Summary:
There is a tiny logic error of D75300, making branch is not
correctly aligned with option -x86-pad-max-prefix-size
Reviewers: reames, MaskRay, craig.topper, LuoYuanke, jyknight
Reviewed By: reames
Subscribers: hiraditya, llvm-commits, annita.zhang
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D76285
const uint64_t OrigOffset = Layout.getFragmentOffset(&F);
#endif
const uint64_t OrigSize = Asm.computeFragmentSize(Layout, F);
- if (OrigSize == 0 || Relaxable.empty()) {
- Relaxable.clear();
- continue;
- }
// To keep the effects local, prefer to relax instructions closest to
// the align directive. This is purely about human understandability
bar:
retq
- # CHECK: <test_pad_via_relax>:
- # CHECK: 200: testq
- # CHECK: 203: jne
- # CHECK: 209: int3
- # note 6 byte jne which could be a 2 byte jne, but is instead
- # expanded for padding purposes
- # CHECK-NOT: nop
- # CHECK: 220: callq
- .global test_pad_via_relax
- .p2align 5
-test_pad_via_relax:
- testq %rax, %rax
- jnz bar
- .rept 23
- int3
- .endr
- callq bar
-
# This case looks really tempting to pad, but doing so for the call causes
# the jmp to be misaligned.
# CHECK: <test_pad_via_relax_neg1>:
- # CHECK: 240: int3
- # CHECK: 25a: testq
- # CHECK: 25d: jne
- # CHECK: 25f: nop
- # CHECK: 260: callq
+ # CHECK: 200: int3
+ # CHECK: 21a: testq
+ # CHECK: 21d: jne
+ # CHECK: 21f: nop
+ # CHECK: 220: callq
.global test_pad_via_relax_neg1
.p2align 5
test_pad_via_relax_neg1:
# Same as previous, but without fusion
# CHECK: <test_pad_via_relax_neg2>:
- # CHECK: 280: int3
- # CHECK: 29d: jmp
- # CHECK: 29f: nop
- # CHECK: 2a0: callq
+ # CHECK: 240: int3
+ # CHECK: 25d: jmp
+ # CHECK: 25f: nop
+ # CHECK: 260: callq
.global test_pad_via_relax_neg2
.p2align 5
test_pad_via_relax_neg2:
jmp bar2
callq bar2
-bar2:
+bar2:
.section "unknown"
.p2align 4
--- /dev/null
+ # RUN: llvm-mc -filetype=obj -triple x86_64-pc-linux-gnu --x86-align-branch-boundary=32 --x86-align-branch=jmp -x86-pad-max-prefix-size=5 %s | llvm-objdump -d --no-show-raw-insn - | FileCheck %s
+ # Check instructions can be aligned correctly along with option -x86-pad-max-prefix-size=5
+
+ .text
+ .p2align 5
+ .rept 24
+ int3
+ .endr
+ # We should not increase the length of this jmp to reduce the bytes of
+ # following nops, doing so would make the jmp misaligned.
+# CHECK: 18: jmp
+ jmp bar
+# CHECK: 1d: nop
+# CHECK: 1e: nop
+# CHECK: 1f: nop
+# CHECK: 20: int3
+ .p2align 5
+ int3