memory.c

	do_set_pte(vma, address, fault_page, pte, true, false);
	pte_unmap_unlock(pte, ptl);

	if (set_page_dirty(fault_page))
		dirtied = 1;
	/*
	 * Take a local copy of the address_space - page.mapping may be zeroed
	 * by truncate after unlock_page().   The address_space itself remains
	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
	 * release semantics to prevent the compiler from undoing this copying.
	 */
	mapping = fault_page->mapping;
	unlock_page(fault_page);
	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
		/*
		 * Some device drivers do not set page.mapping but still
		 * dirty their pages
		 */
		balance_dirty_pages_ratelimited(mapping);
	}

	/* file_update_time outside page_lock */
	if (vma->vm_file && !vma->vm_ops->page_mkwrite)
		file_update_time(vma->vm_file);

	return ret;
}

/*
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults).
 * The mmap_sem may have been released depending on flags and our
 * return value.  See filemap_fault() and __lock_page_or_retry().
 */
static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		unsigned int flags, pte_t orig_pte)
{
	pgoff_t pgoff = (((address & PAGE_MASK)
			- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;

	pte_unmap(page_table);
	if (!(flags & FAULT_FLAG_WRITE))
		return do_read_fault(mm, vma, address, pmd, pgoff, flags,
				orig_pte);
	if (!(vma->vm_flags & VM_SHARED))
		return do_cow_fault(mm, vma, address, pmd, pgoff, flags,
				orig_pte);
	return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
}

/*
 * Fault of a previously existing named mapping. Repopulate the pte
 * from the encoded file_pte if possible. This enables swappable
 * nonlinear vmas.
 *
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with pte unmapped and unlocked.
 * The mmap_sem may have been released depending on flags and our
 * return value.  See filemap_fault() and __lock_page_or_retry().
 */
static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		unsigned int flags, pte_t orig_pte)
{
	pgoff_t pgoff;

	flags |= FAULT_FLAG_NONLINEAR;

	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
		return 0;

	if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
		/*
		 * Page table corrupted: show pte and kill process.
		 */
		print_bad_pte(vma, address, orig_pte, NULL);
		return VM_FAULT_SIGBUS;
	}

	pgoff = pte_to_pgoff(orig_pte);
	if (!(flags & FAULT_FLAG_WRITE))
		return do_read_fault(mm, vma, address, pmd, pgoff, flags,
				orig_pte);
	if (!(vma->vm_flags & VM_SHARED))
		return do_cow_fault(mm, vma, address, pmd, pgoff, flags,
				orig_pte);
	return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
}

static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
				unsigned long addr, int page_nid,
				int *flags)
{
	get_page(page);

	count_vm_numa_event(NUMA_HINT_FAULTS);
	if (page_nid == numa_node_id()) {
		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
		*flags |= TNF_FAULT_LOCAL;
	}

	return mpol_misplaced(page, vma, addr);
}

static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
		   unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd)
{
	struct page *page = NULL;
	spinlock_t *ptl;
	int page_nid = -1;
	int last_cpupid;
	int target_nid;
	bool migrated = false;
	int flags = 0;

	/*
	* The "pte" at this point cannot be used safely without
	* validation through pte_unmap_same(). It's of NUMA type but
	* the pfn may be screwed if the read is non atomic.
	*
	* ptep_modify_prot_start is not called as this is clearing
	* the _PAGE_NUMA bit and it is not really expected that there
	* would be concurrent hardware modifications to the PTE.
	*/
	ptl = pte_lockptr(mm, pmd);
	spin_lock(ptl);
	if (unlikely(!pte_same(*ptep, pte))) {
		pte_unmap_unlock(ptep, ptl);
		goto out;
	}

	pte = pte_mknonnuma(pte);
	set_pte_at(mm, addr, ptep, pte);
	update_mmu_cache(vma, addr, ptep);

	page = vm_normal_page(vma, addr, pte);
	if (!page) {
		pte_unmap_unlock(ptep, ptl);
		return 0;
	}
	BUG_ON(is_zero_pfn(page_to_pfn(page)));

	/*
	 * Avoid grouping on DSO/COW pages in specific and RO pages
	 * in general, RO pages shouldn't hurt as much anyway since
	 * they can be in shared cache state.
	 */
	if (!pte_write(pte))
		flags |= TNF_NO_GROUP;

	/*
	 * Flag if the page is shared between multiple address spaces. This
	 * is later used when determining whether to group tasks together
	 */
	if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
		flags |= TNF_SHARED;

	last_cpupid = page_cpupid_last(page);
	page_nid = page_to_nid(page);
	target_nid = numa_migrate_prep(page, vma, addr, page_nid, &flags);
	pte_unmap_unlock(ptep, ptl);
	if (target_nid == -1) {
		put_page(page);
		goto out;
	}

