[X86] Fix tls variable lowering issue with large code model

Summary:
The problem here is the lowering for tls variable. Below is the DAG for the code.
SelectionDAG has 11 nodes:

t0: ch = EntryToken
      t8: i64,ch = load<(load 8 from `i8 addrspace(257)* null`, addrspace 257)> t0, Constant:i64<0>, undef:i64
        t10: i64 = X86ISD::WrapperRIP TargetGlobalTLSAddress:i64<i32* @x> 0 [TF=10]
      t11: i64,ch = load<(load 8 from got)> t0, t10, undef:i64
    t12: i64 = add t8, t11
  t4: i32,ch = load<(dereferenceable load 4 from @x)> t0, t12, undef:i64
t6: ch = CopyToReg t0, Register:i32 %0, t4
And when mcmodel is large, below instruction can NOT be folded.

  t10: i64 = X86ISD::WrapperRIP TargetGlobalTLSAddress:i64<i32* @x> 0 [TF=10]
t11: i64,ch = load<(load 8 from got)> t0, t10, undef:i64
So "t11: i64,ch = load<(load 8 from got)> t0, t10, undef:i64" is lowered to " Morphed node: t11: i64,ch = MOV64rm<Mem:(load 8 from got)> t10, TargetConstant:i8<1>, Register:i64 $noreg, TargetConstant:i32<0>, Register:i32 $noreg, t0"

When llvm start to lower "t10: i64 = X86ISD::WrapperRIP TargetGlobalTLSAddress:i64<i32* @x> 0 [TF=10]", it fails.

The patch is to fold the load and X86ISD::WrapperRIP.

Fixes PR26906

Patch by LuoYuanke

Reviewers: craig.topper, rnk, annita.zhang, wxiao3

Reviewed By: rnk

Subscribers: llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D58336

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@354756 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 79 insertions, 5 deletions

diff --git a/lib/Target/X86/X86ISelDAGToDAG.cpp b/lib/Target/X86/X86ISelDAGToDAG.cpp
index 25fb5d74698..5f051b39cd5 100644
--- a/lib/Target/X86/X86ISelDAGToDAG.cpp
+++ b/lib/Target/X86/X86ISelDAGToDAG.cpp
@@ -1137,15 +1137,23 @@ bool X86DAGToDAGISel::matchWrapper(SDValue N, X86ISelAddressMode &AM) {
   if (AM.hasSymbolicDisplacement())
     return true;
 
+  bool IsRIPRelTLS = false;
   bool IsRIPRel = N.getOpcode() == X86ISD::WrapperRIP;
+  if (IsRIPRel) {
+    SDValue Val = N.getOperand(0);
+    if (Val.getOpcode() == ISD::TargetGlobalTLSAddress)
+      IsRIPRelTLS = true;
+  }
 
-  // We can't use an addressing mode in the 64-bit large code model. In the
-  // medium code model, we use can use an mode when RIP wrappers are present.
-  // That signifies access to globals that are known to be "near", such as the
-  // GOT itself.
+  // We can't use an addressing mode in the 64-bit large code model.
+  // Global TLS addressing is an exception. In the medium code model,
+  // we use can use a mode when RIP wrappers are present.
+  // That signifies access to globals that are known to be "near",
+  // such as the GOT itself.
   CodeModel::Model M = TM.getCodeModel();
   if (Subtarget->is64Bit() &&
-      (M == CodeModel::Large || (M == CodeModel::Medium && !IsRIPRel)))
+      ((M == CodeModel::Large && !IsRIPRelTLS) ||
+       (M == CodeModel::Medium && !IsRIPRel)))
     return true;
 
   // Base and index reg must be 0 in order to use %rip as base.
diff --git a/test/CodeGen/X86/code-model-elf.ll b/test/CodeGen/X86/code-model-elf.ll
index 56d3f4c102f..f7ffd6ea1eb 100644
--- a/test/CodeGen/X86/code-model-elf.ll
+++ b/test/CodeGen/X86/code-model-elf.ll
@@ -37,6 +37,8 @@ target triple = "x86_64--linux"
 @global_data = dso_local global [10 x i32] [i32 1, i32 2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0], align 16
 @static_data = internal global [10 x i32] zeroinitializer, align 16
 @extern_data = external global [10 x i32], align 16
+@thread_data = external thread_local global i32, align 4
+
 
 define dso_local i32* @lea_static_data() #0 {
 ; SMALL-STATIC-LABEL: lea_static_data:
@@ -373,6 +375,70 @@ define dso_local void ()* @lea_extern_fn() #0 {
   ret void ()* @extern_fn
 }
 
+; FIXME: The result is same for small, medium and large model, because we
+; specify pie option in the test case. And the type of tls is initial exec tls.
+; For pic code. The large model code for pic tls should be emitted as below.
+
+; .L3:
+; leaq	.L3(%rip), %rbx
+; movabsq	$_GLOBAL_OFFSET_TABLE_-.L3, %r11
+; addq	%r11, %rbx
+; leaq	thread_data@TLSGD(%rip), %rdi
+; movabsq	$__tls_get_addr@PLTOFF, %rax
+; addq	%rbx, %rax
+; call	*%rax
+; movl	(%rax), %eax
+
+; The medium and small model code for pic tls should be emitted as below.
+; data16
+; leaq	thread_data@TLSGD(%rip), %rdi
+; data16
+; data16
+; rex64
+; callq	__tls_get_addr@PLT
+; movl	(%rax), %eax
+
+define dso_local i32 @load_thread_data() #0 {
+; SMALL-STATIC-LABEL: load_thread_data:
+; SMALL-STATIC:       # %bb.0:
+; SMALL-STATIC-NEXT:    movq    thread_data@GOTTPOFF(%rip), %rax
+; SMALL-STATIC-NEXT:    movl    %fs:(%rax), %eax
+; SMALL-STATIC-NEXT:    retq
+;
+; MEDIUM-STATIC-LABEL: load_thread_data:
+; MEDIUM-STATIC:       # %bb.0:
+; MEDIUM-STATIC-NEXT:    movq    thread_data@GOTTPOFF(%rip), %rax
+; MEDIUM-STATIC-NEXT:    movl    %fs:(%rax), %eax
+; MEDIUM-STATIC-NEXT:    retq
+;
+; LARGE-STATIC-LABEL: load_thread_data:
+; LARGE-STATIC:       # %bb.0:
+; LARGE-STATIC-NEXT:    movq    thread_data@GOTTPOFF(%rip), %rax
+; LARGE-STATIC-NEXT:    movl    %fs:(%rax), %eax
+; LARGE-STATIC-NEXT:    retq
+;
+; SMALL-PIC-LABEL: load_thread_data:
+; SMALL-PIC:       # %bb.0:
+; SMALL-PIC-NEXT:    movq    thread_data@GOTTPOFF(%rip), %rax
+; SMALL-PIC-NEXT:    movl    %fs:(%rax), %eax
+; SMALL-PIC-NEXT:    retq
+;
+; MEDIUM-PIC-LABEL: load_thread_data:
+; MEDIUM-PIC:       # %bb.0:
+; MEDIUM-PIC-NEXT:    movq    thread_data@GOTTPOFF(%rip), %rax
+; MEDIUM-PIC-NEXT:    movl    %fs:(%rax), %eax
+; MEDIUM-PIC-NEXT:    retq
+;
+; LARGE-PIC-LABEL: load_thread_data:
+; LARGE-PIC:       # %bb.0:
+; LARGE-PIC-NEXT:    movq    thread_data@GOTTPOFF(%rip), %rax
+; LARGE-PIC-NEXT:    movl    %fs:(%rax), %eax
+; LARGE-PIC-NEXT:    retq
+;
+  %1 = load i32, i32* @thread_data, align 4
+  ret i32 %1
+}
+
 attributes #0 = { noinline nounwind uwtable }
 
 !llvm.module.flags = !{!0, !1, !2}