NFS: Add attribute update barriers to NFS writebacks

Ensure that other operations that race with our write RPC calls
cannot revert the file size updates that were made on the server.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Tested-by: Chuck Lever <chuck.lever@oracle.com>

7 files changed, 57 insertions, 8 deletions

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 299bf71..ff9a679 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1491,7 +1491,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
 
 /**
- * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
+ * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache
  * @inode - pointer to inode
  * @fattr - updated attributes
  *
@@ -1501,11 +1501,10 @@ EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
  *
  * This function is mainly designed to be used by the ->write_done() functions.
  */
-int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
+int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
 	int status;
 
-	spin_lock(&inode->i_lock);
 	/* Don't do a WCC update if these attributes are already stale */
 	if ((fattr->valid & NFS_ATTR_FATTR) == 0 ||
 			!nfs_inode_attrs_need_update(inode, fattr)) {
@@ -1537,6 +1536,26 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa
 	}
 out_noforce:
 	status = nfs_post_op_update_inode_locked(inode, fattr);
+	return status;
+}
+
+/**
+ * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
+ * @inode - pointer to inode
+ * @fattr - updated attributes
+ *
+ * After an operation that has changed the inode metadata, mark the
+ * attribute cache as being invalid, then try to update it. Fake up
+ * weak cache consistency data, if none exist.
+ *
+ * This function is mainly designed to be used by the ->write_done() functions.
+ */
+int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
+{
+	int status;
+
+	spin_lock(&inode->i_lock);
+	status = nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
 	spin_unlock(&inode->i_lock);
 	return status;
 }
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b802fb3..9e6475b 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -459,6 +459,7 @@ void nfs_mark_request_commit(struct nfs_page *req,
 			     struct nfs_commit_info *cinfo,
 			     u32 ds_commit_idx);
 int nfs_write_need_commit(struct nfs_pgio_header *);
+void nfs_writeback_update_inode(struct nfs_pgio_header *hdr);
 int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
 			    int how, struct nfs_commit_info *cinfo);
 void nfs_retry_commit(struct list_head *page_list,
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 11109a1..1f11d25 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -834,7 +834,7 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(inode, hdr->res.fattr);
+		nfs_writeback_update_inode(hdr);
 	return 0;
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c499e02..b022e64 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4237,7 +4237,7 @@ static int nfs4_write_done_cb(struct rpc_task *task,
 	}
 	if (task->tk_status >= 0) {
 		renew_lease(NFS_SERVER(inode), hdr->timestamp);
-		nfs_post_op_update_inode_force_wcc(inode, &hdr->fattr);
+		nfs_writeback_update_inode(hdr);
 	}
 	return 0;
 }
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 6202bc0..c63189a 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -609,10 +609,8 @@ static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task,
 
 static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	struct inode *inode = hdr->inode;
-
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(inode, hdr->res.fattr);
+		nfs_writeback_update_inode(hdr);
 	return 0;
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 595d81e..849ed78 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1377,6 +1377,36 @@ static int nfs_should_remove_suid(const struct inode *inode)
 	return 0;
 }
 
+static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr,
+		struct nfs_fattr *fattr)
+{
+	struct nfs_pgio_args *argp = &hdr->args;
+	struct nfs_pgio_res *resp = &hdr->res;
+
+	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
+		return;
+	if (argp->offset + resp->count != fattr->size)
+		return;
+	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode))
+		return;
+	/* Set attribute barrier */
+	nfs_fattr_set_barrier(fattr);
+}
+
+void nfs_writeback_update_inode(struct nfs_pgio_header *hdr)
+{
+	struct nfs_fattr *fattr = hdr->res.fattr;
+	struct inode *inode = hdr->inode;
+
+	if (fattr == NULL)
+		return;
+	spin_lock(&inode->i_lock);
+	nfs_writeback_check_extend(hdr, fattr);
+	nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
+	spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL_GPL(nfs_writeback_update_inode);
+
 /*
  * This function is called when the WRITE call is complete.
  */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index f26e64e..59b1516 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -343,6 +343,7 @@ extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *,
 extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *);
 extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr);
+extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *);
 extern void nfs_access_set_mask(struct nfs_access_entry *, u32);