linux-sg2042/net/sched/sch_teql.c

528 lines
12 KiB
C
Raw Normal View History

/* net/sched/sch_teql.c "True" (or "trivial") link equalizer.
*
* 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.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/if_arp.h>
#include <linux/netdevice.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/moduleparam.h>
#include <net/dst.h>
#include <net/neighbour.h>
#include <net/pkt_sched.h>
/*
How to setup it.
----------------
After loading this module you will find a new device teqlN
and new qdisc with the same name. To join a slave to the equalizer
you should just set this qdisc on a device f.e.
# tc qdisc add dev eth0 root teql0
# tc qdisc add dev eth1 root teql0
That's all. Full PnP 8)
Applicability.
--------------
1. Slave devices MUST be active devices, i.e., they must raise the tbusy
signal and generate EOI events. If you want to equalize virtual devices
like tunnels, use a normal eql device.
2. This device puts no limitations on physical slave characteristics
f.e. it will equalize 9600baud line and 100Mb ethernet perfectly :-)
Certainly, large difference in link speeds will make the resulting
eqalized link unusable, because of huge packet reordering.
I estimate an upper useful difference as ~10 times.
3. If the slave requires address resolution, only protocols using
neighbour cache (IPv4/IPv6) will work over the equalized link.
Other protocols are still allowed to use the slave device directly,
which will not break load balancing, though native slave
traffic will have the highest priority. */
struct teql_master {
struct Qdisc_ops qops;
struct net_device *dev;
struct Qdisc *slaves;
struct list_head master_list;
unsigned long tx_bytes;
unsigned long tx_packets;
unsigned long tx_errors;
unsigned long tx_dropped;
};
struct teql_sched_data {
struct Qdisc *next;
struct teql_master *m;
struct sk_buff_head q;
};
#define NEXT_SLAVE(q) (((struct teql_sched_data *)qdisc_priv(q))->next)
#define FMASK (IFF_BROADCAST | IFF_POINTOPOINT)
/* "teql*" qdisc routines */
static int
teql_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
{
struct net_device *dev = qdisc_dev(sch);
struct teql_sched_data *q = qdisc_priv(sch);
if (q->q.qlen < dev->tx_queue_len) {
__skb_queue_tail(&q->q, skb);
return NET_XMIT_SUCCESS;
}
return qdisc_drop(skb, sch, to_free);
}
static struct sk_buff *
teql_dequeue(struct Qdisc *sch)
{
struct teql_sched_data *dat = qdisc_priv(sch);
struct netdev_queue *dat_queue;
struct sk_buff *skb;
struct Qdisc *q;
skb = __skb_dequeue(&dat->q);
dat_queue = netdev_get_tx_queue(dat->m->dev, 0);
q = rcu_dereference_bh(dat_queue->qdisc);
if (skb == NULL) {
struct net_device *m = qdisc_dev(q);
if (m) {
dat->m->slaves = sch;
netif_wake_queue(m);
}
} else {
qdisc_bstats_update(sch, skb);
}
sch->q.qlen = dat->q.qlen + q->q.qlen;
return skb;
}
static struct sk_buff *
teql_peek(struct Qdisc *sch)
{
/* teql is meant to be used as root qdisc */
return NULL;
}
static void
teql_reset(struct Qdisc *sch)
{
struct teql_sched_data *dat = qdisc_priv(sch);
skb_queue_purge(&dat->q);
sch->q.qlen = 0;
}
static void
teql_destroy(struct Qdisc *sch)
{
struct Qdisc *q, *prev;
struct teql_sched_data *dat = qdisc_priv(sch);
