7 files changed, 121 insertions, 76 deletions

diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 9c3e117c3ed..4d016144256 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -44,7 +44,7 @@
 static inline sector_t normalize(sector_t s, int base)
 {
 	sector_t tmp = s; /* Since do_div modifies its argument */
-	return s - do_div(tmp, base);
+	return s - sector_div(tmp, base);
 }
 
 static inline sector_t normalize_up(sector_t s, int base)
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 57db3244f4d..4b49a8c6cca 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -656,16 +656,19 @@ int nfs_async_inode_return_delegation(struct inode *inode,
 
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (delegation == NULL)
+		goto out_enoent;
 
-	if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
-		rcu_read_unlock();
-		return -ENOENT;
-	}
+	if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
+		goto out_enoent;
 	nfs_mark_return_delegation(server, delegation);
 	rcu_read_unlock();
 
 	nfs_delegation_run_state_manager(clp);
 	return 0;
+out_enoent:
+	rcu_read_unlock();
+	return -ENOENT;
 }
 
 static struct inode *
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 4cbad5d6b27..02773aab43c 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -240,13 +240,11 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	error = nfs4_discover_server_trunking(clp, &old);
 	if (error < 0)
 		goto error;
-	nfs_put_client(clp);
-	if (clp != old) {
-		clp->cl_preserve_clid = true;
-		clp = old;
-	}
 
-	return clp;
+	if (clp != old)
+		clp->cl_preserve_clid = true;
+	nfs_put_client(clp);
+	return old;
 
 error:
 	nfs_mark_client_ready(clp, error);
@@ -324,9 +322,10 @@ int nfs40_walk_client_list(struct nfs_client *new,
 			prev = pos;
 
 			status = nfs_wait_client_init_complete(pos);
-			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
-				continue;
+				goto out;
+			status = -NFS4ERR_STALE_CLIENTID;
+			spin_lock(&nn->nfs_client_lock);
 		}
 		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
@@ -464,7 +463,8 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			}
 			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
-				continue;
+				break;
+			status = -NFS4ERR_STALE_CLIENTID;
 		}
 		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index 661a0f61121..678cb896453 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -797,34 +797,34 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr;
 	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
-
-	if (filelayout_test_devid_unavailable(devid))
-		return NULL;
+	struct nfs4_pnfs_ds *ret = ds;
 
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
 			__func__, ds_idx);
 		filelayout_mark_devid_invalid(devid);
-		return NULL;
+		goto out;
 	}
 	if (ds->ds_clp)
-		return ds;
+		goto out_test_devid;
 
 	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
 		struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
 		int err;
 
 		err = nfs4_ds_connect(s, ds);
-		if (err) {
+		if (err)
 			nfs4_mark_deviceid_unavailable(devid);
-			ds = NULL;
-		}
 		nfs4_clear_ds_conn_bit(ds);
 	} else {
 		/* Either ds is connected, or ds is NULL */
 		nfs4_wait_ds_connect(ds);
 	}
-	return ds;
+out_test_devid:
+	if (filelayout_test_devid_unavailable(devid))
+		ret = NULL;
+out:
+	return ret;
 }
 
 module_param(dataserver_retrans, uint, 0644);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d7ba5616989..1ae7dd5956c 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1160,29 +1160,24 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data)
 	int ret;
 
 	if (!data->rpc_done) {
-		ret = data->rpc_status;
-		goto err;
+		if (data->rpc_status) {
+			ret = data->rpc_status;
+			goto err;
+		}
+		/* cached opens have already been processed */
+		goto update;
 	}
 
