From 9a61d0838cd0a81529badfba7bfa39e81d5529d3 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Fri, 25 Feb 2022 20:00:21 +0530 Subject: [PATCH 01/14] drivers/nvdimm: Add nvdimm pmu structure A structure is added called nvdimm_pmu, for performance stats reporting support of nvdimm devices. It can be used to add device pmu data such as pmu data structure for performance stats, nvdimm device pointer along with cpumask attributes. Acked-by: Peter Zijlstra (Intel) Tested-by: Nageswara R Sastry Signed-off-by: Kajol Jain Reviewed-by: Madhavan Srinivasan Link: https://lore.kernel.org/r/20220225143024.47947-2-kjain@linux.ibm.com Signed-off-by: Dan Williams --- include/linux/nd.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/include/linux/nd.h b/include/linux/nd.h index 8a8c63edb1b2..ad186e828263 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -8,6 +8,7 @@ #include #include #include +#include enum nvdimm_event { NVDIMM_REVALIDATE_POISON, @@ -23,6 +24,25 @@ enum nvdimm_claim_class { NVDIMM_CCLASS_UNKNOWN, }; +/** + * struct nvdimm_pmu - data structure for nvdimm perf driver + * @pmu: pmu data structure for nvdimm performance stats. + * @dev: nvdimm device pointer. + * @cpu: designated cpu for counter access. + * @node: node for cpu hotplug notifier link. + * @cpuhp_state: state for cpu hotplug notification. + * @arch_cpumask: cpumask to get designated cpu for counter access. + */ +struct nvdimm_pmu { + struct pmu pmu; + struct device *dev; + int cpu; + struct hlist_node node; + enum cpuhp_state cpuhp_state; + /* cpumask provided by arch/platform specific code */ + struct cpumask arch_cpumask; +}; + struct nd_device_driver { struct device_driver drv; unsigned long type; From 0fab1ba6ad6ba1f76380f92ead95c6e861ef8116 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Fri, 25 Feb 2022 20:00:22 +0530 Subject: [PATCH 02/14] 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; From 4c08d4bbc089a95f3f38389c2b79dbc6ab24f10b Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Fri, 25 Feb 2022 20:00:23 +0530 Subject: [PATCH 03/14] powerpc/papr_scm: Add perf interface support Performance monitoring support for papr-scm nvdimm devices via perf interface is added which includes addition of pmu functions like add/del/read/event_init for nvdimm_pmu struture. A new parameter 'priv' in added to the pdev_archdata structure to save nvdimm_pmu device pointer, to handle the unregistering of pmu device. papr_scm_pmu_register function populates the nvdimm_pmu structure with name, capabilities, cpumask along with event handling functions. Finally the populated nvdimm_pmu structure is passed to register the pmu device. Event handling functions internally uses hcall to get events and counter data. Result in power9 machine with 2 nvdimm device: Ex: List all event by perf list command:# perf list nmem nmem0/cache_rh_cnt/ [Kernel PMU event] nmem0/cache_wh_cnt/ [Kernel PMU event] nmem0/cri_res_util/ [Kernel PMU event] nmem0/ctl_res_cnt/ [Kernel PMU event] nmem0/ctl_res_tm/ [Kernel PMU event] nmem0/fast_w_cnt/ [Kernel PMU event] nmem0/host_l_cnt/ [Kernel PMU event] nmem0/host_l_dur/ [Kernel PMU event] nmem0/host_s_cnt/ [Kernel PMU event] nmem0/host_s_dur/ [Kernel PMU event] nmem0/med_r_cnt/ [Kernel PMU event] nmem0/med_r_dur/ [Kernel PMU event] nmem0/med_w_cnt/ [Kernel PMU event] nmem0/med_w_dur/ [Kernel PMU event] nmem0/mem_life/ [Kernel PMU event] nmem0/poweron_secs/ [Kernel PMU event] ... nmem1/mem_life/ [Kernel PMU event] nmem1/poweron_secs/ [Kernel PMU event] Acked-by: Peter Zijlstra (Intel) Tested-by: Nageswara R Sastry Signed-off-by: Kajol Jain [Add numa_map_to_online_node function call to get online node id] Reported-by: Nageswara R Sastry Reviewed-by: Madhavan Srinivasan Link: https://lore.kernel.org/r/20220225143024.47947-4-kjain@linux.ibm.com Signed-off-by: Dan Williams --- arch/powerpc/include/asm/device.h | 5 + arch/powerpc/platforms/pseries/papr_scm.c | 225 ++++++++++++++++++++++ 2 files changed, 230 insertions(+) diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index 219559d65864..47ed639f3b8f 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -48,6 +48,11 @@ struct dev_archdata { struct pdev_archdata { u64 dma_mask; + /* + * Pointer to nvdimm_pmu structure, to handle the unregistering + * of pmu device + */ + void *priv; }; #endif /* _ASM_POWERPC_DEVICE_H */ diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f48e87ac89c9..4dd513d7c029 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -19,6 +19,7 @@ #include #include #include +#include #define BIND_ANY_ADDR (~0ul) @@ -68,6 +69,8 @@ #define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS) #define PAPR_SCM_PERF_STATS_VERSION 0x1 +#define to_nvdimm_pmu(_pmu) container_of(_pmu, struct nvdimm_pmu, pmu) + /* Struct holding a single performance metric */ struct papr_scm_perf_stat { u8 stat_id[8]; @@ -120,6 +123,9 @@ struct papr_scm_priv { /* length of the stat buffer as expected by phyp */ size_t stat_buffer_len; + + /* array to have event_code and stat_id mappings */ + char **nvdimm_events_map; }; static int papr_scm_pmem_flush(struct nd_region *nd_region, @@ -340,6 +346,218 @@ static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p, return 0; } +static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev, u64 *count) +{ + struct papr_scm_perf_stat *stat; + struct papr_scm_perf_stats *stats; + struct papr_scm_priv *p = (struct papr_scm_priv *)dev->driver_data; + int rc, size; + + /* Allocate request buffer enough to hold single performance stat */ + size = sizeof(struct papr_scm_perf_stats) + + sizeof(struct papr_scm_perf_stat); + + if (!p || !p->nvdimm_events_map) + return -EINVAL; + + stats = kzalloc(size, GFP_KERNEL); + if (!stats) + return -ENOMEM; + + stat = &stats->scm_statistic[0]; + memcpy(&stat->stat_id, + p->nvdimm_events_map[event->attr.config], + sizeof(stat->stat_id)); + stat->stat_val = 0; + + rc = drc_pmem_query_stats(p, stats, 1); + if (rc < 0) { + kfree(stats); + return rc; + } + + *count = be64_to_cpu(stat->stat_val); + kfree(stats); + return 0; +} + +static int papr_scm_pmu_event_init(struct perf_event *event) +{ + struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu); + struct papr_scm_priv *p; + + if (!nd_pmu) + return -EINVAL; + + /* test the event attr type for PMU enumeration */ + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* it does not support event sampling mode */ + if (is_sampling_event(event)) + return -EOPNOTSUPP; + + /* no branch sampling */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + p = (struct papr_scm_priv *)nd_pmu->dev->driver_data; + if (!p) + return -EINVAL; + + /* Invalid eventcode */ + if (event->attr.config == 0 || event->attr.config > 16) + return -EINVAL; + + return 0; +} + +static int papr_scm_pmu_add(struct perf_event *event, int flags) +{ + u64 count; + int rc; + struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu); + + if (!nd_pmu) + return -EINVAL; + + if (flags & PERF_EF_START) { + rc = papr_scm_pmu_get_value(event, nd_pmu->dev, &count); + if (rc) + return rc; + + local64_set(&event->hw.prev_count, count); + } + + return 0; +} + +static void papr_scm_pmu_read(struct perf_event *event) +{ + u64 prev, now; + int rc; + struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu); + + if (!nd_pmu) + return; + + rc = papr_scm_pmu_get_value(event, nd_pmu->dev, &now); + if (rc) + return; + + prev = local64_xchg(&event->hw.prev_count, now); + local64_add(now - prev, &event->count); +} + +static void papr_scm_pmu_del(struct perf_event *event, int flags) +{ + papr_scm_pmu_read(event); +} + +static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu *nd_pmu) +{ + struct papr_scm_perf_stat *stat; + struct papr_scm_perf_stats *stats; + char *statid; + int index, rc, count; + u32 available_events; + + if (!p->stat_buffer_len) + return -ENOENT; + + available_events = (p->stat_buffer_len - sizeof(struct papr_scm_perf_stats)) + / sizeof(struct papr_scm_perf_stat); + + /* Allocate the buffer for phyp where stats are written */ + stats = kzalloc(p->stat_buffer_len, GFP_KERNEL); + if (!stats) { + rc = -ENOMEM; + return rc; + } + + /* Allocate memory to nvdimm_event_map */ + p->nvdimm_events_map = kcalloc(available_events, sizeof(char *), GFP_KERNEL); + if (!p->nvdimm_events_map) { + rc = -ENOMEM; + goto out_stats; + } + + /* Called to get list of events supported */ + rc = drc_pmem_query_stats(p, stats, 0); + if (rc) + goto out_nvdimm_events_map; + + for (index = 0, stat = stats->scm_statistic, count = 0; + index < available_events; index++, ++stat) { + statid = kzalloc(strlen(stat->stat_id) + 1, GFP_KERNEL); + if (!statid) { + rc = -ENOMEM; + goto out_nvdimm_events_map; + } + + strcpy(statid, stat->stat_id); + p->nvdimm_events_map[count] = statid; + count++; + } + p->nvdimm_events_map[count] = NULL; + kfree(stats); + return 0; + +out_nvdimm_events_map: + kfree(p->nvdimm_events_map); +out_stats: + kfree(stats); + return rc; +} + +static void papr_scm_pmu_register(struct papr_scm_priv *p) +{ + struct nvdimm_pmu *nd_pmu; + int rc, nodeid; + + nd_pmu = kzalloc(sizeof(*nd_pmu), GFP_KERNEL); + if (!nd_pmu) { + rc = -ENOMEM; + goto pmu_err_print; + } + + rc = papr_scm_pmu_check_events(p, nd_pmu); + if (rc) + goto pmu_check_events_err; + + nd_pmu->pmu.task_ctx_nr = perf_invalid_context; + nd_pmu->pmu.name = nvdimm_name(p->nvdimm); + nd_pmu->pmu.event_init = papr_scm_pmu_event_init; + nd_pmu->pmu.read = papr_scm_pmu_read; + nd_pmu->pmu.add = papr_scm_pmu_add; + nd_pmu->pmu.del = papr_scm_pmu_del; + + nd_pmu->pmu.capabilities = PERF_PMU_CAP_NO_INTERRUPT | + PERF_PMU_CAP_NO_EXCLUDE; + + /*updating the cpumask variable */ + nodeid = numa_map_to_online_node(dev_to_node(&p->pdev->dev)); + nd_pmu->arch_cpumask = *cpumask_of_node(nodeid); + + rc = register_nvdimm_pmu(nd_pmu, p->pdev); + if (rc) + goto pmu_register_err; + + /* + * Set archdata.priv value to nvdimm_pmu structure, to handle the + * unregistering of pmu device. + */ + p->pdev->archdata.priv = nd_pmu; + return; + +pmu_register_err: + kfree(p->nvdimm_events_map); +pmu_check_events_err: + kfree(nd_pmu); +pmu_err_print: + dev_info(&p->pdev->dev, "nvdimm pmu didn't register rc=%d\n", rc); +} + /* * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the * health information. @@ -1236,6 +1454,7 @@ static int papr_scm_probe(struct platform_device *pdev) goto err2; platform_set_drvdata(pdev, p); + papr_scm_pmu_register(p); return 0; @@ -1254,6 +1473,12 @@ static int papr_scm_remove(struct platform_device *pdev) nvdimm_bus_unregister(p->bus); drc_pmem_unbind(p); + + if (pdev->archdata.priv) + unregister_nvdimm_pmu(pdev->archdata.priv); + + pdev->archdata.priv = NULL; + kfree(p->nvdimm_events_map); kfree(p->bus_desc.provider_name); kfree(p); From 2bec6d9aa89cbe97deb6fbc64708212b780605a4 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Fri, 25 Feb 2022 20:00:24 +0530 Subject: [PATCH 04/14] docs: ABI: sysfs-bus-nvdimm: Document sysfs event format entries for nvdimm pmu Details are added for the event, cpumask and format attributes in the ABI documentation. Acked-by: Peter Zijlstra (Intel) Tested-by: Nageswara R Sastry Signed-off-by: Kajol Jain Reviewed-by: Madhavan Srinivasan Link: https://lore.kernel.org/r/20220225143024.47947-5-kjain@linux.ibm.com Signed-off-by: Dan Williams --- Documentation/ABI/testing/sysfs-bus-nvdimm | 35 ++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-bus-nvdimm b/Documentation/ABI/testing/sysfs-bus-nvdimm index bff84a16812a..1c1f5acbf53d 100644 --- a/Documentation/ABI/testing/sysfs-bus-nvdimm +++ b/Documentation/ABI/testing/sysfs-bus-nvdimm @@ -6,3 +6,38 @@ Description: The libnvdimm sub-system implements a common sysfs interface for platform nvdimm resources. See Documentation/driver-api/nvdimm/. + +What: /sys/bus/event_source/devices/nmemX/format +Date: February 2022 +KernelVersion: 5.18 +Contact: Kajol Jain +Description: (RO) Attribute group to describe the magic bits + that go into perf_event_attr.config for a particular pmu. + (See ABI/testing/sysfs-bus-event_source-devices-format). + + Each attribute under this group defines a bit range of the + perf_event_attr.config. Supported attribute is listed + below:: + event = "config:0-4" - event ID + + For example:: + ctl_res_cnt = "event=0x1" + +What: /sys/bus/event_source/devices/nmemX/events +Date: February 2022 +KernelVersion: 5.18 +Contact: Kajol Jain +Description: (RO) Attribute group to describe performance monitoring events + for the nvdimm memory device. Each attribute in this group + describes a single performance monitoring event supported by + this nvdimm pmu. The name of the file is the name of the event. + (See ABI/testing/sysfs-bus-event_source-devices-events). A + listing of the events supported by a given nvdimm provider type + can be found in Documentation/driver-api/nvdimm/$provider. + +What: /sys/bus/event_source/devices/nmemX/cpumask +Date: February 2022 +KernelVersion: 5.18 +Contact: Kajol Jain +Description: (RO) This sysfs file exposes the cpumask which is designated to + to retrieve nvdimm pmu event counter data. From d9d290d7e659e9db3e4518040cc18b97f5535f4a Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 9 Mar 2022 19:49:21 -0800 Subject: [PATCH 05/14] nvdimm/region: Fix default alignment for small regions In preparation for removing BLK aperture support the NVDIMM unit tests discovered that the default alignment can be set higher than the capacity of the region. Fall back to PAGE_SIZE in that case. Given this has not been seen in the wild, elide notifying -stable. Fixes: 2522afb86a8c ("libnvdimm/region: Introduce an 'align' attribute") Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/164688416128.2879318.17890707310125575258.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/region_devs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 9ccf3d608799..70ad891a76ba 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -1025,6 +1025,9 @@ static unsigned long default_align(struct nd_region *nd_region) } } + if (nd_region->ndr_size < MEMREMAP_COMPAT_ALIGN_MAX) + align = PAGE_SIZE; + mappings = max_t(u16, 1, nd_region->ndr_mappings); div_u64_rem(align, mappings, &remainder); if (remainder) From f8669f1d6a86a6b17104ceca9340ded280307ac1 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 9 Mar 2022 19:49:26 -0800 Subject: [PATCH 06/14] nvdimm/blk: Delete the block-aperture window driver Block Aperture Window support was an attempt to layer an error model over PMEM for platforms that did not support machine-check-recovery. However, it was abandoned before it ever shipped, and only ever existed in the ACPI specification. Meanwhile Linux has carried a large pile of dead code for non-shipping infrastructure. For years it has been off to the side out of the way, but now CXL and recent directions with DAX support have the potential to collide with this code. In preparation for adding discontiguous namespace support, a pre-requisite for the nvdimm subsystem to replace device-mapper for striping + concatenation use cases, delete BLK aperture support. On the obscure chance that some hardware vendor shipped support for this mode, note that the driver will still keep BLK space reserved in the label area. So an end user in this case would still have the opportunity to report the regression to get BLK-mode support restored without risking the data they have on that device. Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/164688416668.2879318.16903178375774275120.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- Documentation/driver-api/nvdimm/nvdimm.rst | 400 +++++---------------- drivers/nvdimm/Kconfig | 25 +- drivers/nvdimm/Makefile | 3 - drivers/nvdimm/blk.c | 335 ----------------- tools/testing/nvdimm/Kbuild | 4 - tools/testing/nvdimm/config_check.c | 1 - 6 files changed, 89 insertions(+), 679 deletions(-) delete mode 100644 drivers/nvdimm/blk.c diff --git a/Documentation/driver-api/nvdimm/nvdimm.rst b/Documentation/driver-api/nvdimm/nvdimm.rst index 1d8302b89bd4..7917f6471092 100644 --- a/Documentation/driver-api/nvdimm/nvdimm.rst +++ b/Documentation/driver-api/nvdimm/nvdimm.rst @@ -14,10 +14,8 @@ Version 13 Overview Supporting Documents Git Trees - LIBNVDIMM PMEM and BLK - Why BLK? - PMEM vs BLK - BLK-REGIONs, PMEM-REGIONs, Atomic Sectors, and DAX + LIBNVDIMM PMEM + PMEM-REGIONs, Atomic Sectors, and DAX Example NVDIMM Platform LIBNVDIMM Kernel Device Model and LIBNDCTL Userspace API LIBNDCTL: Context @@ -53,19 +51,12 @@ PMEM: block device composed of PMEM is capable of DAX. A PMEM address range may span an interleave of several DIMMs. -BLK: - A set of one or more programmable memory mapped apertures provided - by a DIMM to access its media. This indirection precludes the - performance benefit of interleaving, but enables DIMM-bounded failure - modes. - DPA: DIMM Physical Address, is a DIMM-relative offset. With one DIMM in the system there would be a 1:1 system-physical-address:DPA association. Once more DIMMs are added a memory controller interleave must be decoded to determine the DPA associated with a given - system-physical-address. BLK capacity always has a 1:1 relationship - with a single-DIMM's DPA range. + system-physical-address. DAX: File system extensions to bypass the page cache and block layer to @@ -84,30 +75,30 @@ BTT: Block Translation Table: Persistent memory is byte addressable. Existing software may have an expectation that the power-fail-atomicity of writes is at least one sector, 512 bytes. The BTT is an indirection - table with atomic update semantics to front a PMEM/BLK block device + table with atomic update semantics to front a PMEM block device driver and present arbitrary atomic sector sizes. LABEL: Metadata stored on a DIMM device that partitions and identifies - (persistently names) storage between PMEM and BLK. It also partitions - BLK storage to host BTTs with different parameters per BLK-partition. - Note that traditional partition tables, GPT/MBR, are layered on top of a - BLK or PMEM device. + (persistently names) capacity allocated to different PMEM namespaces. It + also indicates whether an address abstraction like a BTT is applied to + the namepsace. Note that traditional partition tables, GPT/MBR, are + layered on top of a PMEM namespace, or an address abstraction like BTT + if present, but partition support is deprecated going forward. Overview ======== -The LIBNVDIMM subsystem provides support for three types of NVDIMMs, namely, -PMEM, BLK, and NVDIMM devices that can simultaneously support both PMEM -and BLK mode access. These three modes of operation are described by -the "NVDIMM Firmware Interface Table" (NFIT) in ACPI 6. While the LIBNVDIMM -implementation is generic and supports pre-NFIT platforms, it was guided -by the superset of capabilities need to support this ACPI 6 definition -for NVDIMM resources. The bulk of the kernel implementation is in place -to handle the case where DPA