* [PATCH net-next-2.6 3/3] bonding,ipv4,ipv6,vlan: Handle NETDEV_BONDING_FAILOVER like NETDEV_NOTIFY_PEERS
From: Ben Hutchings @ 2011-04-15 23:47 UTC (permalink / raw)
To: David Miller, Jay Vosburgh, Andy Gospodarek, Patrick McHardy; +Cc: netdev
It is undesirable for the bonding driver to be poking into higher
level protocols, and notifiers provide a way to avoid that. This does
mean removing the ability to configure reptitition of gratuitous ARPs
and unsolicited NAs.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
drivers/net/bonding/Makefile | 3 -
drivers/net/bonding/bond_ipv6.c | 225 --------------------------------------
drivers/net/bonding/bond_main.c | 96 ----------------
drivers/net/bonding/bond_sysfs.c | 80 --------------
drivers/net/bonding/bonding.h | 29 -----
net/8021q/vlan.c | 3 +-
net/ipv4/devinet.c | 1 +
net/ipv6/ndisc.c | 1 +
8 files changed, 4 insertions(+), 434 deletions(-)
delete mode 100644 drivers/net/bonding/bond_ipv6.c
diff --git a/drivers/net/bonding/Makefile b/drivers/net/bonding/Makefile
index 3c5c014..4c21bf6 100644
--- a/drivers/net/bonding/Makefile
+++ b/drivers/net/bonding/Makefile
@@ -9,6 +9,3 @@ bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o bond_debugfs.o
proc-$(CONFIG_PROC_FS) += bond_procfs.o
bonding-objs += $(proc-y)
-ipv6-$(subst m,y,$(CONFIG_IPV6)) += bond_ipv6.o
-bonding-objs += $(ipv6-y)
-
diff --git a/drivers/net/bonding/bond_ipv6.c b/drivers/net/bonding/bond_ipv6.c
deleted file mode 100644
index 84fbd4e..0000000
--- a/drivers/net/bonding/bond_ipv6.c
+++ /dev/null
@@ -1,225 +0,0 @@
-/*
- * Copyright(c) 2008 Hewlett-Packard Development Company, L.P.
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
- * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
- * for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called LICENSE.
- *
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/types.h>
-#include <linux/if_vlan.h>
-#include <net/ipv6.h>
-#include <net/ndisc.h>
-#include <net/addrconf.h>
-#include <net/netns/generic.h>
-#include "bonding.h"
-
-/*
- * Assign bond->master_ipv6 to the next IPv6 address in the list, or
- * zero it out if there are none.
- */
-static void bond_glean_dev_ipv6(struct net_device *dev, struct in6_addr *addr)
-{
- struct inet6_dev *idev;
-
- if (!dev)
- return;
-
- idev = in6_dev_get(dev);
- if (!idev)
- return;
-
- read_lock_bh(&idev->lock);
- if (!list_empty(&idev->addr_list)) {
- struct inet6_ifaddr *ifa
- = list_first_entry(&idev->addr_list,
- struct inet6_ifaddr, if_list);
- ipv6_addr_copy(addr, &ifa->addr);
- } else
- ipv6_addr_set(addr, 0, 0, 0, 0);
-
- read_unlock_bh(&idev->lock);
-
- in6_dev_put(idev);
-}
-
-static void bond_na_send(struct net_device *slave_dev,
- struct in6_addr *daddr,
- int router,
- unsigned short vlan_id)
-{
- struct in6_addr mcaddr;
- struct icmp6hdr icmp6h = {
- .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT,
- };
- struct sk_buff *skb;
-
- icmp6h.icmp6_router = router;
- icmp6h.icmp6_solicited = 0;
- icmp6h.icmp6_override = 1;
-
- addrconf_addr_solict_mult(daddr, &mcaddr);
-
- pr_debug("ipv6 na on slave %s: dest %pI6, src %pI6\n",
- slave_dev->name, &mcaddr, daddr);
-
- skb = ndisc_build_skb(slave_dev, &mcaddr, daddr, &icmp6h, daddr,
- ND_OPT_TARGET_LL_ADDR);
-
- if (!skb) {
- pr_err("NA packet allocation failed\n");
- return;
- }
-
- if (vlan_id) {
- /* The Ethernet header is not present yet, so it is
- * too early to insert a VLAN tag. Force use of an
- * out-of-line tag here and let dev_hard_start_xmit()
- * insert it if the slave hardware can't.
- */
- skb = __vlan_hwaccel_put_tag(skb, vlan_id);
- if (!skb) {
- pr_err("failed to insert VLAN tag\n");
- return;
- }
- }
-
- ndisc_send_skb(skb, slave_dev, NULL, &mcaddr, daddr, &icmp6h);
-}
-
-/*
- * Kick out an unsolicited Neighbor Advertisement for an IPv6 address on
- * the bonding master. This will help the switch learn our address
- * if in active-backup mode.
- *
- * Caller must hold curr_slave_lock for read or better
- */
-void bond_send_unsolicited_na(struct bonding *bond)
-{
- struct slave *slave = bond->curr_active_slave;
- struct vlan_entry *vlan;
- struct inet6_dev *idev;
- int is_router;
-
- pr_debug("%s: bond %s slave %s\n", bond->dev->name,
- __func__, slave ? slave->dev->name : "NULL");
-
- if (!slave || !bond->send_unsol_na ||
- test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
- return;
-
- bond->send_unsol_na--;
-
- idev = in6_dev_get(bond->dev);
- if (!idev)
- return;
-
- is_router = !!idev->cnf.forwarding;
-
- in6_dev_put(idev);
-
- if (!ipv6_addr_any(&bond->master_ipv6))
- bond_na_send(slave->dev, &bond->master_ipv6, is_router, 0);
-
- list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
- if (!ipv6_addr_any(&vlan->vlan_ipv6)) {
- bond_na_send(slave->dev, &vlan->vlan_ipv6, is_router,
- vlan->vlan_id);
- }
- }
-}
-
-/*
- * bond_inet6addr_event: handle inet6addr notifier chain events.
- *
- * We keep track of device IPv6 addresses primarily to use as source
- * addresses in NS probes.
- *
- * We track one IPv6 for the main device (if it has one).
- */
-static int bond_inet6addr_event(struct notifier_block *this,
- unsigned long event,
- void *ptr)
-{
- struct inet6_ifaddr *ifa = ptr;
- struct net_device *vlan_dev, *event_dev = ifa->idev->dev;
- struct bonding *bond;
- struct vlan_entry *vlan;
- struct bond_net *bn = net_generic(dev_net(event_dev), bond_net_id);
-
- list_for_each_entry(bond, &bn->dev_list, bond_list) {
- if (bond->dev == event_dev) {
- switch (event) {
- case NETDEV_UP:
- if (ipv6_addr_any(&bond->master_ipv6))
- ipv6_addr_copy(&bond->master_ipv6,
- &ifa->addr);
- return NOTIFY_OK;
- case NETDEV_DOWN:
- if (ipv6_addr_equal(&bond->master_ipv6,
- &ifa->addr))
- bond_glean_dev_ipv6(bond->dev,
- &bond->master_ipv6);
- return NOTIFY_OK;
- default:
- return NOTIFY_DONE;
- }
- }
-
- list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
- if (!bond->vlgrp)
- continue;
- vlan_dev = vlan_group_get_device(bond->vlgrp,
- vlan->vlan_id);
- if (vlan_dev == event_dev) {
- switch (event) {
- case NETDEV_UP:
- if (ipv6_addr_any(&vlan->vlan_ipv6))
- ipv6_addr_copy(&vlan->vlan_ipv6,
- &ifa->addr);
- return NOTIFY_OK;
- case NETDEV_DOWN:
- if (ipv6_addr_equal(&vlan->vlan_ipv6,
- &ifa->addr))
- bond_glean_dev_ipv6(vlan_dev,
- &vlan->vlan_ipv6);
- return NOTIFY_OK;
- default:
- return NOTIFY_DONE;
- }
- }
- }
- }
- return NOTIFY_DONE;
-}
-
-static struct notifier_block bond_inet6addr_notifier = {
- .notifier_call = bond_inet6addr_event,
-};
-
-void bond_register_ipv6_notifier(void)
-{
- register_inet6addr_notifier(&bond_inet6addr_notifier);
-}
-
-void bond_unregister_ipv6_notifier(void)
-{
- unregister_inet6addr_notifier(&bond_inet6addr_notifier);
-}
-
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b51e021..5cd4766 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -89,8 +89,6 @@
static int max_bonds = BOND_DEFAULT_MAX_BONDS;
static int tx_queues = BOND_DEFAULT_TX_QUEUES;
-static int num_grat_arp = 1;
-static int num_unsol_na = 1;
static int miimon = BOND_LINK_MON_INTERV;
static int updelay;
static int downdelay;
@@ -113,10 +111,6 @@ module_param(max_bonds, int, 0);
MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
module_param(tx_queues, int, 0);
MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)");
-module_param(num_grat_arp, int, 0644);
-MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event");
-module_param(num_unsol_na, int, 0644);
-MODULE_PARM_DESC(num_unsol_na, "Number of unsolicited IPv6 Neighbor Advertisements packets to send on failover event");
module_param(miimon, int, 0);
MODULE_PARM_DESC(miimon, "Link check interval in milliseconds");
module_param(updelay, int, 0);
@@ -234,7 +228,6 @@ struct bond_parm_tbl ad_select_tbl[] = {
/*-------------------------- Forward declarations ---------------------------*/
-static void bond_send_gratuitous_arp(struct bonding *bond);
static int bond_init(struct net_device *bond_dev);
static void bond_uninit(struct net_device *bond_dev);
@@ -1160,14 +1153,6 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
bond_do_fail_over_mac(bond, new_active,
old_active);
- if (netif_running(bond->dev)) {
- bond->send_grat_arp = bond->params.num_grat_arp;
- bond_send_gratuitous_arp(bond);
-
- bond->send_unsol_na = bond->params.num_unsol_na;
- bond_send_unsolicited_na(bond);
- }
-
write_unlock_bh(&bond->curr_slave_lock);
read_unlock(&bond->lock);
@@ -2578,18 +2563,6 @@ void bond_mii_monitor(struct work_struct *work)
if (bond->slave_cnt == 0)
goto re_arm;
- if (bond->send_grat_arp) {
- read_lock(&bond->curr_slave_lock);
- bond_send_gratuitous_arp(bond);
- read_unlock(&bond->curr_slave_lock);
- }
-
- if (bond->send_unsol_na) {
- read_lock(&bond->curr_slave_lock);
- bond_send_unsolicited_na(bond);
- read_unlock(&bond->curr_slave_lock);
- }
-
if (bond_miimon_inspect(bond)) {
read_unlock(&bond->lock);
rtnl_lock();
@@ -2751,44 +2724,6 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
}
}
-/*
- * Kick out a gratuitous ARP for an IP on the bonding master plus one
- * for each VLAN above us.
- *
- * Caller must hold curr_slave_lock for read or better
- */
-static void bond_send_gratuitous_arp(struct bonding *bond)
-{
- struct slave *slave = bond->curr_active_slave;
- struct vlan_entry *vlan;
- struct net_device *vlan_dev;
-
- pr_debug("bond_send_grat_arp: bond %s slave %s\n",
- bond->dev->name, slave ? slave->dev->name : "NULL");
-
- if (!slave || !bond->send_grat_arp ||
- test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
- return;
-
- bond->send_grat_arp--;
-
- if (bond->master_ip) {
- bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip,
- bond->master_ip, 0);
- }
-
- if (!bond->vlgrp)
- return;
-
- list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
- vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
- if (vlan->vlan_ip) {
- bond_arp_send(slave->dev, ARPOP_REPLY, vlan->vlan_ip,
- vlan->vlan_ip, vlan->vlan_id);
- }
- }
-}
-
static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
{
int i;
@@ -3255,18 +3190,6 @@ void bond_activebackup_arp_mon(struct work_struct *work)
if (bond->slave_cnt == 0)
goto re_arm;
- if (bond->send_grat_arp) {
- read_lock(&bond->curr_slave_lock);
- bond_send_gratuitous_arp(bond);
- read_unlock(&bond->curr_slave_lock);
- }
-
- if (bond->send_unsol_na) {
- read_lock(&bond->curr_slave_lock);
- bond_send_unsolicited_na(bond);
- read_unlock(&bond->curr_slave_lock);
- }
-
if (bond_ab_arp_inspect(bond, delta_in_ticks)) {
read_unlock(&bond->lock);
rtnl_lock();
@@ -3645,9 +3568,6 @@ static int bond_close(struct net_device *bond_dev)
write_lock_bh(&bond->lock);
- bond->send_grat_arp = 0;
- bond->send_unsol_na = 0;
-
/* signal timers not to re-arm */
bond->kill_timers = 1;
@@ -4724,18 +4644,6 @@ static int bond_check_params(struct bond_params *params)
use_carrier = 1;
}
- if (num_grat_arp < 0 || num_grat_arp > 255) {
- pr_warning("Warning: num_grat_arp (%d) not in range 0-255 so it was reset to 1\n",
- num_grat_arp);
- num_grat_arp = 1;
- }
-
- if (num_unsol_na < 0 || num_unsol_na > 255) {
- pr_warning("Warning: num_unsol_na (%d) not in range 0-255 so it was reset to 1\n",
- num_unsol_na);
- num_unsol_na = 1;
- }
-
/* reset values for 802.3ad */
if (bond_mode == BOND_MODE_8023AD) {
if (!miimon) {
@@ -4925,8 +4833,6 @@ static int bond_check_params(struct bond_params *params)
params->mode = bond_mode;
params->xmit_policy = xmit_hashtype;
params->miimon = miimon;
- params->num_grat_arp = num_grat_arp;
- params->num_unsol_na = num_unsol_na;
params->arp_interval = arp_interval;
params->arp_validate = arp_validate_value;
params->updelay = updelay;
@@ -5121,7 +5027,6 @@ static int __init bonding_init(void)
register_netdevice_notifier(&bond_netdev_notifier);
register_inetaddr_notifier(&bond_inetaddr_notifier);
- bond_register_ipv6_notifier();
out:
return res;
err:
@@ -5136,7 +5041,6 @@ static void __exit bonding_exit(void)
{
unregister_netdevice_notifier(&bond_netdev_notifier);
unregister_inetaddr_notifier(&bond_inetaddr_notifier);
- bond_unregister_ipv6_notifier();
bond_destroy_sysfs();
bond_destroy_debugfs();
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index de87aea..259ff32 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -874,84 +874,6 @@ static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR,
bonding_show_ad_select, bonding_store_ad_select);
/*
- * Show and set the number of grat ARP to send after a failover event.
