Refactor select to reduce contention and hide internal implementation

details from consumers.

 - Track individual selecters on a per-descriptor basis such that there
   are no longer collisions and after sleeping for events only those
   descriptors which triggered events must be rescaned.
 - Protect the selinfo (per descriptor) structure with a mtx pool mutex.
   mtx pool mutexes were chosen to preserve api compatibility with
   existing code which does nothing but bzero() to setup selinfo
   structures.
 - Use a per-thread wait channel rather than a global wait channel.
 - Hide select implementation details in a seltd structure which is
   opaque to the rest of the kernel.
 - Provide a 'selsocket' interface for those kernel consumers who wish to
   select on a socket when they have no fd so they no longer have to
   be aware of select implementation details.

Tested by:	kris
Reviewed on:	arch

1 files changed, 6 insertions, 3 deletions

diff --git a/sys/kern/sys_pipe.c b/sys/kern/sys_pipe.c
index 2a48583..262ef0c 100644
--- a/sys/kern/sys_pipe.c
+++ b/sys/kern/sys_pipe.c
@@ -524,8 +524,9 @@ pipeselwakeup(cpipe)
 
 	PIPE_LOCK_ASSERT(cpipe, MA_OWNED);
 	if (cpipe->pipe_state & PIPE_SEL) {
-		cpipe->pipe_state &= ~PIPE_SEL;
 		selwakeuppri(&cpipe->pipe_sel, PSOCK);
+		if (!SEL_WAITING(&cpipe->pipe_sel))
+			cpipe->pipe_state &= ~PIPE_SEL;
 	}
 	if ((cpipe->pipe_state & PIPE_ASYNC) && cpipe->pipe_sigio)
 		pgsigio(&cpipe->pipe_sigio, SIGIO, 0);
@@ -1354,12 +1355,14 @@ pipe_poll(fp, events, active_cred, td)
 	if (revents == 0) {
 		if (events & (POLLIN | POLLRDNORM)) {
 			selrecord(td, &rpipe->pipe_sel);
-			rpipe->pipe_state |= PIPE_SEL;
+			if (SEL_WAITING(&rpipe->pipe_sel))
+				rpipe->pipe_state |= PIPE_SEL;
 		}
 
 		if (events & (POLLOUT | POLLWRNORM)) {
 			selrecord(td, &wpipe->pipe_sel);
-			wpipe->pipe_state |= PIPE_SEL;
+			if (SEL_WAITING(&wpipe->pipe_sel))
+				wpipe->pipe_state |= PIPE_SEL;
 		}
 	}
 #ifdef MAC