NFS: Fix a race in nfs_sync_inode()
Kudos to Neil Brown for spotting the problem:
"in nfs_sync_inode, there is effectively the sequence:
nfs_wait_on_requests
nfs_flush_inode
nfs_commit_inode
This seems a bit racy to me as if the only requests are on the
->commit list, and nfs_commit_inode is called separately after
nfs_wait_on_requests completes, and before nfs_commit_inode start
(say: by nfs_write_inode) then none of these function will return
>0, yet there will be some pending request that aren't waited for."
The solution is to search for requests to wait upon, search for dirty
requests, and search for uncommitted requests while holding the
nfsi->req_lock
The patch also cleans up nfs_sync_inode(), getting rid of the redundant
FLUSH_WAIT flag. It turns out that we were always setting it.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 55de077..cbebd7d 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -56,9 +56,7 @@
* When flushing a cluster of dirty pages, there can be different
* strategies:
*/
-#define FLUSH_AGING 0 /* only flush old buffers */
#define FLUSH_SYNC 1 /* file being synced, or contention */
-#define FLUSH_WAIT 2 /* wait for completion */
#define FLUSH_STABLE 4 /* commit to stable storage */
#define FLUSH_LOWPRI 8 /* low priority background flush */
#define FLUSH_HIGHPRI 16 /* high priority memory reclaim flush */
@@ -419,7 +417,7 @@
* Try to write back everything synchronously (but check the
* return value!)
*/
-extern int nfs_sync_inode(struct inode *, unsigned long, unsigned int, int);
+extern int nfs_sync_inode_wait(struct inode *, unsigned long, unsigned int, int);
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
extern int nfs_commit_inode(struct inode *, int);
extern void nfs_commit_release(void *wdata);
@@ -440,7 +438,7 @@
static inline int
nfs_wb_all(struct inode *inode)
{
- int error = nfs_sync_inode(inode, 0, 0, FLUSH_WAIT);
+ int error = nfs_sync_inode_wait(inode, 0, 0, 0);
return (error < 0) ? error : 0;
}
@@ -449,8 +447,8 @@
*/
static inline int nfs_wb_page_priority(struct inode *inode, struct page* page, int how)
{
- int error = nfs_sync_inode(inode, page->index, 1,
- how | FLUSH_WAIT | FLUSH_STABLE);
+ int error = nfs_sync_inode_wait(inode, page->index, 1,
+ how | FLUSH_STABLE);
return (error < 0) ? error : 0;
}