[PATCH 03/24] GFS2: Something nonlinear this way comes!

From: Steven Whitehouse
Date: Wed Jun 10 2009 - 05:38:52 EST


For some reason GFS2 has been missing support for non-linear
mappings. This patch fixes that, and also avoids taking any
locks for mmap in the O_NOATIME case. In fact we don't actually need
to take the lock here at all - just doing file_accessed() would be
enough, but we have to take the lock eventually and this helps
it hit disk (and thus be seen by other nodes) faster.

Signed-off-by: Steven Whitehouse <swhiteho@xxxxxxxxxx>

diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index 5d82e91..0ee7bd2 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -425,33 +425,36 @@ static struct vm_operations_struct gfs2_vm_ops = {
.page_mkwrite = gfs2_page_mkwrite,
};

-
/**
* gfs2_mmap -
* @file: The file to map
* @vma: The VMA which described the mapping
*
- * Returns: 0 or error code
+ * There is no need to get a lock here unless we should be updating
+ * atime. We ignore any locking errors since the only consequence is
+ * a missed atime update (which will just be deferred until later).
+ *
+ * Returns: 0
*/

static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
- struct gfs2_holder i_gh;
- int error;

- gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
- error = gfs2_glock_nq(&i_gh);
- if (error) {
- gfs2_holder_uninit(&i_gh);
- return error;
- }
+ if (!(file->f_flags & O_NOATIME)) {
+ struct gfs2_holder i_gh;
+ int error;

+ gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+ error = gfs2_glock_nq(&i_gh);
+ file_accessed(file);
+ if (error == 0)
+ gfs2_glock_dq_uninit(&i_gh);
+ }
vma->vm_ops = &gfs2_vm_ops;
+ vma->vm_flags |= VM_CAN_NONLINEAR;

- gfs2_glock_dq_uninit(&i_gh);
-
- return error;
+ return 0;
}

/**
--
1.6.0.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/