The advertised MSS depends on the first hop route MTU, but will
never be lower than this setting.
-rt_cache_rebuild_count - INTEGER
- The per net-namespace route cache emergency rebuild threshold.
- Any net-namespace having its route cache rebuilt due to
- a hash bucket chain being too long more than this many times
- will have its route caching disabled
-
IP Fragmentation:
ipfrag_high_thresh - INTEGER
{
struct fritzcard *fc = bch->hw;
struct hdlc_hw *hdlc;
- int count, fs, cnt = 0, idx, fillempty = 0;
+ int count, fs, cnt = 0, idx;
+ bool fillempty = false;
u8 *p;
u32 *ptr, val, addr;
return;
count = fs;
p = bch->fill;
- fillempty = 1;
+ fillempty = true;
} else {
count = bch->tx_skb->len - bch->tx_idx;
if (count <= 0)
hdlc->ctrl.sr.cmd |= HDLC_CMD_XME;
}
ptr = (u32 *)p;
- if (fillempty) {
+ if (!fillempty) {
pr_debug("%s.B%d: %d/%d/%d", fc->name, bch->nr, count,
bch->tx_idx, bch->tx_skb->len);
bch->tx_idx += count;
struct bnx2x_prev_path_list *tmp_list;
int rc;
- tmp_list = (struct bnx2x_prev_path_list *)
- kmalloc(sizeof(struct bnx2x_prev_path_list), GFP_KERNEL);
+ tmp_list = kmalloc(sizeof(struct bnx2x_prev_path_list), GFP_KERNEL);
if (!tmp_list) {
BNX2X_ERR("Failed to allocate 'bnx2x_prev_path_list'\n");
return -ENOMEM;
#define DRV_MODULE_NAME "tg3"
#define TG3_MAJ_NUM 3
-#define TG3_MIN_NUM 123
+#define TG3_MIN_NUM 124
#define DRV_MODULE_VERSION \
__stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM)
#define DRV_MODULE_RELDATE "March 21, 2012"
else
bit = 1 << tp->pci_fn;
break;
+ case TG3_APE_LOCK_PHY0:
+ case TG3_APE_LOCK_PHY1:
+ case TG3_APE_LOCK_PHY2:
+ case TG3_APE_LOCK_PHY3:
+ bit = APE_LOCK_REQ_DRIVER;
+ break;
default:
return -EINVAL;
}
else
bit = 1 << tp->pci_fn;
break;
+ case TG3_APE_LOCK_PHY0:
+ case TG3_APE_LOCK_PHY1:
+ case TG3_APE_LOCK_PHY2:
+ case TG3_APE_LOCK_PHY3:
+ bit = APE_LOCK_GRANT_DRIVER;
+ break;
default:
return;
}
udelay(80);
}
+ tg3_ape_lock(tp, tp->phy_ape_lock);
+
*val = 0x0;
frame_val = ((tp->phy_addr << MI_COM_PHY_ADDR_SHIFT) &
udelay(80);
}
+ tg3_ape_unlock(tp, tp->phy_ape_lock);
+
return ret;
}
udelay(80);
}
+ tg3_ape_lock(tp, tp->phy_ape_lock);
+
frame_val = ((tp->phy_addr << MI_COM_PHY_ADDR_SHIFT) &
MI_COM_PHY_ADDR_MASK);
frame_val |= ((reg << MI_COM_REG_ADDR_SHIFT) &
udelay(80);
}
+ tg3_ape_unlock(tp, tp->phy_ape_lock);
+
return ret;
}
GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57780 ||
tg3_flag(tp, 57765_PLUS)) {
val = tr32(TG3_RDMA_RSRVCTRL_REG);
- if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720) {
+ if (tp->pci_chip_rev_id == CHIPREV_ID_5719_A0) {
val &= ~(TG3_RDMA_RSRVCTRL_TXMRGN_MASK |
TG3_RDMA_RSRVCTRL_FIFO_LWM_MASK |
TG3_RDMA_RSRVCTRL_FIFO_HWM_MASK);
tw32_f(RDMAC_MODE, rdmac_mode);
udelay(40);
+ if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) {
+ for (i = 0; i < TG3_NUM_RDMA_CHANNELS; i++) {
