nfsd: implement pNFS operations

Add support for the GETDEVICEINFO, LAYOUTGET, LAYOUTCOMMIT and
LAYOUTRETURN NFSv4.1 operations, as well as backing code to manage
outstanding layouts and devices.

Layout management is very straight forward, with a nfs4_layout_stateid
structure that extends nfs4_stid to manage layout stateids as the
top-level structure.  It is linked into the nfs4_file and nfs4_client
structures like the other stateids, and contains a linked list of
layouts that hang of the stateid.  The actual layout operations are
implemented in layout drivers that are not part of this commit, but
will be added later.

The worst part of this commit is the management of the pNFS device IDs,
which suffers from a specification that is not sanely implementable due
to the fact that the device-IDs are global and not bound to an export,
and have a small enough size so that we can't store the fsid portion of
a file handle, and must never be reused.  As we still do need perform all
export authentication and validation checks on a device ID passed to
GETDEVICEINFO we are caught between a rock and a hard place.  To work
around this issue we add a new hash that maps from a 64-bit integer to a
fsid so that we can look up the export to authenticate against it,
a 32-bit integer as a generation that we can bump when changing the device,
and a currently unused 32-bit integer that could be used in the future
to handle more than a single device per export.  Entries in this hash
table are never deleted as we can't reuse the ids anyway, and would have
a severe lifetime problem anyway as Linux export structures are temporary
structures that can go away under load.

Parts of the XDR data, structures and marshaling/unmarshaling code, as
well as many concepts are derived from the old pNFS server implementation
from Andy Adamson, Benny Halevy, Dean Hildebrand, Marc Eshel, Fred Isaman,
Mike Sager, Ricardo Labiaga and many others.

Signed-off-by: Christoph Hellwig <hch@lst.de>

16 files changed, 1324 insertions, 5 deletions

diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 73395156bdb4..683bf718aead 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -82,6 +82,16 @@ config NFSD_V4
 
 	  If unsure, say N.
 
+config NFSD_PNFS
+	bool "NFSv4.1 server support for Parallel NFS (pNFS)"
+	depends on NFSD_V4
+	help
+	  This option enables support for the parallel NFS features of the
+	  minor version 1 of the NFSv4 protocol (RFC5661) in the kernel's NFS
+	  server.
+
+	  If unsure, say N.
+
 config NFSD_V4_SECURITY_LABEL
 	bool "Provide Security Label support for NFSv4 server"
 	depends on NFSD_V4 && SECURITY
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index af32ef06b4fe..5806270a8567 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -12,3 +12,4 @@ nfsd-$(CONFIG_NFSD_V3)	+= nfs3proc.o nfs3xdr.o
 nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
 nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
 			   nfs4acl.o nfs4callback.o nfs4recover.o
+nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 30a739d896ff..c3e3b6e55ae2 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -20,6 +20,7 @@
 #include "nfsd.h"
 #include "nfsfh.h"
 #include "netns.h"
+#include "pnfs.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT
 
@@ -545,6 +546,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 
 	exp.ex_client = dom;
 	exp.cd = cd;
+	exp.ex_devid_map = NULL;
 
 	/* expiry */
 	err = -EINVAL;
@@ -621,6 +623,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 		if (!gid_valid(exp.ex_anon_gid))
 			goto out4;
 		err = 0;
+
+		nfsd4_setup_layout_type(&exp);
 	}
 
 	expp = svc_export_lookup(&exp);
@@ -703,6 +707,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_fslocs.locations = NULL;
 	new->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = 0;
+	new->ex_layout_type = 0;
 	new->ex_uuid = NULL;
 	new->cd = item->cd;
 }
@@ -717,6 +722,8 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_anon_uid = item->ex_anon_uid;
 	new->ex_anon_gid = item->ex_anon_gid;
 	new->ex_fsid = item->ex_fsid;
+	new->ex_devid_map = item->ex_devid_map;
+	item->ex_devid_map = NULL;
 	new->ex_uuid = item->ex_uuid;
 	item->ex_uuid = NULL;
 	new->ex_fslocs.locations = item->ex_fslocs.locations;
@@ -725,6 +732,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	item->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = item->ex_fslocs.migrated;
 	item->ex_fslocs.migrated = 0;
+	new->ex_layout_type = item->ex_layout_type;
 	new->ex_nflavors = item->ex_nflavors;
 	for (i = 0; i < MAX_SECINFO_LIST; i++) {
 		new->ex_flavors[i] = item->ex_flavors[i];
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index 04dc8c167b0c..1f52bfcc436f 100644
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -56,6 +56,8 @@ struct svc_export {
 	struct nfsd4_fs_locations ex_fslocs;
 	uint32_t		ex_nflavors;
 	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
+	enum pnfs_layouttype	ex_layout_type;
+	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
 };
 
