ychen updated this revision to Diff 353567.
ychen marked an inline comment as done.
ychen added a comment.
- Address comments
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D97915/new/
https://reviews.llvm.org/D97915
Files:
clang/lib/CodeGen/CGBuiltin.cpp
clang/lib/CodeGen/CGCoroutine.cpp
clang/lib/CodeGen/CodeGenFunction.h
clang/test/CodeGenCoroutines/coro-alloc.cpp
clang/test/CodeGenCoroutines/coro-cleanup.cpp
clang/test/CodeGenCoroutines/coro-gro.cpp
llvm/docs/Coroutines.rst
llvm/include/llvm/IR/Intrinsics.td
llvm/lib/Transforms/Coroutines/CoroFrame.cpp
llvm/lib/Transforms/Coroutines/CoroInstr.h
llvm/lib/Transforms/Coroutines/CoroInternal.h
llvm/lib/Transforms/Coroutines/CoroSplit.cpp
llvm/lib/Transforms/Coroutines/Coroutines.cpp
llvm/test/Transforms/Coroutines/coro-frame-overalign.ll
Index: llvm/test/Transforms/Coroutines/coro-frame-overalign.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/Coroutines/coro-frame-overalign.ll
@@ -0,0 +1,78 @@
+; Check that `llvm.coro.align`, `llvm.coro.raw.frame.ptr.offset` and
+; `@llvm.coro.raw.frame.ptr.alloca` are lowered correctly.
+; RUN: opt < %s -passes=coro-split -S | FileCheck %s
+
+%PackedStruct = type <{ i64 }>
+
+declare void @consume(%PackedStruct*, i32, i32, i8**)
+declare void @consume2(i32, i32)
+
+define i8* @f() "coroutine.presplit"="1" {
+entry:
+ %data = alloca %PackedStruct, align 32
+ %id = call token @llvm.coro.id(i32 16, i8* null, i8* null, i8* null)
+ %size = call i32 @llvm.coro.size.i32()
+ %alloc = call i8* @malloc(i32 %size)
+ %hdl = call i8* @llvm.coro.begin(token %id, i8* %alloc)
+ %align = call i32 @llvm.coro.align.i32()
+ %offset = call i32 @llvm.coro.raw.frame.ptr.offset.i32()
+ %addr = call i8** @llvm.coro.raw.frame.ptr.addr()
+ call void @consume(%PackedStruct* %data, i32 %align, i32 %offset, i8** %addr)
+ %0 = call i8 @llvm.coro.suspend(token none, i1 false)
+ switch i8 %0, label %suspend [i8 0, label %resume
+ i8 1, label %cleanup]
+resume:
+ br label %cleanup
+
+cleanup:
+ %align2 = call i32 @llvm.coro.align.i32()
+ %offset2 = call i32 @llvm.coro.raw.frame.ptr.offset.i32()
+ call void @consume2(i32 %align2, i32 %offset2)
+ %mem = call i8* @llvm.coro.free(token %id, i8* %hdl)
+ call void @free(i8* %mem)
+ br label %suspend
+suspend:
+ call i1 @llvm.coro.end(i8* %hdl, i1 0)
+ ret i8* %hdl
+}
+
+; See if the raw frame address was inserted into the frame.
+; CHECK-LABEL: %f.Frame = type { void (%f.Frame*)*, void (%f.Frame*)*, i8*, i1, [7 x i8], %PackedStruct }
+
+; See if we used correct index to access frame addr field (field 2).
+; CHECK-LABEL: @f(
+; CHECK: %alloc.frame.ptr = alloca i8*, align 8
+; CHECK: %[[FIELD:.+]] = getelementptr inbounds %f.Frame, %f.Frame* %FramePtr, i32 0, i32 2
+; CHECK: %[[ADDR:.+]] = load i8*, i8** %alloc.frame.ptr, align 8
+; CHECK: store i8* %[[ADDR]], i8** %[[FIELD]], align 8
+; CHECK: %[[DATA:.+]] = getelementptr inbounds %f.Frame, %f.Frame* %FramePtr, i32 0, i32 5
+; CHECK: call void @consume(%PackedStruct* %[[DATA]], i32 32, i32 16, i8** %[[FIELD]])
+; CHECK: ret i8*
+
+; See if `llvm.coro.align` and `llvm.coro.raw.frame.ptr.offset` are lowered
+; correctly during deallocation.
+; CHECK-LABEL: @f.destroy(
+; CHECK: call void @consume2(i32 32, i32 16)
+; CHECK: call void @free(i8* %{{.*}})
+
+; CHECK-LABEL: @f.cleanup(
+; CHECK: call void @consume2(i32 32, i32 16)
+; CHECK: call void @free(i8*
+
+declare i8* @llvm.coro.free(token, i8*)
+declare i32 @llvm.coro.size.i32()
+declare i32 @llvm.coro.align.i32()
+declare i32 @llvm.coro.raw.frame.ptr.offset.i32()
+declare i8** @llvm.coro.raw.frame.ptr.addr()
+declare i8 @llvm.coro.suspend(token, i1)
+declare void @llvm.coro.resume(i8*)
+declare void @llvm.coro.destroy(i8*)
+
+declare token @llvm.coro.id(i32, i8*, i8*, i8*)
+declare i1 @llvm.coro.alloc(token)
+declare i8* @llvm.coro.begin(token, i8*)
+declare i1 @llvm.coro.end(i8*, i1)
+
+declare noalias i8* @malloc(i32)
+declare double @print(double)
+declare void @free(i8*)
Index: llvm/lib/Transforms/Coroutines/Coroutines.cpp
===================================================================
--- llvm/lib/Transforms/Coroutines/Coroutines.cpp
+++ llvm/lib/Transforms/Coroutines/Coroutines.cpp
@@ -234,6 +234,9 @@
Shape.CoroBegin = nullptr;
Shape.CoroEnds.clear();
Shape.CoroSizes.clear();
+ Shape.CoroAligns.clear();
+ Shape.CoroRawFramePtrOffsets.clear();
+ Shape.CoroRawFramePtrAddrs.clear();
Shape.CoroSuspends.clear();
Shape.FrameTy = nullptr;
@@ -268,6 +271,15 @@
case Intrinsic::coro_size:
CoroSizes.push_back(cast<CoroSizeInst>(II));
break;
+ case Intrinsic::coro_align:
+ CoroAligns.push_back(cast<CoroAlignInst>(II));
+ break;
+ case Intrinsic::coro_raw_frame_ptr_offset:
+ CoroRawFramePtrOffsets.push_back(cast<CoroRawFramePtrOffsetInst>(II));
+ break;
+ case Intrinsic::coro_raw_frame_ptr_addr:
+ CoroRawFramePtrAddrs.push_back(cast<CoroRawFramePtrAddrInst>(II));
+ break;
case Intrinsic::coro_frame:
CoroFrames.push_back(cast<CoroFrameInst>(II));
break;
@@ -375,6 +387,7 @@
this->SwitchLowering.ResumeSwitch = nullptr;
this->SwitchLowering.PromiseAlloca = SwitchId->getPromise();
this->SwitchLowering.ResumeEntryBlock = nullptr;
+ this->SwitchLowering.FramePtrOffset = 0;
for (auto AnySuspend : CoroSuspends) {
auto Suspend = dyn_cast<CoroSuspendInst>(AnySuspend);
Index: llvm/lib/Transforms/Coroutines/CoroSplit.cpp
===================================================================
--- llvm/lib/Transforms/Coroutines/CoroSplit.cpp
+++ llvm/lib/Transforms/Coroutines/CoroSplit.cpp
@@ -1046,23 +1046,44 @@
Shape.AsyncLowering.AsyncFuncPointer->setInitializer(NewFuncPtrStruct);
}
-static void replaceFrameSize(coro::Shape &Shape) {
+static void replaceFrameSizeAndAlign(coro::Shape &Shape) {
if (Shape.ABI == coro::ABI::Async)
updateAsyncFuncPointerContextSize(Shape);
- if (Shape.CoroSizes.empty())
- return;
+ if (!Shape.CoroSizes.empty()) {
+ // In the same function all coro.sizes should have the same result type.
