[PATCH] Add pselect/ppoll system call implementation

The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.

These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.

The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.

The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.

The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.

This patch:

Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

fs/compat.c

@@ -53,6 +53,8 @@
 #include <asm/mmu_context.h>
 #include <asm/ioctls.h>
 
+extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat);
+
 /*
  * Not all architectures have sys_utime, so implement this in terms
  * of sys_utimes.
@@ -1657,36 +1659,14 @@ static void select_bits_free(void *bits, int size)
 #define MAX_SELECT_SECONDS \
 	((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)
 
-asmlinkage long
-compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp,
-		compat_ulong_t __user *exp, struct compat_timeval __user *tvp)
+int compat_core_sys_select(int n, compat_ulong_t __user *inp,
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp, s64 *timeout)
 {
 	fd_set_bits fds;
 	char *bits;
-	long timeout;
 	int size, max_fdset, ret = -EINVAL;
 	struct fdtable *fdt;
 
-	timeout = MAX_SCHEDULE_TIMEOUT;
-	if (tvp) {
-		time_t sec, usec;
-
-		if (!access_ok(VERIFY_READ, tvp, sizeof(*tvp))
-		    || __get_user(sec, &tvp->tv_sec)
-		    || __get_user(usec, &tvp->tv_usec)) {
-			ret = -EFAULT;
-			goto out_nofds;
-		}
-
-		if (sec < 0 || usec < 0)
-			goto out_nofds;
-
-		if ((unsigned long) sec < MAX_SELECT_SECONDS) {
-			timeout = ROUND_UP(usec, 1000000/HZ);
-			timeout += sec * (unsigned long) HZ;
-		}
-	}
-
 	if (n < 0)
 		goto out_nofds;
 
@@ -1723,19 +1703,7 @@ compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp
 	zero_fd_set(n, fds.res_out);
 	zero_fd_set(n, fds.res_ex);
 
-	ret = do_select(n, &fds, &timeout);
-
-	if (tvp && !(current->personality & STICKY_TIMEOUTS)) {
-		time_t sec = 0, usec = 0;
-		if (timeout) {
-			sec = timeout / HZ;
-			usec = timeout % HZ;
-			usec *= (1000000/HZ);
-		}
-		if (put_user(sec, &tvp->tv_sec) ||
-		    put_user(usec, &tvp->tv_usec))
-			ret = -EFAULT;
-	}
+	ret = do_select(n, &fds, timeout);
 
