[llvm] r337878 - [x86/SLH] Teach the x86 speculative load hardening pass to harden
Chandler Carruth via llvm-commits
llvm-commits at lists.llvm.org
Tue Jul 24 18:51:29 PDT 2018
Author: chandlerc
Date: Tue Jul 24 18:51:29 2018
New Revision: 337878
URL: http://llvm.org/viewvc/llvm-project?rev=337878&view=rev
Log:
[x86/SLH] Teach the x86 speculative load hardening pass to harden
against v1.2 BCBS attacks directly.
Attacks using spectre v1.2 (a subset of BCBS) are described in the paper
here:
https://people.csail.mit.edu/vlk/spectre11.pdf
The core idea is to speculatively store over the address in a vtable,
jumptable, or other target of indirect control flow that will be
subsequently loaded. Speculative execution after such a store can
forward the stored value to subsequent loads, and if called or jumped
to, the speculative execution will be steered to this potentially
attacker controlled address.
Up until now, this could be mitigated by enableing retpolines. However,
that is a relatively expensive technique to mitigate this particular
flavor. Especially because in most cases SLH will have already mitigated
this. To fully mitigate this with SLH, we need to do two core things:
1) Unfold loads from calls and jumps, allowing the loads to be post-load
hardened.
2) Force hardening of incoming registers even if we didn't end up
needing to harden the load itself.
The reason we need to do these two things is because hardening calls and
jumps from this particular variant is importantly different from
hardening against leak of secret data. Because the "bad" data here isn't
a secret, but in fact speculatively stored by the attacker, it may be
loaded from any address, regardless of whether it is read-only memory,
mapped memory, or a "hardened" address. The only 100% effective way to
harden these instructions is to harden the their operand itself. But to
the extent possible, we'd like to take advantage of all the other
hardening going on, we just need a fallback in case none of that
happened to cover the particular input to the control transfer
instruction.
For users of SLH, currently they are paing 2% to 6% performance overhead
for retpolines, but this mechanism is expected to be substantially
cheaper. However, it is worth reminding folks that this does not
mitigate all of the things retpolines do -- most notably, variant #2 is
not in *any way* mitigated by this technique. So users of SLH may still
want to enable retpolines, and the implementation is carefuly designed to
gracefully leverage retpolines to avoid the need for further hardening
here when they are enabled.
Differential Revision: https://reviews.llvm.org/D49663
Modified:
llvm/trunk/lib/Target/X86/X86SpeculativeLoadHardening.cpp
llvm/trunk/test/CodeGen/X86/speculative-load-hardening-indirect.ll
Modified: llvm/trunk/lib/Target/X86/X86SpeculativeLoadHardening.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86SpeculativeLoadHardening.cpp?rev=337878&r1=337877&r2=337878&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86SpeculativeLoadHardening.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86SpeculativeLoadHardening.cpp Tue Jul 24 18:51:29 2018
@@ -70,6 +70,8 @@ STATISTIC(NumAddrRegsHardened,
"Number of address mode used registers hardaned");
STATISTIC(NumPostLoadRegsHardened,
"Number of post-load register values hardened");
+STATISTIC(NumCallsOrJumpsHardened,
+ "Number of calls or jumps requiring extra hardening");
STATISTIC(NumInstsInserted, "Number of instructions inserted");
STATISTIC(NumLFENCEsInserted, "Number of lfence instructions inserted");
@@ -105,6 +107,13 @@ static cl::opt<bool>
"significant security is provided."),
cl::init(true), cl::Hidden);
+static cl::opt<bool> HardenIndirectCallsAndJumps(
+ PASS_KEY "-indirect",
+ cl::desc("Harden indirect calls and jumps against using speculatively "
+ "stored attacker controlled addresses. This is designed to "
+ "mitigate Spectre v1.2 style attacks."),
+ cl::init(true), cl::Hidden);
+
namespace llvm {
void initializeX86SpeculativeLoadHardeningPassPass(PassRegistry &);
@@ -168,6 +177,8 @@ private:
SmallVector<MachineInstr *, 16>
tracePredStateThroughCFG(MachineFunction &MF, ArrayRef<BlockCondInfo> Infos);
+ void unfoldCallAndJumpLoads(MachineFunction &MF);
+
void hardenAllLoads(MachineFunction &MF);
unsigned saveEFLAGS(MachineBasicBlock &MBB,
@@ -196,6 +207,9 @@ private:
DebugLoc Loc);
unsigned hardenPostLoad(MachineInstr &MI);
void hardenReturnInstr(MachineInstr &MI);
+ void hardenIndirectCallOrJumpInstr(
+ MachineInstr &MI,
+ SmallDenseMap<unsigned, unsigned, 32> &AddrRegToHardenedReg);
};
} // end anonymous namespace
@@ -507,6 +521,11 @@ bool X86SpeculativeLoadHardeningPass::ru
}
}
+ // If we are going to harden calls and jumps we need to unfold their memory
+ // operands.