- */
-static ssize_t bonding_show_n_grat_arp(struct device *d,
- struct device_attribute *attr,
- char *buf)
-{
- struct bonding *bond = to_bond(d);
-
- return sprintf(buf, "%d\n", bond->params.num_grat_arp);
-}
-
-static ssize_t bonding_store_n_grat_arp(struct device *d,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- int new_value, ret = count;
- struct bonding *bond = to_bond(d);
-
- if (sscanf(buf, "%d", &new_value) != 1) {
- pr_err("%s: no num_grat_arp value specified.\n",
- bond->dev->name);
- ret = -EINVAL;
- goto out;
- }
- if (new_value < 0 || new_value > 255) {
- pr_err("%s: Invalid num_grat_arp value %d not in range 0-255; rejected.\n",
- bond->dev->name, new_value);
- ret = -EINVAL;
- goto out;
- } else {
- bond->params.num_grat_arp = new_value;
- }
-out:
- return ret;
-}
-static DEVICE_ATTR(num_grat_arp, S_IRUGO | S_IWUSR,
- bonding_show_n_grat_arp, bonding_store_n_grat_arp);
-
-/*
- * Show and set the number of unsolicited NA's to send after a failover event.
- */
-static ssize_t bonding_show_n_unsol_na(struct device *d,
- struct device_attribute *attr,
- char *buf)
-{
- struct bonding *bond = to_bond(d);
-
- return sprintf(buf, "%d\n", bond->params.num_unsol_na);
-}
-
-static ssize_t bonding_store_n_unsol_na(struct device *d,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- int new_value, ret = count;
- struct bonding *bond = to_bond(d);
-
- if (sscanf(buf, "%d", &new_value) != 1) {
- pr_err("%s: no num_unsol_na value specified.\n",
- bond->dev->name);
- ret = -EINVAL;
- goto out;
- }
-
- if (new_value < 0 || new_value > 255) {
- pr_err("%s: Invalid num_unsol_na value %d not in range 0-255; rejected.\n",
- bond->dev->name, new_value);
- ret = -EINVAL;
- goto out;
- } else
- bond->params.num_unsol_na = new_value;
-out:
- return ret;
-}
-static DEVICE_ATTR(num_unsol_na, S_IRUGO | S_IWUSR,
- bonding_show_n_unsol_na, bonding_store_n_unsol_na);
-
-/*
* Show and set the MII monitor interval. There are two tricky bits
* here. First, if MII monitoring is activated, then we must disable
* ARP monitoring. Second, if the timer isn't running, we must
@@ -1650,8 +1572,6 @@ static struct attribute *per_bond_attrs[] = {
&dev_attr_lacp_rate.attr,
&dev_attr_ad_select.attr,
&dev_attr_xmit_hash_policy.attr,
- &dev_attr_num_grat_arp.attr,
- &dev_attr_num_unsol_na.attr,
&dev_attr_miimon.attr,
&dev_attr_primary.attr,
&dev_attr_primary_reselect.attr,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 90736cb..77180b1 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -149,8 +149,6 @@ struct bond_params {
int mode;
int xmit_policy;
int miimon;
- int num_grat_arp;
- int num_unsol_na;
int arp_interval;
int arp_validate;
int use_carrier;
@@ -178,9 +176,6 @@ struct vlan_entry {
struct list_head vlan_list;
__be32 vlan_ip;
unsigned short vlan_id;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
- struct in6_addr vlan_ipv6;
-#endif
};
struct slave {
@@ -234,8 +229,6 @@ struct bonding {
rwlock_t lock;
rwlock_t curr_slave_lock;
s8 kill_timers;
- s8 send_grat_arp;
- s8 send_unsol_na;
s8 setup_by_slave;
s8 igmp_retrans;
#ifdef CONFIG_PROC_FS
@@ -260,9 +253,6 @@ struct bonding {
struct delayed_work alb_work;
struct delayed_work ad_work;
struct delayed_work mcast_work;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
- struct in6_addr master_ipv6;
-#endif
#ifdef CONFIG_DEBUG_FS
/* debugging suport via debugfs */
struct dentry *debug_dir;
@@ -459,23 +449,4 @@ extern const struct bond_parm_tbl fail_over_mac_tbl[];
extern const struct bond_parm_tbl pri_reselect_tbl[];
extern struct bond_parm_tbl ad_select_tbl[];
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-void bond_send_unsolicited_na(struct bonding *bond);
-void bond_register_ipv6_notifier(void);
-void bond_unregister_ipv6_notifier(void);
-#else
-static inline void bond_send_unsolicited_na(struct bonding *bond)
-{
- return;
-}
-static inline void bond_register_ipv6_notifier(void)
-{
- return;
-}
-static inline void bond_unregister_ipv6_notifier(void)
-{
- return;
-}
-#endif
-
#endif /* _LINUX_BONDING_H */
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index b2ff70f..969e700 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -501,13 +501,14 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
return NOTIFY_BAD;
case NETDEV_NOTIFY_PEERS:
+ case NETDEV_BONDING_FAILOVER:
/* Propagate to vlan devices */
for (i = 0; i < VLAN_N_VID; i++) {
vlandev = vlan_group_get_device(grp, i);
if (!vlandev)
continue;
- call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, vlandev);
+ call_netdevice_notifiers(event, vlandev);
}
break;
}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 5345b0b..acf553f 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1203,6 +1203,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
break;
/* fall through */
case NETDEV_NOTIFY_PEERS:
+ case NETDEV_BONDING_FAILOVER:
/* Send gratuitous ARP to notify of link change */
inetdev_send_gratuitous_arp(dev, in_dev);
break;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index a51fa74c..6f7d491 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1746,6 +1746,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
fib6_run_gc(~0UL, net);
break;
case NETDEV_NOTIFY_PEERS:
+ case NETDEV_BONDING_FAILOVER:
ndisc_send_unsol_na(dev);
break;
default:
--
1.7.4
--
Ben Hutchings, Senior Software Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply related
* [PATCH net-next-2.6 2/3] vlan: Propagate NETDEV_NOTIFY_PEERS notifier
From: Ben Hutchings @ 2011-04-15 23:46 UTC (permalink / raw)
To: David Miller, Patrick McHardy; +Cc: netdev
The NETDEV_NOTIFY_PEERS notifier indicates that a device moved to a
different physical link; this also applies to any VLAN devices on top
of it.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
net/8021q/vlan.c | 11 +++++++++++
1 files changed, 11 insertions(+), 0 deletions(-)
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 14ef5ef..b2ff70f 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -499,6 +499,17 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
case NETDEV_PRE_TYPE_CHANGE:
/* Forbid underlaying device to change its type. */
return NOTIFY_BAD;
+
+ case NETDEV_NOTIFY_PEERS:
+ /* Propagate to vlan devices */
+ for (i = 0; i < VLAN_N_VID; i++) {
+ vlandev = vlan_group_get_device(grp, i);
+ if (!vlandev)
+ continue;
+
+ call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, vlandev);
+ }
+ break;
}
out:
--
1.7.4
--
Ben Hutchings, Senior Software Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply related
* [PATCH net-next-2.6 1/3] ipv6: Send unsolicited neighbour advertismements when notified
From: Ben Hutchings @ 2011-04-15 23:46 UTC (permalink / raw)
To: David Miller
Cc: netdev, Alexey Kuznetsov, Pekka Savola (ipv6), James Morris,
Hideaki YOSHIFUJI, Patrick McHardy
The NETDEV_NOTIFY_PEERS notifier is a request to send such
advertisements following migration to a different physical link,
e.g. virtual machine migration.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
This seems to work and should match what the bonding driver was
previously doing on failover, except that it iterates over all
addresses. I don't know whether it's actually right though.
Ben.
net/ipv6/ndisc.c | 26 ++++++++++++++++++++++++++
1 files changed, 26 insertions(+), 0 deletions(-)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 92f952d..a51fa74c 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -611,6 +611,29 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
inc_opt ? ND_OPT_TARGET_LL_ADDR : 0);
}
+static void ndisc_send_unsol_na(struct net_device *dev)
+{
+ struct inet6_dev *idev;
+ struct inet6_ifaddr *ifa;
+ struct in6_addr mcaddr;
+
+ idev = in6_dev_get(dev);
+ if (!idev)
+ return;
+
+ read_lock_bh(&idev->lock);
+ list_for_each_entry(ifa, &idev->addr_list, if_list) {
+ addrconf_addr_solict_mult(&ifa->addr, &mcaddr);
+ ndisc_send_na(dev, NULL, &mcaddr, &ifa->addr,
+ /*router=*/ !!idev->cnf.forwarding,
+ /*solicited=*/ false, /*override=*/ true,
+ /*inc_opt=*/ true);
+ }
+ read_unlock_bh(&idev->lock);
+
+ in6_dev_put(idev);
+}
+
void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
const struct in6_addr *solicit,
const struct in6_addr *daddr, const struct in6_addr *saddr)
@@ -1722,6 +1745,9 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
neigh_ifdown(&nd_tbl, dev);
fib6_run_gc(~0UL, net);
break;
+ case NETDEV_NOTIFY_PEERS:
+ ndisc_send_unsol_na(dev);
+ break;
default:
break;
}
--
1.7.4
--
Ben Hutchings, Senior Software Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply related
* [PATCH net-next-2.6 0/3] bonding,ipv4,ipv6,vlan: Use notifiers to trigger advertisements on failover
From: Ben Hutchings @ 2011-04-15 23:41 UTC (permalink / raw)
To: Jay Vosburgh, Andy Gospodarek, Patrick McHardy; +Cc: netdev, Ian Campbell
It is undesirable for the bonding driver to be poking into higher
level protocols, and notifiers provide a way to avoid that.
Ian added NETDEV_NOTIFY_PEERS to trigger gratuitous ARP on VM migration.
We should extend that to unsolicited NAs and propagate it through VLANs,
then treat bonding failover in the same way.
Ben.
Ben Hutchings (3):
ipv6: Send unsolicited neighbour advertisements when notified
vlan: Propagate NETDEV_NOTIFY_PEERS notifier
bonding,ipv4,ipv6,vlan: Handle NETDEV_BONDING_FAILOVER like
NETDEV_NOTIFY_PEERS
drivers/net/bonding/Makefile | 3 -
drivers/net/bonding/bond_ipv6.c | 225 --------------------------------------
drivers/net/bonding/bond_main.c | 96 ----------------
drivers/net/bonding/bond_sysfs.c | 80 --------------
drivers/net/bonding/bonding.h | 29 -----
net/8021q/vlan.c | 12 ++
net/ipv4/devinet.c | 1 +
net/ipv6/ndisc.c | 27 +++++
8 files changed, 40 insertions(+), 433 deletions(-)
delete mode 100644 drivers/net/bonding/bond_ipv6.c
--
1.7.4
--
Ben Hutchings, Senior Software Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply
* Re: net: Automatic IRQ siloing for network devices
From: Ben Hutchings @ 2011-04-15 22:54 UTC (permalink / raw)
To: Neil Horman; +Cc: netdev, davem
In-Reply-To: <1302898677-3833-1-git-send-email-nhorman@tuxdriver.com>
On Fri, 2011-04-15 at 16:17 -0400, Neil Horman wrote:
> Automatic IRQ siloing for network devices
>
> At last years netconf:
> http://vger.kernel.org/netconf2010.html
>
> Tom Herbert gave a talk in which he outlined some of the things we can do to
> improve scalability and througput in our network stack
>
> One of the big items on the slides was the notion of siloing irqs, which is the
> practice of setting irq affinity to a cpu or cpu set that was 'close' to the
> process that would be consuming data. The idea was to ensure that a hard irq
> for a nic (and its subsequent softirq) would execute on the same cpu as the
> process consuming the data, increasing cache hit rates and speeding up overall
> throughput.
>
> I had taken an idea away from that talk, and have finally gotten around to
> implementing it. One of the problems with the above approach is that its all
> quite manual. I.e. to properly enact this siloiong, you have to do a few things
> by hand:
>
> 1) decide which process is the heaviest user of a given rx queue
> 2) restrict the cpus which that task will run on
> 3) identify the irq which the rx queue in (1) maps to
> 4) manually set the affinity for the irq in (3) to cpus which match the cpus in
> (2)
[...]
This presumably works well with small numbers of flows and/or large
numbers of queues. You could scale it up somewhat by manipulating the
device's flow hash indirection table, but that usually only has 128
entries. (Changing the indirection table is currently quite expensive,
though that could be changed.)
I see RFS and accelerated RFS as the only reasonable way to scale to
large numbers of flows. And as part of accelerated RFS, I already did
the work for mapping CPUs to IRQs (note, not the other way round). If
IRQ affinity keeps changing then it will significantly undermine the
usefulness of hardware flow steering.
Now I'm not saying that your approach is useless. There is more
hardware out there with flow hashing than with flow steering, and there
are presumably many systems with small numbers of active flows. But I
think we need to avoid having two features that conflict and a
requirement for administrators to make a careful selection between them.
Ben.
--
Ben Hutchings, Senior Software Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply
* Re: [PATCH 2/3] net: Add net device irq siloing feature
From: Ben Hutchings @ 2011-04-15 22:49 UTC (permalink / raw)
To: Neil Horman
Cc: netdev, davem, Dimitris Michailidis, Thomas Gleixner,
David Howells, Eric Dumazet, Tom Herbert
In-Reply-To: <1302898677-3833-3-git-send-email-nhorman@tuxdriver.com>
On Fri, 2011-04-15 at 16:17 -0400, Neil Horman wrote:
> Using the irq affinity infrastrucuture, we can now allow net devices to call
> request_irq using a new wrapper function (request_net_irq), which will attach a
> common affinty_update handler to each requested irq. This affinty update
> mechanism correlates each tracked irq to the flow(s) that said irq processes
> most frequently. The highest traffic flow is noted, marked and exported to user
> space via the affinity_hint proc file for each irq. In this way, utilities like
> irqbalance are able to determine which cpu is recieving the most data from each
> rx queue on a given NIC, and set irq affinity accordingly.
