diff options
Diffstat (limited to 'samples/bpf')
-rw-r--r-- | samples/bpf/Makefile | 13 | ||||
-rw-r--r-- | samples/bpf/bpf_load.c | 40 | ||||
-rw-r--r-- | samples/bpf/sampleip_user.c | 1 | ||||
-rw-r--r-- | samples/bpf/sockex2_kern.c | 11 | ||||
-rw-r--r-- | samples/bpf/sockex3_kern.c | 8 | ||||
-rw-r--r-- | samples/bpf/sockex3_user.c | 4 | ||||
-rw-r--r-- | samples/bpf/tcp_tos_reflect_kern.c | 87 | ||||
-rw-r--r-- | samples/bpf/test_cgrp2_attach2.c | 19 | ||||
-rw-r--r-- | samples/bpf/test_current_task_under_cgroup_user.c | 1 | ||||
-rw-r--r-- | samples/bpf/tracex3_user.c | 2 | ||||
-rw-r--r-- | samples/bpf/xdp1_user.c | 27 | ||||
-rw-r--r-- | samples/bpf/xdpsock_kern.c | 2 | ||||
-rw-r--r-- | samples/bpf/xdpsock_user.c | 15 |
13 files changed, 183 insertions, 47 deletions
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 36f9f41d094b..66ae15f27c70 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -153,6 +153,7 @@ always += tcp_cong_kern.o always += tcp_iw_kern.o always += tcp_clamp_kern.o always += tcp_basertt_kern.o +always += tcp_tos_reflect_kern.o always += xdp_redirect_kern.o always += xdp_redirect_map_kern.o always += xdp_redirect_cpu_kern.o @@ -207,12 +208,20 @@ endif BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') +BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \ + $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \ + readelf -S ./llvm_btf_verify.o | grep BTF; \ + /bin/rm -f ./llvm_btf_verify.o) +ifneq ($(BTF_LLVM_PROBE),) + EXTRA_CFLAGS += -g +else ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),) EXTRA_CFLAGS += -g LLC_FLAGS += -mattr=dwarfris DWARF2BTF = y endif +endif # Trick to allow make to be run from this directory all: @@ -226,12 +235,10 @@ $(LIBBPF): FORCE # Fix up variables inherited from Kbuild that tools/ build system won't like $(MAKE) -C $(dir $@) RM='rm -rf' LDFLAGS= srctree=$(BPF_SAMPLES_PATH)/../../ O= -$(obj)/syscall_nrs.s: $(src)/syscall_nrs.c - $(call if_changed_dep,cc_s_c) - $(obj)/syscall_nrs.h: $(obj)/syscall_nrs.s FORCE $(call filechk,offsets,__SYSCALL_NRS_H__) +targets += syscall_nrs.s clean-files += syscall_nrs.h FORCE: diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 904e775d1a44..eae7b635343d 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -16,7 +16,6 @@ #include <linux/netlink.h> #include <linux/rtnetlink.h> #include <linux/types.h> -#include <sys/types.h> #include <sys/socket.h> #include <sys/syscall.h> #include <sys/ioctl.h> @@ -55,6 +54,25 @@ static int populate_prog_array(const char *event, int prog_fd) return 0; } +static int write_kprobe_events(const char *val) +{ + int fd, ret, flags; + + if (val == NULL) + return -1; + else if (val[0] == '\0') + flags = O_WRONLY | O_TRUNC; + else + flags = O_WRONLY | O_APPEND; + + fd = open("/sys/kernel/debug/tracing/kprobe_events", flags); + + ret = write(fd, val, strlen(val)); + close(fd); + + return ret; +} + static int load_and_attach(const char *event, struct bpf_insn *prog, int size) { bool is_socket = strncmp(event, "socket", 6) == 0; @@ -166,10 +184,9 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) #ifdef __x86_64__ if (strncmp(event, "sys_", 4) == 0) { - snprintf(buf, sizeof(buf), - "echo '%c:__x64_%s __x64_%s' >> /sys/kernel/debug/tracing/kprobe_events", - is_kprobe ? 'p' : 'r', event, event); - err = system(buf); + snprintf(buf, sizeof(buf), "%c:__x64_%s __x64_%s", + is_kprobe ? 'p' : 'r', event, event); + err = write_kprobe_events(buf); if (err >= 0) { need_normal_check = false; event_prefix = "__x64_"; @@ -177,10 +194,9 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) } #endif if (need_normal_check) { - snprintf(buf, sizeof(buf), - "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events", - is_kprobe ? 'p' : 'r', event, event); - err = system(buf); + snprintf(buf, sizeof(buf), "%c:%s %s", + is_kprobe ? 