int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
struct ceph_acls_info *info)
{
struct posix_acl *acl, *default_acl;
size_t val_size1 = 0, val_size2 = 0;
struct ceph_pagelist *pagelist = NULL;
void *tmp_buf = NULL;
int err;
err = posix_acl_create(dir, mode, &default_acl, &acl);
if (err)
return err;
if (acl) {
int ret = posix_acl_equiv_mode(acl, mode);
if (ret < 0)
goto out_err;
if (ret == 0) {
posix_acl_release(acl);
acl = NULL;
}
}
if (!default_acl && !acl)
return 0;
if (acl)
val_size1 = posix_acl_xattr_size(acl->a_count);
if (default_acl)
val_size2 = posix_acl_xattr_size(default_acl->a_count);
err = -ENOMEM;
tmp_buf = kmalloc(max(val_size1, val_size2), GFP_NOFS);
if (!tmp_buf)
goto out_err;
pagelist = kmalloc(sizeof(struct ceph_pagelist), GFP_NOFS);
if (!pagelist)
goto out_err;
ceph_pagelist_init(pagelist);
err = ceph_pagelist_reserve(pagelist, PAGE_SIZE);
if (err)
goto out_err;
ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1);
if (acl) {
size_t len = strlen(POSIX_ACL_XATTR_ACCESS);
err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8);
if (err)
goto out_err;
ceph_pagelist_encode_string(pagelist, POSIX_ACL_XATTR_ACCESS,
len);
err = posix_acl_to_xattr(&init_user_ns, acl,
tmp_buf, val_size1);
if (err < 0)
goto out_err;
ceph_pagelist_encode_32(pagelist, val_size1);
ceph_pagelist_append(pagelist, tmp_buf, val_size1);
}
if (default_acl) {
size_t len = strlen(POSIX_ACL_XATTR_DEFAULT);
err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
if (err)
goto out_err;
err = ceph_pagelist_encode_string(pagelist,
POSIX_ACL_XATTR_DEFAULT, len);
err = posix_acl_to_xattr(&init_user_ns, default_acl,
tmp_buf, val_size2);
if (err < 0)
goto out_err;
ceph_pagelist_encode_32(pagelist, val_size2);
ceph_pagelist_append(pagelist, tmp_buf, val_size2);
}
kfree(tmp_buf);
info->acl = acl;
info->default_acl = default_acl;
info->pagelist = pagelist;
return 0;
out_err:
posix_acl_release(acl);
posix_acl_release(default_acl);
kfree(tmp_buf);
if (pagelist)
ceph_pagelist_release(pagelist);
return err;
}
static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
struct gfs2_inode *ip, struct gfs2_diradd *da)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_alloc_parms ap = { .target = da->nr_blocks, };
int error;
if (da->nr_blocks) {
error = gfs2_quota_lock_check(dip);
if (error)
goto fail_quota_locks;
error = gfs2_inplace_reserve(dip, &ap);
if (error)
goto fail_quota_locks;
error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(dip, da, 2), 0);
if (error)
goto fail_ipreserv;
} else {
error = gfs2_trans_begin(sdp, RES_LEAF + 2 * RES_DINODE, 0);
if (error)
goto fail_quota_locks;
}
error = gfs2_dir_add(&dip->i_inode, name, ip, da);
if (error)
goto fail_end_trans;
fail_end_trans:
gfs2_trans_end(sdp);
fail_ipreserv:
gfs2_inplace_release(dip);
fail_quota_locks:
gfs2_quota_unlock(dip);
return error;
}
static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
void *fs_info)
{
const struct xattr *xattr;
int err = 0;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
err = __gfs2_xattr_set(inode, xattr->name, xattr->value,
xattr->value_len, 0,
GFS2_EATYPE_SECURITY);
if (err < 0)
break;
}
return err;
}
/**
* gfs2_create_inode - Create a new inode
* @dir: The parent directory
* @dentry: The new dentry
* @file: If non-NULL, the file which is being opened
* @mode: The permissions on the new inode
* @dev: For device nodes, this is the device number
* @symname: For symlinks, this is the link destination
* @size: The initial size of the inode (ignored for directories)
*
* Returns: 0 on success, or error code
*/
static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
struct file *file,
umode_t mode, dev_t dev, const char *symname,
unsigned int size, int excl, int *opened)
{
const struct qstr *name = &dentry->d_name;
struct posix_acl *default_acl, *acl;
struct gfs2_holder ghs[2];
struct inode *inode = NULL;
struct gfs2_inode *dip = GFS2_I(dir), *ip;
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_glock *io_gl;
struct dentry *d;
int error, free_vfs_inode = 0;
u32 aflags = 0;
unsigned blocks = 1;
struct gfs2_diradd da = { .bh = NULL, };
if (!name->len || name->len > GFS2_FNAMESIZE)
return -ENAMETOOLONG;
error = gfs2_rs_alloc(dip);
if (error)
return error;
error = gfs2_rindex_update(sdp);
if (error)
return error;
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
if (error)
goto fail;
error = create_ok(dip, name, mode);
if (error)
goto fail_gunlock;
inode = gfs2_dir_search(dir, &dentry->d_name, !S_ISREG(mode) || excl);
error = PTR_ERR(inode);
if (!IS_ERR(inode)) {
d = d_splice_alias(inode, dentry);
error = PTR_ERR(d);
if (IS_ERR(d))
goto fail_gunlock;
error = 0;
if (file) {
if (S_ISREG(inode->i_mode)) {
WARN_ON(d != NULL);
error = finish_open(file, dentry, gfs2_open_common, opened);
} else {
error = finish_no_open(file, d);
}
} else {
dput(d);
}
gfs2_glock_dq_uninit(ghs);
return error;
} else if (error != -ENOENT) {
goto fail_gunlock;
}
error = gfs2_diradd_alloc_required(dir, name, &da);
if (error < 0)
goto fail_gunlock;
inode = new_inode(sdp->sd_vfs);
error = -ENOMEM;
if (!inode)
goto fail_gunlock;
error = posix_acl_create(dir, &mode, &default_acl, &acl);
if (error)
goto fail_free_vfs_inode;
ip = GFS2_I(inode);
error = gfs2_rs_alloc(ip);
if (error)
goto fail_free_acls;
inode->i_mode = mode;
set_nlink(inode, S_ISDIR(mode) ? 2 : 1);
inode->i_rdev = dev;
inode->i_size = size;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
gfs2_set_inode_blocks(inode, 1);
munge_mode_uid_gid(dip, inode);
ip->i_goal = dip->i_goal;
ip->i_diskflags = 0;
ip->i_eattr = 0;
ip->i_height = 0;
ip->i_depth = 0;
ip->i_entries = 0;
switch(mode & S_IFMT) {
case S_IFREG:
if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) ||
gfs2_tune_get(sdp, gt_new_files_jdata))
ip->i_diskflags |= GFS2_DIF_JDATA;
gfs2_set_aops(inode);
break;
case S_IFDIR:
ip->i_diskflags |= (dip->i_diskflags & GFS2_DIF_INHERIT_JDATA);
ip->i_diskflags |= GFS2_DIF_JDATA;
ip->i_entries = 2;
break;
}
gfs2_set_inode_flags(inode);
if ((GFS2_I(sdp->sd_root_dir->d_inode) == dip) ||
(dip->i_diskflags & GFS2_DIF_TOPDIR))
aflags |= GFS2_AF_ORLOV;
if (default_acl || acl)
blocks++;
error = alloc_dinode(ip, aflags, &blocks);
if (error)
goto fail_free_inode;
gfs2_set_inode_blocks(inode, blocks);
error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
if (error)
goto fail_free_inode;
ip->i_gl->gl_object = ip;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
if (error)
goto fail_free_inode;
error = gfs2_trans_begin(sdp, blocks, 0);
if (error)
goto fail_gunlock2;
if (blocks > 1) {
ip->i_eattr = ip->i_no_addr + 1;
gfs2_init_xattr(ip);
}
init_dinode(dip, ip, symname);
gfs2_trans_end(sdp);
error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (error)
goto fail_gunlock2;
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (error)
goto fail_gunlock2;
ip->i_iopen_gh.gh_gl->gl_object = ip;
gfs2_glock_put(io_gl);
gfs2_set_iop(inode);
insert_inode_hash(inode);
if (default_acl) {
error = gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
posix_acl_release(default_acl);
}
if (acl) {
if (!error)
error = gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS);
posix_acl_release(acl);
}
if (error)
goto fail_gunlock3;
error = security_inode_init_security(&ip->i_inode, &dip->i_inode, name,
&gfs2_initxattrs, NULL);
if (error)
goto fail_gunlock3;
error = link_dinode(dip, name, ip, &da);
if (error)
goto fail_gunlock3;
mark_inode_dirty(inode);
d_instantiate(dentry, inode);
if (file) {
*opened |= FILE_CREATED;
error = finish_open(file, dentry, gfs2_open_common, opened);
}
gfs2_glock_dq_uninit(ghs);
gfs2_glock_dq_uninit(ghs + 1);
return error;
fail_gunlock3:
gfs2_glock_dq_uninit(ghs + 1);
if (ip->i_gl)
gfs2_glock_put(ip->i_gl);
goto fail_gunlock;
fail_gunlock2:
gfs2_glock_dq_uninit(ghs + 1);
fail_free_inode:
if (ip->i_gl)
gfs2_glock_put(ip->i_gl);
gfs2_rs_delete(ip, NULL);
fail_free_acls:
if (default_acl)
posix_acl_release(default_acl);
if (acl)
posix_acl_release(acl);
fail_free_vfs_inode:
free_vfs_inode = 1;
fail_gunlock:
gfs2_dir_no_add(&da);
gfs2_glock_dq_uninit(ghs);
if (inode && !IS_ERR(inode)) {
clear_nlink(inode);
if (!free_vfs_inode)
mark_inode_dirty(inode);
set_bit(free_vfs_inode ? GIF_FREE_VFS_INODE : GIF_ALLOC_FAILED,
&GFS2_I(inode)->i_flags);
iput(inode);
}
fail:
return error;
}
/**
* gfs2_create - Create a file
* @dir: The directory in which to create the file
* @dentry: The dentry of the new file
* @mode: The mode of the new file
*
* Returns: errno
*/
static int gfs2_create(struct inode *dir, struct dentry *dentry,
umode_t mode, bool excl)
{
return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl, NULL);
}
/**
* __gfs2_lookup - Look up a filename in a directory and return its inode
* @dir: The directory inode
* @dentry: The dentry of the new inode
* @file: File to be opened
* @opened: atomic_open flags
*
*
* Returns: errno
*/
static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
struct file *file, int *opened)
{
struct inode *inode;
struct dentry *d;
struct gfs2_holder gh;
struct gfs2_glock *gl;
int error;
inode = gfs2_lookupi(dir, &dentry->d_name, 0);
if (!inode)
return NULL;
if (IS_ERR(inode))
return ERR_CAST(inode);
gl = GFS2_I(inode)->i_gl;
error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
if (error) {
iput(inode);
return ERR_PTR(error);
}
d = d_splice_alias(inode, dentry);
if (IS_ERR(d)) {
iput(inode);
gfs2_glock_dq_uninit(&gh);
return d;
}
if (file && S_ISREG(inode->i_mode))
error = finish_open(file, dentry, gfs2_open_common, opened);
gfs2_glock_dq_uninit(&gh);
if (error) {
dput(d);
return ERR_PTR(error);
}
return d;
}
static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
unsigned flags)
{
return __gfs2_lookup(dir, dentry, NULL, NULL);
}
/**
* gfs2_link - Link to a file
* @old_dentry: The inode to link
* @dir: Add link to this directory
* @dentry: The name of the link
*
* Link the inode in "old_dentry" into the directory "dir" with the
* name in "dentry".