[...]
Is irqbalance expected to poll the affinity hints? How often?
Ben.
--
Ben Hutchings, Senior Software Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply
* Re: [PATCH] net: forcedeth: convert to hw_features
From: David Miller @ 2011-04-15 22:51 UTC (permalink / raw)
To: mirq-linux; +Cc: netdev
In-Reply-To: <20110415145049.CC33613A65@rere.qmqm.pl>
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 15 Apr 2011 16:50:49 +0200 (CEST)
> This also fixes a race around np->txrxctl_bits while changing RXCSUM offload.
>
> Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Applied.
^ permalink raw reply
* Re: [PATCH] net: gianfar: convert to hw_features
From: David Miller @ 2011-04-15 22:51 UTC (permalink / raw)
To: mirq-linux; +Cc: netdev, oakad, cbouatmailru, jarkao2
In-Reply-To: <20110415145050.39D5013A69@rere.qmqm.pl>
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 15 Apr 2011 16:50:50 +0200 (CEST)
> Note: I bet that gfar_set_features() don't really need a full reset.
>
> Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Applied.
^ permalink raw reply
* Re: [PATCH] net: dm9000: convert to hw_features
From: David Miller @ 2011-04-15 22:51 UTC (permalink / raw)
To: mirq-linux; +Cc: netdev, ben-linux, henry.nestler
In-Reply-To: <20110415145050.0222B13A68@rere.qmqm.pl>
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 15 Apr 2011 16:50:49 +0200 (CEST)
> Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Applied.
^ permalink raw reply
* Re: [PATCH] net: spider_net: convert to hw_features
From: David Miller @ 2011-04-15 22:51 UTC (permalink / raw)
To: mirq-linux; +Cc: netdev, kou.ishizaki, jens
In-Reply-To: <20110415145049.D0047138DD@rere.qmqm.pl>
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 15 Apr 2011 16:50:49 +0200 (CEST)
> Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Applied.
^ permalink raw reply
* Re: [PATCH] net: mlx4: convert to hw_features
From: David Miller @ 2011-04-15 22:50 UTC (permalink / raw)
To: mirq-linux; +Cc: netdev, yevgenyp, eli
In-Reply-To: <20110415145049.D929D13A67@rere.qmqm.pl>
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 15 Apr 2011 16:50:49 +0200 (CEST)
> Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Applied.
^ permalink raw reply
* Re: [PATCH] minor cleanup to net_namespace.c.
From: David Miller @ 2011-04-15 22:48 UTC (permalink / raw)
To: jpirko; +Cc: rlandley, linux-kernel, netdev, eric.dumazet
In-Reply-To: <20110415123751.GC2697@psychotron>
From: Jiri Pirko <jpirko@redhat.com>
Date: Fri, 15 Apr 2011 14:37:52 +0200
> Fri, Apr 15, 2011 at 02:26:25PM CEST, rlandley@parallels.com wrote:
>>From: Rob Landley <rlandley@parallels.com>
>>
>>Inline a small static function that's only ever called from one place.
>>
>>Signed-off-by: Rob Landley <rlandley@parallels.com>
...
> Reviewed-by: Jiri Pirko <jpirko@redhat.com>
Applied.
^ permalink raw reply
* Re: [PATCH] net: export skb_clone_tx_timestamp
From: David Miller @ 2011-04-15 22:46 UTC (permalink / raw)
To: richardcochran; +Cc: netdev
In-Reply-To: <20110414173502.GA15244@riccoc20.at.omicron.at>
From: Richard Cochran <richardcochran@gmail.com>
Date: Thu, 14 Apr 2011 19:35:02 +0200
> MAC drivers compiled as modules may well want to call this function via
> the skb_tx_timestamp inline function. This patch exports the function in
> order to let this happen.
>
> Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
You can submit this patch to export this variable when you also submit
a patch to a upstream driver that makes use of this interface in such
a way.
But no sooner.
^ permalink raw reply
* Re: [PATCH 1/1] ipv6: RTA_PREFSRC support for ipv6 route source address selection
From: David Miller @ 2011-04-15 22:45 UTC (permalink / raw)
To: sahne; +Cc: netdev, linux-kernel
In-Reply-To: <20110414071057.GB78446@0x90.at>
From: Daniel Walter <sahne@0x90.at>
Date: Thu, 14 Apr 2011 09:10:57 +0200
> [ipv6] Add support for RTA_PREFSRC
>
> This patch allows a user to select the preferred source address
> for a specific IPv6-Route. It can be set via a netlink message
> setting RTA_PREFSRC to a valid IPv6 address which must be
> up on the device the route will be bound to.
>
>
> Signed-off-by: Daniel Walter <dwalter@barracuda.com>
Applied to net-next-2.6
> + err = ip6_route_get_saddr(net, rt, &fl6->daddr,
^^
This line had trailing whitespace, please avoid this in the future
as GIT complains about it and I have to fix it up by hand.
^ permalink raw reply
* Re: [PATCH 1/1] ipv6: ignore looped-back NA while dad is running
From: David Miller @ 2011-04-15 22:44 UTC (permalink / raw)
To: sahne; +Cc: netdev, linux-kernel
In-Reply-To: <20110414070925.GA78446@0x90.at>
From: Daniel Walter <sahne@0x90.at>
Date: Thu, 14 Apr 2011 09:09:25 +0200
> [ipv6] Ignore looped-back NAs while in Duplicate Address Detection
>
> If we send an unsolicited NA shortly after bringing up an
> IPv6 address, the duplicate address detection algorithm
> fails and the ip stays in tentative mode forever.
> This is due a missing check if the NA is looped-back to us.
>
> Signed-off-by: Daniel Walter <dwalter@barracuda.com>
Applied to net-next-2.6
^ permalink raw reply
* [PATCH v5 7/7] ipv4: Use caller's on-stack flowi as-is in output route lookups.
From: David Miller @ 2011-04-15 22:39 UTC (permalink / raw)
To: netdev
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 2 +-
net/ipv4/route.c | 136 ++++++++++++++++++++++++--------------------------
2 files changed, 66 insertions(+), 72 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 1337917..b7cab6f 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -118,7 +118,7 @@ extern int ip_rt_init(void);
extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
__be32 src, struct net_device *dev);
extern void rt_cache_flush(struct net *net, int how);
-extern struct rtable *__ip_route_output_key(struct net *, const struct flowi4 *flp);
+extern struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp);
extern struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
struct sock *sk);
extern struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e9244e0..c55620d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1047,7 +1047,7 @@ static unsigned int ipv4_default_mtu(const struct dst_entry *dst)
return mtu;
}
-static void rt_init_metrics(struct rtable *rt, const struct flowi4 *oldflp4,
+static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
struct fib_info *fi)
{
struct inet_peer *peer;
@@ -1056,7 +1056,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *oldflp4,
/* If a peer entry exists for this destination, we must hook
* it up in order to get at cached metrics.
*/
- if (oldflp4 && (oldflp4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS))
+ if (fl4 && (fl4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS))
create = 1;
rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create);
@@ -1083,7 +1083,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *oldflp4,
}
}
-static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *oldflp4,
+static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4,
const struct fib_result *res,
struct fib_info *fi, u16 type, u32 itag)
{
@@ -1093,7 +1093,7 @@ static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *oldflp4,
if (FIB_RES_GW(*res) &&
FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
rt->rt_gateway = FIB_RES_GW(*res);
- rt_init_metrics(rt, oldflp4, fi);
+ rt_init_metrics(rt, fl4, fi);
#ifdef CONFIG_IP_ROUTE_CLASSID
dst->tclassid = FIB_RES_NH(*res).nh_tclassid;
#endif
@@ -1587,12 +1587,11 @@ EXPORT_SYMBOL(ip_route_input);
/* called with rcu_read_lock() */
static struct rtable *__mkroute_output(const struct fib_result *res,
const struct flowi4 *fl4,
- const struct flowi4 *oldflp4,
struct net_device *dev_out,
unsigned int flags)
{
struct fib_info *fi = res->fi;
- u32 tos = RT_FL_TOS(oldflp4);
+ u32 tos = RT_FL_TOS(fl4);
struct in_device *in_dev;
u16 type = res->type;
struct rtable *rth;
@@ -1619,8 +1618,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
fi = NULL;
} else if (type == RTN_MULTICAST) {
flags |= RTCF_MULTICAST | RTCF_LOCAL;
- if (!ip_check_mc_rcu(in_dev, oldflp4->daddr, oldflp4->saddr,
- oldflp4->flowi4_proto))
+ if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr,
+ fl4->flowi4_proto))
flags &= ~RTCF_LOCAL;
/* If multicast route do not exist use
* default one, but do not gateway in this case.
@@ -1645,9 +1644,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_dst = fl4->daddr;
rth->rt_src = fl4->saddr;
rth->rt_route_iif = 0;
- rth->rt_iif = oldflp4->flowi4_oif ? : dev_out->ifindex;
- rth->rt_oif = oldflp4->flowi4_oif;
- rth->rt_mark = oldflp4->flowi4_mark;
+ rth->rt_iif = fl4->flowi4_oif ? : dev_out->ifindex;
+ rth->rt_oif = fl4->flowi4_oif;
+ rth->rt_mark = fl4->flowi4_mark;
rth->rt_gateway = fl4->daddr;
rth->rt_spec_dst= fl4->saddr;
rth->rt_peer_genid = 0;
@@ -1670,7 +1669,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
#ifdef CONFIG_IP_MROUTE
if (type == RTN_MULTICAST) {
if (IN_DEV_MFORWARD(in_dev) &&
- !ipv4_is_local_multicast(oldflp4->daddr)) {
+ !ipv4_is_local_multicast(fl4->daddr)) {
rth->dst.input = ip_mr_input;
rth->dst.output = ip_mc_output;
}
@@ -1678,7 +1677,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
#endif
}
- rt_set_nexthop(rth, oldflp4, res, fi, type, 0);
+ rt_set_nexthop(rth, fl4, res, fi, type, 0);
return rth;
}
@@ -1687,13 +1686,12 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
* Major route resolver routine.
*/
-struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *oldflp4)
+struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
{
- u32 tos = RT_FL_TOS(oldflp4);
- struct flowi4 fl4;
- struct fib_result res;
- unsigned int flags = 0;
struct net_device *dev_out = NULL;
+ u32 tos = RT_FL_TOS(fl4);
+ unsigned int flags = 0;
+ struct fib_result res;
struct rtable *rth;
res.fi = NULL;
@@ -1701,21 +1699,17 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *oldfl
res.r = NULL;
#endif
- fl4.flowi4_oif = oldflp4->flowi4_oif;
- fl4.flowi4_iif = net->loopback_dev->ifindex;
- fl4.flowi4_mark = oldflp4->flowi4_mark;
- fl4.daddr = oldflp4->daddr;
- fl4.saddr = oldflp4->saddr;
- fl4.flowi4_tos = tos & IPTOS_RT_MASK;
- fl4.flowi4_scope = ((tos & RTO_ONLINK) ?
- RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
+ fl4->flowi4_iif = net->loopback_dev->ifindex;
+ fl4->flowi4_tos = tos & IPTOS_RT_MASK;
+ fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
+ RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
rcu_read_lock();
- if (oldflp4->saddr) {
+ if (fl4->saddr) {
rth = ERR_PTR(-EINVAL);
- if (ipv4_is_multicast(oldflp4->saddr) ||
- ipv4_is_lbcast(oldflp4->saddr) ||
- ipv4_is_zeronet(oldflp4->saddr))
+ if (ipv4_is_multicast(fl4->saddr) ||
+ ipv4_is_lbcast(fl4->saddr) ||
+ ipv4_is_zeronet(fl4->saddr))
goto out;
/* I removed check for oif == dev_out->oif here.
@@ -1726,11 +1720,11 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *oldfl
of another iface. --ANK
*/
- if (oldflp4->flowi4_oif == 0 &&
- (ipv4_is_multicast(oldflp4->daddr) ||
- ipv4_is_lbcast(oldflp4->daddr))) {
+ if (fl4->flowi4_oif == 0 &&
+ (ipv4_is_multicast(fl4->daddr) ||
+ ipv4_is_lbcast(fl4->daddr))) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
- dev_out = __ip_dev_find(net, oldflp4->saddr, false);
+ dev_out = __ip_dev_find(net, fl4->saddr, false);
if (dev_out == NULL)
goto out;
@@ -1749,20 +1743,20 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *oldfl
Luckily, this hack is good workaround.
