL;
f->f_vfsmnt = NULL;
cleanup_file:
put_filp(f);
cleanup_dentry:
dput(dentry);
mntput(mnt);
return ERR_PTR(error);
}
static long do_sys_truncate(const char __user *pathname, loff_t length)
{
struct path path;
struct inode *inode;
int error;
error = -EINVAL;
if (length < 0)
goto out;
error = user_path(pathname, &path);
if (error)
goto out;
inode = path.dentry->d_inode;
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 = mnt_want_write(path.mnt);
if (error)
goto dput_and_out;
error = inode_permission(inode, MAY_WRITE);
if (error)
goto mnt_drop_write_and_out;
error = -EPERM;
if (IS_APPEND(inode))
goto mnt_drop_write_and_out;
error = get_write_access(inode);
if (error)
goto mnt_drop_write_and_out;
error = break_lease(inode, O_WRONLY);
if (error)
goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error)
error = security_path_truncate(&path);
if (!error)
error = do_truncate(path.dentry, length, 0, NULL);
put_write_and_out:
put_write_access(inode);
mnt_drop_write_and_out:
mnt_drop_write(path.mnt);
dput_and_out:
path_put(&path);
out:
return error;
}
/*
* Open an existing file or directory.
* The wflag argument indicates write access.
* N.B. After this call fhp needs an fh_put
*/
int
nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
int wflag, struct file *filp)
{
struct dentry *dentry;
struct inode *inode;
int access, err;
access = wflag? MAY_WRITE : MAY_READ;
err = fh_verify(rqstp, fhp, type, access);
if (err)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
/* Disallow access to files with the append-only bit set or
* with mandatory locking enabled
*/
err = nfserr_perm;
if (IS_APPEND(inode) || IS_ISMNDLK(inode))
goto out;
if (!inode->i_op || !inode->i_op->default_file_ops)
goto out;
if (wflag && (err = get_write_access(inode)) != 0)
goto out_nfserr;
memset(filp, 0, sizeof(*filp));
filp->f_op = inode->i_op->default_file_ops;
filp->f_count = 1;
filp->f_flags = wflag? O_WRONLY : O_RDONLY;
filp->f_mode = wflag? FMODE_WRITE : FMODE_READ;
filp->f_dentry = dentry;
if (wflag)
DQUOT_INIT(inode);
err = 0;
if (filp->f_op && filp->f_op->open) {
err = filp->f_op->open(inode, filp);
if (err) {
if (wflag)
put_write_access(inode);
/* I nearly added put_filp() call here, but this filp
* is really on callers stack frame. -DaveM
*/
filp->f_count--;
}
}
out_nfserr:
if (err)
err = nfserrno(-err);
out:
return err;
}
int ovl_setattr(struct dentry *dentry, struct iattr *attr)
{
int err;
struct dentry *upperdentry;
/*
* Check for permissions before trying to copy-up. This is redundant
* since it will be rechecked later by ->setattr() on upper dentry. But
* without this, copy-up can be triggered by just about anybody.
*
* We don't initialize inode->size, which just means that
* inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not
* check for a swapfile (which this won't be anyway).
*/
err = inode_change_ok(dentry->d_inode, attr);
if (err)
return err;
err = ovl_want_write(dentry);
if (err)
goto out;
if (attr->ia_valid & ATTR_SIZE) {
struct inode *realinode = d_inode(ovl_dentry_real(dentry));
err = -ETXTBSY;
if (atomic_read(&realinode->i_writecount) < 0)
goto out_drop_write;
}
err = ovl_copy_up(dentry);
if (!err) {
struct inode *winode = NULL;
upperdentry = ovl_dentry_upper(dentry);
if (attr->ia_valid & ATTR_SIZE) {
winode = d_inode(upperdentry);
err = get_write_access(winode);
if (err)
goto out_drop_write;
}
inode_lock(upperdentry->d_inode);
err = notify_change(upperdentry, attr, NULL);
if (!err)
ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
inode_unlock(upperdentry->d_inode);
if (winode)
put_write_access(winode);
}
out_drop_write:
ovl_drop_write(dentry);
out:
return err;
}
/*
* You have to be very careful that these write
* counts get cleaned up in error cases and
* upon __fput(). This should probably never
* be called outside of __dentry_open().
*/
static inline int __get_file_write_access(struct inode *inode,
struct vfsmount *mnt)
{
int error = get_write_access(inode);
if (error)
return error;
error = __mnt_want_write(mnt);
if (error)
put_write_access(inode);
return error;
}
/**
* bus1_pool_create_internal() - create memory pool
* @pool: (uninitialized) pool to operate on
* @size: size of the pool
*
* Initialize a new pool object. This allocates a backing shmem object with the
* given name and size.
*
* NOTE: All pools must be embedded into a parent bus1_peer_info object. The
* code works fine, if you don't, but the lockdep-annotations will fail
* horribly. They rely on bus1_peer_info_from_pool() to be valid on every
* pool. Use the bus1_pool_create_for_peer() macro to make sure you
* never violate this rule.
*
* Return: 0 on success, negative error code on failure.
