NFS recover from destination server reboot for copies

Mark the destination state to indicate a server-side copy is
happening. On detecting a reboot and recovering open state check
if any state is engaged in a server-side copy, if so, find the
copy and mark it and then signal the waiting thread. Upon wakeup,
if copy was marked then propage EAGAIN to the nfsd_copy_file_range
and restart the copy from scratch.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

5 files changed, 41 insertions, 5 deletions

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index d158526d1044..ac5b784a1de0 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -140,6 +140,7 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 	struct nfs4_copy_state *copy;
 	int status = NFS4_OK;
 	bool found_pending = false;
+	struct nfs_open_context *ctx = nfs_file_open_context(dst);
 
 	spin_lock(&server->nfs_client->cl_lock);
 	list_for_each_entry(copy, &server->nfs_client->pending_cb_stateids,
@@ -163,6 +164,7 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 	}
 	memcpy(&copy->stateid, &res->write_res.stateid, NFS4_STATEID_SIZE);
 	init_completion(&copy->completion);
+	copy->parent_state = ctx->state;
 
 	list_add_tail(&copy->copies, &server->ss_copies);
 	spin_unlock(&server->nfs_client->cl_lock);
@@ -172,9 +174,10 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 	list_del_init(&copy->copies);
 	spin_unlock(&server->nfs_client->cl_lock);
 	if (status == -ERESTARTSYS) {
-		nfs42_do_offload_cancel_async(dst, &copy->stateid);
-		kfree(copy);
-		return status;
+		goto out_cancel;
+	} else if (copy->flags) {
+		status = -EAGAIN;
+		goto out_cancel;
 	}
 out:
 	res->write_res.count = copy->count;
@@ -183,6 +186,10 @@ out:
 
 	kfree(copy);
 	return status;
+out_cancel:
+	nfs42_do_offload_cancel_async(dst, &copy->stateid);
+	kfree(copy);
+	return status;
 }
 
 static int process_copy_commit(struct file *dst, loff_t pos_dst,
@@ -254,6 +261,9 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 		if (!res->commit_res.verf)
 			return -ENOMEM;
 	}
+	set_bit(NFS_CLNT_DST_SSC_COPY_STATE,
+		&dst_lock->open_context->state->flags);
+
 	status = nfs4_call_sync(server->client, server, &msg,
 				&args->seq_args, &res->seq_res, 0);
 	if (status == -ENOTSUPP)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index e87d414c40d0..542b2fce0447 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -163,6 +163,9 @@ enum {
 	NFS_STATE_RECOVERY_FAILED,	/* OPEN stateid state recovery failed */
 	NFS_STATE_MAY_NOTIFY_LOCK,	/* server may CB_NOTIFY_LOCK */
 	NFS_STATE_CHANGE_WAIT,		/* A state changing operation is outstanding */
+#ifdef CONFIG_NFS_V4_2
+	NFS_CLNT_DST_SSC_COPY_STATE,    /* dst server open state on client*/
+#endif /* CONFIG_NFS_V4_2 */
 };
 
 struct nfs4_state {
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 6c03d6b570b2..4288a6ecaf75 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -133,10 +133,15 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
 				    size_t count, unsigned int flags)
 {
+	ssize_t ret;
+
 	if (file_inode(file_in) == file_inode(file_out))
 		return -EINVAL;
-
-	return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+retry:
+	ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+	if (ret == -EAGAIN)
+		goto retry;
+	return ret;
 }
 
 static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index f1b27e895a94..b6882e09d0f4 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1589,6 +1589,22 @@ restart:
 				}
 				clear_bit(NFS_STATE_RECLAIM_NOGRACE,
 					&state->flags);
+#ifdef CONFIG_NFS_V4_2
+				if (test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags)) {
+					struct nfs4_copy_state *copy;
+
+					spin_lock(&sp->so_server->nfs_client->cl_lock);
+					list_for_each_entry(copy, &sp->so_server->ss_copies, copies) {
+						if (memcmp(&state->stateid.other, &copy->parent_state->stateid.other, NFS4_STATEID_SIZE))
+							continue;
+						copy->flags = 1;
+						complete(&copy->completion);
+						printk("AGLO: server rebooted waking up the copy\n");
+						break;
+					}
+					spin_unlock(&sp->so_server->nfs_client->cl_lock);
+				}
+#endif /* CONFIG_NFS_V4_2 */
 				nfs4_put_open_state(state);
 				spin_lock(&sp->so_lock);
 				goto restart;
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 645ad8e342f6..a0831e9d19c9 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -192,6 +192,8 @@ struct nfs4_copy_state {
 	uint64_t		count;
 	struct nfs_writeverf	verf;
 	int			error;
+	int			flags;
+	struct nfs4_state	*parent_state;
 };
 
 /*