*/
- fl4.flowi4_oif = dev_out->ifindex;
+ fl4->flowi4_oif = dev_out->ifindex;
goto make_route;
}
- if (!(oldflp4->flowi4_flags & FLOWI_FLAG_ANYSRC)) {
+ if (!(fl4->flowi4_flags & FLOWI_FLAG_ANYSRC)) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
- if (!__ip_dev_find(net, oldflp4->saddr, false))
+ if (!__ip_dev_find(net, fl4->saddr, false))
goto out;
}
}
- if (oldflp4->flowi4_oif) {
- dev_out = dev_get_by_index_rcu(net, oldflp4->flowi4_oif);
+ if (fl4->flowi4_oif) {
+ dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif);
rth = ERR_PTR(-ENODEV);
if (dev_out == NULL)
goto out;
@@ -1772,37 +1766,37 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *oldfl
rth = ERR_PTR(-ENETUNREACH);
goto out;
}
- if (ipv4_is_local_multicast(oldflp4->daddr) ||
- ipv4_is_lbcast(oldflp4->daddr)) {
- if (!fl4.saddr)
- fl4.saddr = inet_select_addr(dev_out, 0,
- RT_SCOPE_LINK);
+ if (ipv4_is_local_multicast(fl4->daddr) ||
+ ipv4_is_lbcast(fl4->daddr)) {
+ if (!fl4->saddr)
+ fl4->saddr = inet_select_addr(dev_out, 0,
+ RT_SCOPE_LINK);
goto make_route;
}
- if (!fl4.saddr) {
- if (ipv4_is_multicast(oldflp4->daddr))
- fl4.saddr = inet_select_addr(dev_out, 0,
- fl4.flowi4_scope);
- else if (!oldflp4->daddr)
- fl4.saddr = inet_select_addr(dev_out, 0,
- RT_SCOPE_HOST);
+ if (fl4->saddr) {
+ if (ipv4_is_multicast(fl4->daddr))
+ fl4->saddr = inet_select_addr(dev_out, 0,
+ fl4->flowi4_scope);
+ else if (!fl4->daddr)
+ fl4->saddr = inet_select_addr(dev_out, 0,
+ RT_SCOPE_HOST);
}
}
- if (!fl4.daddr) {
- fl4.daddr = fl4.saddr;
- if (!fl4.daddr)
- fl4.daddr = fl4.saddr = htonl(INADDR_LOOPBACK);
+ if (!fl4->daddr) {
+ fl4->daddr = fl4->saddr;
+ if (!fl4->daddr)
+ fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK);
dev_out = net->loopback_dev;
- fl4.flowi4_oif = net->loopback_dev->ifindex;
+ fl4->flowi4_oif = net->loopback_dev->ifindex;
res.type = RTN_LOCAL;
flags |= RTCF_LOCAL;
goto make_route;
}
- if (fib_lookup(net, &fl4, &res)) {
+ if (fib_lookup(net, fl4, &res)) {
res.fi = NULL;
- if (oldflp4->flowi4_oif) {
+ if (fl4->flowi4_oif) {
/* Apparently, routing tables are wrong. Assume,
that the destination is on link.
@@ -1821,9 +1815,9 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *oldfl
likely IPv6, but we do not.
*/
- if (fl4.saddr == 0)
- fl4.saddr = inet_select_addr(dev_out, 0,
- RT_SCOPE_LINK);
+ if (fl4->saddr == 0)
+ fl4->saddr = inet_select_addr(dev_out, 0,
+ RT_SCOPE_LINK);
res.type = RTN_UNICAST;
goto make_route;
}
@@ -1832,38 +1826,38 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *oldfl
}
if (res.type == RTN_LOCAL) {
- if (!fl4.saddr) {
+ if (!fl4->saddr) {
if (res.fi->fib_prefsrc)
- fl4.saddr = res.fi->fib_prefsrc;
+ fl4->saddr = res.fi->fib_prefsrc;
else
- fl4.saddr = fl4.daddr;
+ fl4->saddr = fl4->daddr;
}
dev_out = net->loopback_dev;
- fl4.flowi4_oif = dev_out->ifindex;
+ fl4->flowi4_oif = dev_out->ifindex;
res.fi = NULL;
flags |= RTCF_LOCAL;
goto make_route;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
- if (res.fi->fib_nhs > 1 && fl4.flowi4_oif == 0)
+ if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0)
fib_select_multipath(&res);
else
#endif
if (!res.prefixlen &&
res.table->tb_num_default > 1 &&
- res.type == RTN_UNICAST && !fl4.flowi4_oif)
+ res.type == RTN_UNICAST && !fl4->flowi4_oif)
fib_select_default(&res);
- if (!fl4.saddr)
- fl4.saddr = FIB_RES_PREFSRC(net, res);
+ if (!fl4->saddr)
+ fl4->saddr = FIB_RES_PREFSRC(net, res);
dev_out = FIB_RES_DEV(res);
- fl4.flowi4_oif = dev_out->ifindex;
+ fl4->flowi4_oif = dev_out->ifindex;
make_route:
- rth = __mkroute_output(&res, &fl4, oldflp4, dev_out, flags);
+ rth = __mkroute_output(&res, fl4, dev_out, flags);
if (!IS_ERR(rth))
rth = rt_finalize(rth, NULL);
--
1.7.4.3
^ permalink raw reply related
* [PATCH v5 6/7] ipv4: Kill rt_key_{src,dst} from struct rtable.
From: David Miller @ 2011-04-15 22:39 UTC (permalink / raw)
To: netdev
They are always used in contexts where they can be reconstituted,
or where the finally resolved rt->rt_{src,dst} is semantically
equivalent.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 4 ----
net/ipv4/ipmr.c | 4 ++--
net/ipv4/route.c | 24 +++++++-----------------
net/ipv4/xfrm4_policy.c | 2 --
4 files changed, 9 insertions(+), 25 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index b2a44a9..1337917 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -53,10 +53,6 @@ struct fib_info;
struct rtable {
struct dst_entry dst;
- /* Lookup key. */
- __be32 rt_key_dst;
- __be32 rt_key_src;
-
int rt_genid;
unsigned rt_flags;
__u16 rt_type;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 1f62eae..0441b26 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1791,8 +1791,8 @@ dont_forward:
static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct rtable *rt)
{
struct flowi4 fl4 = {
- .daddr = rt->rt_key_dst,
- .saddr = rt->rt_key_src,
+ .daddr = rt->rt_dst,
+ .saddr = rt->rt_src,
.flowi4_tos = rt->rt_tos,
.flowi4_oif = rt->rt_oif,
.flowi4_iif = rt->rt_iif,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b6ad9dc..e9244e0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -988,8 +988,8 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt)
src = rt->rt_src;
else {
struct flowi4 fl4 = {
- .daddr = rt->rt_key_dst,
- .saddr = rt->rt_key_src,
+ .daddr = rt->rt_dst,
+ .saddr = rt->rt_src,
.flowi4_tos = rt->rt_tos,
.flowi4_oif = rt->rt_oif,
.flowi4_iif = rt->rt_iif,
@@ -1164,8 +1164,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
#endif
rth->dst.output = ip_rt_bug;
- rth->rt_key_dst = daddr;
- rth->rt_key_src = saddr;
rth->rt_genid = rt_genid(dev_net(dev));
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
@@ -1300,8 +1298,6 @@ static int __mkroute_input(struct sk_buff *skb,
goto cleanup;
}
- rth->rt_key_dst = daddr;
- rth->rt_key_src = saddr;
rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
rth->rt_flags = flags;
rth->rt_type = res->type;
@@ -1475,8 +1471,6 @@ local_input:
rth->dst.tclassid = itag;
#endif
- rth->rt_key_dst = daddr;
- rth->rt_key_src = saddr;
rth->rt_genid = rt_genid(net);
rth->rt_flags = flags|RTCF_LOCAL;
rth->rt_type = res.type;
@@ -1644,8 +1638,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->dst.output = ip_output;
- rth->rt_key_dst = oldflp4->daddr;
- rth->rt_key_src = oldflp4->saddr;
rth->rt_genid = rt_genid(dev_net(dev_out));
rth->rt_flags = flags;
rth->rt_type = type;
@@ -1922,8 +1914,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
if (new->dev)
dev_hold(new->dev);
- rt->rt_key_dst = ort->rt_key_dst;
- rt->rt_key_src = ort->rt_key_src;
rt->rt_tos = ort->rt_tos;
rt->rt_route_iif = ort->rt_route_iif;
rt->rt_iif = ort->rt_iif;
@@ -1974,7 +1964,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
-static int rt_fill_info(struct net *net,
+static int rt_fill_info(struct net *net, __be32 src,
struct sk_buff *skb, u32 pid, u32 seq, int event,
int nowait, unsigned int flags)
{
@@ -2004,9 +1994,9 @@ static int rt_fill_info(struct net *net,
NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst);
- if (rt->rt_key_src) {
+ if (src) {
r->rtm_src_len = 32;
- NLA_PUT_BE32(skb, RTA_SRC, rt->rt_key_src);
+ NLA_PUT_BE32(skb, RTA_SRC, src);
}
if (rt->dst.dev)
NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
@@ -2016,7 +2006,7 @@ static int rt_fill_info(struct net *net,
#endif
if (rt_is_input_route(rt))
NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst);
- else if (rt->rt_src != rt->rt_key_src)
+ else if (rt->rt_src != src)
NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src);
if (rt->rt_dst != rt->rt_gateway)
@@ -2155,7 +2145,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
- err = rt_fill_info(net, skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
+ err = rt_fill_info(net, src, skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
RTM_NEWROUTE, 0, 0);
if (err <= 0)
goto errout_free;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index d20a05e..4a592d0 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -71,8 +71,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
struct rtable *rt = (struct rtable *)xdst->route;
const struct flowi4 *fl4 = &fl->u.ip4;
- rt->rt_key_dst = fl4->daddr;
- rt->rt_key_src = fl4->saddr;
rt->rt_tos = fl4->flowi4_tos;
rt->rt_route_iif = fl4->flowi4_iif;
rt->rt_iif = fl4->flowi4_iif;
--
1.7.4.3
^ permalink raw reply related
* [PATCH v5 5/7] net: Use non-zero allocations in dst_alloc().
From: David Miller @ 2011-04-15 22:39 UTC (permalink / raw)
To: netdev
Make dst_alloc() and it's users explicitly initialize the entire
entry.
The zero'ing done by kmem_cache_zalloc() was almost entirely
redundant.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/dst.c | 20 ++++++++++--
net/decnet/dn_route.c | 2 +
net/ipv4/route.c | 78 +++++++++++++++++++++++++++++-------------------
net/ipv6/route.c | 8 ++++-
net/xfrm/xfrm_policy.c | 1 +
5 files changed, 74 insertions(+), 35 deletions(-)
diff --git a/net/core/dst.c b/net/core/dst.c
index 9505778..30f0093 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -175,22 +175,36 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
if (ops->gc(ops))
return NULL;
}
- dst = kmem_cache_zalloc(ops->kmem_cachep, GFP_ATOMIC);
+ dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC);
if (!dst)
return NULL;
- dst->ops = ops;
+ dst->child = NULL;
dst->dev = dev;
if (dev)
dev_hold(dev);
+ dst->ops = ops;
dst_init_metrics(dst, dst_default_metrics, true);
+ dst->expires = 0UL;
dst->path = dst;
+ dst->neighbour = NULL;
+ dst->hh = NULL;
+#ifdef CONFIG_XFRM
+ dst->xfrm = NULL;
+#endif
dst->input = dst_discard;
dst->output = dst_discard;
-
+ dst->error = 0;
dst->obsolete = initial_obsolete;
+ dst->header_len = 0;
+ dst->trailer_len = 0;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ dst->tclassid = 0;
+#endif
atomic_set(&dst->__refcnt, initial_ref);
+ dst->__use = 0;
dst->lastuse = jiffies;
dst->flags = flags;
+ dst->next = NULL;
#if RT_CACHE_DEBUG >= 2
atomic_inc(&dst_total);
#endif
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index f489b08..74544bc 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1129,6 +1129,7 @@ make_route:
if (rt == NULL)
goto e_nobufs;
+ memset(&rt->fld, 0, sizeof(rt->fld));
rt->fld.saddr = oldflp->saddr;
rt->fld.daddr = oldflp->daddr;
rt->fld.flowidn_oif = oldflp->flowidn_oif;
@@ -1398,6 +1399,7 @@ make_route:
if (rt == NULL)
goto e_nobufs;
+ memset(&rt->fld, 0, sizeof(rt->fld));
rt->rt_saddr = fld.saddr;
rt->rt_daddr = fld.daddr;
rt->rt_gateway = fld.daddr;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 61a96ca..b6ad9dc 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1110,7 +1110,6 @@ static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *oldflp4,
#endif
set_class_tag(rt, itag);
#endif
- rt->rt_type = type;
}
static struct rtable *rt_dst_alloc(struct net_device *dev,
@@ -1160,25 +1159,28 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
if (!rth)
goto e_nobufs;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ rth->dst.tclassid = itag;
+#endif
rth->dst.output = ip_rt_bug;
rth->rt_key_dst = daddr;
- rth->rt_dst = daddr;
- rth->rt_tos = tos;
- rth->rt_mark = skb->mark;
rth->rt_key_src = saddr;
+ rth->rt_genid = rt_genid(dev_net(dev));
+ rth->rt_flags = RTCF_MULTICAST;
+ rth->rt_type = RTN_MULTICAST;
+ rth->rt_tos = tos;
+ rth->rt_dst = daddr;
rth->rt_src = saddr;
-#ifdef CONFIG_IP_ROUTE_CLASSID
- rth->dst.tclassid = itag;
-#endif
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
+ rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
- rth->rt_genid = rt_genid(dev_net(dev));
- rth->rt_flags = RTCF_MULTICAST;
- rth->rt_type = RTN_MULTICAST;
+ rth->rt_peer_genid = 0;
+ rth->peer = NULL;
+ rth->fi = NULL;
if (our) {
rth->dst.input= ip_local_deliver;
rth->rt_flags |= RTCF_LOCAL;
@@ -1299,25 +1301,28 @@ static int __mkroute_input(struct sk_buff *skb,
}
rth->rt_key_dst = daddr;
- rth->rt_dst = daddr;
- rth->rt_tos = tos;
- rth->rt_mark = skb->mark;
rth->rt_key_src = saddr;
+ rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
+ rth->rt_flags = flags;
+ rth->rt_type = res->type;
+ rth->rt_tos = tos;
+ rth->rt_dst = daddr;
rth->rt_src = saddr;
- rth->rt_gateway = daddr;
rth->rt_route_iif = in_dev->dev->ifindex;
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_oif = 0;
+ rth->rt_mark = skb->mark;
+ rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
+ rth->rt_peer_genid = 0;
+ rth->peer = NULL;
+ rth->fi = NULL;
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
- rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
rt_set_nexthop(rth, NULL, res, res->fi, res->type, itag);
- rth->rt_flags = flags;
-
*result = rth;
err = 0;
cleanup:
@@ -1464,30 +1469,37 @@ local_input:
if (!rth)
goto e_nobufs;
+ rth->dst.input= ip_local_deliver;
rth->dst.output= ip_rt_bug;
- rth->rt_genid = rt_genid(net);
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ rth->dst.tclassid = itag;
+#endif
rth->rt_key_dst = daddr;
- rth->rt_dst = daddr;
- rth->rt_tos = tos;
- rth->rt_mark = skb->mark;
rth->rt_key_src = saddr;
+ rth->rt_genid = rt_genid(net);
+ rth->rt_flags = flags|RTCF_LOCAL;
+ rth->rt_type = res.type;
+ rth->rt_tos = tos;
+ rth->rt_dst = daddr;
rth->rt_src = saddr;
#ifdef CONFIG_IP_ROUTE_CLASSID
rth->dst.tclassid = itag;
#endif
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
+ rth->rt_oif = 0;
+ rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
- rth->dst.input= ip_local_deliver;
- rth->rt_flags = flags|RTCF_LOCAL;
+ rth->rt_peer_genid = 0;
+ rth->peer = NULL;
+ rth->fi = NULL;
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
- rth->rt_type = res.type;
rth = rt_finalize(rth, skb);
err = 0;
if (IS_ERR(rth))
@@ -1630,20 +1642,25 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
if (!rth)
return ERR_PTR(-ENOBUFS);
+ rth->dst.output = ip_output;
+
rth->rt_key_dst = oldflp4->daddr;
- rth->rt_tos = tos;
rth->rt_key_src = oldflp4->saddr;
- rth->rt_oif = oldflp4->flowi4_oif;
- rth->rt_mark = oldflp4->flowi4_mark;
+ rth->rt_genid = rt_genid(dev_net(dev_out));
+ rth->rt_flags = flags;
+ rth->rt_type = type;
+ rth->rt_tos = tos;
rth->rt_dst = fl4->daddr;
rth->rt_src = fl4->saddr;
rth->rt_route_iif = 0;
rth->rt_iif = oldflp4->flowi4_oif ? : dev_out->ifindex;
+ rth->rt_oif = oldflp4->flowi4_oif;
+ rth->rt_mark = oldflp4->flowi4_mark;
rth->rt_gateway = fl4->daddr;
rth->rt_spec_dst= fl4->saddr;
-
- rth->dst.output=ip_output;
- rth->rt_genid = rt_genid(dev_net(dev_out));
+ rth->rt_peer_genid = 0;
+ rth->peer = NULL;
+ rth->fi = NULL;
RT_CACHE_STAT_INC(out_slow_tot);
@@ -1671,7 +1688,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rt_set_nexthop(rth, oldflp4, res, fi, type, 0);
- rth->rt_flags = flags;
return rth;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d3f55cc..4a1d5a0 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -223,7 +223,11 @@ static struct rt6_info ip6_blk_hole_entry_template = {
static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
struct net_device *dev)
{
- return (struct rt6_info *)dst_alloc(ops, dev, 0, 0, 0);
+ struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, 0);
+
+ memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+
+ return rt;
}
static void ip6_dst_destroy(struct dst_entry *dst)
@@ -880,6 +884,8 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0);
if (rt) {
+ memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+
new = &rt->dst;
new->__use = 1;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 70552c4..00bcb88 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1349,6 +1349,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
BUG();
}
xdst = dst_alloc(dst_ops, NULL, 0, 0, 0);
+ memset(&xdst->u.rt6.rt6i_table, 0, sizeof(*xdst) - sizeof(struct dst_entry));
xfrm_policy_put_afinfo(afinfo);
if (likely(xdst))
--
1.7.4.3
^ permalink raw reply related
* [PATCH v5 4/7] net: Make dst_alloc() take more explicit initializations.
