samples/bpf/bpf_load.c

#include <stdio.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <libelf.h>
#include <gelf.h>
#include <errno.h>
#include <unistd.h>
#include <string.h>
#include <stdbool.h>
#include <stdlib.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/perf_event.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <poll.h>
#include <ctype.h>
#include "libbpf.h"
#include "bpf_helpers.h"
#include "bpf_load.h"

#define DEBUGFS "/sys/kernel/debug/tracing/"

static char license[128];
static int kern_version;
static bool processed_sec[128];
int map_fd[MAX_MAPS];
int prog_fd[MAX_PROGS];
int event_fd[MAX_PROGS];
int prog_cnt;
int prog_array_fd = -1;

static int populate_prog_array(const char *event, int prog_fd)
{
	int ind = atoi(event), err;

	err = bpf_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY);
	if (err < 0) {
		printf("failed to store prog_fd in prog_array\n");
		return -1;
	}
	return 0;
}

static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
{
	bool is_socket = strncmp(event, "socket", 6) == 0;
	bool is_kprobe = strncmp(event, "kprobe/", 7) == 0;
	bool is_kretprobe = strncmp(event, "kretprobe/", 10) == 0;
	bool is_tracepoint = strncmp(event, "tracepoint/", 11) == 0;
	bool is_xdp = strncmp(event, "xdp", 3) == 0;
	bool is_perf_event = strncmp(event, "perf_event", 10) == 0;
	bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0;
	bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0;
	enum bpf_prog_type prog_type;
	char buf[256];
	int fd, efd, err, id;
	struct perf_event_attr attr = {};

	attr.type = PERF_TYPE_TRACEPOINT;
	attr.sample_type = PERF_SAMPLE_RAW;
	attr.sample_period = 1;
	attr.wakeup_events = 1;

	if (is_socket) {
		prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
	} else if (is_kprobe || is_kretprobe) {
		prog_type = BPF_PROG_TYPE_KPROBE;
	} else if (is_tracepoint) {
		prog_type = BPF_PROG_TYPE_TRACEPOINT;
	} else if (is_xdp) {
		prog_type = BPF_PROG_TYPE_XDP;
	} else if (is_perf_event) {
		prog_type = BPF_PROG_TYPE_PERF_EVENT;
	} else if (is_cgroup_skb) {
		prog_type = BPF_PROG_TYPE_CGROUP_SKB;
	} else if (is_cgroup_sk) {
		prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
	} else {
		printf("Unknown event '%s'\n", event);
		return -1;
	}

	fd = bpf_prog_load(prog_type, prog, size, license, kern_version);
	if (fd < 0) {
		printf("bpf_prog_load() err=%d\n%s", errno, bpf_log_buf);
		return -1;
	}

	prog_fd[prog_cnt++] = fd;

	if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk)
		return 0;

	if (is_socket) {
		event += 6;
		if (*event != '/')
			return 0;
		event++;
		if (!isdigit(*event)) {
			printf("invalid prog number\n");
			return -1;
		}
		return populate_prog_array(event, fd);
	}

	if (is_kprobe || is_kretprobe) {
		if (is_kprobe)
			event += 7;
		else
			event += 10;

		if (*event == 0) {
			printf("event name cannot be empty\n");
			return -1;
		}

		if (isdigit(*event))
			return populate_prog_array(event, fd);

		snprintf(buf, sizeof(buf),
			 "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events",
			 is_kprobe ? 'p' : 'r', event, event);
		err = system(buf);
		if (err < 0) {
			printf("failed to create kprobe '%s' error '%s'\n",
			       event, strerror(errno));
			return -1;
		}

		strcpy(buf, DEBUGFS);
		strcat(buf, "events/kprobes/");
		strcat(buf, event);
		strcat(buf, "/id");
	} else if (is_tracepoint) {
		event += 11;

		if (*event == 0) {
			printf("event name cannot be empty\n");
			return -1;
		}
		strcpy(buf, DEBUGFS);
		strcat(buf, "events/");
		strcat(buf, event);
		strcat(buf, "/id");
	}

	efd = open(buf, O_RDONLY, 0);
	if (efd < 0) {
		printf("failed to open event %s\n", event);
		return -1;
	}

	err = read(efd, buf, sizeof(buf));
	if (err < 0 || err >= sizeof(buf)) {
		printf("read from '%s' failed '%s'\n", event, strerror(errno));
		return -1;
	}

	close(efd);

	buf[err] = 0;
	id = atoi(buf);
	attr.config = id;

	efd = perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
	if (efd < 0) {
		printf("event %d fd %d err %s\n", id, efd, strerror(errno));
		return -1;
	}
	event_fd[prog_cnt - 1] = efd;
	ioctl(efd, PERF_EVENT_IOC_ENABLE, 0);
	ioctl(efd, PERF_EVENT_IOC_SET_BPF, fd);

	return 0;
}

static int load_maps(struct bpf_map_def *maps, int len)
{
	int i;