+ if (tr32(TG3_RDMA_LENGTH + (i << 2)) > TG3_MAX_MTU(tp))
+ break;
+ }
+ if (i < TG3_NUM_RDMA_CHANNELS) {
+ val = tr32(TG3_LSO_RD_DMA_CRPTEN_CTRL);
+ val |= TG3_LSO_RD_DMA_TX_LENGTH_WA;
+ tw32(TG3_LSO_RD_DMA_CRPTEN_CTRL, val);
+ tg3_flag_set(tp, 5719_RDMA_BUG);
+ }
+ }
+
tw32(RCVDCC_MODE, RCVDCC_MODE_ENABLE | RCVDCC_MODE_ATTN_ENABLE);
if (!tg3_flag(tp, 5705_PLUS))
tw32(MBFREE_MODE, MBFREE_MODE_ENABLE);
TG3_STAT_ADD32(&sp->tx_ucast_packets, MAC_TX_STATS_UCAST);
TG3_STAT_ADD32(&sp->tx_mcast_packets, MAC_TX_STATS_MCAST);
TG3_STAT_ADD32(&sp->tx_bcast_packets, MAC_TX_STATS_BCAST);
+ if (unlikely(tg3_flag(tp, 5719_RDMA_BUG) &&
+ (sp->tx_ucast_packets.low + sp->tx_mcast_packets.low +
+ sp->tx_bcast_packets.low) > TG3_NUM_RDMA_CHANNELS)) {
+ u32 val;
+
+ val = tr32(TG3_LSO_RD_DMA_CRPTEN_CTRL);
+ val &= ~TG3_LSO_RD_DMA_TX_LENGTH_WA;
+ tw32(TG3_LSO_RD_DMA_CRPTEN_CTRL, val);
+ tg3_flag_clear(tp, 5719_RDMA_BUG);
+ }
TG3_STAT_ADD32(&sp->rx_octets, MAC_RX_STATS_OCTETS);
TG3_STAT_ADD32(&sp->rx_fragments, MAC_RX_STATS_FRAGMENTS);
{
struct tg3 *tp = netdev_priv(dev);
- if (!tp->hw_stats)
+ spin_lock_bh(&tp->lock);
+ if (!tp->hw_stats) {
+ spin_unlock_bh(&tp->lock);
return &tp->net_stats_prev;
+ }
- spin_lock_bh(&tp->lock);
tg3_get_nstats(tp, stats);
spin_unlock_bh(&tp->lock);
tg3_flag_set(tp, PAUSE_AUTONEG);
tp->link_config.flowctrl = FLOW_CTRL_TX | FLOW_CTRL_RX;
+ if (tg3_flag(tp, ENABLE_APE)) {
+ switch (tp->pci_fn) {
+ case 0:
+ tp->phy_ape_lock = TG3_APE_LOCK_PHY0;
+ break;
+ case 1:
+ tp->phy_ape_lock = TG3_APE_LOCK_PHY1;
+ break;
+ case 2:
+ tp->phy_ape_lock = TG3_APE_LOCK_PHY2;
+ break;
+ case 3:
+ tp->phy_ape_lock = TG3_APE_LOCK_PHY3;
+ break;
+ }
+ }
+
if (tg3_flag(tp, USE_PHYLIB))
return tg3_phy_init(tp);
#define TG3_LSO_RD_DMA_CRPTEN_CTRL 0x00004910
#define TG3_LSO_RD_DMA_CRPTEN_CTRL_BLEN_BD_4K 0x00030000
#define TG3_LSO_RD_DMA_CRPTEN_CTRL_BLEN_LSO_4K 0x000c0000
-/* 0x4914 --> 0x4c00 unused */
+#define TG3_LSO_RD_DMA_TX_LENGTH_WA 0x02000000
+/* 0x4914 --> 0x4be0 unused */
+
+#define TG3_NUM_RDMA_CHANNELS 4
+#define TG3_RDMA_LENGTH 0x00004be0
/* Write DMA control registers */
#define WDMAC_MODE 0x00004c00
TG3_FLAG_L1PLLPD_EN,
TG3_FLAG_APE_HAS_NCSI,
TG3_FLAG_4K_FIFO_LIMIT,
+ TG3_FLAG_5719_RDMA_BUG,
TG3_FLAG_RESET_TASK_PENDING,
TG3_FLAG_5705_PLUS,
TG3_FLAG_IS_5788,
int old_link;
u8 phy_addr;
+ u8 phy_ape_lock;
/* PHY info */
u32 phy_id;
NETIF_F_HW_VLAN_TX | NETIF_F_RXCSUM;
ndev->features = ndev->hw_features |
NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER;
+ ndev->vlan_features = ndev->hw_features;
if (test_bit(QL_DMA64, &qdev->flags))
ndev->features |= NETIF_F_HIGHDMA;
int __init init_module(void)
{
dev_seeq = seeq8005_probe(-1);
- if (IS_ERR(dev_seeq))
- return PTR_ERR(dev_seeq);
- return 0;
+ return PTR_RET(dev_seeq);
}
void __exit cleanup_module(void)
int vnet_hdr_sz;
int ret;
- if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89)
