From fe238e601d2519f259103ab65caea3b077ed7b39 Mon Sep 17 00:00:00 2001
From: Dave Wysochanski <dwysocha@redhat.com>
Date: Fri, 1 Apr 2016 13:45:09 -0400
Subject: NFS: Save struct inode * inside nfs_commit_info to clarify usage of
 i_lock

Commit ea2cf22 created nfs_commit_info and saved &inode->i_lock inside
this NFS specific structure.  This obscures the usage of i_lock.
Instead, save struct inode * so later it's clear the spinlock taken is
i_lock.

Should be no functional change.

Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/nfs_xdr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index d320906cf13e..cb9982d8f38f 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1431,7 +1431,7 @@ struct nfs_commit_completion_ops {
 };
 
 struct nfs_commit_info {
-	spinlock_t			*lock;	/* inode->i_lock */
+	struct inode 			*inode;	/* Needed for inode->i_lock */
 	struct nfs_mds_commit_info	*mds;
 	struct pnfs_ds_commit_info	*ds;
 	struct nfs_direct_req		*dreq;	/* O_DIRECT request */
-- 
cgit v1.2.3


From 3c6e0bc8a14cfc8e1d4ab87f46f77b070c815bf1 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@poochiereds.net>
Date: Thu, 21 Apr 2016 20:51:54 -0400
Subject: sunrpc: plumb gfp_t parm into crcreate operation

We need to be able to call the generic_cred creator from different
contexts. Add a gfp_t parm to the crcreate operation and to
rpcauth_lookup_credcache. For now, we just push the gfp_t parms up
one level to the *_lookup_cred functions.

Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/auth.h    | 4 ++--
 net/sunrpc/auth.c              | 4 ++--
 net/sunrpc/auth_generic.c      | 6 +++---
 net/sunrpc/auth_gss/auth_gss.c | 6 +++---
 net/sunrpc/auth_unix.c         | 6 +++---
 5 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 6a241a277249..3b616aa7e4d2 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -127,7 +127,7 @@ struct rpc_authops {
 	void			(*destroy)(struct rpc_auth *);
 
 	struct rpc_cred *	(*lookup_cred)(struct rpc_auth *, struct auth_cred *, int);
-	struct rpc_cred *	(*crcreate)(struct rpc_auth*, struct auth_cred *, int);
+	struct rpc_cred *	(*crcreate)(struct rpc_auth*, struct auth_cred *, int, gfp_t);
 	int			(*list_pseudoflavors)(rpc_authflavor_t *, int);
 	rpc_authflavor_t	(*info2flavor)(struct rpcsec_gss_info *);
 	int			(*flavor2info)(rpc_authflavor_t,
@@ -178,7 +178,7 @@ rpc_authflavor_t	rpcauth_get_pseudoflavor(rpc_authflavor_t,
 int			rpcauth_get_gssinfo(rpc_authflavor_t,
 				struct rpcsec_gss_info *);
 int			rpcauth_list_flavors(rpc_authflavor_t *, int);
-struct rpc_cred *	rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int);
+struct rpc_cred *	rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int, gfp_t);
 void			rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *);
 struct rpc_cred *	rpcauth_lookupcred(struct rpc_auth *, int);
 struct rpc_cred *	rpcauth_generic_bind_cred(struct rpc_task *, struct rpc_cred *, int);
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 02f53674dc39..e0bb30fd2ed3 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -543,7 +543,7 @@ rpcauth_cache_enforce_limit(void)
  */
 struct rpc_cred *
 rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
-		int flags)
+		int flags, gfp_t gfp)
 {
 	LIST_HEAD(free);
 	struct rpc_cred_cache *cache = auth->au_credcache;
@@ -580,7 +580,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
 	if (flags & RPCAUTH_LOOKUP_RCU)
 		return ERR_PTR(-ECHILD);
 
-	new = auth->au_ops->crcreate(auth, acred, flags);
+	new = auth->au_ops->crcreate(auth, acred, flags, gfp);
 	if (IS_ERR(new)) {
 		cred = new;
 		goto out;
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index 41248b1820c7..6ed3e3df43e9 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -77,15 +77,15 @@ static struct rpc_cred *generic_bind_cred(struct rpc_task *task,
 static struct rpc_cred *
 generic_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 {
-	return rpcauth_lookup_credcache(&generic_auth, acred, flags);
+	return rpcauth_lookup_credcache(&generic_auth, acred, flags, GFP_KERNEL);
 }
 
 static struct rpc_cred *
-generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
+generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t gfp)
 {
 	struct generic_cred *gcred;
 
-	gcred = kmalloc(sizeof(*gcred), GFP_KERNEL);
+	gcred = kmalloc(sizeof(*gcred), gfp);
 	if (gcred == NULL)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 15612ffa8d57..e64ae93d5b4f 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1299,11 +1299,11 @@ gss_destroy_cred(struct rpc_cred *cred)
 static struct rpc_cred *
 gss_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 {
-	return rpcauth_lookup_credcache(auth, acred, flags);
+	return rpcauth_lookup_credcache(auth, acred, flags, GFP_NOFS);
 }
 
 static struct rpc_cred *
-gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
+gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t gfp)
 {
 	struct gss_auth *gss_auth = container_of(auth, struct gss_auth, rpc_auth);
 	struct gss_cred	*cred = NULL;
@@ -1313,7 +1313,7 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 		__func__, from_kuid(&init_user_ns, acred->uid),
 		auth->au_flavor);
 
-	if (!(cred = kzalloc(sizeof(*cred), GFP_NOFS)))
+	if (!(cred = kzalloc(sizeof(*cred), gfp)))
 		goto out_err;
 
 	rpcauth_init_cred(&cred->gc_base, acred, auth, &gss_credops);
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index 0d3dd364c22f..9f65452b7cbc 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -52,11 +52,11 @@ unx_destroy(struct rpc_auth *auth)
 static struct rpc_cred *
 unx_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 {
-	return rpcauth_lookup_credcache(auth, acred, flags);
+	return rpcauth_lookup_credcache(auth, acred, flags, GFP_NOFS);
 }
 
 static struct rpc_cred *
-unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
+unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t gfp)
 {
 	struct unx_cred	*cred;
 	unsigned int groups = 0;
@@ -66,7 +66,7 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 			from_kuid(&init_user_ns, acred->uid),
 			from_kgid(&init_user_ns, acred->gid));
 
-	if (!(cred = kmalloc(sizeof(*cred), GFP_NOFS)))
+	if (!(cred = kmalloc(sizeof(*cred), gfp)))
 		return ERR_PTR(-ENOMEM);
 
 	rpcauth_init_cred(&cred->uc_base, acred, auth, &unix_credops);
-- 
cgit v1.2.3


From c065d229e308ede426a3608cf480c61983b36fb8 Mon Sep 17 00:00:00 2001
From: Weston Andros Adamson <dros@primarydata.com>
Date: Thu, 21 Apr 2016 20:51:55 -0400
Subject: sunrpc: add rpc_lookup_generic_cred

Add function rpc_lookup_generic_cred, which allows lookups of a generic
credential that's not current_cred().

[jlayton: add gfp_t parm]

Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/auth.h | 1 +
 net/sunrpc/auth_generic.c   | 7 +++++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 3b616aa7e4d2..16bd8f8fef8c 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -167,6 +167,7 @@ void 			rpc_destroy_authunix(void);
 
 struct rpc_cred *	rpc_lookup_cred(void);
 struct rpc_cred *	rpc_lookup_cred_nonblock(void);
+struct rpc_cred *	rpc_lookup_generic_cred(struct auth_cred *, int, gfp_t);
 struct rpc_cred *	rpc_lookup_machine_cred(const char *service_name);
 int			rpcauth_register(const struct rpc_authops *);
 int			rpcauth_unregister(const struct rpc_authops *);
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index 6ed3e3df43e9..54dd3fdead54 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -38,6 +38,13 @@ struct rpc_cred *rpc_lookup_cred(void)
 }
 EXPORT_SYMBOL_GPL(rpc_lookup_cred);
 
+struct rpc_cred *
+rpc_lookup_generic_cred(struct auth_cred *acred, int flags, gfp_t gfp)
+{
+	return rpcauth_lookup_credcache(&generic_auth, acred, flags, gfp);
+}
+EXPORT_SYMBOL_GPL(rpc_lookup_generic_cred);
+
 struct rpc_cred *rpc_lookup_cred_nonblock(void)
 {
 	return rpcauth_lookupcred(&generic_auth, RPCAUTH_LOOKUP_RCU);
-- 
cgit v1.2.3


From 62dbef2ae41393eba2f6853ca174130f2d09c7d3 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@poochiereds.net>
Date: Thu, 21 Apr 2016 20:51:56 -0400
Subject: sunrpc: add a get_rpccred_rcu inline

Sometimes we might have a RCU managed credential pointer and don't want
to use locking to handle it. Add a function that will take a reference
to the cred iff the refcount is not already zero. Callers can dereference
the pointer under the rcu_read_lock and use that function to take a
reference only if the cred is not on its way to destruction.

Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/auth.h | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 16bd8f8fef8c..6f36b2bf3e05 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -206,5 +206,23 @@ struct rpc_cred *	get_rpccred(struct rpc_cred *cred)
 	return cred;
 }
 
+/**
+ * get_rpccred_rcu - get a reference to a cred using rcu-protected pointer
+ * @cred: cred of which to take a reference
+ *
+ * In some cases, we may have a pointer to a credential to which we
+ * want to take a reference, but don't already have one. Because these
+ * objects are freed using RCU, we can access the cr_count while its
+ * on its way to destruction and only take a reference if it's not already
+ * zero.
+ */
+static inline struct rpc_cred *
+get_rpccred_rcu(struct rpc_cred *cred)
+{
+	if (atomic_inc_not_zero(&cred->cr_count))
+		return cred;
+	return NULL;
+}
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_AUTH_H */
-- 
cgit v1.2.3


From 2e72448b07dc3ff1b7593e9bfff91db182262857 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@netapp.com>
Date: Tue, 21 May 2013 16:53:03 -0400
Subject: NFS: Add COPY nfs operation

This adds the copy_range file_ops function pointer used by the
sys_copy_range() function call.  This patch only implements sync copies,
so if an async copy happens we decode the stateid and ignore it.

Signed-off-by: Anna Schumaker <bjschuma@netapp.com>
---
 fs/nfs/nfs42.h            |   1 +
 fs/nfs/nfs42proc.c        | 105 +++++++++++++++++++++++++++++++++
 fs/nfs/nfs42xdr.c         | 146 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4file.c         |  23 ++++++++
 fs/nfs/nfs4proc.c         |   1 +
 fs/nfs/nfs4xdr.c          |   1 +
 include/linux/nfs4.h      |   1 +
 include/linux/nfs_fs_sb.h |   1 +
 include/linux/nfs_xdr.h   |  26 +++++++++
 9 files changed, 305 insertions(+)

(limited to 'include')

diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index b587ccd31083..b6cd15314bab 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -13,6 +13,7 @@
 
 /* nfs4.2proc.c */
 int nfs42_proc_allocate(struct file *, loff_t, loff_t);
+ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t);
 int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
 loff_t nfs42_proc_llseek(struct file *, loff_t, int);
 int nfs42_proc_layoutstats_generic(struct nfs_server *,
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index dff83460e5a6..579ee20e4120 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -126,6 +126,111 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	return err;
 }
 
+static ssize_t _nfs42_proc_copy(struct file *src, loff_t pos_src,
+				struct nfs_lock_context *src_lock,
+				struct file *dst, loff_t pos_dst,
+				struct nfs_lock_context *dst_lock,
+				size_t count)
+{
+	struct nfs42_copy_args args = {
+		.src_fh		= NFS_FH(file_inode(src)),
+		.src_pos	= pos_src,
+		.dst_fh		= NFS_FH(file_inode(dst)),
+		.dst_pos	= pos_dst,
+		.count		= count,
+	};
+	struct nfs42_copy_res res;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	struct inode *dst_inode = file_inode(dst);
+	struct nfs_server *server = NFS_SERVER(dst_inode);
+	int status;
+
+	status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context,
+				     src_lock, FMODE_READ);
+	if (status)
+		return status;
+
+	status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
+				     dst_lock, FMODE_WRITE);
+	if (status)
+		return status;
+
+	status = nfs4_call_sync(server->client, server, &msg,
+				&args.seq_args, &res.seq_res, 0);
+	if (status == -ENOTSUPP)
+		server->caps &= ~NFS_CAP_COPY;
+	if (status)
+		return status;
+
+	if (res.write_res.verifier.committed != NFS_FILE_SYNC) {
+		status = nfs_commit_file(dst, &res.write_res.verifier.verifier);
+		if (status)
+			return status;
+	}
+
+	truncate_pagecache_range(dst_inode, pos_dst,
+				 pos_dst + res.write_res.count);
+
+	return res.write_res.count;
+}
+
+ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
+			struct file *dst, loff_t pos_dst,
+			size_t count)
+{
+	struct nfs_server *server = NFS_SERVER(file_inode(dst));
+	struct nfs_lock_context *src_lock;
+	struct nfs_lock_context *dst_lock;
+	struct nfs4_exception src_exception = { };
+	struct nfs4_exception dst_exception = { };
+	ssize_t err, err2;
+
+	if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY))
+		return -EOPNOTSUPP;
+
+	src_lock = nfs_get_lock_context(nfs_file_open_context(src));
+	if (IS_ERR(src_lock))
+		return PTR_ERR(src_lock);
+
+	src_exception.inode = file_inode(src);
+	src_exception.state = src_lock->open_context->state;
+
+	dst_lock = nfs_get_lock_context(nfs_file_open_context(dst));
+	if (IS_ERR(dst_lock)) {
+		err = PTR_ERR(dst_lock);
+		goto out_put_src_lock;
+	}
+
+	dst_exception.inode = file_inode(dst);
+	dst_exception.state = dst_lock->open_context->state;
+
+	do {
+		mutex_lock(&file_inode(dst)->i_mutex);
+		err = _nfs42_proc_copy(src, pos_src, src_lock,
+				       dst, pos_dst, dst_lock, count);
+		mutex_unlock(&file_inode(dst)->i_mutex);
+
+		if (err == -ENOTSUPP) {
+			err = -EOPNOTSUPP;
+			break;
+		}
+
+		err2 = nfs4_handle_exception(server, err, &src_exception);
+		err  = nfs4_handle_exception(server, err, &dst_exception);
+		if (!err)
+			err = err2;
+	} while (src_exception.retry || dst_exception.retry);
+
+	nfs_put_lock_context(dst_lock);
+out_put_src_lock:
+	nfs_put_lock_context(src_lock);
+	return err;
+}
+
 static loff_t _nfs42_proc_llseek(struct file *filep,
 		struct nfs_lock_context *lock, loff_t offset, int whence)
 {
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 0ca482a51e53..6dc6f2aea0d6 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -9,9 +9,22 @@
 #define encode_fallocate_maxsz		(encode_stateid_maxsz + \
 					 2 /* offset */ + \
 					 2 /* length */)
+#define NFS42_WRITE_RES_SIZE		(1 /* wr_callback_id size */ +\
+					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+					 2 /* wr_count */ + \
+					 1 /* wr_committed */ + \
+					 XDR_QUADLEN(NFS4_VERIFIER_SIZE))
 #define encode_allocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_allocate_maxsz		(op_decode_hdr_maxsz)
+#define encode_copy_maxsz		(op_encode_hdr_maxsz +          \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+					 2 + 2 + 2 + 1 + 1 + 1)
+#define decode_copy_maxsz		(op_decode_hdr_maxsz + \
+					 NFS42_WRITE_RES_SIZE + \
+					 1 /* cr_consecutive */ + \
+					 1 /* cr_synchronous */)
 #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
@@ -49,6 +62,16 @@
 					 decode_putfh_maxsz + \
 					 decode_allocate_maxsz + \
 					 decode_getattr_maxsz)
+#define NFS4_enc_copy_sz		(compound_encode_hdr_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_savefh_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_copy_maxsz)
+#define NFS4_dec_copy_sz		(compound_decode_hdr_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_savefh_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_copy_maxsz)
 #define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
 					 encode_deallocate_maxsz + \
@@ -102,6 +125,23 @@ static void encode_allocate(struct xdr_stream *xdr,
 	encode_fallocate(xdr, args);
 }
 
+static void encode_copy(struct xdr_stream *xdr,
+			struct nfs42_copy_args *args,
+			struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_COPY, decode_copy_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->src_stateid);
+	encode_nfs4_stateid(xdr, &args->dst_stateid);
+
+	encode_uint64(xdr, args->src_pos);
+	encode_uint64(xdr, args->dst_pos);
+	encode_uint64(xdr, args->count);
+
+	encode_uint32(xdr, 1); /* consecutive = true */
+	encode_uint32(xdr, 1); /* synchronous = true */
+	encode_uint32(xdr, 0); /* src server list */
+}
+
 static void encode_deallocate(struct xdr_stream *xdr,
 			      struct nfs42_falloc_args *args,
 			      struct compound_hdr *hdr)
@@ -181,6 +221,26 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode COPY request
+ */
+static void nfs4_xdr_enc_copy(struct rpc_rqst *req,
+			      struct xdr_stream *xdr,
+			      struct nfs42_copy_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->src_fh, &hdr);
+	encode_savefh(xdr, &hdr);
+	encode_putfh(xdr, args->dst_fh, &hdr);
+	encode_copy(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode DEALLOCATE request
  */
@@ -266,6 +326,62 @@ static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
 	return decode_op_hdr(xdr, OP_ALLOCATE);
 }
 
