#include "internal.h"
#include "mount.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/namei.h>
+
/* [Feb-1997 T. Schoebel-Theuer]
* Fundamental changes in the pathname lookup mechanisms (namei)
* were necessary because of omirr. The reason is that omirr needs
* flag in inode->i_opflags, that says "this has not special
* permission function, use the fast case".
*/
-static inline int do_inode_permission(struct inode *inode, int mask)
+static inline int do_inode_permission(struct vfsmount *mnt, struct inode *inode, int mask)
{
if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
+ if (likely(mnt && inode->i_op->permission2))
+ return inode->i_op->permission2(mnt, inode, mask);
if (likely(inode->i_op->permission))
return inode->i_op->permission(inode, mask);
* This does not check for a read-only file system. You probably want
* inode_permission().
*/
-int __inode_permission(struct inode *inode, int mask)
+int __inode_permission2(struct vfsmount *mnt, struct inode *inode, int mask)
{
int retval;
return -EACCES;
}
- retval = do_inode_permission(inode, mask);
+ retval = do_inode_permission(mnt, inode, mask);
if (retval)
return retval;
if (retval)
return retval;
- return security_inode_permission(inode, mask);
+ retval = security_inode_permission(inode, mask);
+ return retval;
+}
+EXPORT_SYMBOL(__inode_permission2);
+
+int __inode_permission(struct inode *inode, int mask)
+{
+ return __inode_permission2(NULL, inode, mask);
}
EXPORT_SYMBOL(__inode_permission);
*
* When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
*/
-int inode_permission(struct inode *inode, int mask)
+int inode_permission2(struct vfsmount *mnt, struct inode *inode, int mask)
{
int retval;
retval = sb_permission(inode->i_sb, inode, mask);
if (retval)
return retval;
- return __inode_permission(inode, mask);
+ return __inode_permission2(mnt, inode, mask);
+}
+EXPORT_SYMBOL(inode_permission2);
+
+int inode_permission(struct inode *inode, int mask)
+{
+ return inode_permission2(NULL, inode, mask);
}
EXPORT_SYMBOL(inode_permission);
return dentry->d_op->d_revalidate(dentry, flags);
}
+#define INIT_PATH_SIZE 64
+
+static void success_walk_trace(struct nameidata *nd)
+{
+ struct path *pt = &nd->path;
+ struct inode *i = nd->inode;
+ char buf[INIT_PATH_SIZE], *try_buf;
+ int cur_path_size;
+ char *p;
+
+ /* When eBPF/ tracepoint is disabled, keep overhead low. */
+ if (!trace_inodepath_enabled())
+ return;
+
+ /* First try stack allocated buffer. */
+ try_buf = buf;
+ cur_path_size = INIT_PATH_SIZE;
+
+ while (cur_path_size <= PATH_MAX) {
+ /* Free previous heap allocation if we are now trying
+ * a second or later heap allocation.
+ */
+ if (try_buf != buf)
+ kfree(try_buf);
+
+ /* All but the first alloc are on the heap. */
+ if (cur_path_size != INIT_PATH_SIZE) {
+ try_buf = kmalloc(cur_path_size, GFP_KERNEL);
+ if (!try_buf) {
+ try_buf = buf;
+ sprintf(try_buf, "error:buf_alloc_failed");
+ break;
+ }
+ }
+
+ p = d_path(pt, try_buf, cur_path_size);
+
+ if (!IS_ERR(p)) {
+ char *end = mangle_path(try_buf, p, "\n");
+
+ if (end) {
+ try_buf[end - try_buf] = 0;
+ break;
+ } else {
+ /* On mangle errors, double path size
+ * till PATH_MAX.
+ */
+ cur_path_size = cur_path_size << 1;
+ continue;
+ }
+ }
+
+ if (PTR_ERR(p) == -ENAMETOOLONG) {
+ /* If d_path complains that name is too long,
+ * then double path size till PATH_MAX.
