perf capstone: Move capstone functionality into its own file

Capstone disassembly support was split between disasm.c and
print_insn.c. Move support out of these files into capstone.[ch] and
remove include capstone/capstone.h from those files. As disassembly
routines can fail, make failure the only option without
HAVE_LIBCAPSTONE_SUPPORT. For simplicity's sake, duplicate the
read_symbol utility function.

The intent with moving capstone support into a single file is that
dynamic support, using dlopen for libcapstone, can be added in later
patches. This can potentially always succeed or fail, so relying on
ifdefs isn't sufficient. Using dlopen is a useful option to minimize
the perf tools dependencies and potentially size.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Charlie Jenkins <charlie@rivosinc.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Haibo Xu <haibo1.xu@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Li Huafei <lihuafei1@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 5 insertions, 351 deletions

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index e257bd918c89..28529fda8a87 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -14,6 +14,7 @@
 #include "annotate.h"
 #include "annotate-data.h"
 #include "build-id.h"
+#include "capstone.h"
 #include "debug.h"
 #include "disasm.h"
 #include "disasm_bpf.h"
@@ -1333,39 +1334,7 @@ fallback:
 	return 0;
 }
 
-#ifdef HAVE_LIBCAPSTONE_SUPPORT
-#include <capstone/capstone.h>
-
-int capstone_init(struct machine *machine, csh *cs_handle, bool is64, bool disassembler_style);
-
-static int open_capstone_handle(struct annotate_args *args, bool is_64bit,
-				csh *handle)
-{
-	struct annotation_options *opt = args->options;
-	cs_mode mode = is_64bit ? CS_MODE_64 : CS_MODE_32;
-
-	/* TODO: support more architectures */
-	if (!arch__is(args->arch, "x86"))
-		return -1;
-
-	if (cs_open(CS_ARCH_X86, mode, handle) != CS_ERR_OK)
-		return -1;
-
-	if (!opt->disassembler_style ||
-	    !strcmp(opt->disassembler_style, "att"))
-		cs_option(*handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT);
-
-	/*
-	 * Resolving address operands to symbols is implemented
-	 * on x86 by investigating instruction details.
-	 */
-	cs_option(*handle, CS_OPT_DETAIL, CS_OPT_ON);
-
-	return 0;
-}
-#endif
-
-#if defined(HAVE_LIBCAPSTONE_SUPPORT) || defined(HAVE_LIBLLVM_SUPPORT)
+#if defined(HAVE_LIBLLVM_SUPPORT)
 struct find_file_offset_data {
 	u64 ip;
 	u64 offset;
@@ -1431,322 +1400,6 @@ err:
 }
 #endif
 
