hugetlb.c

最新最稳定的Linux内存管理模块源代码

		if (err < 0)
			return err;
		return 0;
	}
}
static void vma_commit_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;

	if (vma->vm_flags & VM_SHARED) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		region_add(&inode->i_mapping->private_list, idx, idx + 1);

	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		struct resv_map *reservations = vma_resv_map(vma);

		/* Mark this page used in the map. */
		region_add(&reservations->regions, idx, idx + 1);
	}
}

static struct page *alloc_huge_page(struct vm_area_struct *vma,
				    unsigned long addr, int avoid_reserve)
{
	struct hstate *h = hstate_vma(vma);
	struct page *page;
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;
	unsigned int chg;

	/*
	 * Processes that did not create the mapping will have no reserves and
	 * will not have accounted against quota. Check that the quota can be
	 * made before satisfying the allocation
	 * MAP_NORESERVE mappings may also need pages and quota allocated
	 * if no reserve mapping overlaps.
	 */
	chg = vma_needs_reservation(h, vma, addr);
	if (chg < 0)
		return ERR_PTR(chg);
	if (chg)
		if (hugetlb_get_quota(inode->i_mapping, chg))
			return ERR_PTR(-ENOSPC);

	spin_lock(&hugetlb_lock);
	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
	spin_unlock(&hugetlb_lock);

	if (!page) {
		page = alloc_buddy_huge_page(h, vma, addr);
		if (!page) {
			hugetlb_put_quota(inode->i_mapping, chg);
			return ERR_PTR(-VM_FAULT_OOM);
		}
	}

	set_page_refcounted(page);
	set_page_private(page, (unsigned long) mapping);

	vma_commit_reservation(h, vma, addr);

	return page;
}

int __weak alloc_bootmem_huge_page(struct hstate *h)
{
	struct huge_bootmem_page *m;
	int nr_nodes = nodes_weight(node_online_map);

	while (nr_nodes) {
		void *addr;

		addr = __alloc_bootmem_node_nopanic(
				NODE_DATA(h->hugetlb_next_nid),
				huge_page_size(h), huge_page_size(h), 0);

		if (addr) {
			/*
			 * Use the beginning of the huge page to store the
			 * huge_bootmem_page struct (until gather_bootmem
			 * puts them into the mem_map).
			 */
			m = addr;
			goto found;
		}
		hstate_next_node(h);
		nr_nodes--;
	}
	return 0;

found:
	BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1));
	/* Put them into a private list first because mem_map is not up yet */
	list_add(&m->list, &huge_boot_pages);
	m->hstate = h;
	return 1;
}

static void prep_compound_huge_page(struct page *page, int order)
{
	if (unlikely(order > (MAX_ORDER - 1)))
		prep_compound_gigantic_page(page, order);
	else
		prep_compound_page(page, order);
}

/* Put bootmem huge pages into the standard lists after mem_map is up */
static void __init gather_bootmem_prealloc(void)
{
	struct huge_bootmem_page *m;

	list_for_each_entry(m, &huge_boot_pages, list) {
		struct page *page = virt_to_page(m);
		struct hstate *h = m->hstate;
		__ClearPageReserved(page);
		WARN_ON(page_count(page) != 1);
		prep_compound_huge_page(page, h->order);
		prep_new_huge_page(h, page, page_to_nid(page));
	}
}

static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
{
	unsigned long i;

	for (i = 0; i < h->max_huge_pages; ++i) {
		if (h->order >= MAX_ORDER) {
			if (!alloc_bootmem_huge_page(h))
				break;
		} else if (!alloc_fresh_huge_page(h))
			break;
	}
	h->max_huge_pages = i;
}

static void __init hugetlb_init_hstates(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		/* oversize hugepages were init'ed in early boot */
		if (h->order < MAX_ORDER)
			hugetlb_hstate_alloc_pages(h);
	}
}

static char * __init memfmt(char *buf, unsigned long n)
{
	if (n >= (1UL << 30))
		sprintf(buf, "%lu GB", n >> 30);
	else if (n >= (1UL << 20))
		sprintf(buf, "%lu MB", n >> 20);
	else
		sprintf(buf, "%lu KB", n >> 10);
	return buf;
}

static void __init report_hugepages(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		char buf[32];
		printk(KERN_INFO "HugeTLB registered %s page size, "
				 "pre-allocated %ld pages\n",
			memfmt(buf, huge_page_size(h)),
			h->free_huge_pages);
	}
}

