From 78fe0f41d9937ee62817912ac8d627e06243c269 Mon Sep 17 00:00:00 2001
From: Weston Andros Adamson <dros@netapp.com>
Date: Tue, 31 May 2011 19:05:47 -0400
Subject: NFS: use scope from exchange_id to skip reclaim

can be skipped if the "eir_server_scope" from the exchange_id proc differs from
previous calls.

Also, in the future server_scope will be useful for determining whether client
trunking is available

Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

(limited to 'fs/nfs/nfs4proc.c')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5879b23e0c9..5f4912f7228 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4781,6 +4781,16 @@ out_inval:
 	return -NFS4ERR_INVAL;
 }
 
+static bool
+nfs41_same_server_scope(struct server_scope *a, struct server_scope *b)
+{
+	if (a->server_scope_sz == b->server_scope_sz &&
+	    memcmp(a->server_scope, b->server_scope, a->server_scope_sz) == 0)
+		return true;
+
+	return false;
+}
+
 /*
  * nfs4_proc_exchange_id()
  *
@@ -4823,9 +4833,31 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 				init_utsname()->domainname,
 				clp->cl_rpcclient->cl_auth->au_flavor);
 
+	res.server_scope = kzalloc(sizeof(struct server_scope), GFP_KERNEL);
+	if (unlikely(!res.server_scope))
+		return -ENOMEM;
+
 	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	if (!status)
 		status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
+
+	if (!status) {
+		if (clp->server_scope &&
+		    !nfs41_same_server_scope(clp->server_scope,
+					     res.server_scope)) {
+			dprintk("%s: server_scope mismatch detected\n",
+				__func__);
+			set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state);
+			kfree(clp->server_scope);
+			clp->server_scope = NULL;
+		}
+
+		if (!clp->server_scope)
+			clp->server_scope = res.server_scope;
+		else
+			kfree(res.server_scope);
+	}
+
 	dprintk("<-- %s status= %d\n", __func__, status);
 	return status;
 }
-- 
cgit v1.2.3-70-g09d2


From fca78d6d2c77f87d7dbee89bbe4836a44da881e2 Mon Sep 17 00:00:00 2001
From: Bryan Schumaker <bjschuma@netapp.com>
Date: Thu, 2 Jun 2011 14:59:07 -0400
Subject: NFS: Add SECINFO_NO_NAME procedure

If the client is using NFS v4.1, then we can use SECINFO_NO_NAME to find
the secflavor for the initial mount.  If the server doesn't support
SECINFO_NO_NAME then I fall back on the "guess and check" method used
for v4.0 mounts.

Signed-off-by: Bryan Schumaker <bjschuma@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/internal.h       |  3 ++
 fs/nfs/namespace.c      |  2 +-
 fs/nfs/nfs4_fs.h        |  2 ++
 fs/nfs/nfs4proc.c       | 84 ++++++++++++++++++++++++++++++++++++++++++++++++-
 fs/nfs/nfs4xdr.c        | 68 +++++++++++++++++++++++++++++++++++++++
 include/linux/nfs4.h    |  1 +
 include/linux/nfs_xdr.h |  8 +++++
 7 files changed, 166 insertions(+), 2 deletions(-)

(limited to 'fs/nfs/nfs4proc.c')

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2a55347a2da..fc017eadfe0 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -277,6 +277,9 @@ extern void nfs_sb_deactive(struct super_block *sb);
 extern char *nfs_path(char **p, struct dentry *dentry,
 		      char *buffer, ssize_t buflen);
 extern struct vfsmount *nfs_d_automount(struct path *path);
+#ifdef CONFIG_NFS_V4
+rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
+#endif
 
 /* getroot.c */
 extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *,
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 1f063bacd28..8102391bb37 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -119,7 +119,7 @@ Elong:
 }
 
 #ifdef CONFIG_NFS_V4
-static rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
+rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
 {
 	struct gss_api_mech *mech;
 	struct xdr_netobj oid;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index b47f0d4710f..c30aed2c70f 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -67,6 +67,8 @@ struct nfs4_minor_version_ops {
 			int cache_reply);
 	int	(*validate_stateid)(struct nfs_delegation *,
 			const nfs4_stateid *);
+	int	(*find_root_sec)(struct nfs_server *, struct nfs_fh *,
+			struct nfs_fsinfo *);
 	const struct nfs4_state_recovery_ops *reboot_recovery_ops;
 	const struct nfs4_state_recovery_ops *nograce_recovery_ops;
 	const struct nfs4_state_maintenance_ops *state_renewal_ops;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5f4912f7228..892bff53f61 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2251,13 +2251,14 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
 			      struct nfs_fsinfo *info)
 {
+	int minor_version = server->nfs_client->cl_minorversion;
 	int status = nfs4_lookup_root(server, fhandle, info);
 	if ((status == -NFS4ERR_WRONGSEC) && !(server->flags & NFS_MOUNT_SECFLAVOUR))
 		/*
 		 * A status of -NFS4ERR_WRONGSEC will be mapped to -EPERM
 		 * by nfs4_map_errors() as this function exits.
 		 */
-		status = nfs4_find_root_sec(server, fhandle, info);
+		status = nfs_v4_minor_ops[minor_version]->find_root_sec(server, fhandle, info);
 	if (status == 0)
 		status = nfs4_server_capabilities(server, fhandle);
 	if (status == 0)
@@ -5935,6 +5936,85 @@ out:
 	rpc_put_task(task);
 	return status;
 }
+
+static int
+_nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
+		    struct nfs_fsinfo *info, struct nfs4_secinfo_flavors *flavors)
+{
+	struct nfs41_secinfo_no_name_args args = {
+		.style = SECINFO_STYLE_CURRENT_FH,
+	};
+	struct nfs4_secinfo_res res = {
+		.flavors = flavors,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SECINFO_NO_NAME],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
+}
+
+static int
+nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
+			   struct nfs_fsinfo *info, struct nfs4_secinfo_flavors *flavors)
+{
+	struct nfs4_exception exception = { };
+	int err;
+	do {
+		err = _nfs41_proc_secinfo_no_name(server, fhandle, info, flavors);
+		switch (err) {
+		case 0:
+		case -NFS4ERR_WRONGSEC:
+		case -NFS4ERR_NOTSUPP:
+			break;
+		default:
+			err = nfs4_handle_exception(server, err, &exception);
+		}
+	} while (exception.retry);
+	return err;
+}
+
+static int
+nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
+		    struct nfs_fsinfo *info)
+{
+	int err;
+	struct page *page;
+	rpc_authflavor_t flavor;
+	struct nfs4_secinfo_flavors *flavors;
+
+	page = alloc_page(GFP_KERNEL);
+	if (!page) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	flavors = page_address(page);
+	err = nfs41_proc_secinfo_no_name(server, fhandle, info, flavors);
+
+	/*
+	 * Fall back on "guess and check" method if
+	 * the server doesn't support SECINFO_NO_NAME
+	 */
+	if (err == -NFS4ERR_WRONGSEC || err == -NFS4ERR_NOTSUPP) {
+		err = nfs4_find_root_sec(server, fhandle, info);
+		goto out_freepage;
+	}
+	if (err)
+		goto out_freepage;
+
+	flavor = nfs_find_best_sec(flavors);
+	if (err == 0)
+		err = nfs4_lookup_root_sec(server, fhandle, info, flavor);
+
+out_freepage:
+	put_page(page);
+	if (err == -EACCES)
+		return -EPERM;
+out:
+	return err;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
@@ -5996,6 +6076,7 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
 	.minor_version = 0,
 	.call_sync = _nfs4_call_sync,
 	.validate_stateid = nfs4_validate_delegation_stateid,
+	.find_root_sec = nfs4_find_root_sec,
 	.reboot_recovery_ops = &nfs40_reboot_recovery_ops,
 	.nograce_recovery_ops = &nfs40_nograce_recovery_ops,
 	.state_renewal_ops = &nfs40_state_renewal_ops,
@@ -6006,6 +6087,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 	.minor_version = 1,
 	.call_sync = _nfs4_call_sync_session,
 	.validate_stateid = nfs41_validate_delegation_stateid,
+	.find_root_sec = nfs41_find_root_sec,
 	.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
 	.nograce_recovery_ops = &nfs41_nograce_recovery_ops,
 	.state_renewal_ops = &nfs41_state_renewal_ops,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 1555c74dd33..c8c069a6319 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -343,6 +343,8 @@ static int nfs4_stat_to_errno(int);
 				1 /* FIXME: opaque lrf_body always empty at the moment */)
 #define decode_layoutreturn_maxsz (op_decode_hdr_maxsz + \
 				1 + decode_stateid_maxsz)
+#define encode_secinfo_no_name_maxsz (op_encode_hdr_maxsz + 1)
+#define decode_secinfo_no_name_maxsz decode_secinfo_maxsz
 #else /* CONFIG_NFS_V4_1 */
 #define encode_sequence_maxsz	0
 #define decode_sequence_maxsz	0
@@ -772,6 +774,14 @@ static int nfs4_stat_to_errno(int);
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_layoutreturn_maxsz)
+#define NFS4_enc_secinfo_no_name_sz	(compound_encode_hdr_maxsz + \
+					encode_sequence_maxsz + \
+					encode_putrootfh_maxsz +\
+					encode_secinfo_no_name_maxsz)
+#define NFS4_dec_secinfo_no_name_sz	(compound_decode_hdr_maxsz + \
+					decode_sequence_maxsz + \
+					decode_putrootfh_maxsz + \
+					decode_secinfo_no_name_maxsz)
 