-	ret = -ESTALE;
-	if (!(data->f_attr.valid & NFS_ATTR_FATTR_TYPE) ||
-	    !(data->f_attr.valid & NFS_ATTR_FATTR_FILEID) ||
-	    !(data->f_attr.valid & NFS_ATTR_FATTR_CHANGE))
-		goto err;
-
-	ret = -ENOMEM;
-	state = nfs4_get_open_state(inode, data->owner);
-	if (state == NULL)
-		goto err;
-
 	ret = nfs_refresh_inode(inode, &data->f_attr);
 	if (ret)
 		goto err;
 
 	if (data->o_res.delegation_type != 0)
 		nfs4_opendata_check_deleg(data, state);
+update:
 	update_open_stateid(state, &data->o_res.stateid, NULL,
 			    data->o_arg.fmode);
+	atomic_inc(&state->count);
 
 	return state;
 err:
@@ -3612,8 +3607,9 @@ static bool nfs4_stateid_is_current(nfs4_stateid *stateid,
 {
 	nfs4_stateid current_stateid;
 
-	if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode))
-		return false;
+	/* If the current stateid represents a lost lock, then exit */
+	if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode) == -EIO)
+		return true;
 	return nfs4_stateid_match(stateid, &current_stateid);
 }
 
@@ -4227,8 +4223,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 			dprintk("%s ERROR %d, Reset session\n", __func__,
 				task->tk_status);
 			nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
-			task->tk_status = 0;
-			return -EAGAIN;
+			goto wait_on_recovery;
 #endif /* CONFIG_NFS_V4_1 */
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
@@ -4406,11 +4401,17 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 		return;
 
 	switch (task->tk_status) {
-	case -NFS4ERR_STALE_STATEID:
-	case -NFS4ERR_EXPIRED:
 	case 0:
 		renew_lease(data->res.server, data->timestamp);
 		break;
+	case -NFS4ERR_ADMIN_REVOKED:
+	case -NFS4ERR_DELEG_REVOKED:
+	case -NFS4ERR_BAD_STATEID:
+	case -NFS4ERR_OLD_STATEID:
+	case -NFS4ERR_STALE_STATEID:
+	case -NFS4ERR_EXPIRED:
+		task->tk_status = 0;
+		break;
 	default:
 		if (nfs4_async_handle_error(task, data->res.server, NULL) ==
 				-EAGAIN) {
@@ -4572,6 +4573,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
 			status = 0;
 	}
 	request->fl_ops->fl_release_private(request);
+	request->fl_ops = NULL;
 out:
 	return status;
 }
@@ -6231,9 +6233,9 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layout_hdr *lo;
 	struct nfs4_state *state = NULL;
-	unsigned long timeo, giveup;
+	unsigned long timeo, now, giveup;
 
-	dprintk("--> %s\n", __func__);
+	dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
 
 	if (!nfs41_sequence_done(task, &lgp->res.seq_res))
 		goto out;
@@ -6241,12 +6243,38 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	switch (task->tk_status) {
 	case 0:
 		goto out;
+	/*
+	 * NFS4ERR_LAYOUTTRYLATER is a conflict with another client
+	 * (or clients) writing to the same RAID stripe
+	 */
 	case -NFS4ERR_LAYOUTTRYLATER:
+	/*
+	 * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
+	 * existing layout before getting a new one).
+	 */
 	case -NFS4ERR_RECALLCONFLICT:
 		timeo = rpc_get_timeout(task->tk_client);
 		giveup = lgp->args.timestamp + timeo;
-		if (time_after(giveup, jiffies))
-			task->tk_status = -NFS4ERR_DELAY;
+		now = jiffies;
+		if (time_after(giveup, now)) {
+			unsigned long delay;
+
+			/* Delay for:
+			 * - Not less then NFS4_POLL_RETRY_MIN.
+			 * - One last time a jiffie before we give up
+			 * - exponential backoff (time_now minus start_attempt)
+			 */
+			delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
+				    min((giveup - now - 1),
+					now - lgp->args.timestamp));
+
+			dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
+				__func__, delay);
+			rpc_delay(task, delay);
+			task->tk_status = 0;
+			rpc_restart_call_prepare(task);
+			goto out; /* Do not call nfs4_async_handle_error() */
+		}
 		break;
 	case -NFS4ERR_EXPIRED:
 	case -NFS4ERR_BAD_STATEID:
@@ -6682,7 +6710,7 @@ nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
 		switch (err) {
 		case 0:
 		case -NFS4ERR_WRONGSEC:
-		case -NFS4ERR_NOTSUPP:
+		case -ENOTSUPP:
 			goto out;
 		default:
 			err = nfs4_handle_exception(server, err, &exception);
@@ -6714,7 +6742,7 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	 * Fall back on "guess and check" method if
 	 * the server doesn't support SECINFO_NO_NAME
 	 */
-	if (err == -NFS4ERR_WRONGSEC || err == -NFS4ERR_NOTSUPP) {
+	if (err == -NFS4ERR_WRONGSEC || err == -ENOTSUPP) {
 		err = nfs4_find_root_sec(server, fhandle, info);
 		goto out_freepage;
 	}
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 1fab140764c..2c37442ed93 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -228,19 +228,8 @@ static int nfs41_setup_state_renewal(struct nfs_client *clp)
 	return status;
 }
 
