* [PATCH v9 1/3] perf: cs-etm: Move mapping of Trace ID and cpu into helper function
2023-03-31 5:56 [PATCH v9 0/3] perf: cs-etm: Update perf to handle new Coresight Trace ID Mike Leach
@ 2023-03-31 5:56 ` Mike Leach
2023-03-31 5:56 ` [PATCH v9 2/3] perf: cs-etm: Update record event to use new Trace ID protocol Mike Leach
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: Mike Leach @ 2023-03-31 5:56 UTC (permalink / raw)
To: linux-perf-users, linux-arm-kernel, coresight, linux-kernel, acme
Cc: suzuki.poulose, leo.yan, peterz, mingo, will, mark.rutland,
alexander.shishkin, jolsa, namhyung, gankulkarni, darren,
Mike Leach
The information to associate Trace ID and CPU will be changing.
Drivers will start outputting this as a hardware ID packet in the data
file which if present will be used in preference to the AUXINFO values.
To prepare for this we provide a helper functions to do the individual ID
mapping, and one to extract the IDs from the completed metadata blocks.
Signed-off-by: Mike Leach <mike.leach@linaro.org>
Reviewed-by: James Clark <james.clark@arm.com>
Acked-by: Suzuki K Poulose <suzuki.poulose@arm.com>
---
tools/include/linux/coresight-pmu.h | 5 ++
tools/perf/util/cs-etm-base.c | 3 +-
tools/perf/util/cs-etm.c | 92 +++++++++++++++++++----------
tools/perf/util/cs-etm.h | 14 ++++-
4 files changed, 79 insertions(+), 35 deletions(-)
diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index 6c2fd6cc5a98..db9c7c0abb6a 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -7,9 +7,14 @@
#ifndef _LINUX_CORESIGHT_PMU_H
#define _LINUX_CORESIGHT_PMU_H
+#include <linux/bits.h>
+
#define CORESIGHT_ETM_PMU_NAME "cs_etm"
#define CORESIGHT_ETM_PMU_SEED 0x10
+/* CoreSight trace ID is currently the bottom 7 bits of the value */
+#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0)
+
/*
* Below are the definition of bit offsets for perf option, and works as
* arbitrary values for all ETM versions.
diff --git a/tools/perf/util/cs-etm-base.c b/tools/perf/util/cs-etm-base.c
index 5f48b756c4cf..4abe416e3feb 100644
--- a/tools/perf/util/cs-etm-base.c
+++ b/tools/perf/util/cs-etm-base.c
@@ -148,7 +148,8 @@ static void cs_etm__print_auxtrace_info(u64 *val, int num)
for (i = CS_HEADER_VERSION_MAX; cpu < num; cpu++) {
if (version == 0)
err = cs_etm__print_cpu_metadata_v0(val, &i);
- else if (version == 1)
+ /* printing same for both, but value bit flags added on v2 */
+ else if ((version == 1) || (version == 2))
err = cs_etm__print_cpu_metadata_v1(val, &i);
if (err)
return;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index f65bac5ddbdb..5fc9c288080b 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -196,6 +196,30 @@ int cs_etm__get_pid_fmt(u8 trace_chan_id, u64 *pid_fmt)
return 0;
}
+static int cs_etm__map_trace_id(u8 trace_chan_id, u64 *cpu_metadata)
+{
+ struct int_node *inode;
+
+ /* Get an RB node for this CPU */
+ inode = intlist__findnew(traceid_list, trace_chan_id);
+
+ /* Something went wrong, no need to continue */
+ if (!inode)
+ return -ENOMEM;
+
+ /*
+ * The node for that CPU should not be taken.
+ * Back out if that's the case.
