[PATCH v8 00/20] client and server support for "inter" SSC copy

[PATCH v8 00/20] client and server support for "inter" SSC copy

[Olga Kornievskaia]

-- forgot to cc linux-nfs

--client patches
-- no code changes but I want to note that in my previous client-server
submission (as oppose to the last just client side submission), i have 
forgotten to include one of the patches. this submission corrects that
and is the same submission from client-only submission from July8th.
That patch is: "NFS based on file size issue sync copy or fallback to
generic copy offload"

-- server patches
-- removed the check for copy_notify state on clientid destruction
-- removed the code with unused arg to nfsd4_verify_copy()
-- changed the check_if_stalefh_allowed as per Bruce suggestion to
no return status and set op->status if 2nd putfh is missing in the
compound

patch series is available from git branch "linux-ssc-for-5-5" (forced
update):
git://linux-nfs.org/projects/aglo/linux.git

Olga Kornievskaia (20):
  NFS NFSD: defining nl4_servers structure needed by both
  NFS: add COPY_NOTIFY operation
  NFS: add ca_source_server<> to COPY
  NFS: inter ssc open
  NFS: skip recovery of copy open on dest server
  NFS: for "inter" copy treat ESTALE as ENOTSUPP
  NFS: COPY handle ERR_OFFLOAD_DENIED
  NFS: also send OFFLOAD_CANCEL to source server
  NFS handle NFS4ERR_PARTNER_NO_AUTH error
  NFS: handle source server reboot
  NFS based on file size issue sync copy or fallback to generic copy
    offload
  NFS: replace cross device check in copy_file_range
  NFSD fill-in netloc4 structure
  NFSD add ca_source_server<> to COPY
  NFSD COPY_NOTIFY xdr
  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/nfs/nfs42.h            |  15 +-
 fs/nfs/nfs42proc.c        | 199 +++++++++++++++++----
 fs/nfs/nfs42xdr.c         | 190 +++++++++++++++++++-
 fs/nfs/nfs4_fs.h          |  11 ++
 fs/nfs/nfs4client.c       |   2 +-
 fs/nfs/nfs4file.c         | 139 ++++++++++++++-
 fs/nfs/nfs4proc.c         |   7 +-
 fs/nfs/nfs4state.c        |  40 ++++-
 fs/nfs/nfs4xdr.c          |   1 +
 fs/nfsd/Kconfig           |  10 ++
 fs/nfsd/nfs4proc.c        | 438 ++++++++++++++++++++++++++++++++++++++++++----
 fs/nfsd/nfs4state.c       | 192 +++++++++++++++++---
 fs/nfsd/nfs4xdr.c         | 155 +++++++++++++++-
 fs/nfsd/nfsd.h            |  32 ++++
 fs/nfsd/nfsfh.h           |   5 +-
 fs/nfsd/nfssvc.c          |   6 +
 fs/nfsd/state.h           |  34 +++-
 fs/nfsd/xdr4.h            |  39 ++++-
 include/linux/nfs4.h      |  25 +++
 include/linux/nfs_fs.h    |   4 +-
 include/linux/nfs_fs_sb.h |   1 +
 include/linux/nfs_xdr.h   |  17 ++
 22 files changed, 1441 insertions(+), 121 deletions(-)

-- 
1.8.3.1

[PATCH v8 01/20] NFS NFSD: defining nl4_servers structure needed by both

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

These structures are needed by COPY_NOTIFY on the client and needed
by the nfsd as well

Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 include/linux/nfs4.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index fd59904..5810e24 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -16,6 +16,7 @@
 #include <linux/list.h>
 #include <linux/uidgid.h>
 #include <uapi/linux/nfs4.h>
+#include <linux/sunrpc/msg_prot.h>
 
 enum nfs4_acl_whotype {
 	NFS4_ACL_WHO_NAMED = 0,
@@ -674,4 +675,27 @@ struct nfs4_op_map {
 	} u;
 };
 
+struct nfs42_netaddr {
+	char		netid[RPCBIND_MAXNETIDLEN];
+	char		addr[RPCBIND_MAXUADDRLEN + 1];
+	u32		netid_len;
+	u32		addr_len;
+};
+
+enum netloc_type4 {
+	NL4_NAME		= 1,
+	NL4_URL			= 2,
+	NL4_NETADDR		= 3,
+};
+
+struct nl4_server {
+	enum netloc_type4	nl4_type;
+	union {
+		struct { /* NL4_NAME, NL4_URL */
+			int	nl4_str_sz;
+			char	nl4_str[NFS4_OPAQUE_LIMIT + 1];
+		};
+		struct nfs42_netaddr	nl4_addr; /* NL4_NETADDR */
+	} u;
+};
 #endif
-- 
1.8.3.1

[PATCH v8 02/20] NFS: add COPY_NOTIFY operation

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

Try using the delegation stateid, then the open stateid.

Only NL4_NETATTR, No support for NL4_NAME and NL4_URL.
Allow only one source server address to be returned for now.

To distinguish between same server copy offload ("intra") and
a copy between different server ("inter"), do a check of server
owner identity and also make sure server is capable of doing
a copy offload.

Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42.h            |  12 ++++
 fs/nfs/nfs42proc.c        |  91 ++++++++++++++++++++++++
 fs/nfs/nfs42xdr.c         | 178 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4_fs.h          |   2 +
 fs/nfs/nfs4client.c       |   2 +-
 fs/nfs/nfs4file.c         |  20 +++++-
 fs/nfs/nfs4proc.c         |   1 +
 fs/nfs/nfs4xdr.c          |   1 +
 include/linux/nfs4.h      |   1 +
 include/linux/nfs_fs_sb.h |   1 +
 include/linux/nfs_xdr.h   |  16 +++++
 11 files changed, 323 insertions(+), 2 deletions(-)

diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 901cca7..4995731 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -13,6 +13,7 @@
 #define PNFS_LAYOUTSTATS_MAXDEV (4)
 
 /* nfs4.2proc.c */
+#ifdef CONFIG_NFS_V4_2
 int nfs42_proc_allocate(struct file *, loff_t, loff_t);
 ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t);
 int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
@@ -23,5 +24,16 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *,
 int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg,
 			   const struct nfs42_layout_error *errors,
 			   size_t n);
+int nfs42_proc_copy_notify(struct file *, struct file *,
+			   struct nfs42_copy_notify_res *);
+static inline bool nfs42_files_from_same_server(struct file *in,
+						struct file *out)
+{
+	struct nfs_client *c_in = (NFS_SERVER(file_inode(in)))->nfs_client;
+	struct nfs_client *c_out = (NFS_SERVER(file_inode(out)))->nfs_client;
 
+	return nfs4_check_serverowner_major_id(c_in->cl_serverowner,
+					       c_out->cl_serverowner);
+}
+#endif /* CONFIG_NFS_V4_2 */
 #endif /* __LINUX_FS_NFS_NFS4_2_H */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 5196bfa..6317dd8 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
  */
 #include <linux/fs.h>
+#include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/nfs.h>
 #include <linux/nfs3.h>
@@ -15,10 +16,30 @@
 #include "pnfs.h"
 #include "nfs4session.h"
 #include "internal.h"
+#include "delegation.h"
 
 #define NFSDBG_FACILITY NFSDBG_PROC
 static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *std);
 
+static void nfs42_set_netaddr(struct file *filep, struct nfs42_netaddr *naddr)
+{
+	struct nfs_client *clp = (NFS_SERVER(file_inode(filep)))->nfs_client;
+	unsigned short port = 2049;
+
+	rcu_read_lock();
+	naddr->netid_len = scnprintf(naddr->netid,
+					sizeof(naddr->netid), "%s",
+					rpc_peeraddr2str(clp->cl_rpcclient,
+					RPC_DISPLAY_NETID));
+	naddr->addr_len = scnprintf(naddr->addr,
+					sizeof(naddr->addr),
+					"%s.%u.%u",
+					rpc_peeraddr2str(clp->cl_rpcclient,
+					RPC_DISPLAY_ADDR),
+					port >> 8, port & 255);
+	rcu_read_unlock();
+}
+
 static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 		struct nfs_lock_context *lock, loff_t offset, loff_t len)
 {
@@ -459,6 +480,76 @@ static int nfs42_do_offload_cancel_async(struct file *dst,
 	return status;
 }
 
