mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-04 09:59:32 +00:00
xfs: xfs_check_page_type buffer checks need help
xfs_aops_discard_page() was introduced in the following commit: xfs: truncate delalloc extents when IO fails in writeback ... to clean up left over delalloc ranges after I/O failure in ->writepage(). generic/224 tests for this scenario and occasionally reproduces panics on sub-4k blocksize filesystems. The cause of this is failure to clean up the delalloc range on a page where the first buffer does not match one of the expected states of xfs_check_page_type(). If a buffer is not unwritten, delayed or dirty&mapped, xfs_check_page_type() stops and immediately returns 0. The stress test of generic/224 creates a scenario where the first several buffers of a page with delayed buffers are mapped & uptodate and some subsequent buffer is delayed. If the ->writepage() happens to fail for this page, xfs_aops_discard_page() incorrectly skips the entire page. This then causes later failures either when direct IO maps the range and finds the stale delayed buffer, or we evict the inode and find that the inode still has a delayed block reservation accounted to it. We can easily fix this xfs_aops_discard_page() failure by making xfs_check_page_type() check all buffers, but this breaks xfs_convert_page() more than it is already broken. Indeed, xfs_convert_page() wants xfs_check_page_type() to tell it if the first buffers on the pages are of a type that can be aggregated into the contiguous IO that is already being built. xfs_convert_page() should not be writing random buffers out of a page, but the current behaviour will cause it to do so if there are buffers that don't match the current specification on the page. Hence for xfs_convert_page() we need to: a) return "not ok" if the first buffer on the page does not match the specification provided to we don't write anything; and b) abort it's buffer-add-to-io loop the moment we come across a buffer that does not match the specification. Hence we need to fix both xfs_check_page_type() and xfs_convert_page() to work correctly with pages that have mixed buffer types, whilst allowing xfs_aops_discard_page() to scan all buffers on the page for a type match. Reported-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
This commit is contained in:
parent
e480a72397
commit
a49935f200
1 changed files with 50 additions and 31 deletions
|
@ -632,38 +632,46 @@ xfs_map_at_offset(
|
|||
}
|
||||
|
||||
/*
|
||||
* Test if a given page is suitable for writing as part of an unwritten
|
||||
* or delayed allocate extent.
|
||||
* Test if a given page contains at least one buffer of a given @type.
|
||||
* If @check_all_buffers is true, then we walk all the buffers in the page to
|
||||
* try to find one of the type passed in. If it is not set, then the caller only
|
||||
* needs to check the first buffer on the page for a match.
|
||||
*/
|
||||
STATIC int
|
||||
STATIC bool
|
||||
xfs_check_page_type(
|
||||
struct page *page,
|
||||
unsigned int type)
|
||||
unsigned int type,
|
||||
bool check_all_buffers)
|
||||
{
|
||||
struct buffer_head *bh;
|
||||
struct buffer_head *head;
|
||||
|
||||
if (PageWriteback(page))
|
||||
return 0;
|
||||
return false;
|
||||
if (!page->mapping)
|
||||
return false;
|
||||
if (!page_has_buffers(page))
|
||||
return false;
|
||||
|
||||
if (page->mapping && page_has_buffers(page)) {
|
||||
struct buffer_head *bh, *head;
|
||||
int acceptable = 0;
|
||||
bh = head = page_buffers(page);
|
||||
do {
|
||||
if (buffer_unwritten(bh)) {
|
||||
if (type == XFS_IO_UNWRITTEN)
|
||||
return true;
|
||||
} else if (buffer_delay(bh)) {
|
||||
if (type == XFS_IO_DELALLOC);
|
||||
return true;
|
||||
} else if (buffer_dirty(bh) && buffer_mapped(bh)) {
|
||||
if (type == XFS_IO_OVERWRITE);
|
||||
return true;
|
||||
}
|
||||
|
||||
bh = head = page_buffers(page);
|
||||
do {
|
||||
if (buffer_unwritten(bh))
|
||||
acceptable += (type == XFS_IO_UNWRITTEN);
|
||||
else if (buffer_delay(bh))
|
||||
acceptable += (type == XFS_IO_DELALLOC);
|
||||
else if (buffer_dirty(bh) && buffer_mapped(bh))
|
||||
acceptable += (type == XFS_IO_OVERWRITE);
|
||||
else
|
||||
break;
|
||||
} while ((bh = bh->b_this_page) != head);
|
||||
/* If we are only checking the first buffer, we are done now. */
|
||||
if (!check_all_buffers)
|
||||
break;
|
||||
} while ((bh = bh->b_this_page) != head);
|
||||
|
||||
if (acceptable)
|
||||
return 1;
|
||||
}
|
||||
|
||||
return 0;
|
||||
return false;
|
||||
}
|
||||
|
||||
/*
|
||||
|
@ -697,7 +705,7 @@ xfs_convert_page(
|
|||
goto fail_unlock_page;
|
||||
if (page->mapping != inode->i_mapping)
|
||||
goto fail_unlock_page;
|
||||
if (!xfs_check_page_type(page, (*ioendp)->io_type))
|
||||
if (!xfs_check_page_type(page, (*ioendp)->io_type, false))
|
||||
goto fail_unlock_page;
|
||||
|
||||
/*
|
||||
|
@ -742,6 +750,15 @@ xfs_convert_page(
|
|||
p_offset = p_offset ? roundup(p_offset, len) : PAGE_CACHE_SIZE;
|
||||
page_dirty = p_offset / len;
|
||||
|
||||
/*
|
||||
* The moment we find a buffer that doesn't match our current type
|
||||
* specification or can't be written, abort the loop and start
|
||||
* writeback. As per the above xfs_imap_valid() check, only
|
||||
* xfs_vm_writepage() can handle partial page writeback fully - we are
|
||||
* limited here to the buffers that are contiguous with the current
|
||||
* ioend, and hence a buffer we can't write breaks that contiguity and
|
||||
* we have to defer the rest of the IO to xfs_vm_writepage().
|
||||
*/
|
||||
bh = head = page_buffers(page);
|
||||
do {
|
||||
if (offset >= end_offset)
|
||||
|
@ -750,7 +767,7 @@ xfs_convert_page(
|
|||
uptodate = 0;
|
||||
if (!(PageUptodate(page) || buffer_uptodate(bh))) {
|
||||
done = 1;
|
||||
continue;
|
||||
break;
|
||||
}
|
||||
|
||||
if (buffer_unwritten(bh) || buffer_delay(bh) ||
|
||||
|
@ -762,10 +779,11 @@ xfs_convert_page(
|
|||
else
|
||||
type = XFS_IO_OVERWRITE;
|
||||
|
||||
if (!xfs_imap_valid(inode, imap, offset)) {
|
||||
done = 1;
|
||||
continue;
|
||||
}
|
||||
/*
|
||||
* imap should always be valid because of the above
|
||||
* partial page end_offset check on the imap.
|
||||
*/
|
||||
ASSERT(xfs_imap_valid(inode, imap, offset));
|
||||
|
||||
lock_buffer(bh);
|
||||
if (type != XFS_IO_OVERWRITE)
|
||||
|
@ -777,6 +795,7 @@ xfs_convert_page(
|
|||
count++;
|
||||
} else {
|
||||
done = 1;
|
||||
break;
|
||||
}
|
||||
} while (offset += len, (bh = bh->b_this_page) != head);
|
||||
|
||||
|
@ -868,7 +887,7 @@ xfs_aops_discard_page(
|
|||
struct buffer_head *bh, *head;
|
||||
loff_t offset = page_offset(page);
|
||||
|
||||
if (!xfs_check_page_type(page, XFS_IO_DELALLOC))
|
||||
if (!xfs_check_page_type(page, XFS_IO_DELALLOC, true))
|
||||
goto out_invalidate;
|
||||
|
||||
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
|
||||
|
|
Loading…
Reference in a new issue