From 8c89b5db7a2894e33417dd69680729e8f65f5709 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 18 Apr 2022 21:32:30 -0700 Subject: [PATCH] selftests/bpf: Limit unroll_count for pyperf600 test LLVM commit [1] changed loop pragma behavior such that full loop unroll is always honored with user pragma. Previously, unroll count also depends on the unrolled code size. For pyperf600, without [1], the loop unroll count is 150. With [1], the loop unroll count is 600. The unroll count of 600 caused the program size close to 298k and this caused the following code is generated: 0: 7b 1a 00 ff 00 00 00 00 *(u64 *)(r10 - 256) = r1 ; uint64_t pid_tgid = bpf_get_current_pid_tgid(); 1: 85 00 00 00 0e 00 00 00 call 14 2: bf 06 00 00 00 00 00 00 r6 = r0 ; pid_t pid = (pid_t)(pid_tgid >> 32); 3: bf 61 00 00 00 00 00 00 r1 = r6 4: 77 01 00 00 20 00 00 00 r1 >>= 32 5: 63 1a fc ff 00 00 00 00 *(u32 *)(r10 - 4) = r1 6: bf a2 00 00 00 00 00 00 r2 = r10 7: 07 02 00 00 fc ff ff ff r2 += -4 ; PidData* pidData = bpf_map_lookup_elem(&pidmap, &pid); 8: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll 10: 85 00 00 00 01 00 00 00 call 1 11: bf 08 00 00 00 00 00 00 r8 = r0 ; if (!pidData) 12: 15 08 15 e8 00 00 00 00 if r8 == 0 goto -6123 Note that insn 12 has a branch offset -6123 which is clearly illegal and will be rejected by the verifier. The negative offset is due to the branch range is greater than INT16_MAX. This patch changed the unroll count to be 150 to avoid above branch target insn out-of-range issue. Also the llvm is enhanced ([2]) to assert if the branch target insn is out of INT16 range. [1] https://reviews.llvm.org/D119148 [2] https://reviews.llvm.org/D123877 Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220419043230.2928530-1-yhs@fb.com --- tools/testing/selftests/bpf/progs/pyperf.h | 4 ++++ tools/testing/selftests/bpf/progs/pyperf600.c | 11 +++++++---- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h index 1ed2888..5d3dc4d 100644 --- a/tools/testing/selftests/bpf/progs/pyperf.h +++ b/tools/testing/selftests/bpf/progs/pyperf.h @@ -299,7 +299,11 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx) #ifdef NO_UNROLL #pragma clang loop unroll(disable) #else +#ifdef UNROLL_COUNT +#pragma clang loop unroll_count(UNROLL_COUNT) +#else #pragma clang loop unroll(full) +#endif #endif /* NO_UNROLL */ /* Unwind python stack */ for (int i = 0; i < STACK_MAX_LEN; ++i) { diff --git a/tools/testing/selftests/bpf/progs/pyperf600.c b/tools/testing/selftests/bpf/progs/pyperf600.c index cb49b89..ce1aa51 100644 --- a/tools/testing/selftests/bpf/progs/pyperf600.c +++ b/tools/testing/selftests/bpf/progs/pyperf600.c @@ -1,9 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #define STACK_MAX_LEN 600 -/* clang will not unroll the loop 600 times. - * Instead it will unroll it to the amount it deemed - * appropriate, but the loop will still execute 600 times. - * Total program size is around 90k insns +/* Full unroll of 600 iterations will have total + * program size close to 298k insns and this may + * cause BPF_JMP insn out of 16-bit integer range. + * So limit the unroll size to 150 so the + * total program size is around 80k insns but + * the loop will still execute 600 times. */ +#define UNROLL_COUNT 150 #include "pyperf.h" -- 2.7.4