From: Dave Chinner <dchinner@xxxxxxxxxx>
xfs_vm_writepages() calls generic_writepages to writeback a range of
a file, but then xfs_vm_writepage() clusters pages itself as it does
not have any context it can pass between->writepage calls from
__write_cache_pages().
Introduce a writeback context for xfs_vm_writepages() and call
__write_cache_pages directly with our own writepage callback so that
we can pass that context to each writepage invocation. This
encapsulates the current mapping, whether it is valid or not, the
current ioend and it's IO type and the ioend chain being built.
This requires us to move the ioend submission up to the level where
the writepage context is declared. This does mean we do not submit
IO until we packaged the entire writeback range, but with the block
plugging in the writepages call this is the way IO is submitted,
anyway.
It also means that we need to handle discontiguous page ranges. If
the pages sent down by write_cache_pages to the writepage callback
are discontiguous, we need to detect this and put each discontiguous
page range into individual ioends. This is needed to ensure that the
ioend accurately represents the range of the file that it covers so
that file size updates during IO completion set the size correctly.
Failure to take into account the discontiguous ranges results in
files being too small when writeback patterns are non-sequential.
Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx>
---
fs/xfs/xfs_aops.c | 277 ++++++++++++++++++++++++++++--------------------------
1 file changed, 146 insertions(+), 131 deletions(-)
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 89fad6b..93bf13c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -36,6 +36,18 @@
#include <linux/pagevec.h>
#include <linux/writeback.h>
+/*
+ * structure owned by writepages passed to individual writepage calls
+ */
+struct xfs_writepage_ctx {
+ struct xfs_bmbt_irec imap;
+ bool imap_valid;
+ unsigned int io_type;
+ struct xfs_ioend *iohead;
+ struct xfs_ioend *ioend;
+ sector_t last_block;
+};
+
void
xfs_count_page_state(
struct page *page,
@@ -328,7 +340,7 @@ xfs_map_blocks(
return 0;
}
-STATIC int
+STATIC bool
xfs_imap_valid(
struct inode *inode,
struct xfs_bmbt_irec *imap,
@@ -516,38 +528,6 @@ xfs_submit_ioend(
}
/*
- * Cancel submission of all buffer_heads so far in this endio.
- * Toss the endio too. Only ever called for the initial page
- * in a writepage request, so only ever one page.
- */
-STATIC void
-xfs_cancel_ioend(
- xfs_ioend_t *ioend)
-{
- xfs_ioend_t *next;
- struct buffer_head *bh, *next_bh;
-
- do {
- next = ioend->io_list;
- bh = ioend->io_buffer_head;
- do {
- next_bh = bh->b_private;
- clear_buffer_async_write(bh);
- /*
- * The unwritten flag is cleared when added to the
- * ioend. We're not submitting for I/O so mark the
- * buffer unwritten again for next time around.
- */
- if (ioend->io_type == XFS_IO_UNWRITTEN)
- set_buffer_unwritten(bh);
- unlock_buffer(bh);
- } while ((bh = next_bh) != NULL);
-
- mempool_free(ioend, xfs_ioend_pool);
- } while ((ioend = next) != NULL);
-}
-
-/*
* Test to see if we've been building up a completion structure for
* earlier buffers -- if so, we try to append to this ioend if we
* can, otherwise we finish off any current ioend and start another.
@@ -558,29 +538,27 @@ xfs_add_to_ioend(
struct inode *inode,
struct buffer_head *bh,
xfs_off_t offset,
- unsigned int type,
- xfs_ioend_t **result,
- int need_ioend)
+ struct xfs_writepage_ctx *wpc)
{
- xfs_ioend_t *ioend = *result;
-
- if (!ioend || need_ioend || type != ioend->io_type) {
- xfs_ioend_t *previous = *result;
-
- ioend = xfs_alloc_ioend(inode, type);
- ioend->io_offset = offset;
- ioend->io_buffer_head = bh;
- ioend->io_buffer_tail = bh;
- if (previous)
- previous->io_list = ioend;
- *result = ioend;
+ if (!wpc->ioend || wpc->io_type != wpc->ioend->io_type ||
+ bh->b_blocknr != wpc->last_block + 1) {
+ struct xfs_ioend *new;
+
+ new = xfs_alloc_ioend(inode, wpc->io_type);
+ new->io_offset = offset;
+ new->io_buffer_head = bh;
+ new->io_buffer_tail = bh;
+ if (wpc->ioend)
+ wpc->ioend->io_list = new;
+ wpc->ioend = new;
} else {
- ioend->io_buffer_tail->b_private = bh;
- ioend->io_buffer_tail = bh;
+ wpc->ioend->io_buffer_tail->b_private = bh;
+ wpc->ioend->io_buffer_tail = bh;
}
bh->b_private = NULL;
- ioend->io_size += bh->b_size;
+ wpc->ioend->io_size += bh->b_size;
+ wpc->last_block = bh->b_blocknr;
}
STATIC void
@@ -677,17 +655,15 @@ xfs_convert_page(
struct inode *inode,
struct page *page,
loff_t tindex,
- struct xfs_bmbt_irec *imap,
- xfs_ioend_t **ioendp,
+ struct xfs_writepage_ctx *wpc,
struct writeback_control *wbc)
{
struct buffer_head *bh, *head;
xfs_off_t end_offset;
unsigned long p_offset;
- unsigned int type;
int len, page_dirty;
int count = 0, done = 0, uptodate = 1;
- xfs_off_t offset = page_offset(page);
+ xfs_off_t offset = page_offset(page);
if (page->index != tindex)
goto fail;
@@ -697,7 +673,7 @@ 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, false))
+ if (!xfs_check_page_type(page, wpc->ioend->io_type, false))
goto fail_unlock_page;
/*
@@ -733,7 +709,7 @@ xfs_convert_page(
* writeback. Hence for more optimal IO patterns, we should always
* avoid partial page writeback due to multiple mappings on a page here.
*/
- if (!xfs_imap_valid(inode, imap, end_offset))
+ if (!xfs_imap_valid(inode, &wpc->imap, end_offset))
goto fail_unlock_page;
len = 1 << inode->i_blkbits;
@@ -765,23 +741,22 @@ xfs_convert_page(
if (buffer_unwritten(bh) || buffer_delay(bh) ||
buffer_mapped(bh)) {
if (buffer_unwritten(bh))
- type = XFS_IO_UNWRITTEN;
+ wpc->io_type = XFS_IO_UNWRITTEN;
else if (buffer_delay(bh))
- type = XFS_IO_DELALLOC;
+ wpc->io_type = XFS_IO_DELALLOC;
else
- type = XFS_IO_OVERWRITE;
+ wpc->io_type = XFS_IO_OVERWRITE;
/*
* imap should always be valid because of the above
* partial page end_offset check on the imap.
*/
- ASSERT(xfs_imap_valid(inode, imap, offset));
+ ASSERT(xfs_imap_valid(inode, &wpc->imap, offset));
lock_buffer(bh);
- if (type != XFS_IO_OVERWRITE)
- xfs_map_at_offset(inode, bh, imap, offset);
- xfs_add_to_ioend(inode, bh, offset, type,
- ioendp, done);
+ if (wpc->io_type != XFS_IO_OVERWRITE)
+ xfs_map_at_offset(inode, bh, &wpc->imap, offset);
+ xfs_add_to_ioend(inode, bh, offset, wpc);
page_dirty--;
count++;
@@ -816,8 +791,7 @@ STATIC void
xfs_cluster_write(
struct inode *inode,
pgoff_t tindex,
- struct xfs_bmbt_irec *imap,
- xfs_ioend_t **ioendp,
+ struct xfs_writepage_ctx *wpc,
struct writeback_control *wbc,
pgoff_t tlast)
{
@@ -833,7 +807,7 @@ xfs_cluster_write(
for (i = 0; i < pagevec_count(&pvec); i++) {
done = xfs_convert_page(inode, pvec.pages[i], tindex++,
- imap, ioendp, wbc);
+ wpc, wbc);
if (done)
break;
}
@@ -919,6 +893,27 @@ out_invalidate:
return;
}
+static int
+xfs_writepage_submit(
+ struct xfs_writepage_ctx *wpc,
+ struct writeback_control *wbc,
+ int status)
+{
+ struct blk_plug plug;
+
+ /* Reserve log space if we might write beyond the on-disk inode size. */
+ if (!status && wpc->ioend && wpc->ioend->io_type != XFS_IO_UNWRITTEN &&
+ xfs_ioend_is_append(wpc->ioend))
+ status = xfs_setfilesize_trans_alloc(wpc->ioend);
+
+ if (wpc->iohead) {
+ blk_start_plug(&plug);
+ xfs_submit_ioend(wbc, wpc->iohead, status);
+ blk_finish_plug(&plug);
+ }
+ return status;
+}
+
/*
* Write out a dirty page.
