linux/fs/open.c

1176 lines
26 KiB
C
Raw Normal View History

/*
* linux/fs/open.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/quotaops.h>
#include <linux/fsnotify.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/tty.h>
#include <linux/namei.h>
#include <linux/backing-dev.h>
#include <linux/capability.h>
#include <linux/securebits.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/vfs.h>
[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 01:43:53 +00:00
#include <linux/fcntl.h>
#include <asm/uaccess.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/rcupdate.h>
#include <linux/audit.h>
sys_fallocate() implementation on i386, x86_64 and powerpc fallocate() is a new system call being proposed here which will allow applications to preallocate space to any file(s) in a file system. Each file system implementation that wants to use this feature will need to support an inode operation called ->fallocate(). Applications can use this feature to avoid fragmentation to certain level and thus get faster access speed. With preallocation, applications also get a guarantee of space for particular file(s) - even if later the the system becomes full. Currently, glibc provides an interface called posix_fallocate() which can be used for similar cause. Though this has the advantage of working on all file systems, but it is quite slow (since it writes zeroes to each block that has to be preallocated). Without a doubt, file systems can do this more efficiently within the kernel, by implementing the proposed fallocate() system call. It is expected that posix_fallocate() will be modified to call this new system call first and incase the kernel/filesystem does not implement it, it should fall back to the current implementation of writing zeroes to the new blocks. ToDos: 1. Implementation on other architectures (other than i386, x86_64, and ppc). Patches for s390(x) and ia64 are already available from previous posts, but it was decided that they should be added later once fallocate is in the mainline. Hence not including those patches in this take. 2. Changes to glibc, a) to support fallocate() system call b) to make posix_fallocate() and posix_fallocate64() call fallocate() Signed-off-by: Amit Arora <aarora@in.ibm.com>
2007-07-18 01:42:44 +00:00
#include <linux/falloc.h>
int vfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
int retval = -ENODEV;
if (dentry) {
retval = -ENOSYS;
if (dentry->d_sb->s_op->statfs) {
memset(buf, 0, sizeof(*buf));
retval = security_sb_statfs(dentry);
if (retval)
return retval;
retval = dentry->d_sb->s_op->statfs(dentry, buf);
if (retval == 0 && buf->f_frsize == 0)
buf->f_frsize = buf->f_bsize;
}
}
return retval;
}
EXPORT_SYMBOL(vfs_statfs);
static int vfs_statfs_native(struct dentry *dentry, struct statfs *buf)
{
struct kstatfs st;
int retval;
retval = vfs_statfs(dentry, &st);
if (retval)
return retval;
if (sizeof(*buf) == sizeof(st))
memcpy(buf, &st, sizeof(st));
else {
if (sizeof buf->f_blocks == 4) {
if ((st.f_blocks | st.f_bfree | st.f_bavail |
st.f_bsize | st.f_frsize) &
0xffffffff00000000ULL)
return -EOVERFLOW;
/*
* f_files and f_ffree may be -1; it's okay to stuff
* that into 32 bits
*/
if (st.f_files != -1 &&
(st.f_files & 0xffffffff00000000ULL))
return -EOVERFLOW;
if (st.f_ffree != -1 &&
(st.f_ffree & 0xffffffff00000000ULL))
return -EOVERFLOW;
}
buf->f_type = st.f_type;
buf->f_bsize = st.f_bsize;
buf->f_blocks = st.f_blocks;
buf->f_bfree = st.f_bfree;
buf->f_bavail = st.f_bavail;
buf->f_files = st.f_files;
buf->f_ffree = st.f_ffree;
buf->f_fsid = st.f_fsid;
buf->f_namelen = st.f_namelen;
buf->f_frsize = st.f_frsize;
memset(buf->f_spare, 0, sizeof(buf->f_spare));
}
return 0;
}
static int vfs_statfs64(struct dentry *dentry, struct statfs64 *buf)
{
struct kstatfs st;
int retval;
retval = vfs_statfs(dentry, &st);
if (retval)
return retval;
if (sizeof(*buf) == sizeof(st))
memcpy(buf, &st, sizeof(st));
else {
buf->f_type = st.f_type;
buf->f_bsize = st.f_bsize;
buf->f_blocks = st.f_blocks;
buf->f_bfree = st.f_bfree;
buf->f_bavail = st.f_bavail;
buf->f_files = st.f_files;
buf->f_ffree = st.f_ffree;
buf->f_fsid = st.f_fsid;
buf->f_namelen = st.f_namelen;
buf->f_frsize = st.f_frsize;
memset(buf->f_spare, 0, sizeof(buf->f_spare));
}
return 0;
}
asmlinkage long sys_statfs(const char __user *pathname, struct statfs __user * buf)
{
struct path path;
int error;
error = user_path(pathname, &path);
if (!error) {
struct statfs tmp;
error = vfs_statfs_native(path.dentry, &tmp);
if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
error = -EFAULT;
path_put(&path);
}
return error;
}
asmlinkage long sys_statfs64(const char __user *pathname, size_t sz, struct statfs64 __user *buf)
{
struct path path;
long error;
if (sz != sizeof(*buf))
return -EINVAL;
error = user_path(pathname, &path);
if (!error) {
struct statfs64 tmp;
error = vfs_statfs64(path.dentry, &tmp);
if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
error = -EFAULT;
path_put(&path);
}
return error;
}
asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user * buf)
{
struct file * file;
