xfs: avoid direct I/O write vs buffered I/O race

Currently a buffered reader or writer can add pages to the pagecache
while we are waiting for the iolock in xfs_file_dio_aio_write.  Prevent
this by re-checking mapping->nrpages after we got the iolock, and if
nessecary upgrade the lock to exclusive mode.  To simplify this a bit
only take the ilock inside of xfs_file_aio_write_checks.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Alex Elder <aelder@sgi.com>

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index ee63c4f..06fe97e 100644 (file)
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -676,6 +676,7 @@ xfs_file_aio_write_checks(
        xfs_fsize_t             new_size;
        int                     error = 0;
 
+       xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
        *new_sizep = 0;
 restart:
        error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
@@ -798,14 +799,24 @@ xfs_file_dio_aio_write(
                *iolock = XFS_IOLOCK_EXCL;
        else
                *iolock = XFS_IOLOCK_SHARED;
-       xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
+       xfs_rw_ilock(ip, *iolock);
+
+       /*
+        * Recheck if there are cached pages that need invalidate after we got
+        * the iolock to protect against other threads adding new pages while
+        * we were waiting for the iolock.
+        */
+       if (mapping->nrpages && *iolock == XFS_IOLOCK_SHARED) {
+               xfs_rw_iunlock(ip, *iolock);
+               *iolock = XFS_IOLOCK_EXCL;
+               xfs_rw_ilock(ip, *iolock);
+       }
 
        ret = xfs_file_aio_write_checks(file, &pos, &count, new_size, iolock);
        if (ret)
                return ret;
 
        if (mapping->nrpages) {
-               WARN_ON(*iolock != XFS_IOLOCK_EXCL);
                ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
                                                        FI_REMAPF_LOCKED);
                if (ret)
@@ -851,7 +862,7 @@ xfs_file_buffered_aio_write(
        size_t                  count = ocount;
 
        *iolock = XFS_IOLOCK_EXCL;
-       xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
+       xfs_rw_ilock(ip, *iolock);
 
        ret = xfs_file_aio_write_checks(file, &pos, &count, new_size, iolock);
        if (ret)