* [PATCH net-next 0/7] Faster SO_REUSEPORT for TCP
@ 2016-02-04 15:34 Craig Gallek
2016-02-04 15:34 ` [PATCH net-next 1/7] sock: struct proto hash function may error Craig Gallek
2016-02-04 15:34 ` [PATCH net-next 2/7] inet: create IPv6-equivalent inet_hash function Craig Gallek
0 siblings, 2 replies; 5+ messages in thread
From: Craig Gallek @ 2016-02-04 15:34 UTC (permalink / raw
To: netdev, cgallek
From: Craig Gallek <kraig@google.com>
This patch series complements an earlier series (6a5ef90c58da)
which added faster SO_REUSEPORT lookup for UDP sockets by
extending the feature to TCP sockets. It uses the same
array-based data structure which allows for socket selection
after finding the first listening socket that matches an incoming
packet. Prior to this feature, every socket in the reuseport
group needed to be found and examined before a selection could be
made.
With this series the SO_ATTACH_REUSEPORT_CBPF and
SO_ATTACH_REUSEPORT_EBPF socket options now work for TCP sockets
as well. The test at the end of the series includes an example of
how to use these options to select a reuseport socket based on the
cpu core id handling the incoming packet.
There are several refactoring patches that precede the feature
implementation. Only the last two patches in this series
should result in any behavioral changes.
Craig Gallek (7):
sock: struct proto hash function may error
inet: create IPv6-equivalent inet_hash function
tcp: __tcp_hdrlen() helper
inet: refactor inet[6]_lookup functions to take skb
soreuseport: Prep for fast reuseport TCP socket selection
soreuseport: fast reuseport TCP socket selection
soreuseport: BPF selection functional test for TCP
include/linux/tcp.h | 7 +-
include/net/addrconf.h | 2 +
include/net/inet6_hashtables.h | 13 +-
include/net/inet_hashtables.h | 25 ++-
include/net/ping.h | 2 +-
include/net/raw.h | 2 +-
include/net/sock.h | 6 +-
include/net/udp.h | 2 +-
net/core/filter.c | 2 +-
net/core/sock.c | 1 +
net/dccp/ipv6.c | 2 +-
net/ieee802154/socket.c | 9 +-
net/ipv4/af_inet.c | 9 +-
net/ipv4/inet_connection_sock.c | 22 +-
net/ipv4/inet_diag.c | 6 +-
net/ipv4/inet_hashtables.c | 67 +++++-
net/ipv4/ping.c | 4 +-
net/ipv4/raw.c | 4 +-
net/ipv4/tcp_ipv4.c | 10 +-
net/ipv4/udp.c | 4 +-
net/ipv6/af_inet6.c | 6 +-
net/ipv6/inet6_connection_sock.c | 2 +
net/ipv6/inet6_hashtables.c | 34 +++-
net/ipv6/tcp_ipv6.c | 10 +-
net/l2tp/l2tp_ip6.c | 2 +-
net/netfilter/xt_TPROXY.c | 31 ++-
net/netfilter/xt_socket.c | 28 ++-
net/phonet/socket.c | 2 +-
tools/testing/selftests/net/.gitignore | 1 +
tools/testing/selftests/net/Makefile | 2 +-
tools/testing/selftests/net/reuseport_bpf.c | 117 ++++++++++-
tools/testing/selftests/net/reuseport_bpf_cpu.c | 258 ++++++++++++++++++++++++
32 files changed, 609 insertions(+), 83 deletions(-)
create mode 100644 tools/testing/selftests/net/reuseport_bpf_cpu.c
--
2.7.0.rc3.207.g0ac5344
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH net-next 1/7] sock: struct proto hash function may error
2016-02-04 15:34 [PATCH net-next 0/7] Faster SO_REUSEPORT for TCP Craig Gallek
@ 2016-02-04 15:34 ` Craig Gallek
2016-02-04 15:34 ` [PATCH net-next 2/7] inet: create IPv6-equivalent inet_hash function Craig Gallek
1 sibling, 0 replies; 5+ messages in thread
From: Craig Gallek @ 2016-02-04 15:34 UTC (permalink / raw
To: netdev, cgallek
From: Craig Gallek <kraig@google.com>
In order to support fast reuseport lookups in TCP, the hash function
defined in struct proto must be capable of returning an error code.
