diff options
Diffstat (limited to 'drivers/base/memory.c')
| -rw-r--r-- | drivers/base/memory.c | 1101 |
1 files changed, 755 insertions, 346 deletions
diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 048cbf7d5233..751f248ca4a8 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -19,36 +19,62 @@ #include <linux/memory.h> #include <linux/memory_hotplug.h> #include <linux/mm.h> -#include <linux/mutex.h> #include <linux/stat.h> #include <linux/slab.h> +#include <linux/xarray.h> +#include <linux/export.h> #include <linux/atomic.h> #include <linux/uaccess.h> -static DEFINE_MUTEX(mem_sysfs_mutex); - #define MEMORY_CLASS_NAME "memory" -#define to_memory_block(dev) container_of(dev, struct memory_block, dev) - -static int sections_per_block; +static const char *const online_type_to_str[] = { + [MMOP_OFFLINE] = "offline", + [MMOP_ONLINE] = "online", + [MMOP_ONLINE_KERNEL] = "online_kernel", + [MMOP_ONLINE_MOVABLE] = "online_movable", +}; -static inline int base_memory_block_id(int section_nr) +int mhp_online_type_from_str(const char *str) { - return section_nr / sections_per_block; + int i; + + for (i = 0; i < ARRAY_SIZE(online_type_to_str); i++) { + if (sysfs_streq(str, online_type_to_str[i])) + return i; + } + return -EINVAL; } +#define to_memory_block(dev) container_of(dev, struct memory_block, dev) + +int sections_per_block; +EXPORT_SYMBOL(sections_per_block); + static int memory_subsys_online(struct device *dev); static int memory_subsys_offline(struct device *dev); -static struct bus_type memory_subsys = { +static const struct bus_type memory_subsys = { .name = MEMORY_CLASS_NAME, .dev_name = MEMORY_CLASS_NAME, .online = memory_subsys_online, .offline = memory_subsys_offline, }; +/* + * Memory blocks are cached in a local radix tree to avoid + * a costly linear search for the corresponding device on + * the subsystem bus. + */ +static DEFINE_XARRAY(memory_blocks); + +/* + * Memory groups, indexed by memory group id (mgid). + */ +static DEFINE_XARRAY_FLAGS(memory_groups, XA_FLAGS_ALLOC); +#define MEMORY_GROUP_MARK_DYNAMIC XA_MARK_1 + static BLOCKING_NOTIFIER_HEAD(memory_chain); int register_memory_notifier(struct notifier_block *nb) @@ -63,84 +89,88 @@ void unregister_memory_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_memory_notifier); -static ATOMIC_NOTIFIER_HEAD(memory_isolate_chain); - -int register_memory_isolate_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&memory_isolate_chain, nb); -} -EXPORT_SYMBOL(register_memory_isolate_notifier); - -void unregister_memory_isolate_notifier(struct notifier_block *nb) -{ - atomic_notifier_chain_unregister(&memory_isolate_chain, nb); -} -EXPORT_SYMBOL(unregister_memory_isolate_notifier); - static void memory_block_release(struct device *dev) { struct memory_block *mem = to_memory_block(dev); - + /* Verify that the altmap is freed */ + WARN_ON(mem->altmap); kfree(mem); } -unsigned long __weak memory_block_size_bytes(void) -{ - return MIN_MEMORY_BLOCK_SIZE; -} -static unsigned long get_memory_block_size(void) +/* Max block size to be set by memory_block_advise_max_size */ +static unsigned long memory_block_advised_size; +static bool memory_block_advised_size_queried; + +/** + * memory_block_advise_max_size() - advise memory hotplug on the max suggested + * block size, usually for alignment. + * @size: suggestion for maximum block size. must be aligned on power of 2. + * + * Early boot software (pre-allocator init) may advise archs on the max block + * size. This value can only decrease after initialization, as the intent is + * to identify the largest supported alignment for all sources. + * + * Use of this value is arch-defined, as is min/max block size. + * + * Return: 0 on success + * -EINVAL if size is 0 or not pow2 aligned + * -EBUSY if value has already been probed + */ +int __init memory_block_advise_max_size(unsigned long size) { - unsigned long block_sz; + if (!size || !is_power_of_2(size)) + return -EINVAL; - block_sz = memory_block_size_bytes(); + if (memory_block_advised_size_queried) + return -EBUSY; - /* Validate blk_sz is a power of 2 and not less than section size */ - if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) { - WARN_ON(1); - block_sz = MIN_MEMORY_BLOCK_SIZE; - } + if (memory_block_advised_size) + memory_block_advised_size = min(memory_block_advised_size, size); + else + memory_block_advised_size = size; - return block_sz; + return 0; } -/* - * use this as the physical section index that this memsection - * uses. +/** + * memory_block_advised_max_size() - query advised max hotplug block size. + * + * After the first call, the value can never change. Callers looking for the + * actual block size should use memory_block_size_bytes. This interface is + * intended for use by arch-init when initializing the hotplug block size. + * + * Return: advised size in bytes, or 0 if never set. */ +unsigned long memory_block_advised_max_size(void) +{ + memory_block_advised_size_queried = true; + return memory_block_advised_size; +} + +unsigned long __weak memory_block_size_bytes(void) +{ + return MIN_MEMORY_BLOCK_SIZE; +} +EXPORT_SYMBOL_GPL(memory_block_size_bytes); +/* Show the memory block ID, relative to the memory block size */ static ssize_t phys_index_show(struct device *dev, struct device_attribute *attr, char *buf) { struct memory_block *mem = to_memory_block(dev); - unsigned long phys_index; - phys_index = mem->start_section_nr / sections_per_block; - return sprintf(buf, "%08lx\n", phys_index); + return sysfs_emit(buf, "%08lx\n", memory_block_id(mem->start_section_nr)); } /* - * Show whether the section of memory is likely to be hot-removable + * Legacy interface that we cannot remove. Always indicate "removable" + * with CONFIG_MEMORY_HOTREMOVE - bad heuristic. */ static ssize_t removable_show(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned long i, pfn; - int ret = 1; - struct memory_block *mem = to_memory_block(dev); - - if (mem->state != MEM_ONLINE) - goto out; - - for (i = 0; i < sections_per_block; i++) { - if (!present_section_nr(mem->start_section_nr + i)) - continue; - pfn = section_nr_to_pfn(mem->start_section_nr + i); - ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION); - } - -out: - return sprintf(buf, "%d\n", ret); + return sysfs_emit(buf, "%d\n", (int)IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)); } /* @@ -150,7 +180,7 @@ static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct memory_block *mem = to_memory_block(dev); - ssize_t len = 0; + const char *output; /* * We can probably put these states in a nice little array @@ -158,71 +188,134 @@ static ssize_t state_show(struct device *dev, struct device_attribute *attr, */ switch (mem->state) { case MEM_ONLINE: - len = sprintf(buf, "online\n"); + output = "online"; break; case MEM_OFFLINE: - len = sprintf(buf, "offline\n"); + output = "offline"; break; case MEM_GOING_OFFLINE: - len = sprintf(buf, "going-offline\n"); + output = "going-offline"; break; default: - len = sprintf(buf, "ERROR-UNKNOWN-%ld\n", - mem->state); WARN_ON(1); - break; + return sysfs_emit(buf, "ERROR-UNKNOWN-%d\n", mem->state); } - return len; + return sysfs_emit(buf, "%s\n", output); } -int memory_notify(unsigned long val, void *v) +int memory_notify(enum memory_block_state state, void *v) { - return blocking_notifier_call_chain(&memory_chain, val, v); + return blocking_notifier_call_chain(&memory_chain, state, v); } -int memory_isolate_notify(unsigned long val, void *v) +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) +static unsigned long memblk_nr_poison(struct memory_block *mem); +#else +static inline unsigned long memblk_nr_poison(struct memory_block *mem) { - return atomic_notifier_call_chain(&memory_isolate_chain, val, v); + return 0; } +#endif /* - * The probe routines leave the pages uninitialized, just as the bootmem code - * does. Make sure we do not access them, but instead use only information from - * within sections. + * Must acquire mem_hotplug_lock in write mode. */ -static bool pages_correctly_probed(unsigned long start_pfn) +static int memory_block_online(struct memory_block *mem) { - unsigned long section_nr = pfn_to_section_nr(start_pfn); - unsigned long section_nr_end = section_nr + sections_per_block; - unsigned long pfn = start_pfn; + unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); + unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; + unsigned long nr_vmemmap_pages = 0; + struct zone *zone; + int ret; + + if (memblk_nr_poison(mem)) + return -EHWPOISON; + + zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group, + start_pfn, nr_pages); /* - * memmap between sections is not contiguous except with - * SPARSEMEM_VMEMMAP. We lookup the page once per section - * and assume memmap is contiguous within each section + * Although vmemmap pages have a different lifecycle than the pages + * they describe (they remain until the memory is unplugged), doing + * their initialization and accounting at memory onlining/offlining + * stage helps to keep accounting easier to follow - e.g vmemmaps + * belong to the same zone as the memory they backed. */ - for (; section_nr < section_nr_end; section_nr++) { - if (WARN_ON_ONCE(!pfn_valid(pfn))) - return false; - - if (!present_section_nr(section_nr)) { - pr_warn("section %ld pfn[%lx, %lx) not present\n", - section_nr, pfn, pfn + PAGES_PER_SECTION); - return false; - } else if (!valid_section_nr(section_nr)) { - pr_warn("section %ld pfn[%lx, %lx) no valid memmap\n", - section_nr, pfn, pfn + PAGES_PER_SECTION); - return false; - } else if (online_section_nr(section_nr)) { - pr_warn("section %ld pfn[%lx, %lx) is already online\n", - section_nr, pfn, pfn + PAGES_PER_SECTION); - return false; - } - pfn += PAGES_PER_SECTION; + if (mem->altmap) + nr_vmemmap_pages = mem->altmap->free; + + mem_hotplug_begin(); + if (nr_vmemmap_pages) { + ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); + if (ret) + goto out; + } + + ret = online_pages(start_pfn + nr_vmemmap_pages, + nr_pages - nr_vmemmap_pages, zone, mem->group); + if (ret) { + if (nr_vmemmap_pages) + mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); + goto out; + } + + /* + * Account once onlining succeeded. If the zone was unpopulated, it is + * now already properly populated. + */ + if (nr_vmemmap_pages) + adjust_present_page_count(pfn_to_page(start_pfn), mem->group, + nr_vmemmap_pages); + + mem->zone = zone; +out: + mem_hotplug_done(); + return ret; +} + +/* + * Must acquire mem_hotplug_lock in write mode. + */ +static int memory_block_offline(struct memory_block *mem) +{ + unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); + unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; + unsigned long nr_vmemmap_pages = 0; + int ret; + + if (!mem->zone) + return -EINVAL; + + /* + * Unaccount before offlining, such that unpopulated zone and kthreads + * can properly be torn down in offline_pages(). + */ + if (mem->altmap) + nr_vmemmap_pages = mem->altmap->free; + + mem_hotplug_begin(); + if (nr_vmemmap_pages) + adjust_present_page_count(pfn_to_page(start_pfn), mem->group, + -nr_vmemmap_pages); + + ret = offline_pages(start_pfn + nr_vmemmap_pages, + nr_pages - nr_vmemmap_pages, mem->zone, mem->group); + if (ret) { + /* offline_pages() failed. Account back. */ + if (nr_vmemmap_pages) + adjust_present_page_count(pfn_to_page(start_pfn), + mem->group, nr_vmemmap_pages); + goto out; } - return true; + if (nr_vmemmap_pages) + mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); + + mem->zone = NULL; +out: + mem_hotplug_done(); + return ret; } /* @@ -230,27 +323,20 @@ static bool pages_correctly_probed(unsigned long start_pfn) * OK to have direct references to sparsemem variables in here. */ static int -memory_block_action(unsigned long phys_index, unsigned long action, int online_type) +memory_block_action(struct memory_block *mem, unsigned long action) { - unsigned long start_pfn; - unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; int ret; - start_pfn = section_nr_to_pfn(phys_index); - switch (action) { case MEM_ONLINE: - if (!pages_correctly_probed(start_pfn)) - return -EBUSY; - - ret = online_pages(start_pfn, nr_pages, online_type); + ret = memory_block_online(mem); break; case MEM_OFFLINE: - ret = offline_pages(start_pfn, nr_pages); + ret = memory_block_offline(mem); break; default: WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: " - "%ld\n", __func__, phys_index, action, action); + "%ld\n", __func__, mem->start_section_nr, action, action); ret = -EINVAL; } @@ -268,9 +354,7 @@ static int memory_block_change_state(struct memory_block *mem, if (to_state == MEM_OFFLINE) mem->state = MEM_GOING_OFFLINE; - ret = memory_block_action(mem->start_section_nr, to_state, - mem->online_type); - + ret = memory_block_action(mem, to_state); mem->state = ret ? from_state_req : to_state; return ret; @@ -286,17 +370,14 @@ static int memory_subsys_online(struct device *dev) return 0; /* - * If we are called from state_store(), online_type will be - * set >= 0 Otherwise we were called from the device online - * attribute and need to set the online_type. + * When called via device_online() without configuring the online_type, + * we want to default to MMOP_ONLINE. */ - if (mem->online_type < 0) - mem->online_type = MMOP_ONLINE_KEEP; + if (mem->online_type == MMOP_OFFLINE) + mem->online_type = MMOP_ONLINE; ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE); - - /* clear online_type */ - mem->online_type = -1; + mem->online_type = MMOP_OFFLINE; return ret; } @@ -308,40 +389,27 @@ static int memory_subsys_offline(struct device *dev) if (mem->state == MEM_OFFLINE) return 0; - /* Can't offline block with non-present sections */ - if (mem->section_count != sections_per_block) - return -EINVAL; - return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE); } static ssize_t state_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { + const int online_type = mhp_online_type_from_str(buf); struct memory_block *mem = to_memory_block(dev); - int ret, online_type; + int ret; + + if (online_type < 0) + return -EINVAL; ret = lock_device_hotplug_sysfs(); if (ret) return ret; - if (sysfs_streq(buf, "online_kernel")) - online_type = MMOP_ONLINE_KERNEL; - else if (sysfs_streq(buf, "online_movable")) - online_type = MMOP_ONLINE_MOVABLE; - else if (sysfs_streq(buf, "online")) - online_type = MMOP_ONLINE_KEEP; - else if (sysfs_streq(buf, "offline")) - online_type = MMOP_OFFLINE; - else { - ret = -EINVAL; - goto err; - } - switch (online_type) { case MMOP_ONLINE_KERNEL: case MMOP_ONLINE_MOVABLE: - case MMOP_ONLINE_KEEP: + case MMOP_ONLINE: /* mem->online_type is protected by device_hotplug_lock */ mem->online_type = online_type; ret = device_online(&mem->dev); @@ -353,7 +421,6 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr, ret = -EINVAL; /* should never happen */ } -err: unlock_device_hotplug(); if (ret < 0) @@ -365,33 +432,35 @@ err: } /* - * phys_device is a bad name for this. What I really want - * is a way to differentiate between memory ranges that - * are part of physical devices that constitute - * a complete removable unit or fru. - * i.e. do these ranges belong to the same physical device, - * s.t. if I offline all of these sections I can then - * remove the physical device? + * Legacy interface that we cannot remove: s390x exposes the storage increment + * covered by a memory block, allowing for identifying which memory blocks + * comprise a storage increment. Since a memory block spans complete + * storage increments nowadays, this interface is basically unused. Other + * archs never exposed != 0. */ static ssize_t phys_device_show(struct device *dev, struct device_attribute *attr, char *buf) { struct memory_block *mem = to_memory_block(dev); - return sprintf(buf, "%d\n", mem->phys_device); + unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); + + return