+ auto *SizeIntrin = Shape.CoroSizes.back();
+ Module *M = SizeIntrin->getModule();
+ const DataLayout &DL = M->getDataLayout();
+ auto Size = DL.getTypeAllocSize(Shape.FrameTy);
+ auto *SizeConstant = ConstantInt::get(SizeIntrin->getType(), Size);
+
+ for (CoroSizeInst *CS : Shape.CoroSizes) {
+ CS->replaceAllUsesWith(SizeConstant);
+ CS->eraseFromParent();
+ }
+ }
- // In the same function all coro.sizes should have the same result type.
- auto *SizeIntrin = Shape.CoroSizes.back();
- Module *M = SizeIntrin->getModule();
- const DataLayout &DL = M->getDataLayout();
- auto Size = DL.getTypeAllocSize(Shape.FrameTy);
- auto *SizeConstant = ConstantInt::get(SizeIntrin->getType(), Size);
+ if (!Shape.CoroAligns.empty()) {
+ auto *Intrin = Shape.CoroAligns.back();
+ auto *AlignConstant =
+ ConstantInt::get(Intrin->getType(), Shape.FrameAlign.value());
- for (CoroSizeInst *CS : Shape.CoroSizes) {
- CS->replaceAllUsesWith(SizeConstant);
- CS->eraseFromParent();
+ for (CoroAlignInst *CS : Shape.CoroAligns) {
+ CS->replaceAllUsesWith(AlignConstant);
+ CS->eraseFromParent();
+ }
+ }
+
+ if (!Shape.CoroRawFramePtrOffsets.empty()) {
+ auto *Intrin = Shape.CoroRawFramePtrOffsets.back();
+ auto *FramePtrOffset = ConstantInt::get(
+ Intrin->getType(), Shape.SwitchLowering.FramePtrOffset);
+
+ for (CoroRawFramePtrOffsetInst *CS : Shape.CoroRawFramePtrOffsets) {
+ CS->replaceAllUsesWith(FramePtrOffset);
+ CS->eraseFromParent();
+ }
}
}
@@ -1798,7 +1819,7 @@
simplifySuspendPoints(Shape);
buildCoroutineFrame(F, Shape);
- replaceFrameSize(Shape);
+ replaceFrameSizeAndAlign(Shape);
// If there are no suspend points, no split required, just remove
// the allocation and deallocation blocks, they are not needed.
Index: llvm/lib/Transforms/Coroutines/CoroInternal.h
===================================================================
--- llvm/lib/Transforms/Coroutines/CoroInternal.h
+++ llvm/lib/Transforms/Coroutines/CoroInternal.h
@@ -99,6 +99,9 @@
CoroBeginInst *CoroBegin;
SmallVector<AnyCoroEndInst *, 4> CoroEnds;
SmallVector<CoroSizeInst *, 2> CoroSizes;
+ SmallVector<CoroAlignInst *, 2> CoroAligns;
+ SmallVector<CoroRawFramePtrOffsetInst *, 2> CoroRawFramePtrOffsets;
+ SmallVector<CoroRawFramePtrAddrInst *, 2> CoroRawFramePtrAddrs;
SmallVector<AnyCoroSuspendInst *, 4> CoroSuspends;
SmallVector<CallInst*, 2> SwiftErrorOps;
@@ -135,6 +138,7 @@
unsigned IndexField;
unsigned IndexAlign;
unsigned IndexOffset;
+ unsigned FramePtrOffset;
bool HasFinalSuspend;
};
Index: llvm/lib/Transforms/Coroutines/CoroInstr.h
===================================================================
--- llvm/lib/Transforms/Coroutines/CoroInstr.h
+++ llvm/lib/Transforms/Coroutines/CoroInstr.h
@@ -27,6 +27,7 @@
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/Intrinsics.h"
#include "llvm/Support/raw_ostream.h"
namespace llvm {
@@ -121,6 +122,10 @@
: cast<AllocaInst>(Arg->stripPointerCasts());
}
+ unsigned getAlignment() const {
+ return cast<ConstantInt>(getArgOperand(AlignArg))->getZExtValue();
+ }
+
void clearPromise() {
Value *Arg = getArgOperand(PromiseArg);
setArgOperand(PromiseArg,
@@ -599,6 +604,42 @@
}
};
+/// This represents the llvm.coro.align instruction.
+class LLVM_LIBRARY_VISIBILITY CoroAlignInst : public IntrinsicInst {
+public:
+ // Methods to support type inquiry through isa, cast, and dyn_cast:
+ static bool classof(const IntrinsicInst *I) {
+ return I->getIntrinsicID() == Intrinsic::coro_align;
+ }
+ static bool classof(const Value *V) {
+ return isa<IntrinsicInst>(V) && classof(cast<IntrinsicInst>(V));
+ }
+};
+
+/// This represents the llvm.coro.raw.frame.ptr.offset instruction.
+class LLVM_LIBRARY_VISIBILITY CoroRawFramePtrOffsetInst : public IntrinsicInst {
+public:
+ // Methods to support type inquiry through isa, cast, and dyn_cast:
+ static bool classof(const IntrinsicInst *I) {
+ return I->getIntrinsicID() == Intrinsic::coro_raw_frame_ptr_offset;
+ }
+ static bool classof(const Value *V) {
+ return isa<IntrinsicInst>(V) && classof(cast<IntrinsicInst>(V));
+ }
+};
+
+/// This represents the llvm.coro.raw.frame.ptr.addr instruction.
+class LLVM_LIBRARY_VISIBILITY CoroRawFramePtrAddrInst : public IntrinsicInst {
+public:
+ // Methods to support type inquiry through isa, cast, and dyn_cast:
+ static bool classof(const IntrinsicInst *I) {
+ return I->getIntrinsicID() == Intrinsic::coro_raw_frame_ptr_addr;
+ }
+ static bool classof(const Value *V) {
+ return isa<IntrinsicInst>(V) && classof(cast<IntrinsicInst>(V));
+ }
+};
+
class LLVM_LIBRARY_VISIBILITY AnyCoroEndInst : public IntrinsicInst {
enum { FrameArg, UnwindArg };
Index: llvm/lib/Transforms/Coroutines/CoroFrame.cpp
===================================================================
--- llvm/lib/Transforms/Coroutines/CoroFrame.cpp
+++ llvm/lib/Transforms/Coroutines/CoroFrame.cpp
@@ -21,6 +21,7 @@
#include "llvm/Analysis/StackLifetime.h"
#include "llvm/Config/llvm-config.h"
#include "llvm/IR/CFG.h"
+#include "llvm/IR/Constants.h"
#include "llvm/IR/DIBuilder.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/IRBuilder.h"
@@ -531,6 +532,8 @@
return StructAlign;
}
+ SmallVector<Field, 8> &getFields() { return Fields; }
+
FieldIDType getLayoutFieldIndex(FieldIDType Id) const {
assert(IsFinished && "not yet finished!");
return Fields[Id].LayoutFieldIndex;
@@ -1126,21 +1129,59 @@
// Because multiple allocas may own the same field slot,
// we add allocas to field here.