+static int decode_write_response(struct xdr_stream *xdr,
+				 struct nfs42_write_res *res)
+{
+	__be32 *p;
+	int stateids;
+
+	p = xdr_inline_decode(xdr, 4 + 8 + 4);
+	if (unlikely(!p))
+		goto out_overflow;
+
+	stateids = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &res->count);
+	res->verifier.committed = be32_to_cpup(p);
+	return decode_verifier(xdr, &res->verifier.verifier);
+
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
+static int decode_copy_requirements(struct xdr_stream *xdr,
+				    struct nfs42_copy_res *res) {
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 4 + 4);
+	if (unlikely(!p))
+		goto out_overflow;
+
+	res->consecutive = be32_to_cpup(p++);
+	res->synchronous = be32_to_cpup(p++);
+	return 0;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
+static int decode_copy(struct xdr_stream *xdr, struct nfs42_copy_res *res)
+{
+	int status;
+
+	status = decode_op_hdr(xdr, OP_COPY);
+	if (status == NFS4ERR_OFFLOAD_NO_REQS) {
+		status = decode_copy_requirements(xdr, res);
+		if (status)
+			return status;
+		return NFS4ERR_OFFLOAD_NO_REQS;
+	} else if (status)
+		return status;
+
+	status = decode_write_response(xdr, &res->write_res);
+	if (status)
+		return status;
+
+	return decode_copy_requirements(xdr, res);
+}
+
 static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
 {
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
@@ -330,6 +446,36 @@ out:
 	return status;
 }
 
+/*
+ * Decode COPY response
+ */
+static int nfs4_xdr_dec_copy(struct rpc_rqst *rqstp,
+			     struct xdr_stream *xdr,
+			     struct nfs42_copy_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_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_savefh(xdr);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_copy(xdr, res);
+out:
+	return status;
+}
+
 /*
  * Decode DEALLOCATE request
  */
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index d0390516467c..014b0e41ace5 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -129,6 +129,28 @@ nfs4_file_flush(struct file *file, fl_owner_t id)
 }
 
 #ifdef CONFIG_NFS_V4_2
+static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
+				    struct file *file_out, loff_t pos_out,
+				    size_t count, unsigned int flags)
+{
+	struct inode *in_inode = file_inode(file_in);
+	struct inode *out_inode = file_inode(file_out);
+	int ret;
+
+	if (in_inode == out_inode)
+		return -EINVAL;
+
+	/* flush any pending writes */
+	ret = nfs_sync_inode(in_inode);
+	if (ret)
+		return ret;
+	ret = nfs_sync_inode(out_inode);
+	if (ret)
+		return ret;
+
+	return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+}
+
 static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
 {
 	loff_t ret;
@@ -243,6 +265,7 @@ const struct file_operations nfs4_file_operations = {
 	.check_flags	= nfs_check_flags,
 	.setlease	= simple_nosetlease,
 #ifdef CONFIG_NFS_V4_2
+	.copy_file_range = nfs4_copy_file_range,
 	.llseek		= nfs4_file_llseek,
 	.fallocate	= nfs42_fallocate,
 	.clone_file_range = nfs42_clone_file_range,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index bc2676c95e1b..4e83385ea6a9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -8797,6 +8797,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1
 		| NFS_CAP_ALLOCATE
+		| NFS_CAP_COPY
 		| NFS_CAP_DEALLOCATE
 		| NFS_CAP_SEEK
 		| NFS_CAP_LAYOUTSTATS
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 88474a4fc669..d1c96fc62c51 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7515,6 +7515,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(DEALLOCATE,	enc_deallocate,		dec_deallocate),
 	PROC(LAYOUTSTATS,	enc_layoutstats,	dec_layoutstats),
 	PROC(CLONE,		enc_clone,		dec_clone),
+	PROC(COPY,		enc_copy,		dec_copy),
 #endif /* CONFIG_NFS_V4_2 */
 };
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 011433478a14..722509482e1a 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -504,6 +504,7 @@ enum {
 	NFSPROC4_CLNT_DEALLOCATE,
 	NFSPROC4_CLNT_LAYOUTSTATS,
 	NFSPROC4_CLNT_CLONE,
+	NFSPROC4_CLNT_COPY,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 7fcc13c8cf1f..14a762d2734d 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -246,5 +246,6 @@ struct nfs_server {
 #define NFS_CAP_DEALLOCATE	(1U << 21)
 #define NFS_CAP_LAYOUTSTATS	(1U << 22)
 #define NFS_CAP_CLONE		(1U << 23)
+#define NFS_CAP_COPY		(1U << 24)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index cb9982d8f38f..e70ed54dad94 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1343,6 +1343,32 @@ struct nfs42_falloc_res {
 	const struct nfs_server		*falloc_server;
 };
 
+struct nfs42_copy_args {
+	struct nfs4_sequence_args	seq_args;
+
+	struct nfs_fh			*src_fh;
+	nfs4_stateid			src_stateid;
+	u64				src_pos;
+
+	struct nfs_fh			*dst_fh;
+	nfs4_stateid			dst_stateid;
+	u64				dst_pos;
+
+	u64				count;
+};
+
+struct nfs42_write_res {
+	u64			count;
+	struct nfs_writeverf	verifier;
+};
+
+struct nfs42_copy_res {
+	struct nfs4_sequence_res	seq_res;
+	struct nfs42_write_res		write_res;
+	bool				consecutive;
+	bool				synchronous;
+};
+
 struct nfs42_seek_args {
 	struct nfs4_sequence_args	seq_args;
 
-- 
cgit v1.2.3


From 4b9c7f9db9a003f5c342184dc4401c1b7f2efb39 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 2 May 2016 14:40:31 -0400
Subject: sunrpc: Update RPCBIND_MAXNETIDLEN

Commit 176e21ee2ec8 ("SUNRPC: Support for RPC over AF_LOCAL
transports") added a 5-character netid, but did not bump
RPCBIND_MAXNETIDLEN from 4 to 5.

Fixes: 176e21ee2ec8 ("SUNRPC: Support for RPC over AF_LOCAL ...")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/msg_prot.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index 807371357160..59cbf16eaeb5 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -158,9 +158,9 @@ typedef __be32	rpc_fraghdr;
 
 /*
  * Note that RFC 1833 does not put any size restrictions on the
- * netid string, but all currently defined netid's fit in 4 bytes.
+ * netid string, but all currently defined netid's fit in 5 bytes.
  */
-#define RPCBIND_MAXNETIDLEN	(4u)
+#define RPCBIND_MAXNETIDLEN	(5u)
 
 /*
  * Universal addresses are introduced in RFC 1833 and further spelled
-- 
cgit v1.2.3


From 6b26cc8c8ead3636a18bfd9489984983f4ddd6f4 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 2 May 2016 14:40:40 -0400
Subject: sunrpc: Advertise maximum backchannel payload size

RPC-over-RDMA transports have a limit on how large a backward
direction (backchannel) RPC message can be. Ensure that the NFSv4.x
CREATE_SESSION operation advertises this limit to servers.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c                 | 10 ++++++----
 include/linux/sunrpc/clnt.h       |  1 +
 include/linux/sunrpc/xprt.h       |  1 +
 net/sunrpc/clnt.c                 | 17 +++++++++++++++++
 net/sunrpc/xprtrdma/backchannel.c | 16 ++++++++++++++++
 net/sunrpc/xprtrdma/transport.c   |  1 +
 net/sunrpc/xprtrdma/xprt_rdma.h   |  1 +
 net/sunrpc/xprtsock.c             |  6 ++++++
 8 files changed, 49 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 9795725d708c..196e41e12621 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7371,9 +7371,11 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
  * always set csa_cachethis to FALSE because the current implementation
  * of the back channel DRC only supports caching the CB_SEQUENCE operation.
  */
-static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
+static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args,
+				    struct rpc_clnt *clnt)
 {
 	unsigned int max_rqst_sz, max_resp_sz;
+	unsigned int max_bc_payload = rpc_max_bc_payload(clnt);
 
 	max_rqst_sz = NFS_MAX_FILE_IO_SIZE + nfs41_maxwrite_overhead;
 	max_resp_sz = NFS_MAX_FILE_IO_SIZE + nfs41_maxread_overhead;
@@ -7391,8 +7393,8 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
 		args->fc_attrs.max_ops, args->fc_attrs.max_reqs);
 
 	/* Back channel attributes */
-	args->bc_attrs.max_rqst_sz = PAGE_SIZE;
-	args->bc_attrs.max_resp_sz = PAGE_SIZE;
+	args->bc_attrs.max_rqst_sz = max_bc_payload;
+	args->bc_attrs.max_resp_sz = max_bc_payload;
 	args->bc_attrs.max_resp_sz_cached = 0;
 	args->bc_attrs.max_ops = NFS4_MAX_BACK_CHANNEL_OPS;
 	args->bc_attrs.max_reqs = NFS41_BC_MAX_CALLBACKS;
@@ -7496,7 +7498,7 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
 	};
 	int status;
 
