[PATCH v9 net-next 2/7] net: add low latency socket poll

From: Eliezer Tamir
Date: Wed Jun 05 2013 - 06:34:33 EST

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@xxxxxxxxx>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@xxxxxxxxx>
Tested-by: Willem de Bruijn <willemb@xxxxxxxxxx>
Signed-off-by: Eliezer Tamir <eliezer.tamir@xxxxxxxxxxxxxxx>
---

Documentation/sysctl/net.txt | 7 ++
include/linux/netdevice.h | 3 +
include/linux/skbuff.h | 8 ++
include/net/ll_poll.h | 148 ++++++++++++++++++++++++++++++++++++++++++
include/net/sock.h | 4 +
include/uapi/linux/snmp.h | 1
net/Kconfig | 12 +++
net/core/skbuff.c | 4 +
net/core/sock.c | 6 ++
net/core/sysctl_net_core.c | 10 +++
net/ipv4/proc.c | 1
net/socket.c | 6 ++
12 files changed, 208 insertions(+), 2 deletions(-)
create mode 100644 include/net/ll_poll.h

diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index c1f8640..85ab72d 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -50,6 +50,13 @@ The maximum number of packets that kernel can handle on a NAPI interrupt,
it's a Per-CPU variable.
Default: 64

+low_latency_poll
+----------------
+Low latency busy poll timeout. (needs CONFIG_NET_LL_RX_POLL)
+Approximate time in us to spin waiting for packets on the device queue.
+Recommended value is 50. May increase power usage.
+Default: 0 (off)
+
rmem_default
------------

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 39bbd46..2ecb96d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -972,6 +972,9 @@ struct net_device_ops {
gfp_t gfp);
void (*ndo_netpoll_cleanup)(struct net_device *dev);
#endif
+#ifdef CONFIG_NET_LL_RX_POLL
+ int (*ndo_ll_poll)(struct napi_struct *dev);
+#endif
int (*ndo_set_vf_mac)(struct net_device *dev,
int queue, u8 *mac);
int (*ndo_set_vf_vlan)(struct net_device *dev,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b999790..908246b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -386,6 +386,7 @@ typedef unsigned char *sk_buff_data_t;
* @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS
* @dma_cookie: a cookie to one of several possible DMA operations
* done by skb DMA functions
+ * @napi_id: id of the NAPI struct this skb came from
* @secmark: security marking
* @mark: Generic packet mark
* @dropcount: total number of sk_receive_queue overflows
@@ -500,8 +501,11 @@ struct sk_buff {
/* 7/9 bit hole (depending on ndisc_nodetype presence) */
kmemcheck_bitfield_end(flags2);

