[deliverable/linux.git] / mm / mlock.c

/*
 *      linux/mm/mlock.c
 *
 *  (C) Copyright 1995 Linus Torvalds
 *  (C) Copyright 2002 Christoph Hellwig
 */

#include <linux/capability.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>

#include "internal.h"

int can_do_mlock(void)
{
        if (capable(CAP_IPC_LOCK))
                return 1;
        if (rlimit(RLIMIT_MEMLOCK) != 0)
                return 1;
        return 0;
}
EXPORT_SYMBOL(can_do_mlock);

/*
 * Mlocked pages are marked with PageMlocked() flag for efficient testing
 * in vmscan and, possibly, the fault path; and to support semi-accurate
 * statistics.
 *
 * An mlocked page [PageMlocked(page)] is unevictable.  As such, it will
 * be placed on the LRU "unevictable" list, rather than the [in]active lists.
 * The unevictable list is an LRU sibling list to the [in]active lists.
 * PageUnevictable is set to indicate the unevictable state.
 *
 * When lazy mlocking via vmscan, it is important to ensure that the
 * vma's VM_LOCKED status is not concurrently being modified, otherwise we
 * may have mlocked a page that is being munlocked. So lazy mlock must take
 * the mmap_sem for read, and verify that the vma really is locked
 * (see mm/rmap.c).
 */

/*
 *  LRU accounting for clear_page_mlock()
 */
void clear_page_mlock(struct page *page)
{
        if (!TestClearPageMlocked(page))
                return;

        mod_zone_page_state(page_zone(page), NR_MLOCK,
                            -hpage_nr_pages(page));
        count_vm_event(UNEVICTABLE_PGCLEARED);
        if (!isolate_lru_page(page)) {
                putback_lru_page(page);
        } else {
                /*
                 * We lost the race. the page already moved to evictable list.
                 */
                if (PageUnevictable(page))
                        count_vm_event(UNEVICTABLE_PGSTRANDED);
        }
}

/*
 * Mark page as mlocked if not already.
 * If page on LRU, isolate and putback to move to unevictable list.
 */
void mlock_vma_page(struct page *page)
{
        BUG_ON(!PageLocked(page));

        if (!TestSetPageMlocked(page)) {
                mod_zone_page_state(page_zone(page), NR_MLOCK,
                                    hpage_nr_pages(page));
                count_vm_event(UNEVICTABLE_PGMLOCKED);
                if (!isolate_lru_page(page))
                        putback_lru_page(page);
        }
}

/*
 * Finish munlock after successful page isolation
 *
 * Page must be locked. This is a wrapper for try_to_munlock()
 * and putback_lru_page() with munlock accounting.
 */
static void __munlock_isolated_page(struct page *page)
{
        int ret = SWAP_AGAIN;

        /*
         * Optimization: if the page was mapped just once, that's our mapping
         * and we don't need to check all the other vmas.
         */
        if (page_mapcount(page) > 1)
                ret = try_to_munlock(page);

        /* Did try_to_unlock() succeed or punt? */
        if (ret != SWAP_MLOCK)
                count_vm_event(UNEVICTABLE_PGMUNLOCKED);

        putback_lru_page(page);
}

/*
 * Accounting for page isolation fail during munlock
 *
 * Performs accounting when page isolation fails in munlock. There is nothing
 * else to do because it means some other task has already removed the page
 * from the LRU. putback_lru_page() will take care of removing the page from
 * the unevictable list, if necessary. vmscan [page_referenced()] will move
 * the page back to the unevictable list if some other vma has it mlocked.
 */
static void __munlock_isolation_failed(struct page *page)
{
        if (PageUnevictable(page))
                count_vm_event(UNEVICTABLE_PGSTRANDED);
        else
                count_vm_event(UNEVICTABLE_PGMUNLOCKED);
}

