linux/fs/stat.c

486 lines
11 KiB
C
Raw Normal View History

/*
* linux/fs/stat.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/highuid.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/pagemap.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
void generic_fillattr(struct inode *inode, struct kstat *stat)
{
stat->dev = inode->i_sb->s_dev;
stat->ino = inode->i_ino;
stat->mode = inode->i_mode;
stat->nlink = inode->i_nlink;
stat->uid = inode->i_uid;
stat->gid = inode->i_gid;
stat->rdev = inode->i_rdev;
stat->size = i_size_read(inode);
stat->atime = inode->i_atime;
stat->mtime = inode->i_mtime;
stat->ctime = inode->i_ctime;
stat->blksize = (1 << inode->i_blkbits);
stat->blocks = inode->i_blocks;
}
EXPORT_SYMBOL(generic_fillattr);
int vfs_getattr(struct path *path, struct kstat *stat)
{
struct inode *inode = path->dentry->d_inode;
int retval;
retval = security_inode_getattr(path->mnt, path->dentry);
if (retval)
return retval;
if (inode->i_op->getattr)
return inode->i_op->getattr(path->mnt, path->dentry, stat);
generic_fillattr(inode, stat);
return 0;
}
EXPORT_SYMBOL(vfs_getattr);
int vfs_fstat(unsigned int fd, struct kstat *stat)
{
struct fd f = fdget_raw(fd);
int error = -EBADF;
if (f.file) {
error = vfs_getattr(&f.file->f_path, stat);
fdput(f);
}
return error;
}
EXPORT_SYMBOL(vfs_fstat);
int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
int flag)
{
struct path path;
int error = -EINVAL;
unsigned int lookup_flags = 0;
if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
AT_EMPTY_PATH)) != 0)
goto out;
if (!(flag & AT_SYMLINK_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
if (flag & AT_EMPTY_PATH)
lookup_flags |= LOOKUP_EMPTY;
retry:
error = user_path_at(dfd, filename, lookup_flags, &path);
if (error)
goto out;
error = vfs_getattr(&path, stat);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
EXPORT_SYMBOL(vfs_fstatat);
int vfs_stat(const char __user *name, struct kstat *stat)
{
return vfs_fstatat(AT_FDCWD, name, stat, 0);
}
EXPORT_SYMBOL(vfs_stat);
int vfs_lstat(const char __user *name, struct kstat *stat)
{
return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
}
EXPORT_SYMBOL(vfs_lstat);
#ifdef __ARCH_WANT_OLD_STAT
/*
* For backward compatibility? Maybe this should be moved
* into arch/i386 instead?
*/
static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * statbuf)
{
static int warncount = 5;
struct __old_kernel_stat tmp;
if (warncount > 0) {
warncount--;
printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n",
current->comm);
} else if (warncount < 0) {
/* it's laughable, but... */
warncount = 0;
}
memset(&tmp, 0, sizeof(struct __old_kernel_stat));
tmp.st_dev = old_encode_dev(stat->dev);
tmp.st_ino = stat->ino;
[PATCH] VFS: Make filldir_t and struct kstat deal in 64-bit inode numbers These patches make the kernel pass 64-bit inode numbers internally when communicating to userspace, even on a 32-bit system. They are required because some filesystems have intrinsic 64-bit inode numbers: NFS3+ and XFS for example. The 64-bit inode numbers are then propagated to userspace automatically where the arch supports it. Problems have been seen with userspace (eg: ld.so) using the 64-bit inode number returned by stat64() or getdents64() to differentiate files, and failing because the 64-bit inode number space was compressed to 32-bits, and so overlaps occur. This patch: Make filldir_t take a 64-bit inode number and struct kstat carry a 64-bit inode number so that 64-bit inode numbers can be passed back to userspace. The stat functions then returns the full 64-bit inode number where available and where possible. If it is not possible to represent the inode number supplied by the filesystem in the field provided by userspace, then error EOVERFLOW will be issued. Similarly, the getdents/readdir functions now pass the full 64-bit inode number to userspace where possible, returning EOVERFLOW instead when a directory entry is encountered that can't be properly represented. Note that this means that some inodes will not be stat'able on a 32-bit system with old libraries where they were before - but it does mean that there will be no ambiguity over what a 32-bit inode number refers to. Note similarly that directory scans may be cut short with an error on a 32-bit system with old libraries where the scan would work before for the same reasons. It is judged unlikely that this situation will occur because modern glibc uses 64-bit capable versions of stat and getdents class functions exclusively, and that older systems are unlikely to encounter unrepresentable inode numbers anyway. [akpm: alpha build fix] Signed-off-by: David Howells <dhowells@redhat.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-03 12:13:46 +04:00