*
@@ -928,20 +923,19 @@ out_invalidate:
* For any other dirty buffer heads on the page we should flush them.
*/
STATIC int
-xfs_vm_writepage(
+xfs_do_writepage(
struct page *page,
- struct writeback_control *wbc)
+ struct writeback_control *wbc,
+ void *data)
{
+ struct xfs_writepage_ctx *wpc = data;
struct inode *inode = page->mapping->host;
struct buffer_head *bh, *head;
- struct xfs_bmbt_irec imap;
- xfs_ioend_t *ioend = NULL, *iohead = NULL;
loff_t offset;
- unsigned int type;
__uint64_t end_offset;
pgoff_t end_index, last_index;
ssize_t len;
- int err, imap_valid = 0, uptodate = 1;
+ int err, uptodate = 1;
int count = 0;
trace_xfs_writepage(inode, page, 0, 0);
@@ -1040,11 +1034,8 @@ xfs_vm_writepage(
bh = head = page_buffers(page);
offset = page_offset(page);
- type = XFS_IO_OVERWRITE;
do {
- int new_ioend = 0;
-
if (offset >= end_offset)
break;
if (!buffer_uptodate(bh))
@@ -1057,24 +1048,24 @@ xfs_vm_writepage(
* buffers covering holes here.
*/
if (!buffer_mapped(bh) && buffer_uptodate(bh)) {
- imap_valid = 0;
+ wpc->imap_valid = false;
continue;
}
if (buffer_unwritten(bh)) {
- if (type != XFS_IO_UNWRITTEN) {
- type = XFS_IO_UNWRITTEN;
- imap_valid = 0;
+ if (wpc->io_type != XFS_IO_UNWRITTEN) {
+ wpc->io_type = XFS_IO_UNWRITTEN;
+ wpc->imap_valid = false;
}
} else if (buffer_delay(bh)) {
- if (type != XFS_IO_DELALLOC) {
- type = XFS_IO_DELALLOC;
- imap_valid = 0;
+ if (wpc->io_type != XFS_IO_DELALLOC) {
+ wpc->io_type = XFS_IO_DELALLOC;
+ wpc->imap_valid = false;
}
} else if (buffer_uptodate(bh)) {
- if (type != XFS_IO_OVERWRITE) {
- type = XFS_IO_OVERWRITE;
- imap_valid = 0;
+ if (wpc->io_type != XFS_IO_OVERWRITE) {
+ wpc->io_type = XFS_IO_OVERWRITE;
+ wpc->imap_valid = false;
}
} else {
if (PageUptodate(page))
@@ -1085,38 +1076,31 @@ xfs_vm_writepage(
* subsequent writeable buffers into a new
* ioend.
*/
- imap_valid = 0;
+ wpc->imap_valid = false;
continue;
}
- if (imap_valid)
- imap_valid = xfs_imap_valid(inode, &imap, offset);
- if (!imap_valid) {
- /*
- * If we didn't have a valid mapping then we need to
- * put the new mapping into a separate ioend structure.
- * This ensures non-contiguous extents always have
- * separate ioends, which is particularly important
- * for unwritten extent conversion at I/O completion
- * time.
