linux-stable/fs/open.c

1144 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/fsnotify.h>
#include <linux/module.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>
[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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.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>
#include <linux/fs_struct.h>
#include <linux/ima.h>
#include <linux/dnotify.h>
#include "internal.h"
int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
struct file *filp)
{
int ret;
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 */
ret = should_remove_suid(dentry);
if (ret)
newattrs.ia_valid |= ret | ATTR_FORCE;
mutex_lock(&dentry->d_inode->i_mutex);
ret = notify_change(dentry, &newattrs);
mutex_unlock(&dentry->d_inode->i_mutex);
return ret;
}
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, O_WRONLY);
if (error)
goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error)
error = security_path_truncate(&path);
if (!error)
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;
}
SYSCALL_DEFINE2(truncate, const char __user *, path, long, length)
{
return do_sys_truncate(path, 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)
error = security_path_truncate(&file->f_path);
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;
}
SYSCALL_DEFINE2(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
SYSCALL_DEFINE(truncate64)(const char __user * path, loff_t length)
{
return do_sys_truncate(path, length);
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_truncate64(long path, loff_t length)
{
return SYSC_truncate64((const char __user *) path, length);
}
SYSCALL_ALIAS(sys_truncate64, SyS_truncate64);
#endif
SYSCALL_DEFINE(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;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_ftruncate64(long fd, loff_t length)
{
return SYSC_ftruncate64((unsigned int) fd, length);
}
SYSCALL_ALIAS(sys_ftruncate64, SyS_ftruncate64);
#endif
#endif /* BITS_PER_LONG == 32 */
int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
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
{
struct inode *inode = file->f_path.dentry->d_inode;
long ret;
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
if (offset < 0 || len <= 0)
return -EINVAL;
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
/* Return error if mode is not supported */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
return -EOPNOTSUPP;
/* Punch hole must have keep size set */
if ((mode & FALLOC_FL_PUNCH_HOLE) &&
!(mode & FALLOC_FL_KEEP_SIZE))
return -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
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
/* It's not possible punch hole on append only file */
if (mode & FALLOC_FL_PUNCH_HOLE && IS_APPEND(inode))
return -EPERM;
if (IS_IMMUTABLE(inode))
return -EPERM;
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
/*
* Revalidate the write permissions, in case security policy has
* changed since the files were opened.
*/
ret = security_file_permission(file, MAY_WRITE);
if (ret)
return ret;
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
if (S_ISFIFO(inode->i_mode))
return -ESPIPE;
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
/*
* Let individual file system decide if it supports preallocation
* for directories or not.
*/
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
return -ENODEV;
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
/* Check for wrap through zero too */
if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
return -EFBIG;
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
if (!file->f_op->fallocate)
return -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
return file->f_op->fallocate(file, mode, offset, len);
}
SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len)
{
struct file *file;
int error = -EBADF;
file = fget(fd);
if (file) {
error = do_fallocate(file, mode, offset, len);
fput(file);
}
return error;
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
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_fallocate(long fd, long mode, loff_t offset, loff_t len)
{
return SYSC_fallocate((int)fd, (int)mode, offset, len);
}
SYSCALL_ALIAS(sys_fallocate, SyS_fallocate);
#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
/*
* 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.
*/
SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
{
CRED: Inaugurate COW credentials Inaugurate copy-on-write credentials management. This uses RCU to manage the credentials pointer in the task_struct with respect to accesses by other tasks. A process may only modify its own credentials, and so does not need locking to access or modify its own credentials. A mutex (cred_replace_mutex) is added to the task_struct to control the effect of PTRACE_ATTACHED on credential calculations, particularly with respect to execve(). With this patch, the contents of an active credentials struct may not be changed directly; rather a new set of credentials must be prepared, modified and committed using something like the following sequence of events: struct cred *new = prepare_creds(); int ret = blah(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); There are some exceptions to this rule: the keyrings pointed to by the active credentials may be instantiated - keyrings violate the COW rule as managing COW keyrings is tricky, given that it is possible for a task to directly alter the keys in a keyring in use by another task. To help enforce this, various pointers to sets of credentials, such as those in the task_struct, are declared const. The purpose of this is compile-time discouragement of altering credentials through those pointers. Once a set of credentials has been made public through one of these pointers, it may not be modified, except under special circumstances: (1) Its reference count may incremented and decremented. (2) The keyrings to which it points may be modified, but not replaced. The only safe way to modify anything else is to create a replacement and commit using the functions described in Documentation/credentials.txt (which will be added by a later patch). This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). This now prepares and commits credentials in various places in the security code rather than altering the current creds directly. (2) Temporary credential overrides. do_coredump() and sys_faccessat() now prepare their own credentials and temporarily override the ones currently on the acting thread, whilst preventing interference from other threads by holding cred_replace_mutex on the thread being dumped. This will be replaced in a future patch by something that hands down the credentials directly to the functions being called, rather than altering the task's objective credentials. (3) LSM interface. A number of functions have been changed, added or removed: (*) security_capset_check(), ->capset_check() (*) security_capset_set(), ->capset_set() Removed in favour of security_capset(). (*) security_capset(), ->capset() New. This is passed a pointer to the new creds, a pointer to the old creds and the proposed capability sets. It should fill in the new creds or return an error. All pointers, barring the pointer to the new creds, are now const. (*) security_bprm_apply_creds(), ->bprm_apply_creds() Changed; now returns a value, which will cause the process to be killed if it's an error. (*) security_task_alloc(), ->task_alloc_security() Removed in favour of security_prepare_creds(). (*) security_cred_free(), ->cred_free() New. Free security data attached to cred->security. (*) security_prepare_creds(), ->cred_prepare() New. Duplicate any security data attached to cred->security. (*) security_commit_creds(), ->cred_commit() New. Apply any security effects for the upcoming installation of new security by commit_creds(). (*) security_task_post_setuid(), ->task_post_setuid() Removed in favour of security_task_fix_setuid(). (*) security_task_fix_setuid(), ->task_fix_setuid() Fix up the proposed new credentials for setuid(). This is used by cap_set_fix_setuid() to implicitly adjust capabilities in line with setuid() changes. Changes are made to the new credentials, rather than the task itself as in security_task_post_setuid(). (*) security_task_reparent_to_init(), ->task_reparent_to_init() Removed. Instead the task being reparented to init is referred directly to init's credentials. NOTE! This results in the loss of some state: SELinux's osid no longer records the sid of the thread that forked it. (*) security_key_alloc(), ->key_alloc() (*) security_key_permission(), ->key_permission() Changed. These now take cred pointers rather than task pointers to refer to the security context. (4) sys_capset(). This has been simplified and uses less locking. The LSM functions it calls have been merged. (5) reparent_to_kthreadd(). This gives the current thread the same credentials as init by simply using commit_thread() to point that way. (6) __sigqueue_alloc() and switch_uid() __sigqueue_alloc() can't stop the target task from changing its creds beneath it, so this function gets a reference to the currently applicable user_struct which it then passes into the sigqueue struct it returns if