2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* INET An implementation of the TCP/IP protocol suite for the LINUX
|
|
|
|
* operating system. INET is implemented using the BSD Socket
|
|
|
|
* interface as the means of communication with the user level.
|
|
|
|
*
|
|
|
|
* Definitions for the Interfaces handler.
|
|
|
|
*
|
|
|
|
* Version: @(#)dev.h 1.0.10 08/12/93
|
|
|
|
*
|
2005-05-06 07:16:16 +08:00
|
|
|
* Authors: Ross Biro
|
2005-04-17 06:20:36 +08:00
|
|
|
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
|
|
|
|
* Corey Minyard <wf-rch!minyard@relay.EU.net>
|
|
|
|
* Donald J. Becker, <becker@cesdis.gsfc.nasa.gov>
|
2008-10-14 10:01:08 +08:00
|
|
|
* Alan Cox, <alan@lxorguk.ukuu.org.uk>
|
2005-04-17 06:20:36 +08:00
|
|
|
* Bjorn Ekwall. <bj0rn@blox.se>
|
|
|
|
* Pekka Riikonen <priikone@poseidon.pspt.fi>
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
*
|
|
|
|
* Moved to /usr/include/linux for NET3
|
|
|
|
*/
|
|
|
|
#ifndef _LINUX_NETDEVICE_H
|
|
|
|
#define _LINUX_NETDEVICE_H
|
|
|
|
|
|
|
|
#include <linux/if.h>
|
|
|
|
#include <linux/if_ether.h>
|
|
|
|
#include <linux/if_packet.h>
|
2010-02-10 09:43:46 +08:00
|
|
|
#include <linux/if_link.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#ifdef __KERNEL__
|
2011-08-25 21:35:03 +08:00
|
|
|
#include <linux/pm_qos.h>
|
2006-12-04 12:15:30 +08:00
|
|
|
#include <linux/timer.h>
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
#include <linux/delay.h>
|
2011-07-27 07:09:06 +08:00
|
|
|
#include <linux/atomic.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/cache.h>
|
|
|
|
#include <asm/byteorder.h>
|
|
|
|
|
|
|
|
#include <linux/device.h>
|
|
|
|
#include <linux/percpu.h>
|
2009-05-07 07:52:51 +08:00
|
|
|
#include <linux/rculist.h>
|
2006-06-18 12:24:58 +08:00
|
|
|
#include <linux/dmaengine.h>
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
#include <linux/workqueue.h>
|
2011-11-29 00:33:09 +08:00
|
|
|
#include <linux/dynamic_queue_limits.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-04-20 12:49:28 +08:00
|
|
|
#include <linux/ethtool.h>
|
2007-09-12 20:57:09 +08:00
|
|
|
#include <net/net_namespace.h>
|
2008-10-07 21:45:02 +08:00
|
|
|
#include <net/dsa.h>
|
2008-11-25 17:02:08 +08:00
|
|
|
#ifdef CONFIG_DCB
|
2008-11-21 12:52:10 +08:00
|
|
|
#include <net/dcbnl.h>
|
|
|
|
#endif
|
2011-11-22 13:10:51 +08:00
|
|
|
#include <net/netprio_cgroup.h>
|
2007-09-12 20:57:09 +08:00
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
#include <linux/netdev_features.h>
|
|
|
|
|
2005-06-23 13:05:31 +08:00
|
|
|
struct netpoll_info;
|
2010-07-17 16:49:36 +08:00
|
|
|
struct phy_device;
|
2007-04-24 03:20:05 +08:00
|
|
|
/* 802.11 specific */
|
|
|
|
struct wireless_dev;
|
2005-04-17 06:20:36 +08:00
|
|
|
/* source back-compat hooks */
|
|
|
|
#define SET_ETHTOOL_OPS(netdev,ops) \
|
|
|
|
( (netdev)->ethtool_ops = (ops) )
|
|
|
|
|
2010-07-22 10:50:21 +08:00
|
|
|
/* hardware address assignment types */
|
|
|
|
#define NET_ADDR_PERM 0 /* address is permanent (default) */
|
|
|
|
#define NET_ADDR_RANDOM 1 /* address is generated randomly */
|
|
|
|
#define NET_ADDR_STOLEN 2 /* address is stolen from other device */
|
|
|
|
|
2009-11-15 15:20:12 +08:00
|
|
|
/* Backlog congestion levels */
|
|
|
|
#define NET_RX_SUCCESS 0 /* keep 'em coming, baby */
|
|
|
|
#define NET_RX_DROP 1 /* packet dropped */
|
|
|
|
|
2009-11-10 14:14:14 +08:00
|
|
|
/*
|
|
|
|
* Transmit return codes: transmit return codes originate from three different
|
|
|
|
* namespaces:
|
|
|
|
*
|
|
|
|
* - qdisc return codes
|
|
|
|
* - driver transmit return codes
|
|
|
|
* - errno values
|
|
|
|
*
|
|
|
|
* Drivers are allowed to return any one of those in their hard_start_xmit()
|
|
|
|
* function. Real network devices commonly used with qdiscs should only return
|
|
|
|
* the driver transmit return codes though - when qdiscs are used, the actual
|
|
|
|
* transmission happens asynchronously, so the value is not propagated to
|
|
|
|
* higher layers. Virtual network devices transmit synchronously, in this case
|
|
|
|
* the driver transmit return codes are consumed by dev_queue_xmit(), all
|
|
|
|
* others are propagated to higher layers.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* qdisc ->enqueue() return codes. */
|
|
|
|
#define NET_XMIT_SUCCESS 0x00
|
2009-11-15 15:20:12 +08:00
|
|
|
#define NET_XMIT_DROP 0x01 /* skb dropped */
|
|
|
|
#define NET_XMIT_CN 0x02 /* congestion notification */
|
|
|
|
#define NET_XMIT_POLICED 0x03 /* skb is shot by police */
|
|
|
|
#define NET_XMIT_MASK 0x0f /* qdisc flags in net/sch_generic.h */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-11-14 21:21:36 +08:00
|
|
|
/* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It
|
|
|
|
* indicates that the device will soon be dropping packets, or already drops
|
|
|
|
* some packets of the same priority; prompting us to send less aggressively. */
|
2009-11-10 14:14:14 +08:00
|
|
|
#define net_xmit_eval(e) ((e) == NET_XMIT_CN ? 0 : (e))
|
2005-04-17 06:20:36 +08:00
|
|
|
#define net_xmit_errno(e) ((e) != NET_XMIT_CN ? -ENOBUFS : 0)
|
|
|
|
|
2009-09-01 03:50:40 +08:00
|
|
|
/* Driver transmit return codes */
|
2009-11-15 15:20:12 +08:00
|
|
|
#define NETDEV_TX_MASK 0xf0
|
2009-11-10 14:14:14 +08:00
|
|
|
|
2009-09-01 03:50:40 +08:00
|
|
|
enum netdev_tx {
|
2009-11-10 14:14:14 +08:00
|
|
|
__NETDEV_TX_MIN = INT_MIN, /* make sure enum is signed */
|
2009-11-15 15:20:12 +08:00
|
|
|
NETDEV_TX_OK = 0x00, /* driver took care of packet */
|
|
|
|
NETDEV_TX_BUSY = 0x10, /* driver tx path was busy*/
|
|
|
|
NETDEV_TX_LOCKED = 0x20, /* driver tx lock was already taken */
|
2009-09-01 03:50:40 +08:00
|
|
|
};
|
|
|
|
typedef enum netdev_tx netdev_tx_t;
|
|
|
|
|
2009-11-15 15:20:12 +08:00
|
|
|
/*
|
|
|
|
* Current order: NETDEV_TX_MASK > NET_XMIT_MASK >= 0 is significant;
|
|
|
|
* hard_start_xmit() return < NET_XMIT_MASK means skb was consumed.
|
|
|
|
*/
|
|
|
|
static inline bool dev_xmit_complete(int rc)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Positive cases with an skb consumed by a driver:
|
|
|
|
* - successful transmission (rc == NETDEV_TX_OK)
|
|
|
|
* - error while transmitting (rc < 0)
|
|
|
|
* - error while queueing to a different device (rc & NET_XMIT_MASK)
|
|
|
|
*/
|
|
|
|
if (likely(rc < NET_XMIT_MASK))
|
|
|
|
return true;
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#define MAX_ADDR_LEN 32 /* Largest hardware address length */
|
|
|
|
|
2011-02-27 06:39:12 +08:00
|
|
|
/* Initial net device group. All devices belong to group 0 by default. */
|
|
|
|
#define INIT_NETDEV_GROUP 0
|
|
|
|
|
2008-06-28 10:54:54 +08:00
|
|
|
#ifdef __KERNEL__
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Compute the worst case header length according to the protocols
|
|
|
|
* used.
|
|
|
|
*/
|
2009-02-06 13:26:19 +08:00
|
|
|
|
2011-11-25 22:40:26 +08:00
|
|
|
#if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
|
2008-05-13 11:17:33 +08:00
|
|
|
# if defined(CONFIG_MAC80211_MESH)
|
|
|
|
# define LL_MAX_HEADER 128
|
|
|
|
# else
|
|
|
|
# define LL_MAX_HEADER 96
|
|
|
|
# endif
|
2011-11-25 22:40:26 +08:00
|
|
|
#elif IS_ENABLED(CONFIG_TR)
|
2008-05-13 11:17:33 +08:00
|
|
|
# define LL_MAX_HEADER 48
|
2005-04-17 06:20:36 +08:00
|
|
|
#else
|
2008-05-13 11:17:33 +08:00
|
|
|
# define LL_MAX_HEADER 32
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
2011-11-25 22:40:26 +08:00
|
|
|
#if !IS_ENABLED(CONFIG_NET_IPIP) && !IS_ENABLED(CONFIG_NET_IPGRE) && \
|
|
|
|
!IS_ENABLED(CONFIG_IPV6_SIT) && !IS_ENABLED(CONFIG_IPV6_TUNNEL)
|
2005-04-17 06:20:36 +08:00
|
|
|
#define MAX_HEADER LL_MAX_HEADER
|
|
|
|
#else
|
|
|
|
#define MAX_HEADER (LL_MAX_HEADER + 48)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
2010-06-08 15:19:54 +08:00
|
|
|
* Old network device statistics. Fields are native words
|
|
|
|
* (unsigned long) so they can be read and written atomically.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2009-02-06 13:26:19 +08:00
|
|
|
|
2009-11-05 01:50:58 +08:00
|
|
|
struct net_device_stats {
|
2010-07-09 17:11:52 +08:00
|
|
|
unsigned long rx_packets;
|
|
|
|
unsigned long tx_packets;
|
|
|
|
unsigned long rx_bytes;
|
|
|
|
unsigned long tx_bytes;
|
|
|
|
unsigned long rx_errors;
|
|
|
|
unsigned long tx_errors;
|
|
|
|
unsigned long rx_dropped;
|
|
|
|
unsigned long tx_dropped;
|
|
|
|
unsigned long multicast;
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned long collisions;
|
|
|
|
unsigned long rx_length_errors;
|
2010-07-09 17:11:52 +08:00
|
|
|
unsigned long rx_over_errors;
|
|
|
|
unsigned long rx_crc_errors;
|
|
|
|
unsigned long rx_frame_errors;
|
|
|
|
unsigned long rx_fifo_errors;
|
|
|
|
unsigned long rx_missed_errors;
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned long tx_aborted_errors;
|
|
|
|
unsigned long tx_carrier_errors;
|
|
|
|
unsigned long tx_fifo_errors;
|
|
|
|
unsigned long tx_heartbeat_errors;
|
|
|
|
unsigned long tx_window_errors;
|
|
|
|
unsigned long rx_compressed;
|
|
|
|
unsigned long tx_compressed;
|
|
|
|
};
|
|
|
|
|
2010-06-08 15:19:54 +08:00
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Media selection options. */
|
|
|
|
enum {
|
|
|
|
IF_PORT_UNKNOWN = 0,
|
|
|
|
IF_PORT_10BASE2,
|
|
|
|
IF_PORT_10BASET,
|
|
|
|
IF_PORT_AUI,
|
|
|
|
IF_PORT_100BASET,
|
|
|
|
IF_PORT_100BASETX,
|
|
|
|
IF_PORT_100BASEFX
|
|
|
|
};
|
|
|
|
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
|
|
|
|
#include <linux/cache.h>
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
|
2011-11-17 11:13:26 +08:00
|
|
|
#ifdef CONFIG_RPS
|
|
|
|
#include <linux/jump_label.h>
|
|
|
|
extern struct jump_label_key rps_needed;
|
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
struct neighbour;
|
|
|
|
struct neigh_parms;
|
|
|
|
struct sk_buff;
|
|
|
|
|
2009-05-05 10:48:28 +08:00
|
|
|
struct netdev_hw_addr {
|
|
|
|
struct list_head list;
|
|
|
|
unsigned char addr[MAX_ADDR_LEN];
|
|
|
|
unsigned char type;
|
2009-05-23 07:22:17 +08:00
|
|
|
#define NETDEV_HW_ADDR_T_LAN 1
|
|
|
|
#define NETDEV_HW_ADDR_T_SAN 2
|
|
|
|
#define NETDEV_HW_ADDR_T_SLAVE 3
|
|
|
|
#define NETDEV_HW_ADDR_T_UNICAST 4
|
2010-04-02 05:22:57 +08:00
|
|
|
#define NETDEV_HW_ADDR_T_MULTICAST 5
|
2009-05-23 07:22:17 +08:00
|
|
|
bool synced;
|
2010-04-02 05:22:57 +08:00
|
|
|
bool global_use;
|
2010-09-20 02:24:02 +08:00
|
|
|
int refcount;
|
2009-05-05 10:48:28 +08:00
|
|
|
struct rcu_head rcu_head;
|
|
|
|
};
|
|
|
|
|
2009-06-17 09:12:19 +08:00
|
|
|
struct netdev_hw_addr_list {
|
|
|
|
struct list_head list;
|
|
|
|
int count;
|
|
|
|
};
|
|
|
|
|
2010-04-02 05:22:57 +08:00
|
|
|
#define netdev_hw_addr_list_count(l) ((l)->count)
|
|
|
|
#define netdev_hw_addr_list_empty(l) (netdev_hw_addr_list_count(l) == 0)
|
|
|
|
#define netdev_hw_addr_list_for_each(ha, l) \
|
|
|
|
list_for_each_entry(ha, &(l)->list, list)
|
2010-01-26 05:36:10 +08:00
|
|
|
|
2010-04-02 05:22:57 +08:00
|
|
|
#define netdev_uc_count(dev) netdev_hw_addr_list_count(&(dev)->uc)
|
|
|
|
#define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc)
|
|
|
|
#define netdev_for_each_uc_addr(ha, dev) \
|
|
|
|
netdev_hw_addr_list_for_each(ha, &(dev)->uc)
|
2010-02-05 02:22:25 +08:00
|
|
|
|
2010-04-02 05:22:57 +08:00
|
|
|
#define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc)
|
|
|
|
#define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc)
|
2010-04-08 07:40:09 +08:00
|
|
|
#define netdev_for_each_mc_addr(ha, dev) \
|
2010-04-02 05:22:57 +08:00
|
|
|
netdev_hw_addr_list_for_each(ha, &(dev)->mc)
|
2010-02-05 02:22:25 +08:00
|
|
|
|
2009-11-05 01:50:58 +08:00
|
|
|
struct hh_cache {
|
2011-07-14 22:53:20 +08:00
|
|
|
u16 hh_len;
|
2011-07-13 15:51:10 +08:00
|
|
|
u16 __pad;
|
2006-12-08 07:08:17 +08:00
|
|
|
seqlock_t hh_lock;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* cached hardware header; allow for machine alignment needs. */
|
|
|
|
#define HH_DATA_MOD 16
|
|
|
|
#define HH_DATA_OFF(__len) \
|
2005-06-03 07:48:05 +08:00
|
|
|
(HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1))
|
2005-04-17 06:20:36 +08:00
|
|
|
#define HH_DATA_ALIGN(__len) \
|
|
|
|
(((__len)+(HH_DATA_MOD-1))&~(HH_DATA_MOD - 1))
|
|
|
|
unsigned long hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)];
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Reserve HH_DATA_MOD byte aligned hard_header_len, but at least that much.
|
|
|
|
* Alternative is:
|
|
|
|
* dev->hard_header_len ? (dev->hard_header_len +
|
|
|
|
* (HH_DATA_MOD - 1)) & ~(HH_DATA_MOD - 1) : 0
|
|
|
|
*
|
|
|
|
* We could use other alignment values, but we must maintain the
|
|
|
|
* relationship HH alignment <= LL alignment.
|
|
|
|
*/
|
|
|
|
#define LL_RESERVED_SPACE(dev) \
|
2008-05-13 11:48:31 +08:00
|
|
|
((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
|
2005-04-17 06:20:36 +08:00
|
|
|
#define LL_RESERVED_SPACE_EXTRA(dev,extra) \
|
2008-05-13 11:48:31 +08:00
|
|
|
((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-10-09 16:40:57 +08:00
|
|
|
struct header_ops {
|
|
|
|
int (*create) (struct sk_buff *skb, struct net_device *dev,
|
|
|
|
unsigned short type, const void *daddr,
|
|
|
|
const void *saddr, unsigned len);
|
|
|
|
int (*parse)(const struct sk_buff *skb, unsigned char *haddr);
|
|
|
|
int (*rebuild)(struct sk_buff *skb);
|
2011-07-13 14:28:12 +08:00
|
|
|
int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type);
|
2007-10-09 16:40:57 +08:00
|
|
|
void (*cache_update)(struct hh_cache *hh,
|
|
|
|
const struct net_device *dev,
|
|
|
|
const unsigned char *haddr);
|
|
|
|
};
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* These flag bits are private to the generic network queueing
|
|
|
|
* layer, they may not be explicitly referenced by any other
|
|
|
|
* code.
|
|
|
|
*/
|
|
|
|
|
2009-11-05 01:50:58 +08:00
|
|
|
enum netdev_state_t {
|
2005-04-17 06:20:36 +08:00
|
|
|
__LINK_STATE_START,
|
|
|
|
__LINK_STATE_PRESENT,
|
|
|
|
__LINK_STATE_NOCARRIER,
|
2006-03-21 09:09:11 +08:00
|
|
|
__LINK_STATE_LINKWATCH_PENDING,
|
|
|
|
__LINK_STATE_DORMANT,
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This structure holds at boot time configured netdevice settings. They
|
2009-02-06 13:26:19 +08:00
|
|
|
* are then used in the device probing.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
struct netdev_boot_setup {
|
|
|
|
char name[IFNAMSIZ];
|
|
|
|
struct ifmap map;
|
|
|
|
};
|
|
|
|
#define NETDEV_BOOT_SETUP_MAX 8
|
|
|
|
|
2005-08-16 13:18:02 +08:00
|
|
|
extern int __init netdev_boot_setup(char *str);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/*
|
|
|
|
* Structure for NAPI scheduling similar to tasklet but with weighting
|
|
|
|
*/
|
|
|
|
struct napi_struct {
|
|
|
|
/* The poll_list must only be managed by the entity which
|
|
|
|
* changes the state of the NAPI_STATE_SCHED bit. This means
|
|
|
|
* whoever atomically sets that bit can add this napi_struct
|
|
|
|
* to the per-cpu poll_list, and whoever clears that bit
|
|
|
|
* can remove from the list right before clearing the bit.
|
|
|
|
*/
|
|
|
|
struct list_head poll_list;
|
|
|
|
|
|
|
|
unsigned long state;
|
|
|
|
int weight;
|
|
|
|
int (*poll)(struct napi_struct *, int);
|
|
|
|
#ifdef CONFIG_NETPOLL
|
|
|
|
spinlock_t poll_lock;
|
|
|
|
int poll_owner;
|
|
|
|
#endif
|
2009-02-09 02:00:36 +08:00
|
|
|
|
|
|
|
unsigned int gro_count;
|
|
|
|
|
2009-01-05 08:13:40 +08:00
|
|
|
struct net_device *dev;
|
net: Add Generic Receive Offload infrastructure
This patch adds the top-level GRO (Generic Receive Offload) infrastructure.
This is pretty similar to LRO except that this is protocol-independent.
Instead of holding packets in an lro_mgr structure, they're now held in
napi_struct.
For drivers that intend to use this, they can set the NETIF_F_GRO bit and
call napi_gro_receive instead of netif_receive_skb or just call netif_rx.
The latter will call napi_receive_skb automatically. When napi_gro_receive
is used, the driver must either call napi_complete/napi_rx_complete, or
call napi_gro_flush in softirq context if the driver uses the primitives
__napi_complete/__napi_rx_complete.
Protocols will set the gro_receive and gro_complete function pointers in
order to participate in this scheme.
In addition to the packet, gro_receive will get a list of currently held
packets. Each packet in the list has a same_flow field which is non-zero
if it is a potential match for the new packet. For each packet that may
match, they also have a flush field which is non-zero if the held packet
must not be merged with the new packet.
Once gro_receive has determined that the new skb matches a held packet,
the held packet may be processed immediately if the new skb cannot be
merged with it. In this case gro_receive should return the pointer to
the existing skb in gro_list. Otherwise the new skb should be merged into
the existing packet and NULL should be returned, unless the new skb makes
it impossible for any further merges to be made (e.g., FIN packet) where
the merged skb should be returned.
Whenever the skb is merged into an existing entry, the gro_receive
function should set NAPI_GRO_CB(skb)->same_flow. Note that if an skb
merely matches an existing entry but can't be merged with it, then
this shouldn't be set.
If gro_receive finds it pointless to hold the new skb for future merging,
it should set NAPI_GRO_CB(skb)->flush.
Held packets will be flushed by napi_gro_flush which is called by
napi_complete and napi_rx_complete.
Currently held packets are stored in a singly liked list just like LRO.
The list is limited to a maximum of 8 entries. In future, this may be
expanded to use a hash table to allow more flows to be held for merging.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16 15:38:52 +08:00
|
|
|
struct list_head dev_list;
|
|
|
|
struct sk_buff *gro_list;
|
2009-01-05 08:13:40 +08:00
|
|
|
struct sk_buff *skb;
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
};
|
|
|
|
|
2009-11-05 01:50:58 +08:00
|
|
|
enum {
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
NAPI_STATE_SCHED, /* Poll is scheduled */
|
2008-01-08 12:35:07 +08:00
|
|
|
NAPI_STATE_DISABLE, /* Disable pending */
|
netpoll: fix race on poll_list resulting in garbage entry
A few months back a race was discused between the netpoll napi service
path, and the fast path through net_rx_action:
http://kerneltrap.org/mailarchive/linux-netdev/2007/10/16/345470
A patch was submitted for that bug, but I think we missed a case.
Consider the following scenario:
INITIAL STATE
CPU0 has one napi_struct A on its poll_list
CPU1 is calling netpoll_send_skb and needs to call poll_napi on the same
napi_struct A that CPU0 has on its list
CPU0 CPU1
net_rx_action poll_napi
!list_empty (returns true) locks poll_lock for A
poll_one_napi
napi->poll
netif_rx_complete
__napi_complete
(removes A from poll_list)
list_entry(list->next)
In the above scenario, net_rx_action assumes that the per-cpu poll_list is
exclusive to that cpu. netpoll of course violates that, and because the netpoll
path can dequeue from the poll list, its possible for CPU0 to detect a non-empty
list at the top of the while loop in net_rx_action, but have it become empty by
the time it calls list_entry. Since the poll_list isn't surrounded by any other
structure, the returned data from that list_entry call in this situation is
garbage, and any number of crashes can result based on what exactly that garbage
is.
Given that its not fasible for performance reasons to place exclusive locks
arround each cpus poll list to provide that mutal exclusion, I think the best
solution is modify the netpoll path in such a way that we continue to guarantee
that the poll_list for a cpu is in fact exclusive to that cpu. To do this I've
implemented the patch below. It adds an additional bit to the state field in
the napi_struct. When executing napi->poll from the netpoll_path, this bit will
be set. When a driver calls netif_rx_complete, if that bit is set, it will not
remove the napi_struct from the poll_list. That work will be saved for the next
iteration of net_rx_action.
