* [PATCH] ifb: add multi-queue support
From: Changli Gao @ 2009-11-13 4:37 UTC (permalink / raw)
To: David S. Miller, Stephen Hemminger, Patrick McHardy
Cc: xiaosuo, Eric Dumazet, Tom Herbert, netdev
In-Reply-To: <4AFBD911.6000900@gmail.com>
ifb: add multi-queue support
Add multi-queue support, and one kernel thread is created for per queue.
It can used to emulate multi-queue NIC in software, and distribute work
among CPUs.
gentux linux # modprobe ifb numtxqs=2
gentux linux # ifconfig ifb0 up
gentux linux # pgrep ifb0
18508
18509
gentux linux # taskset -p 1 18508
pid 18508's current affinity mask: 3
pid 18508's new affinity mask: 1
gentux linux # taskset -p 2 18509
pid 18509's current affinity mask: 3
pid 18509's new affinity mask: 2
gentux linux # tc qdisc add dev br0 ingress
gentux linux # tc filter add dev br0 parent ffff: protocol ip basic
action mirred egress redirect dev ifb0
This patch also introduces a ip link option "numtxqs" for specifying the
number of the TX queues. so you can add a new ifb with the command:
ip link add numtxqs 4 type ifb
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
drivers/net/ifb.c | 491 ++++++++++++++++++++++++++++++++++--------------
include/linux/if_link.h | 1
net/core/rtnetlink.c | 3
3 files changed, 360 insertions(+), 135 deletions(-)
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 69c2566..96ab20a 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -33,161 +33,162 @@
#include <linux/etherdevice.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/kthread.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/if_vlan.h>
+#include <linux/if_pppox.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
#include <net/pkt_sched.h>
#include <net/net_namespace.h>
-#define TX_TIMEOUT (2*HZ)
-
#define TX_Q_LIMIT 32
+
+struct ifb_private_q {
+ struct net_device *dev;
+ struct sk_buff_head rq;
+ wait_queue_head_t wq;
+ struct task_struct *task;
+ unsigned long rx_packets;
+ unsigned long rx_bytes;
+ unsigned long rx_dropped;
+} ____cacheline_aligned_in_smp;
+
struct ifb_private {
- struct tasklet_struct ifb_tasklet;
- int tasklet_pending;
- /* mostly debug stats leave in for now */
- unsigned long st_task_enter; /* tasklet entered */
- unsigned long st_txq_refl_try; /* transmit queue refill attempt */
- unsigned long st_rxq_enter; /* receive queue entered */
- unsigned long st_rx2tx_tran; /* receive to trasmit transfers */
- unsigned long st_rxq_notenter; /*receiveQ not entered, resched */
- unsigned long st_rx_frm_egr; /* received from egress path */
- unsigned long st_rx_frm_ing; /* received from ingress path */
- unsigned long st_rxq_check;
- unsigned long st_rxq_rsch;
- struct sk_buff_head rq;
- struct sk_buff_head tq;
+ struct ifb_private_q *pq;
};
+/* Number of ifb devices to be set up by this module. */
static int numifbs = 2;
+module_param(numifbs, int, 0444);
+MODULE_PARM_DESC(numifbs, "Number of ifb devices");
-static void ri_tasklet(unsigned long dev);
-static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev);
-static int ifb_open(struct net_device *dev);
-static int ifb_close(struct net_device *dev);
+/* Number of TX queues per ifb */
+static unsigned int numtxqs = 1;
+module_param(numtxqs, uint, 0444);
+MODULE_PARM_DESC(numtxqs, "Number of TX queues per ifb");
-static void ri_tasklet(unsigned long dev)
+static int ifb_thread(void *priv)
{
-
- struct net_device *_dev = (struct net_device *)dev;
- struct ifb_private *dp = netdev_priv(_dev);
- struct net_device_stats *stats = &_dev->stats;
- struct netdev_queue *txq;
+ struct ifb_private_q *pq = priv;
+ struct net_device *dev = pq->dev, *_dev;
+ int num = pq - ((struct ifb_private *)netdev_priv(dev))->pq;
+ struct netdev_queue *txq = netdev_get_tx_queue(dev, num);
struct sk_buff *skb;
-
- txq = netdev_get_tx_queue(_dev, 0);
- dp->st_task_enter++;
- if ((skb = skb_peek(&dp->tq)) == NULL) {
- dp->st_txq_refl_try++;
- if (__netif_tx_trylock(txq)) {
- dp->st_rxq_enter++;
- while ((skb = skb_dequeue(&dp->rq)) != NULL) {
- skb_queue_tail(&dp->tq, skb);
- dp->st_rx2tx_tran++;
- }
- __netif_tx_unlock(txq);
- } else {
- /* reschedule */
- dp->st_rxq_notenter++;
- goto resched;
+ DEFINE_WAIT(wait);
+ struct sk_buff_head tq;
+
+ __skb_queue_head_init(&tq);
+ while (1) {
+ /* move skb from rq to tq */
+ while (1) {
+ prepare_to_wait(&pq->wq, &wait, TASK_UNINTERRUPTIBLE);
+ __netif_tx_lock_bh(txq);
+ skb_queue_splice_tail_init(&pq->rq, &tq);
+ if (netif_queue_stopped(dev))
+ netif_wake_queue(dev);
+ __netif_tx_unlock_bh(txq);
+ if (kthread_should_stop() || !skb_queue_empty(&tq))
+ break;
+ schedule();
}
- }
-
- while ((skb = skb_dequeue(&dp->tq)) != NULL) {
- u32 from = G_TC_FROM(skb->tc_verd);
-
- skb->tc_verd = 0;
- skb->tc_verd = SET_TC_NCLS(skb->tc_verd);
- stats->tx_packets++;
- stats->tx_bytes +=skb->len;
-
- rcu_read_lock();
- skb->dev = dev_get_by_index_rcu(&init_net, skb->iif);
- if (!skb->dev) {
- rcu_read_unlock();
- dev_kfree_skb(skb);
- stats->tx_dropped++;
+ finish_wait(&pq->wq, &wait);
+ if (kthread_should_stop()) {
+ __skb_queue_purge(&tq);
break;
}
- rcu_read_unlock();
- skb->iif = _dev->ifindex;
-
- if (from & AT_EGRESS) {
- dp->st_rx_frm_egr++;
- dev_queue_xmit(skb);
- } else if (from & AT_INGRESS) {
- dp->st_rx_frm_ing++;
- skb_pull(skb, skb->dev->hard_header_len);
- netif_rx(skb);
- } else
- BUG();
- }
-
- if (__netif_tx_trylock(txq)) {
- dp->st_rxq_check++;
- if ((skb = skb_peek(&dp->rq)) == NULL) {
- dp->tasklet_pending = 0;
- if (netif_queue_stopped(_dev))
- netif_wake_queue(_dev);
- } else {
- dp->st_rxq_rsch++;
- __netif_tx_unlock(txq);
- goto resched;
+ if (need_resched())
+ schedule();
+
+ /* transfer packets */
+ while ((skb = __skb_dequeue(&tq)) != NULL) {
+ u32 from = G_TC_FROM(skb->tc_verd);
+
+ skb->tc_verd = 0;
+ skb->tc_verd = SET_TC_NCLS(skb->tc_verd);
+ txq->tx_packets++;
+ txq->tx_bytes +=skb->len;
+
+ rcu_read_lock();
+ _dev = dev_get_by_index_rcu(&init_net, skb->iif);
+ if (_dev != NULL) {
+ skb->dev = _dev;
+ skb->iif = dev->ifindex;
+ if (from & AT_EGRESS) {
+ dev_queue_xmit(skb);
+ } else if (from & AT_INGRESS) {
+ skb_pull(skb, _dev->hard_header_len);
+ netif_rx_ni(skb);
+ } else {
+ BUG();
+ }
+ } else {
+ dev_kfree_skb(skb);
+ txq->tx_dropped++;
+ }
+ rcu_read_unlock();
}
- __netif_tx_unlock(txq);
- } else {
-resched:
- dp->tasklet_pending = 1;
- tasklet_schedule(&dp->ifb_tasklet);
}
+ return 0;
}
-static const struct net_device_ops ifb_netdev_ops = {
- .ndo_open = ifb_open,
- .ndo_stop = ifb_close,
- .ndo_start_xmit = ifb_xmit,
- .ndo_validate_addr = eth_validate_addr,
-};
-
-static void ifb_setup(struct net_device *dev)
+struct net_device_stats* ifb_get_stats(struct net_device *dev)
{
- /* Initialize the device structure. */
- dev->destructor = free_netdev;
- dev->netdev_ops = &ifb_netdev_ops;
+ struct net_device_stats *stats = &dev->stats;
+ struct ifb_private *dp = netdev_priv(dev);
+ struct ifb_private_q *pq = dp->pq;
+ struct netdev_queue *txq;
+ int i;
+ unsigned long rx_packets = 0, rx_bytes = 0, rx_dropped = 0;
+ unsigned long tx_packets = 0, tx_bytes = 0, tx_dropped = 0;
+
+ for (i = 0; i < dev->real_num_tx_queues; i++) {
+ rx_packets += pq[i].rx_packets;
+ rx_bytes += pq[i].rx_bytes;
+ rx_dropped += pq[i].rx_dropped;
+ txq = netdev_get_tx_queue(dev, i);
+ tx_packets += txq->tx_packets;
+ tx_bytes += txq->tx_bytes;
+ tx_dropped += txq->tx_dropped;
+ }
- /* Fill in device structure with ethernet-generic values. */
- ether_setup(dev);
- dev->tx_queue_len = TX_Q_LIMIT;
+ stats->rx_packets = rx_packets;
+ stats->rx_bytes = rx_bytes;
+ stats->rx_dropped = rx_dropped;
+ stats->tx_packets = tx_packets;
+ stats->tx_bytes = tx_bytes;
+ stats->tx_dropped = tx_dropped;
- dev->flags |= IFF_NOARP;
- dev->flags &= ~IFF_MULTICAST;
- dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
- random_ether_addr(dev->dev_addr);
+ return stats;
}
static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev)
{
- struct ifb_private *dp = netdev_priv(dev);
- struct net_device_stats *stats = &dev->stats;
u32 from = G_TC_FROM(skb->tc_verd);
+ int num = skb_get_queue_mapping(skb);
+ struct ifb_private *dp = netdev_priv(dev);
+ struct ifb_private_q *pq = dp->pq + num;
+ struct netdev_queue *txq = netdev_get_tx_queue(dev, num);
- stats->rx_packets++;
- stats->rx_bytes+=skb->len;
+ pq->rx_packets++;
+ pq->rx_bytes += skb->len;
if (!(from & (AT_INGRESS|AT_EGRESS)) || !skb->iif) {
dev_kfree_skb(skb);
- stats->rx_dropped++;
+ pq->rx_dropped++;
return NETDEV_TX_OK;
}
- if (skb_queue_len(&dp->rq) >= dev->tx_queue_len) {
+ txq->trans_start = jiffies;
+ __skb_queue_tail(&pq->rq, skb);
+ if (skb_queue_len(&pq->rq) >= dev->tx_queue_len)
netif_stop_queue(dev);
- }
-
- dev->trans_start = jiffies;
- skb_queue_tail(&dp->rq, skb);
- if (!dp->tasklet_pending) {
- dp->tasklet_pending = 1;
- tasklet_schedule(&dp->ifb_tasklet);
- }
+ if (skb_queue_len(&pq->rq) == 1)
+ wake_up(&pq->wq);
return NETDEV_TX_OK;
}
@@ -195,26 +196,230 @@ static netdev_tx_t ifb_xmit(struct sk_buff *skb,
struct net_device *dev)
static int ifb_close(struct net_device *dev)
{
struct ifb_private *dp = netdev_priv(dev);
+ struct ifb_private_q *pq = dp->pq;
+ int i;
- tasklet_kill(&dp->ifb_tasklet);
netif_stop_queue(dev);
- skb_queue_purge(&dp->rq);
- skb_queue_purge(&dp->tq);
+ for (i = 0; i < dev->real_num_tx_queues; i++) {
+ kthread_stop(pq[i].task);
+ __skb_queue_purge(&pq[i].rq);
+ }
+
return 0;
}
static int ifb_open(struct net_device *dev)
{
struct ifb_private *dp = netdev_priv(dev);
-
- tasklet_init(&dp->ifb_tasklet, ri_tasklet, (unsigned long)dev);
- skb_queue_head_init(&dp->rq);
- skb_queue_head_init(&dp->tq);
+ struct ifb_private_q *pq = dp->pq;
+ int i;
+
+ for (i = 0; i < dev->real_num_tx_queues; i++) {
+ pq[i].task = kthread_run(ifb_thread, &pq[i], "%s/%d", dev->name,
+ i);
+ if (IS_ERR(pq[i].task)) {
+ int err = PTR_ERR(pq[i].task);
+ while (--i >= 0)
+ kthread_stop(pq[i].task);
+ return err;
+ }
+ }
netif_start_queue(dev);
return 0;
}
+static u32 simple_tx_hashrnd;
+
+static inline __be16 pppoe_proto(const struct sk_buff *skb)
+{
+ return *((__be16 *)(skb_mac_header(skb) + ETH_HLEN +
+ sizeof(struct pppoe_hdr)));
+}
+
+static u16 ifb_select_queue(struct net_device *dev, struct sk_buff *skb)
+{
+ u32 addr1, addr2;
+ u32 hash;
+ union {
+ u16 in16[2];
+ u32 in32;
+ } ports;
+ u8 ip_proto;
+ unsigned int pull_len, proto_pull_len;
+ int ihl;
+
+ if ((hash = skb_rx_queue_recorded(skb))) {
+ while (hash >= dev->real_num_tx_queues)
+ hash -= dev->real_num_tx_queues;
+ return hash;
+ }
+
+ /* act_mirred pushed the skb before calling dev_queue_xmit() */
+ proto_pull_len = 0;
+ pull_len = skb_network_header(skb) - skb->data;
+ if (unlikely(skb_pull(skb, pull_len) == NULL)) {
+ pull_len = 0;
+ goto process_other;
+ }
+
+ ihl = 0;
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_8021Q):
+ if (unlikely(skb_pull(skb, VLAN_HLEN) == NULL))
+ goto process_other;
+ pull_len += VLAN_HLEN;
+ skb->network_header += VLAN_HLEN;
+ proto_pull_len = VLAN_HLEN;
+ switch (vlan_eth_hdr(skb)->h_vlan_encapsulated_proto) {
+ case __constant_htons(ETH_P_IP):
+ goto process_ip;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case __constant_htons(ETH_P_IPV6):
+ goto process_ipv6;
+#endif
+ default:
+ goto process_other;
+ }
+ break;
+ case __constant_htons(ETH_P_PPP_SES):
+ if (unlikely(skb_pull(skb, PPPOE_SES_HLEN) == NULL))
+ goto process_other;
+ pull_len += PPPOE_SES_HLEN;
+ skb->network_header += PPPOE_SES_HLEN;
+ proto_pull_len = PPPOE_SES_HLEN;
+ switch (pppoe_proto(skb)) {
+ case __constant_htons(ETH_P_IP):
+ goto process_ip;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case __constant_htons(ETH_P_IPV6):
+ goto process_ipv6;
+#endif
+ default:
+ goto process_other;
+ }
+ break;
+ case __constant_htons(ETH_P_IP):
+process_ip:
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct iphdr))))
+ goto process_other;
+ if (!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)))
+ ip_proto = ip_hdr(skb)->protocol;
+ else
+ ip_proto = 0;
+ addr1 = ip_hdr(skb)->saddr;
+ addr2 = ip_hdr(skb)->daddr;
+ ihl = ip_hdrlen(skb);
+ break;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case __constant_htons(ETH_P_IPV6):
+process_ipv6:
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct ipv6hdr))))
+ goto process_other;
+ addr1 = ipv6_hdr(skb)->saddr.s6_addr32[3];
+ addr2 = ipv6_hdr(skb)->daddr.s6_addr32[3];
+ ihl = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &ip_proto);
+ if (unlikely(ihl < 0))
+ goto process_other_trans;
+ break;
+#endif
+ default:
+process_other:
+ if (pull_len != 0) {
+ skb_push(skb, pull_len);
+ if (proto_pull_len != 0)
+ skb->network_header -= proto_pull_len;
+ }
+ return skb->protocol % dev->real_num_tx_queues;
+ }
+ if (addr1 > addr2)
+ swap(addr1, addr2);
+
+ switch (ip_proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_DCCP:
+ case IPPROTO_ESP:
+ case IPPROTO_AH:
+ case IPPROTO_SCTP:
+ case IPPROTO_UDPLITE:
+ if (unlikely(skb_copy_bits(skb, ihl, &ports.in32, 4) < 0))
+ goto process_other_trans;
+ if (ports.in16[0] > ports.in16[1])
+ swap(ports.in16[0], ports.in16[1]);
+ break;
+ default:
+process_other_trans:
+ ports.in32 = 0;
+ break;
+ }
+
+ if (pull_len != 0) {
+ skb_push(skb, pull_len);
+ if (proto_pull_len != 0)
+ skb->network_header -= proto_pull_len;
+ }
+
+ hash = jhash_3words(addr1, addr2, ports.in32,
+ simple_tx_hashrnd ^ ip_proto);
+
+ return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
+}
+
+static int ifb_init(struct net_device *dev)
+{
+ struct ifb_private *dp = netdev_priv(dev);
+ struct ifb_private_q *pq = dp->pq;
+ int i;
+
+ pq = kcalloc(dev->real_num_tx_queues, sizeof(*pq), GFP_KERNEL);
+ if (pq == NULL)
+ return -ENOMEM;
+ dp->pq = pq;
+
+ for (i = 0; i < dev->real_num_tx_queues; i++) {
+ pq[i].dev = dev;
+ __skb_queue_head_init(&pq[i].rq);
+ init_waitqueue_head(&pq[i].wq);
+ }
+
+ return 0;
+}
+
+static void ifb_uninit(struct net_device *dev)
+{
+ struct ifb_private *dp = netdev_priv(dev);
+
+ kfree(dp->pq);
+}
+
+static const struct net_device_ops ifb_netdev_ops = {
+ .ndo_init = ifb_init,
+ .ndo_uninit = ifb_uninit,
+ .ndo_open = ifb_open,
+ .ndo_stop = ifb_close,
+ .ndo_start_xmit = ifb_xmit,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_select_queue = ifb_select_queue,
+ .ndo_get_stats = ifb_get_stats,
+};
+
+static void ifb_setup(struct net_device *dev)
+{
+ /* Initialize the device structure. */
+ dev->destructor = free_netdev;
+ dev->netdev_ops = &ifb_netdev_ops;
+
+ /* Fill in device structure with ethernet-generic values. */
+ ether_setup(dev);
+ dev->tx_queue_len = TX_Q_LIMIT;
+
+ dev->flags |= IFF_NOARP;
+ dev->flags &= ~IFF_MULTICAST;
+ dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+ random_ether_addr(dev->dev_addr);
+}
+
static int ifb_validate(struct nlattr *tb[], struct nlattr *data[])
{
if (tb[IFLA_ADDRESS]) {
@@ -226,25 +431,38 @@ static int ifb_validate(struct nlattr *tb[],
struct nlattr *data[])
return 0;
}
+static int ifb_get_tx_queues(struct net *net, struct nlattr *tb[],
+ unsigned int *num_tx_queues,
+ unsigned int *real_num_tx_queues)
+{
+ if (tb[IFLA_NTXQ]) {
+ *num_tx_queues = nla_get_u32(tb[IFLA_NTXQ]);
+ if (*num_tx_queues < 1)
+ return -EINVAL;
+ *real_num_tx_queues = *num_tx_queues;
+ } else {
+ *num_tx_queues = numtxqs;
+ *real_num_tx_queues = numtxqs;
+ }
+
+ return 0;
+}
+
static struct rtnl_link_ops ifb_link_ops __read_mostly = {
.kind = "ifb",
- .priv_size = sizeof(struct ifb_private),
.setup = ifb_setup,
.validate = ifb_validate,
+ .get_tx_queues = ifb_get_tx_queues,
+ .priv_size = sizeof(struct ifb_private),
};
-/* Number of ifb devices to be set up by this module. */
-module_param(numifbs, int, 0);
-MODULE_PARM_DESC(numifbs, "Number of ifb devices");
-
static int __init ifb_init_one(int index)
{
struct net_device *dev_ifb;
int err;
- dev_ifb = alloc_netdev(sizeof(struct ifb_private),
- "ifb%d", ifb_setup);
-
+ dev_ifb = alloc_netdev_mq(sizeof(struct ifb_private), "ifb%d",
+ ifb_setup, numtxqs);
if (!dev_ifb)
return -ENOMEM;
@@ -268,9 +486,12 @@ static int __init ifb_init_module(void)
{
int i, err;
+ if (numtxqs < 1)
+ return -EINVAL;
+
+ get_random_bytes(&simple_tx_hashrnd, 4);
rtnl_lock();
err = __rtnl_link_register(&ifb_link_ops);
-
for (i = 0; i < numifbs && !err; i++)
err = ifb_init_one(i);
if (err)
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 1d3b242..99da411 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -78,6 +78,7 @@ enum {
#define IFLA_LINKINFO IFLA_LINKINFO
IFLA_NET_NS_PID,
IFLA_IFALIAS,
+ IFLA_NTXQ,
__IFLA_MAX
};
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 33148a5..1cbe555 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -597,6 +597,7 @@ static inline size_t if_nlmsg_size(const struct
net_device *dev)
+ nla_total_size(4) /* IFLA_MASTER */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ + nla_total_size(4) /* IFLA_NTXQ */
+ rtnl_link_get_size(dev); /* IFLA_LINKINFO */
}
@@ -627,6 +628,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
struct net_device *dev,
netif_running(dev) ? dev->operstate : IF_OPER_DOWN);
NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode);
NLA_PUT_U32(skb, IFLA_MTU, dev->mtu);
+ NLA_PUT_U32(skb, IFLA_NTXQ, dev->real_num_tx_queues);
if (dev->ifindex != dev->iflink)
NLA_PUT_U32(skb, IFLA_LINK, dev->iflink);
@@ -725,6 +727,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_LINKINFO] = { .type = NLA_NESTED },
[IFLA_NET_NS_PID] = { .type = NLA_U32 },
[IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 },
+ [IFLA_NTXQ] = { .type = NLA_U32 },
};
EXPORT_SYMBOL(ifla_policy);
^ permalink raw reply related
* [net-next-2.6 PATCH 2/7] igb: move timesync init into a seperate function
From: Jeff Kirsher @ 2009-11-13 4:37 UTC (permalink / raw)
To: davem; +Cc: netdev, gospo, Alexander Duyck, Jeff Kirsher
In-Reply-To: <20091113043604.1240.80142.stgit@localhost.localdomain>
From: Alexander Duyck <alexander.h.duyck@intel.com>
Current code is quite large and making igb_probe difficult to read.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/igb/igb_main.c | 115 +++++++++++++++++++++++++-------------------
1 files changed, 65 insertions(+), 50 deletions(-)
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index b044c98..d72d484 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -1566,56 +1566,6 @@ static int __devinit igb_probe(struct pci_dev *pdev,
}
#endif
- switch (hw->mac.type) {
- case e1000_82576:
- /*
- * Initialize hardware timer: we keep it running just in case
- * that some program needs it later on.
