Index: llvm/trunk/lib/Target/AArch64/AArch64.td
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64.td
+++ llvm/trunk/lib/Target/AArch64/AArch64.td
@@ -385,6 +385,14 @@
 include "AArch64SystemOperands.td"
 
 //===----------------------------------------------------------------------===//
+// Access to privileged registers
+//===----------------------------------------------------------------------===//
+
+foreach i = 1-3 in
+def FeatureUseEL#i#ForTP : SubtargetFeature<"tpidr-el"#i, "UseEL"#i#"ForTP",
+  "true", "Permit use of TPIDR_EL"#i#" for the TLS base">;
+
+//===----------------------------------------------------------------------===//
 // AArch64 Processors supported.
 //
 include "AArch64SchedA53.td"
Index: llvm/trunk/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp
+++ llvm/trunk/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp
@@ -505,6 +505,12 @@
     if (MF->getTarget().getTargetTriple().isOSFuchsia() &&
         MF->getTarget().getCodeModel() == CodeModel::Kernel)
       SysReg = AArch64SysReg::TPIDR_EL1;
+    else if (MF->getSubtarget<AArch64Subtarget>().useEL3ForTP())
+      SysReg = AArch64SysReg::TPIDR_EL3;
+    else if (MF->getSubtarget<AArch64Subtarget>().useEL2ForTP())
+      SysReg = AArch64SysReg::TPIDR_EL2;
+    else if (MF->getSubtarget<AArch64Subtarget>().useEL1ForTP())
+      SysReg = AArch64SysReg::TPIDR_EL1;
     BuildMI(MBB, MBBI, MI.getDebugLoc(), TII->get(AArch64::MRS), DstReg)
         .addImm(SysReg);
     MI.eraseFromParent();
Index: llvm/trunk/lib/Target/AArch64/AArch64Subtarget.h
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64Subtarget.h
+++ llvm/trunk/lib/Target/AArch64/AArch64Subtarget.h
@@ -173,6 +173,9 @@
   bool DisableLatencySchedHeuristic = false;
   bool UseRSqrt = false;
   bool Force32BitJumpTables = false;
+  bool UseEL1ForTP = false;
+  bool UseEL2ForTP = false;
+  bool UseEL3ForTP = false;
   uint8_t MaxInterleaveFactor = 2;
   uint8_t VectorInsertExtractBaseCost = 3;
   uint16_t CacheLineSize = 0;
@@ -324,6 +327,10 @@
            hasFuseCCSelect() || hasFuseLiterals();
   }
 
+  bool useEL1ForTP() const { return UseEL1ForTP; }
+  bool useEL2ForTP() const { return UseEL2ForTP; }
+  bool useEL3ForTP() const { return UseEL3ForTP; }
+
   bool useRSqrt() const { return UseRSqrt; }
   bool force32BitJumpTables() const { return Force32BitJumpTables; }
   unsigned getMaxInterleaveFactor() const { return MaxInterleaveFactor; }
Index: llvm/trunk/test/CodeGen/AArch64/arm64-builtins-linux.ll
===================================================================
--- llvm/trunk/test/CodeGen/AArch64/arm64-builtins-linux.ll
+++ llvm/trunk/test/CodeGen/AArch64/arm64-builtins-linux.ll
@@ -1,6 +1,9 @@
 ; RUN: llc < %s -mtriple=aarch64-linux-gnu | FileCheck %s
 ; RUN: llc < %s -mtriple=aarch64-fuchsia | FileCheck %s
 ; RUN: llc < %s -mtriple=aarch64-fuchsia -code-model=kernel | FileCheck --check-prefix=FUCHSIA-KERNEL %s
+; RUN: llc < %s -mtriple=aarch64-linux-gnu -mattr=+tpidr-el1 | FileCheck --check-prefix=USEEL1 %s
+; RUN: llc < %s -mtriple=aarch64-linux-gnu -mattr=+tpidr-el2 | FileCheck --check-prefix=USEEL2 %s
+; RUN: llc < %s -mtriple=aarch64-linux-gnu -mattr=+tpidr-el3 | FileCheck --check-prefix=USEEL3 %s
 
 ; Function Attrs: nounwind readnone
 declare i8* @llvm.thread.pointer() #1
@@ -10,6 +13,12 @@
 ; CHECK: mrs {{x[0-9]+}}, TPIDR_EL0
 ; FUCHSIA-KERNEL: thread_pointer:
 ; FUCHSIA-KERNEL: mrs {{x[0-9]+}}, TPIDR_EL1
+; USEEL1: thread_pointer:
+; USEEL1: mrs {{x[0-9]+}}, TPIDR_EL1
+; USEEL2: thread_pointer:
+; USEEL2: mrs {{x[0-9]+}}, TPIDR_EL2
+; USEEL3: thread_pointer:
+; USEEL3: mrs {{x[0-9]+}}, TPIDR_EL3
   %1 = tail call i8* @llvm.thread.pointer()
   ret i8* %1
 }