+ */
+ cur_path_size = cur_path_size << 1;
+ continue;
+ }
+
+ sprintf(try_buf, "error:d_path_failed_%lu",
+ -1 * PTR_ERR(p));
+ break;
+ }
+
+ if (cur_path_size > PATH_MAX)
+ sprintf(try_buf, "error:d_path_name_too_long");
+
+ trace_inodepath(i, try_buf);
+
+ if (try_buf != buf)
+ kfree(try_buf);
+ return;
+}
+
/**
* complete_walk - successful completion of path walk
* @nd: pointer nameidata
return -ECHILD;
}
- if (likely(!(nd->flags & LOOKUP_JUMPED)))
+ if (likely(!(nd->flags & LOOKUP_JUMPED))) {
+ success_walk_trace(nd);
return 0;
+ }
- if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE)))
+ if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE))) {
+ success_walk_trace(nd);
return 0;
+ }
status = dentry->d_op->d_weak_revalidate(dentry, nd->flags);
- if (status > 0)
+ if (status > 0) {
+ success_walk_trace(nd);
return 0;
+ }
if (!status)
status = -ESTALE;
static inline int may_lookup(struct nameidata *nd)
{
if (nd->flags & LOOKUP_RCU) {
- int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
+ int err = inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
if (err != -ECHILD)
return err;
if (unlazy_walk(nd, NULL, 0))
return -ECHILD;
}
- return inode_permission(nd->inode, MAY_EXEC);
+ return inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC);
}
static inline int handle_dots(struct nameidata *nd, int type)
nd->depth = 0;
if (flags & LOOKUP_ROOT) {
struct dentry *root = nd->root.dentry;
+ struct vfsmount *mnt = nd->root.mnt;
struct inode *inode = root->d_inode;
if (*s) {
if (!d_can_lookup(root))
return ERR_PTR(-ENOTDIR);
- retval = inode_permission(inode, MAY_EXEC);
+ retval = inode_permission2(mnt, inode, MAY_EXEC);
if (retval)
return ERR_PTR(retval);
}
if (!err && nd->flags & LOOKUP_DIRECTORY)
if (!d_can_lookup(nd->path.dentry))
err = -ENOTDIR;
+
if (!err) {
*path = nd->path;
nd->path.mnt = NULL;
/**
* lookup_one_len - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
+ * @mnt: mount we are looking up on
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code.
*/
-struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
+struct dentry *lookup_one_len2(const char *name, struct vfsmount *mnt, struct dentry *base, int len)
{
struct qstr this;
unsigned int c;
return ERR_PTR(err);
}
- err = inode_permission(base->d_inode, MAY_EXEC);
+ err = inode_permission2(mnt, base->d_inode, MAY_EXEC);
if (err)
return ERR_PTR(err);
return __lookup_hash(&this, base, 0);
}
+EXPORT_SYMBOL(lookup_one_len2);
+
+struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
+{
+ return lookup_one_len2(name, NULL, base, len);
+}
EXPORT_SYMBOL(lookup_one_len);
int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
* 10. We don't allow removal of NFS sillyrenamed files; it's handled by
* nfs_async_unlink().
*/
-static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
+static int may_delete(struct vfsmount *mnt, struct inode *dir, struct dentry *victim, bool isdir)
{
struct inode *inode = d_backing_inode(victim);
int error;
BUG_ON(victim->d_parent->d_inode != dir);
audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
- error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ error = inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC);
if (error)
return error;
if (IS_APPEND(dir))
* 3. We should have write and exec permissions on dir
* 4. We can't do it if dir is immutable (done in permission())
*/
-static inline int may_create(struct inode *dir, struct dentry *child)
+static inline int may_create(struct vfsmount *mnt, struct inode *dir, struct dentry *child)
{
audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
if (child->d_inode)
return -EEXIST;
if (IS_DEADDIR(dir))
return -ENOENT;
- return inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ return inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC);
}
/*
}
EXPORT_SYMBOL(unlock_rename);
-int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool want_excl)
+int vfs_create2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool want_excl)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt, dir, dentry);
if (error)
return error;
if (error)
return error;
error = dir->i_op->create(dir, dentry, mode, want_excl);
+ if (error)
+ return error;
+ error = security_inode_post_create(dir, dentry, mode);
+ if (error)
+ return error;
if (!error)
fsnotify_create(dir, dentry);
+
return error;
}
+EXPORT_SYMBOL(vfs_create2);
+