 const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
 				      compound_encode_hdr_maxsz +
@@ -1938,6 +1948,20 @@ encode_layoutreturn(struct xdr_stream *xdr,
 	hdr->nops++;
 	hdr->replen += decode_layoutreturn_maxsz;
 }
+
+static int
+encode_secinfo_no_name(struct xdr_stream *xdr,
+		       const struct nfs41_secinfo_no_name_args *args,
+		       struct compound_hdr *hdr)
+{
+	__be32 *p;
+	p = reserve_space(xdr, 8);
+	*p++ = cpu_to_be32(OP_SECINFO_NO_NAME);
+	*p++ = cpu_to_be32(args->style);
+	hdr->nops++;
+	hdr->replen += decode_secinfo_no_name_maxsz;
+	return 0;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -2790,6 +2814,25 @@ static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req,
 	encode_layoutreturn(xdr, args, &hdr);
 	encode_nops(&hdr);
 }
+
+/*
+ * Encode SECINFO_NO_NAME request
+ */
+static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req,
+					struct xdr_stream *xdr,
+					struct nfs41_secinfo_no_name_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putrootfh(xdr, &hdr);
+	encode_secinfo_no_name(xdr, args, &hdr);
+	encode_nops(&hdr);
+	return 0;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
@@ -6467,6 +6510,30 @@ static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp,
 out:
 	return status;
 }
+
+/*
+ * Decode SECINFO_NO_NAME response
+ */
+static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp,
+					struct xdr_stream *xdr,
+					struct nfs4_secinfo_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putrootfh(xdr);
+	if (status)
+		goto out;
+	status = decode_secinfo(xdr, res);
+out:
+	return status;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /**
@@ -6669,6 +6736,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(LAYOUTGET,		enc_layoutget,		dec_layoutget),
 	PROC(LAYOUTCOMMIT,	enc_layoutcommit,	dec_layoutcommit),
 	PROC(LAYOUTRETURN,	enc_layoutreturn,	dec_layoutreturn),
+	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
 #endif /* CONFIG_NFS_V4_1 */
 };
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 504b289ba68..7cc7d5745be 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -563,6 +563,7 @@ enum {
 	NFSPROC4_CLNT_GETDEVICEINFO,
 	NFSPROC4_CLNT_LAYOUTCOMMIT,
 	NFSPROC4_CLNT_LAYOUTRETURN,
+	NFSPROC4_CLNT_SECINFO_NO_NAME,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index c4d98df884f..7159e1da63b 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1084,6 +1084,14 @@ struct nfs41_reclaim_complete_args {
 struct nfs41_reclaim_complete_res {
 	struct nfs4_sequence_res	seq_res;
 };
+
+#define SECINFO_STYLE_CURRENT_FH 0
+#define SECINFO_STYLE_PARENT 1
+struct nfs41_secinfo_no_name_args {
+	int				style;
+	struct nfs4_sequence_args	seq_args;
+};
+
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs_page;
-- 
cgit v1.2.3-70-g09d2


From 7d9747947ae66d8f6a9a9a023a3a5e28df6a536e Mon Sep 17 00:00:00 2001
From: Bryan Schumaker <bjschuma@netapp.com>
Date: Thu, 2 Jun 2011 14:59:08 -0400
Subject: NFS: Added TEST_STATEID call

This patch adds in the xdr for doing a TEST_STATEID call with a single
stateid. RFC 5661 allows multiple stateids to be tested in a single
call, but only testing one keeps things simpler for now.

Signed-off-by: Bryan Schumaker <bjschuma@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       | 28 +++++++++++++++
 fs/nfs/nfs4xdr.c        | 91 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/nfs4.h    |  1 +
 include/linux/nfs_xdr.h | 10 ++++++
 4 files changed, 130 insertions(+)

(limited to 'fs/nfs/nfs4proc.c')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 892bff53f61..5612ba997db 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6015,6 +6015,34 @@ out_freepage:
 out:
 	return err;
 }
+static int _nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *state)
+{
+	int status;
+	struct nfs41_test_stateid_args args = {
+		.stateid = &state->stateid,
+	};
+	struct nfs41_test_stateid_res res;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_TEST_STATEID],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	args.seq_args.sa_session = res.seq_res.sr_session = NULL;
+	status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 0, 1);
+	return status;
+}
+
+static int nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *state)
+{
+	struct nfs4_exception exception = { };
+	int err;
+	do {
+		err = nfs4_handle_exception(server,
+				_nfs41_test_stateid(server, state),
+				&exception);
+	} while (exception.retry);
+	return err;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c8c069a6319..7d914d9e758 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -345,6 +345,9 @@ static int nfs4_stat_to_errno(int);
 				1 + decode_stateid_maxsz)
 #define encode_secinfo_no_name_maxsz (op_encode_hdr_maxsz + 1)
 #define decode_secinfo_no_name_maxsz decode_secinfo_maxsz
+#define encode_test_stateid_maxsz	(op_encode_hdr_maxsz + 2 + \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE))
+#define decode_test_stateid_maxsz	(op_decode_hdr_maxsz + 2 + 1)
 #else /* CONFIG_NFS_V4_1 */
 #define encode_sequence_maxsz	0
 #define decode_sequence_maxsz	0
@@ -782,6 +785,12 @@ static int nfs4_stat_to_errno(int);
 					decode_sequence_maxsz + \
 					decode_putrootfh_maxsz + \
 					decode_secinfo_no_name_maxsz)
+#define NFS4_enc_test_stateid_sz	(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_test_stateid_maxsz)
+#define NFS4_dec_test_stateid_sz	(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_test_stateid_maxsz)
 