'p' : 'r', event, event); + err = write_kprobe_events(buf); if (err < 0) { printf("failed to create kprobe '%s' error '%s'\n", event, strerror(errno)); @@ -285,8 +301,8 @@ static int load_maps(struct bpf_map_data *maps, int nr_maps, numa_node); } if (map_fd[i] < 0) { - printf("failed to create a map: %d %s\n", - errno, strerror(errno)); + printf("failed to create map %d (%s): %d %s\n", + i, maps[i].name, errno, strerror(errno)); return 1; } maps[i].fd = map_fd[i]; @@ -520,7 +536,7 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) return 1; /* clear all kprobes */ - i = system("echo \"\" > /sys/kernel/debug/tracing/kprobe_events"); + i = write_kprobe_events(""); /* scan over all elf sections to get license and map info */ for (i = 1; i < ehdr.e_shnum; i++) { diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c index 60c2b73d1b4d..216c7ecbbbe9 100644 --- a/samples/bpf/sampleip_user.c +++ b/samples/bpf/sampleip_user.c @@ -9,7 +9,6 @@ */ #include <stdio.h> #include <stdlib.h> -#include <stdio.h> #include <unistd.h> #include <errno.h> #include <signal.h> diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c index f58acfc92556..f2f9dbc021b0 100644 --- a/samples/bpf/sockex2_kern.c +++ b/samples/bpf/sockex2_kern.c @@ -14,7 +14,7 @@ struct vlan_hdr { __be16 h_vlan_encapsulated_proto; }; -struct bpf_flow_keys { +struct flow_key_record { __be32 src; __be32 dst; union { @@ -59,7 +59,7 @@ static inline __u32 ipv6_addr_hash(struct __sk_buff *ctx, __u64 off) } static inline __u64 parse_ip(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto, - struct bpf_flow_keys *flow) + struct flow_key_record *flow) { __u64 verlen; @@ -83,7 +83,7 @@ static inline __u64 parse_ip(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto } static inline __u64 parse_ipv6(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto, - struct bpf_flow_keys *flow) + struct flow_key_record *flow) { *ip_proto = load_byte(skb, nhoff + offsetof(struct ipv6hdr, nexthdr)); @@ -96,7 +96,8 @@ static inline __u64 parse_ipv6(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_pro return nhoff; } -static inline bool flow_dissector(struct __sk_buff *skb, struct bpf_flow_keys *flow) +static inline bool flow_dissector(struct __sk_buff *skb, + struct flow_key_record *flow) { __u64 nhoff = ETH_HLEN; __u64 ip_proto; @@ -198,7 +199,7 @@ struct bpf_map_def SEC("maps") hash_map = { SEC("socket2") int bpf_prog2(struct __sk_buff *skb) { - struct bpf_flow_keys flow = {}; + struct flow_key_record flow = {}; struct pair *value; u32 key; diff --git a/samples/bpf/sockex3_kern.c b/samples/bpf/sockex3_kern.c index 95907f8d2b17..c527b57d3ec8 100644 --- a/samples/bpf/sockex3_kern.c +++ b/samples/bpf/sockex3_kern.c @@ -61,7 +61,7 @@ struct vlan_hdr { __be16 h_vlan_encapsulated_proto; }; -struct bpf_flow_keys { +struct flow_key_record { __be32 src; __be32 dst; union { @@ -88,7 +88,7 @@ static inline __u32 ipv6_addr_hash(struct __sk_buff *ctx, __u64 off) } struct globals { - struct bpf_flow_keys flow; + struct flow_key_record flow; }; struct bpf_map_def SEC("maps") percpu_map = { @@ -114,14 +114,14 @@ struct pair { struct bpf_map_def SEC("maps") hash_map = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct bpf_flow_keys), + .key_size = sizeof(struct flow_key_record), .value_size = sizeof(struct pair), .max_entries = 1024, }; static void update_stats(struct __sk_buff *skb, struct globals *g) { - struct bpf_flow_keys key = g->flow; + struct flow_key_record key = g->flow; struct pair *value; value = bpf_map_lookup_elem(&hash_map, &key); diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c index 5ba3ae9d180b..9d02e0404719 100644 --- a/samples/bpf/sockex3_user.c +++ b/samples/bpf/sockex3_user.c @@ -13,7 +13,7 @@ #define PARSE_IP_PROG_FD (prog_fd[0]) #define PROG_ARRAY_FD (map_fd[0]) -struct bpf_flow_keys { +struct flow_key_record { __be32 src; __be32 dst; union { @@ -64,7 +64,7 @@ int main(int argc, char **argv) (void) f; for (i = 0; i < 5; i++) { - struct bpf_flow_keys key = {}, next_key; + struct flow_key_record key = {}, next_key; struct pair value; sleep(1); diff --git a/samples/bpf/tcp_tos_reflect_kern.c b/samples/bpf/tcp_tos_reflect_kern.c new file mode 100644 index 000000000000..d51dab19eca6 --- /dev/null +++ b/samples/bpf/tcp_tos_reflect_kern.