Index: lib/Transforms/Scalar/RewriteStatepointsForGC.cpp =================================================================== --- lib/Transforms/Scalar/RewriteStatepointsForGC.cpp +++ lib/Transforms/Scalar/RewriteStatepointsForGC.cpp @@ -2392,7 +2392,23 @@ LLVMContext &Ctx = F.getContext(); MDBuilder Builder(Ctx); + // Set of invariantstart instructions that we need to remove. + // Use this to avoid invalidating the instruction iterator. + SmallVector InvariantStartInstructions; + for (Instruction &I : instructions(F)) { + // invariant.start on memory location implies that the referenced memory + // location is constant and unchanging. This is no longer true after + // RewriteStatepointsForGC runs because there can be calls to gc.statepoint + // which frees the entire heap and the presence of invariant.start allows + // the optimizer to sink the load of a memory location past a statepoint, + // which is incorrect. + if (auto *II = dyn_cast(&I)) + if (II->getIntrinsicID() == Intrinsic::invariant_start) { + InvariantStartInstructions.push_back(II); + continue; + } + if (const MDNode *MD = I.getMetadata(LLVMContext::MD_tbaa)) { assert(MD->getNumOperands() < 5 && "unrecognized metadata shape!"); bool IsImmutableTBAA = @@ -2422,6 +2438,18 @@ RemoveNonValidAttrAtIndex(Ctx, CS, AttributeList::ReturnIndex); } } + + // Delete the invariant.start instructions and any corresponding uses that + // don't have further uses, for example invariant.end. + for (auto *II : InvariantStartInstructions) { + for (auto *U : II->users()) + if (auto *I = dyn_cast(U)) + if (U->hasNUses(0)) + I->eraseFromParent(); + // We cannot just delete the remaining uses of II, so we RAUW undef. + II->replaceAllUsesWith(UndefValue::get(II->getType())); + II->eraseFromParent(); + } } /// Returns true if this function should be rewritten by this pass. The main Index: test/Transforms/RewriteStatepointsForGC/drop-invalid-metadata.ll =================================================================== --- test/Transforms/RewriteStatepointsForGC/drop-invalid-metadata.ll +++ test/Transforms/RewriteStatepointsForGC/drop-invalid-metadata.ll @@ -75,6 +75,59 @@ ret void } +; invariant.start allows us to sink the load past the baz statepoint call into taken block, which is +; incorrect. remove the invariant.start and RAUW undef. +define void @test_inv_start(i1 %cond, i32 addrspace(1)* addrspace(1)* %p, i32 %x, i32 addrspace(1)* %q) gc "statepoint-example" { +; CHECK-LABEL: test_inv_start +; CHECK-NOT: invariant.start +; CHECK: gc.statepoint + %v1 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(1)* %p + %invst = call {}* @llvm.invariant.start.p1i32(i64 1, i32 addrspace(1)* %v1) + %v2 = load i32, i32 addrspace(1)* %v1 + call void @baz(i32 %x) + br i1 %cond, label %taken, label %untaken + +; CHECK-LABEL: taken: +; CHECK-NOT: llvm.invariant.end +taken: + store i32 %v2, i32 addrspace(1)* %q, align 16 + call void @llvm.invariant.end.p1i32({}* %invst, i64 4, i32 addrspace(1)* %v1) + ret void + +; CHECK-LABEL: untaken: +; CHECK: gc.statepoint +untaken: + %foo = call i32 @escaping.invariant.start({}* %invst) + call void @dummy(i32 %foo) + ret void +} + +; invariant.start and end is removed. No other uses. +define void @test_inv_start2(i1 %cond, i32 addrspace(1)* addrspace(1)* %p, i32 %x, i32 addrspace(1)* %q) gc "statepoint-example" { +; CHECK-LABEL: test_inv_start2 +; CHECK-NOT: invariant.start +; CHECK: gc.statepoint + %v1 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(1)* %p + %invst = call {}* @llvm.invariant.start.p1i32(i64 1, i32 addrspace(1)* %v1) + %v2 = load i32, i32 addrspace(1)* %v1 + call void @baz(i32 %x) + br i1 %cond, label %taken, label %untaken + +; CHECK-LABEL: taken: +; CHECK-NOT: llvm.invariant.end +taken: + store i32 %v2, i32 addrspace(1)* %q, align 16 + call void @llvm.invariant.end.p1i32({}* %invst, i64 4, i32 addrspace(1)* %v1) + ret void + +; CHECK-LABEL: untaken: +untaken: + ret void +} +declare {}* @llvm.invariant.start.p1i32(i64, i32 addrspace(1)* nocapture) nounwind readonly +declare void @llvm.invariant.end.p1i32({}*, i64, i32 addrspace(1)* nocapture) nounwind +declare i32 @escaping.invariant.start({}*) nounwind +declare void @dummy(i32) declare token @llvm.experimental.gc.statepoint.p0f_isVoidi32f(i64, i32, void (i32)*, i32, i32, ...) ; Function Attrs: nounwind readonly