[TLS] New lower emutls pass, fix linkage bugs.

Previous implementation in http://reviews.llvm.org/D10522
created external references to __emutls_v.* variables.
Such references are inaccurate and cannot be handled by
all linkers, e.g. Android dynamic and gold linkers for aarch64.

Now a new LowerEmuTLS pass to go through all global variables,
and add emutls_v.* and emutls_t.* variables.
These __emutls* variables have the same linkage and
visibility as the associated user defined TLS variable.

Also removed old code that dump __emutls* variables in AsmPrinter.cpp,
and updated TLS unit tests.

Differential Revision: http://reviews.llvm.org/D15300

llvm-svn: 257718

2 files changed, 37 insertions, 21 deletions

diff --git a/llvm/test/CodeGen/ARM/emutls.ll b/llvm/test/CodeGen/ARM/emutls.ll
index 7ba50dd249b..40f75b88756 100644
--- a/llvm/test/CodeGen/ARM/emutls.ll
+++ b/llvm/test/CodeGen/ARM/emutls.ll
@@ -13,6 +13,7 @@ define i32 @my_get_xyz() {
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl my_emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
+; ARM32:        .long my_emutls_v_xyz(GOT_PREL)
 
 entry:
   %call = call i8* @my_emutls_get_address(i8* bitcast (i8** @my_emutls_v_xyz to i8*))
@@ -35,6 +36,7 @@ define i32 @f1() {
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
+; ARM32:        .long __emutls_v.i1(GOT_PREL)
 
 entry:
   %tmp1 = load i32, i32* @i1
@@ -47,6 +49,7 @@ define i32* @f2() {
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
+; ARM32:        .long __emutls_v.i1(GOT_PREL)
 
 entry:
   ret i32* @i1
@@ -58,6 +61,7 @@ define i32 @f3() nounwind {
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
+; ARM32:        .long __emutls_v.i2(GOT_PREL)
 
 entry:
   %tmp1 = load i32, i32* @i2
@@ -70,6 +74,7 @@ define i32* @f4() {
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
+; ARM32:        .long __emutls_v.i2(GOT_PREL)
 
 entry:
   ret i32* @i2
@@ -78,9 +83,10 @@ entry:
 define i32 @f5() nounwind {
 ; ARM32-LABEL: f5:
 ; ARM32:        ldr r0,
-; ARM32:        ldr r0, [pc, r0]
+; ARM32:        add	r0, pc, r0
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
+; ARM32:        .long __emutls_v.i3-
 
 entry:
   %tmp1 = load i32, i32* @i3
@@ -90,9 +96,10 @@ entry:
 define i32* @f6() {
 ; ARM32-LABEL: f6:
 ; ARM32:        ldr r0,
-; ARM32:        ldr r0, [pc, r0]
+; ARM32:        add	r0, pc, r0
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
+; ARM32:        .long __emutls_v.i3-
 
 entry:
   ret i32* @i3
@@ -101,9 +108,10 @@ entry:
 define i32 @f7() {
 ; ARM32-LABEL: f7:
 ; ARM32:        ldr r0,
-; ARM32:        ldr r0, [pc, r0]
+; ARM32:        add r0, pc, r0
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
+; ARM32:        .long __emutls_v.i4-(.LPC
 
 entry:
   %tmp1 = load i32, i32* @i4
@@ -113,9 +121,10 @@ entry:
 define i32* @f8() {
 ; ARM32-LABEL: f8:
 ; ARM32:        ldr r0,
-; ARM32:        ldr r0, [pc, r0]
+; ARM32:        add r0, pc, r0
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
+; ARM32:        .long __emutls_v.i4-(.LPC
 
 entry:
   ret i32* @i4
@@ -124,7 +133,7 @@ entry:
 define i32 @f9() {
 ; ARM32-LABEL: f9:
 ; ARM32:        ldr r0,
-; ARM32:        ldr r0, [pc, r0]
+; ARM32:        add r0, pc, r0
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
 
@@ -136,7 +145,7 @@ entry:
 define i32* @f10() {
 ; ARM32-LABEL: f10:
 ; ARM32:        ldr r0,
-; ARM32:        ldr r0, [pc, r0]
+; ARM32:        add r0, pc, r0
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
 
@@ -198,46 +207,50 @@ entry:
 
 ;;;;;;;;;;;;;; 32-bit __emutls_v. and __emutls_t.
 