*
* Returns: errno
*/
static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_sbd *sdp = GFS2_SB(dir);
struct inode *inode = old_dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder ghs[2];
struct buffer_head *dibh;
struct gfs2_diradd da = { .bh = NULL, };
int error;
if (S_ISDIR(inode->i_mode))
return -EPERM;
error = gfs2_rs_alloc(dip);
if (error)
return error;
gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
error = gfs2_glock_nq(ghs); /* parent */
if (error)
goto out_parent;
error = gfs2_glock_nq(ghs + 1); /* child */
if (error)
goto out_child;
error = -ENOENT;
if (inode->i_nlink == 0)
goto out_gunlock;
error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
if (error)
goto out_gunlock;
error = gfs2_dir_check(dir, &dentry->d_name, NULL);
switch (error) {
case -ENOENT:
break;
case 0:
error = -EEXIST;
default:
goto out_gunlock;
}
error = -EINVAL;
if (!dip->i_inode.i_nlink)
goto out_gunlock;
error = -EFBIG;
if (dip->i_entries == (u32)-1)
goto out_gunlock;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out_gunlock;
error = -EINVAL;
if (!ip->i_inode.i_nlink)
goto out_gunlock;
error = -EMLINK;
if (ip->i_inode.i_nlink == (u32)-1)
goto out_gunlock;
error = gfs2_diradd_alloc_required(dir, &dentry->d_name, &da);
if (error < 0)
goto out_gunlock;
if (da.nr_blocks) {
struct gfs2_alloc_parms ap = { .target = da.nr_blocks, };
error = gfs2_quota_lock_check(dip);
if (error)
goto out_gunlock;
error = gfs2_inplace_reserve(dip, &ap);
if (error)
goto out_gunlock_q;
error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(dip, &da, 2), 0);
if (error)
goto out_ipres;
} else {
error = gfs2_trans_begin(sdp, 2 * RES_DINODE + RES_LEAF, 0);
if (error)
goto out_ipres;
}
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto out_end_trans;
error = gfs2_dir_add(dir, &dentry->d_name, ip, &da);
if (error)
goto out_brelse;
gfs2_trans_add_meta(ip->i_gl, dibh);
inc_nlink(&ip->i_inode);
ip->i_inode.i_ctime = CURRENT_TIME;
ihold(inode);
d_instantiate(dentry, inode);
mark_inode_dirty(inode);
out_brelse:
brelse(dibh);
out_end_trans:
gfs2_trans_end(sdp);
out_ipres:
if (da.nr_blocks)
gfs2_inplace_release(dip);
out_gunlock_q:
if (da.nr_blocks)
gfs2_quota_unlock(dip);
out_gunlock:
gfs2_dir_no_add(&da);
gfs2_glock_dq(ghs + 1);
out_child:
gfs2_glock_dq(ghs);
out_parent:
gfs2_holder_uninit(ghs);
gfs2_holder_uninit(ghs + 1);
return error;
}
/*
* gfs2_unlink_ok - check to see that a inode is still in a directory
* @dip: the directory
* @name: the name of the file
* @ip: the inode
*
* Assumes that the lock on (at least) @dip is held.
*
* Returns: 0 if the parent/child relationship is correct, errno if it isn't
*/
static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
const struct gfs2_inode *ip)
{
int error;
if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
return -EPERM;
if ((dip->i_inode.i_mode & S_ISVTX) &&
!uid_eq(dip->i_inode.i_uid, current_fsuid()) &&
!uid_eq(ip->i_inode.i_uid, current_fsuid()) && !capable(CAP_FOWNER))
return -EPERM;
if (IS_APPEND(&dip->i_inode))
return -EPERM;
error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
if (error)
return error;
error = gfs2_dir_check(&dip->i_inode, name, ip);
if (error)
return error;
return 0;
}
/*
* Convert from filesystem to in-memory representation.
*/
static struct posix_acl *
ext2_acl_from_disk(const void *value, size_t size)
{
const char *end = (char *)value + size;
int n, count;
struct posix_acl *acl;
if (!value)
return NULL;
if (size < sizeof(ext2_acl_header))
return ERR_PTR(-EINVAL);
if (((ext2_acl_header *)value)->a_version !=
cpu_to_le32(EXT2_ACL_VERSION))
return ERR_PTR(-EINVAL);
value = (char *)value + sizeof(ext2_acl_header);
count = ext2_acl_count(size);
if (count < 0)
return ERR_PTR(-EINVAL);
if (count == 0)
return NULL;
acl = posix_acl_alloc(count, GFP_KERNEL);
if (!acl)
return ERR_PTR(-ENOMEM);
for (n=0; n < count; n++) {
ext2_acl_entry *entry =
(ext2_acl_entry *)value;
if ((char *)value + sizeof(ext2_acl_entry_short) > end)
goto fail;
acl->a_entries[n].e_tag = le16_to_cpu(entry->e_tag);
acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
switch(acl->a_entries[n].e_tag) {
case ACL_USER_OBJ:
case ACL_GROUP_OBJ:
case ACL_MASK:
case ACL_OTHER:
value = (char *)value +
sizeof(ext2_acl_entry_short);
acl->a_entries[n].e_id = ACL_UNDEFINED_ID;
break;
case ACL_USER:
case ACL_GROUP:
value = (char *)value + sizeof(ext2_acl_entry);
if ((char *)value > end)
goto fail;
acl->a_entries[n].e_id =
le32_to_cpu(entry->e_id);
break;
default:
goto fail;
}
}
if (value != end)
goto fail;
return acl;
fail:
posix_acl_release(acl);
return ERR_PTR(-EINVAL);
}
/*
* Create a regular file.
*/
static int
nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
int flags)
{
struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
int status = -ENOMEM;
dprintk("NFS call create %pd\n", dentry);
data = nfs3_alloc_createdata();
if (data == NULL)
goto out;
data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_CREATE];
data->arg.create.fh = NFS_FH(dir);
data->arg.create.name = dentry->d_name.name;
data->arg.create.len = dentry->d_name.len;
data->arg.create.sattr = sattr;
data->arg.create.createmode = NFS3_CREATE_UNCHECKED;
if (flags & O_EXCL) {
data->arg.create.createmode = NFS3_CREATE_EXCLUSIVE;
data->arg.create.verifier[0] = cpu_to_be32(jiffies);
data->arg.create.verifier[1] = cpu_to_be32(current->pid);
}
status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl);
if (status)
goto out;
for (;;) {
status = nfs3_do_create(dir, dentry, data);
if (status != -ENOTSUPP)
break;
/* If the server doesn't support the exclusive creation
* semantics, try again with simple 'guarded' mode. */
switch (data->arg.create.createmode) {
case NFS3_CREATE_EXCLUSIVE:
data->arg.create.createmode = NFS3_CREATE_GUARDED;
break;
case NFS3_CREATE_GUARDED:
data->arg.create.createmode = NFS3_CREATE_UNCHECKED;
break;
case NFS3_CREATE_UNCHECKED:
goto out;
}
nfs_fattr_init(data->res.dir_attr);
nfs_fattr_init(data->res.fattr);
}
if (status != 0)
goto out_release_acls;
/* When we created the file with exclusive semantics, make
* sure we set the attributes afterwards. */
if (data->arg.create.createmode == NFS3_CREATE_EXCLUSIVE) {
dprintk("NFS call setattr (post-create)\n");
if (!(sattr->ia_valid & ATTR_ATIME_SET))
sattr->ia_valid |= ATTR_ATIME;
if (!(sattr->ia_valid & ATTR_MTIME_SET))
sattr->ia_valid |= ATTR_MTIME;
/* Note: we could use a guarded setattr here, but I'm
* not sure this buys us anything (and I'd have
* to revamp the NFSv3 XDR code) */
status = nfs3_proc_setattr(dentry, data->res.fattr, sattr);
nfs_post_op_update_inode(dentry->d_inode, data->res.fattr);
dprintk("NFS reply setattr (post-create): %d\n", status);
if (status != 0)
goto out_release_acls;
}
status = nfs3_proc_setacls(dentry->d_inode, acl, default_acl);
out_release_acls:
posix_acl_release(acl);
posix_acl_release(default_acl);
out:
nfs3_free_createdata(data);
dprintk("NFS reply create: %d\n", status);
return status;
}
static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
struct gfs2_inode *ip, struct gfs2_diradd *da)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_alloc_parms ap = { .target = da->nr_blocks, };
int error;
if (da->nr_blocks) {
error = gfs2_quota_lock_check(dip, &ap);
if (error)
goto fail_quota_locks;
error = gfs2_inplace_reserve(dip, &ap);
if (error)
goto fail_quota_locks;
error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(dip, da, 2), 0);
if (error)
goto fail_ipreserv;
} else {
error = gfs2_trans_begin(sdp, RES_LEAF + 2 * RES_DINODE, 0);
if (error)
goto fail_quota_locks;
}
error = gfs2_dir_add(&dip->i_inode, name, ip, da);
gfs2_trans_end(sdp);
fail_ipreserv:
gfs2_inplace_release(dip);
fail_quota_locks:
gfs2_quota_unlock(dip);
return error;
}
