[PATCH v9 00/13] NFS support for async intra COPY

[PATCH v9 00/13] NFS support for async intra COPY

[Olga Kornievskaia]

Change the client side to always request an asynchronous copy.

If server replies to the COPY with the copy stateid, client will go
wait on the CB_OFFLOAD. To fend off the race between CB_OFFLOAD and
COPY reply, we check the list of pending callbacks before going to
wait. Client adds the copy to the global list of copy stateids for the
callback to look thru and signal the waiting copy.

When the client receives reply from the CB_OFFLOAD with some bytes and
committed how is UNSTABLE, then COMMIT is sent to the server. The results
are propagated to the VFS and application. Assuming that application
will deal with a partial result and continue from the new offset if needed.

If server errs with ERR_OFFLOAD_NOREQS the copy will be re-sent as a
synchronous COPY. If application cancels an in-flight COPY,
OFFLOAD_CANCEL is sent to the server (sending it as an async RPC in the
context of the nfsid_workqueue).

v9.
--reworked patches so that OFFLOAD_STATUS are the last 2 patches.

Anna Schumaker (1):
  fs: Don't copy beyond the end of the file

Olga Kornievskaia (12):
  NFS CB_OFFLOAD xdr
  NFS OFFLOAD_CANCEL xdr
  NFS COPY xdr handle async reply
  NFS add support for asynchronous COPY
  NFS handle COPY reply CB_OFFLOAD call race
  NFS export nfs4_async_handle_error
  NFS send OFFLOAD_CANCEL when COPY killed
  NFS handle COPY ERR_OFFLOAD_NO_REQS
  NFS add a simple sync nfs4_proc_commit after async COPY
  NFS recover from destination server reboot for copies
  NFS OFFLOAD_STATUS xdr
  NFS OFFLOAD_STATUS op

 fs/nfs/callback.h         |  12 +++
 fs/nfs/callback_proc.c    |  54 ++++++++++
 fs/nfs/callback_xdr.c     |  80 ++++++++++++++-
 fs/nfs/client.c           |   1 +
 fs/nfs/nfs42.h            |   5 +-
 fs/nfs/nfs42proc.c        | 252 ++++++++++++++++++++++++++++++++++++++++++++--
 fs/nfs/nfs42xdr.c         | 189 +++++++++++++++++++++++++++++++---
 fs/nfs/nfs4_fs.h          |   8 +-
 fs/nfs/nfs4client.c       |  15 +++
 fs/nfs/nfs4file.c         |   9 +-
 fs/nfs/nfs4proc.c         |  38 ++++++-
 fs/nfs/nfs4state.c        |  15 +++
 fs/nfs/nfs4xdr.c          |   2 +
 fs/read_write.c           |   3 +
 include/linux/nfs4.h      |   2 +
 include/linux/nfs_fs.h    |  11 ++
 include/linux/nfs_fs_sb.h |   4 +
 include/linux/nfs_xdr.h   |  14 +++
 18 files changed, 689 insertions(+), 25 deletions(-)

-- 
1.8.3.1

[PATCH v9 01/13] fs: Don't copy beyond the end of the file

[Olga Kornievskaia]

From: Anna Schumaker <Anna.Schumaker@Netapp.com>

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/read_write.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/read_write.c b/fs/read_write.c
index 153f8f6..8d56da8 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1570,6 +1570,9 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (unlikely(ret))
 		return ret;
 
+	if (pos_in >= i_size_read(inode_in))
+		return -EINVAL;
+
 	if (!(file_in->f_mode & FMODE_READ) ||
 	    !(file_out->f_mode & FMODE_WRITE) ||
 	    (file_out->f_flags & O_APPEND))
-- 
1.8.3.1

[PATCH v9 02/13] NFS CB_OFFLOAD xdr

[Olga Kornievskaia]

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/callback.h      | 12 ++++++++
 fs/nfs/callback_proc.c |  7 +++++
 fs/nfs/callback_xdr.c  | 80 +++++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 98 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index a20a0bc..8f34daf 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -184,6 +184,18 @@ struct cb_notify_lock_args {
 extern __be32 nfs4_callback_notify_lock(void *argp, void *resp,
 					 struct cb_process_state *cps);
 #endif /* CONFIG_NFS_V4_1 */
+#ifdef CONFIG_NFS_V4_2
+struct cb_offloadargs {
+	struct nfs_fh		coa_fh;
+	nfs4_stateid		coa_stateid;
+	uint32_t		error;
+	uint64_t		wr_count;
+	struct nfs_writeverf	wr_writeverf;
+};
+
+extern __be32 nfs4_callback_offload(void *args, void *dummy,
+				    struct cb_process_state *cps);
+#endif /* CONFIG_NFS_V4_2 */
 extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *);
 extern __be32 nfs4_callback_getattr(void *argp, void *resp,
 				    struct cb_process_state *cps);
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 43ba390..9647616 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -661,3 +661,10 @@ __be32 nfs4_callback_notify_lock(void *argp, void *resp,
 	return htonl(NFS4_OK);
 }
 #endif /* CONFIG_NFS_V4_1 */
+#ifdef CONFIG_NFS_V4_2
+__be32 nfs4_callback_offload(void *args, void *dummy,
+			     struct cb_process_state *cps)
+{
+	return 0;
+}
+#endif /* CONFIG_NFS_V4_2 */
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index a813979..d1dea85 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -38,6 +38,9 @@
 #define CB_OP_RECALLSLOT_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_NOTIFY_LOCK_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #endif /* CONFIG_NFS_V4_1 */
+#ifdef CONFIG_NFS_V4_2
+#define CB_OP_OFFLOAD_RES_MAXSZ		(CB_OP_HDR_RES_MAXSZ)
+#endif /* CONFIG_NFS_V4_2 */
 
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
 
@@ -527,7 +530,72 @@ static __be32 decode_notify_lock_args(struct svc_rqst *rqstp,
 }
 
