/* * 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/kobject.h>#include <linux/memory_hotplug.h>#include <linux/mm.h>#include <linux/mutex.h>#include <linux/stat.h>#include <linux/slab.h> #include <linux/atomic.h>#include <asm/uaccess.h> static DEFINE_MUTEX(mem_sysfs_mutex); #define MEMORY_CLASS_NAME	"memory" static int sections_per_block; static inline int base_memory_block_id(int section_nr){	return section_nr / sections_per_block;} static struct bus_type memory_subsys = {	.name = MEMORY_CLASS_NAME,	.dev_name = MEMORY_CLASS_NAME,}; 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 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); /* * register_memory - Setup a sysfs device for a memory block */staticint register_memory(struct memory_block *memory){	int error; 	memory->dev.bus = &memory_subsys;	memory->dev.id = memory->start_section_nr / sections_per_block; 	error = device_register(&memory->dev);	return error;} static voidunregister_memory(struct memory_block *memory){	BUG_ON(memory->dev.bus != &memory_subsys); 	/* drop the ref. we got in remove_memory_block() */	kobject_put(&memory->dev.kobj);	device_unregister(&memory->dev);} unsigned long __weak memory_block_size_bytes(void){	return MIN_MEMORY_BLOCK_SIZE;} static unsigned long get_memory_block_size(void){	unsigned long block_sz; 	block_sz = memory_block_size_bytes(); 	/* 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;	} 	return block_sz;} /* * use this as the physical section index that this memsection * uses. */ static ssize_t show_mem_start_phys_index(struct device *dev,			struct device_attribute *attr, char *buf){	struct memory_block *mem =		container_of(dev, struct memory_block, dev);	unsigned long phys_index; 	phys_index = mem->start_section_nr / sections_per_block;	return sprintf(buf, "%08lx\n", phys_index);} static ssize_t show_mem_end_phys_index(struct device *dev,			struct device_attribute *attr, char *buf){	struct memory_block *mem =		container_of(dev, struct memory_block, dev);	unsigned long phys_index; 	phys_index = mem->end_section_nr / sections_per_block;	return sprintf(buf, "%08lx\n", phys_index);} /* * Show whether the section of memory is likely to be hot-removable */static ssize_t show_mem_removable(struct device *dev,			struct device_attribute *attr, char *buf){	unsigned long i, pfn;	int ret = 1;	struct memory_block *mem =		container_of(dev, struct memory_block, dev); 	for (i = 0; i < sections_per_block; i++) {		pfn = section_nr_to_pfn(mem->start_section_nr + i);		ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);	} 	return sprintf(buf, "%d\n", ret);} /* * online, offline, going offline, etc. */static ssize_t show_mem_state(struct device *dev,			struct device_attribute *attr, char *buf){	struct memory_block *mem =		container_of(dev, struct 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);} int memory_isolate_notify(unsigned long val, void *v){	return atomic_notifier_call_chain(&memory_isolate_chain, val, v);} /* * The probe routines leave the pages reserved, just as the bootmem code does. * Make sure they're still that way. */static bool pages_correctly_reserved(unsigned long start_pfn,					unsigned long nr_pages){	int i, j;	struct page *page;	unsigned long pfn = start_pfn; 	/*	 * 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	 */	for (i = 0; i < sections_per_block; i++, pfn += PAGES_PER_SECTION) {		if (WARN_ON_ONCE(!pfn_valid(pfn)))			return false;		page = pfn_to_page(pfn); 		for (j = 0; j < PAGES_PER_SECTION; j++) {			if (PageReserved(page + j))				continue; 			printk(KERN_WARNING "section number %ld page number %d "				"not reserved, was it already online?\n",				pfn_to_section_nr(pfn), j); 			return false;		}	} 	return true;} /* * 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 phys_index, unsigned long action){	unsigned long start_pfn;	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;	struct page *first_page;	int ret; 	first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT);	start_pfn = page_to_pfn(first_page); 	switch (action) {		case MEM_ONLINE:			if (!pages_correctly_reserved(start_pfn, nr_pages))				return -EBUSY; 			ret = online_pages(start_pfn, nr_pages);			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__, phys_index, 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) {		ret = -EINVAL;		goto out;	} 	if (to_state == MEM_OFFLINE)		