Merge branch 'work.mqueue' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull mqueue/bpf vfs cleanups from Al Viro: "mqueue and bpf go through rather painful and similar contortions to create objects in their dentry trees. Provide a primitive for doing that without abusing ->mknod(), switch bpf and mqueue to it. Another mqueue-related thing that has ended up in that branch is on-demand creation of internal mount (based upon the work of Giuseppe Scrivano)" * 'work.mqueue' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: mqueue: switch to on-demand creation of internal mount tidy do_mq_open() up a bit mqueue: clean prepare_open() up do_mq_open(): move all work prior to dentry_open() into a helper mqueue: fold mq_attr_ok() into mqueue_get_inode() move dentry_open() calls up into do_mq_open() mqueue: switch to vfs_mkobj(), quit abusing ->d_fsdata bpf_obj_do_pin(): switch to vfs_mkobj(), quit abusing ->mknod() new primitive: vfs_mkobj()
This commit is contained in:
Linus Torvalds
commit
8b0fdf631c
21
fs/namei.c
21
fs/namei.c
|
|
@ -2895,6 +2895,27 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
|
|||
}
|
||||
EXPORT_SYMBOL(vfs_create);
|
||||
|
||||
int vfs_mkobj(struct dentry *dentry, umode_t mode,
|
||||
int (*f)(struct dentry *, umode_t, void *),
|
||||
void *arg)
|
||||
{
|
||||
struct inode *dir = dentry->d_parent->d_inode;
|
||||
int error = may_create(dir, dentry);
|
||||
if (error)
|
||||
return error;
|
||||
|
||||
mode &= S_IALLUGO;
|
||||
mode |= S_IFREG;
|
||||
error = security_inode_create(dir, dentry, mode);
|
||||
if (error)
|
||||
return error;
|
||||
error = f(dentry, mode, arg);
|
||||
if (!error)
|
||||
fsnotify_create(dir, dentry);
|
||||
return error;
|
||||
}
|
||||
EXPORT_SYMBOL(vfs_mkobj);
|
||||
|
||||
bool may_open_dev(const struct path *path)
|
||||
{
|
||||
return !(path->mnt->mnt_flags & MNT_NODEV) &&
|
||||
|
|
|
|||
|
|
@ -1608,6 +1608,10 @@ extern int vfs_whiteout(struct inode *, struct dentry *);
|
|||
extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
|
||||
int open_flag);
|
||||
|
||||
int vfs_mkobj(struct dentry *, umode_t,
|
||||
int (*f)(struct dentry *, umode_t, void *),
|
||||
void *);
|
||||
|
||||
/*
|
||||
* VFS file helper functions.
|
||||
*/
|
||||
|
|
|
|||
237
ipc/mqueue.c
237
ipc/mqueue.c
|
|
@ -270,13 +270,30 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
|
|||
* that means the min(mq_maxmsg, max_priorities) * struct
|
||||
* posix_msg_tree_node.
|
||||
*/
|
||||
|
||||
ret = -EINVAL;
|
||||
if (info->attr.mq_maxmsg <= 0 || info->attr.mq_msgsize <= 0)
|
||||
goto out_inode;
|
||||
if (capable(CAP_SYS_RESOURCE)) {
|
||||
if (info->attr.mq_maxmsg > HARD_MSGMAX ||
|
||||
info->attr.mq_msgsize > HARD_MSGSIZEMAX)
|
||||
goto out_inode;
|
||||
} else {
|
||||
if (info->attr.mq_maxmsg > ipc_ns->mq_msg_max ||
|
||||
info->attr.mq_msgsize > ipc_ns->mq_msgsize_max)
|
||||
goto out_inode;
|
||||
}
|
||||
ret = -EOVERFLOW;
|
||||
/* check for overflow */
|
||||
if (info->attr.mq_msgsize > ULONG_MAX/info->attr.mq_maxmsg)
|
||||
goto out_inode;
|
||||
mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
|
||||
min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
|
||||
sizeof(struct posix_msg_tree_node);
|
||||
|
||||
mq_bytes = mq_treesize + (info->attr.mq_maxmsg *
|
||||
info->attr.mq_msgsize);
|
||||
|
||||
mq_bytes = info->attr.mq_maxmsg * info->attr.mq_msgsize;
|
||||
if (mq_bytes + mq_treesize < mq_bytes)
|
||||
goto out_inode;
|
||||
mq_bytes += mq_treesize;
|
||||
spin_lock(&mq_lock);
|
||||
if (u->mq_bytes + mq_bytes < u->mq_bytes ||
|
||||
u->mq_bytes + mq_bytes > rlimit(RLIMIT_MSGQUEUE)) {
|
||||
|
|
@ -308,8 +325,9 @@ err:
|
|||
static int mqueue_fill_super(struct super_block *sb, void *data, int silent)
|
||||
{
|
||||
struct inode *inode;
|
||||
struct ipc_namespace *ns = sb->s_fs_info;
|
||||
struct ipc_namespace *ns = data;
|
||||
|
||||
sb->s_fs_info = ns;
|
||||
sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
|
||||
sb->s_blocksize = PAGE_SIZE;
|
||||
sb->s_blocksize_bits = PAGE_SHIFT;
|
||||
|
|
@ -326,18 +344,44 @@ static int mqueue_fill_super(struct super_block *sb, void *data, int silent)
|
|||
return 0;
|
||||
}
|
||||
|
||||
static struct file_system_type mqueue_fs_type;
|
||||
/*
|
||||
* Return value is pinned only by reference in ->mq_mnt; it will
|
||||
* live until ipcns dies. Caller does not need to drop it.
