bpftool: Support inline annotations when dumping the CFG of a program

We support dumping the control flow graph of loaded programs to the DOT
format with bpftool, but so far this feature wouldn't display the source
code lines available through BTF along with the eBPF bytecode. Let's add
support for these annotations, to make it easier to read the graph.

In prog.c, we move the call to dump_xlated_cfg() in order to pass and
use the full struct dump_data, instead of creating a minimal one in
draw_bb_node().

We pass the pointer to this struct down to dump_xlated_for_graph() in
xlated_dumper.c, where most of the logics is added. We deal with BTF
mostly like we do for plain or JSON output, except that we cannot use a
"nr_skip" value to skip a given number of linfo records (we don't
process the BPF instructions linearly, and apart from the root of the
graph we don't know how many records we should skip, so we just store
the last linfo and make sure the new one we find is different before
printing it).

When printing the source instructions to the label of a DOT graph node,
there are a few subtleties to address. We want some special newline
markers, and there are some characters that we must escape. To deal with
them, we introduce a new dedicated function btf_dump_linfo_dotlabel() in
btf_dumper.c. We'll reuse this function in a later commit to format the
filepath, line, and column references as well.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/r/20230405132120.59886-4-quentin@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/bpf/bpftool/btf_dumper.c

@@ -821,3 +821,37 @@ void btf_dump_linfo_json(const struct btf *btf,
 					BPF_LINE_INFO_LINE_COL(linfo->line_col));
 	}
 }
+
+static void dotlabel_puts(const char *s)
+{
+	for (; *s; ++s) {
+		switch (*s) {
+		case '\\':
+		case '"':
+		case '{':
+		case '}':
+		case '<':
+		case '>':
+		case '|':
+		case ' ':
+			putchar('\\');
+			__fallthrough;
+		default:
+			putchar(*s);
+		}
+	}
+}
+
+void btf_dump_linfo_dotlabel(const struct btf *btf,
+			     const struct bpf_line_info *linfo)
+{
+	const char *line = btf__name_by_offset(btf, linfo->line_off);
+
+	if (!line || !strlen(line))
+		return;
+	line = ltrim(line);
+
+	printf("; ");
+	dotlabel_puts(line);
+	printf("\\l\\\n");
+}

tools/bpf/bpftool/cfg.c

@@ -380,7 +380,8 @@ static void cfg_destroy(struct cfg *cfg)
 	}
 }
 
-static void draw_bb_node(struct func_node *func, struct bb_node *bb)
+static void
+draw_bb_node(struct func_node *func, struct bb_node *bb, struct dump_data *dd)
 {
 	const char *shape;
 
@@ -398,13 +399,9 @@ static void draw_bb_node(struct func_node *func, struct bb_node *bb)
 		printf("EXIT");
 	} else {
 		unsigned int start_idx;
-		struct dump_data dd = {};
-
-		printf("{");
-		kernel_syms_load(&dd);
+		printf("{\\\n");
 		start_idx = bb->head - func->start;
-		dump_xlated_for_graph(&dd, bb->head, bb->tail, start_idx);
-		kernel_syms_destroy(&dd);
+		dump_xlated_for_graph(dd, bb->head, bb->tail, start_idx);
 		printf("}");
 	}
 
@@ -430,12 +427,12 @@ static void draw_bb_succ_edges(struct func_node *func, struct bb_node *bb)
 	}
 }
 
-static void func_output_bb_def(struct func_node *func)
+static void func_output_bb_def(struct func_node *func, struct dump_data *dd)
 {
 	struct bb_node *bb;
 
 	list_for_each_entry(bb, &func->bbs, l) {
-		draw_bb_node(func, bb);
+		draw_bb_node(func, bb, dd);
 	}
 }
 
@@ -455,22 +452,22 @@ static void func_output_edges(struct func_node *func)
 	       func_idx, ENTRY_BLOCK_INDEX, func_idx, EXIT_BLOCK_INDEX);
 }
 
-static void cfg_dump(struct cfg *cfg)
+static void cfg_dump(struct cfg *cfg, struct dump_data *dd)
 {
 	struct func_node *func;
 
 	printf("digraph \"DOT graph for eBPF program\" {\n");
 	list_for_each_entry(func, &cfg->funcs, l) {
 		printf("subgraph \"cluster_%d\" {\n\tstyle=\"dashed\";\n\tcolor=\"black\";\n\tlabel=\"func_%d ()\";\n",
 		       func->idx, func->idx);
-		func_output_bb_def(func);
+		func_output_bb_def(func, dd);
 		func_output_edges(func);
 		printf("}\n");
 	}
 	printf("}\n");
 }
 