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
new file mode 100644
index 000000000000..8273270418b1
--- /dev/null
+++ b/fs/nfsd/nfs4layouts.c
@@ -0,0 +1,487 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/jhash.h>
+#include <linux/sched.h>
+
+#include "pnfs.h"
+#include "netns.h"
+
+#define NFSDDBG_FACILITY                NFSDDBG_PNFS
+
+struct nfs4_layout {
+	struct list_head		lo_perstate;
+	struct nfs4_layout_stateid	*lo_state;
+	struct nfsd4_layout_seg		lo_seg;
+};
+
+static struct kmem_cache *nfs4_layout_cache;
+static struct kmem_cache *nfs4_layout_stateid_cache;
+
+const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
+};
+
+/* pNFS device ID to export fsid mapping */
+#define DEVID_HASH_BITS	8
+#define DEVID_HASH_SIZE	(1 << DEVID_HASH_BITS)
+#define DEVID_HASH_MASK	(DEVID_HASH_SIZE - 1)
+static u64 nfsd_devid_seq = 1;
+static struct list_head nfsd_devid_hash[DEVID_HASH_SIZE];
+static DEFINE_SPINLOCK(nfsd_devid_lock);
+
+static inline u32 devid_hashfn(u64 idx)
+{
+	return jhash_2words(idx, idx >> 32, 0) & DEVID_HASH_MASK;
+}
+
+static void
+nfsd4_alloc_devid_map(const struct svc_fh *fhp)
+{
+	const struct knfsd_fh *fh = &fhp->fh_handle;
+	size_t fsid_len = key_len(fh->fh_fsid_type);
+	struct nfsd4_deviceid_map *map, *old;
+	int i;
+
+	map = kzalloc(sizeof(*map) + fsid_len, GFP_KERNEL);
+	if (!map)
+		return;
+
+	map->fsid_type = fh->fh_fsid_type;
+	memcpy(&map->fsid, fh->fh_fsid, fsid_len);
+
+	spin_lock(&nfsd_devid_lock);
+	if (fhp->fh_export->ex_devid_map)
+		goto out_unlock;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		list_for_each_entry(old, &nfsd_devid_hash[i], hash) {
+			if (old->fsid_type != fh->fh_fsid_type)
+				continue;
+			if (memcmp(old->fsid, fh->fh_fsid,
+					key_len(old->fsid_type)))
+				continue;
+
+			fhp->fh_export->ex_devid_map = old;
+			goto out_unlock;
+		}
+	}
+
+	map->idx = nfsd_devid_seq++;
+	list_add_tail_rcu(&map->hash, &nfsd_devid_hash[devid_hashfn(map->idx)]);
+	fhp->fh_export->ex_devid_map = map;
+	map = NULL;
+
+out_unlock:
+	spin_unlock(&nfsd_devid_lock);
+	kfree(map);
+}
+
+struct nfsd4_deviceid_map *
+nfsd4_find_devid_map(int idx)
+{
+	struct nfsd4_deviceid_map *map, *ret = NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(map, &nfsd_devid_hash[devid_hashfn(idx)], hash)
+		if (map->idx == idx)
+			ret = map;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+int
+nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation)
+{
+	if (!fhp->fh_export->ex_devid_map) {
+		nfsd4_alloc_devid_map(fhp);
+		if (!fhp->fh_export->ex_devid_map)
+			return -ENOMEM;
+	}
+
+	id->fsid_idx = fhp->fh_export->ex_devid_map->idx;
+	id->generation = device_generation;
+	id->pad = 0;
+	return 0;
+}
+
+void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+	if (exp->ex_flags & NFSEXP_NOPNFS)
+		return;
+}
+
+static void
+nfsd4_free_layout_stateid(struct nfs4_stid *stid)
+{
+	struct nfs4_layout_stateid *ls = layoutstateid(stid);
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+
+	spin_lock(&clp->cl_lock);
+	list_del_init(&ls->ls_perclnt);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_del_init(&ls->ls_perfile);
+	spin_unlock(&fp->fi_lock);
+
+	kmem_cache_free(nfs4_layout_stateid_cache, ls);
+}
+
+static struct nfs4_layout_stateid *
+nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
+		struct nfs4_stid *parent, u32 layout_type)
+{
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_file *fp = parent->sc_file;
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stp;
+
+	stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache);
+	if (!stp)
+		return NULL;
+	stp->sc_free = nfsd4_free_layout_stateid;
+	get_nfs4_file(fp);
+	stp->sc_file = fp;
+
+	ls = layoutstateid(stp);
+	INIT_LIST_HEAD(&ls->ls_perclnt);
+	INIT_LIST_HEAD(&ls->ls_perfile);
+	spin_lock_init(&ls->ls_lock);
+	INIT_LIST_HEAD(&ls->ls_layouts);
+	ls->ls_layout_type = layout_type;
+
+	spin_lock(&clp->cl_lock);
+	stp->sc_type = NFS4_LAYOUT_STID;
+	list_add(&ls->ls_perclnt, &clp->cl_lo_states);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_add(&ls->ls_perfile, &fp->fi_lo_states);
+	spin_unlock(&fp->fi_lock);
+
+	return ls;
+}
+
+__be32
+nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stid;
+	unsigned char typemask = NFS4_LAYOUT_STID;
+	__be32 status;
+
+	if (create)
+		typemask |= (NFS4_OPEN_STID | NFS4_LOCK_STID | NFS4_DELEG_STID);
+
+	status = nfsd4_lookup_stateid(cstate, stateid, typemask, &stid,
+			net_generic(SVC_NET(rqstp), nfsd_net_id));
+	if (status)
+		goto out;
+
+	if (!fh_match(&cstate->current_fh.fh_handle,
+		      &stid->sc_file->fi_fhandle)) {
+		status = nfserr_bad_stateid;
+		goto out_put_stid;
+	}
+
+	if (stid->sc_type != NFS4_LAYOUT_STID) {
+		ls = nfsd4_alloc_layout_stateid(cstate, stid, layout_type);
+		nfs4_put_stid(stid);
+
+		status = nfserr_jukebox;
+		if (!ls)
+			goto out;
+	} else {
+		ls = container_of(stid, struct nfs4_layout_stateid, ls_stid);
+
+		status = nfserr_bad_stateid;
+		if (stateid->si_generation > stid->sc_stateid.si_generation)
+			goto out_put_stid;
+		if (layout_type != ls->ls_layout_type)
+			goto out_put_stid;
+	}
+
+	*lsp = ls;
+	return 0;
+
+out_put_stid:
+	nfs4_put_stid(stid);
+out:
+	return status;
+}
+
+static inline u64
+layout_end(struct nfsd4_layout_seg *seg)
+{
+	u64 end = seg->offset + seg->length;
+	return end >= seg->offset ? end : NFS4_MAX_UINT64;
+}
+
+static void
+layout_update_len(struct nfsd4_layout_seg *lo, u64 end)
+{
+	if (end == NFS4_MAX_UINT64)
+		lo->length = NFS4_MAX_UINT64;
+	else
+		lo->length = end - lo->offset;
+}
+
+static bool
+layouts_overlapping(struct nfs4_layout *lo, struct nfsd4_layout_seg *s)
+{
+	if (s->iomode != IOMODE_ANY && s->iomode != lo->lo_seg.iomode)
+		return false;
+	if (layout_end(&lo->lo_seg) <= s->offset)
+		return false;
+	if (layout_end(s) <= lo->lo_seg.offset)
+		return false;
+	return true;
+}
+
