[PATCH v10 6/7] perf: cavium: Support transmit-link PMU counters

From: Jan Glauber
Date: Mon Sep 25 2017 - 08:35:43 EST

Add support for the transmit-link (OCX TLK) PMU counters found
on Caviums SOCs with a processor interconnect.

Properties of the OCX TLK counters:
- per-unit control
- fixed purpose
- writable
- one PCI device with multiple TLK units

Signed-off-by: Jan Glauber <jglauber@xxxxxxxxxx>
---
drivers/perf/Kconfig | 7 ++
drivers/perf/cavium_pmu.c | 230 ++++++++++++++++++++++++++++++++++++++++
drivers/soc/cavium/Kconfig | 4 +
drivers/soc/cavium/cavium_ocx.c | 4 +
include/linux/soc/cavium/ocx.h | 3 +
5 files changed, 248 insertions(+)

diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index a787562c5432..efb2ace649c1 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -51,4 +51,11 @@ config CAVIUM_PMU_LMC
Provides PMU counters for the memory controller on
Cavium ThunderX or OcteonTX SOCs.

+config CAVIUM_PMU_OCX_TLK
+ tristate "Cavium ThunderX interconnect PMU"
+ depends on ARCH_THUNDER && m
+ select CAVIUM_OCX
+ help
+ Provides PMU counters for the processor interconnect on
+ Cavium ThunderX processors.
endmenu
diff --git a/drivers/perf/cavium_pmu.c b/drivers/perf/cavium_pmu.c
index 45d1766db474..1a112b0aeaa6 100644
--- a/drivers/perf/cavium_pmu.c
+++ b/drivers/perf/cavium_pmu.c
@@ -20,9 +20,11 @@
#include <linux/perf_event.h>
#include <linux/slab.h>
#include <linux/soc/cavium/lmc.h>
+#include <linux/soc/cavium/ocx.h>

enum cvm_pmu_type {
CVM_PMU_LMC,
+ CVM_PMU_TLK,
};

/* maximum number of parallel hardware counters for all pmu types */
@@ -407,6 +409,234 @@ void cvm_lmc_pmu_remove(struct pci_dev *pdev)
}
EXPORT_SYMBOL_GPL(cvm_lmc_pmu_remove);