+int _nfs42_proc_copy_notify(struct file *src, struct file *dst,
+			    struct nfs42_copy_notify_args *args,
+			    struct nfs42_copy_notify_res *res)
+{
+	struct nfs_server *src_server = NFS_SERVER(file_inode(src));
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY_NOTIFY],
+		.rpc_argp = args,
+		.rpc_resp = res,
+	};
+	int status;
+	struct nfs_open_context *ctx;
+	struct nfs_lock_context *l_ctx;
+
+	ctx = get_nfs_open_context(nfs_file_open_context(src));
+	l_ctx = nfs_get_lock_context(ctx);
+	if (IS_ERR(l_ctx))
+		return PTR_ERR(l_ctx);
+
+	status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx,
+				     FMODE_READ);
+	nfs_put_lock_context(l_ctx);
+	if (status)
+		return status;
+
+	status = nfs4_call_sync(src_server->client, src_server, &msg,
+				&args->cna_seq_args, &res->cnr_seq_res, 0);
+	if (status == -ENOTSUPP)
+		src_server->caps &= ~NFS_CAP_COPY_NOTIFY;
+
+	put_nfs_open_context(nfs_file_open_context(src));
+	return status;
+}
+
+int nfs42_proc_copy_notify(struct file *src, struct file *dst,
+				struct nfs42_copy_notify_res *res)
+{
+	struct nfs_server *src_server = NFS_SERVER(file_inode(src));
+	struct nfs42_copy_notify_args *args;
+	struct nfs4_exception exception = {
+		.inode = file_inode(src),
+	};
+	int status;
+
+	if (!(src_server->caps & NFS_CAP_COPY_NOTIFY))
+		return -EOPNOTSUPP;
+
+	args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_NOFS);
+	if (args == NULL)
+		return -ENOMEM;
+
+	args->cna_src_fh  = NFS_FH(file_inode(src)),
+	args->cna_dst.nl4_type = NL4_NETADDR;
+	nfs42_set_netaddr(dst, &args->cna_dst.u.nl4_addr);
+	exception.stateid = &args->cna_src_stateid;
+
+	do {
+		status = _nfs42_proc_copy_notify(src, dst, args, res);
+		if (status == -ENOTSUPP) {
+			status = -EOPNOTSUPP;
+			goto out;
+		}
+		status = nfs4_handle_exception(src_server, status, &exception);
+	} while (exception.retry);
+
+out:
+	kfree(args);
+	return status;
+}
+
 static loff_t _nfs42_proc_llseek(struct file *filep,
 		struct nfs_lock_context *lock, loff_t offset, int whence)
 {
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index aed865a..ccabc0c 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -29,6 +29,16 @@
 #define encode_offload_cancel_maxsz	(op_encode_hdr_maxsz + \
 					 XDR_QUADLEN(NFS4_STATEID_SIZE))
 #define decode_offload_cancel_maxsz	(op_decode_hdr_maxsz)
+#define encode_copy_notify_maxsz	(op_encode_hdr_maxsz + \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+					 1 + /* nl4_type */ \
+					 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
+#define decode_copy_notify_maxsz	(op_decode_hdr_maxsz + \
+					 3 + /* cnr_lease_time */\
+					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+					 1 + /* Support 1 cnr_source_server */\
+					 1 + /* nl4_type */ \
+					 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
 #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
@@ -99,6 +109,12 @@
 					 decode_sequence_maxsz + \
 					 decode_putfh_maxsz + \
 					 decode_offload_cancel_maxsz)
+#define NFS4_enc_copy_notify_sz		(compound_encode_hdr_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_copy_notify_maxsz)
+#define NFS4_dec_copy_notify_sz		(compound_decode_hdr_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_copy_notify_maxsz)
 #define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
@@ -166,6 +182,26 @@ static void encode_allocate(struct xdr_stream *xdr,
 	encode_fallocate(xdr, args);
 }
 
+static void encode_nl4_server(struct xdr_stream *xdr,
+			      const struct nl4_server *ns)
+{
+	encode_uint32(xdr, ns->nl4_type);
+	switch (ns->nl4_type) {
+	case NL4_NAME:
+	case NL4_URL:
+		encode_string(xdr, ns->u.nl4_str_sz, ns->u.nl4_str);
+		break;
+	case NL4_NETADDR:
+		encode_string(xdr, ns->u.nl4_addr.netid_len,
+			      ns->u.nl4_addr.netid);
+		encode_string(xdr, ns->u.nl4_addr.addr_len,
+			      ns->u.nl4_addr.addr);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+
 static void encode_copy(struct xdr_stream *xdr,
 			const struct nfs42_copy_args *args,
 			struct compound_hdr *hdr)
@@ -191,6 +227,15 @@ static void encode_offload_cancel(struct xdr_stream *xdr,
 	encode_nfs4_stateid(xdr, &args->osa_stateid);
 }
 
+static void encode_copy_notify(struct xdr_stream *xdr,
+			       const struct nfs42_copy_notify_args *args,
+			       struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_COPY_NOTIFY, decode_copy_notify_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->cna_src_stateid);
+	encode_nl4_server(xdr, &args->cna_dst);
+}
+
 static void encode_deallocate(struct xdr_stream *xdr,
 			      const struct nfs42_falloc_args *args,
 			      struct compound_hdr *hdr)
@@ -355,6 +400,25 @@ static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req,
 }
 
 /*
+ * Encode COPY_NOTIFY request
+ */
+static void nfs4_xdr_enc_copy_notify(struct rpc_rqst *req,
+				     struct xdr_stream *xdr,
+				     const void *data)
+{
+	const struct nfs42_copy_notify_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->cna_seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->cna_seq_args, &hdr);
+	encode_putfh(xdr, args->cna_src_fh, &hdr);
+	encode_copy_notify(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
  * Encode DEALLOCATE request
  */
 static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
@@ -490,6 +554,58 @@ static int decode_write_response(struct xdr_stream *xdr,
 	return decode_verifier(xdr, &res->verifier.verifier);
 }
 
+static int decode_nl4_server(struct xdr_stream *xdr, struct nl4_server *ns)
+{
+	struct nfs42_netaddr *naddr;
+	uint32_t dummy;
+	char *dummy_str;
+	__be32 *p;
+	int status;
+
+	/* nl_type */
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -EIO;
+	ns->nl4_type = be32_to_cpup(p);
+	switch (ns->nl4_type) {
+	case NL4_NAME:
+	case NL4_URL:
+		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+		if (unlikely(status))
+			return status;
+		if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
+			return -EIO;
+		memcpy(&ns->u.nl4_str, dummy_str, dummy);
+		ns->u.nl4_str_sz = dummy;
+		break;
+	case NL4_NETADDR:
+		naddr = &ns->u.nl4_addr;
+
+		/* netid string */
+		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+		if (unlikely(status))
+			return status;
+		if (unlikely(dummy > RPCBIND_MAXNETIDLEN))
+			return -EIO;
+		naddr->netid_len = dummy;
+		memcpy(naddr->netid, dummy_str, naddr->netid_len);
+
+		/* uaddr string */
+		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+		if (unlikely(status))
+			return status;
+		if (unlikely(dummy > RPCBIND_MAXUADDRLEN))
+			return -EIO;
+		naddr->addr_len = dummy;
+		memcpy(naddr->addr, dummy_str, naddr->addr_len);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EIO;
+	}
+	return 0;
+}
+
 static int decode_copy_requirements(struct xdr_stream *xdr,
 				    struct nfs42_copy_res *res) {
 	__be32 *p;
@@ -529,6 +645,42 @@ static int decode_offload_cancel(struct xdr_stream *xdr,
 	return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL);
 }
 
+static int decode_copy_notify(struct xdr_stream *xdr,
+			      struct nfs42_copy_notify_res *res)
+{
+	__be32 *p;
+	int status, count;
+
+	status = decode_op_hdr(xdr, OP_COPY_NOTIFY);
+	if (status)
+		return status;
+	/* cnr_lease_time */
+	p = xdr_inline_decode(xdr, 12);
+	if (unlikely(!p))
+		return -EIO;
+	p = xdr_decode_hyper(p, &res->cnr_lease_time.seconds);
+	res->cnr_lease_time.nseconds = be32_to_cpup(p);
+
+	status = decode_opaque_fixed(xdr, &res->cnr_stateid, NFS4_STATEID_SIZE);
+	if (unlikely(status))
+		return -EIO;
+
+	/* number of source addresses */
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	count = be32_to_cpup(p);
+	if (count > 1)
+		pr_warn("NFS: %s: nsvr %d > Supported. Use first servers\n",
+			 __func__, count);
+
+	status = decode_nl4_server(xdr, &res->cnr_src);
+	if (unlikely(status))
+		return -EIO;
+	return 0;
+}
+
 static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
 {
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
@@ -657,6 +809,32 @@ static int nfs4_xdr_dec_offload_cancel(struct rpc_rqst *rqstp,
 }
 
 /*
+ * Decode COPY_NOTIFY response
+ */
+static int nfs4_xdr_dec_copy_notify(struct rpc_rqst *rqstp,
+				    struct xdr_stream *xdr,
+				    void *data)
+{
+	struct nfs42_copy_notify_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->cnr_seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_copy_notify(xdr, res);
+
+out:
+	return status;
+}
+
+/*
  * Decode DEALLOCATE request
  */
 static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 16b2e5c..8e590b4 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -457,6 +457,8 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
 			struct nfs_client **, const struct cred *);
 extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
 extern void nfs41_notify_server(struct nfs_client *);
+bool nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
+			struct nfs41_server_owner *o2);
 #else
 static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
 {
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index da62040..54aaf55 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -629,7 +629,7 @@ int nfs40_walk_client_list(struct nfs_client *new,
 /*
  * Returns true if the server major ids match
  */
-static bool
+bool
 nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
 				struct nfs41_server_owner *o2)
 {
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 339663d..686a6c4 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -133,6 +133,9 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 				      struct file *file_out, loff_t pos_out,
 				      size_t count, unsigned int flags)
 {
+	struct nfs42_copy_notify_res *cn_resp = NULL;
+	ssize_t ret;
+
 	/* Only offload copy if superblock is the same */
 	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
 		return -EXDEV;
@@ -140,7 +143,22 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 		return -EOPNOTSUPP;
 	if (file_inode(file_in) == file_inode(file_out))
 		return -EOPNOTSUPP;
-	return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+	if (!nfs42_files_from_same_server(file_in, file_out)) {
+		cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res),
+				GFP_NOFS);
+		if (unlikely(cn_resp == NULL))
+			return -ENOMEM;
+
+		ret = nfs42_proc_copy_notify(file_in, file_out, cn_resp);
+		if (ret) {
+			ret = -EOPNOTSUPP;
+			goto out;
+		}
+	}
+	ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+out:
+	kfree(cn_resp);
+	return ret;
 }
 
 static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 11eafcf..505045b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -9899,6 +9899,7 @@ static bool nfs4_match_stateid(const nfs4_stateid *s1,
 		| NFS_CAP_ALLOCATE
 		| NFS_CAP_COPY
 		| NFS_CAP_OFFLOAD_CANCEL
+		| NFS_CAP_COPY_NOTIFY
 		| NFS_CAP_DEALLOCATE
 		| NFS_CAP_SEEK
 		| NFS_CAP_LAYOUTSTATS
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index ab07db0..2f9315d 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7581,6 +7581,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	PROC42(CLONE,		enc_clone,		dec_clone),
 	PROC42(COPY,		enc_copy,		dec_copy),
 	PROC42(OFFLOAD_CANCEL,	enc_offload_cancel,	dec_offload_cancel),
+	PROC42(COPY_NOTIFY,	enc_copy_notify,	dec_copy_notify),
 	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 	PROC42(LAYOUTERROR,	enc_layouterror,	dec_layouterror),
 };
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 5810e24..5e7a526 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -537,6 +537,7 @@ enum {
 	NFSPROC4_CLNT_CLONE,
 	NFSPROC4_CLNT_COPY,
 	NFSPROC4_CLNT_OFFLOAD_CANCEL,
+	NFSPROC4_CLNT_COPY_NOTIFY,
 