This patch changes the function signature of all related hash functions
to return an integer and handles or propagates this return value at
all call sites.
Signed-off-by: Craig Gallek <kraig@google.com>
---
include/net/inet_hashtables.h | 2 +-
include/net/ping.h | 2 +-
include/net/raw.h | 2 +-
include/net/sock.h | 6 +++---
include/net/udp.h | 2 +-
net/ieee802154/socket.c | 9 +++++++--
net/ipv4/af_inet.c | 9 ++++++---
net/ipv4/inet_connection_sock.c | 8 +++++---
net/ipv4/inet_hashtables.c | 4 +++-
net/ipv4/ping.c | 4 +++-
net/ipv4/raw.c | 4 +++-
net/ipv6/af_inet6.c | 6 +++++-
net/phonet/socket.c | 2 +-
13 files changed, 40 insertions(+), 20 deletions(-)
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index de2e3ade6102..554440e7f83d 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -208,7 +208,7 @@ void inet_hashinfo_init(struct inet_hashinfo *h);
bool inet_ehash_insert(struct sock *sk, struct sock *osk);
bool inet_ehash_nolisten(struct sock *sk, struct sock *osk);
void __inet_hash(struct sock *sk, struct sock *osk);
-void inet_hash(struct sock *sk);
+int inet_hash(struct sock *sk);
void inet_unhash(struct sock *sk);
struct sock *__inet_lookup_listener(struct net *net,
diff --git a/include/net/ping.h b/include/net/ping.h
index ac80cb45e630..5fd7cc244833 100644
--- a/include/net/ping.h
+++ b/include/net/ping.h
@@ -65,7 +65,7 @@ struct pingfakehdr {
};
int ping_get_port(struct sock *sk, unsigned short ident);
-void ping_hash(struct sock *sk);
+int ping_hash(struct sock *sk);
void ping_unhash(struct sock *sk);
int ping_init_sock(struct sock *sk);
diff --git a/include/net/raw.h b/include/net/raw.h
index 6a40c6562dd2..3e789008394d 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -57,7 +57,7 @@ int raw_seq_open(struct inode *ino, struct file *file,
#endif
-void raw_hash_sk(struct sock *sk);
+int raw_hash_sk(struct sock *sk);
void raw_unhash_sk(struct sock *sk);
struct raw_sock {
diff --git a/include/net/sock.h b/include/net/sock.h
index f5ea148853e2..255d3e03727b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -984,7 +984,7 @@ struct proto {
void (*release_cb)(struct sock *sk);
/* Keeping track of sk's, looking them up, and port selection methods. */
- void (*hash)(struct sock *sk);
+ int (*hash)(struct sock *sk);
void (*unhash)(struct sock *sk);
void (*rehash)(struct sock *sk);
int (*get_port)(struct sock *sk, unsigned short snum);
@@ -1194,10 +1194,10 @@ static inline void sock_prot_inuse_add(struct net *net, struct proto *prot,
/* With per-bucket locks this operation is not-atomic, so that
* this version is not worse.
