1 files changed, 47 insertions, 8 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 7c7addb9333c..cb26e33fd0ff 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -75,8 +75,8 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
  *  ->mmap_sem
  *    ->lock_page               (access_process_vm)
  *
- *  ->mmap_sem
- *    ->i_mutex                 (msync)
+ *  ->i_mutex                   (generic_file_buffered_write)
+ *    ->mmap_sem                (fault_in_pages_readable->do_page_fault)
  *
  *  ->i_mutex
  *    ->i_alloc_sem             (various)
@@ -2236,7 +2236,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
                                 unsigned long nr_segs, loff_t *ppos)
 {
         struct file *file = iocb->ki_filp;
-        const struct address_space * mapping = file->f_mapping;
+        struct address_space * mapping = file->f_mapping;
         size_t ocount;          /* original count */
         size_t count;           /* after file limit checks */
         struct inode    *inode = mapping->host;
@@ -2289,8 +2289,11 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 
         /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
         if (unlikely(file->f_flags & O_DIRECT)) {
-                written = generic_file_direct_write(iocb, iov,
-                                &nr_segs, pos, ppos, count, ocount);
+                loff_t endbyte;
+                ssize_t written_buffered;
+
+                written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
+                                                        ppos, count, ocount);
                 if (written < 0 || written == count)
                         goto out;
                 /*
@@ -2299,10 +2302,46 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
                  */
                 pos += written;
                 count -= written;
-        }
+                written_buffered = generic_file_buffered_write(iocb, iov,
+                                                nr_segs, pos, ppos, count,
+                                                written);
+                /*
+                 * If generic_file_buffered_write() retuned a synchronous error
+                 * then we want to return the number of bytes which were
+                 * direct-written, or the error code if that was zero.  Note
+                 * that this differs from normal direct-io semantics, which
+                 * will return -EFOO even if some bytes were written.
+                 */
+                if (written_buffered < 0) {
+                        err = written_buffered;
+                        goto out;
+                }
 
-        written = generic_file_buffered_write(iocb, iov, nr_segs,
-                        pos, ppos, count, written);
+                /*
+                 * We need to ensure that the page cache pages are written to
+                 * disk and invalidated to preserve the expected O_DIRECT
+                 * semantics.
+                 */
+                endbyte = pos + written_buffered - written - 1;
+                err = do_sync_file_range(file, pos, endbyte,
+                                         SYNC_FILE_RANGE_WAIT_BEFORE|
+                                         SYNC_FILE_RANGE_WRITE|
+                                         SYNC_FILE_RANGE_WAIT_AFTER);
+                if (err == 0) {
+                        written = written_buffered;
+                        invalidate_mapping_pages(mapping,
+                                                 pos >> PAGE_CACHE_SHIFT,
+                                                 endbyte >> PAGE_CACHE_SHIFT);
+                } else {
+                        /*
+                         * We don't know how much we wrote, so just return
+                         * the number of bytes which were direct-written
+                         */
+                }
+        } else {
+                written = generic_file_buffered_write(iocb, iov, nr_segs,
+                                pos, ppos, count, written);
+        }
 out:
         current->backing_dev_info = NULL;
         return written ? written : err;