+int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+ bool want_excl)
+{
+ return vfs_create2(NULL, dir, dentry, mode, want_excl);
+}
EXPORT_SYMBOL(vfs_create);
static int may_open(struct path *path, int acc_mode, int flag)
{
struct dentry *dentry = path->dentry;
+ struct vfsmount *mnt = path->mnt;
struct inode *inode = dentry->d_inode;
int error;
break;
}
- error = inode_permission(inode, acc_mode);
+ error = inode_permission2(mnt, inode, acc_mode);
if (error)
return error;
if (!error)
error = security_path_truncate(path);
if (!error) {
- error = do_truncate(path->dentry, 0,
+ error = do_truncate2(path->mnt, path->dentry, 0,
ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
filp);
}
if (error)
return error;
- error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
+ error = inode_permission2(dir->mnt, dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
if (error)
return error;
bool got_write, int *opened)
{
struct dentry *dir = nd->path.dentry;
+ struct vfsmount *mnt = nd->path.mnt;
struct inode *dir_inode = dir->d_inode;
struct dentry *dentry;
int error;
error = security_path_mknod(&nd->path, dentry, mode, 0);
if (error)
goto out_dput;
- error = vfs_create(dir->d_inode, dentry, mode,
+ error = vfs_create2(mnt, dir->d_inode, dentry, mode,
nd->flags & LOOKUP_EXCL);
if (error)
goto out_dput;
goto out;
dir = path.dentry->d_inode;
/* we want directory to be writable */
- error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ error = inode_permission2(path.mnt, dir, MAY_WRITE | MAY_EXEC);
if (error)
goto out2;
if (!dir->i_op->tmpfile) {
error = -ESTALE;
}
file = ERR_PTR(error);
+ } else {
+ global_filetable_add(file);
}
return file;
}
}
EXPORT_SYMBOL(user_path_create);
-int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+int vfs_mknod2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt, dir, dentry);
if (error)
return error;
return error;
error = dir->i_op->mknod(dir, dentry, mode, dev);
+ if (error)
+ return error;
+
+ error = security_inode_post_create(dir, dentry, mode);
+ if (error)
+ return error;
+
if (!error)
fsnotify_create(dir, dentry);
+
return error;
}
+EXPORT_SYMBOL(vfs_mknod2);
+
+int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+{
+ return vfs_mknod2(NULL, dir, dentry, mode, dev);
+}
EXPORT_SYMBOL(vfs_mknod);
static int may_mknod(umode_t mode)
goto out;
switch (mode & S_IFMT) {
case 0: case S_IFREG:
- error = vfs_create(path.dentry->d_inode,dentry,mode,true);
+ error = vfs_create2(path.mnt, path.dentry->d_inode,dentry,mode,true);
break;
case S_IFCHR: case S_IFBLK:
- error = vfs_mknod(path.dentry->d_inode,dentry,mode,
+ error = vfs_mknod2(path.mnt, path.dentry->d_inode,dentry,mode,
new_decode_dev(dev));
break;
case S_IFIFO: case S_IFSOCK:
return sys_mknodat(AT_FDCWD, filename, mode, dev);
}
-int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+int vfs_mkdir2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, umode_t mode)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt, dir, dentry);
unsigned max_links = dir->i_sb->s_max_links;
if (error)
fsnotify_mkdir(dir, dentry);
return error;
}
+EXPORT_SYMBOL(vfs_mkdir2);
+
+int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ return vfs_mkdir2(NULL, dir, dentry, mode);
+}
EXPORT_SYMBOL(vfs_mkdir);
SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
mode &= ~current_umask();
error = security_path_mkdir(&path, dentry, mode);
if (!error)
- error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
+ error = vfs_mkdir2(path.mnt, path.dentry->d_inode, dentry, mode);
done_path_create(&path, dentry);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
}
EXPORT_SYMBOL(dentry_unhash);
-int vfs_rmdir(struct inode *dir, struct dentry *dentry)
+int vfs_rmdir2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry)
{
- int error = may_delete(dir, dentry, 1);
+ int error = may_delete(mnt, dir, dentry, 1);
if (error)
return error;
d_delete(dentry);
return error;
}
+EXPORT_SYMBOL(vfs_rmdir2);
+
+int vfs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ return vfs_rmdir2(NULL, dir, dentry);
+}
EXPORT_SYMBOL(vfs_rmdir);
static long do_rmdir(int dfd, const char __user *pathname)
error = security_path_rmdir(&path, dentry);
if (error)
goto exit3;
- error = vfs_rmdir(path.dentry->d_inode, dentry);
+ error = vfs_rmdir2(path.mnt, path.dentry->d_inode, dentry);
exit3:
dput(dentry);
exit2:
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported.
