2008-08-18 02:44:35 +08:00
|
|
|
//===-- 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 $0, 112(%esp)
; lowergc loop overhead
leal 44(%esp), %eax
movl %eax, 56(%esp)
leal 40(%esp), %eax
movl %eax, 64(%esp)
leal 36(%esp), %eax
movl %eax, 72(%esp)
leal 32(%esp), %eax
movl %eax, 80(%esp)
leal 28(%esp), %eax
movl %eax, 88(%esp)
leal 24(%esp), %eax
movl %eax, 96(%esp)
leal 20(%esp), %eax
movl %eax, 104(%esp)
leal 16(%esp), %eax
movl %eax, 112(%esp)
; lowergc epilogue
movl 48(%esp), %edx
movl %edx, (%ecx)
; lowergc metadata
(none)
llvm-svn: 45670
2008-01-07 09:30:53 +08:00
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file implements lowering for the llvm.gc* intrinsics for targets that do
|
|
|
|
// not natively support them (which includes the C backend). Note that the code
|
2008-08-18 02:44:35 +08:00
|
|
|
// generated is not quite as efficient as algorithms which generate stack maps
|
With this patch, the LowerGC transformation becomes the
ShadowStackCollector, which additionally has reduced overhead with
no sacrifice in portability.
Considering a function @fun with 8 loop-local roots,
ShadowStackCollector introduces the following overhead
(x86):
; shadowstack prologue
movl L_llvm_gc_root_chain$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 $0, 112(%esp)
; lowergc loop overhead
leal 44(%esp), %eax
movl %eax, 56(%esp)
leal 40(%esp), %eax
movl %eax, 64(%esp)
leal 36(%esp), %eax
movl %eax, 72(%esp)
leal 32(%esp), %eax
movl %eax, 80(%esp)
leal 28(%esp), %eax
movl %eax, 88(%esp)
leal 24(%esp), %eax
movl %eax, 96(%esp)
leal 20(%esp), %eax
movl %eax, 104(%esp)
leal 16(%esp), %eax
movl %eax, 112(%esp)
; lowergc epilogue
movl 48(%esp), %edx
movl %edx, (%ecx)
; lowergc metadata
(none)
llvm-svn: 45670
2008-01-07 09:30:53 +08:00
|
|
|
// to identify roots.
|
|
|
|
//
|
|
|
|
// This pass implements the code transformation described in this paper:
|
|
|
|
// "Accurate Garbage Collection in an Uncooperative Environment"
|
|
|
|
// Fergus Henderson, ISMM, 2002
|
|
|
|
//
|
|
|
|
// In runtime/GC/SemiSpace.cpp is a prototype runtime which is compatible with
|
2008-08-18 02:44:35 +08:00
|
|
|
// ShadowStackGC.
|
With this patch, the LowerGC transformation becomes the
ShadowStackCollector, which additionally has reduced overhead with
no sacrifice in portability.
Considering a function @fun with 8 loop-local roots,
ShadowStackCollector introduces the following overhead
(x86):
; shadowstack prologue
movl L_llvm_gc_root_chain$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 $0, 112(%esp)
; lowergc loop overhead
leal 44(%esp), %eax
movl %eax, 56(%esp)
leal 40(%esp), %eax
movl %eax, 64(%esp)
leal 36(%esp), %eax
movl %eax, 72(%esp)
leal 32(%esp), %eax
movl %eax, 80(%esp)
leal 28(%esp), %eax
movl %eax, 88(%esp)
leal 24(%esp), %eax
movl %eax, 96(%esp)
leal 20(%esp), %eax
movl %eax, 104(%esp)
leal 16(%esp), %eax
movl %eax, 112(%esp)
; lowergc epilogue
movl 48(%esp), %edx
movl %edx, (%ecx)
; lowergc metadata
(none)
llvm-svn: 45670
2008-01-07 09:30:53 +08:00
|
|
|
//
|
|
|
|
// In order to support this particular transformation, all stack roots are
|
|
|
|
// coallocated in the stack. This allows a fully target-independent stack map
|
|
|
|
// while introducing only minor runtime overhead.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2012-12-04 00:50:05 +08:00
|
|
|
#include "llvm/CodeGen/GCs.h"
|
2015-01-27 02:26:35 +08:00
|
|
|
#include "llvm/CodeGen/GCStrategy.h"
|
2012-12-04 00:50:05 +08:00
|
|
|
#include "llvm/ADT/StringExtras.h"
|
2014-03-04 19:01:28 +08:00
|
|
|
#include "llvm/IR/CallSite.h"
|
2013-01-02 19:36:10 +08:00
|
|
|
#include "llvm/IR/IRBuilder.h"
|
|
|
|
#include "llvm/IR/IntrinsicInst.h"
|
|
|
|
#include "llvm/IR/Module.h"
|
With this patch, the LowerGC transformation becomes the
ShadowStackCollector, which additionally has reduced overhead with
no sacrifice in portability.