 const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
 				      compound_encode_hdr_maxsz +
@@ -1962,6 +1971,20 @@ encode_secinfo_no_name(struct xdr_stream *xdr,
 	hdr->replen += decode_secinfo_no_name_maxsz;
 	return 0;
 }
+
+static void encode_test_stateid(struct xdr_stream *xdr,
+				struct nfs41_test_stateid_args *args,
+				struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	p = reserve_space(xdr, 8 + NFS4_STATEID_SIZE);
+	*p++ = cpu_to_be32(OP_TEST_STATEID);
+	*p++ = cpu_to_be32(1);
+	xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE);
+	hdr->nops++;
+	hdr->replen += decode_test_stateid_maxsz;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -2833,6 +2856,23 @@ static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req,
 	encode_nops(&hdr);
 	return 0;
 }
+
+/*
+ *  Encode TEST_STATEID request
+ */
+static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req,
+				      struct xdr_stream *xdr,
+				      struct nfs41_test_stateid_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_test_stateid(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
@@ -5371,6 +5411,35 @@ out_overflow:
 	print_overflow_msg(__func__, xdr);
 	return -EIO;
 }
+
+static int decode_test_stateid(struct xdr_stream *xdr,
+			       struct nfs41_test_stateid_res *res)
+{
+	__be32 *p;
+	int status;
+	int num_res;
+
+	status = decode_op_hdr(xdr, OP_TEST_STATEID);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	num_res = be32_to_cpup(p++);
+	if (num_res != 1)
+		goto out;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	res->status = be32_to_cpup(p++);
+	return res->status;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+out:
+	return -EIO;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -6534,6 +6603,27 @@ static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp,
 out:
 	return status;
 }
+
+/*
+ * Decode TEST_STATEID response
+ */
+static int nfs4_xdr_dec_test_stateid(struct rpc_rqst *rqstp,
+				     struct xdr_stream *xdr,
+				     struct nfs41_test_stateid_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_test_stateid(xdr, res);
+out:
+	return status;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /**
@@ -6737,6 +6827,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(LAYOUTCOMMIT,	enc_layoutcommit,	dec_layoutcommit),
 	PROC(LAYOUTRETURN,	enc_layoutreturn,	dec_layoutreturn),
 	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
+	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
 #endif /* CONFIG_NFS_V4_1 */
 };
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 7cc7d5745be..efe07f7a876 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -564,6 +564,7 @@ enum {
 	NFSPROC4_CLNT_LAYOUTCOMMIT,
 	NFSPROC4_CLNT_LAYOUTRETURN,
 	NFSPROC4_CLNT_SECINFO_NO_NAME,
+	NFSPROC4_CLNT_TEST_STATEID,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 7159e1da63b..e696c1fb139 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1092,6 +1092,16 @@ struct nfs41_secinfo_no_name_args {
 	struct nfs4_sequence_args	seq_args;
 };
 
+struct nfs41_test_stateid_args {
+	nfs4_stateid			*stateid;
+	struct nfs4_sequence_args	seq_args;
+};
+
+struct nfs41_test_stateid_res {
+	unsigned int			status;
+	struct nfs4_sequence_res	seq_res;
+};
+
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs_page;
-- 
cgit v1.2.3-70-g09d2


From 9aeda35fd643eba683fdb8dba8907fa796a85dda Mon Sep 17 00:00:00 2001
From: Bryan Schumaker <bjschuma@netapp.com>
Date: Thu, 2 Jun 2011 14:59:09 -0400
Subject: NFS: added FREE_STATEID call

FREE_STATEID is used to tell the server that we want to free a stateid
that no longer has any locks associated with it.  This allows the client
to reclaim locks without encountering edge conditions documented in
section 8.4.3 of RFC 5661.

Signed-off-by: Bryan Schumaker <bjschuma@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       | 30 +++++++++++++++++++
 fs/nfs/nfs4xdr.c        | 80 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/nfs4.h    |  1 +
 include/linux/nfs_xdr.h | 10 +++++++
 4 files changed, 121 insertions(+)

(limited to 'fs/nfs/nfs4proc.c')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5612ba997db..197ad0a737f 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6043,6 +6043,36 @@ static int nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *stat
 	} while (exception.retry);
 	return err;
 }
+
+static int _nfs4_free_stateid(struct nfs_server *server, struct nfs4_state *state)
+{
+	int status;
+	struct nfs41_free_stateid_args args = {
+		.stateid = &state->stateid,
+	};
+	struct nfs41_free_stateid_res res;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FREE_STATEID],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+
+	args.seq_args.sa_session = res.seq_res.sr_session = NULL;
+	status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 0, 1);
+	return status;
+}
+
+static int nfs41_free_stateid(struct nfs_server *server, struct nfs4_state *state)
+{
+	struct nfs4_exception exception = { };
+	int err;
+	do {
+		err = nfs4_handle_exception(server,
+				_nfs4_free_stateid(server, state),
+				&exception);
+	} while (exception.retry);
+	return err;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 7d914d9e758..c191a9baa42 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -348,6 +348,9 @@ static int nfs4_stat_to_errno(int);
 #define encode_test_stateid_maxsz	(op_encode_hdr_maxsz + 2 + \
 					 XDR_QUADLEN(NFS4_STATEID_SIZE))
 #define decode_test_stateid_maxsz	(op_decode_hdr_maxsz + 2 + 1)
+#define encode_free_stateid_maxsz	(op_encode_hdr_maxsz + 1 + \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE))
+#define decode_free_stateid_maxsz	(op_decode_hdr_maxsz + 1)
 #else /* CONFIG_NFS_V4_1 */
 #define encode_sequence_maxsz	0
 #define decode_sequence_maxsz	0
@@ -791,6 +794,12 @@ static int nfs4_stat_to_errno(int);
 #define NFS4_dec_test_stateid_sz	(compound_decode_hdr_maxsz + \
 					 decode_sequence_maxsz + \
 					 decode_test_stateid_maxsz)
+#define NFS4_enc_free_stateid_sz	(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_free_stateid_maxsz)
+#define NFS4_dec_free_stateid_sz	(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_free_stateid_maxsz)
 