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 Facebook + * + * BPF program to automatically reflect TOS option from received syn packet + * + * Use load_sock_ops to load this BPF program. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/in.h> +#include <linux/socket.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define DEBUG 1 + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +SEC("sockops") +int bpf_basertt(struct bpf_sock_ops *skops) +{ + char header[sizeof(struct ipv6hdr)]; + struct ipv6hdr *hdr6; + struct iphdr *hdr; + int hdr_size = 0; + int save_syn = 1; + int tos = 0; + int rv = 0; + int op; + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("BPF command: %d\n", op); +#endif + switch (op) { + case BPF_SOCK_OPS_TCP_LISTEN_CB: + rv = bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN, + &save_syn, sizeof(save_syn)); + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + if (skops->family == AF_INET) + hdr_size = sizeof(struct iphdr); + else + hdr_size = sizeof(struct ipv6hdr); + rv = bpf_getsockopt(skops, SOL_TCP, TCP_SAVED_SYN, + header, hdr_size); + if (!rv) { + if (skops->family == AF_INET) { + hdr = (struct iphdr *) header; + tos = hdr->tos; + if (tos != 0) + bpf_setsockopt(skops, SOL_IP, IP_TOS, + &tos, sizeof(tos)); + } else { + hdr6 = (struct ipv6hdr *) header; + tos = ((hdr6->priority) << 4 | + (hdr6->flow_lbl[0]) >> 4); + if (tos) + bpf_setsockopt(skops, SOL_IPV6, + IPV6_TCLASS, + &tos, sizeof(tos)); + } + rv = 0; + } + break; + default: + rv = -1; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c index 180f9d813bca..d7b68ef5ba79 100644 --- a/samples/bpf/test_cgrp2_attach2.c +++ b/samples/bpf/test_cgrp2_attach2.c @@ -209,7 +209,7 @@ static int map_fd = -1; static int prog_load_cnt(int verdict, int val) { - int cgroup_storage_fd; + int cgroup_storage_fd, percpu_cgroup_storage_fd; if (map_fd < 0) map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); @@ -225,6 +225,14 @@ static int prog_load_cnt(int verdict, int val) return -1; } + percpu_cgroup_storage_fd = bpf_create_map( + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + if (percpu_cgroup_storage_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + struct bpf_insn prog[] = { BPF_MOV32_IMM(BPF_REG_0, 0), BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ @@ -235,11 +243,20 @@ static int prog_load_cnt(int verdict, int val) BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */ BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd), BPF_MOV64_IMM(BPF_REG_2, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), BPF_MOV64_IMM(BPF_REG_1, val), BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0), + + BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1), + BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ BPF_EXIT_INSN(), }; diff --git a/samples/bpf/test_current_task_under_cgroup_user.c b/samples/bpf/test_current_task_under_cgroup_user.c index 4be4874ca2bc..2259f997a26c 100644 --- a/samples/bpf/test_current_task_under_cgroup_user.c +++ b/samples/bpf/test_current_task_under_cgroup_user.c @@ -11,7 +11,6 @@ #include <unistd.h> #include <bpf/bpf.h> #include "bpf_load.h" -#include <linux/bpf.h> #include "cgroup_helpers.h" #define CGROUP_PATH "/my-cgroup" diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c index 6c6b10f4c3ee..56466d010139 100644 --- a/samples/bpf/tracex3_user.c +++ b/samples/bpf/tracex3_user.c @@ -17,8 +17,6 @@ #include "bpf_load.h" #include "bpf_util.h" -#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) - #define SLOTS 100 static void clear_stats(int fd) diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index b02c531510ed..0a197f86ac43 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -15,6 +15,7 @@ #include <unistd.h> #include <libgen.h> #include <sys/resource.h> +#include <net/if.h> #include "bpf_util.h" #include "bpf/bpf.h" @@ -34,26 +35,24 @@ static void int_exit(int sig) static void poll_stats(int map_fd, int interval) { unsigned int nr_cpus = bpf_num_possible_cpus(); - const unsigned int nr_keys = 256; - __u64 values[nr_cpus], prev[nr_keys][nr_cpus]; - __u32 key; + __u64 values[nr_cpus], prev[UINT8_MAX] = { 0 }; int i; - memset(prev, 0, sizeof(prev)); - while (1) { + __u32 key = UINT32_MAX; + sleep(interval); - for (key = 0; key < nr_keys; key++) { + while (bpf_map_get_next_key(map_fd, &key, &key) != -1) { __u64 sum = 0; assert(bpf_map_lookup_elem(map_fd, &key, values) == 0); for (i = 0; i < nr_cpus; i++) - sum += (values[i] - prev[key][i]); - if (sum) + sum += values[i]; + if (sum > prev[key]) printf("proto %u: %10llu pkt/s\n", - key, sum / interval); - memcpy(prev[key], values, sizeof(values)); + key, (sum - prev[key]) / interval); + prev[key] = sum; } } } @@ -61,7 +60,7 @@ static void poll_stats(int map_fd, int interval) static void usage(const char *prog) { fprintf(stderr, - "usage: %s [OPTS] IFINDEX\n\n" + "usage: %s [OPTS] IFACE\n\n" "OPTS:\n" " -S use skb-mode\n" " -N enforce native mode\n", @@ -104,7 +103,11 @@ int main(int argc, char **argv) return 1; } - ifindex = strtoul(argv[optind], NULL, 0); + ifindex = if_nametoindex(argv[1]); + if (!ifindex) { + perror("if_nametoindex"); + return 1; + } snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; diff --git a/samples/bpf/xdpsock_kern.c b/samples/bpf/xdpsock_kern.c index d8806c41362e..b8ccd0802b3f 100644 --- a/samples/bpf/xdpsock_kern.c +++ b/samples/bpf/xdpsock_kern.c @@ -16,7 +16,7 @@ struct bpf_map_def SEC("maps") xsks_map = { .type = BPF_MAP_TYPE_XSKMAP, .key_size = sizeof(int), .value_size = sizeof(int), - .max_entries = 4, + .max_entries = MAX_SOCKS, }; struct bpf_map_def SEC("maps") rr_map = { diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 4914788b6727..57ecadc58403 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -118,7 +118,6 @@ struct xdpsock { unsigned long prev_tx_npkts; }; -#define MAX_SOCKS 4 static int num_socks; struct xdpsock *xsks[MAX_SOCKS]; @@ -596,7 +595,7 @@ static void dump_stats(void) prev_time = now; - for (i = 0; i < num_socks; i++) { + for (i = 0; i < num_socks && xsks[i]; i++) { char *fmt = "%-15s %'-11.0f %'-11lu\n"; double rx_pps, tx_pps; @@ -649,6 +648,8 @@ static struct option long_options[] = { {"xdp-skb", no_argument, 0, 'S'}, {"xdp-native", no_argument, 0, 'N'}, {"interval", required_argument, 0, 'n'}, + {"zero-copy", no_argument, 0, 'z'}, + {"copy", no_argument, 0, 'c'}, {0, 0, 0, 0} }; @@ -667,6 +668,8 @@ static void usage(const char *prog) " -S, --xdp-skb=n Use XDP skb-mod\n" " -N, --xdp-native=n Enfore XDP native mode\n" " -n, --interval=n Specify statistics update interval (default 1 sec).\n" + " -z, --zero-copy Force zero-copy mode.\n" + " -c, --copy Force copy mode.\n" "\n"; fprintf(stderr, str, prog); exit(EXIT_FAILURE); @@ -679,7 +682,7 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "rtli:q:psSNn:", long_options, + c = getopt_long(argc, argv, "rtli:q:psSNn:cz", long_options, &option_index); if (c == -1) break; @@ -716,6 +719,12 @@ static void parse_command_line(int argc, char **argv) case 'n': opt_interval = atoi(optarg); break; + case 'z': + opt_xdp_bind_flags |= XDP_ZEROCOPY; + break; + case 'c': + opt_xdp_bind_flags |= XDP_COPY; + break; default: usage(basename(argv[0])); } |