[net-next V2 PATCH 5/5] samples/bpf: add cpumap sample program xdp_redirect_cpu
From: Jesper Dangaard Brouer <hidden>
Date: 2017-09-29 16:34:34
Subsystem:
bpf [general] (safe dynamic programs and tools), the rest, xdp (express data path) · Maintainers:
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko, Eduard Zingerman, Kumar Kartikeya Dwivedi, Linus Torvalds, David S. Miller, Jakub Kicinski, Jesper Dangaard Brouer, John Fastabend
This sample program show how to use cpumap and the associated tracepoints. It provides command line stats, which shows how the XDP-RX process, cpumap-enqueue and cpumap kthread dequeue is cooperating on a per CPU basis. It also utilize the xdp_exception and xdp_redirect_err transpoints to allow users quickly to identify setup issues. One issue with ixgbe driver is that the driver reset the link when loading XDP. This reset the procfs smp_affinity settings. Thus, after loading the program, these must be reconfigured. The easiest workaround it to reduce the RX-queue to e.g. two via: # ethtool --set-channels ixgbe1 combined 2 And then add CPUs above 0 and 1, like: # xdp_redirect_cpu --dev ixgbe1 --prog 2 --cpu 2 --cpu 3 --cpu 4 Another issue with ixgbe is that the page recycle mechanism is tied to the RX-ring size. And the default setting of 512 elements is too small. This is the same issue with regular devmap XDP_REDIRECT. To overcome this I've been using 1024 rx-ring size: # ethtool -G ixgbe1 rx 1024 tx 1024 Signed-off-by: Jesper Dangaard Brouer <redacted> --- samples/bpf/Makefile | 4 samples/bpf/xdp_redirect_cpu_kern.c | 640 +++++++++++++++++++++++++++++++++++ samples/bpf/xdp_redirect_cpu_user.c | 639 +++++++++++++++++++++++++++++++++++ 3 files changed, 1283 insertions(+) create mode 100644 samples/bpf/xdp_redirect_cpu_kern.c create mode 100644 samples/bpf/xdp_redirect_cpu_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index ebc2ad69b62c..52c4dab2c153 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile@@ -39,6 +39,7 @@ hostprogs-y += per_socket_stats_example hostprogs-y += load_sock_ops hostprogs-y += xdp_redirect hostprogs-y += xdp_redirect_map +hostprogs-y += xdp_redirect_cpu hostprogs-y += xdp_monitor hostprogs-y += syscall_tp
@@ -84,6 +85,7 @@ test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o 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 syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
@@ -129,6 +131,7 @@ always += tcp_iw_kern.o always += tcp_clamp_kern.o always += xdp_redirect_kern.o always += xdp_redirect_map_kern.o +always += xdp_redirect_cpu_kern.o always += xdp_monitor_kern.o always += syscall_tp_kern.o
@@ -169,6 +172,7 @@ HOSTLOADLIBES_xdp_tx_iptunnel += -lelf HOSTLOADLIBES_test_map_in_map += -lelf HOSTLOADLIBES_xdp_redirect += -lelf HOSTLOADLIBES_xdp_redirect_map += -lelf +HOSTLOADLIBES_xdp_redirect_cpu += -lelf HOSTLOADLIBES_xdp_monitor += -lelf HOSTLOADLIBES_syscall_tp += -lelf
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
new file mode 100644
index 000000000000..7403e7841a88
--- /dev/null
+++ b/samples/bpf/xdp_redirect_cpu_kern.c@@ -0,0 +1,640 @@ +/* XDP redirect to CPUs via cpumap (BPF_MAP_TYPE_CPUMAP) + * + * GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. + */ +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/if_vlan.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/in.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/udp.h> + +#include <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +#define MAX_CPUS 12 /* WARNING - sync with _user.c */ + +/* Special map type that can XDP_REDIRECT frames to another CPU */ +struct bpf_map_def SEC("maps") cpu_map = { + .type = BPF_MAP_TYPE_CPUMAP, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = MAX_CPUS, +}; + +/* Common stats data record to keep userspace more simple */ +struct datarec { + __u64 processed; + __u64 dropped; + __u64 issue; +}; + +/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success + * feedback. Redirect TX errors can be caught via a tracepoint. + */ +struct bpf_map_def SEC("maps") rx_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 1, +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") redirect_err_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 2, + /* TODO: have entries for all possible errno's */ +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = MAX_CPUS, +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") cpumap_kthread_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 1, +}; + +/* Set of maps controlling available CPU, and for iterating through + * selectable redirect CPUs. + */ +struct bpf_map_def SEC("maps") cpus_available = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = MAX_CPUS, +}; +struct bpf_map_def SEC("maps") cpus_count = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = 1, +}; +struct bpf_map_def SEC("maps") cpus_iterator = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = 1, +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") exception_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 1, +}; + +/* Helper parse functions */ + +/* Parse Ethernet layer 2, extract network layer 3 offset and protocol + * + * Returns false on error and non-supported ether-type + */ +struct vlan_hdr { + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; + +static __always_inline +bool parse_eth(struct ethhdr *eth, void *data_end, + u16 *eth_proto, u64 *l3_offset) +{ + u16 eth_type; + u64 offset; + + offset = sizeof(*eth); + if ((void *)eth + offset > data_end) + return false; + + eth_type = eth->h_proto; + + /* Skip non 802.3 Ethertypes */ + if (unlikely(ntohs(eth_type) < ETH_P_802_3_MIN)) + return false; + + /* Handle VLAN tagged packet */ + if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) { + struct vlan_hdr *vlan_hdr; + + vlan_hdr = (void *)eth + offset; + offset += sizeof(*vlan_hdr); + if ((void *)eth + offset > data_end) + return false; + eth_type = vlan_hdr->h_vlan_encapsulated_proto; + } + /* TODO: Handle double VLAN tagged packet */ + + *eth_proto = ntohs(eth_type); + *l3_offset = offset; + return true; +} + +static __always_inline +u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct iphdr *iph = data + nh_off; + struct udphdr *udph; + u16 dport; + + if (iph + 1 > data_end) + return 0; + if (!(iph->protocol == IPPROTO_UDP)) + return 0; + + udph = (void *)(iph + 1); + if (udph + 1 > data_end) + return 0; + + dport = ntohs(udph->dest); + return dport; +} + +static __always_inline +int get_proto_ipv4(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct iphdr *iph = data + nh_off; + + if (iph + 1 > data_end) + return 0; + return iph->protocol; +} + +static __always_inline +int get_proto_ipv6(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ipv6hdr *ip6h = data + nh_off; + + if (ip6h + 1 > data_end) + return 0; + return ip6h->nexthdr; +} + +SEC("xdp_cpu_map0") +int xdp_prognum0_no_touch(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct datarec* rec; + u32 cpu_dest; + u32 key = 0; + + /* Only use first entry in cpus_available */ + u32 *cpu_selected; + cpu_selected = bpf_map_lookup_elem(&cpus_available, &key); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (rec) + rec->processed++; + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map1_touch_data") +int xdp_prognum1_touch_data(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + volatile u16 eth_type; + struct datarec* rec; + u32 cpu_dest; + u32 key = 0; + + /* Only use first entry in cpus_available */ + u32 *cpu_selected; + cpu_selected = bpf_map_lookup_elem(&cpus_available, &key); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Validate packet length is minimum Eth header size */ + if (eth + 1 > data_end) { + return XDP_ABORTED; + } + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + /* Read packet data, and use it (drop non 802.3 Ethertypes) */ + eth_type = eth->h_proto; + if (ntohs(eth_type) < ETH_P_802_3_MIN) { + rec->dropped++; + return XDP_DROP; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map2_round_robin") +int xdp_prognum2_round_robin(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct datarec* rec; + u32 cpu_dest; + u32 *cpu_lookup; + u32 key0 = 0; + + u32 *cpu_selected; + u32 *cpu_iterator; + u32 *cpu_max; + u32 cpu_idx; + + cpu_max = bpf_map_lookup_elem(&cpus_count, &key0); + if (!cpu_max) + return XDP_ABORTED; + + cpu_iterator = bpf_map_lookup_elem(&cpus_iterator, &key0); + if (!cpu_iterator) + return XDP_ABORTED; + cpu_idx = *cpu_iterator; + + *cpu_iterator += 1; + if (*cpu_iterator == *cpu_max) + *cpu_iterator = 0; + + cpu_selected = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key0); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + /* Check cpu_dest is valid */ + cpu_lookup = bpf_map_lookup_elem(&cpu_map, &cpu_dest); + if (!cpu_lookup) { + rec->issue++; + return XDP_DROP; + } + + if (cpu_dest >= MAX_CPUS ) + return XDP_ABORTED; + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map3_proto_separate") +int xdp_prognum3_proto_separate(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + u8 ip_proto = IPPROTO_UDP; + struct datarec* rec; + u16 eth_proto = 0; + u64 l3_offset = 0; + u32 cpu_dest = 0; + u32 cpu_idx = 0; + u32 *cpu_lookup; + u32 key = 0; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (!(parse_eth(eth, data_end, ð_proto, &l3_offset))) { + return XDP_PASS; /* Just skip */ + } + + /* Extract L4 protocol */ + switch (eth_proto) { + case ETH_P_IP: + ip_proto = get_proto_ipv4(ctx, l3_offset); + break; + case ETH_P_IPV6: + ip_proto = get_proto_ipv6(ctx, l3_offset); + break; + case ETH_P_ARP: + cpu_idx = 0; /* ARP packet handled on separate CPU */ + break; + default: + cpu_idx = 0; + } + + /* Choose CPU based on L4 protocol */ + switch (ip_proto) { + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: + cpu_idx = 2; + break; + case IPPROTO_TCP: + cpu_idx = 0; + break; + case IPPROTO_UDP: + cpu_idx = 1; + break; + default: + cpu_idx = 0; + } + + cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_lookup) + return XDP_ABORTED; + cpu_dest = *cpu_lookup; + + if (cpu_dest >= MAX_CPUS ) + return XDP_ABORTED; + + /* Check cpu_dest is valid */ + cpu_lookup = bpf_map_lookup_elem(&cpu_map, &cpu_dest); + if (!cpu_lookup) { + rec->issue++; + return XDP_DROP; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map4_ddos_filter_pktgen") +int xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + u8 ip_proto = IPPROTO_UDP; + struct datarec* rec; + u16 eth_proto = 0; + u64 l3_offset = 0; + u32 cpu_dest = 0; + u32 cpu_idx = 0; + u16 dest_port; + u32 *cpu_lookup; + u32 key = 0; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (!(parse_eth(eth, data_end, ð_proto, &l3_offset))) { + return XDP_PASS; /* Just skip */ + } + + /* Extract L4 protocol */ + switch (eth_proto) { + case ETH_P_IP: + ip_proto = get_proto_ipv4(ctx, l3_offset); + break; + case ETH_P_IPV6: + ip_proto = get_proto_ipv6(ctx, l3_offset); + break; + case ETH_P_ARP: + cpu_idx = 0; /* ARP packet handled on separate CPU */ + break; + default: + cpu_idx = 0; + } + + /* Choose CPU based on L4 protocol */ + switch (ip_proto) { + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: + cpu_idx = 2; + break; + case IPPROTO_TCP: + cpu_idx = 0; + break; + case IPPROTO_UDP: + cpu_idx = 1; + /* DDoS filter UDP port 9 (pktgen) */ + dest_port = get_dest_port_ipv4_udp(ctx, l3_offset); + if (dest_port == 9) { + if (rec) + rec->dropped++; + return XDP_DROP; + } + break; + default: + cpu_idx = 0; + } + + cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_lookup) + return XDP_ABORTED; + cpu_dest = *cpu_lookup; + + if (cpu_dest >= MAX_CPUS ) + return XDP_ABORTED; + + /* Check cpu_dest is valid */ + cpu_lookup = bpf_map_lookup_elem(&cpu_map, &cpu_dest); + if (!cpu_lookup) { + rec->issue++; + return XDP_DROP; + } + + if (cpu_dest >= MAX_CPUS ) + return