https://github.com/jasonmolenda created
https://github.com/llvm/llvm-project/pull/129967
We have a binary image on Darwin that has no code, only metadata. It has a
large symbol table with many external symbol names that will not be needed in
the debugger. And it is possible to not have this binary on the debugger
system - so lldb must read all of the symbol names out of memory, one at a
time, which can be quite slow.
We're adding a section __TEXT,__lldb_no_nlist, to this binary to indicate that
lldb should not read the nlist symbols for it when we are reading out of
memory. If lldb is run with an on-disk version of the binary, we will load the
symbol table as we normally would, there's no benefit to handling this binary
differently.
I added a test where I create a dylib with this specially named section, launch
the process. The main binary deletes the dylib from the disk so lldb is forced
to read it out of memory. lldb attaches to the binary, confirms that the dylib
is present in the process and is a memory Module. If the binary is not
present, or lldb found the on-disk copy because it hasn't been deleted yet, we
delete the target, flush the Debugger's module cache, sleep and retry, up to
ten times. I create the specially named section by compiling an assembly file
that puts a byte in the section which makes for a bit of a messy Makefile (the
pre-canned actions to build a dylib don't quite handle this case) but I don't
think it's much of a problem. This is a purely skipUnlessDarwin test case.
rdar://146167816
>From 6e258eb09b13776fc393a161225438baa92e5f87 Mon Sep 17 00:00:00 2001
From: Jason Molenda <jmole...@apple.com>
Date: Wed, 5 Mar 2025 17:27:20 -0800
Subject: [PATCH] [lldb][Mach-O] Don't read symbol table of specially marked
binary
We have a binary image on Darwin that has no code, only metadata.
It has a large symbol table with many external symbol names that
will not be needed in the debugger. And it is possible to not have
this binary on the debugger system - so lldb must read all of the
symbol names out of memory, one at a time, which can be quite slow.
We're adding a section __TEXT,__lldb_no_nlist, to this binary to
indicate that lldb should not read the nlist symbols for it when
we are reading out of memory. If lldb is run with an on-disk version
of the binary, we will load the symbol table as we normally would,
there's no benefit to handling this binary differently.
I added a test where I create a dylib with this specially named
section, launch the process. The main binary deletes the dylib
from the disk so lldb is forced to read it out of memory. lldb
attaches to the binary, confirms that the dylib is present in
the process and is a memory Module. If the binary is not present,
or lldb found the on-disk copy because it hasn't been deleted yet,
we delete the target, flush the Debugger's module cache, sleep and
retry, up to ten times. I create the specially named section by
compiling an assembly file that puts a byte in the section which
makes for a bit of a messy Makefile (the pre-canned actions to
build a dylib don't quite handle this case) but I don't think it's
much of a problem. This is a purely skipUnlessDarwin test case.
rdar://146167816
---
.../ObjectFile/Mach-O/ObjectFileMachO.cpp | 68 +++++++++++-------
.../ObjectFile/Mach-O/ObjectFileMachO.h | 1 +
.../macosx/no-nlist-memory-module/Makefile | 15 ++++
.../TestNoNlistsDylib.py | 70 +++++++++++++++++++
.../API/macosx/no-nlist-memory-module/main.c | 37 ++++++++++
.../no-nlist-memory-module/no-nlist-sect.s | 3 +
.../macosx/no-nlist-memory-module/no-nlists.c | 3 +