successful. switch_uid() is now called from commit_creds(), and possibly should be folded into that. commit_creds() should take care of protecting __sigqueue_alloc(). (7) [sg]et[ug]id() and co and [sg]et_current_groups. The set functions now all use prepare_creds(), commit_creds() and abort_creds() to build and check a new set of credentials before applying it. security_task_set[ug]id() is called inside the prepared section. This guarantees that nothing else will affect the creds until we've finished. The calling of set_dumpable() has been moved into commit_creds(). Much of the functionality of set_user() has been moved into commit_creds(). The get functions all simply access the data directly. (8) security_task_prctl() and cap_task_prctl(). security_task_prctl() has been modified to return -ENOSYS if it doesn't want to handle a function, or otherwise return the return value directly rather than through an argument. Additionally, cap_task_prctl() now prepares a new set of credentials, even if it doesn't end up using it. (9) Keyrings. A number of changes have been made to the keyrings code: (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have all been dropped and built in to the credentials functions directly. They may want separating out again later. (b) key_alloc() and search_process_keyrings() now take a cred pointer rather than a task pointer to specify the security context. (c) copy_creds() gives a new thread within the same thread group a new thread keyring if its parent had one, otherwise it discards the thread keyring. (d) The authorisation key now points directly to the credentials to extend the search into rather pointing to the task that carries them. (e) Installing thread, process or session keyrings causes a new set of credentials to be created, even though it's not strictly necessary for process or session keyrings (they're shared). (10) Usermode helper. The usermode helper code now carries a cred struct pointer in its subprocess_info struct instead of a new session keyring pointer. This set of credentials is derived from init_cred and installed on the new process after it has been cloned. call_usermodehelper_setup() allocates the new credentials and call_usermodehelper_freeinfo() discards them if they haven't been used. A special cred function (prepare_usermodeinfo_creds()) is provided specifically for call_usermodehelper_setup() to call. call_usermodehelper_setkeys() adjusts the credentials to sport the supplied keyring as the new session keyring. (11) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) selinux_setprocattr() no longer does its check for whether the current ptracer can access processes with the new SID inside the lock that covers getting the ptracer's SID. Whilst this lock ensures that the check is done with the ptracer pinned, the result is only valid until the lock is released, so there's no point doing it inside the lock. (12) is_single_threaded(). This function has been extracted from selinux_setprocattr() and put into a file of its own in the lib/ directory as join_session_keyring() now wants to use it too. The code in SELinux just checked to see whether a task shared mm_structs with other tasks (CLONE_VM), but that isn't good enough. We really want to know if they're part of the same thread group (CLONE_THREAD). (13) nfsd. The NFS server daemon now has to use the COW credentials to set the credentials it is going to use. It really needs to pass the credentials down to the functions it calls, but it can't do that until other patches in this series have been applied. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-13 23:39:23 +00:00
const struct cred *old_cred;
struct cred *override_cred;
struct path path;
struct inode *inode;
int res;
if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */
return -EINVAL;
CRED: Inaugurate COW credentials Inaugurate copy-on-write credentials management. This uses RCU to manage the credentials pointer in the task_struct with respect to accesses by other tasks. A process may only modify its own credentials, and so does not need locking to access or modify its own credentials. A mutex (cred_replace_mutex) is added to the task_struct to control the effect of PTRACE_ATTACHED on credential calculations, particularly with respect to execve(). With this patch, the contents of an active credentials struct may not be changed directly; rather a new set of credentials must be prepared, modified and committed using something like the following sequence of events: struct cred *new = prepare_creds(); int ret = blah(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); There are some exceptions to this rule: the keyrings pointed to by the active credentials may be instantiated - keyrings violate the COW rule as managing COW keyrings is tricky, given that it is possible for a task to directly alter the keys in a keyring in use by another task. To help enforce this, various pointers to sets of credentials, such as those in the task_struct, are declared const. The purpose of this is compile-time discouragement of altering credentials through those pointers. Once a set of credentials has been made public through one of these pointers, it may not be modified, except under special circumstances: (1) Its reference count may incremented and decremented. (2) The keyrings to which it points may be modified, but not replaced. The only safe way to modify anything else is to create a replacement and commit using the functions described in Documentation/credentials.txt (which will be added by a later patch). This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). This now prepares and commits credentials in various places in the security code rather than altering the current creds directly. (2) Temporary credential overrides. do_coredump() and sys_faccessat() now prepare their own credentials and temporarily override the ones currently on the acting thread, whilst preventing interference from other threads by holding cred_replace_mutex on the thread being dumped. This will be replaced in a future patch by something that hands down the credentials directly to the functions being called, rather than altering the task's objective credentials. (3) LSM interface. A number of functions have been changed, added or removed: (*) security_capset_check(), ->capset_check() (*) security_capset_set(), ->capset_set() Removed in favour of security_capset(). (*) security_capset(), ->capset() New. This is passed a pointer to the new creds, a pointer to the old creds and the proposed capability sets. It should fill in the new creds or return an error. All pointers, barring the pointer to the new creds, are now const. (*) security_bprm_apply_creds(), ->bprm_apply_creds() Changed; now returns a value, which will cause the process to be killed if it's an error. (*) security_task_alloc(), ->task_alloc_security() Removed in favour of security_prepare_creds(). (*) security_cred_free(), ->cred_free() New. Free security data attached to cred->security. (*) security_prepare_creds(), ->cred_prepare() New. Duplicate any security data attached to cred->security. (*) security_commit_creds(), ->cred_commit() New. Apply any security effects for the upcoming installation of new security by commit_creds(). (*) security_task_post_setuid(), ->task_post_setuid() Removed in favour of security_task_fix_setuid(). (*) security_task_fix_setuid(), ->task_fix_setuid() Fix up the proposed new credentials for setuid(). This is used by cap_set_fix_setuid() to implicitly adjust capabilities in line with setuid() changes. Changes are made to the new credentials, rather than the task itself as in security_task_post_setuid(). (*) security_task_reparent_to_init(), ->task_reparent_to_init() Removed. Instead the task being reparented to init is referred directly to init's credentials. NOTE! This results in the loss of some state: SELinux's osid no longer records the sid of the thread that forked it. (*) security_key_alloc(), ->key_alloc() (*) security_key_permission(), ->key_permission() Changed. These now take cred pointers rather than task pointers to refer to the security context. (4) sys_capset(). This has been simplified and uses less locking. The LSM functions it calls have been merged. (5) reparent_to_kthreadd(). This gives the current thread the same credentials as init by simply using commit_thread() to point that way. (6) __sigqueue_alloc() and switch_uid() __sigqueue_alloc() can't stop the target task from changing its creds beneath it, so this function gets a reference to the currently applicable user_struct which it then passes into the sigqueue struct it returns if successful. switch_uid() is now called from commit_creds(), and possibly should be folded into that. commit_creds() should take care of protecting __sigqueue_alloc(). (7) [sg]et[ug]id() and co and [sg]et_current_groups. The set functions now all use prepare_creds(), commit_creds() and abort_creds() to build and check a new set of credentials before applying it. security_task_set[ug]id() is called inside the prepared section. This guarantees that nothing else will affect the creds until we've finished. The calling of set_dumpable() has been moved into commit_creds(). Much of