diff options
Diffstat (limited to 'drivers/base')
| -rw-r--r-- | drivers/base/Makefile | 2 | ||||
| -rw-r--r-- | drivers/base/arch_numa.c | 92 | ||||
| -rw-r--r-- | drivers/base/arch_topology.c | 2 | ||||
| -rw-r--r-- | drivers/base/node.c | 9 | ||||
| -rw-r--r-- | drivers/base/power/main.c | 85 |
5 files changed, 141 insertions, 49 deletions
diff --git a/drivers/base/Makefile b/drivers/base/Makefile index ef8e44a7d288..02f7f1358e86 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -13,7 +13,7 @@ obj-y += power/ obj-$(CONFIG_ISA_BUS_API) += isa.o obj-y += firmware_loader/ obj-$(CONFIG_NUMA) += node.o -obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o +obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o ifeq ($(CONFIG_SYSFS),y) obj-$(CONFIG_MODULES) += module.o endif diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 00fb4120a5b3..bc1876915457 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -14,6 +14,7 @@ #include <linux/of.h> #include <asm/sections.h> +#include <asm/pgalloc.h> struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -165,25 +166,86 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free_early(__pa(ptr), size); + memblock_free(ptr, size); } +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK +static void __init pcpu_populate_pte(unsigned long addr) +{ + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + pud_t *new; + + new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!new) + goto err_alloc; + p4d_populate(&init_mm, p4d, new); + } + + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) { + pmd_t *new; + + new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!new) + goto err_alloc; + pud_populate(&init_mm, pud, new); + } + + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) { + pte_t *new; + + new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!new) + goto err_alloc; + pmd_populate_kernel(&init_mm, pmd, new); + } + + return; + +err_alloc: + panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); +} +#endif + void __init setup_per_cpu_areas(void) { unsigned long delta; unsigned int cpu; - int rc; + int rc = -EINVAL; + + if (pcpu_chosen_fc != PCPU_FC_PAGE) { + /* + * Always reserve area for module percpu variables. That's + * what the legacy allocator did. + */ + rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, + PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, + pcpu_cpu_distance, + pcpu_fc_alloc, pcpu_fc_free); +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK + if (rc < 0) + pr_warn("PERCPU: %s allocator failed (%d), falling back to page size\n", + pcpu_fc_names[pcpu_chosen_fc], rc); +#endif + } - /* - * Always reserve area for module percpu variables. That's - * what the legacy allocator did. - */ - rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, - PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, - pcpu_cpu_distance, - pcpu_fc_alloc, pcpu_fc_free); +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK + if (rc < 0) + rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, + pcpu_fc_alloc, + pcpu_fc_free, + pcpu_populate_pte); +#endif if (rc < 0) - panic("Failed to initialize percpu areas."); + panic("Failed to initialize percpu areas (err=%d).", rc); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) @@ -264,7 +326,7 @@ void __init numa_free_distance(void) size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - memblock_free_ptr(numa_distance, size); + memblock_free(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; } @@ -275,15 +337,13 @@ void __init numa_free_distance(void) static int __init numa_alloc_distance(void) { size_t size; - u64 phys; int i, j; size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]); - phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0, PFN_PHYS(max_pfn)); - if (WARN_ON(!phys)) + numa_distance = memblock_alloc(size, PAGE_SIZE); + if (WARN_ON(!numa_distance)) return -ENOMEM; - numa_distance = __va(phys); numa_distance_cnt = nr_node_ids; /* fill with the default distances */ diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 981e72a3dafb..ff16a36a908b 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -677,6 +677,8 @@ void remove_cpu_topology(unsigned int cpu) cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); for_each_cpu(sibling, topology_sibling_cpumask(cpu)) cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); + for_each_cpu(sibling, topology_cluster_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_cluster_cpumask(sibling)); for_each_cpu(sibling, topology_llc_cpumask(cpu)) cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling)); diff --git a/drivers/base/node.c b/drivers/base/node.c index c56d34f8158f..b5a4ba18f9f9 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -629,7 +629,7 @@ static void node_device_release(struct device *dev) { struct node *node = to_node(dev); -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) /* * We schedule the work only when a memory section is * onlined/offlined on this node. When we come here, @@ -782,7 +782,7 