*/
-static inline void __sk_prot_rehash(struct sock *sk)
+static inline int __sk_prot_rehash(struct sock *sk)
{
sk->sk_prot->unhash(sk);
- sk->sk_prot->hash(sk);
+ return sk->sk_prot->hash(sk);
}
void sk_prot_clear_portaddr_nulls(struct sock *sk, int size);
diff --git a/include/net/udp.h b/include/net/udp.h
index 2842541e28e7..ecaeec1acd50 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -177,7 +177,7 @@ static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
}
/* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
-static inline void udp_lib_hash(struct sock *sk)
+static inline int udp_lib_hash(struct sock *sk)
{
BUG();
}
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index a548be247e15..1b9c528e4818 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -1026,8 +1026,13 @@ static int ieee802154_create(struct net *net, struct socket *sock,
/* Checksums on by default */
sock_set_flag(sk, SOCK_ZAPPED);
- if (sk->sk_prot->hash)
- sk->sk_prot->hash(sk);
+ if (sk->sk_prot->hash) {
+ rc = sk->sk_prot->hash(sk);
+ if (rc) {
+ sk_common_release(sk);
+ goto out;
+ }
+ }
if (sk->sk_prot->init) {
rc = sk->sk_prot->init(sk);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 5c5db6636704..eade66db214e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -370,7 +370,11 @@ lookup_protocol:
*/
inet->inet_sport = htons(inet->inet_num);
/* Add to protocol hash chains. */
- sk->sk_prot->hash(sk);
+ err = sk->sk_prot->hash(sk);
+ if (err) {
+ sk_common_release(sk);
+ goto out;
+ }
}
if (sk->sk_prot->init) {
@@ -1142,8 +1146,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
* Besides that, it does not check for connection
* uniqueness. Wait for troubles.
*/
- __sk_prot_rehash(sk);
- return 0;
+ return __sk_prot_rehash(sk);
}
int inet_sk_rebuild_header(struct sock *sk)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 46b9c887bede..4c457c492b1f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -737,6 +737,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
+ int err = -EADDRINUSE;
reqsk_queue_alloc(&icsk->icsk_accept_queue);
@@ -754,13 +755,14 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
inet->inet_sport = htons(inet->inet_num);
sk_dst_reset(sk);
- sk->sk_prot->hash(sk);
+ err = sk->sk_prot->hash(sk);
- return 0;
+ if (likely(!err))
+ return 0;
}
sk->sk_state = TCP_CLOSE;
- return -EADDRINUSE;
+ return err;
}
EXPORT_SYMBOL_GPL(inet_csk_listen_start);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index ccc5980797fc..b6023b7baae0 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -468,13 +468,15 @@ void __inet_hash(struct sock *sk, struct sock *osk)
}
EXPORT_SYMBOL(__inet_hash);
-void inet_hash(struct sock *sk)
+int inet_hash(struct sock *sk)
{
if (sk->sk_state != TCP_CLOSE) {
local_bh_disable();
__inet_hash(sk, NULL);
local_bh_enable();
}
+
+ return 0;
}
EXPORT_SYMBOL_GPL(inet_hash);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index c117b21b937d..f6f93fc2c61f 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -145,10 +145,12 @@ fail:
}
EXPORT_SYMBOL_GPL(ping_get_port);
-void ping_hash(struct sock *sk)
+int ping_hash(struct sock *sk)
{
pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
BUG(); /* "Please do not press this button again." */
+
+ return 0;
}
void ping_unhash(struct sock *sk)
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bc35f1842512..d6352515d738 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -93,7 +93,7 @@ static struct raw_hashinfo raw_v4_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
};
-void raw_hash_sk(struct sock *sk)
+int raw_hash_sk(struct sock *sk)
{
struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
struct hlist_head *head;
@@ -104,6 +104,8 @@ void raw_hash_sk(struct sock *sk)
sk_add_node(sk, head);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
write_unlock_bh(&h->lock);
+
+ return 0;
}
EXPORT_SYMBOL_GPL(raw_hash_sk);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 9f5137cd604e..b11c37cfd67c 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -235,7 +235,11 @@ lookup_protocol:
* creation time automatically shares.