+ if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89) {
if (copy_from_user(&ifr, argp, ifreq_len))
return -EFAULT;
-
+ } else {
+ memset(&ifr, 0, sizeof(ifr));
+ }
if (cmd == TUNGETFEATURES) {
/* Currently this just means: "what IFF flags are valid?".
* This is needed because we never checked for invalid flags on
return flags;
}
+static inline void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+
+ dst_hold(dst);
+ sk->sk_rx_dst = dst;
+ inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+}
+
#endif /* _INET_SOCK_H */
#include <linux/rcupdate.h>
#include <net/fib_rules.h>
#include <net/inetpeer.h>
+#include <linux/percpu.h>
struct fib_config {
u8 fc_dst_len;
u32 fnhe_pmtu;
__be32 fnhe_gw;
unsigned long fnhe_expires;
+ struct rtable __rcu *fnhe_rth;
unsigned long fnhe_stamp;
};
__be32 nh_gw;
__be32 nh_saddr;
int nh_saddr_genid;
- struct rtable *nh_rth_output;
- struct rtable *nh_rth_input;
+ struct rtable __rcu * __percpu *nh_pcpu_rth_output;
+ struct rtable __rcu *nh_rth_input;
struct fnhe_hash_bucket *nh_exceptions;
};
int sysctl_icmp_ratelimit;
int sysctl_icmp_ratemask;
int sysctl_icmp_errors_use_inbound_ifaddr;
- int sysctl_rt_cache_rebuild_count;
- int current_rt_cache_rebuild_count;
unsigned int sysctl_ping_group_range[2];
long sysctl_tcp_mem[3];
/* Miscellaneous cached information */
u32 rt_pmtu;
+
+ struct list_head rt_uncached;
};
static inline bool rt_is_input_route(const struct rtable *rt)
struct in_device;
extern int ip_rt_init(void);
extern void rt_cache_flush(struct net *net, int how);
+extern void rt_flush_dev(struct net_device *dev);
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);
};
#define BRPORT_ATTR(_name,_mode,_show,_store) \
-struct brport_attribute brport_attr_##_name = { \
+const struct brport_attribute brport_attr_##_name = { \
.attr = {.name = __stringify(_name), \
.mode = _mode }, \
.show = _show, \
store_multicast_router);
#endif
-static struct brport_attribute *brport_attrs[] = {
+static const struct brport_attribute *brport_attrs[] = {
&brport_attr_path_cost,
&brport_attr_priority,
&brport_attr_port_id,
int br_sysfs_addif(struct net_bridge_port *p)
{
struct net_bridge *br = p->br;
- struct brport_attribute **a;
+ const struct brport_attribute **a;
int err;
err = sysfs_create_link(&p->kobj, &br->dev->dev.kobj,
.rta_id = id,
};
- if (expires)
- ci.rta_expires = jiffies_to_clock_t(expires);
+ if (expires) {
+ unsigned long clock;
+ clock = jiffies_to_clock_t(abs(expires));
+ clock = min_t(unsigned long, clock, INT_MAX);
+ ci.rta_expires = (expires > 0) ? clock : -clock;
+ }
return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci);
}
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
if (event == NETDEV_UNREGISTER) {
fib_disable_ip(dev, 2, -1);
+ rt_flush_dev(dev);
return NOTIFY_DONE;
}
},
};
