2 files changed, 112 insertions, 54 deletions

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 61ad269c825f..8dc921d83538 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -762,14 +762,14 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 {
 	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_ff_layout_mirror *mirror;
-	struct nfs4_pnfs_ds *ds;
+	struct nfs4_pnfs_ds *ds = ERR_PTR(-EAGAIN);
 	u32 idx;
 
 	/* mirrors are initially sorted by efficiency */
 	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
 		mirror = FF_LAYOUT_COMP(lseg, idx);
 		ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
-		if (!ds)
+		if (IS_ERR(ds))
 			continue;
 
 		if (check_device &&
@@ -777,10 +777,10 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 			continue;
 
 		*best_idx = idx;
-		return ds;
+		break;
 	}
 
-	return NULL;
+	return ds;
 }
 
 static struct nfs4_pnfs_ds *
@@ -942,7 +942,7 @@ retry:
 	for (i = 0; i < pgio->pg_mirror_count; i++) {
 		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
 		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror, true);
-		if (!ds) {
+		if (IS_ERR(ds)) {
 			if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 				goto out_mds;
 			pnfs_generic_pg_cleanup(pgio);
@@ -1105,6 +1105,7 @@ static void ff_layout_reset_read(struct nfs_pgio_header *hdr)
 }
 
 static int ff_layout_async_handle_error_v4(struct rpc_task *task,
+					   u32 op_status,
 					   struct nfs4_state *state,
 					   struct nfs_client *clp,
 					   struct pnfs_layout_segment *lseg,
@@ -1115,32 +1116,42 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 	struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table;
 
-	switch (task->tk_status) {
-	case -NFS4ERR_BADSESSION:
-	case -NFS4ERR_BADSLOT:
-	case -NFS4ERR_BAD_HIGH_SLOT:
-	case -NFS4ERR_DEADSESSION:
-	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-	case -NFS4ERR_SEQ_FALSE_RETRY:
-	case -NFS4ERR_SEQ_MISORDERED:
+	switch (op_status) {
+	case NFS4_OK:
+	case NFS4ERR_NXIO:
+		break;
+	case NFSERR_PERM:
+		if (!task->tk_xprt)
+			break;
+		xprt_force_disconnect(task->tk_xprt);
+		goto out_retry;
+	case NFS4ERR_BADSESSION:
+	case NFS4ERR_BADSLOT:
+	case NFS4ERR_BAD_HIGH_SLOT:
+	case NFS4ERR_DEADSESSION:
+	case NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+	case NFS4ERR_SEQ_FALSE_RETRY:
+	case NFS4ERR_SEQ_MISORDERED:
 		dprintk("%s ERROR %d, Reset session. Exchangeid "
 			"flags 0x%x\n", __func__, task->tk_status,
 			clp->cl_exchange_flags);
 		nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
-		break;
-	case -NFS4ERR_DELAY:
-	case -NFS4ERR_GRACE:
+		goto out_retry;
+	case NFS4ERR_DELAY:
+		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
+		fallthrough;
+	case NFS4ERR_GRACE:
 		rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX);
-		break;
-	case -NFS4ERR_RETRY_UNCACHED_REP:
-		break;
+		goto out_retry;
+	case NFS4ERR_RETRY_UNCACHED_REP:
+		goto out_retry;
 	/* Invalidate Layout errors */
-	case -NFS4ERR_PNFS_NO_LAYOUT:
-	case -ESTALE:           /* mapped NFS4ERR_STALE */
-	case -EBADHANDLE:       /* mapped NFS4ERR_BADHANDLE */
-	case -EISDIR:           /* mapped NFS4ERR_ISDIR */
-	case -NFS4ERR_FHEXPIRED:
-	case -NFS4ERR_WRONG_TYPE:
+	case NFS4ERR_PNFS_NO_LAYOUT:
+	case NFS4ERR_STALE:
+	case NFS4ERR_BADHANDLE:
+	case NFS4ERR_ISDIR:
+	case NFS4ERR_FHEXPIRED:
+	case NFS4ERR_WRONG_TYPE:
 		dprintk("%s Invalid layout error %d\n", __func__,
 			task->tk_status);
 		/*
@@ -1153,6 +1164,11 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 		pnfs_destroy_layout(NFS_I(inode));
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		goto reset;
+	default:
+		break;
+	}
+
+	switch (task->tk_status) {
 	/* RPC connection errors */
 	case -ENETDOWN:
 	case -ENETUNREACH:
@@ -1172,27 +1188,56 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 		nfs4_delete_deviceid(devid->ld, devid->nfs_client,
 				&devid->deviceid);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
-		fallthrough;
+		break;
 	default:
-		if (ff_layout_avoid_mds_available_ds(lseg))
-			return -NFS4ERR_RESET_TO_PNFS;
-reset:
-		dprintk("%s Retry through MDS. Error %d\n", __func__,
-			task->tk_status);
-		return -NFS4ERR_RESET_TO_MDS;
+		break;
 	}
+
+	if (ff_layout_avoid_mds_available_ds(lseg))
+		return -NFS4ERR_RESET_TO_PNFS;
+reset:
+	dprintk("%s Retry through MDS. Error %d\n", __func__,
+		task->tk_status);
+	return -NFS4ERR_RESET_TO_MDS;
+
+out_retry:
 	task->tk_status = 0;
 	return -EAGAIN;
 }
 