I've tested this and it seems to work well. About the biggest drawback I can
see to it is the fact that it might result in an extra loop through
net_rx_action in the event that the device is actually contended for (i.e. the
netpoll path actually preforms all the needed work no the device, and the call
to net_rx_action winds up doing nothing, except removing the napi_struct from
the poll_list. However I think this is probably a small price to pay, given
that the alternative is a crash.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-10 15:22:26 +08:00
|
|
|
NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
};
|
|
|
|
|
2009-10-29 15:17:09 +08:00
|
|
|
enum gro_result {
|
2009-03-17 01:50:02 +08:00
|
|
|
GRO_MERGED,
|
|
|
|
GRO_MERGED_FREE,
|
|
|
|
GRO_HELD,
|
|
|
|
GRO_NORMAL,
|
|
|
|
GRO_DROP,
|
|
|
|
};
|
2009-10-29 15:17:09 +08:00
|
|
|
typedef enum gro_result gro_result_t;
|
2009-03-17 01:50:02 +08:00
|
|
|
|
2011-03-12 11:14:39 +08:00
|
|
|
/*
|
|
|
|
* enum rx_handler_result - Possible return values for rx_handlers.
|
|
|
|
* @RX_HANDLER_CONSUMED: skb was consumed by rx_handler, do not process it
|
|
|
|
* further.
|
|
|
|
* @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in
|
|
|
|
* case skb->dev was changed by rx_handler.
|
|
|
|
* @RX_HANDLER_EXACT: Force exact delivery, no wildcard.
|
|
|
|
* @RX_HANDLER_PASS: Do nothing, passe the skb as if no rx_handler was called.
|
|
|
|
*
|
|
|
|
* rx_handlers are functions called from inside __netif_receive_skb(), to do
|
|
|
|
* special processing of the skb, prior to delivery to protocol handlers.
|
|
|
|
*
|
|
|
|
* Currently, a net_device can only have a single rx_handler registered. Trying
|
|
|
|
* to register a second rx_handler will return -EBUSY.
|
|
|
|
*
|
|
|
|
* To register a rx_handler on a net_device, use netdev_rx_handler_register().
|
|
|
|
* To unregister a rx_handler on a net_device, use
|
|
|
|
* netdev_rx_handler_unregister().
|
|
|
|
*
|
|
|
|
* Upon return, rx_handler is expected to tell __netif_receive_skb() what to
|
|
|
|
* do with the skb.
|
|
|
|
*
|
|
|
|
* If the rx_handler consumed to skb in some way, it should return
|
|
|
|
* RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for
|
|
|
|
* the skb to be delivered in some other ways.
|
|
|
|
*
|
|
|
|
* If the rx_handler changed skb->dev, to divert the skb to another
|
|
|
|
* net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the
|
|
|
|
* new device will be called if it exists.
|
|
|
|
*
|
|
|
|
* If the rx_handler consider the skb should be ignored, it should return
|
|
|
|
* RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that
|
|
|
|
* are registred on exact device (ptype->dev == skb->dev).
|
|
|
|
*
|
|
|
|
* If the rx_handler didn't changed skb->dev, but want the skb to be normally
|
|
|
|
* delivered, it should return RX_HANDLER_PASS.
|
|
|
|
*
|
|
|
|
* A device without a registered rx_handler will behave as if rx_handler
|
|
|
|
* returned RX_HANDLER_PASS.
|
|
|
|
*/
|
|
|
|
|
|
|
|
enum rx_handler_result {
|
|
|
|
RX_HANDLER_CONSUMED,
|
|
|
|
RX_HANDLER_ANOTHER,
|
|
|
|
RX_HANDLER_EXACT,
|
|
|
|
RX_HANDLER_PASS,
|
|
|
|
};
|
|
|
|
typedef enum rx_handler_result rx_handler_result_t;
|
|
|
|
typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb);
|
2010-06-02 05:52:08 +08:00
|
|
|
|
2008-02-14 07:03:15 +08:00
|
|
|
extern void __napi_schedule(struct napi_struct *n);
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
|
2008-01-08 12:35:07 +08:00
|
|
|
static inline int napi_disable_pending(struct napi_struct *n)
|
|
|
|
{
|
|
|
|
return test_bit(NAPI_STATE_DISABLE, &n->state);
|
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* napi_schedule_prep - check if napi can be scheduled
|
|
|
|
* @n: napi context
|
|
|
|
*
|
|
|
|
* Test if NAPI routine is already running, and if not mark
|
|
|
|
* it as running. This is used as a condition variable
|
2008-01-08 12:35:07 +08:00
|
|
|
* insure only one NAPI poll instance runs. We also make
|
|
|
|
* sure there is no pending NAPI disable.
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
*/
|
|
|
|
static inline int napi_schedule_prep(struct napi_struct *n)
|
|
|
|
{
|
2008-01-08 12:35:07 +08:00
|
|
|
return !napi_disable_pending(n) &&
|
|
|
|
!test_and_set_bit(NAPI_STATE_SCHED, &n->state);
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* napi_schedule - schedule NAPI poll
|
|
|
|
* @n: napi context
|
|
|
|
*
|
|
|
|
* Schedule NAPI poll routine to be called if it is not already
|
|
|
|
* running.
|
|
|
|
*/
|
|
|
|
static inline void napi_schedule(struct napi_struct *n)
|
|
|
|
{
|
|
|
|
if (napi_schedule_prep(n))
|
|
|
|
__napi_schedule(n);
|
|
|
|
}
|
|
|
|
|
2007-10-10 06:47:37 +08:00
|
|
|
/* Try to reschedule poll. Called by dev->poll() after napi_complete(). */
|
|
|
|
static inline int napi_reschedule(struct napi_struct *napi)
|
|
|
|
{
|
|
|
|
if (napi_schedule_prep(napi)) {
|
|
|
|
__napi_schedule(napi);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* napi_complete - NAPI processing complete
|
|
|
|
* @n: napi context
|
|
|
|
*
|
|
|
|
* Mark NAPI processing as complete.
|
|
|
|
*/
|
net: Add Generic Receive Offload infrastructure
This patch adds the top-level GRO (Generic Receive Offload) infrastructure.
This is pretty similar to LRO except that this is protocol-independent.
Instead of holding packets in an lro_mgr structure, they're now held in
napi_struct.
For drivers that intend to use this, they can set the NETIF_F_GRO bit and
call napi_gro_receive instead of netif_receive_skb or just call netif_rx.
The latter will call napi_receive_skb automatically. When napi_gro_receive
is used, the driver must either call napi_complete/napi_rx_complete, or
call napi_gro_flush in softirq context if the driver uses the primitives
__napi_complete/__napi_rx_complete.
Protocols will set the gro_receive and gro_complete function pointers in
order to participate in this scheme.
In addition to the packet, gro_receive will get a list of currently held
packets. Each packet in the list has a same_flow field which is non-zero
if it is a potential match for the new packet. For each packet that may
match, they also have a flush field which is non-zero if the held packet
must not be merged with the new packet.
Once gro_receive has determined that the new skb matches a held packet,
the held packet may be processed immediately if the new skb cannot be
merged with it. In this case gro_receive should return the pointer to
the existing skb in gro_list. Otherwise the new skb should be merged into
the existing packet and NULL should be returned, unless the new skb makes
it impossible for any further merges to be made (e.g., FIN packet) where
the merged skb should be returned.
Whenever the skb is merged into an existing entry, the gro_receive
function should set NAPI_GRO_CB(skb)->same_flow. Note that if an skb
merely matches an existing entry but can't be merged with it, then
this shouldn't be set.
If gro_receive finds it pointless to hold the new skb for future merging,
it should set NAPI_GRO_CB(skb)->flush.
Held packets will be flushed by napi_gro_flush which is called by
napi_complete and napi_rx_complete.
Currently held packets are stored in a singly liked list just like LRO.
The list is limited to a maximum of 8 entries. In future, this may be
expanded to use a hash table to allow more flows to be held for merging.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16 15:38:52 +08:00
|
|
|
extern void __napi_complete(struct napi_struct *n);
|
|
|
|
extern void napi_complete(struct napi_struct *n);
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* napi_disable - prevent NAPI from scheduling
|
|
|
|
* @n: napi context
|
|
|
|
*
|
|
|
|
* Stop NAPI from being scheduled on this context.
|
|
|
|
* Waits till any outstanding processing completes.
|
|
|
|
*/
|
|
|
|
static inline void napi_disable(struct napi_struct *n)
|
|
|
|
{
|
2008-01-08 12:35:07 +08:00
|
|
|
set_bit(NAPI_STATE_DISABLE, &n->state);
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
|
2007-10-26 19:23:22 +08:00
|
|
|
msleep(1);
|
2008-01-08 12:35:07 +08:00
|
|
|
clear_bit(NAPI_STATE_DISABLE, &n->state);
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* napi_enable - enable NAPI scheduling
|
|
|
|
* @n: napi context
|
|
|
|
*
|
|
|
|
* Resume NAPI from being scheduled on this context.
|
|
|
|
* Must be paired with napi_disable.
|
|
|
|
*/
|
|
|
|
static inline void napi_enable(struct napi_struct *n)
|
|
|
|
{
|
|
|
|
BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
|
|
|
|
smp_mb__before_clear_bit();
|
|
|
|
clear_bit(NAPI_STATE_SCHED, &n->state);
|
|
|
|
}
|
|
|
|
|
2007-10-18 04:26:41 +08:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/**
|
|
|
|
* napi_synchronize - wait until NAPI is not running
|
|
|
|
* @n: napi context
|
|
|
|
*
|
|
|
|
* Wait until NAPI is done being scheduled on this context.
|
|
|
|
* Waits till any outstanding processing completes but
|
|
|
|
* does not disable future activations.
|
|
|
|
*/
|
|
|
|
static inline void napi_synchronize(const struct napi_struct *n)
|
|
|
|
{
|
|
|
|
while (test_bit(NAPI_STATE_SCHED, &n->state))
|
|
|
|
msleep(1);
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
# define napi_synchronize(n) barrier()
|
|
|
|
#endif
|
|
|
|
|
2009-11-05 01:50:58 +08:00
|
|
|
enum netdev_queue_state_t {
|
2011-11-29 00:32:44 +08:00
|
|
|
__QUEUE_STATE_DRV_XOFF,
|
|
|
|
__QUEUE_STATE_STACK_XOFF,
|
2008-08-01 07:58:50 +08:00
|
|
|
__QUEUE_STATE_FROZEN,
|
2011-11-29 00:32:44 +08:00
|
|
|
#define QUEUE_STATE_ANY_XOFF ((1 << __QUEUE_STATE_DRV_XOFF) | \
|
|
|
|
(1 << __QUEUE_STATE_STACK_XOFF))
|
|
|
|
#define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \
|
|
|
|
(1 << __QUEUE_STATE_FROZEN))
|
2008-07-09 14:14:46 +08:00
|
|
|
};
|
2011-11-29 00:32:44 +08:00
|
|
|
/*
|
|
|
|
* __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue. The
|
|
|
|
* netif_tx_* functions below are used to manipulate this flag. The
|
|
|
|
* __QUEUE_STATE_STACK_XOFF flag is used by the stack to stop the transmit
|
|
|
|
* queue independently. The netif_xmit_*stopped functions below are called
|
|
|
|
* to check if the queue has been stopped by the driver or stack (either
|
|
|
|
* of the XOFF bits are set in the state). Drivers should not need to call
|
|
|
|
* netif_xmit*stopped functions, they should only be using netif_tx_*.
|
|
|
|
*/
|
2008-07-09 14:14:46 +08:00
|
|
|
|
2008-07-09 07:55:56 +08:00
|
|
|
struct netdev_queue {
|
2009-04-28 19:43:42 +08:00
|
|
|
/*
|
|
|
|
* read mostly part
|
|
|
|
*/
|
2008-07-09 07:55:56 +08:00
|
|
|
struct net_device *dev;
|
2008-07-09 08:42:10 +08:00
|
|
|
struct Qdisc *qdisc;
|
|
|
|
struct Qdisc *qdisc_sleeping;
|
2011-11-16 20:15:10 +08:00
|
|
|
#ifdef CONFIG_SYSFS
|
2010-11-21 21:17:27 +08:00
|
|
|
struct kobject kobj;
|
|
|
|
#endif
|
2010-11-29 16:14:37 +08:00
|
|
|
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
|
|
|
|
int numa_node;
|
|
|
|
#endif
|
2009-04-28 19:43:42 +08:00
|
|
|
/*
|
|
|
|
* write mostly part
|
|
|
|
*/
|
|
|
|
spinlock_t _xmit_lock ____cacheline_aligned_in_smp;
|
|
|
|
int xmit_lock_owner;
|
2009-05-18 11:55:16 +08:00
|
|
|
/*
|
|
|
|
* please use this field instead of dev->trans_start
|
|
|
|
*/
|
|
|
|
unsigned long trans_start;
|
2011-11-16 20:15:10 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Number of TX timeouts for this queue
|
|
|
|
* (/sys/class/net/DEV/Q/trans_timeout)
|
|
|
|
*/
|
|
|
|
unsigned long trans_timeout;
|
2011-11-29 00:33:09 +08:00
|
|
|
|
|
|
|
unsigned long state;
|
|
|
|
|
|
|
|
#ifdef CONFIG_BQL
|
|
|
|
struct dql dql;
|
|
|
|
#endif
|
2008-07-17 15:34:19 +08:00
|
|
|
} ____cacheline_aligned_in_smp;
|
2008-07-09 07:55:56 +08:00
|
|
|
|
2010-11-29 16:14:37 +08:00
|
|
|
static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
|
|
|
|
{
|
|
|
|
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
|
|
|
|
return q->numa_node;
|
|
|
|
#else
|
2010-12-14 11:09:15 +08:00
|
|
|
return NUMA_NO_NODE;
|
2010-11-29 16:14:37 +08:00
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node)
|
|
|
|
{
|
|
|
|
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
|
|
|
|
q->numa_node = node;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
2010-03-25 03:13:54 +08:00
|
|
|
#ifdef CONFIG_RPS
|
2010-03-16 16:03:29 +08:00
|
|
|
/*
|
|
|
|
* This structure holds an RPS map which can be of variable length. The
|
|
|
|
* map is an array of CPUs.
|
|
|
|
*/
|
|
|
|
struct rps_map {
|
|
|
|
unsigned int len;
|
|
|
|
struct rcu_head rcu;
|
|
|
|
u16 cpus[0];
|
|
|
|
};
|
2011-12-24 14:56:49 +08:00
|
|
|
#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16)))
|
2010-03-16 16:03:29 +08:00
|
|
|
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
/*
|
2011-01-19 19:03:53 +08:00
|
|
|
* The rps_dev_flow structure contains the mapping of a flow to a CPU, the
|
|
|
|
* tail pointer for that CPU's input queue at the time of last enqueue, and
|
|
|
|
* a hardware filter index.
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
*/
|
|
|
|
struct rps_dev_flow {
|
|
|
|
u16 cpu;
|
2011-01-19 19:03:53 +08:00
|
|
|
u16 filter;
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
unsigned int last_qtail;
|
|
|
|
};
|
2011-01-19 19:03:53 +08:00
|
|
|
#define RPS_NO_FILTER 0xffff
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The rps_dev_flow_table structure contains a table of flow mappings.
|
|
|
|
*/
|
|
|
|
struct rps_dev_flow_table {
|
|
|
|
unsigned int mask;
|
|
|
|
struct rcu_head rcu;
|
|
|
|
struct work_struct free_work;
|
|
|
|
struct rps_dev_flow flows[0];
|
|
|
|
};
|
|
|
|
#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \
|
2011-12-24 14:56:49 +08:00
|
|
|
((_num) * sizeof(struct rps_dev_flow)))
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The rps_sock_flow_table contains mappings of flows to the last CPU
|
|
|
|
* on which they were processed by the application (set in recvmsg).
|
|
|
|
*/
|
|
|
|
struct rps_sock_flow_table {
|
|
|
|
unsigned int mask;
|
|
|
|
u16 ents[0];
|
|
|
|
};
|
|
|
|
#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \
|
2011-12-24 14:56:49 +08:00
|
|
|
((_num) * sizeof(u16)))
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
|
|
|
|
#define RPS_NO_CPU 0xffff
|
|
|
|
|
|
|
|
static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
|
|
|
|
u32 hash)
|
|
|
|
{
|
|
|
|
if (table && hash) {
|
|
|
|
unsigned int cpu, index = hash & table->mask;
|
|
|
|
|
|
|
|
/* We only give a hint, preemption can change cpu under us */
|
|
|
|
cpu = raw_smp_processor_id();
|
|
|
|
|
|
|
|
if (table->ents[index] != cpu)
|
|
|
|
table->ents[index] = cpu;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table,
|
|
|
|
u32 hash)
|
|
|
|
{
|
|
|
|
if (table && hash)
|
|
|
|
table->ents[hash & table->mask] = RPS_NO_CPU;
|
|
|
|
}
|
|
|
|
|
2010-10-25 11:02:02 +08:00
|
|
|
extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
|
2011-01-19 19:03:53 +08:00
|
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
|
|
extern bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
|
|
|
|
u32 flow_id, u16 filter_id);
|
|
|
|
#endif
|
|
|
|
|
2010-03-16 16:03:29 +08:00
|
|
|
/* This structure contains an instance of an RX queue. */
|
|
|
|
struct netdev_rx_queue {
|
2010-10-25 11:02:02 +08:00
|
|
|
struct rps_map __rcu *rps_map;
|
|
|
|
struct rps_dev_flow_table __rcu *rps_flow_table;
|
|
|
|
struct kobject kobj;
|
2010-11-09 18:47:38 +08:00
|
|
|
struct net_device *dev;
|
2010-03-16 16:03:29 +08:00
|
|
|
} ____cacheline_aligned_in_smp;
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
#endif /* CONFIG_RPS */
|
2008-11-20 13:32:24 +08:00
|
|
|
|
2010-11-26 16:36:09 +08:00
|
|
|
#ifdef CONFIG_XPS
|
|
|
|
/*
|
|
|
|
* This structure holds an XPS map which can be of variable length. The
|
|
|
|
* map is an array of queues.
|
|
|
|
*/
|
|
|
|
struct xps_map {
|
|
|
|
unsigned int len;
|
|
|
|
unsigned int alloc_len;
|
|
|
|
struct rcu_head rcu;
|
|
|
|
u16 queues[0];
|
|
|
|
};
|
2011-12-24 14:56:49 +08:00
|
|
|
#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16)))
|
2010-11-26 16:36:09 +08:00
|
|
|
#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map)) \
|
|
|
|
/ sizeof(u16))
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This structure holds all XPS maps for device. Maps are indexed by CPU.
|
|
|
|
*/
|
|
|
|
struct xps_dev_maps {
|
|
|
|
struct rcu_head rcu;
|
2010-11-29 05:43:02 +08:00
|
|
|
struct xps_map __rcu *cpu_map[0];
|
2010-11-26 16:36:09 +08:00
|
|
|
};
|
|
|
|
#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \
|
|
|
|
(nr_cpu_ids * sizeof(struct xps_map *)))
|
|
|
|
#endif /* CONFIG_XPS */
|
|
|
|
|
2011-01-17 16:06:04 +08:00
|
|
|
#define TC_MAX_QUEUE 16
|
|
|
|
#define TC_BITMASK 15
|
|
|
|
/* HW offloaded queuing disciplines txq count and offset maps */
|
|
|
|
struct netdev_tc_txq {
|
|
|
|
u16 count;
|
|
|
|
u16 offset;
|
|
|
|
};
|
|
|
|
|
2012-01-05 04:23:39 +08:00
|
|
|
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
|
|
|
|
/*
|
|
|
|
* This structure is to hold information about the device
|
|
|
|
* configured to run FCoE protocol stack.
|
|
|
|
*/
|
|
|
|
struct netdev_fcoe_hbainfo {
|
|
|
|
char manufacturer[64];
|
|
|
|
char serial_number[64];
|
|
|
|
char hardware_version[64];
|
|
|
|
char driver_version[64];
|
|
|
|
char optionrom_version[64];
|
|
|
|
char firmware_version[64];
|
|
|
|
char model[256];
|
|
|
|
char model_description[256];
|
|
|
|
};
|
|
|
|
#endif
|
|
|
|
|
2008-11-20 13:32:24 +08:00
|
|
|
/*
|
|
|
|
* This structure defines the management hooks for network devices.
|
2008-11-21 12:14:53 +08:00
|
|
|
* The following hooks can be defined; unless noted otherwise, they are
|
|
|
|
* optional and can be filled with a null pointer.
|
2008-11-20 13:32:24 +08:00
|
|
|
*
|
|
|
|
* int (*ndo_init)(struct net_device *dev);
|
|
|
|
* This function is called once when network device is registered.
|
|
|
|
* The network device can use this to any late stage initializaton
|
|
|
|
* or semantic validattion. It can fail with an error code which will
|
|
|
|
* be propogated back to register_netdev
|
|
|
|
*
|
|
|
|
* void (*ndo_uninit)(struct net_device *dev);
|
|
|
|
* This function is called when device is unregistered or when registration
|
|
|
|
* fails. It is not called if init fails.
|
|
|
|
*
|
|
|
|
* int (*ndo_open)(struct net_device *dev);
|
|
|
|
* This function is called when network device transistions to the up
|
|
|
|
* state.
|
|
|
|
*
|
|
|
|
* int (*ndo_stop)(struct net_device *dev);
|
|
|
|
* This function is called when network device transistions to the down
|
|
|
|
* state.
|
|
|
|
*
|
2009-09-01 03:50:40 +08:00
|
|
|
* netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
|
|
|
|
* struct net_device *dev);
|
2008-11-21 12:14:53 +08:00
|
|
|
* Called when a packet needs to be transmitted.
|
2009-09-01 03:50:40 +08:00
|
|
|
* Must return NETDEV_TX_OK , NETDEV_TX_BUSY.
|
|
|
|
* (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
|
2008-11-21 12:14:53 +08:00
|
|
|
* Required can not be NULL.
|
|
|
|
*
|
|
|
|
* u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb);
|
|
|
|
* Called to decide which queue to when device supports multiple
|
|
|
|
* transmit queues.
|
|
|
|
*
|
2008-11-20 13:32:24 +08:00
|
|
|
* void (*ndo_change_rx_flags)(struct net_device *dev, int flags);
|
|
|
|
* This function is called to allow device receiver to make
|
|
|
|
* changes to configuration when multicast or promiscious is enabled.
|
|
|
|
*
|
|
|
|
* void (*ndo_set_rx_mode)(struct net_device *dev);
|
|
|
|
* This function is called device changes address list filtering.
|
2011-08-16 14:29:00 +08:00
|
|
|
* If driver handles unicast address filtering, it should set
|
|
|
|
* IFF_UNICAST_FLT to its priv_flags.
|
2008-11-20 13:32:24 +08:00
|
|
|
*
|
|
|
|
* int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
|
|
|
|
* This function is called when the Media Access Control address
|
2009-04-27 20:45:54 +08:00
|
|
|
* needs to be changed. If this interface is not defined, the
|
2008-11-20 13:32:24 +08:00
|
|
|
* mac address can not be changed.
|
|
|
|
*
|
|
|
|
* int (*ndo_validate_addr)(struct net_device *dev);
|
|
|
|
* Test if Media Access Control address is valid for the device.
|
|
|
|
*
|
|
|
|
* int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd);
|
|
|
|
* Called when a user request an ioctl which can't be handled by
|
|
|
|
* the generic interface code. If not defined ioctl's return
|
|
|
|
* not supported error code.
|
|
|
|
*
|
|
|
|
* int (*ndo_set_config)(struct net_device *dev, struct ifmap *map);
|
|
|
|
* Used to set network devices bus interface parameters. This interface
|
|
|
|
* is retained for legacy reason, new devices should use the bus
|
|
|
|
* interface (PCI) for low level management.
|
|
|
|
*
|
|
|
|
* int (*ndo_change_mtu)(struct net_device *dev, int new_mtu);
|
|
|
|
* Called when a user wants to change the Maximum Transfer Unit
|
|
|
|
* of a device. If not defined, any request to change MTU will
|
|
|
|
* will return an error.
|
|
|
|
*
|
2008-11-21 12:14:53 +08:00
|
|
|
* void (*ndo_tx_timeout)(struct net_device *dev);
|
2008-11-20 13:32:24 +08:00
|
|
|
* Callback uses when the transmitter has not made any progress
|
|
|
|
* for dev->watchdog ticks.
|
|
|
|
*
|
2010-07-09 17:11:52 +08:00
|
|
|
* struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev,
|
2010-07-08 05:58:56 +08:00
|
|
|
* struct rtnl_link_stats64 *storage);
|
2009-10-08 04:53:11 +08:00
|
|
|
* struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
|
2008-11-20 13:32:24 +08:00
|
|
|
* Called when a user wants to get the network device usage
|
2010-06-08 15:19:54 +08:00
|
|
|
* statistics. Drivers must do one of the following:
|
2010-07-09 17:11:52 +08:00
|
|
|
* 1. Define @ndo_get_stats64 to fill in a zero-initialised
|
|
|
|
* rtnl_link_stats64 structure passed by the caller.
|
2010-06-16 06:08:48 +08:00
|
|
|
* 2. Define @ndo_get_stats to update a net_device_stats structure
|
2010-06-08 15:19:54 +08:00
|
|
|
* (which should normally be dev->stats) and return a pointer to
|
|
|
|
* it. The structure may be changed asynchronously only if each
|
|
|
|
* field is written atomically.
|
|
|
|
* 3. Update dev->stats asynchronously and atomically, and define
|
|
|
|
* neither operation.
|
2008-11-20 13:32:24 +08:00
|
|
|
*
|
2011-12-09 08:52:37 +08:00
|
|
|
* int (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid);
|
2008-11-20 13:32:24 +08:00
|
|
|
* If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER)
|
|
|
|
* this function is called when a VLAN id is registered.
|
|
|
|
*
|
2011-12-09 08:52:37 +08:00
|
|
|
* int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid);
|
2008-11-20 13:32:24 +08:00
|
|
|
* If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER)
|
|
|
|
* this function is called when a VLAN id is unregistered.
|
|
|
|
*
|
|
|
|
* void (*ndo_poll_controller)(struct net_device *dev);
|
2010-02-10 09:43:46 +08:00
|
|
|
*
|
|
|
|
* SR-IOV management functions.
|
|
|
|
* int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac);
|
|
|
|
* int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos);
|
|
|
|
* int (*ndo_set_vf_tx_rate)(struct net_device *dev, int vf, int rate);
|
2011-10-08 11:05:24 +08:00
|
|
|
* int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting);
|
2010-02-10 09:43:46 +08:00
|
|
|
* int (*ndo_get_vf_config)(struct net_device *dev,
|
|
|
|
* int vf, struct ifla_vf_info *ivf);
|
net: Add netlink support for virtual port management (was iovnl)
Add new netdev ops ndo_{set|get}_vf_port to allow setting of
port-profile on a netdev interface. Extends netlink socket RTM_SETLINK/
RTM_GETLINK with two new sub msgs called IFLA_VF_PORTS and IFLA_PORT_SELF
(added to end of IFLA_cmd list). These are both nested atrtibutes
using this layout:
[IFLA_NUM_VF]
[IFLA_VF_PORTS]
[IFLA_VF_PORT]
[IFLA_PORT_*], ...
[IFLA_VF_PORT]
[IFLA_PORT_*], ...
...
[IFLA_PORT_SELF]
[IFLA_PORT_*], ...
These attributes are design to be set and get symmetrically. VF_PORTS
is a list of VF_PORTs, one for each VF, when dealing with an SR-IOV
device. PORT_SELF is for the PF of the SR-IOV device, in case it wants
to also have a port-profile, or for the case where the VF==PF, like in
enic patch 2/2 of this patch set.
A port-profile is used to configure/enable the external switch virtual port
backing the netdev interface, not to configure the host-facing side of the
netdev. A port-profile is an identifier known to the switch. How port-
profiles are installed on the switch or how available port-profiles are
made know to the host is outside the scope of this patch.
There are two types of port-profiles specs in the netlink msg. The first spec
is for 802.1Qbg (pre-)standard, VDP protocol. The second spec is for devices
that run a similar protocol as VDP but in firmware, thus hiding the protocol
details. In either case, the specs have much in common and makes sense to
define the netlink msg as the union of the two specs. For example, both specs
have a notition of associating/deassociating a port-profile. And both specs
require some information from the hypervisor manager, such as client port
instance ID.
The general flow is the port-profile is applied to a host netdev interface
using RTM_SETLINK, the receiver of the RTM_SETLINK msg communicates with the
switch, and the switch virtual port backing the host netdev interface is
configured/enabled based on the settings defined by the port-profile. What
those settings comprise, and how those settings are managed is again
outside the scope of this patch, since this patch only deals with the
first step in the flow.
Signed-off-by: Scott Feldman <scofeldm@cisco.com>
Signed-off-by: Roopa Prabhu <roprabhu@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-18 13:49:55 +08:00
|
|
|
* int (*ndo_set_vf_port)(struct net_device *dev, int vf,
|
|
|
|
* struct nlattr *port[]);
|
|
|
|
* int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb);
|
2011-01-17 16:06:04 +08:00
|
|
|
* int (*ndo_setup_tc)(struct net_device *dev, u8 tc)
|
|
|
|
* Called to setup 'tc' number of traffic classes in the net device. This
|
|
|
|
* is always called from the stack with the rtnl lock held and netif tx
|
|
|
|
* queues stopped. This allows the netdevice to perform queue management
|
|
|
|
* safely.
|
2011-01-19 19:03:53 +08:00
|
|
|
*
|
2011-03-09 16:48:03 +08:00
|
|
|
* Fiber Channel over Ethernet (FCoE) offload functions.
|
|
|
|
* int (*ndo_fcoe_enable)(struct net_device *dev);
|
|
|
|
* Called when the FCoE protocol stack wants to start using LLD for FCoE
|
|
|
|
* so the underlying device can perform whatever needed configuration or
|
|
|
|
* initialization to support acceleration of FCoE traffic.
|
|
|
|
*
|
|
|
|
* int (*ndo_fcoe_disable)(struct net_device *dev);
|
|
|
|
* Called when the FCoE protocol stack wants to stop using LLD for FCoE
|
|
|
|
* so the underlying device can perform whatever needed clean-ups to
|
|
|
|
* stop supporting acceleration of FCoE traffic.
|
|
|
|
*
|
|
|
|
* int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid,
|
|
|
|
* struct scatterlist *sgl, unsigned int sgc);
|
|
|
|
* Called when the FCoE Initiator wants to initialize an I/O that
|
|
|
|
* is a possible candidate for Direct Data Placement (DDP). The LLD can
|
|
|
|
* perform necessary setup and returns 1 to indicate the device is set up
|
|
|
|
* successfully to perform DDP on this I/O, otherwise this returns 0.
|
|
|
|
*
|
|
|
|
* int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid);
|
|
|
|
* Called when the FCoE Initiator/Target is done with the DDPed I/O as
|
|
|
|
* indicated by the FC exchange id 'xid', so the underlying device can
|
|
|
|
* clean up and reuse resources for later DDP requests.
|
|
|
|
*
|
|
|
|
* int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid,
|
|
|
|
* struct scatterlist *sgl, unsigned int sgc);
|
|
|
|
* Called when the FCoE Target wants to initialize an I/O that
|
|
|
|
* is a possible candidate for Direct Data Placement (DDP). The LLD can
|
|
|
|
* perform necessary setup and returns 1 to indicate the device is set up
|
|
|
|
* successfully to perform DDP on this I/O, otherwise this returns 0.
|
|
|
|
*
|
2012-01-05 04:23:39 +08:00
|
|
|
* int (*ndo_fcoe_get_hbainfo)(struct net_device *dev,
|
|
|
|
* struct netdev_fcoe_hbainfo *hbainfo);
|
|
|
|
* Called when the FCoE Protocol stack wants information on the underlying
|
|
|
|
* device. This information is utilized by the FCoE protocol stack to
|
|
|
|
* register attributes with Fiber Channel management service as per the
|
|
|
|
* FC-GS Fabric Device Management Information(FDMI) specification.
|
|
|
|
*
|
2011-03-09 16:48:03 +08:00
|
|
|
* int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type);
|
|
|
|
* Called when the underlying device wants to override default World Wide
|
|
|
|
* Name (WWN) generation mechanism in FCoE protocol stack to pass its own
|
|
|
|
* World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE
|
|
|
|
* protocol stack to use.
|
|
|
|
*
|
2011-01-19 19:03:53 +08:00
|
|
|
* RFS acceleration.
|
|
|
|
* int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb,
|
|
|
|
* u16 rxq_index, u32 flow_id);
|
|
|
|
* Set hardware filter for RFS. rxq_index is the target queue index;
|
|
|
|
* flow_id is a flow ID to be passed to rps_may_expire_flow() later.
|
|
|
|
* Return the filter ID on success, or a negative error code.
|
2011-02-13 18:15:37 +08:00
|
|
|
*
|
|
|
|
* Slave management functions (for bridge, bonding, etc). User should
|
|
|
|
* call netdev_set_master() to set dev->master properly.
|
|
|
|
* int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev);
|
|
|
|
* Called to make another netdev an underling.
|
|
|
|
*
|
|
|
|
* int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
|
|
|
|
* Called to release previously enslaved netdev.
|
2011-02-16 00:59:17 +08:00
|
|
|
*
|
|
|
|
* Feature/offload setting functions.
|
2011-11-15 23:29:55 +08:00
|
|
|
* netdev_features_t (*ndo_fix_features)(struct net_device *dev,
|
|
|
|
* netdev_features_t features);
|
2011-02-16 00:59:17 +08:00
|
|
|
* Adjusts the requested feature flags according to device-specific
|
|
|
|
* constraints, and returns the resulting flags. Must not modify
|
|
|
|
* the device state.
|
|
|
|
*
|
2011-11-15 23:29:55 +08:00
|
|
|
* int (*ndo_set_features)(struct net_device *dev, netdev_features_t features);
|
2011-02-16 00:59:17 +08:00
|
|
|
* Called to update device configuration to new features. Passed
|
|
|
|
* feature set might be less than what was returned by ndo_fix_features()).
|
|
|
|
* Must return >0 or -errno if it changed dev->features itself.
|
|
|
|
*
|
2008-11-20 13:32:24 +08:00
|
|
|
*/
|
|
|
|
struct net_device_ops {
|
|
|
|
int (*ndo_init)(struct net_device *dev);
|
|
|
|
void (*ndo_uninit)(struct net_device *dev);
|
|
|
|
int (*ndo_open)(struct net_device *dev);
|
|
|
|
int (*ndo_stop)(struct net_device *dev);
|
2009-09-01 03:50:40 +08:00
|
|
|
netdev_tx_t (*ndo_start_xmit) (struct sk_buff *skb,
|
2008-11-21 12:14:53 +08:00
|
|
|
struct net_device *dev);
|
|
|
|
u16 (*ndo_select_queue)(struct net_device *dev,
|
|
|
|
struct sk_buff *skb);
|
2008-11-20 13:32:24 +08:00
|
|
|
void (*ndo_change_rx_flags)(struct net_device *dev,
|
|
|
|
int flags);
|
|
|
|
void (*ndo_set_rx_mode)(struct net_device *dev);
|
|
|
|
int (*ndo_set_mac_address)(struct net_device *dev,
|
|
|
|
void *addr);
|
|
|
|
int (*ndo_validate_addr)(struct net_device *dev);
|
|
|
|
int (*ndo_do_ioctl)(struct net_device *dev,
|
|
|
|
struct ifreq *ifr, int cmd);
|
|
|
|
int (*ndo_set_config)(struct net_device *dev,
|
|
|
|
struct ifmap *map);
|
2008-11-21 12:14:53 +08:00
|
|
|
int (*ndo_change_mtu)(struct net_device *dev,
|
|
|
|
int new_mtu);
|
|
|
|
int (*ndo_neigh_setup)(struct net_device *dev,
|
|
|
|
struct neigh_parms *);
|
2008-11-20 13:32:24 +08:00
|
|
|
void (*ndo_tx_timeout) (struct net_device *dev);
|
|
|
|
|
2010-07-08 05:58:56 +08:00
|
|
|
struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev,
|
|
|
|
struct rtnl_link_stats64 *storage);
|
2008-11-20 13:32:24 +08:00
|
|
|
struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
|
|
|
|
|
2011-12-09 08:52:37 +08:00
|
|
|
int (*ndo_vlan_rx_add_vid)(struct net_device *dev,
|
2008-11-20 13:32:24 +08:00
|
|
|
unsigned short vid);
|
2011-12-09 08:52:37 +08:00
|
|
|
int (*ndo_vlan_rx_kill_vid)(struct net_device *dev,
|
2008-11-20 13:32:24 +08:00
|
|
|
unsigned short vid);
|
|
|
|
#ifdef CONFIG_NET_POLL_CONTROLLER
|
|
|
|
void (*ndo_poll_controller)(struct net_device *dev);
|
2010-06-11 00:12:47 +08:00
|
|
|
int (*ndo_netpoll_setup)(struct net_device *dev,
|
|
|
|
struct netpoll_info *info);
|
2010-05-06 15:47:21 +08:00
|
|
|
void (*ndo_netpoll_cleanup)(struct net_device *dev);
|
2008-11-20 13:32:24 +08:00
|
|
|
#endif
|
2010-02-10 09:43:46 +08:00
|
|
|
int (*ndo_set_vf_mac)(struct net_device *dev,
|
|
|
|
int queue, u8 *mac);
|
|
|
|
int (*ndo_set_vf_vlan)(struct net_device *dev,
|
|
|
|
int queue, u16 vlan, u8 qos);
|
|
|
|
int (*ndo_set_vf_tx_rate)(struct net_device *dev,
|
|
|
|
int vf, int rate);
|
2011-10-08 11:05:24 +08:00
|
|
|
int (*ndo_set_vf_spoofchk)(struct net_device *dev,
|
|
|
|
int vf, bool setting);
|
2010-02-10 09:43:46 +08:00
|
|
|
int (*ndo_get_vf_config)(struct net_device *dev,
|
|
|
|
int vf,
|
|
|
|
struct ifla_vf_info *ivf);
|
net: Add netlink support for virtual port management (was iovnl)
Add new netdev ops ndo_{set|get}_vf_port to allow setting of
port-profile on a netdev interface. Extends netlink socket RTM_SETLINK/
RTM_GETLINK with two new sub msgs called IFLA_VF_PORTS and IFLA_PORT_SELF
(added to end of IFLA_cmd list). These are both nested atrtibutes
using this layout:
[IFLA_NUM_VF]
[IFLA_VF_PORTS]
[IFLA_VF_PORT]
[IFLA_PORT_*], ...
[IFLA_VF_PORT]
[IFLA_PORT_*], ...
...
[IFLA_PORT_SELF]
[IFLA_PORT_*], ...
These attributes are design to be set and get symmetrically. VF_PORTS
is a list of VF_PORTs, one for each VF, when dealing with an SR-IOV
device. PORT_SELF is for the PF of the SR-IOV device, in case it wants
to also have a port-profile, or for the case where the VF==PF, like in
enic patch 2/2 of this patch set.
A port-profile is used to configure/enable the external switch virtual port
backing the netdev interface, not to configure the host-facing side of the
netdev. A port-profile is an identifier known to the switch. How port-
profiles are installed on the switch or how available port-profiles are
made know to the host is outside the scope of this patch.
There are two types of port-profiles specs in the netlink msg. The first spec
is for 802.1Qbg (pre-)standard, VDP protocol. The second spec is for devices
that run a similar protocol as VDP but in firmware, thus hiding the protocol
details. In either case, the specs have much in common and makes sense to
define the netlink msg as the union of the two specs. For example, both specs
have a notition of associating/deassociating a port-profile. And both specs
require some information from the hypervisor manager, such as client port
instance ID.
The general flow is the port-profile is applied to a host netdev interface
using RTM_SETLINK, the receiver of the RTM_SETLINK msg communicates with the
switch, and the switch virtual port backing the host netdev interface is
configured/enabled based on the settings defined by the port-profile. What
those settings comprise, and how those settings are managed is again
outside the scope of this patch, since this patch only deals with the
first step in the flow.
Signed-off-by: Scott Feldman <scofeldm@cisco.com>
Signed-off-by: Roopa Prabhu <roprabhu@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-18 13:49:55 +08:00
|
|
|
int (*ndo_set_vf_port)(struct net_device *dev,
|
|
|
|
int vf,
|
|
|
|
struct nlattr *port[]);
|
|
|
|
int (*ndo_get_vf_port)(struct net_device *dev,
|
|
|
|
int vf, struct sk_buff *skb);
|
2011-01-17 16:06:04 +08:00
|
|
|
int (*ndo_setup_tc)(struct net_device *dev, u8 tc);
|
2011-11-25 22:40:26 +08:00
|
|
|
#if IS_ENABLED(CONFIG_FCOE)
|
2009-08-31 20:31:36 +08:00
|
|
|
int (*ndo_fcoe_enable)(struct net_device *dev);
|
|
|
|
int (*ndo_fcoe_disable)(struct net_device *dev);
|
2009-02-28 06:06:59 +08:00
|
|
|
int (*ndo_fcoe_ddp_setup)(struct net_device *dev,
|
|
|
|
u16 xid,
|
|
|
|
struct scatterlist *sgl,
|
|
|
|
unsigned int sgc);
|
|
|
|
int (*ndo_fcoe_ddp_done)(struct net_device *dev,
|
|
|
|
u16 xid);
|
2011-02-01 15:22:06 +08:00
|
|
|
int (*ndo_fcoe_ddp_target)(struct net_device *dev,
|
|
|
|
u16 xid,
|
|
|
|
struct scatterlist *sgl,
|
|
|
|
unsigned int sgc);
|
2012-01-05 04:23:39 +08:00
|
|
|
int (*ndo_fcoe_get_hbainfo)(struct net_device *dev,
|
|
|
|
struct netdev_fcoe_hbainfo *hbainfo);
|
2011-08-26 17:45:41 +08:00
|
|
|
#endif
|
|
|
|
|
2011-11-25 22:40:26 +08:00
|
|
|
#if IS_ENABLED(CONFIG_LIBFCOE)
|
2009-10-29 02:24:35 +08:00
|
|
|
#define NETDEV_FCOE_WWNN 0
|
|
|
|
#define NETDEV_FCOE_WWPN 1
|
|
|
|
int (*ndo_fcoe_get_wwn)(struct net_device *dev,
|
|
|
|
u64 *wwn, int type);
|
2009-02-28 06:06:59 +08:00
|
|
|
#endif
|
2011-08-26 17:45:41 +08:00
|
|
|
|
2011-01-19 19:03:53 +08:00
|
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
|
|
int (*ndo_rx_flow_steer)(struct net_device *dev,
|
|
|
|
const struct sk_buff *skb,
|
|
|
|
u16 rxq_index,
|
|
|
|
u32 flow_id);
|
|
|
|
#endif
|
2011-02-13 18:15:37 +08:00
|
|
|
int (*ndo_add_slave)(struct net_device *dev,
|
|
|
|
struct net_device *slave_dev);
|
|
|
|
int (*ndo_del_slave)(struct net_device *dev,
|
|
|
|
struct net_device *slave_dev);
|
2011-11-15 23:29:55 +08:00
|
|
|
netdev_features_t (*ndo_fix_features)(struct net_device *dev,
|
|
|
|
netdev_features_t features);
|
2011-02-16 00:59:17 +08:00
|
|
|
int (*ndo_set_features)(struct net_device *dev,
|
2011-11-15 23:29:55 +08:00
|
|
|
netdev_features_t features);
|
2011-07-25 08:01:38 +08:00
|
|
|
int (*ndo_neigh_construct)(struct neighbour *n);
|
2011-12-20 04:04:41 +08:00
|
|
|
void (*ndo_neigh_destroy)(struct neighbour *n);
|
2008-11-20 13:32:24 +08:00
|
|
|
};
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* The DEVICE structure.
|
|
|
|
* Actually, this whole structure is a big mistake. It mixes I/O
|
|
|
|
* data with strictly "high-level" data, and it has to know about
|
|
|
|
* almost every data structure used in the INET module.
|
|
|
|
*
|
|
|
|
* FIXME: cleanup struct net_device such that network protocol info
|
|
|
|
* moves out.
|
|
|
|
*/
|
|
|
|
|
2009-11-05 01:50:58 +08:00
|
|
|
struct net_device {
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* This is the first field of the "visible" part of this structure
|
|
|
|
* (i.e. as seen by users in the "Space.c" file). It is the name
|
2010-05-27 00:22:40 +08:00
|
|
|
* of the interface.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
char name[IFNAMSIZ];
|
2010-05-06 07:59:26 +08:00
|
|
|
|
2011-08-25 21:35:12 +08:00
|
|
|
struct pm_qos_request pm_qos_req;
|
2010-05-06 07:59:26 +08:00
|
|
|
|
[NET]: Reorder some hot fields of struct net_device
Place them on separate cache lines in SMP to lower memory bouncing
between multiple CPU accessing the device.
- One part is mostly used on receive path (including
eth_type_trans()) (poll_list, poll, quota, weight, last_rx,
dev_addr, broadcast)
- One part is mostly used on queue transmit path (qdisc)
(queue_lock, qdisc, qdisc_sleeping, qdisc_list, tx_queue_len)
- One part is mostly used on xmit path (device)
(xmit_lock, xmit_lock_owner, priv, hard_start_xmit, trans_start)
'features' is placed outside of these hot points, in a location that
may be shared by all cpus (because mostly read)
name_hlist is moved close to name[IFNAMSIZ] to speedup __dev_get_by_name()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-28 06:23:16 +08:00
|
|
|
/* device name hash chain */
|
|
|
|
struct hlist_node name_hlist;
|
2008-09-23 12:28:11 +08:00
|
|
|
/* snmp alias */
|
|
|
|
char *ifalias;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* I/O specific fields
|
|
|
|
* FIXME: Merge these and struct ifmap into one
|
|
|
|
*/
|
|
|
|
unsigned long mem_end; /* shared mem end */
|
|
|
|
unsigned long mem_start; /* shared mem start */
|
|
|
|
unsigned long base_addr; /* device I/O address */
|
|
|
|
unsigned int irq; /* device IRQ number */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Some hardware also needs these fields, but they are not
|
|
|
|
* part of the usual set specified in Space.c.
|
|
|
|
*/
|
|
|
|
|
|
|
|
unsigned long state;
|
|
|
|
|
2007-05-04 06:13:45 +08:00
|
|
|
struct list_head dev_list;
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
struct list_head napi_list;
|
2009-10-27 15:03:04 +08:00
|
|
|
struct list_head unreg_list;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-02-16 00:59:17 +08:00
|
|
|
/* currently active device features */
|
2011-11-15 23:29:55 +08:00
|
|
|
netdev_features_t features;
|
2011-02-16 00:59:17 +08:00
|
|
|
/* user-changeable features */
|
2011-11-15 23:29:55 +08:00
|
|
|
netdev_features_t hw_features;
|
2011-02-16 00:59:17 +08:00
|
|
|
/* user-requested features */
|
2011-11-15 23:29:55 +08:00
|
|
|
netdev_features_t wanted_features;
|
2011-04-12 12:07:39 +08:00
|
|
|
/* mask of features inheritable by VLAN devices */
|
2011-11-15 23:29:55 +08:00
|
|
|
netdev_features_t vlan_features;
|
2011-01-25 07:32:47 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Interface index. Unique device identifier */
|
|
|
|
int ifindex;
|
|
|
|
int iflink;
|
|
|
|
|
2007-03-29 05:29:08 +08:00
|
|
|
struct net_device_stats stats;
|
2010-10-01 05:06:55 +08:00
|
|
|
atomic_long_t rx_dropped; /* dropped packets by core network
|
|
|
|
* Do not use this in drivers.