mem->state = MEM_GOING_OFFLINE; 	ret = memory_block_action(mem->start_section_nr, to_state); 	if (ret) {		mem->state = from_state_req;		goto out;	} 	mem->state = to_state;	switch (mem->state) {	case MEM_OFFLINE:		kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE);		break;	case MEM_ONLINE:		kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE);		break;	default:		break;	}out:	return ret;} static int memory_block_change_state(struct memory_block *mem,		unsigned long to_state, unsigned long from_state_req){	int ret; 	mutex_lock(&mem->state_mutex);	ret = __memory_block_change_state(mem, to_state, from_state_req);	mutex_unlock(&mem->state_mutex); 	return ret;}static ssize_tstore_mem_state(struct device *dev,		struct device_attribute *attr, const char *buf, size_t count){	struct memory_block *mem;	int ret = -EINVAL; 	mem = container_of(dev, struct memory_block, dev); 	if (!strncmp(buf, "online", min((int)count, 6)))		ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);	else if(!strncmp(buf, "offline", min((int)count, 7)))		ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE); 	if (ret)		return ret;	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 show_phys_device(struct device *dev,				struct device_attribute *attr, char *buf){	struct memory_block *mem =		container_of(dev, struct memory_block, dev);	return sprintf(buf, "%d\n", mem->phys_device);} static DEVICE_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);static DEVICE_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);static DEVICE_ATTR(state, 0644, show_mem_state, store_mem_state);static DEVICE_ATTR(phys_device, 0444, show_phys_device, NULL);static DEVICE_ATTR(removable, 0444, show_mem_removable, NULL); #define mem_create_simple_file(mem, attr_name)	\	device_create_file(&mem->dev, &dev_attr_##attr_name)#define mem_remove_simple_file(mem, attr_name)	\	device_remove_file(&mem->dev, &dev_attr_##attr_name) /* * Block size attribute stuff */static ssize_tprint_block_size(struct device *dev, struct device_attribute *attr,		 char *buf){	return sprintf(buf, "%lx\n", get_memory_block_size());} static DEVICE_ATTR(block_size_bytes, 0444, print_block_size, NULL); static int block_size_init(void){	return device_create_file(memory_subsys.dev_root,				  &dev_attr_block_size_bytes);} /* * 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_tmemory_probe_store(struct device *dev, struct device_attribute *attr,		   const char *buf, size_t count){	u64 phys_addr;	int nid;	int i, ret;	unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block; 	phys_addr = simple_strtoull(buf, NULL, 0); 	if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1))		return -EINVAL; 	for (i = 0; i < sections_per_block; i++) {		nid = memory_add_physaddr_to_nid(phys_addr);		ret = add_memory(nid, phys_addr,				 PAGES_PER_SECTION << PAGE_SHIFT);		if (ret)			goto out; 		phys_addr += MIN_MEMORY_BLOCK_SIZE;	} 	ret = count;out:	return ret;}static DEVICE_ATTR(probe, S_IWUSR, NULL, memory_probe_store); static int memory_probe_init(void){	return device_create_file(memory_subsys.dev_root, &dev_attr_probe);}#elsestatic inline int memory_probe_init(void){	return 0;}#endif #ifdef CONFIG_MEMORY_FAILURE/* * Support for offlining pages of memory */ /* Soft offline a page */static ssize_tstore_soft_offline_page(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 (strict_strtoull(buf, 0, &pfn) < 0)		return -EINVAL;	pfn >>= PAGE_SHIFT;	if (!pfn_valid(pfn))		return -ENXIO;	ret = soft_offline_page(pfn_to_page(pfn), 0);	return ret == 0 ? count : ret;} /* Forcibly offline a page, including killing processes. */static ssize_tstore_hard_offline_page(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 (strict_strtoull(buf, 0, &pfn) < 0)		return -EINVAL;	pfn >>= PAGE_SHIFT;	ret = memory_failure(pfn, 0, 0);	return ret ? ret : count;} static DEVICE_ATTR(soft_offline_page, 0644, NULL, store_soft_offline_page);static DEVICE_ATTR(hard_offline_page, 0644, NULL, store_hard_offline_page); static __init int memory_fail_init(void){	int err; 	err = device_create_file(memory_subsys.dev_root,				&dev_attr_soft_offline_page);	if (!err)		err = device_create_file(memory_subsys.dev_root,				&dev_attr_hard_offline_page);	return err;}#elsestatic inline int memory_fail_init(void){	return 0;}#endif /* * Note that phys_device is optional.  It is here to allow for

Lines 1–500 of 725. Load more