mm/gup.c

#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/spinlock.h>

#include <linux/hugetlb.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>

#include "internal.h"

static struct page *no_page_table(struct vm_area_struct *vma,
		unsigned int flags)
{
	/*
	 * When core dumping an enormous anonymous area that nobody
	 * has touched so far, we don't want to allocate unnecessary pages or
	 * page tables.  Return error instead of NULL to skip handle_mm_fault,
	 * then get_dump_page() will return NULL to leave a hole in the dump.
	 * But we can only make this optimization where a hole would surely
	 * be zero-filled if handle_mm_fault() actually did handle it.
	 */
	if ((flags & FOLL_DUMP) && (!vma->vm_ops || !vma->vm_ops->fault))
		return ERR_PTR(-EFAULT);
	return NULL;
}

static struct page *follow_page_pte(struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmd, unsigned int flags)
{
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;
	spinlock_t *ptl;
	pte_t *ptep, pte;

retry:
	if (unlikely(pmd_bad(*pmd)))
		return no_page_table(vma, flags);

	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
	pte = *ptep;
	if (!pte_present(pte)) {
		swp_entry_t entry;
		/*
		 * KSM's break_ksm() relies upon recognizing a ksm page
		 * even while it is being migrated, so for that case we
		 * need migration_entry_wait().
		 */
		if (likely(!(flags & FOLL_MIGRATION)))
			goto no_page;
		if (pte_none(pte) || pte_file(pte))
			goto no_page;
		entry = pte_to_swp_entry(pte);
		if (!is_migration_entry(entry))
			goto no_page;
		pte_unmap_unlock(ptep, ptl);
		migration_entry_wait(mm, pmd, address);
		goto retry;
	}
	if ((flags & FOLL_NUMA) && pte_numa(pte))
		goto no_page;
	if ((flags & FOLL_WRITE) && !pte_write(pte)) {
		pte_unmap_unlock(ptep, ptl);
		return NULL;
	}

	page = vm_normal_page(vma, address, pte);
	if (unlikely(!page)) {
		if ((flags & FOLL_DUMP) ||
		    !is_zero_pfn(pte_pfn(pte)))
			goto bad_page;
		page = pte_page(pte);
	}

	if (flags & FOLL_GET)
		get_page_foll(page);
	if (flags & FOLL_TOUCH) {
		if ((flags & FOLL_WRITE) &&
		    !pte_dirty(pte) && !PageDirty(page))
			set_page_dirty(page);
		/*
		 * pte_mkyoung() would be more correct here, but atomic care
		 * is needed to avoid losing the dirty bit: it is easier to use
		 * mark_page_accessed().
		 */
		mark_page_accessed(page);
	}
	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
		/*
		 * The preliminary mapping check is mainly to avoid the
		 * pointless overhead of lock_page on the ZERO_PAGE
		 * which might bounce very badly if there is contention.
		 *
		 * If the page is already locked, we don't need to
		 * handle it now - vmscan will handle it later if and
		 * when it attempts to reclaim the page.
		 */
		if (page->mapping && trylock_page(page)) {
			lru_add_drain();  /* push cached pages to LRU */
			/*
			 * Because we lock page here, and migration is
			 * blocked by the pte's page reference, and we
			 * know the page is still mapped, we don't even
			 * need to check for file-cache page truncation.
			 */
			mlock_vma_page(page);
			unlock_page(page);
		}
	}
	pte_unmap_unlock(ptep, ptl);
	return page;
bad_page:
	pte_unmap_unlock(ptep, ptl);
	return ERR_PTR(-EFAULT);

no_page:
	pte_unmap_unlock(ptep, ptl);
	if (!pte_none(pte))
		return NULL;
	return no_page_table(vma, flags);
}

