Merge branch 'flexfiles'

* flexfiles: (53 commits)
  pnfs: lookup new lseg at lseg boundary
  nfs41: .init_read and .init_write can be called with valid pg_lseg
  pnfs: Update documentation on the Layout Drivers
  pnfs/flexfiles: Add the FlexFile Layout Driver
  nfs: count DIO good bytes correctly with mirroring
  nfs41: wait for LAYOUTRETURN before retrying LAYOUTGET
  nfs: add a helper to set NFS_ODIRECT_RESCHED_WRITES to direct writes
  nfs41: add NFS_LAYOUT_RETRY_LAYOUTGET to layout header flags
  nfs/flexfiles: send layoutreturn before freeing lseg
  nfs41: introduce NFS_LAYOUT_RETURN_BEFORE_CLOSE
  nfs41: allow async version layoutreturn
  nfs41: add range to layoutreturn args
  pnfs: allow LD to ask to resend read through pnfs
  nfs: add nfs_pgio_current_mirror helper
  nfs: only reset desc->pg_mirror_idx when mirroring is supported
  nfs41: add a debug warning if we destroy an unempty layout
  pnfs: fail comparison when bucket verifier not set
  nfs: mirroring support for direct io
  nfs: add mirroring support to pgio layer
  pnfs: pass ds_commit_idx through the commit path
  ...

Conflicts:
	fs/nfs/pnfs.c
	fs/nfs/pnfs.h

Documentation/filesystems/nfs/pnfs.txt

@@ -57,15 +57,16 @@ bit is set, preventing any new lsegs from being added.
 layout drivers
 --------------
 
-PNFS utilizes what is called layout drivers. The STD defines 3 basic
+PNFS utilizes what is called layout drivers. The STD defines 4 basic
-layout types: "files" "objects" and "blocks". For each of these types
+layout types: "files", "objects", "blocks", and "flexfiles". For each
-there is a layout-driver with a common function-vectors table which
+of these types there is a layout-driver with a common function-vectors
-are called by the nfs-client pnfs-core to implement the different layout
+table which are called by the nfs-client pnfs-core to implement the
-types.
+different layout types.
 
-Files-layout-driver code is in: fs/nfs/nfs4filelayout.c && nfs4filelayoutdev.c
+Files-layout-driver code is in: fs/nfs/filelayout/.. directory
 Objects-layout-deriver code is in: fs/nfs/objlayout/.. directory
 Blocks-layout-deriver code is in: fs/nfs/blocklayout/.. directory
+Flexfiles-layout-driver code is in: fs/nfs/flexfilelayout/.. directory
 
 objects-layout setup
 --------------------

fs/nfs/Kconfig

@@ -128,6 +128,11 @@ config PNFS_OBJLAYOUT
 	depends on NFS_V4_1 && SCSI_OSD_ULD
 	default NFS_V4
 
+config PNFS_FLEXFILE_LAYOUT
+	tristate
+	depends on NFS_V4_1 && NFS_V3
+	default m
+
 config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
 	string "NFSv4.1 Implementation ID Domain"
 	depends on NFS_V4_1

fs/nfs/Makefile

@@ -27,9 +27,10 @@ nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o
 	  dns_resolve.o nfs4trace.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
 nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
-nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
+nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o pnfs_nfs.o
 nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
 obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
 obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
+obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/

fs/nfs/blocklayout/blocklayout.c

@@ -860,12 +860,14 @@ static const struct nfs_pageio_ops bl_pg_read_ops = {
 	.pg_init = bl_pg_init_read,
 	.pg_test = bl_pg_test_read,
 	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static const struct nfs_pageio_ops bl_pg_write_ops = {
 	.pg_init = bl_pg_init_write,
 	.pg_test = bl_pg_test_write,
 	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static struct pnfs_layoutdriver_type blocklayout_type = {

fs/nfs/direct.c

@@ -66,6 +66,10 @@ static struct kmem_cache *nfs_direct_cachep;
 /*
  * This represents a set of asynchronous requests that we're waiting on
  */
+struct nfs_direct_mirror {
+	ssize_t count;
+};
+
 struct nfs_direct_req {
 	struct kref		kref;		/* release manager */
 
@@ -78,8 +82,13 @@ struct nfs_direct_req {
 	/* completion state */
 	atomic_t		io_count;	/* i/os we're waiting for */
 	spinlock_t		lock;		/* protect completion state */
+
+	struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX];
+	int			mirror_count;
+
 	ssize_t			count,		/* bytes actually processed */
 				bytes_left,	/* bytes left to be sent */
+				io_start,	/* start of IO */
 				error;		/* any reported error */
 	struct completion	completion;	/* wait for i/o completion */
 
@@ -108,26 +117,56 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
 	return atomic_dec_and_test(&dreq->io_count);
 }
 
+void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq)
+{
+	dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+}
+EXPORT_SYMBOL_GPL(nfs_direct_set_resched_writes);
+
+static void
+nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
+{
+	int i;
+	ssize_t count;
+
+	WARN_ON_ONCE(hdr->pgio_mirror_idx >= dreq->mirror_count);
+
+	count = dreq->mirrors[hdr->pgio_mirror_idx].count;
+	if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
+		count = hdr->io_start + hdr->good_bytes - dreq->io_start;
+		dreq->mirrors[hdr->pgio_mirror_idx].count = count;
+	}
+
+	/* update the dreq->count by finding the minimum agreed count from all
+	 * mirrors */
+	count = dreq->mirrors[0].count;
+
+	for (i = 1; i < dreq->mirror_count; i++)
+		count = min(count, dreq->mirrors[i].count);
+
+	dreq->count = count;
+}
+
 /*
  * nfs_direct_select_verf - select the right verifier
  * @dreq - direct request possibly spanning multiple servers
  * @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs
- * @ds_idx - index of data server in data server list, only valid if ds_clp set
+ * @commit_idx - commit bucket index for the DS
  *
  * returns the correct verifier to use given the role of the server
  */
 static struct nfs_writeverf *
 nfs_direct_select_verf(struct nfs_direct_req *dreq,
 		       struct nfs_client *ds_clp,
-		       int ds_idx)
+		       int commit_idx)
 {
 	struct nfs_writeverf *verfp = &dreq->verf;
 
 #ifdef CONFIG_NFS_V4_1
 	if (ds_clp) {
 		/* pNFS is in use, use the DS verf */
-		if (ds_idx >= 0 && ds_idx < dreq->ds_cinfo.nbuckets)
+		if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets)
-			verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf;
+			verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf;
 		else
 			WARN_ON_ONCE(1);
 	}
@@ -148,8 +187,7 @@ static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq,
 {
 	struct nfs_writeverf *verfp;
 
-	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp,
+	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx);
-				      hdr->ds_idx);
 	WARN_ON_ONCE(verfp->committed >= 0);
 	memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
 	WARN_ON_ONCE(verfp->committed < 0);
@@ -169,8 +207,7 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
 {
 	struct nfs_writeverf *verfp;
 
-	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp,
+	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx);
-					 hdr->ds_idx);
 	if (verfp->committed < 0) {
 		nfs_direct_set_hdr_verf(dreq, hdr);
 		return 0;
@@ -193,7 +230,11 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
 
 	verfp = nfs_direct_select_verf(dreq, data->ds_clp,
 					 data->ds_commit_index);
-	WARN_ON_ONCE(verfp->committed < 0);
+
+	/* verifier not set so always fail */
+	if (verfp->committed < 0)
+		return 1;
+
 	return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf));
 }
 
@@ -249,6 +290,18 @@ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 	cinfo->completion_ops = &nfs_direct_commit_completion_ops;
 }
 
+static inline void nfs_direct_setup_mirroring(struct nfs_direct_req *dreq,
+					     struct nfs_pageio_descriptor *pgio,
+					     struct nfs_page *req)
+{
+	int mirror_count = 1;
+
+	if (pgio->pg_ops->pg_get_mirror_count)
+		mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req);
+
+	dreq->mirror_count = mirror_count;
+}
+
 static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 {
 	struct nfs_direct_req *dreq;
@@ -263,6 +316,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 	INIT_LIST_HEAD(&dreq->mds_cinfo.list);
 	dreq->verf.committed = NFS_INVALID_STABLE_HOW;	/* not set yet */
 	INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
+	dreq->mirror_count = 1;
 	spin_lock_init(&dreq->lock);
 
 	return dreq;
@@ -369,7 +423,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0))
 		dreq->error = hdr->error;
 	else
-		dreq->count += hdr->good_bytes;
+		nfs_direct_good_bytes(dreq, hdr);
+
 	spin_unlock(&dreq->lock);
 
 	while (!list_empty(&hdr->pages)) {
@@ -547,6 +602,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 
 	dreq->inode = inode;
 	dreq->bytes_left = count;
+	dreq->io_start = pos;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
 	if (IS_ERR(l_ctx)) {
@@ -579,6 +635,20 @@ out:
 	return result;
 }
 
+static void
+nfs_direct_write_scan_commit_list(struct inode *inode,
+				  struct list_head *list,
+				  struct nfs_commit_info *cinfo)
+{
+	spin_lock(cinfo->lock);
+#ifdef CONFIG_NFS_V4_1
+	if (cinfo->ds != NULL && cinfo->ds->nwritten != 0)
+		NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
+#endif
+	nfs_scan_commit_list(&cinfo->mds->list, list, cinfo, 0);
+	spin_unlock(cinfo->lock);
+}
+
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 {
 	struct nfs_pageio_descriptor desc;
@@ -586,20 +656,23 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	LIST_HEAD(reqs);
 	struct nfs_commit_info cinfo;
 	LIST_HEAD(failed);
+	int i;
 
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
-	pnfs_recover_commit_reqs(dreq->inode, &reqs, &cinfo);
+	nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
-	spin_lock(cinfo.lock);
-	nfs_scan_commit_list(&cinfo.mds->list, &reqs, &cinfo, 0);
-	spin_unlock(cinfo.lock);
 
 	dreq->count = 0;
+	for (i = 0; i < dreq->mirror_count; i++)
+		dreq->mirrors[i].count = 0;
 	get_dreq(dreq);
 
 	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 
+	req = nfs_list_entry(reqs.next);
+	nfs_direct_setup_mirroring(dreq, &desc, req);
+
 	list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
 		if (!nfs_pageio_add_request(&desc, req)) {
 			nfs_list_remove_request(req);
@@ -646,7 +719,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 		nfs_list_remove_request(req);
 		if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) {
 			/* Note the rewrite will go through mds */
-			nfs_mark_request_commit(req, NULL, &cinfo);
+			nfs_mark_request_commit(req, NULL, &cinfo, 0);
 		} else
 			nfs_release_request(req);
 		nfs_unlock_and_release_request(req);
@@ -721,7 +794,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 		dreq->error = hdr->error;
 	}
 	if (dreq->error == 0) {
-		dreq->count += hdr->good_bytes;
+		nfs_direct_good_bytes(dreq, hdr);
 		if (nfs_write_need_commit(hdr)) {
 			if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
 				request_commit = true;
@@ -745,7 +818,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 		nfs_list_remove_request(req);
 		if (request_commit) {
 			kref_get(&req->wb_kref);
-			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+			nfs_mark_request_commit(req, hdr->lseg, &cinfo,
+				hdr->ds_commit_idx);
 		}
 		nfs_unlock_and_release_request(req);
 	}
@@ -826,6 +900,9 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 				result = PTR_ERR(req);
 				break;
 			}
+
+			nfs_direct_setup_mirroring(dreq, &desc, req);
+
 			nfs_lock_request(req);
 			req->wb_index = pos >> PAGE_SHIFT;
 			req->wb_offset = pos & ~PAGE_MASK;
@@ -934,6 +1011,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
 
 	dreq->inode = inode;
 	dreq->bytes_left = count;
+	dreq->io_start = pos;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
 	if (IS_ERR(l_ctx)) {

fs/nfs/filelayout/filelayout.c

@@ -118,13 +118,6 @@ static void filelayout_reset_read(struct nfs_pgio_header *hdr)
 	}
 }
 
-static void filelayout_fenceme(struct inode *inode, struct pnfs_layout_hdr *lo)
-{
-	if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
-		return;
-	pnfs_return_layout(inode);
-}
-
 static int filelayout_async_handle_error(struct rpc_task *task,
 					 struct nfs4_state *state,
 					 struct nfs_client *clp,
@@ -207,7 +200,7 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
 		nfs4_mark_deviceid_unavailable(devid);
-		set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
+		pnfs_error_mark_layout_for_return(inode, lseg);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		/* fall through */
 	default:
@@ -339,16 +332,6 @@ static void filelayout_read_count_stats(struct rpc_task *task, void *data)
 	rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics);
 }
 
-static void filelayout_read_release(void *data)
-{
-	struct nfs_pgio_header *hdr = data;
-	struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout;
-
-	filelayout_fenceme(lo->plh_inode, lo);
-	nfs_put_client(hdr->ds_clp);
-	hdr->mds_ops->rpc_release(data);
-}
-
 static int filelayout_write_done_cb(struct rpc_task *task,
 				struct nfs_pgio_header *hdr)
 {
@@ -371,17 +354,6 @@ static int filelayout_write_done_cb(struct rpc_task *task,
 	return 0;
 }
 
-/* Fake up some data that will cause nfs_commit_release to retry the writes. */
-static void prepare_to_resend_writes(struct nfs_commit_data *data)
-{
-	struct nfs_page *first = nfs_list_entry(data->pages.next);
-
-	data->task.tk_status = 0;
-	memcpy(&data->verf.verifier, &first->wb_verf,
-	       sizeof(data->verf.verifier));
-	data->verf.verifier.data[0]++; /* ensure verifier mismatch */
-}
-
 static int filelayout_commit_done_cb(struct rpc_task *task,
 				     struct nfs_commit_data *data)
 {
@@ -393,7 +365,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 
 	switch (err) {
 	case -NFS4ERR_RESET_TO_MDS:
-		prepare_to_resend_writes(data);
+		pnfs_generic_prepare_to_resend_writes(data);
 		return -EAGAIN;
 	case -EAGAIN:
 		rpc_restart_call_prepare(task);
@@ -451,16 +423,6 @@ static void filelayout_write_count_stats(struct rpc_task *task, void *data)
 	rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics);
 }
 
-static void filelayout_write_release(void *data)
-{
-	struct nfs_pgio_header *hdr = data;
-	struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout;
-
-	filelayout_fenceme(lo->plh_inode, lo);
-	nfs_put_client(hdr->ds_clp);
-	hdr->mds_ops->rpc_release(data);
-}
-
 static void filelayout_commit_prepare(struct rpc_task *task, void *data)
 {
 	struct nfs_commit_data *wdata = data;
@@ -471,14 +433,6 @@ static void filelayout_commit_prepare(struct rpc_task *task, void *data)
 			task);
 }
 
-static void filelayout_write_commit_done(struct rpc_task *task, void *data)
-{
-	struct nfs_commit_data *wdata = data;
-
-	/* Note this may cause RPC to be resent */
-	wdata->mds_ops->rpc_call_done(task, data);
-}
-
 static void filelayout_commit_count_stats(struct rpc_task *task, void *data)
 {
 	struct nfs_commit_data *cdata = data;
@@ -486,35 +440,25 @@ static void filelayout_commit_count_stats(struct rpc_task *task, void *data)
 	rpc_count_iostats(task, NFS_SERVER(cdata->inode)->client->cl_metrics);
 }
 
-static void filelayout_commit_release(void *calldata)
-{
-	struct nfs_commit_data *data = calldata;
-
-	data->completion_ops->completion(data);
-	pnfs_put_lseg(data->lseg);
-	nfs_put_client(data->ds_clp);
-	nfs_commitdata_release(data);
-}
-
 static const struct rpc_call_ops filelayout_read_call_ops = {
 	.rpc_call_prepare = filelayout_read_prepare,
 	.rpc_call_done = filelayout_read_call_done,
 	.rpc_count_stats = filelayout_read_count_stats,
-	.rpc_release = filelayout_read_release,
+	.rpc_release = pnfs_generic_rw_release,
 };
 
 static const struct rpc_call_ops filelayout_write_call_ops = {
 	.rpc_call_prepare = filelayout_write_prepare,
 	.rpc_call_done = filelayout_write_call_done,
 	.rpc_count_stats = filelayout_write_count_stats,
-	.rpc_release = filelayout_write_release,
+	.rpc_release = pnfs_generic_rw_release,
 };
 
 static const struct rpc_call_ops filelayout_commit_call_ops = {
 	.rpc_call_prepare = filelayout_commit_prepare,
-	.rpc_call_done = filelayout_write_commit_done,
+	.rpc_call_done = pnfs_generic_write_commit_done,
 	.rpc_count_stats = filelayout_commit_count_stats,
-	.rpc_release = filelayout_commit_release,
+	.rpc_release = pnfs_generic_commit_release,
 };
 
 static enum pnfs_try_status
@@ -548,7 +492,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
 	/* No multipath support. Use first DS */
 	atomic_inc(&ds->ds_clp->cl_count);
 	hdr->ds_clp = ds->ds_clp;
-	hdr->ds_idx = idx;
+	hdr->ds_commit_idx = idx;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
 	if (fh)
 		hdr->args.fh = fh;
@@ -557,8 +501,9 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
 	hdr->mds_offset = offset;
 
 	/* Perform an asynchronous read to ds */
-	nfs_initiate_pgio(ds_clnt, hdr,
+	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
-			    &filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN);
+			  NFS_PROTO(hdr->inode), &filelayout_read_call_ops,
+			  0, RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
 }
 
@@ -591,16 +536,16 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	hdr->pgio_done_cb = filelayout_write_done_cb;
 	atomic_inc(&ds->ds_clp->cl_count);
 	hdr->ds_clp = ds->ds_clp;
-	hdr->ds_idx = idx;
+	hdr->ds_commit_idx = idx;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
 	if (fh)
 		hdr->args.fh = fh;
 	hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
 
 	/* Perform an asynchronous write */
-	nfs_initiate_pgio(ds_clnt, hdr,
+	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
-				    &filelayout_write_call_ops, sync,
+			  NFS_PROTO(hdr->inode), &filelayout_write_call_ops,
-				    RPC_TASK_SOFTCONN);
+			  sync, RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
 }
 
@@ -988,12 +933,14 @@ static const struct nfs_pageio_ops filelayout_pg_read_ops = {
 	.pg_init = filelayout_pg_init_read,
 	.pg_test = filelayout_pg_test,
 	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static const struct nfs_pageio_ops filelayout_pg_write_ops = {
 	.pg_init = filelayout_pg_init_write,
 	.pg_test = filelayout_pg_test,
 	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
@@ -1004,37 +951,11 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
 		return j;
 }
 
-/* The generic layer is about to remove the req from the commit list.
- * If this will make the bucket empty, it will need to put the lseg reference.
- * Note this is must be called holding the inode (/cinfo) lock
- */
-static void
-filelayout_clear_request_commit(struct nfs_page *req,
-				struct nfs_commit_info *cinfo)
-{
-	struct pnfs_layout_segment *freeme = NULL;
-
-	if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
-		goto out;
-	cinfo->ds->nwritten--;
-	if (list_is_singular(&req->wb_list)) {
-		struct pnfs_commit_bucket *bucket;
-
-		bucket = list_first_entry(&req->wb_list,
-					  struct pnfs_commit_bucket,
-					  written);
-		freeme = bucket->wlseg;
-		bucket->wlseg = NULL;
-	}
-out:
-	nfs_request_remove_commit_list(req, cinfo);
-	pnfs_put_lseg_locked(freeme);
-}
-
 static void
 filelayout_mark_request_commit(struct nfs_page *req,
 			       struct pnfs_layout_segment *lseg,
-			       struct nfs_commit_info *cinfo)
+			       struct nfs_commit_info *cinfo,
+			       u32 ds_commit_idx)
 
 {
 	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
@@ -1064,7 +985,7 @@ filelayout_mark_request_commit(struct nfs_page *req,
 		 * is normally transferred to the COMMIT call and released
 		 * there.  It could also be released if the last req is pulled
 		 * off due to a rewrite, in which case it will be done in
-		 * filelayout_clear_request_commit
+		 * pnfs_generic_clear_request_commit
 		 */
 		buckets[i].wlseg = pnfs_get_lseg(lseg);
 	}
@@ -1138,101 +1059,15 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
 	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
 	if (fh)
 		data->args.fh = fh;
-	return nfs_initiate_commit(ds_clnt, data,
+	return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode),
 				   &filelayout_commit_call_ops, how,
 				   RPC_TASK_SOFTCONN);
 out_err:
-	prepare_to_resend_writes(data);
+	pnfs_generic_prepare_to_resend_writes(data);
-	filelayout_commit_release(data);
+	pnfs_generic_commit_release(data);
 	return -EAGAIN;
 }
 