+static bool
+layouts_try_merge(struct nfsd4_layout_seg *lo, struct nfsd4_layout_seg *new)
+{
+	if (lo->iomode != new->iomode)
+		return false;
+	if (layout_end(new) < lo->offset)
+		return false;
+	if (layout_end(lo) < new->offset)
+		return false;
+
+	lo->offset = min(lo->offset, new->offset);
+	layout_update_len(lo, max(layout_end(lo), layout_end(new)));
+	return true;
+}
+
+__be32
+nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls)
+{
+	struct nfsd4_layout_seg *seg = &lgp->lg_seg;
+	struct nfs4_layout *lp, *new = NULL;
+
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+	spin_unlock(&ls->ls_lock);
+
+	new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL);
+	if (!new)
+		return nfserr_jukebox;
+	memcpy(&new->lo_seg, seg, sizeof(lp->lo_seg));
+	new->lo_state = ls;
+
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+
+	atomic_inc(&ls->ls_stid.sc_count);
+	list_add_tail(&new->lo_perstate, &ls->ls_layouts);
+	new = NULL;
+done:
+	update_stateid(&ls->ls_stid.sc_stateid);
+	memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
+	spin_unlock(&ls->ls_lock);
+	if (new)
+		kmem_cache_free(nfs4_layout_cache, new);
+	return nfs_ok;
+}
+
+static void
+nfsd4_free_layouts(struct list_head *reaplist)
+{
+	while (!list_empty(reaplist)) {
+		struct nfs4_layout *lp = list_first_entry(reaplist,
+				struct nfs4_layout, lo_perstate);
+
+		list_del(&lp->lo_perstate);
+		nfs4_put_stid(&lp->lo_state->ls_stid);
+		kmem_cache_free(nfs4_layout_cache, lp);
+	}
+}
+
+static void
+nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg,
+		struct list_head *reaplist)
+{
+	struct nfsd4_layout_seg *lo = &lp->lo_seg;
+	u64 end = layout_end(lo);
+
+	if (seg->offset <= lo->offset) {
+		if (layout_end(seg) >= end) {
+			list_move_tail(&lp->lo_perstate, reaplist);
+			return;
+		}
+		end = seg->offset;
+	} else {
+		/* retain the whole layout segment on a split. */
+		if (layout_end(seg) < end) {
+			dprintk("%s: split not supported\n", __func__);
+			return;
+		}
+
+		lo->offset = layout_end(seg);
+	}
+
+	layout_update_len(lo, end);
+}
+
+__be32
+nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_layout *lp, *n;
+	LIST_HEAD(reaplist);
+	__be32 nfserr;
+	int found = 0;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lrp->lr_sid,
+						false, lrp->lr_layout_type,
+						&ls);
+	if (nfserr)
+		return nfserr;
+
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry_safe(lp, n, &ls->ls_layouts, lo_perstate) {
+		if (layouts_overlapping(lp, &lrp->lr_seg)) {
+			nfsd4_return_file_layout(lp, &lrp->lr_seg, &reaplist);
+			found++;
+		}
+	}
+	if (!list_empty(&ls->ls_layouts)) {
+		if (found) {
+			update_stateid(&ls->ls_stid.sc_stateid);
+			memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid,
+				sizeof(stateid_t));
+		}
+		lrp->lrs_present = 1;
+	} else {
+		nfs4_unhash_stid(&ls->ls_stid);
+		lrp->lrs_present = 0;
+	}
+	spin_unlock(&ls->ls_lock);
+
+	nfs4_put_stid(&ls->ls_stid);
+	nfsd4_free_layouts(&reaplist);
+	return nfs_ok;
+}
+
+__be32
+nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_layout *lp, *t;
+	LIST_HEAD(reaplist);
+
+	lrp->lrs_present = 0;
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) {
+		if (lrp->lr_return_type == RETURN_FSID &&
+		    !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle,
+				   &cstate->current_fh.fh_handle))
+			continue;
+
+		spin_lock(&ls->ls_lock);
+		list_for_each_entry_safe(lp, t, &ls->ls_layouts, lo_perstate) {
+			if (lrp->lr_seg.iomode == IOMODE_ANY ||
+			    lrp->lr_seg.iomode == lp->lo_seg.iomode)
+				list_move_tail(&lp->lo_perstate, &reaplist);
+		}
+		spin_unlock(&ls->ls_lock);
+	}
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+	return 0;
+}
+
+static void
+nfsd4_return_all_layouts(struct nfs4_layout_stateid *ls,
+		struct list_head *reaplist)
+{
+	spin_lock(&ls->ls_lock);
+	list_splice_init(&ls->ls_layouts, reaplist);
+	spin_unlock(&ls->ls_lock);
+}
+
+void
+nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt)
+		nfsd4_return_all_layouts(ls, &reaplist);
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+void
+nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&fp->fi_lock);
+	list_for_each_entry_safe(ls, n, &fp->fi_lo_states, ls_perfile) {
+		if (ls->ls_stid.sc_client == clp)
+			nfsd4_return_all_layouts(ls, &reaplist);
+	}
+	spin_unlock(&fp->fi_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+int
+nfsd4_init_pnfs(void)
+{
+	int i;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++)
+		INIT_LIST_HEAD(&nfsd_devid_hash[i]);
+
+	nfs4_layout_cache = kmem_cache_create("nfs4_layout",
+			sizeof(struct nfs4_layout), 0, 0, NULL);
+	if (!nfs4_layout_cache)
+		return -ENOMEM;
+
+	nfs4_layout_stateid_cache = kmem_cache_create("nfs4_layout_stateid",
+			sizeof(struct nfs4_layout_stateid), 0, 0, NULL);
+	if (!nfs4_layout_stateid_cache) {
+		kmem_cache_destroy(nfs4_layout_cache);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void
+nfsd4_exit_pnfs(void)
+{
+	int i;
+
+	kmem_cache_destroy(nfs4_layout_cache);
+	kmem_cache_destroy(nfs4_layout_stateid_cache);
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		struct nfsd4_deviceid_map *map, *n;
+
+		list_for_each_entry_safe(map, n, &nfsd_devid_hash[i], hash)
+			kfree(map);
+	}
+}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index ac71d13c69ef..2b91443497cc 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -43,6 +43,7 @@
 #include "current_stateid.h"
 #include "netns.h"
 #include "acl.h"
+#include "pnfs.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -1178,6 +1179,252 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status == nfserr_same ? nfs_ok : status;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static const struct nfsd4_layout_ops *
+nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
+{
+	if (!exp->ex_layout_type) {
+		dprintk("%s: export does not support pNFS\n", __func__);
+		return NULL;
+	}
+
+	if (exp->ex_layout_type != layout_type) {
+		dprintk("%s: layout type %d not supported\n",
+			__func__, layout_type);
+		return NULL;
+	}
+
+	return nfsd4_layout_ops[layout_type];
+}
+
+static __be32
+nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	const struct nfsd4_layout_ops *ops;
+	struct nfsd4_deviceid_map *map;
+	struct svc_export *exp;
+	__be32 nfserr;
+
+	dprintk("%s: layout_type %u dev_id [0x%llx:0x%x] maxcnt %u\n",
+	       __func__,
+	       gdp->gd_layout_type,
+	       gdp->gd_devid.fsid_idx, gdp->gd_devid.generation,
+	       gdp->gd_maxcount);
+
+	map = nfsd4_find_devid_map(gdp->gd_devid.fsid_idx);
+	if (!map) {
+		dprintk("%s: couldn't find device ID to export mapping!\n",
+			__func__);
+		return nfserr_noent;
+	}
+
+	exp = rqst_exp_find(rqstp, map->fsid_type, map->fsid);
+	if (IS_ERR(exp)) {
+		dprintk("%s: could not find device id\n", __func__);
+		return nfserr_noent;
+	}
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(exp, gdp->gd_layout_type);
+	if (!ops)
+		goto out;
+
+	nfserr = nfs_ok;
+	if (gdp->gd_maxcount != 0)
+		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp);
+
+	gdp->gd_notify_types &= ops->notify_types;
+	exp_put(exp);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutget(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutget *lgp)
+{
+	struct svc_fh *current_fh = &cstate->current_fh;
+	const struct nfsd4_layout_ops *ops;
+	struct nfs4_layout_stateid *ls;
+	__be32 nfserr;
+	int accmode;
+
+	switch (lgp->lg_seg.iomode) {
+	case IOMODE_READ:
+		accmode = NFSD_MAY_READ;
+		break;
+	case IOMODE_RW:
+		accmode = NFSD_MAY_READ | NFSD_MAY_WRITE;
+		break;
+	default:
+		dprintk("%s: invalid iomode %d\n",
+			__func__, lgp->lg_seg.iomode);
+		nfserr = nfserr_badiomode;
+		goto out;
+	}
+
+	nfserr = fh_verify(rqstp, current_fh, 0, accmode);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(current_fh->fh_export, lgp->lg_layout_type);
+	if (!ops)
+		goto out;
+
+	/*
+	 * Verify minlength and range as per RFC5661:
+	 *  o  If loga_length is less than loga_minlength,
+	 *     the metadata server MUST return NFS4ERR_INVAL.
+	 *  o  If the sum of loga_offset and loga_minlength exceeds
+	 *     NFS4_UINT64_MAX, and loga_minlength is not
+	 *     NFS4_UINT64_MAX, the error NFS4ERR_INVAL MUST result.
+	 *  o  If the sum of loga_offset and loga_length exceeds
+	 *     NFS4_UINT64_MAX, and loga_length is not NFS4_UINT64_MAX,
+	 *     the error NFS4ERR_INVAL MUST result.
+	 */
+	nfserr = nfserr_inval;
+	if (lgp->lg_seg.length < lgp->lg_minlength ||
+	    (lgp->lg_minlength != NFS4_MAX_UINT64 &&
+	     lgp->lg_minlength > NFS4_MAX_UINT64 - lgp->lg_seg.offset) ||
+	    (lgp->lg_seg.length != NFS4_MAX_UINT64 &&
+	     lgp->lg_seg.length > NFS4_MAX_UINT64 - lgp->lg_seg.offset))
+		goto out;
+	if (lgp->lg_seg.length == 0)
+		goto out;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid,
+						true, lgp->lg_layout_type, &ls);
+	if (nfserr)
+		goto out;
+
+	nfserr = ops->proc_layoutget(current_fh->fh_dentry->d_inode,
+				     current_fh, lgp);
+	if (nfserr)
+		goto out_put_stid;
+
+	nfserr = nfsd4_insert_layout(lgp, ls);
+
+out_put_stid:
+	nfs4_put_stid(&ls->ls_stid);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutcommit(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutcommit *lcp)
+{
+	const struct nfsd4_layout_seg *seg = &lcp->lc_seg;
+	struct svc_fh *current_fh = &cstate->current_fh;
+	const struct nfsd4_layout_ops *ops;
+	loff_t new_size = lcp->lc_last_wr + 1;
+	struct inode *inode;
+	struct nfs4_layout_stateid *ls;
+	__be32 nfserr;
+
+	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(current_fh->fh_export, lcp->lc_layout_type);
+	if (!ops)
+		goto out;
+	inode = current_fh->fh_dentry->d_inode;
+
+	nfserr = nfserr_inval;
+	if (new_size <= seg->offset) {
+		dprintk("pnfsd: last write before layout segment\n");
+		goto out;
+	}
+	if (new_size > seg->offset + seg->length) {
+		dprintk("pnfsd: last write beyond layout segment\n");
+		goto out;
+	}
+	if (!lcp->lc_newoffset && new_size > i_size_read(inode)) {
+		dprintk("pnfsd: layoutcommit beyond EOF\n");
+		goto out;
+	}
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid,
+						false, lcp->lc_layout_type,
+						&ls);
+	if (nfserr) {
+		/* fixup error code as per RFC5661 */
+		if (nfserr == nfserr_bad_stateid)
+			nfserr = nfserr_badlayout;
+		goto out;
+	}
+
+	nfserr = ops->proc_layoutcommit(inode, lcp);
+	if (nfserr)
+		goto out_put_stid;
+
+	if (new_size > i_size_read(inode)) {
+		lcp->lc_size_chg = 1;
+		lcp->lc_newsize = new_size;
+	} else {
+		lcp->lc_size_chg = 0;
+	}
+
+out_put_stid:
+	nfs4_put_stid(&ls->ls_stid);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutreturn(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct svc_fh *current_fh = &cstate->current_fh;
+	__be32 nfserr;
+
+	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_NOP);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	if (!nfsd4_layout_verify(current_fh->fh_export, lrp->lr_layout_type))
+		goto out;
+
+	switch (lrp->lr_seg.iomode) {
+	case IOMODE_READ:
+	case IOMODE_RW:
+	case IOMODE_ANY:
+		break;
+	default:
+		dprintk("%s: invalid iomode %d\n", __func__,
+			lrp->lr_seg.iomode);
+		nfserr = nfserr_inval;
+		goto out;
+	}
+
+	switch (lrp->lr_return_type) {
+	case RETURN_FILE:
+		nfserr = nfsd4_return_file_layouts(rqstp, cstate, lrp);
+		break;
+	case RETURN_FSID:
+	case RETURN_ALL:
+		nfserr = nfsd4_return_client_layouts(rqstp, cstate, lrp);
+		break;
+	default:
+		dprintk("%s: invalid return_type %d\n", __func__,
+			lrp->lr_return_type);
+		nfserr = nfserr_inval;
+		break;
+	}
+out:
+	return nfserr;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 /*
  * NULL call.
  */
@@ -1679,6 +1926,36 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd
 		op_encode_channel_attrs_maxsz) * sizeof(__be32);
 }
 