XDP_ABORTED; + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + + +char _license[] SEC("license") = "GPL"; + +/*** Trace point code ***/ + +/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct xdp_redirect_ctx { + unsigned short common_type; // offset:0; size:2; signed:0; + unsigned char common_flags; // offset:2; size:1; signed:0; + unsigned char common_preempt_count;// offset:3; size:1; signed:0; + int common_pid; // offset:4; size:4; signed:1; + + int prog_id; // offset:8; size:4; signed:1; + u32 act; // offset:12 size:4; signed:0; + int ifindex; // offset:16 size:4; signed:1; + int err; // offset:20 size:4; signed:1; + int to_ifindex; // offset:24 size:4; signed:1; + u32 map_id; // offset:28 size:4; signed:0; + int map_index; // offset:32 size:4; signed:1; +}; // offset:36 + +enum { + XDP_REDIRECT_SUCCESS = 0, + XDP_REDIRECT_ERROR = 1 +}; + +static __always_inline +int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx) +{ + u32 key = XDP_REDIRECT_ERROR; + struct datarec *rec; + int err = ctx->err; + + if (!err) + key = XDP_REDIRECT_SUCCESS; + + rec = bpf_map_lookup_elem(&redirect_err_cnt, &key); + if (!rec) + return 0; + rec->dropped += 1; + + return 0; /* Indicate event was filtered (no further processing)*/ + /* + * Returning 1 here would allow e.g. a perf-record tracepoint + * to see and record these events, but it doesn't work well + * in-practice as stopping perf-record also unload this + * bpf_prog. Plus, there is additional overhead of doing so. + */ +} + +SEC("tracepoint/xdp/xdp_redirect_err") +int trace_xdp_redirect_err(struct xdp_redirect_ctx *ctx) +{ + return xdp_redirect_collect_stat(ctx); +} + + +SEC("tracepoint/xdp/xdp_redirect_map_err") +int trace_xdp_redirect_map_err(struct xdp_redirect_ctx *ctx) +{ + return xdp_redirect_collect_stat(ctx); +} + +/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct xdp_exception_ctx { + unsigned short common_type; // offset:0; size:2; signed:0; + unsigned char common_flags; // offset:2; size:1; signed:0; + unsigned char common_preempt_count;// offset:3; size:1; signed:0; + int common_pid; // offset:4; size:4; signed:1; + + int prog_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int ifindex; // offset:16; size:4; signed:1; +}; + +SEC("tracepoint/xdp/xdp_exception") +int trace_xdp_exception(struct xdp_exception_ctx *ctx) +{ + struct datarec *rec; + u32 key = 0; + + rec = bpf_map_lookup_elem(&exception_cnt, &key); + if (!rec) + return 1; + rec->dropped += 1; + + return 0; +} + +/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct cpumap_enqueue_ctx { + unsigned short common_type; // offset:0; size:2; signed:0; + unsigned char common_flags; // offset:2; size:1; signed:0; + unsigned char common_preempt_count;// offset:3; size:1; signed:0; + int common_pid; // offset:4; size:4; signed:1; + + int map_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int cpu; // offset:16; size:4; signed:1; + unsigned int drops; // offset:20; size:4; signed:0; + unsigned int processed; // offset:24; size:4; signed:0; + int to_cpu; // offset:28; size:4; signed:1; +}; + +SEC("tracepoint/xdp/xdp_cpumap_enqueue") +int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx) +{ + u32 to_cpu = ctx->to_cpu; + struct datarec *rec; + + if (to_cpu >= MAX_CPUS) + return 1; + + rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &to_cpu); + if (!rec) + return 0; + rec->processed += ctx->processed; + rec->dropped += ctx->drops; + + /* Detect misconfig. Redirect to "same" CPU, makes no sense + * and indicate user of cpumap have not done proper IRQ RXq + * setup. + */ + if (ctx->cpu == ctx->to_cpu) + rec->issue += ctx->processed; + + /* Keep seperate map for feedback loop */ + // have map that boolean mark drops, and RX side can clean + // this, indicating it have got the notification. TODO, should + // this also contain a (k)timestamp. + + return 0; +} + +/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct cpumap_kthread_ctx { + unsigned short common_type; // offset:0; size:2; signed:0; + unsigned char common_flags; // offset:2; size:1; signed:0; + unsigned char common_preempt_count;// offset:3; size:1; signed:0; + int common_pid; // offset:4; size:4; signed:1; + + int map_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int cpu; // offset:16; size:4; signed:1; + unsigned int drops; // offset:20; size:4; signed:0; + unsigned int processed; // offset:24; size:4; signed:0; + int time_limit; // offset:28; size:4; signed:1; +}; + +SEC("tracepoint/xdp/xdp_cpumap_kthread") +int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx) +{ + struct datarec *rec; + u32 key = 0; + + rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key); + if (!rec) + return 0; + rec->processed += ctx->processed; + rec->dropped += ctx->drops; + + /* Detect when time limit was exceeded, but queue was not-empty */ + if (ctx->processed > 0 && ctx->time_limit) + rec->issue++; + + return 0; +} +
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
new file mode 100644
index 000000000000..c2c971ab7078
--- /dev/null
+++ b/samples/bpf/xdp_redirect_cpu_user.c@@ -0,0 +1,639 @@ +/* GPLv2 Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. + */ +static const char *__doc__= + " XDP redirect with a CPU-map type \"BPF_MAP_TYPE_CPUMAP\""; + +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <unistd.h> +#include <locale.h> +#include <sys/resource.h> +#include <getopt.h> +#include <net/if.h> +#include <time.h> + +#include <arpa/inet.h> +#include <linux/if_link.h> + +#define MAX_CPUS 12 /* WARNING - sync with _kern.c */ + +/* How many xdp_progs are defined in _kern.c */ +#define MAX_PROG 5 + +/* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead + * use bpf/libbpf.h), but cannot as (currently) needed for XDP + * attaching to a device via set_link_xdp_fd() + */ +#include "libbpf.h" +#include "bpf_load.h" + +#include "bpf_util.h" + +static int ifindex = -1; +static char ifname_buf[IF_NAMESIZE]; +static char *ifname = NULL; +static __u32 xdp_flags = 0; + +/* Exit return codes */ +#define EXIT_OK 0 +#define EXIT_FAIL 1 +#define EXIT_FAIL_OPTION 2 +#define EXIT_FAIL_XDP 3 +#define EXIT_FAIL_BPF 4 +#define EXIT_FAIL_MEM 5 + +static const struct option long_options[] = { + {"help", no_argument, NULL, 'h' }, + {"dev", required_argument, NULL, 'd' }, + {"skb-mode", no_argument, NULL, 'S' }, + {"debug", no_argument, NULL, 'D' }, + {"sec", required_argument, NULL, 's' }, + {"prognum", required_argument, NULL, 'p' }, + {"qsize", required_argument, NULL, 'q' }, + {"cpu", required_argument, NULL, 'c' }, + {"no-separators",no_argument, NULL, 'z' }, + {0, 0, NULL, 0 } +}; + +static void int_exit(int sig) +{ + fprintf(stderr, + "Interrupted: Removing XDP program on ifindex:%d device:%s\n", + ifindex, ifname); + if (ifindex > -1) + set_link_xdp_fd(ifindex, -1, xdp_flags); + exit(EXIT_OK); +} + +static void usage(char *argv[]) +{ + int i; + printf("\nDOCUMENTATION:\n%s\n", __doc__); + printf("\n"); + printf(" Usage: %s (options-see-below)\n", + argv[0]); + printf(" Listing options:\n"); + for (i = 0; long_options[i].name != 0; i++) { + printf(" --%-12s", long_options[i].name); + if (long_options[i].flag != NULL) + printf(" flag (internal value:%d)", + *long_options[i].flag); + else + printf(" short-option: -%c", + long_options[i].val); + printf("\n"); + } + printf("\n"); +} + +/* gettime returns the current time of day in nanoseconds. + * Cost: clock_gettime (ns) => 26ns (CLOCK_MONOTONIC) + * clock_gettime (ns) => 9ns (CLOCK_MONOTONIC_COARSE) + */ +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ +static __u64 gettime(void) +{ + struct timespec t; + int res; + + res = clock_gettime(CLOCK_MONOTONIC, &t); + if (res < 0) { + fprintf(stderr, "Error with gettimeofday! (%i)\n", res); + exit(EXIT_FAIL); + } + return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec; +} + +/* Common stats data record shared with _kern.c */ +struct