Release 4.17 fs/fcntl.c

// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/fcntl.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/syscalls.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/sched/task.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/capability.h>
#include <linux/dnotify.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/pipe_fs_i.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/signal.h>
#include <linux/rcupdate.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/shmem_fs.h>
#include <linux/compat.h>

#include <linux/poll.h>
#include <asm/siginfo.h>
#include <linux/uaccess.h>


#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)



static int setfl(int fd, struct file * filp, unsigned long arg)
{
	struct inode * inode = file_inode(filp);
	int error = 0;

	/*
         * O_APPEND cannot be cleared if the file is marked as append-only
         * and the file is open for write.
         */
	if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode))
		return -EPERM;

	/* O_NOATIME can only be set by the owner or superuser */
	if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME))
		if (!inode_owner_or_capable(inode))
			return -EPERM;

	/* required for strict SunOS emulation */
	if (O_NONBLOCK != O_NDELAY)
	       if (arg & O_NDELAY)
		   arg |= O_NONBLOCK;

	/* Pipe packetized mode is controlled by O_DIRECT flag */
	if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT)) {
		if (!filp->f_mapping || !filp->f_mapping->a_ops ||
			!filp->f_mapping->a_ops->direct_IO)
				return -EINVAL;
	}

	if (filp->f_op->check_flags)
		error = filp->f_op->check_flags(arg);
	if (error)
		return error;

	/*
         * ->fasync() is responsible for setting the FASYNC bit.
         */
	if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) {
		error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
		if (error < 0)
			goto out;
		if (error > 0)
			error = 0;
	}
	spin_lock(&filp->f_lock);
	filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
	spin_unlock(&filp->f_lock);

 out:
	return error;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
112
40.14%
3
18.75%
Matthew Wilcox
80
28.67%
2
12.50%
Jonathan Corbet
30
10.75%
3
18.75%
Cesar Eduardo Barros
28
10.04%
1
6.25%
Stanislav Kinsburskiy
10
3.58%
1
6.25%
Dean Gaudet
7
2.51%
1
6.25%
Andrew Morton
6
2.15%
1
6.25%
Al Viro
4
1.43%
2
12.50%
Satyam Sharma
1
0.36%
1
6.25%
Serge E. Hallyn
1
0.36%
1
6.25%
Total
279
100.00%
16
100.00%



static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
                     int force)
{
	write_lock_irq(&filp->f_owner.lock);
	if (force || !filp->f_owner.pid) {
		put_pid(filp->f_owner.pid);
		filp->f_owner.pid = get_pid(pid);
		filp->f_owner.pid_type = type;

		if (pid) {
			const struct cred *cred = current_cred();
			filp->f_owner.uid = cred->uid;
			filp->f_owner.euid = cred->euid;
		}
	}
	write_unlock_irq(&filp->f_owner.lock);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
James Morris
71
59.66%
1
25.00%
Eric W. Biedermann
27
22.69%
1
25.00%
Oleg Nesterov
19
15.97%
1
25.00%
Linus Torvalds
2
1.68%
1
25.00%
Total
119
100.00%
4
100.00%



void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
		int force)
{
	security_file_set_fowner(filp);
	f_modown(filp, pid, type, force);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
James Morris
23
60.53%
1
20.00%
Eric W. Biedermann
12
31.58%
1
20.00%
Greg Kroah-Hartman
2
5.26%
2
40.00%
Jeff Layton
1
2.63%
1
20.00%
Total
38
100.00%
5
100.00%

EXPORT_SYMBOL(__f_setown);



int f_setown(struct file *filp, unsigned long arg, int force)
{
	enum pid_type type;
	struct pid *pid = NULL;
	int who = arg, ret = 0;

	type = PIDTYPE_PID;
	if (who < 0) {
		/* avoid overflow below */
		if (who == INT_MIN)
			return -EINVAL;

		type = PIDTYPE_PGID;
		who = -who;
	}

	rcu_read_lock();
	if (who) {
		pid = find_vpid(who);
		if (!pid)
			ret = -ESRCH;
	}

	if (!ret)
		__f_setown(filp, pid, type, force);
	rcu_read_unlock();

	return ret;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric W. Biedermann
74
63.25%
1
20.00%
Jeff Layton
28
23.93%
1
20.00%
Jiri Slaby
14
11.97%
2
40.00%
Pavel Emelyanov
1
0.85%
1
20.00%
Total
117
100.00%
5
100.00%