B.addFieldForAllocas(F, FrameData, Shape);
- // Add PromiseAlloca to Allocas list so that
- // 1. updateLayoutIndex could update its index after
- // `performOptimizedStructLayout`
- // 2. it is processed in insertSpills.
- if (Shape.ABI == coro::ABI::Switch && PromiseAlloca)
- // We assume that the promise alloca won't be modified before
- // CoroBegin and no alias will be create before CoroBegin.
- FrameData.Allocas.emplace_back(
- PromiseAlloca, DenseMap<Instruction *, llvm::Optional<APInt>>{}, false);
+
// Create an entry for every spilled value.
for (auto &S : FrameData.Spills) {
FieldIDType Id = B.addField(S.first->getType(), None);
FrameData.setFieldIndex(S.first, Id);
}
+ Optional<FieldIDType> FramePtrField = None;
+ if (Shape.ABI == coro::ABI::Switch) {
+ // Add PromiseAlloca to Allocas list so that
+ // 1. updateLayoutIndex could update its index after
+ // `performOptimizedStructLayout`
+ // 2. it is processed in insertSpills.
+ if (PromiseAlloca)
+ // We assume that the promise alloca won't be modified before
+ // CoroBegin and no alias will be create before CoroBegin.
+ FrameData.Allocas.emplace_back(
+ PromiseAlloca, DenseMap<Instruction *, llvm::Optional<APInt>>{},
+ false);
+
+ Align FrameAlign =
+ std::max_element(
+ B.getFields().begin(), B.getFields().end(),
+ [](auto &F1, auto &F2) { return F1.Alignment < F2.Alignment; })
+ ->Alignment;
+
+ // Check for over-alignment.
+ Value *PtrAddr =
+ ConstantPointerNull::get(Type::getInt8PtrTy(C)->getPointerTo());
+ unsigned NewAlign = Shape.getSwitchCoroId()->getAlignment();
+ bool NeedFramePtrField = Shape.CoroRawFramePtrOffsets.size() > 0 ||
+ Shape.CoroRawFramePtrAddrs.size() > 0;
+ if (NeedFramePtrField && NewAlign && FrameAlign > NewAlign) {
+ BasicBlock &Entry = F.getEntryBlock();
+ IRBuilder<> Builder(&Entry, Entry.getFirstInsertionPt());
+
+ // Reserve frame space for raw frame pointer.
+ Value *Mem = Shape.CoroBegin->getMem();
+ AllocaInst *FramePtrAddr =
+ Builder.CreateAlloca(Mem->getType(), nullptr, "alloc.frame.ptr");
+ PtrAddr = FramePtrAddr;
+ FramePtrField = B.addFieldForAlloca(FramePtrAddr);
+ FrameData.setFieldIndex(FramePtrAddr, *FramePtrField);
+ FrameData.Allocas.emplace_back(
+ FramePtrAddr, DenseMap<Instruction *, llvm::Optional<APInt>>{}, true);
+ }
+
+ for (CoroRawFramePtrAddrInst *C : Shape.CoroRawFramePtrAddrs) {
+ C->replaceAllUsesWith(PtrAddr);
+ C->eraseFromParent();
+ }
+ }
+
B.finish(FrameTy);
FrameData.updateLayoutIndex(B);
Shape.FrameAlign = B.getStructAlign();
@@ -1154,6 +1195,12 @@
Shape.SwitchLowering.IndexAlign = IndexField.Alignment.value();
Shape.SwitchLowering.IndexOffset = IndexField.Offset;
+ if (FramePtrField) {
+ FieldIDType FieldIdx = B.getLayoutFieldIndex(*FramePtrField);
+ Shape.SwitchLowering.FramePtrOffset =
+ DL.getStructLayout(FrameTy)->getElementOffset(FieldIdx);
+ }
+
// Also round the frame size up to a multiple of its alignment, as is
// generally expected in C/C++.
Shape.FrameSize = alignTo(Shape.FrameSize, Shape.FrameAlign);
Index: llvm/include/llvm/IR/Intrinsics.td
===================================================================
--- llvm/include/llvm/IR/Intrinsics.td
+++ llvm/include/llvm/IR/Intrinsics.td
@@ -1265,6 +1265,9 @@
def int_coro_frame : Intrinsic<[llvm_ptr_ty], [], [IntrNoMem]>;
def int_coro_noop : Intrinsic<[llvm_ptr_ty], [], [IntrNoMem]>;
def int_coro_size : Intrinsic<[llvm_anyint_ty], [], [IntrNoMem]>;
+def int_coro_align : Intrinsic<[llvm_anyint_ty], [], [IntrNoMem]>;
+def int_coro_raw_frame_ptr_offset : Intrinsic<[llvm_anyint_ty], [], [IntrNoMem]>;
+def int_coro_raw_frame_ptr_addr : Intrinsic<[llvm_ptrptr_ty], [], [IntrNoMem]>;
def int_coro_save : Intrinsic<[llvm_token_ty], [llvm_ptr_ty], []>;
def int_coro_suspend : Intrinsic<[llvm_i8_ty], [llvm_token_ty, llvm_i1_ty], []>;
Index: llvm/docs/Coroutines.rst
===================================================================
--- llvm/docs/Coroutines.rst
+++ llvm/docs/Coroutines.rst
@@ -948,6 +948,88 @@
The `coro.size` intrinsic is lowered to a constant representing the size of
the coroutine frame.
+.. _coro.align:
+
+'llvm.coro.align' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+::
+
+ declare i32 @llvm.coro.align.i32()
+ declare i64 @llvm.coro.align.i64()
+
+Overview:
+"""""""""
+
+The '``llvm.coro.align``' intrinsic returns the alignment of the coroutine frame
+in bytes.
+
+Arguments:
+""""""""""
+
+None
+
+Semantics:
+""""""""""
+
+The `coro.align` intrinsic is lowered to a constant representing the alignment
+of the coroutine frame.
+
+.. _coro.raw.frame.ptr.offset:
+
+'llvm.coro.raw.frame.ptr.offset' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+::
+
+ declare i32 @llvm.coro.raw.frame.ptr.offset.i32()
+ declare i64 @llvm.coro.raw.frame.ptr.offset.i64()
+
+Overview:
+"""""""""
+
+The '``llvm.coro.raw.frame.ptr.offset``' intrinsic returns the byte offset of
+the raw memory block address (returned by the allocator) in coroutine frame.
+This is only supported for switched-resume coroutines. The return value is
+undefined when the coroutine frame is not overaligned.
+
+Arguments:
+""""""""""
+
+None
+
+Semantics:
+""""""""""
+
+The `coro.raw.frame.ptr.offset` intrinsic is lowered to a constant representing
+the byte offset of the raw memory block address in coroutine frame.
+
+
+.. _coro.raw.frame.ptr.addr:
+
+'llvm.coro.raw.frame.ptr.addr' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+::
+
+ declare i8** @llvm.coro.raw.frame.ptr.addr()
+
+Overview:
+"""""""""
+
+The '``llvm.coro.raw.frame.ptr.addr``' intrinsic returns the address storing the raw
+frame address. The returned address is either an alloca or a coroutine frame
+field. This is only supported for switched-resume coroutines. The return value
+is undefined when the coroutine frame is not overaligned.