+ */
+ if (inode->priv)
+ return -EINVAL;
+
+ /* All good, associate the traceID with the metadata pointer */
+ inode->priv = cpu_metadata;
+
+ return 0;
+}
+
void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
u8 trace_chan_id)
{
@@ -2804,17 +2828,46 @@ static bool cs_etm__has_virtual_ts(u64 **metadata, int num_cpu)
return true;
}
+/* map trace ids to correct metadata block, from information in metadata */
+static int cs_etm__map_trace_ids_metadata(int num_cpu, u64 **metadata)
+{
+ u64 cs_etm_magic;
+ u8 trace_chan_id;
+ int i, err;
+
+ for (i = 0; i < num_cpu; i++) {
+ cs_etm_magic = metadata[i][CS_ETM_MAGIC];
+ switch (cs_etm_magic) {
+ case __perf_cs_etmv3_magic:
+ trace_chan_id = (u8)((metadata[i][CS_ETM_ETMTRACEIDR]) &
+ CORESIGHT_TRACE_ID_VAL_MASK);
+ break;
+ case __perf_cs_etmv4_magic:
+ case __perf_cs_ete_magic:
+ trace_chan_id = (u8)((metadata[i][CS_ETMV4_TRCTRACEIDR]) &
+ CORESIGHT_TRACE_ID_VAL_MASK);
+ break;
+ default:
+ /* unknown magic number */
+ return -EINVAL;
+ }
+ err = cs_etm__map_trace_id(trace_chan_id, metadata[i]);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
int cs_etm__process_auxtrace_info_full(union perf_event *event,
struct perf_session *session)
{
struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
struct cs_etm_auxtrace *etm = NULL;
- struct int_node *inode;
struct perf_record_time_conv *tc = &session->time_conv;
int event_header_size = sizeof(struct perf_event_header);
int total_size = auxtrace_info->header.size;
int priv_size = 0;
- int num_cpu, trcidr_idx;
+ int num_cpu;
int err = 0;
int i, j;
u64 *ptr = NULL;
@@ -2853,23 +2906,13 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
cs_etm__create_meta_blk(ptr, &i,
CS_ETM_PRIV_MAX,
CS_ETM_NR_TRC_PARAMS_V0);
-
- /* The traceID is our handle */
- trcidr_idx = CS_ETM_ETMTRACEIDR;
-
} else if (ptr[i] == __perf_cs_etmv4_magic) {
metadata[j] =
cs_etm__create_meta_blk(ptr, &i,
CS_ETMV4_PRIV_MAX,
CS_ETMV4_NR_TRC_PARAMS_V0);
-
- /* The traceID is our handle */
- trcidr_idx = CS_ETMV4_TRCTRACEIDR;
} else if (ptr[i] == __perf_cs_ete_magic) {
metadata[j] = cs_etm__create_meta_blk(ptr, &i, CS_ETE_PRIV_MAX, -1);
-
- /* ETE shares first part of metadata with ETMv4 */
- trcidr_idx = CS_ETMV4_TRCTRACEIDR;
} else {
ui__error("CS ETM Trace: Unrecognised magic number %#"PRIx64". File could be from a newer version of perf.\n",
ptr[i]);
@@ -2881,26 +2924,6 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
err = -ENOMEM;
goto err_free_metadata;
}
-
- /* Get an RB node for this CPU */
- inode = intlist__findnew(traceid_list, metadata[j][trcidr_idx]);
-
- /* Something went wrong, no need to continue */
- if (!inode) {
- err = -ENOMEM;
- goto err_free_metadata;
- }
-
- /*
- * The node for that CPU should not be taken.
- * Back out if that's the case.
- */
- if (inode->priv) {
- err = -EINVAL;
- goto err_free_metadata;
- }
- /* All good, associate the traceID with the metadata pointer */
- inode->priv = metadata[j];
}
/*
@@ -2994,6 +3017,11 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
if (err)
goto err_delete_thread;
+ /* before aux records are queued, need to map metadata to trace IDs */
+ err = cs_etm__map_trace_ids_metadata(num_cpu, metadata);
+ if (err)
+ goto err_delete_thread;
+
err = cs_etm__queue_aux_records(session);
if (err)
goto err_delete_thread;
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 98a4f7113d2f..661f029322e4 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -29,13 +29,17 @@ enum {
/*
* Update the version for new format.
*
- * New version 1 format adds a param count to the per cpu metadata.
+ * Version 1: format adds a param count to the per cpu metadata.
* This allows easy adding of new metadata parameters.
* Requires that new params always added after current ones.
* Also allows client reader to handle file versions that are different by
* checking the number of params in the file vs the number expected.
+ *
+ * Version 2: Drivers will use PERF_RECORD_AUX_OUTPUT_HW_ID to output
+ * CoreSight Trace ID. ...TRACEIDR metadata will be set to legacy values
+ * but with addition flags.
*/
-#define CS_HEADER_CURRENT_VERSION 1
+#define CS_HEADER_CURRENT_VERSION 2
/* Beginning of header common to both ETMv3 and V4 */
enum {
@@ -97,6 +101,12 @@ enum {
CS_ETE_PRIV_MAX
};
+/*
+ * Check for valid CoreSight trace ID. If an invalid value is present in the metadata,
+ * then IDs are present in the hardware ID packet in the data file.
