[PATCH v3 0/8] server-side support for "inter" SSC copy

[PATCH v3 0/8] server-side support for "inter" SSC copy

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

This patch series adds support for NFSv4.2 copy offload feature
allowing copy between two different NFS servers.

This functionality depends on the VFS ability to support generic
copy_file_range() where a copy is done between an NFS file and
a local file system. This is on top of Amir's VFS generic copy
offload series.

This feature is enabled by the kernel module parameter --
inter_copy_offload_enable -- and by default is disabled. There is
also a kernel compile configuration of NFSD_V4_2_INTER_SSC that
adds dependency on the NFS client side functions called from the
server.

These patches work on top of existing async intra copy offload
patches. For the "inter" SSC, the implementation only supports
asynchronous inter copy.

On the source server, upon receiving a COPY_NOTIFY, it generate a
unique stateid that's kept in the global list. Upon receiving a READ
with a stateid, the code checks the normal list of open stateid and
now additionally, it'll check the copy state list as well before
deciding to either fail with BAD_STATEID or find one that matches.
The stored stateid is only valid to be used for the first time
with a choosen lease period (90s currently). When the source server
received an OFFLOAD_CANCEL, it will remove the stateid from the
global list. Otherwise, the copy stateid is removed upon the removal
of its "parent" stateid (open/lock/delegation stateid).

On the destination server, upon receiving a COPY request, the server
establishes the necessary clientid/session with the source server.
It calls into the NFS client code to establish the necessary
open stateid, filehandle, file description (without doing an NFS open).
Then the server calls into the copy_file_range() to preform the copy
where the source file will issue NFS READs and then do local file
system writes (this depends on the VFS ability to do cross device
copy_file_range().

v3:
-- when nfsd_copy_file_range() returns EBADF and no bytes were read
return NFS4ERR_PARTNER_NO_AUTH to signal to the client to restart the
copy. EBADF can happen when (1st) READ wasn't successful to the source
server due to server reboot or taking too long to make the 1st read
after COPY_NOTIFY was sent to the source server
--- made changes as per Bruce's comment. (1) changing struct nl4_server
not to be allocated on the stack (2) move checking for copy compound to
allow for foreigh filehandle in the compound in a separate function.
(3) removed might_sleep().

Olga Kornievskaia (8):
  NFSD fill-in netloc4 structure
  NFSD add ca_source_server<> to COPY
  NFSD return nfs4_stid in nfs4_preprocess_stateid_op
  NFSD add COPY_NOTIFY operation
  NFSD check stateids against copy stateids
  NFSD generalize nfsd4_compound_state flag names
  NFSD: allow inter server COPY to have a STALE source server fh
  NFSD add nfs4 inter ssc to nfsd4_copy

 fs/nfsd/Kconfig      |  10 ++
 fs/nfsd/nfs4proc.c   | 420 ++++++++++++++++++++++++++++++++++++++++++++++-----
 fs/nfsd/nfs4state.c  | 122 +++++++++++++--
 fs/nfsd/nfs4xdr.c    | 172 ++++++++++++++++++++-
 fs/nfsd/nfsd.h       |  32 ++++
 fs/nfsd/nfsfh.h      |   5 +-
 fs/nfsd/nfssvc.c     |   6 +
 fs/nfsd/state.h      |  21 ++-
 fs/nfsd/xdr4.h       |  37 ++++-
 include/linux/nfs4.h |   1 +
 10 files changed, 763 insertions(+), 63 deletions(-)

-- 
1.8.3.1

[PATCH v3 1/8] NFSD fill-in netloc4 structure

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

nfs.4 defines nfs42_netaddr structure that represents netloc4.

Populate needed fields from the sockaddr structure.

This will be used by flexfiles and 4.2 inter copy

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfsd/nfsd.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 24187b5..8f4fc50 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -19,6 +19,7 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svc_xprt.h>
 #include <linux/sunrpc/msg_prot.h>
+#include <linux/sunrpc/addr.h>
 
 #include <uapi/linux/nfsd/debug.h>
 
@@ -375,6 +376,37 @@ static inline bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
 
 extern const u32 nfsd_suppattrs[3][3];
 
+static inline u32 nfsd4_set_netaddr(struct sockaddr *addr,
+				    struct nfs42_netaddr *netaddr)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)addr;
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
+	unsigned int port;
+	size_t ret_addr, ret_port;
+
+	switch (addr->sa_family) {
+	case AF_INET:
+		port = ntohs(sin->sin_port);
+		sprintf(netaddr->netid, "tcp");
+		netaddr->netid_len = 3;
+		break;
+	case AF_INET6:
+		port = ntohs(sin6->sin6_port);
+		sprintf(netaddr->netid, "tcp6");
+		netaddr->netid_len = 4;
+		break;
+	default:
+		return nfserr_inval;
+	}
+	ret_addr = rpc_ntop(addr, netaddr->addr, sizeof(netaddr->addr));
+	ret_port = snprintf(netaddr->addr + ret_addr,
+			    RPCBIND_MAXUADDRLEN + 1 - ret_addr,
+			    ".%u.%u", port >> 8, port & 0xff);
+	WARN_ON(ret_port >= RPCBIND_MAXUADDRLEN + 1 - ret_addr);
+	netaddr->addr_len = ret_addr + ret_port;
+	return 0;
+}
+
 static inline bool bmval_is_subset(const u32 *bm1, const u32 *bm2)
 {
 	return !((bm1[0] & ~bm2[0]) ||
-- 
1.8.3.1

[PATCH v3 2/8] NFSD add ca_source_server<> to COPY

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

Decode the ca_source_server list that's sent but only use the
first one. Presence of non-zero list indicates an "inter" copy.

Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfsd/nfs4xdr.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++++++++--
 fs/nfsd/xdr4.h    | 12 +++++----
 2 files changed, 80 insertions(+), 7 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 52c4f6d..15f53bb 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -40,6 +40,7 @@
 #include <linux/utsname.h>
 #include <linux/pagemap.h>
 #include <linux/sunrpc/svcauth_gss.h>
+#include <linux/sunrpc/addr.h>
 
 #include "idmap.h"
 #include "acl.h"
@@ -1744,11 +1745,58 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
 	DECODE_TAIL;
 }
 
