Merge branch 'bpftool-visualization'

Jakub Kicinski says:

====================
Jiong says:

This patch set is an application of CFG information on eBPF program
visualization. It presents some initial code for building CFG information
from eBPF instruction sequences.

After we get eBPF program bytecode, we do sub-program detection and
basic-block partition. These information then are visualized into DOT
graph.

The user could use any DOT graphic tools (xdot, graphviz etc) to view it.

For example:

  bpftool prog dump xlated id 2 visual &>output.dot

  [xdot | dotty] output.dot
  dot -Tpng -o output.png

This initial patch set hasn't tuned much on the dot description layout
nor decoration, we could improve them later once the direction of the patch
set is agreed on. We could also visualize some static analysis performance
data.

v2 (Jakub):
 - update license headers and add SPDX tags.
====================

Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 30 insertions, 275 deletions

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index e549e329be82..f7a810897eac 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -47,8 +47,9 @@
 #include <bpf.h>
 #include <libbpf.h>
 
+#include "cfg.h"
 #include "main.h"
-#include "disasm.h"
+#include "xlated_dumper.h"
 
 static const char * const prog_type_name[] = {
 	[BPF_PROG_TYPE_UNSPEC]		= "unspec",
@@ -407,259 +408,6 @@ static int do_show(int argc, char **argv)
 	return err;
 }
 
