* [PATCH 1/4 v4] net: Introduce sk_tx_queue_mapping
2009-10-20 9:46 [PATCH 0/4 v4] net: Implement fast TX queue selection Krishna Kumar
@ 2009-10-20 9:46 ` Krishna Kumar
2009-10-20 9:46 ` [PATCH 2/4 v4] net: IPv6 changes Krishna Kumar
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Krishna Kumar @ 2009-10-20 9:46 UTC (permalink / raw)
To: davem; +Cc: netdev, herbert, Krishna Kumar, dada1
From: Krishna Kumar <krkumar2@in.ibm.com>
Introduce sk_tx_queue_mapping; and functions that set, test and
get this value. Reset sk_tx_queue_mapping to -1 whenever the dst
cache is set/reset, and in socket alloc. Setting txq to -1 and
using valid txq=<0 to n-1> allows the tx path to use the value
of sk_tx_queue_mapping directly instead of subtracting 1 on every
tx.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
include/net/sock.h | 26 ++++++++++++++++++++++++++
net/core/sock.c | 5 ++++-
2 files changed, 30 insertions(+), 1 deletion(-)
diff -ruNp org/include/net/sock.h new/include/net/sock.h
--- org/include/net/sock.h 2009-10-16 18:53:40.000000000 +0530
+++ new/include/net/sock.h 2009-10-16 21:38:44.000000000 +0530
@@ -107,6 +107,7 @@ struct net;
* @skc_node: main hash linkage for various protocol lookup tables
* @skc_nulls_node: main hash linkage for UDP/UDP-Lite protocol
* @skc_refcnt: reference count
+ * @skc_tx_queue_mapping: tx queue number for this connection
* @skc_hash: hash value used with various protocol lookup tables
* @skc_family: network address family
* @skc_state: Connection state
@@ -128,6 +129,7 @@ struct sock_common {
struct hlist_nulls_node skc_nulls_node;
};
atomic_t skc_refcnt;
+ int skc_tx_queue_mapping;
unsigned int skc_hash;
unsigned short skc_family;
@@ -215,6 +217,7 @@ struct sock {
#define sk_node __sk_common.skc_node
#define sk_nulls_node __sk_common.skc_nulls_node
#define sk_refcnt __sk_common.skc_refcnt
+#define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping
#define sk_copy_start __sk_common.skc_hash
#define sk_hash __sk_common.skc_hash
@@ -1094,8 +1097,29 @@ static inline void sock_put(struct sock
extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
const int nested);
+static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
+{
+ sk->sk_tx_queue_mapping = tx_queue;
+}
+
+static inline void sk_tx_queue_clear(struct sock *sk)
+{
+ sk->sk_tx_queue_mapping = -1;
+}
+
+static inline int sk_tx_queue_get(const struct sock *sk)
+{
+ return sk->sk_tx_queue_mapping;
+}
+
+static inline bool sk_tx_queue_recorded(const struct sock *sk)
+{
+ return (sk && sk->sk_tx_queue_mapping >= 0);
+}
+
static inline void sk_set_socket(struct sock *sk, struct socket *sock)
{
+ sk_tx_queue_clear(sk);
sk->sk_socket = sock;
}
@@ -1152,6 +1176,7 @@ __sk_dst_set(struct sock *sk, struct dst
{
struct dst_entry *old_dst;
+ sk_tx_queue_clear(sk);
old_dst = sk->sk_dst_cache;
sk->sk_dst_cache = dst;
dst_release(old_dst);
@@ -1170,6 +1195,7 @@ __sk_dst_reset(struct sock *sk)
{
struct dst_entry *old_dst;
+ sk_tx_queue_clear(sk);
old_dst = sk->sk_dst_cache;
sk->sk_dst_cache = NULL;
dst_release(old_dst);
diff -ruNp org/net/core/sock.c new/net/core/sock.c
