OpenCloudOS-Kernel/samples/bpf/xdp_rxq_info_kern.c

140 lines
3.2 KiB
C
Raw Normal View History

/* 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>
samples/bpf: extend xdp_rxq_info to read packet payload There is a cost associated with reading the packet data payload that this test ignored. Add option --read to allow enabling reading part of the payload. This sample/tool helps us analyse an issue observed with a NIC mlx5 (ConnectX-5 Ex) and an Intel(R) Xeon(R) CPU E5-1650 v4. With no_touch of data: Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:no_touch XDP stats CPU pps issue-pps XDP-RX CPU 0 14,465,157 0 XDP-RX CPU 1 14,464,728 0 XDP-RX CPU 2 14,465,283 0 XDP-RX CPU 3 14,465,282 0 XDP-RX CPU 4 14,464,159 0 XDP-RX CPU 5 14,465,379 0 XDP-RX CPU total 86,789,992 When not touching data, we observe that the CPUs have idle cycles. When reading data the CPUs are 100% busy in softirq. With reading data: Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:read XDP stats CPU pps issue-pps XDP-RX CPU 0 9,620,639 0 XDP-RX CPU 1 9,489,843 0 XDP-RX CPU 2 9,407,854 0 XDP-RX CPU 3 9,422,289 0 XDP-RX CPU 4 9,321,959 0 XDP-RX CPU 5 9,395,242 0 XDP-RX CPU total 56,657,828 The effect seen above is a result of cache-misses occuring when more RXQs are being used. Based on perf-event observations, our conclusion is that the CPUs DDIO (Direct Data I/O) choose to deliver packet into main memory, instead of L3-cache. We also found, that this can be mitigated by either using less RXQs or by reducing NICs the RX-ring size. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-06-25 22:27:43 +08:00
#include <uapi/linux/if_ether.h>
#include <uapi/linux/in.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;
samples/bpf: extend xdp_rxq_info to read packet payload There is a cost associated with reading the packet data payload that this test ignored. Add option --read to allow enabling reading part of the payload. This sample/tool helps us analyse an issue observed with a NIC mlx5 (ConnectX-5 Ex) and an Intel(R) Xeon(R) CPU E5-1650 v4. With no_touch of data: Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:no_touch XDP stats CPU pps issue-pps XDP-RX CPU 0 14,465,157 0 XDP-RX CPU 1 14,464,728 0 XDP-RX CPU 2 14,465,283 0 XDP-RX CPU 3 14,465,282 0 XDP-RX CPU 4 14,464,159 0 XDP-RX CPU 5 14,465,379 0 XDP-RX CPU total 86,789,992 When not touching data, we observe that the CPUs have idle cycles. When reading data the CPUs are 100% busy in softirq. With reading data: Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:read XDP stats CPU pps issue-pps XDP-RX CPU 0 9,620,639 0 XDP-RX CPU 1 9,489,843 0 XDP-RX CPU 2 9,407,854 0 XDP-RX CPU 3 9,422,289 0 XDP-RX CPU 4 9,321,959 0 XDP-RX CPU 5 9,395,242 0 XDP-RX CPU total 56,657,828 The effect seen above is a result of cache-misses occuring when more RXQs are being used. Based on perf-event observations, our conclusion is that the CPUs DDIO (Direct Data I/O) choose to deliver packet into main memory, instead of L3-cache. We also found, that this can be mitigated by either using less RXQs or by reducing NICs the RX-ring size. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-06-25 22:27:43 +08:00
__u32 options;
};
enum cfg_options_flags {
NO_TOUCH = 0x0U,
READ_MEM = 0x1U,
SWAP_MAC = 0x2U,
};
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,
};
static __always_inline
void swap_src_dst_mac(void *data)
{
unsigned short *p = data;
unsigned short dst[3];
dst[0] = p[0];
dst[1] = p[1];
dst[2] = p[2];
p[0] = p[3];
p[1] = p[4];
p[2] = p[5];
p[3] = dst[0];
p[4] = dst[1];
p[5] = dst[2];
}
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++;
samples/bpf: extend xdp_rxq_info to read packet payload There is a cost associated with reading the packet data payload that this test ignored. Add option --read to allow enabling reading part of the payload. This sample/tool helps us analyse an issue observed with a NIC mlx5 (ConnectX-5 Ex) and an Intel(R) Xeon(R) CPU E5-1650 v4. With no_touch of data: Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:no_touch XDP stats CPU pps issue-pps XDP-RX CPU 0 14,465,157 0 XDP-RX CPU 1 14,464,728 0 XDP-RX CPU 2 14,465,283 0 XDP-RX CPU 3 14,465,282 0 XDP-RX CPU 4 14,464,159 0 XDP-RX CPU 5 14,465,379 0 XDP-RX CPU total 86,789,992 When not touching