[dpdk-dev] [PATCH v2] vhost: allow for many vhost user ports

[Jan Wickbom]

Currently select() is used to monitor file descriptors for vhostuser
ports. This limits the number of ports possible to create since the
fd number is used as index in the fd_set and we have seen fds > 1023.
This patch changes select() to poll(). This way we can keep an
packed (pollfd) array for the fds, e.g. as many fds as the size of
the array.

Also see:
http://dpdk.org/ml/archives/dev/2016-April/037024.html

Signed-off-by: Jan Wickbom <jan.wickbom at ericsson.com>
Reported-by: Patrik Andersson <patrik.r.andersson at ericsson.com>
---

v2:
* removed unnecessary casts
* static array replacing allocated memory

 lib/librte_vhost/fd_man.c | 142 +++++++++++++++++++++++++++-------------------
 lib/librte_vhost/fd_man.h |   2 +-
 2 files changed, 85 insertions(+), 59 deletions(-)

diff --git a/lib/librte_vhost/fd_man.c b/lib/librte_vhost/fd_man.c
index 2d3eeb7..3c743e3 100644
--- a/lib/librte_vhost/fd_man.c
+++ b/lib/librte_vhost/fd_man.c
@@ -35,16 +35,43 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <sys/socket.h>
-#include <sys/select.h>
 #include <sys/time.h>
 #include <sys/types.h>
+#include <poll.h>
 #include <unistd.h>
+#include <string.h>
 
 #include <rte_common.h>
+#include <rte_malloc.h>
 #include <rte_log.h>
 
 #include "fd_man.h"
 
+#define FDPOLLERR (POLLERR | POLLHUP | POLLNVAL)
+
+
+static struct pollfd rwfds[MAX_FDS];
+
+/**
+ * Adjusts the highest index populated in the array of fds
+ * @return
+ *   The new size of fdset.
+ */
+static int
+fdset_shrink(struct fdset *pfdset)
+{
+	int idx;
+
+	for (idx = pfdset->num - 1;
+	     idx >= 0 && pfdset->fd[idx].fd == -1;
+	     idx--)
+		;
+
+	pfdset->num = idx + 1;
+
+	return pfdset->num;
+}
+
 /**
  * Returns the index in the fdset for a given fd.
  * If fd is -1, it means to search for a free entry.
@@ -56,72 +83,62 @@
 {
 	int i;
 
-	if (pfdset == NULL)
-		return -1;
-
-	for (i = 0; i < MAX_FDS && pfdset->fd[i].fd != fd; i++)
+	for (i = 0; i < pfdset->num && pfdset->fd[i].fd != fd; i++)
 		;
 
-	return i ==  MAX_FDS ? -1 : i;
+	return i == pfdset->num ? -1 : i;
 }
 
 static int
 fdset_find_free_slot(struct fdset *pfdset)
 {
-	return fdset_find_fd(pfdset, -1);
+	if (pfdset->num < MAX_FDS)
+		return pfdset->num;
+	else
+		return fdset_find_fd(pfdset, -1);
 }
 
-static int
-fdset_add_fd(struct fdset  *pfdset, int idx, int fd,
+static void
+fdset_add_fd(struct fdset *pfdset, int idx, int fd,
 	fd_cb rcb, fd_cb wcb, void *dat)
 {
 	struct fdentry *pfdentry;
 
-	if (pfdset == NULL || idx >= MAX_FDS || fd >= FD_SETSIZE)
-		return -1;
-
 	pfdentry = &pfdset->fd[idx];
 	pfdentry->fd = fd;
 	pfdentry->rcb = rcb;
 	pfdentry->wcb = wcb;
 	pfdentry->dat = dat;
-
-	return 0;
 }
 
 /**
- * Fill the read/write fd_set with the fds in the fdset.
+ * Compact the fdset and fill the read/write fds with the fds in the fdset.
  * @return
- *  the maximum fds filled in the read/write fd_set.
+ *  the number of fds filled in the read/write fds.
  */
 static int
-fdset_fill(fd_set *rfset, fd_set *wfset, struct fdset *pfdset)
+fdset_fill(struct pollfd *rwfds, struct fdset *pfdset)
 {
 	struct fdentry *pfdentry;
-	int i, maxfds = -1;
-	int num = MAX_FDS;
-
-	if (pfdset == NULL)
-		return -1;
+	int i;
+	int num;
 
-	for (i = 0; i < num; i++) {
+	for (i = 0, num = pfdset->num; i < num; i++) {
 		pfdentry = &pfdset->fd[i];
-		if (pfdentry->fd != -1) {
-			int added = 0;
-			if (pfdentry->rcb && rfset) {
-				FD_SET(pfdentry->fd, rfset);
-				added = 1;
-			}
-			if (pfdentry->wcb && wfset) {
-				FD_SET(pfdentry->fd, wfset);
-				added = 1;
-			}
-			if (added)
-				maxfds = pfdentry->fd < maxfds ?
-					maxfds : pfdentry->fd;
+
+		if (pfdentry->fd < 0) {
+			/* Hole in the list. Move the last one here */
+
+			*pfdentry = pfdset->fd[num - 1];
+			pfdset->fd[num - 1].fd = -1;
+			num = fdset_shrink(pfdset);
 		}
+		rwfds[i].fd = pfdentry->fd;
+		rwfds[i].events = pfdentry->rcb ? POLLIN : 0;
+		rwfds[i].events |= pfdentry->wcb ? POLLOUT : 0;
 	}
-	return maxfds;
+
+	return i;
 }
 
 void
@@ -132,6 +149,8 @@
 	if (pfdset == NULL)
 		return;
 