 #endif /* CONFIG_NFS_V4_1 */
+#ifdef CONFIG_NFS_V4_2
+static __be32 decode_write_response(struct xdr_stream *xdr,
+					struct cb_offloadargs *args)
+{
+	__be32 *p;
+
+	/* skip the always zero field */
+	p = read_buf(xdr, 4);
+	if (unlikely(!p))
+		goto out;
+	p++;
+
+	/* decode count, stable_how, verifier */
+	p = xdr_inline_decode(xdr, 8 + 4);
+	if (unlikely(!p))
+		goto out;
+	p = xdr_decode_hyper(p, &args->wr_count);
+	args->wr_writeverf.committed = be32_to_cpup(p);
+	p = xdr_inline_decode(xdr, NFS4_VERIFIER_SIZE);
+	if (likely(p)) {
+		memcpy(&args->wr_writeverf.verifier.data[0], p,
+			NFS4_VERIFIER_SIZE);
+		return 0;
+	}
+out:
+	return htonl(NFS4ERR_RESOURCE);
+}
+
+static __be32 decode_offload_args(struct svc_rqst *rqstp,
+					struct xdr_stream *xdr,
+					void *data)
+{
+	struct cb_offloadargs *args = data;
+	__be32 *p;
+	__be32 status;
+
+	/* decode fh */
+	status = decode_fh(xdr, &args->coa_fh);
+	if (unlikely(status != 0))
+		return status;
+
+	/* decode stateid */
+	status = decode_stateid(xdr, &args->coa_stateid);
+	if (unlikely(status != 0))
+		return status;
 
+	/* decode status */
+	p = read_buf(xdr, 4);
+	if (unlikely(!p))
+		goto out;
+	args->error = ntohl(*p++);
+	if (!args->error) {
+		status = decode_write_response(xdr, args);
+		if (unlikely(status != 0))
+			return status;
+	} else {
+		p = xdr_inline_decode(xdr, 8);
+		if (unlikely(!p))
+			goto out;
+		p = xdr_decode_hyper(p, &args->wr_count);
+	}
+	return 0;
+out:
+	return htonl(NFS4ERR_RESOURCE);
+}
+#endif /* CONFIG_NFS_V4_2 */
 static __be32 encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
 {
 	if (unlikely(xdr_stream_encode_opaque(xdr, str, len) < 0))
@@ -773,7 +841,10 @@ static void nfs4_cb_free_slot(struct cb_process_state *cps)
 	if (status != htonl(NFS4ERR_OP_ILLEGAL))
 		return status;
 
-	if (op_nr == OP_CB_OFFLOAD)
+	if (op_nr == OP_CB_OFFLOAD) {
+		*op = &callback_ops[op_nr];
+		return htonl(NFS_OK);
+	} else
 		return htonl(NFS4ERR_NOTSUPP);
 	return htonl(NFS4ERR_OP_ILLEGAL);
 }
@@ -969,6 +1040,13 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 		.res_maxsize = CB_OP_NOTIFY_LOCK_RES_MAXSZ,
 	},
 #endif /* CONFIG_NFS_V4_1 */
+#ifdef CONFIG_NFS_V4_2
+	[OP_CB_OFFLOAD] = {
+		.process_op = nfs4_callback_offload,
+		.decode_args = decode_offload_args,
+		.res_maxsize = CB_OP_OFFLOAD_RES_MAXSZ,
+	},
+#endif /* CONFIG_NFS_V4_2 */
 };
 
 /*
-- 
1.8.3.1

[PATCH v9 03/13] NFS OFFLOAD_CANCEL xdr

[Olga Kornievskaia]

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42xdr.c         | 68 +++++++++++++++++++++++++++++++++++++++++++++++
 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   | 12 +++++++++
 6 files changed, 84 insertions(+)

diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 5966e1e..09a540d0 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -26,6 +26,9 @@
 					 NFS42_WRITE_RES_SIZE + \
 					 1 /* cr_consecutive */ + \
 					 1 /* cr_synchronous */)
+#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_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
@@ -75,6 +78,12 @@
 					 decode_putfh_maxsz + \
 					 decode_copy_maxsz + \
 					 decode_commit_maxsz)
+#define NFS4_enc_offload_cancel_sz	(compound_encode_hdr_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_offload_cancel_maxsz)
+#define NFS4_dec_offload_cancel_sz	(compound_decode_hdr_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_offload_cancel_maxsz)
 #define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
 					 encode_deallocate_maxsz + \
@@ -145,6 +154,14 @@ static void encode_copy(struct xdr_stream *xdr,
 	encode_uint32(xdr, 0); /* src server list */
 }
 
+static void encode_offload_cancel(struct xdr_stream *xdr,
+				  const struct nfs42_offload_status_args *args,
+				  struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_OFFLOAD_CANCEL, decode_offload_cancel_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->osa_stateid);
+}
+
 static void encode_deallocate(struct xdr_stream *xdr,
 			      const struct nfs42_falloc_args *args,
 			      struct compound_hdr *hdr)
@@ -261,6 +278,25 @@ static void nfs4_xdr_enc_copy(struct rpc_rqst *req,
 }
 
 /*
+ * Encode OFFLOAD_CANEL request
+ */
+static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req,
+					struct xdr_stream *xdr,
+					const void *data)
+{
+	const struct nfs42_offload_status_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->osa_seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->osa_seq_args, &hdr);
+	encode_putfh(xdr, args->osa_src_fh, &hdr);
+	encode_offload_cancel(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
  * Encode DEALLOCATE request
  */
 static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
@@ -413,6 +449,12 @@ static int decode_copy(struct xdr_stream *xdr, struct nfs42_copy_res *res)
 	return decode_copy_requirements(xdr, res);
 }
 
+static int decode_offload_cancel(struct xdr_stream *xdr,
+				 struct nfs42_offload_status_res *res)
+{
+	return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL);
+}
+
 static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
 {
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
@@ -513,6 +555,32 @@ static int nfs4_xdr_dec_copy(struct rpc_rqst *rqstp,
 }
 
 /*
+ * Decode OFFLOAD_CANCEL response
+ */
+static int nfs4_xdr_dec_offload_cancel(struct rpc_rqst *rqstp,
+				       struct xdr_stream *xdr,
+				       void *data)
+{
+	struct nfs42_offload_status_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->osr_seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_offload_cancel(xdr, res);
+
+out:
+	return status;
+}
+
+/*
  * Decode DEALLOCATE request
  */
 static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5a8190e..95e35c8 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -9555,6 +9555,7 @@ static bool nfs4_match_stateid(const nfs4_stateid *s1,
 		| NFS_CAP_LGOPEN
 		| NFS_CAP_ALLOCATE
 		| NFS_CAP_COPY
+		| NFS_CAP_OFFLOAD_CANCEL
 		| NFS_CAP_DEALLOCATE
 		| NFS_CAP_SEEK
 		| NFS_CAP_LAYOUTSTATS
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index cd41d25..b7bde12 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7789,6 +7789,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	PROC42(LAYOUTSTATS,	enc_layoutstats,	dec_layoutstats),
 	PROC42(CLONE,		enc_clone,		dec_clone),
 	PROC42(COPY,		enc_copy,		dec_copy),
+	PROC42(OFFLOAD_CANCEL,	enc_offload_cancel,	dec_offload_cancel),
 	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 };
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 57ffaa2..c44b872 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -527,6 +527,7 @@ enum {
 	NFSPROC4_CLNT_LAYOUTSTATS,
 	NFSPROC4_CLNT_CLONE,
 	NFSPROC4_CLNT_COPY,
+	NFSPROC4_CLNT_OFFLOAD_CANCEL,
 
