From 32927393dc1ccd60fb2bdc05b9e8e88753761469 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 24 Apr 2020 08:43:38 +0200
Subject: sysctl: pass kernel pointers to ->proc_handler

Instead of having all the sysctl handlers deal with user pointers, which
is rather hairy in terms of the BPF interaction, copy the input to and
from  userspace in common code.  This also means that the strings are
always NUL-terminated by the common code, making the API a little bit
safer.

As most handler just pass through the data to one of the common handlers
a lot of the changes are mechnical.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c           |  2 +-
 fs/drop_caches.c      |  2 +-
 fs/file_table.c       |  4 ++--
 fs/fscache/main.c     |  3 +--
 fs/inode.c            |  2 +-
 fs/proc/proc_sysctl.c | 47 +++++++++++++++++++++++++++++------------------
 fs/quota/dquot.c      |  2 +-
 fs/xfs/xfs_sysctl.c   |  4 ++--
 8 files changed, 38 insertions(+), 28 deletions(-)

(limited to 'fs')

diff --git a/fs/dcache.c b/fs/dcache.c
index b280e07e162b..8dd4d8d7bd0b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -165,7 +165,7 @@ static long get_nr_dentry_negative(void)
 	return sum < 0 ? 0 : sum;
 }
 
-int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer,
+int proc_nr_dentry(struct ctl_table *table, int write, void *buffer,
 		   size_t *lenp, loff_t *ppos)
 {
 	dentry_stat.nr_dentry = get_nr_dentry();
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index dc1a1d5d825b..f00fcc4a4f72 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -47,7 +47,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 }
 
 int drop_caches_sysctl_handler(struct ctl_table *table, int write,
-	void __user *buffer, size_t *length, loff_t *ppos)
+		void *buffer, size_t *length, loff_t *ppos)
 {
 	int ret;
 
diff --git a/fs/file_table.c b/fs/file_table.c
index 30d55c9a1744..3b612535391f 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -80,14 +80,14 @@ EXPORT_SYMBOL_GPL(get_max_files);
  */
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
 int proc_nr_files(struct ctl_table *table, int write,
-                     void __user *buffer, size_t *lenp, loff_t *ppos)
+                     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	files_stat.nr_files = get_nr_files();
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 #else
 int proc_nr_files(struct ctl_table *table, int write,
-                     void __user *buffer, size_t *lenp, loff_t *ppos)
+                     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
diff --git a/fs/fscache/main.c b/fs/fscache/main.c
index 59c2494efda3..c1e6cc9091aa 100644
--- a/fs/fscache/main.c
+++ b/fs/fscache/main.c
@@ -51,8 +51,7 @@ static unsigned fscache_op_max_active = 2;
 static struct ctl_table_header *fscache_sysctl_header;
 
 static int fscache_max_active_sysctl(struct ctl_table *table, int write,
-				     void __user *buffer,
-				     size_t *lenp, loff_t *ppos)
+				     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct workqueue_struct **wqp = table->extra1;
 	unsigned int *datap = table->data;
diff --git a/fs/inode.c b/fs/inode.c
index 93d9252a00ab..cc6e701b7e5d 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -108,7 +108,7 @@ long get_nr_dirty_inodes(void)
  */
 #ifdef CONFIG_SYSCTL
 int proc_nr_inodes(struct ctl_table *table, int write,
-		   void __user *buffer, size_t *lenp, loff_t *ppos)
+		   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	inodes_stat.nr_inodes = get_nr_inodes();
 	inodes_stat.nr_unused = get_nr_inodes_unused();
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index b6f5d459b087..df2143e05c57 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -539,13 +539,13 @@ out:
 	return err;
 }
 
-static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
+static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
 		size_t count, loff_t *ppos, int write)
 {
 	struct inode *inode = file_inode(filp);
 	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
-	void *new_buf = NULL;
+	void *kbuf;
 	ssize_t error;
 
 	if (IS_ERR(head))
@@ -564,27 +564,38 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
 	if (!table->proc_handler)
 		goto out;
 
-	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count,
-					   ppos, &new_buf);
+	if (write) {
+		kbuf = memdup_user_nul(ubuf, count);
+		if (IS_ERR(kbuf)) {
+			error = PTR_ERR(kbuf);
+			goto out;
+		}
+	} else {
+		error = -ENOMEM;
+		kbuf = kzalloc(count, GFP_KERNEL);
+		if (!kbuf)
+			goto out;
+	}
+
+	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count,
+					   ppos);
 	if (error)
-		goto out;
+		goto out_free_buf;
 
 	/* careful: calling conventions are nasty here */
-	if (new_buf) {
-		mm_segment_t old_fs;
-
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		error = table->proc_handler(table, write, (void __user *)new_buf,
-					    &count, ppos);
-		set_fs(old_fs);
-		kfree(new_buf);
-	} else {
-		error = table->proc_handler(table, write, buf, &count, ppos);
+	error = table->proc_handler(table, write, kbuf, &count, ppos);
+	if (error)
+		goto out_free_buf;
+
+	if (!write) {
+		error = -EFAULT;
+		if (copy_to_user(ubuf, kbuf, count))
+			goto out_free_buf;
 	}
 
-	if (!error)
-		error = count;
+	error = count;
+out_free_buf:
+	kfree(kbuf);
 out:
 	sysctl_head_finish(head);
 
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index b6a4f692d345..7b4bac91146b 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2841,7 +2841,7 @@ const struct quotactl_ops dquot_quotactl_sysfile_ops = {
 EXPORT_SYMBOL(dquot_quotactl_sysfile_ops);
 
 static int do_proc_dqstats(struct ctl_table *table, int write,
-		     void __user *buffer, size_t *lenp, loff_t *ppos)
+		     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	unsigned int type = (unsigned long *)table->data - dqstats.stat;
 	s64 value = percpu_counter_sum(&dqstats.counter[type]);
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index 31b3bdbd2eba..021ef96d0542 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -13,7 +13,7 @@ STATIC int
 xfs_stats_clear_proc_handler(
 	struct ctl_table	*ctl,
 	int			write,
-	void			__user *buffer,
+	void			*buffer,
 	size_t			*lenp,
 	loff_t			*ppos)
 {
@@ -33,7 +33,7 @@ STATIC int
 xfs_panic_mask_proc_handler(
 	struct ctl_table	*ctl,
 	int			write,
-	void			__user *buffer,
+	void			*buffer,
 	size_t			*lenp,
 	loff_t			*ppos)
 {
-- 
cgit v1.2.3-58-ga151


From 138d0be35b141e09f6b267c6ae4094318d4e4491 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:10 -0700
Subject: net: bpf: Add netlink and ipv6_route bpf_iter targets

This patch added netlink and ipv6_route targets, using
the same seq_ops (except show() and minor changes for stop())
for /proc/net/{netlink,ipv6_route}.

The net namespace for these targets are the current net
namespace at file open stage, similar to
/proc/net/{netlink,ipv6_route} reference counting
the net namespace at seq_file open stage.

Since module is not supported for now, ipv6_route is
supported only if the IPV6 is built-in, i.e., not compiled
as a module. The restriction can be lifted once module
is properly supported for bpf_iter.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175910.2476329-1-yhs@fb.com
---
 fs/proc/proc_net.c       | 19 +++++++++++
 include/linux/proc_fs.h  |  3 ++
 net/ipv6/ip6_fib.c       | 65 ++++++++++++++++++++++++++++++++++--
 net/ipv6/route.c         | 37 ++++++++++++++++++++
 net/netlink/af_netlink.c | 87 ++++++++++++++++++++++++++++++++++++++++++++++--
 5 files changed, 207 insertions(+), 4 deletions(-)

(limited to 'fs')

diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 4888c5224442..dba63b2429f0 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -98,6 +98,25 @@ static const struct proc_ops proc_net_seq_ops = {
 	.proc_release	= seq_release_net,
 };
 
+int bpf_iter_init_seq_net(void *priv_data)
+{
+#ifdef CONFIG_NET_NS
+	struct seq_net_private *p = priv_data;
+
+	p->net = get_net(current->nsproxy->net_ns);
+#endif
+	return 0;
+}
+
+void bpf_iter_fini_seq_net(void *priv_data)
+{
+#ifdef CONFIG_NET_NS
+	struct seq_net_private *p = priv_data;
+
+	put_net(p->net);
+#endif
+}
+
 struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
 		struct proc_dir_entry *parent, const struct seq_operations *ops,
 		unsigned int state_size, void *data)
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 45c05fd9c99d..03953c59807d 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -105,6 +105,9 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
 						    void *data);
 extern struct pid *tgid_pidfd_to_pid(const struct file *file);
 
+extern int bpf_iter_init_seq_net(void *priv_data);
+extern void bpf_iter_fini_seq_net(void *priv_data);
+
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 /*
  * The architecture which selects CONFIG_PROC_PID_ARCH_STATUS must
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 46ed56719476..a1fcc0ca21af 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2467,7 +2467,7 @@ void fib6_gc_cleanup(void)
 }
 
 #ifdef CONFIG_PROC_FS
-static int ipv6_route_seq_show(struct seq_file *seq, void *v)
+static int ipv6_route_native_seq_show(struct seq_file *seq, void *v)
 {
 	struct fib6_info *rt = v;
 	struct ipv6_route_iter *iter = seq->private;
@@ -2625,7 +2625,7 @@ static bool ipv6_route_iter_active(struct ipv6_route_iter *iter)
 	return w->node && !(w->state == FWS_U && w->node == w->root);
 }
 
-static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
+static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v)
 	__releases(RCU_BH)
 {
 	struct net *net = seq_file_net(seq);
@@ -2637,6 +2637,67 @@ static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
 	rcu_read_unlock_bh();
 }
 