-static int
-transfer_commit_list(struct list_head *src, struct list_head *dst,
-		     struct nfs_commit_info *cinfo, int max)
-{
-	struct nfs_page *req, *tmp;
-	int ret = 0;
-
-	list_for_each_entry_safe(req, tmp, src, wb_list) {
-		if (!nfs_lock_request(req))
-			continue;
-		kref_get(&req->wb_kref);
-		if (cond_resched_lock(cinfo->lock))
-			list_safe_reset_next(req, tmp, wb_list);
-		nfs_request_remove_commit_list(req, cinfo);
-		clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
-		nfs_list_add_request(req, dst);
-		ret++;
-		if ((ret == max) && !cinfo->dreq)
-			break;
-	}
-	return ret;
-}
-
-/* Note called with cinfo->lock held. */
-static int
-filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
-			       struct nfs_commit_info *cinfo,
-			       int max)
-{
-	struct list_head *src = &bucket->written;
-	struct list_head *dst = &bucket->committing;
-	int ret;
-
-	ret = transfer_commit_list(src, dst, cinfo, max);
-	if (ret) {
-		cinfo->ds->nwritten -= ret;
-		cinfo->ds->ncommitting += ret;
-		bucket->clseg = bucket->wlseg;
-		if (list_empty(src))
-			bucket->wlseg = NULL;
-		else
-			pnfs_get_lseg(bucket->clseg);
-	}
-	return ret;
-}
-
-/* Move reqs from written to committing lists, returning count of number moved.
- * Note called with cinfo->lock held.
- */
-static int filelayout_scan_commit_lists(struct nfs_commit_info *cinfo,
-					int max)
-{
-	int i, rv = 0, cnt;
-
-	for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) {
-		cnt = filelayout_scan_ds_commit_list(&cinfo->ds->buckets[i],
-						     cinfo, max);
-		max -= cnt;
-		rv += cnt;
-	}
-	return rv;
-}
-
-/* Pull everything off the committing lists and dump into @dst */
-static void filelayout_recover_commit_reqs(struct list_head *dst,
-					   struct nfs_commit_info *cinfo)
-{
-	struct pnfs_commit_bucket *b;
-	struct pnfs_layout_segment *freeme;
-	int i;
-
-restart:
-	spin_lock(cinfo->lock);
-	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
-		if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
-			freeme = b->wlseg;
-			b->wlseg = NULL;
-			spin_unlock(cinfo->lock);
-			pnfs_put_lseg(freeme);
-			goto restart;
-		}
-	}
-	cinfo->ds->nwritten = 0;
-	spin_unlock(cinfo->lock);
-}
-
 /* filelayout_search_commit_reqs - Search lists in @cinfo for the head reqest
  *				   for @page
  * @cinfo - commit info for current inode
@@ -1263,108 +1098,14 @@ filelayout_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page)
 	return NULL;
 }
 
-static void filelayout_retry_commit(struct nfs_commit_info *cinfo, int idx)
-{
-	struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
-	struct pnfs_commit_bucket *bucket;
-	struct pnfs_layout_segment *freeme;
-	int i;
-
-	for (i = idx; i < fl_cinfo->nbuckets; i++) {
-		bucket = &fl_cinfo->buckets[i];
-		if (list_empty(&bucket->committing))
-			continue;
-		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
-		spin_lock(cinfo->lock);
-		freeme = bucket->clseg;
-		bucket->clseg = NULL;
-		spin_unlock(cinfo->lock);
-		pnfs_put_lseg(freeme);
-	}
-}
-
-static unsigned int
-alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
-{
-	struct pnfs_ds_commit_info *fl_cinfo;
-	struct pnfs_commit_bucket *bucket;
-	struct nfs_commit_data *data;
-	int i;
-	unsigned int nreq = 0;
-
-	fl_cinfo = cinfo->ds;
-	bucket = fl_cinfo->buckets;
-	for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) {
-		if (list_empty(&bucket->committing))
-			continue;
-		data = nfs_commitdata_alloc();
-		if (!data)
-			break;
-		data->ds_commit_index = i;
-		spin_lock(cinfo->lock);
-		data->lseg = bucket->clseg;
-		bucket->clseg = NULL;
-		spin_unlock(cinfo->lock);
-		list_add(&data->pages, list);
-		nreq++;
-	}
-
-	/* Clean up on error */
-	filelayout_retry_commit(cinfo, i);
-	/* Caller will clean up entries put on list */
-	return nreq;
-}
-
-/* This follows nfs_commit_list pretty closely */
 static int
 filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 			   int how, struct nfs_commit_info *cinfo)
 {
-	struct nfs_commit_data *data, *tmp;
+	return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo,
-	LIST_HEAD(list);
+					    filelayout_initiate_commit);
-	unsigned int nreq = 0;
-
-	if (!list_empty(mds_pages)) {
-		data = nfs_commitdata_alloc();
-		if (data != NULL) {
-			data->lseg = NULL;
-			list_add(&data->pages, &list);
-			nreq++;
-		} else {
-			nfs_retry_commit(mds_pages, NULL, cinfo);
-			filelayout_retry_commit(cinfo, 0);
-			cinfo->completion_ops->error_cleanup(NFS_I(inode));
-			return -ENOMEM;
-		}
 }
 
-	nreq += alloc_ds_commits(cinfo, &list);
-
-	if (nreq == 0) {
-		cinfo->completion_ops->error_cleanup(NFS_I(inode));
-		goto out;
-	}
-
-	atomic_add(nreq, &cinfo->mds->rpcs_out);
-
-	list_for_each_entry_safe(data, tmp, &list, pages) {
-		list_del_init(&data->pages);
-		if (!data->lseg) {
-			nfs_init_commit(data, mds_pages, NULL, cinfo);
-			nfs_initiate_commit(NFS_CLIENT(inode), data,
-					    data->mds_ops, how, 0);
-		} else {
-			struct pnfs_commit_bucket *buckets;
-
-			buckets = cinfo->ds->buckets;
-			nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg, cinfo);
-			filelayout_initiate_commit(data, how);
-		}
-	}
-out:
-	cinfo->ds->ncommitting = 0;
-	return PNFS_ATTEMPTED;
-}
 static struct nfs4_deviceid_node *
 filelayout_alloc_deviceid_node(struct nfs_server *server,
 		struct pnfs_device *pdev, gfp_t gfp_flags)
@@ -1421,9 +1162,9 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.pg_write_ops		= &filelayout_pg_write_ops,
 	.get_ds_info		= &filelayout_get_ds_info,
 	.mark_request_commit	= filelayout_mark_request_commit,
-	.clear_request_commit	= filelayout_clear_request_commit,
+	.clear_request_commit	= pnfs_generic_clear_request_commit,
-	.scan_commit_lists	= filelayout_scan_commit_lists,
+	.scan_commit_lists	= pnfs_generic_scan_commit_lists,
-	.recover_commit_reqs	= filelayout_recover_commit_reqs,
+	.recover_commit_reqs	= pnfs_generic_recover_commit_reqs,
 	.search_commit_reqs	= filelayout_search_commit_reqs,
 	.commit_pagelist	= filelayout_commit_pagelist,
 	.read_pagelist		= filelayout_read_pagelist,

fs/nfs/filelayout/filelayout.h

@@ -32,13 +32,6 @@
 
 #include "../pnfs.h"
 
-/*
- * Default data server connection timeout and retrans vaules.
- * Set by module paramters dataserver_timeo and dataserver_retrans.
- */
-#define NFS4_DEF_DS_TIMEO   600 /* in tenths of a second */
-#define NFS4_DEF_DS_RETRANS 5
-
 /*
  * Field testing shows we need to support up to 4096 stripe indices.
  * We store each index as a u8 (u32 on the wire) to keep the memory footprint
@@ -48,32 +41,11 @@
 #define NFS4_PNFS_MAX_STRIPE_CNT 4096
 #define NFS4_PNFS_MAX_MULTI_CNT  256 /* 256 fit into a u8 stripe_index */
 
-/* error codes for internal use */
-#define NFS4ERR_RESET_TO_MDS   12001
-
 enum stripetype4 {
 	STRIPE_SPARSE = 1,
 	STRIPE_DENSE = 2
 };
 
-/* Individual ip address */
-struct nfs4_pnfs_ds_addr {
-	struct sockaddr_storage	da_addr;
-	size_t			da_addrlen;
-	struct list_head	da_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
-	char			*da_remotestr;	/* human readable addr+port */
-};
-
-struct nfs4_pnfs_ds {
-	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
-	char			*ds_remotestr;	/* comma sep list of addrs */
-	struct list_head	ds_addrs;
-	struct nfs_client	*ds_clp;
-	atomic_t		ds_count;
-	unsigned long		ds_state;
-#define NFS4DS_CONNECTING	0	/* ds is establishing connection */
-};
-
 struct nfs4_file_layout_dsaddr {
 	struct nfs4_deviceid_node	id_node;
 	u32				stripe_count;
@@ -119,17 +91,6 @@ FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg)
 	return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node;
 }
 
-static inline void
-filelayout_mark_devid_invalid(struct nfs4_deviceid_node *node)
-{
-	u32 *p = (u32 *)&node->deviceid;
-
-	printk(KERN_WARNING "NFS: Deviceid [%x%x%x%x] marked out of use.\n",
-		p[0], p[1], p[2], p[3]);
-
-	set_bit(NFS_DEVICEID_INVALID, &node->flags);
-}
-
 static inline bool
 filelayout_test_devid_invalid(struct nfs4_deviceid_node *node)
 {
@@ -142,7 +103,6 @@ filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node);
 extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
 
-extern void print_ds(struct nfs4_pnfs_ds *ds);
 u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
 u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
 struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,

fs/nfs/filelayout/filelayoutdev.c

@@ -31,7 +31,6 @@
 #include <linux/nfs_fs.h>
 #include <linux/vmalloc.h>
 #include <linux/module.h>
-#include <linux/sunrpc/addr.h>
 
 #include "../internal.h"
 #include "../nfs4session.h"
@@ -42,183 +41,6 @@
 static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
 static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
 
-/*
- * Data server cache
- *
- * Data servers can be mapped to different device ids.
- * nfs4_pnfs_ds reference counting
- *   - set to 1 on allocation
- *   - incremented when a device id maps a data server already in the cache.
- *   - decremented when deviceid is removed from the cache.
- */
-static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
-static LIST_HEAD(nfs4_data_server_cache);
-
-/* Debug routines */
-void
-print_ds(struct nfs4_pnfs_ds *ds)
-{
-	if (ds == NULL) {
-		printk("%s NULL device\n", __func__);
-		return;
-	}
-	printk("        ds %s\n"
-		"        ref count %d\n"
-		"        client %p\n"
-		"        cl_exchange_flags %x\n",
-		ds->ds_remotestr,
-		atomic_read(&ds->ds_count), ds->ds_clp,
-		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
-}
-
-static bool
-same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
-{
-	struct sockaddr_in *a, *b;
-	struct sockaddr_in6 *a6, *b6;
-
-	if (addr1->sa_family != addr2->sa_family)
-		return false;
-
-	switch (addr1->sa_family) {
-	case AF_INET:
-		a = (struct sockaddr_in *)addr1;
-		b = (struct sockaddr_in *)addr2;
-
-		if (a->sin_addr.s_addr == b->sin_addr.s_addr &&
-		    a->sin_port == b->sin_port)
-			return true;
-		break;
-
-	case AF_INET6:
-		a6 = (struct sockaddr_in6 *)addr1;
-		b6 = (struct sockaddr_in6 *)addr2;
-
-		/* LINKLOCAL addresses must have matching scope_id */
-		if (ipv6_addr_src_scope(&a6->sin6_addr) ==
-		    IPV6_ADDR_SCOPE_LINKLOCAL &&
-		    a6->sin6_scope_id != b6->sin6_scope_id)
-			return false;
-
-		if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) &&
-		    a6->sin6_port == b6->sin6_port)
-			return true;
-		break;
-
-	default:
-		dprintk("%s: unhandled address family: %u\n",
-			__func__, addr1->sa_family);
-		return false;
-	}
-
-	return false;
-}
-
-static bool
-_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
-			       const struct list_head *dsaddrs2)
-{
-	struct nfs4_pnfs_ds_addr *da1, *da2;
-
-	/* step through both lists, comparing as we go */
-	for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
-	     da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
-	     da1 != NULL && da2 != NULL;
-	     da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
-	     da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
-		if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
-				   (struct sockaddr *)&da2->da_addr))
-			return false;
-	}
-	if (da1 == NULL && da2 == NULL)
-		return true;
-
-	return false;
-}
-
-/*
- * Lookup DS by addresses.  nfs4_ds_cache_lock is held
- */
-static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(const struct list_head *dsaddrs)
-{
-	struct nfs4_pnfs_ds *ds;
-
-	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
-		if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
-			return ds;
-	return NULL;
-}
-
-/*
- * Create an rpc connection to the nfs4_pnfs_ds data server
- * Currently only supports IPv4 and IPv6 addresses
- */
-static int
-nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
-{
-	struct nfs_client *clp = ERR_PTR(-EIO);
-	struct nfs4_pnfs_ds_addr *da;
-	int status = 0;
-
-	dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
-		mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor);
-
-	list_for_each_entry(da, &ds->ds_addrs, da_node) {
-		dprintk("%s: DS %s: trying address %s\n",
-			__func__, ds->ds_remotestr, da->da_remotestr);
-
-		clp = nfs4_set_ds_client(mds_srv->nfs_client,
-					(struct sockaddr *)&da->da_addr,
-					da->da_addrlen, IPPROTO_TCP,
-					dataserver_timeo, dataserver_retrans);
-		if (!IS_ERR(clp))
-			break;
-	}
-
-	if (IS_ERR(clp)) {
-		status = PTR_ERR(clp);
-		goto out;
-	}
-
-	status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time);
-	if (status)
-		goto out_put;
-
-	smp_wmb();
-	ds->ds_clp = clp;
-	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
-out:
-	return status;
-out_put:
-	nfs_put_client(clp);
-	goto out;
-}
-
-static void
-destroy_ds(struct nfs4_pnfs_ds *ds)
-{
-	struct nfs4_pnfs_ds_addr *da;
-
-	dprintk("--> %s\n", __func__);
-	ifdebug(FACILITY)
-		print_ds(ds);
-
-	nfs_put_client(ds->ds_clp);
-
-	while (!list_empty(&ds->ds_addrs)) {
-		da = list_first_entry(&ds->ds_addrs,
-				      struct nfs4_pnfs_ds_addr,
-				      da_node);
-		list_del_init(&da->da_node);
-		kfree(da->da_remotestr);
-		kfree(da);
-	}
-
-	kfree(ds->ds_remotestr);
-	kfree(ds);
-}
-
 void
 nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
@@ -229,259 +51,13 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 
 	for (i = 0; i < dsaddr->ds_num; i++) {
 		ds = dsaddr->ds_list[i];
-		if (ds != NULL) {
+		if (ds != NULL)
-			if (atomic_dec_and_lock(&ds->ds_count,
+			nfs4_pnfs_ds_put(ds);
-						&nfs4_ds_cache_lock)) {
-				list_del_init(&ds->ds_node);
-				spin_unlock(&nfs4_ds_cache_lock);
-				destroy_ds(ds);
-			}
-		}
 	}
 	kfree(dsaddr->stripe_indices);
 	kfree(dsaddr);
 }
 
-/*
- * Create a string with a human readable address and port to avoid
- * complicated setup around many dprinks.
- */
-static char *
-nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
-{
-	struct nfs4_pnfs_ds_addr *da;
-	char *remotestr;
-	size_t len;
-	char *p;
-
-	len = 3;        /* '{', '}' and eol */
-	list_for_each_entry(da, dsaddrs, da_node) {
-		len += strlen(da->da_remotestr) + 1;    /* string plus comma */
-	}
-
-	remotestr = kzalloc(len, gfp_flags);
-	if (!remotestr)
-		return NULL;
-
-	p = remotestr;
-	*(p++) = '{';
-	len--;
-	list_for_each_entry(da, dsaddrs, da_node) {
-		size_t ll = strlen(da->da_remotestr);
-
-		if (ll > len)
-			goto out_err;
-
-		memcpy(p, da->da_remotestr, ll);
-		p += ll;
-		len -= ll;
-
-		if (len < 1)
-			goto out_err;
-		(*p++) = ',';
-		len--;
-	}
-	if (len < 2)
-		goto out_err;
-	*(p++) = '}';
-	*p = '\0';
-	return remotestr;
-out_err:
-	kfree(remotestr);
-	return NULL;
-}
-
-static struct nfs4_pnfs_ds *
-nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
-{
-	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
-	char *remotestr;
-
-	if (list_empty(dsaddrs)) {
-		dprintk("%s: no addresses defined\n", __func__);
-		goto out;
-	}
-
-	ds = kzalloc(sizeof(*ds), gfp_flags);
-	if (!ds)
-		goto out;
-
-	/* this is only used for debugging, so it's ok if its NULL */
-	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
-
-	spin_lock(&nfs4_ds_cache_lock);
-	tmp_ds = _data_server_lookup_locked(dsaddrs);
-	if (tmp_ds == NULL) {
-		INIT_LIST_HEAD(&ds->ds_addrs);
-		list_splice_init(dsaddrs, &ds->ds_addrs);
-		ds->ds_remotestr = remotestr;
-		atomic_set(&ds->ds_count, 1);
-		INIT_LIST_HEAD(&ds->ds_node);
-		ds->ds_clp = NULL;
-		list_add(&ds->ds_node, &nfs4_data_server_cache);
-		dprintk("%s add new data server %s\n", __func__,
-			ds->ds_remotestr);
-	} else {
-		kfree(remotestr);
-		kfree(ds);
-		atomic_inc(&tmp_ds->ds_count);
-		dprintk("%s data server %s found, inc'ed ds_count to %d\n",
-			__func__, tmp_ds->ds_remotestr,
-			atomic_read(&tmp_ds->ds_count));
-		ds = tmp_ds;
-	}
-	spin_unlock(&nfs4_ds_cache_lock);
-out:
-	return ds;
-}
-
-/*
- * Currently only supports ipv4, ipv6 and one multi-path address.
- */
-static struct nfs4_pnfs_ds_addr *
-decode_ds_addr(struct net *net, struct xdr_stream *streamp, gfp_t gfp_flags)
-{
-	struct nfs4_pnfs_ds_addr *da = NULL;
-	char *buf, *portstr;
-	__be16 port;
-	int nlen, rlen;
-	int tmp[2];
-	__be32 *p;
-	char *netid, *match_netid;
-	size_t len, match_netid_len;
-	char *startsep = "";
-	char *endsep = "";
-
-
-	/* r_netid */
-	p = xdr_inline_decode(streamp, 4);
-	if (unlikely(!p))
-		goto out_err;
-	nlen = be32_to_cpup(p++);
-
-	p = xdr_inline_decode(streamp, nlen);
-	if (unlikely(!p))
-		goto out_err;
-
-	netid = kmalloc(nlen+1, gfp_flags);
-	if (unlikely(!netid))
-		goto out_err;
-
-	netid[nlen] = '\0';
-	memcpy(netid, p, nlen);
-
-	/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
-	p = xdr_inline_decode(streamp, 4);
-	if (unlikely(!p))
-		goto out_free_netid;
-	rlen = be32_to_cpup(p);
-
-	p = xdr_inline_decode(streamp, rlen);
-	if (unlikely(!p))
-		goto out_free_netid;
-
-	/* port is ".ABC.DEF", 8 chars max */
-	if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) {
-		dprintk("%s: Invalid address, length %d\n", __func__,
-			rlen);
-		goto out_free_netid;
-	}
-	buf = kmalloc(rlen + 1, gfp_flags);
-	if (!buf) {
-		dprintk("%s: Not enough memory\n", __func__);
-		goto out_free_netid;
-	}
-	buf[rlen] = '\0';
-	memcpy(buf, p, rlen);
-
-	/* replace port '.' with '-' */
-	portstr = strrchr(buf, '.');
-	if (!portstr) {
-		dprintk("%s: Failed finding expected dot in port\n",
-			__func__);
-		goto out_free_buf;
-	}
-	*portstr = '-';
-
-	/* find '.' between address and port */
-	portstr = strrchr(buf, '.');
-	if (!portstr) {
-		dprintk("%s: Failed finding expected dot between address and "
-			"port\n", __func__);
-		goto out_free_buf;
-	}
-	*portstr = '\0';
-
-	da = kzalloc(sizeof(*da), gfp_flags);
-	if (unlikely(!da))
-		goto out_free_buf;
-
-	INIT_LIST_HEAD(&da->da_node);
-
-	if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
-		      sizeof(da->da_addr))) {
-		dprintk("%s: error parsing address %s\n", __func__, buf);
-		goto out_free_da;
-	}
-
-	portstr++;
-	sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]);
-	port = htons((tmp[0] << 8) | (tmp[1]));
-
-	switch (da->da_addr.ss_family) {
-	case AF_INET:
-		((struct sockaddr_in *)&da->da_addr)->sin_port = port;
-		da->da_addrlen = sizeof(struct sockaddr_in);
-		match_netid = "tcp";
-		match_netid_len = 3;
-		break;
-
-	case AF_INET6:
-		((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port;
-		da->da_addrlen = sizeof(struct sockaddr_in6);
-		match_netid = "tcp6";
-		match_netid_len = 4;
-		startsep = "[";
-		endsep = "]";
-		break;
-
-	default:
-		dprintk("%s: unsupported address family: %u\n",
-			__func__, da->da_addr.ss_family);
-		goto out_free_da;
-	}
-
-	if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) {
-		dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n",
-			__func__, netid, match_netid);
-		goto out_free_da;
-	}
-
-	/* save human readable address */
-	len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7;
-	da->da_remotestr = kzalloc(len, gfp_flags);
-
-	/* NULL is ok, only used for dprintk */
-	if (da->da_remotestr)
-		snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep,
-			 buf, endsep, ntohs(port));
-
-	dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr);
-	kfree(buf);
-	kfree(netid);
-	return da;
-
-out_free_da:
-	kfree(da);
-out_free_buf:
-	dprintk("%s: Error parsing DS addr: %s\n", __func__, buf);
-	kfree(buf);
-out_free_netid:
-	kfree(netid);
-out_err:
-	return NULL;
-}
-
 /* Decode opaque device data and return the result */
 struct nfs4_file_layout_dsaddr *
 nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
@@ -584,7 +160,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 
 		mp_count = be32_to_cpup(p); /* multipath count */
 		for (j = 0; j < mp_count; j++) {
-			da = decode_ds_addr(server->nfs_client->cl_net,
+			da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
 						    &stream, gfp_flags);
 			if (da)
 				list_add_tail(&da->da_node, &dsaddrs);
@@ -681,22 +257,7 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
 	return flseg->fh_array[i];
 }
 
-static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
+/* Upon return, either ds is connected, or ds is NULL */
-{
-	might_sleep();
-	wait_on_bit_action(&ds->ds_state, NFS4DS_CONNECTING,
-			   nfs_wait_bit_killable, TASK_KILLABLE);
-}
-
-static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
-{
-	smp_mb__before_atomic();
-	clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
-	smp_mb__after_atomic();
-	wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
-}
-
-
 struct nfs4_pnfs_ds *
 nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 {
@@ -704,29 +265,23 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
 	struct nfs4_pnfs_ds *ret = ds;
+	struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
 
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
 			__func__, ds_idx);
-		filelayout_mark_devid_invalid(devid);
+		pnfs_generic_mark_devid_invalid(devid);
 		goto out;
 	}
 	smp_rmb();
 	if (ds->ds_clp)
 		goto out_test_devid;
 