+static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp,
+				      struct nl4_server *ns)
+{
+	DECODE_HEAD;
+	struct nfs42_netaddr *naddr;
+
+	READ_BUF(4);
+	ns->nl4_type = be32_to_cpup(p++);
+
+	/* currently support for 1 inter-server source server */
+	switch (ns->nl4_type) {
+	case NL4_NAME:
+	case NL4_URL:
+		READ_BUF(4);
+		ns->u.nl4_str_sz = be32_to_cpup(p++);
+		if (ns->u.nl4_str_sz > NFS4_OPAQUE_LIMIT)
+			goto xdr_error;
+
+		READ_BUF(ns->u.nl4_str_sz);
+		COPYMEM(ns->u.nl4_str,
+			ns->u.nl4_str_sz);
+		break;
+	case NL4_NETADDR:
+		naddr = &ns->u.nl4_addr;
+
+		READ_BUF(4);
+		naddr->netid_len = be32_to_cpup(p++);
+		if (naddr->netid_len > RPCBIND_MAXNETIDLEN)
+			goto xdr_error;
+
+		READ_BUF(naddr->netid_len + 4); /* 4 for uaddr len */
+		COPYMEM(naddr->netid, naddr->netid_len);
+
+		naddr->addr_len = be32_to_cpup(p++);
+		if (naddr->addr_len > RPCBIND_MAXUADDRLEN)
+			goto xdr_error;
+
+		READ_BUF(naddr->addr_len);
+		COPYMEM(naddr->addr, naddr->addr_len);
+		break;
+	default:
+		goto xdr_error;
+	}
+	DECODE_TAIL;
+}
+
 static __be32
 nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)
 {
 	DECODE_HEAD;
-	unsigned int tmp;
+	struct nl4_server *ns_dummy;
+	int i, count;
 
 	status = nfsd4_decode_stateid(argp, &copy->cp_src_stateid);
 	if (status)
@@ -1763,8 +1811,31 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
 	p = xdr_decode_hyper(p, &copy->cp_count);
 	p++; /* ca_consecutive: we always do consecutive copies */
 	copy->cp_synchronous = be32_to_cpup(p++);
-	tmp = be32_to_cpup(p); /* Source server list not supported */
+	count = be32_to_cpup(p++);
 
+	copy->cp_intra = false;
+	if (count == 0) { /* intra-server copy */
+		copy->cp_intra = true;
+		goto intra;
+	}
+
+	/* decode all the supplied server addresses but use first */
+	status = nfsd4_decode_nl4_server(argp, &copy->cp_src);
+	if (status)
+		return status;
+
+	ns_dummy = kmalloc(sizeof(struct nl4_server), GFP_KERNEL);
+	if (ns_dummy == NULL)
+		return nfserrno(-ENOMEM);
+	for (i = 0; i < count - 1; i++) {
+		status = nfsd4_decode_nl4_server(argp, ns_dummy);
+		if (status) {
+			kfree(ns_dummy);
+			return status;
+		}
+	}
+	kfree(ns_dummy);
+intra:
 	DECODE_TAIL;
 }
 
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index feeb6d4..513c9ff 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -516,11 +516,13 @@ struct nfsd42_write_res {
 
 struct nfsd4_copy {
 	/* request */
-	stateid_t	cp_src_stateid;
-	stateid_t	cp_dst_stateid;
-	u64		cp_src_pos;
-	u64		cp_dst_pos;
-	u64		cp_count;
+	stateid_t		cp_src_stateid;
+	stateid_t		cp_dst_stateid;
+	u64			cp_src_pos;
+	u64			cp_dst_pos;
+	u64			cp_count;
+	struct nl4_server	cp_src;
+	bool			cp_intra;
 
 	/* both */
 	bool		cp_synchronous;
-- 
1.8.3.1

[PATCH v3 3/8] NFSD return nfs4_stid in nfs4_preprocess_stateid_op

[Olga Kornievskaia]

Needed for copy to add nfs4_cp_state to the nfs4_stid.

Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfsd/nfs4proc.c  | 17 ++++++++++-------
 fs/nfsd/nfs4state.c |  8 ++++++--
 fs/nfsd/state.h     |  3 ++-
 3 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 8beda99..cfd8767 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -782,7 +782,8 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
 	/* check stateid */
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					&read->rd_stateid, RD_STATE,
-					&read->rd_filp, &read->rd_tmp_file);
+					&read->rd_filp, &read->rd_tmp_file,
+					NULL);
 	if (status) {
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;
@@ -954,7 +955,7 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
 		status = nfs4_preprocess_stateid_op(rqstp, cstate,
 				&cstate->current_fh, &setattr->sa_stateid,
-				WR_STATE, NULL, NULL);
+				WR_STATE, NULL, NULL, NULL);
 		if (status) {
 			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
 			return status;
@@ -1005,7 +1006,7 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
 	trace_nfsd_write_start(rqstp, &cstate->current_fh,
 			       write->wr_offset, cnt);
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
-						stateid, WR_STATE, &filp, NULL);
+					stateid, WR_STATE, &filp, NULL, NULL);
 	if (status) {
 		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
 		return status;
@@ -1040,14 +1041,16 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
 		return nfserr_nofilehandle;
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
-					    src_stateid, RD_STATE, src, NULL);
+					    src_stateid, RD_STATE, src, NULL,
+					    NULL);
 	if (status) {
 		dprintk("NFSD: %s: couldn't process src stateid!\n", __func__);
 		goto out;
 	}
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
-					    dst_stateid, WR_STATE, dst, NULL);
+					    dst_stateid, WR_STATE, dst, NULL,
+					    NULL);
 	if (status) {
 		dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
 		goto out_put_src;
@@ -1351,7 +1354,7 @@ struct nfsd4_copy *
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &fallocate->falloc_stateid,
-					    WR_STATE, &file, NULL);
+					    WR_STATE, &file, NULL, NULL);
 	if (status != nfs_ok) {
 		dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n");
 		return status;
@@ -1410,7 +1413,7 @@ struct nfsd4_copy *
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &seek->seek_stateid,
-					    RD_STATE, &file, NULL);
+					    RD_STATE, &file, NULL, NULL);
 	if (status) {
 		dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
 		return status;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 618e660..05c0295 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5187,7 +5187,8 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 __be32
 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
-		stateid_t *stateid, int flags, struct file **filpp, bool *tmp_file)
+		stateid_t *stateid, int flags, struct file **filpp,
+		bool *tmp_file, struct nfs4_stid **cstid)
 {
 	struct inode *ino = d_inode(fhp->fh_dentry);
 	struct net *net = SVC_NET(rqstp);
@@ -5238,8 +5239,11 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	if (!status && filpp)
 		status = nfs4_check_file(rqstp, fhp, s, filpp, tmp_file, flags);
 out:
-	if (s)
+	if (s) {
+		if (!status && cstid)
+			*cstid = s;
 		nfs4_put_stid(s);
+	}
 	return status;
 }
 
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 0b74d37..5da9cc3 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -607,7 +607,8 @@ struct nfsd4_blocked_lock {
 
 extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
-		stateid_t *stateid, int flags, struct file **filp, bool *tmp_file);
+		stateid_t *stateid, int flags, struct file **filp,
+		bool *tmp_file, struct nfs4_stid **cstid);
 __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn);
-- 
1.8.3.1

[PATCH v3 4/8] NFSD add COPY_NOTIFY operation

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

Introducing the COPY_NOTIFY operation.