accessible via PMEM is aliased with DPA -accessible via BLK. When that occurs a LABEL is needed to reserve DPA -for exclusive access via one mode a time. +The LIBNVDIMM subsystem provides support for PMEM described by platform +firmware or a device driver. On ACPI based systems the platform firmware +conveys persistent memory resource via the ACPI NFIT "NVDIMM Firmware +Interface Table" in ACPI 6. While the LIBNVDIMM subsystem implementation +is generic and supports pre-NFIT platforms, it was guided by the +superset of capabilities need to support this ACPI 6 definition for +NVDIMM resources. The original implementation supported the +block-window-aperture capability described in the NFIT, but that support +has since been abandoned and never shipped in a product. Supporting Documents -------------------- @@ -125,107 +116,38 @@ Git Trees --------- LIBNVDIMM: - https://git.kernel.org/cgit/linux/kernel/git/djbw/nvdimm.git + https://git.kernel.org/cgit/linux/kernel/git/nvdimm/nvdimm.git LIBNDCTL: https://github.com/pmem/ndctl.git -PMEM: - https://github.com/01org/prd -LIBNVDIMM PMEM and BLK -====================== +LIBNVDIMM PMEM +============== Prior to the arrival of the NFIT, non-volatile memory was described to a system in various ad-hoc ways. Usually only the bare minimum was provided, namely, a single system-physical-address range where writes are expected to be durable after a system power loss. Now, the NFIT specification standardizes not only the description of PMEM, but also -BLK and platform message-passing entry points for control and -configuration. +platform message-passing entry points for control and configuration. -For each NVDIMM access method (PMEM, BLK), LIBNVDIMM provides a block -device driver: +PMEM (nd_pmem.ko): Drives a system-physical-address range. This range is +contiguous in system memory and may be interleaved (hardware memory controller +striped) across multiple DIMMs. When interleaved the platform may optionally +provide details of which DIMMs are participating in the interleave. - 1. PMEM (nd_pmem.ko): Drives a system-physical-address range. This - range is contiguous in system memory and may be interleaved (hardware - memory controller striped) across multiple DIMMs. When interleaved the - platform may optionally provide details of which DIMMs are participating - in the interleave. +It is worth noting that when the labeling capability is detected (a EFI +namespace label index block is found), then no block device is created +by default as userspace needs to do at least one allocation of DPA to +the PMEM range. In contrast ND_NAMESPACE_IO ranges, once registered, +can be immediately attached to nd_pmem. This latter mode is called +label-less or "legacy". - Note that while LIBNVDIMM describes system-physical-address ranges that may - alias with BLK access as ND_NAMESPACE_PMEM ranges and those without - alias as ND_NAMESPACE_IO ranges, to the nd_pmem driver there is no - distinction. The different device-types are an implementation detail - that userspace can exploit to implement policies like "only interface - with address ranges from certain DIMMs". It is worth noting that when - aliasing is present and a DIMM lacks a label, then no block device can - be created by default as userspace needs to do at least one allocation - of DPA to the PMEM range. In contrast ND_NAMESPACE_IO ranges, once - registered, can be immediately attached to nd_pmem. +PMEM-REGIONs, Atomic Sectors, and DAX +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - 2. BLK (nd_blk.ko): This driver performs I/O using a set of platform - defined apertures. A set of apertures will access just one DIMM. - Multiple windows (apertures) allow multiple concurrent accesses, much like - tagged-command-queuing, and would likely be used by different threads or - different CPUs. - - The NFIT specification defines a standard format for a BLK-aperture, but - the spec also allows for vendor specific layouts, and non-NFIT BLK - implementations may have other designs for BLK I/O. For this reason - "nd_blk" calls back into platform-specific code to perform the I/O. - - One such implementation is defined in the "Driver Writer's Guide" and "DSM - Interface Example". - - -Why BLK? -======== - -While PMEM provides direct byte-addressable CPU-load/store access to -NVDIMM storage, it does not provide the best system RAS (recovery, -availability, and serviceability) model. An access to a corrupted -system-physical-address address causes a CPU exception while an access -to a corrupted address through an BLK-aperture causes that block window -to raise an error status in a register. The latter is more aligned with -the standard error model that host-bus-adapter attached disks present. - -Also, if an administrator ever wants to replace a memory it is easier to -service a system at DIMM module boundaries. Compare this to PMEM where -data could be interleaved in an opaque hardware specific manner across -several DIMMs. - -PMEM vs BLK ------------ - -BLK-apertures solve these RAS problems, but their presence is also the -major contributing factor to the complexity of the ND subsystem. They -complicate the implementation because PMEM and BLK alias in DPA space. -Any given DIMM's DPA-range may contribute to one or more -system-physical-address sets of interleaved DIMMs, *and* may also be -accessed in its entirety through its BLK-aperture. Accessing a DPA -through a system-physical-address while simultaneously accessing the -same DPA through a BLK-aperture has undefined results. For this reason, -DIMMs with this dual interface configuration include a DSM function to -store/retrieve a LABEL. The LABEL effectively partitions the DPA-space -into exclusive system-physical-address and BLK-aperture accessible -regions. For simplicity a DIMM is allowed a PMEM "region" per each -interleave set in which it is a member. The remaining DPA space can be -carved into an arbitrary number of BLK devices with discontiguous -extents. - -BLK-REGIONs, PMEM-REGIONs, Atomic Sectors, and DAX -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - -One of the few -reasons to allow multiple BLK namespaces per REGION is so that each -BLK-namespace can be configured with a BTT with unique atomic sector -sizes. While a PMEM device can host a BTT the LABEL specification does -not provide for a sector size to be specified for a PMEM namespace. - -This is due to the expectation that the primary usage model for PMEM is -via DAX, and the BTT is incompatible with DAX. However, for the cases -where an application or filesystem still needs atomic sector update -guarantees it can register a BTT on a PMEM device or partition. See +For the cases where an application or filesystem still needs atomic sector +update guarantees it can register a BTT on a PMEM device or partition. See LIBNVDIMM/NDCTL: Block Translation Table "btt" @@ -236,51 +158,40 @@ For the remainder of this document the following diagram will be referenced for any example sysfs layouts:: - (a) (b) DIMM BLK-REGION + (a) (b) DIMM +-------------------+--------+--------+--------+ - +------+ | pm0.0 | blk2.0 | pm1.0 | blk2.1 | 0 region2 + +------+ | pm0.0 | free | pm1.0 | free | 0 | imc0 +--+- - - region0- - - +--------+ +--------+ - +--+---+ | pm0.0 | blk3.0 | pm1.0 | blk3.1 | 1 region3 + +--+---+ | pm0.0 | free | pm1.0 | free | 1 | +-------------------+--------v v--------+ +--+---+ | | | cpu0 | region1 +--+---+ | | | +----------------------------^ ^--------+ - +--+---+ | blk4.0 | pm1.0 | blk4.0 | 2 region4 + +--+---+ | free | pm1.0 | free | 2 | imc1 +--+----------------------------| +--------+ - +------+ | blk5.0 | pm1.0 | blk5.0 | 3 region5 + +------+ | free | pm1.0 | free | 3 +----------------------------+--------+--------+ In this platform we have four DIMMs and two memory controllers in one -socket. Each unique interface (BLK or PMEM) to DPA space is identified -by a region device with a dynamically assigned id (REGION0 - REGION5). +socket. Each PMEM interleave set is identified by a region device with +a dynamically assigned id. 1. The first portion of DIMM0 and DIMM1 are interleaved as REGION0. A single PMEM namespace is created in the REGION0-SPA-range that spans most of DIMM0 and DIMM1 with a user-specified name of "pm0.0". Some of that - interleaved system-physical-address range is reclaimed as BLK-aperture - accessed space starting at DPA-offset (a) into each DIMM. In that - reclaimed space we create two BLK-aperture "namespaces" from REGION2 and - REGION3 where "blk2.0" and "blk3.0" are just human readable names that - could be set to any user-desired name in the LABEL. + interleaved system-physical-address range is left free for + another PMEM namespace to be defined. 2. In the last portion of DIMM0 and DIMM1 we have an interleaved system-physical-address range, REGION1, that spans those two DIMMs as well as DIMM2 and DIMM3. Some of REGION1 is allocated to a PMEM namespace - named "pm1.0", the rest is reclaimed in 4 BLK-aperture namespaces (for - each DIMM in the interleave set), "blk2.1", "blk3.1", "blk4.0", and - "blk5.0". - - 3. The portion of DIMM2 and DIMM3 that do not participate in the REGION1 - interleaved system-physical-address range (i.e. the DPA address past - offset (b) are also included in the "blk4.0" and "blk5.0" namespaces. - Note, that this example shows that BLK-aperture namespaces don't need to - be contiguous in DPA-space. + named "pm1.0". This bus is provided by the kernel under the device /sys/devices/platform/nfit_test.0 when the nfit_test.ko module from - tools/testing/nvdimm is loaded. This not only test LIBNVDIMM but the - acpi_nfit.ko driver as well. + tools/testing/nvdimm is loaded. This module is a unit test for + LIBNVDIMM and the acpi_nfit.ko driver. LIBNVDIMM Kernel Device Model and LIBNDCTL Userspace API @@ -469,17 +380,14 @@ identified by an "nfit_handle" a 32-bit value where: LIBNVDIMM/LIBNDCTL: Region -------------------------- -A generic REGION device is registered for each PMEM range or BLK-aperture -set. Per the example there are 6 regions: 2 PMEM and 4 BLK-aperture -sets on the "nfit_test.0" bus. The primary role of regions are to be a -container of "mappings". A mapping is a tuple of . +A generic REGION device is registered for each PMEM interleave-set / +range. Per the example there are 2 PMEM regions on the "nfit_test.0" +bus. The primary role of regions are to be a container of "mappings". A +mapping is a tuple of . -LIBNVDIMM provides a built-in driver for these REGION devices. This driver -is responsible for reconciling the aliased DPA mappings across all -regions, parsing the LABEL, if present, and then emitting NAMESPACE -devices with the resolved/exclusive DPA-boundaries for the nd_pmem or -nd_blk device driver to consume. +LIBNVDIMM provides a built-in driver for REGION devices. This driver +is responsible for all parsing LABELs, if present, and then emitting NAMESPACE +devices for the nd_pmem driver to consume. In addition to the generic attributes of "mapping"s, "interleave_ways" and "size" the REGION device also exports some convenience attributes. @@ -493,8 +401,6 @@ LIBNVDIMM: region:: struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc); - struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, - struct nd_region_desc *ndr_desc); :: @@ -527,8 +433,9 @@ LIBNDCTL: region enumeration example ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Sample region retrieval routines based on NFIT-unique data like -"spa_index" (interleave set id) for PMEM and "nfit_handle" (dimm id) for -BLK:: +"spa_index" (interleave set id). + +:: static struct ndctl_region *get_pmem_region_by_spa_index(struct ndctl_bus *bus, unsigned int spa_index) @@ -544,139 +451,23 @@ BLK:: return NULL; } - static struct ndctl_region *get_blk_region_by_dimm_handle(struct ndctl_bus *bus, - unsigned int handle) - { - struct ndctl_region *region; - - ndctl_region_foreach(bus, region) { - struct ndctl_mapping *map; - - if (ndctl_region_get_type(region) != ND_DEVICE_REGION_BLOCK) - continue; - ndctl_mapping_foreach(region, map) { - struct ndctl_dimm *dimm = ndctl_mapping_get_dimm(map); - - if (ndctl_dimm_get_handle(dimm) == handle) - return region; - } - } - return NULL; - } - - -Why Not Encode the Region Type into the Region Name? ----------------------------------------------------- - -At first glance it seems since NFIT defines just PMEM and BLK interface -types that we should simply name REGION devices with something derived -from those type names. However, the ND subsystem explicitly keeps the -REGION name generic and expects userspace to always consider the -region-attributes for four reasons: - - 1. There are already more than two REGION and "namespace" types. For - PMEM there are two subtypes. As mentioned previously we have PMEM where - the constituent DIMM devices are known and anonymous PMEM. For BLK - regions the NFIT specification already anticipates vendor specific - implementations. The exact distinction of what a region contains is in - the region-attributes not the region-name or the region-devtype. - - 2. A region with zero child-namespaces is a possible configuration. For - example, the NFIT allows for a DCR to be published without a - corresponding BLK-aperture. This equates to a DIMM that can only accept - control/configuration messages, but no i/o through a descendant block - device. Again, this "type" is advertised in the attributes ('mappings' - == 0) and the name does not tell you much. - - 3. What if a third major interface type arises in the future? Outside - of vendor specific implementations, it's not difficult to envision a - third class of interface type beyond BLK and PMEM. With a generic name - for the REGION level of the device-hierarchy old userspace - implementations can still make sense of new kernel advertised - region-types. Userspace can always rely on the generic region - attributes like "mappings", "size", etc and the expected child devices - named "namespace". This generic format of the device-model hierarchy - allows the LIBNVDIMM and LIBNDCTL implementations to be more uniform and - future-proof. - - 4. There are more robust mechanisms for determining the major type of a - region than a device name. See the next section, How Do I Determine the - Major Type of a Region? - -How Do I Determine the Major Type of a Region? ----------------------------------------------- - -Outside of the blanket recommendation of "use libndctl", or simply -looking at the kernel header (/usr/include/linux/ndctl.h) to decode the -"nstype" integer attribute, here are some other options. - -1. module alias lookup -^^^^^^^^^^^^^^^^^^^^^^ - - The whole point of region/namespace device type differentiation is to - decide which block-device driver will attach to a given LIBNVDIMM namespace. - One can simply use the modalias to lookup the resulting module. It's - important to note that this method is robust in the presence of a - vendor-specific driver down the road. If a vendor-specific - implementation wants to supplant the standard nd_blk driver it can with - minimal impact to the rest of LIBNVDIMM. - - In fact, a vendor may also want to have a vendor-specific region-driver - (outside of nd_region). For example, if a vendor defined its own LABEL - format it would need its own region driver to parse that LABEL and emit - the resulting namespaces. The output from module resolution is more - accurate than a region-name or region-devtype. - -2. udev -^^^^^^^ - - The kernel "devtype" is registered in the udev database:: - - # udevadm info --path=/devices/platform/nfit_test.0/ndbus0/region0 - P: /devices/platform/nfit_test.0/ndbus0/region0 - E: DEVPATH=/devices/platform/nfit_test.0/ndbus0/region0 - E: DEVTYPE=nd_pmem - E: MODALIAS=nd:t2 - E: SUBSYSTEM=nd - - # udevadm info --path=/devices/platform/nfit_test.0/ndbus0/region4 - P: /devices/platform/nfit_test.0/ndbus0/region4 - E: DEVPATH=/devices/platform/nfit_test.0/ndbus0/region4 - E: DEVTYPE=nd_blk - E: MODALIAS=nd:t3 - E: SUBSYSTEM=nd - - ...and is available as a region attribute, but keep in mind that the - "devtype" does not indicate sub-type variations and scripts should - really be understanding the other attributes. - -3. type specific attributes -^^^^^^^^^^^^^^^^^^^^^^^^^^^ - - As it currently stands a BLK-aperture region will never have a - "nfit/spa_index" attribute, but neither will a non-NFIT PMEM region. A - BLK region with a "mappings" value of 0 is, as mentioned above, a DIMM - that does not allow I/O. A PMEM region with a "mappings" value of zero - is a simple system-physical-address range. - LIBNVDIMM/LIBNDCTL: Namespace ----------------------------- -A REGION, after resolving DPA aliasing and LABEL specified boundaries, -surfaces one or more "namespace" devices. The arrival of a "namespace" -device currently triggers either the nd_blk or nd_pmem driver to load -and register a disk/block device. +A REGION, after resolving DPA aliasing and LABEL specified boundaries, surfaces +one or more "namespace" devices. The arrival of a "namespace" device currently +triggers the nd_pmem driver to load and register a disk/block device. LIBNVDIMM: namespace ^^^^^^^^^^^^^^^^^^^^ -Here is a sample layout from the three major types of NAMESPACE where -namespace0.0 represents DIMM-info-backed PMEM (note that it has a 'uuid' -attribute), namespace2.0 represents a BLK namespace (note it has a -'sector_size' attribute) that, and namespace6.0 represents an anonymous -PMEM namespace (note that has no 'uuid' attribute due to not support a -LABEL):: +Here is a sample layout from the 2 major types of NAMESPACE where namespace0.0 +represents DIMM-info-backed PMEM (note that it has a 'uuid' attribute), and +namespace1.0 represents an anonymous PMEM namespace (note that has no 'uuid' +attribute due to not support a LABEL) + +:: /sys/devices/platform/nfit_test.0/ndbus0/region0/namespace0.0 |-- alt_name @@ -691,20 +482,7 @@ LABEL):: |-- type |-- uevent `-- uuid - /sys/devices/platform/nfit_test.0/ndbus0/region2/namespace2.0 - |-- alt_name - |-- devtype - |-- dpa_extents - |-- force_raw - |-- modalias - |-- numa_node - |-- sector_size - |-- size - |-- subsystem -> ../../../../../../bus/nd - |-- type - |-- uevent - `-- uuid - /sys/devices/platform/nfit_test.1/ndbus1/region6/namespace6.0 + /sys/devices/platform/nfit_test.1/ndbus1/region1/namespace1.0 |-- block | `-- pmem0 |-- devtype @@ -786,9 +564,9 @@ Why the Term "namespace"? LIBNVDIMM/LIBNDCTL: Block Translation Table "btt" ------------------------------------------------- -A BTT (design document: https://pmem.io/2014/09/23/btt.html) is a stacked -block device driver that fronts either the whole block device or a -partition of a block device emitted by either a PMEM or BLK NAMESPACE. +A BTT (design document: https://pmem.io/2014/09/23/btt.html) is a +personality driver for a namespace that