if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
return -EOVERFLOW;
tmp.st_mode = stat->mode;
tmp.st_nlink = stat->nlink;
if (tmp.st_nlink != stat->nlink)
return -EOVERFLOW;
SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
tmp.st_rdev = old_encode_dev(stat->rdev);
#if BITS_PER_LONG == 32
if (stat->size > MAX_NON_LFS)
return -EOVERFLOW;
#endif
tmp.st_size = stat->size;
tmp.st_atime = stat->atime.tv_sec;
tmp.st_mtime = stat->mtime.tv_sec;
tmp.st_ctime = stat->ctime.tv_sec;
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}
SYSCALL_DEFINE2(stat, const char __user *, filename,
struct __old_kernel_stat __user *, statbuf)
{
struct kstat stat;
int error;
error = vfs_stat(filename, &stat);
if (error)
return error;
return cp_old_stat(&stat, statbuf);
}
SYSCALL_DEFINE2(lstat, const char __user *, filename,
struct __old_kernel_stat __user *, statbuf)
{
struct kstat stat;
int error;
error = vfs_lstat(filename, &stat);
if (error)
return error;
return cp_old_stat(&stat, statbuf);
}
SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, statbuf)
{
struct kstat stat;
int error = vfs_fstat(fd, &stat);
if (!error)
error = cp_old_stat(&stat, statbuf);
return error;
}
#endif /* __ARCH_WANT_OLD_STAT */
#if BITS_PER_LONG == 32
# define choose_32_64(a,b) a
#else
# define choose_32_64(a,b) b
#endif
#define valid_dev(x) choose_32_64(old_valid_dev,new_valid_dev)(x)
#define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x)
#ifndef INIT_STRUCT_STAT_PADDING
# define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st))
#endif
static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
{
struct stat tmp;
if (!valid_dev(stat->dev) || !valid_dev(stat->rdev))
return -EOVERFLOW;
#if BITS_PER_LONG == 32
if (stat->size > MAX_NON_LFS)
return -EOVERFLOW;
#endif
INIT_STRUCT_STAT_PADDING(tmp);
tmp.st_dev = encode_dev(stat->dev);
tmp.st_ino = stat->ino;
[PATCH] VFS: Make filldir_t and struct kstat deal in 64-bit inode numbers These patches make the kernel pass 64-bit inode numbers internally when communicating to userspace, even on a 32-bit system. They are required because some filesystems have intrinsic 64-bit inode numbers: NFS3+ and XFS for example. The 64-bit inode numbers are then propagated to userspace automatically where the arch supports it. Problems have been seen with userspace (eg: ld.so) using the 64-bit inode number returned by stat64() or getdents64() to differentiate files, and failing because the 64-bit inode number space was compressed to 32-bits, and so overlaps occur. This patch: Make filldir_t take a 64-bit inode number and struct kstat carry a 64-bit inode number so that 64-bit inode numbers can be passed back to userspace. The stat functions then returns the full 64-bit inode number where available and where possible. If it is not possible to represent the inode number supplied by the filesystem in the field provided by userspace, then error EOVERFLOW will be issued. Similarly, the getdents/readdir functions now pass the full 64-bit inode number to userspace where possible, returning EOVERFLOW instead when a directory entry is encountered that can't be properly represented. Note that this means that some inodes will not be stat'able on a 32-bit system with old libraries where they were before - but it does mean that there will be no ambiguity over what a 32-bit inode number refers to. Note similarly that directory scans may be cut short with an error on a 32-bit system with old libraries where the scan would work before for the same reasons. It is judged unlikely that this situation will occur because modern glibc uses 64-bit capable versions of stat and getdents class functions exclusively, and that older systems are unlikely to encounter unrepresentable inode numbers anyway. [akpm: alpha build fix] Signed-off-by: David Howells <dhowells@redhat.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-03 12:13:46 +04:00