+static void rt_fibinfo_free(struct rtable __rcu **rtp)
+{
+ struct rtable *rt = rcu_dereference_protected(*rtp, 1);
+
+ if (!rt)
+ return;
+
+ /* Not even needed : RCU_INIT_POINTER(*rtp, NULL);
+ * because we waited an RCU grace period before calling
+ * free_fib_info_rcu()
+ */
+
+ dst_free(&rt->dst);
+}
+
static void free_nh_exceptions(struct fib_nh *nh)
{
struct fnhe_hash_bucket *hash = nh->nh_exceptions;
struct fib_nh_exception *next;
next = rcu_dereference_protected(fnhe->fnhe_next, 1);
+
+ rt_fibinfo_free(&fnhe->fnhe_rth);
+
kfree(fnhe);
fnhe = next;
kfree(hash);
}
+static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
+{
+ int cpu;
+
+ if (!rtp)
+ return;
+
+ for_each_possible_cpu(cpu) {
+ struct rtable *rt;
+
+ rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1);
+ if (rt)
+ dst_free(&rt->dst);
+ }
+ free_percpu(rtp);
+}
+
/* Release a nexthop info record */
static void free_fib_info_rcu(struct rcu_head *head)
{
dev_put(nexthop_nh->nh_dev);
if (nexthop_nh->nh_exceptions)
free_nh_exceptions(nexthop_nh);
- if (nexthop_nh->nh_rth_output)
- dst_free(&nexthop_nh->nh_rth_output->dst);
- if (nexthop_nh->nh_rth_input)
- dst_free(&nexthop_nh->nh_rth_input->dst);
+ rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
+ rt_fibinfo_free(&nexthop_nh->nh_rth_input);
} endfor_nexthops(fi);
release_net(fi->fib_net);
fi->fib_nhs = nhs;
change_nexthops(fi) {
nexthop_nh->nh_parent = fi;
+ nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
} endfor_nexthops(fi)
if (cfg->fc_mx) {
#endif
};
-static void put_child(struct trie *t, struct tnode *tn, int i, struct rt_trie_node *n);
static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n,
int wasfull);
static struct rt_trie_node *resize(struct trie *t, struct tnode *tn);
}
pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode),
- sizeof(struct rt_trie_node) << bits);
+ sizeof(struct rt_trie_node *) << bits);
return tn;
}
return ((struct tnode *) n)->pos == tn->pos + tn->bits;
}
-static inline void put_child(struct trie *t, struct tnode *tn, int i,
+static inline void put_child(struct tnode *tn, int i,
struct rt_trie_node *n)
{
tnode_put_child_reorg(tn, i, n, -1);
goto nomem;
}
- put_child(t, tn, 2*i, (struct rt_trie_node *) left);
- put_child(t, tn, 2*i+1, (struct rt_trie_node *) right);
+ put_child(tn, 2*i, (struct rt_trie_node *) left);
+ put_child(tn, 2*i+1, (struct rt_trie_node *) right);
}
}
if (tkey_extract_bits(node->key,
oldtnode->pos + oldtnode->bits,
1) == 0)
- put_child(t, tn, 2*i, node);
+ put_child(tn, 2*i, node);
else
- put_child(t, tn, 2*i+1, node);
+ put_child(tn, 2*i+1, node);
continue;
}
inode = (struct tnode *) node;
if (inode->bits == 1) {
- put_child(t, tn, 2*i, rtnl_dereference(inode->child[0]));
- put_child(t, tn, 2*i+1, rtnl_dereference(inode->child[1]));
+ put_child(tn, 2*i, rtnl_dereference(inode->child[0]));
