--- zzzz-none-000/linux-3.10.107/fs/nfs/nfs4state.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/fs/nfs/nfs4state.c	2021-02-04 17:41:59.000000000 +0000
@@ -42,7 +42,6 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs_idmap.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/random.h>
@@ -57,6 +56,7 @@
 #include "callback.h"
 #include "delegation.h"
 #include "internal.h"
+#include "nfs4idmap.h"
 #include "nfs4session.h"
 #include "pnfs.h"
 #include "netns.h"
@@ -154,6 +154,19 @@
 	return cred;
 }
 
+static void nfs4_root_machine_cred(struct nfs_client *clp)
+{
+	struct rpc_cred *cred, *new;
+
+	new = rpc_lookup_machine_cred(NULL);
+	spin_lock(&clp->cl_lock);
+	cred = clp->cl_machine_cred;
+	clp->cl_machine_cred = new;
+	spin_unlock(&clp->cl_lock);
+	if (cred != NULL)
+		put_rpccred(cred);
+}
+
 static struct rpc_cred *
 nfs4_get_renew_cred_server_locked(struct nfs_server *server)
 {
@@ -202,32 +215,6 @@
 	return cred;
 }
 
-#if defined(CONFIG_NFS_V4_1)
-
-static int nfs41_setup_state_renewal(struct nfs_client *clp)
-{
-	int status;
-	struct nfs_fsinfo fsinfo;
-
-	if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
-		nfs4_schedule_state_renewal(clp);
-		return 0;
-	}
-
-	status = nfs4_proc_get_lease_time(clp, &fsinfo);
-	if (status == 0) {
-		/* Update lease time and schedule renewal */
-		spin_lock(&clp->cl_lock);
-		clp->cl_lease_time = fsinfo.lease_time * HZ;
-		clp->cl_last_renewal = jiffies;
-		spin_unlock(&clp->cl_lock);
-
-		nfs4_schedule_state_renewal(clp);
-	}
-
-	return status;
-}
-
 static void nfs4_end_drain_slot_table(struct nfs4_slot_table *tbl)
 {
 	if (test_and_clear_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
@@ -241,27 +228,23 @@
 {
 	struct nfs4_session *ses = clp->cl_session;
 
+	if (clp->cl_slot_tbl) {
+		nfs4_end_drain_slot_table(clp->cl_slot_tbl);
+		return;
+	}
+
 	if (ses != NULL) {
 		nfs4_end_drain_slot_table(&ses->bc_slot_table);
 		nfs4_end_drain_slot_table(&ses->fc_slot_table);
 	}
 }
 
-/*
- * Signal state manager thread if session fore channel is drained
- */
-void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl)
-{
-	if (nfs4_slot_tbl_draining(tbl))
-		complete(&tbl->complete);
-}
-
 static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl)
 {
 	set_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
 	spin_lock(&tbl->slot_tbl_lock);
 	if (tbl->highest_used_slotid != NFS4_NO_SLOT) {
-		INIT_COMPLETION(tbl->complete);
+		reinit_completion(&tbl->complete);
 		spin_unlock(&tbl->slot_tbl_lock);
 		return wait_for_completion_interruptible(&tbl->complete);
 	}
@@ -274,6 +257,9 @@
 	struct nfs4_session *ses = clp->cl_session;
 	int ret = 0;
 
+	if (clp->cl_slot_tbl)
+		return nfs4_drain_slot_tbl(clp->cl_slot_tbl);
+
 	/* back channel */
 	ret = nfs4_drain_slot_tbl(&ses->bc_slot_table);
 	if (ret)
@@ -282,6 +268,32 @@
 	return nfs4_drain_slot_tbl(&ses->fc_slot_table);
 }
 
+#if defined(CONFIG_NFS_V4_1)
+
+static int nfs41_setup_state_renewal(struct nfs_client *clp)
+{
+	int status;
+	struct nfs_fsinfo fsinfo;
+
+	if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
+		nfs4_schedule_state_renewal(clp);
+		return 0;
+	}
+
+	status = nfs4_proc_get_lease_time(clp, &fsinfo);
+	if (status == 0) {
+		/* Update lease time and schedule renewal */
+		spin_lock(&clp->cl_lock);
+		clp->cl_lease_time = fsinfo.lease_time * HZ;
+		clp->cl_last_renewal = jiffies;
+		spin_unlock(&clp->cl_lock);
+
+		nfs4_schedule_state_renewal(clp);
+	}
+
+	return status;
+}
+
 static void nfs41_finish_session_reset(struct nfs_client *clp)
 {
 	clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
@@ -297,7 +309,6 @@
 
 	if (test_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state))
 		goto do_confirm;
-	nfs4_begin_drain_session(clp);
 	status = nfs4_proc_exchange_id(clp, cred);
 	if (status != 0)
 		goto out;
@@ -334,67 +345,40 @@
 	status = nfs4_proc_exchange_id(clp, cred);
 	if (status != NFS4_OK)
 		return status;
-	set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
-
-	return nfs41_walk_client_list(clp, result, cred);
-}
 
-struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp)
-{
-	struct rpc_cred *cred;
+	status = nfs41_walk_client_list(clp, result, cred);
+	if (status < 0)
+		return status;
+	if (clp != *result)
+		return 0;
 
-	spin_lock(&clp->cl_lock);
-	cred = nfs4_get_machine_cred_locked(clp);
-	spin_unlock(&clp->cl_lock);
-	return cred;
+	/* Purge state if the client id was established in a prior instance */
+	if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)
+		set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+	else
+		set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	nfs4_schedule_state_manager(clp);
+	status = nfs_wait_client_init_complete(clp);
+	if (status < 0)
+		nfs_put_client(clp);
+	return status;
 }
 
 #endif /* CONFIG_NFS_V4_1 */
 
-static struct rpc_cred *
-nfs4_get_setclientid_cred_server(struct nfs_server *server)
-{
-	struct nfs_client *clp = server->nfs_client;
-	struct rpc_cred *cred = NULL;
-	struct nfs4_state_owner *sp;
-	struct rb_node *pos;
-
-	spin_lock(&clp->cl_lock);
-	pos = rb_first(&server->state_owners);
-	if (pos != NULL) {
-		sp = rb_entry(pos, struct nfs4_state_owner, so_server_node);
-		cred = get_rpccred(sp->so_cred);
-	}
-	spin_unlock(&clp->cl_lock);
-	return cred;
-}
-
 /**
- * nfs4_get_setclientid_cred - Acquire credential for a setclientid operation
+ * nfs4_get_clid_cred - Acquire credential for a setclientid operation
  * @clp: client state handle
  *
  * Returns an rpc_cred with reference count bumped, or NULL.
  */
-struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp)
+struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp)
 {
-	struct nfs_server *server;
 	struct rpc_cred *cred;
 
 	spin_lock(&clp->cl_lock);
 	cred = nfs4_get_machine_cred_locked(clp);
 	spin_unlock(&clp->cl_lock);
-	if (cred != NULL)
-		goto out;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
-		cred = nfs4_get_setclientid_cred_server(server);
-		if (cred != NULL)
-			break;
-	}
-	rcu_read_unlock();
-
-out:
 	return cred;
 }
 
@@ -816,21 +800,12 @@
  * that is compatible with current->files
  */
 static struct nfs4_lock_state *
-__nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid, unsigned int type)
+__nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
 {
 	struct nfs4_lock_state *pos;
 	list_for_each_entry(pos, &state->lock_states, ls_locks) {
-		if (type != NFS4_ANY_LOCK_TYPE && pos->ls_owner.lo_type != type)
+		if (pos->ls_owner != fl_owner)
 			continue;
-		switch (pos->ls_owner.lo_type) {
-		case NFS4_POSIX_LOCK_TYPE:
-			if (pos->ls_owner.lo_u.posix_owner != fl_owner)
-				continue;
-			break;
-		case NFS4_FLOCK_LOCK_TYPE:
-			if (pos->ls_owner.lo_u.flock_owner != fl_pid)
-				continue;
-		}
 		atomic_inc(&pos->ls_count);
 		return pos;
 	}
@@ -842,7 +817,7 @@
  * exists, return an uninitialized one.
  *
  */
-static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid, unsigned int type)
+static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
 {
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server = state->owner->so_server;
@@ -853,17 +828,7 @@
 	nfs4_init_seqid_counter(&lsp->ls_seqid);
 	atomic_set(&lsp->ls_count, 1);
 	lsp->ls_state = state;
-	lsp->ls_owner.lo_type = type;
-	switch (lsp->ls_owner.lo_type) {
-	case NFS4_FLOCK_LOCK_TYPE:
-		lsp->ls_owner.lo_u.flock_owner = fl_pid;
-		break;
-	case NFS4_POSIX_LOCK_TYPE:
-		lsp->ls_owner.lo_u.posix_owner = fl_owner;
-		break;
-	default:
-		goto out_free;
-	}
+	lsp->ls_owner = fl_owner;
 	lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, 0, 0, GFP_NOFS);
 	if (lsp->ls_seqid.owner_id < 0)
 		goto out_free;
@@ -886,13 +851,13 @@
  * exists, return an uninitialized one.
  *
  */
-static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner, pid_t pid, unsigned int type)
+static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner)
 {
 	struct nfs4_lock_state *lsp, *new = NULL;
 	