	for (i = 0; i < len / sizeof(struct bpf_map_def); i++) {

		map_fd[i] = bpf_create_map(maps[i].type,
					   maps[i].key_size,
					   maps[i].value_size,
					   maps[i].max_entries,
					   maps[i].map_flags);
		if (map_fd[i] < 0) {
			printf("failed to create a map: %d %s\n",
			       errno, strerror(errno));
			return 1;
		}

		if (maps[i].type == BPF_MAP_TYPE_PROG_ARRAY)
			prog_array_fd = map_fd[i];
	}
	return 0;
}

static int get_sec(Elf *elf, int i, GElf_Ehdr *ehdr, char **shname,
		   GElf_Shdr *shdr, Elf_Data **data)
{
	Elf_Scn *scn;

	scn = elf_getscn(elf, i);
	if (!scn)
		return 1;

	if (gelf_getshdr(scn, shdr) != shdr)
		return 2;

	*shname = elf_strptr(elf, ehdr->e_shstrndx, shdr->sh_name);
	if (!*shname || !shdr->sh_size)
		return 3;

	*data = elf_getdata(scn, 0);
	if (!*data || elf_getdata(scn, *data) != NULL)
		return 4;

	return 0;
}

static int parse_relo_and_apply(Elf_Data *data, Elf_Data *symbols,
				GElf_Shdr *shdr, struct bpf_insn *insn)
{
	int i, nrels;

	nrels = shdr->sh_size / shdr->sh_entsize;

	for (i = 0; i < nrels; i++) {
		GElf_Sym sym;
		GElf_Rel rel;
		unsigned int insn_idx;

		gelf_getrel(data, i, &rel);

		insn_idx = rel.r_offset / sizeof(struct bpf_insn);

		gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym);

		if (insn[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
			printf("invalid relo for insn[%d].code 0x%x\n",
			       insn_idx, insn[insn_idx].code);
			return 1;
		}
		insn[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
		insn[insn_idx].imm = map_fd[sym.st_value / sizeof(struct bpf_map_def)];
	}

	return 0;
}

int load_bpf_file(char *path)
{
	int fd, i;
	Elf *elf;
	GElf_Ehdr ehdr;
	GElf_Shdr shdr, shdr_prog;
	Elf_Data *data, *data_prog, *symbols = NULL;
	char *shname, *shname_prog;

	if (elf_version(EV_CURRENT) == EV_NONE)
		return 1;

	fd = open(path, O_RDONLY, 0);
	if (fd < 0)
		return 1;

	elf = elf_begin(fd, ELF_C_READ, NULL);

	if (!elf)
		return 1;

	if (gelf_getehdr(elf, &ehdr) != &ehdr)
		return 1;

	/* clear all kprobes */
	i = system("echo \"\" > /sys/kernel/debug/tracing/kprobe_events");

	/* scan over all elf sections to get license and map info */
	for (i = 1; i < ehdr.e_shnum; i++) {

		if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
			continue;

		if (0) /* helpful for llvm debugging */
			printf("section %d:%s data %p size %zd link %d flags %d\n",
			       i, shname, data->d_buf, data->d_size,
			       shdr.sh_link, (int) shdr.sh_flags);

		if (strcmp(shname, "license") == 0) {
			processed_sec[i] = true;
			memcpy(license, data->d_buf, data->d_size);
		} else if (strcmp(shname, "version") == 0) {
			processed_sec[i] = true;
			if (data->d_size != sizeof(int)) {
				printf("invalid size of version section %zd\n",
				       data->d_size);
				return 1;
			}
			memcpy(&kern_version, data->d_buf, sizeof(int));
		} else if (strcmp(shname, "maps") == 0) {
			processed_sec[i] = true;
			if (load_maps(data->d_buf, data->d_size))
				return 1;
		} else if (shdr.sh_type == SHT_SYMTAB) {
			symbols = data;
		}
	}

	/* load programs that need map fixup (relocations) */
	for (i = 1; i < ehdr.e_shnum; i++) {

		if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
			continue;
		if (shdr.sh_type == SHT_REL) {
			struct bpf_insn *insns;

			if (get_sec(elf, shdr.sh_info, &ehdr, &shname_prog,
				    &shdr_prog, &data_prog))
				continue;

			if (shdr_prog.sh_type != SHT_PROGBITS ||
			    !(shdr_prog.sh_flags & SHF_EXECINSTR))
				continue;

			insns = (struct bpf_insn *) data_prog->d_buf;

			processed_sec[shdr.sh_info] = true;
			processed_sec[i] = true;

			if (parse_relo_and_apply(data, symbols, &shdr, insns))
				continue;

			if (memcmp(shname_prog, "kprobe/", 7) == 0 ||
			    memcmp(shname_prog, "kretprobe/", 10) == 0 ||
			    memcmp(shname_prog, "tracepoint/", 11) == 0 ||
			    memcmp(shname_prog, "xdp", 3) == 0 ||
			    memcmp(shname_prog, "perf_event", 10) == 0 ||
			    memcmp(shname_prog, "socket", 6) == 0 ||
			    memcmp(shname_prog, "cgroup/", 7) == 0)
				load_and_attach(shname_prog, insns, data_prog->d_size);
		}
	}

