From dedeb13f9efb4439a37cf56317c8f25860dd667b Mon Sep 17 00:00:00 2001
From: Andrew Elble <aweits@rit.edu>
Date: Wed, 15 Jun 2016 12:52:08 -0400
Subject: nfsd: allow mach_creds_match to be used more broadly

Rename mach_creds_match() to nfsd4_mach_creds_match() and un-staticify

Signed-off-by: Andrew Elble <aweits@rit.edu>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4state.c | 14 +++++++-------
 fs/nfsd/xdr4.h      |  2 ++
 2 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 70d0b9b33031..ef583507d276 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1972,7 +1972,7 @@ static bool svc_rqst_integrity_protected(struct svc_rqst *rqstp)
 	       service == RPC_GSS_SVC_PRIVACY;
 }
 
-static bool mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp)
+bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp)
 {
 	struct svc_cred *cr = &rqstp->rq_cred;
 
@@ -2424,7 +2424,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 				status = nfserr_inval;
 				goto out;
 			}
-			if (!mach_creds_match(conf, rqstp)) {
+			if (!nfsd4_mach_creds_match(conf, rqstp)) {
 				status = nfserr_wrong_cred;
 				goto out;
 			}
@@ -2676,7 +2676,7 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 
 	if (conf) {
 		status = nfserr_wrong_cred;
-		if (!mach_creds_match(conf, rqstp))
+		if (!nfsd4_mach_creds_match(conf, rqstp))
 			goto out_free_conn;
 		cs_slot = &conf->cl_cs_slot;
 		status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
@@ -2692,7 +2692,7 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 			goto out_free_conn;
 		}
 		status = nfserr_wrong_cred;
-		if (!mach_creds_match(unconf, rqstp))
+		if (!nfsd4_mach_creds_match(unconf, rqstp))
 			goto out_free_conn;
 		cs_slot = &unconf->cl_cs_slot;
 		status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
@@ -2801,7 +2801,7 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
 	if (!session)
 		goto out_no_session;
 	status = nfserr_wrong_cred;
-	if (!mach_creds_match(session->se_client, rqstp))
+	if (!nfsd4_mach_creds_match(session->se_client, rqstp))
 		goto out;
 	status = nfsd4_map_bcts_dir(&bcts->dir);
 	if (status)
@@ -2848,7 +2848,7 @@ nfsd4_destroy_session(struct svc_rqst *r,
 	if (!ses)
 		goto out_client_lock;
 	status = nfserr_wrong_cred;
-	if (!mach_creds_match(ses->se_client, r))
+	if (!nfsd4_mach_creds_match(ses->se_client, r))
 		goto out_put_session;
 	status = mark_session_dead_locked(ses, 1 + ref_held_by_me);
 	if (status)
@@ -3087,7 +3087,7 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
 		status = nfserr_stale_clientid;
 		goto out;
 	}
-	if (!mach_creds_match(clp, rqstp)) {
+	if (!nfsd4_mach_creds_match(clp, rqstp)) {
 		clp = NULL;
 		status = nfserr_wrong_cred;
 		goto out;
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index d9554813e58a..74342a7c208a 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -654,6 +654,8 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
 
 }
 
+
+bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp);
 int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
 int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *,
 		struct nfsd4_compoundargs *);
-- 
cgit v1.2.3


From ed94164398c935a42be7b129a478eb19c598b68a Mon Sep 17 00:00:00 2001
From: Andrew Elble <aweits@rit.edu>
Date: Wed, 15 Jun 2016 12:52:09 -0400
Subject: nfsd: implement machine credential support for some operations

This addresses the conundrum referenced in RFC5661 18.35.3,
and will allow clients to return state to the server using the
machine credentials.

The biggest part of the problem is that we need to allow the client
to send a compound op with integrity/privacy on mounts that don't
have it enabled.

Add server support for properly decoding and using spo_must_enforce
and spo_must_allow bits. Add support for machine credentials to be
used for CLOSE, OPEN_DOWNGRADE, LOCKU, DELEGRETURN,
and TEST/FREE STATEID.
Implement a check so as to not throw WRONGSEC errors when these
operations are used if integrity/privacy isn't turned on.

Without this, Linux clients with credentials that expired while holding
delegations were getting stuck in an endless loop.

Signed-off-by: Andrew Elble <aweits@rit.edu>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/export.c    | 10 ++++++++++
 fs/nfsd/nfs4proc.c  | 39 +++++++++++++++++++++++++++++++++++++++
 fs/nfsd/nfs4state.c | 18 ++++++++++++++++++
 fs/nfsd/nfs4xdr.c   | 51 +++++++++++++++++++++++----------------------------
 fs/nfsd/nfsd.h      |  5 +++++
 fs/nfsd/state.h     |  1 +
 fs/nfsd/xdr4.h      |  3 +++
 7 files changed, 99 insertions(+), 28 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index b4d84b579f20..79de2f38dd63 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -954,6 +954,16 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp)
 		    rqstp->rq_cred.cr_flavor == RPC_AUTH_UNIX)
 			return 0;
 	}
+
+	/* If the compound op contains a spo_must_allowed op,
+	 * it will be sent with integrity/protection which
+	 * will have to be expressly allowed on mounts that
+	 * don't support it
+	 */
+
+	if (nfsd4_spo_must_allow(rqstp))
+		return 0;
+
 	return nfserr_wrongsec;
 }
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index de1ff1d98bb1..b1159b3e9816 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2335,6 +2335,45 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	},
 };
 
+/**
+ * nfsd4_spo_must_allow - Determine if the compound op contains an
+ * operation that is allowed to be sent with machine credentials
+ *
+ * @rqstp: a pointer to the struct svc_rqst
+ *
+ * Checks to see if the compound contains a spo_must_allow op
+ * and confirms that it was sent with the proper machine creds.
+ */
+
+bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
+{
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
+	struct nfsd4_compoundargs *argp = rqstp->rq_argp;
+	struct nfsd4_op *this = &argp->ops[resp->opcnt - 1];
+	struct nfsd4_compound_state *cstate = &resp->cstate;
+	struct nfs4_op_map *allow = &cstate->clp->cl_spo_must_allow;
+	u32 opiter;
+
+	if (!cstate->minorversion)
+		return false;
+
+	if (cstate->spo_must_allowed == true)
+		return true;
+
+	opiter = resp->opcnt;
+	while (opiter < argp->opcnt) {
+		this = &argp->ops[opiter++];
+		if (test_bit(this->opnum, allow->u.longs) &&
+			cstate->clp->cl_mach_cred &&
+			nfsd4_mach_creds_match(cstate->clp, rqstp)) {
+			cstate->spo_must_allowed = true;
+			return true;
+		}
+	}
+	cstate->spo_must_allowed = false;
+	return false;
+}
+
 int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	struct nfsd4_operation *opdesc;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ef583507d276..ebfcebd5eab1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2388,6 +2388,22 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 
 	switch (exid->spa_how) {
 	case SP4_MACH_CRED:
+		exid->spo_must_enforce[0] = 0;
+		exid->spo_must_enforce[1] = (
+			1 << (OP_BIND_CONN_TO_SESSION - 32) |
+			1 << (OP_EXCHANGE_ID - 32) |
+			1 << (OP_CREATE_SESSION - 32) |
+			1 << (OP_DESTROY_SESSION - 32) |
+			1 << (OP_DESTROY_CLIENTID - 32));
+
+		exid->spo_must_allow[0] &= (1 << (OP_CLOSE) |
+					1 << (OP_OPEN_DOWNGRADE) |
+					1 << (OP_LOCKU) |
+					1 << (OP_DELEGRETURN));
+
+		exid->spo_must_allow[1] &= (
+					1 << (OP_TEST_STATEID - 32) |
+					1 << (OP_FREE_STATEID - 32));
 		if (!svc_rqst_integrity_protected(rqstp)) {
 			status = nfserr_inval;
 			goto out_nolock;
@@ -2473,6 +2489,8 @@ out_new:
 			goto out;
 	}
 	new->cl_minorversion = cstate->minorversion;
+	new->cl_spo_must_allow.u.words[0] = exid->spo_must_allow[0];
+	new->cl_spo_must_allow.u.words[1] = exid->spo_must_allow[1];
 
 	gen_clid(new, nn);
 	add_to_unconfirmed(new);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 9df898ba648f..84ef94794496 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1299,16 +1299,14 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
 		break;
 	case SP4_MACH_CRED:
 		/* spo_must_enforce */
-		READ_BUF(4);
-		dummy = be32_to_cpup(p++);
-		READ_BUF(dummy * 4);
-		p += dummy;
-
+		status = nfsd4_decode_bitmap(argp,
+					exid->spo_must_enforce);
+		if (status)
+			goto out;
 		/* spo_must_allow */
-		READ_BUF(4);
-		dummy = be32_to_cpup(p++);
-		READ_BUF(dummy * 4);
-		p += dummy;
+		status = nfsd4_decode_bitmap(argp, exid->spo_must_allow);
+		if (status)
+			goto out;
 		break;
 	case SP4_SSV:
 		/* ssp_ops */
@@ -3867,14 +3865,6 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w
 	return nfserr;
 }
 