- */
- memset(&adapter->cycles, 0, sizeof(adapter->cycles));
- adapter->cycles.read = igb_read_clock;
- adapter->cycles.mask = CLOCKSOURCE_MASK(64);
- adapter->cycles.mult = 1;
- /**
- * Scale the NIC clock cycle by a large factor so that
- * relatively small clock corrections can be added or
- * substracted at each clock tick. The drawbacks of a large
- * factor are a) that the clock register overflows more quickly
- * (not such a big deal) and b) that the increment per tick has
- * to fit into 24 bits. As a result we need to use a shift of
- * 19 so we can fit a value of 16 into the TIMINCA register.
- */
- adapter->cycles.shift = IGB_82576_TSYNC_SHIFT;
- wr32(E1000_TIMINCA,
- (1 << E1000_TIMINCA_16NS_SHIFT) |
- (16 << IGB_82576_TSYNC_SHIFT));
-
- /* Set registers so that rollover occurs soon to test this. */
- wr32(E1000_SYSTIML, 0x00000000);
- wr32(E1000_SYSTIMH, 0xFF800000);
- wrfl();
-
- timecounter_init(&adapter->clock,
- &adapter->cycles,
- ktime_to_ns(ktime_get_real()));
- /*
- * Synchronize our NIC clock against system wall clock. NIC
- * time stamp reading requires ~3us per sample, each sample
- * was pretty stable even under load => only require 10
- * samples for each offset comparison.
- */
- memset(&adapter->compare, 0, sizeof(adapter->compare));
- adapter->compare.source = &adapter->clock;
- adapter->compare.target = ktime_get_real;
- adapter->compare.num_samples = 10;
- timecompare_update(&adapter->compare, 0);
- break;
- case e1000_82575:
- /* 82575 does not support timesync */
- default:
- break;
- }
-
dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n");
/* print bus type/speed/width info */
dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n",
@@ -1781,6 +1731,70 @@ static void __devinit igb_probe_vfs(struct igb_adapter * adapter)
#endif /* CONFIG_PCI_IOV */
}
+
+/**
+ * igb_init_hw_timer - Initialize hardware timer used with IEEE 1588 timestamp
+ * @adapter: board private structure to initialize
+ *
+ * igb_init_hw_timer initializes the function pointer and values for the hw
+ * timer found in hardware.
+ **/
+static void igb_init_hw_timer(struct igb_adapter *adapter)
+{
+ struct e1000_hw *hw = &adapter->hw;
+
+ switch (hw->mac.type) {
+ case e1000_82576:
+ /*
+ * Initialize hardware timer: we keep it running just in case
+ * that some program needs it later on.
+ */
+ memset(&adapter->cycles, 0, sizeof(adapter->cycles));
+ adapter->cycles.read = igb_read_clock;
+ adapter->cycles.mask = CLOCKSOURCE_MASK(64);
+ adapter->cycles.mult = 1;
+ /**
+ * Scale the NIC clock cycle by a large factor so that
+ * relatively small clock corrections can be added or
+ * substracted at each clock tick. The drawbacks of a large
+ * factor are a) that the clock register overflows more quickly
+ * (not such a big deal) and b) that the increment per tick has
+ * to fit into 24 bits. As a result we need to use a shift of
+ * 19 so we can fit a value of 16 into the TIMINCA register.
+ */
+ adapter->cycles.shift = IGB_82576_TSYNC_SHIFT;
+ wr32(E1000_TIMINCA,
+ (1 << E1000_TIMINCA_16NS_SHIFT) |
+ (16 << IGB_82576_TSYNC_SHIFT));
+
+ /* Set registers so that rollover occurs soon to test this. */
+ wr32(E1000_SYSTIML, 0x00000000);
+ wr32(E1000_SYSTIMH, 0xFF800000);
+ wrfl();
+
+ timecounter_init(&adapter->clock,
+ &adapter->cycles,
+ ktime_to_ns(ktime_get_real()));
+ /*
+ * Synchronize our NIC clock against system wall clock. NIC
+ * time stamp reading requires ~3us per sample, each sample
+ * was pretty stable even under load => only require 10
+ * samples for each offset comparison.
+ */
+ memset(&adapter->compare, 0, sizeof(adapter->compare));
+ adapter->compare.source = &adapter->clock;
+ adapter->compare.target = ktime_get_real;
+ adapter->compare.num_samples = 10;
+ timecompare_update(&adapter->compare, 0);
+ break;
+ case e1000_82575:
+ /* 82575 does not support timesync */
+ default:
+ break;
+ }
+
+}
+
/**
* igb_sw_init - Initialize general software structures (struct igb_adapter)
* @adapter: board private structure to initialize
@@ -1816,6 +1830,7 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
return -ENOMEM;
}
+ igb_init_hw_timer(adapter);
igb_probe_vfs(adapter);
/* Explicitly disable IRQ since the NIC can be in any state. */
^ permalink raw reply related
* [net-next-2.6 PATCH 3/7] igb: when number of CPUs > 4 combine tx/rx queues to allow more queues
From: Jeff Kirsher @ 2009-11-13 4:37 UTC (permalink / raw)
To: davem; +Cc: netdev, gospo, Alexander Duyck, Jeff Kirsher
In-Reply-To: <20091113043604.1240.80142.stgit@localhost.localdomain>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch makes it so that nics such as 82576 and newer can support more
hardware queues when there are more than 4 cpus by combining a tx/rx queue
pair onto one interrupt so that 8 queue pairs can be supported and thus
allow for more queues.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/igb/igb.h | 9 +++++----
drivers/net/igb/igb_main.c | 31 ++++++++++++++++++++++---------
2 files changed, 27 insertions(+), 13 deletions(-)
diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h
index 3298f5a..2bb9549 100644
--- a/drivers/net/igb/igb.h
+++ b/drivers/net/igb/igb.h
@@ -59,10 +59,10 @@ struct igb_adapter;
#define MAX_Q_VECTORS 8
/* Transmit and receive queues */
-#define IGB_MAX_RX_QUEUES (adapter->vfs_allocated_count ? \
- (adapter->vfs_allocated_count > 6 ? 1 : 2) : 4)
-#define IGB_MAX_TX_QUEUES IGB_MAX_RX_QUEUES
-#define IGB_ABS_MAX_TX_QUEUES 4
+#define IGB_MAX_RX_QUEUES (adapter->vfs_allocated_count ? 2 : \
+ (hw->mac.type > e1000_82575 ? 8 : 4))
+#define IGB_ABS_MAX_TX_QUEUES 8
+#define IGB_MAX_TX_QUEUES IGB_MAX_RX_QUEUES
#define IGB_MAX_VF_MC_ENTRIES 30
#define IGB_MAX_VF_FUNCTIONS 8
@@ -315,6 +315,7 @@ struct igb_adapter {
u16 rx_ring_count;
unsigned int vfs_allocated_count;
struct vf_data_storage *vf_data;
+ u32 rss_queues;
};
#define IGB_FLAG_HAS_MSI (1 << 0)
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index d72d484..0235220 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -296,10 +296,10 @@ static void igb_cache_ring_register(struct igb_adapter *adapter)
* and continue consuming queues in the same sequence
*/
if (adapter->vfs_allocated_count) {
- for (; i < adapter->num_rx_queues; i++)
+ for (; i < adapter->rss_queues; i++)
adapter->rx_ring[i].reg_idx = rbase_offset +
Q_IDX_82576(i);
- for (; j < adapter->num_tx_queues; j++)
+ for (; j < adapter->rss_queues; j++)
adapter->tx_ring[j].reg_idx = rbase_offset +
Q_IDX_82576(j);
}
@@ -618,14 +618,15 @@ static void igb_set_interrupt_capability(struct igb_adapter *adapter)
int numvecs, i;
/* Number of supported queues. */
- adapter->num_rx_queues = min_t(u32, IGB_MAX_RX_QUEUES, num_online_cpus());
- adapter->num_tx_queues = min_t(u32, IGB_MAX_TX_QUEUES, num_online_cpus());
+ adapter->num_rx_queues = adapter->rss_queues;
+ adapter->num_tx_queues = adapter->rss_queues;
/* start with one vector for every rx queue */
numvecs = adapter->num_rx_queues;
/* if tx handler is seperate add 1 for every tx queue */
- numvecs += adapter->num_tx_queues;
+ if (!(adapter->flags & IGB_FLAG_QUEUE_PAIRS))
+ numvecs += adapter->num_tx_queues;
/* store the number of vectors reserved for queues */
adapter->num_q_vectors = numvecs;
@@ -666,6 +667,7 @@ msi_only:
}
#endif
adapter->vfs_allocated_count = 0;
+ adapter->rss_queues = 1;
adapter->flags |= IGB_FLAG_QUEUE_PAIRS;
adapter->num_rx_queues = 1;
adapter->num_tx_queues = 1;
@@ -1824,6 +1826,17 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
adapter->vfs_allocated_count = max_vfs;
#endif /* CONFIG_PCI_IOV */
+ adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES, num_online_cpus());
+
+ /*
+ * if rss_queues > 4 or vfs are going to be allocated with rss_queues
+ * then we should combine the queues into a queue pair in order to
+ * conserve interrupts due to limited supply
+ */
+ if ((adapter->rss_queues > 4) ||
+ ((adapter->rss_queues > 1) && (adapter->vfs_allocated_count > 6)))
+ adapter->flags |= IGB_FLAG_QUEUE_PAIRS;
+
/* This call may decrease the number of queues */
if (igb_init_interrupt_scheme(adapter)) {
dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
@@ -2015,7 +2028,7 @@ static int igb_setup_all_tx_resources(struct igb_adapter *adapter)
}
}
- for (i = 0; i < IGB_MAX_TX_QUEUES; i++) {
+ for (i = 0; i < IGB_ABS_MAX_TX_QUEUES; i++) {
int r_idx = i % adapter->num_tx_queues;
adapter->multi_tx_table[i] = &adapter->tx_ring[r_idx];
}
@@ -2199,7 +2212,7 @@ static void igb_setup_mrqc(struct igb_adapter *adapter)
array_wr32(E1000_RSSRK(0), j, rsskey);
}
- num_rx_queues = adapter->num_rx_queues;
+ num_rx_queues = adapter->rss_queues;
if (adapter->vfs_allocated_count) {
/* 82575 and 82576 supports 2 RSS queues for VMDq */
@@ -2255,7 +2268,7 @@ static void igb_setup_mrqc(struct igb_adapter *adapter)
E1000_VT_CTL_DEFAULT_POOL_SHIFT;
wr32(E1000_VT_CTL, vtctl);
}
- if (adapter->num_rx_queues > 1)
+ if (adapter->rss_queues > 1)
mrqc = E1000_MRQC_ENABLE_VMDQ_RSS_2Q;
else
mrqc = E1000_MRQC_ENABLE_VMDQ;
@@ -2385,7 +2398,7 @@ static inline void igb_set_vmolr(struct igb_adapter *adapter, int vfn)
/* clear all bits that might not be set */
vmolr &= ~(E1000_VMOLR_BAM | E1000_VMOLR_RSSE);
- if (adapter->num_rx_queues > 1 && vfn == adapter->vfs_allocated_count)
+ if (adapter->rss_queues > 1 && vfn == adapter->vfs_allocated_count)
vmolr |= E1000_VMOLR_RSSE; /* enable RSS */
/*
* for VMDq only allow the VFs and pool 0 to accept broadcast and
^ permalink raw reply related
* [net-next-2.6 PATCH 4/7] igb: Rework how netdev->stats is handled
From: Jeff Kirsher @ 2009-11-13 4:37 UTC (permalink / raw)
To: davem; +Cc: netdev, gospo, Alexander Duyck, Jeff Kirsher
In-Reply-To: <20091113043604.1240.80142.stgit@localhost.localdomain>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch does some refactoring work that I felt was needed after reviewing
the changes recently submitted relating to the replacement of net_stats with
netdev->stats.
This patch essentially creates two different collections of stats. The
first handles the adapter specific states and is stored in gstring_stats,
and the second is for netdev specific stats and is stored in
gstring_net_stats.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/igb/igb_ethtool.c | 171 +++++++++++++++++++++--------------------
drivers/net/igb/igb_main.c | 40 +++++-----
2 files changed, 108 insertions(+), 103 deletions(-)
diff --git a/drivers/net/igb/igb_ethtool.c b/drivers/net/igb/igb_ethtool.c
index f2b2825..c1cde5b 100644
--- a/drivers/net/igb/igb_ethtool.c
+++ b/drivers/net/igb/igb_ethtool.c
@@ -37,77 +37,88 @@
#include "igb.h"
-enum {NETDEV_STATS, IGB_STATS};
-
struct igb_stats {
char stat_string[ETH_GSTRING_LEN];
- int type;
int sizeof_stat;
int stat_offset;
};
-#define IGB_STAT(m) IGB_STATS, \
- FIELD_SIZEOF(struct igb_adapter, m), \
- offsetof(struct igb_adapter, m)
-#define IGB_NETDEV_STAT(m) NETDEV_STATS, \
- FIELD_SIZEOF(struct net_device, m), \
- offsetof(struct net_device, m)
-
+#define IGB_STAT(_name, _stat) { \
+ .stat_string = _name, \
+ .sizeof_stat = FIELD_SIZEOF(struct igb_adapter, _stat), \
+ .stat_offset = offsetof(struct igb_adapter, _stat) \
+}
static const struct igb_stats igb_gstrings_stats[] = {
- { "rx_packets", IGB_STAT(stats.gprc) },
- { "tx_packets", IGB_STAT(stats.gptc) },
- { "rx_bytes", IGB_STAT(stats.gorc) },
- { "tx_bytes", IGB_STAT(stats.gotc) },
- { "rx_broadcast", IGB_STAT(stats.bprc) },
- { "tx_broadcast", IGB_STAT(stats.bptc) },
- { "rx_multicast", IGB_STAT(stats.mprc) },
- { "tx_multicast", IGB_STAT(stats.mptc) },
- { "rx_errors", IGB_NETDEV_STAT(stats.rx_errors) },
- { "tx_errors", IGB_NETDEV_STAT(stats.tx_errors) },
- { "tx_dropped", IGB_NETDEV_STAT(stats.tx_dropped) },
- { "multicast", IGB_STAT(stats.mprc) },
- { "collisions", IGB_STAT(stats.colc) },
- { "rx_length_errors", IGB_NETDEV_STAT(stats.rx_length_errors) },
- { "rx_over_errors", IGB_NETDEV_STAT(stats.rx_over_errors) },
- { "rx_crc_errors", IGB_STAT(stats.crcerrs) },
- { "rx_frame_errors", IGB_NETDEV_STAT(stats.rx_frame_errors) },
- { "rx_no_buffer_count", IGB_STAT(stats.rnbc) },
- { "rx_queue_drop_packet_count", IGB_NETDEV_STAT(stats.rx_fifo_errors) },
- { "rx_missed_errors", IGB_STAT(stats.mpc) },
- { "tx_aborted_errors", IGB_STAT(stats.ecol) },
- { "tx_carrier_errors", IGB_STAT(stats.tncrs) },
- { "tx_fifo_errors", IGB_NETDEV_STAT(stats.tx_fifo_errors) },
- { "tx_heartbeat_errors", IGB_NETDEV_STAT(stats.tx_heartbeat_errors) },
- { "tx_window_errors", IGB_STAT(stats.latecol) },
- { "tx_abort_late_coll", IGB_STAT(stats.latecol) },
- { "tx_deferred_ok", IGB_STAT(stats.dc) },
- { "tx_single_coll_ok", IGB_STAT(stats.scc) },
- { "tx_multi_coll_ok", IGB_STAT(stats.mcc) },
- { "tx_timeout_count", IGB_STAT(tx_timeout_count) },
- { "rx_long_length_errors", IGB_STAT(stats.roc) },
- { "rx_short_length_errors", IGB_STAT(stats.ruc) },
- { "rx_align_errors", IGB_STAT(stats.algnerrc) },
- { "tx_tcp_seg_good", IGB_STAT(stats.tsctc) },
- { "tx_tcp_seg_failed", IGB_STAT(stats.tsctfc) },
- { "rx_flow_control_xon", IGB_STAT(stats.xonrxc) },
- { "rx_flow_control_xoff", IGB_STAT(stats.xoffrxc) },
- { "tx_flow_control_xon", IGB_STAT(stats.xontxc) },
- { "tx_flow_control_xoff", IGB_STAT(stats.xofftxc) },
- { "rx_long_byte_count", IGB_STAT(stats.gorc) },
- { "tx_dma_out_of_sync", IGB_STAT(stats.doosync) },
- { "tx_smbus", IGB_STAT(stats.mgptc) },
- { "rx_smbus", IGB_STAT(stats.mgprc) },
- { "dropped_smbus", IGB_STAT(stats.mgpdc) },
+ IGB_STAT("rx_packets", stats.gprc),
+ IGB_STAT("tx_packets", stats.gptc),
+ IGB_STAT("rx_bytes", stats.gorc),
+ IGB_STAT("tx_bytes", stats.gotc),
+ IGB_STAT("rx_broadcast", stats.bprc),
+ IGB_STAT("tx_broadcast", stats.bptc),