static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
void *fs_info)
{
const struct xattr *xattr;
int err = 0;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
err = __gfs2_xattr_set(inode, xattr->name, xattr->value,
xattr->value_len, 0,
GFS2_EATYPE_SECURITY);
if (err < 0)
break;
}
return err;
}
/**
* gfs2_create_inode - Create a new inode
* @dir: The parent directory
* @dentry: The new dentry
* @file: If non-NULL, the file which is being opened
* @mode: The permissions on the new inode
* @dev: For device nodes, this is the device number
* @symname: For symlinks, this is the link destination
* @size: The initial size of the inode (ignored for directories)
*
* Returns: 0 on success, or error code
*/
static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
struct file *file,
umode_t mode, dev_t dev, const char *symname,
unsigned int size, int excl)
{
const struct qstr *name = &dentry->d_name;
struct posix_acl *default_acl, *acl;
struct gfs2_holder ghs[2];
struct inode *inode = NULL;
struct gfs2_inode *dip = GFS2_I(dir), *ip;
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_glock *io_gl = NULL;
int error, free_vfs_inode = 1;
u32 aflags = 0;
unsigned blocks = 1;
struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, };
if (!name->len || name->len > GFS2_FNAMESIZE)
return -ENAMETOOLONG;
error = gfs2_rsqa_alloc(dip);
if (error)
return error;
error = gfs2_rindex_update(sdp);
if (error)
return error;
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
if (error)
goto fail;
gfs2_holder_mark_uninitialized(ghs + 1);
error = create_ok(dip, name, mode);
if (error)
goto fail_gunlock;
inode = gfs2_dir_search(dir, &dentry->d_name, !S_ISREG(mode) || excl);
error = PTR_ERR(inode);
if (!IS_ERR(inode)) {
if (S_ISDIR(inode->i_mode)) {
iput(inode);
inode = ERR_PTR(-EISDIR);
goto fail_gunlock;
}
d_instantiate(dentry, inode);
error = 0;
if (file) {
if (S_ISREG(inode->i_mode))
error = finish_open(file, dentry, gfs2_open_common);
else
error = finish_no_open(file, NULL);
}
gfs2_glock_dq_uninit(ghs);
return error;
} else if (error != -ENOENT) {
goto fail_gunlock;
}
error = gfs2_diradd_alloc_required(dir, name, &da);
if (error < 0)
goto fail_gunlock;
inode = new_inode(sdp->sd_vfs);
error = -ENOMEM;
if (!inode)
goto fail_gunlock;
error = posix_acl_create(dir, &mode, &default_acl, &acl);
if (error)
goto fail_gunlock;
ip = GFS2_I(inode);
error = gfs2_rsqa_alloc(ip);
if (error)
goto fail_free_acls;
inode->i_mode = mode;
set_nlink(inode, S_ISDIR(mode) ? 2 : 1);
inode->i_rdev = dev;
inode->i_size = size;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
gfs2_set_inode_blocks(inode, 1);
munge_mode_uid_gid(dip, inode);
check_and_update_goal(dip);
ip->i_goal = dip->i_goal;
ip->i_diskflags = 0;
ip->i_eattr = 0;
ip->i_height = 0;
ip->i_depth = 0;
ip->i_entries = 0;
ip->i_no_addr = 0; /* Temporarily zero until real addr is assigned */
switch(mode & S_IFMT) {
case S_IFREG:
if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) ||
gfs2_tune_get(sdp, gt_new_files_jdata))
ip->i_diskflags |= GFS2_DIF_JDATA;
gfs2_set_aops(inode);
break;
case S_IFDIR:
ip->i_diskflags |= (dip->i_diskflags & GFS2_DIF_INHERIT_JDATA);
ip->i_diskflags |= GFS2_DIF_JDATA;
ip->i_entries = 2;
break;
}
/* Force SYSTEM flag on all files and subdirs of a SYSTEM directory */
if (dip->i_diskflags & GFS2_DIF_SYSTEM)
ip->i_diskflags |= GFS2_DIF_SYSTEM;
gfs2_set_inode_flags(inode);
if ((GFS2_I(d_inode(sdp->sd_root_dir)) == dip) ||
(dip->i_diskflags & GFS2_DIF_TOPDIR))
aflags |= GFS2_AF_ORLOV;
if (default_acl || acl)
blocks++;
error = alloc_dinode(ip, aflags, &blocks);
if (error)
goto fail_free_inode;
gfs2_set_inode_blocks(inode, blocks);
error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
if (error)
goto fail_free_inode;
flush_delayed_work(&ip->i_gl->gl_work);
glock_set_object(ip->i_gl, ip);
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
if (error)
goto fail_free_inode;
error = gfs2_trans_begin(sdp, blocks, 0);
if (error)
goto fail_gunlock2;
if (blocks > 1) {
ip->i_eattr = ip->i_no_addr + 1;
gfs2_init_xattr(ip);
}
init_dinode(dip, ip, symname);
gfs2_trans_end(sdp);
error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (error)
goto fail_gunlock2;
BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags));
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (error)
goto fail_gunlock2;
glock_set_object(ip->i_iopen_gh.gh_gl, ip);
gfs2_glock_put(io_gl);
gfs2_set_iop(inode);
insert_inode_hash(inode);
free_vfs_inode = 0; /* After this point, the inode is no longer
considered free. Any failures need to undo
the gfs2 structures. */
if (default_acl) {
error = __gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
if (error)
goto fail_gunlock3;
posix_acl_release(default_acl);
default_acl = NULL;
}
if (acl) {
error = __gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS);
if (error)
goto fail_gunlock3;
posix_acl_release(acl);
acl = NULL;
}
error = security_inode_init_security(&ip->i_inode, &dip->i_inode, name,
&gfs2_initxattrs, NULL);
if (error)
goto fail_gunlock3;
error = link_dinode(dip, name, ip, &da);
if (error)
goto fail_gunlock3;
mark_inode_dirty(inode);
d_instantiate(dentry, inode);
if (file) {
file->f_mode |= FMODE_CREATED;
error = finish_open(file, dentry, gfs2_open_common);
}
gfs2_glock_dq_uninit(ghs);
gfs2_glock_dq_uninit(ghs + 1);
clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
return error;
fail_gunlock3:
glock_clear_object(io_gl, ip);
gfs2_glock_dq_uninit(&ip->i_iopen_gh);
gfs2_glock_put(io_gl);
fail_gunlock2:
if (io_gl)
clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
fail_free_inode:
if (ip->i_gl) {
glock_clear_object(ip->i_gl, ip);
gfs2_glock_put(ip->i_gl);
}
gfs2_rsqa_delete(ip, NULL);
fail_free_acls:
posix_acl_release(default_acl);
posix_acl_release(acl);
fail_gunlock:
gfs2_dir_no_add(&da);
gfs2_glock_dq_uninit(ghs);
if (inode && !IS_ERR(inode)) {
clear_nlink(inode);
if (!free_vfs_inode)
mark_inode_dirty(inode);
set_bit(free_vfs_inode ? GIF_FREE_VFS_INODE : GIF_ALLOC_FAILED,
&GFS2_I(inode)->i_flags);
iput(inode);
}
if (gfs2_holder_initialized(ghs + 1))
gfs2_glock_dq_uninit(ghs + 1);
fail:
return error;
}
/**
* gfs2_create - Create a file
* @dir: The directory in which to create the file
* @dentry: The dentry of the new file
* @mode: The mode of the new file
*
* Returns: errno
*/
static int gfs2_create(struct inode *dir, struct dentry *dentry,
umode_t mode, bool excl)
{
return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl);
}
/**
* __gfs2_lookup - Look up a filename in a directory and return its inode
* @dir: The directory inode
* @dentry: The dentry of the new inode
* @file: File to be opened
*
*
* Returns: errno
*/
static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
struct file *file)
{
struct inode *inode;
struct dentry *d;
struct gfs2_holder gh;
struct gfs2_glock *gl;
int error;
inode = gfs2_lookupi(dir, &dentry->d_name, 0);
if (inode == NULL) {
d_add(dentry, NULL);
return NULL;
}
if (IS_ERR(inode))
return ERR_CAST(inode);
gl = GFS2_I(inode)->i_gl;
error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
if (error) {
iput(inode);
return ERR_PTR(error);
}
d = d_splice_alias(inode, dentry);
if (IS_ERR(d)) {
gfs2_glock_dq_uninit(&gh);
return d;
}
if (file && S_ISREG(inode->i_mode))
error = finish_open(file, dentry, gfs2_open_common);
gfs2_glock_dq_uninit(&gh);
if (error) {
dput(d);
return ERR_PTR(error);
}
return d;
}
static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
unsigned flags)
{
return __gfs2_lookup(dir, dentry, NULL);
}
/**
* gfs2_link - Link to a file
* @old_dentry: The inode to link
* @dir: Add link to this directory
* @dentry: The name of the link
*
* Link the inode in "old_dentry" into the directory "dir" with the
* name in "dentry".