the functionality of set_user() has been moved into commit_creds(). The get functions all simply access the data directly. (8) security_task_prctl() and cap_task_prctl(). security_task_prctl() has been modified to return -ENOSYS if it doesn't want to handle a function, or otherwise return the return value directly rather than through an argument. Additionally, cap_task_prctl() now prepares a new set of credentials, even if it doesn't end up using it. (9) Keyrings. A number of changes have been made to the keyrings code: (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have all been dropped and built in to the credentials functions directly. They may want separating out again later. (b) key_alloc() and search_process_keyrings() now take a cred pointer rather than a task pointer to specify the security context. (c) copy_creds() gives a new thread within the same thread group a new thread keyring if its parent had one, otherwise it discards the thread keyring. (d) The authorisation key now points directly to the credentials to extend the search into rather pointing to the task that carries them. (e) Installing thread, process or session keyrings causes a new set of credentials to be created, even though it's not strictly necessary for process or session keyrings (they're shared). (10) Usermode helper. The usermode helper code now carries a cred struct pointer in its subprocess_info struct instead of a new session keyring pointer. This set of credentials is derived from init_cred and installed on the new process after it has been cloned. call_usermodehelper_setup() allocates the new credentials and call_usermodehelper_freeinfo() discards them if they haven't been used. A special cred function (prepare_usermodeinfo_creds()) is provided specifically for call_usermodehelper_setup() to call. call_usermodehelper_setkeys() adjusts the credentials to sport the supplied keyring as the new session keyring. (11) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) selinux_setprocattr() no longer does its check for whether the current ptracer can access processes with the new SID inside the lock that covers getting the ptracer's SID. Whilst this lock ensures that the check is done with the ptracer pinned, the result is only valid until the lock is released, so there's no point doing it inside the lock. (12) is_single_threaded(). This function has been extracted from selinux_setprocattr() and put into a file of its own in the lib/ directory as join_session_keyring() now wants to use it too. The code in SELinux just checked to see whether a task shared mm_structs with other tasks (CLONE_VM), but that isn't good enough. We really want to know if they're part of the same thread group (CLONE_THREAD). (13) nfsd. The NFS server daemon now has to use the COW credentials to set the credentials it is going to use. It really needs to pass the credentials down to the functions it calls, but it can't do that until other patches in this series have been applied. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-13 23:39:23 +00:00
override_cred = prepare_creds();
if (!override_cred)
return -ENOMEM;
CRED: Inaugurate COW credentials Inaugurate copy-on-write credentials management. This uses RCU to manage the credentials pointer in the task_struct with respect to accesses by other tasks. A process may only modify its own credentials, and so does not need locking to access or modify its own credentials. A mutex (cred_replace_mutex) is added to the task_struct to control the effect of PTRACE_ATTACHED on credential calculations, particularly with respect to execve(). With this patch, the contents of an active credentials struct may not be changed directly; rather a new set of credentials must be prepared, modified and committed using something like the following sequence of events: struct cred *new = prepare_creds(); int ret = blah(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); There are some exceptions to this rule: the keyrings pointed to by the active credentials may be instantiated - keyrings violate the COW rule as managing COW keyrings is tricky, given that it is possible for a task to directly alter the keys in a keyring in use by another task. To help enforce this, various pointers to sets of credentials, such as those in the task_struct, are declared const. The purpose of this is compile-time discouragement of altering credentials through those pointers. Once a set of credentials has been made public through one of these pointers, it may not be modified, except under special circumstances: (1) Its reference count may incremented and decremented. (2) The keyrings to which it points may be modified, but not replaced. The only safe way to modify anything else is to create a replacement and commit using the functions described in Documentation/credentials.txt (which will be added by a later patch). This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). This now prepares and commits credentials in various places in the security code rather than altering the current creds directly. (2) Temporary credential overrides. do_coredump() and sys_faccessat() now prepare their own credentials and temporarily override the ones currently on the acting thread, whilst preventing interference from other threads by holding cred_replace_mutex on the thread being dumped. This will be replaced in a future patch by something that hands down the credentials directly to the functions being called, rather than altering the task's objective credentials. (3) LSM interface. A number of functions have been changed, added or removed: (*) security_capset_check(), ->capset_check() (*) security_capset_set(), ->capset_set() Removed in favour of security_capset(). (*) security_capset(), ->capset() New. This is passed a pointer to the new creds, a pointer to the old creds and the proposed capability sets. It should fill in the new creds or return an error. All pointers, barring the pointer to the new creds, are now const. (*) security_bprm_apply_creds(), ->bprm_apply_creds() Changed; now returns a value, which will cause the process to be killed if it's an error. (*) security_task_alloc(), ->task_alloc_security() Removed in favour of security_prepare_creds(). (*) security_cred_free(), ->cred_free() New. Free security data attached to cred->security. (*) security_prepare_creds(), ->cred_prepare() New. Duplicate any security data attached to cred->security. (*) security_commit_creds(), ->cred_commit() New. Apply any security effects for the upcoming installation of new security by commit_creds(). (*) security_task_post_setuid(), ->task_post_setuid() Removed in favour of security_task_fix_setuid(). (*) security_task_fix_setuid(), ->task_fix_setuid() Fix up the proposed new credentials for setuid(). This is used by cap_set_fix_setuid() to implicitly adjust capabilities in line with setuid() changes. Changes are made to the new credentials, rather than the task itself as in security_task_post_setuid(). (*) security_task_reparent_to_init(), ->task_reparent_to_init() Removed. Instead the task being reparented to init is referred directly to init's credentials. NOTE! This results in the loss of some state: SELinux's osid no longer records the sid of the thread that forked it. (*) security_key_alloc(), ->key_alloc() (*) security_key_permission(), ->key_permission() Changed. These now take cred pointers rather than task pointers to refer to the security context. (4) sys_capset(). This has been simplified and uses less locking. The LSM functions it calls have been merged. (5) reparent_to_kthreadd(). This gives the current thread the same credentials as init by simply using commit_thread() to point that way. (6) __sigqueue_alloc() and switch_uid() __sigqueue_alloc() can't stop the target task from changing its creds beneath it, so this function gets a reference to the currently applicable user_struct which it then passes into the sigqueue struct it returns if successful. switch_uid() is now called from commit_creds(), and possibly should be folded into that. commit_creds() should take care of protecting __sigqueue_alloc(). (7) [sg]et[ug]id() and co and [sg]et_current_groups. The set functions now all use prepare_creds(), commit_creds() and abort_creds() to build and check a new set of credentials before applying it. security_task_set[ug]id() is called inside the prepared section. This guarantees that nothing else will affect the creds until we've finished. The calling of set_dumpable() has been moved into commit_creds(). Much of the functionality of set_user() has been moved into commit_creds(). The get functions all simply access the data directly. (8) security_task_prctl() and cap_task_prctl(). security_task_prctl() has been modified to return -ENOSYS if it doesn't want to handle a function, or otherwise return the return value directly rather than through an argument. Additionally, cap_task_prctl() now prepares a new set of credentials, even if it doesn't end up using it. (9) Keyrings. A number of changes have been made to the keyrings code: (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have all been dropped and built in to the credentials functions directly. They may want separating out