+ IGB_STAT("rx_multicast", stats.mprc),
+ IGB_STAT("tx_multicast", stats.mptc),
+ IGB_STAT("multicast", stats.mprc),
+ IGB_STAT("collisions", stats.colc),
+ IGB_STAT("rx_crc_errors", stats.crcerrs),
+ IGB_STAT("rx_no_buffer_count", stats.rnbc),
+ IGB_STAT("rx_missed_errors", stats.mpc),
+ IGB_STAT("tx_aborted_errors", stats.ecol),
+ IGB_STAT("tx_carrier_errors", stats.tncrs),
+ IGB_STAT("tx_window_errors", stats.latecol),
+ IGB_STAT("tx_abort_late_coll", stats.latecol),
+ IGB_STAT("tx_deferred_ok", stats.dc),
+ IGB_STAT("tx_single_coll_ok", stats.scc),
+ IGB_STAT("tx_multi_coll_ok", stats.mcc),
+ IGB_STAT("tx_timeout_count", tx_timeout_count),
+ IGB_STAT("rx_long_length_errors", stats.roc),
+ IGB_STAT("rx_short_length_errors", stats.ruc),
+ IGB_STAT("rx_align_errors", stats.algnerrc),
+ IGB_STAT("tx_tcp_seg_good", stats.tsctc),
+ IGB_STAT("tx_tcp_seg_failed", stats.tsctfc),
+ IGB_STAT("rx_flow_control_xon", stats.xonrxc),
+ IGB_STAT("rx_flow_control_xoff", stats.xoffrxc),
+ IGB_STAT("tx_flow_control_xon", stats.xontxc),
+ IGB_STAT("tx_flow_control_xoff", stats.xofftxc),
+ IGB_STAT("rx_long_byte_count", stats.gorc),
+ IGB_STAT("tx_dma_out_of_sync", stats.doosync),
+ IGB_STAT("tx_smbus", stats.mgptc),
+ IGB_STAT("rx_smbus", stats.mgprc),
+ IGB_STAT("dropped_smbus", stats.mgpdc),
+};
+
+#define IGB_NETDEV_STAT(_net_stat) { \
+ .stat_string = __stringify(_net_stat), \
+ .sizeof_stat = FIELD_SIZEOF(struct net_device_stats, _net_stat), \
+ .stat_offset = offsetof(struct net_device_stats, _net_stat) \
+}
+static const struct igb_stats igb_gstrings_net_stats[] = {
+ IGB_NETDEV_STAT(rx_errors),
+ IGB_NETDEV_STAT(tx_errors),
+ IGB_NETDEV_STAT(tx_dropped),
+ IGB_NETDEV_STAT(rx_length_errors),
+ IGB_NETDEV_STAT(rx_over_errors),
+ IGB_NETDEV_STAT(rx_frame_errors),
+ IGB_NETDEV_STAT(rx_fifo_errors),
+ IGB_NETDEV_STAT(tx_fifo_errors),
+ IGB_NETDEV_STAT(tx_heartbeat_errors)
};
+#define IGB_GLOBAL_STATS_LEN \
+ (sizeof(igb_gstrings_stats) / sizeof(struct igb_stats))
+#define IGB_NETDEV_STATS_LEN \
+ (sizeof(igb_gstrings_net_stats) / sizeof(struct igb_stats))
+#define IGB_RX_QUEUE_STATS_LEN \
+ (sizeof(struct igb_rx_queue_stats) / sizeof(u64))
+#define IGB_TX_QUEUE_STATS_LEN \
+ (sizeof(struct igb_tx_queue_stats) / sizeof(u64))
#define IGB_QUEUE_STATS_LEN \
((((struct igb_adapter *)netdev_priv(netdev))->num_rx_queues * \
- (sizeof(struct igb_rx_queue_stats) / sizeof(u64))) + \
+ IGB_RX_QUEUE_STATS_LEN) + \
(((struct igb_adapter *)netdev_priv(netdev))->num_tx_queues * \
- (sizeof(struct igb_tx_queue_stats) / sizeof(u64))))
-#define IGB_GLOBAL_STATS_LEN \
- (sizeof(igb_gstrings_stats) / sizeof(struct igb_stats))
-#define IGB_STATS_LEN (IGB_GLOBAL_STATS_LEN + IGB_QUEUE_STATS_LEN)
+ IGB_TX_QUEUE_STATS_LEN))
+#define IGB_STATS_LEN \
+ (IGB_GLOBAL_STATS_LEN + IGB_NETDEV_STATS_LEN + IGB_QUEUE_STATS_LEN)
+
static const char igb_gstrings_test[][ETH_GSTRING_LEN] = {
"Register test (offline)", "Eeprom test (offline)",
"Interrupt test (offline)", "Loopback test (offline)",
@@ -1922,43 +1933,32 @@ static void igb_get_ethtool_stats(struct net_device *netdev,
struct ethtool_stats *stats, u64 *data)
{
struct igb_adapter *adapter = netdev_priv(netdev);
+ struct net_device_stats *net_stats = &netdev->stats;
u64 *queue_stat;
- int stat_count_tx = sizeof(struct igb_tx_queue_stats) / sizeof(u64);
- int stat_count_rx = sizeof(struct igb_rx_queue_stats) / sizeof(u64);
- int j;
- int i;
- char *p = NULL;
+ int i, j, k;
+ char *p;
igb_update_stats(adapter);
for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) {
- switch (igb_gstrings_stats[i].type) {
- case NETDEV_STATS:
- p = (char *) netdev +
- igb_gstrings_stats[i].stat_offset;
- break;
- case IGB_STATS:
- p = (char *) adapter +
- igb_gstrings_stats[i].stat_offset;
- break;
- }
-
+ p = (char *)adapter + igb_gstrings_stats[i].stat_offset;
data[i] = (igb_gstrings_stats[i].sizeof_stat ==
sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
}
+ for (j = 0; j < IGB_NETDEV_STATS_LEN; j++, i++) {
+ p = (char *)net_stats + igb_gstrings_net_stats[j].stat_offset;
+ data[i] = (igb_gstrings_net_stats[j].sizeof_stat ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
for (j = 0; j < adapter->num_tx_queues; j++) {
- int k;
queue_stat = (u64 *)&adapter->tx_ring[j].tx_stats;
- for (k = 0; k < stat_count_tx; k++)
- data[i + k] = queue_stat[k];
- i += k;
+ for (k = 0; k < IGB_TX_QUEUE_STATS_LEN; k++, i++)
+ data[i] = queue_stat[k];
}
for (j = 0; j < adapter->num_rx_queues; j++) {
- int k;
queue_stat = (u64 *)&adapter->rx_ring[j].rx_stats;
- for (k = 0; k < stat_count_rx; k++)
- data[i + k] = queue_stat[k];
- i += k;
+ for (k = 0; k < IGB_RX_QUEUE_STATS_LEN; k++, i++)
+ data[i] = queue_stat[k];
}
}
@@ -1979,6 +1979,11 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
ETH_GSTRING_LEN);
p += ETH_GSTRING_LEN;
}
+ for (i = 0; i < IGB_NETDEV_STATS_LEN; i++) {
+ memcpy(p, igb_gstrings_net_stats[i].stat_string,
+ ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
for (i = 0; i < adapter->num_tx_queues; i++) {
sprintf(p, "tx_queue_%u_packets", i);
p += ETH_GSTRING_LEN;
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 0235220..4d4ab87 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -3789,7 +3789,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
void igb_update_stats(struct igb_adapter *adapter)
{
- struct net_device *netdev = adapter->netdev;
+ struct net_device_stats *net_stats = igb_get_stats(adapter->netdev);
struct e1000_hw *hw = &adapter->hw;
struct pci_dev *pdev = adapter->pdev;
u32 rnbc;
@@ -3813,13 +3813,13 @@ void igb_update_stats(struct igb_adapter *adapter)
for (i = 0; i < adapter->num_rx_queues; i++) {
u32 rqdpc_tmp = rd32(E1000_RQDPC(i)) & 0x0FFF;
adapter->rx_ring[i].rx_stats.drops += rqdpc_tmp;
- netdev->stats.rx_fifo_errors += rqdpc_tmp;
+ net_stats->rx_fifo_errors += rqdpc_tmp;
bytes += adapter->rx_ring[i].rx_stats.bytes;
packets += adapter->rx_ring[i].rx_stats.packets;
}
- netdev->stats.rx_bytes = bytes;
- netdev->stats.rx_packets = packets;
+ net_stats->rx_bytes = bytes;
+ net_stats->rx_packets = packets;
bytes = 0;
packets = 0;
@@ -3827,8 +3827,8 @@ void igb_update_stats(struct igb_adapter *adapter)
bytes += adapter->tx_ring[i].tx_stats.bytes;
packets += adapter->tx_ring[i].tx_stats.packets;
}
- netdev->stats.tx_bytes = bytes;
- netdev->stats.tx_packets = packets;
+ net_stats->tx_bytes = bytes;
+ net_stats->tx_packets = packets;
/* read stats registers */
adapter->stats.crcerrs += rd32(E1000_CRCERRS);
@@ -3865,7 +3865,7 @@ void igb_update_stats(struct igb_adapter *adapter)
rd32(E1000_GOTCH); /* clear GOTCL */
rnbc = rd32(E1000_RNBC);
adapter->stats.rnbc += rnbc;
- netdev->stats.rx_fifo_errors += rnbc;
+ net_stats->rx_fifo_errors += rnbc;
adapter->stats.ruc += rd32(E1000_RUC);
adapter->stats.rfc += rd32(E1000_RFC);
adapter->stats.rjc += rd32(E1000_RJC);
@@ -3906,29 +3906,29 @@ void igb_update_stats(struct igb_adapter *adapter)
adapter->stats.icrxdmtc += rd32(E1000_ICRXDMTC);
/* Fill out the OS statistics structure */
- netdev->stats.multicast = adapter->stats.mprc;
- netdev->stats.collisions = adapter->stats.colc;
+ net_stats->multicast = adapter->stats.mprc;
+ net_stats->collisions = adapter->stats.colc;
/* Rx Errors */
/* RLEC on some newer hardware can be incorrect so build
* our own version based on RUC and ROC */
- netdev->stats.rx_errors = adapter->stats.rxerrc +
+ net_stats->rx_errors = adapter->stats.rxerrc +
adapter->stats.crcerrs + adapter->stats.algnerrc +
adapter->stats.ruc + adapter->stats.roc +
adapter->stats.cexterr;
- netdev->stats.rx_length_errors = adapter->stats.ruc +
- adapter->stats.roc;
- netdev->stats.rx_crc_errors = adapter->stats.crcerrs;
- netdev->stats.rx_frame_errors = adapter->stats.algnerrc;
- netdev->stats.rx_missed_errors = adapter->stats.mpc;
+ net_stats->rx_length_errors = adapter->stats.ruc +
+ adapter->stats.roc;
+ net_stats->rx_crc_errors = adapter->stats.crcerrs;
+ net_stats->rx_frame_errors = adapter->stats.algnerrc;
+ net_stats->rx_missed_errors = adapter->stats.mpc;
/* Tx Errors */
- netdev->stats.tx_errors = adapter->stats.ecol +
- adapter->stats.latecol;
- netdev->stats.tx_aborted_errors = adapter->stats.ecol;
- netdev->stats.tx_window_errors = adapter->stats.latecol;
- netdev->stats.tx_carrier_errors = adapter->stats.tncrs;
+ net_stats->tx_errors = adapter->stats.ecol +
+ adapter->stats.latecol;
+ net_stats->tx_aborted_errors = adapter->stats.ecol;
+ net_stats->tx_window_errors = adapter->stats.latecol;
+ net_stats->tx_carrier_errors = adapter->stats.tncrs;
/* Tx Dropped needs to be maintained elsewhere */
^ permalink raw reply related
* [net-next-2.6 PATCH 5/7] igb: removed unused tx/rx total bytes/packets from adapter struct
From: Jeff Kirsher @ 2009-11-13 4:37 UTC (permalink / raw)
To: davem; +Cc: netdev, gospo, Alexander Duyck, Jeff Kirsher
In-Reply-To: <20091113043604.1240.80142.stgit@localhost.localdomain>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch removes unused variables total_tx_bytes, total_tx_packets,
total_rx_bytes, and total_rx_packets from the adapter struct.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/igb/igb.h | 4 ----
1 files changed, 0 insertions(+), 4 deletions(-)
diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h
index 2bb9549..63abd1c 100644
--- a/drivers/net/igb/igb.h
+++ b/drivers/net/igb/igb.h
@@ -249,10 +249,6 @@ struct igb_adapter {
u16 link_speed;
u16 link_duplex;
- unsigned int total_tx_bytes;
- unsigned int total_tx_packets;
- unsigned int total_rx_bytes;
- unsigned int total_rx_packets;
/* Interrupt Throttle Rate */
u32 rx_itr_setting;
u32 tx_itr_setting;
^ permalink raw reply related
* [net-next-2.6 PATCH 6/7] igb: check for packets on all tx rings when link is down
From: Jeff Kirsher @ 2009-11-13 4:38 UTC (permalink / raw)
To: davem; +Cc: netdev, gospo, Alexander Duyck, Jeff Kirsher
In-Reply-To: <20091113043604.1240.80142.stgit@localhost.localdomain>
From: Alexander Duyck <alexander.h.duyck@intel.com>
We were previously only checking the first tx ring to see if it had any
packets in it when the link when down. However we should be checking all
of the rings so this patch makes it so that all of the rings are now being
checked.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/igb/igb_main.c | 23 ++++++++++++-----------
1 files changed, 12 insertions(+), 11 deletions(-)
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 4d4ab87..9911b3a 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -2943,7 +2943,6 @@ static void igb_watchdog_task(struct work_struct *work)
watchdog_task);
struct e1000_hw *hw = &adapter->hw;
struct net_device *netdev = adapter->netdev;
- struct igb_ring *tx_ring = adapter->tx_ring;
u32 link;
int i;
@@ -3013,22 +3012,24 @@ static void igb_watchdog_task(struct work_struct *work)
igb_update_stats(adapter);
igb_update_adaptive(hw);
- if (!netif_carrier_ok(netdev)) {
- if (igb_desc_unused(tx_ring) + 1 < tx_ring->count) {
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ struct igb_ring *tx_ring = &adapter->tx_ring[i];
+ if (!netif_carrier_ok(netdev)) {
/* We've lost link, so the controller stops DMA,
* but we've got queued Tx work that's never going
* to get done, so reset controller to flush Tx.
* (Do the reset outside of interrupt context). */
- adapter->tx_timeout_count++;
- schedule_work(&adapter->reset_task);
- /* return immediately since reset is imminent */
- return;
+ if (igb_desc_unused(tx_ring) + 1 < tx_ring->count) {
+ adapter->tx_timeout_count++;
+ schedule_work(&adapter->reset_task);
+ /* return immediately since reset is imminent */
+ return;
+ }
}
- }
- /* Force detection of hung controller every watchdog period */
- for (i = 0; i < adapter->num_tx_queues; i++)
- adapter->tx_ring[i].detect_tx_hung = true;
+ /* Force detection of hung controller every watchdog period */
+ tx_ring->detect_tx_hung = true;
+ }
/* Cause software interrupt to ensure rx ring is cleaned */
if (adapter->msix_entries) {
^ permalink raw reply related
* [net-next-2.6 PATCH 7/7] igb: only recycle page if it is on our numa node
From: Jeff Kirsher @ 2009-11-13 4:38 UTC (permalink / raw)
To: davem; +Cc: netdev, gospo, Alexander Duyck, Jeff Kirsher
In-Reply-To: <20091113043604.1240.80142.stgit@localhost.localdomain>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch makes it so that we only recycle pages when they are from the
local NUMA node. Non-local pages are freed and replaced with locally
allocated pages.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/igb/igb_main.c | 4 +++-
1 files changed, 3 insertions(+), 1 deletions(-)
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 9911b3a..0cab5e2 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -4952,6 +4952,7 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
struct sk_buff *skb;
bool cleaned = false;
int cleaned_count = 0;
+ int current_node = numa_node_id();
unsigned int total_bytes = 0, total_packets = 0;
unsigned int i;
u32 staterr;
@@ -5006,7 +5007,8 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
buffer_info->page_offset,
length);
- if (page_count(buffer_info->page) != 1)
+ if ((page_count(buffer_info->page) != 1) ||
+ (page_to_nid(buffer_info->page) != current_node))
buffer_info->page = NULL;
else
get_page(buffer_info->page);
^ permalink raw reply related
* [PATCH] ifb: add multi-queue support
From: Changli Gao @ 2009-11-13 4:42 UTC (permalink / raw)
To: David S. Miller, Stephen Hemminger, Patrick McHardy
Cc: xiaosuo, Eric Dumazet, Tom Herbert, netdev
ifb: add multi-queue support
Add multi-queue support, and one kernel thread is created for per queue.
It can used to emulate multi-queue NIC in software, and distribute work
among CPUs.