/**
 * munlock_vma_page - munlock a vma page
 * @page - page to be unlocked
 *
 * called from munlock()/munmap() path with page supposedly on the LRU.
 * When we munlock a page, because the vma where we found the page is being
 * munlock()ed or munmap()ed, we want to check whether other vmas hold the
 * page locked so that we can leave it on the unevictable lru list and not
 * bother vmscan with it.  However, to walk the page's rmap list in
 * try_to_munlock() we must isolate the page from the LRU.  If some other
 * task has removed the page from the LRU, we won't be able to do that.
 * So we clear the PageMlocked as we might not get another chance.  If we
 * can't isolate the page, we leave it for putback_lru_page() and vmscan
 * [page_referenced()/try_to_unmap()] to deal with.
 */
unsigned int munlock_vma_page(struct page *page)
{
        unsigned int page_mask = 0;

        BUG_ON(!PageLocked(page));

        if (TestClearPageMlocked(page)) {
                unsigned int nr_pages = hpage_nr_pages(page);
                mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
                page_mask = nr_pages - 1;
                if (!isolate_lru_page(page))
                        __munlock_isolated_page(page);
                else
                        __munlock_isolation_failed(page);
        }

        return page_mask;
}

/**
 * __mlock_vma_pages_range() -  mlock a range of pages in the vma.
 * @vma:   target vma
 * @start: start address
 * @end:   end address
 *
 * This takes care of making the pages present too.
 *
 * return 0 on success, negative error code on error.
 *
 * vma->vm_mm->mmap_sem must be held for at least read.
 */
long __mlock_vma_pages_range(struct vm_area_struct *vma,
                unsigned long start, unsigned long end, int *nonblocking)
{
        struct mm_struct *mm = vma->vm_mm;
        unsigned long nr_pages = (end - start) / PAGE_SIZE;
        int gup_flags;

        VM_BUG_ON(start & ~PAGE_MASK);
        VM_BUG_ON(end   & ~PAGE_MASK);
        VM_BUG_ON(start < vma->vm_start);
        VM_BUG_ON(end   > vma->vm_end);
        VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));

        gup_flags = FOLL_TOUCH | FOLL_MLOCK;
        /*
         * We want to touch writable mappings with a write fault in order
         * to break COW, except for shared mappings because these don't COW
         * and we would not want to dirty them for nothing.
         */
        if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
                gup_flags |= FOLL_WRITE;

        /*
         * We want mlock to succeed for regions that have any permissions
         * other than PROT_NONE.
         */
        if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
                gup_flags |= FOLL_FORCE;

        /*
         * We made sure addr is within a VMA, so the following will
         * not result in a stack expansion that recurses back here.
         */
        return __get_user_pages(current, mm, start, nr_pages, gup_flags,
                                NULL, NULL, nonblocking);
}

/*
 * convert get_user_pages() return value to posix mlock() error
 */
static int __mlock_posix_error_return(long retval)
{
        if (retval == -EFAULT)
                retval = -ENOMEM;
        else if (retval == -ENOMEM)
                retval = -EAGAIN;
        return retval;
}

/*
 * Munlock a batch of pages from the same zone
 *
 * The work is split to two main phases. First phase clears the Mlocked flag
 * and attempts to isolate the pages, all under a single zone lru lock.
 * The second phase finishes the munlock only for pages where isolation
 * succeeded.
 *
 * Note that pvec is modified during the process. Before returning
 * pagevec_reinit() is called on it.
 */
static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
{
        int i;
        int nr = pagevec_count(pvec);
        int delta_munlocked = -nr;

        /* Phase 1: page isolation */
        spin_lock_irq(&zone->lru_lock);
        for (i = 0; i < nr; i++) {
                struct page *page = pvec->pages[i];

                if (TestClearPageMlocked(page)) {
                        struct lruvec *lruvec;
                        int lru;

                        if (PageLRU(page)) {
                                lruvec = mem_cgroup_page_lruvec(page, zone);
                                lru = page_lru(page);

                                get_page(page);
                                ClearPageLRU(page);
                                del_page_from_lru_list(page, lruvec, lru);
                        } else {
                                __munlock_isolation_failed(page);
                                goto skip_munlock;
                        }