-	nfs4_init_channel_attrs(&args);
+	nfs4_init_channel_attrs(&args, clp->cl_rpcclient);
 	args.flags = (SESSION4_PERSIST | SESSION4_BACK_CHAN);
 
 	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 9a7ddbaf116e..19c659d1c0f8 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -176,6 +176,7 @@ void		rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int);
 int		rpc_protocol(struct rpc_clnt *);
 struct net *	rpc_net_ns(struct rpc_clnt *);
 size_t		rpc_max_payload(struct rpc_clnt *);
+size_t		rpc_max_bc_payload(struct rpc_clnt *);
 unsigned long	rpc_get_timeout(struct rpc_clnt *clnt);
 void		rpc_force_rebind(struct rpc_clnt *);
 size_t		rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t);
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index fb0d212e0d3a..5aa3834619a8 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -142,6 +142,7 @@ struct rpc_xprt_ops {
 	int		(*bc_setup)(struct rpc_xprt *xprt,
 				    unsigned int min_reqs);
 	int		(*bc_up)(struct svc_serv *serv, struct net *net);
+	size_t		(*bc_maxpayload)(struct rpc_xprt *xprt);
 	void		(*bc_free_rqst)(struct rpc_rqst *rqst);
 	void		(*bc_destroy)(struct rpc_xprt *xprt,
 				      unsigned int max_reqs);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 7e0c9bf22df8..06b4df9faaa1 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1413,6 +1413,23 @@ size_t rpc_max_payload(struct rpc_clnt *clnt)
 }
 EXPORT_SYMBOL_GPL(rpc_max_payload);
 
+/**
+ * rpc_max_bc_payload - Get maximum backchannel payload size, in bytes
+ * @clnt: RPC client to query
+ */
+size_t rpc_max_bc_payload(struct rpc_clnt *clnt)
+{
+	struct rpc_xprt *xprt;
+	size_t ret;
+
+	rcu_read_lock();
+	xprt = rcu_dereference(clnt->cl_xprt);
+	ret = xprt->ops->bc_maxpayload(xprt);
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rpc_max_bc_payload);
+
 /**
  * rpc_get_timeout - Get timeout for transport in units of HZ
  * @clnt: RPC client to query
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index 2dcd7640eeb5..87762d976b63 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -191,6 +191,22 @@ int xprt_rdma_bc_up(struct svc_serv *serv, struct net *net)
 	return 0;
 }
 
+/**
+ * xprt_rdma_bc_maxpayload - Return maximum backchannel message size
+ * @xprt: transport
+ *
+ * Returns maximum size, in bytes, of a backchannel message
+ */
+size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *xprt)
+{
+	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data;
+	size_t maxmsg;
+
+	maxmsg = min_t(unsigned int, cdata->inline_rsize, cdata->inline_wsize);
+	return maxmsg - RPCRDMA_HDRLEN_MIN;
+}
+
 /**
  * rpcrdma_bc_marshal_reply - Send backwards direction reply
  * @rqst: buffer containing RPC reply data
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index b1b009f10ea3..9954342924df 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -707,6 +707,7 @@ static struct rpc_xprt_ops xprt_rdma_procs = {
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 	.bc_setup		= xprt_rdma_bc_setup,
 	.bc_up			= xprt_rdma_bc_up,
+	.bc_maxpayload		= xprt_rdma_bc_maxpayload,
 	.bc_free_rqst		= xprt_rdma_bc_free_rqst,
 	.bc_destroy		= xprt_rdma_bc_destroy,
 #endif
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 2ebc743cb96f..7723e5faff4d 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -534,6 +534,7 @@ void xprt_rdma_cleanup(void);
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 int xprt_rdma_bc_setup(struct rpc_xprt *, unsigned int);
 int xprt_rdma_bc_up(struct svc_serv *, struct net *);
+size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *);
 int rpcrdma_bc_post_recv(struct rpcrdma_xprt *, unsigned int);
 void rpcrdma_bc_receive_call(struct rpcrdma_xprt *, struct rpcrdma_rep *);
 int rpcrdma_bc_marshal_reply(struct rpc_rqst *);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 65e759569e48..f1faf6b9aaff 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1365,6 +1365,11 @@ static int xs_tcp_bc_up(struct svc_serv *serv, struct net *net)
 		return ret;
 	return 0;
 }
+
+static size_t xs_tcp_bc_maxpayload(struct rpc_xprt *xprt)
+{
+	return PAGE_SIZE;
+}
 #else
 static inline int _xs_tcp_read_data(struct rpc_xprt *xprt,
 					struct xdr_skb_reader *desc)
@@ -2660,6 +2665,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 	.bc_setup		= xprt_setup_bc,
 	.bc_up			= xs_tcp_bc_up,
+	.bc_maxpayload		= xs_tcp_bc_maxpayload,
 	.bc_free_rqst		= xprt_free_bc_rqst,
 	.bc_destroy		= xprt_destroy_bc,
 #endif
-- 
cgit v1.2.3


From 29c554227aeec48cde5c22f911e51763f096e125 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 2 May 2016 14:40:48 -0400
Subject: xprtrdma: Bound the inline threshold values

Currently the sysctls that allow setting the inline threshold allow
any value to be set.

Small values only make the transport run slower. The default 1KB
setting is as low as is reasonable. And the logic that decides how
to divide a Send buffer between RPC-over-RDMA header and RPC message
assumes (but does not check) that the lower bound is not crazy (say,
57 bytes).

Send and receive buffers share a page with some control information.
Values larger than about 3KB can't be supported, currently.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xprtrdma.h | 4 +++-
 net/sunrpc/xprtrdma/transport.c | 6 ++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h
index 767190b01363..39267dc3486a 100644
--- a/include/linux/sunrpc/xprtrdma.h
+++ b/include/linux/sunrpc/xprtrdma.h
@@ -52,7 +52,9 @@
 #define RPCRDMA_DEF_SLOT_TABLE	(128U)
 #define RPCRDMA_MAX_SLOT_TABLE	(256U)
 
-#define RPCRDMA_DEF_INLINE  (1024)	/* default inline max */
+#define RPCRDMA_MIN_INLINE  (1024)	/* min inline thresh */
+#define RPCRDMA_DEF_INLINE  (1024)	/* default inline thresh */
+#define RPCRDMA_MAX_INLINE  (3068)	/* max inline thresh */
 
 /* Memory registration strategies, by number.
  * This is part of a kernel / user space API. Do not remove. */
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 9954342924df..16595ff91994 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -73,6 +73,8 @@ static unsigned int xprt_rdma_memreg_strategy = RPCRDMA_FRMR;
 
 static unsigned int min_slot_table_size = RPCRDMA_MIN_SLOT_TABLE;
 static unsigned int max_slot_table_size = RPCRDMA_MAX_SLOT_TABLE;
+static unsigned int min_inline_size = RPCRDMA_MIN_INLINE;
+static unsigned int max_inline_size = RPCRDMA_MAX_INLINE;
 static unsigned int zero;
 static unsigned int max_padding = PAGE_SIZE;
 static unsigned int min_memreg = RPCRDMA_BOUNCEBUFFERS;
@@ -96,6 +98,8 @@ static struct ctl_table xr_tunables_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
+		.extra1		= &min_inline_size,
+		.extra2		= &max_inline_size,
 	},
 	{
 		.procname	= "rdma_max_inline_write",
@@ -103,6 +107,8 @@ static struct ctl_table xr_tunables_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
+		.extra1		= &min_inline_size,
+		.extra2		= &max_inline_size,
 	},
 	{
 		.procname	= "rdma_inline_write_padding",
-- 
cgit v1.2.3


From 9a8f6b5ea275ff01fc8ef3b8630a3d4ed6b0a362 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Mon, 16 May 2016 17:42:42 -0400
Subject: SUNRPC: Ensure get_rpccred() and put_rpccred() can take NULL
 arguments

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/auth.h | 3 ++-
 net/sunrpc/auth.c           | 5 +++--
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 6f36b2bf3e05..899791573a40 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -202,7 +202,8 @@ char *			rpcauth_stringify_acceptor(struct rpc_cred *);
 static inline
 struct rpc_cred *	get_rpccred(struct rpc_cred *cred)
 {
-	atomic_inc(&cred->cr_count);
+	if (cred != NULL)
+		atomic_inc(&cred->cr_count);
 	return cred;
 }
 
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index e0bb30fd2ed3..040ff627c18a 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -703,8 +703,7 @@ rpcauth_bindcred(struct rpc_task *task, struct rpc_cred *cred, int flags)
 		new = rpcauth_bind_new_cred(task, lookupflags);
 	if (IS_ERR(new))
 		return PTR_ERR(new);
-	if (req->rq_cred != NULL)
-		put_rpccred(req->rq_cred);
+	put_rpccred(req->rq_cred);
 	req->rq_cred = new;
 	return 0;
 }
@@ -712,6 +711,8 @@ rpcauth_bindcred(struct rpc_task *task, struct rpc_cred *cred, int flags)
 void
 put_rpccred(struct rpc_cred *cred)
 {
+	if (cred == NULL)
+		return;
 	/* Fast path for unhashed credentials */
 	if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) == 0) {
 		if (atomic_dec_and_test(&cred->cr_count))
-- 
cgit v1.2.3


From 93b717fd81bf6b9a73c3702e9b079b4de8148b34 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Mon, 16 May 2016 17:42:43 -0400
Subject: NFSv4: Label stateids with the type

In order to more easily distinguish what kind of stateid we are dealing
with, introduce a type that can be used to label the stateid structure.