+ */
+#define CS_IS_VALID_TRACE_ID(id) ((id > 0) && (id < 0x70))
+
/*
* ETMv3 exception encoding number:
* See Embedded Trace Macrocell specification (ARM IHI 0014Q)
--
2.17.1
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH v9 2/3] perf: cs-etm: Update record event to use new Trace ID protocol
2023-03-31 5:56 [PATCH v9 0/3] perf: cs-etm: Update perf to handle new Coresight Trace ID Mike Leach
2023-03-31 5:56 ` [PATCH v9 1/3] perf: cs-etm: Move mapping of Trace ID and cpu into helper function Mike Leach
@ 2023-03-31 5:56 ` Mike Leach
2023-03-31 5:56 ` [PATCH v9 3/3] perf: cs-etm: Handle PERF_RECORD_AUX_OUTPUT_HW_ID packet Mike Leach
2023-03-31 11:51 ` [PATCH v9 0/3] perf: cs-etm: Update perf to handle new Coresight Trace ID Arnaldo Carvalho de Melo
3 siblings, 0 replies; 5+ messages in thread
From: Mike Leach @ 2023-03-31 5:56 UTC (permalink / raw)
To: linux-perf-users, linux-arm-kernel, coresight, linux-kernel, acme
Cc: suzuki.poulose, leo.yan, peterz, mingo, will, mark.rutland,
alexander.shishkin, jolsa, namhyung, gankulkarni, darren,
Mike Leach
Trace IDs are now dynamically allocated.
Previously used the static association algorithm that is no longer
used. The 'cpu * 2 + seed' was outdated and broken for systems with high
core counts (>46). as it did not scale and was broken for larger
core counts.
Trace ID will now be sent in PERF_RECORD_AUX_OUTPUT_HW_ID record.
Legacy ID algorithm renamed and retained for limited backward
compatibility use.
Signed-off-by: Mike Leach <mike.leach@linaro.org>
Reviewed-by: James Clark <james.clark@arm.com>
Acked-by: Suzuki K Poulose <suzuki.poulose@arm.com>
---
tools/include/linux/coresight-pmu.h | 29 +++++++++++++++++------------
tools/perf/arch/arm/util/cs-etm.c | 27 +++++++++++++++++----------
2 files changed, 34 insertions(+), 22 deletions(-)
diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index db9c7c0abb6a..1760f9a574b0 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -10,11 +10,27 @@
#include <linux/bits.h>
#define CORESIGHT_ETM_PMU_NAME "cs_etm"
-#define CORESIGHT_ETM_PMU_SEED 0x10
+
+/*
+ * The legacy Trace ID system based on fixed calculation from the cpu
+ * number. This has been replaced by drivers using a dynamic allocation
+ * system - but need to retain the legacy algorithm for backward comparibility
+ * in certain situations:-
+ * a) new perf running on older systems that generate the legacy mapping
+ * b) older tools that may not update at the same time as the kernel.
+ */
+#define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2))
/* CoreSight trace ID is currently the bottom 7 bits of the value */
#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0)
+/*
+ * perf record will set the legacy meta data values as unused initially.
+ * This allows perf report to manage the decoders created when dynamic
+ * allocation in operation.
+ */
+#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31)
+
/*
* Below are the definition of bit offsets for perf option, and works as
* arbitrary values for all ETM versions.
@@ -39,15 +55,4 @@
#define ETM4_CFG_BIT_RETSTK 12
#define ETM4_CFG_BIT_VMID_OPT 15
-static inline int coresight_get_trace_id(int cpu)
-{
- /*
- * A trace ID of value 0 is invalid, so let's start at some
- * random value that fits in 7 bits and go from there. Since
- * the common convention is to have data trace IDs be I(N) + 1,
- * set instruction trace IDs as a function of the CPU number.
- */
- return (CORESIGHT_ETM_PMU_SEED + (cpu * 2));
-}
-
#endif
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 86b61ad74f90..e02a9bfc3d42 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -437,13 +437,16 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
evlist__to_front(evlist, cs_etm_evsel);
/*
- * In the case of per-cpu mmaps, we need the CPU on the
- * AUX event. We also need the contextID in order to be notified
+ * get the CPU on the sample - need it to associate trace ID in the
+ * AUX_OUTPUT_HW_ID event, and the AUX event for per-cpu mmaps.
+ */
+ evsel__set_sample_bit(cs_etm_evsel, CPU);
+
+ /*
+ * Also the case of per-cpu mmaps, need the contextID in order to be notified
* when a context switch happened.
