[PATCH v3 1/5] perf: arm_spe: Add format option for discard mode

[James Clark <james.clark@xxxxxxxxxx>]

FEAT_SPEv1p2 (optional from Armv8.6) adds a discard mode that allows all
SPE data to be discarded rather than written to memory. Add a format
bit for this mode.

If the mode isn't supported, the format bit isn't published and attempts
to use it will result in -EOPNOTSUPP. Allocating an aux buffer is still
allowed even though it won't be written to so that old tools continue to
work, but updated tools can choose to skip this step.

Signed-off-by: James Clark <james.clark@xxxxxxxxxx>
---
 drivers/perf/arm_spe_pmu.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index fd5b78732603..f5e6878db9d6 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -85,6 +85,7 @@ struct arm_spe_pmu {
 #define SPE_PMU_FEAT_LDS			(1UL << 4)
 #define SPE_PMU_FEAT_ERND			(1UL << 5)
 #define SPE_PMU_FEAT_INV_FILT_EVT		(1UL << 6)
+#define SPE_PMU_FEAT_DISCARD			(1UL << 7)
 #define SPE_PMU_FEAT_DEV_PROBED			(1UL << 63)
 	u64					features;
 
@@ -193,6 +194,9 @@ static const struct attribute_group arm_spe_pmu_cap_group = {
 #define ATTR_CFG_FLD_store_filter_CFG		config	/* PMSFCR_EL1.ST */
 #define ATTR_CFG_FLD_store_filter_LO		34
 #define ATTR_CFG_FLD_store_filter_HI		34
+#define ATTR_CFG_FLD_discard_CFG		config	/* PMBLIMITR_EL1.FM = DISCARD */
+#define ATTR_CFG_FLD_discard_LO			35
+#define ATTR_CFG_FLD_discard_HI			35
 
 #define ATTR_CFG_FLD_event_filter_CFG		config1	/* PMSEVFR_EL1 */
 #define ATTR_CFG_FLD_event_filter_LO		0
@@ -216,6 +220,7 @@ GEN_PMU_FORMAT_ATTR(store_filter);
 GEN_PMU_FORMAT_ATTR(event_filter);
 GEN_PMU_FORMAT_ATTR(inv_event_filter);
 GEN_PMU_FORMAT_ATTR(min_latency);
+GEN_PMU_FORMAT_ATTR(discard);
 
 static struct attribute *arm_spe_pmu_formats_attr[] = {
 	&format_attr_ts_enable.attr,
@@ -228,6 +233,7 @@ static struct attribute *arm_spe_pmu_formats_attr[] = {
 	&format_attr_event_filter.attr,
 	&format_attr_inv_event_filter.attr,
 	&format_attr_min_latency.attr,
+	&format_attr_discard.attr,
 	NULL,
 };
 
@@ -238,6 +244,9 @@ static umode_t arm_spe_pmu_format_attr_is_visible(struct kobject *kobj,
 	struct device *dev = kobj_to_dev(kobj);
 	struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);
 
+	if (attr == &format_attr_discard.attr && !(spe_pmu->features & SPE_PMU_FEAT_DISCARD))
+		return 0;
+
 	if (attr == &format_attr_inv_event_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT))
 		return 0;
 
@@ -502,6 +511,12 @@ static void arm_spe_perf_aux_output_begin(struct perf_output_handle *handle,
 	u64 base, limit;
 	struct arm_spe_pmu_buf *buf;
 
+	if (ATTR_CFG_GET_FLD(&event->attr, discard)) {
+		limit = FIELD_PREP(PMBLIMITR_EL1_FM, PMBLIMITR_EL1_FM_DISCARD);
+		limit |= PMBLIMITR_EL1_E;
+		goto out_write_limit;
+	}
+
 	/* Start a new aux session */
 	buf = perf_aux_output_begin(handle, event);
 	if (!buf) {
@@ -743,6 +758,10 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
 	    !(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT))
 		return -EOPNOTSUPP;
 
+	if (ATTR_CFG_GET_FLD(&event->attr, discard) &&
+	    !(spe_pmu->features & SPE_PMU_FEAT_DISCARD))
+		return -EOPNOTSUPP;
+
 	set_spe_event_has_cx(event);
 	reg = arm_spe_event_to_pmscr(event);
 	if (reg & (PMSCR_EL1_PA | PMSCR_EL1_PCT))
@@ -1027,6 +1046,9 @@ static void __arm_spe_pmu_dev_probe(void *info)
 	if (FIELD_GET(PMSIDR_EL1_ERND, reg))
 		spe_pmu->features |= SPE_PMU_FEAT_ERND;
 
+	if (spe_pmu->pmsver >= ID_AA64DFR0_EL1_PMSVer_V1P2)
+		spe_pmu->features |= SPE_PMU_FEAT_DISCARD;
+
 	/* This field has a spaced out encoding, so just use a look-up */
 	fld = FIELD_GET(PMSIDR_EL1_INTERVAL, reg);
 	switch (fld) {
-- 
2.34.1