[AMDGPU] Lower LDS in functions without sanitize_address in amdgpu-sw-lower-lds. (#131147)

Background:
"amdgpu-sw-lower-lds" pass lowers LDS accesses based on
"sanitize_address" attribute being tagged to kernel or non-kernels.
"amdgpu-sw-lower-lds" pass ideally should either lower all LDS accesses
or should not lower any based on if asan is enabled.

Issue:
But there has been cases when instrumented and non instrumented bitcodes
are linked and this is leading to few LDS being lowered correctly while
others are not. This typically leads to below error in the subsequent
pass.
"Module cannot mix absolute and non-absolute LDS GVs"

Fix:
This patch fixes this issue, by checking if any kernels in module are
tagged with "sanitize_address" attribute and then lowers all the LDS
accesses in all other kernels and non-kernels even though they do not
have "sanitize_address" attribute.

Author: skc7

llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp

@@ -298,8 +298,7 @@ void AMDGPUSwLowerLDS::getUsesOfLDSByNonKernels() {
     for (User *V : GV->users()) {
       if (auto *I = dyn_cast<Instruction>(V)) {
         Function *F = I->getFunction();
-        if (!isKernelLDS(F) && F->hasFnAttribute(Attribute::SanitizeAddress) &&
-            !F->isDeclaration())
+        if (!isKernelLDS(F) && !F->isDeclaration())
           FuncLDSAccessInfo.NonKernelToLDSAccessMap[F].insert(GV);
       }
     }
@@ -1134,6 +1133,17 @@ void AMDGPUSwLowerLDS::initAsanInfo() {
   AsanInfo.Offset = Offset;
 }
 
+static bool hasFnWithSanitizeAddressAttr(FunctionVariableMap &LDSAccesses) {
+  for (auto &K : LDSAccesses) {
+    Function *F = K.first;
+    if (!F)
+      continue;
+    if (F->hasFnAttribute(Attribute::SanitizeAddress))
+      return true;
+  }
+  return false;
+}
+
 bool AMDGPUSwLowerLDS::run() {
   bool Changed = false;
 
@@ -1144,6 +1154,14 @@ bool AMDGPUSwLowerLDS::run() {
   // Get all the direct and indirect access of LDS for all the kernels.
   LDSUsesInfoTy LDSUsesInfo = getTransitiveUsesOfLDS(CG, M);
 
+  // Flag to decide whether to lower all the LDS accesses
+  // based on sanitize_address attribute.
+  bool LowerAllLDS = hasFnWithSanitizeAddressAttr(LDSUsesInfo.direct_access) ||
+                     hasFnWithSanitizeAddressAttr(LDSUsesInfo.indirect_access);
+
+  if (!LowerAllLDS)
+    return Changed;
+
   // Utility to group LDS access into direct, indirect, static and dynamic.
   auto PopulateKernelStaticDynamicLDS = [&](FunctionVariableMap &LDSAccesses,
                                             bool DirectAccess) {
@@ -1153,8 +1171,6 @@ bool AMDGPUSwLowerLDS::run() {
         continue;
 
       assert(isKernelLDS(F));
-      if (!F->hasFnAttribute(Attribute::SanitizeAddress))
-        continue;
 
       // Only inserts if key isn't already in the map.
       FuncLDSAccessInfo.KernelToLDSParametersMap.insert(
@@ -1221,6 +1237,7 @@ bool AMDGPUSwLowerLDS::run() {
   // Get non-kernels with LDS ptr as argument and called by kernels.
   getNonKernelsWithLDSArguments(CG);
 
+  // Lower LDS accesses in non-kernels.
   if (!FuncLDSAccessInfo.NonKernelToLDSAccessMap.empty() ||
       !FuncLDSAccessInfo.NonKernelsWithLDSArgument.empty()) {
     NonKernelLDSParameters NKLDSParams;

llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-lower-all.ll

@@ -0,0 +1,127 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals all --version 5
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -amdgpu-asan-instrument-lds=false -mtriple=amdgcn-amd-amdhsa | FileCheck %s
+
+; Test to check if static LDS accesses in kernels without sanitize_address attribute are lowered if
+; other kernels in module have sanitize_address attribute.
+@lds_1 = internal addrspace(3) global [1 x i8] poison, align 4
+@lds_2 = internal addrspace(3) global [1 x i32] poison, align 8
+
+define amdgpu_kernel void @k0() sanitize_address {
+; CHECK-LABEL: define amdgpu_kernel void @k0(
+; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  [[WID:.*]]:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label %[[MALLOC:.*]], label %[[BB20:.*]]
+; CHECK:       [[MALLOC]]:
+; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 0), align 4
+; CHECK-NEXT:    [[TMP7:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 2), align 4
+; CHECK-NEXT:    [[TMP8:%.*]] = add i32 [[TMP6]], [[TMP7]]
+; CHECK-NEXT:    [[TMP9:%.*]] = zext i32 [[TMP8]] to i64
+; CHECK-NEXT:    [[TMP10:%.*]] = call ptr @llvm.returnaddress(i32 0)
+; CHECK-NEXT:    [[TMP11:%.*]] = ptrtoint ptr [[TMP10]] to i64
+; CHECK-NEXT:    [[TMP12:%.*]] = call i64 @__asan_malloc_impl(i64 [[TMP9]], i64 [[TMP11]])
+; CHECK-NEXT:    [[TMP13:%.*]] = inttoptr i64 [[TMP12]] to ptr addrspace(1)
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP13]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP13]], i64 8
+; CHECK-NEXT:    [[TMP15:%.*]] = ptrtoint ptr addrspace(1) [[TMP14]] to i64
+; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP15]], i64 24)
+; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP13]], i64 33
+; CHECK-NEXT:    [[TMP17:%.*]] = ptrtoint ptr addrspace(1) [[TMP16]] to i64
+; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP17]], i64 31)
+; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP13]], i64 68
+; CHECK-NEXT:    [[TMP19:%.*]] = ptrtoint ptr addrspace(1) [[TMP18]] to i64
+; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP19]], i64 28)
+; CHECK-NEXT:    br label %[[BB20]]
+; CHECK:       [[BB20]]:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, %[[WID]] ], [ true, %[[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP21:%.*]] = load ptr addrspace(1), ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    [[TMP22:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 4
+; CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP22]]
+; CHECK-NEXT:    [[TMP24:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 0), align 4
+; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP24]]
+; CHECK-NEXT:    [[TMP26:%.*]] = ptrtoint ptr addrspace(3) [[TMP23]] to i32
+; CHECK-NEXT:    [[TMP27:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP21]], i32 [[TMP26]]
+; CHECK-NEXT:    store i8 7, ptr addrspace(1) [[TMP27]], align 4
+; CHECK-NEXT:    [[TMP28:%.*]] = ptrtoint ptr addrspace(3) [[TMP25]] to i32
+; CHECK-NEXT:    [[TMP29:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP21]], i32 [[TMP28]]
+; CHECK-NEXT:    store i32 8, ptr addrspace(1) [[TMP29]], align 2
+; CHECK-NEXT:    br label %[[CONDFREE:.*]]
+; CHECK:       [[CONDFREE]]:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label %[[FREE:.*]], label %[[END:.*]]
+; CHECK:       [[FREE]]:
+; CHECK-NEXT:    [[TMP30:%.*]] = call ptr @llvm.returnaddress(i32 0)
+; CHECK-NEXT:    [[TMP31:%.*]] = ptrtoint ptr [[TMP30]] to i64
+; CHECK-NEXT:    [[TMP32:%.*]] = ptrtoint ptr addrspace(1) [[TMP21]] to i64
+; CHECK-NEXT:    call void @__asan_free_impl(i64 [[TMP32]], i64 [[TMP31]])
+; CHECK-NEXT:    br label %[[END]]
+; CHECK:       [[END]]:
+; CHECK-NEXT:    ret void
+;
+  store i8 7, ptr addrspace(3) @lds_1, align 4
+  store i32 8, ptr addrspace(3) @lds_2, align 2
+  ret void
+}
+
+define amdgpu_kernel void @k1() {
+; CHECK-LABEL: define amdgpu_kernel void @k1(
+; CHECK-SAME: ) #[[ATTR1:[0-9]+]] {
+; CHECK-NEXT:  [[WID:.*]]:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label %[[MALLOC:.*]], label %[[BB18:.*]]
+; CHECK:       [[MALLOC]]:
+; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 1, i32 0), align 4
+; CHECK-NEXT:    [[TMP7:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 1, i32 2), align 4
+; CHECK-NEXT:    [[TMP8:%.*]] = add i32 [[TMP6]], [[TMP7]]
+; CHECK-NEXT:    [[TMP9:%.*]] = zext i32 [[TMP8]] to i64
+; CHECK-NEXT:    [[TMP10:%.*]] = call ptr @llvm.returnaddress(i32 0)
+; CHECK-NEXT:    [[TMP11:%.*]] = ptrtoint ptr [[TMP10]] to i64
+; CHECK-NEXT:    [[TMP12:%.*]] = call i64 @__asan_malloc_impl(i64 [[TMP9]], i64 [[TMP11]])
+; CHECK-NEXT:    [[TMP13:%.*]] = inttoptr i64 [[TMP12]] to ptr addrspace(1)
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP13]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k1, align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP13]], i64 8
+; CHECK-NEXT:    [[TMP15:%.*]] = ptrtoint ptr addrspace(1) [[TMP14]] to i64
+; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP15]], i64 24)
+; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP13]], i64 36
+; CHECK-NEXT:    [[TMP17:%.*]] = ptrtoint ptr addrspace(1) [[TMP16]] to i64
+; CHECK-NEXT:    call void @__asan_poison_region(i64 [[TMP17]], i64 28)
+; CHECK-NEXT:    br label %[[BB18]]
+; CHECK:       [[BB18]]:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, %[[WID]] ], [ true, %[[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP19:%.*]] = load ptr addrspace(1), ptr addrspace(3) @llvm.amdgcn.sw.lds.k1, align 8
+; CHECK-NEXT:    [[TMP20:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 1, i32 0), align 4
+; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k1, i32 [[TMP20]]
+; CHECK-NEXT:    [[TMP22:%.*]] = ptrtoint ptr addrspace(3) [[TMP21]] to i32
+; CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP19]], i32 [[TMP22]]
+; CHECK-NEXT:    store i32 9, ptr addrspace(1) [[TMP23]], align 2
+; CHECK-NEXT:    br label %[[CONDFREE:.*]]
+; CHECK:       [[CONDFREE]]:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label %[[FREE:.*]], label %[[END:.*]]
+; CHECK:       [[FREE]]:
+; CHECK-NEXT:    [[TMP24:%.*]] = call ptr @llvm.returnaddress(i32 0)
+; CHECK-NEXT:    [[TMP25:%.*]] = ptrtoint ptr [[TMP24]] to i64
+; CHECK-NEXT:    [[TMP26:%.*]] = ptrtoint ptr addrspace(1) [[TMP19]] to i64
+; CHECK-NEXT:    call void @__asan_free_impl(i64 [[TMP26]], i64 [[TMP25]])
+; CHECK-NEXT:    br label %[[END]]
+; CHECK:       [[END]]:
+; CHECK-NEXT:    ret void
+;
+  store i32 9, ptr addrspace(3) @lds_2, align 2
+  ret void
+}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 4, !"nosanitize_address", i32 1}

llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-lower-none.ll

@@ -0,0 +1,37 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals all --version 5
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -amdgpu-asan-instrument-lds=false -mtriple=amdgcn-amd-amdhsa | FileCheck %s
+
+; Test to check if LDS accesses in kernels without sanitize_address attribute are not lowered
+; if all other kernels don't have sanitize_address attribute.
+@lds_1 = internal addrspace(3) global [1 x i8] poison, align 4
+@lds_2 = internal addrspace(3) global [1 x i32] poison, align 8
+
+;.
+; CHECK: @lds_1 = internal addrspace(3) global [1 x i8] poison, align 4
+; CHECK: @lds_2 = internal addrspace(3) global [1 x i32] poison, align 8
+;.
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: define amdgpu_kernel void @k0() {
+; CHECK-NEXT:    store i8 7, ptr addrspace(3) @lds_1, align 4
+; CHECK-NEXT:    store i32 8, ptr addrspace(3) @lds_2, align 2
+; CHECK-NEXT:    ret void
+;
+  store i8 7, ptr addrspace(3) @lds_1, align 4
+  store i32 8, ptr addrspace(3) @lds_2, align 2
+  ret void
+}
+
+define amdgpu_kernel void @k1() {
+; CHECK-LABEL: define amdgpu_kernel void @k1() {
+; CHECK-NEXT:    store i32 9, ptr addrspace(3) @lds_2, align 2
+; CHECK-NEXT:    ret void
+;
+  store i32 9, ptr addrspace(3) @lds_2, align 2
+  ret void
+}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 4, !"nosanitize_address", i32 1}
+;.
+; CHECK: [[META0:![0-9]+]] = !{i32 4, !"nosanitize_address", i32 1}
+;.