7 files changed, 173 insertions(+), 24 deletions(-)
create mode 100644 lldb/test/API/macosx/no-nlist-memory-module/Makefile
create mode 100644
lldb/test/API/macosx/no-nlist-memory-module/TestNoNlistsDylib.py
create mode 100644 lldb/test/API/macosx/no-nlist-memory-module/main.c
create mode 100644 lldb/test/API/macosx/no-nlist-memory-module/no-nlist-sect.s
create mode 100644 lldb/test/API/macosx/no-nlist-memory-module/no-nlists.c
diff --git a/lldb/source/Plugins/ObjectFile/Mach-O/ObjectFileMachO.cpp
b/lldb/source/Plugins/ObjectFile/Mach-O/ObjectFileMachO.cpp
index a19322ff1e263..f31b56b9f81e6 100644
--- a/lldb/source/Plugins/ObjectFile/Mach-O/ObjectFileMachO.cpp
+++ b/lldb/source/Plugins/ObjectFile/Mach-O/ObjectFileMachO.cpp
@@ -918,6 +918,11 @@ ConstString ObjectFileMachO::GetSectionNameEHFrame() {
return g_section_name_eh_frame;
}
+ConstString ObjectFileMachO::GetSectionNameLLDBNoNlist() {
+ static ConstString g_section_name_lldb_no_nlist("__lldb_no_nlist");
+ return g_section_name_lldb_no_nlist;
+}
+
bool ObjectFileMachO::MagicBytesMatch(DataBufferSP data_sp,
lldb::addr_t data_offset,
lldb::addr_t data_length) {
@@ -2394,8 +2399,39 @@ void ObjectFileMachO::ParseSymtab(Symtab &symtab) {
uint32_t memory_module_load_level = eMemoryModuleLoadLevelComplete;
bool is_shared_cache_image = IsSharedCacheBinary();
bool is_local_shared_cache_image = is_shared_cache_image && !IsInMemory();
+
+ ConstString g_segment_name_TEXT = GetSegmentNameTEXT();
+ ConstString g_segment_name_DATA = GetSegmentNameDATA();
+ ConstString g_segment_name_DATA_DIRTY = GetSegmentNameDATA_DIRTY();
+ ConstString g_segment_name_DATA_CONST = GetSegmentNameDATA_CONST();
+ ConstString g_segment_name_OBJC = GetSegmentNameOBJC();
+ ConstString g_section_name_eh_frame = GetSectionNameEHFrame();
+ ConstString g_section_name_lldb_no_nlist = GetSectionNameLLDBNoNlist();
+ SectionSP text_section_sp(
+ section_list->FindSectionByName(g_segment_name_TEXT));
+ SectionSP data_section_sp(
+ section_list->FindSectionByName(g_segment_name_DATA));
SectionSP linkedit_section_sp(
section_list->FindSectionByName(GetSegmentNameLINKEDIT()));
+ SectionSP data_dirty_section_sp(
+ section_list->FindSectionByName(g_segment_name_DATA_DIRTY));
+ SectionSP data_const_section_sp(
+ section_list->FindSectionByName(g_segment_name_DATA_CONST));
+ SectionSP objc_section_sp(
+ section_list->FindSectionByName(g_segment_name_OBJC));
+ SectionSP eh_frame_section_sp;
+ SectionSP lldb_no_nlist_section_sp;
+ if (text_section_sp.get()) {
+ eh_frame_section_sp = text_section_sp->GetChildren().FindSectionByName(
+ g_section_name_eh_frame);
+ lldb_no_nlist_section_sp =
text_section_sp->GetChildren().FindSectionByName(
+ g_section_name_lldb_no_nlist);
+ } else {
+ eh_frame_section_sp =
+ section_list->FindSectionByName(g_section_name_eh_frame);
+ lldb_no_nlist_section_sp =
+ section_list->FindSectionByName(g_section_name_lldb_no_nlist);
+ }
if (process && m_header.filetype != llvm::MachO::MH_OBJECT &&
!is_local_shared_cache_image) {
@@ -2403,6 +2439,14 @@ void ObjectFileMachO::ParseSymtab(Symtab &symtab) {
memory_module_load_level = target.GetMemoryModuleLoadLevel();
+ // If __TEXT,__lldb_no_nlist section is present in this binary,
+ // and we're reading it out of memory, do not read any of the
+ // nlist entries. They are not needed in lldb and it may be
+ // expensive to load these. This is to handle a dylib consisting
+ // of only metadata, no code, but it has many nlist entries.
+ if (lldb_no_nlist_section_sp)
+ memory_module_load_level = eMemoryModuleLoadLevelMinimal;
+
// Reading mach file from memory in a process or core file...