 	NFSPROC4_CLNT_LOOKUPP,
 };
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 2c18d61..fbc735f 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -255,5 +255,6 @@ struct nfs_server {
 #define NFS_CAP_LAYOUTSTATS	(1U << 22)
 #define NFS_CAP_CLONE		(1U << 23)
 #define NFS_CAP_COPY		(1U << 24)
+#define NFS_CAP_OFFLOAD_CANCEL	(1U << 25)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 3b7325c..85e928a 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1403,6 +1403,18 @@ struct nfs42_copy_res {
 	struct nfs_commitres		commit_res;
 };
 
+struct nfs42_offload_status_args {
+	struct nfs4_sequence_args	osa_seq_args;
+	struct nfs_fh			*osa_src_fh;
+	nfs4_stateid			osa_stateid;
+};
+
+struct nfs42_offload_status_res {
+	struct nfs4_sequence_res	osr_seq_res;
+	uint64_t			osr_count;
+	int				osr_status;
+};
+
 struct nfs42_seek_args {
 	struct nfs4_sequence_args	seq_args;
 
-- 
1.8.3.1

[PATCH v9 04/13] NFS COPY xdr handle async reply

[Olga Kornievskaia]

If server returns async reply, it must include a callback stateid,
wr_callback_id in the write_response4.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42xdr.c       | 22 ++++++++++++----------
 include/linux/nfs_xdr.h |  1 +
 2 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 09a540d0..205c356 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -389,21 +389,23 @@ static int decode_write_response(struct xdr_stream *xdr,
 				 struct nfs42_write_res *res)
 {
 	__be32 *p;
+	int status, count;
 
-	p = xdr_inline_decode(xdr, 4 + 8 + 4);
+	p = xdr_inline_decode(xdr, 4);
 	if (unlikely(!p))
 		goto out_overflow;
-
-	/*
-	 * We never use asynchronous mode, so warn if a server returns
-	 * a stateid.
-	 */
-	if (unlikely(*p != 0)) {
-		pr_err_once("%s: server has set unrequested "
-				"asynchronous mode\n", __func__);
+	count = be32_to_cpup(p);
+	if (count > 1)
 		return -EREMOTEIO;
+	else if (count == 1) {
+		status = decode_opaque_fixed(xdr, &res->stateid,
+				NFS4_STATEID_SIZE);
+		if (unlikely(status))
+			goto out_overflow;
 	}
-	p++;
+	p = xdr_inline_decode(xdr, 8 + 4);
+	if (unlikely(!p))
+		goto out_overflow;
 	p = xdr_decode_hyper(p, &res->count);
 	res->verifier.committed = be32_to_cpup(p);
 	return decode_verifier(xdr, &res->verifier.verifier);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 85e928a..06ddfa3 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1391,6 +1391,7 @@ struct nfs42_copy_args {
 };
 
 struct nfs42_write_res {
+	nfs4_stateid		stateid;
 	u64			count;
 	struct nfs_writeverf	verifier;
 };
-- 
1.8.3.1

[PATCH v9 05/13] NFS add support for asynchronous COPY

[Olga Kornievskaia]

Change xdr to always send COPY asynchronously.

Keep the list copies send in a list under a server structure.
Once copy is sent, it waits on a completion structure that will
be signalled by the callback thread that receives CB_OFFLOAD.

If CB_OFFLOAD returned an error and even if it returned partial
bytes, ignore them (as we can't commit without a verifier to
match) and return an error.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/callback_proc.c    | 38 +++++++++++++++++++++++++++++++-
 fs/nfs/client.c           |  1 +
 fs/nfs/nfs42proc.c        | 55 ++++++++++++++++++++++++++++++++++++++++++-----
 fs/nfs/nfs42xdr.c         |  8 ++++---
 include/linux/nfs_fs.h    |  9 ++++++++
 include/linux/nfs_fs_sb.h |  1 +
 include/linux/nfs_xdr.h   |  1 +
 7 files changed, 104 insertions(+), 9 deletions(-)

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 9647616..2c4a889 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -662,9 +662,45 @@ __be32 nfs4_callback_notify_lock(void *argp, void *resp,
 }
 #endif /* CONFIG_NFS_V4_1 */
 #ifdef CONFIG_NFS_V4_2
-__be32 nfs4_callback_offload(void *args, void *dummy,
+static void nfs4_copy_cb_args(struct nfs4_copy_state *cp_state,
+				struct cb_offloadargs *args)
+{
+	cp_state->count = args->wr_count;
+	cp_state->error = args->error;
+	if (!args->error) {
+		cp_state->verf.committed = args->wr_writeverf.committed;
+		memcpy(&cp_state->verf.verifier.data[0],
+			&args->wr_writeverf.verifier.data[0],
+			NFS4_VERIFIER_SIZE);
+	}
+}
+
+__be32 nfs4_callback_offload(void *data, void *dummy,
 			     struct cb_process_state *cps)
 {
+	struct cb_offloadargs *args = data;
+	struct nfs_server *server;
+	struct nfs4_copy_state *copy;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &cps->clp->cl_superblocks,
+				client_link) {
+		spin_lock(&server->nfs_client->cl_lock);
+		list_for_each_entry(copy, &server->ss_copies, copies) {
+			if (memcmp(args->coa_stateid.other,
+					copy->stateid.other,
+					sizeof(args->coa_stateid.other)))
+				continue;
+			nfs4_copy_cb_args(copy, args);
+			complete(&copy->completion);
+			spin_unlock(&server->nfs_client->cl_lock);
+			goto out;
+		}
+		spin_unlock(&server->nfs_client->cl_lock);
+	}
+out:
+	rcu_read_unlock();
+
 	return 0;
 }
 #endif /* CONFIG_NFS_V4_2 */
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 377a616..96d5f81 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -886,6 +886,7 @@ struct nfs_server *nfs_alloc_server(void)
 	INIT_LIST_HEAD(&server->delegations);
 	INIT_LIST_HEAD(&server->layouts);
 	INIT_LIST_HEAD(&server->state_owners_lru);
+	INIT_LIST_HEAD(&server->ss_copies);
 
 	atomic_set(&server->active, 0);
 
