perf report: Support LLVM for addr2line()

In addition to the existing support for libbfd and calling out to
an external addr2line command, add support for using libllvm directly.

This is both faster than libbfd, and can be enabled in distro builds
(the LLVM license has an explicit provision for GPLv2 compatibility).

Thus, it is set as the primary choice if available.

As an example, running 'perf report' on a medium-size profile with
DWARF-based backtraces took 58 seconds with LLVM, 78 seconds with
libbfd, 153 seconds with external llvm-addr2line, and I got tired and
aborted the test after waiting for 55 minutes with external bfd
addr2line (which is the default for perf as compiled by distributions
today).

Evidently, for this case, the bfd addr2line process needs 18 seconds (on
a 5.2 GHz Zen 3) to load the .debug ELF in question, hits the 1-second
timeout and gets killed during initialization, getting restarted anew
every time. Having an in-process addr2line makes this much more robust.

As future extensions, libllvm can be used in many other places where
we currently use libbfd or other libraries:

 - Symbol enumeration (in particular, for PE binaries).
 - Demangling (including non-Itanium demangling, e.g. Microsoft
   or Rust).
 - Disassembling (perf annotate).

However, these are much less pressing; most people don't profile PE
binaries, and perf has non-bfd paths for ELF. The same with demangling;
the default _cxa_demangle path works fine for most users, and while bfd
objdump can be slow on large binaries, it is possible to use
--objdump=llvm-objdump to get the speed benefits.  (It appears
LLVM-based demangling is very simple, should we want that.)

Tested with LLVM 14, 15, 16, 18 and 19. For some reason, LLVM 12 was not
correctly detected using feature_check, and thus was not tested.

Committer notes:

 Added the name and a __maybe_unused to address:

   1    13.50 almalinux:8                   : FAIL gcc version 8.5.0 20210514 (Red Hat 8.5.0-22) (GCC)
    util/srcline.c: In function 'dso__free_a2l':
    util/srcline.c:184:20: error: parameter name omitted
     void dso__free_a2l(struct dso *)
                        ^~~~~~~~~~~~
    make[3]: *** [/git/perf-6.11.0-rc3/tools/build/Makefile.build:158: util] Error 2
Signed-off-by: Steinar H. Gunderson <sesse@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20240803152008.2818485-1-sesse@google.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/build/Makefile.feature

@@ -136,6 +136,7 @@ FEATURE_DISPLAY ?=              \
          libunwind              \
          libdw-dwarf-unwind     \
          libcapstone            \
+         llvm                   \
          zlib                   \
          lzma                   \
          get_cpuid              \

tools/perf/Makefile.config

@@ -980,6 +980,23 @@ ifdef BUILD_NONDISTRO
   endif
 endif
 
+ifndef NO_LIBLLVM
+  $(call feature_check,llvm)
+  ifeq ($(feature-llvm), 1)
+    CFLAGS += -DHAVE_LIBLLVM_SUPPORT
+    CFLAGS += $(shell $(LLVM_CONFIG) --cflags)
+    CXXFLAGS += -DHAVE_LIBLLVM_SUPPORT
+    CXXFLAGS += $(shell $(LLVM_CONFIG) --cxxflags)
+    LIBLLVM = $(shell $(LLVM_CONFIG) --libs all) $(shell $(LLVM_CONFIG) --system-libs)
+    EXTLIBS += -L$(shell $(LLVM_CONFIG) --libdir) $(LIBLLVM)
+    EXTLIBS += -lstdc++
+    $(call detected,CONFIG_LIBLLVM)
+  else
+    $(warning No libllvm found, slower source file resolution, please install llvm-devel/llvm-dev)
+    NO_LIBLLVM := 1
+  endif
+endif
+
 ifndef NO_DEMANGLE
   $(call feature_check,cxa-demangle)
   ifeq ($(feature-cxa-demangle), 1)

tools/perf/builtin-version.c

@@ -65,6 +65,7 @@ static void library_status(void)
 	STATUS(HAVE_LIBBFD_SUPPORT, libbfd);
 	STATUS(HAVE_DEBUGINFOD_SUPPORT, debuginfod);
 	STATUS(HAVE_LIBELF_SUPPORT, libelf);
+	STATUS(HAVE_LIBLLVM_SUPPORT, libllvm);
 	STATUS(HAVE_LIBNUMA_SUPPORT, libnuma);
 	STATUS(HAVE_LIBNUMA_SUPPORT, numa_num_possible_cpus);
 	STATUS(HAVE_LIBPERL_SUPPORT, libperl);

