linux-stable/fs/signalfd.c
Davide Libenzi b8fceee17a signalfd simplification
This simplifies signalfd code, by avoiding it to remain attached to the
sighand during its lifetime.

In this way, the signalfd remain attached to the sighand only during
poll(2) (and select and epoll) and read(2).  This also allows to remove
all the custom "tsk == current" checks in kernel/signal.c, since
dequeue_signal() will only be called by "current".

I think this is also what Ben was suggesting time ago.

The external effect of this, is that a thread can extract only its own
private signals and the group ones.  I think this is an acceptable
behaviour, in that those are the signals the thread would be able to
fetch w/out signalfd.

Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-20 13:19:59 -07:00

254 lines
6.5 KiB
C

/*
* fs/signalfd.c
*
* Copyright (C) 2003 Linus Torvalds
*
* Mon Mar 5, 2007: Davide Libenzi <davidel@xmailserver.org>
* Changed ->read() to return a siginfo strcture instead of signal number.
* Fixed locking in ->poll().
* Added sighand-detach notification.
* Added fd re-use in sys_signalfd() syscall.
* Now using anonymous inode source.
* Thanks to Oleg Nesterov for useful code review and suggestions.
* More comments and suggestions from Arnd Bergmann.
* Sat May 19, 2007: Davi E. M. Arnaut <davi@haxent.com.br>
* Retrieve multiple signals with one read() call
* Sun Jul 15, 2007: Davide Libenzi <davidel@xmailserver.org>
* Attach to the sighand only during read() and poll().
*/
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/list.h>
#include <linux/anon_inodes.h>
#include <linux/signalfd.h>
struct signalfd_ctx {
sigset_t sigmask;
};
static int signalfd_release(struct inode *inode, struct file *file)
{
kfree(file->private_data);
return 0;
}
static unsigned int signalfd_poll(struct file *file, poll_table *wait)
{
struct signalfd_ctx *ctx = file->private_data;
unsigned int events = 0;
poll_wait(file, &current->sighand->signalfd_wqh, wait);
spin_lock_irq(&current->sighand->siglock);
if (next_signal(&current->pending, &ctx->sigmask) ||
next_signal(&current->signal->shared_pending,
&ctx->sigmask))
events |= POLLIN;
spin_unlock_irq(&current->sighand->siglock);
return events;
}
/*
* Copied from copy_siginfo_to_user() in kernel/signal.c
*/
static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
siginfo_t const *kinfo)
{
long err;
BUILD_BUG_ON(sizeof(struct signalfd_siginfo) != 128);
/*
* Unused memebers should be zero ...
*/
err = __clear_user(uinfo, sizeof(*uinfo));
/*
* If you change siginfo_t structure, please be sure
* this code is fixed accordingly.
*/
err |= __put_user(kinfo->si_signo, &uinfo->signo);
err |= __put_user(kinfo->si_errno, &uinfo->err);
err |= __put_user((short)kinfo->si_code, &uinfo->code);
switch (kinfo->si_code & __SI_MASK) {
case __SI_KILL:
err |= __put_user(kinfo->si_pid, &uinfo->pid);
err |= __put_user(kinfo->si_uid, &uinfo->uid);
break;
case __SI_TIMER:
err |= __put_user(kinfo->si_tid, &uinfo->tid);
err |= __put_user(kinfo->si_overrun, &uinfo->overrun);
err |= __put_user((long)kinfo->si_ptr, &uinfo->svptr);
break;
case __SI_POLL:
err |= __put_user(kinfo->si_band, &uinfo->band);
err |= __put_user(kinfo->si_fd, &uinfo->fd);
break;
case __SI_FAULT:
err |= __put_user((long)kinfo->si_addr, &uinfo->addr);
#ifdef __ARCH_SI_TRAPNO
err |= __put_user(kinfo->si_trapno, &uinfo->trapno);
#endif
break;
case __SI_CHLD:
err |= __put_user(kinfo->si_pid, &uinfo->pid);
