From 4c3ffd058c28bb1aac30a68d1f02de4a2077823e Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Fri, 6 Jan 2017 14:19:58 +1100
Subject: SUNRPC: two small improvements to rpcauth shrinker.

1/ If we find an entry that is too young to be pruned,
  return SHRINK_STOP to ensure we don't get called again.
  This is more correct, and avoids wasting a little CPU time.
  Prior to 3.12, it can prevent drop_slab() from spinning indefinitely.

2/ Return a precise number from rpcauth_cache_shrink_count(), rather than
  rounding down to a multiple of 100 (of whatever sysctl_vfs_cache_pressure is).
  This ensures that when we "echo 3 > /proc/sys/vm/drop_caches", this cache is
  still purged, even if it has fewer than 100 entires.

Neither of these are really important, they just make behaviour
more predicatable, which can be helpful when debugging related issues.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/auth.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 2bff63a73cf8..d8f17ea7932e 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -464,8 +464,10 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan)
 		 * Note that the cred_unused list must be time-ordered.
 		 */
 		if (time_in_range(cred->cr_expire, expired, jiffies) &&
-		    test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0)
+		    test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) {
+			freed = SHRINK_STOP;
 			break;
+		}
 
 		list_del_init(&cred->cr_lru);
 		number_cred_unused--;
@@ -520,7 +522,7 @@ static unsigned long
 rpcauth_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 
 {
-	return (number_cred_unused / 100) * sysctl_vfs_cache_pressure;
+	return number_cred_unused * sysctl_vfs_cache_pressure / 100;
 }
 
 static void
-- 
cgit v1.2.3


From 2864486bd0fdd14431058650c91fcb9fba605d43 Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Tue, 7 Feb 2017 21:46:39 +0800
Subject: sunrpc: error out if register_shrinker fail

register_shrinker may return error when register fail, error out.

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/auth.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index d8f17ea7932e..8b344d0eb6ed 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -878,8 +878,12 @@ int __init rpcauth_init_module(void)
 	err = rpc_init_generic_auth();
 	if (err < 0)
 		goto out2;
-	register_shrinker(&rpc_cred_shrinker);
+	err = register_shrinker(&rpc_cred_shrinker);
+	if (err < 0)
+		goto out3;
 	return 0;
+out3:
+	rpc_destroy_generic_auth();
 out2:
 	rpc_destroy_authunix();
 out1:
-- 
cgit v1.2.3


From 863d7d9c2e0cbbde6cd15f87c4431dd806f2d917 Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Tue, 7 Feb 2017 21:47:16 +0800
Subject: sunrpc/nfs: cleanup procfs/pipefs entry in cache_detail

Record flush/channel/content entries is useless, remove them.

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/cache_lib.c           |  3 +--
 include/linux/sunrpc/cache.h | 15 +++-----------
 net/sunrpc/cache.c           | 49 +++++++++++++++-----------------------------
 3 files changed, 21 insertions(+), 46 deletions(-)

(limited to 'net/sunrpc')

diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c
index 6de15709d024..2ae676f93e6b 100644
--- a/fs/nfs/cache_lib.c
+++ b/fs/nfs/cache_lib.c
@@ -141,8 +141,7 @@ int nfs_cache_register_net(struct net *net, struct cache_detail *cd)
 
 void nfs_cache_unregister_sb(struct super_block *sb, struct cache_detail *cd)
 {
-	if (cd->u.pipefs.dir)
-		sunrpc_cache_unregister_pipefs(cd);
+	sunrpc_cache_unregister_pipefs(cd);
 }
 
 void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd)
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 62a60eeacb0a..bb5c9c80f12e 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -63,15 +63,6 @@ struct cache_head {
 
 #define	CACHE_NEW_EXPIRY 120	/* keep new things pending confirmation for 120 seconds */
 
-struct cache_detail_procfs {
-	struct proc_dir_entry	*proc_ent;
-	struct proc_dir_entry   *flush_ent, *channel_ent, *content_ent;
-};
-
-struct cache_detail_pipefs {
-	struct dentry *dir;
-};
-
 struct cache_detail {
 	struct module *		owner;
 	int			hash_size;
@@ -123,9 +114,9 @@ struct cache_detail {
 	time_t			last_warn;		/* when we last warned about no readers */
 
 	union {
-		struct cache_detail_procfs procfs;
-		struct cache_detail_pipefs pipefs;
-	} u;
+		struct proc_dir_entry	*procfs;
+		struct dentry		*pipefs;
+	};
 	struct net		*net;
 };
 
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 8147e8d56eb2..688ef8cbac62 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1600,21 +1600,12 @@ static const struct file_operations cache_flush_operations_procfs = {
 	.llseek		= no_llseek,
 };
 
-static void remove_cache_proc_entries(struct cache_detail *cd, struct net *net)
+static void remove_cache_proc_entries(struct cache_detail *cd)
 {
-	struct sunrpc_net *sn;
-
-	if (cd->u.procfs.proc_ent == NULL)
-		return;
-	if (cd->u.procfs.flush_ent)
-		remove_proc_entry("flush", cd->u.procfs.proc_ent);
-	if (cd->u.procfs.channel_ent)
-		remove_proc_entry("channel", cd->u.procfs.proc_ent);
-	if (cd->u.procfs.content_ent)
-		remove_proc_entry("content", cd->u.procfs.proc_ent);
-	cd->u.procfs.proc_ent = NULL;
-	sn = net_generic(net, sunrpc_net_id);
-	remove_proc_entry(cd->name, sn->proc_net_rpc);
+	if (cd->procfs) {
+		proc_remove(cd->procfs);
+		cd->procfs = NULL;
+	}
 }
 
 #ifdef CONFIG_PROC_FS
@@ -1624,38 +1615,30 @@ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
 	struct sunrpc_net *sn;
 
 	sn = net_generic(net, sunrpc_net_id);
-	cd->u.procfs.proc_ent = proc_mkdir(cd->name, sn->proc_net_rpc);
-	if (cd->u.procfs.proc_ent == NULL)
+	cd->procfs = proc_mkdir(cd->name, sn->proc_net_rpc);
+	if (cd->procfs == NULL)
 		goto out_nomem;
-	cd->u.procfs.channel_ent = NULL;
-	cd->u.procfs.content_ent = NULL;
 
 	p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR,
-			     cd->u.procfs.proc_ent,
-			     &cache_flush_operations_procfs, cd);
-	cd->u.procfs.flush_ent = p;
+			     cd->procfs, &cache_flush_operations_procfs, cd);
 	if (p == NULL)
 		goto out_nomem;
 
 	if (cd->cache_request || cd->cache_parse) {
 		p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR,
-				     cd->u.procfs.proc_ent,
-				     &cache_file_operations_procfs, cd);
-		cd->u.procfs.channel_ent = p;
+				cd->procfs, &cache_file_operations_procfs, cd);
 		if (p == NULL)
 			goto out_nomem;
 	}
 	if (cd->cache_show) {
 		p = proc_create_data("content", S_IFREG|S_IRUSR,
-				cd->u.procfs.proc_ent,
-				&content_file_operations_procfs, cd);
-		cd->u.procfs.content_ent = p;
+				cd->procfs, &content_file_operations_procfs, cd);
 		if (p == NULL)
 			goto out_nomem;
 	}
 	return 0;
 out_nomem:
-	remove_cache_proc_entries(cd, net);
+	remove_cache_proc_entries(cd);
 	return -ENOMEM;
 }
 #else /* CONFIG_PROC_FS */
@@ -1684,7 +1667,7 @@ EXPORT_SYMBOL_GPL(cache_register_net);
 
 void cache_unregister_net(struct cache_detail *cd, struct net *net)
 {
-	remove_cache_proc_entries(cd, net);
+	remove_cache_proc_entries(cd);
 	sunrpc_destroy_cache_detail(cd);
 }
 EXPORT_SYMBOL_GPL(cache_unregister_net);
@@ -1843,15 +1826,17 @@ int sunrpc_cache_register_pipefs(struct dentry *parent,
 	struct dentry *dir = rpc_create_cache_dir(parent, name, umode, cd);
 	if (IS_ERR(dir))
 		return PTR_ERR(dir);
-	cd->u.pipefs.dir = dir;
+	cd->pipefs = dir;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sunrpc_cache_register_pipefs);
 
 void sunrpc_cache_unregister_pipefs(struct cache_detail *cd)
 {
-	rpc_remove_cache_dir(cd->u.pipefs.dir);
-	cd->u.pipefs.dir = NULL;
+	if (cd->pipefs) {
+		rpc_remove_cache_dir(cd->pipefs);
+		cd->pipefs = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs);
 
-- 
cgit v1.2.3


From 5786461bd8ea81433d81297215ee814a9a33ce7a Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Tue, 7 Feb 2017 21:48:11 +0800
Subject: sunrpc: rename NFS_NGROUPS to UNX_NGROUPS for auth unix

NFS_NGROUPS has been move to sunrpc, rename to UNX_NGROUPS.