*/
if (!perf_cpu_map__empty(cpus)) {
- evsel__set_sample_bit(cs_etm_evsel, CPU);
-
err = cs_etm_set_option(itr, cs_etm_evsel,
BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_TS));
if (err)
@@ -679,8 +682,10 @@ static void cs_etm_save_etmv4_header(__u64 data[], struct auxtrace_record *itr,
/* Get trace configuration register */
data[CS_ETMV4_TRCCONFIGR] = cs_etmv4_get_config(itr);
- /* Get traceID from the framework */
- data[CS_ETMV4_TRCTRACEIDR] = coresight_get_trace_id(cpu);
+ /* traceID set to legacy version, in case new perf running on older system */
+ data[CS_ETMV4_TRCTRACEIDR] =
+ CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG;
+
/* Get read-only information from sysFS */
data[CS_ETMV4_TRCIDR0] = cs_etm_get_ro(cs_etm_pmu, cpu,
metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
@@ -711,8 +716,10 @@ static void cs_etm_save_ete_header(__u64 data[], struct auxtrace_record *itr, in
/* Get trace configuration register */
data[CS_ETE_TRCCONFIGR] = cs_etmv4_get_config(itr);
- /* Get traceID from the framework */
- data[CS_ETE_TRCTRACEIDR] = coresight_get_trace_id(cpu);
+ /* traceID set to legacy version, in case new perf running on older system */
+ data[CS_ETE_TRCTRACEIDR] =
+ CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG;
+
/* Get read-only information from sysFS */
data[CS_ETE_TRCIDR0] = cs_etm_get_ro(cs_etm_pmu, cpu,
metadata_ete_ro[CS_ETE_TRCIDR0]);
@@ -768,9 +775,9 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
magic = __perf_cs_etmv3_magic;
/* Get configuration register */
info->priv[*offset + CS_ETM_ETMCR] = cs_etm_get_config(itr);
- /* Get traceID from the framework */
+ /* traceID set to legacy value in case new perf running on old system */
info->priv[*offset + CS_ETM_ETMTRACEIDR] =
- coresight_get_trace_id(cpu);
+ CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG;
/* Get read-only information from sysFS */
info->priv[*offset + CS_ETM_ETMCCER] =
cs_etm_get_ro(cs_etm_pmu, cpu,
--
2.17.1
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH v9 3/3] perf: cs-etm: Handle PERF_RECORD_AUX_OUTPUT_HW_ID packet
2023-03-31 5:56 [PATCH v9 0/3] perf: cs-etm: Update perf to handle new Coresight Trace ID Mike Leach
2023-03-31 5:56 ` [PATCH v9 1/3] perf: cs-etm: Move mapping of Trace ID and cpu into helper function Mike Leach
2023-03-31 5:56 ` [PATCH v9 2/3] perf: cs-etm: Update record event to use new Trace ID protocol Mike Leach
@ 2023-03-31 5:56 ` Mike Leach
2023-03-31 11:51 ` [PATCH v9 0/3] perf: cs-etm: Update perf to handle new Coresight Trace ID Arnaldo Carvalho de Melo
3 siblings, 0 replies; 5+ messages in thread
From: Mike Leach @ 2023-03-31 5:56 UTC (permalink / raw)
To: linux-perf-users, linux-arm-kernel, coresight, linux-kernel, acme
Cc: suzuki.poulose, leo.yan, peterz, mingo, will, mark.rutland,
alexander.shishkin, jolsa, namhyung, gankulkarni, darren,
Mike Leach
When using dynamically assigned CoreSight trace IDs the drivers can output
the ID / CPU association as a PERF_RECORD_AUX_OUTPUT_HW_ID packet.
Update cs-etm decoder to handle this packet by setting the CPU/Trace ID
mapping.
Signed-off-by: Mike Leach <mike.leach@linaro.org>
Reviewed-by: James Clark <james.clark@arm.com>
Acked-by: Suzuki K Poulose <suzuki.poulose@arm.com>
---
tools/include/linux/coresight-pmu.h | 15 ++
.../perf/util/cs-etm-decoder/cs-etm-decoder.c | 7 +
tools/perf/util/cs-etm.c | 246 ++++++++++++++++--
3 files changed, 250 insertions(+), 18 deletions(-)
diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index 1760f9a574b0..cef3b1c25335 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -31,6 +31,9 @@
*/
#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31)
+/* Value to set for unused trace ID values */
+#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F
+
/*
* Below are the definition of bit offsets for perf option, and works as
* arbitrary values for all ETM versions.
@@ -55,4 +58,16 @@
#define ETM4_CFG_BIT_RETSTK 12
#define ETM4_CFG_BIT_VMID_OPT 15
+/*
+ * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload.