-	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
+	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
-		struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
+			     dataserver_retrans, 4,
-		int err;
+			     s->nfs_client->cl_minorversion,
+			     s->nfs_client->cl_rpcclient->cl_auth->au_flavor);
 
-		err = nfs4_ds_connect(s, ds);
-		if (err)
-			nfs4_mark_deviceid_unavailable(devid);
-		nfs4_clear_ds_conn_bit(ds);
-	} else {
-		/* Either ds is connected, or ds is NULL */
-		nfs4_wait_ds_connect(ds);
-	}
 out_test_devid:
 	if (filelayout_test_devid_unavailable(devid))
 		ret = NULL;

fs/nfs/flexfilelayout/Makefile

@@ -0,0 +1,5 @@
+#
+# Makefile for the pNFS Flexfile Layout Driver kernel module
+#
+obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += nfs_layout_flexfiles.o
+nfs_layout_flexfiles-y := flexfilelayout.o flexfilelayoutdev.o

fs/nfs/flexfilelayout/flexfilelayout.h

@@ -0,0 +1,155 @@
+/*
+ * NFSv4 flexfile layout driver data structures.
+ *
+ * Copyright (c) 2014, Primary Data, Inc. All rights reserved.
+ *
+ * Tao Peng <bergwolf@primarydata.com>
+ */
+
+#ifndef FS_NFS_NFS4FLEXFILELAYOUT_H
+#define FS_NFS_NFS4FLEXFILELAYOUT_H
+
+#include "../pnfs.h"
+
+/* XXX: Let's filter out insanely large mirror count for now to avoid oom
+ * due to network error etc. */
+#define NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT 4096
+
+struct nfs4_ff_ds_version {
+	u32				version;
+	u32				minor_version;
+	u32				rsize;
+	u32				wsize;
+	bool				tightly_coupled;
+};
+
+/* chained in global deviceid hlist */
+struct nfs4_ff_layout_ds {
+	struct nfs4_deviceid_node	id_node;
+	u32				ds_versions_cnt;
+	struct nfs4_ff_ds_version	*ds_versions;
+	struct nfs4_pnfs_ds		*ds;
+};
+
+struct nfs4_ff_layout_ds_err {
+	struct list_head		list; /* linked in mirror error_list */
+	u64				offset;
+	u64				length;
+	int				status;
+	enum nfs_opnum4			opnum;
+	nfs4_stateid			stateid;
+	struct nfs4_deviceid		deviceid;
+};
+
+struct nfs4_ff_layout_mirror {
+	u32				ds_count;
+	u32				efficiency;
+	struct nfs4_ff_layout_ds	*mirror_ds;
+	u32				fh_versions_cnt;
+	struct nfs_fh			*fh_versions;
+	nfs4_stateid			stateid;
+	struct nfs4_string		user_name;
+	struct nfs4_string		group_name;
+	u32				uid;
+	u32				gid;
+	struct rpc_cred			*cred;
+	spinlock_t			lock;
+};
+
+struct nfs4_ff_layout_segment {
+	struct pnfs_layout_segment	generic_hdr;
+	u64				stripe_unit;
+	u32				mirror_array_cnt;
+	struct nfs4_ff_layout_mirror	**mirror_array;
+};
+
+struct nfs4_flexfile_layout {
+	struct pnfs_layout_hdr generic_hdr;
+	struct pnfs_ds_commit_info commit_info;
+	struct list_head	error_list; /* nfs4_ff_layout_ds_err */
+};
+
+static inline struct nfs4_flexfile_layout *
+FF_LAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo)
+{
+	return container_of(lo, struct nfs4_flexfile_layout, generic_hdr);
+}
+
+static inline struct nfs4_ff_layout_segment *
+FF_LAYOUT_LSEG(struct pnfs_layout_segment *lseg)
+{
+	return container_of(lseg,
+			    struct nfs4_ff_layout_segment,
+			    generic_hdr);
+}
+
+static inline struct nfs4_deviceid_node *
+FF_LAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg, u32 idx)
+{
+	if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt ||
+	    FF_LAYOUT_LSEG(lseg)->mirror_array[idx] == NULL ||
+	    FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds == NULL)
+		return NULL;
+	return &FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds->id_node;
+}
+
+static inline struct nfs4_ff_layout_ds *
+FF_LAYOUT_MIRROR_DS(struct nfs4_deviceid_node *node)
+{
+	return container_of(node, struct nfs4_ff_layout_ds, id_node);
+}
+
+static inline struct nfs4_ff_layout_mirror *
+FF_LAYOUT_COMP(struct pnfs_layout_segment *lseg, u32 idx)
+{
+	if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt)
+		return NULL;
+	return FF_LAYOUT_LSEG(lseg)->mirror_array[idx];
+}
+
+static inline u32
+FF_LAYOUT_MIRROR_COUNT(struct pnfs_layout_segment *lseg)
+{
+	return FF_LAYOUT_LSEG(lseg)->mirror_array_cnt;
+}
+
+static inline bool
+ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
+{
+	return nfs4_test_deviceid_unavailable(node);
+}
+
+static inline int
+nfs4_ff_layout_ds_version(struct pnfs_layout_segment *lseg, u32 ds_idx)
+{
+	return FF_LAYOUT_COMP(lseg, ds_idx)->mirror_ds->ds_versions[0].version;
+}
+
+struct nfs4_ff_layout_ds *
+nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+			    gfp_t gfp_flags);
+void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds);
+void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds);
+int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
+			     struct nfs4_ff_layout_mirror *mirror, u64 offset,
+			     u64 length, int status, enum nfs_opnum4 opnum,
+			     gfp_t gfp_flags);
+int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo,
+			      struct xdr_stream *xdr, int *count,
+			      const struct pnfs_layout_range *range);
+struct nfs_fh *
+nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx);
+
+struct nfs4_pnfs_ds *
+nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
+			  bool fail_return);
+
+struct rpc_clnt *
+nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg,
+				 u32 ds_idx,
+				 struct nfs_client *ds_clp,
+				 struct inode *inode);
+struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg,
+				       u32 ds_idx, struct rpc_cred *mdscred);
+bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg);
+#endif /* FS_NFS_NFS4FLEXFILELAYOUT_H */

fs/nfs/flexfilelayout/flexfilelayoutdev.c

@@ -0,0 +1,552 @@
+/*
+ * Device operations for the pnfs nfs4 file layout driver.
+ *
+ * Copyright (c) 2014, Primary Data, Inc. All rights reserved.
+ *
+ * Tao Peng <bergwolf@primarydata.com>
+ */
+
+#include <linux/nfs_fs.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+#include <linux/sunrpc/addr.h>
+
+#include "../internal.h"
+#include "../nfs4session.h"
+#include "flexfilelayout.h"
+
+#define NFSDBG_FACILITY		NFSDBG_PNFS_LD
+
+static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
+static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
+
+void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
+{
+	if (mirror_ds)
+		nfs4_put_deviceid_node(&mirror_ds->id_node);
+}
+
+void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
+{
+	nfs4_print_deviceid(&mirror_ds->id_node.deviceid);
+	nfs4_pnfs_ds_put(mirror_ds->ds);
+	kfree(mirror_ds);
+}
+
+/* Decode opaque device data and construct new_ds using it */
+struct nfs4_ff_layout_ds *
+nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+			    gfp_t gfp_flags)
+{
+	struct xdr_stream stream;
+	struct xdr_buf buf;
+	struct page *scratch;
+	struct list_head dsaddrs;
+	struct nfs4_pnfs_ds_addr *da;
+	struct nfs4_ff_layout_ds *new_ds = NULL;
+	struct nfs4_ff_ds_version *ds_versions = NULL;
+	u32 mp_count;
+	u32 version_count;
+	__be32 *p;
+	int i, ret = -ENOMEM;
+
+	/* set up xdr stream */
+	scratch = alloc_page(gfp_flags);
+	if (!scratch)
+		goto out_err;
+
+	new_ds = kzalloc(sizeof(struct nfs4_ff_layout_ds), gfp_flags);
+	if (!new_ds)
+		goto out_scratch;
+
+	nfs4_init_deviceid_node(&new_ds->id_node,
+				server,
+				&pdev->dev_id);
+	INIT_LIST_HEAD(&dsaddrs);
+
+	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
+	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+
+	/* multipath count */
+	p = xdr_inline_decode(&stream, 4);
+	if (unlikely(!p))
+		goto out_err_drain_dsaddrs;
+	mp_count = be32_to_cpup(p);
+	dprintk("%s: multipath ds count %d\n", __func__, mp_count);
+
+	for (i = 0; i < mp_count; i++) {
+		/* multipath ds */
+		da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
+					    &stream, gfp_flags);
+		if (da)
+			list_add_tail(&da->da_node, &dsaddrs);
+	}
+	if (list_empty(&dsaddrs)) {
+		dprintk("%s: no suitable DS addresses found\n",
+			__func__);
+		ret = -ENOMEDIUM;
+		goto out_err_drain_dsaddrs;
+	}
+
+	/* version count */
+	p = xdr_inline_decode(&stream, 4);
+	if (unlikely(!p))
+		goto out_err_drain_dsaddrs;
+	version_count = be32_to_cpup(p);
+	dprintk("%s: version count %d\n", __func__, version_count);
+
+	ds_versions = kzalloc(version_count * sizeof(struct nfs4_ff_ds_version),
+			      gfp_flags);
+	if (!ds_versions)
+		goto out_scratch;
+
+	for (i = 0; i < version_count; i++) {
+		/* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) +
+		 * tightly_coupled(4) */
+		p = xdr_inline_decode(&stream, 20);
+		if (unlikely(!p))
+			goto out_err_drain_dsaddrs;
+		ds_versions[i].version = be32_to_cpup(p++);
+		ds_versions[i].minor_version = be32_to_cpup(p++);
+		ds_versions[i].rsize = nfs_block_size(be32_to_cpup(p++), NULL);
+		ds_versions[i].wsize = nfs_block_size(be32_to_cpup(p++), NULL);
+		ds_versions[i].tightly_coupled = be32_to_cpup(p);
+
+		if (ds_versions[i].rsize > NFS_MAX_FILE_IO_SIZE)
+			ds_versions[i].rsize = NFS_MAX_FILE_IO_SIZE;
+		if (ds_versions[i].wsize > NFS_MAX_FILE_IO_SIZE)
+			ds_versions[i].wsize = NFS_MAX_FILE_IO_SIZE;
+
+		if (ds_versions[i].version != 3 || ds_versions[i].minor_version != 0) {
+			dprintk("%s: [%d] unsupported ds version %d-%d\n", __func__,
+				i, ds_versions[i].version,
+				ds_versions[i].minor_version);
+			ret = -EPROTONOSUPPORT;
+			goto out_err_drain_dsaddrs;
+		}
+
+		dprintk("%s: [%d] vers %u minor_ver %u rsize %u wsize %u coupled %d\n",
+			__func__, i, ds_versions[i].version,
+			ds_versions[i].minor_version,
+			ds_versions[i].rsize,
+			ds_versions[i].wsize,
+			ds_versions[i].tightly_coupled);
+	}
+
+	new_ds->ds_versions = ds_versions;
+	new_ds->ds_versions_cnt = version_count;
+
+	new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+	if (!new_ds->ds)
+		goto out_err_drain_dsaddrs;
+
+	/* If DS was already in cache, free ds addrs */
+	while (!list_empty(&dsaddrs)) {
+		da = list_first_entry(&dsaddrs,
+				      struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+
+	__free_page(scratch);
+	return new_ds;
+
+out_err_drain_dsaddrs:
+	while (!list_empty(&dsaddrs)) {
+		da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+
+	kfree(ds_versions);
+out_scratch:
+	__free_page(scratch);
+out_err:
+	kfree(new_ds);
+
+	dprintk("%s ERROR: returning %d\n", __func__, ret);
+	return NULL;
+}
+
+static u64
+end_offset(u64 start, u64 len)
+{
+	u64 end;
+
+	end = start + len;
+	return end >= start ? end : NFS4_MAX_UINT64;
+}
+
+static void extend_ds_error(struct nfs4_ff_layout_ds_err *err,
+			    u64 offset, u64 length)
+{
+	u64 end;
+
+	end = max_t(u64, end_offset(err->offset, err->length),
+		    end_offset(offset, length));
+	err->offset = min_t(u64, err->offset, offset);
+	err->length = end - err->offset;
+}
+
+static bool ds_error_can_merge(struct nfs4_ff_layout_ds_err *err,  u64 offset,
+			       u64 length, int status, enum nfs_opnum4 opnum,
+			       nfs4_stateid *stateid,
+			       struct nfs4_deviceid *deviceid)
+{
+	return err->status == status && err->opnum == opnum &&
+	       nfs4_stateid_match(&err->stateid, stateid) &&
+	       !memcmp(&err->deviceid, deviceid, sizeof(*deviceid)) &&
+	       end_offset(err->offset, err->length) >= offset &&
+	       err->offset <= end_offset(offset, length);
+}
+
+static bool merge_ds_error(struct nfs4_ff_layout_ds_err *old,
+			   struct nfs4_ff_layout_ds_err *new)
+{
+	if (!ds_error_can_merge(old, new->offset, new->length, new->status,
+				new->opnum, &new->stateid, &new->deviceid))
+		return false;
+
+	extend_ds_error(old, new->offset, new->length);
+	return true;
+}
+
+static bool
+ff_layout_add_ds_error_locked(struct nfs4_flexfile_layout *flo,
+			      struct nfs4_ff_layout_ds_err *dserr)
+{
+	struct nfs4_ff_layout_ds_err *err;
+
+	list_for_each_entry(err, &flo->error_list, list) {
+		if (merge_ds_error(err, dserr)) {
+			return true;
+		}
+	}
+
+	list_add(&dserr->list, &flo->error_list);
+	return false;
+}
+
+static bool
+ff_layout_update_ds_error(struct nfs4_flexfile_layout *flo, u64 offset,
+			  u64 length, int status, enum nfs_opnum4 opnum,
+			  nfs4_stateid *stateid, struct nfs4_deviceid *deviceid)
+{
+	bool found = false;
+	struct nfs4_ff_layout_ds_err *err;
+
+	list_for_each_entry(err, &flo->error_list, list) {
+		if (ds_error_can_merge(err, offset, length, status, opnum,
+				       stateid, deviceid)) {
+			found = true;
+			extend_ds_error(err, offset, length);
+			break;
+		}
+	}
+
+	return found;
+}
+
+int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
+			     struct nfs4_ff_layout_mirror *mirror, u64 offset,
+			     u64 length, int status, enum nfs_opnum4 opnum,
+			     gfp_t gfp_flags)
+{
+	struct nfs4_ff_layout_ds_err *dserr;
+	bool needfree;
+
+	if (status == 0)
+		return 0;
+
+	if (mirror->mirror_ds == NULL)
+		return -EINVAL;
+
+	spin_lock(&flo->generic_hdr.plh_inode->i_lock);
+	if (ff_layout_update_ds_error(flo, offset, length, status, opnum,
+				      &mirror->stateid,
+				      &mirror->mirror_ds->id_node.deviceid)) {
+		spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
+		return 0;
+	}
+	spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
+	dserr = kmalloc(sizeof(*dserr), gfp_flags);
+	if (!dserr)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&dserr->list);
+	dserr->offset = offset;
+	dserr->length = length;
+	dserr->status = status;
+	dserr->opnum = opnum;
+	nfs4_stateid_copy(&dserr->stateid, &mirror->stateid);
+	memcpy(&dserr->deviceid, &mirror->mirror_ds->id_node.deviceid,
+	       NFS4_DEVICEID4_SIZE);
+
+	spin_lock(&flo->generic_hdr.plh_inode->i_lock);
+	needfree = ff_layout_add_ds_error_locked(flo, dserr);
+	spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
+	if (needfree)
+		kfree(dserr);
+
+	return 0;
+}
+
+/* currently we only support AUTH_NONE and AUTH_SYS */
+static rpc_authflavor_t
+nfs4_ff_layout_choose_authflavor(struct nfs4_ff_layout_mirror *mirror)
+{
+	if (mirror->uid == (u32)-1)
+		return RPC_AUTH_NULL;
+	return RPC_AUTH_UNIX;
+}
+
+/* fetch cred for NFSv3 DS */
+static int ff_layout_update_mirror_cred(struct nfs4_ff_layout_mirror *mirror,
+				      struct nfs4_pnfs_ds *ds)
+{
+	if (ds->ds_clp && !mirror->cred &&
+	    mirror->mirror_ds->ds_versions[0].version == 3) {
+		struct rpc_auth *auth = ds->ds_clp->cl_rpcclient->cl_auth;
+		struct rpc_cred *cred;
+		struct auth_cred acred = {
+			.uid = make_kuid(&init_user_ns, mirror->uid),
+			.gid = make_kgid(&init_user_ns, mirror->gid),
+		};
+
+		/* AUTH_NULL ignores acred */
+		cred = auth->au_ops->lookup_cred(auth, &acred, 0);
+		if (IS_ERR(cred)) {
+			dprintk("%s: lookup_cred failed with %ld\n",
+				__func__, PTR_ERR(cred));
+			return PTR_ERR(cred);
+		} else {
+			mirror->cred = cred;
+		}
+	}
+	return 0;
+}
+
+struct nfs_fh *
+nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx)
+{
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, mirror_idx);
+	struct nfs_fh *fh = NULL;
+	struct nfs4_deviceid_node *devid;
+
+	if (mirror == NULL || mirror->mirror_ds == NULL ||
+	    mirror->mirror_ds->ds == NULL) {
+		printk(KERN_ERR "NFS: %s: No data server for mirror offset index %d\n",
+			__func__, mirror_idx);
+		if (mirror && mirror->mirror_ds) {
+			devid = &mirror->mirror_ds->id_node;
+			pnfs_generic_mark_devid_invalid(devid);
+		}
+		goto out;
+	}
+
+	/* FIXME: For now assume there is only 1 version available for the DS */
+	fh = &mirror->fh_versions[0];
+out:
+	return fh;
+}
+
+/* Upon return, either ds is connected, or ds is NULL */
+struct nfs4_pnfs_ds *
+nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
+			  bool fail_return)
+{
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
+	struct nfs4_pnfs_ds *ds = NULL;
+	struct nfs4_deviceid_node *devid;
+	struct inode *ino = lseg->pls_layout->plh_inode;
+	struct nfs_server *s = NFS_SERVER(ino);
+	unsigned int max_payload;
+	rpc_authflavor_t flavor;
+
+	if (mirror == NULL || mirror->mirror_ds == NULL ||
+	    mirror->mirror_ds->ds == NULL) {
+		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
+			__func__, ds_idx);
+		if (mirror && mirror->mirror_ds) {
+			devid = &mirror->mirror_ds->id_node;
+			pnfs_generic_mark_devid_invalid(devid);
+		}
+		goto out;
+	}
+
+	devid = &mirror->mirror_ds->id_node;
+	if (ff_layout_test_devid_unavailable(devid))
+		goto out;
+
+	ds = mirror->mirror_ds->ds;
+	/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
+	smp_rmb();
+	if (ds->ds_clp)
+		goto out;
+
+	flavor = nfs4_ff_layout_choose_authflavor(mirror);
+
+	/* FIXME: For now we assume the server sent only one version of NFS
+	 * to use for the DS.
+	 */
+	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+			     dataserver_retrans,
+			     mirror->mirror_ds->ds_versions[0].version,
+			     mirror->mirror_ds->ds_versions[0].minor_version,
+			     flavor);
+
+	/* connect success, check rsize/wsize limit */
+	if (ds->ds_clp) {
+		max_payload =
+			nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
+				       NULL);
+		if (mirror->mirror_ds->ds_versions[0].rsize > max_payload)
+			mirror->mirror_ds->ds_versions[0].rsize = max_payload;
+		if (mirror->mirror_ds->ds_versions[0].wsize > max_payload)
+			mirror->mirror_ds->ds_versions[0].wsize = max_payload;
+	} else {
+		ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
+					 mirror, lseg->pls_range.offset,
+					 lseg->pls_range.length, NFS4ERR_NXIO,
+					 OP_ILLEGAL, GFP_NOIO);
+		if (fail_return) {
+			pnfs_error_mark_layout_for_return(ino, lseg);
+			if (ff_layout_has_available_ds(lseg))
+				pnfs_set_retry_layoutget(lseg->pls_layout);
+			else
+				pnfs_clear_retry_layoutget(lseg->pls_layout);
+
+		} else {
+			if (ff_layout_has_available_ds(lseg))
+				set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					&lseg->pls_layout->plh_flags);
+			else {
+				pnfs_error_mark_layout_for_return(ino, lseg);
+				pnfs_clear_retry_layoutget(lseg->pls_layout);
+			}
+		}
+	}
+
+	if (ff_layout_update_mirror_cred(mirror, ds))
+		ds = NULL;
+out:
+	return ds;
+}
+
+struct rpc_cred *
+ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx,
+		      struct rpc_cred *mdscred)
+{
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
+	struct rpc_cred *cred = ERR_PTR(-EINVAL);
+
+	if (!nfs4_ff_layout_prepare_ds(lseg, ds_idx, true))
+		goto out;
+
+	if (mirror && mirror->cred)
+		cred = mirror->cred;
+	else
+		cred = mdscred;
+out:
+	return cred;
+}
+
+/**
+* Find or create a DS rpc client with th MDS server rpc client auth flavor
+* in the nfs_client cl_ds_clients list.
+*/
+struct rpc_clnt *
+nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, u32 ds_idx,
+				 struct nfs_client *ds_clp, struct inode *inode)
+{
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
+
+	switch (mirror->mirror_ds->ds_versions[0].version) {
+	case 3:
+		/* For NFSv3 DS, flavor is set when creating DS connections */
+		return ds_clp->cl_rpcclient;
+	case 4:
+		return nfs4_find_or_create_ds_client(ds_clp, inode);
+	default:
+		BUG();
+	}
+}
+
+static bool is_range_intersecting(u64 offset1, u64 length1,
+				  u64 offset2, u64 length2)
+{
+	u64 end1 = end_offset(offset1, length1);
+	u64 end2 = end_offset(offset2, length2);
+
+	return (end1 == NFS4_MAX_UINT64 || end1 > offset2) &&
+	       (end2 == NFS4_MAX_UINT64 || end2 > offset1);
+}
+
+/* called with inode i_lock held */
+int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo,
+			      struct xdr_stream *xdr, int *count,
+			      const struct pnfs_layout_range *range)
+{
+	struct nfs4_ff_layout_ds_err *err, *n;
+	__be32 *p;
+
+	list_for_each_entry_safe(err, n, &flo->error_list, list) {
+		if (!is_range_intersecting(err->offset, err->length,
+					   range->offset, range->length))
+			continue;
+		/* offset(8) + length(8) + stateid(NFS4_STATEID_SIZE)
+		 * + deviceid(NFS4_DEVICEID4_SIZE) + status(4) + opnum(4)
+		 */
+		p = xdr_reserve_space(xdr,
+				24 + NFS4_STATEID_SIZE + NFS4_DEVICEID4_SIZE);
+		if (unlikely(!p))
+			return -ENOBUFS;
+		p = xdr_encode_hyper(p, err->offset);
+		p = xdr_encode_hyper(p, err->length);
+		p = xdr_encode_opaque_fixed(p, &err->stateid,
+					    NFS4_STATEID_SIZE);
+		p = xdr_encode_opaque_fixed(p, &err->deviceid,
+					    NFS4_DEVICEID4_SIZE);
+		*p++ = cpu_to_be32(err->status);
+		*p++ = cpu_to_be32(err->opnum);
+		*count += 1;
+		list_del(&err->list);
+		kfree(err);
+		dprintk("%s: offset %llu length %llu status %d op %d count %d\n",
+			__func__, err->offset, err->length, err->status,
+			err->opnum, *count);
+	}
+
+	return 0;
+}
+
+bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg)
+{
+	struct nfs4_ff_layout_mirror *mirror;
+	struct nfs4_deviceid_node *devid;
+	int idx;
+
+	for (idx = 0; idx < FF_LAYOUT_MIRROR_COUNT(lseg); idx++) {
+		mirror = FF_LAYOUT_COMP(lseg, idx);
+		if (mirror && mirror->mirror_ds) {
+			devid = &mirror->mirror_ds->id_node;
+			if (!ff_layout_test_devid_unavailable(devid))
+				return true;
+		}
+	}
+
+	return false;
+}
+
+module_param(dataserver_retrans, uint, 0644);
+MODULE_PARM_DESC(dataserver_retrans, "The  number of times the NFSv4.1 client "
+			"retries a request before it attempts further "
+			" recovery  action.");
+module_param(dataserver_timeo, uint, 0644);
+MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the "
+			"NFSv4.1  client  waits for a response from a "
+			" data server before it retries an NFS request.");

fs/nfs/idmap.c

@@ -152,7 +152,7 @@ void nfs_fattr_map_and_free_names(struct nfs_server *server, struct nfs_fattr *f
 		nfs_fattr_free_group_name(fattr);
 }
 
