diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -3161,10 +3161,13 @@
   const std::string &TripleStr = EffectiveTriple.getTriple();
   if (Arg *A = Args.getLastArg(options::OPT_mstack_protector_guard_EQ)) {
     StringRef Value = A->getValue();
-    if (!EffectiveTriple.isX86() && !EffectiveTriple.isAArch64())
+    if (!EffectiveTriple.isX86() && !EffectiveTriple.isAArch64() &&
+        !EffectiveTriple.isARM() && !EffectiveTriple.isThumb())
       D.Diag(diag::err_drv_unsupported_opt_for_target)
           << A->getAsString(Args) << TripleStr;
-    if (EffectiveTriple.isX86() && Value != "tls" && Value != "global") {
+    if ((EffectiveTriple.isX86() || EffectiveTriple.isARM() ||
+         EffectiveTriple.isThumb()) &&
+        Value != "tls" && Value != "global") {
       D.Diag(diag::err_drv_invalid_value_with_suggestion)
           << A->getOption().getName() << Value << "tls global";
       return;
@@ -3179,7 +3182,8 @@
 
   if (Arg *A = Args.getLastArg(options::OPT_mstack_protector_guard_offset_EQ)) {
     StringRef Value = A->getValue();
-    if (!EffectiveTriple.isX86() && !EffectiveTriple.isAArch64())
+    if (!EffectiveTriple.isX86() && !EffectiveTriple.isAArch64() &&
+        !EffectiveTriple.isARM() && !EffectiveTriple.isThumb())
       D.Diag(diag::err_drv_unsupported_opt_for_target)
           << A->getAsString(Args) << TripleStr;
     int Offset;
@@ -3187,6 +3191,12 @@
       D.Diag(diag::err_drv_invalid_value) << A->getOption().getName() << Value;
       return;
     }
+    if ((EffectiveTriple.isARM() || EffectiveTriple.isThumb()) &&
+        (Offset < 0 || Offset > 0xfffff)) {
+      D.Diag(diag::err_drv_invalid_int_value)
+          << A->getOption().getName() << Value;
+      return;
+    }
     A->render(Args, CmdArgs);
   }
 
diff --git a/clang/test/Driver/stack-protector-guard.c b/clang/test/Driver/stack-protector-guard.c
--- a/clang/test/Driver/stack-protector-guard.c
+++ b/clang/test/Driver/stack-protector-guard.c
@@ -15,7 +15,7 @@
 // RUN:   FileCheck -check-prefix=CHECK-GS %s
 
 // Invalid arch
-// RUN: not %clang -target arm-eabi-c -mstack-protector-guard=tls %s 2>&1 | \
+// RUN: not %clang -target powerpc64le-linux-gnu -mstack-protector-guard=tls %s 2>&1 | \
 // RUN:   FileCheck -check-prefix=INVALID-ARCH %s
 // INVALID-ARCH: unsupported option '-mstack-protector-guard=tls' for target
 
@@ -23,7 +23,7 @@
 // RUN:   FileCheck -check-prefix=INVALID-ARCH2 %s
 // INVALID-ARCH2: unsupported option '-mstack-protector-guard-reg=fs' for target
 
-// RUN: not %clang -target arm-linux-gnueabi -mstack-protector-guard-offset=10 %s 2>&1 | \
+// RUN: not %clang -target powerpc64le-linux-gnu -mstack-protector-guard-offset=10 %s 2>&1 | \
 // RUN:   FileCheck -check-prefix=INVALID-ARCH3 %s
 // INVALID-ARCH3: unsupported option '-mstack-protector-guard-offset=10' for target
 
@@ -37,6 +37,14 @@
 // CHECK-GS: "-cc1" {{.*}}"-mstack-protector-guard-reg=gs"
 // INVALID-REG: error: invalid value {{.*}} in 'mstack-protector-guard-reg=', expected one of: fs gs
 
+// RUN: not %clang -target arm-eabi-c -mstack-protector-guard-offset=1048576 %s 2>&1 | \
+// RUN:   FileCheck -check-prefix=INVALID-OFFSET %s
+// INVALID-OFFSET: invalid integral value '1048576' in 'mstack-protector-guard-offset='
+
+// RUN: not %clang -target arm-eabi-c -mstack-protector-guard=sysreg %s 2>&1 | \
+// RUN:   FileCheck -check-prefix=INVALID-VALUE2 %s
+// INVALID-VALUE2: error: invalid value 'sysreg' in 'mstack-protector-guard=', expected one of: tls global
+
 // RUN: %clang -### -target x86_64-unknown-unknown -mstack-protector-guard-offset=30 %s 2>&1 | \
 // RUN:   FileCheck -check-prefix=CHECK-OFFSET %s
 
diff --git a/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp b/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp
--- a/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -4891,40 +4891,67 @@
   MachineBasicBlock &MBB = *MI->getParent();
   DebugLoc DL = MI->getDebugLoc();
   Register Reg = MI->getOperand(0).getReg();
-  const GlobalValue *GV =
-      cast<GlobalValue>((*MI->memoperands_begin())->getValue());
-  bool IsIndirect = Subtarget.isGVIndirectSymbol(GV);
   MachineInstrBuilder MIB;
+  unsigned int Offset = 0;
 
-  unsigned TargetFlags = ARMII::MO_NO_FLAG;
-  if (Subtarget.isTargetMachO()) {
-    TargetFlags |= ARMII::MO_NONLAZY;
-  } else if (Subtarget.isTargetCOFF()) {
-    if (GV->hasDLLImportStorageClass())
-      TargetFlags |= ARMII::MO_DLLIMPORT;
-    else if (IsIndirect)
-      TargetFlags |= ARMII::MO_COFFSTUB;
-  } else if (Subtarget.isGVInGOT(GV)) {
-    TargetFlags |= ARMII::MO_GOT;
-  }
+  if (LoadImmOpc == ARM::MRC || LoadImmOpc == ARM::t2MRC) {
+    BuildMI(MBB, MI, DL, get(LoadImmOpc), Reg)
+        .addImm(15)
+        .addImm(0)
+        .addImm(13)
+        .addImm(0)
+        .addImm(3)
+        .add(predOps(ARMCC::AL));
 
-  BuildMI(MBB, MI, DL, get(LoadImmOpc), Reg)
-      .addGlobalAddress(GV, 0, TargetFlags);
+    Module &M = *MBB.getParent()->getFunction().getParent();
+    Offset = M.getStackProtectorGuardOffset();
+    if (Offset & ~0xfffU) {
+      // The offset won't fit in the LDR's 12-bit immediate field, so emit an
+      // extra ADD to cover the delta. This gives us a guaranteed 8 additional
+      // bits, resulting in a range of 0 to +1 MiB for the guard offset.
+      unsigned AddOpc = (LoadImmOpc == ARM::MRC) ? ARM::ADDri : ARM::t2ADDri;
+      BuildMI(MBB, MI, DL, get(AddOpc), Reg)
+          .addReg(Reg, RegState::Kill)
+          .addImm(Offset & ~0xfffU)
+          .add(predOps(ARMCC::AL))
+          .addReg(0);
+      Offset &= 0xfffU;
+    }
+  } else {
+    const GlobalValue *GV =
+        cast<GlobalValue>((*MI->memoperands_begin())->getValue());
+    bool IsIndirect = Subtarget.isGVIndirectSymbol(GV);
+
+    unsigned TargetFlags = ARMII::MO_NO_FLAG;
+    if (Subtarget.isTargetMachO()) {
+      TargetFlags |= ARMII::MO_NONLAZY;
+    } else if (Subtarget.isTargetCOFF()) {
+      if (GV->hasDLLImportStorageClass())
+        TargetFlags |= ARMII::MO_DLLIMPORT;
+      else if (IsIndirect)
+        TargetFlags |= ARMII::MO_COFFSTUB;
+    } else if (Subtarget.isGVInGOT(GV)) {
+      TargetFlags |= ARMII::MO_GOT;
+    }
 
-  if (IsIndirect) {
-    MIB = BuildMI(MBB, MI, DL, get(LoadOpc), Reg);
-    MIB.addReg(Reg, RegState::Kill).addImm(0);
-    auto Flags = MachineMemOperand::MOLoad |
-                 MachineMemOperand::MODereferenceable |
-                 MachineMemOperand::MOInvariant;
-    MachineMemOperand *MMO = MBB.getParent()->getMachineMemOperand(
-        MachinePointerInfo::getGOT(*MBB.getParent()), Flags, 4, Align(4));
-    MIB.addMemOperand(MMO).add(predOps(ARMCC::AL));
+    BuildMI(MBB, MI, DL, get(LoadImmOpc), Reg)
+        .addGlobalAddress(GV, 0, TargetFlags);
+
+    if (IsIndirect) {
+      MIB = BuildMI(MBB, MI, DL, get(LoadOpc), Reg);
+      MIB.addReg(Reg, RegState::Kill).addImm(0);
+      auto Flags = MachineMemOperand::MOLoad |
+                   MachineMemOperand::MODereferenceable |
+                   MachineMemOperand::MOInvariant;
+      MachineMemOperand *MMO = MBB.getParent()->getMachineMemOperand(
+          MachinePointerInfo::getGOT(*MBB.getParent()), Flags, 4, Align(4));
+      MIB.addMemOperand(MMO).add(predOps(ARMCC::AL));
+    }
   }
 
   MIB = BuildMI(MBB, MI, DL, get(LoadOpc), Reg);
   MIB.addReg(Reg, RegState::Kill)
-      .addImm(0)
+      .addImm(Offset)
       .cloneMemRefs(*MI)
       .add(predOps(ARMCC::AL));
 }
diff --git a/llvm/lib/Target/ARM/ARMInstrInfo.cpp b/llvm/lib/Target/ARM/ARMInstrInfo.cpp
--- a/llvm/lib/Target/ARM/ARMInstrInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMInstrInfo.cpp
@@ -95,6 +95,13 @@
   MachineFunction &MF = *MI->getParent()->getParent();
   const ARMSubtarget &Subtarget = MF.getSubtarget<ARMSubtarget>();
   const TargetMachine &TM = MF.getTarget();
+  MachineBasicBlock &MBB = *MI->getParent();
+  Module &M = *MBB.getParent()->getFunction().getParent();
+
+  if (M.getStackProtectorGuard() == "tls") {
+    expandLoadStackGuardBase(MI, ARM::MRC, ARM::LDRi12);
+    return;
+  }
 
   const GlobalValue *GV =
       cast<GlobalValue>((*MI->memoperands_begin())->getValue());
@@ -117,7 +124,6 @@
     return;
   }
 
-  MachineBasicBlock &MBB = *MI->getParent();
   DebugLoc DL = MI->getDebugLoc();
   Register Reg = MI->getOperand(0).getReg();
   MachineInstrBuilder MIB;
diff --git a/llvm/lib/Target/ARM/Thumb2InstrInfo.cpp b/llvm/lib/Target/ARM/Thumb2InstrInfo.cpp
--- a/llvm/lib/Target/ARM/Thumb2InstrInfo.cpp
+++ b/llvm/lib/Target/ARM/Thumb2InstrInfo.cpp
@@ -250,6 +250,14 @@
 void Thumb2InstrInfo::expandLoadStackGuard(
     MachineBasicBlock::iterator MI) const {
   MachineFunction &MF = *MI->getParent()->getParent();
+  MachineBasicBlock &MBB = *MI->getParent();
+  Module &M = *MBB.getParent()->getFunction().getParent();
+
+  if (M.getStackProtectorGuard() == "tls") {
+    expandLoadStackGuardBase(MI, ARM::t2MRC, ARM::t2LDRi12);
+    return;
+  }
+
   const GlobalValue *GV =
       cast<GlobalValue>((*MI->memoperands_begin())->getValue());
 
diff --git a/llvm/test/CodeGen/ARM/stack-guard-tls.ll b/llvm/test/CodeGen/ARM/stack-guard-tls.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/stack-guard-tls.ll
@@ -0,0 +1,38 @@
+; RUN: split-file %s %t
+; RUN: cat %t/main.ll %t/a.ll > %t/a2.ll
+; RUN: cat %t/main.ll %t/b.ll > %t/b2.ll
+; RUN: llc %t/a2.ll -mtriple=armv7-unknown-linux-gnueabihf -o - | \
+; RUN: FileCheck --check-prefix=CHECK --check-prefix=CHECK-SMALL %s
+; RUN: llc %t/a2.ll -mtriple=thumbv7-unknown-linux-gnueabihf -o - | \
+; RUN: FileCheck --check-prefix=CHECK --check-prefix=CHECK-SMALL %s
+; RUN: llc %t/b2.ll -mtriple=armv7-unknown-linux-gnueabihf -o - | \
+; RUN: FileCheck --check-prefix=CHECK --check-prefix=CHECK-LARGE %s
+; RUN: llc %t/b2.ll -mtriple=thumbv7-unknown-linux-gnueabihf -o - | \
+; RUN: FileCheck --check-prefix=CHECK --check-prefix=CHECK-LARGE %s
+
+;--- main.ll
+declare void @baz(i32*)
+
+define void @foo(i64 %t) sspstrong {
+  %vla = alloca i32, i64 %t, align 4
+  call void @baz(i32* nonnull %vla)
+  ret void
+}
+!llvm.module.flags = !{!1, !2}
+!1 = !{i32 2, !"stack-protector-guard", !"tls"}
+
+;--- a.ll
+!2 = !{i32 2, !"stack-protector-guard-offset", i32 1296}
+
+;--- b.ll
+!2 = !{i32 2, !"stack-protector-guard-offset", i32 4296}
+
+; CHECK: mrc p15, #0, [[REG1:r[0-9]+]], c13, c0, #3
+; CHECK-SMALL-NEXT: ldr{{(\.w)?}} [[REG1]], {{\[}}[[REG1]], #1296]
+; CHECK-LARGE-NEXT: add{{(\.w)?}} [[REG1]], [[REG1]], #4096
+; CHECK-LARGE-NEXT: ldr{{(\.w)?}} [[REG1]], {{\[}}[[REG1]], #200]
+; CHECK: bl baz
+; CHECK: mrc p15, #0, [[REG2:r[0-9]+]], c13, c0, #3
+; CHECK-SMALL-NEXT: ldr{{(\.w)?}} [[REG2]], {{\[}}[[REG2]], #1296]
+; CHECK-LARGE-NEXT: add{{(\.w)?}} [[REG2]], [[REG2]], #4096
+; CHECK-LARGE-NEXT: ldr{{(\.w)?}} [[REG2]], {{\[}}[[REG2]], #200]