+ * Used to associate a CPU with the CoreSight Trace ID.
+ * [07:00] - Trace ID - uses 8 bits to make value easy to read in file.
+ * [59:08] - Unused (SBZ)
+ * [63:60] - Version
+ */
+#define CS_AUX_HW_ID_TRACE_ID_MASK GENMASK_ULL(7, 0)
+#define CS_AUX_HW_ID_VERSION_MASK GENMASK_ULL(63, 60)
+
+#define CS_AUX_HW_ID_CURR_VERSION 0
+
#endif
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index d0e521dfcf35..82a27ab90c8b 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -668,6 +668,7 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params,
switch (t_params->protocol) {
case CS_ETM_PROTO_ETMV3:
case CS_ETM_PROTO_PTM:
+ csid = (t_params->etmv3.reg_idr & CORESIGHT_TRACE_ID_VAL_MASK);
cs_etm_decoder__gen_etmv3_config(t_params, &config_etmv3);
decoder->decoder_name = (t_params->protocol == CS_ETM_PROTO_ETMV3) ?
OCSD_BUILTIN_DCD_ETMV3 :
@@ -675,11 +676,13 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params,
trace_config = &config_etmv3;
break;
case CS_ETM_PROTO_ETMV4i:
+ csid = (t_params->etmv4.reg_traceidr & CORESIGHT_TRACE_ID_VAL_MASK);
cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4);
decoder->decoder_name = OCSD_BUILTIN_DCD_ETMV4I;
trace_config = &trace_config_etmv4;
break;
case CS_ETM_PROTO_ETE:
+ csid = (t_params->ete.reg_traceidr & CORESIGHT_TRACE_ID_VAL_MASK);
cs_etm_decoder__gen_ete_config(t_params, &trace_config_ete);
decoder->decoder_name = OCSD_BUILTIN_DCD_ETE;
trace_config = &trace_config_ete;
@@ -688,6 +691,10 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params,
return -1;
}
+ /* if the CPU has no trace ID associated, no decoder needed */
+ if (csid == CORESIGHT_TRACE_ID_UNUSED_VAL)
+ return 0;
+
if (d_params->operation == CS_ETM_OPERATION_DECODE) {
if (ocsd_dt_create_decoder(decoder->dcd_tree,
decoder->decoder_name,
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 5fc9c288080b..94e2d02009eb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -220,6 +220,143 @@ static int cs_etm__map_trace_id(u8 trace_chan_id, u64 *cpu_metadata)
return 0;
}
+static int cs_etm__metadata_get_trace_id(u8 *trace_chan_id, u64 *cpu_metadata)
+{
+ u64 cs_etm_magic = cpu_metadata[CS_ETM_MAGIC];
+
+ switch (cs_etm_magic) {
+ case __perf_cs_etmv3_magic:
+ *trace_chan_id = (u8)(cpu_metadata[CS_ETM_ETMTRACEIDR] &
+ CORESIGHT_TRACE_ID_VAL_MASK);
+ break;
+ case __perf_cs_etmv4_magic:
+ case __perf_cs_ete_magic:
+ *trace_chan_id = (u8)(cpu_metadata[CS_ETMV4_TRCTRACEIDR] &
+ CORESIGHT_TRACE_ID_VAL_MASK);
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/*
+ * update metadata trace ID from the value found in the AUX_HW_INFO packet.
+ * This will also clear the CORESIGHT_TRACE_ID_UNUSED_FLAG flag if present.
+ */
+static int cs_etm__metadata_set_trace_id(u8 trace_chan_id, u64 *cpu_metadata)
+{
+ u64 cs_etm_magic = cpu_metadata[CS_ETM_MAGIC];
+
+ switch (cs_etm_magic) {
+ case __perf_cs_etmv3_magic:
+ cpu_metadata[CS_ETM_ETMTRACEIDR] = trace_chan_id;
+ break;
+ case __perf_cs_etmv4_magic:
+ case __perf_cs_ete_magic:
+ cpu_metadata[CS_ETMV4_TRCTRACEIDR] = trace_chan_id;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/*
+ * FIELD_GET (linux/bitfield.h) not available outside kernel code,
+ * and the header contains too many dependencies to just copy over,
+ * so roll our own based on the original
+ */
+#define __bf_shf(x) (__builtin_ffsll(x) - 1)
+#define FIELD_GET(_mask, _reg) \
+ ({ \
+ (typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \
+ })
+
+/*
+ * Handle the PERF_RECORD_AUX_OUTPUT_HW_ID event.
