6c412b6c6f
In [1], a few new insns are proposed to expand BPF ISA to
. fixing the limitation of existing insn (e.g., 16bit jmp offset)
. adding new insns which may improve code quality
(sign_ext_ld, sign_ext_mov, st)
. feature complete (sdiv, smod)
. better user experience (bswap)
This patch implemented insn encoding for
. sign-extended load
. sign-extended mov
. sdiv/smod
. bswap insns
. unconditional jump with 32bit offset
The new bswap insns are generated under cpu=v4 for __builtin_bswap.
For cpu=v3 or earlier, for __builtin_bswap, be or le insns are generated
which is not intuitive for the user.
To support 32-bit branch offset, a 32-bit ja (JMPL) insn is implemented.
For conditional branch which is beyond 16-bit offset, llvm will do
some transformation 'cond_jmp' -> 'cond_jmp + jmpl' to simulate 32bit
conditional jmp. See BPFMIPeephole.cpp for details. The algorithm is
hueristic based. I have tested bpf selftest pyperf600 with unroll account
600 which can indeed generate 32-bit jump insn, e.g.,
13: 06 00 00 00 9b cd 00 00 gotol +0xcd9b <LBB0_6619>
Eduard is working on to add 'st' insn to cpu=v4.
A list of llc flags:
disable-ldsx, disable-movsx, disable-bswap,
disable-sdiv-smod, disable-gotol
can be used to disable a particular insn for cpu v4.
For example, user can do:
llc -march=bpf -mcpu=v4 -disable-movsx t.ll
to enable cpu v4 without movsx insns.
References:
[1] https://lore.kernel.org/bpf/4bfe98be-5333-1c7e-2f6d-42486c8ec039@meta.com/
Differential Revision: https://reviews.llvm.org/D144829
45 lines
1.7 KiB
LLVM
45 lines
1.7 KiB
LLVM
; RUN: llc -march=bpfel -mcpu=v4 -verify-machineinstrs -show-mc-encoding < %s | FileCheck %s
|
|
; Source:
|
|
; int foo(int a, int b, int c) {
|
|
; return a/b + a%c;
|
|
; }
|
|
; long bar(long a, long b, long c) {
|
|
; return a/b + a%c;
|
|
; }
|
|
; Compilation flags:
|
|
; clang -target bpf -O2 -S -emit-llvm t.c
|
|
|
|
; Function Attrs: mustprogress nofree norecurse nosync nounwind willreturn memory(none)
|
|
define dso_local i32 @foo(i32 noundef %a, i32 noundef %b, i32 noundef %c) local_unnamed_addr #0 {
|
|
entry:
|
|
%div = sdiv i32 %a, %b
|
|
%rem = srem i32 %a, %c
|
|
%add = add nsw i32 %rem, %div
|
|
ret i32 %add
|
|
}
|
|
|
|
; CHECK: w0 = w1
|
|
; CHECK-NEXT: w1 s/= w2 # encoding: [0x3c,0x21,0x01,0x00,0x00,0x00,0x00,0x00]
|
|
; CHECK-NEXT: w0 s%= w3 # encoding: [0x9c,0x30,0x01,0x00,0x00,0x00,0x00,0x00]
|
|
|
|
; Function Attrs: mustprogress nofree norecurse nosync nounwind willreturn memory(none)
|
|
define dso_local i64 @bar(i64 noundef %a, i64 noundef %b, i64 noundef %c) local_unnamed_addr #0 {
|
|
entry:
|
|
%div = sdiv i64 %a, %b
|
|
%rem = srem i64 %a, %c
|
|
%add = add nsw i64 %rem, %div
|
|
ret i64 %add
|
|
}
|
|
; CHECK: r0 = r1
|
|
; CHECK-NEXT: r1 s/= r2 # encoding: [0x3f,0x21,0x01,0x00,0x00,0x00,0x00,0x00]
|
|
; CHECK-NEXT: r0 s%= r3 # encoding: [0x9f,0x30,0x01,0x00,0x00,0x00,0x00,0x00]
|
|
|
|
attributes #0 = { mustprogress nofree norecurse nosync nounwind willreturn memory(none) "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
|
|
|
|
!llvm.module.flags = !{!0, !1}
|
|
!llvm.ident = !{!2}
|
|
|
|
!0 = !{i32 1, !"wchar_size", i32 4}
|
|
!1 = !{i32 7, !"frame-pointer", i32 2}
|
|
!2 = !{!"clang version 17.0.0 (https://github.com/llvm/llvm-project.git c102025a4299e74767cdb4dfba8abbf6cbad820b)"}
|