-#ifdef CONFIG_NET_DMA
- dma_cookie_t dma_cookie;
+#if defined CONFIG_NET_DMA || defined CONFIG_NET_LL_RX_POLL
+ union {
+ unsigned int napi_id;
+ dma_cookie_t dma_cookie;
+ };
#endif
#ifdef CONFIG_NETWORK_SECMARK
__u32 secmark;
diff --git a/include/net/ll_poll.h b/include/net/ll_poll.h
new file mode 100644
index 0000000..bc262f8
--- /dev/null
+++ b/include/net/ll_poll.h
@@ -0,0 +1,148 @@
+/*
+ * Low Latency Sockets
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * Author: Eliezer Tamir
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@xxxxxxxxxxxxxxxxxxxxx>
+ */
+
+/*
+ * For now this depends on CONFIG_X86_TSC
+ */
+
+#ifndef _LINUX_NET_LL_POLL_H
+#define _LINUX_NET_LL_POLL_H
+
+#include <linux/netdevice.h>
+#include <net/ip.h>
+
+#ifdef CONFIG_NET_LL_RX_POLL
+
+struct napi_struct;
+extern unsigned long sysctl_net_ll_poll __read_mostly;
+
+/* return values from ndo_ll_poll */
+#define LL_FLUSH_FAILED -1
+#define LL_FLUSH_BUSY -2
+
+/* we don't mind a ~2.5% imprecision */
+#define TSC_MHZ (tsc_khz >> 10)
+
+static inline cycles_t ll_end_time(void)
+{
+ return TSC_MHZ * ACCESS_ONCE(sysctl_net_ll_poll) + get_cycles();
+}
+
+static inline bool sk_valid_ll(struct sock *sk)
+{
+ return sysctl_net_ll_poll && sk->sk_napi_id &&
+ !need_resched() && !signal_pending(current);
+}
+
+static inline bool can_poll_ll(cycles_t end_time)
+{
+ return !time_after((unsigned long)get_cycles(),
+ (unsigned long)end_time);
+}
+
+static inline bool sk_poll_ll(struct sock *sk, int nonblock)
+{
+ cycles_t end_time = ll_end_time();
+ const struct net_device_ops *ops;
+ struct napi_struct *napi;
+ int rc = false;
+
+ /*
+ * rcu read lock for napi hash
+ * bh so we don't race with net_rx_action
+ */
+ rcu_read_lock_bh();
+
+ napi = napi_by_id(sk->sk_napi_id);
+ if (!napi)
+ goto out;
+
+ ops = napi->dev->netdev_ops;
+ if (!ops->ndo_ll_poll)
+ goto out;
+
+ do {
+
+ rc = ops->ndo_ll_poll(napi);
+
+ if (rc == LL_FLUSH_FAILED)
+ break; /* permanent failure */
+
+ if (rc > 0)
+ /* local bh are disabled so it is ok to use _BH */
+ NET_ADD_STATS_BH(sock_net(sk),
+ LINUX_MIB_LOWLATENCYRXPACKETS, rc);
+
+ } while (skb_queue_empty(&sk->sk_receive_queue)
+ && can_poll_ll(end_time) && !nonblock);
+
+ rc = !skb_queue_empty(&sk->sk_receive_queue);
+out:
+ rcu_read_unlock_bh();
+ return rc;
+}
+
+/* used in the NIC receive handler to mark the skb */
+static inline void skb_mark_ll(struct sk_buff *skb, struct napi_struct *napi)
+{
+ skb->napi_id = napi->napi_id;
+}
+
+/* used in the protocol hanlder to propagate the napi_id to the socket */
+static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb)
+{
+ sk->sk_napi_id = skb->napi_id;
+}
+
+#else /* CONFIG_NET_LL_RX_POLL */
+
+static inline cycles_t ll_end_time(void)
+{
+ return 0;
+}
+
+static inline bool sk_valid_ll(struct sock *sk)
+{
+ return false;
+}
+
+static inline bool sk_poll_ll(struct sock *sk, int nonblock)
+{
+ return false;
+}
+
+static inline void skb_mark_ll(struct sk_buff *skb, struct napi_struct *napi)
+{
+}
+
+static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb)
+{
+}
+
+static inline bool can_poll_ll(cycles_t end_time)
+{
+ return false;
+}
+
+#endif /* CONFIG_NET_LL_RX_POLL */
+#endif /* _LINUX_NET_LL_POLL_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 66772cf..ac8e181 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -229,6 +229,7 @@ struct cg_proto;
* @sk_omem_alloc: "o" is "option" or "other"
* @sk_wmem_queued: persistent queue size
* @sk_forward_alloc: space allocated forward
+ * @sk_napi_id: id of the last napi context to receive data for sk
* @sk_allocation: allocation mode
* @sk_sndbuf: size of send buffer in bytes
* @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
@@ -325,6 +326,9 @@ struct sock {
#ifdef CONFIG_RPS
__u32 sk_rxhash;
#endif
+#ifdef CONFIG_NET_LL_RX_POLL
+ unsigned int sk_napi_id;
+#endif
atomic_t sk_drops;
int sk_rcvbuf;

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index df2e8b4..26cbf76 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -253,6 +253,7 @@ enum
LINUX_MIB_TCPFASTOPENLISTENOVERFLOW, /* TCPFastOpenListenOverflow */
LINUX_MIB_TCPFASTOPENCOOKIEREQD, /* TCPFastOpenCookieReqd */
LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */
+ LINUX_MIB_LOWLATENCYRXPACKETS, /* LowLatencyRxPackets */
__LINUX_MIB_MAX
};

diff --git a/net/Kconfig b/net/Kconfig
index 523e43e..d6a9ce6 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 6b1b52c..73ef74d 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 6ba327d..804fd5b 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 741db5fc..4b48f39 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 2a5bf86..6577a11 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 6b94633..721f4e7 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,

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/