/**
 * follow_page_mask - look up a page descriptor from a user-virtual address
 * @vma: vm_area_struct mapping @address
 * @address: virtual address to look up
 * @flags: flags modifying lookup behaviour
 * @page_mask: on output, *page_mask is set according to the size of the page
 *
 * @flags can have FOLL_ flags set, defined in <linux/mm.h>
 *
 * Returns the mapped (struct page *), %NULL if no mapping exists, or
 * an error pointer if there is a mapping to something not represented
 * by a page descriptor (see also vm_normal_page()).
 */
struct page *follow_page_mask(struct vm_area_struct *vma,
			      unsigned long address, unsigned int flags,
			      unsigned int *page_mask)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	spinlock_t *ptl;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

	*page_mask = 0;

	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
	if (!IS_ERR(page)) {
		BUG_ON(flags & FOLL_GET);
		return page;
	}

	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		return no_page_table(vma, flags);

	pud = pud_offset(pgd, address);
	if (pud_none(*pud))
		return no_page_table(vma, flags);
	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
		if (flags & FOLL_GET)
			return NULL;
		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
		return page;
	}
	if (unlikely(pud_bad(*pud)))
		return no_page_table(vma, flags);

	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		return no_page_table(vma, flags);
	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
		if (flags & FOLL_GET) {
			/*
			 * Refcount on tail pages are not well-defined and
			 * shouldn't be taken. The caller should handle a NULL
			 * return when trying to follow tail pages.
			 */
			if (PageHead(page))
				get_page(page);
			else
				page = NULL;
		}
		return page;
	}
	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
		return no_page_table(vma, flags);
	if (pmd_trans_huge(*pmd)) {
		if (flags & FOLL_SPLIT) {
			split_huge_page_pmd(vma, address, pmd);
			return follow_page_pte(vma, address, pmd, flags);
		}
		ptl = pmd_lock(mm, pmd);
		if (likely(pmd_trans_huge(*pmd))) {
			if (unlikely(pmd_trans_splitting(*pmd))) {
				spin_unlock(ptl);
				wait_split_huge_page(vma->anon_vma, pmd);
			} else {
				page = follow_trans_huge_pmd(vma, address,
							     pmd, flags);
				spin_unlock(ptl);
				*page_mask = HPAGE_PMD_NR - 1;
				return page;
			}
		} else
			spin_unlock(ptl);
	}
	return follow_page_pte(vma, address, pmd, flags);
}

static int get_gate_page(struct mm_struct *mm, unsigned long address,
		unsigned int gup_flags, struct vm_area_struct **vma,
		struct page **page)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	int ret = -EFAULT;

	/* user gate pages are read-only */
	if (gup_flags & FOLL_WRITE)
		return -EFAULT;
	if (address > TASK_SIZE)
		pgd = pgd_offset_k(address);
	else
		pgd = pgd_offset_gate(mm, address);
	BUG_ON(pgd_none(*pgd));
	pud = pud_offset(pgd, address);
	BUG_ON(pud_none(*pud));
	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		return -EFAULT;
	VM_BUG_ON(pmd_trans_huge(*pmd));
	pte = pte_offset_map(pmd, address);
	if (pte_none(*pte))
		goto unmap;
	*vma = get_gate_vma(mm);
	if (!page)
		goto out;
	*page = vm_normal_page(*vma, address, *pte);
	if (!*page) {
		if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte)))
			goto unmap;
		*page = pte_page(*pte);
	}
	get_page(*page);
out:
	ret = 0;
unmap:
	pte_unmap(pte);
	return ret;
}

static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
		unsigned long address, unsigned int *flags, int *nonblocking)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned int fault_flags = 0;
	int ret;

	/* For mlock, just skip the stack guard page. */
	if ((*flags & FOLL_MLOCK) &&
			(stack_guard_page_start(vma, address) ||
			 stack_guard_page_end(vma, address + PAGE_SIZE)))
		return -ENOENT;
	if (*flags & FOLL_WRITE)
		fault_flags |= FAULT_FLAG_WRITE;
	if (nonblocking)
		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
	if (*flags & FOLL_NOWAIT)
		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;

	ret = handle_mm_fault(mm, vma, address, fault_flags);
	if (ret & VM_FAULT_ERROR) {
		if (ret & VM_FAULT_OOM)
			return -ENOMEM;
		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
			return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
		if (ret & VM_FAULT_SIGBUS)
			return -EFAULT;
		BUG();
	}

	if (tsk) {
		if (ret & VM_FAULT_MAJOR)
			tsk->maj_flt++;
		else
			tsk->min_flt++;
	}

	if (ret & VM_FAULT_RETRY) {
		if (nonblocking)
			*nonblocking = 0;
		return -EBUSY;
	}