	/* load programs that don't use maps */
	for (i = 1; i < ehdr.e_shnum; i++) {

		if (processed_sec[i])
			continue;

		if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
			continue;

		if (memcmp(shname, "kprobe/", 7) == 0 ||
		    memcmp(shname, "kretprobe/", 10) == 0 ||
		    memcmp(shname, "tracepoint/", 11) == 0 ||
		    memcmp(shname, "xdp", 3) == 0 ||
		    memcmp(shname, "perf_event", 10) == 0 ||
		    memcmp(shname, "socket", 6) == 0 ||
		    memcmp(shname, "cgroup/", 7) == 0)
			load_and_attach(shname, data->d_buf, data->d_size);
	}

	close(fd);
	return 0;
}

void read_trace_pipe(void)
{
	int trace_fd;

	trace_fd = open(DEBUGFS "trace_pipe", O_RDONLY, 0);
	if (trace_fd < 0)
		return;

	while (1) {
		static char buf[4096];
		ssize_t sz;

		sz = read(trace_fd, buf, sizeof(buf));
		if (sz > 0) {
			buf[sz] = 0;
			puts(buf);
		}
	}
}

#define MAX_SYMS 300000
static struct ksym syms[MAX_SYMS];
static int sym_cnt;

static int ksym_cmp(const void *p1, const void *p2)
{
	return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
}

int load_kallsyms(void)
{
	FILE *f = fopen("/proc/kallsyms", "r");
	char func[256], buf[256];
	char symbol;
	void *addr;
	int i = 0;

	if (!f)
		return -ENOENT;

	while (!feof(f)) {
		if (!fgets(buf, sizeof(buf), f))
			break;
		if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
			break;
		if (!addr)
			continue;
		syms[i].addr = (long) addr;
		syms[i].name = strdup(func);
		i++;
	}
	sym_cnt = i;
	qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
	return 0;
}

struct ksym *ksym_search(long key)
{
	int start = 0, end = sym_cnt;
	int result;

	while (start < end) {
		size_t mid = start + (end - start) / 2;

		result = key - syms[mid].addr;
		if (result < 0)
			end = mid;
		else if (result > 0)
			start = mid + 1;
		else
			return &syms[mid];
	}

	if (start >= 1 && syms[start - 1].addr < key &&
	    key < syms[start].addr)
		/* valid ksym */
		return &syms[start - 1];

	/* out of range. return _stext */
	return &syms[0];
}

int set_link_xdp_fd(int ifindex, int fd)
{
	struct sockaddr_nl sa;
	int sock, seq = 0, len, ret = -1;
	char buf[4096];
	struct nlattr *nla, *nla_xdp;
	struct {
		struct nlmsghdr  nh;
		struct ifinfomsg ifinfo;
		char             attrbuf[64];
	} req;
	struct nlmsghdr *nh;
	struct nlmsgerr *err;

	memset(&sa, 0, sizeof(sa));
	sa.nl_family = AF_NETLINK;

	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
	if (sock < 0) {
		printf("open netlink socket: %s\n", strerror(errno));
		return -1;
	}

	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
		printf("bind to netlink: %s\n", strerror(errno));
		goto cleanup;
	}

	memset(&req, 0, sizeof(req));
	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
	req.nh.nlmsg_type = RTM_SETLINK;
	req.nh.nlmsg_pid = 0;
	req.nh.nlmsg_seq = ++seq;
	req.ifinfo.ifi_family = AF_UNSPEC;
	req.ifinfo.ifi_index = ifindex;
	nla = (struct nlattr *)(((char *)&req)
				+ NLMSG_ALIGN(req.nh.nlmsg_len));
	nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;

	nla_xdp = (struct nlattr *)((char *)nla + NLA_HDRLEN);
	nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
	nla->nla_len = NLA_HDRLEN + nla_xdp->nla_len;

	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);

	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
		printf("send to netlink: %s\n", strerror(errno));
		goto cleanup;
	}

	len = recv(sock, buf, sizeof(buf), 0);
	if (len < 0) {
		printf("recv from netlink: %s\n", strerror(errno));
		goto cleanup;
	}

	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
	     nh = NLMSG_NEXT(nh, len)) {
		if (nh->nlmsg_pid != getpid()) {
			printf("Wrong pid %d, expected %d\n",
			       nh->nlmsg_pid, getpid());
			goto cleanup;
		}
		if (nh->nlmsg_seq != seq) {
			printf("Wrong seq %d, expected %d\n",
			       nh->nlmsg_seq, seq);
			goto cleanup;
		}
		switch (nh->nlmsg_type) {
		case NLMSG_ERROR:
			err = (struct nlmsgerr *)NLMSG_DATA(nh);
			if (!err->error)
				continue;
			printf("nlmsg error %s\n", strerror(-err->error));
			goto cleanup;
		case NLMSG_DONE:
			break;
		}
	}

	ret = 0;

cleanup:
	close(sock);
	return ret;
}