[PATCH bpf-next v8 3/4] bpf: support specifying ingress via xdp_md context in BPF_PROG_TEST_RUN

[Zvi Effron <zeffron@xxxxxxxxxxxxx>]

Support specifying the ingress_ifindex and rx_queue_index of xdp_md
contexts for BPF_PROG_TEST_RUN.

The intended use case is to allow testing XDP programs that make decisions
based on the ingress interface or RX queue.

If ingress_ifindex is specified, look up the device by the provided index
in the current namespace and use its xdp_rxq for the xdp_buff. If the
rx_queue_index is out of range, or is non-zero when the ingress_ifindex is
0, return -EINVAL.

Co-developed-by: Cody Haas <chaas@xxxxxxxxxxxxx>
Signed-off-by: Cody Haas <chaas@xxxxxxxxxxxxx>
Co-developed-by: Lisa Watanabe <lwatanabe@xxxxxxxxxxxxx>
Signed-off-by: Lisa Watanabe <lwatanabe@xxxxxxxxxxxxx>
Signed-off-by: Zvi Effron <zeffron@xxxxxxxxxxxxx>
---
 net/bpf/test_run.c | 56 ++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 49 insertions(+), 7 deletions(-)

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 229c5deb813c..cda8375bbbaf 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -690,18 +690,60 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 static int xdp_convert_md_to_buff(struct xdp_md *xdp_md, struct xdp_buff *xdp)
 {
+	unsigned int ingress_ifindex, rx_queue_index;
+	struct netdev_rx_queue *rxqueue;
+	struct net_device *device;
+
 	if (!xdp_md)
 		return 0;
 
 	if (xdp_md->egress_ifindex != 0)
 		return -EINVAL;
 
-	if (xdp_md->ingress_ifindex != 0 || xdp_md->rx_queue_index != 0)
+	ingress_ifindex = xdp_md->ingress_ifindex;
+	rx_queue_index = xdp_md->rx_queue_index;
+
+	if (!ingress_ifindex && rx_queue_index)
 		return -EINVAL;
 
-	xdp->data = xdp->data_meta + xdp_md->data;
+	if (ingress_ifindex) {
+		device = dev_get_by_index(current->nsproxy->net_ns,
+					  ingress_ifindex);
+		if (!device)
+			return -ENODEV;
+
+		if (rx_queue_index >= device->real_num_rx_queues)
+			goto free_dev;
+
+		rxqueue = __netif_get_rx_queue(device, rx_queue_index);
 
+		if (!xdp_rxq_info_is_reg(&rxqueue->xdp_rxq))
+			goto free_dev;
+
+		xdp->rxq = &rxqueue->xdp_rxq;
+		/* The device is now tracked in the xdp->rxq for later
+		 * dev_put()
+		 */
+	}
+
+	xdp->data = xdp->data_meta + xdp_md->data;
 	return 0;
+
+free_dev:
+	dev_put(device);
+	return -EINVAL;
+}
+
+static void xdp_convert_buff_to_md(struct xdp_buff *xdp, struct xdp_md *xdp_md)
+{
+	if (!xdp_md)
+		return;
+
+	xdp_md->data = xdp->data - xdp->data_meta;
+	xdp_md->data_end = xdp->data_end - xdp->data_meta;
+
+	if (xdp_md->ingress_ifindex)
+		dev_put(xdp->rxq->dev);
 }
 
 int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
@@ -753,6 +795,11 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 	bpf_prog_change_xdp(NULL, prog);
 	ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
+	/* We convert the xdp_buff back to an xdp_md before checking the return
+	 * code so the reference count of any held netdevice will be decremented
+	 * even if the test run failed.
+	 */
+	xdp_convert_buff_to_md(&xdp, ctx);
 	if (ret)
 		goto out;
 
@@ -760,11 +807,6 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	    xdp.data_end != xdp.data_meta + size)
 		size = xdp.data_end - xdp.data_meta;
 
-	if (ctx) {
-		ctx->data = xdp.data - xdp.data_meta;
-		ctx->data_end = xdp.data_end - xdp.data_meta;
-	}
-
 	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval,
 			      duration);
 	if (!ret)
-- 
2.31.1