statepoint-call-lowering: use statepoint-example gc

[artagnon]

Summary

Mechanical conversion of statepoint-call-lowering to use the
example-statepoint gc.

[artagnon]

Convert remaining statepoint tests too

[reames]

LGTM

test/CodeGen/X86/statepoint-call-lowering.ll

47

FYI, it should only be the pointers that are being relocated that need updated, not the return value of the function.

[artagnon]

test/CodeGen/X86/statepoint-call-lowering.ll

47

Ah, result of a mechanical replacement. Will fix before committing.

[artagnon]

Made required changes.

[reames]

As I said before, LGTM.

[artagnon]

Philip Reames wrote:

As I said before, LGTM.

Please hit "Accept Revision" when replying with LGTM on Phabricator
next time; I accepted my own revision the last two times.

[reames]

If you list the revision in the commit, it wouldn't matter. It'll be
automatically closed.

p.s. Phabricator (and it's workflow) is not the canonical review
process. Email is. Phabricator is used within the workflow, not as a
replacement for it. Please see
http://llvm.org/docs/DeveloperPolicy.html#code-reviews

test/CodeGen/X86/statepoint-call-lowering.ll

 ; RUN: llc < %s | FileCheck %s
 ; This file contains a collection of basic tests to ensure we didn't
 ; screw up normal call lowering when there are no deopt or gc arguments.
 
 target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-pc-linux-gnu"
 
 declare zeroext i1 @return_i1()
 declare zeroext i32 @return_i32()
-declare i32* @return_i32ptr()
+declare i32 addrspace(1)* @return_i32ptr()
 declare float @return_float()
 
-define i1 @test_i1_return() {
+define i1 @test_i1_return() gc "statepoint-example" {
 ; CHECK-LABEL: test_i1_return
 ; This is just checking that a i1 gets lowered normally when there's no extra
 ; state arguments to the statepoint
 ; CHECK: pushq %rax
 ; CHECK: callq return_i1
 ; CHECK: popq %rdx
 ; CHECK: retq
 entry:
   %safepoint_token = tail call i32 (i1 ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_i1f(i1 ()* @return_i1, i32 0, i32 0, i32 0)
   %call1 = call zeroext i1 @llvm.experimental.gc.result.int.i1(i32 %safepoint_token)
   ret i1 %call1
 }
 
-define i32 @test_i32_return() {
+define i32 @test_i32_return() gc "statepoint-example" {
 ; CHECK-LABEL: test_i32_return
 ; CHECK: pushq %rax
 ; CHECK: callq return_i32
 ; CHECK: popq %rdx
 ; CHECK: retq
 entry:
   %safepoint_token = tail call i32 (i32 ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_i32f(i32 ()* @return_i32, i32 0, i32 0, i32 0)
   %call1 = call zeroext i32 @llvm.experimental.gc.result.int.i32(i32 %safepoint_token)
   ret i32 %call1
 }
 
-define i32* @test_i32ptr_return() {
+define i32 addrspace(1)* @test_i32ptr_return() gc "statepoint-example" {
 ; CHECK-LABEL: test_i32ptr_return
 ; CHECK: pushq %rax
 ; CHECK: callq return_i32ptr
 ; CHECK: popq %rdx
 ; CHECK: retq
 entry:
-  %safepoint_token = tail call i32 (i32* ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_p0i32f(i32* ()* @return_i32ptr, i32 0, i32 0, i32 0)
-  %call1 = call i32* @llvm.experimental.gc.result.ptr.p0i32(i32 %safepoint_token)
-  ret i32* %call1
+  %safepoint_token = tail call i32 (i32 addrspace(1)* ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_p1i32f(i32 addrspace(1)* ()* @return_i32ptr, i32 0, i32 0, i32 0)
+  %call1 = call i32 addrspace(1)* @llvm.experimental.gc.result.ptr.p1i32(i32 %safepoint_token)
+  ret i32 addrspace(1)* %call1
 }
 