Create a new unique stateid that will keep track of the copy
state and the upcoming READs that will use that stateid. Keep
it in the list associated with parent stateid.

Return single netaddr to advertise to the copy.

Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfsd/nfs4proc.c  | 71 +++++++++++++++++++++++++++++++++++----
 fs/nfsd/nfs4state.c | 62 ++++++++++++++++++++++++++++++----
 fs/nfsd/nfs4xdr.c   | 97 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 fs/nfsd/state.h     | 18 ++++++++--
 fs/nfsd/xdr4.h      | 13 +++++++
 5 files changed, 245 insertions(+), 16 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index cfd8767..c39fa72 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -37,6 +37,7 @@
 #include <linux/falloc.h>
 #include <linux/slab.h>
 #include <linux/kthread.h>
+#include <linux/sunrpc/addr.h>
 
 #include "idmap.h"
 #include "cache.h"
@@ -1033,7 +1034,8 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
 static __be32
 nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		  stateid_t *src_stateid, struct file **src,
-		  stateid_t *dst_stateid, struct file **dst)
+		  stateid_t *dst_stateid, struct file **dst,
+		  struct nfs4_stid **stid)
 {
 	__be32 status;
 
@@ -1050,7 +1052,7 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    dst_stateid, WR_STATE, dst, NULL,
-					    NULL);
+					    stid);
 	if (status) {
 		dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
 		goto out_put_src;
@@ -1081,7 +1083,7 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
 	__be32 status;
 
 	status = nfsd4_verify_copy(rqstp, cstate, &clone->cl_src_stateid, &src,
-				   &clone->cl_dst_stateid, &dst);
+				   &clone->cl_dst_stateid, &dst, NULL);
 	if (status)
 		goto out;
 
@@ -1228,7 +1230,7 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
 
 static void cleanup_async_copy(struct nfsd4_copy *copy)
 {
-	nfs4_free_cp_state(copy);
+	nfs4_free_copy_state(copy);
 	fput(copy->file_dst);
 	fput(copy->file_src);
 	spin_lock(&copy->cp_clp->async_lock);
@@ -1268,7 +1270,7 @@ static int nfsd4_do_async_copy(void *data)
 
 	status = nfsd4_verify_copy(rqstp, cstate, &copy->cp_src_stateid,
 				   &copy->file_src, &copy->cp_dst_stateid,
-				   &copy->file_dst);
+				   &copy->file_dst, NULL);
 	if (status)
 		goto out;
 
@@ -1282,7 +1284,7 @@ static int nfsd4_do_async_copy(void *data)
 		async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
 		if (!async_copy)
 			goto out;
-		if (!nfs4_init_cp_state(nn, copy)) {
+		if (!nfs4_init_copy_state(nn, copy)) {
 			kfree(async_copy);
 			goto out;
 		}
@@ -1346,6 +1348,42 @@ struct nfsd4_copy *
 }
 
 static __be32
+nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		  union nfsd4_op_u *u)
+{
+	struct nfsd4_copy_notify *cn = &u->copy_notify;
+	__be32 status;
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+	struct nfs4_stid *stid;
+	struct nfs4_cpntf_state *cps;
+
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+					&cn->cpn_src_stateid, RD_STATE, NULL,
+					NULL, &stid);
+	if (status)
+		return status;
+
+	cn->cpn_sec = nn->nfsd4_lease;
+	cn->cpn_nsec = 0;
+
+	status = nfserrno(-ENOMEM);
+	cps = nfs4_alloc_init_cpntf_state(nn, stid);
+	if (!cps)
+		return status;
+	memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid, sizeof(stateid_t));
+
+	/* For now, only return one server address in cpn_src, the
+	 * address used by the client to connect to this server.
+	 */
+	cn->cpn_src.nl4_type = NL4_NETADDR;
+	status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr,
+				 &cn->cpn_src.u.nl4_addr);
+	WARN_ON_ONCE(status);
+
+	return status;
+}
+
+static __be32
 nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		struct nfsd4_fallocate *fallocate, int flags)
 {
@@ -2298,6 +2336,21 @@ static inline u32 nfsd4_offload_status_rsize(struct svc_rqst *rqstp,
 		1 /* osr_complete<1> optional 0 for now */) * sizeof(__be32);
 }
 
+static inline u32 nfsd4_copy_notify_rsize(struct svc_rqst *rqstp,
+					struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		3 /* cnr_lease_time */ +
+		1 /* We support one cnr_source_server */ +
+		1 /* cnr_stateid seq */ +
+		op_encode_stateid_maxsz /* cnr_stateid */ +
+		1 /* num cnr_source_server*/ +
+		1 /* nl4_type */ +
+		1 /* nl4 size */ +
+		XDR_QUADLEN(NFS4_OPAQUE_LIMIT) /*nl4_loc + nl4_loc_sz */)
+		* sizeof(__be32);
+}
+
 #ifdef CONFIG_NFSD_PNFS
 static inline u32 nfsd4_getdeviceinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
@@ -2722,6 +2775,12 @@ static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 		.op_name = "OP_OFFLOAD_CANCEL",
 		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
+	[OP_COPY_NOTIFY] = {
+		.op_func = nfsd4_copy_notify,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_COPY_NOTIFY",
+		.op_rsize_bop = nfsd4_copy_notify_rsize,
+	},
 };
 
 /**
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 05c0295..07128ef 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -707,6 +707,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla
 	/* Will be incremented before return to client: */
 	refcount_set(&stid->sc_count, 1);
 	spin_lock_init(&stid->sc_lock);
+	INIT_LIST_HEAD(&stid->sc_cp_list);
 
 	/*
 	 * It shouldn't be a problem to reuse an opaque stateid value.
@@ -726,24 +727,53 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla
 /*
  * Create a unique stateid_t to represent each COPY.
  */
-int nfs4_init_cp_state(struct nfsd_net *nn, struct nfsd4_copy *copy)
+static int nfs4_init_cp_state(struct nfsd_net *nn, void *ptr, stateid_t *stid)
 {
 	int new_id;
 
 	idr_preload(GFP_KERNEL);
 	spin_lock(&nn->s2s_cp_lock);
-	new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, copy, 0, 0, GFP_NOWAIT);
+	new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, ptr, 0, 0, GFP_NOWAIT);
 	spin_unlock(&nn->s2s_cp_lock);
 	idr_preload_end();
 	if (new_id < 0)
 		return 0;
-	copy->cp_stateid.si_opaque.so_id = new_id;
-	copy->cp_stateid.si_opaque.so_clid.cl_boot = nn->boot_time;
-	copy->cp_stateid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
+	stid->si_opaque.so_id = new_id;
+	stid->si_opaque.so_clid.cl_boot = nn->boot_time;
+	stid->si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
 	return 1;
 }
 
