Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Support more Realtek wireless chips, from Jes Sorenson.

   2) New BPF types for per-cpu hash and arrap maps, from Alexei
      Starovoitov.

   3) Make several TCP sysctls per-namespace, from Nikolay Borisov.

   4) Allow the use of SO_REUSEPORT in order to do per-thread processing
   of incoming TCP/UDP connections.  The muxing can be done using a
   BPF program which hashes the incoming packet.  From Craig Gallek.

   5) Add a multiplexer for TCP streams, to provide a messaged based
      interface.  BPF programs can be used to determine the message
      boundaries.  From Tom Herbert.

   6) Add 802.1AE MACSEC support, from Sabrina Dubroca.

   7) Avoid factorial complexity when taking down an inetdev interface
      with lots of configured addresses.  We were doing things like
      traversing the entire address less for each address removed, and
      flushing the entire netfilter conntrack table for every address as
      well.

   8) Add and use SKB bulk free infrastructure, from Jesper Brouer.

   9) Allow offloading u32 classifiers to hardware, and implement for
      ixgbe, from John Fastabend.

  10) Allow configuring IRQ coalescing parameters on a per-queue basis,
      from Kan Liang.

  11) Extend ethtool so that larger link mode masks can be supported.
      From David Decotigny.

  12) Introduce devlink, which can be used to configure port link types
      (ethernet vs Infiniband, etc.), port splitting, and switch device
      level attributes as a whole.  From Jiri Pirko.

  13) Hardware offload support for flower classifiers, from Amir Vadai.

  14) Add "Local Checksum Offload".  Basically, for a tunneled packet
      the checksum of the outer header is 'constant' (because with the
      checksum field filled into the inner protocol header, the payload
      of the outer frame checksums to 'zero'), and we can take advantage
      of that in various ways.  From Edward Cree"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
  bonding: fix bond_get_stats()
  net: bcmgenet: fix dma api length mismatch
  net/mlx4_core: Fix backward compatibility on VFs
  phy: mdio-thunder: Fix some Kconfig typos
  lan78xx: add ndo_get_stats64
  lan78xx: handle statistics counter rollover
  RDS: TCP: Remove unused constant
  RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
  net: smc911x: convert pxa dma to dmaengine
  team: remove duplicate set of flag IFF_MULTICAST
  bonding: remove duplicate set of flag IFF_MULTICAST
  net: fix a comment typo
  ethernet: micrel: fix some error codes
  ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
  bpf, dst: add and use dst_tclassid helper
  bpf: make skb->tc_classid also readable
  net: mvneta: bm: clarify dependencies
  cls_bpf: reset class and reuse major in da
  ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
  ldmvsw: Add ldmvsw.c driver code
  ...

1 files changed, 134 insertions, 12 deletions

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 9d6ddbacd875..61ed2a8764ba 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -37,7 +37,6 @@
 #include <net/tcp.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
-#include <net/tcp.h>
 
 #include "rds.h"
 #include "tcp.h"
@@ -53,7 +52,34 @@ static LIST_HEAD(rds_tcp_conn_list);
 
 static struct kmem_cache *rds_tcp_conn_slab;
 
-#define RDS_TCP_DEFAULT_BUFSIZE (128 * 1024)
+static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *fpos);
+
+int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF;
+int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF;
+
+static struct ctl_table rds_tcp_sysctl_table[] = {
+#define	RDS_TCP_SNDBUF	0
+	{
+		.procname       = "rds_tcp_sndbuf",
+		/* data is per-net pointer */
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = rds_tcp_skbuf_handler,
+		.extra1		= &rds_tcp_min_sndbuf,
+	},
+#define	RDS_TCP_RCVBUF	1
+	{
+		.procname       = "rds_tcp_rcvbuf",
+		/* data is per-net pointer */
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = rds_tcp_skbuf_handler,
+		.extra1		= &rds_tcp_min_rcvbuf,
+	},
+	{ }
+};
 
 /* doing it this way avoids calling tcp_sk() */
 void rds_tcp_nonagle(struct socket *sock)
@@ -67,15 +93,6 @@ void rds_tcp_nonagle(struct socket *sock)
 	set_fs(oldfs);
 }
 
-/* All module specific customizations to the RDS-TCP socket should be done in
- * rds_tcp_tune() and applied after socket creation. In general these
- * customizations should be tunable via module_param()
- */
-void rds_tcp_tune(struct socket *sock)
-{
-	rds_tcp_nonagle(sock);
-}
-
 u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc)
 {
 	return tcp_sk(tc->t_sock->sk)->snd_nxt;
@@ -273,8 +290,34 @@ static int rds_tcp_netid;
 struct rds_tcp_net {
 	struct socket *rds_tcp_listen_sock;
 	struct work_struct rds_tcp_accept_w;
+	struct ctl_table_header *rds_tcp_sysctl;
+	struct ctl_table *ctl_table;
+	int sndbuf_size;
+	int rcvbuf_size;
 };
 
+/* All module specific customizations to the RDS-TCP socket should be done in
+ * rds_tcp_tune() and applied after socket creation.
+ */
+void rds_tcp_tune(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
+	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+
+	rds_tcp_nonagle(sock);
+	lock_sock(sk);
+	if (rtn->sndbuf_size > 0) {
+		sk->sk_sndbuf = rtn->sndbuf_size;
+		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
+	}
+	if (rtn->rcvbuf_size > 0) {
+		sk->sk_sndbuf = rtn->rcvbuf_size;
+		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
+	}
+	release_sock(sk);
+}
+
 static void rds_tcp_accept_worker(struct work_struct *work)
 {
 	struct rds_tcp_net *rtn = container_of(work,
@@ -296,20 +339,60 @@ void rds_tcp_accept_work(struct sock *sk)
 static __net_init int rds_tcp_init_net(struct net *net)
 {
 	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+	struct ctl_table *tbl;
+	int err = 0;
 
+	memset(rtn, 0, sizeof(*rtn));
+
+	/* {snd, rcv}buf_size default to 0, which implies we let the
+	 * stack pick the value, and permit auto-tuning of buffer size.
+	 */
+	if (net == &init_net) {
+		tbl = rds_tcp_sysctl_table;
+	} else {
+		tbl = kmemdup(rds_tcp_sysctl_table,
+			      sizeof(rds_tcp_sysctl_table), GFP_KERNEL);
+		if (!tbl) {
+			pr_warn("could not set allocate syctl table\n");
+			return -ENOMEM;
+		}
+		rtn->ctl_table = tbl;
+	}
+	tbl[RDS_TCP_SNDBUF].data = &rtn->sndbuf_size;
+	tbl[RDS_TCP_RCVBUF].data = &rtn->rcvbuf_size;
+	rtn->rds_tcp_sysctl = register_net_sysctl(net, "net/rds/tcp", tbl);
+	if (!rtn->rds_tcp_sysctl) {
+		pr_warn("could not register sysctl\n");
+		err = -ENOMEM;
+		goto fail;
+	}
 	rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net);
 	if (!rtn->rds_tcp_listen_sock) {
 		pr_warn("could not set up listen sock\n");
-		return -EAFNOSUPPORT;
+		unregister_net_sysctl_table(rtn->rds_tcp_sysctl);
+		rtn->rds_tcp_sysctl = NULL;
+		err = -EAFNOSUPPORT;
+		goto fail;
 	}
 	INIT_WORK(&rtn->rds_tcp_accept_w, rds_tcp_accept_worker);
 	return 0;
+
+fail:
+	if (net != &init_net)
+		kfree(tbl);
+	return err;
 }
 
 static void __net_exit rds_tcp_exit_net(struct net *net)
 {
 	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
 
+	if (rtn->rds_tcp_sysctl)
+		unregister_net_sysctl_table(rtn->rds_tcp_sysctl);
+
+	if (net != &init_net && rtn->ctl_table)
+		kfree(rtn->ctl_table);
+
 	/* If rds_tcp_exit_net() is called as a result of netns deletion,
 	 * the rds_tcp_kill_sock() device notifier would already have cleaned
 	 * up the listen socket, thus there is no work to do in this function.
@@ -384,6 +467,45 @@ static struct notifier_block rds_tcp_dev_notifier = {
 	.priority = -10, /* must be called after other network notifiers */
 };
 
+/* when sysctl is used to modify some kernel socket parameters,this
+ * function  resets the RDS connections in that netns  so that we can
+ * restart with new parameters.  The assumption is that such reset
+ * events are few and far-between.
+ */
+static void rds_tcp_sysctl_reset(struct net *net)
+{
+	struct rds_tcp_connection *tc, *_tc;
+
+	spin_lock_irq(&rds_tcp_conn_lock);
+	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
+		struct net *c_net = read_pnet(&tc->conn->c_net);
+
+		if (net != c_net || !tc->t_sock)
+			continue;
+
+		rds_conn_drop(tc->conn); /* reconnect with new parameters */
+	}
+	spin_unlock_irq(&rds_tcp_conn_lock);
+}
+
+static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *fpos)
+{
+	struct net *net = current->nsproxy->net_ns;
+	int err;
+
+	err = proc_dointvec_minmax(ctl, write, buffer, lenp, fpos);
+	if (err < 0) {
+		pr_warn("Invalid input. Must be >= %d\n",
+			*(int *)(ctl->extra1));
+		return err;
+	}
+	if (write)
+		rds_tcp_sysctl_reset(net);
+	return 0;
+}
+
 static void rds_tcp_exit(void)
 {
 	rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);