 	for(;;) {
 		spin_lock(&state->state_lock);
-		lsp = __nfs4_find_lock_state(state, owner, pid, type);
+		lsp = __nfs4_find_lock_state(state, owner);
 		if (lsp != NULL)
 			break;
 		if (new != NULL) {
@@ -903,7 +868,7 @@
 			break;
 		}
 		spin_unlock(&state->state_lock);
-		new = nfs4_alloc_lock_state(state, owner, pid, type);
+		new = nfs4_alloc_lock_state(state, owner);
 		if (new == NULL)
 			return NULL;
 	}
@@ -964,13 +929,7 @@
 
 	if (fl->fl_ops != NULL)
 		return 0;
-	if (fl->fl_flags & FL_POSIX)
-		lsp = nfs4_get_lock_state(state, fl->fl_owner, 0, NFS4_POSIX_LOCK_TYPE);
-	else if (fl->fl_flags & FL_FLOCK)
-		lsp = nfs4_get_lock_state(state, NULL, fl->fl_pid,
-				NFS4_FLOCK_LOCK_TYPE);
-	else
-		return -EINVAL;
+	lsp = nfs4_get_lock_state(state, fl->fl_owner);
 	if (lsp == NULL)
 		return -ENOMEM;
 	fl->fl_u.nfs4_fl.owner = lsp;
@@ -984,7 +943,6 @@
 {
 	struct nfs4_lock_state *lsp;
 	fl_owner_t fl_owner;
-	pid_t fl_pid;
 	int ret = -ENOENT;
 
 
@@ -995,15 +953,13 @@
 		goto out;
 
 	fl_owner = lockowner->l_owner;
-	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) {
+	lsp = __nfs4_find_lock_state(state, fl_owner);
+	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();
-		if (!list_empty(&lsp->ls_seqid.list))
-			ret = -EWOULDBLOCK;
 	}
 	spin_unlock(&state->state_lock);
 	nfs4_put_lock_state(lsp);
@@ -1011,10 +967,9 @@
 	return ret;
 }
 
-static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
 {
 	const nfs4_stateid *src;
-	int ret;
 	int seq;
 
 	do {
@@ -1023,12 +978,7 @@
 		if (test_bit(NFS_OPEN_STATE, &state->flags))
 			src = &state->open_stateid;
 		nfs4_stateid_copy(dst, src);
-		ret = 0;
-		smp_rmb();
-		if (!list_empty(&state->owner->so_seqid.list))
-			ret = -EWOULDBLOCK;
 	} while (read_seqretry(&state->seqlock, seq));
-	return ret;
 }
 
 /*
@@ -1038,13 +988,23 @@
 int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
 		fmode_t fmode, const struct nfs_lockowner *lockowner)
 {
-	int ret = 0;
-	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
+	int ret = nfs4_copy_lock_stateid(dst, state, lockowner);
+	if (ret == -EIO)
+		/* A lost lock - don't even consider delegations */
+		goto out;
+	/* returns true if delegation stateid found and copied */
+	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) {
+		ret = 0;
 		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);
+	nfs4_copy_open_stateid(dst, state);
+	ret = 0;
 out:
 	if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41))
 		dst->seqid = 0;
@@ -1056,11 +1016,11 @@
 	struct nfs_seqid *new;
 
 	new = kmalloc(sizeof(*new), gfp_mask);
-	if (new != NULL) {
-		new->sequence = counter;
-		INIT_LIST_HEAD(&new->list);
-		new->task = NULL;
-	}
+	if (new == NULL)
+		return ERR_PTR(-ENOMEM);
+	new->sequence = counter;
+	INIT_LIST_HEAD(&new->list);
+	new->task = NULL;
 	return new;
 }
 
@@ -1068,7 +1028,7 @@
 {
 	struct nfs_seqid_counter *sequence;
 
-	if (list_empty(&seqid->list))
+	if (seqid == NULL || list_empty(&seqid->list))
 		return;
 	sequence = seqid->sequence;
 	spin_lock(&sequence->lock);
@@ -1092,7 +1052,7 @@
 /*
  * Increment the seqid if the OPEN/OPEN_DOWNGRADE/CLOSE succeeded, or
  * failed with a seqid incrementing error -
- * see comments nfs_fs.h:seqid_mutating_error()
+ * see comments nfs4.h:seqid_mutating_error()
  */
 static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
 {
@@ -1124,31 +1084,37 @@
 
 void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid)
 {
-	struct nfs4_state_owner *sp = container_of(seqid->sequence,
-					struct nfs4_state_owner, so_seqid);
-	struct nfs_server *server = sp->so_server;
+	struct nfs4_state_owner *sp;
 
+	if (seqid == NULL)
+		return;
+
+	sp = container_of(seqid->sequence, struct nfs4_state_owner, so_seqid);
 	if (status == -NFS4ERR_BAD_SEQID)
 		nfs4_drop_state_owner(sp);
-	if (!nfs4_has_session(server->nfs_client))
+	if (!nfs4_has_session(sp->so_server->nfs_client))
 		nfs_increment_seqid(status, seqid);
 }
 
