1 files changed, 209 insertions, 214 deletions

diff --git a/fs/signalfd.c b/fs/signalfd.c
index 7cfeab412b4..424b7b65321 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -11,6 +11,10 @@
  *      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>
@@ -18,103 +22,38 @@
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/list.h>
 #include <linux/anon_inodes.h>
 #include <linux/signalfd.h>
+#include <linux/syscalls.h>
+#include <linux/proc_fs.h>
+#include <linux/compat.h>
 
-struct signalfd_ctx {
-	struct list_head lnk;
-	wait_queue_head_t wqh;
-	sigset_t sigmask;
-	struct task_struct *tsk;
-};
-
-struct signalfd_lockctx {
-	struct task_struct *tsk;
-	unsigned long flags;
-};
-
-/*
- * Tries to acquire the sighand lock. We do not increment the sighand
- * use count, and we do not even pin the task struct, so we need to
- * do it inside an RCU read lock, and we must be prepared for the
- * ctx->tsk going to NULL (in signalfd_deliver()), and for the sighand
- * being detached. We return 0 if the sighand has been detached, or
- * 1 if we were able to pin the sighand lock.
- */
-static int signalfd_lock(struct signalfd_ctx *ctx, struct signalfd_lockctx *lk)
+void signalfd_cleanup(struct sighand_struct *sighand)
 {
-	struct sighand_struct *sighand = NULL;
-
-	rcu_read_lock();
-	lk->tsk = rcu_dereference(ctx->tsk);
-	if (likely(lk->tsk != NULL))
-		sighand = lock_task_sighand(lk->tsk, &lk->flags);
-	rcu_read_unlock();
-
-	if (sighand && !ctx->tsk) {
-		unlock_task_sighand(lk->tsk, &lk->flags);
-		sighand = NULL;
-	}
-
-	return sighand != NULL;
-}
-
-static void signalfd_unlock(struct signalfd_lockctx *lk)
-{
-	unlock_task_sighand(lk->tsk, &lk->flags);
-}
-
-/*
- * This must be called with the sighand lock held.
- */
-void signalfd_deliver(struct task_struct *tsk, int sig)
-{
-	struct sighand_struct *sighand = tsk->sighand;
-	struct signalfd_ctx *ctx, *tmp;
-
-	BUG_ON(!sig);
-	list_for_each_entry_safe(ctx, tmp, &sighand->signalfd_list, lnk) {
-		/*
-		 * We use a negative signal value as a way to broadcast that the
-		 * sighand has been orphaned, so that we can notify all the
-		 * listeners about this. Remember the ctx->sigmask is inverted,
-		 * so if the user is interested in a signal, that corresponding
-		 * bit will be zero.
-		 */
-		if (sig < 0) {
-			if (ctx->tsk == tsk) {
-				ctx->tsk = NULL;
-				list_del_init(&ctx->lnk);
-				wake_up(&ctx->wqh);
-			}
-		} else {
-			if (!sigismember(&ctx->sigmask, sig))
-				wake_up(&ctx->wqh);
-		}
-	}
-}
-
-static void signalfd_cleanup(struct signalfd_ctx *ctx)
-{
-	struct signalfd_lockctx lk;
-
+	wait_queue_head_t *wqh = &sighand->signalfd_wqh;
 	/*
-	 * This is tricky. If the sighand is gone, we do not need to remove
-	 * context from the list, the list itself won't be there anymore.
+	 * The lockless check can race with remove_wait_queue() in progress,
+	 * but in this case its caller should run under rcu_read_lock() and
+	 * sighand_cachep is SLAB_DESTROY_BY_RCU, we can safely return.
 	 */
-	if (signalfd_lock(ctx, &lk)) {
-		list_del(&ctx->lnk);
-		signalfd_unlock(&lk);
-	}
-	kfree(ctx);
+	if (likely(!waitqueue_active(wqh)))
+		return;
+
+	/* wait_queue_t->func(POLLFREE) should do remove_wait_queue() */
+	wake_up_poll(wqh, POLLHUP | POLLFREE);
 }
 
+struct signalfd_ctx {
+	sigset_t sigmask;
+};
+
 static int signalfd_release(struct inode *inode, struct file *file)
 {
-	signalfd_cleanup(file->private_data);
+	kfree(file->private_data);
 	return 0;
 }
 
@@ -122,22 +61,15 @@ static unsigned int signalfd_poll(struct file *file, poll_table *wait)
 {
 	struct signalfd_ctx *ctx = file->private_data;
 	unsigned int events = 0;
-	struct signalfd_lockctx lk;
 
-	poll_wait(file, &ctx->wqh, wait);
+	poll_wait(file, &current->sighand->signalfd_wqh, wait);
 