 const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
 				      compound_encode_hdr_maxsz +
@@ -1985,6 +1994,18 @@ static void encode_test_stateid(struct xdr_stream *xdr,
 	hdr->nops++;
 	hdr->replen += decode_test_stateid_maxsz;
 }
+
+static void encode_free_stateid(struct xdr_stream *xdr,
+				struct nfs41_free_stateid_args *args,
+				struct compound_hdr *hdr)
+{
+	__be32 *p;
+	p = reserve_space(xdr, 4 + NFS4_STATEID_SIZE);
+	*p++ = cpu_to_be32(OP_FREE_STATEID);
+	xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE);
+	hdr->nops++;
+	hdr->replen += decode_free_stateid_maxsz;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -2873,6 +2894,23 @@ static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req,
 	encode_test_stateid(xdr, args, &hdr);
 	encode_nops(&hdr);
 }
+
+/*
+ *  Encode FREE_STATEID request
+ */
+static void nfs4_xdr_enc_free_stateid(struct rpc_rqst *req,
+				     struct xdr_stream *xdr,
+				     struct nfs41_free_stateid_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_free_stateid(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
@@ -5440,6 +5478,26 @@ out_overflow:
 out:
 	return -EIO;
 }
+
+static int decode_free_stateid(struct xdr_stream *xdr,
+			       struct nfs41_free_stateid_res *res)
+{
+	__be32 *p;
+	int status;
+
+	status = decode_op_hdr(xdr, OP_FREE_STATEID);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	res->status = be32_to_cpup(p++);
+	return res->status;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -6624,6 +6682,27 @@ static int nfs4_xdr_dec_test_stateid(struct rpc_rqst *rqstp,
 out:
 	return status;
 }
+
+/*
+ * Decode FREE_STATEID response
+ */
+static int nfs4_xdr_dec_free_stateid(struct rpc_rqst *rqstp,
+				     struct xdr_stream *xdr,
+				     struct nfs41_free_stateid_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_free_stateid(xdr, res);
+out:
+	return status;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /**
@@ -6828,6 +6907,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(LAYOUTRETURN,	enc_layoutreturn,	dec_layoutreturn),
 	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
 	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
+	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
 #endif /* CONFIG_NFS_V4_1 */
 };
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index efe07f7a876..a3c4bc800dc 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -565,6 +565,7 @@ enum {
 	NFSPROC4_CLNT_LAYOUTRETURN,
 	NFSPROC4_CLNT_SECINFO_NO_NAME,
 	NFSPROC4_CLNT_TEST_STATEID,
+	NFSPROC4_CLNT_FREE_STATEID,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index e696c1fb139..20945556174 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1102,6 +1102,16 @@ struct nfs41_test_stateid_res {
 	struct nfs4_sequence_res	seq_res;
 };
 
+struct nfs41_free_stateid_args {
+	nfs4_stateid			*stateid;
+	struct nfs4_sequence_args	seq_args;
+};
+
+struct nfs41_free_stateid_res {
+	unsigned int			status;
+	struct nfs4_sequence_res	seq_res;
+};
+
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs_page;
-- 
cgit v1.2.3-70-g09d2


From f062eb6ced3b297277b94b4da3113b1d3782e539 Mon Sep 17 00:00:00 2001
From: Bryan Schumaker <bjschuma@netapp.com>
Date: Thu, 2 Jun 2011 14:59:10 -0400
Subject: NFS: test and free stateids during recovery

When recovering open files and locks, the stateid should be tested
against the server and freed if it is invalid.  This patch adds new
recovery functions for NFS v4.1.

Signed-off-by: Bryan Schumaker <bjschuma@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c | 37 ++++++++++++++++++++++++++++++++++---
 1 file changed, 34 insertions(+), 3 deletions(-)

(limited to 'fs/nfs/nfs4proc.c')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 197ad0a737f..325706f73ee 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -80,7 +80,10 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
 static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 			    struct nfs_fattr *fattr, struct iattr *sattr,
 			    struct nfs4_state *state);
-
+#ifdef CONFIG_NFS_V4_1
+static int nfs41_test_stateid(struct nfs_server *, struct nfs4_state *);
+static int nfs41_free_stateid(struct nfs_server *, struct nfs4_state *);
+#endif
 /* Prevent leaks of NFSv4 errors into userland */
 static int nfs4_map_errors(int err)
 {
@@ -1687,6 +1690,20 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
 	return ret;
 }
 
+#if defined(CONFIG_NFS_V4_1)
+static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+	int status;
+	struct nfs_server *server = NFS_SERVER(state->inode);
+
+	status = nfs41_test_stateid(server, state);
+	if (status == NFS_OK)
+		return 0;
+	nfs41_free_stateid(server, state);
+	return nfs4_open_expired(sp, state);
+}
+#endif
+
 /*
  * on an EXCLUSIVE create, the server should send back a bitmask with FATTR4-*
  * fields corresponding to attributes that were used to store the verifier.
@@ -4444,6 +4461,20 @@ out:
 	return err;
 }
 
+#if defined(CONFIG_NFS_V4_1)
+static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *request)
+{
+	int status;
+	struct nfs_server *server = NFS_SERVER(state->inode);
+
+	status = nfs41_test_stateid(server, state);
+	if (status == NFS_OK)
+		return 0;
+	nfs41_free_stateid(server, state);
+	return nfs4_lock_expired(state, request);
+}
+#endif
+
 static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 {
 	struct nfs_inode *nfsi = NFS_I(state->inode);
@@ -6109,8 +6140,8 @@ struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
 struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = {
 	.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
 	.state_flag_bit	= NFS_STATE_RECLAIM_NOGRACE,
-	.recover_open	= nfs4_open_expired,
-	.recover_lock	= nfs4_lock_expired,
+	.recover_open	= nfs41_open_expired,
+	.recover_lock	= nfs41_lock_expired,
 	.establish_clid = nfs41_init_clientid,
 	.get_clid_cred	= nfs4_get_exchange_id_cred,
 };
-- 
cgit v1.2.3-70-g09d2


From a56aaa02b1f723e28b41d339ddff02e958d32d43 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Wed, 15 Jun 2011 11:59:10 -0400
Subject: NFSv4.1: Clean up layoutreturn

Since we take a reference to it, we really ought to pass the a pointer to
the layout header in the arguments instead of assuming that
NFS_I(inode)->layout will forever point to the correct object.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       | 4 ++--
 fs/nfs/pnfs.c           | 1 +
 include/linux/nfs_xdr.h | 3 ++-
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'fs/nfs/nfs4proc.c')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 325706f73ee..93ef77666ef 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5770,7 +5770,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutreturn *lrp = calldata;
 	struct nfs_server *server;
-	struct pnfs_layout_hdr *lo = NFS_I(lrp->args.inode)->layout;
+	struct pnfs_layout_hdr *lo = lrp->args.layout;
 
 	dprintk("--> %s\n", __func__);
 
@@ -5799,7 +5799,7 @@ static void nfs4_layoutreturn_release(void *calldata)
 	struct nfs4_layoutreturn *lrp = calldata;
 
 	dprintk("--> %s\n", __func__);
-	put_layout_hdr(NFS_I(lrp->args.inode)->layout);
+	put_layout_hdr(lrp->args.layout);
 	kfree(calldata);
 	dprintk("<-- %s\n", __func__);
 }
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index a7dc3367a85..5fc2e5d755a 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -667,6 +667,7 @@ _pnfs_return_layout(struct inode *ino)
 	lrp->args.stateid = stateid;
 	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
 	lrp->args.inode = ino;
+	lrp->args.layout = lo;
 	lrp->clp = NFS_SERVER(ino)->nfs_client;
 
 	status = nfs4_proc_layoutreturn(lrp);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 20945556174..956d3576df7 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -269,9 +269,10 @@ struct nfs4_layoutcommit_data {
 };
 
 struct nfs4_layoutreturn_args {
-	__u32   layout_type;
+	struct pnfs_layout_hdr *layout;
 	struct inode *inode;
 	nfs4_stateid stateid;
+	__u32   layout_type;
 	struct nfs4_sequence_args seq_args;
 };
 
-- 
cgit v1.2.3-70-g09d2


From a9bae5666d0510ad69bdb437371c9a3e6b770705 Mon Sep 17 00:00:00 2001
From: Peng Tao <peng_tao@emc.com>
Date: Sat, 30 Jul 2011 20:52:33 -0400
Subject: pnfs: let layoutcommit handle a list of lseg

There can be multiple lseg per file, so layoutcommit should be
able to handle it.

