xfs: implement iomap based buffered write path
Convert XFS to use the new iomap based multipage write path. This involves
implementing the ->iomap_begin and ->iomap_end methods, and switching the
buffered file write, page_mkwrite and xfs_iozero paths to the new iomap
helpers.
With this change __xfs_get_blocks will never be used for buffered writes,
and the code handling them can be removed.
Based on earlier code from Dave Chinner.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 47fc632..7316d38 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -37,6 +37,7 @@
#include "xfs_log.h"
#include "xfs_icache.h"
#include "xfs_pnfs.h"
+#include "xfs_iomap.h"
#include <linux/dcache.h>
#include <linux/falloc.h>
@@ -79,57 +80,27 @@
inode_unlock(VFS_I(ip));
}
-/*
- * xfs_iozero clears the specified range supplied via the page cache (except in
- * the DAX case). Writes through the page cache will allocate blocks over holes,
- * though the callers usually map the holes first and avoid them. If a block is
- * not completely zeroed, then it will be read from disk before being partially
- * zeroed.
- *
- * In the DAX case, we can just directly write to the underlying pages. This
- * will not allocate blocks, but will avoid holes and unwritten extents and so
- * not do unnecessary work.
- */
-int
-xfs_iozero(
- struct xfs_inode *ip, /* inode */
- loff_t pos, /* offset in file */
- size_t count) /* size of data to zero */
+static int
+xfs_dax_zero_range(
+ struct inode *inode,
+ loff_t pos,
+ size_t count)
{
- struct page *page;
- struct address_space *mapping;
int status = 0;
-
- mapping = VFS_I(ip)->i_mapping;
do {
unsigned offset, bytes;
- void *fsdata;
offset = (pos & (PAGE_SIZE -1)); /* Within page */
bytes = PAGE_SIZE - offset;
if (bytes > count)
bytes = count;
- if (IS_DAX(VFS_I(ip))) {
- status = dax_zero_page_range(VFS_I(ip), pos, bytes,
- xfs_get_blocks_direct);
- if (status)
- break;
- } else {
- status = pagecache_write_begin(NULL, mapping, pos, bytes,
- AOP_FLAG_UNINTERRUPTIBLE,
- &page, &fsdata);
- if (status)
- break;
+ status = dax_zero_page_range(inode, pos, bytes,
+ xfs_get_blocks_direct);
+ if (status)
+ break;
- zero_user(page, offset, bytes);
-
- status = pagecache_write_end(NULL, mapping, pos, bytes,
- bytes, page, fsdata);
- WARN_ON(status <= 0); /* can't return less than zero! */
- status = 0;
- }
pos += bytes;
count -= bytes;
} while (count);
@@ -137,6 +108,24 @@
return status;
}
+/*
+ * Clear the specified ranges to zero through either the pagecache or DAX.
+ * Holes and unwritten extents will be left as-is as they already are zeroed.
+ */
+int
+xfs_iozero(
+ struct xfs_inode *ip,
+ loff_t pos,
+ size_t count)
+{
+ struct inode *inode = VFS_I(ip);
+
+ if (IS_DAX(VFS_I(ip)))
+ return xfs_dax_zero_range(inode, pos, count);
+ else
+ return iomap_zero_range(inode, pos, count, NULL, &xfs_iomap_ops);
+}
+
int
xfs_update_prealloc_flags(
struct xfs_inode *ip,
@@ -841,7 +830,7 @@
write_retry:
trace_xfs_file_buffered_write(ip, iov_iter_count(from),
iocb->ki_pos, 0);
- ret = generic_perform_write(file, from, iocb->ki_pos);
+ ret = iomap_file_buffered_write(iocb, from, &xfs_iomap_ops);
if (likely(ret >= 0))
iocb->ki_pos += ret;
@@ -1553,7 +1542,7 @@
if (IS_DAX(inode)) {
ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
} else {
- ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
+ ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
ret = block_page_mkwrite_return(ret);
}