-	/*
-	 * Let the caller get a POLLIN in this case, ala socket recv() when
-	 * the peer disconnects.
-	 */
-	if (signalfd_lock(ctx, &lk)) {
-		if (next_signal(&lk.tsk->pending, &ctx->sigmask) > 0 ||
-		    next_signal(&lk.tsk->signal->shared_pending,
-				&ctx->sigmask) > 0)
-			events |= POLLIN;
-		signalfd_unlock(&lk);
-	} else
+	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;
 }
@@ -153,7 +85,7 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 	BUILD_BUG_ON(sizeof(struct signalfd_siginfo) != 128);
 
 	/*
-	 * Unused memebers should be zero ...
+	 * Unused members should be zero ...
 	 */
 	err = __clear_user(uinfo, sizeof(*uinfo));
 
@@ -161,135 +93,182 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *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);
+	err |= __put_user(kinfo->si_signo, &uinfo->ssi_signo);
+	err |= __put_user(kinfo->si_errno, &uinfo->ssi_errno);
+	err |= __put_user((short) kinfo->si_code, &uinfo->ssi_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);
+		err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
+		err |= __put_user(kinfo->si_uid, &uinfo->ssi_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);
+		 err |= __put_user(kinfo->si_tid, &uinfo->ssi_tid);
+		 err |= __put_user(kinfo->si_overrun, &uinfo->ssi_overrun);
+		 err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr);
+		 err |= __put_user(kinfo->si_int, &uinfo->ssi_int);
 		break;
 	case __SI_POLL:
-		err |= __put_user(kinfo->si_band, &uinfo->band);
-		err |= __put_user(kinfo->si_fd, &uinfo->fd);
+		err |= __put_user(kinfo->si_band, &uinfo->ssi_band);
+		err |= __put_user(kinfo->si_fd, &uinfo->ssi_fd);
 		break;
 	case __SI_FAULT:
-		err |= __put_user((long)kinfo->si_addr, &uinfo->addr);
+		err |= __put_user((long) kinfo->si_addr, &uinfo->ssi_addr);
 #ifdef __ARCH_SI_TRAPNO
-		err |= __put_user(kinfo->si_trapno, &uinfo->trapno);
+		err |= __put_user(kinfo->si_trapno, &uinfo->ssi_trapno);
+#endif
+#ifdef BUS_MCEERR_AO
+		/* 
+		 * Other callers might not initialize the si_lsb field,
+		 * so check explicitly for the right codes here.
+		 */
+		if (kinfo->si_code == BUS_MCEERR_AR ||
+		    kinfo->si_code == BUS_MCEERR_AO)
+			err |= __put_user((short) kinfo->si_addr_lsb,
+					  &uinfo->ssi_addr_lsb);
 #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);
+		err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
+		err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
+		err |= __put_user(kinfo->si_status, &uinfo->ssi_status);
+		err |= __put_user(kinfo->si_utime, &uinfo->ssi_utime);
+		err |= __put_user(kinfo->si_stime, &uinfo->ssi_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);
+		err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
+		err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
+		err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr);
+		err |= __put_user(kinfo->si_int, &uinfo->ssi_int);
 		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);
+	default:
+		/*
+		 * This case catches also the signals queued by sigqueue().
+		 */
+		err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
+		err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
+		err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr);
+		err |= __put_user(kinfo->si_int, &uinfo->ssi_int);
 		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 either the size of a "struct signalfd_siginfo", or zero if the
- * sighand we are attached to, has been orphaned. The "count" parameter
- * must be at least the size of a "struct signalfd_siginfo".
+ * 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;
-	ssize_t res = 0;
-	int locked, signo;
+	struct signalfd_siginfo __user *siginfo;
+	int nonblock = file->f_flags & O_NONBLOCK;
+	ssize_t ret, total = 0;
 	siginfo_t info;
-	struct signalfd_lockctx lk;
-	DECLARE_WAITQUEUE(wait, current);
 
-	if (count < sizeof(struct signalfd_siginfo))
+	count /= sizeof(struct signalfd_siginfo);
+	if (!count)
 		return -EINVAL;
-	locked = signalfd_lock(ctx, &lk);
-	if (!locked)
-		return 0;
-	res = -EAGAIN;
-	signo = dequeue_signal(lk.tsk, &ctx->sigmask, &info);
-	if (signo == 0 && !(file->f_flags & O_NONBLOCK)) {
-		add_wait_queue(&ctx->wqh, &wait);
-		for (;;) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			signo = dequeue_signal(lk.tsk, &ctx->sigmask, &info);
-			if (signo != 0)
-				break;
-			if (signal_pending(current)) {
-				res = -ERESTARTSYS;
-				break;
-			}
-			signalfd_unlock(&lk);
-			schedule();
-			locked = signalfd_lock(ctx, &lk);
-			if (unlikely(!locked)) {
-				/*
-				 * Let the caller read zero byte, ala socket
-				 * recv() when the peer disconnect. This test
-				 * must be done before doing a dequeue_signal(),
-				 * because if the sighand has been orphaned,
-				 * the dequeue_signal() call is going to crash.
-				 */
-				res = 0;
-				break;
-			}
-		}
-		remove_wait_queue(&ctx->wqh, &wait);
-		__set_current_state(TASK_RUNNING);
-	}
-	if (likely(locked))
-		signalfd_unlock(&lk);
-	if (likely(signo))
-		res = signalfd_copyinfo((struct signalfd_siginfo __user *) buf,
-					&info);
 