--- org/net/core/sock.c 2009-10-16 18:53:40.000000000 +0530
+++ new/net/core/sock.c 2009-10-16 21:29:02.000000000 +0530
@@ -357,6 +357,7 @@ struct dst_entry *__sk_dst_check(struct
struct dst_entry *dst = sk->sk_dst_cache;
if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
+ sk_tx_queue_clear(sk);
sk->sk_dst_cache = NULL;
dst_release(dst);
return NULL;
@@ -953,7 +954,8 @@ static void sock_copy(struct sock *nsk,
void *sptr = nsk->sk_security;
#endif
BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) !=
- sizeof(osk->sk_node) + sizeof(osk->sk_refcnt));
+ sizeof(osk->sk_node) + sizeof(osk->sk_refcnt) +
+ sizeof(osk->sk_tx_queue_mapping));
memcpy(&nsk->sk_copy_start, &osk->sk_copy_start,
osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start));
#ifdef CONFIG_SECURITY_NETWORK
@@ -997,6 +999,7 @@ static struct sock *sk_prot_alloc(struct
if (!try_module_get(prot->owner))
goto out_free_sec;
+ sk_tx_queue_clear(sk);
}
return sk;
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH 2/4 v4] net: IPv6 changes
2009-10-20 9:46 [PATCH 0/4 v4] net: Implement fast TX queue selection Krishna Kumar
2009-10-20 9:46 ` [PATCH 1/4 v4] net: Introduce sk_tx_queue_mapping Krishna Kumar
@ 2009-10-20 9:46 ` Krishna Kumar
2009-10-20 9:46 ` [PATCH 3/4 v4] net: Fix for dst_negative_advice Krishna Kumar
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Krishna Kumar @ 2009-10-20 9:46 UTC (permalink / raw)
To: davem; +Cc: netdev, herbert, Krishna Kumar, dada1
From: Krishna Kumar <krkumar2@in.ibm.com>
IPv6: Reset sk_tx_queue_mapping when dst_cache is reset. Use existing
macro to do the work.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
net/ipv6/inet6_connection_sock.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff -ruNp org/net/ipv6/inet6_connection_sock.c new/net/ipv6/inet6_connection_sock.c
--- org/net/ipv6/inet6_connection_sock.c 2009-10-16 21:29:19.000000000 +0530
+++ new/net/ipv6/inet6_connection_sock.c 2009-10-16 21:31:00.000000000 +0530
@@ -168,8 +168,7 @@ struct dst_entry *__inet6_csk_dst_check(
if (dst) {
struct rt6_info *rt = (struct rt6_info *)dst;
if (rt->rt6i_flow_cache_genid != atomic_read(&flow_cache_genid)) {
- sk->sk_dst_cache = NULL;
- dst_release(dst);
+ __sk_dst_reset(sk);
dst = NULL;
}
}
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH 3/4 v4] net: Fix for dst_negative_advice
2009-10-20 9:46 [PATCH 0/4 v4] net: Implement fast TX queue selection Krishna Kumar
2009-10-20 9:46 ` [PATCH 1/4 v4] net: Introduce sk_tx_queue_mapping Krishna Kumar
2009-10-20 9:46 ` [PATCH 2/4 v4] net: IPv6 changes Krishna Kumar
@ 2009-10-20 9:46 ` Krishna Kumar
2009-10-20 9:50 ` [PATCH 4/4 v4] net: Use sk_tx_queue_mapping for connected sockets Krishna Kumar
2009-10-21 1:59 ` [PATCH 0/4 v4] net: Implement fast TX queue selection David Miller
4 siblings, 0 replies; 6+ messages in thread
From: Krishna Kumar @ 2009-10-20 9:46 UTC (permalink / raw)
To: davem; +Cc: netdev, herbert, Krishna Kumar, dada1
From: Krishna Kumar <krkumar2@in.ibm.com>
dst_negative_advice() should check for changed dst and reset
sk_tx_queue_mapping accordingly. Pass sock to the callers of
dst_negative_advice.