+ if (HardenIndirectCallsAndJumps)
+ unfoldCallAndJumpLoads(MF);
+
// Now harden all of the loads in the function using the predicate state.
hardenAllLoads(MF);
@@ -817,6 +836,110 @@ X86SpeculativeLoadHardeningPass::tracePr
return CMovs;
}
+/// Compute the register class for the unfolded load.
+///
+/// FIXME: This should probably live in X86InstrInfo, potentially by adding
+/// a way to unfold into a newly created vreg rather than requiring a register
+/// input.
+static const TargetRegisterClass *
+getRegClassForUnfoldedLoad(MachineFunction &MF, const X86InstrInfo &TII,
+ unsigned Opcode) {
+ unsigned Index;
+ unsigned UnfoldedOpc = TII.getOpcodeAfterMemoryUnfold(
+ Opcode, /*UnfoldLoad*/ true, /*UnfoldStore*/ false, &Index);
+ const MCInstrDesc &MCID = TII.get(UnfoldedOpc);
+ return TII.getRegClass(MCID, Index, &TII.getRegisterInfo(), MF);
+}
+
+void X86SpeculativeLoadHardeningPass::unfoldCallAndJumpLoads(
+ MachineFunction &MF) {
+ for (MachineBasicBlock &MBB : MF)
+ for (auto MII = MBB.instr_begin(), MIE = MBB.instr_end(); MII != MIE;) {
+ // Grab a reference and increment the iterator so we can remove this
+ // instruction if needed without disturbing the iteration.
+ MachineInstr &MI = *MII++;
+
+ // Must either be a call or a branch.
+ if (!MI.isCall() && !MI.isBranch())
+ continue;
+ // We only care about loading variants of these instructions.
+ if (!MI.mayLoad())
+ continue;
+
+ switch (MI.getOpcode()) {
+ default: {
+ LLVM_DEBUG(
+ dbgs() << "ERROR: Found an unexpected loading branch or call "
+ "instruction:\n";
+ MI.dump(); dbgs() << "\n");
+ report_fatal_error("Unexpected loading branch or call!");
+ }
+
+ case X86::FARCALL16m:
+ case X86::FARCALL32m:
+ case X86::FARCALL64:
+ case X86::FARJMP16m:
+ case X86::FARJMP32m:
+ case X86::FARJMP64:
+ // We cannot mitigate far jumps or calls, but we also don't expect them
+ // to be vulnerable to Spectre v1.2 style attacks.
+ continue;
+
+ case X86::CALL16m:
+ case X86::CALL16m_NT:
+ case X86::CALL32m:
+ case X86::CALL32m_NT:
+ case X86::CALL64m:
+ case X86::CALL64m_NT:
+ case X86::JMP16m:
+ case X86::JMP16m_NT:
+ case X86::JMP32m:
+ case X86::JMP32m_NT:
+ case X86::JMP64m:
+ case X86::JMP64m_NT:
+ case X86::TAILJMPm64:
+ case X86::TAILJMPm64_REX:
+ case X86::TAILJMPm:
+ case X86::TCRETURNmi64:
+ case X86::TCRETURNmi: {
+ // Use the generic unfold logic now that we know we're dealing with
+ // expected instructions.