*
* Returns: errno
*/
static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_sbd *sdp = GFS2_SB(dir);
struct inode *inode = d_inode(old_dentry);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder ghs[2];
struct buffer_head *dibh;
struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, };
int error;
if (S_ISDIR(inode->i_mode))
return -EPERM;
error = gfs2_rsqa_alloc(dip);
if (error)
return error;
gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
error = gfs2_glock_nq(ghs); /* parent */
if (error)
goto out_parent;
error = gfs2_glock_nq(ghs + 1); /* child */
if (error)
goto out_child;
error = -ENOENT;
if (inode->i_nlink == 0)
goto out_gunlock;
error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
if (error)
goto out_gunlock;
error = gfs2_dir_check(dir, &dentry->d_name, NULL);
switch (error) {
case -ENOENT:
break;
case 0:
error = -EEXIST;
default:
goto out_gunlock;
}
error = -EINVAL;
if (!dip->i_inode.i_nlink)
goto out_gunlock;
error = -EFBIG;
if (dip->i_entries == (u32)-1)
goto out_gunlock;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out_gunlock;
error = -EINVAL;
if (!ip->i_inode.i_nlink)
goto out_gunlock;
error = -EMLINK;
if (ip->i_inode.i_nlink == (u32)-1)
goto out_gunlock;
error = gfs2_diradd_alloc_required(dir, &dentry->d_name, &da);
if (error < 0)
goto out_gunlock;
if (da.nr_blocks) {
struct gfs2_alloc_parms ap = { .target = da.nr_blocks, };
error = gfs2_quota_lock_check(dip, &ap);
if (error)
goto out_gunlock;
error = gfs2_inplace_reserve(dip, &ap);
if (error)
goto out_gunlock_q;
error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(dip, &da, 2), 0);
if (error)
goto out_ipres;
} else {
error = gfs2_trans_begin(sdp, 2 * RES_DINODE + RES_LEAF, 0);
if (error)
goto out_ipres;
}
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto out_end_trans;
error = gfs2_dir_add(dir, &dentry->d_name, ip, &da);
if (error)
goto out_brelse;
gfs2_trans_add_meta(ip->i_gl, dibh);
inc_nlink(&ip->i_inode);
ip->i_inode.i_ctime = current_time(&ip->i_inode);
ihold(inode);
d_instantiate(dentry, inode);
mark_inode_dirty(inode);
out_brelse:
brelse(dibh);
out_end_trans:
gfs2_trans_end(sdp);
out_ipres:
if (da.nr_blocks)
gfs2_inplace_release(dip);
out_gunlock_q:
if (da.nr_blocks)
gfs2_quota_unlock(dip);
out_gunlock:
gfs2_dir_no_add(&da);
gfs2_glock_dq(ghs + 1);
out_child:
gfs2_glock_dq(ghs);
out_parent:
gfs2_holder_uninit(ghs);
gfs2_holder_uninit(ghs + 1);
return error;
}
/*
* gfs2_unlink_ok - check to see that a inode is still in a directory
* @dip: the directory
* @name: the name of the file
* @ip: the inode
*
* Assumes that the lock on (at least) @dip is held.
*
* Returns: 0 if the parent/child relationship is correct, errno if it isn't
*/
static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
const struct gfs2_inode *ip)
{
int error;
if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
return -EPERM;
if ((dip->i_inode.i_mode & S_ISVTX) &&
!uid_eq(dip->i_inode.i_uid, current_fsuid()) &&
!uid_eq(ip->i_inode.i_uid, current_fsuid()) && !capable(CAP_FOWNER))
return -EPERM;
if (IS_APPEND(&dip->i_inode))
return -EPERM;
error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
if (error)
return error;
return gfs2_dir_check(&dip->i_inode, name, ip);
}
/**
* gfs2_unlink_inode - Removes an inode from its parent dir and unlinks it
* @dip: The parent directory
* @name: The name of the entry in the parent directory
* @inode: The inode to be removed
*
* Called with all the locks and in a transaction. This will only be
* called for a directory after it has been checked to ensure it is empty.
*
* Returns: 0 on success, or an error
*/
static int gfs2_unlink_inode(struct gfs2_inode *dip,
const struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
struct gfs2_inode *ip = GFS2_I(inode);
int error;
error = gfs2_dir_del(dip, dentry);
if (error)
return error;
ip->i_entries = 0;
inode->i_ctime = current_time(inode);
if (S_ISDIR(inode->i_mode))
clear_nlink(inode);
else
drop_nlink(inode);
mark_inode_dirty(inode);
if (inode->i_nlink == 0)
gfs2_unlink_di(inode);
return 0;
}
/**
* gfs2_unlink - Unlink an inode (this does rmdir as well)
* @dir: The inode of the directory containing the inode to unlink
* @dentry: The file itself
*
* This routine uses the type of the inode as a flag to figure out
* whether this is an unlink or an rmdir.
*
* Returns: errno
*/
static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
{
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_sbd *sdp = GFS2_SB(dir);
struct inode *inode = d_inode(dentry);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder ghs[3];
struct gfs2_rgrpd *rgd;
int error;
error = gfs2_rindex_update(sdp);
if (error)
return error;
error = -EROFS;
gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr, 1);
if (!rgd)
goto out_inodes;
gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
error = gfs2_glock_nq(ghs); /* parent */
if (error)
goto out_parent;
error = gfs2_glock_nq(ghs + 1); /* child */
if (error)
goto out_child;
error = -ENOENT;
if (inode->i_nlink == 0)
goto out_rgrp;
if (S_ISDIR(inode->i_mode)) {
error = -ENOTEMPTY;
if (ip->i_entries > 2 || inode->i_nlink > 2)
goto out_rgrp;
}
error = gfs2_glock_nq(ghs + 2); /* rgrp */
if (error)
goto out_rgrp;
error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
if (error)
goto out_gunlock;
error = gfs2_trans_begin(sdp, 2*RES_DINODE + 3*RES_LEAF + RES_RG_BIT, 0);
if (error)
goto out_gunlock;
error = gfs2_unlink_inode(dip, dentry);
gfs2_trans_end(sdp);
out_gunlock:
gfs2_glock_dq(ghs + 2);
out_rgrp:
gfs2_glock_dq(ghs + 1);
out_child:
gfs2_glock_dq(ghs);
out_parent:
gfs2_holder_uninit(ghs + 2);
out_inodes:
gfs2_holder_uninit(ghs + 1);
gfs2_holder_uninit(ghs);
return error;
}
/**
* gfs2_symlink - Create a symlink
* @dir: The directory to create the symlink in
* @dentry: The dentry to put the symlink in
* @symname: The thing which the link points to
*
* Returns: errno
*/
static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
unsigned int size;
size = strlen(symname);
if (size >= gfs2_max_stuffed_size(GFS2_I(dir)))
return -ENAMETOOLONG;
return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0);
}
/**
* gfs2_mkdir - Make a directory
* @dir: The parent directory of the new one
* @dentry: The dentry of the new directory
* @mode: The mode of the new directory
*
* Returns: errno
*/
static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir));
return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0);
}
STATIC int
xfs_vn_mknod(
struct inode *dir,
struct dentry *dentry,
int mode,
dev_t rdev)
{
struct inode *inode;
struct xfs_inode *ip = NULL;
struct posix_acl *default_acl = NULL;
struct xfs_name name;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (S_ISCHR(mode) || S_ISBLK(mode)) {
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
rdev = sysv_encode_dev(rdev);
} else {
rdev = 0;
}
if (IS_POSIXACL(dir)) {
default_acl = xfs_get_acl(dir, ACL_TYPE_DEFAULT);
if (IS_ERR(default_acl))
return PTR_ERR(default_acl);
if (!default_acl)
mode &= ~current_umask();
}
xfs_dentry_to_name(&name, dentry);
error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
if (unlikely(error))
goto out_free_acl;
inode = VFS_I(ip);
error = xfs_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
if (default_acl) {
error = -xfs_inherit_acl(inode, default_acl);
default_acl = NULL;
if (unlikely(error))
goto out_cleanup_inode;
}
d_instantiate(dentry, inode);
return -error;
out_cleanup_inode:
xfs_cleanup_inode(dir, inode, dentry);
out_free_acl:
posix_acl_release(default_acl);
return -error;
}
/*
* Initialize the ACLs of a new inode. If parent directory has default ACL,
* then clone to new inode. Called from ocfs2_mknod.
*/
int ocfs2_init_acl(handle_t *handle,
struct inode *inode,
struct inode *dir,
struct buffer_head *di_bh,
struct buffer_head *dir_bh,
struct ocfs2_alloc_context *meta_ac,
struct ocfs2_alloc_context *data_ac)
{
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct posix_acl *acl = NULL;
int ret = 0, ret2;
mode_t mode;
if (!S_ISLNK(inode->i_mode)) {
if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT,
dir_bh);
if (IS_ERR(acl))
return PTR_ERR(acl);
}
if (!acl) {
mode = inode->i_mode & ~current_umask();
ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
if (ret) {
mlog_errno(ret);
goto cleanup;
}
}
}
if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) {
struct posix_acl *clone;
if (S_ISDIR(inode->i_mode)) {
ret = ocfs2_set_acl(handle, inode, di_bh,
ACL_TYPE_DEFAULT, acl,
meta_ac, data_ac);
if (ret)
goto cleanup;
}
clone = posix_acl_clone(acl, GFP_NOFS);
ret = -ENOMEM;
if (!clone)
goto cleanup;
mode = inode->i_mode;
ret = posix_acl_create_masq(clone, &mode);
if (ret >= 0) {
ret2 = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
if (ret2) {
mlog_errno(ret2);
ret = ret2;
goto cleanup;
}
if (ret > 0) {
ret = ocfs2_set_acl(handle, inode,
di_bh, ACL_TYPE_ACCESS,
clone, meta_ac, data_ac);
}
}
posix_acl_release(clone);
}
cleanup:
posix_acl_release(acl);
return ret;
}
void v9fs_put_acl(struct posix_acl *dacl,
struct posix_acl *acl)
{
posix_acl_release(dacl);
posix_acl_release(acl);
}
struct posix_acl *get_acl(struct inode *inode, int type)
{
void *sentinel;
struct posix_acl **p;
struct posix_acl *acl;
/*
* The sentinel is used to detect when another operation like
* set_cached_acl() or forget_cached_acl() races with get_acl().
* It is guaranteed that is_uncached_acl(sentinel) is true.
*/
acl = get_cached_acl(inode, type);
if (!is_uncached_acl(acl))
return acl;
if (!IS_POSIXACL(inode))
return NULL;
sentinel = uncached_acl_sentinel(current);
p = acl_by_type(inode, type);
/*
* If the ACL isn't being read yet, set our sentinel. Otherwise, the
* current value of the ACL will not be ACL_NOT_CACHED and so our own
* sentinel will not be set; another task will update the cache. We
* could wait for that other task to complete its job, but it's easier
* to just call ->get_acl to fetch the ACL ourself. (This is going to
* be an unlikely race.)
*/
if (cmpxchg(p, ACL_NOT_CACHED, sentinel) != ACL_NOT_CACHED)
/* fall through */ ;
/*
* Normally, the ACL returned by ->get_acl will be cached.
* A filesystem can prevent that by calling
* forget_cached_acl(inode, type) in ->get_acl.
*
* If the filesystem doesn't have a get_acl() function at all, we'll
* just create the negative cache entry.
*/
if (!inode->i_op->get_acl) {
set_cached_acl(inode, type, NULL);
return NULL;
}
acl = inode->i_op->get_acl(inode, type);
if (IS_ERR(acl)) {
/*
* Remove our sentinel so that we don't block future attempts
* to cache the ACL.
*/
cmpxchg(p, sentinel, ACL_NOT_CACHED);
return acl;
}
/*
* Cache the result, but only if our sentinel is still in place.