struct statfs tmp;
int error;
error = -EBADF;
file = fget(fd);
if (!file)
goto out;
error = vfs_statfs_native(file->f_path.dentry, &tmp);
if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
error = -EFAULT;
fput(file);
out:
return error;
}
asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, struct statfs64 __user *buf)
{
struct file * file;
struct statfs64 tmp;
int error;
if (sz != sizeof(*buf))
return -EINVAL;
error = -EBADF;
file = fget(fd);
if (!file)
goto out;
error = vfs_statfs64(file->f_path.dentry, &tmp);
if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
error = -EFAULT;
fput(file);
out:
return error;
}
int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
struct file *filp)
{
int err;
struct iattr newattrs;
/* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */
if (length < 0)
return -EINVAL;
newattrs.ia_size = length;
newattrs.ia_valid = ATTR_SIZE | time_attrs;
if (filp) {
newattrs.ia_file = filp;
newattrs.ia_valid |= ATTR_FILE;
}
/* Remove suid/sgid on truncate too */
newattrs.ia_valid |= should_remove_suid(dentry);
mutex_lock(&dentry->d_inode->i_mutex);
err = notify_change(dentry, &newattrs);
mutex_unlock(&dentry->d_inode->i_mutex);
return err;
}
static long do_sys_truncate(const char __user *pathname, loff_t length)
{
struct path path;
struct inode *inode;
int error;
error = -EINVAL;
if (length < 0) /* sorry, but loff_t says... */
goto out;
error = user_path(pathname, &path);
if (error)
goto out;
inode = path.dentry->d_inode;
/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
error = -EISDIR;
if (S_ISDIR(inode->i_mode))
goto dput_and_out;
error = -EINVAL;
if (!S_ISREG(inode->i_mode))
goto dput_and_out;
error = mnt_want_write(path.mnt);
if (error)
goto dput_and_out;
error = inode_permission(inode, MAY_WRITE);
if (error)
goto mnt_drop_write_and_out;
error = -EPERM;
if (IS_APPEND(inode))
goto mnt_drop_write_and_out;
error = get_write_access(inode);
if (error)
goto mnt_drop_write_and_out;
/*
* Make sure that there are no leases. get_write_access() protects
* against the truncate racing with a lease-granting setlease().
*/
error = break_lease(inode, FMODE_WRITE);
if (error)
goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error) {
DQUOT_INIT(inode);
error = do_truncate(path.dentry, length, 0, NULL);
}
put_write_and_out:
put_write_access(inode);
mnt_drop_write_and_out:
mnt_drop_write(path.mnt);
dput_and_out:
path_put(&path);
out:
return error;
}
asmlinkage long sys_truncate(const char __user * path, unsigned long length)
{
/* on 32-bit boxen it will cut the range 2^31--2^32-1 off */
return do_sys_truncate(path, (long)length);
}
static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct inode * inode;
struct dentry *dentry;
struct file * file;
int error;
error = -EINVAL;
if (length < 0)
goto out;
error = -EBADF;
file = fget(fd);
if (!file)
goto out;
/* explicitly opened as large or we are on 64-bit box */
if (file->f_flags & O_LARGEFILE)
small = 0;
dentry = file->f_path.dentry;
inode = dentry->d_inode;
error = -EINVAL;
if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE))
goto out_putf;
error = -EINVAL;
/* Cannot ftruncate over 2^31 bytes without large file support */
if (small && length > MAX_NON_LFS)
goto out_putf;
error = -EPERM;
if (IS_APPEND(inode))
goto out_putf;
error = locks_verify_truncate(inode, file, length);
if (!error)
[PATCH] ftruncate does not always update m/ctime In the course of trying to track down a bug where a file mtime was not being updated correctly, it was discovered that the m/ctime updates were not quite being handled correctly for ftruncate() calls. Quoth SUSv3: open(2): If O_TRUNC is set and the file did previously exist, upon successful completion, open() shall mark for update the st_ctime and st_mtime fields of the file. truncate(2): Upon successful completion, if the file size is changed, this function shall mark for update the st_ctime and st_mtime fields of the file, and the S_ISUID and S_ISGID bits of the file mode may be cleared. ftruncate(2): Upon successful completion, if fildes refers to a regular file, the ftruncate() function shall mark for update the st_ctime and st_mtime fields of the file and the S_ISUID and S_ISGID bits of the file mode may be cleared. If the ftruncate() function is unsuccessful, the file is unaffected. The open(O_TRUNC) and truncate cases were being handled correctly, but the ftruncate case was being handled like the truncate case. The semantics of truncate and ftruncate don't quite match, so ftruncate needs to be handled slightly differently. The attached patch addresses this issue for ftruncate(2). My thanx to Stephen Tweedie and Trond Myklebust for their help in understanding the situation and semantics. Signed-off-by: Peter Staubach <staubach@redhat.com> Cc: "Stephen C. Tweedie" <sct@redhat.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-25 12:48:36 +00:00
error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file);
out_putf:
fput(file);
out:
return error;
}
asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length)
{
