2 files changed, 18 insertions, 5 deletions
diff --git a/lib/Target/AArch64/AArch64ISelLowering.cpp b/lib/Target/AArch64/AArch64ISelLowering.cpp
index 4ecfbe9e2280..9b73c5e9d952 100644
--- a/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -10133,6 +10133,7 @@ void AArch64TargetLowering::insertCopiesSplitCSR(
 
   const TargetInstrInfo *TII = Subtarget->getInstrInfo();
   MachineRegisterInfo *MRI = &Entry->getParent()->getRegInfo();
+  MachineBasicBlock::iterator MBBI = Entry->begin();
   for (const MCPhysReg *I = IStart; *I; ++I) {
     const TargetRegisterClass *RC = nullptr;
     if (AArch64::GPR64RegClass.contains(*I))
@@ -10152,13 +10153,13 @@ void AArch64TargetLowering::insertCopiesSplitCSR(
                Attribute::NoUnwind) &&
            "Function should be nounwind in insertCopiesSplitCSR!");
     Entry->addLiveIn(*I);
-    BuildMI(*Entry, Entry->begin(), DebugLoc(), TII->get(TargetOpcode::COPY),
-            NewVR)
+    BuildMI(*Entry, MBBI, DebugLoc(), TII->get(TargetOpcode::COPY), NewVR)
         .addReg(*I);
 
+    // Insert the copy-back instructions right before the terminator.
     for (auto *Exit : Exits)
-      BuildMI(*Exit, Exit->begin(), DebugLoc(), TII->get(TargetOpcode::COPY),
-              *I)
+      BuildMI(*Exit, Exit->getFirstTerminator(), DebugLoc(),
+              TII->get(TargetOpcode::COPY), *I)
           .addReg(NewVR);
   }
 }
diff --git a/lib/Target/AArch64/MCTargetDesc/AArch64ELFStreamer.cpp b/lib/Target/AArch64/MCTargetDesc/AArch64ELFStreamer.cpp
index d26604f5765d..685907a2178e 100644
--- a/lib/Target/AArch64/MCTargetDesc/AArch64ELFStreamer.cpp
+++ b/lib/Target/AArch64/MCTargetDesc/AArch64ELFStreamer.cpp
@@ -112,9 +112,21 @@ public:
     MCELFStreamer::EmitInstruction(Inst, STI);
   }
 
+  /// Emit a 32-bit value as an instruction. This is only used for the .inst
+  /// directive, EmitInstruction should be used in other cases.
   void emitInst(uint32_t Inst) {
+    char Buffer[4];
+
+    // We can't just use EmitIntValue here, as that will emit a data mapping
+    // symbol, and swap the endianness on big-endian systems (instructions are
+    // always little-endian).
+    for (unsigned I = 0; I < 4; ++I) {
+      Buffer[I] = uint8_t(Inst);
+      Inst >>= 8;
+    }
+
     EmitA64MappingSymbol();
-    MCELFStreamer::EmitIntValue(Inst, 4);
+    MCELFStreamer::EmitBytes(StringRef(Buffer, 4));
   }
 
   /// This is one of the functions used to emit data into an ELF section, so the