-void nfs4_free_cp_state(struct nfsd4_copy *copy)
+int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy)
+{
+	return nfs4_init_cp_state(nn, copy, &copy->cp_stateid);
+}
+
+struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
+						     struct nfs4_stid *p_stid)
+{
+	struct nfs4_cpntf_state *cps;
+
+	cps = kzalloc(sizeof(struct nfs4_cpntf_state), GFP_KERNEL);
+	if (!cps)
+		return NULL;
+	if (!nfs4_init_cp_state(nn, cps, &cps->cp_stateid))
+		goto out_free;
+	cps->cp_p_stid = p_stid;
+	cps->cp_active = false;
+	cps->cp_timeout = jiffies + (nn->nfsd4_lease * HZ);
+	INIT_LIST_HEAD(&cps->cp_list);
+	spin_lock(&nn->s2s_cp_lock);
+	list_add(&cps->cp_list, &p_stid->sc_cp_list);
+	spin_unlock(&nn->s2s_cp_lock);
+
+	return cps;
+out_free:
+	kfree(cps);
+	return NULL;
+}
+
+void nfs4_free_copy_state(struct nfsd4_copy *copy)
 {
 	struct nfsd_net *nn;
 
@@ -753,6 +783,25 @@ void nfs4_free_cp_state(struct nfsd4_copy *copy)
 	spin_unlock(&nn->s2s_cp_lock);
 }
 
+static void nfs4_free_cpntf_statelist(struct net *net, struct nfs4_stid *stid)
+{
+	struct nfs4_cpntf_state *cps;
+	struct nfsd_net *nn;
+
+	nn = net_generic(net, nfsd_net_id);
+
+	spin_lock(&nn->s2s_cp_lock);
+	while (!list_empty(&stid->sc_cp_list)) {
+		cps = list_first_entry(&stid->sc_cp_list,
+				       struct nfs4_cpntf_state, cp_list);
+		list_del(&cps->cp_list);
+		idr_remove(&nn->s2s_cp_stateids,
+			   cps->cp_stateid.si_opaque.so_id);
+		kfree(cps);
+	}
+	spin_unlock(&nn->s2s_cp_lock);
+}
+
 static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp)
 {
 	struct nfs4_stid *stid;
@@ -901,6 +950,7 @@ static void block_delegations(struct knfsd_fh *fh)
 	}
 	idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
 	spin_unlock(&clp->cl_lock);
+	nfs4_free_cpntf_statelist(clp->net, s);
 	s->sc_free(s);
 	if (fp)
 		put_nfs4_file(fp);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 15f53bb..ed37528 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1847,6 +1847,22 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp,
 }
 
 static __be32
+nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp,
+			 struct nfsd4_copy_notify *cn)
+{
+	int status;
+
+	status = nfsd4_decode_stateid(argp, &cn->cpn_src_stateid);
+	if (status)
+		return status;
+	status = nfsd4_decode_nl4_server(argp, &cn->cpn_dst);
+	if (status)
+		return status;
+
+	return status;
+}
+
+static __be32
 nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
 {
 	DECODE_HEAD;
@@ -1947,7 +1963,7 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp,
 	/* new operations for NFSv4.2 */
 	[OP_ALLOCATE]		= (nfsd4_dec)nfsd4_decode_fallocate,
 	[OP_COPY]		= (nfsd4_dec)nfsd4_decode_copy,
-	[OP_COPY_NOTIFY]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_COPY_NOTIFY]	= (nfsd4_dec)nfsd4_decode_copy_notify,
 	[OP_DEALLOCATE]		= (nfsd4_dec)nfsd4_decode_fallocate,
 	[OP_IO_ADVISE]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTERROR]	= (nfsd4_dec)nfsd4_decode_notsupp,
@@ -4336,6 +4352,45 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 }
 
 static __be32
+nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	struct nfs42_netaddr *addr;
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, 4);
+	*p++ = cpu_to_be32(ns->nl4_type);
+
+	switch (ns->nl4_type) {
+	case NL4_NETADDR:
+		addr = &ns->u.nl4_addr;
+
+		/* netid_len, netid, uaddr_len, uaddr (port included
+		 * in RPCBIND_MAXUADDRLEN)
+		 */
+		p = xdr_reserve_space(xdr,
+			4 /* netid len */ +
+			(XDR_QUADLEN(addr->netid_len) * 4) +
+			4 /* uaddr len */ +
+			(XDR_QUADLEN(addr->addr_len) * 4));
+		if (!p)
+			return nfserr_resource;
+
+		*p++ = cpu_to_be32(addr->netid_len);
+		p = xdr_encode_opaque_fixed(p, addr->netid,
+					    addr->netid_len);
+		*p++ = cpu_to_be32(addr->addr_len);
+		p = xdr_encode_opaque_fixed(p, addr->addr,
+					addr->addr_len);
+		break;
+	default:
+		WARN_ON(ns->nl4_type != NL4_NETADDR);
+	}
+
+	return 0;
+}
+
+static __be32
 nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_copy *copy)
 {
@@ -4369,6 +4424,44 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 }
 
 static __be32
+nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr,
+			 struct nfsd4_copy_notify *cn)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	/* 8 sec, 4 nsec */
+	p = xdr_reserve_space(xdr, 12);
+	if (!p)
+		return nfserr_resource;
+
+	/* cnr_lease_time */
+	p = xdr_encode_hyper(p, cn->cpn_sec);
+	*p++ = cpu_to_be32(cn->cpn_nsec);
+
+	/* cnr_stateid */
+	nfserr = nfsd4_encode_stateid(xdr, &cn->cpn_cnr_stateid);
+	if (nfserr)
+		return nfserr;
+
+	/* cnr_src.nl_nsvr */
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+
+	*p++ = cpu_to_be32(1);
+
+	nfserr = nfsd42_encode_nl4_server(resp, &cn->cpn_src);
+	if (nfserr)
+		return nfserr;
+
+	return nfserr;
+}
+
+static __be32
 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_seek *seek)
 {
@@ -4465,7 +4558,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 	/* NFSv4.2 operations */
 	[OP_ALLOCATE]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_COPY]		= (nfsd4_enc)nfsd4_encode_copy,
-	[OP_COPY_NOTIFY]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_COPY_NOTIFY]	= (nfsd4_enc)nfsd4_encode_copy_notify,
 	[OP_DEALLOCATE]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_IO_ADVISE]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTERROR]	= (nfsd4_enc)nfsd4_encode_noop,
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 5da9cc3..106ed56 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -95,6 +95,7 @@ struct nfs4_stid {
 #define NFS4_REVOKED_DELEG_STID 16
 #define NFS4_CLOSED_DELEG_STID 32
 #define NFS4_LAYOUT_STID 64
+	struct list_head	sc_cp_list;
 	unsigned char		sc_type;
 	stateid_t		sc_stateid;
 	spinlock_t		sc_lock;
@@ -103,6 +104,17 @@ struct nfs4_stid {
 	void			(*sc_free)(struct nfs4_stid *);
 };
 
