path: root/drivers/base/memory.c

// 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 mhp_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 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 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);

/*
 * 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)
{
	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 sysfs_emit(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 sysfs_emit(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);
	const char *output;

	/*
	 * We can probably put these states in a nice little array
	 * so that they're not open-coded
	 */
	switch (mem->state) {
	case MEM_ONLINE:
		output = "online";
		break;
	case MEM_OFFLINE:
		output = "offline";
		break;
	case MEM_GOING_OFFLINE:
		output = "going-offline";
		break;
	default:
		WARN_ON(1);
		return sysfs_emit(buf, "ERROR-UNKNOWN-%ld\n", mem->state);
	}

	return sysfs_emit(buf, "%s\n", output);
}

int memory_notify(unsigned long val, void *v)
{
	return blocking_notifier_call_chain(&memory_chain, val, v);
}

static int memory_block_online(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 = mem->nr_vmemmap_pages;
	struct zone *zone;
	int ret;

	zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
				  start_pfn, nr_pages);

	/*
	 * Although vmemmap pages have a diff