+
+Arguments:
+""""""""""
+
+None
+
+Semantics:
+""""""""""
+
+The `coro.raw.frame.ptr.offset.addr` intrinsic is lowered to either an alloca
+or a coroutine frame field storing the raw frame address.
+
.. _coro.begin:
'llvm.coro.begin' Intrinsic
Index: clang/test/CodeGenCoroutines/coro-gro.cpp
===================================================================
--- clang/test/CodeGenCoroutines/coro-gro.cpp
+++ clang/test/CodeGenCoroutines/coro-gro.cpp
@@ -68,6 +68,7 @@
// CHECK: call void @_ZNSt12experimental16coroutine_traitsIJiEE12promise_typeD1Ev(
// CHECK: %[[Mem:.+]] = call i8* @llvm.coro.free(
// CHECK: call void @_ZdlPv(i8* %[[Mem]])
+ // CHECK: call void @_ZdlPv(i8* %{{.*}})
// Initialize retval from Gro and destroy Gro
Index: clang/test/CodeGenCoroutines/coro-cleanup.cpp
===================================================================
--- clang/test/CodeGenCoroutines/coro-cleanup.cpp
+++ clang/test/CodeGenCoroutines/coro-cleanup.cpp
@@ -78,12 +78,46 @@
// CHECK: [[Cleanup]]:
// CHECK: call void @_ZNSt12experimental16coroutine_traitsIJvEE12promise_typeD1Ev(
- // CHECK: %[[Mem0:.+]] = call i8* @llvm.coro.free(
- // CHECK: call void @_ZdlPv(i8* %[[Mem0]]
+ // CHECK: %[[MEM0:.+]] = call i8* @llvm.coro.free(
+ // CHECK: br i1 %{{.*}}, label %[[CheckAlignBB:.+]], label %[[Afterwards:.+]]
+
+ // CHECK: [[CheckAlignBB]]:
+ // CHECK: %[[ALIGN:.+]] = call i64 @llvm.coro.align.i64()
+ // CHECK: %[[CMP:.+]] = icmp ugt i64 %[[ALIGN]],
+ // CHECK: br i1 %[[CMP]], label %[[AlignedFreeBB:.+]], label %[[FreeBB:.+]]
+
+ // CHECK: [[FreeBB]]:
+ // CHECK: call void @_ZdlPv(i8* %[[MEM0]]
+ // CHECK: br label %[[Afterwards]]
+
+ // CHECK: [[AlignedFreeBB]]:
+ // CHECK-NEXT: %[[OFFSET:.+]] = call i32 @llvm.coro.raw.frame.ptr.offset.i32()
+ // CHECK-NEXT: %[[ADDR:.+]] = getelementptr inbounds i8, i8* %[[MEM0]], i32 %[[OFFSET]]
+ // CHECK-NEXT: %[[ADDR2:.+]] = bitcast i8* %[[ADDR]] to i8**
+ // CHECK-NEXT: %[[MEM:.+]] = load i8*, i8** %[[ADDR2]], align 8
+ // CHECK-NEXT: call void @_ZdlPv(i8* %[[MEM]])
+ // CHECK-NEXT: br label %[[Afterwards]]
// CHECK: [[Dealloc]]:
- // CHECK: %[[Mem:.+]] = call i8* @llvm.coro.free(
- // CHECK: call void @_ZdlPv(i8* %[[Mem]])
+ // CHECK: %[[MEM0:.+]] = call i8* @llvm.coro.free(
+ // CHECK: br i1 %{{.*}}, label %[[CheckAlignBB:.+]], label %[[Afterwards:.+]]
+
+ // CHECK: [[CheckAlignBB]]:
+ // CHECK: %[[ALIGN:.+]] = call i64 @llvm.coro.align.i64()
+ // CHECK: %[[CMP:.+]] = icmp ugt i64 %[[ALIGN]],
+ // CHECK: br i1 %[[CMP]], label %[[AlignedFreeBB:.+]], label %[[FreeBB:.+]]
+
+ // CHECK: [[FreeBB]]:
+ // CHECK: call void @_ZdlPv(i8* %[[MEM0]]
+ // CHECK: br label %[[Afterwards]]
+
+ // CHECK: [[AlignedFreeBB]]:
+ // CHECK-NEXT: %[[OFFSET:.+]] = call i32 @llvm.coro.raw.frame.ptr.offset.i32()
+ // CHECK-NEXT: %[[ADDR:.+]] = getelementptr inbounds i8, i8* %[[MEM0]], i32 %[[OFFSET]]
+ // CHECK-NEXT: %[[ADDR2:.+]] = bitcast i8* %[[ADDR]] to i8**
+ // CHECK-NEXT: %[[MEM:.+]] = load i8*, i8** %[[ADDR2]], align 8
+ // CHECK-NEXT: call void @_ZdlPv(i8* %[[MEM]])
+ // CHECK-NEXT: br label %[[Afterwards]]
co_return;
}
Index: clang/test/CodeGenCoroutines/coro-alloc.cpp
===================================================================
--- clang/test/CodeGenCoroutines/coro-alloc.cpp
+++ clang/test/CodeGenCoroutines/coro-alloc.cpp
@@ -57,24 +57,55 @@
extern "C" void f0(global_new_delete_tag) {
// CHECK: %[[ID:.+]] = call token @llvm.coro.id(i32 16
// CHECK: %[[NeedAlloc:.+]] = call i1 @llvm.coro.alloc(token %[[ID]])
- // CHECK: br i1 %[[NeedAlloc]], label %[[AllocBB:.+]], label %[[InitBB:.+]]
+ // CHECK: br i1 %[[NeedAlloc]], label %[[CheckAlignBB:.+]], label %[[InitBB:.+]]
+
+ // CHECK: [[CheckAlignBB]]:
+ // CHECK: %[[ALIGN:.+]] = call i64 @llvm.coro.align.i64()
+ // CHECK: %[[CMP:.+]] = icmp ugt i64 %[[ALIGN]], 16
+ // CHECK: br i1 %[[CMP]], label %[[AlignAllocBB:.+]], label %[[AllocBB:.+]]
// CHECK: [[AllocBB]]:
+ // CHECK-NEXT: %[[SIZE:.+]] = call i64 @llvm.coro.size.i64()
+ // CHECK-NEXT: %[[MEM:.+]] = call noalias nonnull i8* @_Znwm(i64 %[[SIZE]])
+ // CHECK-NEXT: br label %[[InitBB:.+]]
+
+ // CHECK: [[AlignAllocBB]]:
// CHECK: %[[SIZE:.+]] = call i64 @llvm.coro.size.i64()
- // CHECK: %[[MEM:.+]] = call noalias nonnull i8* @_Znwm(i64 %[[SIZE]])
+ // CHECK: %[[ALIGN:.+]] = call i64 @llvm.coro.align.i64()
+ // CHECK: %[[PAD:.+]] = sub nsw i64 %[[ALIGN]], 16
+ // CHECK: %[[NEWSIZE:.+]] = add i64 %[[SIZE]], %[[PAD]]
+ // CHECK: %[[MEM2:.+]] = call noalias nonnull i8* @_Znwm(i64 %[[NEWSIZE]])
+ // CHECK: %[[ALIGN2:.+]] = call i64 @llvm.coro.align.i64()
+ // CHECK: %[[ALIGNED:.+]] = getelementptr inbounds i8, i8* %[[MEM2]],
+ // CHECK: call void @llvm.assume(i1 true) [ "align"(i8* %[[ALIGNED]], i64 %[[ALIGN2]]) ]
+ // CHECK: %[[ADDR:.+]] = call i8** @llvm.coro.raw.frame.ptr.addr()
+ // CHECK: store i8* %[[MEM2]], i8** %[[ADDR]], align 8
// CHECK: br label %[[InitBB]]
