selftests/bpf: Emit top frequent code lines in veristat

Production BPF programs are increasing in number of instructions and states
to the point, where optimising verification process for them is necessary
to avoid running into instruction limit. Authors of those BPF programs
need to analyze verifier output, for example, collecting the most
frequent source code lines to understand which part of the program has
the biggest verification cost.

This patch introduces `--top-src-lines` flag in veristat.
`--top-src-lines=N` makes veristat output N the most popular sorce code
lines, parsed from verification log.

An example of output:
```
sudo ./veristat  --top-src-lines=2   bpf_flow.bpf.o
Processing 'bpf_flow.bpf.o'...
Top source lines (_dissect):
    4: (bpf_helpers.h:161)	asm volatile("r1 = %[ctx]\n\t"
    4: (bpf_flow.c:155)	if (iph && iph->ihl == 5 &&
...
```

Signed-off-by: Mykyta Yatsenko <[email protected]>
Signed-off-by: Andrii Nakryiko <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

tools/testing/selftests/bpf/veristat.c

@@ -179,6 +179,7 @@ static struct env {
 	int files_skipped;
 	int progs_processed;
 	int progs_skipped;
+	int top_src_lines;
 } env;
 
 static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
@@ -228,6 +229,7 @@ static const struct argp_option opts[] = {
 	  "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" },
 	{ "test-reg-invariants", 'r', NULL, 0,
 	  "Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" },
+	{ "top-src-lines", 'S', "N", 0, "Emit N most frequent source code lines" },
 	{},
 };
 
@@ -327,6 +329,14 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 			return err;
 		}
 		break;
+	case 'S':
+		errno = 0;
+		env.top_src_lines = strtol(arg, NULL, 10);
+		if (errno) {
+			fprintf(stderr, "invalid top lines N specifier: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
 	case ARGP_KEY_ARG:
 		tmp = realloc(env.filenames, (env.filename_cnt + 1) * sizeof(*env.filenames));
 		if (!tmp)
@@ -854,6 +864,118 @@ static int parse_verif_log(char * const buf, size_t buf_sz, struct verif_stats *
 	return 0;
 }
 
+struct line_cnt {
+	char *line;
+	int cnt;
+};
+
+static int str_cmp(const void *a, const void *b)
+{
+	const char **str1 = (const char **)a;
+	const char **str2 = (const char **)b;
+
+	return strcmp(*str1, *str2);
+}
+
+static int line_cnt_cmp(const void *a, const void *b)
+{
+	const struct line_cnt *a_cnt = (const struct line_cnt *)a;
+	const struct line_cnt *b_cnt = (const struct line_cnt *)b;
+
+	if (a_cnt->cnt != b_cnt->cnt)
+		return a_cnt->cnt < b_cnt->cnt ? -1 : 1;
+	return strcmp(a_cnt->line, b_cnt->line);
+}
+
+static int print_top_src_lines(char * const buf, size_t buf_sz, const char *prog_name)
+{
+	int lines_cap = 0;
+	int lines_size = 0;
+	char **lines = NULL;
+	char *line = NULL;
+	char *state;
+	struct line_cnt *freq = NULL;
+	struct line_cnt *cur;
+	int unique_lines;
+	int err = 0;
+	int i;
+
+	while ((line = strtok_r(line ? NULL : buf, "\n", &state))) {
+		if (strncmp(line, "; ", 2) != 0)
+			continue;
+		line += 2;
+
+		if (lines_size == lines_cap) {
+			char **tmp;
+
+			lines_cap = max(16, lines_cap * 2);
+			tmp = realloc(lines, lines_cap * sizeof(*tmp));
+			if (!tmp) {
+				err = -ENOMEM;
+				goto cleanup;
+			}
+			lines = tmp;
+		}
+		lines[lines_size] = line;
+		lines_size++;
+	}
+
+	if (lines_size == 0)
+		goto cleanup;
+
+	qsort(lines, lines_size, sizeof(*lines), str_cmp);
+
+	freq = calloc(lines_size, sizeof(*freq));
+	if (!freq) {
+		err = -ENOMEM;
+		goto cleanup;
+	}
+
+	cur = freq;
+	cur->line = lines[0];
+	cur->cnt = 1;
+	for (i = 1; i < lines_size; ++i) {
+		if (strcmp(lines[i], cur->line) != 0) {
+			cur++;
+			cur->line = lines[i];
+			cur->cnt = 0;
+		}
+		cur->cnt++;
+	}
+	unique_lines = cur - freq + 1;
+
+	qsort(freq, unique_lines, sizeof(struct line_cnt), line_cnt_cmp);
+
+	printf("Top source lines (%s):\n", prog_name);
+	for (i = 0; i < min(unique_lines, env.top_src_lines); ++i) {
+		const char *src_code = freq[i].line;
+		const char *src_line = NULL;
+		char *split = strrchr(freq[i].line, '@');
+
+		if (split) {
+			src_line = split + 1;
+
+			while (*src_line && isspace(*src_line))
+				src_line++;
+
+			while (split > src_code && isspace(*split))
+				split--;
+			*split = '\0';
+		}
+
+		if (src_line)
+			printf("%5d: (%s)\t%s\n", freq[i].cnt, src_line, src_code);
+		else
+			printf("%5d: %s\n", freq[i].cnt, src_code);
+	}
+	printf("\n");
+
+cleanup:
+	free(freq);
+	free(lines);
+	return err;
+}
+
 static int guess_prog_type_by_ctx_name(const char *ctx_name,
 				       enum bpf_prog_type *prog_type,
 				       enum bpf_attach_type *attach_type)
@@ -1009,13 +1131,16 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
 	stats = &env.prog_stats[env.prog_stat_cnt++];
 	memset(stats, 0, sizeof(*stats));
 
-	if (env.verbose) {
+	if (env.verbose || env.top_src_lines > 0) {
 		buf_sz = env.log_size ? env.log_size : 16 * 1024 * 1024;
 		buf = malloc(buf_sz);
 		if (!buf)
 			return -ENOMEM;
 		/* ensure we always request stats */
 		log_level = env.log_level | 4 | (env.log_fixed ? 8 : 0);
+		/* --top-src-lines needs verifier log */
+		if (env.top_src_lines > 0 && env.log_level == 0)
+			log_level |= 2;
 	} else {
 		buf = verif_log_buf;
 		buf_sz = sizeof(verif_log_buf);
@@ -1048,6 +1173,8 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
 		       filename, prog_name, stats->stats[DURATION],
 		       err ? "failure" : "success", buf);
 	}
+	if (env.top_src_lines > 0)
+		print_top_src_lines(buf, buf_sz, stats->prog_name);
 
 	if (verif_log_buf != buf)
 		free(buf);