	/*
	 * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when
	 * necessary, even if maybe_mkwrite decided not to set pte_write. We
	 * can thus safely do subsequent page lookups as if they were reads.
	 * But only do so when looping for pte_write is futile: in some cases
	 * userspace may also be wanting to write to the gotten user page,
	 * which a read fault here might prevent (a readonly page might get
	 * reCOWed by userspace write).
	 */
	if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE))
		*flags &= ~FOLL_WRITE;
	return 0;
}

static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
{
	vm_flags_t vm_flags = vma->vm_flags;

	if (vm_flags & (VM_IO | VM_PFNMAP))
		return -EFAULT;

	if (gup_flags & FOLL_WRITE) {
		if (!(vm_flags & VM_WRITE)) {
			if (!(gup_flags & FOLL_FORCE))
				return -EFAULT;
			/*
			 * We used to let the write,force case do COW in a
			 * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
			 * set a breakpoint in a read-only mapping of an
			 * executable, without corrupting the file (yet only
			 * when that file had been opened for writing!).
			 * Anon pages in shared mappings are surprising: now
			 * just reject it.
			 */
			if (!is_cow_mapping(vm_flags)) {
				WARN_ON_ONCE(vm_flags & VM_MAYWRITE);
				return -EFAULT;
			}
		}
	} else if (!(vm_flags & VM_READ)) {
		if (!(gup_flags & FOLL_FORCE))
			return -EFAULT;
		/*
		 * Is there actually any vma we can reach here which does not
		 * have VM_MAYREAD set?
		 */
		if (!(vm_flags & VM_MAYREAD))
			return -EFAULT;
	}
	return 0;
}

/**
 * __get_user_pages() - pin user pages in memory
 * @tsk:	task_struct of target task
 * @mm:		mm_struct of target mm
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
 * @gup_flags:	flags modifying pin behaviour
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long. Or NULL, if caller
 *		only intends to ensure the pages are faulted in.
 * @vmas:	array of pointers to vmas corresponding to each page.
 *		Or NULL if the caller does not require them.
 * @nonblocking: whether waiting for disk IO or mmap_sem contention
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno. Each page returned must be released
 * with a put_page() call when it is finished with. vmas will only
 * remain valid while mmap_sem is held.
 *
 * Must be called with mmap_sem held for read or write.
 *
 * __get_user_pages walks a process's page tables and takes a reference to
 * each struct page that each user address corresponds to at a given
 * instant. That is, it takes the page that would be accessed if a user
 * thread accesses the given user virtual address at that instant.
 *
 * This does not guarantee that the page exists in the user mappings when
 * __get_user_pages returns, and there may even be a completely different
 * page there in some cases (eg. if mmapped pagecache has been invalidated
 * and subsequently re faulted). However it does guarantee that the page
 * won't be freed completely. And mostly callers simply care that the page
 * contains data that was valid *at some point in time*. Typically, an IO
 * or similar operation cannot guarantee anything stronger anyway because
 * locks can't be held over the syscall boundary.
 *
 * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If
 * the page is written to, set_page_dirty (or set_page_dirty_lock, as
 * appropriate) must be called after the page is finished with, and
 * before put_page is called.
 *
 * If @nonblocking != NULL, __get_user_pages will not wait for disk IO
 * or mmap_sem contention, and if waiting is needed to pin all pages,
 * *@nonblocking will be set to 0.
 *
 * In most cases, get_user_pages or get_user_pages_fast should be used
 * instead of __get_user_pages. __get_user_pages should be used only if
 * you need some special @gup_flags.
 */
long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long start, unsigned long nr_pages,
		unsigned int gup_flags, struct page **pages,
		struct vm_area_struct **vmas, int *nonblocking)
{
	long i = 0;
	unsigned int page_mask;
	struct vm_area_struct *vma = NULL;

	if (!nr_pages)
		return 0;

