summaryrefslogtreecommitdiff
path: root/net/core/dev.c
diff options
context:
space:
mode:
authorTom Herbert <therbert@google.com>2010-03-16 11:03:29 +0300
committerDavid S. Miller <davem@davemloft.net>2010-03-17 07:23:18 +0300
commit0a9627f2649a02bea165cfd529d7bcb625c2fcad (patch)
treee5d4424b99208c78e2b2fe6ff5a158fc21bdf782 /net/core/dev.c
parent768bbedf9ca4cc4784eae2003f37abe0818fe0b0 (diff)
downloadlinux-0a9627f2649a02bea165cfd529d7bcb625c2fcad.tar.xz
rps: Receive Packet Steering
This patch implements software receive side packet steering (RPS). RPS distributes the load of received packet processing across multiple CPUs. Problem statement: Protocol processing done in the NAPI context for received packets is serialized per device queue and becomes a bottleneck under high packet load. This substantially limits pps that can be achieved on a single queue NIC and provides no scaling with multiple cores. This solution queues packets early on in the receive path on the backlog queues of other CPUs. This allows protocol processing (e.g. IP and TCP) to be performed on packets in parallel. For each device (or each receive queue in a multi-queue device) a mask of CPUs is set to indicate the CPUs that can process packets. A CPU is selected on a per packet basis by hashing contents of the packet header (e.g. the TCP or UDP 4-tuple) and using the result to index into the CPU mask. The IPI mechanism is used to raise networking receive softirqs between CPUs. This effectively emulates in software what a multi-queue NIC can provide, but is generic requiring no device support. Many devices now provide a hash over the 4-tuple on a per packet basis (e.g. the Toeplitz hash). This patch allow drivers to set the HW reported hash in an skb field, and that value in turn is used to index into the RPS maps. Using the HW generated hash can avoid cache misses on the packet when steering it to a remote CPU. The CPU mask is set on a per device and per queue basis in the sysfs variable /sys/class/net/<device>/queues/rx-<n>/rps_cpus. This is a set of canonical bit maps for receive queues in the device (numbered by <n>). If a device does not support multi-queue, a single variable is used for the device (rx-0). Generally, we have found this technique increases pps capabilities of a single queue device with good CPU utilization. Optimal settings for the CPU mask seem to depend on architectures and cache hierarcy. Below are some results running 500 instances of netperf TCP_RR test with 1 byte req. and resp. Results show cumulative transaction rate and system CPU utilization. e1000e on 8 core Intel Without RPS: 108K tps at 33% CPU With RPS: 311K tps at 64% CPU forcedeth on 16 core AMD Without RPS: 156K tps at 15% CPU With RPS: 404K tps at 49% CPU bnx2x on 16 core AMD Without RPS 567K tps at 61% CPU (4 HW RX queues) Without RPS 738K tps at 96% CPU (8 HW RX queues) With RPS: 854K tps at 76% CPU (4 HW RX queues) Caveats: - The benefits of this patch are dependent on architecture and cache hierarchy. Tuning the masks to get best performance is probably necessary. - This patch adds overhead in the path for processing a single packet. In a lightly loaded server this overhead may eliminate the advantages of increased parallelism, and possibly cause some relative performance degradation. We have found that masks that are cache aware (share same caches with the interrupting CPU) mitigate much of this. - The RPS masks can be changed dynamically, however whenever the mask is changed this introduces the possibility of generating out of order packets. It's probably best not change the masks too frequently. Signed-off-by: Tom Herbert <therbert@google.com> include/linux/netdevice.h | 32 ++++- include/linux/skbuff.h | 3 + net/core/dev.c | 335 +++++++++++++++++++++++++++++++++++++-------- net/core/net-sysfs.c | 225 ++++++++++++++++++++++++++++++- net/core/skbuff.c | 2 + 5 files changed, 538 insertions(+), 59 deletions(-) Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core/dev.c')
-rw-r--r--net/core/dev.c335
1 files changed, 279 insertions, 56 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index bcc490cc9452..17b168671501 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1931,7 +1931,7 @@ out_kfree_skb:
return rc;
}
-static u32 skb_tx_hashrnd;
+static u32 hashrnd __read_mostly;
u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
{
@@ -1949,7 +1949,7 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
else
hash = skb->protocol;
- hash = jhash_1word(hash, skb_tx_hashrnd);
+ hash = jhash_1word(hash, hashrnd);
return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
}
@@ -1959,10 +1959,9 @@ static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
{
if (unlikely(queue_index >= dev->real_num_tx_queues)) {
if (net_ratelimit()) {
- WARN(1, "%s selects TX queue %d, but "
+ netdev_warn(dev, "selects TX queue %d, but "
"real number of TX queues is %d\n",
- dev->name, queue_index,
- dev->real_num_tx_queues);
+ queue_index, dev->real_num_tx_queues);
}
return 0;
}
@@ -2175,6 +2174,172 @@ int weight_p __read_mostly = 64; /* old backlog weight */
DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
+/*
+ * get_rps_cpu is called from netif_receive_skb and returns the target
+ * CPU from the RPS map of the receiving queue for a given skb.