datarec { + __u64 processed; + __u64 dropped; + __u64 issue; +}; +struct record { + __u64 timestamp; + struct datarec total; + struct datarec *cpu; +}; +struct stats_record { + struct record rx_cnt; + struct record redir_err; + struct record kthread; + struct record exception; + struct record enq[MAX_CPUS]; +}; + +static bool map_collect_percpu(int fd, __u32 key, struct record* rec) +{ + /* For percpu maps, userspace gets a value per possible CPU */ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec values[nr_cpus]; + __u64 sum_processed = 0; + __u64 sum_dropped = 0; + __u64 sum_issue = 0; + int i; + + if ((bpf_map_lookup_elem(fd, &key, values)) != 0) { + fprintf(stderr, + "ERR: bpf_map_lookup_elem failed key:0x%X\n", key); + return false; + } + /* Get time as close as possible to reading map contents */ + rec->timestamp = gettime(); + + /* Record and sum values from each CPU */ + for (i = 0; i < nr_cpus; i++) { + rec->cpu[i].processed = values[i].processed; + sum_processed += values[i].processed; + rec->cpu[i].dropped = values[i].dropped; + sum_dropped += values[i].dropped; + rec->cpu[i].issue = values[i].issue; + sum_issue += values[i].issue; + } + rec->total.processed = sum_processed; + rec->total.dropped = sum_dropped; + rec->total.issue = sum_issue; + return true; +} + +static struct datarec *alloc_record_per_cpu(void) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec *array; + size_t size; + + size = sizeof(struct datarec) * nr_cpus; + array = malloc(size); + memset(array, 0, size); + if (!array) { + fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); + exit(EXIT_FAIL_MEM); + } + return array; +} + +static struct stats_record* alloc_stats_record(void) +{ + struct stats_record* rec; + int i; + + rec = malloc(sizeof(*rec)); + memset(rec, 0, sizeof(*rec)); + if (!rec) { + fprintf(stderr, "Mem alloc error\n"); + exit(EXIT_FAIL_MEM); + } + rec->rx_cnt.cpu = alloc_record_per_cpu(); + rec->redir_err.cpu = alloc_record_per_cpu(); + rec->kthread.cpu = alloc_record_per_cpu(); + rec->exception.cpu = alloc_record_per_cpu(); + for (i = 0; i < MAX_CPUS; i++) + rec->enq[i].cpu = alloc_record_per_cpu(); + + return rec; +} + +static void free_stats_record(struct stats_record* r) +{ + int i; + + for (i = 0; i < MAX_CPUS; i++) + free(r->enq[i].cpu); + free(r->exception.cpu); + free(r->kthread.cpu); + free(r->redir_err.cpu); + free(r->rx_cnt.cpu); + free(r); +} + +static double calc_period(struct record *r, struct record *p) +{ + double period_ = 0; + __u64 period = 0; + + period = r->timestamp - p->timestamp; + if (period > 0) { + period_ = ((double) period / NANOSEC_PER_SEC); + } + return period_; +} + +static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->processed - p->processed; + pps = packets / period_; + } + return pps; +} + +static __u64 calc_drop_pps(struct datarec *r, struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->dropped - p->dropped; + pps = packets / period_; + } + return pps; +} + +static __u64 calc_errs_pps(struct datarec *r, + struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->issue - p->issue; + pps = packets / period_; + } + return pps; +} + +static void stats_print(struct stats_record *stats_rec, + struct stats_record *stats_prev, + int prog_num) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + double pps = 0, drop = 0, err = 0; + struct record *rec, *prev; + int to_cpu; + double t; + int i; + + /* Header */ + printf("Running XDP/eBPF prog_num:%d\n", prog_num); + printf("%-15s %-7s %-14s %-11s %-9s\n", + "XDP-cpumap", "CPU:to", "pps", "drop-pps", "extra-info"); + + /* XDP rx_cnt */ + { + char * fmt_rx = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n"; + char * fm2_rx = "%-15s %-7s %'-14.0f %'-11.0f\n"; + char *errstr = ""; + + rec = &stats_rec->rx_cnt; + prev = &stats_prev->rx_cnt; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) + errstr = "cpu-dest/err"; + if (pps > 