-define float @test_float_return() {
+define float @test_float_return() gc "statepoint-example" {
 ; CHECK-LABEL: test_float_return
 ; CHECK: pushq %rax
 ; CHECK: callq return_float
 ; CHECK: popq %rax
 ; CHECK: retq
 entry:
   %safepoint_token = tail call i32 (float ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_f32f(float ()* @return_float, i32 0, i32 0, i32 0)
   %call1 = call float @llvm.experimental.gc.result.float.f32(i32 %safepoint_token)
   ret float %call1
 }
 
-define i1 @test_relocate(i32* %a) {
+define i1 @test_relocate(i32 addrspace(1)* %a) gc "statepoint-example" {
 ; CHECK-LABEL: test_relocate
 ; Check that an ununsed relocate has no code-generation impact
 ; CHECK: pushq %rax
 ; CHECK: callq return_i1
 ; CHECK-NEXT: .Ltmp13:
 ; CHECK-NEXT: popq %rdx
 ; CHECK-NEXT: retq
 entry:
-  %safepoint_token = tail call i32 (i1 ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_i1f(i1 ()* @return_i1, i32 0, i32 0, i32 0, i32* %a)
-  %call1 = call i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 4, i32 4)
+  %safepoint_token = tail call i32 (i1 ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_i1f(i1 ()* @return_i1, i32 0, i32 0, i32 0, i32 addrspace(1)* %a)
+  %call1 = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token, i32 4, i32 4)
   %call2 = call zeroext i1 @llvm.experimental.gc.result.int.i1(i32 %safepoint_token)
   ret i1 %call2
 }
 
 declare i32 @llvm.experimental.gc.statepoint.p0f_i1f(i1 ()*, i32, i32, ...)
 declare i1 @llvm.experimental.gc.result.int.i1(i32)
 
 declare i32 @llvm.experimental.gc.statepoint.p0f_i32f(i32 ()*, i32, i32, ...)
 declare i32 @llvm.experimental.gc.result.int.i32(i32)
 
-declare i32 @llvm.experimental.gc.statepoint.p0f_p0i32f(i32* ()*, i32, i32, ...)
-declare i32* @llvm.experimental.gc.result.ptr.p0i32(i32)
+declare i32 @llvm.experimental.gc.statepoint.p0f_p1i32f(i32 addrspace(1)* ()*, i32, i32, ...)
+declare i32 addrspace(1)* @llvm.experimental.gc.result.ptr.p1i32(i32)
 
 declare i32 @llvm.experimental.gc.statepoint.p0f_f32f(float ()*, i32, i32, ...)
 declare float @llvm.experimental.gc.result.float.f32(i32)
 
-declare i32* @llvm.experimental.gc.relocate.p0i32(i32, i32, i32)
+declare i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32, i32, i32)

test/CodeGen/X86/statepoint-stack-usage.ll

 ; RUN: llc < %s | FileCheck %s
 
 target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-pc-linux-gnu"
 
 ; This test is checking to make sure that we reuse the same stack slots
 ; for GC values spilled over two different call sites.  Since the order
 ; of GC arguments differ, niave lowering code would insert loads and 
 ; stores to rearrange items on the stack.  We need to make sure (for
 ; performance) that this doesn't happen.
-define i32 @back_to_back_calls(i32* %a, i32* %b, i32* %c) #1 {
+define i32 @back_to_back_calls(i32 addrspace(1)* %a, i32 addrspace(1)* %b, i32 addrspace(1)* %c) #1 {
 ; CHECK-LABEL: back_to_back_calls
 ; The exact stores don't matter, but there need to be three stack slots created
 ; CHECK: movq %rdx, 16(%rsp)
 ; CHECK: movq %rdi, 8(%rsp)
 ; CHECK: movq %rsi, (%rsp)
-  %safepoint_token = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32* %a, i32* %b, i32* %c)
-  %a1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 9)
-  %b1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 10)
-  %c1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 11)
+  %safepoint_token = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32 addrspace(1)* %a, i32 addrspace(1)* %b, i32 addrspace(1)* %c)
+  %a1 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token, i32 9, i32 9)
+  %b1 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token, i32 9, i32 10)
+  %c1 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token, i32 9, i32 11)
 ; CHECK: callq
 ; This is the key check.  There should NOT be any memory moves here
 ; CHECK-NOT: movq
-  %safepoint_token2 = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32* %c1, i32* %b1, i32* %a1)
-  %a2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 11)
-  %b2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 10)
-  %c2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 9)
+  %safepoint_token2 = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32 addrspace(1)* %c1, i32 addrspace(1)* %b1, i32 addrspace(1)* %a1)
+  %a2 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token2, i32 9, i32 11)
+  %b2 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token2, i32 9, i32 10)
+  %c2 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token2, i32 9, i32 9)
 ; CHECK: callq
   ret i32 1
 }
 