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/auth.h |  1 +
 net/sunrpc/auth_unix.c      | 18 ++++++++----------
 net/sunrpc/svcauth_unix.c   |  4 ++--
 3 files changed, 11 insertions(+), 12 deletions(-)

(limited to 'net/sunrpc')

diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index b1bc62ba20a2..39c85fb1f0ed 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -32,6 +32,7 @@
  */
 #define UNX_MAXNODENAME	__NEW_UTS_LEN
 #define UNX_CALLSLACK	(21 + XDR_QUADLEN(UNX_MAXNODENAME))
+#define UNX_NGROUPS	16
 
 struct rpcsec_gss_info;
 
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index 306fc0f54596..82337e1ec9cd 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -14,12 +14,10 @@
 #include <linux/sunrpc/auth.h>
 #include <linux/user_namespace.h>
 
-#define NFS_NGROUPS	16
-
 struct unx_cred {
 	struct rpc_cred		uc_base;
 	kgid_t			uc_gid;
-	kgid_t			uc_gids[NFS_NGROUPS];
+	kgid_t			uc_gids[UNX_NGROUPS];
 };
 #define uc_uid			uc_base.cr_uid
 
@@ -82,13 +80,13 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t
 
 	if (acred->group_info != NULL)
 		groups = acred->group_info->ngroups;
-	if (groups > NFS_NGROUPS)
-		groups = NFS_NGROUPS;
+	if (groups > UNX_NGROUPS)
+		groups = UNX_NGROUPS;
 
 	cred->uc_gid = acred->gid;
 	for (i = 0; i < groups; i++)
 		cred->uc_gids[i] = acred->group_info->gid[i];
-	if (i < NFS_NGROUPS)
+	if (i < UNX_NGROUPS)
 		cred->uc_gids[i] = INVALID_GID;
 
 	return &cred->uc_base;
@@ -132,12 +130,12 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags)
 
 	if (acred->group_info != NULL)
 		groups = acred->group_info->ngroups;
-	if (groups > NFS_NGROUPS)
-		groups = NFS_NGROUPS;
+	if (groups > UNX_NGROUPS)
+		groups = UNX_NGROUPS;
 	for (i = 0; i < groups ; i++)
 		if (!gid_eq(cred->uc_gids[i], acred->group_info->gid[i]))
 			return 0;
-	if (groups < NFS_NGROUPS && gid_valid(cred->uc_gids[groups]))
+	if (groups < UNX_NGROUPS && gid_valid(cred->uc_gids[groups]))
 		return 0;
 	return 1;
 }
@@ -166,7 +164,7 @@ unx_marshal(struct rpc_task *task, __be32 *p)
 	*p++ = htonl((u32) from_kuid(&init_user_ns, cred->uc_uid));
 	*p++ = htonl((u32) from_kgid(&init_user_ns, cred->uc_gid));
 	hold = p++;
-	for (i = 0; i < 16 && gid_valid(cred->uc_gids[i]); i++)
+	for (i = 0; i < UNX_NGROUPS && gid_valid(cred->uc_gids[i]); i++)
 		*p++ = htonl((u32) from_kgid(&init_user_ns, cred->uc_gids[i]));
 	*hold = htonl(p - hold - 1);		/* gid array length */
 	*base = htonl((p - base - 1) << 2);	/* cred length */
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index 64af4f034de6..f81eaa8e0888 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -403,7 +403,7 @@ svcauth_unix_info_release(struct svc_xprt *xpt)
 /****************************************************************************
  * auth.unix.gid cache
  * simple cache to map a UID to a list of GIDs
- * because AUTH_UNIX aka AUTH_SYS has a max of 16
+ * because AUTH_UNIX aka AUTH_SYS has a max of UNX_NGROUPS
  */
 #define	GID_HASHBITS	8
 #define	GID_HASHMAX	(1<<GID_HASHBITS)
@@ -810,7 +810,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp)
 	cred->cr_uid = make_kuid(&init_user_ns, svc_getnl(argv)); /* uid */
 	cred->cr_gid = make_kgid(&init_user_ns, svc_getnl(argv)); /* gid */
 	slen = svc_getnl(argv);			/* gids length */
-	if (slen > 16 || (len -= (slen + 2)*4) < 0)
+	if (slen > UNX_NGROUPS || (len -= (slen + 2)*4) < 0)
 		goto badcred;
 	cred->cr_group_info = groups_alloc(slen);
 	if (cred->cr_group_info == NULL)
-- 
cgit v1.2.3


From af4926e5619f8a33463f7202f27ba091893ed2ad Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Tue, 7 Feb 2017 21:48:49 +0800
Subject: sunrpc: remove dead codes of cr_magic in rpc_cred

Don't found any place using the cr_magic.

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/auth.h | 5 -----
 net/sunrpc/auth.c           | 3 ---
 net/sunrpc/auth_null.c      | 3 ---
 3 files changed, 11 deletions(-)

(limited to 'net/sunrpc')

diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 39c85fb1f0ed..8fd3504946ad 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -64,9 +64,6 @@ struct rpc_cred {
 	struct rcu_head		cr_rcu;
 	struct rpc_auth *	cr_auth;
 	const struct rpc_credops *cr_ops;
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-	unsigned long		cr_magic;	/* 0x0f4aa4f0 */
-#endif
 	unsigned long		cr_expire;	/* when to gc */
 	unsigned long		cr_flags;	/* various flags */
 	atomic_t		cr_count;	/* ref count */
@@ -80,8 +77,6 @@ struct rpc_cred {
 #define RPCAUTH_CRED_HASHED	2
 #define RPCAUTH_CRED_NEGATIVE	3
 
-#define RPCAUTH_CRED_MAGIC	0x0f4aa4f0
-
 /* rpc_auth au_flags */
 #define RPCAUTH_AUTH_NO_CRKEY_TIMEOUT	0x0001 /* underlying cred has no key timeout */
 
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 8b344d0eb6ed..a1ee933e3029 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -648,9 +648,6 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred,
 	cred->cr_auth = auth;
 	cred->cr_ops = ops;
 	cred->cr_expire = jiffies;
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-	cred->cr_magic = RPCAUTH_CRED_MAGIC;
-#endif
 	cred->cr_uid = acred->uid;
 }
 EXPORT_SYMBOL_GPL(rpcauth_init_cred);
diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c
index 4d17376b2acb..5f3d527dff65 100644
--- a/net/sunrpc/auth_null.c
+++ b/net/sunrpc/auth_null.c
@@ -139,7 +139,4 @@ struct rpc_cred null_cred = {
 	.cr_ops		= &null_credops,
 	.cr_count	= ATOMIC_INIT(1),
 	.cr_flags	= 1UL << RPCAUTH_CRED_UPTODATE,
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-	.cr_magic	= RPCAUTH_CRED_MAGIC,
-#endif
 };
-- 
cgit v1.2.3


From 6489a8f41370bcc53dac7107e298179da8c6cc05 Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Tue, 7 Feb 2017 21:49:17 +0800
Subject: sunrpc: update the comments of sunrpc proc path

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/cache.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 688ef8cbac62..9e8561d1714d 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -717,7 +717,7 @@ void cache_clean_deferred(void *owner)
 /*
  * communicate with user-space
  *
- * We have a magic /proc file - /proc/sunrpc/<cachename>/channel.
+ * We have a magic /proc file - /proc/net/rpc/<cachename>/channel.
  * On read, you get a full request, or block.
  * On write, an update request is processed.
  * Poll works if anything to read, and always allows write.
@@ -1272,7 +1272,7 @@ EXPORT_SYMBOL_GPL(qword_get);
 
 
 /*
- * support /proc/sunrpc/cache/$CACHENAME/content
+ * support /proc/net/rpc/$CACHENAME/content
  * as a seqfile.
  * We call ->cache_show passing NULL for the item to
  * get a header, then pass each real item in the cache
-- 
cgit v1.2.3


From 3f373e81b1e8d26a90523cd12385cbce588f3f18 Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Tue, 7 Feb 2017 21:49:57 +0800
Subject: sunrpc: record rpc client pointer in seq->private directly

pos in rpc_clnt_iter is useless, drop it and record clnt in seq_private.

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/debugfs.c | 35 ++++++++++-------------------------
 1 file changed, 10 insertions(+), 25 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
index e7b4d93566df..c8fd0b6c1618 100644
--- a/net/sunrpc/debugfs.c
+++ b/net/sunrpc/debugfs.c
@@ -16,11 +16,6 @@ static struct dentry *rpc_xprt_dir;
 
 unsigned int rpc_inject_disconnect;
 
-struct rpc_clnt_iter {
-	struct rpc_clnt	*clnt;
-	loff_t		pos;
-};
-
 static int
 tasks_show(struct seq_file *f, void *v)
 {
@@ -47,12 +42,10 @@ static void *
 tasks_start(struct seq_file *f, loff_t *ppos)
 	__acquires(&clnt->cl_lock)
 {
-	struct rpc_clnt_iter *iter = f->private;
+	struct rpc_clnt *clnt = f->private;
 	loff_t pos = *ppos;
-	struct rpc_clnt *clnt = iter->clnt;
 	struct rpc_task *task;
 
-	iter->pos = pos + 1;
 	spin_lock(&clnt->cl_lock);
 	list_for_each_entry(task, &clnt->cl_tasks, tk_task)
 		if (pos-- == 0)
@@ -63,12 +56,10 @@ tasks_start(struct seq_file *f, loff_t *ppos)
 static void *
 tasks_next(struct seq_file *f, void *v, loff_t *pos)
 {
-	struct rpc_clnt_iter *iter = f->private;
-	struct rpc_clnt *clnt = iter->clnt;
+	struct rpc_clnt *clnt = f->private;
 	struct rpc_task *task = v;
 	struct list_head *next = task->tk_task.next;
 
