Commit d8c5b17f authored by Daniel Mack's avatar Daniel Mack Committed by David S. Miller

samples: bpf: add userspace example for attaching eBPF programs to cgroups

Add a simple userpace program to demonstrate the new API to attach eBPF
programs to cgroups. This is what it does:

 * Create arraymap in kernel with 4 byte keys and 8 byte values

 * Load eBPF program

   The eBPF program accesses the map passed in to store two pieces of
   information. The number of invocations of the program, which maps
   to the number of packets received, is stored to key 0. Key 1 is
   incremented on each iteration by the number of bytes stored in
   the skb.

 * Detach any eBPF program previously attached to the cgroup

 * Attach the new program to the cgroup using BPF_PROG_ATTACH

 * Once a second, read map[0] and map[1] to see how many bytes and
   packets were seen on any socket of tasks in the given cgroup.

The program takes a cgroup path as 1st argument, and either "ingress"
or "egress" as 2nd. Optionally, "drop" can be passed as 3rd argument,
which will make the generated eBPF program return 0 instead of 1, so
the kernel will drop the packet.

libbpf gained two new wrappers for the new syscall commands.
Signed-off-by: default avatarDaniel Mack <daniel@zonque.org>
Acked-by: default avatarAlexei Starovoitov <ast@kernel.org>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 33b48679
...@@ -22,6 +22,7 @@ hostprogs-y += spintest ...@@ -22,6 +22,7 @@ hostprogs-y += spintest
hostprogs-y += map_perf_test hostprogs-y += map_perf_test
hostprogs-y += test_overhead hostprogs-y += test_overhead
hostprogs-y += test_cgrp2_array_pin hostprogs-y += test_cgrp2_array_pin
hostprogs-y += test_cgrp2_attach
hostprogs-y += xdp1 hostprogs-y += xdp1
hostprogs-y += xdp2 hostprogs-y += xdp2
hostprogs-y += test_current_task_under_cgroup hostprogs-y += test_current_task_under_cgroup
...@@ -49,6 +50,7 @@ spintest-objs := bpf_load.o libbpf.o spintest_user.o ...@@ -49,6 +50,7 @@ spintest-objs := bpf_load.o libbpf.o spintest_user.o
map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o
test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o
test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o
test_cgrp2_attach-objs := libbpf.o test_cgrp2_attach.o
xdp1-objs := bpf_load.o libbpf.o xdp1_user.o xdp1-objs := bpf_load.o libbpf.o xdp1_user.o
# reuse xdp1 source intentionally # reuse xdp1 source intentionally
xdp2-objs := bpf_load.o libbpf.o xdp1_user.o xdp2-objs := bpf_load.o libbpf.o xdp1_user.o
......
...@@ -104,6 +104,27 @@ int bpf_prog_load(enum bpf_prog_type prog_type, ...@@ -104,6 +104,27 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
} }
int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
{
union bpf_attr attr = {
.target_fd = target_fd,
.attach_bpf_fd = prog_fd,
.attach_type = type,
};
return syscall(__NR_bpf, BPF_PROG_ATTACH, &attr, sizeof(attr));
}
int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
{
union bpf_attr attr = {
.target_fd = target_fd,
.attach_type = type,
};
return syscall(__NR_bpf, BPF_PROG_DETACH, &attr, sizeof(attr));
}
int bpf_obj_pin(int fd, const char *pathname) int bpf_obj_pin(int fd, const char *pathname)
{ {
union bpf_attr attr = { union bpf_attr attr = {
......
...@@ -15,6 +15,9 @@ int bpf_prog_load(enum bpf_prog_type prog_type, ...@@ -15,6 +15,9 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
const struct bpf_insn *insns, int insn_len, const struct bpf_insn *insns, int insn_len,
const char *license, int kern_version); const char *license, int kern_version);
int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type);
int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