+#ifdef CONFIG_NFSD_PNFS
+/*
+ * At this stage we don't really know what layout driver will handle the request,
+ * so we need to define an arbitrary upper bound here.
+ */
+#define MAX_LAYOUT_SIZE		128
+static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* logr_return_on_close */ +
+		op_encode_stateid_maxsz +
+		1 /* nr of layouts */ +
+		MAX_LAYOUT_SIZE) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* locr_newsize */ +
+		2 /* ns_size */) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* lrs_stateid */ +
+		op_encode_stateid_maxsz) * sizeof(__be32);
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static struct nfsd4_operation nfsd4_ops[] = {
 	[OP_ACCESS] = {
 		.op_func = (nfsd4op_func)nfsd4_access,
@@ -1966,6 +2243,31 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO] = {
+		.op_func = (nfsd4op_func)nfsd4_getdeviceinfo,
+		.op_flags = ALLOWED_WITHOUT_FH,
+		.op_name = "OP_GETDEVICEINFO",
+	},
+	[OP_LAYOUTGET] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutget,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTGET",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize,
+	},
+	[OP_LAYOUTCOMMIT] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutcommit,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTCOMMIT",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize,
+	},
+	[OP_LAYOUTRETURN] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutreturn,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTRETURN",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize,
+	},
+#endif /* CONFIG_NFSD_PNFS */
 