The label will be useful both for debugging, but also when dealing with
operations like SETATTR, READ and WRITE that can take several different
types of stateid as arguments.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/callback_xdr.c                     | 17 ++++++++++---
 fs/nfs/flexfilelayout/flexfilelayout.c    |  7 +++---
 fs/nfs/flexfilelayout/flexfilelayoutdev.c |  3 ++-
 fs/nfs/nfs4_fs.h                          |  7 ++++--
 fs/nfs/nfs4proc.c                         |  3 +++
 fs/nfs/nfs4state.c                        |  5 +++-
 fs/nfs/nfs4xdr.c                          | 42 ++++++++++++++++++++++++-------
 include/linux/nfs4.h                      | 25 ++++++++++++++----
 8 files changed, 85 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 976c90608e56..d81f96aacd51 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -146,10 +146,16 @@ static __be32 decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
 	p = read_buf(xdr, NFS4_STATEID_SIZE);
 	if (unlikely(p == NULL))
 		return htonl(NFS4ERR_RESOURCE);
-	memcpy(stateid, p, NFS4_STATEID_SIZE);
+	memcpy(stateid->data, p, NFS4_STATEID_SIZE);
 	return 0;
 }
 
+static __be32 decode_delegation_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+	stateid->type = NFS4_DELEGATION_STATEID_TYPE;
+	return decode_stateid(xdr, stateid);
+}
+
 static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound_hdr_arg *hdr)
 {
 	__be32 *p;
@@ -211,7 +217,7 @@ static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	__be32 *p;
 	__be32 status;
 
-	status = decode_stateid(xdr, &args->stateid);
+	status = decode_delegation_stateid(xdr, &args->stateid);
 	if (unlikely(status != 0))
 		goto out;
 	p = read_buf(xdr, 4);
@@ -227,6 +233,11 @@ out:
 }
 
 #if defined(CONFIG_NFS_V4_1)
+static __be32 decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+	stateid->type = NFS4_LAYOUT_STATEID_TYPE;
+	return decode_stateid(xdr, stateid);
+}
 
 static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp,
 				       struct xdr_stream *xdr,
@@ -263,7 +274,7 @@ static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp,
 		}
 		p = xdr_decode_hyper(p, &args->cbl_range.offset);
 		p = xdr_decode_hyper(p, &args->cbl_range.length);
-		status = decode_stateid(xdr, &args->cbl_stateid);
+		status = decode_layout_stateid(xdr, &args->cbl_stateid);
 		if (unlikely(status != 0))
 			goto out;
 	} else if (args->cbl_recall_type == RETURN_FSID) {
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 60d690dbc947..53b6391e0eba 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -55,14 +55,15 @@ ff_layout_free_layout_hdr(struct pnfs_layout_hdr *lo)
 	kfree(FF_LAYOUT_FROM_HDR(lo));
 }
 
-static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+static int decode_pnfs_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
 {
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, NFS4_STATEID_SIZE);
 	if (unlikely(p == NULL))
 		return -ENOBUFS;
-	memcpy(stateid, p, NFS4_STATEID_SIZE);
+	stateid->type = NFS4_PNFS_DS_STATEID_TYPE;
+	memcpy(stateid->data, p, NFS4_STATEID_SIZE);
 	dprintk("%s: stateid id= [%x%x%x%x]\n", __func__,
 		p[0], p[1], p[2], p[3]);
 	return 0;
@@ -465,7 +466,7 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
 		fls->mirror_array[i]->efficiency = be32_to_cpup(p);
 
 		/* stateid */
-		rc = decode_stateid(&stream, &fls->mirror_array[i]->stateid);
+		rc = decode_pnfs_stateid(&stream, &fls->mirror_array[i]->stateid);
 		if (rc)
 			goto out_err_free;
 
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 56296f3df19c..eeef89359ad2 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -228,7 +228,8 @@ ff_ds_error_match(const struct nfs4_ff_layout_ds_err *e1,
 		return e1->opnum < e2->opnum ? -1 : 1;
 	if (e1->status != e2->status)
 		return e1->status < e2->status ? -1 : 1;
-	ret = memcmp(&e1->stateid, &e2->stateid, sizeof(e1->stateid));
+	ret = memcmp(e1->stateid.data, e2->stateid.data,
+			sizeof(e1->stateid.data));
 	if (ret != 0)
 		return ret;
 	ret = memcmp(&e1->deviceid, &e2->deviceid, sizeof(e1->deviceid));
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 4afdee420d25..b5d9f345c9f2 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -496,12 +496,15 @@ extern struct svc_version nfs4_callback_version4;
 
 static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src)
 {
-	memcpy(dst, src, sizeof(*dst));
+	memcpy(dst->data, src->data, sizeof(dst->data));
+	dst->type = src->type;
 }
 
 static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_stateid *src)
 {
-	return memcmp(dst, src, sizeof(*dst)) == 0;
+	if (dst->type != src->type)
+		return false;
+	return memcmp(dst->data, src->data, sizeof(dst->data)) == 0;
 }
 
 static inline bool nfs4_stateid_match_other(const nfs4_stateid *dst, const nfs4_stateid *src)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 196e41e12621..2516467ff17f 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -8675,6 +8675,9 @@ nfs41_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
 static bool nfs41_match_stateid(const nfs4_stateid *s1,
 		const nfs4_stateid *s2)
 {
+	if (s1->type != s2->type)
+		return false;
+
 	if (memcmp(s1->other, s2->other, sizeof(s1->other)) != 0)
 		return false;
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index d854693a15b0..d630f9cca0f1 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -65,7 +65,10 @@
 
 #define OPENOWNER_POOL_SIZE	8
 
-const nfs4_stateid zero_stateid;
+const nfs4_stateid zero_stateid = {
+	.data = { 0 },
+	.type = NFS4_SPECIAL_STATEID_TYPE,
+};
 static DEFINE_MUTEX(nfs_clid_init_mutex);
 
 int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index d1c96fc62c51..661e753fe1c9 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -4270,6 +4270,24 @@ static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
 	return decode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE);
 }
 
+static int decode_open_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+	stateid->type = NFS4_OPEN_STATEID_TYPE;
+	return decode_stateid(xdr, stateid);
+}
+
+static int decode_lock_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+	stateid->type = NFS4_LOCK_STATEID_TYPE;
+	return decode_stateid(xdr, stateid);
+}
+
+static int decode_delegation_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+	stateid->type = NFS4_DELEGATION_STATEID_TYPE;
+	return decode_stateid(xdr, stateid);
+}
+
 static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
 {
 	int status;
@@ -4278,7 +4296,7 @@ static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
 	if (status != -EIO)
 		nfs_increment_open_seqid(status, res->seqid);
 	if (!status)
-		status = decode_stateid(xdr, &res->stateid);
+		status = decode_open_stateid(xdr, &res->stateid);
 	return status;
 }
 
@@ -4937,7 +4955,7 @@ static int decode_lock(struct xdr_stream *xdr, struct nfs_lock_res *res)
 	if (status == -EIO)
 		goto out;
 	if (status == 0) {
-		status = decode_stateid(xdr, &res->stateid);
+		status = decode_lock_stateid(xdr, &res->stateid);
 		if (unlikely(status))
 			goto out;
 	} else if (status == -NFS4ERR_DENIED)
@@ -4966,7 +4984,7 @@ static int decode_locku(struct xdr_stream *xdr, struct nfs_locku_res *res)
 	if (status != -EIO)
 		nfs_increment_lock_seqid(status, res->seqid);
 	if (status == 0)
-		status = decode_stateid(xdr, &res->stateid);
+		status = decode_lock_stateid(xdr, &res->stateid);
 	return status;
 }
 
@@ -5016,7 +5034,7 @@ static int decode_rw_delegation(struct xdr_stream *xdr,
 	__be32 *p;
 	int status;
 
-	status = decode_stateid(xdr, &res->delegation);
+	status = decode_delegation_stateid(xdr, &res->delegation);
 	if (unlikely(status))
 		return status;
 	p = xdr_inline_decode(xdr, 4);
@@ -5096,7 +5114,7 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
 	nfs_increment_open_seqid(status, res->seqid);
 	if (status)
 		return status;
-	status = decode_stateid(xdr, &res->stateid);
+	status = decode_open_stateid(xdr, &res->stateid);
 	if (unlikely(status))
 		return status;
 