long ret = do_sys_ftruncate(fd, length, 1);
/* avoid REGPARM breakage on x86: */
asmlinkage_protect(2, ret, fd, length);
return ret;
}
/* LFS versions of truncate are only needed on 32 bit machines */
#if BITS_PER_LONG == 32
asmlinkage long sys_truncate64(const char __user * path, loff_t length)
{
return do_sys_truncate(path, length);
}
asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length)
{
long ret = do_sys_ftruncate(fd, length, 0);
/* avoid REGPARM breakage on x86: */
asmlinkage_protect(2, ret, fd, length);
return ret;
}
#endif
sys_fallocate() implementation on i386, x86_64 and powerpc fallocate() is a new system call being proposed here which will allow applications to preallocate space to any file(s) in a file system. Each file system implementation that wants to use this feature will need to support an inode operation called ->fallocate(). Applications can use this feature to avoid fragmentation to certain level and thus get faster access speed. With preallocation, applications also get a guarantee of space for particular file(s) - even if later the the system becomes full. Currently, glibc provides an interface called posix_fallocate() which can be used for similar cause. Though this has the advantage of working on all file systems, but it is quite slow (since it writes zeroes to each block that has to be preallocated). Without a doubt, file systems can do this more efficiently within the kernel, by implementing the proposed fallocate() system call. It is expected that posix_fallocate() will be modified to call this new system call first and incase the kernel/filesystem does not implement it, it should fall back to the current implementation of writing zeroes to the new blocks. ToDos: 1. Implementation on other architectures (other than i386, x86_64, and ppc). Patches for s390(x) and ia64 are already available from previous posts, but it was decided that they should be added later once fallocate is in the mainline. Hence not including those patches in this take. 2. Changes to glibc, a) to support fallocate() system call b) to make posix_fallocate() and posix_fallocate64() call fallocate() Signed-off-by: Amit Arora <aarora@in.ibm.com>
2007-07-18 01:42:44 +00:00
asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len)
{
struct file *file;
struct inode *inode;
long ret = -EINVAL;
if (offset < 0 || len <= 0)
goto out;
/* Return error if mode is not supported */
ret = -EOPNOTSUPP;
if (mode && !(mode & FALLOC_FL_KEEP_SIZE))
goto out;
ret = -EBADF;
file = fget(fd);
if (!file)
goto out;
if (!(file->f_mode & FMODE_WRITE))
goto out_fput;
/*
* Revalidate the write permissions, in case security policy has
* changed since the files were opened.
*/
ret = security_file_permission(file, MAY_WRITE);
if (ret)
goto out_fput;
inode = file->f_path.dentry->d_inode;
ret = -ESPIPE;
if (S_ISFIFO(inode->i_mode))
goto out_fput;
ret = -ENODEV;
/*
* Let individual file system decide if it supports preallocation
* for directories or not.
*/
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
goto out_fput;
ret = -EFBIG;
/* Check for wrap through zero too */
if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
goto out_fput;
if (inode->i_op && inode->i_op->fallocate)
ret = inode->i_op->fallocate(inode, mode, offset, len);
else
ret = -EOPNOTSUPP;
sys_fallocate() implementation on i386, x86_64 and powerpc fallocate() is a new system call being proposed here which will allow applications to preallocate space to any file(s) in a file system. Each file system implementation that wants to use this feature will need to support an inode operation called ->fallocate(). Applications can use this feature to avoid fragmentation to certain level and thus get faster access speed. With preallocation, applications also get a guarantee of space for particular file(s) - even if later the the system becomes full. Currently, glibc provides an interface called posix_fallocate() which can be used for similar cause. Though this has the advantage of working on all file systems, but it is quite slow (since it writes zeroes to each block that has to be preallocated). Without a doubt, file systems can do this more efficiently within the kernel, by implementing the proposed fallocate() system call. It is expected that posix_fallocate() will be modified to call this new system call first and incase the kernel/filesystem does not implement it, it should fall back to the current implementation of writing zeroes to the new blocks. ToDos: 1. Implementation on other architectures (other than i386, x86_64, and ppc). Patches for s390(x) and ia64 are already available from previous posts, but it was decided that they should be added later once fallocate is in the mainline. Hence not including those patches in this take. 2. Changes to glibc, a) to support fallocate() system call b) to make posix_fallocate() and posix_fallocate64() call fallocate() Signed-off-by: Amit Arora <aarora@in.ibm.com>
2007-07-18 01:42:44 +00:00
out_fput:
fput(file);
out:
return ret;
}
/*
* access() needs to use the real uid/gid, not the effective uid/gid.