if (linkedit_section_sp) {
@@ -2526,30 +2570,6 @@ void ObjectFileMachO::ParseSymtab(Symtab &symtab) {
const bool have_strtab_data = strtab_data.GetByteSize() > 0;
- ConstString g_segment_name_TEXT = GetSegmentNameTEXT();
- ConstString g_segment_name_DATA = GetSegmentNameDATA();
- ConstString g_segment_name_DATA_DIRTY = GetSegmentNameDATA_DIRTY();
- ConstString g_segment_name_DATA_CONST = GetSegmentNameDATA_CONST();
- ConstString g_segment_name_OBJC = GetSegmentNameOBJC();
- ConstString g_section_name_eh_frame = GetSectionNameEHFrame();
- SectionSP text_section_sp(
- section_list->FindSectionByName(g_segment_name_TEXT));
- SectionSP data_section_sp(
- section_list->FindSectionByName(g_segment_name_DATA));
- SectionSP data_dirty_section_sp(
- section_list->FindSectionByName(g_segment_name_DATA_DIRTY));
- SectionSP data_const_section_sp(
- section_list->FindSectionByName(g_segment_name_DATA_CONST));
- SectionSP objc_section_sp(
- section_list->FindSectionByName(g_segment_name_OBJC));
- SectionSP eh_frame_section_sp;
- if (text_section_sp.get())
- eh_frame_section_sp = text_section_sp->GetChildren().FindSectionByName(
- g_section_name_eh_frame);
- else
- eh_frame_section_sp =
- section_list->FindSectionByName(g_section_name_eh_frame);
-
const bool is_arm = (m_header.cputype == llvm::MachO::CPU_TYPE_ARM);
const bool always_thumb = GetArchitecture().IsAlwaysThumbInstructions();
diff --git a/lldb/source/Plugins/ObjectFile/Mach-O/ObjectFileMachO.h
b/lldb/source/Plugins/ObjectFile/Mach-O/ObjectFileMachO.h
index 27b2078b5a3fc..7f67f5e04f1d6 100644
--- a/lldb/source/Plugins/ObjectFile/Mach-O/ObjectFileMachO.h
+++ b/lldb/source/Plugins/ObjectFile/Mach-O/ObjectFileMachO.h
@@ -286,6 +286,7 @@ class ObjectFileMachO : public lldb_private::ObjectFile {
static lldb_private::ConstString GetSegmentNameDWARF();
static lldb_private::ConstString GetSegmentNameLLVM_COV();
static lldb_private::ConstString GetSectionNameEHFrame();
+ static lldb_private::ConstString GetSectionNameLLDBNoNlist();
llvm::MachO::dysymtab_command m_dysymtab;
std::vector<llvm::MachO::section_64> m_mach_sections;
diff --git a/lldb/test/API/macosx/no-nlist-memory-module/Makefile
b/lldb/test/API/macosx/no-nlist-memory-module/Makefile
new file mode 100644
index 0000000000000..cb4f9968112cd
--- /dev/null
+++ b/lldb/test/API/macosx/no-nlist-memory-module/Makefile
@@ -0,0 +1,15 @@
+C_SOURCES := main.c
+LD_EXTRAS = -Wl,-rpath "-Wl,$(shell pwd)" -L. -lno-nlists
+
+.PHONY: build-libno-nlists
+all: build-libno-nlists a.out
+
+include Makefile.rules
+
+build-libno-nlists: no-nlists.c no-nlist-sect.s
+ $(CC) $(CFLAGS) -c -o no-nlists.o $(<D)/no-nlists.c
+ $(CC) $(CFLAGS) -c -o no-nlist-sect.o $(<D)/no-nlist-sect.s
+ $(LD) -dynamiclib -o libno-nlists.dylib no-nlists.o no-nlist-sect.o
-install_name "@executable_path/libno-nlists.dylib"
+
+clean::
+ rm -rf no-nlists.o no-nlist-sect.o main.o main.s a.out a.out.dSYM
libno-nlists.dylib libno-nlists.dylib.dSYM
diff --git a/lldb/test/API/macosx/no-nlist-memory-module/TestNoNlistsDylib.py
b/lldb/test/API/macosx/no-nlist-memory-module/TestNoNlistsDylib.py
new file mode 100644
index 0000000000000..73644a5f00531
--- /dev/null
+++ b/lldb/test/API/macosx/no-nlist-memory-module/TestNoNlistsDylib.py
@@ -0,0 +1,70 @@
+"""
+Test that we read don't read the nlist symbols for a specially marked dylib
+when read from memory.