*/
posix_acl_dup(acl);
if (unlikely(cmpxchg(p, sentinel, acl) != sentinel))
posix_acl_release(acl);
return acl;
}
/*
* inode->i_sem: down, or inode is just being initialized
* BKL: held
*/
static int
ext3_do_set_acl(handle_t *handle, struct inode *inode, int type,
struct posix_acl *acl)
{
struct ext3_inode_info *ei = EXT3_I(inode);
int name_index;
void *value = NULL;
size_t size;
int error;
if (S_ISLNK(inode->i_mode))
return -ENODATA;
switch(type) {
case ACL_TYPE_ACCESS:
name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS;
if (acl) {
mode_t mode = inode->i_mode;
error = posix_acl_equiv_mode(acl, &mode);
if (error < 0)
return error;
else {
inode->i_mode = mode;
ext3_mark_inode_dirty(handle, inode);
if (error == 0)
acl = NULL;
}
}
break;
case ACL_TYPE_DEFAULT:
name_index = EXT3_XATTR_INDEX_POSIX_ACL_DEFAULT;
if (!S_ISDIR(inode->i_mode))
return acl ? -EACCES : 0;
break;
default:
return -EINVAL;
}
if (acl) {
if (acl->a_count > EXT3_ACL_MAX_ENTRIES)
return -EINVAL;
value = ext3_acl_to_disk(acl, &size);
if (IS_ERR(value))
return (int)PTR_ERR(value);
}
error = ext3_xattr_set_handle(handle, inode, name_index, "",
value, size, 0);
if (value)
kfree(value);
if (!error) {
switch(type) {
case ACL_TYPE_ACCESS:
if (ei->i_acl != EXT3_ACL_NOT_CACHED)
posix_acl_release(ei->i_acl);
ei->i_acl = posix_acl_dup(acl);
break;
case ACL_TYPE_DEFAULT:
if (ei->i_default_acl != EXT3_ACL_NOT_CACHED)
posix_acl_release(ei->i_default_acl);
ei->i_default_acl = posix_acl_dup(acl);
break;
}
}
return error;
}
/* dir->i_mutex: locked,
* inode is new and not released into the wild yet */
int
reiserfs_inherit_default_acl(struct inode *dir, struct dentry *dentry,
struct inode *inode)
{
struct posix_acl *acl;
int err = 0;
/* ACLs only get applied to files and directories */
if (S_ISLNK(inode->i_mode))
return 0;
/* ACLs can only be used on "new" objects, so if it's an old object
* there is nothing to inherit from */
if (get_inode_sd_version(dir) == STAT_DATA_V1)
goto apply_umask;
/* Don't apply ACLs to objects in the .reiserfs_priv tree.. This
* would be useless since permissions are ignored, and a pain because
* it introduces locking cycles */
if (is_reiserfs_priv_object(dir)) {
reiserfs_mark_inode_private(inode);
goto apply_umask;
}
acl = reiserfs_get_acl(dir, ACL_TYPE_DEFAULT);
if (IS_ERR(acl)) {
if (PTR_ERR(acl) == -ENODATA)
goto apply_umask;
return PTR_ERR(acl);
}
if (acl) {
struct posix_acl *acl_copy;
mode_t mode = inode->i_mode;
int need_acl;
/* Copy the default ACL to the default ACL of a new directory */
if (S_ISDIR(inode->i_mode)) {
err = reiserfs_set_acl(inode, ACL_TYPE_DEFAULT, acl);
if (err)
goto cleanup;
}
/* Now we reconcile the new ACL and the mode,
potentially modifying both */
acl_copy = posix_acl_clone(acl, GFP_NOFS);
if (!acl_copy) {
err = -ENOMEM;
goto cleanup;
}
need_acl = posix_acl_create_masq(acl_copy, &mode);
if (need_acl >= 0) {
if (mode != inode->i_mode) {
inode->i_mode = mode;
}
/* If we need an ACL.. */
if (need_acl > 0) {
err =
reiserfs_set_acl(inode, ACL_TYPE_ACCESS,
acl_copy);
if (err)
goto cleanup_copy;
}
}
cleanup_copy:
posix_acl_release(acl_copy);
cleanup:
posix_acl_release(acl);
} else {
apply_umask:
/* no ACL, apply umask */
inode->i_mode &= ~current->fs->umask;
}
return err;
}
/*
* Inode operation set_posix_acl().
*
* inode->i_mutex: down
* BKL held [before 2.5.x]
*/
static int
reiserfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
{
char *name;
void *value = NULL;
struct posix_acl **p_acl;
size_t size;
int error;
struct reiserfs_inode_info *reiserfs_i = REISERFS_I(inode);
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
switch (type) {
case ACL_TYPE_ACCESS:
name = POSIX_ACL_XATTR_ACCESS;
p_acl = &reiserfs_i->i_acl_access;
if (acl) {
mode_t mode = inode->i_mode;
error = posix_acl_equiv_mode(acl, &mode);
if (error < 0)
return error;
else {
inode->i_mode = mode;
if (error == 0)
acl = NULL;
}
}
break;
case ACL_TYPE_DEFAULT:
name = POSIX_ACL_XATTR_DEFAULT;
p_acl = &reiserfs_i->i_acl_default;
if (!S_ISDIR(inode->i_mode))
return acl ? -EACCES : 0;
break;
default:
return -EINVAL;
}
if (acl) {
value = posix_acl_to_disk(acl, &size);
if (IS_ERR(value))
return (int)PTR_ERR(value);
error = reiserfs_xattr_set(inode, name, value, size, 0);
} else {
error = reiserfs_xattr_del(inode, name);
if (error == -ENODATA) {
/* This may seem odd here, but it means that the ACL was set
* with a value representable with mode bits. If there was
* an ACL before, reiserfs_xattr_del already dirtied the inode.
*/
mark_inode_dirty(inode);
error = 0;
}
}
kfree(value);
if (!error) {
/* Release the old one */
if (!IS_ERR(*p_acl) && *p_acl)
posix_acl_release(*p_acl);
if (acl == NULL)
*p_acl = ERR_PTR(-ENODATA);
else
*p_acl = posix_acl_dup(acl);
}
return error;
}
static int
nfs3_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
{
struct nfs3_linkargs arg = {
.fromfh = NFS_FH(inode),
.tofh = NFS_FH(dir),
.toname = name->name,
.tolen = name->len
};
struct nfs3_linkres res;
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_LINK],
.rpc_argp = &arg,
.rpc_resp = &res,
};
int status = -ENOMEM;
dprintk("NFS call link %s\n", name->name);
res.fattr = nfs_alloc_fattr();
res.dir_attr = nfs_alloc_fattr();
if (res.fattr == NULL || res.dir_attr == NULL)
goto out;
status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
nfs_post_op_update_inode(dir, res.dir_attr);
nfs_post_op_update_inode(inode, res.fattr);
out:
nfs_free_fattr(res.dir_attr);
nfs_free_fattr(res.fattr);
dprintk("NFS reply link: %d\n", status);
return status;
}
static int
nfs3_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
unsigned int len, struct iattr *sattr)
{
struct nfs3_createdata *data;
int status = -ENOMEM;
if (len > NFS3_MAXPATHLEN)
return -ENAMETOOLONG;
dprintk("NFS call symlink %pd\n", dentry);
data = nfs3_alloc_createdata();
if (data == NULL)
goto out;
data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_SYMLINK];
data->arg.symlink.fromfh = NFS_FH(dir);
data->arg.symlink.fromname = dentry->d_name.name;
data->arg.symlink.fromlen = dentry->d_name.len;
data->arg.symlink.pages = &page;
data->arg.symlink.pathlen = len;
data->arg.symlink.sattr = sattr;
status = nfs3_do_create(dir, dentry, data);
nfs3_free_createdata(data);
out:
dprintk("NFS reply symlink: %d\n", status);
return status;
}
static int
nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr)
{
struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
int status = -ENOMEM;
dprintk("NFS call mkdir %pd\n", dentry);
data = nfs3_alloc_createdata();
if (data == NULL)
goto out;
status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl);
if (status)
goto out;
data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKDIR];
data->arg.mkdir.fh = NFS_FH(dir);
data->arg.mkdir.name = dentry->d_name.name;
data->arg.mkdir.len = dentry->d_name.len;
data->arg.mkdir.sattr = sattr;
status = nfs3_do_create(dir, dentry, data);
if (status != 0)
goto out_release_acls;
status = nfs3_proc_setacls(dentry->d_inode, acl, default_acl);
out_release_acls:
posix_acl_release(acl);
posix_acl_release(default_acl);
out:
nfs3_free_createdata(data);
dprintk("NFS reply mkdir: %d\n", status);
return status;
}
static int
nfs3_proc_rmdir(struct inode *dir, struct qstr *name)
{
struct nfs_fattr *dir_attr;
struct nfs3_diropargs arg = {
.fh = NFS_FH(dir),
.name = name->name,
.len = name->len
};
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_RMDIR],
.rpc_argp = &arg,
};
int status = -ENOMEM;
dprintk("NFS call rmdir %s\n", name->name);
dir_attr = nfs_alloc_fattr();
if (dir_attr == NULL)
goto out;
msg.rpc_resp = dir_attr;
status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
nfs_post_op_update_inode(dir, dir_attr);
nfs_free_fattr(dir_attr);
out:
dprintk("NFS reply rmdir: %d\n", status);
return status;
}
/*
* The READDIR implementation is somewhat hackish - we pass the user buffer
* to the encode function, which installs it in the receive iovec.
* The decode function itself doesn't perform any decoding, it just makes
* sure the reply is syntactically correct.
*
* Also note that this implementation handles both plain readdir and
* readdirplus.