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 5f59b6f..023aea8 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -130,6 +130,37 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	return err;
 }
 
+static int handle_async_copy(struct nfs42_copy_res *res,
+			     struct nfs_server *server,
+			     struct file *src,
+			     struct file *dst,
+			     nfs4_stateid *src_stateid)
+{
+	struct nfs4_copy_state *copy;
+	int status = NFS4_OK;
+
+	copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS);
+	if (!copy)
+		return -ENOMEM;
+	memcpy(&copy->stateid, &res->write_res.stateid, NFS4_STATEID_SIZE);
+	init_completion(&copy->completion);
+
+	spin_lock(&server->nfs_client->cl_lock);
+	list_add_tail(&copy->copies, &server->ss_copies);
+	spin_unlock(&server->nfs_client->cl_lock);
+
+	wait_for_completion_interruptible(&copy->completion);
+	spin_lock(&server->nfs_client->cl_lock);
+	list_del_init(&copy->copies);
+	spin_unlock(&server->nfs_client->cl_lock);
+	res->write_res.count = copy->count;
+	memcpy(&res->write_res.verifier, &copy->verf, sizeof(copy->verf));
+	status = -copy->error;
+
+	kfree(copy);
+	return status;
+}
+
 static ssize_t _nfs42_proc_copy(struct file *src,
 				struct nfs_lock_context *src_lock,
 				struct file *dst,
@@ -168,9 +199,13 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 	if (status)
 		return status;
 
-	res->commit_res.verf = kzalloc(sizeof(struct nfs_writeverf), GFP_NOFS);
-	if (!res->commit_res.verf)
-		return -ENOMEM;
+	res->commit_res.verf = NULL;
+	if (args->sync) {
+		res->commit_res.verf =
+			kzalloc(sizeof(struct nfs_writeverf), GFP_NOFS);
+		if (!res->commit_res.verf)
+			return -ENOMEM;
+	}
 	status = nfs4_call_sync(server->client, server, &msg,
 				&args->seq_args, &res->seq_res, 0);
 	if (status == -ENOTSUPP)
@@ -178,18 +213,27 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 	if (status)
 		goto out;
 
-	if (nfs_write_verifier_cmp(&res->write_res.verifier.verifier,
+	if (args->sync &&
+		nfs_write_verifier_cmp(&res->write_res.verifier.verifier,
 				    &res->commit_res.verf->verifier)) {
 		status = -EAGAIN;
 		goto out;
 	}
 
+	if (!res->synchronous) {
+		status = handle_async_copy(res, server, src, dst,
+				&args->src_stateid);
+		if (status)
+			return status;
+	}
+
 	truncate_pagecache_range(dst_inode, pos_dst,
 				 pos_dst + res->write_res.count);
 
 	status = res->write_res.count;
 out:
-	kfree(res->commit_res.verf);
+	if (args->sync)
+		kfree(res->commit_res.verf);
 	return status;
 }
 
@@ -206,6 +250,7 @@ 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,
 	};
 	struct nfs42_copy_res res;
 	struct nfs4_exception src_exception = {
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 205c356..69f72ed 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -150,7 +150,7 @@ static void encode_copy(struct xdr_stream *xdr,
 	encode_uint64(xdr, args->count);
 
 	encode_uint32(xdr, 1); /* consecutive = true */
-	encode_uint32(xdr, 1); /* synchronous = true */
+	encode_uint32(xdr, args->sync);
 	encode_uint32(xdr, 0); /* src server list */
 }
 
@@ -273,7 +273,8 @@ static void nfs4_xdr_enc_copy(struct rpc_rqst *req,
 	encode_savefh(xdr, &hdr);
 	encode_putfh(xdr, args->dst_fh, &hdr);
 	encode_copy(xdr, args, &hdr);
-	encode_copy_commit(xdr, args, &hdr);
+	if (args->sync)
+		encode_copy_commit(xdr, args, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -551,7 +552,8 @@ static int nfs4_xdr_dec_copy(struct rpc_rqst *rqstp,
 	status = decode_copy(xdr, res);
 	if (status)
 		goto out;
-	status = decode_commit(xdr, &res->commit_res);
+	if (res->commit_res.verf)
+		status = decode_commit(xdr, &res->commit_res);
 out:
 	return status;
 }
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 2f129bb..645ad8e 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -185,6 +185,15 @@ struct nfs_inode {
 	struct inode		vfs_inode;
 };
 
+struct nfs4_copy_state {
+	struct list_head	copies;
+	nfs4_stateid		stateid;
+	struct completion	completion;
+	uint64_t		count;
+	struct nfs_writeverf	verf;
+	int			error;
+};
+
 /*
  * Access bit flags
  */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index fbc735f..f88952d 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -208,6 +208,7 @@ struct nfs_server {
 	struct list_head	state_owners_lru;
 	struct list_head	layouts;
 	struct list_head	delegations;
+	struct list_head	ss_copies;
 
 	unsigned long		mig_gen;
 	unsigned long		mig_status;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 06ddfa3..bd1c889 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1388,6 +1388,7 @@ struct nfs42_copy_args {
 	u64				dst_pos;
 
 	u64				count;
+	bool				sync;
 };
 
 struct nfs42_write_res {
-- 
1.8.3.1

[PATCH v9 06/13] NFS handle COPY reply CB_OFFLOAD call race

[Olga Kornievskaia]

It's possible that server replies back with CB_OFFLOAD call and
COPY reply at the same time such that client will process
CB_OFFLOAD before reply to COPY. For that keep a list of pending
callback stateids received and then before waiting on completion
check the pending list.

Cleanup any pending copies on the client shutdown.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/callback_proc.c    | 17 ++++++++++++++---
 fs/nfs/nfs42proc.c        | 22 ++++++++++++++++++++--
 fs/nfs/nfs4client.c       | 15 +++++++++++++++
 include/linux/nfs_fs_sb.h |  1 +
 4 files changed, 50 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 2c4a889..07f29c8 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -681,11 +681,12 @@ __be32 nfs4_callback_offload(void *data, void *dummy,
 	struct cb_offloadargs *args = data;
 	struct nfs_server *server;
 	struct nfs4_copy_state *copy;
+	bool found = false;
 
+	spin_lock(&cps->clp->cl_lock);
 	rcu_read_lock();
 	list_for_each_entry_rcu(server, &cps->clp->cl_superblocks,
 				client_link) {
-		spin_lock(&server->nfs_client->cl_lock);
 		list_for_each_entry(copy, &server->ss_copies, copies) {
 			if (memcmp(args->coa_stateid.other,
 					copy->stateid.other,
@@ -693,13 +694,23 @@ __be32 nfs4_callback_offload(void *data, void *dummy,
 				continue;
 			nfs4_copy_cb_args(copy, args);
 			complete(&copy->completion);
-			spin_unlock(&server->nfs_client->cl_lock);
+			found = true;
 			goto out;
 		}
-		spin_unlock(&server->nfs_client->cl_lock);
 	}
 out:
 	rcu_read_unlock();
+	if (!found) {
+		copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS);
+		if (!copy) {
+			spin_unlock(&cps->clp->cl_lock);
+			return htonl(NFS4ERR_SERVERFAULT);
+		}
+		memcpy(&copy->stateid, &args->coa_stateid, NFS4_STATEID_SIZE);
+		nfs4_copy_cb_args(copy, args);
+		list_add_tail(&copy->copies, &cps->clp->pending_cb_stateids);
+	}
+	spin_unlock(&cps->clp->cl_lock);
 
 	return 0;
 }
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 023aea8..c7d31f7 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -138,14 +138,31 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 {
 	struct nfs4_copy_state *copy;
 	int status = NFS4_OK;
+	bool found_pending = false;
+
+	spin_lock(&server->nfs_client->cl_lock);
+	list_for_each_entry(copy, &server->nfs_client->pending_cb_stateids,
+				copies) {
+		if (memcmp(&res->write_res.stateid, &copy->stateid,
+				NFS4_STATEID_SIZE))
+			continue;
+		found_pending = true;
+		list_del(&copy->copies);
+		break;
+	}
+	if (found_pending) {
+		spin_unlock(&server->nfs_client->cl_lock);
+		goto out;
+	}
 
 	copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS);
-	if (!copy)
+	if (!copy) {
+		spin_unlock(&server->nfs_client->cl_lock);
 		return -ENOMEM;
+	}
 	memcpy(&copy->stateid, &res->write_res.stateid, NFS4_STATEID_SIZE);
 	init_completion(&copy->completion);
 
-	spin_lock(&server->nfs_client->cl_lock);
 	list_add_tail(&copy->copies, &server->ss_copies);
 	spin_unlock(&server->nfs_client->cl_lock);
 
@@ -153,6 +170,7 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 	spin_lock(&server->nfs_client->cl_lock);
 	list_del_init(&copy->copies);
 	spin_unlock(&server->nfs_client->cl_lock);
+out:
 	res->write_res.count = copy->count;
 	memcpy(&res->write_res.verifier, &copy->verf, sizeof(copy->verf));
 	status = -copy->error;
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 9796314..d68ba73 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -156,9 +156,23 @@ struct rpc_clnt *
 	}
 }
 
+static void
+nfs4_cleanup_callback(struct nfs_client *clp)
+{
+	struct nfs4_copy_state *cp_state;
+
+	while (!list_empty(&clp->pending_cb_stateids)) {
+		cp_state = list_entry(clp->pending_cb_stateids.next,
+					struct nfs4_copy_state, copies);
+		list_del(&cp_state->copies);
+		kfree(cp_state);
+	}
+}
+
 void nfs41_shutdown_client(struct nfs_client *clp)
 {
 	if (nfs4_has_session(clp)) {
+		nfs4_cleanup_callback(clp);
 		nfs4_shutdown_ds_clients(clp);
 		nfs4_destroy_session(clp->cl_session);
 		nfs4_destroy_clientid(clp);
@@ -202,6 +216,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
 #if IS_ENABLED(CONFIG_NFS_V4_1)
 	init_waitqueue_head(&clp->cl_lock_waitq);
 #endif
+	INIT_LIST_HEAD(&clp->pending_cb_stateids);
 	return clp;
 
 error:
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index f88952d..bf39d9c 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -121,6 +121,7 @@ struct nfs_client {
 #endif
 
 	struct net		*cl_net;
+	struct list_head	pending_cb_stateids;
 };
 
 /*
-- 
1.8.3.1

[PATCH v9 07/13] NFS export nfs4_async_handle_error

[Olga Kornievskaia]

Make this function available to nfs42proc.c

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs4_fs.h  | 3 +++
 fs/nfs/nfs4proc.c | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 137e18a..a417aaa 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -273,6 +273,9 @@ int nfs4_replace_transport(struct nfs_server *server,
 
 /* nfs4proc.c */
 extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *);
+extern int nfs4_async_handle_error(struct rpc_task *task,
+				   struct nfs_server *server,
+				   struct nfs4_state *state, long *timeout);
 extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *,
 			  struct rpc_message *, struct nfs4_sequence_args *,
 			  struct nfs4_sequence_res *, int);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 95e35c8..d820284 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -586,7 +586,7 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_
 	return ret;
 }
 
-static int
+int
 nfs4_async_handle_error(struct rpc_task *task, struct nfs_server *server,
 			struct nfs4_state *state, long *timeout)
 {
-- 
1.8.3.1

[PATCH v9 08/13] NFS send OFFLOAD_CANCEL when COPY killed

[Olga Kornievskaia]

When COPY is killed by the user send OFFLOAD_CANCEL to server
processing the copy.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42proc.c | 91 +++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 90 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index c7d31f7..aeb9837 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -17,6 +17,7 @@
 #include "internal.h"
 
 #define NFSDBG_FACILITY NFSDBG_PROC
+static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *std);
 
 static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 		struct nfs_lock_context *lock, loff_t offset, loff_t len)
@@ -166,10 +167,15 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 	list_add_tail(&copy->copies, &server->ss_copies);
 	spin_unlock(&server->nfs_client->cl_lock);
 
-	wait_for_completion_interruptible(&copy->completion);
+	status = wait_for_completion_interruptible(&copy->completion);
 	spin_lock(&server->nfs_client->cl_lock);
 	list_del_init(&copy->copies);
 	spin_unlock(&server->nfs_client->cl_lock);
+	if (status == -ERESTARTSYS) {
+		nfs42_do_offload_cancel_async(dst, &copy->stateid);
+		kfree(copy);
+		return status;
+	}
 out:
 	res->write_res.count = copy->count;
 	memcpy(&res->write_res.verifier, &copy->verf, sizeof(copy->verf));
@@ -327,6 +333,89 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 	return err;
 }
 