// CHECK: [[InitBB]]:
- // CHECK: %[[PHI:.+]] = phi i8* [ null, %{{.+}} ], [ %call, %[[AllocBB]] ]
+ // CHECK: %[[PHI:.+]] = phi i8* [ null, %{{.+}} ], [ %[[MEM]], %[[AllocBB]] ], [ %[[ALIGNED]], %[[AlignAllocBB]] ]
// CHECK: %[[FRAME:.+]] = call i8* @llvm.coro.begin(token %[[ID]], i8* %[[PHI]])
// CHECK: %[[MEM:.+]] = call i8* @llvm.coro.free(token %[[ID]], i8* %[[FRAME]])
// CHECK: %[[NeedDealloc:.+]] = icmp ne i8* %[[MEM]], null
- // CHECK: br i1 %[[NeedDealloc]], label %[[FreeBB:.+]], label %[[Afterwards:.+]]
+ // CHECK: br i1 %[[NeedDealloc]], label %[[CheckAlignBB:.+]], label %[[Afterwards:.+]]
+
+ // CHECK: [[CheckAlignBB]]:
+ // CHECK: %[[ALIGN:.+]] = call i64 @llvm.coro.align.i64()
+ // CHECK: %[[CMP:.+]] = icmp ugt i64 %[[ALIGN]], 16
+ // CHECK: br i1 %[[CMP]], label %[[AlignedFreeBB:.+]], label %[[FreeBB:.+]]
// CHECK: [[FreeBB]]:
- // CHECK: call void @_ZdlPv(i8* %[[MEM]])
- // CHECK: br label %[[Afterwards]]
+ // CHECK-NEXT: call void @_ZdlPv(i8* %[[MEM]])
+ // CHECK-NEXT: br label %[[Afterwards]]
+
+ // CHECK: [[AlignedFreeBB]]:
+ // CHECK-NEXT: %[[OFFSET:.+]] = call i32 @llvm.coro.raw.frame.ptr.offset.i32()
+ // CHECK-NEXT: %[[ADDR:.+]] = getelementptr inbounds i8, i8* %[[MEM]], i32 %[[OFFSET]]
+ // CHECK-NEXT: %[[ADDR2:.+]] = bitcast i8* %[[ADDR]] to i8**
+ // CHECK-NEXT: %[[MEM:.+]] = load i8*, i8** %[[ADDR2]], align 8
+ // CHECK-NEXT: call void @_ZdlPv(i8* %[[MEM]])
+ // CHECK-NEXT: br label %[[Afterwards]]
// CHECK: [[Afterwards]]:
// CHECK: ret void
@@ -157,6 +188,7 @@
// CHECK-LABEL: f1b(
extern "C" void f1b(promise_matching_global_placement_new_tag, dummy *) {
// CHECK: call noalias nonnull i8* @_Znwm(i64
+ // CHECK-NOT: call noalias nonnull i8* @_ZnwmSt11align_val_t(i64
co_return;
}
@@ -182,6 +214,7 @@
// CHECK: %[[FRAME:.+]] = call i8* @llvm.coro.begin(
// CHECK: %[[MEM:.+]] = call i8* @llvm.coro.free(token %[[ID]], i8* %[[FRAME]])
// CHECK: call void @_ZNSt12experimental16coroutine_traitsIJv18promise_delete_tagEE12promise_typedlEPv(i8* %[[MEM]])
+ // CHECK: call void @_ZNSt12experimental16coroutine_traitsIJv18promise_delete_tagEE12promise_typedlEPv(i8*
co_return;
}
@@ -206,8 +239,24 @@
// CHECK: %[[FRAME:.+]] = call i8* @llvm.coro.begin(
// CHECK: %[[MEM:.+]] = call i8* @llvm.coro.free(token %[[ID]], i8* %[[FRAME]])
+ // CHECK: call i64 @llvm.coro.align.i64()
+ // CHECK: br i1 {{.*}}, label %[[AlignFreeBB:.+]], label %[[FreeBB:.+]]
+
+ // CHECK: [[FreeBB]]:
// CHECK: %[[SIZE2:.+]] = call i64 @llvm.coro.size.i64()
// CHECK: call void @_ZNSt12experimental16coroutine_traitsIJv24promise_sized_delete_tagEE12promise_typedlEPvm(i8* %[[MEM]], i64 %[[SIZE2]])
+
+ // CHECK: [[AlignFreeBB]]:
+ // CHECK: %[[OFFSET:.+]] = call i32 @llvm.coro.raw.frame.ptr.offset.i32()
+ // CHECK: %[[ADDR:.+]] = getelementptr inbounds i8, i8* %[[MEM]], i32 %[[OFFSET]]
+ // CHECK: %[[ADDR2:.+]] = bitcast i8* %[[ADDR]] to i8**
+ // CHECK: %[[MEM2:.+]] = load i8*, i8** %[[ADDR2]], align 8
+ // CHECK: %[[SIZE:.+]] = call i64 @llvm.coro.size.i64()
+ // CHECK: %[[ALIGN:.+]] = call i64 @llvm.coro.align.i64()
+ // CHECK: %[[DIFF:.+]] = sub nsw i64 %[[ALIGN]], 16
+ // CHECK: %[[SIZE2:.+]] = add i64 %[[SIZE]], %[[DIFF]]
+ // CHECK: call void @_ZNSt12experimental16coroutine_traitsIJv24promise_sized_delete_tagEE12promise_typedlEPvm(i8* %[[MEM2]], i64 %[[SIZE2]])
+
co_return;
}
@@ -229,16 +278,41 @@
// CHECK: %[[RetVal:.+]] = alloca i32
// CHECK: %[[Gro:.+]] = alloca i32
// CHECK: %[[ID:.+]] = call token @llvm.coro.id(i32 16
+ // CHECK: br i1 %{{.*}}, label %[[CheckAlignBB:.+]], label %[[OKBB:.+]]
+
+ // CHECK: [[CheckAlignBB]]:
+ // CHECK: %[[ALIGN:.+]] = call i64 @llvm.coro.align.i64()
+ // CHECK: %[[CMP:.+]] = icmp ugt i64 %[[ALIGN]], 16
+ // CHECK: br i1 %[[CMP]], label %[[AlignAllocBB:.+]], label %[[AllocBB:.+]]
+
+ // CHECK: [[AllocBB]]:
// CHECK: %[[SIZE:.+]] = call i64 @llvm.coro.size.i64()
// CHECK: %[[MEM:.+]] = call noalias i8* @_ZnwmRKSt9nothrow_t(i64 %[[SIZE]], %"struct.std::nothrow_t"* nonnull align 1 dereferenceable(1) @_ZStL7nothrow)
// CHECK: %[[OK:.+]] = icmp ne i8* %[[MEM]], null
- // CHECK: br i1 %[[OK]], label %[[OKBB:.+]], label %[[ERRBB:.+]]
+ // CHECK: br i1 %[[OK]], label %[[OKBB]], label %[[ERRBB:.+]]
// CHECK: [[ERRBB]]:
// CHECK: %[[FailRet:.+]] = call i32 @_ZNSt12experimental16coroutine_traitsIJi28promise_on_alloc_failure_tagEE12promise_type39get_return_object_on_allocation_failureEv(
// CHECK: store i32 %[[FailRet]], i32* %[[RetVal]]
// CHECK: br label %[[RetBB:.+]]
+ // CHECK: [[AlignAllocBB]]:
+ // CHECK: %[[SIZE:.+]] = call i64 @llvm.coro.size.i64()
+ // CHECK: %[[ALIGN:.+]] = call i64 @llvm.coro.align.i64()
+ // CHECK: %[[PAD:.+]] = sub nsw i64 %[[ALIGN]], 16
+ // CHECK: %[[NEWSIZE:.+]] = add i64 %[[SIZE]], %[[PAD]]
+ // CHECK: %[[MEM2:.+]] = call noalias i8* @_ZnwmRKSt9nothrow_t(i64 %[[NEWSIZE]], %"struct.std::nothrow_t"* nonnull align 1 dereferenceable(1) @_ZStL7nothrow)
