7 files changed, 54 insertions, 21 deletions

diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 1db588a3f08b..90cb10d7b693 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -826,9 +826,10 @@ static void nfs3_proc_read_setup(struct nfs_read_data *data, struct rpc_message
         msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
 }
 
-static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
 {
         rpc_call_start(task);
+        return 0;
 }
 
 static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
@@ -847,9 +848,10 @@ static void nfs3_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
         msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE];
 }
 
-static void nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
 {
         rpc_call_start(task);
+        return 0;
 }
 
 static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index af2d5bf043f0..64118316a407 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -133,6 +133,7 @@ struct nfs4_lock_state {
         struct list_head        ls_locks;       /* Other lock stateids */
         struct nfs4_state *     ls_state;       /* Pointer to open state */
 #define NFS_LOCK_INITIALIZED 0
+#define NFS_LOCK_LOST        1
         unsigned long           ls_flags;
         struct nfs_seqid_counter        ls_seqid;
         nfs4_stateid            ls_stateid;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0122919a311a..1eb694e0f305 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4028,15 +4028,19 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message
         nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
 }
 
-static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
 {
         if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
                         &data->args.seq_args,
                         &data->res.seq_res,
                         task))
-                return;
-        nfs4_set_rw_stateid(&data->args.stateid, data->args.context,
-                        data->args.lock_context, FMODE_READ);
+                return 0;
+        if (nfs4_set_rw_stateid(&data->args.stateid, data->args.context,
+                                data->args.lock_context, FMODE_READ) == -EIO)
+                return -EIO;
+        if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
+                return -EIO;
+        return 0;
 }
 
 static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data)
@@ -4112,15 +4116,19 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
         nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
 }
 
-static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
 {
         if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
                         &data->args.seq_args,
                         &data->res.seq_res,
                         task))
-                return;
-        nfs4_set_rw_stateid(&data->args.stateid, data->args.context,
-                        data->args.lock_context, FMODE_WRITE);
+                return 0;
+        if (nfs4_set_rw_stateid(&data->args.stateid, data->args.context,
+                                data->args.lock_context, FMODE_WRITE) == -EIO)
+                return -EIO;
+        if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
+                return -EIO;
+        return 0;
 }
 
 static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
@@ -5515,6 +5523,12 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request
         return err;
 }
 
+bool recover_locks = true;
+module_param(recover_locks, bool, 0644);
+MODULE_PARM_DESC(recover_locks,
+                 "If the server reports that a lock might be lost, "
+                 "try to recovery it risking corruption.");
+
 static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request)
 {
         struct nfs_server *server = NFS_SERVER(state->inode);
@@ -5526,6 +5540,10 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request
         err = nfs4_set_lock_state(state, request);
         if (err != 0)
                 return err;
+        if (!recover_locks) {
+                set_bit(NFS_LOCK_LOST, &request->fl_u.nfs4_fl.owner->ls_flags);
+                return 0;
+        }
         do {
                 if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0)
                         return 0;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index da608ee8d5ff..cc14cbb78b73 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -969,7 +969,9 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
         fl_pid = lockowner->l_pid;
         spin_lock(&state->state_lock);
         lsp = __nfs4_find_lock_state(state, fl_owner, fl_pid, NFS4_ANY_LOCK_TYPE);
-        if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
+        if (lsp && test_bit(NFS_LOCK_LOST, &lsp->ls_flags))
+                ret = -EIO;
+        else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
                 nfs4_stateid_copy(dst, &lsp->ls_stateid);
                 ret = 0;
                 smp_rmb();
@@ -1009,11 +1011,17 @@ static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
 int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
                 fmode_t fmode, const struct nfs_lockowner *lockowner)
 {
-        int ret = 0;
+        int ret = nfs4_copy_lock_stateid(dst, state, lockowner);
+        if (ret == -EIO)
+                /* A lost lock - don't even consider delegations */
+                goto out;
         if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
                 goto out;
-        ret = nfs4_copy_lock_stateid(dst, state, lockowner);
         if (ret != -ENOENT)
+                /* nfs4_copy_delegation_stateid() didn't over-write
+                 * dst, so it still has the lock stateid which we now
+                 * choose to use.
+                 */
                 goto out;
         ret = nfs4_copy_open_stateid(dst, state);
 out:
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index c041c41f7a52..a8f57c728df5 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -623,9 +623,10 @@ static void nfs_proc_read_setup(struct nfs_read_data *data, struct rpc_message *
         msg->rpc_proc = &nfs_procedures[NFSPROC_READ];
 }
 
-static void nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
 {
         rpc_call_start(task);
+        return 0;
 }
 
 static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
@@ -644,9 +645,10 @@ static void nfs_proc_write_setup(struct nfs_write_data *data, struct rpc_message
         msg->rpc_proc = &nfs_procedures[NFSPROC_WRITE];
 }
 
-static void nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
 {
         rpc_call_start(task);
+        return 0;
 }
 
 static void nfs_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 70a26c651f09..31db5c366b81 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -513,9 +513,10 @@ static void nfs_readpage_release_common(void *calldata)
 void nfs_read_prepare(struct rpc_task *task, void *calldata)
 {
         struct nfs_read_data *data = calldata;
-        NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data);
-        if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
-                rpc_exit(task, -EIO);
+        int err;
+        err = NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data);
+        if (err)
+                rpc_exit(task, err);
 }
 
 static const struct rpc_call_ops nfs_read_common_ops = {
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 94eb4504731a..379450c8d04b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1294,9 +1294,10 @@ EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
 void nfs_write_prepare(struct rpc_task *task, void *calldata)
 {
         struct nfs_write_data *data = calldata;
-        NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data);
-        if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
-                rpc_exit(task, -EIO);
+        int err;
+        err = NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data);
+        if (err)
+                rpc_exit(task, err);
 }
 
 void nfs_commit_prepare(struct rpc_task *task, void *calldata)