From: Krishna Kumar <krkumar2@in•ibm.com>
To: davem@davemloft•net, arnd@arndb•de
Cc: mst@redhat•com, netdev@vger•kernel.org, xiaosuo@gmail•com,
bhutchings@solarflare•com, Krishna Kumar <krkumar2@in•ibm.com>,
therbert@google•com
Subject: [PATCH v4 1/2] core: Factor out flow calculation from get_rps_cpu
Date: Wed, 04 Aug 2010 16:25:15 +0530 [thread overview]
Message-ID: <20100804105515.22212.41598.sendpatchset@krkumar2.in.ibm.com> (raw)
From: Krishna Kumar <krkumar2@in•ibm.com>
Factor out flow calculation code from get_rps_cpu, since other
functions can use the same code.
Revisions:
v2 - Ben: Separate flow calcuation out and use in select queue.
v3 - Arnd: Don't re-implement MIN.
v4 - Changli: skb->data points to ethernet header in macvtap, and
make a fast path.
Tested macvtap with this patch.
Signed-off-by: Krishna Kumar <krkumar2@in•ibm.com>
---
include/linux/skbuff.h | 11 ++++
net/core/dev.c | 107 ++++++++++++++++++++++-----------------
2 files changed, 74 insertions(+), 44 deletions(-)
diff -ruNp org/include/linux/skbuff.h new/include/linux/skbuff.h
--- org/include/linux/skbuff.h 2010-08-04 09:07:05.000000000 +0530
+++ new/include/linux/skbuff.h 2010-08-04 16:19:30.000000000 +0530
@@ -558,6 +558,17 @@ extern unsigned int skb_find_text(stru
unsigned int to, struct ts_config *config,
struct ts_state *state);
+extern __u32 __skb_get_rxhash(struct sk_buff *skb);
+static inline __u32 skb_get_rxhash(struct sk_buff *skb)
+{
+ __u32 rxhash = skb->rxhash;
+
+ if (!rxhash)
+ rxhash = __skb_get_rxhash(skb);
+
+ return rxhash;
+}
+
#ifdef NET_SKBUFF_DATA_USES_OFFSET
static inline unsigned char *skb_end_pointer(const struct sk_buff *skb)
{
diff -ruNp org/net/core/dev.c new/net/core/dev.c
--- org/net/core/dev.c 2010-08-04 09:07:05.000000000 +0530
+++ new/net/core/dev.c 2010-08-04 16:19:30.000000000 +0530
@@ -2259,69 +2259,41 @@ static inline void ____napi_schedule(str
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
}
-#ifdef CONFIG_RPS
-
-/* One global table that all flow-based protocols share. */
-struct rps_sock_flow_table *rps_sock_flow_table __read_mostly;
-EXPORT_SYMBOL(rps_sock_flow_table);
-
/*
- * 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.
- * rcu_read_lock must be held on entry.
+ * __skb_get_rxhash: calculate a flow hash based on src/dst addresses
+ * and src/dst port numbers. On success, returns a non-zero hash number,
+ * otherwise 0.
*/
-static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
- struct rps_dev_flow **rflowp)
+__u32 __skb_get_rxhash(struct sk_buff *skb)
{
+ int nhoff, hash = 0;
struct ipv6hdr *ip6;
struct iphdr *ip;
- struct netdev_rx_queue *rxqueue;
- struct rps_map *map;
- struct rps_dev_flow_table *flow_table;
- struct rps_sock_flow_table *sock_flow_table;
- int cpu = -1;
u8 ip_proto;
- u16 tcpu;
u32 addr1, addr2, ihl;
union {
u32 v32;
u16 v16[2];
} ports;
- if (skb_rx_queue_recorded(skb)) {
- u16 index = skb_get_rx_queue(skb);
- if (unlikely(index >= dev->num_rx_queues)) {
- WARN_ONCE(dev->num_rx_queues > 1, "%s received packet "
- "on queue %u, but number of RX queues is %u\n",
- dev->name, index, dev->num_rx_queues);
- goto done;
- }
- rxqueue = dev->_rx + index;
- } else
- rxqueue = dev->_rx;
-
- if (!rxqueue->rps_map && !rxqueue->rps_flow_table)
- goto done;
-
- if (skb->rxhash)
- goto got_hash; /* Skip hash computation on packet header */
+ nhoff = skb_network_offset(skb);
switch (skb->protocol) {
case __constant_htons(ETH_P_IP):
- if (!pskb_may_pull(skb, sizeof(*ip)))
+ if (!pskb_may_pull(skb, sizeof(*ip) + nhoff))
goto done;
- ip = (struct iphdr *) skb->data;
+ ip = (struct iphdr *) skb->data + nhoff;
ip_proto = ip->protocol;