*/
static int
nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
u64 cookie, struct page **pages, unsigned int count, int plus)
{
struct inode *dir = dentry->d_inode;
__be32 *verf = NFS_I(dir)->cookieverf;
struct nfs3_readdirargs arg = {
.fh = NFS_FH(dir),
.cookie = cookie,
.verf = {verf[0], verf[1]},
.plus = plus,
.count = count,
.pages = pages
};
struct nfs3_readdirres res = {
.verf = verf,
.plus = plus
};
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_READDIR],
.rpc_argp = &arg,
.rpc_resp = &res,
.rpc_cred = cred
};
int status = -ENOMEM;
if (plus)
msg.rpc_proc = &nfs3_procedures[NFS3PROC_READDIRPLUS];
dprintk("NFS call readdir%s %d\n",
plus? "plus" : "", (unsigned int) cookie);
res.dir_attr = nfs_alloc_fattr();
if (res.dir_attr == NULL)
goto out;
status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
nfs_invalidate_atime(dir);
nfs_refresh_inode(dir, res.dir_attr);
nfs_free_fattr(res.dir_attr);
out:
dprintk("NFS reply readdir%s: %d\n",
plus? "plus" : "", status);
return status;
}
static int
nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
dev_t rdev)
{
struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
int status = -ENOMEM;
dprintk("NFS call mknod %pd %u:%u\n", dentry,
MAJOR(rdev), MINOR(rdev));
data = nfs3_alloc_createdata();
if (data == NULL)
goto out;
status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl);
if (status)
goto out;
data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKNOD];
data->arg.mknod.fh = NFS_FH(dir);
data->arg.mknod.name = dentry->d_name.name;
data->arg.mknod.len = dentry->d_name.len;
data->arg.mknod.sattr = sattr;
data->arg.mknod.rdev = rdev;
switch (sattr->ia_mode & S_IFMT) {
case S_IFBLK:
data->arg.mknod.type = NF3BLK;
break;
case S_IFCHR:
data->arg.mknod.type = NF3CHR;
break;
case S_IFIFO:
data->arg.mknod.type = NF3FIFO;
break;
case S_IFSOCK:
data->arg.mknod.type = NF3SOCK;
break;
default:
status = -EINVAL;
goto out;
}
status = nfs3_do_create(dir, dentry, data);
if (status != 0)
goto out_release_acls;
status = nfs3_proc_setacls(dentry->d_inode, acl, default_acl);
out_release_acls:
posix_acl_release(acl);
posix_acl_release(default_acl);
out:
nfs3_free_createdata(data);
dprintk("NFS reply mknod: %d\n", status);
return status;
}
static int
nfs3_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fsstat *stat)
{
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_FSSTAT],
.rpc_argp = fhandle,
.rpc_resp = stat,
};
int status;
dprintk("NFS call fsstat\n");
nfs_fattr_init(stat->fattr);
status = rpc_call_sync(server->client, &msg, 0);
dprintk("NFS reply fsstat: %d\n", status);
return status;
}
static int
do_proc_fsinfo(struct rpc_clnt *client, struct nfs_fh *fhandle,
struct nfs_fsinfo *info)
{
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_FSINFO],
.rpc_argp = fhandle,
.rpc_resp = info,
};
int status;
dprintk("NFS call fsinfo\n");
nfs_fattr_init(info->fattr);
status = rpc_call_sync(client, &msg, 0);
dprintk("NFS reply fsinfo: %d\n", status);
return status;
}
/*
* Bare-bones access to fsinfo: this is for nfs_get_root/nfs_get_sb via
* nfs_create_server
*/
static int
nfs3_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fsinfo *info)
{
int status;
status = do_proc_fsinfo(server->client, fhandle, info);
if (status && server->nfs_client->cl_rpcclient != server->client)
status = do_proc_fsinfo(server->nfs_client->cl_rpcclient, fhandle, info);
return status;
}
static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
{
int i, count;
struct posix_acl *acl;
struct f2fs_acl_header *hdr = (struct f2fs_acl_header *)value;
struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1);
const char *end = value + size;
if (hdr->a_version != cpu_to_le32(F2FS_ACL_VERSION))
return ERR_PTR(-EINVAL);
count = f2fs_acl_count(size);
if (count < 0)
return ERR_PTR(-EINVAL);
if (count == 0)
return NULL;
acl = posix_acl_alloc(count, GFP_NOFS);
if (!acl)
return ERR_PTR(-ENOMEM);
for (i = 0; i < count; i++) {
if ((char *)entry > end)
goto fail;
acl->a_entries[i].e_tag = le16_to_cpu(entry->e_tag);
acl->a_entries[i].e_perm = le16_to_cpu(entry->e_perm);
switch (acl->a_entries[i].e_tag) {
case ACL_USER_OBJ:
case ACL_GROUP_OBJ:
case ACL_MASK:
case ACL_OTHER:
entry = (struct f2fs_acl_entry *)((char *)entry +
sizeof(struct f2fs_acl_entry_short));
break;
case ACL_USER:
acl->a_entries[i].e_uid =
make_kuid(&init_user_ns,
le32_to_cpu(entry->e_id));
entry = (struct f2fs_acl_entry *)((char *)entry +
sizeof(struct f2fs_acl_entry));
break;
case ACL_GROUP:
acl->a_entries[i].e_gid =
make_kgid(&init_user_ns,
le32_to_cpu(entry->e_id));
entry = (struct f2fs_acl_entry *)((char *)entry +
sizeof(struct f2fs_acl_entry));
break;
default:
goto fail;
}
}
if ((char *)entry != end)
goto fail;
return acl;
fail:
posix_acl_release(acl);
return ERR_PTR(-EINVAL);
}
struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
{
struct nfs_server *server = NFS_SERVER(inode);
struct page *pages[NFSACL_MAXPAGES] = { };
struct nfs3_getaclargs args = {
.fh = NFS_FH(inode),
/* The xdr layer may allocate pages here. */
.pages = pages,
};
struct nfs3_getaclres res = {
NULL,
};
struct rpc_message msg = {
.rpc_argp = &args,
.rpc_resp = &res,
};
int status, count;
if (!nfs_server_capable(inode, NFS_CAP_ACLS))
return ERR_PTR(-EOPNOTSUPP);
status = nfs_revalidate_inode(server, inode);
if (status < 0)
return ERR_PTR(status);
/*
* Only get the access acl when explicitly requested: We don't
* need it for access decisions, and only some applications use
* it. Applications which request the access acl first are not
* penalized from this optimization.
*/
if (type == ACL_TYPE_ACCESS)
args.mask |= NFS_ACLCNT|NFS_ACL;
if (S_ISDIR(inode->i_mode))
args.mask |= NFS_DFACLCNT|NFS_DFACL;
if (args.mask == 0)
return NULL;
dprintk("NFS call getacl\n");
msg.rpc_proc = &server->client_acl->cl_procinfo[ACLPROC3_GETACL];
res.fattr = nfs_alloc_fattr();
if (res.fattr == NULL)
return ERR_PTR(-ENOMEM);
if (args.mask & NFS_ACL)
nfs3_prepare_get_acl(&inode->i_acl);
if (args.mask & NFS_DFACL)
nfs3_prepare_get_acl(&inode->i_default_acl);
status = rpc_call_sync(server->client_acl, &msg, 0);
dprintk("NFS reply getacl: %d\n", status);
/* pages may have been allocated at the xdr layer. */
for (count = 0; count < NFSACL_MAXPAGES && args.pages[count]; count++)
__free_page(args.pages[count]);
switch (status) {
case 0:
status = nfs_refresh_inode(inode, res.fattr);
break;
case -EPFNOSUPPORT:
case -EPROTONOSUPPORT:
dprintk("NFS_V3_ACL extension not supported; disabling\n");
server->caps &= ~NFS_CAP_ACLS;
case -ENOTSUPP:
status = -EOPNOTSUPP;
default:
goto getout;
}
if ((args.mask & res.mask) != args.mask) {
status = -EIO;
goto getout;
}
if (res.acl_access != NULL) {
if ((posix_acl_equiv_mode(res.acl_access, NULL) == 0) ||
res.acl_access->a_count == 0) {
posix_acl_release(res.acl_access);
res.acl_access = NULL;
}
}
if (res.mask & NFS_ACL)
nfs3_complete_get_acl(&inode->i_acl, res.acl_access);
else
forget_cached_acl(inode, ACL_TYPE_ACCESS);
if (res.mask & NFS_DFACL)
nfs3_complete_get_acl(&inode->i_default_acl, res.acl_default);
else
forget_cached_acl(inode, ACL_TYPE_DEFAULT);
nfs_free_fattr(res.fattr);
if (type == ACL_TYPE_ACCESS) {
posix_acl_release(res.acl_default);
return res.acl_access;
} else {
posix_acl_release(res.acl_access);
return res.acl_default;
}
getout:
nfs3_abort_get_acl(&inode->i_acl);
nfs3_abort_get_acl(&inode->i_default_acl);
posix_acl_release(res.acl_access);
posix_acl_release(res.acl_default);
nfs_free_fattr(res.fattr);
return ERR_PTR(status);
}
/*
* Inode operation listxattr()
*
* We totally ignore the generic listxattr here because it would be stupid
* not to. Since the xattrs are organized in a directory, we can just
* readdir to find them.
