Merging r324449:

------------------------------------------------------------------------
r324449 | chandlerc | 2018-02-06 22:16:24 -0800 (Tue, 06 Feb 2018) | 15 lines

[x86/retpoline] Make the external thunk names exactly match the names
that happened to end up in GCC.

This is really unfortunate, as the names don't have much rhyme or reason
to them. Originally in the discussions it seemed fine to rely on aliases
to map different names to whatever external thunk code developers wished
to use but there are practical problems with that in the kernel it turns
out. And since we're discovering this practical problems late and since
GCC has already shipped a release with one set of names, we are forced,
yet again, to blindly match what is there.

Somewhat rushing this patch out for the Linux kernel folks to test and
so we can get it patched into our releases.

Differential Revision: https://reviews.llvm.org/D42998
------------------------------------------------------------------------


git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325082 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 68 insertions, 39 deletions

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 38885c42b52..d036e49a447 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -27094,28 +27094,57 @@ static unsigned getOpcodeForRetpoline(unsigned RPOpc) {
 
 static const char *getRetpolineSymbol(const X86Subtarget &Subtarget,
                                       unsigned Reg) {
+  if (Subtarget.useRetpolineExternalThunk()) {
+    // When using an external thunk for retpolines, we pick names that match the
+    // names GCC happens to use as well. This helps simplify the implementation
+    // of the thunks for kernels where they have no easy ability to create
+    // aliases and are doing non-trivial configuration of the thunk's body. For
+    // example, the Linux kernel will do boot-time hot patching of the thunk
+    // bodies and cannot easily export aliases of these to loaded modules.
+    //
+    // Note that at any point in the future, we may need to change the semantics
+    // of how we implement retpolines and at that time will likely change the
+    // name of the called thunk. Essentially, there is no hard guarantee that
+    // LLVM will generate calls to specific thunks, we merely make a best-effort
+    // attempt to help out kernels and other systems where duplicating the
+    // thunks is costly.
+    switch (Reg) {
+    case 0:
+      assert(!Subtarget.is64Bit() && "R11 should always be available on x64");
+      return "__x86_indirect_thunk";
+    case X86::EAX:
+      assert(!Subtarget.is64Bit() && "Should not be using a 32-bit thunk!");
+      return "__x86_indirect_thunk_eax";
+    case X86::ECX:
+      assert(!Subtarget.is64Bit() && "Should not be using a 32-bit thunk!");
+      return "__x86_indirect_thunk_ecx";
+    case X86::EDX:
+      assert(!Subtarget.is64Bit() && "Should not be using a 32-bit thunk!");
+      return "__x86_indirect_thunk_edx";
+    case X86::R11:
+      assert(Subtarget.is64Bit() && "Should not be using a 64-bit thunk!");
+      return "__x86_indirect_thunk_r11";
+    }
+    llvm_unreachable("unexpected reg for retpoline");
+  }
+
+  // When targeting an internal COMDAT thunk use an LLVM-specific name.
   switch (Reg) {
   case 0:
     assert(!Subtarget.is64Bit() && "R11 should always be available on x64");
-    return Subtarget.useRetpolineExternalThunk()
-               ? "__llvm_external_retpoline_push"
-               : "__llvm_retpoline_push";
+    return "__llvm_retpoline_push";
   case X86::EAX:
-    return Subtarget.useRetpolineExternalThunk()
-               ? "__llvm_external_retpoline_eax"
-               : "__llvm_retpoline_eax";
+    assert(!Subtarget.is64Bit() && "Should not be using a 32-bit thunk!");
+    return "__llvm_retpoline_eax";
   case X86::ECX:
-    return Subtarget.useRetpolineExternalThunk()
-               ? "__llvm_external_retpoline_ecx"
-               : "__llvm_retpoline_ecx";
+    assert(!Subtarget.is64Bit() && "Should not be using a 32-bit thunk!");
+    return "__llvm_retpoline_ecx";
   case X86::EDX:
-    return Subtarget.useRetpolineExternalThunk()
-               ? "__llvm_external_retpoline_edx"
-               : "__llvm_retpoline_edx";
+    assert(!Subtarget.is64Bit() && "Should not be using a 32-bit thunk!");
+    return "__llvm_retpoline_edx";
   case X86::R11:
-    return Subtarget.useRetpolineExternalThunk()
-               ? "__llvm_external_retpoline_r11"
-               : "__llvm_retpoline_r11";
+    assert(Subtarget.is64Bit() && "Should not be using a 64-bit thunk!");
+    return "__llvm_retpoline_r11";
   }
   llvm_unreachable("unexpected reg for retpoline");
 }
diff --git a/test/CodeGen/X86/retpoline-external.ll b/test/CodeGen/X86/retpoline-external.ll
index 66d32ba5d73..2f21bb2566d 100644
--- a/test/CodeGen/X86/retpoline-external.ll
+++ b/test/CodeGen/X86/retpoline-external.ll
@@ -23,18 +23,18 @@ entry:
 ; X64:       callq bar
 ; X64-DAG:   movl %[[x]], %edi
 ; X64-DAG:   movq %[[fp]], %r11
-; X64:       callq __llvm_external_retpoline_r11
+; X64:       callq __x86_indirect_thunk_r11
 ; X64:       movl %[[x]], %edi
 ; X64:       callq bar
 ; X64-DAG:   movl %[[x]], %edi
 ; X64-DAG:   movq %[[fp]], %r11
-; X64:       jmp __llvm_external_retpoline_r11 # TAILCALL
+; X64:       jmp __x86_indirect_thunk_r11 # TAILCALL
 
 ; X64FAST-LABEL: icall_reg:
 ; X64FAST:       callq bar
-; X64FAST:       callq __llvm_external_retpoline_r11
+; X64FAST:       callq __x86_indirect_thunk_r11
 ; X64FAST:       callq bar
-; X64FAST:       jmp __llvm_external_retpoline_r11 # TAILCALL
+; X64FAST:       jmp __x86_indirect_thunk_r11 # TAILCALL
 
 ; X86-LABEL: icall_reg:
 ; X86-DAG:   movl 12(%esp), %[[fp:[^ ]*]]
@@ -43,19 +43,19 @@ entry:
 ; X86:       calll bar
 ; X86:       movl %[[fp]], %eax
 ; X86:       pushl %[[x]]
-; X86:       calll __llvm_external_retpoline_eax
+; X86:       calll __x86_indirect_thunk_eax
 ; X86:       pushl %[[x]]
 ; X86:       calll bar
 ; X86:       movl %[[fp]], %eax
 ; X86:       pushl %[[x]]
-; X86:       calll __llvm_external_retpoline_eax
+; X86:       calll __x86_indirect_thunk_eax
 ; X86-NOT:   # TAILCALL
 
 ; X86FAST-LABEL: icall_reg:
 ; X86FAST:       calll bar
-; X86FAST:       calll __llvm_external_retpoline_eax
+; X86FAST:       calll __x86_indirect_thunk_eax
 ; X86FAST:       calll bar
-; X86FAST:       calll __llvm_external_retpoline_eax
+; X86FAST:       calll __x86_indirect_thunk_eax
 
 
 @global_fp = external global void (i32)*
@@ -72,28 +72,28 @@ define void @icall_global_fp(i32 %x, void (i32)** %fpp) #0 {
 ; X64-LABEL: icall_global_fp:
 ; X64-DAG:   movl %edi, %[[x:[^ ]*]]
 ; X64-DAG:   movq global_fp(%rip), %r11
-; X64:       callq __llvm_external_retpoline_r11
+; X64:       callq __x86_indirect_thunk_r11
 ; X64-DAG:   movl %[[x]], %edi
 ; X64-DAG:   movq global_fp(%rip), %r11
-; X64:       jmp __llvm_external_retpoline_r11 # TAILCALL
+; X64:       jmp __x86_indirect_thunk_r11 # TAILCALL
 
 ; X64FAST-LABEL: icall_global_fp:
 ; X64FAST:       movq global_fp(%rip), %r11
-; X64FAST:       callq __llvm_external_retpoline_r11
+; X64FAST:       callq __x86_indirect_thunk_r11
 ; X64FAST:       movq global_fp(%rip), %r11
-; X64FAST:       jmp __llvm_external_retpoline_r11 # TAILCALL
+; X64FAST:       jmp __x86_indirect_thunk_r11 # TAILCALL
 
 ; X86-LABEL: icall_global_fp:
 ; X86:       movl global_fp, %eax
 ; X86:       pushl 4(%esp)
-; X86:       calll __llvm_external_retpoline_eax
+; X86:       calll __x86_indirect_thunk_eax
 ; X86:       addl $4, %esp
 ; X86:       movl global_fp, %eax
-; X86:       jmp __llvm_external_retpoline_eax # TAILCALL
+; X86:       jmp __x86_indirect_thunk_eax # TAILCALL
 
 ; X86FAST-LABEL: icall_global_fp:
-; X86FAST:       calll __llvm_external_retpoline_eax
-; X86FAST:       jmp __llvm_external_retpoline_eax # TAILCALL
+; X86FAST:       calll __x86_indirect_thunk_eax
+; X86FAST:       jmp __x86_indirect_thunk_eax # TAILCALL
 
 
 %struct.Foo = type { void (%struct.Foo*)** }
@@ -114,14 +114,14 @@ define void @vcall(%struct.Foo* %obj) #0 {
 ; X64:       movq (%[[obj]]), %[[vptr:[^ ]*]]
 ; X64:       movq 8(%[[vptr]]), %[[fp:[^ ]*]]
 ; X64:       movq %[[fp]], %r11
-; X64:       callq __llvm_external_retpoline_r11
+; X64:       callq __x86_indirect_thunk_r11
 ; X64-DAG:   movq %[[obj]], %rdi
 ; X64-DAG:   movq %[[fp]], %r11
-; X64:       jmp __llvm_external_retpoline_r11 # TAILCALL
+; X64:       jmp __x86_indirect_thunk_r11 # TAILCALL
 
 ; X64FAST-LABEL: vcall:
-; X64FAST:       callq __llvm_external_retpoline_r11
-; X64FAST:       jmp __llvm_external_retpoline_r11 # TAILCALL
+; X64FAST:       callq __x86_indirect_thunk_r11
+; X64FAST:       jmp __x86_indirect_thunk_r11 # TAILCALL
 
 ; X86-LABEL: vcall:
 ; X86:       movl 8(%esp), %[[obj:[^ ]*]]
@@ -129,14 +129,14 @@ define void @vcall(%struct.Foo* %obj) #0 {
 ; X86:       movl 4(%[[vptr]]), %[[fp:[^ ]*]]
 ; X86:       movl %[[fp]], %eax
 ; X86:       pushl %[[obj]]
-; X86:       calll __llvm_external_retpoline_eax
+; X86:       calll __x86_indirect_thunk_eax
 ; X86:       addl $4, %esp
 ; X86:       movl %[[fp]], %eax
-; X86:       jmp __llvm_external_retpoline_eax # TAILCALL
+; X86:       jmp __x86_indirect_thunk_eax # TAILCALL
 
 ; X86FAST-LABEL: vcall:
-; X86FAST:       calll __llvm_external_retpoline_eax
-; X86FAST:       jmp __llvm_external_retpoline_eax # TAILCALL
+; X86FAST:       calll __x86_indirect_thunk_eax
+; X86FAST:       jmp __x86_indirect_thunk_eax # TAILCALL
 
 
 declare void @direct_callee()