[Needed in v3.0]
CC: Stable Tree <stable@kernel.org>
Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
Signed-off-by: Jim Rees <rees@umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       |  8 +++++++-
 fs/nfs/pnfs.c           | 32 ++++++++++++++++----------------
 fs/nfs/pnfs.h           |  2 ++
 include/linux/nfs_xdr.h |  2 +-
 4 files changed, 26 insertions(+), 18 deletions(-)

(limited to 'fs/nfs/nfs4proc.c')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 079614deca3..efa6ae822ca 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5912,9 +5912,15 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 static void nfs4_layoutcommit_release(void *calldata)
 {
 	struct nfs4_layoutcommit_data *data = calldata;
+	struct pnfs_layout_segment *lseg, *tmp;
 
 	/* Matched by references in pnfs_set_layoutcommit */
-	put_lseg(data->lseg);
+	list_for_each_entry_safe(lseg, tmp, &data->lseg_list, pls_lc_list) {
+		list_del_init(&lseg->pls_lc_list);
+		if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT,
+				       &lseg->pls_flags))
+			put_lseg(lseg);
+	}
 	put_rpccred(data->cred);
 	kfree(data);
 }
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index ab2cb04f8a2..a7e5f17f777 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -225,6 +225,7 @@ static void
 init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
 {
 	INIT_LIST_HEAD(&lseg->pls_list);
+	INIT_LIST_HEAD(&lseg->pls_lc_list);
 	atomic_set(&lseg->pls_refcount, 1);
 	smp_mb();
 	set_bit(NFS_LSEG_VALID, &lseg->pls_flags);
@@ -1356,16 +1357,17 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages);
 
 /*
- * Currently there is only one (whole file) write lseg.
+ * There can be multiple RW segments.
  */
-static struct pnfs_layout_segment *pnfs_list_write_lseg(struct inode *inode)
+static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 {
-	struct pnfs_layout_segment *lseg, *rv = NULL;
+	struct pnfs_layout_segment *lseg;
 
-	list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list)
-		if (lseg->pls_range.iomode == IOMODE_RW)
-			rv = lseg;
-	return rv;
+	list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
+		if (lseg->pls_range.iomode == IOMODE_RW &&
+		    test_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
+			list_add(&lseg->pls_lc_list, listp);
+	}
 }
 
 void
@@ -1377,12 +1379,14 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 
 	spin_lock(&nfsi->vfs_inode.i_lock);
 	if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
-		/* references matched in nfs4_layoutcommit_release */
-		get_lseg(wdata->lseg);
 		mark_as_dirty = true;
 		dprintk("%s: Set layoutcommit for inode %lu ",
 			__func__, wdata->inode->i_ino);
 	}
+	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags)) {
+		/* references matched in nfs4_layoutcommit_release */
+		get_lseg(wdata->lseg);
+	}
 	if (end_pos > nfsi->layout->plh_lwb)
 		nfsi->layout->plh_lwb = end_pos;
 	spin_unlock(&nfsi->vfs_inode.i_lock);
@@ -1409,7 +1413,6 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
 	struct nfs4_layoutcommit_data *data;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	struct pnfs_layout_segment *lseg;
 	loff_t end_pos;
 	int status = 0;
 
@@ -1426,17 +1429,15 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 		goto out;
 	}
 
+	INIT_LIST_HEAD(&data->lseg_list);
 	spin_lock(&inode->i_lock);
 	if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
 		spin_unlock(&inode->i_lock);
 		kfree(data);
 		goto out;
 	}
-	/*
-	 * Currently only one (whole file) write lseg which is referenced
-	 * in pnfs_set_layoutcommit and will be found.
-	 */
-	lseg = pnfs_list_write_lseg(inode);
+
+	pnfs_list_write_lseg(inode, &data->lseg_list);
 
 	end_pos = nfsi->layout->plh_lwb;
 	nfsi->layout->plh_lwb = 0;
@@ -1446,7 +1447,6 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	spin_unlock(&inode->i_lock);
 
 	data->args.inode = inode;
-	data->lseg = lseg;
 	data->cred = get_rpccred(nfsi->layout->plh_lc_cred);
 	nfs_fattr_init(&data->fattr);
 	data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 1f5cb47e2a2..b94f874886c 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -36,10 +36,12 @@
 enum {
 	NFS_LSEG_VALID = 0,	/* cleared when lseg is recalled/returned */
 	NFS_LSEG_ROC,		/* roc bit received from server */
+	NFS_LSEG_LAYOUTCOMMIT,	/* layoutcommit bit set for layoutcommit */
 };
 
 struct pnfs_layout_segment {
 	struct list_head pls_list;
+	struct list_head pls_lc_list;
 	struct pnfs_layout_range pls_range;
 	atomic_t pls_refcount;
 	unsigned long pls_flags;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 5b115956aba..feb312716c0 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -262,7 +262,7 @@ struct nfs4_layoutcommit_res {
 struct nfs4_layoutcommit_data {
 	struct rpc_task task;
 	struct nfs_fattr fattr;
-	struct pnfs_layout_segment *lseg;
+	struct list_head lseg_list;
 	struct rpc_cred *cred;
 	struct nfs4_layoutcommit_args args;
 	struct nfs4_layoutcommit_res res;
-- 
cgit v1.2.3-70-g09d2


From 7f11d8d38d64739e190581e015a2a2730ff54e2a Mon Sep 17 00:00:00 2001
From: Andy Adamson <andros@netapp.com>
Date: Sat, 30 Jul 2011 20:52:35 -0400
Subject: pnfs: GETDEVICELIST

The block driver uses GETDEVICELIST

Signed-off-by: Andy Adamson <andros@netapp.com>
[pass struct nfs_server * to getdevicelist]
[get machince creds for getdevicelist]
[fix getdevicelist decode sizing]
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Jim Rees <rees@umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       |  48 ++++++++++++++++++
 fs/nfs/nfs4xdr.c        | 131 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/pnfs.h           |  12 +++++
 include/linux/nfs4.h    |   1 +
 include/linux/nfs_xdr.h |  11 ++++
 5 files changed, 203 insertions(+)

(limited to 'fs/nfs/nfs4proc.c')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index efa6ae822ca..af32d3df054 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5834,6 +5834,54 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
 	return status;
 }
 