-	return res;
+	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;
+}
+
+#ifdef CONFIG_PROC_FS
+static int signalfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct signalfd_ctx *ctx = f->private_data;
+	sigset_t sigmask;
+
+	sigmask = ctx->sigmask;
+	signotset(&sigmask);
+	render_sigset_t(m, "sigmask:\t", &sigmask);
+
+	return 0;
 }
+#endif
 
 static const struct file_operations signalfd_fops = {
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= signalfd_show_fdinfo,
+#endif
 	.release	= signalfd_release,
 	.poll		= signalfd_poll,
 	.read		= signalfd_read,
+	.llseek		= noop_llseek,
 };
 
-/*
- * Create a file descriptor that is associated with our signal
- * state. We can pass it around to others if we want to, but
- * it will always be _our_ signal state.
- */
-asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask)
+SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask,
+		size_t, sizemask, int, flags)
 {
-	int error;
 	sigset_t sigmask;
 	struct signalfd_ctx *ctx;
-	struct sighand_struct *sighand;
-	struct file *file;
-	struct inode *inode;
-	struct signalfd_lockctx lk;
+
+	/* Check the SFD_* constants for consistency.  */
+	BUILD_BUG_ON(SFD_CLOEXEC != O_CLOEXEC);
+	BUILD_BUG_ON(SFD_NONBLOCK != O_NONBLOCK);
+
+	if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK))
+		return -EINVAL;
 
 	if (sizemask != sizeof(sigset_t) ||
 	    copy_from_user(&sigmask, user_mask, sizeof(sigmask)))
-		return error = -EINVAL;
+		return -EINVAL;
 	sigdelsetmask(&sigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
 	signotset(&sigmask);
 
@@ -298,52 +277,68 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas
 		if (!ctx)
 			return -ENOMEM;
 
-		init_waitqueue_head(&ctx->wqh);
 		ctx->sigmask = sigmask;
-		ctx->tsk = current;
-
-		sighand = current->sighand;
-		/*
-		 * Add this fd to the list of signal listeners.
-		 */
-		spin_lock_irq(&sighand->siglock);
-		list_add_tail(&ctx->lnk, &sighand->signalfd_list);
-		spin_unlock_irq(&sighand->siglock);
 
 		/*
 		 * 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;
+		ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx,
+				       O_RDWR | (flags & (O_CLOEXEC | O_NONBLOCK)));
+		if (ufd < 0)
+			kfree(ctx);
 	} else {
-		file = fget(ufd);
-		if (!file)
+		struct fd f = fdget(ufd);
+		if (!f.file)
 			return -EBADF;
-		ctx = file->private_data;
-		if (file->f_op != &signalfd_fops) {
-			fput(file);
+		ctx = f.file->private_data;
+		if (f.file->f_op != &signalfd_fops) {
+			fdput(f);
 			return -EINVAL;
 		}
-		/*
-		 * We need to be prepared of the fact that the sighand this fd
-		 * is attached to, has been detched. In that case signalfd_lock()
-		 * will return 0, and we'll just skip setting the new mask.
-		 */
-		if (signalfd_lock(ctx, &lk)) {
-			ctx->sigmask = sigmask;
-			signalfd_unlock(&lk);
-		}
-		wake_up(&ctx->wqh);
-		fput(file);
+		spin_lock_irq(&current->sighand->siglock);
+		ctx->sigmask = sigmask;
+		spin_unlock_irq(&current->sighand->siglock);
+
+		wake_up(&current->sighand->signalfd_wqh);
+		fdput(f);
 	}
 
 	return ufd;
+}
 
-err_fdalloc:
-	signalfd_cleanup(ctx);
-	return error;
+SYSCALL_DEFINE3(signalfd, int, ufd, sigset_t __user *, user_mask,
+		size_t, sizemask)
+{
+	return sys_signalfd4(ufd, user_mask, sizemask, 0);
 }
 
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE4(signalfd4, int, ufd,
+		     const compat_sigset_t __user *,sigmask,
+		     compat_size_t, sigsetsize,
+		     int, flags)
+{
+	compat_sigset_t ss32;
+	sigset_t tmp;
+	sigset_t __user *ksigmask;
+
+	if (sigsetsize != sizeof(compat_sigset_t))
+		return -EINVAL;
+	if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+		return -EFAULT;
+	sigset_from_compat(&tmp, &ss32);
+	ksigmask = compat_alloc_user_space(sizeof(sigset_t));
+	if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t)))
+		return -EFAULT;
+
+	return sys_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags);
+}
+
+COMPAT_SYSCALL_DEFINE3(signalfd, int, ufd,
+		     const compat_sigset_t __user *,sigmask,
+		     compat_size_t, sigsetsize)
+{
+	return compat_sys_signalfd4(ufd, sigmask, sigsetsize, 0);
+}
+#endif