gentux linux # modprobe ifb numtxqs=2
gentux linux # ifconfig ifb0 up
gentux linux # pgrep ifb0
18508
18509
gentux linux # taskset -p 1 18508
pid 18508's current affinity mask: 3
pid 18508's new affinity mask: 1
gentux linux # taskset -p 2 18509
pid 18509's current affinity mask: 3
pid 18509's new affinity mask: 2
gentux linux # tc qdisc add dev br0 ingress
gentux linux # tc filter add dev br0 parent ffff: protocol ip basic
action mirred egress redirect dev ifb0
This patch also introduces a ip link option "numtxqs" for specifying the
number of the TX queues. so you can add a new ifb with the command:
ip link add numtxqs 4 type ifb
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
drivers/net/ifb.c | 491 ++++++++++++++++++++++++++++++++++--------------
include/linux/if_link.h | 1
net/core/rtnetlink.c | 3
3 files changed, 360 insertions(+), 135 deletions(-)
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 69c2566..96ab20a 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -33,161 +33,162 @@
#include <linux/etherdevice.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/kthread.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/if_vlan.h>
+#include <linux/if_pppox.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
#include <net/pkt_sched.h>
#include <net/net_namespace.h>
-#define TX_TIMEOUT (2*HZ)
-
#define TX_Q_LIMIT 32
+
+struct ifb_private_q {
+ struct net_device *dev;
+ struct sk_buff_head rq;
+ wait_queue_head_t wq;
+ struct task_struct *task;
+ unsigned long rx_packets;
+ unsigned long rx_bytes;
+ unsigned long rx_dropped;
+} ____cacheline_aligned_in_smp;
+
struct ifb_private {
- struct tasklet_struct ifb_tasklet;
- int tasklet_pending;
- /* mostly debug stats leave in for now */
- unsigned long st_task_enter; /* tasklet entered */
- unsigned long st_txq_refl_try; /* transmit queue refill attempt */
- unsigned long st_rxq_enter; /* receive queue entered */
- unsigned long st_rx2tx_tran; /* receive to trasmit transfers */
- unsigned long st_rxq_notenter; /*receiveQ not entered, resched */
- unsigned long st_rx_frm_egr; /* received from egress path */
- unsigned long st_rx_frm_ing; /* received from ingress path */
- unsigned long st_rxq_check;
- unsigned long st_rxq_rsch;
- struct sk_buff_head rq;
- struct sk_buff_head tq;
+ struct ifb_private_q *pq;
};
+/* Number of ifb devices to be set up by this module. */
static int numifbs = 2;
+module_param(numifbs, int, 0444);
+MODULE_PARM_DESC(numifbs, "Number of ifb devices");
-static void ri_tasklet(unsigned long dev);
-static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev);
-static int ifb_open(struct net_device *dev);
-static int ifb_close(struct net_device *dev);
+/* Number of TX queues per ifb */
+static unsigned int numtxqs = 1;
+module_param(numtxqs, uint, 0444);
+MODULE_PARM_DESC(numtxqs, "Number of TX queues per ifb");
-static void ri_tasklet(unsigned long dev)
+static int ifb_thread(void *priv)
{
-
- struct net_device *_dev = (struct net_device *)dev;
- struct ifb_private *dp = netdev_priv(_dev);
- struct net_device_stats *stats = &_dev->stats;
- struct netdev_queue *txq;
+ struct ifb_private_q *pq = priv;
+ struct net_device *dev = pq->dev, *_dev;
+ int num = pq - ((struct ifb_private *)netdev_priv(dev))->pq;
+ struct netdev_queue *txq = netdev_get_tx_queue(dev, num);
struct sk_buff *skb;
-
- txq = netdev_get_tx_queue(_dev, 0);
- dp->st_task_enter++;
- if ((skb = skb_peek(&dp->tq)) == NULL) {
- dp->st_txq_refl_try++;
- if (__netif_tx_trylock(txq)) {
- dp->st_rxq_enter++;
- while ((skb = skb_dequeue(&dp->rq)) != NULL) {
- skb_queue_tail(&dp->tq, skb);
- dp->st_rx2tx_tran++;
- }
- __netif_tx_unlock(txq);
- } else {
- /* reschedule */
- dp->st_rxq_notenter++;
- goto resched;
+ DEFINE_WAIT(wait);
+ struct sk_buff_head tq;
+
+ __skb_queue_head_init(&tq);
+ while (1) {
+ /* move skb from rq to tq */
+ while (1) {
+ prepare_to_wait(&pq->wq, &wait, TASK_UNINTERRUPTIBLE);
+ __netif_tx_lock_bh(txq);
+ skb_queue_splice_tail_init(&pq->rq, &tq);
+ if (netif_queue_stopped(dev))
+ netif_wake_queue(dev);
+ __netif_tx_unlock_bh(txq);
+ if (kthread_should_stop() || !skb_queue_empty(&tq))
+ break;
+ schedule();
}
- }
-
- while ((skb = skb_dequeue(&dp->tq)) != NULL) {
- u32 from = G_TC_FROM(skb->tc_verd);
-
- skb->tc_verd = 0;
- skb->tc_verd = SET_TC_NCLS(skb->tc_verd);
- stats->tx_packets++;
- stats->tx_bytes +=skb->len;
-
- rcu_read_lock();
- skb->dev = dev_get_by_index_rcu(&init_net, skb->iif);
- if (!skb->dev) {
- rcu_read_unlock();
- dev_kfree_skb(skb);
- stats->tx_dropped++;
+ finish_wait(&pq->wq, &wait);
+ if (kthread_should_stop()) {
+ __skb_queue_purge(&tq);
break;
}
- rcu_read_unlock();
- skb->iif = _dev->ifindex;
-
- if (from & AT_EGRESS) {
- dp->st_rx_frm_egr++;
- dev_queue_xmit(skb);
- } else if (from & AT_INGRESS) {
- dp->st_rx_frm_ing++;
- skb_pull(skb, skb->dev->hard_header_len);
- netif_rx(skb);
- } else
- BUG();
- }
-
- if (__netif_tx_trylock(txq)) {
- dp->st_rxq_check++;
- if ((skb = skb_peek(&dp->rq)) == NULL) {
- dp->tasklet_pending = 0;
- if (netif_queue_stopped(_dev))
- netif_wake_queue(_dev);
- } else {
- dp->st_rxq_rsch++;
- __netif_tx_unlock(txq);
- goto resched;
+ if (need_resched())
+ schedule();
+
+ /* transfer packets */
+ while ((skb = __skb_dequeue(&tq)) != NULL) {
+ u32 from = G_TC_FROM(skb->tc_verd);
+
+ skb->tc_verd = 0;
+ skb->tc_verd = SET_TC_NCLS(skb->tc_verd);
+ txq->tx_packets++;
+ txq->tx_bytes +=skb->len;
+
+ rcu_read_lock();
+ _dev = dev_get_by_index_rcu(&init_net, skb->iif);
+ if (_dev != NULL) {
+ skb->dev = _dev;
+ skb->iif = dev->ifindex;
+ if (from & AT_EGRESS) {
+ dev_queue_xmit(skb);
+ } else if (from & AT_INGRESS) {
+ skb_pull(skb, _dev->hard_header_len);
+ netif_rx_ni(skb);
+ } else {
+ BUG();
+ }
+ } else {
+ dev_kfree_skb(skb);
+ txq->tx_dropped++;
+ }
+ rcu_read_unlock();
}
- __netif_tx_unlock(txq);
- } else {
-resched:
- dp->tasklet_pending = 1;
- tasklet_schedule(&dp->ifb_tasklet);
}
+ return 0;
}
-static const struct net_device_ops ifb_netdev_ops = {
- .ndo_open = ifb_open,
- .ndo_stop = ifb_close,
- .ndo_start_xmit = ifb_xmit,
- .ndo_validate_addr = eth_validate_addr,
-};
-
-static void ifb_setup(struct net_device *dev)
+struct net_device_stats* ifb_get_stats(struct net_device *dev)
{
- /* Initialize the device structure. */
- dev->destructor = free_netdev;
- dev->netdev_ops = &ifb_netdev_ops;
+ struct net_device_stats *stats = &dev->stats;
+ struct ifb_private *dp = netdev_priv(dev);
+ struct ifb_private_q *pq = dp->pq;
+ struct netdev_queue *txq;
+ int i;
+ unsigned long rx_packets = 0, rx_bytes = 0, rx_dropped = 0;
+ unsigned long tx_packets = 0, tx_bytes = 0, tx_dropped = 0;
+
+ for (i = 0; i < dev->real_num_tx_queues; i++) {
+ rx_packets += pq[i].rx_packets;
+ rx_bytes += pq[i].rx_bytes;
+ rx_dropped += pq[i].rx_dropped;
+ txq = netdev_get_tx_queue(dev, i);
+ tx_packets += txq->tx_packets;
+ tx_bytes += txq->tx_bytes;
+ tx_dropped += txq->tx_dropped;
+ }
- /* Fill in device structure with ethernet-generic values. */
- ether_setup(dev);
- dev->tx_queue_len = TX_Q_LIMIT;
+ stats->rx_packets = rx_packets;
+ stats->rx_bytes = rx_bytes;
+ stats->rx_dropped = rx_dropped;
+ stats->tx_packets = tx_packets;
+ stats->tx_bytes = tx_bytes;
+ stats->tx_dropped = tx_dropped;
- dev->flags |= IFF_NOARP;
- dev->flags &= ~IFF_MULTICAST;
- dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
- random_ether_addr(dev->dev_addr);
+ return stats;
}
static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev)
{
- struct ifb_private *dp = netdev_priv(dev);
- struct net_device_stats *stats = &dev->stats;
u32 from = G_TC_FROM(skb->tc_verd);
+ int num = skb_get_queue_mapping(skb);
+ struct ifb_private *dp = netdev_priv(dev);
+ struct ifb_private_q *pq = dp->pq + num;
+ struct netdev_queue *txq = netdev_get_tx_queue(dev, num);
- stats->rx_packets++;
- stats->rx_bytes+=skb->len;
+ pq->rx_packets++;
+ pq->rx_bytes += skb->len;
if (!(from & (AT_INGRESS|AT_EGRESS)) || !skb->iif) {
dev_kfree_skb(skb);
- stats->rx_dropped++;
+ pq->rx_dropped++;
return NETDEV_TX_OK;
}
- if (skb_queue_len(&dp->rq) >= dev->tx_queue_len) {
+ txq->trans_start = jiffies;
+ __skb_queue_tail(&pq->rq, skb);
+ if (skb_queue_len(&pq->rq) >= dev->tx_queue_len)
netif_stop_queue(dev);
- }
-
- dev->trans_start = jiffies;
- skb_queue_tail(&dp->rq, skb);
- if (!dp->tasklet_pending) {
- dp->tasklet_pending = 1;
- tasklet_schedule(&dp->ifb_tasklet);
- }
+ if (skb_queue_len(&pq->rq) == 1)
+ wake_up(&pq->wq);
return NETDEV_TX_OK;
}
@@ -195,26 +196,230 @@ static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev)
static int ifb_close(struct net_device *dev)
{
struct ifb_private *dp = netdev_priv(dev);
+ struct ifb_private_q *pq = dp->pq;
+ int i;
- tasklet_kill(&dp->ifb_tasklet);
netif_stop_queue(dev);
- skb_queue_purge(&dp->rq);
- skb_queue_purge(&dp->tq);
+ for (i = 0; i < dev->real_num_tx_queues; i++) {
+ kthread_stop(pq[i].task);
+ __skb_queue_purge(&pq[i].rq);
+ }
+
return 0;
}
static int ifb_open(struct net_device *dev)
{
struct ifb_private *dp = netdev_priv(dev);
-
- tasklet_init(&dp->ifb_tasklet, ri_tasklet, (unsigned long)dev);
- skb_queue_head_init(&dp->rq);
- skb_queue_head_init(&dp->tq);
+ struct ifb_private_q *pq = dp->pq;
+ int i;
+
+ for (i = 0; i < dev->real_num_tx_queues; i++) {
+ pq[i].task = kthread_run(ifb_thread, &pq[i], "%s/%d", dev->name,
+ i);
+ if (IS_ERR(pq[i].task)) {
+ int err = PTR_ERR(pq[i].task);
+ while (--i >= 0)
+ kthread_stop(pq[i].task);
+ return err;
+ }
+ }
netif_start_queue(dev);
return 0;
}
+static u32 simple_tx_hashrnd;
+
+static inline __be16 pppoe_proto(const struct sk_buff *skb)
+{
+ return *((__be16 *)(skb_mac_header(skb) + ETH_HLEN +
+ sizeof(struct pppoe_hdr)));
+}
+
+static u16 ifb_select_queue(struct net_device *dev, struct sk_buff *skb)
+{
+ u32 addr1, addr2;
+ u32 hash;
+ union {
+ u16 in16[2];
+ u32 in32;
+ } ports;
+ u8 ip_proto;
+ unsigned int pull_len, proto_pull_len;
+ int ihl;
+
+ if ((hash = skb_rx_queue_recorded(skb))) {
+ while (hash >= dev->real_num_tx_queues)
+ hash -= dev->real_num_tx_queues;
+ return hash;
+ }
+
+ /* act_mirred pushed the skb before calling dev_queue_xmit() */
+ proto_pull_len = 0;
+ pull_len = skb_network_header(skb) - skb->data;
+ if (unlikely(skb_pull(skb, pull_len) == NULL)) {
+ pull_len = 0;
+ goto process_other;
+ }
+
+ ihl = 0;
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_8021Q):
+ if (unlikely(skb_pull(skb, VLAN_HLEN) == NULL))
+ goto process_other;
+ pull_len += VLAN_HLEN;
+ skb->network_header += VLAN_HLEN;
+ proto_pull_len = VLAN_HLEN;
+ switch (vlan_eth_hdr(skb)->h_vlan_encapsulated_proto) {
+ case __constant_htons(ETH_P_IP):
+ goto process_ip;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case __constant_htons(ETH_P_IPV6):
+ goto process_ipv6;
+#endif
+ default:
+ goto process_other;
+ }
+ break;
+ case __constant_htons(ETH_P_PPP_SES):
+ if (unlikely(skb_pull(skb, PPPOE_SES_HLEN) == NULL))
+ goto process_other;
+ pull_len += PPPOE_SES_HLEN;
+ skb->network_header += PPPOE_SES_HLEN;
+ proto_pull_len = PPPOE_SES_HLEN;
+ switch (pppoe_proto(skb)) {
+ case __constant_htons(ETH_P_IP):
+ goto process_ip;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case __constant_htons(ETH_P_IPV6):
+ goto process_ipv6;
+#endif
+ default:
+ goto process_other;
+ }
+ break;
+ case __constant_htons(ETH_P_IP):
+process_ip:
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct iphdr))))
+ goto process_other;
+ if (!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)))
+ ip_proto = ip_hdr(skb)->protocol;
+ else
+ ip_proto = 0;
+ addr1 = ip_hdr(skb)->saddr;
+ addr2 = ip_hdr(skb)->daddr;
+ ihl = ip_hdrlen(skb);
+ break;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case __constant_htons(ETH_P_IPV6):
+process_ipv6:
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct ipv6hdr))))
+ goto process_other;
+ addr1 = ipv6_hdr(skb)->saddr.s6_addr32[3];
+ addr2 = ipv6_hdr(skb)->daddr.s6_addr32[3];
+ ihl = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &ip_proto);
+ if (unlikely(ihl < 0))
+ goto process_other_trans;
+ break;
+#endif
+ default:
+process_other:
+ if (pull_len != 0) {
+ skb_push(skb, pull_len);
+ if (proto_pull_len != 0)
+ skb->network_header -= proto_pull_len;
+ }
+ return skb->protocol % dev->real_num_tx_queues;
+ }
+ if (addr1 > addr2)
+ swap(addr1, addr2);
+
+ switch (ip_proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_DCCP:
+ case IPPROTO_ESP:
+ case IPPROTO_AH:
+ case IPPROTO_SCTP:
+ case IPPROTO_UDPLITE:
+ if (unlikely(skb_copy_bits(skb, ihl, &ports.in32, 4) < 0))
+ goto process_other_trans;
+ if (ports.in16[0] > ports.in16[1])
+ swap(ports.in16[0], ports.in16[1]);
+ break;
+ default:
+process_other_trans:
+ ports.in32 = 0;
+ break;
+ }
+
+ if (pull_len != 0) {
+ skb_push(skb, pull_len);
+ if (proto_pull_len != 0)
+ skb->network_header -= proto_pull_len;
+ }
+
+ hash = jhash_3words(addr1, addr2, ports.in32,
+ simple_tx_hashrnd ^ ip_proto);
+
+ return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
+}
+
+static int ifb_init(struct net_device *dev)
+{
+ struct ifb_private *dp = netdev_priv(dev);
+ struct ifb_private_q *pq = dp->pq;
+ int i;
+
+ pq = kcalloc(dev->real_num_tx_queues, sizeof(*pq), GFP_KERNEL);
+ if (pq == NULL)
+ return -ENOMEM;
+ dp->pq = pq;
+
+ for (i = 0; i < dev->real_num_tx_queues; i++) {
+ pq[i].dev = dev;
+ __skb_queue_head_init(&pq[i].rq);
+ init_waitqueue_head(&pq[i].wq);
+ }
+
+ return 0;
+}
+
+static void ifb_uninit(struct net_device *dev)
+{
+ struct ifb_private *dp = netdev_priv(dev);
+
+ kfree(dp->pq);
+}
+
+static const struct net_device_ops ifb_netdev_ops = {
+ .ndo_init = ifb_init,
+ .ndo_uninit = ifb_uninit,
+ .ndo_open = ifb_open,
+ .ndo_stop = ifb_close,
+ .ndo_start_xmit = ifb_xmit,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_select_queue = ifb_select_queue,
+ .ndo_get_stats = ifb_get_stats,
+};
+
+static void ifb_setup(struct net_device *dev)
+{
+ /* Initialize the device structure. */
+ dev->destructor = free_netdev;
+ dev->netdev_ops = &ifb_netdev_ops;
+
+ /* Fill in device structure with ethernet-generic values. */
+ ether_setup(dev);
+ dev->tx_queue_len = TX_Q_LIMIT;
+
+ dev->flags |= IFF_NOARP;
+ dev->flags &= ~IFF_MULTICAST;
+ dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+ random_ether_addr(dev->dev_addr);
+}
+
static int ifb_validate(struct nlattr *tb[], struct nlattr *data[])
{
if (tb[IFLA_ADDRESS]) {
@@ -226,25 +431,38 @@ static int ifb_validate(struct nlattr *tb[], struct nlattr *data[])
return 0;
}
+static int ifb_get_tx_queues(struct net *net, struct nlattr *tb[],
+ unsigned int *num_tx_queues,
+ unsigned int *real_num_tx_queues)
+{
+ if (tb[IFLA_NTXQ]) {
+ *num_tx_queues = nla_get_u32(tb[IFLA_NTXQ]);
+ if (*num_tx_queues < 1)
+ return -EINVAL;
+ *real_num_tx_queues = *num_tx_queues;
+ } else {
+ *num_tx_queues = numtxqs;
+ *real_num_tx_queues = numtxqs;
+ }
+
+ return 0;
+}
+
static struct rtnl_link_ops ifb_link_ops __read_mostly = {
.kind = "ifb",
- .priv_size = sizeof(struct ifb_private),
.setup = ifb_setup,
.validate = ifb_validate,
+ .get_tx_queues = ifb_get_tx_queues,
+ .priv_size = sizeof(struct ifb_private),
};
-/* Number of ifb devices to be set up by this module. */
-module_param(numifbs, int, 0);
-MODULE_PARM_DESC(numifbs, "Number of ifb devices");
-
static int __init ifb_init_one(int index)
{
struct net_device *dev_ifb;
int err;
- dev_ifb = alloc_netdev(sizeof(struct ifb_private),
- "ifb%d", ifb_setup);
-
+ dev_ifb = alloc_netdev_mq(sizeof(struct ifb_private), "ifb%d",
+ ifb_setup, numtxqs);
if (!dev_ifb)
return -ENOMEM;
@@ -268,9 +486,12 @@ static int __init ifb_init_module(void)
{
int i, err;
+ if (numtxqs < 1)
+ return -EINVAL;
+
+ get_random_bytes(&simple_tx_hashrnd, 4);
rtnl_lock();
err = __rtnl_link_register(&ifb_link_ops);
-
for (i = 0; i < numifbs && !err; i++)
err = ifb_init_one(i);
if (err)
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 1d3b242..99da411 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -78,6 +78,7 @@ enum {
#define IFLA_LINKINFO IFLA_LINKINFO
IFLA_NET_NS_PID,
IFLA_IFALIAS,
+ IFLA_NTXQ,
__IFLA_MAX
};
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 33148a5..1cbe555 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -597,6 +597,7 @@ static inline size_t if_nlmsg_size(const struct net_device *dev)
+ nla_total_size(4) /* IFLA_MASTER */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ + nla_total_size(4) /* IFLA_NTXQ */
+ rtnl_link_get_size(dev); /* IFLA_LINKINFO */
}
@@ -627,6 +628,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
netif_running(dev) ? dev->operstate : IF_OPER_DOWN);
NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode);
NLA_PUT_U32(skb, IFLA_MTU, dev->mtu);
+ NLA_PUT_U32(skb, IFLA_NTXQ, dev->real_num_tx_queues);
if (dev->ifindex != dev->iflink)
NLA_PUT_U32(skb, IFLA_LINK, dev->iflink);
@@ -725,6 +727,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_LINKINFO] = { .type = NLA_NESTED },
[IFLA_NET_NS_PID] = { .type = NLA_U32 },
[IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 },
+ [IFLA_NTXQ] = { .type = NLA_U32 },
};
EXPORT_SYMBOL(ifla_policy);
^ permalink raw reply related
* Re: [PATCH] ifb: add multi-queue support
From: Changli Gao @ 2009-11-13 4:46 UTC (permalink / raw)
To: David S. Miller, Stephen Hemminger, Patrick McHardy
Cc: xiaosuo, Eric Dumazet, Tom Herbert, netdev
In-Reply-To: <4AFCE3CB.5030201@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1102 bytes --]
2009/11/13 Changli Gao <xiaosuo@gmail.com>:
> ifb: add multi-queue support
>
> Add multi-queue support, and one kernel thread is created for per queue.
> It can used to emulate multi-queue NIC in software, and distribute work
> among CPUs.
> gentux linux # modprobe ifb numtxqs=2
> gentux linux # ifconfig ifb0 up
> gentux linux # pgrep ifb0
> 18508
> 18509
> gentux linux # taskset -p 1 18508
> pid 18508's current affinity mask: 3
> pid 18508's new affinity mask: 1
> gentux linux # taskset -p 2 18509
> pid 18509's current affinity mask: 3
> pid 18509's new affinity mask: 2
> gentux linux # tc qdisc add dev br0 ingress
> gentux linux # tc filter add dev br0 parent ffff: protocol ip basic
> action mirred egress redirect dev ifb0
>
> This patch also introduces a ip link option "numtxqs" for specifying the
> number of the TX queues. so you can add a new ifb with the command:
>
> ip link add numtxqs 4 type ifb
>
> Signed-off-by: Changli Gao <xiaosuo@gmail.com>
> ----
the corresponding iproute2 patch is attached.
--
Regards，
Changli Gao(xiaosuo@gmail.com)
[-- Attachment #2: iproute2-support-numtxqs.diff --]
[-- Type: application/octet-stream, Size: 1628 bytes --]
--- ip/iplink.c.orig 2009-11-11 16:56:41.000000000 +0800
+++ ip/iplink.c 2009-11-12 14:57:25.000000000 +0800
@@ -48,6 +48,7 @@
fprintf(stderr, " [ address LLADDR ]\n");
fprintf(stderr, " [ broadcast LLADDR ]\n");
fprintf(stderr, " [ mtu MTU ]\n");
+ fprintf(stderr, " [ numtxqs NUMTXQS ]\n");
fprintf(stderr, " type TYPE [ ARGS ]\n");
fprintf(stderr, " ip link delete DEV type TYPE [ ARGS ]\n");
fprintf(stderr, "\n");
@@ -180,6 +181,7 @@
int qlen = -1;
int mtu = -1;
int netns = -1;
+ int numtxqs = -1;
ret = argc;
@@ -221,6 +223,13 @@
if (get_integer(&mtu, *argv, 0))
invarg("Invalid \"mtu\" value\n", *argv);
addattr_l(&req->n, sizeof(*req), IFLA_MTU, &mtu, 4);
+ } else if (strcmp(*argv, "numtxqs") == 0) {
+ NEXT_ARG();
+ if (numtxqs != -1)
+ duparg("numtxqs", *argv);
+ if (get_integer(&numtxqs, *argv, 0))
+ invarg("Invalid \"numtxqs\" value\n", *argv);
+ addattr_l(&req->n, sizeof(*req), IFLA_NTXQ, &numtxqs, 4);
} else if (strcmp(*argv, "netns") == 0) {
NEXT_ARG();
if (netns != -1)
--- ip/ipaddress.c.orig 2009-11-13 12:00:33.000000000 +0800
+++ ip/ipaddress.c 2009-11-13 12:04:14.000000000 +0800
@@ -255,6 +255,9 @@
if (filter.showqueue)
print_queuelen(fp, (char*)RTA_DATA(tb[IFLA_IFNAME]));
+ if (tb[IFLA_NTXQ])
+ fprintf(fp, " numtxqs %d", *(unsigned int*)RTA_DATA(tb[IFLA_NTXQ]));
+
if (!filter.family || filter.family == AF_PACKET) {
SPRINT_BUF(b1);
fprintf(fp, "%s", _SL_);
^ permalink raw reply
* [net-next-2.6 PATCH] ixgbe: Flush the LSC mask change to prevent repeated interrupts
From: Jeff Kirsher @ 2009-11-13 4:47 UTC (permalink / raw)
To: davem; +Cc: netdev, gospo, Shannon Nelson, Jeff Kirsher
From: Nelson, Shannon <shannon.nelson@intel.com>
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ixgbe/ixgbe_main.c | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index afd49e0..0489286 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -1204,6 +1204,7 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter)
adapter->link_check_timeout = jiffies;
if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_EIMC_LSC);
+ IXGBE_WRITE_FLUSH(hw);
schedule_work(&adapter->watchdog_task);
}
}
^ permalink raw reply related
* [net-next-2.6 PATCH v6 4/7 RFC] TCPCT part 1d: define TCP cookie option, extend existing struct's
From: William Allen Simpson @ 2009-11-13 4:53 UTC (permalink / raw)
To: Linux Kernel Network Developers
In-Reply-To: <4AFCDA9E.8050003@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1702 bytes --]
Data structures are carefully composed to require minimal additions.