                } else {
skip_munlock:
                        /*
                         * We won't be munlocking this page in the next phase
                         * but we still need to release the follow_page_mask()
                         * pin.
                         */
                        pvec->pages[i] = NULL;
                        put_page(page);
                        delta_munlocked++;
                }
        }
        __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
        spin_unlock_irq(&zone->lru_lock);

        /* Phase 2: page munlock and putback */
        for (i = 0; i < nr; i++) {
                struct page *page = pvec->pages[i];

                if (page) {
                        lock_page(page);
                        __munlock_isolated_page(page);
                        unlock_page(page);
                        put_page(page); /* pin from follow_page_mask() */
                }
        }
        pagevec_reinit(pvec);
}

/*
 * munlock_vma_pages_range() - munlock all pages in the vma range.'
 * @vma - vma containing range to be munlock()ed.
 * @start - start address in @vma of the range
 * @end - end of range in @vma.
 *
 *  For mremap(), munmap() and exit().
 *
 * Called with @vma VM_LOCKED.
 *
 * Returns with VM_LOCKED cleared.  Callers must be prepared to
 * deal with this.
 *
 * We don't save and restore VM_LOCKED here because pages are
 * still on lru.  In unmap path, pages might be scanned by reclaim
 * and re-mlocked by try_to_{munlock|unmap} before we unmap and
 * free them.  This will result in freeing mlocked pages.
 */
void munlock_vma_pages_range(struct vm_area_struct *vma,
                             unsigned long start, unsigned long end)
{
        struct pagevec pvec;
        struct zone *zone = NULL;

        pagevec_init(&pvec, 0);
        vma->vm_flags &= ~VM_LOCKED;

        while (start < end) {
                struct page *page;
                unsigned int page_mask, page_increm;
                struct zone *pagezone;

                /*
                 * Although FOLL_DUMP is intended for get_dump_page(),
                 * it just so happens that its special treatment of the
                 * ZERO_PAGE (returning an error instead of doing get_page)
                 * suits munlock very well (and if somehow an abnormal page
                 * has sneaked into the range, we won't oops here: great).
                 */
                page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
                                        &page_mask);
                if (page && !IS_ERR(page)) {
                        pagezone = page_zone(page);
                        /* The whole pagevec must be in the same zone */
                        if (pagezone != zone) {
                                if (pagevec_count(&pvec))
                                        __munlock_pagevec(&pvec, zone);
                                zone = pagezone;
                        }
                        if (PageTransHuge(page)) {
                                /*
                                 * THP pages are not handled by pagevec due
                                 * to their possible split (see below).
                                 */
                                if (pagevec_count(&pvec))
                                        __munlock_pagevec(&pvec, zone);
                                lock_page(page);
                                /*
                                 * Any THP page found by follow_page_mask() may
                                 * have gotten split before reaching
                                 * munlock_vma_page(), so we need to recompute
                                 * the page_mask here.
                                 */
                                page_mask = munlock_vma_page(page);
                                unlock_page(page);
                                put_page(page); /* follow_page_mask() */
                        } else {
                                /*
                                 * Non-huge pages are handled in batches
                                 * via pagevec. The pin from
                                 * follow_page_mask() prevents them from
                                 * collapsing by THP.
                                 */
                                if (pagevec_add(&pvec, page) == 0)
                                        __munlock_pagevec(&pvec, zone);
                        }
                }
                page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
                start += page_increm * PAGE_SIZE;
                cond_resched();
        }
        if (pagevec_count(&pvec))
                __munlock_pagevec(&pvec, zone);
}

