Subject: Re: [PATCH] perf bpf: Fix endianness problem when loading parameters
 in prologue
To: <tmricht@linux.vnet.ibm.com>
References: <20170812184959.32694-1-wangnan0@huawei.com>
CC: <linux-kernel@vger.kernel.org>, Li Zefan <lizefan@huawei.com>
From: "Wangnan (F)" <wangnan0@huawei.com>
Message-ID: <0e9620f7-e0d9-e8a4-ee87-3284bc9b8cc2@huawei.com>
Date: Fri, 11 Aug 2017 18:47:56 +0800
User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:45.0) Gecko/20100101
 Thunderbird/45.5.1
MIME-Version: 1.0
In-Reply-To: <20170812184959.32694-1-wangnan0@huawei.com>
Content-Type: text/plain; charset="utf-8"; format=flowed
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 3414
Lines: 113

Hi Thomas,

Please try this patch on your machine and give me the result.

Thank you.

On 2017/8/13 2:49, Wang Nan wrote:
> 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-abe4-8830-8d69-49f62529d151@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 <wangnan0@huawei.com>
> Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
> Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
> Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
> Cc: Li Zefan <lizefan@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);
>