summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJeff Moyer <jmoyer@redhat.com>2006-10-20 06:28:13 (GMT)
committerLinus Torvalds <torvalds@g5.osdl.org>2006-10-20 17:26:35 (GMT)
commitfb5527e68d495650a7658fec9a7246bf922db212 (patch)
treedc0c993c3f07ddf1d1cf02a725ac3348f638d7bc
parente8e82b76e0312827f5ae04b573a05b02854a447e (diff)
downloadlinux-fb5527e68d495650a7658fec9a7246bf922db212.tar.xz
[PATCH] direct-io: sync and invalidate file region when falling back to buffered write
When direct-io falls back to buffered write, it will just leave the dirty data floating about in pagecache, pending regular writeback. But normal direct-io semantics are that IO is synchronous, and that it leaves no pagecache behind. So change the fallback-to-buffered-write code to sync the file region and to then strip away the pagecache, just as a regular direct-io write would do. Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Zach Brown <zach.brown@oracle.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-rw-r--r--mm/filemap.c51
1 files changed, 45 insertions, 6 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index 3464b68..57faa8d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2222,7 +2222,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t *ppos)
{
struct file *file = iocb->ki_filp;
- const struct address_space * mapping = file->f_mapping;
+ struct address_space * mapping = file->f_mapping;
size_t ocount; /* original count */
size_t count; /* after file limit checks */
struct inode *inode = mapping->host;
@@ -2275,8 +2275,11 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (unlikely(file->f_flags & O_DIRECT)) {
- written = generic_file_direct_write(iocb, iov,
- &nr_segs, pos, ppos, count, ocount);
+ loff_t endbyte;
+ ssize_t written_buffered;
+
+ written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
+ ppos, count, ocount);
if (written < 0 || written == count)
goto out;
/*
@@ -2285,10 +2288,46 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
*/
pos += written;
count -= written;
- }
+ written_buffered = generic_file_buffered_write(iocb, iov,
+ nr_segs, pos, ppos, count,
+ written);
+ /*
+ * If generic_file_buffered_write() retuned a synchronous error
+ * then we want to return the number of bytes which were
+ * direct-written, or the error code if that was zero. Note
+ * that this differs from normal direct-io semantics, which
+ * will return -EFOO even if some bytes were written.
+ */
+ if (written_buffered < 0) {
+ err = written_buffered;
+ goto out;
+ }
- written = generic_file_buffered_write(iocb, iov, nr_segs,
- pos, ppos, count, written);
+ /*
+ * We need to ensure that the page cache pages are written to
+ * disk and invalidated to preserve the expected O_DIRECT
+ * semantics.
+ */
+ endbyte = pos + written_buffered - written - 1;
+ err = do_sync_file_range(file, pos, endbyte,
+ SYNC_FILE_RANGE_WAIT_BEFORE|
+ SYNC_FILE_RANGE_WRITE|
+ SYNC_FILE_RANGE_WAIT_AFTER);
+ if (err == 0) {
+ written = written_buffered;
+ invalidate_mapping_pages(mapping,
+ pos >> PAGE_CACHE_SHIFT,
+ endbyte >> PAGE_CACHE_SHIFT);
+ } else {
+ /*
+ * We don't know how much we wrote, so just return
+ * the number of bytes which were direct-written
+ */
+ }
+ } else {
+ written = generic_file_buffered_write(iocb, iov, nr_segs,
+ pos, ppos, count, written);
+ }
out:
current->backing_dev_info = NULL;
return written ? written : err;