#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/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/module.h>
+#include <linux/rmap.h>
+#include <linux/mmzone.h>
+#include <linux/hugetlb.h>
+
+#include "internal.h"
int can_do_mlock(void)
{
}
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)
+{
+ VM_BUG_ON(!PageLocked(page));
+
+ if (!page->mapping) { /* truncated ? */
+ return;
+ }
+
+ dec_zone_page_state(page, NR_MLOCK);
+ 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)) {
+ inc_zone_page_state(page, NR_MLOCK);
+ count_vm_event(UNEVICTABLE_PGMLOCKED);
+ if (!isolate_lru_page(page))
+ putback_lru_page(page);
+ }
+}
+
+/*
+ * called from munlock()/munmap() path with page supposedly on the LRU.
+ *
+ * Note: unlike mlock_vma_page(), we can't just clear the PageMlocked
+ * [in try_to_munlock()] and then attempt to isolate the page. We must
+ * isolate the page to keep others from messing with its unevictable
+ * and mlocked state while trying to munlock. However, we pre-clear the
+ * mlocked state anyway as we might lose the isolation race and we might
+ * not get another chance to clear PageMlocked. If we successfully
+ * isolate the page and try_to_munlock() detects other VM_LOCKED vmas
+ * mapping the page, it will restore the PageMlocked state, unless the page
+ * is mapped in a non-linear vma. So, we go ahead and SetPageMlocked(),
+ * perhaps redundantly.
+ * If we lose the isolation race, and the page is mapped by other VM_LOCKED
+ * vmas, we'll detect this in vmscan--via try_to_munlock() or try_to_unmap()
+ * either of which will restore the PageMlocked state by calling
+ * mlock_vma_page() above, if it can grab the vma's mmap sem.
+ */
+static void munlock_vma_page(struct page *page)
+{
+ BUG_ON(!PageLocked(page));
+
+ if (TestClearPageMlocked(page)) {
+ dec_zone_page_state(page, NR_MLOCK);
+ if (!isolate_lru_page(page)) {
+ int ret = try_to_munlock(page);
+ /*
+ * did try_to_unlock() succeed or punt?
+ */
+ if (ret == SWAP_SUCCESS || ret == SWAP_AGAIN)
+ count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+
+ putback_lru_page(page);
+ } else {
+ /*
+ * We lost the race. let try_to_unmap() deal
+ * with it. At least we get the page state and
+ * mlock stats right. However, page is still on
+ * the noreclaim list. We'll fix that up when
+ * the page is eventually freed or we scan the
+ * noreclaim list.
+ */
+ if (PageUnevictable(page))
+ count_vm_event(UNEVICTABLE_PGSTRANDED);
+ else
+ count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+ }
+ }
+}
+
+/**
+ * __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.
+ */
+static long __mlock_vma_pages_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long addr = start;
+ struct page *pages[16]; /* 16 gives a reasonable batch */
+ int nr_pages = (end - start) / PAGE_SIZE;
+ int ret = 0;
+ 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_GET;
+ if (vma->vm_flags & VM_WRITE)
+ gup_flags |= FOLL_WRITE;
+
+ while (nr_pages > 0) {
+ int i;
+
+ cond_resched();
+
+ /*
+ * get_user_pages makes pages present if we are
+ * setting mlock. and this extra reference count will
+ * disable migration of this page. However, page may
+ * still be truncated out from under us.
+ */
+ ret = __get_user_pages(current, mm, addr,
+ min_t(int, nr_pages, ARRAY_SIZE(pages)),
+ gup_flags, pages, NULL);
+ /*
+ * This can happen for, e.g., VM_NONLINEAR regions before
+ * a page has been allocated and mapped at a given offset,
+ * or for addresses that map beyond end of a file.
+ * We'll mlock the pages if/when they get faulted in.
+ */
+ if (ret < 0)
+ break;
+
+ lru_add_drain(); /* push cached pages to LRU */
+
+ for (i = 0; i < ret; i++) {
+ struct page *page = pages[i];
+
+ if (page->mapping) {
+ /*
+ * That preliminary check is mainly to avoid
+ * the pointless overhead of lock_page on the
+ * ZERO_PAGE: which might bounce very badly if
+ * there is contention. However, we're still
+ * dirtying its cacheline with get/put_page:
+ * we'll add another __get_user_pages flag to
+ * avoid it if that case turns out to matter.
+ */
+ lock_page(page);
+ /*
+ * Because we lock page here and migration is
+ * blocked by the elevated reference, we need
+ * only check for file-cache page truncation.
+ */
+ if (page->mapping)
+ mlock_vma_page(page);
+ unlock_page(page);
+ }
+ put_page(page); /* ref from get_user_pages() */
+ }
+
+ addr += ret * PAGE_SIZE;
+ nr_pages -= ret;
+ ret = 0;
+ }
+
+ return ret; /* 0 or negative error code */
+}
+
+/*
+ * 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;
+}
+
+/**
+ * mlock_vma_pages_range() - mlock pages in specified vma range.
+ * @vma - the vma containing the specfied address range
+ * @start - starting address in @vma to mlock
+ * @end - end address [+1] in @vma to mlock
+ *
+ * For mmap()/mremap()/expansion of mlocked vma.
+ *
+ * return 0 on success for "normal" vmas.
+ *
+ * return number of pages [> 0] to be removed from locked_vm on success
+ * of "special" vmas.