+ *
+ * The payload associates the Trace ID and the CPU.
+ * The routine is tolerant of seeing multiple packets with the same association,
+ * but a CPU / Trace ID association changing during a session is an error.
+ */
+static int cs_etm__process_aux_output_hw_id(struct perf_session *session,
+ union perf_event *event)
+{
+ struct cs_etm_auxtrace *etm;
+ struct perf_sample sample;
+ struct int_node *inode;
+ struct evsel *evsel;
+ u64 *cpu_data;
+ u64 hw_id;
+ int cpu, version, err;
+ u8 trace_chan_id, curr_chan_id;
+
+ /* extract and parse the HW ID */
+ hw_id = event->aux_output_hw_id.hw_id;
+ version = FIELD_GET(CS_AUX_HW_ID_VERSION_MASK, hw_id);
+ trace_chan_id = FIELD_GET(CS_AUX_HW_ID_TRACE_ID_MASK, hw_id);
+
+ /* check that we can handle this version */
+ if (version > CS_AUX_HW_ID_CURR_VERSION)
+ return -EINVAL;
+
+ /* get access to the etm metadata */
+ etm = container_of(session->auxtrace, struct cs_etm_auxtrace, auxtrace);
+ if (!etm || !etm->metadata)
+ return -EINVAL;
+
+ /* parse the sample to get the CPU */
+ evsel = evlist__event2evsel(session->evlist, event);
+ if (!evsel)
+ return -EINVAL;
+ err = evsel__parse_sample(evsel, event, &sample);
+ if (err)
+ return err;
+ cpu = sample.cpu;
+ if (cpu == -1) {
+ /* no CPU in the sample - possibly recorded with an old version of perf */
+ pr_err("CS_ETM: no CPU AUX_OUTPUT_HW_ID sample. Use compatible perf to record.");
+ return -EINVAL;
+ }
+
+ /* See if the ID is mapped to a CPU, and it matches the current CPU */
+ inode = intlist__find(traceid_list, trace_chan_id);
+ if (inode) {
+ cpu_data = inode->priv;
+ if ((int)cpu_data[CS_ETM_CPU] != cpu) {
+ pr_err("CS_ETM: map mismatch between HW_ID packet CPU and Trace ID\n");
+ return -EINVAL;
+ }
+
+ /* check that the mapped ID matches */
+ err = cs_etm__metadata_get_trace_id(&curr_chan_id, cpu_data);
+ if (err)
+ return err;
+ if (curr_chan_id != trace_chan_id) {
+ pr_err("CS_ETM: mismatch between CPU trace ID and HW_ID packet ID\n");
+ return -EINVAL;
+ }
+
+ /* mapped and matched - return OK */
+ return 0;
+ }
+
+ /* not one we've seen before - lets map it */
+ cpu_data = etm->metadata[cpu];
+ err = cs_etm__map_trace_id(trace_chan_id, cpu_data);
+ if (err)
+ return err;
+
+ /*
+ * if we are picking up the association from the packet, need to plug
+ * the correct trace ID into the metadata for setting up decoders later.
+ */
+ err = cs_etm__metadata_set_trace_id(trace_chan_id, cpu_data);
+ return err;
+}
+
void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
u8 trace_chan_id)
{
@@ -2668,11 +2805,16 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o
}
/*
- * In per-thread mode, CPU is set to -1, but TID will be set instead. See
- * auxtrace_mmap_params__set_idx(). Return 'not found' if neither CPU nor TID match.
+ * In per-thread mode, auxtrace CPU is set to -1, but TID will be set instead. See
+ * auxtrace_mmap_params__set_idx(). However, the sample AUX event will contain a
+ * CPU as we set this always for the AUX_OUTPUT_HW_ID event.
+ * So now compare only TIDs if auxtrace CPU is -1, and CPUs if auxtrace CPU is not -1.
+ * Return 'not found' if mismatch.