*/
int bus1_pool_create_internal(struct bus1_pool *pool, size_t size)
{
struct bus1_pool_slice *slice;
struct file *f;
int r;
/* cannot calculate width of bitfields, so hardcode '4' as flag-size */
BUILD_BUG_ON(BUS1_POOL_SLICE_SIZE_BITS + 4 > 32);
BUILD_BUG_ON(BUS1_POOL_SIZE_MAX >=
(1ULL <<
(sizeof(((struct bus1_pool_slice *)0)->offset) * 8)));
size = ALIGN(size, 8);
if (size == 0 || size > BUS1_POOL_SIZE_MAX)
return -EMSGSIZE;
f = shmem_file_setup(KBUILD_MODNAME "-peer", size, 0);
if (IS_ERR(f))
return PTR_ERR(f);
r = get_write_access(file_inode(f));
if (r < 0)
goto error_put_file;
slice = bus1_pool_slice_new(0, size);
if (IS_ERR(slice)) {
r = PTR_ERR(slice);
goto error_put_write;
}
slice->free = true;
slice->accounted = false;
slice->ref_kernel = false;
slice->ref_user = false;
pool->f = f;
pool->size = size;
pool->accounted_size = 0;
INIT_LIST_HEAD(&pool->slices);
pool->slices_free = RB_ROOT;
pool->slices_busy = RB_ROOT;
list_add(&slice->entry, &pool->slices);
bus1_pool_slice_link_free(slice, pool);
return 0;
error_put_write:
put_write_access(file_inode(f));
error_put_file:
fput(f);
return r;
}
long vfs_truncate(struct path *path, loff_t length)
{
struct inode *inode;
long error;
inode = path->dentry->d_inode;
/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
if (S_ISDIR(inode->i_mode))
return -EISDIR;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
error = mnt_want_write(path->mnt);
if (error)
goto out;
error = inode_permission(inode, MAY_WRITE);
if (error)
goto mnt_drop_write_and_out;
error = -EPERM;
if (IS_APPEND(inode))
goto mnt_drop_write_and_out;
error = get_write_access(inode);
if (error)
goto mnt_drop_write_and_out;
/*
* Make sure that there are no leases. get_write_access() protects
* against the truncate racing with a lease-granting setlease().
*/
error = break_lease(inode, O_WRONLY);
if (error)
goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error)
error = security_path_truncate(path, length, 0);
if (!error) {
vfs_dq_init(inode);
error = do_truncate(path->dentry, length, 0, NULL);
}
put_write_and_out:
put_write_access(inode);
mnt_drop_write_and_out:
mnt_drop_write(path->mnt);
out:
return error;
}
static inline int __get_file_write_access(struct inode *inode,
struct vfsmount *mnt)
{
int error;
error = get_write_access(inode);
if (error)
return error;
if (!special_file(inode->i_mode)) {
error = mnt_want_write(mnt);
if (error)
put_write_access(inode);
}
return error;
}
static int unionfs_permission(struct inode *inode, int mask,
struct nameidata *nd)
{
struct inode *hidden_inode = NULL;
int err = 0;
int bindex, bstart, bend;
const int is_file = !S_ISDIR(inode->i_mode);
const int write_mask = (mask & MAY_WRITE) && !(mask & MAY_READ);
print_entry_location();
bstart = ibstart(inode);
bend = ibend(inode);
fist_print_inode("IN unionfs_permission", inode);
for (bindex = bstart; bindex <= bend; bindex++) {
hidden_inode = itohi_index(inode, bindex);
if (!hidden_inode)
continue;
/* check the condition for D-F-D underlying files/directories,
* we dont have to check for files, if we are checking for
* directories.
*/
if (!is_file && !S_ISDIR(hidden_inode->i_mode))
continue;
/* We use our own special version of permission, such that
* only the first branch returns -EROFS. */
err = inode_permission(hidden_inode, mask, nd, bindex);
/* The permissions are an intersection of the overall directory
* permissions, so we fail if one fails. */
if (err)
goto out;
/* only the leftmost file matters. */
if (is_file || write_mask) {
if (is_file && write_mask) {
err = get_write_access(hidden_inode);
if (!err)
put_write_access(hidden_inode);
}
break;
}
}
out:
print_exit_status(err);
return err;
}
/*
* Note that while the flag value (low two bits) for sys_open means:
* 00 - read-only
* 01 - write-only
* 10 - read-write
* 11 - special
* it is changed into
* 00 - no permissions needed
* 01 - read-permission
* 10 - write-permission
* 11 - read-write
* for the internal routines (ie open_namei()/follow_link() etc). 00 is
* used by symlinks.