#ifdef CONFIG_HIGHMEM
static void try_to_free_low(struct hstate *h, unsigned long count)
{
	int i;

	if (h->order >= MAX_ORDER)
		return;

	for (i = 0; i < MAX_NUMNODES; ++i) {
		struct page *page, *next;
		struct list_head *freel = &h->hugepage_freelists[i];
		list_for_each_entry_safe(page, next, freel, lru) {
			if (count >= h->nr_huge_pages)
				return;
			if (PageHighMem(page))
				continue;
			list_del(&page->lru);
			update_and_free_page(h, page);
			h->free_huge_pages--;
			h->free_huge_pages_node[page_to_nid(page)]--;
		}
	}
}
#else
static inline void try_to_free_low(struct hstate *h, unsigned long count)
{
}
#endif

#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
{
	unsigned long min_count, ret;

	if (h->order >= MAX_ORDER)
		return h->max_huge_pages;

	/*
	 * Increase the pool size
	 * First take pages out of surplus state.  Then make up the
	 * remaining difference by allocating fresh huge pages.
	 *
	 * We might race with alloc_buddy_huge_page() here and be unable
	 * to convert a surplus huge page to a normal huge page. That is
	 * not critical, though, it just means the overall size of the
	 * pool might be one hugepage larger than it needs to be, but
	 * within all the constraints specified by the sysctls.
	 */
	spin_lock(&hugetlb_lock);
	while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, -1))
			break;
	}

	while (count > persistent_huge_pages(h)) {
		/*
		 * If this allocation races such that we no longer need the
		 * page, free_huge_page will handle it by freeing the page
		 * and reducing the surplus.
		 */
		spin_unlock(&hugetlb_lock);
		ret = alloc_fresh_huge_page(h);
		spin_lock(&hugetlb_lock);
		if (!ret)
			goto out;

	}

	/*
	 * Decrease the pool size
	 * First return free pages to the buddy allocator (being careful
	 * to keep enough around to satisfy reservations).  Then place
	 * pages into surplus state as needed so the pool will shrink
	 * to the desired size as pages become free.
	 *
	 * By placing pages into the surplus state independent of the
	 * overcommit value, we are allowing the surplus pool size to
	 * exceed overcommit. There are few sane options here. Since
	 * alloc_buddy_huge_page() is checking the global counter,
	 * though, we'll note that we're not allowed to exceed surplus
	 * and won't grow the pool anywhere else. Not until one of the
	 * sysctls are changed, or the surplus pages go out of use.
	 */
	min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
	min_count = max(count, min_count);
	try_to_free_low(h, min_count);
	while (min_count < persistent_huge_pages(h)) {
		struct page *page = dequeue_huge_page(h);
		if (!page)
			break;
		update_and_free_page(h, page);
	}
	while (count < persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, 1))
			break;
	}
out:
	ret = persistent_huge_pages(h);
	spin_unlock(&hugetlb_lock);
	return ret;
}

#define HSTATE_ATTR_RO(_name) \
	static struct kobj_attribute _name##_attr = __ATTR_RO(_name)