again later. (b) key_alloc() and search_process_keyrings() now take a cred pointer rather than a task pointer to specify the security context. (c) copy_creds() gives a new thread within the same thread group a new thread keyring if its parent had one, otherwise it discards the thread keyring. (d) The authorisation key now points directly to the credentials to extend the search into rather pointing to the task that carries them. (e) Installing thread, process or session keyrings causes a new set of credentials to be created, even though it's not strictly necessary for process or session keyrings (they're shared). (10) Usermode helper. The usermode helper code now carries a cred struct pointer in its subprocess_info struct instead of a new session keyring pointer. This set of credentials is derived from init_cred and installed on the new process after it has been cloned. call_usermodehelper_setup() allocates the new credentials and call_usermodehelper_freeinfo() discards them if they haven't been used. A special cred function (prepare_usermodeinfo_creds()) is provided specifically for call_usermodehelper_setup() to call. call_usermodehelper_setkeys() adjusts the credentials to sport the supplied keyring as the new session keyring. (11) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) selinux_setprocattr() no longer does its check for whether the current ptracer can access processes with the new SID inside the lock that covers getting the ptracer's SID. Whilst this lock ensures that the check is done with the ptracer pinned, the result is only valid until the lock is released, so there's no point doing it inside the lock. (12) is_single_threaded(). This function has been extracted from selinux_setprocattr() and put into a file of its own in the lib/ directory as join_session_keyring() now wants to use it too. The code in SELinux just checked to see whether a task shared mm_structs with other tasks (CLONE_VM), but that isn't good enough. We really want to know if they're part of the same thread group (CLONE_THREAD). (13) nfsd. The NFS server daemon now has to use the COW credentials to set the credentials it is going to use. It really needs to pass the credentials down to the functions it calls, but it can't do that until other patches in this series have been applied. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-13 23:39:23 +00:00
override_cred->fsuid = override_cred->uid;
override_cred->fsgid = override_cred->gid;
if (!issecure(SECURE_NO_SETUID_FIXUP)) {
/* Clear the capabilities if we switch to a non-root user */
CRED: Inaugurate COW credentials Inaugurate copy-on-write credentials management. This uses RCU to manage the credentials pointer in the task_struct with respect to accesses by other tasks. A process may only modify its own credentials, and so does not need locking to access or modify its own credentials. A mutex (cred_replace_mutex) is added to the task_struct to control the effect of PTRACE_ATTACHED on credential calculations, particularly with respect to execve(). With this patch, the contents of an active credentials struct may not be changed directly; rather a new set of credentials must be prepared, modified and committed using something like the following sequence of events: struct cred *new = prepare_creds(); int ret = blah(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); There are some exceptions to this rule: the keyrings pointed to by the active credentials may be instantiated - keyrings violate the COW rule as managing COW keyrings is tricky, given that it is possible for a task to directly alter the keys in a keyring in use by another task. To help enforce this, various pointers to sets of credentials, such as those in the task_struct, are declared const. The purpose of this is compile-time discouragement of altering credentials through those pointers. Once a set of credentials has been made public through one of these pointers, it may not be modified, except under special circumstances: (1) Its reference count may incremented and decremented. (2) The keyrings to which it points may be modified, but not replaced. The only safe way to modify anything else is to create a replacement and commit using the functions described in Documentation/credentials.txt (which will be added by a later patch). This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). This now prepares and commits credentials in various places in the security code rather than altering the current creds directly. (2) Temporary credential overrides. do_coredump() and sys_faccessat() now prepare their own credentials and temporarily override the ones currently on the acting thread, whilst preventing interference from other threads by holding cred_replace_mutex on the thread being dumped. This will be replaced in a future patch by something that hands down the credentials directly to the functions being called, rather than altering the task's objective credentials. (3) LSM interface. A number of functions have been changed, added or removed: (*) security_capset_check(), ->capset_check() (*) security_capset_set(), ->capset_set() Removed in favour of security_capset(). (*) security_capset(), ->capset() New. This is passed a pointer to the new creds, a pointer to the old creds and the proposed capability sets. It should fill in the new creds or return an error. All pointers, barring the pointer to the new creds, are now const. (*) security_bprm_apply_creds(), ->bprm_apply_creds() Changed; now returns a value, which will cause the process to be killed if it's an error. (*) security_task_alloc(), ->task_alloc_security() Removed in favour of security_prepare_creds(). (*) security_cred_free(), ->cred_free() New. Free security data attached to cred->security. (*) security_prepare_creds(), ->cred_prepare() New. Duplicate any security data attached to cred->security. (*) security_commit_creds(), ->cred_commit() New. Apply any security effects for the upcoming installation of new security by commit_creds(). (*) security_task_post_setuid(), ->task_post_setuid() Removed in favour of security_task_fix_setuid(). (*) security_task_fix_setuid(), ->task_fix_setuid() Fix up the proposed new credentials for setuid(). This is used by cap_set_fix_setuid() to implicitly adjust capabilities in line with setuid() changes. Changes are made to the new credentials, rather than the task itself as in security_task_post_setuid(). (*) security_task_reparent_to_init(), ->task_reparent_to_init() Removed. Instead the task being reparented to init is referred directly to init's credentials. NOTE! This results in the loss of some state: SELinux's osid no longer records the sid of the thread that forked it. (*) security_key_alloc(), ->key_alloc() (*) security_key_permission(), ->key_permission() Changed. These now take cred pointers rather than task pointers to refer to the security context. (4) sys_capset(). This has been simplified and uses less locking. The LSM functions it calls have been merged. (5) reparent_to_kthreadd(). This gives the current thread the same credentials as init by simply using commit_thread() to point that way. (6) __sigqueue_alloc() and switch_uid() __sigqueue_alloc() can't stop the target task from changing its creds beneath it, so this function gets a reference to the currently applicable user_struct which it then passes into the sigqueue struct it returns if successful. switch_uid() is now called from commit_creds(), and possibly should be folded into that. commit_creds() should take care of protecting __sigqueue_alloc(). (7) [sg]et[ug]id() and co and [sg]et_current_groups. The set functions now all use prepare_creds(), commit_creds() and abort_creds() to build and check a new set of credentials before applying it. security_task_set[ug]id() is called inside the prepared section. This guarantees that nothing else will affect the creds until we've finished. The calling of set_dumpable() has been moved into commit_creds(). Much of the functionality of set_user() has been moved into commit_creds(). The get functions all simply access the data directly. (8) security_task_prctl() and cap_task_prctl(). security_task_prctl() has been modified to return -ENOSYS if it doesn't want to handle a function, or otherwise return the return value directly rather than through an argument. Additionally, cap_task_prctl() now prepares a new set of credentials, even if it doesn't end up using it. (9) Keyrings. A number of changes have been made to the keyrings code: (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have all been dropped and built in to the credentials functions directly. They may want separating out again later. (b) key_alloc() and search_process_keyrings() now take a cred pointer rather than a task pointer to specify the security context. (c) copy_creds() gives a new thread within the same thread group a new thread keyring if its parent had one, otherwise it discards the thread keyring. (d) The authorisation key now points directly to the credentials to extend the search into rather pointing to the task that carries them. (e) Installing thread, process or session keyrings causes a new set of credentials to be created, even though it's not strictly necessary for process or session keyrings (they're shared). (10) Usermode helper. The usermode helper code now carries a cred struct pointer in its subprocess_info struct instead of a new session keyring pointer. This set of credentials is derived from init_cred and installed on the new process after it has been cloned. call_usermodehelper_setup() allocates the new credentials and call_usermodehelper_freeinfo() discards them if they haven't been used. A special cred function (prepare_usermodeinfo_creds()) is provided specifically for call_usermodehelper_setup() to call. call_usermodehelper_setkeys() adjusts the credentials to sport the supplied keyring as the new session keyring. (11) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) selinux_setprocattr() no longer does its check for whether the current ptracer can access processes with the new SID inside the lock that covers getting the ptracer's SID. Whilst this lock ensures that the check is done with the ptracer pinned, the result is only valid until the lock is released, so there's no point doing it inside the lock. (12) is_single_threaded(). This function has been extracted from selinux_setprocattr() and put into a file of its own in the lib/ directory as join_session_keyring() now wants to use it too. The code in SELinux just checked to see whether a task shared mm_structs with other tasks (CLONE_VM), but that isn't good enough. We really want to know if they're part of the same thread group (CLONE_THREAD). (13) nfsd. The NFS server daemon now has to use the COW credentials to set the credentials it is going to use. It really needs to pass the credentials down to the functions it calls, but it can't do that until other patches in this series have been applied. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-13 23:39:23 +00:00
if (override_cred->uid)
cap_clear(override_cred->cap_effective);
else
CRED: Inaugurate COW credentials Inaugurate copy-on-write credentials management. This uses RCU to manage the credentials pointer in the task_struct with respect to accesses by other tasks. A process may only modify its own credentials, and so does not need locking to access or modify its own credentials. A mutex (cred_replace_mutex) is added to the task_struct to control the effect of PTRACE_ATTACHED on credential calculations, particularly with respect to execve(). With this patch, the contents of an active credentials struct may not be changed directly; rather a new set of credentials must be prepared, modified and committed using something like the following sequence of events: struct cred *new = prepare_creds(); int ret = blah(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); There are some exceptions to this rule: the keyrings pointed to by the active credentials may be instantiated - keyrings violate the COW rule as managing COW keyrings is tricky, given that it is possible for a task to directly alter the keys in a keyring in use by another task. To help enforce this, various pointers to sets of credentials, such as those in the task_struct, are declared const. The purpose of this is compile-time discouragement of altering credentials through those pointers. Once a set of credentials has been made public through one of these pointers, it may not be modified, except under special circumstances: (1) Its reference count may incremented and decremented. (2) The keyrings to which it points may be modified, but not replaced. The only safe way to modify anything else is to create a replacement and commit using the functions described in Documentation/credentials.txt (which will be added by a later patch). This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). This now prepares and commits credentials in various places in the security code rather than altering the current creds directly. (2) Temporary credential overrides. do_coredump() and sys_faccessat() now prepare their own credentials and temporarily override the ones currently on the acting thread, whilst preventing interference from other threads by holding cred_replace_mutex on the thread being dumped. This will be replaced in a future patch by something that hands down the credentials directly to the functions being called, rather than altering the task's objective credentials. (3) LSM interface. A number of functions have been changed, added or removed: (*) security_capset_check(), ->capset_check() (*) security_capset_set(), ->capset_set() Removed in favour of security_capset(). (*) security_capset(), ->capset() New. This is passed a pointer to the new creds, a pointer to the old creds and the proposed capability sets. It should fill in the new creds or return an error. All pointers, barring the pointer to the new creds, are now const. (*) security_bprm_apply_creds(), ->bprm_apply_creds() Changed; now returns a value, which will cause the process to be killed if it's an error. (*) security_task_alloc(), ->task_alloc_security() Removed in favour of security_prepare_creds(). (*) security_cred_free(), ->cred_free() New. Free security data attached to cred->security. (*) security_prepare_creds(), ->cred_prepare() New. Duplicate any security data attached to cred->security. (*) security_commit_creds(), ->cred_commit() New. Apply any security effects for the upcoming installation of new security by commit_creds(). (*) security_task_post_setuid(), ->task_post_setuid() Removed in favour of security_task_fix_setuid(). (*) security_task_fix_setuid(), ->task_fix_setuid() Fix up the proposed new credentials for setuid(). This is used by cap_set_fix_setuid() to implicitly adjust capabilities in line with setuid() changes. Changes are made to the new credentials, rather than the task itself as in security_task_post_setuid(). (*) security_task_reparent_to_init(), ->task_reparent_to_init() Removed. Instead the task being reparented to init is referred directly to init's credentials. NOTE! This results in the loss of some state: SELinux's osid no longer records the sid of the thread that forked it. (*) security_key_alloc(), ->key_alloc() (*) security_key_permission(), ->key_permission() Changed. These now take cred pointers rather than task pointers to refer to the security context. (4) sys_capset(). This has been simplified and uses less locking. The LSM functions it calls have been merged. (5) reparent_to_kthreadd(). This gives the current thread the same credentials as init by simply using commit_thread() to point that way. (6) __sigqueue_alloc() and switch_uid() __sigqueue_alloc() can't stop the target task from changing its creds beneath it, so this function gets a reference to the currently applicable user_struct which it then passes into the sigqueue struct it returns if successful. switch_uid() is now called from commit_creds(), and possibly should be folded into that. commit_creds() should take care of protecting __sigqueue_alloc(). (7) [sg]et[ug]id() and co and [sg]et_current_groups. The set functions now all use prepare_creds(), commit_creds() and abort_creds() to build and check a new set of credentials before applying it. security_task_set[ug]id() is called inside the prepared section. This guarantees that nothing else will affect the creds until we've finished. The calling of set_dumpable() has been moved into commit_creds(). Much of the functionality of set_user() has been moved into commit_creds(). The get functions all simply access the data directly. (8) security_task_prctl() and cap_task_prctl(). security_task_prctl() has been modified to return -ENOSYS if it doesn't want to handle a function, or otherwise return the return value directly rather than through an argument. Additionally, cap_task_prctl() now prepares a new set of credentials, even if it doesn't end up using it. (9) Keyrings. A number of changes have been made to the keyrings code: (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have all been dropped and built in to the credentials functions directly. They may want separating out again later. (b) key_alloc() and search_process_keyrings() now take a cred pointer rather than a task pointer to specify the security context. (c) copy_creds() gives a new thread within the same thread group a new thread keyring if its parent had one, otherwise it discards the thread keyring. (d) The authorisation key now points directly to the credentials to extend the search into rather pointing to the task that carries them. (e) Installing thread, process or session keyrings causes a new set of credentials to be created, even though it's not strictly necessary for process or session keyrings (they're shared). (10) Usermode helper. The usermode helper code now carries a cred struct pointer in its subprocess_info struct instead of a new session keyring pointer. This set of credentials is derived from init_cred and installed on the new process after it has been cloned. call_usermodehelper_setup() allocates the new credentials and call_usermodehelper_freeinfo() discards them if they haven't been used. A special cred function (prepare_usermodeinfo_creds()) is provided specifically for call_usermodehelper_setup() to call. call_usermodehelper_setkeys() adjusts the credentials to sport the supplied keyring as the new session keyring. (11) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) selinux_setprocattr() no longer does its check for whether the current ptracer can access processes with the new SID inside the lock that covers getting the ptracer's SID. Whilst this lock ensures that the check is done with the ptracer pinned, the result is only valid until the lock is released, so there's no point doing it inside the lock. (12) is_single_threaded(). This function has been extracted from selinux_setprocattr() and put into a file of its own in the lib/ directory as join_session_keyring() now wants to use it too. The code in SELinux just checked to see whether a task shared mm_structs with other tasks (CLONE_VM), but that isn't good enough. We really want to know if they're part of the same thread group (CLONE_THREAD). (13) nfsd. The NFS server daemon now has to use the COW credentials to set the credentials it is going to use. It really needs to pass the credentials down to the functions it calls, but it can't do that until other patches in this series have been applied. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-13 23:39:23 +00:00
override_cred->cap_effective =
override_cred->cap_permitted;
}
CRED: Inaugurate COW credentials Inaugurate copy-on-write credentials management. This uses RCU to manage the credentials pointer in the task_struct with respect to accesses by other tasks. A process may only modify its own credentials, and so does not need locking to access or modify its own credentials. A mutex (cred_replace_mutex) is added to the task_struct to control the effect of PTRACE_ATTACHED on credential calculations, particularly with respect to execve(). With this patch, the contents of an active credentials struct may not be changed directly; rather a new set of credentials must be prepared, modified and committed using something like the following sequence of events: struct cred *new = prepare_creds(); int ret = blah(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); There are some exceptions to this rule: the keyrings pointed to by the active credentials may be instantiated - keyrings violate the COW rule as managing COW keyrings is tricky, given that it is possible for a task to directly alter the keys in a keyring in use by another task. To help enforce this, various pointers to sets of credentials, such as those in the task_struct, are declared const. The purpose of this is compile-time discouragement of altering credentials through those pointers. Once a set of credentials has been made public through one of these pointers, it may not be modified, except under special circumstances: (1) Its reference count may incremented and decremented. (2) The keyrings to which it points may be modified, but not replaced. The only safe way to modify anything else is to create a replacement and commit using the functions described in Documentation/credentials.txt (which will be added by a later patch). This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). This now prepares and commits credentials in various places in the security code rather than altering the current creds directly. (2) Temporary credential overrides. do_coredump() and sys_faccessat() now prepare their own credentials and temporarily override the ones currently on the acting thread, whilst preventing interference from other threads by holding cred_replace_mutex on the thread being dumped. This will be replaced in a future patch by something that hands down the credentials directly to the functions being called, rather than altering the task's objective credentials. (3) LSM interface. A number of functions have been changed, added or removed: (*) security_capset_check(), ->capset_check() (*) security_capset_set(), ->capset_set() Removed in favour of security_capset(). (*) security_capset(), ->capset() New. This is passed a pointer to the new creds, a pointer to the old creds and the proposed capability sets. It should fill in the new creds or return an error. All pointers, barring the pointer to the new creds, are now const. (*) security_bprm_apply_creds(), ->bprm_apply_creds() Changed; now returns a value, which will cause the process to be killed if it's an error. (*) security_task_alloc(), ->task_alloc_security() Removed in favour of security_prepare_creds(). (*) security_cred_free(), ->cred_free() New. Free security data attached to cred->security. (*) security_prepare_creds(), ->cred_prepare() New. Duplicate any security data attached to cred->security. (*) security_commit_creds(), ->cred_commit() New. Apply any security effects for the upcoming installation of new security by commit_creds(). (*) security_task_post_setuid(), ->task_post_setuid() Removed in favour of security_task_fix_setuid(). (*) security_task_fix_setuid(), ->task_fix_setuid() Fix up the proposed new credentials for setuid(). This is used by cap_set_fix_setuid() to implicitly adjust capabilities in line with setuid() changes. Changes are made to the new credentials, rather than the task itself as in security_task_post_setuid(). (*) security_task_reparent_to_init(), ->task_reparent_to_init() Removed. Instead the task being reparented to init is referred directly to init's credentials. NOTE! This results in the loss of some state: SELinux's osid no longer records the sid of the thread that forked it. (*) security_key_alloc(), ->key_alloc() (*) security_key_permission(), ->key_permission() Changed. These now take cred pointers rather than task pointers to refer to the security context. (4) sys_capset(). This has been simplified and uses less locking. The LSM functions it calls have been merged. (5) reparent_to_kthreadd(). This gives the current thread the same credentials as init by simply using commit_thread() to point that way. (6) __sigqueue_alloc() and switch_uid() __sigqueue_alloc() can't stop the target task from changing its creds beneath it, so this function gets a reference to the currently applicable user_struct which it then passes into the sigqueue struct it returns if successful. switch_uid() is now called from commit_creds(), and possibly should be folded into that. commit_creds() should take care of protecting __sigqueue_alloc(). (7) [sg]et[ug]id() and co and [sg]et_current_groups. The set functions now all use prepare_creds(), commit_creds() and abort_creds() to build and check a new set of credentials before applying it. security_task_set[ug]id() is called inside the prepared section. This guarantees that nothing else will affect the creds until we've finished. The calling of set_dumpable() has been moved into commit_creds(). Much of the functionality of set_user() has been moved into commit_creds(). The get functions all simply access the data directly. (8) security_task_prctl() and cap_task_prctl(). security_task_prctl() has been modified to return -ENOSYS if it doesn't want to handle a function, or otherwise return the return value directly rather than through an argument. Additionally, cap_task_prctl() now prepares a new set of credentials, even if it doesn't end up using it. (9) Keyrings. A number of changes have been made to the keyrings code: (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have all been dropped and built in to the credentials functions directly. They may want separating out again later. (b) key_alloc() and search_process_keyrings() now take a cred pointer rather than a task pointer to specify the security context. (c) copy_creds() gives a new thread within the same thread group a new thread keyring if its parent had one, otherwise it discards the thread keyring. (d) The authorisation key now points directly to the credentials to extend the search into rather pointing to the task that carries them. (e) Installing thread, process or session keyrings causes a new set of credentials to be created, even though it's not strictly necessary for process or session keyrings (they're shared). (10) Usermode helper. The usermode helper code now carries a cred struct pointer in its subprocess_info struct instead of a new session keyring pointer. This set of credentials is derived from init_cred and installed on the new process after it has been cloned. call_usermodehelper_setup() allocates the new credentials and call_usermodehelper_freeinfo() discards them if they haven't been used. A special cred function (prepare_usermodeinfo_creds()) is provided specifically for call_usermodehelper_setup() to call. call_usermodehelper_setkeys() adjusts the credentials to sport the supplied keyring as the new session keyring. (11) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) selinux_setprocattr() no longer does its check for whether the current ptracer can access processes with the new SID inside the lock that covers getting the ptracer's SID. Whilst this lock ensures that the check is done with the ptracer pinned, the result is only valid until the lock is released, so there's no point doing it inside the lock. (12) is_single_threaded(). This function has been extracted from selinux_setprocattr() and put into a file of its own in the lib/ directory as join_session_keyring() now wants to use it too. The code in SELinux just checked to see whether a task shared mm_structs with other tasks (CLONE_VM), but that isn't good enough. We really want to know if they're part of the same thread group (CLONE_THREAD). (13) nfsd. The NFS server daemon now has to use the COW credentials to set the credentials it is going to use. It really needs to pass the credentials down to the functions it calls, but it can't do that until other patches in this series have been applied. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-13 23:39:23 +00:00
old_cred = override_creds(override_cred);
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:
CRED: Inaugurate COW credentials Inaugurate copy-on-write credentials management. This uses RCU to manage the credentials pointer in the task_struct with respect to accesses by other tasks. A process may only modify its own credentials, and so does not need locking to access or modify its own credentials. A mutex (cred_replace_mutex) is added to the task_struct to control the effect of PTRACE_ATTACHED on credential calculations, particularly with respect to execve(). With this patch, the contents of an active credentials struct may not be changed directly; rather a new set of credentials must be prepared, modified and committed using something like the following sequence of events: struct cred *new = prepare_creds(); int ret = blah(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); There are some exceptions to this rule: the keyrings pointed to by the active credentials may be instantiated - keyrings violate the COW rule as managing COW keyrings is tricky, given that it is possible for a task to directly alter the keys in a keyring in use by another task. To help enforce this, various pointers to sets of credentials, such as those in the task_struct, are declared const. The purpose of this is compile-time discouragement of altering credentials through those pointers. Once a set of credentials has been made public through one of these pointers, it may not be modified, except under special circumstances: (1) Its reference count may incremented and decremented. (2) The keyrings to which it points may be modified, but not replaced. The only safe way to modify anything else is to create a replacement and commit using the functions described in Documentation/credentials.txt (which will be added by a later patch). This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). This now prepares and commits credentials in various places in the security code rather than altering the current creds directly. (2) Temporary credential overrides. do_coredump() and sys_faccessat() now prepare their own credentials and temporarily override the ones currently on the acting thread, whilst preventing interference from other threads by holding cred_replace_mutex on the thread being dumped. This will be replaced in a future patch by something that hands down the credentials directly to the functions being called, rather than altering the task's objective credentials. (3) LSM interface. A number of functions have been changed, added or removed: (*) security_capset_check(), ->capset_check() (*) security_capset_set(), ->capset_set() Removed in favour of security_capset(). (*) security_capset(), ->capset() New. This is passed a pointer to the new creds, a pointer to the old creds and the proposed capability sets. It should fill in the new creds or return an error. All pointers, barring the pointer to the new creds, are now const. (*) security_bprm_apply_creds(), ->bprm_apply_creds() Changed; now returns a value, which will cause the process to be killed if it's an error. (*) security_task_alloc(), ->task_alloc_security() Removed in favour of security_prepare_creds(). (*) security_cred_free(), ->cred_free() New. Free security data attached to cred->security. (*) security_prepare_creds(), ->cred_prepare() New. Duplicate any security data attached to cred->security. (*) security_commit_creds(), ->cred_commit() New. Apply any security effects for the upcoming installation of new security by commit_creds(). (*) security_task_post_setuid(), ->task_post_setuid() Removed in favour of security_task_fix_setuid(). (*) security_task_fix_setuid(), ->task_fix_setuid() Fix up the proposed new credentials for setuid(). This is used by cap_set_fix_setuid() to implicitly adjust capabilities in line with setuid() changes. Changes are made to the new credentials, rather than the task itself as in security_task_post_setuid(). (*) security_task_reparent_to_init(), ->task_reparent_to_init() Removed. Instead the task being reparented to init is referred directly to init's credentials. NOTE! This results in the loss of some state: SELinux's osid no longer records the sid of the thread that forked it. (*) security_key_alloc(), ->key_alloc() (*) security_key_permission(), ->key_permission() Changed. These now take cred pointers rather than task pointers to refer to the security context. (4) sys_capset(). This has been simplified and uses less locking. The LSM functions it calls have been merged. (5) reparent_to_kthreadd(). This gives the current thread the same credentials as init by simply using commit_thread() to point that way. (6) __sigqueue_alloc() and switch_uid() __sigqueue_alloc() can't stop the target task from changing its creds beneath it, so this function gets a reference to the currently applicable user_struct which it then passes into the sigqueue struct it returns if successful. switch_uid() is now called from commit_creds(), and possibly should be folded into that. commit_creds() should take care of protecting __sigqueue_alloc(). (7) [sg]et[ug]id() and co and [sg]et_current_groups. The set functions now all use prepare_creds(), commit_creds() and abort_creds() to build and check a new set of credentials before applying it. security_task_set[ug]id() is called inside the prepared section. This guarantees that nothing else will affect the creds until we've finished. The calling of set_dumpable() has been moved into commit_creds(). Much of the functionality of set_user() has been moved into commit_creds(). The get functions all simply access the data directly. (8) security_task_prctl() and cap_task_prctl(). security_task_prctl() has been modified to return -ENOSYS if it doesn't want to handle a function, or otherwise return the return value directly rather than through an argument. Additionally, cap_task_prctl() now prepares a new set of credentials, even if it doesn't end up using it. (9) Keyrings. A number of changes have been made to the keyrings code: (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have all been dropped and built in to the credentials functions directly. They may want separating out again later. (b) key_alloc() and search_process_keyrings() now take a cred pointer rather than a task pointer to specify the security context. (c) copy_creds() gives a new thread within the same thread group a new thread keyring if its parent had one, otherwise it discards the thread keyring. (d) The authorisation key now points directly to the credentials to extend the search into rather pointing to the task that carries them. (e) Installing thread, process or session keyrings causes a new set of credentials to be created, even though it's not strictly necessary for process or session keyrings (they're shared). (10) Usermode helper. The usermode helper code now carries a cred struct pointer in its subprocess_info struct instead of a new session keyring pointer. This set of credentials is derived from init_cred and installed on the new process after it has been cloned. call_usermodehelper_setup() allocates the new credentials and call_usermodehelper_freeinfo() discards them if they haven't been used. A special cred function (prepare_usermodeinfo_creds()) is provided specifically for call_usermodehelper_setup() to call. call_usermodehelper_setkeys() adjusts the credentials to sport the supplied keyring as the new session keyring. (11) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) selinux_setprocattr() no longer does its check for whether the current ptracer can access processes with the new SID inside the lock that covers getting the ptracer's SID. Whilst this lock ensures that the check is done with the ptracer pinned, the result is only valid until the lock is released, so there's no point doing it inside the lock. (12) is_single_threaded(). This function has been extracted from selinux_setprocattr() and put into a file of its own in the lib/ directory as join_session_keyring() now wants to use it too. The code in SELinux just checked to see whether a task shared mm_structs with other tasks (CLONE_VM), but that isn't good enough. We really want to know if they're part of the same thread group (CLONE_THREAD). (13) nfsd. The NFS server daemon now has to use the COW credentials to set the credentials it is going to use. It really needs to pass the credentials down to the functions it calls, but it can't do that until other patches in this series have been applied. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-13 23:39:23 +00:00
revert_creds(old_cred);
put_cred(override_cred);
return res;
}
SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
[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
{
return sys_faccessat(AT_FDCWD, filename, mode);