sysfs_emit(buf, "%d\n", + arch_get_memory_phys_device(start_pfn)); } #ifdef CONFIG_MEMORY_HOTREMOVE -static void print_allowed_zone(char *buf, int nid, unsigned long start_pfn, - unsigned long nr_pages, int online_type, - struct zone *default_zone) +static int print_allowed_zone(char *buf, int len, int nid, + struct memory_group *group, + unsigned long start_pfn, unsigned long nr_pages, + int online_type, struct zone *default_zone) { struct zone *zone; - zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages); - if (zone != default_zone) { - strcat(buf, " "); - strcat(buf, zone->name); - } + zone = zone_for_pfn_range(online_type, nid, group, start_pfn, nr_pages); + if (zone == default_zone) + return 0; + + return sysfs_emit_at(buf, len, " %s", zone->name); } static ssize_t valid_zones_show(struct device *dev, @@ -400,9 +469,10 @@ static ssize_t valid_zones_show(struct device *dev, struct memory_block *mem = to_memory_block(dev); unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; - unsigned long valid_start_pfn, valid_end_pfn; + struct memory_group *group = mem->group; struct zone *default_zone; - int nid; + int nid = mem->nid; + int len; /* * Check the existing zone. Make sure that we do that only on the @@ -410,29 +480,23 @@ static ssize_t valid_zones_show(struct device *dev, */ if (mem->state == MEM_ONLINE) { /* - * The block contains more than one zone can not be offlined. - * This can happen e.g. for ZONE_DMA and ZONE_DMA32 + * If !mem->zone, the memory block spans multiple zones and + * cannot get offlined. */ - if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, - &valid_start_pfn, &valid_end_pfn)) - return sprintf(buf, "none\n"); - start_pfn = valid_start_pfn; - strcat(buf, page_zone(pfn_to_page(start_pfn))->name); - goto out; + return sysfs_emit(buf, "%s\n", + mem->zone ? mem->zone->name : "none"); } - nid = mem->nid; - default_zone = zone_for_pfn_range(MMOP_ONLINE_KEEP, nid, start_pfn, nr_pages); - strcat(buf, default_zone->name); + default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, group, + start_pfn, nr_pages); - print_allowed_zone(buf, nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL, - default_zone); - print_allowed_zone(buf, nid, start_pfn, nr_pages, MMOP_ONLINE_MOVABLE, - default_zone); -out: - strcat(buf, "\n"); - - return strlen(buf); + len = sysfs_emit(buf, "%s", default_zone->name); + len += print_allowed_zone(buf, len, nid, group, start_pfn, nr_pages, + MMOP_ONLINE_KERNEL, default_zone); + len += print_allowed_zone(buf, len, nid, group, start_pfn, nr_pages, + MMOP_ONLINE_MOVABLE, default_zone); + len += sysfs_emit_at(buf, len, "\n"); + return len; } static DEVICE_ATTR_RO(valid_zones); #endif @@ -443,12 +507,12 @@ static DEVICE_ATTR_RO(phys_device); static DEVICE_ATTR_RO(removable); /* - * Block size attribute stuff + * Show the memory block size (shared by all memory blocks). */ static ssize_t block_size_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%lx\n", get_memory_block_size()); + return sysfs_emit(buf, "%lx\n", memory_block_size_bytes()); } static DEVICE_ATTR_RO(block_size_bytes); @@ -460,28 +524,35 @@ static DEVICE_ATTR_RO(block_size_bytes); static ssize_t auto_online_blocks_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (memhp_auto_online) - return sprintf(buf, "online\n"); - else - return sprintf(buf, "offline\n"); + return sysfs_emit(buf, "%s\n", + online_type_to_str[mhp_get_default_online_type()]); } static ssize_t auto_online_blocks_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - if (sysfs_streq(buf, "online")) - memhp_auto_online = true; - else if (sysfs_streq(buf, "offline")) - memhp_auto_online = false; - else + const int online_type = mhp_online_type_from_str(buf); + + if (online_type < 0) return -EINVAL; + mhp_set_default_online_type(online_type); return count; } static DEVICE_ATTR_RW(auto_online_blocks); +#ifdef CONFIG_CRASH_HOTPLUG +#include <linux/kexec.h> +static ssize_t crash_hotplug_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%d\n", crash_check_hotplug_support()); +} +static DEVICE_ATTR_RO(crash_hotplug); +#endif + /* * Some architectures will have custom drivers to do this, and * will not need to do it from userspace. The fake hot-add code @@ -505,11 +576,12 @@ static ssize_t probe_store(struct device *dev, struct device_attribute *attr, ret = lock_device_hotplug_sysfs(); if (ret) - goto out; + return ret; nid = memory_add_physaddr_to_nid(phys_addr); ret = __add_memory(nid, phys_addr, - MIN_MEMORY_BLOCK_SIZE * sections_per_block); + MIN_MEMORY_BLOCK_SIZE * sections_per_block, + MHP_NONE); if (ret) goto out; @@ -540,9 +612,7 @@ static ssize_t soft_offline_page_store(struct device *dev, if (kstrtoull(buf, 0, &pfn) < 0) return -EINVAL; pfn >>= PAGE_SHIFT; - if (!pfn_valid(pfn)) - return -ENXIO; - ret = soft_offline_page(pfn_to_page(pfn), 0); + ret = soft_offline_page(pfn, 0); return ret == 0 ? count : ret; } @@ -558,7 +628,9 @@ static ssize_t hard_offline_page_store(struct device *dev, if (kstrtoull(buf, 0, &pfn) < 0) return -EINVAL; pfn >>= PAGE_SHIFT; - ret = memory_failure(pfn, 0); + ret = memory_failure(pfn, MF_SW_SIMULATED); + if (ret == -EOPNOTSUPP) + ret = 0; return ret ? ret : count; } @@ -566,46 +638,35 @@ static DEVICE_ATTR_WO(soft_offline_page); static DEVICE_ATTR_WO(hard_offline_page); #endif -/* - * Note that phys_device