* We do this by temporarily clearing all FS-related capabilities and
* switching the fsuid/fsgid around to the real ones.
*/
[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 01:43:53 +00:00
asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
{
struct path path;
struct inode *inode;
int old_fsuid, old_fsgid;
kernel_cap_t uninitialized_var(old_cap); /* !SECURE_NO_SETUID_FIXUP */
int res;
if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */
return -EINVAL;
old_fsuid = current->fsuid;
old_fsgid = current->fsgid;
current->fsuid = current->uid;
current->fsgid = current->gid;
if (!issecure(SECURE_NO_SETUID_FIXUP)) {
/*
* Clear the capabilities if we switch to a non-root user
*/
#ifndef CONFIG_SECURITY_FILE_CAPABILITIES
/*
* FIXME: There is a race here against sys_capset. The
* capabilities can change yet we will restore the old
* value below. We should hold task_capabilities_lock,
* but we cannot because user_path_at can sleep.
*/
#endif /* ndef CONFIG_SECURITY_FILE_CAPABILITIES */
if (current->uid)
old_cap = cap_set_effective(__cap_empty_set);
else
old_cap = cap_set_effective(current->cap_permitted);
}
res = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
if (res)
goto out;
inode = path.dentry->d_inode;
if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
/*
* MAY_EXEC on regular files is denied if the fs is mounted
* with the "noexec" flag.
*/
res = -EACCES;
if (path.mnt->mnt_flags & MNT_NOEXEC)
goto out_path_release;
}
res = inode_permission(inode, mode | MAY_ACCESS);
/* SuS v2 requires we report a read only fs too */
if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
goto out_path_release;
/*
* This is a rare case where using __mnt_is_readonly()
* is OK without a mnt_want/drop_write() pair. Since
* no actual write to the fs is performed here, we do
* not need to telegraph to that to anyone.
*
* By doing this, we accept that this access is
* inherently racy and know that the fs may change
* state before we even see this result.
*/
if (__mnt_is_readonly(path.mnt))
res = -EROFS;
out_path_release:
path_put(&path);
out:
current->fsuid = old_fsuid;
current->fsgid = old_fsgid;
if (!issecure(SECURE_NO_SETUID_FIXUP))
cap_set_effective(old_cap);
return res;
}
[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 01:43:53 +00:00
asmlinkage long sys_access(const char __user *filename, int mode)
{
return sys_faccessat(AT_FDCWD, filename, mode);
}
asmlinkage long sys_chdir(const char __user * filename)
{
struct path path;
int error;
error = user_path_dir(filename, &path);
if (error)
goto out;
error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_ACCESS);
if (error)
goto dput_and_out;
set_fs_pwd(current->fs, &path);
dput_and_out:
path_put(&path);
out:
return error;
}
asmlinkage long sys_fchdir(unsigned int fd)
{
struct file *file;
struct inode *inode;
int error;
error = -EBADF;
file = fget(fd);
if (!file)
goto out;
inode = file->f_path.dentry->d_inode;
error = -ENOTDIR;
if (!S_ISDIR(inode->i_mode))
goto out_putf;
error = inode_permission(inode, MAY_EXEC | MAY_ACCESS);
if (!error)
set_fs_pwd(current->fs, &file->f_path);
out_putf:
fput(file);
out:
return error;
}
asmlinkage long sys_chroot(const char __user * filename)
{
struct path path;
int error;
error = user_path_dir(filename, &path);
if (error)
goto out;
error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_ACCESS);
if (error)
goto dput_and_out;
error = -EPERM;
if (!capable(CAP_SYS_CHROOT))
goto dput_and_out;
set_fs_root(current->fs, &path);
error = 0;
dput_and_out:
path_put(&path);
out:
return error;
}
asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
{
struct inode * inode;
struct dentry * dentry;
struct file * file;
int err = -EBADF;
struct iattr newattrs;
file = fget(fd);
if (!file)
goto out;
dentry = file->f_path.dentry;
inode = dentry->d_inode;
audit_inode(NULL, dentry);
err = mnt_want_write(file->f_path.mnt);
if (err)
goto out_putf;
mutex_lock(&inode->i_mutex);
if (mode == (mode_t) -1)
mode = inode->i_mode;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
err = notify_change(dentry, &newattrs);
mutex_unlock(&inode->i_mutex);
mnt_drop_write(file->f_path.mnt);
out_putf:
fput(file);
out:
return err;
}
[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 01:43:53 +00:00
asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
mode_t mode)
{
struct path path;
struct inode *inode;
int error;
struct iattr newattrs;
error = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