@@ -5136,7 +5154,7 @@ static int decode_open_confirm(struct xdr_stream *xdr, struct nfs_open_confirmre
 	if (status != -EIO)
 		nfs_increment_open_seqid(status, res->seqid);
 	if (!status)
-		status = decode_stateid(xdr, &res->stateid);
+		status = decode_open_stateid(xdr, &res->stateid);
 	return status;
 }
 
@@ -5148,7 +5166,7 @@ static int decode_open_downgrade(struct xdr_stream *xdr, struct nfs_closeres *re
 	if (status != -EIO)
 		nfs_increment_open_seqid(status, res->seqid);
 	if (!status)
-		status = decode_stateid(xdr, &res->stateid);
+		status = decode_open_stateid(xdr, &res->stateid);
 	return status;
 }
 
@@ -5838,6 +5856,12 @@ out_overflow:
 }
 
 #if defined(CONFIG_NFS_V4_1)
+static int decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+	stateid->type = NFS4_LAYOUT_STATEID_TYPE;
+	return decode_stateid(xdr, stateid);
+}
+
 static int decode_getdeviceinfo(struct xdr_stream *xdr,
 				struct nfs4_getdeviceinfo_res *res)
 {
@@ -5919,7 +5943,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 	if (unlikely(!p))
 		goto out_overflow;
 	res->return_on_close = be32_to_cpup(p);
-	decode_stateid(xdr, &res->stateid);
+	decode_layout_stateid(xdr, &res->stateid);
 	p = xdr_inline_decode(xdr, 4);
 	if (unlikely(!p))
 		goto out_overflow;
@@ -5985,7 +6009,7 @@ static int decode_layoutreturn(struct xdr_stream *xdr,
 		goto out_overflow;
 	res->lrs_present = be32_to_cpup(p);
 	if (res->lrs_present)
-		status = decode_stateid(xdr, &res->stateid);
+		status = decode_layout_stateid(xdr, &res->stateid);
 	return status;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 722509482e1a..e1692c96cbc8 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -50,12 +50,27 @@ struct nfs4_label {
 
 typedef struct { char data[NFS4_VERIFIER_SIZE]; } nfs4_verifier;
 
-struct nfs_stateid4 {
-	__be32 seqid;
-	char other[NFS4_STATEID_OTHER_SIZE];
-} __attribute__ ((packed));
+struct nfs4_stateid_struct {
+	union {
+		char data[NFS4_STATEID_SIZE];
+		struct {
+			__be32 seqid;
+			char other[NFS4_STATEID_OTHER_SIZE];
+		} __attribute__ ((packed));
+	};
+
+	enum {
+		NFS4_INVALID_STATEID_TYPE = 0,
+		NFS4_SPECIAL_STATEID_TYPE,
+		NFS4_OPEN_STATEID_TYPE,
+		NFS4_LOCK_STATEID_TYPE,
+		NFS4_DELEGATION_STATEID_TYPE,
+		NFS4_LAYOUT_STATEID_TYPE,
+		NFS4_PNFS_DS_STATEID_TYPE,
+	} type;
+};
 
-typedef struct nfs_stateid4 nfs4_stateid;
+typedef struct nfs4_stateid_struct nfs4_stateid;
 
 enum nfs_opnum4 {
 	OP_ACCESS = 3,
-- 
cgit v1.2.3


From 183d9e7b112aaed0d19c16ffcf0f8c3a86dc71e0 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@poochiereds.net>
Date: Tue, 17 May 2016 12:28:47 -0400
Subject: pnfs: rework LAYOUTGET retry handling

There are several problems in the way a stateid is selected for a
LAYOUTGET operation:

We pick a stateid to use in the RPC prepare op, but that makes
it difficult to serialize LAYOUTGETs that use the open stateid. That
serialization is done in pnfs_update_layout, which occurs well before
the rpc_prepare operation.

Between those two events, the i_lock is dropped and reacquired.
pnfs_update_layout can find that the list has lsegs in it and not do any
serialization, but then later pnfs_choose_layoutget_stateid ends up
choosing the open stateid.

This patch changes the client to select the stateid to use in the
LAYOUTGET earlier, when we're searching for a usable layout segment.
This way we can do it all while holding the i_lock the first time, and
ensure that we serialize any LAYOUTGET call that uses a non-layout
stateid.

This also means a rework of how LAYOUTGET replies are handled, as we
must now get the latest stateid if we want to retransmit in response
to a retryable error.

Most of those errors boil down to the fact that the layout state has
changed in some fashion. Thus, what we really want to do is to re-search
for a layout when it fails with a retryable error, so that we can avoid
reissuing the RPC at all if possible.

While the LAYOUTGET RPC is async, the initiating thread always waits for
it to complete, so it's effectively synchronous anyway. Currently, when
we need to retry a LAYOUTGET because of an error, we drive that retry
via the rpc state machine.

This means that once the call has been submitted, it runs until it
completes. So, we must move the error handling for this RPC out of the
rpc_call_done operation and into the caller.

In order to handle errors like NFS4ERR_DELAY properly, we must also
pass a pointer to the sliding timeout, which is now moved to the stack
in pnfs_update_layout.

The complicating errors are -NFS4ERR_RECALLCONFLICT and
-NFS4ERR_LAYOUTTRYLATER, as those involve a timeout after which we give
up and return NULL back to the caller. So, there is some special
handling for those errors to ensure that the layers driving the retries
can handle that appropriately.

Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c       | 115 ++++++++++++++++----------------------
 fs/nfs/nfs4trace.h      |  10 +++-
 fs/nfs/pnfs.c           | 144 +++++++++++++++++++++++++-----------------------
 fs/nfs/pnfs.h           |   6 +-
 include/linux/errno.h   |   1 +
 include/linux/nfs4.h    |   2 +
 include/linux/nfs_xdr.h |   2 -
 7 files changed, 136 insertions(+), 144 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 2a29f5d12aeb..62d67f040906 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -427,6 +427,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
 		case -NFS4ERR_GRACE:
+		case -NFS4ERR_RECALLCONFLICT:
 			exception->delay = 1;
 			return 0;
 
@@ -7847,40 +7848,34 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 	struct nfs4_layoutget *lgp = calldata;
 	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
 	struct nfs4_session *session = nfs4_get_session(server);
-	int ret;
 
 	dprintk("--> %s\n", __func__);
-	/* Note the is a race here, where a CB_LAYOUTRECALL can come in
-	 * right now covering the LAYOUTGET we are about to send.
-	 * However, that is not so catastrophic, and there seems
-	 * to be no way to prevent it completely.
-	 */
-	if (nfs41_setup_sequence(session, &lgp->args.seq_args,
-				&lgp->res.seq_res, task))
-		return;
-	ret = pnfs_choose_layoutget_stateid(&lgp->args.stateid,
-					  NFS_I(lgp->args.inode)->layout,
-					  &lgp->args.range,
-					  lgp->args.ctx->state);
-	if (ret < 0)
-		rpc_exit(task, ret);
+	nfs41_setup_sequence(session, &lgp->args.seq_args,
+				&lgp->res.seq_res, task);
+	dprintk("<-- %s\n", __func__);
 }
 
 static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutget *lgp = calldata;
+
+	dprintk("--> %s\n", __func__);
+	nfs41_sequence_done(task, &lgp->res.seq_res);
+	dprintk("<-- %s\n", __func__);
+}
+
+static int
+nfs4_layoutget_handle_exception(struct rpc_task *task,
+		struct nfs4_layoutget *lgp, struct nfs4_exception *exception)
+{
 	struct inode *inode = lgp->args.inode;
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layout_hdr *lo;
-	struct nfs4_state *state = NULL;
-	unsigned long timeo, now, giveup;
+	int status = task->tk_status;
 
 	dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
 
-	if (!nfs41_sequence_done(task, &lgp->res.seq_res))
-		goto out;
-
-	switch (task->tk_status) {
+	switch (status) {
 	case 0:
 		goto out;
 