+ // CHECK: %[[OK:.+]] = icmp ne i8* %[[MEM2]], null
+ // CHECK: br i1 %[[OK]], label %[[AlignAllocBBCont:.+]], label %[[ERRBB:.+]]
+
+ // CHECK: [[AlignAllocBBCont]]:
+ // CHECK: %[[ALIGN2:.+]] = call i64 @llvm.coro.align.i64()
+ // CHECK: %[[ALIGNED:.+]] = getelementptr inbounds i8, i8* %[[MEM2]],
+ // CHECK: call void @llvm.assume(i1 true) [ "align"(i8* %[[ALIGNED]], i64 %[[ALIGN2]]) ]
+ // CHECK: %[[ADDR:.+]] = call i8** @llvm.coro.raw.frame.ptr.addr()
+ // CHECK: store i8* %[[MEM2]], i8** %[[ADDR]], align 8
+ // CHECK: br label %[[OKBB]]
+
// CHECK: [[OKBB]]:
// CHECK: %[[OkRet:.+]] = call i32 @_ZNSt12experimental16coroutine_traitsIJi28promise_on_alloc_failure_tagEE12promise_type17get_return_objectEv(
// CHECK: store i32 %[[OkRet]], i32* %[[Gro]]
Index: clang/lib/CodeGen/CodeGenFunction.h
===================================================================
--- clang/lib/CodeGen/CodeGenFunction.h
+++ clang/lib/CodeGen/CodeGenFunction.h
@@ -1917,6 +1917,11 @@
void EmitOpenCLKernelMetadata(const FunctionDecl *FD,
llvm::Function *Fn);
+ llvm::Value *EmitBuiltinAlignTo(llvm::Value *Src, llvm::Type *SrcType,
+ llvm::Value *Alignment, llvm::Value *Mask,
+ llvm::IntegerType *IntType, const Expr *E,
+ bool AlignUp);
+
public:
CodeGenFunction(CodeGenModule &cgm, bool suppressNewContext=false);
~CodeGenFunction();
@@ -4068,6 +4073,8 @@
RValue EmitBuiltinIsAligned(const CallExpr *E);
/// Emit IR for __builtin_align_up/__builtin_align_down.
RValue EmitBuiltinAlignTo(const CallExpr *E, bool AlignUp);
+ llvm::Value *EmitBuiltinAlignTo(llvm::Value *Src, llvm::Value *Align,
+ const Expr *E, bool AlignUp);
llvm::Function *generateBuiltinOSLogHelperFunction(
const analyze_os_log::OSLogBufferLayout &Layout,
Index: clang/lib/CodeGen/CGCoroutine.cpp
===================================================================
--- clang/lib/CodeGen/CGCoroutine.cpp
+++ clang/lib/CodeGen/CGCoroutine.cpp
@@ -12,9 +12,12 @@
#include "CGCleanup.h"
#include "CodeGenFunction.h"
-#include "llvm/ADT/ScopeExit.h"
#include "clang/AST/StmtCXX.h"
#include "clang/AST/StmtVisitor.h"
+#include "llvm/ADT/ScopeExit.h"
+#include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/IntrinsicInst.h"
+#include <cstdint>
using namespace clang;
using namespace CodeGen;
@@ -75,6 +78,7 @@
// Stores the last emitted coro.free for the deallocate expressions, we use it
// to wrap dealloc code with if(auto mem = coro.free) dealloc(mem).
llvm::CallInst *LastCoroFree = nullptr;
+ bool LastCoroFreeUsedForDealloc = false;
// If coro.id came from the builtin, remember the expression to give better
// diagnostic. If CoroIdExpr is nullptr, the coro.id was created by
@@ -412,9 +416,85 @@
}
}
};
+
+// If the coroutine frame is overaligned and only an allocation function
+// that does not take `std::align_val_t` is available, the proper alignement
+// for coroutine frame is achieved by allocating more memory than needed and
+// dynamically adjust the frame start address at runtime.
+void OverAllocateFrame(CodeGenFunction &CGF, llvm::CallInst *CI, bool IsAlloc) {
+ unsigned CoroSizeIdx = IsAlloc ? 0 : 1;
+ CGBuilderTy &Builder = CGF.Builder;
+ auto OrigIP = Builder.saveIP();
+ Builder.SetInsertPoint(CI);
+ llvm::Function *CoroAlign =
+ CGF.CGM.getIntrinsic(llvm::Intrinsic::coro_align, CGF.SizeTy);
+ const auto &TI = CGF.CGM.getContext().getTargetInfo();
+ unsigned AlignOfNew = TI.getNewAlign() / TI.getCharWidth();
+ auto *AlignCall = Builder.CreateCall(CoroAlign);
+ auto *AlignOfNewInt = llvm::ConstantInt::get(CGF.SizeTy, AlignOfNew, true);
+ auto *Diff = Builder.CreateNSWSub(AlignCall, AlignOfNewInt);
+ auto *NewCoroSize = Builder.CreateAdd(CI->getArgOperand(CoroSizeIdx), Diff);
+ CI->setArgOperand(CoroSizeIdx, NewCoroSize);
+ Builder.restoreIP(OrigIP);
+}
+
+void EmitDynamicAlignedDealloc(CodeGenFunction &CGF,
+ llvm::BasicBlock *AlignedFreeBB,
+ llvm::CallInst *CoroFree) {
+ llvm::CallInst *Dealloc = nullptr;
+ for (llvm::User *U : CoroFree->users()) {
+ if (auto *CI = dyn_cast<llvm::CallInst>(U))
+ if (CI->getParent() == CGF.Builder.GetInsertBlock())
+ Dealloc = CI;
+ }
+ assert(Dealloc);
+
+ CGF.Builder.SetInsertPoint(AlignedFreeBB->getFirstNonPHI());
+
+ // Replace `coro.free` argument with the address from coroutine frame.
+
+ llvm::Function *RawFramePtrOffsetIntrin = CGF.CGM.getIntrinsic(
+ llvm::Intrinsic::coro_raw_frame_ptr_offset, CGF.Int32Ty);
+ auto *RawFramePtrOffset = CGF.Builder.CreateCall(RawFramePtrOffsetIntrin);
+ auto *FramePtrAddrStart =
+ CGF.Builder.CreateInBoundsGEP(CoroFree, {RawFramePtrOffset});
+ auto *FramePtrAddr = CGF.Builder.CreatePointerCast(
+ FramePtrAddrStart, CGF.Int8PtrTy->getPointerTo());
+ auto *FramePtr =
+ CGF.Builder.CreateLoad({FramePtrAddr, CGF.getPointerAlign()});
+ Dealloc->setArgOperand(0, FramePtr);
+
+ // Match size_t argument with the one used during allocation.