 	NFSPROC4_CLNT_LOOKUPP,
 	NFSPROC4_CLNT_LAYOUTERROR,
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index a87fe85..e1c8748 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -276,5 +276,6 @@ struct nfs_server {
 #define NFS_CAP_COPY		(1U << 24)
 #define NFS_CAP_OFFLOAD_CANCEL	(1U << 25)
 #define NFS_CAP_LAYOUTERROR	(1U << 26)
+#define NFS_CAP_COPY_NOTIFY	(1U << 27)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9b8324e..0a7af40 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1463,6 +1463,22 @@ struct nfs42_offload_status_res {
 	int				osr_status;
 };
 
+struct nfs42_copy_notify_args {
+	struct nfs4_sequence_args	cna_seq_args;
+
+	struct nfs_fh		*cna_src_fh;
+	nfs4_stateid		cna_src_stateid;
+	struct nl4_server	cna_dst;
+};
+
+struct nfs42_copy_notify_res {
+	struct nfs4_sequence_res	cnr_seq_res;
+
+	struct nfstime4		cnr_lease_time;
+	nfs4_stateid		cnr_stateid;
+	struct nl4_server	cnr_src;
+};
+
 struct nfs42_seek_args {
 	struct nfs4_sequence_args	seq_args;
 
-- 
1.8.3.1

[PATCH v8 03/20] NFS: add ca_source_server<> to COPY

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

Support only one source server address: the same address that
the client and source server use.

Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42.h          |  3 ++-
 fs/nfs/nfs42proc.c      | 26 +++++++++++++++++---------
 fs/nfs/nfs42xdr.c       | 12 ++++++++++--
 fs/nfs/nfs4file.c       |  7 ++++++-
 include/linux/nfs_xdr.h |  1 +
 5 files changed, 36 insertions(+), 13 deletions(-)

diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 4995731..02e3810 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -15,7 +15,8 @@
 /* nfs4.2proc.c */
 #ifdef CONFIG_NFS_V4_2
 int nfs42_proc_allocate(struct file *, loff_t, loff_t);
-ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t);
+ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t,
+			struct nl4_server *, nfs4_stateid *);
 int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
 loff_t nfs42_proc_llseek(struct file *, loff_t, int);
 int nfs42_proc_layoutstats_generic(struct nfs_server *,
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 6317dd8..e34ade8 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -243,7 +243,9 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 				struct file *dst,
 				struct nfs_lock_context *dst_lock,
 				struct nfs42_copy_args *args,
-				struct nfs42_copy_res *res)
+				struct nfs42_copy_res *res,
+				struct nl4_server *nss,
+				nfs4_stateid *cnr_stateid)
 {
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY],
@@ -257,11 +259,15 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 	size_t count = args->count;
 	ssize_t status;
 
-	status = nfs4_set_rw_stateid(&args->src_stateid, src_lock->open_context,
-				     src_lock, FMODE_READ);
-	if (status)
-		return status;
-
+	if (nss) {
+		args->cp_src = nss;
+		nfs4_stateid_copy(&args->src_stateid, cnr_stateid);
+	} else {
+		status = nfs4_set_rw_stateid(&args->src_stateid,
+				src_lock->open_context, src_lock, FMODE_READ);
+		if (status)
+			return status;
+	}
 	status = nfs_filemap_write_and_wait_range(file_inode(src)->i_mapping,
 			pos_src, pos_src + (loff_t)count - 1);
 	if (status)
@@ -325,8 +331,9 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 }
 
 ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
-			struct file *dst, loff_t pos_dst,
-			size_t count)
+			struct file *dst, loff_t pos_dst, size_t count,
+			struct nl4_server *nss,
+			nfs4_stateid *cnr_stateid)
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(dst));
 	struct nfs_lock_context *src_lock;
@@ -368,7 +375,8 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 		inode_lock(file_inode(dst));
 		err = _nfs42_proc_copy(src, src_lock,
 				dst, dst_lock,
-				&args, &res);
+				&args, &res,
+				nss, cnr_stateid);
 		inode_unlock(file_inode(dst));
 
 		if (err >= 0)
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index ccabc0c..c03f324 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -21,7 +21,10 @@
 #define encode_copy_maxsz		(op_encode_hdr_maxsz +          \
 					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
 					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
-					 2 + 2 + 2 + 1 + 1 + 1)
+					 2 + 2 + 2 + 1 + 1 + 1 +\
+					 1 + /* One cnr_source_server */\
+					 1 + /* nl4_type */ \
+					 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
 #define decode_copy_maxsz		(op_decode_hdr_maxsz + \
 					 NFS42_WRITE_RES_SIZE + \
 					 1 /* cr_consecutive */ + \
@@ -216,7 +219,12 @@ static void encode_copy(struct xdr_stream *xdr,
 
 	encode_uint32(xdr, 1); /* consecutive = true */
 	encode_uint32(xdr, args->sync);
-	encode_uint32(xdr, 0); /* src server list */
+	if (args->cp_src == NULL) { /* intra-ssc */
+		encode_uint32(xdr, 0); /* no src server list */
+		return;
+	}
+	encode_uint32(xdr, 1); /* supporting 1 server */
+	encode_nl4_server(xdr, args->cp_src);
 }
 
 static void encode_offload_cancel(struct xdr_stream *xdr,
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 686a6c4..b68b41b 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -134,6 +134,8 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 				      size_t count, unsigned int flags)
 {
 	struct nfs42_copy_notify_res *cn_resp = NULL;
+	struct nl4_server *nss = NULL;
+	nfs4_stateid *cnrs = NULL;
 	ssize_t ret;
 
 	/* Only offload copy if superblock is the same */
@@ -154,8 +156,11 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 			ret = -EOPNOTSUPP;
 			goto out;
 		}
+		nss = &cn_resp->cnr_src;
+		cnrs = &cn_resp->cnr_stateid;
 	}
-	ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+	ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count,
+				nss, cnrs);
 out:
 	kfree(cn_resp);
 	return ret;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 0a7af40..008faca 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1435,6 +1435,7 @@ struct nfs42_copy_args {
 
 	u64				count;
 	bool				sync;
+	struct nl4_server		*cp_src;
 };
 
 struct nfs42_write_res {
-- 
1.8.3.1

[PATCH v8 04/20] NFS: inter ssc open

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

NFSv4.2 inter server to server copy requires the destination server to
READ the data from the source server using the provided stateid and
file handle.

Given an NFSv4 stateid and filehandle from the COPY operaion, provide the
destination server with an NFS client function to create a struct file
suitable for the destiniation server to READ the data to be copied.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Andy Adamson <andros@netapp.com>
---
 fs/nfs/nfs4_fs.h  |  7 +++++
 fs/nfs/nfs4file.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4proc.c |  5 ++-
 3 files changed, 103 insertions(+), 3 deletions(-)

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 8e590b4..5f27942 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -311,6 +311,13 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid,
 		const struct nfs_open_context *ctx,
 		const struct nfs_lock_context *l_ctx,
 		fmode_t fmode);
+extern int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
+			     struct nfs_fattr *fattr, struct nfs4_label *label,
+			     struct inode *inode);
+extern int update_open_stateid(struct nfs4_state *state,
+				const nfs4_stateid *open_stateid,
+				const nfs4_stateid *deleg_stateid,
+				fmode_t fmode);
 
 extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
 		struct nfs_fsinfo *fsinfo);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index b68b41b..1898262a 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -8,6 +8,7 @@
 #include <linux/file.h>
 #include <linux/falloc.h>
 #include <linux/nfs_fs.h>
+#include <linux/file.h>
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
@@ -286,6 +287,99 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
 out:
 	return ret < 0 ? ret : count;
 }
+
+static int read_name_gen = 1;
+#define SSC_READ_NAME_BODY "ssc_read_%d"
+
+struct file *
+nfs42_ssc_open(struct vfsmount *ss_mnt, struct nfs_fh *src_fh,
+		nfs4_stateid *stateid)
+{
+	struct nfs_fattr fattr;
+	struct file *filep, *res;
+	struct nfs_server *server;
+	struct inode *r_ino = NULL;
+	struct nfs_open_context *ctx;
+	struct nfs4_state_owner *sp;
+	char *read_name;
+	int len, status = 0;
+
+	server = NFS_SERVER(ss_mnt->mnt_root->d_inode);
+
+	nfs_fattr_init(&fattr);
+
+	status = nfs4_proc_getattr(server, src_fh, &fattr, NULL, NULL);
+	if (status < 0) {
+		res = ERR_PTR(status);
+		goto out;
+	}
+
+	res = ERR_PTR(-ENOMEM);
+	len = strlen(SSC_READ_NAME_BODY) + 16;
+	read_name = kzalloc(len, GFP_NOFS);
+	if (read_name == NULL)
+		goto out;
+	snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++);
+
+	r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, &fattr,
+			NULL);
+	if (IS_ERR(r_ino)) {
+		res = ERR_CAST(r_ino);
+		goto out;
+	}
+
+	filep = alloc_file_pseudo(r_ino, ss_mnt, read_name, FMODE_READ,
+				     r_ino->i_fop);
+	if (IS_ERR(filep)) {
+		res = ERR_CAST(filep);
+		goto out;
+	}
+	filep->f_mode |= FMODE_READ;
+
+	ctx = alloc_nfs_open_context(filep->f_path.dentry, filep->f_mode,
+					filep);
+	if (IS_ERR(ctx)) {
+		res = ERR_CAST(ctx);
+		goto out_filep;
+	}
+
+	res = ERR_PTR(-EINVAL);
+	sp = nfs4_get_state_owner(server, ctx->cred, GFP_KERNEL);
+	if (sp == NULL)
+		goto out_ctx;
+
+	ctx->state = nfs4_get_open_state(r_ino, sp);
+	if (ctx->state == NULL)
+		goto out_stateowner;
+
+	set_bit(NFS_OPEN_STATE, &ctx->state->flags);
+	memcpy(&ctx->state->open_stateid.other, &stateid->other,
+	       NFS4_STATEID_OTHER_SIZE);
+	update_open_stateid(ctx->state, stateid, NULL, filep->f_mode);
+
+	nfs_file_set_open_context(filep, ctx);
+	put_nfs_open_context(ctx);
+
+	file_ra_state_init(&filep->f_ra, filep->f_mapping->host->i_mapping);
+	res = filep;
+out:
+	return res;
+out_stateowner:
+	nfs4_put_state_owner(sp);
+out_ctx:
+	put_nfs_open_context(ctx);
+out_filep:
+	fput(filep);
+	goto out;
+}
+EXPORT_SYMBOL_GPL(nfs42_ssc_open);
+void nfs42_ssc_close(struct file *filep)
+{
+	struct nfs_open_context *ctx = nfs_file_open_context(filep);
+
+	ctx->state->flags = 0;
+}
+EXPORT_SYMBOL_GPL(nfs42_ssc_close);
 #endif /* CONFIG_NFS_V4_2 */
 
 const struct file_operations nfs4_file_operations = {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 505045b..f3a1f8d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -91,7 +91,6 @@
 static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
 static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
 static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
-static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label, struct inode *inode);
 static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label, struct inode *inode);
 static int nfs4_do_setattr(struct inode *inode, const struct cred *cred,
 			    struct nfs_fattr *fattr, struct iattr *sattr,
@@ -1718,7 +1717,7 @@ static void nfs_state_clear_delegation(struct nfs4_state *state)
 	write_sequnlock(&state->seqlock);
 }
 
-static int update_open_stateid(struct nfs4_state *state,
+int update_open_stateid(struct nfs4_state *state,
 		const nfs4_stateid *open_stateid,
 		const nfs4_stateid *delegation,
 		fmode_t fmode)
@@ -4065,7 +4064,7 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
 	return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
 }
 
-static int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
+int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
 				struct nfs_fattr *fattr, struct nfs4_label *label,
 				struct inode *inode)
 {
-- 
1.8.3.1

[PATCH v8 05/20] NFS: skip recovery of copy open on dest server

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

Mark the open created for the source file on the destination
server. Then if this open is going thru a recovery, then fail
the recovery as we don't need to be recoving a "fake" open.
We need to fail the ongoing READs and vfs_copy_file_range().

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs4_fs.h   |  1 +
 fs/nfs/nfs4file.c  |  1 +
 fs/nfs/nfs4state.c | 14 ++++++++++++++
 3 files changed, 16 insertions(+)

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 5f27942..814674f 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -168,6 +168,7 @@ enum {
 	NFS_STATE_CHANGE_WAIT,		/* A state changing operation is outstanding */
 #ifdef CONFIG_NFS_V4_2
 	NFS_CLNT_DST_SSC_COPY_STATE,    /* dst server open state on client*/
+	NFS_SRV_SSC_COPY_STATE,		/* ssc state on the dst server */
 #endif /* CONFIG_NFS_V4_2 */
 };
 
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 1898262a..a932fc9 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -352,6 +352,7 @@ struct file *
 	if (ctx->state == NULL)
 		goto out_stateowner;
 
+	set_bit(NFS_SRV_SSC_COPY_STATE, &ctx->state->flags);
 	set_bit(NFS_OPEN_STATE, &ctx->state->flags);
 	memcpy(&ctx->state->open_stateid.other, &stateid->other,
 	       NFS4_STATEID_OTHER_SIZE);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 0c6d53d..c45b300 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1609,6 +1609,9 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 	struct nfs4_state *state;
 	unsigned int loop = 0;
 	int status = 0;
+#ifdef CONFIG_NFS_V4_2
+	bool found_ssc_copy_state = false;
+#endif /* CONFIG_NFS_V4_2 */
 
 	/* Note: we rely on the sp->so_states list being ordered 
 	 * so that we always reclaim open(O_RDWR) and/or open(O_WRITE)
@@ -1628,6 +1631,13 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 			continue;
 		if (state->state == 0)
 			continue;
+#ifdef CONFIG_NFS_V4_2
+		if (test_bit(NFS_SRV_SSC_COPY_STATE, &state->flags)) {
+			nfs4_state_mark_recovery_failed(state, -EIO);
+			found_ssc_copy_state = true;
+			continue;
+		}
+#endif /* CONFIG_NFS_V4_2 */
 		refcount_inc(&state->count);
 		spin_unlock(&sp->so_lock);
 		status = __nfs4_reclaim_open_state(sp, state, ops);
@@ -1682,6 +1692,10 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 	}
 	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
+#ifdef CONFIG_NFS_V4_2
+	if (found_ssc_copy_state)
+		return -EIO;
+#endif /* CONFIG_NFS_V4_2 */
 	return 0;
 out_err:
 	nfs4_put_open_state(state);
-- 
1.8.3.1

[PATCH v8 06/20] NFS: for "inter" copy treat ESTALE as ENOTSUPP

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

If the client sends an "inter" copy to the destination server but
it only supports "intra" copy, it can return ESTALE (since it
doesn't know anything about the file handle from the other server
and does not recognize the special case of "inter" copy). Translate
this error as ENOTSUPP and also send OFFLOAD_CANCEL to the source
server so that it can clean up state.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42proc.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index e34ade8..6ed5a16 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -391,6 +391,11 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 			args.sync = true;
 			dst_exception.retry = 1;
 			continue;
+		} else if (err == -ESTALE &&
+				!nfs42_files_from_same_server(src, dst)) {
+			nfs42_do_offload_cancel_async(src, &args.src_stateid);
+			err = -EOPNOTSUPP;
+			break;
 		}
 
 		err2 = nfs4_handle_exception(server, err, &src_exception);
-- 
1.8.3.1

[PATCH v8 07/20] NFS: COPY handle ERR_OFFLOAD_DENIED

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

If server sends ERR_OFFLOAD_DENIED error, the client must fall
back on doing copy the normal way. Return ENOTSUPP to the vfs and
fallback to regular copy.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42proc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 6ed5a16..50538b9 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -391,7 +391,8 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 			args.sync = true;
 			dst_exception.retry = 1;
 			continue;
-		} else if (err == -ESTALE &&
+		} else if ((err == -ESTALE ||
+				err == -NFS4ERR_OFFLOAD_DENIED) &&
 				!nfs42_files_from_same_server(src, dst)) {
 			nfs42_do_offload_cancel_async(src, &args.src_stateid);
 			err = -EOPNOTSUPP;
-- 
1.8.3.1

[PATCH v8 08/20] NFS: also send OFFLOAD_CANCEL to source server

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

In case of copy is cancelled, also send OFFLOAD_CANCEL to the source
server.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42proc.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 50538b9..5d833f5 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -206,12 +206,14 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 	memcpy(&res->write_res.verifier, &copy->verf, sizeof(copy->verf));
 	status = -copy->error;
 
+out_free:
 	kfree(copy);
 	return status;
 out_cancel:
 	nfs42_do_offload_cancel_async(dst, &copy->stateid);
-	kfree(copy);
-	return status;
+	if (!nfs42_files_from_same_server(src, dst))
+		nfs42_do_offload_cancel_async(src, src_stateid);
+	goto out_free;
 }
 
 static int process_copy_commit(struct file *dst, loff_t pos_dst,
@@ -381,7 +383,8 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 
 		if (err >= 0)
 			break;
-		if (err == -ENOTSUPP) {
+		if (err == -ENOTSUPP &&
+				nfs42_files_from_same_server(src, dst)) {
 			err = -EOPNOTSUPP;
 			break;
 		} else if (err == -EAGAIN) {
@@ -392,7 +395,8 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 			dst_exception.retry = 1;
 			continue;
 		} else if ((err == -ESTALE ||
-				err == -NFS4ERR_OFFLOAD_DENIED) &&
+				err == -NFS4ERR_OFFLOAD_DENIED ||
+				err == -ENOTSUPP) &&
 				!nfs42_files_from_same_server(src, dst)) {
 			nfs42_do_offload_cancel_async(src, &args.src_stateid);
 			err = -EOPNOTSUPP;
-- 
1.8.3.1

[PATCH v8 09/20] NFS handle NFS4ERR_PARTNER_NO_AUTH error

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

When a destination server sends a READ to the source server it can
get a NFS4ERR_PARTNER_NO_AUTH, which means a copy needs to be
restarted.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs4proc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f3a1f8d..a7a55d6 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -475,6 +475,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_EXPIRED:
 		case -NFS4ERR_BAD_STATEID:
+		case -NFS4ERR_PARTNER_NO_AUTH:
 			if (inode != NULL && stateid != NULL) {
 				nfs_inode_find_state_and_recover(inode,
 						stateid);
-- 
1.8.3.1