@@ -7890,57 +7885,43 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	 * retry go inband.
 	 */
 	case -NFS4ERR_LAYOUTUNAVAILABLE:
-		task->tk_status = -ENODATA;
+		status = -ENODATA;
 		goto out;
 	/*
 	 * NFS4ERR_BADLAYOUT means the MDS cannot return a layout of
 	 * length lgp->args.minlength != 0 (see RFC5661 section 18.43.3).
 	 */
 	case -NFS4ERR_BADLAYOUT:
-		goto out_overflow;
+		status = -EOVERFLOW;
+		goto out;
 	/*
 	 * NFS4ERR_LAYOUTTRYLATER is a conflict with another client
 	 * (or clients) writing to the same RAID stripe except when
 	 * the minlength argument is 0 (see RFC5661 section 18.43.3).
+	 *
+	 * Treat it like we would RECALLCONFLICT -- we retry for a little
+	 * while, and then eventually give up.
 	 */
 	case -NFS4ERR_LAYOUTTRYLATER:
-		if (lgp->args.minlength == 0)
-			goto out_overflow;
-	/*
-	 * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
-	 * existing layout before getting a new one).
-	 */
-	case -NFS4ERR_RECALLCONFLICT:
-		timeo = rpc_get_timeout(task->tk_client);
-		giveup = lgp->args.timestamp + timeo;
-		now = jiffies;
-		if (time_after(giveup, now)) {
-			unsigned long delay;
-
-			/* Delay for:
-			 * - Not less then NFS4_POLL_RETRY_MIN.
-			 * - One last time a jiffie before we give up
-			 * - exponential backoff (time_now minus start_attempt)
-			 */
-			delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
-				    min((giveup - now - 1),
-					now - lgp->args.timestamp));
-
-			dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
-				__func__, delay);
-			rpc_delay(task, delay);
-			/* Do not call nfs4_async_handle_error() */
-			goto out_restart;
+		if (lgp->args.minlength == 0) {
+			status = -EOVERFLOW;
+			goto out;
 		}
-		break;
+		/* Fallthrough */
+	case -NFS4ERR_RECALLCONFLICT:
+		nfs4_handle_exception(server, -NFS4ERR_RECALLCONFLICT,
+					exception);
+		status = -ERECALLCONFLICT;
+		goto out;
 	case -NFS4ERR_EXPIRED:
 	case -NFS4ERR_BAD_STATEID:
+		exception->timeout = 0;
 		spin_lock(&inode->i_lock);
 		if (nfs4_stateid_match(&lgp->args.stateid,
 					&lgp->args.ctx->state->stateid)) {
 			spin_unlock(&inode->i_lock);
 			/* If the open stateid was bad, then recover it. */
-			state = lgp->args.ctx->state;
+			exception->state = lgp->args.ctx->state;
 			break;
 		}
 		lo = NFS_I(inode)->layout;
@@ -7958,20 +7939,16 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 			pnfs_free_lseg_list(&head);
 		} else
 			spin_unlock(&inode->i_lock);
-		goto out_restart;
+		status = -EAGAIN;
+		goto out;
 	}
-	if (nfs4_async_handle_error(task, server, state, &lgp->timeout) == -EAGAIN)
-		goto out_restart;
+
+	status = nfs4_handle_exception(server, status, exception);
+	if (exception->retry)
+		status = -EAGAIN;
 out:
 	dprintk("<-- %s\n", __func__);
-	return;
-out_restart:
-	task->tk_status = 0;
-	rpc_restart_call_prepare(task);
-	return;
-out_overflow:
-	task->tk_status = -EOVERFLOW;
-	goto out;
+	return status;
 }
 
 static size_t max_response_pages(struct nfs_server *server)
@@ -8040,7 +8017,7 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = {
 };
 
 struct pnfs_layout_segment *
-nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
+nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags)
 {
 	struct inode *inode = lgp->args.inode;
 	struct nfs_server *server = NFS_SERVER(inode);
@@ -8060,6 +8037,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 		.flags = RPC_TASK_ASYNC,
 	};
 	struct pnfs_layout_segment *lseg = NULL;
+	struct nfs4_exception exception = { .timeout = *timeout };
 	int status = 0;
 
 	dprintk("--> %s\n", __func__);
@@ -8073,7 +8051,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 		return ERR_PTR(-ENOMEM);
 	}
 	lgp->args.layout.pglen = max_pages * PAGE_SIZE;
-	lgp->args.timestamp = jiffies;
 
 	lgp->res.layoutp = &lgp->args.layout;
 	lgp->res.seq_res.sr_slot = NULL;
@@ -8083,13 +8060,17 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 	if (IS_ERR(task))
 		return ERR_CAST(task);
 	status = nfs4_wait_for_completion_rpc_task(task);
-	if (status == 0)
-		status = task->tk_status;
+	if (status == 0) {
+		status = nfs4_layoutget_handle_exception(task, lgp, &exception);
+		*timeout = exception.timeout;
+	}
+
 	trace_nfs4_layoutget(lgp->args.ctx,
 			&lgp->args.range,
 			&lgp->res.range,
 			&lgp->res.stateid,
 			status);
+
 	/* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
 	if (status == 0 && lgp->res.layoutp->len)
 		lseg = pnfs_layout_process(lgp);
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 2c8d05dae5b1..9c150b153782 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -1520,6 +1520,8 @@ DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close);
 		{ PNFS_UPDATE_LAYOUT_FOUND_CACHED, "found cached" },	\
 		{ PNFS_UPDATE_LAYOUT_RETURN, "layoutreturn" },		\
 		{ PNFS_UPDATE_LAYOUT_BLOCKED, "layouts blocked" },	\
+		{ PNFS_UPDATE_LAYOUT_INVALID_OPEN, "invalid open" },	\
+		{ PNFS_UPDATE_LAYOUT_RETRY, "retrying" },	\
 		{ PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, "sent layoutget" })
 
 TRACE_EVENT(pnfs_update_layout,
@@ -1528,9 +1530,10 @@ TRACE_EVENT(pnfs_update_layout,
 			u64 count,
 			enum pnfs_iomode iomode,
 			struct pnfs_layout_hdr *lo,
+			struct pnfs_layout_segment *lseg,
 			enum pnfs_update_layout_reason reason
 		),
-		TP_ARGS(inode, pos, count, iomode, lo, reason),
+		TP_ARGS(inode, pos, count, iomode, lo, lseg, reason),
 		TP_STRUCT__entry(
 			__field(dev_t, dev)
 			__field(u64, fileid)
@@ -1540,6 +1543,7 @@ TRACE_EVENT(pnfs_update_layout,
 			__field(enum pnfs_iomode, iomode)
 			__field(int, layoutstateid_seq)
 			__field(u32, layoutstateid_hash)
+			__field(long, lseg)
 			__field(enum pnfs_update_layout_reason, reason)
 		),
 		TP_fast_assign(
@@ -1559,11 +1563,12 @@ TRACE_EVENT(pnfs_update_layout,
 				__entry->layoutstateid_seq = 0;
 				__entry->layoutstateid_hash = 0;
 			}
+			__entry->lseg = (long)lseg;
 		),
 		TP_printk(
 			"fileid=%02x:%02x:%llu fhandle=0x%08x "
 			"iomode=%s pos=%llu count=%llu "
-			"layoutstateid=%d:0x%08x (%s)",
+			"layoutstateid=%d:0x%08x lseg=0x%lx (%s)",
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle,
@@ -1571,6 +1576,7 @@ TRACE_EVENT(pnfs_update_layout,
 			(unsigned long long)__entry->pos,
 			(unsigned long long)__entry->count,
 			__entry->layoutstateid_seq, __entry->layoutstateid_hash,
+			__entry->lseg,
 			show_pnfs_update_layout_reason(__entry->reason)
 		)
 );
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 2a609af845fe..46339a7fb191 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -796,45 +796,18 @@ pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo)
 		test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
 }
 
-int
-pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
-			      const struct pnfs_layout_range *range,
-			      struct nfs4_state *open_state)
-{
-	int status = 0;
-
-	dprintk("--> %s\n", __func__);
-	spin_lock(&lo->plh_inode->i_lock);
-	if (pnfs_layoutgets_blocked(lo)) {
-		status = -EAGAIN;
-	} else if (!nfs4_valid_open_stateid(open_state)) {
-		status = -EBADF;
-	} else if (list_empty(&lo->plh_segs) ||
-		   test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
-		int seq;
-
-		do {
-			seq = read_seqbegin(&open_state->seqlock);
-			nfs4_stateid_copy(dst, &open_state->stateid);
-		} while (read_seqretry(&open_state->seqlock, seq));
-	} else
-		nfs4_stateid_copy(dst, &lo->plh_stateid);
-	spin_unlock(&lo->plh_inode->i_lock);
-	dprintk("<-- %s\n", __func__);
-	return status;
-}
-
 /*
-* Get layout from server.
-*    for now, assume that whole file layouts are requested.
-*    arg->offset: 0
-*    arg->length: all ones
-*/
+ * Get layout from server.
+ *    for now, assume that whole file layouts are requested.
+ *    arg->offset: 0
+ *    arg->length: all ones
+ */
 static struct pnfs_layout_segment *
 send_layoutget(struct pnfs_layout_hdr *lo,
 	   struct nfs_open_context *ctx,
+	   nfs4_stateid *stateid,
 	   const struct pnfs_layout_range *range,
-	   gfp_t gfp_flags)
+	   long *timeout, gfp_t gfp_flags)
 {
 	struct inode *ino = lo->plh_inode;
 	struct nfs_server *server = NFS_SERVER(ino);
@@ -868,10 +841,11 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	lgp->args.type = server->pnfs_curr_ld->id;
 	lgp->args.inode = ino;
 	lgp->args.ctx = get_nfs_open_context(ctx);
+	nfs4_stateid_copy(&lgp->args.stateid, stateid);
 	lgp->gfp_flags = gfp_flags;
 	lgp->cred = lo->plh_lc_cred;
 