|
||||
*/
|
||||
static struct vfsmount *mq_internal_mount(void)
|
||||
{
|
||||
struct ipc_namespace *ns = current->nsproxy->ipc_ns;
|
||||
struct vfsmount *m = ns->mq_mnt;
|
||||
if (m)
|
||||
return m;
|
||||
m = kern_mount_data(&mqueue_fs_type, ns);
|
||||
spin_lock(&mq_lock);
|
||||
if (unlikely(ns->mq_mnt)) {
|
||||
spin_unlock(&mq_lock);
|
||||
if (!IS_ERR(m))
|
||||
kern_unmount(m);
|
||||
return ns->mq_mnt;
|
||||
}
|
||||
if (!IS_ERR(m))
|
||||
ns->mq_mnt = m;
|
||||
spin_unlock(&mq_lock);
|
||||
return m;
|
||||
}
|
||||
|
||||
static struct dentry *mqueue_mount(struct file_system_type *fs_type,
|
||||
int flags, const char *dev_name,
|
||||
void *data)
|
||||
{
|
||||
struct ipc_namespace *ns;
|
||||
if (flags & SB_KERNMOUNT) {
|
||||
ns = data;
|
||||
data = NULL;
|
||||
} else {
|
||||
ns = current->nsproxy->ipc_ns;
|
||||
}
|
||||
return mount_ns(fs_type, flags, data, ns, ns->user_ns, mqueue_fill_super);
|
||||
struct vfsmount *m;
|
||||
if (flags & SB_KERNMOUNT)
|
||||
return mount_nodev(fs_type, flags, data, mqueue_fill_super);
|
||||
m = mq_internal_mount();
|
||||
if (IS_ERR(m))
|
||||
return ERR_CAST(m);
|
||||
atomic_inc(&m->mnt_sb->s_active);
|
||||
down_write(&m->mnt_sb->s_umount);
|
||||
return dget(m->mnt_root);
|
||||
}
|
||||
|
||||
static void init_once(void *foo)
|
||||
|
|
@ -416,11 +460,11 @@ static void mqueue_evict_inode(struct inode *inode)
|
|||
put_ipc_ns(ipc_ns);
|
||||
}
|
||||
|
||||
static int mqueue_create(struct inode *dir, struct dentry *dentry,
|
||||
umode_t mode, bool excl)
|
||||
static int mqueue_create_attr(struct dentry *dentry, umode_t mode, void *arg)
|
||||
{
|
||||
struct inode *dir = dentry->d_parent->d_inode;
|
||||
struct inode *inode;
|
||||
struct mq_attr *attr = dentry->d_fsdata;
|
||||
struct mq_attr *attr = arg;
|
||||
int error;
|
||||
struct ipc_namespace *ipc_ns;
|
||||
|
||||
|
|
@ -461,6 +505,12 @@ out_unlock:
|
|||
return error;
|
||||
}
|
||||
|
||||
static int mqueue_create(struct inode *dir, struct dentry *dentry,
|
||||
umode_t mode, bool excl)
|
||||
{
|
||||
return mqueue_create_attr(dentry, mode, NULL);
|
||||
}
|
||||
|
||||
static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
|
||||
{
|
||||
struct inode *inode = d_inode(dentry);
|
||||
|
|
@ -691,96 +741,46 @@ static void remove_notification(struct mqueue_inode_info *info)
|
|||
info->notify_user_ns = NULL;
|
||||
}
|
||||
|
||||
static int mq_attr_ok(struct ipc_namespace *ipc_ns, struct mq_attr *attr)
|
||||
{
|
||||
int mq_treesize;
|
||||
unsigned long total_size;
|
||||
|
||||
if (attr->mq_maxmsg <= 0 || attr->mq_msgsize <= 0)
|
||||
return -EINVAL;
|
||||
if (capable(CAP_SYS_RESOURCE)) {
|
||||
if (attr->mq_maxmsg > HARD_MSGMAX ||
|
||||
attr->mq_msgsize > HARD_MSGSIZEMAX)
|
||||
return -EINVAL;
|
||||
} else {
|
||||
if (attr->mq_maxmsg > ipc_ns->mq_msg_max ||
|
||||
attr->mq_msgsize > ipc_ns->mq_msgsize_max)
|
||||
return -EINVAL;
|
||||
}
|
||||
/* check for overflow */
|
||||
if (attr->mq_msgsize > ULONG_MAX/attr->mq_maxmsg)
|
||||
return -EOVERFLOW;
|
||||
mq_treesize = attr->mq_maxmsg * sizeof(struct msg_msg) +
|
||||
min_t(unsigned int, attr->mq_maxmsg, MQ_PRIO_MAX) *
|
||||
sizeof(struct posix_msg_tree_node);
