From 0fab1ba6ad6ba1f76380f92ead95c6e861ef8116 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Fri, 25 Feb 2022 20:00:22 +0530 Subject: [PATCH] drivers/nvdimm: Add perf interface to expose nvdimm performance stats A common interface is added to get performance stats reporting support for nvdimm devices. Added interface defines supported event list, config fields for the event attributes and their corresponding bit values which are exported via sysfs. Interface also added support for pmu register/unregister functions, cpu hotplug feature along with macros for handling events addition via sysfs. It adds attribute groups for format, cpumask and events to the pmu structure. User could use the standard perf tool to access perf events exposed via nvdimm pmu. [Declare pmu functions in nd.h file to resolve implicit-function-declaration warning and make hotplug function static as reported by kernel test robot] Acked-by: Peter Zijlstra (Intel) Tested-by: Nageswara R Sastry Signed-off-by: Kajol Jain Link: https://lore.kernel.org/all/202202241242.zqzGkguy-lkp@intel.com/ Reported-by: kernel test robot Reviewed-by: Madhavan Srinivasan Link: https://lore.kernel.org/r/20220225143024.47947-3-kjain@linux.ibm.com Signed-off-by: Dan Williams --- drivers/nvdimm/Makefile | 1 + drivers/nvdimm/nd_perf.c | 328 +++++++++++++++++++++++++++++++++++++++ include/linux/nd.h | 24 +++ 3 files changed, 353 insertions(+) create mode 100644 drivers/nvdimm/nd_perf.c diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index 29203f3d3069..25dba6095612 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -18,6 +18,7 @@ nd_e820-y := e820.o libnvdimm-y := core.o libnvdimm-y += bus.o libnvdimm-y += dimm_devs.o +libnvdimm-y += nd_perf.o libnvdimm-y += dimm.o libnvdimm-y += region_devs.o libnvdimm-y += region.o diff --git a/drivers/nvdimm/nd_perf.c b/drivers/nvdimm/nd_perf.c new file mode 100644 index 000000000000..314415894acf --- /dev/null +++ b/drivers/nvdimm/nd_perf.c @@ -0,0 +1,328 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * nd_perf.c: NVDIMM Device Performance Monitoring Unit support + * + * Perf interface to expose nvdimm performance stats. + * + * Copyright (C) 2021 IBM Corporation + */ + +#define pr_fmt(fmt) "nvdimm_pmu: " fmt + +#include + +#define EVENT(_name, _code) enum{_name = _code} + +/* + * NVDIMM Events codes. + */ + +/* Controller Reset Count */ +EVENT(CTL_RES_CNT, 0x1); +/* Controller Reset Elapsed Time */ +EVENT(CTL_RES_TM, 0x2); +/* Power-on Seconds */ +EVENT(POWERON_SECS, 0x3); +/* Life Remaining */ +EVENT(MEM_LIFE, 0x4); +/* Critical Resource Utilization */ +EVENT(CRI_RES_UTIL, 0x5); +/* Host Load Count */ +EVENT(HOST_L_CNT, 0x6); +/* Host Store Count */ +EVENT(HOST_S_CNT, 0x7); +/* Host Store Duration */ +EVENT(HOST_S_DUR, 0x8); +/* Host Load Duration */ +EVENT(HOST_L_DUR, 0x9); +/* Media Read Count */ +EVENT(MED_R_CNT, 0xa); +/* Media Write Count */ +EVENT(MED_W_CNT, 0xb); +/* Media Read Duration */ +EVENT(MED_R_DUR, 0xc); +/* Media Write Duration */ +EVENT(MED_W_DUR, 0xd); +/* Cache Read Hit Count */ +EVENT(CACHE_RH_CNT, 0xe); +/* Cache Write Hit Count */ +EVENT(CACHE_WH_CNT, 