+#if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL)
+struct bpf_iter__ipv6_route {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct fib6_info *, rt);
+};
+
+static int ipv6_route_prog_seq_show(struct bpf_prog *prog,
+				    struct bpf_iter_meta *meta,
+				    void *v)
+{
+	struct bpf_iter__ipv6_route ctx;
+
+	ctx.meta = meta;
+	ctx.rt = v;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int ipv6_route_seq_show(struct seq_file *seq, void *v)
+{
+	struct ipv6_route_iter *iter = seq->private;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int ret;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, false);
+	if (!prog)
+		return ipv6_route_native_seq_show(seq, v);
+
+	ret = ipv6_route_prog_seq_show(prog, &meta, v);
+	iter->w.leaf = NULL;
+
+	return ret;
+}
+
+static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	if (!v) {
+		meta.seq = seq;
+		prog = bpf_iter_get_info(&meta, true);
+		if (prog)
+			(void)ipv6_route_prog_seq_show(prog, &meta, v);
+	}
+
+	ipv6_route_native_seq_stop(seq, v);
+}
+#else
+static int ipv6_route_seq_show(struct seq_file *seq, void *v)
+{
+	return ipv6_route_native_seq_show(seq, v);
+}
+
+static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
+{
+	ipv6_route_native_seq_stop(seq, v);
+}
+#endif
+
 const struct seq_operations ipv6_route_seq_ops = {
 	.start	= ipv6_route_seq_start,
 	.next	= ipv6_route_seq_next,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3912aac7854d..25f6d3e619d0 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -6393,6 +6393,30 @@ void __init ip6_route_init_special_entries(void)
   #endif
 }
 
+#if IS_BUILTIN(CONFIG_IPV6)
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *rt)
+
+static int __init bpf_iter_register(void)
+{
+	struct bpf_iter_reg reg_info = {
+		.target			= "ipv6_route",
+		.seq_ops		= &ipv6_route_seq_ops,
+		.init_seq_private	= bpf_iter_init_seq_net,
+		.fini_seq_private	= bpf_iter_fini_seq_net,
+		.seq_priv_size		= sizeof(struct ipv6_route_iter),
+	};
+
+	return bpf_iter_reg_target(&reg_info);
+}
+
+static void bpf_iter_unregister(void)
+{
+	bpf_iter_unreg_target("ipv6_route");
+}
+#endif
+#endif
+
 int __init ip6_route_init(void)
 {
 	int ret;
@@ -6455,6 +6479,14 @@ int __init ip6_route_init(void)
 	if (ret)
 		goto out_register_late_subsys;
 
+#if IS_BUILTIN(CONFIG_IPV6)
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+	ret = bpf_iter_register();
+	if (ret)
+		goto out_register_late_subsys;
+#endif
+#endif
+
 	for_each_possible_cpu(cpu) {
 		struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
 
@@ -6487,6 +6519,11 @@ out_kmem_cache:
 
 void ip6_route_cleanup(void)
 {
+#if IS_BUILTIN(CONFIG_IPV6)
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+	bpf_iter_unregister();
+#endif
+#endif
 	unregister_netdevice_notifier(&ip6_route_dev_notifier);
 	unregister_pernet_subsys(&ip6_route_net_late_ops);
 	fib6_rules_cleanup();
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 5ded01ca8b20..33cda9baa979 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2596,7 +2596,7 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	return __netlink_seq_next(seq);
 }
 
-static void netlink_seq_stop(struct seq_file *seq, void *v)
+static void netlink_native_seq_stop(struct seq_file *seq, void *v)
 {
 	struct nl_seq_iter *iter = seq->private;
 
@@ -2607,7 +2607,7 @@ static void netlink_seq_stop(struct seq_file *seq, void *v)
 }
 
 
-static int netlink_seq_show(struct seq_file *seq, void *v)
+static int netlink_native_seq_show(struct seq_file *seq, void *v)
 {
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
@@ -2634,6 +2634,68 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+struct bpf_iter__netlink {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct netlink_sock *, sk);
+};
+
+DEFINE_BPF_ITER_FUNC(netlink, struct bpf_iter_meta *meta, struct netlink_sock *sk)
+
+static int netlink_prog_seq_show(struct bpf_prog *prog,
+				  struct bpf_iter_meta *meta,
+				  void *v)
+{
+	struct bpf_iter__netlink ctx;
+
+	meta->seq_num--;  /* skip SEQ_START_TOKEN */
+	ctx.meta = meta;
+	ctx.sk = nlk_sk((struct sock *)v);
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int netlink_seq_show(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, false);
+	if (!prog)
+		return netlink_native_seq_show(seq, v);
+
+	if (v != SEQ_START_TOKEN)
+		return netlink_prog_seq_show(prog, &meta, v);
+
+	return 0;
+}
+
+static void netlink_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	if (!v) {
+		meta.seq = seq;
+		prog = bpf_iter_get_info(&meta, true);
+		if (prog)
+			(void)netlink_prog_seq_show(prog, &meta, v);
+	}
+
+	netlink_native_seq_stop(seq, v);
+}
+#else
+static int netlink_seq_show(struct seq_file *seq, void *v)
+{
+	return netlink_native_seq_show(seq, v);
+}
+
+static void netlink_seq_stop(struct seq_file *seq, void *v)
+{
+	netlink_native_seq_stop(seq, v);
+}
+#endif
+
 static const struct seq_operations netlink_seq_ops = {
 	.start  = netlink_seq_start,
 	.next   = netlink_seq_next,
@@ -2740,6 +2802,21 @@ static const struct rhashtable_params netlink_rhashtable_params = {
 	.automatic_shrinking = true,
 };
 
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+static int __init bpf_iter_register(void)
+{
+	struct bpf_iter_reg reg_info = {
+		.target			= "netlink",
+		.seq_ops		= &netlink_seq_ops,
+		.init_seq_private	= bpf_iter_init_seq_net,
+		.fini_seq_private	= bpf_iter_fini_seq_net,
+		.seq_priv_size		= sizeof(struct nl_seq_iter),
+	};
+
+	return bpf_iter_reg_target(&reg_info);
+}
+#endif
+
 static int __init netlink_proto_init(void)
 {
 	int i;
@@ -2748,6 +2825,12 @@ static int __init netlink_proto_init(void)
 	if (err != 0)
 		goto out;
 
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+	err = bpf_iter_register();
+	if (err)
+		goto out;
+#endif
+
 	BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb));
 
 	nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL);
-- 
cgit v1.2.3-58-ga151


From 0774dc7643db525f0bb9d0aa212cbfad3a412fc6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 27 May 2020 20:22:28 +0200
Subject: dlm: use the tcp version of accept_from_sock for sctp as well

The only difference between a few missing fixes applied to the SCTP
one is that TCP uses ->getpeername to get the remote address, while
SCTP uses kernel_getsockopt(.. SCTP_PRIMARY_ADDR).  But given that
getpeername is defined to return the primary address for sctp, there
doesn't seem to be any reason for the different way of quering the
peername, or all the code duplication.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/dlm/lowcomms.c | 123 ++----------------------------------------------------
 1 file changed, 3 insertions(+), 120 deletions(-)

(limited to 'fs')

diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index cdfaf4f0e11a..f13dad0fd9ef 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -724,7 +724,7 @@ out_close:
 }
 
 /* Listening socket is busy, accept a connection */
-static int tcp_accept_from_sock(struct connection *con)
+static int accept_from_sock(struct connection *con)
 {
 	int result;
 	struct sockaddr_storage peeraddr;
@@ -852,123 +852,6 @@ accept_err:
 	return result;
 }
 
-static int sctp_accept_from_sock(struct connection *con)
-{
-	/* Check that the new node is in the lockspace */
-	struct sctp_prim prim;
-	int nodeid;
-	int prim_len, ret;
-	int addr_len;
-	struct connection *newcon;
-	struct connection *addcon;
-	struct socket *newsock;
-
-	mutex_lock(&connections_lock);
-	if (!dlm_allow_conn) {
-		mutex_unlock(&connections_lock);
-		return -1;
-	}
-	mutex_unlock(&connections_lock);
-
-	mutex_lock_nested(&con->sock_mutex, 0);
-
-	ret = kernel_accept(con->sock, &newsock, O_NONBLOCK);
-	if (ret < 0)
-		goto accept_err;
-
-	memset(&prim, 0, sizeof(struct sctp_prim));
-	prim_len = sizeof(struct sctp_prim);
-
-	ret = kernel_getsockopt(newsock, IPPROTO_SCTP, SCTP_PRIMARY_ADDR,
-				(char *)&prim, &prim_len);
-	if (ret < 0) {
-		log_print("getsockopt/sctp_primary_addr failed: %d", ret);
-		goto accept_err;
-	}
-
-	make_sockaddr(&prim.ssp_addr, 0, &addr_len);
-	ret = addr_to_nodeid(&prim.ssp_addr, &nodeid);
-	if (ret) {
-		unsigned char *b = (unsigned char *)&prim.ssp_addr;
-
-		log_print("reject connect from unknown addr");
-		print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE,
-				     b, sizeof(struct sockaddr_storage));
-		goto accept_err;
-	}
-
-	newcon = nodeid2con(nodeid, GFP_NOFS);
-	if (!newcon) {
-		ret = -ENOMEM;
-		goto accept_err;
-	}
-
-	mutex_lock_nested(&newcon->sock_mutex, 1);
-
-	if (newcon->sock) {
-		struct connection *othercon = newcon->othercon;
-
-		if (!othercon) {
-			othercon = kmem_cache_zalloc(con_cache, GFP_NOFS);
-			if (!othercon) {
-				log_print("failed to allocate incoming socket");
-				mutex_unlock(&newcon->sock_mutex);
-				ret = -ENOMEM;
-				goto accept_err;
-			}
-			othercon->nodeid = nodeid;
-			othercon->rx_action = receive_from_sock;
-			mutex_init(&othercon->sock_mutex);
-			INIT_LIST_HEAD(&othercon->writequeue);
-			spin_lock_init(&othercon->writequeue_lock);
-			INIT_WORK(&othercon->swork, process_send_sockets);
-			INIT_WORK(&othercon->rwork, process_recv_sockets);
-			set_bit(CF_IS_OTHERCON, &othercon->flags);
-		}
-		mutex_lock_nested(&othercon->sock_mutex, 2);
-		if (!othercon->sock) {
-			newcon->othercon = othercon;
-			add_sock(newsock, othercon);
-			addcon = othercon;
-			mutex_unlock(&othercon->sock_mutex);
-		} else {
-			printk("Extra connection from node %d attempted\n", nodeid);
-			ret = -EAGAIN;
-			mutex_unlock(&othercon->sock_mutex);
-			mutex_unlock(&newcon->sock_mutex);
-			goto accept_err;
-		}
-	} else {
-		newcon->rx_action = receive_from_sock;
-		add_sock(newsock, newcon);
-		addcon = newcon;
-	}
-
-	log_print("connected to %d", nodeid);
-
-	mutex_unlock(&newcon->sock_mutex);
-
-	/*
-	 * Add it to the active queue in case we got data
-	 * between processing the accept adding the socket
-	 * to the read_sockets list
-	 */
-	if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags))
-		queue_work(recv_workqueue, &addcon->rwork);
-	mutex_unlock(&con->sock_mutex);
-
-	return 0;
-
-accept_err:
-	mutex_unlock(&con->sock_mutex);
-	if (newsock)
-		sock_release(newsock);
-	if (ret != -EAGAIN)
-		log_print("error accepting connection from node: %d", ret);
-
-	return ret;
-}
-
 static void free_entry(struct writequeue_entry *e)
 {
 	__free_page(e->page);
@@ -1253,7 +1136,7 @@ static struct socket *tcp_create_listen_sock(struct connection *con,
 	write_lock_bh(&sock->sk->sk_callback_lock);
 	sock->sk->sk_user_data = con;
 	save_listen_callbacks(sock);
-	con->rx_action = tcp_accept_from_sock;
+	con->rx_action = accept_from_sock;
 	con->connect_action = tcp_connect_to_sock;
 	write_unlock_bh(&sock->sk->sk_callback_lock);
 