-/*
- * Back channel returns NFS4ERR_DELAY for new requests when
- * NFS4_SESSION_DRAINING is set so there is no work to be done when draining
- * is ended.
- */
-static void nfs4_end_drain_session(struct nfs_client *clp)
+static void nfs4_end_drain_slot_table(struct nfs4_slot_table *tbl)
 {
-	struct nfs4_session *ses = clp->cl_session;
-	struct nfs4_slot_table *tbl;
-
-	if (ses == NULL)
-		return;
-	tbl = &ses->fc_slot_table;
 	if (test_and_clear_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
 		spin_lock(&tbl->slot_tbl_lock);
 		nfs41_wake_slot_table(tbl);
@@ -248,6 +237,16 @@ static void nfs4_end_drain_session(struct nfs_client *clp)
 	}
 }
 
+static void nfs4_end_drain_session(struct nfs_client *clp)
+{
+	struct nfs4_session *ses = clp->cl_session;
+
+	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
  */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 4be8d135ed6..988efb4caac 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3002,7 +3002,8 @@ out_overflow:
 	return -EIO;
 }
 
-static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+static bool __decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected,
+		int *nfs_retval)
 {
 	__be32 *p;
 	uint32_t opnum;
@@ -3012,19 +3013,32 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
 	if (unlikely(!p))
 		goto out_overflow;
 	opnum = be32_to_cpup(p++);
-	if (opnum != expected) {
-		dprintk("nfs: Server returned operation"
-			" %d but we issued a request for %d\n",
-				opnum, expected);
-		return -EIO;
-	}
+	if (unlikely(opnum != expected))
+		goto out_bad_operation;
 	nfserr = be32_to_cpup(p);
-	if (nfserr != NFS_OK)
-		return nfs4_stat_to_errno(nfserr);
-	return 0;
+	if (nfserr == NFS_OK)
+		*nfs_retval = 0;
+	else
+		*nfs_retval = nfs4_stat_to_errno(nfserr);
+	return true;
+out_bad_operation:
+	dprintk("nfs: Server returned operation"
+		" %d but we issued a request for %d\n",
+			opnum, expected);
+	*nfs_retval = -EREMOTEIO;
+	return false;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
-	return -EIO;
+	*nfs_retval = -EIO;
+	return false;
+}
+
+static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+{
+	int retval;
+
+	__decode_op_hdr(xdr, expected, &retval);
+	return retval;
 }
 
 /* Dummy routine */
@@ -4842,11 +4856,12 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
 	uint32_t savewords, bmlen, i;
 	int status;
 
-	status = decode_op_hdr(xdr, OP_OPEN);
-	if (status != -EIO)
-		nfs_increment_open_seqid(status, res->seqid);
-	if (!status)
-		status = decode_stateid(xdr, &res->stateid);
+	if (!__decode_op_hdr(xdr, OP_OPEN, &status))
+		return status;
+	nfs_increment_open_seqid(status, res->seqid);
+	if (status)
+		return status;
+	status = decode_stateid(xdr, &res->stateid);
 	if (unlikely(status))
 		return status;