Re: [PATCH v6 03/15] perf arm-spe: Use SPE data source for neoverse cores

From: Arnaldo Carvalho de Melo
Date: Thu Aug 11 2022 - 18:01:14 EST


Em Thu, Aug 11, 2022 at 02:24:39PM +0800, Leo Yan escreveu:
> From: Ali Saidi <alisaidi@xxxxxxxxxx>
>
> When synthesizing data from SPE, augment the type with source information
> for Arm Neoverse cores. The field is IMPLDEF but the Neoverse cores all use
> the same encoding. I can't find encoding information for any other SPE
> implementations to unify their choices with Arm's thus that is left for
> future work.
>
> This change populates the mem_lvl_num for Neoverse cores as well as the
> deprecated mem_lvl namespace.

So at this point, building on x86_64, I get:

In file included from util/arm-spe.c:37:
util/../../arch/arm64/include/asm/cputype.h:183:10: fatal error: asm/sysreg.h: No such file or directory
183 | #include <asm/sysreg.h>
| ^~~~~~~~~~~~~~
compilation terminated.
make[4]: *** [/var/home/acme/git/perf/tools/build/Makefile.build:96: /tmp/build/perf/util/arm-spe.o] Error 1
make[4]: *** Waiting for unfinished jobs....
LD /tmp/build/perf/util/arm-spe-decoder/perf-in.o
make[3]: *** [/var/home/acme/git/perf/tools/build/Makefile.build:139: util] Error 2
make[2]: *** [Makefile.perf:660: /tmp/build/perf/perf-in.o] Error 2
make[1]: *** [Makefile.perf:240: sub-make] Error 2
make: *** [Makefile:113: install-bin] Error 2
make: Leaving directory '/var/home/acme/git/perf/tools/perf'

Performance counter stats for 'make -k BUILD_BPF_SKEL=1 CORESIGHT=1 O=/tmp/build/perf -C tools/perf install-bin':

12,163,704,676 cycles:u
20,601,569,045 instructions:u # 1.69 insn per cycle

3.733981168 seconds time elapsed

2.897595000 seconds user
1.446798000 seconds sys


⬢[acme@toolbox perf]$

I saw a patch floating by that seems related, will check.

