mm anon rmap: replace same_anon_vma linked list with an interval tree.

When a large VMA (anon or private file mapping) is first touched, which
will populate its anon_vma field, and then split into many regions through
the use of mprotect(), the original anon_vma ends up linking all of the
vmas on a linked list.  This can cause rmap to become inefficient, as we
have to walk potentially thousands of irrelevent vmas before finding the
one a given anon page might fall into.

By replacing the same_anon_vma linked list with an interval tree (where
each avc's interval is determined by its vma's start and last pgoffs), we
can make rmap efficient for this use case again.

While the change is large, all of its pieces are fairly simple.

Most places that were walking the same_anon_vma list were looking for a
known pgoff, so they can just use the anon_vma_interval_tree_foreach()
interval tree iterator instead.  The exception here is ksm, where the
page's index is not known.  It would probably be possible to rework ksm so
that the index would be known, but for now I have decided to keep things
simple and just walk the entirety of the interval tree there.

When updating vma's that already have an anon_vma assigned, we must take
care to re-index the corresponding avc's on their interval tree.  This is
done through the use of anon_vma_interval_tree_pre_update_vma() and
anon_vma_interval_tree_post_update_vma(), which remove the avc's from
their interval tree before the update and re-insert them after the update.
 The anon_vma stays locked during the update, so there is no chance that
rmap would miss the vmas that are being updated.

Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 20 insertions, 5 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f1d9aaadb566..0cdab4e0f814 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -20,6 +20,7 @@
 
 struct mempolicy;
 struct anon_vma;
+struct anon_vma_chain;
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
@@ -1377,6 +1378,19 @@ static inline void vma_nonlinear_insert(struct vm_area_struct *vma,
         list_add_tail(&vma->shared.nonlinear, list);
 }
 
+void anon_vma_interval_tree_insert(struct anon_vma_chain *node,
+                                   struct rb_root *root);
+void anon_vma_interval_tree_remove(struct anon_vma_chain *node,
+                                   struct rb_root *root);
+struct anon_vma_chain *anon_vma_interval_tree_iter_first(
+        struct rb_root *root, unsigned long start, unsigned long last);
+struct anon_vma_chain *anon_vma_interval_tree_iter_next(
+        struct anon_vma_chain *node, unsigned long start, unsigned long last);
+
+#define anon_vma_interval_tree_foreach(avc, root, start, last)           \
+        for (avc = anon_vma_interval_tree_iter_first(root, start, last); \
+             avc; avc = anon_vma_interval_tree_iter_next(avc, start, last))
+
 /* mmap.c */
 extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin);
 extern int vma_adjust(struct vm_area_struct *vma, unsigned long start,
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 7f32cec57e67..dce44f7d3ed8 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -37,14 +37,14 @@ struct anon_vma {
         atomic_t refcount;
 
         /*
-         * NOTE: the LSB of the head.next is set by
+         * NOTE: the LSB of the rb_root.rb_node is set by
          * mm_take_all_locks() _after_ taking the above lock. So the
-         * head must only be read/written after taking the above lock
+         * rb_root must only be read/written after taking the above lock
          * to be sure to see a valid next pointer. The LSB bit itself
          * is serialized by a system wide lock only visible to
          * mm_take_all_locks() (mm_all_locks_mutex).
          */
-        struct list_head head;  /* Chain of private "related" vmas */
+        struct rb_root rb_root; /* Interval tree of private "related" vmas */
 };
 
 /*
@@ -57,14 +57,15 @@ struct anon_vma {
  * with a VMA, or the VMAs associated with an anon_vma.
  * The "same_vma" list contains the anon_vma_chains linking
  * all the anon_vmas associated with this VMA.
- * The "same_anon_vma" list contains the anon_vma_chains
+ * The "rb" field indexes on an interval tree the anon_vma_chains
  * which link all the VMAs associated with this anon_vma.
  */
 struct anon_vma_chain {
         struct vm_area_struct *vma;
         struct anon_vma *anon_vma;
         struct list_head same_vma;   /* locked by mmap_sem & page_table_lock */
-        struct list_head same_anon_vma; /* locked by anon_vma->mutex */
+        struct rb_node rb;                      /* locked by anon_vma->mutex */
+        unsigned long rb_subtree_last;
 };
 
 #ifdef CONFIG_MMU