	/* Migrate to the requested node */
	migrated = migrate_misplaced_page(page, vma, target_nid);
	if (migrated) {
		page_nid = target_nid;
		flags |= TNF_MIGRATED;
	}

out:
	if (page_nid != -1)
		task_numa_fault(last_cpupid, page_nid, 1, flags);
	return 0;
}

/*
 * These routines also need to handle stuff like marking pages dirty
 * and/or accessed for architectures that don't do it in hardware (most
 * RISC architectures).  The early dirtying is also good on the i386.
 *
 * There is also a hook called "update_mmu_cache()" that architectures
 * with external mmu caches can use to update those (ie the Sparc or
 * PowerPC hashed page tables that act as extended TLBs).
 *
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with pte unmapped and unlocked.
 *
 * The mmap_sem may have been released depending on flags and our
 * return value.  See filemap_fault() and __lock_page_or_retry().
 */
static int handle_pte_fault(struct mm_struct *mm,
		     struct vm_area_struct *vma, unsigned long address,
		     pte_t *pte, pmd_t *pmd, unsigned int flags)
{
	pte_t entry;
	spinlock_t *ptl;

	/*
	 * some architectures can have larger ptes than wordsize,
	 * e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and CONFIG_32BIT=y,
	 * so READ_ONCE or ACCESS_ONCE cannot guarantee atomic accesses.
	 * The code below just needs a consistent view for the ifs and
	 * we later double check anyway with the ptl lock held. So here
	 * a barrier will do.
	 */
	entry = *pte;
	barrier();
	if (!pte_present(entry)) {
		if (pte_none(entry)) {
			if (vma->vm_ops) {
				if (likely(vma->vm_ops->fault))
					return do_linear_fault(mm, vma, address,
						pte, pmd, flags, entry);
			}
			return do_anonymous_page(mm, vma, address,
						 pte, pmd, flags);
		}
		if (pte_file(entry))
			return do_nonlinear_fault(mm, vma, address,
					pte, pmd, flags, entry);
		return do_swap_page(mm, vma, address,
					pte, pmd, flags, entry);
	}

	if (pte_numa(entry))
		return do_numa_page(mm, vma, address, entry, pte, pmd);

	ptl = pte_lockptr(mm, pmd);
	spin_lock(ptl);
	if (unlikely(!pte_same(*pte, entry)))
		goto unlock;
	if (flags & FAULT_FLAG_WRITE) {
		if (!pte_write(entry))
			return do_wp_page(mm, vma, address,
					pte, pmd, ptl, entry);
		entry = pte_mkdirty(entry);
	}
	entry = pte_mkyoung(entry);
	if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) {
		update_mmu_cache(vma, address, pte);
	} else {
		/*
		 * This is needed only for protection faults but the arch code
		 * is not yet telling us if this is a protection fault or not.
		 * This still avoids useless tlb flushes for .text page faults
		 * with threads.
		 */
		if (flags & FAULT_FLAG_WRITE)
			flush_tlb_fix_spurious_fault(vma, address);
	}
unlock:
	pte_unmap_unlock(pte, ptl);
	return 0;
}

/*
 * By the time we get here, we already hold the mm semaphore
 *
 * The mmap_sem may have been released depending on flags and our
 * return value.  See filemap_fault() and __lock_page_or_retry().
 */
static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
			     unsigned long address, unsigned int flags)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	if (unlikely(is_vm_hugetlb_page(vma)))
		return hugetlb_fault(mm, vma, address, flags);

	pgd = pgd_offset(mm, address);
	pud = pud_alloc(mm, pgd, address);
	if (!pud)
		return VM_FAULT_OOM;
	pmd = pmd_alloc(mm, pud, address);
	if (!pmd)
		return VM_FAULT_OOM;
	if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
		int ret = VM_FAULT_FALLBACK;
		if (!vma->vm_ops)
			ret = do_huge_pmd_anonymous_page(mm, vma, address,
					pmd, flags);
		if (!(ret & VM_FAULT_FALLBACK))
			return ret;
	} else {
		pmd_t orig_pmd = *pmd;
		int ret;

		barrier();
		if (pmd_trans_huge(orig_pmd)) {
			unsigned int dirty = flags & FAULT_FLAG_WRITE;