For example, the struct tcp_options_received cookie_plus variable fits
between existing 16-bit and 8-bit variables, requiring no additional
space (taking alignment into consideration). There are no additions to
tcp_request_sock, and only 1 pointer in tcp_sock.
This is a significantly revised implementation of an earlier (year-old)
patch that no longer applies cleanly, with permission of the original
author (Adam Langley):
http://thread.gmane.org/gmane.linux.network/102586
The principle difference is using a TCP option to carry the cookie nonce,
instead of a user configured offset in the data. This is more flexible and
less subject to user configuration error. Such a cookie option has been
suggested for many years, and is also useful without SYN data, allowing
several related concepts to use the same extension option.
"Re: SYN floods (was: does history repeat itself?)", September 9, 1996.
http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html
"Re: what a new TCP header might look like", May 12, 1998.
ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail
These functions will also be used in subsequent patches that implement
additional features.
Requires:
TCPCT part 1a: add request_values parameter for sending SYNACK
TCPCT part 1b: generate Responder Cookie
TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS
Signed-off-by: William.Allen.Simpson@gmail.com
---
include/linux/tcp.h | 29 ++++++++++++++++----
include/net/tcp.h | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 95 insertions(+), 6 deletions(-)
[-- Attachment #2: TCPCT+1d6.patch --]
[-- Type: text/plain, Size: 6048 bytes --]
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index eaa3113..6c5ff66 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -247,31 +247,38 @@ struct tcp_options_received {
sack_ok : 4, /* SACK seen on SYN packet */
snd_wscale : 4, /* Window scaling received from sender */
rcv_wscale : 4; /* Window scaling to send to receiver */
-/* SACKs data */
+ u8 cookie_plus:6, /* bytes in authenticator/cookie option */
+ cookie_out_never:1,
+ cookie_in_always:1;
u8 num_sacks; /* Number of SACK blocks */
- u16 user_mss; /* mss requested by user in ioctl */
+ u16 user_mss; /* mss requested by user in ioctl */
u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
};
static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
{
- rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+ rx_opt->tstamp_ok = rx_opt->sack_ok = 0;
+ rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+ rx_opt->cookie_plus = 0;
}
/* This is the max number of SACKS that we'll generate and process. It's safe
- * to increse this, although since:
+ * to increase this, although since:
* size = TCPOLEN_SACK_BASE_ALIGNED (4) + n * TCPOLEN_SACK_PERBLOCK (8)
* only four options will fit in a standard TCP header */
#define TCP_NUM_SACKS 4
+struct tcp_cookie_values;
+struct tcp_request_sock_ops;
+
struct tcp_request_sock {
struct inet_request_sock req;
#ifdef CONFIG_TCP_MD5SIG
/* Only used by TCP MD5 Signature so far. */
const struct tcp_request_sock_ops *af_specific;
#endif
- u32 rcv_isn;
- u32 snt_isn;
+ u32 rcv_isn;
+ u32 snt_isn;
};
static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
@@ -441,6 +448,12 @@ struct tcp_sock {
/* TCP MD5 Signature Option information */
struct tcp_md5sig_info *md5sig_info;
#endif
+
+ /* When the cookie options are generated and exchanged, then this
+ * object holds a reference to them (cookie_values->kref). Also
+ * contains related tcp_cookie_transactions fields.
+ */
+ struct tcp_cookie_values *cookie_values;
};
static inline struct tcp_sock *tcp_sk(const struct sock *sk)
@@ -459,6 +472,10 @@ struct tcp_timewait_sock {
u16 tw_md5_keylen;
u8 tw_md5_key[TCP_MD5SIG_MAXKEYLEN];
#endif
+ /* Few sockets in timewait have cookies; in that case, then this
+ * object holds a reference to them (tw_cookie_values->kref).
+ */
+ struct tcp_cookie_values *tw_cookie_values;
};
static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 738b65f..3a4c840 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -30,6 +30,7 @@
#include <linux/dmaengine.h>
#include <linux/crypto.h>
#include <linux/cryptohash.h>
+#include <linux/kref.h>
#include <net/inet_connection_sock.h>
#include <net/inet_timewait_sock.h>
@@ -164,6 +165,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOPT_SACK 5 /* SACK Block */
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
+#define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */
/*
* TCP option lengths
@@ -174,6 +176,10 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOLEN_SACK_PERM 2
#define TCPOLEN_TIMESTAMP 10
#define TCPOLEN_MD5SIG 18
+#define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */
+#define TCPOLEN_COOKIE_PAIR 3 /* Cookie pair header extension */
+#define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN)
+#define TCPOLEN_COOKIE_MAX (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MAX)
/* But this is what stacks really send out. */
#define TCPOLEN_TSTAMP_ALIGNED 12
@@ -1482,6 +1488,72 @@ struct tcp_request_sock_ops {
extern int tcp_cookie_generator(u32 *bakery);
+/**
+ * A tcp_sock contains a pointer to the current value, and this is cloned to
+ * the tcp_timewait_sock.
+ *
+ * @cookie_pair: variable data from the option exchange.
+ *
+ * @cookie_desired: user specified tcpct_cookie_desired. Zero
+ * indicates default (sysctl_tcp_cookie_size).
+ * After cookie sent, remembers size of cookie.
+ * Range 0, TCP_COOKIE_MIN to TCP_COOKIE_MAX.
+ *
+ * @s_data_desired: user specified tcpct_s_data_desired. When the
+ * constant payload is specified (@s_data_constant),
+ * holds its length instead.
+ * Range 0 to TCP_MSS_DESIRED.
+ *
+ * @s_data_payload: constant data that is to be included in the
+ * payload of SYN or SYNACK segments when the
+ * cookie option is present.
+ */
+struct tcp_cookie_values {
+ struct kref kref;
+ u8 cookie_pair[TCP_COOKIE_PAIR_SIZE];
+ u8 cookie_pair_size;
+ u8 cookie_desired;
+ u16 s_data_desired:11,
+ s_data_constant:1,
+ s_data_in:1,
+ s_data_out:1,
+ s_data_unused:2;
+ u8 s_data_payload[0];
+};
+
+static inline void tcp_cookie_values_release(struct kref *kref)
+{
+ kfree(container_of(kref, struct tcp_cookie_values, kref));
+}
+
+/* The length of constant payload data. Note that s_data_desired is
+ * overloaded, depending on s_data_constant: either the length of constant
+ * data (returned here) or the limit on variable data.
+ */
+static inline int tcp_s_data_size(const struct tcp_sock *tp)
+{
+ return (tp->cookie_values != NULL && tp->cookie_values->s_data_constant)
+ ? tp->cookie_values->s_data_desired
+ : 0;
+}
+
+/* As tcp_request_sock has already been extended in other places, the
+ * only remaining method is to pass stack values along as function
+ * parameters. These parameters are not needed after sending SYNACK.
+ */
+struct tcp_extend_values {
+ struct request_values rv;
+ u32 cookie_bakery[COOKIE_WORKSPACE_WORDS];
+ u8 cookie_plus:6,
+ cookie_out_never:1,
+ cookie_in_always:1;
+};
+
+static inline struct tcp_extend_values *tcp_xv(struct request_values *rvp)
+{
+ return (struct tcp_extend_values *)rvp;
+}
+
extern void tcp_v4_init(void);
extern void tcp_init(void);
--
1.6.3.3
^ permalink raw reply related
* Re: [net-next-2.6 PATCH v6 1/7 RFC] TCPCT part 1a: add request_values parameter for sending SYNACK
From: Ilpo Järvinen @ 2009-11-13 4:54 UTC (permalink / raw)
To: William Allen Simpson; +Cc: Linux Kernel Network Developers
In-Reply-To: <4AFCDB9D.6050804@gmail.com>
On Thu, 12 Nov 2009, William Allen Simpson wrote:
> Add optional function parameters associated with sending SYNACK.
> These parameters are not needed after sending SYNACK, and are not
> used for retransmission. Avoids extending struct tcp_request_sock,
> and avoids allocating kernel memory.
>
> Also affects DCCP as it uses common struct request_sock_ops,
> but this parameter is currently reserved for future use.
>
> Signed-off-by: William.Allen.Simpson@gmail.com
> Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
> ---
> include/net/request_sock.h | 8 +++++++-
> include/net/tcp.h | 3 ++-
> net/dccp/ipv4.c | 5 +++--
> net/dccp/ipv6.c | 5 +++--
> net/dccp/minisocks.c | 2 +-
> net/ipv4/inet_connection_sock.c | 2 +-
> net/ipv4/tcp_ipv4.c | 19 +++++++++++--------
> net/ipv4/tcp_minisocks.c | 2 +-
> net/ipv4/tcp_output.c | 3 ++-
> net/ipv6/tcp_ipv6.c | 28 +++++++++++++---------------
> 10 files changed, 44 insertions(+), 33 deletions(-)
>
> diff --git a/include/net/request_sock.h b/include/net/request_sock.h
> index c719084..c9b50eb 100644
> --- a/include/net/request_sock.h
> +++ b/include/net/request_sock.h
> @@ -27,13 +27,19 @@ struct sk_buff;
> struct dst_entry;
> struct proto;
>
> +/* empty to "strongly type" an otherwise void parameter.
> + */
> +struct request_values {
> +};
> +
> struct request_sock_ops {
> int family;
> int obj_size;
> struct kmem_cache *slab;
> char *slab_name;
> int (*rtx_syn_ack)(struct sock *sk,
> - struct request_sock *req);
> + struct request_sock *req,
> + struct request_values *rvp);
> void (*send_ack)(struct sock *sk, struct sk_buff *skb,
> struct request_sock *req);
> void (*send_reset)(struct sock *sk,
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 325bfcf..ec183fd 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -440,7 +440,8 @@ extern int tcp_connect(struct sock *sk);
>
> extern struct sk_buff * tcp_make_synack(struct sock *sk,
> struct dst_entry *dst,
> - struct request_sock *req);
> + struct request_sock *req,
> + struct request_values *rvp);
>
> extern int tcp_disconnect(struct sock *sk, int flags);
>
> diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
> index 2423a08..efbcfdc 100644
> --- a/net/dccp/ipv4.c
> +++ b/net/dccp/ipv4.c
> @@ -477,7 +477,8 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
> return &rt->u.dst;
> }
>
> -static int dccp_v4_send_response(struct sock *sk, struct request_sock *req)
> +static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
> + struct request_values *rv_unused)
> {
> int err = -1;
> struct sk_buff *skb;
> @@ -626,7 +627,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
> dreq->dreq_iss = dccp_v4_init_sequence(skb);
> dreq->dreq_service = service;
>
> - if (dccp_v4_send_response(sk, req))
> + if (dccp_v4_send_response(sk, req, NULL))
> goto drop_and_free;
>
> inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
> diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
> index 50ea91a..6574215 100644
> --- a/net/dccp/ipv6.c
> +++ b/net/dccp/ipv6.c
> @@ -241,7 +241,8 @@ out:
> }
>
>
> -static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
> +static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
> + struct request_values *rv_unused)
> {
> struct inet6_request_sock *ireq6 = inet6_rsk(req);
> struct ipv6_pinfo *np = inet6_sk(sk);
> @@ -468,7 +469,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
> dreq->dreq_iss = dccp_v6_init_sequence(skb);
> dreq->dreq_service = service;
>
> - if (dccp_v6_send_response(sk, req))
> + if (dccp_v6_send_response(sk, req, NULL))
> goto drop_and_free;
>
> inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
> diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
> index 5ca49ce..af226a0 100644
> --- a/net/dccp/minisocks.c
> +++ b/net/dccp/minisocks.c
> @@ -184,7 +184,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
> * counter (backoff, monitored by dccp_response_timer).
> */
> req->retrans++;
> - req->rsk_ops->rtx_syn_ack(sk, req);
> + req->rsk_ops->rtx_syn_ack(sk, req, NULL);
> }
> /* Network Duplicate, discard packet */
> return NULL;
> diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
> index 26fb50e..ad098d6 100644
> --- a/net/ipv4/inet_connection_sock.c
> +++ b/net/ipv4/inet_connection_sock.c
> @@ -531,7 +531,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
> &expire, &resend);
> if (!expire &&
> (!resend ||
> - !req->rsk_ops->rtx_syn_ack(parent, req) ||
> + !req->rsk_ops->rtx_syn_ack(parent, req, NULL) ||
> inet_rsk(req)->acked)) {
> unsigned long timeo;
>
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index cf7f208..094231b 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -742,8 +742,9 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
> * This still operates on a request_sock only, not on a big
> * socket.
> */
> -static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
> - struct dst_entry *dst)
> +static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
> + struct request_sock *req,
> + struct request_values *rvp)
> {
> const struct inet_request_sock *ireq = inet_rsk(req);
> int err = -1;
> @@ -753,7 +754,7 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
> if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
> return -1;
>
> - skb = tcp_make_synack(sk, dst, req);
> + skb = tcp_make_synack(sk, dst, req, rvp);
>
> if (skb) {
> struct tcphdr *th = tcp_hdr(skb);
> @@ -774,9 +775,10 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
> return err;
> }
>
> -static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req)
> +static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
> + struct request_values *rvp)
> {
> - return __tcp_v4_send_synack(sk, req, NULL);
> + return __tcp_v4_send_synack(sk, NULL, req, rvp);
> }
>
> /*
> @@ -1211,13 +1213,13 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = {
>
> int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
> {
> - struct inet_request_sock *ireq;
> struct tcp_options_received tmp_opt;
> struct request_sock *req;
> + struct inet_request_sock *ireq;
> + struct dst_entry *dst = NULL;
> __be32 saddr = ip_hdr(skb)->saddr;
> __be32 daddr = ip_hdr(skb)->daddr;
> __u32 isn = TCP_SKB_CB(skb)->when;
> - struct dst_entry *dst = NULL;
> #ifdef CONFIG_SYN_COOKIES
> int want_cookie = 0;
> #else
> @@ -1337,7 +1339,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
> }
> tcp_rsk(req)->snt_isn = isn;
>
> - if (__tcp_v4_send_synack(sk, req, dst) || want_cookie)
> + if (__tcp_v4_send_synack(sk, dst, req, NULL)
> + || want_cookie)
> goto drop_and_free;
>
> inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
> diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
> index 4be2228..7a42990 100644
> --- a/net/ipv4/tcp_minisocks.c
> +++ b/net/ipv4/tcp_minisocks.c
> @@ -537,7 +537,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
> * Enforce "SYN-ACK" according to figure 8, figure 6
> * of RFC793, fixed by RFC1122.
> */
> - req->rsk_ops->rtx_syn_ack(sk, req);
> + req->rsk_ops->rtx_syn_ack(sk, req, NULL);
> return NULL;
> }
>
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index 616c686..1151cb8 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -2224,7 +2224,8 @@ int tcp_send_synack(struct sock *sk)
>
> /* Prepare a SYN-ACK. */
> struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
> - struct request_sock *req)
> + struct request_sock *req,
> + struct request_values *rvp)
> {
> struct inet_request_sock *ireq = inet_rsk(req);
> struct tcp_sock *tp = tcp_sk(sk);
> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> index de70909..3e327bc 100644
> --- a/net/ipv6/tcp_ipv6.c
> +++ b/net/ipv6/tcp_ipv6.c
> @@ -461,7 +461,8 @@ out:
> }
>
>
> -static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req)
> +static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
> + struct request_values *rvp)
> {
> struct inet6_request_sock *treq = inet6_rsk(req);
> struct ipv6_pinfo *np = inet6_sk(sk);
> @@ -499,7 +500,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req)
> if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
> goto done;
>
> - skb = tcp_make_synack(sk, dst, req);
> + skb = tcp_make_synack(sk, dst, req, rvp);
> if (skb) {
> struct tcphdr *th = tcp_hdr(skb);
>
> @@ -1161,13 +1162,13 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
> */
> static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
> {
> + struct tcp_options_received tmp_opt;
> + struct request_sock *req;
> struct inet6_request_sock *treq;
> struct ipv6_pinfo *np = inet6_sk(sk);
> - struct tcp_options_received tmp_opt;
> struct tcp_sock *tp = tcp_sk(sk);
> - struct request_sock *req = NULL;
> - __u32 isn = TCP_SKB_CB(skb)->when;
> struct dst_entry *dst = __sk_dst_get(sk);
> + __u32 isn = TCP_SKB_CB(skb)->when;
> #ifdef CONFIG_SYN_COOKIES
> int want_cookie = 0;
> #else
> @@ -1239,23 +1240,20 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
>
> isn = tcp_v6_init_sequence(skb);
> }
> -
> tcp_rsk(req)->snt_isn = isn;
>
> security_inet_conn_request(sk, skb, req);
>
> - if (tcp_v6_send_synack(sk, req))
> - goto drop;
> + if (tcp_v6_send_synack(sk, req, NULL)
> + || want_cookie)
This fits to one line very well. There were other unnecessary line-breaks
too (might have been in another patch than this).
However, in cases where you really would have to split lines in if
statement. Please move || (or &&) to the end of the previous line and use
matching indent level on the line below (in this example the text is
matching already, so it is just about converting || into spaces here).
...As was mentioned by somebody already earlier.
Splitting of 1-3 is quite ok, the rest haven't arrived yet.
> + goto drop_and_free;
>
> - if (!want_cookie) {
> - inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
> - return 0;
> - }
> + inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
> + return 0;
>
> +drop_and_free:
> + reqsk_free(req);
> drop:
> - if (req)
> - reqsk_free(req);
> -
> return 0; /* don't send reset */
> }
>
> --
> 1.6.3.3
>
--
i.
^ permalink raw reply
* Re: Subject: [PATCH 5/6] bna: Brocade 10Gb Ethernet device driver
From: Stephen Hemminger @ 2009-11-13 5:03 UTC (permalink / raw)
To: Rasesh Mody; +Cc: netdev, adapter_linux_open_src_team
In-Reply-To: <200911130346.nAD3kquT001065@blc-10-10.brocade.com>
On Thu, 12 Nov 2009 19:46:52 -0800
Rasesh Mody <rmody@brocade.com> wrote:
> +#define bfa_cb_queue(__bfa, __hcb_qe, __cbfn, __cbarg) do { \
> + (__hcb_qe)->cbfn = (__cbfn); \
> + (__hcb_qe)->cbarg = (__cbarg); \
> + list_add_tail(&(__hcb_qe)->qe, &(__bfa)->comp_q); \
> +} while (0)
> +
> +#define bfa_cb_dequeue(__hcb_qe) list_del(&(__hcb_qe)->qe)
> +
> +#define bfa_cb_queue_once(__bfa, __hcb_qe, __cbfn, __cbarg) do { \
> + (__hcb_qe)->cbfn = (__cbfn); \
> + (__hcb_qe)->cbarg = (__cbarg); \
> + if (!(__hcb_qe)->once) { \
> + list_add_tail((__hcb_qe), &(__bfa)->comp_q); \
> + (__hcb_qe)->once = true; \
> + } \
> +} while (0)
> +
> +#define bfa_cb_queue_done(__hcb_qe) do { \
> + (__hcb_qe)->once = false; \
> +} while (0)
> +
Could these be inline functions or are they typeless macros?
--
^ permalink raw reply
* [net-next-2.6 PATCH] net: fast consecutive name allocation
From: Octavian Purdila @ 2009-11-13 5:01 UTC (permalink / raw)
To: netdev
[-- Attachment #1: Type: text/plain, Size: 621 bytes --]
This patch speeds up the network device name allocation for the case
where a significant number of devices of the same type are created
consecutively.
