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
13 lines
444 B
LLVM
13 lines
444 B
LLVM
; RUN: not llc -march=bpf -mcpu=v1 < %s 2> %t1
|
|
; RUN: FileCheck %s < %t1
|
|
; CHECK: error: <unknown>:0:0: in function foo i32 (i32, i32, i32): {{t10|0x[0-f]+}}: i64 = GlobalAddress<ptr @bar> 0 too many arguments
|
|
|
|
; Function Attrs: nounwind uwtable
|
|
define i32 @foo(i32 %a, i32 %b, i32 %c) #0 {
|
|
entry:
|
|
%call = tail call i32 @bar(i32 %a, i32 %b, i32 %c, i32 1, i32 2, i32 3) #3
|
|
ret i32 %call
|
|
}
|
|
|
|
declare i32 @bar(i32, i32, i32, i32, i32, i32) #1
|