|
||||
total_size = attr->mq_maxmsg * attr->mq_msgsize;
|
||||
if (total_size + mq_treesize < total_size)
|
||||
return -EOVERFLOW;
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Invoked when creating a new queue via sys_mq_open
|
||||
*/
|
||||
static struct file *do_create(struct ipc_namespace *ipc_ns, struct inode *dir,
|
||||
struct path *path, int oflag, umode_t mode,
|
||||
static int prepare_open(struct dentry *dentry, int oflag, int ro,
|
||||
umode_t mode, struct filename *name,
|
||||
struct mq_attr *attr)
|
||||
{
|
||||
const struct cred *cred = current_cred();
|
||||
int ret;
|
||||
|
||||
if (attr) {
|
||||
ret = mq_attr_ok(ipc_ns, attr);
|
||||
if (ret)
|
||||
return ERR_PTR(ret);
|
||||
/* store for use during create */
|
||||
path->dentry->d_fsdata = attr;
|
||||
} else {
|
||||
struct mq_attr def_attr;
|
||||
|
||||
def_attr.mq_maxmsg = min(ipc_ns->mq_msg_max,
|
||||
ipc_ns->mq_msg_default);
|
||||
def_attr.mq_msgsize = min(ipc_ns->mq_msgsize_max,
|
||||
ipc_ns->mq_msgsize_default);
|
||||
ret = mq_attr_ok(ipc_ns, &def_attr);
|
||||
if (ret)
|
||||
return ERR_PTR(ret);
|
||||
}
|
||||
|
||||
mode &= ~current_umask();
|
||||
ret = vfs_create(dir, path->dentry, mode, true);
|
||||
path->dentry->d_fsdata = NULL;
|
||||
if (ret)
|
||||
return ERR_PTR(ret);
|
||||
return dentry_open(path, oflag, cred);
|
||||
}
|
||||
|
||||
/* Opens existing queue */
|
||||
static struct file *do_open(struct path *path, int oflag)
|
||||
{
|
||||
static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
|
||||
MAY_READ | MAY_WRITE };
|
||||
int acc;
|
||||
|
||||
if (d_really_is_negative(dentry)) {
|
||||
if (!(oflag & O_CREAT))
|
||||
return -ENOENT;
|
||||
if (ro)
|
||||
return ro;
|
||||
audit_inode_parent_hidden(name, dentry->d_parent);
|
||||
return vfs_mkobj(dentry, mode & ~current_umask(),
|
||||
mqueue_create_attr, attr);
|
||||
}
|
||||
/* it already existed */
|
||||
audit_inode(name, dentry, 0);
|
||||
if ((oflag & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
|
||||
return -EEXIST;
|
||||
if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
|
||||
return ERR_PTR(-EINVAL);
|
||||
return -EINVAL;
|
||||
acc = oflag2acc[oflag & O_ACCMODE];
|
||||
if (inode_permission(d_inode(path->dentry), acc))
|
||||
return ERR_PTR(-EACCES);
|
||||
return dentry_open(path, oflag, current_cred());
|
||||
return inode_permission(d_inode(dentry), acc);
|
||||
}
|
||||
|
||||
static int do_mq_open(const char __user *u_name, int oflag, umode_t mode,
|
||||
struct mq_attr *attr)
|
||||
{
|
||||
struct path path;
|
||||
struct file *filp;
|
||||
struct vfsmount *mnt = mq_internal_mount();
|
||||
struct dentry *root;
|
||||
struct filename *name;
|
||||
struct path path;
|
||||
int fd, error;
|
||||
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
|
||||
struct vfsmount *mnt = ipc_ns->mq_mnt;
|
||||
struct dentry *root = mnt->mnt_root;
|
||||
int ro;
|
||||
|
||||
if (IS_ERR(mnt))
|
||||
return PTR_ERR(mnt);
|
||||
|
||||
audit_mq_open(oflag, mode, attr);
|
||||
|
||||
if (IS_ERR(name = getname(u_name)))
|
||||
|
|
@ -791,7 +791,7 @@ static int do_mq_open(const char __user *u_name, int oflag, umode_t mode,
|
|||
goto out_putname;
|
||||
|
||||