 ; This test simply checks that minor changes in vm state don't prevent slots
 ; being reused for gc values.  
-define i32 @reserve_first(i32* %a, i32* %b, i32* %c) #1 {
+define i32 @reserve_first(i32 addrspace(1)* %a, i32 addrspace(1)* %b, i32 addrspace(1)* %c) #1 {
 ; CHECK-LABEL: reserve_first
 ; The exact stores don't matter, but there need to be three stack slots created
 ; CHECK: movq %rdx, 16(%rsp)
 ; CHECK: movq %rdi, 8(%rsp)
 ; CHECK: movq %rsi, (%rsp)
-  %safepoint_token = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32* %a, i32* %b, i32* %c)
-  %a1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 9)
-  %b1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 10)
-  %c1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 11)
+  %safepoint_token = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32 addrspace(1)* %a, i32 addrspace(1)* %b, i32 addrspace(1)* %c)
+  %a1 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token, i32 9, i32 9)
+  %b1 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token, i32 9, i32 10)
+  %c1 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token, i32 9, i32 11)
 ; CHECK: callq
 ; This is the key check.  There should NOT be any memory moves here
 ; CHECK-NOT: movq
-  %safepoint_token2 = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32* %a1, i32 0, i32* %c1, i32 0, i32 0, i32* %c1, i32* %b1, i32* %a1)
-  %a2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 11)
-  %b2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 10)
-  %c2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 9)
+  %safepoint_token2 = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 addrspace(1)* %a1, i32 0, i32 addrspace(1)* %c1, i32 0, i32 0, i32 addrspace(1)* %c1, i32 addrspace(1)* %b1, i32 addrspace(1)* %a1)
+  %a2 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token2, i32 9, i32 11)
+  %b2 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token2, i32 9, i32 10)
+  %c2 = tail call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token2, i32 9, i32 9)
 ; CHECK: callq
   ret i32 1
 }
 
 ; Function Attrs: nounwind
-declare i32* @llvm.experimental.gc.relocate.p0i32(i32, i32, i32) #3
+declare i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32, i32, i32) #3
 
 declare i32 @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()*, i32, i32, ...)
 
 attributes #1 = { uwtable }

test/CodeGen/X86/statepoint-stackmap-format.ll

 ; RUN: llc < %s | FileCheck %s
 ; This test is a sanity check to ensure statepoints are generating StackMap
 ; sections correctly.  This is not intended to be a rigorous test of the 
 ; StackMap format (see the stackmap tests for that).
 
 target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-pc-linux-gnu"
 
 declare zeroext i1 @return_i1()
 
-define i1 @test(i32 addrspace(1)* %ptr) {
+define i1 @test(i32 addrspace(1)* %ptr) gc "statepoint-example" {
 ; CHECK-LABEL: test
 ; Do we see one spill for the local value and the store to the
 ; alloca?
 ; CHECK: subq $24, %rsp
 ; CHECK: movq $0, 8(%rsp)
 ; CHECK: movq %rdi, (%rsp)
 ; CHECK: callq return_i1
 ; CHECK: addq $24, %rsp