+ put_child(tn, 2*i+1, rtnl_dereference(inode->child[1]));
tnode_free_safe(inode);
continue;
*/
left = (struct tnode *) tnode_get_child(tn, 2*i);
- put_child(t, tn, 2*i, NULL);
+ put_child(tn, 2*i, NULL);
BUG_ON(!left);
right = (struct tnode *) tnode_get_child(tn, 2*i+1);
- put_child(t, tn, 2*i+1, NULL);
+ put_child(tn, 2*i+1, NULL);
BUG_ON(!right);
size = tnode_child_length(left);
for (j = 0; j < size; j++) {
- put_child(t, left, j, rtnl_dereference(inode->child[j]));
- put_child(t, right, j, rtnl_dereference(inode->child[j + size]));
+ put_child(left, j, rtnl_dereference(inode->child[j]));
+ put_child(right, j, rtnl_dereference(inode->child[j + size]));
}
- put_child(t, tn, 2*i, resize(t, left));
- put_child(t, tn, 2*i+1, resize(t, right));
+ put_child(tn, 2*i, resize(t, left));
+ put_child(tn, 2*i+1, resize(t, right));
tnode_free_safe(inode);
}
if (!newn)
goto nomem;
- put_child(t, tn, i/2, (struct rt_trie_node *)newn);
+ put_child(tn, i/2, (struct rt_trie_node *)newn);
}
}
if (left == NULL) {
if (right == NULL) /* Both are empty */
continue;
- put_child(t, tn, i/2, right);
+ put_child(tn, i/2, right);
continue;
}
if (right == NULL) {
- put_child(t, tn, i/2, left);
+ put_child(tn, i/2, left);
continue;
}
/* Two nonempty children */
newBinNode = (struct tnode *) tnode_get_child(tn, i/2);
- put_child(t, tn, i/2, NULL);
- put_child(t, newBinNode, 0, left);
- put_child(t, newBinNode, 1, right);
- put_child(t, tn, i/2, resize(t, newBinNode));
+ put_child(tn, i/2, NULL);
+ put_child(newBinNode, 0, left);
+ put_child(newBinNode, 1, right);
+ put_child(tn, i/2, resize(t, newBinNode));
}
tnode_free_safe(oldtnode);
return tn;
node_set_parent((struct rt_trie_node *)l, tp);
cindex = tkey_extract_bits(key, tp->pos, tp->bits);
- put_child(t, tp, cindex, (struct rt_trie_node *)l);
+ put_child(tp, cindex, (struct rt_trie_node *)l);
} else {
/* Case 3: n is a LEAF or a TNODE and the key doesn't match. */
/*
node_set_parent((struct rt_trie_node *)tn, tp);
missbit = tkey_extract_bits(key, newpos, 1);
- put_child(t, tn, missbit, (struct rt_trie_node *)l);
- put_child(t, tn, 1-missbit, n);
+ put_child(tn, missbit, (struct rt_trie_node *)l);
+ put_child(tn, 1-missbit, n);
if (tp) {
cindex = tkey_extract_bits(key, tp->pos, tp->bits);
- put_child(t, tp, cindex, (struct rt_trie_node *)tn);
+ put_child(tp, cindex, (struct rt_trie_node *)tn);
} else {
rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn);
tp = tn;
if (tp) {
t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits);
- put_child(t, tp, cindex, NULL);
+ put_child(tp, cindex, NULL);
trie_rebalance(t, tp);
} else
RCU_INIT_POINTER(t->trie, NULL);
const struct net_protocol *ipprot;
int protocol = iph->protocol;
- rcu_read_lock();
ipprot = rcu_dereference(inet_protos[protocol]);
if (ipprot && ipprot->early_demux) {
ipprot->early_demux(skb);
/* must reload iph, skb->head might have changed */