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-04-27 11:48:23 +08:00
|
|
|
#ifdef CONFIG_WIRELESS_EXT
|
2005-04-17 06:20:36 +08:00
|
|
|
/* List of functions to handle Wireless Extensions (instead of ioctl).
|
|
|
|
* See <net/iw_handler.h> for details. Jean II */
|
|
|
|
const struct iw_handler_def * wireless_handlers;
|
|
|
|
/* Instance data managed by the core of Wireless Extensions. */
|
|
|
|
struct iw_public_data * wireless_data;
|
2007-04-27 11:48:23 +08:00
|
|
|
#endif
|
2008-11-20 13:32:24 +08:00
|
|
|
/* Management operations */
|
|
|
|
const struct net_device_ops *netdev_ops;
|
2006-09-09 02:16:13 +08:00
|
|
|
const struct ethtool_ops *ethtool_ops;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-10-09 16:40:57 +08:00
|
|
|
/* Hardware header description */
|
|
|
|
const struct header_ops *header_ops;
|
|
|
|
|
2006-03-21 09:09:11 +08:00
|
|
|
unsigned int flags; /* interface flags (a la BSD) */
|
2011-05-10 01:42:46 +08:00
|
|
|
unsigned int priv_flags; /* Like 'flags' but invisible to userspace. */
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned short gflags;
|
|
|
|
unsigned short padded; /* How much padding added by alloc_netdev() */
|
|
|
|
|
2006-03-21 09:09:11 +08:00
|
|
|
unsigned char operstate; /* RFC2863 operstate */
|
|
|
|
unsigned char link_mode; /* mapping policy to operstate */
|
|
|
|
|
2011-05-10 01:42:46 +08:00
|
|
|
unsigned char if_port; /* Selectable AUI, TP,..*/
|
|
|
|
unsigned char dma; /* DMA channel */
|
|
|
|
|
2010-05-03 13:27:59 +08:00
|
|
|
unsigned int mtu; /* interface MTU value */
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned short type; /* interface hardware type */
|
|
|
|
unsigned short hard_header_len; /* hardware hdr length */
|
|
|
|
|
2008-05-13 11:48:31 +08:00
|
|
|
/* extra head- and tailroom the hardware may need, but not in all cases
|
|
|
|
* can this be guaranteed, especially tailroom. Some cases also use
|
|
|
|
* LL_MAX_HEADER instead to allocate the skb.
|
|
|
|
*/
|
|
|
|
unsigned short needed_headroom;
|
|
|
|
unsigned short needed_tailroom;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Interface address info. */
|
2005-08-21 08:15:54 +08:00
|
|
|
unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */
|
2010-07-22 10:50:21 +08:00
|
|
|
unsigned char addr_assign_type; /* hw address assignment type */
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned char addr_len; /* hardware address length */
|
2011-07-25 08:01:25 +08:00
|
|
|
unsigned char neigh_priv_len;
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned short dev_id; /* for shared network cards */
|
|
|
|
|
2009-05-23 07:22:17 +08:00
|
|
|
spinlock_t addr_list_lock;
|
2010-04-02 05:22:57 +08:00
|
|
|
struct netdev_hw_addr_list uc; /* Unicast mac addresses */
|
|
|
|
struct netdev_hw_addr_list mc; /* Multicast mac addresses */
|
2011-07-26 07:17:35 +08:00
|
|
|
bool uc_promisc;
|
2008-06-18 12:12:48 +08:00
|
|
|
unsigned int promiscuity;
|
|
|
|
unsigned int allmulti;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
|
|
|
/* Protocol specific pointers */
|
2010-10-20 21:56:05 +08:00
|
|
|
|
2011-11-25 22:40:26 +08:00
|
|
|
#if IS_ENABLED(CONFIG_VLAN_8021Q)
|
2011-12-08 12:11:18 +08:00
|
|
|
struct vlan_info __rcu *vlan_info; /* VLAN info */
|
2010-10-20 21:56:05 +08:00
|
|
|
#endif
|
2011-11-25 22:38:38 +08:00
|
|
|
#if IS_ENABLED(CONFIG_NET_DSA)
|
2011-11-25 22:32:52 +08:00
|
|
|
struct dsa_switch_tree *dsa_ptr; /* dsa specific data */
|
net: Distributed Switch Architecture protocol support
Distributed Switch Architecture is a protocol for managing hardware
switch chips. It consists of a set of MII management registers and
commands to configure the switch, and an ethernet header format to
signal which of the ports of the switch a packet was received from
or is intended to be sent to.
The switches that this driver supports are typically embedded in
access points and routers, and a typical setup with a DSA switch
looks something like this:
+-----------+ +-----------+
| | RGMII | |
| +-------+ +------ 1000baseT MDI ("WAN")
| | | 6-port +------ 1000baseT MDI ("LAN1")
| CPU | | ethernet +------ 1000baseT MDI ("LAN2")
| |MIImgmt| switch +------ 1000baseT MDI ("LAN3")
| +-------+ w/5 PHYs +------ 1000baseT MDI ("LAN4")
| | | |
+-----------+ +-----------+
The switch driver presents each port on the switch as a separate
network interface to Linux, polls the switch to maintain software
link state of those ports, forwards MII management interface
accesses to those network interfaces (e.g. as done by ethtool) to
the switch, and exposes the switch's hardware statistics counters
via the appropriate Linux kernel interfaces.
This initial patch supports the MII management interface register
layout of the Marvell 88E6123, 88E6161 and 88E6165 switch chips, and
supports the "Ethertype DSA" packet tagging format.
(There is no officially registered ethertype for the Ethertype DSA
packet format, so we just grab a random one. The ethertype to use
is programmed into the switch, and the switch driver uses the value
of ETH_P_EDSA for this, so this define can be changed at any time in
the future if the one we chose is allocated to another protocol or
if Ethertype DSA gets its own officially registered ethertype, and
everything will continue to work.)
Signed-off-by: Lennert Buytenhek <buytenh@marvell.com>
Tested-by: Nicolas Pitre <nico@marvell.com>
Tested-by: Byron Bradley <byron.bbradley@gmail.com>
Tested-by: Tim Ellis <tim.ellis@mac.com>
Tested-by: Peter van Valderen <linux@ddcrew.com>
Tested-by: Dirk Teurlings <dirk@upexia.nl>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-07 21:44:02 +08:00
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
void *atalk_ptr; /* AppleTalk link */
|
2010-09-15 12:04:31 +08:00
|
|
|
struct in_device __rcu *ip_ptr; /* IPv4 specific data */
|
2010-10-29 11:09:24 +08:00
|
|
|
struct dn_dev __rcu *dn_ptr; /* DECnet specific data */
|
2010-10-25 05:32:05 +08:00
|
|
|
struct inet6_dev __rcu *ip6_ptr; /* IPv6 specific data */
|
2005-04-17 06:20:36 +08:00
|
|
|
void *ec_ptr; /* Econet specific data */
|
|
|
|
void *ax25_ptr; /* AX.25 specific data */
|
2007-04-24 03:20:05 +08:00
|
|
|
struct wireless_dev *ieee80211_ptr; /* IEEE 802.11 specific data,
|
|
|
|
assign before registering */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
[NET]: Reorder some hot fields of struct net_device
Place them on separate cache lines in SMP to lower memory bouncing
between multiple CPU accessing the device.
- One part is mostly used on receive path (including
eth_type_trans()) (poll_list, poll, quota, weight, last_rx,
dev_addr, broadcast)
- One part is mostly used on queue transmit path (qdisc)
(queue_lock, qdisc, qdisc_sleeping, qdisc_list, tx_queue_len)
- One part is mostly used on xmit path (device)
(xmit_lock, xmit_lock_owner, priv, hard_start_xmit, trans_start)
'features' is placed outside of these hot points, in a location that
may be shared by all cpus (because mostly read)
name_hlist is moved close to name[IFNAMSIZ] to speedup __dev_get_by_name()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-28 06:23:16 +08:00
|
|
|
/*
|
2010-09-16 10:58:13 +08:00
|
|
|
* Cache lines mostly used on receive path (including eth_type_trans())
|
[NET]: Reorder some hot fields of struct net_device
Place them on separate cache lines in SMP to lower memory bouncing
between multiple CPU accessing the device.
- One part is mostly used on receive path (including
eth_type_trans()) (poll_list, poll, quota, weight, last_rx,
dev_addr, broadcast)
- One part is mostly used on queue transmit path (qdisc)
(queue_lock, qdisc, qdisc_sleeping, qdisc_list, tx_queue_len)
- One part is mostly used on xmit path (device)
(xmit_lock, xmit_lock_owner, priv, hard_start_xmit, trans_start)
'features' is placed outside of these hot points, in a location that
may be shared by all cpus (because mostly read)
name_hlist is moved close to name[IFNAMSIZ] to speedup __dev_get_by_name()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-28 06:23:16 +08:00
|
|
|
*/
|
2010-08-31 15:40:16 +08:00
|
|
|
unsigned long last_rx; /* Time of last Rx
|
|
|
|
* This should not be set in
|
|
|
|
* drivers, unless really needed,
|
|
|
|
* because network stack (bonding)
|
|
|
|
* use it if/when necessary, to
|
|
|
|
* avoid dirtying this cache line.
|
|
|
|
*/
|
|
|
|
|
2010-09-16 10:58:13 +08:00
|
|
|
struct net_device *master; /* Pointer to master device of a group,
|
|
|
|
* which this device is member of.
|
|
|
|
*/
|
|
|
|
|
[NET]: Reorder some hot fields of struct net_device
Place them on separate cache lines in SMP to lower memory bouncing
between multiple CPU accessing the device.
- One part is mostly used on receive path (including
eth_type_trans()) (poll_list, poll, quota, weight, last_rx,
dev_addr, broadcast)
- One part is mostly used on queue transmit path (qdisc)
(queue_lock, qdisc, qdisc_sleeping, qdisc_list, tx_queue_len)
- One part is mostly used on xmit path (device)
(xmit_lock, xmit_lock_owner, priv, hard_start_xmit, trans_start)
'features' is placed outside of these hot points, in a location that
may be shared by all cpus (because mostly read)
name_hlist is moved close to name[IFNAMSIZ] to speedup __dev_get_by_name()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-28 06:23:16 +08:00
|
|
|
/* Interface address info used in eth_type_trans() */
|
2009-05-05 10:48:28 +08:00
|
|
|
unsigned char *dev_addr; /* hw address, (before bcast
|
|
|
|
because most packets are
|
|
|
|
unicast) */
|
|
|
|
|
2009-06-17 09:12:19 +08:00
|
|
|
struct netdev_hw_addr_list dev_addrs; /* list of device
|
|
|
|
hw addresses */
|
[NET]: Reorder some hot fields of struct net_device
Place them on separate cache lines in SMP to lower memory bouncing
between multiple CPU accessing the device.
- One part is mostly used on receive path (including
eth_type_trans()) (poll_list, poll, quota, weight, last_rx,
dev_addr, broadcast)
- One part is mostly used on queue transmit path (qdisc)
(queue_lock, qdisc, qdisc_sleeping, qdisc_list, tx_queue_len)
- One part is mostly used on xmit path (device)
(xmit_lock, xmit_lock_owner, priv, hard_start_xmit, trans_start)
'features' is placed outside of these hot points, in a location that
may be shared by all cpus (because mostly read)
name_hlist is moved close to name[IFNAMSIZ] to speedup __dev_get_by_name()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-28 06:23:16 +08:00
|
|
|
|
|
|
|
unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-11-16 20:15:10 +08:00
|
|
|
#ifdef CONFIG_SYSFS
|
2010-03-16 16:03:29 +08:00
|
|
|
struct kset *queues_kset;
|
2011-11-16 20:15:10 +08:00
|
|
|
#endif
|
2010-03-16 16:03:29 +08:00
|
|
|
|
2011-11-16 20:15:10 +08:00
|
|
|
#ifdef CONFIG_RPS
|
2010-03-16 16:03:29 +08:00
|
|
|
struct netdev_rx_queue *_rx;
|
|
|
|
|
2010-09-27 16:24:33 +08:00
|
|
|
/* Number of RX queues allocated at register_netdev() time */
|
2010-03-16 16:03:29 +08:00
|
|
|
unsigned int num_rx_queues;
|
2010-09-27 16:24:33 +08:00
|
|
|
|
|
|
|
/* Number of RX queues currently active in device */
|
|
|
|
unsigned int real_num_rx_queues;
|
2011-01-19 19:03:53 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
|
|
/* CPU reverse-mapping for RX completion interrupts, indexed
|
|
|
|
* by RX queue number. Assigned by driver. This must only be
|
|
|
|
* set if the ndo_rx_flow_steer operation is defined. */
|
|
|
|
struct cpu_rmap *rx_cpu_rmap;
|
|
|
|
#endif
|
2010-03-25 03:13:54 +08:00
|
|
|
#endif
|
2010-03-16 16:03:29 +08:00
|
|
|
|
2010-11-15 14:38:12 +08:00
|
|
|
rx_handler_func_t __rcu *rx_handler;
|
|
|
|
void __rcu *rx_handler_data;
|
2008-07-17 15:34:19 +08:00
|
|
|
|
2010-10-02 14:11:55 +08:00
|
|
|
struct netdev_queue __rcu *ingress_queue;
|
2010-09-16 10:58:13 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Cache lines mostly used on transmit path
|
|
|
|
*/
|
2008-07-17 15:34:19 +08:00
|
|
|
struct netdev_queue *_tx ____cacheline_aligned_in_smp;
|
2008-07-17 16:56:23 +08:00
|
|
|
|
|
|
|
/* Number of TX queues allocated at alloc_netdev_mq() time */
|
2008-07-17 15:34:19 +08:00
|
|
|
unsigned int num_tx_queues;
|
2008-07-17 16:56:23 +08:00
|
|
|
|
|
|
|
/* Number of TX queues currently active in device */
|
|
|
|
unsigned int real_num_tx_queues;
|
|
|
|
|
2009-09-04 14:41:18 +08:00
|
|
|
/* root qdisc from userspace point of view */
|
|
|
|
struct Qdisc *qdisc;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned long tx_queue_len; /* Max frames per queue allowed */
|
2008-08-01 07:58:50 +08:00
|
|
|
spinlock_t tx_global_lock;
|
2010-09-16 10:58:13 +08:00
|
|
|
|
2010-11-26 16:36:09 +08:00
|
|
|
#ifdef CONFIG_XPS
|
2010-11-29 05:43:02 +08:00
|
|
|
struct xps_dev_maps __rcu *xps_maps;
|
2010-11-26 16:36:09 +08:00
|
|
|
#endif
|
2010-11-21 21:17:27 +08:00
|
|
|
|
[NET]: Reorder some hot fields of struct net_device
Place them on separate cache lines in SMP to lower memory bouncing
between multiple CPU accessing the device.
- One part is mostly used on receive path (including
eth_type_trans()) (poll_list, poll, quota, weight, last_rx,
dev_addr, broadcast)
- One part is mostly used on queue transmit path (qdisc)
(queue_lock, qdisc, qdisc_sleeping, qdisc_list, tx_queue_len)
- One part is mostly used on xmit path (device)
(xmit_lock, xmit_lock_owner, priv, hard_start_xmit, trans_start)
'features' is placed outside of these hot points, in a location that
may be shared by all cpus (because mostly read)
name_hlist is moved close to name[IFNAMSIZ] to speedup __dev_get_by_name()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-28 06:23:16 +08:00
|
|
|
/* These may be needed for future network-power-down code. */
|
2009-05-18 11:55:16 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* trans_start here is expensive for high speed devices on SMP,
|
|
|
|
* please use netdev_queue->trans_start instead.
|
|
|
|
*/
|
[NET]: Reorder some hot fields of struct net_device
Place them on separate cache lines in SMP to lower memory bouncing
between multiple CPU accessing the device.
- One part is mostly used on receive path (including
eth_type_trans()) (poll_list, poll, quota, weight, last_rx,
dev_addr, broadcast)
- One part is mostly used on queue transmit path (qdisc)
(queue_lock, qdisc, qdisc_sleeping, qdisc_list, tx_queue_len)
- One part is mostly used on xmit path (device)
(xmit_lock, xmit_lock_owner, priv, hard_start_xmit, trans_start)
'features' is placed outside of these hot points, in a location that
may be shared by all cpus (because mostly read)
name_hlist is moved close to name[IFNAMSIZ] to speedup __dev_get_by_name()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-28 06:23:16 +08:00
|
|
|
unsigned long trans_start; /* Time (in jiffies) of last Tx */
|
|
|
|
|
|
|
|
int watchdog_timeo; /* used by dev_watchdog() */
|
|
|
|
struct timer_list watchdog_timer;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Number of references to this device */
|
net: percpu net_device refcount
We tried very hard to remove all possible dev_hold()/dev_put() pairs in
network stack, using RCU conversions.
There is still an unavoidable device refcount change for every dst we
create/destroy, and this can slow down some workloads (routers or some
app servers, mmap af_packet)
We can switch to a percpu refcount implementation, now dynamic per_cpu
infrastructure is mature. On a 64 cpus machine, this consumes 256 bytes
per device.
On x86, dev_hold(dev) code :
before
lock incl 0x280(%ebx)
after:
movl 0x260(%ebx),%eax
incl fs:(%eax)
Stress bench :
(Sending 160.000.000 UDP frames,
IP route cache disabled, dual E5540 @2.53GHz,
32bit kernel, FIB_TRIE)
Before:
real 1m1.662s
user 0m14.373s
sys 12m55.960s
After:
real 0m51.179s
user 0m15.329s
sys 10m15.942s
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-11 18:22:12 +08:00
|
|
|
int __percpu *pcpu_refcnt;
|
[NET]: Reorder some hot fields of struct net_device
Place them on separate cache lines in SMP to lower memory bouncing
between multiple CPU accessing the device.
- One part is mostly used on receive path (including
eth_type_trans()) (poll_list, poll, quota, weight, last_rx,
dev_addr, broadcast)
- One part is mostly used on queue transmit path (qdisc)
(queue_lock, qdisc, qdisc_sleeping, qdisc_list, tx_queue_len)
- One part is mostly used on xmit path (device)
(xmit_lock, xmit_lock_owner, priv, hard_start_xmit, trans_start)
'features' is placed outside of these hot points, in a location that
may be shared by all cpus (because mostly read)
name_hlist is moved close to name[IFNAMSIZ] to speedup __dev_get_by_name()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-28 06:23:16 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* delayed register/unregister */
|
|
|
|
struct list_head todo_list;
|
|
|
|
/* device index hash chain */
|
|
|
|
struct hlist_node index_hlist;
|
|
|
|
|
linkwatch: linkwatch_forget_dev() to speedup device dismantle
Herbert Xu a écrit :
> On Tue, Nov 17, 2009 at 04:26:04AM -0800, David Miller wrote:
>> Really, the link watch stuff is just due for a redesign. I don't
>> think a simple hack is going to cut it this time, sorry Eric :-)
>
> I have no objections against any redesigns, but since the only
> caller of linkwatch_forget_dev runs in process context with the
> RTNL, it could also legally emit those events.
Thanks guys, here an updated version then, before linkwatch surgery ?
In this version, I force the event to be sent synchronously.
[PATCH net-next-2.6] linkwatch: linkwatch_forget_dev() to speedup device dismantle
time ip link del eth3.103 ; time ip link del eth3.104 ; time ip link del eth3.105
real 0m0.266s
user 0m0.000s
sys 0m0.001s
real 0m0.770s
user 0m0.000s
sys 0m0.000s
real 0m1.022s
user 0m0.000s
sys 0m0.000s
One problem of current schem in vlan dismantle phase is the
holding of device done by following chain :
vlan_dev_stop() ->
netif_carrier_off(dev) ->
linkwatch_fire_event(dev) ->
dev_hold() ...
And __linkwatch_run_queue() runs up to one second later...
A generic fix to this problem is to add a linkwatch_forget_dev() method
to unlink the device from the list of watched devices.
dev->link_watch_next becomes dev->link_watch_list (and use a bit more memory),
to be able to unlink device in O(1).
After patch :
time ip link del eth3.103 ; time ip link del eth3.104 ; time ip link del eth3.105
real 0m0.024s
user 0m0.000s
sys 0m0.000s
real 0m0.032s
user 0m0.000s
sys 0m0.001s
real 0m0.033s
user 0m0.000s
sys 0m0.000s
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-17 13:59:21 +08:00
|
|
|
struct list_head link_watch_list;
|
2007-05-09 09:34:17 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* register/unregister state machine */
|
|
|
|
enum { NETREG_UNINITIALIZED=0,
|
2006-05-11 04:21:17 +08:00
|
|
|
NETREG_REGISTERED, /* completed register_netdevice */
|
2005-04-17 06:20:36 +08:00
|
|
|
NETREG_UNREGISTERING, /* called unregister_netdevice */
|
|
|
|
NETREG_UNREGISTERED, /* completed unregister todo */
|
|
|
|
NETREG_RELEASED, /* called free_netdev */
|
2009-01-15 13:05:05 +08:00
|
|
|
NETREG_DUMMY, /* dummy device for NAPI poll */
|
2011-05-19 20:24:16 +08:00
|
|
|
} reg_state:8;
|
|
|
|
|
|
|
|
bool dismantle; /* device is going do be freed */
|
2010-02-26 14:34:51 +08:00
|
|
|
|
|
|
|
enum {
|
|
|
|
RTNL_LINK_INITIALIZED,
|
|
|
|
RTNL_LINK_INITIALIZING,
|
|
|
|
} rtnl_link_state:16;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-11-20 13:32:24 +08:00
|
|
|
/* Called from unregister, can be used to call free_netdev */
|
|
|
|
void (*destructor)(struct net_device *dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_NETPOLL
|
2005-06-23 13:05:31 +08:00
|
|
|
struct netpoll_info *npinfo;
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
2008-07-15 18:03:33 +08:00
|
|
|
|
2008-03-25 20:47:49 +08:00
|
|
|
#ifdef CONFIG_NET_NS
|
2007-09-12 17:56:32 +08:00
|
|
|
/* Network namespace this network device is inside */
|
|
|
|
struct net *nd_net;
|
2008-03-25 20:47:49 +08:00
|
|
|
#endif
|
2007-09-12 17:56:32 +08:00
|
|
|
|
2008-05-12 18:29:11 +08:00
|
|
|
/* mid-layer private */
|
2010-09-24 07:51:51 +08:00
|
|
|
union {
|
|
|
|
void *ml_priv;
|
|
|
|
struct pcpu_lstats __percpu *lstats; /* loopback stats */
|
2010-09-27 08:33:35 +08:00
|
|
|
struct pcpu_tstats __percpu *tstats; /* tunnel stats */
|
2010-09-28 04:50:33 +08:00
|
|
|
struct pcpu_dstats __percpu *dstats; /* dummy stats */
|
2010-09-24 07:51:51 +08:00
|
|
|
};
|
2008-07-06 12:26:13 +08:00
|
|
|
/* GARP */
|
2010-10-25 05:32:36 +08:00
|
|
|
struct garp_port __rcu *garp_port;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* class/net/name entry */
|
2002-04-10 03:14:34 +08:00
|
|
|
struct device dev;
|
2009-10-29 22:18:21 +08:00
|
|
|
/* space for optional device, statistics, and wireless sysfs groups */
|
|
|
|
const struct attribute_group *sysfs_groups[4];
|
2007-06-14 03:03:51 +08:00
|
|
|
|
|
|
|
/* rtnetlink link ops */
|
|
|
|
const struct rtnl_link_ops *rtnl_link_ops;
|
2007-07-07 04:36:20 +08:00
|
|
|
|
[NET]: Add per-connection option to set max TSO frame size
Update: My mailer ate one of Jarek's feedback mails... Fixed the
parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the
whitespace issue due to a patch import botch. Changed the types from
u32 to unsigned int to be more consistent with other variables in the
area. Also brought the patch up to the latest net-2.6.26 tree.
Update: Made gso_max_size container 32 bits, not 16. Moved the
location of gso_max_size within netdev to be less hotpath. Made more
consistent names between the sock and netdev layers, and added a
define for the max GSO size.
Update: Respun for net-2.6.26 tree.
