| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20220221224807.18172-1-alisaidi@amazon.com>
Date: Mon, 21 Feb 2022 22:47:59 +0000
From: Ali Saidi <alisaidi@...zon.com>
To: <linux-kernel@...r.kernel.org>, <linux-perf-users@...r.kernel.org>,
<linux-arm-kernel@...ts.infradead.org>, <german.gomez@....com>,
<leo.yan@...aro.org>
CC: <alisaidi@...zon.com>, <benh@...nel.crashing.org>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
"Arnaldo Carvalho de Melo" <acme@...nel.org>,
Mark Rutland <mark.rutland@....com>,
"Alexander Shishkin" <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...hat.com>,
Namhyung Kim <namhyung@...nel.org>,
John Garry <john.garry@...wei.com>,
"Will Deacon" <will@...nel.org>,
Mathieu Poirier <mathieu.poirier@...aro.org>,
"James Clark" <james.clark@....com>,
Andrew Kilroy <andrew.kilroy@....com>,
Jin Yao <yao.jin@...ux.intel.com>,
Kajol Jain <kjain@...ux.ibm.com>,
Li Huafei <lihuafei1@...wei.com>
Subject: [PATCH v2 1/2] perf arm-spe: Use SPE data source for neoverse cores
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 instead of the
deprecated mem_lvl namespace.
Signed-off-by: Ali Saidi <alisaidi@...zon.com>
---
.../util/arm-spe-decoder/arm-spe-decoder.c | 1 +
.../util/arm-spe-decoder/arm-spe-decoder.h | 12 ++
tools/perf/util/arm-spe.c | 106 +++++++++++++++---
3 files changed, 104 insertions(+), 15 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..c81bf90c0996 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_LCL_CLSTR = 0xa,
+ ARM_SPE_NV_SYS_CACHE = 0xb,
+ ARM_SPE_NV_PEER_CLSTR = 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 d2b64e3f588b..e0243c2fed5f 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;
@@ -399,33 +401,103 @@ 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 };
+static const struct midr_range neoverse_spe[] = {
+ MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
+ MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+ {},
+};
- if (record->op == ARM_SPE_LD)
- data_src.mem_op = PERF_MEM_OP_LOAD;
- else
- data_src.mem_op = PERF_MEM_OP_STORE;
+static void arm_spe__synth_data_source_neoverse(const struct arm_spe_record *record,
+ union perf_mem_data_src *data_src)
+{
+ switch (record->source) {
+ case ARM_SPE_NV_L1D:
+ data_src->mem_lvl = PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L1;
+ break;
+ case ARM_SPE_NV_L2:
+ data_src->mem_lvl = PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
+ break;
+ case ARM_SPE_NV_PEER_CORE:
+ data_src->mem_lvl = PERF_MEM_LVL_HIT;
+ data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE;
+ break;
+ /*
+ * We don't know if this is L1, L2, or even L3 (for the cases the system
+ * has an L3, but we do know it was a cache-2-cache transfer, so set
+ * SNOOP_HITM
+ */
+ case ARM_SPE_NV_LCL_CLSTR:
+ case ARM_SPE_NV_PEER_CLSTR:
+ data_src->mem_lvl = PERF_MEM_LVL_HIT;
+ data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE;
+ break;
+ /*
+ * System cache is assumed to be L4, as cluster cache (if it exists)
+ * would be L3 cache on Neoverse platforms
+ */
+ case ARM_SPE_NV_SYS_CACHE:
+ data_src->mem_lvl = PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L4;
+ 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_snoop = PERF_MEM_SNOOP_HITM;
+ data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
+ break;
+ case ARM_SPE_NV_DRAM:
+ data_src->mem_lvl = PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_RAM;
+ 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
+ data_src.mem_op = PERF_MEM_OP_STORE;
+
+ 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;
@@ -446,7 +518,7 @@ 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) {
@@ -796,6 +868,10 @@ static int arm_spe_process_event(struct perf_session *session,
u64 timestamp;
struct arm_spe *spe = container_of(session->auxtrace,
struct arm_spe, auxtrace);
+ const char *cpuid = perf_env__cpuid(session->evlist->env);
+ u64 midr = strtol(cpuid, NULL, 16);
+
+ spe->midr = midr;
if (dump_trace)
return 0;
--
2.32.0
Powered by blists - more mailing lists