mremap: enforce rmap src/dst vma ordering in case of vma_merge() succeeding in copy_vma()

migrate was doing an rmap_walk with speculative lock-less access on
pagetables.  That could lead it to not serializing properly against mremap
PT locks.  But a second problem remains in the order of vmas in the
same_anon_vma list used by the rmap_walk.

If vma_merge succeeds in copy_vma, the src vma could be placed after the
dst vma in the same_anon_vma list.  That could still lead to migrate
missing some pte.

This patch adds an anon_vma_moveto_tail() function to force the dst vma at
the end of the list before mremap starts to solve the problem.

If the mremap is very large and there are a lots of parents or childs
sharing the anon_vma root lock, this should still scale better than taking
the anon_vma root lock around every pte copy practically for the whole
duration of mremap.

Update: Hugh noticed special care is needed in the error path where
move_page_tables goes in the reverse direction, a second
anon_vma_moveto_tail() call is needed in the error path.

This program exercises the anon_vma_moveto_tail:

===

int main()
{
	static struct timeval oldstamp, newstamp;
	long diffsec;
	char *p, *p2, *p3, *p4;
	if (posix_memalign((void **)&p, 2*1024*1024, SIZE))
		perror("memalign"), exit(1);
	if (posix_memalign((void **)&p2, 2*1024*1024, SIZE))
		perror("memalign"), exit(1);
	if (posix_memalign((void **)&p3, 2*1024*1024, SIZE))
		perror("memalign"), exit(1);

	memset(p, 0xff, SIZE);
	printf("%p\n", p);
	memset(p2, 0xff, SIZE);
	memset(p3, 0x77, 4096);
	if (memcmp(p, p2, SIZE))
		printf("error\n");
	p4 = mremap(p+SIZE/2, SIZE/2, SIZE/2, MREMAP_FIXED|MREMAP_MAYMOVE, p3);
	if (p4 != p3)
		perror("mremap"), exit(1);
	p4 = mremap(p4, SIZE/2, SIZE/2, MREMAP_FIXED|MREMAP_MAYMOVE, p+SIZE/2);
	if (p4 != p+SIZE/2)
		perror("mremap"), exit(1);
	if (memcmp(p, p2, SIZE))
		printf("error\n");
	printf("ok\n");

	return 0;
}
===

$ perf probe -a anon_vma_moveto_tail
Add new event:
  probe:anon_vma_moveto_tail (on anon_vma_moveto_tail)

You can now use it on all perf tools, such as:

        perf record -e probe:anon_vma_moveto_tail -aR sleep 1

$ perf record -e probe:anon_vma_moveto_tail -aR ./anon_vma_moveto_tail
0x7f2ca2800000
ok
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.043 MB perf.data (~1860 samples) ]
$ perf report --stdio
   100.00%  anon_vma_moveto  [kernel.kallsyms]  [k] anon_vma_moveto_tail

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Nai Xia <nai.xia@gmail.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Pawel Sikora <pluto@agmk.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 21 insertions, 3 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index eae90af60ea6..adea3b8880e3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2322,13 +2322,16 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
         struct vm_area_struct *new_vma, *prev;
         struct rb_node **rb_link, *rb_parent;
         struct mempolicy *pol;
+        bool faulted_in_anon_vma = true;
 
         /*
          * If anonymous vma has not yet been faulted, update new pgoff
          * to match new location, to increase its chance of merging.
          */
-        if (!vma->vm_file && !vma->anon_vma)
+        if (unlikely(!vma->vm_file && !vma->anon_vma)) {
                 pgoff = addr >> PAGE_SHIFT;
+                faulted_in_anon_vma = false;
+        }
 
         find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
         new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
@@ -2337,9 +2340,24 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
                 /*
                  * Source vma may have been merged into new_vma
                  */
-                if (vma_start >= new_vma->vm_start &&
-                    vma_start < new_vma->vm_end)
+                if (unlikely(vma_start >= new_vma->vm_start &&
+                             vma_start < new_vma->vm_end)) {
+                        /*
+                         * The only way we can get a vma_merge with
+                         * self during an mremap is if the vma hasn't
+                         * been faulted in yet and we were allowed to
+                         * reset the dst vma->vm_pgoff to the
+                         * destination address of the mremap to allow
+                         * the merge to happen. mremap must change the
+                         * vm_pgoff linearity between src and dst vmas
+                         * (in turn preventing a vma_merge) to be
+                         * safe. It is only safe to keep the vm_pgoff
+                         * linear if there are no pages mapped yet.
+                         */
+                        VM_BUG_ON(faulted_in_anon_vma);
                         *vmap = new_vma;
+                } else
+                        anon_vma_moveto_tail(new_vma);
         } else {
                 new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
                 if (new_vma) {