	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));

	/*
	 * If FOLL_FORCE is set then do not force a full fault as the hinting
	 * fault information is unrelated to the reference behaviour of a task
	 * using the address space
	 */
	if (!(gup_flags & FOLL_FORCE))
		gup_flags |= FOLL_NUMA;

	do {
		struct page *page;
		unsigned int foll_flags = gup_flags;
		unsigned int page_increm;

		/* first iteration or cross vma bound */
		if (!vma || start >= vma->vm_end) {
			vma = find_extend_vma(mm, start);
			if (!vma && in_gate_area(mm, start)) {
				int ret;
				ret = get_gate_page(mm, start & PAGE_MASK,
						gup_flags, &vma,
						pages ? &pages[i] : NULL);
				if (ret)
					return i ? : ret;
				page_mask = 0;
				goto next_page;
			}

			if (!vma || check_vma_flags(vma, gup_flags))
				return i ? : -EFAULT;
			if (is_vm_hugetlb_page(vma)) {
				i = follow_hugetlb_page(mm, vma, pages, vmas,
						&start, &nr_pages, i,
						gup_flags);
				continue;
			}
		}
retry:
		/*
		 * If we have a pending SIGKILL, don't keep faulting pages and
		 * potentially allocating memory.
		 */
		if (unlikely(fatal_signal_pending(current)))
			return i ? i : -ERESTARTSYS;
		cond_resched();
		page = follow_page_mask(vma, start, foll_flags, &page_mask);
		if (!page) {
			int ret;
			ret = faultin_page(tsk, vma, start, &foll_flags,
					nonblocking);
			switch (ret) {
			case 0:
				goto retry;
			case -EFAULT:
			case -ENOMEM:
			case -EHWPOISON:
				return i ? i : ret;
			case -EBUSY:
				return i;
			case -ENOENT:
				goto next_page;
			}
			BUG();
		}
		if (IS_ERR(page))
			return i ? i : PTR_ERR(page);
		if (pages) {
			pages[i] = page;
			flush_anon_page(vma, page, start);
			flush_dcache_page(page);
			page_mask = 0;
		}
next_page:
		if (vmas) {
			vmas[i] = vma;
			page_mask = 0;
		}
		page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
		if (page_increm > nr_pages)
			page_increm = nr_pages;
		i += page_increm;
		start += page_increm * PAGE_SIZE;
		nr_pages -= page_increm;
	} while (nr_pages);
	return i;
}
EXPORT_SYMBOL(__get_user_pages);

/*
 * fixup_user_fault() - manually resolve a user page fault
 * @tsk:	the task_struct to use for page fault accounting, or
 *		NULL if faults are not to be recorded.
 * @mm:		mm_struct of target mm
 * @address:	user address
 * @fault_flags:flags to pass down to handle_mm_fault()
 *
 * This is meant to be called in the specific scenario where for locking reasons
 * we try to access user memory in atomic context (within a pagefault_disable()
 * section), this returns -EFAULT, and we want to resolve the user fault before
 * trying again.
 *
 * Typically this is meant to be used by the futex code.
 *
 * The main difference with get_user_pages() is that this function will
 * unconditionally call handle_mm_fault() which will in turn perform all the
 * necessary SW fixup of the dirty and young bits in the PTE, while
 * handle_mm_fault() only guarantees to update these in the struct page.
 *
 * This is important for some architectures where those bits also gate the
 * access permission to the page because they are maintained in software.  On
 * such architectures, gup() will not be enough to make a subsequent access
 * succeed.
 *
 * This should be called with the mm_sem held for read.
 */
int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
		     unsigned long address, unsigned int fault_flags)
{
	struct vm_area_struct *vma;
	vm_flags_t vm_flags;
	int ret;

