Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 06021292 authored by Eliezer Tamir's avatar Eliezer Tamir Committed by David S. Miller
Browse files

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: default avatarAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: default avatarJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: default avatarEliezer Tamir <eliezer.tamir@linux.intel.com>
Acked-by: default avatarEric Dumazet <edumazet@google.com>
Tested-by: default avatarWillem de Bruijn <willemb@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent af12fa6e

Documentation/sysctl/net.txt

+7 −0
Original line number Diff line number Diff line
@@ -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

------------

include/linux/netdevice.h

+3 −0
Original line number Diff line number Diff line
@@ -971,6 +971,9 @@ struct net_device_ops { 
						     struct netpoll_info *info,

						     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);

include/linux/skbuff.h

+6 −2
Original line number Diff line number Diff line
@@ -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

#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;

include/net/ll_poll.h

0 → 100644
+148 −0
Original line number Diff line number Diff line 
/*

 * 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@lists.sourceforge.net>

 */



/*

 * 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 */

include/net/sock.h

+4 −0
Original line number Diff line number Diff line
@@ -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,
@@ -324,6 +325,9 @@ struct sock { 
	int			sk_forward_alloc;

#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;