			/*
			 * If the pmd is splitting, return and retry the
			 * the fault.  Alternative: wait until the split
			 * is done, and goto retry.
			 */
			if (pmd_trans_splitting(orig_pmd))
				return 0;

			if (pmd_numa(orig_pmd))
				return do_huge_pmd_numa_page(mm, vma, address,
							     orig_pmd, pmd);

			if (dirty && !pmd_write(orig_pmd)) {
				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
							  orig_pmd);
				if (!(ret & VM_FAULT_FALLBACK))
					return ret;
			} else {
				huge_pmd_set_accessed(mm, vma, address, pmd,
						      orig_pmd, dirty);
				return 0;
			}
		}
	}

	/*
	 * Use __pte_alloc instead of pte_alloc_map, because we can't
	 * run pte_offset_map on the pmd, if an huge pmd could
	 * materialize from under us from a different thread.
	 */
	if (unlikely(pmd_none(*pmd)) &&
	    unlikely(__pte_alloc(mm, vma, pmd, address)))
		return VM_FAULT_OOM;
	/* if an huge pmd materialized from under us just retry later */
	if (unlikely(pmd_trans_huge(*pmd)))
		return 0;
	/*
	 * A regular pmd is established and it can't morph into a huge pmd
	 * from under us anymore at this point because we hold the mmap_sem
	 * read mode and khugepaged takes it in write mode. So now it's
	 * safe to run pte_offset_map().
	 */
	pte = pte_offset_map(pmd, address);

	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}

/*
 * By the time we get here, we already hold the mm semaphore
 *
 * The mmap_sem may have been released depending on flags and our
 * return value.  See filemap_fault() and __lock_page_or_retry().
 */
int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		    unsigned long address, unsigned int flags)
{
	int ret;

	__set_current_state(TASK_RUNNING);

	count_vm_event(PGFAULT);
	mem_cgroup_count_vm_event(mm, PGFAULT);

	/* do counter updates before entering really critical section. */
	check_sync_rss_stat(current);

	/*
	 * Enable the memcg OOM handling for faults triggered in user
	 * space.  Kernel faults are handled more gracefully.
	 */
	if (flags & FAULT_FLAG_USER)
		mem_cgroup_oom_enable();

	ret = __handle_mm_fault(mm, vma, address, flags);

	if (flags & FAULT_FLAG_USER) {
		mem_cgroup_oom_disable();
                /*
                 * The task may have entered a memcg OOM situation but
                 * if the allocation error was handled gracefully (no
                 * VM_FAULT_OOM), there is no need to kill anything.
                 * Just clean up the OOM state peacefully.
                 */
                if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
                        mem_cgroup_oom_synchronize(false);
	}

	return ret;
}
EXPORT_SYMBOL_GPL(handle_mm_fault);

#ifndef __PAGETABLE_PUD_FOLDED
/*
 * Allocate page upper directory.
 * We've already handled the fast-path in-line.
 */
int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
	pud_t *new = pud_alloc_one(mm, address);
	if (!new)
		return -ENOMEM;

	smp_wmb(); /* See comment in __pte_alloc */

	spin_lock(&mm->page_table_lock);
	if (pgd_present(*pgd))		/* Another has populated it */
		pud_free(mm, new);
	else
		pgd_populate(mm, pgd, new);
	spin_unlock(&mm->page_table_lock);
	return 0;
}
#endif /* __PAGETABLE_PUD_FOLDED */

#ifndef __PAGETABLE_PMD_FOLDED
/*
 * Allocate page middle directory.
 * We've already handled the fast-path in-line.
 */
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
	pmd_t *new = pmd_alloc_one(mm, address);
	if (!new)
		return -ENOMEM;

	smp_wmb(); /* See comment in __pte_alloc */

	spin_lock(&mm->page_table_lock);
#ifndef __ARCH_HAS_4LEVEL_HACK
	if (pud_present(*pud))		/* Another has populated it */
		pmd_free(mm, new);
	else
		pud_populate(mm, pud, new);
#else
	if (pgd_present(*pud))		/* Another has populated it */
		pmd_free(mm, new);
	else
		pgd_populate(mm, pud, new);
#endif /* __ARCH_HAS_4LEVEL_HACK */
	spin_unlock(&mm->page_table_lock);
	return 0;
}
#endif /* __PAGETABLE_PMD_FOLDED */

static int __follow_pte(struct mm_struct *mm, unsigned long address,
		pte_t **ptepp, spinlock_t **ptlp)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *ptep;

	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		goto out;

	pud = pud_offset(pgd, address);
	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
		goto out;

	pmd = pmd_offset(pud, address);
	VM_BUG_ON(pmd_trans_huge(*pmd));
	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
		goto out;

