llvm-project/llvm/lib/CodeGen/ShadowStackGC.cpp

56 lines
1.7 KiB
C++
Raw Normal View History

//===-- ShadowStackGC.cpp - GC support for uncooperative targets ----------===//
With this patch, the LowerGC transformation becomes the ShadowStackCollector, which additionally has reduced overhead with no sacrifice in portability. Considering a function @fun with 8 loop-local roots, ShadowStackCollector introduces the following overhead (x86): ; shadowstack prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl $___gc_fun, 20(%esp) movl $0, 24(%esp) movl $0, 28(%esp) movl $0, 32(%esp) movl $0, 36(%esp) movl $0, 40(%esp) movl $0, 44(%esp) movl $0, 48(%esp) movl $0, 52(%esp) movl %ecx, 16(%esp) leal 16(%esp), %ecx movl %ecx, (%eax) ; shadowstack loop overhead (none) ; shadowstack epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; shadowstack metadata .align 3 ___gc_fun: # __gc_fun .long 8 .space 4 In comparison to LowerGC: ; lowergc prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl %ecx, 48(%esp) movl $8, 52(%esp) movl $0, 60(%esp) movl $0, 56(%esp) movl $0, 68(%esp) movl $0, 64(%esp) movl $0, 76(%esp) movl $0, 72(%esp) movl $0, 84(%esp) movl $0, 80(%esp) movl $0, 92(%esp) movl $0, 88(%esp) movl $0, 100(%esp) movl $0, 96(%esp) movl $0, 108(%esp) movl $0, 104(%esp) movl $0, 116(%esp) movl $0, 112(%esp) ; lowergc loop overhead leal 44(%esp), %eax movl %eax, 56(%esp) leal 40(%esp), %eax movl %eax, 64(%esp) leal 36(%esp), %eax movl %eax, 72(%esp) leal 32(%esp), %eax movl %eax, 80(%esp) leal 28(%esp), %eax movl %eax, 88(%esp) leal 24(%esp), %eax movl %eax, 96(%esp) leal 20(%esp), %eax movl %eax, 104(%esp) leal 16(%esp), %eax movl %eax, 112(%esp) ; lowergc epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; lowergc metadata (none) llvm-svn: 45670
2008-01-07 09:30:53 +08:00
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements lowering for the llvm.gc* intrinsics for targets that do
// not natively support them (which includes the C backend). Note that the code
// generated is not quite as efficient as algorithms which generate stack maps
With this patch, the LowerGC transformation becomes the ShadowStackCollector, which additionally has reduced overhead with no sacrifice in portability. Considering a function @fun with 8 loop-local roots, ShadowStackCollector introduces the following overhead (x86): ; shadowstack prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl $___gc_fun, 20(%esp) movl $0, 24(%esp) movl $0, 28(%esp) movl $0, 32(%esp) movl $0, 36(%esp) movl $0, 40(%esp) movl $0, 44(%esp) movl $0, 48(%esp) movl $0, 52(%esp) movl %ecx, 16(%esp) leal 16(%esp), %ecx movl %ecx, (%eax) ; shadowstack loop overhead (none) ; shadowstack epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; shadowstack metadata .align 3 ___gc_fun: # __gc_fun .long 8 .space 4 In comparison to LowerGC: ; lowergc prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl %ecx, 48(%esp) movl $8, 52(%esp) movl $0, 60(%esp) movl $0, 56(%esp) movl $0, 68(%esp) movl $0, 64(%esp) movl $0, 76(%esp) movl $0, 72(%esp) movl $0, 84(%esp) movl $0, 80(%esp) movl $0, 92(%esp) movl $0, 88(%esp) movl $0, 100(%esp) movl $0, 96(%esp) movl $0, 108(%esp) movl $0, 104(%esp) movl $0, 116(%esp) movl $0, 112(%esp) ; lowergc loop overhead leal 44(%esp), %eax movl %eax, 56(%esp) leal 40(%esp), %eax movl %eax, 64(%esp) leal 36(%esp), %eax movl %eax, 72(%esp) leal 32(%esp), %eax movl %eax, 80(%esp) leal 28(%esp), %eax movl %eax, 88(%esp) leal 24(%esp), %eax movl %eax, 96(%esp) leal 20(%esp), %eax movl %eax, 104(%esp) leal 16(%esp), %eax movl %eax, 112(%esp) ; lowergc epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; lowergc metadata (none) llvm-svn: 45670
2008-01-07 09:30:53 +08:00
// to identify roots.