+/* Keep a list of stateids issued by the COPY_NOTIFY, associate it with the
+ * parent OPEN/LOCK/DELEG stateid.
+ */
+struct nfs4_cpntf_state {
+	stateid_t		cp_stateid;
+	struct list_head	cp_list;	/* per parent nfs4_stid */
+	struct nfs4_stid	*cp_p_stid;	/* pointer to parent */
+	bool			cp_active;	/* has the copy started */
+	unsigned long		cp_timeout;	/* copy timeout */
+};
+
 /*
  * Represents a delegation stateid. The nfs4_client holds references to these
  * and they are put when it is being destroyed or when the delegation is
@@ -614,8 +626,10 @@ __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     struct nfs4_stid **s, struct nfsd_net *nn);
 struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
 				  void (*sc_free)(struct nfs4_stid *));
-int nfs4_init_cp_state(struct nfsd_net *nn, struct nfsd4_copy *copy);
-void nfs4_free_cp_state(struct nfsd4_copy *copy);
+int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy);
+void nfs4_free_copy_state(struct nfsd4_copy *copy);
+struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
+			struct nfs4_stid *p_stid);
 void nfs4_unhash_stid(struct nfs4_stid *s);
 void nfs4_put_stid(struct nfs4_stid *s);
 void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 513c9ff..bade8e5 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -568,6 +568,18 @@ struct nfsd4_offload_status {
 	u32		status;
 };
 
+struct nfsd4_copy_notify {
+	/* request */
+	stateid_t		cpn_src_stateid;
+	struct nl4_server	cpn_dst;
+
+	/* response */
+	stateid_t		cpn_cnr_stateid;
+	u64			cpn_sec;
+	u32			cpn_nsec;
+	struct nl4_server	cpn_src;
+};
+
 struct nfsd4_op {
 	int					opnum;
 	const struct nfsd4_operation *		opdesc;
@@ -627,6 +639,7 @@ struct nfsd4_op {
 		struct nfsd4_clone		clone;
 		struct nfsd4_copy		copy;
 		struct nfsd4_offload_status	offload_status;
+		struct nfsd4_copy_notify	copy_notify;
 		struct nfsd4_seek		seek;
 	} u;
 	struct nfs4_replay *			replay;
-- 
1.8.3.1

[PATCH v3 5/8] NFSD check stateids against copy stateids

[Olga Kornievskaia]

Incoming stateid (used by a READ) could be a saved copy stateid.
On first use make it active and check that the copy has started
within the allowable lease time.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfsd/nfs4state.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 07128ef..d151257 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5230,6 +5230,49 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 
 	return 0;
 }
+/*
+ * A READ from an inter server to server COPY will have a
+ * copy stateid. Return the parent nfs4_stid.
+ */
+static __be32 _find_cpntf_state(struct nfsd_net *nn, stateid_t *st,
+		     struct nfs4_cpntf_state **cps)
+{
+	struct nfs4_cpntf_state *state = NULL;
+
+	if (st->si_opaque.so_clid.cl_id != nn->s2s_cp_cl_id)
+		return nfserr_bad_stateid;
+	spin_lock(&nn->s2s_cp_lock);
+	state = idr_find(&nn->s2s_cp_stateids, st->si_opaque.so_id);
+	if (state)
+		refcount_inc(&state->cp_p_stid->sc_count);
+	spin_unlock(&nn->s2s_cp_lock);
+	if (!state)
+		return nfserr_bad_stateid;
+	*cps = state;
+	return 0;
+}
+
+static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st,
+			       struct nfs4_stid **stid)
+{
+	__be32 status;
+	struct nfs4_cpntf_state *cps = NULL;
+
+	status = _find_cpntf_state(nn, st, &cps);
+	if (status)
+		return status;
+
+	/* Did the inter server to server copy start in time? */
+	if (cps->cp_active == false && !time_after(cps->cp_timeout, jiffies)) {
+		nfs4_put_stid(cps->cp_p_stid);
+		return nfserr_partner_no_auth;
+	} else
+		cps->cp_active = true;
+
+	*stid = cps->cp_p_stid;
+
+	return nfs_ok;
+}
 
 /*
  * Checks for stateid operations
@@ -5262,6 +5305,8 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	status = nfsd4_lookup_stateid(cstate, stateid,
 				NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
 				&s, nn);
+	if (status == nfserr_bad_stateid)
+		status = find_cpntf_state(nn, stateid, &s);
 	if (status)
 		return status;
 	status = nfsd4_stid_check_stateid_generation(stateid, s,
-- 
1.8.3.1

[PATCH v3 6/8] NFSD generalize nfsd4_compound_state flag names

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

Allow for sid_flag field non-stateid use.

Signed-off-by: Andy Adamson <andros@netapp.com>
---
 fs/nfsd/nfs4proc.c  | 8 ++++----
 fs/nfsd/nfs4state.c | 7 ++++---
 fs/nfsd/xdr4.h      | 6 +++---
 3 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index c39fa72..8c2273e 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -531,9 +531,9 @@ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_stat
 		return nfserr_restorefh;
 
 	fh_dup2(&cstate->current_fh, &cstate->save_fh);
-	if (HAS_STATE_ID(cstate, SAVED_STATE_ID_FLAG)) {
+	if (HAS_CSTATE_FLAG(cstate, SAVED_STATE_ID_FLAG)) {
 		memcpy(&cstate->current_stateid, &cstate->save_stateid, sizeof(stateid_t));
-		SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+		SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG);
 	}
 	return nfs_ok;
 }
@@ -543,9 +543,9 @@ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_stat
 	     union nfsd4_op_u *u)
 {
 	fh_dup2(&cstate->save_fh, &cstate->current_fh);
-	if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG)) {
+	if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG)) {
 		memcpy(&cstate->save_stateid, &cstate->current_stateid, sizeof(stateid_t));
-		SET_STATE_ID(cstate, SAVED_STATE_ID_FLAG);
+		SET_CSTATE_FLAG(cstate, SAVED_STATE_ID_FLAG);
 	}
 	return nfs_ok;
 }
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d151257..8263f08 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -7464,7 +7464,8 @@ static int nfs4_state_create_net(struct net *net)
 static void
 get_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid)
 {
-	if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG) && CURRENT_STATEID(stateid))
+	if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG) &&
+	    CURRENT_STATEID(stateid))
 		memcpy(stateid, &cstate->current_stateid, sizeof(stateid_t));
 }
 
@@ -7473,14 +7474,14 @@ static int nfs4_state_create_net(struct net *net)
 {
 	if (cstate->minorversion) {
 		memcpy(&cstate->current_stateid, stateid, sizeof(stateid_t));
-		SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+		SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG);
 	}
 }
 
 void
 clear_current_stateid(struct nfsd4_compound_state *cstate)
 {
-	CLEAR_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+	CLEAR_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG);
 }
 