Update: changed max_gso_frame_size and sk_gso_max_size from signed to
unsigned - thanks Stephen!
This patch adds the ability for device drivers to control the size of
the TSO frames being sent to them, per TCP connection. By setting the
netdevice's gso_max_size value, the socket layer will set the GSO
frame size based on that value. This will propogate into the TCP
layer, and send TSO's of that size to the hardware.
This can be desirable to help tune the bursty nature of TSO on a
per-adapter basis, where one may have 1 GbE and 10 GbE devices
coexisting in a system, one running multiqueue and the other not, etc.
This can also be desirable for devices that cannot support full 64 KB
TSO's, but still want to benefit from some level of segmentation
offloading.
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 18:43:19 +08:00
|
|
|
/* for setting kernel sock attribute on TCP connection setup */
|
|
|
|
#define GSO_MAX_SIZE 65536
|
|
|
|
unsigned int gso_max_size;
|
2008-11-20 13:32:24 +08:00
|
|
|
|
2008-11-25 17:02:08 +08:00
|
|
|
#ifdef CONFIG_DCB
|
2008-11-21 12:52:10 +08:00
|
|
|
/* Data Center Bridging netlink ops */
|
2009-10-05 14:01:03 +08:00
|
|
|
const struct dcbnl_rtnl_ops *dcbnl_ops;
|
2008-11-21 12:52:10 +08:00
|
|
|
#endif
|
2011-01-17 16:06:04 +08:00
|
|
|
u8 num_tc;
|
|
|
|
struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
|
|
|
|
u8 prio_tc_map[TC_BITMASK + 1];
|
2008-11-21 12:52:10 +08:00
|
|
|
|
2011-11-25 22:40:26 +08:00
|
|
|
#if IS_ENABLED(CONFIG_FCOE)
|
2009-02-28 06:06:59 +08:00
|
|
|
/* max exchange id for FCoE LRO by ddp */
|
|
|
|
unsigned int fcoe_ddp_xid;
|
2011-11-22 13:10:51 +08:00
|
|
|
#endif
|
|
|
|
#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
|
|
|
|
struct netprio_map __rcu *priomap;
|
2009-02-28 06:06:59 +08:00
|
|
|
#endif
|
2010-07-17 16:49:36 +08:00
|
|
|
/* phy device may attach itself for hardware timestamping */
|
|
|
|
struct phy_device *phydev;
|
2011-01-14 07:38:30 +08:00
|
|
|
|
|
|
|
/* group the device belongs to */
|
|
|
|
int group;
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
2002-04-10 03:14:34 +08:00
|
|
|
#define to_net_dev(d) container_of(d, struct net_device, dev)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define NETDEV_ALIGN 32
|
|
|
|
|
2011-01-17 16:06:04 +08:00
|
|
|
static inline
|
|
|
|
int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio)
|
|
|
|
{
|
|
|
|
return dev->prio_tc_map[prio & TC_BITMASK];
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc)
|
|
|
|
{
|
|
|
|
if (tc >= dev->num_tc)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void netdev_reset_tc(struct net_device *dev)
|
|
|
|
{
|
|
|
|
dev->num_tc = 0;
|
|
|
|
memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
|
|
|
|
memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset)
|
|
|
|
{
|
|
|
|
if (tc >= dev->num_tc)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
dev->tc_to_txq[tc].count = count;
|
|
|
|
dev->tc_to_txq[tc].offset = offset;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
|
|
|
|
{
|
|
|
|
if (num_tc > TC_MAX_QUEUE)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
dev->num_tc = num_tc;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
int netdev_get_num_tc(struct net_device *dev)
|
|
|
|
{
|
|
|
|
return dev->num_tc;
|
|
|
|
}
|
|
|
|
|
2008-07-17 15:34:19 +08:00
|
|
|
static inline
|
|
|
|
struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
|
|
|
|
unsigned int index)
|
|
|
|
{
|
|
|
|
return &dev->_tx[index];
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netdev_for_each_tx_queue(struct net_device *dev,
|
|
|
|
void (*f)(struct net_device *,
|
|
|
|
struct netdev_queue *,
|
|
|
|
void *),
|
|
|
|
void *arg)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
for (i = 0; i < dev->num_tx_queues; i++)
|
|
|
|
f(dev, &dev->_tx[i], arg);
|
|
|
|
}
|
|
|
|
|
2008-03-25 20:47:49 +08:00
|
|
|
/*
|
|
|
|
* Net namespace inlines
|
|
|
|
*/
|
|
|
|
static inline
|
|
|
|
struct net *dev_net(const struct net_device *dev)
|
|
|
|
{
|
2010-06-01 14:51:19 +08:00
|
|
|
return read_pnet(&dev->nd_net);
|
2008-03-25 20:47:49 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
2008-03-26 15:48:17 +08:00
|
|
|
void dev_net_set(struct net_device *dev, struct net *net)
|
2008-03-25 20:47:49 +08:00
|
|
|
{
|
|
|
|
#ifdef CONFIG_NET_NS
|
2008-04-16 17:02:18 +08:00
|
|
|
release_net(dev->nd_net);
|
|
|
|
dev->nd_net = hold_net(net);
|
2008-03-25 20:47:49 +08:00
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
2008-10-07 21:45:02 +08:00
|
|
|
static inline bool netdev_uses_dsa_tags(struct net_device *dev)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_NET_DSA_TAG_DSA
|
|
|
|
if (dev->dsa_ptr != NULL)
|
|
|
|
return dsa_uses_dsa_tags(dev->dsa_ptr);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2010-01-30 20:23:03 +08:00
|
|
|
#ifndef CONFIG_NET_NS
|
|
|
|
static inline void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
|
|
|
|
{
|
|
|
|
skb->dev = dev;
|
|
|
|
}
|
|
|
|
#else /* CONFIG_NET_NS */
|
|
|
|
void skb_set_dev(struct sk_buff *skb, struct net_device *dev);
|
|
|
|
#endif
|
|
|
|
|
2008-10-07 21:46:07 +08:00
|
|
|
static inline bool netdev_uses_trailer_tags(struct net_device *dev)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_NET_DSA_TAG_TRAILER
|
|
|
|
if (dev->dsa_ptr != NULL)
|
|
|
|
return dsa_uses_trailer_tags(dev->dsa_ptr);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netdev_priv - access network device private data
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Get network device private data
|
|
|
|
*/
|
2007-06-14 03:03:21 +08:00
|
|
|
static inline void *netdev_priv(const struct net_device *dev)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2009-05-27 12:42:37 +08:00
|
|
|
return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Set the sysfs physical device reference for the network logical device
|
|
|
|
* if set prior to registration will cause a symlink during initialization.
|
|
|
|
*/
|
2002-04-10 03:14:34 +08:00
|
|
|
#define SET_NETDEV_DEV(net, pdev) ((net)->dev.parent = (pdev))
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-09-01 05:08:19 +08:00
|
|
|
/* Set the sysfs device type for the network logical device to allow
|
|
|
|
* fin grained indentification of different network device types. For
|
|
|
|
* example Ethernet, Wirelss LAN, Bluetooth, WiMAX etc.
|
|
|
|
*/
|
|
|
|
#define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype))
|
|
|
|
|
2007-11-01 17:21:47 +08:00
|
|
|
/**
|
|
|
|
* netif_napi_add - initialize a napi context
|
|
|
|
* @dev: network device
|
|
|
|
* @napi: napi context
|
|
|
|
* @poll: polling function
|
|
|
|
* @weight: default weight
|
|
|
|
*
|
|
|
|
* netif_napi_add() must be used to initialize a napi context prior to calling
|
|
|
|
* *any* of the other napi related functions.
|
|
|
|
*/
|
net: Add Generic Receive Offload infrastructure
This patch adds the top-level GRO (Generic Receive Offload) infrastructure.
This is pretty similar to LRO except that this is protocol-independent.
Instead of holding packets in an lro_mgr structure, they're now held in
napi_struct.
For drivers that intend to use this, they can set the NETIF_F_GRO bit and
call napi_gro_receive instead of netif_receive_skb or just call netif_rx.
The latter will call napi_receive_skb automatically. When napi_gro_receive
is used, the driver must either call napi_complete/napi_rx_complete, or
call napi_gro_flush in softirq context if the driver uses the primitives
__napi_complete/__napi_rx_complete.
Protocols will set the gro_receive and gro_complete function pointers in
order to participate in this scheme.
In addition to the packet, gro_receive will get a list of currently held
packets. Each packet in the list has a same_flow field which is non-zero
if it is a potential match for the new packet. For each packet that may
match, they also have a flush field which is non-zero if the held packet
must not be merged with the new packet.
Once gro_receive has determined that the new skb matches a held packet,
the held packet may be processed immediately if the new skb cannot be
merged with it. In this case gro_receive should return the pointer to
the existing skb in gro_list. Otherwise the new skb should be merged into
the existing packet and NULL should be returned, unless the new skb makes
it impossible for any further merges to be made (e.g., FIN packet) where
the merged skb should be returned.
Whenever the skb is merged into an existing entry, the gro_receive
function should set NAPI_GRO_CB(skb)->same_flow. Note that if an skb
merely matches an existing entry but can't be merged with it, then
this shouldn't be set.
If gro_receive finds it pointless to hold the new skb for future merging,
it should set NAPI_GRO_CB(skb)->flush.
Held packets will be flushed by napi_gro_flush which is called by
napi_complete and napi_rx_complete.
Currently held packets are stored in a singly liked list just like LRO.
The list is limited to a maximum of 8 entries. In future, this may be
expanded to use a hash table to allow more flows to be held for merging.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16 15:38:52 +08:00
|
|
|
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
|
|
|
|
int (*poll)(struct napi_struct *, int), int weight);
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
|
2008-07-09 06:13:05 +08:00
|
|
|
/**
|
|
|
|
* netif_napi_del - remove a napi context
|
|
|
|
* @napi: napi context
|
|
|
|
*
|
|
|
|
* netif_napi_del() removes a napi context from the network device napi list
|
|
|
|
*/
|
net: Add Generic Receive Offload infrastructure
This patch adds the top-level GRO (Generic Receive Offload) infrastructure.
This is pretty similar to LRO except that this is protocol-independent.
Instead of holding packets in an lro_mgr structure, they're now held in
napi_struct.
For drivers that intend to use this, they can set the NETIF_F_GRO bit and
call napi_gro_receive instead of netif_receive_skb or just call netif_rx.
The latter will call napi_receive_skb automatically. When napi_gro_receive
is used, the driver must either call napi_complete/napi_rx_complete, or
call napi_gro_flush in softirq context if the driver uses the primitives
__napi_complete/__napi_rx_complete.
Protocols will set the gro_receive and gro_complete function pointers in
order to participate in this scheme.
In addition to the packet, gro_receive will get a list of currently held
packets. Each packet in the list has a same_flow field which is non-zero
if it is a potential match for the new packet. For each packet that may
match, they also have a flush field which is non-zero if the held packet
must not be merged with the new packet.
Once gro_receive has determined that the new skb matches a held packet,
the held packet may be processed immediately if the new skb cannot be
merged with it. In this case gro_receive should return the pointer to
the existing skb in gro_list. Otherwise the new skb should be merged into
the existing packet and NULL should be returned, unless the new skb makes
it impossible for any further merges to be made (e.g., FIN packet) where
the merged skb should be returned.
Whenever the skb is merged into an existing entry, the gro_receive
function should set NAPI_GRO_CB(skb)->same_flow. Note that if an skb
merely matches an existing entry but can't be merged with it, then
this shouldn't be set.
If gro_receive finds it pointless to hold the new skb for future merging,
it should set NAPI_GRO_CB(skb)->flush.
Held packets will be flushed by napi_gro_flush which is called by
napi_complete and napi_rx_complete.
Currently held packets are stored in a singly liked list just like LRO.
The list is limited to a maximum of 8 entries. In future, this may be
expanded to use a hash table to allow more flows to be held for merging.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16 15:38:52 +08:00
|
|
|
void netif_napi_del(struct napi_struct *napi);
|
|
|
|
|
|
|
|
struct napi_gro_cb {
|
2009-05-27 02:50:21 +08:00
|
|
|
/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
|
|
|
|
void *frag0;
|
|
|
|
|
2009-05-27 02:50:27 +08:00
|
|
|
/* Length of frag0. */
|
|
|
|
unsigned int frag0_len;
|
|
|
|
|
2009-01-29 22:19:50 +08:00
|
|
|
/* This indicates where we are processing relative to skb->data. */
|
|
|
|
int data_offset;
|
|
|
|
|
net: Add Generic Receive Offload infrastructure
This patch adds the top-level GRO (Generic Receive Offload) infrastructure.
This is pretty similar to LRO except that this is protocol-independent.
Instead of holding packets in an lro_mgr structure, they're now held in
napi_struct.
For drivers that intend to use this, they can set the NETIF_F_GRO bit and
call napi_gro_receive instead of netif_receive_skb or just call netif_rx.
The latter will call napi_receive_skb automatically. When napi_gro_receive
is used, the driver must either call napi_complete/napi_rx_complete, or
call napi_gro_flush in softirq context if the driver uses the primitives
__napi_complete/__napi_rx_complete.
Protocols will set the gro_receive and gro_complete function pointers in
order to participate in this scheme.
In addition to the packet, gro_receive will get a list of currently held
packets. Each packet in the list has a same_flow field which is non-zero
if it is a potential match for the new packet. For each packet that may
match, they also have a flush field which is non-zero if the held packet
must not be merged with the new packet.
Once gro_receive has determined that the new skb matches a held packet,
the held packet may be processed immediately if the new skb cannot be
merged with it. In this case gro_receive should return the pointer to
the existing skb in gro_list. Otherwise the new skb should be merged into
the existing packet and NULL should be returned, unless the new skb makes
it impossible for any further merges to be made (e.g., FIN packet) where
the merged skb should be returned.
Whenever the skb is merged into an existing entry, the gro_receive
function should set NAPI_GRO_CB(skb)->same_flow. Note that if an skb
merely matches an existing entry but can't be merged with it, then
this shouldn't be set.
If gro_receive finds it pointless to hold the new skb for future merging,
it should set NAPI_GRO_CB(skb)->flush.
Held packets will be flushed by napi_gro_flush which is called by
napi_complete and napi_rx_complete.
Currently held packets are stored in a singly liked list just like LRO.
The list is limited to a maximum of 8 entries. In future, this may be
expanded to use a hash table to allow more flows to be held for merging.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16 15:38:52 +08:00
|
|
|
/* This is non-zero if the packet may be of the same flow. */
|
|
|
|
int same_flow;
|
|
|
|
|
|
|
|
/* This is non-zero if the packet cannot be merged with the new skb. */
|
|
|
|
int flush;
|
|
|
|
|
|
|
|
/* Number of segments aggregated. */
|
|
|
|
int count;
|
2009-01-05 08:13:40 +08:00
|
|
|
|
|
|
|
/* Free the skb? */
|
|
|
|
int free;
|
net: Add Generic Receive Offload infrastructure
This patch adds the top-level GRO (Generic Receive Offload) infrastructure.
This is pretty similar to LRO except that this is protocol-independent.
Instead of holding packets in an lro_mgr structure, they're now held in
napi_struct.
For drivers that intend to use this, they can set the NETIF_F_GRO bit and
call napi_gro_receive instead of netif_receive_skb or just call netif_rx.
The latter will call napi_receive_skb automatically. When napi_gro_receive
is used, the driver must either call napi_complete/napi_rx_complete, or
call napi_gro_flush in softirq context if the driver uses the primitives
__napi_complete/__napi_rx_complete.
Protocols will set the gro_receive and gro_complete function pointers in
order to participate in this scheme.
In addition to the packet, gro_receive will get a list of currently held
packets. Each packet in the list has a same_flow field which is non-zero
if it is a potential match for the new packet. For each packet that may
match, they also have a flush field which is non-zero if the held packet
must not be merged with the new packet.
Once gro_receive has determined that the new skb matches a held packet,
the held packet may be processed immediately if the new skb cannot be
merged with it. In this case gro_receive should return the pointer to
the existing skb in gro_list. Otherwise the new skb should be merged into
the existing packet and NULL should be returned, unless the new skb makes
it impossible for any further merges to be made (e.g., FIN packet) where
the merged skb should be returned.
Whenever the skb is merged into an existing entry, the gro_receive
function should set NAPI_GRO_CB(skb)->same_flow. Note that if an skb
merely matches an existing entry but can't be merged with it, then
this shouldn't be set.
If gro_receive finds it pointless to hold the new skb for future merging,
it should set NAPI_GRO_CB(skb)->flush.
Held packets will be flushed by napi_gro_flush which is called by
napi_complete and napi_rx_complete.
Currently held packets are stored in a singly liked list just like LRO.
The list is limited to a maximum of 8 entries. In future, this may be
expanded to use a hash table to allow more flows to be held for merging.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16 15:38:52 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
|
2008-07-09 06:13:05 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
struct packet_type {
|
2005-08-10 10:34:12 +08:00
|
|
|
__be16 type; /* This is really htons(ether_type). */
|
|
|
|
struct net_device *dev; /* NULL is wildcarded here */
|
|
|
|
int (*func) (struct sk_buff *,
|
|
|
|
struct net_device *,
|
|
|
|
struct packet_type *,
|
|
|
|
struct net_device *);
|
2006-06-28 04:22:38 +08:00
|
|
|
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
|
2011-11-15 23:29:55 +08:00
|
|
|
netdev_features_t features);
|
2006-07-09 04:34:56 +08:00
|
|
|
int (*gso_send_check)(struct sk_buff *skb);
|
net: Add Generic Receive Offload infrastructure
This patch adds the top-level GRO (Generic Receive Offload) infrastructure.
This is pretty similar to LRO except that this is protocol-independent.
Instead of holding packets in an lro_mgr structure, they're now held in
napi_struct.
For drivers that intend to use this, they can set the NETIF_F_GRO bit and
call napi_gro_receive instead of netif_receive_skb or just call netif_rx.
The latter will call napi_receive_skb automatically. When napi_gro_receive
is used, the driver must either call napi_complete/napi_rx_complete, or
call napi_gro_flush in softirq context if the driver uses the primitives
__napi_complete/__napi_rx_complete.
Protocols will set the gro_receive and gro_complete function pointers in
order to participate in this scheme.
In addition to the packet, gro_receive will get a list of currently held
packets. Each packet in the list has a same_flow field which is non-zero
if it is a potential match for the new packet. For each packet that may
match, they also have a flush field which is non-zero if the held packet
must not be merged with the new packet.
Once gro_receive has determined that the new skb matches a held packet,
the held packet may be processed immediately if the new skb cannot be
merged with it. In this case gro_receive should return the pointer to
the existing skb in gro_list. Otherwise the new skb should be merged into
the existing packet and NULL should be returned, unless the new skb makes
it impossible for any further merges to be made (e.g., FIN packet) where
the merged skb should be returned.
Whenever the skb is merged into an existing entry, the gro_receive
function should set NAPI_GRO_CB(skb)->same_flow. Note that if an skb
merely matches an existing entry but can't be merged with it, then
this shouldn't be set.
If gro_receive finds it pointless to hold the new skb for future merging,
it should set NAPI_GRO_CB(skb)->flush.
Held packets will be flushed by napi_gro_flush which is called by
napi_complete and napi_rx_complete.
Currently held packets are stored in a singly liked list just like LRO.
The list is limited to a maximum of 8 entries. In future, this may be
expanded to use a hash table to allow more flows to be held for merging.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16 15:38:52 +08:00
|
|
|
struct sk_buff **(*gro_receive)(struct sk_buff **head,
|
|
|
|
struct sk_buff *skb);
|
|
|
|
int (*gro_complete)(struct sk_buff *skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
void *af_packet_priv;
|
|
|
|
struct list_head list;
|
|
|
|
};
|
|
|
|
|
|
|
|
#include <linux/notifier.h>
|
|
|
|
|
2011-07-26 08:13:09 +08:00
|
|
|
/* netdevice notifier chain. Please remember to update the rtnetlink
|
|
|
|
* notification exclusion list in rtnetlink_event() when adding new
|
|
|
|
* types.
|
|
|
|
*/
|
|
|
|
#define NETDEV_UP 0x0001 /* For now you can't veto a device up/down */
|
|
|
|
#define NETDEV_DOWN 0x0002
|
|
|
|
#define NETDEV_REBOOT 0x0003 /* Tell a protocol stack a network interface
|
|
|
|
detected a hardware crash and restarted
|
|
|
|
- we can use this eg to kick tcp sessions
|
|
|
|
once done */
|
|
|
|
#define NETDEV_CHANGE 0x0004 /* Notify device state change */
|
|
|
|
#define NETDEV_REGISTER 0x0005
|
|
|
|
#define NETDEV_UNREGISTER 0x0006
|
|
|
|
#define NETDEV_CHANGEMTU 0x0007
|
|
|
|
#define NETDEV_CHANGEADDR 0x0008
|
|
|
|
#define NETDEV_GOING_DOWN 0x0009
|
|
|
|
#define NETDEV_CHANGENAME 0x000A
|
|
|
|
#define NETDEV_FEAT_CHANGE 0x000B
|
|
|
|
#define NETDEV_BONDING_FAILOVER 0x000C
|
|
|
|
#define NETDEV_PRE_UP 0x000D
|
|
|
|
#define NETDEV_PRE_TYPE_CHANGE 0x000E
|
|
|
|
#define NETDEV_POST_TYPE_CHANGE 0x000F
|
|
|
|
#define NETDEV_POST_INIT 0x0010
|
|
|
|
#define NETDEV_UNREGISTER_BATCH 0x0011
|
|
|
|
#define NETDEV_RELEASE 0x0012
|
|
|
|
#define NETDEV_NOTIFY_PEERS 0x0013
|
|
|
|
#define NETDEV_JOIN 0x0014
|
|
|
|
|
|
|
|
extern int register_netdevice_notifier(struct notifier_block *nb);
|
|
|
|
extern int unregister_netdevice_notifier(struct notifier_block *nb);
|
|
|
|
extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
|
|
|
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
extern rwlock_t dev_base_lock; /* Device list lock */
|
|
|
|
|
2007-05-04 06:13:45 +08:00
|
|
|
|
2007-09-18 02:56:21 +08:00
|
|
|
#define for_each_netdev(net, d) \
|
|
|
|
list_for_each_entry(d, &(net)->dev_base_head, dev_list)
|
2009-11-30 06:25:26 +08:00
|
|
|
#define for_each_netdev_reverse(net, d) \
|
|
|
|
list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list)
|
2009-11-04 21:43:23 +08:00
|
|
|
#define for_each_netdev_rcu(net, d) \
|
|
|
|
list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list)
|
2007-09-18 02:56:21 +08:00
|
|
|
#define for_each_netdev_safe(net, d, n) \
|
|
|
|
list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list)
|
|
|
|
#define for_each_netdev_continue(net, d) \
|
|
|
|
list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list)
|
2009-11-10 15:54:47 +08:00
|
|
|
#define for_each_netdev_continue_rcu(net, d) \
|
|
|
|
list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
|
2007-09-18 02:56:21 +08:00
|
|
|
#define net_device_entry(lh) list_entry(lh, struct net_device, dev_list)
|
2007-05-04 06:13:45 +08:00
|
|
|
|
2007-09-12 20:57:09 +08:00
|
|
|
static inline struct net_device *next_net_device(struct net_device *dev)
|
|
|
|
{
|
|
|
|
struct list_head *lh;
|
|
|
|
struct net *net;
|
|
|
|
|
2008-03-25 20:47:49 +08:00
|
|
|
net = dev_net(dev);
|
2007-09-12 20:57:09 +08:00
|
|
|
lh = dev->dev_list.next;
|
|
|
|
return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
|
|
|
|
}
|
|
|
|
|
2009-11-12 01:34:30 +08:00
|
|
|
static inline struct net_device *next_net_device_rcu(struct net_device *dev)
|
|
|
|
{
|
|
|
|
struct list_head *lh;
|
|
|
|
struct net *net;
|
|
|
|
|
|
|
|
net = dev_net(dev);
|
2011-01-27 02:08:02 +08:00
|
|
|
lh = rcu_dereference(list_next_rcu(&dev->dev_list));
|
2009-11-12 01:34:30 +08:00
|
|
|
return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
|
|
|
|
}
|
|
|
|
|
2007-09-12 20:57:09 +08:00
|
|
|
static inline struct net_device *first_net_device(struct net *net)
|
|
|
|
{
|
|
|
|
return list_empty(&net->dev_base_head) ? NULL :
|
|
|
|
net_device_entry(net->dev_base_head.next);
|
|
|
|
}
|
2007-05-04 06:13:45 +08:00
|
|
|
|
2011-01-27 02:08:02 +08:00
|
|
|
static inline struct net_device *first_net_device_rcu(struct net *net)
|
|
|
|
{
|
|
|
|
struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head));
|
|
|
|
|
|
|
|
return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int netdev_boot_setup_check(struct net_device *dev);
|
|
|
|
extern unsigned long netdev_boot_base(const char *prefix, int unit);
|
2010-12-05 09:23:53 +08:00
|
|
|
extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
|
|
|
|
const char *hwaddr);
|
2007-09-18 02:56:21 +08:00
|
|
|
extern struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
|
|
|
|
extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void dev_add_pack(struct packet_type *pt);
|
|
|
|
extern void dev_remove_pack(struct packet_type *pt);
|
|
|
|
extern void __dev_remove_pack(struct packet_type *pt);
|
|
|
|
|
2010-06-07 19:42:13 +08:00
|
|
|
extern struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags,
|
|
|
|
unsigned short mask);
|
2007-09-18 02:56:21 +08:00
|
|
|
extern struct net_device *dev_get_by_name(struct net *net, const char *name);
|
2009-10-30 15:11:27 +08:00
|
|
|
extern struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
|
2007-09-18 02:56:21 +08:00
|
|
|
extern struct net_device *__dev_get_by_name(struct net *net, const char *name);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int dev_alloc_name(struct net_device *dev, const char *name);
|
|
|
|
extern int dev_open(struct net_device *dev);
|
|
|
|
extern int dev_close(struct net_device *dev);
|
2008-06-20 07:15:47 +08:00
|
|
|
extern void dev_disable_lro(struct net_device *dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int dev_queue_xmit(struct sk_buff *skb);
|
|
|
|
extern int register_netdevice(struct net_device *dev);
|
2009-10-27 15:03:04 +08:00
|
|
|
extern void unregister_netdevice_queue(struct net_device *dev,
|
|
|
|
struct list_head *head);
|
2009-10-27 15:04:19 +08:00
|
|
|
extern void unregister_netdevice_many(struct list_head *head);
|
2009-10-27 15:03:04 +08:00
|
|
|
static inline void unregister_netdevice(struct net_device *dev)
|
|
|
|
{
|
|
|
|
unregister_netdevice_queue(dev, NULL);
|
|
|
|
}
|
|
|
|
|
net: percpu net_device refcount
We tried very hard to remove all possible dev_hold()/dev_put() pairs in
network stack, using RCU conversions.