int bpf_obj_pin(int fd, const char *pathname); int bpf_obj_pin(int fd, const char *pathname);
int bpf_obj_get(const char *pathname); int bpf_obj_get(const char *pathname);
......
/* eBPF example program:
*
* - Creates arraymap in kernel with 4 bytes keys and 8 byte values
*
* - Loads eBPF program
*
* The eBPF program accesses the map passed in to store two pieces of
* information. The number of invocations of the program, which maps
* to the number of packets received, is stored to key 0. Key 1 is
* incremented on each iteration by the number of bytes stored in
* the skb.
*
* - Detaches any eBPF program previously attached to the cgroup
*
* - Attaches the new program to a cgroup using BPF_PROG_ATTACH
*
* - Every second, reads map[0] and map[1] to see how many bytes and
* packets were seen on any socket of tasks in the given cgroup.
*/
#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <stddef.h>
#include <string.h>
#include <unistd.h>
#include <assert.h>
#include <errno.h>
#include <fcntl.h>
#include <linux/bpf.h>
#include "libbpf.h"
enum {
MAP_KEY_PACKETS,
MAP_KEY_BYTES,
};
static int prog_load(int map_fd, int verdict)
{
struct bpf_insn prog[] = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), /* save r6 so it's not clobbered by BPF_CALL */
/* Count packets */
BPF_MOV64_IMM(BPF_REG_0, MAP_KEY_PACKETS), /* r0 = 0 */
BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
BPF_LD_MAP_FD(BPF_REG_1, map_fd), /* load map fd to r1 */
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */
BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
/* Count bytes */
BPF_MOV64_IMM(BPF_REG_0, MAP_KEY_BYTES), /* r0 = 1 */
BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
BPF_LD_MAP_FD(BPF_REG_1, map_fd),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, offsetof(struct __sk_buff, len)), /* r1 = skb->len */
BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
BPF_EXIT_INSN(),
};
return bpf_prog_load(BPF_PROG_TYPE_CGROUP_SKB,
prog, sizeof(prog), "GPL", 0);
}
static int usage(const char *argv0)
{
printf("Usage: %s <cg-path> <egress|ingress> [drop]\n", argv0);
return EXIT_FAILURE;
}
int main(int argc, char **argv)
{
int cg_fd, map_fd, prog_fd, key, ret;
long long pkt_cnt, byte_cnt;
enum bpf_attach_type type;
int verdict = 1;
if (argc < 3)
return usage(argv[0]);
if (strcmp(argv[2], "ingress") == 0)
type = BPF_CGROUP_INET_INGRESS;
else if (strcmp(argv[2], "egress") == 0)
type = BPF_CGROUP_INET_EGRESS;
else
return usage(argv[0]);
if (argc > 3 && strcmp(argv[3], "drop") == 0)
verdict = 0;
cg_fd = open(argv[1], O_DIRECTORY | O_RDONLY);
if (cg_fd < 0) {
printf("Failed to open cgroup path: '%s'\n", strerror(errno));
return EXIT_FAILURE;
}
map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY,
sizeof(key), sizeof(byte_cnt),
256, 0);
if (map_fd < 0) {
printf("Failed to create map: '%s'\n", strerror(errno));
return EXIT_FAILURE;
}
prog_fd = prog_load(map_fd, verdict);
printf("Output from kernel verifier:\n%s\n-------\n", bpf_log_buf);
if (prog_fd < 0) {
printf("Failed to load prog: '%s'\n", strerror(errno));
return EXIT_FAILURE;
}
ret = bpf_prog_detach(cg_fd, type);
printf("bpf_prog_detach() returned '%s' (%d)\n", strerror(errno), errno);
ret = bpf_prog_attach(prog_fd, cg_fd, type);
if (ret < 0) {
printf("Failed to attach prog to cgroup: '%s'\n",
strerror(errno));
return EXIT_FAILURE;
}
while (1) {
key = MAP_KEY_PACKETS;
assert(bpf_lookup_elem(map_fd, &key, &pkt_cnt) == 0);
key = MAP_KEY_BYTES;
assert(bpf_lookup_elem(map_fd, &key, &byte_cnt) == 0);
printf("cgroup received %lld packets, %lld bytes\n",
pkt_cnt, byte_cnt);
sleep(1);
}
return EXIT_SUCCESS;
}
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment