Index: lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/SIISelLowering.cpp
+++ lib/Target/AMDGPU/SIISelLowering.cpp
@@ -3478,14 +3478,20 @@
   case AMDGPU::SI_TCRETURN_ISEL: {
     const SIInstrInfo *TII = getSubtarget()->getInstrInfo();
     const DebugLoc &DL = MI.getDebugLoc();
+    MachineRegisterInfo &MRI = MF->getRegInfo();
+
     unsigned ReturnAddrReg = TII->getRegisterInfo().getReturnAddressReg(*MF);
 
-    MachineRegisterInfo &MRI = MF->getRegInfo();
-    unsigned GlobalAddrReg = MI.getOperand(0).getReg();
-    MachineInstr *PCRel = MRI.getVRegDef(GlobalAddrReg);
-    assert(PCRel->getOpcode() == AMDGPU::SI_PC_ADD_REL_OFFSET);
+    unsigned AddrReg = MI.getOperand(0).getReg();
+    MachineInstr *DefI = MRI.getVRegDef(AddrReg);
+
+    if (DefI->getOpcode() == AMDGPU::S_LOAD_DWORDX2_IMM) {
+      AddrReg = DefI->getOperand(1).getReg();
+      DefI = MRI.getVRegDef(AddrReg);
+    }
+    assert(DefI->getOpcode() == AMDGPU::SI_PC_ADD_REL_OFFSET);
 
-    const GlobalValue *G = PCRel->getOperand(1).getGlobal();
+    const GlobalValue *G = DefI->getOperand(1).getGlobal();
 
     MachineInstrBuilder MIB;
     if (MI.getOpcode() == AMDGPU::SI_CALL_ISEL) {
@@ -4008,7 +4014,8 @@
 }
 
 bool SITargetLowering::shouldEmitGOTReloc(const GlobalValue *GV) const {
-  return (GV->getType()->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS ||
+  return (GV->getValueType()->isFunctionTy() ||
+          GV->getType()->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS ||
           GV->getType()->getAddressSpace() == AMDGPUAS::CONSTANT_ADDRESS ||
           GV->getType()->getAddressSpace() == AMDGPUAS::CONSTANT_ADDRESS_32BIT) &&
          !shouldEmitFixup(GV) &&
Index: test/CodeGen/AMDGPU/byval-frame-setup.ll
===================================================================
--- test/CodeGen/AMDGPU/byval-frame-setup.ll
+++ test/CodeGen/AMDGPU/byval-frame-setup.ll
@@ -14,7 +14,7 @@
 ; GCN-NOT: s32
 ; GCN: buffer_store_dword [[LOAD1]], off, s[0:3], s5 offset:20{{$}}
 ; GCN-NOT: s32
-define void @void_func_byval_struct(%struct.ByValStruct addrspace(5)* byval noalias nocapture align 4 %arg0, %struct.ByValStruct addrspace(5)* byval noalias nocapture align 4 %arg1) #1 {
+define hidden void @void_func_byval_struct(%struct.ByValStruct addrspace(5)* byval noalias nocapture align 4 %arg0, %struct.ByValStruct addrspace(5)* byval noalias nocapture align 4 %arg1) #1 {
 entry:
   %arrayidx = getelementptr inbounds %struct.ByValStruct, %struct.ByValStruct addrspace(5)* %arg0, i32 0, i32 0, i32 0
   %tmp = load volatile i32, i32 addrspace(5)* %arrayidx, align 4
@@ -193,7 +193,7 @@
 ; GCN-NOT: s32
 ; GCN: buffer_store_dword [[LOAD1]], off, s[0:3], s5 offset:24{{$}}
 ; GCN-NOT: s32
-define void @void_func_byval_struct_align8(%struct.ByValStruct addrspace(5)* byval noalias nocapture align 8 %arg0, %struct.ByValStruct addrspace(5)* byval noalias nocapture align 8 %arg1) #1 {
+define hidden void @void_func_byval_struct_align8(%struct.ByValStruct addrspace(5)* byval noalias nocapture align 8 %arg0, %struct.ByValStruct addrspace(5)* byval noalias nocapture align 8 %arg1) #1 {
 entry:
   %arrayidx = getelementptr inbounds %struct.ByValStruct, %struct.ByValStruct addrspace(5)* %arg0, i32 0, i32 0, i32 0
   %tmp = load volatile i32, i32 addrspace(5)* %arrayidx, align 8
Index: test/CodeGen/AMDGPU/call-argument-types.ll
===================================================================
--- test/CodeGen/AMDGPU/call-argument-types.ll
+++ test/CodeGen/AMDGPU/call-argument-types.ll
@@ -3,56 +3,56 @@
 ; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-scalarize-global-loads=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,VI,MESA %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -mattr=-flat-for-global -amdgpu-scalarize-global-loads=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,HSA %s
 
-declare void @external_void_func_i1(i1) #0
-declare void @external_void_func_i1_signext(i1 signext) #0
-declare void @external_void_func_i1_zeroext(i1 zeroext) #0
-
-declare void @external_void_func_i8(i8) #0
-declare void @external_void_func_i8_signext(i8 signext) #0
-declare void @external_void_func_i8_zeroext(i8 zeroext) #0
-
-declare void @external_void_func_i16(i16) #0
-declare void @external_void_func_i16_signext(i16 signext) #0
-declare void @external_void_func_i16_zeroext(i16 zeroext) #0
-
-declare void @external_void_func_i32(i32) #0
-declare void @external_void_func_i64(i64) #0
-declare void @external_void_func_v2i64(<2 x i64>) #0
-declare void @external_void_func_v3i64(<3 x i64>) #0
-declare void @external_void_func_v4i64(<4 x i64>) #0
-
-declare void @external_void_func_f16(half) #0
-declare void @external_void_func_f32(float) #0
-declare void @external_void_func_f64(double) #0
-declare void @external_void_func_v2f32(<2 x float>) #0
-declare void @external_void_func_v2f64(<2 x double>) #0
-declare void @external_void_func_v3f64(<3 x double>) #0
-
-declare void @external_void_func_v2i16(<2 x i16>) #0
-declare void @external_void_func_v2f16(<2 x half>) #0
-declare void @external_void_func_v3i16(<3 x i16>) #0
-declare void @external_void_func_v3f16(<3 x half>) #0
-declare void @external_void_func_v4i16(<4 x i16>) #0
-declare void @external_void_func_v4f16(<4 x half>) #0
-
-declare void @external_void_func_v2i32(<2 x i32>) #0
-declare void @external_void_func_v3i32(<3 x i32>) #0
-declare void @external_void_func_v3i32_i32(<3 x i32>, i32) #0
-declare void @external_void_func_v4i32(<4 x i32>) #0
-declare void @external_void_func_v8i32(<8 x i32>) #0
-declare void @external_void_func_v16i32(<16 x i32>) #0
-declare void @external_void_func_v32i32(<32 x i32>) #0
-declare void @external_void_func_v32i32_i32(<32 x i32>, i32) #0
+declare hidden void @external_void_func_i1(i1) #0
+declare hidden void @external_void_func_i1_signext(i1 signext) #0
+declare hidden void @external_void_func_i1_zeroext(i1 zeroext) #0
+
+declare hidden void @external_void_func_i8(i8) #0
+declare hidden void @external_void_func_i8_signext(i8 signext) #0
+declare hidden void @external_void_func_i8_zeroext(i8 zeroext) #0
+
+declare hidden void @external_void_func_i16(i16) #0
+declare hidden void @external_void_func_i16_signext(i16 signext) #0
+declare hidden void @external_void_func_i16_zeroext(i16 zeroext) #0
+
+declare hidden void @external_void_func_i32(i32) #0
+declare hidden void @external_void_func_i64(i64) #0
+declare hidden void @external_void_func_v2i64(<2 x i64>) #0
+declare hidden void @external_void_func_v3i64(<3 x i64>) #0
+declare hidden void @external_void_func_v4i64(<4 x i64>) #0
+
+declare hidden void @external_void_func_f16(half) #0
+declare hidden void @external_void_func_f32(float) #0
+declare hidden void @external_void_func_f64(double) #0
+declare hidden void @external_void_func_v2f32(<2 x float>) #0
+declare hidden void @external_void_func_v2f64(<2 x double>) #0
+declare hidden void @external_void_func_v3f64(<3 x double>) #0
+
+declare hidden void @external_void_func_v2i16(<2 x i16>) #0
+declare hidden void @external_void_func_v2f16(<2 x half>) #0
+declare hidden void @external_void_func_v3i16(<3 x i16>) #0
+declare hidden void @external_void_func_v3f16(<3 x half>) #0
+declare hidden void @external_void_func_v4i16(<4 x i16>) #0
+declare hidden void @external_void_func_v4f16(<4 x half>) #0
+
+declare hidden void @external_void_func_v2i32(<2 x i32>) #0
+declare hidden void @external_void_func_v3i32(<3 x i32>) #0
+declare hidden void @external_void_func_v3i32_i32(<3 x i32>, i32) #0
+declare hidden void @external_void_func_v4i32(<4 x i32>) #0
+declare hidden void @external_void_func_v8i32(<8 x i32>) #0
+declare hidden void @external_void_func_v16i32(<16 x i32>) #0
+declare hidden void @external_void_func_v32i32(<32 x i32>) #0
+declare hidden void @external_void_func_v32i32_i32(<32 x i32>, i32) #0
 
 ; return value and argument
-declare i32 @external_i32_func_i32(i32) #0
+declare hidden i32 @external_i32_func_i32(i32) #0
 
 ; Structs
-declare void @external_void_func_struct_i8_i32({ i8, i32 }) #0
-declare void @external_void_func_byval_struct_i8_i32({ i8, i32 } addrspace(5)* byval) #0
-declare void @external_void_func_sret_struct_i8_i32_byval_struct_i8_i32({ i8, i32 } addrspace(5)* sret, { i8, i32 } addrspace(5)* byval) #0
+declare hidden void @external_void_func_struct_i8_i32({ i8, i32 }) #0
+declare hidden void @external_void_func_byval_struct_i8_i32({ i8, i32 } addrspace(5)* byval) #0
+declare hidden void @external_void_func_sret_struct_i8_i32_byval_struct_i8_i32({ i8, i32 } addrspace(5)* sret, { i8, i32 } addrspace(5)* byval) #0
 
-declare void @external_void_func_v16i8(<16 x i8>) #0
+declare hidden void @external_void_func_v16i8(<16 x i8>) #0
 
 
 ; FIXME: Should be passing -1
@@ -764,8 +764,8 @@
   ret void
 }
 
-declare void @byval_align16_f64_arg(<32 x i32>, double addrspace(5)* byval align 16) #0
-declare void @stack_passed_f64_arg(<32 x i32>, double) #0
+declare hidden void @byval_align16_f64_arg(<32 x i32>, double addrspace(5)* byval align 16) #0
+declare hidden void @stack_passed_f64_arg(<32 x i32>, double) #0
 
 attributes #0 = { nounwind }
 attributes #1 = { nounwind readnone }
Index: test/CodeGen/AMDGPU/call-constexpr.ll
===================================================================
--- test/CodeGen/AMDGPU/call-constexpr.ll
+++ test/CodeGen/AMDGPU/call-constexpr.ll
@@ -67,7 +67,7 @@
 ; GCN: s_waitcnt
 ; GCN-NEXT: v_add_i32_e32 v0, vcc, v1, v0
 ; GCN-NEXT: s_setpc_b64
-define i32 @use_workitem_id_x(i32 %arg0) #0 {
+define hidden i32 @use_workitem_id_x(i32 %arg0) #0 {
   %id = call i32 @llvm.amdgcn.workitem.id.x()
   %op = add i32 %id, %arg0
   ret i32 %op
@@ -121,15 +121,15 @@
 ; Callees appears last in source file to test that we still lower their
 ; arguments before we lower any calls to them.
 
-define i32 @ret_i32_noinline() #0 {
+define hidden i32 @ret_i32_noinline() #0 {
   ret i32 4
 }
 
-define i32 @ret_i32_alwaysinline() #1 {
+define hidden i32 @ret_i32_alwaysinline() #1 {
   ret i32 4
 }
 
-define i32 @ident_i32(i32 %i) #0 {
+define hidden i32 @ident_i32(i32 %i) #0 {
   ret i32 %i
 }
 
Index: test/CodeGen/AMDGPU/call-preserved-registers.ll
===================================================================
--- test/CodeGen/AMDGPU/call-preserved-registers.ll
+++ test/CodeGen/AMDGPU/call-preserved-registers.ll
@@ -2,7 +2,7 @@
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -enable-ipra=0 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-ipra=0 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
-declare void @external_void_func_void() #0
+declare hidden void @external_void_func_void() #0
 
 ; GCN-LABEL: {{^}}test_kernel_call_external_void_func_void_clobber_s30_s31_call_external_void_func_void:
 ; GCN: s_mov_b32 s33, s7
@@ -84,7 +84,7 @@
 ; GCN-NEXT: ;;#ASMSTART
 ; GCN-NEXT: ;;#ASMEND
 ; GCN-NEXT: s_setpc_b64 s[30:31]
-define void @void_func_void_clobber_vcc() #2 {
+define hidden void @void_func_void_clobber_vcc() #2 {
   call void asm sideeffect "", "~{VCC}"() #0
   ret void
 }
@@ -176,7 +176,7 @@
 ; GCN-NEXT: #ASMEND
 ; GCN-NEXT:	v_readlane_b32 s33, v0, 0
 ; GCN-NEXT: s_setpc_b64
-define void @void_func_void_clobber_s33() #2 {
+define hidden void @void_func_void_clobber_s33() #2 {
   call void asm sideeffect "; clobber", "~{s33}"() #0
   ret void
 }
Index: test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
===================================================================
--- test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
+++ test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
@@ -166,11 +166,11 @@
 }
 
 
-declare <2 x float> @func_v2f32() #0
-declare <3 x float> @func_v3f32() #0
-declare <4 x float> @func_v4f32() #0
-declare <4 x half> @func_v4f16() #0
+declare hidden <2 x float> @func_v2f32() #0
+declare hidden <3 x float> @func_v3f32() #0
+declare hidden <4 x float> @func_v4f32() #0
+declare hidden <4 x half> @func_v4f16() #0
 
-declare { <4 x i32>, <4 x half> } @func_struct() #0
+declare hidden { <4 x i32>, <4 x half> } @func_struct() #0
 
 attributes #0 = { nounwind}
Index: test/CodeGen/AMDGPU/function-call-relocs.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/function-call-relocs.ll
@@ -0,0 +1,49 @@
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji < %s | FileCheck %s
+
+define void @func(i32 addrspace(1)* %out) #0 {
+  store i32 1, i32 addrspace(1)* %out
+  ret void
+}
+
+define protected void @protected_func(i32 addrspace(1)* %out) #0 {
+  store i32 1, i32 addrspace(1)* %out
+  ret void
+}
+
+define hidden void @hidden_func(i32 addrspace(1)* %out) #0 {
+  store i32 1, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK-LABEL: call_func:
+; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
+; CHECK: s_add_u32 s[[GOT_ADDR_LO:[0-9]+]], s[[PC_LO]], func@gotpcrel32@lo+4
+; CHECK: s_addc_u32 s[[GOT_ADDR_HI:[0-9]+]], s[[PC_HI]], func@gotpcrel32@hi+4
+; CHECK: s_load_dwordx2 s{{\[}}[[ADDR_LO:[0-9]+]]:[[ADDR_HI:[0-9]+]]{{\]}}, s{{\[}}[[GOT_ADDR_LO]]:[[GOT_ADDR_HI]]{{\]}}, 0x0
+; CHECK: s_swappc_b64 s{{\[}}{{[0-9]+:[0-9]+}}{{\]}}, s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
+define amdgpu_kernel void @call_func(i32 addrspace(1)* %out) {
+  call void @func(i32 addrspace(1)* %out)
+  ret void
+}
+
+; CHECK-LABEL: call_protected_func:
+; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
+; CHECK: s_add_u32 s[[ADDR_LO:[0-9]+]], s[[PC_LO]], protected_func@rel32@lo+4
+; CHECK: s_addc_u32 s[[ADDR_HI:[0-9]+]], s[[PC_HI]], protected_func@rel32@hi+4
+; CHECK: s_swappc_b64 s{{\[}}{{[0-9]+:[0-9]+}}{{\]}}, s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
+define amdgpu_kernel void @call_protected_func(i32 addrspace(1)* %out) {
+  call void @protected_func(i32 addrspace(1)* %out)
+  ret void
+}
+
+; CHECK-LABEL: call_hidden_func:
+; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
+; CHECK: s_add_u32 s[[ADDR_LO:[0-9]+]], s[[PC_LO]], hidden_func@rel32@lo+4
+; CHECK: s_addc_u32 s[[ADDR_HI:[0-9]+]], s[[PC_HI]], hidden_func@rel32@hi+4
+; CHECK: s_swappc_b64 s{{\[}}{{[0-9]+:[0-9]+}}{{\]}}, s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
+define amdgpu_kernel void @call_hidden_func(i32 addrspace(1)* %out) {
+  call void @hidden_func(i32 addrspace(1)* %out)
+  ret void
+}
+
+attributes #0 = { noinline }
Index: test/CodeGen/AMDGPU/ipra.ll
===================================================================
--- test/CodeGen/AMDGPU/ipra.ll
+++ test/CodeGen/AMDGPU/ipra.ll
@@ -12,7 +12,7 @@
 
 ; GCN-LABEL: {{^}}func:
 ; GCN: ; NumVgprs: 8
-define void @func() #1 {
+define hidden void @func() #1 {
   call void asm sideeffect "", "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7}"() #0
   ret void
 }
Index: test/CodeGen/AMDGPU/mem-builtins.ll
===================================================================
--- test/CodeGen/AMDGPU/mem-builtins.ll
+++ test/CodeGen/AMDGPU/mem-builtins.ll
@@ -1,12 +1,12 @@
 ; RUN: not llc -march=r600 < %s 2>&1 | FileCheck -check-prefix=ERROR %s
 ; RUN: llc -march=amdgcn < %s | FileCheck -check-prefix=GCN %s
 
-declare i32 @memcmp(i8 addrspace(1)* readonly nocapture, i8 addrspace(1)* readonly nocapture, i64) #0
-declare i8 addrspace(1)* @memchr(i8 addrspace(1)* readonly nocapture, i32, i64) #1
-declare i8* @strcpy(i8* nocapture, i8* readonly nocapture) #0
-declare i32 @strlen(i8* nocapture) #1
-declare i32 @strnlen(i8* nocapture, i32) #1
-declare i32 @strcmp(i8* nocapture, i8* nocapture) #1
+declare hidden i32 @memcmp(i8 addrspace(1)* readonly nocapture, i8 addrspace(1)* readonly nocapture, i64) #0
+declare hidden i8 addrspace(1)* @memchr(i8 addrspace(1)* readonly nocapture, i32, i64) #1
+declare hidden i8* @strcpy(i8* nocapture, i8* readonly nocapture) #0
+declare hidden i32 @strlen(i8* nocapture) #1
+declare hidden i32 @strnlen(i8* nocapture, i32) #1
+declare hidden i32 @strcmp(i8* nocapture, i8* nocapture) #1
 
 
 ; ERROR: error: <unknown>:0:0: in function test_memcmp void (i8 addrspace(1)*, i8 addrspace(1)*, i32*): unsupported call to function memcmp
Index: test/CodeGen/AMDGPU/sibling-call.ll
===================================================================
--- test/CodeGen/AMDGPU/sibling-call.ll
+++ test/CodeGen/AMDGPU/sibling-call.ll
@@ -32,7 +32,7 @@
 }
 
 ; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32:
-define fastcc i32 @sibling_call_i32_fastcc_i32_i32(i32 %a, i32 %b, i32 %c) #1 {
+define hidden fastcc i32 @sibling_call_i32_fastcc_i32_i32(i32 %a, i32 %b, i32 %c) #1 {
 entry:
   %ret = tail call fastcc i32 @i32_fastcc_i32_i32(i32 %a, i32 %b)
   ret i32 %ret
@@ -92,7 +92,7 @@
 ; GFX9-NEXT: v_add_u32_e32 v0, v0, v1
 
 ; GCN-NEXT: s_setpc_b64 s[30:31]
-define fastcc i32 @i32_fastcc_i32_byval_i32(i32 %arg0, i32 addrspace(5)* byval align 4 %arg1) #1 {
+define hidden fastcc i32 @i32_fastcc_i32_byval_i32(i32 %arg0, i32 addrspace(5)* byval align 4 %arg1) #1 {
   %arg1.load = load i32, i32 addrspace(5)* %arg1, align 4
   %add0 = add i32 %arg0, %arg1.load
   ret i32 %add0