7852ebc088
Before llvm20, (void)__sync_fetch_and_add(...) always generates locked xadd insns. In linux kernel upstream discussion [1], it is found that for arm64 architecture, the original semantics of (void)__sync_fetch_and_add(...), i.e., __atomic_fetch_add(...), is preferred in order for jit to emit proper native barrier insns. In llvm commits [2] and [3], (void)__sync_fetch_and_add(...) will generate the following insns: - for cpu v1/v2: locked xadd insns to keep backward compatibility - for cpu v3/v4: __atomic_fetch_add() insns To ensure proper barrier semantics for (void)__sync_fetch_and_add(...), cpu v3/v4 is recommended. This patch enables cpu=v3 as the default cpu version. For users wanting to use cpu v1, -mcpu=v1 needs to be explicitly added to clang/llc command line. [1] https://lore.kernel.org/bpf/ZqqiQQWRnz7H93Hc@google.com/T/#mb68d67bc8f39e35a0c3db52468b9de59b79f021f [2] https://github.com/llvm/llvm-project/pull/101428 [3] https://github.com/llvm/llvm-project/pull/106494
39 lines
1.2 KiB
LLVM
39 lines
1.2 KiB
LLVM
; RUN: llc -mtriple=bpfel -mcpu=v1 -filetype=obj -o - %s | llvm-objdump --no-print-imm-hex --mcpu=v1 -d - | FileCheck --check-prefix=CHECK %s
|
|
; RUN: llc -mtriple=bpfeb -mcpu=v1 -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}
|