perf/x86/intel/uncore: Expose an Uncore unit to IIO PMON mapping

Current version supports a server line starting Intel® Xeon® Processor
Scalable Family and introduces mapping for IIO Uncore units only.
Other units can be added on demand.

IIO stack to PMON mapping is exposed through:
    /sys/devices/uncore_iio_<pmu_idx>/dieX
    where dieX is file which holds "Segment:Root Bus" for PCIe root port,
    which can be monitored by that IIO PMON block.

Details are explained in Documentation/ABI/testing/sysfs-devices-mapping

Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Alexander Antonov <alexander.antonov@linux.intel.com>
Signed-off-by: Roman Sudarikov <roman.sudarikov@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lkml.kernel.org/r/20200601083543.30011-4-alexander.antonov@linux.intel.com

2 files changed, 200 insertions, 0 deletions

diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 594a2fe20de9..105fdc69825e 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -182,6 +182,15 @@ int uncore_pcibus_to_physid(struct pci_bus *bus);
 ssize_t uncore_event_show(struct kobject *kobj,
 			  struct kobj_attribute *attr, char *buf);
 
+static inline struct intel_uncore_pmu *dev_to_uncore_pmu(struct device *dev)
+{
+	return container_of(dev_get_drvdata(dev), struct intel_uncore_pmu, pmu);
+}
+
+#define to_device_attribute(n)	container_of(n, struct device_attribute, attr)
+#define to_dev_ext_attribute(n)	container_of(n, struct dev_ext_attribute, attr)
+#define attr_to_ext_attr(n)	to_dev_ext_attribute(to_device_attribute(n))
+
 extern int __uncore_max_dies;
 #define uncore_max_dies()	(__uncore_max_dies)
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 045c2d2231d2..62e88ad919ff 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -273,6 +273,30 @@
 #define SKX_CPUNODEID			0xc0
 #define SKX_GIDNIDMAP			0xd4
 
+/*
+ * The CPU_BUS_NUMBER MSR returns the values of the respective CPUBUSNO CSR
+ * that BIOS programmed. MSR has package scope.
+ * |  Bit  |  Default  |  Description
+ * | [63]  |    00h    | VALID - When set, indicates the CPU bus
+ *                       numbers have been initialized. (RO)
+ * |[62:48]|    ---    | Reserved
+ * |[47:40]|    00h    | BUS_NUM_5 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(5). (RO)
+ * |[39:32]|    00h    | BUS_NUM_4 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(4). (RO)
+ * |[31:24]|    00h    | BUS_NUM_3 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(3). (RO)
+ * |[23:16]|    00h    | BUS_NUM_2 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(2). (RO)
+ * |[15:8] |    00h    | BUS_NUM_1 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(1). (RO)
+ * | [7:0] |    00h    | BUS_NUM_0 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(0). (RO)
+ */
+#define SKX_MSR_CPU_BUS_NUMBER		0x300
+#define SKX_MSR_CPU_BUS_VALID_BIT	(1ULL << 63)
+#define BUS_NUM_STRIDE			8
+
 /* SKX CHA */
 #define SKX_CHA_MSR_PMON_BOX_FILTER_TID		(0x1ffULL << 0)
 #define SKX_CHA_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 9)
@@ -3612,6 +3636,170 @@ static struct intel_uncore_ops skx_uncore_iio_ops = {
 	.read_counter		= uncore_msr_read_counter,
 };
 