-	++iter->pos;
 	++*pos;
 
 	/* If there's another task on list, return it */
@@ -81,9 +72,7 @@ static void
 tasks_stop(struct seq_file *f, void *v)
 	__releases(&clnt->cl_lock)
 {
-	struct rpc_clnt_iter *iter = f->private;
-	struct rpc_clnt *clnt = iter->clnt;
-
+	struct rpc_clnt *clnt = f->private;
 	spin_unlock(&clnt->cl_lock);
 }
 
@@ -96,17 +85,13 @@ static const struct seq_operations tasks_seq_operations = {
 
 static int tasks_open(struct inode *inode, struct file *filp)
 {
-	int ret = seq_open_private(filp, &tasks_seq_operations,
-					sizeof(struct rpc_clnt_iter));
-
+	int ret = seq_open(filp, &tasks_seq_operations);
 	if (!ret) {
 		struct seq_file *seq = filp->private_data;
-		struct rpc_clnt_iter *iter = seq->private;
-
-		iter->clnt = inode->i_private;
+		struct rpc_clnt *clnt = seq->private = inode->i_private;
 
-		if (!atomic_inc_not_zero(&iter->clnt->cl_count)) {
-			seq_release_private(inode, filp);
+		if (!atomic_inc_not_zero(&clnt->cl_count)) {
+			seq_release(inode, filp);
 			ret = -EINVAL;
 		}
 	}
@@ -118,10 +103,10 @@ static int
 tasks_release(struct inode *inode, struct file *filp)
 {
 	struct seq_file *seq = filp->private_data;
-	struct rpc_clnt_iter *iter = seq->private;
+	struct rpc_clnt *clnt = seq->private;
 
-	rpc_release_client(iter->clnt);
-	return seq_release_private(inode, filp);
+	rpc_release_client(clnt);
+	return seq_release(inode, filp);
 }
 
 static const struct file_operations tasks_fops = {
-- 
cgit v1.2.3


From 8ccc869169d0c59d288b20ec2b060317f87e08b4 Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Tue, 7 Feb 2017 21:50:32 +0800
Subject: sunrpc: use simple_read_from_buffer for reading cache flush

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/cache.c | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 9e8561d1714d..2f06f510b570 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1427,20 +1427,11 @@ static ssize_t read_flush(struct file *file, char __user *buf,
 			  struct cache_detail *cd)
 {
 	char tbuf[22];
-	unsigned long p = *ppos;
 	size_t len;
 
-	snprintf(tbuf, sizeof(tbuf), "%lu\n", convert_to_wallclock(cd->flush_time));
-	len = strlen(tbuf);
-	if (p >= len)
-		return 0;
-	len -= p;
-	if (len > count)
-		len = count;
-	if (copy_to_user(buf, (void*)(tbuf+p), len))
-		return -EFAULT;
-	*ppos += len;
-	return len;
+	len = snprintf(tbuf, sizeof(tbuf), "%lu\n",
+			convert_to_wallclock(cd->flush_time));
+	return simple_read_from_buffer(buf, count, ppos, tbuf, len);
 }
 
 static ssize_t write_flush(struct file *file, const char __user *buf,
-- 
cgit v1.2.3


From d23bb113952db88b03a71c9533e5a40e444e18d3 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Wed, 8 Feb 2017 11:17:52 -0500
Subject: SUNRPC: Remove unused function rpc_get_timeout()

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/clnt.h |  1 -
 net/sunrpc/clnt.c           | 15 ---------------
 2 files changed, 16 deletions(-)

(limited to 'net/sunrpc')

diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 333ad11b3dd9..33f216edb434 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -182,7 +182,6 @@ 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);
 const char	*rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 1dc9f3bac099..2838a1fab460 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1452,21 +1452,6 @@ size_t rpc_max_bc_payload(struct rpc_clnt *clnt)
 }
 EXPORT_SYMBOL_GPL(rpc_max_bc_payload);
 
-/**
- * rpc_get_timeout - Get timeout for transport in units of HZ
- * @clnt: RPC client to query
- */
-unsigned long rpc_get_timeout(struct rpc_clnt *clnt)
-{
-	unsigned long ret;
-
-	rcu_read_lock();
-	ret = rcu_dereference(clnt->cl_xprt)->timeout->to_initval;
-	rcu_read_unlock();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(rpc_get_timeout);
-
 /**
  * rpc_force_rebind - force transport to check that remote port is unchanged
  * @clnt: client to rebind
-- 
cgit v1.2.3


From 8d1b8c62e0805af7df900ef121389778d2126997 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Wed, 8 Feb 2017 11:17:53 -0500
Subject: SUNRPC: Refactor TCP socket timeout code into a helper function

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtsock.c | 45 ++++++++++++++++++++++++++-------------------
 1 file changed, 26 insertions(+), 19 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index af392d9b9cec..c8ac649a51cb 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2235,6 +2235,31 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt)
 		xs_reset_transport(transport);
 }
 
+static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
+		struct socket *sock)
+{
+	unsigned int keepidle = DIV_ROUND_UP(xprt->timeout->to_initval, HZ);
+	unsigned int keepcnt = xprt->timeout->to_retries + 1;
+	unsigned int opt_on = 1;
+	unsigned int timeo;
+
+	/* TCP Keepalive options */
+	kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
+			(char *)&opt_on, sizeof(opt_on));
+	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE,
+			(char *)&keepidle, sizeof(keepidle));
+	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL,
+			(char *)&keepidle, sizeof(keepidle));
+	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
+			(char *)&keepcnt, sizeof(keepcnt));
+
+	/* TCP user timeout (see RFC5482) */
+	timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
+		(xprt->timeout->to_retries + 1);
+	kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
+			(char *)&timeo, sizeof(timeo));
+}
+
 static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -2242,22 +2267,8 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 
 	if (!transport->inet) {
 		struct sock *sk = sock->sk;
-		unsigned int keepidle = xprt->timeout->to_initval / HZ;
-		unsigned int keepcnt = xprt->timeout->to_retries + 1;
-		unsigned int opt_on = 1;
-		unsigned int timeo;
 		unsigned int addr_pref = IPV6_PREFER_SRC_PUBLIC;
 
-		/* TCP Keepalive options */
-		kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
-				(char *)&opt_on, sizeof(opt_on));
-		kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE,
-				(char *)&keepidle, sizeof(keepidle));
-		kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL,
-				(char *)&keepidle, sizeof(keepidle));
-		kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
-				(char *)&keepcnt, sizeof(keepcnt));
-
 		/* Avoid temporary address, they are bad for long-lived
 		 * connections such as NFS mounts.
 		 * RFC4941, section 3.6 suggests that:
@@ -2268,11 +2279,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		kernel_setsockopt(sock, SOL_IPV6, IPV6_ADDR_PREFERENCES,
 				(char *)&addr_pref, sizeof(addr_pref));
 
-		/* TCP user timeout (see RFC5482) */
-		timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
-			(xprt->timeout->to_retries + 1);
-		kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
-				(char *)&timeo, sizeof(timeo));
+		xs_tcp_set_socket_timeouts(xprt, sock);
 
 		write_lock_bh(&sk->sk_callback_lock);
 
-- 
cgit v1.2.3


From 7196dbb02ea05835b9ee56910ee82cb55422c7f1 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Wed, 8 Feb 2017 11:17:54 -0500
Subject: SUNRPC: Allow changing of the TCP timeout parameters on the fly

When the NFSv4 server tells us the lease period, we usually want
to adjust down the timeout parameters on the TCP connection to
ensure that we don't miss lease renewals due to a faulty connection.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xprt.h     |  4 ++++
 include/linux/sunrpc/xprtsock.h |  3 +++
 net/sunrpc/clnt.c               | 30 ++++++++++++++++++------
 net/sunrpc/xprtsock.c           | 51 +++++++++++++++++++++++++++++++++++++----
 4 files changed, 77 insertions(+), 11 deletions(-)

(limited to 'net/sunrpc')

diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index a5da60b24d83..eab1c749e192 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -137,6 +137,9 @@ struct rpc_xprt_ops {
 	void		(*release_request)(struct rpc_task *task);
 	void		(*close)(struct rpc_xprt *xprt);
 	void		(*destroy)(struct rpc_xprt *xprt);
+	void		(*set_connect_timeout)(struct rpc_xprt *xprt,
+					unsigned long connect_timeout,
+					unsigned long reconnect_timeout);
 	void		(*print_stats)(struct rpc_xprt *xprt, struct seq_file *seq);
 	int		(*enable_swap)(struct rpc_xprt *xprt);
 	void		(*disable_swap)(struct rpc_xprt *xprt);
@@ -221,6 +224,7 @@ struct rpc_xprt {
 	struct timer_list	timer;
 	unsigned long		last_used,
 				idle_timeout,
+				connect_timeout,
 				max_reconnect_timeout;
 
 	/*
diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index bef3fb0abb8f..c9959d7e3579 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -55,6 +55,8 @@ struct sock_xprt {
 	size_t			rcvsize,
 				sndsize;
 
+	struct rpc_timeout	tcp_timeout;
+
 	/*
 	 * Saved socket callback addresses
 	 */
@@ -81,6 +83,7 @@ struct sock_xprt {
 
 #define XPRT_SOCK_CONNECTING	1U
 #define XPRT_SOCK_DATA_READY	(2)
+#define XPRT_SOCK_UPD_TIMEOUT	(3)
 
