// SPDX-License-Identifier: GPL-2.0/* * Memory subsystem support * * Written by Matt Tolentino <matthew.e.tolentino@intel.com> *            Dave Hansen <haveblue@us.ibm.com> * * This file provides the necessary infrastructure to represent * a SPARSEMEM-memory-model system's physical memory in /sysfs. * All arch-independent code that assumes MEMORY_HOTPLUG requires * SPARSEMEM should be contained here, or in mm/memory_hotplug.c. */ #include <linux/module.h>#include <linux/init.h>#include <linux/topology.h>#include <linux/capability.h>#include <linux/device.h>#include <linux/memory.h>#include <linux/memory_hotplug.h>#include <linux/mm.h>#include <linux/stat.h>#include <linux/slab.h>#include <linux/xarray.h> #include <linux/atomic.h>#include <linux/uaccess.h> #define MEMORY_CLASS_NAME	"memory" static const char *const online_type_to_str[] = {	[MMOP_OFFLINE] = "offline",	[MMOP_ONLINE] = "online",	[MMOP_ONLINE_KERNEL] = "online_kernel",	[MMOP_ONLINE_MOVABLE] = "online_movable",}; int memhp_online_type_from_str(const char *str){	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) static int sections_per_block; static inline unsigned long base_memory_block_id(unsigned long section_nr){	return section_nr / sections_per_block;} static inline unsigned long pfn_to_block_id(unsigned long pfn){	return base_memory_block_id(pfn_to_section_nr(pfn));} static inline unsigned long phys_to_block_id(unsigned long phys){	return pfn_to_block_id(PFN_DOWN(phys));} static int memory_subsys_online(struct device *dev);static int memory_subsys_offline(struct device *dev); static 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); static BLOCKING_NOTIFIER_HEAD(memory_chain); int register_memory_notifier(struct notifier_block *nb){	return blocking_notifier_chain_register(&memory_chain, nb);}EXPORT_SYMBOL(register_memory_notifier); void unregister_memory_notifier(struct notifier_block *nb){	blocking_notifier_chain_unregister(&memory_chain, nb);}EXPORT_SYMBOL(unregister_memory_notifier); static void memory_block_release(struct device *dev){	struct memory_block *mem = to_memory_block(dev); 	kfree(mem);} unsigned long __weak memory_block_size_bytes(void){	return MIN_MEMORY_BLOCK_SIZE;}EXPORT_SYMBOL_GPL(memory_block_size_bytes); /* * Show the first physical section index (number) of this memory block. */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);} /* * 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){	return sprintf(buf, "%d\n", (int)IS_ENABLED(CONFIG_MEMORY_HOTREMOVE));} /* * online, offline, going offline, etc. */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; 	/*	 * We can probably put these states in a nice little array	 * so that they're not open-coded	 */	switch (mem->state) {	case MEM_ONLINE:		len = sprintf(buf, "online\n");		break;	case MEM_OFFLINE:		len = sprintf(buf, "offline\n");		break;	case MEM_GOING_OFFLINE:		len = sprintf(buf, "going-offline\n");		break;	default:		len = sprintf(buf, "ERROR-UNKNOWN-%ld\n",				mem->state);		WARN_ON(1);		break;	} 	return len;} int memory_notify(unsigned long val, void *v){	return blocking_notifier_call_chain(&memory_chain, val, v);} /* * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is * OK to have direct references to sparsemem variables in here. */static intmemory_block_action(unsigned long start_section_nr, unsigned long action,		    int online_type, int nid){	unsigned long start_pfn;	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;	int ret; 	start_pfn = section_nr_to_pfn(start_section_nr); 	switch (action) {	case MEM_ONLINE:		ret = online_pages(start_pfn, nr_pages, online_type, nid);		break;	case MEM_OFFLINE:		ret = offline_pages(start_pfn, nr_pages);		break;	default:		WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "		     "%ld\n", __func__, start_section_nr, action, action);		ret = -EINVAL;	} 	return ret;} static int memory_block_change_state(struct memory_block *mem,		unsigned long to_state, unsigned long from_state_req){	int ret = 0; 	if (mem->state != from_state_req)		return -EINVAL; 	if (to_state == MEM_OFFLINE)		mem->state = MEM_GOING_OFFLINE; 	ret = memory_block_action(mem->start_section_nr, to_state,				  mem->online_type, mem->nid); 	mem->state = ret ? from_state_req : to_state; 	return ret;} /* The device lock serializes operations on memory_subsys_[online|offline] */static int memory_subsys_online(struct device *dev){	struct memory_block *mem = to_memory_block(dev);	int ret; 	if (mem->state == MEM_ONLINE)		return 0; 	/*	 * When called via device_online() without configuring the online_type,	 * we want to default to MMOP_ONLINE.	 */	if (mem->online_type == MMOP_OFFLINE)		mem->online_type = MMOP_ONLINE; 	ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);	mem->online_type = MMOP_OFFLINE; 	return ret;} static int memory_subsys_offline(struct device *dev){	struct memory_block *mem = to_memory_block(dev); 	if (mem->state == MEM_OFFLINE)		return 0; 	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 = memhp_online_type_from_str(buf);	struct memory_block *mem = to_memory_block(dev);	int ret; 	if (online_type < 0)		return -EINVAL; 	ret = lock_device_hotplug_sysfs();	if (ret)		return ret; 	switch (online_type) {	case MMOP_ONLINE_KERNEL:	case MMOP_ONLINE_MOVABLE:	case MMOP_ONLINE:		/* mem->online_type is protected by device_hotplug_lock */		mem->online_type = online_type;		ret = device_online(&mem->dev);		break;	case MMOP_OFFLINE:		ret = device_offline(&mem->dev);		break;	default:		ret = -EINVAL; /* should never happen */	} 	unlock_device_hotplug(); 	if (ret < 0)		return ret;	if (ret)		return -EINVAL; 	return count;} /* * 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? */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);} #ifdef CONFIG_MEMORY_HOTREMOVEstatic void print_allowed_zone(char *buf, int nid, 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);	}} static ssize_t valid_zones_show(struct device *dev,				struct device_attribute *attr, char *buf){	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;	struct zone *default_zone;	int nid; 	/*	 * Check the existing zone. Make sure that we do that only on the	 * online nodes otherwise the page_zone is not reliable	 */	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		 */		default_zone = test_pages_in_a_zone(start_pfn,						    start_pfn + nr_pages);		if (!default_zone)			return sprintf(buf, "none\n");		strcat(buf, default_zone->name);		goto out;	} 	nid = mem->nid;	default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, start_pfn,					  nr_pages);	strcat(buf, default_zone->name); 	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);}static DEVICE_ATTR_RO(valid_zones);#endif static DEVICE_ATTR_RO(phys_index);static DEVICE_ATTR_RW(state);static DEVICE_ATTR_RO(phys_device);static DEVICE_ATTR_RO(removable); /* * 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", memory_block_size_bytes());} static DEVICE_ATTR_RO(block_size_bytes); /* * Memory auto online policy. */ static ssize_t auto_online_blocks_show(struct device *dev,				       struct device_attribute *attr, char *buf){	return sprintf(buf, "%s\n",		       online_type_to_str[memhp_default_online_type]);} static ssize_t auto_online_blocks_store(struct device *dev,					struct device_attribute *attr,					const char *buf, size_t count){	const int online_type = memhp_online_type_from_str(buf); 	if (online_type < 0)		return -EINVAL; 	memhp_default_online_type = online_type;	return count;} static DEVICE_ATTR_RW(auto_online_blocks); /* * Some architectures will have custom drivers to do this, and * will not need to do it from userspace.  The fake hot-add code * as well as ppc64 will do all of their discovery in userspace * and will require this interface. */#ifdef CONFIG_ARCH_MEMORY_PROBEstatic ssize_t probe_store(struct device *dev, struct device_attribute *attr,			   const char *buf, size_t count){	u64 phys_addr;	int nid, ret;	unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block; 	ret = kstrtoull(buf, 0, &phys_addr);	if (ret)		return ret; 	if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1))		return -EINVAL; 	ret = lock_device_hotplug_sysfs();	if (ret)		return ret; 	nid = memory_add_physaddr_to_nid(phys_addr);	ret = __add_memory(nid, phys_addr,			   MIN_MEMORY_BLOCK_SIZE * sections_per_block); 	if (ret)		goto out; 	ret = count;out:	unlock_device_hotplug();	return ret;} static DEVICE_ATTR_WO(probe);#endif #ifdef CONFIG_MEMORY_FAILURE/* * Support for offlining pages of memory */ /* Soft offline a page */static ssize_t soft_offline_page_store(struct device *dev,				       struct device_attribute *attr,				       const char *buf, size_t count){	int ret;	u64 pfn;	if (!capable(CAP_SYS_ADMIN))		return -EPERM;	if (kstrtoull(buf, 0, &pfn) < 0)		return -EINVAL;	pfn >>= PAGE_SHIFT;	ret = soft_offline_page(pfn, 0);	return ret == 0 ? count : ret;} /* Forcibly offline a page, including killing processes. */static ssize_t hard_offline_page_store(struct device *dev,				       struct device_attribute *attr,				       const char *buf, size_t count){	int ret;	u64 pfn;	if (!capable(CAP_SYS_ADMIN))		return -EPERM;	if (kstrtoull(buf, 0, &pfn) < 0)		return -EINVAL;	pfn >>= PAGE_SHIFT;	ret = memory_failure(pfn, 0);	return ret ? ret : count;} 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... */int __weak arch_get_memory_phys_device(unsigned long start_pfn){	return 0;} /*

Lines 1–500 of 833. Load more