There is still an unavoidable device refcount change for every dst we
create/destroy, and this can slow down some workloads (routers or some
app servers, mmap af_packet)
We can switch to a percpu refcount implementation, now dynamic per_cpu
infrastructure is mature. On a 64 cpus machine, this consumes 256 bytes
per device.
On x86, dev_hold(dev) code :
before
lock incl 0x280(%ebx)
after:
movl 0x260(%ebx),%eax
incl fs:(%eax)
Stress bench :
(Sending 160.000.000 UDP frames,
IP route cache disabled, dual E5540 @2.53GHz,
32bit kernel, FIB_TRIE)
Before:
real 1m1.662s
user 0m14.373s
sys 12m55.960s
After:
real 0m51.179s
user 0m15.329s
sys 10m15.942s
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-11 18:22:12 +08:00
|
|
|
extern int netdev_refcnt_read(const struct net_device *dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void free_netdev(struct net_device *dev);
|
|
|
|
extern void synchronize_net(void);
|
2009-01-15 13:05:05 +08:00
|
|
|
extern int init_dummy_netdev(struct net_device *dev);
|
2009-03-05 15:46:25 +08:00
|
|
|
extern void netdev_resync_ops(struct net_device *dev);
|
2009-01-15 13:05:05 +08:00
|
|
|
|
2007-09-18 02:56:21 +08:00
|
|
|
extern struct net_device *dev_get_by_index(struct net *net, int ifindex);
|
|
|
|
extern struct net_device *__dev_get_by_index(struct net *net, int ifindex);
|
2009-10-20 03:18:49 +08:00
|
|
|
extern struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int dev_restart(struct net_device *dev);
|
|
|
|
#ifdef CONFIG_NETPOLL_TRAP
|
|
|
|
extern int netpoll_trap(void);
|
|
|
|
#endif
|
2009-01-29 22:19:50 +08:00
|
|
|
extern int skb_gro_receive(struct sk_buff **head,
|
|
|
|
struct sk_buff *skb);
|
2009-05-27 02:50:21 +08:00
|
|
|
extern void skb_gro_reset_offset(struct sk_buff *skb);
|
2009-01-29 22:19:50 +08:00
|
|
|
|
|
|
|
static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
return NAPI_GRO_CB(skb)->data_offset;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline unsigned int skb_gro_len(const struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
return skb->len - NAPI_GRO_CB(skb)->data_offset;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len)
|
|
|
|
{
|
|
|
|
NAPI_GRO_CB(skb)->data_offset += len;
|
|
|
|
}
|
|
|
|
|
2009-05-27 02:50:28 +08:00
|
|
|
static inline void *skb_gro_header_fast(struct sk_buff *skb,
|
|
|
|
unsigned int offset)
|
2009-01-29 22:19:50 +08:00
|
|
|
{
|
2009-05-27 02:50:28 +08:00
|
|
|
return NAPI_GRO_CB(skb)->frag0 + offset;
|
|
|
|
}
|
2009-05-27 02:50:21 +08:00
|
|
|
|
2009-05-27 02:50:28 +08:00
|
|
|
static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen)
|
|
|
|
{
|
|
|
|
return NAPI_GRO_CB(skb)->frag0_len < hlen;
|
|
|
|
}
|
2009-05-27 02:50:21 +08:00
|
|
|
|
2009-05-27 02:50:28 +08:00
|
|
|
static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
|
|
|
|
unsigned int offset)
|
|
|
|
{
|
2011-07-27 21:16:28 +08:00
|
|
|
if (!pskb_may_pull(skb, hlen))
|
|
|
|
return NULL;
|
|
|
|
|
2009-05-27 02:50:28 +08:00
|
|
|
NAPI_GRO_CB(skb)->frag0 = NULL;
|
|
|
|
NAPI_GRO_CB(skb)->frag0_len = 0;
|
2011-07-27 21:16:28 +08:00
|
|
|
return skb->data + offset;
|
2009-01-29 22:19:50 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-02-09 02:00:37 +08:00
|
|
|
static inline void *skb_gro_mac_header(struct sk_buff *skb)
|
|
|
|
{
|
2009-05-27 02:50:23 +08:00
|
|
|
return NAPI_GRO_CB(skb)->frag0 ?: skb_mac_header(skb);
|
2009-02-09 02:00:37 +08:00
|
|
|
}
|
|
|
|
|
2009-04-27 20:44:45 +08:00
|
|
|
static inline void *skb_gro_network_header(struct sk_buff *skb)
|
|
|
|
{
|
2009-05-27 02:50:23 +08:00
|
|
|
return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) +
|
|
|
|
skb_network_offset(skb);
|
2009-04-27 20:44:45 +08:00
|
|
|
}
|
|
|
|
|
2007-10-09 16:36:32 +08:00
|
|
|
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
|
|
|
|
unsigned short type,
|
2007-10-09 16:40:57 +08:00
|
|
|
const void *daddr, const void *saddr,
|
|
|
|
unsigned len)
|
2007-10-09 16:36:32 +08:00
|
|
|
{
|
2007-10-22 22:16:14 +08:00
|
|
|
if (!dev->header_ops || !dev->header_ops->create)
|
2007-10-09 16:36:32 +08:00
|
|
|
return 0;
|
2007-10-09 16:40:57 +08:00
|
|
|
|
|
|
|
return dev->header_ops->create(skb, dev, type, daddr, saddr, len);
|
2007-10-09 16:36:32 +08:00
|
|
|
}
|
|
|
|
|
2007-09-27 13:13:38 +08:00
|
|
|
static inline int dev_parse_header(const struct sk_buff *skb,
|
|
|
|
unsigned char *haddr)
|
|
|
|
{
|
|
|
|
const struct net_device *dev = skb->dev;
|
|
|
|
|
2007-10-18 20:09:28 +08:00
|
|
|
if (!dev->header_ops || !dev->header_ops->parse)
|
2007-09-27 13:13:38 +08:00
|
|
|
return 0;
|
2007-10-09 16:40:57 +08:00
|
|
|
return dev->header_ops->parse(skb, haddr);
|
2007-09-27 13:13:38 +08:00
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
|
|
|
|
extern int register_gifconf(unsigned int family, gifconf_func_t * gifconf);
|
|
|
|
static inline int unregister_gifconf(unsigned int family)
|
|
|
|
{
|
|
|
|
return register_gifconf(family, NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2010-04-19 13:07:33 +08:00
|
|
|
* Incoming packets are placed on per-cpu queues
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2009-11-05 01:50:58 +08:00
|
|
|
struct softnet_data {
|
2008-07-16 17:15:04 +08:00
|
|
|
struct Qdisc *output_queue;
|
2010-04-27 07:06:24 +08:00
|
|
|
struct Qdisc **output_queue_tailp;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct list_head poll_list;
|
|
|
|
struct sk_buff *completion_queue;
|
2010-04-28 06:07:33 +08:00
|
|
|
struct sk_buff_head process_queue;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-05-02 13:42:16 +08:00
|
|
|
/* stats */
|
2010-05-03 13:27:59 +08:00
|
|
|
unsigned int processed;
|
|
|
|
unsigned int time_squeeze;
|
|
|
|
unsigned int cpu_collision;
|
|
|
|
unsigned int received_rps;
|
2010-05-02 13:42:16 +08:00
|
|
|
|
2010-04-15 15:16:59 +08:00
|
|
|
#ifdef CONFIG_RPS
|
2010-04-19 13:07:33 +08:00
|
|
|
struct softnet_data *rps_ipi_list;
|
|
|
|
|
|
|
|
/* Elements below can be accessed between CPUs for RPS */
|
2010-03-16 16:03:29 +08:00
|
|
|
struct call_single_data csd ____cacheline_aligned_in_smp;
|
2010-04-19 13:07:33 +08:00
|
|
|
struct softnet_data *rps_ipi_next;
|
|
|
|
unsigned int cpu;
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
unsigned int input_queue_head;
|
2010-05-21 02:37:59 +08:00
|
|
|
unsigned int input_queue_tail;
|
2010-03-19 08:45:44 +08:00
|
|
|
#endif
|
2010-05-02 13:42:16 +08:00
|
|
|
unsigned dropped;
|
2010-03-16 16:03:29 +08:00
|
|
|
struct sk_buff_head input_pkt_queue;
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
struct napi_struct backlog;
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
2010-05-21 02:37:59 +08:00
|
|
|
static inline void input_queue_head_incr(struct softnet_data *sd)
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
{
|
|
|
|
#ifdef CONFIG_RPS
|
2010-05-21 02:37:59 +08:00
|
|
|
sd->input_queue_head++;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void input_queue_tail_incr_save(struct softnet_data *sd,
|
|
|
|
unsigned int *qtail)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_RPS
|
|
|
|
*qtail = ++sd->input_queue_tail;
|
rfs: Receive Flow Steering
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
2010-03-16 16:03:29 +08:00
|
|
|
DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-07-16 17:15:04 +08:00
|
|
|
extern void __netif_schedule(struct Qdisc *q);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-07-09 14:11:25 +08:00
|
|
|
static inline void netif_schedule_queue(struct netdev_queue *txq)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2011-11-29 00:32:44 +08:00
|
|
|
if (!(txq->state & QUEUE_STATE_ANY_XOFF))
|
2008-07-16 17:15:04 +08:00
|
|
|
__netif_schedule(txq->qdisc);
|
2008-07-09 14:11:25 +08:00
|
|
|
}
|
|
|
|
|
2008-07-17 16:56:23 +08:00
|
|
|
static inline void netif_tx_schedule_all(struct net_device *dev)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
for (i = 0; i < dev->num_tx_queues; i++)
|
|
|
|
netif_schedule_queue(netdev_get_tx_queue(dev, i));
|
|
|
|
}
|
|
|
|
|
2008-07-23 05:09:06 +08:00
|
|
|
static inline void netif_tx_start_queue(struct netdev_queue *dev_queue)
|
|
|
|
{
|
2011-11-29 00:32:44 +08:00
|
|
|
clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
|
2008-07-23 05:09:06 +08:00
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_start_queue - allow transmit
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Allow upper layers to call the device hard_start_xmit routine.
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline void netif_start_queue(struct net_device *dev)
|
|
|
|
{
|
2008-07-17 15:34:19 +08:00
|
|
|
netif_tx_start_queue(netdev_get_tx_queue(dev, 0));
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2008-07-17 16:56:23 +08:00
|
|
|
static inline void netif_tx_start_all_queues(struct net_device *dev)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
for (i = 0; i < dev->num_tx_queues; i++) {
|
|
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
|
|
|
|
netif_tx_start_queue(txq);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-07-09 14:14:46 +08:00
|
|
|
static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
#ifdef CONFIG_NETPOLL_TRAP
|
2007-04-29 11:57:37 +08:00
|
|
|
if (netpoll_trap()) {
|
2009-08-30 04:21:21 +08:00
|
|
|
netif_tx_start_queue(dev_queue);
|
2005-04-17 06:20:36 +08:00
|
|
|
return;
|
2007-04-29 11:57:37 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
2011-11-29 00:32:44 +08:00
|
|
|
if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state))
|
2008-07-16 17:15:04 +08:00
|
|
|
__netif_schedule(dev_queue->qdisc);
|
2008-07-09 14:14:46 +08:00
|
|
|
}
|
|
|
|
|
2008-07-23 05:09:06 +08:00
|
|
|
/**
|
|
|
|
* netif_wake_queue - restart transmit
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Allow upper layers to call the device hard_start_xmit routine.
|
|
|
|
* Used for flow control when transmit resources are available.
|
|
|
|
*/
|
2008-07-09 14:14:46 +08:00
|
|
|
static inline void netif_wake_queue(struct net_device *dev)
|
|
|
|
{
|
2008-07-17 15:34:19 +08:00
|
|
|
netif_tx_wake_queue(netdev_get_tx_queue(dev, 0));
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2008-07-17 16:56:23 +08:00
|
|
|
static inline void netif_tx_wake_all_queues(struct net_device *dev)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
for (i = 0; i < dev->num_tx_queues; i++) {
|
|
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
|
|
|
|
netif_tx_wake_queue(txq);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-07-23 05:09:06 +08:00
|
|
|
static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
|
|
|
|
{
|
2010-11-06 14:39:32 +08:00
|
|
|
if (WARN_ON(!dev_queue)) {
|
2011-03-01 15:06:12 +08:00
|
|
|
pr_info("netif_stop_queue() cannot be called before register_netdev()\n");
|
2010-11-06 14:39:32 +08:00
|
|
|
return;
|
|
|
|
}
|
2011-11-29 00:32:44 +08:00
|
|
|
set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
|
2008-07-23 05:09:06 +08:00
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_stop_queue - stop transmitted packets
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Stop upper layers calling the device hard_start_xmit routine.
|
|
|
|
* Used for flow control when transmit resources are unavailable.
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline void netif_stop_queue(struct net_device *dev)
|
|
|
|
{
|
2008-07-17 15:34:19 +08:00
|
|
|
netif_tx_stop_queue(netdev_get_tx_queue(dev, 0));
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2008-07-17 16:56:23 +08:00
|
|
|
static inline void netif_tx_stop_all_queues(struct net_device *dev)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
for (i = 0; i < dev->num_tx_queues; i++) {
|
|
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
|
|
|
|
netif_tx_stop_queue(txq);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-07-23 05:09:06 +08:00
|
|
|
static inline int netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
|
|
|
|
{
|
2011-11-29 00:32:44 +08:00
|
|
|
return test_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
|
2008-07-23 05:09:06 +08:00
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_queue_stopped - test if transmit queue is flowblocked
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Test if transmit queue on device is currently unable to send.
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline int netif_queue_stopped(const struct net_device *dev)
|
|
|
|
{
|
2008-07-17 15:34:19 +08:00
|
|
|
return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0));
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2011-11-29 00:32:44 +08:00
|
|
|
static inline int netif_xmit_stopped(const struct netdev_queue *dev_queue)
|
2008-08-01 07:58:50 +08:00
|
|
|
{
|
2011-11-29 00:32:44 +08:00
|
|
|
return dev_queue->state & QUEUE_STATE_ANY_XOFF;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue)
|
|
|
|
{
|
|
|
|
return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN;
|
|
|
|
}
|
|
|
|
|
2011-11-29 00:32:52 +08:00
|
|
|
static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
|
|
|
|
unsigned int bytes)
|
|
|
|
{
|
2011-11-29 00:33:09 +08:00
|
|
|
#ifdef CONFIG_BQL
|
|
|
|
dql_queued(&dev_queue->dql, bytes);
|
|
|
|
if (unlikely(dql_avail(&dev_queue->dql) < 0)) {
|
|
|
|
set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
|
|
|
|
if (unlikely(dql_avail(&dev_queue->dql) >= 0))
|
|
|
|
clear_bit(__QUEUE_STATE_STACK_XOFF,
|
|
|
|
&dev_queue->state);
|
|
|
|
}
|
|
|
|
#endif
|
2011-11-29 00:32:52 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes)
|
|
|
|
{
|
|
|
|
netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
|
|
|
|
unsigned pkts, unsigned bytes)
|
|
|
|
{
|
2011-11-29 00:33:09 +08:00
|
|
|
#ifdef CONFIG_BQL
|
|
|
|
if (likely(bytes)) {
|
|
|
|
dql_completed(&dev_queue->dql, bytes);
|
|
|
|
if (unlikely(test_bit(__QUEUE_STATE_STACK_XOFF,
|
|
|
|
&dev_queue->state) &&
|
|
|
|
dql_avail(&dev_queue->dql) >= 0)) {
|
|
|
|
if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF,
|
|
|
|
&dev_queue->state))
|
|
|
|
netif_schedule_queue(dev_queue);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#endif
|
2011-11-29 00:32:52 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netdev_completed_queue(struct net_device *dev,
|
|
|
|
unsigned pkts, unsigned bytes)
|
|
|
|
{
|
|
|
|
netdev_tx_completed_queue(netdev_get_tx_queue(dev, 0), pkts, bytes);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netdev_tx_reset_queue(struct netdev_queue *q)
|
|
|
|
{
|
2011-11-29 00:33:09 +08:00
|
|
|
#ifdef CONFIG_BQL
|
|
|
|
dql_reset(&q->dql);
|
|
|
|
#endif
|
2011-11-29 00:32:52 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netdev_reset_queue(struct net_device *dev_queue)
|
|
|
|
{
|
|
|
|
netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));
|
2008-08-01 07:58:50 +08:00
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_running - test if up
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Test if the device has been brought up.
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline int netif_running(const struct net_device *dev)
|
|
|
|
{
|
|
|
|
return test_bit(__LINK_STATE_START, &dev->state);
|
|
|
|
}
|
|
|
|
|
2007-07-07 04:36:20 +08:00
|
|
|
/*
|
|
|
|
* Routines to manage the subqueues on a device. We only need start
|
|
|
|
* stop, and a check if it's stopped. All other device management is
|
|
|
|
* done at the overall netdevice level.
|
|
|
|
* Also test the device if we're multiqueue.
|
|
|
|
*/
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* netif_start_subqueue - allow sending packets on subqueue
|
|
|
|
* @dev: network device
|
|
|
|
* @queue_index: sub queue index
|
|
|
|
*
|
|
|
|
* Start individual transmit queue of a device with multiple transmit queues.
|
|
|
|
*/
|
2007-07-07 04:36:20 +08:00
|
|
|
static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
|
|
|
|
{
|
2008-07-17 16:56:23 +08:00
|
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
|
2009-08-30 04:21:21 +08:00
|
|
|
|
|
|
|
netif_tx_start_queue(txq);
|
2007-07-07 04:36:20 +08:00
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_stop_subqueue - stop sending packets on subqueue
|
|
|
|
* @dev: network device
|
|
|
|
* @queue_index: sub queue index
|
|
|
|
*
|
|
|
|
* Stop individual transmit queue of a device with multiple transmit queues.
|
|
|
|
*/
|
2007-07-07 04:36:20 +08:00
|
|
|
static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
|
|
|
|
{
|
2008-07-17 16:56:23 +08:00
|
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
|
2007-07-07 04:36:20 +08:00
|
|
|
#ifdef CONFIG_NETPOLL_TRAP
|
|
|
|
if (netpoll_trap())
|
|
|
|
return;
|
|
|
|
#endif
|
2009-08-30 04:21:21 +08:00
|
|
|
netif_tx_stop_queue(txq);
|
2007-07-07 04:36:20 +08:00
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_subqueue_stopped - test status of subqueue
|
|
|
|
* @dev: network device
|
|
|
|
* @queue_index: sub queue index
|
|
|
|
*
|
|
|
|
* Check individual transmit queue of a device with multiple transmit queues.
|
|
|
|
*/
|
2007-10-22 08:01:56 +08:00
|
|
|
static inline int __netif_subqueue_stopped(const struct net_device *dev,
|
2007-07-07 04:36:20 +08:00
|
|
|
u16 queue_index)
|
|
|
|
{
|
2008-07-17 16:56:23 +08:00
|
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
|
2009-08-30 04:21:21 +08:00
|
|
|
|
|
|
|
return netif_tx_queue_stopped(txq);
|
2007-07-07 04:36:20 +08:00
|
|
|
}
|
|
|
|
|
2007-10-22 08:01:56 +08:00
|
|
|
static inline int netif_subqueue_stopped(const struct net_device *dev,
|
|
|
|
struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb));
|
|
|
|
}
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* netif_wake_subqueue - allow sending packets on subqueue
|
|
|
|
* @dev: network device
|
|
|
|
* @queue_index: sub queue index
|
|
|
|
*
|
|
|
|
* Resume individual transmit queue of a device with multiple transmit queues.
|
|
|
|
*/
|
2007-07-07 04:36:20 +08:00
|
|
|
static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
|
|
|
|
{
|
2008-07-17 16:56:23 +08:00
|
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
|
2007-07-07 04:36:20 +08:00
|
|
|
#ifdef CONFIG_NETPOLL_TRAP
|
|
|
|
if (netpoll_trap())
|
|
|
|
return;
|
|
|
|
#endif
|
2011-11-29 00:32:44 +08:00
|
|
|
if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state))
|
2008-07-16 17:15:04 +08:00
|
|
|
__netif_schedule(txq->qdisc);
|
2007-07-07 04:36:20 +08:00
|
|
|
}
|
|
|
|
|
2010-12-13 14:27:10 +08:00
|
|
|
/*
|
|
|
|
* Returns a Tx hash for the given packet when dev->real_num_tx_queues is used
|
|
|
|
* as a distribution range limit for the returned value.
|
|
|
|
*/
|
|
|
|
static inline u16 skb_tx_hash(const struct net_device *dev,
|
|
|
|
const struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
return __skb_tx_hash(dev, skb, dev->real_num_tx_queues);
|
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_is_multiqueue - test if device has multiple transmit queues
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Check if device has multiple transmit queues
|
|
|
|
*/
|
2007-07-07 04:36:20 +08:00
|
|
|
static inline int netif_is_multiqueue(const struct net_device *dev)
|
|
|
|
{
|
2010-09-23 04:43:57 +08:00
|
|
|
return dev->num_tx_queues > 1;
|
2007-07-07 04:36:20 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-10-19 02:04:39 +08:00
|
|
|
extern int netif_set_real_num_tx_queues(struct net_device *dev,
|
|
|
|
unsigned int txq);
|
2010-07-01 21:21:57 +08:00
|
|
|
|
2010-09-27 16:24:33 +08:00
|
|
|
#ifdef CONFIG_RPS
|
|
|
|
extern int netif_set_real_num_rx_queues(struct net_device *dev,
|
|
|
|
unsigned int rxq);
|
|
|
|
#else
|
|
|
|
static inline int netif_set_real_num_rx_queues(struct net_device *dev,
|
|
|
|
unsigned int rxq)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2010-09-27 16:24:49 +08:00
|
|
|
static inline int netif_copy_real_num_queues(struct net_device *to_dev,
|
|
|
|
const struct net_device *from_dev)
|
|
|
|
{
|
|
|
|
netif_set_real_num_tx_queues(to_dev, from_dev->real_num_tx_queues);
|
|
|
|
#ifdef CONFIG_RPS
|
|
|
|
return netif_set_real_num_rx_queues(to_dev,
|
|
|
|
from_dev->real_num_rx_queues);
|
|
|
|
#else
|
|
|
|
return 0;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Use this variant when it is known for sure that it
|
2008-03-29 07:33:00 +08:00
|
|
|
* is executing from hardware interrupt context or with hardware interrupts
|
|
|
|
* disabled.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
extern void dev_kfree_skb_irq(struct sk_buff *skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Use this variant in places where it could be invoked
|
2008-03-29 07:33:00 +08:00
|
|
|
* from either hardware interrupt or other context, with hardware interrupts
|
|
|
|
* either disabled or enabled.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2006-03-30 07:57:29 +08:00
|
|
|
extern void dev_kfree_skb_any(struct sk_buff *skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
extern int netif_rx(struct sk_buff *skb);
|
|
|
|
extern int netif_rx_ni(struct sk_buff *skb);
|
|
|
|
extern int netif_receive_skb(struct sk_buff *skb);
|
2009-10-29 15:17:09 +08:00
|
|
|
extern gro_result_t dev_gro_receive(struct napi_struct *napi,
|
2009-01-07 02:49:34 +08:00
|
|
|
struct sk_buff *skb);
|
2009-10-30 12:36:53 +08:00
|
|
|
extern gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb);
|
|
|
|
extern gro_result_t napi_gro_receive(struct napi_struct *napi,
|
net: Add Generic Receive Offload infrastructure
This patch adds the top-level GRO (Generic Receive Offload) infrastructure.