-static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res)
+int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res)
 {
 	unsigned long val;
 	char buf[16];
@@ -166,6 +166,7 @@ static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *re
 	*res = val;
 	return 1;
 }
+EXPORT_SYMBOL_GPL(nfs_map_string_to_numeric);
 
 static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen)
 {

fs/nfs/internal.h

@@ -6,6 +6,7 @@
 #include <linux/mount.h>
 #include <linux/security.h>
 #include <linux/crc32.h>
+#include <linux/nfs_page.h>
 
 #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
 
@@ -187,9 +188,15 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 					     const struct sockaddr *ds_addr,
 					     int ds_addrlen, int ds_proto,
 					     unsigned int ds_timeo,
-					     unsigned int ds_retrans);
+					     unsigned int ds_retrans,
+					     u32 minor_version,
+					     rpc_authflavor_t au_flavor);
 extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *,
 						struct inode *);
+extern struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
+			const struct sockaddr *ds_addr, int ds_addrlen,
+			int ds_proto, unsigned int ds_timeo,
+			unsigned int ds_retrans, rpc_authflavor_t au_flavor);
 #ifdef CONFIG_PROC_FS
 extern int __init nfs_fs_proc_init(void);
 extern void nfs_fs_proc_exit(void);
@@ -242,9 +249,12 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
 void nfs_pgio_header_free(struct nfs_pgio_header *);
 void nfs_pgio_data_destroy(struct nfs_pgio_header *);
 int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
-int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_header *,
+int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
-		      const struct rpc_call_ops *, int, int);
+		      struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
+		      const struct rpc_call_ops *call_ops, int how, int flags);
 void nfs_free_request(struct nfs_page *req);
+struct nfs_pgio_mirror *
+nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc);
 
 static inline void nfs_iocounter_init(struct nfs_io_counter *c)
 {
@@ -252,6 +262,12 @@ static inline void nfs_iocounter_init(struct nfs_io_counter *c)
 	atomic_set(&c->io_count, 0);
 }
 
+static inline bool nfs_pgio_has_mirroring(struct nfs_pageio_descriptor *desc)
+{
+	WARN_ON_ONCE(desc->pg_mirror_count < 1);
+	return desc->pg_mirror_count > 1;
+}
+
 /* nfs2xdr.c */
 extern struct rpc_procinfo nfs_procedures[];
 extern int nfs2_decode_dirent(struct xdr_stream *,
@@ -427,6 +443,7 @@ extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
 extern void nfs_commit_prepare(struct rpc_task *task, void *calldata);
 extern int nfs_initiate_commit(struct rpc_clnt *clnt,
 			       struct nfs_commit_data *data,
+			       const struct nfs_rpc_ops *nfs_ops,
 			       const struct rpc_call_ops *call_ops,
 			       int how, int flags);
 extern void nfs_init_commit(struct nfs_commit_data *data,
@@ -440,13 +457,15 @@ int nfs_scan_commit(struct inode *inode, struct list_head *dst,
 		    struct nfs_commit_info *cinfo);
 void nfs_mark_request_commit(struct nfs_page *req,
 			     struct pnfs_layout_segment *lseg,
-			     struct nfs_commit_info *cinfo);
+			     struct nfs_commit_info *cinfo,
+			     u32 ds_commit_idx);
 int nfs_write_need_commit(struct nfs_pgio_header *);
 int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
 			    int how, struct nfs_commit_info *cinfo);
 void nfs_retry_commit(struct list_head *page_list,
 		      struct pnfs_layout_segment *lseg,
-		      struct nfs_commit_info *cinfo);
+		      struct nfs_commit_info *cinfo,
+		      u32 ds_commit_idx);
 void nfs_commitdata_release(struct nfs_commit_data *data);
 void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
 				 struct nfs_commit_info *cinfo);
@@ -457,6 +476,7 @@ void nfs_init_cinfo(struct nfs_commit_info *cinfo,
 		    struct nfs_direct_req *dreq);
 int nfs_key_timeout_notify(struct file *filp, struct inode *inode);
 bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx);
+void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio);
 
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,
@@ -480,6 +500,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode)
 	inode_dio_wait(inode);
 }
 extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
+extern void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq);
 
 /* nfs4proc.c */
 extern void __nfs4_read_done_cb(struct nfs_pgio_header *);

fs/nfs/nfs2xdr.c

@@ -481,7 +481,8 @@ out_overflow:
  *		void;
  *	};
  */
-static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result)
+static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result,
+			   __u32 *op_status)
 {
 	enum nfs_stat status;
 	int error;
@@ -489,6 +490,8 @@ static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result)
 	error = decode_stat(xdr, &status);
 	if (unlikely(error))
 		goto out;
+	if (op_status)
+		*op_status = status;
 	if (status != NFS_OK)
 		goto out_default;
 	error = decode_fattr(xdr, result);
@@ -808,7 +811,7 @@ out_default:
 static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr,
 				 struct nfs_fattr *result)
 {
-	return decode_attrstat(xdr, result);
+	return decode_attrstat(xdr, result, NULL);
 }
 
 static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr,
@@ -865,6 +868,7 @@ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr,
 	error = decode_stat(xdr, &status);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS_OK)
 		goto out_default;
 	error = decode_fattr(xdr, result->fattr);
@@ -882,7 +886,7 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr,
 {
 	/* All NFSv2 writes are "file sync" writes */
 	result->verf->committed = NFS_FILE_SYNC;
-	return decode_attrstat(xdr, result->fattr);
+	return decode_attrstat(xdr, result->fattr, &result->op_status);
 }
 
 /**

fs/nfs/nfs3_fs.h

@@ -30,5 +30,7 @@ struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subver
 struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
 				     struct nfs_fattr *, rpc_authflavor_t);
 
+/* nfs3super.c */
+extern struct nfs_subversion nfs_v3;
 
 #endif /* __LINUX_FS_NFS_NFS3_FS_H */

fs/nfs/nfs3client.c

@@ -1,5 +1,6 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
+#include <linux/sunrpc/addr.h>
 #include "internal.h"
 #include "nfs3_fs.h"
 
@@ -64,3 +65,43 @@ struct nfs_server *nfs3_clone_server(struct nfs_server *source,
 		nfs_init_server_aclclient(server);
 	return server;
 }
+
+/*
+ * Set up a pNFS Data Server client over NFSv3.
+ *
+ * Return any existing nfs_client that matches server address,port,version
+ * and minorversion.
+ *
+ * For a new nfs_client, use a soft mount (default), a low retrans and a
+ * low timeout interval so that if a connection is lost, we retry through
+ * the MDS.
+ */
+struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
+		const struct sockaddr *ds_addr, int ds_addrlen,
+		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
+		rpc_authflavor_t au_flavor)
+{
+	struct nfs_client_initdata cl_init = {
+		.addr = ds_addr,
+		.addrlen = ds_addrlen,
+		.nfs_mod = &nfs_v3,
+		.proto = ds_proto,
+		.net = mds_clp->cl_net,
+	};
+	struct rpc_timeout ds_timeout;
+	struct nfs_client *clp;
+	char buf[INET6_ADDRSTRLEN + 1];
+
+	/* fake a hostname because lockd wants it */
+	if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0)
+		return ERR_PTR(-EINVAL);
+	cl_init.hostname = buf;
+
+	/* Use the MDS nfs_client cl_ipaddr. */
+	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
+	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
+			     au_flavor);
+
+	return clp;
+}
+EXPORT_SYMBOL_GPL(nfs3_set_ds_client);

fs/nfs/nfs3proc.c

@@ -800,6 +800,9 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
 	struct inode *inode = hdr->inode;
 
+	if (hdr->pgio_done_cb != NULL)
+		return hdr->pgio_done_cb(task, hdr);
+
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 
@@ -825,6 +828,9 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
 	struct inode *inode = hdr->inode;
 
+	if (hdr->pgio_done_cb != NULL)
+		return hdr->pgio_done_cb(task, hdr);
+
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 	if (task->tk_status >= 0)
@@ -845,6 +851,9 @@ static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commi
 
 static int nfs3_commit_done(struct rpc_task *task, struct nfs_commit_data *data)
 {
+	if (data->commit_done_cb != NULL)
+		return data->commit_done_cb(task, data);
+
 	if (nfs3_async_handle_jukebox(task, data->inode))
 		return -EAGAIN;
 	nfs_refresh_inode(data->inode, data->res.fattr);

fs/nfs/nfs3super.c

@@ -7,7 +7,7 @@
 #include "nfs3_fs.h"
 #include "nfs.h"
 
-static struct nfs_subversion nfs_v3 = {
+struct nfs_subversion nfs_v3 = {
 	.owner = THIS_MODULE,
 	.nfs_fs   = &nfs_fs_type,
 	.rpc_vers = &nfs_version3,

fs/nfs/nfs3xdr.c

@@ -1636,6 +1636,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 	error = decode_post_op_attr(xdr, result->fattr);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
 	error = decode_read3resok(xdr, result);
@@ -1708,6 +1709,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 	error = decode_wcc_data(xdr, result->fattr);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
 	error = decode_write3resok(xdr, result);
@@ -2323,6 +2325,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 	error = decode_wcc_data(xdr, result->fattr);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
 	error = decode_writeverf3(xdr, &result->verf->verifier);

fs/nfs/nfs4_fs.h

@@ -446,6 +446,12 @@ extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_release_seqid(struct nfs_seqid *seqid);
 extern void nfs_free_seqid(struct nfs_seqid *seqid);
+extern int nfs40_setup_sequence(struct nfs4_slot_table *tbl,
+				struct nfs4_sequence_args *args,
+				struct nfs4_sequence_res *res,
+				struct rpc_task *task);
+extern int nfs4_sequence_done(struct rpc_task *task,
+			      struct nfs4_sequence_res *res);
 
 extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp);
 

fs/nfs/nfs4client.c

@@ -849,14 +849,15 @@ error:
  */
 struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 		const struct sockaddr *ds_addr, int ds_addrlen,
-		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
+		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
+		u32 minor_version, rpc_authflavor_t au_flavor)
 {
 	struct nfs_client_initdata cl_init = {
 		.addr = ds_addr,
 		.addrlen = ds_addrlen,
 		.nfs_mod = &nfs_v4,
 		.proto = ds_proto,
-		.minorversion = mds_clp->cl_minorversion,
+		.minorversion = minor_version,
 		.net = mds_clp->cl_net,
 	};
 	struct rpc_timeout ds_timeout;
@@ -874,7 +875,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 	 */
 	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
 	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
-			     mds_clp->cl_rpcclient->cl_auth->au_flavor);
+			     au_flavor);
 
 	dprintk("<-- %s %p\n", __func__, clp);
 	return clp;

fs/nfs/nfs4proc.c

@@ -495,12 +495,11 @@ static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args)
 	args->sa_privileged = 1;
 }
 
-static int nfs40_setup_sequence(const struct nfs_server *server,
+int nfs40_setup_sequence(struct nfs4_slot_table *tbl,
 			 struct nfs4_sequence_args *args,
 			 struct nfs4_sequence_res *res,
 			 struct rpc_task *task)
 {
-	struct nfs4_slot_table *tbl = server->nfs_client->cl_slot_tbl;
 	struct nfs4_slot *slot;
 
 	/* slot already allocated? */
@@ -535,6 +534,7 @@ out_sleep:
 	spin_unlock(&tbl->slot_tbl_lock);
 	return -EAGAIN;
 }
+EXPORT_SYMBOL_GPL(nfs40_setup_sequence);
 
 static int nfs40_sequence_done(struct rpc_task *task,
 			       struct nfs4_sequence_res *res)
@@ -694,8 +694,7 @@ out_retry:
 }
 EXPORT_SYMBOL_GPL(nfs41_sequence_done);
 
-static int nfs4_sequence_done(struct rpc_task *task,
+int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
-			       struct nfs4_sequence_res *res)
 {
 	if (res->sr_slot == NULL)
 		return 1;
@@ -703,6 +702,7 @@ static int nfs4_sequence_done(struct rpc_task *task,
 		return nfs40_sequence_done(task, res);
 	return nfs41_sequence_done(task, res);
 }
+EXPORT_SYMBOL_GPL(nfs4_sequence_done);
 
 int nfs41_setup_sequence(struct nfs4_session *session,
 				struct nfs4_sequence_args *args,
@@ -777,7 +777,8 @@ static int nfs4_setup_sequence(const struct nfs_server *server,
 	int ret = 0;
 
 	if (!session)
-		return nfs40_setup_sequence(server, args, res, task);
+		return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
+					    args, res, task);
 
 	dprintk("--> %s clp %p session %p sr_slot %u\n",
 		__func__, session->clp, session, res->sr_slot ?
@@ -818,14 +819,16 @@ static int nfs4_setup_sequence(const struct nfs_server *server,
 			       struct nfs4_sequence_res *res,
 			       struct rpc_task *task)
 {
-	return nfs40_setup_sequence(server, args, res, task);
+	return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
+				    args, res, task);
 }
 
-static int nfs4_sequence_done(struct rpc_task *task,
+int nfs4_sequence_done(struct rpc_task *task,
 		       struct nfs4_sequence_res *res)
 {
 	return nfs40_sequence_done(task, res);
 }
+EXPORT_SYMBOL_GPL(nfs4_sequence_done);
 
 #endif	/* !CONFIG_NFS_V4_1 */
 
@@ -1712,8 +1715,8 @@ static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_opendata *data = calldata;
 
-	nfs40_setup_sequence(data->o_arg.server, &data->c_arg.seq_args,
+	nfs40_setup_sequence(data->o_arg.server->nfs_client->cl_slot_tbl,
-				&data->c_res.seq_res, task);
+			     &data->c_arg.seq_args, &data->c_res.seq_res, task);
 }
 
 static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
@@ -5994,8 +5997,8 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata
 {
 	struct nfs_release_lockowner_data *data = calldata;
 	struct nfs_server *server = data->server;
-	nfs40_setup_sequence(server, &data->args.seq_args,
+	nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
-				&data->res.seq_res, task);
+			     &data->args.seq_args, &data->res.seq_res, task);
 	data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
 	data->timestamp = jiffies;
 }
@@ -7557,6 +7560,7 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 		return;
 	if (pnfs_choose_layoutget_stateid(&lgp->args.stateid,
 					  NFS_I(lgp->args.inode)->layout,
+					  &lgp->args.range,
 					  lgp->args.ctx->state)) {
 		rpc_exit(task, NFS4_OK);
 	}
@@ -7812,6 +7816,9 @@ static void nfs4_layoutreturn_release(void *calldata)
 	spin_lock(&lo->plh_inode->i_lock);
 	if (lrp->res.lrs_present)
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+	pnfs_clear_layoutreturn_waitbit(lo);
+	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
+	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 	lo->plh_block_lgets--;
 	spin_unlock(&lo->plh_inode->i_lock);
 	pnfs_put_layout_hdr(lrp->args.layout);
@@ -7825,7 +7832,7 @@ static const struct rpc_call_ops nfs4_layoutreturn_call_ops = {
 	.rpc_release = nfs4_layoutreturn_release,
 };
 
-int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
+int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync)
 {
 	struct rpc_task *task;
 	struct rpc_message msg = {
@@ -7839,16 +7846,23 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
 		.rpc_message = &msg,
 		.callback_ops = &nfs4_layoutreturn_call_ops,
 		.callback_data = lrp,
+		.flags = RPC_TASK_ASYNC,
 	};
-	int status;
+	int status = 0;
 
 	dprintk("--> %s\n", __func__);
 	nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1);
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
+	if (sync == false)
+		goto out;
+	status = nfs4_wait_for_completion_rpc_task(task);
+	if (status != 0)
+		goto out;
 	status = task->tk_status;
 	trace_nfs4_layoutreturn(lrp->args.inode, status);
+out:
 	dprintk("<-- %s status=%d\n", __func__, status);
 	rpc_put_task(task);
 	return status;

fs/nfs/nfs4super.c

@@ -346,6 +346,9 @@ out:
 
 static void __exit exit_nfs_v4(void)
 {
+	/* Not called in the _init(), conditionally loaded */
+	nfs4_pnfs_v3_ds_connect_unload();
+
 	unregister_nfs_version(&nfs_v4);
 	nfs4_unregister_sysctl();
 	nfs_idmap_quit();

fs/nfs/nfs4xdr.c

@@ -2011,11 +2011,11 @@ encode_layoutreturn(struct xdr_stream *xdr,
 	p = reserve_space(xdr, 16);
 	*p++ = cpu_to_be32(0);		/* reclaim. always 0 for now */
 	*p++ = cpu_to_be32(args->layout_type);
-	*p++ = cpu_to_be32(IOMODE_ANY);
+	*p++ = cpu_to_be32(args->range.iomode);
 	*p = cpu_to_be32(RETURN_FILE);
 	p = reserve_space(xdr, 16);
-	p = xdr_encode_hyper(p, 0);
+	p = xdr_encode_hyper(p, args->range.offset);
-	p = xdr_encode_hyper(p, NFS4_MAX_UINT64);
+	p = xdr_encode_hyper(p, args->range.length);
 	spin_lock(&args->inode->i_lock);
 	encode_nfs4_stateid(xdr, &args->stateid);
 	spin_unlock(&args->inode->i_lock);
@@ -6566,6 +6566,7 @@ static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	int status;
 
 	status = decode_compound_hdr(xdr, &hdr);
+	res->op_status = hdr.status;
 	if (status)
 		goto out;
 	status = decode_sequence(xdr, &res->seq_res, rqstp);
@@ -6591,6 +6592,7 @@ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	int status;
 
 	status = decode_compound_hdr(xdr, &hdr);
+	res->op_status = hdr.status;
 	if (status)
 		goto out;
 	status = decode_sequence(xdr, &res->seq_res, rqstp);
@@ -6620,6 +6622,7 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	int status;
 
 	status = decode_compound_hdr(xdr, &hdr);
+	res->op_status = hdr.status;
 	if (status)
 		goto out;
 	status = decode_sequence(xdr, &res->seq_res, rqstp);

fs/nfs/objlayout/objio_osd.c

@@ -537,11 +537,12 @@ int objio_write_pagelist(struct nfs_pgio_header *hdr, int how)
 static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio,
 			  struct nfs_page *prev, struct nfs_page *req)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(pgio);
 	unsigned int size;
 
 	size = pnfs_generic_pg_test(pgio, prev, req);
 
-	if (!size || pgio->pg_count + req->wb_bytes >
+	if (!size || mirror->pg_count + req->wb_bytes >
 	    (unsigned long)pgio->pg_layout_private)
 		return 0;
 
@@ -607,12 +608,14 @@ static const struct nfs_pageio_ops objio_pg_read_ops = {
 	.pg_init = objio_init_read,
 	.pg_test = objio_pg_test,
 	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static const struct nfs_pageio_ops objio_pg_write_ops = {
 	.pg_init = objio_init_write,
 	.pg_test = objio_pg_test,
 	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static struct pnfs_layoutdriver_type objlayout_type = {

fs/nfs/pagelist.c

@@ -42,21 +42,35 @@ static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
 	return p->pagevec != NULL;
 }
 