@@ -1340,7 +1223,7 @@ static int sctp_listen_for_all(void)
 	save_listen_callbacks(sock);
 	con->sock = sock;
 	con->sock->sk->sk_data_ready = lowcomms_data_ready;
-	con->rx_action = sctp_accept_from_sock;
+	con->rx_action = accept_from_sock;
 	con->connect_action = sctp_connect_to_sock;
 
 	write_unlock_bh(&sock->sk->sk_callback_lock);
-- 
cgit v1.2.3-58-ga151


From b58f0e8f38c0a44afa59601a115bd231f23471e1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:09 +0200
Subject: net: add sock_set_reuseaddr

Add a helper to directly set the SO_REUSEADDR sockopt from kernel space
without going through a fake uaccess.

For this the iscsi target now has to formally depend on inet to avoid
a mostly theoretical compile failure.  For actual operation it already
did depend on having ipv4 or ipv6 support.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/sw/siw/siw_cm.c        | 18 +++++-------------
 drivers/nvme/target/tcp.c                 |  8 +-------
 drivers/target/iscsi/Kconfig              |  2 +-
 drivers/target/iscsi/iscsi_target_login.c |  9 +--------
 fs/dlm/lowcomms.c                         |  6 +-----
 include/net/sock.h                        |  2 ++
 net/core/sock.c                           |  8 ++++++++
 7 files changed, 19 insertions(+), 34 deletions(-)

(limited to 'fs')

diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
index 559e5fd3bad8..d1860f3e8740 100644
--- a/drivers/infiniband/sw/siw/siw_cm.c
+++ b/drivers/infiniband/sw/siw/siw_cm.c
@@ -1312,17 +1312,14 @@ static void siw_cm_llp_state_change(struct sock *sk)
 static int kernel_bindconnect(struct socket *s, struct sockaddr *laddr,
 			      struct sockaddr *raddr)
 {
-	int rv, flags = 0, s_val = 1;
+	int rv, flags = 0;
 	size_t size = laddr->sa_family == AF_INET ?
 		sizeof(struct sockaddr_in) : sizeof(struct sockaddr_in6);
 
 	/*
 	 * Make address available again asap.
 	 */
-	rv = kernel_setsockopt(s, SOL_SOCKET, SO_REUSEADDR, (char *)&s_val,
-			       sizeof(s_val));
-	if (rv < 0)
-		return rv;
+	sock_set_reuseaddr(s->sk);
 
 	rv = s->ops->bind(s, laddr, size);
 	if (rv < 0)
@@ -1781,7 +1778,7 @@ int siw_create_listen(struct iw_cm_id *id, int backlog)
 	struct siw_cep *cep = NULL;
 	struct siw_device *sdev = to_siw_dev(id->device);
 	int addr_family = id->local_addr.ss_family;
-	int rv = 0, s_val;
+	int rv = 0;
 
 	if (addr_family != AF_INET && addr_family != AF_INET6)
 		return -EAFNOSUPPORT;
@@ -1793,13 +1790,8 @@ int siw_create_listen(struct iw_cm_id *id, int backlog)
 	/*
 	 * Allow binding local port when still in TIME_WAIT from last close.
 	 */
-	s_val = 1;
-	rv = kernel_setsockopt(s, SOL_SOCKET, SO_REUSEADDR, (char *)&s_val,
-			       sizeof(s_val));
-	if (rv) {
-		siw_dbg(id->device, "setsockopt error: %d\n", rv);
-		goto error;
-	}
+	sock_set_reuseaddr(s->sk);
+
 	if (addr_family == AF_INET) {
 		struct sockaddr_in *laddr = &to_sockaddr_in(id->local_addr);
 
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index f0da04e960f4..40757a63f455 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1632,6 +1632,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 	port->sock->sk->sk_user_data = port;
 	port->data_ready = port->sock->sk->sk_data_ready;
 	port->sock->sk->sk_data_ready = nvmet_tcp_listen_data_ready;
+	sock_set_reuseaddr(port->sock->sk);
 
 	opt = 1;
 	ret = kernel_setsockopt(port->sock, IPPROTO_TCP,
@@ -1641,13 +1642,6 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 		goto err_sock;
 	}
 
-	ret = kernel_setsockopt(port->sock, SOL_SOCKET, SO_REUSEADDR,
-			(char *)&opt, sizeof(opt));
-	if (ret) {
-		pr_err("failed to set SO_REUSEADDR sock opt %d\n", ret);
-		goto err_sock;
-	}
-
 	if (so_priority > 0) {
 		ret = kernel_setsockopt(port->sock, SOL_SOCKET, SO_PRIORITY,
 				(char *)&so_priority, sizeof(so_priority));
diff --git a/drivers/target/iscsi/Kconfig b/drivers/target/iscsi/Kconfig
index 1f93ea381353..922484ea4e30 100644
--- a/drivers/target/iscsi/Kconfig
+++ b/drivers/target/iscsi/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config ISCSI_TARGET
 	tristate "Linux-iSCSI.org iSCSI Target Mode Stack"
-	depends on NET
+	depends on INET
 	select CRYPTO
 	select CRYPTO_CRC32C
 	select CRYPTO_CRC32C_INTEL if X86
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 731ee67fe914..91acb3f07b4c 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -909,14 +909,7 @@ int iscsit_setup_np(
 		}
 	}
 
-	/* FIXME: Someone please explain why this is endian-safe */
-	ret = kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR,
-			(char *)&opt, sizeof(opt));
-	if (ret < 0) {
-		pr_err("kernel_setsockopt() for SO_REUSEADDR"
-			" failed\n");
-		goto fail;
-	}
+	sock_set_reuseaddr(sock->sk);
 
 	ret = kernel_setsockopt(sock, IPPROTO_IP, IP_FREEBIND,
 			(char *)&opt, sizeof(opt));
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index f13dad0fd9ef..88f2574ca63a 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1127,12 +1127,8 @@ static struct socket *tcp_create_listen_sock(struct connection *con,
 	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
 			  sizeof(one));
 
-	result = kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR,
-				   (char *)&one, sizeof(one));
+	sock_set_reuseaddr(sock->sk);
 
-	if (result < 0) {
-		log_print("Failed to set SO_REUSEADDR on socket: %d", result);
-	}
 	write_lock_bh(&sock->sk->sk_callback_lock);
 	sock->sk->sk_user_data = con;
 	save_listen_callbacks(sock);
diff --git a/include/net/sock.h b/include/net/sock.h
index 3e8c6d4b4b59..2ec085044790 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2688,4 +2688,6 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)
 
 void sock_def_readable(struct sock *sk);
 
+void sock_set_reuseaddr(struct sock *sk);
+
 #endif	/* _SOCK_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index fd85e651ce28..18eb84fdf5fb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -712,6 +712,14 @@ bool sk_mc_loop(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_mc_loop);
 
+void sock_set_reuseaddr(struct sock *sk)
+{
+	lock_sock(sk);
+	sk->sk_reuse = SK_CAN_REUSE;
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_reuseaddr);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
-- 
cgit v1.2.3-58-ga151


From 76ee0785f42afbc0418072b7179d95f450d3c9a8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:12 +0200
Subject: net: add sock_set_sndtimeo