	/* We cannot handle huge page PFN maps. Luckily they don't exist. */
	if (pmd_huge(*pmd))
		goto out;

	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
	if (!ptep)
		goto out;
	if (!pte_present(*ptep))
		goto unlock;
	*ptepp = ptep;
	return 0;
unlock:
	pte_unmap_unlock(ptep, *ptlp);
out:
	return -EINVAL;
}

static inline int follow_pte(struct mm_struct *mm, unsigned long address,
			     pte_t **ptepp, spinlock_t **ptlp)
{
	int res;

	/* (void) is needed to make gcc happy */
	(void) __cond_lock(*ptlp,
			   !(res = __follow_pte(mm, address, ptepp, ptlp)));
	return res;
}

/**
 * follow_pfn - look up PFN at a user virtual address
 * @vma: memory mapping
 * @address: user virtual address
 * @pfn: location to store found PFN
 *
 * Only IO mappings and raw PFN mappings are allowed.
 *
 * Returns zero and the pfn at @pfn on success, -ve otherwise.
 */
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
	unsigned long *pfn)
{
	int ret = -EINVAL;
	spinlock_t *ptl;
	pte_t *ptep;

	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
		return ret;

	ret = follow_pte(vma->vm_mm, address, &ptep, &ptl);
	if (ret)
		return ret;
	*pfn = pte_pfn(*ptep);
	pte_unmap_unlock(ptep, ptl);
	return 0;
}
EXPORT_SYMBOL(follow_pfn);

#ifdef CONFIG_HAVE_IOREMAP_PROT
int follow_phys(struct vm_area_struct *vma,
		unsigned long address, unsigned int flags,
		unsigned long *prot, resource_size_t *phys)
{
	int ret = -EINVAL;
	pte_t *ptep, pte;
	spinlock_t *ptl;

	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
		goto out;

	if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
		goto out;
	pte = *ptep;

	if ((flags & FOLL_WRITE) && !pte_write(pte))
		goto unlock;

	*prot = pgprot_val(pte_pgprot(pte));
	*phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;

	ret = 0;
unlock:
	pte_unmap_unlock(ptep, ptl);
out:
	return ret;
}

int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
			void *buf, int len, int write)
{
	resource_size_t phys_addr;
	unsigned long prot = 0;
	void __iomem *maddr;
	int offset = addr & (PAGE_SIZE-1);

	if (follow_phys(vma, addr, write, &prot, &phys_addr))
		return -EINVAL;

	maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
	if (write)
		memcpy_toio(maddr + offset, buf, len);
	else
		memcpy_fromio(buf, maddr + offset, len);
	iounmap(maddr);

	return len;
}
EXPORT_SYMBOL_GPL(generic_access_phys);
#endif

/*
 * Access another process' address space as given in mm.  If non-NULL, use the
 * given task for page fault accounting.
 */
static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long addr, void *buf, int len, int write)
{
	struct vm_area_struct *vma;
	void *old_buf = buf;

	down_read(&mm->mmap_sem);
	/* ignore errors, just check how much was successfully transferred */
	while (len) {
		int bytes, ret, offset;
		void *maddr;
		struct page *page = NULL;

		ret = get_user_pages(tsk, mm, addr, 1,
				write, 1, &page, &vma);
		if (ret <= 0) {
#ifndef CONFIG_HAVE_IOREMAP_PROT
			break;
#else
			/*
			 * Check if this is a VM_IO | VM_PFNMAP VMA, which
			 * we can access using slightly different code.
			 */
			vma = find_vma(mm, addr);
			if (!vma || vma->vm_start > addr)
				break;
			if (vma->vm_ops && vma->vm_ops->access)
				ret = vma->vm_ops->access(vma, addr, buf,
							  len, write);
			if (ret <= 0)
				break;
			bytes = ret;
#endif
		} else {
			bytes = len;
			offset = addr & (PAGE_SIZE-1);
			if (bytes > PAGE_SIZE-offset)
				bytes = PAGE_SIZE-offset;

			maddr = kmap(page);
			if (write) {
				copy_to_user_page(vma, page, addr,
						  maddr + offset, buf, bytes);
				set_page_dirty_lock(page);
			} else {
				copy_from_user_page(vma, page, addr,
						    buf, maddr + offset, bytes);
			}
			kunmap(page);
			page_cache_release(page);
		}
		len -= bytes;
		buf += bytes;
		addr += bytes;
	}
	up_read(&mm->mmap_sem);

	return buf - old_buf;
}

/**
 * access_remote_vm - access another process' address space
 * @mm:		the mm_struct of the target address space
 * @addr:	start address to access
 * @buf:	source or destination buffer
 * @len:	number of bytes to transfer
 * @write:	whether the access is a write
 *
 * The caller must hold a reference on @mm.
 */
int access_remote_vm(struct mm_struct *mm, unsigned long addr,
		void *buf, int len, int write)
{
	return __access_remote_vm(NULL, mm, addr, buf, len, write);
}