*/
inet->inet_sport = htons(inet->inet_num);
- sk->sk_prot->hash(sk);
+ err = sk->sk_prot->hash(sk);
+ if (err) {
+ sk_common_release(sk);
+ goto out;
+ }
}
if (sk->sk_prot->init) {
err = sk->sk_prot->init(sk);
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index d575ef4e9aa6..6273d57762bb 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -200,7 +200,7 @@ static int pn_socket_bind(struct socket *sock, struct sockaddr *addr, int len)
pn->resource = spn->spn_resource;
/* Enable RX on the socket */
- sk->sk_prot->hash(sk);
+ err = sk->sk_prot->hash(sk);
out_port:
mutex_unlock(&port_mutex);
out:
--
2.7.0.rc3.207.g0ac5344
^ permalink raw reply related [flat|nested] 5+ messages in thread
* [PATCH net-next 2/7] inet: create IPv6-equivalent inet_hash function
2016-02-04 15:34 [PATCH net-next 0/7] Faster SO_REUSEPORT for TCP Craig Gallek
2016-02-04 15:34 ` [PATCH net-next 1/7] sock: struct proto hash function may error Craig Gallek
@ 2016-02-04 15:34 ` Craig Gallek
1 sibling, 0 replies; 5+ messages in thread
From: Craig Gallek @ 2016-02-04 15:34 UTC (permalink / raw
To: netdev, cgallek
From: Craig Gallek <kraig@google.com>
In order to support fast lookups for TCP sockets with SO_REUSEPORT,
the function that adds sockets to the listening hash set needs
to be able to check receive address equality. Since this equality
check is different for IPv4 and IPv6, we will need two different
socket hashing functions.
This patch adds inet6_hash identical to the existing inet_hash function
and updates the appropriate references. A following patch will
differentiate the two by passing different comparison functions to
__inet_hash.
Signed-off-by: Craig Gallek <kraig@google.com>
---
include/net/inet6_hashtables.h | 2 ++
net/dccp/ipv6.c | 2 +-
net/ipv6/inet6_hashtables.c | 12 ++++++++++++
net/ipv6/tcp_ipv6.c | 2 +-
net/l2tp/l2tp_ip6.c | 2 +-
5 files changed, 17 insertions(+), 3 deletions(-)
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 7ff588ca6817..b3c28a9dfbf1 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -96,6 +96,8 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
const struct in6_addr *saddr, const __be16 sport,
const struct in6_addr *daddr, const __be16 dport,
const int dif);
+
+int inet6_hash(struct sock *sk);
#endif /* IS_ENABLED(CONFIG_IPV6) */
#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif) \
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 9c6d0508e63a..90a8269b28d0 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -993,7 +993,7 @@ static struct proto dccp_v6_prot = {
.sendmsg = dccp_sendmsg,
.recvmsg = dccp_recvmsg,
.backlog_rcv = dccp_v6_do_rcv,
- .hash = inet_hash,
+ .hash = inet6_hash,
.unhash = inet_unhash,
.accept = inet_csk_accept,
.get_port = inet_csk_get_port,
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 21ace5a2bf7c..3521b15b8b85 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -274,3 +274,15 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row,
__inet6_check_established);
}
EXPORT_SYMBOL_GPL(inet6_hash_connect);
+
+int inet6_hash(struct sock *sk)
+{
+ if (sk->sk_state != TCP_CLOSE) {
+ local_bh_disable();
+ __inet_hash(sk, NULL);
+ local_bh_enable();
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(inet6_hash);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 006396e31cb0..d72bcfb326d8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1865,7 +1865,7 @@ struct proto tcpv6_prot = {
.sendpage = tcp_sendpage,
.backlog_rcv = tcp_v6_do_rcv,
.release_cb = tcp_release_cb,
- .hash = inet_hash,
+ .hash = inet6_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index a2c8747d2936..77adffd227e4 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -718,7 +718,7 @@ static struct proto l2tp_ip6_prot = {
.sendmsg = l2tp_ip6_sendmsg,
.recvmsg = l2tp_ip6_recvmsg,
.backlog_rcv = l2tp_ip6_backlog_recv,
- .hash = inet_hash,
+ .hash = inet6_hash,
.unhash = inet_unhash,
.obj_size = sizeof(struct l2tp_ip6_sock),
#ifdef CONFIG_COMPAT
--
2.7.0.rc3.207.g0ac5344
^ permalink raw reply related [flat|nested] 5+ messages in thread
* [PATCH net-next 0/7] Faster SO_REUSEPORT for TCP
@ 2016-02-04 15:35 Craig Gallek
0 siblings, 0 replies; 5+ messages in thread
From: Craig Gallek @ 2016-02-04 15:35 UTC (permalink / raw
To: netdev, David Miller
From: Craig Gallek <kraig@google.com>
This patch series complements an earlier series (6a5ef90c58da)
which added faster SO_REUSEPORT lookup for UDP sockets by
extending the feature to TCP sockets. It uses the same
array-based data structure which allows for socket selection
after finding the first listening socket that matches an incoming
packet. Prior to this feature, every socket in the reuseport
group needed to be found and examined before a selection could be
made.