fronts entire namespace as an +'address abstraction'. LIBNVDIMM: btt layout ^^^^^^^^^^^^^^^^^^^^^ @@ -815,7 +593,9 @@ LIBNDCTL: btt creation example Similar to namespaces an idle BTT device is automatically created per region. Each time this "seed" btt device is configured and enabled a new seed is created. Creating a BTT configuration involves two steps of -finding and idle BTT and assigning it to consume a PMEM or BLK namespace:: +finding and idle BTT and assigning it to consume a namespace. + +:: static struct ndctl_btt *get_idle_btt(struct ndctl_region *region) { @@ -863,25 +643,15 @@ For the given example above, here is the view of the objects as seen by the LIBNDCTL API:: +---+ - |CTX| +---------+ +--------------+ +---------------+ - +-+-+ +-> REGION0 +---> NAMESPACE0.0 +--> PMEM8 "pm0.0" | - | | +---------+ +--------------+ +---------------+ - +-------+ | | +---------+ +--------------+ +---------------+ - | DIMM0 <-+ | +-> REGION1 +---> NAMESPACE1.0 +--> PMEM6 "pm1.0" | - +-------+ | | | +---------+ +--------------+ +---------------+ + |CTX| + +-+-+ + | + +-------+ | + | DIMM0 <-+ | +---------+ +--------------+ +---------------+ + +-------+ | | +-> REGION0 +---> NAMESPACE0.0 +--> PMEM8 "pm0.0" | | DIMM1 <-+ +-v--+ | +---------+ +--------------+ +---------------+ - +-------+ +-+BUS0+---> REGION2 +-+-> NAMESPACE2.0 +--> ND6 "blk2.0" | - | DIMM2 <-+ +----+ | +---------+ | +--------------+ +----------------------+ - +-------+ | | +-> NAMESPACE2.1 +--> ND5 "blk2.1" | BTT2 | - | DIMM3 <-+ | +--------------+ +----------------------+ - +-------+ | +---------+ +--------------+ +---------------+ - +-> REGION3 +-+-> NAMESPACE3.0 +--> ND4 "blk3.0" | - | +---------+ | +--------------+ +----------------------+ - | +-> NAMESPACE3.1 +--> ND3 "blk3.1" | BTT1 | - | +--------------+ +----------------------+ - | +---------+ +--------------+ +---------------+ - +-> REGION4 +---> NAMESPACE4.0 +--> ND2 "blk4.0" | - | +---------+ +--------------+ +---------------+ - | +---------+ +--------------+ +----------------------+ - +-> REGION5 +---> NAMESPACE5.0 +--> ND1 "blk5.0" | BTT0 | - +---------+ +--------------+ +---------------+------+ + +-------+ +-+BUS0+-| +---------+ +--------------+ +----------------------+ + | DIMM2 <-+ +----+ +-> REGION1 +---> NAMESPACE1.0 +--> PMEM6 "pm1.0" | BTT1 | + +-------+ | | +---------+ +--------------+ +---------------+------+ + | DIMM3 <-+ + +-------+ diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index 347fe7afa583..5a29046e3319 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -10,12 +10,9 @@ menuconfig LIBNVDIMM ACPI-6-NFIT defined resources. On platforms that define an NFIT, or otherwise can discover NVDIMM resources, a libnvdimm bus is registered to advertise PMEM (persistent memory) - namespaces (/dev/pmemX) and BLK (sliding mmio window(s)) - namespaces (/dev/ndblkX.Y). A PMEM namespace refers to a + namespaces (/dev/pmemX). A PMEM namespace refers to a memory resource that may span multiple DIMMs and support DAX - (see CONFIG_DAX). A BLK namespace refers to an NVDIMM control - region which exposes an mmio register set for windowed access - mode to non-volatile memory. + (see CONFIG_DAX). if LIBNVDIMM @@ -38,19 +35,6 @@ config BLK_DEV_PMEM Say Y if you want to use an NVDIMM -config ND_BLK - tristate "BLK: Block data window (aperture) device support" - default LIBNVDIMM - select ND_BTT if BTT - help - Support NVDIMMs, or other devices, that implement a BLK-mode - access capability. BLK-mode access uses memory-mapped-i/o - apertures to access persistent media. - - Say Y if your platform firmware emits an ACPI.NFIT table - (CONFIG_ACPI_NFIT), or otherwise exposes BLK-mode - capabilities. - config ND_CLAIM bool @@ -67,9 +51,8 @@ config BTT applications that rely on sector writes not being torn (a guarantee that typical disks provide) can continue to do so. The BTT manifests itself as an alternate personality for an - NVDIMM namespace, i.e. a namespace can be in raw mode (pmemX, - ndblkX.Y, etc...), or 'sectored' mode, (pmemXs, ndblkX.Ys, - etc...). + NVDIMM namespace, i.e. a namespace can be in raw mode pmemX, + or 'sectored' mode. Select Y if unsure diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index 25dba6095612..3fb806748716 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -2,7 +2,6 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o obj-$(CONFIG_ND_BTT) += nd_btt.o -obj-$(CONFIG_ND_BLK) += nd_blk.o obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o obj-$(CONFIG_OF_PMEM) += of_pmem.o obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o @@ -11,8 +10,6 @@ nd_pmem-y := pmem.o nd_btt-y := btt.o -nd_blk-y := blk.o - nd_e820-y := e820.o libnvdimm-y := core.o diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c deleted file mode 100644 index 228c33b8d1d6..000000000000 --- a/drivers/nvdimm/blk.c +++ /dev/null @@ -1,335 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * NVDIMM Block Window Driver - * Copyright (c) 2014, Intel Corporation. - */ - -#include -#include -#include -#include -#include -#include -#include -#include "nd.h" - -static u32 nsblk_meta_size(struct nd_namespace_blk *nsblk) -{ - return nsblk->lbasize - ((nsblk->lbasize >= 4096) ? 4096 : 512); -} - -static u32 nsblk_internal_lbasize(struct nd_namespace_blk *nsblk) -{ - return roundup(nsblk->lbasize, INT_LBASIZE_ALIGNMENT); -} - -static u32 nsblk_sector_size(struct nd_namespace_blk *nsblk) -{ - return nsblk->lbasize - nsblk_meta_size(nsblk); -} - -static resource_size_t to_dev_offset(struct nd_namespace_blk *nsblk, - resource_size_t ns_offset, unsigned int len) -{ - int i; - - for (i = 0; i < nsblk->num_resources; i++) { - if (ns_offset < resource_size(nsblk->res[i])) { - if (ns_offset + len > resource_size(nsblk->res[i])) { - dev_WARN_ONCE(&nsblk->common.dev, 1, - "illegal request\n"); - return SIZE_MAX; - } - return nsblk->res[i]->start + ns_offset; - } - ns_offset -= resource_size(nsblk->res[i]); - } - - dev_WARN_ONCE(&nsblk->common.dev, 1, "request out of range\n"); - return SIZE_MAX; -} - -static struct nd_blk_region *to_ndbr(struct nd_namespace_blk *nsblk) -{ - struct nd_region *nd_region; - struct device *parent; - - parent = nsblk->common.dev.parent; - nd_region = container_of(parent, struct nd_region, dev); - return container_of(nd_region, struct nd_blk_region, nd_region); -} - -#ifdef CONFIG_BLK_DEV_INTEGRITY -static int nd_blk_rw_integrity(struct nd_namespace_blk *nsblk, - struct bio_integrity_payload *bip, u64 lba, int rw) -{ - struct nd_blk_region *ndbr = to_ndbr(nsblk); - unsigned int len = nsblk_meta_size(nsblk); - resource_size_t dev_offset, ns_offset; - u32 internal_lbasize, sector_size; - int err = 0; - - internal_lbasize = nsblk_internal_lbasize(nsblk); - sector_size = nsblk_sector_size(nsblk); - ns_offset = lba * internal_lbasize + sector_size; - dev_offset = to_dev_offset(nsblk, ns_offset, len); - if (dev_offset == SIZE_MAX) - return -EIO; - - while (len) { - unsigned int cur_len; - struct bio_vec bv; - void *iobuf; - - bv = bvec_iter_bvec(bip->bip_vec, bip->bip_iter); - /* - * The 'bv' obtained from bvec_iter_bvec has its .bv_len and - * .bv_offset already adjusted for iter->bi_bvec_done, and we - * can use those directly - */ - - cur_len = min(len, bv.bv_len); - iobuf = kmap_atomic(bv.bv_page); - err = ndbr->do_io(ndbr, dev_offset, iobuf + bv.bv_offset, - cur_len, rw); - kunmap_atomic(iobuf); - if (err) - return err; - - len -= cur_len; - dev_offset += cur_len; - if (!bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len)) - return -EIO; - } - - return err; -} - -#else /* CONFIG_BLK_DEV_INTEGRITY */ -static int nd_blk_rw_integrity(struct nd_namespace_blk *nsblk, - struct bio_integrity_payload *bip, u64 lba, int rw) -{ - return 0; -} -#endif - -static int nsblk_do_bvec(struct nd_namespace_blk *nsblk, - struct bio_integrity_payload *bip, struct page *page, - unsigned int len, unsigned int off, int rw, sector_t sector) -{ - struct nd_blk_region *ndbr = to_ndbr(nsblk); - resource_size_t dev_offset, ns_offset; - u32 internal_lbasize, sector_size; - int err = 0; - void *iobuf; - u64 lba; - - internal_lbasize = nsblk_internal_lbasize(nsblk); - sector_size = nsblk_sector_size(nsblk); - while (len) { - unsigned int cur_len; - - /* - * If we don't have an integrity payload, we don't have to - * split the bvec into sectors, as this would cause unnecessary - * Block Window setup/move steps. the do_io routine is capable - * of handling len <= PAGE_SIZE. - */ - cur_len = bip ? min(len, sector_size) : len; - - lba = div_u64(sector << SECTOR_SHIFT, sector_size); - ns_offset = lba * internal_lbasize; - dev_offset = to_dev_offset(nsblk, ns_offset, cur_len); - if (dev_offset == SIZE_MAX) - return -EIO; - - iobuf = kmap_atomic(page); - err = ndbr->do_io(ndbr, dev_offset, iobuf + off, cur_len, rw); - kunmap_atomic(iobuf); - if (err) - return err; - - if (bip) { - err = nd_blk_rw_integrity(nsblk, bip, lba, rw); - if (err) - return err; - } - len -= cur_len; - off += cur_len; - sector += sector_size >> SECTOR_SHIFT; - } - - return err; -} - -static void nd_blk_submit_bio(struct bio *bio) -{ - struct bio_integrity_payload *bip; - struct nd_namespace_blk *nsblk = bio->bi_bdev->bd_disk->private_data; - struct bvec_iter iter; - unsigned long start; - struct bio_vec bvec; - int err = 0, rw; - bool do_acct; - - if (!bio_integrity_prep(bio)) - return; - - bip = bio_integrity(bio); - rw = bio_data_dir(bio); - do_acct = blk_queue_io_stat(bio->bi_bdev->bd_disk->queue); - if (do_acct) - start = bio_start_io_acct(bio); - bio_for_each_segment(bvec, bio, iter) { - unsigned int len = bvec.bv_len; - - BUG_ON(len > PAGE_SIZE); - err = nsblk_do_bvec(nsblk, bip, bvec.bv_page, len, - bvec.bv_offset, rw, iter.bi_sector); - if (err) { - dev_dbg(&nsblk->common.dev, - "io error in %s sector %lld, len %d,\n", - (rw == READ) ? "READ" : "WRITE", - (unsigned long long) iter.bi_sector, len); - bio->bi_status = errno_to_blk_status(err); - break; - } - } - if (do_acct) - bio_end_io_acct(bio, start); - - bio_endio(bio); -} - -static int nsblk_rw_bytes(struct nd_namespace_common *ndns, - resource_size_t offset, void *iobuf, size_t n, int rw, - unsigned long flags) -{ - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(&ndns->dev); - struct nd_blk_region *ndbr = to_ndbr(nsblk); - resource_size_t dev_offset; - - dev_offset = to_dev_offset(nsblk, offset, n); - - if (unlikely(offset + n > nsblk->size)) { - dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n"); - return -EFAULT; - } - - if (dev_offset == SIZE_MAX) - return -EIO; - - return ndbr->do_io(ndbr, dev_offset, iobuf, n, rw); -} - -static const struct block_device_operations nd_blk_fops = { - .owner = THIS_MODULE, - .submit_bio = nd_blk_submit_bio, -}; - -static void nd_blk_release_disk(void *disk) -{ - del_gendisk(disk); - blk_cleanup_disk(disk); -} - -static int nsblk_attach_disk(struct nd_namespace_blk *nsblk) -{ - struct device *dev = &nsblk->common.dev; - resource_size_t available_disk_size; - struct gendisk *disk; - u64 internal_nlba; - int rc; - - internal_nlba = div_u64(nsblk->size, nsblk_internal_lbasize(nsblk)); - available_disk_size = internal_nlba * nsblk_sector_size(nsblk); - - disk = blk_alloc_disk(NUMA_NO_NODE); - if (!disk) - return -ENOMEM; - - disk->fops = &nd_blk_fops; - disk->private_data = nsblk; - nvdimm_namespace_disk_name(&nsblk->common, disk->disk_name); - - blk_queue_max_hw_sectors(disk->queue, UINT_MAX); - blk_queue_logical_block_size(disk->queue, nsblk_sector_size(nsblk)); - blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); - - if (nsblk_meta_size(nsblk)) { - rc = nd_integrity_init(disk, nsblk_meta_size(nsblk)); - - if (rc) - goto out_before_devm_err; - } - - set_capacity(disk, available_disk_size >> SECTOR_SHIFT); - rc = device_add_disk(dev, disk, NULL); - if (rc) - goto out_before_devm_err; - - /* nd_blk_release_disk() is called if this fails */ - if (devm_add_action_or_reset(dev, nd_blk_release_disk, disk)) - return -ENOMEM; - - nvdimm_check_and_set_ro(disk); - return 0; - -out_before_devm_err: - blk_cleanup_disk(disk); - return rc; -} - -static int nd_blk_probe(struct device *dev) -{ - struct nd_namespace_common *ndns; - struct nd_namespace_blk *nsblk; - - ndns = nvdimm_namespace_common_probe(dev); - if (IS_ERR(ndns)) - return PTR_ERR(ndns); - - nsblk = to_nd_namespace_blk(&ndns->dev); - nsblk->size = nvdimm_namespace_capacity(ndns); - dev_set_drvdata(dev, nsblk); - - ndns->rw_bytes = nsblk_rw_bytes; - if (is_nd_btt(dev)) - return nvdimm_namespace_attach_btt(ndns); - else if (nd_btt_probe(dev, ndns) == 0) { - /* we'll come back as btt-blk */ - return -ENXIO; - } else - return nsblk_attach_disk(nsblk); -} - -static void nd_blk_remove(struct device *dev) -{ - if (is_nd_btt(dev)) - nvdimm_namespace_detach_btt(to_nd_btt(dev)); -} - -static struct nd_device_driver nd_blk_driver = { - .probe = nd_blk_probe, - .remove = nd_blk_remove, - .drv = { - .name = "nd_blk", - }, - .type = ND_DRIVER_NAMESPACE_BLK, -}; - -static int __init nd_blk_init(void) -{ - return nd_driver_register(&nd_blk_driver); -} - -static void __exit nd_blk_exit(void) -{ - driver_unregister(&nd_blk_driver.drv); -} - -MODULE_AUTHOR("Ross Zwisler "); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_BLK); -module_init(nd_blk_init); -module_exit(nd_blk_exit); diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index c57d9e9d4480..5eb5c23b062f 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -27,7 +27,6 @@ ccflags-y += -I$(srctree)/drivers/acpi/nfit/ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o obj-$(CONFIG_ND_BTT) += nd_btt.o -obj-$(CONFIG_ND_BLK) += nd_blk.o obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o obj-$(CONFIG_ACPI_NFIT) += nfit.o ifeq ($(CONFIG_DAX),m) @@ -50,9 +49,6 @@ nd_pmem-y += config_check.o nd_btt-y := $(NVDIMM_SRC)/btt.o nd_btt-y += config_check.o -nd_blk-y := $(NVDIMM_SRC)/blk.o -nd_blk-y += config_check.o - nd_e820-y := $(NVDIMM_SRC)/e820.o nd_e820-y += config_check.o diff --git a/tools/testing/nvdimm/config_check.c b/tools/testing/nvdimm/config_check.c index 3e3a5f518864..baed75e2ccbc 100644 --- a/tools/testing/nvdimm/config_check.c +++ b/tools/testing/nvdimm/config_check.c @@ -11,7 +11,6 @@ void check(void) BUILD_BUG_ON(!IS_MODULE(CONFIG_BLK_DEV_PMEM)); BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BTT)); BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_PFN)); - BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BLK)); if (IS_ENABLED(CONFIG_ACPI_NFIT)) BUILD_BUG_ON(!IS_MODULE(CONFIG_ACPI_NFIT)); BUILD_BUG_ON(!IS_MODULE(CONFIG_DEV_DAX)); From fadc38a6672a72bfb2937e85bc5a967f7ab581f8 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 9 Mar 2022 19:49:32 -0800 Subject: [PATCH 07/14] nvdimm/namespace: Delete blk namespace consideration in shared paths Given is_namespace_blk() is never true outside of the NVDIMM unit tests delete the support from namespace device management. Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/164688417214.2879318.4698377272678028573.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/namespace_devs.c | 152 ++------------------------------ 1 file changed, 9 insertions(+), 143 deletions(-) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index b57a2d36c517..5c76547c9b84 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -46,7 +46,6 @@ static void namespace_blk_release(struct device *dev) } static bool is_namespace_pmem(const struct device *dev); -static bool is_namespace_blk(const struct device *dev); static bool is_namespace_io(const struct device *dev); static int is_uuid_busy(struct device *dev, void *data) @@ -57,10 +56,6 @@ static int is_uuid_busy(struct device *dev, void *data) struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); uuid2 = nspm->uuid; - } else if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - uuid2 = nsblk->uuid; } else if (is_nd_btt(dev)) { struct nd_btt *nd_btt = to_nd_btt(dev); @@ -178,12 +173,6 @@ const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns, else sprintf(name, "pmem%d%s", nd_region->id, suffix ? suffix : ""); - } else if (is_namespace_blk(&ndns->dev)) { - struct nd_namespace_blk *nsblk; - - nsblk = to_nd_namespace_blk(&ndns->dev); - sprintf(name, "ndblk%d.