kernel_optimize_test/fs/readdir.c
David Howells afefdbb28a [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 08:03:40 -07:00

309 lines
6.9 KiB
C

/*
* linux/fs/readdir.c
*
* Copyright (C) 1995 Linus Torvalds
*/
#include <linux/module.h>
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/stat.h>
#include <linux/file.h>
#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/dirent.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/unistd.h>
#include <asm/uaccess.h>
int vfs_readdir(struct file *file, filldir_t filler, void *buf)
{
struct inode *inode = file->f_dentry->d_inode;
int res = -ENOTDIR;
if (!file->f_op || !file->f_op->readdir)
goto out;
res = security_file_permission(file, MAY_READ);
if (res)
goto out;
mutex_lock(&inode->i_mutex);
res = -ENOENT;
if (!IS_DEADDIR(inode)) {
res = file->f_op->readdir(file, buf, filler);
file_accessed(file);
}
mutex_unlock(&inode->i_mutex);
out:
return res;
}
EXPORT_SYMBOL(vfs_readdir);
/*
* Traditional linux readdir() handling..
*
* "count=1" is a special case, meaning that the buffer is one
* dirent-structure in size and that the code can't handle more
* anyway. Thus the special "fillonedir()" function for that
* case (the low-level handlers don't need to care about this).
*/
#define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de)))
#define ROUND_UP(x) (((x)+sizeof(long)-1) & ~(sizeof(long)-1))
#ifdef __ARCH_WANT_OLD_READDIR
struct old_linux_dirent {
unsigned long d_ino;
unsigned long d_offset;
unsigned short d_namlen;
char d_name[1];
};
struct readdir_callback {
struct old_linux_dirent __user * dirent;
int result;
};
static int fillonedir(void * __buf, const char * name, int namlen, loff_t offset,
u64 ino, unsigned int d_type)
{
struct readdir_callback * buf = (struct readdir_callback *) __buf;
struct old_linux_dirent __user * dirent;
unsigned long d_ino;
if (buf->result)
return -EINVAL;
d_ino = ino;
if (sizeof(d_ino) < sizeof(ino) && d_ino != ino)
return -EOVERFLOW;
buf->result++;
dirent = buf->dirent;
if (!access_ok(VERIFY_WRITE, dirent,
(unsigned long)(dirent->d_name + namlen + 1) -
(unsigned long)dirent))
goto efault;
if ( __put_user(d_ino, &dirent->d_ino) ||
__put_user(offset, &dirent->d_offset) ||
__put_user(namlen, &dirent->d_namlen) ||
__copy_to_user(dirent->d_name, name, namlen) ||
__put_user(0, dirent->d_name + namlen))
goto efault;
return 0;
efault:
buf->result = -EFAULT;
return -EFAULT;
}
asmlinkage long old_readdir(unsigned int fd, struct old_linux_dirent __user * dirent, unsigned int count)
{
int error;
struct file * file;
struct readdir_callback buf;
error = -EBADF;
file = fget(fd);
if (!file)
goto out;
buf.result = 0;
buf.dirent = dirent;
error = vfs_readdir(file, fillonedir, &buf);
if (error >= 0)
error = buf.result;
fput(file);
out:
return error;
}
#endif /* __ARCH_WANT_OLD_READDIR */
/*
* New, all-improved, singing, dancing, iBCS2-compliant getdents()
* interface.