+/*
+ * Retrieve the list of Data Server devices from the MDS.
+ */
+static int _nfs4_getdevicelist(struct nfs_server *server,
+				    const struct nfs_fh *fh,
+				    struct pnfs_devicelist *devlist)
+{
+	struct nfs4_getdevicelist_args args = {
+		.fh = fh,
+		.layoutclass = server->pnfs_curr_ld->id,
+	};
+	struct nfs4_getdevicelist_res res = {
+		.devlist = devlist,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICELIST],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	int status;
+
+	dprintk("--> %s\n", __func__);
+	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args,
+				&res.seq_res, 0);
+	dprintk("<-- %s status=%d\n", __func__, status);
+	return status;
+}
+
+int nfs4_proc_getdevicelist(struct nfs_server *server,
+			    const struct nfs_fh *fh,
+			    struct pnfs_devicelist *devlist)
+{
+	struct nfs4_exception exception = { };
+	int err;
+
+	do {
+		err = nfs4_handle_exception(server,
+				_nfs4_getdevicelist(server, fh, devlist),
+				&exception);
+	} while (exception.retry);
+
+	dprintk("%s: err=%d, num_devs=%u\n", __func__,
+		err, devlist->num_devs);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(nfs4_proc_getdevicelist);
+
 static int
 _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev)
 {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index b851b560a6f..5f769f8d05b 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -314,6 +314,17 @@ static int nfs4_stat_to_errno(int);
 				XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5)
 #define encode_reclaim_complete_maxsz	(op_encode_hdr_maxsz + 4)
 #define decode_reclaim_complete_maxsz	(op_decode_hdr_maxsz + 4)
+#define encode_getdevicelist_maxsz (op_encode_hdr_maxsz + 4 + \
+				encode_verifier_maxsz)
+#define decode_getdevicelist_maxsz (op_decode_hdr_maxsz + \
+				2 /* nfs_cookie4 gdlr_cookie */ + \
+				decode_verifier_maxsz \
+				  /* verifier4 gdlr_verifier */ + \
+				1 /* gdlr_deviceid_list count */ + \
+				XDR_QUADLEN(NFS4_PNFS_GETDEVLIST_MAXNUM * \
+					    NFS4_DEVICEID4_SIZE) \
+				  /* gdlr_deviceid_list */ + \
+				1 /* bool gdlr_eof */)
 #define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \
 				XDR_QUADLEN(NFS4_DEVICEID4_SIZE))
 #define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \
@@ -748,6 +759,14 @@ static int nfs4_stat_to_errno(int);
 #define NFS4_dec_reclaim_complete_sz	(compound_decode_hdr_maxsz + \
 					 decode_sequence_maxsz + \
 					 decode_reclaim_complete_maxsz)
+#define NFS4_enc_getdevicelist_sz (compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
+				encode_putfh_maxsz + \
+				encode_getdevicelist_maxsz)
+#define NFS4_dec_getdevicelist_sz (compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
+				decode_putfh_maxsz + \
+				decode_getdevicelist_maxsz)
 #define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz +    \
 				encode_sequence_maxsz +\
 				encode_getdeviceinfo_maxsz)
@@ -1854,6 +1873,26 @@ static void encode_sequence(struct xdr_stream *xdr,
 }
 
 #ifdef CONFIG_NFS_V4_1
+static void
+encode_getdevicelist(struct xdr_stream *xdr,
+		     const struct nfs4_getdevicelist_args *args,
+		     struct compound_hdr *hdr)
+{
+	__be32 *p;
+	nfs4_verifier dummy = {
+		.data = "dummmmmy",
+	};
+
+	p = reserve_space(xdr, 20);
+	*p++ = cpu_to_be32(OP_GETDEVICELIST);
+	*p++ = cpu_to_be32(args->layoutclass);
+	*p++ = cpu_to_be32(NFS4_PNFS_GETDEVLIST_MAXNUM);
+	xdr_encode_hyper(p, 0ULL);                          /* cookie */
+	encode_nfs4_verifier(xdr, &dummy);
+	hdr->nops++;
+	hdr->replen += decode_getdevicelist_maxsz;
+}
+
 static void
 encode_getdeviceinfo(struct xdr_stream *xdr,
 		     const struct nfs4_getdeviceinfo_args *args,
@@ -2774,6 +2813,24 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode GETDEVICELIST request
+ */
+static void nfs4_xdr_enc_getdevicelist(struct rpc_rqst *req,
+				       struct xdr_stream *xdr,
+				       struct nfs4_getdevicelist_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_getdevicelist(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode GETDEVICEINFO request
  */
@@ -5268,6 +5325,53 @@ out_overflow:
 }
 
 #if defined(CONFIG_NFS_V4_1)
+/*
+ * TODO: Need to handle case when EOF != true;
+ */
+static int decode_getdevicelist(struct xdr_stream *xdr,
+				struct pnfs_devicelist *res)
+{
+	__be32 *p;
+	int status, i;
+	struct nfs_writeverf verftemp;
+
+	status = decode_op_hdr(xdr, OP_GETDEVICELIST);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 8 + 8 + 4);
+	if (unlikely(!p))
+		goto out_overflow;
+
+	/* TODO: Skip cookie for now */
+	p += 2;
+
+	/* Read verifier */
+	p = xdr_decode_opaque_fixed(p, verftemp.verifier, 8);
+
+	res->num_devs = be32_to_cpup(p);
+
+	dprintk("%s: num_dev %d\n", __func__, res->num_devs);
+
+	if (res->num_devs > NFS4_PNFS_GETDEVLIST_MAXNUM) {
+		printk(KERN_ERR "%s too many result dev_num %u\n",
+				__func__, res->num_devs);
+		return -EIO;
+	}
+
+	p = xdr_inline_decode(xdr,
+			      res->num_devs * NFS4_DEVICEID4_SIZE + 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	for (i = 0; i < res->num_devs; i++)
+		p = xdr_decode_opaque_fixed(p, res->dev_id[i].data,
+					    NFS4_DEVICEID4_SIZE);
+	res->eof = be32_to_cpup(p);
+	return 0;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
 
 static int decode_getdeviceinfo(struct xdr_stream *xdr,
 				struct pnfs_device *pdev)
@@ -6541,6 +6645,32 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp,
 	return status;
 }
 
+/*
+ * Decode GETDEVICELIST response
+ */
+static int nfs4_xdr_dec_getdevicelist(struct rpc_rqst *rqstp,
+				      struct xdr_stream *xdr,
+				      struct nfs4_getdevicelist_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	dprintk("encoding getdevicelist!\n");
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status != 0)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status != 0)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status != 0)
+		goto out;
+	status = decode_getdevicelist(xdr, res->devlist);
+out:
+	return status;
+}
+
 /*
  * Decode GETDEVINFO response
  */
@@ -6908,6 +7038,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
 	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
 	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
+	PROC(GETDEVICELIST,	enc_getdevicelist,	dec_getdevicelist),
 #endif /* CONFIG_NFS_V4_1 */
 };
 
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index b94f874886c..7074394944a 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -135,14 +135,26 @@ struct pnfs_device {
 	unsigned int  layout_type;
 	unsigned int  mincount;
 	struct page **pages;
+	void          *area;
 	unsigned int  pgbase;
 	unsigned int  pglen;
 };
 
+#define NFS4_PNFS_GETDEVLIST_MAXNUM 16
+
+struct pnfs_devicelist {
+	unsigned int		eof;
+	unsigned int		num_devs;
+	struct nfs4_deviceid	dev_id[NFS4_PNFS_GETDEVLIST_MAXNUM];
+};
+
 extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
 extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
 
 /* nfs4proc.c */
+extern int nfs4_proc_getdevicelist(struct nfs_server *server,
+				   const struct nfs_fh *fh,
+				   struct pnfs_devicelist *devlist);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev);
 extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp);
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index a3c4bc800dc..76f99e8714f 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -566,6 +566,7 @@ enum {
 	NFSPROC4_CLNT_SECINFO_NO_NAME,
 	NFSPROC4_CLNT_TEST_STATEID,
 	NFSPROC4_CLNT_FREE_STATEID,
+	NFSPROC4_CLNT_GETDEVICELIST,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index feb312716c0..21f333eae3c 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -235,6 +235,17 @@ struct nfs4_layoutget {
 	gfp_t gfp_flags;
 };
 