0) + printf(fmt_rx, "XDP-RX", + i, pps, drop, err, errstr); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + printf(fm2_rx, "XDP-RX", "total", pps, drop); + } + + /* cpumap enqueue stats */ + for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) { + char *fmt="%-15s %3d:%-3d %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *fm2="%-15s %3s:%-3d %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *errstr = ""; + + rec = &stats_rec->enq[to_cpu]; + prev = &stats_prev->enq[to_cpu]; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) + errstr = "same-cpu/pps"; + if (pps > 0) + printf(fmt, "cpumap-enqueue", + i, to_cpu, pps, drop, err, errstr); + } + pps = calc_pps(&rec->total, &prev->total, t); + if (pps > 0) { + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + printf(fm2, "cpumap-enqueue", + "sum", to_cpu, pps, drop, err, errstr); + } + } + + /* cpumap kthread stats */ + { + char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %-10.0f %s\n"; + char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %-10.0f %s\n"; + char *errstr = ""; + rec = &stats_rec->kthread; + prev = &stats_prev->kthread; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) + errstr = "time_exceed"; + if (pps > 0) + printf(fmt_k, "cpumap_kthread", + i, pps, drop, err, errstr); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + printf(fm2_k, "cpumap_kthread", "total", pps, drop); + } + + /* XDP redirect err tracepoints (very unlikely) */ + { + char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n"; + char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n"; + rec = &stats_rec->redir_err; + prev = &stats_prev->redir_err; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + if (pps > 0) + printf(fmt_err, "redirect_err", i, pps, drop); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + printf(fm2_err, "redirect_err", "total", pps, drop); + } + + /* XDP general exception tracepoints */ + { + char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n"; + char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n"; + rec = &stats_rec->exception; + prev = &stats_prev->exception; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + if (pps > 0) + printf(fmt_err, "xdp_exception", i, pps, drop); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + printf(fm2_err, "xdp_exception", "total", pps, drop); + } + + printf("\n"); + fflush(stdout); +} + +static void stats_collect(struct stats_record *rec) +{ + int fd, i; + + fd = map_fd[1]; /* map: rx_cnt */ + map_collect_percpu(fd, 0, &rec->rx_cnt); + + fd = map_fd[2]; /* map: redirect_err_cnt */ + map_collect_percpu(fd, 1, &rec->redir_err); + + fd = map_fd[3]; /* map: cpumap_enqueue_cnt */ + for (i = 0; i < MAX_CPUS; i++) { + map_collect_percpu(fd, i, &rec->enq[i]); + } + + fd = map_fd[4]; /* map: cpumap_kthread_cnt */ + map_collect_percpu(fd, 0, &rec->kthread); + + fd = map_fd[8]; /* map: exception_cnt */ + map_collect_percpu(fd, 0, &rec->exception); +} + + +/* Pointer swap trick */ +static inline void swap(struct stats_record **a, struct stats_record **b) +{ + struct stats_record *tmp; + + tmp = *a; + *a = *b; + *b = tmp; +} + +static void stats_poll(int interval, bool use_separators, int prog_num) +{ + struct stats_record *record, *prev; + + record = alloc_stats_record(); + prev = alloc_stats_record(); + stats_collect(record); + + /* Trick to pretty printf with thousands separators use %' */ + if (use_separators) + setlocale(LC_NUMERIC, "en_US"); + + while (1) { + swap(&prev, &record); + stats_collect(record); + stats_print(record, prev, prog_num); + sleep(interval); + } + + free_stats_record(record); + free_stats_record(prev); +} + +static int create_cpu_entry(__u32 cpu, __u32 queue_size, + __u32 avail_idx, bool new) +{ + __u32 curr_cpus_count; + __u32 key = 0; + int ret; + + /* Add a CPU entry to cpumap, as this allocate a cpu entry in + * the kernel for the cpu. + */ + ret = bpf_map_update_elem(map_fd[0], &cpu, &queue_size, 0); + if (ret) { + fprintf(stderr, "Create CPU entry failed\n"); + exit(EXIT_FAIL_BPF); + } + + /* Inform bpf_prog's that a new CPU is available to select + * from via some control maps. + */ + /* map_fd[5] = cpus_available */ + ret = bpf_map_update_elem(map_fd[5], &avail_idx, &cpu, 0); + if (ret) { + fprintf(stderr, "Add to avail CPUs failed\n"); + exit(EXIT_FAIL_BPF); + } + + /* When not replacing/updating existing entry, bump the count */ + /* map_fd[6] = cpus_count */ + if (new) { + ret = bpf_map_lookup_elem(map_fd[6], &key, &curr_cpus_count); + if (ret) { + fprintf(stderr, "Failed reading curr cpus_count \n"); + exit(EXIT_FAIL_BPF); + } + curr_cpus_count++; + ret = bpf_map_update_elem(map_fd[6], &key, &curr_cpus_count, 0); + if (ret) { + fprintf(stderr, "Failed write curr cpus_count \n"); + exit(EXIT_FAIL_BPF); + } + } + /* map_fd[7] = cpus_iterator */ + printf("%s CPU:%u as idx:%u cpus_count:%u\n", + new ? "Add-new":"Replace", cpu, avail_idx, curr_cpus_count); + + return 0; +} + +int main(int argc, char **argv) +{ + struct rlimit r = {10 * 1024*1024, RLIM_INFINITY}; + bool use_separators = true; + char filename[256]; + bool debug = false; + int added_cpus = 0; + int longindex = 0; + int interval = 2; + int prog_num = 0; + int add_cpu = -1; + __u32 qsize; + int opt; + + /* Notice: choosing he queue size is very important with the + * ixgbe driver, because it's driver page recycling trick is + * dependend on pages being returned quickly. The number of + * out-standing packets in the system must be less-than 2x + * RX-ring size. + */ + qsize = 128+64; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (load_bpf_file(filename)) { + fprintf(stderr, "ERR in load_bpf_file(): %s", bpf_log_buf); + return EXIT_FAIL; + } + + if (!prog_fd[0]) { + fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno)); + return EXIT_FAIL; + } + + /* Parse commands line args */ + while ((opt = getopt_long(argc, argv, "hSd:", + long_options, &longindex)) != -1) { + switch (opt) { + case 'd': + if (strlen(optarg) >= IF_NAMESIZE) { + fprintf(stderr, "ERR: --dev name too long\n"); + goto error; + } + ifname = (char *)&ifname_buf; + strncpy(ifname, optarg, IF_NAMESIZE); + ifindex = if_nametoindex(ifname); + if (ifindex == 0) { + fprintf(stderr, + "ERR: --dev name unknown err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + break; + case 's': + interval = atoi(optarg); + break; + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'D': + debug = true; + break; + case 'z': + use_separators = false; + break; + case 'p': + /* Selecting eBPF prog to load */ + prog_num = atoi(optarg); + if (prog_num < 0 || prog_num >= MAX_PROG) { + fprintf(stderr, + "--prognum too large err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + break; + case 'c': + /* Add multiple CPUs */ + add_cpu = strtoul(optarg, NULL, 0); + if (add_cpu > MAX_CPUS) { + fprintf(stderr, + "--cpu nr too large for cpumap err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + create_cpu_entry(add_cpu, qsize, added_cpus, true); + added_cpus++; + break; + case 'q': + qsize = atoi(optarg); + break; + case 'h': + error: + default: + usage(argv); + return EXIT_FAIL_OPTION; + } + } + /* Required option */ + if (ifindex == -1) { + fprintf(stderr, "ERR: required option --dev missing\n"); + usage(argv); + return EXIT_FAIL_OPTION; + } + /* Required option */ + if (add_cpu == -1) { + fprintf(stderr, "ERR: required option --cpu missing\n"); + fprintf(stderr, " Specify multiple --cpu option to add more\n"); + usage(argv); + return EXIT_FAIL_OPTION; + } + + /* Remove XDP program when program is interrupted */ + signal(SIGINT, int_exit); + + if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) { + fprintf(stderr, "link set xdp fd failed\n"); + return EXIT_FAIL_XDP; + } + + if (debug) { + printf("Debug-mode reading trace pipe (fix #define DEBUG)\n"); + read_trace_pipe(); + } + + stats_poll(interval, use_separators, prog_num); + return EXIT_OK; +}