 #endif /* __KERNEL__ */
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 2838a1fab460..b5bc0c589f6a 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2684,6 +2684,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt,
 {
 	struct rpc_xprt_switch *xps;
 	struct rpc_xprt *xprt;
+	unsigned long connect_timeout;
 	unsigned long reconnect_timeout;
 	unsigned char resvport;
 	int ret = 0;
@@ -2696,6 +2697,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt,
 		return -EAGAIN;
 	}
 	resvport = xprt->resvport;
+	connect_timeout = xprt->connect_timeout;
 	reconnect_timeout = xprt->max_reconnect_timeout;
 	rcu_read_unlock();
 
@@ -2705,7 +2707,10 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt,
 		goto out_put_switch;
 	}
 	xprt->resvport = resvport;
-	xprt->max_reconnect_timeout = reconnect_timeout;
+	if (xprt->ops->set_connect_timeout != NULL)
+		xprt->ops->set_connect_timeout(xprt,
+				connect_timeout,
+				reconnect_timeout);
 
 	rpc_xprt_switch_set_roundrobin(xps);
 	if (setup) {
@@ -2722,24 +2727,35 @@ out_put_switch:
 }
 EXPORT_SYMBOL_GPL(rpc_clnt_add_xprt);
 
+struct connect_timeout_data {
+	unsigned long connect_timeout;
+	unsigned long reconnect_timeout;
+};
+
 static int
-rpc_xprt_cap_max_reconnect_timeout(struct rpc_clnt *clnt,
+rpc_xprt_set_connect_timeout(struct rpc_clnt *clnt,
 		struct rpc_xprt *xprt,
 		void *data)
 {
-	unsigned long timeout = *((unsigned long *)data);
+	struct connect_timeout_data *timeo = data;
 
-	if (timeout < xprt->max_reconnect_timeout)
-		xprt->max_reconnect_timeout = timeout;
+	if (xprt->ops->set_connect_timeout)
+		xprt->ops->set_connect_timeout(xprt,
+				timeo->connect_timeout,
+				timeo->reconnect_timeout);
 	return 0;
 }
 
 void
 rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, unsigned long timeo)
 {
+	struct connect_timeout_data timeout = {
+		.connect_timeout = timeo,
+		.reconnect_timeout = timeo,
+	};
 	rpc_clnt_iterate_for_each_xprt(clnt,
-			rpc_xprt_cap_max_reconnect_timeout,
-			&timeo);
+			rpc_xprt_set_connect_timeout,
+			&timeout);
 }
 EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout);
 
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c8ac649a51cb..810e9b59be16 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -52,6 +52,8 @@
 #include "sunrpc.h"
 
 static void xs_close(struct rpc_xprt *xprt);
+static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
+		struct socket *sock);
 
 /*
  * xprtsock tunables
@@ -666,6 +668,9 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	if (task->tk_flags & RPC_TASK_SENT)
 		zerocopy = false;
 
+	if (test_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state))
+		xs_tcp_set_socket_timeouts(xprt, transport->sock);
+
 	/* Continue transmitting the packet/record. We must be careful
 	 * to cope with writespace callbacks arriving _after_ we have
 	 * called sendmsg(). */
@@ -2238,11 +2243,20 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt)
 static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
 		struct socket *sock)
 {
-	unsigned int keepidle = DIV_ROUND_UP(xprt->timeout->to_initval, HZ);
-	unsigned int keepcnt = xprt->timeout->to_retries + 1;
+	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	unsigned int keepidle;
+	unsigned int keepcnt;
 	unsigned int opt_on = 1;
 	unsigned int timeo;
 
+	spin_lock_bh(&xprt->transport_lock);
+	keepidle = DIV_ROUND_UP(xprt->timeout->to_initval, HZ);
+	keepcnt = xprt->timeout->to_retries + 1;
+	timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
+		(xprt->timeout->to_retries + 1);
+	clear_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state);
+	spin_unlock_bh(&xprt->transport_lock);
+
 	/* TCP Keepalive options */
 	kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
 			(char *)&opt_on, sizeof(opt_on));
@@ -2254,12 +2268,38 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
 			(char *)&keepcnt, sizeof(keepcnt));
 
 	/* TCP user timeout (see RFC5482) */
-	timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
-		(xprt->timeout->to_retries + 1);
 	kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
 			(char *)&timeo, sizeof(timeo));
 }
 
+static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt,
+		unsigned long connect_timeout,
+		unsigned long reconnect_timeout)
+{
+	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	struct rpc_timeout to;
+	unsigned long initval;
+
+	spin_lock_bh(&xprt->transport_lock);
+	if (reconnect_timeout < xprt->max_reconnect_timeout)
+		xprt->max_reconnect_timeout = reconnect_timeout;
+	if (connect_timeout < xprt->connect_timeout) {
+		memcpy(&to, xprt->timeout, sizeof(to));
+		initval = DIV_ROUND_UP(connect_timeout, to.to_retries + 1);
+		/* Arbitrary lower limit */
+		if (initval <  XS_TCP_INIT_REEST_TO << 1)
+			initval = XS_TCP_INIT_REEST_TO << 1;
+		to.to_initval = initval;
+		to.to_maxval = initval;
+		memcpy(&transport->tcp_timeout, &to,
+				sizeof(transport->tcp_timeout));
+		xprt->timeout = &transport->tcp_timeout;
+		xprt->connect_timeout = connect_timeout;
+	}
+	set_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state);
+	spin_unlock_bh(&xprt->transport_lock);
+}
+
 static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -2728,6 +2768,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 	.set_retrans_timeout	= xprt_set_retrans_timeout_def,
 	.close			= xs_tcp_shutdown,
 	.destroy		= xs_destroy,
+	.set_connect_timeout	= xs_tcp_set_connect_timeout,
 	.print_stats		= xs_tcp_print_stats,
 	.enable_swap		= xs_enable_swap,
 	.disable_swap		= xs_disable_swap,
@@ -3014,6 +3055,8 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
 	xprt->timeout = &xs_tcp_default_timeout;
 
 	xprt->max_reconnect_timeout = xprt->timeout->to_maxval;
+	xprt->connect_timeout = xprt->timeout->to_initval *
+		(xprt->timeout->to_retries + 1);
 
 	INIT_WORK(&transport->recv_worker, xs_tcp_data_receive_workfn);
 	INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_setup_socket);
-- 
cgit v1.2.3


From 26ae102f2cfd0215daa57dc790aa3bfe534403a9 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Wed, 8 Feb 2017 11:17:55 -0500
Subject: NFSv4: Set the connection timeout to match the lease period

Set the timeout for TCP connections to be 1 lease period to ensure
that we don't lose our lease due to a faulty TCP connection.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4renewd.c         |  2 +-
 include/linux/sunrpc/clnt.h |  5 +++--
 net/sunrpc/clnt.c           | 10 ++++++----
 3 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'net/sunrpc')

diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 82e77198d17e..1f8c2ae43a8d 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -153,7 +153,7 @@ void nfs4_set_lease_period(struct nfs_client *clp,
 	spin_unlock(&clp->cl_lock);
 
 	/* Cap maximum reconnect timeout at 1/2 lease period */
-	rpc_cap_max_reconnect_timeout(clp->cl_rpcclient, lease >> 1);
+	rpc_set_connect_timeout(clp->cl_rpcclient, lease, lease >> 1);
 }
 
 /*
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 33f216edb434..6095ecba0dde 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -201,8 +201,9 @@ int		rpc_clnt_add_xprt(struct rpc_clnt *, struct xprt_create *,
 				struct rpc_xprt *,
 				void *),
 			void *data);
-void		rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt,
-			unsigned long timeo);
+void		rpc_set_connect_timeout(struct rpc_clnt *clnt,
+			unsigned long connect_timeout,
+			unsigned long reconnect_timeout);
 
 int		rpc_clnt_setup_test_and_add_xprt(struct rpc_clnt *,
 			struct rpc_xprt_switch *,
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index b5bc0c589f6a..52da3ce54bb5 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2747,17 +2747,19 @@ rpc_xprt_set_connect_timeout(struct rpc_clnt *clnt,
 }
 
 void
-rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, unsigned long timeo)
+rpc_set_connect_timeout(struct rpc_clnt *clnt,
+		unsigned long connect_timeout,
+		unsigned long reconnect_timeout)
 {
 	struct connect_timeout_data timeout = {
-		.connect_timeout = timeo,
-		.reconnect_timeout = timeo,
+		.connect_timeout = connect_timeout,
+		.reconnect_timeout = reconnect_timeout,
 	};
 	rpc_clnt_iterate_for_each_xprt(clnt,
 			rpc_xprt_set_connect_timeout,
 			&timeout);
 }
-EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout);
+EXPORT_SYMBOL_GPL(rpc_set_connect_timeout);
 
 void rpc_clnt_xprt_switch_put(struct rpc_clnt *clnt)
 {
-- 
cgit v1.2.3


From 24abdf1be15c478e2821d6fc903a4a4440beff02 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Feb 2017 16:59:46 -0500
Subject: xprtrdma: Fix Read chunk padding

When pad optimization is disabled, rpcrdma_convert_iovs still
does not add explicit XDR round-up padding to a Read chunk.

Commit 677eb17e94ed ("xprtrdma: Fix XDR tail buffer marshalling")
incorrectly short-circuited the test for whether round-up padding
is needed that appears later in rpcrdma_convert_iovs.