//
// This pass implements the code transformation described in this paper:
// "Accurate Garbage Collection in an Uncooperative Environment"
// Fergus Henderson, ISMM, 2002
//
// In runtime/GC/SemiSpace.cpp is a prototype runtime which is compatible with
// ShadowStackGC.
With this patch, the LowerGC transformation becomes the ShadowStackCollector, which additionally has reduced overhead with no sacrifice in portability. Considering a function @fun with 8 loop-local roots, ShadowStackCollector introduces the following overhead (x86): ; shadowstack prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl $___gc_fun, 20(%esp) movl $0, 24(%esp) movl $0, 28(%esp) movl $0, 32(%esp) movl $0, 36(%esp) movl $0, 40(%esp) movl $0, 44(%esp) movl $0, 48(%esp) movl $0, 52(%esp) movl %ecx, 16(%esp) leal 16(%esp), %ecx movl %ecx, (%eax) ; shadowstack loop overhead (none) ; shadowstack epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; shadowstack metadata .align 3 ___gc_fun: # __gc_fun .long 8 .space 4 In comparison to LowerGC: ; lowergc prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl %ecx, 48(%esp) movl $8, 52(%esp) movl $0, 60(%esp) movl $0, 56(%esp) movl $0, 68(%esp) movl $0, 64(%esp) movl $0, 76(%esp) movl $0, 72(%esp) movl $0, 84(%esp) movl $0, 80(%esp) movl $0, 92(%esp) movl $0, 88(%esp) movl $0, 100(%esp) movl $0, 96(%esp) movl $0, 108(%esp) movl $0, 104(%esp) movl $0, 116(%esp) movl $0, 112(%esp) ; lowergc loop overhead leal 44(%esp), %eax movl %eax, 56(%esp) leal 40(%esp), %eax movl %eax, 64(%esp) leal 36(%esp), %eax movl %eax, 72(%esp) leal 32(%esp), %eax movl %eax, 80(%esp) leal 28(%esp), %eax movl %eax, 88(%esp) leal 24(%esp), %eax movl %eax, 96(%esp) leal 20(%esp), %eax movl %eax, 104(%esp) leal 16(%esp), %eax movl %eax, 112(%esp) ; lowergc epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; lowergc metadata (none) llvm-svn: 45670
2008-01-07 09:30:53 +08:00
//
// In order to support this particular transformation, all stack roots are
// coallocated in the stack. This allows a fully target-independent stack map
// while introducing only minor runtime overhead.
