samples/bpf: bpf_tail_call example for tracing

kprobe example that demonstrates how future seccomp programs may look like.
It attaches to seccomp_phase1() function and tail-calls other BPF programs
depending on syscall number.

Existing optimized classic BPF seccomp programs generated by Chrome look like:
if (sd.nr < 121) {
  if (sd.nr < 57) {
    if (sd.nr < 22) {
      if (sd.nr < 7) {
        if (sd.nr < 4) {
          if (sd.nr < 1) {
            check sys_read
          } else {
            if (sd.nr < 3) {
              check sys_write and sys_open
            } else {
              check sys_close
            }
          }
        } else {
      } else {
    } else {
  } else {
} else {
}

the future seccomp using native eBPF may look like:
  bpf_tail_call(&sd, &syscall_jmp_table, sd.nr);
which is simpler, faster and leaves more room for per-syscall checks.

Usage:
$ sudo ./tracex5
<...>-366   [001] d...     4.870033: : read(fd=1, buf=00007f6d5bebf000, size=771)
<...>-369   [003] d...     4.870066: : mmap
<...>-369   [003] d...     4.870077: : syscall=110 (one of get/set uid/pid/gid)
<...>-369   [003] d...     4.870089: : syscall=107 (one of get/set uid/pid/gid)
   sh-369   [000] d...     4.891740: : read(fd=0, buf=00000000023d1000, size=512)
   sh-369   [000] d...     4.891747: : write(fd=1, buf=00000000023d3000, size=512)
   sh-369   [000] d...     4.891747: : read(fd=1, buf=00000000023d3000, size=512)

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 45 insertions, 12 deletions

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 38dac5a53b51..da86a8e0a95a 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -16,6 +16,7 @@
 #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"
@@ -29,6 +30,19 @@ 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)
 {
@@ -54,12 +68,40 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		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_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);
@@ -71,18 +113,6 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		}
 	}
 
-	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_socket)
-		return 0;
-
 	strcpy(buf, DEBUGFS);
 	strcat(buf, "events/kprobes/");
 	strcat(buf, event);
@@ -130,6 +160,9 @@ static int load_maps(struct bpf_map_def *maps, int len)
 					   maps[i].max_entries);
 		if (map_fd[i] < 0)
 			return 1;
+
+		if (maps[i].type == BPF_MAP_TYPE_PROG_ARRAY)
+			prog_array_fd = map_fd[i];
 	}
 	return 0;
 }