 /*
  * Increment the seqid if the LOCK/LOCKU succeeded, or
  * failed with a seqid incrementing error -
- * see comments nfs_fs.h:seqid_mutating_error()
+ * see comments nfs4.h:seqid_mutating_error()
  */
 void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid)
 {
-	nfs_increment_seqid(status, seqid);
+	if (seqid != NULL)
+		nfs_increment_seqid(status, seqid);
 }
 
 int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task)
 {
-	struct nfs_seqid_counter *sequence = seqid->sequence;
+	struct nfs_seqid_counter *sequence;
 	int status = 0;
 
+	if (seqid == NULL)
+		goto out;
+	sequence = seqid->sequence;
 	spin_lock(&sequence->lock);
 	seqid->task = task;
 	if (list_empty(&seqid->list))
@@ -1159,6 +1125,7 @@
 	status = -EAGAIN;
 unlock:
 	spin_unlock(&sequence->lock);
+out:
 	return status;
 }
 
@@ -1166,9 +1133,9 @@
 
 static void nfs4_clear_state_manager_bit(struct nfs_client *clp)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING);
 	rpc_wake_up(&clp->cl_rpcwaitq);
 }
@@ -1193,7 +1160,7 @@
 	snprintf(buf, sizeof(buf), "%s-manager",
 			rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR));
 	rcu_read_unlock();
-	task = kthread_run(nfs4_run_state_manager, clp, buf);
+	task = kthread_run(nfs4_run_state_manager, clp, "%s", buf);
 	if (IS_ERR(task)) {
 		printk(KERN_ERR "%s: kthread_run: %ld\n",
 			__func__, PTR_ERR(task));
@@ -1218,20 +1185,74 @@
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery);
 
+/**
+ * nfs4_schedule_migration_recovery - trigger migration recovery
+ *
+ * @server: FSID that is migrating
+ *
+ * Returns zero if recovery has started, otherwise a negative NFS4ERR
+ * value is returned.
+ */
+int nfs4_schedule_migration_recovery(const struct nfs_server *server)
+{
+	struct nfs_client *clp = server->nfs_client;
+
+	if (server->fh_expire_type != NFS4_FH_PERSISTENT) {
+		pr_err("NFS: volatile file handles not supported (server %s)\n",
+				clp->cl_hostname);
+		return -NFS4ERR_IO;
+	}
+
+	if (test_bit(NFS_MIG_FAILED, &server->mig_status))
+		return -NFS4ERR_IO;
+
+	dprintk("%s: scheduling migration recovery for (%llx:%llx) on %s\n",
+			__func__,
+			(unsigned long long)server->fsid.major,
+			(unsigned long long)server->fsid.minor,
+			clp->cl_hostname);
+
+	set_bit(NFS_MIG_IN_TRANSITION,
+			&((struct nfs_server *)server)->mig_status);
+	set_bit(NFS4CLNT_MOVED, &clp->cl_state);
+
+	nfs4_schedule_state_manager(clp);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nfs4_schedule_migration_recovery);
+
+/**
+ * nfs4_schedule_lease_moved_recovery - start lease-moved recovery
+ *
+ * @clp: server to check for moved leases
+ *
+ */
+void nfs4_schedule_lease_moved_recovery(struct nfs_client *clp)
+{
+	dprintk("%s: scheduling lease-moved recovery for client ID %llx on %s\n",
+		__func__, clp->cl_clientid, clp->cl_hostname);
+
+	set_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state);
+	nfs4_schedule_state_manager(clp);
+}
+EXPORT_SYMBOL_GPL(nfs4_schedule_lease_moved_recovery);
+
 int nfs4_wait_clnt_recover(struct nfs_client *clp)
 {
 	int res;
 
 	might_sleep();
 
-	res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
-			nfs_wait_bit_killable, TASK_KILLABLE);
+	atomic_inc(&clp->cl_count);
+	res = wait_on_bit_action(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
+				 nfs_wait_bit_killable, TASK_KILLABLE);
 	if (res)
-		return res;
-
+		goto out;
 	if (clp->cl_cons_state < 0)
-		return clp->cl_cons_state;
-	return 0;
+		res = clp->cl_cons_state;
+out:
+	nfs_put_client(clp);
+	return res;
 }
 
 int nfs4_client_recover_expired_lease(struct nfs_client *clp)
@@ -1288,7 +1309,7 @@
 	return 1;
 }
 
-static int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state)
+int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state)
 {
 	set_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags);
 	clear_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags);
@@ -1365,49 +1386,55 @@
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct file_lock *fl;
 	int status = 0;
+	struct file_lock_context *flctx = inode->i_flctx;
+	struct list_head *list;
 
-	if (inode->i_flock == NULL)
+	if (flctx == NULL)
 		return 0;
 
