net: add low latency socket poll

Adds an ndo_ll_poll method and the code that supports it.
This method can be used by low latency applications to busy-poll
Ethernet device queues directly from the socket code.
sysctl_net_ll_poll controls how many microseconds to poll.
Default is zero (disabled).
Individual protocol support will be added by subsequent patches.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Eliezer Tamir <eliezer.tamir@linux.intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Tested-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 39 insertions, 0 deletions

diff --git a/net/Kconfig b/net/Kconfig
index 523e43e6da1b..d6a9ce6e1800 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -243,6 +243,18 @@ config NETPRIO_CGROUP
 	  Cgroup subsystem for use in assigning processes to network priorities on
 	  a per-interface basis
 
+config NET_LL_RX_POLL
+	bool "Low Latency Receive Poll"
+	depends on X86_TSC
+	default n
+	---help---
+	  Support Low Latency Receive Queue Poll.
+	  (For network card drivers which support this option.)
+	  When waiting for data in read or poll call directly into the the device driver
+	  to flush packets which may be pending on the device queues into the stack.
+
+	  If unsure, say N.
+
 config BQL
 	boolean
 	depends on SYSFS
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 73f57a0e1523..4a4181e16c1a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -733,6 +733,10 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->vlan_tci		= old->vlan_tci;
 
 	skb_copy_secmark(new, old);
+
+#ifdef CONFIG_NET_LL_RX_POLL
+	new->napi_id	= old->napi_id;
+#endif
 }
 
 /*
diff --git a/net/core/sock.c b/net/core/sock.c
index 88868a9d21da..788c0da5eed1 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -139,6 +139,8 @@
 #include <net/tcp.h>
 #endif
 
+#include <net/ll_poll.h>
+
 static DEFINE_MUTEX(proto_list_mutex);
 static LIST_HEAD(proto_list);
 
@@ -2284,6 +2286,10 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 	sk->sk_stamp = ktime_set(-1L, 0);
 
+#ifdef CONFIG_NET_LL_RX_POLL
+	sk->sk_napi_id		=	0;
+#endif
+
 	/*
 	 * Before updating sk_refcnt, we must commit prior changes to memory
 	 * (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 741db5fc7806..4b48f39582b0 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -19,6 +19,7 @@
 #include <net/ip.h>
 #include <net/sock.h>
 #include <net/net_ratelimit.h>
+#include <net/ll_poll.h>
 
 static int one = 1;
 
@@ -284,6 +285,15 @@ static struct ctl_table net_core_table[] = {
 		.proc_handler	= flow_limit_table_len_sysctl
 	},
 #endif /* CONFIG_NET_FLOW_LIMIT */
+#ifdef CONFIG_NET_LL_RX_POLL
+	{
+		.procname	= "low_latency_poll",
+		.data		= &sysctl_net_ll_poll,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax
+	},
+#endif
 #endif /* CONFIG_NET */
 	{
 		.procname	= "netdev_budget",
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 2a5bf86d2415..6577a1149a47 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -273,6 +273,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
 	SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
 	SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
+	SNMP_MIB_ITEM("LowLatencyRxPackets", LINUX_MIB_LOWLATENCYRXPACKETS),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/socket.c b/net/socket.c
index 3ebdcb805c51..21fd29f63ed2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -104,6 +104,12 @@
 #include <linux/route.h>
 #include <linux/sockios.h>
 #include <linux/atalk.h>
+#include <net/ll_poll.h>
+
+#ifdef CONFIG_NET_LL_RX_POLL
+unsigned long sysctl_net_ll_poll __read_mostly;
+EXPORT_SYMBOL_GPL(sysctl_net_ll_poll);
+#endif
 
 static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
 static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,