*/
static int do_open(const char * filename,int flags,int mode, int fd)
{
struct inode * inode;
struct file * f;
int flag,error;
f = get_empty_filp();
if (!f)
return -ENFILE;
f->f_flags = flag = flags;
f->f_mode = (flag+1) & O_ACCMODE;
if (f->f_mode)
flag++;
if (flag & O_TRUNC)
flag |= 2;
error = open_namei(filename,flag,mode,&inode,NULL);
if (error)
goto cleanup_file;
if (f->f_mode & FMODE_WRITE) {
error = get_write_access(inode);
if (error)
goto cleanup_inode;
}
f->f_inode = inode;
f->f_pos = 0;
f->f_reada = 0;
f->f_op = NULL;
if (inode->i_op)
f->f_op = inode->i_op->default_file_ops;
if (f->f_op && f->f_op->open) {
error = f->f_op->open(inode,f);
if (error)
goto cleanup_all;
}
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
current->files->fd[fd] = f;
return 0;
cleanup_all:
if (f->f_mode & FMODE_WRITE)
put_write_access(inode);
cleanup_inode:
iput(inode);
cleanup_file:
f->f_count--;
return error;
}
struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags)
{
struct file * f;
struct inode *inode;
int error;
error = -ENFILE;
f = get_empty_filp();
if (!f)
goto cleanup_dentry;
f->f_flags = flags;
f->f_mode = (flags+1) & O_ACCMODE;
inode = dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
error = get_write_access(inode);
if (error)
goto cleanup_file;
}
f->f_dentry = dentry;
f->f_vfsmnt = mnt;
f->f_pos = 0;
f->f_reada = 0;
f->f_op = fops_get(inode->i_fop);
if (inode->i_sb)
file_move(f, &inode->i_sb->s_files);
if (f->f_op && f->f_op->open) {
error = f->f_op->open(inode,f);
if (error)
goto cleanup_all;
}
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
return f;
cleanup_all:
fops_put(f->f_op);
if (f->f_mode & FMODE_WRITE)
put_write_access(inode);
f->f_dentry = NULL;
f->f_vfsmnt = NULL;
cleanup_file:
put_filp(f);
cleanup_dentry:
dput(dentry);
mntput(mnt);
return ERR_PTR(error);
}
long vfs_truncate(struct path *path, loff_t length)
{
struct inode *inode;
long error;
inode = path->dentry->d_inode;
if (S_ISDIR(inode->i_mode))
return -EISDIR;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
error = mnt_want_write(path->mnt);
if (error)
goto out;
error = inode_permission(inode, MAY_WRITE);
if (error)
goto mnt_drop_write_and_out;
error = -EPERM;
if (IS_APPEND(inode))
goto mnt_drop_write_and_out;
error = get_write_access(inode);
if (error)
goto mnt_drop_write_and_out;
error = break_lease(inode, O_WRONLY);
if (error)
goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error)
error = security_path_truncate(path);
if (!error)
error = do_truncate(path->dentry, length, 0, NULL);
put_write_and_out:
put_write_access(inode);
mnt_drop_write_and_out:
mnt_drop_write(path->mnt);
out:
return error;
}
/*
* Truncate a file.
* The calling routines must make sure to update the ctime
* field and call notify_change.
*
* XXX Nobody calls this thing? -DaveM
* N.B. After this call fhp needs an fh_put
*/
int
nfsd_truncate(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned long size)
{
struct dentry *dentry;
struct inode *inode;
struct iattr newattrs;
int err;
kernel_cap_t saved_cap;
err = fh_verify(rqstp, fhp, S_IFREG, MAY_WRITE | MAY_TRUNC);
if (err)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
err = get_write_access(inode);
if (err)
goto out_nfserr;
/* Things look sane, lock and do it. */
fh_lock(fhp);
DQUOT_INIT(inode);
newattrs.ia_size = size;
newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
if (current->fsuid != 0) {
saved_cap = current->cap_effective;
cap_clear(current->cap_effective);
}
err = notify_change(dentry, &newattrs);
if (current->fsuid != 0)
current->cap_effective = saved_cap;
if (!err) {
vmtruncate(inode, size);
if (inode->i_op && inode->i_op->truncate)
inode->i_op->truncate(inode);
}
put_write_access(inode);
DQUOT_DROP(inode);
fh_unlock(fhp);
out_nfserr:
if (err)
err = nfserrno(-err);
out:
return err;
}
asmlinkage int sys_truncate(const char * path, unsigned long length)
{
struct inode * inode;
int error;
error = namei(path,&inode);
if (error)
return error;
error = -EACCES;
if (S_ISDIR(inode->i_mode))
goto out;
error = permission(inode,MAY_WRITE);
if (error)
goto out;
error = -EROFS;
if (IS_RDONLY(inode))
goto out;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out;
error = get_write_access(inode);
if (error)
goto out;
error = locks_verify_area(FLOCK_VERIFY_WRITE, inode, NULL,
length < inode->i_size ? length : inode->i_size,
abs(inode->i_size - length));
if (!error) {
if (inode->i_sb && inode->i_sb->dq_op)
inode->i_sb->dq_op->initialize(inode, -1);
error = do_truncate(inode, length);
}
put_write_access(inode);
out:
iput(inode);
return error;
}
/* cf. open.c:do_sys_truncate() and do_sys_ftruncate() */
int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr,
struct file *h_file)
{
int err;
struct inode *h_inode;
h_inode = h_path->dentry->d_inode;
if (!h_file) {
err = mnt_want_write(h_path->mnt);
if (err)
goto out;
err = inode_permission(h_inode, MAY_WRITE);
if (err)
goto out_mnt;
err = get_write_access(h_inode);
if (err)
goto out_mnt;
err = break_lease(h_inode, O_WRONLY);
if (err)
goto out_inode;
}
err = locks_verify_truncate(h_inode, h_file, length);
if (!err)
err = security_path_truncate(h_path);
if (!err) {
lockdep_off();
err = do_truncate(h_path->dentry, length, attr, h_file);
lockdep_on();
}
out_inode:
if (!h_file)
put_write_access(h_inode);
out_mnt:
if (!h_file)
mnt_drop_write(h_path->mnt);
out:
return err;
}
/*
* You have to be very careful that these write
* counts get cleaned up in error cases and
* upon __fput(). This should probably never
* be called outside of __dentry_open().
*/
static inline int __get_file_write_access(struct inode *inode,
struct vfsmount *mnt)
{
int error;
error = get_write_access(inode);
if (error)
return error;
/*
* Do not take mount writer counts on
* special files since no writes to
* the mount itself will occur.
