[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
llvm-svn: 325049
diff --git a/llvm/lib/Target/X86/X86RetpolineThunks.cpp b/llvm/lib/Target/X86/X86RetpolineThunks.cpp
index 223fa57..59ace3f 100644
--- a/llvm/lib/Target/X86/X86RetpolineThunks.cpp
+++ b/llvm/lib/Target/X86/X86RetpolineThunks.cpp
@@ -43,7 +43,7 @@
static const char EAXThunkName[] = "__llvm_retpoline_eax";
static const char ECXThunkName[] = "__llvm_retpoline_ecx";
static const char EDXThunkName[] = "__llvm_retpoline_edx";
-static const char PushThunkName[] = "__llvm_retpoline_push";
+static const char EDIThunkName[] = "__llvm_retpoline_edi";
namespace {
class X86RetpolineThunks : public MachineFunctionPass {
@@ -127,7 +127,7 @@
createThunkFunction(M, R11ThunkName);
else
for (StringRef Name :
- {EAXThunkName, ECXThunkName, EDXThunkName, PushThunkName})
+ {EAXThunkName, ECXThunkName, EDXThunkName, EDIThunkName})
createThunkFunction(M, Name);
InsertedThunks = true;
return true;
@@ -151,9 +151,8 @@
populateThunk(MF, X86::R11);
} else {
// For 32-bit targets we need to emit a collection of thunks for various
- // possible scratch registers as well as a fallback that is used when
- // there are no scratch registers and assumes the retpoline target has
- // been pushed.
+ // possible scratch registers as well as a fallback that uses EDI, which is
+ // normally callee saved.
// __llvm_retpoline_eax:
// calll .Leax_call_target
// .Leax_capture_spec:
@@ -174,32 +173,18 @@
// movl %edx, (%esp)
// retl
//
- // This last one is a bit more special and so needs a little extra
- // handling.
- // __llvm_retpoline_push:
- // calll .Lpush_call_target
- // .Lpush_capture_spec:
- // pause
- // lfence
- // jmp .Lpush_capture_spec
- // .align 16
- // .Lpush_call_target:
- // # Clear pause_loop return address.
- // addl $4, %esp
- // # Top of stack words are: Callee, RA. Exchange Callee and RA.
- // pushl 4(%esp) # Push callee
- // pushl 4(%esp) # Push RA
- // popl 8(%esp) # Pop RA to final RA
- // popl (%esp) # Pop callee to next top of stack
- // retl # Ret to callee
+ // __llvm_retpoline_edi:
+ // ... # Same setup
+ // movl %edi, (%esp)
+ // retl
if (MF.getName() == EAXThunkName)
populateThunk(MF, X86::EAX);
else if (MF.getName() == ECXThunkName)
populateThunk(MF, X86::ECX);
else if (MF.getName() == EDXThunkName)
populateThunk(MF, X86::EDX);
- else if (MF.getName() == PushThunkName)
- populateThunk(MF);
+ else if (MF.getName() == EDIThunkName)
+ populateThunk(MF, X86::EDI);
else
llvm_unreachable("Invalid thunk name on x86-32!");
}
@@ -301,11 +286,6 @@
CaptureSpec->addSuccessor(CaptureSpec);
CallTarget->setAlignment(4);
- if (Reg) {
- insertRegReturnAddrClobber(*CallTarget, *Reg);
- } else {
- assert(!Is64Bit && "We only support non-reg thunks on 32-bit x86!");
- insert32BitPushReturnAddrClobber(*CallTarget);
- }
+ insertRegReturnAddrClobber(*CallTarget, *Reg);
BuildMI(CallTarget, DebugLoc(), TII->get(RetOpc));
}