+	list = &flctx->flc_posix;
+
 	/* Guard against delegation returns and new lock/unlock calls */
 	down_write(&nfsi->rwsem);
-	/* Protect inode->i_flock using the BKL */
-	lock_flocks();
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
-			continue;
+	spin_lock(&flctx->flc_lock);
+restart:
+	list_for_each_entry(fl, list, fl_list) {
 		if (nfs_file_open_context(fl->fl_file)->state != state)
 			continue;
-		unlock_flocks();
+		spin_unlock(&flctx->flc_lock);
 		status = ops->recover_lock(state, fl);
 		switch (status) {
-			case 0:
-				break;
-			case -ESTALE:
-			case -NFS4ERR_ADMIN_REVOKED:
-			case -NFS4ERR_STALE_STATEID:
-			case -NFS4ERR_BAD_STATEID:
-			case -NFS4ERR_EXPIRED:
-			case -NFS4ERR_NO_GRACE:
-			case -NFS4ERR_STALE_CLIENTID:
-			case -NFS4ERR_BADSESSION:
-			case -NFS4ERR_BADSLOT:
-			case -NFS4ERR_BAD_HIGH_SLOT:
-			case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-				goto out;
-			default:
-				printk(KERN_ERR "NFS: %s: unhandled error %d. "
-					"Zeroing state\n", __func__, status);
-			case -ENOMEM:
-			case -NFS4ERR_DENIED:
-			case -NFS4ERR_RECLAIM_BAD:
-			case -NFS4ERR_RECLAIM_CONFLICT:
-				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
-				status = 0;
+		case 0:
+			break;
+		case -ESTALE:
+		case -NFS4ERR_ADMIN_REVOKED:
+		case -NFS4ERR_STALE_STATEID:
+		case -NFS4ERR_BAD_STATEID:
+		case -NFS4ERR_EXPIRED:
+		case -NFS4ERR_NO_GRACE:
+		case -NFS4ERR_STALE_CLIENTID:
+		case -NFS4ERR_BADSESSION:
+		case -NFS4ERR_BADSLOT:
+		case -NFS4ERR_BAD_HIGH_SLOT:
+		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+			goto out;
+		default:
+			pr_err("NFS: %s: unhandled error %d\n",
+					__func__, status);
+		case -ENOMEM:
+		case -NFS4ERR_DENIED:
+		case -NFS4ERR_RECLAIM_BAD:
+		case -NFS4ERR_RECLAIM_CONFLICT:
+			/* kill_proc(fl->fl_pid, SIGLOST, 1); */
+			status = 0;
 		}
-		lock_flocks();
+		spin_lock(&flctx->flc_lock);
 	}
-	unlock_flocks();
+	if (list == &flctx->flc_posix) {
+		list = &flctx->flc_flock;
+		goto restart;
+	}
+	spin_unlock(&flctx->flc_lock);
 out:
 	up_write(&nfsi->rwsem);
 	return status;
@@ -1428,7 +1455,7 @@
 	 * server that doesn't support a grace period.
 	 */
 	spin_lock(&sp->so_lock);
-	write_seqcount_begin(&sp->so_reclaim_seqcount);
+	raw_write_seqcount_begin(&sp->so_reclaim_seqcount);
 restart:
 	list_for_each_entry(state, &sp->so_states, open_states) {
 		if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
@@ -1443,14 +1470,16 @@
 		if (status >= 0) {
 			status = nfs4_reclaim_locks(state, ops);
 			if (status >= 0) {
-				spin_lock(&state->state_lock);
-				list_for_each_entry(lock, &state->lock_states, ls_locks) {
-					if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
-						pr_warn_ratelimited("NFS: "
-							"%s: Lock reclaim "
-							"failed!\n", __func__);
+				if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) {
+					spin_lock(&state->state_lock);
+					list_for_each_entry(lock, &state->lock_states, ls_locks) {
+						if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
+							pr_warn_ratelimited("NFS: "
+									    "%s: Lock reclaim "
+									    "failed!\n", __func__);
+					}
+					spin_unlock(&state->state_lock);
 				}
-				spin_unlock(&state->state_lock);
 				nfs4_put_open_state(state);
 				clear_bit(NFS_STATE_RECLAIM_NOGRACE,
 					&state->flags);
@@ -1460,18 +1489,15 @@
 		}
 		switch (status) {
 			default:
-				printk(KERN_ERR "NFS: %s: unhandled error %d. "
-					"Zeroing state\n", __func__, status);
+				printk(KERN_ERR "NFS: %s: unhandled error %d\n",
+					__func__, status);
 			case -ENOENT:
 			case -ENOMEM:
 			case -EACCES:
 			case -EROFS:
 			case -EIO:
 			case -ESTALE:
-				/*
-				 * Open state on this file cannot be recovered
-				 * All we can do is revert to using the zero stateid.
-				 */
+				/* Open state on this file cannot be recovered */
 				nfs4_state_mark_recovery_failed(state, status);
 				break;
 			case -EAGAIN:
@@ -1497,13 +1523,13 @@
 		spin_lock(&sp->so_lock);
 		goto restart;
 	}
-	write_seqcount_end(&sp->so_reclaim_seqcount);
+	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
 	return 0;
 out_err:
 	nfs4_put_open_state(state);
 	spin_lock(&sp->so_lock);
-	write_seqcount_end(&sp->so_reclaim_seqcount);
+	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
 	return status;
 }
@@ -1567,11 +1593,12 @@
 }
 
