1 files changed, 181 insertions, 65 deletions

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 3e724cb7ef01..4bea008dbebd 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -11,6 +11,7 @@
 #include <linux/nfs_mount.h>
 #include <linux/nfs_page.h>
 #include <linux/module.h>
+#include <linux/file.h>
 #include <linux/sched/mm.h>
 
 #include <linux/sunrpc/metrics.h>
@@ -162,6 +163,20 @@ decode_name(struct xdr_stream *xdr, u32 *id)
 	return 0;
 }
 
+static struct nfsd_file *
+ff_local_open_fh(struct pnfs_layout_segment *lseg, u32 ds_idx,
+		 struct nfs_client *clp, const struct cred *cred,
+		 struct nfs_fh *fh, fmode_t mode)
+{
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
+
+	return nfs_local_open_fh(clp, cred, fh, &mirror->nfl, mode);
+#else
+	return NULL;
+#endif
+}
+
 static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
 		const struct nfs4_ff_layout_mirror *m2)
 {
@@ -231,16 +246,18 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
 		spin_lock_init(&mirror->lock);
 		refcount_set(&mirror->ref, 1);
 		INIT_LIST_HEAD(&mirror->mirrors);
+		nfs_localio_file_init(&mirror->nfl);
 	}
 	return mirror;
 }
 
 static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
 {
-	const struct cred	*cred;
+	const struct cred *cred;
 
 	ff_layout_remove_mirror(mirror);
 	kfree(mirror->fh_versions);
+	nfs_close_local_fh(&mirror->nfl);
 	cred = rcu_access_pointer(mirror->ro_cred);
 	put_cred(cred);
 	cred = rcu_access_pointer(mirror->rw_cred);
@@ -823,14 +840,6 @@ ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio,
 }
 
 static void
-ff_layout_pg_check_layout(struct nfs_pageio_descriptor *pgio,
-			  struct nfs_page *req)
-{
-	pnfs_generic_pg_check_layout(pgio);
-	pnfs_generic_pg_check_range(pgio, req);
-}
-
-static void
 ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			struct nfs_page *req)
 {
@@ -839,8 +848,11 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	struct nfs4_pnfs_ds *ds;
 	u32 ds_idx;
 
+	if (NFS_SERVER(pgio->pg_inode)->flags &
+			(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
+		pgio->pg_maxretrans = io_maxretrans;
 retry:
-	ff_layout_pg_check_layout(pgio, req);
+	pnfs_generic_pg_check_layout(pgio, req);
 	/* Use full layout for now */
 	if (!pgio->pg_lseg) {
 		ff_layout_pg_get_read(pgio, req, false);
@@ -852,6 +864,8 @@ retry:
 		if (!pgio->pg_lseg)
 			goto out_nolseg;
 	}
+	/* Reset wb_nio, since getting layout segment was successful */
+	req->wb_nio = 0;
 
 	ds = ff_layout_get_ds_for_read(pgio, &ds_idx);
 	if (!ds) {
@@ -868,14 +882,24 @@ retry:
 	pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
 
 	pgio->pg_mirror_idx = ds_idx;
-
-	if (NFS_SERVER(pgio->pg_inode)->flags &
-			(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
-		pgio->pg_maxretrans = io_maxretrans;
 	return;
 out_nolseg:
-	if (pgio->pg_error < 0)
-		return;
+	if (pgio->pg_error < 0) {
+		if (pgio->pg_error != -EAGAIN)
+			return;
+		/* Retry getting layout segment if lower layer returned -EAGAIN */
+		if (pgio->pg_maxretrans && req->wb_nio++ > pgio->pg_maxretrans) {
+			if (NFS_SERVER(pgio->pg_inode)->flags & NFS_MOUNT_SOFTERR)
+				pgio->pg_error = -ETIMEDOUT;
+			else
+				pgio->pg_error = -EIO;
+			return;
+		}
+		pgio->pg_error = 0;
+		/* Sleep for 1 second before retrying */
+		ssleep(1);
+		goto retry;
+	}
 out_mds:
 	trace_pnfs_mds_fallback_pg_init_read(pgio->pg_inode,
 			0, NFS4_MAX_UINT64, IOMODE_READ,
@@ -895,7 +919,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	u32 i;
 
 retry:
-	ff_layout_pg_check_layout(pgio, req);
+	pnfs_generic_pg_check_layout(pgio, req);
 	if (!pgio->pg_lseg) {
 		pgio->pg_lseg =
 			pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req),
@@ -1081,6 +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,
@@ -1091,32 +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);
 		/*
@@ -1129,11 +1164,20 @@ 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:
+		if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
+			return -NFS4ERR_FATAL_IOERROR;
+		fallthrough;
 	case -ECONNREFUSED:
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
-	case -ENETUNREACH:
 	case -EIO:
 	case -ETIMEDOUT:
 	case -EPIPE:
@@ -1144,26 +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:
@@ -1176,12 +1250,18 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 	case -EJUKEBOX:
 		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
 		goto out_retry;
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
+			return -NFS4ERR_FATAL_IOERROR;
+		fallthrough;
 	default:
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
 		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:
@@ -1192,6 +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,
@@ -1210,10 +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, 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);
@@ -1240,6 +1322,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 		case -ECONNRESET:
 		case -EHOSTDOWN:
 		case -EHOSTUNREACH:
+		case -ENETDOWN:
 		case -ENETUNREACH:
 		case -EADDRINUSE:
 		case -ENOBUFS:
@@ -1265,6 +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);
@@ -1294,10 +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);
 