EXPORT_SYMBOL(f_setown);



void f_delown(struct file *filp)
{
	f_modown(filp, NULL, PIDTYPE_PID, 1);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
James Morris
18
85.71%
1
50.00%
Eric W. Biedermann
3
14.29%
1
50.00%
Total
21
100.00%
2
100.00%



pid_t f_getown(struct file *filp)
{
	pid_t pid;
	read_lock(&filp->f_owner.lock);
	pid = pid_vnr(filp->f_owner.pid);
	if (filp->f_owner.pid_type == PIDTYPE_PGID)
		pid = -pid;
	read_unlock(&filp->f_owner.lock);
	return pid;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric W. Biedermann
61
98.39%
2
66.67%
Pavel Emelyanov
1
1.61%
1
33.33%
Total
62
100.00%
3
100.00%



static int f_setown_ex(struct file *filp, unsigned long arg)
{
	struct f_owner_ex __user *owner_p = (void __user *)arg;
	struct f_owner_ex owner;
	struct pid *pid;
	int type;
	int ret;

	ret = copy_from_user(&owner, owner_p, sizeof(owner));
	if (ret)
		return -EFAULT;

	switch (owner.type) {
	case F_OWNER_TID:
		type = PIDTYPE_MAX;
		break;

	case F_OWNER_PID:
		type = PIDTYPE_PID;
		break;

	case F_OWNER_PGRP:
		type = PIDTYPE_PGID;
		break;

	default:
		return -EINVAL;
	}

	rcu_read_lock();
	pid = find_vpid(owner.pid);
	if (owner.pid && !pid)
		ret = -ESRCH;
	else
		 __f_setown(filp, pid, type, 1);
	rcu_read_unlock();

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
143
97.28%
2
50.00%
Dan Carpenter
2
1.36%
1
25.00%
Al Viro
2
1.36%
1
25.00%
Total
147
100.00%
4
100.00%



static int f_getown_ex(struct file *filp, unsigned long arg)
{
	struct f_owner_ex __user *owner_p = (void __user *)arg;
	struct f_owner_ex owner;
	int ret = 0;

	read_lock(&filp->f_owner.lock);
	owner.pid = pid_vnr(filp->f_owner.pid);
	switch (filp->f_owner.pid_type) {
	case PIDTYPE_MAX:
		owner.type = F_OWNER_TID;
		break;

	case PIDTYPE_PID:
		owner.type = F_OWNER_PID;
		break;

	case PIDTYPE_PGID:
		owner.type = F_OWNER_PGRP;
		break;

	default:
		WARN_ON(1);
		ret = -EINVAL;
		break;
	}
	read_unlock(&filp->f_owner.lock);

	if (!ret) {
		ret = copy_to_user(owner_p, &owner, sizeof(owner));
		if (ret)
			ret = -EFAULT;
	}
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
143
91.67%
2
50.00%
Dan Carpenter
11
7.05%
1
25.00%
Al Viro
2
1.28%
1
25.00%
Total
156
100.00%
4
100.00%

#ifdef CONFIG_CHECKPOINT_RESTORE


static int f_getowner_uids(struct file *filp, unsigned long arg)
{
	struct user_namespace *user_ns = current_user_ns();
	uid_t __user *dst = (void __user *)arg;
	uid_t src[2];
	int err;

	read_lock(&filp->f_owner.lock);
	src[0] = from_kuid(user_ns, filp->f_owner.uid);
	src[1] = from_kuid(user_ns, filp->f_owner.euid);
	read_unlock(&filp->f_owner.lock);

	err  = put_user(src[0], &dst[0]);
	err |= put_user(src[1], &dst[1]);

	return err;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Cyrill V. Gorcunov
129
98.47%
1
50.00%
Al Viro
2
1.53%
1
50.00%
Total
131
100.00%
2
100.00%