 static void nfs4_reclaim_complete(struct nfs_client *clp,
-				 const struct nfs4_state_recovery_ops *ops)
+				 const struct nfs4_state_recovery_ops *ops,
+				 struct rpc_cred *cred)
 {
 	/* Notify the server we're done reclaiming our state */
 	if (ops->reclaim_complete)
-		(void)ops->reclaim_complete(clp);
+		(void)ops->reclaim_complete(clp, cred);
 }
 
 static void nfs4_clear_reclaim_server(struct nfs_server *server)
@@ -1616,9 +1643,15 @@
 
 static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
 {
+	const struct nfs4_state_recovery_ops *ops;
+	struct rpc_cred *cred;
+
 	if (!nfs4_state_clear_reclaim_reboot(clp))
 		return;
-	nfs4_reclaim_complete(clp, clp->cl_mvops->reboot_recovery_ops);
+	ops = clp->cl_mvops->reboot_recovery_ops;
+	cred = nfs4_get_clid_cred(clp);
+	nfs4_reclaim_complete(clp, ops, cred);
+	put_rpccred(cred);
 }
 
 static void nfs_delegation_clear_all(struct nfs_client *clp)
@@ -1645,7 +1678,6 @@
 			nfs4_state_end_reclaim_reboot(clp);
 			break;
 		case -NFS4ERR_STALE_CLIENTID:
-		case -NFS4ERR_LEASE_MOVED:
 			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
 			nfs4_state_clear_reclaim_reboot(clp);
 			nfs4_state_start_reclaim_reboot(clp);
@@ -1696,7 +1728,8 @@
 			if (!test_and_clear_bit(ops->owner_flag_bit,
 							&sp->so_flags))
 				continue;
-			atomic_inc(&sp->so_count);
+			if (!atomic_inc_not_zero(&sp->so_count))
+				continue;
 			spin_unlock(&clp->cl_lock);
 			rcu_read_unlock();
 
@@ -1731,7 +1764,7 @@
 	cred = ops->get_state_renewal_cred_locked(clp);
 	spin_unlock(&clp->cl_lock);
 	if (cred == NULL) {
-		cred = nfs4_get_setclientid_cred(clp);
+		cred = nfs4_get_clid_cred(clp);
 		status = -ENOKEY;
 		if (cred == NULL)
 			goto out;
@@ -1802,7 +1835,8 @@
 		clp->cl_mvops->reboot_recovery_ops;
 	int status;
 
-	cred = ops->get_clid_cred(clp);
+	nfs4_begin_drain_session(clp);
+	cred = nfs4_get_clid_cred(clp);
 	if (cred == NULL)
 		return -ENOENT;
 	status = ops->establish_clid(clp, cred);
@@ -1846,6 +1880,168 @@
 	return 0;
 }
 