Tests performed on a PPC750 @ 800Mhz machine with per device sysctl
and sysfs entries disabled:
Without the patch With the patch
real 0m 43.43s real 0m 0.49s
user 0m 0.00s user 0m 0.00s
sys 0m 43.43s sys 0m 0.48s
Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
---
include/net/net_namespace.h | 3 +++
net/core/dev.c | 23 ++++++++++++++++++++++-
2 files changed, 25 insertions(+), 1 deletions(-)
[-- Attachment #2: 3ad8e007a0c929204c3ee7e7afa309e2e53b5b8a.diff --]
[-- Type: text/x-patch, Size: 2073 bytes --]
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 0addd45..39c65a2 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -56,6 +56,9 @@ struct net {
struct list_head dev_base_head;
struct hlist_head *dev_name_head;
struct hlist_head *dev_index_head;
+ /* fast consecutive name allocation (e.g. eth0, eth1, ...) */
+ char fcna_name[IFNAMSIZ];
+ int fcna_no;
/* core fib_rules */
struct list_head rules_ops;
diff --git a/net/core/dev.c b/net/core/dev.c
index ad8e320..008e3c7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -226,8 +226,12 @@ static int list_netdevice(struct net_device *dev)
*/
static void unlist_netdevice(struct net_device *dev)
{
+ struct net *net = dev_net(dev);
+
ASSERT_RTNL();
+ net->fcna_no = -1;
+
/* Unlink dev from the device chain */
write_lock_bh(&dev_base_lock);
list_del_rcu(&dev->dev_list);
@@ -872,6 +876,16 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
if (p[1] != 'd' || strchr(p + 2, '%'))
return -EINVAL;
+ /* avoid fast allocation for strange templates like "fan%dcy" */
+ if (net->fcna_no >= 0 && p[2] == 0 &&
+ net->fcna_name[p - name] == 0 &&
+ memcmp(name, net->fcna_name, p - name) == 0) {
+ snprintf(buf, IFNAMSIZ, name, ++net->fcna_no);
+ if (!__dev_get_by_name(net, buf))
+ return net->fcna_no;
+ net->fcna_no = -1;
+ }
+
/* Use one page as a bit array of possible slots */
inuse = (unsigned long *) get_zeroed_page(GFP_ATOMIC);
if (!inuse)
@@ -894,8 +908,15 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
}
snprintf(buf, IFNAMSIZ, name, i);
- if (!__dev_get_by_name(net, buf))
+ if (!__dev_get_by_name(net, buf)) {
+ if (p[2] == 0) {
+ memcpy(net->fcna_name, name, p - name);
+ net->fcna_name[p - name] = 0;
+ net->fcna_no = i;
+ } else
+ net->fcna_no = -1;
return i;
+ }
/* It is possible to run out of possible slots
* when the name is long and there isn't enough space left
^ permalink raw reply related
* Re: Subject: [PATCH 3/6] bna: Brocade 10Gb Ethernet device driver
From: Stephen Hemminger @ 2009-11-13 5:05 UTC (permalink / raw)
To: Rasesh Mody; +Cc: netdev, adapter_linux_open_src_team
In-Reply-To: <200911130346.nAD3kqsL001058@blc-10-10.brocade.com>
On Thu, 12 Nov 2009 19:46:52 -0800
Rasesh Mody <rmody@brocade.com> wrote:
> +
> +#ifndef __BIGENDIAN
> +#define bna_dma_addr64(_x) swab64((_x))
> +#else
> +#define bna_dma_addr64(_x) (_x)
> +#endif
> +
This should be cpu_to_le64 and any data with byte order
dependency should be declared leXX etc. Then sparse tool can
check for misuse of endian.
--
^ permalink raw reply
* Re: Subject: [PATCH 5/6] bna: Brocade 10Gb Ethernet device driver
From: Stephen Hemminger @ 2009-11-13 5:07 UTC (permalink / raw)
To: Rasesh Mody; +Cc: netdev, adapter_linux_open_src_team
In-Reply-To: <200911130346.nAD3kquT001065@blc-10-10.brocade.com>
On Thu, 12 Nov 2009 19:46:52 -0800
Rasesh Mody <rmody@brocade.com> wrote:
> +
> +#define wwn_t u64
> +#define lun_t u64
No need for obfuscation, at least use a typedef.
> +
> +#define WWN_NULL (0)
Why is NULL not good enuf
> +#define FC_SYMNAME_MAX 256 /* max name server symbolic name size */
> +#define FC_ALPA_MAX 128
> +
> +#pragma pack(1)
> +
> +#define MAC_ADDRLEN (6)
> +struct mac { u8 mac[MAC_ADDRLEN]; };
Cant you use ETH_ALEN instead?
--
^ permalink raw reply
* Re: Subject: [PATCH 2/6] bna: Brocade 10Gb Ethernet device driver
From: Stephen Hemminger @ 2009-11-13 5:08 UTC (permalink / raw)
To: Rasesh Mody; +Cc: netdev, adapter_linux_open_src_team
In-Reply-To: <200911130346.nAD3kqjM001055@blc-10-10.brocade.com>
On Thu, 12 Nov 2009 19:46:52 -0800
Rasesh Mody <rmody@brocade.com> wrote:
> +/*
> + * Copyright (c) 2006-2009 Brocade Communications Systems, Inc.
> + * All rights reserved
> + * www.brocade.com
> + *
> + * See LICENSE.bna for copyright and licensing details.
> + */
> +
I don't see LICENSE.bna in any of the patches.
--
^ permalink raw reply
* [net-next-2.6 PATCH v6 5/7 RFC] TCPCT part 1e: implement socket option TCP_COOKIE_TRANSACTIONS
From: William Allen Simpson @ 2009-11-13 5:10 UTC (permalink / raw)
To: Linux Kernel Network Developers
In-Reply-To: <4AFCDA9E.8050003@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 868 bytes --]
Provide per socket control of the TCP cookie option and SYN/SYNACK data.
This is a straightforward re-implementation of an earlier (year-old)
patch that no longer applies cleanly, with permission of the original
author (Adam Langley):
http://thread.gmane.org/gmane.linux.network/102586
The principle difference is using a TCP option to carry the cookie nonce,
instead of a user configured offset in the data.
Allocations have been rearranged to avoid requiring GFP_ATOMIC.
Requires:
net: TCP_MSS_DEFAULT, TCP_MSS_DESIRED
TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS
TCPCT part 1d: define TCP cookie option, extend existing struct's
Signed-off-by: William.Allen.Simpson@gmail.com
---
net/ipv4/tcp.c | 133 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 files changed, 131 insertions(+), 2 deletions(-)
[-- Attachment #2: TCPCT+1e6.patch --]
[-- Type: text/plain, Size: 4406 bytes --]
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3ae01bf..3424499 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2079,8 +2079,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
int val;
int err = 0;
- /* This is a string value all the others are int's */
- if (optname == TCP_CONGESTION) {
+ /* These are data/string values, all the others are ints */
+ switch (optname) {
+ case TCP_CONGESTION: {
char name[TCP_CA_NAME_MAX];
if (optlen < 1)
@@ -2097,6 +2098,93 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
release_sock(sk);
return err;
}
+ case TCP_COOKIE_TRANSACTIONS: {
+ struct tcp_cookie_transactions ctd;
+ struct tcp_cookie_values *cvp = NULL;
+
+ if (sizeof(ctd) > optlen)
+ return -EINVAL;
+ if (copy_from_user(&ctd, optval, sizeof(ctd)))
+ return -EFAULT;
+
+ if (ctd.tcpct_used > sizeof(ctd.tcpct_value)
+ || ctd.tcpct_s_data_desired > TCP_MSS_DESIRED)
+ return -EINVAL;
+
+ if (ctd.tcpct_cookie_desired == 0) {
+ /* default to global value */
+ } else if ((0x1 & ctd.tcpct_cookie_desired)
+ || ctd.tcpct_cookie_desired > TCP_COOKIE_MAX
+ || ctd.tcpct_cookie_desired < TCP_COOKIE_MIN) {
+ return -EINVAL;
+ }
+
+ if (TCP_COOKIE_OUT_NEVER & ctd.tcpct_flags) {
+ /* Supercedes all other values */
+ lock_sock(sk);
+ if (tp->cookie_values != NULL) {
+ kref_put(&tp->cookie_values->kref,
+ tcp_cookie_values_release);
+ tp->cookie_values = NULL;
+ }
+ tp->rx_opt.cookie_in_always = 0; /* false */
+ tp->rx_opt.cookie_out_never = 1; /* true */
+ release_sock(sk);
+ return err;
+ }
+
+ /* Allocate ancillary memory before locking.
+ */
+ if (ctd.tcpct_used > 0
+ || (tp->cookie_values == NULL
+ && (sysctl_tcp_cookie_size > 0
+ || ctd.tcpct_cookie_desired > 0
+ || ctd.tcpct_s_data_desired > 0))) {
+ cvp = kzalloc(sizeof(*cvp) + ctd.tcpct_used,
+ GFP_KERNEL);
+ if (cvp == NULL)
+ return -ENOMEM;
+ }
+ lock_sock(sk);
+ tp->rx_opt.cookie_in_always =
+ (TCP_COOKIE_IN_ALWAYS & ctd.tcpct_flags);
+ tp->rx_opt.cookie_out_never = 0; /* false */
+
+ if (tp->cookie_values != NULL) {
+ if (cvp != NULL) {
+ /* Changed values are recorded by a changed
+ * pointer, ensuring the cookie will differ,
+ * without separately hashing each value later.
+ */
+ kref_put(&tp->cookie_values->kref,
+ tcp_cookie_values_release);
+ kref_init(&cvp->kref);
+ tp->cookie_values = cvp;
+ } else {
+ cvp = tp->cookie_values;
+ }
+ }
+ if (cvp != NULL) {
+ cvp->cookie_desired = ctd.tcpct_cookie_desired;
+
+ if (ctd.tcpct_used > 0) {
+ memcpy(cvp->s_data_payload, ctd.tcpct_value,
+ ctd.tcpct_used);
+ cvp->s_data_desired = ctd.tcpct_used;
+ cvp->s_data_constant = 1; /* true */
+ } else {
+ /* No constant payload data. */
+ cvp->s_data_desired = ctd.tcpct_s_data_desired;
+ cvp->s_data_constant = 0; /* false */
+ }
+ }
+ release_sock(sk);
+ return err;
+ }
+ default:
+ /* fallthru */
+ break;
+ };
if (optlen < sizeof(int))
return -EINVAL;
@@ -2421,6 +2509,47 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
if (copy_to_user(optval, icsk->icsk_ca_ops->name, len))
return -EFAULT;
return 0;
+
+ case TCP_COOKIE_TRANSACTIONS: {
+ struct tcp_cookie_transactions ctd;
+ struct tcp_cookie_values *cvp = tp->cookie_values;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+ if (len < sizeof(ctd))
+ return -EINVAL;
+
+ memset(&ctd, 0, sizeof(ctd));
+ ctd.tcpct_flags = (tp->rx_opt.cookie_in_always
+ ? TCP_COOKIE_IN_ALWAYS : 0)
+ + (tp->rx_opt.cookie_out_never
+ ? TCP_COOKIE_OUT_NEVER : 0);
+
+ if (cvp != NULL) {
+ ctd.tcpct_flags += (cvp->s_data_in
+ ? TCP_S_DATA_IN : 0)
+ + (cvp->s_data_out
+ ? TCP_S_DATA_OUT : 0);
+
+ ctd.tcpct_cookie_desired = cvp->cookie_desired;
+ ctd.tcpct_s_data_desired = cvp->s_data_desired;
+
+ /* Cookie(s) saved, return as nonce */
+ if (sizeof(ctd.tcpct_value) < cvp->cookie_pair_size) {
+ /* impossible? */
+ return -EINVAL;
+ }
+ memcpy(&ctd.tcpct_value[0], &cvp->cookie_pair[0],
+ cvp->cookie_pair_size);
+ ctd.tcpct_used = cvp->cookie_pair_size;
+ }
+
+ if (put_user(sizeof(ctd), optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &ctd, sizeof(ctd)))
+ return -EFAULT;
+ return 0;
+ }
default:
return -ENOPROTOOPT;
}
--
1.6.3.3
^ permalink raw reply related
* Re: [net-next-2.6 PATCH] net: fast consecutive name allocation
From: Octavian Purdila @ 2009-11-13 5:20 UTC (permalink / raw)
To: netdev
In-Reply-To: <200911130701.14847.opurdila@ixiacom.com>
On Friday 13 November 2009 07:01:14 you wrote:
> This patch speeds up the network device name allocation for the case
> where a significant number of devices of the same type are created
> consecutively.
>
> Tests performed on a PPC750 @ 800Mhz machine with per device sysctl
> and sysfs entries disabled:
>
> Without the patch With the patch
>
> real 0m 43.43s real 0m 0.49s
> user 0m 0.00s user 0m 0.00s
> sys 0m 43.43s sys 0m 0.48s
>
Oops, pasting root prompts (e.g. # modprobe ....) directly into the git commit message is not a good idea :) Here it is again, with the full commit message.
[net-next-2.6 PATCH] net: fast consecutive name allocation
This patch speeds up the network device name allocation for the case
where a significant number of devices of the same type are created
consecutively.
Tests performed on a PPC750 @ 800Mhz machine with per device sysctl
and sysfs entries disabled:
$ time insmod /lib/modules/dummy.ko numdummies=8000
Without the patch With the patch
real 0m 43.43s real 0m 0.49s
user 0m 0.00s user 0m 0.00s
sys 0m 43.43s sys 0m 0.48s
Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
---
include/net/net_namespace.h | 3 +++
net/core/dev.c | 23 ++++++++++++++++++++++-
2 files changed, 25 insertions(+), 1 deletions(-)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 0addd45..39c65a2 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -56,6 +56,9 @@ struct net {
struct list_head dev_base_head;
struct hlist_head *dev_name_head;
struct hlist_head *dev_index_head;
+ /* fast consecutive name allocation (e.g. eth0, eth1, ...) */
+ char fcna_name[IFNAMSIZ];
+ int fcna_no;
/* core fib_rules */
struct list_head rules_ops;
diff --git a/net/core/dev.c b/net/core/dev.c
index ad8e320..008e3c7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -226,8 +226,12 @@ static int list_netdevice(struct net_device *dev)
*/
static void unlist_netdevice(struct net_device *dev)
{
+ struct net *net = dev_net(dev);
+
ASSERT_RTNL();
+ net->fcna_no = -1;
+
/* Unlink dev from the device chain */
write_lock_bh(&dev_base_lock);
list_del_rcu(&dev->dev_list);
@@ -872,6 +876,16 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
if (p[1] != 'd' || strchr(p + 2, '%'))
return -EINVAL;
+ /* avoid fast allocation for strange templates like "fan%dcy" */
+ if (net->fcna_no >= 0 && p[2] == 0 &&
+ net->fcna_name[p - name] == 0 &&
+ memcmp(name, net->fcna_name, p - name) == 0) {
+ snprintf(buf, IFNAMSIZ, name, ++net->fcna_no);
+ if (!__dev_get_by_name(net, buf))
+ return net->fcna_no;
+ net->fcna_no = -1;
+ }
+
/* Use one page as a bit array of possible slots */
inuse = (unsigned long *) get_zeroed_page(GFP_ATOMIC);
if (!inuse)
@@ -894,8 +908,15 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
}
snprintf(buf, IFNAMSIZ, name, i);
- if (!__dev_get_by_name(net, buf))
+ if (!__dev_get_by_name(net, buf)) {
+ if (p[2] == 0) {
+ memcpy(net->fcna_name, name, p - name);
+ net->fcna_name[p - name] = 0;
+ net->fcna_no = i;
+ } else
+ net->fcna_no = -1;
return i;
+ }
/* It is possible to run out of possible slots
* when the name is long and there isn't enough space left
--
1.5.6.5
^ permalink raw reply related
* [PATCH] act_mirred: cleanup and optimization
From: Changli Gao @ 2009-11-13 5:36 UTC (permalink / raw)
To: Jamal Hadi Salim; +Cc: Stephen Hemminger, David S. Miller, netdev, xiaosuo
act_mirred: cleanup and optimization.
cleanup and optimization.
1. don't let go back using goto.
2. move checking if eaction is valid in tcf_mirred_init().
3. don't call skb_act_clone() until it is necessary.
4. one exit of the critical context.
5. allow eaction is TCA_INGRESS_MIRROR & TCA_INGRESS_REDIR.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
net/sched/act_mirred.c | 121
++++++++++++++++++++++++++-----------------------
1 file changed, 65 insertions(+), 56 deletions(-)
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index b9aaab4..1e8b042 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -8,8 +8,6 @@
*
* Authors: Jamal Hadi Salim (2002-4)
*
- * TODO: Add ingress support (and socket redirect support)
- *
*/
#include <linux/types.h>
@@ -65,52 +63,63 @@ static int tcf_mirred_init(struct nlattr *nla, struct nlattr *est,
struct tc_mirred *parm;
struct tcf_mirred *m;
struct tcf_common *pc;
- struct net_device *dev = NULL;
- int ret = 0, err;
- int ok_push = 0;
+ struct net_device *dev;
+ int ret, ok_push = 0;
if (nla == NULL)
return -EINVAL;
-
- err = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy);
- if (err < 0)
- return err;
-
+ ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy);
+ if (ret < 0)
+ return ret;
if (tb[TCA_MIRRED_PARMS] == NULL)
return -EINVAL;
parm = nla_data(tb[TCA_MIRRED_PARMS]);
-
+ switch (parm->eaction) {
+ case TCA_EGRESS_MIRROR:
+ case TCA_EGRESS_REDIR:
+ case TCA_INGRESS_MIRROR:
+ case TCA_INGRESS_REDIR:
+ break;
+ default:
+ return -EINVAL;
+ }
if (parm->ifindex) {
- dev = __dev_get_by_index(&init_net, parm->ifindex);
+ dev = dev_get_by_index(&init_net, parm->ifindex);
if (dev == NULL)
return -ENODEV;
switch (dev->type) {
- case ARPHRD_TUNNEL:
- case ARPHRD_TUNNEL6:
- case ARPHRD_SIT:
- case ARPHRD_IPGRE:
- case ARPHRD_VOID:
- case ARPHRD_NONE:
- ok_push = 0;
- break;
- default:
- ok_push = 1;
- break;
+ case ARPHRD_TUNNEL:
+ case ARPHRD_TUNNEL6:
+ case ARPHRD_SIT:
+ case ARPHRD_IPGRE:
+ case ARPHRD_VOID:
+ case ARPHRD_NONE:
+ ok_push = 0;
+ break;
+ default:
+ ok_push = 1;
+ break;
}
+ } else {
+ dev = NULL;
}
pc = tcf_hash_check(parm->index, a, bind, &mirred_hash_info);
if (!pc) {
- if (!parm->ifindex)
+ if (dev == NULL)
return -EINVAL;
pc = tcf_hash_create(parm->index, est, a, sizeof(*m), bind,
&mirred_idx_gen, &mirred_hash_info);
- if (IS_ERR(pc))
- return PTR_ERR(pc);
+ if (IS_ERR(pc)) {
+ dev_put(dev);
+ return PTR_ERR(pc);
+ }
ret = ACT_P_CREATED;
} else {
if (!ovr) {
tcf_mirred_release(to_mirred(pc), bind);
+ if (dev != NULL)
+ dev_put(dev);
return -EEXIST;
}
}
@@ -119,12 +128,11 @@ static int tcf_mirred_init(struct nlattr *nla, struct nlattr *est,
spin_lock_bh(&m->tcf_lock);
m->tcf_action = parm->action;
m->tcfm_eaction = parm->eaction;
- if (parm->ifindex) {
+ if (dev != NULL) {
m->tcfm_ifindex = parm->ifindex;
if (ret != ACT_P_CREATED)
dev_put(m->tcfm_dev);
m->tcfm_dev = dev;
- dev_hold(dev);
m->tcfm_ok_push = ok_push;
}
spin_unlock_bh(&m->tcf_lock);
@@ -146,59 +154,60 @@ static int tcf_mirred_cleanup(struct tc_action *a, int bind)
static int tcf_mirred(struct sk_buff *skb, struct tc_action *a,
struct tcf_result *res)
{
- struct tcf_mirred *m = a->priv;
struct net_device *dev;
- struct sk_buff *skb2 = NULL;
- u32 at = G_TC_AT(skb->tc_verd);
+ struct sk_buff *skb2;
+ u32 at;
+ struct tcf_mirred *m = a->priv;
+ int retval, err = 1;
spin_lock(&m->tcf_lock);
-
- dev = m->tcfm_dev;
m->tcf_tm.lastuse = jiffies;
- if (!(dev->flags&IFF_UP) ) {
+ dev = m->tcfm_dev;
+ if (!(dev->flags & IFF_UP) ) {
if (net_ratelimit())
printk("mirred to Houston: device %s is gone!\n",
dev->name);
-bad_mirred:
- if (skb2 != NULL)
- kfree_skb(skb2);
- m->tcf_qstats.overlimits++;
- m->tcf_bstats.bytes += qdisc_pkt_len(skb);
- m->tcf_bstats.packets++;
- spin_unlock(&m->tcf_lock);
- /* should we be asking for packet to be dropped?