+static inline u8 skx_iio_stack(struct intel_uncore_pmu *pmu, int die)
+{
+	return pmu->type->topology[die] >> (pmu->pmu_idx * BUS_NUM_STRIDE);
+}
+
+static umode_t
+skx_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, int die)
+{
+	struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(kobj_to_dev(kobj));
+
+	/* Root bus 0x00 is valid only for die 0 AND pmu_idx = 0. */
+	return (!skx_iio_stack(pmu, die) && pmu->pmu_idx) ? 0 : attr->mode;
+}
+
+static ssize_t skx_iio_mapping_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct pci_bus *bus = pci_find_next_bus(NULL);
+	struct intel_uncore_pmu *uncore_pmu = dev_to_uncore_pmu(dev);
+	struct dev_ext_attribute *ea = to_dev_ext_attribute(attr);
+	long die = (long)ea->var;
+
+	/*
+	 * Current implementation is for single segment configuration hence it's
+	 * safe to take the segment value from the first available root bus.
+	 */
+	return sprintf(buf, "%04x:%02x\n", pci_domain_nr(bus),
+					   skx_iio_stack(uncore_pmu, die));
+}
+
+static int skx_msr_cpu_bus_read(int cpu, u64 *topology)
+{
+	u64 msr_value;
+
+	if (rdmsrl_on_cpu(cpu, SKX_MSR_CPU_BUS_NUMBER, &msr_value) ||
+			!(msr_value & SKX_MSR_CPU_BUS_VALID_BIT))
+		return -ENXIO;
+
+	*topology = msr_value;
+
+	return 0;
+}
+
+static int die_to_cpu(int die)
+{
+	int res = 0, cpu, current_die;
+	/*
+	 * Using cpus_read_lock() to ensure cpu is not going down between
+	 * looking at cpu_online_mask.
+	 */
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		current_die = topology_logical_die_id(cpu);
+		if (current_die == die) {
+			res = cpu;
+			break;
+		}
+	}
+	cpus_read_unlock();
+	return res;
+}
+
+static int skx_iio_get_topology(struct intel_uncore_type *type)
+{
+	int i, ret;
+	struct pci_bus *bus = NULL;
+
+	/*
+	 * Verified single-segment environments only; disabled for multiple
+	 * segment topologies for now except VMD domains.
+	 * VMD domains start at 0x10000 to not clash with ACPI _SEG domains.
+	 */
+	while ((bus = pci_find_next_bus(bus))
+		&& (!pci_domain_nr(bus) || pci_domain_nr(bus) > 0xffff))
+		;
+	if (bus)
+		return -EPERM;
+
+	type->topology = kcalloc(uncore_max_dies(), sizeof(u64), GFP_KERNEL);
+	if (!type->topology)
+		return -ENOMEM;
+
+	for (i = 0; i < uncore_max_dies(); i++) {
+		ret = skx_msr_cpu_bus_read(die_to_cpu(i), &type->topology[i]);
+		if (ret) {
+			kfree(type->topology);
+			type->topology = NULL;
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static struct attribute_group skx_iio_mapping_group = {
+	.is_visible	= skx_iio_mapping_visible,
+};
+
+static const struct attribute_group *skx_iio_attr_update[] = {
+	&skx_iio_mapping_group,
+	NULL,
+};
+
+static int skx_iio_set_mapping(struct intel_uncore_type *type)
+{
+	char buf[64];
+	int ret;
+	long die = -1;
+	struct attribute **attrs = NULL;
+	struct dev_ext_attribute *eas = NULL;
+
+	ret = skx_iio_get_topology(type);
+	if (ret)
+		return ret;
+
+	/* One more for NULL. */
+	attrs = kcalloc((uncore_max_dies() + 1), sizeof(*attrs), GFP_KERNEL);
+	if (!attrs)
+		goto err;
+
+	eas = kcalloc(uncore_max_dies(), sizeof(*eas), GFP_KERNEL);
+	if (!eas)
+		goto err;
+
+	for (die = 0; die < uncore_max_dies(); die++) {
+		sprintf(buf, "die%ld", die);
+		sysfs_attr_init(&eas[die].attr.attr);
+		eas[die].attr.attr.name = kstrdup(buf, GFP_KERNEL);
+		if (!eas[die].attr.attr.name)
+			goto err;
+		eas[die].attr.attr.mode = 0444;
+		eas[die].attr.show = skx_iio_mapping_show;
+		eas[die].attr.store = NULL;
+		eas[die].var = (void *)die;
+		attrs[die] = &eas[die].attr.attr;
+	}
+	skx_iio_mapping_group.attrs = attrs;
+
+	return 0;
+err:
+	for (; die >= 0; die--)
+		kfree(eas[die].attr.attr.name);
+	kfree(eas);
+	kfree(attrs);
+	kfree(type->topology);
+	type->attr_update = NULL;
+	return -ENOMEM;
+}
+
+static void skx_iio_cleanup_mapping(struct intel_uncore_type *type)
+{
+	struct attribute **attr = skx_iio_mapping_group.attrs;
+
+	if (!attr)
+		return;
+
+	for (; *attr; attr++)
+		kfree((*attr)->name);
+	kfree(attr_to_ext_attr(*skx_iio_mapping_group.attrs));
+	kfree(skx_iio_mapping_group.attrs);
+	skx_iio_mapping_group.attrs = NULL;
+	kfree(type->topology);
+}
+
 static struct intel_uncore_type skx_uncore_iio = {
 	.name			= "iio",
 	.num_counters		= 4,
@@ -3626,6 +3814,9 @@ static struct intel_uncore_type skx_uncore_iio = {
 	.constraints		= skx_uncore_iio_constraints,
 	.ops			= &skx_uncore_iio_ops,
 	.format_group		= &skx_uncore_iio_format_group,
+	.attr_update		= skx_iio_attr_update,
+	.set_mapping		= skx_iio_set_mapping,
+	.cleanup_mapping	= skx_iio_cleanup_mapping,
 };
 
 enum perf_uncore_iio_freerunning_type_id {