%d%s", nd_region->id, nsblk->id, - suffix ? suffix : ""); } else { return NULL; } @@ -201,10 +190,6 @@ const uuid_t *nd_dev_to_uuid(struct device *dev) struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); return nspm->uuid; - } else if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - return nsblk->uuid; } else return &uuid_null; } @@ -229,10 +214,6 @@ static ssize_t __alt_name_store(struct device *dev, const char *buf, struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); ns_altname = &nspm->alt_name; - } else if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - ns_altname = &nsblk->alt_name; } else return -ENXIO; @@ -264,24 +245,6 @@ out: return rc; } -static resource_size_t nd_namespace_blk_size(struct nd_namespace_blk *nsblk) -{ - struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent); - struct nd_mapping *nd_mapping = &nd_region->mapping[0]; - struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); - struct nd_label_id label_id; - resource_size_t size = 0; - struct resource *res; - - if (!nsblk->uuid) - return 0; - nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL); - for_each_dpa_resource(ndd, res) - if (strcmp(res->name, label_id.id) == 0) - size += resource_size(res); - return size; -} - static bool __nd_namespace_blk_validate(struct nd_namespace_blk *nsblk) { struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent); @@ -363,16 +326,6 @@ static int nd_namespace_label_update(struct nd_region *nd_region, return 0; return nd_pmem_namespace_label_update(nd_region, nspm, size); - } else if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - resource_size_t size = nd_namespace_blk_size(nsblk); - - if (size == 0 && nsblk->uuid) - /* delete allocation */; - else if (!nsblk->uuid || !nsblk->lbasize) - return 0; - - return nd_blk_namespace_label_update(nd_region, nsblk, size); } else return -ENXIO; } @@ -405,10 +358,6 @@ static ssize_t alt_name_show(struct device *dev, struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); ns_altname = nspm->alt_name; - } else if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - ns_altname = nsblk->alt_name; } else return -ENXIO; @@ -966,12 +915,6 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) uuid = nspm->uuid; id = nspm->id; - } else if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - uuid = nsblk->uuid; - flags = NSLABEL_FLAG_LOCAL; - id = nsblk->id; } /* @@ -1067,10 +1010,6 @@ static ssize_t size_store(struct device *dev, struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); uuid = &nspm->uuid; - } else if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - uuid = &nsblk->uuid; } if (rc == 0 && val == 0 && uuid) { @@ -1095,8 +1034,6 @@ resource_size_t __nvdimm_namespace_capacity(struct nd_namespace_common *ndns) struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); return resource_size(&nspm->nsio.res); - } else if (is_namespace_blk(dev)) { - return nd_namespace_blk_size(to_nd_namespace_blk(dev)); } else if (is_namespace_io(dev)) { struct nd_namespace_io *nsio = to_nd_namespace_io(dev); @@ -1152,12 +1089,8 @@ static uuid_t *namespace_to_uuid(struct device *dev) struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); return nspm->uuid; - } else if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - return nsblk->uuid; - } else - return ERR_PTR(-ENXIO); + } + return ERR_PTR(-ENXIO); } static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, @@ -1183,7 +1116,6 @@ static int namespace_update_uuid(struct nd_region *nd_region, struct device *dev, uuid_t *new_uuid, uuid_t **old_uuid) { - u32 flags = is_namespace_blk(dev) ? NSLABEL_FLAG_LOCAL : 0; struct nd_label_id old_label_id; struct nd_label_id new_label_id; int i; @@ -1214,8 +1146,8 @@ static int namespace_update_uuid(struct nd_region *nd_region, return -EBUSY; } - nd_label_gen_id(&old_label_id, *old_uuid, flags); - nd_label_gen_id(&new_label_id, new_uuid, flags); + nd_label_gen_id(&old_label_id, *old_uuid, 0); + nd_label_gen_id(&new_label_id, new_uuid, 0); for (i = 0; i < nd_region->ndr_mappings; i++) { struct nd_mapping *nd_mapping = &nd_region->mapping[i]; struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); @@ -1261,10 +1193,6 @@ static ssize_t uuid_store(struct device *dev, struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); ns_uuid = &nspm->uuid; - } else if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - ns_uuid = &nsblk->uuid; } else return -ENXIO; @@ -1321,13 +1249,6 @@ static const unsigned long pmem_lbasize_supported[] = { 512, 4096, 0 }; static ssize_t sector_size_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - return nd_size_select_show(nsblk->lbasize, - blk_lbasize_supported, buf); - } - if (is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); @@ -1345,12 +1266,7 @@ static ssize_t sector_size_store(struct device *dev, unsigned long *lbasize; ssize_t rc = 0; - if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - lbasize = &nsblk->lbasize; - supported = blk_lbasize_supported; - } else if (is_namespace_pmem(dev)) { + if (is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); lbasize = &nspm->lbasize; @@ -1390,11 +1306,6 @@ static ssize_t dpa_extents_show(struct device *dev, uuid = nspm->uuid; flags = 0; - } else if (is_namespace_blk(dev)) { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - uuid = nsblk->uuid; - flags = NSLABEL_FLAG_LOCAL; } if (!uuid) @@ -1627,10 +1538,7 @@ static umode_t namespace_visible(struct kobject *kobj, { struct device *dev = container_of(kobj, struct device, kobj); - if (a == &dev_attr_resource.attr && is_namespace_blk(dev)) - return 0; - - if (is_namespace_pmem(dev) || is_namespace_blk(dev)) { + if (is_namespace_pmem(dev)) { if (a == &dev_attr_size.attr) return 0644; @@ -1682,11 +1590,6 @@ static bool is_namespace_pmem(const struct device *dev) return dev ? dev->type == &namespace_pmem_device_type : false; } -static bool is_namespace_blk(const struct device *dev) -{ - return dev ? dev->type == &namespace_blk_device_type : false; -} - static bool is_namespace_io(const struct device *dev) { return dev ? dev->type == &namespace_io_device_type : false; @@ -1769,18 +1672,6 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev) nspm = to_nd_namespace_pmem(&ndns->dev); if (uuid_not_set(nspm->uuid, &ndns->dev, __func__)) return ERR_PTR(-ENODEV); - } else if (is_namespace_blk(&ndns->dev)) { - struct nd_namespace_blk *nsblk; - - nsblk = to_nd_namespace_blk(&ndns->dev); - if (uuid_not_set(nsblk->uuid, &ndns->dev, __func__)) - return ERR_PTR(-ENODEV); - if (!nsblk->lbasize) { - dev_dbg(&ndns->dev, "sector size not set\n"); - return ERR_PTR(-ENODEV); - } - if (!nd_namespace_blk_validate(nsblk)) - return ERR_PTR(-ENODEV); } return ndns; @@ -1790,16 +1681,12 @@ EXPORT_SYMBOL(nvdimm_namespace_common_probe); int devm_namespace_enable(struct device *dev, struct nd_namespace_common *ndns, resource_size_t size) { - if (is_namespace_blk(&ndns->dev)) - return 0; return devm_nsio_enable(dev, to_nd_namespace_io(&ndns->dev), size); } EXPORT_SYMBOL_GPL(devm_namespace_enable); void devm_namespace_disable(struct device *dev, struct nd_namespace_common *ndns) { - if (is_namespace_blk(&ndns->dev)) - return; devm_nsio_disable(dev, to_nd_namespace_io(&ndns->dev)); } EXPORT_SYMBOL_GPL(devm_namespace_disable); @@ -2225,7 +2112,6 @@ static int add_namespace_resource(struct nd_region *nd_region, for (i = 0; i < count; i++) { uuid_t *uuid = namespace_to_uuid(devs[i]); - struct resource *res; if (IS_ERR(uuid)) { WARN_ON(1); @@ -2234,20 +2120,9 @@ static int add_namespace_resource(struct nd_region *nd_region, if (!nsl_uuid_equal(ndd, nd_label, uuid)) continue; - if (is_namespace_blk(devs[i])) { - res = nsblk_add_resource(nd_region, ndd, - to_nd_namespace_blk(devs[i]), - nsl_get_dpa(ndd, nd_label)); - if (!res) - return -ENXIO; - nd_dbg_dpa(nd_region, ndd, res, "%d assign\n", count); - } else { - dev_err(&nd_region->dev, - "error: conflicting extents for uuid: %pUb\n", - uuid); - return -ENXIO; - } - break; + dev_err(&nd_region->dev, + "error: conflicting extents for uuid: %pUb\n", uuid); + return -ENXIO; } return i; @@ -2305,20 +2180,11 @@ static int cmp_dpa(const void *a, const void *b) { const struct device *dev_a = *(const struct device **) a; const struct device *dev_b = *(const struct device **) b; - struct nd_namespace_blk *nsblk_a, *nsblk_b; struct nd_namespace_pmem *nspm_a, *nspm_b; if (is_namespace_io(dev_a)) return 0; - if (is_namespace_blk(dev_a)) { - nsblk_a = to_nd_namespace_blk(dev_a); - nsblk_b = to_nd_namespace_blk(dev_b); - - return memcmp(&nsblk_a->res[0]->start, &nsblk_b->res[0]->start, - sizeof(resource_size_t)); - } - nspm_a = to_nd_namespace_pmem(dev_a); nspm_b = to_nd_namespace_pmem(dev_b); From 84bd3690bf54a2f2f3b8449afa022aac1957ba17 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 9 Mar 2022 19:49:37 -0800 Subject: [PATCH 08/14] nvdimm/namespace: Delete nd_namespace_blk Now that none of the configuration paths consider BLK namespaces, delete the BLK namespace data and supporting code. Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/164688417727.2879318.11691110761800109662.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/label.c | 340 -------------------------------- drivers/nvdimm/label.h | 3 - drivers/nvdimm/namespace_devs.c | 227 ++------------------- drivers/nvdimm/nd-core.h | 3 - drivers/nvdimm/nd.h | 1 - include/linux/nd.h | 26 --- 6 files changed, 13 insertions(+), 587 deletions(-) diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c index 5ec9a4023df9..8c972bcb2ac3 100644 --- a/drivers/nvdimm/label.c +++ b/drivers/nvdimm/label.c @@ -968,326 +968,6 @@ static int __pmem_label_update(struct nd_region *nd_region, return rc; } -static bool is_old_resource(struct resource *res, struct resource **list, int n) -{ - int i; - - if (res->flags & DPA_RESOURCE_ADJUSTED) - return false; - for (i = 0; i < n; i++) - if (res == list[i]) - return true; - return false; -} - -static struct resource *to_resource(struct nvdimm_drvdata *ndd, - struct nd_namespace_label *nd_label) -{ - struct resource *res; - - for_each_dpa_resource(ndd, res) { - if (res->start != nsl_get_dpa(ndd, nd_label)) - continue; - if (resource_size(res) != nsl_get_rawsize(ndd, nd_label)) - continue; - return res; - } - - return NULL; -} - -/* - * Use the presence of the type_guid as a flag to determine isetcookie - * usage and nlabel + position policy for blk-aperture namespaces. - */ -static void nsl_set_blk_isetcookie(struct nvdimm_drvdata *ndd, - struct nd_namespace_label *nd_label, - u64 isetcookie) -{ - if (efi_namespace_label_has(ndd, type_guid)) { - nsl_set_isetcookie(ndd, nd_label, isetcookie); - return; - } - nsl_set_isetcookie(ndd, nd_label, 0); /* N/A */ -} - -bool nsl_validate_blk_isetcookie(struct nvdimm_drvdata *ndd, - struct nd_namespace_label *nd_label, - u64 isetcookie) -{ - if (!efi_namespace_label_has(ndd, type_guid)) - return true; - - if (nsl_get_isetcookie(ndd, nd_label) != isetcookie) { - dev_dbg(ndd->dev, "expect cookie %#llx got %#llx\n", isetcookie, - nsl_get_isetcookie(ndd, nd_label)); - return false; - } - - return true; -} - -static void nsl_set_blk_nlabel(struct nvdimm_drvdata *ndd, - struct nd_namespace_label *nd_label, int nlabel, - bool first) -{ - if (!efi_namespace_label_has(ndd, type_guid)) { - nsl_set_nlabel(ndd, nd_label, 0); /* N/A */ - return; - } - nsl_set_nlabel(ndd, nd_label, first ? nlabel : 0xffff); -} - -static void nsl_set_blk_position(struct nvdimm_drvdata *ndd, - struct nd_namespace_label *nd_label, - bool first) -{ - if (!efi_namespace_label_has(ndd, type_guid)) { - nsl_set_position(ndd, nd_label, 0); - return; - } - nsl_set_position(ndd, nd_label, first ? 0 : 0xffff); -} - -/* - * 1/ Account all the labels that can be freed after this update - * 2/ Allocate and write the label to the staging (next) index - * 3/ Record the resources in the namespace device - */ -static int __blk_label_update(struct nd_region *nd_region, - struct nd_mapping *nd_mapping, struct nd_namespace_blk *nsblk, - int num_labels) -{ - int i, alloc, victims, nfree, old_num_resources, nlabel, rc = -ENXIO; - struct nd_interleave_set *nd_set = nd_region->nd_set; - struct nd_namespace_common *ndns = &nsblk->common; - struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); - struct nd_namespace_label *nd_label; - struct nd_label_ent *label_ent, *e; - struct nd_namespace_index *nsindex; - unsigned long *free, *victim_map = NULL; - struct resource *res, **old_res_list; - struct nd_label_id label_id; - int min_dpa_idx = 0; - LIST_HEAD(list); - u32 nslot, slot; - - if (!preamble_next(ndd, &nsindex, &free, &nslot)) - return -ENXIO; - - old_res_list = nsblk->res; - nfree = nd_label_nfree(ndd); - old_num_resources = nsblk->num_resources; - nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL); - - /* - * We need to loop over the old resources a few times, which seems a - * bit inefficient, but we need to know that we have the label - * space before we start mutating the tracking structures. - * Otherwise the recovery method of last resort for userspace is - * disable and re-enable the parent region. - */ - alloc = 0; - for_each_dpa_resource(ndd, res) { - if (strcmp(res->name, label_id.id) != 0) - continue; - if (!is_old_resource(res, old_res_list, old_num_resources)) - alloc++; - } - - victims = 0; - if (old_num_resources) { - /* convert old local-label-map to dimm-slot victim-map */ - victim_map = bitmap_zalloc(nslot, GFP_KERNEL); - if (!victim_map) - return -ENOMEM; - - /* mark unused labels for garbage collection */ - for_each_clear_bit_le(slot, free, nslot) { - nd_label = to_label(ndd, slot); - if (!nsl_uuid_equal(ndd, nd_label, nsblk->uuid)) - continue; - res = to_resource(ndd, nd_label); - if (res && is_old_resource(res, old_res_list, - old_num_resources)) - continue; - slot = to_slot(ndd, nd_label); - set_bit(slot, victim_map); - victims++; - } - } - - /* don't allow updates that consume the last label */ - if (nfree - alloc < 0 || nfree - alloc + victims < 1) { - dev_info(&nsblk->common.dev, "insufficient label space\n"); - bitmap_free(victim_map); - return -ENOSPC; - } - /* from here on we need to abort on error */ - - - /* assign all resources to the namespace before writing the labels */ - nsblk->res = NULL; - nsblk->num_resources = 0; - for_each_dpa_resource(ndd, res) { - if (strcmp(res->name, label_id.id) != 0) - continue; - if (!nsblk_add_resource(nd_region, ndd, nsblk, res->start)) { - rc = -ENOMEM; - goto abort; - } - } - - /* release slots associated with any invalidated UUIDs */ - mutex_lock(&nd_mapping->lock); - list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) - if (test_and_clear_bit(ND_LABEL_REAP, &label_ent->flags)) { - reap_victim(nd_mapping, label_ent); - list_move(&label_ent->list, &list); - } - mutex_unlock(&nd_mapping->lock); - - /* - * Find the resource associated with the first label in the set - * per the v1.2 namespace specification. - */ - for (i = 0; i < nsblk->num_resources; i++) { - struct resource *min = nsblk->res[min_dpa_idx]; - - res = nsblk->res[i]; - if (res->start < min->start) - min_dpa_idx = i; - } - - for (i = 0; i < nsblk->num_resources; i++) { - size_t offset; - - res = nsblk->res[i]; - if (is_old_resource(res, old_res_list, old_num_resources)) - continue; /* carry-over */ - slot = nd_label_alloc_slot(ndd); - if (slot == UINT_MAX) { - rc = -ENXIO; - goto abort; - } - dev_dbg(ndd->dev, "allocated: %d\n", slot); - - nd_label = to_label(ndd, slot); - memset(nd_label, 0, sizeof_namespace_label(ndd)); - nsl_set_uuid(ndd, nd_label, nsblk->uuid); - nsl_set_name(ndd, nd_label, nsblk->alt_name); - nsl_set_flags(ndd, nd_label, NSLABEL_FLAG_LOCAL); - - nsl_set_blk_nlabel(ndd, nd_label, nsblk->num_resources, - i == min_dpa_idx); - nsl_set_blk_position(ndd, nd_label, i == min_dpa_idx); - nsl_set_blk_isetcookie(ndd, nd_label, nd_set->cookie2); - - nsl_set_dpa(ndd, nd_label, res->start); - nsl_set_rawsize(ndd, nd_label, resource_size(res)); - nsl_set_lbasize(ndd, nd_label, nsblk->lbasize); - nsl_set_slot(ndd, nd_label, slot); - nsl_set_type_guid(ndd, nd_label, &nd_set->type_guid); - nsl_set_claim_class(ndd, nd_label, ndns->claim_class); - nsl_calculate_checksum(ndd, nd_label); - - /* update label */ - offset = nd_label_offset(ndd, nd_label); - rc = nvdimm_set_config_data(ndd, offset, nd_label, - sizeof_namespace_label(ndd)); - if (rc < 0) - goto abort; - } - - /* free up now unused slots in the new index */ - for_each_set_bit(slot, victim_map, victim_map ? nslot : 0) { - dev_dbg(ndd->dev, "free: %d\n", slot); - nd_label_free_slot(ndd, slot); - } - - /* update index */ - rc = nd_label_write_index(ndd, ndd->ns_next, - nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0); - if (rc) - goto abort; - - /* - * Now that the on-dimm labels are up to date, fix up the tracking - * entries in nd_mapping->labels - */ - nlabel = 0; - mutex_lock(&nd_mapping->lock); - list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) { - nd_label = label_ent->label; - if (!nd_label) - continue; - nlabel++; - if (!nsl_uuid_equal(ndd, nd_label, nsblk->uuid)) - continue; - nlabel--; - list_move(&label_ent->list, &list); - label_ent->label = NULL; - } - list_splice_tail_init(&list, &nd_mapping->labels); - mutex_unlock(&nd_mapping->lock); - - if (nlabel + nsblk->num_resources > num_labels) { - /* - * Bug, we can't end up with more resources than - * available labels - */ - WARN_ON_ONCE(1); - rc = -ENXIO; - goto out; - } - - mutex_lock(&nd_mapping->lock); - label_ent = list_first_entry_or_null(&nd_mapping->labels, - typeof(*label_ent), list); - if (!label_ent) { - WARN_ON(1); - mutex_unlock(&nd_mapping->lock); - rc = -ENXIO; - goto out; - } - for_each_clear_bit_le(slot, free, nslot) { - nd_label = to_label(ndd, slot); - if (!nsl_uuid_equal(ndd, nd_label, nsblk->uuid)) - continue; - res = to_resource(ndd, nd_label); - res->flags &= ~DPA_RESOURCE_ADJUSTED; - dev_vdbg(&nsblk->common.dev, "assign label slot: %d\n", slot); - list_for_each_entry_from(label_ent, &nd_mapping->labels, list) { - if (label_ent->label) - continue; - label_ent->label = nd_label; - nd_label = NULL; - break; - } - if (nd_label) - dev_WARN(&nsblk->common.dev, - "failed to track label slot%d\n", slot); - } - mutex_unlock(&nd_mapping->lock); - - out: - kfree(old_res_list); - bitmap_free(victim_map); - return rc; - - abort: - /* - * 1/ repair the allocated label bitmap in the index - * 2/ restore the resource list - */ - nd_label_copy(ndd, nsindex, to_current_namespace_index(ndd)); - kfree(nsblk->res); - nsblk->res = old_res_list; - nsblk->num_resources = old_num_resources; - old_res_list = NULL; - goto out; -} - static int init_labels(struct nd_mapping *nd_mapping, int num_labels) { int i, old_num_labels = 0; @@ -1425,26 +1105,6 @@ int nd_pmem_namespace_label_update(struct nd_region *nd_region, return 0; } -int nd_blk_namespace_label_update(struct nd_region *nd_region, - struct nd_namespace_blk *nsblk, resource_size_t size) -{ - struct nd_mapping *nd_mapping = &nd_region->mapping[0]; - struct resource *res; - int count = 0; - - if (size == 0) - return del_labels(nd_mapping, nsblk->uuid); - - for_each_dpa_resource(to_ndd(nd_mapping), res) - count++; - - count = init_labels(nd_mapping, count); - if (count < 0) - return count; - - return __blk_label_update(nd_region, nd_mapping, nsblk, count); -} - int __init nd_label_init(void) { WARN_ON(guid_parse(NVDIMM_BTT_GUID, &nvdimm_btt_guid)); diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h index 8ee248fc214f..198ef1df298b 100644 --- a/drivers/nvdimm/label.h +++ b/drivers/nvdimm/label.h @@ -221,9 +221,6 @@ bool nd_label_free_slot(struct nvdimm_drvdata *ndd, u32 slot); u32 nd_label_nfree(struct nvdimm_drvdata *ndd); struct nd_region; struct nd_namespace_pmem; -struct nd_namespace_blk; int nd_pmem_namespace_label_update(struct nd_region *nd_region, struct nd_namespace_pmem *nspm, resource_size_t size); -int nd_blk_namespace_label_update(struct nd_region *nd_region, - struct nd_namespace_blk *nsblk, resource_size_t size); #endif /* __LABEL_H__ */ diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 5c76547c9b84..d1c190b02657 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -32,19 +32,6 @@ static void namespace_pmem_release(struct device *dev) kfree(nspm); } -static void namespace_blk_release(struct device *dev) -{ - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - struct nd_region *nd_region = to_nd_region(dev->parent); - - if (nsblk->id >= 0) - ida_simple_remove(&nd_region->ns_ida, nsblk->id); - kfree(nsblk->alt_name); - kfree(nsblk->uuid); - kfree(nsblk->res); - kfree(nsblk); -} - static bool is_namespace_pmem(const struct device *dev); static bool is_namespace_io(const struct device *dev); @@ -245,65 +232,6 @@ out: return rc; } -static bool __nd_namespace_blk_validate(struct nd_namespace_blk *nsblk) -{ - struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent); - struct nd_mapping *nd_mapping = &nd_region->mapping[0]; - struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); - struct nd_label_id label_id; - struct resource *res; - int count, i; - - if (!nsblk->uuid || !nsblk->lbasize || !ndd) - return false; - - count = 0; - nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL); - for_each_dpa_resource(ndd, res) { - if (strcmp(res->name, label_id.id) != 0) - continue; - /* - * Resources with unacknowledged adjustments indicate a - * failure to update labels - */ - if (res->flags & DPA_RESOURCE_ADJUSTED) - return false; - count++; - } - - /* These values match after a successful label update */ - if (count != nsblk->num_resources) - return false; - - for (i = 0; i < nsblk->num_resources; i++) { - struct resource *found = NULL; - - for_each_dpa_resource(ndd, res) - if (res == nsblk->res[i]) { - found = res; - break; - } - /* stale resource */ - if (!found) - return false; - } - - return true; -} - -resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk) -{ - resource_size_t size; - - nvdimm_bus_lock(&nsblk->common.dev); - size = __nd_namespace_blk_validate(nsblk); - nvdimm_bus_unlock(&nsblk->common.dev); - - return size; -} -EXPORT_SYMBOL(nd_namespace_blk_validate); - - static int nd_namespace_label_update(struct nd_region *nd_region, struct device *dev) { @@ -1579,12 +1507,6 @@ static const struct device_type namespace_pmem_device_type = { .groups = nd_namespace_attribute_groups, }; -static const struct device_type namespace_blk_device_type = { - .name = "nd_namespace_blk", - .release = namespace_blk_release, - .groups = nd_namespace_attribute_groups, -}; - static bool is_namespace_pmem(const struct device *dev) { return dev ? dev->type == &namespace_pmem_device_type : false; @@ -1964,54 +1886,6 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, return ERR_PTR(rc); } -struct resource *nsblk_add_resource(struct nd_region *nd_region, - struct nvdimm_drvdata *ndd, struct nd_namespace_blk *nsblk, - resource_size_t start) -{ - struct nd_label_id label_id; - struct resource *res; - - nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL); - res = krealloc(nsblk->res, - sizeof(void *) * (nsblk->num_resources + 1), - GFP_KERNEL); - if (!res) - return NULL; - nsblk->res = (struct resource **) res; - for_each_dpa_resource(ndd, res) - if (strcmp(res->name, label_id.id) == 0 - && res->start == start) { - nsblk->res[nsblk->num_resources++] = res; - return res; - } - return NULL; -} - -static struct device *nd_namespace_blk_create(struct nd_region *nd_region) -{ - struct nd_namespace_blk *nsblk; - struct device *dev; - - if (!is_nd_blk(&nd_region->dev)) - return NULL; - - nsblk = kzalloc(sizeof(*nsblk), GFP_KERNEL); - if (!nsblk) - return NULL; - - dev = &nsblk->common.dev; - dev->type = &namespace_blk_device_type; - nsblk->id = ida_simple_get(&nd_region->ns_ida, 0, 0, GFP_KERNEL); - if (nsblk->id < 0) { - kfree(nsblk); - return NULL; - } - dev_set_name(dev, "namespace%d.