However, if this is indeed a regular Read chunk (and not a
Position-Zero Read chunk), the tail iovec _always_ contains the
chunk's padding, and never anything else.

So, it's easy to just skip the tail when padding optimization is
enabled, and add the tail in a subsequent Read chunk segment, if
disabled.

Fixes: 677eb17e94ed ("xprtrdma: Fix XDR tail buffer marshalling")
Cc: stable@vger.kernel.org # v4.9+
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/rpc_rdma.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index c52e0f2ffe52..a524d3c2e8ac 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -226,8 +226,10 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 	if (len && n == RPCRDMA_MAX_SEGS)
 		goto out_overflow;
 
-	/* When encoding the read list, the tail is always sent inline */
-	if (type == rpcrdma_readch)
+	/* When encoding a Read chunk, the tail iovec contains an
+	 * XDR pad and may be omitted.
+	 */
+	if (type == rpcrdma_readch && xprt_rdma_pad_optimize)
 		return n;
 
 	/* When encoding the Write list, some servers need to see an extra
@@ -238,10 +240,6 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 		return n;
 
 	if (xdrbuf->tail[0].iov_len) {
-		/* the rpcrdma protocol allows us to omit any trailing
-		 * xdr pad bytes, saving the server an RDMA operation. */
-		if (xdrbuf->tail[0].iov_len < 4 && xprt_rdma_pad_optimize)
-			return n;
 		n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n);
 		if (n == RPCRDMA_MAX_SEGS)
 			goto out_overflow;
-- 
cgit v1.2.3


From b5f0afbea4f2ea52c613ac2b06cb6de2ea18cb6d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Feb 2017 16:59:54 -0500
Subject: xprtrdma: Per-connection pad optimization

Pad optimization is changed by echoing into
/proc/sys/sunrpc/rdma_pad_optimize. This is a global setting,
affecting all RPC-over-RDMA connections to all servers.

The marshaling code picks up that value and uses it for decisions
about how to construct each RPC-over-RDMA frame. Having it change
suddenly in mid-operation can result in unexpected failures. And
some servers a client mounts might need chunk round-up, while
others don't.

So instead, copy the pad_optimize setting into each connection's
rpcrdma_ia when the transport is created, and use the copy, which
can't change during the life of the connection, instead.

This also removes a hack: rpcrdma_convert_iovs was using
the remote-invalidation-expected flag to predict when it could leave
out Write chunk padding. This is because the Linux server handles
implicit XDR padding on Write chunks correctly, and only Linux
servers can set the connection's remote-invalidation-expected flag.

It's more sensible to use the pad optimization setting instead.

Fixes: 677eb17e94ed ("xprtrdma: Fix XDR tail buffer marshalling")
Cc: stable@vger.kernel.org # v4.9+
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/rpc_rdma.c  | 28 ++++++++++++++--------------
 net/sunrpc/xprtrdma/verbs.c     |  1 +
 net/sunrpc/xprtrdma/xprt_rdma.h |  1 +
 3 files changed, 16 insertions(+), 14 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index a524d3c2e8ac..c634f0f3f9ce 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -186,9 +186,9 @@ rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, int n)
  */
 
 static int
-rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
-	enum rpcrdma_chunktype type, struct rpcrdma_mr_seg *seg,
-	bool reminv_expected)
+rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
+		     unsigned int pos, enum rpcrdma_chunktype type,
+		     struct rpcrdma_mr_seg *seg)
 {
 	int len, n, p, page_base;
 	struct page **ppages;
@@ -229,14 +229,15 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 	/* When encoding a Read chunk, the tail iovec contains an
 	 * XDR pad and may be omitted.
 	 */
-	if (type == rpcrdma_readch && xprt_rdma_pad_optimize)
+	if (type == rpcrdma_readch && r_xprt->rx_ia.ri_implicit_roundup)
 		return n;
 
-	/* When encoding the Write list, some servers need to see an extra
-	 * segment for odd-length Write chunks. The upper layer provides
-	 * space in the tail iovec for this purpose.
+	/* When encoding a Write chunk, some servers need to see an
+	 * extra segment for non-XDR-aligned Write chunks. The upper
+	 * layer provides space in the tail iovec that may be used
+	 * for this purpose.
 	 */
-	if (type == rpcrdma_writech && reminv_expected)
+	if (type == rpcrdma_writech && r_xprt->rx_ia.ri_implicit_roundup)
 		return n;
 
 	if (xdrbuf->tail[0].iov_len) {
@@ -291,7 +292,8 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 	if (rtype == rpcrdma_areadch)
 		pos = 0;
 	seg = req->rl_segments;
-	nsegs = rpcrdma_convert_iovs(&rqst->rq_snd_buf, pos, rtype, seg, false);
+	nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_snd_buf, pos,
+				     rtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
@@ -353,10 +355,9 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	}
 
 	seg = req->rl_segments;
-	nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf,
+	nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf,
 				     rqst->rq_rcv_buf.head[0].iov_len,
-				     wtype, seg,
-				     r_xprt->rx_ia.ri_reminv_expected);
+				     wtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
@@ -421,8 +422,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 	}
 
 	seg = req->rl_segments;
-	nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, 0, wtype, seg,
-				     r_xprt->rx_ia.ri_reminv_expected);
+	nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf, 0, wtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 11d07748f699..2a6a367a2dac 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -208,6 +208,7 @@ rpcrdma_update_connect_private(struct rpcrdma_xprt *r_xprt,
 
 	/* Default settings for RPC-over-RDMA Version One */
 	r_xprt->rx_ia.ri_reminv_expected = false;
+	r_xprt->rx_ia.ri_implicit_roundup = xprt_rdma_pad_optimize;
 	rsize = RPCRDMA_V1_DEF_INLINE_SIZE;
 	wsize = RPCRDMA_V1_DEF_INLINE_SIZE;
 
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index e35efd4ac1e4..c13715431419 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -75,6 +75,7 @@ struct rpcrdma_ia {
 	unsigned int		ri_max_inline_write;
 	unsigned int		ri_max_inline_read;
 	bool			ri_reminv_expected;
+	bool			ri_implicit_roundup;
 	enum ib_mr_type		ri_mrtype;
 	struct ib_qp_attr	ri_qp_attr;
 	struct ib_qp_init_attr	ri_qp_init_attr;
-- 
cgit v1.2.3


From c95a3c6b88658bcb8f77f85f31a0b9d9036e8016 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Feb 2017 17:00:02 -0500
Subject: xprtrdma: Disable pad optimization by default

Commit d5440e27d3e5 ("xprtrdma: Enable pad optimization") made the
Linux client omit XDR round-up padding in normal Read and Write
chunks so that the client doesn't have to register and invalidate
3-byte memory regions that contain no real data.

Unfortunately, my cheery 2014 assessment that this optimization "is
supported now by both Linux and Solaris servers" was premature.
We've found bugs in Solaris in this area since commit d5440e27d3e5
("xprtrdma: Enable pad optimization") was merged (SYMLINK is the
main offender).

So for maximum interoperability, I'm disabling this optimization
again. If a CM private message is exchanged when connecting, the
client recognizes that the server is Linux, and enables the
optimization for that connection.

Until now the Solaris server bugs did not impact common operations,
and were thus largely benign. Soon, less capable devices on Linux
NFS/RDMA clients will make use of Read chunks more often, and these
Solaris bugs will prevent interoperation in more cases.

Fixes: 677eb17e94ed ("xprtrdma: Fix XDR tail buffer marshalling")
Cc: stable@vger.kernel.org # v4.9+
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/transport.c | 2 +-
 net/sunrpc/xprtrdma/verbs.c     | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 534c178d2a7e..699058169cfc 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -67,7 +67,7 @@ unsigned int xprt_rdma_max_inline_read = RPCRDMA_DEF_INLINE;
 static unsigned int xprt_rdma_max_inline_write = RPCRDMA_DEF_INLINE;
 static unsigned int xprt_rdma_inline_write_padding;
 static unsigned int xprt_rdma_memreg_strategy = RPCRDMA_FRMR;
-		int xprt_rdma_pad_optimize = 1;
+		int xprt_rdma_pad_optimize = 0;
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 2a6a367a2dac..23f4da419a64 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -216,6 +216,7 @@ rpcrdma_update_connect_private(struct rpcrdma_xprt *r_xprt,
 	    pmsg->cp_magic == rpcrdma_cmp_magic &&
 	    pmsg->cp_version == RPCRDMA_CMP_VERSION) {
 		r_xprt->rx_ia.ri_reminv_expected = true;
+		r_xprt->rx_ia.ri_implicit_roundup = true;
 		rsize = rpcrdma_decode_buffer_size(pmsg->cp_send_size);
 		wsize = rpcrdma_decode_buffer_size(pmsg->cp_recv_size);
 	}
-- 
cgit v1.2.3


From 16f906d66cd76fb9895cbc628f447532a7ac1faa Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Feb 2017 17:00:10 -0500
Subject: xprtrdma: Reduce required number of send SGEs

The MAX_SEND_SGES check introduced in commit 655fec6987be
("xprtrdma: Use gathered Send for large inline messages") fails
for devices that have a small max_sge.

Instead of checking for a large fixed maximum number of SGEs,
check for a minimum small number. RPC-over-RDMA will switch to
using a Read chunk if an xdr_buf has more pages than can fit in
the device's max_sge limit. This is considerably better than
failing all together to mount the server.

