Perf BPF prologue generator unconditionally fetches 8 bytes for function parameters, which causes problem on big endian machine. Thomas gives a detail analysis for this problem:
http://lkml.kernel.org/r/968ebda5-abe4-8830-8d69-49f62529d...@linux.vnet.ibm.com This patch parses the type of each argument and converts data from memory to expected type. Signed-off-by: Wang Nan <wangn...@huawei.com> Cc: Arnaldo Carvalho de Melo <a...@kernel.org> Cc: Thomas Richter <tmri...@linux.vnet.ibm.com> Cc: Alexei Starovoitov <alexei.starovoi...@gmail.com> Cc: Hendrik Brueckner <brueck...@linux.vnet.ibm.com> Cc: Li Zefan <lize...@huawei.com> --- tools/perf/tests/bpf-script-test-prologue.c | 4 ++- tools/perf/util/bpf-prologue.c | 49 +++++++++++++++++++++++++++-- 2 files changed, 50 insertions(+), 3 deletions(-) diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c index b4ebc75..43f1e16 100644 --- a/tools/perf/tests/bpf-script-test-prologue.c +++ b/tools/perf/tests/bpf-script-test-prologue.c @@ -26,9 +26,11 @@ static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) = (void *) 6; SEC("func=null_lseek file->f_mode offset orig") -int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode, +int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode, unsigned long offset, unsigned long orig) { + fmode_t f_mode = (fmode_t)_f_mode; + if (err) return 0; if (f_mode & FMODE_WRITE) diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c index 6cdbee1..ce28993 100644 --- a/tools/perf/util/bpf-prologue.c +++ b/tools/perf/util/bpf-prologue.c @@ -57,6 +57,46 @@ check_pos(struct bpf_insn_pos *pos) return 0; } +/* + * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see + * Documentation/trace/kprobetrace.txt) to size field of BPF_LDX_MEM + * instruction (BPF_{B,H,W,DW}). + */ +static int +argtype_to_ldx_size(const char *type) +{ + int arg_size = type ? atoi(&type[1]) : 64; + + switch (arg_size) { + case 8: + return BPF_B; + case 16: + return BPF_H; + case 32: + return BPF_W; + case 64: + default: + return BPF_DW; + } +} + +static const char * +insn_sz_to_str(int insn_sz) +{ + switch (insn_sz) { + case BPF_B: + return "BPF_B"; + case BPF_H: + return "BPF_H"; + case BPF_W: + return "BPF_W"; + case BPF_DW: + return "BPF_DW"; + default: + return "UNKNOWN"; + } +} + /* Give it a shorter name */ #define ins(i, p) append_insn((i), (p)) @@ -257,9 +297,14 @@ gen_prologue_slowpath(struct bpf_insn_pos *pos, } /* Final pass: read to registers */ - for (i = 0; i < nargs; i++) - ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i, + for (i = 0; i < nargs; i++) { + int insn_sz = argtype_to_ldx_size(args[i].type); + + pr_debug("prologue: load arg %d, insn_sz is %s\n", + i, insn_sz_to_str(insn_sz)); + ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i, BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos); + } ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos); -- 2.10.1