tools/perf/tests/make

@@ -93,6 +93,7 @@ make_no_libbpf	    := NO_LIBBPF=1
 make_libbpf_dynamic := LIBBPF_DYNAMIC=1
 make_no_libbpf_DEBUG := NO_LIBBPF=1 DEBUG=1
 make_no_libcrypto   := NO_LIBCRYPTO=1
+make_no_libllvm     := NO_LIBLLVM=1
 make_with_babeltrace:= LIBBABELTRACE=1
 make_with_coresight := CORESIGHT=1
 make_no_sdt	    := NO_SDT=1
@@ -163,6 +164,7 @@ run += make_no_auxtrace
 run += make_no_libbpf
 run += make_no_libbpf_DEBUG
 run += make_no_libcrypto
+run += make_no_libllvm
 run += make_no_sdt
 run += make_no_syscall_tbl
 run += make_with_babeltrace

tools/perf/util/Build

@@ -229,6 +229,7 @@ perf-util-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o
 perf-util-y += demangle-ocaml.o
 perf-util-y += demangle-java.o
 perf-util-y += demangle-rust.o
+perf-util-$(CONFIG_LIBLLVM) += llvm-c-helpers.o
 
 ifdef CONFIG_JITDUMP
 perf-util-$(CONFIG_LIBELF) += jitdump.o

tools/perf/util/llvm-c-helpers.cpp

+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Must come before the linux/compiler.h include, which defines several
+ * macros (e.g. noinline) that conflict with compiler builtins used
+ * by LLVM.
+ */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wunused-parameter"  /* Needed for LLVM <= 15 */
+#include <llvm/DebugInfo/Symbolize/Symbolize.h>
+#pragma GCC diagnostic pop
+
+#include <stdio.h>
+#include <sys/types.h>
+#include <linux/compiler.h>
+extern "C" {
+#include <linux/zalloc.h>
+}
+#include "symbol_conf.h"
+#include "llvm-c-helpers.h"
+
+using namespace llvm;
+using llvm::symbolize::LLVMSymbolizer;
+
+/*
+ * Allocate a static LLVMSymbolizer, which will live to the end of the program.
+ * Unlike the bfd paths, LLVMSymbolizer has its own cache, so we do not need
+ * to store anything in the dso struct.
+ */
+static LLVMSymbolizer *get_symbolizer()
+{
+	static LLVMSymbolizer *instance = nullptr;
+	if (instance == nullptr) {
+		LLVMSymbolizer::Options opts;
+		/*
+		 * LLVM sometimes demangles slightly different from the rest
+		 * of the code, and this mismatch can cause new_inline_sym()
+		 * to get confused and mark non-inline symbol as inlined
+		 * (since the name does not properly match up with base_sym).
+		 * Thus, disable the demangling and let the rest of the code
+		 * handle it.
+		 */
+		opts.Demangle = false;
+		instance = new LLVMSymbolizer(opts);
+	}
+	return instance;
+}
+
+/* Returns 0 on error, 1 on success. */
+static int extract_file_and_line(const DILineInfo &line_info, char **file,
+				 unsigned int *line)
+{
+	if (file) {
+		if (line_info.FileName == "<invalid>") {
+			/* Match the convention of libbfd. */
+			*file = nullptr;
+		} else {
+			/* The caller expects to get something it can free(). */
+			*file = strdup(line_info.FileName.c_str());
+			if (*file == nullptr)
+				return 0;
+		}
+	}
+	if (line)
+		*line = line_info.Line;
+	return 1;
+}
+
+extern "C"
+int llvm_addr2line(const char *dso_name, u64 addr,
+		   char **file, unsigned int *line,
+		   bool unwind_inlines,
+		   llvm_a2l_frame **inline_frames)
+{
+	LLVMSymbolizer *symbolizer = get_symbolizer();
+	object::SectionedAddress sectioned_addr = {
+		addr,
+		object::SectionedAddress::UndefSection
+	};
+
+	if (unwind_inlines) {
+		Expected<DIInliningInfo> res_or_err =
+			symbolizer->symbolizeInlinedCode(dso_name,
+							 sectioned_addr);
+		if (!res_or_err)
+			return 0;
+		unsigned num_frames = res_or_err->getNumberOfFrames();
+		if (num_frames == 0)
+			return 0;
+
+		if (extract_file_and_line(res_or_err->getFrame(0),
+					  file, line) == 0)
+			return 0;
+
+		*inline_frames = (llvm_a2l_frame *)calloc(
+			num_frames, sizeof(**inline_frames));
+		if (*inline_frames == nullptr)
+			return 0;
+
+		for (unsigned i = 0; i < num_frames; ++i) {
+			const DILineInfo &src = res_or_err->getFrame(i);
+
+			llvm_a2l_frame &dst = (*inline_frames)[i];
+			if (src.FileName == "<invalid>")
+				/* Match the convention of libbfd. */
+				dst.filename = nullptr;
+			else
+				dst.filename = strdup(src.FileName.c_str());
+			dst.funcname = strdup(src.FunctionName.c_str());
+			dst.line = src.Line;
+
+			if (dst.filename == nullptr ||
+			    dst.funcname == nullptr) {
+				for (unsigned j = 0; j <= i; ++j) {
+					zfree(&(*inline_frames)[j].filename);
+					zfree(&(*inline_frames)[j].funcname);
+				}
+				zfree(inline_frames);
+				return 0;
+			}
+		}
+
+		return num_frames;
+	} else {
+		if (inline_frames)
+			*inline_frames = nullptr;
+
+		Expected<DILineInfo> res_or_err =
+			symbolizer->symbolizeCode(dso_name, sectioned_addr);
+		if (!res_or_err)
+			return 0;
+		return extract_file_and_line(*res_or_err, file, line);
+	}
+}