 /*
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index bade8e5..9d7318c 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -46,9 +46,9 @@
 #define CURRENT_STATE_ID_FLAG (1<<0)
 #define SAVED_STATE_ID_FLAG (1<<1)
 
-#define SET_STATE_ID(c, f) ((c)->sid_flags |= (f))
-#define HAS_STATE_ID(c, f) ((c)->sid_flags & (f))
-#define CLEAR_STATE_ID(c, f) ((c)->sid_flags &= ~(f))
+#define SET_CSTATE_FLAG(c, f) ((c)->sid_flags |= (f))
+#define HAS_CSTATE_FLAG(c, f) ((c)->sid_flags & (f))
+#define CLEAR_CSTATE_FLAG(c, f) ((c)->sid_flags &= ~(f))
 
 struct nfsd4_compound_state {
 	struct svc_fh		current_fh;
-- 
1.8.3.1

[PATCH v3 7/8] NFSD: allow inter server COPY to have a STALE source server fh

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

The inter server to server COPY source server filehandle
is a foreign filehandle as the COPY is sent to the destination
server.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfsd/Kconfig    | 10 ++++++++++
 fs/nfsd/nfs4proc.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++----
 fs/nfsd/nfsfh.h    |  5 ++++-
 fs/nfsd/xdr4.h     |  1 +
 4 files changed, 64 insertions(+), 5 deletions(-)

diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index d25f6bb..bef3a58 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -132,6 +132,16 @@ config NFSD_FLEXFILELAYOUT
 
 	  If unsure, say N.
 
+config NFSD_V4_2_INTER_SSC
+	bool "NFSv4.2 inter server to server COPY"
+	depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2
+	help
+	  This option enables support for NFSv4.2 inter server to
+	  server copy where the destination server calls the NFSv4.2
+	  client to read the data to copy from the source 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/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 8c2273e..1039528 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -504,12 +504,20 @@ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_stat
 	    union nfsd4_op_u *u)
 {
 	struct nfsd4_putfh *putfh = &u->putfh;
+	__be32 ret;
 
 	fh_put(&cstate->current_fh);
 	cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
 	memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
 	       putfh->pf_fhlen);
-	return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS);
+	ret = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS);
+#ifdef CONFIG_NFSD_V4_2_INTER_SSC
+	if (ret == nfserr_stale && putfh->no_verify) {
+		SET_FH_FLAG(&cstate->current_fh, NFSD4_FH_FOREIGN);
+		ret = 0;
+	}
+#endif
+	return ret;
 }
 
 static __be32
@@ -1956,6 +1964,41 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp,
 		- rqstp->rq_auth_slack;
 }
 
+#ifdef CONFIG_NFSD_V4_2_INTER_SSC
+static void
+check_if_stalefh_allowed(struct nfsd4_compoundargs *args)
+{
+	struct nfsd4_op	*op, *current_op, *saved_op;
+	struct nfsd4_copy *copy;
+	struct nfsd4_putfh *putfh;
+	int i;
+
+	/* traverse all operation and if it's a COPY compound, mark the
+	 * source filehandle to skip verification
+	 */
+	for (i = 0; i < args->opcnt; i++) {
+		op = &args->ops[i];
+		if (op->opnum == OP_PUTFH)
+			current_op = op;
+		else if (op->opnum == OP_SAVEFH)
+			saved_op = current_op;
+		else if (op->opnum == OP_RESTOREFH)
+			current_op = saved_op;
+		else if (op->opnum == OP_COPY) {
+			copy = (struct nfsd4_copy *)&op->u;
+			putfh = (struct nfsd4_putfh *)&saved_op->u;
+			if (!copy->cp_intra)
+				putfh->no_verify = true;
+		}
+	}
+}
+#else
+static void
+check_if_stalefh_allowed(struct nfsd4_compoundargs *args)
+{
+}
+#endif
+
 /*
  * COMPOUND call.
  */
@@ -2004,6 +2047,7 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp,
 		resp->opcnt = 1;
 		goto encode_op;
 	}
+	check_if_stalefh_allowed(args);
 
 	trace_nfsd_compound(rqstp, args->opcnt);
 	while (!status && resp->opcnt < args->opcnt) {
@@ -2019,13 +2063,14 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp,
 				op->status = nfsd4_open_omfg(rqstp, cstate, op);
 			goto encode_op;
 		}
-
-		if (!current_fh->fh_dentry) {
+		if (!current_fh->fh_dentry &&
+				!HAS_FH_FLAG(current_fh, NFSD4_FH_FOREIGN)) {
 			if (!(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) {
 				op->status = nfserr_nofilehandle;
 				goto encode_op;
 			}
-		} else if (current_fh->fh_export->ex_fslocs.migrated &&
+		} else if (current_fh->fh_export &&
+			   current_fh->fh_export->ex_fslocs.migrated &&
 			  !(op->opdesc->op_flags & ALLOWED_ON_ABSENT_FS)) {
 			op->status = nfserr_moved;
 			goto encode_op;
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 755e256..b9c7568 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -35,7 +35,7 @@ static inline ino_t u32_to_ino_t(__u32 uino)
 
 	bool			fh_locked;	/* inode locked by us */
 	bool			fh_want_write;	/* remount protection taken */
-
+	int			fh_flags;	/* FH flags */
 #ifdef CONFIG_NFSD_V3
 	bool			fh_post_saved;	/* post-op attrs saved */
 	bool			fh_pre_saved;	/* pre-op attrs saved */
@@ -56,6 +56,9 @@ static inline ino_t u32_to_ino_t(__u32 uino)
 #endif /* CONFIG_NFSD_V3 */
 
 } svc_fh;
+#define NFSD4_FH_FOREIGN (1<<0)
+#define SET_FH_FLAG(c, f) ((c)->fh_flags |= (f))
+#define HAS_FH_FLAG(c, f) ((c)->fh_flags & (f))
 
 enum nfsd_fsid {
 	FSID_DEV = 0,
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 9d7318c..fbd18d6 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -221,6 +221,7 @@ struct nfsd4_lookup {
 struct nfsd4_putfh {
 	u32		pf_fhlen;           /* request */
 	char		*pf_fhval;          /* request */
+	bool		no_verify;	    /* represents foreigh fh */
 };
 
 struct nfsd4_open {
-- 
1.8.3.1

[PATCH v3 8/8] NFSD add nfs4 inter ssc to nfsd4_copy

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

Given a universal address, mount the source server from the destination
server.  Use an internal mount. Call the NFS client nfs42_ssc_open to
obtain the NFS struct file suitable for nfsd_copy_file_range.

Ability to do "inter" server-to-server depends on the an nfsd kernel
parameter "inter_copy_offload_enabled".

On server reboot nfsd_copy_file_range(), will return EBADF which we
choose to translate to NFS4ERR_PARTNER_NO_AUTH when 0 bytes were also
read before the reboot. It signals the client to restart the copy and
not EOF of the file.

Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfsd/nfs4proc.c   | 277 +++++++++++++++++++++++++++++++++++++++++++++++----
 fs/nfsd/nfssvc.c     |   6 ++
 fs/nfsd/xdr4.h       |   5 +
 include/linux/nfs4.h |   1 +
 4 files changed, 271 insertions(+), 18 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 1039528..e1ea257 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1153,6 +1153,209 @@ void nfsd4_shutdown_copy(struct nfs4_client *clp)
 	while ((copy = nfsd4_get_copy(clp)) != NULL)
 		nfsd4_stop_copy(copy);
 }
+#ifdef CONFIG_NFSD_V4_2_INTER_SSC
+
+extern struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
+				   struct nfs_fh *src_fh,
+				   nfs4_stateid *stateid);
+extern void nfs42_ssc_close(struct file *filep);
+
+extern void nfs_sb_deactive(struct super_block *sb);
+
+#define NFSD42_INTERSSC_MOUNTOPS "minorversion=2,vers=4,addr=%s"
+
+/**
+ * Support one copy source server for now.
+ */
+static __be32
+nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp,
+		       struct vfsmount **mount)
+{
+	struct file_system_type *type;
+	struct vfsmount *ss_mnt;
+	struct nfs42_netaddr *naddr;
+	struct sockaddr_storage tmp_addr;
+	size_t tmp_addrlen, match_netid_len = 3;
+	char *startsep = "", *endsep = "", *match_netid = "tcp";
+	char *ipaddr, *dev_name, *raw_data;
+	int len, raw_len, status = -EINVAL;
+
+	naddr = &nss->u.nl4_addr;
+	tmp_addrlen = rpc_uaddr2sockaddr(SVC_NET(rqstp), naddr->addr,
+					 naddr->addr_len,
+					 (struct sockaddr *)&tmp_addr,
+					 sizeof(tmp_addr));
+	if (tmp_addrlen == 0)
+		goto out_err;
+
+	if (tmp_addr.ss_family == AF_INET6) {
+		startsep = "[";
+		endsep = "]";
+		match_netid = "tcp6";
+		match_netid_len = 4;
+	}
+
+	if (naddr->netid_len != match_netid_len ||
+		strncmp(naddr->netid, match_netid, naddr->netid_len))
+		goto out_err;
+
+	/* Construct the raw data for the vfs_kern_mount call */
+	len = RPC_MAX_ADDRBUFLEN + 1;
+	ipaddr = kzalloc(len, GFP_KERNEL);
+	if (!ipaddr)
+		goto out_err;
+
+	rpc_ntop((struct sockaddr *)&tmp_addr, ipaddr, len);
+
+	/* 2 for ipv6 endsep and startsep. 3 for ":/" and trailing '/0'*/
+
+	raw_len = strlen(NFSD42_INTERSSC_MOUNTOPS) + strlen(ipaddr);
+	raw_data = kzalloc(raw_len, GFP_KERNEL);
+	if (!raw_data)
+		goto out_free_ipaddr;
+
+	snprintf(raw_data, raw_len, NFSD42_INTERSSC_MOUNTOPS, ipaddr);
+
+	status = -ENODEV;
+	type = get_fs_type("nfs");
+	if (!type)
+		goto out_free_rawdata;
+
+	/* Set the server:<export> for the vfs_kern_mount call */
+	dev_name = kzalloc(len + 5, GFP_KERNEL);
+	if (!dev_name)
+		goto out_free_rawdata;
+	snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep);
+
+	/* Use an 'internal' mount: SB_KERNMOUNT -> MNT_INTERNAL */
+	ss_mnt = vfs_kern_mount(type, SB_KERNMOUNT, dev_name, raw_data);
+	module_put(type->owner);
+	if (IS_ERR(ss_mnt))
+		goto out_free_devname;
+
+	status = 0;
+	*mount = ss_mnt;
+
+out_free_devname:
+	kfree(dev_name);
+out_free_rawdata:
+	kfree(raw_data);
+out_free_ipaddr:
+	kfree(ipaddr);
+out_err:
+	return status;
+}
+
+static void
+nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
+{
+	nfs_sb_deactive(ss_mnt->mnt_sb);
+	mntput(ss_mnt);
+}
+
+/**
+ * nfsd4_setup_inter_ssc
+ *
+ * Verify COPY destination stateid.
+ * Connect to the source server with NFSv4.1.
+ * Create the source struct file for nfsd_copy_range.
+ * Called with COPY cstate:
+ *    SAVED_FH: source filehandle
+ *    CURRENT_FH: destination filehandle
+ *
+ * Returns errno (not nfserrxxx)
+ */
+static __be32
+nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
+		      struct nfsd4_compound_state *cstate,
+		      struct nfsd4_copy *copy, struct vfsmount **mount)
+{
+	struct svc_fh *s_fh = NULL;
+	stateid_t *s_stid = &copy->cp_src_stateid;
+	__be32 status = -EINVAL;
+
+	/* Verify the destination stateid and set dst struct file*/
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+					    &copy->cp_dst_stateid,
+					    WR_STATE, &copy->file_dst, NULL,
+					    NULL);
+	if (status)
+		goto out;
+
+	status = nfsd4_interssc_connect(&copy->cp_src, rqstp, mount);
+	if (status)
+		goto out;
+
+	s_fh = &cstate->save_fh;
+
+	copy->c_fh.size = s_fh->fh_handle.fh_size;
+	memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_base, copy->c_fh.size);
+	copy->stateid.seqid = s_stid->si_generation;
+	memcpy(copy->stateid.other, (void *)&s_stid->si_opaque,
+	       sizeof(stateid_opaque_t));
+
+	status = 0;
+out:
+	return status;
+}
+
+static void
+nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *src,
+			struct file *dst)
+{
+	nfs42_ssc_close(src);
+	fput(src);
+	fput(dst);
+	mntput(ss_mnt);
+}
+
+#else /* CONFIG_NFSD_V4_2_INTER_SSC */
+
+static __be32
+nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
+		      struct nfsd4_compound_state *cstate,
+		      struct nfsd4_copy *copy,
+		      struct vfsmount **mount)
+{
+	*mount = NULL;
+	return -EINVAL;
+}
+
+static void
+nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *src,
+			struct file *dst)
+{
+}
+
+static void
+nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
+{
+}
+
+static struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
+				   struct nfs_fh *src_fh,
+				   nfs4_stateid *stateid)
+{
+	return NULL;
+}
+#endif /* CONFIG_NFSD_V4_2_INTER_SSC */
+
+static __be32
+nfsd4_setup_intra_ssc(struct svc_rqst *rqstp,
+		      struct nfsd4_compound_state *cstate,
+		      struct nfsd4_copy *copy)
+{
+	return nfsd4_verify_copy(rqstp, cstate, &copy->cp_src_stateid,
+				 &copy->file_src, &copy->cp_dst_stateid,
+				 &copy->file_dst, NULL);
+}
+
+static void
+nfsd4_cleanup_intra_ssc(struct file *src, struct file *dst)
+{
+	fput(src);
+	fput(dst);
+}
 
