* 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)
+ unsigned long start, unsigned long end,
+ int *nonblocking)
{
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 > vma->vm_end);
VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
- gup_flags = FOLL_TOUCH | FOLL_GET;
+ gup_flags = FOLL_TOUCH;
/*
* We want to touch writable mappings with a write fault in order
* to break COW, except for shared mappings because these don't COW
if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
gup_flags |= FOLL_WRITE;
+ if (vma->vm_flags & VM_LOCKED)
+ gup_flags |= FOLL_MLOCK;
+
/* We don't try to access the guard page of a stack vma */
if (stack_guard_page(vma, start)) {
addr += PAGE_SIZE;
nr_pages--;
}
- 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 */
+ return __get_user_pages(current, mm, addr, nr_pages, gup_flags,
+ NULL, NULL, nonblocking);
}
/*
is_vm_hugetlb_page(vma) ||
vma == get_gate_vma(current))) {
- __mlock_vma_pages_range(vma, start, end);
+ __mlock_vma_pages_range(vma, start, end, NULL);
/* Hide errors from mmap() and other callers */
return 0;
struct mm_struct *mm = current->mm;
unsigned long end, nstart, nend;
struct vm_area_struct *vma = NULL;
+ int locked = 0;
int ret = 0;
VM_BUG_ON(start & ~PAGE_MASK);
VM_BUG_ON(len != PAGE_ALIGN(len));
end = start + len;
- down_read(&mm->mmap_sem);
for (nstart = start; nstart < end; nstart = nend) {
/*
* We want to fault in pages for [nstart; end) address range.
* Find first corresponding VMA.
*/
- if (!vma)
+ if (!locked) {
+ locked = 1;
+ down_read(&mm->mmap_sem);
vma = find_vma(mm, nstart);
- else
+ } else if (nstart >= vma->vm_end)
vma = vma->vm_next;
if (!vma || vma->vm_start >= end)
break;
if (nstart < vma->vm_start)
nstart = vma->vm_start;
/*
- * Now fault in a range of pages within the first VMA.
+ * 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.
*/
- if (vma->vm_flags & VM_LOCKED) {
- ret = __mlock_vma_pages_range(vma, nstart, nend);
- if (ret < 0 && ignore_errors) {
+ ret = __mlock_vma_pages_range(vma, nstart, nend, &locked);
+ if (ret < 0) {
+ if (ignore_errors) {
ret = 0;
continue; /* continue at next VMA */
}
- if (ret) {
- ret = __mlock_posix_error_return(ret);
- break;
- }
- } else
- make_pages_present(nstart, nend);
+ ret = __mlock_posix_error_return(ret);
+ break;
+ }
+ nend = nstart + ret * PAGE_SIZE;
+ ret = 0;
}
- up_read(&mm->mmap_sem);
+ if (locked)
+ up_read(&mm->mmap_sem);
return ret; /* 0 or negative error code */
}