tools/perf/util/llvm-c-helpers.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_LLVM_C_HELPERS
+#define __PERF_LLVM_C_HELPERS 1
+
+/*
+ * Helpers to call into LLVM C++ code from C, for the parts that do not have
+ * C APIs.
+ */
+
+#include <linux/compiler.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+struct llvm_a2l_frame {
+  char* filename;
+  char* funcname;
+  unsigned int line;
+};
+
+/*
+ * Implement addr2line() using libLLVM. LLVM is a C++ API, and
+ * many of the linux/ headers cannot be included in a C++ compile unit,
+ * so we need to make a little bridge code here. llvm_addr2line() will
+ * convert the inline frame information from LLVM's internal structures
+ * and put them into a flat array given in inline_frames. The caller
+ * is then responsible for taking that array and convert it into perf's
+ * regular inline frame structures (which depend on e.g. struct list_head).
+ *
+ * If the address could not be resolved, or an error occurred (e.g. OOM),
+ * returns 0. Otherwise, returns the number of inline frames (which means 1
+ * if the address was not part of an inlined function). If unwind_inlines
+ * is set and the return code is nonzero, inline_frames will be set to
+ * a newly allocated array with that length. The caller is then responsible
+ * for freeing both the strings and the array itself.
+ */
+int llvm_addr2line(const char* dso_name,
+                   u64 addr,
+                   char** file,
+                   unsigned int* line,
+                   bool unwind_inlines,
+                   struct llvm_a2l_frame** inline_frames);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __PERF_LLVM_C_HELPERS */

tools/perf/util/srcline.c

@@ -6,6 +6,7 @@
 #include <string.h>
 #include <sys/types.h>
 
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
@@ -16,6 +17,9 @@
 #include "util/debug.h"
 #include "util/callchain.h"
 #include "util/symbol_conf.h"
+#ifdef HAVE_LIBLLVM_SUPPORT
+#include "util/llvm-c-helpers.h"
+#endif
 #include "srcline.h"
 #include "string2.h"
 #include "symbol.h"
@@ -130,7 +134,60 @@ static struct symbol *new_inline_sym(struct dso *dso,
 
 #define MAX_INLINE_NEST 1024
 
-#ifdef HAVE_LIBBFD_SUPPORT
+#ifdef HAVE_LIBLLVM_SUPPORT
+
+static void free_llvm_inline_frames(struct llvm_a2l_frame *inline_frames,
+				    int num_frames)
+{
+	if (inline_frames != NULL) {
+		for (int i = 0; i < num_frames; ++i) {
+			zfree(&inline_frames[i].filename);
+			zfree(&inline_frames[i].funcname);
+		}
+		zfree(&inline_frames);
+	}
+}
+
+static int addr2line(const char *dso_name, u64 addr,
+		     char **file, unsigned int *line, struct dso *dso,
+		     bool unwind_inlines, struct inline_node *node,
+		     struct symbol *sym)
+{
+	struct llvm_a2l_frame *inline_frames = NULL;
+	int num_frames = llvm_addr2line(dso_name, addr, file, line,
+					node && unwind_inlines, &inline_frames);
+
+	if (num_frames == 0 || !inline_frames) {
+		/* Error, or we didn't want inlines. */
+		return num_frames;
+	}
+
+	for (int i = 0; i < num_frames; ++i) {
+		struct symbol *inline_sym =
+			new_inline_sym(dso, sym, inline_frames[i].funcname);
+		char *srcline = NULL;
+
+		if (inline_frames[i].filename) {
+			srcline =
+				srcline_from_fileline(inline_frames[i].filename,
+						      inline_frames[i].line);
+		}
+		if (inline_list__append(inline_sym, srcline, node) != 0) {
+			free_llvm_inline_frames(inline_frames, num_frames);
+			return 0;
+		}
+	}
+	free_llvm_inline_frames(inline_frames, num_frames);
+
+	return num_frames;
+}
+
+void dso__free_a2l(struct dso *dso __maybe_unused)
+{
+	/* Nothing to free. */
+}
+
+#elif defined(HAVE_LIBBFD_SUPPORT)
 
 /*
  * Implement addr2line using libbfd.