-#if !defined(HAVE_LIBCAPSTONE_SUPPORT) || !defined(HAVE_LIBLLVM_SUPPORT)
-static void symbol__disassembler_missing(const char *disassembler, const char *filename,
-					 struct symbol *sym)
-{
-	pr_debug("The %s disassembler isn't linked in for %s in %s\n",
-		 disassembler, sym->name, filename);
-}
-#endif
-
-#ifdef HAVE_LIBCAPSTONE_SUPPORT
-static void print_capstone_detail(cs_insn *insn, char *buf, size_t len,
-				  struct annotate_args *args, u64 addr)
-{
-	int i;
-	struct map *map = args->ms.map;
-	struct symbol *sym;
-
-	/* TODO: support more architectures */
-	if (!arch__is(args->arch, "x86"))
-		return;
-
-	if (insn->detail == NULL)
-		return;
-
-	for (i = 0; i < insn->detail->x86.op_count; i++) {
-		cs_x86_op *op = &insn->detail->x86.operands[i];
-		u64 orig_addr;
-
-		if (op->type != X86_OP_MEM)
-			continue;
-
-		/* only print RIP-based global symbols for now */
-		if (op->mem.base != X86_REG_RIP)
-			continue;
-
-		/* get the target address */
-		orig_addr = addr + insn->size + op->mem.disp;
-		addr = map__objdump_2mem(map, orig_addr);
-
-		if (dso__kernel(map__dso(map))) {
-			/*
-			 * The kernel maps can be splitted into sections,
-			 * let's find the map first and the search the symbol.
-			 */
-			map = maps__find(map__kmaps(map), addr);
-			if (map == NULL)
-				continue;
-		}
-
-		/* convert it to map-relative address for search */
-		addr = map__map_ip(map, addr);
-
-		sym = map__find_symbol(map, addr);
-		if (sym == NULL)
-			continue;
-
-		if (addr == sym->start) {
-			scnprintf(buf, len, "\t# %"PRIx64" <%s>",
-				  orig_addr, sym->name);
-		} else {
-			scnprintf(buf, len, "\t# %"PRIx64" <%s+%#"PRIx64">",
-				  orig_addr, sym->name, addr - sym->start);
-		}
-		break;
-	}
-}
-
-static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *sym,
-					struct annotate_args *args)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct map *map = args->ms.map;
-	struct dso *dso = map__dso(map);
-	struct nscookie nsc;
-	u64 start = map__rip_2objdump(map, sym->start);
-	u64 end = map__rip_2objdump(map, sym->end);
-	u64 len = end - start;
-	u64 offset;
-	int i, fd, count;
-	bool is_64bit = false;
-	bool needs_cs_close = false;
-	u8 *buf = NULL;
-	struct find_file_offset_data data = {
-		.ip = start,
-	};
-	csh handle;
-	char disasm_buf[512];
-	struct disasm_line *dl;
-	u32 *line;
-	bool disassembler_style = false;
-
-	if (args->options->objdump_path)
-		return -1;
-
-	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
-	fd = open(filename, O_RDONLY);
-	nsinfo__mountns_exit(&nsc);
-	if (fd < 0)
-		return -1;
-
-	if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data,
-			    &is_64bit) == 0)
-		goto err;
-
-	if (!args->options->disassembler_style ||
-			!strcmp(args->options->disassembler_style, "att"))
-		disassembler_style = true;
-
-	if (capstone_init(maps__machine(args->ms.maps), &handle, is_64bit, disassembler_style) < 0)
-		goto err;
-
-	needs_cs_close = true;
-
-	buf = malloc(len);
-	if (buf == NULL)
-		goto err;
-
-	count = pread(fd, buf, len, data.offset);
-	close(fd);
-	fd = -1;
-
-	if ((u64)count != len)
-		goto err;
-
-	line = (u32 *)buf;
-
-	/* add the function address and name */
-	scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:",
-		  start, sym->name);
-
-	args->offset = -1;
-	args->line = disasm_buf;
-	args->line_nr = 0;
-	args->fileloc = NULL;
-	args->ms.sym = sym;
-
-	dl = disasm_line__new(args);
-	if (dl == NULL)
-		goto err;
-
-	annotation_line__add(&dl->al, &notes->src->source);
-
-	/*
-	 * TODO: enable disassm for powerpc
-	 * count = cs_disasm(handle, buf, len, start, len, &insn);
-	 *
-	 * For now, only binary code is saved in disassembled line
-	 * to be used in "type" and "typeoff" sort keys. Each raw code
-	 * is 32 bit instruction. So use "len/4" to get the number of
-	 * entries.
-	 */
-	count = len/4;
-
-	for (i = 0, offset = 0; i < count; i++) {
-		args->offset = offset;
-		sprintf(args->line, "%x", line[i]);
-
-		dl = disasm_line__new(args);
-		if (dl == NULL)
-			break;
-
-		annotation_line__add(&dl->al, &notes->src->source);
-
-		offset += 4;