(sk_reset_txq is defined just for use by dst_negative_advice. The
only way I could find to get around this is to move dst_negative_()
from dst.h to dst.c, include sock.h in dst.c, etc)
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
include/net/dst.h | 12 ++++++++++--
net/core/sock.c | 6 ++++++
net/dccp/timer.c | 4 ++--
net/decnet/af_decnet.c | 2 +-
net/ipv4/tcp_timer.c | 4 ++--
5 files changed, 21 insertions(+), 7 deletions(-)
diff -ruNp org/include/net/dst.h new/include/net/dst.h
--- org/include/net/dst.h 2009-10-16 21:30:56.000000000 +0530
+++ new/include/net/dst.h 2009-10-16 21:31:30.000000000 +0530
@@ -222,11 +222,19 @@ static inline void dst_confirm(struct ds
neigh_confirm(dst->neighbour);
}
-static inline void dst_negative_advice(struct dst_entry **dst_p)
+static inline void dst_negative_advice(struct dst_entry **dst_p,
+ struct sock *sk)
{
struct dst_entry * dst = *dst_p;
- if (dst && dst->ops->negative_advice)
+ if (dst && dst->ops->negative_advice) {
*dst_p = dst->ops->negative_advice(dst);
+
+ if (dst != *dst_p) {
+ extern void sk_reset_txq(struct sock *sk);
+
+ sk_reset_txq(sk);
+ }
+ }
}
static inline void dst_link_failure(struct sk_buff *skb)
diff -ruNp org/net/core/sock.c new/net/core/sock.c
--- org/net/core/sock.c 2009-10-16 21:30:56.000000000 +0530
+++ new/net/core/sock.c 2009-10-16 21:32:33.000000000 +0530
@@ -352,6 +352,12 @@ discard_and_relse:
}
EXPORT_SYMBOL(sk_receive_skb);
+void sk_reset_txq(struct sock *sk)
+{
+ sk_tx_queue_clear(sk);
+}
+EXPORT_SYMBOL(sk_reset_txq);
+
struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst = sk->sk_dst_cache;
diff -ruNp org/net/dccp/timer.c new/net/dccp/timer.c
--- org/net/dccp/timer.c 2009-10-16 21:30:56.000000000 +0530
+++ new/net/dccp/timer.c 2009-10-16 21:31:30.000000000 +0530
@@ -38,7 +38,7 @@ static int dccp_write_timeout(struct soc
if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) {
if (icsk->icsk_retransmits != 0)
- dst_negative_advice(&sk->sk_dst_cache);
+ dst_negative_advice(&sk->sk_dst_cache, sk);
retry_until = icsk->icsk_syn_retries ?
: sysctl_dccp_request_retries;
} else {
@@ -63,7 +63,7 @@ static int dccp_write_timeout(struct soc
Golden words :-).
*/
- dst_negative_advice(&sk->sk_dst_cache);
+ dst_negative_advice(&sk->sk_dst_cache, sk);
}
retry_until = sysctl_dccp_retries2;
diff -ruNp org/net/decnet/af_decnet.c new/net/decnet/af_decnet.c
--- org/net/decnet/af_decnet.c 2009-10-16 21:30:56.000000000 +0530
+++ new/net/decnet/af_decnet.c 2009-10-16 21:31:30.000000000 +0530
@@ -1955,7 +1955,7 @@ static int dn_sendmsg(struct kiocb *iocb
}
if ((flags & MSG_TRYHARD) && sk->sk_dst_cache)
- dst_negative_advice(&sk->sk_dst_cache);
+ dst_negative_advice(&sk->sk_dst_cache, sk);
mss = scp->segsize_rem;
fctype = scp->services_rem & NSP_FC_MASK;
diff -ruNp org/net/ipv4/tcp_timer.c new/net/ipv4/tcp_timer.c
--- org/net/ipv4/tcp_timer.c 2009-10-16 21:30:56.000000000 +0530
+++ new/net/ipv4/tcp_timer.c 2009-10-16 21:31:30.000000000 +0530
@@ -141,14 +141,14 @@ static int tcp_write_timeout(struct sock
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
if (icsk->icsk_retransmits)
- dst_negative_advice(&sk->sk_dst_cache);
+ dst_negative_advice(&sk->sk_dst_cache, sk);
retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
} else {
if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
- dst_negative_advice(&sk->sk_dst_cache);
+ dst_negative_advice(&sk->sk_dst_cache, sk);
}
retry_until = sysctl_tcp_retries2;
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH 4/4 v4] net: Use sk_tx_queue_mapping for connected sockets
2009-10-20 9:46 [PATCH 0/4 v4] net: Implement fast TX queue selection Krishna Kumar
` (2 preceding siblings ...)