0xf); +/* Fast Write Count */ +EVENT(FAST_W_CNT, 0x10); + +NVDIMM_EVENT_ATTR(ctl_res_cnt, CTL_RES_CNT); +NVDIMM_EVENT_ATTR(ctl_res_tm, CTL_RES_TM); +NVDIMM_EVENT_ATTR(poweron_secs, POWERON_SECS); +NVDIMM_EVENT_ATTR(mem_life, MEM_LIFE); +NVDIMM_EVENT_ATTR(cri_res_util, CRI_RES_UTIL); +NVDIMM_EVENT_ATTR(host_l_cnt, HOST_L_CNT); +NVDIMM_EVENT_ATTR(host_s_cnt, HOST_S_CNT); +NVDIMM_EVENT_ATTR(host_s_dur, HOST_S_DUR); +NVDIMM_EVENT_ATTR(host_l_dur, HOST_L_DUR); +NVDIMM_EVENT_ATTR(med_r_cnt, MED_R_CNT); +NVDIMM_EVENT_ATTR(med_w_cnt, MED_W_CNT); +NVDIMM_EVENT_ATTR(med_r_dur, MED_R_DUR); +NVDIMM_EVENT_ATTR(med_w_dur, MED_W_DUR); +NVDIMM_EVENT_ATTR(cache_rh_cnt, CACHE_RH_CNT); +NVDIMM_EVENT_ATTR(cache_wh_cnt, CACHE_WH_CNT); +NVDIMM_EVENT_ATTR(fast_w_cnt, FAST_W_CNT); + +static struct attribute *nvdimm_events_attr[] = { + NVDIMM_EVENT_PTR(CTL_RES_CNT), + NVDIMM_EVENT_PTR(CTL_RES_TM), + NVDIMM_EVENT_PTR(POWERON_SECS), + NVDIMM_EVENT_PTR(MEM_LIFE), + NVDIMM_EVENT_PTR(CRI_RES_UTIL), + NVDIMM_EVENT_PTR(HOST_L_CNT), + NVDIMM_EVENT_PTR(HOST_S_CNT), + NVDIMM_EVENT_PTR(HOST_S_DUR), + NVDIMM_EVENT_PTR(HOST_L_DUR), + NVDIMM_EVENT_PTR(MED_R_CNT), + NVDIMM_EVENT_PTR(MED_W_CNT), + NVDIMM_EVENT_PTR(MED_R_DUR), + NVDIMM_EVENT_PTR(MED_W_DUR), + NVDIMM_EVENT_PTR(CACHE_RH_CNT), + NVDIMM_EVENT_PTR(CACHE_WH_CNT), + NVDIMM_EVENT_PTR(FAST_W_CNT), + NULL +}; + +static struct attribute_group nvdimm_pmu_events_group = { + .name = "events", + .attrs = nvdimm_events_attr, +}; + +PMU_FORMAT_ATTR(event, "config:0-4"); + +static struct attribute *nvdimm_pmu_format_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group nvdimm_pmu_format_group = { + .name = "format", + .attrs = nvdimm_pmu_format_attr, +}; + +ssize_t nvdimm_events_sysfs_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct perf_pmu_events_attr *pmu_attr; + + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); + + return sprintf(page, "event=0x%02llx\n", pmu_attr->id); +} + +static ssize_t nvdimm_pmu_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pmu *pmu = dev_get_drvdata(dev); + struct nvdimm_pmu *nd_pmu; + + nd_pmu = container_of(pmu, struct nvdimm_pmu, pmu); + + return cpumap_print_to_pagebuf(true, buf, cpumask_of(nd_pmu->cpu)); +} + +static int nvdimm_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node) +{ + struct nvdimm_pmu *nd_pmu; + u32 target; + int nodeid; + const struct cpumask *cpumask; + + nd_pmu = hlist_entry_safe(node, struct nvdimm_pmu, node); + + /* Clear it, incase given cpu is set in nd_pmu->arch_cpumask */ + cpumask_test_and_clear_cpu(cpu, &nd_pmu->arch_cpumask); + + /* + * If given cpu is not same as current designated cpu for + * counter access, just return. + */ + if (cpu != nd_pmu->cpu) + return 0; + + /* Check for any active cpu in nd_pmu->arch_cpumask */ + target = cpumask_any(&nd_pmu->arch_cpumask); + + /* + * Incase we don't have any active cpu in nd_pmu->arch_cpumask, + * check in given cpu's numa node list. + */ + if (target >= nr_cpu_ids) { + nodeid = cpu_to_node(cpu); + cpumask = cpumask_of_node(nodeid); + target = cpumask_any_but(cpumask, cpu); + } + nd_pmu->cpu = target; + + /* Migrate nvdimm pmu events