This fix supports devices that have as few as three send SGEs
available.

Reported-by: Selvin Xavier <selvin.xavier@broadcom.com>
Reported-by: Devesh Sharma <devesh.sharma@broadcom.com>
Reported-by: Honggang Li <honli@redhat.com>
Reported-by: Ram Amrani <Ram.Amrani@cavium.com>
Fixes: 655fec6987be ("xprtrdma: Use gathered Send for large ...")
Cc: stable@vger.kernel.org # v4.9+
Tested-by: Honggang Li <honli@redhat.com>
Tested-by: Ram Amrani <Ram.Amrani@cavium.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/rpc_rdma.c  | 26 +++++++++++++++++++++++---
 net/sunrpc/xprtrdma/verbs.c     | 13 +++++++------
 net/sunrpc/xprtrdma/xprt_rdma.h |  2 ++
 3 files changed, 32 insertions(+), 9 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index c634f0f3f9ce..d88988365cd2 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -125,14 +125,34 @@ void rpcrdma_set_max_header_sizes(struct rpcrdma_xprt *r_xprt)
 /* The client can send a request inline as long as the RPCRDMA header
  * plus the RPC call fit under the transport's inline limit. If the
  * combined call message size exceeds that limit, the client must use
- * the read chunk list for this operation.
+ * a Read chunk for this operation.
+ *
+ * A Read chunk is also required if sending the RPC call inline would
+ * exceed this device's max_sge limit.
  */
 static bool rpcrdma_args_inline(struct rpcrdma_xprt *r_xprt,
 				struct rpc_rqst *rqst)
 {
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct xdr_buf *xdr = &rqst->rq_snd_buf;
+	unsigned int count, remaining, offset;
+
+	if (xdr->len > r_xprt->rx_ia.ri_max_inline_write)
+		return false;
 
-	return rqst->rq_snd_buf.len <= ia->ri_max_inline_write;
+	if (xdr->page_len) {
+		remaining = xdr->page_len;
+		offset = xdr->page_base & ~PAGE_MASK;
+		count = 0;
+		while (remaining) {
+			remaining -= min_t(unsigned int,
+					   PAGE_SIZE - offset, remaining);
+			offset = 0;
+			if (++count > r_xprt->rx_ia.ri_max_send_sges)
+				return false;
+		}
+	}
+
+	return true;
 }
 
 /* The client can't know how large the actual reply will be. Thus it
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 23f4da419a64..61d16c39e92c 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -488,18 +488,19 @@ rpcrdma_ia_close(struct rpcrdma_ia *ia)
  */
 int
 rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
-				struct rpcrdma_create_data_internal *cdata)
+		  struct rpcrdma_create_data_internal *cdata)
 {
 	struct rpcrdma_connect_private *pmsg = &ep->rep_cm_private;
+	unsigned int max_qp_wr, max_sge;
 	struct ib_cq *sendcq, *recvcq;
-	unsigned int max_qp_wr;
 	int rc;
 
-	if (ia->ri_device->attrs.max_sge < RPCRDMA_MAX_SEND_SGES) {
-		dprintk("RPC:       %s: insufficient sge's available\n",
-			__func__);
+	max_sge = min(ia->ri_device->attrs.max_sge, RPCRDMA_MAX_SEND_SGES);
+	if (max_sge < RPCRDMA_MIN_SEND_SGES) {
+		pr_warn("rpcrdma: HCA provides only %d send SGEs\n", max_sge);
 		return -ENOMEM;
 	}
+	ia->ri_max_send_sges = max_sge - RPCRDMA_MIN_SEND_SGES;
 
 	if (ia->ri_device->attrs.max_qp_wr <= RPCRDMA_BACKWARD_WRS) {
 		dprintk("RPC:       %s: insufficient wqe's available\n",
@@ -524,7 +525,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
 	ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
 	ep->rep_attr.cap.max_recv_wr += 1;	/* drain cqe */
-	ep->rep_attr.cap.max_send_sge = RPCRDMA_MAX_SEND_SGES;
+	ep->rep_attr.cap.max_send_sge = max_sge;
 	ep->rep_attr.cap.max_recv_sge = 1;
 	ep->rep_attr.cap.max_inline_data = 0;
 	ep->rep_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index c13715431419..3d7e9c9bad1f 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -74,6 +74,7 @@ struct rpcrdma_ia {
 	unsigned int		ri_max_frmr_depth;
 	unsigned int		ri_max_inline_write;
 	unsigned int		ri_max_inline_read;
+	unsigned int		ri_max_send_sges;
 	bool			ri_reminv_expected;
 	bool			ri_implicit_roundup;
 	enum ib_mr_type		ri_mrtype;
@@ -311,6 +312,7 @@ struct rpcrdma_mr_seg {		/* chunk descriptors */
  * - xdr_buf tail iovec
  */
 enum {
+	RPCRDMA_MIN_SEND_SGES = 3,
 	RPCRDMA_MAX_SEND_PAGES = PAGE_SIZE + RPCRDMA_MAX_INLINE - 1,
 	RPCRDMA_MAX_PAGE_SGES = (RPCRDMA_MAX_SEND_PAGES >> PAGE_SHIFT) + 1,
 	RPCRDMA_MAX_SEND_SGES = 1 + 1 + RPCRDMA_MAX_PAGE_SGES + 1,
-- 
cgit v1.2.3


From c6f5b47f9fdeef12c0896e5af4bb3416c97d91c4 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Feb 2017 17:00:18 -0500
Subject: xprtrdma: Shrink send SGEs array

We no longer need to accommodate an xdr_buf whose pages start at an
offset and cross extra page boundaries. If there are more partial or
whole pages to send than there are available SGEs, the marshaling
logic is now smart enough to use a Read chunk instead of failing.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/xprt_rdma.h | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 3d7e9c9bad1f..852dd0a750a5 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -305,16 +305,19 @@ struct rpcrdma_mr_seg {		/* chunk descriptors */
 	char		*mr_offset;	/* kva if no page, else offset */
 };
 
-/* Reserve enough Send SGEs to send a maximum size inline request:
+/* The Send SGE array is provisioned to send a maximum size
+ * inline request:
  * - RPC-over-RDMA header
  * - xdr_buf head iovec
- * - RPCRDMA_MAX_INLINE bytes, possibly unaligned, in pages
+ * - RPCRDMA_MAX_INLINE bytes, in pages
  * - xdr_buf tail iovec
+ *
+ * The actual number of array elements consumed by each RPC
+ * depends on the device's max_sge limit.
  */
 enum {
 	RPCRDMA_MIN_SEND_SGES = 3,
-	RPCRDMA_MAX_SEND_PAGES = PAGE_SIZE + RPCRDMA_MAX_INLINE - 1,
-	RPCRDMA_MAX_PAGE_SGES = (RPCRDMA_MAX_SEND_PAGES >> PAGE_SHIFT) + 1,
+	RPCRDMA_MAX_PAGE_SGES = RPCRDMA_MAX_INLINE >> PAGE_SHIFT,
 	RPCRDMA_MAX_SEND_SGES = 1 + 1 + RPCRDMA_MAX_PAGE_SGES + 1,
 };
 
-- 
cgit v1.2.3


From 18c0fb31a034023e5cb2d3c9c1320d5d47d91afe Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Feb 2017 17:00:27 -0500
Subject: xprtrdma: Properly recover FRWRs with in-flight FASTREG WRs

Sriharsha (sriharsha.basavapatna@broadcom.com) reports an occasional
double DMA unmap of an FRWR MR when a connection is lost. I see one
way this can happen.

When a request requires more than one segment or chunk,
rpcrdma_marshal_req loops, invoking ->frwr_op_map for each segment
(MR) in each chunk. Each call posts a FASTREG Work Request to
register one MR.

Now suppose that the transport connection is lost part-way through
marshaling this request. As part of recovering and resetting that
req, rpcrdma_marshal_req invokes ->frwr_op_unmap_safe, which hands
all the req's registered FRWRs to the MR recovery thread.

But note: FRWR registration is asynchronous. So it's possible that
some of these "already registered" FRWRs are fully registered, and
some are still waiting for their FASTREG WR to complete.

When the connection is lost, the "already registered" frmrs are
marked FRMR_IS_VALID, and the "still waiting" WRs flush. Then
frwr_wc_fastreg marks these frmrs FRMR_FLUSHED_FR.

But thanks to ->frwr_op_unmap_safe, the MR recovery thread is doing
an unreg / alloc_mr, a DMA unmap, and marking each of these frwrs
FRMR_IS_INVALID, at the same time frwr_wc_fastreg might be running.

- If the recovery thread runs last, then the frmr is marked
FRMR_IS_INVALID, and life continues.

- If frwr_wc_fastreg runs last, the frmr is marked FRMR_FLUSHED_FR,
but the recovery thread has already DMA unmapped that MR. When
->frwr_op_map later re-uses this frmr, it sees it is not marked
FRMR_IS_INVALID, and tries to recover it before using it, resulting
in a second DMA unmap of the same MR.

The fix is to guarantee in-flight FASTREG WRs have flushed before MR
recovery runs on those FRWRs. Thus we depend on ro_unmap_safe
(called from xprt_rdma_send_request on retransmit, or from
xprt_rdma_free) to clean up old registrations as needed.