-static const u32 nfs4_minimal_spo_must_enforce[2] = {
-	[1] = 1 << (OP_BIND_CONN_TO_SESSION - 32) |
-	      1 << (OP_EXCHANGE_ID - 32) |
-	      1 << (OP_CREATE_SESSION - 32) |
-	      1 << (OP_DESTROY_SESSION - 32) |
-	      1 << (OP_DESTROY_CLIENTID - 32)
-};
-
 static __be32
 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 			 struct nfsd4_exchange_id *exid)
@@ -3885,6 +3875,7 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 	char *server_scope;
 	int major_id_sz;
 	int server_scope_sz;
+	int status = 0;
 	uint64_t minor_id = 0;
 
 	if (nfserr)
@@ -3913,18 +3904,20 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 	case SP4_NONE:
 		break;
 	case SP4_MACH_CRED:
-		/* spo_must_enforce, spo_must_allow */
-		p = xdr_reserve_space(xdr, 16);
-		if (!p)
-			return nfserr_resource;
-
 		/* spo_must_enforce bitmap: */
-		*p++ = cpu_to_be32(2);
-		*p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[0]);
-		*p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[1]);
-		/* empty spo_must_allow bitmap: */
-		*p++ = cpu_to_be32(0);
-
+		status = nfsd4_encode_bitmap(xdr,
+					exid->spo_must_enforce[0],
+					exid->spo_must_enforce[1],
+					exid->spo_must_enforce[2]);
+		if (status)
+			goto out;
+		/* spo_must_allow bitmap: */
+		status = nfsd4_encode_bitmap(xdr,
+					exid->spo_must_allow[0],
+					exid->spo_must_allow[1],
+					exid->spo_must_allow[2]);
+		if (status)
+			goto out;
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -3951,6 +3944,8 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 	/* Implementation id */
 	*p++ = cpu_to_be32(0);	/* zero length nfs_impl_id4 array */
 	return 0;
+out:
+	return status;
 }
 
 static __be32
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index cf980523898b..9446849888d5 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -124,6 +124,7 @@ void nfs4_state_shutdown_net(struct net *net);
 void nfs4_reset_lease(time_t leasetime);
 int nfs4_reset_recoverydir(char *recdir);
 char * nfs4_recoverydir(void);
+bool nfsd4_spo_must_allow(struct svc_rqst *rqstp);
 #else
 static inline int nfsd4_init_slabs(void) { return 0; }
 static inline void nfsd4_free_slabs(void) { }
@@ -134,6 +135,10 @@ static inline void nfs4_state_shutdown_net(struct net *net) { }
 static inline void nfs4_reset_lease(time_t leasetime) { }
 static inline int nfs4_reset_recoverydir(char *recdir) { return 0; }
 static inline char * nfs4_recoverydir(void) {return NULL; }
+static inline bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
+{
+	return false;
+}
 #endif
 
 /*
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 64053eadeb81..b95adf9a1595 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -345,6 +345,7 @@ struct nfs4_client {
 	u32			cl_exchange_flags;
 	/* number of rpc's in progress over an associated session: */
 	atomic_t		cl_refcount;
+	struct nfs4_op_map      cl_spo_must_allow;
 
 	/* for nfs41 callbacks */
 	/* We currently support a single back channel with a single slot */
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 74342a7c208a..beea0c5edc51 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -59,6 +59,7 @@ struct nfsd4_compound_state {
 	struct nfsd4_session	*session;
 	struct nfsd4_slot	*slot;
 	int			data_offset;
+	bool                    spo_must_allowed;
 	size_t			iovlen;
 	u32			minorversion;
 	__be32			status;
@@ -403,6 +404,8 @@ struct nfsd4_exchange_id {
 	clientid_t	clientid;
 	u32		seqid;
 	int		spa_how;
+	u32             spo_must_enforce[3];
+	u32             spo_must_allow[3];
 };
 
 struct nfsd4_sequence {
-- 
cgit v1.2.3


From d7c920d1349ad78b9181d8933404e1a378da6feb Mon Sep 17 00:00:00 2001
From: Tom Haynes <thomas.haynes@primarydata.com>
Date: Tue, 14 Jun 2016 13:41:27 -0700
Subject: nfsd: flex file device id encoding will need the server address

Signed-off-by: Tom Haynes <loghyr@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jeff Layton <jlayton@poochiereds.net>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/blocklayout.c | 2 ++
 fs/nfsd/nfs4proc.c    | 2 +-
 fs/nfsd/pnfs.h        | 1 +
 3 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 31f3df193bdb..c98563d35822 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -162,6 +162,7 @@ nfsd4_block_get_device_info_simple(struct super_block *sb,
 
 static __be32
 nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
+		struct svc_rqst *rqstp,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
@@ -354,6 +355,7 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb,
 
 static __be32
 nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
+		struct svc_rqst *rqstp,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index b1159b3e9816..89fad8aeffe2 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1270,7 +1270,7 @@ nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
 	nfserr = nfs_ok;
 	if (gdp->gd_maxcount != 0) {
 		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb,
-					cstate->session->se_client, gdp);
+				rqstp, cstate->session->se_client, gdp);
 	}
 
 	gdp->gd_notify_types &= ops->notify_types;
diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
index 7d073b9b1553..e855677fb132 100644
--- a/fs/nfsd/pnfs.h
+++ b/fs/nfsd/pnfs.h
@@ -21,6 +21,7 @@ struct nfsd4_layout_ops {
 	u32		notify_types;
 
 	__be32 (*proc_getdeviceinfo)(struct super_block *sb,
+			struct svc_rqst *rqstp,
 			struct nfs4_client *clp,
 			struct nfsd4_getdeviceinfo *gdevp);
 	__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
-- 
cgit v1.2.3


From 9b9960a0ca4773e21c4b153ed355583946346b25 Mon Sep 17 00:00:00 2001
From: Tom Haynes <thomas.haynes@primarydata.com>
Date: Tue, 14 Jun 2016 13:41:28 -0700
Subject: nfsd: Add a super simple flex file server

Have a simple flex file server where the mds (NFSv4.1 or NFSv4.2)
is also the ds (NFSv3). I.e., the metadata and the data file are
the exact same file.

This will allow testing of the flex file client.

Simply add the "pnfs" export option to your export
in /etc/exports and mount from a client that supports
flex files.

Signed-off-by: Tom Haynes <loghyr@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/Kconfig             |  17 ++++++
 fs/nfsd/Makefile            |   1 +
 fs/nfsd/flexfilelayout.c    | 133 ++++++++++++++++++++++++++++++++++++++++++++
 fs/nfsd/flexfilelayoutxdr.c | 115 ++++++++++++++++++++++++++++++++++++++
 fs/nfsd/flexfilelayoutxdr.h |  49 ++++++++++++++++
 fs/nfsd/nfs4layouts.c       |  12 +++-
 fs/nfsd/pnfs.h              |   3 +
 7 files changed, 329 insertions(+), 1 deletion(-)
 create mode 100644 fs/nfsd/flexfilelayout.c
 create mode 100644 fs/nfsd/flexfilelayoutxdr.c
 create mode 100644 fs/nfsd/flexfilelayoutxdr.h

(limited to 'fs')

diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index c9f583d7bac8..e64d1a3ec770 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -111,6 +111,23 @@ config NFSD_SCSILAYOUT
 
 	  If unsure, say N.
 
