perf annotate: LLVM-based disassembler

Support using LLVM as a disassembler method, allowing helperless
annotation in non-distro builds. (It is also much faster than
using libbfd or bfd objdump on binaries with a lot of debug
information.)

This is nearly identical to the output of llvm-objdump; there are
some very rare whitespace differences, some minor changes to demangling
(since we use perf's regular demangling and not LLVM's own) and
the occasional case where llvm-objdump makes a different choice
when multiple symbols share the same address.

It should work across all of LLVM's supported architectures, although
I've only tested 64-bit x86, and finding the right triple from perf's
idea of machine architecture can sometimes be a bit tricky. Ideally, we
should have some way of finding the triplet just from the file itself.

Committer notes:

Address this on 32-bit systems by using PRIu64 from inttypes.h

     3    17.58 almalinux:9-i386              : FAIL gcc version 11.4.1 20231218 (Red Hat 11.4.1-3) (GCC)
      util/llvm-c-helpers.cpp: In function ‘char* make_symbol_relative_string(dso*, const char*, u64, u64)’:
      util/llvm-c-helpers.cpp:150:52: error: format ‘%lx’ expects argument of type ‘long unsigned int’, but argument 5 has type ‘u64’ {aka
  +‘long long unsigned int’} [-Werror=format=]
        150 |                 snprintf(buf, sizeof(buf), "%s+0x%lx",
            |                                                  ~~^
            |                                                    |
            |                                                    long unsigned int
            |                                                  %llx
        151 |                          demangled ? demangled : sym_name, addr - base_addr);
            |                                                            ~~~~~~~~~~~~~~~~
            |                                                                 |
            |                                                                 u64 {aka long long unsigned int}
      cc1plus: all warnings being treated as errors

Signed-off-by: Steinar H. Gunderson <sesse@google.com>
Cc: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20240803152008.2818485-3-sesse@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 63 insertions, 0 deletions

diff --git a/tools/perf/util/llvm-c-helpers.cpp b/tools/perf/util/llvm-c-helpers.cpp
index 3cc967ec6f28..663bcaba2041 100644
--- a/tools/perf/util/llvm-c-helpers.cpp
+++ b/tools/perf/util/llvm-c-helpers.cpp
@@ -8,8 +8,10 @@
 #pragma GCC diagnostic push
 #pragma GCC diagnostic ignored "-Wunused-parameter"  /* Needed for LLVM <= 15 */
 #include <llvm/DebugInfo/Symbolize/Symbolize.h>
+#include <llvm/Support/TargetSelect.h>
 #pragma GCC diagnostic pop
 
+#include <inttypes.h>
 #include <stdio.h>
 #include <sys/types.h>
 #include <linux/compiler.h>
@@ -19,6 +21,9 @@ extern "C" {
 #include "symbol_conf.h"
 #include "llvm-c-helpers.h"
 
+extern "C"
+char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name);
+
 using namespace llvm;
 using llvm::symbolize::LLVMSymbolizer;
 
@@ -132,3 +137,61 @@ int llvm_addr2line(const char *dso_name, u64 addr,
 		return extract_file_and_line(*res_or_err, file, line);
 	}
 }
+
+static char *
+make_symbol_relative_string(struct dso *dso, const char *sym_name,
+			    u64 addr, u64 base_addr)
+{
+	if (!strcmp(sym_name, "<invalid>"))
+		return NULL;
+
+	char *demangled = dso__demangle_sym(dso, 0, sym_name);
+	if (base_addr && base_addr != addr) {
+		char buf[256];
+		snprintf(buf, sizeof(buf), "%s+0x%" PRIx64,
+			 demangled ? demangled : sym_name, addr - base_addr);
+		free(demangled);
+		return strdup(buf);
+	} else {
+		if (demangled)
+			return demangled;
+		else
+			return strdup(sym_name);
+	}
+}
+
+extern "C"
+char *llvm_name_for_code(struct dso *dso, const char *dso_name, u64 addr)
+{
+	LLVMSymbolizer *symbolizer = get_symbolizer();
+	object::SectionedAddress sectioned_addr = {
+		addr,
+		object::SectionedAddress::UndefSection
+	};
+	Expected<DILineInfo> res_or_err =
+		symbolizer->symbolizeCode(dso_name, sectioned_addr);
+	if (!res_or_err) {
+		return NULL;
+	}
+	return make_symbol_relative_string(
+		dso, res_or_err->FunctionName.c_str(),
+		addr, res_or_err->StartAddress ? *res_or_err->StartAddress : 0);
+}
+
+extern "C"
+char *llvm_name_for_data(struct dso *dso, const char *dso_name, u64 addr)
+{
+	LLVMSymbolizer *symbolizer = get_symbolizer();
+	object::SectionedAddress sectioned_addr = {
+		addr,
+		object::SectionedAddress::UndefSection
+	};
+	Expected<DIGlobal> res_or_err =
+		symbolizer->symbolizeData(dso_name, sectioned_addr);
+	if (!res_or_err) {
+		return NULL;
+	}
+	return make_symbol_relative_string(
+		dso, res_or_err->Name.c_str(),
+		addr, res_or_err->Start);
+}