ro = mnt_want_write(mnt); /* we'll drop it in any case */
|
||||
error = 0;
|
||||
root = mnt->mnt_root;
|
||||
inode_lock(d_inode(root));
|
||||
path.dentry = lookup_one_len(name->name, root, strlen(name->name));
|
||||
if (IS_ERR(path.dentry)) {
|
||||
|
|
@ -799,38 +799,14 @@ static int do_mq_open(const char __user *u_name, int oflag, umode_t mode,
|
|||
goto out_putfd;
|
||||
}
|
||||
path.mnt = mntget(mnt);
|
||||
|
||||
if (oflag & O_CREAT) {
|
||||
if (d_really_is_positive(path.dentry)) { /* entry already exists */
|
||||
audit_inode(name, path.dentry, 0);
|
||||
if (oflag & O_EXCL) {
|
||||
error = -EEXIST;
|
||||
goto out;
|
||||
}
|
||||
filp = do_open(&path, oflag);
|
||||
} else {
|
||||
if (ro) {
|
||||
error = ro;
|
||||
goto out;
|
||||
}
|
||||
audit_inode_parent_hidden(name, root);
|
||||
filp = do_create(ipc_ns, d_inode(root), &path,
|
||||
oflag, mode, attr);
|
||||
}
|
||||
} else {
|
||||
if (d_really_is_negative(path.dentry)) {
|
||||
error = -ENOENT;
|
||||
goto out;
|
||||
}
|
||||
audit_inode(name, path.dentry, 0);
|
||||
filp = do_open(&path, oflag);
|
||||
}
|
||||
|
||||
if (!IS_ERR(filp))
|
||||
fd_install(fd, filp);
|
||||
error = prepare_open(path.dentry, oflag, ro, mode, name, attr);
|
||||
if (!error) {
|
||||
struct file *file = dentry_open(&path, oflag, current_cred());
|
||||
if (!IS_ERR(file))
|
||||
fd_install(fd, file);
|
||||
else
|
||||
error = PTR_ERR(filp);
|
||||
out:
|
||||
error = PTR_ERR(file);
|
||||
}
|
||||
path_put(&path);
|
||||
out_putfd:
|
||||
if (error) {
|
||||
|
|
@ -864,6 +840,9 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
|
|||
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
|
||||
struct vfsmount *mnt = ipc_ns->mq_mnt;
|
||||
|
||||
if (!mnt)
|
||||
return -ENOENT;
|
||||
|
||||
name = getname(u_name);
|
||||
if (IS_ERR(name))
|
||||
return PTR_ERR(name);
|
||||
|
|
@ -1590,28 +1569,26 @@ int mq_init_ns(struct ipc_namespace *ns)
|
|||
ns->mq_msgsize_max = DFLT_MSGSIZEMAX;
|
||||
ns->mq_msg_default = DFLT_MSG;
|
||||
ns->mq_msgsize_default = DFLT_MSGSIZE;
|
||||
|
||||
ns->mq_mnt = kern_mount_data(&mqueue_fs_type, ns);
|
||||
if (IS_ERR(ns->mq_mnt)) {
|
||||
int err = PTR_ERR(ns->mq_mnt);
|
||||
ns->mq_mnt = NULL;
|
||||
return err;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
void mq_clear_sbinfo(struct ipc_namespace *ns)
|
||||
{
|
||||
if (ns->mq_mnt)
|
||||
ns->mq_mnt->mnt_sb->s_fs_info = NULL;
|
||||
}
|
||||
|
||||
void mq_put_mnt(struct ipc_namespace *ns)
|
||||
{
|
||||
if (ns->mq_mnt)
|
||||
kern_unmount(ns->mq_mnt);
|
||||
}
|
||||
|
||||
static int __init init_mqueue_fs(void)
|
||||
{
|
||||
struct vfsmount *m;
|
||||
int error;
|
||||
|
||||
mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache",
|
||||
|
|
@ -1633,6 +1610,10 @@ static int __init init_mqueue_fs(void)
|
|||
if (error)
|
||||
goto out_filesystem;
|
||||
|
||||
m = kern_mount_data(&mqueue_fs_type, &init_ipc_ns);
|
||||
if (IS_ERR(m))
|
||||
goto out_filesystem;
|
||||
init_ipc_ns.mq_mnt = m;
|
||||
return 0;
|
||||
|
||||
out_filesystem:
|
||||
|
|
|
|||
|
|
@ -150,39 +150,29 @@ static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
|
|||
return 0;
|
||||
}
|
||||
|
||||