-#define SYM_MAX_NAME	256
-
-struct kernel_sym {
-	unsigned long address;
-	char name[SYM_MAX_NAME];
-};
-
-struct dump_data {
-	unsigned long address_call_base;
-	struct kernel_sym *sym_mapping;
-	__u32 sym_count;
-	char scratch_buff[SYM_MAX_NAME];
-};
-
-static int kernel_syms_cmp(const void *sym_a, const void *sym_b)
-{
-	return ((struct kernel_sym *)sym_a)->address -
-	       ((struct kernel_sym *)sym_b)->address;
-}
-
-static void kernel_syms_load(struct dump_data *dd)
-{
-	struct kernel_sym *sym;
-	char buff[256];
-	void *tmp, *address;
-	FILE *fp;
-
-	fp = fopen("/proc/kallsyms", "r");
-	if (!fp)
-		return;
-
-	while (!feof(fp)) {
-		if (!fgets(buff, sizeof(buff), fp))
-			break;
-		tmp = realloc(dd->sym_mapping,
-			      (dd->sym_count + 1) *
-			      sizeof(*dd->sym_mapping));
-		if (!tmp) {
-out:
-			free(dd->sym_mapping);
-			dd->sym_mapping = NULL;
-			fclose(fp);
-			return;
-		}
-		dd->sym_mapping = tmp;
-		sym = &dd->sym_mapping[dd->sym_count];
-		if (sscanf(buff, "%p %*c %s", &address, sym->name) != 2)
-			continue;
-		sym->address = (unsigned long)address;
-		if (!strcmp(sym->name, "__bpf_call_base")) {
-			dd->address_call_base = sym->address;
-			/* sysctl kernel.kptr_restrict was set */
-			if (!sym->address)
-				goto out;
-		}
-		if (sym->address)
-			dd->sym_count++;
-	}
-
-	fclose(fp);
-
-	qsort(dd->sym_mapping, dd->sym_count,
-	      sizeof(*dd->sym_mapping), kernel_syms_cmp);
-}
-
-static void kernel_syms_destroy(struct dump_data *dd)
-{
-	free(dd->sym_mapping);
-}
-
-static struct kernel_sym *kernel_syms_search(struct dump_data *dd,
-					     unsigned long key)
-{
-	struct kernel_sym sym = {
-		.address = key,
-	};
-
-	return dd->sym_mapping ?
-	       bsearch(&sym, dd->sym_mapping, dd->sym_count,
-		       sizeof(*dd->sym_mapping), kernel_syms_cmp) : NULL;
-}
-
-static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...)
-{
-	va_list args;
-
-	va_start(args, fmt);
-	vprintf(fmt, args);
-	va_end(args);
-}
-
-static const char *print_call_pcrel(struct dump_data *dd,
-				    struct kernel_sym *sym,
-				    unsigned long address,
-				    const struct bpf_insn *insn)
-{
-	if (sym)
-		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
-			 "%+d#%s", insn->off, sym->name);
-	else
-		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
-			 "%+d#0x%lx", insn->off, address);
-	return dd->scratch_buff;
-}
-
-static const char *print_call_helper(struct dump_data *dd,
-				     struct kernel_sym *sym,
-				     unsigned long address)
-{
-	if (sym)
-		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
-			 "%s", sym->name);
-	else
-		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
-			 "0x%lx", address);
-	return dd->scratch_buff;
-}
-
-static const char *print_call(void *private_data,
-			      const struct bpf_insn *insn)
-{
-	struct dump_data *dd = private_data;
-	unsigned long address = dd->address_call_base + insn->imm;
-	struct kernel_sym *sym;
-
-	sym = kernel_syms_search(dd, address);
-	if (insn->src_reg == BPF_PSEUDO_CALL)
-		return print_call_pcrel(dd, sym, address, insn);
-	else
-		return print_call_helper(dd, sym, address);
-}
-
-static const char *print_imm(void *private_data,
-			     const struct bpf_insn *insn,
-			     __u64 full_imm)
-{
-	struct dump_data *dd = private_data;
-
-	if (insn->src_reg == BPF_PSEUDO_MAP_FD)
-		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
-			 "map[id:%u]", insn->imm);
-	else
-		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
-			 "0x%llx", (unsigned long long)full_imm);
-	return dd->scratch_buff;
-}
-
-static void dump_xlated_plain(struct dump_data *dd, void *buf,
-			      unsigned int len, bool opcodes)
-{
-	const struct bpf_insn_cbs cbs = {
-		.cb_print	= print_insn,
-		.cb_call	= print_call,
-		.cb_imm		= print_imm,
-		.private_data	= dd,
-	};
-	struct bpf_insn *insn = buf;
-	bool double_insn = false;
-	unsigned int i;
-
-	for (i = 0; i < len / sizeof(*insn); i++) {
-		if (double_insn) {
-			double_insn = false;
-			continue;
-		}
-
-		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
-
-		printf("% 4d: ", i);
-		print_bpf_insn(&cbs, NULL, insn + i, true);
-
-		if (opcodes) {
-			printf("       ");
-			fprint_hex(stdout, insn + i, 8, " ");
-			if (double_insn && i < len - 1) {
-				printf(" ");
-				fprint_hex(stdout, insn + i + 1, 8, " ");
-			}
-			printf("\n");
-		}
-	}
-}
-
-static void print_insn_json(struct bpf_verifier_env *env, const char *fmt, ...)
-{
-	unsigned int l = strlen(fmt);
-	char chomped_fmt[l];
-	va_list args;
-
-	va_start(args, fmt);
-	if (l > 0) {
-		strncpy(chomped_fmt, fmt, l - 1);
-		chomped_fmt[l - 1] = '\0';
-	}
-	jsonw_vprintf_enquote(json_wtr, chomped_fmt, args);
-	va_end(args);
-}
-
-static void dump_xlated_json(struct dump_data *dd, void *buf,
-			     unsigned int len, bool opcodes)
-{
-	const struct bpf_insn_cbs cbs = {
-		.cb_print	= print_insn_json,
-		.cb_call	= print_call,
-		.cb_imm		= print_imm,
-		.private_data	= dd,
-	};
-	struct bpf_insn *insn = buf;
-	bool double_insn = false;
-	unsigned int i;
-
-	jsonw_start_array(json_wtr);
-	for (i = 0; i < len / sizeof(*insn); i++) {
-		if (double_insn) {
-			double_insn = false;
-			continue;
-		}
-		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
-
-		jsonw_start_object(json_wtr);
-		jsonw_name(json_wtr, "disasm");
-		print_bpf_insn(&cbs, NULL, insn + i, true);
-
-		if (opcodes) {
-			jsonw_name(json_wtr, "opcodes");
-			jsonw_start_object(json_wtr);
-
-			jsonw_name(json_wtr, "code");
-			jsonw_printf(json_wtr, "\"0x%02hhx\"", insn[i].code);
-
-			jsonw_name(json_wtr, "src_reg");
-			jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].src_reg);
-
-			jsonw_name(json_wtr, "dst_reg");
-			jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].dst_reg);
-
-			jsonw_name(json_wtr, "off");
-			print_hex_data_json((uint8_t *)(&insn[i].off), 2);
-
-			jsonw_name(json_wtr, "imm");
-			if (double_insn && i < len - 1)
-				print_hex_data_json((uint8_t *)(&insn[i].imm),
-						    12);
-			else
-				print_hex_data_json((uint8_t *)(&insn[i].imm),
-						    4);
-			jsonw_end_object(json_wtr);
-		}
-		jsonw_end_object(json_wtr);
-	}
-	jsonw_end_array(json_wtr);
-}
-
 static int do_dump(int argc, char **argv)
 {
 	struct bpf_prog_info info = {};
@@ -668,6 +416,7 @@ static int do_dump(int argc, char **argv)
 	unsigned int buf_size;
 	char *filepath = NULL;
 	bool opcodes = false;
+	bool visual = false;
 	unsigned char *buf;
 	__u32 *member_len;
 	__u64 *member_ptr;
@@ -706,6 +455,9 @@ static int do_dump(int argc, char **argv)
 	} else if (is_prefix(*argv, "opcodes")) {
 		opcodes = true;
 		NEXT_ARG();
+	} else if (is_prefix(*argv, "visual")) {
+		visual = true;
+		NEXT_ARG();
 	}
 