This is pretty similar to LRO except that this is protocol-independent.
Instead of holding packets in an lro_mgr structure, they're now held in
napi_struct.
For drivers that intend to use this, they can set the NETIF_F_GRO bit and
call napi_gro_receive instead of netif_receive_skb or just call netif_rx.
The latter will call napi_receive_skb automatically. When napi_gro_receive
is used, the driver must either call napi_complete/napi_rx_complete, or
call napi_gro_flush in softirq context if the driver uses the primitives
__napi_complete/__napi_rx_complete.
Protocols will set the gro_receive and gro_complete function pointers in
order to participate in this scheme.
In addition to the packet, gro_receive will get a list of currently held
packets. Each packet in the list has a same_flow field which is non-zero
if it is a potential match for the new packet. For each packet that may
match, they also have a flush field which is non-zero if the held packet
must not be merged with the new packet.
Once gro_receive has determined that the new skb matches a held packet,
the held packet may be processed immediately if the new skb cannot be
merged with it. In this case gro_receive should return the pointer to
the existing skb in gro_list. Otherwise the new skb should be merged into
the existing packet and NULL should be returned, unless the new skb makes
it impossible for any further merges to be made (e.g., FIN packet) where
the merged skb should be returned.
Whenever the skb is merged into an existing entry, the gro_receive
function should set NAPI_GRO_CB(skb)->same_flow. Note that if an skb
merely matches an existing entry but can't be merged with it, then
this shouldn't be set.
If gro_receive finds it pointless to hold the new skb for future merging,
it should set NAPI_GRO_CB(skb)->flush.
Held packets will be flushed by napi_gro_flush which is called by
napi_complete and napi_rx_complete.
Currently held packets are stored in a singly liked list just like LRO.
The list is limited to a maximum of 8 entries. In future, this may be
expanded to use a hash table to allow more flows to be held for merging.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16 15:38:52 +08:00
|
|
|
struct sk_buff *skb);
|
2010-09-01 02:25:32 +08:00
|
|
|
extern void napi_gro_flush(struct napi_struct *napi);
|
2009-04-16 17:02:07 +08:00
|
|
|
extern struct sk_buff * napi_get_frags(struct napi_struct *napi);
|
2009-10-30 12:36:53 +08:00
|
|
|
extern gro_result_t napi_frags_finish(struct napi_struct *napi,
|
2009-10-29 15:17:09 +08:00
|
|
|
struct sk_buff *skb,
|
|
|
|
gro_result_t ret);
|
2009-04-16 17:02:07 +08:00
|
|
|
extern struct sk_buff * napi_frags_skb(struct napi_struct *napi);
|
2009-10-30 12:36:53 +08:00
|
|
|
extern gro_result_t napi_gro_frags(struct napi_struct *napi);
|
2009-04-16 17:02:07 +08:00
|
|
|
|
|
|
|
static inline void napi_free_frags(struct napi_struct *napi)
|
|
|
|
{
|
|
|
|
kfree_skb(napi->skb);
|
|
|
|
napi->skb = NULL;
|
|
|
|
}
|
|
|
|
|
2010-06-02 05:52:08 +08:00
|
|
|
extern int netdev_rx_handler_register(struct net_device *dev,
|
2010-06-10 11:34:59 +08:00
|
|
|
rx_handler_func_t *rx_handler,
|
|
|
|
void *rx_handler_data);
|
2010-06-02 05:52:08 +08:00
|
|
|
extern void netdev_rx_handler_unregister(struct net_device *dev);
|
|
|
|
|
2005-11-10 02:34:45 +08:00
|
|
|
extern int dev_valid_name(const char *name);
|
2007-09-18 02:56:21 +08:00
|
|
|
extern int dev_ioctl(struct net *net, unsigned int cmd, void __user *);
|
|
|
|
extern int dev_ethtool(struct net *net, struct ifreq *);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern unsigned dev_get_flags(const struct net_device *);
|
2010-02-26 14:34:53 +08:00
|
|
|
extern int __dev_change_flags(struct net_device *, unsigned int flags);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int dev_change_flags(struct net_device *, unsigned);
|
2010-02-26 14:34:53 +08:00
|
|
|
extern void __dev_notify_flags(struct net_device *, unsigned int old_flags);
|
2008-09-30 17:22:14 +08:00
|
|
|
extern int dev_change_name(struct net_device *, const char *);
|
2008-09-23 12:28:11 +08:00
|
|
|
extern int dev_set_alias(struct net_device *, const char *, size_t);
|
2007-09-12 19:53:49 +08:00
|
|
|
extern int dev_change_net_namespace(struct net_device *,
|
|
|
|
struct net *, const char *);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int dev_set_mtu(struct net_device *, int);
|
2011-01-14 07:38:30 +08:00
|
|
|
extern void dev_set_group(struct net_device *, int);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int dev_set_mac_address(struct net_device *,
|
|
|
|
struct sockaddr *);
|
2006-06-22 17:57:17 +08:00
|
|
|
extern int dev_hard_start_xmit(struct sk_buff *skb,
|
2008-07-17 16:56:23 +08:00
|
|
|
struct net_device *dev,
|
|
|
|
struct netdev_queue *txq);
|
2009-11-26 14:07:08 +08:00
|
|
|
extern int dev_forward_skb(struct net_device *dev,
|
|
|
|
struct sk_buff *skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-08-16 13:18:02 +08:00
|
|
|
extern int netdev_budget;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Called by rtnetlink.c:rtnl_unlock() */
|
|
|
|
extern void netdev_run_todo(void);
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* dev_put - release reference to device
|
|
|
|
* @dev: network device
|
|
|
|
*
|
2007-10-11 12:18:17 +08:00
|
|
|
* Release reference to device to allow it to be freed.
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline void dev_put(struct net_device *dev)
|
|
|
|
{
|
2011-12-23 01:58:51 +08:00
|
|
|
this_cpu_dec(*dev->pcpu_refcnt);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* dev_hold - get reference to device
|
|
|
|
* @dev: network device
|
|
|
|
*
|
2007-10-11 12:18:17 +08:00
|
|
|
* Hold reference to device to keep it from being freed.
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
*/
|
2006-03-21 14:32:28 +08:00
|
|
|
static inline void dev_hold(struct net_device *dev)
|
|
|
|
{
|
2011-12-23 01:58:51 +08:00
|
|
|
this_cpu_inc(*dev->pcpu_refcnt);
|
2006-03-21 14:32:28 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Carrier loss detection, dial on demand. The functions netif_carrier_on
|
|
|
|
* and _off may be called from IRQ context, but it is caller
|
|
|
|
* who is responsible for serialization of these calls.
|
2006-03-21 09:09:11 +08:00
|
|
|
*
|
|
|
|
* The name carrier is inappropriate, these functions should really be
|
|
|
|
* called netif_lowerlayer_*() because they represent the state of any
|
|
|
|
* kind of lower layer not just hardware media.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
extern void linkwatch_fire_event(struct net_device *dev);
|
linkwatch: linkwatch_forget_dev() to speedup device dismantle
Herbert Xu a écrit :
> On Tue, Nov 17, 2009 at 04:26:04AM -0800, David Miller wrote:
>> Really, the link watch stuff is just due for a redesign. I don't
>> think a simple hack is going to cut it this time, sorry Eric :-)
>
> I have no objections against any redesigns, but since the only
> caller of linkwatch_forget_dev runs in process context with the
> RTNL, it could also legally emit those events.
Thanks guys, here an updated version then, before linkwatch surgery ?
In this version, I force the event to be sent synchronously.
[PATCH net-next-2.6] linkwatch: linkwatch_forget_dev() to speedup device dismantle
time ip link del eth3.103 ; time ip link del eth3.104 ; time ip link del eth3.105
real 0m0.266s
user 0m0.000s
sys 0m0.001s
real 0m0.770s
user 0m0.000s
sys 0m0.000s
real 0m1.022s
user 0m0.000s
sys 0m0.000s
One problem of current schem in vlan dismantle phase is the
holding of device done by following chain :
vlan_dev_stop() ->
netif_carrier_off(dev) ->
linkwatch_fire_event(dev) ->
dev_hold() ...
And __linkwatch_run_queue() runs up to one second later...
A generic fix to this problem is to add a linkwatch_forget_dev() method
to unlink the device from the list of watched devices.
dev->link_watch_next becomes dev->link_watch_list (and use a bit more memory),
to be able to unlink device in O(1).
After patch :
time ip link del eth3.103 ; time ip link del eth3.104 ; time ip link del eth3.105
real 0m0.024s
user 0m0.000s
sys 0m0.000s
real 0m0.032s
user 0m0.000s
sys 0m0.001s
real 0m0.033s
user 0m0.000s
sys 0m0.000s
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-17 13:59:21 +08:00
|
|
|
extern void linkwatch_forget_dev(struct net_device *dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_carrier_ok - test if carrier present
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Check if carrier is present on device
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline int netif_carrier_ok(const struct net_device *dev)
|
|
|
|
{
|
|
|
|
return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
|
|
|
|
}
|
|
|
|
|
2009-05-18 11:55:16 +08:00
|
|
|
extern unsigned long dev_trans_start(struct net_device *dev);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void __netdev_watchdog_up(struct net_device *dev);
|
|
|
|
|
2005-08-12 06:32:53 +08:00
|
|
|
extern void netif_carrier_on(struct net_device *dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-08-12 06:32:53 +08:00
|
|
|
extern void netif_carrier_off(struct net_device *dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-05-26 08:09:42 +08:00
|
|
|
extern void netif_notify_peers(struct net_device *dev);
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_dormant_on - mark device as dormant.
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Mark device as dormant (as per RFC2863).
|
|
|
|
*
|
|
|
|
* The dormant state indicates that the relevant interface is not
|
|
|
|
* actually in a condition to pass packets (i.e., it is not 'up') but is
|
|
|
|
* in a "pending" state, waiting for some external event. For "on-
|
|
|
|
* demand" interfaces, this new state identifies the situation where the
|
|
|
|
* interface is waiting for events to place it in the up state.
|
|
|
|
*
|
|
|
|
*/
|
2006-03-21 09:09:11 +08:00
|
|
|
static inline void netif_dormant_on(struct net_device *dev)
|
|
|
|
{
|
|
|
|
if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state))
|
|
|
|
linkwatch_fire_event(dev);
|
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_dormant_off - set device as not dormant.
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Device is not in dormant state.
|
|
|
|
*/
|
2006-03-21 09:09:11 +08:00
|
|
|
static inline void netif_dormant_off(struct net_device *dev)
|
|
|
|
{
|
|
|
|
if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state))
|
|
|
|
linkwatch_fire_event(dev);
|
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_dormant - test if carrier present
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Check if carrier is present on device
|
|
|
|
*/
|
2006-03-21 09:09:11 +08:00
|
|
|
static inline int netif_dormant(const struct net_device *dev)
|
|
|
|
{
|
|
|
|
return test_bit(__LINK_STATE_DORMANT, &dev->state);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_oper_up - test if device is operational
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Check if carrier is operational
|
|
|
|
*/
|
2009-11-05 01:50:58 +08:00
|
|
|
static inline int netif_oper_up(const struct net_device *dev)
|
|
|
|
{
|
2006-03-21 09:09:11 +08:00
|
|
|
return (dev->operstate == IF_OPER_UP ||
|
|
|
|
dev->operstate == IF_OPER_UNKNOWN /* backward compat */);
|
|
|
|
}
|
|
|
|
|
[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 07:41:36 +08:00
|
|
|
/**
|
|
|
|
* netif_device_present - is device available or removed
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Check if device has not been removed from system.
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline int netif_device_present(struct net_device *dev)
|
|
|
|
{
|
|
|
|
return test_bit(__LINK_STATE_PRESENT, &dev->state);
|
|
|
|
}
|
|
|
|
|
2006-03-30 07:57:29 +08:00
|
|
|
extern void netif_device_detach(struct net_device *dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-03-30 07:57:29 +08:00
|
|
|
extern void netif_device_attach(struct net_device *dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Network interface message level settings
|
|
|
|
*/
|
|
|
|
|
|
|
|
enum {
|
|
|
|
NETIF_MSG_DRV = 0x0001,
|
|
|
|
NETIF_MSG_PROBE = 0x0002,
|
|
|
|
NETIF_MSG_LINK = 0x0004,
|
|
|
|
NETIF_MSG_TIMER = 0x0008,
|
|
|
|
NETIF_MSG_IFDOWN = 0x0010,
|
|
|
|
NETIF_MSG_IFUP = 0x0020,
|
|
|
|
NETIF_MSG_RX_ERR = 0x0040,
|
|
|
|
NETIF_MSG_TX_ERR = 0x0080,
|
|
|
|
NETIF_MSG_TX_QUEUED = 0x0100,
|
|
|
|
NETIF_MSG_INTR = 0x0200,
|
|
|
|
NETIF_MSG_TX_DONE = 0x0400,
|
|
|
|
NETIF_MSG_RX_STATUS = 0x0800,
|
|
|
|
NETIF_MSG_PKTDATA = 0x1000,
|
|
|
|
NETIF_MSG_HW = 0x2000,
|
|
|
|
NETIF_MSG_WOL = 0x4000,
|
|
|
|
};
|
|
|
|
|
|
|
|
#define netif_msg_drv(p) ((p)->msg_enable & NETIF_MSG_DRV)
|
|
|
|
#define netif_msg_probe(p) ((p)->msg_enable & NETIF_MSG_PROBE)
|
|
|
|
#define netif_msg_link(p) ((p)->msg_enable & NETIF_MSG_LINK)
|
|
|
|
#define netif_msg_timer(p) ((p)->msg_enable & NETIF_MSG_TIMER)
|
|
|
|
#define netif_msg_ifdown(p) ((p)->msg_enable & NETIF_MSG_IFDOWN)
|
|
|
|
#define netif_msg_ifup(p) ((p)->msg_enable & NETIF_MSG_IFUP)
|
|
|
|
#define netif_msg_rx_err(p) ((p)->msg_enable & NETIF_MSG_RX_ERR)
|
|
|
|
#define netif_msg_tx_err(p) ((p)->msg_enable & NETIF_MSG_TX_ERR)
|
|
|
|
#define netif_msg_tx_queued(p) ((p)->msg_enable & NETIF_MSG_TX_QUEUED)
|
|
|
|
#define netif_msg_intr(p) ((p)->msg_enable & NETIF_MSG_INTR)
|
|
|
|
#define netif_msg_tx_done(p) ((p)->msg_enable & NETIF_MSG_TX_DONE)
|
|
|
|
#define netif_msg_rx_status(p) ((p)->msg_enable & NETIF_MSG_RX_STATUS)
|
|
|
|
#define netif_msg_pktdata(p) ((p)->msg_enable & NETIF_MSG_PKTDATA)
|
|
|
|
#define netif_msg_hw(p) ((p)->msg_enable & NETIF_MSG_HW)
|
|
|
|
#define netif_msg_wol(p) ((p)->msg_enable & NETIF_MSG_WOL)
|
|
|
|
|
|
|
|
static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
|
|
|
|
{
|
|
|
|
/* use default */
|
|
|
|
if (debug_value < 0 || debug_value >= (sizeof(u32) * 8))
|
|
|
|
return default_msg_enable_bits;
|
|
|
|
if (debug_value == 0) /* no output */
|
|
|
|
return 0;
|
|
|
|
/* set low N bits */
|
|
|
|
return (1 << debug_value) - 1;
|
|
|
|
}
|
|
|
|
|
2008-07-09 14:13:53 +08:00
|
|
|
static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
|
2006-06-10 03:20:56 +08:00
|
|
|
{
|
2008-07-09 14:13:53 +08:00
|
|
|
spin_lock(&txq->_xmit_lock);
|
|
|
|
txq->xmit_lock_owner = cpu;
|
2007-09-17 05:40:49 +08:00
|
|
|
}
|
|
|
|
|
2008-07-17 16:56:23 +08:00
|
|
|
static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
|
|
|
|
{
|
|
|
|
spin_lock_bh(&txq->_xmit_lock);
|
|
|
|
txq->xmit_lock_owner = smp_processor_id();
|
|
|
|
}
|
|
|
|
|
2008-08-01 07:58:50 +08:00
|
|
|
static inline int __netif_tx_trylock(struct netdev_queue *txq)
|
|
|
|
{
|
|
|
|
int ok = spin_trylock(&txq->_xmit_lock);
|
|
|
|
if (likely(ok))
|
|
|
|
txq->xmit_lock_owner = smp_processor_id();
|
|
|
|
return ok;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __netif_tx_unlock(struct netdev_queue *txq)
|
|
|
|
{
|
|
|
|
txq->xmit_lock_owner = -1;
|
|
|
|
spin_unlock(&txq->_xmit_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
|
|
|
|
{
|
|
|
|
txq->xmit_lock_owner = -1;
|
|
|
|
spin_unlock_bh(&txq->_xmit_lock);
|
|
|
|
}
|
|
|
|
|
2009-05-26 13:58:01 +08:00
|
|
|
static inline void txq_trans_update(struct netdev_queue *txq)
|
|
|
|
{
|
|
|
|
if (txq->xmit_lock_owner != -1)
|
|
|
|
txq->trans_start = jiffies;
|
|
|
|
}
|
|
|
|
|
2008-07-23 05:09:06 +08:00
|
|
|
/**
|
|
|
|
* netif_tx_lock - grab network device transmit lock
|
|
|
|
* @dev: network device
|
|
|
|
*
|
|
|
|
* Get network device transmit lock
|
|
|
|
*/
|
2007-09-17 05:40:49 +08:00
|
|
|
static inline void netif_tx_lock(struct net_device *dev)
|
|
|
|
{
|
2008-07-17 15:34:19 +08:00
|
|
|
unsigned int i;
|
2008-08-01 07:58:50 +08:00
|
|
|
int cpu;
|
2008-07-09 14:13:53 +08:00
|
|
|
|
2008-08-01 07:58:50 +08:00
|
|
|
spin_lock(&dev->tx_global_lock);
|
|
|
|
cpu = smp_processor_id();
|
2008-07-17 15:34:19 +08:00
|
|
|
for (i = 0; i < dev->num_tx_queues; i++) {
|
|
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
|
2008-08-01 07:58:50 +08:00
|
|
|
|
|
|
|
/* We are the only thread of execution doing a
|
|
|
|
* freeze, but we have to grab the _xmit_lock in
|
|
|
|
* order to synchronize with threads which are in
|
|
|
|
* the ->hard_start_xmit() handler and already
|
|
|
|
* checked the frozen bit.
|
|
|
|
*/
|
2008-07-17 15:34:19 +08:00
|
|
|
__netif_tx_lock(txq, cpu);
|
2008-08-01 07:58:50 +08:00
|
|
|
set_bit(__QUEUE_STATE_FROZEN, &txq->state);
|
|
|
|
__netif_tx_unlock(txq);
|
2008-07-17 15:34:19 +08:00
|
|
|
}
|
2006-06-10 03:20:56 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netif_tx_lock_bh(struct net_device *dev)
|
|
|
|
{
|
2008-07-17 15:34:19 +08:00
|
|
|
local_bh_disable();
|
|
|
|
netif_tx_lock(dev);
|
2006-06-10 03:20:56 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netif_tx_unlock(struct net_device *dev)
|
|
|
|
{
|
2008-07-17 15:34:19 +08:00
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
for (i = 0; i < dev->num_tx_queues; i++) {
|
|
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
|
2008-07-09 14:13:53 +08:00
|
|
|
|
2008-08-01 07:58:50 +08:00
|
|
|
/* No need to grab the _xmit_lock here. If the
|
|
|
|
* queue is not stopped for another reason, we
|
|
|
|
* force a schedule.