/*
 * Access another process' address space.
 * Source/target buffer must be kernel space,
 * Do not walk the page table directly, use get_user_pages
 */
int access_process_vm(struct task_struct *tsk, unsigned long addr,
		void *buf, int len, int write)
{
	struct mm_struct *mm;
	int ret;

	mm = get_task_mm(tsk);
	if (!mm)
		return 0;

	ret = __access_remote_vm(tsk, mm, addr, buf, len, write);
	mmput(mm);

	return ret;
}

/*
 * Print the name of a VMA.
 */
void print_vma_addr(char *prefix, unsigned long ip)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;

	/*
	 * Do not print if we are in atomic
	 * contexts (in exception stacks, etc.):
	 */
	if (preempt_count())
		return;

	down_read(&mm->mmap_sem);
	vma = find_vma(mm, ip);
	if (vma && vma->vm_file) {
		struct file *f = vma->vm_file;
		char *buf = (char *)__get_free_page(GFP_KERNEL);
		if (buf) {
			char *p;

			p = d_path(&f->f_path, buf, PAGE_SIZE);
			if (IS_ERR(p))
				p = "?";
			printk("%s%s[%lx+%lx]", prefix, kbasename(p),
					vma->vm_start,
					vma->vm_end - vma->vm_start);
			free_page((unsigned long)buf);
		}
	}
	up_read(&mm->mmap_sem);
}

#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)
void might_fault(void)
{
	/*
	 * Some code (nfs/sunrpc) uses socket ops on kernel memory while
	 * holding the mmap_sem, this is safe because kernel memory doesn't
	 * get paged out, therefore we'll never actually fault, and the
	 * below annotations will generate false positives.
	 */
	if (segment_eq(get_fs(), KERNEL_DS))
		return;

	/*
	 * it would be nicer only to annotate paths which are not under
	 * pagefault_disable, however that requires a larger audit and
	 * providing helpers like get_user_atomic.
	 */
	if (in_atomic())
		return;

	__might_sleep(__FILE__, __LINE__, 0);

	if (current->mm)
		might_lock_read(&current->mm->mmap_sem);
}
EXPORT_SYMBOL(might_fault);
#endif

#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
static void clear_gigantic_page(struct page *page,
				unsigned long addr,
				unsigned int pages_per_huge_page)
{
	int i;
	struct page *p = page;

	might_sleep();
	for (i = 0; i < pages_per_huge_page;
	     i++, p = mem_map_next(p, page, i)) {
		cond_resched();
		clear_user_highpage(p, addr + i * PAGE_SIZE);
	}
}
void clear_huge_page(struct page *page,
		     unsigned long addr, unsigned int pages_per_huge_page)
{
	int i;

	if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
		clear_gigantic_page(page, addr, pages_per_huge_page);
		return;
	}

	might_sleep();
	for (i = 0; i < pages_per_huge_page; i++) {
		cond_resched();
		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
	}
}

static void copy_user_gigantic_page(struct page *dst, struct page *src,
				    unsigned long addr,
				    struct vm_area_struct *vma,
				    unsigned int pages_per_huge_page)
{
	int i;
	struct page *dst_base = dst;
	struct page *src_base = src;

	for (i = 0; i < pages_per_huge_page; ) {
		cond_resched();
		copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);

		i++;
		dst = mem_map_next(dst, dst_base, i);
		src = mem_map_next(src, src_base, i);
	}
}

void copy_user_huge_page(struct page *dst, struct page *src,
			 unsigned long addr, struct vm_area_struct *vma,
			 unsigned int pages_per_huge_page)
{
	int i;

	if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
		copy_user_gigantic_page(dst, src, addr, vma,
					pages_per_huge_page);
		return;
	}

	might_sleep();
	for (i = 0; i < pages_per_huge_page; i++) {
		cond_resched();
		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
	}
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */

#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS

static struct kmem_cache *page_ptl_cachep;

void __init ptlock_cache_init(void)
{
	page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
			SLAB_PANIC, NULL);
}

bool ptlock_alloc(struct page *page)
{
	spinlock_t *ptl;

	ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL);
	if (!ptl)
		return false;
	page->ptl = ptl;
	return true;
}

void ptlock_free(struct page *page)
{
	kmem_cache_free(page_ptl_cachep, page->ptl);
}
#endif