 	if (argc) {
@@ -777,27 +529,30 @@ static int do_dump(int argc, char **argv)
 
 		if (json_output)
 			jsonw_null(json_wtr);
-	} else {
-		if (member_len == &info.jited_prog_len) {
-			const char *name = NULL;
-
-			if (info.ifindex) {
-				name = ifindex_to_bfd_name_ns(info.ifindex,
-							      info.netns_dev,
-							      info.netns_ino);
-				if (!name)
-					goto err_free;
-			}
-
-			disasm_print_insn(buf, *member_len, opcodes, name);
-		} else {
-			kernel_syms_load(&dd);
-			if (json_output)
-				dump_xlated_json(&dd, buf, *member_len, opcodes);
-			else
-				dump_xlated_plain(&dd, buf, *member_len, opcodes);
-			kernel_syms_destroy(&dd);
+	} else if (member_len == &info.jited_prog_len) {
+		const char *name = NULL;
+
+		if (info.ifindex) {
+			name = ifindex_to_bfd_name_ns(info.ifindex,
+						      info.netns_dev,
+						      info.netns_ino);
+			if (!name)
+				goto err_free;
 		}
+
+		disasm_print_insn(buf, *member_len, opcodes, name);
+	} else if (visual) {
+		if (json_output)
+			jsonw_null(json_wtr);
+		else
+			dump_xlated_cfg(buf, *member_len);
+	} else {
+		kernel_syms_load(&dd);
+		if (json_output)
+			dump_xlated_json(&dd, buf, *member_len, opcodes);
+		else
+			dump_xlated_plain(&dd, buf, *member_len, opcodes);
+		kernel_syms_destroy(&dd);
 	}
 
 	free(buf);
@@ -851,7 +606,7 @@ static int do_help(int argc, char **argv)
 
 	fprintf(stderr,
 		"Usage: %s %s { show | list } [PROG]\n"
-		"       %s %s dump xlated PROG [{ file FILE | opcodes }]\n"
+		"       %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
 		"       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
 		"       %s %s pin   PROG FILE\n"
 		"       %s %s load  OBJ  FILE\n"