With this series the SO_ATTACH_REUSEPORT_CBPF and
SO_ATTACH_REUSEPORT_EBPF socket options now work for TCP sockets
as well. The test at the end of the series includes an example of
how to use these options to select a reuseport socket based on the
cpu core id handling the incoming packet.
There are several refactoring patches that precede the feature
implementation. Only the last two patches in this series
should result in any behavioral changes.
Craig Gallek (7):
sock: struct proto hash function may error
inet: create IPv6-equivalent inet_hash function
tcp: __tcp_hdrlen() helper
inet: refactor inet[6]_lookup functions to take skb
soreuseport: Prep for fast reuseport TCP socket selection
soreuseport: fast reuseport TCP socket selection
soreuseport: BPF selection functional test for TCP
include/linux/tcp.h | 7 +-
include/net/addrconf.h | 2 +
include/net/inet6_hashtables.h | 13 +-
include/net/inet_hashtables.h | 25 ++-
include/net/ping.h | 2 +-
include/net/raw.h | 2 +-
include/net/sock.h | 6 +-
include/net/udp.h | 2 +-
net/core/filter.c | 2 +-
net/core/sock.c | 1 +
net/dccp/ipv6.c | 2 +-
net/ieee802154/socket.c | 9 +-
net/ipv4/af_inet.c | 9 +-
net/ipv4/inet_connection_sock.c | 22 +-
net/ipv4/inet_diag.c | 6 +-
net/ipv4/inet_hashtables.c | 67 +++++-
net/ipv4/ping.c | 4 +-
net/ipv4/raw.c | 4 +-
net/ipv4/tcp_ipv4.c | 10 +-
net/ipv4/udp.c | 4 +-
net/ipv6/af_inet6.c | 6 +-
net/ipv6/inet6_connection_sock.c | 2 +
net/ipv6/inet6_hashtables.c | 34 +++-
net/ipv6/tcp_ipv6.c | 10 +-
net/l2tp/l2tp_ip6.c | 2 +-
net/netfilter/xt_TPROXY.c | 31 ++-
net/netfilter/xt_socket.c | 28 ++-
net/phonet/socket.c | 2 +-
tools/testing/selftests/net/.gitignore | 1 +
tools/testing/selftests/net/Makefile | 2 +-
tools/testing/selftests/net/reuseport_bpf.c | 117 ++++++++++-
tools/testing/selftests/net/reuseport_bpf_cpu.c | 258 ++++++++++++++++++++++++
32 files changed, 609 insertions(+), 83 deletions(-)
create mode 100644 tools/testing/selftests/net/reuseport_bpf_cpu.c
--
2.7.0.rc3.207.g0ac5344
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH net-next 0/7] Faster SO_REUSEPORT for TCP
@ 2016-02-09 23:39 Craig Gallek
0 siblings, 0 replies; 5+ messages in thread
From: Craig Gallek @ 2016-02-09 23:39 UTC (permalink / raw
To: netdev, David Miller
From: Craig Gallek <kraig@google.com>
This patch series complements an earlier series (6a5ef90c58da)
which added faster SO_REUSEPORT lookup for UDP sockets by
extending the feature to TCP sockets. It uses the same
array-based data structure which allows for socket selection
after finding the first listening socket that matches an incoming
packet. Prior to this feature, every socket in the reuseport
group needed to be found and examined before a selection could be
made.