is optional. It is here to allow for - * differentiation between which *physical* devices each - * section belongs to... - */ +/* See phys_device_show(). */ int __weak arch_get_memory_phys_device(unsigned long start_pfn) { return 0; } /* - * A reference for the returned object is held and the reference for the - * hinted object is released. + * A reference for the returned memory block device is acquired. + * + * Called under device_hotplug_lock. */ -struct memory_block *find_memory_block_hinted(struct mem_section *section, - struct memory_block *hint) +struct memory_block *find_memory_block_by_id(unsigned long block_id) { - int block_id = base_memory_block_id(__section_nr(section)); - struct device *hintdev = hint ? &hint->dev : NULL; - struct device *dev; + struct memory_block *mem; - dev = subsys_find_device_by_id(&memory_subsys, block_id, hintdev); - if (hint) - put_device(&hint->dev); - if (!dev) - return NULL; - return to_memory_block(dev); + mem = xa_load(&memory_blocks, block_id); + if (mem) + get_device(&mem->dev); + return mem; } /* - * For now, we have a linear search to go find the appropriate - * memory_block corresponding to a particular phys_index. If - * this gets to be a real problem, we can always use a radix - * tree or something here. - * - * This could be made generic for all device subsystems. + * Called under device_hotplug_lock. */ -struct memory_block *find_memory_block(struct mem_section *section) +struct memory_block *find_memory_block(unsigned long section_nr) { - return find_memory_block_hinted(section, NULL); + unsigned long block_id = memory_block_id(section_nr); + + return find_memory_block_by_id(block_id); } static struct attribute *memory_memblk_attrs[] = { @@ -619,7 +680,7 @@ static struct attribute *memory_memblk_attrs[] = { NULL }; -static struct attribute_group memory_memblk_attr_group = { +static const struct attribute_group memory_memblk_attr_group = { .attrs = memory_memblk_attrs, }; @@ -628,11 +689,7 @@ static const struct attribute_group *memory_memblk_attr_groups[] = { NULL, }; -/* - * register_memory - Setup a sysfs device for a memory block - */ -static -int register_memory(struct memory_block *memory) +static int __add_memory_block(struct memory_block *memory) { int ret; @@ -643,141 +700,221 @@ int register_memory(struct memory_block *memory) memory->dev.offline = memory->state == MEM_OFFLINE; ret = device_register(&memory->dev); - if (ret) + if (ret) { put_device(&memory->dev); + return ret; + } + ret = xa_err(xa_store(&memory_blocks, memory->dev.id, memory, + GFP_KERNEL)); + if (ret) + device_unregister(&memory->dev); return ret; } -static int init_memory_block(struct memory_block **memory, - struct mem_section *section, unsigned long state) +static struct zone *early_node_zone_for_memory_block(struct memory_block *mem, + int nid) +{ + const unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); + const unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; + struct zone *zone, *matching_zone = NULL; + pg_data_t *pgdat = NODE_DATA(nid); + int i; + + /* + * This logic only works for early memory, when the applicable zones + * already span the memory block. We don't expect overlapping zones on + * a single node for early memory. So if we're told that some PFNs + * of a node fall into this memory block, we can assume that all node + * zones that intersect with the memory block are actually applicable. + * No need to look at the memmap. + */ + for (i = 0; i < MAX_NR_ZONES; i++) { + zone = pgdat->node_zones + i; + if (!populated_zone(zone)) + continue; + if (!zone_intersects(zone, start_pfn, nr_pages)) + continue; + if (!matching_zone) { + matching_zone = zone; + continue; + } + /* Spans multiple zones ... */ + matching_zone = NULL; + break; + } + return matching_zone; +} + +#ifdef CONFIG_NUMA +/** + * memory_block_add_nid_early() - Indicate that early system RAM falling into + * this memory block device (partially) belongs + * to the given node. + * @mem: The memory block device. + * @nid: The node id. + * + * Indicate that early system RAM falling into this memory block (partially) + * belongs to the given node. This will also properly set/adjust mem->zone based + * on the zone ranges of the given node. + * + * Memory hotplug handles this on memory block creation, where we can only have + * a single nid span a memory block. + */ +void memory_block_add_nid_early(struct memory_block *mem, int nid) +{ + if (mem->nid != nid) { + /* + * For early memory we have to determine the zone when setting + * the node id and handle multiple nodes spanning a single + * memory block by indicate via zone == NULL that we're not + * dealing with a single zone. So if we're setting the node id + * the first time, determine if there is a single zone. If we're + * setting the node id a second time to a different node, + * invalidate the single detected zone. + */ + if (mem->nid == NUMA_NO_NODE) + mem->zone = early_node_zone_for_memory_block(mem, nid); + else + mem->zone = NULL; + /* + * If this memory block spans multiple nodes, we only indicate + * the last processed node. If we span multiple nodes (not applicable + * to hotplugged memory), zone == NULL will prohibit memory offlining + * and consequently unplug. + */ + mem->nid = nid; + } +} +#endif + +static int