mm/z3fold.c: use kref to prevent page free/compact race

There is a race in the current z3fold implementation between
do_compact() called in a work queue context and the page release
procedure when page's kref goes to 0.

do_compact() may be waiting for page lock, which is released by
release_z3fold_page_locked right before putting the page onto the
"stale" list, and then the page may be freed as do_compact() modifies
its contents.

The mechanism currently implemented to handle that (checking the
PAGE_STALE flag) is not reliable enough.  Instead, we'll use page's kref
counter to guarantee that the page is not released if its compaction is
scheduled.  It then becomes compaction function's responsibility to
decrease the counter and quit immediately if the page was actually
freed.

Link: http://lkml.kernel.org/r/20171117092032.00ea56f42affbed19f4fcc6c@gmail.com
Signed-off-by: Vitaly Wool <vitaly.wool@sonymobile.com>
Cc: <Oleksiy.Avramchenko@sony.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/z3fold.c b/mm/z3fold.c
index b2ba2ba585f3c0ccb422531ae9dc26909ae463d4..39e19125d6a019439e5795cbf9be5d54ad2d3349 100644 (file)
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -404,8 +404,7 @@ static void do_compact_page(struct z3fold_header *zhdr, bool locked)
                WARN_ON(z3fold_page_trylock(zhdr));
        else
                z3fold_page_lock(zhdr);
-       if (test_bit(PAGE_STALE, &page->private) ||
-           !test_and_clear_bit(NEEDS_COMPACTING, &page->private)) {
+       if (WARN_ON(!test_and_clear_bit(NEEDS_COMPACTING, &page->private))) {
                z3fold_page_unlock(zhdr);
                return;
        }
@@ -413,6 +412,11 @@ static void do_compact_page(struct z3fold_header *zhdr, bool locked)
        list_del_init(&zhdr->buddy);
        spin_unlock(&pool->lock);
 
+       if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) {
+               atomic64_dec(&pool->pages_nr);
+               return;
+       }
+
        z3fold_compact_page(zhdr);
        unbuddied = get_cpu_ptr(pool->unbuddied);
        fchunks = num_free_chunks(zhdr);
@@ -753,9 +757,11 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
                list_del_init(&zhdr->buddy);
                spin_unlock(&pool->lock);
                zhdr->cpu = -1;
+               kref_get(&zhdr->refcount);
                do_compact_page(zhdr, true);
                return;
        }
+       kref_get(&zhdr->refcount);
        queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work);
        z3fold_page_unlock(zhdr);
 }