-	return nfs4_proc_layoutget(lgp, gfp_flags);
+	return nfs4_proc_layoutget(lgp, timeout, gfp_flags);
 }
 
 static void pnfs_clear_layoutcommit(struct inode *inode,
@@ -1511,27 +1485,30 @@ pnfs_update_layout(struct inode *ino,
 		.offset = pos,
 		.length = count,
 	};
-	unsigned pg_offset;
+	unsigned pg_offset, seq;
 	struct nfs_server *server = NFS_SERVER(ino);
 	struct nfs_client *clp = server->nfs_client;
-	struct pnfs_layout_hdr *lo;
+	struct pnfs_layout_hdr *lo = NULL;
 	struct pnfs_layout_segment *lseg = NULL;
+	nfs4_stateid stateid;
+	long timeout = 0;
+	unsigned long giveup = jiffies + rpc_get_timeout(server->client);
 	bool first;
 
 	if (!pnfs_enabled_sb(NFS_SERVER(ino))) {
-		trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				 PNFS_UPDATE_LAYOUT_NO_PNFS);
 		goto out;
 	}
 
 	if (iomode == IOMODE_READ && i_size_read(ino) == 0) {
-		trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				 PNFS_UPDATE_LAYOUT_RD_ZEROLEN);
 		goto out;
 	}
 
 	if (pnfs_within_mdsthreshold(ctx, ino, iomode)) {
-		trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				 PNFS_UPDATE_LAYOUT_MDSTHRESH);
 		goto out;
 	}
@@ -1542,14 +1519,14 @@ lookup_again:
 	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
 	if (lo == NULL) {
 		spin_unlock(&ino->i_lock);
-		trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				 PNFS_UPDATE_LAYOUT_NOMEM);
 		goto out;
 	}
 
 	/* Do we even need to bother with this? */
 	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
-		trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				 PNFS_UPDATE_LAYOUT_BULK_RECALL);
 		dprintk("%s matches recall, use MDS\n", __func__);
 		goto out_unlock;
@@ -1557,14 +1534,34 @@ lookup_again:
 
 	/* if LAYOUTGET already failed once we don't try again */
 	if (pnfs_layout_io_test_failed(lo, iomode)) {
-		trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				 PNFS_UPDATE_LAYOUT_IO_TEST_FAIL);
 		goto out_unlock;
 	}
 
-	first = list_empty(&lo->plh_segs);
-	if (first) {
-		/* The first layoutget for the file. Need to serialize per
+	lseg = pnfs_find_lseg(lo, &arg);
+	if (lseg) {
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+				PNFS_UPDATE_LAYOUT_FOUND_CACHED);
+		goto out_unlock;
+	}
+
+	if (!nfs4_valid_open_stateid(ctx->state)) {
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+				PNFS_UPDATE_LAYOUT_INVALID_OPEN);
+		goto out_unlock;
+	}
+
+	/*
+	 * Choose a stateid for the LAYOUTGET. If we don't have a layout
+	 * stateid, or it has been invalidated, then we must use the open
+	 * stateid.
+	 */
+	if (lo->plh_stateid.seqid == 0 ||
+	    test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
+
+		/*
+		 * The first layoutget for the file. Need to serialize per
 		 * RFC 5661 Errata 3208.
 		 */
 		if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET,
@@ -1573,18 +1570,17 @@ lookup_again:
 			wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET,
 				    TASK_UNINTERRUPTIBLE);
 			pnfs_put_layout_hdr(lo);
+			dprintk("%s retrying\n", __func__);
 			goto lookup_again;
 		}
+
+		first = true;
+		do {
+			seq = read_seqbegin(&ctx->state->seqlock);
+			nfs4_stateid_copy(&stateid, &ctx->state->stateid);
+		} while (read_seqretry(&ctx->state->seqlock, seq));
 	} else {
-		/* Check to see if the layout for the given range
-		 * already exists
-		 */
-		lseg = pnfs_find_lseg(lo, &arg);
-		if (lseg) {
-			trace_pnfs_update_layout(ino, pos, count, iomode, lo,
-					PNFS_UPDATE_LAYOUT_FOUND_CACHED);
-			goto out_unlock;
-		}
+		nfs4_stateid_copy(&stateid, &lo->plh_stateid);
 	}
 
 	/*
@@ -1599,15 +1595,17 @@ lookup_again:
 				pnfs_clear_first_layoutget(lo);
 			pnfs_put_layout_hdr(lo);
 			dprintk("%s retrying\n", __func__);
+			trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+					lseg, PNFS_UPDATE_LAYOUT_RETRY);
 			goto lookup_again;
 		}
-		trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				PNFS_UPDATE_LAYOUT_RETURN);
 		goto out_put_layout_hdr;
 	}
 
 	if (pnfs_layoutgets_blocked(lo)) {
-		trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				PNFS_UPDATE_LAYOUT_BLOCKED);
 		goto out_unlock;
 	}
@@ -1632,26 +1630,36 @@ lookup_again:
 	if (arg.length != NFS4_MAX_UINT64)
 		arg.length = PAGE_ALIGN(arg.length);
 
-	lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
+	lseg = send_layoutget(lo, ctx, &stateid, &arg, &timeout, gfp_flags);
+	trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+				 PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET);
 	if (IS_ERR(lseg)) {
-		if (lseg == ERR_PTR(-EAGAIN)) {
+		switch(PTR_ERR(lseg)) {
+		case -ERECALLCONFLICT:
+			if (time_after(jiffies, giveup))
+				lseg = NULL;
+			/* Fallthrough */
+		case -EAGAIN:
+			pnfs_put_layout_hdr(lo);
 			if (first)
 				pnfs_clear_first_layoutget(lo);
-			pnfs_put_layout_hdr(lo);
-			goto lookup_again;
-		}
-
-		if (!nfs_error_is_fatal(PTR_ERR(lseg))) {
-			pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
-			lseg = NULL;
+			if (lseg) {
+				trace_pnfs_update_layout(ino, pos, count,
+					iomode, lo, lseg, PNFS_UPDATE_LAYOUT_RETRY);
+				goto lookup_again;
+			}
+			/* Fallthrough */
+		default:
+			if (!nfs_error_is_fatal(PTR_ERR(lseg))) {
+				pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
+				lseg = NULL;
+			}
 		}
 	} else {
 		pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
 	}
 
 	atomic_dec(&lo->plh_outstanding);
-	trace_pnfs_update_layout(ino, pos, count, iomode, lo,
-				 PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET);
 out_put_layout_hdr:
 	if (first)
 		pnfs_clear_first_layoutget(lo);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 971068b58647..f9f3331bef49 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -228,7 +228,7 @@ extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev,
 				   struct rpc_cred *cred);
-extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags);
+extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags);
 extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync);
 
 /* pnfs.c */
@@ -260,10 +260,6 @@ void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo);
 void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
 			     const nfs4_stateid *new,
 			     bool update_barrier);
-int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
-				  struct pnfs_layout_hdr *lo,
-				  const struct pnfs_layout_range *range,
-				  struct nfs4_state *open_state);
 int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
 				const struct pnfs_layout_range *recall_range,
diff --git a/include/linux/errno.h b/include/linux/errno.h
index 89627b9187f9..7ce9fb1b7d28 100644
--- a/include/linux/errno.h
+++ b/include/linux/errno.h
@@ -28,5 +28,6 @@
 #define EBADTYPE	527	/* Type not supported by server */
 #define EJUKEBOX	528	/* Request initiated, but will not complete before timeout */
 #define EIOCBQUEUED	529	/* iocb queued, will get completion event */
+#define ERECALLCONFLICT	530	/* conflict with recalled state */
 
 #endif
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index e1692c96cbc8..bfed6b367350 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -637,7 +637,9 @@ enum pnfs_update_layout_reason {
 	PNFS_UPDATE_LAYOUT_IO_TEST_FAIL,
 	PNFS_UPDATE_LAYOUT_FOUND_CACHED,
 	PNFS_UPDATE_LAYOUT_RETURN,
+	PNFS_UPDATE_LAYOUT_RETRY,
 	PNFS_UPDATE_LAYOUT_BLOCKED,
+	PNFS_UPDATE_LAYOUT_INVALID_OPEN,
 	PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET,
 };
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index e70ed54dad94..ccb2928a0e64 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -233,7 +233,6 @@ struct nfs4_layoutget_args {
 	struct inode *inode;
 	struct nfs_open_context *ctx;
 	nfs4_stateid stateid;
-	unsigned long timestamp;
 	struct nfs4_layoutdriver_data layout;
 };
 
@@ -251,7 +250,6 @@ struct nfs4_layoutget {
 	struct nfs4_layoutget_res res;
 	struct rpc_cred *cred;
 	gfp_t gfp_flags;
-	long timeout;
 };
 
 struct nfs4_getdeviceinfo_args {
-- 
cgit v1.2.3