add_memory_block(unsigned long block_id, int nid, unsigned long state, + struct vmem_altmap *altmap, + struct memory_group *group) { struct memory_block *mem; - unsigned long start_pfn; - int scn_nr; int ret = 0; + mem = find_memory_block_by_id(block_id); + if (mem) { + put_device(&mem->dev); + return -EEXIST; + } mem = kzalloc(sizeof(*mem), GFP_KERNEL); if (!mem) return -ENOMEM; - scn_nr = __section_nr(section); - mem->start_section_nr = - base_memory_block_id(scn_nr) * sections_per_block; - mem->end_section_nr = mem->start_section_nr + sections_per_block - 1; + mem->start_section_nr = block_id * sections_per_block; mem->state = state; - start_pfn = section_nr_to_pfn(mem->start_section_nr); - mem->phys_device = arch_get_memory_phys_device(start_pfn); + mem->nid = nid; + mem->altmap = altmap; + INIT_LIST_HEAD(&mem->group_next); - ret = register_memory(mem); - - *memory = mem; - return ret; -} +#ifndef CONFIG_NUMA + if (state == MEM_ONLINE) + /* + * MEM_ONLINE at this point implies early memory. With NUMA, + * we'll determine the zone when setting the node id via + * memory_block_add_nid(). Memory hotplug updated the zone + * manually when memory onlining/offlining succeeds. + */ + mem->zone = early_node_zone_for_memory_block(mem, NUMA_NO_NODE); +#endif /* CONFIG_NUMA */ -static int add_memory_block(int base_section_nr) -{ - struct memory_block *mem; - int i, ret, section_count = 0, section_nr; + ret = __add_memory_block(mem); + if (ret) + return ret; - for (i = base_section_nr; - i < base_section_nr + sections_per_block; - i++) { - if (!present_section_nr(i)) - continue; - if (section_count == 0) - section_nr = i; - section_count++; + if (group) { + mem->group = group; + list_add(&mem->group_next, &group->memory_blocks); } - if (section_count == 0) - return 0; - ret = init_memory_block(&mem, __nr_to_section(section_nr), MEM_ONLINE); - if (ret) - return ret; - mem->section_count = section_count; return 0; } -/* - * need an interface for the VM to add new memory regions, - * but without onlining it. - */ -int hotplug_memory_register(int nid, struct mem_section *section) +static void remove_memory_block(struct memory_block *memory) { - int ret = 0; - struct memory_block *mem; + if (WARN_ON_ONCE(memory->dev.bus != &memory_subsys)) + return; - mutex_lock(&mem_sysfs_mutex); + WARN_ON(xa_erase(&memory_blocks, memory->dev.id) == NULL); - mem = find_memory_block(section); - if (mem) { - mem->section_count++; - put_device(&mem->dev); - } else { - ret = init_memory_block(&mem, section, MEM_OFFLINE); - if (ret) - goto out; - mem->section_count++; + if (memory->group) { + list_del(&memory->group_next); + memory->group = NULL; } -out: - mutex_unlock(&mem_sysfs_mutex); - return ret; -} - -#ifdef CONFIG_MEMORY_HOTREMOVE -static void -unregister_memory(struct memory_block *memory) -{ - BUG_ON(memory->dev.bus != &memory_subsys); - - /* drop the ref. we got in remove_memory_section() */ + /* drop the ref. we got via find_memory_block() */ put_device(&memory->dev); device_unregister(&memory->dev); } -static int remove_memory_section(unsigned long node_id, - struct mem_section *section, int phys_device) +/* + * Create memory block devices for the given memory area. Start and size + * have to be aligned to memory block granularity. Memory block devices + * will be initialized as offline. + * + * Called under device_hotplug_lock. + */ +int create_memory_block_devices(unsigned long start, unsigned long size, + int nid, struct vmem_altmap *altmap, + struct memory_group *group) { + const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start)); + unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size)); struct memory_block *mem; + unsigned long block_id; + int ret = 0; - mutex_lock(&mem_sysfs_mutex); - - /* - * Some users of the memory hotplug do not want/need memblock to - * track all sections. Skip over those. - */ - mem = find_memory_block(section); - if (!mem) - goto out_unlock; - - unregister_mem_sect_under_nodes(mem, __section_nr(section)); - - mem->section_count--; - if (mem->section_count == 0) - unregister_memory(mem); - else - put_device(&mem->dev); + if (WARN_ON_ONCE(!IS_ALIGNED(start, memory_block_size_bytes()) || + !IS_ALIGNED(size, memory_block_size_bytes()))) + return -EINVAL; -out_unlock: - mutex_unlock(&mem_sysfs_mutex); - return 0; + for (block_id = start_block_id; block_id != end_block_id; block_id++) { + ret = add_memory_block(block_id, nid, MEM_OFFLINE, altmap, group); + if (ret) + break; + } + if (ret) { + end_block_id = block_id; + for (block_id = start_block_id; block_id != end_block_id; + block_id++) { + mem = find_memory_block_by_id(block_id); + if (WARN_ON_ONCE(!mem)) + continue; + remove_memory_block(mem); + } + } + return ret; } -int unregister_memory_section(struct mem_section *section) +/* + * Remove memory block devices for the given memory area. Start and size + * have to be aligned to memory block granularity. Memory block devices + * have to be offline. + * + * Called under device_hotplug_lock. + */ +void remove_memory_block_devices(unsigned long start, unsigned long size) { - if (!present_section(section)) - return -EINVAL; + const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start)); + const unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size)); + struct memory_block *mem; + unsigned long block_id; - return remove_memory_section(0, section, 0); -} -#endif /* CONFIG_MEMORY_HOTREMOVE */ + if (WARN_ON_ONCE(!IS_ALIGNED(start, memory_block_size_bytes()) || + !IS_ALIGNED(size, memory_block_size_bytes()))) + return; -/* return true if the memory block is offlined, otherwise, return false */ -bool is_memblock_offlined(struct memory_block *mem) -{ - return mem->state == MEM_OFFLINE; + for (block_id = start_block_id; block_id != end_block_id; block_id++) { + mem = find_memory_block_by_id(block_id); + if (WARN_ON_ONCE(!mem)) + continue; + num_poisoned_pages_sub(-1UL, memblk_nr_poison(mem)); + unregister_memory_block_under_nodes(mem); + remove_memory_block(mem); + } } static struct attribute *memory_root_attrs[] = { @@ -792,10 +929,13 @@ static struct attribute *memory_root_attrs[] = { &dev_attr_block_size_bytes.attr, &dev_attr_auto_online_blocks.attr, +#ifdef CONFIG_CRASH_HOTPLUG + &dev_attr_crash_hotplug.attr, +#endif NULL }; -static struct attribute_group memory_root_attr_group = { +static const struct attribute_group memory_root_attr_group = { .attrs = memory_root_attrs, }; @@ -805,37 +945,306 @@ static const struct attribute_group *memory_root_attr_groups[] = { }; /* - * Initialize the sysfs support for memory devices... + * Initialize the sysfs support for memory devices. At the time this function + * is called, we cannot have concurrent creation/deletion of memory block + * devices, the device_hotplug_lock is not needed. */ -int __init memory_dev_init(void) +void __init memory_dev_init(void) { - unsigned int i; int ret; - int err; - unsigned long block_sz; + unsigned long block_sz, block_id, nr; + + /* Validate the configured memory block size */ + block_sz = memory_block_size_bytes(); + if (!is_power_of_2(block_sz) || block_sz < MIN_MEMORY_BLOCK_SIZE) + panic("Memory block size not suitable: 0x%lx\n", block_sz); + sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; ret = subsys_system_register(&memory_subsys, memory_root_attr_groups); if (ret) - goto out; - - block_sz = get_memory_block_size(); - sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; + panic("%s() failed to register subsystem: %d\n", __func__, ret); /* - * Create entries for memory sections that were found - * during boot and have been initialized + * Create entries for memory sections that were found during boot + * and have been initialized. Use @block_id to track the last + * handled block and initialize it to an invalid value (ULONG_MAX) + * to bypass the block ID matching check for the first present + * block so that it can be covered. */ - mutex_lock(&mem_sysfs_mutex); - for (i = 0; i <= __highest_present_section_nr; - i += sections_per_block) { - err = add_memory_block(i); - if (!ret) - ret = err; + block_id = ULONG_MAX; + for_each_present_section_nr(0, nr) { + if (block_id != ULONG_MAX && memory_block_id(nr) == block_id) + continue; + + block_id = memory_block_id(nr); + ret = add_memory_block(block_id, NUMA_NO_NODE, MEM_ONLINE, NULL, NULL); + if (ret) { + panic("%s() failed to add memory block: %d\n", + __func__, ret); + } } - mutex_unlock(&mem_sysfs_mutex); +} -out: - if (ret) - printk(KERN_ERR "%s() failed: %d\n", __func__, ret); +/** + * walk_memory_blocks - walk through all present memory blocks overlapped + * by the range [start, start + size) + * + * @start: start address of the memory range + * @size: size of the memory range + * @arg: argument passed to func + * @func: callback for each memory section walked + * + * This function walks through all present memory blocks overlapped by the + * range [start, start + size), calling func on each memory block. + * + * In case func() returns an error, walking is aborted and the error is + * returned. + * + * Called under device_hotplug_lock. + */ +int walk_memory_blocks(unsigned long start, unsigned long size, + void *arg, walk_memory_blocks_func_t func) +{ + const unsigned long start_block_id = phys_to_block_id(start); + const unsigned long end_block_id = phys_to_block_id(start + size - 1); + struct memory_block *mem; + unsigned long block_id; + int ret = 0; + + if (!size) + return 0; + + for (block_id = start_block_id; block_id <= end_block_id; block_id++) { + mem = find_memory_block_by_id(block_id); + if (!mem) + continue; + + ret = func(mem, arg); + put_device(&mem->dev); + if (ret) + break; + } return ret; } + +struct for_each_memory_block_cb_data { + walk_memory_blocks_func_t func; + void *arg; +}; + +static int for_each_memory_block_cb(struct device *dev, void *data) +{ + struct memory_block *mem = to_memory_block(dev); + struct for_each_memory_block_cb_data *cb_data = data; + + return cb_data->func(mem, cb_data->arg); +} + +/** + * for_each_memory_block - walk through all present memory blocks + * + * @arg: argument passed to func + * @func: callback for each memory block walked + * + * This function walks through all present memory blocks, calling func on + * each memory block. + * + * In case func() returns an error, walking is aborted and the error is + * returned. + */ +int for_each_memory_block(void *arg, walk_memory_blocks_func_t func) +{ + struct for_each_memory_block_cb_data cb_data = { + .func = func, + .arg = arg, + }; + + return bus_for_each_dev(&memory_subsys, NULL, &cb_data, + for_each_memory_block_cb); +} + +/* + * This