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) return 0; } -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG static int __ref get_nid_for_pfn(unsigned long pfn) { #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -958,10 +958,9 @@ static int node_memory_callback(struct notifier_block *self, return NOTIFY_OK; } #endif /* CONFIG_HUGETLBFS */ -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ +#endif /* CONFIG_MEMORY_HOTPLUG */ -#if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \ - !defined(CONFIG_HUGETLBFS) +#if !defined(CONFIG_MEMORY_HOTPLUG) || !defined(CONFIG_HUGETLBFS) static inline int node_memory_callback(struct notifier_block *self, unsigned long action, void *arg) { diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index ac4dde8fdb8b..f4d0c555de29 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -710,6 +710,7 @@ static void dpm_noirq_resume_devices(pm_message_t state) dev = to_device(dpm_noirq_list.next); get_device(dev); list_move_tail(&dev->power.entry, &dpm_late_early_list); + mutex_unlock(&dpm_list_mtx); if (!is_async(dev)) { @@ -724,8 +725,9 @@ static void dpm_noirq_resume_devices(pm_message_t state) } } - mutex_lock(&dpm_list_mtx); put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -849,6 +851,7 @@ void dpm_resume_early(pm_message_t state) dev = to_device(dpm_late_early_list.next); get_device(dev); list_move_tail(&dev->power.entry, &dpm_suspended_list); + mutex_unlock(&dpm_list_mtx); if (!is_async(dev)) { @@ -862,8 +865,10 @@ void dpm_resume_early(pm_message_t state) pm_dev_err(dev, state, " early", error); } } - mutex_lock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -1026,7 +1031,12 @@ void dpm_resume(pm_message_t state) } if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list); + + mutex_unlock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -1104,14 +1114,16 @@ void dpm_complete(pm_message_t state) get_device(dev); dev->power.is_prepared = false; list_move(&dev->power.entry, &list); + mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); device_complete(dev, state); trace_device_pm_callback_end(dev, 0); - mutex_lock(&dpm_list_mtx); put_device(dev); + + mutex_lock(&dpm_list_mtx); } list_splice(&list, &dpm_list); mutex_unlock(&dpm_list_mtx); @@ -1296,17 +1308,21 @@ static int dpm_noirq_suspend_devices(pm_message_t state) error = device_suspend_noirq(dev); mutex_lock(&dpm_list_mtx); + if (error) { pm_dev_err(dev, state, " noirq", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; - } - if (!list_empty(&dev->power.entry)) + } else if (!list_empty(&dev->power.entry)) { list_move(&dev->power.entry, &dpm_noirq_list); + } + + mutex_unlock(&dpm_list_mtx); + put_device(dev); - if (async_error) + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1463,6 +1479,7 @@ int dpm_suspend_late(pm_message_t state) int error = 0; trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true); + wake_up_all_idle_cpus(); mutex_lock(&dpm_list_mtx); pm_transition = state; async_error = 0; @@ -1471,23 +1488,28 @@ int dpm_suspend_late(pm_message_t state) struct device *dev = to_device(dpm_suspended_list.prev); get_device(dev); + mutex_unlock(&dpm_list_mtx); error = device_suspend_late(dev); mutex_lock(&dpm_list_mtx); + if (!list_empty(&dev->power.entry)) list_move(&dev->power.entry, &dpm_late_early_list); if (error) { pm_dev_err(dev, state, " late", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; } + + mutex_unlock(&dpm_list_mtx); + put_device(dev); - if (async_error) + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1747,21 +1769,27 @@ int dpm_suspend(pm_message_t state) struct device *dev = to_device(dpm_prepared_list.prev); get_device(dev); + mutex_unlock(&dpm_list_mtx); error = device_suspend(dev); mutex_lock(&dpm_list_mtx); + if (error) { pm_dev_err(dev, state, "", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; - } - if (!list_empty(&dev->power.entry)) + } else if (!list_empty(&dev->power.entry)) { list_move(&dev->power.entry, &dpm_suspended_list); + } + + mutex_unlock(&dpm_list_mtx); + put_device(dev); - if (async_error) + + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1878,6 +1906,7 @@ int dpm_prepare(pm_message_t state) struct device *dev = to_device(dpm_list.next); get_device(dev); + mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); @@ -1885,21 +1914,23 @@ int dpm_prepare(pm_message_t state) trace_device_pm_callback_end(dev, error); mutex_lock(&dpm_list_mtx); - if (error) { - if (error == -EAGAIN) { - put_device(dev); - error = 0; - continue; - } + + if (!error) { + dev->power.is_prepared = true; + if (!list_empty(&dev->power.entry)) + list_move_tail(&dev->power.entry, &dpm_prepared_list); + } else if (error == -EAGAIN) { + error = 0; + } else { dev_info(dev, "not prepared for power transition: code %d\n", error); - put_device(dev); - break; } - dev->power.is_prepared = true; - if (!list_empty(&dev->power.entry)) - list_move_tail(&dev->power.entry, &dpm_prepared_list); + + mutex_unlock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); trace_suspend_resume(TPS("dpm_prepare"), state.event, false); |