+/*
+ * CCPI interface controller (OCX) Transmit link (TLK) counters:
+ * - per-unit control
+ * - writable
+ * - one PCI device with multiple TLK units
+ */
+
+#define TLK_NR_UNITS 3
+#define TLK_UNIT_OFFSET 0x2000
+#define TLK_UNIT_LEN 0x7ff
+#define TLK_START_ADDR 0x10000
+#define TLK_STAT_CTL_OFFSET 0x40
+#define TLK_STAT_OFFSET 0x400
+
+#define TLK_STAT_ENABLE_BIT BIT(0)
+#define TLK_STAT_RESET_BIT BIT(1)
+
+#define CVM_PMU_TLK_EVENT_ATTR(_name, _id) \
+ &((struct perf_pmu_events_attr[]) { \
+ { \
+ __ATTR(_name, S_IRUGO, cvm_pmu_event_sysfs_show, NULL), \
+ _id, \
+ "tlk_event=" __stringify(_id), \
+ } \
+ })[0].attr.attr
+
+static void cvm_pmu_tlk_enable_pmu(struct pmu *pmu)
+{
+ struct cvm_pmu_dev *pmu_dev = container_of(pmu, struct cvm_pmu_dev, pmu);
+
+ /* enable all counters */
+ writeb(TLK_STAT_ENABLE_BIT, pmu_dev->map + TLK_STAT_CTL_OFFSET);
+}
+
+static void cvm_pmu_tlk_disable_pmu(struct pmu *pmu)
+{
+ struct cvm_pmu_dev *pmu_dev = container_of(pmu, struct cvm_pmu_dev, pmu);
+
+ /* disable all counters */
+ writeb(0, pmu_dev->map + TLK_STAT_CTL_OFFSET);
+}
+
+static int cvm_pmu_tlk_add(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ return cvm_pmu_add(event, flags, TLK_STAT_OFFSET + hwc->config * 8);
+}
+
+PMU_FORMAT_ATTR(tlk_event, "config:0-5");
+
+static struct attribute *cvm_pmu_tlk_format_attr[] = {
+ &format_attr_tlk_event.attr,
+ NULL,
+};
+
+static struct attribute_group cvm_pmu_tlk_format_group = {
+ .name = "format",
+ .attrs = cvm_pmu_tlk_format_attr,
+};
+
+static struct attribute *cvm_pmu_tlk_events_attr[] = {
+ CVM_PMU_TLK_EVENT_ATTR(idle_cnt, 0x00),
+ CVM_PMU_TLK_EVENT_ATTR(data_cnt, 0x01),
+ CVM_PMU_TLK_EVENT_ATTR(sync_cnt, 0x02),
+ CVM_PMU_TLK_EVENT_ATTR(retry_cnt, 0x03),
+ CVM_PMU_TLK_EVENT_ATTR(err_cnt, 0x04),
+ CVM_PMU_TLK_EVENT_ATTR(mat0_cnt, 0x08),
+ CVM_PMU_TLK_EVENT_ATTR(mat1_cnt, 0x09),
+ CVM_PMU_TLK_EVENT_ATTR(mat2_cnt, 0x0a),
+ CVM_PMU_TLK_EVENT_ATTR(mat3_cnt, 0x0b),
+ CVM_PMU_TLK_EVENT_ATTR(vc0_cmd, 0x10),
+ CVM_PMU_TLK_EVENT_ATTR(vc1_cmd, 0x11),
+ CVM_PMU_TLK_EVENT_ATTR(vc2_cmd, 0x12),
+ CVM_PMU_TLK_EVENT_ATTR(vc3_cmd, 0x13),
+ CVM_PMU_TLK_EVENT_ATTR(vc4_cmd, 0x14),
+ CVM_PMU_TLK_EVENT_ATTR(vc5_cmd, 0x15),
+ CVM_PMU_TLK_EVENT_ATTR(vc0_pkt, 0x20),
+ CVM_PMU_TLK_EVENT_ATTR(vc1_pkt, 0x21),
+ CVM_PMU_TLK_EVENT_ATTR(vc2_pkt, 0x22),
+ CVM_PMU_TLK_EVENT_ATTR(vc3_pkt, 0x23),
+ CVM_PMU_TLK_EVENT_ATTR(vc4_pkt, 0x24),
+ CVM_PMU_TLK_EVENT_ATTR(vc5_pkt, 0x25),
+ CVM_PMU_TLK_EVENT_ATTR(vc6_pkt, 0x26),
+ CVM_PMU_TLK_EVENT_ATTR(vc7_pkt, 0x27),
+ CVM_PMU_TLK_EVENT_ATTR(vc8_pkt, 0x28),
+ CVM_PMU_TLK_EVENT_ATTR(vc9_pkt, 0x29),
+ CVM_PMU_TLK_EVENT_ATTR(vc10_pkt, 0x2a),