- * may make sense for redirect case only
- */
- return TC_ACT_SHOT;
+ goto out;
}
skb2 = skb_act_clone(skb, GFP_ATOMIC);
if (skb2 == NULL)
- goto bad_mirred;
- if (m->tcfm_eaction != TCA_EGRESS_MIRROR &&
- m->tcfm_eaction != TCA_EGRESS_REDIR) {
- if (net_ratelimit())
- printk("tcf_mirred unknown action %d\n",
- m->tcfm_eaction);
- goto bad_mirred;
- }
+ goto out;
m->tcf_bstats.bytes += qdisc_pkt_len(skb2);
m->tcf_bstats.packets++;
- if (!(at & AT_EGRESS))
+ at = G_TC_AT(skb->tc_verd);
+ if (!(at & AT_EGRESS)) {
if (m->tcfm_ok_push)
skb_push(skb2, skb2->dev->hard_header_len);
+ }
/* mirror is always swallowed */
- if (m->tcfm_eaction != TCA_EGRESS_MIRROR)
+ if (m->tcfm_eaction != TCA_EGRESS_MIRROR &&
+ m->tcfm_eaction != TCA_INGRESS_MIRROR)
skb2->tc_verd = SET_TC_FROM(skb2->tc_verd, at);
skb2->dev = dev;
skb2->iif = skb->dev->ifindex;
dev_queue_xmit(skb2);
+ err = 0;
+
+out:
+ if (err) {
+ m->tcf_qstats.overlimits++;
+ m->tcf_bstats.bytes += qdisc_pkt_len(skb);
+ m->tcf_bstats.packets++;
+ /* should we be asking for packet to be dropped?
+ * may make sense for redirect case only
+ */
+ retval = TC_ACT_SHOT;
+ } else {
+ retval = m->tcf_action;
+ }
spin_unlock(&m->tcf_lock);
- return m->tcf_action;
+
+ return retval;
}
static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
^ permalink raw reply related
* [net-next-2.6 PATCH v6 6/7 RFC] TCPCT part 1f: Initiator Cookie => Responder
From: William Allen Simpson @ 2009-11-13 5:40 UTC (permalink / raw)
To: Linux Kernel Network Developers
In-Reply-To: <4AFCDA9E.8050003@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 783 bytes --]
Calculate and format TCP_COOKIE SYN option.
Create (and destroy) cookie data structures.
This is a significantly revised implementation of an earlier (year-old)
patch that no longer applies cleanly, with permission of the original
author (Adam Langley):
http://thread.gmane.org/gmane.linux.network/102586
Requires:
TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS
TCPCT part 1d: define TCP cookie option, extend existing struct's
Signed-off-by: William.Allen.Simpson@gmail.com
---
net/ipv4/tcp_ipv4.c | 20 +++++
net/ipv4/tcp_minisocks.c | 45 +++++++++--
net/ipv4/tcp_output.c | 182 ++++++++++++++++++++++++++++++++++++++++------
net/ipv6/tcp_ipv6.c | 13 +++
4 files changed, 228 insertions(+), 32 deletions(-)
[-- Attachment #2: TCPCT+1f6.patch --]
[-- Type: text/plain, Size: 13998 bytes --]
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 094231b..2ae1985 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1834,6 +1834,19 @@ static int tcp_v4_init_sock(struct sock *sk)
tp->af_specific = &tcp_sock_ipv4_specific;
#endif
+ /* TCP Cookie Transactions */
+ if (sysctl_tcp_cookie_size > 0) {
+ /* Default, cookies without s_data. */
+ tp->cookie_values =
+ kzalloc(sizeof(*tp->cookie_values),
+ sk->sk_allocation);
+ if (tp->cookie_values != NULL)
+ kref_init(&tp->cookie_values->kref);
+ }
+ /* Presumed zeroed, in order of appearance:
+ * cookie_in_always, cookie_out_never,
+ * s_data_constant, s_data_in, s_data_out
+ */
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
@@ -1887,6 +1900,13 @@ void tcp_v4_destroy_sock(struct sock *sk)
sk->sk_sndmsg_page = NULL;
}
+ /* TCP Cookie Transactions */
+ if (tp->cookie_values != NULL) {
+ kref_put(&tp->cookie_values->kref,
+ tcp_cookie_values_release);
+ tp->cookie_values = NULL;
+ }
+
percpu_counter_dec(&tcp_sockets_allocated);
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7a42990..2b50da8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -389,14 +389,42 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
const struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_request_sock *treq = tcp_rsk(req);
struct inet_connection_sock *newicsk = inet_csk(newsk);
- struct tcp_sock *newtp;
+ struct tcp_sock *newtp = tcp_sk(newsk);
+ struct tcp_sock *oldtp = tcp_sk(sk);
+ struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
+
+ /* TCP Cookie Transactions require space for the cookie pair,
+ * as it differs for each connection. There is no need to
+ * copy any s_data stored at the original socket. Failure
+ * will prevent resuming the connection.
+ *
+ * Presumed copied, in order of appearance:
+ * cookie_in_always, cookie_out_never
+ */
+ if (oldcvp != NULL) {
+ struct tcp_cookie_values *newcvp =
+ kzalloc(sizeof(*newtp->cookie_values),
+ GFP_ATOMIC);
+
+ if (newcvp != NULL) {
+ kref_init(&newcvp->kref);
+ newcvp->cookie_desired =
+ oldcvp->cookie_desired;
+ newtp->cookie_values = newcvp;
+ } else {
+ /* Not Yet Implemented */
+ newtp->cookie_values = NULL;
+ }
+ }
/* Now setup tcp_sock */
- newtp = tcp_sk(newsk);
newtp->pred_flags = 0;
- newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1;
- newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1;
- newtp->snd_up = treq->snt_isn + 1;
+
+ newtp->rcv_wup = newtp->copied_seq =
+ newtp->rcv_nxt = treq->rcv_isn + 1;
+
+ newtp->snd_sml = newtp->snd_una = newtp->snd_nxt =
+ newtp->snd_up = treq->snt_isn + 1 + tcp_s_data_size(oldtp);
tcp_prequeue_init(newtp);
@@ -429,8 +457,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);
skb_queue_head_init(&newtp->out_of_order_queue);
- newtp->write_seq = treq->snt_isn + 1;
- newtp->pushed_seq = newtp->write_seq;
+ newtp->write_seq = newtp->pushed_seq =
+ treq->snt_isn + 1 + tcp_s_data_size(oldtp);
newtp->rx_opt.saw_tstamp = 0;
@@ -596,7 +624,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
* Invalid ACK: reset will be sent by listening socket
*/
if ((flg & TCP_FLAG_ACK) &&
- (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1))
+ (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1 +
+ tcp_s_data_size(tcp_sk(sk))))
return sk;
/* Also, it would be not so bad idea to check rcv_tsecr, which
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e59fa5a..e1553d3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -370,15 +370,45 @@ static inline int tcp_urg_mode(const struct tcp_sock *tp)
#define OPTION_TS (1 << 1)
#define OPTION_MD5 (1 << 2)
#define OPTION_WSCALE (1 << 3)
+#define OPTION_COOKIE_EXTENSION (1 << 4)
struct tcp_out_options {
u8 options; /* bit field of OPTION_* */
u8 ws; /* window scale, 0 to disable */
+ u8 hash_size; /* bytes in hash */
u8 num_sack_blocks; /* number of SACK blocks to include */
u16 mss; /* 0 to disable */
__u32 tsval, tsecr; /* need to include OPTION_TS */
+ __u8 *hash_location; /* temporary pointer, overloaded */
};
+/* The sysctl int routines are generic, so check consistency here.
+ */
+static u8 tcp_cookie_size_check(u8 desired)
+{
+ if (desired > 0) {
+ /* previously specified */
+ return desired;
+ }
+ if (sysctl_tcp_cookie_size <= 0) {
+ /* no default specified */
+ return 0;
+ }
+ if (sysctl_tcp_cookie_size < TCP_COOKIE_MIN) {
+ /* value too small, increase to minimum */
+ return TCP_COOKIE_MIN;
+ }
+ if (sysctl_tcp_cookie_size > TCP_COOKIE_MAX) {
+ /* value too large, decrease to maximum */
+ return TCP_COOKIE_MAX;
+ }
+ if (0x1 & sysctl_tcp_cookie_size) {
+ /* 8-bit multiple, illegal, fix it */
+ return (u8)(sysctl_tcp_cookie_size + 0x1);
+ }
+ return (u8)sysctl_tcp_cookie_size;
+}
+
/* Write previously computed TCP options to the packet.
*
* Beware: Something in the Internet is very sensitive to the ordering of
@@ -393,17 +423,34 @@ struct tcp_out_options {
* (but it may well be that other scenarios fail similarly).
*/
static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
- const struct tcp_out_options *opts,
- __u8 **md5_hash) {
- if (unlikely(OPTION_MD5 & opts->options)) {
- *ptr++ = htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_MD5SIG << 8) |
- TCPOLEN_MD5SIG);
- *md5_hash = (__u8 *)ptr;
+ struct tcp_out_options *opts)
+{
+ u8 options = opts->options; /* mungable copy */
+
+ /* Having both authentication and cookies for security is redundant,
+ * and there's certainly not enough room. Instead, the cookie-less
+ * extension variant is proposed.
+ *
+ * Consider the pessimal case with authentication. The options
+ * could look like:
+ * COOKIE|MD5(20) + MSS(4) + SACK|TS(12) + WSCALE(4) == 40
+ */
+ if (unlikely(OPTION_MD5 & options)) {
+ if (unlikely(OPTION_COOKIE_EXTENSION & options)) {
+ *ptr++ = htonl((TCPOPT_COOKIE << 24) |
+ (TCPOLEN_COOKIE_BASE << 16) |
+ (TCPOPT_MD5SIG << 8) |
+ TCPOLEN_MD5SIG);
+ } else {
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_MD5SIG << 8) |
+ TCPOLEN_MD5SIG);
+ }
+ options &= ~OPTION_COOKIE_EXTENSION;
+ /* overload cookie hash location */
+ opts->hash_location = (__u8 *)ptr;
ptr += 4;
- } else {
- *md5_hash = NULL;
}
if (unlikely(opts->mss)) {
@@ -412,12 +459,13 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
opts->mss);
}
- if (likely(OPTION_TS & opts->options)) {
- if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) {
+ if (likely(OPTION_TS & options)) {
+ if (unlikely(OPTION_SACK_ADVERTISE & options)) {
*ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
(TCPOLEN_SACK_PERM << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
+ options &= ~OPTION_SACK_ADVERTISE;
} else {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
@@ -428,15 +476,52 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
*ptr++ = htonl(opts->tsecr);
}
- if (unlikely(OPTION_SACK_ADVERTISE & opts->options &&
- !(OPTION_TS & opts->options))) {
+ /* Specification requires after timestamp, so do it now.
+ *
+ * Consider the pessimal case without authentication. The options
+ * could look like:
+ * MSS(4) + SACK|TS(12) + COOKIE(20) + WSCALE(4) == 40
+ */
+ if (unlikely(OPTION_COOKIE_EXTENSION & options)) {
+ __u8 *cookie_copy = opts->hash_location;
+ u8 cookie_size = opts->hash_size;
+
+ if (unlikely(0x1 & cookie_size)) {
+ /* 8-bit multiple, illegal, ignore */
+ cookie_size = 0;
+ } else if (likely(0x2 & cookie_size)) {
+ __u8 *p = (__u8 *)ptr;
+
+ /* 16-bit multiple */
+ *p++ = TCPOPT_COOKIE;
+ *p++ = TCPOLEN_COOKIE_BASE + cookie_size;
+ *p++ = *cookie_copy++;
+ *p++ = *cookie_copy++;
+ ptr++;
+ cookie_size -= 2;
+ } else {
+ /* 32-bit multiple */
+ *ptr++ = htonl(((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_COOKIE << 8) |
+ TCPOLEN_COOKIE_BASE) +
+ cookie_size);
+ }
+
+ if (cookie_size > 0) {
+ memcpy(ptr, cookie_copy, cookie_size);
+ ptr += (cookie_size >> 2);
+ }
+ }
+
+ if (unlikely(OPTION_SACK_ADVERTISE & options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_SACK_PERM << 8) |
TCPOLEN_SACK_PERM);
}
- if (unlikely(OPTION_WSCALE & opts->options)) {
+ if (unlikely(OPTION_WSCALE & options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_WINDOW << 16) |
(TCPOLEN_WINDOW << 8) |
@@ -471,8 +556,12 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_out_options *opts,
struct tcp_md5sig_key **md5) {
struct tcp_sock *tp = tcp_sk(sk);
- unsigned size = 0;
+ struct tcp_cookie_values *cvp = tp->cookie_values;
struct dst_entry *dst = __sk_dst_get(sk);
+ unsigned size = 0;
+ u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL)
+ ? tcp_cookie_size_check(cvp->cookie_desired)
+ : 0;
#ifdef CONFIG_TCP_MD5SIG
*md5 = tp->af_specific->md5_lookup(sk, sk);
@@ -517,6 +606,53 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
size += TCPOLEN_SACKPERM_ALIGNED;
}
+ /* Note that timestamps are required by the specification.
+ *
+ * Odd numbers of bytes are prohibited by the specification, ensuring
+ * that the cookie is 16-bit aligned, and the resulting cookie pair is
+ * 32-bit aligned.
+ */
+ if (*md5 == NULL
+ && (OPTION_TS & opts->options)
+ && cookie_size > 0) {
+ int need = TCPOLEN_COOKIE_BASE + cookie_size;
+ int remaining = MAX_TCP_OPTION_SPACE - size;
+
+ if (0x2 & need) {
+ /* 32-bit multiple */
+ need += 2; /* NOPs */
+
+ if (need > remaining) {
+ /* try shrinking cookie to fit */
+ cookie_size -= 2;
+ need -= 4;
+ }
+ }
+ while (need > remaining && TCP_COOKIE_MIN <= cookie_size) {
+ cookie_size -= 4;
+ need -= 4;
+ }
+ if (TCP_COOKIE_MIN <= cookie_size) {
+ opts->options |= OPTION_COOKIE_EXTENSION;
+ opts->hash_location = (__u8 *)&cvp->cookie_pair[0];
+ opts->hash_size = cookie_size;
+
+ /* Remember for future incarnations. */
+ cvp->cookie_desired = cookie_size;
+
+ if (cvp->cookie_desired != cvp->cookie_pair_size) {
+ /* Currently use random bytes as a nonce,
+ * assuming these are completely unpredictable
+ * by hostile users of the same system.
+ */
+ get_random_bytes(&cvp->cookie_pair[0],
+ cookie_size);
+ cvp->cookie_pair_size = cookie_size;
+ }
+
+ size += need;
+ }
+ }
return size;
}
@@ -632,7 +768,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
struct tcp_out_options opts;
unsigned tcp_options_size, tcp_header_size;
struct tcp_md5sig_key *md5;
- __u8 *md5_hash_location;
struct tcphdr *th;
int err;
@@ -703,7 +838,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
}
}
- tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
+ tcp_options_write((__be32 *)(th + 1), tp, &opts);
if (likely((tcb->flags & TCPCB_FLAG_SYN) == 0))
TCP_ECN_send(sk, skb, tcp_header_size);
@@ -711,7 +846,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
/* Calculate the MD5 hash, as we have all we need now */
if (md5) {
sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
- tp->af_specific->calc_md5_hash(md5_hash_location,
+ tp->af_specific->calc_md5_hash(opts.hash_location,
md5, sk, NULL, skb);
}
#endif
@@ -2235,14 +2370,13 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
struct request_values *rvp)
{
+ struct tcp_out_options opts;
struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_sock *tp = tcp_sk(sk);
struct tcphdr *th;
- int tcp_header_size;
- struct tcp_out_options opts;
struct sk_buff *skb;
struct tcp_md5sig_key *md5;
- __u8 *md5_hash_location;
+ int tcp_header_size;
int mss;
skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
@@ -2303,14 +2437,14 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
th->window = htons(min(req->rcv_wnd, 65535U));
- tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
+ tcp_options_write((__be32 *)(th + 1), tp, &opts);
th->doff = (tcp_header_size >> 2);
TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
if (md5) {
- tcp_rsk(req)->af_specific->calc_md5_hash(md5_hash_location,
+ tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location,
md5, NULL, req, skb);
}
#endif
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3e327bc..2b16f9a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1865,6 +1865,19 @@ static int tcp_v6_init_sock(struct sock *sk)
tp->af_specific = &tcp_sock_ipv6_specific;
#endif
+ /* TCP Cookie Transactions */
+ if (sysctl_tcp_cookie_size > 0) {
+ /* Default, cookies without s_data. */
+ tp->cookie_values =
+ kzalloc(sizeof(*tp->cookie_values),
+ sk->sk_allocation);
+ if (tp->cookie_values != NULL)
+ kref_init(&tp->cookie_values->kref);
+ }
+ /* Presumed zeroed, in order of appearance:
+ * cookie_in_always, cookie_out_never,
+ * s_data_constant, s_data_in, s_data_out
+ */
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
--
1.6.3.3
^ permalink raw reply related
* [net-next-2.6 PATCH v6 7/7 RFC] TCPCT part 1g: Responder Cookie => Initiator
From: William Allen Simpson @ 2009-11-13 5:53 UTC (permalink / raw)
To: Linux Kernel Network Developers
In-Reply-To: <4AFCDA9E.8050003@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1264 bytes --]
Calculate and format TCP_COOKIE SYNACK option.
Process optional SYNACK data.
This is a significantly revised implementation of an earlier (year-old)
patch that no longer applies cleanly, with permission of the original
author (Adam Langley):
http://thread.gmane.org/gmane.linux.network/102586
Requires:
TCPCT part 1a: add request_values parameter for sending SYNACK
TCPCT part 1b: generate Responder Cookie
TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS
TCPCT part 1d: define TCP cookie option, extend existing struct's
TCPCT part 1e: implement socket option TCP_COOKIE_TRANSACTIONS
TCPCT part 1f: Initiator Cookie => Responder
Signed-off-by: William.Allen.Simpson@gmail.com
---
include/linux/tcp.h | 11 ++++++
include/net/tcp.h | 1 +
net/ipv4/syncookies.c | 5 ++-
net/ipv4/tcp_input.c | 84 ++++++++++++++++++++++++++++++++++++++++------
net/ipv4/tcp_ipv4.c | 46 +++++++++++++++++++++++--
net/ipv4/tcp_minisocks.c | 14 ++++---
net/ipv4/tcp_output.c | 75 ++++++++++++++++++++++++++++++++++++++--
net/ipv6/syncookies.c | 5 ++-
net/ipv6/tcp_ipv6.c | 51 +++++++++++++++++++++++++++-
9 files changed, 261 insertions(+), 31 deletions(-)
[-- Attachment #2: TCPCT+1g6.patch --]
[-- Type: text/plain, Size: 18598 bytes --]
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 6c5ff66..bbedc80 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -223,6 +223,17 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb)
return (tcp_hdr(skb)->doff - 5) * 4;
}
+static inline unsigned int tcp_header_len_th(const struct tcphdr *th)
+{
+ return th->doff * 4;
+}
+
+/* When doff is bad, this could be negative. */
+static inline int tcp_option_len_th(const struct tcphdr *th)
+{
+ return (int)(th->doff * 4) - sizeof(*th);
+}
+
/* This defines a selective acknowledgement block. */
struct tcp_sack_block_wire {
__be32 start_seq;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3a4c840..14796c4 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -407,6 +407,7 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
extern void tcp_parse_options(struct sk_buff *skb,
struct tcp_options_received *opt_rx,
+ u8 **hvpp,
int estab,
struct dst_entry *dst);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 3146cc4..26399ad 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -253,6 +253,8 @@ EXPORT_SYMBOL(cookie_check_timestamp);
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
struct ip_options *opt)
{
+ struct tcp_options_received tcp_opt;
+ u8 *hash_location;
struct inet_request_sock *ireq;
struct tcp_request_sock *treq;
struct tcp_sock *tp = tcp_sk(sk);
@@ -263,7 +265,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
int mss;
struct rtable *rt;
__u8 rcv_wscale;
- struct tcp_options_received tcp_opt;
if (!sysctl_tcp_syncookies || !th->ack)
goto out;
@@ -341,7 +342,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, 0, &rt->u.dst);
+ tcp_parse_options(skb, &tcp_opt, &hash_location, 0, &rt->u.dst);
if (tcp_opt.saw_tstamp)
cookie_check_timestamp(&tcp_opt);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc306ac..104fe2d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3698,7 +3698,7 @@ old_ack:
* the fast version below fails.
*/
void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
- int estab, struct dst_entry *dst)
+ u8 **hvpp, int estab, struct dst_entry *dst)
{
unsigned char *ptr;
struct tcphdr *th = tcp_hdr(skb);
@@ -3785,6 +3785,19 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
*/
break;
#endif
+ case TCPOPT_COOKIE:
+ /* This option carries 3 different lengths.
