03958680b2
Currently, with the following example,
$ cat t.c
void foo(int a, _Atomic int *b)
{
*b &= a;
}
$ clang --target=bpf -O2 -c -mcpu=v3 t.c
$ llvm-objdump -d t.o
t.o: file format elf64-bpf
Disassembly of section .text:
0000000000000000 <foo>:
0: c3 12 00 00 51 00 00 00 <unknown>
1: 95 00 00 00 00 00 00 00 exit
Basically, the default cpu for llvm-objdump is v1 and it won't be able
to decode insn properly.
If we add --mcpu=v3 to llvm-objdump command line, we will have
$ llvm-objdump -d --mcpu=v3 t.o
t.o: file format elf64-bpf
Disassembly of section .text:
0000000000000000 <foo>:
0: c3 12 00 00 51 00 00 00 w1 = atomic_fetch_and((u32 *)(r2 + 0x0), w1)
1: 95 00 00 00 00 00 00 00 exit
The atomic_fetch_and insn can be decoded properly. Using latest cpu
version --mcpu=v4 can also decode properly like the above --mcpu=v3.
To avoid the above '<unknown>' decoding with common 'llvm-objdump -d
t.o', this patch marked the default cpu for llvm-objdump with the
current highest cpu number v4 in ELFObjectFileBase::tryGetCPUName(). The
cpu number in ELFObjectFileBase::tryGetCPUName() will be adjusted in the
future if cpu number is increased e.g. v5 etc. Such an approach also
aligns with gcc-bpf as discussed in [1].
Six bpf unit tests are affected with this change. I changed test output
for three unit tests and added --mcpu=v1 for the other three unit tests,
to demonstrate the default (cpu v4) behavior and explicit --mcpu=v1
behavior.
[1]
https://lore.kernel.org/bpf/6f32c0a1-9de2-4145-92ea-be025362182f@linux.dev/T/#m0f7e63c390bc8f5a5523e7f2f0537becd4205200
Co-authored-by: Yonghong Song <yonghong.song@linux.dev>
39 lines
1.1 KiB
LLVM
39 lines
1.1 KiB
LLVM
; RUN: llc -mtriple=bpfel -filetype=obj -o - %s | llvm-objdump --no-print-imm-hex --mcpu=v1 -d - | FileCheck --check-prefix=CHECK %s
|
|
; RUN: llc -mtriple=bpfeb -filetype=obj -o - %s | llvm-objdump --no-print-imm-hex --mcpu=v1 -d - | FileCheck --check-prefix=CHECK %s
|
|
|
|
; src:
|
|
; static volatile long a = 2;
|
|
; static volatile int b = 3;
|
|
; int test() { return a + b; }
|
|
@a = internal global i64 2, align 8
|
|
@b = internal global i32 3, align 4
|
|
|
|
; Function Attrs: norecurse nounwind
|
|
define dso_local i32 @test() local_unnamed_addr #0 {
|
|
%1 = load volatile i64, ptr @a, align 8, !tbaa !2
|
|
; CHECK: r1 = 0 ll
|
|
; CHECK: r1 = *(u64 *)(r1 + 0)
|
|
%2 = load volatile i32, ptr @b, align 4, !tbaa !6
|
|
; CHECK: r2 = 8 ll
|
|
; CHECK: r0 = *(u32 *)(r2 + 0)
|
|
%3 = trunc i64 %1 to i32
|
|
%4 = add i32 %2, %3
|
|
; CHECK: r0 += r1
|
|
ret i32 %4
|
|
; CHECK: exit
|
|
}
|
|
|
|
attributes #0 = { norecurse nounwind }
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!llvm.ident = !{!1}
|
|
|
|
!0 = !{i32 1, !"wchar_size", i32 4}
|
|
!1 = !{!"clang version 8.0.20181009 "}
|
|
!2 = !{!3, !3, i64 0}
|
|
!3 = !{!"long", !4, i64 0}
|
|
!4 = !{!"omnipotent char", !5, i64 0}
|
|
!5 = !{!"Simple C/C++ TBAA"}
|
|
!6 = !{!7, !7, i64 0}
|
|
!7 = !{!"int", !4, i64 0}
|