+config NFSD_FLEXFILELAYOUT
+	bool "NFSv4.1 server support for pNFS Flex File layouts"
+	depends on NFSD_V4
+	select NFSD_PNFS
+	help
+	  This option enables support for the exporting pNFS Flex File
+	  layouts in the kernel's NFS server. The pNFS Flex File  layout
+	  enables NFS clients to directly perform I/O to NFSv3 devices
+	  accesible to both the server and the clients.  See
+	  draft-ietf-nfsv4-flex-files for more details.
+
+	  Warning, this server implements the bare minimum functionality
+	  to be a flex file server - it is for testing the client,
+	  not for use in production.
+
+	  If unsure, say N.
+
 config NFSD_V4_SECURITY_LABEL
 	bool "Provide Security Label support for NFSv4 server"
 	depends on NFSD_V4 && SECURITY
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index 3ae5f3c77e28..5f5d3a76980c 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -20,3 +20,4 @@ nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
 nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
 nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
 nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
+nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o
diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c
new file mode 100644
index 000000000000..df880e9fa71f
--- /dev/null
+++ b/fs/nfsd/flexfilelayout.c
@@ -0,0 +1,133 @@
+/*
+ * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
+ *
+ * The following implements a super-simple flex-file server
+ * where the NFSv4.1 mds is also the ds. And the storage is
+ * the same. I.e., writing to the mds via a NFSv4.1 WRITE
+ * goes to the same location as the NFSv3 WRITE.
+ */
+#include <linux/slab.h>
+
+#include <linux/nfsd/debug.h>
+
+#include <linux/sunrpc/addr.h>
+
+#include "flexfilelayoutxdr.h"
+#include "pnfs.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+static __be32
+nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
+		struct nfsd4_layoutget *args)
+{
+	struct nfsd4_layout_seg *seg = &args->lg_seg;
+	u32 device_generation = 0;
+	int error;
+	uid_t u;
+
+	struct pnfs_ff_layout *fl;
+
+	/*
+	 * The super simple flex file server has 1 mirror, 1 data server,
+	 * and 1 file handle. So instead of 4 allocs, do 1 for now.
+	 * Zero it out for the stateid - don't want junk in there!
+	 */
+	error = -ENOMEM;
+	fl = kzalloc(sizeof(*fl), GFP_KERNEL);
+	if (!fl)
+		goto out_error;
+	args->lg_content = fl;
+
+	/*
+	 * Avoid layout commit, try to force the I/O to the DS,
+	 * and for fun, cause all IOMODE_RW layout segments to
+	 * effectively be WRITE only.
+	 */
+	fl->flags = FF_FLAGS_NO_LAYOUTCOMMIT | FF_FLAGS_NO_IO_THRU_MDS |
+		    FF_FLAGS_NO_READ_IO;
+
+	/* Do not allow a IOMODE_READ segment to have write pemissions */
+	if (seg->iomode == IOMODE_READ) {
+		u = from_kuid(&init_user_ns, inode->i_uid) + 1;
+		fl->uid = make_kuid(&init_user_ns, u);
+	} else
+		fl->uid = inode->i_uid;
+	fl->gid = inode->i_gid;
+
+	error = nfsd4_set_deviceid(&fl->deviceid, fhp, device_generation);
+	if (error)
+		goto out_error;
+
+	fl->fh.size = fhp->fh_handle.fh_size;
+	memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size);
+
+	/* Give whole file layout segments */
+	seg->offset = 0;
+	seg->length = NFS4_MAX_UINT64;
+
+	dprintk("GET: 0x%llx:0x%llx %d\n", seg->offset, seg->length,
+		seg->iomode);
+	return 0;
+
+out_error:
+	seg->length = 0;
+	return nfserrno(error);
+}
+
+static __be32
+nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, struct svc_rqst *rqstp,
+		struct nfs4_client *clp, struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_ff_device_addr *da;
+
+	u16 port;
+	char addr[INET6_ADDRSTRLEN];
+
+	da = kzalloc(sizeof(struct pnfs_ff_device_addr), GFP_KERNEL);
+	if (!da)
+		return nfserrno(-ENOMEM);
+
+	gdp->gd_device = da;
+
+	da->version = 3;
+	da->minor_version = 0;
+
+	da->rsize = svc_max_payload(rqstp);
+	da->wsize = da->rsize;
+
+	rpc_ntop((struct sockaddr *)&rqstp->rq_daddr,
+		 addr, INET6_ADDRSTRLEN);
+	if (rqstp->rq_daddr.ss_family == AF_INET) {
+		struct sockaddr_in *sin;
+
+		sin = (struct sockaddr_in *)&rqstp->rq_daddr;
+		port = ntohs(sin->sin_port);
+		snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp");
+		da->netaddr.netid_len = 3;
+	} else {
+		struct sockaddr_in6 *sin6;
+
+		sin6 = (struct sockaddr_in6 *)&rqstp->rq_daddr;
+		port = ntohs(sin6->sin6_port);
+		snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp6");
+		da->netaddr.netid_len = 4;
+	}
+
+	da->netaddr.addr_len =
+		snprintf(da->netaddr.addr, FF_ADDR_LEN + 1,
+			 "%s.%hhu.%hhu", addr, port >> 8, port & 0xff);
+
+	da->tightly_coupled = false;
+
+	return 0;
+}
+
+const struct nfsd4_layout_ops ff_layout_ops = {
+	.notify_types		=
+			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
+	.proc_getdeviceinfo	= nfsd4_ff_proc_getdeviceinfo,
+	.encode_getdeviceinfo	= nfsd4_ff_encode_getdeviceinfo,
+	.proc_layoutget		= nfsd4_ff_proc_layoutget,
+	.encode_layoutget	= nfsd4_ff_encode_layoutget,
+};
diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c
new file mode 100644
index 000000000000..5e3fd7fc1a9f
--- /dev/null
+++ b/fs/nfsd/flexfilelayoutxdr.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
+ */
+#include <linux/sunrpc/svc.h>
+#include <linux/nfs4.h>
+
+#include "nfsd.h"
+#include "flexfilelayoutxdr.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+struct ff_idmap {
+	char buf[11];
+	int len;
+};
+
+__be32
+nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
+		struct nfsd4_layoutget *lgp)
+{
+	struct pnfs_ff_layout *fl = lgp->lg_content;
+	int len, mirror_len, ds_len, fh_len;
+	__be32 *p;
+
+	/*
+	 * Unlike nfsd4_encode_user, we know these will
+	 * always be stringified.
+	 */
+	struct ff_idmap uid;
+	struct ff_idmap gid;
+
+	fh_len = 4 + fl->fh.size;
+
+	uid.len = sprintf(uid.buf, "%u", from_kuid(&init_user_ns, fl->uid));
+	gid.len = sprintf(gid.buf, "%u", from_kgid(&init_user_ns, fl->gid));
+
+	/* 8 + len for recording the length, name, and padding */
+	ds_len = 20 + sizeof(stateid_opaque_t) + 4 + fh_len +
+		 8 + uid.len + 8 + gid.len;
+
+	mirror_len = 4 + ds_len;
+
+	/* The layout segment */
+	len = 20 + mirror_len;
+
+	p = xdr_reserve_space(xdr, sizeof(__be32) + len);
+	if (!p)
+		return nfserr_toosmall;
+
+	*p++ = cpu_to_be32(len);
+	p = xdr_encode_hyper(p, 0);		/* stripe unit of 1 */
+
+	*p++ = cpu_to_be32(1);			/* single mirror */
+	*p++ = cpu_to_be32(1);			/* single data server */
+
+	p = xdr_encode_opaque_fixed(p, &fl->deviceid,
+			sizeof(struct nfsd4_deviceid));
+
+	*p++ = cpu_to_be32(1);			/* efficiency */
+
+	*p++ = cpu_to_be32(fl->stateid.si_generation);
+	p = xdr_encode_opaque_fixed(p, &fl->stateid.si_opaque,
+				    sizeof(stateid_opaque_t));
+
+	*p++ = cpu_to_be32(1);			/* single file handle */
+	p = xdr_encode_opaque(p, fl->fh.data, fl->fh.size);
+
+	p = xdr_encode_opaque(p, uid.buf, uid.len);
+	p = xdr_encode_opaque(p, gid.buf, gid.len);
+
+	*p++ = cpu_to_be32(fl->flags);
+	*p++ = cpu_to_be32(0);			/* No stats collect hint */
+
+	return 0;
+}
+
+__be32
+nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_ff_device_addr *da = gdp->gd_device;
+	int len;
+	int ver_len;
+	int addr_len;
+	__be32 *p;
+
+	/* len + padding for two strings */
+	addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len;
+	ver_len = 20;
+
+	len = 4 + ver_len + 4 + addr_len;
+
+	p = xdr_reserve_space(xdr, len + sizeof(__be32));
+	if (!p)
+		return nfserr_resource;
+
+	/*
+	 * Fill in the overall length and number of volumes at the beginning
+	 * of the layout.
+	 */
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(1);			/* 1 netaddr */
+	p = xdr_encode_opaque(p, da->netaddr.netid, da->netaddr.netid_len);
+	p = xdr_encode_opaque(p, da->netaddr.addr, da->netaddr.addr_len);
+
+	*p++ = cpu_to_be32(1);			/* 1 versions */
+
+	*p++ = cpu_to_be32(da->version);
+	*p++ = cpu_to_be32(da->minor_version);
+	*p++ = cpu_to_be32(da->rsize);
+	*p++ = cpu_to_be32(da->wsize);
+	*p++ = cpu_to_be32(da->tightly_coupled);
+
+	return 0;
+}
diff --git a/fs/nfsd/flexfilelayoutxdr.h b/fs/nfsd/flexfilelayoutxdr.h
new file mode 100644
index 000000000000..467defd4e563
--- /dev/null
+++ b/fs/nfsd/flexfilelayoutxdr.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
+ */
+#ifndef _NFSD_FLEXFILELAYOUTXDR_H
+#define _NFSD_FLEXFILELAYOUTXDR_H 1
+
+#include <linux/inet.h>
+#include "xdr4.h"
+
+#define FF_FLAGS_NO_LAYOUTCOMMIT 1
+#define FF_FLAGS_NO_IO_THRU_MDS  2
+#define FF_FLAGS_NO_READ_IO      4
+
+struct xdr_stream;
+
+#define FF_NETID_LEN		(4)
+#define FF_ADDR_LEN		(INET6_ADDRSTRLEN + 8)
+struct pnfs_ff_netaddr {
+	char				netid[FF_NETID_LEN + 1];
+	char				addr[FF_ADDR_LEN + 1];
+	u32				netid_len;
+	u32				addr_len;
+};
+
+struct pnfs_ff_device_addr {
+	struct pnfs_ff_netaddr		netaddr;
+	u32				version;
+	u32				minor_version;
+	u32				rsize;
+	u32				wsize;
+	bool				tightly_coupled;
+};
+
+struct pnfs_ff_layout {
+	u32				flags;
+	u32				stats_collect_hint;
+	kuid_t				uid;
+	kgid_t				gid;
+	struct nfsd4_deviceid		deviceid;
+	stateid_t			stateid;
+	struct nfs_fh			fh;
+};
+
+__be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr,
+		struct nfsd4_getdeviceinfo *gdp);
+__be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
+		struct nfsd4_layoutget *lgp);
+
+#endif /* _NFSD_FLEXFILELAYOUTXDR_H */
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 953c0755cb37..6d98d16b3354 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -27,6 +27,9 @@ static const struct nfsd4_callback_ops nfsd4_cb_layout_ops;
 static const struct lock_manager_operations nfsd4_layouts_lm_ops;
 
