1 files changed, 59 insertions, 1 deletions

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 2e8322c8aa88..7b80d543b89e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -55,11 +55,47 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
         return 0;
 }
 
+static void ext4_aiodio_wait(struct inode *inode)
+{
+        wait_queue_head_t *wq = ext4_ioend_wq(inode);
+
+        wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0));
+}
+
+/*
+ * This tests whether the IO in question is block-aligned or not.
+ * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
+ * are converted to written only after the IO is complete.  Until they are
+ * mapped, these blocks appear as holes, so dio_zero_block() will assume that
+ * it needs to zero out portions of the start and/or end block.  If 2 AIO
+ * threads are at work on the same unwritten block, they must be synchronized
+ * or one thread will zero the other's data, causing corruption.
+ */
+static int
+ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
+                   unsigned long nr_segs, loff_t pos)
+{
+        struct super_block *sb = inode->i_sb;
+        int blockmask = sb->s_blocksize - 1;
+        size_t count = iov_length(iov, nr_segs);
+        loff_t final_size = pos + count;
+
+        if (pos >= inode->i_size)
+                return 0;
+
+        if ((pos & blockmask) || (final_size & blockmask))
+                return 1;
+
+        return 0;
+}
+
 static ssize_t
 ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
                 unsigned long nr_segs, loff_t pos)
 {
         struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+        int unaligned_aio = 0;
+        int ret;
 
         /*
          * If we have encountered a bitmap-format file, the size limit
@@ -78,9 +114,31 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
                         nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
                                               sbi->s_bitmap_maxbytes - pos);
                 }
+        } else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
+                   !is_sync_kiocb(iocb))) {
+                unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
         }
 
-        return generic_file_aio_write(iocb, iov, nr_segs, pos);
+        /* Unaligned direct AIO must be serialized; see comment above */
+        if (unaligned_aio) {
+                static unsigned long unaligned_warn_time;
+
+                /* Warn about this once per day */
+                if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
+                        ext4_msg(inode->i_sb, KERN_WARNING,
+                                 "Unaligned AIO/DIO on inode %ld by %s; "
+                                 "performance will be poor.",
+                                 inode->i_ino, current->comm);
+                mutex_lock(ext4_aio_mutex(inode));
+                ext4_aiodio_wait(inode);
+        }
+
+        ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+
+        if (unaligned_aio)
+                mutex_unlock(ext4_aio_mutex(inode));
+
+        return ret;
 }
 
 static const struct vm_operations_struct ext4_file_vm_ops = {