Add a helper to directly set the SO_SNDTIMEO_NEW sockopt from kernel
space without going through a fake uaccess.  The interface is
simplified to only pass the seconds value, as that is the only
thing needed at the moment.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/dlm/lowcomms.c  |  8 ++------
 include/net/sock.h |  1 +
 net/core/sock.c    | 11 +++++++++++
 3 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'fs')

diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 88f2574ca63a..b79711d0aac7 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -918,7 +918,6 @@ static void sctp_connect_to_sock(struct connection *con)
 	int result;
 	int addr_len;
 	struct socket *sock;
-	struct __kernel_sock_timeval tv = { .tv_sec = 5, .tv_usec = 0 };
 
 	if (con->nodeid == 0) {
 		log_print("attempt to connect sock 0 foiled");
@@ -970,13 +969,10 @@ static void sctp_connect_to_sock(struct connection *con)
 	 * since O_NONBLOCK argument in connect() function does not work here,
 	 * then, we should restore the default value of this attribute.
 	 */
-	kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_NEW, (char *)&tv,
-			  sizeof(tv));
+	sock_set_sndtimeo(sock->sk, 5);
 	result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len,
 				   0);
-	memset(&tv, 0, sizeof(tv));
-	kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_NEW, (char *)&tv,
-			  sizeof(tv));
+	sock_set_sndtimeo(sock->sk, 0);
 
 	if (result == -EINPROGRESS)
 		result = 0;
diff --git a/include/net/sock.h b/include/net/sock.h
index a3a43141a4be..9a7b9e98685a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2691,5 +2691,6 @@ void sock_def_readable(struct sock *sk);
 void sock_no_linger(struct sock *sk);
 void sock_set_priority(struct sock *sk, u32 priority);
 void sock_set_reuseaddr(struct sock *sk);
+void sock_set_sndtimeo(struct sock *sk, s64 secs);
 
 #endif	/* _SOCK_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index ceda1a9248b3..d3b1d61e4f76 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -737,6 +737,17 @@ void sock_set_priority(struct sock *sk, u32 priority)
 }
 EXPORT_SYMBOL(sock_set_priority);
 
+void sock_set_sndtimeo(struct sock *sk, s64 secs)
+{
+	lock_sock(sk);
+	if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1)
+		sk->sk_sndtimeo = secs * HZ;
+	else
+		sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_sndtimeo);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
-- 
cgit v1.2.3-58-ga151


From ce3d9544cecacd40389c399d2b7ca31acc533b70 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:15 +0200
Subject: net: add sock_set_keepalive

Add a helper to directly set the SO_KEEPALIVE sockopt from kernel space
without going through a fake uaccess.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/dlm/lowcomms.c     |  6 +-----
 include/net/sock.h    |  1 +
 net/core/sock.c       | 10 ++++++++++
 net/rds/tcp_listen.c  |  6 +-----
 net/sunrpc/xprtsock.c |  4 +---
 5 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'fs')

diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index b79711d0aac7..b6e6dba28154 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1142,11 +1142,7 @@ static struct socket *tcp_create_listen_sock(struct connection *con,
 		con->sock = NULL;
 		goto create_out;
 	}
-	result = kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
-				 (char *)&one, sizeof(one));
-	if (result < 0) {
-		log_print("Set keepalive failed: %d", result);
-	}
+	sock_set_keepalive(sock->sk);
 
 	result = sock->ops->listen(sock, 5);
 	if (result < 0) {
diff --git a/include/net/sock.h b/include/net/sock.h
index 99ef43508d2b..dc08c176238f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2691,6 +2691,7 @@ void sock_def_readable(struct sock *sk);
 int sock_bindtoindex(struct sock *sk, int ifindex);
 void sock_enable_timestamps(struct sock *sk);
 void sock_no_linger(struct sock *sk);
+void sock_set_keepalive(struct sock *sk);
 void sock_set_priority(struct sock *sk, u32 priority);
 void sock_set_reuseaddr(struct sock *sk);
 void sock_set_sndtimeo(struct sock *sk, s64 secs);
diff --git a/net/core/sock.c b/net/core/sock.c
index e4a4dd2b3d8b..728f5fb156a0 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -779,6 +779,16 @@ void sock_enable_timestamps(struct sock *sk)
 }
 EXPORT_SYMBOL(sock_enable_timestamps);
 
+void sock_set_keepalive(struct sock *sk)
+{
+	lock_sock(sk);
+	if (sk->sk_prot->keepalive)
+		sk->sk_prot->keepalive(sk, true);
+	sock_valbool_flag(sk, SOCK_KEEPOPEN, true);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_keepalive);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index bbb31b9c0b39..d8bd13276959 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -43,13 +43,9 @@ int rds_tcp_keepalive(struct socket *sock)
 	/* values below based on xs_udp_default_timeout */
 	int keepidle = 5; /* send a probe 'keepidle' secs after last data */
 	int keepcnt = 5; /* number of unack'ed probes before declaring dead */
-	int keepalive = 1;
 	int ret = 0;
 
-	ret = kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
-				(char *)&keepalive, sizeof(keepalive));
-	if (ret < 0)
-		goto bail;
+	sock_set_keepalive(sock->sk);
 
 	ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPCNT,
 				(char *)&keepcnt, sizeof(keepcnt));
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 845d0be805ec..30082cd03996 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2110,7 +2110,6 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
 	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(&xprt->transport_lock);
@@ -2122,8 +2121,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
 	spin_unlock(&xprt->transport_lock);
 
 	/* TCP Keepalive options */
-	kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
-			(char *)&opt_on, sizeof(opt_on));
+	sock_set_keepalive(sock->sk);
 	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE,
 			(char *)&keepidle, sizeof(keepidle));
 	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL,
-- 
cgit v1.2.3-58-ga151


From 26cfabf9cdd273650126d84a48a7f8dedbcded48 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:16 +0200
Subject: net: add sock_set_rcvbuf

Add a helper to directly set the SO_RCVBUFFORCE sockopt from kernel space
without going through a fake uaccess.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/dlm/lowcomms.c  |  7 +------
 include/net/sock.h |  1 +
 net/core/sock.c    | 59 +++++++++++++++++++++++++++++-------------------------
 3 files changed, 34 insertions(+), 33 deletions(-)

(limited to 'fs')

diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index b6e6dba28154..2822a430a2b4 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1180,7 +1180,6 @@ static int sctp_listen_for_all(void)
 	struct socket *sock = NULL;
 	int result = -EINVAL;
 	struct connection *con = nodeid2con(0, GFP_NOFS);
-	int bufsize = NEEDED_RMEM;
 	int one = 1;
 
 	if (!con)
@@ -1195,11 +1194,7 @@ static int sctp_listen_for_all(void)
 		goto out;
 	}
 
-	result = kernel_setsockopt(sock, SOL_SOCKET, SO_RCVBUFFORCE,
-				 (char *)&bufsize, sizeof(bufsize));
-	if (result)
-		log_print("Error increasing buffer space on socket %d", result);
-
+	sock_set_rcvbuf(sock->sk, NEEDED_RMEM);
 	result = kernel_setsockopt(sock, SOL_SCTP, SCTP_NODELAY, (char *)&one,
 				   sizeof(one));
 	if (result < 0)
diff --git a/include/net/sock.h b/include/net/sock.h
index dc08c176238f..c997289aabbf 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2693,6 +2693,7 @@ void sock_enable_timestamps(struct sock *sk);
 void sock_no_linger(struct sock *sk);
 void sock_set_keepalive(struct sock *sk);
 void sock_set_priority(struct sock *sk, u32 priority);
+void sock_set_rcvbuf(struct sock *sk, int val);
 void sock_set_reuseaddr(struct sock *sk);
 void sock_set_sndtimeo(struct sock *sk, s64 secs);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 728f5fb156a0..3c6ebf952e9a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -789,6 +789,35 @@ void sock_set_keepalive(struct sock *sk)
 }
 EXPORT_SYMBOL(sock_set_keepalive);
 
+static void __sock_set_rcvbuf(struct sock *sk, int val)
+{
+	/* Ensure val * 2 fits into an int, to prevent max_t() from treating it
+	 * as a negative value.
+	 */
+	val = min_t(int, val, INT_MAX / 2);
+	sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
+
+	/* We double it on the way in to account for "struct sk_buff" etc.
+	 * overhead.   Applications assume that the SO_RCVBUF setting they make
+	 * will allow that much actual data to be received on that socket.
+	 *
+	 * Applications are unaware that "struct sk_buff" and other overheads
+	 * allocate from the receive buffer during socket buffer allocation.
+	 *
+	 * And after considering the possible alternatives, returning the value
+	 * we actually used in getsockopt is the most desirable behavior.
+	 */
+	WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF));
+}
+
+void sock_set_rcvbuf(struct sock *sk, int val)
+{
+	lock_sock(sk);
+	__sock_set_rcvbuf(sk, val);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_rcvbuf);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
@@ -885,30 +914,7 @@ set_sndbuf:
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		val = min_t(u32, val, sysctl_rmem_max);
-set_rcvbuf:
-		/* Ensure val * 2 fits into an int, to prevent max_t()
-		 * from treating it as a negative value.
-		 */
-		val = min_t(int, val, INT_MAX / 2);
-		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
-		/*
-		 * We double it on the way in to account for
-		 * "struct sk_buff" etc. overhead.   Applications
-		 * assume that the SO_RCVBUF setting they make will
-		 * allow that much actual data to be received on that
-		 * socket.
-		 *
-		 * Applications are unaware that "struct sk_buff" and
-		 * other overheads allocate from the receive buffer
-		 * during socket buffer allocation.
-		 *
-		 * And after considering the possible alternatives,
-		 * returning the value we actually used in getsockopt
-		 * is the most desirable behavior.
-		 */
-		WRITE_ONCE(sk->sk_rcvbuf,
-			   max_t(int, val * 2, SOCK_MIN_RCVBUF));
+		__sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max));
 		break;
 
 	case SO_RCVBUFFORCE:
@@ -920,9 +926,8 @@ set_rcvbuf:
 		/* No negative values (to prevent underflow, as val will be
 		 * multiplied by 2).
 		 */
-		if (val < 0)
-			val = 0;
-		goto set_rcvbuf;
+		__sock_set_rcvbuf(sk, max(val, 0));
+		break;
 
 	case SO_KEEPALIVE:
 		if (sk->sk_prot->keepalive)
-- 
cgit v1.2.3-58-ga151


From db10538a4b997a77a1fd561adaaa58afc7dcfa2f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:18 +0200
Subject: tcp: add tcp_sock_set_cork