Reported-by: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/rpc_rdma.c  | 14 ++++++++------
 net/sunrpc/xprtrdma/transport.c |  4 ----
 2 files changed, 8 insertions(+), 10 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index d88988365cd2..72b3ca0253a0 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -759,13 +759,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	iptr = headerp->rm_body.rm_chunks;
 	iptr = rpcrdma_encode_read_list(r_xprt, req, rqst, iptr, rtype);
 	if (IS_ERR(iptr))
-		goto out_unmap;
+		goto out_err;
 	iptr = rpcrdma_encode_write_list(r_xprt, req, rqst, iptr, wtype);
 	if (IS_ERR(iptr))
-		goto out_unmap;
+		goto out_err;
 	iptr = rpcrdma_encode_reply_chunk(r_xprt, req, rqst, iptr, wtype);
 	if (IS_ERR(iptr))
-		goto out_unmap;
+		goto out_err;
 	hdrlen = (unsigned char *)iptr - (unsigned char *)headerp;
 
 	dprintk("RPC: %5u %s: %s/%s: hdrlen %zd rpclen %zd\n",
@@ -776,12 +776,14 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	if (!rpcrdma_prepare_send_sges(&r_xprt->rx_ia, req, hdrlen,
 				       &rqst->rq_snd_buf, rtype)) {
 		iptr = ERR_PTR(-EIO);
-		goto out_unmap;
+		goto out_err;
 	}
 	return 0;
 
-out_unmap:
-	r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false);
+out_err:
+	pr_err("rpcrdma: rpcrdma_marshal_req failed, status %ld\n",
+	       PTR_ERR(iptr));
+	r_xprt->rx_stats.failed_marshal_count++;
 	return PTR_ERR(iptr);
 }
 
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 699058169cfc..c717f5410776 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -709,10 +709,6 @@ xprt_rdma_send_request(struct rpc_task *task)
 	return 0;
 
 failed_marshal:
-	dprintk("RPC:       %s: rpcrdma_marshal_req failed, status %i\n",
-		__func__, rc);
-	if (rc == -EIO)
-		r_xprt->rx_stats.failed_marshal_count++;
 	if (rc != -ENOTCONN)
 		return rc;
 drop_connection:
-- 
cgit v1.2.3


From 0a90487bf7182c74830616b91bd33f68f8c6e18b Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Feb 2017 17:00:35 -0500
Subject: xprtrdma: Handle stale connection rejection

A server rejects a connection attempt with STALE_CONNECTION when a
client attempts to connect to a working remote service, but uses a
QPN and GUID that corresponds to an old connection that was
abandoned. This might occur after a client crashes and restarts.

Fix rpcrdma_conn_upcall() to distinguish between a normal rejection
and rejection of stale connection parameters.

As an additional clean-up, remove the code that retries the
connection attempt with different ORD/IRD values. Code audit of
other ULP initiators shows no similar special case handling of
initiator_depth or responder_resources.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/verbs.c | 66 +++++++++++++++------------------------------
 1 file changed, 21 insertions(+), 45 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 61d16c39e92c..d1ee33fa8055 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -54,6 +54,7 @@
 #include <linux/sunrpc/svc_rdma.h>
 #include <asm/bitops.h>
 #include <linux/module.h> /* try_module_get()/module_put() */
+#include <rdma/ib_cm.h>
 
 #include "xprt_rdma.h"
 
@@ -279,7 +280,14 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event)
 		connstate = -ENETDOWN;
 		goto connected;
 	case RDMA_CM_EVENT_REJECTED:
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+		pr_info("rpcrdma: connection to %pIS:%u on %s rejected: %s\n",
+			sap, rpc_get_port(sap), ia->ri_device->name,
+			rdma_reject_msg(id, event->status));
+#endif
 		connstate = -ECONNREFUSED;
+		if (event->status == IB_CM_REJ_STALE_CONN)
+			connstate = -EAGAIN;
 		goto connected;
 	case RDMA_CM_EVENT_DISCONNECTED:
 		connstate = -ECONNABORTED;
@@ -643,20 +651,21 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 int
 rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 {
+	struct rpcrdma_xprt *r_xprt = container_of(ia, struct rpcrdma_xprt,
+						   rx_ia);
 	struct rdma_cm_id *id, *old;
+	struct sockaddr *sap;
+	unsigned int extras;
 	int rc = 0;
-	int retry_count = 0;
 
 	if (ep->rep_connected != 0) {
-		struct rpcrdma_xprt *xprt;
 retry:
 		dprintk("RPC:       %s: reconnecting...\n", __func__);
 
 		rpcrdma_ep_disconnect(ep, ia);
 
-		xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
-		id = rpcrdma_create_id(xprt, ia,
-				(struct sockaddr *)&xprt->rx_data.addr);
+		sap = (struct sockaddr *)&r_xprt->rx_data.addr;
+		id = rpcrdma_create_id(r_xprt, ia, sap);
 		if (IS_ERR(id)) {
 			rc = -EHOSTUNREACH;
 			goto out;
@@ -711,51 +720,18 @@ retry:
 	}
 
 	wait_event_interruptible(ep->rep_connect_wait, ep->rep_connected != 0);
-
-	/*
-	 * Check state. A non-peer reject indicates no listener
-	 * (ECONNREFUSED), which may be a transient state. All
-	 * others indicate a transport condition which has already
-	 * undergone a best-effort.
-	 */
-	if (ep->rep_connected == -ECONNREFUSED &&
-	    ++retry_count <= RDMA_CONNECT_RETRY_MAX) {
-		dprintk("RPC:       %s: non-peer_reject, retry\n", __func__);
-		goto retry;
-	}
 	if (ep->rep_connected <= 0) {
-		/* Sometimes, the only way to reliably connect to remote
-		 * CMs is to use same nonzero values for ORD and IRD. */
-		if (retry_count++ <= RDMA_CONNECT_RETRY_MAX + 1 &&
-		    (ep->rep_remote_cma.responder_resources == 0 ||
-		     ep->rep_remote_cma.initiator_depth !=
-				ep->rep_remote_cma.responder_resources)) {
-			if (ep->rep_remote_cma.responder_resources == 0)
-				ep->rep_remote_cma.responder_resources = 1;
-			ep->rep_remote_cma.initiator_depth =
-				ep->rep_remote_cma.responder_resources;
+		if (ep->rep_connected == -EAGAIN)
 			goto retry;
-		}
 		rc = ep->rep_connected;
-	} else {
-		struct rpcrdma_xprt *r_xprt;
-		unsigned int extras;
-
-		dprintk("RPC:       %s: connected\n", __func__);
-
-		r_xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
-		extras = r_xprt->rx_buf.rb_bc_srv_max_requests;
-
-		if (extras) {
-			rc = rpcrdma_ep_post_extra_recv(r_xprt, extras);
-			if (rc) {
-				pr_warn("%s: rpcrdma_ep_post_extra_recv: %i\n",
-					__func__, rc);
-				rc = 0;
-			}
-		}
+		goto out;
 	}
 
+	dprintk("RPC:       %s: connected\n", __func__);
+	extras = r_xprt->rx_buf.rb_bc_srv_max_requests;
+	if (extras)
+		rpcrdma_ep_post_extra_recv(r_xprt, extras);
+
 out:
 	if (rc)
 		ep->rep_connected = rc;
-- 
cgit v1.2.3


From 9a5c63e9c4056de8a73555131e6f698ddb0b9e0d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Feb 2017 17:00:43 -0500
Subject: xprtrdma: Refactor management of mw_list field

Clean up some duplicate code.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/fmr_ops.c   |  5 +----
 net/sunrpc/xprtrdma/frwr_ops.c  | 11 ++++-------
 net/sunrpc/xprtrdma/rpc_rdma.c  |  6 +++---
 net/sunrpc/xprtrdma/verbs.c     | 15 +++++----------
 net/sunrpc/xprtrdma/xprt_rdma.h | 16 ++++++++++++++++
 5 files changed, 29 insertions(+), 24 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index 1ebb09e1ac4f..59e64025ed96 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -310,10 +310,7 @@ fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	struct rpcrdma_mw *mw;
 
 	while (!list_empty(&req->rl_registered)) {
-		mw = list_first_entry(&req->rl_registered,
-				      struct rpcrdma_mw, mw_list);
-		list_del_init(&mw->mw_list);
-
+		mw = rpcrdma_pop_mw(&req->rl_registered);
 		if (sync)
 			fmr_op_recover_mr(mw);
 		else
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 47bed5333c7f..f81dd93176c0 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -466,8 +466,8 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	struct ib_send_wr *first, **prev, *last, *bad_wr;
 	struct rpcrdma_rep *rep = req->rl_reply;
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct rpcrdma_mw *mw, *tmp;
 	struct rpcrdma_frmr *f;
+	struct rpcrdma_mw *mw;
 	int count, rc;
 
 	dprintk("RPC:       %s: req %p\n", __func__, req);
@@ -534,10 +534,10 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * them to the free MW list.
 	 */
 unmap:
-	list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) {
+	while (!list_empty(&req->rl_registered)) {
+		mw = rpcrdma_pop_mw(&req->rl_registered);
 		dprintk("RPC:       %s: DMA unmapping frmr %p\n",
 			__func__, &mw->frmr);
-		list_del_init(&mw->mw_list);
 		ib_dma_unmap_sg(ia->ri_device,
 				mw->mw_sg, mw->mw_nents, mw->mw_dir);
 		rpcrdma_put_mw(r_xprt, mw);
@@ -571,10 +571,7 @@ frwr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	struct rpcrdma_mw *mw;
 
 	while (!list_empty(&req->rl_registered)) {
-		mw = list_first_entry(&req->rl_registered,
-				      struct rpcrdma_mw, mw_list);
-		list_del_init(&mw->mw_list);
-
+		mw = rpcrdma_pop_mw(&req->rl_registered);
 		if (sync)
 			frwr_op_recover_mr(mw);
 		else
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 72b3ca0253a0..a044be2d6ad7 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -322,7 +322,7 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 						 false, &mw);
 		if (n < 0)
 			return ERR_PTR(n);
-		list_add(&mw->mw_list, &req->rl_registered);
+		rpcrdma_push_mw(mw, &req->rl_registered);
 