*/
if (!special_file(inode->i_mode)) {
/*
* Balanced in __fput()
*/
error = mnt_want_write(mnt);
if (error)
put_write_access(inode);
}
return error;
}
static int do_dentry_open(struct file *f,
int (*open)(struct inode *, struct file *),
const struct cred *cred)
{
static const struct file_operations empty_fops = {};
struct inode *inode;
int error;
f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
FMODE_PREAD | FMODE_PWRITE;
path_get(&f->f_path);
inode = f->f_inode = f->f_path.dentry->d_inode;
f->f_mapping = inode->i_mapping;
if (unlikely(f->f_flags & O_PATH)) {
f->f_mode = FMODE_PATH;
f->f_op = &empty_fops;
return 0;
}
if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
error = get_write_access(inode);
if (unlikely(error))
goto cleanup_file;
error = __mnt_want_write(f->f_path.mnt);
if (unlikely(error)) {
put_write_access(inode);
goto cleanup_file;
}
f->f_mode |= FMODE_WRITER;
}
/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
if (S_ISREG(inode->i_mode))
f->f_mode |= FMODE_ATOMIC_POS;
f->f_op = fops_get(inode->i_fop);
if (unlikely(WARN_ON(!f->f_op))) {
error = -ENODEV;
goto cleanup_all;
}
error = security_file_open(f, cred);
if (error)
goto cleanup_all;
error = break_lease(inode, f->f_flags);
if (error)
goto cleanup_all;
if (!open)
open = f->f_op->open;
if (open) {
error = open(inode, f);
if (error)
goto cleanup_all;
}
if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
i_readcount_inc(inode);
if ((f->f_mode & FMODE_READ) &&
likely(f->f_op->read || f->f_op->aio_read || f->f_op->read_iter))
f->f_mode |= FMODE_CAN_READ;
if ((f->f_mode & FMODE_WRITE) &&
likely(f->f_op->write || f->f_op->aio_write || f->f_op->write_iter))
f->f_mode |= FMODE_CAN_WRITE;
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
return 0;
cleanup_all:
fops_put(f->f_op);
if (f->f_mode & FMODE_WRITER) {
put_write_access(inode);
__mnt_drop_write(f->f_path.mnt);
}
cleanup_file:
path_put(&f->f_path);
f->f_path.mnt = NULL;
f->f_path.dentry = NULL;
f->f_inode = NULL;
return error;
}
/*
* Set various file attributes.
* N.B. After this call fhp needs an fh_put
*/
__be32
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
int check_guard, time_t guardtime)
{
struct dentry *dentry;
struct inode *inode;
int accmode = NFSD_MAY_SATTR;
int ftype = 0;
__be32 err;
int host_err;
int size_change = 0;
if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
if (iap->ia_valid & ATTR_SIZE)
ftype = S_IFREG;
/* Get inode */
err = fh_verify(rqstp, fhp, ftype, accmode);
if (err)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
/* Ignore any mode updates on symlinks */
if (S_ISLNK(inode->i_mode))
iap->ia_valid &= ~ATTR_MODE;
if (!iap->ia_valid)
goto out;
/*
* NFSv2 does not differentiate between "set-[ac]time-to-now"
* which only requires access, and "set-[ac]time-to-X" which
* requires ownership.
* So if it looks like it might be "set both to the same time which
* is close to now", and if inode_change_ok fails, then we
* convert to "set to now" instead of "set to explicit time"
*
* We only call inode_change_ok as the last test as technically
* it is not an interface that we should be using. It is only
* valid if the filesystem does not define it's own i_op->setattr.
*/
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define MAX_TOUCH_TIME_ERROR (30*60)
if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET &&
iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) {
/*
* Looks probable.
*
* Now just make sure time is in the right ballpark.
* Solaris, at least, doesn't seem to care what the time
* request is. We require it be within 30 minutes of now.
*/
time_t delta = iap->ia_atime.tv_sec - get_seconds();
if (delta < 0)
delta = -delta;
if (delta < MAX_TOUCH_TIME_ERROR &&
inode_change_ok(inode, iap) != 0) {
/*
* Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME.
* This will cause notify_change to set these times
* to "now"
*/
iap->ia_valid &= ~BOTH_TIME_SET;
}
}
/*
* The size case is special.
* It changes the file as well as the attributes.
*/
if (iap->ia_valid & ATTR_SIZE) {
if (iap->ia_size < inode->i_size) {
err = nfsd_permission(rqstp, fhp->fh_export, dentry,
NFSD_MAY_TRUNC|NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
}
/*
* If we are changing the size of the file, then
* we need to break all leases.
*/
host_err = break_lease(inode, FMODE_WRITE | O_NONBLOCK);
if (host_err == -EWOULDBLOCK)
host_err = -ETIMEDOUT;
if (host_err) /* ENOMEM or EWOULDBLOCK */
goto out_nfserr;
host_err = get_write_access(inode);
if (host_err)
goto out_nfserr;
size_change = 1;
host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
if (host_err) {
put_write_access(inode);
goto out_nfserr;
}
DQUOT_INIT(inode);
}
/* sanitize the mode change */
if (iap->ia_valid & ATTR_MODE) {
iap->ia_mode &= S_IALLUGO;
iap->ia_mode |= (inode->i_mode & ~S_IALLUGO);
}
/* Revoke setuid/setgid on chown */
if (((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) ||
((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)) {
iap->ia_valid |= ATTR_KILL_PRIV;
if (iap->ia_valid & ATTR_MODE) {
/* we're setting mode too, just clear the s*id bits */
iap->ia_mode &= ~S_ISUID;
if (iap->ia_mode & S_IXGRP)
iap->ia_mode &= ~S_ISGID;
} else {
/* set ATTR_KILL_* bits and let VFS handle it */
iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID);
}
}
/* Change the attributes. */
iap->ia_valid |= ATTR_CTIME;
err = nfserr_notsync;
if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
fh_lock(fhp);
host_err = notify_change(dentry, iap);
err = nfserrno(host_err);
fh_unlock(fhp);
}
if (size_change)
put_write_access(inode);
if (!err)
if (EX_ISSYNC(fhp->fh_export))
write_inode_now(inode, 1);
out:
return err;
out_nfserr:
err = nfserrno(host_err);
goto out;
}
/*
* Don't grab the superblock read-lock in unionfs_permission, which prevents
* a deadlock with the branch-management "add branch" code (which grabbed
* the write lock). It is safe to not grab the read lock here, because even
* with branch management taking place, there is no chance that
* unionfs_permission, or anything it calls, will use stale branch
* information.
