diff --git a/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp b/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
@@ -27,6 +27,7 @@
 #include "AMDGPU.h"
 #include "GCNSubtarget.h"
 #include "SIMachineFunctionInfo.h"
+#include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/Analysis/CallGraph.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
@@ -105,15 +106,19 @@
   const TargetMachine &TM = TPC->getTM<TargetMachine>();
   bool HasIndirectCall = false;
 
-  for (Function &F : M) {
-    if (F.isDeclaration())
+  CallGraph CG = CallGraph(M);
+  auto End = po_end(&CG);
+
+  for (auto IT = po_begin(&CG); IT != End; ++IT) {
+    Function *F = IT->getFunction();
+    if (!F || F->isDeclaration())
       continue;
 
-    MachineFunction *MF = MMI.getMachineFunction(F);
+    MachineFunction *MF = MMI.getMachineFunction(*F);
     assert(MF && "function must have been generated already");
 
     auto CI = CallGraphResourceInfo.insert(
-        std::make_pair(&F, SIFunctionResourceInfo()));
+        std::make_pair(F, SIFunctionResourceInfo()));
     SIFunctionResourceInfo &Info = CI.first->second;
     assert(CI.second && "should only be called once per function");
     Info = analyzeResourceUsage(*MF, TM);
diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-resource-usage-function-ordering.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-resource-usage-function-ordering.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-resource-usage-function-ordering.ll
@@ -0,0 +1,28 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 --amdhsa-code-object-version=4 -enable-misched=0 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s
+; RUN: llc -mattr=-xnack -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=4 -mcpu=gfx803 -enable-misched=0 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s
+; RUN: llc -mattr=-xnack -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=4 -mcpu=gfx900 -enable-misched=0 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s
+; RUN: llc -mattr=-xnack -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=4 -mcpu=gfx1010 -enable-misched=0 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s
+
+; CHECK: amdhsa.kernels:
+
+; test a kernel that occurs before its callee in the module
+; CHECK:   - .args:
+; CHECK:     .private_segment_fixed_size: 0
+define amdgpu_kernel void @test1() {
+  call void @f()
+  ret void
+}
+
+define void @f() #0 {
+  ret void
+}
+
+; test a kernel that occurs after its callee in the module
+; CHECK:   - .args:
+; CHECK:     .private_segment_fixed_size: 0
+define amdgpu_kernel void @test2() {
+  call void @f()
+  ret void
+}
+
+attributes #0 = { norecurse }
\ No newline at end of file