-void dump_xlated_cfg(void *buf, unsigned int len)
+void dump_xlated_cfg(struct dump_data *dd, void *buf, unsigned int len)
 {
 	struct bpf_insn *insn = buf;
 	struct cfg cfg;
@@ -479,7 +476,7 @@ void dump_xlated_cfg(void *buf, unsigned int len)
 	if (cfg_build(&cfg, insn, len))
 		return;
 
-	cfg_dump(&cfg);
+	cfg_dump(&cfg, dd);
 
 	cfg_destroy(&cfg);
 }

tools/bpf/bpftool/cfg.h

@@ -4,6 +4,8 @@
 #ifndef __BPF_TOOL_CFG_H
 #define __BPF_TOOL_CFG_H
 
-void dump_xlated_cfg(void *buf, unsigned int len);
+#include "xlated_dumper.h"
+
+void dump_xlated_cfg(struct dump_data *dd, void *buf, unsigned int len);
 
 #endif /* __BPF_TOOL_CFG_H */

tools/bpf/bpftool/main.h

@@ -229,6 +229,8 @@ void btf_dump_linfo_plain(const struct btf *btf,
 			  const char *prefix, bool linum);
 void btf_dump_linfo_json(const struct btf *btf,
 			 const struct bpf_line_info *linfo, bool linum);
+void btf_dump_linfo_dotlabel(const struct btf *btf,
+			     const struct bpf_line_info *linfo);
 
 struct nlattr;
 struct ifinfomsg;

tools/bpf/bpftool/prog.c

@@ -840,11 +840,6 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 					      false))
 				goto exit_free;
 		}
-	} else if (visual) {
-		if (json_output)
-			jsonw_null(json_wtr);
-		else
-			dump_xlated_cfg(buf, member_len);
 	} else {
 		kernel_syms_load(&dd);
 		dd.nr_jited_ksyms = info->nr_jited_ksyms;
@@ -854,12 +849,14 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 		dd.finfo_rec_size = info->func_info_rec_size;
 		dd.prog_linfo = prog_linfo;
 
-		if (json_output)
-			dump_xlated_json(&dd, buf, member_len, opcodes,
-					 linum);
+		if (json_output && visual)
+			jsonw_null(json_wtr);
+		else if (json_output)
+			dump_xlated_json(&dd, buf, member_len, opcodes, linum);
+		else if (visual)
+			dump_xlated_cfg(&dd, buf, member_len);
 		else
-			dump_xlated_plain(&dd, buf, member_len, opcodes,
-					  linum);
+			dump_xlated_plain(&dd, buf, member_len, opcodes, linum);
 		kernel_syms_destroy(&dd);
 	}
 

tools/bpf/bpftool/xlated_dumper.c

@@ -369,21 +369,51 @@ void dump_xlated_for_graph(struct dump_data *dd, void *buf_start, void *buf_end,
 		.cb_imm		= print_imm,
 		.private_data	= dd,
 	};
+	const struct bpf_prog_linfo *prog_linfo = dd->prog_linfo;
+	const struct bpf_line_info *last_linfo = NULL;
+	struct bpf_func_info *record = dd->func_info;
 	struct bpf_insn *insn_start = buf_start;
 	struct bpf_insn *insn_end = buf_end;
 	struct bpf_insn *cur = insn_start;
+	struct btf *btf = dd->btf;
 	bool double_insn = false;
+	char func_sig[1024];
 
 	for (; cur <= insn_end; cur++) {
+		unsigned int insn_off;
+
 		if (double_insn) {
 			double_insn = false;
 			continue;
 		}
 		double_insn = cur->code == (BPF_LD | BPF_IMM | BPF_DW);
 
-		printf("% 4d: ", (int)(cur - insn_start + start_idx));
+		insn_off = (unsigned int)(cur - insn_start + start_idx);
+		if (btf && record) {
+			if (record->insn_off == insn_off) {
+				btf_dumper_type_only(btf, record->type_id,
+						     func_sig,
+						     sizeof(func_sig));
+				if (func_sig[0] != '\0')
+					printf("; %s:\\l\\\n", func_sig);
+				record = (void *)record + dd->finfo_rec_size;
+			}
+		}
+
+		if (prog_linfo) {
+			const struct bpf_line_info *linfo;
+
+			linfo = bpf_prog_linfo__lfind(prog_linfo, insn_off, 0);
+			if (linfo && linfo != last_linfo) {
+				btf_dump_linfo_dotlabel(btf, linfo);
+				last_linfo = linfo;
+			}
+		}
+
+		printf("%d: ", insn_off);
 		print_bpf_insn(&cbs, cur, true);
+
 		if (cur != insn_end)
-			printf(" | ");
+			printf("| ");
 	}
 }