struct teql_master *master = dat->m;
prev = master->slaves;
if (prev) {
do {
q = NEXT_SLAVE(prev);
if (q == sch) {
NEXT_SLAVE(prev) = NEXT_SLAVE(q);
if (q == master->slaves) {
master->slaves = NEXT_SLAVE(q);
if (q == master->slaves) {
struct netdev_queue *txq;
spinlock_t *root_lock;
txq = netdev_get_tx_queue(master->dev, 0);
master->slaves = NULL;
root_lock = qdisc_root_sleeping_lock(rtnl_dereference(txq->qdisc));
spin_lock_bh(root_lock);
qdisc_reset(rtnl_dereference(txq->qdisc));
spin_unlock_bh(root_lock);
}
}
skb_queue_purge(&dat->q);
break;
}
} while ((prev = q) != master->slaves);
}
}
static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct net_device *dev = qdisc_dev(sch);
struct teql_master *m = (struct teql_master *)sch->ops;
struct teql_sched_data *q = qdisc_priv(sch);
if (dev->hard_header_len > m->dev->hard_header_len)
return -EINVAL;
if (m->dev == dev)
return -ELOOP;
q->m = m;
skb_queue_head_init(&q->q);
if (m->slaves) {
if (m->dev->flags & IFF_UP) {
if ((m->dev->flags & IFF_POINTOPOINT &&
!(dev->flags & IFF_POINTOPOINT)) ||
(m->dev->flags & IFF_BROADCAST &&
!(dev->flags & IFF_BROADCAST)) ||
(m->dev->flags & IFF_MULTICAST &&
!(dev->flags & IFF_MULTICAST)) ||
dev->mtu < m->dev->mtu)
return -EINVAL;
} else {
if (!(dev->flags&IFF_POINTOPOINT))
m->dev->flags &= ~IFF_POINTOPOINT;
if (!(dev->flags&IFF_BROADCAST))
m->dev->flags &= ~IFF_BROADCAST;
if (!(dev->flags&IFF_MULTICAST))
m->dev->flags &= ~IFF_MULTICAST;
if (dev->mtu < m->dev->mtu)
m->dev->mtu = dev->mtu;
}
q->next = NEXT_SLAVE(m->slaves);
NEXT_SLAVE(m->slaves) = sch;
} else {
q->next = sch;
m->slaves = sch;
m->dev->mtu = dev->mtu;
m->dev->flags = (m->dev->flags&~FMASK)|(dev->flags&FMASK);
}
return 0;
}
static int
__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res,
struct net_device *dev, struct netdev_queue *txq,
struct dst_entry *dst)
{
struct neighbour *n;
int err = 0;
n = dst_neigh_lookup_skb(dst, skb);
if (!n)
return -ENOENT;
if (dst->dev != dev) {
struct neighbour *mn;
mn = __neigh_lookup_errno(n->tbl, n->primary_key, dev);
neigh_release(n);
if (IS_ERR(mn))
return PTR_ERR(mn);
n = mn;
}
if (neigh_event_send(n, skb_res) == 0) {
int err;
char haddr[MAX_ADDR_LEN];
neigh_ha_snapshot(haddr, n, dev);
err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)),
haddr, NULL, skb->len);
if (err < 0)
err = -EINVAL;
} else {
err = (skb_res == NULL) ? -EAGAIN : 1;
}
neigh_release(n);
return err;
}
static inline int teql_resolve(struct sk_buff *skb,
struct sk_buff *skb_res,
struct net_device *dev,
struct netdev_queue *txq)
{
struct dst_entry *dst = skb_dst(skb);
int res;
if (rcu_access_pointer(txq->qdisc) == &noop_qdisc)
return -ENODEV;
if (!dev->header_ops || !dst)
return 0;
rcu_read_lock();
res = __teql_resolve(skb, skb_res, dev, txq, dst);
rcu_read_unlock();
return res;
}
static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct teql_master *master = netdev_priv(dev);
struct Qdisc *start, *q;
int busy;
int nores;
int subq = skb_get_queue_mapping(skb);
struct sk_buff *skb_res = NULL;
start = master->slaves;
restart:
nores = 0;
busy = 0;
q = start;
if (!q)
goto drop;
do {
struct net_device *slave = qdisc_dev(q);
struct netdev_queue *slave_txq = netdev_get_tx_queue(slave, 0);
