1 files changed, 19 insertions, 13 deletions

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 19c679456a0e..4cead341ae57 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -613,7 +613,16 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 {
 	struct xsk_umem_info *umem;
 	struct xsk_umem_config cfg = {
-		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		/* We recommend that you set the fill ring size >= HW RX ring size +
+		 * AF_XDP RX ring size. Make sure you fill up the fill ring
+		 * with buffers at regular intervals, and you will with this setting
+		 * avoid allocation failures in the driver. These are usually quite
+		 * expensive since drivers have not been written to assume that
+		 * allocation failures are common. For regular sockets, kernel
+		 * allocated memory is used that only runs out in OOM situations
+		 * that should be rare.
+		 */
+		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = opt_xsk_frame_size,
 		.frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM,
@@ -640,13 +649,13 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
 	u32 idx;
 
 	ret = xsk_ring_prod__reserve(&umem->fq,
-				     XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
-	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
+				     XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, &idx);
+	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS * 2)
 		exit_with_error(-ret);
-	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
+	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS * 2; i++)
 		*xsk_ring_prod__fill_addr(&umem->fq, idx++) =
 			i * opt_xsk_frame_size;
-	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
+	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS * 2);
 }
 
 static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem,
@@ -888,9 +897,6 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk,
 	if (!xsk->outstanding_tx)
 		return;
 
-	if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx))
-		kick_tx(xsk);
-
 	ndescs = (xsk->outstanding_tx > opt_batch_size) ? opt_batch_size :
 		xsk->outstanding_tx;
 
@@ -1004,7 +1010,7 @@ static void rx_drop_all(void)
 	}
 }
 
-static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size)
+static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size)
 {
 	u32 idx;
 	unsigned int i;
@@ -1017,14 +1023,14 @@ static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size)
 	for (i = 0; i < batch_size; i++) {
 		struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx,
 								  idx + i);
-		tx_desc->addr = (frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT;
+		tx_desc->addr = (*frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT;
 		tx_desc->len = PKT_SIZE;
 	}
 
 	xsk_ring_prod__submit(&xsk->tx, batch_size);
 	xsk->outstanding_tx += batch_size;
-	frame_nb += batch_size;
-	frame_nb %= NUM_FRAMES;
+	*frame_nb += batch_size;
+	*frame_nb %= NUM_FRAMES;
 	complete_tx_only(xsk, batch_size);
 }
 
@@ -1080,7 +1086,7 @@ static void tx_only_all(void)
 		}
 
 		for (i = 0; i < num_socks; i++)
-			tx_only(xsks[i], frame_nb[i], batch_size);
+			tx_only(xsks[i], &frame_nb[i], batch_size);
 
 		pkt_cnt += batch_size;