static int bpf_mkobj_ops(struct inode *dir, struct dentry *dentry,
|
||||
umode_t mode, const struct inode_operations *iops)
|
||||
static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
|
||||
const struct inode_operations *iops)
|
||||
{
|
||||
struct inode *inode;
|
||||
|
||||
inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFREG);
|
||||
struct inode *dir = dentry->d_parent->d_inode;
|
||||
struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode);
|
||||
if (IS_ERR(inode))
|
||||
return PTR_ERR(inode);
|
||||
|
||||
inode->i_op = iops;
|
||||
inode->i_private = dentry->d_fsdata;
|
||||
inode->i_private = raw;
|
||||
|
||||
bpf_dentry_finalize(dentry, inode, dir);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int bpf_mkobj(struct inode *dir, struct dentry *dentry, umode_t mode,
|
||||
dev_t devt)
|
||||
static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg)
|
||||
{
|
||||
enum bpf_type type = MINOR(devt);
|
||||
|
||||
if (MAJOR(devt) != UNNAMED_MAJOR || !S_ISREG(mode) ||
|
||||
dentry->d_fsdata == NULL)
|
||||
return -EPERM;
|
||||
|
||||
switch (type) {
|
||||
case BPF_TYPE_PROG:
|
||||
return bpf_mkobj_ops(dir, dentry, mode, &bpf_prog_iops);
|
||||
case BPF_TYPE_MAP:
|
||||
return bpf_mkobj_ops(dir, dentry, mode, &bpf_map_iops);
|
||||
default:
|
||||
return -EPERM;
|
||||
return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops);
|
||||
}
|
||||
|
||||
static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
|
||||
{
|
||||
return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops);
|
||||
}
|
||||
|
||||
static struct dentry *
|
||||
|
|
@ -218,7 +208,6 @@ static int bpf_symlink(struct inode *dir, struct dentry *dentry,
|
|||
|
||||
static const struct inode_operations bpf_dir_iops = {
|
||||
.lookup = bpf_lookup,
|
||||
.mknod = bpf_mkobj,
|
||||
.mkdir = bpf_mkdir,
|
||||
.symlink = bpf_symlink,
|
||||
.rmdir = simple_rmdir,
|
||||
|
|
@ -234,7 +223,6 @@ static int bpf_obj_do_pin(const struct filename *pathname, void *raw,
|
|||
struct inode *dir;
|
||||
struct path path;
|
||||
umode_t mode;
|
||||
dev_t devt;
|
||||
int ret;
|
||||
|
||||
dentry = kern_path_create(AT_FDCWD, pathname->name, &path, 0);
|
||||
|
|
@ -242,9 +230,8 @@ static int bpf_obj_do_pin(const struct filename *pathname, void *raw,
|
|||
return PTR_ERR(dentry);
|
||||
|
||||
mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask());
|
||||
devt = MKDEV(UNNAMED_MAJOR, type);
|
||||
|
||||
ret = security_path_mknod(&path, dentry, mode, devt);
|
||||
ret = security_path_mknod(&path, dentry, mode, 0);
|
||||
if (ret)
|
||||
goto out;
|
||||
|
||||
|
|
@ -254,9 +241,16 @@ static int bpf_obj_do_pin(const struct filename *pathname, void *raw,
|
|||
goto out;
|
||||
}
|
||||
|
||||
dentry->d_fsdata = raw;
|
||||
ret = vfs_mknod(dir, dentry, mode, devt);
|
||||
dentry->d_fsdata = NULL;
|
||||
switch (type) {
|
||||
case BPF_TYPE_PROG:
|
||||
ret = vfs_mkobj(dentry, mode, bpf_mkprog, raw);
|
||||
break;
|
||||
case BPF_TYPE_MAP:
|
||||
ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw);
|
||||
break;
|
||||
default:
|
||||
ret = -EPERM;
|
||||
}
|
||||
out:
|
||||
done_path_create(&path, dentry);
|
||||
return ret;
|
||||
|
|
|
|||
Loading…
Reference in New Issue