%d", nd_region->id, nsblk->id); - dev->parent = &nd_region->dev; - - return &nsblk->common.dev; -} - static struct device *nd_namespace_pmem_create(struct nd_region *nd_region) { struct nd_namespace_pmem *nspm; @@ -2050,10 +1924,7 @@ void nd_region_create_ns_seed(struct nd_region *nd_region) if (nd_region_to_nstype(nd_region) == ND_DEVICE_NAMESPACE_IO) return; - if (is_nd_blk(&nd_region->dev)) - nd_region->ns_seed = nd_namespace_blk_create(nd_region); - else - nd_region->ns_seed = nd_namespace_pmem_create(nd_region); + nd_region->ns_seed = nd_namespace_pmem_create(nd_region); /* * Seed creation failures are not fatal, provisioning is simply @@ -2128,54 +1999,6 @@ static int add_namespace_resource(struct nd_region *nd_region, return i; } -static struct device *create_namespace_blk(struct nd_region *nd_region, - struct nd_namespace_label *nd_label, int count) -{ - - struct nd_mapping *nd_mapping = &nd_region->mapping[0]; - struct nd_interleave_set *nd_set = nd_region->nd_set; - struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); - struct nd_namespace_blk *nsblk; - char name[NSLABEL_NAME_LEN]; - struct device *dev = NULL; - struct resource *res; - uuid_t uuid; - - if (!nsl_validate_type_guid(ndd, nd_label, &nd_set->type_guid)) - return ERR_PTR(-EAGAIN); - if (!nsl_validate_blk_isetcookie(ndd, nd_label, nd_set->cookie2)) - return ERR_PTR(-EAGAIN); - - nsblk = kzalloc(sizeof(*nsblk), GFP_KERNEL); - if (!nsblk) - return ERR_PTR(-ENOMEM); - dev = &nsblk->common.dev; - dev->type = &namespace_blk_device_type; - dev->parent = &nd_region->dev; - nsblk->id = -1; - nsblk->lbasize = nsl_get_lbasize(ndd, nd_label); - nsl_get_uuid(ndd, nd_label, &uuid); - nsblk->uuid = kmemdup(&uuid, sizeof(uuid_t), GFP_KERNEL); - nsblk->common.claim_class = nsl_get_claim_class(ndd, nd_label); - if (!nsblk->uuid) - goto blk_err; - nsl_get_name(ndd, nd_label, name); - if (name[0]) { - nsblk->alt_name = kmemdup(name, NSLABEL_NAME_LEN, GFP_KERNEL); - if (!nsblk->alt_name) - goto blk_err; - } - res = nsblk_add_resource(nd_region, ndd, nsblk, - nsl_get_dpa(ndd, nd_label)); - if (!res) - goto blk_err; - nd_dbg_dpa(nd_region, ndd, res, "%d: assign\n", count); - return dev; - blk_err: - namespace_blk_release(dev); - return ERR_PTR(-ENXIO); -} - static int cmp_dpa(const void *a, const void *b) { const struct device *dev_a = *(const struct device **) a; @@ -2233,12 +2056,7 @@ static struct device **scan_labels(struct nd_region *nd_region) kfree(devs); devs = __devs; - if (is_nd_blk(&nd_region->dev)) - dev = create_namespace_blk(nd_region, nd_label, count); - else - dev = create_namespace_pmem(nd_region, nd_mapping, - nd_label); - + dev = create_namespace_pmem(nd_region, nd_mapping, nd_label); if (IS_ERR(dev)) { switch (PTR_ERR(dev)) { case -EAGAIN: @@ -2260,30 +2078,21 @@ static struct device **scan_labels(struct nd_region *nd_region) ? "blk" : "pmem", count == 1 ? "" : "s"); if (count == 0) { + struct nd_namespace_pmem *nspm; + /* Publish a zero-sized namespace for userspace to configure. */ nd_mapping_free_labels(nd_mapping); devs = kcalloc(2, sizeof(dev), GFP_KERNEL); if (!devs) goto err; - if (is_nd_blk(&nd_region->dev)) { - struct nd_namespace_blk *nsblk; - nsblk = kzalloc(sizeof(*nsblk), GFP_KERNEL); - if (!nsblk) - goto err; - dev = &nsblk->common.dev; - dev->type = &namespace_blk_device_type; - } else { - struct nd_namespace_pmem *nspm; - - nspm = kzalloc(sizeof(*nspm), GFP_KERNEL); - if (!nspm) - goto err; - dev = &nspm->nsio.common.dev; - dev->type = &namespace_pmem_device_type; - nd_namespace_pmem_set_resource(nd_region, nspm, 0); - } + nspm = kzalloc(sizeof(*nspm), GFP_KERNEL); + if (!nspm) + goto err; + dev = &nspm->nsio.common.dev; + dev->type = &namespace_pmem_device_type; + nd_namespace_pmem_set_resource(nd_region, nspm, 0); dev->parent = &nd_region->dev; devs[count++] = dev; } else if (is_memory(&nd_region->dev)) { @@ -2318,10 +2127,7 @@ static struct device **scan_labels(struct nd_region *nd_region) err: if (devs) { for (i = 0; devs[i]; i++) - if (is_nd_blk(&nd_region->dev)) - namespace_blk_release(devs[i]); - else - namespace_pmem_release(devs[i]); + namespace_pmem_release(devs[i]); kfree(devs); } return NULL; @@ -2484,19 +2290,12 @@ int nd_region_register_namespaces(struct nd_region *nd_region, int *err) struct device *dev = devs[i]; int id; - if (type == ND_DEVICE_NAMESPACE_BLK) { - struct nd_namespace_blk *nsblk; - - nsblk = to_nd_namespace_blk(dev); - id = ida_simple_get(&nd_region->ns_ida, 0, 0, - GFP_KERNEL); - nsblk->id = id; - } else if (type == ND_DEVICE_NAMESPACE_PMEM) { + if (type == ND_DEVICE_NAMESPACE_PMEM) { struct nd_namespace_pmem *nspm; nspm = to_nd_namespace_pmem(dev); id = ida_simple_get(&nd_region->ns_ida, 0, 0, - GFP_KERNEL); + GFP_KERNEL); nspm->id = id; } else id = i; diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index a11850dd475d..e4af0719cf33 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -150,9 +150,6 @@ int nd_region_conflict(struct nd_region *nd_region, resource_size_t start, resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd, struct nd_label_id *label_id); int alias_dpa_busy(struct device *dev, void *data); -struct resource *nsblk_add_resource(struct nd_region *nd_region, - struct nvdimm_drvdata *ndd, struct nd_namespace_blk *nsblk, - resource_size_t start); int nvdimm_num_label_slots(struct nvdimm_drvdata *ndd); void get_ndd(struct nvdimm_drvdata *ndd); resource_size_t __nvdimm_namespace_capacity(struct nd_namespace_common *ndns); diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 6f8ce114032d..8391bf2729bc 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -687,7 +687,6 @@ static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector, return false; } -resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk); const uuid_t *nd_dev_to_uuid(struct device *dev); bool pmem_should_map_pages(struct device *dev); #endif /* __ND_H__ */ diff --git a/include/linux/nd.h b/include/linux/nd.h index 4813c7089e5c..7b2ccbdc1cbc 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -136,27 +136,6 @@ struct nd_namespace_pmem { int id; }; -/** - * struct nd_namespace_blk - namespace for dimm-bounded persistent memory - * @alt_name: namespace name supplied in the dimm label - * @uuid: namespace name supplied in the dimm label - * @id: ida allocated id - * @lbasize: blk namespaces have a native sector size when btt not present - * @size: sum of all the resource ranges allocated to this namespace - * @num_resources: number of dpa extents to claim - * @res: discontiguous dpa extents for given dimm - */ -struct nd_namespace_blk { - struct nd_namespace_common common; - char *alt_name; - uuid_t *uuid; - int id; - unsigned long lbasize; - resource_size_t size; - int num_resources; - struct resource **res; -}; - static inline struct nd_namespace_io *to_nd_namespace_io(const struct device *dev) { return container_of(dev, struct nd_namespace_io, common.dev); @@ -169,11 +148,6 @@ static inline struct nd_namespace_pmem *to_nd_namespace_pmem(const struct device return container_of(nsio, struct nd_namespace_pmem, nsio); } -static inline struct nd_namespace_blk *to_nd_namespace_blk(const struct device *dev) -{ - return container_of(dev, struct nd_namespace_blk, common.dev); -} - /** * nvdimm_read_bytes() - synchronously read bytes from an nvdimm namespace * @ndns: device to read From a4b96046a8823a796b28e713ecc8ec535f5e4607 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 9 Mar 2022 19:49:42 -0800 Subject: [PATCH 09/14] ACPI: NFIT: Remove block aperture support Delete the code to parse interleave-descriptor-tables and coordinate I/O through a BLK aperture. Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/164688418240.2879318.400185926874596938.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/acpi/nfit/core.c | 376 ------------------------------- drivers/acpi/nfit/nfit.h | 6 - tools/testing/nvdimm/test/nfit.c | 23 -- 3 files changed, 405 deletions(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index e5d7f2bda13f..bea6a219fddd 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -999,80 +999,6 @@ static void *add_table(struct acpi_nfit_desc *acpi_desc, return table + hdr->length; } -static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc, - struct nfit_mem *nfit_mem) -{ - u32 device_handle = __to_nfit_memdev(nfit_mem)->device_handle; - u16 dcr = nfit_mem->dcr->region_index; - struct nfit_spa *nfit_spa; - - list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { - u16 range_index = nfit_spa->spa->range_index; - int type = nfit_spa_type(nfit_spa->spa); - struct nfit_memdev *nfit_memdev; - - if (type != NFIT_SPA_BDW) - continue; - - list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { - if (nfit_memdev->memdev->range_index != range_index) - continue; - if (nfit_memdev->memdev->device_handle != device_handle) - continue; - if (nfit_memdev->memdev->region_index != dcr) - continue; - - nfit_mem->spa_bdw = nfit_spa->spa; - return; - } - } - - dev_dbg(acpi_desc->dev, "SPA-BDW not found for SPA-DCR %d\n", - nfit_mem->spa_dcr->range_index); - nfit_mem->bdw = NULL; -} - -static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc, - struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa) -{ - u16 dcr = __to_nfit_memdev(nfit_mem)->region_index; - struct nfit_memdev *nfit_memdev; - struct nfit_bdw *nfit_bdw; - struct nfit_idt *nfit_idt; - u16 idt_idx, range_index; - - list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) { - if (nfit_bdw->bdw->region_index != dcr) - continue; - nfit_mem->bdw = nfit_bdw->bdw; - break; - } - - if (!nfit_mem->bdw) - return; - - nfit_mem_find_spa_bdw(acpi_desc, nfit_mem); - - if (!nfit_mem->spa_bdw) - return; - - range_index = nfit_mem->spa_bdw->range_index; - list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { - if (nfit_memdev->memdev->range_index != range_index || - nfit_memdev->memdev->region_index != dcr) - continue; - nfit_mem->memdev_bdw = nfit_memdev->memdev; - idt_idx = nfit_memdev->memdev->interleave_index; - list_for_each_entry(nfit_idt, &acpi_desc->idts, list) { - if (nfit_idt->idt->interleave_index != idt_idx) - continue; - nfit_mem->idt_bdw = nfit_idt->idt; - break; - } - break; - } -} - static int __nfit_mem_init(struct acpi_nfit_desc *acpi_desc, struct acpi_nfit_system_address *spa) { @@ -1189,7 +1115,6 @@ static int __nfit_mem_init(struct acpi_nfit_desc *acpi_desc, nfit_mem->idt_dcr = nfit_idt->idt; break; } - nfit_mem_init_bdw(acpi_desc, nfit_mem, spa); } else if (type == NFIT_SPA_PM) { /* * A single dimm may belong to multiple SPA-PM @@ -1532,8 +1457,6 @@ static int num_nvdimm_formats(struct nvdimm *nvdimm) if (nfit_mem->memdev_pmem) formats++; - if (nfit_mem->memdev_bdw) - formats++; return formats; } @@ -2079,11 +2002,6 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) continue; } - if (nfit_mem->bdw && nfit_mem->memdev_pmem) { - set_bit(NDD_ALIASING, &flags); - set_bit(NDD_LABELING, &flags); - } - /* collate flags across all memdevs for this dimm */ list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { struct acpi_nfit_memory_map *dimm_memdev; @@ -2429,272 +2347,6 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc, return 0; } -static u64 to_interleave_offset(u64 offset, struct nfit_blk_mmio *mmio) -{ - struct acpi_nfit_interleave *idt = mmio->idt; - u32 sub_line_offset, line_index, line_offset; - u64 line_no, table_skip_count, table_offset; - - line_no = div_u64_rem(offset, mmio->line_size, &sub_line_offset); - table_skip_count = div_u64_rem(line_no, mmio->num_lines, &line_index); - line_offset = idt->line_offset[line_index] - * mmio->line_size; - table_offset = table_skip_count * mmio->table_size; - - return mmio->base_offset + line_offset + table_offset + sub_line_offset; -} - -static u32 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw) -{ - struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR]; - u64 offset = nfit_blk->stat_offset + mmio->size * bw; - const u32 STATUS_MASK = 0x80000037; - - if (mmio->num_lines) - offset = to_interleave_offset(offset, mmio); - - return readl(mmio->addr.base + offset) & STATUS_MASK; -} - -static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw, - resource_size_t dpa, unsigned int len, unsigned int write) -{ - u64 cmd, offset; - struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR]; - - enum { - BCW_OFFSET_MASK = (1ULL << 48)-1, - BCW_LEN_SHIFT = 48, - BCW_LEN_MASK = (1ULL << 8) - 1, - BCW_CMD_SHIFT = 56, - }; - - cmd = (dpa >> L1_CACHE_SHIFT) & BCW_OFFSET_MASK; - len = len >> L1_CACHE_SHIFT; - cmd |= ((u64) len & BCW_LEN_MASK) << BCW_LEN_SHIFT; - cmd |= ((u64) write) << BCW_CMD_SHIFT; - - offset = nfit_blk->cmd_offset + mmio->size * bw; - if (mmio->num_lines) - offset = to_interleave_offset(offset, mmio); - - writeq(cmd, mmio->addr.base + offset); - nvdimm_flush(nfit_blk->nd_region, NULL); - - if (nfit_blk->dimm_flags & NFIT_BLK_DCR_LATCH) - readq(mmio->addr.base + offset); -} - -static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk, - resource_size_t dpa, void *iobuf, size_t len, int rw, - unsigned int lane) -{ - struct nfit_blk_mmio *mmio = &nfit_blk->mmio[BDW]; - unsigned int copied = 0; - u64 base_offset; - int rc; - - base_offset = nfit_blk->bdw_offset + dpa % L1_CACHE_BYTES - + lane * mmio->size; - write_blk_ctl(nfit_blk, lane, dpa, len, rw); - while (len) { - unsigned int c; - u64 offset; - - if (mmio->num_lines) { - u32 line_offset; - - offset = to_interleave_offset(base_offset + copied, - mmio); - div_u64_rem(offset, mmio->line_size, &line_offset); - c = min_t(size_t, len, mmio->line_size - line_offset); - } else { - offset = base_offset + nfit_blk->bdw_offset; - c = len; - } - - if (rw) - memcpy_flushcache(mmio->addr.aperture + offset, iobuf + copied, c); - else { - if (nfit_blk->dimm_flags & NFIT_BLK_READ_FLUSH) - arch_invalidate_pmem((void __force *) - mmio->addr.aperture + offset, c); - - memcpy(iobuf + copied, mmio->addr.aperture + offset, c); - } - - copied += c; - len -= c; - } - - if (rw) - nvdimm_flush(nfit_blk->nd_region, NULL); - - rc = read_blk_stat(nfit_blk, lane) ? -EIO : 0; - return rc; -} - -static int acpi_nfit_blk_region_do_io(struct nd_blk_region *ndbr, - resource_size_t dpa, void *iobuf, u64 len, int rw) -{ - struct nfit_blk *nfit_blk = nd_blk_region_provider_data(ndbr); - struct nfit_blk_mmio *mmio = &nfit_blk->mmio[BDW]; - struct nd_region *nd_region = nfit_blk->nd_region; - unsigned int lane, copied = 0; - int rc = 0; - - lane = nd_region_acquire_lane(nd_region); - while (len) { - u64 c = min(len, mmio->size); - - rc = acpi_nfit_blk_single_io(nfit_blk, dpa + copied, - iobuf + copied, c, rw, lane); - if (rc) - break; - - copied += c; - len -= c; - } - nd_region_release_lane(nd_region, lane); - - return rc; -} - -static int nfit_blk_init_interleave(struct nfit_blk_mmio *mmio, - struct acpi_nfit_interleave *idt, u16 interleave_ways) -{ - if (idt) { - mmio->num_lines = idt->line_count; - mmio->line_size = idt->line_size; - if (interleave_ways == 0) - return -ENXIO; - mmio->table_size = mmio->num_lines * interleave_ways - * mmio->line_size; - } - - return 0; -} - -static int acpi_nfit_blk_get_flags(struct nvdimm_bus_descriptor *nd_desc, - struct nvdimm *nvdimm, struct nfit_blk *nfit_blk) -{ - struct nd_cmd_dimm_flags flags; - int rc; - - memset(&flags, 0, sizeof(flags)); - rc = nd_desc->ndctl(nd_desc, nvdimm, ND_CMD_DIMM_FLAGS, &flags, - sizeof(flags), NULL); - - if (rc >= 0 && flags.status == 0) - nfit_blk->dimm_flags = flags.flags; - else if (rc == -ENOTTY) { - /* fall back to a conservative default */ - nfit_blk->dimm_flags = NFIT_BLK_DCR_LATCH | NFIT_BLK_READ_FLUSH; - rc = 0; - } else - rc = -ENXIO; - - return rc; -} - -static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, - struct device *dev) -{ - struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus); - struct nd_blk_region *ndbr = to_nd_blk_region(dev); - struct nfit_blk_mmio *mmio; - struct nfit_blk *nfit_blk; - struct nfit_mem *nfit_mem; - struct nvdimm *nvdimm; - int rc; - - nvdimm = nd_blk_region_to_dimm(ndbr); - nfit_mem = nvdimm_provider_data(nvdimm); - if (!nfit_mem || !nfit_mem->dcr || !nfit_mem->bdw) { - dev_dbg(dev, "missing%s%s%s\n", - nfit_mem ? "" : " nfit_mem", - (nfit_mem && nfit_mem->dcr) ? "" : " dcr", - (nfit_mem && nfit_mem->bdw) ? "" : " bdw"); - return -ENXIO; - } - - nfit_blk = devm_kzalloc(dev, sizeof(*nfit_blk), GFP_KERNEL); - if (!nfit_blk) - return -ENOMEM; - nd_blk_region_set_provider_data(ndbr, nfit_blk); - nfit_blk->nd_region = to_nd_region(dev); - - /* map block aperture memory */ - nfit_blk->bdw_offset = nfit_mem->bdw->offset; - mmio = &nfit_blk->mmio[BDW]; - mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address, - nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr)); - if (!mmio->addr.base) { - dev_dbg(dev, "%s failed to map bdw\n", - nvdimm_name(nvdimm)); - return -ENOMEM; - } - mmio->size = nfit_mem->bdw->size; - mmio->base_offset = nfit_mem->memdev_bdw->region_offset; - mmio->idt = nfit_mem->idt_bdw; - mmio->spa = nfit_mem->spa_bdw; - rc = nfit_blk_init_interleave(mmio, nfit_mem->idt_bdw, - nfit_mem->memdev_bdw->interleave_ways); - if (rc) { - dev_dbg(dev, "%s failed to init bdw interleave\n", - nvdimm_name(nvdimm)); - return rc; - } - - /* map block control memory */ - nfit_blk->cmd_offset = nfit_mem->dcr->command_offset; - nfit_blk->stat_offset = nfit_mem->dcr->status_offset; - mmio = &nfit_blk->mmio[DCR]; - mmio->addr.base = devm_nvdimm_ioremap(dev, nfit_mem->spa_dcr->address, - nfit_mem->spa_dcr->length); - if (!mmio->addr.base) { - dev_dbg(dev, "%s failed to map dcr\n", - nvdimm_name(nvdimm)); - return -ENOMEM; - } - mmio->size = nfit_mem->dcr->window_size; - mmio->base_offset = nfit_mem->memdev_dcr->region_offset; - mmio->idt = nfit_mem->idt_dcr; - mmio->spa = nfit_mem->spa_dcr; - rc = nfit_blk_init_interleave(mmio, nfit_mem->idt_dcr, - nfit_mem->memdev_dcr->interleave_ways); - if (rc) { - dev_dbg(dev, "%s failed to init dcr interleave\n", - nvdimm_name(nvdimm)); - return rc; - } - - rc = acpi_nfit_blk_get_flags(nd_desc, nvdimm, nfit_blk); - if (rc < 0) { - dev_dbg(dev, "%s failed get DIMM flags\n", - nvdimm_name(nvdimm)); - return rc; - } - - if (nvdimm_has_flush(nfit_blk->nd_region) < 0) - dev_warn(dev, "unable to guarantee persistence of writes\n"); - - if (mmio->line_size == 0) - return 0; - - if ((u32) nfit_blk->cmd_offset % mmio->line_size - + 8 > mmio->line_size) { - dev_dbg(dev, "cmd_offset crosses interleave boundary\n"); - return -ENXIO; - } else if ((u32) nfit_blk->stat_offset % mmio->line_size - + 8 > mmio->line_size) { - dev_dbg(dev, "stat_offset crosses interleave boundary\n"); - return -ENXIO; - } - - return 0; -} - static int ars_get_cap(struct acpi_nfit_desc *acpi_desc, struct nd_cmd_ars_cap *cmd, struct nfit_spa *nfit_spa) { @@ -2911,9 +2563,6 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, struct nvdimm *nvdimm = acpi_nfit_dimm_by_handle(acpi_desc, memdev->device_handle); struct acpi_nfit_system_address *spa = nfit_spa->spa; - struct nd_blk_region_desc *ndbr_desc; - struct nfit_mem *nfit_mem; - int rc; if (!nvdimm) { dev_err(acpi_desc->dev, "spa%d dimm: %#x not found\n", @@ -2928,30 +2577,6 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, mapping->start = memdev->address; mapping->size = memdev->region_size; break; - case NFIT_SPA_DCR: - nfit_mem = nvdimm_provider_data(nvdimm); - if (!nfit_mem || !nfit_mem->bdw) { - dev_dbg(acpi_desc->dev, "spa%d %s missing bdw\n", - spa->range_index, nvdimm_name(nvdimm)); - break; - } - - mapping->size = nfit_mem->bdw->capacity; - mapping->start = nfit_mem->bdw->start_address; - ndr_desc->num_lanes = nfit_mem->bdw->windows; - ndr_desc->mapping = mapping; - ndr_desc->num_mappings = 1; - ndbr_desc = to_blk_region_desc(ndr_desc); - ndbr_desc->enable = acpi_nfit_blk_region_enable; - ndbr_desc->do_io = acpi_desc->blk_do_io; - rc = acpi_nfit_init_interleave_set(acpi_desc, ndr_desc, spa); - if (rc) - return rc; - nfit_spa->nd_region = nvdimm_blk_region_create(acpi_desc->nvdimm_bus, - ndr_desc); - if (!nfit_spa->nd_region) - return -ENOMEM; - break; } return 0; @@ -3635,7 +3260,6 @@ void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev) dev_set_drvdata(dev, acpi_desc); acpi_desc->dev = dev; - acpi_desc->blk_do_io = acpi_nfit_blk_region_do_io; nd_desc = &acpi_desc->nd_desc; nd_desc->provider_name = "ACPI.NFIT"; nd_desc->module = THIS_MODULE; diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index c674f3df9be7..50882bdbeb96 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -208,13 +208,9 @@ struct nfit_mem { struct nvdimm *nvdimm; struct acpi_nfit_memory_map *memdev_dcr; struct acpi_nfit_memory_map *memdev_pmem; - struct acpi_nfit_memory_map *memdev_bdw; struct acpi_nfit_control_region *dcr; - struct acpi_nfit_data_region *bdw; struct acpi_nfit_system_address *spa_dcr; - struct acpi_nfit_system_address *spa_bdw; struct acpi_nfit_interleave *idt_dcr; - struct acpi_nfit_interleave *idt_bdw; struct kernfs_node *flags_attr; struct nfit_flush *nfit_flush; struct list_head list; @@ -266,8 +262,6 @@ struct acpi_nfit_desc { unsigned long family_dsm_mask[NVDIMM_BUS_FAMILY_MAX + 1]; unsigned int platform_cap; unsigned int scrub_tmo; - int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, - void *iobuf, u64 len, int rw); enum nvdimm_fwa_state fwa_state; enum nvdimm_fwa_capability fwa_cap; int fwa_count; diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 0bc91ffee257..65dbdda3a054 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -2842,28 +2842,6 @@ static void nfit_test1_setup(struct nfit_test *t) set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en); } -static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa, - void *iobuf, u64 len, int rw) -{ - struct nfit_blk *nfit_blk = ndbr->blk_provider_data; - struct nfit_blk_mmio *mmio = &nfit_blk->mmio[BDW]; - struct nd_region *nd_region = &ndbr->nd_region; - unsigned int lane; - - lane = nd_region_acquire_lane(nd_region); - if (rw) - memcpy(mmio->addr.base + dpa, iobuf, len); - else { - memcpy(iobuf, mmio->addr.base + dpa, len); - - /* give us some some coverage of the arch_invalidate_pmem() API */ - arch_invalidate_pmem(mmio->addr.base + dpa, len); - } - nd_region_release_lane(nd_region, lane); - - return 0; -} - static unsigned long nfit_ctl_handle; union acpi_object *result; @@ -3219,7 +3197,6 @@ static int nfit_test_probe(struct platform_device *pdev) nfit_test->setup(nfit_test); acpi_desc = &nfit_test->acpi_desc; acpi_nfit_desc_init(acpi_desc, &pdev->dev); - acpi_desc->blk_do_io = nfit_test_blk_do_io; nd_desc = &acpi_desc->nd_desc; nd_desc->provider_name = NULL; nd_desc->module = THIS_MODULE; From 3b6c6c039707f6bb7c64af2aa82a437fabb93aee Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 9 Mar 2022 19:49:48 -0800 Subject: [PATCH 10/14] nvdimm/region: Delete nd_blk_region infrastructure Now that the nd_namespace_blk infrastructure is removed, delete all the region machinery to coordinate provisioning aliased capacity between PMEM and BLK. Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/164688418803.2879318.1302315202397235855.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/acpi/nfit/core.c | 11 +- drivers/nvdimm/bus.c | 2 - drivers/nvdimm/dimm_devs.c | 204 ++--------------------------- drivers/nvdimm/label.c | 6 +- drivers/nvdimm/label.h | 2 +- drivers/nvdimm/namespace_devs.c | 127 ++---------------- drivers/nvdimm/nd-core.h | 24 +--- drivers/nvdimm/nd.h | 12 -- drivers/nvdimm/region.c | 31 ++--- drivers/nvdimm/region_devs.c | 158 +++------------------- include/linux/libnvdimm.h | 24 ---- include/uapi/linux/ndctl.h | 2 - tools/testing/nvdimm/test/ndtest.c | 67 +--------- 13 files changed, 66 insertions(+), 604 deletions(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index bea6a219fddd..fe61f617a943 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2036,10 +2036,6 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) cmd_mask |= nfit_mem->dsm_mask & NVDIMM_STANDARD_CMDMASK; } - /* Quirk to ignore LOCAL for labels on HYPERV DIMMs */ - if (nfit_mem->family == NVDIMM_FAMILY_HYPERV) - set_bit(NDD_NOBLK, &flags); - if (test_bit(NFIT_MEM_LSR, &nfit_mem->flags)) { set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask); set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask); @@ -2602,8 +2598,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, { static struct nd_mapping_desc mappings[ND_MAX_MAPPINGS]; struct acpi_nfit_system_address *spa = nfit_spa->spa; - struct nd_blk_region_desc ndbr_desc; - struct nd_region_desc *ndr_desc; + struct nd_region_desc *ndr_desc, _ndr_desc; struct nfit_memdev *nfit_memdev; struct nvdimm_bus *nvdimm_bus; struct resource res; @@ -2619,10 +2614,10 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, memset(&res, 0, sizeof(res)); memset(&mappings, 0, sizeof(mappings)); - memset(&ndbr_desc, 0, sizeof(ndbr_desc)); + memset(&_ndr_desc, 0, sizeof(_ndr_desc)); res.start = spa->address; res.end = res.start + spa->length - 1; - ndr_desc = &ndbr_desc.ndr_desc; + ndr_desc = &_ndr_desc; ndr_desc->res = &res; ndr_desc->provider_data = nfit_spa; ndr_desc->attr_groups = acpi_nfit_region_attribute_groups; diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 9dc7f3edd42b..a4b5f637e599 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -35,8 +35,6 @@ static int to_nd_device_type(struct device *dev) return ND_DEVICE_DIMM; else if (is_memory(dev)) return ND_DEVICE_REGION_PMEM; - else if (is_nd_blk(dev)) - return ND_DEVICE_REGION_BLK; else if (is_nd_dax(dev)) return ND_DEVICE_DAX_PMEM; else if (is_nd_region(dev->parent)) diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index dc7449a40003..ee507eed42b5 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -18,10 +18,6 @@ static DEFINE_IDA(dimm_ida); -static bool noblk; -module_param(noblk, bool, 0444); -MODULE_PARM_DESC(noblk, "force disable BLK / local alias support"); - /* * Retrieve bus and dimm handle and return if this bus supports * get_config_data commands @@ -211,22 +207,6 @@ struct nvdimm *to_nvdimm(struct device *dev) } EXPORT_SYMBOL_GPL(to_nvdimm); -struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr) -{ - struct nd_region *nd_region = &ndbr->nd_region; - struct nd_mapping *nd_mapping = &nd_region->mapping[0]; - - return nd_mapping->nvdimm; -} -EXPORT_SYMBOL_GPL(nd_blk_region_to_dimm); - -unsigned long nd_blk_memremap_flags(struct nd_blk_region *ndbr) -{ - /* pmem mapping properties are private to libnvdimm */ - return ARCH_MEMREMAP_PMEM; -} -EXPORT_SYMBOL_GPL(nd_blk_memremap_flags); - struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping) { struct nvdimm *nvdimm = nd_mapping->nvdimm; @@ -312,8 +292,7 @@ static ssize_t flags_show(struct device *dev, { struct nvdimm *nvdimm = to_nvdimm(dev); - return sprintf(buf, "%s%s%s\n", - test_bit(NDD_ALIASING, &nvdimm->flags) ? "alias " : "", + return sprintf(buf, "%s%s\n", test_bit(NDD_LABELING, &nvdimm->flags) ? "label " : "", test_bit(NDD_LOCKED, &nvdimm->flags) ? "lock " : ""); } @@ -612,8 +591,6 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus, nvdimm->dimm_id = dimm_id; nvdimm->provider_data = provider_data; - if (noblk) - flags |= 1 << NDD_NOBLK; nvdimm->flags = flags; nvdimm->cmd_mask = cmd_mask; nvdimm->num_flush = num_flush; @@ -726,133 +703,6 @@ static unsigned long dpa_align(struct nd_region *nd_region) return nd_region->align / nd_region->ndr_mappings; } -int alias_dpa_busy(struct device *dev, void *data) -{ - resource_size_t map_end, blk_start, new; - struct blk_alloc_info *info = data; - struct nd_mapping *nd_mapping; - struct nd_region *nd_region; - struct nvdimm_drvdata *ndd; - struct resource *res; - unsigned long align; - int i; - - if (!is_memory(dev)) - return 0; - - nd_region = to_nd_region(dev); - for (i = 0; i < nd_region->ndr_mappings; i++) { - nd_mapping = &nd_region->mapping[i]; - if (nd_mapping->nvdimm == info->nd_mapping->nvdimm) - break; - } - - if (i >= nd_region->ndr_mappings) - return 0; - - ndd = to_ndd(nd_mapping); - map_end = nd_mapping->start + nd_mapping->size - 1; - blk_start = nd_mapping->start; - - /* - * In the allocation case ->res is set to free space that we are - * looking to validate against PMEM aliasing collision rules - * (i.e. BLK is allocated after all aliased PMEM). - */ - if (info->res) { - if (info->res->start >= nd_mapping->start - && info->res->start < map_end) - /* pass */; - else - return 0; - } - - retry: - /* - * Find the free dpa from the end of the last pmem allocation to - * the end of the interleave-set mapping. - */ - align = dpa_align(nd_region); - if (!align) - return 0; - - for_each_dpa_resource(ndd, res) { - resource_size_t start, end; - - if (strncmp(res->name, "pmem", 4) != 0) - continue; - - start = ALIGN_DOWN(res->start, align); - end = ALIGN(res->end + 1, align) - 1; - if ((start >= blk_start && start < map_end) - || (end >= blk_start && end <= map_end)) { - new = max(blk_start, min(map_end, end) + 1); - if (new != blk_start) { - blk_start = new; - goto retry; - } - } - } - - /* update the free space range with the probed blk_start */ - if (info->res && blk_start > info->res->start) { - info->res->start = max(info->res->start, blk_start); - if (info->res->start > info->res->end) - info->res->end = info->res->start - 1; - return 1; - } - - info->available -= blk_start - nd_mapping->start; - - return 0; -} - -/** - * nd_blk_available_dpa - account the unused dpa of BLK region - * @nd_mapping: container of dpa-resource-root + labels - * - * Unlike PMEM, BLK namespaces can occupy discontiguous DPA ranges, but - * we arrange for them to never start at an lower dpa than the last - * PMEM allocation in an aliased region. - */ -resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) -{ - struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev); - struct nd_mapping *nd_mapping = &nd_region->mapping[0]; - struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); - struct blk_alloc_info info = { - .nd_mapping = nd_mapping, - .available = nd_mapping->size, - .res = NULL, - }; - struct resource *res; - unsigned long align; - - if (!ndd) - return 0; - - device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy); - - /* now account for busy blk allocations in unaliased dpa */ - align = dpa_align(nd_region); - if (!align) - return 0; - for_each_dpa_resource(ndd, res) { - resource_size_t start, end, size; - - if (strncmp(res->name, "blk", 3) != 0) - continue; - start = ALIGN_DOWN(res->start, align); - end = ALIGN(res->end + 1, align) - 1; - size = end - start + 1; - if (size >= info.available) - return 0; - info.available -= size; - } - - return info.available; -} - /** * nd_pmem_max_contiguous_dpa - For the given dimm+region, return the max * contiguous unallocated dpa range. @@ -900,24 +750,16 @@ resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region, * nd_pmem_available_dpa - for the given dimm+region account unallocated dpa * @nd_mapping: container of dpa-resource-root + labels * @nd_region: constrain available space check to this reference region - * @overlap: calculate available space assuming this level of overlap * * Validate that a PMEM label, if present, aligns with the start of an - * interleave set and truncate the available size at the lowest BLK - * overlap point. - * - * The expectation is that this routine is called multiple times as it - * probes for the largest BLK encroachment for any single member DIMM of - * the interleave set. Once that value is determined the PMEM-limit for - * the set can be established. + * interleave set. */ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, - struct nd_mapping *nd_mapping, resource_size_t *overlap) + struct nd_mapping *nd_mapping) { - resource_size_t map_start, map_end, busy = 0, available, blk_start; struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + resource_size_t map_start, map_end, busy = 0; struct resource *res; - const char *reason; unsigned long align; if (!ndd) @@ -929,46 +771,28 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, map_start = nd_mapping->start; map_end = map_start + nd_mapping->size - 1; - blk_start = max(map_start, map_end + 1 - *overlap); for_each_dpa_resource(ndd, res) { resource_size_t start, end; start = ALIGN_DOWN(res->start, align); end = ALIGN(res->end + 1, align) - 1; if (start >= map_start && start < map_end) { - if (strncmp(res->name, "blk", 3) == 0) - blk_start = min(blk_start, - max(map_start, start)); - else if (end > map_end) { - reason = "misaligned to iset"; - goto err; - } else - busy += end - start + 1; + if (end > map_end) { + nd_dbg_dpa(nd_region, ndd, res, + "misaligned to iset\n"); + return 0; + } + busy += end - start + 1; } else if (end >= map_start && end <= map_end) { - if (strncmp(res->name, "blk", 3) == 0) { - /* - * If a BLK allocation overlaps the start of - * PMEM the entire interleave set may now only - * be used for BLK. - */ - blk_start = map_start; - } else - busy += end - start + 1; + busy += end - start + 1; } else if (map_start > start && map_start < end) { /* total eclipse of the mapping */ busy += nd_mapping->size; - blk_start = map_start; } } - *overlap = map_end + 1 - blk_start; - available = blk_start - map_start; - if (busy < available) - return ALIGN_DOWN(available - busy, align); - return 0; - - err: - nd_dbg_dpa(nd_region, ndd, res, "%s\n", reason); + if (busy < nd_mapping->size) + return ALIGN_DOWN(nd_mapping->size - busy, align); return 0; } @@ -999,7 +823,7 @@ struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd, /** * nvdimm_allocated_dpa - sum up the dpa currently allocated to this label_id * @nvdimm: container of dpa-resource-root + labels - * @label_id: dpa resource name of the form {pmem|blk}- + * @label_id: dpa resource name of the form pmem- */ resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd, struct nd_label_id *label_id) diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c index 8c972bcb2ac3..082253a3a956 100644 --- a/drivers/nvdimm/label.c +++ b/drivers/nvdimm/label.c @@ -334,8 +334,7 @@ char *nd_label_gen_id(struct nd_label_id *label_id, const uuid_t *uuid, { if (!label_id || !uuid) return NULL; - snprintf(label_id->id, ND_LABEL_ID_SIZE, "%s-%pUb", - flags & NSLABEL_FLAG_LOCAL ? "blk" : "pmem", uuid); + snprintf(label_id->id, ND_LABEL_ID_SIZE, "pmem-%pUb", uuid); return label_id->id; } @@ -406,7 +405,6 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd) return 0; /* no label, nothing to reserve */ for_each_clear_bit_le(slot, free, nslot) { - struct nvdimm *nvdimm = to_nvdimm(ndd->dev); struct nd_namespace_label *nd_label; struct nd_region *nd_region = NULL; struct nd_label_id label_id; @@ -421,8 +419,6 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd) nsl_get_uuid(ndd, nd_label, &label_uuid); flags = nsl_get_flags(ndd, nd_label); - if (test_bit(NDD_NOBLK, &nvdimm->flags)) - flags &= ~NSLABEL_FLAG_LOCAL; nd_label_gen_id(&label_id, &label_uuid, flags); res = nvdimm_allocate_dpa(ndd, &label_id, nsl_get_dpa(ndd, nd_label), diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h index 198ef1df298b..0650fb4b9821 100644 --- a/drivers/nvdimm/label.h +++ b/drivers/nvdimm/label.h @@ -193,7 +193,7 @@ struct nd_namespace_label { /** * struct nd_label_id - identifier string for dpa allocation - * @id: "{blk|pmem}-" + * @id: "pmem-" */ struct nd_label_id { char id[ND_LABEL_ID_SIZE]; diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index d1c190b02657..62b83b2e26e3 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -297,13 +297,11 @@ static int scan_free(struct nd_region *nd_region, struct nd_mapping *nd_mapping, struct nd_label_id *label_id, resource_size_t n) { - bool is_blk = strncmp(label_id->id, "blk", 3) == 0; struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); int rc = 0; while (n) { struct resource *res, *last; - resource_size_t new_start; last = NULL; for_each_dpa_resource(ndd, res) @@ -321,16 +319,7 @@ static int scan_free(struct nd_region *nd_region, continue; } - /* - * Keep BLK allocations relegated to high DPA as much as - * possible - */ - if (is_blk) - new_start = res->start + n; - else - new_start = res->start; - - rc = adjust_resource(res, new_start, resource_size(res) - n); + rc = adjust_resource(res, res->start, resource_size(res) - n); if (rc == 0) res->flags |= DPA_RESOURCE_ADJUSTED; nd_dbg_dpa(nd_region, ndd, res, "shrink %d\n", rc); @@ -372,20 +361,12 @@ static resource_size_t init_dpa_allocation(struct nd_label_id *label_id, struct nd_region *nd_region, struct nd_mapping *nd_mapping, resource_size_t n) { - bool is_blk = strncmp(label_id->id, "blk", 3) == 0; struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); - resource_size_t first_dpa; struct resource *res; int rc = 0; - /* allocate blk from highest dpa first */ - if (is_blk) - first_dpa = nd_mapping->start + nd_mapping->size - n; - else - first_dpa = nd_mapping->start; - /* first resource allocation for this label-id or dimm */ - res = nvdimm_allocate_dpa(ndd, label_id, first_dpa, n); + res = nvdimm_allocate_dpa(ndd, label_id, nd_mapping->start, n); if (!res) rc = -EBUSY; @@ -416,7 +397,6 @@ static void space_valid(struct nd_region *nd_region, struct nvdimm_drvdata *ndd, resource_size_t n, struct resource *valid) { bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0; - bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0; unsigned long align; align = nd_region->align / nd_region->ndr_mappings; @@ -429,21 +409,6 @@ static void space_valid(struct nd_region *nd_region, struct nvdimm_drvdata *ndd, if (is_reserve) return; - if (!is_pmem) { - struct nd_mapping *nd_mapping = &nd_region->mapping[0]; - struct nvdimm_bus *nvdimm_bus; - struct blk_alloc_info info = { - .nd_mapping = nd_mapping, - .available = nd_mapping->size, - .res = valid, - }; - - WARN_ON(!is_nd_blk(&nd_region->dev)); - nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev); - device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy); - return; - } - /* allocation needs to be contiguous, so this is all or nothing */ if (resource_size(valid) < n) goto invalid; @@ -471,7 +436,6 @@ static resource_size_t scan_allocate(struct nd_region *nd_region, resource_size_t n) { resource_size_t mapping_end = nd_mapping->start + nd_mapping->size - 1; - bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0; struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); struct resource *res, *exist = NULL, valid; const resource_size_t to_allocate = n; @@ -569,10 +533,6 @@ static resource_size_t scan_allocate(struct nd_region *nd_region, } if (strcmp(action, "allocate") == 0) { - /* BLK allocate bottom up */ - if (!is_pmem) - valid.start += available - allocate; - new_res = nvdimm_allocate_dpa(ndd, label_id, valid.start, allocate); if (!new_res) @@ -608,12 +568,7 @@ static resource_size_t scan_allocate(struct nd_region *nd_region, return 0; } - /* - * If we allocated nothing in the BLK case it may be because we are in - * an initial "pmem-reserve pass". Only do an initial BLK allocation - * when none of the DPA space is reserved. - */ - if ((is_pmem || !ndd->dpa.child) && n == to_allocate) + if (n == to_allocate) return init_dpa_allocation(label_id, nd_region, nd_mapping, n); return n; } @@ -672,7 +627,7 @@ int __reserve_free_pmem(struct device *dev, void *data) if (nd_mapping->nvdimm != nvdimm) continue; - n = nd_pmem_available_dpa(nd_region, nd_mapping, &rem); + n = nd_pmem_available_dpa(nd_region, nd_mapping); if (n == 0) return 0; rem = scan_allocate(nd_region, nd_mapping, &label_id, n); @@ -697,19 +652,6 @@ void release_free_pmem(struct nvdimm_bus *nvdimm_bus, nvdimm_free_dpa(ndd, res); } -static int reserve_free_pmem(struct nvdimm_bus *nvdimm_bus, - struct nd_mapping *nd_mapping) -{ - struct nvdimm *nvdimm = nd_mapping->nvdimm; - int rc; - - rc = device_for_each_child(&nvdimm_bus->dev, nvdimm, - __reserve_free_pmem); - if (rc) - release_free_pmem(nvdimm_bus, nd_mapping); - return rc; -} - /** * grow_dpa_allocation - for each dimm allocate n bytes for @label_id * @nd_region: the set of dimms to allocate @n more bytes from @@ -726,37 +668,14 @@ static int reserve_free_pmem(struct nvdimm_bus *nvdimm_bus, static int grow_dpa_allocation(struct nd_region *nd_region, struct nd_label_id *label_id, resource_size_t n) { - struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev); - bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0; int i; for (i = 0; i < nd_region->ndr_mappings; i++) { struct nd_mapping *nd_mapping = &nd_region->mapping[i]; resource_size_t rem = n; - int rc, j; - - /* - * In the BLK case try once with all unallocated PMEM - * reserved, and once without - */ - for (j = is_pmem; j < 2; j++) { - bool blk_only = j == 0; - - if (blk_only) { - rc = reserve_free_pmem(nvdimm_bus, nd_mapping); - if (rc) - return rc; - } - rem = scan_allocate(nd_region, nd_mapping, - label_id, rem); - if (blk_only) - release_free_pmem(nvdimm_bus, nd_mapping); - - /* try again and allow encroachments into PMEM */ - if (rem == 0) - break; - } + int rc; + rem = scan_allocate(nd_region, nd_mapping, label_id, rem); dev_WARN_ONCE(&nd_region->dev, rem, "allocation underrun: %#llx of %#llx bytes\n", (unsigned long long) n - rem, @@ -869,8 +788,8 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) ndd = to_ndd(nd_mapping); /* - * All dimms in an interleave set, or the base dimm for a blk - * region, need to be enabled for the size to be changed. + * All dimms in an interleave set, need to be enabled + * for the size to be changed. */ if (!ndd) return -ENXIO; @@ -1169,9 +1088,6 @@ static ssize_t resource_show(struct device *dev, } static DEVICE_ATTR_ADMIN_RO(resource); -static const unsigned long blk_lbasize_supported[] = { 512, 520, 528, - 4096, 4104, 4160, 4224, 0 }; - static const unsigned long pmem_lbasize_supported[] = { 512, 4096, 0 }; static ssize_t sector_size_show(struct device *dev, @@ -1823,10 +1739,7 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, /* * Fix up each mapping's 'labels' to have the validated pmem label for * that position at labels[0], and NULL at labels[1]. In the process, - * check that the namespace aligns with interleave-set. We know - * that it does not overlap with any blk namespaces by virtue of - * the dimm being enabled (i.e. nd_label_reserve_dpa() - * succeeded). + * check that the namespace aligns with interleave-set. */ nsl_get_uuid(ndd, nd_label, &uuid); rc = select_pmem_id(nd_region, &uuid); @@ -1931,8 +1844,7 @@ void nd_region_create_ns_seed(struct nd_region *nd_region) * disabled until memory becomes available */ if (!nd_region->ns_seed) - dev_err(&nd_region->dev, "failed to create %s namespace\n", - is_nd_blk(&nd_region->dev) ? "blk" : "pmem"); + dev_err(&nd_region->dev, "failed to create namespace\n"); else nd_device_register(nd_region->ns_seed); } @@ -2028,16 +1940,9 @@ static struct device **scan_labels(struct nd_region *nd_region) list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) { struct nd_namespace_label *nd_label = label_ent->label; struct device **__devs; - u32 flags; if (!nd_label) continue; - flags = nsl_get_flags(ndd, nd_label); - if (is_nd_blk(&nd_region->dev) - == !!(flags & NSLABEL_FLAG_LOCAL)) - /* pass, region matches label type */; - else - continue; /* skip labels that describe extents outside of the region */ if (nsl_get_dpa(ndd, nd_label) < nd_mapping->start || @@ -2073,9 +1978,8 @@ static struct device **scan_labels(struct nd_region *nd_region) } - dev_dbg(&nd_region->dev, "discovered %d %s namespace%s\n", - count, is_nd_blk(&nd_region->dev) - ? "blk" : "pmem", count == 1 ? "" : "s"); + dev_dbg(&nd_region->dev, "discovered %d namespace%s\n", count, + count == 1 ? "" : "s"); if (count == 0) { struct nd_namespace_pmem *nspm; @@ -2226,12 +2130,6 @@ static int init_active_labels(struct nd_region *nd_region) if (!label_ent) break; label = nd_label_active(ndd, j); - if (test_bit(NDD_NOBLK, &nvdimm->flags)) { - u32 flags = nsl_get_flags(ndd, label); - - flags &= ~NSLABEL_FLAG_LOCAL; - nsl_set_flags(ndd, label, flags); - } label_ent->label = label; mutex_lock(&nd_mapping->lock); @@ -2275,7 +2173,6 @@ int nd_region_register_namespaces(struct nd_region *nd_region, int *err) devs = create_namespace_io(nd_region); break; case ND_DEVICE_NAMESPACE_PMEM: - case ND_DEVICE_NAMESPACE_BLK: devs = create_namespaces(nd_region); break; default: diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index e4af0719cf33..17febf9ac911 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -82,30 +82,12 @@ static inline void nvdimm_security_overwrite_query(struct work_struct *work) } #endif -/** - * struct blk_alloc_info - tracking info for BLK dpa scanning - * @nd_mapping: blk region mapping boundaries - * @available: decremented in alias_dpa_busy as aliased PMEM is scanned - * @busy: decremented in blk_dpa_busy to account for ranges already - * handled by alias_dpa_busy - * @res: alias_dpa_busy interprets this a free space range that needs to - * be truncated to the valid BLK allocation starting DPA, blk_dpa_busy - * treats it as a busy range that needs the aliased PMEM ranges - * truncated. - */ -struct blk_alloc_info { - struct nd_mapping *nd_mapping; - resource_size_t available, busy; - struct resource *res; -}; - bool is_nvdimm(struct device *dev); bool is_nd_pmem(struct device *dev); bool is_nd_volatile(struct device *dev); -bool is_nd_blk(struct device *dev); static inline bool is_nd_region(struct device *dev) { - return is_nd_pmem(dev) || is_nd_blk(dev) || is_nd_volatile(dev); + return is_nd_pmem(dev) || is_nd_volatile(dev); } static inline bool is_memory(struct device *dev) { @@ -142,14 +124,12 @@ resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region, struct nd_mapping *nd_mapping); resource_size_t nd_region_allocatable_dpa(struct nd_region *nd_region); resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, - struct nd_mapping *nd_mapping, resource_size_t *overlap); -resource_size_t nd_blk_available_dpa(struct nd_region *nd_region); + struct nd_mapping *nd_mapping); resource_size_t nd_region_available_dpa(struct nd_region *nd_region); int nd_region_conflict(struct nd_region *nd_region, resource_size_t start, resource_size_t size); resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd, struct nd_label_id *label_id); -int alias_dpa_busy(struct device *dev, void *data); int nvdimm_num_label_slots(struct nvdimm_drvdata *ndd); void get_ndd(struct nvdimm_drvdata *ndd); resource_size_t __nvdimm_namespace_capacity(struct nd_namespace_common *ndns); diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 8391bf2729bc..ec5219680092 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -295,9 +295,6 @@ static inline const u8 *nsl_uuid_raw(struct nvdimm_drvdata *ndd, return nd_label->efi.uuid; } -bool nsl_validate_blk_isetcookie(struct nvdimm_drvdata *ndd, - struct nd_namespace_label *nd_label, - u64 isetcookie); bool nsl_validate_type_guid(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, guid_t *guid); enum nvdimm_claim_class nsl_get_claim_class(struct nvdimm_drvdata *ndd, @@ -437,14 +434,6 @@ static inline bool nsl_validate_nlabel(struct nd_region *nd_region, return nsl_get_nlabel(ndd, nd_label) == nd_region->ndr_mappings; } -struct nd_blk_region { - int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); - int (*do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, - void *iobuf, u64 len, int rw); - void *blk_provider_data; - struct nd_region nd_region; -}; - /* * Lookup next in the repeating sequence of 01, 10, and 11. */ @@ -672,7 +661,6 @@ static inline int nvdimm_setup_pfn(struct nd_pfn *nd_pfn, return -ENXIO; } #endif -int nd_blk_region_init(struct nd_region *nd_region); int nd_region_activate(struct nd_region *nd_region); static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector, unsigned int len) diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c index e0c34120df37..188560b1c110 100644 --- a/drivers/nvdimm/region.c +++ b/drivers/nvdimm/region.c @@ -15,6 +15,10 @@ static int nd_region_probe(struct device *dev) static unsigned long once; struct nd_region_data *ndrd; struct nd_region *nd_region = to_nd_region(dev); + struct range range = { + .start = nd_region->ndr_start, + .end = nd_region->ndr_start + nd_region->ndr_size - 1, + }; if (nd_region->num_lanes > num_online_cpus() && nd_region->num_lanes < num_possible_cpus() @@ -30,25 +34,13 @@ static int nd_region_probe(struct device *dev) if (rc) return rc; - rc = nd_blk_region_init(nd_region); - if (rc) - return rc; - - if (is_memory(&nd_region->dev)) { - struct range range = { - .start = nd_region->ndr_start, - .end = nd_region->ndr_start + nd_region->ndr_size - 1, - }; - - if (devm_init_badblocks(dev, &nd_region->bb)) - return -ENODEV; - nd_region->bb_state = sysfs_get_dirent(nd_region->dev.kobj.sd, - "badblocks"); - if (!nd_region->bb_state) - dev_warn(&nd_region->dev, - "'badblocks' notification disabled\n"); - nvdimm_badblocks_populate(nd_region, &nd_region->bb, &range); - } + if (devm_init_badblocks(dev, &nd_region->bb)) + return -ENODEV; + nd_region->bb_state = + sysfs_get_dirent(nd_region->dev.kobj.sd, "badblocks"); + if (!nd_region->bb_state) + dev_warn(dev, "'badblocks' notification disabled\n"); + nvdimm_badblocks_populate(nd_region, &nd_region->bb, &range); rc = nd_region_register_namespaces(nd_region, &err); if (rc < 0) @@ -158,4 +150,3 @@ void nd_region_exit(void) } MODULE_ALIAS_ND_DEVICE(ND_DEVICE_REGION_PMEM); -MODULE_ALIAS_ND_DEVICE(ND_DEVICE_REGION_BLK); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 70ad891a76ba..0cb274c2b508 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -134,10 +134,7 @@ static void nd_region_release(struct device *dev) } free_percpu(nd_region->lane); memregion_free(nd_region->id); - if (is_nd_blk(dev)) - kfree(to_nd_blk_region(dev)); - else - kfree(nd_region); + kfree(nd_region); } struct nd_region *to_nd_region(struct device *dev) @@ -157,33 +154,12 @@ struct device *nd_region_dev(struct nd_region *nd_region) } EXPORT_SYMBOL_GPL(nd_region_dev); -struct nd_blk_region *to_nd_blk_region(struct device *dev) -{ - struct nd_region *nd_region = to_nd_region(dev); - - WARN_ON(!is_nd_blk(dev)); - return container_of(nd_region, struct nd_blk_region, nd_region); -} -EXPORT_SYMBOL_GPL(to_nd_blk_region); - void *nd_region_provider_data(struct nd_region *nd_region) { return nd_region->provider_data; } EXPORT_SYMBOL_GPL(nd_region_provider_data); -void *nd_blk_region_provider_data(struct nd_blk_region *ndbr) -{ - return ndbr->blk_provider_data; -} -EXPORT_SYMBOL_GPL(nd_blk_region_provider_data); - -void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data) -{ - ndbr->blk_provider_data = data; -} -EXPORT_SYMBOL_GPL(nd_blk_region_set_provider_data); - /** * nd_region_to_nstype() - region to an integer namespace type * @nd_region: region-device to interrogate @@ -208,8 +184,6 @@ int nd_region_to_nstype(struct nd_region *nd_region) return ND_DEVICE_NAMESPACE_PMEM; else return ND_DEVICE_NAMESPACE_IO; - } else if (is_nd_blk(&nd_region->dev)) { - return ND_DEVICE_NAMESPACE_BLK; } return 0; @@ -332,14 +306,12 @@ static DEVICE_ATTR_RO(set_cookie); resource_size_t nd_region_available_dpa(struct nd_region *nd_region) { - resource_size_t blk_max_overlap = 0, available, overlap; + resource_size_t available; int i; WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev)); - retry: available = 0; - overlap = blk_max_overlap; for (i = 0; i < nd_region->ndr_mappings; i++) { struct nd_mapping *nd_mapping = &nd_region->mapping[i]; struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); @@ -348,15 +320,7 @@ resource_size_t nd_region_available_dpa(struct nd_region *nd_region) if (!ndd) return 0; - if (is_memory(&nd_region->dev)) { - available += nd_pmem_available_dpa(nd_region, - nd_mapping, &overlap); - if (overlap > blk_max_overlap) { - blk_max_overlap = overlap; - goto retry; - } - } else if (is_nd_blk(&nd_region->dev)) - available += nd_blk_available_dpa(nd_region); + available += nd_pmem_available_dpa(nd_region, nd_mapping); } return available; @@ -364,26 +328,17 @@ resource_size_t nd_region_available_dpa(struct nd_region *nd_region) resource_size_t nd_region_allocatable_dpa(struct nd_region *nd_region) { - resource_size_t available = 0; + resource_size_t avail = 0; int i; - if (is_memory(&nd_region->dev)) - available = PHYS_ADDR_MAX; - WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev)); for (i = 0; i < nd_region->ndr_mappings; i++) { struct nd_mapping *nd_mapping = &nd_region->mapping[i]; - if (is_memory(&nd_region->dev)) - available = min(available, - nd_pmem_max_contiguous_dpa(nd_region, - nd_mapping)); - else if (is_nd_blk(&nd_region->dev)) - available += nd_blk_available_dpa(nd_region); + avail = min_not_zero(avail, nd_pmem_max_contiguous_dpa( + nd_region, nd_mapping)); } - if (is_memory(&nd_region->dev)) - return available * nd_region->ndr_mappings; - return available; + return avail * nd_region->ndr_mappings; } static ssize_t available_size_show(struct device *dev, @@ -693,9 +648,8 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n) && a != &dev_attr_available_size.attr) return a->mode; - if ((type == ND_DEVICE_NAMESPACE_PMEM - || type == ND_DEVICE_NAMESPACE_BLK) - && a == &dev_attr_available_size.attr) + if (type == ND_DEVICE_NAMESPACE_PMEM && + a == &dev_attr_available_size.attr) return a->mode; else if (is_memory(dev) && nd_set) return a->mode; @@ -828,12 +782,6 @@ static const struct attribute_group *nd_region_attribute_groups[] = { NULL, }; -static const struct device_type nd_blk_device_type = { - .name = "nd_blk", - .release = nd_region_release, - .groups = nd_region_attribute_groups, -}; - static const struct device_type nd_pmem_device_type = { .name = "nd_pmem", .release = nd_region_release, @@ -851,11 +799,6 @@ bool is_nd_pmem(struct device *dev) return dev ? dev->type == &nd_pmem_device_type : false; } -bool is_nd_blk(struct device *dev) -{ - return dev ? dev->type == &nd_blk_device_type : false; -} - bool is_nd_volatile(struct device *dev) { return dev ? dev->type == &nd_volatile_device_type : false; @@ -929,22 +872,6 @@ void nd_region_advance_seeds(struct nd_region *nd_region, struct device *dev) nvdimm_bus_unlock(dev); } -int nd_blk_region_init(struct nd_region *nd_region) -{ - struct device *dev = &nd_region->dev; - struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); - - if (!is_nd_blk(dev)) - return 0; - - if (nd_region->ndr_mappings < 1) { - dev_dbg(dev, "invalid BLK region\n"); - return -ENXIO; - } - - return to_nd_blk_region(dev)->enable(nvdimm_bus, dev); -} - /** * nd_region_acquire_lane - allocate