2009-10-20 9:46 ` [PATCH 3/4 v4] net: Fix for dst_negative_advice Krishna Kumar
@ 2009-10-20 9:50 ` Krishna Kumar
2009-10-21 1:59 ` [PATCH 0/4 v4] net: Implement fast TX queue selection David Miller
4 siblings, 0 replies; 6+ messages in thread
From: Krishna Kumar @ 2009-10-20 9:50 UTC (permalink / raw)
To: davem; +Cc: netdev, herbert, Krishna Kumar, dada1
From: Krishna Kumar <krkumar2@in.ibm.com>
For connected sockets, the first run of dev_pick_tx saves the
calculated txq in sk_tx_queue_mapping. This is not saved if
either the device has a queue select or the socket is not
connected. Next iterations of dev_pick_tx uses the cached value
of sk_tx_queue_mapping.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
net/core/dev.c | 24 ++++++++++++++++++------
1 file changed, 18 insertions(+), 6 deletions(-)
diff -ruNp org/net/core/dev.c new/net/core/dev.c
--- org/net/core/dev.c 2009-10-19 15:43:30.000000000 +0530
+++ new/net/core/dev.c 2009-10-20 12:24:40.000000000 +0530
@@ -1791,13 +1791,25 @@ EXPORT_SYMBOL(skb_tx_hash);
static struct netdev_queue *dev_pick_tx(struct net_device *dev,
struct sk_buff *skb)
{
- const struct net_device_ops *ops = dev->netdev_ops;
- u16 queue_index = 0;
+ u16 queue_index;
+ struct sock *sk = skb->sk;
+
+ if (sk_tx_queue_recorded(sk)) {
+ queue_index = sk_tx_queue_get(sk);
+ } else {
+ const struct net_device_ops *ops = dev->netdev_ops;
- if (ops->ndo_select_queue)
- queue_index = ops->ndo_select_queue(dev, skb);
- else if (dev->real_num_tx_queues > 1)
- queue_index = skb_tx_hash(dev, skb);
+ if (ops->ndo_select_queue) {
+ queue_index = ops->ndo_select_queue(dev, skb);
+ } else {
+ queue_index = 0;
+ if (dev->real_num_tx_queues > 1)
+ queue_index = skb_tx_hash(dev, skb);
+
+ if (sk && sk->sk_dst_cache)
+ sk_tx_queue_set(sk, queue_index);
+ }
+ }
skb_set_queue_mapping(skb, queue_index);
return netdev_get_tx_queue(dev, queue_index);
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH 0/4 v4] net: Implement fast TX queue selection
2009-10-20 9:46 [PATCH 0/4 v4] net: Implement fast TX queue selection Krishna Kumar
` (3 preceding siblings ...)
2009-10-20 9:50 ` [PATCH 4/4 v4] net: Use sk_tx_queue_mapping for connected sockets Krishna Kumar
@ 2009-10-21 1:59 ` David Miller
4 siblings, 0 replies; 6+ messages in thread
From: David Miller @ 2009-10-21 1:59 UTC (permalink / raw)
To: krkumar2; +Cc: netdev, herbert, dada1
I've applied this set to net-next-2.6, will push out to kernel.org
after some build tests, thanks!
^ permalink raw reply [flat|nested] 6+ messages in thread