From: David Miller @ 2011-04-15 22:39 UTC (permalink / raw)
To: netdev
Now the dst->dev, dev->obsolete, and dst->flags values can
be specified as well.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/dst.h | 3 ++-
net/core/dst.c | 18 +++++++++++++-----
net/decnet/dn_route.c | 13 ++-----------
net/ipv4/route.c | 48 +++++++++++++++++++-----------------------------
net/ipv6/route.c | 29 +++++++++++------------------
net/xfrm/xfrm_policy.c | 2 +-
6 files changed, 48 insertions(+), 65 deletions(-)
diff --git a/include/net/dst.h b/include/net/dst.h
index 75b95df..9fc2ada 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -352,7 +352,8 @@ static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb)
}
extern int dst_discard(struct sk_buff *skb);
-extern void *dst_alloc(struct dst_ops * ops, int initial_ref);
+extern void *dst_alloc(struct dst_ops * ops, struct net_device *dev,
+ int initial_ref, int initial_obsolete, int flags);
extern void __dst_free(struct dst_entry * dst);
extern struct dst_entry *dst_destroy(struct dst_entry * dst);
diff --git a/net/core/dst.c b/net/core/dst.c
index 91104d3..9505778 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -166,7 +166,8 @@ EXPORT_SYMBOL(dst_discard);
const u32 dst_default_metrics[RTAX_MAX];
-void *dst_alloc(struct dst_ops *ops, int initial_ref)
+void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
+ int initial_ref, int initial_obsolete, int flags)
{
struct dst_entry *dst;
@@ -177,12 +178,19 @@ void *dst_alloc(struct dst_ops *ops, int initial_ref)
dst = kmem_cache_zalloc(ops->kmem_cachep, GFP_ATOMIC);
if (!dst)
return NULL;
- atomic_set(&dst->__refcnt, initial_ref);
dst->ops = ops;
- dst->lastuse = jiffies;
- dst->path = dst;
- dst->input = dst->output = dst_discard;
+ dst->dev = dev;
+ if (dev)
+ dev_hold(dev);
dst_init_metrics(dst, dst_default_metrics, true);
+ dst->path = dst;
+ dst->input = dst_discard;
+ dst->output = dst_discard;
+
+ dst->obsolete = initial_obsolete;
+ atomic_set(&dst->__refcnt, initial_ref);
+ dst->lastuse = jiffies;
+ dst->flags = flags;
#if RT_CACHE_DEBUG >= 2
atomic_inc(&dst_total);
#endif
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 9f09d4f..f489b08 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1125,13 +1125,10 @@ make_route:
if (dev_out->flags & IFF_LOOPBACK)
flags |= RTCF_LOCAL;
- rt = dst_alloc(&dn_dst_ops, 0);
+ rt = dst_alloc(&dn_dst_ops, dev_out, 1, 0, DST_HOST);
if (rt == NULL)
goto e_nobufs;
- atomic_set(&rt->dst.__refcnt, 1);
- rt->dst.flags = DST_HOST;
-
rt->fld.saddr = oldflp->saddr;
rt->fld.daddr = oldflp->daddr;
rt->fld.flowidn_oif = oldflp->flowidn_oif;
@@ -1146,8 +1143,6 @@ make_route:
rt->rt_dst_map = fld.daddr;
rt->rt_src_map = fld.saddr;
- rt->dst.dev = dev_out;
- dev_hold(dev_out);
rt->dst.neighbour = neigh;
neigh = NULL;
@@ -1399,7 +1394,7 @@ static int dn_route_input_slow(struct sk_buff *skb)
}
make_route:
- rt = dst_alloc(&dn_dst_ops, 0);
+ rt = dst_alloc(&dn_dst_ops, out_dev, 0, 0, DST_HOST);
if (rt == NULL)
goto e_nobufs;
@@ -1419,9 +1414,7 @@ make_route:
rt->fld.flowidn_iif = in_dev->ifindex;
rt->fld.flowidn_mark = fld.flowidn_mark;
- rt->dst.flags = DST_HOST;
rt->dst.neighbour = neigh;
- rt->dst.dev = out_dev;
rt->dst.lastuse = jiffies;
rt->dst.output = dn_rt_bug;
switch(res.type) {
@@ -1440,8 +1433,6 @@ make_route:
rt->dst.input = dst_discard;
}
rt->rt_flags = flags;
- if (rt->dst.dev)
- dev_hold(rt->dst.dev);
err = dn_rt_set_next_hop(rt, &res);
if (err)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f66898c..61a96ca 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1113,21 +1113,17 @@ static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *oldflp4,
rt->rt_type = type;
}
-static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm)
+static struct rtable *rt_dst_alloc(struct net_device *dev,
+ bool nopolicy, bool noxfrm)
{
- struct rtable *rt = dst_alloc(&ipv4_dst_ops, 1);
- if (rt) {
- rt->dst.obsolete = -1;
-
- /* To avoid expensive rcu stuff for this uncached dst, we set
- * DST_NOCACHE so that dst_release() can free dst without
- * waiting a grace period.
- */
- rt->dst.flags = DST_NOCACHE | DST_HOST |
- (nopolicy ? DST_NOPOLICY : 0) |
- (noxfrm ? DST_NOXFRM : 0);
- }
- return rt;
+ /* To avoid expensive rcu stuff for this uncached dst, we set
+ * DST_NOCACHE so that dst_release() can free dst without
+ * waiting a grace period.
+ */
+ return dst_alloc(&ipv4_dst_ops, dev, 1, -1,
+ DST_NOCACHE | DST_HOST |
+ (nopolicy ? DST_NOPOLICY : 0) |
+ (noxfrm ? DST_NOXFRM : 0));
}
/* called in rcu_read_lock() section */
@@ -1159,7 +1155,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
if (err < 0)
goto e_err;
}
- rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ rth = rt_dst_alloc(init_net.loopback_dev,
+ IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
@@ -1176,8 +1173,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
#endif
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
- rth->dst.dev = init_net.loopback_dev;
- dev_hold(rth->dst.dev);
rth->rt_oif = 0;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
@@ -1295,7 +1290,8 @@ static int __mkroute_input(struct sk_buff *skb,
}
}
- rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
+ rth = rt_dst_alloc(out_dev->dev,
+ IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
@@ -1311,8 +1307,6 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_gateway = daddr;
rth->rt_route_iif = in_dev->dev->ifindex;
rth->rt_iif = in_dev->dev->ifindex;
- rth->dst.dev = (out_dev)->dev;
- dev_hold(rth->dst.dev);
rth->rt_oif = 0;
rth->rt_spec_dst= spec_dst;
@@ -1465,7 +1459,8 @@ brd_input:
RT_CACHE_STAT_INC(in_brd);
local_input:
- rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ rth = rt_dst_alloc(net->loopback_dev,
+ IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
@@ -1483,8 +1478,6 @@ local_input:
#endif
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
- rth->dst.dev = net->loopback_dev;
- dev_hold(rth->dst.dev);
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->dst.input= ip_local_deliver;
@@ -1631,7 +1624,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
fi = NULL;
}
- rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
+ rth = rt_dst_alloc(dev_out,
+ IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(in_dev, NOXFRM));
if (!rth)
return ERR_PTR(-ENOBUFS);
@@ -1645,10 +1639,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_src = fl4->saddr;
rth->rt_route_iif = 0;
rth->rt_iif = oldflp4->flowi4_oif ? : dev_out->ifindex;
- /* get references to the devices that are to be hold by the routing
- cache entry */
- rth->dst.dev = dev_out;
- dev_hold(dev_out);
rth->rt_gateway = fl4->daddr;
rth->rt_spec_dst= fl4->saddr;
@@ -1901,7 +1891,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
- struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, 1);
+ struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, 0, 0);
struct rtable *ort = (struct rtable *) dst_orig;
if (rt) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 843406f..d3f55cc 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -220,9 +220,10 @@ static struct rt6_info ip6_blk_hole_entry_template = {
#endif
/* allocate dst with ip6_dst_ops */
-static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops)
+static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
+ struct net_device *dev)
{
- return (struct rt6_info *)dst_alloc(ops, 0);
+ return (struct rt6_info *)dst_alloc(ops, dev, 0, 0, 0);
}
static void ip6_dst_destroy(struct dst_entry *dst)
@@ -874,10 +875,10 @@ EXPORT_SYMBOL(ip6_route_output);
struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
- struct rt6_info *rt = dst_alloc(&ip6_dst_blackhole_ops, 1);
- struct rt6_info *ort = (struct rt6_info *) dst_orig;
+ struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig;
struct dst_entry *new = NULL;
+ rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0);
if (rt) {
new = &rt->dst;
@@ -886,9 +887,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
new->output = dst_discard;
dst_copy_metrics(new, &ort->dst);
- new->dev = ort->dst.dev;
- if (new->dev)
- dev_hold(new->dev);
rt->rt6i_idev = ort->rt6i_idev;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
@@ -1031,13 +1029,12 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
if (unlikely(idev == NULL))
return NULL;
- rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+ rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev);
if (unlikely(rt == NULL)) {
in6_dev_put(idev);
goto out;
}
- dev_hold(dev);
if (neigh)
neigh_hold(neigh);
else {
@@ -1046,7 +1043,6 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
neigh = NULL;
}
- rt->rt6i_dev = dev;
rt->rt6i_idev = idev;
rt->rt6i_nexthop = neigh;
atomic_set(&rt->dst.__refcnt, 1);
@@ -1205,7 +1201,7 @@ int ip6_route_add(struct fib6_config *cfg)
goto out;
}
- rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+ rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL);
if (rt == NULL) {
err = -ENOMEM;
@@ -1714,7 +1710,8 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
{
struct net *net = dev_net(ort->rt6i_dev);
- struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+ struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
+ ort->dst.dev);
if (rt) {
rt->dst.input = ort->dst.input;
@@ -1722,9 +1719,6 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
dst_copy_metrics(&rt->dst, &ort->dst);
rt->dst.error = ort->dst.error;
- rt->dst.dev = ort->dst.dev;
- if (rt->dst.dev)
- dev_hold(rt->dst.dev);
rt->rt6i_idev = ort->rt6i_idev;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
@@ -1994,7 +1988,8 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
int anycast)
{
struct net *net = dev_net(idev->dev);
- struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+ struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
+ net->loopback_dev);
struct neighbour *neigh;
if (rt == NULL) {
@@ -2004,13 +1999,11 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
return ERR_PTR(-ENOMEM);
}
- dev_hold(net->loopback_dev);
in6_dev_hold(idev);
rt->dst.flags = DST_HOST;
rt->dst.input = ip6_input;
rt->dst.output = ip6_output;
- rt->rt6i_dev = net->loopback_dev;
rt->rt6i_idev = idev;
dst_metric_set(&rt->dst, RTAX_HOPLIMIT, -1);
rt->dst.obsolete = -1;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 15792d8..70552c4 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1348,7 +1348,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
default:
BUG();
}
- xdst = dst_alloc(dst_ops, 0);
+ xdst = dst_alloc(dst_ops, NULL, 0, 0, 0);
xfrm_policy_put_afinfo(afinfo);
if (likely(xdst))
--
1.7.4.3
^ permalink raw reply related
* [PATCH v5 3/7] ipv4: Set DST_NOCACHE in rt_dst_alloc().