 const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
+#ifdef CONFIG_NFSD_FLEXFILELAYOUT
+	[LAYOUT_FLEX_FILES]	= &ff_layout_ops,
+#endif
 #ifdef CONFIG_NFSD_BLOCKLAYOUT
 	[LAYOUT_BLOCK_VOLUME]	= &bl_layout_ops,
 #endif
@@ -122,17 +125,24 @@ nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
 
 void nfsd4_setup_layout_type(struct svc_export *exp)
 {
+#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT)
 	struct super_block *sb = exp->ex_path.mnt->mnt_sb;
+#endif
 
 	if (!(exp->ex_flags & NFSEXP_PNFS))
 		return;
 
 	/*
-	 * Check if the file system supports exporting a block-like layout.
+	 * If flex file is configured, use it by default. Otherwise
+	 * check if the file system supports exporting a block-like layout.
 	 * If the block device supports reservations prefer the SCSI layout,
 	 * otherwise advertise the block layout.
 	 */
+#ifdef CONFIG_NFSD_FLEXFILELAYOUT
+	exp->ex_layout_type = LAYOUT_FLEX_FILES;
+#endif
 #ifdef CONFIG_NFSD_BLOCKLAYOUT
+	/* overwrite flex file layout selection if needed */
 	if (sb->s_export_op->get_uuid &&
 	    sb->s_export_op->map_blocks &&
 	    sb->s_export_op->commit_blocks)
diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
index e855677fb132..0c2a716e8741 100644
--- a/fs/nfsd/pnfs.h
+++ b/fs/nfsd/pnfs.h
@@ -45,6 +45,9 @@ extern const struct nfsd4_layout_ops bl_layout_ops;
 #ifdef CONFIG_NFSD_SCSILAYOUT
 extern const struct nfsd4_layout_ops scsi_layout_ops;
 #endif
+#ifdef CONFIG_NFSD_FLEXFILELAYOUT
+extern const struct nfsd4_layout_ops ff_layout_ops;
+#endif
 
 __be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, stateid_t *stateid,
-- 
cgit v1.2.3


From 93f580a9a2413def2fcc5fd07085efcd95943f1b Mon Sep 17 00:00:00 2001
From: Oleg Drokin <green@linuxhacker.ru>
Date: Thu, 7 Jul 2016 21:49:38 -0400
Subject: nfsd: Correct a comment for NFSD_MAY_ defines location

Those are now defined in fs/nfsd/vfs.h

Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Reviewed-by: Jeff Layton <jlayton@poochiereds.net>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfsfh.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index a8919444c460..7e49dcbbf452 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -298,7 +298,7 @@ out:
  * that it expects something not of the given type.
  *
  * @access is formed from the NFSD_MAY_* constants defined in
- * include/linux/nfsd/nfsd.h.
+ * fs/nfsd/vfs.h.
  */
 __be32
 fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
-- 
cgit v1.2.3


From d28c442f5bd5471adc4d1add5fa78109f811c0a3 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 2 Jul 2016 08:24:32 +0200
Subject: nfsd: Fix some indent inconsistancy

Silent a few smatch warnings about indentation

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4state.c | 2 +-
 fs/nfsd/nfsfh.c     | 2 +-
 fs/nfsd/nfsxdr.c    | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ebfcebd5eab1..bc2173a31b5d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3130,7 +3130,7 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
 		 * We don't take advantage of the rca_one_fs case.
 		 * That's OK, it's optional, we can safely ignore it.
 		 */
-		 return nfs_ok;
+		return nfs_ok;
 	}
 
 	status = nfserr_complete_already;
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 7e49dcbbf452..27250e279c37 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -533,7 +533,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 	 * the reference filehandle (if it is in the same export)
 	 * or the export options.
 	 */
-	 set_version_and_fsid_type(fhp, exp, ref_fh);
+	set_version_and_fsid_type(fhp, exp, ref_fh);
 
 	if (ref_fh == fhp)
 		fh_put(ref_fh);
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 79d964aa8079..41b468a6a90f 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -240,7 +240,7 @@ nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
 
