samples/bpf: program demonstrating access to xdp_rxq_info

This sample program can be used for monitoring and reporting how many
packets per sec (pps) are received per NIC RX queue index and which
CPU processed the packet. In itself it is a useful tool for quickly
identifying RSS imbalance issues, see below.

The default XDP action is XDP_PASS in-order to provide a monitor
mode. For benchmarking purposes it is possible to specify other XDP
actions on the cmdline --action.

Output below shows an imbalance RSS case where most RXQ's deliver to
CPU-0 while CPU-2 only get packets from a single RXQ.  Looking at
things from a CPU level the two CPUs are processing approx the same
amount, BUT looking at the rx_queue_index levels it is clear that
RXQ-2 receive much better service, than other RXQs which all share CPU-0.

Running XDP on dev:i40e1 (ifindex:3) action:XDP_PASS
XDP stats       CPU     pps         issue-pps
XDP-RX CPU      0       900,473     0
XDP-RX CPU      2       906,921     0
XDP-RX CPU      total   1,807,395

RXQ stats       RXQ:CPU pps         issue-pps
rx_queue_index    0:0   180,098     0
rx_queue_index    0:sum 180,098
rx_queue_index    1:0   180,098     0
rx_queue_index    1:sum 180,098
rx_queue_index    2:2   906,921     0
rx_queue_index    2:sum 906,921
rx_queue_index    3:0   180,098     0
rx_queue_index    3:sum 180,098
rx_queue_index    4:0   180,082     0
rx_queue_index    4:sum 180,082
rx_queue_index    5:0   180,093     0
rx_queue_index    5:sum 180,093

Signed-off-by: Jesper Dangaard Brouer <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: netoptimizer

samples/bpf/Makefile

@@ -41,6 +41,7 @@ hostprogs-y += xdp_redirect
 hostprogs-y += xdp_redirect_map
 hostprogs-y += xdp_redirect_cpu
 hostprogs-y += xdp_monitor
+hostprogs-y += xdp_rxq_info
 hostprogs-y += syscall_tp
 
 # Libbpf dependencies
@@ -90,6 +91,7 @@ xdp_redirect-objs := bpf_load.o $(LIBBPF) xdp_redirect_user.o
 xdp_redirect_map-objs := bpf_load.o $(LIBBPF) xdp_redirect_map_user.o
 xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o
 xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o
+xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o
 syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
 
 # Tell kbuild to always build the programs
@@ -139,6 +141,7 @@ always += xdp_redirect_kern.o
 always += xdp_redirect_map_kern.o
 always += xdp_redirect_cpu_kern.o
 always += xdp_monitor_kern.o
+always += xdp_rxq_info_kern.o
 always += syscall_tp_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
@@ -182,6 +185,7 @@ HOSTLOADLIBES_xdp_redirect += -lelf
 HOSTLOADLIBES_xdp_redirect_map += -lelf
 HOSTLOADLIBES_xdp_redirect_cpu += -lelf
 HOSTLOADLIBES_xdp_monitor += -lelf
+HOSTLOADLIBES_xdp_rxq_info += -lelf
 HOSTLOADLIBES_syscall_tp += -lelf
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:

samples/bpf/xdp_rxq_info_kern.c

@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
+ *
+ *  Example howto extract XDP RX-queue info
+ */
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+/* Config setup from with userspace
+ *
+ * User-side setup ifindex in config_map, to verify that
+ * ctx->ingress_ifindex is correct (against configured ifindex)
+ */
+struct config {
+	__u32 action;
+	int ifindex;
+};
+struct bpf_map_def SEC("maps") config_map = {
+	.type		= BPF_MAP_TYPE_ARRAY,
+	.key_size	= sizeof(int),
+	.value_size	= sizeof(struct config),
+	.max_entries	= 1,
+};
+
+/* Common stats data record (shared with userspace) */
+struct datarec {
+	__u64 processed;
+	__u64 issue;
+};
+
+struct bpf_map_def SEC("maps") stats_global_map = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(struct datarec),
+	.max_entries	= 1,
+};
+
+#define MAX_RXQs 64
+
+/* Stats per rx_queue_index (per CPU) */
+struct bpf_map_def SEC("maps") rx_queue_index_map = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(struct datarec),
+	.max_entries	= MAX_RXQs + 1,
+};
+
+SEC("xdp_prog0")
+int  xdp_prognum0(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct datarec *rec, *rxq_rec;
+	int ingress_ifindex;
+	struct config *config;
+	u32 key = 0;
+
+	/* Global stats record */
+	rec = bpf_map_lookup_elem(&stats_global_map, &key);
+	if (!rec)
+		return XDP_ABORTED;
+	rec->processed++;
+
+	/* Accessing ctx->ingress_ifindex, cause BPF to rewrite BPF
+	 * instructions inside kernel to access xdp_rxq->dev->ifindex
+	 */
+	ingress_ifindex = ctx->ingress_ifindex;
+
+	config = bpf_map_lookup_elem(&config_map, &key);
+	if (!config)
+		return XDP_ABORTED;
+
+	/* Simple test: check ctx provided ifindex is as expected */
+	if (ingress_ifindex != config->ifindex) {
+		/* count this error case */
+		rec->issue++;
+		return XDP_ABORTED;
+	}
+
+	/* Update stats per rx_queue_index. Handle if rx_queue_index
+	 * is larger than stats map can contain info for.
+	 */
+	key = ctx->rx_queue_index;
+	if (key >= MAX_RXQs)
+		key = MAX_RXQs;
+	rxq_rec = bpf_map_lookup_elem(&rx_queue_index_map, &key);
+	if (!rxq_rec)
+		return XDP_ABORTED;
+	rxq_rec->processed++;
+	if (key == MAX_RXQs)
+		rxq_rec->issue++;
+
+	return config->action;
+}
+
+char _license[] SEC("license") = "GPL";