+ */
+static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb)
+{
+ struct ipv6hdr *ip6;
+ struct iphdr *ip;
+ struct netdev_rx_queue *rxqueue;
+ struct rps_map *map;
+ int cpu = -1;
+ u8 ip_proto;
+ u32 addr1, addr2, ports, ihl;
+
+ rcu_read_lock();
+
+ if (skb_rx_queue_recorded(skb)) {
+ u16 index = skb_get_rx_queue(skb);
+ if (unlikely(index >= dev->num_rx_queues)) {
+ if (net_ratelimit()) {
+ netdev_warn(dev, "received packet on queue "
+ "%u, but number of RX queues is %u\n",
+ index, dev->num_rx_queues);
+ }
+ goto done;
+ }
+ rxqueue = dev->_rx + index;
+ } else
+ rxqueue = dev->_rx;
+
+ if (!rxqueue->rps_map)
+ goto done;
+
+ if (skb->rxhash)
+ goto got_hash; /* Skip hash computation on packet header */
+
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_IP):
+ if (!pskb_may_pull(skb, sizeof(*ip)))
+ goto done;
+
+ ip = (struct iphdr *) skb->data;
+ ip_proto = ip->protocol;
+ addr1 = ip->saddr;
+ addr2 = ip->daddr;
+ ihl = ip->ihl;
+ break;
+ case __constant_htons(ETH_P_IPV6):
+ if (!pskb_may_pull(skb, sizeof(*ip6)))
+ goto done;
+
+ ip6 = (struct ipv6hdr *) skb->data;
+ ip_proto = ip6->nexthdr;
+ addr1 = ip6->saddr.s6_addr32[3];
+ addr2 = ip6->daddr.s6_addr32[3];
+ ihl = (40 >> 2);
+ break;
+ default:
+ goto done;
+ }
+ ports = 0;
+ 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 (pskb_may_pull(skb, (ihl * 4) + 4))
+ ports = *((u32 *) (skb->data + (ihl * 4)));
+ break;
+
+ default:
+ break;
+ }
+
+ skb->rxhash = jhash_3words(addr1, addr2, ports, hashrnd);
+ if (!skb->rxhash)
+ skb->rxhash = 1;
+
+got_hash:
+ map = rcu_dereference(rxqueue->rps_map);
+ if (map) {
+ u16 tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+
+ if (cpu_online(tcpu)) {
+ cpu = tcpu;
+ goto done;
+ }
+ }
+
+done:
+ rcu_read_unlock();
+ return cpu;
+}
+
+/*
+ * This structure holds the per-CPU mask of CPUs for which IPIs are scheduled
+ * to be sent to kick remote softirq processing. There are two masks since
+ * the sending of IPIs must be done with interrupts enabled. The select field
+ * indicates the current mask that enqueue_backlog uses to schedule IPIs.
+ * select is flipped before net_rps_action is called while still under lock,
+ * net_rps_action then uses the non-selected mask to send the IPIs and clears
+ * it without conflicting with enqueue_backlog operation.
+ */
+struct rps_remote_softirq_cpus {
+ cpumask_t mask[2];
+ int select;
+};
+static DEFINE_PER_CPU(struct rps_remote_softirq_cpus, rps_remote_softirq_cpus);
+
+/* Called from hardirq (IPI) context */
+static void trigger_softirq(void *data)
+{
+ struct softnet_data *queue = data;
+ __napi_schedule(&queue->backlog);
+ __get_cpu_var(netdev_rx_stat).received_rps++;
+}
+
+/*
+ * enqueue_to_backlog is called to queue an skb to a per CPU backlog
+ * queue (may be a remote CPU queue).
