ext4: Allow parallel DIO reads

We can easily support parallel direct IO reads. We only have to make
sure we cannot expose uninitialized data by reading allocated block to
which data was not written yet, or which was already truncated. That is
easily achieved by holding inode_lock in shared mode - that excludes all
writes, truncates, hole punches. We also have to guard against page
writeback allocating blocks for delay-allocated pages - that race is
handled by the fact that we writeback all the pages in the affected
range and the lock protects us from new pages being created there.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 39883158b970eca08db7175cfa515368547780ac..d8a4afc5eedbcc6b4cc790ea1f011d469ea5d06a 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3528,35 +3528,31 @@ out:
 
 static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
 {
-       int unlocked = 0;
-       struct inode *inode = iocb->ki_filp->f_mapping->host;
+       struct address_space *mapping = iocb->ki_filp->f_mapping;
+       struct inode *inode = mapping->host;
        ssize_t ret;
 
-       if (ext4_should_dioread_nolock(inode)) {
-               /*
-                * Nolock dioread optimization may be dynamically disabled
-                * via ext4_inode_block_unlocked_dio(). Check inode's state
-                * while holding extra i_dio_count ref.
-                */
-               inode_dio_begin(inode);
-               smp_mb();
-               if (unlikely(ext4_test_inode_state(inode,
-                                                   EXT4_STATE_DIOREAD_LOCK)))
-                       inode_dio_end(inode);
-               else
-                       unlocked = 1;
-       }
+       /*
+        * Shared inode_lock is enough for us - it protects against concurrent
+        * writes & truncates and since we take care of writing back page cache,
+        * we are protected against page writeback as well.
+        */
+       inode_lock_shared(inode);
        if (IS_DAX(inode)) {
-               ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block,
-                               NULL, unlocked ? 0 : DIO_LOCKING);
+               ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block, NULL, 0);
        } else {
+               size_t count = iov_iter_count(iter);
+
+               ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
+                                                  iocb->ki_pos + count);
+               if (ret)
+                       goto out_unlock;
                ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
                                           iter, ext4_dio_get_block,
-                                          NULL, NULL,
-                                          unlocked ? 0 : DIO_LOCKING);
+                                          NULL, NULL, 0);
        }
-       if (unlocked)
-               inode_dio_end(inode);
+out_unlock:
+       inode_unlock_shared(inode);
        return ret;
 }