NFSv4: Fix deadlock between nfs4_evict_inode() and nfs4_opendata_get_inode()

[ Upstream commit dfe1fe75e00e4c724ede7b9e593f6f680e446c5f ]

If the inode is being evicted, but has to return a delegation first,
then it can cause a deadlock in the corner case where the server reboots
before the delegreturn completes, but while the call to iget5_locked() in
nfs4_opendata_get_inode() is waiting for the inode free to complete.
Since the open call still holds a session slot, the reboot recovery
cannot proceed.

In order to break the logjam, we can turn the delegation return into a
privileged operation for the case where we're evicting the inode. We
know that in that case, there can be no other state recovery operation
that conflicts.

Reported-by: zhangxiaoxu (A) <zhangxiaoxu5@huawei.com>
Fixes: 5fcdfacc01f3 ("NFSv4: Return delegations synchronously in evict_inode")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index c4a98cbda6dd9d5c5c45aacaa655f95d05d5e9fa..5708b5a636f19f842154c40e784b361824e6077c 100644 (file)
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -203,6 +203,7 @@ struct nfs4_exception {
        struct inode *inode;
        nfs4_stateid *stateid;
        long timeout;
+       unsigned char task_is_privileged : 1;
        unsigned char delay : 1,
                      recovering : 1,
                      retry : 1;

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ff54ba3c824773cb3148862a43d18c32aa1f050f..ff48d7b23f079fb941103e5019ebc9224e6f1f22 100644 (file)
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -581,6 +581,8 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_
                goto out_retry;
        }
        if (exception->recovering) {
+               if (exception->task_is_privileged)
+                       return -EDEADLOCK;
                ret = nfs4_wait_clnt_recover(clp);
                if (test_bit(NFS_MIG_FAILED, &server->mig_status))
                        return -EIO;
@@ -606,6 +608,8 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server,
                goto out_retry;
        }
        if (exception->recovering) {
+               if (exception->task_is_privileged)
+                       return -EDEADLOCK;
                rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
                if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
                        rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
@@ -6231,6 +6235,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
        struct nfs4_exception exception = {
                .inode = data->inode,
                .stateid = &data->stateid,
+               .task_is_privileged = data->args.seq_args.sa_privileged,
        };
 
        if (!nfs4_sequence_done(task, &data->res.seq_res))
@@ -6349,7 +6354,6 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
        data = kzalloc(sizeof(*data), GFP_NOFS);
        if (data == NULL)
                return -ENOMEM;
-       nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, 0);
 
        nfs4_state_protect(server->nfs_client,
                        NFS_SP4_MACH_CRED_CLEANUP,
@@ -6377,6 +6381,12 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
                }
        }
 
+       if (!data->inode)
+               nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1,
+                                  1);
+       else
+               nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1,
+                                  0);
        task_setup_data.callback_data = data;
        msg.rpc_argp = &data->args;
        msg.rpc_resp = &data->res;