if (error)
goto out;
inode = path.dentry->d_inode;
error = mnt_want_write(path.mnt);
if (error)
goto dput_and_out;
mutex_lock(&inode->i_mutex);
if (mode == (mode_t) -1)
mode = inode->i_mode;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
error = notify_change(path.dentry, &newattrs);
mutex_unlock(&inode->i_mutex);
mnt_drop_write(path.mnt);
dput_and_out:
path_put(&path);
out:
return error;
}
[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 01:43:53 +00:00
asmlinkage long sys_chmod(const char __user *filename, mode_t mode)
{
return sys_fchmodat(AT_FDCWD, filename, mode);
}
static int chown_common(struct dentry * dentry, uid_t user, gid_t group)
{
struct inode *inode = dentry->d_inode;
int error;
struct iattr newattrs;
newattrs.ia_valid = ATTR_CTIME;
if (user != (uid_t) -1) {
newattrs.ia_valid |= ATTR_UID;
newattrs.ia_uid = user;
}
if (group != (gid_t) -1) {
newattrs.ia_valid |= ATTR_GID;
newattrs.ia_gid = group;
}
if (!S_ISDIR(inode->i_mode))
Implement file posix capabilities Implement file posix capabilities. This allows programs to be given a subset of root's powers regardless of who runs them, without having to use setuid and giving the binary all of root's powers. This version works with Kaigai Kohei's userspace tools, found at http://www.kaigai.gr.jp/index.php. For more information on how to use this patch, Chris Friedhoff has posted a nice page at http://www.friedhoff.org/fscaps.html. Changelog: Nov 27: Incorporate fixes from Andrew Morton (security-introduce-file-caps-tweaks and security-introduce-file-caps-warning-fix) Fix Kconfig dependency. Fix change signaling behavior when file caps are not compiled in. Nov 13: Integrate comments from Alexey: Remove CONFIG_ ifdef from capability.h, and use %zd for printing a size_t. Nov 13: Fix endianness warnings by sparse as suggested by Alexey Dobriyan. Nov 09: Address warnings of unused variables at cap_bprm_set_security when file capabilities are disabled, and simultaneously clean up the code a little, by pulling the new code into a helper function. Nov 08: For pointers to required userspace tools and how to use them, see http://www.friedhoff.org/fscaps.html. Nov 07: Fix the calculation of the highest bit checked in check_cap_sanity(). Nov 07: Allow file caps to be enabled without CONFIG_SECURITY, since capabilities are the default. Hook cap_task_setscheduler when !CONFIG_SECURITY. Move capable(TASK_KILL) to end of cap_task_kill to reduce audit messages. Nov 05: Add secondary calls in selinux/hooks.c to task_setioprio and task_setscheduler so that selinux and capabilities with file cap support can be stacked. Sep 05: As Seth Arnold points out, uid checks are out of place for capability code. Sep 01: Define task_setscheduler, task_setioprio, cap_task_kill, and task_setnice to make sure a user cannot affect a process in which they called a program with some fscaps. One remaining question is the note under task_setscheduler: are we ok with CAP_SYS_NICE being sufficient to confine a process to a cpuset? It is a semantic change, as without fsccaps, attach_task doesn't allow CAP_SYS_NICE to override the uid equivalence check. But since it uses security_task_setscheduler, which elsewhere is used where CAP_SYS_NICE can be used to override the uid equivalence check, fixing it might be tough. task_setscheduler note: this also controls cpuset:attach_task. Are we ok with CAP_SYS_NICE being used to confine to a cpuset? task_setioprio task_setnice sys_setpriority uses this (through set_one_prio) for another process. Need same checks as setrlimit Aug 21: Updated secureexec implementation to reflect the fact that euid and uid might be the same and nonzero, but the process might still have elevated caps. Aug 15: Handle endianness of xattrs. Enforce capability version match between kernel and disk. Enforce that no bits beyond the known max capability are set, else return -EPERM. With this extra processing, it may be worth reconsidering doing all the work at bprm_set_security rather than d_instantiate. Aug 10: Always call getxattr at bprm_set_security, rather than caching it at d_instantiate. [morgan@kernel.org: file-caps clean up for linux/capability.h] [bunk@kernel.org: unexport cap_inode_killpriv] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Andrew Morgan <morgan@kernel.org> Signed-off-by: Andrew Morgan <morgan@kernel.org> Signed-off-by: Adrian Bunk <bunk@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 06:31:36 +00:00