	vma = find_extend_vma(mm, address);
	if (!vma || address < vma->vm_start)
		return -EFAULT;

	vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ;
	if (!(vm_flags & vma->vm_flags))
		return -EFAULT;

	ret = handle_mm_fault(mm, vma, address, fault_flags);
	if (ret & VM_FAULT_ERROR) {
		if (ret & VM_FAULT_OOM)
			return -ENOMEM;
		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
			return -EHWPOISON;
		if (ret & VM_FAULT_SIGBUS)
			return -EFAULT;
		BUG();
	}
	if (tsk) {
		if (ret & VM_FAULT_MAJOR)
			tsk->maj_flt++;
		else
			tsk->min_flt++;
	}
	return 0;
}

/*
 * get_user_pages() - pin user pages in memory
 * @tsk:	the task_struct to use for page fault accounting, or
 *		NULL if faults are not to be recorded.
 * @mm:		mm_struct of target mm
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
 * @write:	whether pages will be written to by the caller
 * @force:	whether to force access even when user mapping is currently
 *		protected (but never forces write access to shared mapping).
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long. Or NULL, if caller
 *		only intends to ensure the pages are faulted in.
 * @vmas:	array of pointers to vmas corresponding to each page.
 *		Or NULL if the caller does not require them.
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno. Each page returned must be released
 * with a put_page() call when it is finished with. vmas will only
 * remain valid while mmap_sem is held.
 *
 * Must be called with mmap_sem held for read or write.
 *
 * get_user_pages walks a process's page tables and takes a reference to
 * each struct page that each user address corresponds to at a given
 * instant. That is, it takes the page that would be accessed if a user
 * thread accesses the given user virtual address at that instant.
 *
 * This does not guarantee that the page exists in the user mappings when
 * get_user_pages returns, and there may even be a completely different
 * page there in some cases (eg. if mmapped pagecache has been invalidated
 * and subsequently re faulted). However it does guarantee that the page
 * won't be freed completely. And mostly callers simply care that the page
 * contains data that was valid *at some point in time*. Typically, an IO
 * or similar operation cannot guarantee anything stronger anyway because
 * locks can't be held over the syscall boundary.
 *
 * If write=0, the page must not be written to. If the page is written to,
 * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called
 * after the page is finished with, and before put_page is called.
 *
 * get_user_pages is typically used for fewer-copy IO operations, to get a
 * handle on the memory by some means other than accesses via the user virtual
 * addresses. The pages may be submitted for DMA to devices or accessed via
 * their kernel linear mapping (via the kmap APIs). Care should be taken to
 * use the correct cache flushing APIs.
 *
 * See also get_user_pages_fast, for performance critical applications.
 */
long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long start, unsigned long nr_pages, int write,
		int force, struct page **pages, struct vm_area_struct **vmas)
{
	int flags = FOLL_TOUCH;

	if (pages)
		flags |= FOLL_GET;
	if (write)
		flags |= FOLL_WRITE;
	if (force)
		flags |= FOLL_FORCE;

	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
				NULL);
}
EXPORT_SYMBOL(get_user_pages);

/**
 * get_dump_page() - pin user page in memory while writing it to core dump
 * @addr: user address
 *
 * Returns struct page pointer of user page pinned for dump,
 * to be freed afterwards by page_cache_release() or put_page().
 *
 * Returns NULL on any kind of failure - a hole must then be inserted into
 * the corefile, to preserve alignment with its headers; and also returns
 * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
 * allowing a hole to be left in the corefile to save diskspace.
 *
 * Called without mmap_sem, but after all other threads have been killed.
 */
#ifdef CONFIG_ELF_CORE
struct page *get_dump_page(unsigned long addr)
{
	struct vm_area_struct *vma;
	struct page *page;

	if (__get_user_pages(current, current->mm, addr, 1,
			     FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
			     NULL) < 1)
		return NULL;
	flush_cache_page(vma, addr, page_to_pfn(page));
	return page;
}
#endif /* CONFIG_ELF_CORE */