//
//===----------------------------------------------------------------------===//
#include "llvm/CodeGen/GCs.h"
#include "llvm/CodeGen/GCStrategy.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Module.h"
With this patch, the LowerGC transformation becomes the ShadowStackCollector, which additionally has reduced overhead with no sacrifice in portability. Considering a function @fun with 8 loop-local roots, ShadowStackCollector introduces the following overhead (x86): ; shadowstack prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl $___gc_fun, 20(%esp) movl $0, 24(%esp) movl $0, 28(%esp) movl $0, 32(%esp) movl $0, 36(%esp) movl $0, 40(%esp) movl $0, 44(%esp) movl $0, 48(%esp) movl $0, 52(%esp) movl %ecx, 16(%esp) leal 16(%esp), %ecx movl %ecx, (%eax) ; shadowstack loop overhead (none) ; shadowstack epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; shadowstack metadata .align 3 ___gc_fun: # __gc_fun .long 8 .space 4 In comparison to LowerGC: ; lowergc prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl %ecx, 48(%esp) movl $8, 52(%esp) movl $0, 60(%esp) movl $0, 56(%esp) movl $0, 68(%esp) movl $0, 64(%esp) movl $0, 76(%esp) movl $0, 72(%esp) movl $0, 84(%esp) movl $0, 80(%esp) movl $0, 92(%esp) movl $0, 88(%esp) movl $0, 100(%esp) movl $0, 96(%esp) movl $0, 108(%esp) movl $0, 104(%esp) movl $0, 116(%esp) movl $0, 112(%esp) ; lowergc loop overhead leal 44(%esp), %eax movl %eax, 56(%esp) leal 40(%esp), %eax movl %eax, 64(%esp) leal 36(%esp), %eax movl %eax, 72(%esp) leal 32(%esp), %eax movl %eax, 80(%esp) leal 28(%esp), %eax movl %eax, 88(%esp) leal 24(%esp), %eax movl %eax, 96(%esp) leal 20(%esp), %eax movl %eax, 104(%esp) leal 16(%esp), %eax movl %eax, 112(%esp) ; lowergc epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; lowergc metadata (none) llvm-svn: 45670
2008-01-07 09:30:53 +08:00
using namespace llvm;
#define DEBUG_TYPE "shadowstackgc"
With this patch, the LowerGC transformation becomes the ShadowStackCollector, which additionally has reduced overhead with no sacrifice in portability. Considering a function @fun with 8 loop-local roots, ShadowStackCollector introduces the following overhead (x86): ; shadowstack prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl $___gc_fun, 20(%esp) movl $0, 24(%esp) movl $0, 28(%esp) movl $0, 32(%esp) movl $0, 36(%esp) movl $0, 40(%esp) movl $0, 44(%esp) movl $0, 48(%esp) movl $0, 52(%esp) movl %ecx, 16(%esp) leal 16(%esp), %ecx movl %ecx, (%eax) ; shadowstack loop overhead (none) ; shadowstack epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; shadowstack metadata .align 3 ___gc_fun: # __gc_fun .long 8 .space 4 In comparison to LowerGC: ; lowergc prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl %ecx, 48(%esp) movl $8, 52(%esp) movl $0, 60(%esp) movl $0, 56(%esp) movl $0, 68(%esp) movl $0, 64(%esp) movl $0, 76(%esp) movl $0, 72(%esp) movl $0, 84(%esp) movl $0, 80(%esp) movl $0, 92(%esp) movl $0, 88(%esp) movl $0, 100(%esp) movl $0, 96(%esp) movl $0, 108(%esp) movl $0, 104(%esp) movl $0, 116(%esp) movl $0, 112(%esp) ; lowergc loop overhead leal 44(%esp), %eax movl %eax, 56(%esp) leal 40(%esp), %eax movl %eax, 64(%esp) leal 36(%esp), %eax movl %eax, 72(%esp) leal 32(%esp), %eax movl %eax, 80(%esp) leal 28(%esp), %eax movl %eax, 88(%esp) leal 24(%esp), %eax movl %eax, 96(%esp) leal 20(%esp), %eax movl %eax, 104(%esp) leal 16(%esp), %eax movl %eax, 112(%esp) ; lowergc epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; lowergc metadata (none) llvm-svn: 45670
2008-01-07 09:30:53 +08:00
namespace {