+struct nfs42_offloadcancel_data {
+	struct nfs_server *seq_server;
+	struct nfs42_offload_status_args args;
+	struct nfs42_offload_status_res res;
+};
+
+static void nfs42_offload_cancel_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs42_offloadcancel_data *data = calldata;
+
+	nfs4_setup_sequence(data->seq_server->nfs_client,
+				&data->args.osa_seq_args,
+				&data->res.osr_seq_res, task);
+}
+
+static void nfs42_offload_cancel_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs42_offloadcancel_data *data = calldata;
+
+	nfs41_sequence_done(task, &data->res.osr_seq_res);
+	if (task->tk_status &&
+		nfs4_async_handle_error(task, data->seq_server, NULL,
+			NULL) == -EAGAIN)
+		rpc_restart_call_prepare(task);
+}
+
+static void nfs42_free_offloadcancel_data(void *data)
+{
+	kfree(data);
+}
+
+static const struct rpc_call_ops nfs42_offload_cancel_ops = {
+	.rpc_call_prepare = nfs42_offload_cancel_prepare,
+	.rpc_call_done = nfs42_offload_cancel_done,
+	.rpc_release = nfs42_free_offloadcancel_data,
+};
+
+static int nfs42_do_offload_cancel_async(struct file *dst,
+					 nfs4_stateid *stateid)
+{
+	struct nfs_server *dst_server = NFS_SERVER(file_inode(dst));
+	struct nfs42_offloadcancel_data *data = NULL;
+	struct nfs_open_context *ctx = nfs_file_open_context(dst);
+	struct rpc_task *task;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OFFLOAD_CANCEL],
+		.rpc_cred = ctx->cred,
+	};
+	struct rpc_task_setup task_setup_data = {
+		.rpc_client = dst_server->client,
+		.rpc_message = &msg,
+		.callback_ops = &nfs42_offload_cancel_ops,
+		.workqueue = nfsiod_workqueue,
+		.flags = RPC_TASK_ASYNC,
+	};
+	int status;
+
+	if (!(dst_server->caps & NFS_CAP_OFFLOAD_CANCEL))
+		return -EOPNOTSUPP;
+
+	data = kzalloc(sizeof(struct nfs42_offloadcancel_data), GFP_NOFS);
+	if (data == NULL)
+		return -ENOMEM;
+
+	data->seq_server = dst_server;
+	data->args.osa_src_fh = NFS_FH(file_inode(dst));
+	memcpy(&data->args.osa_stateid, stateid,
+		sizeof(data->args.osa_stateid));
+	msg.rpc_argp = &data->args;
+	msg.rpc_resp = &data->res;
+	task_setup_data.callback_data = data;
+	nfs4_init_sequence(&data->args.osa_seq_args, &data->res.osr_seq_res,
+			   1, 0);
+	task = rpc_run_task(&task_setup_data);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	status = rpc_wait_for_completion_task(task);
+	if (status == -ENOTSUPP)
+		dst_server->caps &= ~NFS_CAP_OFFLOAD_CANCEL;
+	rpc_put_task(task);
+	return status;
+}
+
 static loff_t _nfs42_proc_llseek(struct file *filep,
 		struct nfs_lock_context *lock, loff_t offset, int whence)
 {
-- 
1.8.3.1

[PATCH v9 09/13] NFS handle COPY ERR_OFFLOAD_NO_REQS

[Olga Kornievskaia]

If client sent async COPY and server replied with
ERR_OFFLOAD_NO_REQS, client should retry with a synchronous copy.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42proc.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index aeb9837..77451be 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -316,7 +316,11 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 		if (err == -ENOTSUPP) {
 			err = -EOPNOTSUPP;
 			break;
-		} if (err == -EAGAIN) {
+		} else if (err == -EAGAIN) {
+			dst_exception.retry = 1;
+			continue;
+		} else if (err == -NFS4ERR_OFFLOAD_NO_REQS && !args.sync) {
+			args.sync = true;
 			dst_exception.retry = 1;
 			continue;
 		}
-- 
1.8.3.1

[PATCH v9 10/13] NFS add a simple sync nfs4_proc_commit after async COPY

[Olga Kornievskaia]

A COPY with unstable write data needs a simple sync commit.
Filehandle value is gotten as a part of the inner loop so in
case of a reboot retry it should get the new value.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42proc.c | 31 +++++++++++++++++++++++++++++++
 fs/nfs/nfs4_fs.h   |  2 +-
 fs/nfs/nfs4proc.c  | 34 ++++++++++++++++++++++++++++++++++
 3 files changed, 66 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 77451be..d158526 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -185,6 +185,30 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 	return status;
 }
 
+static int process_copy_commit(struct file *dst, loff_t pos_dst,
+			       struct nfs42_copy_res *res)
+{
+	struct nfs_commitres cres;
+	int status = -ENOMEM;
+
+	cres.verf = kzalloc(sizeof(struct nfs_writeverf), GFP_NOFS);
+	if (!cres.verf)
+		goto out;
+
+	status = nfs4_proc_commit(dst, pos_dst, res->write_res.count, &cres);
+	if (status)
+		goto out_free;
+	if (nfs_write_verifier_cmp(&res->write_res.verifier.verifier,
+				    &cres.verf->verifier)) {
+		dprintk("commit verf differs from copy verf\n");
+		status = -EAGAIN;
+	}
+out_free:
+	kfree(cres.verf);
+out:
+	return status;
+}
+
 static ssize_t _nfs42_proc_copy(struct file *src,
 				struct nfs_lock_context *src_lock,
 				struct file *dst,
@@ -251,6 +275,13 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 			return status;
 	}
 
+	if ((!res->synchronous || !args->sync) &&
+			res->write_res.verifier.committed != NFS_FILE_SYNC) {
+		status = process_copy_commit(dst, pos_dst, res);
+		if (status)
+			return status;
+	}
+
 	truncate_pagecache_range(dst_inode, pos_dst,
 				 pos_dst + res->write_res.count);
 
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index a417aaa..e87d414 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -508,7 +508,7 @@ extern int nfs4_sequence_done(struct rpc_task *task,
 			      struct nfs4_sequence_res *res);
 
 extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp);
-
+extern int nfs4_proc_commit(struct file *dst, __u64 offset, __u32 count, struct nfs_commitres *res);
 extern const nfs4_stateid zero_stateid;
 extern const nfs4_stateid invalid_stateid;
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d820284..ff49e87 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5074,6 +5074,40 @@ static void nfs4_proc_commit_setup(struct nfs_commit_data *data, struct rpc_mess
 	nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_COMMIT, clnt, msg);
 }
 