Considering a function @fun with 8 loop-local roots,
ShadowStackCollector introduces the following overhead
(x86):
; shadowstack prologue
movl L_llvm_gc_root_chain$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 $0, 112(%esp)
; lowergc loop overhead
leal 44(%esp), %eax
movl %eax, 56(%esp)
leal 40(%esp), %eax
movl %eax, 64(%esp)
leal 36(%esp), %eax
movl %eax, 72(%esp)
leal 32(%esp), %eax
movl %eax, 80(%esp)
leal 28(%esp), %eax
movl %eax, 88(%esp)
leal 24(%esp), %eax
movl %eax, 96(%esp)
leal 20(%esp), %eax
movl %eax, 104(%esp)
leal 16(%esp), %eax
movl %eax, 112(%esp)
; lowergc epilogue
movl 48(%esp), %edx
movl %edx, (%ecx)
; lowergc metadata
(none)
llvm-svn: 45670
2008-01-07 09:30:53 +08:00
|
|
|
|
|
|
|
using namespace llvm;
|
|
|
|
|
2014-04-22 10:02:50 +08:00
|
|
|
#define DEBUG_TYPE "shadowstackgc"
|
|
|
|
|
With this patch, the LowerGC transformation becomes the
ShadowStackCollector, which additionally has reduced overhead with
no sacrifice in portability.
Considering a function @fun with 8 loop-local roots,
ShadowStackCollector introduces the following overhead
(x86):
; shadowstack prologue
movl L_llvm_gc_root_chain$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 $0, 112(%esp)
; lowergc loop overhead
leal 44(%esp), %eax
movl %eax, 56(%esp)
leal 40(%esp), %eax
movl %eax, 64(%esp)
leal 36(%esp), %eax
movl %eax, 72(%esp)
leal 32(%esp), %eax
movl %eax, 80(%esp)
leal 28(%esp), %eax
movl %eax, 88(%esp)
leal 24(%esp), %eax
movl %eax, 96(%esp)
leal 20(%esp), %eax
movl %eax, 104(%esp)
leal 16(%esp), %eax
movl %eax, 112(%esp)
; lowergc epilogue
movl 48(%esp), %edx
movl %edx, (%ecx)
; lowergc metadata
(none)
llvm-svn: 45670
2008-01-07 09:30:53 +08:00
|
|
|
namespace {
|
2015-01-17 07:16:12 +08:00
|
|
|
class ShadowStackGC : public GCStrategy {
|
|
|
|
public:
|
|
|
|
ShadowStackGC();
|
|
|
|
};
|
2008-05-13 08:00:25 +08:00
|
|
|
}
|
2009-01-16 14:53:46 +08:00
|
|
|
|
2008-08-18 02:44:35 +08:00
|
|
|
static GCRegistry::Add<ShadowStackGC>
|
2015-01-17 07:16:12 +08:00
|
|
|
X("shadow-stack", "Very portable GC for uncooperative code generators");
|
2009-01-16 14:53:46 +08:00
|
|
|
|
2015-01-17 07:16:12 +08:00
|
|
|
void llvm::linkShadowStackGC() {}
|
With this patch, the LowerGC transformation becomes the
ShadowStackCollector, which additionally has reduced overhead with
no sacrifice in portability.
Considering a function @fun with 8 loop-local roots,
ShadowStackCollector introduces the following overhead
(x86):
; shadowstack prologue
movl L_llvm_gc_root_chain$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 $0, 112(%esp)
; lowergc loop overhead
leal 44(%esp), %eax
movl %eax, 56(%esp)
leal 40(%esp), %eax
movl %eax, 64(%esp)
leal 36(%esp), %eax
movl %eax, 72(%esp)
leal 32(%esp), %eax
movl %eax, 80(%esp)
leal 28(%esp), %eax
movl %eax, 88(%esp)
leal 24(%esp), %eax
movl %eax, 96(%esp)
leal 20(%esp), %eax
movl %eax, 104(%esp)
leal 16(%esp), %eax
movl %eax, 112(%esp)
; lowergc epilogue
movl 48(%esp), %edx
movl %edx, (%ecx)
; lowergc metadata
(none)
llvm-svn: 45670
2008-01-07 09:30:53 +08:00
|
|
|
|
2015-01-29 03:28:03 +08:00
|
|
|
ShadowStackGC::ShadowStackGC() {
|
With this patch, the LowerGC transformation becomes the
ShadowStackCollector, which additionally has reduced overhead with
no sacrifice in portability.
Considering a function @fun with 8 loop-local roots,
ShadowStackCollector introduces the following overhead
(x86):
; shadowstack prologue
movl L_llvm_gc_root_chain$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;
|
|
|
|
}
|