*/
static int unionfs_permission(struct inode *inode, int mask)
{
struct inode *lower_inode = NULL;
int err = 0;
int bindex, bstart, bend;
int is_file;
const int write_mask = (mask & MAY_WRITE) && !(mask & MAY_READ);
struct inode *inode_grabbed;
inode_grabbed = igrab(inode);
is_file = !S_ISDIR(inode->i_mode);
if (!UNIONFS_I(inode)->lower_inodes) {
if (is_file) /* dirs can be unlinked but chdir'ed to */
err = -ESTALE; /* force revalidate */
goto out;
}
bstart = ibstart(inode);
bend = ibend(inode);
if (unlikely(bstart < 0 || bend < 0)) {
/*
* With branch-management, we can get a stale inode here.
* If so, we return ESTALE back to link_path_walk, which
* would discard the dcache entry and re-lookup the
* dentry+inode. This should be equivalent to issuing
* __unionfs_d_revalidate_chain on nd.dentry here.
*/
if (is_file) /* dirs can be unlinked but chdir'ed to */
err = -ESTALE; /* force revalidate */
goto out;
}
for (bindex = bstart; bindex <= bend; bindex++) {
lower_inode = unionfs_lower_inode_idx(inode, bindex);
if (!lower_inode)
continue;
/*
* check the condition for D-F-D underlying files/directories,
* we don't have to check for files, if we are checking for
* directories.
*/
if (!is_file && !S_ISDIR(lower_inode->i_mode))
continue;
/*
* We check basic permissions, but we ignore any conditions
* such as readonly file systems or branches marked as
* readonly, because those conditions should lead to a
* copyup taking place later on. However, if user never had
* access to the file, then no copyup could ever take place.
*/
err = __inode_permission(lower_inode, mask);
if (err && err != -EACCES && err != EPERM && bindex > 0) {
umode_t mode = lower_inode->i_mode;
if ((is_robranch_super(inode->i_sb, bindex) ||
__is_rdonly(lower_inode)) &&
(S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
err = 0;
if (IS_COPYUP_ERR(err))
err = 0;
}
/*
* NFS HACK: NFSv2/3 return EACCES on readonly-exported,
* locally readonly-mounted file systems, instead of EROFS
* like other file systems do. So we have no choice here
* but to intercept this and ignore it for NFS branches
* marked readonly. Specifically, we avoid using NFS's own
* "broken" ->permission method, and rely on
* generic_permission() to do basic checking for us.
*/
if (err && err == -EACCES &&
is_robranch_super(inode->i_sb, bindex) &&
lower_inode->i_sb->s_magic == NFS_SUPER_MAGIC)
err = generic_permission(lower_inode, mask);
/*
* The permissions are an intersection of the overall directory
* permissions, so we fail if one fails.
*/
if (err)
goto out;
/* only the leftmost file matters. */
if (is_file || write_mask) {
if (is_file && write_mask) {
err = get_write_access(lower_inode);
if (!err)
put_write_access(lower_inode);
}
break;
}
}
/* sync times which may have changed (asynchronously) below */
unionfs_copy_attr_times(inode);
out:
unionfs_check_inode(inode);
iput(inode_grabbed);
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);
}
static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
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;
int alloc_required = 0;
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_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);
gfs2_size_hint(inode, pos, PAGE_CACHE_SIZE);
ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required);
if (ret)
goto out_unlock;
if (!alloc_required) {
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;
ret = gfs2_quota_lock_check(ip);
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_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,
.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;
vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
/**
* gfs2_open - open a file
* @inode: the inode to open
* @file: the struct file for this opening
*
* Returns: errno
*/
static int gfs2_open(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder i_gh;
struct gfs2_file *fp;
int error;
fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
if (!fp)
return -ENOMEM;
mutex_init(&fp->f_fl_mutex);
gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
file->private_data = fp;
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)
goto fail;
if (!(file->f_flags & O_LARGEFILE) &&
i_size_read(inode) > MAX_NON_LFS) {
error = -EOVERFLOW;
goto fail_gunlock;
}
gfs2_glock_dq_uninit(&i_gh);
}
return 0;
fail_gunlock:
gfs2_glock_dq_uninit(&i_gh);
fail:
file->private_data = NULL;
kfree(fp);
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);
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
*
* The VFS will flush data for us. We only need to worry
* about metadata here.
