summaryrefslogtreecommitdiff
path: root/fs/aio.c
diff options
context:
space:
mode:
authorBenjamin LaHaise <bcrl@kvack.org>2013-09-09 11:57:59 -0400
committerBenjamin LaHaise <bcrl@kvack.org>2013-09-09 11:57:59 -0400
commitd6c355c7dabcd753a75bc77d150d36328a355267 (patch)
tree97b30abf03e5758fca4eef8572de38b77af54ae8 /fs/aio.c
parent77d30b14d24e557f89c41980011d72428514d729 (diff)
aio: fix race in ring buffer page lookup introduced by page migration support
Prior to the introduction of page migration support in "fs/aio: Add support to aio ring pages migration" / 36bc08cc01709b4a9bb563b35aa530241ddc63e3, mapping of the ring buffer pages was done via get_user_pages() while retaining mmap_sem held for write. This avoided possible races with userland racing an munmap() or mremap(). The page migration patch, however, switched to using mm_populate() to prime the page mapping. mm_populate() cannot be called with mmap_sem held. Instead of dropping the mmap_sem, revert to the old behaviour and simply drop the use of mm_populate() since get_user_pages() will cause the pages to get mapped anyways. Thanks to Al Viro for spotting this issue. Signed-off-by: Benjamin LaHaise <bcrl@kvack.org>
Diffstat (limited to 'fs/aio.c')
-rw-r--r--fs/aio.c15
1 files changed, 12 insertions, 3 deletions
diff --git a/fs/aio.c b/fs/aio.c
index 6e267553604c..f4a27af6c9ac 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -307,16 +307,25 @@ static int aio_setup_ring(struct kioctx *ctx)
aio_free_ring(ctx);
return -EAGAIN;
}
- up_write(&mm->mmap_sem);
-
- mm_populate(ctx->mmap_base, populate);
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;