+struct nfs_pgio_mirror *
+nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc)
+{
+	return nfs_pgio_has_mirroring(desc) ?
+		&desc->pg_mirrors[desc->pg_mirror_idx] :
+		&desc->pg_mirrors[0];
+}
+EXPORT_SYMBOL_GPL(nfs_pgio_current_mirror);
+
 void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 		       struct nfs_pgio_header *hdr,
 		       void (*release)(struct nfs_pgio_header *hdr))
 {
-	hdr->req = nfs_list_entry(desc->pg_list.next);
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
+
+	hdr->req = nfs_list_entry(mirror->pg_list.next);
 	hdr->inode = desc->pg_inode;
 	hdr->cred = hdr->req->wb_context->cred;
 	hdr->io_start = req_offset(hdr->req);
-	hdr->good_bytes = desc->pg_count;
+	hdr->good_bytes = mirror->pg_count;
 	hdr->dreq = desc->pg_dreq;
 	hdr->layout_private = desc->pg_layout_private;
 	hdr->release = release;
 	hdr->completion_ops = desc->pg_completion_ops;
 	if (hdr->completion_ops->init_hdr)
 		hdr->completion_ops->init_hdr(hdr);
+
+	hdr->pgio_mirror_idx = desc->pg_mirror_idx;
 }
 EXPORT_SYMBOL_GPL(nfs_pgheader_init);
 
@@ -480,7 +494,10 @@ nfs_wait_on_request(struct nfs_page *req)
 size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 			   struct nfs_page *prev, struct nfs_page *req)
 {
-	if (desc->pg_count > desc->pg_bsize) {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
+
+	if (mirror->pg_count > mirror->pg_bsize) {
 		/* should never happen */
 		WARN_ON_ONCE(1);
 		return 0;
@@ -490,11 +507,11 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 	 * Limit the request size so that we can still allocate a page array
 	 * for it without upsetting the slab allocator.
 	 */
-	if (((desc->pg_count + req->wb_bytes) >> PAGE_SHIFT) *
+	if (((mirror->pg_count + req->wb_bytes) >> PAGE_SHIFT) *
 			sizeof(struct page) > PAGE_SIZE)
 		return 0;
 
-	return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes);
+	return min(mirror->pg_bsize - mirror->pg_count, (size_t)req->wb_bytes);
 }
 EXPORT_SYMBOL_GPL(nfs_generic_pg_test);
 
@@ -597,13 +614,14 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata)
 }
 
 int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
+		      struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
 		      const struct rpc_call_ops *call_ops, int how, int flags)
 {
 	struct rpc_task *task;
 	struct rpc_message msg = {
 		.rpc_argp = &hdr->args,
 		.rpc_resp = &hdr->res,
-		.rpc_cred = hdr->cred,
+		.rpc_cred = cred,
 	};
 	struct rpc_task_setup task_setup_data = {
 		.rpc_client = clnt,
@@ -616,7 +634,7 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
 	};
 	int ret = 0;
 
-	hdr->rw_ops->rw_initiate(hdr, &msg, &task_setup_data, how);
+	hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how);
 
 	dprintk("NFS: %5u initiated pgio call "
 		"(req %s/%llu, %u bytes @ offset %llu)\n",
@@ -650,10 +668,18 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio);
 static int nfs_pgio_error(struct nfs_pageio_descriptor *desc,
 			  struct nfs_pgio_header *hdr)
 {
+	struct nfs_pgio_mirror *mirror;
+	u32 midx;
+
 	set_bit(NFS_IOHDR_REDO, &hdr->flags);
 	nfs_pgio_data_destroy(hdr);
 	hdr->completion_ops->completion(hdr);
-	desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+	/* TODO: Make sure it's right to clean up all mirrors here
+	 *       and not just hdr->pgio_mirror_idx */
+	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
+		mirror = &desc->pg_mirrors[midx];
+		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
+	}
 	return -ENOMEM;
 }
 
@@ -670,6 +696,17 @@ static void nfs_pgio_release(void *calldata)
 	hdr->completion_ops->completion(hdr);
 }
 
+static void nfs_pageio_mirror_init(struct nfs_pgio_mirror *mirror,
+				   unsigned int bsize)
+{
+	INIT_LIST_HEAD(&mirror->pg_list);
+	mirror->pg_bytes_written = 0;
+	mirror->pg_count = 0;
+	mirror->pg_bsize = bsize;
+	mirror->pg_base = 0;
+	mirror->pg_recoalesce = 0;
+}
+
 /**
  * nfs_pageio_init - initialise a page io descriptor
  * @desc: pointer to descriptor
@@ -686,13 +723,10 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 		     size_t bsize,
 		     int io_flags)
 {
-	INIT_LIST_HEAD(&desc->pg_list);
+	struct nfs_pgio_mirror *new;
-	desc->pg_bytes_written = 0;
+	int i;
-	desc->pg_count = 0;
+
-	desc->pg_bsize = bsize;
-	desc->pg_base = 0;
 	desc->pg_moreio = 0;
-	desc->pg_recoalesce = 0;
 	desc->pg_inode = inode;
 	desc->pg_ops = pg_ops;
 	desc->pg_completion_ops = compl_ops;
@@ -702,6 +736,26 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_lseg = NULL;
 	desc->pg_dreq = NULL;
 	desc->pg_layout_private = NULL;
+	desc->pg_bsize = bsize;
+
+	desc->pg_mirror_count = 1;
+	desc->pg_mirror_idx = 0;
+
+	if (pg_ops->pg_get_mirror_count) {
+		/* until we have a request, we don't have an lseg and no
+		 * idea how many mirrors there will be */
+		new = kcalloc(NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX,
+			      sizeof(struct nfs_pgio_mirror), GFP_KERNEL);
+		desc->pg_mirrors_dynamic = new;
+		desc->pg_mirrors = new;
+
+		for (i = 0; i < NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX; i++)
+			nfs_pageio_mirror_init(&desc->pg_mirrors[i], bsize);
+	} else {
+		desc->pg_mirrors_dynamic = NULL;
+		desc->pg_mirrors = desc->pg_mirrors_static;
+		nfs_pageio_mirror_init(&desc->pg_mirrors[0], bsize);
+	}
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_init);
 
@@ -737,14 +791,16 @@ static void nfs_pgio_result(struct rpc_task *task, void *calldata)
 int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 		     struct nfs_pgio_header *hdr)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	struct nfs_page		*req;
 	struct page		**pages,
 				*last_page;
-	struct list_head *head = &desc->pg_list;
+	struct list_head *head = &mirror->pg_list;
 	struct nfs_commit_info cinfo;
 	unsigned int pagecount, pageused;
 
-	pagecount = nfs_page_array_len(desc->pg_base, desc->pg_count);
+	pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count);
 	if (!nfs_pgarray_set(&hdr->page_array, pagecount))
 		return nfs_pgio_error(desc, hdr);
 
@@ -772,7 +828,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
 
 	/* Set up the argument struct */
-	nfs_pgio_rpcsetup(hdr, desc->pg_count, 0, desc->pg_ioflags, &cinfo);
+	nfs_pgio_rpcsetup(hdr, mirror->pg_count, 0, desc->pg_ioflags, &cinfo);
 	desc->pg_rpc_callops = &nfs_pgio_common_ops;
 	return 0;
 }
@@ -780,23 +836,74 @@ EXPORT_SYMBOL_GPL(nfs_generic_pgio);
 
 static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
 {
+	struct nfs_pgio_mirror *mirror;
 	struct nfs_pgio_header *hdr;
 	int ret;
 
+	mirror = nfs_pgio_current_mirror(desc);
+
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
-		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+		/* TODO: make sure this is right with mirroring - or
+		 *       should it back out all mirrors? */
+		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
 		return -ENOMEM;
 	}
 	nfs_pgheader_init(desc, hdr, nfs_pgio_header_free);
 	ret = nfs_generic_pgio(desc, hdr);
 	if (ret == 0)
 		ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode),
-					hdr, desc->pg_rpc_callops,
+					hdr,
+					hdr->cred,
+					NFS_PROTO(hdr->inode),
+					desc->pg_rpc_callops,
 					desc->pg_ioflags, 0);
 	return ret;
 }
 
+/*
+ * nfs_pageio_setup_mirroring - determine if mirroring is to be used
+ *				by calling the pg_get_mirror_count op
+ */
+static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio,
+				       struct nfs_page *req)
+{
+	int mirror_count = 1;
+
+	if (!pgio->pg_ops->pg_get_mirror_count)
+		return 0;
+
+	mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req);
+
+	if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX)
+		return -EINVAL;
+
+	if (WARN_ON_ONCE(!pgio->pg_mirrors_dynamic))
+		return -EINVAL;
+
+	pgio->pg_mirror_count = mirror_count;
+
+	return 0;
+}
+
+/*
+ * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1)
+ */
+void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio)
+{
+	pgio->pg_mirror_count = 1;
+	pgio->pg_mirror_idx = 0;
+}
+
+static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio)
+{
+	pgio->pg_mirror_count = 1;
+	pgio->pg_mirror_idx = 0;
+	pgio->pg_mirrors = pgio->pg_mirrors_static;
+	kfree(pgio->pg_mirrors_dynamic);
+	pgio->pg_mirrors_dynamic = NULL;
+}
+
 static bool nfs_match_open_context(const struct nfs_open_context *ctx1,
 		const struct nfs_open_context *ctx2)
 {
@@ -863,19 +970,22 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
 				     struct nfs_page *req)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	struct nfs_page *prev = NULL;
-	if (desc->pg_count != 0) {
+
-		prev = nfs_list_entry(desc->pg_list.prev);
+	if (mirror->pg_count != 0) {
+		prev = nfs_list_entry(mirror->pg_list.prev);
 	} else {
 		if (desc->pg_ops->pg_init)
 			desc->pg_ops->pg_init(desc, req);
-		desc->pg_base = req->wb_pgbase;
+		mirror->pg_base = req->wb_pgbase;
 	}
 	if (!nfs_can_coalesce_requests(prev, req, desc))
 		return 0;
 	nfs_list_remove_request(req);
-	nfs_list_add_request(req, &desc->pg_list);
+	nfs_list_add_request(req, &mirror->pg_list);
-	desc->pg_count += req->wb_bytes;
+	mirror->pg_count += req->wb_bytes;
 	return 1;
 }
 
@@ -884,16 +994,19 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
  */
 static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
 {
-	if (!list_empty(&desc->pg_list)) {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
+
+	if (!list_empty(&mirror->pg_list)) {
 		int error = desc->pg_ops->pg_doio(desc);
 		if (error < 0)
 			desc->pg_error = error;
 		else
-			desc->pg_bytes_written += desc->pg_count;
+			mirror->pg_bytes_written += mirror->pg_count;
 	}
-	if (list_empty(&desc->pg_list)) {
+	if (list_empty(&mirror->pg_list)) {
-		desc->pg_count = 0;
+		mirror->pg_count = 0;
-		desc->pg_base = 0;
+		mirror->pg_base = 0;
 	}
 }
 
@@ -911,6 +1024,8 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
 static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			   struct nfs_page *req)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	struct nfs_page *subreq;
 	unsigned int bytes_left = 0;
 	unsigned int offset, pgbase;
@@ -934,7 +1049,7 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			nfs_pageio_doio(desc);
 			if (desc->pg_error < 0)
 				return 0;
-			if (desc->pg_recoalesce)
+			if (mirror->pg_recoalesce)
 				return 0;
 			/* retry add_request for this subreq */
 			nfs_page_group_lock(req, false);
@@ -972,14 +1087,16 @@ err_ptr:
 
 static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
 	LIST_HEAD(head);
 
 	do {
-		list_splice_init(&desc->pg_list, &head);
+		list_splice_init(&mirror->pg_list, &head);
-		desc->pg_bytes_written -= desc->pg_count;
+		mirror->pg_bytes_written -= mirror->pg_count;
-		desc->pg_count = 0;
+		mirror->pg_count = 0;
-		desc->pg_base = 0;
+		mirror->pg_base = 0;
-		desc->pg_recoalesce = 0;
+		mirror->pg_recoalesce = 0;
+
 		desc->pg_moreio = 0;
 
 		while (!list_empty(&head)) {
@@ -993,11 +1110,11 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
 				return 0;
 			break;
 		}
-	} while (desc->pg_recoalesce);
+	} while (mirror->pg_recoalesce);
 	return 1;
 }
 
-int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
+static int nfs_pageio_add_request_mirror(struct nfs_pageio_descriptor *desc,
 		struct nfs_page *req)
 {
 	int ret;
@@ -1010,9 +1127,80 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			break;
 		ret = nfs_do_recoalesce(desc);
 	} while (ret);
+
 	return ret;
 }
 
+int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
+			   struct nfs_page *req)
+{
+	u32 midx;
+	unsigned int pgbase, offset, bytes;
+	struct nfs_page *dupreq, *lastreq;
+
+	pgbase = req->wb_pgbase;
+	offset = req->wb_offset;
+	bytes = req->wb_bytes;
+
+	nfs_pageio_setup_mirroring(desc, req);
+
+	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
+		if (midx) {
+			nfs_page_group_lock(req, false);
+
+			/* find the last request */
+			for (lastreq = req->wb_head;
+			     lastreq->wb_this_page != req->wb_head;
+			     lastreq = lastreq->wb_this_page)
+				;
+
+			dupreq = nfs_create_request(req->wb_context,
+					req->wb_page, lastreq, pgbase, bytes);
+
+			if (IS_ERR(dupreq)) {
+				nfs_page_group_unlock(req);
+				return 0;
+			}
+
+			nfs_lock_request(dupreq);
+			nfs_page_group_unlock(req);
+			dupreq->wb_offset = offset;
+			dupreq->wb_index = req->wb_index;
+		} else
+			dupreq = req;
+
+		if (nfs_pgio_has_mirroring(desc))
+			desc->pg_mirror_idx = midx;
+		if (!nfs_pageio_add_request_mirror(desc, dupreq))
+			return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * nfs_pageio_complete_mirror - Complete I/O on the current mirror of an
+ *				nfs_pageio_descriptor
+ * @desc: pointer to io descriptor
+ */
+static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc,
+				       u32 mirror_idx)
+{
+	struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx];
+	u32 restore_idx = desc->pg_mirror_idx;
+
+	if (nfs_pgio_has_mirroring(desc))
+		desc->pg_mirror_idx = mirror_idx;
+	for (;;) {
+		nfs_pageio_doio(desc);
+		if (!mirror->pg_recoalesce)
+			break;
+		if (!nfs_do_recoalesce(desc))
+			break;
+	}
+	desc->pg_mirror_idx = restore_idx;
+}
+
 /*
  * nfs_pageio_resend - Transfer requests to new descriptor and resend
  * @hdr - the pgio header to move request from
@@ -1046,18 +1234,19 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
 EXPORT_SYMBOL_GPL(nfs_pageio_resend);
 
 /**
- * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor
+ * nfs_pageio_complete - Complete I/O then cleanup an nfs_pageio_descriptor
  * @desc: pointer to io descriptor
  */
 void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
 {
-	for (;;) {
+	u32 midx;
-		nfs_pageio_doio(desc);
+
-		if (!desc->pg_recoalesce)
+	for (midx = 0; midx < desc->pg_mirror_count; midx++)
-			break;
+		nfs_pageio_complete_mirror(desc, midx);
-		if (!nfs_do_recoalesce(desc))
+
-			break;
+	if (desc->pg_ops->pg_cleanup)
-	}
+		desc->pg_ops->pg_cleanup(desc);
+	nfs_pageio_cleanup_mirroring(desc);
 }
 
 /**
@@ -1073,10 +1262,17 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
  */
 void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
 {
-	if (!list_empty(&desc->pg_list)) {
+	struct nfs_pgio_mirror *mirror;
-		struct nfs_page *prev = nfs_list_entry(desc->pg_list.prev);
+	struct nfs_page *prev;
+	u32 midx;
+
+	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
+		mirror = &desc->pg_mirrors[midx];
+		if (!list_empty(&mirror->pg_list)) {
+			prev = nfs_list_entry(mirror->pg_list.prev);
 			if (index != prev->wb_index + 1)
-			nfs_pageio_complete(desc);
+				nfs_pageio_complete_mirror(desc, midx);
+		}
 	}
 }
 

fs/nfs/pnfs.c

@@ -51,6 +51,10 @@ static DEFINE_SPINLOCK(pnfs_spinlock);
  */
 static LIST_HEAD(pnfs_modules_tbl);
 
+static int
+pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
+		       enum pnfs_iomode iomode, bool sync);
+
 /* Return the registered pnfs layout driver module matching given id */
 static struct pnfs_layoutdriver_type *
 find_pnfs_driver_locked(u32 id)
@@ -239,6 +243,8 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 	struct inode *inode = lo->plh_inode;
 
 	if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
+		if (!list_empty(&lo->plh_segs))
+			WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n");
 		pnfs_detach_layout_hdr(lo);
 		spin_unlock(&inode->i_lock);
 		pnfs_free_layout_hdr(lo);
@@ -338,6 +344,65 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
 	rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
 }
 
+/* Return true if layoutreturn is needed */
+static bool
+pnfs_layout_need_return(struct pnfs_layout_hdr *lo,
+			struct pnfs_layout_segment *lseg)
+{
+	struct pnfs_layout_segment *s;
+
+	if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+		return false;
+
+	list_for_each_entry(s, &lo->plh_segs, pls_list)
+		if (s != lseg && test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
+			return false;
+
+	return true;
+}
+
+static void pnfs_layoutreturn_free_lseg(struct work_struct *work)
+{
+	struct pnfs_layout_segment *lseg;
+	struct pnfs_layout_hdr *lo;
+	struct inode *inode;
+
+	lseg = container_of(work, struct pnfs_layout_segment, pls_work);
+	WARN_ON(atomic_read(&lseg->pls_refcount));
+	lo = lseg->pls_layout;
+	inode = lo->plh_inode;
+
+	spin_lock(&inode->i_lock);
+	if (pnfs_layout_need_return(lo, lseg)) {
+		nfs4_stateid stateid;
+		enum pnfs_iomode iomode;
+
+		stateid = lo->plh_stateid;
+		iomode = lo->plh_return_iomode;
+		/* decreased in pnfs_send_layoutreturn() */
+		lo->plh_block_lgets++;
+		lo->plh_return_iomode = 0;
+		spin_unlock(&inode->i_lock);
+
+		pnfs_send_layoutreturn(lo, stateid, iomode, true);
+		spin_lock(&inode->i_lock);
+	} else
+		/* match pnfs_get_layout_hdr #2 in pnfs_put_lseg */
+		pnfs_put_layout_hdr(lo);
+	pnfs_layout_remove_lseg(lo, lseg);
+	spin_unlock(&inode->i_lock);
+	pnfs_free_lseg(lseg);
+	/* match pnfs_get_layout_hdr #1 in pnfs_put_lseg */
+	pnfs_put_layout_hdr(lo);
+}
+
+static void
+pnfs_layoutreturn_free_lseg_async(struct pnfs_layout_segment *lseg)
+{
+	INIT_WORK(&lseg->pls_work, pnfs_layoutreturn_free_lseg);
+	queue_work(nfsiod_workqueue, &lseg->pls_work);
+}
+
 void
 pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {
@@ -354,12 +419,19 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 	inode = lo->plh_inode;
 	if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
 		pnfs_get_layout_hdr(lo);
+		if (pnfs_layout_need_return(lo, lseg)) {
+			spin_unlock(&inode->i_lock);
+			/* hdr reference dropped in nfs4_layoutreturn_release */
+			pnfs_get_layout_hdr(lo);
+			pnfs_layoutreturn_free_lseg_async(lseg);
+		} else {
 			pnfs_layout_remove_lseg(lo, lseg);
 			spin_unlock(&inode->i_lock);
 			pnfs_free_lseg(lseg);
 			pnfs_put_layout_hdr(lo);
 		}
 	}
+}
 EXPORT_SYMBOL_GPL(pnfs_put_lseg);
 
 static void pnfs_free_lseg_async_work(struct work_struct *work)
@@ -544,6 +616,7 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 		pnfs_get_layout_hdr(lo);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
+		pnfs_clear_retry_layoutget(lo);
 		spin_unlock(&nfsi->vfs_inode.i_lock);
 		pnfs_free_lseg_list(&tmp_list);
 		pnfs_put_layout_hdr(lo);
@@ -741,25 +814,37 @@ pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo,
 	return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
 }
 
+static bool
+pnfs_layout_returning(const struct pnfs_layout_hdr *lo,
+		      struct pnfs_layout_range *range)
+{
+	return test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) &&
+		(lo->plh_return_iomode == IOMODE_ANY ||
+		 lo->plh_return_iomode == range->iomode);
+}
+
 /* lget is set to 1 if called from inside send_layoutget call chain */
 static bool
-pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo, int lget)
+pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo,
+			struct pnfs_layout_range *range, int lget)
 {
 	return lo->plh_block_lgets ||
 		test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
 		(list_empty(&lo->plh_segs) &&
-		 (atomic_read(&lo->plh_outstanding) > lget));
+		 (atomic_read(&lo->plh_outstanding) > lget)) ||
+		pnfs_layout_returning(lo, range);
 }
 
 int
 pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
+			      struct pnfs_layout_range *range,
 			      struct nfs4_state *open_state)
 {
 	int status = 0;
 
 	dprintk("--> %s\n", __func__);
 	spin_lock(&lo->plh_inode->i_lock);
-	if (pnfs_layoutgets_blocked(lo, 1)) {
+	if (pnfs_layoutgets_blocked(lo, range, 1)) {
 		status = -EAGAIN;
 	} else if (!nfs4_valid_open_stateid(open_state)) {
 		status = -EBADF;
@@ -826,7 +911,9 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 			pnfs_layout_io_set_failed(lo, range->iomode);
 		}
 		return NULL;
-	}
+	} else
+		pnfs_layout_clear_fail_bit(lo,
+				pnfs_iomode_to_fail_bit(range->iomode));
 
 	return lseg;
 }
@@ -846,6 +933,49 @@ static void pnfs_clear_layoutcommit(struct inode *inode,
 	}
 }
 