is an internal helper to unify allocation and initialization of + * memory groups. Note that the passed memory group will be copied to a + * dynamically allocated memory group. After this call, the passed + * memory group should no longer be used. + */ +static int memory_group_register(struct memory_group group) +{ + struct memory_group *new_group; + uint32_t mgid; + int ret; + + if (!node_possible(group.nid)) + return -EINVAL; + + new_group = kzalloc(sizeof(group), GFP_KERNEL); + if (!new_group) + return -ENOMEM; + *new_group = group; + INIT_LIST_HEAD(&new_group->memory_blocks); + + ret = xa_alloc(&memory_groups, &mgid, new_group, xa_limit_31b, + GFP_KERNEL); + if (ret) { + kfree(new_group); + return ret; + } else if (group.is_dynamic) { + xa_set_mark(&memory_groups, mgid, MEMORY_GROUP_MARK_DYNAMIC); + } + return mgid; +} + +/** + * memory_group_register_static() - Register a static memory group. + * @nid: The node id. + * @max_pages: The maximum number of pages we'll have in this static memory + * group. + * + * Register a new static memory group and return the memory group id. + * All memory in the group belongs to a single unit, such as a DIMM. All + * memory belonging to a static memory group is added in one go to be removed + * in one go -- it's static. + * + * Returns an error if out of memory, if the node id is invalid, if no new + * memory groups can be registered, or if max_pages is invalid (0). Otherwise, + * returns the new memory group id. + */ +int memory_group_register_static(int nid, unsigned long max_pages) +{ + struct memory_group group = { + .nid = nid, + .s = { + .max_pages = max_pages, + }, + }; + + if (!max_pages) + return -EINVAL; + return memory_group_register(group); +} +EXPORT_SYMBOL_GPL(memory_group_register_static); + +/** + * memory_group_register_dynamic() - Register a dynamic memory group. + * @nid: The node id. + * @unit_pages: Unit in pages in which is memory added/removed in this dynamic + * memory group. + * + * Register a new dynamic memory group and return the memory group id. + * Memory within a dynamic memory group is added/removed dynamically + * in unit_pages. + * + * Returns an error if out of memory, if the node id is invalid, if no new + * memory groups can be registered, or if unit_pages is invalid (0, not a + * power of two, smaller than a single memory block). Otherwise, returns the + * new memory group id. + */ +int memory_group_register_dynamic(int nid, unsigned long unit_pages) +{ + struct memory_group group = { + .nid = nid, + .is_dynamic = true, + .d = { + .unit_pages = unit_pages, + }, + }; + + if (!unit_pages || !is_power_of_2(unit_pages) || + unit_pages < PHYS_PFN(memory_block_size_bytes())) + return -EINVAL; + return memory_group_register(group); +} +EXPORT_SYMBOL_GPL(memory_group_register_dynamic); + +/** + * memory_group_unregister() - Unregister a memory group. + * @mgid: the memory group id + * + * Unregister a memory group. If any memory block still belongs to this + * memory group, unregistering will fail. + * + * Returns -EINVAL if the memory group id is invalid, returns -EBUSY if some + * memory blocks still belong to this memory group and returns 0 if + * unregistering succeeded. + */ +int memory_group_unregister(int mgid) +{ + struct memory_group *group; + + if (mgid < 0) + return -EINVAL; + + group = xa_load(&memory_groups, mgid); + if (!group) + return -EINVAL; + if (!list_empty(&group->memory_blocks)) + return -EBUSY; + xa_erase(&memory_groups, mgid); + kfree(group); + return 0; +} +EXPORT_SYMBOL_GPL(memory_group_unregister); + +/* + * This is an internal helper only to be used in core memory hotplug code to + * lookup a memory group. We don't care about locking, as we don't expect a + * memory group to get unregistered while adding memory to it -- because + * the group and the memory is managed by the same driver. + */ +struct memory_group *memory_group_find_by_id(int mgid) +{ + return xa_load(&memory_groups, mgid); +} + +/* + * This is an internal helper only to be used in core memory hotplug code to + * walk all dynamic memory groups excluding a given memory group, either + * belonging to a specific node, or belonging to any node. + */ +int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, + struct memory_group *excluded, void *arg) +{ + struct memory_group *group; + unsigned long index; + int ret = 0; + + xa_for_each_marked(&memory_groups, index, group, + MEMORY_GROUP_MARK_DYNAMIC) { + if (group == excluded) + continue; +#ifdef CONFIG_NUMA + if (nid != NUMA_NO_NODE && group->nid != nid) + continue; +#endif /* CONFIG_NUMA */ + ret = func(group, arg); + if (ret) + break; + } + return ret; +} + +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) +void memblk_nr_poison_inc(unsigned long pfn) +{ + const unsigned long block_id = pfn_to_block_id(pfn); + struct memory_block *mem = find_memory_block_by_id(block_id); + + if (mem) + atomic_long_inc(&mem->nr_hwpoison); +} + +void memblk_nr_poison_sub(unsigned long pfn, long i) +{ + const unsigned long block_id = pfn_to_block_id(pfn); + struct memory_block *mem = find_memory_block_by_id(block_id); + + if (mem) + atomic_long_sub(i, &mem->nr_hwpoison); +} + +static unsigned long memblk_nr_poison(struct memory_block *mem) +{ + return atomic_long_read(&mem->nr_hwpoison); +} +#endif |