iph = ip_hdr(skb);
}
- rcu_read_unlock();
}
/*
struct sk_buff *skb, u32 mtu);
static void ip_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
+static void ipv4_dst_destroy(struct dst_entry *dst);
static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int how)
.default_advmss = ipv4_default_advmss,
.mtu = ipv4_mtu,
.cow_metrics = ipv4_cow_metrics,
+ .destroy = ipv4_dst_destroy,
.ifdown = ipv4_dst_ifdown,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
build_sk_flow_key(fl4, sk);
}
-static DEFINE_SEQLOCK(fnhe_seqlock);
+static inline void rt_free(struct rtable *rt)
+{
+ call_rcu(&rt->dst.rcu_head, dst_rcu_free);
+}
+
+static DEFINE_SPINLOCK(fnhe_lock);
static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
{
struct fib_nh_exception *fnhe, *oldest;
+ struct rtable *orig;
oldest = rcu_dereference(hash->chain);
for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe;
if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp))
oldest = fnhe;
}
+ orig = rcu_dereference(oldest->fnhe_rth);
+ if (orig) {
+ RCU_INIT_POINTER(oldest->fnhe_rth, NULL);
+ rt_free(orig);
+ }
return oldest;
}
int depth;
u32 hval = fnhe_hashfun(daddr);
- write_seqlock_bh(&fnhe_seqlock);
+ spin_lock_bh(&fnhe_lock);
hash = nh->nh_exceptions;
if (!hash) {
fnhe->fnhe_stamp = jiffies;
out_unlock:
- write_sequnlock_bh(&fnhe_seqlock);
+ spin_unlock_bh(&fnhe_lock);
return;
}
return NULL;
}
-static void rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
+static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
__be32 daddr)
{
- __be32 fnhe_daddr, gw;
- unsigned long expires;
- unsigned int seq;
- u32 pmtu;
-
-restart:
- seq = read_seqbegin(&fnhe_seqlock);
- fnhe_daddr = fnhe->fnhe_daddr;
- gw = fnhe->fnhe_gw;
- pmtu = fnhe->fnhe_pmtu;
- expires = fnhe->fnhe_expires;
- if (read_seqretry(&fnhe_seqlock, seq))
- goto restart;
-
- if (daddr != fnhe_daddr)
- return;
+ bool ret = false;
+
+ spin_lock_bh(&fnhe_lock);
- if (pmtu) {
- unsigned long diff = expires - jiffies;
+ if (daddr == fnhe->fnhe_daddr) {
+ struct rtable *orig;
- if (time_before(jiffies, expires)) {
- rt->rt_pmtu = pmtu;
- dst_set_expires(&rt->dst, diff);
+ if (fnhe->fnhe_pmtu) {
+ unsigned long expires = fnhe->fnhe_expires;
+ unsigned long diff = expires - jiffies;
+
+ if (time_before(jiffies, expires)) {
+ rt->rt_pmtu = fnhe->fnhe_pmtu;
+ dst_set_expires(&rt->dst, diff);
+ }
}
+ if (fnhe->fnhe_gw) {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ rt->rt_gateway = fnhe->fnhe_gw;
+ }
+
+ orig = rcu_dereference(fnhe->fnhe_rth);
+ rcu_assign_pointer(fnhe->fnhe_rth, rt);
+ if (orig)
+ rt_free(orig);
+
+ fnhe->fnhe_stamp = jiffies;
+ ret = true;
+ } else {
+ /* Routes we intend to cache in nexthop exception have
+ * the DST_NOCACHE bit clear. However, if we are
+ * unsuccessful at storing this route into the cache
+ * we really need to set it.