From: David Miller @ 2011-04-15 22:39 UTC (permalink / raw)
To: netdev
Instead of using a read/modify/write in rt_finalize().
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/route.c | 11 +++++------
1 files changed, 5 insertions(+), 6 deletions(-)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 4ed7788..f66898c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -492,11 +492,6 @@ void rt_cache_flush(struct net *net, int delay)
static struct rtable *rt_finalize(struct rtable *rt, struct sk_buff *skb)
{
- /* To avoid expensive rcu stuff for this uncached dst, we set
- * DST_NOCACHE so that dst_release() can free dst without
- * waiting a grace period.
- */
- rt->dst.flags |= DST_NOCACHE;
if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
int err = arp_bind_neighbour(&rt->dst);
if (err) {
@@ -1124,7 +1119,11 @@ static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm)
if (rt) {
rt->dst.obsolete = -1;
- rt->dst.flags = DST_HOST |
+ /* To avoid expensive rcu stuff for this uncached dst, we set
+ * DST_NOCACHE so that dst_release() can free dst without
+ * waiting a grace period.
+ */
+ rt->dst.flags = DST_NOCACHE | DST_HOST |
(nopolicy ? DST_NOPOLICY : 0) |
(noxfrm ? DST_NOXFRM : 0);
}
--
1.7.4.3
^ permalink raw reply related
* [PATCH v5 2/7] ipv4: Kill ip_route_input_noref().
From: David Miller @ 2011-04-15 22:39 UTC (permalink / raw)
To: netdev
The "noref" argument to ip_route_input_common() is now always ignored
because we do not cache routes, and in that case we must always grab
a reference to the resulting 'dst'.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 16 ++--------------
net/ipv4/arp.c | 2 +-
net/ipv4/ip_input.c | 4 ++--
net/ipv4/route.c | 6 +++---
net/ipv4/xfrm4_input.c | 4 ++--
5 files changed, 10 insertions(+), 22 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index f09d08f..b2a44a9 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -175,20 +175,8 @@ static inline struct rtable *ip_route_output_gre(struct net *net,
return ip_route_output_key(net, &fl4);
}
-extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
- u8 tos, struct net_device *devin, bool noref);
-
-static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
- u8 tos, struct net_device *devin)
-{
- return ip_route_input_common(skb, dst, src, tos, devin, false);
-}
-
-static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
- u8 tos, struct net_device *devin)
-{
- return ip_route_input_common(skb, dst, src, tos, devin, true);
-}
+extern int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
+ u8 tos, struct net_device *devin);
extern unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, unsigned short new_mtu, struct net_device *dev);
extern void ip_rt_send_redirect(struct sk_buff *skb);
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 1b74d3b..ef44a91 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -875,7 +875,7 @@ static int arp_process(struct sk_buff *skb)
}
if (arp->ar_op == htons(ARPOP_REQUEST) &&
- ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
+ ip_route_input(skb, tip, sip, 0, dev) == 0) {
rt = skb_rtable(skb);
addr_type = rt->rt_type;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index d7b2b09..577eb45 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -324,8 +324,8 @@ static int ip_rcv_finish(struct sk_buff *skb)
* how the packet travels inside Linux networking.
*/
if (skb_dst(skb) == NULL) {
- int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev);
+ int err = ip_route_input(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev);
if (unlikely(err)) {
if (err == -EHOSTUNREACH)
IP_INC_STATS_BH(dev_net(skb->dev),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8033171..4ed7788 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1540,8 +1540,8 @@ martian_source_keep_err:
goto out;
}
-int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
- u8 tos, struct net_device *dev, bool noref)
+int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+ u8 tos, struct net_device *dev)
{
int res;
@@ -1584,7 +1584,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rcu_read_unlock();
return res;
}
-EXPORT_SYMBOL(ip_route_input_common);
+EXPORT_SYMBOL(ip_route_input);
/* called with rcu_read_lock() */
static struct rtable *__mkroute_output(const struct fib_result *res,
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 06814b6..58d23a5 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -27,8 +27,8 @@ static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb)
if (skb_dst(skb) == NULL) {
const struct iphdr *iph = ip_hdr(skb);
- if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev))
+ if (ip_route_input(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev))
goto drop;
}
return dst_input(skb);
--
1.7.4.3
^ permalink raw reply related
* [PATCH v5 1/7] ipv4: Delete routing cache.
From: David Miller @ 2011-04-15 22:39 UTC (permalink / raw)
To: netdev
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 1 -
net/ipv4/fib_frontend.c | 5 -
net/ipv4/route.c | 908 ++---------------------------------------------
3 files changed, 23 insertions(+), 891 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 3782cdd..f09d08f 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -122,7 +122,6 @@ extern int ip_rt_init(void);
extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
__be32 src, struct net_device *dev);
extern void rt_cache_flush(struct net *net, int how);
-extern void rt_cache_flush_batch(struct net *net);
extern struct rtable *__ip_route_output_key(struct net *, const struct flowi4 *flp);
extern struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
struct sock *sk);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 2252471..33bbbda 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1022,11 +1022,6 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
rt_cache_flush(dev_net(dev), 0);
break;
case NETDEV_UNREGISTER_BATCH:
- /* The batch unregister is only called on the first
- * device in the list of devices being unregistered.
- * Therefore we should not pass dev_net(dev) in here.
- */
- rt_cache_flush_batch(NULL);
break;
}
return NOTIFY_DONE;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e9aee81..8033171 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,7 +129,6 @@ static int ip_rt_gc_elasticity __read_mostly = 8;
static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
-static int rt_chain_length_max __read_mostly = 20;
/*
* Interface to generic destination cache.
@@ -142,7 +141,6 @@ static void ipv4_dst_destroy(struct dst_entry *dst);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
-static int rt_garbage_collect(struct dst_ops *ops);
static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int how)
@@ -187,7 +185,6 @@ static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old)
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
- .gc = rt_garbage_collect,
.check = ipv4_dst_check,
.default_advmss = ipv4_default_advmss,
.default_mtu = ipv4_default_mtu,
@@ -222,184 +219,30 @@ const __u8 ip_tos2prio[16] = {
};
-/*
- * Route cache.
- */
-
-/* The locking scheme is rather straight forward:
- *
- * 1) Read-Copy Update protects the buckets of the central route hash.
- * 2) Only writers remove entries, and they hold the lock
- * as they look at rtable reference counts.
- * 3) Only readers acquire references to rtable entries,
- * they do so with atomic increments and with the
- * lock held.
- */
-
-struct rt_hash_bucket {
- struct rtable __rcu *chain;
-};
-
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
- defined(CONFIG_PROVE_LOCKING)
-/*
- * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
- * The size of this table is a power of two and depends on the number of CPUS.
- * (on lockdep we have a quite big spinlock_t, so keep the size down there)
- */
-#ifdef CONFIG_LOCKDEP
-# define RT_HASH_LOCK_SZ 256
-#else
-# if NR_CPUS >= 32
-# define RT_HASH_LOCK_SZ 4096
-# elif NR_CPUS >= 16
-# define RT_HASH_LOCK_SZ 2048
-# elif NR_CPUS >= 8
-# define RT_HASH_LOCK_SZ 1024
-# elif NR_CPUS >= 4
-# define RT_HASH_LOCK_SZ 512
-# else
-# define RT_HASH_LOCK_SZ 256
-# endif
-#endif
-
-static spinlock_t *rt_hash_locks;
-# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)]
-
-static __init void rt_hash_lock_init(void)
-{
- int i;
-
- rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ,
- GFP_KERNEL);
- if (!rt_hash_locks)
- panic("IP: failed to allocate rt_hash_locks\n");
-
- for (i = 0; i < RT_HASH_LOCK_SZ; i++)
- spin_lock_init(&rt_hash_locks[i]);
-}
-#else
-# define rt_hash_lock_addr(slot) NULL
-
-static inline void rt_hash_lock_init(void)
-{
-}
-#endif
-
-static struct rt_hash_bucket *rt_hash_table __read_mostly;
-static unsigned rt_hash_mask __read_mostly;
-static unsigned int rt_hash_log __read_mostly;
-
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)
-static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
- int genid)
-{
- return jhash_3words((__force u32)daddr, (__force u32)saddr,
- idx, genid)
- & rt_hash_mask;
-}
-
static inline int rt_genid(struct net *net)
{
return atomic_read(&net->ipv4.rt_genid);
}
#ifdef CONFIG_PROC_FS
-struct rt_cache_iter_state {
- struct seq_net_private p;
- int bucket;
- int genid;
-};
-
-static struct rtable *rt_cache_get_first(struct seq_file *seq)
-{
- struct rt_cache_iter_state *st = seq->private;
- struct rtable *r = NULL;
-
- for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {
- if (!rcu_dereference_raw(rt_hash_table[st->bucket].chain))
- continue;
- rcu_read_lock_bh();
- r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
- while (r) {
- if (dev_net(r->dst.dev) == seq_file_net(seq) &&
- r->rt_genid == st->genid)
- return r;
- r = rcu_dereference_bh(r->dst.rt_next);
- }
- rcu_read_unlock_bh();
- }
- return r;
-}
-
-static struct rtable *__rt_cache_get_next(struct seq_file *seq,
- struct rtable *r)
-{
- struct rt_cache_iter_state *st = seq->private;
-
- r = rcu_dereference_bh(r->dst.rt_next);
- while (!r) {
- rcu_read_unlock_bh();
- do {
- if (--st->bucket < 0)
- return NULL;
- } while (!rcu_dereference_raw(rt_hash_table[st->bucket].chain));
- rcu_read_lock_bh();
- r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
- }
- return r;
-}
-
-static struct rtable *rt_cache_get_next(struct seq_file *seq,
- struct rtable *r)
-{
- struct rt_cache_iter_state *st = seq->private;
- while ((r = __rt_cache_get_next(seq, r)) != NULL) {
- if (dev_net(r->dst.dev) != seq_file_net(seq))
- continue;
- if (r->rt_genid == st->genid)
- break;
- }
- return r;
-}
-
-static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
-{
- struct rtable *r = rt_cache_get_first(seq);
-
- if (r)
- while (pos && (r = rt_cache_get_next(seq, r)))
- --pos;
- return pos ? NULL : r;
-}
-
static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct rt_cache_iter_state *st = seq->private;
if (*pos)
- return rt_cache_get_idx(seq, *pos - 1);
- st->genid = rt_genid(seq_file_net(seq));
+ return NULL;
return SEQ_START_TOKEN;
}
static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct rtable *r;
-
- if (v == SEQ_START_TOKEN)
- r = rt_cache_get_first(seq);
- else
- r = rt_cache_get_next(seq, v);
++*pos;
- return r;
+ return NULL;
}
static void rt_cache_seq_stop(struct seq_file *seq, void *v)
{
- if (v && v != SEQ_START_TOKEN)
- rcu_read_unlock_bh();
}
static int rt_cache_seq_show(struct seq_file *seq, void *v)
@@ -409,29 +252,6 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
"Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t"
"Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t"
"HHUptod\tSpecDst");
- else {
- struct rtable *r = v;
- int len;
-
- seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
- "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
- r->dst.dev ? r->dst.dev->name : "*",
- (__force u32)r->rt_dst,
- (__force u32)r->rt_gateway,
- r->rt_flags, atomic_read(&r->dst.__refcnt),
- r->dst.__use, 0, (__force u32)r->rt_src,
- dst_metric_advmss(&r->dst) + 40,
- dst_metric(&r->dst, RTAX_WINDOW),
- (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) +
- dst_metric(&r->dst, RTAX_RTTVAR)),
- r->rt_tos,
- r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1,
- r->dst.hh ? (r->dst.hh->hh_output ==
- dev_queue_xmit) : 0,
- r->rt_spec_dst, &len);
-
- seq_printf(seq, "%*s\n", 127 - len, "");
- }
return 0;
}
@@ -444,8 +264,7 @@ static const struct seq_operations rt_cache_seq_ops = {
static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
- return seq_open_net(inode, file, &rt_cache_seq_ops,
- sizeof(struct rt_cache_iter_state));
+ return seq_open(file, &rt_cache_seq_ops);
}
static const struct file_operations rt_cache_seq_fops = {
@@ -453,7 +272,7 @@ static const struct file_operations rt_cache_seq_fops = {
.open = rt_cache_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_net,
+ .release = seq_release,
};
@@ -643,184 +462,12 @@ static inline int ip_rt_proc_init(void)
}
#endif /* CONFIG_PROC_FS */
-static inline void rt_free(struct rtable *rt)
-{
- call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
-}
-
-static inline void rt_drop(struct rtable *rt)
-{
- ip_rt_put(rt);
- call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
-}
-
-static inline int rt_fast_clean(struct rtable *rth)
-{
- /* Kill broadcast/multicast entries very aggresively, if they
- collide in hash table with more useful entries */
- return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) &&
- rt_is_input_route(rth) && rth->dst.rt_next;
-}
-
-static inline int rt_valuable(struct rtable *rth)
-{
- return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
- (rth->peer && rth->peer->pmtu_expires);
-}
-
-static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
-{
- unsigned long age;
- int ret = 0;
-
- if (atomic_read(&rth->dst.__refcnt))
- goto out;
-
- age = jiffies - rth->dst.lastuse;
- if ((age <= tmo1 && !rt_fast_clean(rth)) ||
- (age <= tmo2 && rt_valuable(rth)))
- goto out;
- ret = 1;
-out: return ret;
-}
-
-/* Bits of score are:
- * 31: very valuable
- * 30: not quite useless
- * 29..0: usage counter
- */
-static inline u32 rt_score(struct rtable *rt)
-{
- u32 score = jiffies - rt->dst.lastuse;
-
- score = ~score & ~(3<<30);
-
- if (rt_valuable(rt))
- score |= (1<<31);
-
- if (rt_is_output_route(rt) ||
- !(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL)))
- score |= (1<<30);
-
- return score;
-}
-
-static inline bool rt_caching(const struct net *net)
-{
- return net->ipv4.current_rt_cache_rebuild_count <=
- net->ipv4.sysctl_rt_cache_rebuild_count;
-}
-
-static inline bool compare_hash_inputs(const struct rtable *rt1,
- const struct rtable *rt2)
-{
- return ((((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) |
- ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) |
- (rt1->rt_iif ^ rt2->rt_iif)) == 0);
-}
-
-static inline int compare_keys(struct rtable *rt1, struct rtable *rt2)
-{
- return (((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) |
- ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) |
- (rt1->rt_mark ^ rt2->rt_mark) |
- (rt1->rt_tos ^ rt2->rt_tos) |
- (rt1->rt_oif ^ rt2->rt_oif) |
- (rt1->rt_iif ^ rt2->rt_iif)) == 0;
-}
-
-static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
-{
- return net_eq(dev_net(rt1->dst.dev), dev_net(rt2->dst.dev));
-}
-
static inline int rt_is_expired(struct rtable *rth)
{
return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
}
/*
- * Perform a full scan of hash table and free all entries.