 /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
 static int ff_layout_async_handle_error_v3(struct rpc_task *task,
+					   u32 op_status,
 					   struct nfs_client *clp,
 					   struct pnfs_layout_segment *lseg,
 					   u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
+	switch (op_status) {
+	case NFS_OK:
+	case NFSERR_NXIO:
+		break;
+	case NFSERR_PERM:
+		if (!task->tk_xprt)
+			break;
+		xprt_force_disconnect(task->tk_xprt);
+		goto out_retry;
+	case NFSERR_ACCES:
+	case NFSERR_BADHANDLE:
+	case NFSERR_FBIG:
+	case NFSERR_IO:
+	case NFSERR_NOSPC:
+	case NFSERR_ROFS:
+	case NFSERR_STALE:
+		goto out_reset_to_pnfs;
+	case NFSERR_JUKEBOX:
+		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
+		goto out_retry;
+	default:
+		break;
+	}
+
 	switch (task->tk_status) {
 	/* File access problems. Don't mark the device as unavailable */
 	case -EACCES:
@@ -1216,6 +1261,7 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 		nfs4_delete_deviceid(devid->ld, devid->nfs_client,
 				&devid->deviceid);
 	}
+out_reset_to_pnfs:
 	/* FIXME: Need to prevent infinite looping here. */
 	return -NFS4ERR_RESET_TO_PNFS;
 out_retry:
@@ -1226,6 +1272,7 @@ out_retry:
 }
 
 static int ff_layout_async_handle_error(struct rpc_task *task,
+					u32 op_status,
 					struct nfs4_state *state,
 					struct nfs_client *clp,
 					struct pnfs_layout_segment *lseg,
@@ -1244,10 +1291,11 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
 
 	switch (vers) {
 	case 3:
-		return ff_layout_async_handle_error_v3(task, clp, lseg, idx);
-	case 4:
-		return ff_layout_async_handle_error_v4(task, state, clp,
+		return ff_layout_async_handle_error_v3(task, op_status, clp,
 						       lseg, idx);
+	case 4:
+		return ff_layout_async_handle_error_v4(task, op_status, state,
+						       clp, lseg, idx);
 	default:
 		/* should never happen */
 		WARN_ON_ONCE(1);
@@ -1300,6 +1348,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 	switch (status) {
 	case NFS4ERR_DELAY:
 	case NFS4ERR_GRACE:
+	case NFS4ERR_PERM:
 		break;
 	case NFS4ERR_NXIO:
 		ff_layout_mark_ds_unreachable(lseg, idx);
@@ -1329,10 +1378,11 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 					    hdr->args.offset, hdr->args.count,
 					    &hdr->res.op_status, OP_READ,
 					    task->tk_status);
-		trace_ff_layout_read_error(hdr);
+		trace_ff_layout_read_error(hdr, task->tk_status);
 	}
 
-	err = ff_layout_async_handle_error(task, hdr->args.context->state,
+	err = ff_layout_async_handle_error(task, hdr->res.op_status,
+					   hdr->args.context->state,
 					   hdr->ds_clp, hdr->lseg,
 					   hdr->pgio_mirror_idx);
 
@@ -1502,10 +1552,11 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
 					    hdr->args.offset, hdr->args.count,
 					    &hdr->res.op_status, OP_WRITE,
 					    task->tk_status);
-		trace_ff_layout_write_error(hdr);
+		trace_ff_layout_write_error(hdr, task->tk_status);
 	}
 
-	err = ff_layout_async_handle_error(task, hdr->args.context->state,
+	err = ff_layout_async_handle_error(task, hdr->res.op_status,
+					   hdr->args.context->state,
 					   hdr->ds_clp, hdr->lseg,
 					   hdr->pgio_mirror_idx);
 
@@ -1551,11 +1602,12 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 					    data->args.offset, data->args.count,
 					    &data->res.op_status, OP_COMMIT,
 					    task->tk_status);
-		trace_ff_layout_commit_error(data);
+		trace_ff_layout_commit_error(data, task->tk_status);
 	}
 
-	err = ff_layout_async_handle_error(task, NULL, data->ds_clp,
-					   data->lseg, data->ds_commit_index);
+	err = ff_layout_async_handle_error(task, data->res.op_status,
+					   NULL, data->ds_clp, data->lseg,
+					   data->ds_commit_index);
 
 	trace_nfs4_pnfs_commit_ds(data, err);
 	switch (err) {
@@ -1815,6 +1867,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	u32 idx = hdr->pgio_mirror_idx;
 	int vers;
 	struct nfs_fh *fh;
+	bool ds_fatal_error = false;
 
 	dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n",
 		__func__, hdr->inode->i_ino,
@@ -1822,8 +1875,10 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
-	if (!ds)
+	if (IS_ERR(ds)) {
+		ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
 		goto out_failed;
+	}
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
 						   hdr->inode);
@@ -1871,7 +1926,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	return PNFS_ATTEMPTED;
 
 out_failed:
-	if (ff_layout_avoid_mds_available_ds(lseg))
+	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
 		return PNFS_TRY_AGAIN;
 	trace_pnfs_mds_fallback_read_pagelist(hdr->inode,
 			hdr->args.offset, hdr->args.count,
@@ -1893,11 +1948,14 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	int vers;
 	struct nfs_fh *fh;
 	u32 idx = hdr->pgio_mirror_idx;
+	bool ds_fatal_error = false;
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
-	if (!ds)
+	if (IS_ERR(ds)) {
+		ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
 		goto out_failed;
+	}
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
 						   hdr->inode);
@@ -1948,7 +2006,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	return PNFS_ATTEMPTED;
 
 out_failed:
-	if (ff_layout_avoid_mds_available_ds(lseg))
+	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
 		return PNFS_TRY_AGAIN;
 	trace_pnfs_mds_fallback_write_pagelist(hdr->inode,
 			hdr->args.offset, hdr->args.count,
@@ -1991,7 +2049,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
-	if (!ds)
+	if (IS_ERR(ds))
 		goto out_err;
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e58bedfb1dcc..30365ec782bb 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -49,6 +49,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct nfs4_pnfs_ds_addr *da;
 	struct nfs4_ff_layout_ds *new_ds = NULL;
 	struct nfs4_ff_ds_version *ds_versions = NULL;
+	struct net *net = server->nfs_client->cl_net;
 	u32 mp_count;
 	u32 version_count;
 	__be32 *p;
@@ -80,8 +81,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 
 	for (i = 0; i < mp_count; i++) {
 		/* multipath ds */
-		da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
-					    &stream, gfp_flags);
+		da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
 		if (da)
 			list_add_tail(&da->da_node, &dsaddrs);
 	}
@@ -149,7 +149,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	new_ds->ds_versions = ds_versions;
 	new_ds->ds_versions_cnt = version_count;
 
-	new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+	new_ds->ds = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
 	if (!new_ds->ds)
 		goto out_err_drain_dsaddrs;
 
@@ -370,11 +370,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
 			  struct nfs4_ff_layout_mirror *mirror,
 			  bool fail_return)
 {
-	struct nfs4_pnfs_ds *ds = NULL;
+	struct nfs4_pnfs_ds *ds;
 	struct inode *ino = lseg->pls_layout->plh_inode;
 	struct nfs_server *s = NFS_SERVER(ino);
 	unsigned int max_payload;
-	int status;
+	int status = -EAGAIN;
 
 	if (!ff_layout_init_mirror_ds(lseg->pls_layout, mirror))
 		goto noconnect;
@@ -400,7 +400,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
 		 * keep ds_clp even if DS is local, so that if local IO cannot
 		 * proceed somehow, we can fall back to NFS whenever we want.
 		 */
-		nfs_local_probe(ds->ds_clp);
+		nfs_local_probe_async(ds->ds_clp);
 		max_payload =
 			nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
 				       NULL);
@@ -418,7 +418,7 @@ noconnect:
 	ff_layout_send_layouterror(lseg);
 	if (fail_return || !ff_layout_has_available_ds(lseg))
 		pnfs_error_mark_layout_for_return(ino, lseg);
-	ds = NULL;
+	ds = ERR_PTR(status);
 out:
 	return ds;
 }