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
-layout types: "files" "objects" and "blocks". For each of these types
-there is a layout-driver with a common function-vectors table which
-are called by the nfs-client pnfs-core to implement the different layout
-types.
+PNFS utilizes what is called layout drivers. The STD defines 4 basic
+layout types: "files", "objects", "blocks", and "flexfiles". For each
+of these types there is a layout-driver with a common function-vectors
+table which are called by the nfs-client pnfs-core to implement the
+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)
-			verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf;
+		if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets)
+			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,
-				      hdr->ds_idx);
+	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_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,
-					 hdr->ds_idx);
+	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_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 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 	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);
-	spin_lock(cinfo.lock);
-	nfs_scan_commit_list(&cinfo.mds->list, &reqs, &cinfo, 0);
-	spin_unlock(cinfo.lock);
+	nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
 
 	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.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/flexfilelayout/Makefile

+#
+# 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

+/*
+ * 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/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 *,
-		      const struct rpc_call_ops *, int, int);
+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);
 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 @@ static int decode_path(struct xdr_stream *xdr)
  *		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 @@ static int nfs2_xdr_dec_stat(struct rpc_rqst *req, struct xdr_stream *xdr,
 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

 #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 @@ static int nfs4_set_client(struct nfs_server *server,
  */
 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,
-				struct nfs4_sequence_args *args,
-				struct nfs4_sequence_res *res,
-				struct rpc_task *task)
+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 @@ static int nfs40_setup_sequence(const struct nfs_server *server,
 	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 @@ int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 }
 EXPORT_SYMBOL_GPL(nfs41_sequence_done);
 
-static int nfs4_sequence_done(struct rpc_task *task,
-			       struct nfs4_sequence_res *res)
+int nfs4_sequence_done(struct rpc_task *task, 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,
-			       struct nfs4_sequence_res *res)
+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,
-				&data->c_res.seq_res, task);
+	nfs40_setup_sequence(data->o_arg.server->nfs_client->cl_slot_tbl,
+			     &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,
-				&data->res.seq_res, task);
+	nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
+			     &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 @@ static int __init init_nfs_v4(void)
 
 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, NFS4_MAX_UINT64);
+	p = xdr_encode_hyper(p, args->range.offset);
+	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/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/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 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr)
 
 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);

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/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) {}