+struct nfs4_getdevicelist_args {
+	const struct nfs_fh *fh;
+	u32 layoutclass;
+	struct nfs4_sequence_args seq_args;
+};
+
+struct nfs4_getdevicelist_res {
+	struct pnfs_devicelist *devlist;
+	struct nfs4_sequence_res seq_res;
+};
+
 struct nfs4_getdeviceinfo_args {
 	struct pnfs_device *pdev;
 	struct nfs4_sequence_args seq_args;
-- 
cgit v1.2.3-70-g09d2


From dae100c2b1b9463996aab9162f2258145c43f7df Mon Sep 17 00:00:00 2001
From: Fred Isaman <iisaman@citi.umich.edu>
Date: Sat, 30 Jul 2011 20:52:37 -0400
Subject: pnfs: ask for layout_blksize and save it in nfs_server

Block layout needs it to determine IO size.

Signed-off-by: Fred Isaman <iisaman@citi.umich.edu>
Signed-off-by: Tao Guo <glorioustao@gmail.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Jim Rees <rees@umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/client.c           |  1 +
 fs/nfs/nfs4_fs.h          |  2 +-
 fs/nfs/nfs4proc.c         |  5 ++-
 fs/nfs/nfs4xdr.c          | 99 +++++++++++++++++++++++++++++++++++++++--------
 include/linux/nfs_fs_sb.h |  3 +-
 include/linux/nfs_xdr.h   |  3 +-
 6 files changed, 91 insertions(+), 22 deletions(-)

(limited to 'fs/nfs/nfs4proc.c')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index a9b18483cb2..de00a373f08 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -936,6 +936,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
 	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	server->pnfs_blksize = fsinfo->blksize;
 	set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype);
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 1909ee8be35..1ec1a85fa71 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -318,7 +318,7 @@ extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
 extern const u32 nfs4_fattr_bitmap[2];
 extern const u32 nfs4_statfs_bitmap[2];
 extern const u32 nfs4_pathconf_bitmap[2];
-extern const u32 nfs4_fsinfo_bitmap[2];
+extern const u32 nfs4_fsinfo_bitmap[3];
 extern const u32 nfs4_fs_locations_bitmap[2];
 
 /* nfs4renewd.c */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index af32d3df054..e86de799dd1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -140,12 +140,13 @@ const u32 nfs4_pathconf_bitmap[2] = {
 	0
 };
 
-const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE
+const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
 			| FATTR4_WORD0_MAXREAD
 			| FATTR4_WORD0_MAXWRITE
 			| FATTR4_WORD0_LEASE_TIME,
 			FATTR4_WORD1_TIME_DELTA
-			| FATTR4_WORD1_FS_LAYOUT_TYPES
+			| FATTR4_WORD1_FS_LAYOUT_TYPES,
+			FATTR4_WORD2_LAYOUT_BLKSIZE
 };
 
 const u32 nfs4_fs_locations_bitmap[2] = {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 5f769f8d05b..026166993d1 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -113,7 +113,11 @@ static int nfs4_stat_to_errno(int);
 #define encode_restorefh_maxsz  (op_encode_hdr_maxsz)
 #define decode_restorefh_maxsz  (op_decode_hdr_maxsz)
 #define encode_fsinfo_maxsz	(encode_getattr_maxsz)
-#define decode_fsinfo_maxsz	(op_decode_hdr_maxsz + 15)
+/* The 5 accounts for the PNFS attributes, and assumes that at most three
+ * layout types will be returned.
+ */
+#define decode_fsinfo_maxsz	(op_decode_hdr_maxsz + \
+				 nfs4_fattr_bitmap_maxsz + 4 + 8 + 5)
 #define encode_renew_maxsz	(op_encode_hdr_maxsz + 3)
 #define decode_renew_maxsz	(op_decode_hdr_maxsz)
 #define encode_setclientid_maxsz \
@@ -1123,6 +1127,35 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm
 	hdr->replen += decode_getattr_maxsz;
 }
 
+static void
+encode_getattr_three(struct xdr_stream *xdr,
+		     uint32_t bm0, uint32_t bm1, uint32_t bm2,
+		     struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	p = reserve_space(xdr, 4);
+	*p = cpu_to_be32(OP_GETATTR);
+	if (bm2) {
+		p = reserve_space(xdr, 16);
+		*p++ = cpu_to_be32(3);
+		*p++ = cpu_to_be32(bm0);
+		*p++ = cpu_to_be32(bm1);
+		*p = cpu_to_be32(bm2);
+	} else if (bm1) {
+		p = reserve_space(xdr, 12);
+		*p++ = cpu_to_be32(2);
+		*p++ = cpu_to_be32(bm0);
+		*p = cpu_to_be32(bm1);
+	} else {
+		p = reserve_space(xdr, 8);
+		*p++ = cpu_to_be32(1);
+		*p = cpu_to_be32(bm0);
+	}
+	hdr->nops++;
+	hdr->replen += decode_getattr_maxsz;
+}
+
 static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
 {
 	encode_getattr_two(xdr, bitmask[0] & nfs4_fattr_bitmap[0],
@@ -1131,8 +1164,11 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c
 
 static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
 {
-	encode_getattr_two(xdr, bitmask[0] & nfs4_fsinfo_bitmap[0],
-			   bitmask[1] & nfs4_fsinfo_bitmap[1], hdr);
+	encode_getattr_three(xdr,
+			     bitmask[0] & nfs4_fsinfo_bitmap[0],
+			     bitmask[1] & nfs4_fsinfo_bitmap[1],
+			     bitmask[2] & nfs4_fsinfo_bitmap[2],
+			     hdr);
 }
 
 static void encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
@@ -2643,7 +2679,7 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req,
 	struct compound_hdr hdr = {
 		.nops	= 0,
 	};
-	const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
+	const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME };
 
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_setclientid_confirm(xdr, arg, &hdr);
@@ -2787,7 +2823,7 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req,
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->la_seq_args),
 	};
-	const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
+	const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME };
 
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->la_seq_args, &hdr);
@@ -3068,14 +3104,17 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap)
 		goto out_overflow;
 	bmlen = be32_to_cpup(p);
 
-	bitmap[0] = bitmap[1] = 0;
+	bitmap[0] = bitmap[1] = bitmap[2] = 0;
 	p = xdr_inline_decode(xdr, (bmlen << 2));
 	if (unlikely(!p))
 		goto out_overflow;
 	if (bmlen > 0) {
 		bitmap[0] = be32_to_cpup(p++);
-		if (bmlen > 1)
-			bitmap[1] = be32_to_cpup(p);
+		if (bmlen > 1) {
+			bitmap[1] = be32_to_cpup(p++);
+			if (bmlen > 2)
+				bitmap[2] = be32_to_cpup(p);
+		}
 	}
 	return 0;
 out_overflow:
@@ -3107,8 +3146,9 @@ static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint3
 			return ret;
 		bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS;
 	} else
-		bitmask[0] = bitmask[1] = 0;
-	dprintk("%s: bitmask=%08x:%08x\n", __func__, bitmask[0], bitmask[1]);
+		bitmask[0] = bitmask[1] = bitmask[2] = 0;
+	dprintk("%s: bitmask=%08x:%08x:%08x\n", __func__,
+		bitmask[0], bitmask[1], bitmask[2]);
 	return 0;
 }
 