+"""
+
+import lldb
+from lldbsuite.test.decorators import *
+from lldbsuite.test.lldbtest import *
+from lldbsuite.test import lldbutil
+from time import sleep
+
+
+class NoNlistsTestCase(TestBase):
+ NO_DEBUG_INFO_TESTCASE = True
+
+ @skipIfRemote
+ @skipUnlessDarwin
+ def test_no_nlist_symbols(self):
+ self.build()
+
+ exe = os.path.realpath(self.getBuildArtifact("a.out"))
+
+ popen = self.spawnSubprocess(exe)
+ pid = popen.pid
+
+ self.dbg.SetAsync(False)
+
+ m = lldb.SBModule()
+ target = lldb.SBTarget()
+ process = lldb.SBProcess()
+ reattach_count = 0
+
+ # Attach to the process, see if we have a memory module
+ # for libno-nlists.dylib. If not, detach, delete the
+ # Target, and flush the orphaned modules from the Debugger
+ # so we don't hold on to a reference of the on-disk binary.
+
+ # If we haven't succeeded after ten attemps of attaching and
+ # detaching, fail the test.
+ while not m.IsValid() or m.IsFileBacked():
+ if process.IsValid():
+ process.Detach()
+ self.dbg.DeleteTarget(target)
+ self.dbg.MemoryPressureDetected()
+ time.sleep(2)
+
+ self.runCmd("process attach -p " + str(pid))
+ target = self.dbg.GetSelectedTarget()
+ process = target.GetProcess()
+ m = target.FindModule(lldb.SBFileSpec("libno-nlists.dylib"))
+
+ reattach_count = reattach_count + 1
+ if reattach_count > 10:
+ break
+
+ self.assertTrue(process, PROCESS_IS_VALID)
+
+ # Test that we found libno-nlists.dylib, it is a memory
+ # module, and that it has no symbols.
+ self.assertTrue(m.IsValid())
+ self.assertFalse(m.IsFileBacked())
+ self.assertEqual(m.GetNumSymbols(), 0)
+
+ # And as a sanity check, get the main binary's module,
+ # test that it is file backed and that it has more than
+ # zero symbols.
+ m = target.FindModule(lldb.SBFileSpec("a.out"))
+ self.assertTrue(m.IsValid())
+ self.assertTrue(m.IsFileBacked())
+ self.assertGreater(m.GetNumSymbols(), 0)
diff --git a/lldb/test/API/macosx/no-nlist-memory-module/main.c
b/lldb/test/API/macosx/no-nlist-memory-module/main.c
new file mode 100644
index 0000000000000..fb1451ccc99d1
--- /dev/null
+++ b/lldb/test/API/macosx/no-nlist-memory-module/main.c
@@ -0,0 +1,37 @@
+#include <libgen.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/param.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+int get_return_value();
+
+int main(int argc, char **argv) {
+
+ // Remove libno-nlists.dylib that we are linked against.
+ char executable_path[PATH_MAX];
+ realpath(argv[0], executable_path);
+ executable_path[PATH_MAX - 1] = '\0';
+
+ char *dir = dirname(executable_path);
+ char dylib_path[PATH_MAX];
+ snprintf(dylib_path, PATH_MAX, "%s/%s", dir, "libno-nlists.dylib");
+ dylib_path[PATH_MAX - 1] = '\0';
+ struct stat sb;
+ if (stat(dylib_path, &sb) == -1) {
+ printf("Could not find dylib %s to remove it\n", dylib_path);
+ exit(1);
+ }
+ if (unlink(dylib_path) == -1) {
+ printf("Could not remove dylib %s\n", dylib_path);
+ exit(2);
+ }
+
+ // This sleep will exit as soon as lldb attaches
+ // and interrupts it.
+ sleep(200);
+
+ int retval = get_return_value();
+ return retval;
+}
diff --git a/lldb/test/API/macosx/no-nlist-memory-module/no-nlist-sect.s
b/lldb/test/API/macosx/no-nlist-memory-module/no-nlist-sect.s
new file mode 100644
index 0000000000000..0a7c974f9362c
--- /dev/null
+++ b/lldb/test/API/macosx/no-nlist-memory-module/no-nlist-sect.s
@@ -0,0 +1,3 @@
+ .section __TEXT,__lldb_no_nlist,regular,pure_instructions
+ .p2align 2
+ .byte 0x10
diff --git a/lldb/test/API/macosx/no-nlist-memory-module/no-nlists.c
b/lldb/test/API/macosx/no-nlist-memory-module/no-nlists.c
new file mode 100644
index 0000000000000..e75c5a5274bc0
--- /dev/null
+++ b/lldb/test/API/macosx/no-nlist-memory-module/no-nlists.c
@@ -0,0 +1,3 @@
+int get_return_value() {
+ return 10;
+}
_______________________________________________
lldb-commits mailing list
lldb-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/lldb-commits