With this series the SO_ATTACH_REUSEPORT_CBPF and
SO_ATTACH_REUSEPORT_EBPF socket options now work for TCP sockets
as well. The test at the end of the series includes an example of
how to use these options to select a reuseport socket based on the
cpu core id handling the incoming packet.
There are several refactoring patches that precede the feature
implementation. Only the last two patches in this series
should result in any behavioral changes.
v2:
- In the first patched I missed a couple of hash functions that should now be
returning int instead of void. I missed these the first time through as it
only generated a warning and not an error :\
Craig Gallek (7):
sock: struct proto hash function may error
inet: create IPv6-equivalent inet_hash function
tcp: __tcp_hdrlen() helper
inet: refactor inet[6]_lookup functions to take skb
soreuseport: Prep for fast reuseport TCP socket selection
soreuseport: fast reuseport TCP socket selection
soreuseport: BPF selection functional test for TCP
include/linux/tcp.h | 7 +-
include/net/addrconf.h | 2 +
include/net/inet6_hashtables.h | 13 +-
include/net/inet_hashtables.h | 25 ++-
include/net/phonet/phonet.h | 2 +-
include/net/ping.h | 2 +-
include/net/raw.h | 2 +-
include/net/sock.h | 6 +-
include/net/udp.h | 2 +-
net/core/filter.c | 2 +-
net/core/sock.c | 1 +
net/dccp/ipv4.c | 2 +-
net/dccp/ipv6.c | 4 +-
net/ieee802154/socket.c | 17 +-
net/ipv4/af_inet.c | 9 +-
net/ipv4/inet_connection_sock.c | 22 +-
net/ipv4/inet_diag.c | 6 +-
net/ipv4/inet_hashtables.c | 67 +++++-
net/ipv4/ping.c | 4 +-
net/ipv4/raw.c | 4 +-
net/ipv4/tcp_ipv4.c | 10 +-
net/ipv4/udp.c | 4 +-
net/ipv6/af_inet6.c | 6 +-
net/ipv6/inet6_connection_sock.c | 2 +
net/ipv6/inet6_hashtables.c | 34 +++-
net/ipv6/tcp_ipv6.c | 10 +-
net/l2tp/l2tp_ip6.c | 3 +-
net/netfilter/xt_TPROXY.c | 31 ++-
net/netfilter/xt_socket.c | 28 ++-
net/phonet/socket.c | 6 +-
net/sctp/socket.c | 3 +-
tools/testing/selftests/net/.gitignore | 1 +
tools/testing/selftests/net/Makefile | 2 +-
tools/testing/selftests/net/reuseport_bpf.c | 117 ++++++++++-
tools/testing/selftests/net/reuseport_bpf_cpu.c | 258 ++++++++++++++++++++++++
35 files changed, 624 insertions(+), 90 deletions(-)
create mode 100644 tools/testing/selftests/net/reuseport_bpf_cpu.c
--
2.7.0.rc3.207.g0ac5344
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2016-02-09 23:39 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2016-02-04 15:34 [PATCH net-next 0/7] Faster SO_REUSEPORT for TCP Craig Gallek
2016-02-04 15:34 ` [PATCH net-next 1/7] sock: struct proto hash function may error Craig Gallek
2016-02-04 15:34 ` [PATCH net-next 2/7] inet: create IPv6-equivalent inet_hash function Craig Gallek
-- strict thread matches above, loose matches on Subject: below --
2016-02-04 15:35 [PATCH net-next 0/7] Faster SO_REUSEPORT for TCP Craig Gallek
2016-02-09 23:39 Craig Gallek
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.