[PATCH v8 10/20] NFS: handle source server reboot

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

When the source server reboots after a server-to-server copy was
issued, we need to retry the copy from COPY_NOTIFY. We need to
detect that the source server rebooted and there is a copy waiting
on a destination server and wake it up.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42proc.c     | 68 ++++++++++++++++++++++++++++++++++----------------
 fs/nfs/nfs4_fs.h       |  1 +
 fs/nfs/nfs4file.c      |  3 +++
 fs/nfs/nfs4state.c     | 26 +++++++++++++++----
 include/linux/nfs_fs.h |  4 ++-
 5 files changed, 75 insertions(+), 27 deletions(-)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 5d833f5..9c7feac 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -153,22 +153,26 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 }
 
 static int handle_async_copy(struct nfs42_copy_res *res,
-			     struct nfs_server *server,
+			     struct nfs_server *dst_server,
+			     struct nfs_server *src_server,
 			     struct file *src,
 			     struct file *dst,
-			     nfs4_stateid *src_stateid)
+			     nfs4_stateid *src_stateid,
+			     bool *restart)
 {
 	struct nfs4_copy_state *copy, *tmp_copy;
 	int status = NFS4_OK;
 	bool found_pending = false;
-	struct nfs_open_context *ctx = nfs_file_open_context(dst);
+	struct nfs_open_context *dst_ctx = nfs_file_open_context(dst);
+	struct nfs_open_context *src_ctx = nfs_file_open_context(src);
 
 	copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS);
 	if (!copy)
 		return -ENOMEM;
 
-	spin_lock(&server->nfs_client->cl_lock);
-	list_for_each_entry(tmp_copy, &server->nfs_client->pending_cb_stateids,
+	spin_lock(&dst_server->nfs_client->cl_lock);
+	list_for_each_entry(tmp_copy,
+				&dst_server->nfs_client->pending_cb_stateids,
 				copies) {
 		if (memcmp(&res->write_res.stateid, &tmp_copy->stateid,
 				NFS4_STATEID_SIZE))
@@ -178,7 +182,7 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 		break;
 	}
 	if (found_pending) {
-		spin_unlock(&server->nfs_client->cl_lock);
+		spin_unlock(&dst_server->nfs_client->cl_lock);
 		kfree(copy);
 		copy = tmp_copy;
 		goto out;
@@ -186,19 +190,32 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 
 	memcpy(&copy->stateid, &res->write_res.stateid, NFS4_STATEID_SIZE);
 	init_completion(&copy->completion);
-	copy->parent_state = ctx->state;
+	copy->parent_dst_state = dst_ctx->state;
+	copy->parent_src_state = src_ctx->state;
+
+	list_add_tail(&copy->copies, &dst_server->ss_copies);
+	spin_unlock(&dst_server->nfs_client->cl_lock);
 
-	list_add_tail(&copy->copies, &server->ss_copies);
-	spin_unlock(&server->nfs_client->cl_lock);
+	if (dst_server != src_server) {
+		spin_lock(&src_server->nfs_client->cl_lock);
+		list_add_tail(&copy->src_copies, &src_server->ss_copies);
+		spin_unlock(&src_server->nfs_client->cl_lock);
+	}
 
 	status = wait_for_completion_interruptible(&copy->completion);
-	spin_lock(&server->nfs_client->cl_lock);
+	spin_lock(&dst_server->nfs_client->cl_lock);
 	list_del_init(&copy->copies);
-	spin_unlock(&server->nfs_client->cl_lock);
+	spin_unlock(&dst_server->nfs_client->cl_lock);
+	if (dst_server != src_server) {
+		spin_lock(&src_server->nfs_client->cl_lock);
+		list_del_init(&copy->src_copies);
+		spin_unlock(&src_server->nfs_client->cl_lock);
+	}
 	if (status == -ERESTARTSYS) {
 		goto out_cancel;
-	} else if (copy->flags) {
+	} else if (copy->flags || copy->error == NFS4ERR_PARTNER_NO_AUTH) {
 		status = -EAGAIN;
+		*restart = true;
 		goto out_cancel;
 	}
 out:
@@ -247,7 +264,8 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 				struct nfs42_copy_args *args,
 				struct nfs42_copy_res *res,
 				struct nl4_server *nss,
-				nfs4_stateid *cnr_stateid)
+				nfs4_stateid *cnr_stateid,
+				bool *restart)
 {
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY],
@@ -255,7 +273,9 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 		.rpc_resp = res,
 	};
 	struct inode *dst_inode = file_inode(dst);
-	struct nfs_server *server = NFS_SERVER(dst_inode);
+	struct inode *src_inode = file_inode(src);
+	struct nfs_server *dst_server = NFS_SERVER(dst_inode);
+	struct nfs_server *src_server = NFS_SERVER(src_inode);
 	loff_t pos_src = args->src_pos;
 	loff_t pos_dst = args->dst_pos;
 	size_t count = args->count;
@@ -291,13 +311,15 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 		if (!res->commit_res.verf)
 			return -ENOMEM;
 	}
+	set_bit(NFS_CLNT_SRC_SSC_COPY_STATE,
+		&src_lock->open_context->state->flags);
 	set_bit(NFS_CLNT_DST_SSC_COPY_STATE,
 		&dst_lock->open_context->state->flags);
 
-	status = nfs4_call_sync(server->client, server, &msg,
+	status = nfs4_call_sync(dst_server->client, dst_server, &msg,
 				&args->seq_args, &res->seq_res, 0);
 	if (status == -ENOTSUPP)
-		server->caps &= ~NFS_CAP_COPY;
+		dst_server->caps &= ~NFS_CAP_COPY;
 	if (status)
 		goto out;
 
@@ -309,8 +331,8 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 	}
 
 	if (!res->synchronous) {
-		status = handle_async_copy(res, server, src, dst,
-				&args->src_stateid);
+		status = handle_async_copy(res, dst_server, src_server, src,
+				dst, &args->src_stateid, restart);
 		if (status)
 			return status;
 	}
@@ -358,6 +380,7 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 		.stateid	= &args.dst_stateid,
 	};
 	ssize_t err, err2;
+	bool restart = false;
 
 	src_lock = nfs_get_lock_context(nfs_file_open_context(src));
 	if (IS_ERR(src_lock))
@@ -378,7 +401,7 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 		err = _nfs42_proc_copy(src, src_lock,
 				dst, dst_lock,
 				&args, &res,
-				nss, cnr_stateid);
+				nss, cnr_stateid, &restart);
 		inode_unlock(file_inode(dst));
 
 		if (err >= 0)
@@ -388,8 +411,11 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 			err = -EOPNOTSUPP;
 			break;
 		} else if (err == -EAGAIN) {
-			dst_exception.retry = 1;
-			continue;
+			if (!restart) {
+				dst_exception.retry = 1;
+				continue;
+			}
+			break;
 		} else if (err == -NFS4ERR_OFFLOAD_NO_REQS && !args.sync) {
 			args.sync = true;
 			dst_exception.retry = 1;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 814674f..2122748 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -168,6 +168,7 @@ enum {
 	NFS_STATE_CHANGE_WAIT,		/* A state changing operation is outstanding */
 #ifdef CONFIG_NFS_V4_2
 	NFS_CLNT_DST_SSC_COPY_STATE,    /* dst server open state on client*/
+	NFS_CLNT_SRC_SSC_COPY_STATE,    /* src server open state on client*/
 	NFS_SRV_SSC_COPY_STATE,		/* ssc state on the dst server */
 #endif /* CONFIG_NFS_V4_2 */
 };
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index a932fc9..2af30b7 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -146,6 +146,7 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 		return -EOPNOTSUPP;
 	if (file_inode(file_in) == file_inode(file_out))
 		return -EOPNOTSUPP;
+retry:
 	if (!nfs42_files_from_same_server(file_in, file_out)) {
 		cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res),
 				GFP_NOFS);
@@ -164,6 +165,8 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 				nss, cnrs);
 out:
 	kfree(cn_resp);
+	if (ret == -EAGAIN)
+		goto retry;
 	return ret;
 }
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index c45b300..e799fbe 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1556,16 +1556,32 @@ static void nfs42_complete_copies(struct nfs4_state_owner *sp, struct nfs4_state
 {
 	struct nfs4_copy_state *copy;
 
-	if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags))
+	if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags) &&
+		!test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags))
 		return;
 
 	spin_lock(&sp->so_server->nfs_client->cl_lock);
 	list_for_each_entry(copy, &sp->so_server->ss_copies, copies) {
-		if (!nfs4_stateid_match_other(&state->stateid, &copy->parent_state->stateid))
-			continue;
+		if ((test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags) &&
+				!nfs4_stateid_match_other(&state->stateid,
+				&copy->parent_dst_state->stateid)))
+				continue;
 		copy->flags = 1;
-		complete(&copy->completion);
-		break;
+		if (test_and_clear_bit(NFS_CLNT_DST_SSC_COPY_STATE,
+				&state->flags)) {
+			clear_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags);
+			complete(&copy->completion);
+		}
+	}
+	list_for_each_entry(copy, &sp->so_server->ss_copies, src_copies) {
+		if ((test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags) &&
+				!nfs4_stateid_match_other(&state->stateid,
+				&copy->parent_src_state->stateid)))
+				continue;
+		copy->flags = 1;
+		if (test_and_clear_bit(NFS_CLNT_DST_SSC_COPY_STATE,
+				&state->flags))
+			complete(&copy->completion);
 	}
 	spin_unlock(&sp->so_server->nfs_client->cl_lock);
 }
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 570a60c..c06b1fd 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -189,13 +189,15 @@ struct nfs_inode {
 
 struct nfs4_copy_state {
 	struct list_head	copies;
+	struct list_head	src_copies;
 	nfs4_stateid		stateid;
 	struct completion	completion;
 	uint64_t		count;
 	struct nfs_writeverf	verf;
 	int			error;
 	int			flags;
-	struct nfs4_state	*parent_state;
+	struct nfs4_state	*parent_src_state;
+	struct nfs4_state	*parent_dst_state;
 };
 
 /*
-- 
1.8.3.1

[PATCH v8 11/20] NFS based on file size issue sync copy or fallback to generic copy offload

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

For small file sizes, it make sense to issue a synchronous copy (and
save an RPC callback operation). Also, for the inter copy offload,
copy len must be larger than the cost of doing a mount between the
destination and source server (14RPCs are sent during 4.x mount).