+ */
+ rt->dst.flags |= DST_NOCACHE;
}
- if (gw) {
- rt->rt_flags |= RTCF_REDIRECTED;
- rt->rt_gateway = gw;
- }
- fnhe->fnhe_stamp = jiffies;
-}
+ spin_unlock_bh(&fnhe_lock);
-static inline void rt_free(struct rtable *rt)
-{
- call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
+ return ret;
}
-static void rt_cache_route(struct fib_nh *nh, struct rtable *rt)
+static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
{
- struct rtable *orig, *prev, **p = &nh->nh_rth_output;
-
- if (rt_is_input_route(rt))
- p = &nh->nh_rth_input;
+ struct rtable *orig, *prev, **p;
+ bool ret = true;
+ if (rt_is_input_route(rt)) {
+ p = (struct rtable **)&nh->nh_rth_input;
+ } else {
+ if (!nh->nh_pcpu_rth_output)
+ goto nocache;
+ p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
+ }
orig = *p;
prev = cmpxchg(p, orig, rt);
* unsuccessful at storing this route into the cache
* we really need to set it.
*/
+nocache:
rt->dst.flags |= DST_NOCACHE;
+ ret = false;
+ }
+
+ return ret;
+}
+
+static DEFINE_SPINLOCK(rt_uncached_lock);
+static LIST_HEAD(rt_uncached_list);
+
+static void rt_add_uncached_list(struct rtable *rt)
+{
+ spin_lock_bh(&rt_uncached_lock);
+ list_add_tail(&rt->rt_uncached, &rt_uncached_list);
+ spin_unlock_bh(&rt_uncached_lock);
+}
+
+static void ipv4_dst_destroy(struct dst_entry *dst)
+{
+ struct rtable *rt = (struct rtable *) dst;
+
+ if (dst->flags & DST_NOCACHE) {
+ spin_lock_bh(&rt_uncached_lock);
+ list_del(&rt->rt_uncached);
+ spin_unlock_bh(&rt_uncached_lock);
+ }
+}
+
+void rt_flush_dev(struct net_device *dev)
+{
+ if (!list_empty(&rt_uncached_list)) {
+ struct net *net = dev_net(dev);
+ struct rtable *rt;
+
+ spin_lock_bh(&rt_uncached_lock);
+ list_for_each_entry(rt, &rt_uncached_list, rt_uncached) {
+ if (rt->dst.dev != dev)
+ continue;
+ rt->dst.dev = net->loopback_dev;
+ dev_hold(rt->dst.dev);
+ dev_put(dev);
+ }
+ spin_unlock_bh(&rt_uncached_lock);
}
}
struct fib_nh_exception *fnhe,
struct fib_info *fi, u16 type, u32 itag)
{
+ bool cached = false;
+
if (fi) {
struct fib_nh *nh = &FIB_RES_NH(*res);
if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK)
rt->rt_gateway = nh->nh_gw;
- if (unlikely(fnhe))
- rt_bind_exception(rt, fnhe, daddr);
dst_init_metrics(&rt->dst, fi->fib_metrics, true);
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
#endif
- if (!(rt->dst.flags & DST_NOCACHE))
- rt_cache_route(nh, rt);
+ if (unlikely(fnhe))
+ cached = rt_bind_exception(rt, fnhe, daddr);
+ else if (!(rt->dst.flags & DST_NOCACHE))
+ cached = rt_cache_route(nh, rt);
}
+ if (unlikely(!cached))
+ rt_add_uncached_list(rt);
#ifdef CONFIG_IP_ROUTE_CLASSID
#ifdef CONFIG_IP_MULTIPLE_TABLES
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ INIT_LIST_HEAD(&rth->rt_uncached);
if (our) {
rth->dst.input= ip_local_deliver;
rth->rt_flags |= RTCF_LOCAL;
do_cache = false;
if (res->fi) {
if (!itag) {
- rth = FIB_RES_NH(*res).nh_rth_input;
+ rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
goto out;
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ INIT_LIST_HEAD(&rth->rt_uncached);
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
do_cache = false;
if (res.fi) {
if (!itag) {
- rth = FIB_RES_NH(res).nh_rth_input;
+ rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
err = 0;
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ INIT_LIST_HEAD(&rth->rt_uncached);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
fnhe = NULL;
if (fi) {
+ struct rtable __rcu **prth;
+
fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
- if (!fnhe) {
- rth = FIB_RES_NH(*res).nh_rth_output;