*/
ssize_t reiserfs_listxattr(struct dentry * dentry, char *buffer, size_t size)
{
struct dentry *dir;
int err = 0;
loff_t pos = 0;
struct listxattr_buf buf = {
.dentry = dentry,
.buf = buffer,
.size = buffer ? size : 0,
};
if (!dentry->d_inode)
return -EINVAL;
if (!dentry->d_sb->s_xattr ||
get_inode_sd_version(dentry->d_inode) == STAT_DATA_V1)
return -EOPNOTSUPP;
dir = open_xa_dir(dentry->d_inode, XATTR_REPLACE);
if (IS_ERR(dir)) {
err = PTR_ERR(dir);
if (err == -ENODATA)
err = 0; /* Not an error if there aren't any xattrs */
goto out;
}
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_XATTR);
err = reiserfs_readdir_dentry(dir, &buf, listxattr_filler, &pos);
mutex_unlock(&dir->d_inode->i_mutex);
if (!err)
err = buf.pos;
dput(dir);
out:
return err;
}
static int reiserfs_check_acl(struct inode *inode, int mask)
{
struct posix_acl *acl;
int error = -EAGAIN; /* do regular unix permission checks by default */
acl = reiserfs_get_acl(inode, ACL_TYPE_ACCESS);
if (acl) {
if (!IS_ERR(acl)) {
error = posix_acl_permission(inode, acl, mask);
posix_acl_release(acl);
} else if (PTR_ERR(acl) != -ENODATA)
error = PTR_ERR(acl);
}
return error;
}
static int create_privroot(struct dentry *dentry)
{
int err;
struct inode *inode = dentry->d_parent->d_inode;
WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
err = xattr_mkdir(inode, dentry, 0700);
if (err || !dentry->d_inode) {
reiserfs_warning(dentry->d_sb, "jdm-20006",
"xattrs/ACLs enabled and couldn't "
"find/create .reiserfs_priv. "
"Failing mount.");
return -EOPNOTSUPP;
}
dentry->d_inode->i_flags |= S_PRIVATE;
reiserfs_info(dentry->d_sb, "Created %s - reserved for xattr "
"storage.\n", PRIVROOT_NAME);
return 0;
}
STATIC int
xfs_generic_create(
struct inode *dir,
struct dentry *dentry,
umode_t mode,
dev_t rdev,
bool tmpfile) /* unnamed file */
{
struct inode *inode;
struct xfs_inode *ip = NULL;
struct posix_acl *default_acl, *acl;
struct xfs_name name;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (S_ISCHR(mode) || S_ISBLK(mode)) {
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
rdev = sysv_encode_dev(rdev);
} else {
rdev = 0;
}
error = posix_acl_create(dir, &mode, &default_acl, &acl);
if (error)
return error;
if (!tmpfile) {
xfs_dentry_to_name(&name, dentry, mode);
error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
} else {
error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip);
}
if (unlikely(error))
goto out_free_acl;
inode = VFS_I(ip);
error = xfs_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
#ifdef CONFIG_XFS_POSIX_ACL
if (default_acl) {
error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
if (error)
goto out_cleanup_inode;
}
if (acl) {
error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
if (error)
goto out_cleanup_inode;
}
#endif
if (tmpfile)
d_tmpfile(dentry, inode);
else
d_instantiate(dentry, inode);
xfs_finish_inode_setup(ip);
out_free_acl:
if (default_acl)
posix_acl_release(default_acl);
if (acl)
posix_acl_release(acl);
return error;
out_cleanup_inode:
xfs_finish_inode_setup(ip);
if (!tmpfile)
xfs_cleanup_inode(dir, inode, dentry);
iput(inode);
goto out_free_acl;
}
static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
{
int retval;
struct posix_acl *acl;
struct v9fs_session_info *v9ses;
v9ses = v9fs_dentry2v9ses(dentry);
/*
* set the attribute on the remote. Without even looking at the
* xattr value. We leave it to the server to validate
*/
if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
return v9fs_xattr_set(dentry, handler->name, value, size,
flags);
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
if (!inode_owner_or_capable(inode))
return -EPERM;
if (value) {
/* update the cached acl value */
acl = posix_acl_from_xattr(&init_user_ns, value, size);
if (IS_ERR(acl))
return PTR_ERR(acl);
else if (acl) {
retval = posix_acl_valid(inode->i_sb->s_user_ns, acl);
if (retval)
goto err_out;
}
} else
acl = NULL;
switch (handler->flags) {
case ACL_TYPE_ACCESS:
if (acl) {
struct iattr iattr;
struct posix_acl *old_acl = acl;
retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl);
if (retval)
goto err_out;
if (!acl) {
/*
* ACL can be represented
* by the mode bits. So don't
* update ACL.
*/
posix_acl_release(old_acl);
value = NULL;
size = 0;
}
iattr.ia_valid = ATTR_MODE;
/* FIXME should we update ctime ?
* What is the following setxattr update the
* mode ?
*/
v9fs_vfs_setattr_dotl(dentry, &iattr);
}
break;
case ACL_TYPE_DEFAULT:
if (!S_ISDIR(inode->i_mode)) {
retval = acl ? -EINVAL : 0;
goto err_out;
}
break;
default:
BUG();
}
retval = v9fs_xattr_set(dentry, handler->name, value, size, flags);
if (!retval)
set_cached_acl(inode, handler->flags, acl);
err_out:
posix_acl_release(acl);
return retval;
}
static int
xfs_xattr_acl_set(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags, int type)
{
struct inode *inode = dentry->d_inode;
struct posix_acl *acl = NULL;
int error = 0;
if (flags & XATTR_CREATE)
return -EINVAL;
if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
return value ? -EACCES : 0;
if ((current_fsuid() != inode->i_uid) && !capable(CAP_FOWNER))
return -EPERM;
if (!value)
goto set_acl;
acl = posix_acl_from_xattr(value, size);
if (!acl) {
/*
* acl_set_file(3) may request that we set default ACLs with
* zero length -- defend (gracefully) against that here.
*/
goto out;
}
if (IS_ERR(acl)) {
error = PTR_ERR(acl);
goto out;
}
error = posix_acl_valid(acl);
if (error)
goto out_release;
error = -EINVAL;
if (acl->a_count > XFS_ACL_MAX_ENTRIES)
goto out_release;
if (type == ACL_TYPE_ACCESS) {
mode_t mode = inode->i_mode;
error = posix_acl_equiv_mode(acl, &mode);
if (error <= 0) {
posix_acl_release(acl);
acl = NULL;
if (error < 0)
return error;
}
error = xfs_set_mode(inode, mode);
if (error)
goto out_release;
}
set_acl:
error = xfs_set_acl(inode, type, acl);
out_release:
posix_acl_release(acl);
out:
return error;
}
static
int ll_getxattr_common(struct inode *inode, const char *name,
void *buffer, size_t size, __u64 valid)
{
struct ll_sb_info *sbi = ll_i2sbi(inode);
struct ptlrpc_request *req = NULL;
struct mdt_body *body;
int xattr_type, rc;
void *xdata;
struct rmtacl_ctl_entry *rce = NULL;
struct ll_inode_info *lli = ll_i2info(inode);
CDEBUG(D_VFSTRACE, "VFS Op:inode=%lu/%u(%p)\n",
inode->i_ino, inode->i_generation, inode);
/* listxattr have slightly different behavior from of ext3:
* without 'user_xattr' ext3 will list all xattr names but
* filtered out "^user..*"; we list them all for simplicity.
*/
if (!name) {
xattr_type = XATTR_OTHER_T;
goto do_getxattr;
}
xattr_type = get_xattr_type(name);
rc = xattr_type_filter(sbi, xattr_type);
if (rc)
return rc;
/* b15587: ignore security.capability xattr for now */
if ((xattr_type == XATTR_SECURITY_T &&
strcmp(name, "security.capability") == 0))
return -ENODATA;
/* LU-549: Disable security.selinux when selinux is disabled */
if (xattr_type == XATTR_SECURITY_T && !selinux_is_enabled() &&
strcmp(name, "security.selinux") == 0)
return -EOPNOTSUPP;
#ifdef CONFIG_FS_POSIX_ACL
if (sbi->ll_flags & LL_SBI_RMT_CLIENT &&
(xattr_type == XATTR_ACL_ACCESS_T ||
xattr_type == XATTR_ACL_DEFAULT_T)) {
rce = rct_search(&sbi->ll_rct, current_pid());
if (rce == NULL ||
(rce->rce_ops != RMT_LSETFACL &&
rce->rce_ops != RMT_LGETFACL &&
rce->rce_ops != RMT_RSETFACL &&
rce->rce_ops != RMT_RGETFACL))
return -EOPNOTSUPP;
}
/* posix acl is under protection of LOOKUP lock. when calling to this,
* we just have path resolution to the target inode, so we have great
* chance that cached ACL is uptodate.
*/
if (xattr_type == XATTR_ACL_ACCESS_T &&
!(sbi->ll_flags & LL_SBI_RMT_CLIENT)) {
struct posix_acl *acl;
spin_lock(&lli->lli_lock);
acl = posix_acl_dup(lli->lli_posix_acl);
spin_unlock(&lli->lli_lock);
if (!acl)
return -ENODATA;
rc = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
posix_acl_release(acl);
return rc;
}
if (xattr_type == XATTR_ACL_DEFAULT_T && !S_ISDIR(inode->i_mode))
return -ENODATA;
#endif
do_getxattr:
if (sbi->ll_xattr_cache_enabled && xattr_type != XATTR_ACL_ACCESS_T) {
rc = ll_xattr_cache_get(inode, name, buffer, size, valid);
if (rc == -EAGAIN)
goto getxattr_nocache;
if (rc < 0)
goto out_xattr;
/* Add "system.posix_acl_access" to the list */
if (lli->lli_posix_acl != NULL && valid & OBD_MD_FLXATTRLS) {
if (size == 0) {
rc += sizeof(XATTR_NAME_ACL_ACCESS);
} else if (size - rc >= sizeof(XATTR_NAME_ACL_ACCESS)) {
memcpy(buffer + rc, XATTR_NAME_ACL_ACCESS,
sizeof(XATTR_NAME_ACL_ACCESS));
rc += sizeof(XATTR_NAME_ACL_ACCESS);
} else {
rc = -ERANGE;
goto out_xattr;
}
}
} else {
getxattr_nocache:
rc = md_getxattr(sbi->ll_md_exp, ll_inode2fid(inode),
valid | (rce ? rce_ops2valid(rce->rce_ops) : 0),
name, NULL, 0, size, 0, &req);
if (rc < 0)
goto out_xattr;
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
LASSERT(body);
/* only detect the xattr size */
if (size == 0) {
rc = body->eadatasize;
goto out;
}
if (size < body->eadatasize) {
CERROR("server bug: replied size %u > %u\n",
body->eadatasize, (int)size);
rc = -ERANGE;
goto out;
}
if (body->eadatasize == 0) {
rc = -ENODATA;
goto out;
}
/* do not need swab xattr data */
xdata = req_capsule_server_sized_get(&req->rq_pill, &RMF_EADATA,
body->eadatasize);
if (!xdata) {
rc = -EFAULT;
goto out;
}