+ // FIXME: We don't have test coverage for all of these!
+ auto *UnfoldedRC = getRegClassForUnfoldedLoad(MF, *TII, MI.getOpcode());
+ if (!UnfoldedRC) {
+ LLVM_DEBUG(dbgs()
+ << "ERROR: Unable to unfold load from instruction:\n";
+ MI.dump(); dbgs() << "\n");
+ report_fatal_error("Unable to unfold load!");
+ }
+ unsigned Reg = MRI->createVirtualRegister(UnfoldedRC);
+ SmallVector<MachineInstr *, 2> NewMIs;
+ // If we were able to compute an unfolded reg class, any failure here
+ // is just a programming error so just assert.
+ bool Unfolded =
+ TII->unfoldMemoryOperand(MF, MI, Reg, /*UnfoldLoad*/ true,
+ /*UnfoldStore*/ false, NewMIs);
+ (void)Unfolded;
+ assert(Unfolded &&
+ "Computed unfolded register class but failed to unfold");
+ // Now stitch the new instructions into place and erase the old one.
+ for (auto *NewMI : NewMIs)
+ MBB.insert(MI.getIterator(), NewMI);
+ MI.eraseFromParent();
+ LLVM_DEBUG({
+ dbgs() << "Unfolded load successfully into:\n";
+ for (auto *NewMI : NewMIs) {
+ NewMI->dump();
+ dbgs() << "\n";
+ }
+ });
+ continue;
+ }
+ }
+ llvm_unreachable("Escaped switch with default!");
+ }
+}
+
/// Returns true if the instruction has no behavior (specified or otherwise)
/// that is based on the value of any of its register operands
///
@@ -1441,6 +1564,14 @@ void X86SpeculativeLoadHardeningPass::ha
continue;
}
+ // Check for an indirect call or branch that may need its input hardened
+ // even if we couldn't find the specific load used, or were able to avoid
+ // hardening it for some reason. Note that here we cannot break out
+ // afterward as we may still need to handle any call aspect of this
+ // instruction.
+ if ((MI.isCall() || MI.isBranch()) && HardenIndirectCallsAndJumps)
+ hardenIndirectCallOrJumpInstr(MI, AddrRegToHardenedReg);
+
// After we finish processing the instruction and doing any hardening
// necessary for it, we need to handle transferring the predicate state
// into a call and recovering it after the call returns (if it returns).
@@ -2010,6 +2141,75 @@ void X86SpeculativeLoadHardeningPass::ha
mergePredStateIntoSP(MBB, InsertPt, Loc, PS->SSA.GetValueAtEndOfBlock(&MBB));
}
+/// An attacker may speculatively store over a value that is then speculatively
+/// loaded and used as the target of an indirect call or jump instruction. This
+/// is called Spectre v1.2 or Bounds Check Bypass Store (BCBS) and is described
+/// in this paper:
+/// https://people.csail.mit.edu/vlk/spectre11.pdf
+///
+/// When this happens, the speculative execution of the call or jump will end up
+/// being steered to this attacker controlled address. While most such loads
+/// will be adequately hardened already, we want to ensure that they are
+/// definitively treated as needing post-load hardening. While address hardening
+/// is sufficient to prevent secret data from leaking to the attacker, it may
+/// not be sufficient to prevent an attacker from steering speculative
+/// execution. We forcibly unfolded all relevant loads above and so will always
+/// have an opportunity to post-load harden here, we just need to scan for cases
+/// not already flagged and add them.
+void X86SpeculativeLoadHardeningPass::hardenIndirectCallOrJumpInstr(
+ MachineInstr &MI,
+ SmallDenseMap<unsigned, unsigned, 32> &AddrRegToHardenedReg) {
+ switch (MI.getOpcode()) {
+ case X86::FARCALL16m:
+ case X86::FARCALL32m:
+ case X86::FARCALL64:
+ case X86::FARJMP16m:
+ case X86::FARJMP32m:
+ case X86::FARJMP64:
+ // We don't need to harden either far calls or far jumps as they are
+ // safe from Spectre.