- * Can be called by a softirq or a process.
- * In the later case, we want to be reschedule if necessary
- */
-static void rt_do_flush(struct net *net, int process_context)
-{
- unsigned int i;
- struct rtable *rth, *next;
-
- for (i = 0; i <= rt_hash_mask; i++) {
- struct rtable __rcu **pprev;
- struct rtable *list;
-
- if (process_context && need_resched())
- cond_resched();
- rth = rcu_dereference_raw(rt_hash_table[i].chain);
- if (!rth)
- continue;
-
- spin_lock_bh(rt_hash_lock_addr(i));
-
- list = NULL;
- pprev = &rt_hash_table[i].chain;
- rth = rcu_dereference_protected(*pprev,
- lockdep_is_held(rt_hash_lock_addr(i)));
-
- while (rth) {
- next = rcu_dereference_protected(rth->dst.rt_next,
- lockdep_is_held(rt_hash_lock_addr(i)));
-
- if (!net ||
- net_eq(dev_net(rth->dst.dev), net)) {
- rcu_assign_pointer(*pprev, next);
- rcu_assign_pointer(rth->dst.rt_next, list);
- list = rth;
- } else {
- pprev = &rth->dst.rt_next;
- }
- rth = next;
- }
-
- spin_unlock_bh(rt_hash_lock_addr(i));
-
- for (; list; list = next) {
- next = rcu_dereference_protected(list->dst.rt_next, 1);
- rt_free(list);
- }
- }
-}
-
-/*
- * While freeing expired entries, we compute average chain length
- * and standard deviation, using fixed-point arithmetic.
- * This to have an estimation of rt_chain_length_max
- * rt_chain_length_max = max(elasticity, AVG + 4*SD)
- * We use 3 bits for frational part, and 29 (or 61) for magnitude.
- */
-
-#define FRACT_BITS 3
-#define ONE (1UL << FRACT_BITS)
-
-/*
- * Given a hash chain and an item in this hash chain,
- * find if a previous entry has the same hash_inputs
- * (but differs on tos, mark or oif)
- * Returns 0 if an alias is found.
- * Returns ONE if rth has no alias before itself.
- */
-static int has_noalias(const struct rtable *head, const struct rtable *rth)
-{
- const struct rtable *aux = head;
-
- while (aux != rth) {
- if (compare_hash_inputs(aux, rth))
- return 0;
- aux = rcu_dereference_protected(aux->dst.rt_next, 1);
- }
- return ONE;
-}
-
-/*
* Perturbation of rt_genid by a small quantity [1..256]
* Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
* many times (2^24) without giving recent rt_genid.
@@ -841,364 +488,25 @@ static void rt_cache_invalidate(struct net *net)
void rt_cache_flush(struct net *net, int delay)
{
rt_cache_invalidate(net);
- if (delay >= 0)
- rt_do_flush(net, !in_softirq());
}
-/* Flush previous cache invalidated entries from the cache */
-void rt_cache_flush_batch(struct net *net)
+static struct rtable *rt_finalize(struct rtable *rt, struct sk_buff *skb)
{
- rt_do_flush(net, !in_softirq());
-}
-
-static void rt_emergency_hash_rebuild(struct net *net)
-{
- if (net_ratelimit())
- printk(KERN_WARNING "Route hash chain too long!\n");
- rt_cache_invalidate(net);
-}
-
-/*
- Short description of GC goals.
-
- We want to build algorithm, which will keep routing cache
- at some equilibrium point, when number of aged off entries
- is kept approximately equal to newly generated ones.
-
- Current expiration strength is variable "expire".
- We try to adjust it dynamically, so that if networking
- is idle expires is large enough to keep enough of warm entries,
- and when load increases it reduces to limit cache size.
- */
-
-static int rt_garbage_collect(struct dst_ops *ops)
-{
- static unsigned long expire = RT_GC_TIMEOUT;
- static unsigned long last_gc;
- static int rover;
- static int equilibrium;
- struct rtable *rth;
- struct rtable __rcu **rthp;
- unsigned long now = jiffies;
- int goal;
- int entries = dst_entries_get_fast(&ipv4_dst_ops);
-
- /*
- * Garbage collection is pretty expensive,
- * do not make it too frequently.
- */
-
- RT_CACHE_STAT_INC(gc_total);
-
- if (now - last_gc < ip_rt_gc_min_interval &&
- entries < ip_rt_max_size) {
- RT_CACHE_STAT_INC(gc_ignored);
- goto out;
- }
-
- entries = dst_entries_get_slow(&ipv4_dst_ops);
- /* Calculate number of entries, which we want to expire now. */
- goal = entries - (ip_rt_gc_elasticity << rt_hash_log);
- if (goal <= 0) {
- if (equilibrium < ipv4_dst_ops.gc_thresh)
- equilibrium = ipv4_dst_ops.gc_thresh;
- goal = entries - equilibrium;
- if (goal > 0) {
- equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1);
- goal = entries - equilibrium;
- }
- } else {
- /* We are in dangerous area. Try to reduce cache really
- * aggressively.
- */
- goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1);
- equilibrium = entries - goal;
- }
-
- if (now - last_gc >= ip_rt_gc_min_interval)
- last_gc = now;
-
- if (goal <= 0) {
- equilibrium += goal;
- goto work_done;
- }
-
- do {
- int i, k;
-
- for (i = rt_hash_mask, k = rover; i >= 0; i--) {
- unsigned long tmo = expire;
-
- k = (k + 1) & rt_hash_mask;
- rthp = &rt_hash_table[k].chain;
- spin_lock_bh(rt_hash_lock_addr(k));
- while ((rth = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(k)))) != NULL) {
- if (!rt_is_expired(rth) &&
- !rt_may_expire(rth, tmo, expire)) {
- tmo >>= 1;
- rthp = &rth->dst.rt_next;
- continue;
- }
- *rthp = rth->dst.rt_next;
- rt_free(rth);
- goal--;
- }
- spin_unlock_bh(rt_hash_lock_addr(k));
- if (goal <= 0)
- break;
- }
- rover = k;
-
- if (goal <= 0)
- goto work_done;
-
- /* Goal is not achieved. We stop process if:
-
- - if expire reduced to zero. Otherwise, expire is halfed.
- - if table is not full.
- - if we are called from interrupt.
- - jiffies check is just fallback/debug loop breaker.
- We will not spin here for long time in any case.
- */
-
- RT_CACHE_STAT_INC(gc_goal_miss);
-
- if (expire == 0)
- break;
-
- expire >>= 1;
-#if RT_CACHE_DEBUG >= 2
- printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire,
- dst_entries_get_fast(&ipv4_dst_ops), goal, i);
-#endif
-
- if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
- goto out;
- } while (!in_softirq() && time_before_eq(jiffies, now));
-
- if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
- goto out;
- if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size)
- goto out;
- if (net_ratelimit())
- printk(KERN_WARNING "dst cache overflow\n");
- RT_CACHE_STAT_INC(gc_dst_overflow);
- return 1;
-
-work_done:
- expire += ip_rt_gc_min_interval;
- if (expire > ip_rt_gc_timeout ||
- dst_entries_get_fast(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh ||
- dst_entries_get_slow(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh)
- expire = ip_rt_gc_timeout;
-#if RT_CACHE_DEBUG >= 2
- printk(KERN_DEBUG "expire++ %u %d %d %d\n", expire,
- dst_entries_get_fast(&ipv4_dst_ops), goal, rover);
-#endif
-out: return 0;
-}
-
-/*
- * Returns number of entries in a hash chain that have different hash_inputs
- */
-static int slow_chain_length(const struct rtable *head)
-{
- int length = 0;
- const struct rtable *rth = head;
-
- while (rth) {
- length += has_noalias(head, rth);
- rth = rcu_dereference_protected(rth->dst.rt_next, 1);
- }
- return length >> FRACT_BITS;
-}
-
-static struct rtable *rt_intern_hash(unsigned hash, struct rtable *rt,
- struct sk_buff *skb, int ifindex)
-{
- struct rtable *rth, *cand;
- struct rtable __rcu **rthp, **candp;
- unsigned long now;
- u32 min_score;
- int chain_length;
- int attempts = !in_softirq();
-
-restart:
- chain_length = 0;
- min_score = ~(u32)0;
- cand = NULL;
- candp = NULL;
- now = jiffies;
-
- if (!rt_caching(dev_net(rt->dst.dev))) {
- /*
- * If we're not caching, just tell the caller we
- * were successful and don't touch the route. The
- * caller hold the sole reference to the cache entry, and
- * it will be released when the caller is done with it.
- * If we drop it here, the callers have no way to resolve routes
- * when we're not caching. Instead, just point *rp at rt, so
- * the caller gets a single use out of the route
- * Note that we do rt_free on this new route entry, so that
- * once its refcount hits zero, we are still able to reap it
- * (Thanks Alexey)
- * Note: To avoid expensive rcu stuff for this uncached dst,
- * we set DST_NOCACHE so that dst_release() can free dst without
- * waiting a grace period.
- */
-
- rt->dst.flags |= DST_NOCACHE;
- if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
- int err = arp_bind_neighbour(&rt->dst);
- if (err) {
- if (net_ratelimit())
- printk(KERN_WARNING
- "Neighbour table failure & not caching routes.\n");
- ip_rt_put(rt);
- return ERR_PTR(err);
- }
- }
-
- goto skip_hashing;
- }
-
- rthp = &rt_hash_table[hash].chain;
-
- spin_lock_bh(rt_hash_lock_addr(hash));
- while ((rth = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
- if (rt_is_expired(rth)) {
- *rthp = rth->dst.rt_next;
- rt_free(rth);
- continue;
- }
- if (compare_keys(rth, rt) && compare_netns(rth, rt)) {
- /* Put it first */
- *rthp = rth->dst.rt_next;
- /*
- * Since lookup is lockfree, the deletion
- * must be visible to another weakly ordered CPU before
- * the insertion at the start of the hash chain.
- */
- rcu_assign_pointer(rth->dst.rt_next,
- rt_hash_table[hash].chain);
- /*
- * Since lookup is lockfree, the update writes
- * must be ordered for consistency on SMP.
- */
- rcu_assign_pointer(rt_hash_table[hash].chain, rth);
-
- dst_use(&rth->dst, now);
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- rt_drop(rt);
- if (skb)
- skb_dst_set(skb, &rth->dst);
- return rth;
- }
-
- if (!atomic_read(&rth->dst.__refcnt)) {
- u32 score = rt_score(rth);
-
- if (score <= min_score) {
- cand = rth;
- candp = rthp;
- min_score = score;
- }
- }
-
- chain_length++;
-
- rthp = &rth->dst.rt_next;
- }
-
- if (cand) {
- /* ip_rt_gc_elasticity used to be average length of chain
- * length, when exceeded gc becomes really aggressive.
- *
- * The second limit is less certain. At the moment it allows
- * only 2 entries per bucket. We will see.
- */
- if (chain_length > ip_rt_gc_elasticity) {
- *candp = cand->dst.rt_next;
- rt_free(cand);
- }
- } else {
- if (chain_length > rt_chain_length_max &&
- slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) {
- struct net *net = dev_net(rt->dst.dev);
- int num = ++net->ipv4.current_rt_cache_rebuild_count;
- if (!rt_caching(net)) {
- printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n",
- rt->dst.dev->name, num);
- }
- rt_emergency_hash_rebuild(net);
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
- ifindex, rt_genid(net));
- goto restart;
- }
- }
-
- /* Try to bind route to arp only if it is output
- route or unicast forwarding path.
+ /* To avoid expensive rcu stuff for this uncached dst, we set
+ * DST_NOCACHE so that dst_release() can free dst without
+ * waiting a grace period.
*/
+ rt->dst.flags |= DST_NOCACHE;
if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
int err = arp_bind_neighbour(&rt->dst);
if (err) {
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- if (err != -ENOBUFS) {
- rt_drop(rt);
- return ERR_PTR(err);
- }
-
- /* Neighbour tables are full and nothing
- can be released. Try to shrink route cache,
- it is most likely it holds some neighbour records.
