mlock: mlocked pages are unevictable

Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.

This is achieved through various strategies:

1) add yet another page flag--PG_mlocked--to indicate that
   the page is locked for efficient testing in vmscan and,
   optionally, fault path.  This allows early culling of
   unevictable pages, preventing them from getting to
   page_referenced()/try_to_unmap().  Also allows separate
   accounting of mlock'd pages, as Nick's original patch
   did.

   Note:  Nick's original mlock patch used a PG_mlocked
   flag.  I had removed this in favor of the PG_unevictable
   flag + an mlock_count [new page struct member].  I
   restored the PG_mlocked flag to eliminate the new
   count field.

2) add the mlock/unevictable infrastructure to mm/mlock.c,
   with internal APIs in mm/internal.h.  This is a rework
   of Nick's original patch to these files, taking into
   account that mlocked pages are now kept on unevictable
   LRU list.

3) update vmscan.c:page_evictable() to check PageMlocked()
   and, if vma passed in, the vm_flags.  Note that the vma
   will only be passed in for new pages in the fault path;
   and then only if the "cull unevictable pages in fault
   path" patch is included.

4) add try_to_unlock() to rmap.c to walk a page's rmap and
   ClearPageMlocked() if no other vmas have it mlocked.
   Reuses as much of try_to_unmap() as possible.  This
   effectively replaces the use of one of the lru list links
   as an mlock count.  If this mechanism let's pages in mlocked
   vmas leak through w/o PG_mlocked set [I don't know that it
   does], we should catch them later in try_to_unmap().  One
   hopes this will be rare, as it will be relatively expensive.

Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>

splitlru: introduce __get_user_pages():

  New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
  because current get_user_pages() can't grab PROT_NONE pages theresore it
  cause PROT_NONE pages can't munlock.

[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 49 insertions, 7 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 71cdefd1ef1..9fef7272fb9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -64,6 +64,8 @@
 
 #include "internal.h"
 
+#include "internal.h"
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 /* use the per-pgdat data instead for discontigmem - mbligh */
 unsigned long max_mapnr;
@@ -1129,12 +1131,17 @@ static inline int use_zero_page(struct vm_area_struct *vma)
         return !vma->vm_ops || !vma->vm_ops->fault;
 }
 
-int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-                unsigned long start, int len, int write, int force,
+
+
+int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+                     unsigned long start, int len, int flags,
                 struct page **pages, struct vm_area_struct **vmas)
 {
         int i;
-        unsigned int vm_flags;
+        unsigned int vm_flags = 0;
+        int write = !!(flags & GUP_FLAGS_WRITE);
+        int force = !!(flags & GUP_FLAGS_FORCE);
+        int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
 
         if (len <= 0)
                 return 0;
@@ -1158,7 +1165,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                         pud_t *pud;
                         pmd_t *pmd;
                         pte_t *pte;
-                        if (write) /* user gate pages are read-only */
+
+                        /* user gate pages are read-only */
+                        if (!ignore && write)
                                 return i ? : -EFAULT;
                         if (pg > TASK_SIZE)
                                 pgd = pgd_offset_k(pg);
@@ -1190,8 +1199,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                         continue;
                 }
 
-                if (!vma || (vma->vm_flags & (VM_IO | VM_PFNMAP))
-                                || !(vm_flags & vma->vm_flags))
+                if (!vma ||
+                    (vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
+                    (!ignore && !(vm_flags & vma->vm_flags)))
                         return i ? : -EFAULT;
 
                 if (is_vm_hugetlb_page(vma)) {
@@ -1266,6 +1276,23 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
         } while (len);
         return i;
 }
+
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+                unsigned long start, int len, int write, int force,
+                struct page **pages, struct vm_area_struct **vmas)
+{
+        int flags = 0;
+
+        if (write)
+                flags |= GUP_FLAGS_WRITE;
+        if (force)
+                flags |= GUP_FLAGS_FORCE;
+
+        return __get_user_pages(tsk, mm,
+                                start, len, flags,
+                                pages, vmas);
+}
+
 EXPORT_SYMBOL(get_user_pages);
 
 pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
@@ -1858,6 +1885,15 @@ gotten:
         new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
         if (!new_page)
                 goto oom;
+        /*
+         * Don't let another task, with possibly unlocked vma,
+         * keep the mlocked page.
+         */
+        if (vma->vm_flags & VM_LOCKED) {
+                lock_page(old_page);    /* for LRU manipulation */
+                clear_page_mlock(old_page);
+                unlock_page(old_page);
+        }
         cow_user_page(new_page, old_page, address, vma);
         __SetPageUptodate(new_page);
 
@@ -2325,7 +2361,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
         page_add_anon_rmap(page, vma, address);
 
         swap_free(entry);
-        if (vm_swap_full())
+        if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
                 remove_exclusive_swap_page(page);
         unlock_page(page);
 
@@ -2465,6 +2501,12 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                                 ret = VM_FAULT_OOM;
                                 goto out;
                         }
+                        /*
+                         * Don't let another task, with possibly unlocked vma,
+                         * keep the mlocked page.
+                         */
+                        if (vma->vm_flags & VM_LOCKED)
+                                clear_page_mlock(vmf.page);
                         copy_user_highpage(page, vmf.page, address, vma);
                         __SetPageUptodate(page);
                 } else {