Merge git://git.kvack.org/~bcrl/aio-next

Pull AIO leak fixes from Ben LaHaise:
 "I've put these two patches plus Linus's change through a round of
  tests, and it passes millions of iterations of the aio numa
  migratepage test, as well as a number of repetitions of a few simple
  read and write tests.

  The first patch fixes the memory leak Kent introduced, while the
  second patch makes aio_migratepage() much more paranoid and robust"

* git://git.kvack.org/~bcrl/aio-next:
  aio/migratepages: make aio migrate pages sane
  aio: fix kioctx leak introduced by "aio: Fix a trinity splat"

diff --git a/fs/aio.c b/fs/aio.c
index efa708b..062a5f6 100644 (file)
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -362,7 +362,7 @@ static int aio_setup_ring(struct kioctx *ctx)
        struct aio_ring *ring;
        unsigned nr_events = ctx->max_reqs;
        struct mm_struct *mm = current->mm;
-       unsigned long size, populate;
+       unsigned long size, unused;
        int nr_pages;
        int i;
        struct file *file;
@@ -383,6 +383,20 @@ static int aio_setup_ring(struct kioctx *ctx)
                return -EAGAIN;
        }
 
+       ctx->aio_ring_file = file;
+       nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
+                       / sizeof(struct io_event);
+
+       ctx->ring_pages = ctx->internal_pages;
+       if (nr_pages > AIO_RING_PAGES) {
+               ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
+                                         GFP_KERNEL);
+               if (!ctx->ring_pages) {
+                       put_aio_ring_file(ctx);
+                       return -ENOMEM;
+               }
+       }
+
        for (i = 0; i < nr_pages; i++) {
                struct page *page;
                page = find_or_create_page(file->f_inode->i_mapping,
@@ -394,19 +408,14 @@ static int aio_setup_ring(struct kioctx *ctx)
                SetPageUptodate(page);
                SetPageDirty(page);
                unlock_page(page);
+
+               ctx->ring_pages[i] = page;
        }
-       ctx->aio_ring_file = file;
-       nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
-                       / sizeof(struct io_event);
+       ctx->nr_pages = i;
 
-       ctx->ring_pages = ctx->internal_pages;
-       if (nr_pages > AIO_RING_PAGES) {
-               ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
-                                         GFP_KERNEL);
-               if (!ctx->ring_pages) {
-                       put_aio_ring_file(ctx);
-                       return -ENOMEM;
-               }
+       if (unlikely(i != nr_pages)) {
+               aio_free_ring(ctx);
+               return -EAGAIN;
        }
 
        ctx->mmap_size = nr_pages * PAGE_SIZE;
@@ -415,9 +424,9 @@ static int aio_setup_ring(struct kioctx *ctx)
        down_write(&mm->mmap_sem);
        ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
                                       PROT_READ | PROT_WRITE,
-                                      MAP_SHARED | MAP_POPULATE, 0, &populate);
+                                      MAP_SHARED, 0, &unused);
+       up_write(&mm->mmap_sem);
        if (IS_ERR((void *)ctx->mmap_base)) {
-               up_write(&mm->mmap_sem);
                ctx->mmap_size = 0;
                aio_free_ring(ctx);
                return -EAGAIN;
@@ -425,27 +434,6 @@ static int aio_setup_ring(struct kioctx *ctx)
 
        pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
 
-       /* We must do this while still holding mmap_sem for write, as we
-        * need to be protected against userspace attempting to mremap()
-        * or munmap() the ring buffer.
-        */
-       ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages,
-                                      1, 0, ctx->ring_pages, NULL);
-
-       /* Dropping the reference here is safe as the page cache will hold
-        * onto the pages for us.  It is also required so that page migration
-        * can unmap the pages and get the right reference count.
-        */
-       for (i = 0; i < ctx->nr_pages; i++)
-               put_page(ctx->ring_pages[i]);
-
-       up_write(&mm->mmap_sem);
-
-       if (unlikely(ctx->nr_pages != nr_pages)) {
-               aio_free_ring(ctx);
-               return -EAGAIN;
-       }
-
        ctx->user_id = ctx->mmap_base;
        ctx->nr_events = nr_events; /* trusted copy */