|
|
|
|
*/
|
|
|
|
clear_bit(__QUEUE_STATE_FROZEN, &txq->state);
|
2009-08-30 04:21:21 +08:00
|
|
|
netif_schedule_queue(txq);
|
2008-08-01 07:58:50 +08:00
|
|
|
}
|
|
|
|
spin_unlock(&dev->tx_global_lock);
|
2006-06-10 03:20:56 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netif_tx_unlock_bh(struct net_device *dev)
|
|
|
|
{
|
2008-07-17 15:34:19 +08:00
|
|
|
netif_tx_unlock(dev);
|
|
|
|
local_bh_enable();
|
2006-06-10 03:20:56 +08:00
|
|
|
}
|
|
|
|
|
2008-07-09 14:13:53 +08:00
|
|
|
#define HARD_TX_LOCK(dev, txq, cpu) { \
|
2007-09-17 05:40:49 +08:00
|
|
|
if ((dev->features & NETIF_F_LLTX) == 0) { \
|
2008-07-09 14:13:53 +08:00
|
|
|
__netif_tx_lock(txq, cpu); \
|
2007-09-17 05:40:49 +08:00
|
|
|
} \
|
|
|
|
}
|
|
|
|
|
2008-07-09 14:13:53 +08:00
|
|
|
#define HARD_TX_UNLOCK(dev, txq) { \
|
2007-09-17 05:40:49 +08:00
|
|
|
if ((dev->features & NETIF_F_LLTX) == 0) { \
|
2008-07-09 14:13:53 +08:00
|
|
|
__netif_tx_unlock(txq); \
|
2007-09-17 05:40:49 +08:00
|
|
|
} \
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline void netif_tx_disable(struct net_device *dev)
|
|
|
|
{
|
2008-07-17 16:56:23 +08:00
|
|
|
unsigned int i;
|
2008-08-01 07:58:50 +08:00
|
|
|
int cpu;
|
2008-07-17 16:56:23 +08:00
|
|
|
|
2008-08-01 07:58:50 +08:00
|
|
|
local_bh_disable();
|
|
|
|
cpu = smp_processor_id();
|
2008-07-17 16:56:23 +08:00
|
|
|
for (i = 0; i < dev->num_tx_queues; i++) {
|
|
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
|
2008-08-01 07:58:50 +08:00
|
|
|
|
|
|
|
__netif_tx_lock(txq, cpu);
|
2008-07-17 16:56:23 +08:00
|
|
|
netif_tx_stop_queue(txq);
|
2008-08-01 07:58:50 +08:00
|
|
|
__netif_tx_unlock(txq);
|
2008-07-17 16:56:23 +08:00
|
|
|
}
|
2008-08-01 07:58:50 +08:00
|
|
|
local_bh_enable();
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2008-07-15 15:13:44 +08:00
|
|
|
static inline void netif_addr_lock(struct net_device *dev)
|
|
|
|
{
|
|
|
|
spin_lock(&dev->addr_list_lock);
|
|
|
|
}
|
|
|
|
|
2012-01-09 14:36:54 +08:00
|
|
|
static inline void netif_addr_lock_nested(struct net_device *dev)
|
|
|
|
{
|
|
|
|
spin_lock_nested(&dev->addr_list_lock, SINGLE_DEPTH_NESTING);
|
|
|
|
}
|
|
|
|
|
2008-07-15 15:13:44 +08:00
|
|
|
static inline void netif_addr_lock_bh(struct net_device *dev)
|
|
|
|
{
|
|
|
|
spin_lock_bh(&dev->addr_list_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netif_addr_unlock(struct net_device *dev)
|
|
|
|
{
|
|
|
|
spin_unlock(&dev->addr_list_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void netif_addr_unlock_bh(struct net_device *dev)
|
|
|
|
{
|
|
|
|
spin_unlock_bh(&dev->addr_list_lock);
|
|
|
|
}
|
|
|
|
|
2009-05-05 10:48:28 +08:00
|
|
|
/*
|
2009-06-17 09:12:19 +08:00
|
|
|
* dev_addrs walker. Should be used only for read access. Call with
|
2009-05-05 10:48:28 +08:00
|
|
|
* rcu_read_lock held.
|
|
|
|
*/
|
|
|
|
#define for_each_dev_addr(dev, ha) \
|
2009-06-17 09:12:19 +08:00
|
|
|
list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list)
|
2009-05-05 10:48:28 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* These functions live elsewhere (drivers/net/net_init.c, but related) */
|
|
|
|
|
|
|
|
extern void ether_setup(struct net_device *dev);
|
|
|
|
|
|
|
|
/* Support for loadable net-drivers */
|
2011-01-10 03:36:31 +08:00
|
|
|
extern struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
|
2007-07-07 04:36:20 +08:00
|
|
|
void (*setup)(struct net_device *),
|
2011-01-10 03:36:31 +08:00
|
|
|
unsigned int txqs, unsigned int rxqs);
|
2007-07-07 04:36:20 +08:00
|
|
|
#define alloc_netdev(sizeof_priv, name, setup) \
|
2011-01-10 03:36:31 +08:00
|
|
|
alloc_netdev_mqs(sizeof_priv, name, setup, 1, 1)
|
|
|
|
|
|
|
|
#define alloc_netdev_mq(sizeof_priv, name, setup, count) \
|
|
|
|
alloc_netdev_mqs(sizeof_priv, name, setup, count, count)
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int register_netdev(struct net_device *dev);
|
|
|
|
extern void unregister_netdev(struct net_device *dev);
|
2009-05-05 10:48:28 +08:00
|
|
|
|
2010-04-02 05:22:57 +08:00
|
|
|
/* General hardware address lists handling functions */
|
|
|
|
extern int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list,
|
|
|
|
struct netdev_hw_addr_list *from_list,
|
|
|
|
int addr_len, unsigned char addr_type);
|
|
|
|
extern void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list,
|
|
|
|
struct netdev_hw_addr_list *from_list,
|
|
|
|
int addr_len, unsigned char addr_type);
|
|
|
|
extern int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
|
|
|
|
struct netdev_hw_addr_list *from_list,
|
|
|
|
int addr_len);
|
|
|
|
extern void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
|
|
|
|
struct netdev_hw_addr_list *from_list,
|
|
|
|
int addr_len);
|
|
|
|
extern void __hw_addr_flush(struct netdev_hw_addr_list *list);
|
|
|
|
extern void __hw_addr_init(struct netdev_hw_addr_list *list);
|
|
|
|
|
2009-05-05 10:48:28 +08:00
|
|
|
/* Functions used for device addresses handling */
|
|
|
|
extern int dev_addr_add(struct net_device *dev, unsigned char *addr,
|
|
|
|
unsigned char addr_type);
|
|
|
|
extern int dev_addr_del(struct net_device *dev, unsigned char *addr,
|
|
|
|
unsigned char addr_type);
|
|
|
|
extern int dev_addr_add_multiple(struct net_device *to_dev,
|
|
|
|
struct net_device *from_dev,
|
|
|
|
unsigned char addr_type);
|
|
|
|
extern int dev_addr_del_multiple(struct net_device *to_dev,
|
|
|
|
struct net_device *from_dev,
|
|
|
|
unsigned char addr_type);
|
2010-04-02 05:22:09 +08:00
|
|
|
extern void dev_addr_flush(struct net_device *dev);
|
|
|
|
extern int dev_addr_init(struct net_device *dev);
|
|
|
|
|
|
|
|
/* Functions used for unicast addresses handling */
|
|
|
|
extern int dev_uc_add(struct net_device *dev, unsigned char *addr);
|
|
|
|
extern int dev_uc_del(struct net_device *dev, unsigned char *addr);
|
|
|
|
extern int dev_uc_sync(struct net_device *to, struct net_device *from);
|
|
|
|
extern void dev_uc_unsync(struct net_device *to, struct net_device *from);
|
|
|
|
extern void dev_uc_flush(struct net_device *dev);
|
|
|
|
extern void dev_uc_init(struct net_device *dev);
|
2009-05-05 10:48:28 +08:00
|
|
|
|
2010-04-02 05:22:57 +08:00
|
|
|
/* Functions used for multicast addresses handling */
|
|
|
|
extern int dev_mc_add(struct net_device *dev, unsigned char *addr);
|
|
|
|
extern int dev_mc_add_global(struct net_device *dev, unsigned char *addr);
|
|
|
|
extern int dev_mc_del(struct net_device *dev, unsigned char *addr);
|
|
|
|
extern int dev_mc_del_global(struct net_device *dev, unsigned char *addr);
|
|
|
|
extern int dev_mc_sync(struct net_device *to, struct net_device *from);
|
|
|
|
extern void dev_mc_unsync(struct net_device *to, struct net_device *from);
|
|
|
|
extern void dev_mc_flush(struct net_device *dev);
|
|
|
|
extern void dev_mc_init(struct net_device *dev);
|
2009-05-05 10:48:28 +08:00
|
|
|
|
2007-06-27 16:28:10 +08:00
|
|
|
/* Functions used for secondary unicast and multicast support */
|
|
|
|
extern void dev_set_rx_mode(struct net_device *dev);
|
|
|
|
extern void __dev_set_rx_mode(struct net_device *dev);
|
2008-06-18 16:48:28 +08:00
|
|
|
extern int dev_set_promiscuity(struct net_device *dev, int inc);
|
|
|
|
extern int dev_set_allmulti(struct net_device *dev, int inc);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void netdev_state_change(struct net_device *dev);
|
2010-03-10 18:29:35 +08:00
|
|
|
extern int netdev_bonding_change(struct net_device *dev,
|
2009-09-15 17:37:40 +08:00
|
|
|
unsigned long event);
|
2005-05-30 05:13:47 +08:00
|
|
|
extern void netdev_features_change(struct net_device *dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Load a device via the kmod */
|
2007-09-18 02:56:21 +08:00
|
|
|
extern void dev_load(struct net *net, const char *name);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void dev_mcast_init(void);
|
2010-07-09 17:12:41 +08:00
|
|
|
extern struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
|
|
|
|
struct rtnl_link_stats64 *storage);
|
2008-11-20 13:40:23 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int netdev_max_backlog;
|
net: Consistent skb timestamping
With RPS inclusion, skb timestamping is not consistent in RX path.
If netif_receive_skb() is used, its deferred after RPS dispatch.
If netif_rx() is used, its done before RPS dispatch.
This can give strange tcpdump timestamps results.
I think timestamping should be done as soon as possible in the receive
path, to get meaningful values (ie timestamps taken at the time packet
was delivered by NIC driver to our stack), even if NAPI already can
defer timestamping a bit (RPS can help to reduce the gap)
Tom Herbert prefer to sample timestamps after RPS dispatch. In case
sampling is expensive (HPET/acpi_pm on x86), this makes sense.
Let admins switch from one mode to another, using a new
sysctl, /proc/sys/net/core/netdev_tstamp_prequeue
Its default value (1), means timestamps are taken as soon as possible,
before backlog queueing, giving accurate timestamps.
Setting a 0 value permits to sample timestamps when processing backlog,
after RPS dispatch, to lower the load of the pre-RPS cpu.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-16 14:57:10 +08:00
|
|
|
extern int netdev_tstamp_prequeue;
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int weight_p;
|
2011-04-20 17:27:32 +08:00
|
|
|
extern int bpf_jit_enable;
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int netdev_set_master(struct net_device *dev, struct net_device *master);
|
2011-02-12 14:48:36 +08:00
|
|
|
extern int netdev_set_bond_master(struct net_device *dev,
|
|
|
|
struct net_device *master);
|
2006-08-30 07:44:56 +08:00
|
|
|
extern int skb_checksum_help(struct sk_buff *skb);
|
2011-11-15 23:29:55 +08:00
|
|
|
extern struct sk_buff *skb_gso_segment(struct sk_buff *skb,
|
|
|
|
netdev_features_t features);
|
2005-11-11 05:01:24 +08:00
|
|
|
#ifdef CONFIG_BUG
|
|
|
|
extern void netdev_rx_csum_fault(struct net_device *dev);
|
|
|
|
#else
|
|
|
|
static inline void netdev_rx_csum_fault(struct net_device *dev)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
/* rx skb timestamps */
|
|
|
|
extern void net_enable_timestamp(void);
|
|
|
|
extern void net_disable_timestamp(void);
|
|
|
|
|
2005-08-16 13:18:02 +08:00
|
|
|
#ifdef CONFIG_PROC_FS
|
|
|
|
extern void *dev_seq_start(struct seq_file *seq, loff_t *pos);
|
|
|
|
extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos);
|
|
|
|
extern void dev_seq_stop(struct seq_file *seq, void *v);
|
2011-11-28 05:14:46 +08:00
|
|
|
extern int dev_seq_open_ops(struct inode *inode, struct file *file,
|
|
|
|
const struct seq_operations *ops);
|
2005-08-16 13:18:02 +08:00
|
|
|
#endif
|
|
|
|
|
2008-06-14 09:12:04 +08:00
|
|
|
extern int netdev_class_create_file(struct class_attribute *class_attr);
|
|
|
|
extern void netdev_class_remove_file(struct class_attribute *class_attr);
|
|
|
|
|
2010-08-05 23:45:15 +08:00
|
|
|
extern struct kobj_ns_type_operations net_ns_type_operations;
|
|
|
|
|
2011-06-07 07:41:33 +08:00
|
|
|
extern const char *netdev_drivername(const struct net_device *dev);
|
2008-07-22 04:31:48 +08:00
|
|
|
|
2005-08-16 13:18:02 +08:00
|
|
|
extern void linkwatch_run_queue(void);
|
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
static inline netdev_features_t netdev_get_wanted_features(
|
|
|
|
struct net_device *dev)
|
2011-02-16 00:59:17 +08:00
|
|
|
{
|
|
|
|
return (dev->features & ~dev->hw_features) | dev->wanted_features;
|
|
|
|
}
|
2011-11-15 23:29:55 +08:00
|
|
|
netdev_features_t netdev_increment_features(netdev_features_t all,
|
|
|
|
netdev_features_t one, netdev_features_t mask);
|
2011-04-03 13:48:47 +08:00
|
|
|
int __netdev_update_features(struct net_device *dev);
|
2011-02-16 00:59:17 +08:00
|
|
|
void netdev_update_features(struct net_device *dev);
|
2011-05-07 11:22:17 +08:00
|
|
|
void netdev_change_features(struct net_device *dev);
|
2007-08-11 06:47:58 +08:00
|
|
|
|
2009-12-04 07:59:22 +08:00
|
|
|
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
|
|
|
|
struct net_device *dev);
|
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
netdev_features_t netif_skb_features(struct sk_buff *skb);
|
2010-10-29 20:14:55 +08:00
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
static inline int net_gso_ok(netdev_features_t features, int gso_type)
|
2006-06-28 04:22:38 +08:00
|
|
|
{
|
2011-11-15 23:29:55 +08:00
|
|
|
netdev_features_t feature = gso_type << NETIF_F_GSO_SHIFT;
|
2011-11-16 22:05:33 +08:00
|
|
|
|
|
|
|
/* check flags correspondence */
|
|
|
|
BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT));
|
|
|
|
BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT));
|
|
|
|
BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
|
|
|
|
BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
|
|
|
|
BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
|
|
|
|
BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
|
|
|
|
|
2006-06-30 03:25:53 +08:00
|
|
|
return (features & feature) == feature;
|
2006-06-28 04:22:38 +08:00
|
|
|
}
|
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
static inline int skb_gso_ok(struct sk_buff *skb, netdev_features_t features)
|
2006-07-01 04:36:35 +08:00
|
|
|
{
|
2009-06-04 12:20:51 +08:00
|
|
|
return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
|
2010-08-23 15:13:46 +08:00
|
|
|
(!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
|
2006-07-01 04:36:35 +08:00
|
|
|
}
|
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
static inline int netif_needs_gso(struct sk_buff *skb,
|
|
|
|
netdev_features_t features)
|
2006-06-22 17:40:14 +08:00
|
|
|
{
|
2011-01-09 14:23:32 +08:00
|
|
|
return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
|
|
|
|
unlikely(skb->ip_summed != CHECKSUM_PARTIAL));
|
2006-06-22 17:40:14 +08:00
|
|
|
}
|
|
|
|
|
[NET]: Add per-connection option to set max TSO frame size
Update: My mailer ate one of Jarek's feedback mails... Fixed the
parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the
whitespace issue due to a patch import botch. Changed the types from
u32 to unsigned int to be more consistent with other variables in the
area. Also brought the patch up to the latest net-2.6.26 tree.
Update: Made gso_max_size container 32 bits, not 16. Moved the
location of gso_max_size within netdev to be less hotpath. Made more
consistent names between the sock and netdev layers, and added a
define for the max GSO size.
Update: Respun for net-2.6.26 tree.
Update: changed max_gso_frame_size and sk_gso_max_size from signed to
unsigned - thanks Stephen!
This patch adds the ability for device drivers to control the size of
the TSO frames being sent to them, per TCP connection. By setting the
netdevice's gso_max_size value, the socket layer will set the GSO
frame size based on that value. This will propogate into the TCP
layer, and send TSO's of that size to the hardware.
This can be desirable to help tune the bursty nature of TSO on a
per-adapter basis, where one may have 1 GbE and 10 GbE devices
coexisting in a system, one running multiqueue and the other not, etc.
This can also be desirable for devices that cannot support full 64 KB
TSO's, but still want to benefit from some level of segmentation
offloading.
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 18:43:19 +08:00
|
|
|
static inline void netif_set_gso_max_size(struct net_device *dev,
|
|
|
|
unsigned int size)
|
|
|
|
{
|
|
|
|
dev->gso_max_size = size;
|
|
|
|
}
|
|
|
|
|
2011-02-12 14:48:36 +08:00
|
|
|
static inline int netif_is_bond_slave(struct net_device *dev)
|
|
|
|
{
|
|
|
|
return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING;
|
|
|
|
}
|
|
|
|
|
2008-11-08 14:54:20 +08:00
|
|
|
extern struct pernet_operations __net_initdata loopback_net_ops;
|
2009-04-20 12:49:28 +08:00
|
|
|
|
2010-02-09 19:49:47 +08:00
|
|
|
/* Logging, debugging and troubleshooting/diagnostic helpers. */
|
|
|
|
|
|
|
|
/* netdev_printk helpers, similar to dev_printk */
|
|
|
|
|
|
|
|
static inline const char *netdev_name(const struct net_device *dev)
|
|
|
|
{
|
|
|
|
if (dev->reg_state != NETREG_REGISTERED)
|
|
|
|
return "(unregistered net_device)";
|
|
|
|
return dev->name;
|
|
|
|
}
|
|
|
|
|
2011-08-12 02:36:48 +08:00
|
|
|
extern int __netdev_printk(const char *level, const struct net_device *dev,
|
|
|
|
struct va_format *vaf);
|
|
|
|
|
2011-11-01 08:11:33 +08:00
|
|
|
extern __printf(3, 4)
|
|
|
|
int netdev_printk(const char *level, const struct net_device *dev,
|
|
|
|
const char *format, ...);
|
|
|
|
extern __printf(2, 3)
|
|
|
|
int netdev_emerg(const struct net_device *dev, const char *format, ...);
|
|
|
|
extern __printf(2, 3)
|
|
|
|
int netdev_alert(const struct net_device *dev, const char *format, ...);
|
|
|
|
extern __printf(2, 3)
|
|
|
|
int netdev_crit(const struct net_device *dev, const char *format, ...);
|
|
|
|
extern __printf(2, 3)
|
|
|
|
int netdev_err(const struct net_device *dev, const char *format, ...);
|
|
|
|
extern __printf(2, 3)
|
|
|
|
int netdev_warn(const struct net_device *dev, const char *format, ...);
|
|
|
|
extern __printf(2, 3)
|
|
|
|
int netdev_notice(const struct net_device *dev, const char *format, ...);
|
|
|
|
extern __printf(2, 3)
|
|
|
|
int netdev_info(const struct net_device *dev, const char *format, ...);
|
2010-02-09 19:49:47 +08:00
|
|
|
|
2011-03-02 05:33:13 +08:00
|
|
|
#define MODULE_ALIAS_NETDEV(device) \
|
|
|
|
MODULE_ALIAS("netdev-" device)
|
|
|
|
|
2010-02-09 19:49:47 +08:00
|
|
|
#if defined(DEBUG)
|
|
|
|
#define netdev_dbg(__dev, format, args...) \
|
|
|
|
netdev_printk(KERN_DEBUG, __dev, format, ##args)
|
|
|
|
#elif defined(CONFIG_DYNAMIC_DEBUG)
|
|
|
|
#define netdev_dbg(__dev, format, args...) \
|
|
|
|
do { \
|
2011-08-12 02:36:48 +08:00
|
|
|
dynamic_netdev_dbg(__dev, format, ##args); \
|
2010-02-09 19:49:47 +08:00
|
|
|
} while (0)
|
|
|
|
#else
|
|
|
|
#define netdev_dbg(__dev, format, args...) \
|
|
|
|
({ \
|
|
|
|
if (0) \
|
|
|
|
netdev_printk(KERN_DEBUG, __dev, format, ##args); \
|
|
|
|
0; \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#if defined(VERBOSE_DEBUG)
|
|
|
|
#define netdev_vdbg netdev_dbg
|
|
|
|
#else
|
|
|
|
|
|
|
|
#define netdev_vdbg(dev, format, args...) \
|
|
|
|
({ \
|
|
|
|
if (0) \
|
|
|
|
netdev_printk(KERN_DEBUG, dev, format, ##args); \
|
|
|
|
0; \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* netdev_WARN() acts like dev_printk(), but with the key difference
|
|
|
|
* of using a WARN/WARN_ON to get the message out, including the
|
|
|
|
* file/line information and a backtrace.
|
|
|
|
*/
|
|
|
|
#define netdev_WARN(dev, format, args...) \
|
|
|
|
WARN(1, "netdevice: %s\n" format, netdev_name(dev), ##args);
|
|
|
|
|
2010-02-09 19:49:49 +08:00
|
|
|
/* netif printk helpers, similar to netdev_printk */
|
|
|
|
|
|
|
|
#define netif_printk(priv, type, level, dev, fmt, args...) \
|
|
|
|
do { \
|
|
|
|
if (netif_msg_##type(priv)) \
|
|
|
|
netdev_printk(level, (dev), fmt, ##args); \
|
|
|
|
} while (0)
|
|
|
|
|
2010-06-27 09:02:36 +08:00
|
|
|
#define netif_level(level, priv, type, dev, fmt, args...) \
|
|
|
|
do { \
|
|
|
|
if (netif_msg_##type(priv)) \
|
|
|
|
netdev_##level(dev, fmt, ##args); \
|
|
|
|
} while (0)
|
|
|
|
|
2010-02-09 19:49:49 +08:00
|
|
|
#define netif_emerg(priv, type, dev, fmt, args...) \
|
2010-06-27 09:02:36 +08:00
|
|
|
netif_level(emerg, priv, type, dev, fmt, ##args)
|
2010-02-09 19:49:49 +08:00
|
|
|
#define netif_alert(priv, type, dev, fmt, args...) \
|
2010-06-27 09:02:36 +08:00
|
|
|
netif_level(alert, priv, type, dev, fmt, ##args)
|
2010-02-09 19:49:49 +08:00
|
|
|
#define netif_crit(priv, type, dev, fmt, args...) \
|
2010-06-27 09:02:36 +08:00
|
|
|
netif_level(crit, priv, type, dev, fmt, ##args)
|
2010-02-09 19:49:49 +08:00
|
|
|
#define netif_err(priv, type, dev, fmt, args...) \
|
2010-06-27 09:02:36 +08:00
|
|
|
netif_level(err, priv, type, dev, fmt, ##args)
|
2010-02-09 19:49:49 +08:00
|
|
|
#define netif_warn(priv, type, dev, fmt, args...) \
|
2010-06-27 09:02:36 +08:00
|
|
|
netif_level(warn, priv, type, dev, fmt, ##args)
|
2010-02-09 19:49:49 +08:00
|
|
|
#define netif_notice(priv, type, dev, fmt, args...) \
|
2010-06-27 09:02:36 +08:00
|
|
|
netif_level(notice, priv, type, dev, fmt, ##args)
|
2010-02-09 19:49:49 +08:00
|
|
|
#define netif_info(priv, type, dev, fmt, args...) \
|
2010-06-27 09:02:36 +08:00
|
|
|
netif_level(info, priv, type, dev, fmt, ##args)
|
2010-02-09 19:49:49 +08:00
|
|
|
|
|
|
|
#if defined(DEBUG)
|
|
|
|
#define netif_dbg(priv, type, dev, format, args...) \
|
|
|
|
netif_printk(priv, type, KERN_DEBUG, dev, format, ##args)
|
|
|
|
#elif defined(CONFIG_DYNAMIC_DEBUG)
|
|
|
|
#define netif_dbg(priv, type, netdev, format, args...) \
|
|
|
|
do { \
|
|
|
|
if (netif_msg_##type(priv)) \
|
2011-08-12 02:36:53 +08:00
|
|
|
dynamic_netdev_dbg(netdev, format, ##args); \
|
2010-02-09 19:49:49 +08:00
|
|
|
} while (0)
|
|
|
|
#else
|
|
|
|
#define netif_dbg(priv, type, dev, format, args...) \
|
|
|
|
({ \
|
|
|
|
if (0) \
|
|
|
|
netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
|
|
|
|
0; \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#if defined(VERBOSE_DEBUG)
|
2010-07-02 15:08:44 +08:00
|
|
|
#define netif_vdbg netif_dbg
|
2010-02-09 19:49:49 +08:00
|
|
|
#else
|
|
|
|
#define netif_vdbg(priv, type, dev, format, args...) \
|
|
|
|
({ \
|
|
|
|
if (0) \
|
2010-05-18 14:56:32 +08:00
|
|
|
netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
|
2010-02-09 19:49:49 +08:00
|
|
|
0; \
|
|
|
|
})
|
|
|
|
#endif
|
2010-02-09 19:49:47 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
|
2009-05-28 06:48:07 +08:00
|
|
|
#endif /* _LINUX_NETDEVICE_H */
|