mm: move VM_LOCKED check to __mlock_vma_pages_range()

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

diff --git a/mm/memory.c b/mm/memory.c
index d0cc1c134a6477384c54d04223cd338875400b2f..15e1f19a3b1003a5aa5e0b618766cfe648b3b81d 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1310,6 +1310,28 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
                 */
                mark_page_accessed(page);
        }
+       if (flags & FOLL_MLOCK) {
+               /*
+                * 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, we need
+                        * only check for file-cache page truncation.
+                        */
+                       if (page->mapping)
+                               mlock_vma_page(page);
+                       unlock_page(page);
+               }
+       }
 unlock:
        pte_unmap_unlock(ptep, ptl);
 out:
@@ -2229,8 +2251,45 @@ reuse:
                entry = maybe_mkwrite(pte_mkdirty(entry), vma);
                if (ptep_set_access_flags(vma, address, page_table, entry,1))
                        update_mmu_cache(vma, address, page_table);
+               pte_unmap_unlock(page_table, ptl);
                ret |= VM_FAULT_WRITE;
-               goto unlock;
+
+               if (!dirty_page)
+                       return ret;
+
+               /*
+                * Yes, Virginia, this is actually required to prevent a race
+                * with clear_page_dirty_for_io() from clearing the page dirty
+                * bit after it clear all dirty ptes, but before a racing
+                * do_wp_page installs a dirty pte.
+                *
+                * do_no_page is protected similarly.
+                */
+               if (!page_mkwrite) {
+                       wait_on_page_locked(dirty_page);
+                       set_page_dirty_balance(dirty_page, page_mkwrite);
+               }
+               put_page(dirty_page);
+               if (page_mkwrite) {
+                       struct address_space *mapping = dirty_page->mapping;
+
+                       set_page_dirty(dirty_page);
+                       unlock_page(dirty_page);
+                       page_cache_release(dirty_page);
+                       if (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)
+                       file_update_time(vma->vm_file);
+
+               return ret;
        }
 
        /*
@@ -2336,39 +2395,6 @@ gotten:
                page_cache_release(old_page);
 unlock:
        pte_unmap_unlock(page_table, ptl);
-       if (dirty_page) {
-               /*
-                * Yes, Virginia, this is actually required to prevent a race
-                * with clear_page_dirty_for_io() from clearing the page dirty
-                * bit after it clear all dirty ptes, but before a racing
-                * do_wp_page installs a dirty pte.
-                *
-                * do_no_page is protected similarly.
-                */
-               if (!page_mkwrite) {
-                       wait_on_page_locked(dirty_page);
-                       set_page_dirty_balance(dirty_page, page_mkwrite);
-               }
-               put_page(dirty_page);
-               if (page_mkwrite) {
-                       struct address_space *mapping = dirty_page->mapping;
-
-                       set_page_dirty(dirty_page);
-                       unlock_page(dirty_page);
-                       page_cache_release(dirty_page);
-                       if (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)
-                       file_update_time(vma->vm_file);
-       }
        return ret;
 oom_free_new:
        page_cache_release(new_page);
@@ -3295,7 +3321,12 @@ int make_pages_present(unsigned long addr, unsigned long end)
        vma = find_vma(current->mm, addr);
        if (!vma)
                return -ENOMEM;
-       write = (vma->vm_flags & VM_WRITE) != 0;
+       /*
+        * 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.
+        */
+       write = (vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE;
        BUG_ON(addr >= end);
        BUG_ON(end > vma->vm_end);
        len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;