-; ARM32       .section .data.rel.local,
+; ARM32:      .data{{$}}
+; ARM32:      .globl __emutls_v.i1
 ; ARM32-LABEL: __emutls_v.i1:
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 0
 ; ARM32-NEXT: .long __emutls_t.i1
 
-; ARM32       .section .rodata,
+; ARM32:      .section .rodata,
 ; ARM32-LABEL: __emutls_t.i1:
 ; ARM32-NEXT: .long 15
 
 ; ARM32-NOT:   __emutls_v.i2
 
-; ARM32       .section .data.rel.local,
+; ARM32:      .data{{$}}
+; ARM32-NOT:  .globl
 ; ARM32-LABEL: __emutls_v.i3:
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 0
 ; ARM32-NEXT: .long __emutls_t.i3
 
-; ARM32       .section .rodata,
+; ARM32:      .section .rodata,
 ; ARM32-LABEL: __emutls_t.i3:
 ; ARM32-NEXT: .long 15
 
-; ARM32       .section .data.rel.local,
+; ARM32:      .data{{$}}
+; ARM32:      .globl __emutls_v.i4
 ; ARM32-LABEL: __emutls_v.i4:
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 0
 ; ARM32-NEXT: .long __emutls_t.i4
 
-; ARM32       .section .rodata,
+; ARM32:      .section .rodata,
 ; ARM32-LABEL: __emutls_t.i4:
 ; ARM32-NEXT: .long 15
 
 ; ARM32-NOT:   __emutls_v.i5:
-; ARM32       .hidden __emutls_v.i5
+; ARM32:      .hidden __emutls_v.i5
 ; ARM32-NOT:   __emutls_v.i5:
 
-; ARM32 .section .data.rel.local,
+; ARM32:      .data{{$}}
+; ARM32:      .globl __emutls_v.s1
 ; ARM32-LABEL: __emutls_v.s1:
 ; ARM32-NEXT: .long 2
 ; ARM32-NEXT: .long 2
@@ -248,7 +261,8 @@ entry:
 ; ARM32-LABEL: __emutls_t.s1:
 ; ARM32-NEXT: .short 15
 
-; ARM32 .section .data.rel.local,
+; ARM32:      .data{{$}}
+; ARM32:      .globl __emutls_v.b1
 ; ARM32-LABEL: __emutls_v.b1:
 ; ARM32-NEXT: .long 1
 ; ARM32-NEXT: .long 1
diff --git a/llvm/test/CodeGen/ARM/emutls_generic.ll b/llvm/test/CodeGen/ARM/emutls_generic.ll
index 0fada88fb5d..872dd83f299 100644
--- a/llvm/test/CodeGen/ARM/emutls_generic.ll
+++ b/llvm/test/CodeGen/ARM/emutls_generic.ll
@@ -35,11 +35,12 @@ entry:
 ; ARM_32:        bl __emutls_get_address
 ; ARM_32:        .long __emutls_v.external_y
 ; ARM_32-LABEL:  get_internal_y:
-; ARM_32:      bl __emutls_get_address
-; ARM_32:      .long __emutls_v.internal_y
-; ARM_32-NOT:   __emutls_t.external_x
-; ARM_32-NOT:   __emutls_v.external_x:
-; ARM_32:        .data
+; ARM_32:        bl __emutls_get_address
+; ARM_32:        .long __emutls_v.internal_y
+; ARM_32-NOT:    __emutls_t.external_x
+; ARM_32-NOT:    __emutls_v.external_x:
+; ARM_32:        .data{{$}}
+; ARM_32:        .globl __emutls_v.external_y
 ; ARM_32:        .align 2
 ; ARM_32-LABEL:  __emutls_v.external_y:
 ; ARM_32-NEXT:   .long 1
@@ -49,7 +50,8 @@ entry:
 ; ARM_32:        .section .rodata,
 ; ARM_32-LABEL:  __emutls_t.external_y:
 ; ARM_32-NEXT:   .byte 7
-; ARM_32:        .data
+; ARM_32:        .data{{$}}
+; ARM_32-NOT:    .globl
 ; ARM_32:        .align 2
 ; ARM_32-LABEL:  __emutls_v.internal_y:
 ; ARM_32-NEXT:   .long 8