+ */
+static int enqueue_to_backlog(struct sk_buff *skb, int cpu)
+{
+ struct softnet_data *queue;
+ unsigned long flags;
+
+ queue = &per_cpu(softnet_data, cpu);
+
+ local_irq_save(flags);
+ __get_cpu_var(netdev_rx_stat).total++;
+
+ spin_lock(&queue->input_pkt_queue.lock);
+ if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
+ if (queue->input_pkt_queue.qlen) {
+enqueue:
+ __skb_queue_tail(&queue->input_pkt_queue, skb);
+ spin_unlock_irqrestore(&queue->input_pkt_queue.lock,
+ flags);
+ return NET_RX_SUCCESS;
+ }
+
+ /* Schedule NAPI for backlog device */
+ if (napi_schedule_prep(&queue->backlog)) {
+ if (cpu != smp_processor_id()) {
+ struct rps_remote_softirq_cpus *rcpus =
+ &__get_cpu_var(rps_remote_softirq_cpus);
+
+ cpu_set(cpu, rcpus->mask[rcpus->select]);
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ } else
+ __napi_schedule(&queue->backlog);
+ }
+ goto enqueue;
+ }
+
+ spin_unlock(&queue->input_pkt_queue.lock);
+
+ __get_cpu_var(netdev_rx_stat).dropped++;
+ local_irq_restore(flags);
+
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
/**
* netif_rx - post buffer to the network code
@@ -2193,8 +2358,7 @@ DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
int netif_rx(struct sk_buff *skb)
{
- struct softnet_data *queue;
- unsigned long flags;
+ int cpu;
/* if netpoll wants it, pretend we never saw it */
if (netpoll_rx(skb))
@@ -2203,31 +2367,11 @@ int netif_rx(struct sk_buff *skb)
if (!skb->tstamp.tv64)
net_timestamp(skb);
- /*
- * The code is rearranged so that the path is the most
- * short when CPU is congested, but is still operating.
- */
- local_irq_save(flags);
- queue = &__get_cpu_var(softnet_data);
-
- __get_cpu_var(netdev_rx_stat).total++;
- if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
- if (queue->input_pkt_queue.qlen) {
-enqueue:
- __skb_queue_tail(&queue->input_pkt_queue, skb);
- local_irq_restore(flags);
- return NET_RX_SUCCESS;
- }
-
- napi_schedule(&queue->backlog);
- goto enqueue;
- }
-
- __get_cpu_var(netdev_rx_stat).dropped++;
- local_irq_restore(flags);
+ cpu = get_rps_cpu(skb->dev, skb);
+ if (cpu < 0)
+ cpu = smp_processor_id();
- kfree_skb(skb);
- return NET_RX_DROP;
+ return enqueue_to_backlog(skb, cpu);
}
EXPORT_SYMBOL(netif_rx);
@@ -2464,22 +2608,7 @@ void netif_nit_deliver(struct sk_buff *skb)
rcu_read_unlock();
}
-/**
- * netif_receive_skb - process receive buffer from network
- * @skb: buffer to process
- *
- * netif_receive_skb() is the main receive data processing function.
- * It always succeeds. The buffer may be dropped during processing
- * for congestion control or by the protocol layers.
- *
- * This function may only be called from softirq context and interrupts
- * should be enabled.
- *
- * Return values (usually ignored):
- * NET_RX_SUCCESS: no congestion
- * NET_RX_DROP: packet was dropped
- */
-int netif_receive_skb(struct sk_buff *skb)
+int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
struct net_device *orig_dev;
@@ -2588,6 +2717,33 @@ out:
rcu_read_unlock();
return ret;
}
+
+/**
+ * netif_receive_skb - process receive buffer from network
+ * @skb: buffer to process
+ *
+ * netif_receive_skb() is the main receive data processing function.
+ * It always succeeds. The buffer may be dropped during processing
+ * for congestion control or by the protocol layers.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ *
+ * Return values (usually ignored):
+ * NET_RX_SUCCESS: no congestion
+ * NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb(struct sk_buff *skb)
+{
+ int cpu;
+
+ cpu = get_rps_cpu(skb->dev, skb);
+
+ if (cpu < 0)
+ return __netif_receive_skb(skb);
+ else
+ return enqueue_to_backlog(skb, cpu);
+}
EXPORT_SYMBOL(netif_receive_skb);
/* Network device is going away, flush any packets still pending */
@@ -2914,16 +3070,16 @@ static int process_backlog(struct napi_struct *napi, int quota)
do {
struct sk_buff *skb;
- local_irq_disable();
+ spin_lock_irq(&queue->input_pkt_queue.lock);
skb = __skb_dequeue(&queue->input_pkt_queue);
if (!skb) {
__napi_complete(napi);
- local_irq_enable();
+ spin_unlock_irq(&queue->input_pkt_queue.lock);
break;
}
- local_irq_enable();
+ spin_unlock_irq(&queue->input_pkt_queue.lock);
- netif_receive_skb(skb);
+ __netif_receive_skb(skb);
} while (++work < quota && jiffies == start_time);
return work;
@@ -3012,6 +3168,22 @@ void netif_napi_del(struct napi_struct *napi)
}
EXPORT_SYMBOL(netif_napi_del);
+/*
+ * net_rps_action sends any pending IPI's for rps. This is only called from
+ * softirq and interrupts must be enabled.