- */
- new_ioend = 1;
- err = xfs_map_blocks(inode, offset, &imap, type);
+ if (wpc->imap_valid)
+ wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
+ offset);
+ if (!wpc->imap_valid) {
+ err = xfs_map_blocks(inode, offset, &wpc->imap,
+ wpc->io_type);
if (err)
goto error;
- imap_valid = xfs_imap_valid(inode, &imap, offset);
+ wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
+ offset);
}
- if (imap_valid) {
+ if (wpc->imap_valid) {
lock_buffer(bh);
- if (type != XFS_IO_OVERWRITE)
- xfs_map_at_offset(inode, bh, &imap, offset);
- xfs_add_to_ioend(inode, bh, offset, type, &ioend,
- new_ioend);
+ if (wpc->io_type != XFS_IO_OVERWRITE)
+ xfs_map_at_offset(inode, bh, &wpc->imap, offset);
+ xfs_add_to_ioend(inode, bh, offset, wpc);
count++;
}
- if (!iohead)
- iohead = ioend;
+ if (!wpc->iohead)
+ wpc->iohead = wpc->ioend;
} while (offset += len, ((bh = bh->b_this_page) != head));
@@ -1126,20 +1110,20 @@ xfs_vm_writepage(
xfs_start_page_writeback(page, 1, count);
/* if there is no IO to be submitted for this page, we are done */
- if (!ioend)
+ if (!count)
return 0;
- ASSERT(iohead);
+ ASSERT(wpc->iohead);
/*
* Any errors from this point onwards need tobe reported through the IO
* completion path as we have marked the initial page as under writeback
* and unlocked it.
*/
- if (imap_valid) {
+ if (wpc->imap_valid) {
xfs_off_t end_index;
- end_index = imap.br_startoff + imap.br_blockcount;
+ end_index = wpc->imap.br_startoff + wpc->imap.br_blockcount;
/* to bytes */
end_index <<= inode->i_blkbits;
@@ -1151,29 +1135,36 @@ xfs_vm_writepage(
if (end_index > last_index)
end_index = last_index;
- xfs_cluster_write(inode, page->index + 1, &imap, &ioend,
- wbc, end_index);
+ xfs_cluster_write(inode, page->index + 1, wpc, wbc, end_index);
}
-
- /*
- * Reserve log space if we might write beyond the on-disk inode size.
- */
- err = 0;
- if (ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend))
- err = xfs_setfilesize_trans_alloc(ioend);
-
- xfs_submit_ioend(wbc, iohead, err);
-
return 0;
error:
- if (iohead)
- xfs_cancel_ioend(iohead);
+ /*
+ * We have to fail the iohead here because we buffers locked in the
+ * ioend chain. If we don't do this, we'll deadlock invalidating the
+ * page as that tries to lock the buffers on the page. Also, because we
+ * have set pages under writeback, we have to run IO completion to mark
+ * the error state of the IO appropriately, so we can't cancel the ioend
+ * directly here. That means we have to mark this page as under
+ * writeback if we included any buffers from it in the ioend chain.
+ */
+ if (count)
+ xfs_start_page_writeback(page, 0, count);
+ xfs_writepage_submit(wpc, wbc, err);
- xfs_aops_discard_page(page);
- ClearPageUptodate(page);
- unlock_page(page);
+ /*
+ * We can only discard the page we had the IO error on if we haven't
+ * included it in the ioend above. If it has already been errored out,
+ * the it is unlocked and we can't touch it here.
+ */
+ if (!count) {
+ xfs_aops_discard_page(page);
+ ClearPageUptodate(page);
+ unlock_page(page);
+ }
+ mapping_set_error(page->mapping, err);
return err;
redirty:
@@ -1183,12 +1174,36 @@ redirty:
}
STATIC int
+xfs_vm_writepage(
+ struct page *page,
+ struct writeback_control *wbc)
+{
+ struct xfs_writepage_ctx wpc = {
+ .io_type = XFS_IO_OVERWRITE,
+ };
+ int ret;
+
+ ret = xfs_do_writepage(page, wbc, &wpc);
+ if (ret)
+ return ret;
+ return xfs_writepage_submit(&wpc, wbc, ret);
+}
+
+STATIC int
xfs_vm_writepages(
struct address_space *mapping,
struct writeback_control *wbc)
{
+ struct xfs_writepage_ctx wpc = {
+ .io_type = XFS_IO_OVERWRITE,
+ };
+ int ret;
+
xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
- return generic_writepages(mapping, wbc);
+ ret = write_cache_pages(mapping, wbc, xfs_do_writepage, &wpc);
+ if (ret)
+ return ret;
+ return xfs_writepage_submit(&wpc, wbc, ret);
}
/*
--
2.5.0
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