-	 return xdr_argsize_check(rqstp, p);
+	return xdr_argsize_check(rqstp, p);
 }
 
 int
-- 
cgit v1.2.3


From 15d66ac20927e00ac0e65af6707eff60b92e61b8 Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Fri, 8 Jul 2016 09:53:20 -0400
Subject: xfs: abstract block export operations from nfsd layouts

Instead of creeping pnfs layout configuration into filesystems, move the
definition of block-based export operations under a more abstract
configuration.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/Kconfig          | 6 ++++++
 fs/nfsd/Kconfig     | 2 ++
 fs/xfs/Makefile     | 3 +--
 fs/xfs/xfs_export.c | 2 +-
 fs/xfs/xfs_pnfs.h   | 4 ++--
 5 files changed, 12 insertions(+), 5 deletions(-)

(limited to 'fs')

diff --git a/fs/Kconfig b/fs/Kconfig
index b8fcb416be72..4d2f9210e748 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -67,6 +67,12 @@ config FS_POSIX_ACL
 config EXPORTFS
 	tristate
 
+config EXPORTFS_BLOCK_OPS
+	bool "Enable filesystem export operations for block IO"
+	help
+	  This option enables the export operations for a filesystem to support
+	  external block IO.
+
 config FILE_LOCKING
 	bool "Enable POSIX file locking API" if EXPERT
 	default y
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index e64d1a3ec770..47febcf99185 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -90,6 +90,7 @@ config NFSD_BLOCKLAYOUT
 	bool "NFSv4.1 server support for pNFS block layouts"
 	depends on NFSD_V4 && BLOCK
 	select NFSD_PNFS
+	select EXPORTFS_BLOCK_OPS
 	help
 	  This option enables support for the exporting pNFS block layouts
 	  in the kernel's NFS server. The pNFS block layout enables NFS
@@ -102,6 +103,7 @@ config NFSD_SCSILAYOUT
 	bool "NFSv4.1 server support for pNFS SCSI layouts"
 	depends on NFSD_V4 && BLOCK
 	select NFSD_PNFS
+	select EXPORTFS_BLOCK_OPS
 	help
 	  This option enables support for the exporting pNFS SCSI layouts
 	  in the kernel's NFS server. The pNFS SCSI layout enables NFS
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 3542d94fddce..52c288514be1 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -121,5 +121,4 @@ xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o
 xfs-$(CONFIG_XFS_POSIX_ACL)	+= xfs_acl.o
 xfs-$(CONFIG_SYSCTL)		+= xfs_sysctl.o
 xfs-$(CONFIG_COMPAT)		+= xfs_ioctl32.o
-xfs-$(CONFIG_NFSD_BLOCKLAYOUT)	+= xfs_pnfs.o
-xfs-$(CONFIG_NFSD_SCSILAYOUT)	+= xfs_pnfs.o
+xfs-$(CONFIG_EXPORTFS_BLOCK_OPS)	+= xfs_pnfs.o
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index a1b2dd828b9d..fe1bfee35898 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -246,7 +246,7 @@ const struct export_operations xfs_export_operations = {
 	.fh_to_parent		= xfs_fs_fh_to_parent,
 	.get_parent		= xfs_fs_get_parent,
 	.commit_metadata	= xfs_fs_nfs_commit_metadata,
-#ifdef CONFIG_NFSD_BLOCKLAYOUT
+#ifdef CONFIG_EXPORTFS_BLOCK_OPS
 	.get_uuid		= xfs_fs_get_uuid,
 	.map_blocks		= xfs_fs_map_blocks,
 	.commit_blocks		= xfs_fs_commit_blocks,
diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h
index 93f74853961b..e8339f74966b 100644
--- a/fs/xfs/xfs_pnfs.h
+++ b/fs/xfs/xfs_pnfs.h
@@ -1,7 +1,7 @@
 #ifndef _XFS_PNFS_H
 #define _XFS_PNFS_H 1
 
-#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT)
+#ifdef CONFIG_EXPORTFS_BLOCK_OPS
 int xfs_fs_get_uuid(struct super_block *sb, u8 *buf, u32 *len, u64 *offset);
 int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length,
 		struct iomap *iomap, bool write, u32 *device_generation);
@@ -15,5 +15,5 @@ xfs_break_layouts(struct inode *inode, uint *iolock, bool with_imutex)
 {
 	return 0;
 }
-#endif /* CONFIG_NFSD_PNFS */
+#endif /* CONFIG_EXPORTFS_BLOCK_OPS */
 #endif /* _XFS_PNFS_H */
-- 
cgit v1.2.3


From dd51db188600c8c54c46cff84e83358ece8ccb4d Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Thu, 14 Jul 2016 12:01:17 +0800
Subject: nfsd/blocklayout: Make sure calculate signature/designator length
 aligned

These values are all multiples of 4 already, so there's no change in
behavior from this patch.  But perhaps this will prevent mistakes in the
future.

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/blocklayoutxdr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c
index 6c3b316f932e..d72467e5eb6e 100644
--- a/fs/nfsd/blocklayoutxdr.c
+++ b/fs/nfsd/blocklayoutxdr.c
@@ -43,7 +43,7 @@ nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 
 	switch (b->type) {
 	case PNFS_BLOCK_VOLUME_SIMPLE:
-		len = 4 + 4 + 8 + 4 + b->simple.sig_len;
+		len = 4 + 4 + 8 + 4 + (XDR_QUADLEN(b->simple.sig_len) << 2);
 		p = xdr_reserve_space(xdr, len);
 		if (!p)
 			return -ETOOSMALL;
@@ -54,7 +54,7 @@ nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 		p = xdr_encode_opaque(p, b->simple.sig, b->simple.sig_len);
 		break;
 	case PNFS_BLOCK_VOLUME_SCSI:
-		len = 4 + 4 + 4 + 4 + b->scsi.designator_len + 8;
+		len = 4 + 4 + 4 + 4 + (XDR_QUADLEN(b->scsi.designator_len) << 2) + 8;
 		p = xdr_reserve_space(xdr, len);
 		if (!p)
 			return -ETOOSMALL;
-- 
cgit v1.2.3


From 885848186fbc2d1d8fb6d2fdc2156638ae289a46 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 13 Jul 2016 16:40:14 -0400
Subject: nfsd: Close race between nfsd4_release_lockowner and nfsd4_lock

nfsd4_release_lockowner finds a lock owner that has no lock state,
and drops cl_lock. Then release_lockowner picks up cl_lock and
unhashes the lock owner.

During the window where cl_lock is dropped, I don't see anything
preventing a concurrent nfsd4_lock from finding that same lock owner
and adding lock state to it.

Move release_lockowner() into nfsd4_release_lockowner and hang onto
the cl_lock until after the lock owner's state cannot be found
again.

Found by inspection, we don't currently have a reproducer.

