[PATCH v2 6/6] perf arm-spe: Set sample's data source field

From: James Clark
Date: Thu Feb 11 2021 - 08:56:54 EST


From: Leo Yan <leo.yan@xxxxxxxxxx>

The sample structure contains the field 'data_src' which is used to
tell the data operation attributions, e.g. operation type is loading or
storing, cache level, it's snooping or remote accessing, etc. At the
end, the 'data_src' will be parsed by perf mem/c2c tools to display
human readable strings.

This patch is to fill the 'data_src' field in the synthesized samples
base on different types. Currently perf tool can display statistics for
L1/L2/L3 caches but it doesn't support the 'last level cache'. To fit
to current implementation, 'data_src' field uses L3 cache for last level
cache.

Before this commit, perf mem report looks like this:
# Samples: 75K of event 'l1d-miss'
# Total weight : 75951
# Sort order : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked
#
# Overhead Samples Local Weight Memory access Symbol Shared Object Data Symbol Data Object Snoop TLB access
# ........ ............ ............ ........................ ...................... ................ ...................... ................ ............ ...................
#
81.56% 61945 0 N/A [.] 0x00000000000009d8 serial_c [.] 0000000000000000 [unknown] N/A N/A
18.44% 14003 0 N/A [.] 0x0000000000000828 serial_c [.] 0000000000000000 [unknown] N/A N/A

Now on a system with Arm SPE, addresses and access types are displayed:

# Samples: 75K of event 'l1d-miss'
# Total weight : 75951
# Sort order : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked
#
# Overhead Samples Local Weight Memory access Symbol Shared Object Data Symbol Data Object Snoop TLB access
# ........ ............ ............ ........................ ...................... ................ ...................... ........... ............ ......................
#
0.43% 324 0 L1 miss [.] 0x00000000000009d8 serial_c [.] 0x0000ffff80794e00 anon N/A Walker hit
0.42% 322 0 L1 miss [.] 0x00000000000009d8 serial_c [.] 0x0000ffff80794580 anon N/A Walker hit

Signed-off-by: Leo Yan <leo.yan@xxxxxxxxxx>
Signed-off-by: James Clark <james.clark@xxxxxxx>
Reviewed-by: James Clark <james.clark@xxxxxxx>
Tested-by: James Clark <james.clark@xxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: John Garry <john.garry@xxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
Cc: Al Grant <al.grant@xxxxxxx>
Cc: Andre Przywara <andre.przywara@xxxxxxx>
Cc: Wei Li <liwei391@xxxxxxxxxx>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
---
tools/perf/util/arm-spe.c | 69 ++++++++++++++++++++++++++++++++++-----
1 file changed, 60 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 5550906486d8..27a0b9dfe22d 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -261,7 +261,7 @@ arm_spe_deliver_synth_event(struct arm_spe *spe,
}

static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
- u64 spe_events_id)
+ u64 spe_events_id, u64 data_src)
{
struct arm_spe *spe = speq->spe;
struct arm_spe_record *record = &speq->decoder->record;
@@ -274,6 +274,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
sample.stream_id = spe_events_id;
sample.addr = record->virt_addr;
sample.phys_addr = record->phys_addr;
+ sample.data_src = data_src;

return arm_spe_deliver_synth_event(spe, speq, event, &sample);
}
@@ -307,21 +308,66 @@ static bool arm_spe__is_memory_event(enum arm_spe_sample_type type)
return false;
}