@@ -4162,7 +4202,7 @@ out_overflow:
 static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2] = {0};
+	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4188,7 +4228,7 @@ xdr_error:
 static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2] = {0};
+	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4220,7 +4260,7 @@ xdr_error:
 static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2] = {0};
+	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4360,7 +4400,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
 {
 	__be32 *savep;
 	uint32_t attrlen,
-		 bitmap[2] = {0};
+		 bitmap[3] = {0};
 	int status;
 
 	status = decode_op_hdr(xdr, OP_GETATTR);
@@ -4446,10 +4486,32 @@ static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap,
 	return status;
 }
 
+/*
+ * The prefered block size for layout directed io
+ */
+static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
+				      uint32_t *res)
+{
+	__be32 *p;
+
+	dprintk("%s: bitmap is %x\n", __func__, bitmap[2]);
+	*res = 0;
+	if (bitmap[2] & FATTR4_WORD2_LAYOUT_BLKSIZE) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p)) {
+			print_overflow_msg(__func__, xdr);
+			return -EIO;
+		}
+		*res = be32_to_cpup(p);
+		bitmap[2] &= ~FATTR4_WORD2_LAYOUT_BLKSIZE;
+	}
+	return 0;
+}
+
 static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2];
+	uint32_t attrlen, bitmap[3];
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4477,6 +4539,9 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 	status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype);
 	if (status != 0)
 		goto xdr_error;
+	status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize);
+	if (status)
+		goto xdr_error;
 
 	status = verify_attr_len(xdr, savep, attrlen);
 xdr_error:
@@ -4896,7 +4961,7 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 {
 	__be32 *savep;
 	uint32_t attrlen,
-		 bitmap[2] = {0};
+		 bitmap[3] = {0};
 	struct kvec *iov = req->rq_rcv_buf.head;
 	int status;
 
@@ -6852,7 +6917,7 @@ out:
 int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		       int plus)
 {
-	uint32_t bitmap[2] = {0};
+	uint32_t bitmap[3] = {0};
 	uint32_t len;
 	__be32 *p = xdr_inline_decode(xdr, 4);
 	if (unlikely(!p))
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 4faeac8f448..b2ea8b82d2c 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -132,7 +132,7 @@ struct nfs_server {
 #endif
 
 #ifdef CONFIG_NFS_V4
-	u32			attr_bitmask[2];/* V4 bitmask representing the set
+	u32			attr_bitmask[3];/* V4 bitmask representing the set
 						   of attributes supported on this
 						   filesystem */
 	u32			cache_consistency_bitmask[2];
@@ -145,6 +145,7 @@ struct nfs_server {
 						   filesystem */
 	struct pnfs_layoutdriver_type  *pnfs_curr_ld; /* Active layout driver */
 	struct rpc_wait_queue	roc_rpcwaitq;
+	u32			pnfs_blksize;	/* layout_blksize attr */
 
 	/* the following fields are protected by nfs_client->cl_lock */
 	struct rb_root		state_owners;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 21f333eae3c..94f27e56df9 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -122,6 +122,7 @@ struct nfs_fsinfo {
 	struct timespec		time_delta; /* server time granularity */
 	__u32			lease_time; /* in seconds */
 	__u32			layouttype; /* supported pnfs layout driver */
+	__u32			blksize; /* preferred pnfs io block size */
 };
 
 struct nfs_fsstat {
@@ -954,7 +955,7 @@ struct nfs4_server_caps_arg {
 };
 
 struct nfs4_server_caps_res {
-	u32				attr_bitmask[2];
+	u32				attr_bitmask[3];
 	u32				acl_bitmask;
 	u32				has_links;
 	u32				has_symlinks;
-- 
cgit v1.2.3-70-g09d2


From db29c089094b2e686ebc9ed9f002be4a4f94b1f8 Mon Sep 17 00:00:00 2001
From: Andy Adamson <andros@netapp.com>
Date: Sat, 30 Jul 2011 20:52:38 -0400
Subject: pnfs: cleanup_layoutcommit

This gives layout driver a chance to cleanup structures they put in at
encode_layoutcommit.

Signed-off-by: Andy Adamson <andros@netapp.com>
[fixup layout header pointer for layoutcommit]
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
[rm inode and pnfs_layout_hdr args from cleanup_layoutcommit()]
Signed-off-by: Jim Rees <rees@umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       | 1 +
 fs/nfs/nfs4xdr.c        | 1 +
 fs/nfs/pnfs.c           | 8 ++++++++
 fs/nfs/pnfs.h           | 3 +++
 include/linux/nfs_xdr.h | 1 +
 5 files changed, 14 insertions(+)

(limited to 'fs/nfs/nfs4proc.c')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e86de799dd1..8c77039e7a8 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5963,6 +5963,7 @@ static void nfs4_layoutcommit_release(void *calldata)
 	struct nfs4_layoutcommit_data *data = calldata;
 	struct pnfs_layout_segment *lseg, *tmp;
 
+	pnfs_cleanup_layoutcommit(data);
 	/* Matched by references in pnfs_set_layoutcommit */
 	list_for_each_entry_safe(lseg, tmp, &data->lseg_list, pls_lc_list) {
 		list_del_init(&lseg->pls_lc_list);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 026166993d1..1dce12f41a4 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -5599,6 +5599,7 @@ static int decode_layoutcommit(struct xdr_stream *xdr,
 	int status;
 
 	status = decode_op_hdr(xdr, OP_LAYOUTCOMMIT);
+	res->status = status;
 	if (status)
 		return status;
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 3a47f7ce1e9..e550e8836c3 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1411,6 +1411,14 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 }
 EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
 
+void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
+{
+	struct nfs_server *nfss = NFS_SERVER(data->args.inode);
+
+	if (nfss->pnfs_curr_ld->cleanup_layoutcommit)
+		nfss->pnfs_curr_ld->cleanup_layoutcommit(data);
+}
+
 /*
  * For the LAYOUT4_NFSV4_1_FILES layout type, NFS_DATA_SYNC WRITEs and
  * NFS_UNSTABLE WRITEs with a COMMIT to data servers must store enough
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index bddd8b997e1..606fbde2e75 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -113,6 +113,8 @@ struct pnfs_layoutdriver_type {
 				     struct xdr_stream *xdr,
 				     const struct nfs4_layoutreturn_args *args);
 
+	void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data);
+
 	void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid,
 				     struct xdr_stream *xdr,
 				     const struct nfs4_layoutcommit_args *args);
@@ -196,6 +198,7 @@ void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
 bool pnfs_roc_drain(struct inode *ino, u32 *barrier);
 void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
+void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
 int pnfs_ld_write_done(struct nfs_write_data *);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 94f27e56df9..569ea5b76fd 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -269,6 +269,7 @@ struct nfs4_layoutcommit_res {
 	struct nfs_fattr *fattr;
 	const struct nfs_server *server;
 	struct nfs4_sequence_res seq_res;
+	int status;
 };
 
 struct nfs4_layoutcommit_data {
-- 
cgit v1.2.3-70-g09d2