Re: [PATCH bpf-next 2/3] bpf: Add bpf_perf_event_read_sample() helper

[Jiri Olsa]

On Mon, Oct 31, 2022 at 10:23:39PM -0700, Namhyung Kim wrote:
> The bpf_perf_event_read_sample() helper is to get the specified sample
> data (by using PERF_SAMPLE_* flag in the argument) from BPF to make a
> decision for filtering on samples.  Currently PERF_SAMPLE_IP and
> PERF_SAMPLE_DATA flags are supported only.
> 
> Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
> ---
>  include/uapi/linux/bpf.h       | 23 ++++++++++++++++
>  kernel/trace/bpf_trace.c       | 49 ++++++++++++++++++++++++++++++++++
>  tools/include/uapi/linux/bpf.h | 23 ++++++++++++++++
>  3 files changed, 95 insertions(+)
> 
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 94659f6b3395..cba501de9373 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -5481,6 +5481,28 @@ union bpf_attr {
>   *		0 on success.
>   *
>   *		**-ENOENT** if the bpf_local_storage cannot be found.
> + *
> + * long bpf_perf_event_read_sample(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 sample_flags)
> + *	Description
> + *		For an eBPF program attached to a perf event, retrieve the
> + *		sample data associated to *ctx*	and store it in the buffer
> + *		pointed by *buf* up to size *size* bytes.
> + *
> + *		The *sample_flags* should contain a single value in the
> + *		**enum perf_event_sample_format**.
> + *	Return
> + *		On success, number of bytes written to *buf*. On error, a
> + *		negative value.
> + *
> + *		The *buf* can be set to **NULL** to return the number of bytes
> + *		required to store the requested sample data.
> + *
> + *		**-EINVAL** if *sample_flags* is not a PERF_SAMPLE_* flag.
> + *
> + *		**-ENOENT** if the associated perf event doesn't have the data.
> + *
> + *		**-ENOSYS** if system doesn't support the sample data to be
> + *		retrieved.
>   */
>  #define ___BPF_FUNC_MAPPER(FN, ctx...)			\
>  	FN(unspec, 0, ##ctx)				\
> @@ -5695,6 +5717,7 @@ union bpf_attr {
>  	FN(user_ringbuf_drain, 209, ##ctx)		\
>  	FN(cgrp_storage_get, 210, ##ctx)		\
>  	FN(cgrp_storage_delete, 211, ##ctx)		\
> +	FN(perf_event_read_sample, 212, ##ctx)		\
>  	/* */
>  
>  /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't
> diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
> index ce0228c72a93..befd937afa3c 100644
> --- a/kernel/trace/bpf_trace.c
> +++ b/kernel/trace/bpf_trace.c
> @@ -28,6 +28,7 @@
>  
>  #include <uapi/linux/bpf.h>
>  #include <uapi/linux/btf.h>
> +#include <uapi/linux/perf_event.h>
>  
>  #include <asm/tlb.h>
>  
> @@ -1743,6 +1744,52 @@ static const struct bpf_func_proto bpf_read_branch_records_proto = {
>  	.arg4_type      = ARG_ANYTHING,
>  };
>  
> +BPF_CALL_4(bpf_perf_event_read_sample, struct bpf_perf_event_data_kern *, ctx,
> +	   void *, buf, u32, size, u64, flags)
> +{

I wonder we could add perf_btf (like we have tp_btf) program type that
could access ctx->data directly without helpers

> +	struct perf_sample_data *sd = ctx->data;
> +	void *data;
> +	u32 to_copy = sizeof(u64);
> +
> +	/* only allow a single sample flag */
> +	if (!is_power_of_2(flags))
> +		return -EINVAL;
> +
> +	/* support reading only already populated info */
> +	if (flags & ~sd->sample_flags)
> +		return -ENOENT;
> +
> +	switch (flags) {
> +	case PERF_SAMPLE_IP:
> +		data = &sd->ip;
> +		break;
> +	case PERF_SAMPLE_ADDR:
> +		data = &sd->addr;
> +		break;

AFAICS from pe_prog_convert_ctx_access you should be able to read addr
directly from context right? same as sample_period.. so I think if this
will be generic way to read sample data, should we add sample_period
as well?


> +	default:
> +		return -ENOSYS;
> +	}
> +
> +	if (!buf)
> +		return to_copy;
> +
> +	if (size < to_copy)
> +		to_copy = size;

should we fail in here instead? is there any point in returning
not complete data?

jirka


> +
> +	memcpy(buf, data, to_copy);
> +	return to_copy;
> +}
> +
> +static const struct bpf_func_proto bpf_perf_event_read_sample_proto = {
> +	.func           = bpf_perf_event_read_sample,
> +	.gpl_only       = true,
> +	.ret_type       = RET_INTEGER,
> +	.arg1_type      = ARG_PTR_TO_CTX,
> +	.arg2_type      = ARG_PTR_TO_MEM_OR_NULL,
> +	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
> +	.arg4_type      = ARG_ANYTHING,
> +};
> +
>  static const struct bpf_func_proto *
>  pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
>  {
> @@ -1759,6 +1806,8 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
>  		return &bpf_read_branch_records_proto;
>  	case BPF_FUNC_get_attach_cookie:
>  		return &bpf_get_attach_cookie_proto_pe;
> +	case BPF_FUNC_perf_event_read_sample:
> +		return &bpf_perf_event_read_sample_proto;
>  	default:
>  		return bpf_tracing_func_proto(func_id, prog);
>  	}
> diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
> index 94659f6b3395..cba501de9373 100644
> --- a/tools/include/uapi/linux/bpf.h
> +++ b/tools/include/uapi/linux/bpf.h
> @@ -5481,6 +5481,28 @@ union bpf_attr {
>   *		0 on success.
>   *
>   *		**-ENOENT** if the bpf_local_storage cannot be found.
> + *
> + * long bpf_perf_event_read_sample(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 sample_flags)
> + *	Description
> + *		For an eBPF program attached to a perf event, retrieve the
> + *		sample data associated to *ctx*	and store it in the buffer
> + *		pointed by *buf* up to size *size* bytes.
> + *
> + *		The *sample_flags* should contain a single value in the
> + *		**enum perf_event_sample_format**.
> + *	Return
> + *		On success, number of bytes written to *buf*. On error, a
> + *		negative value.
> + *
> + *		The *buf* can be set to **NULL** to return the number of bytes
> + *		required to store the requested sample data.
> + *
> + *		**-EINVAL** if *sample_flags* is not a PERF_SAMPLE_* flag.
> + *
> + *		**-ENOENT** if the associated perf event doesn't have the data.
> + *
> + *		**-ENOSYS** if system doesn't support the sample data to be
> + *		retrieved.
>   */
>  #define ___BPF_FUNC_MAPPER(FN, ctx...)			\
>  	FN(unspec, 0, ##ctx)				\
> @@ -5695,6 +5717,7 @@ union bpf_attr {
>  	FN(user_ringbuf_drain, 209, ##ctx)		\
>  	FN(cgrp_storage_get, 210, ##ctx)		\
>  	FN(cgrp_storage_delete, 211, ##ctx)		\
> +	FN(perf_event_read_sample, 212, ##ctx)		\
>  	/* */
>  
>  /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't
> -- 
> 2.38.1.273.g43a17bfeac-goog
>