+static int _nfs4_proc_commit(struct file *dst, struct nfs_commitargs *args,
+				struct nfs_commitres *res)
+{
+	struct inode *dst_inode = file_inode(dst);
+	struct nfs_server *server = NFS_SERVER(dst_inode);
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT],
+		.rpc_argp = args,
+		.rpc_resp = res,
+	};
+
+	args->fh = NFS_FH(dst_inode);
+	return nfs4_call_sync(server->client, server, &msg,
+			&args->seq_args, &res->seq_res, 1);
+}
+
+int nfs4_proc_commit(struct file *dst, __u64 offset, __u32 count, struct nfs_commitres *res)
+{
+	struct nfs_commitargs args = {
+		.offset = offset,
+		.count = count,
+	};
+	struct nfs_server *dst_server = NFS_SERVER(file_inode(dst));
+	struct nfs4_exception exception = { };
+	int status;
+
+	do {
+		status = _nfs4_proc_commit(dst, &args, res);
+		status = nfs4_handle_exception(dst_server, status, &exception);
+	} while (exception.retry);
+
+	return status;
+}
+
 struct nfs4_renewdata {
 	struct nfs_client	*client;
 	unsigned long		timestamp;
-- 
1.8.3.1

[PATCH v9 11/13] NFS recover from destination server reboot for copies

[Olga Kornievskaia]

Mark the destination state to indicate a server-side copy is
happening. On detecting a reboot and recovering open state check
if any state is engaged in a server-side copy, if so, find the
copy and mark it and then signal the waiting thread. Upon wakeup,
if copy was marked then propage EAGAIN to the nfsd_copy_file_range
and restart the copy from scratch.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42proc.c     | 16 +++++++++++++---
 fs/nfs/nfs4_fs.h       |  3 +++
 fs/nfs/nfs4file.c      |  9 +++++++--
 fs/nfs/nfs4state.c     | 15 +++++++++++++++
 include/linux/nfs_fs.h |  2 ++
 5 files changed, 40 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index d158526..ac5b784 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -140,6 +140,7 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 	struct nfs4_copy_state *copy;
 	int status = NFS4_OK;
 	bool found_pending = false;
+	struct nfs_open_context *ctx = nfs_file_open_context(dst);
 
 	spin_lock(&server->nfs_client->cl_lock);
 	list_for_each_entry(copy, &server->nfs_client->pending_cb_stateids,
@@ -163,6 +164,7 @@ 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;
 
 	list_add_tail(&copy->copies, &server->ss_copies);
 	spin_unlock(&server->nfs_client->cl_lock);
@@ -172,9 +174,10 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 	list_del_init(&copy->copies);
 	spin_unlock(&server->nfs_client->cl_lock);
 	if (status == -ERESTARTSYS) {
-		nfs42_do_offload_cancel_async(dst, &copy->stateid);
-		kfree(copy);
-		return status;
+		goto out_cancel;
+	} else if (copy->flags) {
+		status = -EAGAIN;
+		goto out_cancel;
 	}
 out:
 	res->write_res.count = copy->count;
@@ -183,6 +186,10 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 
 	kfree(copy);
 	return status;
+out_cancel:
+	nfs42_do_offload_cancel_async(dst, &copy->stateid);
+	kfree(copy);
+	return status;
 }
 
 static int process_copy_commit(struct file *dst, loff_t pos_dst,
@@ -254,6 +261,9 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 		if (!res->commit_res.verf)
 			return -ENOMEM;
 	}
+	set_bit(NFS_CLNT_DST_SSC_COPY_STATE,
+		&dst_lock->open_context->state->flags);
+
 	status = nfs4_call_sync(server->client, server, &msg,
 				&args->seq_args, &res->seq_res, 0);
 	if (status == -ENOTSUPP)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index e87d414..542b2fc 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -163,6 +163,9 @@ enum {
 	NFS_STATE_RECOVERY_FAILED,	/* OPEN stateid state recovery failed */
 	NFS_STATE_MAY_NOTIFY_LOCK,	/* server may CB_NOTIFY_LOCK */
 	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*/
+#endif /* CONFIG_NFS_V4_2 */
 };
 
 struct nfs4_state {
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 6b3b372..eaef5fa 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -133,10 +133,15 @@ 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)
 {
+	ssize_t ret;
+
 	if (file_inode(file_in) == file_inode(file_out))
 		return -EINVAL;
-
-	return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+retry:
+	ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+	if (ret == -EAGAIN)
+		goto retry;
+	return ret;
 }
 
 static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 2bf2eaa..6ce6782 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1590,6 +1590,21 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 					&state->flags);
 				nfs4_put_open_state(state);
 				spin_lock(&sp->so_lock);
+#ifdef CONFIG_NFS_V4_2
+				if (test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags)) {
+					struct nfs4_copy_state *copy;
+
+					spin_lock(&sp->so_server->nfs_client->cl_lock);
+					list_for_each_entry(copy, &sp->so_server->ss_copies, copies) {
+						if (memcmp(&state->stateid.other, &copy->parent_state->stateid.other, NFS4_STATEID_SIZE))
+							continue;
+						copy->flags = 1;
+						complete(&copy->completion);
+						break;
+					}
+					spin_unlock(&sp->so_server->nfs_client->cl_lock);
+				}
+#endif /* CONFIG_NFS_V4_2 */
 				goto restart;
 			}
 		}
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 645ad8e..a0831e9 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -192,6 +192,8 @@ struct nfs4_copy_state {
 	uint64_t		count;
 	struct nfs_writeverf	verf;
 	int			error;
+	int			flags;
+	struct nfs4_state	*parent_state;
 };
 
 /*
-- 
1.8.3.1

[PATCH v9 12/13] NFS OFFLOAD_STATUS xdr

[Olga Kornievskaia]

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42xdr.c         | 91 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4proc.c         |  1 +
 fs/nfs/nfs4xdr.c          |  1 +
 include/linux/nfs4.h      |  1 +
 include/linux/nfs_fs_sb.h |  1 +
 5 files changed, 95 insertions(+)

diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 69f72ed..f279552 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -29,6 +29,11 @@
 #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_offload_status_maxsz	(op_encode_hdr_maxsz + \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE))
+#define decode_offload_status_maxsz	(op_decode_hdr_maxsz + \
+					 2 /* osr_count */ + \
+					 1 + 1 /* osr_complete<1> */)
 #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
@@ -84,6 +89,12 @@
 #define NFS4_dec_offload_cancel_sz	(compound_decode_hdr_maxsz + \
 					 decode_putfh_maxsz + \
 					 decode_offload_cancel_maxsz)
+#define NFS4_enc_offload_status_sz	(compound_encode_hdr_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_offload_status_maxsz)
+#define NFS4_dec_offload_status_sz	(compound_decode_hdr_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_offload_status_maxsz)
 #define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
 					 encode_deallocate_maxsz + \
@@ -162,6 +173,14 @@ static void encode_offload_cancel(struct xdr_stream *xdr,
 	encode_nfs4_stateid(xdr, &args->osa_stateid);
 }
 