newattrs.ia_valid |=
ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
mutex_lock(&inode->i_mutex);
error = notify_change(dentry, &newattrs);
mutex_unlock(&inode->i_mutex);
return error;
}
asmlinkage long sys_chown(const char __user * filename, uid_t user, gid_t group)
{
struct path path;
int error;
error = user_path(filename, &path);
if (error)
goto out;
error = mnt_want_write(path.mnt);
if (error)
goto out_release;
error = chown_common(path.dentry, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
out:
return error;
}
[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 01:43:53 +00:00
asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
gid_t group, int flag)
{
struct path path;
[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 01:43:53 +00:00
int error = -EINVAL;
int follow;
if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
goto out;
follow = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
error = user_path_at(dfd, filename, follow, &path);
if (error)
goto out;
error = mnt_want_write(path.mnt);
if (error)
goto out_release;
error = chown_common(path.dentry, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
[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 01:43:53 +00:00
out:
return error;
}
asmlinkage long sys_lchown(const char __user * filename, uid_t user, gid_t group)
{
struct path path;
int error;
error = user_lpath(filename, &path);
if (error)
goto out;
error = mnt_want_write(path.mnt);
if (error)
goto out_release;
error = chown_common(path.dentry, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
out:
return error;
}
asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group)
{
struct file * file;
int error = -EBADF;
struct dentry * dentry;
file = fget(fd);
if (!file)
goto out;
error = mnt_want_write(file->f_path.mnt);
if (error)
goto out_fput;
dentry = file->f_path.dentry;
audit_inode(NULL, dentry);
error = chown_common(dentry, user, group);
mnt_drop_write(file->f_path.mnt);
out_fput:
fput(file);
out:
return error;
}
/*
* You have to be very careful that these write
* counts get cleaned up in error cases and
* upon __fput(). This should probably never
* be called outside of __dentry_open().
*/
static inline int __get_file_write_access(struct inode *inode,
struct vfsmount *mnt)
{
int error;
error = get_write_access(inode);
if (error)
return error;
/*
* Do not take mount writer counts on
* special files since no writes to
* the mount itself will occur.
*/
if (!special_file(inode->i_mode)) {
/*
* Balanced in __fput()
*/
error = mnt_want_write(mnt);
if (error)
put_write_access(inode);
}
return error;
}
static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
int flags, struct file *f,
int (*open)(struct inode *, struct file *))
{
struct inode *inode;
int error;
f->f_flags = flags;
f->f_mode = ((flags+1) & O_ACCMODE) | FMODE_LSEEK |
FMODE_PREAD | FMODE_PWRITE;
inode = dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
error = __get_file_write_access(inode, mnt);
if (error)
goto cleanup_file;
if (!special_file(inode->i_mode))
file_take_write(f);
}
f->f_mapping = inode->i_mapping;
f->f_path.dentry = dentry;
f->f_path.mnt = mnt;
f->f_pos = 0;
f->f_op = fops_get(inode->i_fop);
file_move(f, &inode->i_sb->s_files);
error = security_dentry_open(f);
if (error)
goto cleanup_all;
if (!open && f->f_op)
open = f->f_op->open;
if (open) {
error = open(inode, f);
if (error)
goto cleanup_all;
}
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
/* NB: we're sure to have correct a_ops only after f_op->open */
if (f->f_flags & O_DIRECT) {
if (!f->f_mapping->a_ops ||
((!f->f_mapping->a_ops->direct_IO) &&
(!f->f_mapping->a_ops->get_xip_mem))) {
fput(f);
f = ERR_PTR(-EINVAL);
}
}
return f;
cleanup_all:
fops_put(f->f_op);
if (f->f_mode & FMODE_WRITE) {
put_write_access(inode);
if (!special_file(inode->i_mode)) {
/*
* We don't consider this a real
* mnt_want/drop_write() pair
* because it all happenend right
* here, so just reset the state.
*/
file_reset_write(f);
mnt_drop_write(mnt);
}
}
file_kill(f);
f->f_path.dentry = NULL;
f->f_path.mnt = NULL;
cleanup_file:
put_filp(f);
dput(dentry);
mntput(mnt);
return ERR_PTR(error);
}
/**
* lookup_instantiate_filp - instantiates the open intent filp
* @nd: pointer to nameidata
* @dentry: pointer to dentry
* @open: open callback
*
* Helper for filesystems that want to use lookup open intents and pass back
* a fully instantiated struct file to the caller.
