pselect: Use linux pselect syscall when available

Linux has a pselect syscall since 2.6.something. Using it
rather than emulating it with sigprocmask+select+sigprocmask
is smaller code, and works properly. (The emulation has
race conditions when unblocked signals arrive before or
after the select)

The tv.nsec >= 1E9 handling comes from uclibc's linux select()
implementation, which itself uses pselect() internally if the
pselect syscall exists. I though it would be good to do the
same here.

Note that although the libc pselect() API has 6 arguments,
the linux kernel syscall as 7 arguments. There is an extra,
somewhat vestigial, sizeof the signal mask argument.

Signed-off-by: Nicolas S. Dade <nic.dade@gmail.com>

1 files changed, 52 insertions, 0 deletions

diff --git a/libc/sysdeps/linux/common/pselect.c b/libc/sysdeps/linux/common/pselect.c
index bf19ce3d7..3f1dd28a2 100644
--- a/libc/sysdeps/linux/common/pselect.c
+++ b/libc/sysdeps/linux/common/pselect.c
@@ -30,6 +30,57 @@ static int __NC(pselect)(int nfds, fd_set *readfds, fd_set *writefds,
 			 fd_set *exceptfds, const struct timespec *timeout,
 			 const sigset_t *sigmask)
 {
+#ifdef __NR_pselect6
+#define NSEC_PER_SEC 1000000000L
+	struct timespec _ts, *ts = 0;
+	if (timeout) {
+		/* The Linux kernel can in some situations update the timeout value.
+		 * We do not want that so use a local variable.
+		 */
+		_ts = *timeout;
+
+		/* GNU extension: allow for timespec values where the sub-sec
+		* field is equal to or more than 1 second.  The kernel will
+		* reject this on us, so take care of the time shift ourself.
+		* Some applications (like readline and linphone) do this.
+		* See 'clarification on select() type calls and invalid timeouts'
+		* on the POSIX general list for more information.
+		*/
+		if (_ts.tv_nsec >= NSEC_PER_SEC) {
+			_ts.tv_sec += _ts.tv_nsec / NSEC_PER_SEC;
+			_ts.tv_nsec %= NSEC_PER_SEC;
+		}
+
+		ts = &_ts;
+	}
+
+	/* The pselect6 syscall API is strange. It wants a 7th arg to be
+	 * the sizeof(*sigmask). However syscalls with > 6 arguments aren't
+	 * supported on linux. So arguments 6 and 7 are stuffed in a struct
+	 * and a pointer to that struct is passed as the 6th argument to
+	 * the syscall.
+	 * Glibc stuffs arguments 6 and 7 in a ulong[2]. Linux reads
+	 * them as if there were a struct { sigset_t*; size_t } in
+	 * userspace. There woudl be trouble if userspace and the kernel are
+	 * compiled differently enough that size_t isn't the same as ulong,
+	 * but not enough to trigger the compat layer in linux. I can't
+	 * think of such a case, so I'm using linux's struct.
+	 * Furthermore Glibc sets the sigsetsize to _NSIG/8. However linux
+	 * checks for sizeof(sigset_t), which internally is a ulong array.
+	 * This means that if _NSIG isn't a multiple of BITS_PER_LONG then
+	 * linux will refuse glibc's value. So I prefer sizeof(sigset_t) for
+	 * the value of sigsetsize.
+	 */
+	struct {
+		const sigset_t *sigmask;
+		size_t sigsetsize;
+	} args67 = {
+		sigmask,
+		sizeof(sigset_t),
+	};
+
+	return INLINE_SYSCALL(pselect6, 6, nfds, readfds, writefds, exceptfds, ts, &args67);
+#else
 	struct timeval tval;
 	int retval;
 	sigset_t savemask;
@@ -57,6 +108,7 @@ static int __NC(pselect)(int nfds, fd_set *readfds, fd_set *writefds,
 		sigprocmask (SIG_SETMASK, &savemask, NULL);
 
 	return retval;
+#endif
 }
 CANCELLABLE_SYSCALL(int, pselect, (int nfds, fd_set *readfds, fd_set *writefds, fd_set *exceptfds,
 				   const struct timespec *timeout, const sigset_t *sigmask),