*/
struct linux_dirent {
unsigned long d_ino;
unsigned long d_off;
unsigned short d_reclen;
char d_name[1];
};
struct getdents_callback {
struct linux_dirent __user * current_dir;
struct linux_dirent __user * previous;
int count;
int error;
};
static int filldir(void * __buf, const char * name, int namlen, loff_t offset,
u64 ino, unsigned int d_type)
{
struct linux_dirent __user * dirent;
struct getdents_callback * buf = (struct getdents_callback *) __buf;
unsigned long d_ino;
int reclen = ROUND_UP(NAME_OFFSET(dirent) + namlen + 2);
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
return -EINVAL;
d_ino = ino;
if (sizeof(d_ino) < sizeof(ino) && d_ino != ino)
return -EOVERFLOW;
dirent = buf->previous;
if (dirent) {
if (__put_user(offset, &dirent->d_off))
goto efault;
}
dirent = buf->current_dir;
if (__put_user(d_ino, &dirent->d_ino))
goto efault;
if (__put_user(reclen, &dirent->d_reclen))
goto efault;
if (copy_to_user(dirent->d_name, name, namlen))
goto efault;
if (__put_user(0, dirent->d_name + namlen))
goto efault;
if (__put_user(d_type, (char __user *) dirent + reclen - 1))
goto efault;
buf->previous = dirent;
dirent = (void __user *)dirent + reclen;
buf->current_dir = dirent;
buf->count -= reclen;
return 0;
efault:
buf->error = -EFAULT;
return -EFAULT;
}
asmlinkage long sys_getdents(unsigned int fd, struct linux_dirent __user * dirent, unsigned int count)
{
struct file * file;
struct linux_dirent __user * lastdirent;
struct getdents_callback buf;
int error;
error = -EFAULT;
if (!access_ok(VERIFY_WRITE, dirent, count))
goto out;
error = -EBADF;
file = fget(fd);
if (!file)
goto out;
buf.current_dir = dirent;
buf.previous = NULL;
buf.count = count;
buf.error = 0;
error = vfs_readdir(file, filldir, &buf);
if (error < 0)
goto out_putf;
error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
if (put_user(file->f_pos, &lastdirent->d_off))
error = -EFAULT;
else
error = count - buf.count;
}
out_putf:
fput(file);
out:
return error;
}
#define ROUND_UP64(x) (((x)+sizeof(u64)-1) & ~(sizeof(u64)-1))
struct getdents_callback64 {
struct linux_dirent64 __user * current_dir;
struct linux_dirent64 __user * previous;
int count;
int error;
};
static int filldir64(void * __buf, const char * name, int namlen, loff_t offset,
u64 ino, unsigned int d_type)
{
struct linux_dirent64 __user *dirent;
struct getdents_callback64 * buf = (struct getdents_callback64 *) __buf;
int reclen = ROUND_UP64(NAME_OFFSET(dirent) + namlen + 1);
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
return -EINVAL;
dirent = buf->previous;
if (dirent) {
if (__put_user(offset, &dirent->d_off))
goto efault;
}
dirent = buf->current_dir;
if (__put_user(ino, &dirent->d_ino))
goto efault;
if (__put_user(0, &dirent->d_off))
goto efault;
if (__put_user(reclen, &dirent->d_reclen))
goto efault;
if (__put_user(d_type, &dirent->d_type))
goto efault;
if (copy_to_user(dirent->d_name, name, namlen))
goto efault;
if (__put_user(0, dirent->d_name + namlen))
goto efault;
buf->previous = dirent;
dirent = (void __user *)dirent + reclen;
buf->current_dir = dirent;
buf->count -= reclen;
return 0;
efault:
buf->error = -EFAULT;
return -EFAULT;
}
asmlinkage long sys_getdents64(unsigned int fd, struct linux_dirent64 __user * dirent, unsigned int count)
{
struct file * file;
struct linux_dirent64 __user * lastdirent;
struct getdents_callback64 buf;
int error;
error = -EFAULT;
if (!access_ok(VERIFY_WRITE, dirent, count))
goto out;
error = -EBADF;
file = fget(fd);
if (!file)
goto out;
buf.current_dir = dirent;
buf.previous = NULL;
buf.count = count;
buf.error = 0;
error = vfs_readdir(file, filldir64, &buf);
if (error < 0)
goto out_putf;
error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
typeof(lastdirent->d_off) d_off = file->f_pos;
error = -EFAULT;
if (__put_user(d_off, &lastdirent->d_off))
goto out_putf;
error = count - buf.count;
}
out_putf:
fput(file);
out:
return error;
}