CXX_FAST_TLS calling convention: fix issue on X86-64.

When we have a single basic block, the explicit copy-back instructions should
be inserted right before the terminator. Before this fix, they were wrongly
placed at the beginning of the basic block.

I will commit fixes to other platforms as well.

PR26136

llvm-svn: 257925

2 files changed, 20 insertions, 4 deletions

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index b723059f091..6904714ec78 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -28908,6 +28908,7 @@ void X86TargetLowering::insertCopiesSplitCSR(
 
   const TargetInstrInfo *TII = Subtarget->getInstrInfo();
   MachineRegisterInfo *MRI = &Entry->getParent()->getRegInfo();
+  MachineBasicBlock::iterator MBBI = Entry->begin();
   for (const MCPhysReg *I = IStart; *I; ++I) {
     const TargetRegisterClass *RC = nullptr;
     if (X86::GR64RegClass.contains(*I))
@@ -28925,13 +28926,13 @@ void X86TargetLowering::insertCopiesSplitCSR(
                Attribute::NoUnwind) &&
            "Function should be nounwind in insertCopiesSplitCSR!");
     Entry->addLiveIn(*I);
-    BuildMI(*Entry, Entry->begin(), DebugLoc(), TII->get(TargetOpcode::COPY),
-            NewVR)
+    BuildMI(*Entry, MBBI, DebugLoc(), TII->get(TargetOpcode::COPY), NewVR)
         .addReg(*I);
 
+    // Insert the copy-back instructions right before the terminator.
     for (auto *Exit : Exits)
-      BuildMI(*Exit, Exit->begin(), DebugLoc(), TII->get(TargetOpcode::COPY),
-              *I)
+      BuildMI(*Exit, Exit->getFirstTerminator(), DebugLoc(),
+              TII->get(TargetOpcode::COPY), *I)
           .addReg(NewVR);
   }
 }
diff --git a/llvm/test/CodeGen/X86/cxx_tlscc64.ll b/llvm/test/CodeGen/X86/cxx_tlscc64.ll
index 70fe501040b..7f6e0d71cd7 100644
--- a/llvm/test/CodeGen/X86/cxx_tlscc64.ll
+++ b/llvm/test/CodeGen/X86/cxx_tlscc64.ll
@@ -9,6 +9,7 @@
 @sg = internal thread_local global %struct.S zeroinitializer, align 1
 @__dso_handle = external global i8
 @__tls_guard = internal thread_local unnamed_addr global i1 false
+@sum1 = internal thread_local global i32 0, align 4
 
 declare void @_ZN1SC1Ev(%struct.S*)
 declare void @_ZN1SD1Ev(%struct.S*)
@@ -50,3 +51,17 @@ init.i:
 __tls_init.exit:
   ret %struct.S* @sg
 }
+
+; CHECK-LABEL: _ZTW4sum1
+; CHECK-NOT: pushq %r11
+; CHECK-NOT: pushq %r10
+; CHECK-NOT: pushq %r9
+; CHECK-NOT: pushq %r8
+; CHECK-NOT: pushq %rsi
+; CHECK-NOT: pushq %rdx
+; CHECK-NOT: pushq %rcx
+; CHECK-NOT: pushq %rbx
+; CHECK: callq
+define cxx_fast_tlscc nonnull i32* @_ZTW4sum1() nounwind {
+  ret i32* @sum1
+}