+ */
+long mlock_vma_pages_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ int nr_pages = (end - start) / PAGE_SIZE;
+ BUG_ON(!(vma->vm_flags & VM_LOCKED));
+
+ /*
+ * filter unlockable vmas
+ */
+ if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+ goto no_mlock;
+
+ if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
+ is_vm_hugetlb_page(vma) ||
+ vma == get_gate_vma(current))) {
+
+ __mlock_vma_pages_range(vma, start, end);
+
+ /* Hide errors from mmap() and other callers */
+ return 0;
+ }
+
+ /*
+ * User mapped kernel pages or huge pages:
+ * make these pages present to populate the ptes, but
+ * fall thru' to reset VM_LOCKED--no need to unlock, and
+ * return nr_pages so these don't get counted against task's
+ * locked limit. huge pages are already counted against
+ * locked vm limit.
+ */
+ make_pages_present(start, end);
+
+no_mlock:
+ vma->vm_flags &= ~VM_LOCKED; /* and don't come back! */
+ return nr_pages; /* error or pages NOT mlocked */
+}
+
+/*
+ * 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)
+{
+ unsigned long addr;
+
+ lru_add_drain();
+ vma->vm_flags &= ~VM_LOCKED;
+
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
+ struct page *page;
+ /*
+ * 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(vma, addr, FOLL_GET | FOLL_DUMP);
+ if (page && !IS_ERR(page)) {
+ lock_page(page);
+ /*
+ * Like in __mlock_vma_pages_range(),
+ * because we lock page here and migration is
+ * blocked by the elevated reference, we need
+ * only check for file-cache page truncation.
+ */
+ if (page->mapping)
+ munlock_vma_page(page);
+ unlock_page(page);
+ put_page(page);
+ }
+ cond_resched();
+ }
+}
+
+/*
+ * 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 via make_pages_present().
+ *
+ * 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, unsigned int newflags)
{
- struct mm_struct * mm = vma->vm_mm;
+ struct mm_struct *mm = vma->vm_mm;
pgoff_t pgoff;
- int pages;
+ int nr_pages;
int ret = 0;
-
- if (newflags == vma->vm_flags) {
- *prev = vma;
- goto out;
+ int lock = newflags & VM_LOCKED;
+
+ if (newflags == vma->vm_flags ||
+ (vma->vm_flags & (VM_IO | VM_PFNMAP)))
+ goto out; /* don't set VM_LOCKED, don't count */
+
+ if ((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
+ is_vm_hugetlb_page(vma) ||
+ vma == get_gate_vma(current)) {
+ if (lock)
+ make_pages_present(start, end);
+ goto out; /* don't set VM_LOCKED, don't count */
}
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
goto success;
}
- *prev = vma;
-
if (start != vma->vm_start) {
ret = split_vma(mm, vma, start, 1);
if (ret)
success:
/*
- * 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, make_pages_present below will bring it back.
+ * Keep track of amount of locked VM.
*/
- vma->vm_flags = newflags;
+ nr_pages = (end - start) >> PAGE_SHIFT;
+ if (!lock)
+ nr_pages = -nr_pages;
+ mm->locked_vm += nr_pages;
/*
- * Keep track of amount of locked VM.
+ * 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.
*/
- pages = (end - start) >> PAGE_SHIFT;
- if (newflags & VM_LOCKED) {
- pages = -pages;
- if (!(newflags & VM_IO))
- ret = make_pages_present(start, end);
+
+ if (lock) {
+ vma->vm_flags = newflags;
+ ret = __mlock_vma_pages_range(vma, start, end);
+ if (ret < 0)
+ ret = __mlock_posix_error_return(ret);
+ } else {
+ munlock_vma_pages_range(vma, start, end);
}
- mm->locked_vm -= pages;
out:
- if (ret == -ENOMEM)
- ret = -EAGAIN;
+ *prev = vma;
return ret;
}
return error;
}
-asmlinkage long sys_mlock(unsigned long start, size_t len)
+SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
{
unsigned long locked;
unsigned long lock_limit;
if (!can_do_mlock())
return -EPERM;
+ lru_add_drain_all(); /* flush pagevec */
+
down_write(¤t->mm->mmap_sem);
len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
start &= PAGE_MASK;
return error;
}
-asmlinkage long sys_munlock(unsigned long start, size_t len)
+SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
int ret;
return 0;
}
-asmlinkage long sys_mlockall(int flags)
+SYSCALL_DEFINE1(mlockall, int, flags)
{
unsigned long lock_limit;
int ret = -EINVAL;
if (!can_do_mlock())
goto out;
+ lru_add_drain_all(); /* flush pagevec */
+
down_write(¤t->mm->mmap_sem);
lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
return ret;
}
-asmlinkage long sys_munlockall(void)
+SYSCALL_DEFINE0(munlockall)
{
int ret;
locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+ if (lock_limit == RLIM_INFINITY)
+ allowed = 1;
lock_limit >>= PAGE_SHIFT;
spin_lock(&shmlock_user_lock);
- if (locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
+ if (!allowed &&
+ locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
goto out;
get_uid(user);
user->locked_shm += locked;
spin_unlock(&shmlock_user_lock);
free_uid(user);
}
+
+int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
+ size_t size)
+{
+ unsigned long lim, vm, pgsz;
+ int error = -ENOMEM;
+
+ pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ down_write(&mm->mmap_sem);
+
+ lim = rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+ vm = mm->total_vm + pgsz;
+ if (lim < vm)
+ goto out;
+
+ lim = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+ vm = mm->locked_vm + pgsz;
+ if (lim < vm)
+ goto out;
+
+ mm->total_vm += pgsz;
+ mm->locked_vm += pgsz;
+
+ error = 0;
+ out:
+ up_write(&mm->mmap_sem);
+ return error;
+}
+
+void refund_locked_memory(struct mm_struct *mm, size_t size)
+{
+ unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ down_write(&mm->mmap_sem);
+
+ mm->total_vm -= pgsz;
+ mm->locked_vm -= pgsz;
+
+ up_write(&mm->mmap_sem);
+}