Add a helper to directly set the TCP_CORK sockopt from kernel space
without going through a fake uaccess.  Cleanup the callers to avoid
pointless wrappers now that this is a simple function call.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/drbd/drbd_int.h      | 14 -----------
 drivers/block/drbd/drbd_receiver.c |  4 +--
 drivers/block/drbd/drbd_worker.c   |  6 ++---
 fs/cifs/transport.c                |  8 ++----
 include/linux/tcp.h                |  2 ++
 net/ipv4/tcp.c                     | 51 ++++++++++++++++++++++++--------------
 net/rds/tcp_send.c                 |  9 ++-----
 7 files changed, 43 insertions(+), 51 deletions(-)

(limited to 'fs')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index aae99a2d7bd4..3550adc93c68 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1570,20 +1570,6 @@ extern void drbd_set_recv_tcq(struct drbd_device *device, int tcq_enabled);
 extern void _drbd_clear_done_ee(struct drbd_device *device, struct list_head *to_be_freed);
 extern int drbd_connected(struct drbd_peer_device *);
 
-static inline void drbd_tcp_cork(struct socket *sock)
-{
-	int val = 1;
-	(void) kernel_setsockopt(sock, SOL_TCP, TCP_CORK,
-			(char*)&val, sizeof(val));
-}
-
-static inline void drbd_tcp_uncork(struct socket *sock)
-{
-	int val = 0;
-	(void) kernel_setsockopt(sock, SOL_TCP, TCP_CORK,
-			(char*)&val, sizeof(val));
-}
-
 static inline void drbd_tcp_nodelay(struct socket *sock)
 {
 	int val = 1;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index c15e7083b13a..55ea907ad33c 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -6162,7 +6162,7 @@ void drbd_send_acks_wf(struct work_struct *ws)
 	rcu_read_unlock();
 
 	if (tcp_cork)
-		drbd_tcp_cork(connection->meta.socket);
+		tcp_sock_set_cork(connection->meta.socket->sk, true);
 
 	err = drbd_finish_peer_reqs(device);
 	kref_put(&device->kref, drbd_destroy_device);
@@ -6175,7 +6175,7 @@ void drbd_send_acks_wf(struct work_struct *ws)
 	}
 
 	if (tcp_cork)
-		drbd_tcp_uncork(connection->meta.socket);
+		tcp_sock_set_cork(connection->meta.socket->sk, false);
 
 	return;
 }
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 0dc019da1f8d..2b89c9f2ca70 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -2098,7 +2098,7 @@ static void wait_for_work(struct drbd_connection *connection, struct list_head *
 	if (uncork) {
 		mutex_lock(&connection->data.mutex);
 		if (connection->data.socket)
-			drbd_tcp_uncork(connection->data.socket);
+			tcp_sock_set_cork(connection->data.socket->sk, false);
 		mutex_unlock(&connection->data.mutex);
 	}
 
@@ -2153,9 +2153,9 @@ static void wait_for_work(struct drbd_connection *connection, struct list_head *
 	mutex_lock(&connection->data.mutex);
 	if (connection->data.socket) {
 		if (cork)
-			drbd_tcp_cork(connection->data.socket);
+			tcp_sock_set_cork(connection->data.socket->sk, true);
 		else if (!uncork)
-			drbd_tcp_uncork(connection->data.socket);
+			tcp_sock_set_cork(connection->data.socket->sk, false);
 	}
 	mutex_unlock(&connection->data.mutex);
 }
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index c97570eb2c18..99760063e000 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -325,7 +325,6 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	size_t total_len = 0, sent, size;
 	struct socket *ssocket = server->ssocket;
 	struct msghdr smb_msg;
-	int val = 1;
 	__be32 rfc1002_marker;
 
 	if (cifs_rdma_enabled(server)) {
@@ -345,8 +344,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	}
 
 	/* cork the socket */
-	kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
-				(char *)&val, sizeof(val));
+	tcp_sock_set_cork(ssocket->sk, true);
 
 	for (j = 0; j < num_rqst; j++)
 		send_length += smb_rqst_len(server, &rqst[j]);
@@ -435,9 +433,7 @@ unmask:
 	}
 
 	/* uncork it */
-	val = 0;
-	kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
-				(char *)&val, sizeof(val));
+	tcp_sock_set_cork(ssocket->sk, false);
 
 	if ((total_len > 0) && (total_len != send_length)) {
 		cifs_dbg(FYI, "partial send (wanted=%u sent=%zu): terminating session\n",
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index bf44e85d709d..889eeb2256c2 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -497,4 +497,6 @@ static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss)
 int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
 		  int shiftlen);
 
+void tcp_sock_set_cork(struct sock *sk, bool on);
+
 #endif	/* _LINUX_TCP_H */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 970064996377..e6cf702e16d6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2801,6 +2801,37 @@ static void tcp_enable_tx_delay(void)
 	}
 }
 
+/* When set indicates to always queue non-full frames.  Later the user clears
+ * this option and we transmit any pending partial frames in the queue.  This is
+ * meant to be used alongside sendfile() to get properly filled frames when the
+ * user (for example) must write out headers with a write() call first and then
+ * use sendfile to send out the data parts.
+ *
+ * TCP_CORK can be set together with TCP_NODELAY and it is stronger than
+ * TCP_NODELAY.
+ */
+static void __tcp_sock_set_cork(struct sock *sk, bool on)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (on) {
+		tp->nonagle |= TCP_NAGLE_CORK;
+	} else {
+		tp->nonagle &= ~TCP_NAGLE_CORK;
+		if (tp->nonagle & TCP_NAGLE_OFF)
+			tp->nonagle |= TCP_NAGLE_PUSH;
+		tcp_push_pending_frames(sk);
+	}
+}
+
+void tcp_sock_set_cork(struct sock *sk, bool on)
+{
+	lock_sock(sk);
+	__tcp_sock_set_cork(sk, on);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(tcp_sock_set_cork);
+
 /*
  *	Socket option code for TCP.
  */
@@ -2979,25 +3010,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_CORK:
-		/* When set indicates to always queue non-full frames.
-		 * Later the user clears this option and we transmit
-		 * any pending partial frames in the queue.  This is
-		 * meant to be used alongside sendfile() to get properly
-		 * filled frames when the user (for example) must write
-		 * out headers with a write() call first and then use
-		 * sendfile to send out the data parts.
-		 *
-		 * TCP_CORK can be set together with TCP_NODELAY and it is
-		 * stronger than TCP_NODELAY.
-		 */
-		if (val) {
-			tp->nonagle |= TCP_NAGLE_CORK;
-		} else {
-			tp->nonagle &= ~TCP_NAGLE_CORK;
-			if (tp->nonagle&TCP_NAGLE_OFF)
-				tp->nonagle |= TCP_NAGLE_PUSH;
-			tcp_push_pending_frames(sk);
-		}
+		__tcp_sock_set_cork(sk, val);
 		break;
 
 	case TCP_KEEPIDLE:
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 78a2554a4497..8c4d1d6e9249 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -38,23 +38,18 @@
 #include "rds.h"
 #include "tcp.h"
 
-static void rds_tcp_cork(struct socket *sock, int val)
-{
-	kernel_setsockopt(sock, SOL_TCP, TCP_CORK, (void *)&val, sizeof(val));
-}
-
 void rds_tcp_xmit_path_prepare(struct rds_conn_path *cp)
 {
 	struct rds_tcp_connection *tc = cp->cp_transport_data;
 
-	rds_tcp_cork(tc->t_sock, 1);
+	tcp_sock_set_cork(tc->t_sock->sk, true);
 }
 
 void rds_tcp_xmit_path_complete(struct rds_conn_path *cp)
 {
 	struct rds_tcp_connection *tc = cp->cp_transport_data;
 
-	rds_tcp_cork(tc->t_sock, 0);
+	tcp_sock_set_cork(tc->t_sock->sk, false);
 }
 
 /* the core send_sem serializes this with other xmit and shutdown */
-- 
cgit v1.2.3-58-ga151


From 12abc5ee7873a085cc280240822b8ac53c86fecd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:19 +0200
Subject: tcp: add tcp_sock_set_nodelay

Add a helper to directly set the TCP_NODELAY sockopt from kernel space
without going through a fake uaccess.  Cleanup the callers to avoid
pointless wrappers now that this is a simple function call.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Sagi Grimberg <sagi@grimberg.me>
Acked-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/drbd/drbd_int.h             |  7 ------
 drivers/block/drbd/drbd_main.c            |  2 +-
 drivers/block/drbd/drbd_receiver.c        |  4 ++--
 drivers/infiniband/sw/siw/siw_cm.c        | 24 ++++---------------
 drivers/nvme/host/tcp.c                   |  9 +------
 drivers/nvme/target/tcp.c                 | 12 ++--------
 drivers/target/iscsi/iscsi_target_login.c | 15 +++---------
 fs/cifs/connect.c                         | 10 ++------
 fs/dlm/lowcomms.c                         |  8 ++-----
 fs/ocfs2/cluster/tcp.c                    | 20 ++--------------
 include/linux/tcp.h                       |  1 +
 net/ceph/messenger.c                      | 11 ++-------
 net/ipv4/tcp.c                            | 39 ++++++++++++++++++++-----------
 net/rds/tcp.c                             | 11 +--------
 net/rds/tcp.h                             |  1 -
 net/rds/tcp_listen.c                      |  2 +-
 16 files changed, 49 insertions(+), 127 deletions(-)

