1 files changed, 43 insertions, 7 deletions

diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index fa50645fedda..4801115f2b54 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -87,6 +87,7 @@ struct arm_spe_pmu {
 #define SPE_PMU_FEAT_INV_FILT_EVT		(1UL << 6)
 #define SPE_PMU_FEAT_DISCARD			(1UL << 7)
 #define SPE_PMU_FEAT_EFT			(1UL << 8)
+#define SPE_PMU_FEAT_FDS			(1UL << 9)
 #define SPE_PMU_FEAT_DEV_PROBED			(1UL << 63)
 	u64					features;
 
@@ -252,6 +253,10 @@ static const struct attribute_group arm_spe_pmu_cap_group = {
 #define ATTR_CFG_FLD_inv_event_filter_LO	0
 #define ATTR_CFG_FLD_inv_event_filter_HI	63
 
+#define ATTR_CFG_FLD_inv_data_src_filter_CFG	config4	/* inverse of PMSDSFR_EL1 */
+#define ATTR_CFG_FLD_inv_data_src_filter_LO	0
+#define ATTR_CFG_FLD_inv_data_src_filter_HI	63
+
 GEN_PMU_FORMAT_ATTR(ts_enable);
 GEN_PMU_FORMAT_ATTR(pa_enable);
 GEN_PMU_FORMAT_ATTR(pct_enable);
@@ -268,6 +273,7 @@ GEN_PMU_FORMAT_ATTR(float_filter);
 GEN_PMU_FORMAT_ATTR(float_filter_mask);
 GEN_PMU_FORMAT_ATTR(event_filter);
 GEN_PMU_FORMAT_ATTR(inv_event_filter);
+GEN_PMU_FORMAT_ATTR(inv_data_src_filter);
 GEN_PMU_FORMAT_ATTR(min_latency);
 GEN_PMU_FORMAT_ATTR(discard);
 
@@ -288,6 +294,7 @@ static struct attribute *arm_spe_pmu_formats_attr[] = {
 	&format_attr_float_filter_mask.attr,
 	&format_attr_event_filter.attr,
 	&format_attr_inv_event_filter.attr,
+	&format_attr_inv_data_src_filter.attr,
 	&format_attr_min_latency.attr,
 	&format_attr_discard.attr,
 	NULL,
@@ -306,6 +313,10 @@ static umode_t arm_spe_pmu_format_attr_is_visible(struct kobject *kobj,
 	if (attr == &format_attr_inv_event_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT))
 		return 0;
 
+	if (attr == &format_attr_inv_data_src_filter.attr &&
+	    !(spe_pmu->features & SPE_PMU_FEAT_FDS))
+		return 0;
+
 	if ((attr == &format_attr_branch_filter_mask.attr ||
 	     attr == &format_attr_load_filter_mask.attr ||
 	     attr == &format_attr_store_filter_mask.attr ||
@@ -430,6 +441,9 @@ static u64 arm_spe_event_to_pmsfcr(struct perf_event *event)
 	if (ATTR_CFG_GET_FLD(attr, inv_event_filter))
 		reg |= PMSFCR_EL1_FnE;
 
+	if (ATTR_CFG_GET_FLD(attr, inv_data_src_filter))
+		reg |= PMSFCR_EL1_FDS;
+
 	if (ATTR_CFG_GET_FLD(attr, min_latency))
 		reg |= PMSFCR_EL1_FL;
 
@@ -454,6 +468,17 @@ static u64 arm_spe_event_to_pmslatfr(struct perf_event *event)
 	return FIELD_PREP(PMSLATFR_EL1_MINLAT, ATTR_CFG_GET_FLD(attr, min_latency));
 }
 
+static u64 arm_spe_event_to_pmsdsfr(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+
+	/*
+	 * Data src filter is inverted so that the default value of 0 is
+	 * equivalent to no filtering.
+	 */
+	return ~ATTR_CFG_GET_FLD(attr, inv_data_src_filter);
+}
+
 static void arm_spe_pmu_pad_buf(struct perf_output_handle *handle, int len)
 {
 	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
@@ -791,6 +816,10 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
 	if (arm_spe_event_to_pmsnevfr(event) & spe_pmu->pmsevfr_res0)
 		return -EOPNOTSUPP;
 
+	if (arm_spe_event_to_pmsdsfr(event) != U64_MAX &&
+	    !(spe_pmu->features & SPE_PMU_FEAT_FDS))
+		return -EOPNOTSUPP;
+
 	if (attr->exclude_idle)
 		return -EOPNOTSUPP;
 
@@ -866,6 +895,11 @@ static void arm_spe_pmu_start(struct perf_event *event, int flags)
 		write_sysreg_s(reg, SYS_PMSNEVFR_EL1);
 	}
 
+	if (spe_pmu->features & SPE_PMU_FEAT_FDS) {
+		reg = arm_spe_event_to_pmsdsfr(event);
+		write_sysreg_s(reg, SYS_PMSDSFR_EL1);
+	}
+
 	reg = arm_spe_event_to_pmslatfr(event);
 	write_sysreg_s(reg, SYS_PMSLATFR_EL1);
 
@@ -1125,6 +1159,9 @@ static void __arm_spe_pmu_dev_probe(void *info)
 	if (FIELD_GET(PMSIDR_EL1_EFT, reg))
 		spe_pmu->features |= SPE_PMU_FEAT_EFT;
 
+	if (FIELD_GET(PMSIDR_EL1_FDS, reg))
+		spe_pmu->features |= SPE_PMU_FEAT_FDS;
+
 	/* This field has a spaced out encoding, so just use a look-up */
 	fld = FIELD_GET(PMSIDR_EL1_INTERVAL, reg);
 	switch (fld) {
@@ -1259,8 +1296,8 @@ static int arm_spe_pmu_dev_init(struct arm_spe_pmu *spe_pmu)
 		return -ENXIO;
 
 	/* Request our PPIs (note that the IRQ is still disabled) */
-	ret = request_percpu_irq(spe_pmu->irq, arm_spe_pmu_irq_handler, DRVNAME,
-				 spe_pmu->handle);
+	ret = request_percpu_irq_affinity(spe_pmu->irq, arm_spe_pmu_irq_handler,
+					  DRVNAME, mask, spe_pmu->handle);
 	if (ret)
 		return ret;
 
@@ -1287,8 +1324,10 @@ static void arm_spe_pmu_dev_teardown(struct arm_spe_pmu *spe_pmu)
 static int arm_spe_pmu_irq_probe(struct arm_spe_pmu *spe_pmu)
 {
 	struct platform_device *pdev = spe_pmu->pdev;
-	int irq = platform_get_irq(pdev, 0);
+	const struct cpumask *affinity;
+	int irq;
 
+	irq = platform_get_irq_affinity(pdev, 0, &affinity);
 	if (irq < 0)
 		return -ENXIO;
 
@@ -1297,10 +1336,7 @@ static int arm_spe_pmu_irq_probe(struct arm_spe_pmu *spe_pmu)
 		return -EINVAL;
 	}
 
-	if (irq_get_percpu_devid_partition(irq, &spe_pmu->supported_cpus)) {
-		dev_err(&pdev->dev, "failed to get PPI partition (%d)\n", irq);
-		return -EINVAL;
-	}
+	cpumask_copy(&spe_pmu->supported_cpus, affinity);
 
 	spe_pmu->irq = irq;
 	return 0;