to the new target cpu if valid */ + if (target >= 0 && target < nr_cpu_ids) + perf_pmu_migrate_context(&nd_pmu->pmu, cpu, target); + + return 0; +} + +static int nvdimm_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) +{ + struct nvdimm_pmu *nd_pmu; + + nd_pmu = hlist_entry_safe(node, struct nvdimm_pmu, node); + + if (nd_pmu->cpu >= nr_cpu_ids) + nd_pmu->cpu = cpu; + + return 0; +} + +static int create_cpumask_attr_group(struct nvdimm_pmu *nd_pmu) +{ + struct perf_pmu_events_attr *pmu_events_attr; + struct attribute **attrs_group; + struct attribute_group *nvdimm_pmu_cpumask_group; + + pmu_events_attr = kzalloc(sizeof(*pmu_events_attr), GFP_KERNEL); + if (!pmu_events_attr) + return -ENOMEM; + + attrs_group = kzalloc(2 * sizeof(struct attribute *), GFP_KERNEL); + if (!attrs_group) { + kfree(pmu_events_attr); + return -ENOMEM; + } + + /* Allocate memory for cpumask attribute group */ + nvdimm_pmu_cpumask_group = kzalloc(sizeof(*nvdimm_pmu_cpumask_group), GFP_KERNEL); + if (!nvdimm_pmu_cpumask_group) { + kfree(pmu_events_attr); + kfree(attrs_group); + return -ENOMEM; + } + + sysfs_attr_init(&pmu_events_attr->attr.attr); + pmu_events_attr->attr.attr.name = "cpumask"; + pmu_events_attr->attr.attr.mode = 0444; + pmu_events_attr->attr.show = nvdimm_pmu_cpumask_show; + attrs_group[0] = &pmu_events_attr->attr.attr; + attrs_group[1] = NULL; + + nvdimm_pmu_cpumask_group->attrs = attrs_group; + nd_pmu->pmu.attr_groups[NVDIMM_PMU_CPUMASK_ATTR] = nvdimm_pmu_cpumask_group; + return 0; +} + +static int nvdimm_pmu_cpu_hotplug_init(struct nvdimm_pmu *nd_pmu) +{ + int nodeid, rc; + const struct cpumask *cpumask; + + /* + * Incase of cpu hotplug feature, arch specific code + * can provide required cpumask which can be used + * to get designatd cpu for counter access. + * Check for any active cpu in nd_pmu->arch_cpumask. + */ + if (!cpumask_empty(&nd_pmu->arch_cpumask)) { + nd_pmu->cpu = cpumask_any(&nd_pmu->arch_cpumask); + } else { + /* pick active cpu from the cpumask of device numa node. */ + nodeid = dev_to_node(nd_pmu->dev); + cpumask = cpumask_of_node(nodeid); + nd_pmu->cpu = cpumask_any(cpumask); + } + + rc = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "perf/nvdimm:online", + nvdimm_pmu_cpu_online, nvdimm_pmu_cpu_offline); + + if (rc < 0) + return rc; + + nd_pmu->cpuhp_state = rc; + + /* Register the pmu instance for cpu hotplug */ + rc = cpuhp_state_add_instance_nocalls(nd_pmu->cpuhp_state, &nd_pmu->node); + if (rc) { + cpuhp_remove_multi_state(nd_pmu->cpuhp_state); + return rc; + } + + /* Create cpumask attribute group */ + rc = create_cpumask_attr_group(nd_pmu); + if (rc) { + cpuhp_state_remove_instance_nocalls(nd_pmu->cpuhp_state, &nd_pmu->node); + cpuhp_remove_multi_state(nd_pmu->cpuhp_state); + return rc; + } + + return 0; +} + +static void nvdimm_pmu_free_hotplug_memory(struct nvdimm_pmu *nd_pmu) +{ + cpuhp_state_remove_instance_nocalls(nd_pmu->cpuhp_state, &nd_pmu->node); + cpuhp_remove_multi_state(nd_pmu->cpuhp_state); + + if (nd_pmu->pmu.attr_groups[NVDIMM_PMU_CPUMASK_ATTR]) + kfree(nd_pmu->pmu.attr_groups[NVDIMM_PMU_CPUMASK_ATTR]->attrs); + kfree(nd_pmu->pmu.attr_groups[NVDIMM_PMU_CPUMASK_ATTR]); +} + +int register_nvdimm_pmu(struct nvdimm_pmu *nd_pmu, struct platform_device *pdev) +{ + int rc; + + if (!nd_pmu || !pdev) + return -EINVAL; + + /* event functions like add/del/read/event_init and pmu name should not be NULL */ + if (WARN_ON_ONCE(!