1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
|
//===-- AMDGPUCtorDtorLowering.cpp - Handle global ctors and dtors --------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \file
/// This pass creates a unified init and fini kernel with the required metadata
//===----------------------------------------------------------------------===//
#include "AMDGPUCtorDtorLowering.h"
#include "AMDGPU.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Value.h"
#include "llvm/Pass.h"
#include "llvm/Transforms/Utils/ModuleUtils.h"
using namespace llvm;
#define DEBUG_TYPE "amdgpu-lower-ctor-dtor"
namespace {
static Function *createInitOrFiniKernelFunction(Module &M, bool IsCtor) {
StringRef InitOrFiniKernelName = "amdgcn.device.init";
if (!IsCtor)
InitOrFiniKernelName = "amdgcn.device.fini";
if (M.getFunction(InitOrFiniKernelName))
return nullptr;
Function *InitOrFiniKernel = Function::createWithDefaultAttr(
FunctionType::get(Type::getVoidTy(M.getContext()), false),
GlobalValue::WeakODRLinkage, 0, InitOrFiniKernelName, &M);
InitOrFiniKernel->setCallingConv(CallingConv::AMDGPU_KERNEL);
InitOrFiniKernel->addFnAttr("amdgpu-flat-work-group-size", "1,1");
if (IsCtor)
InitOrFiniKernel->addFnAttr("device-init");
else
InitOrFiniKernel->addFnAttr("device-fini");
return InitOrFiniKernel;
}
// The linker will provide the associated symbols to allow us to traverse the
// global constructors / destructors in priority order. We create the IR
// required to call each callback in this section. This is equivalent to the
// following code.
//
// extern "C" void * __init_array_start[];
// extern "C" void * __init_array_end[];
//
// using InitCallback = void();
//
// void call_init_array_callbacks() {
// for (auto start = __init_array_start; start != __init_array_end; ++start)
// reinterpret_cast<InitCallback *>(*start)();
// }
static void createInitOrFiniCalls(Function &F, bool IsCtor) {
Module &M = *F.getParent();
LLVMContext &C = M.getContext();
IRBuilder<> IRB(BasicBlock::Create(C, "entry", &F));
auto *LoopBB = BasicBlock::Create(C, "while.entry", &F);
auto *ExitBB = BasicBlock::Create(C, "while.end", &F);
Type *PtrTy = IRB.getPtrTy(AMDGPUAS::GLOBAL_ADDRESS);
auto *Begin = M.getOrInsertGlobal(
IsCtor ? "__init_array_start" : "__fini_array_start",
ArrayType::get(PtrTy, 0), [&]() {
return new GlobalVariable(
M, ArrayType::get(PtrTy, 0),
/*isConstant=*/true, GlobalValue::ExternalLinkage,
/*Initializer=*/nullptr,
IsCtor ? "__init_array_start" : "__fini_array_start",
/*InsertBefore=*/nullptr, GlobalVariable::NotThreadLocal,
/*AddressSpace=*/1);
});
auto *End = M.getOrInsertGlobal(
IsCtor ? "__init_array_end" : "__fini_array_end",
ArrayType::get(PtrTy, 0), [&]() {
return new GlobalVariable(
M, ArrayType::get(PtrTy, 0),
/*isConstant=*/true, GlobalValue::ExternalLinkage,
/*Initializer=*/nullptr,
IsCtor ? "__init_array_end" : "__fini_array_end",
/*InsertBefore=*/nullptr, GlobalVariable::NotThreadLocal,
/*AddressSpace=*/1);
});
// The constructor type is suppoed to allow using the argument vectors, but
// for now we just call them with no arguments.
auto *CallBackTy = FunctionType::get(IRB.getVoidTy(), {});
IRB.CreateCondBr(IRB.CreateICmpNE(Begin, End), LoopBB, ExitBB);
IRB.SetInsertPoint(LoopBB);
auto *CallBackPHI = IRB.CreatePHI(PtrTy, 2, "ptr");
auto *CallBack = IRB.CreateLoad(CallBackTy->getPointerTo(F.getAddressSpace()),
CallBackPHI, "callback");
IRB.CreateCall(CallBackTy, CallBack);
auto *NewCallBack = IRB.CreateConstGEP1_64(PtrTy, CallBackPHI, 1, "next");
auto *EndCmp = IRB.CreateICmpEQ(NewCallBack, End, "end");
CallBackPHI->addIncoming(Begin, &F.getEntryBlock());
CallBackPHI->addIncoming(NewCallBack, LoopBB);
IRB.CreateCondBr(EndCmp, ExitBB, LoopBB);
IRB.SetInsertPoint(ExitBB);
IRB.CreateRetVoid();
}
static bool createInitOrFiniKernel(Module &M, StringRef GlobalName,
bool IsCtor) {
GlobalVariable *GV = M.getGlobalVariable(GlobalName);
if (!GV || !GV->hasInitializer())
return false;
ConstantArray *GA = dyn_cast<ConstantArray>(GV->getInitializer());
if (!GA || GA->getNumOperands() == 0)
return false;
Function *InitOrFiniKernel = createInitOrFiniKernelFunction(M, IsCtor);
if (!InitOrFiniKernel)
return false;
createInitOrFiniCalls(*InitOrFiniKernel, IsCtor);
appendToUsed(M, {InitOrFiniKernel});
return true;
}
static bool lowerCtorsAndDtors(Module &M) {
bool Modified = false;
Modified |= createInitOrFiniKernel(M, "llvm.global_ctors", /*IsCtor =*/true);
Modified |= createInitOrFiniKernel(M, "llvm.global_dtors", /*IsCtor =*/false);
return Modified;
}
class AMDGPUCtorDtorLoweringLegacy final : public ModulePass {
public:
static char ID;
AMDGPUCtorDtorLoweringLegacy() : ModulePass(ID) {}
bool runOnModule(Module &M) override { return lowerCtorsAndDtors(M); }
};
} // End anonymous namespace
PreservedAnalyses AMDGPUCtorDtorLoweringPass::run(Module &M,
ModuleAnalysisManager &AM) {
return lowerCtorsAndDtors(M) ? PreservedAnalyses::none()
: PreservedAnalyses::all();
}
char AMDGPUCtorDtorLoweringLegacy::ID = 0;
char &llvm::AMDGPUCtorDtorLoweringLegacyPassID =
AMDGPUCtorDtorLoweringLegacy::ID;
INITIALIZE_PASS(AMDGPUCtorDtorLoweringLegacy, DEBUG_TYPE,
"Lower ctors and dtors for AMDGPU", false, false)
ModulePass *llvm::createAMDGPUCtorDtorLoweringLegacyPass() {
return new AMDGPUCtorDtorLoweringLegacy();
}
|