memcpy(buffer, xdata, body->eadatasize);
rc = body->eadatasize;
}
#ifdef CONFIG_FS_POSIX_ACL
if (rce && rce->rce_ops == RMT_LSETFACL) {
ext_acl_xattr_header *acl;
acl = lustre_posix_acl_xattr_2ext(
(posix_acl_xattr_header *)buffer, rc);
if (IS_ERR(acl)) {
rc = PTR_ERR(acl);
goto out;
}
rc = ee_add(&sbi->ll_et, current_pid(), ll_inode2fid(inode),
xattr_type, acl);
if (unlikely(rc < 0)) {
lustre_ext_acl_xattr_free(acl);
goto out;
}
}
#endif
out_xattr:
if (rc == -EOPNOTSUPP && xattr_type == XATTR_USER_T) {
LCONSOLE_INFO(
"%s: disabling user_xattr feature because it is not supported on the server: rc = %d\n",
ll_get_fsname(inode->i_sb, NULL, 0), rc);
sbi->ll_flags &= ~LL_SBI_USER_XATTR;
}
out:
ptlrpc_req_finished(req);
return rc;
}
static struct posix_acl *jffs2_acl_from_medium(void *value, size_t size)
{
void *end = value + size;
struct jffs2_acl_header *header = value;
struct jffs2_acl_entry *entry;
struct posix_acl *acl;
uint32_t ver;
int i, count;
if (!value)
return NULL;
if (size < sizeof(struct jffs2_acl_header))
return ERR_PTR(-EINVAL);
ver = je32_to_cpu(header->a_version);
if (ver != JFFS2_ACL_VERSION) {
JFFS2_WARNING("Invalid ACL version. (=%u)\n", ver);
return ERR_PTR(-EINVAL);
}
value += sizeof(struct jffs2_acl_header);
count = jffs2_acl_count(size);
if (count < 0)
return ERR_PTR(-EINVAL);
if (count == 0)
return NULL;
acl = posix_acl_alloc(count, GFP_KERNEL);
if (!acl)
return ERR_PTR(-ENOMEM);
for (i=0; i < count; i++) {
entry = value;
if (value + sizeof(struct jffs2_acl_entry_short) > end)
goto fail;
acl->a_entries[i].e_tag = je16_to_cpu(entry->e_tag);
acl->a_entries[i].e_perm = je16_to_cpu(entry->e_perm);
switch (acl->a_entries[i].e_tag) {
case ACL_USER_OBJ:
case ACL_GROUP_OBJ:
case ACL_MASK:
case ACL_OTHER:
value += sizeof(struct jffs2_acl_entry_short);
break;
case ACL_USER:
value += sizeof(struct jffs2_acl_entry);
if (value > end)
goto fail;
acl->a_entries[i].e_uid =
make_kuid(&init_user_ns,
je32_to_cpu(entry->e_id));
break;
case ACL_GROUP:
value += sizeof(struct jffs2_acl_entry);
if (value > end)
goto fail;
acl->a_entries[i].e_gid =
make_kgid(&init_user_ns,
je32_to_cpu(entry->e_id));
break;
default:
goto fail;
}
}
if (value != end)
goto fail;
return acl;
fail:
posix_acl_release(acl);
return ERR_PTR(-EINVAL);
}
static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
const void *value, size_t size,
int flags, int type)
{
int retval;
struct posix_acl *acl;
struct v9fs_session_info *v9ses;
struct inode *inode = dentry->d_inode;
if (strcmp(name, "") != 0)
return -EINVAL;
v9ses = v9fs_dentry2v9ses(dentry);
/*
* set the attribute on the remote. Without even looking at the
* xattr value. We leave it to the server to validate
*/
if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
return v9fs_remote_set_acl(dentry, name,
value, size, flags, type);
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
if (!inode_owner_or_capable(inode))
return -EPERM;
if (value) {
/* update the cached acl value */
acl = posix_acl_from_xattr(value, size);
if (IS_ERR(acl))
return PTR_ERR(acl);
else if (acl) {
retval = posix_acl_valid(acl);
if (retval)
goto err_out;
}
} else
acl = NULL;
switch (type) {
case ACL_TYPE_ACCESS:
name = POSIX_ACL_XATTR_ACCESS;
if (acl) {
mode_t mode = inode->i_mode;
retval = posix_acl_equiv_mode(acl, &mode);
if (retval < 0)
goto err_out;
else {
struct iattr iattr;
if (retval == 0) {
/*
* ACL can be represented
* by the mode bits. So don't
* update ACL.
*/
acl = NULL;
value = NULL;
size = 0;
}
/* Updte the mode bits */
iattr.ia_mode = ((mode & S_IALLUGO) |
(inode->i_mode & ~S_IALLUGO));
iattr.ia_valid = ATTR_MODE;
/* FIXME should we update ctime ?
* What is the following setxattr update the
* mode ?
*/
v9fs_vfs_setattr_dotl(dentry, &iattr);
}
}
break;
case ACL_TYPE_DEFAULT:
name = POSIX_ACL_XATTR_DEFAULT;
if (!S_ISDIR(inode->i_mode)) {
retval = acl ? -EINVAL : 0;
goto err_out;
}
break;
default:
BUG();
}
retval = v9fs_xattr_set(dentry, name, value, size, flags);
if (!retval)
set_cached_acl(inode, type, acl);
err_out:
posix_acl_release(acl);
return retval;
}
static int gfs2_xattr_system_set(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags,
int xtype)
{
struct inode *inode = dentry->d_inode;
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct posix_acl *acl = NULL;
int error = 0, type;
if (!sdp->sd_args.ar_posix_acl)
return -EOPNOTSUPP;
type = gfs2_acl_type(name);
if (type < 0)
return type;
if (flags & XATTR_CREATE)
return -EINVAL;
if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
return value ? -EACCES : 0;
if ((current_fsuid() != inode->i_uid) && !capable(CAP_FOWNER))
return -EPERM;
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
if (!value)
goto set_acl;
acl = posix_acl_from_xattr(value, size);
if (!acl) {
/*
* acl_set_file(3) may request that we set default ACLs with
* zero length -- defend (gracefully) against that here.
*/
goto out;
}
if (IS_ERR(acl)) {
error = PTR_ERR(acl);
goto out;
}
error = posix_acl_valid(acl);
if (error)
goto out_release;
error = -EINVAL;
if (acl->a_count > GFS2_ACL_MAX_ENTRIES)
goto out_release;
if (type == ACL_TYPE_ACCESS) {
mode_t mode = inode->i_mode;
error = posix_acl_equiv_mode(acl, &mode);
if (error <= 0) {
posix_acl_release(acl);
acl = NULL;
if (error < 0)
return error;
}
error = gfs2_set_mode(inode, mode);
if (error)
goto out_release;
}
set_acl:
error = __gfs2_xattr_set(inode, name, value, size, 0, GFS2_EATYPE_SYS);
if (!error) {
if (acl)
set_cached_acl(inode, type, acl);
else
forget_cached_acl(inode, type);
}
out_release:
posix_acl_release(acl);
out:
return error;
}
/*
* Get the Access and/or Default ACL of a file.
*/
static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp,
struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
{
svc_fh *fh;
struct posix_acl *acl;
__be32 nfserr = 0;
fh = fh_copy(&resp->fh, &argp->fh);
nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
if (nfserr)
RETURN_STATUS(nfserr);
if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
RETURN_STATUS(nfserr_inval);
resp->mask = argp->mask;
if (resp->mask & (NFS_ACL|NFS_ACLCNT)) {
acl = nfsd_get_posix_acl(fh, ACL_TYPE_ACCESS);
if (IS_ERR(acl)) {
int err = PTR_ERR(acl);
if (err == -ENODATA || err == -EOPNOTSUPP)
acl = NULL;
else {
nfserr = nfserrno(err);
goto fail;
}
}
if (acl == NULL) {
/* Solaris returns the inode's minimum ACL. */
struct inode *inode = fh->fh_dentry->d_inode;
acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
}
resp->acl_access = acl;
}
if (resp->mask & (NFS_DFACL|NFS_DFACLCNT)) {
/* Check how Solaris handles requests for the Default ACL
of a non-directory! */
acl = nfsd_get_posix_acl(fh, ACL_TYPE_DEFAULT);
if (IS_ERR(acl)) {
int err = PTR_ERR(acl);
if (err == -ENODATA || err == -EOPNOTSUPP)
acl = NULL;
else {
nfserr = nfserrno(err);
goto fail;
}
}
resp->acl_default = acl;
}
/* resp->acl_{access,default} are released in nfs3svc_release_getacl. */
RETURN_STATUS(0);
fail:
posix_acl_release(resp->acl_access);
posix_acl_release(resp->acl_default);
RETURN_STATUS(nfserr);
}
struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
{
struct nfs_server *server = NFS_SERVER(inode);
struct nfs_fattr fattr;
struct page *pages[NFSACL_MAXPAGES] = { };
struct nfs3_getaclargs args = {
.fh = NFS_FH(inode),
/* The xdr layer may allocate pages here. */
.pages = pages,
};
struct nfs3_getaclres res = {
.fattr = &fattr,
};
struct posix_acl *acl;
int status, count;
if (!nfs_server_capable(inode, NFS_CAP_ACLS))
return ERR_PTR(-EOPNOTSUPP);
status = nfs_revalidate_inode(server, inode);
if (status < 0)
return ERR_PTR(status);
acl = nfs3_get_cached_acl(inode, type);
if (acl != ERR_PTR(-EAGAIN))
return acl;
acl = NULL;
/*
* Only get the access acl when explicitly requested: We don't
* need it for access decisions, and only some applications use
* it. Applications which request the access acl first are not
* penalized from this optimization.
*/
if (type == ACL_TYPE_ACCESS)
args.mask |= NFS_ACLCNT|NFS_ACL;
if (S_ISDIR(inode->i_mode))
args.mask |= NFS_DFACLCNT|NFS_DFACL;
if (args.mask == 0)
return NULL;
dprintk("NFS call getacl\n");
status = rpc_call(server->client_acl, ACLPROC3_GETACL,
&args, &res, 0);
dprintk("NFS reply getacl: %d\n", status);
/* pages may have been allocated at the xdr layer. */
for (count = 0; count < NFSACL_MAXPAGES && args.pages[count]; count++)
__free_page(args.pages[count]);
switch (status) {
case 0:
status = nfs_refresh_inode(inode, &fattr);
break;
case -EPFNOSUPPORT:
case -EPROTONOSUPPORT:
dprintk("NFS_V3_ACL extension not supported; disabling\n");
server->caps &= ~NFS_CAP_ACLS;
case -ENOTSUPP:
status = -EOPNOTSUPP;
default:
goto getout;
}
if ((args.mask & res.mask) != args.mask) {
status = -EIO;
goto getout;
}
if (res.acl_access != NULL) {
if (posix_acl_equiv_mode(res.acl_access, NULL) == 0) {
posix_acl_release(res.acl_access);
res.acl_access = NULL;
}
}
nfs3_cache_acls(inode, res.acl_access, res.acl_default);
switch(type) {
case ACL_TYPE_ACCESS:
acl = res.acl_access;
res.acl_access = NULL;
break;
case ACL_TYPE_DEFAULT:
acl = res.acl_default;
res.acl_default = NULL;
}
getout:
posix_acl_release(res.acl_access);
posix_acl_release(res.acl_default);
if (status != 0) {
posix_acl_release(acl);
acl = ERR_PTR(status);
}
return acl;
}