(limited to 'fs')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 3550adc93c68..e24bba87c8e0 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1570,13 +1570,6 @@ extern void drbd_set_recv_tcq(struct drbd_device *device, int tcq_enabled);
 extern void _drbd_clear_done_ee(struct drbd_device *device, struct list_head *to_be_freed);
 extern int drbd_connected(struct drbd_peer_device *);
 
-static inline void drbd_tcp_nodelay(struct socket *sock)
-{
-	int val = 1;
-	(void) kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
-			(char*)&val, sizeof(val));
-}
-
 static inline void drbd_tcp_quickack(struct socket *sock)
 {
 	int val = 2;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index c094c3c2c5d4..45fbd526c453 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -660,7 +660,7 @@ static int __send_command(struct drbd_connection *connection, int vnr,
 	/* DRBD protocol "pings" are latency critical.
 	 * This is supposed to trigger tcp_push_pending_frames() */
 	if (!err && (cmd == P_PING || cmd == P_PING_ACK))
-		drbd_tcp_nodelay(sock->socket);
+		tcp_sock_set_nodelay(sock->socket->sk);
 
 	return err;
 }
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 55ea907ad33c..20a5e94494ac 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1051,8 +1051,8 @@ randomize:
 
 	/* we don't want delays.
 	 * we use TCP_CORK where appropriate, though */
-	drbd_tcp_nodelay(sock.socket);
-	drbd_tcp_nodelay(msock.socket);
+	tcp_sock_set_nodelay(sock.socket->sk);
+	tcp_sock_set_nodelay(msock.socket->sk);
 
 	connection->data.socket = sock.socket;
 	connection->meta.socket = msock.socket;
diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
index d1860f3e8740..1662216be66d 100644
--- a/drivers/infiniband/sw/siw/siw_cm.c
+++ b/drivers/infiniband/sw/siw/siw_cm.c
@@ -947,16 +947,8 @@ static void siw_accept_newconn(struct siw_cep *cep)
 	siw_cep_get(new_cep);
 	new_s->sk->sk_user_data = new_cep;
 
-	if (siw_tcp_nagle == false) {
-		int val = 1;
-
-		rv = kernel_setsockopt(new_s, SOL_TCP, TCP_NODELAY,
-				       (char *)&val, sizeof(val));
-		if (rv) {
-			siw_dbg_cep(cep, "setsockopt NODELAY error: %d\n", rv);
-			goto error;
-		}
-	}
+	if (siw_tcp_nagle == false)
+		tcp_sock_set_nodelay(new_s->sk);
 	new_cep->state = SIW_EPSTATE_AWAIT_MPAREQ;
 
 	rv = siw_cm_queue_work(new_cep, SIW_CM_WORK_MPATIMEOUT);
@@ -1386,16 +1378,8 @@ int siw_connect(struct iw_cm_id *id, struct iw_cm_conn_param *params)
 		siw_dbg_qp(qp, "kernel_bindconnect: error %d\n", rv);
 		goto error;
 	}
-	if (siw_tcp_nagle == false) {
-		int val = 1;
-
-		rv = kernel_setsockopt(s, SOL_TCP, TCP_NODELAY, (char *)&val,
-				       sizeof(val));
-		if (rv) {
-			siw_dbg_qp(qp, "setsockopt NODELAY error: %d\n", rv);
-			goto error;
-		}
-	}
+	if (siw_tcp_nagle == false)
+		tcp_sock_set_nodelay(s->sk);
 	cep = siw_cep_alloc(sdev);
 	if (!cep) {
 		rv = -ENOMEM;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index a307972d33a0..4e4a750ecdb9 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1346,14 +1346,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 	}
 
 	/* Set TCP no delay */
-	opt = 1;
-	ret = kernel_setsockopt(queue->sock, IPPROTO_TCP,
-			TCP_NODELAY, (char *)&opt, sizeof(opt));
-	if (ret) {
-		dev_err(nctrl->device,
-			"failed to set TCP_NODELAY sock opt %d\n", ret);
-		goto err_sock;
-	}
+	tcp_sock_set_nodelay(queue->sock->sk);
 
 	/*
 	 * Cleanup whatever is sitting in the TCP transmit queue on socket
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index f3088156d01d..55bc4c3c0a74 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1580,7 +1580,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 {
 	struct nvmet_tcp_port *port;
 	__kernel_sa_family_t af;
-	int opt, ret;
+	int ret;
 
 	port = kzalloc(sizeof(*port), GFP_KERNEL);
 	if (!port)
@@ -1625,15 +1625,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 	port->data_ready = port->sock->sk->sk_data_ready;
 	port->sock->sk->sk_data_ready = nvmet_tcp_listen_data_ready;
 	sock_set_reuseaddr(port->sock->sk);
-
-	opt = 1;
-	ret = kernel_setsockopt(port->sock, IPPROTO_TCP,
-			TCP_NODELAY, (char *)&opt, sizeof(opt));
-	if (ret) {
-		pr_err("failed to set TCP_NODELAY sock opt %d\n", ret);
-		goto err_sock;
-	}
-
+	tcp_sock_set_nodelay(port->sock->sk);
 	if (so_priority > 0)
 		sock_set_priority(port->sock->sk, so_priority);
 
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 91acb3f07b4c..b561b07a869a 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -897,20 +897,11 @@ int iscsit_setup_np(
 	/*
 	 * Set SO_REUSEADDR, and disable Nagel Algorithm with TCP_NODELAY.
 	 */
-	/* FIXME: Someone please explain why this is endian-safe */
-	opt = 1;
-	if (np->np_network_transport == ISCSI_TCP) {
-		ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_NODELAY,
-				(char *)&opt, sizeof(opt));
-		if (ret < 0) {
-			pr_err("kernel_setsockopt() for TCP_NODELAY"
-				" failed: %d\n", ret);
-			goto fail;
-		}
-	}
-
+	if (np->np_network_transport == ISCSI_TCP)
+		tcp_sock_set_nodelay(sock->sk);
 	sock_set_reuseaddr(sock->sk);
 
+	opt = 1;
 	ret = kernel_setsockopt(sock, IPPROTO_IP, IP_FREEBIND,
 			(char *)&opt, sizeof(opt));
 	if (ret < 0) {
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 28268ed461b8..ad8fb53b3682 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3929,14 +3929,8 @@ generic_ip_connect(struct TCP_Server_Info *server)
 			socket->sk->sk_rcvbuf = 140 * 1024;
 	}
 
-	if (server->tcp_nodelay) {
-		int val = 1;
-		rc = kernel_setsockopt(socket, SOL_TCP, TCP_NODELAY,
-				(char *)&val, sizeof(val));
-		if (rc)
-			cifs_dbg(FYI, "set TCP_NODELAY socket option error %d\n",
-				 rc);
-	}
+	if (server->tcp_nodelay)
+		tcp_sock_set_nodelay(socket->sk);
 
 	cifs_dbg(FYI, "sndbuf %d rcvbuf %d rcvtimeo 0x%lx\n",
 		 socket->sk->sk_sndbuf,
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 2822a430a2b4..69333728d871 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1011,7 +1011,6 @@ static void tcp_connect_to_sock(struct connection *con)
 	struct sockaddr_storage saddr, src_addr;
 	int addr_len;
 	struct socket *sock = NULL;
-	int one = 1;
 	int result;
 
 	if (con->nodeid == 0) {
@@ -1060,8 +1059,7 @@ static void tcp_connect_to_sock(struct connection *con)
 	log_print("connecting to %d", con->nodeid);
 
 	/* Turn off Nagle's algorithm */
-	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
-			  sizeof(one));
+	tcp_sock_set_nodelay(sock->sk);
 
 	result = sock->ops->connect(sock, (struct sockaddr *)&saddr, addr_len,
 				   O_NONBLOCK);
@@ -1103,7 +1101,6 @@ static struct socket *tcp_create_listen_sock(struct connection *con,
 {
 	struct socket *sock = NULL;
 	int result = 0;
-	int one = 1;
 	int addr_len;
 
 	if (dlm_local_addr[0]->ss_family == AF_INET)
@@ -1120,8 +1117,7 @@ static struct socket *tcp_create_listen_sock(struct connection *con,
 	}
 
 	/* Turn off Nagle's algorithm */
-	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
-			  sizeof(one));
+	tcp_sock_set_nodelay(sock->sk);
 
 	sock_set_reuseaddr(sock->sk);
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 2c512b40a940..4c70fe9d19ab 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1441,14 +1441,6 @@ static void o2net_rx_until_empty(struct work_struct *work)
 	sc_put(sc);
 }
 
-static int o2net_set_nodelay(struct socket *sock)
-{
-	int val = 1;
-
-	return kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
-				    (void *)&val, sizeof(val));
-}
-
 static int o2net_set_usertimeout(struct socket *sock)
 {
 	int user_timeout = O2NET_TCP_USER_TIMEOUT;
@@ -1636,11 +1628,7 @@ static void o2net_start_connect(struct work_struct *work)
 		goto out;
 	}
 
-	ret = o2net_set_nodelay(sc->sc_sock);
-	if (ret) {
-		mlog(ML_ERROR, "setting TCP_NODELAY failed with %d\n", ret);
-		goto out;
-	}
+	tcp_sock_set_nodelay(sc->sc_sock->sk);
 
 	ret = o2net_set_usertimeout(sock);
 	if (ret) {
@@ -1832,11 +1820,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
 	*more = 1;
 	new_sock->sk->sk_allocation = GFP_ATOMIC;
 
-	ret = o2net_set_nodelay(new_sock);
-	if (ret) {
-		mlog(ML_ERROR, "setting TCP_NODELAY failed with %d\n", ret);
-		goto out;
-	}
+	tcp_sock_set_nodelay(new_sock->sk);
 
 	ret = o2net_set_usertimeout(new_sock);
 	if (ret) {
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 889eeb2256c2..9e42c7fe50a8 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -498,5 +498,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
 		  int shiftlen);
 
 void tcp_sock_set_cork(struct sock *sk, bool on);
+void tcp_sock_set_nodelay(struct sock *sk);
 
 #endif	/* _LINUX_TCP_H */
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index f8ca5edc5f2c..27d6ab11f9ee 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -490,15 +490,8 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 		return ret;
 	}
 
-	if (ceph_test_opt(from_msgr(con->msgr), TCP_NODELAY)) {
-		int optval = 1;
-
-		ret = kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
-					(char *)&optval, sizeof(optval));
-		if (ret)
-			pr_err("kernel_setsockopt(TCP_NODELAY) failed: %d",
-			       ret);
-	}
+	if (ceph_test_opt(from_msgr(con->msgr), TCP_NODELAY))
+		tcp_sock_set_nodelay(sock->sk);
 
 	con->sock = sock;
 	return 0;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e6cf702e16d6..a65f293a19fa 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2832,6 +2832,30 @@ void tcp_sock_set_cork(struct sock *sk, bool on)
 }
 EXPORT_SYMBOL(tcp_sock_set_cork);
 
+/* TCP_NODELAY is weaker than TCP_CORK, so that this option on corked socket is
+ * remembered, but it is not activated until cork is cleared.
+ *
+ * However, when TCP_NODELAY is set we make an explicit push, which overrides
+ * even TCP_CORK for currently queued segments.
+ */
+static void __tcp_sock_set_nodelay(struct sock *sk, bool on)
+{
+	if (on) {
+		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
+		tcp_push_pending_frames(sk);
+	} else {
+		tcp_sk(sk)->nonagle &= ~TCP_NAGLE_OFF;
+	}
+}
+
+void tcp_sock_set_nodelay(struct sock *sk)
+{
+	lock_sock(sk);
+	__tcp_sock_set_nodelay(sk, true);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(tcp_sock_set_nodelay);
+
 /*
  *	Socket option code for TCP.
  */
@@ -2929,20 +2953,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_NODELAY:
-		if (val) {
-			/* TCP_NODELAY is weaker than TCP_CORK, so that
-			 * this option on corked socket is remembered, but
-			 * it is not activated until cork is cleared.
-			 *
-			 * However, when TCP_NODELAY is set we make
-			 * an explicit push, which overrides even TCP_CORK
-			 * for currently queued segments.
-			 */
-			tp->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
-			tcp_push_pending_frames(sk);
-		} else {
-			tp->nonagle &= ~TCP_NAGLE_OFF;
-		}
+		__tcp_sock_set_nodelay(sk, val);
 		break;
 
 	case TCP_THIN_LINEAR_TIMEOUTS:
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 46782fac4c16..43db0eca911f 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -89,15 +89,6 @@ static struct ctl_table rds_tcp_sysctl_table[] = {
 	{ }
 };
 
-/* doing it this way avoids calling tcp_sk() */
-void rds_tcp_nonagle(struct socket *sock)
-{
-	int val = 1;
-
-	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (void *)&val,
-			      sizeof(val));
-}
-
 u32 rds_tcp_write_seq(struct rds_tcp_connection *tc)
 {
 	/* seq# of the last byte of data in tcp send buffer */
@@ -502,7 +493,7 @@ void rds_tcp_tune(struct socket *sock)
 	struct net *net = sock_net(sk);
 	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
 
-	rds_tcp_nonagle(sock);
+	tcp_sock_set_nodelay(sock->sk);
 	lock_sock(sk);
 	if (rtn->sndbuf_size > 0) {
 		sk->sk_sndbuf = rtn->sndbuf_size;
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index d640e210b97b..f6d75d8cb167 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -50,7 +50,6 @@ struct rds_tcp_statistics {
 
 /* tcp.c */
 void rds_tcp_tune(struct socket *sock);
-void rds_tcp_nonagle(struct socket *sock);
 void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp);
 void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp);
 void rds_tcp_restore_callbacks(struct socket *sock,
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index d8bd13276959..6f90ea077adc 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -288,7 +288,7 @@ struct socket *rds_tcp_listen_init(struct net *net, bool isv6)
 	}
 
 	sock->sk->sk_reuse = SK_CAN_REUSE;
-	rds_tcp_nonagle(sock);
+	tcp_sock_set_nodelay(sock->sk);
 
 	write_lock_bh(&sock->sk->sk_callback_lock);
 	sock->sk->sk_user_data = sock->sk->sk_data_ready;
-- 
cgit v1.2.3-58-ga151


From c488aeadcbd002a992593e6090d54e8ac27c4310 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:22 +0200
Subject: tcp: add tcp_sock_set_user_timeout

Add a helper to directly set the TCP_USER_TIMEOUT sockopt from kernel
space without going through a fake uaccess.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/ocfs2/cluster/tcp.c | 22 ++--------------------
 include/linux/tcp.h    |  1 +
 net/ipv4/tcp.c         |  8 ++++++++
 net/sunrpc/xprtsock.c  |  3 +--
 4 files changed, 12 insertions(+), 22 deletions(-)

(limited to 'fs')

diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 4c70fe9d19ab..79a231719460 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1441,14 +1441,6 @@ static void o2net_rx_until_empty(struct work_struct *work)
 	sc_put(sc);
 }
 
-static int o2net_set_usertimeout(struct socket *sock)
-{
-	int user_timeout = O2NET_TCP_USER_TIMEOUT;
-
-	return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
-				(void *)&user_timeout, sizeof(user_timeout));
-}
-
 static void o2net_initialize_handshake(void)
 {
 	o2net_hand->o2hb_heartbeat_timeout_ms = cpu_to_be32(
@@ -1629,12 +1621,7 @@ static void o2net_start_connect(struct work_struct *work)
 	}
 
 	tcp_sock_set_nodelay(sc->sc_sock->sk);
-
-	ret = o2net_set_usertimeout(sock);
-	if (ret) {
-		mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret);
-		goto out;
-	}
+	tcp_sock_set_user_timeout(sock->sk, O2NET_TCP_USER_TIMEOUT);
 
 	o2net_register_callbacks(sc->sc_sock->sk, sc);
 
@@ -1821,12 +1808,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
 	new_sock->sk->sk_allocation = GFP_ATOMIC;
 
 	tcp_sock_set_nodelay(new_sock->sk);
-
-	ret = o2net_set_usertimeout(new_sock);
-	if (ret) {
-		mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret);
-		goto out;
-	}
+	tcp_sock_set_user_timeout(new_sock->sk, O2NET_TCP_USER_TIMEOUT);
 
 	ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin, 1);
 	if (ret < 0)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 6aa4ae5ebf3d..de682143efe4 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -501,5 +501,6 @@ void tcp_sock_set_cork(struct sock *sk, bool on);
 void tcp_sock_set_nodelay(struct sock *sk);
 void tcp_sock_set_quickack(struct sock *sk, int val);
 int tcp_sock_set_syncnt(struct sock *sk, int val);
+void tcp_sock_set_user_timeout(struct sock *sk, u32 val);
 
 #endif	/* _LINUX_TCP_H */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d2c67ae1da07..0004bd9ae7b0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2893,6 +2893,14 @@ int tcp_sock_set_syncnt(struct sock *sk, int val)
 }
 EXPORT_SYMBOL(tcp_sock_set_syncnt);
 
+void tcp_sock_set_user_timeout(struct sock *sk, u32 val)
+{
+	lock_sock(sk);
+	inet_csk(sk)->icsk_user_timeout = val;
+	release_sock(sk);
+}
+EXPORT_SYMBOL(tcp_sock_set_user_timeout);
+
 /*
  *	Socket option code for TCP.
  */
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 399848c2bcb2..231fd6162f68 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2115,8 +2115,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
 			(char *)&keepcnt, sizeof(keepcnt));
 
 	/* TCP user timeout (see RFC5482) */
-	kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
-			(char *)&timeo, sizeof(timeo));
+	tcp_sock_set_user_timeout(sock->sk, timeo);
 }
 
 static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt,
-- 
cgit v1.2.3-58-ga151


From 298cd88a66a02c899772ffafbf648786ceb5ab95 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:35 +0200
Subject: rxrpc: add rxrpc_sock_set_min_security_level

Add a helper to directly set the RXRPC_MIN_SECURITY_LEVEL sockopt from
kernel space without going through a fake uaccess.

Thanks to David Howells for the documentation updates.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/rxrpc.rst | 13 +++++++++++--
 fs/afs/rxrpc.c                     |  6 ++----
 include/net/af_rxrpc.h             |  2 ++
 net/rxrpc/af_rxrpc.c               | 13 +++++++++++++
 4 files changed, 28 insertions(+), 6 deletions(-)

(limited to 'fs')

diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst
index 5ad35113d0f4..68552b92dc44 100644
--- a/Documentation/networking/rxrpc.rst
+++ b/Documentation/networking/rxrpc.rst
@@ -477,7 +477,7 @@ AF_RXRPC sockets support a few socket options at the SOL_RXRPC level:
 	 Encrypted checksum plus packet padded and first eight bytes of packet
 	 encrypted - which includes the actual packet length.
 
-     (c) RXRPC_SECURITY_ENCRYPTED
+     (c) RXRPC_SECURITY_ENCRYPT
 
 	 Encrypted checksum plus entire packet padded and encrypted, including
 	 actual packet length.
@@ -578,7 +578,7 @@ A client would issue an operation by:
      This issues a request_key() to get the key representing the security
      context.  The minimum security level can be set::
 
-	unsigned int sec = RXRPC_SECURITY_ENCRYPTED;
+	unsigned int sec = RXRPC_SECURITY_ENCRYPT;
 	setsockopt(client, SOL_RXRPC, RXRPC_MIN_SECURITY_LEVEL,
 		   &sec, sizeof(sec));
 
@@ -1090,6 +1090,15 @@ The kernel interface functions are as follows:
      jiffies).  In the event of the timeout occurring, the call will be
      aborted and -ETIME or -ETIMEDOUT will be returned.
 
+ (#) Apply the RXRPC_MIN_SECURITY_LEVEL sockopt to a socket from within in the
+     kernel::
+
+       int rxrpc_sock_set_min_security_level(struct sock *sk,
+					     unsigned int val);
+
+     This specifies the minimum security level required for calls on this
+     socket.
+
 
 Configurable Parameters
 =======================
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 1ecc67da6c1a..e313dae01674 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -37,7 +37,6 @@ int afs_open_socket(struct afs_net *net)
 {
 	struct sockaddr_rxrpc srx;
 	struct socket *socket;
-	unsigned int min_level;
 	int ret;
 
 	_enter("");
@@ -57,9 +56,8 @@ int afs_open_socket(struct afs_net *net)
 	srx.transport.sin6.sin6_family	= AF_INET6;
 	srx.transport.sin6.sin6_port	= htons(AFS_CM_PORT);
 
-	min_level = RXRPC_SECURITY_ENCRYPT;
-	ret = kernel_setsockopt(socket, SOL_RXRPC, RXRPC_MIN_SECURITY_LEVEL,
-				(void *)&min_level, sizeof(min_level));
+	ret = rxrpc_sock_set_min_security_level(socket->sk,
+						RXRPC_SECURITY_ENCRYPT);
 	if (ret < 0)
 		goto error_2;
 
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index ab988940bf04..91eacbdcf33d 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -72,4 +72,6 @@ bool rxrpc_kernel_call_is_complete(struct rxrpc_call *);
 void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *,
 			       unsigned long);
 
+int rxrpc_sock_set_min_security_level(struct sock *sk, unsigned int val);
+
 #endif /* _NET_RXRPC_H */
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 15ee92d79581..394189b81849 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -571,6 +571,19 @@ out:
 	return ret;
 }
 
+int rxrpc_sock_set_min_security_level(struct sock *sk, unsigned int val)
+{
+	if (sk->sk_state != RXRPC_UNBOUND)
+		return -EISCONN;
+	if (val > RXRPC_SECURITY_MAX)
+		return -EINVAL;
+	lock_sock(sk);
+	rxrpc_sk(sk)->min_sec_level = val;
+	release_sock(sk);
+	return 0;
+}
+EXPORT_SYMBOL(rxrpc_sock_set_min_security_level);
+
 /*
  * set RxRPC socket options
  */
-- 
cgit v1.2.3-58-ga151


From 40ef92c6ec09bd8aaffccfa41a715d1df5625f95 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 May 2020 14:09:40 +0200
Subject: sctp: add sctp_sock_set_nodelay

Add a helper to directly set the SCTP_NODELAY sockopt from kernel space
without going through a fake uaccess.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/dlm/lowcomms.c       | 10 ++--------
 include/net/sctp/sctp.h |  7 +++++++
 2 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'fs')

diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 69333728d871..9f1c3cdc9d65 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -914,7 +914,6 @@ static int sctp_bind_addrs(struct connection *con, uint16_t port)
 static void sctp_connect_to_sock(struct connection *con)
 {
 	struct sockaddr_storage daddr;
-	int one = 1;
 	int result;
 	int addr_len;
 	struct socket *sock;
@@ -961,8 +960,7 @@ static void sctp_connect_to_sock(struct connection *con)
 	log_print("connecting to %d", con->nodeid);
 
 	/* Turn off Nagle's algorithm */
-	kernel_setsockopt(sock, SOL_SCTP, SCTP_NODELAY, (char *)&one,
-			  sizeof(one));
+	sctp_sock_set_nodelay(sock->sk);
 
 	/*
 	 * Make sock->ops->connect() function return in specified time,
@@ -1176,7 +1174,6 @@ static int sctp_listen_for_all(void)
 	struct socket *sock = NULL;
 	int result = -EINVAL;
 	struct connection *con = nodeid2con(0, GFP_NOFS);
-	int one = 1;
 
 	if (!con)
 		return -ENOMEM;
@@ -1191,10 +1188,7 @@ static int sctp_listen_for_all(void)
 	}
 
 	sock_set_rcvbuf(sock->sk, NEEDED_RMEM);
-	result = kernel_setsockopt(sock, SOL_SCTP, SCTP_NODELAY, (char *)&one,
-				   sizeof(one));
-	if (result < 0)
-		log_print("Could not set SCTP NODELAY error %d\n", result);
+	sctp_sock_set_nodelay(sock->sk);
 
 	write_lock_bh(&sock->sk->sk_callback_lock);
 	/* Init con struct */
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 3ab5c6bbb90b..f8bcb75bb044 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -615,4 +615,11 @@ static inline bool sctp_newsk_ready(const struct sock *sk)
 	return sock_flag(sk, SOCK_DEAD) || sk->sk_socket;
 }
 
+static inline void sctp_sock_set_nodelay(struct sock *sk)
+{
+	lock_sock(sk);
+	sctp_sk(sk)->nodelay = true;
+	release_sock(sk);
+}
+
 #endif /* __net_sctp_h__ */
-- 
cgit v1.2.3-58-ga151


From c0425a4249e9d313eec5f81c0bde8a286ebf9a63 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 May 2020 14:09:42 +0200
Subject: net: add a new bind_add method

The SCTP protocol allows to bind multiple address to a socket.  That
feature is currently only exposed as a socket option.  Add a bind_add
method struct proto that allows to bind additional addresses, and
switch the dlm code to use the method instead of going through the
socket option from kernel space.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/dlm/lowcomms.c  |  9 +++------
 include/net/sock.h |  6 +++++-
 net/core/sock.c    |  8 ++++++++
 net/sctp/socket.c  | 14 ++++++++++++++
 4 files changed, 30 insertions(+), 7 deletions(-)

(limited to 'fs')

diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 9f1c3cdc9d65..3543a8fec907 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -882,6 +882,7 @@ static void writequeue_entry_complete(struct writequeue_entry *e, int completed)
 static int sctp_bind_addrs(struct connection *con, uint16_t port)
 {
 	struct sockaddr_storage localaddr;
+	struct sockaddr *addr = (struct sockaddr *)&localaddr;
 	int i, addr_len, result = 0;
 
 	for (i = 0; i < dlm_local_count; i++) {
@@ -889,13 +890,9 @@ static int sctp_bind_addrs(struct connection *con, uint16_t port)
 		make_sockaddr(&localaddr, port, &addr_len);
 
 		if (!i)
-			result = kernel_bind(con->sock,
-					     (struct sockaddr *)&localaddr,
-					     addr_len);
+			result = kernel_bind(con->sock, addr, addr_len);
 		else
-			result = kernel_setsockopt(con->sock, SOL_SCTP,
-						   SCTP_SOCKOPT_BINDX_ADD,
-						   (char *)&localaddr, addr_len);
+			result = sock_bind_add(con->sock->sk, addr, addr_len);
 
 		if (result < 0) {
 			log_print("Can't bind to %d addr number %d, %d.\n",
diff --git a/include/net/sock.h b/include/net/sock.h
index d994daa418ec..6e9f713a7860 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1156,7 +1156,9 @@ struct proto {
 	int			(*sendpage)(struct sock *sk, struct page *page,
 					int offset, size_t size, int flags);
 	int			(*bind)(struct sock *sk,
-					struct sockaddr *uaddr, int addr_len);
+					struct sockaddr *addr, int addr_len);
+	int			(*bind_add)(struct sock *sk,
+					struct sockaddr *addr, int addr_len);
 
 	int			(*backlog_rcv) (struct sock *sk,
 						struct sk_buff *skb);
@@ -2698,4 +2700,6 @@ void sock_set_reuseaddr(struct sock *sk);
 void sock_set_reuseport(struct sock *sk);
 void sock_set_sndtimeo(struct sock *sk, s64 secs);
 
+int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len);
+
 #endif	/* _SOCK_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index 2ca3425b519c..61ec573221a6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3712,3 +3712,11 @@ bool sk_busy_loop_end(void *p, unsigned long start_time)
 }
 EXPORT_SYMBOL(sk_busy_loop_end);
 #endif /* CONFIG_NET_RX_BUSY_POLL */
+
+int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len)
+{
+	if (!sk->sk_prot->bind_add)
+		return -EOPNOTSUPP;
+	return sk->sk_prot->bind_add(sk, addr, addr_len);
+}
+EXPORT_SYMBOL(sock_bind_add);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6e745ac3c4a5..d57e1a002ffc 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1052,6 +1052,18 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	return err;
 }
 
+static int sctp_bind_add(struct sock *sk, struct sockaddr *addrs,
+		int addrlen)
+{
+	int err;
+
+	lock_sock(sk);
+	err = sctp_setsockopt_bindx_kernel(sk, addrs, addrlen,
+					   SCTP_BINDX_ADD_ADDR);
+	release_sock(sk);
+	return err;
+}
+
 static int sctp_connect_new_asoc(struct sctp_endpoint *ep,
 				 const union sctp_addr *daddr,
 				 const struct sctp_initmsg *init,
@@ -9620,6 +9632,7 @@ struct proto sctp_prot = {
 	.sendmsg     =	sctp_sendmsg,
 	.recvmsg     =	sctp_recvmsg,
 	.bind        =	sctp_bind,
+	.bind_add    =  sctp_bind_add,
 	.backlog_rcv =	sctp_backlog_rcv,
 	.hash        =	sctp_hash,
 	.unhash      =	sctp_unhash,
@@ -9662,6 +9675,7 @@ struct proto sctpv6_prot = {
 	.sendmsg	= sctp_sendmsg,
 	.recvmsg	= sctp_recvmsg,
 	.bind		= sctp_bind,
+	.bind_add	= sctp_bind_add,
 	.backlog_rcv	= sctp_backlog_rcv,
 	.hash		= sctp_hash,
 	.unhash		= sctp_unhash,
-- 
cgit v1.2.3-58-ga151