addr1 = (__force u32) ip->saddr;
addr2 = (__force u32) ip->daddr;
ihl = ip->ihl;
break;
case __constant_htons(ETH_P_IPV6):
- if (!pskb_may_pull(skb, sizeof(*ip6)))
+ if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff))
goto done;
- ip6 = (struct ipv6hdr *) skb->data;
+ ip6 = (struct ipv6hdr *) skb->data + nhoff;
ip_proto = ip6->nexthdr;
addr1 = (__force u32) ip6->saddr.s6_addr32[3];
addr2 = (__force u32) ip6->daddr.s6_addr32[3];
@@ -2330,6 +2302,7 @@ static int get_rps_cpu(struct net_device
default:
goto done;
}
+
switch (ip_proto) {
case IPPROTO_TCP:
case IPPROTO_UDP:
@@ -2338,8 +2311,9 @@ static int get_rps_cpu(struct net_device
case IPPROTO_AH:
case IPPROTO_SCTP:
case IPPROTO_UDPLITE:
- if (pskb_may_pull(skb, (ihl * 4) + 4)) {
- ports.v32 = * (__force u32 *) (skb->data + (ihl * 4));
+ if (pskb_may_pull(skb, (ihl * 4) + 4 + nhoff)) {
+ ports.v32 = * (__force u32 *) (skb->data + nhoff +
+ (ihl * 4));
if (ports.v16[1] < ports.v16[0])
swap(ports.v16[0], ports.v16[1]);
break;
@@ -2352,11 +2326,56 @@ static int get_rps_cpu(struct net_device
/* get a consistent hash (same value on both flow directions) */
if (addr2 < addr1)
swap(addr1, addr2);
- skb->rxhash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
- if (!skb->rxhash)
- skb->rxhash = 1;
-got_hash:
+ hash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
+ if (!hash)
+ hash = 1;
+
+done:
+ return hash;
+}
+EXPORT_SYMBOL(__skb_get_rxhash);
+
+#ifdef CONFIG_RPS
+
+/* One global table that all flow-based protocols share. */
+struct rps_sock_flow_table *rps_sock_flow_table __read_mostly;
+EXPORT_SYMBOL(rps_sock_flow_table);
+
+/*
+ * 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.
+ * rcu_read_lock must be held on entry.
+ */
+static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
+ struct rps_dev_flow **rflowp)
+{
+ struct netdev_rx_queue *rxqueue;
+ struct rps_map *map;
+ struct rps_dev_flow_table *flow_table;
+ struct rps_sock_flow_table *sock_flow_table;
+ int cpu = -1;
+ u16 tcpu;
+
+ if (skb_rx_queue_recorded(skb)) {
+ u16 index = skb_get_rx_queue(skb);
+ if (unlikely(index >= dev->num_rx_queues)) {
+ WARN_ONCE(dev->num_rx_queues > 1, "%s received packet "
+ "on queue %u, but number of RX queues is %u\n",
+ dev->name, index, dev->num_rx_queues);
+ goto done;
+ }
+ rxqueue = dev->_rx + index;
+ } else
+ rxqueue = dev->_rx;
+
+ if (!rxqueue->rps_map && !rxqueue->rps_flow_table)
+ goto done;
+
+ skb->rxhash = skb_get_rxhash(skb);
+ if (skb->rxhash < 0)
+ goto done;
+
flow_table = rcu_dereference(rxqueue->rps_flow_table);
sock_flow_table = rcu_dereference(rps_sock_flow_table);
if (flow_table && sock_flow_table) {
next reply other threads:[~2010-08-04 10:55 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-08-04 10:55 Krishna Kumar [this message]
2010-08-04 10:55 ` [PATCH v4 2/2] macvtap: Implement multiqueue for macvtap driver Krishna Kumar
2010-08-04 11:37 ` Changli Gao
2010-08-04 13:25 ` Krishna Kumar2
2010-08-04 13:42 ` Changli Gao
2010-08-04 14:54 ` Arnd Bergmann
2010-08-04 11:22 ` [PATCH v4 1/2] core: Factor out flow calculation from get_rps_cpu Changli Gao
2010-08-04 12:02 ` Krishna Kumar2
2010-08-04 13:38 ` Changli Gao
2010-08-04 14:23 ` Krishna Kumar2
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20100804105515.22212.41598.sendpatchset@krkumar2.in.ibm.com \
--to=krkumar2@in$(echo .)ibm.com \
--cc=arnd@arndb$(echo .)de \
--cc=bhutchings@solarflare$(echo .)com \
--cc=davem@davemloft$(echo .)net \
--cc=mst@redhat$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=therbert@google$(echo .)com \
--cc=xiaosuo@gmail$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox