Merging r325049:

------------------------------------------------------------------------
r325049 | rnk | 2018-02-13 12:47:49 -0800 (Tue, 13 Feb 2018) | 17 lines

[X86] Use EDI for retpoline when no scratch regs are left

Summary:
Instead of solving the hard problem of how to pass the callee to the indirect
jump thunk without a register, just use a CSR. At a call boundary, there's
nothing stopping us from using a CSR to hold the callee as long as we save and
restore it in the prologue.

Also, add tests for this mregparm=3 case. I wrote execution tests for
__llvm_retpoline_push, but they never got committed as lit tests, either
because I never rewrote them or because they got lost in merge conflicts.

Reviewers: chandlerc, dwmw2

Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits

Differential Revision: https://reviews.llvm.org/D43214
------------------------------------------------------------------------


git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325084 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 47 insertions, 9 deletions

diff --git a/test/CodeGen/X86/retpoline-regparm.ll b/test/CodeGen/X86/retpoline-regparm.ll
new file mode 100644
index 00000000000..13b32740b28
--- /dev/null
+++ b/test/CodeGen/X86/retpoline-regparm.ll
@@ -0,0 +1,42 @@
+; RUN: llc -mtriple=i686-linux < %s | FileCheck --implicit-check-not="jmp.*\*" --implicit-check-not="call.*\*" %s
+
+; Test 32-bit retpoline when -mregparm=3 is used. This case is interesting
+; because there are no available scratch registers.  The Linux kernel builds
+; with -mregparm=3, so we need to support it.  TCO should fail because we need
+; to restore EDI.
+
+define void @call_edi(void (i32, i32, i32)* %fp) #0 {
+entry:
+  tail call void %fp(i32 inreg 0, i32 inreg 0, i32 inreg 0)
+  ret void
+}
+
+; CHECK-LABEL: call_edi:
+;     EDI is used, so it must be saved.
+; CHECK: pushl %edi
+; CHECK-DAG: xorl %eax, %eax
+; CHECK-DAG: xorl %edx, %edx
+; CHECK-DAG: xorl %ecx, %ecx
+; CHECK-DAG: movl {{.*}}, %edi
+; CHECK: calll __llvm_retpoline_edi
+; CHECK: popl %edi
+; CHECK: retl
+
+define void @edi_external(void (i32, i32, i32)* %fp) #1 {
+entry:
+  tail call void %fp(i32 inreg 0, i32 inreg 0, i32 inreg 0)
+  ret void
+}
+
+; CHECK-LABEL: edi_external:
+; CHECK: pushl %edi
+; CHECK-DAG: xorl %eax, %eax
+; CHECK-DAG: xorl %edx, %edx
+; CHECK-DAG: xorl %ecx, %ecx
+; CHECK-DAG: movl {{.*}}, %edi
+; CHECK: calll __x86_indirect_thunk_edi
+; CHECK: popl %edi
+; CHECK: retl
+
+attributes #0 = { "target-features"="+retpoline" }
+attributes #1 = { "target-features"="+retpoline-external-thunk" }
diff --git a/test/CodeGen/X86/retpoline.ll b/test/CodeGen/X86/retpoline.ll
index 57d3388b812..477609e2d10 100644
--- a/test/CodeGen/X86/retpoline.ll
+++ b/test/CodeGen/X86/retpoline.ll
@@ -340,10 +340,10 @@ latch:
 ; X86-NEXT:          movl    %edx, (%esp)
 ; X86-NEXT:          retl
 ;
-; X86-LABEL:         .section        .text.__llvm_retpoline_push,{{.*}},__llvm_retpoline_push,comdat
-; X86-NEXT:          .hidden __llvm_retpoline_push
-; X86-NEXT:          .weak   __llvm_retpoline_push
-; X86:       __llvm_retpoline_push:
+; X86-LABEL:         .section        .text.__llvm_retpoline_edi,{{.*}},__llvm_retpoline_edi,comdat
+; X86-NEXT:          .hidden __llvm_retpoline_edi
+; X86-NEXT:          .weak   __llvm_retpoline_edi
+; X86:       __llvm_retpoline_edi:
 ; X86-NEXT:  # {{.*}}                                # %entry
 ; X86-NEXT:          calll   [[CALL_TARGET:.*]]
 ; X86-NEXT:  [[CAPTURE_SPEC:.*]]:                    # Block address taken
@@ -355,11 +355,7 @@ latch:
 ; X86-NEXT:          .p2align        4, 0x90
 ; X86-NEXT:  [[CALL_TARGET]]:                        # Block address taken
 ; X86-NEXT:                                          # %entry
-; X86-NEXT:          addl    $4, %esp
-; X86-NEXT:          pushl   4(%esp)
-; X86-NEXT:          pushl   4(%esp)
-; X86-NEXT:          popl    8(%esp)
-; X86-NEXT:          popl    (%esp)
+; X86-NEXT:          movl    %edi, (%esp)
 ; X86-NEXT:          retl