+ CVM_PMU_TLK_EVENT_ATTR(vc11_pkt, 0x2b),
+ CVM_PMU_TLK_EVENT_ATTR(vc12_pkt, 0x2c),
+ CVM_PMU_TLK_EVENT_ATTR(vc13_pkt, 0x2d),
+ CVM_PMU_TLK_EVENT_ATTR(vc0_con, 0x30),
+ CVM_PMU_TLK_EVENT_ATTR(vc1_con, 0x31),
+ CVM_PMU_TLK_EVENT_ATTR(vc2_con, 0x32),
+ CVM_PMU_TLK_EVENT_ATTR(vc3_con, 0x33),
+ CVM_PMU_TLK_EVENT_ATTR(vc4_con, 0x34),
+ CVM_PMU_TLK_EVENT_ATTR(vc5_con, 0x35),
+ CVM_PMU_TLK_EVENT_ATTR(vc6_con, 0x36),
+ CVM_PMU_TLK_EVENT_ATTR(vc7_con, 0x37),
+ CVM_PMU_TLK_EVENT_ATTR(vc8_con, 0x38),
+ CVM_PMU_TLK_EVENT_ATTR(vc9_con, 0x39),
+ CVM_PMU_TLK_EVENT_ATTR(vc10_con, 0x3a),
+ CVM_PMU_TLK_EVENT_ATTR(vc11_con, 0x3b),
+ CVM_PMU_TLK_EVENT_ATTR(vc12_con, 0x3c),
+ CVM_PMU_TLK_EVENT_ATTR(vc13_con, 0x3d),
+ NULL,
+};
+
+static struct attribute_group cvm_pmu_tlk_events_group = {
+ .name = "events",
+ .attrs = cvm_pmu_tlk_events_attr,
+};
+
+static const struct attribute_group *cvm_pmu_tlk_attr_groups[] = {
+ &cvm_pmu_attr_group,
+ &cvm_pmu_tlk_format_group,
+ &cvm_pmu_tlk_events_group,
+ NULL,
+};
+
+static bool cvm_pmu_tlk_event_valid(u64 config)
+{
+ struct perf_pmu_events_attr *attr;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(cvm_pmu_tlk_events_attr) - 1; i++) {
+ attr = (struct perf_pmu_events_attr *)cvm_pmu_tlk_events_attr[i];
+ if (attr->id == config)
+ return true;
+ }
+ return false;
+}
+
+static int cvm_pmu_tlk_probe_unit(struct pci_dev *pdev, int nr)
+{
+ struct cvm_pmu_dev *tlk;
+ int ret = -ENOMEM;
+ char *name;
+
+ tlk = devm_kzalloc(&pdev->dev, sizeof(*tlk), GFP_KERNEL);
+ if (!tlk)
+ return -ENOMEM;
+
+ tlk->map = devm_ioremap(&pdev->dev,
+ pci_resource_start(pdev, 0) + TLK_START_ADDR +
+ nr * TLK_UNIT_OFFSET, TLK_UNIT_LEN);
+ if (!tlk->map)
+ return -EINVAL;
+
+ name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "ocx_tlk%d", nr);
+ if (!name)
+ return -ENOMEM;
+
+ tlk->pdev = pdev;
+ tlk->num_counters = ARRAY_SIZE(cvm_pmu_tlk_events_attr) - 1;
+ tlk->pmu = (struct pmu) {
+ .task_ctx_nr = perf_invalid_context,
+ .name = name,
+ .pmu_enable = cvm_pmu_tlk_enable_pmu,
+ .pmu_disable = cvm_pmu_tlk_disable_pmu,
+ .event_init = cvm_pmu_event_init,
+ .add = cvm_pmu_tlk_add,
+ .del = cvm_pmu_del,
+ .start = cvm_pmu_start,
+ .stop = cvm_pmu_stop,
+ .read = cvm_pmu_read,
+ .attr_groups = cvm_pmu_tlk_attr_groups,
+ };
+
+ cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CVM_ONLINE,
+ &tlk->cpuhp_node);
+
+ /*
+ * perf PMU is CPU dependent so pick a random CPU and migrate away
+ * if it goes offline.
+ */
+ cpumask_set_cpu(smp_processor_id(), &tlk->active_mask);
+
+ list_add(&tlk->entry, &cvm_pmu_tlks);
+ tlk->event_valid = cvm_pmu_tlk_event_valid;
+
+ ret = perf_pmu_register(&tlk->pmu, name, -1);