+static u64 arm_spe__synth_data_source(const struct arm_spe_record *record)
+{
+ union perf_mem_data_src data_src = { 0 };
+
+ if (record->op == ARM_SPE_LD)
+ data_src.mem_op = PERF_MEM_OP_LOAD;
+ else
+ data_src.mem_op = PERF_MEM_OP_STORE;
+
+ if (record->type & (ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS)) {
+ data_src.mem_lvl = PERF_MEM_LVL_L3;
+
+ if (record->type & ARM_SPE_LLC_MISS)
+ data_src.mem_lvl |= PERF_MEM_LVL_MISS;
+ else
+ 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;
+
+ if (record->type & ARM_SPE_L1D_MISS)
+ data_src.mem_lvl |= PERF_MEM_LVL_MISS;
+ else
+ data_src.mem_lvl |= PERF_MEM_LVL_HIT;
+ }
+
+ if (record->type & ARM_SPE_REMOTE_ACCESS)
+ data_src.mem_lvl |= PERF_MEM_LVL_REM_CCE1;
+
+ if (record->type & (ARM_SPE_TLB_ACCESS | ARM_SPE_TLB_MISS)) {
+ data_src.mem_dtlb = PERF_MEM_TLB_WK;
+
+ if (record->type & ARM_SPE_TLB_MISS)
+ data_src.mem_dtlb |= PERF_MEM_TLB_MISS;
+ else
+ data_src.mem_dtlb |= PERF_MEM_TLB_HIT;
+ }
+
+ return data_src.val;
+}
+
static int arm_spe_sample(struct arm_spe_queue *speq)
{
const struct arm_spe_record *record = &speq->decoder->record;
struct arm_spe *spe = speq->spe;
+ u64 data_src;
int err;

+ data_src = arm_spe__synth_data_source(record);
+
if (spe->sample_flc) {
if (record->type & ARM_SPE_L1D_MISS) {
- err = arm_spe__synth_mem_sample(speq, spe->l1d_miss_id);
+ err = arm_spe__synth_mem_sample(speq, spe->l1d_miss_id,
+ data_src);
if (err)
return err;
}

if (record->type & ARM_SPE_L1D_ACCESS) {
- err = arm_spe__synth_mem_sample(speq, spe->l1d_access_id);
+ err = arm_spe__synth_mem_sample(speq, spe->l1d_access_id,
+ data_src);
if (err)
return err;
}
@@ -329,13 +375,15 @@ static int arm_spe_sample(struct arm_spe_queue *speq)

if (spe->sample_llc) {
if (record->type & ARM_SPE_LLC_MISS) {
- err = arm_spe__synth_mem_sample(speq, spe->llc_miss_id);
+ err = arm_spe__synth_mem_sample(speq, spe->llc_miss_id,
+ data_src);
if (err)
return err;
}

if (record->type & ARM_SPE_LLC_ACCESS) {
- err = arm_spe__synth_mem_sample(speq, spe->llc_access_id);
+ err = arm_spe__synth_mem_sample(speq, spe->llc_access_id,
+ data_src);
if (err)
return err;
}
@@ -343,13 +391,15 @@ static int arm_spe_sample(struct arm_spe_queue *speq)

if (spe->sample_tlb) {
if (record->type & ARM_SPE_TLB_MISS) {
- err = arm_spe__synth_mem_sample(speq, spe->tlb_miss_id);
+ err = arm_spe__synth_mem_sample(speq, spe->tlb_miss_id,
+ data_src);
if (err)
return err;
}

if (record->type & ARM_SPE_TLB_ACCESS) {
- err = arm_spe__synth_mem_sample(speq, spe->tlb_access_id);
+ err = arm_spe__synth_mem_sample(speq, spe->tlb_access_id,
+ data_src);
if (err)
return err;
}
@@ -363,13 +413,14 @@ static int arm_spe_sample(struct arm_spe_queue *speq)

if (spe->sample_remote_access &&
(record->type & ARM_SPE_REMOTE_ACCESS)) {
- err = arm_spe__synth_mem_sample(speq, spe->remote_access_id);
+ err = arm_spe__synth_mem_sample(speq, spe->remote_access_id,
+ data_src);
if (err)
return err;
}

if (spe->sample_memory && arm_spe__is_memory_event(record->type)) {
- err = arm_spe__synth_mem_sample(speq, spe->memory_id);
+ err = arm_spe__synth_mem_sample(speq, spe->memory_id, data_src);
if (err)
return err;
}
--
2.28.0