+
+ assert(Dealloc->getNumArgOperands() >= 1);
+ if (Dealloc->getNumArgOperands() > 1) {
+ // Size may only be the second argument of allocator call.
+ if (auto *CoroSize =
+ dyn_cast<llvm::IntrinsicInst>(Dealloc->getArgOperand(1)))
+ if (CoroSize->getIntrinsicID() == llvm::Intrinsic::coro_size)
+ OverAllocateFrame(CGF, Dealloc, /*IsAlloc*/ false);
+ }
+
+ CGF.Builder.SetInsertPoint(AlignedFreeBB);
+}
+
+void EmitCheckAlignBasicBlock(CodeGenFunction &CGF,
+ llvm::BasicBlock *CheckAlignBB,
+ llvm::BasicBlock *AlignBB,
+ llvm::BasicBlock *NonAlignBB) {
+ CGF.EmitBlock(CheckAlignBB);
+
+ auto &Builder = CGF.Builder;
+ auto &TI = CGF.CGM.getContext().getTargetInfo();
+ unsigned NewAlign = TI.getNewAlign() / TI.getCharWidth();
+ auto *CoroAlign = Builder.CreateCall(
+ CGF.CGM.getIntrinsic(llvm::Intrinsic::coro_align, CGF.SizeTy));
+ auto *AlignOfNew = llvm::ConstantInt::get(CGF.SizeTy, NewAlign);
+ auto *Cmp =
+ Builder.CreateICmp(llvm::CmpInst::ICMP_UGT, CoroAlign, AlignOfNew);
+ Builder.CreateCondBr(Cmp, AlignBB, NonAlignBB);
}
-namespace {
// Make sure to call coro.delete on scope exit.
struct CallCoroDelete final : public EHScopeStack::Cleanup {
Stmt *Deallocate;
@@ -432,21 +512,33 @@
// call.
BasicBlock *SaveInsertBlock = CGF.Builder.GetInsertBlock();
+ auto *CheckAlignBB = CGF.createBasicBlock("coro.free.check.align");
+ auto *AlignedFreeBB = CGF.createBasicBlock("coro.free.align");
auto *FreeBB = CGF.createBasicBlock("coro.free");
+ auto *AfterFreeBB = CGF.createBasicBlock("after.coro.free");
+
+ EmitCheckAlignBasicBlock(CGF, CheckAlignBB, AlignedFreeBB, FreeBB);
+
CGF.EmitBlock(FreeBB);
CGF.EmitStmt(Deallocate);
-
- auto *AfterFreeBB = CGF.createBasicBlock("after.coro.free");
- CGF.EmitBlock(AfterFreeBB);
+ CGF.Builder.CreateBr(AfterFreeBB);
// We should have captured coro.free from the emission of deallocate.
auto *CoroFree = CGF.CurCoro.Data->LastCoroFree;
+ CGF.CurCoro.Data->LastCoroFreeUsedForDealloc = true;
if (!CoroFree) {
CGF.CGM.Error(Deallocate->getBeginLoc(),
"Deallocation expressoin does not refer to coro.free");
return;
}
+ CGF.EmitBlock(AlignedFreeBB);
+ CGF.EmitStmt(Deallocate);
+ CGF.CurCoro.Data->LastCoroFreeUsedForDealloc = false;
+ EmitDynamicAlignedDealloc(CGF, AlignedFreeBB, CoroFree);
+
+ CGF.EmitBlock(AfterFreeBB);
+
// Get back to the block we were originally and move coro.free there.
auto *InsertPt = SaveInsertBlock->getTerminator();
CoroFree->moveBefore(InsertPt);
@@ -455,7 +547,7 @@
// Add if (auto *mem = coro.free) Deallocate;
auto *NullPtr = llvm::ConstantPointerNull::get(CGF.Int8PtrTy);
auto *Cond = CGF.Builder.CreateICmpNE(CoroFree, NullPtr);
- CGF.Builder.CreateCondBr(Cond, FreeBB, AfterFreeBB);
+ CGF.Builder.CreateCondBr(Cond, CheckAlignBB, AfterFreeBB);
// No longer need old terminator.
InsertPt->eraseFromParent();
@@ -547,9 +639,13 @@
auto *EntryBB = Builder.GetInsertBlock();
auto *AllocBB = createBasicBlock("coro.alloc");
+ auto *AlignAllocBB = createBasicBlock("coro.alloc.align");
+ auto *CheckAlignBB = createBasicBlock("coro.alloc.check.align");
auto *InitBB = createBasicBlock("coro.init");
auto *FinalBB = createBasicBlock("coro.final");
auto *RetBB = createBasicBlock("coro.ret");
+ llvm::BasicBlock *RetOnFailureBB = nullptr;
+ llvm::BasicBlock *AlignAllocBBCont = nullptr;
auto *CoroId = Builder.CreateCall(
CGM.getIntrinsic(llvm::Intrinsic::coro_id),
@@ -564,7 +660,9 @@
auto *CoroAlloc = Builder.CreateCall(
CGM.getIntrinsic(llvm::Intrinsic::coro_alloc), {CoroId});
- Builder.CreateCondBr(CoroAlloc, AllocBB, InitBB);
+ Builder.CreateCondBr(CoroAlloc, CheckAlignBB, InitBB);
+
+ EmitCheckAlignBasicBlock(*this, CheckAlignBB, AlignAllocBB, AllocBB);
EmitBlock(AllocBB);
auto *AllocateCall = EmitScalarExpr(S.getAllocate());
@@ -572,10 +670,9 @@
// Handle allocation failure if 'ReturnStmtOnAllocFailure' was provided.
if (auto *RetOnAllocFailure = S.getReturnStmtOnAllocFailure()) {
- auto *RetOnFailureBB = createBasicBlock("coro.ret.on.failure");
+ RetOnFailureBB = createBasicBlock("coro.ret.on.failure");
// See if allocation was successful.
- auto *NullPtr = llvm::ConstantPointerNull::get(Int8PtrTy);
auto *Cond = Builder.CreateICmpNE(AllocateCall, NullPtr);
Builder.CreateCondBr(Cond, InitBB, RetOnFailureBB);
@@ -587,12 +684,55 @@
Builder.CreateBr(InitBB);
}
+ EmitBlock(AlignAllocBB);
+ auto *AlignedAllocateCall = EmitScalarExpr(S.getAllocate());
+
+ // The codegen'd IR looks like:
+ // void *rawFrame = nullptr;
+ // ...
+ // if (llvm.coro.alloc()) {
+ // size_t size = llvm.coro.size(), align = llvm.coro.align();
+ // if (align > NEW_ALIGN) {
+ // size += align - NEW_ALIGN;
+ // frame = operator new(size);
+ // rawFrame = frame;
+ // frame = (frame + align - 1) & ~(align - 1);
+ // } else {
+ // frame = operator new(size);
+ // }
+ // }
+
+ // size += align - NEW_ALIGN
+ OverAllocateFrame(*this, cast<llvm::CallInst>(AlignedAllocateCall),
+ /*IsAlloc*/ true);
+ if (S.getReturnStmtOnAllocFailure()) {
+ auto *Cond = Builder.CreateICmpNE(AlignedAllocateCall, NullPtr);
+ AlignAllocBBCont = createBasicBlock("coro.alloc.align2");
+ assert(RetOnFailureBB);
+ Builder.CreateCondBr(Cond, AlignAllocBBCont, RetOnFailureBB);
+ EmitBlock(AlignAllocBBCont);
+ }
+ // frame = (frame + align - 1) & ~(align - 1)
+ auto *CoroAlign =
+ Builder.CreateCall(CGM.getIntrinsic(llvm::Intrinsic::coro_align, SizeTy));
+ auto *AlignedUpAddr =
+ EmitBuiltinAlignTo(AlignedAllocateCall, CoroAlign, S.getAllocate(), true);
+ // rawFrame = frame
+ auto *RawFramePtrAddrIntrin =
+ CGM.getIntrinsic(llvm::Intrinsic::coro_raw_frame_ptr_addr);
+ auto *RawFramePtrAddr = Builder.CreateCall(RawFramePtrAddrIntrin);
+ Builder.CreateStore(AlignedAllocateCall,
+ {RawFramePtrAddr, getPointerAlign()});
+
EmitBlock(InitBB);
// Pass the result of the allocation to coro.begin.
