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 The 'cpu * 2 + seed' was outdated and broken for systems with high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 | 30 +++++++++++++++++------------
tools/perf/arch/arm/util/cs-etm.c | 21 ++++++++++++--------
2 files changed, 31 insertions(+), 20 deletions(-)
@@ -10,11 +10,28 @@
#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 This has been replaced by drivers using a dynamic allocation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 e.g. simpleperf in Android, 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 +56,4 @@
#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
@@ -421,13 +421,16 @@ 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)
@@ -633,8 +636,10 @@ 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]);
@@ -681,9 +686,9 @@ 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,