/*
 * mlock_fixup  - handle mlock[all]/munlock[all] requests.
 *
 * Filters out "special" vmas -- VM_LOCKED never gets set for these, and
 * munlock is a no-op.  However, for some special vmas, we go ahead and
 * populate the ptes.
 *
 * For vmas that pass the filters, merge/split as appropriate.
 */
static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
        unsigned long start, unsigned long end, vm_flags_t newflags)
{
        struct mm_struct *mm = vma->vm_mm;
        pgoff_t pgoff;
        int nr_pages;
        int ret = 0;
        int lock = !!(newflags & VM_LOCKED);

        if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
            is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
                goto out;       /* don't set VM_LOCKED,  don't count */

        pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
        *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
                          vma->vm_file, pgoff, vma_policy(vma));
        if (*prev) {
                vma = *prev;
                goto success;
        }

        if (start != vma->vm_start) {
                ret = split_vma(mm, vma, start, 1);
                if (ret)
                        goto out;
        }

        if (end != vma->vm_end) {
                ret = split_vma(mm, vma, end, 0);
                if (ret)
                        goto out;
        }

success:
        /*
         * Keep track of amount of locked VM.
         */
        nr_pages = (end - start) >> PAGE_SHIFT;
        if (!lock)
                nr_pages = -nr_pages;
        mm->locked_vm += nr_pages;

        /*
         * vm_flags is protected by the mmap_sem held in write mode.
         * It's okay if try_to_unmap_one unmaps a page just after we
         * set VM_LOCKED, __mlock_vma_pages_range will bring it back.
         */

        if (lock)
                vma->vm_flags = newflags;
        else
                munlock_vma_pages_range(vma, start, end);

out:
        *prev = vma;
        return ret;
}

static int do_mlock(unsigned long start, size_t len, int on)
{
        unsigned long nstart, end, tmp;
        struct vm_area_struct * vma, * prev;
        int error;

        VM_BUG_ON(start & ~PAGE_MASK);
        VM_BUG_ON(len != PAGE_ALIGN(len));
        end = start + len;
        if (end < start)
                return -EINVAL;
        if (end == start)
                return 0;
        vma = find_vma(current->mm, start);
        if (!vma || vma->vm_start > start)
                return -ENOMEM;

        prev = vma->vm_prev;
        if (start > vma->vm_start)
                prev = vma;

        for (nstart = start ; ; ) {
                vm_flags_t newflags;

                /* Here we know that  vma->vm_start <= nstart < vma->vm_end. */

                newflags = vma->vm_flags & ~VM_LOCKED;
                if (on)
                        newflags |= VM_LOCKED;

                tmp = vma->vm_end;
                if (tmp > end)
                        tmp = end;
                error = mlock_fixup(vma, &prev, nstart, tmp, newflags);
                if (error)
                        break;
                nstart = tmp;
                if (nstart < prev->vm_end)
                        nstart = prev->vm_end;
                if (nstart >= end)
                        break;

                vma = prev->vm_next;
                if (!vma || vma->vm_start != nstart) {
                        error = -ENOMEM;
                        break;
                }
        }
        return error;
}

/*
 * __mm_populate - populate and/or mlock pages within a range of address space.
 *
 * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
 * flags. VMAs must be already marked with the desired vm_flags, and
 * mmap_sem must not be held.
 */
int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
{
        struct mm_struct *mm = current->mm;
        unsigned long end, nstart, nend;
        struct vm_area_struct *vma = NULL;
        int locked = 0;
        long ret = 0;

        VM_BUG_ON(start & ~PAGE_MASK);
        VM_BUG_ON(len != PAGE_ALIGN(len));
        end = start + len;

        for (nstart = start; nstart < end; nstart = nend) {
                /*
                 * We want to fault in pages for [nstart; end) address range.
                 * Find first corresponding VMA.
                 */
                if (!locked) {
                        locked = 1;
                        down_read(&mm->mmap_sem);
                        vma = find_vma(mm, nstart);
                } else if (nstart >= vma->vm_end)
                        vma = vma->vm_next;
                if (!vma || vma->vm_start >= end)
                        break;
                /*
                 * Set [nstart; nend) to intersection of desired address
                 * range with the first VMA. Also, skip undesirable VMA types.
                 */
                nend = min(end, vma->vm_end);
                if (vma->vm_flags & (VM_IO | VM_PFNMAP))
                        continue;
                if (nstart < vma->vm_start)
                        nstart = vma->vm_start;
                /*
                 * Now fault in a range of pages. __mlock_vma_pages_range()
                 * double checks the vma flags, so that it won't mlock pages
                 * if the vma was already munlocked.
                 */
                ret = __mlock_vma_pages_range(vma, nstart, nend, &locked);
                if (ret < 0) {
                        if (ignore_errors) {
                                ret = 0;
                                continue;       /* continue at next VMA */
                        }
                        ret = __mlock_posix_error_return(ret);
                        break;
                }
                nend = nstart + ret * PAGE_SIZE;
                ret = 0;
        }
        if (locked)
                up_read(&mm->mmap_sem);
        return ret;     /* 0 or negative error code */
}

SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
{
        unsigned long locked;
        unsigned long lock_limit;
        int error = -ENOMEM;

        if (!can_do_mlock())
                return -EPERM;

        lru_add_drain_all();    /* flush pagevec */

        down_write(&current->mm->mmap_sem);
        len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
        start &= PAGE_MASK;

        locked = len >> PAGE_SHIFT;
        locked += current->mm->locked_vm;

        lock_limit = rlimit(RLIMIT_MEMLOCK);
        lock_limit >>= PAGE_SHIFT;

        /* check against resource limits */
        if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
                error = do_mlock(start, len, 1);
        up_write(&current->mm->mmap_sem);
        if (!error)
                error = __mm_populate(start, len, 0);
        return error;
}

SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
        int ret;

        down_write(&current->mm->mmap_sem);
        len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
        start &= PAGE_MASK;
        ret = do_mlock(start, len, 0);
        up_write(&current->mm->mmap_sem);
        return ret;
}

static int do_mlockall(int flags)
{
        struct vm_area_struct * vma, * prev = NULL;

        if (flags & MCL_FUTURE)
                current->mm->def_flags |= VM_LOCKED;
        else
                current->mm->def_flags &= ~VM_LOCKED;
        if (flags == MCL_FUTURE)
                goto out;

        for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
                vm_flags_t newflags;

                newflags = vma->vm_flags & ~VM_LOCKED;
                if (flags & MCL_CURRENT)
                        newflags |= VM_LOCKED;

                /* Ignore errors */
                mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
        }
out:
        return 0;
}

SYSCALL_DEFINE1(mlockall, int, flags)
{
        unsigned long lock_limit;
        int ret = -EINVAL;

        if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
                goto out;

        ret = -EPERM;
        if (!can_do_mlock())
                goto out;

        if (flags & MCL_CURRENT)
                lru_add_drain_all();    /* flush pagevec */

        down_write(&current->mm->mmap_sem);

        lock_limit = rlimit(RLIMIT_MEMLOCK);
        lock_limit >>= PAGE_SHIFT;

        ret = -ENOMEM;
        if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
            capable(CAP_IPC_LOCK))
                ret = do_mlockall(flags);
        up_write(&current->mm->mmap_sem);
        if (!ret && (flags & MCL_CURRENT))
                mm_populate(0, TASK_SIZE);
out:
        return ret;
}

SYSCALL_DEFINE0(munlockall)
{
        int ret;

        down_write(&current->mm->mmap_sem);
        ret = do_mlockall(0);
        up_write(&current->mm->mmap_sem);
        return ret;
}

/*
 * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB
 * shm segments) get accounted against the user_struct instead.
 */
static DEFINE_SPINLOCK(shmlock_user_lock);

int user_shm_lock(size_t size, struct user_struct *user)
{
        unsigned long lock_limit, locked;
        int allowed = 0;

        locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
        lock_limit = rlimit(RLIMIT_MEMLOCK);
        if (lock_limit == RLIM_INFINITY)
                allowed = 1;
        lock_limit >>= PAGE_SHIFT;
        spin_lock(&shmlock_user_lock);
        if (!allowed &&
            locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
                goto out;
        get_uid(user);
        user->locked_shm += locked;
        allowed = 1;
out:
        spin_unlock(&shmlock_user_lock);
        return allowed;
}

void user_shm_unlock(size_t size, struct user_struct *user)
{
        spin_lock(&shmlock_user_lock);
        user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
        spin_unlock(&shmlock_user_lock);
        free_uid(user);
}