 	if (ret < 0)
 		goto out;
@@ -1756,6 +1724,224 @@ out_nofds:
 	return ret;
 }
 
+asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct compat_timeval __user *tvp)
+{
+	s64 timeout = -1;
+	struct compat_timeval tv;
+	int ret;
+
+	if (tvp) {
+		if (copy_from_user(&tv, tvp, sizeof(tv)))
+			return -EFAULT;
+
+		if (tv.tv_sec < 0 || tv.tv_usec < 0)
+			return -EINVAL;
+
+		/* Cast to u64 to make GCC stop complaining */
+		if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS)
+			timeout = -1;	/* infinite */
+		else {
+			timeout = ROUND_UP(tv.tv_sec, 1000000/HZ);
+			timeout += tv.tv_sec * HZ;
+		}
+	}
+
+	ret = compat_core_sys_select(n, inp, outp, exp, &timeout);
+
+	if (tvp) {
+		if (current->personality & STICKY_TIMEOUTS)
+			goto sticky;
+		tv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
+		tv.tv_sec = timeout;
+		if (copy_to_user(tvp, &tv, sizeof(tv))) {
+sticky:
+			/*
+			 * If an application puts its timeval in read-only
+			 * memory, we don't want the Linux-specific update to
+			 * the timeval to cause a fault after the select has
+			 * completed successfully. However, because we're not
+			 * updating the timeval, we can't restart the system
+			 * call.
+			 */
+			if (ret == -ERESTARTNOHAND)
+				ret = -EINTR;
+		}
+	}
+
+	return ret;
+}
+
+#ifdef TIF_RESTORE_SIGMASK
+asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp,
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask,
+	compat_size_t sigsetsize)
+{
+	compat_sigset_t ss32;
+	sigset_t ksigmask, sigsaved;
+	long timeout = MAX_SCHEDULE_TIMEOUT;
+	struct compat_timespec ts;
+	int ret;
+
+	if (tsp) {
+		if (copy_from_user(&ts, tsp, sizeof(ts)))
+			return -EFAULT;
+
+		if (ts.tv_sec < 0 || ts.tv_nsec < 0)
+			return -EINVAL;
+	}
+
+	if (sigmask) {
+		if (sigsetsize != sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+			return -EFAULT;
+		sigset_from_compat(&ksigmask, &ss32);
+
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	do {
+		if (tsp) {
+			if ((unsigned long)ts.tv_sec < MAX_SELECT_SECONDS) {
+				timeout = ROUND_UP(ts.tv_nsec, 1000000000/HZ);
+				timeout += ts.tv_sec * (unsigned long)HZ;
+				ts.tv_sec = 0;
+				ts.tv_nsec = 0;
+			} else {
+				ts.tv_sec -= MAX_SELECT_SECONDS;
+				timeout = MAX_SELECT_SECONDS * HZ;
+			}
+		}
+
+		ret = compat_core_sys_select(n, inp, outp, exp, &timeout);
+
+	} while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec));
+
+	if (tsp && !(current->personality & STICKY_TIMEOUTS)) {
+		ts.tv_sec += timeout / HZ;
+		ts.tv_nsec += (timeout % HZ) * (1000000000/HZ);
+		if (ts.tv_nsec >= 1000000000) {
+			ts.tv_sec++;
+			ts.tv_nsec -= 1000000000;
+		}
+		(void)copy_to_user(tsp, &ts, sizeof(ts));
+	}
+
+	if (ret == -ERESTARTNOHAND) {
+		/*
+		 * Don't restore the signal mask yet. Let do_signal() deliver
+		 * the signal on the way back to userspace, before the signal
+		 * mask is restored.
+		 */
+		if (sigmask) {
+			memcpy(&current->saved_sigmask, &sigsaved,
+					sizeof(sigsaved));
+			set_thread_flag(TIF_RESTORE_SIGMASK);
+		}
+	} else if (sigmask)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	return ret;
+}
+
+asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp,
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct compat_timespec __user *tsp, void __user *sig)
+{
+	compat_size_t sigsetsize = 0;
+	compat_uptr_t up = 0;
+
+	if (sig) {
+		if (!access_ok(VERIFY_READ, sig,
+				sizeof(compat_uptr_t)+sizeof(compat_size_t)) ||
+		    	__get_user(up, (compat_uptr_t __user *)sig) ||
+		    	__get_user(sigsetsize,
+				(compat_size_t __user *)(sig+sizeof(up))))
+			return -EFAULT;
+	}
+	return compat_sys_pselect7(n, inp, outp, exp, tsp, compat_ptr(up),
+					sigsetsize);
+}
+
+asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
+	unsigned int nfds, struct compat_timespec __user *tsp,
+	const compat_sigset_t __user *sigmask, compat_size_t sigsetsize)
+{
+	compat_sigset_t ss32;
+	sigset_t ksigmask, sigsaved;
+	struct compat_timespec ts;
+	s64 timeout = -1;
+	int ret;
+
+	if (tsp) {
+		if (copy_from_user(&ts, tsp, sizeof(ts)))
+			return -EFAULT;
+
+		/* We assume that ts.tv_sec is always lower than
+		   the number of seconds that can be expressed in
+		   an s64. Otherwise the compiler bitches at us */
+		timeout = ROUND_UP(ts.tv_sec, 1000000000/HZ);
+		timeout += ts.tv_sec * HZ;
+	}
+
+	if (sigmask) {
+		if (sigsetsize |= sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+			return -EFAULT;
+		sigset_from_compat(&ksigmask, &ss32);
+
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	ret = do_sys_poll(ufds, nfds, &timeout);
+
+	/* We can restart this syscall, usually */
+	if (ret == -EINTR) {
+		/*
+		 * Don't restore the signal mask yet. Let do_signal() deliver
+		 * the signal on the way back to userspace, before the signal
+		 * mask is restored.
+		 */
+		if (sigmask) {
+			memcpy(&current->saved_sigmask, &sigsaved,
+				sizeof(sigsaved));
+			set_thread_flag(TIF_RESTORE_SIGMASK);
+		}
+		ret = -ERESTARTNOHAND;
+	} else if (sigmask)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	if (tsp && timeout >= 0) {
+		if (current->personality & STICKY_TIMEOUTS)
+			goto sticky;
+		/* Yes, we know it's actually an s64, but it's also positive. */
+		ts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * 1000;
+		ts.tv_sec = timeout;
+		if (copy_to_user(tsp, &ts, sizeof(ts))) {
+sticky:
+			/*
+			 * If an application puts its timeval in read-only
+			 * memory, we don't want the Linux-specific update to
+			 * the timeval to cause a fault after the select has
+			 * completed successfully. However, because we're not
+			 * updating the timeval, we can't restart the system
+			 * call.
+			 */
+			if (ret == -ERESTARTNOHAND && timeout >= 0)
+				ret = -EINTR;
+		}
+	}
+
+	return ret;
+}
+#endif /* TIF_RESTORE_SIGMASK */
+
 #if defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE)
 /* Stuff for NFS server syscalls... */
 struct compat_nfsctl_svc {

include/linux/poll.h

@@ -92,7 +92,11 @@ void zero_fd_set(unsigned long nr, unsigned long *fdset)
 	memset(fdset, 0, FDS_BYTES(nr));
 }
 
-extern int do_select(int n, fd_set_bits *fds, long *timeout);
+#define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)
+
+extern int do_select(int n, fd_set_bits *fds, s64 *timeout);
+extern int do_sys_poll(struct pollfd __user * ufds, unsigned int nfds,
+		       s64 *timeout);
 
 #endif /* KERNEL */