if (slave_txq->qdisc_sleeping != q)
continue;
if (netif_xmit_stopped(netdev_get_tx_queue(slave, subq)) ||
!netif_running(slave)) {
busy = 1;
continue;
}
switch (teql_resolve(skb, skb_res, slave, slave_txq)) {
case 0:
if (__netif_tx_trylock(slave_txq)) {
unsigned int length = qdisc_pkt_len(skb);
if (!netif_xmit_frozen_or_stopped(slave_txq) &&
netdev_start_xmit(skb, slave, slave_txq, false) ==
NETDEV_TX_OK) {
__netif_tx_unlock(slave_txq);
master->slaves = NEXT_SLAVE(q);
netif_wake_queue(dev);
master->tx_packets++;
master->tx_bytes += length;
return NETDEV_TX_OK;
}
__netif_tx_unlock(slave_txq);
}
if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)))
busy = 1;
break;
case 1:
master->slaves = NEXT_SLAVE(q);
return NETDEV_TX_OK;
default:
nores = 1;
break;
}
__skb_pull(skb, skb_network_offset(skb));
} while ((q = NEXT_SLAVE(q)) != start);
if (nores && skb_res == NULL) {
skb_res = skb;
goto restart;
}
if (busy) {
netif_stop_queue(dev);
return NETDEV_TX_BUSY;
}
master->tx_errors++;
drop:
master->tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
static int teql_master_open(struct net_device *dev)
{
struct Qdisc *q;
struct teql_master *m = netdev_priv(dev);
int mtu = 0xFFFE;
unsigned int flags = IFF_NOARP | IFF_MULTICAST;
if (m->slaves == NULL)
return -EUNATCH;
flags = FMASK;
q = m->slaves;
do {
struct net_device *slave = qdisc_dev(q);
if (slave == NULL)
return -EUNATCH;
if (slave->mtu < mtu)
mtu = slave->mtu;
if (slave->hard_header_len > LL_MAX_HEADER)
return -EINVAL;
/* If all the slaves are BROADCAST, master is BROADCAST
If all the slaves are PtP, master is PtP
Otherwise, master is NBMA.
*/
if (!(slave->flags&IFF_POINTOPOINT))
flags &= ~IFF_POINTOPOINT;
if (!(slave->flags&IFF_BROADCAST))
flags &= ~IFF_BROADCAST;
if (!(slave->flags&IFF_MULTICAST))
flags &= ~IFF_MULTICAST;
} while ((q = NEXT_SLAVE(q)) != m->slaves);
m->dev->mtu = mtu;
m->dev->flags = (m->dev->flags&~FMASK) | flags;
netif_start_queue(m->dev);
return 0;
}
static int teql_master_close(struct net_device *dev)
{
netif_stop_queue(dev);
return 0;
}
static void teql_master_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct teql_master *m = netdev_priv(dev);
stats->tx_packets = m->tx_packets;
stats->tx_bytes = m->tx_bytes;
stats->tx_errors = m->tx_errors;
stats->tx_dropped = m->tx_dropped;
}
static int teql_master_mtu(struct net_device *dev, int new_mtu)
{
struct teql_master *m = netdev_priv(dev);
struct Qdisc *q;
q = m->slaves;
if (q) {
do {
if (new_mtu > qdisc_dev(q)->mtu)
return -EINVAL;
} while ((q = NEXT_SLAVE(q)) != m->slaves);
}
dev->mtu = new_mtu;
return 0;
}
static const struct net_device_ops teql_netdev_ops = {
.ndo_open = teql_master_open,
.ndo_stop = teql_master_close,
.ndo_start_xmit = teql_master_xmit,
.ndo_get_stats64 = teql_master_stats64,
.ndo_change_mtu = teql_master_mtu,
};
static __init void teql_master_setup(struct net_device *dev)
{
struct teql_master *master = netdev_priv(dev);
struct Qdisc_ops *ops = &master->qops;
master->dev = dev;
ops->priv_size = sizeof(struct teql_sched_data);
ops->enqueue = teql_enqueue;
ops->dequeue = teql_dequeue;
ops->peek = teql_peek;
ops->init = teql_qdisc_init;
ops->reset = teql_reset;
ops->destroy = teql_destroy;
