net: fix psock_fanout selftest hash collision

Fix flaky results with PACKET_FANOUT_HASH depending on whether the
two flows hash into the same packet socket or not.

Also adds tests for PACKET_FANOUT_LB and PACKET_FANOUT_CPU and
replaces the counting method with a packet ring.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 120 insertions, 40 deletions

diff --git a/tools/testing/selftests/net-afpacket/psock_fanout.c b/tools/testing/selftests/net-afpacket/psock_fanout.c
index af9b0196b0be..f765f09931bd 100644
--- a/tools/testing/selftests/net-afpacket/psock_fanout.c
+++ b/tools/testing/selftests/net-afpacket/psock_fanout.c
@@ -16,11 +16,11 @@
  *   The test currently runs for
  *   - PACKET_FANOUT_HASH
  *   - PACKET_FANOUT_HASH with PACKET_FANOUT_FLAG_ROLLOVER
+ *   - PACKET_FANOUT_LB
+ *   - PACKET_FANOUT_CPU
  *   - PACKET_FANOUT_ROLLOVER
  *
  * Todo:
- * - datapath: PACKET_FANOUT_LB
- * - datapath: PACKET_FANOUT_CPU
  * - functionality: PACKET_FANOUT_FLAG_DEFRAG
  *
  * License (GPLv2):
@@ -39,18 +39,23 @@
  * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
+#define _GNU_SOURCE             /* for sched_setaffinity */
+
 #include <arpa/inet.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <linux/filter.h>
 #include <linux/if_packet.h>
 #include <net/ethernet.h>
 #include <netinet/ip.h>
 #include <netinet/udp.h>
-#include <fcntl.h>
+#include <poll.h>
+#include <sched.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <sys/mman.h>
 #include <sys/socket.h>
 #include <sys/stat.h>
 #include <sys/types.h>
@@ -58,6 +63,8 @@
 
 #define DATA_LEN                        100
 #define DATA_CHAR                       'a'
+#define RING_NUM_FRAMES                 20
+#define PORT_BASE                       8000
 
 static void pair_udp_open(int fds[], uint16_t port)
 {
@@ -162,37 +169,55 @@ static int sock_fanout_open(uint16_t typeflags, int num_packets)
                 return -1;
         }
 
-        val = sizeof(struct iphdr) + sizeof(struct udphdr) + DATA_LEN;
-        val *= num_packets;
-        /* hack: apparently, the above calculation is too small (TODO: fix) */
-        val *= 3;
-        if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val))) {
-                perror("setsockopt SO_RCVBUF");
-                exit(1);
-        }
-
         sock_fanout_setfilter(fd);
         return fd;
 }
 
-static void sock_fanout_read(int fds[], const int expect[])
+static char *sock_fanout_open_ring(int fd)
 {
-        struct tpacket_stats stats;
-        socklen_t ssize;
-        int ret[2];
+        struct tpacket_req req = {
+                .tp_block_size = getpagesize(),
+                .tp_frame_size = getpagesize(),
+                .tp_block_nr   = RING_NUM_FRAMES,
+                .tp_frame_nr   = RING_NUM_FRAMES,
+        };
+        char *ring;
 
-        ssize = sizeof(stats);
-        if (getsockopt(fds[0], SOL_PACKET, PACKET_STATISTICS, &stats, &ssize)) {
-                perror("getsockopt statistics 0");
+        if (setsockopt(fd, SOL_PACKET, PACKET_RX_RING, (void *) &req,
+                       sizeof(req))) {
+                perror("packetsock ring setsockopt");
                 exit(1);
         }
-        ret[0] = stats.tp_packets - stats.tp_drops;
-        ssize = sizeof(stats);
-        if (getsockopt(fds[1], SOL_PACKET, PACKET_STATISTICS, &stats, &ssize)) {
-                perror("getsockopt statistics 1");
+
+        ring = mmap(0, req.tp_block_size * req.tp_block_nr,
+                    PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+        if (!ring) {
+                fprintf(stderr, "packetsock ring mmap\n");
                 exit(1);
         }
-        ret[1] = stats.tp_packets - stats.tp_drops;
+
+        return ring;
+}
+
+static int sock_fanout_read_ring(int fd, void *ring)
+{
+        struct tpacket_hdr *header = ring;
+        int count = 0;
+
+        while (header->tp_status & TP_STATUS_USER && count < RING_NUM_FRAMES) {
+                count++;
+                header = ring + (count * getpagesize());
+        }
+
+        return count;
+}
+
+static int sock_fanout_read(int fds[], char *rings[], const int expect[])
+{
+        int ret[2];
+
+        ret[0] = sock_fanout_read_ring(fds[0], rings[0]);
+        ret[1] = sock_fanout_read_ring(fds[1], rings[1]);
 
         fprintf(stderr, "info: count=%d,%d, expect=%d,%d\n",
                         ret[0], ret[1], expect[0], expect[1]);
@@ -200,8 +225,10 @@ static void sock_fanout_read(int fds[], const int expect[])
         if ((!(ret[0] == expect[0] && ret[1] == expect[1])) &&
             (!(ret[0] == expect[1] && ret[1] == expect[0]))) {
                 fprintf(stderr, "ERROR: incorrect queue lengths\n");
-                exit(1);
+                return 1;
         }
+
+        return 0;
 }
 
 /* Test illegal mode + flag combination */
@@ -253,11 +280,12 @@ static void test_control_group(void)
         }
 }
 
-static void test_datapath(uint16_t typeflags,
-                          const int expect1[], const int expect2[])
+static int test_datapath(uint16_t typeflags, int port_off,
+                         const int expect1[], const int expect2[])
 {
         const int expect0[] = { 0, 0 };
-        int fds[2], fds_udp[2][2];
+        char *rings[2];