and lock a lane * @nd_region: region id and number of lanes possible @@ -1007,24 +934,10 @@ EXPORT_SYMBOL(nd_region_release_lane); static unsigned long default_align(struct nd_region *nd_region) { unsigned long align; - int i, mappings; u32 remainder; + int mappings; - if (is_nd_blk(&nd_region->dev)) - align = PAGE_SIZE; - else - align = MEMREMAP_COMPAT_ALIGN_MAX; - - for (i = 0; i < nd_region->ndr_mappings; i++) { - struct nd_mapping *nd_mapping = &nd_region->mapping[i]; - struct nvdimm *nvdimm = nd_mapping->nvdimm; - - if (test_bit(NDD_ALIASING, &nvdimm->flags)) { - align = MEMREMAP_COMPAT_ALIGN_MAX; - break; - } - } - + align = MEMREMAP_COMPAT_ALIGN_MAX; if (nd_region->ndr_size < MEMREMAP_COMPAT_ALIGN_MAX) align = PAGE_SIZE; @@ -1042,7 +955,6 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, { struct nd_region *nd_region; struct device *dev; - void *region_buf; unsigned int i; int ro = 0; @@ -1060,36 +972,13 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, if (test_bit(NDD_UNARMED, &nvdimm->flags)) ro = 1; - if (test_bit(NDD_NOBLK, &nvdimm->flags) - && dev_type == &nd_blk_device_type) { - dev_err(&nvdimm_bus->dev, "%s: %s mapping%d is not BLK capable\n", - caller, dev_name(&nvdimm->dev), i); - return NULL; - } } - if (dev_type == &nd_blk_device_type) { - struct nd_blk_region_desc *ndbr_desc; - struct nd_blk_region *ndbr; + nd_region = + kzalloc(struct_size(nd_region, mapping, ndr_desc->num_mappings), + GFP_KERNEL); - ndbr_desc = to_blk_region_desc(ndr_desc); - ndbr = kzalloc(sizeof(*ndbr) + sizeof(struct nd_mapping) - * ndr_desc->num_mappings, - GFP_KERNEL); - if (ndbr) { - nd_region = &ndbr->nd_region; - ndbr->enable = ndbr_desc->enable; - ndbr->do_io = ndbr_desc->do_io; - } - region_buf = ndbr; - } else { - nd_region = kzalloc(struct_size(nd_region, mapping, - ndr_desc->num_mappings), - GFP_KERNEL); - region_buf = nd_region; - } - - if (!region_buf) + if (!nd_region) return NULL; nd_region->id = memregion_alloc(GFP_KERNEL); if (nd_region->id < 0) @@ -1153,7 +1042,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, err_percpu: memregion_free(nd_region->id); err_id: - kfree(region_buf); + kfree(nd_region); return NULL; } @@ -1166,17 +1055,6 @@ struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus, } EXPORT_SYMBOL_GPL(nvdimm_pmem_region_create); -struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, - struct nd_region_desc *ndr_desc) -{ - if (ndr_desc->num_mappings > 1) - return NULL; - ndr_desc->num_lanes = min(ndr_desc->num_lanes, ND_MAX_LANES); - return nd_region_create(nvdimm_bus, ndr_desc, &nd_blk_device_type, - __func__); -} -EXPORT_SYMBOL_GPL(nvdimm_blk_region_create); - struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc) { @@ -1201,7 +1079,7 @@ int nvdimm_flush(struct nd_region *nd_region, struct bio *bio) } /** * nvdimm_flush - flush any posted write queues between the cpu and pmem media - * @nd_region: blk or interleaved pmem region + * @nd_region: interleaved pmem region */ int generic_nvdimm_flush(struct nd_region *nd_region) { @@ -1234,7 +1112,7 @@ EXPORT_SYMBOL_GPL(nvdimm_flush); /** * nvdimm_has_flush - determine write flushing requirements - * @nd_region: blk or interleaved pmem region + * @nd_region: interleaved pmem region * * Returns 1 if writes require flushing * Returns 0 if writes do not require flushing diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 7074aa9af525..0d61e07b6827 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -25,8 +25,6 @@ struct badrange { }; enum { - /* when a dimm supports both PMEM and BLK access a label is required */ - NDD_ALIASING = 0, /* unarmed memory devices may not persist writes */ NDD_UNARMED = 1, /* locked memory devices should not be accessed */ @@ -35,8 +33,6 @@ enum { NDD_SECURITY_OVERWRITE = 3, /* tracking whether or not there is a pending device reference */ NDD_WORK_PENDING = 4, - /* ignore / filter NSLABEL_FLAG_LOCAL for this DIMM, i.e. no aliasing */ - NDD_NOBLK = 5, /* dimm supports namespace labels */ NDD_LABELING = 6, @@ -140,21 +136,6 @@ static inline void __iomem *devm_nvdimm_ioremap(struct device *dev, } struct nvdimm_bus; -struct module; -struct nd_blk_region; -struct nd_blk_region_desc { - int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); - int (*do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, - void *iobuf, u64 len, int rw); - struct nd_region_desc ndr_desc; -}; - -static inline struct nd_blk_region_desc *to_blk_region_desc( - struct nd_region_desc *ndr_desc) -{ - return container_of(ndr_desc, struct nd_blk_region_desc, ndr_desc); - -} /* * Note that separate bits for locked + unlocked are defined so that @@ -257,7 +238,6 @@ struct nvdimm_bus *nvdimm_to_bus(struct nvdimm *nvdimm); struct nvdimm *to_nvdimm(struct device *dev); struct nd_region *to_nd_region(struct device *dev); struct device *nd_region_dev(struct nd_region *nd_region); -struct nd_blk_region *to_nd_blk_region(struct device *dev); struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus); struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus); const char *nvdimm_name(struct nvdimm *nvdimm); @@ -295,10 +275,6 @@ struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc); void *nd_region_provider_data(struct nd_region *nd_region); -void *nd_blk_region_provider_data(struct nd_blk_region *ndbr); -void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data); -struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr); -unsigned long nd_blk_memremap_flags(struct nd_blk_region *ndbr); unsigned int nd_region_acquire_lane(struct nd_region *nd_region); void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); u64 nd_fletcher64(void *addr, size_t len, bool le); diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 8cf1e4884fd5..17e02b64ea2e 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -189,7 +189,6 @@ static inline const char *nvdimm_cmd_name(unsigned cmd) #define ND_DEVICE_REGION_BLK 3 /* nd_region: (parent of BLK namespaces) */ #define ND_DEVICE_NAMESPACE_IO 4 /* legacy persistent memory */ #define ND_DEVICE_NAMESPACE_PMEM 5 /* PMEM namespace (may alias with BLK) */ -#define ND_DEVICE_NAMESPACE_BLK 6 /* BLK namespace (may alias with PMEM) */ #define ND_DEVICE_DAX_PMEM 7 /* Device DAX interface to pmem */ enum nd_driver_flags { @@ -198,7 +197,6 @@ enum nd_driver_flags { ND_DRIVER_REGION_BLK = 1 << ND_DEVICE_REGION_BLK, ND_DRIVER_NAMESPACE_IO = 1 << ND_DEVICE_NAMESPACE_IO, ND_DRIVER_NAMESPACE_PMEM = 1 << ND_DEVICE_NAMESPACE_PMEM, - ND_DRIVER_NAMESPACE_BLK = 1 << ND_DEVICE_NAMESPACE_BLK, ND_DRIVER_DAX_PMEM = 1 << ND_DEVICE_DAX_PMEM, }; diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c index 3ca7c32e9362..4d1a947367f9 100644 --- a/tools/testing/nvdimm/test/ndtest.c +++ b/tools/testing/nvdimm/test/ndtest.c @@ -338,62 +338,6 @@ static int ndtest_ctl(struct nvdimm_bus_descriptor *nd_desc, return 0; } -static int ndtest_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa, - void *iobuf, u64 len, int rw) -{ - struct ndtest_dimm *dimm = ndbr->blk_provider_data; - struct ndtest_blk_mmio *mmio = dimm->mmio; - struct nd_region *nd_region = &ndbr->nd_region; - unsigned int lane; - - if (!mmio) - return -ENOMEM; - - lane = nd_region_acquire_lane(nd_region); - if (rw) - memcpy(mmio->base + dpa, iobuf, len); - else { - memcpy(iobuf, mmio->base + dpa, len); - arch_invalidate_pmem(mmio->base + dpa, len); - } - - nd_region_release_lane(nd_region, lane); - - return 0; -} - -static int ndtest_blk_region_enable(struct nvdimm_bus *nvdimm_bus, - struct device *dev) -{ - struct nd_blk_region *ndbr = to_nd_blk_region(dev); - struct nvdimm *nvdimm; - struct ndtest_dimm *dimm; - struct ndtest_blk_mmio *mmio; - - nvdimm = nd_blk_region_to_dimm(ndbr); - dimm = nvdimm_provider_data(nvdimm); - - nd_blk_region_set_provider_data(ndbr, dimm); - dimm->blk_region = to_nd_region(dev); - - mmio = devm_kzalloc(dev, sizeof(struct ndtest_blk_mmio), GFP_KERNEL); - if (!mmio) - return -ENOMEM; - - mmio->base = (void __iomem *) devm_nvdimm_memremap( - dev, dimm->address, 12, nd_blk_memremap_flags(ndbr)); - if (!mmio->base) { - dev_err(dev, "%s failed to map blk dimm\n", nvdimm_name(nvdimm)); - return -ENOMEM; - } - mmio->size = dimm->size; - mmio->base_offset = 0; - - dimm->mmio = mmio; - - return 0; -} - static struct nfit_test_resource *ndtest_resource_lookup(resource_size_t addr) { int i; @@ -523,17 +467,16 @@ static int ndtest_create_region(struct ndtest_priv *p, struct ndtest_region *region) { struct nd_mapping_desc mappings[NDTEST_MAX_MAPPING]; - struct nd_blk_region_desc ndbr_desc; + struct nd_region_desc *ndr_desc, _ndr_desc; struct nd_interleave_set *nd_set; - struct nd_region_desc *ndr_desc; struct resource res; int i, ndimm = region->mapping[0].dimm; u64 uuid[2]; memset(&res, 0, sizeof(res)); memset(&mappings, 0, sizeof(mappings)); - memset(&ndbr_desc, 0, sizeof(ndbr_desc)); - ndr_desc = &ndbr_desc.ndr_desc; + memset(&_ndr_desc, 0, sizeof(_ndr_desc)); + ndr_desc = &_ndr_desc; if (!ndtest_alloc_resource(p, region->size, &res.start)) return -ENOMEM; @@ -857,10 +800,8 @@ static int ndtest_dimm_register(struct ndtest_priv *priv, struct device *dev = &priv->pdev.dev; unsigned long dimm_flags = dimm->flags; - if (dimm->num_formats > 1) { - set_bit(NDD_ALIASING, &dimm_flags); + if (dimm->num_formats > 1) set_bit(NDD_LABELING, &dimm_flags); - } if (dimm->flags & PAPR_PMEM_UNARMED_MASK) set_bit(NDD_UNARMED, &dimm_flags); From de7a9e949f4f094741f708cd05572f932d009d02 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 23 Mar 2022 22:15:49 +0530 Subject: [PATCH 11/14] drivers/nvdimm: Fix build failure when CONFIG_PERF_EVENTS is not set The following build failure occurs when CONFIG_PERF_EVENTS is not set as generic pmu functions are not visible in that scenario. |-- s390-randconfig-r044-20220313 | |-- nd_perf.c:(.text):undefined-reference-to-perf_pmu_migrate_context | |-- nd_perf.c:(.text):undefined-reference-to-perf_pmu_register | `-- nd_perf.c:(.text):undefined-reference-to-perf_pmu_unregister Similar build failure in nds32 architecture: nd_perf.c:(.text+0x21e): undefined reference to `perf_pmu_migrate_context' nd_perf.c:(.text+0x434): undefined reference to `perf_pmu_register' nd_perf.c:(.text+0x57c): undefined reference to `perf_pmu_unregister' Fix this issue by adding check for CONFIG_PERF_EVENTS config option and disabling the nvdimm perf interface incase this config is not set. Also remove function declaration of perf_pmu_migrate_context, perf_pmu_register, perf_pmu_unregister functions from nd.h as these are common pmu functions which are part of perf_event.h and since we are disabling nvdimm perf interface incase CONFIG_PERF_EVENTS option is not set, we not need to declare them in nd.h Also move the platform_device header file addition part from nd.h to nd_perf.c and add stub functions for register_nvdimm_pmu and unregister_nvdimm_pmu functions to handle CONFIG_PERF_EVENTS=n case. Fixes: 0fab1ba6ad6b ("drivers/nvdimm: Add perf interface to expose nvdimm performance stats") (Commit id based on libnvdimm-for-next tree) Signed-off-by: Kajol Jain Link: https://lore.kernel.org/all/62317124.YBQFU33+s%2FwdvWGj%25lkp@intel.com/ Reported-by: kernel test robot Link: https://lore.kernel.org/r/20220323164550.109768-1-kjain@linux.ibm.com Signed-off-by: Dan Williams --- drivers/nvdimm/Makefile | 2 +- drivers/nvdimm/nd_perf.c | 1 + include/linux/nd.h | 16 ++++++++++++---- 3 files changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index 3fb806748716..ba0296dca9db 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -15,7 +15,7 @@ nd_e820-y := e820.o libnvdimm-y := core.o libnvdimm-y += bus.o libnvdimm-y += dimm_devs.o -libnvdimm-y += nd_perf.o +libnvdimm-$(CONFIG_PERF_EVENTS) += 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 index 314415894acf..433bbb68ae64 100644 --- a/drivers/nvdimm/nd_perf.c +++ b/drivers/nvdimm/nd_perf.c @@ -10,6 +10,7 @@ #define pr_fmt(fmt) "nvdimm_pmu: " fmt #include +#include #define EVENT(_name, _code) enum{_name = _code} diff --git a/include/linux/nd.h b/include/linux/nd.h index 7b2ccbdc1cbc..b9771ba1ef87 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -9,7 +9,6 @@ #include #include #include -#include enum nvdimm_event { NVDIMM_REVALIDATE_POISON, @@ -57,15 +56,24 @@ struct nvdimm_pmu { struct cpumask arch_cpumask; }; +struct platform_device; + +#ifdef CONFIG_PERF_EVENTS 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); + +#else +static inline int register_nvdimm_pmu(struct nvdimm_pmu *nvdimm, struct platform_device *pdev) +{ + return -ENXIO; +} + +static inline void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu) { } +#endif struct nd_device_driver { struct device_driver drv; From d0007eb15c2a8113e847143c783ea83d93963741 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 23 Mar 2022 22:15:50 +0530 Subject: [PATCH 12/14] powerpc/papr_scm: Fix build failure when MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The following build failure occurs when CONFIG_PERF_EVENTS is not set as generic pmu functions are not visible in that scenario. arch/powerpc/platforms/pseries/papr_scm.c:372:35: error: ‘struct perf_event’ has no member named ‘attr’ p->nvdimm_events_map[event->attr.config], ^~ In file included from ./include/linux/list.h:5, from ./include/linux/kobject.h:19, from ./include/linux/of.h:17, from arch/powerpc/platforms/pseries/papr_scm.c:5: arch/powerpc/platforms/pseries/papr_scm.c: In function ‘papr_scm_pmu_event_init’: arch/powerpc/platforms/pseries/papr_scm.c:389:49: error: ‘struct perf_event’ has no member named ‘pmu’ struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu); ^~ ./include/linux/container_of.h:18:26: note: in definition of macro ‘container_of’ void *__mptr = (void *)(ptr); \ ^~~ arch/powerpc/platforms/pseries/papr_scm.c:389:30: note: in expansion of macro ‘to_nvdimm_pmu’ struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu); ^~~~~~~~~~~~~ In file included from ./include/linux/bits.h:22, from ./include/linux/bitops.h:6, from ./include/linux/of.h:15, from arch/powerpc/platforms/pseries/papr_scm.c:5: Fix the build issue by adding check for CONFIG_PERF_EVENTS config option and also add stub function for papr_scm_pmu_register to handle the CONFIG_PERF_EVENTS=n case. Also move the position of macro "to_nvdimm_pmu" inorder to merge it in CONFIG_PERF_EVENTS=y block. based on libnvdimm-for-next tree) Fixes: 4c08d4bbc089 ("powerpc/papr_scm: Add perf interface support") (Commit id Signed-off-by: Kajol Jain Link: https://lore.kernel.org/r/20220323164550.109768-2-kjain@linux.ibm.com Signed-off-by: Dan Williams --- arch/powerpc/platforms/pseries/papr_scm.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 4dd513d7c029..9dba9e71fde9 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -69,8 +69,6 @@ #define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS) #define PAPR_SCM_PERF_STATS_VERSION 0x1 -#define to_nvdimm_pmu(_pmu) container_of(_pmu, struct nvdimm_pmu, pmu) - /* Struct holding a single performance metric */ struct papr_scm_perf_stat { u8 stat_id[8]; @@ -346,6 +344,9 @@ static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p, return 0; } +#ifdef CONFIG_PERF_EVENTS +#define to_nvdimm_pmu(_pmu) container_of(_pmu, struct nvdimm_pmu, pmu) + static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev, u64 *count) { struct papr_scm_perf_stat *stat; @@ -558,6 +559,10 @@ pmu_err_print: dev_info(&p->pdev->dev, "nvdimm pmu didn't register rc=%d\n", rc); } +#else +static void papr_scm_pmu_register(struct papr_scm_priv *p) { } +#endif + /* * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the * health information. From 11cddee9c19f57bba335cff9787f23fb2d6d6f26 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Wed, 16 Mar 2022 06:21:33 +0100 Subject: [PATCH 13/14] MAINTAINERS: remove section LIBNVDIMM BLK: MMIO-APERTURE DRIVER Commit f8669f1d6a86 ("nvdimm/blk: Delete the block-aperture window driver") removes the file drivers/nvdimm/blk.c, but misses to adjust MAINTAINERS. Hence, ./scripts/get_maintainer.pl --self-test=patterns complains about a broken reference. The section LIBNVDIMM BLK: MMIO-APERTURE DRIVER refers to the driver in blk.c, and some more generic nvdimm code in region_devs.c. As the driver is deleted, delete the section LIBNVDIMM BLK: MMIO-APERTURE DRIVER in MAINTAINERS as well. The remaining file region_devs.c is still covered by the section LIBNVDIMM: NON-VOLATILE MEMORY DEVICE SUBSYSTEM, and all patches to region_devs.c will still reach the same developers as before. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20220316052133.26212-1-lukas.bulwahn@gmail.com Signed-off-by: Dan Williams --- MAINTAINERS | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index fca970a46e77..2a802dc83bc3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10933,17 +10933,6 @@ F: drivers/ata/ F: include/linux/ata.h F: include/linux/libata.h -LIBNVDIMM BLK: MMIO-APERTURE DRIVER -M: Dan Williams -M: Vishal Verma -M: Dave Jiang -L: nvdimm@lists.linux.dev -S: Supported -Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ -P: Documentation/nvdimm/maintainer-entry-profile.rst -F: drivers/nvdimm/blk.c -F: drivers/nvdimm/region_devs.c - LIBNVDIMM BTT: BLOCK TRANSLATION TABLE M: Vishal Verma M: Dan Williams From ada8d8d337ee970860c9844126e634df8076aa11 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 21 Mar 2022 15:04:08 -0700 Subject: [PATCH 14/14] nvdimm/blk: Fix title level make htmldocs fails with Sphinx parallel build error: docutils.utils.SystemMessage: ...nvdimm.rst:146: (SEVERE/4) Title level inconsistent: PMEM-REGIONs, Atomic Sectors, and DAX ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ The PMEM vs BLK section was removed without changing the PMEM-REGIONS... title line. Replace '^' with '_'. Fixes: f8669f1d6a86 ("nvdimm/blk: Delete the block-aperture window driver") Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20220321220408.2381974-1-trix@redhat.com Signed-off-by: Dan Williams --- Documentation/driver-api/nvdimm/nvdimm.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/driver-api/nvdimm/nvdimm.rst b/Documentation/driver-api/nvdimm/nvdimm.rst index 7917f6471092..be8587a558e1 100644 --- a/Documentation/driver-api/nvdimm/nvdimm.rst +++ b/Documentation/driver-api/nvdimm/nvdimm.rst @@ -15,7 +15,7 @@ Version 13 Supporting Documents Git Trees LIBNVDIMM PMEM - PMEM-REGIONs, Atomic Sectors, and DAX + PMEM-REGIONs, Atomic Sectors, and DAX Example NVDIMM Platform LIBNVDIMM Kernel Device Model and LIBNDCTL Userspace API LIBNDCTL: Context @@ -144,7 +144,7 @@ can be immediately attached to nd_pmem. This latter mode is called label-less or "legacy". PMEM-REGIONs, Atomic Sectors, and DAX -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +------------------------------------- For the cases where an application or filesystem still needs atomic sector update guarantees it can register a BTT on a PMEM device or partition. See