class ShadowStackGC : public GCStrategy {
public:
ShadowStackGC();
};
}
static GCRegistry::Add<ShadowStackGC>
X("shadow-stack", "Very portable GC for uncooperative code generators");
void llvm::linkShadowStackGC() {}
With this patch, the LowerGC transformation becomes the ShadowStackCollector, which additionally has reduced overhead with no sacrifice in portability. Considering a function @fun with 8 loop-local roots, ShadowStackCollector introduces the following overhead (x86): ; shadowstack prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl $___gc_fun, 20(%esp) movl $0, 24(%esp) movl $0, 28(%esp) movl $0, 32(%esp) movl $0, 36(%esp) movl $0, 40(%esp) movl $0, 44(%esp) movl $0, 48(%esp) movl $0, 52(%esp) movl %ecx, 16(%esp) leal 16(%esp), %ecx movl %ecx, (%eax) ; shadowstack loop overhead (none) ; shadowstack epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; shadowstack metadata .align 3 ___gc_fun: # __gc_fun .long 8 .space 4 In comparison to LowerGC: ; lowergc prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl %ecx, 48(%esp) movl $8, 52(%esp) movl $0, 60(%esp) movl $0, 56(%esp) movl $0, 68(%esp) movl $0, 64(%esp) movl $0, 76(%esp) movl $0, 72(%esp) movl $0, 84(%esp) movl $0, 80(%esp) movl $0, 92(%esp) movl $0, 88(%esp) movl $0, 100(%esp) movl $0, 96(%esp) movl $0, 108(%esp) movl $0, 104(%esp) movl $0, 116(%esp) movl $0, 112(%esp) ; lowergc loop overhead leal 44(%esp), %eax movl %eax, 56(%esp) leal 40(%esp), %eax movl %eax, 64(%esp) leal 36(%esp), %eax movl %eax, 72(%esp) leal 32(%esp), %eax movl %eax, 80(%esp) leal 28(%esp), %eax movl %eax, 88(%esp) leal 24(%esp), %eax movl %eax, 96(%esp) leal 20(%esp), %eax movl %eax, 104(%esp) leal 16(%esp), %eax movl %eax, 112(%esp) ; lowergc epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; lowergc metadata (none) llvm-svn: 45670
2008-01-07 09:30:53 +08:00
ShadowStackGC::ShadowStackGC() {
With this patch, the LowerGC transformation becomes the ShadowStackCollector, which additionally has reduced overhead with no sacrifice in portability. Considering a function @fun with 8 loop-local roots, ShadowStackCollector introduces the following overhead (x86): ; shadowstack prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl $___gc_fun, 20(%esp) movl $0, 24(%esp) movl $0, 28(%esp) movl $0, 32(%esp) movl $0, 36(%esp) movl $0, 40(%esp) movl $0, 44(%esp) movl $0, 48(%esp) movl $0, 52(%esp) movl %ecx, 16(%esp) leal 16(%esp), %ecx movl %ecx, (%eax) ; shadowstack loop overhead (none) ; shadowstack epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; shadowstack metadata .align 3 ___gc_fun: # __gc_fun .long 8 .space 4 In comparison to LowerGC: ; lowergc prologue movl L_llvm_gc_root_chain$non_lazy_ptr, %eax movl (%eax), %ecx movl %ecx, 48(%esp) movl $8, 52(%esp) movl $0, 60(%esp) movl $0, 56(%esp) movl $0, 68(%esp) movl $0, 64(%esp) movl $0, 76(%esp) movl $0, 72(%esp) movl $0, 84(%esp) movl $0, 80(%esp) movl $0, 92(%esp) movl $0, 88(%esp) movl $0, 100(%esp) movl $0, 96(%esp) movl $0, 108(%esp) movl $0, 104(%esp) movl $0, 116(%esp) movl $0, 112(%esp) ; lowergc loop overhead leal 44(%esp), %eax movl %eax, 56(%esp) leal 40(%esp), %eax movl %eax, 64(%esp) leal 36(%esp), %eax movl %eax, 72(%esp) leal 32(%esp), %eax movl %eax, 80(%esp) leal 28(%esp), %eax movl %eax, 88(%esp) leal 24(%esp), %eax movl %eax, 96(%esp) leal 20(%esp), %eax movl %eax, 104(%esp) leal 16(%esp), %eax movl %eax, 112(%esp) ; lowergc epilogue movl 48(%esp), %edx movl %edx, (%ecx) ; lowergc metadata (none) llvm-svn: 45670
2008-01-07 09:30:53 +08:00
InitRoots = true;
CustomRoots = true;
}