+ if (ret)
+ goto fail_pmu;
+
+ dev_info(&pdev->dev, "Enabled %s PMU with %d counters\n",
+ name, tlk->num_counters);
+ return 0;
+
+fail_pmu:
+ list_del(&tlk->entry);
+ cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_CVM_ONLINE,
+ &tlk->cpuhp_node);
+ return ret;
+}
+
+int cvm_ocx_tlk_pmu_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+ int rc, i;
+
+ for (i = 0; i < TLK_NR_UNITS; i++) {
+ rc = cvm_pmu_tlk_probe_unit(pdev, i);
+ if (rc)
+ return rc;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cvm_ocx_tlk_pmu_probe);
+
+void cvm_ocx_tlk_pmu_remove(struct pci_dev *pdev)
+{
+ struct list_head *l, *tmp;
+ struct cvm_pmu_dev *tlk;
+
+ list_for_each_safe(l, tmp, &cvm_pmu_tlks) {
+ tlk = list_entry(l, struct cvm_pmu_dev, entry);
+
+ if (pdev != tlk->pdev)
+ continue;
+
+ perf_pmu_unregister(&tlk->pmu);
+ cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_CVM_ONLINE,
+ &tlk->cpuhp_node);
+ list_del(&tlk->entry);
+ }
+}
+EXPORT_SYMBOL_GPL(cvm_ocx_tlk_pmu_remove);
+
static int __init cvm_pmu_init(void)
{
INIT_LIST_HEAD(&cvm_pmu_lmcs);
diff --git a/drivers/soc/cavium/Kconfig b/drivers/soc/cavium/Kconfig
index fe56503d20f4..2c7406872b18 100644
--- a/drivers/soc/cavium/Kconfig
+++ b/drivers/soc/cavium/Kconfig
@@ -8,3 +8,7 @@ config CAVIUM_LMC
config CAVIUM_OCX
depends on ARCH_THUNDER
def_tristate m
+
+config CAVIUM_OCX
+ depends on ARCH_THUNDER
+ def_tristate m
diff --git a/drivers/soc/cavium/cavium_ocx.c b/drivers/soc/cavium/cavium_ocx.c
index fa3341b0744f..de1ad146c0dd 100644
--- a/drivers/soc/cavium/cavium_ocx.c
+++ b/drivers/soc/cavium/cavium_ocx.c
@@ -13,6 +13,8 @@
static int cvm_ocx_probe(struct pci_dev *pdev,
const struct pci_device_id *ent)
{
+ if (IS_ENABLED(CONFIG_CAVIUM_PMU_OCX_TLK))
+ cvm_ocx_tlk_pmu_probe(pdev, ent);
if (IS_ENABLED(CONFIG_EDAC_THUNDERX))
thunderx_edac_ocx_probe(pdev, ent);
return 0;
@@ -20,6 +22,8 @@ static int cvm_ocx_probe(struct pci_dev *pdev,

static void cvm_ocx_remove(struct pci_dev *pdev)
{
+ if (IS_ENABLED(CONFIG_CAVIUM_PMU_OCX_TLK))
+ cvm_ocx_tlk_pmu_remove(pdev);
if (IS_ENABLED(CONFIG_EDAC_THUNDERX))
thunderx_edac_ocx_remove(pdev);
}
diff --git a/include/linux/soc/cavium/ocx.h b/include/linux/soc/cavium/ocx.h
index 29f55b3d3171..f7b2caada671 100644
--- a/include/linux/soc/cavium/ocx.h
+++ b/include/linux/soc/cavium/ocx.h
@@ -3,6 +3,9 @@

#include <linux/pci.h>

+int cvm_ocx_tlk_pmu_probe(struct pci_dev *pdev, const struct pci_device_id *ent);
+void cvm_ocx_tlk_pmu_remove(struct pci_dev *pdev);
+
int thunderx_edac_ocx_probe(struct pci_dev *pdev, const struct pci_device_id *ent);
void thunderx_edac_ocx_remove(struct pci_dev *pdev);

--
2.9.0.rc0.21.g7777322