#else


static int f_getowner_uids(struct file *filp, unsigned long arg)
{
	return -EINVAL;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Cyrill V. Gorcunov
19
100.00%
1
100.00%
Total
19
100.00%
1
100.00%

#endif



static bool rw_hint_valid(enum rw_hint hint)
{
	switch (hint) {
	case RWF_WRITE_LIFE_NOT_SET:
	case RWH_WRITE_LIFE_NONE:
	case RWH_WRITE_LIFE_SHORT:
	case RWH_WRITE_LIFE_MEDIUM:
	case RWH_WRITE_LIFE_LONG:
	case RWH_WRITE_LIFE_EXTREME:
		return true;
	default:
		return false;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jens Axboe
41
100.00%
1
100.00%
Total
41
100.00%
1
100.00%



static long fcntl_rw_hint(struct file *file, unsigned int cmd,
			  unsigned long arg)
{
	struct inode *inode = file_inode(file);
	u64 *argp = (u64 __user *)arg;
	enum rw_hint hint;
	u64 h;

	switch (cmd) {
	case F_GET_FILE_RW_HINT:
		h = file_write_hint(file);
		if (copy_to_user(argp, &h, sizeof(*argp)))
			return -EFAULT;
		return 0;
	case F_SET_FILE_RW_HINT:
		if (copy_from_user(&h, argp, sizeof(h)))
			return -EFAULT;
		hint = (enum rw_hint) h;
		if (!rw_hint_valid(hint))
			return -EINVAL;

		spin_lock(&file->f_lock);
		file->f_write_hint = hint;
		spin_unlock(&file->f_lock);
		return 0;
	case F_GET_RW_HINT:
		h = inode->i_write_hint;
		if (copy_to_user(argp, &h, sizeof(*argp)))
			return -EFAULT;
		return 0;
	case F_SET_RW_HINT:
		if (copy_from_user(&h, argp, sizeof(h)))
			return -EFAULT;
		hint = (enum rw_hint) h;
		if (!rw_hint_valid(hint))
			return -EINVAL;

		inode_lock(inode);
		inode->i_write_hint = hint;
		inode_unlock(inode);
		return 0;
	default:
		return -EINVAL;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jens Axboe
251
100.00%
2
100.00%
Total
251
100.00%
2
100.00%



static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
		struct file *filp)
{
	void __user *argp = (void __user *)arg;
	struct flock flock;
	long err = -EINVAL;