- auto *Phi = Builder.CreatePHI(VoidPtrTy, 2);
+ auto *Phi = Builder.CreatePHI(VoidPtrTy, 3);
Phi->addIncoming(NullPtr, EntryBB);
Phi->addIncoming(AllocateCall, AllocOrInvokeContBB);
+ Phi->addIncoming(AlignedUpAddr,
+ AlignAllocBBCont ? AlignAllocBBCont : AlignAllocBB);
+
auto *CoroBegin = Builder.CreateCall(
CGM.getIntrinsic(llvm::Intrinsic::coro_begin), {CoroId, Phi});
CurCoro.Data->CoroBegin = CoroBegin;
@@ -729,6 +869,10 @@
case llvm::Intrinsic::coro_alloc:
case llvm::Intrinsic::coro_begin:
case llvm::Intrinsic::coro_free: {
+ // Make deallocation and aligned deallocation share one `coro.free`.
+ if (CurCoro.Data && CurCoro.Data->LastCoroFreeUsedForDealloc)
+ return RValue::get(CurCoro.Data->LastCoroFree);
+
if (CurCoro.Data && CurCoro.Data->CoroId) {
Args.push_back(CurCoro.Data->CoroId);
break;
Index: clang/lib/CodeGen/CGBuiltin.cpp
===================================================================
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -16958,28 +16958,28 @@
llvm::Constant::getNullValue(Args.IntType), "is_aligned"));
}
-/// Generate (x & ~(y-1)) to align down or ((x+(y-1)) & ~(y-1)) to align up.
-/// Note: For pointer types we can avoid ptrtoint/inttoptr pairs by using the
-/// llvm.ptrmask instrinsic (with a GEP before in the align_up case).
-/// TODO: actually use ptrmask once most optimization passes know about it.
-RValue CodeGenFunction::EmitBuiltinAlignTo(const CallExpr *E, bool AlignUp) {
- BuiltinAlignArgs Args(E, *this);
- llvm::Value *SrcAddr = Args.Src;
- if (Args.Src->getType()->isPointerTy())
- SrcAddr = Builder.CreatePtrToInt(Args.Src, Args.IntType, "intptr");
+llvm::Value *CodeGenFunction::EmitBuiltinAlignTo(llvm::Value *Src,
+ llvm::Type *SrcType,
+ llvm::Value *Alignment,
+ llvm::Value *Mask,
+ llvm::IntegerType *IntType,
+ const Expr *E, bool AlignUp) {
+ llvm::Value *SrcAddr = Src;
+ if (Src->getType()->isPointerTy())
+ SrcAddr = Builder.CreatePtrToInt(Src, IntType, "intptr");
llvm::Value *SrcForMask = SrcAddr;
if (AlignUp) {
// When aligning up we have to first add the mask to ensure we go over the
// next alignment value and then align down to the next valid multiple.
// By adding the mask, we ensure that align_up on an already aligned
// value will not change the value.
- SrcForMask = Builder.CreateAdd(SrcForMask, Args.Mask, "over_boundary");
+ SrcForMask = Builder.CreateAdd(SrcForMask, Mask, "over_boundary");
}
// Invert the mask to only clear the lower bits.
- llvm::Value *InvertedMask = Builder.CreateNot(Args.Mask, "inverted_mask");
+ llvm::Value *InvertedMask = Builder.CreateNot(Mask, "inverted_mask");
llvm::Value *Result =
Builder.CreateAnd(SrcForMask, InvertedMask, "aligned_result");
- if (Args.Src->getType()->isPointerTy()) {
+ if (Src->getType()->isPointerTy()) {
/// TODO: Use ptrmask instead of ptrtoint+gep once it is optimized well.
// Result = Builder.CreateIntrinsic(
// Intrinsic::ptrmask, {Args.SrcType, SrcForMask->getType(), Args.IntType},
@@ -16988,7 +16988,7 @@
llvm::Value *Difference = Builder.CreateSub(Result, SrcAddr, "diff");
// The result must point to the same underlying allocation. This means we
// can use an inbounds GEP to enable better optimization.
- Value *Base = EmitCastToVoidPtr(Args.Src);
+ Value *Base = EmitCastToVoidPtr(Src);
if (getLangOpts().isSignedOverflowDefined())
Result = Builder.CreateGEP(Base, Difference, "aligned_result");
else
@@ -16996,13 +16996,41 @@
/*SignedIndices=*/true,
/*isSubtraction=*/!AlignUp,
E->getExprLoc(), "aligned_result");
- Result = Builder.CreatePointerCast(Result, Args.SrcType);
+ Result = Builder.CreatePointerCast(Result, SrcType);
// Emit an alignment assumption to ensure that the new alignment is
// propagated to loads/stores, etc.
- emitAlignmentAssumption(Result, E, E->getExprLoc(), Args.Alignment);
+ emitAlignmentAssumption(Result, E, E->getExprLoc(), Alignment);
}
- assert(Result->getType() == Args.SrcType);
- return RValue::get(Result);
+ assert(Result->getType() == SrcType);
+ return Result;
+}
+
+/// Generate (x & ~(y-1)) to align down or ((x+(y-1)) & ~(y-1)) to align up.
+/// Note: For pointer types we can avoid ptrtoint/inttoptr pairs by using the
+/// llvm.ptrmask instrinsic (with a GEP before in the align_up case).
+/// TODO: actually use ptrmask once most optimization passes know about it.
+RValue CodeGenFunction::EmitBuiltinAlignTo(const CallExpr *E, bool AlignUp) {
+ BuiltinAlignArgs Args(E, *this);
+ return RValue::get(EmitBuiltinAlignTo(Args.Src, Args.SrcType, Args.Alignment,
+ Args.Mask, Args.IntType, E, AlignUp));
+}
+
+llvm::Value *CodeGenFunction::EmitBuiltinAlignTo(llvm::Value *Src,
+ llvm::Value *Align,
+ const Expr *E, bool AlignUp) {
+ llvm::Type *SrcType = Src->getType();
+ llvm::IntegerType *IntType = nullptr;
+ if (SrcType->isPointerTy()) {
+ IntType = IntegerType::get(
+ getLLVMContext(), CGM.getDataLayout().getIndexTypeSizeInBits(SrcType));
+ } else {
+ assert(SrcType->isIntegerTy());
+ IntType = cast<llvm::IntegerType>(SrcType);
+ }
+ llvm::Value *Alignment = Align;
+ auto *One = llvm::ConstantInt::get(IntType, 1);
+ llvm::Value *Mask = Builder.CreateSub(Alignment, One, "mask");
+ return EmitBuiltinAlignTo(Src, SrcType, Alignment, Mask, IntType, E, AlignUp);
}
Value *CodeGenFunction::EmitWebAssemblyBuiltinExpr(unsigned BuiltinID,
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
