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>

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 2148b122779b5a2fd8421c5e15cfc9ca91ea85ff..1afb9954bbf125fc3da62e2d9ef631b6508b5b89 100644 (file)
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -120,6 +120,7 @@ void anon_vma_init(void);   /* create anon_vma_cachep */
 int  anon_vma_prepare(struct vm_area_struct *);
 void unlink_anon_vmas(struct vm_area_struct *);
 int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
+void anon_vma_moveto_tail(struct vm_area_struct *);
 int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
 void __anon_vma_link(struct vm_area_struct *);
 

diff --git a/mm/mmap.c b/mm/mmap.c
index eae90af60ea62e066defeab345e5079f57a80dc2..adea3b8880e3ff025f0b7b880d0a6bf4e326903a 100644 (file)
--- 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) {

diff --git a/mm/mremap.c b/mm/mremap.c
index d6959cb4df58f1d694c179898553bf7e3150cc49..87bb8393e7d238115a450139d24c090347c215a7 100644 (file)
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -220,6 +220,15 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 
        moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len);
        if (moved_len < old_len) {
+               /*
+                * Before moving the page tables from the new vma to
+                * the old vma, we need to be sure the old vma is
+                * queued after new vma in the same_anon_vma list to
+                * prevent SMP races with rmap_walk (that could lead
+                * rmap_walk to miss some page table).
+                */
+               anon_vma_moveto_tail(vma);
+
                /*
                 * On error, move entries back from new area to old,
                 * which will succeed since page tables still there,

diff --git a/mm/rmap.c b/mm/rmap.c
index a4fd3680038be499a47cf747d1ba657646e5d36c..a2e5ce1fa08142f60a0abba7ea6512fe6713555c 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -271,6 +271,51 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
        return -ENOMEM;
 }
 
+/*
+ * Some rmap walk that needs to find all ptes/hugepmds without false
+ * negatives (like migrate and split_huge_page) running concurrent
+ * with operations that copy or move pagetables (like mremap() and
+ * fork()) to be safe. They depend on the anon_vma "same_anon_vma"
+ * list to be in a certain order: the dst_vma must be placed after the
+ * src_vma in the list. This is always guaranteed by fork() but
+ * mremap() needs to call this function to enforce it in case the
+ * dst_vma isn't newly allocated and chained with the anon_vma_clone()
+ * function but just an extension of a pre-existing vma through
+ * vma_merge.
+ *
+ * NOTE: the same_anon_vma list can still be changed by other
+ * processes while mremap runs because mremap doesn't hold the
+ * anon_vma mutex to prevent modifications to the list while it
+ * runs. All we need to enforce is that the relative order of this
+ * process vmas isn't changing (we don't care about other vmas
+ * order). Each vma corresponds to an anon_vma_chain structure so
+ * there's no risk that other processes calling anon_vma_moveto_tail()
+ * and changing the same_anon_vma list under mremap() will screw with
+ * the relative order of this process vmas in the list, because we
+ * they can't alter the order of any vma that belongs to this
+ * process. And there can't be another anon_vma_moveto_tail() running
+ * concurrently with mremap() coming from this process because we hold
+ * the mmap_sem for the whole mremap(). fork() ordering dependency
+ * also shouldn't be affected because fork() only cares that the
+ * parent vmas are placed in the list before the child vmas and
+ * anon_vma_moveto_tail() won't reorder vmas from either the fork()
+ * parent or child.
+ */
+void anon_vma_moveto_tail(struct vm_area_struct *dst)
+{
+       struct anon_vma_chain *pavc;
+       struct anon_vma *root = NULL;
+
+       list_for_each_entry_reverse(pavc, &dst->anon_vma_chain, same_vma) {
+               struct anon_vma *anon_vma = pavc->anon_vma;
+               VM_BUG_ON(pavc->vma != dst);
+               root = lock_anon_vma_root(root, anon_vma);
+               list_del(&pavc->same_anon_vma);
+               list_add_tail(&pavc->same_anon_vma, &anon_vma->head);
+       }
+       unlock_anon_vma_root(root);
+}
+
 /*
  * Attach vma to its own anon_vma, as well as to the anon_vmas that
  * the corresponding VMA in the parent process is attached to.