* This function is meant to be called from within a filesystem's
* lookup method.
* Beware of calling it for non-regular files! Those ->open methods might block
* (e.g. in fifo_open), leaving you with parent locked (and in case of fifo,
* leading to a deadlock, as nobody can open that fifo anymore, because
* another process to open fifo will block on locked parent when doing lookup).
* Note that in case of error, nd->intent.open.file is destroyed, but the
* path information remains valid.
* If the open callback is set to NULL, then the standard f_op->open()
* filesystem callback is substituted.
*/
struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
int (*open)(struct inode *, struct file *))
{
if (IS_ERR(nd->intent.open.file))
goto out;
if (IS_ERR(dentry))
goto out_err;
nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt),
nd->intent.open.flags - 1,
nd->intent.open.file,
open);
out:
return nd->intent.open.file;
out_err:
release_open_intent(nd);
nd->intent.open.file = (struct file *)dentry;
goto out;
}
EXPORT_SYMBOL_GPL(lookup_instantiate_filp);
/**
* nameidata_to_filp - convert a nameidata to an open filp.
* @nd: pointer to nameidata
* @flags: open flags
*
* Note that this function destroys the original nameidata
*/
struct file *nameidata_to_filp(struct nameidata *nd, int flags)
{
struct file *filp;
/* Pick up the filp from the open intent */
filp = nd->intent.open.file;
/* Has the filesystem initialised the file for us? */
if (filp->f_path.dentry == NULL)
filp = __dentry_open(nd->path.dentry, nd->path.mnt, flags, filp,
NULL);
else
path_put(&nd->path);
return filp;
}
/*
* dentry_open() will have done dput(dentry) and mntput(mnt) if it returns an
* error.
*/
struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags)
{
int error;
struct file *f;
/*
* We must always pass in a valid mount pointer. Historically
* callers got away with not passing it, but we must enforce this at
* the earliest possible point now to avoid strange problems deep in the
* filesystem stack.
*/
if (!mnt) {
printk(KERN_WARNING "%s called with NULL vfsmount\n", __func__);
dump_stack();
return ERR_PTR(-EINVAL);
}
error = -ENFILE;
f = get_empty_filp();
if (f == NULL) {
dput(dentry);
mntput(mnt);
return ERR_PTR(error);
}
return __dentry_open(dentry, mnt, flags, f, NULL);
}
EXPORT_SYMBOL(dentry_open);
static void __put_unused_fd(struct files_struct *files, unsigned int fd)
{
struct fdtable *fdt = files_fdtable(files);
__FD_CLR(fd, fdt->open_fds);
if (fd < files->next_fd)
files->next_fd = fd;
}
void put_unused_fd(unsigned int fd)
{
struct files_struct *files = current->files;
spin_lock(&files->file_lock);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
}
EXPORT_SYMBOL(put_unused_fd);
/*
[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 01:43:53 +00:00
* Install a file pointer in the fd array.
*
* The VFS is full of places where we drop the files lock between
* setting the open_fds bitmap and installing the file in the file
* array. At any such point, we are vulnerable to a dup2() race
* installing a file in the array before us. We need to detect this and
* fput() the struct file we are about to overwrite in this case.
*
* It should never happen - if we allow dup2() do it, _really_ bad things
* will follow.