- */
- if (attempts-- > 0) {
- int saved_elasticity = ip_rt_gc_elasticity;
- int saved_int = ip_rt_gc_min_interval;
- ip_rt_gc_elasticity = 1;
- ip_rt_gc_min_interval = 0;
- rt_garbage_collect(&ipv4_dst_ops);
- ip_rt_gc_min_interval = saved_int;
- ip_rt_gc_elasticity = saved_elasticity;
- goto restart;
- }
-
if (net_ratelimit())
- printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
- rt_drop(rt);
- return ERR_PTR(-ENOBUFS);
+ printk(KERN_WARNING
+ "Neighbour table failure & not caching routes.\n");
+ ip_rt_put(rt);
+ return ERR_PTR(err);
}
}
-
- rt->dst.rt_next = rt_hash_table[hash].chain;
-
-#if RT_CACHE_DEBUG >= 2
- if (rt->dst.rt_next) {
- struct rtable *trt;
- printk(KERN_DEBUG "rt_cache @%02x: %pI4",
- hash, &rt->rt_dst);
- for (trt = rt->dst.rt_next; trt; trt = trt->dst.rt_next)
- printk(" . %pI4", &trt->rt_dst);
- printk("\n");
- }
-#endif
- /*
- * Since lookup is lockfree, we must make sure
- * previous writes to rt are committed to memory
- * before making rt visible to other CPUS.
- */
- rcu_assign_pointer(rt_hash_table[hash].chain, rt);
-
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
-skip_hashing:
if (skb)
skb_dst_set(skb, &rt->dst);
return rt;
@@ -1266,26 +574,6 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
}
EXPORT_SYMBOL(__ip_select_ident);
-static void rt_del(unsigned hash, struct rtable *rt)
-{
- struct rtable __rcu **rthp;
- struct rtable *aux;
-
- rthp = &rt_hash_table[hash].chain;
- spin_lock_bh(rt_hash_lock_addr(hash));
- ip_rt_put(rt);
- while ((aux = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
- if (aux == rt || rt_is_expired(aux)) {
- *rthp = aux->dst.rt_next;
- rt_free(aux);
- continue;
- }
- rthp = &aux->dst.rt_next;
- }
- spin_unlock_bh(rt_hash_lock_addr(hash));
-}
-
/* called in rcu_read_lock() section */
void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
__be32 saddr, struct net_device *dev)
@@ -1344,14 +632,11 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
ip_rt_put(rt);
ret = NULL;
} else if (rt->rt_flags & RTCF_REDIRECTED) {
- unsigned hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
- rt->rt_oif,
- rt_genid(dev_net(dst->dev)));
#if RT_CACHE_DEBUG >= 1
printk(KERN_DEBUG "ipv4_negative_advice: redirect to %pI4/%02x dropped\n",
- &rt->rt_dst, rt->rt_tos);
+ &rt->rt_dst, rt->rt_tos);
#endif
- rt_del(hash, rt);
+ ip_rt_put(rt);
ret = NULL;
} else if (rt->peer &&
rt->peer->pmtu_expires &&
@@ -1850,7 +1135,6 @@ static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm)
static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, int our)
{
- unsigned int hash;
struct rtable *rth;
__be32 spec_dst;
struct in_device *in_dev = __in_dev_get_rcu(dev);
@@ -1912,8 +1196,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
#endif
RT_CACHE_STAT_INC(in_slow_mc);
- hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
- rth = rt_intern_hash(hash, rth, skb, dev->ifindex);
+ rth = rt_finalize(rth, skb);
err = 0;
if (IS_ERR(rth))
err = PTR_ERR(rth);
@@ -2056,7 +1339,6 @@ static int ip_mkroute_input(struct sk_buff *skb,
{
struct rtable* rth = NULL;
int err;
- unsigned hash;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi && res->fi->fib_nhs > 1)
@@ -2068,10 +1350,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
if (err)
return err;
- /* put it into the cache */
- hash = rt_hash(daddr, saddr, fl4->flowi4_iif,
- rt_genid(dev_net(rth->dst.dev)));
- rth = rt_intern_hash(hash, rth, skb, fl4->flowi4_iif);
+ rth = rt_finalize(rth, skb);
if (IS_ERR(rth))
return PTR_ERR(rth);
return 0;
@@ -2097,7 +1376,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
unsigned flags = 0;
u32 itag = 0;
struct rtable * rth;
- unsigned hash;
__be32 spec_dst;
int err = -EINVAL;
struct net * net = dev_net(dev);
@@ -2218,8 +1496,7 @@ local_input:
rth->rt_flags &= ~RTCF_LOCAL;
}
rth->rt_type = res.type;
- hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net));
- rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif);
+ rth = rt_finalize(rth, skb);
err = 0;
if (IS_ERR(rth))
err = PTR_ERR(rth);
@@ -2266,47 +1543,10 @@ martian_source_keep_err:
int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, bool noref)
{
- struct rtable * rth;
- unsigned hash;
- int iif = dev->ifindex;
- struct net *net;
int res;
- net = dev_net(dev);
-
rcu_read_lock();
- if (!rt_caching(net))
- goto skip_cache;
-
- tos &= IPTOS_RT_MASK;
- hash = rt_hash(daddr, saddr, iif, rt_genid(net));
-
- for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->dst.rt_next)) {
- if ((((__force u32)rth->rt_key_dst ^ (__force u32)daddr) |
- ((__force u32)rth->rt_key_src ^ (__force u32)saddr) |
- (rth->rt_iif ^ iif) |
- rth->rt_oif |
- (rth->rt_tos ^ tos)) == 0 &&
- rth->rt_mark == skb->mark &&
- net_eq(dev_net(rth->dst.dev), net) &&
- !rt_is_expired(rth)) {
- if (noref) {
- dst_use_noref(&rth->dst, jiffies);
- skb_dst_set_noref(skb, &rth->dst);
- } else {
- dst_use(&rth->dst, jiffies);
- skb_dst_set(skb, &rth->dst);
- }
- RT_CACHE_STAT_INC(in_hit);
- rcu_read_unlock();
- return 0;
- }
- RT_CACHE_STAT_INC(in_hlist_search);
- }
-
-skip_cache:
/* Multicast recognition logic is moved from route cache to here.
The problem was that too many Ethernet cards have broken/missing
hardware multicast filters :-( As result the host on multicasting
@@ -2448,11 +1688,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
/*
* Major route resolver routine.
- * called with rcu_read_lock();
*/
-static struct rtable *ip_route_output_slow(struct net *net,
- const struct flowi4 *oldflp4)
+struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *oldflp4)
{
u32 tos = RT_FL_TOS(oldflp4);
struct flowi4 fl4;
@@ -2629,53 +1867,13 @@ static struct rtable *ip_route_output_slow(struct net *net,
make_route:
rth = __mkroute_output(&res, &fl4, oldflp4, dev_out, flags);
- if (!IS_ERR(rth)) {
- unsigned int hash;
-
- hash = rt_hash(oldflp4->daddr, oldflp4->saddr, oldflp4->flowi4_oif,
- rt_genid(dev_net(dev_out)));
- rth = rt_intern_hash(hash, rth, NULL, oldflp4->flowi4_oif);
- }
+ if (!IS_ERR(rth))
+ rth = rt_finalize(rth, NULL);
out:
rcu_read_unlock();
return rth;
}
-
-struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *flp4)
-{
- struct rtable *rth;
- unsigned int hash;
-
- if (!rt_caching(net))
- goto slow_output;
-
- hash = rt_hash(flp4->daddr, flp4->saddr, flp4->flowi4_oif, rt_genid(net));
-
- rcu_read_lock_bh();
- for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference_bh(rth->dst.rt_next)) {
- if (rth->rt_key_dst == flp4->daddr &&
- rth->rt_key_src == flp4->saddr &&
- rt_is_output_route(rth) &&
- rth->rt_oif == flp4->flowi4_oif &&
- rth->rt_mark == flp4->flowi4_mark &&
- !((rth->rt_tos ^ flp4->flowi4_tos) &
- (IPTOS_RT_MASK | RTO_ONLINK)) &&
- net_eq(dev_net(rth->dst.dev), net) &&
- !rt_is_expired(rth)) {
- dst_use(&rth->dst, jiffies);
- RT_CACHE_STAT_INC(out_hit);
- rcu_read_unlock_bh();
- return rth;
- }
- RT_CACHE_STAT_INC(out_hlist_search);
- }
- rcu_read_unlock_bh();
-
-slow_output:
- return ip_route_output_slow(net, flp4);
-}
EXPORT_SYMBOL_GPL(__ip_route_output_key);
static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
@@ -2968,43 +2166,6 @@ errout_free:
int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct rtable *rt;
- int h, s_h;
- int idx, s_idx;
- struct net *net;
-
- net = sock_net(skb->sk);
-
- s_h = cb->args[0];
- if (s_h < 0)
- s_h = 0;
- s_idx = idx = cb->args[1];
- for (h = s_h; h <= rt_hash_mask; h++, s_idx = 0) {
- if (!rt_hash_table[h].chain)
- continue;
- rcu_read_lock_bh();
- for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt;
- rt = rcu_dereference_bh(rt->dst.rt_next), idx++) {
- if (!net_eq(dev_net(rt->dst.dev), net) || idx < s_idx)
- continue;
- if (rt_is_expired(rt))
- continue;
- skb_dst_set_noref(skb, &rt->dst);
- if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid,
- cb->nlh->nlmsg_seq, RTM_NEWROUTE,
- 1, NLM_F_MULTI) <= 0) {
- skb_dst_drop(skb);
- rcu_read_unlock_bh();
- goto done;
- }
- skb_dst_drop(skb);
- }
- rcu_read_unlock_bh();
- }
-
-done:
- cb->args[0] = h;
- cb->args[1] = idx;
return skb->len;
}
@@ -3239,16 +2400,6 @@ static __net_initdata struct pernet_operations rt_genid_ops = {
struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
#endif /* CONFIG_IP_ROUTE_CLASSID */
-static __initdata unsigned long rhash_entries;
-static int __init set_rhash_entries(char *str)
-{
- if (!str)
- return 0;
- rhash_entries = simple_strtoul(str, &str, 0);
- return 1;
-}
-__setup("rhash_entries=", set_rhash_entries);
-
int __init ip_rt_init(void)
{
int rc = 0;
@@ -3271,21 +2422,8 @@ int __init ip_rt_init(void)
if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0)
panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n");
- rt_hash_table = (struct rt_hash_bucket *)
- alloc_large_system_hash("IP route cache",
- sizeof(struct rt_hash_bucket),
- rhash_entries,
- (totalram_pages >= 128 * 1024) ?
- 15 : 17,
- 0,
- &rt_hash_log,
- &rt_hash_mask,
- rhash_entries ? 0 : 512 * 1024);
- memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
- rt_hash_lock_init();
-
- ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1);
- ip_rt_max_size = (rt_hash_mask + 1) * 16;
+ ipv4_dst_ops.gc_thresh = ~0;
+ ip_rt_max_size = INT_MAX;
devinet_init();
ip_fib_init();
--
1.7.4.3
^ permalink raw reply related
* [PATCH v5 0/7] rtcache removal respin
From: David Miller @ 2011-04-15 22:39 UTC (permalink / raw)
To: netdev
This is just a respin of the routing cache removal patches,
to deal with conflicts that have arisen since v4.
I'm leaving out the netlink patch from now on because that
change is totally unrelated to this work.
No functional changes are present since the last respin.
^ permalink raw reply
* Re: Feature request: "inverted" ping -a (beep on failure)
From: Martin Topholm @ 2011-04-15 21:57 UTC (permalink / raw)
To: Christian Boltz; +Cc: netdev
In-Reply-To: <201104152135.33171@tux.boltz.de.vu>
On Fri, 15 Apr 2011, Christian Boltz wrote:
> I'd like to have the exact opposite of it: beep when pinging fails.
I too have missed this feature (from the BSDs ping). Also I needed
adhoc tracking of multiple hosts. So I experimented with libevent2 and
some code from the BSD ping...
You can see the result here http://hoth.dk/xping/screenshot.jpeg
or http://hoth.dk/xping/xping-20110415.tar.gz .
> I understand that this is slightly difficult because "ping success" is
> easier to detect (incoming package) than "ping failure" (no incoming
> package or firewall reject)
I used the transmit interval for timeout. There's propably a lot of
corner cases I haven't thought about, but it works fairly well.
Regards, Martin
^ permalink raw reply
* Re: The bonding driver should notify userspace of MAC address change
From: Jay Vosburgh @ 2011-04-15 21:45 UTC (permalink / raw)
To: =?UTF-8?B?Tmljb2xhcyBkZSBQZXNsb8O8YW4=?=
Cc: =?UTF-8?B?TWljaGHFgiBHw7Nybnk=?=, netdev, roy, Andy Gospodarek
In-Reply-To: <4DA89ADC.7040808@gmail.com>
Nicolas de Pesloüan <nicolas.2p.debian@gmail.com> wrote:
>Agreed.
>
>> Is there some race window there between the register and the
>> netif_carrier_off?
>
>It might be that dhcpd does not wait for link to be up before starting to send DHCP requests.
It looks like it's not related to carrier state at all:
#212: dhcpcd requires restart to get an IP address for bonded interface
-----------------------+-----------------
Reporter: mgorny@… | Owner: roy
Type: defect | Status: new
Priority: major | Milestone:
Component: dhcpcd | Version: 5.1
Resolution: | Keywords:
-----------------------+-----------------
Comment (by roy):
Sorry, the above isn't too clear.
dhcpcd will read the hardware address when the interface is marked IFF_UP
or when given RTM_NEWLINK with ifi->ifi_change = ~0U, the latter being
sent by some drivers to tell userland that an interface characteristic has
changed - like say a hardware address - if the driver supports such a
change whilst still up. Normal behaviour is to mark device as DOWN before
changing hardware address. bonding does this whilst marked UP, hence this
issue.
carrier going up / down is just that, it's not a signal to re-read the
interface characteristics.
Now this confuses me again; I thought that running the dhcp
client (dhcpcd) over bonding has worked for years, although I've not
personally tried it recently. Perhaps it varies by distro. In any
event, this behavior of bonding (setting the bond's MAC without a
down/up flip) has never been different in my memory.
I've not yet dug down to see if NETDEV_CHANGEADDR will result in
an RTM_NEWLINK to user space. At first glance it doesn't look like it.
When bonding goes link up, however, I think linkwatch_do_dev
will issue an RTM_NEWLINK (via a call to netdev_state_change), or,
alternately, dev_change_flags will do it at IFF_UP time.
-J
---
-Jay Vosburgh, IBM Linux Technology Center, fubar@us.ibm.com
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox