hugetlb.c

最新最稳定的Linux内存管理模块源代码

	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
	h->nr_huge_pages = 0;
	h->free_huge_pages = 0;
	for (i = 0; i < MAX_NUMNODES; ++i)
		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
	h->hugetlb_next_nid = first_node(node_online_map);
	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
					huge_page_size(h)/1024);

	parsed_hstate = h;
}

static int __init hugetlb_nrpages_setup(char *s)
{
	unsigned long *mhp;
	static unsigned long *last_mhp;

	/*
	 * !max_hstate means we haven't parsed a hugepagesz= parameter yet,
	 * so this hugepages= parameter goes to the "default hstate".
	 */
	if (!max_hstate)
		mhp = &default_hstate_max_huge_pages;
	else
		mhp = &parsed_hstate->max_huge_pages;

	if (mhp == last_mhp) {
		printk(KERN_WARNING "hugepages= specified twice without "
			"interleaving hugepagesz=, ignoring\n");
		return 1;
	}

	if (sscanf(s, "%lu", mhp) <= 0)
		*mhp = 0;

	/*
	 * Global state is always initialized later in hugetlb_init.
	 * But we need to allocate >= MAX_ORDER hstates here early to still
	 * use the bootmem allocator.
	 */
	if (max_hstate && parsed_hstate->order >= MAX_ORDER)
		hugetlb_hstate_alloc_pages(parsed_hstate);

	last_mhp = mhp;

	return 1;
}
__setup("hugepages=", hugetlb_nrpages_setup);

static int __init hugetlb_default_setup(char *s)
{
	default_hstate_size = memparse(s, &s);
	return 1;
}
__setup("default_hugepagesz=", hugetlb_default_setup);

static unsigned int cpuset_mems_nr(unsigned int *array)
{
	int node;
	unsigned int nr = 0;

	for_each_node_mask(node, cpuset_current_mems_allowed)
		nr += array[node];

	return nr;
}

#ifdef CONFIG_SYSCTL
int hugetlb_sysctl_handler(struct ctl_table *table, int write,
			   struct file *file, void __user *buffer,
			   size_t *length, loff_t *ppos)
{
	struct hstate *h = &default_hstate;
	unsigned long tmp;

	if (!write)
		tmp = h->max_huge_pages;

	table->data = &tmp;
	table->maxlen = sizeof(unsigned long);
	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);

	if (write)
		h->max_huge_pages = set_max_huge_pages(h, tmp);

	return 0;
}

int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
			struct file *file, void __user *buffer,
			size_t *length, loff_t *ppos)
{
	proc_dointvec(table, write, file, buffer, length, ppos);
	if (hugepages_treat_as_movable)
		htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
	else
		htlb_alloc_mask = GFP_HIGHUSER;
	return 0;
}

int hugetlb_overcommit_handler(struct ctl_table *table, int write,
			struct file *file, void __user *buffer,
			size_t *length, loff_t *ppos)
{
	struct hstate *h = &default_hstate;
	unsigned long tmp;

	if (!write)
		tmp = h->nr_overcommit_huge_pages;

	table->data = &tmp;
	table->maxlen = sizeof(unsigned long);
	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);

	if (write) {
		spin_lock(&hugetlb_lock);
		h->nr_overcommit_huge_pages = tmp;
		spin_unlock(&hugetlb_lock);
	}

	return 0;
}

#endif /* CONFIG_SYSCTL */

void hugetlb_report_meminfo(struct seq_file *m)
{
	struct hstate *h = &default_hstate;
	seq_printf(m,
			"HugePages_Total:   %5lu\n"
			"HugePages_Free:    %5lu\n"
			"HugePages_Rsvd:    %5lu\n"
			"HugePages_Surp:    %5lu\n"
			"Hugepagesize:   %8lu kB\n",
			h->nr_huge_pages,
			h->free_huge_pages,
			h->resv_huge_pages,
			h->surplus_huge_pages,
			1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
}

int hugetlb_report_node_meminfo(int nid, char *buf)
{
	struct hstate *h = &default_hstate;
	return sprintf(buf,
		"Node %d HugePages_Total: %5u\n"
		"Node %d HugePages_Free:  %5u\n"
		"Node %d HugePages_Surp:  %5u\n",
		nid, h->nr_huge_pages_node[nid],
		nid, h->free_huge_pages_node[nid],
		nid, h->surplus_huge_pages_node[nid]);
}

/* Return the number pages of memory we physically have, in PAGE_SIZE units. */
unsigned long hugetlb_total_pages(void)
{
	struct hstate *h = &default_hstate;
	return h->nr_huge_pages * pages_per_huge_page(h);
}

static int hugetlb_acct_memory(struct hstate *h, long delta)
{
	int ret = -ENOMEM;

	spin_lock(&hugetlb_lock);
	/*
	 * When cpuset is configured, it breaks the strict hugetlb page
	 * reservation as the accounting is done on a global variable. Such
	 * reservation is completely rubbish in the presence of cpuset because
	 * the reservation is not checked against page availability for the
	 * current cpuset. Application can still potentially OOM'ed by kernel
	 * with lack of free htlb page in cpuset that the task is in.
	 * Attempt to enforce strict accounting with cpuset is almost
	 * impossible (or too ugly) because cpuset is too fluid that
	 * task or memory node can be dynamically moved between cpusets.
	 *
	 * The change of semantics for shared hugetlb mapping with cpuset is
	 * undesirable. However, in order to preserve some of the semantics,
	 * we fall back to check against current free page availability as
	 * a best attempt and hopefully to minimize the impact of changing
	 * semantics that cpuset has.
	 */
	if (delta > 0) {
		if (gather_surplus_pages(h, delta) < 0)
			goto out;

		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
			return_unused_surplus_pages(h, delta);
			goto out;
		}
	}

	ret = 0;
	if (delta < 0)
		return_unused_surplus_pages(h, (unsigned long) -delta);

out:
	spin_unlock(&hugetlb_lock);
	return ret;
}

static void hugetlb_vm_op_open(struct vm_area_struct *vma)
{
	struct resv_map *reservations = vma_resv_map(vma);

	/*
	 * This new VMA should share its siblings reservation map if present.
	 * The VMA will only ever have a valid reservation map pointer where
	 * it is being copied for another still existing VMA.  As that VMA
	 * has a reference to the reservation map it cannot dissappear until
	 * after this open call completes.  It is therefore safe to take a
	 * new reference here without additional locking.
	 */
	if (reservations)
		kref_get(&reservations->refs);
}

static void hugetlb_vm_op_close(struct vm_area_struct *vma)
{
	struct hstate *h = hstate_vma(vma);
	struct resv_map *reservations = vma_resv_map(vma);
	unsigned long reserve;
	unsigned long start;
	unsigned long end;

	if (reservations) {
		start = vma_hugecache_offset(h, vma, vma->vm_start);
		end = vma_hugecache_offset(h, vma, vma->vm_end);

		reserve = (end - start) -
			region_count(&reservations->regions, start, end);

		kref_put(&reservations->refs, resv_map_release);

		if (reserve) {
			hugetlb_acct_memory(h, -reserve);
			hugetlb_put_quota(vma->vm_file->f_mapping, reserve);
		}
	}
}

/*
 * We cannot handle pagefaults against hugetlb pages at all.  They cause
 * handle_mm_fault() to try to instantiate regular-sized pages in the
 * hugegpage VMA.  do_page_fault() is supposed to trap this, so BUG is we get
 * this far.
 */
static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	BUG();
	return 0;
}

struct vm_operations_struct hugetlb_vm_ops = {
	.fault = hugetlb_vm_op_fault,
	.open = hugetlb_vm_op_open,
	.close = hugetlb_vm_op_close,
};

static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
				int writable)
{
	pte_t entry;

	if (writable) {
		entry =
		    pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
	} else {
		entry = huge_pte_wrprotect(mk_pte(page, vma->vm_page_prot));
	}
	entry = pte_mkyoung(entry);
	entry = pte_mkhuge(entry);

	return entry;
}

static void set_huge_ptep_writable(struct vm_area_struct *vma,
				   unsigned long address, pte_t *ptep)
{
	pte_t entry;

	entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
	if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) {
		update_mmu_cache(vma, address, entry);
	}
}


int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
			    struct vm_area_struct *vma)
{
	pte_t *src_pte, *dst_pte, entry;
	struct page *ptepage;
	unsigned long addr;
	int cow;
	struct hstate *h = hstate_vma(vma);
	unsigned long sz = huge_page_size(h);

	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;

	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
		src_pte = huge_pte_offset(src, addr);
		if (!src_pte)
			continue;
		dst_pte = huge_pte_alloc(dst, addr, sz);
		if (!dst_pte)
			goto nomem;

		/* If the pagetables are shared don't copy or take references */
		if (dst_pte == src_pte)
			continue;

		spin_lock(&dst->page_table_lock);
		spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
		if (!huge_pte_none(huge_ptep_get(src_pte))) {
			if (cow)
				huge_ptep_set_wrprotect(src, addr, src_pte);
			entry = huge_ptep_get(src_pte);
			ptepage = pte_page(entry);
			get_page(ptepage);
			set_huge_pte_at(dst, addr, dst_pte, entry);
		}
		spin_unlock(&src->page_table_lock);
		spin_unlock(&dst->page_table_lock);
	}
	return 0;

nomem:
	return -ENOMEM;
}

void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
			    unsigned long end, struct page *ref_page)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long address;
	pte_t *ptep;
	pte_t pte;
	struct page *page;
	struct page *tmp;
	struct hstate *h = hstate_vma(vma);
	unsigned long sz = huge_page_size(h);

	/*
	 * A page gathering list, protected by per file i_mmap_lock. The
	 * lock is used to avoid list corruption from multiple unmapping
	 * of the same page since we are using page->lru.
	 */
	LIST_HEAD(page_list);

	WARN_ON(!is_vm_hugetlb_page(vma));
	BUG_ON(start & ~huge_page_mask(h));
	BUG_ON(end & ~huge_page_mask(h));

	mmu_notifier_invalidate_range_start(mm, start, end);
	spin_lock(&mm->page_table_lock);
	for (address = start; address < end; address += sz) {
		ptep = huge_pte_offset(mm, address);
		if (!ptep)
			continue;

		if (huge_pmd_unshare(mm, &address, ptep))
			continue;

		/*
		 * If a reference page is supplied, it is because a specific
		 * page is being unmapped, not a range. Ensure the page we
		 * are about to unmap is the actual page of interest.
		 */
		if (ref_page) {
			pte = huge_ptep_get(ptep);
			if (huge_pte_none(pte))
				continue;
			page = pte_page(pte);
			if (page != ref_page)
				continue;

			/*
			 * Mark the VMA as having unmapped its page so that
			 * future faults in this VMA will fail rather than
			 * looking like data was lost
			 */
			set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED);
		}

		pte = huge_ptep_get_and_clear(mm, address, ptep);
		if (huge_pte_none(pte))
			continue;

		page = pte_page(pte);
		if (pte_dirty(pte))
			set_page_dirty(page);
		list_add(&page->lru, &page_list);
	}
	spin_unlock(&mm->page_table_lock);
	flush_tlb_range(vma, start, end);
	mmu_notifier_invalidate_range_end(mm, start, end);
	list_for_each_entry_safe(page, tmp, &page_list, lru) {
		list_del(&page->lru);
		put_page(page);
	}
}

void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
			  unsigned long end, struct page *ref_page)
{
	spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
	__unmap_hugepage_range(vma, start, end, ref_page);
	spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
}

/*
 * This is called when the original mapper is failing to COW a MAP_PRIVATE
 * mappping it owns the reserve page for. The intention is to unmap the page
 * from other VMAs and let the children be SIGKILLed if they are faulting the
 * same region.
 */
static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
				struct page *page, unsigned long address)
{
	struct hstate *h = hstate_vma(vma);
	struct vm_area_struct *iter_vma;
	struct address_space *mapping;
	struct prio_tree_iter iter;
	pgoff_t pgoff;

	/*
	 * vm_pgoff is in PAGE_SIZE units, hence the different calculation
	 * from page cache lookup which is in HPAGE_SIZE units.
	 */
	address = address & huge_page_mask(h);
	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT)
		+ (vma->vm_pgoff >> PAGE_SHIFT);
	mapping = (struct address_space *)page_private(page);

	vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
		/* Do not unmap the current VMA */
		if (iter_vma == vma)
			continue;

		/*
		 * Unmap the page from other VMAs without their own reserves.
		 * They get marked to be SIGKILLed if they fault in these
		 * areas. This is because a future no-page fault on this VMA
		 * could insert a zeroed page instead of the data existing
		 * from the time of fork. This would look like data corruption
		 */
		if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
			unmap_hugepage_range(iter_vma,
				address, address + huge_page_size(h),
				page);
	}

	return 1;
}

static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, pte_t *ptep, pte_t pte,
			struct page *pagecache_page)
{
	struct hstate *h = hstate_vma(vma);
	struct page *old_page, *new_page;
	int avoidcopy;
	int outside_reserve = 0;

	old_page = pte_page(pte);

retry_avoidcopy:
	/* If no-one else is actually using this page, avoid the copy
	 * and just make the page writable */