+ return;
+
+ default:
+ break;
+ }
+
+ // We should never see a loading instruction at this point, as those should
+ // have been unfolded.
+ assert(!MI.mayLoad() && "Found a lingering loading instruction!");
+
+ // If the first operand isn't a register, this is a branch or call
+ // instruction with an immediate operand which doesn't need to be hardened.
+ if (!MI.getOperand(0).isReg())
+ return;
+
+ // For all of these, the target register is the first operand of the
+ // instruction.
+ auto &TargetOp = MI.getOperand(0);
+ unsigned OldTargetReg = TargetOp.getReg();
+
+ // Try to lookup a hardened version of this register. We retain a reference
+ // here as we want to update the map to track any newly computed hardened
+ // register.
+ unsigned &HardenedTargetReg = AddrRegToHardenedReg[OldTargetReg];
+
+ // If we don't have a hardened register yet, compute one. Otherwise, just use
+ // the already hardened register.
+ //
+ // FIXME: It is a little suspect that we use partially hardened registers that
+ // only feed addresses. The complexity of partial hardening with SHRX
+ // continues to pile up. Should definitively measure its value and consider
+ // eliminating it.
+ if (!HardenedTargetReg)
+ HardenedTargetReg = hardenValueInRegister(
+ OldTargetReg, *MI.getParent(), MI.getIterator(), MI.getDebugLoc());
+
+ // Set the target operand to the hardened register.
+ TargetOp.setReg(HardenedTargetReg);
+
+ ++NumCallsOrJumpsHardened;
+}
+
INITIALIZE_PASS_BEGIN(X86SpeculativeLoadHardeningPass, DEBUG_TYPE,
"X86 speculative load hardener", false, false)
INITIALIZE_PASS_END(X86SpeculativeLoadHardeningPass, DEBUG_TYPE,
Modified: llvm/trunk/test/CodeGen/X86/speculative-load-hardening-indirect.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/speculative-load-hardening-indirect.ll?rev=337878&r1=337877&r2=337878&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/speculative-load-hardening-indirect.ll (original)
+++ llvm/trunk/test/CodeGen/X86/speculative-load-hardening-indirect.ll Tue Jul 24 18:51:29 2018
@@ -1,5 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -x86-speculative-load-hardening -data-sections | FileCheck %s --check-prefix=X64
+; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -x86-speculative-load-hardening -data-sections -mattr=+retpoline | FileCheck %s --check-prefix=X64-RETPOLINE
;
; FIXME: Add support for 32-bit.
@@ -15,16 +16,39 @@