+	pthread_mutex_init(&pfdset->fd_mutex, NULL);
+
 	for (i = 0; i < MAX_FDS; i++) {
 		pfdset->fd[i].fd = -1;
 		pfdset->fd[i].dat = NULL;
@@ -152,14 +171,15 @@
 
 	pthread_mutex_lock(&pfdset->fd_mutex);
 
-	/* Find a free slot in the list. */
 	i = fdset_find_free_slot(pfdset);
-	if (i == -1 || fdset_add_fd(pfdset, i, fd, rcb, wcb, dat) < 0) {
+	if (i == -1) {
 		pthread_mutex_unlock(&pfdset->fd_mutex);
 		return -2;
 	}
 
-	pfdset->num++;
+	fdset_add_fd(pfdset, i, fd, rcb, wcb, dat);
+	if (i == pfdset->num)
+		pfdset->num++;
 
 	pthread_mutex_unlock(&pfdset->fd_mutex);
 
@@ -189,7 +209,7 @@
 			pfdset->fd[i].fd = -1;
 			pfdset->fd[i].rcb = pfdset->fd[i].wcb = NULL;
 			pfdset->fd[i].dat = NULL;
-			pfdset->num--;
+			fdset_shrink(pfdset);
 			i = -1;
 		}
 		pthread_mutex_unlock(&pfdset->fd_mutex);
@@ -211,12 +231,12 @@
 
 	pfdset->fd[index].fd = -1;
 	pfdset->fd[index].rcb = pfdset->fd[index].wcb = NULL;
-	pfdset->fd[index].dat = NULL;
-	pfdset->num--;
+	fdset_shrink(pfdset);
 
 	pthread_mutex_unlock(&pfdset->fd_mutex);
 }
 
+
 /**
  * This functions runs in infinite blocking loop until there is no fd in
  * pfdset. It calls corresponding r/w handler if there is event on the fd.
@@ -229,44 +249,47 @@
 void
 fdset_event_dispatch(struct fdset *pfdset)
 {
-	fd_set rfds, wfds;
-	int i, maxfds;
+	int i;
 	struct fdentry *pfdentry;
-	int num = MAX_FDS;
+	int numfds;
 	fd_cb rcb, wcb;
 	void *dat;
 	int fd;
 	int remove1, remove2;
 	int ret;
+	int handled;
 
 	if (pfdset == NULL)
 		return;
 
+	memset(rwfds, 0, sizeof(rwfds));
+
 	while (1) {
-		struct timeval tv;
-		tv.tv_sec = 1;
-		tv.tv_usec = 0;
-		FD_ZERO(&rfds);
-		FD_ZERO(&wfds);
 		pthread_mutex_lock(&pfdset->fd_mutex);
 
-		maxfds = fdset_fill(&rfds, &wfds, pfdset);
+		numfds = fdset_fill(rwfds, pfdset);
 
 		pthread_mutex_unlock(&pfdset->fd_mutex);
 
 		/*
-		 * When select is blocked, other threads might unregister
+		 * When poll is blocked, other threads might unregister
 		 * listenfds from and register new listenfds into fdset.
-		 * When select returns, the entries for listenfds in the fdset
+		 * When poll returns, the entries for listenfds in the fdset
 		 * might have been updated. It is ok if there is unwanted call
 		 * for new listenfds.
 		 */
-		ret = select(maxfds + 1, &rfds, &wfds, NULL, &tv);
+		ret = poll(rwfds, numfds, 1000 /* millisecs */);
+
 		if (ret <= 0)
 			continue;
 
-		for (i = 0; i < num; i++) {
+		for (i = handled = 0; i < numfds && handled < ret; i++) {
+			if (!rwfds[i].revents)
+				continue;
+
+			handled++;
 			remove1 = remove2 = 0;
+
 			pthread_mutex_lock(&pfdset->fd_mutex);
 			pfdentry = &pfdset->fd[i];
 			fd = pfdentry->fd;
@@ -275,9 +298,12 @@
 			dat = pfdentry->dat;
 			pfdentry->busy = 1;
 			pthread_mutex_unlock(&pfdset->fd_mutex);
-			if (fd >= 0 && FD_ISSET(fd, &rfds) && rcb)
+
+			if (fd >= 0 && rcb &&
+			    rwfds[i].revents & (POLLIN | FDPOLLERR))
 				rcb(fd, dat, &remove1);
-			if (fd >= 0 && FD_ISSET(fd, &wfds) && wcb)
+			if (fd >= 0 && wcb &&
+			    rwfds[i].revents & (POLLOUT | FDPOLLERR))
 				wcb(fd, dat, &remove2);
 			pfdentry->busy = 0;
 			/*
diff --git a/lib/librte_vhost/fd_man.h b/lib/librte_vhost/fd_man.h
index bd66ed1..b5ba688 100644
--- a/lib/librte_vhost/fd_man.h
+++ b/lib/librte_vhost/fd_man.h
@@ -51,7 +51,7 @@ struct fdentry {
 struct fdset {
 	struct fdentry fd[MAX_FDS];
 	pthread_mutex_t fd_mutex;
-	int num;	/* current fd number of this fdset */
+	int num;	/* highest index occupied in fd array + 1 */
 };
 
 
-- 
1.9.1