data, we observe that the CPUs have idle cycles. When reading data the CPUs are 100% busy in softirq. With reading data: Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:read XDP stats CPU pps issue-pps XDP-RX CPU 0 9,620,639 0 XDP-RX CPU 1 9,489,843 0 XDP-RX CPU 2 9,407,854 0 XDP-RX CPU 3 9,422,289 0 XDP-RX CPU 4 9,321,959 0 XDP-RX CPU 5 9,395,242 0 XDP-RX CPU total 56,657,828 The effect seen above is a result of cache-misses occuring when more RXQs are being used. Based on perf-event observations, our conclusion is that the CPUs DDIO (Direct Data I/O) choose to deliver packet into main memory, instead of L3-cache. We also found, that this can be mitigated by either using less RXQs or by reducing NICs the RX-ring size. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-06-25 22:27:43 +08:00
/* Default: Don't touch packet data, only count packets */
if (unlikely(config->options & (READ_MEM|SWAP_MAC))) {
samples/bpf: extend xdp_rxq_info to read packet payload There is a cost associated with reading the packet data payload that this test ignored. Add option --read to allow enabling reading part of the payload. This sample/tool helps us analyse an issue observed with a NIC mlx5 (ConnectX-5 Ex) and an Intel(R) Xeon(R) CPU E5-1650 v4. With no_touch of data: Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:no_touch XDP stats CPU pps issue-pps XDP-RX CPU 0 14,465,157 0 XDP-RX CPU 1 14,464,728 0 XDP-RX CPU 2 14,465,283 0 XDP-RX CPU 3 14,465,282 0 XDP-RX CPU 4 14,464,159 0 XDP-RX CPU 5 14,465,379 0 XDP-RX CPU total 86,789,992 When not touching data, we observe that the CPUs have idle cycles. When reading data the CPUs are 100% busy in softirq. With reading data: Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:read XDP stats CPU pps issue-pps XDP-RX CPU 0 9,620,639 0 XDP-RX CPU 1 9,489,843 0 XDP-RX CPU 2 9,407,854 0 XDP-RX CPU 3 9,422,289 0 XDP-RX CPU 4 9,321,959 0 XDP-RX CPU 5 9,395,242 0 XDP-RX CPU total 56,657,828 The effect seen above is a result of cache-misses occuring when more RXQs are being used. Based on perf-event observations, our conclusion is that the CPUs DDIO (Direct Data I/O) choose to deliver packet into main memory, instead of L3-cache. We also found, that this can be mitigated by either using less RXQs or by reducing NICs the RX-ring size. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-06-25 22:27:43 +08:00
struct ethhdr *eth = data;
if (eth + 1 > data_end)
return XDP_ABORTED;
/* Avoid compiler removing this: Drop non 802.3 Ethertypes */
if (ntohs(eth->h_proto) < ETH_P_802_3_MIN)
return XDP_ABORTED;
/* XDP_TX requires changing MAC-addrs, else HW may drop.
* Can also be enabled with --swapmac (for test purposes)
*/
if (unlikely(config->options & SWAP_MAC))
swap_src_dst_mac(data);
samples/bpf: extend xdp_rxq_info to read packet payload There is a cost associated with reading the packet data payload that this test ignored. Add option --read to allow enabling reading part of the payload. This sample/tool helps us analyse an issue observed with a NIC mlx5 (ConnectX-5 Ex) and an Intel(R) Xeon(R) CPU E5-1650 v4. With no_touch of data: Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:no_touch XDP stats CPU pps issue-pps XDP-RX CPU 0 14,465,157 0 XDP-RX CPU 1 14,464,728 0 XDP-RX CPU 2 14,465,283 0 XDP-RX CPU 3 14,465,282 0 XDP-RX CPU 4 14,464,159 0 XDP-RX CPU 5 14,465,379 0 XDP-RX CPU total 86,789,992 When not touching data, we observe that the CPUs have idle cycles. When reading data the CPUs are 100% busy in softirq. With reading data: Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:read XDP stats CPU pps issue-pps XDP-RX CPU 0 9,620,639 0 XDP-RX CPU 1 9,489,843 0 XDP-RX CPU 2 9,407,854 0 XDP-RX CPU 3 9,422,289 0 XDP-RX CPU 4 9,321,959 0 XDP-RX CPU 5 9,395,242 0 XDP-RX CPU total 56,657,828 The effect seen above is a result of cache-misses occuring when more RXQs are being used. Based on perf-event observations, our conclusion is that the CPUs DDIO (Direct Data I/O) choose to deliver packet into main memory, instead of L3-cache. We also found, that this can be mitigated by either using less RXQs or by reducing NICs the RX-ring size. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-06-25 22:27:43 +08:00
}
return config->action;
}
char _license[] SEC("license") = "GPL";