+/*
+ * Try remote migration of one FSID from a source server to a
+ * destination server.  The source server provides a list of
+ * potential destinations.
+ *
+ * Returns zero or a negative NFS4ERR status code.
+ */
+static int nfs4_try_migration(struct nfs_server *server, struct rpc_cred *cred)
+{
+	struct nfs_client *clp = server->nfs_client;
+	struct nfs4_fs_locations *locations = NULL;
+	struct inode *inode;
+	struct page *page;
+	int status, result;
+
+	dprintk("--> %s: FSID %llx:%llx on \"%s\"\n", __func__,
+			(unsigned long long)server->fsid.major,
+			(unsigned long long)server->fsid.minor,
+			clp->cl_hostname);
+
+	result = 0;
+	page = alloc_page(GFP_KERNEL);
+	locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
+	if (page == NULL || locations == NULL) {
+		dprintk("<-- %s: no memory\n", __func__);
+		goto out;
+	}
+
+	inode = d_inode(server->super->s_root);
+	result = nfs4_proc_get_locations(inode, locations, page, cred);
+	if (result) {
+		dprintk("<-- %s: failed to retrieve fs_locations: %d\n",
+			__func__, result);
+		goto out;
+	}
+
+	result = -NFS4ERR_NXIO;
+	if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) {
+		dprintk("<-- %s: No fs_locations data, migration skipped\n",
+			__func__);
+		goto out;
+	}
+
+	nfs4_begin_drain_session(clp);
+
+	status = nfs4_replace_transport(server, locations);
+	if (status != 0) {
+		dprintk("<-- %s: failed to replace transport: %d\n",
+			__func__, status);
+		goto out;
+	}
+
+	result = 0;
+	dprintk("<-- %s: migration succeeded\n", __func__);
+
+out:
+	if (page != NULL)
+		__free_page(page);
+	kfree(locations);
+	if (result) {
+		pr_err("NFS: migration recovery failed (server %s)\n",
+				clp->cl_hostname);
+		set_bit(NFS_MIG_FAILED, &server->mig_status);
+	}
+	return result;
+}
+
+/*
+ * Returns zero or a negative NFS4ERR status code.
+ */
+static int nfs4_handle_migration(struct nfs_client *clp)
+{
+	const struct nfs4_state_maintenance_ops *ops =
+				clp->cl_mvops->state_renewal_ops;
+	struct nfs_server *server;
+	struct rpc_cred *cred;
+
+	dprintk("%s: migration reported on \"%s\"\n", __func__,
+			clp->cl_hostname);
+
+	spin_lock(&clp->cl_lock);
+	cred = ops->get_state_renewal_cred_locked(clp);
+	spin_unlock(&clp->cl_lock);
+	if (cred == NULL)
+		return -NFS4ERR_NOENT;
+
+	clp->cl_mig_gen++;
+restart:
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		int status;
+
+		if (server->mig_gen == clp->cl_mig_gen)
+			continue;
+		server->mig_gen = clp->cl_mig_gen;
+
+		if (!test_and_clear_bit(NFS_MIG_IN_TRANSITION,
+						&server->mig_status))
+			continue;
+
+		rcu_read_unlock();
+		status = nfs4_try_migration(server, cred);
+		if (status < 0) {
+			put_rpccred(cred);
+			return status;
+		}
+		goto restart;
+	}
+	rcu_read_unlock();
+	put_rpccred(cred);
+	return 0;
+}
+
+/*
+ * Test each nfs_server on the clp's cl_superblocks list to see
+ * if it's moved to another server.  Stop when the server no longer
+ * returns NFS4ERR_LEASE_MOVED.
+ */
+static int nfs4_handle_lease_moved(struct nfs_client *clp)
+{
+	const struct nfs4_state_maintenance_ops *ops =
+				clp->cl_mvops->state_renewal_ops;
+	struct nfs_server *server;
+	struct rpc_cred *cred;
+
+	dprintk("%s: lease moved reported on \"%s\"\n", __func__,
+			clp->cl_hostname);
+
+	spin_lock(&clp->cl_lock);
+	cred = ops->get_state_renewal_cred_locked(clp);
+	spin_unlock(&clp->cl_lock);
+	if (cred == NULL)
+		return -NFS4ERR_NOENT;
+
+	clp->cl_mig_gen++;
+restart:
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		struct inode *inode;
+		int status;
+
+		if (server->mig_gen == clp->cl_mig_gen)
+			continue;
+		server->mig_gen = clp->cl_mig_gen;
+
+		rcu_read_unlock();
+
+		inode = d_inode(server->super->s_root);
+		status = nfs4_proc_fsid_present(inode, cred);
+		if (status != -NFS4ERR_MOVED)
+			goto restart;	/* wasn't this one */
+		if (nfs4_try_migration(server, cred) == -NFS4ERR_LEASE_MOVED)
+			goto restart;	/* there are more */
+		goto out;
+	}
+	rcu_read_unlock();
+
+out:
+	put_rpccred(cred);
+	return 0;
+}
+
 /**
  * nfs4_discover_server_trunking - Detect server IP address trunking
  *
@@ -1876,7 +2072,7 @@
 	mutex_lock(&nfs_clid_init_mutex);
 again:
 	status  = -ENOENT;
-	cred = ops->get_clid_cred(clp);
+	cred = nfs4_get_clid_cred(clp);
 	if (cred == NULL)
 		goto out_unlock;
 
@@ -1885,8 +2081,10 @@
 	switch (status) {
 	case 0:
 		break;
-	case -NFS4ERR_DELAY:
 	case -ETIMEDOUT:
+		if (clnt->cl_softrtry)
+			break;
+	case -NFS4ERR_DELAY:
 	case -EAGAIN:
 		ssleep(1);
 	case -NFS4ERR_STALE_CLIENTID:
@@ -1894,10 +2092,19 @@
 			__func__, status);
 		goto again;
 	case -EACCES:
-		if (i++)
+		if (i++ == 0) {
+			nfs4_root_machine_cred(clp);
+			goto again;
+		}
+		if (clnt->cl_auth->au_flavor == RPC_AUTH_UNIX)
 			break;
 	case -NFS4ERR_CLID_INUSE:
 	case -NFS4ERR_WRONGSEC:
+		/* No point in retrying if we already used RPC_AUTH_UNIX */
+		if (clnt->cl_auth->au_flavor == RPC_AUTH_UNIX) {
+			status = -EPERM;
+			break;
+		}
 		clnt = rpc_clone_client_set_auth(clnt, RPC_AUTH_UNIX);
 		if (IS_ERR(clnt)) {
 			status = PTR_ERR(clnt);
@@ -1949,23 +2156,13 @@
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery);
 