#define HSTATE_ATTR(_name) \
	static struct kobj_attribute _name##_attr = \
		__ATTR(_name, 0644, _name##_show, _name##_store)

static struct kobject *hugepages_kobj;
static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];

static struct hstate *kobj_to_hstate(struct kobject *kobj)
{
	int i;
	for (i = 0; i < HUGE_MAX_HSTATE; i++)
		if (hstate_kobjs[i] == kobj)
			return &hstates[i];
	BUG();
	return NULL;
}

static ssize_t nr_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj);
	return sprintf(buf, "%lu\n", h->nr_huge_pages);
}
static ssize_t nr_hugepages_store(struct kobject *kobj,
		struct kobj_attribute *attr, const char *buf, size_t count)
{
	int err;
	unsigned long input;
	struct hstate *h = kobj_to_hstate(kobj);

	err = strict_strtoul(buf, 10, &input);
	if (err)
		return 0;

	h->max_huge_pages = set_max_huge_pages(h, input);

	return count;
}
HSTATE_ATTR(nr_hugepages);

static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj);
	return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages);
}
static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
		struct kobj_attribute *attr, const char *buf, size_t count)
{
	int err;
	unsigned long input;
	struct hstate *h = kobj_to_hstate(kobj);

	err = strict_strtoul(buf, 10, &input);
	if (err)
		return 0;

	spin_lock(&hugetlb_lock);
	h->nr_overcommit_huge_pages = input;
	spin_unlock(&hugetlb_lock);

	return count;
}
HSTATE_ATTR(nr_overcommit_hugepages);

static ssize_t free_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj);
	return sprintf(buf, "%lu\n", h->free_huge_pages);
}
HSTATE_ATTR_RO(free_hugepages);

static ssize_t resv_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj);
	return sprintf(buf, "%lu\n", h->resv_huge_pages);
}
HSTATE_ATTR_RO(resv_hugepages);

static ssize_t surplus_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj);
	return sprintf(buf, "%lu\n", h->surplus_huge_pages);
}
HSTATE_ATTR_RO(surplus_hugepages);

static struct attribute *hstate_attrs[] = {
	&nr_hugepages_attr.attr,
	&nr_overcommit_hugepages_attr.attr,
	&free_hugepages_attr.attr,
	&resv_hugepages_attr.attr,
	&surplus_hugepages_attr.attr,
	NULL,
};

static struct attribute_group hstate_attr_group = {
	.attrs = hstate_attrs,
};

static int __init hugetlb_sysfs_add_hstate(struct hstate *h)
{
	int retval;

	hstate_kobjs[h - hstates] = kobject_create_and_add(h->name,
							hugepages_kobj);
	if (!hstate_kobjs[h - hstates])
		return -ENOMEM;

	retval = sysfs_create_group(hstate_kobjs[h - hstates],
							&hstate_attr_group);
	if (retval)
		kobject_put(hstate_kobjs[h - hstates]);

	return retval;
}

static void __init hugetlb_sysfs_init(void)
{
	struct hstate *h;
	int err;

	hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
	if (!hugepages_kobj)
		return;

	for_each_hstate(h) {
		err = hugetlb_sysfs_add_hstate(h);
		if (err)
			printk(KERN_ERR "Hugetlb: Unable to add hstate %s",
								h->name);
	}
}

static void __exit hugetlb_exit(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		kobject_put(hstate_kobjs[h - hstates]);
	}

	kobject_put(hugepages_kobj);
}
module_exit(hugetlb_exit);

static int __init hugetlb_init(void)
{
	/* Some platform decide whether they support huge pages at boot
	 * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
	 * there is no such support
	 */
	if (HPAGE_SHIFT == 0)
		return 0;

	if (!size_to_hstate(default_hstate_size)) {
		default_hstate_size = HPAGE_SIZE;
		if (!size_to_hstate(default_hstate_size))
			hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
	}
	default_hstate_idx = size_to_hstate(default_hstate_size) - hstates;
	if (default_hstate_max_huge_pages)
		default_hstate.max_huge_pages = default_hstate_max_huge_pages;

	hugetlb_init_hstates();

	gather_bootmem_prealloc();

	report_hugepages();

	hugetlb_sysfs_init();

	return 0;
}
module_init(hugetlb_init);

/* Should be called on processing a hugepagesz=... option */
void __init hugetlb_add_hstate(unsigned order)
{
	struct hstate *h;
	unsigned long i;

	if (size_to_hstate(PAGE_SIZE << order)) {
		printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
		return;
	}
	BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
	BUG_ON(order == 0);
	h = &hstates[max_hstate++];
	h->order = order;