+void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
+{
+	clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
+}
+
+static int
+pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
+		       enum pnfs_iomode iomode, bool sync)
+{
+	struct inode *ino = lo->plh_inode;
+	struct nfs4_layoutreturn *lrp;
+	int status = 0;
+
+	lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
+	if (unlikely(lrp == NULL)) {
+		status = -ENOMEM;
+		spin_lock(&ino->i_lock);
+		lo->plh_block_lgets--;
+		pnfs_clear_layoutreturn_waitbit(lo);
+		rpc_wake_up(&NFS_SERVER(ino)->roc_rpcwaitq);
+		spin_unlock(&ino->i_lock);
+		pnfs_put_layout_hdr(lo);
+		goto out;
+	}
+
+	lrp->args.stateid = stateid;
+	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
+	lrp->args.inode = ino;
+	lrp->args.range.iomode = iomode;
+	lrp->args.range.offset = 0;
+	lrp->args.range.length = NFS4_MAX_UINT64;
+	lrp->args.layout = lo;
+	lrp->clp = NFS_SERVER(ino)->nfs_client;
+	lrp->cred = lo->plh_lc_cred;
+
+	status = nfs4_proc_layoutreturn(lrp, sync);
+out:
+	dprintk("<-- %s status: %d\n", __func__, status);
+	return status;
+}
+
 /*
  * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
  * when the layout segment list is empty.
@@ -860,7 +990,6 @@ _pnfs_return_layout(struct inode *ino)
 	struct pnfs_layout_hdr *lo = NULL;
 	struct nfs_inode *nfsi = NFS_I(ino);
 	LIST_HEAD(tmp_list);
-	struct nfs4_layoutreturn *lrp;
 	nfs4_stateid stateid;
 	int status = 0, empty;
 
@@ -902,24 +1031,7 @@ _pnfs_return_layout(struct inode *ino)
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 
-	lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
+	status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
-	if (unlikely(lrp == NULL)) {
-		status = -ENOMEM;
-		spin_lock(&ino->i_lock);
-		lo->plh_block_lgets--;
-		spin_unlock(&ino->i_lock);
-		pnfs_put_layout_hdr(lo);
-		goto out;
-	}
-
-	lrp->args.stateid = stateid;
-	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
-	lrp->args.inode = ino;
-	lrp->args.layout = lo;
-	lrp->clp = NFS_SERVER(ino)->nfs_client;
-	lrp->cred = lo->plh_lc_cred;
-
-	status = nfs4_proc_layoutreturn(lrp);
 out:
 	dprintk("<-- %s status: %d\n", __func__, status);
 	return status;
@@ -960,8 +1072,9 @@ bool pnfs_roc(struct inode *ino)
 	struct nfs4_state *state;
 	struct pnfs_layout_hdr *lo;
 	struct pnfs_layout_segment *lseg, *tmp;
+	nfs4_stateid stateid;
 	LIST_HEAD(tmp_list);
-	bool found = false;
+	bool found = false, layoutreturn = false;
 
 	spin_lock(&ino->i_lock);
 	lo = nfsi->layout;
@@ -980,6 +1093,8 @@ bool pnfs_roc(struct inode *ino)
 			goto out_noroc;
 	}
 
+		goto out_noroc;
+	pnfs_clear_retry_layoutget(lo);
 	list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list)
 		if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
 			mark_lseg_invalid(lseg, &tmp_list);
@@ -994,7 +1109,19 @@ bool pnfs_roc(struct inode *ino)
 	return true;
 
 out_noroc:
+	if (lo) {
+		stateid = lo->plh_stateid;
+		layoutreturn =
+			test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					   &lo->plh_flags);
+		if (layoutreturn) {
+			lo->plh_block_lgets++;
+			pnfs_get_layout_hdr(lo);
+		}
+	}
 	spin_unlock(&ino->i_lock);
+	if (layoutreturn)
+		pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
 	return false;
 }
 
@@ -1029,8 +1156,9 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 	struct nfs_inode *nfsi = NFS_I(ino);
 	struct pnfs_layout_hdr *lo;
 	struct pnfs_layout_segment *lseg;
+	nfs4_stateid stateid;
 	u32 current_seqid;
-	bool found = false;
+	bool found = false, layoutreturn = false;
 
 	spin_lock(&ino->i_lock);
 	list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list)
@@ -1047,7 +1175,21 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 	 */
 	*barrier = current_seqid + atomic_read(&lo->plh_outstanding);
 out:
+	if (!found) {
+		stateid = lo->plh_stateid;
+		layoutreturn =
+			test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					   &lo->plh_flags);
+		if (layoutreturn) {
+			lo->plh_block_lgets++;
+			pnfs_get_layout_hdr(lo);
+		}
+	}
 	spin_unlock(&ino->i_lock);
+	if (layoutreturn) {
+		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+		pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, false);
+	}
 	return found;
 }
 
@@ -1194,6 +1336,7 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
 
 	list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
 		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
+		    !test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags) &&
 		    pnfs_lseg_range_match(&lseg->pls_range, range)) {
 			ret = pnfs_get_lseg(lseg);
 			break;
@@ -1282,6 +1425,35 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx,
 	return ret;
 }
 
+/* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */
+static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key)
+{
+	if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags))
+		return 1;
+	return nfs_wait_bit_killable(key);
+}
+
+static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
+{
+	/*
+	 * send layoutcommit as it can hold up layoutreturn due to lseg
+	 * reference
+	 */
+	pnfs_layoutcommit_inode(lo->plh_inode, false);
+	return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN,
+				   pnfs_layoutget_retry_bit_wait,
+				   TASK_UNINTERRUPTIBLE);
+}
+
+static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo)
+{
+	unsigned long *bitlock = &lo->plh_flags;
+
+	clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock);
+	smp_mb__after_atomic();
+	wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET);
+}
+
 /*
  * Layout segment is retreived from the server if not cached.
  * The appropriate layout segment is referenced and returned to the caller.
@@ -1312,6 +1484,8 @@ pnfs_update_layout(struct inode *ino,
 	if (pnfs_within_mdsthreshold(ctx, ino, iomode))
 		goto out;
 
+lookup_again:
+	first = false;
 	spin_lock(&ino->i_lock);
 	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
 	if (lo == NULL) {
@@ -1326,26 +1500,61 @@ pnfs_update_layout(struct inode *ino,
 	}
 
 	/* if LAYOUTGET already failed once we don't try again */
-	if (pnfs_layout_io_test_failed(lo, iomode))
+	if (pnfs_layout_io_test_failed(lo, iomode) &&
+	    !pnfs_should_retry_layoutget(lo))
 		goto out_unlock;
 
-	/* Check to see if the layout for the given range already exists */
+	first = list_empty(&lo->plh_segs);
+	if (first) {
+		/* The first layoutget for the file. Need to serialize per
+		 * RFC 5661 Errata 3208.
+		 */
+		if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET,
+				     &lo->plh_flags)) {
+			spin_unlock(&ino->i_lock);
+			wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET,
+				    TASK_UNINTERRUPTIBLE);
+			pnfs_put_layout_hdr(lo);
+			goto lookup_again;
+		}
+	} else {
+		/* Check to see if the layout for the given range
+		 * already exists
+		 */
 		lseg = pnfs_find_lseg(lo, &arg);
 		if (lseg)
 			goto out_unlock;
+	}
 
-	if (pnfs_layoutgets_blocked(lo, 0))
+	/*
+	 * Because we free lsegs before sending LAYOUTRETURN, we need to wait
+	 * for LAYOUTRETURN even if first is true.
+	 */
+	if (!lseg && pnfs_should_retry_layoutget(lo) &&
+	    test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
+		spin_unlock(&ino->i_lock);
+		dprintk("%s wait for layoutreturn\n", __func__);
+		if (pnfs_prepare_to_retry_layoutget(lo)) {
+			if (first)
+				pnfs_clear_first_layoutget(lo);
+			pnfs_put_layout_hdr(lo);
+			dprintk("%s retrying\n", __func__);
+			goto lookup_again;
+		}
+		goto out_put_layout_hdr;
+	}
+
+	if (pnfs_layoutgets_blocked(lo, &arg, 0))
 		goto out_unlock;
 	atomic_inc(&lo->plh_outstanding);
-
-	first = list_empty(&lo->plh_layouts) ? true : false;
 	spin_unlock(&ino->i_lock);
 
-	if (first) {
+	if (list_empty(&lo->plh_layouts)) {
 		/* The lo must be on the clp list if there is any
 		 * chance of a CB_LAYOUTRECALL(FILE) coming in.
 		 */
 		spin_lock(&clp->cl_lock);
+		if (list_empty(&lo->plh_layouts))
 			list_add_tail(&lo->plh_layouts, &server->layouts);
 		spin_unlock(&clp->cl_lock);
 	}
@@ -1359,8 +1568,11 @@ pnfs_update_layout(struct inode *ino,
 		arg.length = PAGE_CACHE_ALIGN(arg.length);
 
 	lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
+	pnfs_clear_retry_layoutget(lo);
 	atomic_dec(&lo->plh_outstanding);
 out_put_layout_hdr:
+	if (first)
+		pnfs_clear_first_layoutget(lo);
 	pnfs_put_layout_hdr(lo);
 out:
 	dprintk("%s: inode %s/%llu pNFS layout segment %s for "
@@ -1409,7 +1621,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		goto out_forget_reply;
 	}
 
-	if (pnfs_layoutgets_blocked(lo, 1)) {
+	if (pnfs_layoutgets_blocked(lo, &lgp->args.range, 1)) {
 		dprintk("%s forget reply due to state\n", __func__);
 		goto out_forget_reply;
 	}
@@ -1456,13 +1668,67 @@ out_forget_reply:
 	goto out;
 }
 
+static void
+pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
+				struct list_head *tmp_list,
+				struct pnfs_layout_range *return_range)
+{
+	struct pnfs_layout_segment *lseg, *next;
+
+	dprintk("%s:Begin lo %p\n", __func__, lo);
+
+	if (list_empty(&lo->plh_segs))
+		return;
+
+	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
+		if (should_free_lseg(&lseg->pls_range, return_range)) {
+			dprintk("%s: marking lseg %p iomode %d "
+				"offset %llu length %llu\n", __func__,
+				lseg, lseg->pls_range.iomode,
+				lseg->pls_range.offset,
+				lseg->pls_range.length);
+			set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
+			mark_lseg_invalid(lseg, tmp_list);
+		}
+}
+
+void pnfs_error_mark_layout_for_return(struct inode *inode,
+				       struct pnfs_layout_segment *lseg)
+{
+	struct pnfs_layout_hdr *lo = NFS_I(inode)->layout;
+	int iomode = pnfs_iomode_to_fail_bit(lseg->pls_range.iomode);
+	struct pnfs_layout_range range = {
+		.iomode = lseg->pls_range.iomode,
+		.offset = 0,
+		.length = NFS4_MAX_UINT64,
+	};
+	LIST_HEAD(free_me);
+
+	spin_lock(&inode->i_lock);
+	/* set failure bit so that pnfs path will be retried later */
+	pnfs_layout_set_fail_bit(lo, iomode);
+	set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
+	if (lo->plh_return_iomode == 0)
+		lo->plh_return_iomode = range.iomode;
+	else if (lo->plh_return_iomode != range.iomode)
+		lo->plh_return_iomode = IOMODE_ANY;
+	/*
+	 * mark all matching lsegs so that we are sure to have no live
+	 * segments at hand when sending layoutreturn. See pnfs_put_lseg()
+	 * for how it works.
+	 */
+	pnfs_mark_matching_lsegs_return(lo, &free_me, &range);
+	spin_unlock(&inode->i_lock);
+	pnfs_free_lseg_list(&free_me);
+}
+EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return);
+
 void
 pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
 	u64 rd_size = req->wb_bytes;
 
-	WARN_ON_ONCE(pgio->pg_lseg != NULL);
+	if (pgio->pg_lseg == NULL) {
-
 		if (pgio->pg_dreq == NULL)
 			rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
 		else
@@ -1474,6 +1740,7 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 						   rd_size,
 						   IOMODE_READ,
 						   GFP_KERNEL);
+	}
 	/* If no lseg, fall back to read through mds */
 	if (pgio->pg_lseg == NULL)
 		nfs_pageio_reset_read_mds(pgio);
@@ -1485,8 +1752,7 @@ void
 pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			   struct nfs_page *req, u64 wb_size)
 {
-	WARN_ON_ONCE(pgio->pg_lseg != NULL);
+	if (pgio->pg_lseg == NULL)
-
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
 						   req_offset(req),
@@ -1499,13 +1765,23 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
 
+void
+pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *desc)
+{
+	if (desc->pg_lseg) {
+		pnfs_put_lseg(desc->pg_lseg);
+		desc->pg_lseg = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_cleanup);
+
 /*
  * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
  * of bytes (maximum @req->wb_bytes) that can be coalesced.
  */
 size_t
-pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
+pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
-		     struct nfs_page *req)
+		     struct nfs_page *prev, struct nfs_page *req)
 {
 	unsigned int size;
 	u64 seg_end, req_start, seg_left;
@@ -1529,10 +1805,16 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		seg_end = end_offset(pgio->pg_lseg->pls_range.offset,
 				     pgio->pg_lseg->pls_range.length);
 		req_start = req_offset(req);
-		WARN_ON_ONCE(req_start > seg_end);
+		WARN_ON_ONCE(req_start >= seg_end);
 		/* start of request is past the last byte of this segment */
-		if (req_start >= seg_end)
+		if (req_start >= seg_end) {
+			/* reference the new lseg */
+			if (pgio->pg_ops->pg_cleanup)
+				pgio->pg_ops->pg_cleanup(pgio);
+			if (pgio->pg_ops->pg_init)
+				pgio->pg_ops->pg_init(pgio, req);
 			return 0;
+		}
 
 		/* adjust 'size' iff there are fewer bytes left in the
 		 * segment than what nfs_generic_pg_test returned */
@@ -1587,10 +1869,12 @@ static void
 pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
 		struct nfs_pgio_header *hdr)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
-		list_splice_tail_init(&hdr->pages, &desc->pg_list);
+		list_splice_tail_init(&hdr->pages, &mirror->pg_list);
 		nfs_pageio_reset_write_mds(desc);
-		desc->pg_recoalesce = 1;
+		mirror->pg_recoalesce = 1;
 	}
 	nfs_pgio_data_destroy(hdr);
 }
@@ -1624,11 +1908,9 @@ pnfs_do_write(struct nfs_pageio_descriptor *desc,
 	struct pnfs_layout_segment *lseg = desc->pg_lseg;
 	enum pnfs_try_status trypnfs;
 
-	desc->pg_lseg = NULL;
 	trypnfs = pnfs_try_to_write_data(hdr, call_ops, lseg, how);
 	if (trypnfs == PNFS_NOT_ATTEMPTED)
 		pnfs_write_through_mds(desc, hdr);
-	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
@@ -1641,24 +1923,23 @@ EXPORT_SYMBOL_GPL(pnfs_writehdr_free);
 int
 pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	struct nfs_pgio_header *hdr;
 	int ret;
 
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
-		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
 		return -ENOMEM;
 	}
 	nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
+
 	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	ret = nfs_generic_pgio(desc, hdr);
-	if (ret != 0) {
+	if (!ret)
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
-	} else
 		pnfs_do_write(desc, hdr, desc->pg_ioflags);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
@@ -1703,10 +1984,12 @@ static void
 pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
 		struct nfs_pgio_header *hdr)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
-		list_splice_tail_init(&hdr->pages, &desc->pg_list);
+		list_splice_tail_init(&hdr->pages, &mirror->pg_list);
 		nfs_pageio_reset_read_mds(desc);
-		desc->pg_recoalesce = 1;
+		mirror->pg_recoalesce = 1;
 	}
 	nfs_pgio_data_destroy(hdr);
 }
@@ -1735,18 +2018,29 @@ pnfs_try_to_read_data(struct nfs_pgio_header *hdr,
 	return trypnfs;
 }
 
+/* Resend all requests through pnfs. */
+int pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr)
+{
+	struct nfs_pageio_descriptor pgio;
+
+	nfs_pageio_init_read(&pgio, hdr->inode, false, hdr->completion_ops);
+	return nfs_pageio_resend(&pgio, hdr);
+}
+EXPORT_SYMBOL_GPL(pnfs_read_resend_pnfs);
+
 static void
 pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
 {
 	const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
 	struct pnfs_layout_segment *lseg = desc->pg_lseg;
 	enum pnfs_try_status trypnfs;
+	int err = 0;
 
-	desc->pg_lseg = NULL;
 	trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg);
-	if (trypnfs == PNFS_NOT_ATTEMPTED)
+	if (trypnfs == PNFS_TRY_AGAIN)
+		err = pnfs_read_resend_pnfs(hdr);
+	if (trypnfs == PNFS_NOT_ATTEMPTED || err)
 		pnfs_read_through_mds(desc, hdr);
-	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
@@ -1759,24 +2053,20 @@ EXPORT_SYMBOL_GPL(pnfs_readhdr_free);
 int
 pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	struct nfs_pgio_header *hdr;
 	int ret;
 
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
-		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
-		ret = -ENOMEM;
+		return -ENOMEM;
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
-		return ret;
 	}
 	nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
 	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	ret = nfs_generic_pgio(desc, hdr);
-	if (ret != 0) {
+	if (!ret)
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
-	} else
 		pnfs_do_read(desc, hdr);
 	return ret;
 }
@@ -1982,6 +2272,7 @@ clear_layoutcommitting:
 	pnfs_clear_layoutcommitting(inode);
 	goto out;
 }
+EXPORT_SYMBOL_GPL(pnfs_layoutcommit_inode);
 
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
 {

fs/nfs/pnfs.h

@@ -38,6 +38,25 @@ enum {
 	NFS_LSEG_VALID = 0,	/* cleared when lseg is recalled/returned */
 	NFS_LSEG_ROC,		/* roc bit received from server */
 	NFS_LSEG_LAYOUTCOMMIT,	/* layoutcommit bit set for layoutcommit */
+	NFS_LSEG_LAYOUTRETURN,	/* layoutreturn bit set for layoutreturn */
+};
+
+/* Individual ip address */
+struct nfs4_pnfs_ds_addr {
+	struct sockaddr_storage	da_addr;
+	size_t			da_addrlen;
+	struct list_head	da_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
+	char			*da_remotestr;	/* human readable addr+port */
+};
+
+struct nfs4_pnfs_ds {
+	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
+	char			*ds_remotestr;	/* comma sep list of addrs */
+	struct list_head	ds_addrs;
+	struct nfs_client	*ds_clp;
+	atomic_t		ds_count;
+	unsigned long		ds_state;
+#define NFS4DS_CONNECTING	0	/* ds is establishing connection */
 };
 
 struct pnfs_layout_segment {
@@ -53,19 +72,34 @@ struct pnfs_layout_segment {
 enum pnfs_try_status {
 	PNFS_ATTEMPTED     = 0,
 	PNFS_NOT_ATTEMPTED = 1,
+	PNFS_TRY_AGAIN     = 2,
 };
 
 #ifdef CONFIG_NFS_V4_1
 
 #define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4"
 
+/*
+ * Default data server connection timeout and retrans vaules.
+ * Set by module parameters dataserver_timeo and dataserver_retrans.
+ */
+#define NFS4_DEF_DS_TIMEO   600 /* in tenths of a second */
+#define NFS4_DEF_DS_RETRANS 5
+
+/* error codes for internal use */
+#define NFS4ERR_RESET_TO_MDS   12001
+#define NFS4ERR_RESET_TO_PNFS  12002
+
 enum {
 	NFS_LAYOUT_RO_FAILED = 0,	/* get ro layout failed stop trying */
 	NFS_LAYOUT_RW_FAILED,		/* get rw layout failed stop trying */
 	NFS_LAYOUT_BULK_RECALL,		/* bulk recall affecting layout */
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
 	NFS_LAYOUT_RETURN,		/* Return this layout ASAP */
+	NFS_LAYOUT_RETURN_BEFORE_CLOSE,	/* Return this layout before close */
 	NFS_LAYOUT_INVALID_STID,	/* layout stateid id is invalid */
+	NFS_LAYOUT_FIRST_LAYOUTGET,	/* Serialize first layoutget */
+	NFS_LAYOUT_RETRY_LAYOUTGET,	/* Retry layoutget */
 };
 
 enum layoutdriver_policy_flags {
@@ -106,7 +140,8 @@ struct pnfs_layoutdriver_type {
 	struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode);
 	void (*mark_request_commit) (struct nfs_page *req,
 				     struct pnfs_layout_segment *lseg,
-				     struct nfs_commit_info *cinfo);
+				     struct nfs_commit_info *cinfo,
+				     u32 ds_commit_idx);
 	void (*clear_request_commit) (struct nfs_page *req,
 				      struct nfs_commit_info *cinfo);
 	int (*scan_commit_lists) (struct nfs_commit_info *cinfo,
@@ -154,6 +189,7 @@ struct pnfs_layout_hdr {
 	u32			plh_barrier; /* ignore lower seqids */
 	unsigned long		plh_retry_timestamp;
 	unsigned long		plh_flags;
+	enum pnfs_iomode	plh_return_iomode;
 	loff_t			plh_lwb; /* last write byte for layoutcommit */
 	struct rpc_cred		*plh_lc_cred; /* layoutcommit cred */
 	struct inode		*plh_inode;
@@ -185,7 +221,7 @@ extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev,
 				   struct rpc_cred *cred);
 extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags);
-extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
+extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync);
 
 /* pnfs.c */
 void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo);
@@ -198,6 +234,7 @@ void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *
 int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
 void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			        struct nfs_page *req, u64 wb_size);
+void pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *);
 int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
 size_t pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
 			    struct nfs_page *prev, struct nfs_page *req);
@@ -217,6 +254,7 @@ void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
 			     bool update_barrier);
 int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
 				  struct pnfs_layout_hdr *lo,
+				  struct pnfs_layout_range *range,
 				  struct nfs4_state *open_state);
 int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
@@ -233,17 +271,21 @@ int _pnfs_return_layout(struct inode *);
 int pnfs_commit_and_return_layout(struct inode *);
 void pnfs_ld_write_done(struct nfs_pgio_header *);
 void pnfs_ld_read_done(struct nfs_pgio_header *);
+int pnfs_read_resend_pnfs(struct nfs_pgio_header *);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       struct nfs_open_context *ctx,
 					       loff_t pos,
 					       u64 count,
 					       enum pnfs_iomode iomode,
 					       gfp_t gfp_flags);
+void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo);
 
 void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
 int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *);
 int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *);
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
+void pnfs_error_mark_layout_for_return(struct inode *inode,
+				       struct pnfs_layout_segment *lseg);
 
 /* nfs4_deviceid_flags */
 enum {
@@ -275,6 +317,34 @@ void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
 bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
 void nfs4_deviceid_purge_client(const struct nfs_client *);
 
+/* pnfs_nfs.c */
+void pnfs_generic_clear_request_commit(struct nfs_page *req,
+				       struct nfs_commit_info *cinfo);
+void pnfs_generic_commit_release(void *calldata);
+void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data);
+void pnfs_generic_rw_release(void *data);
+void pnfs_generic_recover_commit_reqs(struct list_head *dst,
+				      struct nfs_commit_info *cinfo);
+int pnfs_generic_commit_pagelist(struct inode *inode,
+				 struct list_head *mds_pages,
+				 int how,
+				 struct nfs_commit_info *cinfo,
+				 int (*initiate_commit)(struct nfs_commit_data *data,
+							int how));
+int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max);
+void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
+void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
+struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
+				      gfp_t gfp_flags);
+void nfs4_pnfs_v3_ds_connect_unload(void);
+void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+			  struct nfs4_deviceid_node *devid, unsigned int timeo,
+			  unsigned int retrans, u32 version, u32 minor_version,
+			  rpc_authflavor_t au_flavor);
+struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net,
+						 struct xdr_stream *xdr,
+						 gfp_t gfp_flags);
+
 static inline bool nfs_have_layout(struct inode *inode)
 {
 	return NFS_I(inode)->layout != NULL;
@@ -287,6 +357,26 @@ nfs4_get_deviceid(struct nfs4_deviceid_node *d)
 	return d;
 }
 
+static inline void pnfs_set_retry_layoutget(struct pnfs_layout_hdr *lo)
+{
+	if (!test_and_set_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags))
+		atomic_inc(&lo->plh_refcount);
+}
+
+static inline void pnfs_clear_retry_layoutget(struct pnfs_layout_hdr *lo)
+{
+	if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) {
+		atomic_dec(&lo->plh_refcount);
+		/* wake up waiters for LAYOUTRETURN as that is not needed */
+		wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
+	}
+}
+
+static inline bool pnfs_should_retry_layoutget(struct pnfs_layout_hdr *lo)
+{
+	return test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags);
+}
+
 static inline struct pnfs_layout_segment *
 pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
@@ -322,16 +412,22 @@ pnfs_get_ds_info(struct inode *inode)
 	return ld->get_ds_info(inode);
 }
 
+static inline void
+pnfs_generic_mark_devid_invalid(struct nfs4_deviceid_node *node)
+{
+	set_bit(NFS_DEVICEID_INVALID, &node->flags);
+}
+
 static inline bool
 pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			 struct nfs_commit_info *cinfo)
+			 struct nfs_commit_info *cinfo, u32 ds_commit_idx)
 {
 	struct inode *inode = req->wb_context->dentry->d_inode;
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 
 	if (lseg == NULL || ld->mark_request_commit == NULL)
 		return false;
-	ld->mark_request_commit(req, lseg, cinfo);
+	ld->mark_request_commit(req, lseg, cinfo, ds_commit_idx);
 	return true;
 }
 
@@ -357,15 +453,6 @@ pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
 		return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max);
 }
 
-static inline void
-pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
-			 struct nfs_commit_info *cinfo)
-{
-	if (cinfo->ds == NULL || cinfo->ds->nwritten == 0)
-		return;
-	NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
-}
-
 static inline struct nfs_page *
 pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo,
 			struct page *page)
@@ -523,7 +610,7 @@ pnfs_get_ds_info(struct inode *inode)
 
 static inline bool
 pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			 struct nfs_commit_info *cinfo)
+			 struct nfs_commit_info *cinfo, u32 ds_commit_idx)
 {
 	return false;
 }
@@ -541,12 +628,6 @@ pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
 	return 0;
 }
 
-static inline void
-pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
-			 struct nfs_commit_info *cinfo)
-{
-}
-
 static inline struct nfs_page *
 pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo,
 			struct page *page)
@@ -578,6 +659,10 @@ static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
 	return NULL;
 }
 
+static inline void nfs4_pnfs_v3_ds_connect_unload(void)
+{
+}
+
 #endif /* CONFIG_NFS_V4_1 */
 
 #endif /* FS_NFS_PNFS_H */

fs/nfs/pnfs_nfs.c

@@ -0,0 +1,840 @@
+/*
+ * Common NFS I/O  operations for the pnfs file based
+ * layout drivers.
+ *
+ * Copyright (c) 2014, Primary Data, Inc. All rights reserved.
+ *
+ * Tom Haynes <loghyr@primarydata.com>
+ */
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/module.h>
+
+#include "nfs4session.h"
+#include "internal.h"
+#include "pnfs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_PNFS
+
+void pnfs_generic_rw_release(void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	nfs_put_client(hdr->ds_clp);
+	hdr->mds_ops->rpc_release(data);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_rw_release);
+
+/* Fake up some data that will cause nfs_commit_release to retry the writes. */
+void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data)
+{
+	struct nfs_page *first = nfs_list_entry(data->pages.next);
+
+	data->task.tk_status = 0;
+	memcpy(&data->verf.verifier, &first->wb_verf,
+	       sizeof(data->verf.verifier));
+	data->verf.verifier.data[0]++; /* ensure verifier mismatch */
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_prepare_to_resend_writes);
+
+void pnfs_generic_write_commit_done(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *wdata = data;
+
+	/* Note this may cause RPC to be resent */
+	wdata->mds_ops->rpc_call_done(task, data);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_write_commit_done);
+
+void pnfs_generic_commit_release(void *calldata)
+{
+	struct nfs_commit_data *data = calldata;
+
+	data->completion_ops->completion(data);
+	pnfs_put_lseg(data->lseg);
+	nfs_put_client(data->ds_clp);
+	nfs_commitdata_release(data);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_commit_release);
+
+/* The generic layer is about to remove the req from the commit list.
+ * If this will make the bucket empty, it will need to put the lseg reference.
+ * Note this must be called holding the inode (/cinfo) lock
+ */
+void
+pnfs_generic_clear_request_commit(struct nfs_page *req,
+				  struct nfs_commit_info *cinfo)
+{
+	struct pnfs_layout_segment *freeme = NULL;
+
+	if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
+		goto out;
+	cinfo->ds->nwritten--;
+	if (list_is_singular(&req->wb_list)) {
+		struct pnfs_commit_bucket *bucket;
+
+		bucket = list_first_entry(&req->wb_list,
+					  struct pnfs_commit_bucket,
+					  written);
+		freeme = bucket->wlseg;
+		bucket->wlseg = NULL;
+	}
+out:
+	nfs_request_remove_commit_list(req, cinfo);
+	pnfs_put_lseg_locked(freeme);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit);
+
+static int
+pnfs_generic_transfer_commit_list(struct list_head *src, struct list_head *dst,
+				  struct nfs_commit_info *cinfo, int max)
+{
+	struct nfs_page *req, *tmp;
+	int ret = 0;
+
+	list_for_each_entry_safe(req, tmp, src, wb_list) {
+		if (!nfs_lock_request(req))
+			continue;
+		kref_get(&req->wb_kref);
+		if (cond_resched_lock(cinfo->lock))
+			list_safe_reset_next(req, tmp, wb_list);
+		nfs_request_remove_commit_list(req, cinfo);
+		clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
+		nfs_list_add_request(req, dst);
+		ret++;
+		if ((ret == max) && !cinfo->dreq)
+			break;
+	}
+	return ret;
+}
+
+static int
+pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
+				 struct nfs_commit_info *cinfo,
+				 int max)
+{
+	struct list_head *src = &bucket->written;
+	struct list_head *dst = &bucket->committing;
+	int ret;
+
+	lockdep_assert_held(cinfo->lock);
+	ret = pnfs_generic_transfer_commit_list(src, dst, cinfo, max);
+	if (ret) {
+		cinfo->ds->nwritten -= ret;
+		cinfo->ds->ncommitting += ret;
+		bucket->clseg = bucket->wlseg;
+		if (list_empty(src))
+			bucket->wlseg = NULL;
+		else
+			pnfs_get_lseg(bucket->clseg);
+	}
+	return ret;
+}
+
+/* Move reqs from written to committing lists, returning count
+ * of number moved.
+ */
+int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo,
+				   int max)
+{
+	int i, rv = 0, cnt;
+
+	lockdep_assert_held(cinfo->lock);
+	for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) {
+		cnt = pnfs_generic_scan_ds_commit_list(&cinfo->ds->buckets[i],
+						       cinfo, max);
+		max -= cnt;
+		rv += cnt;
+	}
+	return rv;
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_scan_commit_lists);
+
+/* Pull everything off the committing lists and dump into @dst.  */
+void pnfs_generic_recover_commit_reqs(struct list_head *dst,
+				      struct nfs_commit_info *cinfo)
+{
+	struct pnfs_commit_bucket *b;
+	struct pnfs_layout_segment *freeme;
+	int i;
+
+	lockdep_assert_held(cinfo->lock);
+restart:
+	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
+		if (pnfs_generic_transfer_commit_list(&b->written, dst,
+						      cinfo, 0)) {
+			freeme = b->wlseg;
+			b->wlseg = NULL;
+			spin_unlock(cinfo->lock);
+			pnfs_put_lseg(freeme);
+			spin_lock(cinfo->lock);
+			goto restart;
+		}
+	}
+	cinfo->ds->nwritten = 0;
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs);
+
+static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
+{
+	struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
+	struct pnfs_commit_bucket *bucket;
+	struct pnfs_layout_segment *freeme;
+	int i;
+
+	for (i = idx; i < fl_cinfo->nbuckets; i++) {
+		bucket = &fl_cinfo->buckets[i];
+		if (list_empty(&bucket->committing))
+			continue;
+		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo, i);
+		spin_lock(cinfo->lock);
+		freeme = bucket->clseg;
+		bucket->clseg = NULL;
+		spin_unlock(cinfo->lock);
+		pnfs_put_lseg(freeme);
+	}
+}
+
+static unsigned int
+pnfs_generic_alloc_ds_commits(struct nfs_commit_info *cinfo,
+			      struct list_head *list)
+{
+	struct pnfs_ds_commit_info *fl_cinfo;
+	struct pnfs_commit_bucket *bucket;
+	struct nfs_commit_data *data;
+	int i;
+	unsigned int nreq = 0;
+
+	fl_cinfo = cinfo->ds;
+	bucket = fl_cinfo->buckets;
+	for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) {
+		if (list_empty(&bucket->committing))
+			continue;
+		data = nfs_commitdata_alloc();
+		if (!data)
+			break;
+		data->ds_commit_index = i;
+		spin_lock(cinfo->lock);
+		data->lseg = bucket->clseg;
+		bucket->clseg = NULL;
+		spin_unlock(cinfo->lock);
+		list_add(&data->pages, list);
+		nreq++;
+	}
+
+	/* Clean up on error */
+	pnfs_generic_retry_commit(cinfo, i);
+	return nreq;
+}
+
+/* This follows nfs_commit_list pretty closely */
+int
+pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
+			     int how, struct nfs_commit_info *cinfo,
+			     int (*initiate_commit)(struct nfs_commit_data *data,
+						    int how))
+{
+	struct nfs_commit_data *data, *tmp;
+	LIST_HEAD(list);
+	unsigned int nreq = 0;
+
+	if (!list_empty(mds_pages)) {
+		data = nfs_commitdata_alloc();
+		if (data != NULL) {
+			data->lseg = NULL;
+			list_add(&data->pages, &list);
+			nreq++;
+		} else {
+			nfs_retry_commit(mds_pages, NULL, cinfo, 0);
+			pnfs_generic_retry_commit(cinfo, 0);
+			cinfo->completion_ops->error_cleanup(NFS_I(inode));
+			return -ENOMEM;
+		}
+	}
+
+	nreq += pnfs_generic_alloc_ds_commits(cinfo, &list);
+
+	if (nreq == 0) {
+		cinfo->completion_ops->error_cleanup(NFS_I(inode));
+		goto out;
+	}
+
+	atomic_add(nreq, &cinfo->mds->rpcs_out);
+
+	list_for_each_entry_safe(data, tmp, &list, pages) {
+		list_del_init(&data->pages);
+		if (!data->lseg) {
+			nfs_init_commit(data, mds_pages, NULL, cinfo);
+			nfs_initiate_commit(NFS_CLIENT(inode), data,
+					    NFS_PROTO(data->inode),
+					    data->mds_ops, how, 0);
+		} else {
+			struct pnfs_commit_bucket *buckets;
+
+			buckets = cinfo->ds->buckets;
+			nfs_init_commit(data,
+					&buckets[data->ds_commit_index].committing,
+					data->lseg,
+					cinfo);
+			initiate_commit(data, how);
+		}
+	}
+out:
+	cinfo->ds->ncommitting = 0;
+	return PNFS_ATTEMPTED;
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist);
+
+/*
+ * Data server cache
+ *
+ * Data servers can be mapped to different device ids.
+ * nfs4_pnfs_ds reference counting
+ *   - set to 1 on allocation
+ *   - incremented when a device id maps a data server already in the cache.
+ *   - decremented when deviceid is removed from the cache.
+ */
+static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
+static LIST_HEAD(nfs4_data_server_cache);
+
+/* Debug routines */
+static void
+print_ds(struct nfs4_pnfs_ds *ds)
+{
+	if (ds == NULL) {
+		printk(KERN_WARNING "%s NULL device\n", __func__);
+		return;
+	}
+	printk(KERN_WARNING "        ds %s\n"
+		"        ref count %d\n"
+		"        client %p\n"
+		"        cl_exchange_flags %x\n",
+		ds->ds_remotestr,
+		atomic_read(&ds->ds_count), ds->ds_clp,
+		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
+}
+
+static bool
+same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
+{
+	struct sockaddr_in *a, *b;
+	struct sockaddr_in6 *a6, *b6;
+
+	if (addr1->sa_family != addr2->sa_family)
+		return false;
+
+	switch (addr1->sa_family) {
+	case AF_INET:
+		a = (struct sockaddr_in *)addr1;
+		b = (struct sockaddr_in *)addr2;
+
+		if (a->sin_addr.s_addr == b->sin_addr.s_addr &&
+		    a->sin_port == b->sin_port)
+			return true;
+		break;
+
+	case AF_INET6:
+		a6 = (struct sockaddr_in6 *)addr1;
+		b6 = (struct sockaddr_in6 *)addr2;
+
+		/* LINKLOCAL addresses must have matching scope_id */
+		if (ipv6_addr_src_scope(&a6->sin6_addr) ==
+		    IPV6_ADDR_SCOPE_LINKLOCAL &&
+		    a6->sin6_scope_id != b6->sin6_scope_id)
+			return false;
+
+		if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) &&
+		    a6->sin6_port == b6->sin6_port)
+			return true;
+		break;
+
+	default:
+		dprintk("%s: unhandled address family: %u\n",
+			__func__, addr1->sa_family);
+		return false;
+	}
+
+	return false;
+}
+
+static bool
+_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
+			       const struct list_head *dsaddrs2)
+{
+	struct nfs4_pnfs_ds_addr *da1, *da2;
+
+	/* step through both lists, comparing as we go */
+	for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
+	     da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
+	     da1 != NULL && da2 != NULL;
+	     da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
+	     da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
+		if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
+				   (struct sockaddr *)&da2->da_addr))
+			return false;
+	}
+	if (da1 == NULL && da2 == NULL)
+		return true;
+
+	return false;
+}
+
+/*
+ * Lookup DS by addresses.  nfs4_ds_cache_lock is held
+ */
+static struct nfs4_pnfs_ds *
+_data_server_lookup_locked(const struct list_head *dsaddrs)
+{
+	struct nfs4_pnfs_ds *ds;
+
+	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
+		if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
+			return ds;
+	return NULL;
+}
+
+static void destroy_ds(struct nfs4_pnfs_ds *ds)
+{
+	struct nfs4_pnfs_ds_addr *da;
+
+	dprintk("--> %s\n", __func__);
+	ifdebug(FACILITY)
+		print_ds(ds);
+
+	nfs_put_client(ds->ds_clp);
+
+	while (!list_empty(&ds->ds_addrs)) {
+		da = list_first_entry(&ds->ds_addrs,
+				      struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+
+	kfree(ds->ds_remotestr);
+	kfree(ds);
+}
+
+void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds)
+{
+	if (atomic_dec_and_lock(&ds->ds_count,
+				&nfs4_ds_cache_lock)) {
+		list_del_init(&ds->ds_node);
+		spin_unlock(&nfs4_ds_cache_lock);
+		destroy_ds(ds);
+	}
+}
+EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_put);
+
+/*
+ * Create a string with a human readable address and port to avoid
+ * complicated setup around many dprinks.
+ */
+static char *
+nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
+{
+	struct nfs4_pnfs_ds_addr *da;
+	char *remotestr;
+	size_t len;
+	char *p;
+
+	len = 3;        /* '{', '}' and eol */
+	list_for_each_entry(da, dsaddrs, da_node) {
+		len += strlen(da->da_remotestr) + 1;    /* string plus comma */
+	}
+
+	remotestr = kzalloc(len, gfp_flags);
+	if (!remotestr)
+		return NULL;
+
+	p = remotestr;
+	*(p++) = '{';
+	len--;
+	list_for_each_entry(da, dsaddrs, da_node) {
+		size_t ll = strlen(da->da_remotestr);
+
+		if (ll > len)
+			goto out_err;
+
+		memcpy(p, da->da_remotestr, ll);
+		p += ll;
+		len -= ll;
+
+		if (len < 1)
+			goto out_err;
+		(*p++) = ',';
+		len--;
+	}
+	if (len < 2)
+		goto out_err;
+	*(p++) = '}';
+	*p = '\0';
+	return remotestr;
+out_err:
+	kfree(remotestr);
+	return NULL;
+}
+
+/*
+ * Given a list of multipath struct nfs4_pnfs_ds_addr, add it to ds cache if
+ * uncached and return cached struct nfs4_pnfs_ds.
+ */
+struct nfs4_pnfs_ds *
+nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
+{
+	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
+	char *remotestr;
+
+	if (list_empty(dsaddrs)) {
+		dprintk("%s: no addresses defined\n", __func__);
+		goto out;
+	}
+
+	ds = kzalloc(sizeof(*ds), gfp_flags);
+	if (!ds)
+		goto out;
+
+	/* this is only used for debugging, so it's ok if its NULL */
+	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
+
+	spin_lock(&nfs4_ds_cache_lock);
+	tmp_ds = _data_server_lookup_locked(dsaddrs);
+	if (tmp_ds == NULL) {
+		INIT_LIST_HEAD(&ds->ds_addrs);
+		list_splice_init(dsaddrs, &ds->ds_addrs);
+		ds->ds_remotestr = remotestr;
+		atomic_set(&ds->ds_count, 1);
+		INIT_LIST_HEAD(&ds->ds_node);
+		ds->ds_clp = NULL;
+		list_add(&ds->ds_node, &nfs4_data_server_cache);
+		dprintk("%s add new data server %s\n", __func__,
+			ds->ds_remotestr);
+	} else {
+		kfree(remotestr);
+		kfree(ds);
+		atomic_inc(&tmp_ds->ds_count);
+		dprintk("%s data server %s found, inc'ed ds_count to %d\n",
+			__func__, tmp_ds->ds_remotestr,
+			atomic_read(&tmp_ds->ds_count));
+		ds = tmp_ds;
+	}
+	spin_unlock(&nfs4_ds_cache_lock);
+out:
+	return ds;
+}
+EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_add);
+
+static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
+{
+	might_sleep();
+	wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING,
+			TASK_KILLABLE);
+}
+
+static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
+{
+	smp_mb__before_atomic();
+	clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
+	smp_mb__after_atomic();
+	wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
+}
+
+static struct nfs_client *(*get_v3_ds_connect)(
+			struct nfs_client *mds_clp,
+			const struct sockaddr *ds_addr,
+			int ds_addrlen,
+			int ds_proto,
+			unsigned int ds_timeo,
+			unsigned int ds_retrans,
+			rpc_authflavor_t au_flavor);
+
+static bool load_v3_ds_connect(void)
+{
+	if (!get_v3_ds_connect) {
+		get_v3_ds_connect = symbol_request(nfs3_set_ds_client);
+		WARN_ON_ONCE(!get_v3_ds_connect);
+	}
+
+	return(get_v3_ds_connect != NULL);
+}
+
+void __exit nfs4_pnfs_v3_ds_connect_unload(void)
+{
+	if (get_v3_ds_connect) {
+		symbol_put(nfs3_set_ds_client);
+		get_v3_ds_connect = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(nfs4_pnfs_v3_ds_connect_unload);
+
+static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
+				 struct nfs4_pnfs_ds *ds,
+				 unsigned int timeo,
+				 unsigned int retrans,
+				 rpc_authflavor_t au_flavor)
+{
+	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs4_pnfs_ds_addr *da;
+	int status = 0;
+
+	dprintk("--> %s DS %s au_flavor %d\n", __func__,
+		ds->ds_remotestr, au_flavor);
+
+	if (!load_v3_ds_connect())
+		goto out;
+
+	list_for_each_entry(da, &ds->ds_addrs, da_node) {
+		dprintk("%s: DS %s: trying address %s\n",
+			__func__, ds->ds_remotestr, da->da_remotestr);
+
+		clp = get_v3_ds_connect(mds_srv->nfs_client,
+					(struct sockaddr *)&da->da_addr,
+					da->da_addrlen, IPPROTO_TCP,
+					timeo, retrans, au_flavor);
+		if (!IS_ERR(clp))
+			break;
+	}
+
+	if (IS_ERR(clp)) {
+		status = PTR_ERR(clp);
+		goto out;
+	}
+
+	smp_wmb();
+	ds->ds_clp = clp;
+	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
+out:
+	return status;
+}
+
+static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
+				 struct nfs4_pnfs_ds *ds,
+				 unsigned int timeo,
+				 unsigned int retrans,
+				 u32 minor_version,
+				 rpc_authflavor_t au_flavor)
+{
+	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs4_pnfs_ds_addr *da;
+	int status = 0;
+
+	dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
+		au_flavor);
+
+	list_for_each_entry(da, &ds->ds_addrs, da_node) {
+		dprintk("%s: DS %s: trying address %s\n",
+			__func__, ds->ds_remotestr, da->da_remotestr);
+
+		clp = nfs4_set_ds_client(mds_srv->nfs_client,
+					(struct sockaddr *)&da->da_addr,
+					da->da_addrlen, IPPROTO_TCP,
+					timeo, retrans, minor_version,
+					au_flavor);
+		if (!IS_ERR(clp))
+			break;
+	}
+
+	if (IS_ERR(clp)) {
+		status = PTR_ERR(clp);
+		goto out;
+	}
+
+	status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time);
+	if (status)
+		goto out_put;
+
+	smp_wmb();
+	ds->ds_clp = clp;
+	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
+out:
+	return status;
+out_put:
+	nfs_put_client(clp);
+	goto out;
+}
+
+/*
+ * Create an rpc connection to the nfs4_pnfs_ds data server.
+ * Currently only supports IPv4 and IPv6 addresses.
+ * If connection fails, make devid unavailable.
+ */
+void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+			  struct nfs4_deviceid_node *devid, unsigned int timeo,
+			  unsigned int retrans, u32 version,
+			  u32 minor_version, rpc_authflavor_t au_flavor)
+{
+	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
+		int err = 0;
+
+		if (version == 3) {
+			err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo,
+						       retrans, au_flavor);
+		} else if (version == 4) {
+			err = _nfs4_pnfs_v4_ds_connect(mds_srv, ds, timeo,
+						       retrans, minor_version,
+						       au_flavor);
+		} else {
+			dprintk("%s: unsupported DS version %d\n", __func__,
+				version);
+			err = -EPROTONOSUPPORT;
+		}
+
+		if (err)
+			nfs4_mark_deviceid_unavailable(devid);
+		nfs4_clear_ds_conn_bit(ds);
+	} else {
+		nfs4_wait_ds_connect(ds);
+	}
+}
+EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect);
+
+/*
+ * Currently only supports ipv4, ipv6 and one multi-path address.
+ */
+struct nfs4_pnfs_ds_addr *
+nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags)
+{
+	struct nfs4_pnfs_ds_addr *da = NULL;
+	char *buf, *portstr;
+	__be16 port;
+	int nlen, rlen;
+	int tmp[2];
+	__be32 *p;
+	char *netid, *match_netid;
+	size_t len, match_netid_len;
+	char *startsep = "";
+	char *endsep = "";
+
+
+	/* r_netid */
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_err;
+	nlen = be32_to_cpup(p++);
+
+	p = xdr_inline_decode(xdr, nlen);
+	if (unlikely(!p))
+		goto out_err;
+
+	netid = kmalloc(nlen+1, gfp_flags);
+	if (unlikely(!netid))
+		goto out_err;
+
+	netid[nlen] = '\0';
+	memcpy(netid, p, nlen);
+
+	/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_free_netid;
+	rlen = be32_to_cpup(p);
+
+	p = xdr_inline_decode(xdr, rlen);
+	if (unlikely(!p))
+		goto out_free_netid;
+
+	/* port is ".ABC.DEF", 8 chars max */
+	if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) {
+		dprintk("%s: Invalid address, length %d\n", __func__,
+			rlen);
+		goto out_free_netid;
+	}
+	buf = kmalloc(rlen + 1, gfp_flags);
+	if (!buf) {
+		dprintk("%s: Not enough memory\n", __func__);
+		goto out_free_netid;
+	}
+	buf[rlen] = '\0';
+	memcpy(buf, p, rlen);
+
+	/* replace port '.' with '-' */
+	portstr = strrchr(buf, '.');
+	if (!portstr) {
+		dprintk("%s: Failed finding expected dot in port\n",
+			__func__);
+		goto out_free_buf;
+	}
+	*portstr = '-';
+
+	/* find '.' between address and port */
+	portstr = strrchr(buf, '.');
+	if (!portstr) {
+		dprintk("%s: Failed finding expected dot between address and "
+			"port\n", __func__);
+		goto out_free_buf;
+	}
+	*portstr = '\0';
+
+	da = kzalloc(sizeof(*da), gfp_flags);
+	if (unlikely(!da))
+		goto out_free_buf;
+
+	INIT_LIST_HEAD(&da->da_node);
+
+	if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
+		      sizeof(da->da_addr))) {
+		dprintk("%s: error parsing address %s\n", __func__, buf);
+		goto out_free_da;
+	}
+
+	portstr++;
+	sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]);
+	port = htons((tmp[0] << 8) | (tmp[1]));
+
+	switch (da->da_addr.ss_family) {
+	case AF_INET:
+		((struct sockaddr_in *)&da->da_addr)->sin_port = port;
+		da->da_addrlen = sizeof(struct sockaddr_in);
+		match_netid = "tcp";
+		match_netid_len = 3;
+		break;
+
+	case AF_INET6:
+		((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port;
+		da->da_addrlen = sizeof(struct sockaddr_in6);
+		match_netid = "tcp6";
+		match_netid_len = 4;
+		startsep = "[";
+		endsep = "]";
+		break;
+
+	default:
+		dprintk("%s: unsupported address family: %u\n",
+			__func__, da->da_addr.ss_family);
+		goto out_free_da;
+	}
+
+	if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) {
+		dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n",
+			__func__, netid, match_netid);
+		goto out_free_da;
+	}
+
+	/* save human readable address */
+	len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7;
+	da->da_remotestr = kzalloc(len, gfp_flags);
+
+	/* NULL is ok, only used for dprintk */
+	if (da->da_remotestr)
+		snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep,
+			 buf, endsep, ntohs(port));
+
+	dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr);
+	kfree(buf);
+	kfree(netid);
+	return da;
+
+out_free_da:
+	kfree(da);
+out_free_buf:
+	dprintk("%s: Error parsing DS addr: %s\n", __func__, buf);
+	kfree(buf);
+out_free_netid:
+	kfree(netid);
+out_err:
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(nfs4_decode_mp_ds_addr);