-static void nfs41_ping_server(struct nfs_client *clp)
+void nfs41_notify_server(struct nfs_client *clp)
 {
 	/* Use CHECK_LEASE to ping the server with a SEQUENCE */
 	set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
 	nfs4_schedule_state_manager(clp);
 }
 
-void nfs41_server_notify_target_slotid_update(struct nfs_client *clp)
-{
-	nfs41_ping_server(clp);
-}
-
-void nfs41_server_notify_highest_slotid_update(struct nfs_client *clp)
-{
-	nfs41_ping_server(clp);
-}
-
 static void nfs4_reset_all_state(struct nfs_client *clp)
 {
 	if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
@@ -1988,25 +2185,35 @@
 	}
 }
 
-static void nfs41_handle_state_revoked(struct nfs_client *clp)
+static void nfs41_handle_all_state_revoked(struct nfs_client *clp)
 {
 	nfs4_reset_all_state(clp);
 	dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname);
 }
 
+static void nfs41_handle_some_state_revoked(struct nfs_client *clp)
+{
+	nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce);
+	nfs4_schedule_state_manager(clp);
+
+	dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname);
+}
+
 static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp)
 {
-	/* This will need to handle layouts too */
-	nfs_expire_all_delegations(clp);
+	/* FIXME: For now, we destroy all layouts. */
+	pnfs_destroy_all_layouts(clp);
+	/* FIXME: For now, we test all delegations+open state+locks. */
+	nfs41_handle_some_state_revoked(clp);
 	dprintk("%s: Recallable state revoked on server %s!\n", __func__,
 			clp->cl_hostname);
 }
 
 static void nfs41_handle_backchannel_fault(struct nfs_client *clp)
 {
-	nfs_expire_all_delegations(clp);
-	if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
-		nfs4_schedule_state_manager(clp);
+	set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+	nfs4_schedule_state_manager(clp);
+
 	dprintk("%s: server %s declared a backchannel fault\n", __func__,
 			clp->cl_hostname);
 }
@@ -2028,11 +2235,13 @@
 
 	if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
 		nfs41_handle_server_reboot(clp);
-	if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
-			    SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
-			    SEQ4_STATUS_ADMIN_STATE_REVOKED |
-			    SEQ4_STATUS_LEASE_MOVED))
-		nfs41_handle_state_revoked(clp);
+	if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED))
+		nfs41_handle_all_state_revoked(clp);
+	if (flags & (SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
+			    SEQ4_STATUS_ADMIN_STATE_REVOKED))
+		nfs41_handle_some_state_revoked(clp);
+	if (flags & SEQ4_STATUS_LEASE_MOVED)
+		nfs4_schedule_lease_moved_recovery(clp);
 	if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
 		nfs41_handle_recallable_state_revoked(clp);
 	if (flags & SEQ4_STATUS_BACKCHANNEL_FAULT)
@@ -2050,7 +2259,7 @@
 	if (!nfs4_has_session(clp))
 		return 0;
 	nfs4_begin_drain_session(clp);
-	cred = nfs4_get_exchange_id_cred(clp);
+	cred = nfs4_get_clid_cred(clp);
 	status = nfs4_proc_destroy_session(clp->cl_session, cred);
 	switch (status) {
 	case 0:
@@ -2093,7 +2302,7 @@
 	if (!nfs4_has_session(clp))
 		return 0;
 	nfs4_begin_drain_session(clp);
-	cred = nfs4_get_exchange_id_cred(clp);
+	cred = nfs4_get_clid_cred(clp);
 	ret = nfs4_proc_bind_conn_to_session(clp, cred);
 	if (cred)
 		put_rpccred(cred);
@@ -2114,7 +2323,6 @@
 }
 #else /* CONFIG_NFS_V4_1 */
 static int nfs4_reset_session(struct nfs_client *clp) { return 0; }
-static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; }
 
 static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 {
@@ -2174,6 +2382,20 @@
 			continue;
 		}
 
+		if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) {
+			section = "migration";
+			status = nfs4_handle_migration(clp);
+			if (status < 0)
+				goto out_error;
+		}
+
+		if (test_and_clear_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state)) {
+			section = "lease moved";
+			status = nfs4_handle_lease_moved(clp);
+			if (status < 0)
+				goto out_error;
+		}
+
 		/* First recover reboot state... */
 		if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
 			section = "reclaim reboot";