-	}
-
-	/* It failed in the middle */
-	if (offset != len) {
-		struct list_head *list = &notes->src->source;
-
-		/* Discard all lines and fallback to objdump */
-		while (!list_empty(list)) {
-			dl = list_first_entry(list, struct disasm_line, al.node);
-
-			list_del_init(&dl->al.node);
-			disasm_line__free(dl);
-		}
-		count = -1;
-	}
-
-out:
-	if (needs_cs_close)
-		cs_close(&handle);
-	free(buf);
-	return count < 0 ? count : 0;
-
-err:
-	if (fd >= 0)
-		close(fd);
-	count = -1;
-	goto out;
-}
-
-static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
-					struct annotate_args *args)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct map *map = args->ms.map;
-	u64 start = map__rip_2objdump(map, sym->start);
-	u64 len;
-	u64 offset;
-	int i, count, free_count;
-	bool is_64bit = false;
-	bool needs_cs_close = false;
-	u8 *buf = NULL;
-	csh handle;
-	cs_insn *insn = NULL;
-	char disasm_buf[512];
-	struct disasm_line *dl;
-
-	if (args->options->objdump_path)
-		return -1;
-
-	buf = read_symbol(filename, map, sym, &len, &is_64bit);
-	if (buf == NULL)
-		return -1;
-
-	/* add the function address and name */
-	scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:",
-		  start, sym->name);
-
-	args->offset = -1;
-	args->line = disasm_buf;
-	args->line_nr = 0;
-	args->fileloc = NULL;
-	args->ms.sym = sym;
-
-	dl = disasm_line__new(args);
-	if (dl == NULL)
-		goto err;
-
-	annotation_line__add(&dl->al, &notes->src->source);
-
-	if (open_capstone_handle(args, is_64bit, &handle) < 0)
-		goto err;
-
-	needs_cs_close = true;
-
-	free_count = count = cs_disasm(handle, buf, len, start, len, &insn);
-	for (i = 0, offset = 0; i < count; i++) {
-		int printed;
-
-		printed = scnprintf(disasm_buf, sizeof(disasm_buf),
-				    "       %-7s %s",
-				    insn[i].mnemonic, insn[i].op_str);
-		print_capstone_detail(&insn[i], disasm_buf + printed,
-				      sizeof(disasm_buf) - printed, args,
-				      start + offset);
-
-		args->offset = offset;
-		args->line = disasm_buf;
-
-		dl = disasm_line__new(args);
-		if (dl == NULL)
-			goto err;
-
-		annotation_line__add(&dl->al, &notes->src->source);
-
-		offset += insn[i].size;
-	}
-
-	/* It failed in the middle: probably due to unknown instructions */
-	if (offset != len) {
-		struct list_head *list = &notes->src->source;
-
-		/* Discard all lines and fallback to objdump */
-		while (!list_empty(list)) {
-			dl = list_first_entry(list, struct disasm_line, al.node);
-
-			list_del_init(&dl->al.node);
-			disasm_line__free(dl);
-		}
-		count = -1;
-	}
-
-out:
-	if (needs_cs_close) {
-		cs_close(&handle);
-		if (free_count > 0)
-			cs_free(insn, free_count);
-	}
-	free(buf);
-	return count < 0 ? count : 0;
-
-err:
-	if (needs_cs_close) {
-		struct disasm_line *tmp;
-
-		/*
-		 * It probably failed in the middle of the above loop.
-		 * Release any resources it might add.
-		 */
-		list_for_each_entry_safe(dl, tmp, &notes->src->source, al.node) {
-			list_del(&dl->al.node);
-			disasm_line__free(dl);
-		}
-	}
-	count = -1;
-	goto out;
-}
-#else // HAVE_LIBCAPSTONE_SUPPORT
-static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
-					struct annotate_args *args __maybe_unused)
-{
-	symbol__disassembler_missing("capstone", filename, sym);
-	return -1;
-}
-
-static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *sym,
-						struct annotate_args *args __maybe_unused)
-{
-	symbol__disassembler_missing("capstone powerpc", filename, sym);
-	return -1;
-}
-#endif // HAVE_LIBCAPSTONE_SUPPORT
-
 static int symbol__disassemble_raw(char *filename, struct symbol *sym,
 					struct annotate_args *args)
 {
@@ -2014,10 +1667,11 @@ err:
 	return ret;
 }
 #else // HAVE_LIBLLVM_SUPPORT
-static int symbol__disassemble_llvm(char *filename, struct symbol *sym,
+static int symbol__disassemble_llvm(const char *filename, struct symbol *sym,
 				    struct annotate_args *args __maybe_unused)
 {
-	symbol__disassembler_missing("LLVM", filename, sym);
+	pr_debug("The LLVM disassembler isn't linked in for %s in %s\n",
+		 sym->name, filename);
 	return -1;
 }
 #endif // HAVE_LIBLLVM_SUPPORT