fs/nfs/read.c

@@ -70,8 +70,15 @@ EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
 
 void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 {
+	struct nfs_pgio_mirror *mirror;
+
 	pgio->pg_ops = &nfs_pgio_rw_ops;
-	pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
+
+	/* read path should never have more than one mirror */
+	WARN_ON_ONCE(pgio->pg_mirror_count != 1);
+
+	mirror = &pgio->pg_mirrors[0];
+	mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
 
@@ -81,6 +88,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 	struct nfs_page	*new;
 	unsigned int len;
 	struct nfs_pageio_descriptor pgio;
+	struct nfs_pgio_mirror *pgm;
 
 	len = nfs_page_length(page);
 	if (len == 0)
@@ -97,7 +105,13 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 			     &nfs_async_read_completion_ops);
 	nfs_pageio_add_request(&pgio, new);
 	nfs_pageio_complete(&pgio);
-	NFS_I(inode)->read_io += pgio.pg_bytes_written;
+
+	/* It doesn't make sense to do mirrored reads! */
+	WARN_ON_ONCE(pgio.pg_mirror_count != 1);
+
+	pgm = &pgio.pg_mirrors[0];
+	NFS_I(inode)->read_io += pgm->pg_bytes_written;
+
 	return 0;
 }
 
@@ -168,13 +182,14 @@ out:
 
 static void nfs_initiate_read(struct nfs_pgio_header *hdr,
 			      struct rpc_message *msg,
+			      const struct nfs_rpc_ops *rpc_ops,
 			      struct rpc_task_setup *task_setup_data, int how)
 {
 	struct inode *inode = hdr->inode;
 	int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
 
 	task_setup_data->flags |= swap_flags;
-	NFS_PROTO(inode)->read_setup(hdr, msg);
+	rpc_ops->read_setup(hdr, msg);
 }
 
 static void
@@ -351,6 +366,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 		struct list_head *pages, unsigned nr_pages)
 {
 	struct nfs_pageio_descriptor pgio;
+	struct nfs_pgio_mirror *pgm;
 	struct nfs_readdesc desc = {
 		.pgio = &pgio,
 	};
@@ -386,10 +402,15 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 			     &nfs_async_read_completion_ops);
 
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
-
 	nfs_pageio_complete(&pgio);
-	NFS_I(inode)->read_io += pgio.pg_bytes_written;
+
-	npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	/* It doesn't make sense to do mirrored reads! */
+	WARN_ON_ONCE(pgio.pg_mirror_count != 1);
+
+	pgm = &pgio.pg_mirrors[0];
+	NFS_I(inode)->read_io += pgm->pg_bytes_written;
+	npages = (pgm->pg_bytes_written + PAGE_CACHE_SIZE - 1) >>
+		 PAGE_CACHE_SHIFT;
 	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
 read_complete:
 	put_nfs_open_context(desc.ctx);

fs/nfs/write.c

@@ -473,13 +473,18 @@ try_again:
 	do {
 		/*
 		 * Subrequests are always contiguous, non overlapping
-		 * and in order. If not, it's a programming error.
+		 * and in order - but may be repeated (mirrored writes).
 		 */
-		WARN_ON_ONCE(subreq->wb_offset !=
+		if (subreq->wb_offset == (head->wb_offset + total_bytes)) {
-		     (head->wb_offset + total_bytes));
-
 			/* keep track of how many bytes this group covers */
 			total_bytes += subreq->wb_bytes;
+		} else if (WARN_ON_ONCE(subreq->wb_offset < head->wb_offset ||
+			    ((subreq->wb_offset + subreq->wb_bytes) >
+			     (head->wb_offset + total_bytes)))) {
+			nfs_page_group_unlock(head);
+			spin_unlock(&inode->i_lock);
+			return ERR_PTR(-EIO);
+		}
 
 		if (!nfs_lock_request(subreq)) {
 			/* releases page group bit lock and
@@ -842,9 +847,9 @@ EXPORT_SYMBOL_GPL(nfs_init_cinfo);
  */
 void
 nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			struct nfs_commit_info *cinfo)
+			struct nfs_commit_info *cinfo, u32 ds_commit_idx)
 {
-	if (pnfs_mark_request_commit(req, lseg, cinfo))
+	if (pnfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx))
 		return;
 	nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo);
 }
@@ -900,7 +905,8 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
 		}
 		if (nfs_write_need_commit(hdr)) {
 			memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf));
-			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+			nfs_mark_request_commit(req, hdr->lseg, &cinfo,
+				hdr->pgio_mirror_idx);
 			goto next;
 		}
 remove_req:
@@ -1240,15 +1246,15 @@ static int flush_task_priority(int how)
 
 static void nfs_initiate_write(struct nfs_pgio_header *hdr,
 			       struct rpc_message *msg,
+			       const struct nfs_rpc_ops *rpc_ops,
 			       struct rpc_task_setup *task_setup_data, int how)
 {
-	struct inode *inode = hdr->inode;
 	int priority = flush_task_priority(how);
 
 	task_setup_data->priority = priority;
-	NFS_PROTO(inode)->write_setup(hdr, msg);
+	rpc_ops->write_setup(hdr, msg);
 
-	nfs4_state_protect_write(NFS_SERVER(inode)->nfs_client,
+	nfs4_state_protect_write(NFS_SERVER(hdr->inode)->nfs_client,
 				 &task_setup_data->rpc_client, msg, hdr);
 }
 
@@ -1298,8 +1304,14 @@ EXPORT_SYMBOL_GPL(nfs_pageio_init_write);
 
 void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 {
+	struct nfs_pgio_mirror *mirror;
+
 	pgio->pg_ops = &nfs_pgio_rw_ops;
-	pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize;
+
+	nfs_pageio_stop_mirroring(pgio);
+
+	mirror = &pgio->pg_mirrors[0];
+	mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize;
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
 
@@ -1465,6 +1477,7 @@ void nfs_commitdata_release(struct nfs_commit_data *data)
 EXPORT_SYMBOL_GPL(nfs_commitdata_release);
 
 int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
+			const struct nfs_rpc_ops *nfs_ops,
 			const struct rpc_call_ops *call_ops,
 			int how, int flags)
 {
@@ -1486,7 +1499,7 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 		.priority = priority,
 	};
 	/* Set up the initial task struct.  */
-	NFS_PROTO(data->inode)->commit_setup(data, &msg);
+	nfs_ops->commit_setup(data, &msg);
 
 	dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid);
 
@@ -1554,14 +1567,15 @@ EXPORT_SYMBOL_GPL(nfs_init_commit);
 
 void nfs_retry_commit(struct list_head *page_list,
 		      struct pnfs_layout_segment *lseg,
-		      struct nfs_commit_info *cinfo)
+		      struct nfs_commit_info *cinfo,
+		      u32 ds_commit_idx)
 {
 	struct nfs_page *req;
 
 	while (!list_empty(page_list)) {
 		req = nfs_list_entry(page_list->next);
 		nfs_list_remove_request(req);
-		nfs_mark_request_commit(req, lseg, cinfo);
+		nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx);
 		if (!cinfo->dreq) {
 			dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
 			dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
@@ -1589,10 +1603,10 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 	/* Set up the argument struct */
 	nfs_init_commit(data, head, NULL, cinfo);
 	atomic_inc(&cinfo->mds->rpcs_out);
-	return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops,
+	return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
-				   how, 0);
+				   data->mds_ops, how, 0);
  out_bad:
-	nfs_retry_commit(head, NULL, cinfo);
+	nfs_retry_commit(head, NULL, cinfo, 0);
 	cinfo->completion_ops->error_cleanup(NFS_I(inode));
 	return -ENOMEM;
 }

include/linux/nfs4.h

@@ -516,6 +516,7 @@ enum pnfs_layouttype {
 	LAYOUT_NFSV4_1_FILES  = 1,
 	LAYOUT_OSD2_OBJECTS = 2,
 	LAYOUT_BLOCK_VOLUME = 3,
+	LAYOUT_FLEX_FILES = 4,
 };
 
 /* used for both layout return and recall */

include/linux/nfs_fs_sb.h

@@ -77,10 +77,6 @@ struct nfs_client {
 	/* Client owner identifier */
 	const char *		cl_owner_id;
 
-	/* Our own IP address, as a null-terminated string.
-	 * This is used to generate the mv0 callback address.
-	 */
-	char			cl_ipaddr[48];
 	u32			cl_cb_ident;	/* v4.0 callback identifier */
 	const struct nfs4_minor_version_ops *cl_mvops;
 	unsigned long		cl_mig_gen;
@@ -108,6 +104,11 @@ struct nfs_client {
 #define NFS_SP4_MACH_CRED_COMMIT   6	/* COMMIT */
 #endif /* CONFIG_NFS_V4 */
 
+	/* Our own IP address, as a null-terminated string.
+	 * This is used to generate the mv0 callback address.
+	 */
+	char			cl_ipaddr[48];
+
 #ifdef CONFIG_NFS_FSCACHE
 	struct fscache_cookie	*fscache;	/* client index cache cookie */
 #endif

include/linux/nfs_idmap.h

@@ -73,5 +73,7 @@ int nfs_map_group_to_gid(const struct nfs_server *, const char *, size_t, kgid_t
 int nfs_map_uid_to_name(const struct nfs_server *, kuid_t, char *, size_t);
 int nfs_map_gid_to_group(const struct nfs_server *, kgid_t, char *, size_t);
 
+int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res);
+
 extern unsigned int nfs_idmap_cache_timeout;
 #endif /* NFS_IDMAP_H */

include/linux/nfs_page.h

@@ -58,6 +58,9 @@ struct nfs_pageio_ops {
 	size_t	(*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *,
 			   struct nfs_page *);
 	int	(*pg_doio)(struct nfs_pageio_descriptor *);
+	unsigned int	(*pg_get_mirror_count)(struct nfs_pageio_descriptor *,
+				       struct nfs_page *);
+	void	(*pg_cleanup)(struct nfs_pageio_descriptor *);
 };
 
 struct nfs_rw_ops {
@@ -69,18 +72,21 @@ struct nfs_rw_ops {
 			struct inode *);
 	void (*rw_result)(struct rpc_task *, struct nfs_pgio_header *);
 	void (*rw_initiate)(struct nfs_pgio_header *, struct rpc_message *,
+			    const struct nfs_rpc_ops *,
 			    struct rpc_task_setup *, int);
 };
 
-struct nfs_pageio_descriptor {
+struct nfs_pgio_mirror {
 	struct list_head	pg_list;
 	unsigned long		pg_bytes_written;
 	size_t			pg_count;
 	size_t			pg_bsize;
 	unsigned int		pg_base;
-	unsigned char		pg_moreio : 1,
+	unsigned char		pg_recoalesce : 1;
-				pg_recoalesce : 1;
+};
 
+struct nfs_pageio_descriptor {
+	unsigned char		pg_moreio : 1;
 	struct inode		*pg_inode;
 	const struct nfs_pageio_ops *pg_ops;
 	const struct nfs_rw_ops *pg_rw_ops;
@@ -91,8 +97,18 @@ struct nfs_pageio_descriptor {
 	struct pnfs_layout_segment *pg_lseg;
 	struct nfs_direct_req	*pg_dreq;
 	void			*pg_layout_private;
+	unsigned int		pg_bsize;	/* default bsize for mirrors */
+
+	u32			pg_mirror_count;
+	struct nfs_pgio_mirror	*pg_mirrors;
+	struct nfs_pgio_mirror	pg_mirrors_static[1];
+	struct nfs_pgio_mirror	*pg_mirrors_dynamic;
+	u32			pg_mirror_idx;	/* current mirror */
 };
 
+/* arbitrarily selected limit to number of mirrors */
+#define NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX 16
+
 #define NFS_WBACK_BUSY(req)	(test_bit(PG_BUSY,&(req)->wb_flags))
 
 extern	struct nfs_page *nfs_create_request(struct nfs_open_context *ctx,

include/linux/nfs_xdr.h

@@ -293,6 +293,7 @@ struct nfs4_layoutreturn_args {
 	struct nfs4_sequence_args seq_args;
 	struct pnfs_layout_hdr *layout;
 	struct inode *inode;
+	struct pnfs_layout_range range;
 	nfs4_stateid stateid;
 	__u32   layout_type;
 };
@@ -514,6 +515,7 @@ struct nfs_pgio_res {
 	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr *	fattr;
 	__u32			count;
+	__u32			op_status;
 	int			eof;		/* used by read */
 	struct nfs_writeverf *	verf;		/* used by write */
 	const struct nfs_server *server;	/* used by write */
@@ -533,6 +535,7 @@ struct nfs_commitargs {
 
 struct nfs_commitres {
 	struct nfs4_sequence_res	seq_res;
+	__u32			op_status;
 	struct nfs_fattr	*fattr;
 	struct nfs_writeverf	*verf;
 	const struct nfs_server *server;
@@ -1326,7 +1329,8 @@ struct nfs_pgio_header {
 	__u64			mds_offset;	/* Filelayout dense stripe */
 	struct nfs_page_array	page_array;
 	struct nfs_client	*ds_clp;	/* pNFS data server */
-	int			ds_idx;		/* ds index if ds_clp is set */
+	int			ds_commit_idx;	/* ds index if ds_clp is set */
+	int			pgio_mirror_idx;/* mirror index in pgio layer */
 };
 
 struct nfs_mds_commit_info {

include/linux/sunrpc/metrics.h

@@ -79,6 +79,8 @@ struct rpc_clnt;
 struct rpc_iostats *	rpc_alloc_iostats(struct rpc_clnt *);
 void			rpc_count_iostats(const struct rpc_task *,
 					  struct rpc_iostats *);
+void			rpc_count_iostats_metrics(const struct rpc_task *,
+					  struct rpc_iostats *);
 void			rpc_print_iostats(struct seq_file *, struct rpc_clnt *);
 void			rpc_free_iostats(struct rpc_iostats *);
 
@@ -87,6 +89,8 @@ void			rpc_free_iostats(struct rpc_iostats *);
 static inline struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { return NULL; }
 static inline void rpc_count_iostats(const struct rpc_task *task,
 				     struct rpc_iostats *stats) {}
+static inline void rpc_count_iostats_metrics(const struct rpc_task *,
+					     struct rpc_iostats *) {}
 static inline void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) {}
 static inline void rpc_free_iostats(struct rpc_iostats *stats) {}
 

net/sunrpc/stats.c

@@ -140,22 +140,20 @@ void rpc_free_iostats(struct rpc_iostats *stats)
 EXPORT_SYMBOL_GPL(rpc_free_iostats);
 
 /**
- * rpc_count_iostats - tally up per-task stats
+ * rpc_count_iostats_metrics - tally up per-task stats
  * @task: completed rpc_task
- * @stats: array of stat structures
+ * @op_metrics: stat structure for OP that will accumulate stats from @task
  */
-void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
+void rpc_count_iostats_metrics(const struct rpc_task *task,
+			       struct rpc_iostats *op_metrics)
 {
 	struct rpc_rqst *req = task->tk_rqstp;
-	struct rpc_iostats *op_metrics;
 	ktime_t delta, now;
 
-	if (!stats || !req)
+	if (!op_metrics || !req)
 		return;
 
 	now = ktime_get();
-	op_metrics = &stats[task->tk_msg.rpc_proc->p_statidx];
-
 	spin_lock(&op_metrics->om_lock);
 
 	op_metrics->om_ops++;
@@ -175,6 +173,20 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
 
 	spin_unlock(&op_metrics->om_lock);
 }
+EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics);
+
+/**
+ * rpc_count_iostats - tally up per-task stats
+ * @task: completed rpc_task
+ * @stats: array of stat structures
+ *
+ * Uses the statidx from @task
+ */
+void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
+{
+	rpc_count_iostats_metrics(task,
+				  &stats[task->tk_msg.rpc_proc->p_statidx]);
+}
 EXPORT_SYMBOL_GPL(rpc_count_iostats);
 
 static void _print_name(struct seq_file *seq, unsigned int op,