+ */
+ if (TCPOLEN_COOKIE_MAX >= opsize
+ && TCPOLEN_COOKIE_MIN <= opsize) {
+ opt_rx->cookie_plus = opsize;
+ *hvpp = ptr;
+ } else if (TCPOLEN_COOKIE_PAIR == opsize) {
+ /* not yet implemented */
+ } else if (TCPOLEN_COOKIE_BASE == opsize) {
+ /* not yet implemented */
+ }
+ break;
}
ptr += opsize-2;
@@ -3813,17 +3826,20 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th)
* If it is wrong it falls back on tcp_parse_options().
*/
static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
- struct tcp_sock *tp)
+ struct tcp_sock *tp, u8 **hvpp)
{
- if (th->doff == sizeof(struct tcphdr) >> 2) {
+ /* In the spirit of fast parsing, compare doff directly to constant
+ * values. Because equality is used, short doff can be ignored here.
+ */
+ if (th->doff == (sizeof(*th) / 4)) {
tp->rx_opt.saw_tstamp = 0;
return 0;
} else if (tp->rx_opt.tstamp_ok &&
- th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) {
+ th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) {
if (tcp_parse_aligned_timestamp(tp, th))
return 1;
}
- tcp_parse_options(skb, &tp->rx_opt, 1, NULL);
+ tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
return 1;
}
@@ -5077,11 +5093,13 @@ out:
static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, int syn_inerr)
{
+ u8 *hash_location;
struct tcp_sock *tp = tcp_sk(sk);
/* RFC1323: H1. Apply PAWS check first. */
- if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp &&
- tcp_paws_discard(sk, skb)) {
+ if (tcp_fast_parse_options(skb, th, tp, &hash_location)
+ && tp->rx_opt.saw_tstamp
+ && tcp_paws_discard(sk, skb)) {
if (!th->rst) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
tcp_send_dupack(sk, skb);
@@ -5368,12 +5386,15 @@ discard:
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, unsigned len)
{
- struct tcp_sock *tp = tcp_sk(sk);
+ u8 *hash_location;
struct inet_connection_sock *icsk = inet_csk(sk);
- int saved_clamp = tp->rx_opt.mss_clamp;
+ struct tcp_sock *tp = tcp_sk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
+ struct tcp_cookie_values *cvp = tp->cookie_values;
+ int saved_clamp = tp->rx_opt.mss_clamp;
+ int queued = 0;
- tcp_parse_options(skb, &tp->rx_opt, 0, dst);
+ tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, dst);
if (th->ack) {
/* rfc793:
@@ -5470,6 +5491,44 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
* Change state from SYN-SENT only after copied_seq
* is initialized. */
tp->copied_seq = tp->rcv_nxt;
+
+ if (cvp != NULL
+ && cvp->cookie_pair_size > 0
+ && tp->rx_opt.cookie_plus > 0) {
+ int cookie_size = tp->rx_opt.cookie_plus
+ - TCPOLEN_COOKIE_BASE;
+ int cookie_pair_size = cookie_size
+ + cvp->cookie_desired;
+
+ /* A cookie extension option was sent and returned.
+ * Note that each incoming SYNACK replaces the
+ * Responder cookie. The initial exchange is most
+ * fragile, as protection against spoofing relies
+ * entirely upon the sequence and timestamp (above).
+ * This replacement strategy allows the correct pair to
+ * pass through, while any others will be filtered via
+ * Responder verification later.
+ */
+ if (sizeof(cvp->cookie_pair) >= cookie_pair_size) {
+ memcpy(&cvp->cookie_pair[cvp->cookie_desired],
+ hash_location, cookie_size);
+ cvp->cookie_pair_size = cookie_pair_size;
+ }
+
+ if (tcp_header_len_th(th) < skb->len) {
+ /* Queue incoming transaction data. */
+ __skb_pull(skb, tcp_header_len_th(th));
+ __skb_queue_tail(&sk->sk_receive_queue, skb);
+ skb_set_owner_r(skb, sk);
+ sk->sk_data_ready(sk, 0);
+ cvp->s_data_in = 1; /* true */
+ queued = 1; /* should be amount? */
+ tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tp->rcv_wup = TCP_SKB_CB(skb)->end_seq;
+ tp->copied_seq = TCP_SKB_CB(skb)->seq + 1;
+ }
+ }
+
smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
@@ -5521,11 +5580,14 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
TCP_DELACK_MAX, TCP_RTO_MAX);
discard:
- __kfree_skb(skb);
+ if (queued == 0)
+ __kfree_skb(skb);
return 0;
} else {
tcp_send_ack(sk);
}
+ if (queued > 0)
+ return 0; /* amount queued? */
return -1;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2ae1985..1597b66 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1213,9 +1213,12 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = {
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
+ u8 *hash_location;
struct request_sock *req;
struct inet_request_sock *ireq;
+ struct tcp_sock *tp = tcp_sk(sk);
struct dst_entry *dst = NULL;
__be32 saddr = ip_hdr(skb)->saddr;
__be32 daddr = ip_hdr(skb)->daddr;
@@ -1271,15 +1274,49 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
- tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss;
+ tmp_opt.user_mss = tp->rx_opt.user_mss;
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst);
+
+ if (tmp_opt.cookie_plus > 0
+ && tmp_opt.saw_tstamp
+ && !tp->rx_opt.cookie_out_never
+ && (sysctl_tcp_cookie_size > 0
+ || (tp->cookie_values != NULL
+ && tp->cookie_values->cookie_desired > 0))) {
+ u8 *c;
+ u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS];
+ int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;
+
+ if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
+ goto drop_and_release;
+
+ /* Secret recipe starts with IP addresses */
+ *mess++ ^= daddr;
+ *mess++ ^= saddr;
- tcp_parse_options(skb, &tmp_opt, 0, dst);
+ /* plus variable length Initiator Cookie */
+ c = (u8 *)mess;
+ while (l-- > 0)
+ *c++ ^= *hash_location++;
+
+#ifdef CONFIG_SYN_COOKIES
+ want_cookie = 0; /* not our kind of cookie */
+#endif
+ tmp_ext.cookie_out_never = 0; /* false */
+ tmp_ext.cookie_plus = tmp_opt.cookie_plus;
+ } else if (!tp->rx_opt.cookie_in_always) {
+ /* redundant indications, but ensure initialization. */
+ tmp_ext.cookie_out_never = 1; /* true */
+ tmp_ext.cookie_plus = 0;
+ } else {
+ goto drop_and_release;
+ }
+ tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
-
tcp_openreq_init(req, &tmp_opt, skb);
if (security_inet_conn_request(sk, skb, req))
@@ -1339,7 +1376,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
}
tcp_rsk(req)->snt_isn = isn;
- if (__tcp_v4_send_synack(sk, dst, req, NULL)
+ if (__tcp_v4_send_synack(sk, dst, req,
+ (struct request_values *)&tmp_ext)
|| want_cookie)
goto drop_and_free;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 2b50da8..7b01ea0 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -96,13 +96,14 @@ enum tcp_tw_status
tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
const struct tcphdr *th)
{
- struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
struct tcp_options_received tmp_opt;
+ u8 *hash_location;
+ struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
int paws_reject = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
tmp_opt.tstamp_ok = 1;
- tcp_parse_options(skb, &tmp_opt, 1, NULL);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
@@ -523,15 +524,16 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct request_sock **prev)
{
+ struct tcp_options_received tmp_opt;
+ u8 *hash_location;
+ struct sock *child;
const struct tcphdr *th = tcp_hdr(skb);
__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
int paws_reject = 0;
- struct tcp_options_received tmp_opt;
- struct sock *child;
- if ((th->doff > (sizeof(struct tcphdr)>>2)) && (req->ts_recent)) {
+ if ((th->doff > (sizeof(*th) >> 2)) && (req->ts_recent)) {
tmp_opt.tstamp_ok = 1;
- tcp_parse_options(skb, &tmp_opt, 1, NULL);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e1553d3..18708d3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -661,9 +661,14 @@ static unsigned tcp_synack_options(struct sock *sk,
struct request_sock *req,
unsigned mss, struct sk_buff *skb,
struct tcp_out_options *opts,
- struct tcp_md5sig_key **md5) {
- unsigned size = 0;
+ struct tcp_md5sig_key **md5,
+ struct tcp_extend_values *xvp)
+{
struct inet_request_sock *ireq = inet_rsk(req);
+ unsigned size = 0;
+ u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never)
+ ? xvp->cookie_plus
+ : 0;
char doing_ts;
#ifdef CONFIG_TCP_MD5SIG
@@ -702,6 +707,28 @@ static unsigned tcp_synack_options(struct sock *sk,
size += TCPOLEN_SACKPERM_ALIGNED;
}
+ /* Similar rationale to tcp_syn_options() applies here, too.
+ * If the <SYN> options fit, the same options should fit now!
+ */
+ if (*md5 == NULL
+ && doing_ts
+ && cookie_plus > TCPOLEN_COOKIE_BASE) {
+ int need = cookie_plus; /* has TCPOLEN_COOKIE_BASE */
+ int remaining = MAX_TCP_OPTION_SPACE - size;
+
+ if (0x2 & need) {
+ /* 32-bit multiple */
+ need += 2; /* NOPs */
+ }
+ if (need <= remaining) {
+ opts->options |= OPTION_COOKIE_EXTENSION;
+ opts->hash_size = cookie_plus - TCPOLEN_COOKIE_BASE;
+ size += need;
+ } else {
+ /* There's no error return, so flag it. */
+ xvp->cookie_out_never = 1; /* true */
+ }
+ }
return size;
}
@@ -2371,6 +2398,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct request_values *rvp)
{
struct tcp_out_options opts;
+ struct tcp_extend_values *xvp = tcp_xv(rvp);
struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_sock *tp = tcp_sk(sk);
struct tcphdr *th;
@@ -2414,8 +2442,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
#endif
TCP_SKB_CB(skb)->when = tcp_time_stamp;
tcp_header_size = tcp_synack_options(sk, req, mss,
- skb, &opts, &md5) +
- sizeof(struct tcphdr);
+ skb, &opts, &md5, xvp)
+ + sizeof(*th);
skb_push(skb, tcp_header_size);
skb_reset_transport_header(skb);
@@ -2432,6 +2460,45 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
*/
tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
TCPCB_FLAG_SYN | TCPCB_FLAG_ACK);
+
+ if (OPTION_COOKIE_EXTENSION & opts.options) {
+ const struct tcp_cookie_values *cvp = tp->cookie_values;
+
+ if (cvp != NULL
+ && cvp->s_data_constant
+ && cvp->s_data_desired > 0) {
+ u8 *buf = skb_put(skb, cvp->s_data_desired);
+
+ /* copy data directly from the listening socket. */
+ memcpy(buf, cvp->s_data_payload, cvp->s_data_desired);
+ TCP_SKB_CB(skb)->end_seq += cvp->s_data_desired;
+ }
+
+ if (opts.hash_size > 0) {
+ __u32 workspace[SHA_WORKSPACE_WORDS];
+ u32 *mess = &xvp->cookie_bakery[COOKIE_DIGEST_WORDS];
+ u32 *tail = &mess[COOKIE_MESSAGE_WORDS-1];
+
+ /* Secret recipe depends on the Timestamp, (future)
+ * Sequence and Acknowledgment Numbers, Initiator
+ * Cookie, and others handled by IP variant caller.
+ */
+ *tail-- ^= opts.tsval;
+ *tail-- ^= tcp_rsk(req)->rcv_isn + 1;
+ *tail-- ^= TCP_SKB_CB(skb)->seq + 1;
+
+ /* recommended */
+ *tail-- ^= ((th->dest << 16) | th->source);
+ *tail-- ^= (u32)cvp; /* per sockopt */
+
+ sha_transform((__u32 *)&xvp->cookie_bakery[0],
+ (char *)mess,
+ &workspace[0]);
+ opts.hash_location =
+ (__u8 *)&xvp->cookie_bakery[0];
+ }
+ }
+
th->seq = htonl(TCP_SKB_CB(skb)->seq);
th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 612fc53..5b9af50 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -159,6 +159,8 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie)
struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_options_received tcp_opt;
+ u8 *hash_location;
struct inet_request_sock *ireq;
struct inet6_request_sock *ireq6;
struct tcp_request_sock *treq;
@@ -171,7 +173,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
int mss;
struct dst_entry *dst;
__u8 rcv_wscale;
- struct tcp_options_received tcp_opt;
if (!sysctl_tcp_syncookies || !th->ack)
goto out;
@@ -254,7 +255,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, 0, dst);
+ tcp_parse_options(skb, &tcp_opt, &hash_location, 0, dst);
if (tcp_opt.saw_tstamp)
cookie_check_timestamp(&tcp_opt);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 2b16f9a..5005ba2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1162,7 +1162,9 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
*/
static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
+ u8 *hash_location;
struct request_sock *req;
struct inet6_request_sock *treq;
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -1206,8 +1208,52 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
tmp_opt.user_mss = tp->rx_opt.user_mss;
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst);
+
+ if (tmp_opt.cookie_plus > 0
+ && tmp_opt.saw_tstamp
+ && !tp->rx_opt.cookie_out_never
+ && (sysctl_tcp_cookie_size > 0
+ || (tp->cookie_values != NULL
+ && tp->cookie_values->cookie_desired > 0))) {
+ u8 *c;
+ u32 *d;
+ u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS];
+ int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;
+
+ if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
+ goto drop_and_free;
+
+ /* Secret recipe starts with IP addresses */
+ d = &ipv6_hdr(skb)->daddr.s6_addr32[0];
+ *mess++ ^= *d++;
+ *mess++ ^= *d++;
+ *mess++ ^= *d++;
+ *mess++ ^= *d++;
+ d = &ipv6_hdr(skb)->saddr.s6_addr32[0];
+ *mess++ ^= *d++;
+ *mess++ ^= *d++;
+ *mess++ ^= *d++;
+ *mess++ ^= *d++;
+
+ /* plus variable length Initiator Cookie */
+ c = (u8 *)mess;
+ while (l-- > 0)
+ *c++ ^= *hash_location++;
- tcp_parse_options(skb, &tmp_opt, 0, dst);
+#ifdef CONFIG_SYN_COOKIES
+ want_cookie = 0; /* not our kind of cookie */
+#endif
+ tmp_ext.cookie_out_never = 0; /* false */
+ tmp_ext.cookie_plus = tmp_opt.cookie_plus;
+ } else if (!tp->rx_opt.cookie_in_always) {
+ /* redundant indications, but ensure initialization. */
+ tmp_ext.cookie_out_never = 1; /* true */
+ tmp_ext.cookie_plus = 0;
+ } else {
+ goto drop_and_free;
+ }
+ tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
@@ -1244,7 +1290,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
security_inet_conn_request(sk, skb, req);
- if (tcp_v6_send_synack(sk, req, NULL)
+ if (tcp_v6_send_synack(sk, req,
+ (struct request_values *)&tmp_ext)
|| want_cookie)
goto drop_and_free;
--
1.6.3.3
^ permalink raw reply related
* Re: [PATCH] ifb: add multi-queue support
From: Eric Dumazet @ 2009-11-13 5:56 UTC (permalink / raw)
To: Changli Gao
Cc: David S. Miller, Stephen Hemminger, Patrick McHardy, Tom Herbert,
netdev
In-Reply-To: <412e6f7f0911121726t47874807g2223d2f1141818f5@mail.gmail.com>
Changli Gao a écrit :
> 2009/11/12 Eric Dumazet <eric.dumazet@gmail.com>:
>> I believe this patch is fine, but maybe Jarek concern about workqueue
>> vs tasklet should be addressed...
>>
>> We could use the previous handling in case numtxqs==1 , ie use a tasklet
>> instead of a work queue ?
>
> I don't think it is a good idea. If we do so, the code will be messy,
> and lost the flexibility of process. In fact, latency isn't a problem
> when system load isn't high, and when system load is high (due to too
> many NIC IRQs), throughput and interaction is more important, and the
> current linux networking subsystem just dose so through the softirqd
> mechanism.
>
Messy ? Because of few tests added in code, and branches always
correctly predicted ?
Still some people might rely on tasklet instead of workqueues
and added scheduler stress and latency penalty. Tasklet are softirq
and normally are processed a few nanosecs later than RX softirq,
on the same CPU, while with your workqueue, I guess the scheduler will
try to not migrate it, so we add a penalty for light to moderate load.
I guess this new ifb mode would be a regression for them ?
If you dont want to maintain a compatibility mode, maybe you
should introduce a complete new driver, drivers/net/ifbmq.c or ifbwq.c
(multiqueue or workqueue references)
^ permalink raw reply
* Re: [net-next-2.6 PATCH] net: fast consecutive name allocation
From: Eric Dumazet @ 2009-11-13 6:12 UTC (permalink / raw)
To: Octavian Purdila; +Cc: netdev
In-Reply-To: <200911130720.19671.opurdila@ixiacom.com>
Octavian Purdila a écrit :
> On Friday 13 November 2009 07:01:14 you wrote:
>> This patch speeds up the network device name allocation for the case
>> where a significant number of devices of the same type are created
>> consecutively.
>>
>> Tests performed on a PPC750 @ 800Mhz machine with per device sysctl
>> and sysfs entries disabled:
>>
>> Without the patch With the patch
>>
>> real 0m 43.43s real 0m 0.49s
>> user 0m 0.00s user 0m 0.00s
>> sys 0m 43.43s sys 0m 0.48s
>>
>
> Oops, pasting root prompts (e.g. # modprobe ....) directly into the git commit message is not a good idea :) Here it is again, with the full commit message.
>
> [net-next-2.6 PATCH] net: fast consecutive name allocation
>
> This patch speeds up the network device name allocation for the case
> where a significant number of devices of the same type are created
> consecutively.
>
> Tests performed on a PPC750 @ 800Mhz machine with per device sysctl
> and sysfs entries disabled:
>
> $ time insmod /lib/modules/dummy.ko numdummies=8000
>
> Without the patch With the patch
>
> real 0m 43.43s real 0m 0.49s
> user 0m 0.00s user 0m 0.00s
> sys 0m 43.43s sys 0m 0.48s
>
> Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
> ---
Honestly I dont like this bloat.
Changing dummy.c is trivial, and you can allocate 100.000.000 dummies if you want now :)
I not tested yet this patch but here it is :
[PATCH] dummy: Allow more than 32768 dummies
And speedup name allocation : O(N) instead of O(N^2)
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
drivers/net/dummy.c | 8 +++++---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 37dcfdc..f600c4c 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -107,12 +107,14 @@ static struct rtnl_link_ops dummy_link_ops __read_mostly = {
module_param(numdummies, int, 0);
MODULE_PARM_DESC(numdummies, "Number of dummy pseudo devices");
-static int __init dummy_init_one(void)
+static int __init dummy_init_one(int i)
{
struct net_device *dev_dummy;
int err;
+ char name[IFNAMSIZ];
- dev_dummy = alloc_netdev(0, "dummy%d", dummy_setup);
+ snprintf(name, IFNAMSIZ, "dummy%d", i);
+ dev_dummy = alloc_netdev(0, name, dummy_setup);
if (!dev_dummy)
return -ENOMEM;
@@ -139,7 +141,7 @@ static int __init dummy_init_module(void)
err = __rtnl_link_register(&dummy_link_ops);
for (i = 0; i < numdummies && !err; i++)
- err = dummy_init_one();
+ err = dummy_init_one(i);
if (err < 0)
__rtnl_link_unregister(&dummy_link_ops);
rtnl_unlock();
^ permalink raw reply related
* Re: [PATCH] ifb: add multi-queue support
From: Changli Gao @ 2009-11-13 6:16 UTC (permalink / raw)
To: Eric Dumazet
Cc: David S. Miller, Stephen Hemminger, Patrick McHardy, Tom Herbert,
netdev
In-Reply-To: <4AFCF50D.6040106@gmail.com>
2009/11/13 Eric Dumazet <eric.dumazet@gmail.com>:
>
> Messy ? Because of few tests added in code, and branches always
> correctly predicted ?
>
> Still some people might rely on tasklet instead of workqueues
> and added scheduler stress and latency penalty. Tasklet are softirq
> and normally are processed a few nanosecs later than RX softirq,
> on the same CPU, while with your workqueue, I guess the scheduler will
> try to not migrate it, so we add a penalty for light to moderate load.
>
> I guess this new ifb mode would be a regression for them ?
>
> If you dont want to maintain a compatibility mode, maybe you
> should introduce a complete new driver, drivers/net/ifbmq.c or ifbwq.c
>
> (multiqueue or workqueue references)
>
It sounds a good idea.
--
Regards，
Changli Gao(xiaosuo@gmail.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