define i32 @test_indirect_call(i32 ()** %ptr) nounwind {
; X64-LABEL: test_indirect_call:
; X64: # %bb.0: # %entry
-; X64-NEXT: pushq %rbx
-; X64-NEXT: movq %rsp, %rbx
-; X64-NEXT: movq $-1, %rax
-; X64-NEXT: sarq $63, %rbx
-; X64-NEXT: orq %rbx, %rdi
-; X64-NEXT: callq *(%rdi)
-; X64-NEXT: shlq $47, %rbx
-; X64-NEXT: orq %rbx, %rsp
-; X64-NEXT: popq %rbx
+; X64-NEXT: pushq %rax
+; X64-NEXT: movq %rsp, %rax
+; X64-NEXT: movq $-1, %rcx
+; X64-NEXT: sarq $63, %rax
+; X64-NEXT: movq (%rdi), %rcx
+; X64-NEXT: orq %rax, %rcx
+; X64-NEXT: shlq $47, %rax
+; X64-NEXT: orq %rax, %rsp
+; X64-NEXT: callq *%rcx
+; X64-NEXT: movq %rsp, %rcx
+; X64-NEXT: sarq $63, %rcx
+; X64-NEXT: shlq $47, %rcx
+; X64-NEXT: orq %rcx, %rsp
+; X64-NEXT: popq %rcx
; X64-NEXT: retq
+;
+; X64-RETPOLINE-LABEL: test_indirect_call:
+; X64-RETPOLINE: # %bb.0: # %entry
+; X64-RETPOLINE-NEXT: pushq %rax
+; X64-RETPOLINE-NEXT: movq %rsp, %rax
+; X64-RETPOLINE-NEXT: movq $-1, %rcx
+; X64-RETPOLINE-NEXT: sarq $63, %rax
+; X64-RETPOLINE-NEXT: movq (%rdi), %r11
+; X64-RETPOLINE-NEXT: orq %rax, %r11
+; X64-RETPOLINE-NEXT: shlq $47, %rax
+; X64-RETPOLINE-NEXT: orq %rax, %rsp
+; X64-RETPOLINE-NEXT: callq __llvm_retpoline_r11
+; X64-RETPOLINE-NEXT: movq %rsp, %rcx
+; X64-RETPOLINE-NEXT: sarq $63, %rcx
+; X64-RETPOLINE-NEXT: shlq $47, %rcx
+; X64-RETPOLINE-NEXT: orq %rcx, %rsp
+; X64-RETPOLINE-NEXT: popq %rcx
+; X64-RETPOLINE-NEXT: retq
entry:
%fp = load i32 ()*, i32 ()** %ptr
%v = call i32 %fp()
@@ -37,9 +61,22 @@ define i32 @test_indirect_tail_call(i32
; X64-NEXT: movq %rsp, %rax
; X64-NEXT: movq $-1, %rcx
; X64-NEXT: sarq $63, %rax
+; X64-NEXT: movq (%rdi), %rcx
+; X64-NEXT: orq %rax, %rcx
; X64-NEXT: shlq $47, %rax
; X64-NEXT: orq %rax, %rsp
-; X64-NEXT: jmpq *(%rdi) # TAILCALL
+; X64-NEXT: jmpq *%rcx # TAILCALL
+;
+; X64-RETPOLINE-LABEL: test_indirect_tail_call:
+; X64-RETPOLINE: # %bb.0: # %entry
+; X64-RETPOLINE-NEXT: movq %rsp, %rax
+; X64-RETPOLINE-NEXT: movq $-1, %rcx
+; X64-RETPOLINE-NEXT: sarq $63, %rax
+; X64-RETPOLINE-NEXT: movq (%rdi), %r11
+; X64-RETPOLINE-NEXT: orq %rax, %r11
+; X64-RETPOLINE-NEXT: shlq $47, %rax
+; X64-RETPOLINE-NEXT: orq %rax, %rsp
+; X64-RETPOLINE-NEXT: jmp __llvm_retpoline_r11 # TAILCALL
entry:
%fp = load i32 ()*, i32 ()** %ptr
%v = tail call i32 %fp()
@@ -53,15 +90,34 @@ define i32 @test_indirect_call_global()
; X64-NEXT: movq %rsp, %rax
; X64-NEXT: movq $-1, %rcx