+ */
+static void net_rps_action(cpumask_t *mask)
+{
+ int cpu;
+
+ /* Send pending IPI's to kick RPS processing on remote cpus. */
+ for_each_cpu_mask_nr(cpu, *mask) {
+ struct softnet_data *queue = &per_cpu(softnet_data, cpu);
+ if (cpu_online(cpu))
+ __smp_call_function_single(cpu, &queue->csd, 0);
+ }
+ cpus_clear(*mask);
+}
static void net_rx_action(struct softirq_action *h)
{
@@ -3019,6 +3191,8 @@ static void net_rx_action(struct softirq_action *h)
unsigned long time_limit = jiffies + 2;
int budget = netdev_budget;
void *have;
+ int select;
+ struct rps_remote_softirq_cpus *rcpus;
local_irq_disable();
@@ -3081,8 +3255,14 @@ static void net_rx_action(struct softirq_action *h)
netpoll_poll_unlock(have);
}
out:
+ rcpus = &__get_cpu_var(rps_remote_softirq_cpus);
+ select = rcpus->select;
+ rcpus->select ^= 1;
+
local_irq_enable();
+ net_rps_action(&rcpus->mask[select]);
+
#ifdef CONFIG_NET_DMA
/*
* There may not be any more sk_buffs coming right now, so push
@@ -3327,10 +3507,10 @@ static int softnet_seq_show(struct seq_file *seq, void *v)
{
struct netif_rx_stats *s = v;
- seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+ seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
s->total, s->dropped, s->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- s->cpu_collision);
+ s->cpu_collision, s->received_rps);
return 0;
}
@@ -5067,6 +5247,23 @@ int register_netdevice(struct net_device *dev)
dev->iflink = -1;
+ if (!dev->num_rx_queues) {
+ /*
+ * Allocate a single RX queue if driver never called
+ * alloc_netdev_mq
+ */
+
+ dev->_rx = kzalloc(sizeof(struct netdev_rx_queue), GFP_KERNEL);
+ if (!dev->_rx) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ dev->_rx->first = dev->_rx;
+ atomic_set(&dev->_rx->count, 1);
+ dev->num_rx_queues = 1;
+ }
+
/* Init, if this function is available */
if (dev->netdev_ops->ndo_init) {
ret = dev->netdev_ops->ndo_init(dev);
@@ -5424,9 +5621,11 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
void (*setup)(struct net_device *), unsigned int queue_count)
{
struct netdev_queue *tx;
+ struct netdev_rx_queue *rx;
struct net_device *dev;
size_t alloc_size;
struct net_device *p;
+ int i;
BUG_ON(strlen(name) >= sizeof(dev->name));
@@ -5452,11 +5651,27 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
goto free_p;
}
+ rx = kcalloc(queue_count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
+ if (!rx) {
+ printk(KERN_ERR "alloc_netdev: Unable to allocate "
+ "rx queues.\n");
+ goto free_tx;
+ }
+
+ atomic_set(&rx->count, queue_count);
+
+ /*
+ * Set a pointer to first element in the array which holds the
+ * reference count.
+ */
+ for (i = 0; i < queue_count; i++)
+ rx[i].first = rx;
+
dev = PTR_ALIGN(p, NETDEV_ALIGN);
dev->padded = (char *)dev - (char *)p;
if (dev_addr_init(dev))
- goto free_tx;
+ goto free_rx;
dev_unicast_init(dev);
@@ -5466,6 +5681,9 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
dev->num_tx_queues = queue_count;
dev->real_num_tx_queues = queue_count;
+ dev->_rx = rx;
+ dev->num_rx_queues = queue_count;
+
dev->gso_max_size = GSO_MAX_SIZE;
netdev_init_queues(dev);
@@ -5480,9 +5698,10 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
strcpy(dev->name, name);
return dev;
+free_rx:
+ kfree(rx);
free_tx:
kfree(tx);
-
free_p:
kfree(p);
return NULL;
@@ -5985,6 +6204,10 @@ static int __init net_dev_init(void)
queue->completion_queue = NULL;
INIT_LIST_HEAD(&queue->poll_list);
+ queue->csd.func = trigger_softirq;
+ queue->csd.info = queue;
+ queue->csd.flags = 0;
+
queue->backlog.poll = process_backlog;
queue->backlog.weight = weight_p;
queue->backlog.gro_list = NULL;
@@ -6023,7 +6246,7 @@ subsys_initcall(net_dev_init);
static int __init initialize_hashrnd(void)
{
- get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd));
+ get_random_bytes(&hashrnd, sizeof(hashrnd));
return 0;
}