summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2014-09-02 12:12:51 +1000
committerDave Chinner <david@fromorbit.com>2014-09-02 12:12:51 +1000
commit22e757a49cf010703fcb9c9b4ef793248c39b0c2 (patch)
tree7bbd8018010a887e386642eae10d947b4561bcb8 /fs
parent52addcf9d6669fa439387610bc65c92fa0980cef (diff)
xfs: don't dirty buffers beyond EOF
generic/263 is failing fsx at this point with a page spanning EOF that cannot be invalidated. The operations are: 1190 mapwrite 0x52c00 thru 0x5e569 (0xb96a bytes) 1191 mapread 0x5c000 thru 0x5d636 (0x1637 bytes) 1192 write 0x5b600 thru 0x771ff (0x1bc00 bytes) where 1190 extents EOF from 0x54000 to 0x5e569. When the direct IO write attempts to invalidate the cached page over this range, it fails with -EBUSY and so any attempt to do page invalidation fails. The real question is this: Why can't that page be invalidated after it has been written to disk and cleaned? Well, there's data on the first two buffers in the page (1k block size, 4k page), but the third buffer on the page (i.e. beyond EOF) is failing drop_buffers because it's bh->b_state == 0x3, which is BH_Uptodate | BH_Dirty. IOWs, there's dirty buffers beyond EOF. Say what? OK, set_buffer_dirty() is called on all buffers from __set_page_buffers_dirty(), regardless of whether the buffer is beyond EOF or not, which means that when we get to ->writepage, we have buffers marked dirty beyond EOF that we need to clean. So, we need to implement our own .set_page_dirty method that doesn't dirty buffers beyond EOF. This is messy because the buffer code is not meant to be shared and it has interesting locking issues on the buffer dirty bits. So just copy and paste it and then modify it to suit what we need. Note: the solutions the other filesystems and generic block code use of marking the buffers clean in ->writepage does not work for XFS. It still leaves dirty buffers beyond EOF and invalidations still fail. Hence rather than play whack-a-mole, this patch simply prevents those buffers from being dirtied in the first place. cc: <stable@kernel.org> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
Diffstat (limited to 'fs')
-rw-r--r--fs/xfs/xfs_aops.c61
1 files changed, 61 insertions, 0 deletions
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 11e9b4caa54f..b984647c24db 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1753,11 +1753,72 @@ xfs_vm_readpages(
return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
}
+/*
+ * This is basically a copy of __set_page_dirty_buffers() with one
+ * small tweak: buffers beyond EOF do not get marked dirty. If we mark them
+ * dirty, we'll never be able to clean them because we don't write buffers
+ * beyond EOF, and that means we can't invalidate pages that span EOF
+ * that have been marked dirty. Further, the dirty state can leak into
+ * the file interior if the file is extended, resulting in all sorts of
+ * bad things happening as the state does not match the underlying data.
+ *
+ * XXX: this really indicates that bufferheads in XFS need to die. Warts like
+ * this only exist because of bufferheads and how the generic code manages them.
+ */
+STATIC int
+xfs_vm_set_page_dirty(
+ struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ struct inode *inode = mapping->host;
+ loff_t end_offset;
+ loff_t offset;
+ int newly_dirty;
+
+ if (unlikely(!mapping))
+ return !TestSetPageDirty(page);
+
+ end_offset = i_size_read(inode);
+ offset = page_offset(page);
+
+ spin_lock(&mapping->private_lock);
+ if (page_has_buffers(page)) {
+ struct buffer_head *head = page_buffers(page);
+ struct buffer_head *bh = head;
+
+ do {
+ if (offset < end_offset)
+ set_buffer_dirty(bh);
+ bh = bh->b_this_page;
+ offset += 1 << inode->i_blkbits;
+ } while (bh != head);
+ }
+ newly_dirty = !TestSetPageDirty(page);
+ spin_unlock(&mapping->private_lock);
+
+ if (newly_dirty) {
+ /* sigh - __set_page_dirty() is static, so copy it here, too */
+ unsigned long flags;
+
+ spin_lock_irqsave(&mapping->tree_lock, flags);
+ if (page->mapping) { /* Race with truncate? */
+ WARN_ON_ONCE(!PageUptodate(page));
+ account_page_dirtied(page, mapping);
+ radix_tree_tag_set(&mapping->page_tree,
+ page_index(page), PAGECACHE_TAG_DIRTY);
+ }
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
+ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+ }
+ return newly_dirty;
+}
+
const struct address_space_operations xfs_address_space_operations = {
.readpage = xfs_vm_readpage,
.readpages = xfs_vm_readpages,
.writepage = xfs_vm_writepage,
.writepages = xfs_vm_writepages,
+ .set_page_dirty = xfs_vm_set_page_dirty,
.releasepage = xfs_vm_releasepage,
.invalidatepage = xfs_vm_invalidatepage,
.write_begin = xfs_vm_write_begin,