; X64-NEXT: sarq $63, %rax
+; X64-NEXT: movq {{.*}}(%rip), %rcx
+; X64-NEXT: orq %rax, %rcx
; X64-NEXT: shlq $47, %rax
; X64-NEXT: orq %rax, %rsp
-; X64-NEXT: callq *{{.*}}(%rip)
+; X64-NEXT: callq *%rcx
; X64-NEXT: movq %rsp, %rcx
; X64-NEXT: sarq $63, %rcx
; X64-NEXT: shlq $47, %rcx
; X64-NEXT: orq %rcx, %rsp
; X64-NEXT: popq %rcx
; X64-NEXT: retq
+;
+; X64-RETPOLINE-LABEL: test_indirect_call_global:
+; X64-RETPOLINE: # %bb.0: # %entry
+; X64-RETPOLINE-NEXT: pushq %rax
+; X64-RETPOLINE-NEXT: movq %rsp, %rax
+; X64-RETPOLINE-NEXT: movq $-1, %rcx
+; X64-RETPOLINE-NEXT: sarq $63, %rax
+; X64-RETPOLINE-NEXT: movq {{.*}}(%rip), %r11
+; X64-RETPOLINE-NEXT: shlq $47, %rax
+; X64-RETPOLINE-NEXT: orq %rax, %rsp
+; X64-RETPOLINE-NEXT: callq __llvm_retpoline_r11
+; X64-RETPOLINE-NEXT: movq %rsp, %rcx
+; X64-RETPOLINE-NEXT: sarq $63, %rcx
+; X64-RETPOLINE-NEXT: shlq $47, %rcx
+; X64-RETPOLINE-NEXT: orq %rcx, %rsp
+; X64-RETPOLINE-NEXT: popq %rcx
+; X64-RETPOLINE-NEXT: retq
entry:
%fp = load i32 ()*, i32 ()** @global_fnptr
%v = call i32 %fp()
@@ -74,9 +130,21 @@ define i32 @test_indirect_tail_call_glob
; X64-NEXT: movq %rsp, %rax
; X64-NEXT: movq $-1, %rcx
; X64-NEXT: sarq $63, %rax
+; X64-NEXT: movq {{.*}}(%rip), %rcx
+; X64-NEXT: orq %rax, %rcx
; X64-NEXT: shlq $47, %rax
; X64-NEXT: orq %rax, %rsp
-; X64-NEXT: jmpq *{{.*}}(%rip) # TAILCALL
+; X64-NEXT: jmpq *%rcx # TAILCALL
+;
+; X64-RETPOLINE-LABEL: test_indirect_tail_call_global:
+; X64-RETPOLINE: # %bb.0: # %entry
+; X64-RETPOLINE-NEXT: movq %rsp, %rax
+; X64-RETPOLINE-NEXT: movq $-1, %rcx
+; X64-RETPOLINE-NEXT: sarq $63, %rax
+; X64-RETPOLINE-NEXT: movq {{.*}}(%rip), %r11
+; X64-RETPOLINE-NEXT: shlq $47, %rax
+; X64-RETPOLINE-NEXT: orq %rax, %rsp
+; X64-RETPOLINE-NEXT: jmp __llvm_retpoline_r11 # TAILCALL
entry:
%fp = load i32 ()*, i32 ()** @global_fnptr
%v = tail call i32 %fp()
@@ -89,8 +157,9 @@ define i32 @test_indirectbr(i8** %ptr) n
; X64-NEXT: movq %rsp, %rcx
; X64-NEXT: movq $-1, %rax
; X64-NEXT: sarq $63, %rcx
-; X64-NEXT: orq %rcx, %rdi
-; X64-NEXT: jmpq *(%rdi)
+; X64-NEXT: movq (%rdi), %rax
+; X64-NEXT: orq %rcx, %rax
+; X64-NEXT: jmpq *%rax
; X64-NEXT: .LBB4_1: # %bb0
; X64-NEXT: movl $2, %eax
; X64-NEXT: jmp .LBB4_2
@@ -106,6 +175,9 @@ define i32 @test_indirectbr(i8** %ptr) n
; X64-NEXT: shlq $47, %rcx
; X64-NEXT: orq %rcx, %rsp
; X64-NEXT: retq
+;
+; X64-RETPOLINE-LABEL: test_indirectbr:
+; X64-RETPOLINE: # %bb.0: # %entry
entry:
%a = load i8*, i8** %ptr
indirectbr i8* %a, [ label %bb0, label %bb1, label %bb2, label %bb3 ]
@@ -130,8 +202,9 @@ define i32 @test_indirectbr_global(i32 %
; X64-NEXT: movq $-1, %rax
; X64-NEXT: sarq $63, %rcx
; X64-NEXT: movslq %edi, %rax
+; X64-NEXT: movq global_blockaddrs(,%rax,8), %rax
; X64-NEXT: orq %rcx, %rax
-; X64-NEXT: jmpq *global_blockaddrs(,%rax,8)
+; X64-NEXT: jmpq *%rax
; X64-NEXT: .Ltmp0: # Block address taken
; X64-NEXT: .LBB5_1: # %bb0
; X64-NEXT: movl $2, %eax
@@ -151,6 +224,48 @@ define i32 @test_indirectbr_global(i32 %
; X64-NEXT: shlq $47, %rcx
; X64-NEXT: orq %rcx, %rsp
; X64-NEXT: retq
+;
+; X64-RETPOLINE-LABEL: test_indirectbr_global:
+; X64-RETPOLINE: # %bb.0: # %entry
+; X64-RETPOLINE-NEXT: movq %rsp, %rcx
+; X64-RETPOLINE-NEXT: movq $-1, %rax
+; X64-RETPOLINE-NEXT: sarq $63, %rcx
+; X64-RETPOLINE-NEXT: movslq %edi, %rdx
+; X64-RETPOLINE-NEXT: movq global_blockaddrs(,%rdx,8), %rdx
+; X64-RETPOLINE-NEXT: orq %rcx, %rdx
+; X64-RETPOLINE-NEXT: cmpq $2, %rdx
+; X64-RETPOLINE-NEXT: je .LBB6_5
+; X64-RETPOLINE-NEXT: # %bb.1: # %entry
+; X64-RETPOLINE-NEXT: cmoveq %rax, %rcx
+; X64-RETPOLINE-NEXT: cmpq $3, %rdx
+; X64-RETPOLINE-NEXT: je .LBB6_6
+; X64-RETPOLINE-NEXT: # %bb.2: # %entry
+; X64-RETPOLINE-NEXT: cmoveq %rax, %rcx
+; X64-RETPOLINE-NEXT: cmpq $4, %rdx
+; X64-RETPOLINE-NEXT: jne .LBB6_3
+; X64-RETPOLINE-NEXT: .Ltmp0: # Block address taken
+; X64-RETPOLINE-NEXT: # %bb.7: # %bb3
+; X64-RETPOLINE-NEXT: cmovneq %rax, %rcx
+; X64-RETPOLINE-NEXT: movl $42, %eax
+; X64-RETPOLINE-NEXT: jmp .LBB6_4
+; X64-RETPOLINE-NEXT: .Ltmp1: # Block address taken
+; X64-RETPOLINE-NEXT: .LBB6_5: # %bb1
+; X64-RETPOLINE-NEXT: cmovneq %rax, %rcx
+; X64-RETPOLINE-NEXT: movl $7, %eax
+; X64-RETPOLINE-NEXT: jmp .LBB6_4
+; X64-RETPOLINE-NEXT: .Ltmp2: # Block address taken
+; X64-RETPOLINE-NEXT: .LBB6_6: # %bb2
+; X64-RETPOLINE-NEXT: cmovneq %rax, %rcx
+; X64-RETPOLINE-NEXT: movl $13, %eax
+; X64-RETPOLINE-NEXT: jmp .LBB6_4
+; X64-RETPOLINE-NEXT: .Ltmp3: # Block address taken
+; X64-RETPOLINE-NEXT: .LBB6_3: # %bb0
+; X64-RETPOLINE-NEXT: cmoveq %rax, %rcx
+; X64-RETPOLINE-NEXT: movl $2, %eax
+; X64-RETPOLINE-NEXT: .LBB6_4: # %bb0
+; X64-RETPOLINE-NEXT: shlq $47, %rcx
+; X64-RETPOLINE-NEXT: orq %rcx, %rsp
+; X64-RETPOLINE-NEXT: retq
entry:
%ptr = getelementptr [4 x i8*], [4 x i8*]* @global_blockaddrs, i32 0, i32 %idx