- Arnaldo

> Signed-off-by: Ali Saidi <alisaidi@xxxxxxxxxx>
> Reviewed-by: German Gomez <german.gomez@xxxxxxx>
> Reviewed-by: Leo Yan <leo.yan@xxxxxxxxxx>
> Tested-by: Leo Yan <leo.yan@xxxxxxxxxx>
> ---
> .../util/arm-spe-decoder/arm-spe-decoder.c | 1 +
> .../util/arm-spe-decoder/arm-spe-decoder.h | 12 ++
> tools/perf/util/arm-spe.c | 130 +++++++++++++++---
> 3 files changed, 127 insertions(+), 16 deletions(-)
>
> diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
> index 5e390a1a79ab..091987dd3966 100644
> --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
> +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
> @@ -220,6 +220,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
>
> break;
> case ARM_SPE_DATA_SOURCE:
> + decoder->record.source = payload;
> break;
> case ARM_SPE_BAD:
> break;
> diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
> index 69b31084d6be..46a61df1145b 100644
> --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
> +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
> @@ -29,6 +29,17 @@ enum arm_spe_op_type {
> ARM_SPE_ST = 1 << 1,
> };
>
> +enum arm_spe_neoverse_data_source {
> + ARM_SPE_NV_L1D = 0x0,
> + ARM_SPE_NV_L2 = 0x8,
> + ARM_SPE_NV_PEER_CORE = 0x9,
> + ARM_SPE_NV_LOCAL_CLUSTER = 0xa,
> + ARM_SPE_NV_SYS_CACHE = 0xb,
> + ARM_SPE_NV_PEER_CLUSTER = 0xc,
> + ARM_SPE_NV_REMOTE = 0xd,
> + ARM_SPE_NV_DRAM = 0xe,
> +};
> +
> struct arm_spe_record {
> enum arm_spe_sample_type type;
> int err;
> @@ -40,6 +51,7 @@ struct arm_spe_record {
> u64 virt_addr;
> u64 phys_addr;
> u64 context_id;
> + u16 source;
> };
>
> struct arm_spe_insn;
> diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
> index d040406f3314..22dcfe07e886 100644
> --- a/tools/perf/util/arm-spe.c
> +++ b/tools/perf/util/arm-spe.c
> @@ -34,6 +34,7 @@
> #include "arm-spe-decoder/arm-spe-decoder.h"
> #include "arm-spe-decoder/arm-spe-pkt-decoder.h"
>
> +#include "../../arch/arm64/include/asm/cputype.h"
> #define MAX_TIMESTAMP (~0ULL)
>
> struct arm_spe {
> @@ -45,6 +46,7 @@ struct arm_spe {
> struct perf_session *session;
> struct machine *machine;
> u32 pmu_type;
> + u64 midr;
>
> struct perf_tsc_conversion tc;
>
> @@ -387,35 +389,128 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
> return arm_spe_deliver_synth_event(spe, speq, event, &sample);
> }
>
> -static u64 arm_spe__synth_data_source(const struct arm_spe_record *record)
> +static const struct midr_range neoverse_spe[] = {
> + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
> + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
> + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
> + {},
> +};
> +
> +static void arm_spe__synth_data_source_neoverse(const struct arm_spe_record *record,
> + union perf_mem_data_src *data_src)
> {
> - union perf_mem_data_src data_src = { 0 };
> + /*
> + * Even though four levels of cache hierarchy are possible, no known
> + * production Neoverse systems currently include more than three levels
> + * so for the time being we assume three exist. If a production system
> + * is built with four the this function would have to be changed to
> + * detect the number of levels for reporting.
> + */
>
> - if (record->op == ARM_SPE_LD)
> - data_src.mem_op = PERF_MEM_OP_LOAD;
> - else if (record->op == ARM_SPE_ST)
> - data_src.mem_op = PERF_MEM_OP_STORE;
> - else
> - return 0;
> + /*
> + * We have no data on the hit level or data source for stores in the
> + * Neoverse SPE records.
> + */
> + if (record->op & ARM_SPE_ST) {
> + data_src->mem_lvl = PERF_MEM_LVL_NA;
> + data_src->mem_lvl_num = PERF_MEM_LVLNUM_NA;
> + data_src->mem_snoop = PERF_MEM_SNOOP_NA;
> + return;
> + }
> +
> + switch (record->source) {
> + case ARM_SPE_NV_L1D:
> + data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
> + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L1;
> + data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
> + break;
> + case ARM_SPE_NV_L2:
> + data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
> + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
> + data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
> + break;
> + case ARM_SPE_NV_PEER_CORE:
> + data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
> + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
> + data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
> + break;
> + /*
> + * We don't know if this is L1, L2 but we do know it was a cache-2-cache
> + * transfer, so set SNOOPX_PEER
> + */
> + case ARM_SPE_NV_LOCAL_CLUSTER:
> + case ARM_SPE_NV_PEER_CLUSTER:
> + data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT;
> + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
> + data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
> + break;
> + /*
> + * System cache is assumed to be L3
> + */
> + case ARM_SPE_NV_SYS_CACHE:
> + data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT;
> + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
> + data_src->mem_snoop = PERF_MEM_SNOOP_HIT;
> + break;
> + /*
> + * We don't know what level it hit in, except it came from the other
> + * socket
> + */
> + case ARM_SPE_NV_REMOTE:
> + data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1;
> + data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE;
> + data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
> + data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
> + break;
> + case ARM_SPE_NV_DRAM:
> + data_src->mem_lvl = PERF_MEM_LVL_LOC_RAM | PERF_MEM_LVL_HIT;
> + data_src->mem_lvl_num = PERF_MEM_LVLNUM_RAM;
> + data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
> + break;
> + default:
> + break;
> + }
> +}
>
> +static void arm_spe__synth_data_source_generic(const struct arm_spe_record *record,
> + union perf_mem_data_src *data_src)
> +{
> if (record->type & (ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS)) {
> - data_src.mem_lvl = PERF_MEM_LVL_L3;
> + data_src->mem_lvl = PERF_MEM_LVL_L3;
>
> if (record->type & ARM_SPE_LLC_MISS)
> - data_src.mem_lvl |= PERF_MEM_LVL_MISS;
> + data_src->mem_lvl |= PERF_MEM_LVL_MISS;
> else
> - data_src.mem_lvl |= PERF_MEM_LVL_HIT;
> + data_src->mem_lvl |= PERF_MEM_LVL_HIT;
> } else if (record->type & (ARM_SPE_L1D_ACCESS | ARM_SPE_L1D_MISS)) {
> - data_src.mem_lvl = PERF_MEM_LVL_L1;
> + data_src->mem_lvl = PERF_MEM_LVL_L1;
>
> if (record->type & ARM_SPE_L1D_MISS)
> - data_src.mem_lvl |= PERF_MEM_LVL_MISS;
> + data_src->mem_lvl |= PERF_MEM_LVL_MISS;
> else
> - data_src.mem_lvl |= PERF_MEM_LVL_HIT;
> + data_src->mem_lvl |= PERF_MEM_LVL_HIT;
> }
>
> if (record->type & ARM_SPE_REMOTE_ACCESS)
> - data_src.mem_lvl |= PERF_MEM_LVL_REM_CCE1;
> + data_src->mem_lvl |= PERF_MEM_LVL_REM_CCE1;
> +}
> +
> +static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 midr)
> +{
> + union perf_mem_data_src data_src = { 0 };
> + bool is_neoverse = is_midr_in_range(midr, neoverse_spe);
> +
> + if (record->op == ARM_SPE_LD)
> + data_src.mem_op = PERF_MEM_OP_LOAD;
> + else if (record->op == ARM_SPE_ST)
> + data_src.mem_op = PERF_MEM_OP_STORE;
> + else
> + return 0;
> +
> + if (is_neoverse)
> + arm_spe__synth_data_source_neoverse(record, &data_src);
> + else
> + arm_spe__synth_data_source_generic(record, &data_src);
>
> if (record->type & (ARM_SPE_TLB_ACCESS | ARM_SPE_TLB_MISS)) {
> data_src.mem_dtlb = PERF_MEM_TLB_WK;
> @@ -436,7 +531,7 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
> u64 data_src;
> int err;
>
> - data_src = arm_spe__synth_data_source(record);
> + data_src = arm_spe__synth_data_source(record, spe->midr);
>
> if (spe->sample_flc) {
> if (record->type & ARM_SPE_L1D_MISS) {
> @@ -1178,6 +1273,8 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
> struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
> size_t min_sz = sizeof(u64) * ARM_SPE_AUXTRACE_PRIV_MAX;
> struct perf_record_time_conv *tc = &session->time_conv;
> + const char *cpuid = perf_env__cpuid(session->evlist->env);
> + u64 midr = strtol(cpuid, NULL, 16);
> struct arm_spe *spe;
> int err;
>
> @@ -1197,6 +1294,7 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
> spe->machine = &session->machines.host; /* No kvm support */
> spe->auxtrace_type = auxtrace_info->type;
> spe->pmu_type = auxtrace_info->priv[ARM_SPE_PMU_TYPE];
> + spe->midr = midr;
>
> spe->timeless_decoding = arm_spe__is_timeless_decoding(spe);
>
> --
> 2.34.1

--

- Arnaldo