if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
return -EOVERFLOW;
tmp.st_mode = stat->mode;
tmp.st_nlink = stat->nlink;
if (tmp.st_nlink != stat->nlink)
return -EOVERFLOW;
SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
tmp.st_rdev = encode_dev(stat->rdev);
tmp.st_size = stat->size;
tmp.st_atime = stat->atime.tv_sec;
tmp.st_mtime = stat->mtime.tv_sec;
tmp.st_ctime = stat->ctime.tv_sec;
#ifdef STAT_HAVE_NSEC
tmp.st_atime_nsec = stat->atime.tv_nsec;
tmp.st_mtime_nsec = stat->mtime.tv_nsec;
tmp.st_ctime_nsec = stat->ctime.tv_nsec;
#endif
tmp.st_blocks = stat->blocks;
tmp.st_blksize = stat->blksize;
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}
SYSCALL_DEFINE2(newstat, const char __user *, filename,
struct stat __user *, statbuf)
[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>
2006-01-19 04:43:53 +03:00
{
struct kstat stat;
int error = vfs_stat(filename, &stat);
[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>
2006-01-19 04:43:53 +03:00
if (error)
return error;
return cp_new_stat(&stat, statbuf);
[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>
2006-01-19 04:43:53 +03:00
}
SYSCALL_DEFINE2(newlstat, const char __user *, filename,
struct stat __user *, statbuf)
{
struct kstat stat;
int error;
error = vfs_lstat(filename, &stat);
if (error)
return error;
return cp_new_stat(&stat, statbuf);
}
[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>
2006-01-19 04:43:53 +03:00
#if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT)
SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename,
struct stat __user *, statbuf, int, flag)
{
struct kstat stat;
int error;
error = vfs_fstatat(dfd, filename, &stat, flag);
if (error)
return error;
return cp_new_stat(&stat, statbuf);
}
#endif
[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>
2006-01-19 04:43:53 +03:00
SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf)
{
struct kstat stat;
int error = vfs_fstat(fd, &stat);
if (!error)
error = cp_new_stat(&stat, statbuf);
return error;
}
SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
char __user *, buf, int, bufsiz)
{
struct path path;
int error;
int empty = 0;
unsigned int lookup_flags = LOOKUP_EMPTY;
if (bufsiz <= 0)
return -EINVAL;
retry:
error = user_path_at_empty(dfd, pathname, lookup_flags, &path, &empty);
if (!error) {
struct inode *inode = path.dentry->d_inode;
error = empty ? -ENOENT : -EINVAL;
if (inode->i_op->readlink) {
error = security_inode_readlink(path.dentry);
if (!error) {
touch_atime(&path);
error = inode->i_op->readlink(path.dentry,
buf, bufsiz);
}
}
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
}
return error;
}
SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf,
int, bufsiz)
[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>
2006-01-19 04:43:53 +03:00
{
return sys_readlinkat(AT_FDCWD, path, buf, bufsiz);
}
/* ---------- LFS-64 ----------- */
#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64)
#ifndef INIT_STRUCT_STAT64_PADDING
# define INIT_STRUCT_STAT64_PADDING(st) memset(&st, 0, sizeof(st))
#endif
static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf)
{
struct stat64 tmp;
INIT_STRUCT_STAT64_PADDING(tmp);
#ifdef CONFIG_MIPS
/* mips has weird padding, so we don't get 64 bits there */
if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev))
return -EOVERFLOW;
tmp.st_dev = new_encode_dev(stat->dev);
tmp.st_rdev = new_encode_dev(stat->rdev);
#else
tmp.st_dev = huge_encode_dev(stat->dev);
tmp.st_rdev = huge_encode_dev(stat->rdev);
#endif
tmp.st_ino = stat->ino;
[PATCH] VFS: Make filldir_t and struct kstat deal in 64-bit inode numbers These patches make the kernel pass 64-bit inode numbers internally when communicating to userspace, even on a 32-bit system. They are required because some filesystems have intrinsic 64-bit inode numbers: NFS3+ and XFS for example. The 64-bit inode numbers are then propagated to userspace automatically where the arch supports it. Problems have been seen with userspace (eg: ld.so) using the 64-bit inode number returned by stat64() or getdents64() to differentiate files, and failing because the 64-bit inode number space was compressed to 32-bits, and so overlaps occur. This patch: Make filldir_t take a 64-bit inode number and struct kstat carry a 64-bit inode number so that 64-bit inode numbers can be passed back to userspace. The stat functions then returns the full 64-bit inode number where available and where possible. If it is not possible to represent the inode number supplied by the filesystem in the field provided by userspace, then error EOVERFLOW will be issued. Similarly, the getdents/readdir functions now pass the full 64-bit inode number to userspace where possible, returning EOVERFLOW instead when a directory entry is encountered that can't be properly represented. Note that this means that some inodes will not be stat'able on a 32-bit system with old libraries where they were before - but it does mean that there will be no ambiguity over what a 32-bit inode number refers to. Note similarly that directory scans may be cut short with an error on a 32-bit system with old libraries where the scan would work before for the same reasons. It is judged unlikely that this situation will occur because modern glibc uses 64-bit capable versions of stat and getdents class functions exclusively, and that older systems are unlikely to encounter unrepresentable inode numbers anyway. [akpm: alpha build fix] Signed-off-by: David Howells <dhowells@redhat.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-03 12:13:46 +04:00
if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
return -EOVERFLOW;
#ifdef STAT64_HAS_BROKEN_ST_INO
tmp.__st_ino = stat->ino;
#endif
tmp.st_mode = stat->mode;
tmp.st_nlink = stat->nlink;
tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid);
tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid);
tmp.st_atime = stat->atime.tv_sec;
tmp.st_atime_nsec = stat->atime.tv_nsec;
tmp.st_mtime = stat->mtime.tv_sec;
tmp.st_mtime_nsec = stat->mtime.tv_nsec;
tmp.st_ctime = stat->ctime.tv_sec;
tmp.st_ctime_nsec = stat->ctime.tv_nsec;
tmp.st_size = stat->size;
tmp.st_blocks = stat->blocks;
tmp.st_blksize = stat->blksize;
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}
SYSCALL_DEFINE2(stat64, const char __user *, filename,
struct stat64 __user *, statbuf)
{
struct kstat stat;
int error = vfs_stat(filename, &stat);
if (!error)
error = cp_new_stat64(&stat, statbuf);
return error;
}
SYSCALL_DEFINE2(lstat64, const char __user *, filename,
struct stat64 __user *, statbuf)
{
struct kstat stat;
int error = vfs_lstat(filename, &stat);
if (!error)
error = cp_new_stat64(&stat, statbuf);
return error;
}
SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf)
{
struct kstat stat;
int error = vfs_fstat(fd, &stat);
if (!error)
error = cp_new_stat64(&stat, statbuf);
return error;
}
SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
struct stat64 __user *, statbuf, int, flag)
{
struct kstat stat;
int error;
error = vfs_fstatat(dfd, filename, &stat, flag);
if (error)
return error;
return cp_new_stat64(&stat, statbuf);
}
#endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
/* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
void __inode_add_bytes(struct inode *inode, loff_t bytes)
{
inode->i_blocks += bytes >> 9;
bytes &= 511;
inode->i_bytes += bytes;
if (inode->i_bytes >= 512) {
inode->i_blocks++;
inode->i_bytes -= 512;
}
}
void inode_add_bytes(struct inode *inode, loff_t bytes)
{
spin_lock(&inode->i_lock);
__inode_add_bytes(inode, bytes);
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(inode_add_bytes);
void inode_sub_bytes(struct inode *inode, loff_t bytes)
{
spin_lock(&inode->i_lock);
inode->i_blocks -= bytes >> 9;
bytes &= 511;
if (inode->i_bytes < bytes) {
inode->i_blocks--;
inode->i_bytes += 512;
}
inode->i_bytes -= bytes;
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(inode_sub_bytes);
loff_t inode_get_bytes(struct inode *inode)
{
loff_t ret;
spin_lock(&inode->i_lock);
ret = (((loff_t)inode->i_blocks) << 9) + inode->i_bytes;
spin_unlock(&inode->i_lock);
return ret;
}
EXPORT_SYMBOL(inode_get_bytes);
void inode_set_bytes(struct inode *inode, loff_t bytes)
{
/* Caller is here responsible for sufficient locking
* (ie. inode->i_lock) */
inode->i_blocks = bytes >> 9;
inode->i_bytes = bytes & 511;
}
EXPORT_SYMBOL(inode_set_bytes);