+static void encode_offload_status(struct xdr_stream *xdr,
+				  const struct nfs42_offload_status_args *args,
+				  struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_OFFLOAD_STATUS, decode_offload_status_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->osa_stateid);
+}
+
 static void encode_deallocate(struct xdr_stream *xdr,
 			      const struct nfs42_falloc_args *args,
 			      struct compound_hdr *hdr)
@@ -298,6 +317,25 @@ static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req,
 }
 
 /*
+ * Encode OFFLOAD_STATUS request
+ */
+static void nfs4_xdr_enc_offload_status(struct rpc_rqst *req,
+					struct xdr_stream *xdr,
+					const void *data)
+{
+	const struct nfs42_offload_status_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->osa_seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->osa_seq_args, &hdr);
+	encode_putfh(xdr, args->osa_src_fh, &hdr);
+	encode_offload_status(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
  * Encode DEALLOCATE request
  */
 static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
@@ -458,6 +496,33 @@ static int decode_offload_cancel(struct xdr_stream *xdr,
 	return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL);
 }
 
+static int decode_offload_status(struct xdr_stream *xdr,
+				 struct nfs42_offload_status_res *res)
+{
+	__be32 *p;
+	uint32_t count;
+	int status;
+
+	status = decode_op_hdr(xdr, OP_OFFLOAD_STATUS);
+	if (status)
+		return status;
+	p = xdr_inline_decode(xdr, 8 + 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	p = xdr_decode_hyper(p, &res->osr_count);
+	count = be32_to_cpup(p++);
+	if (count) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			goto out_overflow;
+		res->osr_status = nfs4_stat_to_errno(be32_to_cpup(p));
+	}
+	return 0;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
 static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
 {
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
@@ -585,6 +650,32 @@ static int nfs4_xdr_dec_offload_cancel(struct rpc_rqst *rqstp,
 }
 
 /*
+ * Decode OFFLOAD_STATUS response
+ */
+static int nfs4_xdr_dec_offload_status(struct rpc_rqst *rqstp,
+				       struct xdr_stream *xdr,
+				       void *data)
+{
+	struct nfs42_offload_status_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->osr_seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_offload_status(xdr, res);
+
+out:
+	return status;
+}
+
+/*
  * Decode DEALLOCATE request
  */
 static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ff49e87..bc6e940 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -9590,6 +9590,7 @@ static bool nfs4_match_stateid(const nfs4_stateid *s1,
 		| NFS_CAP_ALLOCATE
 		| NFS_CAP_COPY
 		| NFS_CAP_OFFLOAD_CANCEL
+		| NFS_CAP_OFFLOAD_STATUS
 		| NFS_CAP_DEALLOCATE
 		| NFS_CAP_SEEK
 		| NFS_CAP_LAYOUTSTATS
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index b7bde12..b51cb1b 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7790,6 +7790,7 @@ 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(OFFLOAD_STATUS,	enc_offload_status,	dec_offload_status),
 	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 };
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index c44b872..cd6797be 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -528,6 +528,7 @@ enum {
 	NFSPROC4_CLNT_CLONE,
 	NFSPROC4_CLNT_COPY,
 	NFSPROC4_CLNT_OFFLOAD_CANCEL,
+	NFSPROC4_CLNT_OFFLOAD_STATUS,
 
 	NFSPROC4_CLNT_LOOKUPP,
 };
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index bf39d9c..3430ab0 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -258,5 +258,6 @@ struct nfs_server {
 #define NFS_CAP_CLONE		(1U << 23)
 #define NFS_CAP_COPY		(1U << 24)
 #define NFS_CAP_OFFLOAD_CANCEL	(1U << 25)
+#define NFS_CAP_OFFLOAD_STATUS	(1U << 26)
 
 #endif
-- 
1.8.3.1

[PATCH v9 13/13] NFS OFFLOAD_STATUS op

[Olga Kornievskaia]

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42.h     |  5 ++++-
 fs/nfs/nfs42proc.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 19ec38f8..93e9d19 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -12,6 +12,7 @@
  */
 #define PNFS_LAYOUTSTATS_MAXDEV (4)
 
+#if defined(CONFIG_NFS_V4_2)
 /* nfs4.2proc.c */
 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);
@@ -20,5 +21,7 @@
 int nfs42_proc_layoutstats_generic(struct nfs_server *,
 				   struct nfs42_layoutstat_data *);
 int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t);
-
+int nfs42_proc_offload_status(struct file *, nfs4_stateid *,
+			      struct nfs42_offload_status_res *);
+#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 ac5b784..3e79c0b 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -461,6 +461,49 @@ static int nfs42_do_offload_cancel_async(struct file *dst,
 	return status;
 }
 
+int _nfs42_proc_offload_status(struct file *dst, nfs4_stateid *stateid,
+				struct nfs42_offload_status_res *res)
+{
+	struct nfs42_offload_status_args args = {
+		.osa_src_fh = NFS_FH(file_inode(dst)),
+	};
+	struct nfs_server *dst_server = NFS_SERVER(file_inode(dst));
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OFFLOAD_STATUS],
+		.rpc_resp = res,
+		.rpc_argp = &args,
+	};
+	int status;
+
+	memcpy(&args.osa_stateid, stateid, sizeof(args.osa_stateid));
+	status = nfs4_call_sync(dst_server->client, dst_server, &msg,
+				&args.osa_seq_args, &res->osr_seq_res, 0);
+	if (status == -ENOTSUPP)
+		dst_server->caps &= ~NFS_CAP_OFFLOAD_STATUS;
+
+	return status;
+}
+
+int nfs42_proc_offload_status(struct file *dst, nfs4_stateid *stateid,
+				struct nfs42_offload_status_res *res)
+{
+	struct nfs_server *dst_server = NFS_SERVER(file_inode(dst));
+	struct nfs4_exception exception = { };
+	int status;
+
+	if (!(dst_server->caps & NFS_CAP_OFFLOAD_STATUS))
+		return -EOPNOTSUPP;
+
+	do {
+		status = _nfs42_proc_offload_status(dst, stateid, res);
+		if (status == -ENOTSUPP)
+			return -EOPNOTSUPP;
+		status = nfs4_handle_exception(dst_server, status, &exception);
+	} while (exception.retry);
+
+	return status;
+}
+
 static loff_t _nfs42_proc_llseek(struct file *filep,
 		struct nfs_lock_context *lock, loff_t offset, int whence)
 {
-- 
1.8.3.1