*/
-int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
+int vfs_unlink2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
{
struct inode *target = dentry->d_inode;
- int error = may_delete(dir, dentry, 0);
+ int error = may_delete(mnt, dir, dentry, 0);
if (error)
return error;
return error;
}
+EXPORT_SYMBOL(vfs_unlink2);
+
+int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
+{
+ return vfs_unlink2(NULL, dir, dentry, delegated_inode);
+}
EXPORT_SYMBOL(vfs_unlink);
/*
error = security_path_unlink(&path, dentry);
if (error)
goto exit2;
- error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode);
+ error = vfs_unlink2(path.mnt, path.dentry->d_inode, dentry, &delegated_inode);
exit2:
dput(dentry);
}
return do_unlinkat(AT_FDCWD, pathname);
}
-int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
+int vfs_symlink2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, const char *oldname)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt, dir, dentry);
if (error)
return error;
fsnotify_create(dir, dentry);
return error;
}
+EXPORT_SYMBOL(vfs_symlink2);
+
+int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
+{
+ return vfs_symlink2(NULL, dir, dentry, oldname);
+}
EXPORT_SYMBOL(vfs_symlink);
SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
error = security_path_symlink(&path, dentry, from->name);
if (!error)
- error = vfs_symlink(path.dentry->d_inode, dentry, from->name);
+ error = vfs_symlink2(path.mnt, path.dentry->d_inode, dentry, from->name);
done_path_create(&path, dentry);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported.
*/
-int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
+int vfs_link2(struct vfsmount *mnt, struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
{
struct inode *inode = old_dentry->d_inode;
unsigned max_links = dir->i_sb->s_max_links;
if (!inode)
return -ENOENT;
- error = may_create(dir, new_dentry);
+ error = may_create(mnt, dir, new_dentry);
if (error)
return error;
fsnotify_link(dir, inode, new_dentry);
return error;
}
+EXPORT_SYMBOL(vfs_link2);
+
+int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
+{
+ return vfs_link2(NULL, old_dentry, dir, new_dentry, delegated_inode);
+}
EXPORT_SYMBOL(vfs_link);
/*
error = security_path_link(old_path.dentry, &new_path, new_dentry);
if (error)
goto out_dput;
- error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
+ error = vfs_link2(old_path.mnt, old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
out_dput:
done_path_create(&new_path, new_dentry);
if (delegated_inode) {
* ->i_mutex on parents, which works but leads to some truly excessive
* locking].
*/
-int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+int vfs_rename2(struct vfsmount *mnt,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
struct inode **delegated_inode, unsigned int flags)
{
if (vfs_select_inode(old_dentry, 0) == vfs_select_inode(new_dentry, 0))
return 0;
- error = may_delete(old_dir, old_dentry, is_dir);
+ error = may_delete(mnt, old_dir, old_dentry, is_dir);
if (error)
return error;
if (!target) {
- error = may_create(new_dir, new_dentry);
+ error = may_create(mnt, new_dir, new_dentry);
} else {
new_is_dir = d_is_dir(new_dentry);
if (!(flags & RENAME_EXCHANGE))
- error = may_delete(new_dir, new_dentry, is_dir);
+ error = may_delete(mnt, new_dir, new_dentry, is_dir);
else
- error = may_delete(new_dir, new_dentry, new_is_dir);
+ error = may_delete(mnt, new_dir, new_dentry, new_is_dir);
}
if (error)
return error;
*/
if (new_dir != old_dir) {
if (is_dir) {
- error = inode_permission(source, MAY_WRITE);
+ error = inode_permission2(mnt, source, MAY_WRITE);
if (error)
return error;
}
if ((flags & RENAME_EXCHANGE) && new_is_dir) {
- error = inode_permission(target, MAY_WRITE);
+ error = inode_permission2(mnt, target, MAY_WRITE);
if (error)
return error;
}
return error;
}
+EXPORT_SYMBOL(vfs_rename2);
+
+int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ struct inode **delegated_inode, unsigned int flags)
+{
+ return vfs_rename2(NULL, old_dir, old_dentry, new_dir, new_dentry, delegated_inode, flags);
+}
EXPORT_SYMBOL(vfs_rename);
SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
&new_path, new_dentry, flags);
if (error)
goto exit5;
- error = vfs_rename(old_path.dentry->d_inode, old_dentry,
+ error = vfs_rename2(old_path.mnt, old_path.dentry->d_inode, old_dentry,
new_path.dentry->d_inode, new_dentry,
&delegated_inode, flags);
exit5:
int vfs_whiteout(struct inode *dir, struct dentry *dentry)
{
- int error = may_create(dir, dentry);
+ int error = may_create(NULL, dir, dentry);
if (error)
return error;
OSDN Git Service