(nd_pmu->pmu.event_init && nd_pmu->pmu.add && + nd_pmu->pmu.del && nd_pmu->pmu.read && nd_pmu->pmu.name))) + return -EINVAL; + + nd_pmu->pmu.attr_groups = kzalloc((NVDIMM_PMU_NULL_ATTR + 1) * + sizeof(struct attribute_group *), GFP_KERNEL); + if (!nd_pmu->pmu.attr_groups) + return -ENOMEM; + + /* + * Add platform_device->dev pointer to nvdimm_pmu to access + * device data in events functions. + */ + nd_pmu->dev = &pdev->dev; + + /* Fill attribute groups for the nvdimm pmu device */ + nd_pmu->pmu.attr_groups[NVDIMM_PMU_FORMAT_ATTR] = &nvdimm_pmu_format_group; + nd_pmu->pmu.attr_groups[NVDIMM_PMU_EVENT_ATTR] = &nvdimm_pmu_events_group; + nd_pmu->pmu.attr_groups[NVDIMM_PMU_NULL_ATTR] = NULL; + + /* Fill attribute group for cpumask */ + rc = nvdimm_pmu_cpu_hotplug_init(nd_pmu); + if (rc) { + pr_info("cpu hotplug feature failed for device: %s\n", nd_pmu->pmu.name); + kfree(nd_pmu->pmu.attr_groups); + return rc; + } + + rc = perf_pmu_register(&nd_pmu->pmu, nd_pmu->pmu.name, -1); + if (rc) { + kfree(nd_pmu->pmu.attr_groups); + nvdimm_pmu_free_hotplug_memory(nd_pmu); + return rc; + } + + pr_info("%s NVDIMM performance monitor support registered\n", + nd_pmu->pmu.name); + + return 0; +} +EXPORT_SYMBOL_GPL(register_nvdimm_pmu); + +void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu) +{ + perf_pmu_unregister(&nd_pmu->pmu); + nvdimm_pmu_free_hotplug_memory(nd_pmu); + kfree(nd_pmu); +} +EXPORT_SYMBOL_GPL(unregister_nvdimm_pmu); diff --git a/include/linux/nd.h b/include/linux/nd.h index ad186e828263..4813c7089e5c 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -9,6 +9,7 @@ #include #include #include +#include enum nvdimm_event { NVDIMM_REVALIDATE_POISON, @@ -24,6 +25,19 @@ enum nvdimm_claim_class { NVDIMM_CCLASS_UNKNOWN, }; +#define NVDIMM_EVENT_VAR(_id) event_attr_##_id +#define NVDIMM_EVENT_PTR(_id) (&event_attr_##_id.attr.attr) + +#define NVDIMM_EVENT_ATTR(_name, _id) \ + PMU_EVENT_ATTR(_name, NVDIMM_EVENT_VAR(_id), _id, \ + nvdimm_events_sysfs_show) + +/* Event attribute array index */ +#define NVDIMM_PMU_FORMAT_ATTR 0 +#define NVDIMM_PMU_EVENT_ATTR 1 +#define NVDIMM_PMU_CPUMASK_ATTR 2 +#define NVDIMM_PMU_NULL_ATTR 3 + /** * struct nvdimm_pmu - data structure for nvdimm perf driver * @pmu: pmu data structure for nvdimm performance stats. @@ -43,6 +57,16 @@ struct nvdimm_pmu { struct cpumask arch_cpumask; }; +extern ssize_t nvdimm_events_sysfs_show(struct device *dev, + struct device_attribute *attr, + char *page); + +int register_nvdimm_pmu(struct nvdimm_pmu *nvdimm, struct platform_device *pdev); +void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu); +void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); +int perf_pmu_register(struct pmu *pmu, const char *name, int type); +void perf_pmu_unregister(struct pmu *pmu); + struct nd_device_driver { struct device_driver drv; unsigned long type;