Fixes: 2c41beb0e5cf ("nfsd: reduce cl_lock thrashing in ... ")
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4state.c | 40 +++++++++++++++++-----------------------
 1 file changed, 17 insertions(+), 23 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index bc2173a31b5d..8410ca275db1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1200,27 +1200,6 @@ free_ol_stateid_reaplist(struct list_head *reaplist)
 	}
 }
 
-static void release_lockowner(struct nfs4_lockowner *lo)
-{
-	struct nfs4_client *clp = lo->lo_owner.so_client;
-	struct nfs4_ol_stateid *stp;
-	struct list_head reaplist;
-
-	INIT_LIST_HEAD(&reaplist);
-
-	spin_lock(&clp->cl_lock);
-	unhash_lockowner_locked(lo);
-	while (!list_empty(&lo->lo_owner.so_stateids)) {
-		stp = list_first_entry(&lo->lo_owner.so_stateids,
-				struct nfs4_ol_stateid, st_perstateowner);
-		WARN_ON(!unhash_lock_stateid(stp));
-		put_ol_stateid_locked(stp, &reaplist);
-	}
-	spin_unlock(&clp->cl_lock);
-	free_ol_stateid_reaplist(&reaplist);
-	nfs4_put_stateowner(&lo->lo_owner);
-}
-
 static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
 				       struct list_head *reaplist)
 {
@@ -5963,6 +5942,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 	__be32 status;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct nfs4_client *clp;
+	LIST_HEAD (reaplist);
 
 	dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
 		clid->cl_boot, clid->cl_id);
@@ -5993,9 +5973,23 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		nfs4_get_stateowner(sop);
 		break;
 	}
+	if (!lo) {
+		spin_unlock(&clp->cl_lock);
+		return status;
+	}
+
+	unhash_lockowner_locked(lo);
+	while (!list_empty(&lo->lo_owner.so_stateids)) {
+		stp = list_first_entry(&lo->lo_owner.so_stateids,
+				       struct nfs4_ol_stateid,
+				       st_perstateowner);
+		WARN_ON(!unhash_lock_stateid(stp));
+		put_ol_stateid_locked(stp, &reaplist);
+	}
 	spin_unlock(&clp->cl_lock);
-	if (lo)
-		release_lockowner(lo);
+	free_ol_stateid_reaplist(&reaplist);
+	nfs4_put_stateowner(&lo->lo_owner);
+
 	return status;
 }
 
-- 
cgit v1.2.3


From 8a4c3926889e7bf226e9f0254e7eface1f85f312 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@poochiereds.net>
Date: Sun, 10 Jul 2016 15:55:58 -0400
Subject: nfsd: allow nfsd to advertise multiple layout types

If the underlying filesystem supports multiple layout types, then there
is little reason not to advertise that fact to clients and let them
choose what type to use.

Turn the ex_layout_type field into a bitfield. For each supported
layout type, we set a bit in that field. When the client requests a
layout, ensure that the bit for that layout type is set. When the
client requests attributes, send back a list of supported types.

Signed-off-by: Jeff Layton <jlayton@poochiereds.net>
Reviewed-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/export.c      |  4 ++--
 fs/nfsd/export.h      |  2 +-
 fs/nfsd/nfs4layouts.c |  6 +++---
 fs/nfsd/nfs4proc.c    |  4 ++--
 fs/nfsd/nfs4xdr.c     | 30 ++++++++++++++----------------
 5 files changed, 22 insertions(+), 24 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 79de2f38dd63..43e109cc0ccc 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -706,7 +706,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_fslocs.locations = NULL;
 	new->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = 0;
-	new->ex_layout_type = 0;
+	new->ex_layout_types = 0;
 	new->ex_uuid = NULL;
 	new->cd = item->cd;
 }
@@ -731,7 +731,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	item->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = item->ex_fslocs.migrated;
 	item->ex_fslocs.migrated = 0;
-	new->ex_layout_type = item->ex_layout_type;
+	new->ex_layout_types = item->ex_layout_types;
 	new->ex_nflavors = item->ex_nflavors;
 	for (i = 0; i < MAX_SECINFO_LIST; i++) {
 		new->ex_flavors[i] = item->ex_flavors[i];
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index 2e315072bf3f..730f15eeb7ed 100644
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -57,7 +57,7 @@ struct svc_export {
 	struct nfsd4_fs_locations ex_fslocs;
 	uint32_t		ex_nflavors;
 	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
-	enum pnfs_layouttype	ex_layout_type;
+	u32			ex_layout_types;
 	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
 };
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 6d98d16b3354..2be9602b0221 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -139,21 +139,21 @@ void nfsd4_setup_layout_type(struct svc_export *exp)
 	 * otherwise advertise the block layout.
 	 */
 #ifdef CONFIG_NFSD_FLEXFILELAYOUT
-	exp->ex_layout_type = LAYOUT_FLEX_FILES;
+	exp->ex_layout_types |= 1 << LAYOUT_FLEX_FILES;
 #endif
 #ifdef CONFIG_NFSD_BLOCKLAYOUT
 	/* overwrite flex file layout selection if needed */
 	if (sb->s_export_op->get_uuid &&
 	    sb->s_export_op->map_blocks &&
 	    sb->s_export_op->commit_blocks)
-		exp->ex_layout_type = LAYOUT_BLOCK_VOLUME;
+		exp->ex_layout_types |= 1 << LAYOUT_BLOCK_VOLUME;
 #endif
 #ifdef CONFIG_NFSD_SCSILAYOUT
 	/* overwrite block layout selection if needed */
 	if (sb->s_export_op->map_blocks &&
 	    sb->s_export_op->commit_blocks &&
 	    sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops)
-		exp->ex_layout_type = LAYOUT_SCSI;
+		exp->ex_layout_types |= 1 << LAYOUT_SCSI;
 #endif
 }
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 89fad8aeffe2..e0c15f879d89 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1219,12 +1219,12 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 static const struct nfsd4_layout_ops *
 nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
 {
-	if (!exp->ex_layout_type) {
+	if (!exp->ex_layout_types) {
 		dprintk("%s: export does not support pNFS\n", __func__);
 		return NULL;
 	}
 
-	if (exp->ex_layout_type != layout_type) {
+	if (!(exp->ex_layout_types & (1 << layout_type))) {
 		dprintk("%s: layout type %d not supported\n",
 			__func__, layout_type);
 		return NULL;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 84ef94794496..0aa0236a1429 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2162,22 +2162,20 @@ nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp,
 }
 
 static inline __be32
-nfsd4_encode_layout_type(struct xdr_stream *xdr, enum pnfs_layouttype layout_type)
+nfsd4_encode_layout_types(struct xdr_stream *xdr, u32 layout_types)
 {
-	__be32 *p;
+	__be32		*p;
+	unsigned long	i = hweight_long(layout_types);
 
-	if (layout_type) {
-		p = xdr_reserve_space(xdr, 8);
-		if (!p)
-			return nfserr_resource;
-		*p++ = cpu_to_be32(1);
-		*p++ = cpu_to_be32(layout_type);
-	} else {
-		p = xdr_reserve_space(xdr, 4);
-		if (!p)
-			return nfserr_resource;
-		*p++ = cpu_to_be32(0);
-	}
+	p = xdr_reserve_space(xdr, 4 + 4 * i);
+	if (!p)
+		return nfserr_resource;
+
+	*p++ = cpu_to_be32(i);
+
+	for (i = LAYOUT_NFSV4_1_FILES; i < LAYOUT_TYPE_MAX; ++i)
+		if (layout_types & (1 << i))
+			*p++ = cpu_to_be32(i);
 
 	return 0;
 }
@@ -2752,13 +2750,13 @@ out_acl:
 	}
 #ifdef CONFIG_NFSD_PNFS
 	if (bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) {
-		status = nfsd4_encode_layout_type(xdr, exp->ex_layout_type);
+		status = nfsd4_encode_layout_types(xdr, exp->ex_layout_types);
 		if (status)
 			goto out;
 	}
 
 	if (bmval2 & FATTR4_WORD2_LAYOUT_TYPES) {
-		status = nfsd4_encode_layout_type(xdr, exp->ex_layout_type);
+		status = nfsd4_encode_layout_types(xdr, exp->ex_layout_types);
 		if (status)
 			goto out;
 	}
-- 
cgit v1.2.3


From 7eed34f18d9f0f96f51bfb73d649a51a20857eb0 Mon Sep 17 00:00:00 2001
From: Oleg Drokin <green@linuxhacker.ru>
Date: Thu, 14 Jul 2016 23:20:22 -0400
Subject: nfsd: Make creates return EEXIST instead of EACCES

When doing a create (mkdir/mknod) on a name, it's worth
checking the name exists first before returning EACCES in case
the directory is not writeable by the user.
This makes return values on the client more consistent
regardless of whenever the entry there is cached in the local
cache or not.
Another positive side effect is certain programs only expect
EEXIST in that case even despite POSIX allowing any valid
error to be returned.

Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4proc.c |  6 +++++-
 fs/nfsd/vfs.c      | 11 ++++++++++-
 2 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index e0c15f879d89..9d7e1edf0cca 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -605,8 +605,12 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	fh_init(&resfh, NFS4_FHSIZE);
 
+	/*
+	 * We just check that parent is accessible here, nfsd_* do their
+	 * own access permission checks
+	 */
 	status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR,
-			   NFSD_MAY_CREATE);
+			   NFSD_MAY_EXEC);
 	if (status)
 		return status;
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 6fbd81ecb410..fda4f86161f8 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1161,7 +1161,11 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (isdotent(fname, flen))
 		goto out;
 
-	err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
+	/*
+	 * Even though it is a create, first let's see if we are even allowed
+	 * to peek inside the parent
+	 */
+	err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
 	if (err)
 		goto out;
 
@@ -1211,6 +1215,11 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out; 
 	}
 
+	/* Now let's see if we actually have permissions to create */
+	err = nfsd_permission(rqstp, fhp->fh_export, dentry, NFSD_MAY_CREATE);
+	if (err)
+		goto out;
+
 	if (!(iap->ia_valid & ATTR_MODE))
 		iap->ia_mode = 0;
 	iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;
-- 
cgit v1.2.3


From 12391d07230ec7368269227207b961b2dcb34180 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Tue, 19 Jul 2016 17:25:42 -0400
Subject: nfsd: remove redundant zero-length check from create

lookup_one_len already has this check.

The only effect of this patch is to return access instead of perm in the
0-length-filename case.  I actually prefer nfserr_perm (or _inval?), but
I doubt anyone cares.

The isdotent check seems redundant too, but I worry that some client
might actually care about that strange nfserr_exist error.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfsproc.c | 3 ---
 fs/nfsd/vfs.c     | 3 ---
 2 files changed, 6 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 4cd78ef4c95c..6722fe52ea15 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -251,9 +251,6 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
 
 	/* Check for NFSD_MAY_WRITE in nfsd_create if necessary */
 
-	nfserr = nfserr_acces;
-	if (!argp->len)
-		goto done;
 	nfserr = nfserr_exist;
 	if (isdotent(argp->name, argp->len))
 		goto done;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fda4f86161f8..fba8e7e521e0 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1154,9 +1154,6 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	__be32		err2;
 	int		host_err;
 
-	err = nfserr_perm;
-	if (!flen)
-		goto out;
 	err = nfserr_exist;
 	if (isdotent(fname, flen))
 		goto out;
-- 
cgit v1.2.3


From e75b23f9e323b1e0759619c39d5a9f7a3a5d9d2c Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Tue, 19 Jul 2016 17:33:04 -0400
Subject: nfsd: check d_can_lookup in fh_verify of directories

Create and other nfsd ops generally assume we can call lookup_one_len on
inodes with S_IFDIR set.  Al says that this assumption isn't true in
general, though it should be for the filesystem objects nfsd sees.

Add a check just to make sure our assumption isn't violated.

Remove a couple checks for i_op->lookup in create code.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfsfh.c | 14 ++++++++++----
 fs/nfsd/vfs.c   |  9 ---------
 2 files changed, 10 insertions(+), 13 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 27250e279c37..cfe7500d5847 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -59,14 +59,20 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry)
  * the write call).
  */
 static inline __be32
-nfsd_mode_check(struct svc_rqst *rqstp, umode_t mode, umode_t requested)
+nfsd_mode_check(struct svc_rqst *rqstp, struct dentry *dentry,
+		umode_t requested)
 {
-	mode &= S_IFMT;
+	umode_t mode = d_inode(dentry)->i_mode & S_IFMT;
 
 	if (requested == 0) /* the caller doesn't care */
 		return nfs_ok;
-	if (mode == requested)
+	if (mode == requested) {
+		if (mode == S_IFDIR && !d_can_lookup(dentry)) {
+			WARN_ON_ONCE(1);
+			return nfserr_notdir;
+		}
 		return nfs_ok;
+	}
 	/*
 	 * v4 has an error more specific than err_notdir which we should
 	 * return in preference to err_notdir:
@@ -340,7 +346,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
 	if (error)
 		goto out;
 
-	error = nfsd_mode_check(rqstp, d_inode(dentry)->i_mode, type);
+	error = nfsd_mode_check(rqstp, dentry, type);
 	if (error)
 		goto out;
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fba8e7e521e0..cf14e394a1b0 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1169,9 +1169,6 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	dentry = fhp->fh_dentry;
 	dirp = d_inode(dentry);
 
-	err = nfserr_notdir;
-	if (!dirp->i_op->lookup)
-		goto out;
 	/*
 	 * Check whether the response file handle has been verified yet.
 	 * If it has, the parent directory should already be locked.
@@ -1310,12 +1307,6 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	dentry = fhp->fh_dentry;
 	dirp = d_inode(dentry);
 
-	/* Get all the sanity checks out of the way before
-	 * we lock the parent. */
-	err = nfserr_notdir;
-	if (!dirp->i_op->lookup)
-		goto out;
-
 	host_err = fh_want_write(fhp);
 	if (host_err)
 		goto out_nfserr;
-- 
cgit v1.2.3


From b44061d0b914c11fb8f8a747c91d111973f56d76 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Wed, 20 Jul 2016 16:16:06 -0400
Subject: nfsd: reorganize nfsd_create

There's some odd logic in nfsd_create() that allows it to be called with
the parent directory either locked or unlocked.  The only already-locked
caller is NFSv2's nfsd_proc_create().  It's less confusing to split out
the unlocked case into a separate function which the NFSv2 code can call
directly.

Also fix some comments while we're here.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfsproc.c |   4 +-
 fs/nfsd/vfs.c     | 109 ++++++++++++++++++++++++++++--------------------------
 fs/nfsd/vfs.h     |   3 ++
 3 files changed, 61 insertions(+), 55 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 6722fe52ea15..e9214768cde9 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -359,8 +359,8 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
 	nfserr = 0;
 	if (!inode) {
 		/* File doesn't exist. Create it and set attrs */
-		nfserr = nfsd_create(rqstp, dirfhp, argp->name, argp->len,
-					attr, type, rdev, newfhp);
+		nfserr = nfsd_create_locked(rqstp, dirfhp, argp->name,
+					argp->len, attr, type, rdev, newfhp);
 	} else if (type == S_IFREG) {
 		dprintk("nfsd:   existing %s, valid=%x, size=%ld\n",
 			argp->name, attr->ia_valid, (long) attr->ia_size);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index cf14e394a1b0..d21d0827cac4 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1135,16 +1135,9 @@ nfsd_check_ignore_resizing(struct iattr *iap)
 		iap->ia_valid &= ~ATTR_SIZE;
 }
 
-/*
- * Create a file (regular, directory, device, fifo); UNIX sockets 
- * not yet implemented.
- * If the response fh has been verified, the parent directory should
- * already be locked. Note that the parent directory is left locked.
- *
- * N.B. Every call to nfsd_create needs an fh_put for _both_ fhp and resfhp
- */
+/* The parent directory should already be locked: */
 __be32
-nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
+nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		char *fname, int flen, struct iattr *iap,
 		int type, dev_t rdev, struct svc_fh *resfhp)
 {
@@ -1154,50 +1147,15 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	__be32		err2;
 	int		host_err;
 
-	err = nfserr_exist;
-	if (isdotent(fname, flen))
-		goto out;
-
-	/*
-	 * Even though it is a create, first let's see if we are even allowed
-	 * to peek inside the parent
-	 */
-	err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
-	if (err)
-		goto out;
-
 	dentry = fhp->fh_dentry;
 	dirp = d_inode(dentry);
 
