- Run sched_userret() after thread_userret(). Before, sched_userret() would

lower the priority of the returning thread to a user priority before
   calling into thread_userret() which would call wakeup() which in turn would
   cause the returning thread to eventually context switch rather than
   completing its slice.  Allowing this thread to complete its slice first
   yields a 15% performance improvement in super-smack on my dual opteron with
   4BSD.

sys/kern/subr_trap.c

@@ -101,11 +101,6 @@ userret(td, frame, oticks)
 	if (td->td_pflags & TDP_GEOM)
 		g_waitidle();
 
-	/*
-	 * Let the scheduler adjust our priority etc.
-	 */
-	sched_userret(td);
-
 	/*
 	 * We need to check to see if we have to exit or wait due to a
 	 * single threading requirement or some other STOP condition.
@@ -133,6 +128,10 @@ userret(td, frame, oticks)
 		ticks = td->td_sticks - oticks;
 		addupc_task(td, TRAPF_PC(frame), (u_int)ticks * psratio);
 	}
+	/*
+	 * Let the scheduler adjust our priority etc.
+	 */
+	sched_userret(td);
 }
 
 /*