%a = load i8*, i8** %ptr
@@ -182,8 +297,9 @@ define i32 @test_switch_jumptable(i32 %i
; X64-NEXT: # %bb.1: # %entry
; X64-NEXT: cmovaq %rax, %rcx
; X64-NEXT: movl %edi, %eax
+; X64-NEXT: movq .LJTI6_0(,%rax,8), %rax
; X64-NEXT: orq %rcx, %rax
-; X64-NEXT: jmpq *.LJTI6_0(,%rax,8)
+; X64-NEXT: jmpq *%rax
; X64-NEXT: .LBB6_3: # %bb1
; X64-NEXT: movl $7, %eax
; X64-NEXT: jmp .LBB6_4
@@ -203,6 +319,53 @@ define i32 @test_switch_jumptable(i32 %i
; X64-NEXT: shlq $47, %rcx
; X64-NEXT: orq %rcx, %rsp
; X64-NEXT: retq
+;
+; X64-RETPOLINE-LABEL: test_switch_jumptable:
+; X64-RETPOLINE: # %bb.0: # %entry
+; X64-RETPOLINE-NEXT: movq %rsp, %rcx
+; X64-RETPOLINE-NEXT: movq $-1, %rax
+; X64-RETPOLINE-NEXT: sarq $63, %rcx
+; X64-RETPOLINE-NEXT: cmpl $1, %edi
+; X64-RETPOLINE-NEXT: jg .LBB7_4
+; X64-RETPOLINE-NEXT: # %bb.1: # %entry
+; X64-RETPOLINE-NEXT: cmovgq %rax, %rcx
+; X64-RETPOLINE-NEXT: testl %edi, %edi
+; X64-RETPOLINE-NEXT: je .LBB7_8
+; X64-RETPOLINE-NEXT: # %bb.2: # %entry
+; X64-RETPOLINE-NEXT: cmoveq %rax, %rcx
+; X64-RETPOLINE-NEXT: cmpl $1, %edi
+; X64-RETPOLINE-NEXT: jne .LBB7_6
+; X64-RETPOLINE-NEXT: # %bb.3: # %bb2
+; X64-RETPOLINE-NEXT: cmovneq %rax, %rcx
+; X64-RETPOLINE-NEXT: movl $13, %eax
+; X64-RETPOLINE-NEXT: jmp .LBB7_7
+; X64-RETPOLINE-NEXT: .LBB7_4: # %entry
+; X64-RETPOLINE-NEXT: cmovleq %rax, %rcx
+; X64-RETPOLINE-NEXT: cmpl $2, %edi
+; X64-RETPOLINE-NEXT: je .LBB7_9
+; X64-RETPOLINE-NEXT: # %bb.5: # %entry
+; X64-RETPOLINE-NEXT: cmoveq %rax, %rcx
+; X64-RETPOLINE-NEXT: cmpl $3, %edi
+; X64-RETPOLINE-NEXT: jne .LBB7_6
+; X64-RETPOLINE-NEXT: # %bb.10: # %bb5
+; X64-RETPOLINE-NEXT: cmovneq %rax, %rcx
+; X64-RETPOLINE-NEXT: movl $11, %eax
+; X64-RETPOLINE-NEXT: jmp .LBB7_7
+; X64-RETPOLINE-NEXT: .LBB7_6:
+; X64-RETPOLINE-NEXT: cmoveq %rax, %rcx
+; X64-RETPOLINE-NEXT: movl $2, %eax
+; X64-RETPOLINE-NEXT: jmp .LBB7_7
+; X64-RETPOLINE-NEXT: .LBB7_8: # %bb1
+; X64-RETPOLINE-NEXT: cmovneq %rax, %rcx
+; X64-RETPOLINE-NEXT: movl $7, %eax
+; X64-RETPOLINE-NEXT: jmp .LBB7_7
+; X64-RETPOLINE-NEXT: .LBB7_9: # %bb3
+; X64-RETPOLINE-NEXT: cmovneq %rax, %rcx
+; X64-RETPOLINE-NEXT: movl $42, %eax
+; X64-RETPOLINE-NEXT: .LBB7_7: # %bb0
+; X64-RETPOLINE-NEXT: shlq $47, %rcx
+; X64-RETPOLINE-NEXT: orq %rcx, %rsp
+; X64-RETPOLINE-NEXT: retq
entry:
switch i32 %idx, label %bb0 [
i32 0, label %bb1
More information about the llvm-commits
mailing list