*
* Returns: errno
*/
static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
int sync_state = inode->i_state & I_DIRTY;
struct gfs2_inode *ip = GFS2_I(inode);
int ret;
if (!gfs2_is_jdata(ip))
sync_state &= ~I_DIRTY_PAGES;
if (datasync)
sync_state &= ~I_DIRTY_SYNC;
if (sync_state) {
ret = sync_inode_metadata(inode, 1);
if (ret)
return ret;
if (gfs2_is_jdata(ip))
filemap_write_and_wait(inode->i_mapping);
gfs2_ail_flush(ip->i_gl, 1);
}
return 0;
}
/**
* gfs2_file_aio_write - 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_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
size_t writesize = iov_length(iov, nr_segs);
struct dentry *dentry = file->f_dentry;
struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
struct gfs2_sbd *sdp;
int ret;
sdp = GFS2_SB(file->f_mapping->host);
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
gfs2_size_hint(file->f_dentry->d_inode, pos, writesize);
if (file->f_flags & O_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_aio_write(iocb, iov, nr_segs, pos);
}
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 inode *inode = out->f_mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
error = gfs2_rs_alloc(ip);
if (error)
return (ssize_t)error;
gfs2_size_hint(inode, *ppos, len);
return generic_file_splice_write(pipe, out, ppos, len, flags);
}
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);
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;
ret = gfs2_quota_lock_check(ip);
if (ret)
goto out_unlock;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
ret = gfs2_inplace_reserve(ip, data_blocks + ind_blocks, 0);
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 long do_sys_truncate(const char __user *pathname, loff_t length)
{
struct path path;
struct inode *inode;
int error;
error = -EINVAL;
if (length < 0) /* sorry, but loff_t says... */
goto out;
error = user_path(pathname, &path);
if (error)
goto out;
inode = path.dentry->d_inode;
/* 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 = mnt_want_write(path.mnt);
if (error)
goto dput_and_out;
error = inode_permission(inode, MAY_WRITE);
if (error)
goto mnt_drop_write_and_out;
error = -EPERM;
if (IS_APPEND(inode))
goto mnt_drop_write_and_out;
error = get_write_access(inode);
if (error)
goto mnt_drop_write_and_out;
/*
* Make sure that there are no leases. get_write_access() protects
* against the truncate racing with a lease-granting setlease().
*/
error = break_lease(inode, O_WRONLY);
if (error)
goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error)
error = security_path_truncate(&path);
if (!error)
error = do_truncate(path.dentry, length, 0, NULL);
put_write_and_out:
put_write_access(inode);
mnt_drop_write_and_out:
mnt_drop_write(path.mnt);
dput_and_out:
path_put(&path);
out:
return error;
}
/*
* Set various file attributes.
* N.B. After this call fhp needs an fh_put
*/
int
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
int check_guard, time_t guardtime)
{
struct dentry *dentry;
struct inode *inode;
int accmode = MAY_SATTR;
int ftype = 0;
int imode;
int err;
int size_change = 0;
if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
accmode |= MAY_WRITE|MAY_OWNER_OVERRIDE;
if (iap->ia_valid & ATTR_SIZE)
ftype = S_IFREG;
/* Get inode */
err = fh_verify(rqstp, fhp, ftype, accmode);
if (err || !iap->ia_valid)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
/* NFSv2 does not differentiate between "set-[ac]time-to-now"
* which only requires access, and "set-[ac]time-to-X" which
* requires ownership.
* So if it looks like it might be "set both to the same time which
* is close to now", and if inode_change_ok fails, then we
* convert to "set to now" instead of "set to explicit time"
*
* We only call inode_change_ok as the last test as technically
* it is not an interface that we should be using. It is only
* valid if the filesystem does not define it's own i_op->setattr.
*/
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define MAX_TOUCH_TIME_ERROR (30*60)
if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET
&& iap->ia_mtime == iap->ia_atime
) {
/* Looks probable. Now just make sure time is in the right ballpark.
* Solaris, at least, doesn't seem to care what the time request is.
* We require it be within 30 minutes of now.
*/
time_t delta = iap->ia_atime - CURRENT_TIME;
if (delta<0) delta = -delta;
if (delta < MAX_TOUCH_TIME_ERROR &&
inode_change_ok(inode, iap) != 0) {
/* turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME
* this will cause notify_change to set these times to "now"
*/
iap->ia_valid &= ~BOTH_TIME_SET;
}
}
/* The size case is special. It changes the file as well as the attributes. */
if (iap->ia_valid & ATTR_SIZE) {
if (iap->ia_size < inode->i_size) {
err = nfsd_permission(fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE);
if (err)
goto out;
}
/*
* If we are changing the size of the file, then
* we need to break all leases.