 static void nfsd4_cb_offload_release(struct nfsd4_callback *cb)
 {
@@ -1210,15 +1413,25 @@ static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync)
 	/* for async copy, we ignore the error, client can always retry
 	 * to get the error
 	 */
-	if (bytes < 0 && !copy->cp_res.wr_bytes_written)
-		status = nfserrno(bytes);
-	else {
+	if (bytes < 0 && !copy->cp_res.wr_bytes_written) {
+		if (!copy->cp_intra && bytes == -EBADF)
+			/* if source server rebooted, copy_file_range fails
+			 * with EBADF, translate that to NFS4ERR_PARTNER_NO_AUTH
+			 */
+			status = nfserr_partner_no_auth;
+		else
+			status = nfserrno(bytes);
+	} else {
 		nfsd4_init_copy_res(copy, sync);
 		status = nfs_ok;
 	}
 
-	fput(copy->file_src);
-	fput(copy->file_dst);
+	if (!copy->cp_intra) /* Inter server SSC */
+		nfsd4_cleanup_inter_ssc(copy->ss_mnt, copy->file_src,
+					copy->file_dst);
+	else
+		nfsd4_cleanup_intra_ssc(copy->file_src, copy->file_dst);
+
 	return status;
 }
 
@@ -1232,8 +1445,14 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
 	memcpy(&dst->fh, &src->fh, sizeof(src->fh));
 	dst->cp_clp = src->cp_clp;
 	dst->file_dst = get_file(src->file_dst);
-	dst->file_src = get_file(src->file_src);
+	dst->cp_intra = src->cp_intra;
+	if (src->cp_intra) /* for inter, file_src doesn't exist yet */
+		dst->file_src = get_file(src->file_src);
 	memcpy(&dst->cp_stateid, &src->cp_stateid, sizeof(src->cp_stateid));
+	memcpy(&dst->cp_src, &src->cp_src, sizeof(struct nl4_server));
+	memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid));
+	memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh));
+	dst->ss_mnt = src->ss_mnt;
 }
 
 static void cleanup_async_copy(struct nfsd4_copy *copy)
@@ -1252,7 +1471,18 @@ static int nfsd4_do_async_copy(void *data)
 	struct nfsd4_copy *copy = (struct nfsd4_copy *)data;
 	struct nfsd4_copy *cb_copy;
 
+	if (!copy->cp_intra) { /* Inter server SSC */
+		copy->file_src = nfs42_ssc_open(copy->ss_mnt, &copy->c_fh,
+					      &copy->stateid);
+		if (IS_ERR(copy->file_src)) {
+			copy->nfserr = nfserr_offload_denied;
+			nfsd4_interssc_disconnect(copy->ss_mnt);
+			goto do_callback;
+		}
+	}
+
 	copy->nfserr = nfsd4_do_copy(copy, 0);
+do_callback:
 	cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
 	if (!cb_copy)
 		goto out;
@@ -1276,11 +1506,20 @@ static int nfsd4_do_async_copy(void *data)
 	__be32 status;
 	struct nfsd4_copy *async_copy = NULL;
 
-	status = nfsd4_verify_copy(rqstp, cstate, &copy->cp_src_stateid,
-				   &copy->file_src, &copy->cp_dst_stateid,
-				   &copy->file_dst, NULL);
-	if (status)
-		goto out;
+	if (!copy->cp_intra) { /* Inter server SSC */
+		if (!inter_copy_offload_enable || copy->cp_synchronous) {
+			status = nfserr_notsupp;
+			goto out;
+		}
+		status = nfsd4_setup_inter_ssc(rqstp, cstate, copy,
+					&copy->ss_mnt);
+		if (status)
+			return nfserr_offload_denied;
+	} else {
+		status = nfsd4_setup_intra_ssc(rqstp, cstate, copy);
+		if (status)
+			return status;
+	}
 
 	copy->cp_clp = cstate->clp;
 	memcpy(&copy->fh, &cstate->current_fh.fh_handle,
@@ -1291,11 +1530,9 @@ static int nfsd4_do_async_copy(void *data)
 		status = nfserrno(-ENOMEM);
 		async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
 		if (!async_copy)
-			goto out;
-		if (!nfs4_init_copy_state(nn, copy)) {
-			kfree(async_copy);
-			goto out;
-		}
+			goto out_err;
+		if (!nfs4_init_copy_state(nn, copy))
+			goto out_err;
 		refcount_set(&async_copy->refcount, 1);
 		memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid,
 			sizeof(copy->cp_stateid));
@@ -1310,13 +1547,17 @@ static int nfsd4_do_async_copy(void *data)
 		spin_unlock(&async_copy->cp_clp->async_lock);
 		wake_up_process(async_copy->copy_task);
 		status = nfs_ok;
-	} else
+	} else {
 		status = nfsd4_do_copy(copy, 1);
+	}
 out:
 	return status;
 out_err:
 	cleanup_async_copy(async_copy);
-	goto out;
+	status = nfserrno(-ENOMEM);
+	if (!copy->cp_intra)
+		nfsd4_interssc_disconnect(copy->ss_mnt);
+	goto out_err;
 }
 
 struct nfsd4_copy *
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 18d94ea..033bfcb 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -30,6 +30,12 @@
 
 #define NFSDDBG_FACILITY	NFSDDBG_SVC
 
+bool inter_copy_offload_enable;
+EXPORT_SYMBOL_GPL(inter_copy_offload_enable);
+module_param(inter_copy_offload_enable, bool, 0644);
+MODULE_PARM_DESC(inter_copy_offload_enable,
+		 "Enable inter server to server copy offload. Default: false");
+
 extern struct svc_program	nfsd_program;
 static int			nfsd(void *vrqstp);
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index fbd18d6..bb2f8e5 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -547,7 +547,12 @@ struct nfsd4_copy {
 	struct task_struct	*copy_task;
 	refcount_t		refcount;
 	bool			stopped;
+
+	struct vfsmount		*ss_mnt;
+	struct nfs_fh		c_fh;
+	nfs4_stateid		stateid;
 };
+extern bool inter_copy_offload_enable;
 
 struct nfsd4_seek {
 	/* request */
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index ec4420e..3cc2632 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -17,6 +17,7 @@
 #include <linux/uidgid.h>
 #include <uapi/linux/nfs4.h>
 #include <linux/sunrpc/msg_prot.h>
+#include <linux/nfs.h>
 
 enum nfs4_acl_whotype {
 	NFS4_ACL_WHO_NAMED = 0,
-- 
1.8.3.1