Fix possible splice() mmap_sem deadlock

Nick Piggin points out that splice isn't being good about the mmap
semaphore: while two readers can nest inside each others, it does leave
a possible deadlock if a writer (ie a new mmap()) comes in during that
nesting.

Original "just move the locking" patch by Nick, replaced by one by me
based on an optimistic pagefault_disable().  And then Jens tested and
updated that patch.

Reported-by: Nick Piggin <npiggin@suse.de>
Tested-by: Jens Axboe <jens.axboe@oracle.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/splice.c b/fs/splice.c
index c010a72..e95a362 100644 (file)
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1224,6 +1224,33 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 }
 
 /*
+ * Do a copy-from-user while holding the mmap_semaphore for reading, in a
+ * manner safe from deadlocking with simultaneous mmap() (grabbing mmap_sem
+ * for writing) and page faulting on the user memory pointed to by src.
+ * This assumes that we will very rarely hit the partial != 0 path, or this
+ * will not be a win.
+ */
+static int copy_from_user_mmap_sem(void *dst, const void __user *src, size_t n)
+{
+       int partial;
+
+       pagefault_disable();
+       partial = __copy_from_user_inatomic(dst, src, n);
+       pagefault_enable();
+
+       /*
+        * Didn't copy everything, drop the mmap_sem and do a faulting copy
+        */
+       if (unlikely(partial)) {
+               up_read(&current->mm->mmap_sem);
+               partial = copy_from_user(dst, src, n);
+               down_read(&current->mm->mmap_sem);
+       }
+
+       return partial;
+}
+
+/*
  * Map an iov into an array of pages and offset/length tupples. With the
  * partial_page structure, we can map several non-contiguous ranges into
  * our ones pages[] map instead of splitting that operation into pieces.
@@ -1236,31 +1263,26 @@ static int get_iovec_page_array(const struct iovec __user *iov,
 {
        int buffers = 0, error = 0;
 
-       /*
-        * It's ok to take the mmap_sem for reading, even
-        * across a "get_user()".
-        */
        down_read(&current->mm->mmap_sem);
 
        while (nr_vecs) {
                unsigned long off, npages;
+               struct iovec entry;
                void __user *base;
                size_t len;
                int i;
 
-               /*
-                * Get user address base and length for this iovec.
-                */
-               error = get_user(base, &iov->iov_base);
-               if (unlikely(error))
-                       break;
-               error = get_user(len, &iov->iov_len);
-               if (unlikely(error))
+               error = -EFAULT;
+               if (copy_from_user_mmap_sem(&entry, iov, sizeof(entry)))
                        break;
 
+               base = entry.iov_base;
+               len = entry.iov_len;
+
                /*
                 * Sanity check this iovec. 0 read succeeds.
                 */
+               error = 0;
                if (unlikely(!len))
                        break;
                error = -EFAULT;