*/
- if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) ||
- auxtrace_event->cpu != sample->cpu)
+ if (auxtrace_event->cpu == (__u32) -1) {
+ if (auxtrace_event->tid != sample->tid)
+ return 1;
+ } else if (auxtrace_event->cpu != sample->cpu)
return 1;
if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) {
@@ -2721,6 +2863,17 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o
return 1;
}
+static int cs_etm__process_aux_hw_id_cb(struct perf_session *session, union perf_event *event,
+ u64 offset __maybe_unused, void *data __maybe_unused)
+{
+ /* look to handle PERF_RECORD_AUX_OUTPUT_HW_ID early to ensure decoders can be set up */
+ if (event->header.type == PERF_RECORD_AUX_OUTPUT_HW_ID) {
+ (*(int *)data)++; /* increment found count */
+ return cs_etm__process_aux_output_hw_id(session, event);
+ }
+ return 0;
+}
+
static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event,
u64 offset __maybe_unused, void *data __maybe_unused)
{
@@ -2839,13 +2992,13 @@ static int cs_etm__map_trace_ids_metadata(int num_cpu, u64 **metadata)
cs_etm_magic = metadata[i][CS_ETM_MAGIC];
switch (cs_etm_magic) {
case __perf_cs_etmv3_magic:
- trace_chan_id = (u8)((metadata[i][CS_ETM_ETMTRACEIDR]) &
- CORESIGHT_TRACE_ID_VAL_MASK);
+ metadata[i][CS_ETM_ETMTRACEIDR] &= CORESIGHT_TRACE_ID_VAL_MASK;
+ trace_chan_id = (u8)(metadata[i][CS_ETM_ETMTRACEIDR]);
break;
case __perf_cs_etmv4_magic:
case __perf_cs_ete_magic:
- trace_chan_id = (u8)((metadata[i][CS_ETMV4_TRCTRACEIDR]) &
- CORESIGHT_TRACE_ID_VAL_MASK);
+ metadata[i][CS_ETMV4_TRCTRACEIDR] &= CORESIGHT_TRACE_ID_VAL_MASK;
+ trace_chan_id = (u8)(metadata[i][CS_ETMV4_TRCTRACEIDR]);
break;
default:
/* unknown magic number */
@@ -2858,6 +3011,35 @@ static int cs_etm__map_trace_ids_metadata(int num_cpu, u64 **metadata)
return 0;
}
+/*
+ * If we found AUX_HW_ID packets, then set any metadata marked as unused to the
+ * unused value to reduce the number of unneeded decoders created.
+ */
+static int cs_etm__clear_unused_trace_ids_metadata(int num_cpu, u64 **metadata)
+{
+ u64 cs_etm_magic;
+ int i;
+
+ for (i = 0; i < num_cpu; i++) {
+ cs_etm_magic = metadata[i][CS_ETM_MAGIC];
+ switch (cs_etm_magic) {
+ case __perf_cs_etmv3_magic:
+ if (metadata[i][CS_ETM_ETMTRACEIDR] & CORESIGHT_TRACE_ID_UNUSED_FLAG)
+ metadata[i][CS_ETM_ETMTRACEIDR] = CORESIGHT_TRACE_ID_UNUSED_VAL;
+ break;
+ case __perf_cs_etmv4_magic:
+ case __perf_cs_ete_magic:
+ if (metadata[i][CS_ETMV4_TRCTRACEIDR] & CORESIGHT_TRACE_ID_UNUSED_FLAG)
+ metadata[i][CS_ETMV4_TRCTRACEIDR] = CORESIGHT_TRACE_ID_UNUSED_VAL;
+ break;
+ default:
+ /* unknown magic number */
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
int cs_etm__process_auxtrace_info_full(union perf_event *event,
struct perf_session *session)
{
@@ -2869,6 +3051,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
int priv_size = 0;
int num_cpu;
int err = 0;
+ int aux_hw_id_found;
int i, j;
u64 *ptr = NULL;
u64 **metadata = NULL;
@@ -3017,8 +3200,43 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
if (err)
goto err_delete_thread;
- /* before aux records are queued, need to map metadata to trace IDs */
- err = cs_etm__map_trace_ids_metadata(num_cpu, metadata);
+ /*
+ * Map Trace ID values to CPU metadata.
+ *
+ * Trace metadata will always contain Trace ID values from the legacy algorithm. If the
+ * files has been recorded by a "new" perf updated to handle AUX_HW_ID then the metadata
+ * ID value will also have the CORESIGHT_TRACE_ID_UNUSED_FLAG set.
+ *
+ * The updated kernel drivers that use AUX_HW_ID to sent Trace IDs will attempt to use
+ * the same IDs as the old algorithm as far as is possible, unless there are clashes
+ * in which case a different value will be used. This means an older perf may still
+ * be able to record and read files generate on a newer system.
+ *
+ * For a perf able to interpret AUX_HW_ID packets we first check for the presence of
+ * those packets. If they are there then the values will be mapped and plugged into
+ * the metadata. We then set any remaining metadata values with the used flag to a
+ * value CORESIGHT_TRACE_ID_UNUSED_VAL - which indicates no decoder is required.