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42.h     |  2 +-
 fs/nfs/nfs42proc.c |  4 ++--
 fs/nfs/nfs4file.c  | 16 +++++++++++++++-
 3 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 02e3810..c891af9 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -16,7 +16,7 @@
 #ifdef CONFIG_NFS_V4_2
 int nfs42_proc_allocate(struct file *, loff_t, loff_t);
 ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t,
-			struct nl4_server *, nfs4_stateid *);
+			struct nl4_server *, nfs4_stateid *, bool);
 int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
 loff_t nfs42_proc_llseek(struct file *, loff_t, int);
 int nfs42_proc_layoutstats_generic(struct nfs_server *,
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 9c7feac..aab6b7b 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -357,7 +357,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 			struct file *dst, loff_t pos_dst, size_t count,
 			struct nl4_server *nss,
-			nfs4_stateid *cnr_stateid)
+			nfs4_stateid *cnr_stateid, bool sync)
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(dst));
 	struct nfs_lock_context *src_lock;
@@ -368,7 +368,7 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 		.dst_fh		= NFS_FH(file_inode(dst)),
 		.dst_pos	= pos_dst,
 		.count		= count,
-		.sync		= false,
+		.sync		= sync,
 	};
 	struct nfs42_copy_res res;
 	struct nfs4_exception src_exception = {
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 2af30b7..8978325 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -138,6 +138,7 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 	struct nl4_server *nss = NULL;
 	nfs4_stateid *cnrs = NULL;
 	ssize_t ret;
+	bool sync = false;
 
 	/* Only offload copy if superblock is the same */
 	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
@@ -146,8 +147,21 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 		return -EOPNOTSUPP;
 	if (file_inode(file_in) == file_inode(file_out))
 		return -EOPNOTSUPP;
+	/* if the copy size if smaller than 2 RPC payloads, make it
+	 * synchronous
+	 */
+	if (count <= 2 * NFS_SERVER(file_inode(file_in))->rsize)
+		sync = true;
 retry:
 	if (!nfs42_files_from_same_server(file_in, file_out)) {
+		/* for inter copy, if copy size if smaller than 12 RPC
+		 * payloads, fallback to traditional copy. There are
+		 * 14 RPCs during an NFSv4.x mount between source/dest
+		 * servers.
+		 */
+		if (sync ||
+			count <= 14 * NFS_SERVER(file_inode(file_in))->rsize)
+			return -EOPNOTSUPP;
 		cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res),
 				GFP_NOFS);
 		if (unlikely(cn_resp == NULL))
@@ -162,7 +176,7 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 		cnrs = &cn_resp->cnr_stateid;
 	}
 	ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count,
-				nss, cnrs);
+				nss, cnrs, sync);
 out:
 	kfree(cn_resp);
 	if (ret == -EAGAIN)
-- 
1.8.3.1

[PATCH v8 12/20] NFS: replace cross device check in copy_file_range

[Olga Kornievskaia]

From: Olga Kornievskaia <kolga@netapp.com>

Add a check to disallow cross file systems copy offload, both
files are expected to be of NFS4.2+ type.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs4file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 8978325..e97813b 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -141,7 +141,7 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 	bool sync = false;
 
 	/* Only offload copy if superblock is the same */
-	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
+	if (file_in->f_op != &nfs4_file_operations)
 		return -EXDEV;
 	if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY))
 		return -EOPNOTSUPP;
-- 
1.8.3.1

[PATCH v8 13/20] 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 af29475..687f8e1 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>
 
@@ -386,6 +387,37 @@ 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 v8 14/20] NFSD add ca_source_server<> to COPY

[Olga Kornievskaia]

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 | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 fs/nfsd/xdr4.h    | 12 +++++-----
 2 files changed, 71 insertions(+), 6 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 533d0fc..a664c18 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"
@@ -1744,10 +1745,47 @@ 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_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;
+	struct nl4_server *ns_dummy;
+	int i, count;
 
 	status = nfsd4_decode_stateid(argp, &copy->cp_src_stateid);
 	if (status)
@@ -1762,7 +1800,32 @@ 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 f4737d6..e815a9c 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -518,11 +518,13 @@ 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 v8 15/20] NFSD COPY_NOTIFY xdr

[Olga Kornievskaia]

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfsd/nfs4proc.c | 28 +++++++++++++++++
 fs/nfsd/nfs4xdr.c  | 90 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
 fs/nfsd/xdr4.h     | 13 ++++++++
 3 files changed, 129 insertions(+), 2 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 4e3e77b..7fa694d 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1338,6 +1338,13 @@ struct nfsd4_copy *
 }
 
 static __be32
+nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		  union nfsd4_op_u *u)
+{
+	return nfserr_notsupp;
+}
+
+static __be32
 nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		struct nfsd4_fallocate *fallocate, int flags)
 {
@@ -2290,6 +2297,21 @@ 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)
 {
@@ -2714,6 +2736,12 @@ 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/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index a664c18..a7b8b81 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1838,6 +1838,18 @@ 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;
+	return nfsd4_decode_nl4_server(argp, &cn->cpn_dst);
+}
+
+static __be32
 nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
 {
 	DECODE_HEAD;
@@ -1938,7 +1950,7 @@ 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,
@@ -4318,6 +4330,46 @@ 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_ONCE(ns->nl4_type != NL4_NETADDR);
+		return nfserr_inval;
+	}
+
+	return 0;
+}
+
+static __be32
 nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_copy *copy)
 {
@@ -4351,6 +4403,40 @@ 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);
+
+	return nfsd42_encode_nl4_server(resp, &cn->cpn_src);
+}
+
+static __be32
 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_seek *seek)
 {
@@ -4447,7 +4533,7 @@ 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/xdr4.h b/fs/nfsd/xdr4.h
index e815a9c..8231fe0 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -570,6 +570,18 @@ 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;
@@ -629,6 +641,7 @@ 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 v8 16/20] NFSD add COPY_NOTIFY operation

[Olga Kornievskaia]

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.
Each associated parent stateid has a list of copy
notify stateids. A copy notify structure makes a copy of
the parent stateid and a clientid and will use it to look
up the parent stateid during the READ request (suggested
by Trond Myklebust <trond.myklebust@hammerspace.com>).

At nfs4_put_stid() time, we walk the list of the associated
copy notify stateids and delete them.

Laundromat thread will traverse globally stored copy notify
stateid in idr and notice if any haven't been referenced in the
lease period, if so, it'll remove them.

Return single netaddr to advertise to the copy.

Suggested-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Andy Adamson <andros@netapp.com>
---
 fs/nfsd/nfs4proc.c  |  58 +++++++++++++++++++++++-----
 fs/nfsd/nfs4state.c | 106 +++++++++++++++++++++++++++++++++++++++++++++++-----
 fs/nfsd/state.h     |  31 +++++++++++++--
 fs/nfsd/xdr4.h      |   2 +-
 4 files changed, 173 insertions(+), 24 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 7fa694d..9400636 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"
@@ -776,7 +777,7 @@ 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_nf);
+					&read->rd_nf, NULL);
 	if (status) {
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;
@@ -948,7 +949,7 @@ 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);
+				WR_STATE, NULL, NULL);
 		if (status) {
 			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
 			return status;
@@ -999,7 +1000,7 @@ 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, &nf);
+						stateid, WR_STATE, &nf, NULL);
 	if (status) {
 		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
 		return status;
@@ -1034,14 +1035,14 @@ 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);
+					    src_stateid, RD_STATE, src, 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);
+					    dst_stateid, WR_STATE, dst, NULL);
 	if (status) {
 		dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
 		goto out_put_src;
@@ -1220,7 +1221,7 @@ 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);
 	nfsd_file_put(copy->nf_dst);
 	nfsd_file_put(copy->nf_src);
 	spin_lock(&copy->cp_clp->async_lock);
@@ -1274,7 +1275,7 @@ 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;
 		}
@@ -1341,7 +1342,44 @@ struct nfsd4_copy *
 nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		  union nfsd4_op_u *u)
 {
-	return nfserr_notsupp;
+	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;
+	struct nfs4_client *clp = cstate->clp;
+
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+					&cn->cpn_src_stateid, RD_STATE, 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)
+		goto out;
+	memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.stid, sizeof(stateid_t));
+	memcpy(&cps->cp_p_stateid, &stid->sc_stateid, sizeof(stateid_t));
+	memcpy(&cps->cp_p_clid, &clp->cl_clientid, sizeof(clientid_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);
+	if (status) {
+		nfs4_put_cpntf_state(nn, cps);
+		goto out;
+	}
+out:
+	nfs4_put_stid(stid);
+	return status;
 }
 
 static __be32
@@ -1353,7 +1391,7 @@ struct nfsd4_copy *
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &fallocate->falloc_stateid,
-					    WR_STATE, &nf);
+					    WR_STATE, &nf, NULL);
 	if (status != nfs_ok) {
 		dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n");
 		return status;
@@ -1412,7 +1450,7 @@ struct nfsd4_copy *
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &seek->seek_stateid,
-					    RD_STATE, &nf);
+					    RD_STATE, &nf, 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 c65aeaa..b7859b6 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -80,6 +80,7 @@
 static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner);
 static void nfs4_free_ol_stateid(struct nfs4_stid *stid);
 void nfsd4_end_grace(struct nfsd_net *nn);
+static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps);
 
