diff --git a/llvm/lib/CodeGen/GlobalISel/CallLowering.cpp b/llvm/lib/CodeGen/GlobalISel/CallLowering.cpp
--- a/llvm/lib/CodeGen/GlobalISel/CallLowering.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/CallLowering.cpp
@@ -698,10 +698,12 @@
                       ValTy, extendOpFromFlags(Args[i].Flags[0]));
     }
 
+    bool BigEndianPartOrdering = TLI->hasBigEndianPartOrdering(OrigVT, DL);
     for (unsigned Part = 0; Part < NumParts; ++Part) {
       Register ArgReg = Args[i].Regs[Part];
       // There should be Regs.size() ArgLocs per argument.
-      VA = ArgLocs[j + Part];
+      unsigned Idx = BigEndianPartOrdering ? NumParts - 1 - Part : Part;
+      CCValAssign &VA = ArgLocs[j + Idx];
       const ISD::ArgFlagsTy Flags = Args[i].Flags[Part];
 
       if (VA.isMemLoc() && !Flags.isByVal()) {
diff --git a/llvm/test/CodeGen/M68k/GlobalISel/irtranslator-ret.ll b/llvm/test/CodeGen/M68k/GlobalISel/irtranslator-ret.ll
--- a/llvm/test/CodeGen/M68k/GlobalISel/irtranslator-ret.ll
+++ b/llvm/test/CodeGen/M68k/GlobalISel/irtranslator-ret.ll
@@ -206,8 +206,8 @@
   ; CHECK:   [[G_LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[G_F_I2]](p0)
   ; CHECK:   [[G_MERGE_VAL:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[G_LOAD1]](s32), [[G_LOAD2]](s32)
   ; CHECK:   [[G_UNMERGE_VAL1:%[0-9]+]]:_(s32), [[G_UNMERGE_VAL2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[G_MERGE_VAL]](s64)
-  ; CHECK:   $d0 = COPY [[G_UNMERGE_VAL1]](s32)
-  ; CHECK:   $d1 = COPY [[G_UNMERGE_VAL2]](s32)
-  ; CHECK:   RTS implicit $d0, implicit $d1
+  ; CHECK:   $d1 = COPY [[G_UNMERGE_VAL1]](s32)
+  ; CHECK:   $d0 = COPY [[G_UNMERGE_VAL2]](s32)
+  ; CHECK:   RTS implicit $d1, implicit $d0
   ret i64 %a
 }