	switch (cmd) {
	case F_DUPFD:
		err = f_dupfd(arg, filp, 0);
		break;
	case F_DUPFD_CLOEXEC:
		err = f_dupfd(arg, filp, O_CLOEXEC);
		break;
	case F_GETFD:
		err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
		break;
	case F_SETFD:
		err = 0;
		set_close_on_exec(fd, arg & FD_CLOEXEC);
		break;
	case F_GETFL:
		err = filp->f_flags;
		break;
	case F_SETFL:
		err = setfl(fd, filp, arg);
		break;
#if BITS_PER_LONG != 32
	/* 32-bit arches must use fcntl64() */
	case F_OFD_GETLK:
#endif
	case F_GETLK:
		if (copy_from_user(&flock, argp, sizeof(flock)))
			return -EFAULT;
		err = fcntl_getlk(filp, cmd, &flock);
		if (!err && copy_to_user(argp, &flock, sizeof(flock)))
			return -EFAULT;
		break;
#if BITS_PER_LONG != 32
	/* 32-bit arches must use fcntl64() */
	case F_OFD_SETLK:
	case F_OFD_SETLKW:
#endif
		/* Fallthrough */
	case F_SETLK:
	case F_SETLKW:
		if (copy_from_user(&flock, argp, sizeof(flock)))
			return -EFAULT;
		err = fcntl_setlk(fd, filp, cmd, &flock);
		break;
	case F_GETOWN:
		/*
                 * XXX If f_owner is a process group, the
                 * negative return value will get converted
                 * into an error.  Oops.  If we keep the
                 * current syscall conventions, the only way
                 * to fix this will be in libc.
                 */
		err = f_getown(filp);
		force_successful_syscall_return();
		break;
	case F_SETOWN:
		err = f_setown(filp, arg, 1);
		break;
	case F_GETOWN_EX:
		err = f_getown_ex(filp, arg);
		break;
	case F_SETOWN_EX:
		err = f_setown_ex(filp, arg);
		break;
	case F_GETOWNER_UIDS:
		err = f_getowner_uids(filp, arg);
		break;
	case F_GETSIG:
		err = filp->f_owner.signum;
		break;
	case F_SETSIG:
		/* arg == 0 restores default behaviour. */
		if (!valid_signal(arg)) {
			break;
		}
		err = 0;
		filp->f_owner.signum = arg;
		break;
	case F_GETLEASE:
		err = fcntl_getlease(filp);
		break;
	case F_SETLEASE:
		err = fcntl_setlease(fd, filp, arg);
		break;
	case F_NOTIFY:
		err = fcntl_dirnotify(fd, filp, arg);
		break;
	case F_SETPIPE_SZ:
	case F_GETPIPE_SZ:
		err = pipe_fcntl(filp, cmd, arg);
		break;
	case F_ADD_SEALS:
	case F_GET_SEALS:
		err = memfd_fcntl(filp, cmd, arg);
		break;
	case F_GET_RW_HINT:
	case F_SET_RW_HINT:
	case F_GET_FILE_RW_HINT:
	case F_SET_FILE_RW_HINT:
		err = fcntl_rw_hint(filp, cmd, arg);
		break;
	default:
		break;
	}
	return err;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
218
45.89%
13
35.14%
Christoph Hellwig
78
16.42%
1
2.70%
Jens Axboe
42
8.84%
2
5.41%
Jeff Layton
28
5.89%
3
8.11%
Peter Zijlstra
26
5.47%
1
2.70%
Al Viro
21
4.42%
3
8.11%
David Herrmann
17
3.58%
1
2.70%
Cyrill V. Gorcunov
13
2.74%
1
2.70%
James Morris
6
1.26%
1
2.70%
David Howells
5
1.05%
1
2.70%
Andrew Morton
4
0.84%
2
5.41%
Jesper Juhl
4
0.84%
1
2.70%
Eric W. Biedermann
3
0.63%
1
2.70%
Jiri Slaby
2
0.42%
1
2.70%
Peter Staubach
2
0.42%
1
2.70%
Stephen Rothwell
2
0.42%
1
2.70%
Matthew Wilcox
2
0.42%
1
2.70%
Ulrich Drepper
1
0.21%
1
2.70%
Marc-André Lureau
1
0.21%
1
2.70%
Total
475
100.00%
37
100.00%



static int check_fcntl_cmd(unsigned cmd)
{
	switch (cmd) {
	case F_DUPFD:
	case F_DUPFD_CLOEXEC:
	case F_GETFD:
	case F_SETFD:
	case F_GETFL:
		return 1;
	}
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Al Viro
36
100.00%
1
100.00%
Total
36
100.00%
1
100.00%


SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{	
	struct fd f = fdget_raw(fd);
	long err = -EBADF;

	if (!f.file)
		goto out;

	if (unlikely(f.file->f_mode & FMODE_PATH)) {
		if (!check_fcntl_cmd(cmd))
			goto out1;
	}

	err = security_file_fcntl(f.file, cmd, arg);
	if (!err)
		err = do_fcntl(fd, cmd, arg, f.file);

out1:
 	fdput(f);
out:
	return err;
}

#if BITS_PER_LONG == 32

SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
		unsigned long, arg)
{	
	void __user *argp = (void __user *)arg;
	struct fd f = fdget_raw(fd);
	struct flock64 flock;
	long err = -EBADF;

	if (!f.file)
		goto out;

	if (unlikely(f.file->f_mode & FMODE_PATH)) {
		if (!check_fcntl_cmd(cmd))
			goto out1;
	}

	err = security_file_fcntl(f.file, cmd, arg);
	if (err)
		goto out1;
	
	switch (cmd) {
	case F_GETLK64:
	case F_OFD_GETLK:
		err = -EFAULT;
		if (copy_from_user(&flock, argp, sizeof(flock)))
			break;
		err = fcntl_getlk64(f.file, cmd, &flock);
		if (!err && copy_to_user(argp, &flock, sizeof(flock)))
			err = -EFAULT;
		break;
	case F_SETLK64:
	case F_SETLKW64:
	case F_OFD_SETLK:
	case F_OFD_SETLKW:
		err = -EFAULT;
		if (copy_from_user(&flock, argp, sizeof(flock)))
			break;
		err = fcntl_setlk64(fd, f.file, cmd, &flock);
		break;
	default:
		err = do_fcntl(fd, cmd, arg, f.file);
		break;
	}
out1:
	fdput(f);
out:
	return err;
}
#endif