 /* Locking: */
 
@@ -722,6 +723,7 @@ 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.
@@ -741,30 +743,76 @@ 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, copy_stateid_t *stid,
+			      unsigned char sc_type)
 {
 	int new_id;
 
+	stid->stid.si_opaque.so_clid.cl_boot = nn->boot_time;
+	stid->stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
+	stid->sc_type = sc_type;
+
 	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, stid, 0, 0, GFP_NOWAIT);
+	stid->stid.si_opaque.so_id = new_id;
 	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;
 	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->cp_stateid, NFS4_COPY_STID);
+}
+
+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;
+	cps->cpntf_time = get_seconds();
+	refcount_set(&cps->cp_stateid.sc_count, 1);
+	if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID))
+		goto out_free;
+	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;
 
+	WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID);
 	nn = net_generic(copy->cp_clp->net, nfsd_net_id);
 	spin_lock(&nn->s2s_cp_lock);
-	idr_remove(&nn->s2s_cp_stateids, copy->cp_stateid.si_opaque.so_id);
+	idr_remove(&nn->s2s_cp_stateids,
+		   copy->cp_stateid.stid.si_opaque.so_id);
+	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);
+		_free_cpntf_state_locked(nn, cps);
+	}
 	spin_unlock(&nn->s2s_cp_lock);
 }
 
@@ -915,6 +963,7 @@ static void block_delegations(struct knfsd_fh *fh)
 		return;
 	}
 	idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
+	nfs4_free_cpntf_statelist(clp->net, s);
 	spin_unlock(&clp->cl_lock);
 	s->sc_free(s);
 	if (fp)
@@ -5210,6 +5259,9 @@ static bool clients_still_reclaiming(struct nfsd_net *nn)
 	struct list_head *pos, *next, reaplist;
 	time_t cutoff = get_seconds() - nn->nfsd4_lease;
 	time_t t, new_timeo = nn->nfsd4_lease;
+	struct nfs4_cpntf_state *cps;
+	copy_stateid_t *cps_t;
+	int i;
 
 	dprintk("NFSD: laundromat service - starting\n");
 
@@ -5220,6 +5272,17 @@ static bool clients_still_reclaiming(struct nfsd_net *nn)
 	dprintk("NFSD: end of grace period\n");
 	nfsd4_end_grace(nn);
 	INIT_LIST_HEAD(&reaplist);
+
+	spin_lock(&nn->s2s_cp_lock);
+	idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
+		cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
+		if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
+				!time_after((unsigned long)cps->cpntf_time,
+				(unsigned long)cutoff))
+			_free_cpntf_state_locked(nn, cps);
+	}
+	spin_unlock(&nn->s2s_cp_lock);
+
 	spin_lock(&nn->client_lock);
 	list_for_each_safe(pos, next, &nn->client_lru) {
 		clp = list_entry(pos, struct nfs4_client, cl_lru);
@@ -5595,6 +5658,24 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 out:
 	return status;
 }
+static void
+_free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
+{
+	WARN_ON_ONCE(cps->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID);
+	if (!refcount_dec_and_test(&cps->cp_stateid.sc_count))
+		return;
+	list_del(&cps->cp_list);
+	idr_remove(&nn->s2s_cp_stateids,
+		   cps->cp_stateid.stid.si_opaque.so_id);
+	kfree(cps);
+}
+
+void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
+{
+	spin_lock(&nn->s2s_cp_lock);
+	_free_cpntf_state_locked(nn, cps);
+	spin_unlock(&nn->s2s_cp_lock);
+}
 
 /*
  * Checks for stateid operations
@@ -5602,7 +5683,8 @@ 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 nfsd_file **nfp)
+		stateid_t *stateid, int flags, struct nfsd_file **nfp,
+		struct nfs4_stid **cstid)
 {
 	struct inode *ino = d_inode(fhp->fh_dentry);
 	struct net *net = SVC_NET(rqstp);
@@ -5651,8 +5733,12 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	if (status == nfs_ok && nfp)
 		status = nfs4_check_file(rqstp, fhp, s, nfp, flags);
 out:
-	if (s)
-		nfs4_put_stid(s);
+	if (s) {
+		if (!status && cstid)
+			*cstid = s;
+		else
+			nfs4_put_stid(s);
+	}
 	return status;
 }
 
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 46f56af..967b937 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -56,6 +56,14 @@
 	stateid_opaque_t        si_opaque;
 } stateid_t;
 
+typedef struct {
+	stateid_t		stid;
+#define NFS4_COPY_STID 1
+#define NFS4_COPYNOTIFY_STID 2
+	unsigned char		sc_type;
+	refcount_t		sc_count;
+} copy_stateid_t;
+
 #define STATEID_FMT	"(%08x/%08x/%08x/%08x)"
 #define STATEID_VAL(s) \
 	(s)->si_opaque.so_clid.cl_boot, \
@@ -96,6 +104,7 @@ 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;
@@ -104,6 +113,17 @@ 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 {
+	copy_stateid_t		cp_stateid;
+	struct list_head	cp_list;	/* per parent nfs4_stid */
+	stateid_t		cp_p_stateid;	/* copy of parent's stateid */
+	clientid_t		cp_p_clid;	/* copy of parent's clid */
+	time_t			cpntf_time;	/* last time stateid used */
+};
+
 /*
  * 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
@@ -617,14 +637,17 @@ 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 nfsd_file **filp);
+		stateid_t *stateid, int flags, struct nfsd_file **filp,
+		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);
 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);
@@ -654,6 +677,8 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name
 extern void nfs4_put_copy(struct nfsd4_copy *copy);
 extern struct nfsd4_copy *
 find_async_copy(struct nfs4_client *clp, stateid_t *staetid);
+extern void nfs4_put_cpntf_state(struct nfsd_net *nn,
+				 struct nfs4_cpntf_state *cps);
 static inline void get_nfs4_file(struct nfs4_file *fi)
 {
 	refcount_inc(&fi->fi_ref);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 8231fe0..2937e06 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -542,7 +542,7 @@ struct nfsd4_copy {
 	struct nfsd_file        *nf_src;
 	struct nfsd_file        *nf_dst;
 
-	stateid_t		cp_stateid;
+	copy_stateid_t		cp_stateid;
 
 	struct list_head	copies;
 	struct task_struct	*copy_task;
-- 
1.8.3.1

[PATCH v8 17/20] NFSD check stateids against copy stateids

[Olga Kornievskaia]

Incoming stateid (used by a READ) could be a saved copy stateid.
Using the provided stateid, look it up in the list of copy_notify
stateids. If found, use the parent's stateid and parent's clid
to look up the parent's stid to do the appropriate checks.

Update the copy notify timestamp (cpntf_time) with current time
this making it 'active' so that laundromat thread will not delete
copy notify state.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfsd/nfs4state.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 66 insertions(+), 8 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b7859b6..f0942bd 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4534,7 +4534,8 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4
 
 static __be32 lookup_clientid(clientid_t *clid,
 		struct nfsd4_compound_state *cstate,
-		struct nfsd_net *nn)
+		struct nfsd_net *nn,
+		bool sessions)
 {
 	struct nfs4_client *found;
 
@@ -4555,7 +4556,7 @@ static __be32 lookup_clientid(clientid_t *clid,
 	 */
 	WARN_ON_ONCE(cstate->session);
 	spin_lock(&nn->client_lock);
-	found = find_confirmed_client(clid, false, nn);
+	found = find_confirmed_client(clid, sessions, nn);
 	if (!found) {
 		spin_unlock(&nn->client_lock);
 		return nfserr_expired;
@@ -4588,7 +4589,7 @@ static __be32 lookup_clientid(clientid_t *clid,
 	if (open->op_file == NULL)
 		return nfserr_jukebox;
 
-	status = lookup_clientid(clientid, cstate, nn);
+	status = lookup_clientid(clientid, cstate, nn, false);
 	if (status)
 		return status;
 	clp = cstate->clp;
@@ -5177,7 +5178,7 @@ void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate,
 
 	dprintk("process_renew(%08x/%08x): starting\n", 
 			clid->cl_boot, clid->cl_id);
-	status = lookup_clientid(clid, cstate, nn);
+	status = lookup_clientid(clid, cstate, nn, false);
 	if (status)
 		goto out;
 	clp = cstate->clp;
@@ -5579,7 +5580,8 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
 		CLOSE_STATEID(stateid))
 		return nfserr_bad_stateid;
-	status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn);
+	status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn,
+				 false);
 	if (status == nfserr_stale_clientid) {
 		if (cstate->session)
 			return nfserr_bad_stateid;
@@ -5669,6 +5671,59 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 		   cps->cp_stateid.stid.si_opaque.so_id);
 	kfree(cps);
 }
+/*
+ * A READ from an inter server to server COPY will have a
+ * copy stateid. Look up the copy notify stateid from the
+ * idr structure and take a reference on it.
+ */
+static __be32 _find_cpntf_state(struct nfsd_net *nn, stateid_t *st,
+		     struct nfs4_cpntf_state **cps)
+{
+	copy_stateid_t *cps_t;
+	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);
+	cps_t = idr_find(&nn->s2s_cp_stateids, st->si_opaque.so_id);
+	if (cps_t) {
+		state = container_of(cps_t, struct nfs4_cpntf_state,
+				     cp_stateid);
+		if (state->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID)
+			return nfserr_bad_stateid;
+		refcount_inc(&state->cp_stateid.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;
+	struct nfsd4_compound_state cstate;
+
+	status = _find_cpntf_state(nn, st, &cps);
+	if (status)
+		return status;
+
+	cps->cpntf_time = get_seconds();
+	memset(&cstate, 0, sizeof(cstate));
+	status = lookup_clientid(&cps->cp_p_clid, &cstate, nn, true);
+	if (status)
+		goto out;
+	status = nfsd4_lookup_stateid(&cstate, &cps->cp_p_stateid,
+				NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
+				stid, nn);
+	put_client_renew(cstate.clp);
+out:
+	nfs4_put_cpntf_state(nn, cps);
+	return status;
+}
 
 void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
 {
@@ -5706,6 +5761,8 @@ void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
 	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,
@@ -6738,7 +6795,8 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct
 		 return nfserr_inval;
 
 	if (!nfsd4_has_session(cstate)) {
-		status = lookup_clientid(&lockt->lt_clientid, cstate, nn);
+		status = lookup_clientid(&lockt->lt_clientid, cstate, nn,
+					 false);
 		if (status)
 			goto out;
 	}
@@ -6922,7 +6980,7 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct
 	dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
 		clid->cl_boot, clid->cl_id);
 