 	/* NFSv4.2 operations */
 	[OP_ALLOCATE] = {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index eefd29ec43f2..c89f79dc69e2 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -48,6 +48,7 @@
 #include "current_stateid.h"
 
 #include "netns.h"
+#include "pnfs.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
@@ -1539,6 +1540,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 	INIT_LIST_HEAD(&clp->cl_lru);
 	INIT_LIST_HEAD(&clp->cl_callbacks);
 	INIT_LIST_HEAD(&clp->cl_revoked);
+#ifdef CONFIG_NFSD_PNFS
+	INIT_LIST_HEAD(&clp->cl_lo_states);
+#endif
 	spin_lock_init(&clp->cl_lock);
 	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	return clp;
@@ -1643,6 +1647,7 @@ __destroy_client(struct nfs4_client *clp)
 		nfs4_get_stateowner(&oo->oo_owner);
 		release_openowner(oo);
 	}
+	nfsd4_return_all_client_layouts(clp);
 	nfsd4_shutdown_callback(clp);
 	if (clp->cl_cb_conn.cb_xprt)
 		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
@@ -2126,8 +2131,11 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
 static void
 nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid)
 {
-	/* pNFS is not supported */
+#ifdef CONFIG_NFSD_PNFS
+	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS;
+#else
 	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS;
+#endif
 