#ifdef CONFIG_COMPAT
/* careful - don't use anywhere else */

#define copy_flock_fields(dst, src)		\
	(dst)->l_type = (src)->l_type;          \
        (dst)->l_whence = (src)->l_whence;      \
        (dst)->l_start = (src)->l_start;        \
        (dst)->l_len = (src)->l_len;            \
        (dst)->l_pid = (src)->l_pid;



static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl)
{
	struct compat_flock fl;

	if (copy_from_user(&fl, ufl, sizeof(struct compat_flock)))
		return -EFAULT;
	copy_flock_fields(kfl, &fl);
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Al Viro
51
96.23%
2
66.67%
Linus Torvalds
2
3.77%
1
33.33%
Total
53
100.00%
3
100.00%



static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl)
{
	struct compat_flock64 fl;

	if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64)))
		return -EFAULT;
	copy_flock_fields(kfl, &fl);
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Al Viro
51
96.23%
2
66.67%
Linus Torvalds
2
3.77%
1
33.33%
Total
53
100.00%
3
100.00%



static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl)
{
	struct compat_flock fl;

	memset(&fl, 0, sizeof(struct compat_flock));
	copy_flock_fields(&fl, kfl);
	if (copy_to_user(ufl, &fl, sizeof(struct compat_flock)))
		return -EFAULT;
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Al Viro
65
97.01%
2
66.67%
Linus Torvalds
2
2.99%
1
33.33%
Total
67
100.00%
3
100.00%



static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl)
{
	struct compat_flock64 fl;

	BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start));
	BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len));

	memset(&fl, 0, sizeof(struct compat_flock64));
	copy_flock_fields(&fl, kfl);
	if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64)))
		return -EFAULT;
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Al Viro
65
64.36%
2
50.00%
Jeff Layton
34
33.66%
1
25.00%
Linus Torvalds
2
1.98%
1
25.00%
Total
101
100.00%
4
100.00%

#undef copy_flock_fields


static unsigned int

convert_fcntl_cmd(unsigned int cmd)
{
	switch (cmd) {
	case F_GETLK64:
		return F_GETLK;
	case F_SETLK64:
		return F_SETLK;
	case F_SETLKW64:
		return F_SETLKW;
	}

	return cmd;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Al Viro
38
100.00%
1
100.00%
Total
38
100.00%
1
100.00%

/*
 * GETLK was successful and we need to return the data, but it needs to fit in
 * the compat structure.
 * l_start shouldn't be too big, unless the original start + end is greater than
 * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return
 * -EOVERFLOW in that case.  l_len could be too big, in which case we just
 * truncate it, and only allow the app to see that part of the conflicting lock
 * that might make sense to it anyway
 */


static int fixup_compat_flock(struct flock *flock)
{
	if (flock->l_start > COMPAT_OFF_T_MAX)
		return -EOVERFLOW;
	if (flock->l_len > COMPAT_OFF_T_MAX)
		flock->l_len = COMPAT_OFF_T_MAX;
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
40
100.00%
1
100.00%
Total
40
100.00%
1
100.00%



static long do_compat_fcntl64(unsigned int fd, unsigned int cmd,
			     compat_ulong_t arg)
{
	struct fd f = fdget_raw(fd);
	struct flock flock;
	long err = -EBADF;

	if (!f.file)
		return err;

	if (unlikely(f.file->f_mode & FMODE_PATH)) {
		if (!check_fcntl_cmd(cmd))
			goto out_put;
	}

	err = security_file_fcntl(f.file, cmd, arg);
	if