ops->owner = THIS_MODULE;
dev->netdev_ops = &teql_netdev_ops;
dev->type = ARPHRD_VOID;
dev->mtu = 1500;
net: use core MTU range checking in core net infra geneve: - Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu - This one isn't quite as straight-forward as others, could use some closer inspection and testing macvlan: - set min/max_mtu tun: - set min/max_mtu, remove tun_net_change_mtu vxlan: - Merge __vxlan_change_mtu back into vxlan_change_mtu - Set max_mtu to IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function - This one is also not as straight-forward and could use closer inspection and testing from vxlan folks bridge: - set max_mtu of IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function openvswitch: - set min/max_mtu, remove internal_dev_change_mtu - note: max_mtu wasn't checked previously, it's been set to 65535, which is the largest possible size supported sch_teql: - set min/max_mtu (note: max_mtu previously unchecked, used max of 65535) macsec: - min_mtu = 0, max_mtu = 65535 macvlan: - min_mtu = 0, max_mtu = 65535 ntb_netdev: - min_mtu = 0, max_mtu = 65535 veth: - min_mtu = 68, max_mtu = 65535 8021q: - min_mtu = 0, max_mtu = 65535 CC: netdev@vger.kernel.org CC: Nicolas Dichtel <nicolas.dichtel@6wind.com> CC: Hannes Frederic Sowa <hannes@stressinduktion.org> CC: Tom Herbert <tom@herbertland.com> CC: Daniel Borkmann <daniel@iogearbox.net> CC: Alexander Duyck <alexander.h.duyck@intel.com> CC: Paolo Abeni <pabeni@redhat.com> CC: Jiri Benc <jbenc@redhat.com> CC: WANG Cong <xiyou.wangcong@gmail.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> CC: Pravin B Shelar <pshelar@ovn.org> CC: Sabrina Dubroca <sd@queasysnail.net> CC: Patrick McHardy <kaber@trash.net> CC: Stephen Hemminger <stephen@networkplumber.org> CC: Pravin Shelar <pshelar@nicira.com> CC: Maxim Krasnyansky <maxk@qti.qualcomm.com> Signed-off-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 01:55:20 +08:00
dev->min_mtu = 68;
dev->max_mtu = 65535;
dev->tx_queue_len = 100;
dev->flags = IFF_NOARP;
dev->hard_header_len = LL_MAX_HEADER;
netif_keep_dst(dev);
}
static LIST_HEAD(master_dev_list);
static int max_equalizers = 1;
module_param(max_equalizers, int, 0);
MODULE_PARM_DESC(max_equalizers, "Max number of link equalizers");
static int __init teql_init(void)
{
int i;
int err = -ENODEV;
for (i = 0; i < max_equalizers; i++) {
struct net_device *dev;
struct teql_master *master;
dev = alloc_netdev(sizeof(struct teql_master), "teql%d",
NET_NAME_UNKNOWN, teql_master_setup);
if (!dev) {
err = -ENOMEM;
break;
}
if ((err = register_netdev(dev))) {
free_netdev(dev);
break;
}
master = netdev_priv(dev);
strlcpy(master->qops.id, dev->name, IFNAMSIZ);
err = register_qdisc(&master->qops);
if (err) {
unregister_netdev(dev);
free_netdev(dev);
break;
}
list_add_tail(&master->master_list, &master_dev_list);
}
return i ? 0 : err;
}
static void __exit teql_exit(void)
{
struct teql_master *master, *nxt;
list_for_each_entry_safe(master, nxt, &master_dev_list, master_list) {
list_del(&master->master_list);
unregister_qdisc(&master->qops);
unregister_netdev(master->dev);
free_netdev(master->dev);
}
}
module_init(teql_init);
module_exit(teql_exit);
MODULE_LICENSE("GPL");