*/
err = get_lease(inode, FMODE_WRITE);
if (err)
goto out_nfserr;
err = get_write_access(inode);
if (err)
goto out_nfserr;
err = locks_verify_truncate(inode, NULL, iap->ia_size);
if (err) {
put_write_access(inode);
goto out_nfserr;
}
DQUOT_INIT(inode);
}
imode = inode->i_mode;
if (iap->ia_valid & ATTR_MODE) {
iap->ia_mode &= S_IALLUGO;
imode = iap->ia_mode |= (imode & ~S_IALLUGO);
}
/* Revoke setuid/setgid bit on chown/chgrp */
if ((iap->ia_valid & ATTR_UID) && (imode & S_ISUID)
&& iap->ia_uid != inode->i_uid) {
iap->ia_valid |= ATTR_MODE;
iap->ia_mode = imode &= ~S_ISUID;
}
if ((iap->ia_valid & ATTR_GID) && (imode & S_ISGID)
&& iap->ia_gid != inode->i_gid) {
iap->ia_valid |= ATTR_MODE;
iap->ia_mode = imode &= ~S_ISGID;
}
/* Change the attributes. */
iap->ia_valid |= ATTR_CTIME;
if (iap->ia_valid & ATTR_SIZE) {
fh_lock(fhp);
size_change = 1;
}
err = nfserr_notsync;
if (!check_guard || guardtime == inode->i_ctime) {
err = notify_change(dentry, iap);
err = nfserrno(err);
}
if (size_change) {
fh_unlock(fhp);
put_write_access(inode);
}
if (!err)
if (EX_ISSYNC(fhp->fh_export))
write_inode_now(inode, 1);
out:
return err;
out_nfserr:
err = nfserrno(err);
goto out;
}
static int hpfs_unlink(struct inode *dir, struct dentry *dentry)
{
const char *name = dentry->d_name.name;
unsigned len = dentry->d_name.len;
struct quad_buffer_head qbh;
struct hpfs_dirent *de;
struct inode *inode = dentry->d_inode;
dnode_secno dno;
fnode_secno fno;
int r;
int rep = 0;
int err;
lock_kernel();
hpfs_adjust_length((char *)name, &len);
again:
mutex_lock(&hpfs_i(inode)->i_parent_mutex);
mutex_lock(&hpfs_i(dir)->i_mutex);
err = -ENOENT;
de = map_dirent(dir, hpfs_i(dir)->i_dno, (char *)name, len, &dno, &qbh);
if (!de)
goto out;
err = -EPERM;
if (de->first)
goto out1;
err = -EISDIR;
if (de->directory)
goto out1;
fno = de->fnode;
r = hpfs_remove_dirent(dir, dno, de, &qbh, 1);
switch (r) {
case 1:
hpfs_error(dir->i_sb, "there was error when removing dirent");
err = -EFSERROR;
break;
case 2: /* no space for deleting, try to truncate file */
err = -ENOSPC;
if (rep++)
break;
mutex_unlock(&hpfs_i(dir)->i_mutex);
mutex_unlock(&hpfs_i(inode)->i_parent_mutex);
d_drop(dentry);
spin_lock(&dentry->d_lock);
if (atomic_read(&dentry->d_count) > 1 ||
permission(inode, MAY_WRITE, NULL) ||
!S_ISREG(inode->i_mode) ||
get_write_access(inode)) {
spin_unlock(&dentry->d_lock);
d_rehash(dentry);
} else {
struct iattr newattrs;
spin_unlock(&dentry->d_lock);
/*printk("HPFS: truncating file before delete.\n");*/
newattrs.ia_size = 0;
newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
err = notify_change(dentry, &newattrs);
put_write_access(inode);
if (!err)
goto again;
}
unlock_kernel();
return -ENOSPC;
default:
inode->i_nlink--;
err = 0;
}
goto out;
out1:
hpfs_brelse4(&qbh);
out:
mutex_unlock(&hpfs_i(dir)->i_mutex);
mutex_unlock(&hpfs_i(inode)->i_parent_mutex);
unlock_kernel();
return err;
}
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;
ret = gfs2_quota_lock_check(ip);
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_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,
.remap_pages = generic_file_remap_pages,
};
/**
* 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;
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;
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_aio_write - 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_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
size_t writesize = iov_length(iov, nr_segs);
struct gfs2_inode *ip = GFS2_I(file_inode(file));
int ret;
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
gfs2_size_hint(file, pos, writesize);
if (file->f_flags & O_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_aio_write(iocb, iov, nr_segs, pos);
}
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;
loff_t size = len;
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;
}
}
if (offset + size > inode->i_size && !(mode & FALLOC_FL_KEEP_SIZE))
i_size_write(inode, offset + size);
mark_inode_dirty(inode);
out:
brelse(dibh);
return error;
}
static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len,
unsigned int *data_blocks, unsigned int *ind_blocks)
{
const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
unsigned int max_blocks = ip->i_rgd->rd_free_clone;
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;
}
/* This calculation isn't the exact reverse of gfs2_write_calc_reserve,
so it might end up with fewer data blocks */
if (max_data <= *data_blocks)
return;
*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;
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;
struct gfs2_holder gh;
next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
/* We only support the FALLOC_FL_KEEP_SIZE mode */
if (mode & ~FALLOC_FL_KEEP_SIZE)
return -EOPNOTSUPP;
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;
error = gfs2_rs_alloc(ip);
if (error)
return error;
mutex_lock(&inode->i_mutex);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
error = gfs2_glock_nq(&gh);
if (unlikely(error))
goto out_uninit;
gfs2_size_hint(file, offset, len);
while (len > 0) {
if (len < bytes)
bytes = len;
if (!gfs2_write_alloc_required(ip, offset, bytes)) {
len -= bytes;
offset += bytes;
continue;
}
error = gfs2_quota_lock_check(ip);
if (error)
goto out_unlock;
retry:
gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
error = gfs2_inplace_reserve(ip, &ap);
if (error) {
if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) {
bytes >>= 1;
bytes &= bsize_mask;
if (bytes == 0)
bytes = sdp->sd_sb.sb_bsize;
goto retry;
}
goto out_qunlock;
}
max_bytes = bytes;
calc_max_reserv(ip, (len > max_chunk_size)? max_chunk_size: len,
&max_bytes, &data_blocks, &ind_blocks);
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 (error == 0)
error = generic_write_sync(file, pos, count);
goto out_unlock;
out_trans_fail:
gfs2_inplace_release(ip);
out_qunlock:
gfs2_quota_unlock(ip);
out_unlock:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
mutex_unlock(&inode->i_mutex);
return error;
}
#ifdef CONFIG_GFS2_FS_LOCKING_DLM
/**
* gfs2_setlease - acquire/release a file lease
* @file: the file pointer
* @arg: lease type
* @fl: file lock
*
* We don't currently have a way to enforce a lease across the whole
* cluster; until we do, disable leases (by just returning -EINVAL),
* unless the administrator has requested purely local locking.
