ceph: sync read/write considers page cache

In the cases where we either do a sync read or a write, we
need to make sure that everything in the page cache is flushed.
In the case of a sync write we invalidate the relevant pages,
so that subsequent read/write reflects the new data written.

Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 43bd2f2e51a572279bbd2d82bffd8ea5ae735da5..bbf1ccf2d56ef4647df9346f22d260e1855023b0 100644 (file)
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -409,7 +409,7 @@ static void zero_page_vector_range(int off, int len, struct page **pages)
                i++;
        }
        while (len >= PAGE_CACHE_SIZE) {
-               dout("zeroing %d %p\n", i, pages[i]);
+               dout("zeroing %d %p len=%d\n", i, pages[i], len);
                zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
                len -= PAGE_CACHE_SIZE;
                i++;
@@ -542,13 +542,16 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
                 * but it will at least behave sensibly when they are
                 * in sequence.
                 */
-               filemap_write_and_wait(inode->i_mapping);
        } else {
                pages = alloc_page_vector(num_pages);
        }
        if (IS_ERR(pages))
                return PTR_ERR(pages);
 
+       ret = filemap_write_and_wait(inode->i_mapping);
+       if (ret < 0)
+               goto done;
+
        ret = striped_read(inode, off, len, pages, num_pages);
 
        if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
@@ -556,6 +559,7 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
        if (ret >= 0)
                *poff = off + ret;
 
+done:
        if (file->f_flags & O_DIRECT)
                put_page_vector(pages, num_pages);
        else
@@ -617,6 +621,16 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
        else
                pos = *offset;
 
+       ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left);
+       if (ret < 0)
+               return ret;
+
+       ret = invalidate_inode_pages2_range(inode->i_mapping,
+                                           pos >> PAGE_CACHE_SHIFT,
+                                           (pos + left) >> PAGE_CACHE_SHIFT);
+       if (ret < 0)
+               dout("invalidate_inode_pages2_range returned %d\n", ret);
+
        flags = CEPH_OSD_FLAG_ORDERSNAP |
                CEPH_OSD_FLAG_ONDISK |
                CEPH_OSD_FLAG_WRITE;