*/
void fd_install(unsigned int fd, struct file *file)
{
struct files_struct *files = current->files;
struct fdtable *fdt;
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
BUG_ON(fdt->fd[fd] != NULL);
rcu_assign_pointer(fdt->fd[fd], file);
spin_unlock(&files->file_lock);
}
EXPORT_SYMBOL(fd_install);
[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 01:43:53 +00:00
long do_sys_open(int dfd, const char __user *filename, int flags, int mode)
{
char *tmp = getname(filename);
int fd = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
Introduce O_CLOEXEC The problem is as follows: in multi-threaded code (or more correctly: all code using clone() with CLONE_FILES) we have a race when exec'ing. thread #1 thread #2 fd=open() fork + exec fcntl(fd,F_SETFD,FD_CLOEXEC) In some applications this can happen frequently. Take a web browser. One thread opens a file and another thread starts, say, an external PDF viewer. The result can even be a security issue if that open file descriptor refers to a sensitive file and the external program can somehow be tricked into using that descriptor. Just adding O_CLOEXEC support to open() doesn't solve the whole set of problems. There are other ways to create file descriptors (socket, epoll_create, Unix domain socket transfer, etc). These can and should be addressed separately though. open() is such an easy case that it makes not much sense putting the fix off. The test program: #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <unistd.h> #ifndef O_CLOEXEC # define O_CLOEXEC 02000000 #endif int main (int argc, char *argv[]) { int fd; if (argc > 1) { fd = atol (argv[1]); printf ("child: fd = %d\n", fd); if (fcntl (fd, F_GETFD) == 0 || errno != EBADF) { puts ("file descriptor valid in child"); return 1; } return 0; } fd = open ("/proc/self/exe", O_RDONLY | O_CLOEXEC); printf ("in parent: new fd = %d\n", fd); char buf[20]; snprintf (buf, sizeof (buf), "%d", fd); execl ("/proc/self/exe", argv[0], buf, NULL); puts ("execl failed"); return 1; } [kyle@parisc-linux.org: parisc fix] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Chris Zankel <chris@zankel.net> Signed-off-by: Kyle McMartin <kyle@parisc-linux.org> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-16 06:40:32 +00:00
fd = get_unused_fd_flags(flags);
if (fd >= 0) {
[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 01:43:53 +00:00
struct file *f = do_filp_open(dfd, tmp, flags, mode);
if (IS_ERR(f)) {
put_unused_fd(fd);
fd = PTR_ERR(f);
} else {
fsnotify_open(f->f_path.dentry);
fd_install(fd, f);
}
}
putname(tmp);
}
return fd;
}
asmlinkage long sys_open(const char __user *filename, int flags, int mode)
{
long ret;
if (force_o_largefile())
flags |= O_LARGEFILE;
ret = do_sys_open(AT_FDCWD, filename, flags, mode);
/* avoid REGPARM breakage on x86: */
asmlinkage_protect(3, ret, filename, flags, mode);
return ret;
}
[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 01:43:53 +00:00
asmlinkage long sys_openat(int dfd, const char __user *filename, int flags,
int mode)
{
long ret;
[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 01:43:53 +00:00
if (force_o_largefile())
flags |= O_LARGEFILE;
ret = do_sys_open(dfd, filename, flags, mode);
/* avoid REGPARM breakage on x86: */
asmlinkage_protect(4, ret, dfd, filename, flags, mode);
return ret;
[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 01:43:53 +00:00
}
#ifndef __alpha__
/*
* For backward compatibility? Maybe this should be moved
* into arch/i386 instead?
*/
asmlinkage long sys_creat(const char __user * pathname, int mode)
{
return sys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode);
}
#endif
/*
* "id" is the POSIX thread ID. We use the
* files pointer for this..
*/
int filp_close(struct file *filp, fl_owner_t id)
{
int retval = 0;
if (!file_count(filp)) {
printk(KERN_ERR "VFS: Close: file count is 0\n");
return 0;
}
if (filp->f_op && filp->f_op->flush)
retval = filp->f_op->flush(filp, id);
dnotify_flush(filp, id);
locks_remove_posix(filp, id);
fput(filp);
return retval;
}
EXPORT_SYMBOL(filp_close);
/*
* Careful here! We test whether the file pointer is NULL before
* releasing the fd. This ensures that one clone task can't release
* an fd while another clone is opening it.
*/
asmlinkage long sys_close(unsigned int fd)
{
struct file * filp;
struct files_struct *files = current->files;
struct fdtable *fdt;
2006-09-29 09:00:13 +00:00
int retval;
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
if (fd >= fdt->max_fds)
goto out_unlock;
filp = fdt->fd[fd];
if (!filp)
goto out_unlock;
rcu_assign_pointer(fdt->fd[fd], NULL);
FD_CLR(fd, fdt->close_on_exec);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
2006-09-29 09:00:13 +00:00
retval = filp_close(filp, files);
/* can't restart close syscall because file table entry was cleared */
if (unlikely(retval == -ERESTARTSYS ||
retval == -ERESTARTNOINTR ||
retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK))
retval = -EINTR;
return retval;
out_unlock:
spin_unlock(&files->file_lock);
return -EBADF;
}
EXPORT_SYMBOL(sys_close);
/*
* This routine simulates a hangup on the tty, to arrange that users
* are given clean terminals at login time.
*/
asmlinkage long sys_vhangup(void)
{
if (capable(CAP_SYS_TTY_CONFIG)) {
tty_vhangup_self();
return 0;
}
return -EPERM;
}
/*
* Called when an inode is about to be open.
* We use this to disallow opening large files on 32bit systems if
* the caller didn't specify O_LARGEFILE. On 64bit systems we force
* on this flag in sys_open.
*/
int generic_file_open(struct inode * inode, struct file * filp)
{
if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
return -EOVERFLOW;
return 0;
}
EXPORT_SYMBOL(generic_file_open);
/*
* This is used by subsystems that don't want seekable
* file descriptors
*/
int nonseekable_open(struct inode *inode, struct file *filp)
{
filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
return 0;
}
EXPORT_SYMBOL(nonseekable_open);