-	status = lookup_clientid(clid, cstate, nn);
+	status = lookup_clientid(clid, cstate, nn, false);
 	if (status)
 		return status;
 
@@ -7069,7 +7127,7 @@ struct nfs4_client_reclaim *
 	__be32 status;
 
 	/* find clientid in conf_id_hashtbl */
-	status = lookup_clientid(clid, cstate, nn);
+	status = lookup_clientid(clid, cstate, nn, false);
 	if (status)
 		return nfserr_reclaim_bad;
 
-- 
1.8.3.1

[PATCH v8 18/20] 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 9400636..3dfa7d7 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 f0942bd..1a84616 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -7925,7 +7925,8 @@ 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));
 }
 
@@ -7934,14 +7935,14 @@ 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 2937e06..0b4fe07 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 v8 19/20] NFSD: allow inter server COPY to have a STALE source server fh

[Olga Kornievskaia]

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 | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++----
 fs/nfsd/nfsfh.h    |  5 ++++-
 fs/nfsd/xdr4.h     |  1 +
 4 files changed, 68 insertions(+), 5 deletions(-)

diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 10cefb0..b7172a8 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -133,6 +133,16 @@ 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 3dfa7d7..dde42ea 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
@@ -1955,6 +1963,45 @@ 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 = NULL, *saved_op = NULL;
+	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;
+			if (!saved_op) {
+				op->status = nfserr_nofilehandle;
+				return;
+			}
+			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.
  */
@@ -2003,6 +2050,7 @@ 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) {
@@ -2018,13 +2066,14 @@ 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 0b4fe07..b16f602 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 v8 20/20] 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_range.

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

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfsd/nfs4proc.c  | 293 ++++++++++++++++++++++++++++++++++++++++++++++++----
 fs/nfsd/nfs4state.c |  15 ++-
 fs/nfsd/nfssvc.c    |   6 ++
 fs/nfsd/state.h     |   3 +
 fs/nfsd/xdr4.h      |   5 +
 5 files changed, 295 insertions(+), 27 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index dde42ea..1675129 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1143,6 +1143,208 @@ 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 "vers=4.2,addr=%s,sec=sys"
+
+/**
+ * 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->nf_dst, 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 nfsd_file *src,
+			struct nfsd_file *dst)
+{
+	nfs42_ssc_close(src->nf_file);
+	nfsd_file_put(src);
+	nfsd_file_put(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 nfsd_file *src,
+			struct nfsd_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->nf_src, &copy->cp_dst_stateid,
+				 &copy->nf_dst);
+}
+
+static void
+nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst)
+{
+	nfsd_file_put(src);
+	nfsd_file_put(dst);
+}
 
 static void nfsd4_cb_offload_release(struct nfsd4_callback *cb)
 {
@@ -1208,12 +1410,16 @@ static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync)
 		status = nfs_ok;
 	}
 
-	nfsd_file_put(copy->nf_src);
-	nfsd_file_put(copy->nf_dst);
+	if (!copy->cp_intra) /* Inter server SSC */
+		nfsd4_cleanup_inter_ssc(copy->ss_mnt, copy->nf_src,
+					copy->nf_dst);
+	else
+		nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst);
+
 	return status;
 }
 
-static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
+static int dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
 {
 	dst->cp_src_pos = src->cp_src_pos;
 	dst->cp_dst_pos = src->cp_dst_pos;
@@ -1223,8 +1429,17 @@ 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->nf_dst = nfsd_file_get(src->nf_dst);
-	dst->nf_src = nfsd_file_get(src->nf_src);
+	dst->cp_intra = src->cp_intra;
+	if (src->cp_intra) /* for inter, file_src doesn't exist yet */
+		dst->nf_src = nfsd_file_get(src->nf_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;
+
+	return 0;
 }
 
 static void cleanup_async_copy(struct nfsd4_copy *copy)
@@ -1243,7 +1458,25 @@ 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->nf_src = kzalloc(sizeof(struct nfsd_file), GFP_KERNEL);
+		if (!copy->nf_src) {
+			copy->nfserr = nfserr_serverfault;
+			nfsd4_interssc_disconnect(copy->ss_mnt);
+			goto do_callback;
+		}
+		copy->nf_src->nf_file = nfs42_ssc_open(copy->ss_mnt, &copy->c_fh,
+					      &copy->stateid);
+		if (IS_ERR(copy->nf_src->nf_file)) {
+			kfree(copy->nf_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;
@@ -1255,6 +1488,8 @@ static int nfsd4_do_async_copy(void *data)
 			&nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD);
 	nfsd4_run_cb(&cb_copy->cp_cb);
 out:
+	if (!copy->cp_intra)
+		kfree(copy->nf_src);
 	cleanup_async_copy(copy);
 	return 0;
 }
@@ -1267,11 +1502,20 @@ 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->nf_src, &copy->cp_dst_stateid,
-				   &copy->nf_dst);
-	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,
@@ -1282,15 +1526,15 @@ 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));
-		dup_copy_fields(copy, async_copy);
+		status = dup_copy_fields(copy, async_copy);
+		if (status)
+			goto out_err;
 		async_copy->copy_task = kthread_create(nfsd4_do_async_copy,
 				async_copy, "%s", "copy thread");
 		if (IS_ERR(async_copy->copy_task))
@@ -1301,12 +1545,16 @@ 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);
+	status = nfserrno(-ENOMEM);
+	if (!copy->cp_intra)
+		nfsd4_interssc_disconnect(copy->ss_mnt);
 	goto out;
 }
 
@@ -1317,7 +1565,7 @@ struct nfsd4_copy *
 
 	spin_lock(&clp->async_lock);
 	list_for_each_entry(copy, &clp->async_copies, copies) {
-		if (memcmp(&copy->cp_stateid, stateid, NFS4_STATEID_SIZE))
+		if (memcmp(&copy->cp_stateid.stid, stateid, NFS4_STATEID_SIZE))
 			continue;
 		refcount_inc(&copy->refcount);
 		spin_unlock(&clp->async_lock);
@@ -1333,17 +1581,18 @@ struct nfsd4_copy *
 		     union nfsd4_op_u *u)
 {
 	struct nfsd4_offload_status *os = &u->offload_status;
-	__be32 status = 0;
 	struct nfsd4_copy *copy;
 	struct nfs4_client *clp = cstate->clp;
 
 	copy = find_async_copy(clp, &os->stateid);
-	if (copy)
+	if (!copy) {
+		struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
+		return manage_cpntf_state(nn, &os->stateid, clp, NULL);
+	} else
 		nfsd4_stop_copy(copy);
-	else
-		status = nfserr_bad_stateid;
 
-	return status;
+	return nfs_ok;
 }
 
 static __be32
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 1a84616..767ada7 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5676,8 +5676,9 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
  * copy stateid. Look up the copy notify stateid from the
  * idr structure and take a reference on it.
  */
-static __be32 _find_cpntf_state(struct nfsd_net *nn, stateid_t *st,
-		     struct nfs4_cpntf_state **cps)
+__be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st,
+			  struct nfs4_client *clp,
+			  struct nfs4_cpntf_state **cps)
 {
 	copy_stateid_t *cps_t;
 	struct nfs4_cpntf_state *state = NULL;
@@ -5691,12 +5692,16 @@ static __be32 _find_cpntf_state(struct nfsd_net *nn, stateid_t *st,
 				     cp_stateid);
 		if (state->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID)
 			return nfserr_bad_stateid;
-		refcount_inc(&state->cp_stateid.sc_count);
+		if (!clp)
+			refcount_inc(&state->cp_stateid.sc_count);
+		else
+			_free_cpntf_state_locked(nn, state);
 	}
 	spin_unlock(&nn->s2s_cp_lock);
 	if (!state)
 		return nfserr_bad_stateid;
-	*cps = state;
+	if (!clp && state)
+		*cps = state;
 	return 0;
 }
 
@@ -5707,7 +5712,7 @@ static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st,
 	struct nfs4_cpntf_state *cps = NULL;
 	struct nfsd4_compound_state cstate;
 
-	status = _find_cpntf_state(nn, st, &cps);
+	status = manage_cpntf_state(nn, st, NULL, &cps);
 	if (status)
 		return status;
 
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index fdf7ed4..97bfee9 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -31,6 +31,12 @@
 
 #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/state.h b/fs/nfsd/state.h
index 967b937..3f57680 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -679,6 +679,9 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name
 find_async_copy(struct nfs4_client *clp, stateid_t *staetid);
 extern void nfs4_put_cpntf_state(struct nfsd_net *nn,
 				 struct nfs4_cpntf_state *cps);
+extern __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st,
+				 struct nfs4_client *clp,
+				 struct nfs4_cpntf_state **cps);
 static inline void get_nfs4_file(struct nfs4_file *fi)
 {
 	refcount_inc(&fi->fi_ref);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index b16f602..db63d39 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -549,7 +549,12 @@ 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 */
-- 
1.8.3.1