*
* Locking: called under i_lock
*
* Returns: errno
*/
static int gfs2_setlease(struct file *file, long arg, struct file_lock **fl)
{
return -EINVAL;
}
/**
* 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)
posix_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;
state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
mutex_lock(&fp->f_fl_mutex);
gl = fl_gh->gh_gl;
if (gl) {
if (fl_gh->gh_state == state)
goto out;
flock_lock_file_wait(file,
&(struct file_lock){.fl_type = F_UNLCK});
gfs2_glock_dq_wait(fl_gh);
gfs2_holder_reinit(state, flags, fl_gh);
} else {
error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
&gfs2_flock_glops, CREATE, &gl);
if (error)
goto out;
gfs2_holder_init(gl, state, flags, fl_gh);
gfs2_glock_put(gl);
}
error = gfs2_glock_nq(fl_gh);
if (error) {
gfs2_holder_uninit(fl_gh);
if (error == GLR_TRYFAILED)
error = -EAGAIN;
} else {
error = flock_lock_file_wait(file, fl);
gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
}
out:
mutex_unlock(&fp->f_fl_mutex);
return error;
}
static int hpfs_unlink(struct inode *dir, struct dentry *dentry)
{
const unsigned char *name = dentry->d_name.name;
unsigned len = dentry->d_name.len;
struct quad_buffer_head qbh;
struct hpfs_dirent *de;
struct inode *inode = dentry->d_inode;
dnode_secno dno;
int r;
int rep = 0;
int err;
hpfs_lock(dir->i_sb);
hpfs_adjust_length(name, &len);
again:
err = -ENOENT;
de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh);
if (!de)
goto out;
err = -EPERM;
if (de->first)
goto out1;
err = -EISDIR;
if (de->directory)
goto out1;
r = hpfs_remove_dirent(dir, dno, de, &qbh, 1);
switch (r) {
case 1:
hpfs_error(dir->i_sb, "there was error when removing dirent");
err = -EFSERROR;
break;
case 2: /* no space for deleting, try to truncate file */
err = -ENOSPC;
if (rep++)
break;
dentry_unhash(dentry);
if (!d_unhashed(dentry)) {
hpfs_unlock(dir->i_sb);
return -ENOSPC;
}
if (generic_permission(inode, MAY_WRITE) ||
!S_ISREG(inode->i_mode) ||
get_write_access(inode)) {
d_rehash(dentry);
} else {
struct iattr newattrs;
/*printk("HPFS: truncating file before delete.\n");*/
newattrs.ia_size = 0;
newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
err = notify_change(dentry, &newattrs);
put_write_access(inode);
if (!err)
goto again;
}
hpfs_unlock(dir->i_sb);
return -ENOSPC;
default:
drop_nlink(inode);
err = 0;
}
goto out;
out1:
hpfs_brelse4(&qbh);
out:
if (!err)
hpfs_update_directory_times(dir);
hpfs_unlock(dir->i_sb);
return err;
}
static int may_handle_open(struct dentry *dentry, int open_flag)
{
int acc_mode;
int error;
struct inode *inode = dentry->d_inode;
if((open_flag + 1) & O_ACCMODE)
open_flag++;
acc_mode = ACC_MODE(open_flag);
/* O_TRUNC implies we need access checks for write permissions */
if(open_flag & O_TRUNC)
acc_mode |= MAY_WRITE;
/* Allow the LSM permission hook to distinguish append
access from general write access. */
if(open_flag & O_APPEND)
acc_mode |= MAY_APPEND;
if(S_ISDIR(inode->i_mode) && (acc_mode & MAY_WRITE))
return -EISDIR;
error = handle_permission(inode, acc_mode);
if (error)
return error;
if(S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode))
{
open_flag &= ~O_TRUNC;
}
else if(S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode))
{
#ifdef IN_KERNEL_CHANGE_NOT_SUPP
if(nd->mnt->mnt_flags & MNT_NODEV)
return -EACCES;
#endif
open_flag &= ~O_TRUNC;
}
else if(IS_RDONLY(inode) && (acc_mode & MAY_WRITE))
return -EROFS;
/*
* An append-only file must be opened in append mode for writing.
*/
if(IS_APPEND(inode))
{
if((open_flag & FMODE_WRITE) && !(open_flag & O_APPEND))
return -EPERM;
if(open_flag & O_TRUNC)
return -EPERM;
}
/* O_NOATIME can only be set by the owner or superuser */
if(open_flag & O_NOATIME)
if(current->fsuid != inode->i_uid && !capable(CAP_FOWNER))
return -EPERM;
/*
* Ensure there are no outstanding leases on the file.
*/
error = break_lease(inode, open_flag);
if(error)
return error;
if(open_flag & O_TRUNC)
{
error = get_write_access(inode);
if(error)
return error;
#ifdef IN_KERNEL_CHANGE_NOT_SUPP
/*
* Refuse to truncate files with mandatory locks held on them.
*/
error = locks_verify_locked(inode);
#endif
if(!error)
{
DQUOT_INIT(inode);
error = handle_truncate(dentry, 0, ATTR_MTIME | ATTR_CTIME);
}
put_write_access(inode);
if(error)
return error;
}
else if(open_flag & FMODE_WRITE)
DQUOT_INIT(inode);
return 0;
}