@@ -1313,6 +1398,9 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 		return task->tk_status;
 	case -EAGAIN:
 		goto out_eagain;
+	case -NFS4ERR_FATAL_IOERROR:
+		task->tk_status = -EIO;
+		return 0;
 	}
 
 	return 0;
@@ -1464,10 +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);
 
@@ -1483,6 +1572,9 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
 		return task->tk_status;
 	case -EAGAIN:
 		return -EAGAIN;
+	case -NFS4ERR_FATAL_IOERROR:
+		task->tk_status = -EIO;
+		return 0;
 	}
 
 	if (hdr->res.verf->committed == NFS_FILE_SYNC ||
@@ -1510,11 +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) {
@@ -1527,6 +1620,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 	case -EAGAIN:
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
+	case -NFS4ERR_FATAL_IOERROR:
+		task->tk_status = -EIO;
+		return 0;
 	}
 
 	ff_layout_set_layoutcommit(data->inode, data->lseg, data->lwb);
@@ -1764,6 +1860,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	struct pnfs_layout_segment *lseg = hdr->lseg;
 	struct nfs4_pnfs_ds *ds;
 	struct rpc_clnt *ds_clnt;
+	struct nfsd_file *localio;
 	struct nfs4_ff_layout_mirror *mirror;
 	const struct cred *ds_cred;
 	loff_t offset = hdr->args.offset;
@@ -1810,11 +1907,18 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	hdr->args.offset = offset;
 	hdr->mds_offset = offset;
 
+	/* Start IO accounting for local read */
+	localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh, FMODE_READ);
+	if (localio) {
+		hdr->task.tk_start = ktime_get();
+		ff_layout_read_record_layoutstats_start(&hdr->task, hdr);
+	}
+
 	/* Perform an asynchronous read to ds */
 	nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
 			  vers == 3 ? &ff_layout_read_call_ops_v3 :
 				      &ff_layout_read_call_ops_v4,
-			  0, RPC_TASK_SOFTCONN);
+			  0, RPC_TASK_SOFTCONN, localio);
 	put_cred(ds_cred);
 	return PNFS_ATTEMPTED;
 
@@ -1834,6 +1938,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	struct pnfs_layout_segment *lseg = hdr->lseg;
 	struct nfs4_pnfs_ds *ds;
 	struct rpc_clnt *ds_clnt;
+	struct nfsd_file *localio;
 	struct nfs4_ff_layout_mirror *mirror;
 	const struct cred *ds_cred;
 	loff_t offset = hdr->args.offset;
@@ -1878,11 +1983,19 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	 */
 	hdr->args.offset = offset;
 
+	/* Start IO accounting for local write */
+	localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
+				   FMODE_READ|FMODE_WRITE);
+	if (localio) {
+		hdr->task.tk_start = ktime_get();
+		ff_layout_write_record_layoutstats_start(&hdr->task, hdr);
+	}
+
 	/* Perform an asynchronous write */
 	nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
 			  vers == 3 ? &ff_layout_write_call_ops_v3 :
 				      &ff_layout_write_call_ops_v4,
-			  sync, RPC_TASK_SOFTCONN);
+			  sync, RPC_TASK_SOFTCONN, localio);
 	put_cred(ds_cred);
 	return PNFS_ATTEMPTED;
 
@@ -1916,6 +2029,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	struct pnfs_layout_segment *lseg = data->lseg;
 	struct nfs4_pnfs_ds *ds;
 	struct rpc_clnt *ds_clnt;
+	struct nfsd_file *localio;
 	struct nfs4_ff_layout_mirror *mirror;
 	const struct cred *ds_cred;
 	u32 idx;
@@ -1954,10 +2068,18 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	if (fh)
 		data->args.fh = fh;
 
+	/* Start IO accounting for local commit */
+	localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
+				   FMODE_READ|FMODE_WRITE);
+	if (localio) {
+		data->task.tk_start = ktime_get();
+		ff_layout_commit_record_layoutstats_start(&data->task, data);
+	}
+
 	ret = nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
 				   vers == 3 ? &ff_layout_commit_call_ops_v3 :
 					       &ff_layout_commit_call_ops_v4,
-				   how, RPC_TASK_SOFTCONN);
+				   how, RPC_TASK_SOFTCONN, localio);
 	put_cred(ds_cred);
 	return ret;
 out_err:
@@ -2095,12 +2217,6 @@ static int ff_layout_encode_ioerr(struct xdr_stream *xdr,
 }
 
 static void
-encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
-{
-	WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
-}
-
-static void
 ff_layout_encode_ff_iostat_head(struct xdr_stream *xdr,
 			    const nfs4_stateid *stateid,
 			    const struct nfs42_layoutstat_devinfo *devinfo)
@@ -2556,7 +2672,7 @@ ff_layout_set_layoutdriver(struct nfs_server *server,
 		const struct nfs_fh *dummy)
 {
 #if IS_ENABLED(CONFIG_NFS_V4_2)
-	server->caps |= NFS_CAP_LAYOUTSTATS;
+	server->caps |= NFS_CAP_LAYOUTSTATS | NFS_CAP_REBOOT_LAYOUTRETURN;
 #endif
 	return 0;
 }