 	/* Referrals are supported, Migration is not. */
 	new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER;
@@ -3055,6 +3063,9 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
 	fp->fi_share_deny = 0;
 	memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
 	memset(fp->fi_access, 0, sizeof(fp->fi_access));
+#ifdef CONFIG_NFSD_PNFS
+	INIT_LIST_HEAD(&fp->fi_lo_states);
+#endif
 	hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]);
 }
 
@@ -4841,6 +4852,9 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
 
+	nfsd4_return_all_file_layouts(stp->st_stateowner->so_client,
+				      stp->st_stid.sc_file);
+
 	nfsd4_close_open_stateid(stp);
 
 	/* put reference from nfs4_preprocess_seqid_op */
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 974533e5a427..df5e66caf100 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -47,6 +47,7 @@
 #include "state.h"
 #include "cache.h"
 #include "netns.h"
+#include "pnfs.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -1522,6 +1523,127 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
 	DECODE_TAIL;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static __be32
+nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp,
+		struct nfsd4_getdeviceinfo *gdev)
+{
+	DECODE_HEAD;
+	u32 num, i;
+
+	READ_BUF(sizeof(struct nfsd4_deviceid) + 3 * 4);
+	COPYMEM(&gdev->gd_devid, sizeof(struct nfsd4_deviceid));
+	gdev->gd_layout_type = be32_to_cpup(p++);