- if (rt_cache_valid(rth)) {
- dst_hold(&rth->dst);
- return rth;
- }
+ if (fnhe)
+ prth = &fnhe->fnhe_rth;
+ else
+ prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output);
+ rth = rcu_dereference(*prth);
+ if (rt_cache_valid(rth)) {
+ dst_hold(&rth->dst);
+ return rth;
}
}
rth = rt_dst_alloc(dev_out,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(in_dev, NOXFRM),
- fi && !fnhe);
+ fi);
if (!rth)
return ERR_PTR(-ENOBUFS);
rth->rt_iif = orig_oif ? : 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ INIT_LIST_HEAD(&rth->rt_uncached);
RT_CACHE_STAT_INC(out_slow_tot);
rt->rt_type = ort->rt_type;
rt->rt_gateway = ort->rt_gateway;
+ INIT_LIST_HEAD(&rt->rt_uncached);
+
dst_free(new);
}
.mode = 0644,
.proc_handler = proc_dointvec
},
- {
- .procname = "rt_cache_rebuild_count",
- .data = &init_net.ipv4.sysctl_rt_cache_rebuild_count,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
{
.procname = "ping_group_range",
.data = &init_net.ipv4.sysctl_ping_group_range,
table[5].data =
&net->ipv4.sysctl_icmp_ratemask;
table[6].data =
- &net->ipv4.sysctl_rt_cache_rebuild_count;
- table[7].data =
&net->ipv4.sysctl_ping_group_range;
}
net->ipv4.sysctl_ping_group_range[0] = 1;
net->ipv4.sysctl_ping_group_range[1] = 0;
- net->ipv4.sysctl_rt_cache_rebuild_count = 4;
-
tcp_init_mem(net);
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
tcp_set_state(sk, TCP_ESTABLISHED);
if (skb != NULL) {
- sk->sk_rx_dst = dst_clone(skb_dst(skb));
- inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+ inet_sk_rx_dst_set(sk, skb);
security_inet_conn_established(sk, skb);
}
#endif
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
+ struct dst_entry *dst = sk->sk_rx_dst;
+
sock_rps_save_rxhash(sk, skb);
- if (sk->sk_rx_dst) {
- struct dst_entry *dst = sk->sk_rx_dst;
+ if (dst) {
if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
dst->ops->check(dst, 0) == NULL) {
dst_release(dst);
sk->sk_rx_dst = NULL;
}
}
- if (unlikely(sk->sk_rx_dst == NULL)) {
- sk->sk_rx_dst = dst_clone(skb_dst(skb));
- inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
- }
+ if (unlikely(sk->sk_rx_dst == NULL))
+ inet_sk_rx_dst_set(sk, skb);
+
if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
rsk = sk;
goto reset;
struct tcp_sock *oldtp = tcp_sk(sk);
struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
- newsk->sk_rx_dst = dst_clone(skb_dst(skb));
- inet_sk(newsk)->rx_dst_ifindex = skb->skb_iif;
+ inet_sk_rx_dst_set(newsk, skb);
/* TCP Cookie Transactions require space for the cookie pair,
* as it differs for each connection. There is no need to
xdst->u.rt.rt_type = rt->rt_type;
xdst->u.rt.rt_gateway = rt->rt_gateway;
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
+ INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
return 0;
}
if (sysctl_ip_early_demux && !skb_dst(skb)) {
const struct inet6_protocol *ipprot;
- rcu_read_lock();
ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
if (ipprot && ipprot->early_demux)
ipprot->early_demux(skb);
- rcu_read_unlock();
}
if (!skb_dst(skb))
ip6_route_input(skb);
goto nla_put_failure;
if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric))
goto nla_put_failure;
- if (!(rt->rt6i_flags & RTF_EXPIRES))
- expires = 0;
- else if (rt->dst.expires - jiffies < INT_MAX)
- expires = rt->dst.expires - jiffies;
- else
- expires = INT_MAX;
+
+ expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0;
if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
goto nla_put_failure;
git.openpandora.org / pandora-kernel.git / commitdiff