[PATCH] vfs: *at functions: core

Here is a series of patches which introduce in total 13 new system calls
which take a file descriptor/filename pair instead of a single file
name.  These functions, openat etc, have been discussed on numerous
occasions.  They are needed to implement race-free filesystem traversal,
they are necessary to implement a virtual per-thread current working
directory (think multi-threaded backup software), etc.

We have in glibc today implementations of the interfaces which use the
/proc/self/fd magic.  But this code is rather expensive.  Here are some
results (similar to what Jim Meyering posted before).

The test creates a deep directory hierarchy on a tmpfs filesystem.  Then
rm -fr is used to remove all directories.  Without syscall support I get
this:

real    0m31.921s
user    0m0.688s
sys     0m31.234s

With syscall support the results are much better:

real    0m20.699s
user    0m0.536s
sys     0m20.149s

The interfaces are for obvious reasons currently not much used.  But they'll
be used.  coreutils (and Jeff's posixutils) are already using them.
Furthermore, code like ftw/fts in libc (maybe even glob) will also start using
them.  I expect a patch to make follow soon.  Every program which is walking
the filesystem tree will benefit.

Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@ftp.linux.org.uk>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 53 insertions, 13 deletions

diff --git a/fs/stat.c b/fs/stat.c
index b8a0e5110ab2..24211b030f39 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -63,12 +63,12 @@ int vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 
 EXPORT_SYMBOL(vfs_getattr);
 
-int vfs_stat(char __user *name, struct kstat *stat)
+int vfs_stat_fd(int dfd, char __user *name, struct kstat *stat)
 {
         struct nameidata nd;
         int error;
 
-        error = user_path_walk(name, &nd);
+        error = __user_walk_fd(dfd, name, LOOKUP_FOLLOW, &nd);
         if (!error) {
                 error = vfs_getattr(nd.mnt, nd.dentry, stat);
                 path_release(&nd);
@@ -76,14 +76,19 @@ int vfs_stat(char __user *name, struct kstat *stat)
         return error;
 }
 
+int vfs_stat(char __user *name, struct kstat *stat)
+{
+        return vfs_stat_fd(AT_FDCWD, name, stat);
+}
+
 EXPORT_SYMBOL(vfs_stat);
 
-int vfs_lstat(char __user *name, struct kstat *stat)
+int vfs_lstat_fd(int dfd, char __user *name, struct kstat *stat)
 {
         struct nameidata nd;
         int error;
 
-        error = user_path_walk_link(name, &nd);
+        error = __user_walk_fd(dfd, name, 0, &nd);
         if (!error) {
                 error = vfs_getattr(nd.mnt, nd.dentry, stat);
                 path_release(&nd);
@@ -91,6 +96,11 @@ int vfs_lstat(char __user *name, struct kstat *stat)
         return error;
 }
 
+int vfs_lstat(char __user *name, struct kstat *stat)
+{
+        return vfs_lstat_fd(AT_FDCWD, name, stat);
+}
+
 EXPORT_SYMBOL(vfs_lstat);
 
 int vfs_fstat(unsigned int fd, struct kstat *stat)
@@ -151,7 +161,7 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta
 asmlinkage long sys_stat(char __user * filename, struct __old_kernel_stat __user * statbuf)
 {
         struct kstat stat;
-        int error = vfs_stat(filename, &stat);
+        int error = vfs_stat_fd(AT_FDCWD, filename, &stat);
 
         if (!error)
                 error = cp_old_stat(&stat, statbuf);
@@ -161,7 +171,7 @@ asmlinkage long sys_stat(char __user * filename, struct __old_kernel_stat __user
 asmlinkage long sys_lstat(char __user * filename, struct __old_kernel_stat __user * statbuf)
 {
         struct kstat stat;
-        int error = vfs_lstat(filename, &stat);
+        int error = vfs_lstat_fd(AT_FDCWD, filename, &stat);
 
         if (!error)
                 error = cp_old_stat(&stat, statbuf);
@@ -229,27 +239,50 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
         return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
 }
 
-asmlinkage long sys_newstat(char __user * filename, struct stat __user * statbuf)
+asmlinkage long sys_newstat(char __user *filename, struct stat __user *statbuf)
 {
         struct kstat stat;
-        int error = vfs_stat(filename, &stat);
+        int error = vfs_stat_fd(AT_FDCWD, filename, &stat);
 
         if (!error)
                 error = cp_new_stat(&stat, statbuf);
 
         return error;
 }
-asmlinkage long sys_newlstat(char __user * filename, struct stat __user * statbuf)
+
+asmlinkage long sys_newlstat(char __user *filename, struct stat __user *statbuf)
 {
         struct kstat stat;
-        int error = vfs_lstat(filename, &stat);
+        int error = vfs_lstat_fd(AT_FDCWD, filename, &stat);
 
         if (!error)
                 error = cp_new_stat(&stat, statbuf);
 
         return error;
 }
-asmlinkage long sys_newfstat(unsigned int fd, struct stat __user * statbuf)
+
+asmlinkage long sys_newfstatat(int dfd, char __user *filename,
+                                struct stat __user *statbuf, int flag)
+{
+        struct kstat stat;
+        int error = -EINVAL;
+
+        if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
+                goto out;
+
+        if (flag & AT_SYMLINK_NOFOLLOW)
+                error = vfs_lstat_fd(dfd, filename, &stat);
+        else
+                error = vfs_stat_fd(dfd, filename, &stat);
+
+        if (!error)
+                error = cp_new_stat(&stat, statbuf);
+
+out:
+        return error;
+}
+
+asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf)
 {
         struct kstat stat;
         int error = vfs_fstat(fd, &stat);
@@ -260,7 +293,8 @@ asmlinkage long sys_newfstat(unsigned int fd, struct stat __user * statbuf)
         return error;
 }
 
-asmlinkage long sys_readlink(const char __user * path, char __user * buf, int bufsiz)
+asmlinkage long sys_readlinkat(int dfd, const char __user *path,
+                                char __user *buf, int bufsiz)
 {
         struct nameidata nd;
         int error;
@@ -268,7 +302,7 @@ asmlinkage long sys_readlink(const char __user * path, char __user * buf, int bu
         if (bufsiz <= 0)
                 return -EINVAL;
 
-        error = user_path_walk_link(path, &nd);
+        error = __user_walk_fd(dfd, path, 0, &nd);
         if (!error) {
                 struct inode * inode = nd.dentry->d_inode;
 
@@ -285,6 +319,12 @@ asmlinkage long sys_readlink(const char __user * path, char __user * buf, int bu
         return error;
 }
 
+asmlinkage long sys_readlink(const char __user *path, char __user *buf,
+                                int bufsiz)
+{
+        return sys_readlinkat(AT_FDCWD, path, buf, bufsiz);
+}
+
 
 /* ---------- LFS-64 ----------- */
 #ifdef __ARCH_WANT_STAT64