err |= __put_user(kinfo->si_uid, &uinfo->uid);
err |= __put_user(kinfo->si_status, &uinfo->status);
err |= __put_user(kinfo->si_utime, &uinfo->utime);
err |= __put_user(kinfo->si_stime, &uinfo->stime);
break;
case __SI_RT: /* This is not generated by the kernel as of now. */
case __SI_MESGQ: /* But this is */
err |= __put_user(kinfo->si_pid, &uinfo->pid);
err |= __put_user(kinfo->si_uid, &uinfo->uid);
err |= __put_user((long)kinfo->si_ptr, &uinfo->svptr);
break;
default: /* this is just in case for now ... */
err |= __put_user(kinfo->si_pid, &uinfo->pid);
err |= __put_user(kinfo->si_uid, &uinfo->uid);
break;
}
return err ? -EFAULT: sizeof(*uinfo);
}
static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, siginfo_t *info,
int nonblock)
{
ssize_t ret;
DECLARE_WAITQUEUE(wait, current);
spin_lock_irq(&current->sighand->siglock);
ret = dequeue_signal(current, &ctx->sigmask, info);
switch (ret) {
case 0:
if (!nonblock)
break;
ret = -EAGAIN;
default:
spin_unlock_irq(&current->sighand->siglock);
return ret;
}
add_wait_queue(&current->sighand->signalfd_wqh, &wait);
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
ret = dequeue_signal(current, &ctx->sigmask, info);
if (ret != 0)
break;
if (signal_pending(current)) {
ret = -ERESTARTSYS;
break;
}
spin_unlock_irq(&current->sighand->siglock);
schedule();
spin_lock_irq(&current->sighand->siglock);
}
spin_unlock_irq(&current->sighand->siglock);
remove_wait_queue(&current->sighand->signalfd_wqh, &wait);
__set_current_state(TASK_RUNNING);
return ret;
}
/*
* Returns a multiple of the size of a "struct signalfd_siginfo", or a negative
* error code. The "count" parameter must be at least the size of a
* "struct signalfd_siginfo".
*/
static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count,
loff_t *ppos)
{
struct signalfd_ctx *ctx = file->private_data;
struct signalfd_siginfo __user *siginfo;
int nonblock = file->f_flags & O_NONBLOCK;
ssize_t ret, total = 0;
siginfo_t info;
count /= sizeof(struct signalfd_siginfo);
if (!count)
return -EINVAL;
siginfo = (struct signalfd_siginfo __user *) buf;
do {
ret = signalfd_dequeue(ctx, &info, nonblock);
if (unlikely(ret <= 0))
break;
ret = signalfd_copyinfo(siginfo, &info);
if (ret < 0)
break;
siginfo++;
total += ret;
nonblock = 1;
} while (--count);
return total ? total: ret;
}
static const struct file_operations signalfd_fops = {
.release = signalfd_release,
.poll = signalfd_poll,
.read = signalfd_read,
};
asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask)
{
int error;
sigset_t sigmask;
struct signalfd_ctx *ctx;
struct file *file;
struct inode *inode;
if (sizemask != sizeof(sigset_t) ||
copy_from_user(&sigmask, user_mask, sizeof(sigmask)))
return -EINVAL;
sigdelsetmask(&sigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
signotset(&sigmask);
if (ufd == -1) {
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
ctx->sigmask = sigmask;
/*
* When we call this, the initialization must be complete, since
* anon_inode_getfd() will install the fd.
*/
error = anon_inode_getfd(&ufd, &inode, &file, "[signalfd]",
&signalfd_fops, ctx);
if (error)
goto err_fdalloc;
} else {
file = fget(ufd);
if (!file)
return -EBADF;
ctx = file->private_data;
if (file->f_op != &signalfd_fops) {
fput(file);
return -EINVAL;
}
spin_lock_irq(&current->sighand->siglock);
ctx->sigmask = sigmask;
spin_unlock_irq(&current->sighand->siglock);
wake_up(&current->sighand->signalfd_wqh);
fput(file);
}
return ufd;
err_fdalloc:
kfree(ctx);
return error;
}