}
SYSCALL_DEFINE1(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_CHDIR);
if (error)
goto dput_and_out;
set_fs_pwd(current->fs, &path);
dput_and_out:
path_put(&path);
out:
return error;
}
SYSCALL_DEFINE1(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_CHDIR);
if (!error)
set_fs_pwd(current->fs, &file->f_path);
out_putf:
fput(file);
out:
return error;
}
SYSCALL_DEFINE1(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_CHDIR);
if (error)
goto dput_and_out;
error = -EPERM;
if (!capable(CAP_SYS_CHROOT))
goto dput_and_out;
error = security_path_chroot(&path);
if (error)
goto dput_and_out;
set_fs_root(current->fs, &path);
error = 0;
dput_and_out:
path_put(&path);
out:
return error;
}
static int chmod_common(struct path *path, umode_t mode)
{
struct inode *inode = path->dentry->d_inode;
struct iattr newattrs;
int error;
error = mnt_want_write(path->mnt);
if (error)
return error;
mutex_lock(&inode->i_mutex);
error = security_path_chmod(path->dentry, path->mnt, mode);
if (error)
goto out_unlock;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
error = notify_change(path->dentry, &newattrs);
out_unlock:
mutex_unlock(&inode->i_mutex);
mnt_drop_write(path->mnt);
return error;
}
SYSCALL_DEFINE2(fchmod, unsigned int, fd, mode_t, mode)
{
struct file * file;
int err = -EBADF;
file = fget(fd);
if (file) {
audit_inode(NULL, file->f_path.dentry);
err = chmod_common(&file->f_path, mode);
fput(file);
}
return err;
}
SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, mode_t, mode)
{
struct path path;
int error;
error = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
if (!error) {
error = chmod_common(&path, mode);
path_put(&path);
}
return error;
}
SYSCALL_DEFINE2(chmod, const char __user *, filename, mode_t, mode)
[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
{
return sys_fchmodat(AT_FDCWD, filename, mode);
}
static int chown_common(struct path *path, uid_t user, gid_t group)
{
struct inode *inode = path->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 = security_path_chown(path, user, group);
if (!error)
error = notify_change(path->dentry, &newattrs);
mutex_unlock(&inode->i_mutex);
return error;
}
SYSCALL_DEFINE3(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, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
out:
return error;
}
SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
gid_t, group, int, flag)
[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 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 lookup_flags;
[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 ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 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
goto out;
lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
if (flag & AT_EMPTY_PATH)
lookup_flags |= LOOKUP_EMPTY;
error = user_path_at(dfd, filename, lookup_flags, &path);
if (error)
goto out;
error = mnt_want_write(path.mnt);
if (error)
goto out_release;
error = chown_common(&path, 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;
}
SYSCALL_DEFINE3(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, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
out:
return error;
}
SYSCALL_DEFINE3(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(file);
if (error)
goto out_fput;
dentry = file->f_path.dentry;
audit_inode(NULL, dentry);
error = chown_common(&file->f_path, 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,
struct file *f,
int (*open)(struct inode *, struct file *),
const struct cred *cred)
{
2011-03-13 07:51:11 +00:00
static const struct file_operations empty_fops = {};
struct inode *inode;
int error;
f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
FMODE_PREAD | FMODE_PWRITE;
2011-03-13 07:51:11 +00:00
if (unlikely(f->f_flags & O_PATH))
f->f_mode = FMODE_PATH;
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;
file_sb_list_add(f, inode->i_sb);
2011-03-13 07:51:11 +00:00
if (unlikely(f->f_mode & FMODE_PATH)) {
f->f_op = &empty_fops;
return f;
}
f->f_op = fops_get(inode->i_fop);
error = security_dentry_open(f, cred);
if (error)
goto cleanup_all;
error = break_lease(inode, f->f_flags);
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;
}
if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
i_readcount_inc(inode);
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_sb_list_del(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 *))
{
const struct cred *cred = current_cred();
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.file,
open, cred);
out:
return nd->intent.open.file;
out_err:
release_open_intent(nd);
nd->intent.open.file = ERR_CAST(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)
{
const struct cred *cred = current_cred();
struct file *filp;
/* Pick up the filp from the open intent */
filp = nd->intent.open.file;
nd->intent.open.file = NULL;
/* Has the filesystem initialised the file for us? */
if (filp->f_path.dentry == NULL) {
path_get(&nd->path);
filp = __dentry_open(nd->path.dentry, nd->path.mnt, filp,
NULL, cred);
}
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,
const struct cred *cred)
{
int error;
struct file *f;
validate_creds(cred);
/* We must always pass in a valid mount pointer. */
BUG_ON(!mnt);
error = -ENFILE;
f = get_empty_filp();
if (f == NULL) {
dput(dentry);
mntput(mnt);
return ERR_PTR(error);
}
f->f_flags = flags;
return __dentry_open(dentry, mnt, f, NULL, cred);
}
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);
static inline int build_open_flags(int flags, int mode, struct open_flags *op)
{
int lookup_flags = 0;
int acc_mode;
if (!(flags & O_CREAT))
mode = 0;
op->mode = mode;
/* Must never be set by userspace */
flags &= ~FMODE_NONOTIFY;
/*
* O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
* check for O_DSYNC if the need any syncing at all we enforce it's
* always set instead of having to deal with possibly weird behaviour
* for malicious applications setting only __O_SYNC.
*/
if (flags & __O_SYNC)
flags |= O_DSYNC;
2011-03-13 07:51:11 +00:00
/*
* If we have O_PATH in the open flag. Then we
* cannot have anything other than the below set of flags
*/
if (flags & O_PATH) {
flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
acc_mode = 0;
} else {
acc_mode = MAY_OPEN | ACC_MODE(flags);
}
2011-03-13 07:51:11 +00:00
op->open_flag = flags;
/* O_TRUNC implies we need access checks for write permissions */
if (flags & O_TRUNC)
acc_mode |= MAY_WRITE;
/* Allow the LSM permission hook to distinguish append
access from general write access. */
if (flags & O_APPEND)
acc_mode |= MAY_APPEND;
op->acc_mode = acc_mode;
2011-03-13 07:51:11 +00:00
op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
if (flags & O_CREAT) {
op->intent |= LOOKUP_CREATE;
if (flags & O_EXCL)
op->intent |= LOOKUP_EXCL;
}
if (flags & O_DIRECTORY)
lookup_flags |= LOOKUP_DIRECTORY;
if (!(flags & O_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
return lookup_flags;
}
/**
* filp_open - open file and return file pointer
*
* @filename: path to open
* @flags: open flags as per the open(2) second argument
* @mode: mode for the new file if O_CREAT is set, else ignored
*
* This is the helper to open a file from kernelspace if you really
* have to. But in generally you should not do this, so please move
* along, nothing to see here..
*/
struct file *filp_open(const char *filename, int flags, int mode)
{
struct open_flags op;
int lookup = build_open_flags(flags, mode, &op);
return do_filp_open(AT_FDCWD, filename, &op, lookup);
}
EXPORT_SYMBOL(filp_open);
struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
const char *filename, int flags)
{
struct open_flags op;
int lookup = build_open_flags(flags, 0, &op);
if (flags & O_CREAT)
return ERR_PTR(-EINVAL);
if (!filename && (flags & O_DIRECTORY))
if (!dentry->d_inode->i_op->lookup)
return ERR_PTR(-ENOTDIR);
return do_file_open_root(dentry, mnt, filename, &op, lookup);
}
EXPORT_SYMBOL(file_open_root);
[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)
{
struct open_flags op;
int lookup = build_open_flags(flags, mode, &op);
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) {
struct file *f = do_filp_open(dfd, tmp, &op, lookup);
if (IS_ERR(f)) {
put_unused_fd(fd);
fd = PTR_ERR(f);
} else {
fsnotify_open(f);
fd_install(fd, f);
}
}
putname(tmp);
}
return fd;
}
SYSCALL_DEFINE3(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;
}
SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
int, mode)
[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 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?
*/
SYSCALL_DEFINE2(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);
2011-03-13 07:51:11 +00:00
if (likely(!(filp->f_mode & FMODE_PATH))) {
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.
*/
SYSCALL_DEFINE1(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.
*/
SYSCALL_DEFINE0(vhangup)
{
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. The function is not supposed to ever fail, the only
* reason it returns an 'int' and not 'void' is so that it can be plugged
* directly into file_operations structure.
*/
int nonseekable_open(struct inode *inode, struct file *filp)
{
filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
return 0;
}
EXPORT_SYMBOL(nonseekable_open);