 		*iptr++ = xdr_one;	/* item present */
 
@@ -390,7 +390,7 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 						 true, &mw);
 		if (n < 0)
 			return ERR_PTR(n);
-		list_add(&mw->mw_list, &req->rl_registered);
+		rpcrdma_push_mw(mw, &req->rl_registered);
 
 		iptr = xdr_encode_rdma_segment(iptr, mw);
 
@@ -455,7 +455,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 						 true, &mw);
 		if (n < 0)
 			return ERR_PTR(n);
-		list_add(&mw->mw_list, &req->rl_registered);
+		rpcrdma_push_mw(mw, &req->rl_registered);
 
 		iptr = xdr_encode_rdma_segment(iptr, mw);
 
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index d1ee33fa8055..81cd31acf690 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -776,9 +776,7 @@ rpcrdma_mr_recovery_worker(struct work_struct *work)
 
 	spin_lock(&buf->rb_recovery_lock);
 	while (!list_empty(&buf->rb_stale_mrs)) {
-		mw = list_first_entry(&buf->rb_stale_mrs,
-				      struct rpcrdma_mw, mw_list);
-		list_del_init(&mw->mw_list);
+		mw = rpcrdma_pop_mw(&buf->rb_stale_mrs);
 		spin_unlock(&buf->rb_recovery_lock);
 
 		dprintk("RPC:       %s: recovering MR %p\n", __func__, mw);
@@ -796,7 +794,7 @@ rpcrdma_defer_mr_recovery(struct rpcrdma_mw *mw)
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 
 	spin_lock(&buf->rb_recovery_lock);
-	list_add(&mw->mw_list, &buf->rb_stale_mrs);
+	rpcrdma_push_mw(mw, &buf->rb_stale_mrs);
 	spin_unlock(&buf->rb_recovery_lock);
 
 	schedule_delayed_work(&buf->rb_recovery_worker, 0);
@@ -1072,11 +1070,8 @@ rpcrdma_get_mw(struct rpcrdma_xprt *r_xprt)
 	struct rpcrdma_mw *mw = NULL;
 
 	spin_lock(&buf->rb_mwlock);
-	if (!list_empty(&buf->rb_mws)) {
-		mw = list_first_entry(&buf->rb_mws,
-				      struct rpcrdma_mw, mw_list);
-		list_del_init(&mw->mw_list);
-	}
+	if (!list_empty(&buf->rb_mws))
+		mw = rpcrdma_pop_mw(&buf->rb_mws);
 	spin_unlock(&buf->rb_mwlock);
 
 	if (!mw)
@@ -1099,7 +1094,7 @@ rpcrdma_put_mw(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mw *mw)
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 
 	spin_lock(&buf->rb_mwlock);
-	list_add_tail(&mw->mw_list, &buf->rb_mws);
+	rpcrdma_push_mw(mw, &buf->rb_mws);
 	spin_unlock(&buf->rb_mwlock);
 }
 
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 852dd0a750a5..171a35116de9 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -354,6 +354,22 @@ rpcr_to_rdmar(struct rpc_rqst *rqst)
 	return rqst->rq_xprtdata;
 }
 
+static inline void
+rpcrdma_push_mw(struct rpcrdma_mw *mw, struct list_head *list)
+{
+	list_add_tail(&mw->mw_list, list);
+}
+
+static inline struct rpcrdma_mw *
+rpcrdma_pop_mw(struct list_head *list)
+{
+	struct rpcrdma_mw *mw;
+
+	mw = list_first_entry(list, struct rpcrdma_mw, mw_list);
+	list_del(&mw->mw_list);
+	return mw;
+}
+
 /*
  * struct rpcrdma_buffer -- holds list/queue of pre-registered memory for
  * inline requests/replies, and client/server credits.
-- 
cgit v1.2.3


From b977b644ccf821ab1269582f7efe1d0d85faa1f6 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Feb 2017 17:00:51 -0500
Subject: sunrpc: Allow xprt->ops->timer method to sleep

The transport lock is needed to protect the xprt_adjust_cwnd() call
in xs_udp_timer, but it is not necessary for accessing the
rq_reply_bytes_recvd or tk_status fields. It is correct to sublimate
the lock into UDP's xs_udp_timer method, where it is required.

The ->timer method has to take the transport lock if needed, but it
can now sleep safely, or even call back into the RPC scheduler.

This is more a clean-up than a fix, but the "issue" was introduced
by my transport switch patches back in 2005.

Fixes: 46c0ee8bc4ad ("RPC: separate xprt_timer implementations")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprt.c     | 2 --
 net/sunrpc/xprtsock.c | 2 ++
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 9a6be030ca7d..b530a2852ba8 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -897,13 +897,11 @@ static void xprt_timer(struct rpc_task *task)
 		return;
 	dprintk("RPC: %5u xprt_timer\n", task->tk_pid);
 
-	spin_lock_bh(&xprt->transport_lock);
 	if (!req->rq_reply_bytes_recvd) {
 		if (xprt->ops->timer)
 			xprt->ops->timer(xprt, task);
 	} else
 		task->tk_status = 0;
-	spin_unlock_bh(&xprt->transport_lock);
 }
 
 /**
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 810e9b59be16..18b4e7ff8879 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1739,7 +1739,9 @@ static void xs_udp_set_buffer_size(struct rpc_xprt *xprt, size_t sndsize, size_t
  */
 static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task)
 {
+	spin_lock_bh(&xprt->transport_lock);
 	xprt_adjust_cwnd(xprt, task, -ETIMEDOUT);
+	spin_unlock_bh(&xprt->transport_lock);
 }
 
 static unsigned short xs_get_random_port(void)
-- 
cgit v1.2.3


From 9761a2469dc287c6d75ca148f4fc483becbcad88 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sun, 19 Feb 2017 00:34:59 +0300
Subject: sunrpc: silence uninitialized variable warning

kstrtouint() can return a couple different error codes so the check for
"ret == -EINVAL" is wrong and static analysis tools correctly complain
that we can use "num" without initializing it.  It's not super harmful
because we check the bounds.  But it's also easy enough to fix.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtsock.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 18b4e7ff8879..5cbabf2c75b2 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -3261,7 +3261,9 @@ static int param_set_uint_minmax(const char *val,
 	if (!val)
 		return -EINVAL;
 	ret = kstrtouint(val, 0, &num);
-	if (ret == -EINVAL || num < min || num > max)
+	if (ret)
+		return ret;
+	if (num < min || num > max)
 		return -EINVAL;
 	*((unsigned int *)kp->arg) = num;
 	return 0;
-- 
cgit v1.2.3


From 5c741d4f2215371ae17e3dbdf3d46da850662e13 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Sun, 19 Feb 2017 16:08:31 -0500
Subject: SUNRPC: Add a helper function xdr_stream_decode_string_dup()

Create a helper function that decodes a xdr string object, allocates a memory
buffer and then store it as a NUL terminated string.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xdr.h |  2 ++
 net/sunrpc/xdr.c           | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

(limited to 'net/sunrpc')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index dc7e51a769ac..054c8cde18f3 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -242,6 +242,8 @@ extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
 
+ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str,
+		size_t maxlen, gfp_t gfp_flags);
 /**
  * xdr_align_size - Calculate padded size of an object
  * @n: Size of an object being XDR encoded (in bytes)
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 7f1071e103ca..1f7082144e01 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -1518,3 +1518,37 @@ out:
 }
 EXPORT_SYMBOL_GPL(xdr_process_buf);
 
+/**
+ * xdr_stream_decode_string_dup - Decode and duplicate variable length string
+ * @xdr: pointer to xdr_stream
+ * @str: location to store pointer to string
+ * @maxlen: maximum acceptable string length
+ * @gfp_flags: GFP mask to use
+ *
+ * Return values:
+ *   On success, returns length of NUL-terminated string stored in *@ptr
+ *   %-EBADMSG on XDR buffer overflow
+ *   %-EMSGSIZE if the size of the string would exceed @maxlen
+ *   %-ENOMEM on memory allocation failure
+ */
+ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str,
+		size_t maxlen, gfp_t gfp_flags)
+{
+	void *p;
+	ssize_t ret;
+
+	ret = xdr_stream_decode_opaque_inline(xdr, &p, maxlen);
+	if (ret > 0) {
+		char *s = kmalloc(ret + 1, gfp_flags);
+		if (s != NULL) {
+			memcpy(s, p, ret);
+			s[ret] = '\0';
+			*str = s;
+			return strlen(s);
+		}
+		ret = -ENOMEM;
+	}
+	*str = NULL;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xdr_stream_decode_string_dup);
-- 
cgit v1.2.3