-	/*
-	 * Check whether the response file handle has been verified yet.
-	 * If it has, the parent directory should already be locked.
-	 */
-	if (!resfhp->fh_dentry) {
-		host_err = fh_want_write(fhp);
-		if (host_err)
-			goto out_nfserr;
-
-		/* called from nfsd_proc_mkdir, or possibly nfsd3_proc_create */
-		fh_lock_nested(fhp, I_MUTEX_PARENT);
-		dchild = lookup_one_len(fname, dentry, flen);
-		host_err = PTR_ERR(dchild);
-		if (IS_ERR(dchild))
-			goto out_nfserr;
-		err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
-		if (err)
-			goto out;
-	} else {
-		/* called from nfsd_proc_create */
-		dchild = dget(resfhp->fh_dentry);
-		if (!fhp->fh_locked) {
-			/* not actually possible */
-			printk(KERN_ERR
-				"nfsd_create: parent %pd2 not locked!\n",
+	dchild = dget(resfhp->fh_dentry);
+	if (!fhp->fh_locked) {
+		WARN_ONCE(1, "nfsd_create: parent %pd2 not locked!\n",
 				dentry);
-			err = nfserr_io;
-			goto out;
-		}
+		err = nfserr_io;
+		goto out;
 	}
 	/*
 	 * Make sure the child dentry is still negative ...
@@ -1225,9 +1183,6 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out;
 	}
 
-	/*
-	 * Get the dir op function pointer.
-	 */
 	err = 0;
 	host_err = 0;
 	switch (type) {
@@ -1254,7 +1209,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	/*
 	 * nfsd_create_setattr already committed the child.  Transactional
 	 * filesystems had a chance to commit changes for both parent and
-	 * child * simultaneously making the following commit_metadata a
+	 * child simultaneously making the following commit_metadata a
 	 * noop.
 	 */
 	err2 = nfserrno(commit_metadata(fhp));
@@ -1275,6 +1230,54 @@ out_nfserr:
 	goto out;
 }
 
+/*
+ * Create a filesystem object (regular, directory, special).
+ * Note that the parent directory is left locked.
+ *
+ * N.B. Every call to nfsd_create needs an fh_put for _both_ fhp and resfhp
+ */
+__be32
+nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		char *fname, int flen, struct iattr *iap,
+		int type, dev_t rdev, struct svc_fh *resfhp)
+{
+	struct dentry	*dentry, *dchild = NULL;
+	struct inode	*dirp;
+	__be32		err;
+	int		host_err;
+
+	if (isdotent(fname, flen))
+		return nfserr_exist;
+
+	/*
+	 * Even though it is a create, first let's see if we are even allowed
+	 * to peek inside the parent
+	 */
+	err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
+	if (err)
+		return err;
+
+	dentry = fhp->fh_dentry;
+	dirp = d_inode(dentry);
+
+	host_err = fh_want_write(fhp);
+	if (host_err)
+		return nfserrno(host_err);
+
+	fh_lock_nested(fhp, I_MUTEX_PARENT);
+	dchild = lookup_one_len(fname, dentry, flen);
+	host_err = PTR_ERR(dchild);
+	if (IS_ERR(dchild))
+		return nfserrno(host_err);
+	err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
+	if (err) {
+		dput(dchild);
+		return err;
+	}
+	return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type,
+					rdev, resfhp);
+}
+
 #ifdef CONFIG_NFSD_V3
 
 /*
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 2d573ec057f8..3cbb1b33777b 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -59,6 +59,9 @@ __be32		nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *,
 __be32		nfsd4_clone_file_range(struct file *, u64, struct file *,
 			u64, u64);
 #endif /* CONFIG_NFSD_V4 */
+__be32		nfsd_create_locked(struct svc_rqst *, struct svc_fh *,
+				char *name, int len, struct iattr *attrs,
+				int type, dev_t rdev, struct svc_fh *res);
 __be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
 				char *name, int len, struct iattr *attrs,
 				int type, dev_t rdev, struct svc_fh *res);
-- 
cgit v1.2.3


From d03d9fe476ea81ad3be25967ef35a671dbd79b55 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Thu, 21 Jul 2016 21:55:42 -0400
Subject: nfsd: remove unnecessary positive-dentry check

vfs_{create,mkdir,mknod} each begin with a call to may_create(), which
returns EEXIST if the object already exists.

This check is therefore unnecessary.

(In the NFSv2 case, nfsd_proc_create also has such a check.  Contrary to
RFC 1094, our code seems to believe that a CREATE of an existing file
should succeed.  I'm leaving that behavior alone.)

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/vfs.c | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index d21d0827cac4..c95709486ca4 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1157,17 +1157,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		err = nfserr_io;
 		goto out;
 	}
-	/*
-	 * Make sure the child dentry is still negative ...
-	 */
-	err = nfserr_exist;
-	if (d_really_is_positive(dchild)) {
-		dprintk("nfsd_create: dentry %pd/%pd not negative!\n",
-			dentry, dchild);
-		goto out; 
-	}
 
-	/* Now let's see if we actually have permissions to create */
 	err = nfsd_permission(rqstp, fhp->fh_export, dentry, NFSD_MAY_CREATE);
 	if (err)
 		goto out;
-- 
cgit v1.2.3


From 71423274498169911bf9eedf02d5e7ac0a083801 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Fri, 22 Jul 2016 12:03:46 -0400
Subject: nfsd: clean up bad-type check in nfsd_create_locked

Minor cleanup, no change in behavior.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/vfs.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c95709486ca4..1809624997f0 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1166,13 +1166,6 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		iap->ia_mode = 0;
 	iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;
 
-	err = nfserr_inval;
-	if (!S_ISREG(type) && !S_ISDIR(type) && !special_file(type)) {
-		printk(KERN_WARNING "nfsd: bad file type %o in nfsd_create\n",
-		       type);
-		goto out;
-	}
-
 	err = 0;
 	host_err = 0;
 	switch (type) {
@@ -1190,6 +1183,10 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	case S_IFSOCK:
 		host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
 		break;
+	default:
+		printk(KERN_WARNING "nfsd: bad file type %o in nfsd_create\n",
+		       type);
+		host_err = -EINVAL;
 	}
 	if (host_err < 0)
 		goto out_nfserr;
-- 
cgit v1.2.3


From fa08139d5e02838ccabd9dcde22663d3b6780cad Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Thu, 21 Jul 2016 16:00:12 -0400
Subject: nfsd: drop unnecessary MAY_EXEC check from create

We need an fh_verify to make sure we at least have a dentry, but actual
permission checks happen later.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4proc.c | 7 +------
 fs/nfsd/vfs.c      | 6 +-----
 2 files changed, 2 insertions(+), 11 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 9d7e1edf0cca..1fb222752b2b 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -605,12 +605,7 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	fh_init(&resfh, NFS4_FHSIZE);
 
-	/*
-	 * We just check that parent is accessible here, nfsd_* do their
-	 * own access permission checks
-	 */
-	status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR,
-			   NFSD_MAY_EXEC);
+	status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, NFSD_MAY_NOP);
 	if (status)
 		return status;
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 1809624997f0..6666188c1138 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1236,11 +1236,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (isdotent(fname, flen))
 		return nfserr_exist;
 
-	/*
-	 * Even though it is a create, first let's see if we are even allowed
-	 * to peek inside the parent
-	 */
-	err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
+	err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_NOP);
 	if (err)
 		return err;
 
-- 
cgit v1.2.3


From 2b11885921a48767b6ace27c481beba3b42371ce Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 3 Aug 2016 22:05:00 +0300
Subject: nfsd: remove some dead code in nfsd_create_locked()

We changed this around in f135af1041f ('nfsd: reorganize nfsd_create')
so "dchild" can't be an error pointer any more.  Also, dchild can't be
NULL here (and dput would already handle this even if it was).

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/vfs.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'fs')

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 6666188c1138..ba944123167b 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1141,7 +1141,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		char *fname, int flen, struct iattr *iap,
 		int type, dev_t rdev, struct svc_fh *resfhp)
 {
-	struct dentry	*dentry, *dchild = NULL;
+	struct dentry	*dentry, *dchild;
 	struct inode	*dirp;
 	__be32		err;
 	__be32		err2;
@@ -1208,8 +1208,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (!err)
 		err = fh_update(resfhp);
 out:
-	if (dchild && !IS_ERR(dchild))
-		dput(dchild);
+	dput(dchild);
 	return err;
 
 out_nfserr:
-- 
cgit v1.2.3