+ *
+ * If no AUX_HW_ID packets are present - which means a file recorded on an old kernel
+ * then we map Trace ID values to CPU directly from the metadata - clearing any unused
+ * flags if present.
+ */
+
+ /* first scan for AUX_OUTPUT_HW_ID records to map trace ID values to CPU metadata */
+ aux_hw_id_found = 0;
+ err = perf_session__peek_events(session, session->header.data_offset,
+ session->header.data_size,
+ cs_etm__process_aux_hw_id_cb, &aux_hw_id_found);
+ if (err)
+ goto err_delete_thread;
+
+ /* if HW ID found then clear any unused metadata ID values */
+ if (aux_hw_id_found)
+ err = cs_etm__clear_unused_trace_ids_metadata(num_cpu, metadata);
+ /* otherwise, this is a file with metadata values only, map from metadata */
+ else
+ err = cs_etm__map_trace_ids_metadata(num_cpu, metadata);
+
if (err)
goto err_delete_thread;
@@ -3027,14 +3245,6 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
goto err_delete_thread;
etm->data_queued = etm->queues.populated;
- /*
- * Print warning in pipe mode, see cs_etm__process_auxtrace_event() and
- * cs_etm__queue_aux_fragment() for details relating to limitations.
- */
- if (!etm->data_queued)
- pr_warning("CS ETM warning: Coresight decode and TRBE support requires random file access.\n"
- "Continuing with best effort decoding in piped mode.\n\n");
-
return 0;
err_delete_thread:
--
2.17.1
^ permalink raw reply related [flat|nested] 5+ messages in thread* Re: [PATCH v9 0/3] perf: cs-etm: Update perf to handle new Coresight Trace ID
2023-03-31 5:56 [PATCH v9 0/3] perf: cs-etm: Update perf to handle new Coresight Trace ID Mike Leach
` (2 preceding siblings ...)
2023-03-31 5:56 ` [PATCH v9 3/3] perf: cs-etm: Handle PERF_RECORD_AUX_OUTPUT_HW_ID packet Mike Leach
@ 2023-03-31 11:51 ` Arnaldo Carvalho de Melo
3 siblings, 0 replies; 5+ messages in thread
From: Arnaldo Carvalho de Melo @ 2023-03-31 11:51 UTC (permalink / raw)
To: Mike Leach
Cc: linux-perf-users, linux-arm-kernel, coresight, linux-kernel,
suzuki.poulose, leo.yan, peterz, mingo, will, mark.rutland,
alexander.shishkin, jolsa, namhyung, gankulkarni, darren
Em Fri, Mar 31, 2023 at 06:56:42AM +0100, Mike Leach escreveu:
> The original method for allocating trace source ID values to sources was
> to use a fixed algorithm for CPU based sources of (cpu_num * 2 + 0x10).
> The STM was allocated ID 0x1.
>
> This mechanism is broken for systems with more than 47 cores.
>
> The kernel related patches the provide a fixed Trace ID allocation mechanism
> are now upstreamed.
>
> This patchset updates the perf code to handle the changes to the trace ID
> notification mechanism that now uses the PERF_RECORD_AUX_OUTPUT_HW_ID
> packet to set Trace ID in the perf ETM decoders.
>
> Applies and test oo perf/core
I'm keeping perf/core with the same contents as perf-tools-next, please
use perf-tools-next as in the future I'll stop using the old perf/core
name.
Applied, testing.
- Arnaldo
> Changes since v8:
> 1. Fix build issues
> 2. Fix implicit function problem
>
> Changes since v7:
> Split from original patchset [1] to be sent separately as kernel related
> patches are now upstream.
>
> [1] https://lore.kernel.org/linux-arm-kernel/20230116124928.5440-1-mike.leach@linaro.org/
>
> Mike Leach (3):
> perf: cs-etm: Move mapping of Trace ID and cpu into helper function
> perf: cs-etm: Update record event to use new Trace ID protocol
> perf: cs-etm: Handle PERF_RECORD_AUX_OUTPUT_HW_ID packet
>
> tools/include/linux/coresight-pmu.h | 47 ++-
> tools/perf/arch/arm/util/cs-etm.c | 27 +-
> tools/perf/util/cs-etm-base.c | 3 +-
> .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 7 +
> tools/perf/util/cs-etm.c | 326 +++++++++++++++---
> tools/perf/util/cs-etm.h | 14 +-
> 6 files changed, 356 insertions(+), 68 deletions(-)
>
> --
> 2.17.1
>
--
- Arnaldo
^ permalink raw reply [flat|nested] 5+ messages in thread